Merge tag 'batadv-next-for-davem-20161119' of git://git.open-mesh.org/linux-merge
Simon Wunderlich says:
====================
This feature patchset includes the following changes:
- 6 patches adding functionality to detect a WiFi interface under
other virtual interfaces, like VLANs. They introduce a cache for
the detected the WiFi configuration to avoid RTNL locking in
critical sections. Patches have been prepared by Marek Lindner
and Sven Eckelmann
- Enable automatic module loading for genl requests, by Sven Eckelmann
- Fix a potential race condition on interface removal. This is not
happening very often in practice, but requires bigger changes to fix,
so we are sending this to net-next. By Linus Luessing
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/.mailmap b/.mailmap
index 2408e56..02d2614 100644
--- a/.mailmap
+++ b/.mailmap
@@ -127,6 +127,7 @@
Peter Oruba <peter.oruba@amd.com>
Pratyush Anand <pratyush.anand@gmail.com> <pratyush.anand@st.com>
Praveen BP <praveenbp@ti.com>
+Qais Yousef <qsyousef@gmail.com> <qais.yousef@imgtec.com>
Rajesh Shah <rajesh.shah@intel.com>
Ralf Baechle <ralf@linux-mips.org>
Ralf Wildenhues <Ralf.Wildenhues@gmx.de>
diff --git a/CREDITS b/CREDITS
index 513aaa3..8373676 100644
--- a/CREDITS
+++ b/CREDITS
@@ -1864,10 +1864,11 @@
N: Martin Kepplinger
E: martink@posteo.de
-E: martin.kepplinger@theobroma-systems.com
+E: martin.kepplinger@ginzinger.com
W: http://www.martinkepplinger.com
D: mma8452 accelerators iio driver
-D: Kernel cleanups
+D: pegasus_notetaker input driver
+D: Kernel fixes and cleanups
S: Garnisonstraße 26
S: 4020 Linz
S: Austria
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index cb9a6c6..3acc4f1 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -46,7 +46,8 @@
Intel-IOMMU.txt
- basic info on the Intel IOMMU virtualization support.
Makefile
- - some files in Documentation dir are actually sample code to build
+ - This file does nothing. Removing it breaks make htmldocs and
+ make distclean.
ManagementStyle
- how to (attempt to) manage kernel hackers.
RCU/
diff --git a/Documentation/80211/cfg80211.rst b/Documentation/80211/cfg80211.rst
new file mode 100644
index 0000000..b1e149e
--- /dev/null
+++ b/Documentation/80211/cfg80211.rst
@@ -0,0 +1,345 @@
+==================
+cfg80211 subsystem
+==================
+
+Device registration
+===================
+
+.. kernel-doc:: include/net/cfg80211.h
+ :doc: Device registration
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_channel_flags
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_channel
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_rate_flags
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_rate
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_sta_ht_cap
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_supported_band
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_signal_type
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wiphy_params_flags
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wiphy_flags
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wiphy
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wireless_dev
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wiphy_new
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wiphy_register
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wiphy_unregister
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wiphy_free
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wiphy_name
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wiphy_dev
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wiphy_priv
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: priv_to_wiphy
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: set_wiphy_dev
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wdev_priv
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_iface_limit
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_iface_combination
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_check_combinations
+
+Actions and configuration
+=========================
+
+.. kernel-doc:: include/net/cfg80211.h
+ :doc: Actions and configuration
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_ops
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: vif_params
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: key_params
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: survey_info_flags
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: survey_info
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_beacon_data
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_ap_settings
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: station_parameters
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: rate_info_flags
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: rate_info
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: station_info
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: monitor_flags
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: mpath_info_flags
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: mpath_info
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: bss_parameters
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_txq_params
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_crypto_settings
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_auth_request
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_assoc_request
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_deauth_request
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_disassoc_request
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_ibss_params
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_connect_params
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_pmksa
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_rx_mlme_mgmt
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_auth_timeout
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_rx_assoc_resp
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_assoc_timeout
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_tx_mlme_mgmt
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_ibss_joined
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_connect_result
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_connect_bss
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_connect_timeout
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_roamed
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_disconnected
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_ready_on_channel
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_remain_on_channel_expired
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_new_sta
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_rx_mgmt
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_mgmt_tx_status
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_cqm_rssi_notify
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_cqm_pktloss_notify
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_michael_mic_failure
+
+Scanning and BSS list handling
+==============================
+
+.. kernel-doc:: include/net/cfg80211.h
+ :doc: Scanning and BSS list handling
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_ssid
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_scan_request
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_scan_done
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_bss
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_inform_bss
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_inform_bss_frame_data
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_inform_bss_data
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_unlink_bss
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_find_ie
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_bss_get_ie
+
+Utility functions
+=================
+
+.. kernel-doc:: include/net/cfg80211.h
+ :doc: Utility functions
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_channel_to_frequency
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_frequency_to_channel
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_get_channel
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_get_response_rate
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_hdrlen
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_get_hdrlen_from_skb
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_radiotap_iterator
+
+Data path helpers
+=================
+
+.. kernel-doc:: include/net/cfg80211.h
+ :doc: Data path helpers
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_data_to_8023
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_data_from_8023
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: ieee80211_amsdu_to_8023s
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_classify8021d
+
+Regulatory enforcement infrastructure
+=====================================
+
+.. kernel-doc:: include/net/cfg80211.h
+ :doc: Regulatory enforcement infrastructure
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: regulatory_hint
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wiphy_apply_custom_regulatory
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: freq_reg_info
+
+RFkill integration
+==================
+
+.. kernel-doc:: include/net/cfg80211.h
+ :doc: RFkill integration
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wiphy_rfkill_set_hw_state
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wiphy_rfkill_start_polling
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: wiphy_rfkill_stop_polling
+
+Test mode
+=========
+
+.. kernel-doc:: include/net/cfg80211.h
+ :doc: Test mode
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_testmode_alloc_reply_skb
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_testmode_reply
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_testmode_alloc_event_skb
+
+.. kernel-doc:: include/net/cfg80211.h
+ :functions: cfg80211_testmode_event
diff --git a/Documentation/80211/conf.py b/Documentation/80211/conf.py
new file mode 100644
index 0000000..20c7c27
--- /dev/null
+++ b/Documentation/80211/conf.py
@@ -0,0 +1,5 @@
+# -*- coding: utf-8; mode: python -*-
+
+project = "Linux 802.11 Driver Developer's Guide"
+
+tags.add("subproject")
diff --git a/Documentation/80211/index.rst b/Documentation/80211/index.rst
new file mode 100644
index 0000000..90bba47
--- /dev/null
+++ b/Documentation/80211/index.rst
@@ -0,0 +1,17 @@
+=====================================
+Linux 802.11 Driver Developer's Guide
+=====================================
+
+.. toctree::
+
+ introduction
+ cfg80211
+ mac80211
+ mac80211-advanced
+
+.. only:: subproject
+
+ Indices
+ =======
+
+ * :ref:`genindex`
diff --git a/Documentation/80211/introduction.rst b/Documentation/80211/introduction.rst
new file mode 100644
index 0000000..4938fa8
--- /dev/null
+++ b/Documentation/80211/introduction.rst
@@ -0,0 +1,17 @@
+============
+Introduction
+============
+
+Explaining wireless 802.11 networking in the Linux kernel
+
+Copyright 2007-2009 Johannes Berg
+
+These books attempt to give a description of the various subsystems
+that play a role in 802.11 wireless networking in Linux. Since these
+books are for kernel developers they attempts to document the
+structures and functions used in the kernel as well as giving a
+higher-level overview.
+
+The reader is expected to be familiar with the 802.11 standard as
+published by the IEEE in 802.11-2007 (or possibly later versions).
+References to this standard will be given as "802.11-2007 8.1.5".
diff --git a/Documentation/80211/mac80211-advanced.rst b/Documentation/80211/mac80211-advanced.rst
new file mode 100644
index 0000000..70a89b2
--- /dev/null
+++ b/Documentation/80211/mac80211-advanced.rst
@@ -0,0 +1,295 @@
+=============================
+mac80211 subsystem (advanced)
+=============================
+
+Information contained within this part of the book is of interest only
+for advanced interaction of mac80211 with drivers to exploit more
+hardware capabilities and improve performance.
+
+LED support
+===========
+
+Mac80211 supports various ways of blinking LEDs. Wherever possible,
+device LEDs should be exposed as LED class devices and hooked up to the
+appropriate trigger, which will then be triggered appropriately by
+mac80211.
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_get_tx_led_name
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_get_rx_led_name
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_get_assoc_led_name
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_get_radio_led_name
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_tpt_blink
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_tpt_led_trigger_flags
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_create_tpt_led_trigger
+
+Hardware crypto acceleration
+============================
+
+.. kernel-doc:: include/net/mac80211.h
+ :doc: Hardware crypto acceleration
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: set_key_cmd
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_key_conf
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_key_flags
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_get_tkip_p1k
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_get_tkip_p1k_iv
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_get_tkip_p2k
+
+Powersave support
+=================
+
+.. kernel-doc:: include/net/mac80211.h
+ :doc: Powersave support
+
+Beacon filter support
+=====================
+
+.. kernel-doc:: include/net/mac80211.h
+ :doc: Beacon filter support
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_beacon_loss
+
+Multiple queues and QoS support
+===============================
+
+TBD
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_tx_queue_params
+
+Access point mode support
+=========================
+
+TBD
+
+Some parts of the if_conf should be discussed here instead
+
+Insert notes about VLAN interfaces with hw crypto here or in the hw
+crypto chapter.
+
+support for powersaving clients
+-------------------------------
+
+.. kernel-doc:: include/net/mac80211.h
+ :doc: AP support for powersaving clients
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_get_buffered_bc
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_beacon_get
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_sta_eosp
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_frame_release_type
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_sta_ps_transition
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_sta_ps_transition_ni
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_sta_set_buffered
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_sta_block_awake
+
+Supporting multiple virtual interfaces
+======================================
+
+TBD
+
+Note: WDS with identical MAC address should almost always be OK
+
+Insert notes about having multiple virtual interfaces with different MAC
+addresses here, note which configurations are supported by mac80211, add
+notes about supporting hw crypto with it.
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_iterate_active_interfaces
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_iterate_active_interfaces_atomic
+
+Station handling
+================
+
+TODO
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_sta
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: sta_notify_cmd
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_find_sta
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_find_sta_by_ifaddr
+
+Hardware scan offload
+=====================
+
+TBD
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_scan_completed
+
+Aggregation
+===========
+
+TX A-MPDU aggregation
+---------------------
+
+.. kernel-doc:: net/mac80211/agg-tx.c
+ :doc: TX A-MPDU aggregation
+
+.. WARNING: DOCPROC directive not supported: !Cnet/mac80211/agg-tx.c
+
+RX A-MPDU aggregation
+---------------------
+
+.. kernel-doc:: net/mac80211/agg-rx.c
+ :doc: RX A-MPDU aggregation
+
+.. WARNING: DOCPROC directive not supported: !Cnet/mac80211/agg-rx.c
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_ampdu_mlme_action
+
+Spatial Multiplexing Powersave (SMPS)
+=====================================
+
+.. kernel-doc:: include/net/mac80211.h
+ :doc: Spatial multiplexing power save
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_request_smps
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_smps_mode
+
+TBD
+
+This part of the book describes the rate control algorithm interface and
+how it relates to mac80211 and drivers.
+
+Rate Control API
+================
+
+TBD
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_start_tx_ba_session
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_start_tx_ba_cb_irqsafe
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_stop_tx_ba_session
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_stop_tx_ba_cb_irqsafe
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_rate_control_changed
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_tx_rate_control
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: rate_control_send_low
+
+TBD
+
+This part of the book describes mac80211 internals.
+
+Key handling
+============
+
+Key handling basics
+-------------------
+
+.. kernel-doc:: net/mac80211/key.c
+ :doc: Key handling basics
+
+MORE TBD
+--------
+
+TBD
+
+Receive processing
+==================
+
+TBD
+
+Transmit processing
+===================
+
+TBD
+
+Station info handling
+=====================
+
+Programming information
+-----------------------
+
+.. kernel-doc:: net/mac80211/sta_info.h
+ :functions: sta_info
+
+.. kernel-doc:: net/mac80211/sta_info.h
+ :functions: ieee80211_sta_info_flags
+
+STA information lifetime rules
+------------------------------
+
+.. kernel-doc:: net/mac80211/sta_info.c
+ :doc: STA information lifetime rules
+
+Aggregation
+===========
+
+.. kernel-doc:: net/mac80211/sta_info.h
+ :functions: sta_ampdu_mlme
+
+.. kernel-doc:: net/mac80211/sta_info.h
+ :functions: tid_ampdu_tx
+
+.. kernel-doc:: net/mac80211/sta_info.h
+ :functions: tid_ampdu_rx
+
+Synchronisation
+===============
+
+TBD
+
+Locking, lots of RCU
diff --git a/Documentation/80211/mac80211.rst b/Documentation/80211/mac80211.rst
new file mode 100644
index 0000000..85a8335
--- /dev/null
+++ b/Documentation/80211/mac80211.rst
@@ -0,0 +1,216 @@
+===========================
+mac80211 subsystem (basics)
+===========================
+
+You should read and understand the information contained within this
+part of the book while implementing a mac80211 driver. In some chapters,
+advanced usage is noted, those may be skipped if this isn't needed.
+
+This part of the book only covers station and monitor mode
+functionality, additional information required to implement the other
+modes is covered in the second part of the book.
+
+Basic hardware handling
+=======================
+
+TBD
+
+This chapter shall contain information on getting a hw struct allocated
+and registered with mac80211.
+
+Since it is required to allocate rates/modes before registering a hw
+struct, this chapter shall also contain information on setting up the
+rate/mode structs.
+
+Additionally, some discussion about the callbacks and the general
+programming model should be in here, including the definition of
+ieee80211_ops which will be referred to a lot.
+
+Finally, a discussion of hardware capabilities should be done with
+references to other parts of the book.
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_hw
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_hw_flags
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: SET_IEEE80211_DEV
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: SET_IEEE80211_PERM_ADDR
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_ops
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_alloc_hw
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_register_hw
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_unregister_hw
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_free_hw
+
+PHY configuration
+=================
+
+TBD
+
+This chapter should describe PHY handling including start/stop callbacks
+and the various structures used.
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_conf
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_conf_flags
+
+Virtual interfaces
+==================
+
+TBD
+
+This chapter should describe virtual interface basics that are relevant
+to the driver (VLANs, MGMT etc are not.) It should explain the use of
+the add_iface/remove_iface callbacks as well as the interface
+configuration callbacks.
+
+Things related to AP mode should be discussed there.
+
+Things related to supporting multiple interfaces should be in the
+appropriate chapter, a BIG FAT note should be here about this though and
+the recommendation to allow only a single interface in STA mode at
+first!
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_vif
+
+Receive and transmit processing
+===============================
+
+what should be here
+-------------------
+
+TBD
+
+This should describe the receive and transmit paths in mac80211/the
+drivers as well as transmit status handling.
+
+Frame format
+------------
+
+.. kernel-doc:: include/net/mac80211.h
+ :doc: Frame format
+
+Packet alignment
+----------------
+
+.. kernel-doc:: net/mac80211/rx.c
+ :doc: Packet alignment
+
+Calling into mac80211 from interrupts
+-------------------------------------
+
+.. kernel-doc:: include/net/mac80211.h
+ :doc: Calling mac80211 from interrupts
+
+functions/definitions
+---------------------
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_rx_status
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: mac80211_rx_flags
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: mac80211_tx_info_flags
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: mac80211_tx_control_flags
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: mac80211_rate_control_flags
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_tx_rate
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_tx_info
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_tx_info_clear_status
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_rx
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_rx_ni
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_rx_irqsafe
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_tx_status
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_tx_status_ni
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_tx_status_irqsafe
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_rts_get
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_rts_duration
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_ctstoself_get
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_ctstoself_duration
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_generic_frame_duration
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_wake_queue
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_stop_queue
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_wake_queues
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_stop_queues
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_queue_stopped
+
+Frame filtering
+===============
+
+.. kernel-doc:: include/net/mac80211.h
+ :doc: Frame filtering
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_filter_flags
+
+The mac80211 workqueue
+======================
+
+.. kernel-doc:: include/net/mac80211.h
+ :doc: mac80211 workqueue
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_queue_work
+
+.. kernel-doc:: include/net/mac80211.h
+ :functions: ieee80211_queue_delayed_work
diff --git a/Documentation/ABI/testing/sysfs-class-cxl b/Documentation/ABI/testing/sysfs-class-cxl
index 4ba0a2a..640f65e 100644
--- a/Documentation/ABI/testing/sysfs-class-cxl
+++ b/Documentation/ABI/testing/sysfs-class-cxl
@@ -220,8 +220,11 @@
Date: October 2014
Contact: linuxppc-dev@lists.ozlabs.org
Description: write only
- Writing 1 will issue a PERST to card which may cause the card
- to reload the FPGA depending on load_image_on_perst.
+ Writing 1 will issue a PERST to card provided there are no
+ contexts active on any one of the card AFUs. This may cause
+ the card to reload the FPGA depending on load_image_on_perst.
+ Writing -1 will do a force PERST irrespective of any active
+ contexts on the card AFUs.
Users: https://github.com/ibm-capi/libcxl
What: /sys/class/cxl/<card>/perst_reloads_same_image (not in a guest)
diff --git a/Documentation/ABI/testing/sysfs-devices-system-ibm-rtl b/Documentation/ABI/testing/sysfs-devices-system-ibm-rtl
index b82deea..470def0 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-ibm-rtl
+++ b/Documentation/ABI/testing/sysfs-devices-system-ibm-rtl
@@ -1,4 +1,4 @@
-What: state
+What: /sys/devices/system/ibm_rtl/state
Date: Sep 2010
KernelVersion: 2.6.37
Contact: Vernon Mauery <vernux@us.ibm.com>
@@ -10,7 +10,7 @@
Users: The ibm-prtm userspace daemon uses this interface.
-What: version
+What: /sys/devices/system/ibm_rtl/version
Date: Sep 2010
KernelVersion: 2.6.37
Contact: Vernon Mauery <vernux@us.ibm.com>
diff --git a/Documentation/DocBook/80211.tmpl b/Documentation/DocBook/80211.tmpl
deleted file mode 100644
index 800fe7a..0000000
--- a/Documentation/DocBook/80211.tmpl
+++ /dev/null
@@ -1,584 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE set PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
- "http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
-<set>
- <setinfo>
- <title>The 802.11 subsystems – for kernel developers</title>
- <subtitle>
- Explaining wireless 802.11 networking in the Linux kernel
- </subtitle>
-
- <copyright>
- <year>2007-2009</year>
- <holder>Johannes Berg</holder>
- </copyright>
-
- <authorgroup>
- <author>
- <firstname>Johannes</firstname>
- <surname>Berg</surname>
- <affiliation>
- <address><email>johannes@sipsolutions.net</email></address>
- </affiliation>
- </author>
- </authorgroup>
-
- <legalnotice>
- <para>
- This documentation is free software; you can redistribute
- it and/or modify it under the terms of the GNU General Public
- License version 2 as published by the Free Software Foundation.
- </para>
- <para>
- This documentation is distributed in the hope that it will be
- useful, but WITHOUT ANY WARRANTY; without even the implied
- warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the GNU General Public License for more details.
- </para>
- <para>
- You should have received a copy of the GNU General Public
- License along with this documentation; if not, write to the Free
- Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
- MA 02111-1307 USA
- </para>
- <para>
- For more details see the file COPYING in the source
- distribution of Linux.
- </para>
- </legalnotice>
-
- <abstract>
- <para>
- These books attempt to give a description of the
- various subsystems that play a role in 802.11 wireless
- networking in Linux. Since these books are for kernel
- developers they attempts to document the structures
- and functions used in the kernel as well as giving a
- higher-level overview.
- </para>
- <para>
- The reader is expected to be familiar with the 802.11
- standard as published by the IEEE in 802.11-2007 (or
- possibly later versions). References to this standard
- will be given as "802.11-2007 8.1.5".
- </para>
- </abstract>
- </setinfo>
- <book id="cfg80211-developers-guide">
- <bookinfo>
- <title>The cfg80211 subsystem</title>
-
- <abstract>
-!Pinclude/net/cfg80211.h Introduction
- </abstract>
- </bookinfo>
- <chapter>
- <title>Device registration</title>
-!Pinclude/net/cfg80211.h Device registration
-!Finclude/net/cfg80211.h ieee80211_channel_flags
-!Finclude/net/cfg80211.h ieee80211_channel
-!Finclude/net/cfg80211.h ieee80211_rate_flags
-!Finclude/net/cfg80211.h ieee80211_rate
-!Finclude/net/cfg80211.h ieee80211_sta_ht_cap
-!Finclude/net/cfg80211.h ieee80211_supported_band
-!Finclude/net/cfg80211.h cfg80211_signal_type
-!Finclude/net/cfg80211.h wiphy_params_flags
-!Finclude/net/cfg80211.h wiphy_flags
-!Finclude/net/cfg80211.h wiphy
-!Finclude/net/cfg80211.h wireless_dev
-!Finclude/net/cfg80211.h wiphy_new
-!Finclude/net/cfg80211.h wiphy_register
-!Finclude/net/cfg80211.h wiphy_unregister
-!Finclude/net/cfg80211.h wiphy_free
-
-!Finclude/net/cfg80211.h wiphy_name
-!Finclude/net/cfg80211.h wiphy_dev
-!Finclude/net/cfg80211.h wiphy_priv
-!Finclude/net/cfg80211.h priv_to_wiphy
-!Finclude/net/cfg80211.h set_wiphy_dev
-!Finclude/net/cfg80211.h wdev_priv
-!Finclude/net/cfg80211.h ieee80211_iface_limit
-!Finclude/net/cfg80211.h ieee80211_iface_combination
-!Finclude/net/cfg80211.h cfg80211_check_combinations
- </chapter>
- <chapter>
- <title>Actions and configuration</title>
-!Pinclude/net/cfg80211.h Actions and configuration
-!Finclude/net/cfg80211.h cfg80211_ops
-!Finclude/net/cfg80211.h vif_params
-!Finclude/net/cfg80211.h key_params
-!Finclude/net/cfg80211.h survey_info_flags
-!Finclude/net/cfg80211.h survey_info
-!Finclude/net/cfg80211.h cfg80211_beacon_data
-!Finclude/net/cfg80211.h cfg80211_ap_settings
-!Finclude/net/cfg80211.h station_parameters
-!Finclude/net/cfg80211.h rate_info_flags
-!Finclude/net/cfg80211.h rate_info
-!Finclude/net/cfg80211.h station_info
-!Finclude/net/cfg80211.h monitor_flags
-!Finclude/net/cfg80211.h mpath_info_flags
-!Finclude/net/cfg80211.h mpath_info
-!Finclude/net/cfg80211.h bss_parameters
-!Finclude/net/cfg80211.h ieee80211_txq_params
-!Finclude/net/cfg80211.h cfg80211_crypto_settings
-!Finclude/net/cfg80211.h cfg80211_auth_request
-!Finclude/net/cfg80211.h cfg80211_assoc_request
-!Finclude/net/cfg80211.h cfg80211_deauth_request
-!Finclude/net/cfg80211.h cfg80211_disassoc_request
-!Finclude/net/cfg80211.h cfg80211_ibss_params
-!Finclude/net/cfg80211.h cfg80211_connect_params
-!Finclude/net/cfg80211.h cfg80211_pmksa
-!Finclude/net/cfg80211.h cfg80211_rx_mlme_mgmt
-!Finclude/net/cfg80211.h cfg80211_auth_timeout
-!Finclude/net/cfg80211.h cfg80211_rx_assoc_resp
-!Finclude/net/cfg80211.h cfg80211_assoc_timeout
-!Finclude/net/cfg80211.h cfg80211_tx_mlme_mgmt
-!Finclude/net/cfg80211.h cfg80211_ibss_joined
-!Finclude/net/cfg80211.h cfg80211_connect_result
-!Finclude/net/cfg80211.h cfg80211_connect_bss
-!Finclude/net/cfg80211.h cfg80211_connect_timeout
-!Finclude/net/cfg80211.h cfg80211_roamed
-!Finclude/net/cfg80211.h cfg80211_disconnected
-!Finclude/net/cfg80211.h cfg80211_ready_on_channel
-!Finclude/net/cfg80211.h cfg80211_remain_on_channel_expired
-!Finclude/net/cfg80211.h cfg80211_new_sta
-!Finclude/net/cfg80211.h cfg80211_rx_mgmt
-!Finclude/net/cfg80211.h cfg80211_mgmt_tx_status
-!Finclude/net/cfg80211.h cfg80211_cqm_rssi_notify
-!Finclude/net/cfg80211.h cfg80211_cqm_pktloss_notify
-!Finclude/net/cfg80211.h cfg80211_michael_mic_failure
- </chapter>
- <chapter>
- <title>Scanning and BSS list handling</title>
-!Pinclude/net/cfg80211.h Scanning and BSS list handling
-!Finclude/net/cfg80211.h cfg80211_ssid
-!Finclude/net/cfg80211.h cfg80211_scan_request
-!Finclude/net/cfg80211.h cfg80211_scan_done
-!Finclude/net/cfg80211.h cfg80211_bss
-!Finclude/net/cfg80211.h cfg80211_inform_bss
-!Finclude/net/cfg80211.h cfg80211_inform_bss_frame_data
-!Finclude/net/cfg80211.h cfg80211_inform_bss_data
-!Finclude/net/cfg80211.h cfg80211_unlink_bss
-!Finclude/net/cfg80211.h cfg80211_find_ie
-!Finclude/net/cfg80211.h ieee80211_bss_get_ie
- </chapter>
- <chapter>
- <title>Utility functions</title>
-!Pinclude/net/cfg80211.h Utility functions
-!Finclude/net/cfg80211.h ieee80211_channel_to_frequency
-!Finclude/net/cfg80211.h ieee80211_frequency_to_channel
-!Finclude/net/cfg80211.h ieee80211_get_channel
-!Finclude/net/cfg80211.h ieee80211_get_response_rate
-!Finclude/net/cfg80211.h ieee80211_hdrlen
-!Finclude/net/cfg80211.h ieee80211_get_hdrlen_from_skb
-!Finclude/net/cfg80211.h ieee80211_radiotap_iterator
- </chapter>
- <chapter>
- <title>Data path helpers</title>
-!Pinclude/net/cfg80211.h Data path helpers
-!Finclude/net/cfg80211.h ieee80211_data_to_8023
-!Finclude/net/cfg80211.h ieee80211_data_from_8023
-!Finclude/net/cfg80211.h ieee80211_amsdu_to_8023s
-!Finclude/net/cfg80211.h cfg80211_classify8021d
- </chapter>
- <chapter>
- <title>Regulatory enforcement infrastructure</title>
-!Pinclude/net/cfg80211.h Regulatory enforcement infrastructure
-!Finclude/net/cfg80211.h regulatory_hint
-!Finclude/net/cfg80211.h wiphy_apply_custom_regulatory
-!Finclude/net/cfg80211.h freq_reg_info
- </chapter>
- <chapter>
- <title>RFkill integration</title>
-!Pinclude/net/cfg80211.h RFkill integration
-!Finclude/net/cfg80211.h wiphy_rfkill_set_hw_state
-!Finclude/net/cfg80211.h wiphy_rfkill_start_polling
-!Finclude/net/cfg80211.h wiphy_rfkill_stop_polling
- </chapter>
- <chapter>
- <title>Test mode</title>
-!Pinclude/net/cfg80211.h Test mode
-!Finclude/net/cfg80211.h cfg80211_testmode_alloc_reply_skb
-!Finclude/net/cfg80211.h cfg80211_testmode_reply
-!Finclude/net/cfg80211.h cfg80211_testmode_alloc_event_skb
-!Finclude/net/cfg80211.h cfg80211_testmode_event
- </chapter>
- </book>
- <book id="mac80211-developers-guide">
- <bookinfo>
- <title>The mac80211 subsystem</title>
- <abstract>
-!Pinclude/net/mac80211.h Introduction
-!Pinclude/net/mac80211.h Warning
- </abstract>
- </bookinfo>
-
- <toc></toc>
-
- <!--
- Generally, this document shall be ordered by increasing complexity.
- It is important to note that readers should be able to read only
- the first few sections to get a working driver and only advanced
- usage should require reading the full document.
- -->
-
- <part>
- <title>The basic mac80211 driver interface</title>
- <partintro>
- <para>
- You should read and understand the information contained
- within this part of the book while implementing a driver.
- In some chapters, advanced usage is noted, that may be
- skipped at first.
- </para>
- <para>
- This part of the book only covers station and monitor mode
- functionality, additional information required to implement
- the other modes is covered in the second part of the book.
- </para>
- </partintro>
-
- <chapter id="basics">
- <title>Basic hardware handling</title>
- <para>TBD</para>
- <para>
- This chapter shall contain information on getting a hw
- struct allocated and registered with mac80211.
- </para>
- <para>
- Since it is required to allocate rates/modes before registering
- a hw struct, this chapter shall also contain information on setting
- up the rate/mode structs.
- </para>
- <para>
- Additionally, some discussion about the callbacks and
- the general programming model should be in here, including
- the definition of ieee80211_ops which will be referred to
- a lot.
- </para>
- <para>
- Finally, a discussion of hardware capabilities should be done
- with references to other parts of the book.
- </para>
- <!-- intentionally multiple !F lines to get proper order -->
-!Finclude/net/mac80211.h ieee80211_hw
-!Finclude/net/mac80211.h ieee80211_hw_flags
-!Finclude/net/mac80211.h SET_IEEE80211_DEV
-!Finclude/net/mac80211.h SET_IEEE80211_PERM_ADDR
-!Finclude/net/mac80211.h ieee80211_ops
-!Finclude/net/mac80211.h ieee80211_alloc_hw
-!Finclude/net/mac80211.h ieee80211_register_hw
-!Finclude/net/mac80211.h ieee80211_unregister_hw
-!Finclude/net/mac80211.h ieee80211_free_hw
- </chapter>
-
- <chapter id="phy-handling">
- <title>PHY configuration</title>
- <para>TBD</para>
- <para>
- This chapter should describe PHY handling including
- start/stop callbacks and the various structures used.
- </para>
-!Finclude/net/mac80211.h ieee80211_conf
-!Finclude/net/mac80211.h ieee80211_conf_flags
- </chapter>
-
- <chapter id="iface-handling">
- <title>Virtual interfaces</title>
- <para>TBD</para>
- <para>
- This chapter should describe virtual interface basics
- that are relevant to the driver (VLANs, MGMT etc are not.)
- It should explain the use of the add_iface/remove_iface
- callbacks as well as the interface configuration callbacks.
- </para>
- <para>Things related to AP mode should be discussed there.</para>
- <para>
- Things related to supporting multiple interfaces should be
- in the appropriate chapter, a BIG FAT note should be here about
- this though and the recommendation to allow only a single
- interface in STA mode at first!
- </para>
-!Finclude/net/mac80211.h ieee80211_vif
- </chapter>
-
- <chapter id="rx-tx">
- <title>Receive and transmit processing</title>
- <sect1>
- <title>what should be here</title>
- <para>TBD</para>
- <para>
- This should describe the receive and transmit
- paths in mac80211/the drivers as well as
- transmit status handling.
- </para>
- </sect1>
- <sect1>
- <title>Frame format</title>
-!Pinclude/net/mac80211.h Frame format
- </sect1>
- <sect1>
- <title>Packet alignment</title>
-!Pnet/mac80211/rx.c Packet alignment
- </sect1>
- <sect1>
- <title>Calling into mac80211 from interrupts</title>
-!Pinclude/net/mac80211.h Calling mac80211 from interrupts
- </sect1>
- <sect1>
- <title>functions/definitions</title>
-!Finclude/net/mac80211.h ieee80211_rx_status
-!Finclude/net/mac80211.h mac80211_rx_flags
-!Finclude/net/mac80211.h mac80211_tx_info_flags
-!Finclude/net/mac80211.h mac80211_tx_control_flags
-!Finclude/net/mac80211.h mac80211_rate_control_flags
-!Finclude/net/mac80211.h ieee80211_tx_rate
-!Finclude/net/mac80211.h ieee80211_tx_info
-!Finclude/net/mac80211.h ieee80211_tx_info_clear_status
-!Finclude/net/mac80211.h ieee80211_rx
-!Finclude/net/mac80211.h ieee80211_rx_ni
-!Finclude/net/mac80211.h ieee80211_rx_irqsafe
-!Finclude/net/mac80211.h ieee80211_tx_status
-!Finclude/net/mac80211.h ieee80211_tx_status_ni
-!Finclude/net/mac80211.h ieee80211_tx_status_irqsafe
-!Finclude/net/mac80211.h ieee80211_rts_get
-!Finclude/net/mac80211.h ieee80211_rts_duration
-!Finclude/net/mac80211.h ieee80211_ctstoself_get
-!Finclude/net/mac80211.h ieee80211_ctstoself_duration
-!Finclude/net/mac80211.h ieee80211_generic_frame_duration
-!Finclude/net/mac80211.h ieee80211_wake_queue
-!Finclude/net/mac80211.h ieee80211_stop_queue
-!Finclude/net/mac80211.h ieee80211_wake_queues
-!Finclude/net/mac80211.h ieee80211_stop_queues
-!Finclude/net/mac80211.h ieee80211_queue_stopped
- </sect1>
- </chapter>
-
- <chapter id="filters">
- <title>Frame filtering</title>
-!Pinclude/net/mac80211.h Frame filtering
-!Finclude/net/mac80211.h ieee80211_filter_flags
- </chapter>
-
- <chapter id="workqueue">
- <title>The mac80211 workqueue</title>
-!Pinclude/net/mac80211.h mac80211 workqueue
-!Finclude/net/mac80211.h ieee80211_queue_work
-!Finclude/net/mac80211.h ieee80211_queue_delayed_work
- </chapter>
- </part>
-
- <part id="advanced">
- <title>Advanced driver interface</title>
- <partintro>
- <para>
- Information contained within this part of the book is
- of interest only for advanced interaction of mac80211
- with drivers to exploit more hardware capabilities and
- improve performance.
- </para>
- </partintro>
-
- <chapter id="led-support">
- <title>LED support</title>
- <para>
- Mac80211 supports various ways of blinking LEDs. Wherever possible,
- device LEDs should be exposed as LED class devices and hooked up to
- the appropriate trigger, which will then be triggered appropriately
- by mac80211.
- </para>
-!Finclude/net/mac80211.h ieee80211_get_tx_led_name
-!Finclude/net/mac80211.h ieee80211_get_rx_led_name
-!Finclude/net/mac80211.h ieee80211_get_assoc_led_name
-!Finclude/net/mac80211.h ieee80211_get_radio_led_name
-!Finclude/net/mac80211.h ieee80211_tpt_blink
-!Finclude/net/mac80211.h ieee80211_tpt_led_trigger_flags
-!Finclude/net/mac80211.h ieee80211_create_tpt_led_trigger
- </chapter>
-
- <chapter id="hardware-crypto-offload">
- <title>Hardware crypto acceleration</title>
-!Pinclude/net/mac80211.h Hardware crypto acceleration
- <!-- intentionally multiple !F lines to get proper order -->
-!Finclude/net/mac80211.h set_key_cmd
-!Finclude/net/mac80211.h ieee80211_key_conf
-!Finclude/net/mac80211.h ieee80211_key_flags
-!Finclude/net/mac80211.h ieee80211_get_tkip_p1k
-!Finclude/net/mac80211.h ieee80211_get_tkip_p1k_iv
-!Finclude/net/mac80211.h ieee80211_get_tkip_p2k
- </chapter>
-
- <chapter id="powersave">
- <title>Powersave support</title>
-!Pinclude/net/mac80211.h Powersave support
- </chapter>
-
- <chapter id="beacon-filter">
- <title>Beacon filter support</title>
-!Pinclude/net/mac80211.h Beacon filter support
-!Finclude/net/mac80211.h ieee80211_beacon_loss
- </chapter>
-
- <chapter id="qos">
- <title>Multiple queues and QoS support</title>
- <para>TBD</para>
-!Finclude/net/mac80211.h ieee80211_tx_queue_params
- </chapter>
-
- <chapter id="AP">
- <title>Access point mode support</title>
- <para>TBD</para>
- <para>Some parts of the if_conf should be discussed here instead</para>
- <para>
- Insert notes about VLAN interfaces with hw crypto here or
- in the hw crypto chapter.
- </para>
- <section id="ps-client">
- <title>support for powersaving clients</title>
-!Pinclude/net/mac80211.h AP support for powersaving clients
-!Finclude/net/mac80211.h ieee80211_get_buffered_bc
-!Finclude/net/mac80211.h ieee80211_beacon_get
-!Finclude/net/mac80211.h ieee80211_sta_eosp
-!Finclude/net/mac80211.h ieee80211_frame_release_type
-!Finclude/net/mac80211.h ieee80211_sta_ps_transition
-!Finclude/net/mac80211.h ieee80211_sta_ps_transition_ni
-!Finclude/net/mac80211.h ieee80211_sta_set_buffered
-!Finclude/net/mac80211.h ieee80211_sta_block_awake
- </section>
- </chapter>
-
- <chapter id="multi-iface">
- <title>Supporting multiple virtual interfaces</title>
- <para>TBD</para>
- <para>
- Note: WDS with identical MAC address should almost always be OK
- </para>
- <para>
- Insert notes about having multiple virtual interfaces with
- different MAC addresses here, note which configurations are
- supported by mac80211, add notes about supporting hw crypto
- with it.
- </para>
-!Finclude/net/mac80211.h ieee80211_iterate_active_interfaces
-!Finclude/net/mac80211.h ieee80211_iterate_active_interfaces_atomic
- </chapter>
-
- <chapter id="station-handling">
- <title>Station handling</title>
- <para>TODO</para>
-!Finclude/net/mac80211.h ieee80211_sta
-!Finclude/net/mac80211.h sta_notify_cmd
-!Finclude/net/mac80211.h ieee80211_find_sta
-!Finclude/net/mac80211.h ieee80211_find_sta_by_ifaddr
- </chapter>
-
- <chapter id="hardware-scan-offload">
- <title>Hardware scan offload</title>
- <para>TBD</para>
-!Finclude/net/mac80211.h ieee80211_scan_completed
- </chapter>
-
- <chapter id="aggregation">
- <title>Aggregation</title>
- <sect1>
- <title>TX A-MPDU aggregation</title>
-!Pnet/mac80211/agg-tx.c TX A-MPDU aggregation
-!Cnet/mac80211/agg-tx.c
- </sect1>
- <sect1>
- <title>RX A-MPDU aggregation</title>
-!Pnet/mac80211/agg-rx.c RX A-MPDU aggregation
-!Cnet/mac80211/agg-rx.c
-!Finclude/net/mac80211.h ieee80211_ampdu_mlme_action
- </sect1>
- </chapter>
-
- <chapter id="smps">
- <title>Spatial Multiplexing Powersave (SMPS)</title>
-!Pinclude/net/mac80211.h Spatial multiplexing power save
-!Finclude/net/mac80211.h ieee80211_request_smps
-!Finclude/net/mac80211.h ieee80211_smps_mode
- </chapter>
- </part>
-
- <part id="rate-control">
- <title>Rate control interface</title>
- <partintro>
- <para>TBD</para>
- <para>
- This part of the book describes the rate control algorithm
- interface and how it relates to mac80211 and drivers.
- </para>
- </partintro>
- <chapter id="ratecontrol-api">
- <title>Rate Control API</title>
- <para>TBD</para>
-!Finclude/net/mac80211.h ieee80211_start_tx_ba_session
-!Finclude/net/mac80211.h ieee80211_start_tx_ba_cb_irqsafe
-!Finclude/net/mac80211.h ieee80211_stop_tx_ba_session
-!Finclude/net/mac80211.h ieee80211_stop_tx_ba_cb_irqsafe
-!Finclude/net/mac80211.h ieee80211_rate_control_changed
-!Finclude/net/mac80211.h ieee80211_tx_rate_control
-!Finclude/net/mac80211.h rate_control_send_low
- </chapter>
- </part>
-
- <part id="internal">
- <title>Internals</title>
- <partintro>
- <para>TBD</para>
- <para>
- This part of the book describes mac80211 internals.
- </para>
- </partintro>
-
- <chapter id="key-handling">
- <title>Key handling</title>
- <sect1>
- <title>Key handling basics</title>
-!Pnet/mac80211/key.c Key handling basics
- </sect1>
- <sect1>
- <title>MORE TBD</title>
- <para>TBD</para>
- </sect1>
- </chapter>
-
- <chapter id="rx-processing">
- <title>Receive processing</title>
- <para>TBD</para>
- </chapter>
-
- <chapter id="tx-processing">
- <title>Transmit processing</title>
- <para>TBD</para>
- </chapter>
-
- <chapter id="sta-info">
- <title>Station info handling</title>
- <sect1>
- <title>Programming information</title>
-!Fnet/mac80211/sta_info.h sta_info
-!Fnet/mac80211/sta_info.h ieee80211_sta_info_flags
- </sect1>
- <sect1>
- <title>STA information lifetime rules</title>
-!Pnet/mac80211/sta_info.c STA information lifetime rules
- </sect1>
- </chapter>
-
- <chapter id="aggregation-internals">
- <title>Aggregation</title>
-!Fnet/mac80211/sta_info.h sta_ampdu_mlme
-!Fnet/mac80211/sta_info.h tid_ampdu_tx
-!Fnet/mac80211/sta_info.h tid_ampdu_rx
- </chapter>
-
- <chapter id="synchronisation">
- <title>Synchronisation</title>
- <para>TBD</para>
- <para>Locking, lots of RCU</para>
- </chapter>
- </part>
- </book>
-</set>
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index 736f591..fdf8232 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -12,7 +12,7 @@
kernel-api.xml filesystems.xml lsm.xml usb.xml kgdb.xml \
gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
- 80211.xml debugobjects.xml sh.xml regulator.xml \
+ debugobjects.xml sh.xml regulator.xml \
alsa-driver-api.xml writing-an-alsa-driver.xml \
tracepoint.xml w1.xml \
writing_musb_glue_layer.xml crypto-API.xml iio.xml
diff --git a/Documentation/Makefile b/Documentation/Makefile
index de955e1..c2a4691 100644
--- a/Documentation/Makefile
+++ b/Documentation/Makefile
@@ -1,3 +1 @@
-subdir-y := accounting auxdisplay blackfin \
- filesystems filesystems ia64 laptops mic misc-devices \
- networking pcmcia prctl ptp timers vDSO watchdog
+subdir-y :=
diff --git a/Documentation/accounting/Makefile b/Documentation/accounting/Makefile
deleted file mode 100644
index 7e232cb..0000000
--- a/Documentation/accounting/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-# List of programs to build
-hostprogs-y := getdelays
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
-
-HOSTCFLAGS_getdelays.o += -I$(objtree)/usr/include
diff --git a/Documentation/accounting/delay-accounting.txt b/Documentation/accounting/delay-accounting.txt
index 8a12f07..042ea59 100644
--- a/Documentation/accounting/delay-accounting.txt
+++ b/Documentation/accounting/delay-accounting.txt
@@ -54,9 +54,9 @@
task of a thread group, the per-tgid statistics are also sent. More details
are given in the taskstats interface description.
-The getdelays.c userspace utility in this directory allows simple commands to
-be run and the corresponding delay statistics to be displayed. It also serves
-as an example of using the taskstats interface.
+The getdelays.c userspace utility in tools/accounting directory allows simple
+commands to be run and the corresponding delay statistics to be displayed. It
+also serves as an example of using the taskstats interface.
Usage
-----
diff --git a/Documentation/arm/00-INDEX b/Documentation/arm/00-INDEX
index dea011c..b6e69fd 100644
--- a/Documentation/arm/00-INDEX
+++ b/Documentation/arm/00-INDEX
@@ -8,8 +8,6 @@
- ARM Interrupt subsystem documentation
IXP4xx
- Intel IXP4xx Network processor.
-Makefile
- - Build sourcefiles as part of the Documentation-build for arm
Netwinder
- Netwinder specific documentation
Porting
diff --git a/Documentation/auxdisplay/Makefile b/Documentation/auxdisplay/Makefile
deleted file mode 100644
index ada4dac..0000000
--- a/Documentation/auxdisplay/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-# List of programs to build
-hostprogs-y := cfag12864b-example
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
-
-HOSTCFLAGS_cfag12864b-example.o += -I$(objtree)/usr/include
diff --git a/Documentation/auxdisplay/cfag12864b b/Documentation/auxdisplay/cfag12864b
index eb7be39..12fd51b 100644
--- a/Documentation/auxdisplay/cfag12864b
+++ b/Documentation/auxdisplay/cfag12864b
@@ -101,5 +101,5 @@
Also, you can mmap the framebuffer: open & mmap, munmap & close...
which is the best option for most uses.
-Check Documentation/auxdisplay/cfag12864b-example.c
+Check samples/auxdisplay/cfag12864b-example.c
for a real working userspace complete program with usage examples.
diff --git a/Documentation/blackfin/00-INDEX b/Documentation/blackfin/00-INDEX
index c54fcdd..265a1ef 100644
--- a/Documentation/blackfin/00-INDEX
+++ b/Documentation/blackfin/00-INDEX
@@ -1,10 +1,6 @@
00-INDEX
- This file
-Makefile
- - Makefile for gptimers example file.
bfin-gpio-notes.txt
- Notes in developing/using bfin-gpio driver.
bfin-spi-notes.txt
- Notes for using bfin spi bus driver.
-gptimers-example.c
- - gptimers example
diff --git a/Documentation/blackfin/Makefile b/Documentation/blackfin/Makefile
deleted file mode 100644
index 6782c58..0000000
--- a/Documentation/blackfin/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-ifneq ($(CONFIG_BLACKFIN),)
-ifneq ($(CONFIG_BFIN_GPTIMERS),)
-obj-m := gptimers-example.o
-endif
-endif
diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt
index e5b6497..c75b64a 100644
--- a/Documentation/device-mapper/dm-raid.txt
+++ b/Documentation/device-mapper/dm-raid.txt
@@ -309,3 +309,4 @@
with a reshape in progress.
1.9.0 Add support for RAID level takeover/reshape/region size
and set size reduction.
+1.9.1 Fix activation of existing RAID 4/10 mapped devices
diff --git a/Documentation/devicetree/bindings/auxdisplay/img-ascii-lcd.txt b/Documentation/devicetree/bindings/auxdisplay/img-ascii-lcd.txt
new file mode 100644
index 0000000..b69bb68
--- /dev/null
+++ b/Documentation/devicetree/bindings/auxdisplay/img-ascii-lcd.txt
@@ -0,0 +1,17 @@
+Binding for ASCII LCD displays on Imagination Technologies boards
+
+Required properties:
+- compatible : should be one of:
+ "img,boston-lcd"
+ "mti,malta-lcd"
+ "mti,sead3-lcd"
+
+Required properties for "img,boston-lcd":
+- reg : memory region locating the device registers
+
+Required properties for "mti,malta-lcd" or "mti,sead3-lcd":
+- regmap: phandle of the system controller containing the LCD registers
+- offset: offset in bytes to the LCD registers within the system controller
+
+The layout of the registers & properties of the display are determined
+from the compatible string, making this binding somewhat trivial.
diff --git a/Documentation/devicetree/bindings/clock/uniphier-clock.txt b/Documentation/devicetree/bindings/clock/uniphier-clock.txt
index c7179d3..8121630 100644
--- a/Documentation/devicetree/bindings/clock/uniphier-clock.txt
+++ b/Documentation/devicetree/bindings/clock/uniphier-clock.txt
@@ -24,7 +24,7 @@
reg = <0x61840000 0x4000>;
clock {
- compatible = "socionext,uniphier-ld20-clock";
+ compatible = "socionext,uniphier-ld11-clock";
#clock-cells = <1>;
};
@@ -43,8 +43,8 @@
21: USB3 ch1 PHY1
-Media I/O (MIO) clock
----------------------
+Media I/O (MIO) clock, SD clock
+-------------------------------
Required properties:
- compatible: should be one of the following:
@@ -52,10 +52,10 @@
"socionext,uniphier-ld4-mio-clock" - for LD4 SoC.
"socionext,uniphier-pro4-mio-clock" - for Pro4 SoC.
"socionext,uniphier-sld8-mio-clock" - for sLD8 SoC.
- "socionext,uniphier-pro5-mio-clock" - for Pro5 SoC.
- "socionext,uniphier-pxs2-mio-clock" - for PXs2/LD6b SoC.
+ "socionext,uniphier-pro5-sd-clock" - for Pro5 SoC.
+ "socionext,uniphier-pxs2-sd-clock" - for PXs2/LD6b SoC.
"socionext,uniphier-ld11-mio-clock" - for LD11 SoC.
- "socionext,uniphier-ld20-mio-clock" - for LD20 SoC.
+ "socionext,uniphier-ld20-sd-clock" - for LD20 SoC.
- #clock-cells: should be 1.
Example:
@@ -66,7 +66,7 @@
reg = <0x59810000 0x800>;
clock {
- compatible = "socionext,uniphier-ld20-mio-clock";
+ compatible = "socionext,uniphier-ld11-mio-clock";
#clock-cells = <1>;
};
@@ -112,7 +112,7 @@
reg = <0x59820000 0x200>;
clock {
- compatible = "socionext,uniphier-ld20-peri-clock";
+ compatible = "socionext,uniphier-ld11-peri-clock";
#clock-cells = <1>;
};
diff --git a/Documentation/devicetree/bindings/i2c/i2c.txt b/Documentation/devicetree/bindings/i2c/i2c.txt
index f31b2ad..5fa691e 100644
--- a/Documentation/devicetree/bindings/i2c/i2c.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c.txt
@@ -32,6 +32,14 @@
- clock-frequency
frequency of bus clock in Hz.
+- i2c-bus
+ For I2C adapters that have child nodes that are a mixture of both I2C
+ devices and non-I2C devices, the 'i2c-bus' subnode can be used for
+ populating I2C devices. If the 'i2c-bus' subnode is present, only
+ subnodes of this will be considered as I2C slaves. The properties,
+ '#address-cells' and '#size-cells' must be defined under this subnode
+ if present.
+
- i2c-scl-falling-time-ns
Number of nanoseconds the SCL signal takes to fall; t(f) in the I2C
specification.
diff --git a/Documentation/devicetree/bindings/i2c/trivial-devices.txt b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
index 1416c6a..fbbad64 100644
--- a/Documentation/devicetree/bindings/i2c/trivial-devices.txt
+++ b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
@@ -51,7 +51,6 @@
gmt,g751 G751: Digital Temperature Sensor and Thermal Watchdog with Two-Wire Interface
infineon,slb9635tt Infineon SLB9635 (Soft-) I2C TPM (old protocol, max 100khz)
infineon,slb9645tt Infineon SLB9645 I2C TPM (new protocol, max 400khz)
-isil,isl12057 Intersil ISL12057 I2C RTC Chip
isil,isl29028 Intersil ISL29028 Ambient Light and Proximity Sensor
maxim,ds1050 5 Bit Programmable, Pulse-Width Modulator
maxim,max1237 Low-Power, 4-/12-Channel, 2-Wire Serial, 12-Bit ADCs
diff --git a/Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt b/Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt
index f97993b..d3b273e 100644
--- a/Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt
+++ b/Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt
@@ -14,6 +14,7 @@
representing a ethernet device.
- dsaf-handle: phandle, specifies a reference to a node
representing a dsaf device.
+- node_guid: a number that uniquely identifies a device or component
- #address-cells: must be 2
- #size-cells: must be 2
Optional properties:
@@ -32,6 +33,7 @@
dma-coherent;
eth-handle = <ð2 ð3 ð4 ð5 ð6 ð7>;
dsaf-handle = <&soc0_dsa>;
+ node-guid = [00 9A CD 00 00 01 02 03];
#address-cells = <2>;
#size-cells = <2>;
interrupt-parent = <&mbigen_dsa>;
diff --git a/Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt b/Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt
new file mode 100644
index 0000000..7b8944c
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt
@@ -0,0 +1,21 @@
+* MELFAS MIP4 Touchscreen
+
+Required properties:
+- compatible: must be "melfas,mip4_ts"
+- reg: I2C slave address of the chip (0x48 or 0x34)
+- interrupt-parent: interrupt controller to which the chip is connected
+- interrupts: interrupt to which the chip is connected
+
+Optional properties:
+- ce-gpios: GPIO connected to the CE (chip enable) pin of the chip
+
+Example:
+ i2c@00000000 {
+ touchscreen: melfas_mip4@48 {
+ compatible = "melfas,mip4_ts";
+ reg = <0x48>;
+ interrupt-parent = <&gpio>;
+ interrupts = <0 IRQ_TYPE_EDGE_FALLING>;
+ ce-gpios = <&gpio 0 GPIO_ACTIVE_HIGH>;
+ };
+ };
diff --git a/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt b/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt
new file mode 100644
index 0000000..fbbacd9
--- /dev/null
+++ b/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt
@@ -0,0 +1,23 @@
+* Aspeed BT (Block Transfer) IPMI interface
+
+The Aspeed SOCs (AST2400 and AST2500) are commonly used as BMCs
+(BaseBoard Management Controllers) and the BT interface can be used to
+perform in-band IPMI communication with their host.
+
+Required properties:
+
+- compatible : should be "aspeed,ast2400-bt-bmc"
+- reg: physical address and size of the registers
+
+Optional properties:
+
+- interrupts: interrupt generated by the BT interface. without an
+ interrupt, the driver will operate in poll mode.
+
+Example:
+
+ ibt@1e789140 {
+ compatible = "aspeed,ast2400-bt-bmc";
+ reg = <0x1e789140 0x18>;
+ interrupts = <8>;
+ };
diff --git a/Documentation/devicetree/bindings/ipmi.txt b/Documentation/devicetree/bindings/ipmi/ipmi-smic.txt
similarity index 100%
rename from Documentation/devicetree/bindings/ipmi.txt
rename to Documentation/devicetree/bindings/ipmi/ipmi-smic.txt
diff --git a/Documentation/devicetree/bindings/mips/brcm/soc.txt b/Documentation/devicetree/bindings/mips/brcm/soc.txt
index 4a7e030..e4e1cd9 100644
--- a/Documentation/devicetree/bindings/mips/brcm/soc.txt
+++ b/Documentation/devicetree/bindings/mips/brcm/soc.txt
@@ -2,9 +2,9 @@
Required properties:
-- compatible: "brcm,bcm3384", "brcm,bcm33843"
+- compatible: "brcm,bcm3368", "brcm,bcm3384", "brcm,bcm33843"
"brcm,bcm3384-viper", "brcm,bcm33843-viper"
- "brcm,bcm6328", "brcm,bcm6358", "brcm,bcm6368",
+ "brcm,bcm6328", "brcm,bcm6358", "brcm,bcm6362", "brcm,bcm6368",
"brcm,bcm63168", "brcm,bcm63268",
"brcm,bcm7125", "brcm,bcm7346", "brcm,bcm7358", "brcm,bcm7360",
"brcm,bcm7362", "brcm,bcm7420", "brcm,bcm7425"
diff --git a/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
index 4e00e85..bfa461a 100644
--- a/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
@@ -43,6 +43,9 @@
reset signal present internally in some host controller IC designs.
See Documentation/devicetree/bindings/reset/reset.txt for details.
+* reset-names: request name for using "resets" property. Must be "reset".
+ (It will be used together with "resets" property.)
+
* clocks: from common clock binding: handle to biu and ciu clocks for the
bus interface unit clock and the card interface unit clock.
@@ -103,6 +106,8 @@
interrupts = <0 75 0>;
#address-cells = <1>;
#size-cells = <0>;
+ resets = <&rst 20>;
+ reset-names = "reset";
};
[board specific internal DMA resources]
diff --git a/Documentation/devicetree/bindings/net/brcm,amac.txt b/Documentation/devicetree/bindings/net/brcm,amac.txt
index ba5ecc1..2fefa1a 100644
--- a/Documentation/devicetree/bindings/net/brcm,amac.txt
+++ b/Documentation/devicetree/bindings/net/brcm,amac.txt
@@ -2,11 +2,17 @@
-------------------------------------------------------------
Required properties:
- - compatible: "brcm,amac" or "brcm,nsp-amac"
- - reg: Address and length of the GMAC registers,
- Address and length of the GMAC IDM registers
- - reg-names: Names of the registers. Must have both "amac_base" and
- "idm_base"
+ - compatible: "brcm,amac"
+ "brcm,nsp-amac"
+ "brcm,ns2-amac"
+ - reg: Address and length of the register set for the device. It
+ contains the information of registers in the same order as
+ described by reg-names
+ - reg-names: Names of the registers.
+ "amac_base": Address and length of the GMAC registers
+ "idm_base": Address and length of the GMAC IDM registers
+ "nicpm_base": Address and length of the NIC Port Manager
+ registers (required for Northstar2)
- interrupts: Interrupt number
Optional properties:
diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
index d4b7f2e..abfbeec 100644
--- a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
+++ b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
@@ -45,6 +45,12 @@
depends on the hardware user manual.
- port-mode-offset: is offset of port mode field for each port in dsaf. Its
value depends on the hardware user manual.
+- mc-mac-mask: mask of multicast address, determines bit in multicast address
+ to set:
+ 1 stands for this bit will be precisely matched, TCAM will check this bit of
+ MAC address.
+ 0 stands for this bit will be fuzzy matched, TCAM won't care about this bit
+ of MAC address.
[1] Documentation/devicetree/bindings/net/phy.txt
@@ -74,10 +80,12 @@
reg = 0;
phy-handle = <&phy0>;
serdes-syscon = <&serdes>;
+ mc-mac-mask = [ff f0 00 00 00 00];
};
port@1 {
reg = 1;
serdes-syscon = <&serdes>;
+ mc-mac-mask = [ff f0 00 00 00 00];
};
};
diff --git a/Documentation/devicetree/bindings/net/marvell-orion-net.txt b/Documentation/devicetree/bindings/net/marvell-orion-net.txt
index bce52b2..6fd988c 100644
--- a/Documentation/devicetree/bindings/net/marvell-orion-net.txt
+++ b/Documentation/devicetree/bindings/net/marvell-orion-net.txt
@@ -49,6 +49,7 @@
and
- phy-handle: See ethernet.txt file in the same directory.
+ - phy-mode: See ethernet.txt file in the same directory.
or
diff --git a/Documentation/devicetree/bindings/net/mdio-mux-mmioreg.txt b/Documentation/devicetree/bindings/net/mdio-mux-mmioreg.txt
index 8516929..065e8bd 100644
--- a/Documentation/devicetree/bindings/net/mdio-mux-mmioreg.txt
+++ b/Documentation/devicetree/bindings/net/mdio-mux-mmioreg.txt
@@ -3,7 +3,7 @@
This is a special case of a MDIO bus multiplexer. A memory-mapped device,
like an FPGA, is used to control which child bus is connected. The mdio-mux
node must be a child of the memory-mapped device. The driver currently only
-supports devices with eight-bit registers.
+supports devices with 8, 16 or 32-bit registers.
Required properties in addition to the generic multiplexer properties:
@@ -11,7 +11,7 @@
- reg : integer, contains the offset of the register that controls the bus
multiplexer. The size field in the 'reg' property is the size of
- register, and must therefore be 1.
+ register, and must therefore be 1, 2, or 4.
- mux-mask : integer, contains an eight-bit mask that specifies which
bits in the register control the actual bus multiplexer. The
diff --git a/Documentation/devicetree/bindings/net/oxnas-dwmac.txt b/Documentation/devicetree/bindings/net/oxnas-dwmac.txt
new file mode 100644
index 0000000..df0534e
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/oxnas-dwmac.txt
@@ -0,0 +1,39 @@
+* Oxford Semiconductor OXNAS DWMAC Ethernet controller
+
+The device inherits all the properties of the dwmac/stmmac devices
+described in the file stmmac.txt in the current directory with the
+following changes.
+
+Required properties on all platforms:
+
+- compatible: For the OX820 SoC, it should be :
+ - "oxsemi,ox820-dwmac" to select glue
+ - "snps,dwmac-3.512" to select IP version.
+
+- clocks: Should contain phandles to the following clocks
+- clock-names: Should contain the following:
+ - "stmmaceth" for the host clock - see stmmac.txt
+ - "gmac" for the peripheral gate clock
+
+- oxsemi,sys-ctrl: a phandle to the system controller syscon node
+
+Example :
+
+etha: ethernet@40400000 {
+ compatible = "oxsemi,ox820-dwmac", "snps,dwmac-3.512";
+ reg = <0x40400000 0x2000>;
+ interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_wake_irq";
+ mac-address = [000000000000]; /* Filled in by U-Boot */
+ phy-mode = "rgmii";
+
+ clocks = <&stdclk CLK_820_ETHA>, <&gmacclk>;
+ clock-names = "gmac", "stmmaceth";
+ resets = <&reset RESET_MAC>;
+
+ /* Regmap for sys registers */
+ oxsemi,sys-ctrl = <&sys>;
+
+ status = "disabled";
+};
diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt
index bc1c3c8..4627da3 100644
--- a/Documentation/devicetree/bindings/net/phy.txt
+++ b/Documentation/devicetree/bindings/net/phy.txt
@@ -35,6 +35,10 @@
- broken-turn-around: If set, indicates the PHY device does not correctly
release the turn around line low at the end of a MDIO transaction.
+- enet-phy-lane-swap: If set, indicates the PHY will swap the TX/RX lanes to
+ compensate for the board being designed with the lanes swapped.
+
+
Example:
ethernet-phy@0 {
diff --git a/Documentation/devicetree/bindings/pci/rockchip-pcie.txt b/Documentation/devicetree/bindings/pci/rockchip-pcie.txt
index ba67b39..71aeda1 100644
--- a/Documentation/devicetree/bindings/pci/rockchip-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/rockchip-pcie.txt
@@ -26,13 +26,16 @@
- "sys"
- "legacy"
- "client"
-- resets: Must contain five entries for each entry in reset-names.
+- resets: Must contain seven entries for each entry in reset-names.
See ../reset/reset.txt for details.
- reset-names: Must include the following names
- "core"
- "mgmt"
- "mgmt-sticky"
- "pipe"
+ - "pm"
+ - "aclk"
+ - "pclk"
- pinctrl-names : The pin control state names
- pinctrl-0: The "default" pinctrl state
- #interrupt-cells: specifies the number of cells needed to encode an
@@ -86,8 +89,10 @@
reg = <0x0 0xf8000000 0x0 0x2000000>, <0x0 0xfd000000 0x0 0x1000000>;
reg-names = "axi-base", "apb-base";
resets = <&cru SRST_PCIE_CORE>, <&cru SRST_PCIE_MGMT>,
- <&cru SRST_PCIE_MGMT_STICKY>, <&cru SRST_PCIE_PIPE>;
- reset-names = "core", "mgmt", "mgmt-sticky", "pipe";
+ <&cru SRST_PCIE_MGMT_STICKY>, <&cru SRST_PCIE_PIPE> ,
+ <&cru SRST_PCIE_PM>, <&cru SRST_P_PCIE>, <&cru SRST_A_PCIE>;
+ reset-names = "core", "mgmt", "mgmt-sticky", "pipe",
+ "pm", "pclk", "aclk";
phys = <&pcie_phy>;
phy-names = "pcie-phy";
pinctrl-names = "default";
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-aspeed.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-aspeed.txt
index 5e60ad1..2ad18c4 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-aspeed.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-aspeed.txt
@@ -43,7 +43,9 @@
GPID0 GPID2 GPIE0 I2C10 I2C11 I2C12 I2C13 I2C14 I2C3 I2C4 I2C5 I2C6 I2C7 I2C8
I2C9 MAC1LINK MDIO1 MDIO2 OSCCLK PEWAKE PWM0 PWM1 PWM2 PWM3 PWM4 PWM5 PWM6 PWM7
-RGMII1 RGMII2 RMII1 RMII2 SD1 SPI1 TIMER4 TIMER5 TIMER6 TIMER7 TIMER8
+RGMII1 RGMII2 RMII1 RMII2 SD1 SPI1 SPI1DEBUG SPI1PASSTHRU TIMER4 TIMER5 TIMER6
+TIMER7 TIMER8 VGABIOSROM
+
Examples:
diff --git a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
index f9753c4..b24583a 100644
--- a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
@@ -14,11 +14,6 @@
- #size-cells : The value of this property must be 1
- ranges : defines mapping between pin controller node (parent) to
gpio-bank node (children).
- - interrupt-parent: phandle of the interrupt parent to which the external
- GPIO interrupts are forwarded to.
- - st,syscfg: Should be phandle/offset pair. The phandle to the syscon node
- which includes IRQ mux selection register, and the offset of the IRQ mux
- selection register.
- pins-are-numbered: Specify the subnodes are using numbered pinmux to
specify pins.
@@ -37,6 +32,11 @@
Optional properties:
- reset: : Reference to the reset controller
+ - interrupt-parent: phandle of the interrupt parent to which the external
+ GPIO interrupts are forwarded to.
+ - st,syscfg: Should be phandle/offset pair. The phandle to the syscon node
+ which includes IRQ mux selection register, and the offset of the IRQ mux
+ selection register.
Example:
#include <dt-bindings/pinctrl/stm32f429-pinfunc.h>
diff --git a/Documentation/devicetree/bindings/reset/uniphier-reset.txt b/Documentation/devicetree/bindings/reset/uniphier-reset.txt
index e6bbfcc..5020524 100644
--- a/Documentation/devicetree/bindings/reset/uniphier-reset.txt
+++ b/Documentation/devicetree/bindings/reset/uniphier-reset.txt
@@ -6,25 +6,25 @@
Required properties:
- compatible: should be one of the following:
- "socionext,uniphier-sld3-reset" - for PH1-sLD3 SoC.
- "socionext,uniphier-ld4-reset" - for PH1-LD4 SoC.
- "socionext,uniphier-pro4-reset" - for PH1-Pro4 SoC.
- "socionext,uniphier-sld8-reset" - for PH1-sLD8 SoC.
- "socionext,uniphier-pro5-reset" - for PH1-Pro5 SoC.
- "socionext,uniphier-pxs2-reset" - for ProXstream2/PH1-LD6b SoC.
- "socionext,uniphier-ld11-reset" - for PH1-LD11 SoC.
- "socionext,uniphier-ld20-reset" - for PH1-LD20 SoC.
+ "socionext,uniphier-sld3-reset" - for sLD3 SoC.
+ "socionext,uniphier-ld4-reset" - for LD4 SoC.
+ "socionext,uniphier-pro4-reset" - for Pro4 SoC.
+ "socionext,uniphier-sld8-reset" - for sLD8 SoC.
+ "socionext,uniphier-pro5-reset" - for Pro5 SoC.
+ "socionext,uniphier-pxs2-reset" - for PXs2/LD6b SoC.
+ "socionext,uniphier-ld11-reset" - for LD11 SoC.
+ "socionext,uniphier-ld20-reset" - for LD20 SoC.
- #reset-cells: should be 1.
Example:
sysctrl@61840000 {
- compatible = "socionext,uniphier-ld20-sysctrl",
+ compatible = "socionext,uniphier-ld11-sysctrl",
"simple-mfd", "syscon";
reg = <0x61840000 0x4000>;
reset {
- compatible = "socionext,uniphier-ld20-reset";
+ compatible = "socionext,uniphier-ld11-reset";
#reset-cells = <1>;
};
@@ -32,30 +32,30 @@
};
-Media I/O (MIO) reset
----------------------
+Media I/O (MIO) reset, SD reset
+-------------------------------
Required properties:
- compatible: should be one of the following:
- "socionext,uniphier-sld3-mio-reset" - for PH1-sLD3 SoC.
- "socionext,uniphier-ld4-mio-reset" - for PH1-LD4 SoC.
- "socionext,uniphier-pro4-mio-reset" - for PH1-Pro4 SoC.
- "socionext,uniphier-sld8-mio-reset" - for PH1-sLD8 SoC.
- "socionext,uniphier-pro5-mio-reset" - for PH1-Pro5 SoC.
- "socionext,uniphier-pxs2-mio-reset" - for ProXstream2/PH1-LD6b SoC.
- "socionext,uniphier-ld11-mio-reset" - for PH1-LD11 SoC.
- "socionext,uniphier-ld20-mio-reset" - for PH1-LD20 SoC.
+ "socionext,uniphier-sld3-mio-reset" - for sLD3 SoC.
+ "socionext,uniphier-ld4-mio-reset" - for LD4 SoC.
+ "socionext,uniphier-pro4-mio-reset" - for Pro4 SoC.
+ "socionext,uniphier-sld8-mio-reset" - for sLD8 SoC.
+ "socionext,uniphier-pro5-sd-reset" - for Pro5 SoC.
+ "socionext,uniphier-pxs2-sd-reset" - for PXs2/LD6b SoC.
+ "socionext,uniphier-ld11-mio-reset" - for LD11 SoC.
+ "socionext,uniphier-ld20-sd-reset" - for LD20 SoC.
- #reset-cells: should be 1.
Example:
mioctrl@59810000 {
- compatible = "socionext,uniphier-ld20-mioctrl",
+ compatible = "socionext,uniphier-ld11-mioctrl",
"simple-mfd", "syscon";
reg = <0x59810000 0x800>;
reset {
- compatible = "socionext,uniphier-ld20-mio-reset";
+ compatible = "socionext,uniphier-ld11-mio-reset";
#reset-cells = <1>;
};
@@ -68,24 +68,24 @@
Required properties:
- compatible: should be one of the following:
- "socionext,uniphier-ld4-peri-reset" - for PH1-LD4 SoC.
- "socionext,uniphier-pro4-peri-reset" - for PH1-Pro4 SoC.
- "socionext,uniphier-sld8-peri-reset" - for PH1-sLD8 SoC.
- "socionext,uniphier-pro5-peri-reset" - for PH1-Pro5 SoC.
- "socionext,uniphier-pxs2-peri-reset" - for ProXstream2/PH1-LD6b SoC.
- "socionext,uniphier-ld11-peri-reset" - for PH1-LD11 SoC.
- "socionext,uniphier-ld20-peri-reset" - for PH1-LD20 SoC.
+ "socionext,uniphier-ld4-peri-reset" - for LD4 SoC.
+ "socionext,uniphier-pro4-peri-reset" - for Pro4 SoC.
+ "socionext,uniphier-sld8-peri-reset" - for sLD8 SoC.
+ "socionext,uniphier-pro5-peri-reset" - for Pro5 SoC.
+ "socionext,uniphier-pxs2-peri-reset" - for PXs2/LD6b SoC.
+ "socionext,uniphier-ld11-peri-reset" - for LD11 SoC.
+ "socionext,uniphier-ld20-peri-reset" - for LD20 SoC.
- #reset-cells: should be 1.
Example:
perictrl@59820000 {
- compatible = "socionext,uniphier-ld20-perictrl",
+ compatible = "socionext,uniphier-ld11-perictrl",
"simple-mfd", "syscon";
reg = <0x59820000 0x200>;
reset {
- compatible = "socionext,uniphier-ld20-peri-reset";
+ compatible = "socionext,uniphier-ld11-peri-reset";
#reset-cells = <1>;
};
diff --git a/Documentation/devicetree/bindings/rtc/dallas,ds1390.txt b/Documentation/devicetree/bindings/rtc/dallas,ds1390.txt
index 8e76f26..9882b81 100644
--- a/Documentation/devicetree/bindings/rtc/dallas,ds1390.txt
+++ b/Documentation/devicetree/bindings/rtc/dallas,ds1390.txt
@@ -11,7 +11,7 @@
- trickle-diode-disable : Do not use internal trickle charger diode
Should be given if internal trickle charger diode should be disabled
Example:
- ds1390: rtc@68 {
+ ds1390: rtc@0 {
compatible = "dallas,ds1390";
trickle-resistor-ohms = <250>;
reg = <0>;
diff --git a/Documentation/devicetree/bindings/rtc/epson,rx8900.txt b/Documentation/devicetree/bindings/rtc/epson,rx8900.txt
new file mode 100644
index 0000000..3f61e51
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/epson,rx8900.txt
@@ -0,0 +1,22 @@
+Real Time Clock driver for:
+ - Epson RX8900
+ - Micro Crystal rv8803
+
+Required properties:
+- compatible: should be: "microcrystal,rv8803" or "epson,rx8900"
+- reg : the I2C address of the device for I2C
+
+Optional properties:
+- epson,vdet-disable : boolean, if present will disable voltage detector.
+ Should be set if no backup battery is used.
+- trickle-diode-disable : boolean, if present will disable internal trickle
+ charger diode
+
+Example:
+
+ rtc: rtc@32 {
+ compatible = "epson,rx8900"
+ reg = <0x32>;
+ epson,vdet-disable;
+ trickle-diode-disable;
+ };
diff --git a/Documentation/devicetree/bindings/rtc/rtc-omap.txt b/Documentation/devicetree/bindings/rtc/rtc-omap.txt
index bf7d11a..bee41f9 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-omap.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-omap.txt
@@ -18,6 +18,18 @@
through pmic_power_en
- clocks: Any internal or external clocks feeding in to rtc
- clock-names: Corresponding names of the clocks
+- pinctrl-0: a phandle pointing to the pin settings for the device
+- pinctrl-names: should be "default"
+
+Optional subnodes:
+- generic pinctrl node
+
+Required pinctrl subnodes properties:
+- pins - Names of ext_wakeup pins to configure
+
+Optional pinctrl subnodes properties:
+- input-enable - Enables ext_wakeup
+- ti,active-high - Set input active high (by default active low)
Example:
@@ -30,4 +42,13 @@
system-power-controller;
clocks = <&clk_32k_rtc>, <&clk_32768_ck>;
clock-names = "ext-clk", "int-clk";
+
+ pinctrl-0 = <&ext_wakeup>;
+ pinctrl-names = "default";
+
+ ext_wakeup: ext-wakeup {
+ pins = "ext_wakeup0";
+ input-enable;
+ ti,active-high;
+ };
};
diff --git a/Documentation/devicetree/bindings/serial/cdns,uart.txt b/Documentation/devicetree/bindings/serial/cdns,uart.txt
index a3eb154..227bb77 100644
--- a/Documentation/devicetree/bindings/serial/cdns,uart.txt
+++ b/Documentation/devicetree/bindings/serial/cdns,uart.txt
@@ -1,7 +1,9 @@
Binding for Cadence UART Controller
Required properties:
-- compatible : should be "cdns,uart-r1p8", or "xlnx,xuartps"
+- compatible :
+ Use "xlnx,xuartps","cdns,uart-r1p8" for Zynq-7xxx SoC.
+ Use "xlnx,zynqmp-uart","cdns,uart-r1p12" for Zynq Ultrascale+ MPSoC.
- reg: Should contain UART controller registers location and length.
- interrupts: Should contain UART controller interrupts.
- clocks: Must contain phandles to the UART clocks
diff --git a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
index 1e4000d..8d27d1a 100644
--- a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
+++ b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
@@ -9,6 +9,14 @@
- "renesas,scifb-r8a73a4" for R8A73A4 (R-Mobile APE6) SCIFB compatible UART.
- "renesas,scifa-r8a7740" for R8A7740 (R-Mobile A1) SCIFA compatible UART.
- "renesas,scifb-r8a7740" for R8A7740 (R-Mobile A1) SCIFB compatible UART.
+ - "renesas,scif-r8a7743" for R8A7743 (RZ/G1M) SCIF compatible UART.
+ - "renesas,scifa-r8a7743" for R8A7743 (RZ/G1M) SCIFA compatible UART.
+ - "renesas,scifb-r8a7743" for R8A7743 (RZ/G1M) SCIFB compatible UART.
+ - "renesas,hscif-r8a7743" for R8A7743 (RZ/G1M) HSCIF compatible UART.
+ - "renesas,scif-r8a7745" for R8A7745 (RZ/G1E) SCIF compatible UART.
+ - "renesas,scifa-r8a7745" for R8A7745 (RZ/G1E) SCIFA compatible UART.
+ - "renesas,scifb-r8a7745" for R8A7745 (RZ/G1E) SCIFB compatible UART.
+ - "renesas,hscif-r8a7745" for R8A7745 (RZ/G1E) HSCIF compatible UART.
- "renesas,scif-r8a7778" for R8A7778 (R-Car M1) SCIF compatible UART.
- "renesas,scif-r8a7779" for R8A7779 (R-Car H1) SCIF compatible UART.
- "renesas,scif-r8a7790" for R8A7790 (R-Car H2) SCIF compatible UART.
diff --git a/Documentation/devicetree/bindings/timer/jcore,pit.txt b/Documentation/devicetree/bindings/timer/jcore,pit.txt
new file mode 100644
index 0000000..af5dd35
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/jcore,pit.txt
@@ -0,0 +1,24 @@
+J-Core Programmable Interval Timer and Clocksource
+
+Required properties:
+
+- compatible: Must be "jcore,pit".
+
+- reg: Memory region(s) for timer/clocksource registers. For SMP,
+ there should be one region per cpu, indexed by the sequential,
+ zero-based hardware cpu number.
+
+- interrupts: An interrupt to assign for the timer. The actual pit
+ core is integrated with the aic and allows the timer interrupt
+ assignment to be programmed by software, but this property is
+ required in order to reserve an interrupt number that doesn't
+ conflict with other devices.
+
+
+Example:
+
+timer@200 {
+ compatible = "jcore,pit";
+ reg = < 0x200 0x30 0x500 0x30 >;
+ interrupts = < 0x48 >;
+};
diff --git a/Documentation/devicetree/bindings/usb/dwc2.txt b/Documentation/devicetree/bindings/usb/dwc2.txt
index 455f2c3..2c30a54 100644
--- a/Documentation/devicetree/bindings/usb/dwc2.txt
+++ b/Documentation/devicetree/bindings/usb/dwc2.txt
@@ -28,10 +28,7 @@
- g-use-dma: enable dma usage in gadget driver.
- g-rx-fifo-size: size of rx fifo size in gadget mode.
- g-np-tx-fifo-size: size of non-periodic tx fifo size in gadget mode.
-
-Deprecated properties:
-- g-tx-fifo-size: size of periodic tx fifo per endpoint (except ep0)
- in gadget mode.
+- g-tx-fifo-size: size of periodic tx fifo per endpoint (except ep0) in gadget mode.
Example:
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 24c6f65..f0a48ea 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -163,9 +163,11 @@
meas Measurement Specialties
mediatek MediaTek Inc.
melexis Melexis N.V.
+melfas MELFAS Inc.
merrii Merrii Technology Co., Ltd.
micrel Micrel Inc.
microchip Microchip Technology Inc.
+microcrystal Micro Crystal AG
micron Micron Technology Inc.
minix MINIX Technology Ltd.
mitsubishi Mitsubishi Electric Corporation
diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index 1670708..ca9d1eb 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -332,6 +332,10 @@
MFD
devm_mfd_add_devices()
+PER-CPU MEM
+ devm_alloc_percpu()
+ devm_free_percpu()
+
PCI
pcim_enable_device() : after success, all PCI ops become managed
pcim_pin_device() : keep PCI device enabled after release
diff --git a/Documentation/features/perf/kprobes-event/arch-support.txt b/Documentation/features/perf/kprobes-event/arch-support.txt
index 9855ad0..4660bf2 100644
--- a/Documentation/features/perf/kprobes-event/arch-support.txt
+++ b/Documentation/features/perf/kprobes-event/arch-support.txt
@@ -22,7 +22,7 @@
| m68k: | TODO |
| metag: | TODO |
| microblaze: | TODO |
- | mips: | TODO |
+ | mips: | ok |
| mn10300: | TODO |
| nios2: | TODO |
| openrisc: | TODO |
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 9922939..f66e748 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -2,8 +2,6 @@
- this file (info on some of the filesystems supported by linux).
Locking
- info on locking rules as they pertain to Linux VFS.
-Makefile
- - Makefile for building the filsystems-part of DocBook.
9p.txt
- 9p (v9fs) is an implementation of the Plan 9 remote fs protocol.
adfs.txt
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 14cdc10..1b5f156 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -447,7 +447,6 @@
int (*flush) (struct file *);
int (*release) (struct inode *, struct file *);
int (*fsync) (struct file *, loff_t start, loff_t end, int datasync);
- int (*aio_fsync) (struct kiocb *, int datasync);
int (*fasync) (int, struct file *, int);
int (*lock) (struct file *, int, struct file_lock *);
ssize_t (*readv) (struct file *, const struct iovec *, unsigned long,
diff --git a/Documentation/filesystems/Makefile b/Documentation/filesystems/Makefile
deleted file mode 100644
index 883010c..0000000
--- a/Documentation/filesystems/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-# List of programs to build
-hostprogs-y := dnotify_test
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 219ffd4..74329fd 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -395,32 +395,6 @@
or if empty, the mapping is anonymous.
-The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
-of the individual tasks of a process. In this file you will see a mapping marked
-as [stack] if that task sees it as a stack. Hence, for the example above, the
-task-level map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
-
-08048000-08049000 r-xp 00000000 03:00 8312 /opt/test
-08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
-0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
-a7cb1000-a7cb2000 ---p 00000000 00:00 0
-a7cb2000-a7eb2000 rw-p 00000000 00:00 0
-a7eb2000-a7eb3000 ---p 00000000 00:00 0
-a7eb3000-a7ed5000 rw-p 00000000 00:00 0 [stack]
-a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
-a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6
-a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6
-a800b000-a800e000 rw-p 00000000 00:00 0
-a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0
-a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0
-a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0
-a8024000-a8027000 rw-p 00000000 00:00 0
-a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2
-a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2
-a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2
-aff35000-aff4a000 rw-p 00000000 00:00 0
-ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]
-
The /proc/PID/smaps is an extension based on maps, showing the memory
consumption for each of the process's mappings. For each of mappings there
is a series of lines such as the following:
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index d619c8d..b5039a0 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -828,7 +828,6 @@
int (*flush) (struct file *, fl_owner_t id);
int (*release) (struct inode *, struct file *);
int (*fsync) (struct file *, loff_t, loff_t, int datasync);
- int (*aio_fsync) (struct kiocb *, int datasync);
int (*fasync) (int, struct file *, int);
int (*lock) (struct file *, int, struct file_lock *);
ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
diff --git a/Documentation/gpio/board.txt b/Documentation/gpio/board.txt
index 40884c4..a0f6189 100644
--- a/Documentation/gpio/board.txt
+++ b/Documentation/gpio/board.txt
@@ -6,7 +6,7 @@
description of the deprecated integer-based GPIO interface please refer to
gpio-legacy.txt (actually, there is no real mapping possible with the old
interface; you just fetch an integer from somewhere and request the
-corresponding GPIO.
+corresponding GPIO).
All platforms can enable the GPIO library, but if the platform strictly
requires GPIO functionality to be present, it needs to select GPIOLIB from its
@@ -162,6 +162,9 @@
Since the "led" GPIOs are mapped as active-high, this example will switch their
signals to 1, i.e. enabling the LEDs. And for the "power" GPIO, which is mapped
-as active-low, its actual signal will be 0 after this code. Contrary to the legacy
-integer GPIO interface, the active-low property is handled during mapping and is
-thus transparent to GPIO consumers.
+as active-low, its actual signal will be 0 after this code. Contrary to the
+legacy integer GPIO interface, the active-low property is handled during
+mapping and is thus transparent to GPIO consumers.
+
+A set of functions such as gpiod_set_value() is available to work with
+the new descriptor-oriented interface.
diff --git a/Documentation/ia64/Makefile b/Documentation/ia64/Makefile
deleted file mode 100644
index d493163..0000000
--- a/Documentation/ia64/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-# List of programs to build
-hostprogs-y := aliasing-test
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
diff --git a/Documentation/index.rst b/Documentation/index.rst
index d9ccb94..c53d089 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -17,6 +17,7 @@
driver-api/index
media/index
gpu/index
+ 80211/index
Indices and tables
==================
diff --git a/Documentation/input/alps.txt b/Documentation/input/alps.txt
index 1fec113..8d1341c 100644
--- a/Documentation/input/alps.txt
+++ b/Documentation/input/alps.txt
@@ -319,3 +319,60 @@
otherwise byte 0 bit 4 must be set and byte 0/4/5 are
in NEW fmt
F: Number of fingers - 3, 0 means 3 fingers, 1 means 4 ...
+
+
+ALPS Absolute Mode - Protocol Version 8
+---------------------------------------
+
+Spoken by SS4 (73 03 14) and SS5 (73 03 28) hardware.
+
+The packet type is given by the APD field, bits 4-5 of byte 3.
+
+Touchpad packet (APD = 0x2):
+
+ b7 b6 b5 b4 b3 b2 b1 b0
+ byte 0: SWM SWR SWL 1 1 0 0 X7
+ byte 1: 0 X6 X5 X4 X3 X2 X1 X0
+ byte 2: 0 Y6 Y5 Y4 Y3 Y2 Y1 Y0
+ byte 3: 0 T&P 1 0 1 0 0 Y7
+ byte 4: 0 Z6 Z5 Z4 Z3 Z2 Z1 Z0
+ byte 5: 0 0 0 0 0 0 0 0
+
+SWM, SWR, SWL: Middle, Right, and Left button states
+
+Touchpad 1 Finger packet (APD = 0x0):
+
+ b7 b6 b5 b4 b3 b2 b1 b0
+ byte 0: SWM SWR SWL 1 1 X2 X1 X0
+ byte 1: X9 X8 X7 1 X6 X5 X4 X3
+ byte 2: 0 X11 X10 LFB Y3 Y2 Y1 Y0
+ byte 3: Y5 Y4 0 0 1 TAPF2 TAPF1 TAPF0
+ byte 4: Zv7 Y11 Y10 1 Y9 Y8 Y7 Y6
+ byte 5: Zv6 Zv5 Zv4 0 Zv3 Zv2 Zv1 Zv0
+
+TAPF: ???
+LFB: ???
+
+Touchpad 2 Finger packet (APD = 0x1):
+
+ b7 b6 b5 b4 b3 b2 b1 b0
+ byte 0: SWM SWR SWL 1 1 AX6 AX5 AX4
+ byte 1: AX11 AX10 AX9 AX8 AX7 AZ1 AY4 AZ0
+ byte 2: AY11 AY10 AY9 CONT AY8 AY7 AY6 AY5
+ byte 3: 0 0 0 1 1 BX6 BX5 BX4
+ byte 4: BX11 BX10 BX9 BX8 BX7 BZ1 BY4 BZ0
+ byte 5: BY11 BY10 BY9 0 BY8 BY7 BY5 BY5
+
+CONT: A 3-or-4 Finger packet is to follow
+
+Touchpad 3-or-4 Finger packet (APD = 0x3):
+
+ b7 b6 b5 b4 b3 b2 b1 b0
+ byte 0: SWM SWR SWL 1 1 AX6 AX5 AX4
+ byte 1: AX11 AX10 AX9 AX8 AX7 AZ1 AY4 AZ0
+ byte 2: AY11 AY10 AY9 OVF AY8 AY7 AY6 AY5
+ byte 3: 0 0 1 1 1 BX6 BX5 BX4
+ byte 4: BX11 BX10 BX9 BX8 BX7 BZ1 BY4 BZ0
+ byte 5: BY11 BY10 BY9 0 BY8 BY7 BY5 BY5
+
+OVF: 5th finger detected
diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt
index 385a5ef..9b9c479 100644
--- a/Documentation/kbuild/makefiles.txt
+++ b/Documentation/kbuild/makefiles.txt
@@ -41,6 +41,7 @@
--- 6.8 Custom kbuild commands
--- 6.9 Preprocessing linker scripts
--- 6.10 Generic header files
+ --- 6.11 Post-link pass
=== 7 Kbuild syntax for exported headers
--- 7.1 header-y
@@ -1237,6 +1238,21 @@
to list the file in the Kbuild file.
See "7.4 generic-y" for further info on syntax etc.
+--- 6.11 Post-link pass
+
+ If the file arch/xxx/Makefile.postlink exists, this makefile
+ will be invoked for post-link objects (vmlinux and modules.ko)
+ for architectures to run post-link passes on. Must also handle
+ the clean target.
+
+ This pass runs after kallsyms generation. If the architecture
+ needs to modify symbol locations, rather than manipulate the
+ kallsyms, it may be easier to add another postlink target for
+ .tmp_vmlinux? targets to be called from link-vmlinux.sh.
+
+ For example, powerpc uses this to check relocation sanity of
+ the linked vmlinux file.
+
=== 7 Kbuild syntax for exported headers
The kernel includes a set of headers that is exported to userspace.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 58f3c10..37babf9 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1511,7 +1511,14 @@
i8042.nopnp [HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX
controllers
i8042.notimeout [HW] Ignore timeout condition signalled by controller
- i8042.reset [HW] Reset the controller during init and cleanup
+ i8042.reset [HW] Reset the controller during init, cleanup and
+ suspend-to-ram transitions, only during s2r
+ transitions, or never reset
+ Format: { 1 | Y | y | 0 | N | n }
+ 1, Y, y: always reset controller
+ 0, N, n: don't ever reset controller
+ Default: only on s2r transitions on x86; most other
+ architectures force reset to be always executed
i8042.unlock [HW] Unlock (ignore) the keylock
i8042.kbdreset [HW] Reset device connected to KBD port
diff --git a/Documentation/kselftest.txt b/Documentation/kselftest.txt
index 979eaca..54bee77 100644
--- a/Documentation/kselftest.txt
+++ b/Documentation/kselftest.txt
@@ -1,8 +1,9 @@
Linux Kernel Selftests
The kernel contains a set of "self tests" under the tools/testing/selftests/
-directory. These are intended to be small unit tests to exercise individual
-code paths in the kernel.
+directory. These are intended to be small tests to exercise individual code
+paths in the kernel. Tests are intended to be run after building, installing
+and booting a kernel.
On some systems, hot-plug tests could hang forever waiting for cpu and
memory to be ready to be offlined. A special hot-plug target is created
diff --git a/Documentation/laptops/00-INDEX b/Documentation/laptops/00-INDEX
index 7c0ac2a..86169dc 100644
--- a/Documentation/laptops/00-INDEX
+++ b/Documentation/laptops/00-INDEX
@@ -1,13 +1,9 @@
00-INDEX
- This file
-Makefile
- - Makefile for building dslm example program.
asus-laptop.txt
- information on the Asus Laptop Extras driver.
disk-shock-protection.txt
- information on hard disk shock protection.
-dslm.c
- - Simple Disk Sleep Monitor program
laptop-mode.txt
- how to conserve battery power using laptop-mode.
sony-laptop.txt
diff --git a/Documentation/laptops/Makefile b/Documentation/laptops/Makefile
deleted file mode 100644
index 0abe44f..0000000
--- a/Documentation/laptops/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-# List of programs to build
-hostprogs-y := dslm
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
diff --git a/Documentation/laptops/laptop-mode.txt b/Documentation/laptops/laptop-mode.txt
index 4ebbfc3..19276f5 100644
--- a/Documentation/laptops/laptop-mode.txt
+++ b/Documentation/laptops/laptop-mode.txt
@@ -779,4 +779,4 @@
---------------
Bartek Kania submitted this, it can be used to measure how much time your disk
-spends spun up/down. See Documentation/laptops/dslm.c
+spends spun up/down. See tools/laptop/dslm/dslm.c
diff --git a/Documentation/mic/Makefile b/Documentation/mic/Makefile
deleted file mode 100644
index a191d45..0000000
--- a/Documentation/mic/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-subdir-y := mpssd
diff --git a/Documentation/mic/mpssd/Makefile b/Documentation/mic/mpssd/Makefile
deleted file mode 100644
index 06871b0..0000000
--- a/Documentation/mic/mpssd/Makefile
+++ /dev/null
@@ -1,21 +0,0 @@
-ifndef CROSS_COMPILE
-# List of programs to build
-hostprogs-$(CONFIG_X86_64) := mpssd
-
-mpssd-objs := mpssd.o sysfs.o
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
-
-HOSTCFLAGS += -I$(objtree)/usr/include -I$(srctree)/tools/include
-
-ifdef DEBUG
-HOSTCFLAGS += -DDEBUG=$(DEBUG)
-endif
-
-HOSTLOADLIBES_mpssd := -lpthread
-
-install:
- install mpssd /usr/sbin/mpssd
- install micctrl /usr/sbin/micctrl
-endif
diff --git a/Documentation/misc-devices/Makefile b/Documentation/misc-devices/Makefile
deleted file mode 100644
index e2b7aa4..0000000
--- a/Documentation/misc-devices/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-subdir-y := mei
diff --git a/Documentation/misc-devices/mei/Makefile b/Documentation/misc-devices/mei/Makefile
deleted file mode 100644
index d758047..0000000
--- a/Documentation/misc-devices/mei/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-# List of programs to build
-hostprogs-y := mei-amt-version
-HOSTCFLAGS_mei-amt-version.o += -I$(objtree)/usr/include
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX
index a7697783..c6beb5f 100644
--- a/Documentation/networking/00-INDEX
+++ b/Documentation/networking/00-INDEX
@@ -10,8 +10,6 @@
- GPLv2 for QLogic Linux qlge NIC Driver
LICENSE.qlcnic
- GPLv2 for QLogic Linux qlcnic NIC Driver
-Makefile
- - Makefile for docsrc.
PLIP.txt
- PLIP: The Parallel Line Internet Protocol device driver
README.ipw2100
diff --git a/Documentation/networking/Makefile b/Documentation/networking/Makefile
deleted file mode 100644
index 4c5d7c48..0000000
--- a/Documentation/networking/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-subdir-y := timestamping
diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt
index 6d6c07c..63912ef3 100644
--- a/Documentation/networking/dsa/dsa.txt
+++ b/Documentation/networking/dsa/dsa.txt
@@ -67,13 +67,14 @@
Switch tagging protocols
------------------------
-DSA currently supports 4 different tagging protocols, and a tag-less mode as
+DSA currently supports 5 different tagging protocols, and a tag-less mode as
well. The different protocols are implemented in:
net/dsa/tag_trailer.c: Marvell's 4 trailer tag mode (legacy)
net/dsa/tag_dsa.c: Marvell's original DSA tag
net/dsa/tag_edsa.c: Marvell's enhanced DSA tag
net/dsa/tag_brcm.c: Broadcom's 4 bytes tag
+net/dsa/tag_qca.c: Qualcomm's 2 bytes tag
The exact format of the tag protocol is vendor specific, but in general, they
all contain something which:
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 3db8c67..5af48dd 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -967,6 +967,21 @@
Default: 2 (as specified by RFC2236 8.1)
Minimum: 1 (as specified by RFC6636 4.5)
+force_igmp_version - INTEGER
+ 0 - (default) No enforcement of a IGMP version, IGMPv1/v2 fallback
+ allowed. Will back to IGMPv3 mode again if all IGMPv1/v2 Querier
+ Present timer expires.
+ 1 - Enforce to use IGMP version 1. Will also reply IGMPv1 report if
+ receive IGMPv2/v3 query.
+ 2 - Enforce to use IGMP version 2. Will fallback to IGMPv1 if receive
+ IGMPv1 query message. Will reply report if receive IGMPv3 query.
+ 3 - Enforce to use IGMP version 3. The same react with default 0.
+
+ Note: this is not the same with force_mld_version because IGMPv3 RFC3376
+ Security Considerations does not have clear description that we could
+ ignore other version messages completely as MLDv2 RFC3810. So make
+ this value as default 0 is recommended.
+
conf/interface/* changes special settings per interface (where
"interface" is the name of your network interface)
diff --git a/Documentation/networking/mac80211_hwsim/README b/Documentation/networking/mac80211_hwsim/README
index 24ac91d..3566a72 100644
--- a/Documentation/networking/mac80211_hwsim/README
+++ b/Documentation/networking/mac80211_hwsim/README
@@ -60,7 +60,7 @@
hostapd hostapd.conf
# Run wpa_supplicant (station) for wlan1
-wpa_supplicant -Dwext -iwlan1 -c wpa_supplicant.conf
+wpa_supplicant -Dnl80211 -iwlan1 -c wpa_supplicant.conf
More test cases are available in hostap.git:
diff --git a/Documentation/networking/netdev-FAQ.txt b/Documentation/networking/netdev-FAQ.txt
index 0fe1c6e..a20b2fa 100644
--- a/Documentation/networking/netdev-FAQ.txt
+++ b/Documentation/networking/netdev-FAQ.txt
@@ -29,8 +29,8 @@
Linus, and net-next is where the new code goes for the future release.
You can find the trees here:
- http://git.kernel.org/?p=linux/kernel/git/davem/net.git
- http://git.kernel.org/?p=linux/kernel/git/davem/net-next.git
+ https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git
+ https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git
Q: How often do changes from these trees make it to the mainline Linus tree?
@@ -76,7 +76,7 @@
A: Load the mainline (Linus) page here:
- http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git
+ https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
and note the top of the "tags" section. If it is rc1, it is early
in the dev cycle. If it was tagged rc7 a week ago, then a release
@@ -123,7 +123,7 @@
It contains the patches which Dave has selected, but not yet handed
off to Greg. If Greg already has the patch, then it will be here:
- http://git.kernel.org/cgit/linux/kernel/git/stable/stable-queue.git
+ https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git
A quick way to find whether the patch is in this stable-queue is
to simply clone the repo, and then git grep the mainline commit ID, e.g.
diff --git a/Documentation/networking/nf_conntrack-sysctl.txt b/Documentation/networking/nf_conntrack-sysctl.txt
index 4fb51d3..399e4e8 100644
--- a/Documentation/networking/nf_conntrack-sysctl.txt
+++ b/Documentation/networking/nf_conntrack-sysctl.txt
@@ -33,24 +33,6 @@
If this option is enabled, the connection tracking code will
provide userspace with connection tracking events via ctnetlink.
-nf_conntrack_events_retry_timeout - INTEGER (seconds)
- default 15
-
- This option is only relevant when "reliable connection tracking
- events" are used. Normally, ctnetlink is "lossy", that is,
- events are normally dropped when userspace listeners can't keep up.
-
- Userspace can request "reliable event mode". When this mode is
- active, the conntrack will only be destroyed after the event was
- delivered. If event delivery fails, the kernel periodically
- re-tries to send the event to userspace.
-
- This is the maximum interval the kernel should use when re-trying
- to deliver the destroy event.
-
- A higher number means there will be fewer delivery retries and it
- will take longer for a backlog to be processed.
-
nf_conntrack_expect_max - INTEGER
Maximum size of expectation table. Default value is
nf_conntrack_buckets / 256. Minimum is 1.
diff --git a/Documentation/networking/seg6-sysctl.txt b/Documentation/networking/seg6-sysctl.txt
new file mode 100644
index 0000000..bdbde23
--- /dev/null
+++ b/Documentation/networking/seg6-sysctl.txt
@@ -0,0 +1,18 @@
+/proc/sys/net/conf/<iface>/seg6_* variables:
+
+seg6_enabled - BOOL
+ Accept or drop SR-enabled IPv6 packets on this interface.
+
+ Relevant packets are those with SRH present and DA = local.
+
+ 0 - disabled (default)
+ not 0 - enabled
+
+seg6_require_hmac - INTEGER
+ Define HMAC policy for ingress SR-enabled packets on this interface.
+
+ -1 - Ignore HMAC field
+ 0 - Accept SR packets without HMAC, validate SR packets with HMAC
+ 1 - Drop SR packets without HMAC, validate SR packets with HMAC
+
+ Default is 0.
diff --git a/Documentation/networking/timestamping/Makefile b/Documentation/networking/timestamping/Makefile
deleted file mode 100644
index 8c20dfa..0000000
--- a/Documentation/networking/timestamping/Makefile
+++ /dev/null
@@ -1,14 +0,0 @@
-# To compile, from the source root
-#
-# make headers_install
-# make M=documentation
-
-# List of programs to build
-hostprogs-y := hwtstamp_config timestamping txtimestamp
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
-
-HOSTCFLAGS_timestamping.o += -I$(objtree)/usr/include
-HOSTCFLAGS_txtimestamp.o += -I$(objtree)/usr/include
-HOSTCFLAGS_hwtstamp_config.o += -I$(objtree)/usr/include
diff --git a/Documentation/pcmcia/Makefile b/Documentation/pcmcia/Makefile
deleted file mode 100644
index 47a8fa1..0000000
--- a/Documentation/pcmcia/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-# List of programs to build
-hostprogs-y := crc32hash
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
-
-HOSTCFLAGS_crc32hash.o += -I$(objtree)/usr/include
diff --git a/Documentation/pcmcia/devicetable.txt b/Documentation/pcmcia/devicetable.txt
index 199afd1..5f3e00a 100644
--- a/Documentation/pcmcia/devicetable.txt
+++ b/Documentation/pcmcia/devicetable.txt
@@ -27,7 +27,7 @@
The hex value after "pa" is the hash of product ID string 1, after "pb" for
string 2 and so on.
-Alternatively, you can use crc32hash (see Documentation/pcmcia/crc32hash.c)
+Alternatively, you can use crc32hash (see tools/pcmcia/crc32hash.c)
to determine the crc32 hash. Simply pass the string you want to evaluate
as argument to this program, e.g.:
-$ ./crc32hash "Dual Speed"
+$ tools/pcmcia/crc32hash "Dual Speed"
diff --git a/Documentation/prctl/Makefile b/Documentation/prctl/Makefile
deleted file mode 100644
index 44de308..0000000
--- a/Documentation/prctl/Makefile
+++ /dev/null
@@ -1,10 +0,0 @@
-ifndef CROSS_COMPILE
-# List of programs to build
-hostprogs-$(CONFIG_X86) := disable-tsc-ctxt-sw-stress-test disable-tsc-on-off-stress-test disable-tsc-test
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
-
-HOSTCFLAGS_disable-tsc-ctxt-sw-stress-test.o += -I$(objtree)/usr/include
-HOSTCFLAGS_disable-tsc-on-off-stress-test.o += -I$(objtree)/usr/include
-HOSTCFLAGS_disable-tsc-test.o += -I$(objtree)/usr/include
-endif
diff --git a/Documentation/ptp/Makefile b/Documentation/ptp/Makefile
deleted file mode 100644
index 293d6c0..0000000
--- a/Documentation/ptp/Makefile
+++ /dev/null
@@ -1,8 +0,0 @@
-# List of programs to build
-hostprogs-y := testptp
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
-
-HOSTCFLAGS_testptp.o += -I$(objtree)/usr/include
-HOSTLOADLIBES_testptp := -lrt
diff --git a/Documentation/scsi/g_NCR5380.txt b/Documentation/scsi/g_NCR5380.txt
index fd88015..e2c1879 100644
--- a/Documentation/scsi/g_NCR5380.txt
+++ b/Documentation/scsi/g_NCR5380.txt
@@ -21,16 +21,6 @@
The NCR53c400 does not support DMA but it does have Pseudo-DMA which is
supported by the driver.
-If the default configuration does not work for you, you can use the kernel
-command lines (eg using the lilo append command):
- ncr5380=addr,irq
- ncr53c400=addr,irq
- ncr53c400a=addr,irq
- dtc3181e=addr,irq
-
-The driver does not probe for any addresses or ports other than those in
-the OVERRIDE or given to the kernel as above.
-
This driver provides some information on what it has detected in
/proc/scsi/g_NCR5380/x where x is the scsi card number as detected at boot
time. More info to come in the future.
@@ -38,6 +28,16 @@
This driver works as a module.
When included as a module, parameters can be passed on the insmod/modprobe
command line:
+ irq=xx[,...] the interrupt(s)
+ base=xx[,...] the port or base address(es) (for port or memory mapped, resp.)
+ card=xx[,...] card type(s):
+ 0 = NCR5380,
+ 1 = NCR53C400,
+ 2 = NCR53C400A,
+ 3 = Domex Technology Corp 3181E (DTC3181E)
+ 4 = Hewlett Packard C2502
+
+These old-style parameters can support only one card:
ncr_irq=xx the interrupt
ncr_addr=xx the port or base address (for port or memory
mapped, resp.)
@@ -46,11 +46,19 @@
ncr_53c400a=1 to set up for a NCR53C400A board
dtc_3181e=1 to set up for a Domex Technology Corp 3181E board
hp_c2502=1 to set up for a Hewlett Packard C2502 board
+
e.g.
-modprobe g_NCR5380 ncr_irq=5 ncr_addr=0x350 ncr_5380=1
+OLD: modprobe g_NCR5380 ncr_irq=5 ncr_addr=0x350 ncr_5380=1
+NEW: modprobe g_NCR5380 irq=5 base=0x350 card=0
for a port mapped NCR5380 board or
-modprobe g_NCR5380 ncr_irq=255 ncr_addr=0xc8000 ncr_53c400=1
- for a memory mapped NCR53C400 board with interrupts disabled.
+
+OLD: modprobe g_NCR5380 ncr_irq=255 ncr_addr=0xc8000 ncr_53c400=1
+NEW: modprobe g_NCR5380 irq=255 base=0xc8000 card=1
+ for a memory mapped NCR53C400 board with interrupts disabled or
+
+NEW: modprobe g_NCR5380 irq=0,7 base=0x240,0x300 card=3,4
+ for two cards: DTC3181 (in non-PnP mode) at 0x240 with no IRQ
+ and HP C2502 at 0x300 with IRQ 7
(255 should be specified for no or DMA interrupt, 254 to autoprobe for an
IRQ line if overridden on the command line.)
diff --git a/Documentation/spi/00-INDEX b/Documentation/spi/00-INDEX
index 4644bf0..8e4bb17 100644
--- a/Documentation/spi/00-INDEX
+++ b/Documentation/spi/00-INDEX
@@ -1,7 +1,5 @@
00-INDEX
- this file.
-Makefile
- - Makefile for the example sourcefiles.
butterfly
- AVR Butterfly SPI driver overview and pin configuration.
ep93xx_spi
diff --git a/Documentation/timers/00-INDEX b/Documentation/timers/00-INDEX
index ee212a2..3be05fe 100644
--- a/Documentation/timers/00-INDEX
+++ b/Documentation/timers/00-INDEX
@@ -4,12 +4,8 @@
- High resolution timers and dynamic ticks design notes
hpet.txt
- High Precision Event Timer Driver for Linux
-hpet_example.c
- - sample hpet timer test program
hrtimers.txt
- subsystem for high-resolution kernel timers
-Makefile
- - Build and link hpet_example
NO_HZ.txt
- Summary of the different methods for the scheduler clock-interrupts management.
timekeeping.txt
diff --git a/Documentation/timers/Makefile b/Documentation/timers/Makefile
deleted file mode 100644
index 6c09ee6..0000000
--- a/Documentation/timers/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-# List of programs to build
-hostprogs-$(CONFIG_X86) := hpet_example
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
diff --git a/Documentation/timers/hpet.txt b/Documentation/timers/hpet.txt
index a484d2c..895345e 100644
--- a/Documentation/timers/hpet.txt
+++ b/Documentation/timers/hpet.txt
@@ -25,4 +25,4 @@
The driver provides a userspace API which resembles the API found in the
RTC driver framework. An example user space program is provided in
-file:Documentation/timers/hpet_example.c
+file:samples/timers/hpet_example.c
diff --git a/Documentation/vDSO/Makefile b/Documentation/vDSO/Makefile
deleted file mode 100644
index b12e987..0000000
--- a/Documentation/vDSO/Makefile
+++ /dev/null
@@ -1,17 +0,0 @@
-ifndef CROSS_COMPILE
-# vdso_test won't build for glibc < 2.16, so disable it
-# hostprogs-y := vdso_test
-hostprogs-$(CONFIG_X86) := vdso_standalone_test_x86
-vdso_standalone_test_x86-objs := vdso_standalone_test_x86.o parse_vdso.o
-vdso_test-objs := parse_vdso.o vdso_test.o
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
-
-HOSTCFLAGS := -I$(objtree)/usr/include -std=gnu99
-HOSTCFLAGS_vdso_standalone_test_x86.o := -fno-asynchronous-unwind-tables -fno-stack-protector
-HOSTLOADLIBES_vdso_standalone_test_x86 := -nostdlib
-ifeq ($(CONFIG_X86_32),y)
-HOSTLOADLIBES_vdso_standalone_test_x86 += -lgcc_s
-endif
-endif
diff --git a/Documentation/virtual/kvm/locking.txt b/Documentation/virtual/kvm/locking.txt
index f2491a8..e5dd9f4 100644
--- a/Documentation/virtual/kvm/locking.txt
+++ b/Documentation/virtual/kvm/locking.txt
@@ -4,7 +4,17 @@
1. Acquisition Orders
---------------------
-(to be written)
+The acquisition orders for mutexes are as follows:
+
+- kvm->lock is taken outside vcpu->mutex
+
+- kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock
+
+- kvm->slots_lock is taken outside kvm->irq_lock, though acquiring
+ them together is quite rare.
+
+For spinlocks, kvm_lock is taken outside kvm->mmu_lock. Everything
+else is a leaf: no other lock is taken inside the critical sections.
2: Exception
------------
diff --git a/Documentation/watchdog/Makefile b/Documentation/watchdog/Makefile
deleted file mode 100644
index 6018f45..0000000
--- a/Documentation/watchdog/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-subdir-y := src
diff --git a/Documentation/watchdog/src/.gitignore b/Documentation/watchdog/src/.gitignore
deleted file mode 100644
index ac90997..0000000
--- a/Documentation/watchdog/src/.gitignore
+++ /dev/null
@@ -1,2 +0,0 @@
-watchdog-simple
-watchdog-test
diff --git a/Documentation/watchdog/src/Makefile b/Documentation/watchdog/src/Makefile
deleted file mode 100644
index 4a892c3..0000000
--- a/Documentation/watchdog/src/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-# List of programs to build
-hostprogs-y := watchdog-simple watchdog-test
-
-# Tell kbuild to always build the programs
-always := $(hostprogs-y)
diff --git a/Documentation/watchdog/watchdog-api.txt b/Documentation/watchdog/watchdog-api.txt
index b3a701f..0e62ba3 100644
--- a/Documentation/watchdog/watchdog-api.txt
+++ b/Documentation/watchdog/watchdog-api.txt
@@ -37,7 +37,7 @@
the watchdog is pinged within a certain time, this time is called the
timeout or margin. The simplest way to ping the watchdog is to write
some data to the device. So a very simple watchdog daemon would look
-like this source file: see Documentation/watchdog/src/watchdog-simple.c
+like this source file: see samples/watchdog/watchdog-simple.c
A more advanced driver could for example check that a HTTP server is
still responding before doing the write call to ping the watchdog.
diff --git a/Documentation/watchdog/wdt.txt b/Documentation/watchdog/wdt.txt
index 061c2e3..ed2f0b8 100644
--- a/Documentation/watchdog/wdt.txt
+++ b/Documentation/watchdog/wdt.txt
@@ -47,4 +47,4 @@
Minor numbers are however allocated for it.
-Example Watchdog Driver: see Documentation/watchdog/src/watchdog-simple.c
+Example Watchdog Driver: see samples/watchdog/watchdog-simple.c
diff --git a/MAINTAINERS b/MAINTAINERS
index f18b546..9870812 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -316,6 +316,14 @@
S: Supported
F: drivers/acpi/fan.c
+ACPI FOR ARM64 (ACPI/arm64)
+M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+M: Hanjun Guo <hanjun.guo@linaro.org>
+M: Sudeep Holla <sudeep.holla@arm.com>
+L: linux-acpi@vger.kernel.org
+S: Maintained
+F: drivers/acpi/arm64
+
ACPI THERMAL DRIVER
M: Zhang Rui <rui.zhang@intel.com>
L: linux-acpi@vger.kernel.org
@@ -1434,6 +1442,7 @@
F: arch/arm/configs/mvebu_*_defconfig
ARM/Marvell Berlin SoC support
+M: Jisheng Zhang <jszhang@marvell.com>
M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
@@ -2545,15 +2554,18 @@
F: drivers/net/ethernet/broadcom/genet/
BROADCOM BNX2 GIGABIT ETHERNET DRIVER
-M: Sony Chacko <sony.chacko@qlogic.com>
-M: Dept-HSGLinuxNICDev@qlogic.com
+M: Rasesh Mody <rasesh.mody@cavium.com>
+M: Harish Patil <harish.patil@cavium.com>
+M: Dept-GELinuxNICDev@cavium.com
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/broadcom/bnx2.*
F: drivers/net/ethernet/broadcom/bnx2_*
BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER
-M: Ariel Elior <ariel.elior@qlogic.com>
+M: Yuval Mintz <Yuval.Mintz@cavium.com>
+M: Ariel Elior <ariel.elior@cavium.com>
+M: everest-linux-l2@cavium.com
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/broadcom/bnx2x/
@@ -2760,7 +2772,9 @@
F: drivers/scsi/bfa/
BROCADE BNA 10 GIGABIT ETHERNET DRIVER
-M: Rasesh Mody <rasesh.mody@qlogic.com>
+M: Rasesh Mody <rasesh.mody@cavium.com>
+M: Sudarsana Kalluru <sudarsana.kalluru@cavium.com>
+M: Dept-GELinuxNICDev@cavium.com
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/brocade/bna/
@@ -4614,8 +4628,9 @@
EXTENSIBLE FIRMWARE INTERFACE (EFI)
M: Matt Fleming <matt@codeblueprint.co.uk>
+M: Ard Biesheuvel <ard.biesheuvel@linaro.org>
L: linux-efi@vger.kernel.org
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/efi.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi.git
S: Maintained
F: Documentation/efi-stub.txt
F: arch/ia64/kernel/efi.c
@@ -5280,6 +5295,12 @@
S: Maintained
F: scripts/get_maintainer.pl
+GENWQE (IBM Generic Workqueue Card)
+M: Frank Haverkamp <haver@linux.vnet.ibm.com>
+M: Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com>
+S: Supported
+F: drivers/misc/genwqe/
+
GFS2 FILE SYSTEM
M: Steven Whitehouse <swhiteho@redhat.com>
M: Bob Peterson <rpeterso@redhat.com>
@@ -6125,6 +6146,12 @@
S: Maintained
F: drivers/usb/atm/ueagle-atm.c
+IMGTEC ASCII LCD DRIVER
+M: Paul Burton <paul.burton@imgtec.com>
+S: Maintained
+F: Documentation/devicetree/bindings/auxdisplay/img-ascii-lcd.txt
+F: drivers/auxdisplay/img-ascii-lcd.c
+
INA209 HARDWARE MONITOR DRIVER
M: Guenter Roeck <linux@roeck-us.net>
L: linux-hwmon@vger.kernel.org
@@ -6436,6 +6463,7 @@
F: drivers/misc/mei/*
F: drivers/watchdog/mei_wdt.c
F: Documentation/misc-devices/mei/*
+F: samples/mei/*
INTEL MIC DRIVERS (mic)
M: Sudeep Dutt <sudeep.dutt@intel.com>
@@ -6622,10 +6650,10 @@
F: drivers/firmware/iscsi_ibft*
ISCSI
-M: Mike Christie <michaelc@cs.wisc.edu>
+M: Lee Duncan <lduncan@suse.com>
+M: Chris Leech <cleech@redhat.com>
L: open-iscsi@googlegroups.com
-W: www.open-iscsi.org
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/mnc/linux-2.6-iscsi.git
+W: www.open-iscsi.com
S: Maintained
F: drivers/scsi/*iscsi*
F: include/scsi/*iscsi*
@@ -7203,17 +7231,11 @@
F: include/linux/lightnvm.h
F: include/uapi/linux/lightnvm.h
-LINUX FOR IBM pSERIES (RS/6000)
-M: Paul Mackerras <paulus@au.ibm.com>
-W: http://www.ibm.com/linux/ltc/projects/ppc
-S: Supported
-F: arch/powerpc/boot/rs6000.h
-
LINUX FOR POWERPC (32-BIT AND 64-BIT)
M: Benjamin Herrenschmidt <benh@kernel.crashing.org>
M: Paul Mackerras <paulus@samba.org>
M: Michael Ellerman <mpe@ellerman.id.au>
-W: http://www.penguinppc.org/
+W: https://github.com/linuxppc/linux/wiki
L: linuxppc-dev@lists.ozlabs.org
Q: http://patchwork.ozlabs.org/project/linuxppc-dev/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git
@@ -7228,6 +7250,7 @@
F: drivers/pci/hotplug/pnv_php.c
F: drivers/pci/hotplug/rpa*
F: drivers/scsi/ibmvscsi/
+F: tools/testing/selftests/powerpc
N: opal
N: /pmac
N: powermac
@@ -7284,9 +7307,8 @@
F: arch/powerpc/platforms/85xx/
LINUX FOR POWERPC PA SEMI PWRFICIENT
-M: Olof Johansson <olof@lixom.net>
L: linuxppc-dev@lists.ozlabs.org
-S: Maintained
+S: Orphan
F: arch/powerpc/platforms/pasemi/
F: drivers/*/*pasemi*
F: drivers/*/*/*pasemi*
@@ -7829,6 +7851,13 @@
F: drivers/scsi/megaraid.*
F: drivers/scsi/megaraid/
+MELFAS MIP4 TOUCHSCREEN DRIVER
+M: Sangwon Jee <jeesw@melfas.com>
+W: http://www.melfas.com
+S: Supported
+F: drivers/input/touchscreen/melfas_mip4.c
+F: Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt
+
MELLANOX ETHERNET DRIVER (mlx4_en)
M: Tariq Toukan <tariqt@mellanox.com>
L: netdev@vger.kernel.org
@@ -7898,6 +7927,10 @@
MEMORY TECHNOLOGY DEVICES (MTD)
M: David Woodhouse <dwmw2@infradead.org>
M: Brian Norris <computersforpeace@gmail.com>
+M: Boris Brezillon <boris.brezillon@free-electrons.com>
+M: Marek Vasut <marek.vasut@gmail.com>
+M: Richard Weinberger <richard@nod.at>
+M: Cyrille Pitchen <cyrille.pitchen@atmel.com>
L: linux-mtd@lists.infradead.org
W: http://www.linux-mtd.infradead.org/
Q: http://patchwork.ozlabs.org/project/linux-mtd/list/
@@ -8026,6 +8059,7 @@
F: include/linux/mlx4/
MELLANOX MLX5 core VPI driver
+M: Saeed Mahameed <saeedm@mellanox.com>
M: Matan Barak <matanb@mellanox.com>
M: Leon Romanovsky <leonro@mellanox.com>
L: netdev@vger.kernel.org
@@ -8085,6 +8119,7 @@
F: drivers/media/dvb-frontends/mn88473*
MODULE SUPPORT
+M: Jessica Yu <jeyu@redhat.com>
M: Rusty Russell <rusty@rustcorp.com.au>
S: Maintained
F: include/linux/module.h
@@ -8198,7 +8233,7 @@
MULTIMEDIA CARD (MMC), SECURE DIGITAL (SD) AND SDIO SUBSYSTEM
M: Ulf Hansson <ulf.hansson@linaro.org>
L: linux-mmc@vger.kernel.org
-T: git git://git.linaro.org/people/ulf.hansson/mmc.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc.git
S: Maintained
F: Documentation/devicetree/bindings/mmc/
F: drivers/mmc/
@@ -8493,11 +8528,10 @@
F: drivers/net/wireless/
NETXEN (1/10) GbE SUPPORT
-M: Manish Chopra <manish.chopra@qlogic.com>
-M: Sony Chacko <sony.chacko@qlogic.com>
-M: Rajesh Borundia <rajesh.borundia@qlogic.com>
+M: Manish Chopra <manish.chopra@cavium.com>
+M: Rahul Verma <rahul.verma@cavium.com>
+M: Dept-GELinuxNICDev@cavium.com
L: netdev@vger.kernel.org
-W: http://www.qlogic.com
S: Supported
F: drivers/net/ethernet/qlogic/netxen/
@@ -9020,15 +9054,13 @@
F: drivers/net/wireless/intersil/p54/
PA SEMI ETHERNET DRIVER
-M: Olof Johansson <olof@lixom.net>
L: netdev@vger.kernel.org
-S: Maintained
+S: Orphan
F: drivers/net/ethernet/pasemi/*
PA SEMI SMBUS DRIVER
-M: Olof Johansson <olof@lixom.net>
L: linux-i2c@vger.kernel.org
-S: Maintained
+S: Orphan
F: drivers/i2c/busses/i2c-pasemi.c
PADATA PARALLEL EXECUTION MECHANISM
@@ -9286,7 +9318,7 @@
F: drivers/pci/host/*designware*
PCI DRIVER FOR SYNOPSYS PROTOTYPING DEVICE
-M: Joao Pinto <jpinto@synopsys.com>
+M: Jose Abreu <Jose.Abreu@synopsys.com>
L: linux-pci@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/pci/designware-pcie.txt
@@ -9305,7 +9337,7 @@
M: Keith Busch <keith.busch@intel.com>
L: linux-pci@vger.kernel.org
S: Supported
-F: arch/x86/pci/vmd.c
+F: drivers/pci/host/vmd.c
PCIE DRIVER FOR ST SPEAR13XX
M: Pratyush Anand <pratyush.anand@gmail.com>
@@ -9377,6 +9409,7 @@
T: git git://git.kernel.org/pub/scm/linux/kernel/git/brodo/pcmcia.git
S: Maintained
F: Documentation/pcmcia/
+F: tools/pcmcia/
F: drivers/pcmcia/
F: include/pcmcia/
@@ -9874,33 +9907,32 @@
F: drivers/scsi/qla4xxx/
QLOGIC QLA3XXX NETWORK DRIVER
-M: Jitendra Kalsaria <jitendra.kalsaria@qlogic.com>
-M: Ron Mercer <ron.mercer@qlogic.com>
-M: linux-driver@qlogic.com
+M: Dept-GELinuxNICDev@cavium.com
L: netdev@vger.kernel.org
S: Supported
F: Documentation/networking/LICENSE.qla3xxx
F: drivers/net/ethernet/qlogic/qla3xxx.*
QLOGIC QLCNIC (1/10)Gb ETHERNET DRIVER
-M: Dept-GELinuxNICDev@qlogic.com
+M: Harish Patil <harish.patil@cavium.com>
+M: Manish Chopra <manish.chopra@cavium.com>
+M: Dept-GELinuxNICDev@cavium.com
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/qlogic/qlcnic/
QLOGIC QLGE 10Gb ETHERNET DRIVER
-M: Harish Patil <harish.patil@qlogic.com>
-M: Sudarsana Kalluru <sudarsana.kalluru@qlogic.com>
-M: Dept-GELinuxNICDev@qlogic.com
-M: linux-driver@qlogic.com
+M: Harish Patil <harish.patil@cavium.com>
+M: Manish Chopra <manish.chopra@cavium.com>
+M: Dept-GELinuxNICDev@cavium.com
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/qlogic/qlge/
QLOGIC QL4xxx ETHERNET DRIVER
-M: Yuval Mintz <Yuval.Mintz@qlogic.com>
-M: Ariel Elior <Ariel.Elior@qlogic.com>
-M: everest-linux-l2@qlogic.com
+M: Yuval Mintz <Yuval.Mintz@cavium.com>
+M: Ariel Elior <Ariel.Elior@cavium.com>
+M: everest-linux-l2@cavium.com
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/qlogic/qed/
@@ -11378,6 +11410,17 @@
S: Maintained
F: drivers/clk/spear/
+SPI NOR SUBSYSTEM
+M: Cyrille Pitchen <cyrille.pitchen@atmel.com>
+M: Marek Vasut <marek.vasut@gmail.com>
+L: linux-mtd@lists.infradead.org
+W: http://www.linux-mtd.infradead.org/
+Q: http://patchwork.ozlabs.org/project/linux-mtd/list/
+T: git git://github.com/spi-nor/linux.git
+S: Maintained
+F: drivers/mtd/spi-nor/
+F: include/linux/mtd/spi-nor.h
+
SPI SUBSYSTEM
M: Mark Brown <broonie@kernel.org>
L: linux-spi@vger.kernel.org
@@ -12757,6 +12800,7 @@
VIRTIO CORE, NET AND BLOCK DRIVERS
M: "Michael S. Tsirkin" <mst@redhat.com>
+M: Jason Wang <jasowang@redhat.com>
L: virtualization@lists.linux-foundation.org
S: Maintained
F: Documentation/devicetree/bindings/virtio/
@@ -12787,6 +12831,7 @@
VIRTIO HOST (VHOST)
M: "Michael S. Tsirkin" <mst@redhat.com>
+M: Jason Wang <jasowang@redhat.com>
L: kvm@vger.kernel.org
L: virtualization@lists.linux-foundation.org
L: netdev@vger.kernel.org
diff --git a/Makefile b/Makefile
index 27f97b5..247430a 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 4
-PATCHLEVEL = 8
+PATCHLEVEL = 9
SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc5
NAME = Psychotic Stoned Sheep
# *DOCUMENTATION*
@@ -370,7 +370,7 @@
CFLAGS_KERNEL =
AFLAGS_KERNEL =
LDFLAGS_vmlinux =
-CFLAGS_GCOV = -fprofile-arcs -ftest-coverage -fno-tree-loop-im
+CFLAGS_GCOV = -fprofile-arcs -ftest-coverage -fno-tree-loop-im -Wno-maybe-uninitialized
CFLAGS_KCOV := $(call cc-option,-fsanitize-coverage=trace-pc,)
@@ -620,19 +620,26 @@
include arch/$(SRCARCH)/Makefile
KBUILD_CFLAGS += $(call cc-option,-fno-delete-null-pointer-checks,)
-KBUILD_CFLAGS += $(call cc-disable-warning,maybe-uninitialized,)
KBUILD_CFLAGS += $(call cc-disable-warning,frame-address,)
+ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
+KBUILD_CFLAGS += $(call cc-option,-ffunction-sections,)
+KBUILD_CFLAGS += $(call cc-option,-fdata-sections,)
+endif
+
ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
-KBUILD_CFLAGS += -Os
+KBUILD_CFLAGS += -Os $(call cc-disable-warning,maybe-uninitialized,)
else
ifdef CONFIG_PROFILE_ALL_BRANCHES
-KBUILD_CFLAGS += -O2
+KBUILD_CFLAGS += -O2 $(call cc-disable-warning,maybe-uninitialized,)
else
KBUILD_CFLAGS += -O2
endif
endif
+KBUILD_CFLAGS += $(call cc-ifversion, -lt, 0409, \
+ $(call cc-disable-warning,maybe-uninitialized,))
+
# Tell gcc to never replace conditional load with a non-conditional one
KBUILD_CFLAGS += $(call cc-option,--param=allow-store-data-races=0)
@@ -803,6 +810,10 @@
KBUILD_LDFLAGS_MODULE += $(LDFLAGS_BUILD_ID)
LDFLAGS_vmlinux += $(LDFLAGS_BUILD_ID)
+ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
+LDFLAGS_vmlinux += $(call ld-option, --gc-sections,)
+endif
+
ifeq ($(CONFIG_STRIP_ASM_SYMS),y)
LDFLAGS_vmlinux += $(call ld-option, -X,)
endif
@@ -927,9 +938,6 @@
ifdef CONFIG_HEADERS_CHECK
$(Q)$(MAKE) -f $(srctree)/Makefile headers_check
endif
-ifdef CONFIG_BUILD_DOCSRC
- $(Q)$(MAKE) $(build)=Documentation
-endif
ifdef CONFIG_GDB_SCRIPTS
$(Q)ln -fsn `cd $(srctree) && /bin/pwd`/scripts/gdb/vmlinux-gdb.py
endif
@@ -942,9 +950,12 @@
include/generated/autoksyms.h: FORCE
$(Q)$(CONFIG_SHELL) $(srctree)/scripts/adjust_autoksyms.sh true
-# Final link of vmlinux
- cmd_link-vmlinux = $(CONFIG_SHELL) $< $(LD) $(LDFLAGS) $(LDFLAGS_vmlinux)
-quiet_cmd_link-vmlinux = LINK $@
+ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink)
+
+# Final link of vmlinux with optional arch pass after final link
+ cmd_link-vmlinux = \
+ $(CONFIG_SHELL) $< $(LD) $(LDFLAGS) $(LDFLAGS_vmlinux) ; \
+ $(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
vmlinux: scripts/link-vmlinux.sh vmlinux_prereq $(vmlinux-deps) FORCE
+$(call if_changed,link-vmlinux)
@@ -1271,6 +1282,7 @@
vmlinuxclean:
$(Q)$(CONFIG_SHELL) $(srctree)/scripts/link-vmlinux.sh clean
+ $(Q)$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) clean)
clean: archclean vmlinuxclean
diff --git a/arch/Kconfig b/arch/Kconfig
index 180ea33..659bdd0 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -383,6 +383,24 @@
gcc-4.5 on). It is based on the commit "Add fuzzing coverage support"
by Dmitry Vyukov <dvyukov@google.com>.
+config GCC_PLUGIN_LATENT_ENTROPY
+ bool "Generate some entropy during boot and runtime"
+ depends on GCC_PLUGINS
+ help
+ By saying Y here the kernel will instrument some kernel code to
+ extract some entropy from both original and artificially created
+ program state. This will help especially embedded systems where
+ there is little 'natural' source of entropy normally. The cost
+ is some slowdown of the boot process (about 0.5%) and fork and
+ irq processing.
+
+ Note that entropy extracted this way is not cryptographically
+ secure!
+
+ This plugin was ported from grsecurity/PaX. More information at:
+ * https://grsecurity.net/
+ * https://pax.grsecurity.net/
+
config HAVE_CC_STACKPROTECTOR
bool
help
@@ -450,6 +468,27 @@
endchoice
+config THIN_ARCHIVES
+ bool
+ help
+ Select this if the architecture wants to use thin archives
+ instead of ld -r to create the built-in.o files.
+
+config LD_DEAD_CODE_DATA_ELIMINATION
+ bool
+ help
+ Select this if the architecture wants to do dead code and
+ data elimination with the linker by compiling with
+ -ffunction-sections -fdata-sections and linking with
+ --gc-sections.
+
+ This requires that the arch annotates or otherwise protects
+ its external entry points from being discarded. Linker scripts
+ must also merge .text.*, .data.*, and .bss.* correctly into
+ output sections. Care must be taken not to pull in unrelated
+ sections (e.g., '.text.init'). Typically '.' in section names
+ is used to distinguish them from label names / C identifiers.
+
config HAVE_ARCH_WITHIN_STACK_FRAMES
bool
help
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index ffd9cf5..bf8475c 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -3,6 +3,7 @@
generic-y += clkdev.h
generic-y += cputime.h
generic-y += exec.h
+generic-y += export.h
generic-y += irq_work.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h
index 466e42e..94f5875 100644
--- a/arch/alpha/include/asm/uaccess.h
+++ b/arch/alpha/include/asm/uaccess.h
@@ -396,11 +396,12 @@ copy_to_user(void __user *to, const void *from, long n)
extern inline long
copy_from_user(void *to, const void __user *from, long n)
{
+ long res = n;
if (likely(__access_ok((unsigned long)from, n, get_fs())))
- n = __copy_tofrom_user_nocheck(to, (__force void *)from, n);
- else
- memset(to, 0, n);
- return n;
+ res = __copy_from_user_inatomic(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
extern void __do_clear_user(void);
diff --git a/arch/alpha/kernel/Makefile b/arch/alpha/kernel/Makefile
index 3ecac01..8ce13d7 100644
--- a/arch/alpha/kernel/Makefile
+++ b/arch/alpha/kernel/Makefile
@@ -8,7 +8,7 @@
obj-y := entry.o traps.o process.o osf_sys.o irq.o \
irq_alpha.o signal.o setup.o ptrace.o time.o \
- alpha_ksyms.o systbls.o err_common.o io.o
+ systbls.o err_common.o io.o
obj-$(CONFIG_VGA_HOSE) += console.o
obj-$(CONFIG_SMP) += smp.o
diff --git a/arch/alpha/kernel/alpha_ksyms.c b/arch/alpha/kernel/alpha_ksyms.c
deleted file mode 100644
index f4c7ab6..0000000
--- a/arch/alpha/kernel/alpha_ksyms.c
+++ /dev/null
@@ -1,102 +0,0 @@
-/*
- * linux/arch/alpha/kernel/alpha_ksyms.c
- *
- * Export the alpha-specific functions that are needed for loadable
- * modules.
- */
-
-#include <linux/module.h>
-#include <asm/console.h>
-#include <asm/uaccess.h>
-#include <asm/checksum.h>
-#include <asm/fpu.h>
-#include <asm/machvec.h>
-
-#include <linux/syscalls.h>
-
-/* these are C runtime functions with special calling conventions: */
-extern void __divl (void);
-extern void __reml (void);
-extern void __divq (void);
-extern void __remq (void);
-extern void __divlu (void);
-extern void __remlu (void);
-extern void __divqu (void);
-extern void __remqu (void);
-
-EXPORT_SYMBOL(alpha_mv);
-EXPORT_SYMBOL(callback_getenv);
-EXPORT_SYMBOL(callback_setenv);
-EXPORT_SYMBOL(callback_save_env);
-
-/* platform dependent support */
-EXPORT_SYMBOL(strcat);
-EXPORT_SYMBOL(strcpy);
-EXPORT_SYMBOL(strlen);
-EXPORT_SYMBOL(strncpy);
-EXPORT_SYMBOL(strncat);
-EXPORT_SYMBOL(strchr);
-EXPORT_SYMBOL(strrchr);
-EXPORT_SYMBOL(memmove);
-EXPORT_SYMBOL(__memcpy);
-EXPORT_SYMBOL(__memset);
-EXPORT_SYMBOL(___memset);
-EXPORT_SYMBOL(__memsetw);
-EXPORT_SYMBOL(__constant_c_memset);
-EXPORT_SYMBOL(copy_page);
-EXPORT_SYMBOL(clear_page);
-
-EXPORT_SYMBOL(alpha_read_fp_reg);
-EXPORT_SYMBOL(alpha_read_fp_reg_s);
-EXPORT_SYMBOL(alpha_write_fp_reg);
-EXPORT_SYMBOL(alpha_write_fp_reg_s);
-
-/* Networking helper routines. */
-EXPORT_SYMBOL(csum_tcpudp_magic);
-EXPORT_SYMBOL(ip_compute_csum);
-EXPORT_SYMBOL(ip_fast_csum);
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
-EXPORT_SYMBOL(csum_partial_copy_from_user);
-EXPORT_SYMBOL(csum_ipv6_magic);
-
-#ifdef CONFIG_MATHEMU_MODULE
-extern long (*alpha_fp_emul_imprecise)(struct pt_regs *, unsigned long);
-extern long (*alpha_fp_emul) (unsigned long pc);
-EXPORT_SYMBOL(alpha_fp_emul_imprecise);
-EXPORT_SYMBOL(alpha_fp_emul);
-#endif
-
-/*
- * The following are specially called from the uaccess assembly stubs.
- */
-EXPORT_SYMBOL(__copy_user);
-EXPORT_SYMBOL(__do_clear_user);
-
-/*
- * SMP-specific symbols.
- */
-
-#ifdef CONFIG_SMP
-EXPORT_SYMBOL(_atomic_dec_and_lock);
-#endif /* CONFIG_SMP */
-
-/*
- * The following are special because they're not called
- * explicitly (the C compiler or assembler generates them in
- * response to division operations). Fortunately, their
- * interface isn't gonna change any time soon now, so it's OK
- * to leave it out of version control.
- */
-# undef memcpy
-# undef memset
-EXPORT_SYMBOL(__divl);
-EXPORT_SYMBOL(__divlu);
-EXPORT_SYMBOL(__divq);
-EXPORT_SYMBOL(__divqu);
-EXPORT_SYMBOL(__reml);
-EXPORT_SYMBOL(__remlu);
-EXPORT_SYMBOL(__remq);
-EXPORT_SYMBOL(__remqu);
-EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memchr);
diff --git a/arch/alpha/kernel/machvec_impl.h b/arch/alpha/kernel/machvec_impl.h
index d3398f6a..b7d6960 100644
--- a/arch/alpha/kernel/machvec_impl.h
+++ b/arch/alpha/kernel/machvec_impl.h
@@ -144,9 +144,11 @@
else beforehand. Fine. We'll do it ourselves. */
#if 0
#define ALIAS_MV(system) \
- struct alpha_machine_vector alpha_mv __attribute__((alias(#system "_mv")));
+ struct alpha_machine_vector alpha_mv __attribute__((alias(#system "_mv"))); \
+ EXPORT_SYMBOL(alpha_mv);
#else
#define ALIAS_MV(system) \
- asm(".global alpha_mv\nalpha_mv = " #system "_mv");
+ asm(".global alpha_mv\nalpha_mv = " #system "_mv"); \
+ EXPORT_SYMBOL(alpha_mv);
#endif
#endif /* GENERIC */
diff --git a/arch/alpha/kernel/ptrace.c b/arch/alpha/kernel/ptrace.c
index d9ee817..940dfb4 100644
--- a/arch/alpha/kernel/ptrace.c
+++ b/arch/alpha/kernel/ptrace.c
@@ -157,14 +157,16 @@ put_reg(struct task_struct *task, unsigned long regno, unsigned long data)
static inline int
read_int(struct task_struct *task, unsigned long addr, int * data)
{
- int copied = access_process_vm(task, addr, data, sizeof(int), 0);
+ int copied = access_process_vm(task, addr, data, sizeof(int),
+ FOLL_FORCE);
return (copied == sizeof(int)) ? 0 : -EIO;
}
static inline int
write_int(struct task_struct *task, unsigned long addr, int data)
{
- int copied = access_process_vm(task, addr, &data, sizeof(int), 1);
+ int copied = access_process_vm(task, addr, &data, sizeof(int),
+ FOLL_FORCE | FOLL_WRITE);
return (copied == sizeof(int)) ? 0 : -EIO;
}
@@ -281,7 +283,8 @@ long arch_ptrace(struct task_struct *child, long request,
/* When I and D space are separate, these will need to be fixed. */
case PTRACE_PEEKTEXT: /* read word at location addr. */
case PTRACE_PEEKDATA:
- copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
+ copied = access_process_vm(child, addr, &tmp, sizeof(tmp),
+ FOLL_FORCE);
ret = -EIO;
if (copied != sizeof(tmp))
break;
diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c
index b20af76..4811e54 100644
--- a/arch/alpha/kernel/setup.c
+++ b/arch/alpha/kernel/setup.c
@@ -115,6 +115,7 @@ unsigned long alpha_agpgart_size = DEFAULT_AGP_APER_SIZE;
#ifdef CONFIG_ALPHA_GENERIC
struct alpha_machine_vector alpha_mv;
+EXPORT_SYMBOL(alpha_mv);
#endif
#ifndef alpha_using_srm
diff --git a/arch/alpha/lib/callback_srm.S b/arch/alpha/lib/callback_srm.S
index 8804bec..6093add 100644
--- a/arch/alpha/lib/callback_srm.S
+++ b/arch/alpha/lib/callback_srm.S
@@ -3,6 +3,7 @@
*/
#include <asm/console.h>
+#include <asm/export.h>
.text
#define HWRPB_CRB_OFFSET 0xc0
@@ -92,6 +93,10 @@
CALLBACK(save_env, CCB_SAVE_ENV, 1)
CALLBACK(pswitch, CCB_PSWITCH, 3)
CALLBACK(bios_emul, CCB_BIOS_EMUL, 5)
+
+EXPORT_SYMBOL(callback_getenv)
+EXPORT_SYMBOL(callback_setenv)
+EXPORT_SYMBOL(callback_save_env)
.data
__alpha_using_srm: # For use by bootpheader
diff --git a/arch/alpha/lib/checksum.c b/arch/alpha/lib/checksum.c
index 377f9e3..b57f800 100644
--- a/arch/alpha/lib/checksum.c
+++ b/arch/alpha/lib/checksum.c
@@ -48,6 +48,7 @@ __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
(__force u64)saddr + (__force u64)daddr +
(__force u64)sum + ((len + proto) << 8));
}
+EXPORT_SYMBOL(csum_tcpudp_magic);
__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
__u32 len, __u8 proto, __wsum sum)
@@ -144,6 +145,7 @@ __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
{
return (__force __sum16)~do_csum(iph,ihl*4);
}
+EXPORT_SYMBOL(ip_fast_csum);
/*
* computes the checksum of a memory block at buff, length len,
@@ -178,3 +180,4 @@ __sum16 ip_compute_csum(const void *buff, int len)
{
return (__force __sum16)~from64to16(do_csum(buff,len));
}
+EXPORT_SYMBOL(ip_compute_csum);
diff --git a/arch/alpha/lib/clear_page.S b/arch/alpha/lib/clear_page.S
index a221ae2..263d739 100644
--- a/arch/alpha/lib/clear_page.S
+++ b/arch/alpha/lib/clear_page.S
@@ -3,7 +3,7 @@
*
* Zero an entire page.
*/
-
+#include <asm/export.h>
.text
.align 4
.global clear_page
@@ -37,3 +37,4 @@
nop
.end clear_page
+ EXPORT_SYMBOL(clear_page)
diff --git a/arch/alpha/lib/clear_user.S b/arch/alpha/lib/clear_user.S
index 8860316..bf5b931 100644
--- a/arch/alpha/lib/clear_user.S
+++ b/arch/alpha/lib/clear_user.S
@@ -24,6 +24,7 @@
* Clobbers:
* $1,$2,$3,$4,$5,$6
*/
+#include <asm/export.h>
/* Allow an exception for an insn; exit if we get one. */
#define EX(x,y...) \
@@ -111,3 +112,4 @@
ret $31, ($28), 1 # .. e1 :
.end __do_clear_user
+ EXPORT_SYMBOL(__do_clear_user)
diff --git a/arch/alpha/lib/copy_page.S b/arch/alpha/lib/copy_page.S
index 9f3b974..2ee0bd0 100644
--- a/arch/alpha/lib/copy_page.S
+++ b/arch/alpha/lib/copy_page.S
@@ -3,7 +3,7 @@
*
* Copy an entire page.
*/
-
+#include <asm/export.h>
.text
.align 4
.global copy_page
@@ -47,3 +47,4 @@
nop
.end copy_page
+ EXPORT_SYMBOL(copy_page)
diff --git a/arch/alpha/lib/copy_user.S b/arch/alpha/lib/copy_user.S
index 6f3fab9..509f62b 100644
--- a/arch/alpha/lib/copy_user.S
+++ b/arch/alpha/lib/copy_user.S
@@ -26,6 +26,8 @@
* $1,$2,$3,$4,$5,$6,$7
*/
+#include <asm/export.h>
+
/* Allow an exception for an insn; exit if we get one. */
#define EXI(x,y...) \
99: x,##y; \
@@ -124,22 +126,9 @@
bis $31,$31,$0
$41:
$35:
+$exitin:
$exitout:
ret $31,($28),1
-$exitin:
- /* A stupid byte-by-byte zeroing of the rest of the output
- buffer. This cures security holes by never leaving
- random kernel data around to be copied elsewhere. */
-
- mov $0,$1
-$101:
- EXO ( ldq_u $2,0($6) )
- subq $1,1,$1
- mskbl $2,$6,$2
- EXO ( stq_u $2,0($6) )
- addq $6,1,$6
- bgt $1,$101
- ret $31,($28),1
-
.end __copy_user
+EXPORT_SYMBOL(__copy_user)
diff --git a/arch/alpha/lib/csum_ipv6_magic.S b/arch/alpha/lib/csum_ipv6_magic.S
index 2c2acb9..e74b4544 100644
--- a/arch/alpha/lib/csum_ipv6_magic.S
+++ b/arch/alpha/lib/csum_ipv6_magic.S
@@ -12,6 +12,7 @@
* added by Ivan Kokshaysky <ink@jurassic.park.msu.ru>
*/
+#include <asm/export.h>
.globl csum_ipv6_magic
.align 4
.ent csum_ipv6_magic
@@ -113,3 +114,4 @@
ret # .. e1 :
.end csum_ipv6_magic
+ EXPORT_SYMBOL(csum_ipv6_magic)
diff --git a/arch/alpha/lib/csum_partial_copy.c b/arch/alpha/lib/csum_partial_copy.c
index 5675dca..b4ff3b6 100644
--- a/arch/alpha/lib/csum_partial_copy.c
+++ b/arch/alpha/lib/csum_partial_copy.c
@@ -374,6 +374,7 @@ csum_partial_copy_from_user(const void __user *src, void *dst, int len,
}
return (__force __wsum)checksum;
}
+EXPORT_SYMBOL(csum_partial_copy_from_user);
__wsum
csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
@@ -386,3 +387,4 @@ csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
set_fs(oldfs);
return checksum;
}
+EXPORT_SYMBOL(csum_partial_copy_nocheck);
diff --git a/arch/alpha/lib/dec_and_lock.c b/arch/alpha/lib/dec_and_lock.c
index f9f5fe8..4221b40 100644
--- a/arch/alpha/lib/dec_and_lock.c
+++ b/arch/alpha/lib/dec_and_lock.c
@@ -7,6 +7,7 @@
#include <linux/spinlock.h>
#include <linux/atomic.h>
+#include <linux/export.h>
asm (".text \n\
.global _atomic_dec_and_lock \n\
@@ -39,3 +40,4 @@ static int __used atomic_dec_and_lock_1(atomic_t *atomic, spinlock_t *lock)
spin_unlock(lock);
return 0;
}
+EXPORT_SYMBOL(_atomic_dec_and_lock);
diff --git a/arch/alpha/lib/divide.S b/arch/alpha/lib/divide.S
index 2d1a048..1e33bd1 100644
--- a/arch/alpha/lib/divide.S
+++ b/arch/alpha/lib/divide.S
@@ -45,6 +45,7 @@
* $28 - compare status
*/
+#include <asm/export.h>
#define halt .long 0
/*
@@ -151,6 +152,7 @@
addq $30,STACK,$30
ret $31,($23),1
.end ufunction
+EXPORT_SYMBOL(ufunction)
/*
* Uhh.. Ugly signed division. I'd rather not have it at all, but
@@ -193,3 +195,4 @@
addq $30,STACK,$30
ret $31,($23),1
.end sfunction
+EXPORT_SYMBOL(sfunction)
diff --git a/arch/alpha/lib/ev6-clear_page.S b/arch/alpha/lib/ev6-clear_page.S
index adf4f7b..abe99e6 100644
--- a/arch/alpha/lib/ev6-clear_page.S
+++ b/arch/alpha/lib/ev6-clear_page.S
@@ -3,7 +3,7 @@
*
* Zero an entire page.
*/
-
+#include <asm/export.h>
.text
.align 4
.global clear_page
@@ -52,3 +52,4 @@
nop
.end clear_page
+ EXPORT_SYMBOL(clear_page)
diff --git a/arch/alpha/lib/ev6-clear_user.S b/arch/alpha/lib/ev6-clear_user.S
index 4f42a16..05bef6b 100644
--- a/arch/alpha/lib/ev6-clear_user.S
+++ b/arch/alpha/lib/ev6-clear_user.S
@@ -43,6 +43,7 @@
* want to leave a hole (and we also want to avoid repeating lots of work)
*/
+#include <asm/export.h>
/* Allow an exception for an insn; exit if we get one. */
#define EX(x,y...) \
99: x,##y; \
@@ -222,4 +223,4 @@
nop # .. E .. .. :
ret $31, ($28), 1 # L0 .. .. .. : L U L U
.end __do_clear_user
-
+ EXPORT_SYMBOL(__do_clear_user)
diff --git a/arch/alpha/lib/ev6-copy_page.S b/arch/alpha/lib/ev6-copy_page.S
index b789db1..7793506 100644
--- a/arch/alpha/lib/ev6-copy_page.S
+++ b/arch/alpha/lib/ev6-copy_page.S
@@ -56,7 +56,7 @@
destination pages are in the dcache, but it is my guess that this is
less important than the dcache miss case. */
-
+#include <asm/export.h>
.text
.align 4
.global copy_page
@@ -201,3 +201,4 @@
nop
.end copy_page
+ EXPORT_SYMBOL(copy_page)
diff --git a/arch/alpha/lib/ev6-copy_user.S b/arch/alpha/lib/ev6-copy_user.S
index db42ffe..be720b5 100644
--- a/arch/alpha/lib/ev6-copy_user.S
+++ b/arch/alpha/lib/ev6-copy_user.S
@@ -37,6 +37,7 @@
* L - lower subcluster; L0 - subcluster L0; L1 - subcluster L1
*/
+#include <asm/export.h>
/* Allow an exception for an insn; exit if we get one. */
#define EXI(x,y...) \
99: x,##y; \
@@ -227,33 +228,12 @@
bgt $0,$onebyteloop # U .. .. .. : U L U L
$zerolength:
+$exitin:
$exitout: # Destination for exception recovery(?)
nop # .. .. .. E
nop # .. .. E ..
nop # .. E .. ..
ret $31,($28),1 # L0 .. .. .. : L U L U
-$exitin:
-
- /* A stupid byte-by-byte zeroing of the rest of the output
- buffer. This cures security holes by never leaving
- random kernel data around to be copied elsewhere. */
-
- nop
- nop
- nop
- mov $0,$1
-
-$101:
- EXO ( stb $31,0($6) ) # L
- subq $1,1,$1 # E
- addq $6,1,$6 # E
- bgt $1,$101 # U
-
- nop
- nop
- nop
- ret $31,($28),1 # L0
-
.end __copy_user
-
+ EXPORT_SYMBOL(__copy_user)
diff --git a/arch/alpha/lib/ev6-csum_ipv6_magic.S b/arch/alpha/lib/ev6-csum_ipv6_magic.S
index fc0bc39..de62627 100644
--- a/arch/alpha/lib/ev6-csum_ipv6_magic.S
+++ b/arch/alpha/lib/ev6-csum_ipv6_magic.S
@@ -52,6 +52,7 @@
* may cause additional delay in rare cases (load-load replay traps).
*/
+#include <asm/export.h>
.globl csum_ipv6_magic
.align 4
.ent csum_ipv6_magic
@@ -148,3 +149,4 @@
ret # L0 : L U L U
.end csum_ipv6_magic
+ EXPORT_SYMBOL(csum_ipv6_magic)
diff --git a/arch/alpha/lib/ev6-divide.S b/arch/alpha/lib/ev6-divide.S
index 2a82b9b..d18dc0e 100644
--- a/arch/alpha/lib/ev6-divide.S
+++ b/arch/alpha/lib/ev6-divide.S
@@ -55,6 +55,7 @@
* Try not to change the actual algorithm if possible for consistency.
*/
+#include <asm/export.h>
#define halt .long 0
/*
@@ -205,6 +206,7 @@
addq $30,STACK,$30 # E :
ret $31,($23),1 # L0 : L U U L
.end ufunction
+EXPORT_SYMBOL(ufunction)
/*
* Uhh.. Ugly signed division. I'd rather not have it at all, but
@@ -257,3 +259,4 @@
addq $30,STACK,$30 # E :
ret $31,($23),1 # L0 : L U U L
.end sfunction
+EXPORT_SYMBOL(sfunction)
diff --git a/arch/alpha/lib/ev6-memchr.S b/arch/alpha/lib/ev6-memchr.S
index 1a5f71b..419adc5 100644
--- a/arch/alpha/lib/ev6-memchr.S
+++ b/arch/alpha/lib/ev6-memchr.S
@@ -27,7 +27,7 @@
* L - lower subcluster; L0 - subcluster L0; L1 - subcluster L1
* Try not to change the actual algorithm if possible for consistency.
*/
-
+#include <asm/export.h>
.set noreorder
.set noat
@@ -189,3 +189,4 @@
ret # L0 :
.end memchr
+ EXPORT_SYMBOL(memchr)
diff --git a/arch/alpha/lib/ev6-memcpy.S b/arch/alpha/lib/ev6-memcpy.S
index 52b37b0..b19798b 100644
--- a/arch/alpha/lib/ev6-memcpy.S
+++ b/arch/alpha/lib/ev6-memcpy.S
@@ -19,7 +19,7 @@
* Temp usage notes:
* $1,$2, - scratch
*/
-
+#include <asm/export.h>
.set noreorder
.set noat
@@ -242,6 +242,7 @@
nop # E :
.end memcpy
+ EXPORT_SYMBOL(memcpy)
/* For backwards module compatibility. */
__memcpy = memcpy
diff --git a/arch/alpha/lib/ev6-memset.S b/arch/alpha/lib/ev6-memset.S
index 356bb2f..fed21c6 100644
--- a/arch/alpha/lib/ev6-memset.S
+++ b/arch/alpha/lib/ev6-memset.S
@@ -26,7 +26,7 @@
* as fixes will need to be made in multiple places. The performance gain
* is worth it.
*/
-
+#include <asm/export.h>
.set noat
.set noreorder
.text
@@ -229,6 +229,7 @@
nop
ret $31,($26),1 # L0 :
.end ___memset
+ EXPORT_SYMBOL(___memset)
/*
* This is the original body of code, prior to replication and
@@ -406,6 +407,7 @@
nop
ret $31,($26),1 # L0 :
.end __constant_c_memset
+ EXPORT_SYMBOL(__constant_c_memset)
/*
* This is a replicant of the __constant_c_memset code, rescheduled
@@ -594,6 +596,9 @@
ret $31,($26),1 # L0 :
.end __memsetw
+ EXPORT_SYMBOL(__memsetw)
memset = ___memset
__memset = ___memset
+ EXPORT_SYMBOL(memset)
+ EXPORT_SYMBOL(__memset)
diff --git a/arch/alpha/lib/ev67-strcat.S b/arch/alpha/lib/ev67-strcat.S
index c426fe3..b69f604 100644
--- a/arch/alpha/lib/ev67-strcat.S
+++ b/arch/alpha/lib/ev67-strcat.S
@@ -19,7 +19,7 @@
* string once.
*/
-
+#include <asm/export.h>
.text
.align 4
@@ -52,3 +52,4 @@
br __stxcpy # L0 :
.end strcat
+ EXPORT_SYMBOL(strcat)
diff --git a/arch/alpha/lib/ev67-strchr.S b/arch/alpha/lib/ev67-strchr.S
index fbb7b4f..ea8f2f3 100644
--- a/arch/alpha/lib/ev67-strchr.S
+++ b/arch/alpha/lib/ev67-strchr.S
@@ -15,7 +15,7 @@
* L - lower subcluster; L0 - subcluster L0; L1 - subcluster L1
* Try not to change the actual algorithm if possible for consistency.
*/
-
+#include <asm/export.h>
#include <asm/regdef.h>
.set noreorder
@@ -86,3 +86,4 @@
ret # L0 :
.end strchr
+ EXPORT_SYMBOL(strchr)
diff --git a/arch/alpha/lib/ev67-strlen.S b/arch/alpha/lib/ev67-strlen.S
index 5039280..736fd41 100644
--- a/arch/alpha/lib/ev67-strlen.S
+++ b/arch/alpha/lib/ev67-strlen.S
@@ -17,7 +17,7 @@
* U - upper subcluster; U0 - subcluster U0; U1 - subcluster U1
* L - lower subcluster; L0 - subcluster L0; L1 - subcluster L1
*/
-
+#include <asm/export.h>
.set noreorder
.set noat
@@ -47,3 +47,4 @@
ret $31, ($26) # L0 :
.end strlen
+ EXPORT_SYMBOL(strlen)
diff --git a/arch/alpha/lib/ev67-strncat.S b/arch/alpha/lib/ev67-strncat.S
index 4ae716c..cd35cba 100644
--- a/arch/alpha/lib/ev67-strncat.S
+++ b/arch/alpha/lib/ev67-strncat.S
@@ -20,7 +20,7 @@
* Try not to change the actual algorithm if possible for consistency.
*/
-
+#include <asm/export.h>
.text
.align 4
@@ -92,3 +92,4 @@
ret # L0 :
.end strncat
+ EXPORT_SYMBOL(strncat)
diff --git a/arch/alpha/lib/ev67-strrchr.S b/arch/alpha/lib/ev67-strrchr.S
index dd0d8c6..747455f 100644
--- a/arch/alpha/lib/ev67-strrchr.S
+++ b/arch/alpha/lib/ev67-strrchr.S
@@ -18,7 +18,7 @@
* L - lower subcluster; L0 - subcluster L0; L1 - subcluster L1
*/
-
+#include <asm/export.h>
#include <asm/regdef.h>
.set noreorder
@@ -107,3 +107,4 @@
nop
.end strrchr
+ EXPORT_SYMBOL(strrchr)
diff --git a/arch/alpha/lib/fpreg.c b/arch/alpha/lib/fpreg.c
index 05017ba..4aa6dbf 100644
--- a/arch/alpha/lib/fpreg.c
+++ b/arch/alpha/lib/fpreg.c
@@ -4,6 +4,9 @@
* (C) Copyright 1998 Linus Torvalds
*/
+#include <linux/compiler.h>
+#include <linux/export.h>
+
#if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67)
#define STT(reg,val) asm volatile ("ftoit $f"#reg",%0" : "=r"(val));
#else
@@ -52,6 +55,7 @@ alpha_read_fp_reg (unsigned long reg)
}
return val;
}
+EXPORT_SYMBOL(alpha_read_fp_reg);
#if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67)
#define LDT(reg,val) asm volatile ("itoft %0,$f"#reg : : "r"(val));
@@ -97,6 +101,7 @@ alpha_write_fp_reg (unsigned long reg, unsigned long val)
case 31: LDT(31, val); break;
}
}
+EXPORT_SYMBOL(alpha_write_fp_reg);
#if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67)
#define STS(reg,val) asm volatile ("ftois $f"#reg",%0" : "=r"(val));
@@ -146,6 +151,7 @@ alpha_read_fp_reg_s (unsigned long reg)
}
return val;
}
+EXPORT_SYMBOL(alpha_read_fp_reg_s);
#if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67)
#define LDS(reg,val) asm volatile ("itofs %0,$f"#reg : : "r"(val));
@@ -191,3 +197,4 @@ alpha_write_fp_reg_s (unsigned long reg, unsigned long val)
case 31: LDS(31, val); break;
}
}
+EXPORT_SYMBOL(alpha_write_fp_reg_s);
diff --git a/arch/alpha/lib/memchr.S b/arch/alpha/lib/memchr.S
index 14427ee..c13d3ec 100644
--- a/arch/alpha/lib/memchr.S
+++ b/arch/alpha/lib/memchr.S
@@ -31,7 +31,7 @@
- only minimum number of quadwords may be accessed
- the third argument is an unsigned long
*/
-
+#include <asm/export.h>
.set noreorder
.set noat
@@ -162,3 +162,4 @@
ret # .. e1 :
.end memchr
+ EXPORT_SYMBOL(memchr)
diff --git a/arch/alpha/lib/memcpy.c b/arch/alpha/lib/memcpy.c
index 64083fc..57d9291 100644
--- a/arch/alpha/lib/memcpy.c
+++ b/arch/alpha/lib/memcpy.c
@@ -16,6 +16,7 @@
*/
#include <linux/types.h>
+#include <linux/export.h>
/*
* This should be done in one go with ldq_u*2/mask/stq_u. Do it
@@ -158,6 +159,4 @@ void * memcpy(void * dest, const void *src, size_t n)
__memcpy_unaligned_up ((unsigned long) dest, (unsigned long) src, n);
return dest;
}
-
-/* For backward modules compatibility, define __memcpy. */
-asm("__memcpy = memcpy; .globl __memcpy");
+EXPORT_SYMBOL(memcpy);
diff --git a/arch/alpha/lib/memmove.S b/arch/alpha/lib/memmove.S
index eb3b6e0..6872c85 100644
--- a/arch/alpha/lib/memmove.S
+++ b/arch/alpha/lib/memmove.S
@@ -6,7 +6,7 @@
* This is hand-massaged output from the original memcpy.c. We defer to
* memcpy whenever possible; the backwards copy loops are not unrolled.
*/
-
+#include <asm/export.h>
.set noat
.set noreorder
.text
@@ -179,3 +179,4 @@
nop
.end memmove
+ EXPORT_SYMBOL(memmove)
diff --git a/arch/alpha/lib/memset.S b/arch/alpha/lib/memset.S
index 76ccc6d..89a26f5 100644
--- a/arch/alpha/lib/memset.S
+++ b/arch/alpha/lib/memset.S
@@ -13,7 +13,7 @@
* The scheduling comments are according to the EV5 documentation (and done by
* hand, so they might well be incorrect, please do tell me about it..)
*/
-
+#include <asm/export.h>
.set noat
.set noreorder
.text
@@ -106,6 +106,8 @@
end:
ret $31,($26),1 /* E1 */
.end ___memset
+EXPORT_SYMBOL(___memset)
+EXPORT_SYMBOL(__constant_c_memset)
.align 5
.ent __memsetw
@@ -122,6 +124,9 @@
br __constant_c_memset /* .. E1 */
.end __memsetw
+EXPORT_SYMBOL(__memsetw)
memset = ___memset
__memset = ___memset
+ EXPORT_SYMBOL(memset)
+ EXPORT_SYMBOL(__memset)
diff --git a/arch/alpha/lib/strcat.S b/arch/alpha/lib/strcat.S
index 393f503..249837b 100644
--- a/arch/alpha/lib/strcat.S
+++ b/arch/alpha/lib/strcat.S
@@ -4,6 +4,7 @@
*
* Append a null-terminated string from SRC to DST.
*/
+#include <asm/export.h>
.text
@@ -50,3 +51,4 @@
br __stxcpy
.end strcat
+EXPORT_SYMBOL(strcat);
diff --git a/arch/alpha/lib/strchr.S b/arch/alpha/lib/strchr.S
index 011a175..7412a17 100644
--- a/arch/alpha/lib/strchr.S
+++ b/arch/alpha/lib/strchr.S
@@ -5,7 +5,7 @@
* Return the address of a given character within a null-terminated
* string, or null if it is not found.
*/
-
+#include <asm/export.h>
#include <asm/regdef.h>
.set noreorder
@@ -68,3 +68,4 @@
ret # .. e1 :
.end strchr
+ EXPORT_SYMBOL(strchr)
diff --git a/arch/alpha/lib/strcpy.S b/arch/alpha/lib/strcpy.S
index e0728e4..98deae1 100644
--- a/arch/alpha/lib/strcpy.S
+++ b/arch/alpha/lib/strcpy.S
@@ -5,7 +5,7 @@
* Copy a null-terminated string from SRC to DST. Return a pointer
* to the null-terminator in the source.
*/
-
+#include <asm/export.h>
.text
.align 3
@@ -21,3 +21,4 @@
br __stxcpy # do the copy
.end strcpy
+ EXPORT_SYMBOL(strcpy)
diff --git a/arch/alpha/lib/strlen.S b/arch/alpha/lib/strlen.S
index fe63353..79c416f 100644
--- a/arch/alpha/lib/strlen.S
+++ b/arch/alpha/lib/strlen.S
@@ -11,7 +11,7 @@
* do this instead of the 9 instructions that
* binary search needs).
*/
-
+#include <asm/export.h>
.set noreorder
.set noat
@@ -55,3 +55,4 @@
ret $31, ($26)
.end strlen
+ EXPORT_SYMBOL(strlen)
diff --git a/arch/alpha/lib/strncat.S b/arch/alpha/lib/strncat.S
index a827816..6c29ea6 100644
--- a/arch/alpha/lib/strncat.S
+++ b/arch/alpha/lib/strncat.S
@@ -9,7 +9,7 @@
* past count, whereas libc may write to count+1. This follows the generic
* implementation in lib/string.c and is, IMHO, more sensible.
*/
-
+#include <asm/export.h>
.text
.align 3
@@ -82,3 +82,4 @@
ret
.end strncat
+ EXPORT_SYMBOL(strncat)
diff --git a/arch/alpha/lib/strncpy.S b/arch/alpha/lib/strncpy.S
index a46f7f3..e102cf1 100644
--- a/arch/alpha/lib/strncpy.S
+++ b/arch/alpha/lib/strncpy.S
@@ -10,7 +10,7 @@
* version has cropped that bit o' nastiness as well as assuming that
* __stxncpy is in range of a branch.
*/
-
+#include <asm/export.h>
.set noat
.set noreorder
@@ -79,3 +79,4 @@
ret
.end strncpy
+ EXPORT_SYMBOL(strncpy)
diff --git a/arch/alpha/lib/strrchr.S b/arch/alpha/lib/strrchr.S
index 1970dc0..4bc6cb4 100644
--- a/arch/alpha/lib/strrchr.S
+++ b/arch/alpha/lib/strrchr.S
@@ -5,7 +5,7 @@
* Return the address of the last occurrence of a given character
* within a null-terminated string, or null if it is not found.
*/
-
+#include <asm/export.h>
#include <asm/regdef.h>
.set noreorder
@@ -85,3 +85,4 @@
ret # .. e1 :
.end strrchr
+ EXPORT_SYMBOL(strrchr)
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index ecd1237..bd204bf 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -41,6 +41,8 @@
select PERF_USE_VMALLOC
select HAVE_DEBUG_STACKOVERFLOW
select HAVE_GENERIC_DMA_COHERENT
+ select HAVE_KERNEL_GZIP
+ select HAVE_KERNEL_LZMA
config MIGHT_HAVE_PCI
bool
@@ -186,14 +188,6 @@
config ARC_HAS_COH_CACHES
def_bool n
-config ARC_MCIP
- bool "ARConnect Multicore IP (MCIP) Support "
- depends on ISA_ARCV2
- help
- This IP block enables SMP in ARC-HS38 cores.
- It provides for cross-core interrupts, multi-core debug
- hardware semaphores, shared memory,....
-
config NR_CPUS
int "Maximum number of CPUs (2-4096)"
range 2 4096
@@ -211,6 +205,15 @@
endif #SMP
+config ARC_MCIP
+ bool "ARConnect Multicore IP (MCIP) Support "
+ depends on ISA_ARCV2
+ default y if SMP
+ help
+ This IP block enables SMP in ARC-HS38 cores.
+ It provides for cross-core interrupts, multi-core debug
+ hardware semaphores, shared memory,....
+
menuconfig ARC_CACHE
bool "Enable Cache Support"
default y
@@ -537,14 +540,6 @@
bool "Paranoia Checks in Low Level TLB Handlers"
default n
-config ARC_DBG_TLB_MISS_COUNT
- bool "Profile TLB Misses"
- default n
- select DEBUG_FS
- help
- Counts number of I and D TLB Misses and exports them via Debugfs
- The counters can be cleared via Debugfs as well
-
endif
config ARC_UBOOT_SUPPORT
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index aa82d13..19cce22 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -71,7 +71,9 @@
ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
# Generic build system uses -O2, we want -O3
# Note: No need to add to cflags-y as that happens anyways
-ARCH_CFLAGS += -O3
+#
+# Disable the false maybe-uninitialized warings gcc spits out at -O3
+ARCH_CFLAGS += -O3 $(call cc-disable-warning,maybe-uninitialized,)
endif
# small data is default for elf32 tool-chain. If not usable, disable it
diff --git a/arch/arc/boot/Makefile b/arch/arc/boot/Makefile
index e597cb34..f94cf15 100644
--- a/arch/arc/boot/Makefile
+++ b/arch/arc/boot/Makefile
@@ -14,9 +14,15 @@
suffix-y := bin
suffix-$(CONFIG_KERNEL_GZIP) := gz
+suffix-$(CONFIG_KERNEL_LZMA) := lzma
-targets += uImage uImage.bin uImage.gz
-extra-y += vmlinux.bin vmlinux.bin.gz
+targets += uImage
+targets += uImage.bin
+targets += uImage.gz
+targets += uImage.lzma
+extra-y += vmlinux.bin
+extra-y += vmlinux.bin.gz
+extra-y += vmlinux.bin.lzma
$(obj)/vmlinux.bin: vmlinux FORCE
$(call if_changed,objcopy)
@@ -24,12 +30,18 @@
$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
$(call if_changed,gzip)
+$(obj)/vmlinux.bin.lzma: $(obj)/vmlinux.bin FORCE
+ $(call if_changed,lzma)
+
$(obj)/uImage.bin: $(obj)/vmlinux.bin FORCE
$(call if_changed,uimage,none)
$(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE
$(call if_changed,uimage,gzip)
+$(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma FORCE
+ $(call if_changed,uimage,lzma)
+
$(obj)/uImage: $(obj)/uImage.$(suffix-y)
@ln -sf $(notdir $<) $@
@echo ' Image $@ is ready'
diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi
index 6ae2c47..53ce226 100644
--- a/arch/arc/boot/dts/axc001.dtsi
+++ b/arch/arc/boot/dts/axc001.dtsi
@@ -71,7 +71,7 @@
reg-io-width = <4>;
};
- arcpmu0: pmu {
+ arcpct0: pct {
compatible = "snps,arc700-pct";
};
};
diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts
index ce0ccd20..5ee96b0 100644
--- a/arch/arc/boot/dts/nsim_700.dts
+++ b/arch/arc/boot/dts/nsim_700.dts
@@ -69,7 +69,7 @@
};
};
- arcpmu0: pmu {
+ arcpct0: pct {
compatible = "snps,arc700-pct";
};
};
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index bcf6031..3c391ba 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -83,5 +83,9 @@
reg = <0xf0003000 0x44>;
interrupts = <7>;
};
+
+ arcpct0: pct {
+ compatible = "snps,arc700-pct";
+ };
};
};
diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig
index 7314f53..b0066a7 100644
--- a/arch/arc/configs/nsim_700_defconfig
+++ b/arch/arc/configs/nsim_700_defconfig
@@ -14,6 +14,7 @@
CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
CONFIG_KALLSYMS_ALL=y
CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
# CONFIG_SLUB_DEBUG is not set
# CONFIG_COMPAT_BRK is not set
CONFIG_KPROBES=y
diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig
index 65ab9fb..ebe9ebb 100644
--- a/arch/arc/configs/nsim_hs_defconfig
+++ b/arch/arc/configs/nsim_hs_defconfig
@@ -14,6 +14,7 @@
CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
CONFIG_KALLSYMS_ALL=y
CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
# CONFIG_SLUB_DEBUG is not set
# CONFIG_COMPAT_BRK is not set
CONFIG_KPROBES=y
diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig
index 3b3990c..4bde432 100644
--- a/arch/arc/configs/nsim_hs_smp_defconfig
+++ b/arch/arc/configs/nsim_hs_smp_defconfig
@@ -12,6 +12,7 @@
CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
CONFIG_KALLSYMS_ALL=y
CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
# CONFIG_SLUB_DEBUG is not set
# CONFIG_COMPAT_BRK is not set
CONFIG_KPROBES=y
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
index 98cf209..f6fb3d26 100644
--- a/arch/arc/configs/nsimosci_defconfig
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -14,6 +14,7 @@
CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
CONFIG_KALLSYMS_ALL=y
CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
# CONFIG_SLUB_DEBUG is not set
# CONFIG_COMPAT_BRK is not set
CONFIG_KPROBES=y
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
index ddf8b96..b9f0fe0 100644
--- a/arch/arc/configs/nsimosci_hs_defconfig
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -14,6 +14,7 @@
CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
CONFIG_KALLSYMS_ALL=y
CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
# CONFIG_SLUB_DEBUG is not set
# CONFIG_COMPAT_BRK is not set
CONFIG_KPROBES=y
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
index ceb9074..6da71ba 100644
--- a/arch/arc/configs/nsimosci_hs_smp_defconfig
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -10,6 +10,7 @@
# CONFIG_PID_NS is not set
CONFIG_BLK_DEV_INITRD=y
CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
+CONFIG_PERF_EVENTS=y
# CONFIG_COMPAT_BRK is not set
CONFIG_KPROBES=y
CONFIG_MODULES=y
@@ -34,7 +35,6 @@
# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
# CONFIG_INET_XFRM_MODE_TUNNEL is not set
# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
# CONFIG_IPV6 is not set
# CONFIG_WIRELESS is not set
CONFIG_DEVTMPFS=y
@@ -72,7 +72,6 @@
# CONFIG_HWMON is not set
CONFIG_DRM=y
CONFIG_DRM_ARCPGU=y
-CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_LOGO=y
# CONFIG_HID is not set
# CONFIG_USB_SUPPORT is not set
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index db25c65..1bd24ec 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -43,12 +43,14 @@
#define STATUS_AE_BIT 5 /* Exception active */
#define STATUS_DE_BIT 6 /* PC is in delay slot */
#define STATUS_U_BIT 7 /* User/Kernel mode */
+#define STATUS_Z_BIT 11
#define STATUS_L_BIT 12 /* Loop inhibit */
/* These masks correspond to the status word(STATUS_32) bits */
#define STATUS_AE_MASK (1<<STATUS_AE_BIT)
#define STATUS_DE_MASK (1<<STATUS_DE_BIT)
#define STATUS_U_MASK (1<<STATUS_U_BIT)
+#define STATUS_Z_MASK (1<<STATUS_Z_BIT)
#define STATUS_L_MASK (1<<STATUS_L_BIT)
/*
@@ -349,10 +351,11 @@ struct cpuinfo_arc {
struct cpuinfo_arc_bpu bpu;
struct bcr_identity core;
struct bcr_isa isa;
+ const char *details, *name;
unsigned int vec_base;
struct cpuinfo_arc_ccm iccm, dccm;
struct {
- unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, pad1:3,
+ unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, swape:1, pad1:2,
fpu_sp:1, fpu_dp:1, pad2:6,
debug:1, ap:1, smart:1, rtt:1, pad3:4,
timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index fb781e3..b3410ff 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -53,7 +53,7 @@ extern void arc_cache_init(void);
extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
extern void read_decode_cache_bcr(void);
-extern int ioc_exists;
+extern int ioc_enable;
extern unsigned long perip_base, perip_end;
#endif /* !__ASSEMBLY__ */
diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h
index 7096f97..aa2d6da 100644
--- a/arch/arc/include/asm/elf.h
+++ b/arch/arc/include/asm/elf.h
@@ -54,7 +54,7 @@ extern int elf_check_arch(const struct elf32_hdr *);
* the loader. We need to make sure that it is out of the way of the program
* that it will "exec", and that there is sufficient room for the brk.
*/
-#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3)
+#define ELF_ET_DYN_BASE (2UL * TASK_SIZE / 3)
/*
* When the program starts, a1 contains a pointer to a function to be
diff --git a/arch/arc/include/asm/mcip.h b/arch/arc/include/asm/mcip.h
index 847e3bb..c8fbe41 100644
--- a/arch/arc/include/asm/mcip.h
+++ b/arch/arc/include/asm/mcip.h
@@ -55,6 +55,22 @@ struct mcip_cmd {
#define IDU_M_DISTRI_DEST 0x2
};
+struct mcip_bcr {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+ unsigned int pad3:8,
+ idu:1, llm:1, num_cores:6,
+ iocoh:1, gfrc:1, dbg:1, pad2:1,
+ msg:1, sem:1, ipi:1, pad:1,
+ ver:8;
+#else
+ unsigned int ver:8,
+ pad:1, ipi:1, sem:1, msg:1,
+ pad2:1, dbg:1, gfrc:1, iocoh:1,
+ num_cores:6, llm:1, idu:1,
+ pad3:8;
+#endif
+};
+
/*
* MCIP programming model
*
diff --git a/arch/arc/include/asm/module.h b/arch/arc/include/asm/module.h
index 518222b..6e91d8b 100644
--- a/arch/arc/include/asm/module.h
+++ b/arch/arc/include/asm/module.h
@@ -18,6 +18,7 @@
struct mod_arch_specific {
void *unw_info;
int unw_sec_idx;
+ const char *secstr;
};
#endif
diff --git a/arch/arc/include/asm/setup.h b/arch/arc/include/asm/setup.h
index 48b37c6..cb954cd 100644
--- a/arch/arc/include/asm/setup.h
+++ b/arch/arc/include/asm/setup.h
@@ -27,11 +27,6 @@ struct id_to_str {
const char *str;
};
-struct cpuinfo_data {
- struct id_to_str info;
- int up_range;
-};
-
extern int root_mountflags, end_mem;
void setup_processor(void);
@@ -43,5 +38,6 @@ void __init setup_arch_memory(void);
#define IS_USED_RUN(v) ((v) ? "" : "(not used) ")
#define IS_USED_CFG(cfg) IS_USED_RUN(IS_ENABLED(cfg))
#define IS_AVAIL2(v, s, cfg) IS_AVAIL1(v, s), IS_AVAIL1(v, IS_USED_CFG(cfg))
+#define IS_AVAIL3(v, v2, s) IS_AVAIL1(v, s), IS_AVAIL1(v, IS_DISABLED_RUN(v2))
#endif /* __ASMARC_SETUP_H */
diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h
index 89fdd1b..0861007 100644
--- a/arch/arc/include/asm/smp.h
+++ b/arch/arc/include/asm/smp.h
@@ -37,9 +37,9 @@ extern const char *arc_platform_smp_cpuinfo(void);
* API expected BY platform smp code (FROM arch smp code)
*
* smp_ipi_irq_setup:
- * Takes @cpu and @irq to which the arch-common ISR is hooked up
+ * Takes @cpu and @hwirq to which the arch-common ISR is hooked up
*/
-extern int smp_ipi_irq_setup(int cpu, int irq);
+extern int smp_ipi_irq_setup(int cpu, irq_hw_number_t hwirq);
/*
* struct plat_smp_ops - SMP callbacks provided by platform to ARC SMP
diff --git a/arch/arc/include/asm/syscalls.h b/arch/arc/include/asm/syscalls.h
index e56f9fc..772b67c 100644
--- a/arch/arc/include/asm/syscalls.h
+++ b/arch/arc/include/asm/syscalls.h
@@ -17,6 +17,7 @@ int sys_clone_wrapper(int, int, int, int, int);
int sys_cacheflush(uint32_t, uint32_t uint32_t);
int sys_arc_settls(void *);
int sys_arc_gettls(void);
+int sys_arc_usr_cmpxchg(int *, int, int);
#include <asm-generic/syscalls.h>
diff --git a/arch/arc/include/uapi/asm/unistd.h b/arch/arc/include/uapi/asm/unistd.h
index 41fa2ec..9a34136 100644
--- a/arch/arc/include/uapi/asm/unistd.h
+++ b/arch/arc/include/uapi/asm/unistd.h
@@ -27,18 +27,19 @@
#define NR_syscalls __NR_syscalls
+/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */
+#define __NR_sysfs (__NR_arch_specific_syscall + 3)
+
/* ARC specific syscall */
#define __NR_cacheflush (__NR_arch_specific_syscall + 0)
#define __NR_arc_settls (__NR_arch_specific_syscall + 1)
#define __NR_arc_gettls (__NR_arch_specific_syscall + 2)
+#define __NR_arc_usr_cmpxchg (__NR_arch_specific_syscall + 4)
__SYSCALL(__NR_cacheflush, sys_cacheflush)
__SYSCALL(__NR_arc_settls, sys_arc_settls)
__SYSCALL(__NR_arc_gettls, sys_arc_gettls)
-
-
-/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */
-#define __NR_sysfs (__NR_arch_specific_syscall + 3)
+__SYSCALL(__NR_arc_usr_cmpxchg, sys_arc_usr_cmpxchg)
__SYSCALL(__NR_sysfs, sys_sysfs)
#undef __SYSCALL
diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c
index f1e07c2..3b67f53 100644
--- a/arch/arc/kernel/devtree.c
+++ b/arch/arc/kernel/devtree.c
@@ -31,6 +31,8 @@ static void __init arc_set_early_base_baud(unsigned long dt_root)
arc_base_baud = 166666666; /* Fixed 166.6MHz clk (TB10x) */
else if (of_flat_dt_is_compatible(dt_root, "snps,arc-sdp"))
arc_base_baud = 33333333; /* Fixed 33MHz clk (AXS10x) */
+ else if (of_flat_dt_is_compatible(dt_root, "ezchip,arc-nps"))
+ arc_base_baud = 800000000; /* Fixed 800MHz clk (NPS) */
else
arc_base_baud = 50000000; /* Fixed default 50MHz */
}
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index 72f9179..f39142a 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -15,11 +15,12 @@
#include <asm/mcip.h>
#include <asm/setup.h>
-static char smp_cpuinfo_buf[128];
-static int idu_detected;
-
static DEFINE_RAW_SPINLOCK(mcip_lock);
+#ifdef CONFIG_SMP
+
+static char smp_cpuinfo_buf[128];
+
static void mcip_setup_per_cpu(int cpu)
{
smp_ipi_irq_setup(cpu, IPI_IRQ);
@@ -86,21 +87,7 @@ static void mcip_ipi_clear(int irq)
static void mcip_probe_n_setup(void)
{
- struct mcip_bcr {
-#ifdef CONFIG_CPU_BIG_ENDIAN
- unsigned int pad3:8,
- idu:1, llm:1, num_cores:6,
- iocoh:1, gfrc:1, dbg:1, pad2:1,
- msg:1, sem:1, ipi:1, pad:1,
- ver:8;
-#else
- unsigned int ver:8,
- pad:1, ipi:1, sem:1, msg:1,
- pad2:1, dbg:1, gfrc:1, iocoh:1,
- num_cores:6, llm:1, idu:1,
- pad3:8;
-#endif
- } mp;
+ struct mcip_bcr mp;
READ_BCR(ARC_REG_MCIP_BCR, mp);
@@ -114,7 +101,6 @@ static void mcip_probe_n_setup(void)
IS_AVAIL1(mp.gfrc, "GFRC"));
cpuinfo_arc700[0].extn.gfrc = mp.gfrc;
- idu_detected = mp.idu;
if (mp.dbg) {
__mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, 0xf);
@@ -130,6 +116,8 @@ struct plat_smp_ops plat_smp_ops = {
.ipi_clear = mcip_ipi_clear,
};
+#endif
+
/***************************************************************************
* ARCv2 Interrupt Distribution Unit (IDU)
*
@@ -193,6 +181,8 @@ idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
{
unsigned long flags;
cpumask_t online;
+ unsigned int destination_bits;
+ unsigned int distribution_mode;
/* errout if no online cpu per @cpumask */
if (!cpumask_and(&online, cpumask, cpu_online_mask))
@@ -200,8 +190,15 @@ idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
raw_spin_lock_irqsave(&mcip_lock, flags);
- idu_set_dest(data->hwirq, cpumask_bits(&online)[0]);
- idu_set_mode(data->hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR);
+ destination_bits = cpumask_bits(&online)[0];
+ idu_set_dest(data->hwirq, destination_bits);
+
+ if (ffs(destination_bits) == fls(destination_bits))
+ distribution_mode = IDU_M_DISTRI_DEST;
+ else
+ distribution_mode = IDU_M_DISTRI_RR;
+
+ idu_set_mode(data->hwirq, IDU_M_TRIG_LEVEL, distribution_mode);
raw_spin_unlock_irqrestore(&mcip_lock, flags);
@@ -219,16 +216,15 @@ static struct irq_chip idu_irq_chip = {
};
-static int idu_first_irq;
+static irq_hw_number_t idu_first_hwirq;
static void idu_cascade_isr(struct irq_desc *desc)
{
- struct irq_domain *domain = irq_desc_get_handler_data(desc);
- unsigned int core_irq = irq_desc_get_irq(desc);
- unsigned int idu_irq;
+ struct irq_domain *idu_domain = irq_desc_get_handler_data(desc);
+ irq_hw_number_t core_hwirq = irqd_to_hwirq(irq_desc_get_irq_data(desc));
+ irq_hw_number_t idu_hwirq = core_hwirq - idu_first_hwirq;
- idu_irq = core_irq - idu_first_irq;
- generic_handle_irq(irq_find_mapping(domain, idu_irq));
+ generic_handle_irq(irq_find_mapping(idu_domain, idu_hwirq));
}
static int idu_irq_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hwirq)
@@ -294,9 +290,12 @@ idu_of_init(struct device_node *intc, struct device_node *parent)
struct irq_domain *domain;
/* Read IDU BCR to confirm nr_irqs */
int nr_irqs = of_irq_count(intc);
- int i, irq;
+ int i, virq;
+ struct mcip_bcr mp;
- if (!idu_detected)
+ READ_BCR(ARC_REG_MCIP_BCR, mp);
+
+ if (!mp.idu)
panic("IDU not detected, but DeviceTree using it");
pr_info("MCIP: IDU referenced from Devicetree %d irqs\n", nr_irqs);
@@ -312,11 +311,11 @@ idu_of_init(struct device_node *intc, struct device_node *parent)
* however we need it to get the parent virq and set IDU handler
* as first level isr
*/
- irq = irq_of_parse_and_map(intc, i);
+ virq = irq_of_parse_and_map(intc, i);
if (!i)
- idu_first_irq = irq;
+ idu_first_hwirq = irqd_to_hwirq(irq_get_irq_data(virq));
- irq_set_chained_handler_and_data(irq, idu_cascade_isr, domain);
+ irq_set_chained_handler_and_data(virq, idu_cascade_isr, domain);
}
__mcip_cmd(CMD_IDU_ENABLE, 0);
diff --git a/arch/arc/kernel/module.c b/arch/arc/kernel/module.c
index 9a28497..42e964d 100644
--- a/arch/arc/kernel/module.c
+++ b/arch/arc/kernel/module.c
@@ -30,17 +30,9 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
char *secstr, struct module *mod)
{
#ifdef CONFIG_ARC_DW2_UNWIND
- int i;
-
mod->arch.unw_sec_idx = 0;
mod->arch.unw_info = NULL;
-
- for (i = 1; i < hdr->e_shnum; i++) {
- if (strcmp(secstr+sechdrs[i].sh_name, ".eh_frame") == 0) {
- mod->arch.unw_sec_idx = i;
- break;
- }
- }
+ mod->arch.secstr = secstr;
#endif
return 0;
}
@@ -59,29 +51,33 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
unsigned int relsec, /* sec index for relo sec */
struct module *module)
{
- int i, n;
+ int i, n, relo_type;
Elf32_Rela *rel_entry = (void *)sechdrs[relsec].sh_addr;
Elf32_Sym *sym_entry, *sym_sec;
- Elf32_Addr relocation;
- Elf32_Addr location;
- Elf32_Addr sec_to_patch;
- int relo_type;
+ Elf32_Addr relocation, location, tgt_addr;
+ unsigned int tgtsec;
- sec_to_patch = sechdrs[sechdrs[relsec].sh_info].sh_addr;
+ /*
+ * @relsec has relocations e.g. .rela.init.text
+ * @tgtsec is section to patch e.g. .init.text
+ */
+ tgtsec = sechdrs[relsec].sh_info;
+ tgt_addr = sechdrs[tgtsec].sh_addr;
sym_sec = (Elf32_Sym *) sechdrs[symindex].sh_addr;
n = sechdrs[relsec].sh_size / sizeof(*rel_entry);
- pr_debug("\n========== Module Sym reloc ===========================\n");
- pr_debug("Section to fixup %x\n", sec_to_patch);
+ pr_debug("\nSection to fixup %s @%x\n",
+ module->arch.secstr + sechdrs[tgtsec].sh_name, tgt_addr);
pr_debug("=========================================================\n");
- pr_debug("rela->r_off | rela->addend | sym->st_value | ADDR | VALUE\n");
+ pr_debug("r_off\tr_add\tst_value ADDRESS VALUE\n");
pr_debug("=========================================================\n");
/* Loop thru entries in relocation section */
for (i = 0; i < n; i++) {
+ const char *s;
/* This is where to make the change */
- location = sec_to_patch + rel_entry[i].r_offset;
+ location = tgt_addr + rel_entry[i].r_offset;
/* This is the symbol it is referring to. Note that all
undefined symbols have been resolved. */
@@ -89,10 +85,15 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
relocation = sym_entry->st_value + rel_entry[i].r_addend;
- pr_debug("\t%x\t\t%x\t\t%x %x %x [%s]\n",
- rel_entry[i].r_offset, rel_entry[i].r_addend,
- sym_entry->st_value, location, relocation,
- strtab + sym_entry->st_name);
+ if (sym_entry->st_name == 0 && ELF_ST_TYPE (sym_entry->st_info) == STT_SECTION) {
+ s = module->arch.secstr + sechdrs[sym_entry->st_shndx].sh_name;
+ } else {
+ s = strtab + sym_entry->st_name;
+ }
+
+ pr_debug(" %x\t%x\t%x %x %x [%s]\n",
+ rel_entry[i].r_offset, rel_entry[i].r_addend,
+ sym_entry->st_value, location, relocation, s);
/* This assumes modules are built with -mlong-calls
* so any branches/jumps are absolute 32 bit jmps
@@ -111,6 +112,10 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
goto relo_err;
}
+
+ if (strcmp(module->arch.secstr+sechdrs[tgtsec].sh_name, ".eh_frame") == 0)
+ module->arch.unw_sec_idx = tgtsec;
+
return 0;
relo_err:
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index be1972b..a41a79a 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -41,6 +41,41 @@ SYSCALL_DEFINE0(arc_gettls)
return task_thread_info(current)->thr_ptr;
}
+SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
+{
+ struct pt_regs *regs = current_pt_regs();
+ int uval = -EFAULT;
+
+ /*
+ * This is only for old cores lacking LLOCK/SCOND, which by defintion
+ * can't possibly be SMP. Thus doesn't need to be SMP safe.
+ * And this also helps reduce the overhead for serializing in
+ * the UP case
+ */
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_SMP));
+
+ /* Z indicates to userspace if operation succeded */
+ regs->status32 &= ~STATUS_Z_MASK;
+
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ return -EFAULT;
+
+ preempt_disable();
+
+ if (__get_user(uval, uaddr))
+ goto done;
+
+ if (uval == expected) {
+ if (!__put_user(new, uaddr))
+ regs->status32 |= STATUS_Z_MASK;
+ }
+
+done:
+ preempt_enable();
+
+ return uval;
+}
+
void arch_cpu_idle(void)
{
/* sleep, but enable all interrupts before committing */
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 3df7f9c..0385df7 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -40,6 +40,29 @@ struct task_struct *_current_task[NR_CPUS]; /* For stack switching */
struct cpuinfo_arc cpuinfo_arc700[NR_CPUS];
+static const struct id_to_str arc_cpu_rel[] = {
+#ifdef CONFIG_ISA_ARCOMPACT
+ { 0x34, "R4.10"},
+ { 0x35, "R4.11"},
+#else
+ { 0x51, "R2.0" },
+ { 0x52, "R2.1" },
+ { 0x53, "R3.0" },
+#endif
+ { 0x00, NULL }
+};
+
+static const struct id_to_str arc_cpu_nm[] = {
+#ifdef CONFIG_ISA_ARCOMPACT
+ { 0x20, "ARC 600" },
+ { 0x30, "ARC 770" }, /* 750 identified seperately */
+#else
+ { 0x40, "ARC EM" },
+ { 0x50, "ARC HS38" },
+#endif
+ { 0x00, "Unknown" }
+};
+
static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu)
{
if (is_isa_arcompact()) {
@@ -92,11 +115,26 @@ static void read_arc_build_cfg_regs(void)
struct bcr_timer timer;
struct bcr_generic bcr;
struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
+ const struct id_to_str *tbl;
+
FIX_PTR(cpu);
READ_BCR(AUX_IDENTITY, cpu->core);
READ_BCR(ARC_REG_ISA_CFG_BCR, cpu->isa);
+ for (tbl = &arc_cpu_rel[0]; tbl->id != 0; tbl++) {
+ if (cpu->core.family == tbl->id) {
+ cpu->details = tbl->str;
+ break;
+ }
+ }
+
+ for (tbl = &arc_cpu_nm[0]; tbl->id != 0; tbl++) {
+ if ((cpu->core.family & 0xF0) == tbl->id)
+ break;
+ }
+ cpu->name = tbl->str;
+
READ_BCR(ARC_REG_TIMERS_BCR, timer);
cpu->extn.timer0 = timer.t0;
cpu->extn.timer1 = timer.t1;
@@ -111,6 +149,9 @@ static void read_arc_build_cfg_regs(void)
cpu->extn.swap = read_aux_reg(ARC_REG_SWAP_BCR) ? 1 : 0; /* 1,3 */
cpu->extn.crc = read_aux_reg(ARC_REG_CRC_BCR) ? 1 : 0;
cpu->extn.minmax = read_aux_reg(ARC_REG_MIXMAX_BCR) > 1 ? 1 : 0; /* 2 */
+ cpu->extn.swape = (cpu->core.family >= 0x34) ? 1 :
+ IS_ENABLED(CONFIG_ARC_HAS_SWAPE);
+
READ_BCR(ARC_REG_XY_MEM_BCR, cpu->extn_xymem);
/* Read CCM BCRs for boot reporting even if not enabled in Kconfig */
@@ -160,64 +201,38 @@ static void read_arc_build_cfg_regs(void)
cpu->extn.rtt = bcr.ver ? 1 : 0;
cpu->extn.debug = cpu->extn.ap | cpu->extn.smart | cpu->extn.rtt;
+
+ /* some hacks for lack of feature BCR info in old ARC700 cores */
+ if (is_isa_arcompact()) {
+ if (!cpu->isa.ver) /* ISA BCR absent, use Kconfig info */
+ cpu->isa.atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC);
+ else
+ cpu->isa.atomic = cpu->isa.atomic1;
+
+ cpu->isa.be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
+
+ /* there's no direct way to distinguish 750 vs. 770 */
+ if (unlikely(cpu->core.family < 0x34 || cpu->mmu.ver < 3))
+ cpu->name = "ARC750";
+ }
}
-static const struct cpuinfo_data arc_cpu_tbl[] = {
-#ifdef CONFIG_ISA_ARCOMPACT
- { {0x20, "ARC 600" }, 0x2F},
- { {0x30, "ARC 700" }, 0x33},
- { {0x34, "ARC 700 R4.10"}, 0x34},
- { {0x35, "ARC 700 R4.11"}, 0x35},
-#else
- { {0x50, "ARC HS38 R2.0"}, 0x51},
- { {0x52, "ARC HS38 R2.1"}, 0x52},
- { {0x53, "ARC HS38 R3.0"}, 0x53},
-#endif
- { {0x00, NULL } }
-};
-
-
static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
{
struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id];
struct bcr_identity *core = &cpu->core;
- const struct cpuinfo_data *tbl;
- char *isa_nm;
- int i, be, atomic;
- int n = 0;
+ int i, n = 0;
FIX_PTR(cpu);
- if (is_isa_arcompact()) {
- isa_nm = "ARCompact";
- be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
-
- atomic = cpu->isa.atomic1;
- if (!cpu->isa.ver) /* ISA BCR absent, use Kconfig info */
- atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC);
- } else {
- isa_nm = "ARCv2";
- be = cpu->isa.be;
- atomic = cpu->isa.atomic;
- }
-
n += scnprintf(buf + n, len - n,
"\nIDENTITY\t: ARCVER [%#02x] ARCNUM [%#02x] CHIPID [%#4x]\n",
core->family, core->cpu_id, core->chip_id);
- for (tbl = &arc_cpu_tbl[0]; tbl->info.id != 0; tbl++) {
- if ((core->family >= tbl->info.id) &&
- (core->family <= tbl->up_range)) {
- n += scnprintf(buf + n, len - n,
- "processor [%d]\t: %s (%s ISA) %s\n",
- cpu_id, tbl->info.str, isa_nm,
- IS_AVAIL1(be, "[Big-Endian]"));
- break;
- }
- }
-
- if (tbl->info.id == 0)
- n += scnprintf(buf + n, len - n, "UNKNOWN ARC Processor\n");
+ n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s\n",
+ cpu_id, cpu->name, cpu->details,
+ is_isa_arcompact() ? "ARCompact" : "ARCv2",
+ IS_AVAIL1(cpu->isa.be, "[Big-Endian]"));
n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s\nISA Extn\t: ",
IS_AVAIL1(cpu->extn.timer0, "Timer0 "),
@@ -226,7 +241,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
CONFIG_ARC_HAS_RTC));
n += i = scnprintf(buf + n, len - n, "%s%s%s%s%s",
- IS_AVAIL2(atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
+ IS_AVAIL2(cpu->isa.atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
IS_AVAIL2(cpu->isa.ldd, "ll64 ", CONFIG_ARC_HAS_LL64),
IS_AVAIL1(cpu->isa.unalign, "unalign (not used)"));
@@ -253,7 +268,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
IS_AVAIL1(cpu->extn.swap, "swap "),
IS_AVAIL1(cpu->extn.minmax, "minmax "),
IS_AVAIL1(cpu->extn.crc, "crc "),
- IS_AVAIL2(1, "swape", CONFIG_ARC_HAS_SWAPE));
+ IS_AVAIL2(cpu->extn.swape, "swape", CONFIG_ARC_HAS_SWAPE));
if (cpu->bpu.ver)
n += scnprintf(buf + n, len - n,
@@ -272,9 +287,7 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
FIX_PTR(cpu);
- n += scnprintf(buf + n, len - n,
- "Vector Table\t: %#x\nPeripherals\t: %#lx:%#lx\n",
- cpu->vec_base, perip_base, perip_end);
+ n += scnprintf(buf + n, len - n, "Vector Table\t: %#x\n", cpu->vec_base);
if (cpu->extn.fpu_sp || cpu->extn.fpu_dp)
n += scnprintf(buf + n, len - n, "FPU\t\t: %s%s\n",
@@ -507,7 +520,7 @@ static void *c_start(struct seq_file *m, loff_t *pos)
* way to pass it w/o having to kmalloc/free a 2 byte string.
* Encode cpu-id as 0xFFcccc, which is decoded by show routine.
*/
- return *pos < num_possible_cpus() ? cpu_to_ptr(*pos) : NULL;
+ return *pos < nr_cpu_ids ? cpu_to_ptr(*pos) : NULL;
}
static void *c_next(struct seq_file *m, void *v, loff_t *pos)
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 6cb3736..d347bbc 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -107,13 +107,13 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
struct user_regs_struct uregs;
err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
- if (!err)
- set_current_blocked(&set);
-
err |= __copy_from_user(&uregs.scratch,
&(sf->uc.uc_mcontext.regs.scratch),
sizeof(sf->uc.uc_mcontext.regs.scratch));
+ if (err)
+ return err;
+ set_current_blocked(&set);
regs->bta = uregs.scratch.bta;
regs->lp_start = uregs.scratch.lp_start;
regs->lp_end = uregs.scratch.lp_end;
@@ -138,7 +138,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
regs->r0 = uregs.scratch.r0;
regs->sp = uregs.scratch.sp;
- return err;
+ return 0;
}
static inline int is_do_ss_needed(unsigned int magic)
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index f183cc6..88674d9 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -22,6 +22,7 @@
#include <linux/atomic.h>
#include <linux/cpumask.h>
#include <linux/reboot.h>
+#include <linux/irqdomain.h>
#include <asm/processor.h>
#include <asm/setup.h>
#include <asm/mach_desc.h>
@@ -67,11 +68,13 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
int i;
/*
- * Initialise the present map, which describes the set of CPUs
- * actually populated at the present time.
+ * if platform didn't set the present map already, do it now
+ * boot cpu is set to present already by init/main.c
*/
- for (i = 0; i < max_cpus; i++)
- set_cpu_present(i, true);
+ if (num_present_cpus() <= 1) {
+ for (i = 0; i < max_cpus; i++)
+ set_cpu_present(i, true);
+ }
}
void __init smp_cpus_done(unsigned int max_cpus)
@@ -351,20 +354,24 @@ irqreturn_t do_IPI(int irq, void *dev_id)
*/
static DEFINE_PER_CPU(int, ipi_dev);
-int smp_ipi_irq_setup(int cpu, int irq)
+int smp_ipi_irq_setup(int cpu, irq_hw_number_t hwirq)
{
int *dev = per_cpu_ptr(&ipi_dev, cpu);
+ unsigned int virq = irq_find_mapping(NULL, hwirq);
+
+ if (!virq)
+ panic("Cannot find virq for root domain and hwirq=%lu", hwirq);
/* Boot cpu calls request, all call enable */
if (!cpu) {
int rc;
- rc = request_percpu_irq(irq, do_IPI, "IPI Interrupt", dev);
+ rc = request_percpu_irq(virq, do_IPI, "IPI Interrupt", dev);
if (rc)
- panic("Percpu IRQ request failed for %d\n", irq);
+ panic("Percpu IRQ request failed for %u\n", virq);
}
- enable_percpu_irq(irq, 0);
+ enable_percpu_irq(virq, 0);
return 0;
}
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index f927b8d..c10390d 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -152,14 +152,17 @@ static cycle_t arc_read_rtc(struct clocksource *cs)
cycle_t full;
} stamp;
-
- __asm__ __volatile(
- "1: \n"
- " lr %0, [AUX_RTC_LOW] \n"
- " lr %1, [AUX_RTC_HIGH] \n"
- " lr %2, [AUX_RTC_CTRL] \n"
- " bbit0.nt %2, 31, 1b \n"
- : "=r" (stamp.low), "=r" (stamp.high), "=r" (status));
+ /*
+ * hardware has an internal state machine which tracks readout of
+ * low/high and updates the CTRL.status if
+ * - interrupt/exception taken between the two reads
+ * - high increments after low has been read
+ */
+ do {
+ stamp.low = read_aux_reg(AUX_RTC_LOW);
+ stamp.high = read_aux_reg(AUX_RTC_HIGH);
+ status = read_aux_reg(AUX_RTC_CTRL);
+ } while (!(status & _BITUL(31)));
return stamp.full;
}
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index 934150e..82f9bc8 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -237,113 +237,3 @@ void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
if (!user_mode(regs))
show_stacktrace(current, regs);
}
-
-#ifdef CONFIG_DEBUG_FS
-
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/mount.h>
-#include <linux/pagemap.h>
-#include <linux/init.h>
-#include <linux/namei.h>
-#include <linux/debugfs.h>
-
-static struct dentry *test_dentry;
-static struct dentry *test_dir;
-static struct dentry *test_u32_dentry;
-
-static u32 clr_on_read = 1;
-
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
-u32 numitlb, numdtlb, num_pte_not_present;
-
-static int fill_display_data(char *kbuf)
-{
- size_t num = 0;
- num += sprintf(kbuf + num, "I-TLB Miss %x\n", numitlb);
- num += sprintf(kbuf + num, "D-TLB Miss %x\n", numdtlb);
- num += sprintf(kbuf + num, "PTE not present %x\n", num_pte_not_present);
-
- if (clr_on_read)
- numitlb = numdtlb = num_pte_not_present = 0;
-
- return num;
-}
-
-static int tlb_stats_open(struct inode *inode, struct file *file)
-{
- file->private_data = (void *)__get_free_page(GFP_KERNEL);
- return 0;
-}
-
-/* called on user read(): display the counters */
-static ssize_t tlb_stats_output(struct file *file, /* file descriptor */
- char __user *user_buf, /* user buffer */
- size_t len, /* length of buffer */
- loff_t *offset) /* offset in the file */
-{
- size_t num;
- char *kbuf = (char *)file->private_data;
-
- /* All of the data can he shoved in one iteration */
- if (*offset != 0)
- return 0;
-
- num = fill_display_data(kbuf);
-
- /* simple_read_from_buffer() is helper for copy to user space
- It copies up to @2 (num) bytes from kernel buffer @4 (kbuf) at offset
- @3 (offset) into the user space address starting at @1 (user_buf).
- @5 (len) is max size of user buffer
- */
- return simple_read_from_buffer(user_buf, num, offset, kbuf, len);
-}
-
-/* called on user write : clears the counters */
-static ssize_t tlb_stats_clear(struct file *file, const char __user *user_buf,
- size_t length, loff_t *offset)
-{
- numitlb = numdtlb = num_pte_not_present = 0;
- return length;
-}
-
-static int tlb_stats_close(struct inode *inode, struct file *file)
-{
- free_page((unsigned long)(file->private_data));
- return 0;
-}
-
-static const struct file_operations tlb_stats_file_ops = {
- .read = tlb_stats_output,
- .write = tlb_stats_clear,
- .open = tlb_stats_open,
- .release = tlb_stats_close
-};
-#endif
-
-static int __init arc_debugfs_init(void)
-{
- test_dir = debugfs_create_dir("arc", NULL);
-
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
- test_dentry = debugfs_create_file("tlb_stats", 0444, test_dir, NULL,
- &tlb_stats_file_ops);
-#endif
-
- test_u32_dentry =
- debugfs_create_u32("clr_on_read", 0444, test_dir, &clr_on_read);
-
- return 0;
-}
-
-module_init(arc_debugfs_init);
-
-static void __exit arc_debugfs_exit(void)
-{
- debugfs_remove(test_u32_dentry);
- debugfs_remove(test_dentry);
- debugfs_remove(test_dir);
-}
-module_exit(arc_debugfs_exit);
-
-#endif
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 97dddbe..2b96cfc 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -22,8 +22,8 @@
#include <asm/setup.h>
static int l2_line_sz;
-int ioc_exists;
-volatile int slc_enable = 1, ioc_enable = 1;
+static int ioc_exists;
+int slc_enable = 1, ioc_enable = 1;
unsigned long perip_base = ARC_UNCACHED_ADDR_SPACE; /* legacy value for boot */
unsigned long perip_end = 0xFFFFFFFF; /* legacy value */
@@ -53,18 +53,15 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len)
PR_CACHE(&cpuinfo_arc700[c].icache, CONFIG_ARC_HAS_ICACHE, "I-Cache");
PR_CACHE(&cpuinfo_arc700[c].dcache, CONFIG_ARC_HAS_DCACHE, "D-Cache");
- if (!is_isa_arcv2())
- return buf;
-
p = &cpuinfo_arc700[c].slc;
if (p->ver)
n += scnprintf(buf + n, len - n,
"SLC\t\t: %uK, %uB Line%s\n",
p->sz_k, p->line_len, IS_USED_RUN(slc_enable));
- if (ioc_exists)
- n += scnprintf(buf + n, len - n, "IOC\t\t:%s\n",
- IS_DISABLED_RUN(ioc_enable));
+ n += scnprintf(buf + n, len - n, "Peripherals\t: %#lx%s%s\n",
+ perip_base,
+ IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency "));
return buf;
}
@@ -113,8 +110,10 @@ static void read_decode_cache_bcr_arcv2(int cpu)
}
READ_BCR(ARC_REG_CLUSTER_BCR, cbcr);
- if (cbcr.c && ioc_enable)
+ if (cbcr.c)
ioc_exists = 1;
+ else
+ ioc_enable = 0;
/* HS 2.0 didn't have AUX_VOL */
if (cpuinfo_arc700[cpu].core.family > 0x51) {
@@ -1002,7 +1001,7 @@ void arc_cache_init(void)
read_aux_reg(ARC_REG_SLC_CTRL) | SLC_CTRL_DISABLE);
}
- if (is_isa_arcv2() && ioc_exists) {
+ if (is_isa_arcv2() && ioc_enable) {
/* IO coherency base - 0x8z */
write_aux_reg(ARC_REG_IO_COH_AP0_BASE, 0x80000);
/* IO coherency aperture size - 512Mb: 0x8z-0xAz */
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 20afc65..cd8aad8 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -45,7 +45,7 @@ static void *arc_dma_alloc(struct device *dev, size_t size,
* -For coherent data, Read/Write to buffers terminate early in cache
* (vs. always going to memory - thus are faster)
*/
- if ((is_isa_arcv2() && ioc_exists) ||
+ if ((is_isa_arcv2() && ioc_enable) ||
(attrs & DMA_ATTR_NON_CONSISTENT))
need_coh = 0;
@@ -97,7 +97,7 @@ static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
int is_non_coh = 1;
is_non_coh = (attrs & DMA_ATTR_NON_CONSISTENT) ||
- (is_isa_arcv2() && ioc_exists);
+ (is_isa_arcv2() && ioc_enable);
if (PageHighMem(page) || !is_non_coh)
iounmap((void __force __iomem *)vaddr);
@@ -105,6 +105,31 @@ static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
__free_pages(page, get_order(size));
}
+static int arc_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs)
+{
+ unsigned long user_count = vma_pages(vma);
+ unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ unsigned long pfn = __phys_to_pfn(plat_dma_to_phys(dev, dma_addr));
+ unsigned long off = vma->vm_pgoff;
+ int ret = -ENXIO;
+
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+ if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+ return ret;
+
+ if (off < count && user_count <= (count - off)) {
+ ret = remap_pfn_range(vma, vma->vm_start,
+ pfn + off,
+ user_count << PAGE_SHIFT,
+ vma->vm_page_prot);
+ }
+
+ return ret;
+}
+
/*
* streaming DMA Mapping API...
* CPU accesses page via normal paddr, thus needs to explicitly made
@@ -193,6 +218,7 @@ static int arc_dma_supported(struct device *dev, u64 dma_mask)
struct dma_map_ops arc_dma_ops = {
.alloc = arc_dma_alloc,
.free = arc_dma_free,
+ .mmap = arc_dma_mmap,
.map_page = arc_dma_map_page,
.map_sg = arc_dma_map_sg,
.sync_single_for_device = arc_dma_sync_single_for_device,
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index ec868a9..bdb295e 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -793,16 +793,16 @@ char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len)
char super_pg[64] = "";
if (p_mmu->s_pg_sz_m)
- scnprintf(super_pg, 64, "%dM Super Page%s, ",
+ scnprintf(super_pg, 64, "%dM Super Page %s",
p_mmu->s_pg_sz_m,
IS_USED_CFG(CONFIG_TRANSPARENT_HUGEPAGE));
n += scnprintf(buf + n, len - n,
- "MMU [v%x]\t: %dk PAGE, %sJTLB %d (%dx%d), uDTLB %d, uITLB %d %s%s\n",
+ "MMU [v%x]\t: %dk PAGE, %sJTLB %d (%dx%d), uDTLB %d, uITLB %d%s%s\n",
p_mmu->ver, p_mmu->pg_sz_k, super_pg,
p_mmu->sets * p_mmu->ways, p_mmu->sets, p_mmu->ways,
p_mmu->u_dtlb, p_mmu->u_itlb,
- IS_AVAIL2(p_mmu->pae, "PAE40 ", CONFIG_ARC_HAS_PAE40));
+ IS_AVAIL2(p_mmu->pae, ", PAE40 ", CONFIG_ARC_HAS_PAE40));
return buf;
}
diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S
index f1967ee..b30e4e3 100644
--- a/arch/arc/mm/tlbex.S
+++ b/arch/arc/mm/tlbex.S
@@ -237,15 +237,6 @@
2:
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
- and.f 0, r0, _PAGE_PRESENT
- bz 1f
- ld r3, [num_pte_not_present]
- add r3, r3, 1
- st r3, [num_pte_not_present]
-1:
-#endif
-
.endm
;-----------------------------------------------------------------
@@ -309,12 +300,6 @@
TLBMISS_FREEUP_REGS
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
- ld r0, [@numitlb]
- add r0, r0, 1
- st r0, [@numitlb]
-#endif
-
;----------------------------------------------------------------
; Get the PTE corresponding to V-addr accessed, r2 is setup with EFA
LOAD_FAULT_PTE
@@ -349,12 +334,6 @@
TLBMISS_FREEUP_REGS
-#ifdef CONFIG_ARC_DBG_TLB_MISS_COUNT
- ld r0, [@numdtlb]
- add r0, r0, 1
- st r0, [@numdtlb]
-#endif
-
;----------------------------------------------------------------
; Get the PTE corresponding to V-addr accessed
; If PTE exists, it will setup, r0 = PTE, r1 = Ptr to PTE, r2 = EFA
diff --git a/arch/arc/plat-eznps/smp.c b/arch/arc/plat-eznps/smp.c
index 5e901f8..56a4c85 100644
--- a/arch/arc/plat-eznps/smp.c
+++ b/arch/arc/plat-eznps/smp.c
@@ -140,16 +140,10 @@ static void eznps_init_per_cpu(int cpu)
mtm_enable_core(cpu);
}
-static void eznps_ipi_clear(int irq)
-{
- write_aux_reg(CTOP_AUX_IACK, 1 << irq);
-}
-
struct plat_smp_ops plat_smp_ops = {
.info = smp_cpuinfo_buf,
.init_early_smp = eznps_init_cpumasks,
.cpu_kick = eznps_smp_wakeup_cpu,
.ipi_send = eznps_ipi_send,
.init_per_cpu = eznps_init_per_cpu,
- .ipi_clear = eznps_ipi_clear,
};
diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts
index b3df1c6..386eee6 100644
--- a/arch/arm/boot/dts/ste-snowball.dts
+++ b/arch/arm/boot/dts/ste-snowball.dts
@@ -239,14 +239,25 @@
arm,primecell-periphid = <0x10480180>;
max-frequency = <100000000>;
bus-width = <4>;
+ cap-sd-highspeed;
cap-mmc-highspeed;
+ sd-uhs-sdr12;
+ sd-uhs-sdr25;
+ /* All direction control is used */
+ st,sig-dir-cmd;
+ st,sig-dir-dat0;
+ st,sig-dir-dat2;
+ st,sig-dir-dat31;
+ st,sig-pin-fbclk;
+ full-pwr-cycle;
vmmc-supply = <&ab8500_ldo_aux3_reg>;
vqmmc-supply = <&vmmci>;
pinctrl-names = "default", "sleep";
pinctrl-0 = <&sdi0_default_mode>;
pinctrl-1 = <&sdi0_sleep_mode>;
- cd-gpios = <&gpio6 26 GPIO_ACTIVE_LOW>; // 218
+ /* GPIO218 MMC_CD */
+ cd-gpios = <&gpio6 26 GPIO_ACTIVE_LOW>;
status = "okay";
};
@@ -549,7 +560,7 @@
/* VMMCI level-shifter enable */
snowball_cfg3 {
pins = "GPIO217_AH12";
- ste,config = <&gpio_out_lo>;
+ ste,config = <&gpio_out_hi>;
};
/* VMMCI level-shifter voltage select */
snowball_cfg4 {
diff --git a/arch/arm/boot/dts/uniphier-pro5.dtsi b/arch/arm/boot/dts/uniphier-pro5.dtsi
index 2c49c36..5357ea9 100644
--- a/arch/arm/boot/dts/uniphier-pro5.dtsi
+++ b/arch/arm/boot/dts/uniphier-pro5.dtsi
@@ -184,11 +184,11 @@
};
&mio_clk {
- compatible = "socionext,uniphier-pro5-mio-clock";
+ compatible = "socionext,uniphier-pro5-sd-clock";
};
&mio_rst {
- compatible = "socionext,uniphier-pro5-mio-reset";
+ compatible = "socionext,uniphier-pro5-sd-reset";
};
&peri_clk {
diff --git a/arch/arm/boot/dts/uniphier-pxs2.dtsi b/arch/arm/boot/dts/uniphier-pxs2.dtsi
index 8789cd5..950f07b 100644
--- a/arch/arm/boot/dts/uniphier-pxs2.dtsi
+++ b/arch/arm/boot/dts/uniphier-pxs2.dtsi
@@ -197,11 +197,11 @@
};
&mio_clk {
- compatible = "socionext,uniphier-pxs2-mio-clock";
+ compatible = "socionext,uniphier-pxs2-sd-clock";
};
&mio_rst {
- compatible = "socionext,uniphier-pxs2-mio-reset";
+ compatible = "socionext,uniphier-pxs2-sd-reset";
};
&peri_clk {
diff --git a/arch/arm/boot/dts/vf500.dtsi b/arch/arm/boot/dts/vf500.dtsi
index a3824e6..d7fdb2a 100644
--- a/arch/arm/boot/dts/vf500.dtsi
+++ b/arch/arm/boot/dts/vf500.dtsi
@@ -70,7 +70,7 @@
global_timer: timer@40002200 {
compatible = "arm,cortex-a9-global-timer";
reg = <0x40002200 0x20>;
- interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
interrupt-parent = <&intc>;
clocks = <&clks VF610_CLK_PLATFORM_BUS>;
};
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 437d074..11f37ed 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -850,6 +850,7 @@
CONFIG_PWM_TEGRA=y
CONFIG_PWM_VT8500=y
CONFIG_PHY_HIX5HD2_SATA=y
+CONFIG_E1000E=y
CONFIG_PWM_STI=y
CONFIG_PWM_BCM2835=y
CONFIG_PWM_BRCMSTB=m
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 55e0e3e..0745538 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -8,6 +8,7 @@
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
+generic-y += export.h
generic-y += ioctl.h
generic-y += ipcbuf.h
generic-y += irq_regs.h
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index d7ea6bc..8ef0538 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -66,6 +66,7 @@ extern char __kvm_hyp_vector[];
extern void __kvm_flush_vm_context(void);
extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
+extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 2d19e02..d5423ab 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -57,6 +57,9 @@ struct kvm_arch {
/* VTTBR value associated with below pgd and vmid */
u64 vttbr;
+ /* The last vcpu id that ran on each physical CPU */
+ int __percpu *last_vcpu_ran;
+
/* Timer */
struct arch_timer_kvm timer;
diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h
index 343135e..5850890 100644
--- a/arch/arm/include/asm/kvm_hyp.h
+++ b/arch/arm/include/asm/kvm_hyp.h
@@ -71,6 +71,7 @@
#define ICIALLUIS __ACCESS_CP15(c7, 0, c1, 0)
#define ATS1CPR __ACCESS_CP15(c7, 0, c8, 0)
#define TLBIALLIS __ACCESS_CP15(c8, 0, c3, 0)
+#define TLBIALL __ACCESS_CP15(c8, 0, c7, 0)
#define TLBIALLNSNHIS __ACCESS_CP15(c8, 4, c3, 4)
#define PRRR __ACCESS_CP15(c10, 0, c2, 0)
#define NMRR __ACCESS_CP15(c10, 0, c2, 1)
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index a93c0f9..1f59ea05 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -533,11 +533,12 @@ __clear_user(void __user *addr, unsigned long n)
static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
{
- if (access_ok(VERIFY_READ, from, n))
- n = __copy_from_user(to, from, n);
- else /* security hole - plug it */
- memset(to, 0, n);
- return n;
+ unsigned long res = n;
+ if (likely(access_ok(VERIFY_READ, from, n)))
+ res = __copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n)
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 194b699..ada0d29 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -19,7 +19,7 @@
* This may need to be greater than __NR_last_syscall+1 in order to
* account for the padding in the syscall table
*/
-#define __NR_syscalls (396)
+#define __NR_syscalls (400)
#define __ARCH_WANT_STAT64
#define __ARCH_WANT_SYS_GETHOSTNAME
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index 2cb9dc7..314100a 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -420,6 +420,9 @@
#define __NR_copy_file_range (__NR_SYSCALL_BASE+391)
#define __NR_preadv2 (__NR_SYSCALL_BASE+392)
#define __NR_pwritev2 (__NR_SYSCALL_BASE+393)
+#define __NR_pkey_mprotect (__NR_SYSCALL_BASE+394)
+#define __NR_pkey_alloc (__NR_SYSCALL_BASE+395)
+#define __NR_pkey_free (__NR_SYSCALL_BASE+396)
/*
* The following SWIs are ARM private.
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index ad325a8..68c2c09 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -33,7 +33,7 @@
obj-$(CONFIG_CPU_IDLE) += cpuidle.o
obj-$(CONFIG_ISA_DMA_API) += dma.o
obj-$(CONFIG_FIQ) += fiq.o fiqasm.o
-obj-$(CONFIG_MODULES) += armksyms.o module.o
+obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_ARM_MODULE_PLTS) += module-plts.o
obj-$(CONFIG_ISA_DMA) += dma-isa.o
obj-$(CONFIG_PCI) += bios32.o isa.o
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
deleted file mode 100644
index 7e45f69..0000000
--- a/arch/arm/kernel/armksyms.c
+++ /dev/null
@@ -1,183 +0,0 @@
-/*
- * linux/arch/arm/kernel/armksyms.c
- *
- * Copyright (C) 2000 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/export.h>
-#include <linux/sched.h>
-#include <linux/string.h>
-#include <linux/cryptohash.h>
-#include <linux/delay.h>
-#include <linux/in6.h>
-#include <linux/syscalls.h>
-#include <linux/uaccess.h>
-#include <linux/io.h>
-#include <linux/arm-smccc.h>
-
-#include <asm/checksum.h>
-#include <asm/ftrace.h>
-
-/*
- * libgcc functions - functions that are used internally by the
- * compiler... (prototypes are not correct though, but that
- * doesn't really matter since they're not versioned).
- */
-extern void __ashldi3(void);
-extern void __ashrdi3(void);
-extern void __divsi3(void);
-extern void __lshrdi3(void);
-extern void __modsi3(void);
-extern void __muldi3(void);
-extern void __ucmpdi2(void);
-extern void __udivsi3(void);
-extern void __umodsi3(void);
-extern void __do_div64(void);
-extern void __bswapsi2(void);
-extern void __bswapdi2(void);
-
-extern void __aeabi_idiv(void);
-extern void __aeabi_idivmod(void);
-extern void __aeabi_lasr(void);
-extern void __aeabi_llsl(void);
-extern void __aeabi_llsr(void);
-extern void __aeabi_lmul(void);
-extern void __aeabi_uidiv(void);
-extern void __aeabi_uidivmod(void);
-extern void __aeabi_ulcmp(void);
-
-extern void fpundefinstr(void);
-
-void mmioset(void *, unsigned int, size_t);
-void mmiocpy(void *, const void *, size_t);
-
- /* platform dependent support */
-EXPORT_SYMBOL(arm_delay_ops);
-
- /* networking */
-EXPORT_SYMBOL(csum_partial);
-EXPORT_SYMBOL(csum_partial_copy_from_user);
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
-EXPORT_SYMBOL(__csum_ipv6_magic);
-
- /* io */
-#ifndef __raw_readsb
-EXPORT_SYMBOL(__raw_readsb);
-#endif
-#ifndef __raw_readsw
-EXPORT_SYMBOL(__raw_readsw);
-#endif
-#ifndef __raw_readsl
-EXPORT_SYMBOL(__raw_readsl);
-#endif
-#ifndef __raw_writesb
-EXPORT_SYMBOL(__raw_writesb);
-#endif
-#ifndef __raw_writesw
-EXPORT_SYMBOL(__raw_writesw);
-#endif
-#ifndef __raw_writesl
-EXPORT_SYMBOL(__raw_writesl);
-#endif
-
- /* string / mem functions */
-EXPORT_SYMBOL(strchr);
-EXPORT_SYMBOL(strrchr);
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(memmove);
-EXPORT_SYMBOL(memchr);
-EXPORT_SYMBOL(__memzero);
-
-EXPORT_SYMBOL(mmioset);
-EXPORT_SYMBOL(mmiocpy);
-
-#ifdef CONFIG_MMU
-EXPORT_SYMBOL(copy_page);
-
-EXPORT_SYMBOL(arm_copy_from_user);
-EXPORT_SYMBOL(arm_copy_to_user);
-EXPORT_SYMBOL(arm_clear_user);
-
-EXPORT_SYMBOL(__get_user_1);
-EXPORT_SYMBOL(__get_user_2);
-EXPORT_SYMBOL(__get_user_4);
-EXPORT_SYMBOL(__get_user_8);
-
-#ifdef __ARMEB__
-EXPORT_SYMBOL(__get_user_64t_1);
-EXPORT_SYMBOL(__get_user_64t_2);
-EXPORT_SYMBOL(__get_user_64t_4);
-EXPORT_SYMBOL(__get_user_32t_8);
-#endif
-
-EXPORT_SYMBOL(__put_user_1);
-EXPORT_SYMBOL(__put_user_2);
-EXPORT_SYMBOL(__put_user_4);
-EXPORT_SYMBOL(__put_user_8);
-#endif
-
- /* gcc lib functions */
-EXPORT_SYMBOL(__ashldi3);
-EXPORT_SYMBOL(__ashrdi3);
-EXPORT_SYMBOL(__divsi3);
-EXPORT_SYMBOL(__lshrdi3);
-EXPORT_SYMBOL(__modsi3);
-EXPORT_SYMBOL(__muldi3);
-EXPORT_SYMBOL(__ucmpdi2);
-EXPORT_SYMBOL(__udivsi3);
-EXPORT_SYMBOL(__umodsi3);
-EXPORT_SYMBOL(__do_div64);
-EXPORT_SYMBOL(__bswapsi2);
-EXPORT_SYMBOL(__bswapdi2);
-
-#ifdef CONFIG_AEABI
-EXPORT_SYMBOL(__aeabi_idiv);
-EXPORT_SYMBOL(__aeabi_idivmod);
-EXPORT_SYMBOL(__aeabi_lasr);
-EXPORT_SYMBOL(__aeabi_llsl);
-EXPORT_SYMBOL(__aeabi_llsr);
-EXPORT_SYMBOL(__aeabi_lmul);
-EXPORT_SYMBOL(__aeabi_uidiv);
-EXPORT_SYMBOL(__aeabi_uidivmod);
-EXPORT_SYMBOL(__aeabi_ulcmp);
-#endif
-
- /* bitops */
-EXPORT_SYMBOL(_set_bit);
-EXPORT_SYMBOL(_test_and_set_bit);
-EXPORT_SYMBOL(_clear_bit);
-EXPORT_SYMBOL(_test_and_clear_bit);
-EXPORT_SYMBOL(_change_bit);
-EXPORT_SYMBOL(_test_and_change_bit);
-EXPORT_SYMBOL(_find_first_zero_bit_le);
-EXPORT_SYMBOL(_find_next_zero_bit_le);
-EXPORT_SYMBOL(_find_first_bit_le);
-EXPORT_SYMBOL(_find_next_bit_le);
-
-#ifdef __ARMEB__
-EXPORT_SYMBOL(_find_first_zero_bit_be);
-EXPORT_SYMBOL(_find_next_zero_bit_be);
-EXPORT_SYMBOL(_find_first_bit_be);
-EXPORT_SYMBOL(_find_next_bit_be);
-#endif
-
-#ifdef CONFIG_FUNCTION_TRACER
-#ifdef CONFIG_OLD_MCOUNT
-EXPORT_SYMBOL(mcount);
-#endif
-EXPORT_SYMBOL(__gnu_mcount_nc);
-#endif
-
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
-EXPORT_SYMBOL(__pv_phys_pfn_offset);
-EXPORT_SYMBOL(__pv_offset);
-#endif
-
-#ifdef CONFIG_HAVE_ARM_SMCCC
-EXPORT_SYMBOL(arm_smccc_smc);
-EXPORT_SYMBOL(arm_smccc_hvc);
-#endif
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index 703fa0f..08030b1 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -403,6 +403,9 @@
CALL(sys_copy_file_range)
CALL(sys_preadv2)
CALL(sys_pwritev2)
+ CALL(sys_pkey_mprotect)
+/* 395 */ CALL(sys_pkey_alloc)
+ CALL(sys_pkey_free)
#ifndef syscalls_counted
.equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
#define syscalls_counted
diff --git a/arch/arm/kernel/entry-ftrace.S b/arch/arm/kernel/entry-ftrace.S
index c73c403..b629d3f 100644
--- a/arch/arm/kernel/entry-ftrace.S
+++ b/arch/arm/kernel/entry-ftrace.S
@@ -7,6 +7,7 @@
#include <asm/assembler.h>
#include <asm/ftrace.h>
#include <asm/unwind.h>
+#include <asm/export.h>
#include "entry-header.S"
@@ -153,6 +154,7 @@
__mcount _old
#endif
ENDPROC(mcount)
+EXPORT_SYMBOL(mcount)
#ifdef CONFIG_DYNAMIC_FTRACE
ENTRY(ftrace_caller_old)
@@ -205,6 +207,7 @@
#endif
UNWIND(.fnend)
ENDPROC(__gnu_mcount_nc)
+EXPORT_SYMBOL(__gnu_mcount_nc)
#ifdef CONFIG_DYNAMIC_FTRACE
ENTRY(ftrace_caller)
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 04286fd..f41cee4 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -22,6 +22,7 @@
#include <asm/memory.h>
#include <asm/thread_info.h>
#include <asm/pgtable.h>
+#include <asm/export.h>
#if defined(CONFIG_DEBUG_LL) && !defined(CONFIG_DEBUG_SEMIHOSTING)
#include CONFIG_DEBUG_LL_INCLUDE
@@ -727,6 +728,8 @@
__pv_offset:
.quad 0
.size __pv_offset, . -__pv_offset
+EXPORT_SYMBOL(__pv_phys_pfn_offset)
+EXPORT_SYMBOL(__pv_offset)
#endif
#include "head-common.S"
diff --git a/arch/arm/kernel/smccc-call.S b/arch/arm/kernel/smccc-call.S
index 2e48b67..37669e7 100644
--- a/arch/arm/kernel/smccc-call.S
+++ b/arch/arm/kernel/smccc-call.S
@@ -16,6 +16,7 @@
#include <asm/opcodes-sec.h>
#include <asm/opcodes-virt.h>
#include <asm/unwind.h>
+#include <asm/export.h>
/*
* Wrap c macros in asm macros to delay expansion until after the
@@ -51,6 +52,7 @@
ENTRY(arm_smccc_smc)
SMCCC SMCCC_SMC
ENDPROC(arm_smccc_smc)
+EXPORT_SYMBOL(arm_smccc_smc)
/*
* void smccc_hvc(unsigned long a0, unsigned long a1, unsigned long a2,
@@ -60,3 +62,4 @@
ENTRY(arm_smccc_hvc)
SMCCC SMCCC_HVC
ENDPROC(arm_smccc_hvc)
+EXPORT_SYMBOL(arm_smccc_hvc)
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 03e9273..19b5f5c 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -114,11 +114,18 @@ void kvm_arch_check_processor_compat(void *rtn)
*/
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
- int ret = 0;
+ int ret, cpu;
if (type)
return -EINVAL;
+ kvm->arch.last_vcpu_ran = alloc_percpu(typeof(*kvm->arch.last_vcpu_ran));
+ if (!kvm->arch.last_vcpu_ran)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu)
+ *per_cpu_ptr(kvm->arch.last_vcpu_ran, cpu) = -1;
+
ret = kvm_alloc_stage2_pgd(kvm);
if (ret)
goto out_fail_alloc;
@@ -141,6 +148,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
out_free_stage2_pgd:
kvm_free_stage2_pgd(kvm);
out_fail_alloc:
+ free_percpu(kvm->arch.last_vcpu_ran);
+ kvm->arch.last_vcpu_ran = NULL;
return ret;
}
@@ -168,6 +177,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
{
int i;
+ free_percpu(kvm->arch.last_vcpu_ran);
+ kvm->arch.last_vcpu_ran = NULL;
+
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
if (kvm->vcpus[i]) {
kvm_arch_vcpu_free(kvm->vcpus[i]);
@@ -312,6 +324,19 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
+ int *last_ran;
+
+ last_ran = this_cpu_ptr(vcpu->kvm->arch.last_vcpu_ran);
+
+ /*
+ * We might get preempted before the vCPU actually runs, but
+ * over-invalidation doesn't affect correctness.
+ */
+ if (*last_ran != vcpu->vcpu_id) {
+ kvm_call_hyp(__kvm_tlb_flush_local_vmid, vcpu);
+ *last_ran = vcpu->vcpu_id;
+ }
+
vcpu->cpu = cpu;
vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state);
@@ -1312,6 +1337,13 @@ static int init_hyp_mode(void)
goto out_err;
}
+ err = create_hyp_mappings(kvm_ksym_ref(__bss_start),
+ kvm_ksym_ref(__bss_stop), PAGE_HYP_RO);
+ if (err) {
+ kvm_err("Cannot map bss section\n");
+ goto out_err;
+ }
+
/*
* Map the Hyp stack pages
*/
diff --git a/arch/arm/kvm/hyp/tlb.c b/arch/arm/kvm/hyp/tlb.c
index 7296528..6d810af 100644
--- a/arch/arm/kvm/hyp/tlb.c
+++ b/arch/arm/kvm/hyp/tlb.c
@@ -55,6 +55,21 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
__kvm_tlb_flush_vmid(kvm);
}
+void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
+
+ /* Switch to requested VMID */
+ write_sysreg(kvm->arch.vttbr, VTTBR);
+ isb();
+
+ write_sysreg(0, TLBIALL);
+ dsb(nsh);
+ isb();
+
+ write_sysreg(0, VTTBR);
+}
+
void __hyp_text __kvm_flush_vm_context(void)
{
write_sysreg(0, TLBIALLNSNHIS);
diff --git a/arch/arm/lib/ashldi3.S b/arch/arm/lib/ashldi3.S
index b05e958..a7e7de8 100644
--- a/arch/arm/lib/ashldi3.S
+++ b/arch/arm/lib/ashldi3.S
@@ -28,6 +28,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
#ifdef __ARMEB__
#define al r1
@@ -52,3 +53,5 @@
ENDPROC(__ashldi3)
ENDPROC(__aeabi_llsl)
+EXPORT_SYMBOL(__ashldi3)
+EXPORT_SYMBOL(__aeabi_llsl)
diff --git a/arch/arm/lib/ashrdi3.S b/arch/arm/lib/ashrdi3.S
index 275d7d2..490336e 100644
--- a/arch/arm/lib/ashrdi3.S
+++ b/arch/arm/lib/ashrdi3.S
@@ -28,6 +28,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
#ifdef __ARMEB__
#define al r1
@@ -52,3 +53,5 @@
ENDPROC(__ashrdi3)
ENDPROC(__aeabi_lasr)
+EXPORT_SYMBOL(__ashrdi3)
+EXPORT_SYMBOL(__aeabi_lasr)
diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h
index 7d807cf..df06638 100644
--- a/arch/arm/lib/bitops.h
+++ b/arch/arm/lib/bitops.h
@@ -1,5 +1,6 @@
#include <asm/assembler.h>
#include <asm/unwind.h>
+#include <asm/export.h>
#if __LINUX_ARM_ARCH__ >= 6
.macro bitop, name, instr
@@ -25,6 +26,7 @@ UNWIND( .fnstart )
bx lr
UNWIND( .fnend )
ENDPROC(\name )
+EXPORT_SYMBOL(\name )
.endm
.macro testop, name, instr, store
@@ -55,6 +57,7 @@ UNWIND( .fnstart )
2: bx lr
UNWIND( .fnend )
ENDPROC(\name )
+EXPORT_SYMBOL(\name )
.endm
#else
.macro bitop, name, instr
@@ -74,6 +77,7 @@ UNWIND( .fnstart )
ret lr
UNWIND( .fnend )
ENDPROC(\name )
+EXPORT_SYMBOL(\name )
.endm
/**
@@ -102,5 +106,6 @@ UNWIND( .fnstart )
ret lr
UNWIND( .fnend )
ENDPROC(\name )
+EXPORT_SYMBOL(\name )
.endm
#endif
diff --git a/arch/arm/lib/bswapsdi2.S b/arch/arm/lib/bswapsdi2.S
index 07cda73..f05f782 100644
--- a/arch/arm/lib/bswapsdi2.S
+++ b/arch/arm/lib/bswapsdi2.S
@@ -1,5 +1,6 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
#if __LINUX_ARM_ARCH__ >= 6
ENTRY(__bswapsi2)
@@ -35,3 +36,5 @@
ret lr
ENDPROC(__bswapdi2)
#endif
+EXPORT_SYMBOL(__bswapsi2)
+EXPORT_SYMBOL(__bswapdi2)
diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S
index e936352..b566154 100644
--- a/arch/arm/lib/clear_user.S
+++ b/arch/arm/lib/clear_user.S
@@ -10,6 +10,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/unwind.h>
+#include <asm/export.h>
.text
@@ -50,6 +51,9 @@
UNWIND(.fnend)
ENDPROC(arm_clear_user)
ENDPROC(__clear_user_std)
+#ifndef CONFIG_UACCESS_WITH_MEMCPY
+EXPORT_SYMBOL(arm_clear_user)
+#endif
.pushsection .text.fixup,"ax"
.align 0
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 1512beb..63e4c1e 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -13,6 +13,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/unwind.h>
+#include <asm/export.h>
/*
* Prototype:
@@ -94,16 +95,14 @@
#include "copy_template.S"
ENDPROC(arm_copy_from_user)
+EXPORT_SYMBOL(arm_copy_from_user)
.pushsection .fixup,"ax"
.align 0
copy_abort_preamble
- ldmfd sp!, {r1, r2}
- sub r3, r0, r1
- rsb r1, r3, r2
- str r1, [sp]
- bl __memzero
- ldr r0, [sp], #4
+ ldmfd sp!, {r1, r2, r3}
+ sub r0, r0, r1
+ rsb r0, r0, r2
copy_abort_end
.popsection
diff --git a/arch/arm/lib/copy_page.S b/arch/arm/lib/copy_page.S
index 6ee2f67..d97851d 100644
--- a/arch/arm/lib/copy_page.S
+++ b/arch/arm/lib/copy_page.S
@@ -13,6 +13,7 @@
#include <asm/assembler.h>
#include <asm/asm-offsets.h>
#include <asm/cache.h>
+#include <asm/export.h>
#define COPY_COUNT (PAGE_SZ / (2 * L1_CACHE_BYTES) PLD( -1 ))
@@ -45,3 +46,4 @@
PLD( beq 2b )
ldmfd sp!, {r4, pc} @ 3
ENDPROC(copy_page)
+EXPORT_SYMBOL(copy_page)
diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S
index caf5019..592c179 100644
--- a/arch/arm/lib/copy_to_user.S
+++ b/arch/arm/lib/copy_to_user.S
@@ -13,6 +13,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/unwind.h>
+#include <asm/export.h>
/*
* Prototype:
@@ -99,6 +100,9 @@
ENDPROC(arm_copy_to_user)
ENDPROC(__copy_to_user_std)
+#ifndef CONFIG_UACCESS_WITH_MEMCPY
+EXPORT_SYMBOL(arm_copy_to_user)
+#endif
.pushsection .text.fixup,"ax"
.align 0
diff --git a/arch/arm/lib/csumipv6.S b/arch/arm/lib/csumipv6.S
index 3ac6ef0..68603b5 100644
--- a/arch/arm/lib/csumipv6.S
+++ b/arch/arm/lib/csumipv6.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
.text
@@ -30,4 +31,4 @@
adcs r0, r0, #0
ldmfd sp!, {pc}
ENDPROC(__csum_ipv6_magic)
-
+EXPORT_SYMBOL(__csum_ipv6_magic)
diff --git a/arch/arm/lib/csumpartial.S b/arch/arm/lib/csumpartial.S
index 984e0f2..830b20e 100644
--- a/arch/arm/lib/csumpartial.S
+++ b/arch/arm/lib/csumpartial.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
.text
@@ -140,3 +141,4 @@
bne 4b
b .Lless4
ENDPROC(csum_partial)
+EXPORT_SYMBOL(csum_partial)
diff --git a/arch/arm/lib/csumpartialcopy.S b/arch/arm/lib/csumpartialcopy.S
index d03fc71..9c3383f 100644
--- a/arch/arm/lib/csumpartialcopy.S
+++ b/arch/arm/lib/csumpartialcopy.S
@@ -49,5 +49,6 @@
#define FN_ENTRY ENTRY(csum_partial_copy_nocheck)
#define FN_EXIT ENDPROC(csum_partial_copy_nocheck)
+#define FN_EXPORT EXPORT_SYMBOL(csum_partial_copy_nocheck)
#include "csumpartialcopygeneric.S"
diff --git a/arch/arm/lib/csumpartialcopygeneric.S b/arch/arm/lib/csumpartialcopygeneric.S
index 10b4590..8b94d20 100644
--- a/arch/arm/lib/csumpartialcopygeneric.S
+++ b/arch/arm/lib/csumpartialcopygeneric.S
@@ -8,6 +8,7 @@
* published by the Free Software Foundation.
*/
#include <asm/assembler.h>
+#include <asm/export.h>
/*
* unsigned int
@@ -331,3 +332,4 @@
mov r5, r4, get_byte_1
b .Lexit
FN_EXIT
+FN_EXPORT
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
index 1712f13..5d495ed 100644
--- a/arch/arm/lib/csumpartialcopyuser.S
+++ b/arch/arm/lib/csumpartialcopyuser.S
@@ -73,6 +73,7 @@
#define FN_ENTRY ENTRY(csum_partial_copy_from_user)
#define FN_EXIT ENDPROC(csum_partial_copy_from_user)
+#define FN_EXPORT EXPORT_SYMBOL(csum_partial_copy_from_user)
#include "csumpartialcopygeneric.S"
diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
index 2cef118..69aad80 100644
--- a/arch/arm/lib/delay.c
+++ b/arch/arm/lib/delay.c
@@ -24,6 +24,7 @@
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/export.h>
#include <linux/timex.h>
/*
@@ -34,6 +35,7 @@ struct arm_delay_ops arm_delay_ops __ro_after_init = {
.const_udelay = __loop_const_udelay,
.udelay = __loop_udelay,
};
+EXPORT_SYMBOL(arm_delay_ops);
static const struct delay_timer *delay_timer;
static bool delay_calibrated;
diff --git a/arch/arm/lib/div64.S b/arch/arm/lib/div64.S
index a9eafe4..0c9e1c1 100644
--- a/arch/arm/lib/div64.S
+++ b/arch/arm/lib/div64.S
@@ -15,6 +15,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/unwind.h>
+#include <asm/export.h>
#ifdef __ARMEB__
#define xh r0
@@ -210,3 +211,4 @@
UNWIND(.fnend)
ENDPROC(__do_div64)
+EXPORT_SYMBOL(__do_div64)
diff --git a/arch/arm/lib/findbit.S b/arch/arm/lib/findbit.S
index 7848780..26302b8 100644
--- a/arch/arm/lib/findbit.S
+++ b/arch/arm/lib/findbit.S
@@ -15,6 +15,7 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
.text
/*
@@ -37,6 +38,7 @@
3: mov r0, r1 @ no free bits
ret lr
ENDPROC(_find_first_zero_bit_le)
+EXPORT_SYMBOL(_find_first_zero_bit_le)
/*
* Purpose : Find next 'zero' bit
@@ -57,6 +59,7 @@
add r2, r2, #1 @ align bit pointer
b 2b @ loop for next bit
ENDPROC(_find_next_zero_bit_le)
+EXPORT_SYMBOL(_find_next_zero_bit_le)
/*
* Purpose : Find a 'one' bit
@@ -78,6 +81,7 @@
3: mov r0, r1 @ no free bits
ret lr
ENDPROC(_find_first_bit_le)
+EXPORT_SYMBOL(_find_first_bit_le)
/*
* Purpose : Find next 'one' bit
@@ -97,6 +101,7 @@
add r2, r2, #1 @ align bit pointer
b 2b @ loop for next bit
ENDPROC(_find_next_bit_le)
+EXPORT_SYMBOL(_find_next_bit_le)
#ifdef __ARMEB__
@@ -116,6 +121,7 @@
3: mov r0, r1 @ no free bits
ret lr
ENDPROC(_find_first_zero_bit_be)
+EXPORT_SYMBOL(_find_first_zero_bit_be)
ENTRY(_find_next_zero_bit_be)
teq r1, #0
@@ -133,6 +139,7 @@
add r2, r2, #1 @ align bit pointer
b 2b @ loop for next bit
ENDPROC(_find_next_zero_bit_be)
+EXPORT_SYMBOL(_find_next_zero_bit_be)
ENTRY(_find_first_bit_be)
teq r1, #0
@@ -150,6 +157,7 @@
3: mov r0, r1 @ no free bits
ret lr
ENDPROC(_find_first_bit_be)
+EXPORT_SYMBOL(_find_first_bit_be)
ENTRY(_find_next_bit_be)
teq r1, #0
@@ -166,6 +174,7 @@
add r2, r2, #1 @ align bit pointer
b 2b @ loop for next bit
ENDPROC(_find_next_bit_be)
+EXPORT_SYMBOL(_find_next_bit_be)
#endif
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index 8ecfd15..9d09a38 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -31,6 +31,7 @@
#include <asm/assembler.h>
#include <asm/errno.h>
#include <asm/domain.h>
+#include <asm/export.h>
ENTRY(__get_user_1)
check_uaccess r0, 1, r1, r2, __get_user_bad
@@ -38,6 +39,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_1)
+EXPORT_SYMBOL(__get_user_1)
ENTRY(__get_user_2)
check_uaccess r0, 2, r1, r2, __get_user_bad
@@ -58,6 +60,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_2)
+EXPORT_SYMBOL(__get_user_2)
ENTRY(__get_user_4)
check_uaccess r0, 4, r1, r2, __get_user_bad
@@ -65,6 +68,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_4)
+EXPORT_SYMBOL(__get_user_4)
ENTRY(__get_user_8)
check_uaccess r0, 8, r1, r2, __get_user_bad
@@ -78,6 +82,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_8)
+EXPORT_SYMBOL(__get_user_8)
#ifdef __ARMEB__
ENTRY(__get_user_32t_8)
@@ -91,6 +96,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_32t_8)
+EXPORT_SYMBOL(__get_user_32t_8)
ENTRY(__get_user_64t_1)
check_uaccess r0, 1, r1, r2, __get_user_bad8
@@ -98,6 +104,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_64t_1)
+EXPORT_SYMBOL(__get_user_64t_1)
ENTRY(__get_user_64t_2)
check_uaccess r0, 2, r1, r2, __get_user_bad8
@@ -114,6 +121,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_64t_2)
+EXPORT_SYMBOL(__get_user_64t_2)
ENTRY(__get_user_64t_4)
check_uaccess r0, 4, r1, r2, __get_user_bad8
@@ -121,6 +129,7 @@
mov r0, #0
ret lr
ENDPROC(__get_user_64t_4)
+EXPORT_SYMBOL(__get_user_64t_4)
#endif
__get_user_bad8:
diff --git a/arch/arm/lib/io-readsb.S b/arch/arm/lib/io-readsb.S
index c31b2f3..3dff7a3 100644
--- a/arch/arm/lib/io-readsb.S
+++ b/arch/arm/lib/io-readsb.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
.Linsb_align: rsb ip, ip, #4
cmp ip, r2
@@ -121,3 +122,4 @@
ldmfd sp!, {r4 - r6, pc}
ENDPROC(__raw_readsb)
+EXPORT_SYMBOL(__raw_readsb)
diff --git a/arch/arm/lib/io-readsl.S b/arch/arm/lib/io-readsl.S
index 2ed86fa..bfd3968 100644
--- a/arch/arm/lib/io-readsl.S
+++ b/arch/arm/lib/io-readsl.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
ENTRY(__raw_readsl)
teq r2, #0 @ do we have to check for the zero len?
@@ -77,3 +78,4 @@
strb r3, [r1, #0]
ret lr
ENDPROC(__raw_readsl)
+EXPORT_SYMBOL(__raw_readsl)
diff --git a/arch/arm/lib/io-readsw-armv3.S b/arch/arm/lib/io-readsw-armv3.S
index 413da99..b3af3db 100644
--- a/arch/arm/lib/io-readsw-armv3.S
+++ b/arch/arm/lib/io-readsw-armv3.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
.Linsw_bad_alignment:
adr r0, .Linsw_bad_align_msg
@@ -103,4 +104,4 @@
ldmfd sp!, {r4, r5, r6, pc}
-
+EXPORT_SYMBOL(__raw_readsw)
diff --git a/arch/arm/lib/io-readsw-armv4.S b/arch/arm/lib/io-readsw-armv4.S
index d9a45e9..3c7a7a4 100644
--- a/arch/arm/lib/io-readsw-armv4.S
+++ b/arch/arm/lib/io-readsw-armv4.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
.macro pack, rd, hw1, hw2
#ifndef __ARMEB__
@@ -129,3 +130,4 @@
strneb ip, [r1]
ldmfd sp!, {r4, pc}
ENDPROC(__raw_readsw)
+EXPORT_SYMBOL(__raw_readsw)
diff --git a/arch/arm/lib/io-writesb.S b/arch/arm/lib/io-writesb.S
index a46bbc9..fa36335 100644
--- a/arch/arm/lib/io-writesb.S
+++ b/arch/arm/lib/io-writesb.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
.macro outword, rd
#ifndef __ARMEB__
@@ -92,3 +93,4 @@
ldmfd sp!, {r4, r5, pc}
ENDPROC(__raw_writesb)
+EXPORT_SYMBOL(__raw_writesb)
diff --git a/arch/arm/lib/io-writesl.S b/arch/arm/lib/io-writesl.S
index 4ea2435..98ed6ae 100644
--- a/arch/arm/lib/io-writesl.S
+++ b/arch/arm/lib/io-writesl.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
ENTRY(__raw_writesl)
teq r2, #0 @ do we have to check for the zero len?
@@ -65,3 +66,4 @@
bne 6b
ret lr
ENDPROC(__raw_writesl)
+EXPORT_SYMBOL(__raw_writesl)
diff --git a/arch/arm/lib/io-writesw-armv3.S b/arch/arm/lib/io-writesw-armv3.S
index 121789e..577184c 100644
--- a/arch/arm/lib/io-writesw-armv3.S
+++ b/arch/arm/lib/io-writesw-armv3.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
.Loutsw_bad_alignment:
adr r0, .Loutsw_bad_align_msg
@@ -124,3 +125,4 @@
strne ip, [r0]
ldmfd sp!, {r4, r5, r6, pc}
+EXPORT_SYMBOL(__raw_writesw)
diff --git a/arch/arm/lib/io-writesw-armv4.S b/arch/arm/lib/io-writesw-armv4.S
index 269f90c..e335f48 100644
--- a/arch/arm/lib/io-writesw-armv4.S
+++ b/arch/arm/lib/io-writesw-armv4.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
.macro outword, rd
#ifndef __ARMEB__
@@ -98,3 +99,4 @@
strneh ip, [r0]
ret lr
ENDPROC(__raw_writesw)
+EXPORT_SYMBOL(__raw_writesw)
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index 9397b2e..f541bc0 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -36,6 +36,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/unwind.h>
+#include <asm/export.h>
.macro ARM_DIV_BODY dividend, divisor, result, curbit
@@ -238,6 +239,8 @@
UNWIND(.fnend)
ENDPROC(__udivsi3)
ENDPROC(__aeabi_uidiv)
+EXPORT_SYMBOL(__udivsi3)
+EXPORT_SYMBOL(__aeabi_uidiv)
ENTRY(__umodsi3)
UNWIND(.fnstart)
@@ -256,6 +259,7 @@
UNWIND(.fnend)
ENDPROC(__umodsi3)
+EXPORT_SYMBOL(__umodsi3)
#ifdef CONFIG_ARM_PATCH_IDIV
.align 3
@@ -303,6 +307,8 @@
UNWIND(.fnend)
ENDPROC(__divsi3)
ENDPROC(__aeabi_idiv)
+EXPORT_SYMBOL(__divsi3)
+EXPORT_SYMBOL(__aeabi_idiv)
ENTRY(__modsi3)
UNWIND(.fnstart)
@@ -327,6 +333,7 @@
UNWIND(.fnend)
ENDPROC(__modsi3)
+EXPORT_SYMBOL(__modsi3)
#ifdef CONFIG_AEABI
@@ -343,6 +350,7 @@
UNWIND(.fnend)
ENDPROC(__aeabi_uidivmod)
+EXPORT_SYMBOL(__aeabi_uidivmod)
ENTRY(__aeabi_idivmod)
UNWIND(.fnstart)
@@ -356,6 +364,7 @@
UNWIND(.fnend)
ENDPROC(__aeabi_idivmod)
+EXPORT_SYMBOL(__aeabi_idivmod)
#endif
diff --git a/arch/arm/lib/lshrdi3.S b/arch/arm/lib/lshrdi3.S
index 922dcd8..e408339 100644
--- a/arch/arm/lib/lshrdi3.S
+++ b/arch/arm/lib/lshrdi3.S
@@ -28,6 +28,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
#ifdef __ARMEB__
#define al r1
@@ -52,3 +53,5 @@
ENDPROC(__lshrdi3)
ENDPROC(__aeabi_llsr)
+EXPORT_SYMBOL(__lshrdi3)
+EXPORT_SYMBOL(__aeabi_llsr)
diff --git a/arch/arm/lib/memchr.S b/arch/arm/lib/memchr.S
index 74a5bed..44182bf 100644
--- a/arch/arm/lib/memchr.S
+++ b/arch/arm/lib/memchr.S
@@ -11,6 +11,7 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
.text
.align 5
@@ -24,3 +25,4 @@
2: movne r0, #0
ret lr
ENDPROC(memchr)
+EXPORT_SYMBOL(memchr)
diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S
index 64111bd..1be5b6d 100644
--- a/arch/arm/lib/memcpy.S
+++ b/arch/arm/lib/memcpy.S
@@ -13,6 +13,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/unwind.h>
+#include <asm/export.h>
#define LDR1W_SHIFT 0
#define STR1W_SHIFT 0
@@ -68,3 +69,5 @@
ENDPROC(memcpy)
ENDPROC(mmiocpy)
+EXPORT_SYMBOL(memcpy)
+EXPORT_SYMBOL(mmiocpy)
diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S
index 69a9d47..71dcc54 100644
--- a/arch/arm/lib/memmove.S
+++ b/arch/arm/lib/memmove.S
@@ -13,6 +13,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/unwind.h>
+#include <asm/export.h>
.text
@@ -225,3 +226,4 @@
18: backward_copy_shift push=24 pull=8
ENDPROC(memmove)
+EXPORT_SYMBOL(memmove)
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index 3c65e3b..7b72044 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -12,6 +12,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/unwind.h>
+#include <asm/export.h>
.text
.align 5
@@ -135,3 +136,5 @@
UNWIND( .fnend )
ENDPROC(memset)
ENDPROC(mmioset)
+EXPORT_SYMBOL(memset)
+EXPORT_SYMBOL(mmioset)
diff --git a/arch/arm/lib/memzero.S b/arch/arm/lib/memzero.S
index 0eded95..6dec26e 100644
--- a/arch/arm/lib/memzero.S
+++ b/arch/arm/lib/memzero.S
@@ -10,6 +10,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/unwind.h>
+#include <asm/export.h>
.text
.align 5
@@ -135,3 +136,4 @@
ret lr @ 1
UNWIND( .fnend )
ENDPROC(__memzero)
+EXPORT_SYMBOL(__memzero)
diff --git a/arch/arm/lib/muldi3.S b/arch/arm/lib/muldi3.S
index 2043059..b8f1238 100644
--- a/arch/arm/lib/muldi3.S
+++ b/arch/arm/lib/muldi3.S
@@ -12,6 +12,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
#ifdef __ARMEB__
#define xh r0
@@ -46,3 +47,5 @@
ENDPROC(__muldi3)
ENDPROC(__aeabi_lmul)
+EXPORT_SYMBOL(__muldi3)
+EXPORT_SYMBOL(__aeabi_lmul)
diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S
index 38d660d..11de126 100644
--- a/arch/arm/lib/putuser.S
+++ b/arch/arm/lib/putuser.S
@@ -31,6 +31,7 @@
#include <asm/assembler.h>
#include <asm/errno.h>
#include <asm/domain.h>
+#include <asm/export.h>
ENTRY(__put_user_1)
check_uaccess r0, 1, r1, ip, __put_user_bad
@@ -38,6 +39,7 @@
mov r0, #0
ret lr
ENDPROC(__put_user_1)
+EXPORT_SYMBOL(__put_user_1)
ENTRY(__put_user_2)
check_uaccess r0, 2, r1, ip, __put_user_bad
@@ -62,6 +64,7 @@
mov r0, #0
ret lr
ENDPROC(__put_user_2)
+EXPORT_SYMBOL(__put_user_2)
ENTRY(__put_user_4)
check_uaccess r0, 4, r1, ip, __put_user_bad
@@ -69,6 +72,7 @@
mov r0, #0
ret lr
ENDPROC(__put_user_4)
+EXPORT_SYMBOL(__put_user_4)
ENTRY(__put_user_8)
check_uaccess r0, 8, r1, ip, __put_user_bad
@@ -82,6 +86,7 @@
mov r0, #0
ret lr
ENDPROC(__put_user_8)
+EXPORT_SYMBOL(__put_user_8)
__put_user_bad:
mov r0, #-EFAULT
diff --git a/arch/arm/lib/strchr.S b/arch/arm/lib/strchr.S
index 013d64c..7301f6e6 100644
--- a/arch/arm/lib/strchr.S
+++ b/arch/arm/lib/strchr.S
@@ -11,6 +11,7 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
.text
.align 5
@@ -25,3 +26,4 @@
subeq r0, r0, #1
ret lr
ENDPROC(strchr)
+EXPORT_SYMBOL(strchr)
diff --git a/arch/arm/lib/strrchr.S b/arch/arm/lib/strrchr.S
index 3cec1c7..aaf9fd9 100644
--- a/arch/arm/lib/strrchr.S
+++ b/arch/arm/lib/strrchr.S
@@ -11,6 +11,7 @@
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
.text
.align 5
@@ -24,3 +25,4 @@
mov r0, r3
ret lr
ENDPROC(strrchr)
+EXPORT_SYMBOL(strrchr)
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index 6bd1089..1626e3a 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -19,6 +19,7 @@
#include <linux/gfp.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
+#include <linux/export.h>
#include <asm/current.h>
#include <asm/page.h>
@@ -156,6 +157,7 @@ arm_copy_to_user(void __user *to, const void *from, unsigned long n)
}
return n;
}
+EXPORT_SYMBOL(arm_copy_to_user);
static unsigned long noinline
__clear_user_memset(void __user *addr, unsigned long n)
@@ -213,6 +215,7 @@ unsigned long arm_clear_user(void __user *addr, unsigned long n)
}
return n;
}
+EXPORT_SYMBOL(arm_clear_user);
#if 0
diff --git a/arch/arm/lib/ucmpdi2.S b/arch/arm/lib/ucmpdi2.S
index ad4a630..127a91a 100644
--- a/arch/arm/lib/ucmpdi2.S
+++ b/arch/arm/lib/ucmpdi2.S
@@ -12,6 +12,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
#ifdef __ARMEB__
#define xh r0
@@ -35,6 +36,7 @@
ret lr
ENDPROC(__ucmpdi2)
+EXPORT_SYMBOL(__ucmpdi2)
#ifdef CONFIG_AEABI
@@ -48,6 +50,7 @@
ret lr
ENDPROC(__aeabi_ulcmp)
+EXPORT_SYMBOL(__aeabi_ulcmp)
#endif
diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile
index cab1289..737450f 100644
--- a/arch/arm/mach-imx/Makefile
+++ b/arch/arm/mach-imx/Makefile
@@ -32,7 +32,6 @@
ifdef CONFIG_SND_IMX_SOC
obj-y += ssi-fiq.o
-obj-y += ssi-fiq-ksym.o
endif
# i.MX21 based machines
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index 0df062d..b54db47 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -408,7 +408,7 @@ static struct genpd_onecell_data imx_gpc_onecell_data = {
static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg)
{
struct clk *clk;
- int i;
+ int i, ret;
imx6q_pu_domain.reg = pu_reg;
@@ -430,13 +430,22 @@ static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg)
if (!IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS))
return 0;
- pm_genpd_init(&imx6q_pu_domain.base, NULL, false);
- return of_genpd_add_provider_onecell(dev->of_node,
- &imx_gpc_onecell_data);
+ for (i = 0; i < ARRAY_SIZE(imx_gpc_domains); i++)
+ pm_genpd_init(imx_gpc_domains[i], NULL, false);
+ ret = of_genpd_add_provider_onecell(dev->of_node,
+ &imx_gpc_onecell_data);
+ if (ret)
+ goto power_off;
+
+ return 0;
+
+power_off:
+ imx6q_pm_pu_power_off(&imx6q_pu_domain.base);
clk_err:
while (i--)
clk_put(imx6q_pu_domain.clk[i]);
+ imx6q_pu_domain.reg = NULL;
return -EINVAL;
}
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index 97fd251..45801b2 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -173,7 +173,7 @@ static void __init imx6q_enet_phy_init(void)
ksz9021rn_phy_fixup);
phy_register_fixup_for_uid(PHY_ID_KSZ9031, MICREL_PHY_ID_MASK,
ksz9031rn_phy_fixup);
- phy_register_fixup_for_uid(PHY_ID_AR8031, 0xffffffff,
+ phy_register_fixup_for_uid(PHY_ID_AR8031, 0xffffffef,
ar8031_phy_fixup);
phy_register_fixup_for_uid(PHY_ID_AR8035, 0xffffffef,
ar8035_phy_fixup);
diff --git a/arch/arm/mach-imx/ssi-fiq-ksym.c b/arch/arm/mach-imx/ssi-fiq-ksym.c
deleted file mode 100644
index 792090f..0000000
--- a/arch/arm/mach-imx/ssi-fiq-ksym.c
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * Exported ksyms for the SSI FIQ handler
- *
- * Copyright (C) 2009, Sascha Hauer <s.hauer@pengutronix.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/module.h>
-
-#include <linux/platform_data/asoc-imx-ssi.h>
-
-EXPORT_SYMBOL(imx_ssi_fiq_tx_buffer);
-EXPORT_SYMBOL(imx_ssi_fiq_rx_buffer);
-EXPORT_SYMBOL(imx_ssi_fiq_start);
-EXPORT_SYMBOL(imx_ssi_fiq_end);
-EXPORT_SYMBOL(imx_ssi_fiq_base);
-
diff --git a/arch/arm/mach-imx/ssi-fiq.S b/arch/arm/mach-imx/ssi-fiq.S
index a8b93c5..fd7917f 100644
--- a/arch/arm/mach-imx/ssi-fiq.S
+++ b/arch/arm/mach-imx/ssi-fiq.S
@@ -8,6 +8,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/export.h>
/*
* r8 = bit 0-15: tx offset, bit 16-31: tx buffer size
@@ -144,4 +145,8 @@
.word 0x0
.L_imx_ssi_fiq_end:
imx_ssi_fiq_end:
-
+EXPORT_SYMBOL(imx_ssi_fiq_tx_buffer)
+EXPORT_SYMBOL(imx_ssi_fiq_rx_buffer)
+EXPORT_SYMBOL(imx_ssi_fiq_start)
+EXPORT_SYMBOL(imx_ssi_fiq_end)
+EXPORT_SYMBOL(imx_ssi_fiq_base)
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index f9b6bd3..541647f 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -23,6 +23,7 @@
select CACHE_L2X0
select ARM_CPU_SUSPEND
select MACH_MVEBU_ANY
+ select MVEBU_CLK_COREDIV
config MACH_ARMADA_370
bool "Marvell Armada 370 boards"
@@ -32,7 +33,6 @@
select CPU_PJ4B
select MACH_MVEBU_V7
select PINCTRL_ARMADA_370
- select MVEBU_CLK_COREDIV
help
Say 'Y' here if you want your kernel to support boards based
on the Marvell Armada 370 SoC with device tree.
@@ -50,7 +50,6 @@
select HAVE_SMP
select MACH_MVEBU_V7
select PINCTRL_ARMADA_375
- select MVEBU_CLK_COREDIV
help
Say 'Y' here if you want your kernel to support boards based
on the Marvell Armada 375 SoC with device tree.
@@ -68,7 +67,6 @@
select HAVE_SMP
select MACH_MVEBU_V7
select PINCTRL_ARMADA_38X
- select MVEBU_CLK_COREDIV
help
Say 'Y' here if you want your kernel to support boards based
on the Marvell Armada 380/385 SoC with device tree.
diff --git a/arch/arm/mach-uniphier/Kconfig b/arch/arm/mach-uniphier/Kconfig
index 82dddee..3930fbb 100644
--- a/arch/arm/mach-uniphier/Kconfig
+++ b/arch/arm/mach-uniphier/Kconfig
@@ -1,6 +1,7 @@
config ARCH_UNIPHIER
bool "Socionext UniPhier SoCs"
depends on ARCH_MULTI_V7
+ select ARCH_HAS_RESET_CONTROLLER
select ARM_AMBA
select ARM_GLOBAL_TIMER
select ARM_GIC
diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S
index 6d8e8e3..4cdfab3 100644
--- a/arch/arm/mm/abort-lv4t.S
+++ b/arch/arm/mm/abort-lv4t.S
@@ -7,7 +7,7 @@
* : r4 = aborted context pc
* : r5 = aborted context psr
*
- * Returns : r4-r5, r10-r11, r13 preserved
+ * Returns : r4-r5, r9-r11, r13 preserved
*
* Purpose : obtain information about current aborted instruction.
* Note: we read user space. This means we might cause a data
@@ -48,7 +48,10 @@
/* c */ b do_DataAbort @ ldc rd, [rn], #m @ Same as ldr rd, [rn], #m
/* d */ b do_DataAbort @ ldc rd, [rn, #m]
/* e */ b .data_unknown
-/* f */
+/* f */ b .data_unknown
+
+.data_unknown_r9:
+ ldr r9, [sp], #4
.data_unknown: @ Part of jumptable
mov r0, r4
mov r1, r8
@@ -57,6 +60,7 @@
.data_arm_ldmstm:
tst r8, #1 << 21 @ check writeback bit
beq do_DataAbort @ no writeback -> no fixup
+ str r9, [sp, #-4]!
mov r7, #0x11
orr r7, r7, #0x1100
and r6, r8, r7
@@ -75,12 +79,14 @@
subne r7, r7, r6, lsl #2 @ Undo increment
addeq r7, r7, r6, lsl #2 @ Undo decrement
str r7, [r2, r9, lsr #14] @ Put register 'Rn'
+ ldr r9, [sp], #4
b do_DataAbort
.data_arm_lateldrhpre:
tst r8, #1 << 21 @ Check writeback bit
beq do_DataAbort @ No writeback -> no fixup
.data_arm_lateldrhpost:
+ str r9, [sp, #-4]!
and r9, r8, #0x00f @ get Rm / low nibble of immediate value
tst r8, #1 << 22 @ if (immediate offset)
andne r6, r8, #0xf00 @ { immediate high nibble
@@ -93,6 +99,7 @@
subne r7, r7, r6 @ Undo incrmenet
addeq r7, r7, r6 @ Undo decrement
str r7, [r2, r9, lsr #14] @ Put register 'Rn'
+ ldr r9, [sp], #4
b do_DataAbort
.data_arm_lateldrpreconst:
@@ -101,12 +108,14 @@
.data_arm_lateldrpostconst:
movs r6, r8, lsl #20 @ Get offset
beq do_DataAbort @ zero -> no fixup
+ str r9, [sp, #-4]!
and r9, r8, #15 << 16 @ Extract 'n' from instruction
ldr r7, [r2, r9, lsr #14] @ Get register 'Rn'
tst r8, #1 << 23 @ Check U bit
subne r7, r7, r6, lsr #20 @ Undo increment
addeq r7, r7, r6, lsr #20 @ Undo decrement
str r7, [r2, r9, lsr #14] @ Put register 'Rn'
+ ldr r9, [sp], #4
b do_DataAbort
.data_arm_lateldrprereg:
@@ -115,6 +124,7 @@
.data_arm_lateldrpostreg:
and r7, r8, #15 @ Extract 'm' from instruction
ldr r6, [r2, r7, lsl #2] @ Get register 'Rm'
+ str r9, [sp, #-4]!
mov r9, r8, lsr #7 @ get shift count
ands r9, r9, #31
and r7, r8, #0x70 @ get shift type
@@ -126,33 +136,33 @@
b .data_arm_apply_r6_and_rn
b .data_arm_apply_r6_and_rn @ 1: LSL #0
nop
- b .data_unknown @ 2: MUL?
+ b .data_unknown_r9 @ 2: MUL?
nop
- b .data_unknown @ 3: MUL?
+ b .data_unknown_r9 @ 3: MUL?
nop
mov r6, r6, lsr r9 @ 4: LSR #!0
b .data_arm_apply_r6_and_rn
mov r6, r6, lsr #32 @ 5: LSR #32
b .data_arm_apply_r6_and_rn
- b .data_unknown @ 6: MUL?
+ b .data_unknown_r9 @ 6: MUL?
nop
- b .data_unknown @ 7: MUL?
+ b .data_unknown_r9 @ 7: MUL?
nop
mov r6, r6, asr r9 @ 8: ASR #!0
b .data_arm_apply_r6_and_rn
mov r6, r6, asr #32 @ 9: ASR #32
b .data_arm_apply_r6_and_rn
- b .data_unknown @ A: MUL?
+ b .data_unknown_r9 @ A: MUL?
nop
- b .data_unknown @ B: MUL?
+ b .data_unknown_r9 @ B: MUL?
nop
mov r6, r6, ror r9 @ C: ROR #!0
b .data_arm_apply_r6_and_rn
mov r6, r6, rrx @ D: RRX
b .data_arm_apply_r6_and_rn
- b .data_unknown @ E: MUL?
+ b .data_unknown_r9 @ E: MUL?
nop
- b .data_unknown @ F: MUL?
+ b .data_unknown_r9 @ F: MUL?
.data_thumb_abort:
ldrh r8, [r4] @ read instruction
@@ -190,6 +200,7 @@
.data_thumb_pushpop:
tst r8, #1 << 10
beq .data_unknown
+ str r9, [sp, #-4]!
and r6, r8, #0x55 @ hweight8(r8) + R bit
and r9, r8, #0xaa
add r6, r6, r9, lsr #1
@@ -204,9 +215,11 @@
addeq r7, r7, r6, lsl #2 @ increment SP if PUSH
subne r7, r7, r6, lsl #2 @ decrement SP if POP
str r7, [r2, #13 << 2]
+ ldr r9, [sp], #4
b do_DataAbort
.data_thumb_ldmstm:
+ str r9, [sp, #-4]!
and r6, r8, #0x55 @ hweight8(r8)
and r9, r8, #0xaa
add r6, r6, r9, lsr #1
@@ -219,4 +232,5 @@
and r6, r6, #15 @ number of regs to transfer
sub r7, r7, r6, lsl #2 @ always decrement
str r7, [r2, r9, lsr #6]
+ ldr r9, [sp], #4
b do_DataAbort
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 30398db..969ef88 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -915,7 +915,7 @@
config RANDOMIZE_MODULE_REGION_FULL
bool "Randomize the module region independently from the core kernel"
- depends on RANDOMIZE_BASE
+ depends on RANDOMIZE_BASE && !DYNAMIC_FTRACE
default y
help
Randomizes the location of the module region without considering the
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index cfbdf02..101794f 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -190,6 +190,7 @@
config ARCH_UNIPHIER
bool "Socionext UniPhier SoC Family"
+ select ARCH_HAS_RESET_CONTROLLER
select PINCTRL
help
This enables support for Socionext UniPhier SoC family.
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index ab51aed..3635b86 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -15,7 +15,7 @@
GZFLAGS :=-9
ifneq ($(CONFIG_RELOCATABLE),)
-LDFLAGS_vmlinux += -pie -Bsymbolic
+LDFLAGS_vmlinux += -pie -shared -Bsymbolic
endif
ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)
diff --git a/arch/arm64/boot/dts/broadcom/ns2-svk.dts b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
index 2d7872a..c4d5442 100644
--- a/arch/arm64/boot/dts/broadcom/ns2-svk.dts
+++ b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
@@ -56,6 +56,10 @@
};
};
+&enet {
+ status = "ok";
+};
+
&pci_phy0 {
status = "ok";
};
@@ -164,6 +168,8 @@
nand-ecc-mode = "hw";
nand-ecc-strength = <8>;
nand-ecc-step-size = <512>;
+ nand-bus-width = <16>;
+ brcm,nand-oob-sector-size = <16>;
#address-cells = <1>;
#size-cells = <1>;
};
@@ -172,6 +178,7 @@
&mdio_mux_iproc {
mdio@10 {
gphy0: eth-phy@10 {
+ enet-phy-lane-swap;
reg = <0x10>;
};
};
diff --git a/arch/arm64/boot/dts/broadcom/ns2.dtsi b/arch/arm64/boot/dts/broadcom/ns2.dtsi
index d95dc40..773ed59 100644
--- a/arch/arm64/boot/dts/broadcom/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/ns2.dtsi
@@ -191,6 +191,18 @@
#include "ns2-clock.dtsi"
+ enet: ethernet@61000000 {
+ compatible = "brcm,ns2-amac";
+ reg = <0x61000000 0x1000>,
+ <0x61090000 0x1000>,
+ <0x61030000 0x100>;
+ reg-names = "amac_base", "idm_base", "nicpm_base";
+ interrupts = <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>;
+ phy-handle = <&gphy0>;
+ phy-mode = "rgmii";
+ status = "disabled";
+ };
+
dma0: dma@61360000 {
compatible = "arm,pl330", "arm,primecell";
reg = <0x61360000 0x1000>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index 58635f7..97d331e 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -123,6 +123,7 @@
<1 14 0xf08>, /* Physical Non-Secure PPI */
<1 11 0xf08>, /* Virtual PPI */
<1 10 0xf08>; /* Hypervisor PPI */
+ fsl,erratum-a008585;
};
pmu {
@@ -502,10 +503,11 @@
};
sata: sata@3200000 {
- compatible = "fsl,ls1043a-ahci", "fsl,ls1021a-ahci";
+ compatible = "fsl,ls1043a-ahci";
reg = <0x0 0x3200000 0x0 0x10000>;
interrupts = <0 69 0x4>;
clocks = <&clockgen 4 0>;
+ dma-coherent;
};
msi1: msi-controller1@1571000 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
index d105976..7f0dc13 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
@@ -195,6 +195,7 @@
<1 14 4>, /* Physical Non-Secure PPI, active-low */
<1 11 4>, /* Virtual PPI, active-low */
<1 10 4>; /* Hypervisor PPI, active-low */
+ fsl,erratum-a008585;
};
pmu {
@@ -683,6 +684,7 @@
reg = <0x0 0x3200000 0x0 0x10000>;
interrupts = <0 133 0x4>; /* Level high type */
clocks = <&clockgen 4 3>;
+ dma-coherent;
};
sata1: sata@3210000 {
@@ -691,6 +693,7 @@
reg = <0x0 0x3210000 0x0 0x10000>;
interrupts = <0 136 0x4>; /* Level high type */
clocks = <&clockgen 4 3>;
+ dma-coherent;
};
usb0: usb3@3100000 {
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
index e5e3ed6..602e2c2 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
@@ -131,7 +131,7 @@
#address-cells = <0x1>;
#size-cells = <0x0>;
cell-index = <1>;
- clocks = <&cpm_syscon0 0 3>;
+ clocks = <&cpm_syscon0 1 21>;
status = "disabled";
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts b/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts
index 46cdddf..e5eeca2 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3368-geekbox.dts
@@ -116,7 +116,6 @@
cap-mmc-highspeed;
clock-frequency = <150000000>;
disable-wp;
- keep-power-in-suspend;
non-removable;
num-slots = <1>;
vmmc-supply = <&vcc_io>;
@@ -258,8 +257,6 @@
};
vcc_sd: SWITCH_REG1 {
- regulator-always-on;
- regulator-boot-on;
regulator-name = "vcc_sd";
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts b/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts
index 5797933..ea0a8ec 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3368-orion-r68-meta.dts
@@ -152,8 +152,6 @@
gpio = <&gpio3 11 GPIO_ACTIVE_LOW>;
regulator-min-microvolt = <1800000>;
regulator-max-microvolt = <3300000>;
- regulator-always-on;
- regulator-boot-on;
vin-supply = <&vcc_io>;
};
@@ -201,7 +199,6 @@
bus-width = <8>;
cap-mmc-highspeed;
disable-wp;
- keep-power-in-suspend;
mmc-pwrseq = <&emmc_pwrseq>;
mmc-hs200-1_2v;
mmc-hs200-1_8v;
@@ -350,7 +347,6 @@
clock-freq-min-max = <400000 50000000>;
cap-sd-highspeed;
card-detect-delay = <200>;
- keep-power-in-suspend;
num-slots = <1>;
pinctrl-names = "default";
pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd &sdmmc_bus4>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index b65c193..7afbfb0 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -300,8 +300,11 @@
ranges = <0x83000000 0x0 0xfa000000 0x0 0xfa000000 0x0 0x600000
0x81000000 0x0 0xfa600000 0x0 0xfa600000 0x0 0x100000>;
resets = <&cru SRST_PCIE_CORE>, <&cru SRST_PCIE_MGMT>,
- <&cru SRST_PCIE_MGMT_STICKY>, <&cru SRST_PCIE_PIPE>;
- reset-names = "core", "mgmt", "mgmt-sticky", "pipe";
+ <&cru SRST_PCIE_MGMT_STICKY>, <&cru SRST_PCIE_PIPE>,
+ <&cru SRST_PCIE_PM>, <&cru SRST_P_PCIE>,
+ <&cru SRST_A_PCIE>;
+ reset-names = "core", "mgmt", "mgmt-sticky", "pipe",
+ "pm", "pclk", "aclk";
status = "disabled";
pcie0_intc: interrupt-controller {
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
index 08fd7cf..56a1b2e 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
@@ -257,18 +257,18 @@
reg = <0x59801000 0x400>;
};
- mioctrl@59810000 {
- compatible = "socionext,uniphier-mioctrl",
+ sdctrl@59810000 {
+ compatible = "socionext,uniphier-ld20-sdctrl",
"simple-mfd", "syscon";
reg = <0x59810000 0x800>;
- mio_clk: clock {
- compatible = "socionext,uniphier-ld20-mio-clock";
+ sd_clk: clock {
+ compatible = "socionext,uniphier-ld20-sd-clock";
#clock-cells = <1>;
};
- mio_rst: reset {
- compatible = "socionext,uniphier-ld20-mio-reset";
+ sd_rst: reset {
+ compatible = "socionext,uniphier-ld20-sd-reset";
#reset-cells = <1>;
};
};
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index 39feb85..6e1cb8c 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -1,7 +1,7 @@
#ifndef __ASM_ALTERNATIVE_H
#define __ASM_ALTERNATIVE_H
-#include <asm/cpufeature.h>
+#include <asm/cpucaps.h>
#include <asm/insn.h>
#ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
new file mode 100644
index 0000000..87b4465
--- /dev/null
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -0,0 +1,40 @@
+/*
+ * arch/arm64/include/asm/cpucaps.h
+ *
+ * Copyright (C) 2016 ARM Ltd.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_CPUCAPS_H
+#define __ASM_CPUCAPS_H
+
+#define ARM64_WORKAROUND_CLEAN_CACHE 0
+#define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE 1
+#define ARM64_WORKAROUND_845719 2
+#define ARM64_HAS_SYSREG_GIC_CPUIF 3
+#define ARM64_HAS_PAN 4
+#define ARM64_HAS_LSE_ATOMICS 5
+#define ARM64_WORKAROUND_CAVIUM_23154 6
+#define ARM64_WORKAROUND_834220 7
+#define ARM64_HAS_NO_HW_PREFETCH 8
+#define ARM64_HAS_UAO 9
+#define ARM64_ALT_PAN_NOT_UAO 10
+#define ARM64_HAS_VIRT_HOST_EXTN 11
+#define ARM64_WORKAROUND_CAVIUM_27456 12
+#define ARM64_HAS_32BIT_EL0 13
+#define ARM64_HYP_OFFSET_LOW 14
+#define ARM64_MISMATCHED_CACHE_LINE_SIZE 15
+
+#define ARM64_NCAPS 16
+
+#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 758d74f..0bc0b1d 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -11,6 +11,7 @@
#include <linux/jump_label.h>
+#include <asm/cpucaps.h>
#include <asm/hwcap.h>
#include <asm/sysreg.h>
@@ -24,25 +25,6 @@
#define MAX_CPU_FEATURES (8 * sizeof(elf_hwcap))
#define cpu_feature(x) ilog2(HWCAP_ ## x)
-#define ARM64_WORKAROUND_CLEAN_CACHE 0
-#define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE 1
-#define ARM64_WORKAROUND_845719 2
-#define ARM64_HAS_SYSREG_GIC_CPUIF 3
-#define ARM64_HAS_PAN 4
-#define ARM64_HAS_LSE_ATOMICS 5
-#define ARM64_WORKAROUND_CAVIUM_23154 6
-#define ARM64_WORKAROUND_834220 7
-#define ARM64_HAS_NO_HW_PREFETCH 8
-#define ARM64_HAS_UAO 9
-#define ARM64_ALT_PAN_NOT_UAO 10
-#define ARM64_HAS_VIRT_HOST_EXTN 11
-#define ARM64_WORKAROUND_CAVIUM_27456 12
-#define ARM64_HAS_32BIT_EL0 13
-#define ARM64_HYP_OFFSET_LOW 14
-#define ARM64_MISMATCHED_CACHE_LINE_SIZE 15
-
-#define ARM64_NCAPS 16
-
#ifndef __ASSEMBLY__
#include <linux/kernel.h>
@@ -94,7 +76,7 @@ struct arm64_cpu_capabilities {
u16 capability;
int def_scope; /* default scope */
bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope);
- void (*enable)(void *); /* Called on all active CPUs */
+ int (*enable)(void *); /* Called on all active CPUs */
union {
struct { /* To be used for erratum handling only */
u32 midr_model;
diff --git a/arch/arm64/include/asm/exec.h b/arch/arm64/include/asm/exec.h
index db0563c..f7865dd 100644
--- a/arch/arm64/include/asm/exec.h
+++ b/arch/arm64/include/asm/exec.h
@@ -18,6 +18,9 @@
#ifndef __ASM_EXEC_H
#define __ASM_EXEC_H
+#include <linux/sched.h>
+
extern unsigned long arch_align_stack(unsigned long sp);
+void uao_thread_switch(struct task_struct *next);
#endif /* __ASM_EXEC_H */
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 18f7465..ec3553eb 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -54,6 +54,7 @@ extern char __kvm_hyp_vector[];
extern void __kvm_flush_vm_context(void);
extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
+extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index fd9d5fd..f5ea0ba 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -178,11 +178,6 @@ static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu)
return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV);
}
-static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
-{
- return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR);
-}
-
static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu)
{
return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE);
@@ -203,6 +198,12 @@ static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW);
}
+static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
+{
+ return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) ||
+ kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */
+}
+
static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
{
return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM);
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index bd94e67..e505038 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -62,6 +62,9 @@ struct kvm_arch {
/* VTTBR value associated with above pgd and vmid */
u64 vttbr;
+ /* The last vcpu id that ran on each physical CPU */
+ int __percpu *last_vcpu_ran;
+
/* The maximum number of vCPUs depends on the used GIC model */
int max_vcpus;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index a79b969..6f72fe8 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -128,7 +128,7 @@ static inline unsigned long __kern_hyp_va(unsigned long v)
return v;
}
-#define kern_hyp_va(v) (typeof(v))(__kern_hyp_va((unsigned long)(v)))
+#define kern_hyp_va(v) ((typeof(v))(__kern_hyp_va((unsigned long)(v))))
/*
* We currently only support a 40bit IPA.
diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h
index 23acc00..fc756e2 100644
--- a/arch/arm64/include/asm/lse.h
+++ b/arch/arm64/include/asm/lse.h
@@ -5,7 +5,6 @@
#include <linux/stringify.h>
#include <asm/alternative.h>
-#include <asm/cpufeature.h>
#ifdef __ASSEMBLER__
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index ba62df8..b71086d 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -217,7 +217,7 @@ static inline void *phys_to_virt(phys_addr_t x)
#define _virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
#else
#define __virt_to_pgoff(kaddr) (((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page))
-#define __page_to_voff(kaddr) (((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
+#define __page_to_voff(page) (((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
#define page_to_virt(page) ((void *)((__page_to_voff(page)) | PAGE_OFFSET))
#define virt_to_page(vaddr) ((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START))
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index e12af67..06ff7fd 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -17,6 +17,7 @@
#define __ASM_MODULE_H
#include <asm-generic/module.h>
+#include <asm/memory.h>
#define MODULE_ARCH_VERMAGIC "aarch64"
@@ -32,6 +33,10 @@ u64 module_emit_plt_entry(struct module *mod, const Elf64_Rela *rela,
Elf64_Sym *sym);
#ifdef CONFIG_RANDOMIZE_BASE
+#ifdef CONFIG_MODVERSIONS
+#define ARCH_RELOCATES_KCRCTAB
+#define reloc_start (kimage_vaddr - KIMAGE_VADDR)
+#endif
extern u64 module_alloc_base;
#else
#define module_alloc_base ((u64)_etext - MODULES_VSIZE)
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 2fee2f5..5394c84 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -44,48 +44,44 @@ static inline unsigned long __percpu_##op(void *ptr, \
\
switch (size) { \
case 1: \
- do { \
- asm ("//__per_cpu_" #op "_1\n" \
- "ldxrb %w[ret], %[ptr]\n" \
+ asm ("//__per_cpu_" #op "_1\n" \
+ "1: ldxrb %w[ret], %[ptr]\n" \
#asm_op " %w[ret], %w[ret], %w[val]\n" \
- "stxrb %w[loop], %w[ret], %[ptr]\n" \
- : [loop] "=&r" (loop), [ret] "=&r" (ret), \
- [ptr] "+Q"(*(u8 *)ptr) \
- : [val] "Ir" (val)); \
- } while (loop); \
+ " stxrb %w[loop], %w[ret], %[ptr]\n" \
+ " cbnz %w[loop], 1b" \
+ : [loop] "=&r" (loop), [ret] "=&r" (ret), \
+ [ptr] "+Q"(*(u8 *)ptr) \
+ : [val] "Ir" (val)); \
break; \
case 2: \
- do { \
- asm ("//__per_cpu_" #op "_2\n" \
- "ldxrh %w[ret], %[ptr]\n" \
+ asm ("//__per_cpu_" #op "_2\n" \
+ "1: ldxrh %w[ret], %[ptr]\n" \
#asm_op " %w[ret], %w[ret], %w[val]\n" \
- "stxrh %w[loop], %w[ret], %[ptr]\n" \
- : [loop] "=&r" (loop), [ret] "=&r" (ret), \
- [ptr] "+Q"(*(u16 *)ptr) \
- : [val] "Ir" (val)); \
- } while (loop); \
+ " stxrh %w[loop], %w[ret], %[ptr]\n" \
+ " cbnz %w[loop], 1b" \
+ : [loop] "=&r" (loop), [ret] "=&r" (ret), \
+ [ptr] "+Q"(*(u16 *)ptr) \
+ : [val] "Ir" (val)); \
break; \
case 4: \
- do { \
- asm ("//__per_cpu_" #op "_4\n" \
- "ldxr %w[ret], %[ptr]\n" \
+ asm ("//__per_cpu_" #op "_4\n" \
+ "1: ldxr %w[ret], %[ptr]\n" \
#asm_op " %w[ret], %w[ret], %w[val]\n" \
- "stxr %w[loop], %w[ret], %[ptr]\n" \
- : [loop] "=&r" (loop), [ret] "=&r" (ret), \
- [ptr] "+Q"(*(u32 *)ptr) \
- : [val] "Ir" (val)); \
- } while (loop); \
+ " stxr %w[loop], %w[ret], %[ptr]\n" \
+ " cbnz %w[loop], 1b" \
+ : [loop] "=&r" (loop), [ret] "=&r" (ret), \
+ [ptr] "+Q"(*(u32 *)ptr) \
+ : [val] "Ir" (val)); \
break; \
case 8: \
- do { \
- asm ("//__per_cpu_" #op "_8\n" \
- "ldxr %[ret], %[ptr]\n" \
+ asm ("//__per_cpu_" #op "_8\n" \
+ "1: ldxr %[ret], %[ptr]\n" \
#asm_op " %[ret], %[ret], %[val]\n" \
- "stxr %w[loop], %[ret], %[ptr]\n" \
- : [loop] "=&r" (loop), [ret] "=&r" (ret), \
- [ptr] "+Q"(*(u64 *)ptr) \
- : [val] "Ir" (val)); \
- } while (loop); \
+ " stxr %w[loop], %[ret], %[ptr]\n" \
+ " cbnz %w[loop], 1b" \
+ : [loop] "=&r" (loop), [ret] "=&r" (ret), \
+ [ptr] "+Q"(*(u64 *)ptr) \
+ : [val] "Ir" (val)); \
break; \
default: \
BUILD_BUG(); \
@@ -150,44 +146,40 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
switch (size) {
case 1:
- do {
- asm ("//__percpu_xchg_1\n"
- "ldxrb %w[ret], %[ptr]\n"
- "stxrb %w[loop], %w[val], %[ptr]\n"
- : [loop] "=&r"(loop), [ret] "=&r"(ret),
- [ptr] "+Q"(*(u8 *)ptr)
- : [val] "r" (val));
- } while (loop);
+ asm ("//__percpu_xchg_1\n"
+ "1: ldxrb %w[ret], %[ptr]\n"
+ " stxrb %w[loop], %w[val], %[ptr]\n"
+ " cbnz %w[loop], 1b"
+ : [loop] "=&r"(loop), [ret] "=&r"(ret),
+ [ptr] "+Q"(*(u8 *)ptr)
+ : [val] "r" (val));
break;
case 2:
- do {
- asm ("//__percpu_xchg_2\n"
- "ldxrh %w[ret], %[ptr]\n"
- "stxrh %w[loop], %w[val], %[ptr]\n"
- : [loop] "=&r"(loop), [ret] "=&r"(ret),
- [ptr] "+Q"(*(u16 *)ptr)
- : [val] "r" (val));
- } while (loop);
+ asm ("//__percpu_xchg_2\n"
+ "1: ldxrh %w[ret], %[ptr]\n"
+ " stxrh %w[loop], %w[val], %[ptr]\n"
+ " cbnz %w[loop], 1b"
+ : [loop] "=&r"(loop), [ret] "=&r"(ret),
+ [ptr] "+Q"(*(u16 *)ptr)
+ : [val] "r" (val));
break;
case 4:
- do {
- asm ("//__percpu_xchg_4\n"
- "ldxr %w[ret], %[ptr]\n"
- "stxr %w[loop], %w[val], %[ptr]\n"
- : [loop] "=&r"(loop), [ret] "=&r"(ret),
- [ptr] "+Q"(*(u32 *)ptr)
- : [val] "r" (val));
- } while (loop);
+ asm ("//__percpu_xchg_4\n"
+ "1: ldxr %w[ret], %[ptr]\n"
+ " stxr %w[loop], %w[val], %[ptr]\n"
+ " cbnz %w[loop], 1b"
+ : [loop] "=&r"(loop), [ret] "=&r"(ret),
+ [ptr] "+Q"(*(u32 *)ptr)
+ : [val] "r" (val));
break;
case 8:
- do {
- asm ("//__percpu_xchg_8\n"
- "ldxr %[ret], %[ptr]\n"
- "stxr %w[loop], %[val], %[ptr]\n"
- : [loop] "=&r"(loop), [ret] "=&r"(ret),
- [ptr] "+Q"(*(u64 *)ptr)
- : [val] "r" (val));
- } while (loop);
+ asm ("//__percpu_xchg_8\n"
+ "1: ldxr %[ret], %[ptr]\n"
+ " stxr %w[loop], %[val], %[ptr]\n"
+ " cbnz %w[loop], 1b"
+ : [loop] "=&r"(loop), [ret] "=&r"(ret),
+ [ptr] "+Q"(*(u64 *)ptr)
+ : [val] "r" (val));
break;
default:
BUILD_BUG();
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index df2e53d..60e3482 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -188,8 +188,8 @@ static inline void spin_lock_prefetch(const void *ptr)
#endif
-void cpu_enable_pan(void *__unused);
-void cpu_enable_uao(void *__unused);
-void cpu_enable_cache_maint_trap(void *__unused);
+int cpu_enable_pan(void *__unused);
+int cpu_enable_uao(void *__unused);
+int cpu_enable_cache_maint_trap(void *__unused);
#endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index e8d46e8..6c80b36 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -286,7 +286,7 @@ asm(
#define write_sysreg_s(v, r) do { \
u64 __val = (u64)v; \
- asm volatile("msr_s " __stringify(r) ", %0" : : "rZ" (__val)); \
+ asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val)); \
} while (0)
static inline void config_sctlr_el1(u32 clear, u32 set)
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index c47257c9..55d0adb 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -21,6 +21,7 @@
/*
* User space memory access functions
*/
+#include <linux/bitops.h>
#include <linux/kasan-checks.h>
#include <linux/string.h>
#include <linux/thread_info.h>
@@ -102,6 +103,13 @@ static inline void set_fs(mm_segment_t fs)
flag; \
})
+/*
+ * When dealing with data aborts or instruction traps we may end up with
+ * a tagged userland pointer. Clear the tag to get a sane pointer to pass
+ * on to access_ok(), for instance.
+ */
+#define untagged_addr(addr) sign_extend64(addr, 55)
+
#define access_ok(type, addr, size) __range_ok(addr, size)
#define user_addr_max get_fs
@@ -278,14 +286,16 @@ static inline unsigned long __must_check __copy_to_user(void __user *to, const v
static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
{
+ unsigned long res = n;
kasan_check_write(to, n);
if (access_ok(VERIFY_READ, from, n)) {
check_object_size(to, n, false);
- n = __arch_copy_from_user(to, from, n);
- } else /* security hole - plug it */
- memset(to, 0, n);
- return n;
+ res = __arch_copy_from_user(to, from, n);
+ }
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n)
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 42ffdb54..b0988bb 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -280,35 +280,43 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table)
/*
* Error-checking SWP macros implemented using ldxr{b}/stxr{b}
*/
-#define __user_swpX_asm(data, addr, res, temp, B) \
+
+/* Arbitrary constant to ensure forward-progress of the LL/SC loop */
+#define __SWP_LL_SC_LOOPS 4
+
+#define __user_swpX_asm(data, addr, res, temp, temp2, B) \
__asm__ __volatile__( \
+ " mov %w3, %w7\n" \
ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, \
CONFIG_ARM64_PAN) \
- "0: ldxr"B" %w2, [%3]\n" \
- "1: stxr"B" %w0, %w1, [%3]\n" \
+ "0: ldxr"B" %w2, [%4]\n" \
+ "1: stxr"B" %w0, %w1, [%4]\n" \
" cbz %w0, 2f\n" \
- " mov %w0, %w4\n" \
+ " sub %w3, %w3, #1\n" \
+ " cbnz %w3, 0b\n" \
+ " mov %w0, %w5\n" \
" b 3f\n" \
"2:\n" \
" mov %w1, %w2\n" \
"3:\n" \
" .pushsection .fixup,\"ax\"\n" \
" .align 2\n" \
- "4: mov %w0, %w5\n" \
+ "4: mov %w0, %w6\n" \
" b 3b\n" \
" .popsection" \
_ASM_EXTABLE(0b, 4b) \
_ASM_EXTABLE(1b, 4b) \
ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, \
CONFIG_ARM64_PAN) \
- : "=&r" (res), "+r" (data), "=&r" (temp) \
- : "r" (addr), "i" (-EAGAIN), "i" (-EFAULT) \
+ : "=&r" (res), "+r" (data), "=&r" (temp), "=&r" (temp2) \
+ : "r" (addr), "i" (-EAGAIN), "i" (-EFAULT), \
+ "i" (__SWP_LL_SC_LOOPS) \
: "memory")
-#define __user_swp_asm(data, addr, res, temp) \
- __user_swpX_asm(data, addr, res, temp, "")
-#define __user_swpb_asm(data, addr, res, temp) \
- __user_swpX_asm(data, addr, res, temp, "b")
+#define __user_swp_asm(data, addr, res, temp, temp2) \
+ __user_swpX_asm(data, addr, res, temp, temp2, "")
+#define __user_swpb_asm(data, addr, res, temp, temp2) \
+ __user_swpX_asm(data, addr, res, temp, temp2, "b")
/*
* Bit 22 of the instruction encoding distinguishes between
@@ -328,12 +336,12 @@ static int emulate_swpX(unsigned int address, unsigned int *data,
}
while (1) {
- unsigned long temp;
+ unsigned long temp, temp2;
if (type == TYPE_SWPB)
- __user_swpb_asm(*data, address, res, temp);
+ __user_swpb_asm(*data, address, res, temp, temp2);
else
- __user_swp_asm(*data, address, res, temp);
+ __user_swp_asm(*data, address, res, temp, temp2);
if (likely(res != -EAGAIN) || signal_pending(current))
break;
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 0150394..b75e917 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -39,10 +39,11 @@ has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry,
(arm64_ftr_reg_ctrel0.sys_val & arm64_ftr_reg_ctrel0.strict_mask);
}
-static void cpu_enable_trap_ctr_access(void *__unused)
+static int cpu_enable_trap_ctr_access(void *__unused)
{
/* Clear SCTLR_EL1.UCT */
config_sctlr_el1(SCTLR_EL1_UCT, 0);
+ return 0;
}
#define MIDR_RANGE(model, min, max) \
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index d577f26..c02504e 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -19,7 +19,9 @@
#define pr_fmt(fmt) "CPU features: " fmt
#include <linux/bsearch.h>
+#include <linux/cpumask.h>
#include <linux/sort.h>
+#include <linux/stop_machine.h>
#include <linux/types.h>
#include <asm/cpu.h>
#include <asm/cpufeature.h>
@@ -941,7 +943,13 @@ void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
{
for (; caps->matches; caps++)
if (caps->enable && cpus_have_cap(caps->capability))
- on_each_cpu(caps->enable, NULL, true);
+ /*
+ * Use stop_machine() as it schedules the work allowing
+ * us to modify PSTATE, instead of on_each_cpu() which
+ * uses an IPI, giving us a PSTATE that disappears when
+ * we return.
+ */
+ stop_machine(caps->enable, NULL, cpu_online_mask);
}
/*
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 427f6d3..332e331 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -586,8 +586,9 @@
b.lt 4f // Skip if no PMU present
mrs x0, pmcr_el0 // Disable debug access traps
ubfx x0, x0, #11, #5 // to EL2 and allow access to
- msr mdcr_el2, x0 // all PMU counters from EL1
4:
+ csel x0, xzr, x0, lt // all PMU counters from EL1
+ msr mdcr_el2, x0 // (if they exist)
/* Stage-2 translation */
msr vttbr_el2, xzr
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 27b2f138..01753cd 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -49,6 +49,7 @@
#include <asm/alternative.h>
#include <asm/compat.h>
#include <asm/cacheflush.h>
+#include <asm/exec.h>
#include <asm/fpsimd.h>
#include <asm/mmu_context.h>
#include <asm/processor.h>
@@ -186,10 +187,19 @@ void __show_regs(struct pt_regs *regs)
printk("pc : [<%016llx>] lr : [<%016llx>] pstate: %08llx\n",
regs->pc, lr, regs->pstate);
printk("sp : %016llx\n", sp);
- for (i = top_reg; i >= 0; i--) {
+
+ i = top_reg;
+
+ while (i >= 0) {
printk("x%-2d: %016llx ", i, regs->regs[i]);
- if (i % 2 == 0)
- printk("\n");
+ i--;
+
+ if (i % 2 == 0) {
+ pr_cont("x%-2d: %016llx ", i, regs->regs[i]);
+ i--;
+ }
+
+ pr_cont("\n");
}
printk("\n");
}
@@ -301,7 +311,7 @@ static void tls_thread_switch(struct task_struct *next)
}
/* Restore the UAO state depending on next's addr_limit */
-static void uao_thread_switch(struct task_struct *next)
+void uao_thread_switch(struct task_struct *next)
{
if (IS_ENABLED(CONFIG_ARM64_UAO)) {
if (task_thread_info(next)->addr_limit == KERNEL_DS)
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index b8799e7..1bec41b 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -135,7 +135,7 @@
#ifdef CONFIG_KASAN
mov x0, sp
- bl kasan_unpoison_remaining_stack
+ bl kasan_unpoison_task_stack_below
#endif
ldp x19, x20, [x29, #16]
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index d3f151c..8507703 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -544,6 +544,7 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
return;
}
bootcpu_valid = true;
+ early_map_cpu_to_node(0, acpi_numa_get_nid(0, hwid));
return;
}
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index ad73414..bb0cd78 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -1,8 +1,11 @@
#include <linux/ftrace.h>
#include <linux/percpu.h>
#include <linux/slab.h>
+#include <asm/alternative.h>
#include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
#include <asm/debug-monitors.h>
+#include <asm/exec.h>
#include <asm/pgtable.h>
#include <asm/memory.h>
#include <asm/mmu_context.h>
@@ -50,6 +53,14 @@ void notrace __cpu_suspend_exit(void)
set_my_cpu_offset(per_cpu_offset(cpu));
/*
+ * PSTATE was not saved over suspend/resume, re-enable any detected
+ * features that might not have been set correctly.
+ */
+ asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,
+ CONFIG_ARM64_PAN));
+ uao_thread_switch(current);
+
+ /*
* Restore HW breakpoint registers to sane values
* before debug exceptions are possibly reenabled
* through local_dbg_restore.
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 5ff020f..c9986b3 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -428,24 +428,28 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
}
-void cpu_enable_cache_maint_trap(void *__unused)
+int cpu_enable_cache_maint_trap(void *__unused)
{
config_sctlr_el1(SCTLR_EL1_UCI, 0);
+ return 0;
}
#define __user_cache_maint(insn, address, res) \
- asm volatile ( \
- "1: " insn ", %1\n" \
- " mov %w0, #0\n" \
- "2:\n" \
- " .pushsection .fixup,\"ax\"\n" \
- " .align 2\n" \
- "3: mov %w0, %w2\n" \
- " b 2b\n" \
- " .popsection\n" \
- _ASM_EXTABLE(1b, 3b) \
- : "=r" (res) \
- : "r" (address), "i" (-EFAULT) )
+ if (untagged_addr(address) >= user_addr_max()) \
+ res = -EFAULT; \
+ else \
+ asm volatile ( \
+ "1: " insn ", %1\n" \
+ " mov %w0, #0\n" \
+ "2:\n" \
+ " .pushsection .fixup,\"ax\"\n" \
+ " .align 2\n" \
+ "3: mov %w0, %w2\n" \
+ " b 2b\n" \
+ " .popsection\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : "=r" (res) \
+ : "r" (address), "i" (-EFAULT) )
static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
{
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index 9cc0ea7..88e2f2b 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -64,6 +64,21 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
write_sysreg(0, vttbr_el2);
}
+void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
+
+ /* Switch to requested VMID */
+ write_sysreg(kvm->arch.vttbr, vttbr_el2);
+ isb();
+
+ asm volatile("tlbi vmalle1" : : );
+ dsb(nsh);
+ isb();
+
+ write_sysreg(0, vttbr_el2);
+}
+
void __hyp_text __kvm_flush_vm_context(void)
{
dsb(ishst);
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 0b90497..4fd67ea 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -79,11 +79,6 @@
.section .fixup,"ax"
.align 2
-9998:
- sub x0, end, dst
-9999:
- strb wzr, [dst], #1 // zero remaining buffer space
- cmp dst, end
- b.lo 9999b
+9998: sub x0, end, dst // bytes not copied
ret
.previous
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 53d9159..0f87883 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -29,7 +29,9 @@
#include <linux/sched.h>
#include <linux/highmem.h>
#include <linux/perf_event.h>
+#include <linux/preempt.h>
+#include <asm/bug.h>
#include <asm/cpufeature.h>
#include <asm/exception.h>
#include <asm/debug-monitors.h>
@@ -670,9 +672,17 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
NOKPROBE_SYMBOL(do_debug_exception);
#ifdef CONFIG_ARM64_PAN
-void cpu_enable_pan(void *__unused)
+int cpu_enable_pan(void *__unused)
{
+ /*
+ * We modify PSTATE. This won't work from irq context as the PSTATE
+ * is discarded once we return from the exception.
+ */
+ WARN_ON_ONCE(in_interrupt());
+
config_sctlr_el1(SCTLR_EL1_SPAN, 0);
+ asm(SET_PSTATE_PAN(1));
+ return 0;
}
#endif /* CONFIG_ARM64_PAN */
@@ -683,8 +693,9 @@ void cpu_enable_pan(void *__unused)
* We need to enable the feature at runtime (instead of adding it to
* PSR_MODE_EL1h) as the feature may not be implemented by the cpu.
*/
-void cpu_enable_uao(void *__unused)
+int cpu_enable_uao(void *__unused)
{
asm(SET_PSTATE_UAO(1));
+ return 0;
}
#endif /* CONFIG_ARM64_UAO */
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 21c489b..212c4d1 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -421,35 +421,35 @@ void __init mem_init(void)
pr_notice("Virtual kernel memory layout:\n");
#ifdef CONFIG_KASAN
- pr_cont(" kasan : 0x%16lx - 0x%16lx (%6ld GB)\n",
+ pr_notice(" kasan : 0x%16lx - 0x%16lx (%6ld GB)\n",
MLG(KASAN_SHADOW_START, KASAN_SHADOW_END));
#endif
- pr_cont(" modules : 0x%16lx - 0x%16lx (%6ld MB)\n",
+ pr_notice(" modules : 0x%16lx - 0x%16lx (%6ld MB)\n",
MLM(MODULES_VADDR, MODULES_END));
- pr_cont(" vmalloc : 0x%16lx - 0x%16lx (%6ld GB)\n",
+ pr_notice(" vmalloc : 0x%16lx - 0x%16lx (%6ld GB)\n",
MLG(VMALLOC_START, VMALLOC_END));
- pr_cont(" .text : 0x%p" " - 0x%p" " (%6ld KB)\n",
+ pr_notice(" .text : 0x%p" " - 0x%p" " (%6ld KB)\n",
MLK_ROUNDUP(_text, _etext));
- pr_cont(" .rodata : 0x%p" " - 0x%p" " (%6ld KB)\n",
+ pr_notice(" .rodata : 0x%p" " - 0x%p" " (%6ld KB)\n",
MLK_ROUNDUP(__start_rodata, __init_begin));
- pr_cont(" .init : 0x%p" " - 0x%p" " (%6ld KB)\n",
+ pr_notice(" .init : 0x%p" " - 0x%p" " (%6ld KB)\n",
MLK_ROUNDUP(__init_begin, __init_end));
- pr_cont(" .data : 0x%p" " - 0x%p" " (%6ld KB)\n",
+ pr_notice(" .data : 0x%p" " - 0x%p" " (%6ld KB)\n",
MLK_ROUNDUP(_sdata, _edata));
- pr_cont(" .bss : 0x%p" " - 0x%p" " (%6ld KB)\n",
+ pr_notice(" .bss : 0x%p" " - 0x%p" " (%6ld KB)\n",
MLK_ROUNDUP(__bss_start, __bss_stop));
- pr_cont(" fixed : 0x%16lx - 0x%16lx (%6ld KB)\n",
+ pr_notice(" fixed : 0x%16lx - 0x%16lx (%6ld KB)\n",
MLK(FIXADDR_START, FIXADDR_TOP));
- pr_cont(" PCI I/O : 0x%16lx - 0x%16lx (%6ld MB)\n",
+ pr_notice(" PCI I/O : 0x%16lx - 0x%16lx (%6ld MB)\n",
MLM(PCI_IO_START, PCI_IO_END));
#ifdef CONFIG_SPARSEMEM_VMEMMAP
- pr_cont(" vmemmap : 0x%16lx - 0x%16lx (%6ld GB maximum)\n",
+ pr_notice(" vmemmap : 0x%16lx - 0x%16lx (%6ld GB maximum)\n",
MLG(VMEMMAP_START, VMEMMAP_START + VMEMMAP_SIZE));
- pr_cont(" 0x%16lx - 0x%16lx (%6ld MB actual)\n",
+ pr_notice(" 0x%16lx - 0x%16lx (%6ld MB actual)\n",
MLM((unsigned long)phys_to_page(memblock_start_of_DRAM()),
(unsigned long)virt_to_page(high_memory)));
#endif
- pr_cont(" memory : 0x%16lx - 0x%16lx (%6ld MB)\n",
+ pr_notice(" memory : 0x%16lx - 0x%16lx (%6ld MB)\n",
MLM(__phys_to_virt(memblock_start_of_DRAM()),
(unsigned long)high_memory));
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 778a985..4b32168 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -147,7 +147,7 @@ static int __init early_cpu_to_node(int cpu)
static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
{
- return node_distance(from, to);
+ return node_distance(early_cpu_to_node(from), early_cpu_to_node(to));
}
static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
@@ -223,8 +223,11 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
void *nd;
int tnid;
- pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
- nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
+ if (start_pfn < end_pfn)
+ pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n", nid,
+ start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
+ else
+ pr_info("Initmem setup node %d [<memory-less node>]\n", nid);
nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
nd = __va(nd_pa);
diff --git a/arch/blackfin/include/asm/uaccess.h b/arch/blackfin/include/asm/uaccess.h
index 0a2a700..0eff88a 100644
--- a/arch/blackfin/include/asm/uaccess.h
+++ b/arch/blackfin/include/asm/uaccess.h
@@ -163,18 +163,29 @@ static inline int bad_user_access_length(void)
: "a" (__ptr(ptr))); \
})
-#define __copy_from_user(to, from, n) copy_from_user(to, from, n)
-#define __copy_to_user(to, from, n) copy_to_user(to, from, n)
#define __copy_to_user_inatomic __copy_to_user
#define __copy_from_user_inatomic __copy_from_user
static inline unsigned long __must_check
+__copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ memcpy(to, (const void __force *)from, n);
+ return 0;
+}
+
+static inline unsigned long __must_check
+__copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+ memcpy((void __force *)to, from, n);
+ SSYNC();
+ return 0;
+}
+
+static inline unsigned long __must_check
copy_from_user(void *to, const void __user *from, unsigned long n)
{
- if (likely(access_ok(VERIFY_READ, from, n))) {
- memcpy(to, (const void __force *)from, n);
- return 0;
- }
+ if (likely(access_ok(VERIFY_READ, from, n)))
+ return __copy_from_user(to, from, n);
memset(to, 0, n);
return n;
}
@@ -182,12 +193,9 @@ copy_from_user(void *to, const void __user *from, unsigned long n)
static inline unsigned long __must_check
copy_to_user(void __user *to, const void *from, unsigned long n)
{
- if (access_ok(VERIFY_WRITE, to, n))
- memcpy((void __force *)to, from, n);
- else
- return n;
- SSYNC();
- return 0;
+ if (likely(access_ok(VERIFY_WRITE, to, n)))
+ return __copy_to_user(to, from, n);
+ return n;
}
/*
diff --git a/arch/blackfin/kernel/ptrace.c b/arch/blackfin/kernel/ptrace.c
index 8b8fe67..8d79286 100644
--- a/arch/blackfin/kernel/ptrace.c
+++ b/arch/blackfin/kernel/ptrace.c
@@ -271,7 +271,7 @@ long arch_ptrace(struct task_struct *child, long request,
case BFIN_MEM_ACCESS_CORE:
case BFIN_MEM_ACCESS_CORE_ONLY:
copied = access_process_vm(child, addr, &tmp,
- to_copy, 0);
+ to_copy, FOLL_FORCE);
if (copied)
break;
@@ -324,7 +324,8 @@ long arch_ptrace(struct task_struct *child, long request,
case BFIN_MEM_ACCESS_CORE:
case BFIN_MEM_ACCESS_CORE_ONLY:
copied = access_process_vm(child, addr, &data,
- to_copy, 1);
+ to_copy,
+ FOLL_FORCE | FOLL_WRITE);
break;
case BFIN_MEM_ACCESS_DMA:
if (safe_dma_memcpy(paddr, &data, to_copy))
diff --git a/arch/cris/arch-v32/drivers/cryptocop.c b/arch/cris/arch-v32/drivers/cryptocop.c
index b5698c8..0068fd4 100644
--- a/arch/cris/arch-v32/drivers/cryptocop.c
+++ b/arch/cris/arch-v32/drivers/cryptocop.c
@@ -2722,7 +2722,6 @@ static int cryptocop_ioctl_process(struct inode *inode, struct file *filp, unsig
err = get_user_pages((unsigned long int)(oper.indata + prev_ix),
noinpages,
0, /* read access only for in data */
- 0, /* no force */
inpages,
NULL);
@@ -2736,8 +2735,7 @@ static int cryptocop_ioctl_process(struct inode *inode, struct file *filp, unsig
if (oper.do_cipher){
err = get_user_pages((unsigned long int)oper.cipher_outdata,
nooutpages,
- 1, /* write access for out data */
- 0, /* no force */
+ FOLL_WRITE, /* write access for out data */
outpages,
NULL);
up_read(¤t->mm->mmap_sem);
@@ -3151,7 +3149,7 @@ static void print_dma_descriptors(struct cryptocop_int_operation *iop)
printk("print_dma_descriptors start\n");
printk("iop:\n");
- printk("\tsid: 0x%lld\n", iop->sid);
+ printk("\tsid: 0x%llx\n", iop->sid);
printk("\tcdesc_out: 0x%p\n", iop->cdesc_out);
printk("\tcdesc_in: 0x%p\n", iop->cdesc_in);
diff --git a/arch/cris/arch-v32/kernel/ptrace.c b/arch/cris/arch-v32/kernel/ptrace.c
index f085229..f0df654 100644
--- a/arch/cris/arch-v32/kernel/ptrace.c
+++ b/arch/cris/arch-v32/kernel/ptrace.c
@@ -147,7 +147,7 @@ long arch_ptrace(struct task_struct *child, long request,
/* The trampoline page is globally mapped, no page table to traverse.*/
tmp = *(unsigned long*)addr;
} else {
- copied = access_process_vm(child, addr, &tmp, sizeof(tmp), 0);
+ copied = access_process_vm(child, addr, &tmp, sizeof(tmp), FOLL_FORCE);
if (copied != sizeof(tmp))
break;
@@ -279,7 +279,7 @@ static int insn_size(struct task_struct *child, unsigned long pc)
int opsize = 0;
/* Read the opcode at pc (do what PTRACE_PEEKTEXT would do). */
- copied = access_process_vm(child, pc, &opcode, sizeof(opcode), 0);
+ copied = access_process_vm(child, pc, &opcode, sizeof(opcode), FOLL_FORCE);
if (copied != sizeof(opcode))
return 0;
diff --git a/arch/h8300/include/asm/thread_info.h b/arch/h8300/include/asm/thread_info.h
index b408fe6..3cef068 100644
--- a/arch/h8300/include/asm/thread_info.h
+++ b/arch/h8300/include/asm/thread_info.h
@@ -31,7 +31,6 @@ struct thread_info {
int cpu; /* cpu we're on */
int preempt_count; /* 0 => preemptable, <0 => BUG */
mm_segment_t addr_limit;
- struct restart_block restart_block;
};
/*
@@ -44,9 +43,6 @@ struct thread_info {
.cpu = 0, \
.preempt_count = INIT_PREEMPT_COUNT, \
.addr_limit = KERNEL_DS, \
- .restart_block = { \
- .fn = do_no_restart_syscall, \
- }, \
}
#define init_thread_info (init_thread_union.thread_info)
diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c
index ad1f81f..7138303 100644
--- a/arch/h8300/kernel/signal.c
+++ b/arch/h8300/kernel/signal.c
@@ -79,7 +79,7 @@ restore_sigcontext(struct sigcontext *usc, int *pd0)
unsigned int er0;
/* Always make any pending restarted system calls return -EINTR */
- current_thread_info()->restart_block.fn = do_no_restart_syscall;
+ current->restart_block.fn = do_no_restart_syscall;
/* restore passed registers */
#define COPY(r) do { err |= get_user(regs->r, &usc->sc_##r); } while (0)
diff --git a/arch/ia64/hp/sim/boot/Makefile b/arch/ia64/hp/sim/boot/Makefile
index 2e805e0..df6e996 100644
--- a/arch/ia64/hp/sim/boot/Makefile
+++ b/arch/ia64/hp/sim/boot/Makefile
@@ -33,5 +33,5 @@
LDFLAGS_bootloader = -static -T
$(obj)/bootloader: $(src)/bootloader.lds $(obj)/bootloader.o $(obj)/boot_head.o $(obj)/fw-emu.o \
- lib/lib.a arch/ia64/lib/built-in.o arch/ia64/lib/lib.a FORCE
+ lib/lib.a arch/ia64/lib/lib.a FORCE
$(call if_changed,ld)
diff --git a/arch/ia64/include/asm/export.h b/arch/ia64/include/asm/export.h
new file mode 100644
index 0000000..ad18c65
--- /dev/null
+++ b/arch/ia64/include/asm/export.h
@@ -0,0 +1,3 @@
+/* EXPORT_DATA_SYMBOL != EXPORT_SYMBOL here */
+#define KSYM_FUNC(name) @fptr(name)
+#include <asm-generic/export.h>
diff --git a/arch/ia64/include/asm/libata-portmap.h b/arch/ia64/include/asm/libata-portmap.h
index 0e00c9a..7a1f831 100644
--- a/arch/ia64/include/asm/libata-portmap.h
+++ b/arch/ia64/include/asm/libata-portmap.h
@@ -1,12 +1,8 @@
#ifndef __ASM_IA64_LIBATA_PORTMAP_H
#define __ASM_IA64_LIBATA_PORTMAP_H
-#define ATA_PRIMARY_CMD 0x1F0
-#define ATA_PRIMARY_CTL 0x3F6
#define ATA_PRIMARY_IRQ(dev) isa_irq_to_vector(14)
-#define ATA_SECONDARY_CMD 0x170
-#define ATA_SECONDARY_CTL 0x376
#define ATA_SECONDARY_IRQ(dev) isa_irq_to_vector(15)
#endif
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index cfaa7b2..6f27a66 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -48,6 +48,7 @@
#include <asm/thread_info.h>
#include <asm/unistd.h>
#include <asm/ftrace.h>
+#include <asm/export.h>
#include "minstate.h"
@@ -1345,12 +1346,14 @@
mov rp=loc0
br.ret.sptk.many rp
END(unw_init_running)
+EXPORT_SYMBOL(unw_init_running)
#ifdef CONFIG_FUNCTION_TRACER
#ifdef CONFIG_DYNAMIC_FTRACE
GLOBAL_ENTRY(_mcount)
br ftrace_stub
END(_mcount)
+EXPORT_SYMBOL(_mcount)
.here:
br.ret.sptk.many b0
diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c
index 09f8457..5ed0ea9 100644
--- a/arch/ia64/kernel/err_inject.c
+++ b/arch/ia64/kernel/err_inject.c
@@ -142,7 +142,7 @@ store_virtual_to_phys(struct device *dev, struct device_attribute *attr,
u64 virt_addr=simple_strtoull(buf, NULL, 16);
int ret;
- ret = get_user_pages(virt_addr, 1, VM_READ, 0, NULL, NULL);
+ ret = get_user_pages(virt_addr, 1, FOLL_WRITE, NULL, NULL);
if (ret<=0) {
#ifdef ERR_INJ_DEBUG
printk("Virtual address %lx is not existing.\n",virt_addr);
diff --git a/arch/ia64/kernel/esi_stub.S b/arch/ia64/kernel/esi_stub.S
index 6b3d6c1..2c369bf 100644
--- a/arch/ia64/kernel/esi_stub.S
+++ b/arch/ia64/kernel/esi_stub.S
@@ -35,6 +35,7 @@
#include <asm/processor.h>
#include <asm/asmmacro.h>
+#include <asm/export.h>
/*
* Inputs:
@@ -94,3 +95,4 @@
mov gp=loc2
br.ret.sptk.many rp
END(esi_call_phys)
+EXPORT_SYMBOL_GPL(esi_call_phys)
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index bb748c5..c9b5e94 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -32,6 +32,7 @@
#include <asm/mca_asm.h>
#include <linux/init.h>
#include <linux/linkage.h>
+#include <asm/export.h>
#ifdef CONFIG_HOTPLUG_CPU
#define SAL_PSR_BITS_TO_SET \
@@ -168,6 +169,7 @@
__PAGE_ALIGNED_DATA
.global empty_zero_page
+EXPORT_DATA_SYMBOL_GPL(empty_zero_page)
empty_zero_page:
.skip PAGE_SIZE
diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c
index 0967310..d111248 100644
--- a/arch/ia64/kernel/ia64_ksyms.c
+++ b/arch/ia64/kernel/ia64_ksyms.c
@@ -1,101 +1,11 @@
/*
* Architecture-specific kernel symbols
- *
- * Don't put any exports here unless it's defined in an assembler file.
- * All other exports should be put directly after the definition.
*/
-#include <linux/module.h>
-
-#include <linux/string.h>
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(strlen);
-
-#include <asm/pgtable.h>
-EXPORT_SYMBOL_GPL(empty_zero_page);
-
-#include <asm/checksum.h>
-EXPORT_SYMBOL(ip_fast_csum); /* hand-coded assembly */
-EXPORT_SYMBOL(csum_ipv6_magic);
-
-#include <asm/page.h>
-EXPORT_SYMBOL(clear_page);
-EXPORT_SYMBOL(copy_page);
-
#ifdef CONFIG_VIRTUAL_MEM_MAP
+#include <linux/compiler.h>
+#include <linux/export.h>
#include <linux/bootmem.h>
EXPORT_SYMBOL(min_low_pfn); /* defined by bootmem.c, but not exported by generic code */
EXPORT_SYMBOL(max_low_pfn); /* defined by bootmem.c, but not exported by generic code */
#endif
-
-#include <asm/processor.h>
-EXPORT_SYMBOL(ia64_cpu_info);
-#ifdef CONFIG_SMP
-EXPORT_SYMBOL(local_per_cpu_offset);
-#endif
-
-#include <asm/uaccess.h>
-EXPORT_SYMBOL(__copy_user);
-EXPORT_SYMBOL(__do_clear_user);
-EXPORT_SYMBOL(__strlen_user);
-EXPORT_SYMBOL(__strncpy_from_user);
-EXPORT_SYMBOL(__strnlen_user);
-
-/* from arch/ia64/lib */
-extern void __divsi3(void);
-extern void __udivsi3(void);
-extern void __modsi3(void);
-extern void __umodsi3(void);
-extern void __divdi3(void);
-extern void __udivdi3(void);
-extern void __moddi3(void);
-extern void __umoddi3(void);
-
-EXPORT_SYMBOL(__divsi3);
-EXPORT_SYMBOL(__udivsi3);
-EXPORT_SYMBOL(__modsi3);
-EXPORT_SYMBOL(__umodsi3);
-EXPORT_SYMBOL(__divdi3);
-EXPORT_SYMBOL(__udivdi3);
-EXPORT_SYMBOL(__moddi3);
-EXPORT_SYMBOL(__umoddi3);
-
-#if defined(CONFIG_MD_RAID456) || defined(CONFIG_MD_RAID456_MODULE)
-extern void xor_ia64_2(void);
-extern void xor_ia64_3(void);
-extern void xor_ia64_4(void);
-extern void xor_ia64_5(void);
-
-EXPORT_SYMBOL(xor_ia64_2);
-EXPORT_SYMBOL(xor_ia64_3);
-EXPORT_SYMBOL(xor_ia64_4);
-EXPORT_SYMBOL(xor_ia64_5);
-#endif
-
-#include <asm/pal.h>
-EXPORT_SYMBOL(ia64_pal_call_phys_stacked);
-EXPORT_SYMBOL(ia64_pal_call_phys_static);
-EXPORT_SYMBOL(ia64_pal_call_stacked);
-EXPORT_SYMBOL(ia64_pal_call_static);
-EXPORT_SYMBOL(ia64_load_scratch_fpregs);
-EXPORT_SYMBOL(ia64_save_scratch_fpregs);
-
-#include <asm/unwind.h>
-EXPORT_SYMBOL(unw_init_running);
-
-#if defined(CONFIG_IA64_ESI) || defined(CONFIG_IA64_ESI_MODULE)
-extern void esi_call_phys (void);
-EXPORT_SYMBOL_GPL(esi_call_phys);
-#endif
-extern char ia64_ivt[];
-EXPORT_SYMBOL(ia64_ivt);
-
-#include <asm/ftrace.h>
-#ifdef CONFIG_FUNCTION_TRACER
-/* mcount is defined in assembly */
-EXPORT_SYMBOL(_mcount);
-#endif
-
-#include <asm/cacheflush.h>
-EXPORT_SYMBOL_GPL(flush_icache_range);
diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S
index b1c3cfc..44a103a 100644
--- a/arch/ia64/kernel/ivt.S
+++ b/arch/ia64/kernel/ivt.S
@@ -57,6 +57,7 @@
#include <asm/thread_info.h>
#include <asm/unistd.h>
#include <asm/errno.h>
+#include <asm/export.h>
#if 0
# define PSR_DEFAULT_BITS psr.ac
@@ -85,6 +86,7 @@
.align 32768 // align on 32KB boundary
.global ia64_ivt
+ EXPORT_DATA_SYMBOL(ia64_ivt)
ia64_ivt:
/////////////////////////////////////////////////////////////////////////////////////////
// 0x0000 Entry 0 (size 64 bundles) VHPT Translation (8,20,47)
diff --git a/arch/ia64/kernel/pal.S b/arch/ia64/kernel/pal.S
index 0b53344..94fb2e3 100644
--- a/arch/ia64/kernel/pal.S
+++ b/arch/ia64/kernel/pal.S
@@ -14,6 +14,7 @@
#include <asm/asmmacro.h>
#include <asm/processor.h>
+#include <asm/export.h>
.data
pal_entry_point:
@@ -87,6 +88,7 @@
srlz.d // seralize restoration of psr.l
br.ret.sptk.many b0
END(ia64_pal_call_static)
+EXPORT_SYMBOL(ia64_pal_call_static)
/*
* Make a PAL call using the stacked registers calling convention.
@@ -122,6 +124,7 @@
srlz.d // serialize restoration of psr.l
br.ret.sptk.many b0
END(ia64_pal_call_stacked)
+EXPORT_SYMBOL(ia64_pal_call_stacked)
/*
* Make a physical mode PAL call using the static registers calling convention.
@@ -193,6 +196,7 @@
srlz.d // seralize restoration of psr.l
br.ret.sptk.many b0
END(ia64_pal_call_phys_static)
+EXPORT_SYMBOL(ia64_pal_call_phys_static)
/*
* Make a PAL call using the stacked registers in physical mode.
@@ -250,6 +254,7 @@
srlz.d // seralize restoration of psr.l
br.ret.sptk.many b0
END(ia64_pal_call_phys_stacked)
+EXPORT_SYMBOL(ia64_pal_call_phys_stacked)
/*
* Save scratch fp scratch regs which aren't saved in pt_regs already
@@ -275,6 +280,7 @@
stf.spill [r2] = f15,32
br.ret.sptk.many rp
END(ia64_save_scratch_fpregs)
+EXPORT_SYMBOL(ia64_save_scratch_fpregs)
/*
* Load scratch fp scratch regs (fp10-fp15)
@@ -296,3 +302,4 @@
ldf.fill f15 = [r2],32
br.ret.sptk.many rp
END(ia64_load_scratch_fpregs)
+EXPORT_SYMBOL(ia64_load_scratch_fpregs)
diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index 6f54d51..31aa8c0 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -453,7 +453,7 @@ ia64_peek (struct task_struct *child, struct switch_stack *child_stack,
return 0;
}
}
- copied = access_process_vm(child, addr, &ret, sizeof(ret), 0);
+ copied = access_process_vm(child, addr, &ret, sizeof(ret), FOLL_FORCE);
if (copied != sizeof(ret))
return -EIO;
*val = ret;
@@ -489,7 +489,8 @@ ia64_poke (struct task_struct *child, struct switch_stack *child_stack,
*ia64_rse_skip_regs(krbs, regnum) = val;
}
}
- } else if (access_process_vm(child, addr, &val, sizeof(val), 1)
+ } else if (access_process_vm(child, addr, &val, sizeof(val),
+ FOLL_FORCE | FOLL_WRITE)
!= sizeof(val))
return -EIO;
return 0;
@@ -543,7 +544,8 @@ ia64_sync_user_rbs (struct task_struct *child, struct switch_stack *sw,
ret = ia64_peek(child, sw, user_rbs_end, addr, &val);
if (ret < 0)
return ret;
- if (access_process_vm(child, addr, &val, sizeof(val), 1)
+ if (access_process_vm(child, addr, &val, sizeof(val),
+ FOLL_FORCE | FOLL_WRITE)
!= sizeof(val))
return -EIO;
}
@@ -559,7 +561,8 @@ ia64_sync_kernel_rbs (struct task_struct *child, struct switch_stack *sw,
/* now copy word for word from user rbs to kernel rbs: */
for (addr = user_rbs_start; addr < user_rbs_end; addr += 8) {
- if (access_process_vm(child, addr, &val, sizeof(val), 0)
+ if (access_process_vm(child, addr, &val, sizeof(val),
+ FOLL_FORCE)
!= sizeof(val))
return -EIO;
@@ -1156,7 +1159,8 @@ arch_ptrace (struct task_struct *child, long request,
case PTRACE_PEEKTEXT:
case PTRACE_PEEKDATA:
/* read word at location addr */
- if (access_process_vm(child, addr, &data, sizeof(data), 0)
+ if (access_process_vm(child, addr, &data, sizeof(data),
+ FOLL_FORCE)
!= sizeof(data))
return -EIO;
/* ensure return value is not mistaken for error code */
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index afddb3e..7ec7acc 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -71,7 +71,11 @@ EXPORT_SYMBOL(__per_cpu_offset);
#endif
DEFINE_PER_CPU(struct cpuinfo_ia64, ia64_cpu_info);
+EXPORT_SYMBOL(ia64_cpu_info);
DEFINE_PER_CPU(unsigned long, local_per_cpu_offset);
+#ifdef CONFIG_SMP
+EXPORT_SYMBOL(local_per_cpu_offset);
+#endif
unsigned long ia64_cycles_per_usec;
struct ia64_boot_param *ia64_boot_param;
struct screen_info screen_info;
diff --git a/arch/ia64/lib/Makefile b/arch/ia64/lib/Makefile
index 98771e2..1f3d387 100644
--- a/arch/ia64/lib/Makefile
+++ b/arch/ia64/lib/Makefile
@@ -2,17 +2,15 @@
# Makefile for ia64-specific library routines..
#
-obj-y := io.o
-
-lib-y := __divsi3.o __udivsi3.o __modsi3.o __umodsi3.o \
+lib-y := io.o __divsi3.o __udivsi3.o __modsi3.o __umodsi3.o \
__divdi3.o __udivdi3.o __moddi3.o __umoddi3.o \
checksum.o clear_page.o csum_partial_copy.o \
clear_user.o strncpy_from_user.o strlen_user.o strnlen_user.o \
flush.o ip_fast_csum.o do_csum.o \
memset.o strlen.o xor.o
-obj-$(CONFIG_ITANIUM) += copy_page.o copy_user.o memcpy.o
-obj-$(CONFIG_MCKINLEY) += copy_page_mck.o memcpy_mck.o
+lib-$(CONFIG_ITANIUM) += copy_page.o copy_user.o memcpy.o
+lib-$(CONFIG_MCKINLEY) += copy_page_mck.o memcpy_mck.o
lib-$(CONFIG_PERFMON) += carta_random.o
AFLAGS___divdi3.o =
diff --git a/arch/ia64/lib/clear_page.S b/arch/ia64/lib/clear_page.S
index 2d814e7..3cf5b76 100644
--- a/arch/ia64/lib/clear_page.S
+++ b/arch/ia64/lib/clear_page.S
@@ -11,6 +11,7 @@
#include <asm/asmmacro.h>
#include <asm/page.h>
+#include <asm/export.h>
#ifdef CONFIG_ITANIUM
# define L3_LINE_SIZE 64 // Itanium L3 line size
@@ -74,3 +75,4 @@
mov ar.lc = saved_lc // restore lc
br.ret.sptk.many rp
END(clear_page)
+EXPORT_SYMBOL(clear_page)
diff --git a/arch/ia64/lib/clear_user.S b/arch/ia64/lib/clear_user.S
index eecd857..7b40731 100644
--- a/arch/ia64/lib/clear_user.S
+++ b/arch/ia64/lib/clear_user.S
@@ -12,6 +12,7 @@
*/
#include <asm/asmmacro.h>
+#include <asm/export.h>
//
// arguments
@@ -207,3 +208,4 @@
mov ar.lc=saved_lc
br.ret.sptk.many rp
END(__do_clear_user)
+EXPORT_SYMBOL(__do_clear_user)
diff --git a/arch/ia64/lib/copy_page.S b/arch/ia64/lib/copy_page.S
index 127d1d0..cbdb9e3 100644
--- a/arch/ia64/lib/copy_page.S
+++ b/arch/ia64/lib/copy_page.S
@@ -16,6 +16,7 @@
*/
#include <asm/asmmacro.h>
#include <asm/page.h>
+#include <asm/export.h>
#define PIPE_DEPTH 3
#define EPI p[PIPE_DEPTH-1]
@@ -96,3 +97,4 @@
mov ar.lc=saved_lc
br.ret.sptk.many rp
END(copy_page)
+EXPORT_SYMBOL(copy_page)
diff --git a/arch/ia64/lib/copy_page_mck.S b/arch/ia64/lib/copy_page_mck.S
index 3c45d60..c13f690 100644
--- a/arch/ia64/lib/copy_page_mck.S
+++ b/arch/ia64/lib/copy_page_mck.S
@@ -61,6 +61,7 @@
*/
#include <asm/asmmacro.h>
#include <asm/page.h>
+#include <asm/export.h>
#define PREFETCH_DIST 8 // McKinley sustains 16 outstanding L2 misses (8 ld, 8 st)
@@ -183,3 +184,4 @@
mov pr = saved_pr, -1
br.ret.sptk.many rp
END(copy_page)
+EXPORT_SYMBOL(copy_page)
diff --git a/arch/ia64/lib/copy_user.S b/arch/ia64/lib/copy_user.S
index c952bdc..66facd5 100644
--- a/arch/ia64/lib/copy_user.S
+++ b/arch/ia64/lib/copy_user.S
@@ -30,6 +30,7 @@
*/
#include <asm/asmmacro.h>
+#include <asm/export.h>
//
// Tuneable parameters
@@ -608,3 +609,4 @@
mov ar.pfs=saved_pfs
br.ret.sptk.many rp
END(__copy_user)
+EXPORT_SYMBOL(__copy_user)
diff --git a/arch/ia64/lib/flush.S b/arch/ia64/lib/flush.S
index 1d8c888..9a5a2f9 100644
--- a/arch/ia64/lib/flush.S
+++ b/arch/ia64/lib/flush.S
@@ -8,6 +8,7 @@
*/
#include <asm/asmmacro.h>
+#include <asm/export.h>
/*
@@ -60,6 +61,7 @@
mov ar.lc=r3 // restore ar.lc
br.ret.sptk.many rp
END(flush_icache_range)
+EXPORT_SYMBOL_GPL(flush_icache_range)
/*
* clflush_cache_range(start,size)
diff --git a/arch/ia64/lib/idiv32.S b/arch/ia64/lib/idiv32.S
index c91b5b0..715aed7 100644
--- a/arch/ia64/lib/idiv32.S
+++ b/arch/ia64/lib/idiv32.S
@@ -15,6 +15,7 @@
*/
#include <asm/asmmacro.h>
+#include <asm/export.h>
#ifdef MODULO
# define OP mod
@@ -81,3 +82,4 @@
getf.sig r8 = f6 // transfer result to result register
br.ret.sptk.many rp
END(NAME)
+EXPORT_SYMBOL(NAME)
diff --git a/arch/ia64/lib/idiv64.S b/arch/ia64/lib/idiv64.S
index 627573c..25840f6 100644
--- a/arch/ia64/lib/idiv64.S
+++ b/arch/ia64/lib/idiv64.S
@@ -15,6 +15,7 @@
*/
#include <asm/asmmacro.h>
+#include <asm/export.h>
#ifdef MODULO
# define OP mod
@@ -78,3 +79,4 @@
getf.sig r8 = f11 // transfer result to result register
br.ret.sptk.many rp
END(NAME)
+EXPORT_SYMBOL(NAME)
diff --git a/arch/ia64/lib/ip_fast_csum.S b/arch/ia64/lib/ip_fast_csum.S
index 620d9dc..648e0d4 100644
--- a/arch/ia64/lib/ip_fast_csum.S
+++ b/arch/ia64/lib/ip_fast_csum.S
@@ -13,6 +13,7 @@
*/
#include <asm/asmmacro.h>
+#include <asm/export.h>
/*
* Since we know that most likely this function is called with buf aligned
@@ -92,6 +93,7 @@
mov b0=r34
br.ret.sptk.many b0
END(ip_fast_csum)
+EXPORT_SYMBOL(ip_fast_csum)
GLOBAL_ENTRY(csum_ipv6_magic)
ld4 r20=[in0],4
@@ -142,3 +144,4 @@
andcm r8=r9,r8
br.ret.sptk.many b0
END(csum_ipv6_magic)
+EXPORT_SYMBOL(csum_ipv6_magic)
diff --git a/arch/ia64/lib/memcpy.S b/arch/ia64/lib/memcpy.S
index 448908d..ba172fd 100644
--- a/arch/ia64/lib/memcpy.S
+++ b/arch/ia64/lib/memcpy.S
@@ -14,6 +14,7 @@
* David Mosberger-Tang <davidm@hpl.hp.com>
*/
#include <asm/asmmacro.h>
+#include <asm/export.h>
GLOBAL_ENTRY(memcpy)
@@ -299,3 +300,4 @@
COPY(56, 0)
END(memcpy)
+EXPORT_SYMBOL(memcpy)
diff --git a/arch/ia64/lib/memcpy_mck.S b/arch/ia64/lib/memcpy_mck.S
index ab0f876..b264b6a 100644
--- a/arch/ia64/lib/memcpy_mck.S
+++ b/arch/ia64/lib/memcpy_mck.S
@@ -15,6 +15,7 @@
*/
#include <asm/asmmacro.h>
#include <asm/page.h>
+#include <asm/export.h>
#define EK(y...) EX(y)
@@ -78,6 +79,7 @@
br.cond.sptk .common_code
;;
END(memcpy)
+EXPORT_SYMBOL(memcpy)
GLOBAL_ENTRY(__copy_user)
.prologue
// check dest alignment
@@ -664,3 +666,4 @@
/* end of McKinley specific optimization */
END(__copy_user)
+EXPORT_SYMBOL(__copy_user)
diff --git a/arch/ia64/lib/memset.S b/arch/ia64/lib/memset.S
index f26c16a..87b9747 100644
--- a/arch/ia64/lib/memset.S
+++ b/arch/ia64/lib/memset.S
@@ -18,6 +18,7 @@
to get peak speed when value = 0. */
#include <asm/asmmacro.h>
+#include <asm/export.h>
#undef ret
#define dest in0
@@ -360,3 +361,4 @@
br.ret.sptk.many rp
}
END(memset)
+EXPORT_SYMBOL(memset)
diff --git a/arch/ia64/lib/strlen.S b/arch/ia64/lib/strlen.S
index e0cdac0..1a6e17c 100644
--- a/arch/ia64/lib/strlen.S
+++ b/arch/ia64/lib/strlen.S
@@ -17,6 +17,7 @@
*/
#include <asm/asmmacro.h>
+#include <asm/export.h>
//
//
@@ -190,3 +191,4 @@
mov ar.pfs=saved_pfs // because of ar.ec, restore no matter what
br.ret.sptk.many rp // end of successful recovery code
END(strlen)
+EXPORT_SYMBOL(strlen)
diff --git a/arch/ia64/lib/strlen_user.S b/arch/ia64/lib/strlen_user.S
index c71eded..9d25768 100644
--- a/arch/ia64/lib/strlen_user.S
+++ b/arch/ia64/lib/strlen_user.S
@@ -16,6 +16,7 @@
*/
#include <asm/asmmacro.h>
+#include <asm/export.h>
//
// int strlen_user(char *)
@@ -196,3 +197,4 @@
mov ar.pfs=saved_pfs // because of ar.ec, restore no matter what
br.ret.sptk.many rp
END(__strlen_user)
+EXPORT_SYMBOL(__strlen_user)
diff --git a/arch/ia64/lib/strncpy_from_user.S b/arch/ia64/lib/strncpy_from_user.S
index a504381..ca9ccf2 100644
--- a/arch/ia64/lib/strncpy_from_user.S
+++ b/arch/ia64/lib/strncpy_from_user.S
@@ -17,6 +17,7 @@
*/
#include <asm/asmmacro.h>
+#include <asm/export.h>
GLOBAL_ENTRY(__strncpy_from_user)
alloc r2=ar.pfs,3,0,0,0
@@ -42,3 +43,4 @@
[.Lexit:]
br.ret.sptk.many rp
END(__strncpy_from_user)
+EXPORT_SYMBOL(__strncpy_from_user)
diff --git a/arch/ia64/lib/strnlen_user.S b/arch/ia64/lib/strnlen_user.S
index d09066b1..80a5dfd 100644
--- a/arch/ia64/lib/strnlen_user.S
+++ b/arch/ia64/lib/strnlen_user.S
@@ -13,6 +13,7 @@
*/
#include <asm/asmmacro.h>
+#include <asm/export.h>
GLOBAL_ENTRY(__strnlen_user)
.prologue
@@ -43,3 +44,4 @@
mov ar.lc=r16 // restore ar.lc
br.ret.sptk.many rp
END(__strnlen_user)
+EXPORT_SYMBOL(__strnlen_user)
diff --git a/arch/ia64/lib/xor.S b/arch/ia64/lib/xor.S
index 54e3f7e..c83f1c4 100644
--- a/arch/ia64/lib/xor.S
+++ b/arch/ia64/lib/xor.S
@@ -14,6 +14,7 @@
*/
#include <asm/asmmacro.h>
+#include <asm/export.h>
GLOBAL_ENTRY(xor_ia64_2)
.prologue
@@ -51,6 +52,7 @@
mov pr = r29, -1
br.ret.sptk.few rp
END(xor_ia64_2)
+EXPORT_SYMBOL(xor_ia64_2)
GLOBAL_ENTRY(xor_ia64_3)
.prologue
@@ -91,6 +93,7 @@
mov pr = r29, -1
br.ret.sptk.few rp
END(xor_ia64_3)
+EXPORT_SYMBOL(xor_ia64_3)
GLOBAL_ENTRY(xor_ia64_4)
.prologue
@@ -134,6 +137,7 @@
mov pr = r29, -1
br.ret.sptk.few rp
END(xor_ia64_4)
+EXPORT_SYMBOL(xor_ia64_4)
GLOBAL_ENTRY(xor_ia64_5)
.prologue
@@ -182,3 +186,4 @@
mov pr = r29, -1
br.ret.sptk.few rp
END(xor_ia64_5)
+EXPORT_SYMBOL(xor_ia64_5)
diff --git a/arch/m32r/kernel/ptrace.c b/arch/m32r/kernel/ptrace.c
index 51f5e9a..c145605 100644
--- a/arch/m32r/kernel/ptrace.c
+++ b/arch/m32r/kernel/ptrace.c
@@ -493,7 +493,8 @@ unregister_all_debug_traps(struct task_struct *child)
int i;
for (i = 0; i < p->nr_trap; i++)
- access_process_vm(child, p->addr[i], &p->insn[i], sizeof(p->insn[i]), 1);
+ access_process_vm(child, p->addr[i], &p->insn[i], sizeof(p->insn[i]),
+ FOLL_FORCE | FOLL_WRITE);
p->nr_trap = 0;
}
@@ -537,7 +538,8 @@ embed_debug_trap(struct task_struct *child, unsigned long next_pc)
unsigned long next_insn, code;
unsigned long addr = next_pc & ~3;
- if (access_process_vm(child, addr, &next_insn, sizeof(next_insn), 0)
+ if (access_process_vm(child, addr, &next_insn, sizeof(next_insn),
+ FOLL_FORCE)
!= sizeof(next_insn)) {
return -1; /* error */
}
@@ -546,7 +548,8 @@ embed_debug_trap(struct task_struct *child, unsigned long next_pc)
if (register_debug_trap(child, next_pc, next_insn, &code)) {
return -1; /* error */
}
- if (access_process_vm(child, addr, &code, sizeof(code), 1)
+ if (access_process_vm(child, addr, &code, sizeof(code),
+ FOLL_FORCE | FOLL_WRITE)
!= sizeof(code)) {
return -1; /* error */
}
@@ -562,7 +565,8 @@ withdraw_debug_trap(struct pt_regs *regs)
addr = (regs->bpc - 2) & ~3;
regs->bpc -= 2;
if (unregister_debug_trap(current, addr, &code)) {
- access_process_vm(current, addr, &code, sizeof(code), 1);
+ access_process_vm(current, addr, &code, sizeof(code),
+ FOLL_FORCE | FOLL_WRITE);
invalidate_cache();
}
}
@@ -589,7 +593,8 @@ void user_enable_single_step(struct task_struct *child)
/* Compute next pc. */
pc = get_stack_long(child, PT_BPC);
- if (access_process_vm(child, pc&~3, &insn, sizeof(insn), 0)
+ if (access_process_vm(child, pc&~3, &insn, sizeof(insn),
+ FOLL_FORCE)
!= sizeof(insn))
return;
diff --git a/arch/m68k/include/asm/export.h b/arch/m68k/include/asm/export.h
new file mode 100644
index 0000000..0af20f4
--- /dev/null
+++ b/arch/m68k/include/asm/export.h
@@ -0,0 +1,3 @@
+#define KSYM_ALIGN 2
+#define KCRC_ALIGN 2
+#include <asm-generic/export.h>
diff --git a/arch/m68k/kernel/Makefile b/arch/m68k/kernel/Makefile
index 8a1c4d3..74c898c 100644
--- a/arch/m68k/kernel/Makefile
+++ b/arch/m68k/kernel/Makefile
@@ -13,7 +13,7 @@
extra-$(CONFIG_SUN3) := sun3-head.o
extra-y += vmlinux.lds
-obj-y := entry.o irq.o m68k_ksyms.o module.o process.o ptrace.o
+obj-y := entry.o irq.o module.o process.o ptrace.o
obj-y += setup.o signal.o sys_m68k.o syscalltable.o time.o traps.o
obj-$(CONFIG_MMU_MOTOROLA) += ints.o vectors.o
diff --git a/arch/m68k/kernel/m68k_ksyms.c b/arch/m68k/kernel/m68k_ksyms.c
deleted file mode 100644
index 774c1bd..0000000
--- a/arch/m68k/kernel/m68k_ksyms.c
+++ /dev/null
@@ -1,32 +0,0 @@
-#include <linux/module.h>
-
-asmlinkage long long __ashldi3 (long long, int);
-asmlinkage long long __ashrdi3 (long long, int);
-asmlinkage long long __lshrdi3 (long long, int);
-asmlinkage long long __muldi3 (long long, long long);
-
-/* The following are special because they're not called
- explicitly (the C compiler generates them). Fortunately,
- their interface isn't gonna change any time soon now, so
- it's OK to leave it out of version control. */
-EXPORT_SYMBOL(__ashldi3);
-EXPORT_SYMBOL(__ashrdi3);
-EXPORT_SYMBOL(__lshrdi3);
-EXPORT_SYMBOL(__muldi3);
-
-#if defined(CONFIG_CPU_HAS_NO_MULDIV64)
-/*
- * Simpler 68k and ColdFire parts also need a few other gcc functions.
- */
-extern long long __divsi3(long long, long long);
-extern long long __modsi3(long long, long long);
-extern long long __mulsi3(long long, long long);
-extern long long __udivsi3(long long, long long);
-extern long long __umodsi3(long long, long long);
-
-EXPORT_SYMBOL(__divsi3);
-EXPORT_SYMBOL(__modsi3);
-EXPORT_SYMBOL(__mulsi3);
-EXPORT_SYMBOL(__udivsi3);
-EXPORT_SYMBOL(__umodsi3);
-#endif
diff --git a/arch/m68k/lib/ashldi3.c b/arch/m68k/lib/ashldi3.c
index 37234c2..8dffd36 100644
--- a/arch/m68k/lib/ashldi3.c
+++ b/arch/m68k/lib/ashldi3.c
@@ -13,6 +13,9 @@ but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details. */
+#include <linux/compiler.h>
+#include <linux/export.h>
+
#define BITS_PER_UNIT 8
typedef int SItype __attribute__ ((mode (SI)));
@@ -55,3 +58,4 @@ __ashldi3 (DItype u, word_type b)
return w.ll;
}
+EXPORT_SYMBOL(__ashldi3);
diff --git a/arch/m68k/lib/ashrdi3.c b/arch/m68k/lib/ashrdi3.c
index 1d59345..e6565a3 100644
--- a/arch/m68k/lib/ashrdi3.c
+++ b/arch/m68k/lib/ashrdi3.c
@@ -13,6 +13,9 @@ but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details. */
+#include <linux/compiler.h>
+#include <linux/export.h>
+
#define BITS_PER_UNIT 8
typedef int SItype __attribute__ ((mode (SI)));
@@ -56,3 +59,4 @@ __ashrdi3 (DItype u, word_type b)
return w.ll;
}
+EXPORT_SYMBOL(__ashrdi3);
diff --git a/arch/m68k/lib/divsi3.S b/arch/m68k/lib/divsi3.S
index 2c0ec85..3a2143f 100644
--- a/arch/m68k/lib/divsi3.S
+++ b/arch/m68k/lib/divsi3.S
@@ -33,6 +33,8 @@
D. V. Henkel-Wallace (gumby@cygnus.com) Fete Bastille, 1992
*/
+#include <asm/export.h>
+
/* These are predefined by new versions of GNU cpp. */
#ifndef __USER_LABEL_PREFIX__
@@ -118,3 +120,4 @@
L3: movel sp@+, d2
rts
+ EXPORT_SYMBOL(__divsi3)
diff --git a/arch/m68k/lib/lshrdi3.c b/arch/m68k/lib/lshrdi3.c
index 49e1ec8..0397797 100644
--- a/arch/m68k/lib/lshrdi3.c
+++ b/arch/m68k/lib/lshrdi3.c
@@ -13,6 +13,9 @@ but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details. */
+#include <linux/compiler.h>
+#include <linux/export.h>
+
#define BITS_PER_UNIT 8
typedef int SItype __attribute__ ((mode (SI)));
@@ -55,3 +58,4 @@ __lshrdi3 (DItype u, word_type b)
return w.ll;
}
+EXPORT_SYMBOL(__lshrdi3);
diff --git a/arch/m68k/lib/modsi3.S b/arch/m68k/lib/modsi3.S
index 1d9e0ef..1c96764 100644
--- a/arch/m68k/lib/modsi3.S
+++ b/arch/m68k/lib/modsi3.S
@@ -33,6 +33,8 @@
D. V. Henkel-Wallace (gumby@cygnus.com) Fete Bastille, 1992
*/
+#include <asm/export.h>
+
/* These are predefined by new versions of GNU cpp. */
#ifndef __USER_LABEL_PREFIX__
@@ -106,3 +108,4 @@
movel d1, d0
rts
+ EXPORT_SYMBOL(__modsi3)
diff --git a/arch/m68k/lib/muldi3.c b/arch/m68k/lib/muldi3.c
index 9006d15..6459af5 100644
--- a/arch/m68k/lib/muldi3.c
+++ b/arch/m68k/lib/muldi3.c
@@ -14,6 +14,9 @@ but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details. */
+#include <linux/compiler.h>
+#include <linux/export.h>
+
#ifdef CONFIG_CPU_HAS_NO_MULDIV64
#define SI_TYPE_SIZE 32
@@ -90,3 +93,4 @@ __muldi3 (DItype u, DItype v)
return w.ll;
}
+EXPORT_SYMBOL(__muldi3);
diff --git a/arch/m68k/lib/mulsi3.S b/arch/m68k/lib/mulsi3.S
index c39ad4e..855675e 100644
--- a/arch/m68k/lib/mulsi3.S
+++ b/arch/m68k/lib/mulsi3.S
@@ -32,7 +32,7 @@
Some of this code comes from MINIX, via the folks at ericsson.
D. V. Henkel-Wallace (gumby@cygnus.com) Fete Bastille, 1992
*/
-
+#include <asm/export.h>
/* These are predefined by new versions of GNU cpp. */
#ifndef __USER_LABEL_PREFIX__
@@ -102,4 +102,4 @@
addl d1, d0
rts
-
+ EXPORT_SYMBOL(__mulsi3)
diff --git a/arch/m68k/lib/udivsi3.S b/arch/m68k/lib/udivsi3.S
index 35a5446..78440ae 100644
--- a/arch/m68k/lib/udivsi3.S
+++ b/arch/m68k/lib/udivsi3.S
@@ -32,7 +32,7 @@
Some of this code comes from MINIX, via the folks at ericsson.
D. V. Henkel-Wallace (gumby@cygnus.com) Fete Bastille, 1992
*/
-
+#include <asm/export.h>
/* These are predefined by new versions of GNU cpp. */
#ifndef __USER_LABEL_PREFIX__
@@ -154,4 +154,4 @@
unlk a6 | and return
rts
#endif /* __mcf5200__ || __mcoldfire__ */
-
+ EXPORT_SYMBOL(__udivsi3)
diff --git a/arch/m68k/lib/umodsi3.S b/arch/m68k/lib/umodsi3.S
index 099da51..b6fd11f 100644
--- a/arch/m68k/lib/umodsi3.S
+++ b/arch/m68k/lib/umodsi3.S
@@ -32,7 +32,7 @@
Some of this code comes from MINIX, via the folks at ericsson.
D. V. Henkel-Wallace (gumby@cygnus.com) Fete Bastille, 1992
*/
-
+#include <asm/export.h>
/* These are predefined by new versions of GNU cpp. */
#ifndef __USER_LABEL_PREFIX__
@@ -105,4 +105,4 @@
subl d0, d1 /* d1 = a - (a/b)*b */
movel d1, d0
rts
-
+ EXPORT_SYMBOL(__umodsi3)
diff --git a/arch/metag/include/asm/atomic.h b/arch/metag/include/asm/atomic.h
index 470e365..8ff0a70 100644
--- a/arch/metag/include/asm/atomic.h
+++ b/arch/metag/include/asm/atomic.h
@@ -39,11 +39,10 @@
#define atomic_dec(v) atomic_sub(1, (v))
#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
+#define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v)
#endif
-#define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v)
-
#include <asm-generic/atomic64.h>
#endif /* __ASM_METAG_ATOMIC_H */
diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms
index c5cd63a..f5f1bdb 100644
--- a/arch/mips/Kbuild.platforms
+++ b/arch/mips/Kbuild.platforms
@@ -11,6 +11,7 @@
platforms += cobalt
platforms += dec
platforms += emma
+platforms += generic
platforms += jazz
platforms += jz4740
platforms += lantiq
@@ -18,7 +19,6 @@
platforms += loongson32
platforms += loongson64
platforms += mti-malta
-platforms += mti-sead3
platforms += netlogic
platforms += paravirt
platforms += pic32
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 1a322c8..b3c5bde 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -65,6 +65,7 @@
select HANDLE_DOMAIN_IRQ
select HAVE_EXIT_THREAD
select HAVE_REGS_AND_STACK_ACCESS_API
+ select HAVE_ARCH_HARDENED_USERCOPY
menu "Machine selection"
@@ -72,6 +73,57 @@
prompt "System type"
default SGI_IP22
+config MIPS_GENERIC
+ bool "Generic board-agnostic MIPS kernel"
+ select BOOT_RAW
+ select BUILTIN_DTB
+ select CEVT_R4K
+ select CLKSRC_MIPS_GIC
+ select COMMON_CLK
+ select CPU_MIPSR2_IRQ_VI
+ select CPU_MIPSR2_IRQ_EI
+ select CSRC_R4K
+ select DMA_PERDEV_COHERENT
+ select HW_HAS_PCI
+ select IRQ_MIPS_CPU
+ select LIBFDT
+ select MIPS_CPU_SCACHE
+ select MIPS_GIC
+ select MIPS_L1_CACHE_SHIFT_7
+ select NO_EXCEPT_FILL
+ select PCI_DRIVERS_GENERIC
+ select PINCTRL
+ select SMP_UP if SMP
+ select SYS_HAS_CPU_MIPS32_R1
+ select SYS_HAS_CPU_MIPS32_R2
+ select SYS_HAS_CPU_MIPS32_R6
+ select SYS_HAS_CPU_MIPS64_R1
+ select SYS_HAS_CPU_MIPS64_R2
+ select SYS_HAS_CPU_MIPS64_R6
+ select SYS_SUPPORTS_32BIT_KERNEL
+ select SYS_SUPPORTS_64BIT_KERNEL
+ select SYS_SUPPORTS_BIG_ENDIAN
+ select SYS_SUPPORTS_HIGHMEM
+ select SYS_SUPPORTS_LITTLE_ENDIAN
+ select SYS_SUPPORTS_MICROMIPS
+ select SYS_SUPPORTS_MIPS_CPS
+ select SYS_SUPPORTS_MIPS16
+ select SYS_SUPPORTS_MULTITHREADING
+ select SYS_SUPPORTS_RELOCATABLE
+ select SYS_SUPPORTS_SMARTMIPS
+ select USB_EHCI_BIG_ENDIAN_DESC if BIG_ENDIAN
+ select USB_EHCI_BIG_ENDIAN_MMIO if BIG_ENDIAN
+ select USB_OHCI_BIG_ENDIAN_DESC if BIG_ENDIAN
+ select USB_OHCI_BIG_ENDIAN_MMIO if BIG_ENDIAN
+ select USB_UHCI_BIG_ENDIAN_DESC if BIG_ENDIAN
+ select USB_UHCI_BIG_ENDIAN_MMIO if BIG_ENDIAN
+ select USE_OF
+ help
+ Select this to build a kernel which aims to support multiple boards,
+ generally using a flattened device tree passed from the bootloader
+ using the boot protocol defined in the UHI (Unified Hosting
+ Interface) specification.
+
config MIPS_ALCHEMY
bool "Alchemy processor based machines"
select ARCH_PHYS_ADDR_T_64BIT
@@ -478,6 +530,7 @@
select SYS_SUPPORTS_ZBOOT
select SYS_SUPPORTS_RELOCATABLE
select USE_OF
+ select LIBFDT
select ZONE_DMA32 if 64BIT
select BUILTIN_DTB
select LIBFDT
@@ -493,42 +546,6 @@
Microchip PIC32 is a family of general-purpose 32 bit MIPS core
microcontrollers.
-config MIPS_SEAD3
- bool "MIPS SEAD3 board"
- select BOOT_ELF32
- select BOOT_RAW
- select BUILTIN_DTB
- select CEVT_R4K
- select CSRC_R4K
- select CLKSRC_MIPS_GIC
- select COMMON_CLK
- select CPU_MIPSR2_IRQ_VI
- select CPU_MIPSR2_IRQ_EI
- select DMA_NONCOHERENT
- select IRQ_MIPS_CPU
- select MIPS_GIC
- select LIBFDT
- select MIPS_MSC
- select SYS_HAS_CPU_MIPS32_R1
- select SYS_HAS_CPU_MIPS32_R2
- select SYS_HAS_CPU_MIPS32_R6
- select SYS_HAS_CPU_MIPS64_R1
- select SYS_HAS_EARLY_PRINTK
- select SYS_SUPPORTS_32BIT_KERNEL
- select SYS_SUPPORTS_64BIT_KERNEL
- select SYS_SUPPORTS_BIG_ENDIAN
- select SYS_SUPPORTS_LITTLE_ENDIAN
- select SYS_SUPPORTS_SMARTMIPS
- select SYS_SUPPORTS_MICROMIPS
- select SYS_SUPPORTS_MIPS16
- select SYS_SUPPORTS_RELOCATABLE
- select USB_EHCI_BIG_ENDIAN_DESC
- select USB_EHCI_BIG_ENDIAN_MMIO
- select USE_OF
- help
- This enables support for the MIPS Technologies SEAD3 evaluation
- board.
-
config NEC_MARKEINS
bool "NEC EMMA2RH Mark-eins board"
select SOC_EMMA2RH
@@ -988,6 +1005,7 @@
source "arch/mips/bcm47xx/Kconfig"
source "arch/mips/bcm63xx/Kconfig"
source "arch/mips/bmips/Kconfig"
+source "arch/mips/generic/Kconfig"
source "arch/mips/jazz/Kconfig"
source "arch/mips/jz4740/Kconfig"
source "arch/mips/lantiq/Kconfig"
@@ -1098,6 +1116,10 @@
select DMA_NONCOHERENT
bool
+config DMA_PERDEV_COHERENT
+ bool
+ select DMA_MAYBE_COHERENT
+
config DMA_COHERENT
bool
@@ -1401,6 +1423,16 @@
The Loongson 1B is a 32-bit SoC, which implements the MIPS32
release 2 instruction set.
+config CPU_LOONGSON1C
+ bool "Loongson 1C"
+ depends on SYS_HAS_CPU_LOONGSON1C
+ select CPU_LOONGSON1
+ select ARCH_WANT_OPTIONAL_GPIOLIB
+ select LEDS_GPIO_REGISTER
+ help
+ The Loongson 1C is a 32-bit SoC, which implements the MIPS32
+ release 2 instruction set.
+
config CPU_MIPS32_R1
bool "MIPS32 Release 1"
depends on SYS_HAS_CPU_MIPS32_R1
@@ -1850,6 +1882,9 @@
config SYS_HAS_CPU_LOONGSON1B
bool
+config SYS_HAS_CPU_LOONGSON1C
+ bool
+
config SYS_HAS_CPU_MIPS32_R1
bool
@@ -2906,7 +2941,7 @@
choice
prompt "Kernel command line type" if !CMDLINE_OVERRIDE
default MIPS_CMDLINE_FROM_DTB if USE_OF && !ATH79 && !MACH_INGENIC && \
- !MIPS_MALTA && !MIPS_SEAD3 && \
+ !MIPS_MALTA && \
!CAVIUM_OCTEON_SOC
default MIPS_CMDLINE_FROM_BOOTLOADER
@@ -2960,7 +2995,6 @@
bool "Support for PCI controller"
depends on HW_HAS_PCI
select PCI_DOMAINS
- select NO_GENERIC_PCI_IOPORT_MAP
help
Find out whether you have a PCI motherboard. PCI is the name of a
bus system, i.e. the way the CPU talks to the other stuff inside
@@ -2981,6 +3015,17 @@
config PCI_DOMAINS
bool
+config PCI_DOMAINS_GENERIC
+ bool
+
+config PCI_DRIVERS_GENERIC
+ select PCI_DOMAINS_GENERIC if PCI_DOMAINS
+ bool
+
+config PCI_DRIVERS_LEGACY
+ def_bool !PCI_DRIVERS_GENERIC
+ select NO_GENERIC_PCI_IOPORT_MAP
+
source "drivers/pci/Kconfig"
#
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 598ab29..1a6bac7 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -262,7 +262,14 @@
KBUILD_CPPFLAGS += -DDATAOFFSET=$(if $(dataoffset-y),$(dataoffset-y),0)
bootvars-y = VMLINUX_LOAD_ADDRESS=$(load-y) \
- VMLINUX_ENTRY_ADDRESS=$(entry-y)
+ VMLINUX_ENTRY_ADDRESS=$(entry-y) \
+ PLATFORM="$(platform-y)"
+ifdef CONFIG_32BIT
+bootvars-y += ADDR_BITS=32
+endif
+ifdef CONFIG_64BIT
+bootvars-y += ADDR_BITS=64
+endif
LDFLAGS += -m $(ld-emul)
@@ -302,6 +309,11 @@
boot-y += uImage.lzma
boot-y += uImage.lzo
endif
+boot-y += vmlinux.itb
+boot-y += vmlinux.gz.itb
+boot-y += vmlinux.bz2.itb
+boot-y += vmlinux.lzma.itb
+boot-y += vmlinux.lzo.itb
# compressed boot image targets (arch/mips/boot/compressed/)
bootz-y := vmlinuz
@@ -425,4 +437,67 @@
echo ' dtbs_install - Install dtbs to $(INSTALL_DTBS_PATH)'
echo
echo ' These will be default as appropriate for a configured platform.'
+ echo
+ echo ' If you are targeting a system supported by generic kernels you may'
+ echo ' configure the kernel for a given architecture target like so:'
+ echo
+ echo ' {micro32,32,64}{r1,r2,r6}{el,}_defconfig <BOARDS="list of boards">'
+ echo
+ echo ' Otherwise, the following default configurations are available:'
endef
+
+generic_config_dir = $(srctree)/arch/$(ARCH)/configs/generic
+generic_defconfigs :=
+
+#
+# If the user generates a generic kernel configuration without specifying a
+# list of boards to include the config fragments for, default to including all
+# available board config fragments.
+#
+ifeq ($(BOARDS),)
+BOARDS = $(patsubst board-%.config,%,$(notdir $(wildcard $(generic_config_dir)/board-*.config)))
+endif
+
+#
+# Generic kernel configurations which merge generic_defconfig with the
+# appropriate config fragments from arch/mips/configs/generic/, resulting in
+# the ability to easily configure the kernel for a given architecture,
+# endianness & set of boards without duplicating the needed configuration in
+# hundreds of defconfig files.
+#
+define gen_generic_defconfigs
+$(foreach bits,$(1),$(foreach rev,$(2),$(foreach endian,$(3),
+target := $(bits)$(rev)$(filter el,$(endian))_defconfig
+generic_defconfigs += $$(target)
+$$(target): $(generic_config_dir)/$(bits)$(rev).config
+$$(target): $(generic_config_dir)/$(endian).config
+)))
+endef
+
+$(eval $(call gen_generic_defconfigs,32 64,r1 r2 r6,eb el))
+$(eval $(call gen_generic_defconfigs,micro32,r2,eb el))
+
+.PHONY: $(generic_defconfigs)
+$(generic_defconfigs):
+ $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \
+ -m -O $(objtree) $(srctree)/arch/$(ARCH)/configs/generic_defconfig $^ \
+ $(foreach board,$(BOARDS),$(generic_config_dir)/board-$(board).config)
+ $(Q)$(MAKE) olddefconfig
+
+#
+# Prevent generic merge_config rules attempting to merge single fragments
+#
+$(generic_config_dir)/%.config: ;
+
+#
+# Legacy defconfig compatibility - these targets used to be real defconfigs but
+# now that the boards have been converted to use the generic kernel they are
+# wrappers around the generic rules above.
+#
+.PHONY: sead3_defconfig
+sead3_defconfig:
+ $(Q)$(MAKE) 32r2el_defconfig BOARDS=sead-3
+
+.PHONY: sead3micro_defconfig
+sead3micro_defconfig:
+ $(Q)$(MAKE) micro32r2el_defconfig BOARDS=sead-3
diff --git a/arch/mips/alchemy/common/setup.c b/arch/mips/alchemy/common/setup.c
index 2902138..7faaa6d 100644
--- a/arch/mips/alchemy/common/setup.c
+++ b/arch/mips/alchemy/common/setup.c
@@ -48,17 +48,17 @@ void __init plat_mem_setup(void)
clear_c0_config(1 << 19); /* Clear Config[OD] */
hw_coherentio = 0;
- coherentio = 1;
+ coherentio = IO_COHERENCE_ENABLED;
switch (alchemy_get_cputype()) {
case ALCHEMY_CPU_AU1000:
case ALCHEMY_CPU_AU1500:
case ALCHEMY_CPU_AU1100:
- coherentio = 0;
+ coherentio = IO_COHERENCE_DISABLED;
break;
case ALCHEMY_CPU_AU1200:
/* Au1200 AB USB does not support coherent memory */
if (0 == (read_c0_prid() & PRID_REV_MASK))
- coherentio = 0;
+ coherentio = IO_COHERENCE_DISABLED;
break;
}
diff --git a/arch/mips/bcm47xx/serial.c b/arch/mips/bcm47xx/serial.c
index df761d3..e3c9872 100644
--- a/arch/mips/bcm47xx/serial.c
+++ b/arch/mips/bcm47xx/serial.c
@@ -1,4 +1,7 @@
/*
+ * 8250 UART probe driver for the BCM47XX platforms
+ * Author: Aurelien Jarno
+ *
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
@@ -6,7 +9,6 @@
* Copyright (C) 2007 Aurelien Jarno <aurelien@aurel32.net>
*/
-#include <linux/module.h>
#include <linux/init.h>
#include <linux/serial.h>
#include <linux/serial_8250.h>
@@ -88,9 +90,4 @@ static int __init uart8250_init(void)
}
return -EINVAL;
}
-
-module_init(uart8250_init);
-
-MODULE_AUTHOR("Aurelien Jarno <aurelien@aurel32.net>");
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("8250 UART probe driver for the BCM47XX platforms");
+device_initcall(uart8250_init);
diff --git a/arch/mips/bcm63xx/clk.c b/arch/mips/bcm63xx/clk.c
index 6375652..b49fc9c 100644
--- a/arch/mips/bcm63xx/clk.c
+++ b/arch/mips/bcm63xx/clk.c
@@ -326,6 +326,9 @@ EXPORT_SYMBOL(clk_enable);
void clk_disable(struct clk *clk)
{
+ if (!clk)
+ return;
+
mutex_lock(&clocks_mutex);
clk_disable_unlocked(clk);
mutex_unlock(&clocks_mutex);
diff --git a/arch/mips/bmips/Kconfig b/arch/mips/bmips/Kconfig
index 264328d..2d60f25 100644
--- a/arch/mips/bmips/Kconfig
+++ b/arch/mips/bmips/Kconfig
@@ -21,10 +21,6 @@
bool "BCM93384WVG Viper CPU (EXPERIMENTAL)"
select BUILTIN_DTB
-config DT_BCM96358NB4SER
- bool "BCM96358NB4SER"
- select BUILTIN_DTB
-
config DT_BCM96368MVWG
bool "BCM96368MVWG"
select BUILTIN_DTB
@@ -65,6 +61,22 @@
bool "BCM97435SVMB"
select BUILTIN_DTB
+config DT_COMTREND_VR3032U
+ bool "Comtrend VR-3032u"
+ select BUILTIN_DTB
+
+config DT_NETGEAR_CVG834G
+ bool "NETGEAR CVG834G"
+ select BUILTIN_DTB
+
+config DT_SFR_NEUFBOX4_SERCOMM
+ bool "SFR Neufbox 4 (Sercomm)"
+ select BUILTIN_DTB
+
+config DT_SFR_NEUFBOX6_SERCOMM
+ bool "SFR Neufbox 6 (Sercomm)"
+ select BUILTIN_DTB
+
endchoice
endif
diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c
index 6776042..3b6f687 100644
--- a/arch/mips/bmips/setup.c
+++ b/arch/mips/bmips/setup.c
@@ -17,6 +17,7 @@
#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/of_platform.h>
+#include <linux/libfdt.h>
#include <linux/smp.h>
#include <asm/addrspace.h>
#include <asm/bmips.h>
@@ -98,7 +99,7 @@ static void bcm6328_quirks(void)
static void bcm6358_quirks(void)
{
/*
- * BCM6358 needs special handling for its shared TLB, so
+ * BCM3368/BCM6358 need special handling for their shared TLB, so
* disable SMP for now
*/
bmips_smp_enabled = 0;
@@ -110,10 +111,12 @@ static void bcm6368_quirks(void)
}
static const struct bmips_quirk bmips_quirk_list[] = {
+ { "brcm,bcm3368", &bcm6358_quirks },
{ "brcm,bcm3384-viper", &bcm3384_viper_quirks },
{ "brcm,bcm33843-viper", &bcm3384_viper_quirks },
{ "brcm,bcm6328", &bcm6328_quirks },
{ "brcm,bcm6358", &bcm6358_quirks },
+ { "brcm,bcm6362", &bcm6368_quirks },
{ "brcm,bcm6368", &bcm6368_quirks },
{ "brcm,bcm63168", &bcm6368_quirks },
{ "brcm,bcm63268", &bcm6368_quirks },
@@ -150,6 +153,8 @@ void __init plat_time_init(void)
mips_hpt_frequency = freq;
}
+extern const char __appended_dtb;
+
void __init plat_mem_setup(void)
{
void *dtb;
@@ -159,6 +164,11 @@ void __init plat_mem_setup(void)
ioport_resource.start = 0;
ioport_resource.end = ~0;
+#ifdef CONFIG_MIPS_ELF_APPENDED_DTB
+ if (!fdt_check_header(&__appended_dtb))
+ dtb = (void *)&__appended_dtb;
+ else
+#endif
/* intended to somewhat resemble ARM; see Documentation/arm/Booting */
if (fw_arg0 == 0 && fw_arg1 == 0xffffffff)
dtb = phys_to_virt(fw_arg2);
diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile
index acb1988..2728a9a 100644
--- a/arch/mips/boot/Makefile
+++ b/arch/mips/boot/Makefile
@@ -100,3 +100,69 @@
$(obj)/uImage: $(obj)/uImage.$(suffix-y)
@ln -sf $(notdir $<) $@
@echo ' Image $@ is ready'
+
+#
+# Flattened Image Tree (.itb) images
+#
+
+targets += vmlinux.itb
+targets += vmlinux.gz.itb
+targets += vmlinux.bz2.itb
+targets += vmlinux.lzma.itb
+targets += vmlinux.lzo.itb
+
+ifeq ($(ADDR_BITS),32)
+ itb_addr_cells = 1
+endif
+ifeq ($(ADDR_BITS),64)
+ itb_addr_cells = 2
+endif
+
+quiet_cmd_cpp_its_S = ITS $@
+ cmd_cpp_its_S = $(CPP) $(cpp_flags) -P -C -o $@ $< \
+ -DKERNEL_NAME="\"Linux $(KERNELRELEASE)\"" \
+ -DVMLINUX_BINARY="\"$(3)\"" \
+ -DVMLINUX_COMPRESSION="\"$(2)\"" \
+ -DVMLINUX_LOAD_ADDRESS=$(VMLINUX_LOAD_ADDRESS) \
+ -DVMLINUX_ENTRY_ADDRESS=$(VMLINUX_ENTRY_ADDRESS) \
+ -DADDR_BITS=$(ADDR_BITS) \
+ -DADDR_CELLS=$(itb_addr_cells)
+
+$(obj)/vmlinux.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S FORCE
+ $(call if_changed_dep,cpp_its_S,none,vmlinux.bin)
+
+$(obj)/vmlinux.gz.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S FORCE
+ $(call if_changed_dep,cpp_its_S,gzip,vmlinux.bin.gz)
+
+$(obj)/vmlinux.bz2.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S FORCE
+ $(call if_changed_dep,cpp_its_S,bzip2,vmlinux.bin.bz2)
+
+$(obj)/vmlinux.lzma.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S FORCE
+ $(call if_changed_dep,cpp_its_S,lzma,vmlinux.bin.lzma)
+
+$(obj)/vmlinux.lzo.its: $(srctree)/arch/mips/$(PLATFORM)/vmlinux.its.S FORCE
+ $(call if_changed_dep,cpp_its_S,lzo,vmlinux.bin.lzo)
+
+quiet_cmd_itb-image = ITB $@
+ cmd_itb-image = \
+ env PATH="$(objtree)/scripts/dtc:$(PATH)" \
+ $(CONFIG_SHELL) $(MKIMAGE) \
+ -D "-I dts -O dtb -p 500 \
+ --include $(objtree)/arch/mips \
+ --warning no-unit_address_vs_reg" \
+ -f $(2) $@
+
+$(obj)/vmlinux.itb: $(obj)/vmlinux.its $(obj)/vmlinux.bin FORCE
+ $(call if_changed,itb-image,$<)
+
+$(obj)/vmlinux.gz.itb: $(obj)/vmlinux.gz.its $(obj)/vmlinux.bin.gz FORCE
+ $(call if_changed,itb-image,$<)
+
+$(obj)/vmlinux.bz2.itb: $(obj)/vmlinux.bz2.its $(obj)/vmlinux.bin.bz2 FORCE
+ $(call if_changed,itb-image,$<)
+
+$(obj)/vmlinux.lzma.itb: $(obj)/vmlinux.lzma.its $(obj)/vmlinux.bin.lzma FORCE
+ $(call if_changed,itb-image,$<)
+
+$(obj)/vmlinux.lzo.itb: $(obj)/vmlinux.lzo.its $(obj)/vmlinux.bin.lzo FORCE
+ $(call if_changed,itb-image,$<)
diff --git a/arch/mips/boot/dts/brcm/Makefile b/arch/mips/boot/dts/brcm/Makefile
index fda9d38..d61bc2a 100644
--- a/arch/mips/boot/dts/brcm/Makefile
+++ b/arch/mips/boot/dts/brcm/Makefile
@@ -1,6 +1,5 @@
dtb-$(CONFIG_DT_BCM93384WVG) += bcm93384wvg.dtb
dtb-$(CONFIG_DT_BCM93384WVG_VIPER) += bcm93384wvg_viper.dtb
-dtb-$(CONFIG_DT_BCM96358NB4SER) += bcm96358nb4ser.dtb
dtb-$(CONFIG_DT_BCM96368MVWG) += bcm96368mvwg.dtb
dtb-$(CONFIG_DT_BCM9EJTAGPRB) += bcm9ejtagprb.dtb
dtb-$(CONFIG_DT_BCM97125CBMB) += bcm97125cbmb.dtb
@@ -11,20 +10,29 @@
dtb-$(CONFIG_DT_BCM97420C) += bcm97420c.dtb
dtb-$(CONFIG_DT_BCM97425SVMB) += bcm97425svmb.dtb
dtb-$(CONFIG_DT_BCM97435SVMB) += bcm97435svmb.dtb
+dtb-$(CONFIG_DT_COMTREND_VR3032U) += bcm63268-comtrend-vr-3032u.dtb
+dtb-$(CONFIG_DT_NETGEAR_CVG834G) += bcm3368-netgear-cvg834g.dtb
+dtb-$(CONFIG_DT_SFR_NEUFBOX4_SERCOMM) += bcm6358-neufbox4-sercomm.dtb
+dtb-$(CONFIG_DT_SFR_NEUFBOX6_SERCOMM) += bcm6362-neufbox6-sercomm.dtb
-dtb-$(CONFIG_DT_NONE) += \
- bcm93384wvg.dtb \
- bcm93384wvg_viper.dtb \
- bcm96358nb4ser.dtb \
- bcm96368mvwg.dtb \
- bcm9ejtagprb.dtb \
- bcm97125cbmb.dtb \
- bcm97346dbsmb.dtb \
- bcm97358svmb.dtb \
- bcm97360svmb.dtb \
- bcm97362svmb.dtb \
- bcm97420c.dtb \
- bcm97425svmb.dtb
+dtb-$(CONFIG_DT_NONE) += \
+ bcm3368-netgear-cvg834g.dtb \
+ bcm6358-neufbox4-sercomm.dtb \
+ bcm6362-neufbox6-sercomm.dtb \
+ bcm63268-comtrend-vr-3032u.dtb \
+ bcm93384wvg.dtb \
+ bcm93384wvg_viper.dtb \
+ bcm96358nb4ser.dtb \
+ bcm96368mvwg.dtb \
+ bcm9ejtagprb.dtb \
+ bcm97125cbmb.dtb \
+ bcm97346dbsmb.dtb \
+ bcm97358svmb.dtb \
+ bcm97360svmb.dtb \
+ bcm97362svmb.dtb \
+ bcm97420c.dtb \
+ bcm97425svmb.dtb \
+ bcm97435svmb.dtb
obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y))
diff --git a/arch/mips/boot/dts/brcm/bcm3368-netgear-cvg834g.dts b/arch/mips/boot/dts/brcm/bcm3368-netgear-cvg834g.dts
new file mode 100644
index 0000000..2f2e80f
--- /dev/null
+++ b/arch/mips/boot/dts/brcm/bcm3368-netgear-cvg834g.dts
@@ -0,0 +1,22 @@
+/dts-v1/;
+
+/include/ "bcm3368.dtsi"
+
+/ {
+ compatible = "netgear,cvg834g", "brcm,bcm3368";
+ model = "NETGEAR CVG834G";
+
+ memory@0 {
+ device_type = "memory";
+ reg = <0x00000000 0x02000000>;
+ };
+
+ chosen {
+ bootargs = "console=ttyS0,115200";
+ stdout-path = &uart0;
+ };
+};
+
+&uart0 {
+ status = "okay";
+};
diff --git a/arch/mips/boot/dts/brcm/bcm3368.dtsi b/arch/mips/boot/dts/brcm/bcm3368.dtsi
new file mode 100644
index 0000000..bee855c
--- /dev/null
+++ b/arch/mips/boot/dts/brcm/bcm3368.dtsi
@@ -0,0 +1,101 @@
+/ {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "brcm,bcm3368";
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ mips-hpt-frequency = <150000000>;
+
+ cpu@0 {
+ compatible = "brcm,bmips4350";
+ device_type = "cpu";
+ reg = <0>;
+ };
+
+ cpu@1 {
+ compatible = "brcm,bmips4350";
+ device_type = "cpu";
+ reg = <1>;
+ };
+ };
+
+ clocks {
+ periph_clk: periph-clk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <50000000>;
+ };
+ };
+
+ aliases {
+ serial0 = &uart0;
+ serial1 = &uart1;
+ };
+
+ cpu_intc: interrupt-controller {
+ #address-cells = <0>;
+ compatible = "mti,cpu-interrupt-controller";
+
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ };
+
+ ubus {
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ compatible = "simple-bus";
+ ranges;
+
+ periph_cntl: syscon@fff8c000 {
+ compatible = "syscon";
+ reg = <0xfff8c000 0xc>;
+ native-endian;
+ };
+
+ reboot: syscon-reboot@fff8c008 {
+ compatible = "syscon-reboot";
+ regmap = <&periph_cntl>;
+ offset = <0x8>;
+ mask = <0x1>;
+ };
+
+ periph_intc: interrupt-controller@fff8c00c {
+ compatible = "brcm,bcm6345-l1-intc";
+ reg = <0xfff8c00c 0x8>;
+
+ interrupt-controller;
+ #interrupt-cells = <1>;
+
+ interrupt-parent = <&cpu_intc>;
+ interrupts = <2>;
+ };
+
+ uart0: serial@fff8c100 {
+ compatible = "brcm,bcm6345-uart";
+ reg = <0xfff8c100 0x18>;
+
+ interrupt-parent = <&periph_intc>;
+ interrupts = <2>;
+
+ clocks = <&periph_clk>;
+
+ status = "disabled";
+ };
+
+ uart1: serial@fff8c120 {
+ compatible = "brcm,bcm6345-uart";
+ reg = <0xfff8c120 0x18>;
+
+ interrupt-parent = <&periph_intc>;
+ interrupts = <3>;
+
+ clocks = <&periph_clk>;
+
+ status = "disabled";
+ };
+ };
+};
diff --git a/arch/mips/boot/dts/brcm/bcm63268-comtrend-vr-3032u.dts b/arch/mips/boot/dts/brcm/bcm63268-comtrend-vr-3032u.dts
new file mode 100644
index 0000000..430d35c
--- /dev/null
+++ b/arch/mips/boot/dts/brcm/bcm63268-comtrend-vr-3032u.dts
@@ -0,0 +1,108 @@
+/dts-v1/;
+
+/include/ "bcm63268.dtsi"
+
+/ {
+ compatible = "comtrend,vr-3032u", "brcm,bcm63268";
+ model = "Comtrend VR-3032u";
+
+ memory@0 {
+ device_type = "memory";
+ reg = <0x00000000 0x04000000>;
+ };
+
+ chosen {
+ bootargs = "console=ttyS0,115200";
+ stdout-path = &uart0;
+ };
+};
+
+&leds0 {
+ status = "ok";
+ brcm,serial-leds;
+ brcm,serial-dat-low;
+ brcm,serial-shift-inv;
+
+ led@0 {
+ reg = <0>;
+ brcm,hardware-controlled;
+ brcm,link-signal-sources = <0>;
+ /* GPHY0 Speed 0 */
+ };
+ led@1 {
+ reg = <1>;
+ brcm,hardware-controlled;
+ brcm,link-signal-sources = <1>;
+ /* GPHY0 Speed 1 */
+ };
+ led@2 {
+ reg = <2>;
+ active-low;
+ label = "vr-3032u:red:inet";
+ };
+ led@3 {
+ reg = <3>;
+ active-low;
+ label = "vr-3032u:green:dsl";
+ };
+ led@4 {
+ reg = <4>;
+ active-low;
+ label = "vr-3032u:green:usb";
+ };
+ led@7 {
+ reg = <7>;
+ active-low;
+ label = "vr-3032u:green:wps";
+ };
+ led@8 {
+ reg = <8>;
+ active-low;
+ label = "vr-3032u:green:inet";
+ };
+ led@9 {
+ reg = <9>;
+ brcm,hardware-controlled;
+ /* EPHY0 Activity */
+ };
+ led@10 {
+ reg = <10>;
+ brcm,hardware-controlled;
+ /* EPHY1 Activity */
+ };
+ led@11 {
+ reg = <11>;
+ brcm,hardware-controlled;
+ /* EPHY2 Activity */
+ };
+ led@12 {
+ reg = <12>;
+ brcm,hardware-controlled;
+ /* GPHY0 Activity */
+ };
+ led@13 {
+ reg = <13>;
+ brcm,hardware-controlled;
+ /* EPHY0 Speed */
+ };
+ led@14 {
+ reg = <14>;
+ brcm,hardware-controlled;
+ /* EPHY1 Speed */
+ };
+ led@15 {
+ reg = <15>;
+ brcm,hardware-controlled;
+ /* EPHY2 Speed */
+ };
+ led@20 {
+ reg = <20>;
+ active-low;
+ label = "vr-3032u:green:power";
+ default-state = "on";
+ };
+};
+
+&uart0 {
+ status = "okay";
+};
diff --git a/arch/mips/boot/dts/brcm/bcm63268.dtsi b/arch/mips/boot/dts/brcm/bcm63268.dtsi
new file mode 100644
index 0000000..7e6bf2c
--- /dev/null
+++ b/arch/mips/boot/dts/brcm/bcm63268.dtsi
@@ -0,0 +1,134 @@
+/ {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "brcm,bcm63268";
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ mips-hpt-frequency = <200000000>;
+
+ cpu@0 {
+ compatible = "brcm,bmips4350";
+ device_type = "cpu";
+ reg = <0>;
+ };
+
+ cpu@1 {
+ compatible = "brcm,bmips4350";
+ device_type = "cpu";
+ reg = <1>;
+ };
+ };
+
+ clocks {
+ periph_clk: periph-clk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <50000000>;
+ };
+ };
+
+ aliases {
+ serial0 = &uart0;
+ serial1 = &uart1;
+ };
+
+ cpu_intc: interrupt-controller {
+ #address-cells = <0>;
+ compatible = "mti,cpu-interrupt-controller";
+
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ };
+
+ ubus {
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ compatible = "simple-bus";
+ ranges;
+
+ periph_cntl: syscon@10000000 {
+ compatible = "syscon";
+ reg = <0x10000000 0x14>;
+ native-endian;
+ };
+
+ reboot: syscon-reboot@10000008 {
+ compatible = "syscon-reboot";
+ regmap = <&periph_cntl>;
+ offset = <0x8>;
+ mask = <0x1>;
+ };
+
+ periph_intc: interrupt-controller@10000020 {
+ compatible = "brcm,bcm6345-l1-intc";
+ reg = <0x10000020 0x20>,
+ <0x10000040 0x20>;
+
+ interrupt-controller;
+ #interrupt-cells = <1>;
+
+ interrupt-parent = <&cpu_intc>;
+ interrupts = <2>, <3>;
+ };
+
+ uart0: serial@10000180 {
+ compatible = "brcm,bcm6345-uart";
+ reg = <0x10000180 0x18>;
+
+ interrupt-parent = <&periph_intc>;
+ interrupts = <5>;
+
+ clocks = <&periph_clk>;
+
+ status = "disabled";
+ };
+
+ uart1: serial@100001a0 {
+ compatible = "brcm,bcm6345-uart";
+ reg = <0x100001a0 0x18>;
+
+ interrupt-parent = <&periph_intc>;
+ interrupts = <34>;
+
+ clocks = <&periph_clk>;
+
+ status = "disabled";
+ };
+
+ leds0: led-controller@10001900 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ compatible = "brcm,bcm6328-leds";
+ reg = <0x10001900 0x24>;
+
+ status = "disabled";
+ };
+
+ ehci: usb@10002500 {
+ compatible = "brcm,bcm63268-ehci", "generic-ehci";
+ reg = <0x10002500 0x100>;
+ big-endian;
+
+ interrupt-parent = <&periph_intc>;
+ interrupts = <10>;
+
+ status = "disabled";
+ };
+
+ ohci: usb@10002600 {
+ compatible = "brcm,bcm63268-ohci", "generic-ohci";
+ reg = <0x10002600 0x100>;
+ big-endian;
+ no-big-frame-no;
+
+ interrupt-parent = <&periph_intc>;
+ interrupts = <9>;
+
+ status = "disabled";
+ };
+ };
+};
diff --git a/arch/mips/boot/dts/brcm/bcm96358nb4ser.dts b/arch/mips/boot/dts/brcm/bcm6358-neufbox4-sercomm.dts
similarity index 93%
rename from arch/mips/boot/dts/brcm/bcm96358nb4ser.dts
rename to arch/mips/boot/dts/brcm/bcm6358-neufbox4-sercomm.dts
index f412117..702eae2 100644
--- a/arch/mips/boot/dts/brcm/bcm96358nb4ser.dts
+++ b/arch/mips/boot/dts/brcm/bcm6358-neufbox4-sercomm.dts
@@ -12,6 +12,7 @@
};
chosen {
+ bootargs = "console=ttyS0,115200";
stdout-path = &uart0;
};
};
diff --git a/arch/mips/boot/dts/brcm/bcm6362-neufbox6-sercomm.dts b/arch/mips/boot/dts/brcm/bcm6362-neufbox6-sercomm.dts
new file mode 100644
index 0000000..480f2a5
--- /dev/null
+++ b/arch/mips/boot/dts/brcm/bcm6362-neufbox6-sercomm.dts
@@ -0,0 +1,22 @@
+/dts-v1/;
+
+/include/ "bcm6362.dtsi"
+
+/ {
+ compatible = "sfr,nb6-ser", "brcm,bcm6362";
+ model = "SFR NeufBox 6 (Sercomm)";
+
+ memory@0 {
+ device_type = "memory";
+ reg = <0x00000000 0x08000000>;
+ };
+
+ chosen {
+ bootargs = "console=ttyS0,115200";
+ stdout-path = &uart0;
+ };
+};
+
+&uart0 {
+ status = "okay";
+};
diff --git a/arch/mips/boot/dts/brcm/bcm6362.dtsi b/arch/mips/boot/dts/brcm/bcm6362.dtsi
new file mode 100644
index 0000000..c507da5
--- /dev/null
+++ b/arch/mips/boot/dts/brcm/bcm6362.dtsi
@@ -0,0 +1,134 @@
+/ {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "brcm,bcm6362";
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ mips-hpt-frequency = <200000000>;
+
+ cpu@0 {
+ compatible = "brcm,bmips4350";
+ device_type = "cpu";
+ reg = <0>;
+ };
+
+ cpu@1 {
+ compatible = "brcm,bmips4350";
+ device_type = "cpu";
+ reg = <1>;
+ };
+ };
+
+ clocks {
+ periph_clk: periph-clk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <50000000>;
+ };
+ };
+
+ aliases {
+ serial0 = &uart0;
+ serial1 = &uart1;
+ };
+
+ cpu_intc: interrupt-controller {
+ #address-cells = <0>;
+ compatible = "mti,cpu-interrupt-controller";
+
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ };
+
+ ubus {
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ compatible = "simple-bus";
+ ranges;
+
+ periph_cntl: syscon@10000000 {
+ compatible = "syscon";
+ reg = <0x10000000 0x14>;
+ native-endian;
+ };
+
+ reboot: syscon-reboot@10000008 {
+ compatible = "syscon-reboot";
+ regmap = <&periph_cntl>;
+ offset = <0x8>;
+ mask = <0x1>;
+ };
+
+ periph_intc: interrupt-controller@10000020 {
+ compatible = "brcm,bcm6345-l1-intc";
+ reg = <0x10000020 0x10>,
+ <0x10000030 0x10>;
+
+ interrupt-controller;
+ #interrupt-cells = <1>;
+
+ interrupt-parent = <&cpu_intc>;
+ interrupts = <2>, <3>;
+ };
+
+ uart0: serial@10000100 {
+ compatible = "brcm,bcm6345-uart";
+ reg = <0x10000100 0x18>;
+
+ interrupt-parent = <&periph_intc>;
+ interrupts = <3>;
+
+ clocks = <&periph_clk>;
+
+ status = "disabled";
+ };
+
+ uart1: serial@10000120 {
+ compatible = "brcm,bcm6345-uart";
+ reg = <0x10000120 0x18>;
+
+ interrupt-parent = <&periph_intc>;
+ interrupts = <4>;
+
+ clocks = <&periph_clk>;
+
+ status = "disabled";
+ };
+
+ leds0: led-controller@10001900 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ compatible = "brcm,bcm6328-leds";
+ reg = <0x10001900 0x24>;
+
+ status = "disabled";
+ };
+
+ ehci: usb@10002500 {
+ compatible = "brcm,bcm6362-ehci", "generic-ehci";
+ reg = <0x10002500 0x100>;
+ big-endian;
+
+ interrupt-parent = <&periph_intc>;
+ interrupts = <10>;
+
+ status = "disabled";
+ };
+
+ ohci: usb@10002600 {
+ compatible = "brcm,bcm6362-ohci", "generic-ohci";
+ reg = <0x10002600 0x100>;
+ big-endian;
+ no-big-frame-no;
+
+ interrupt-parent = <&periph_intc>;
+ interrupts = <9>;
+
+ status = "disabled";
+ };
+ };
+};
diff --git a/arch/mips/boot/dts/brcm/bcm7125.dtsi b/arch/mips/boot/dts/brcm/bcm7125.dtsi
index 550e1d9..bbd00f6 100644
--- a/arch/mips/boot/dts/brcm/bcm7125.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7125.dtsi
@@ -26,7 +26,7 @@
uart0 = &uart0;
};
- cpu_intc: cpu_intc {
+ cpu_intc: interrupt-controller {
#address-cells = <0>;
compatible = "mti,cpu-interrupt-controller";
@@ -40,6 +40,12 @@
#clock-cells = <0>;
clock-frequency = <81000000>;
};
+
+ upg_clk: upg_clk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <27000000>;
+ };
};
rdb {
@@ -49,7 +55,7 @@
compatible = "simple-bus";
ranges = <0 0x10000000 0x01000000>;
- periph_intc: periph_intc@441400 {
+ periph_intc: interrupt-controller@441400 {
compatible = "brcm,bcm7038-l1-intc";
reg = <0x441400 0x30>, <0x441600 0x30>;
@@ -60,7 +66,7 @@
interrupts = <2>, <3>;
};
- sun_l2_intc: sun_l2_intc@401800 {
+ sun_l2_intc: interrupt-controller@401800 {
compatible = "brcm,l2-intc";
reg = <0x401800 0x30>;
interrupt-controller;
@@ -81,7 +87,7 @@
"avd_0", "jtag_0";
};
- upg_irq0_intc: upg_irq0_intc@406780 {
+ upg_irq0_intc: interrupt-controller@406780 {
compatible = "brcm,bcm7120-l2-intc";
reg = <0x406780 0x8>;
@@ -183,6 +189,26 @@
status = "disabled";
};
+ pwma: pwm@406580 {
+ compatible = "brcm,bcm7038-pwm";
+ reg = <0x406580 0x28>;
+ #pwm-cells = <2>;
+ clocks = <&upg_clk>;
+ status = "disabled";
+ };
+
+ upg_gio: gpio@406700 {
+ compatible = "brcm,brcmstb-gpio";
+ reg = <0x406700 0x80>;
+ #gpio-cells = <2>;
+ #interrupt-cells = <2>;
+ gpio-controller;
+ interrupt-controller;
+ interrupt-parent = <&upg_irq0_intc>;
+ interrupts = <6>;
+ brcm,gpio-bank-widths = <32 32 32 18>;
+ };
+
ehci0: usb@488300 {
compatible = "brcm,bcm7125-ehci", "generic-ehci";
reg = <0x488300 0x100>;
diff --git a/arch/mips/boot/dts/brcm/bcm7346.dtsi b/arch/mips/boot/dts/brcm/bcm7346.dtsi
index ec95906..4bbcc95 100644
--- a/arch/mips/boot/dts/brcm/bcm7346.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7346.dtsi
@@ -26,7 +26,7 @@
uart0 = &uart0;
};
- cpu_intc: cpu_intc {
+ cpu_intc: interrupt-controller {
#address-cells = <0>;
compatible = "mti,cpu-interrupt-controller";
@@ -40,6 +40,12 @@
#clock-cells = <0>;
clock-frequency = <81000000>;
};
+
+ upg_clk: upg_clk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <27000000>;
+ };
};
rdb {
@@ -49,7 +55,7 @@
compatible = "simple-bus";
ranges = <0 0x10000000 0x01000000>;
- periph_intc: periph_intc@411400 {
+ periph_intc: interrupt-controller@411400 {
compatible = "brcm,bcm7038-l1-intc";
reg = <0x411400 0x30>, <0x411600 0x30>;
@@ -60,7 +66,7 @@
interrupts = <2>, <3>;
};
- sun_l2_intc: sun_l2_intc@403000 {
+ sun_l2_intc: interrupt-controller@403000 {
compatible = "brcm,l2-intc";
reg = <0x403000 0x30>;
interrupt-controller;
@@ -81,7 +87,7 @@
"jtag_0", "svd_0";
};
- upg_irq0_intc: upg_irq0_intc@406780 {
+ upg_irq0_intc: interrupt-controller@406780 {
compatible = "brcm,bcm7120-l2-intc";
reg = <0x406780 0x8>;
@@ -96,7 +102,7 @@
interrupt-names = "upg_main", "upg_bsc";
};
- upg_aon_irq0_intc: upg_aon_irq0_intc@408b80 {
+ upg_aon_irq0_intc: interrupt-controller@408b80 {
compatible = "brcm,bcm7120-l2-intc";
reg = <0x408b80 0x8>;
@@ -210,6 +216,59 @@
status = "disabled";
};
+ pwma: pwm@406580 {
+ compatible = "brcm,bcm7038-pwm";
+ reg = <0x406580 0x28>;
+ #pwm-cells = <2>;
+ clocks = <&upg_clk>;
+ status = "disabled";
+ };
+
+ pwmb: pwm@406800 {
+ compatible = "brcm,bcm7038-pwm";
+ reg = <0x406800 0x28>;
+ #pwm-cells = <2>;
+ clocks = <&upg_clk>;
+ status = "disabled";
+ };
+
+ aon_pm_l2_intc: interrupt-controller@408440 {
+ compatible = "brcm,l2-intc";
+ reg = <0x408440 0x30>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <53>;
+ brcm,irq-can-wake;
+ };
+
+ upg_gio: gpio@406700 {
+ compatible = "brcm,brcmstb-gpio";
+ reg = <0x406700 0x60>;
+ #gpio-cells = <2>;
+ #interrupt-cells = <2>;
+ gpio-controller;
+ interrupt-controller;
+ interrupt-parent = <&upg_irq0_intc>;
+ interrupts = <6>;
+ brcm,gpio-bank-widths = <32 32 16>;
+ };
+
+ upg_gio_aon: gpio@408c00 {
+ compatible = "brcm,brcmstb-gpio";
+ reg = <0x408c00 0x60>;
+ #gpio-cells = <2>;
+ #interrupt-cells = <2>;
+ gpio-controller;
+ interrupt-controller;
+ interrupt-parent = <&upg_aon_irq0_intc>;
+ interrupts = <6>;
+ interrupts-extended = <&upg_aon_irq0_intc 6>,
+ <&aon_pm_l2_intc 5>;
+ wakeup-source;
+ brcm,gpio-bank-widths = <27 32 2>;
+ };
+
enet0: ethernet@430000 {
phy-mode = "internal";
phy-handle = <&phy1>;
@@ -313,6 +372,26 @@
status = "disabled";
};
+ hif_l2_intc: interrupt-controller@411000 {
+ compatible = "brcm,l2-intc";
+ reg = <0x411000 0x30>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <30>;
+ };
+
+ nand: nand@412800 {
+ compatible = "brcm,brcmnand-v5.0", "brcm,brcmnand";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg-names = "nand";
+ reg = <0x412800 0x400>;
+ interrupt-parent = <&hif_l2_intc>;
+ interrupts = <24>;
+ status = "disabled";
+ };
+
sata: sata@181000 {
compatible = "brcm,bcm7425-ahci", "brcm,sata3-ahci";
reg-names = "ahci", "top-ctrl";
@@ -352,5 +431,13 @@
#phy-cells = <0>;
};
};
+
+ sdhci0: sdhci@413500 {
+ compatible = "brcm,bcm7425-sdhci";
+ reg = <0x413500 0x100>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <85>;
+ status = "disabled";
+ };
};
};
diff --git a/arch/mips/boot/dts/brcm/bcm7358.dtsi b/arch/mips/boot/dts/brcm/bcm7358.dtsi
index ca57fb5..3e42535 100644
--- a/arch/mips/boot/dts/brcm/bcm7358.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7358.dtsi
@@ -20,7 +20,7 @@
uart0 = &uart0;
};
- cpu_intc: cpu_intc {
+ cpu_intc: interrupt-controller {
#address-cells = <0>;
compatible = "mti,cpu-interrupt-controller";
@@ -34,6 +34,12 @@
#clock-cells = <0>;
clock-frequency = <81000000>;
};
+
+ upg_clk: upg_clk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <27000000>;
+ };
};
rdb {
@@ -43,7 +49,7 @@
compatible = "simple-bus";
ranges = <0 0x10000000 0x01000000>;
- periph_intc: periph_intc@411400 {
+ periph_intc: interrupt-controller@411400 {
compatible = "brcm,bcm7038-l1-intc";
reg = <0x411400 0x30>;
@@ -54,7 +60,7 @@
interrupts = <2>;
};
- sun_l2_intc: sun_l2_intc@403000 {
+ sun_l2_intc: interrupt-controller@403000 {
compatible = "brcm,l2-intc";
reg = <0x403000 0x30>;
interrupt-controller;
@@ -75,7 +81,7 @@
"avd_0", "jtag_0";
};
- upg_irq0_intc: upg_irq0_intc@406600 {
+ upg_irq0_intc: interrupt-controller@406600 {
compatible = "brcm,bcm7120-l2-intc";
reg = <0x406600 0x8>;
@@ -90,7 +96,7 @@
interrupt-names = "upg_main", "upg_bsc";
};
- upg_aon_irq0_intc: upg_aon_irq0_intc@408b80 {
+ upg_aon_irq0_intc: interrupt-controller@408b80 {
compatible = "brcm,bcm7120-l2-intc";
reg = <0x408b80 0x8>;
@@ -194,6 +200,59 @@
status = "disabled";
};
+ pwma: pwm@406400 {
+ compatible = "brcm,bcm7038-pwm";
+ reg = <0x406400 0x28>;
+ #pwm-cells = <2>;
+ clocks = <&upg_clk>;
+ status = "disabled";
+ };
+
+ pwmb: pwm@406700 {
+ compatible = "brcm,bcm7038-pwm";
+ reg = <0x406700 0x28>;
+ #pwm-cells = <2>;
+ clocks = <&upg_clk>;
+ status = "disabled";
+ };
+
+ aon_pm_l2_intc: interrupt-controller@408240 {
+ compatible = "brcm,l2-intc";
+ reg = <0x408240 0x30>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <50>;
+ brcm,irq-can-wake;
+ };
+
+ upg_gio: gpio@406500 {
+ compatible = "brcm,brcmstb-gpio";
+ reg = <0x406500 0xa0>;
+ #gpio-cells = <2>;
+ #interrupt-cells = <2>;
+ gpio-controller;
+ interrupt-controller;
+ interrupt-parent = <&upg_irq0_intc>;
+ interrupts = <6>;
+ brcm,gpio-bank-widths = <32 32 32 29 4>;
+ };
+
+ upg_gio_aon: gpio@408c00 {
+ compatible = "brcm,brcmstb-gpio";
+ reg = <0x408c00 0x60>;
+ #gpio-cells = <2>;
+ #interrupt-cells = <2>;
+ gpio-controller;
+ interrupt-controller;
+ interrupt-parent = <&upg_aon_irq0_intc>;
+ interrupts = <6>;
+ interrupts-extended = <&upg_aon_irq0_intc 6>,
+ <&aon_pm_l2_intc 5>;
+ wakeup-source;
+ brcm,gpio-bank-widths = <21 32 2>;
+ };
+
enet0: ethernet@430000 {
phy-mode = "internal";
phy-handle = <&phy1>;
@@ -239,5 +298,25 @@
interrupts = <66>;
status = "disabled";
};
+
+ hif_l2_intc: interrupt-controller@411000 {
+ compatible = "brcm,l2-intc";
+ reg = <0x411000 0x30>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <30>;
+ };
+
+ nand: nand@412800 {
+ compatible = "brcm,brcmnand-v5.0", "brcm,brcmnand";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg-names = "nand";
+ reg = <0x412800 0x400>;
+ interrupt-parent = <&hif_l2_intc>;
+ interrupts = <24>;
+ status = "disabled";
+ };
};
};
diff --git a/arch/mips/boot/dts/brcm/bcm7360.dtsi b/arch/mips/boot/dts/brcm/bcm7360.dtsi
index 1c0c3d4..112a557 100644
--- a/arch/mips/boot/dts/brcm/bcm7360.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7360.dtsi
@@ -20,7 +20,7 @@
uart0 = &uart0;
};
- cpu_intc: cpu_intc {
+ cpu_intc: interrupt-controller {
#address-cells = <0>;
compatible = "mti,cpu-interrupt-controller";
@@ -34,6 +34,12 @@
#clock-cells = <0>;
clock-frequency = <81000000>;
};
+
+ upg_clk: upg_clk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <27000000>;
+ };
};
rdb {
@@ -43,7 +49,7 @@
compatible = "simple-bus";
ranges = <0 0x10000000 0x01000000>;
- periph_intc: periph_intc@411400 {
+ periph_intc: interrupt-controller@411400 {
compatible = "brcm,bcm7038-l1-intc";
reg = <0x411400 0x30>;
@@ -54,7 +60,7 @@
interrupts = <2>;
};
- sun_l2_intc: sun_l2_intc@403000 {
+ sun_l2_intc: interrupt-controller@403000 {
compatible = "brcm,l2-intc";
reg = <0x403000 0x30>;
interrupt-controller;
@@ -75,7 +81,7 @@
"avd_0", "jtag_0";
};
- upg_irq0_intc: upg_irq0_intc@406600 {
+ upg_irq0_intc: interrupt-controller@406600 {
compatible = "brcm,bcm7120-l2-intc";
reg = <0x406600 0x8>;
@@ -90,7 +96,7 @@
interrupt-names = "upg_main", "upg_bsc";
};
- upg_aon_irq0_intc: upg_aon_irq0_intc@408b80 {
+ upg_aon_irq0_intc: interrupt-controller@408b80 {
compatible = "brcm,bcm7120-l2-intc";
reg = <0x408b80 0x8>;
@@ -194,6 +200,51 @@
status = "disabled";
};
+ pwma: pwm@406400 {
+ compatible = "brcm,bcm7038-pwm";
+ reg = <0x406400 0x28>;
+ #pwm-cells = <2>;
+ clocks = <&upg_clk>;
+ status = "disabled";
+ };
+
+ aon_pm_l2_intc: interrupt-controller@408440 {
+ compatible = "brcm,l2-intc";
+ reg = <0x408440 0x30>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <50>;
+ brcm,irq-can-wake;
+ };
+
+ upg_gio: gpio@406500 {
+ compatible = "brcm,brcmstb-gpio";
+ reg = <0x406500 0xa0>;
+ #gpio-cells = <2>;
+ #interrupt-cells = <2>;
+ gpio-controller;
+ interrupt-controller;
+ interrupt-parent = <&upg_irq0_intc>;
+ interrupts = <6>;
+ brcm,gpio-bank-widths = <32 32 32 29 4>;
+ };
+
+ upg_gio_aon: gpio@408c00 {
+ compatible = "brcm,brcmstb-gpio";
+ reg = <0x408c00 0x60>;
+ #gpio-cells = <2>;
+ #interrupt-cells = <2>;
+ gpio-controller;
+ interrupt-controller;
+ interrupt-parent = <&upg_aon_irq0_intc>;
+ interrupts = <6>;
+ interrupts-extended = <&upg_aon_irq0_intc 6>,
+ <&aon_pm_l2_intc 5>;
+ wakeup-source;
+ brcm,gpio-bank-widths = <21 32 2>;
+ };
+
enet0: ethernet@430000 {
phy-mode = "internal";
phy-handle = <&phy1>;
@@ -240,6 +291,26 @@
status = "disabled";
};
+ hif_l2_intc: interrupt-controller@411000 {
+ compatible = "brcm,l2-intc";
+ reg = <0x411000 0x30>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <30>;
+ };
+
+ nand: nand@412800 {
+ compatible = "brcm,brcmnand-v5.0", "brcm,brcmnand";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg-names = "nand";
+ reg = <0x412800 0x400>;
+ interrupt-parent = <&hif_l2_intc>;
+ interrupts = <24>;
+ status = "disabled";
+ };
+
sata: sata@181000 {
compatible = "brcm,bcm7425-ahci", "brcm,sata3-ahci";
reg-names = "ahci", "top-ctrl";
@@ -279,5 +350,13 @@
#phy-cells = <0>;
};
};
+
+ sdhci0: sdhci@410000 {
+ compatible = "brcm,bcm7425-sdhci";
+ reg = <0x410000 0x100>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <82>;
+ status = "disabled";
+ };
};
};
diff --git a/arch/mips/boot/dts/brcm/bcm7362.dtsi b/arch/mips/boot/dts/brcm/bcm7362.dtsi
index 6b4713a..34abfb0 100644
--- a/arch/mips/boot/dts/brcm/bcm7362.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7362.dtsi
@@ -26,7 +26,7 @@
uart0 = &uart0;
};
- cpu_intc: cpu_intc {
+ cpu_intc: interrupt-controller {
#address-cells = <0>;
compatible = "mti,cpu-interrupt-controller";
@@ -40,6 +40,12 @@
#clock-cells = <0>;
clock-frequency = <81000000>;
};
+
+ upg_clk: upg_clk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <27000000>;
+ };
};
rdb {
@@ -49,7 +55,7 @@
compatible = "simple-bus";
ranges = <0 0x10000000 0x01000000>;
- periph_intc: periph_intc@411400 {
+ periph_intc: interrupt-controller@411400 {
compatible = "brcm,bcm7038-l1-intc";
reg = <0x411400 0x30>, <0x411600 0x30>;
@@ -60,7 +66,7 @@
interrupts = <2>, <3>;
};
- sun_l2_intc: sun_l2_intc@403000 {
+ sun_l2_intc: interrupt-controller@403000 {
compatible = "brcm,l2-intc";
reg = <0x403000 0x30>;
interrupt-controller;
@@ -81,7 +87,7 @@
"avd_0", "jtag_0";
};
- upg_irq0_intc: upg_irq0_intc@406600 {
+ upg_irq0_intc: interrupt-controller@406600 {
compatible = "brcm,bcm7120-l2-intc";
reg = <0x406600 0x8>;
@@ -96,7 +102,7 @@
interrupt-names = "upg_main", "upg_bsc";
};
- upg_aon_irq0_intc: upg_aon_irq0_intc@408b80 {
+ upg_aon_irq0_intc: interrupt-controller@408b80 {
compatible = "brcm,bcm7120-l2-intc";
reg = <0x408b80 0x8>;
@@ -190,6 +196,51 @@
status = "disabled";
};
+ pwma: pwm@406400 {
+ compatible = "brcm,bcm7038-pwm";
+ reg = <0x406400 0x28>;
+ #pwm-cells = <2>;
+ clocks = <&upg_clk>;
+ status = "disabled";
+ };
+
+ aon_pm_l2_intc: interrupt-controller@408440 {
+ compatible = "brcm,l2-intc";
+ reg = <0x408440 0x30>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <50>;
+ brcm,irq-can-wake;
+ };
+
+ upg_gio: gpio@406500 {
+ compatible = "brcm,brcmstb-gpio";
+ reg = <0x406500 0xa0>;
+ #gpio-cells = <2>;
+ #interrupt-cells = <2>;
+ gpio-controller;
+ interrupt-controller;
+ interrupt-parent = <&upg_irq0_intc>;
+ interrupts = <6>;
+ brcm,gpio-bank-widths = <32 32 32 29 4>;
+ };
+
+ upg_gio_aon: gpio@408c00 {
+ compatible = "brcm,brcmstb-gpio";
+ reg = <0x408c00 0x60>;
+ #gpio-cells = <2>;
+ #interrupt-cells = <2>;
+ gpio-controller;
+ interrupt-controller;
+ interrupt-parent = <&upg_aon_irq0_intc>;
+ interrupts = <6>;
+ interrupts-extended = <&upg_aon_irq0_intc 6>,
+ <&aon_pm_l2_intc 5>;
+ wakeup-source;
+ brcm,gpio-bank-widths = <21 32 2>;
+ };
+
enet0: ethernet@430000 {
phy-mode = "internal";
phy-handle = <&phy1>;
@@ -236,6 +287,26 @@
status = "disabled";
};
+ hif_l2_intc: interrupt-controller@411000 {
+ compatible = "brcm,l2-intc";
+ reg = <0x411000 0x30>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <30>;
+ };
+
+ nand: nand@412800 {
+ compatible = "brcm,brcmnand-v5.0", "brcm,brcmnand";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg-names = "nand";
+ reg = <0x412800 0x400>;
+ interrupt-parent = <&hif_l2_intc>;
+ interrupts = <24>;
+ status = "disabled";
+ };
+
sata: sata@181000 {
compatible = "brcm,bcm7425-ahci", "brcm,sata3-ahci";
reg-names = "ahci", "top-ctrl";
@@ -275,5 +346,13 @@
#phy-cells = <0>;
};
};
+
+ sdhci0: sdhci@410000 {
+ compatible = "brcm,bcm7425-sdhci";
+ reg = <0x410000 0x100>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <82>;
+ status = "disabled";
+ };
};
};
diff --git a/arch/mips/boot/dts/brcm/bcm7420.dtsi b/arch/mips/boot/dts/brcm/bcm7420.dtsi
index 0586bf6..b143723 100644
--- a/arch/mips/boot/dts/brcm/bcm7420.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7420.dtsi
@@ -26,7 +26,7 @@
uart0 = &uart0;
};
- cpu_intc: cpu_intc {
+ cpu_intc: interrupt-controller {
#address-cells = <0>;
compatible = "mti,cpu-interrupt-controller";
@@ -40,6 +40,12 @@
#clock-cells = <0>;
clock-frequency = <81000000>;
};
+
+ upg_clk: upg_clk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <27000000>;
+ };
};
rdb {
@@ -49,7 +55,7 @@
compatible = "simple-bus";
ranges = <0 0x10000000 0x01000000>;
- periph_intc: periph_intc@441400 {
+ periph_intc: interrupt-controller@441400 {
compatible = "brcm,bcm7038-l1-intc";
reg = <0x441400 0x30>, <0x441600 0x30>;
@@ -60,7 +66,7 @@
interrupts = <2>, <3>;
};
- sun_l2_intc: sun_l2_intc@401800 {
+ sun_l2_intc: interrupt-controller@401800 {
compatible = "brcm,l2-intc";
reg = <0x401800 0x30>;
interrupt-controller;
@@ -82,7 +88,7 @@
"jtag_0";
};
- upg_irq0_intc: upg_irq0_intc@406780 {
+ upg_irq0_intc: interrupt-controller@406780 {
compatible = "brcm,bcm7120-l2-intc";
reg = <0x406780 0x8>;
@@ -191,6 +197,34 @@
status = "disabled";
};
+ pwma: pwm@406580 {
+ compatible = "brcm,bcm7038-pwm";
+ reg = <0x406580 0x28>;
+ #pwm-cells = <2>;
+ clocks = <&upg_clk>;
+ status = "disabled";
+ };
+
+ pwmb: pwm@406880 {
+ compatible = "brcm,bcm7038-pwm";
+ reg = <0x406880 0x28>;
+ #pwm-cells = <2>;
+ clocks = <&upg_clk>;
+ status = "disabled";
+ };
+
+ upg_gio: gpio@406700 {
+ compatible = "brcm,brcmstb-gpio";
+ reg = <0x406700 0x80>;
+ #gpio-cells = <2>;
+ #interrupt-cells = <2>;
+ gpio-controller;
+ interrupt-controller;
+ interrupt-parent = <&upg_irq0_intc>;
+ interrupts = <6>;
+ brcm,gpio-bank-widths = <32 32 32 27>;
+ };
+
enet0: ethernet@468000 {
phy-mode = "internal";
phy-handle = <&phy1>;
diff --git a/arch/mips/boot/dts/brcm/bcm7425.dtsi b/arch/mips/boot/dts/brcm/bcm7425.dtsi
index c1c15ed..2488d2f 100644
--- a/arch/mips/boot/dts/brcm/bcm7425.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7425.dtsi
@@ -26,7 +26,7 @@
uart0 = &uart0;
};
- cpu_intc: cpu_intc {
+ cpu_intc: interrupt-controller {
#address-cells = <0>;
compatible = "mti,cpu-interrupt-controller";
@@ -40,6 +40,12 @@
#clock-cells = <0>;
clock-frequency = <81000000>;
};
+
+ upg_clk: upg_clk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <27000000>;
+ };
};
rdb {
@@ -49,7 +55,7 @@
compatible = "simple-bus";
ranges = <0 0x10000000 0x01000000>;
- periph_intc: periph_intc@41a400 {
+ periph_intc: interrupt-controller@41a400 {
compatible = "brcm,bcm7038-l1-intc";
reg = <0x41a400 0x30>, <0x41a600 0x30>;
@@ -60,7 +66,7 @@
interrupts = <2>, <3>;
};
- sun_l2_intc: sun_l2_intc@403000 {
+ sun_l2_intc: interrupt-controller@403000 {
compatible = "brcm,l2-intc";
reg = <0x403000 0x30>;
interrupt-controller;
@@ -83,7 +89,7 @@
"vice_0";
};
- upg_irq0_intc: upg_irq0_intc@406780 {
+ upg_irq0_intc: interrupt-controller@406780 {
compatible = "brcm,bcm7120-l2-intc";
reg = <0x406780 0x8>;
@@ -98,7 +104,7 @@
interrupt-names = "upg_main", "upg_bsc";
};
- upg_aon_irq0_intc: upg_aon_irq0_intc@409480 {
+ upg_aon_irq0_intc: interrupt-controller@409480 {
compatible = "brcm,bcm7120-l2-intc";
reg = <0x409480 0x8>;
@@ -209,6 +215,59 @@
status = "disabled";
};
+ pwma: pwm@406580 {
+ compatible = "brcm,bcm7038-pwm";
+ reg = <0x406580 0x28>;
+ #pwm-cells = <2>;
+ clocks = <&upg_clk>;
+ status = "disabled";
+ };
+
+ pwmb: pwm@406800 {
+ compatible = "brcm,bcm7038-pwm";
+ reg = <0x406800 0x28>;
+ #pwm-cells = <2>;
+ clocks = <&upg_clk>;
+ status = "disabled";
+ };
+
+ aon_pm_l2_intc: interrupt-controller@408440 {
+ compatible = "brcm,l2-intc";
+ reg = <0x408440 0x30>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <49>;
+ brcm,irq-can-wake;
+ };
+
+ upg_gio: gpio@406700 {
+ compatible = "brcm,brcmstb-gpio";
+ reg = <0x406700 0x80>;
+ #gpio-cells = <2>;
+ #interrupt-cells = <2>;
+ gpio-controller;
+ interrupt-controller;
+ interrupt-parent = <&upg_irq0_intc>;
+ interrupts = <6>;
+ brcm,gpio-bank-widths = <32 32 32 21>;
+ };
+
+ upg_gio_aon: gpio@4094c0 {
+ compatible = "brcm,brcmstb-gpio";
+ reg = <0x4094c0 0x40>;
+ #gpio-cells = <2>;
+ #interrupt-cells = <2>;
+ gpio-controller;
+ interrupt-controller;
+ interrupt-parent = <&upg_aon_irq0_intc>;
+ interrupts = <6>;
+ interrupts-extended = <&upg_aon_irq0_intc 6>,
+ <&aon_pm_l2_intc 5>;
+ wakeup-source;
+ brcm,gpio-bank-widths = <18 4>;
+ };
+
enet0: ethernet@b80000 {
phy-mode = "internal";
phy-handle = <&phy1>;
@@ -312,6 +371,26 @@
status = "disabled";
};
+ hif_l2_intc: interrupt-controller@41a000 {
+ compatible = "brcm,l2-intc";
+ reg = <0x41a000 0x30>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <24>;
+ };
+
+ nand: nand@41b800 {
+ compatible = "brcm,brcmnand-v5.0", "brcm,brcmnand";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg-names = "nand";
+ reg = <0x41b800 0x400>;
+ interrupt-parent = <&hif_l2_intc>;
+ interrupts = <24>;
+ status = "disabled";
+ };
+
sata: sata@181000 {
compatible = "brcm,bcm7425-ahci", "brcm,sata3-ahci";
reg-names = "ahci", "top-ctrl";
@@ -351,5 +430,25 @@
#phy-cells = <0>;
};
};
+
+ sdhci0: sdhci@419000 {
+ compatible = "brcm,bcm7425-sdhci";
+ reg = <0x419000 0x100>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <43>;
+ sd-uhs-sdr50;
+ mmc-hs200-1_8v;
+ status = "disabled";
+ };
+
+ sdhci1: sdhci@419200 {
+ compatible = "brcm,bcm7425-sdhci";
+ reg = <0x419200 0x100>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <44>;
+ sd-uhs-sdr50;
+ mmc-hs200-1_8v;
+ status = "disabled";
+ };
};
};
diff --git a/arch/mips/boot/dts/brcm/bcm7435.dtsi b/arch/mips/boot/dts/brcm/bcm7435.dtsi
index a874d3a..19fa259 100644
--- a/arch/mips/boot/dts/brcm/bcm7435.dtsi
+++ b/arch/mips/boot/dts/brcm/bcm7435.dtsi
@@ -38,7 +38,7 @@
uart0 = &uart0;
};
- cpu_intc: cpu_intc {
+ cpu_intc: interrupt-controller {
#address-cells = <0>;
compatible = "mti,cpu-interrupt-controller";
@@ -52,6 +52,12 @@
#clock-cells = <0>;
clock-frequency = <81000000>;
};
+
+ upg_clk: upg_clk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <27000000>;
+ };
};
rdb {
@@ -61,7 +67,7 @@
compatible = "simple-bus";
ranges = <0 0x10000000 0x01000000>;
- periph_intc: periph_intc@41b500 {
+ periph_intc: interrupt-controller@41b500 {
compatible = "brcm,bcm7038-l1-intc";
reg = <0x41b500 0x40>, <0x41b600 0x40>,
<0x41b700 0x40>, <0x41b800 0x40>;
@@ -73,7 +79,7 @@
interrupts = <2>, <3>, <2>, <3>;
};
- sun_l2_intc: sun_l2_intc@403000 {
+ sun_l2_intc: interrupt-controller@403000 {
compatible = "brcm,l2-intc";
reg = <0x403000 0x30>;
interrupt-controller;
@@ -98,7 +104,7 @@
"scpu";
};
- upg_irq0_intc: upg_irq0_intc@406780 {
+ upg_irq0_intc: interrupt-controller@406780 {
compatible = "brcm,bcm7120-l2-intc";
reg = <0x406780 0x8>;
@@ -113,7 +119,7 @@
interrupt-names = "upg_main", "upg_bsc";
};
- upg_aon_irq0_intc: upg_aon_irq0_intc@409480 {
+ upg_aon_irq0_intc: interrupt-controller@409480 {
compatible = "brcm,bcm7120-l2-intc";
reg = <0x409480 0x8>;
@@ -224,6 +230,59 @@
status = "disabled";
};
+ pwma: pwm@406580 {
+ compatible = "brcm,bcm7038-pwm";
+ reg = <0x406580 0x28>;
+ #pwm-cells = <2>;
+ clocks = <&upg_clk>;
+ status = "disabled";
+ };
+
+ pwmb: pwm@406800 {
+ compatible = "brcm,bcm7038-pwm";
+ reg = <0x406800 0x28>;
+ #pwm-cells = <2>;
+ clocks = <&upg_clk>;
+ status = "disabled";
+ };
+
+ aon_pm_l2_intc: interrupt-controller@408440 {
+ compatible = "brcm,l2-intc";
+ reg = <0x408440 0x30>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <54>;
+ brcm,irq-can-wake;
+ };
+
+ upg_gio: gpio@406700 {
+ compatible = "brcm,brcmstb-gpio";
+ reg = <0x406700 0x80>;
+ #gpio-cells = <2>;
+ #interrupt-cells = <2>;
+ gpio-controller;
+ interrupt-controller;
+ interrupt-parent = <&upg_irq0_intc>;
+ interrupts = <6>;
+ brcm,gpio-bank-widths = <32 32 32 21>;
+ };
+
+ upg_gio_aon: gpio@4094c0 {
+ compatible = "brcm,brcmstb-gpio";
+ reg = <0x4094c0 0x40>;
+ #gpio-cells = <2>;
+ #interrupt-cells = <2>;
+ gpio-controller;
+ interrupt-controller;
+ interrupt-parent = <&upg_aon_irq0_intc>;
+ interrupts = <6>;
+ interrupts-extended = <&upg_aon_irq0_intc 6>,
+ <&aon_pm_l2_intc 5>;
+ wakeup-source;
+ brcm,gpio-bank-widths = <18 4>;
+ };
+
enet0: ethernet@b80000 {
phy-mode = "internal";
phy-handle = <&phy1>;
@@ -327,6 +386,26 @@
status = "disabled";
};
+ hif_l2_intc: interrupt-controller@41b000 {
+ compatible = "brcm,l2-intc";
+ reg = <0x41b000 0x30>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <24>;
+ };
+
+ nand: nand@41c800 {
+ compatible = "brcm,brcmnand-v6.2", "brcm,brcmnand";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg-names = "nand", "flash-dma";
+ reg = <0x41c800 0x600>, <0x41d000 0x100>;
+ interrupt-parent = <&hif_l2_intc>;
+ interrupts = <24>, <4>;
+ status = "disabled";
+ };
+
sata: sata@181000 {
compatible = "brcm,bcm7425-ahci", "brcm,sata3-ahci";
reg-names = "ahci", "top-ctrl";
@@ -366,5 +445,25 @@
#phy-cells = <0>;
};
};
+
+ sdhci0: sdhci@41a000 {
+ compatible = "brcm,bcm7425-sdhci";
+ reg = <0x41a000 0x100>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <47>;
+ sd-uhs-sdr50;
+ mmc-hs200-1_8v;
+ status = "disabled";
+ };
+
+ sdhci1: sdhci@41a200 {
+ compatible = "brcm,bcm7425-sdhci";
+ reg = <0x41a200 0x100>;
+ interrupt-parent = <&periph_intc>;
+ interrupts = <48>;
+ sd-uhs-sdr50;
+ mmc-hs200-1_8v;
+ status = "disabled";
+ };
};
};
diff --git a/arch/mips/boot/dts/brcm/bcm97125cbmb.dts b/arch/mips/boot/dts/brcm/bcm97125cbmb.dts
index f2449d1..5c24eac 100644
--- a/arch/mips/boot/dts/brcm/bcm97125cbmb.dts
+++ b/arch/mips/boot/dts/brcm/bcm97125cbmb.dts
@@ -45,6 +45,10 @@
status = "okay";
};
+&pwma {
+ status = "okay";
+};
+
/* FIXME: USB is wonky; disable it for now */
&ehci0 {
status = "disabled";
diff --git a/arch/mips/boot/dts/brcm/bcm97346dbsmb.dts b/arch/mips/boot/dts/brcm/bcm97346dbsmb.dts
index d3d2881..e67eaf3 100644
--- a/arch/mips/boot/dts/brcm/bcm97346dbsmb.dts
+++ b/arch/mips/boot/dts/brcm/bcm97346dbsmb.dts
@@ -1,6 +1,7 @@
/dts-v1/;
/include/ "bcm7346.dtsi"
+/include/ "bcm97xxx-nand-cs1-bch24.dtsi"
/ {
compatible = "brcm,bcm97346dbsmb", "brcm,bcm7346";
@@ -49,6 +50,14 @@
status = "okay";
};
+&pwma {
+ status = "okay";
+};
+
+&pwmb {
+ status = "okay";
+};
+
&enet0 {
status = "okay";
};
@@ -85,6 +94,10 @@
status = "okay";
};
+&nand {
+ status = "okay";
+};
+
&sata {
status = "okay";
};
@@ -92,3 +105,7 @@
&sata_phy {
status = "okay";
};
+
+&sdhci0 {
+ status = "okay";
+};
diff --git a/arch/mips/boot/dts/brcm/bcm97358svmb.dts b/arch/mips/boot/dts/brcm/bcm97358svmb.dts
index 02ce6b4..ee4607f 100644
--- a/arch/mips/boot/dts/brcm/bcm97358svmb.dts
+++ b/arch/mips/boot/dts/brcm/bcm97358svmb.dts
@@ -1,6 +1,7 @@
/dts-v1/;
/include/ "bcm7358.dtsi"
+/include/ "bcm97xxx-nand-cs1-bch4.dtsi"
/ {
compatible = "brcm,bcm97358svmb", "brcm,bcm7358";
@@ -45,6 +46,14 @@
status = "okay";
};
+&pwma {
+ status = "okay";
+};
+
+&pwmb {
+ status = "okay";
+};
+
&enet0 {
status = "okay";
};
@@ -56,3 +65,7 @@
&ohci0 {
status = "okay";
};
+
+&nand {
+ status = "okay";
+};
diff --git a/arch/mips/boot/dts/brcm/bcm97360svmb.dts b/arch/mips/boot/dts/brcm/bcm97360svmb.dts
index 73124be..bed821b 100644
--- a/arch/mips/boot/dts/brcm/bcm97360svmb.dts
+++ b/arch/mips/boot/dts/brcm/bcm97360svmb.dts
@@ -45,6 +45,10 @@
status = "okay";
};
+&pwma {
+ status = "okay";
+};
+
&enet0 {
status = "okay";
};
@@ -64,3 +68,7 @@
&sata_phy {
status = "okay";
};
+
+&sdhci0 {
+ status = "okay";
+};
diff --git a/arch/mips/boot/dts/brcm/bcm97362svmb.dts b/arch/mips/boot/dts/brcm/bcm97362svmb.dts
index 3cfcaeb..68fd8238 100644
--- a/arch/mips/boot/dts/brcm/bcm97362svmb.dts
+++ b/arch/mips/boot/dts/brcm/bcm97362svmb.dts
@@ -1,6 +1,7 @@
/dts-v1/;
/include/ "bcm7362.dtsi"
+/include/ "bcm97xxx-nand-cs1-bch4.dtsi"
/ {
compatible = "brcm,bcm97362svmb", "brcm,bcm7362";
@@ -41,6 +42,10 @@
status = "okay";
};
+&pwma {
+ status = "okay";
+};
+
&enet0 {
status = "okay";
};
@@ -53,6 +58,10 @@
status = "okay";
};
+&nand {
+ status = "okay";
+};
+
&sata {
status = "okay";
};
@@ -60,3 +69,7 @@
&sata_phy {
status = "okay";
};
+
+&sdhci0 {
+ status = "okay";
+};
diff --git a/arch/mips/boot/dts/brcm/bcm97420c.dts b/arch/mips/boot/dts/brcm/bcm97420c.dts
index 600d57a..e66271a 100644
--- a/arch/mips/boot/dts/brcm/bcm97420c.dts
+++ b/arch/mips/boot/dts/brcm/bcm97420c.dts
@@ -51,6 +51,14 @@
status = "okay";
};
+&pwma {
+ status = "okay";
+};
+
+&pwmb {
+ status = "okay";
+};
+
/* FIXME: MAC driver comes up but cannot attach to PHY */
&enet0 {
status = "disabled";
diff --git a/arch/mips/boot/dts/brcm/bcm97425svmb.dts b/arch/mips/boot/dts/brcm/bcm97425svmb.dts
index 119c714..f95ba1b 100644
--- a/arch/mips/boot/dts/brcm/bcm97425svmb.dts
+++ b/arch/mips/boot/dts/brcm/bcm97425svmb.dts
@@ -1,6 +1,7 @@
/dts-v1/;
/include/ "bcm7425.dtsi"
+/include/ "bcm97xxx-nand-cs1-bch24.dtsi"
/ {
compatible = "brcm,bcm97425svmb", "brcm,bcm7425";
@@ -51,6 +52,14 @@
status = "okay";
};
+&pwma {
+ status = "okay";
+};
+
+&pwmb {
+ status = "okay";
+};
+
&enet0 {
status = "okay";
};
@@ -86,3 +95,15 @@
&ohci3 {
status = "okay";
};
+
+&nand {
+ status = "okay";
+};
+
+&sdhci0 {
+ status = "okay";
+};
+
+&sdhci1 {
+ status = "okay";
+};
diff --git a/arch/mips/boot/dts/brcm/bcm97435svmb.dts b/arch/mips/boot/dts/brcm/bcm97435svmb.dts
index 43e3ba2..fb37b71 100644
--- a/arch/mips/boot/dts/brcm/bcm97435svmb.dts
+++ b/arch/mips/boot/dts/brcm/bcm97435svmb.dts
@@ -1,6 +1,7 @@
/dts-v1/;
/include/ "bcm7435.dtsi"
+/include/ "bcm97xxx-nand-cs1-bch24.dtsi"
/ {
compatible = "brcm,bcm97435svmb", "brcm,bcm7435";
@@ -51,6 +52,14 @@
status = "okay";
};
+&pwma {
+ status = "okay";
+};
+
+&pwmb {
+ status = "okay";
+};
+
&enet0 {
status = "okay";
};
@@ -87,6 +96,10 @@
status = "okay";
};
+&nand {
+ status = "okay";
+};
+
&sata {
status = "okay";
};
@@ -94,3 +107,11 @@
&sata_phy {
status = "okay";
};
+
+&sdhci0 {
+ status = "okay";
+};
+
+&sdhci1 {
+ status = "okay";
+};
diff --git a/arch/mips/boot/dts/brcm/bcm97xxx-nand-cs1-bch24.dtsi b/arch/mips/boot/dts/brcm/bcm97xxx-nand-cs1-bch24.dtsi
new file mode 100644
index 0000000..3c24f97
--- /dev/null
+++ b/arch/mips/boot/dts/brcm/bcm97xxx-nand-cs1-bch24.dtsi
@@ -0,0 +1,25 @@
+&nand {
+ nandcs@1 {
+ compatible = "brcm,nandcs";
+ reg = <1>;
+ nand-on-flash-bbt;
+
+ nand-ecc-strength = <24>;
+ nand-ecc-step-size = <1024>;
+ brcm,nand-oob-sector-size = <27>;
+
+ partitions {
+ compatible = "fixed-partitions";
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ flash1.rootfs@0 {
+ reg = <0x0 0x10000000>;
+ };
+
+ flash1.kernel@10000000 {
+ reg = <0x10000000 0x400000>;
+ };
+ };
+ };
+};
diff --git a/arch/mips/boot/dts/brcm/bcm97xxx-nand-cs1-bch4.dtsi b/arch/mips/boot/dts/brcm/bcm97xxx-nand-cs1-bch4.dtsi
new file mode 100644
index 0000000..cb53181
--- /dev/null
+++ b/arch/mips/boot/dts/brcm/bcm97xxx-nand-cs1-bch4.dtsi
@@ -0,0 +1,25 @@
+&nand {
+ nandcs@1 {
+ compatible = "brcm,nandcs";
+ reg = <1>;
+ nand-on-flash-bbt;
+
+ nand-ecc-strength = <4>;
+ nand-ecc-step-size = <512>;
+ brcm,nand-oob-sector-size = <16>;
+
+ partitions {
+ compatible = "fixed-partitions";
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ flash1.rootfs@0 {
+ reg = <0x0 0x10000000>;
+ };
+
+ flash1.kernel@10000000 {
+ reg = <0x10000000 0x400000>;
+ };
+ };
+ };
+};
diff --git a/arch/mips/boot/dts/cavium-octeon/dlink_dsr-1000n.dts b/arch/mips/boot/dts/cavium-octeon/dlink_dsr-1000n.dts
index b134798..cfa2915 100644
--- a/arch/mips/boot/dts/cavium-octeon/dlink_dsr-1000n.dts
+++ b/arch/mips/boot/dts/cavium-octeon/dlink_dsr-1000n.dts
@@ -8,55 +8,16 @@
* published by the Free Software Foundation.
*/
-/include/ "octeon_3xxx.dtsi"
+/include/ "dlink_dsr-500n-1000n.dtsi"
#include <dt-bindings/gpio/gpio.h>
/ {
model = "dlink,dsr-1000n";
soc@0 {
- smi0: mdio@1180000001800 {
- phy8: ethernet-phy@8 {
- reg = <8>;
- compatible = "ethernet-phy-ieee802.3-c22";
- };
- };
-
- pip: pip@11800a0000000 {
- interface@0 {
- ethernet@0 {
- fixed-link {
- speed = <1000>;
- full-duplex;
- };
- };
- ethernet@1 {
- fixed-link {
- speed = <1000>;
- full-duplex;
- };
- };
- ethernet@2 {
- phy-handle = <&phy8>;
- };
- };
- };
-
- twsi0: i2c@1180000001000 {
- rtc@68 {
- compatible = "dallas,ds1337";
- reg = <0x68>;
- };
- };
-
uart0: serial@1180000000800 {
clock-frequency = <500000000>;
};
-
- usbn: usbn@1180068000000 {
- refclk-frequency = <12000000>;
- refclk-type = "crystal";
- };
};
leds {
@@ -87,8 +48,4 @@
gpios = <&gpio 18 GPIO_ACTIVE_LOW>;
};
};
-
- aliases {
- pip = &pip;
- };
};
diff --git a/arch/mips/boot/dts/cavium-octeon/dlink_dsr-500n-1000n.dtsi b/arch/mips/boot/dts/cavium-octeon/dlink_dsr-500n-1000n.dtsi
new file mode 100644
index 0000000..246b598
--- /dev/null
+++ b/arch/mips/boot/dts/cavium-octeon/dlink_dsr-500n-1000n.dtsi
@@ -0,0 +1,58 @@
+/*
+ * Device tree source for D-Link DSR-500N/1000N (common parts).
+ *
+ * Written by: Aaro Koskinen <aaro.koskinen@iki.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/include/ "octeon_3xxx.dtsi"
+
+/ {
+ soc@0 {
+ smi0: mdio@1180000001800 {
+ phy8: ethernet-phy@8 {
+ reg = <8>;
+ compatible = "ethernet-phy-ieee802.3-c22";
+ };
+ };
+
+ pip: pip@11800a0000000 {
+ interface@0 {
+ ethernet@0 {
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ };
+ };
+ ethernet@1 {
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ };
+ };
+ ethernet@2 {
+ phy-handle = <&phy8>;
+ };
+ };
+ };
+
+ twsi0: i2c@1180000001000 {
+ rtc@68 {
+ compatible = "dallas,ds1337";
+ reg = <0x68>;
+ };
+ };
+
+ usbn: usbn@1180068000000 {
+ refclk-frequency = <12000000>;
+ refclk-type = "crystal";
+ };
+ };
+
+ aliases {
+ pip = &pip;
+ };
+};
diff --git a/arch/mips/boot/dts/cavium-octeon/dlink_dsr-500n.dts b/arch/mips/boot/dts/cavium-octeon/dlink_dsr-500n.dts
new file mode 100644
index 0000000..78886e1
--- /dev/null
+++ b/arch/mips/boot/dts/cavium-octeon/dlink_dsr-500n.dts
@@ -0,0 +1,40 @@
+/*
+ * Device tree source for D-Link DSR-500N.
+ *
+ * Written by: Aaro Koskinen <aaro.koskinen@iki.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/include/ "dlink_dsr-500n-1000n.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+
+/ {
+ model = "dlink,dsr-500n";
+ compatible = "dlink,dsr-500n", "cavium,octeon-3860";
+
+ soc@0 {
+ uart0: serial@1180000000800 {
+ clock-frequency = <300000000>;
+ };
+ };
+
+ leds {
+ compatible = "gpio-leds";
+
+ usb {
+ gpios = <&gpio 9 GPIO_ACTIVE_LOW>;
+ };
+
+ wps {
+ gpios = <&gpio 11 GPIO_ACTIVE_LOW>;
+ };
+
+ wireless {
+ label = "2.4g";
+ gpios = <&gpio 18 GPIO_ACTIVE_LOW>;
+ };
+ };
+};
diff --git a/arch/mips/boot/dts/mti/Makefile b/arch/mips/boot/dts/mti/Makefile
index 144d776..fcabd69 100644
--- a/arch/mips/boot/dts/mti/Makefile
+++ b/arch/mips/boot/dts/mti/Makefile
@@ -1,5 +1,5 @@
dtb-$(CONFIG_MIPS_MALTA) += malta.dtb
-dtb-$(CONFIG_MIPS_SEAD3) += sead3.dtb
+dtb-$(CONFIG_LEGACY_BOARD_SEAD3) += sead3.dtb
obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y))
diff --git a/arch/mips/boot/dts/mti/malta.dts b/arch/mips/boot/dts/mti/malta.dts
index b18c466..ffe3a15 100644
--- a/arch/mips/boot/dts/mti/malta.dts
+++ b/arch/mips/boot/dts/mti/malta.dts
@@ -1,5 +1,8 @@
/dts-v1/;
+#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/interrupt-controller/mips-gic.h>
+
/memreserve/ 0x00000000 0x00001000; /* YAMON exception vectors */
/memreserve/ 0x00001000 0x000ef000; /* YAMON */
/memreserve/ 0x000f0000 0x00010000; /* PIIX4 ISA memory */
@@ -8,4 +11,101 @@
#address-cells = <1>;
#size-cells = <1>;
compatible = "mti,malta";
+
+ cpu_intc: interrupt-controller {
+ compatible = "mti,cpu-interrupt-controller";
+
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ };
+
+ gic: interrupt-controller@1bdc0000 {
+ compatible = "mti,gic";
+ reg = <0x1bdc0000 0x20000>;
+
+ interrupt-controller;
+ #interrupt-cells = <3>;
+
+ /*
+ * Declare the interrupt-parent even though the mti,gic
+ * binding doesn't require it, such that the kernel can
+ * figure out that cpu_intc is the root interrupt
+ * controller & should be probed first.
+ */
+ interrupt-parent = <&cpu_intc>;
+
+ timer {
+ compatible = "mti,gic-timer";
+ interrupts = <GIC_LOCAL 1 IRQ_TYPE_NONE>;
+ };
+ };
+
+ i8259: interrupt-controller@20 {
+ compatible = "intel,i8259";
+
+ interrupt-controller;
+ #interrupt-cells = <1>;
+
+ interrupt-parent = <&gic>;
+ interrupts = <GIC_SHARED 3 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
+ flash@1e000000 {
+ compatible = "intel,dt28f160", "cfi-flash";
+ reg = <0x1e000000 0x400000>;
+ bank-width = <4>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ partitions {
+ compatible = "fixed-partitions";
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ yamon@0 {
+ label = "YAMON";
+ reg = <0x0 0x100000>;
+ read-only;
+ };
+
+ user-fs@100000 {
+ label = "User FS";
+ reg = <0x100000 0x2e0000>;
+ };
+
+ board-config@3e0000 {
+ label = "Board Config";
+ reg = <0x3e0000 0x20000>;
+ read-only;
+ };
+ };
+ };
+
+ fpga_regs: system-controller@1f000000 {
+ compatible = "mti,malta-fpga", "syscon", "simple-mfd";
+ reg = <0x1f000000 0x1000>;
+ native-endian;
+
+ reboot {
+ compatible = "syscon-reboot";
+ regmap = <&fpga_regs>;
+ offset = <0x500>;
+ mask = <0x42>;
+ };
+ };
+
+ isa {
+ compatible = "isa";
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <1 0 0 0x1000>;
+
+ rtc@70 {
+ compatible = "motorola,mc146818";
+ reg = <1 0x70 0x8>;
+
+ interrupt-parent = <&i8259>;
+ interrupts = <8>;
+ };
+ };
};
diff --git a/arch/mips/boot/dts/mti/sead3.dts b/arch/mips/boot/dts/mti/sead3.dts
index e4b317d..b112879 100644
--- a/arch/mips/boot/dts/mti/sead3.dts
+++ b/arch/mips/boot/dts/mti/sead3.dts
@@ -4,10 +4,23 @@
/memreserve/ 0x00001000 0x000ef000; // ROM data
/memreserve/ 0x000f0000 0x004cc000; // reserved
+#include <dt-bindings/interrupt-controller/mips-gic.h>
+
/ {
#address-cells = <1>;
#size-cells = <1>;
compatible = "mti,sead-3";
+ model = "MIPS SEAD-3";
+ interrupt-parent = <&gic>;
+
+ chosen {
+ stdout-path = "uart1:115200";
+ };
+
+ aliases {
+ uart0 = &uart0;
+ uart1 = &uart1;
+ };
cpus {
cpu@0 {
@@ -19,4 +32,229 @@
device_type = "memory";
reg = <0x0 0x08000000>;
};
+
+ cpu_intc: interrupt-controller {
+ compatible = "mti,cpu-interrupt-controller";
+
+ interrupt-controller;
+ #interrupt-cells = <1>;
+ };
+
+ gic: interrupt-controller@1b1c0000 {
+ compatible = "mti,gic";
+ reg = <0x1b1c0000 0x20000>;
+
+ interrupt-controller;
+ #interrupt-cells = <3>;
+
+ /*
+ * Declare the interrupt-parent even though the mti,gic
+ * binding doesn't require it, such that the kernel can
+ * figure out that cpu_intc is the root interrupt
+ * controller & should be probed first.
+ */
+ interrupt-parent = <&cpu_intc>;
+
+ timer {
+ compatible = "mti,gic-timer";
+ interrupts = <GIC_LOCAL 1 IRQ_TYPE_NONE>;
+ };
+ };
+
+ ehci@1b200000 {
+ compatible = "generic-ehci";
+ reg = <0x1b200000 0x1000>;
+
+ interrupts = <0>; /* GIC 0 or CPU 6 */
+
+ has-transaction-translator;
+ };
+
+ flash@1c000000 {
+ compatible = "intel,28f128j3", "cfi-flash";
+ reg = <0x1c000000 0x2000000>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ bank-width = <4>;
+
+ partitions {
+ compatible = "fixed-partitions";
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ user-fs@0 {
+ label = "User FS";
+ reg = <0x0 0x1fc0000>;
+ };
+
+ board-config@3e0000 {
+ label = "Board Config";
+ reg = <0x1fc0000 0x40000>;
+ };
+ };
+ };
+
+ fpga_regs: system-controller@1f000000 {
+ compatible = "mti,sead3-fpga", "syscon", "simple-mfd";
+ reg = <0x1f000000 0x200>;
+
+ reboot {
+ compatible = "syscon-reboot";
+ regmap = <&fpga_regs>;
+ offset = <0x50>;
+ mask = <0x4d>;
+ };
+
+ poweroff {
+ compatible = "restart-poweroff";
+ };
+ };
+
+ system-controller@1f000200 {
+ compatible = "mti,sead3-cpld", "syscon", "simple-mfd";
+ reg = <0x1f000200 0x300>;
+
+ led@10.0 {
+ compatible = "register-bit-led";
+ offset = <0x10>;
+ mask = <0x1>;
+ label = "pled0";
+ };
+ led@10.1 {
+ compatible = "register-bit-led";
+ offset = <0x10>;
+ mask = <0x2>;
+ label = "pled1";
+ };
+ led@10.2 {
+ compatible = "register-bit-led";
+ offset = <0x10>;
+ mask = <0x4>;
+ label = "pled2";
+ };
+ led@10.3 {
+ compatible = "register-bit-led";
+ offset = <0x10>;
+ mask = <0x8>;
+ label = "pled3";
+ };
+ led@10.4 {
+ compatible = "register-bit-led";
+ offset = <0x10>;
+ mask = <0x10>;
+ label = "pled4";
+ };
+ led@10.5 {
+ compatible = "register-bit-led";
+ offset = <0x10>;
+ mask = <0x20>;
+ label = "pled5";
+ };
+ led@10.6 {
+ compatible = "register-bit-led";
+ offset = <0x10>;
+ mask = <0x40>;
+ label = "pled6";
+ };
+ led@10.7 {
+ compatible = "register-bit-led";
+ offset = <0x10>;
+ mask = <0x80>;
+ label = "pled7";
+ };
+
+ led@18.0 {
+ compatible = "register-bit-led";
+ offset = <0x18>;
+ mask = <0x1>;
+ label = "fled0";
+ };
+ led@18.1 {
+ compatible = "register-bit-led";
+ offset = <0x18>;
+ mask = <0x2>;
+ label = "fled1";
+ };
+ led@18.2 {
+ compatible = "register-bit-led";
+ offset = <0x18>;
+ mask = <0x4>;
+ label = "fled2";
+ };
+ led@18.3 {
+ compatible = "register-bit-led";
+ offset = <0x18>;
+ mask = <0x8>;
+ label = "fled3";
+ };
+ led@18.4 {
+ compatible = "register-bit-led";
+ offset = <0x18>;
+ mask = <0x10>;
+ label = "fled4";
+ };
+ led@18.5 {
+ compatible = "register-bit-led";
+ offset = <0x18>;
+ mask = <0x20>;
+ label = "fled5";
+ };
+ led@18.6 {
+ compatible = "register-bit-led";
+ offset = <0x18>;
+ mask = <0x40>;
+ label = "fled6";
+ };
+ led@18.7 {
+ compatible = "register-bit-led";
+ offset = <0x18>;
+ mask = <0x80>;
+ label = "fled7";
+ };
+
+ lcd@200 {
+ compatible = "mti,sead3-lcd";
+ offset = <0x200>;
+ };
+ };
+
+ /* UART connected to FTDI & miniUSB socket */
+ uart0: uart@1f000900 {
+ compatible = "ns16550a";
+ reg = <0x1f000900 0x20>;
+ reg-io-width = <4>;
+ reg-shift = <2>;
+
+ clock-frequency = <14745600>;
+
+ interrupts = <3>; /* GIC 3 or CPU 4 */
+
+ no-loopback-test;
+ };
+
+ /* UART connected to RS232 socket */
+ uart1: uart@1f000800 {
+ compatible = "ns16550a";
+ reg = <0x1f000800 0x20>;
+ reg-io-width = <4>;
+ reg-shift = <2>;
+
+ clock-frequency = <14745600>;
+
+ interrupts = <2>; /* GIC 2 or CPU 4 */
+
+ no-loopback-test;
+ };
+
+ eth@1f010000 {
+ compatible = "smsc,lan9115";
+ reg = <0x1f010000 0x10000>;
+ reg-io-width = <4>;
+
+ interrupts = <0>; /* GIC 0 or CPU 6 */
+
+ phy-mode = "mii";
+ smsc,irq-push-pull;
+ smsc,save-mac-address;
+ };
};
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-board.c b/arch/mips/cavium-octeon/executive/cvmx-helper-board.c
index ff49fc0..ab8362e 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-board.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-board.c
@@ -36,8 +36,6 @@
#include <asm/octeon/cvmx-config.h>
-#include <asm/octeon/cvmx-mdio.h>
-
#include <asm/octeon/cvmx-helper.h>
#include <asm/octeon/cvmx-helper-util.h>
#include <asm/octeon/cvmx-helper-board.h>
@@ -46,17 +44,6 @@
#include <asm/octeon/cvmx-asxx-defs.h>
/**
- * cvmx_override_board_link_get(int ipd_port) is a function
- * pointer. It is meant to allow customization of the process of
- * talking to a PHY to determine link speed. It is called every
- * time a PHY must be polled for link status. Users should set
- * this pointer to a function before calling any cvmx-helper
- * operations.
- */
-cvmx_helper_link_info_t(*cvmx_override_board_link_get) (int ipd_port) =
- NULL;
-
-/**
* Return the MII PHY address associated with the given IPD
* port. A result of -1 means there isn't a MII capable PHY
* connected to this port. On chips supporting multiple MII
@@ -222,12 +209,6 @@ int cvmx_helper_board_get_mii_address(int ipd_port)
cvmx_helper_link_info_t __cvmx_helper_board_link_get(int ipd_port)
{
cvmx_helper_link_info_t result;
- int phy_addr;
- int is_broadcom_phy = 0;
-
- /* Give the user a chance to override the processing of this function */
- if (cvmx_override_board_link_get)
- return cvmx_override_board_link_get(ipd_port);
/* Unless we fix it later, all links are defaulted to down */
result.u64 = 0;
@@ -263,8 +244,7 @@ cvmx_helper_link_info_t __cvmx_helper_board_link_get(int ipd_port)
result.s.full_duplex = 1;
result.s.speed = 1000;
return result;
- } else /* The other port uses a broadcom PHY */
- is_broadcom_phy = 1;
+ }
break;
case CVMX_BOARD_TYPE_BBGW_REF:
/* Port 1 on these boards is always Gigabit */
@@ -282,108 +262,7 @@ cvmx_helper_link_info_t __cvmx_helper_board_link_get(int ipd_port)
break;
}
- phy_addr = cvmx_helper_board_get_mii_address(ipd_port);
- if (phy_addr != -1) {
- if (is_broadcom_phy) {
- /*
- * Below we are going to read SMI/MDIO
- * register 0x19 which works on Broadcom
- * parts
- */
- int phy_status =
- cvmx_mdio_read(phy_addr >> 8, phy_addr & 0xff,
- 0x19);
- switch ((phy_status >> 8) & 0x7) {
- case 0:
- result.u64 = 0;
- break;
- case 1:
- result.s.link_up = 1;
- result.s.full_duplex = 0;
- result.s.speed = 10;
- break;
- case 2:
- result.s.link_up = 1;
- result.s.full_duplex = 1;
- result.s.speed = 10;
- break;
- case 3:
- result.s.link_up = 1;
- result.s.full_duplex = 0;
- result.s.speed = 100;
- break;
- case 4:
- result.s.link_up = 1;
- result.s.full_duplex = 1;
- result.s.speed = 100;
- break;
- case 5:
- result.s.link_up = 1;
- result.s.full_duplex = 1;
- result.s.speed = 100;
- break;
- case 6:
- result.s.link_up = 1;
- result.s.full_duplex = 0;
- result.s.speed = 1000;
- break;
- case 7:
- result.s.link_up = 1;
- result.s.full_duplex = 1;
- result.s.speed = 1000;
- break;
- }
- } else {
- /*
- * This code assumes we are using a Marvell
- * Gigabit PHY. All the speed information can
- * be read from register 17 in one
- * go. Somebody using a different PHY will
- * need to handle it above in the board
- * specific area.
- */
- int phy_status =
- cvmx_mdio_read(phy_addr >> 8, phy_addr & 0xff, 17);
-
- /*
- * If the resolve bit 11 isn't set, see if
- * autoneg is turned off (bit 12, reg 0). The
- * resolve bit doesn't get set properly when
- * autoneg is off, so force it.
- */
- if ((phy_status & (1 << 11)) == 0) {
- int auto_status =
- cvmx_mdio_read(phy_addr >> 8,
- phy_addr & 0xff, 0);
- if ((auto_status & (1 << 12)) == 0)
- phy_status |= 1 << 11;
- }
-
- /*
- * Only return a link if the PHY has finished
- * auto negotiation and set the resolved bit
- * (bit 11)
- */
- if (phy_status & (1 << 11)) {
- result.s.link_up = 1;
- result.s.full_duplex = ((phy_status >> 13) & 1);
- switch ((phy_status >> 14) & 3) {
- case 0: /* 10 Mbps */
- result.s.speed = 10;
- break;
- case 1: /* 100 Mbps */
- result.s.speed = 100;
- break;
- case 2: /* 1 Gbps */
- result.s.speed = 1000;
- break;
- case 3: /* Illegal */
- result.u64 = 0;
- break;
- }
- }
- }
- } else if (OCTEON_IS_MODEL(OCTEON_CN3XXX)
+ if (OCTEON_IS_MODEL(OCTEON_CN3XXX)
|| OCTEON_IS_MODEL(OCTEON_CN58XX)
|| OCTEON_IS_MODEL(OCTEON_CN50XX)) {
/*
@@ -433,176 +312,6 @@ cvmx_helper_link_info_t __cvmx_helper_board_link_get(int ipd_port)
}
/**
- * This function as a board specific method of changing the PHY
- * speed, duplex, and auto-negotiation. This programs the PHY and
- * not Octeon. This can be used to force Octeon's links to
- * specific settings.
- *
- * @phy_addr: The address of the PHY to program
- * @enable_autoneg:
- * Non zero if you want to enable auto-negotiation.
- * @link_info: Link speed to program. If the speed is zero and auto-negotiation
- * is enabled, all possible negotiation speeds are advertised.
- *
- * Returns Zero on success, negative on failure
- */
-int cvmx_helper_board_link_set_phy(int phy_addr,
- cvmx_helper_board_set_phy_link_flags_types_t
- link_flags,
- cvmx_helper_link_info_t link_info)
-{
-
- /* Set the flow control settings based on link_flags */
- if ((link_flags & set_phy_link_flags_flow_control_mask) !=
- set_phy_link_flags_flow_control_dont_touch) {
- cvmx_mdio_phy_reg_autoneg_adver_t reg_autoneg_adver;
- reg_autoneg_adver.u16 =
- cvmx_mdio_read(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_AUTONEG_ADVER);
- reg_autoneg_adver.s.asymmetric_pause =
- (link_flags & set_phy_link_flags_flow_control_mask) ==
- set_phy_link_flags_flow_control_enable;
- reg_autoneg_adver.s.pause =
- (link_flags & set_phy_link_flags_flow_control_mask) ==
- set_phy_link_flags_flow_control_enable;
- cvmx_mdio_write(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_AUTONEG_ADVER,
- reg_autoneg_adver.u16);
- }
-
- /* If speed isn't set and autoneg is on advertise all supported modes */
- if ((link_flags & set_phy_link_flags_autoneg)
- && (link_info.s.speed == 0)) {
- cvmx_mdio_phy_reg_control_t reg_control;
- cvmx_mdio_phy_reg_status_t reg_status;
- cvmx_mdio_phy_reg_autoneg_adver_t reg_autoneg_adver;
- cvmx_mdio_phy_reg_extended_status_t reg_extended_status;
- cvmx_mdio_phy_reg_control_1000_t reg_control_1000;
-
- reg_status.u16 =
- cvmx_mdio_read(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_STATUS);
- reg_autoneg_adver.u16 =
- cvmx_mdio_read(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_AUTONEG_ADVER);
- reg_autoneg_adver.s.advert_100base_t4 =
- reg_status.s.capable_100base_t4;
- reg_autoneg_adver.s.advert_10base_tx_full =
- reg_status.s.capable_10_full;
- reg_autoneg_adver.s.advert_10base_tx_half =
- reg_status.s.capable_10_half;
- reg_autoneg_adver.s.advert_100base_tx_full =
- reg_status.s.capable_100base_x_full;
- reg_autoneg_adver.s.advert_100base_tx_half =
- reg_status.s.capable_100base_x_half;
- cvmx_mdio_write(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_AUTONEG_ADVER,
- reg_autoneg_adver.u16);
- if (reg_status.s.capable_extended_status) {
- reg_extended_status.u16 =
- cvmx_mdio_read(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_EXTENDED_STATUS);
- reg_control_1000.u16 =
- cvmx_mdio_read(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_CONTROL_1000);
- reg_control_1000.s.advert_1000base_t_full =
- reg_extended_status.s.capable_1000base_t_full;
- reg_control_1000.s.advert_1000base_t_half =
- reg_extended_status.s.capable_1000base_t_half;
- cvmx_mdio_write(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_CONTROL_1000,
- reg_control_1000.u16);
- }
- reg_control.u16 =
- cvmx_mdio_read(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_CONTROL);
- reg_control.s.autoneg_enable = 1;
- reg_control.s.restart_autoneg = 1;
- cvmx_mdio_write(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_CONTROL, reg_control.u16);
- } else if ((link_flags & set_phy_link_flags_autoneg)) {
- cvmx_mdio_phy_reg_control_t reg_control;
- cvmx_mdio_phy_reg_status_t reg_status;
- cvmx_mdio_phy_reg_autoneg_adver_t reg_autoneg_adver;
- cvmx_mdio_phy_reg_control_1000_t reg_control_1000;
-
- reg_status.u16 =
- cvmx_mdio_read(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_STATUS);
- reg_autoneg_adver.u16 =
- cvmx_mdio_read(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_AUTONEG_ADVER);
- reg_autoneg_adver.s.advert_100base_t4 = 0;
- reg_autoneg_adver.s.advert_10base_tx_full = 0;
- reg_autoneg_adver.s.advert_10base_tx_half = 0;
- reg_autoneg_adver.s.advert_100base_tx_full = 0;
- reg_autoneg_adver.s.advert_100base_tx_half = 0;
- if (reg_status.s.capable_extended_status) {
- reg_control_1000.u16 =
- cvmx_mdio_read(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_CONTROL_1000);
- reg_control_1000.s.advert_1000base_t_full = 0;
- reg_control_1000.s.advert_1000base_t_half = 0;
- }
- switch (link_info.s.speed) {
- case 10:
- reg_autoneg_adver.s.advert_10base_tx_full =
- link_info.s.full_duplex;
- reg_autoneg_adver.s.advert_10base_tx_half =
- !link_info.s.full_duplex;
- break;
- case 100:
- reg_autoneg_adver.s.advert_100base_tx_full =
- link_info.s.full_duplex;
- reg_autoneg_adver.s.advert_100base_tx_half =
- !link_info.s.full_duplex;
- break;
- case 1000:
- reg_control_1000.s.advert_1000base_t_full =
- link_info.s.full_duplex;
- reg_control_1000.s.advert_1000base_t_half =
- !link_info.s.full_duplex;
- break;
- }
- cvmx_mdio_write(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_AUTONEG_ADVER,
- reg_autoneg_adver.u16);
- if (reg_status.s.capable_extended_status)
- cvmx_mdio_write(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_CONTROL_1000,
- reg_control_1000.u16);
- reg_control.u16 =
- cvmx_mdio_read(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_CONTROL);
- reg_control.s.autoneg_enable = 1;
- reg_control.s.restart_autoneg = 1;
- cvmx_mdio_write(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_CONTROL, reg_control.u16);
- } else {
- cvmx_mdio_phy_reg_control_t reg_control;
- reg_control.u16 =
- cvmx_mdio_read(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_CONTROL);
- reg_control.s.autoneg_enable = 0;
- reg_control.s.restart_autoneg = 1;
- reg_control.s.duplex = link_info.s.full_duplex;
- if (link_info.s.speed == 1000) {
- reg_control.s.speed_msb = 1;
- reg_control.s.speed_lsb = 0;
- } else if (link_info.s.speed == 100) {
- reg_control.s.speed_msb = 0;
- reg_control.s.speed_lsb = 1;
- } else if (link_info.s.speed == 10) {
- reg_control.s.speed_msb = 0;
- reg_control.s.speed_lsb = 0;
- }
- cvmx_mdio_write(phy_addr >> 8, phy_addr & 0xff,
- CVMX_MDIO_PHY_REG_CONTROL, reg_control.u16);
- }
- return 0;
-}
-
-/**
* This function is called by cvmx_helper_interface_probe() after it
* determines the number of ports Octeon can support on a specific
* interface. This function is the per board location to override
@@ -676,48 +385,6 @@ int __cvmx_helper_board_hardware_enable(int interface)
0xc);
}
} else if (cvmx_sysinfo_get()->board_type ==
- CVMX_BOARD_TYPE_CN3010_EVB_HS5) {
- /*
- * Broadcom PHYs require differnet ASX
- * clocks. Unfortunately many boards don't define a
- * new board Id and simply mangle the
- * CN3010_EVB_HS5
- */
- if (interface == 0) {
- /*
- * Some boards use a hacked up bootloader that
- * identifies them as CN3010_EVB_HS5
- * evaluation boards. This leads to all kinds
- * of configuration problems. Detect one
- * case, and print warning, while trying to do
- * the right thing.
- */
- int phy_addr = cvmx_helper_board_get_mii_address(0);
- if (phy_addr != -1) {
- int phy_identifier =
- cvmx_mdio_read(phy_addr >> 8,
- phy_addr & 0xff, 0x2);
- /* Is it a Broadcom PHY? */
- if (phy_identifier == 0x0143) {
- cvmx_dprintf("\n");
- cvmx_dprintf("ERROR:\n");
- cvmx_dprintf
- ("ERROR: Board type is CVMX_BOARD_TYPE_CN3010_EVB_HS5, but Broadcom PHY found.\n");
- cvmx_dprintf
- ("ERROR: The board type is mis-configured, and software malfunctions are likely.\n");
- cvmx_dprintf
- ("ERROR: All boards require a unique board type to identify them.\n");
- cvmx_dprintf("ERROR:\n");
- cvmx_dprintf("\n");
- cvmx_wait(1000000000);
- cvmx_write_csr(CVMX_ASXX_RX_CLK_SETX
- (0, interface), 5);
- cvmx_write_csr(CVMX_ASXX_TX_CLK_SETX
- (0, interface), 5);
- }
- }
- }
- } else if (cvmx_sysinfo_get()->board_type ==
CVMX_BOARD_TYPE_UBNT_E100) {
cvmx_write_csr(CVMX_ASXX_RX_CLK_SETX(0, interface), 0);
cvmx_write_csr(CVMX_ASXX_TX_CLK_SETX(0, interface), 0x10);
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c b/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c
index f59c88e..671ab1d 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c
@@ -33,8 +33,6 @@
#include <asm/octeon/cvmx-config.h>
-
-#include <asm/octeon/cvmx-mdio.h>
#include <asm/octeon/cvmx-pko.h>
#include <asm/octeon/cvmx-helper.h>
#include <asm/octeon/cvmx-helper-board.h>
@@ -243,8 +241,7 @@ int __cvmx_helper_rgmii_enable(int interface)
/* enable the ports now */
for (port = 0; port < num_ports; port++) {
union cvmx_gmxx_prtx_cfg gmx_cfg;
- cvmx_helper_link_autoconf(cvmx_helper_get_ipd_port
- (interface, port));
+
gmx_cfg.u64 =
cvmx_read_csr(CVMX_GMXX_PRTX_CFG(port, interface));
gmx_cfg.s.en = 1;
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c b/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c
index 6f9609e..5437534 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c
@@ -34,7 +34,6 @@
#include <asm/octeon/cvmx-config.h>
-#include <asm/octeon/cvmx-mdio.h>
#include <asm/octeon/cvmx-helper.h>
#include <asm/octeon/cvmx-helper-board.h>
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c b/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c
index a56ee59..d347fe1 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c
@@ -234,8 +234,6 @@ int __cvmx_helper_xaui_enable(int interface)
cvmx_write_csr(CVMX_GMXX_TX_INT_EN(interface), gmx_tx_int_en.u64);
cvmx_write_csr(CVMX_PCSXX_INT_EN_REG(interface), pcsx_int_en_reg.u64);
- cvmx_helper_link_autoconf(cvmx_helper_get_ipd_port(interface, 0));
-
/* (8) Enable packet reception */
xauiMiscCtl.s.gmxeno = 0;
cvmx_write_csr(CVMX_PCSXX_MISC_CTL_REG(interface), xauiMiscCtl.u64);
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper.c b/arch/mips/cavium-octeon/executive/cvmx-helper.c
index ff26d02..6456af6 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper.c
@@ -841,7 +841,6 @@ int __cvmx_helper_errata_fix_ipd_ptr_alignment(void)
int retry_cnt;
int retry_loop_cnt;
int i;
- cvmx_helper_link_info_t link_info;
/* Save values for restore at end */
uint64_t prtx_cfg =
@@ -1002,15 +1001,6 @@ int __cvmx_helper_errata_fix_ipd_ptr_alignment(void)
(INDEX(FIX_IPD_OUTPORT), INTERFACE(FIX_IPD_OUTPORT)),
frame_max);
cvmx_write_csr(CVMX_ASXX_PRT_LOOP(INTERFACE(FIX_IPD_OUTPORT)), 0);
- /* Set link to down so autonegotiation will set it up again */
- link_info.u64 = 0;
- cvmx_helper_link_set(FIX_IPD_OUTPORT, link_info);
-
- /*
- * Bring the link back up as autonegotiation is not done in
- * user applications.
- */
- cvmx_helper_link_autoconf(FIX_IPD_OUTPORT);
CVMX_SYNC;
if (num_segs)
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 5537f95..9a2db1c 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -65,7 +65,8 @@ EXPORT_SYMBOL(octeon_should_swizzle_table);
extern void pci_console_init(const char *arg);
#endif
-static unsigned long long MAX_MEMORY = 512ull << 20;
+static unsigned long long max_memory = ULLONG_MAX;
+static unsigned long long reserve_low_mem;
DEFINE_SEMAPHORE(octeon_bootbus_sem);
EXPORT_SYMBOL(octeon_bootbus_sem);
@@ -75,7 +76,6 @@ struct octeon_boot_descriptor *octeon_boot_desc_ptr;
struct cvmx_bootinfo *octeon_bootinfo;
EXPORT_SYMBOL(octeon_bootinfo);
-static unsigned long long RESERVE_LOW_MEM = 0ull;
#ifdef CONFIG_KEXEC
#ifdef CONFIG_SMP
/*
@@ -125,18 +125,18 @@ static void kexec_bootmem_init(uint64_t mem_size, uint32_t low_reserved_bytes)
bootmem_desc->major_version = CVMX_BOOTMEM_DESC_MAJ_VER;
bootmem_desc->minor_version = CVMX_BOOTMEM_DESC_MIN_VER;
- addr = (OCTEON_DDR0_BASE + RESERVE_LOW_MEM + low_reserved_bytes);
+ addr = (OCTEON_DDR0_BASE + reserve_low_mem + low_reserved_bytes);
bootmem_desc->head_addr = 0;
if (mem_size <= OCTEON_DDR0_SIZE) {
__cvmx_bootmem_phy_free(addr,
- mem_size - RESERVE_LOW_MEM -
+ mem_size - reserve_low_mem -
low_reserved_bytes, 0);
return;
}
__cvmx_bootmem_phy_free(addr,
- OCTEON_DDR0_SIZE - RESERVE_LOW_MEM -
+ OCTEON_DDR0_SIZE - reserve_low_mem -
low_reserved_bytes, 0);
mem_size -= OCTEON_DDR0_SIZE;
@@ -857,15 +857,15 @@ void __init prom_init(void)
/* Default to 64MB in the simulator to speed things up */
if (octeon_is_simulation())
- MAX_MEMORY = 64ull << 20;
+ max_memory = 64ull << 20;
arg = strstr(arcs_cmdline, "mem=");
if (arg) {
- MAX_MEMORY = memparse(arg + 4, &p);
- if (MAX_MEMORY == 0)
- MAX_MEMORY = 32ull << 30;
+ max_memory = memparse(arg + 4, &p);
+ if (max_memory == 0)
+ max_memory = 32ull << 30;
if (*p == '@')
- RESERVE_LOW_MEM = memparse(p + 1, &p);
+ reserve_low_mem = memparse(p + 1, &p);
}
arcs_cmdline[0] = 0;
@@ -875,11 +875,11 @@ void __init prom_init(void)
cvmx_phys_to_ptr(octeon_boot_desc_ptr->argv[i]);
if ((strncmp(arg, "MEM=", 4) == 0) ||
(strncmp(arg, "mem=", 4) == 0)) {
- MAX_MEMORY = memparse(arg + 4, &p);
- if (MAX_MEMORY == 0)
- MAX_MEMORY = 32ull << 30;
+ max_memory = memparse(arg + 4, &p);
+ if (max_memory == 0)
+ max_memory = 32ull << 30;
if (*p == '@')
- RESERVE_LOW_MEM = memparse(p + 1, &p);
+ reserve_low_mem = memparse(p + 1, &p);
#ifdef CONFIG_KEXEC
} else if (strncmp(arg, "crashkernel=", 12) == 0) {
crashk_size = memparse(arg+12, &p);
@@ -971,13 +971,13 @@ void __init plat_mem_setup(void)
* to consistently work.
*/
mem_alloc_size = 4 << 20;
- if (mem_alloc_size > MAX_MEMORY)
- mem_alloc_size = MAX_MEMORY;
+ if (mem_alloc_size > max_memory)
+ mem_alloc_size = max_memory;
/* Crashkernel ignores bootmem list. It relies on mem=X@Y option */
#ifdef CONFIG_CRASH_DUMP
- add_memory_region(RESERVE_LOW_MEM, MAX_MEMORY, BOOT_MEM_RAM);
- total += MAX_MEMORY;
+ add_memory_region(reserve_low_mem, max_memory, BOOT_MEM_RAM);
+ total += max_memory;
#else
#ifdef CONFIG_KEXEC
if (crashk_size > 0) {
@@ -992,7 +992,7 @@ void __init plat_mem_setup(void)
*/
cvmx_bootmem_lock();
while ((boot_mem_map.nr_map < BOOT_MEM_MAP_MAX)
- && (total < MAX_MEMORY)) {
+ && (total < max_memory)) {
memory = cvmx_bootmem_phy_alloc(mem_alloc_size,
__pa_symbol(&_end), -1,
0x100000,
diff --git a/arch/mips/configs/generic/32r1.config b/arch/mips/configs/generic/32r1.config
new file mode 100644
index 0000000..a11cd87
--- /dev/null
+++ b/arch/mips/configs/generic/32r1.config
@@ -0,0 +1,2 @@
+CONFIG_CPU_MIPS32_R1=y
+CONFIG_HIGHMEM=y
diff --git a/arch/mips/configs/generic/32r2.config b/arch/mips/configs/generic/32r2.config
new file mode 100644
index 0000000..9570672
--- /dev/null
+++ b/arch/mips/configs/generic/32r2.config
@@ -0,0 +1,3 @@
+CONFIG_CPU_MIPS32_R2=y
+CONFIG_MIPS_O32_FP64_SUPPORT=y
+CONFIG_HIGHMEM=y
diff --git a/arch/mips/configs/generic/32r6.config b/arch/mips/configs/generic/32r6.config
new file mode 100644
index 0000000..ca606e7
--- /dev/null
+++ b/arch/mips/configs/generic/32r6.config
@@ -0,0 +1,2 @@
+CONFIG_CPU_MIPS32_R6=y
+CONFIG_HIGHMEM=y
diff --git a/arch/mips/configs/generic/64r1.config b/arch/mips/configs/generic/64r1.config
new file mode 100644
index 0000000..7c1ea7e
--- /dev/null
+++ b/arch/mips/configs/generic/64r1.config
@@ -0,0 +1,4 @@
+CONFIG_CPU_MIPS64_R1=y
+CONFIG_64BIT=y
+CONFIG_MIPS32_O32=y
+CONFIG_MIPS32_N32=y
diff --git a/arch/mips/configs/generic/64r2.config b/arch/mips/configs/generic/64r2.config
new file mode 100644
index 0000000..b4d31ae
--- /dev/null
+++ b/arch/mips/configs/generic/64r2.config
@@ -0,0 +1,5 @@
+CONFIG_CPU_MIPS64_R2=y
+CONFIG_MIPS_O32_FP64_SUPPORT=y
+CONFIG_64BIT=y
+CONFIG_MIPS32_O32=y
+CONFIG_MIPS32_N32=y
diff --git a/arch/mips/configs/generic/64r6.config b/arch/mips/configs/generic/64r6.config
new file mode 100644
index 0000000..7cac033
--- /dev/null
+++ b/arch/mips/configs/generic/64r6.config
@@ -0,0 +1,4 @@
+CONFIG_CPU_MIPS64_R6=y
+CONFIG_64BIT=y
+CONFIG_MIPS32_O32=y
+CONFIG_MIPS32_N32=y
diff --git a/arch/mips/configs/generic/board-sead-3.config b/arch/mips/configs/generic/board-sead-3.config
new file mode 100644
index 0000000..3b5e1ac
--- /dev/null
+++ b/arch/mips/configs/generic/board-sead-3.config
@@ -0,0 +1,32 @@
+CONFIG_LEGACY_BOARD_SEAD3=y
+
+CONFIG_AUXDISPLAY=y
+CONFIG_IMG_ASCII_LCD=y
+
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_SYSCON=y
+
+CONFIG_MMC=y
+CONFIG_MMC_SPI=y
+
+CONFIG_MTD=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_INTELEXT=y
+CONFIG_MTD_OF_PARTS=y
+CONFIG_MTD_PHYSMAP=y
+CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_UBI=y
+CONFIG_MTD_UBI_GLUEBI=y
+
+CONFIG_NETDEVICES=y
+CONFIG_SMSC911X=y
+CONFIG_SMSC_PHY=y
+
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+
+CONFIG_USB=y
+CONFIG_USB_EHCI_HCD=y
diff --git a/arch/mips/configs/generic/eb.config b/arch/mips/configs/generic/eb.config
new file mode 100644
index 0000000..c5cdc99
--- /dev/null
+++ b/arch/mips/configs/generic/eb.config
@@ -0,0 +1 @@
+CONFIG_CPU_BIG_ENDIAN=y
diff --git a/arch/mips/configs/generic/el.config b/arch/mips/configs/generic/el.config
new file mode 100644
index 0000000..ee43fdb
--- /dev/null
+++ b/arch/mips/configs/generic/el.config
@@ -0,0 +1 @@
+CONFIG_CPU_LITTLE_ENDIAN=y
diff --git a/arch/mips/configs/generic/micro32r2.config b/arch/mips/configs/generic/micro32r2.config
new file mode 100644
index 0000000..b701fe7a
--- /dev/null
+++ b/arch/mips/configs/generic/micro32r2.config
@@ -0,0 +1,4 @@
+CONFIG_CPU_MIPS32_R2=y
+CONFIG_CPU_MICROMIPS=y
+CONFIG_MIPS_O32_FP64_SUPPORT=y
+CONFIG_HIGHMEM=y
diff --git a/arch/mips/configs/generic_defconfig b/arch/mips/configs/generic_defconfig
new file mode 100644
index 0000000..c95d94c
--- /dev/null
+++ b/arch/mips/configs/generic_defconfig
@@ -0,0 +1,96 @@
+CONFIG_MIPS_GENERIC=y
+CONFIG_CPU_LITTLE_ENDIAN=y
+CONFIG_MIPS_CPS=y
+CONFIG_CPU_HAS_MSA=y
+CONFIG_HIGHMEM=y
+CONFIG_NR_CPUS=2
+CONFIG_MIPS_O32_FP64_SUPPORT=y
+CONFIG_SYSVIPC=y
+CONFIG_NO_HZ_IDLE=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_MEMCG=y
+CONFIG_MEMCG_SWAP=y
+CONFIG_BLK_CGROUP=y
+CONFIG_CFS_BANDWIDTH=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CPUSETS=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
+CONFIG_SCHED_AUTOGROUP=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_USERFAULTFD=y
+CONFIG_EMBEDDED=y
+# CONFIG_SLUB_DEBUG is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_CC_STACKPROTECTOR_REGULAR=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_TRIM_UNUSED_KSYMS=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_NETFILTER=y
+# CONFIG_WIRELESS is not set
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_SCSI=y
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO is not set
+CONFIG_HW_RANDOM=y
+# CONFIG_HWMON is not set
+CONFIG_MFD_SYSCON=y
+CONFIG_HID_A4TECH=y
+CONFIG_HID_APPLE=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_EZKEY=y
+CONFIG_HID_KENSINGTON=y
+CONFIG_HID_LOGITECH=y
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_MIPS_PLATFORM_DEVICES is not set
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_EXT4_ENCRYPTION=y
+CONFIG_FANOTIFY=y
+CONFIG_FUSE_FS=y
+CONFIG_CUSE=y
+CONFIG_OVERLAY_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_NFS_V4_2=y
+CONFIG_PRINTK_TIME=y
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_REDUCED=y
+CONFIG_DEBUG_FS=y
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_FTRACE is not set
+CONFIG_CMDLINE_BOOL=y
+CONFIG_CMDLINE="earlycon"
+# CONFIG_XZ_DEC_X86 is not set
+# CONFIG_XZ_DEC_POWERPC is not set
+# CONFIG_XZ_DEC_IA64 is not set
+# CONFIG_XZ_DEC_ARM is not set
+# CONFIG_XZ_DEC_ARMTHUMB is not set
+# CONFIG_XZ_DEC_SPARC is not set
diff --git a/arch/mips/configs/loongson1c_defconfig b/arch/mips/configs/loongson1c_defconfig
new file mode 100644
index 0000000..2304d41
--- /dev/null
+++ b/arch/mips/configs/loongson1c_defconfig
@@ -0,0 +1,126 @@
+CONFIG_MACH_LOONGSON32=y
+CONFIG_LOONGSON1_LS1C=y
+CONFIG_PREEMPT=y
+# CONFIG_SECCOMP is not set
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_KERNEL_XZ=y
+CONFIG_SYSVIPC=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_BSD_PROCESS_ACCT_V3=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=16
+CONFIG_NAMESPACES=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_EXPERT=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+# CONFIG_LBDAF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_SUSPEND is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_SYN_COOKIES=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_DIAG is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_STANDALONE is not set
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_LOONGSON1=y
+CONFIG_MTD_UBI=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_SCSI=m
+# CONFIG_SCSI_PROC_FS is not set
+CONFIG_BLK_DEV_SD=m
+# CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SMSC is not set
+CONFIG_STMMAC_ETH=y
+# CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_WLAN is not set
+CONFIG_INPUT_EVDEV=y
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO is not set
+CONFIG_VT_HW_CONSOLE_BINDING=y
+CONFIG_LEGACY_PTY_COUNT=8
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+# CONFIG_HW_RANDOM is not set
+CONFIG_GPIOLIB=y
+CONFIG_GPIO_LOONGSON1=y
+# CONFIG_HWMON is not set
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_HID_GENERIC=m
+CONFIG_USB_HID=m
+CONFIG_USB=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_TT_NEWSCHED is not set
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=m
+CONFIG_USB_SERIAL=m
+CONFIG_USB_SERIAL_PL2303=m
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_LOONGSON1=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_EXT2_FS_POSIX_ACL=y
+CONFIG_EXT2_FS_SECURITY=y
+CONFIG_EXT3_FS=y
+CONFIG_EXT3_FS_POSIX_ACL=y
+CONFIG_EXT3_FS_SECURITY=y
+# CONFIG_DNOTIFY is not set
+CONFIG_VFAT_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_UBIFS_FS=y
+CONFIG_UBIFS_FS_ADVANCED_COMPR=y
+CONFIG_UBIFS_ATIME_SUPPORT=y
+CONFIG_NFS_FS=y
+CONFIG_ROOT_NFS=y
+CONFIG_NLS_CODEPAGE_437=m
+CONFIG_NLS_ISO8859_1=m
+CONFIG_DYNAMIC_DEBUG=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_DEBUG_FS=y
+CONFIG_MAGIC_SYSRQ=y
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_DEBUG_PREEMPT is not set
+# CONFIG_FTRACE is not set
+# CONFIG_EARLY_PRINTK is not set
+# CONFIG_CRYPTO_ECHAINIV is not set
+# CONFIG_CRYPTO_HW is not set
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index 5afb484..58d43f3 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -230,7 +230,7 @@
CONFIG_MTD_CFI_INTELEXT=y
CONFIG_MTD_CFI_AMDSTD=y
CONFIG_MTD_CFI_STAA=y
-CONFIG_MTD_PHYSMAP=y
+CONFIG_MTD_PHYSMAP_OF=y
CONFIG_MTD_UBI=m
CONFIG_MTD_UBI_GLUEBI=m
CONFIG_BLK_DEV_FD=m
@@ -318,6 +318,8 @@
# CONFIG_SERIO_I8042 is not set
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_FB=y
CONFIG_FB_CIRRUS=y
diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig
index 98f1387..c8f7e28 100644
--- a/arch/mips/configs/malta_kvm_defconfig
+++ b/arch/mips/configs/malta_kvm_defconfig
@@ -235,7 +235,7 @@
CONFIG_MTD_CFI_INTELEXT=y
CONFIG_MTD_CFI_AMDSTD=y
CONFIG_MTD_CFI_STAA=y
-CONFIG_MTD_PHYSMAP=y
+CONFIG_MTD_PHYSMAP_OF=y
CONFIG_MTD_UBI=m
CONFIG_MTD_UBI_GLUEBI=m
CONFIG_BLK_DEV_FD=m
@@ -331,6 +331,8 @@
# CONFIG_SERIO_I8042 is not set
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_FB=y
CONFIG_FB_CIRRUS=y
diff --git a/arch/mips/configs/malta_kvm_guest_defconfig b/arch/mips/configs/malta_kvm_guest_defconfig
index 3b5d591..d2f54e5 100644
--- a/arch/mips/configs/malta_kvm_guest_defconfig
+++ b/arch/mips/configs/malta_kvm_guest_defconfig
@@ -234,7 +234,7 @@
CONFIG_MTD_CFI_INTELEXT=y
CONFIG_MTD_CFI_AMDSTD=y
CONFIG_MTD_CFI_STAA=y
-CONFIG_MTD_PHYSMAP=y
+CONFIG_MTD_PHYSMAP_OF=y
CONFIG_MTD_UBI=m
CONFIG_MTD_UBI_GLUEBI=m
CONFIG_BLK_DEV_FD=m
@@ -331,6 +331,8 @@
# CONFIG_SERIO_I8042 is not set
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_FB=y
CONFIG_FB_CIRRUS=y
diff --git a/arch/mips/configs/malta_qemu_32r6_defconfig b/arch/mips/configs/malta_qemu_32r6_defconfig
index 65f140e..cbf37dd 100644
--- a/arch/mips/configs/malta_qemu_32r6_defconfig
+++ b/arch/mips/configs/malta_qemu_32r6_defconfig
@@ -132,6 +132,8 @@
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_HW_RANDOM=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_FB=y
CONFIG_FIRMWARE_EDID=y
diff --git a/arch/mips/configs/maltaaprp_defconfig b/arch/mips/configs/maltaaprp_defconfig
index 799c433..35f6ba2 100644
--- a/arch/mips/configs/maltaaprp_defconfig
+++ b/arch/mips/configs/maltaaprp_defconfig
@@ -132,6 +132,8 @@
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_HW_RANDOM=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_VIDEO_OUTPUT_CONTROL=m
CONFIG_FB=y
diff --git a/arch/mips/configs/maltasmvp_defconfig b/arch/mips/configs/maltasmvp_defconfig
index ac0eb4d..900f145 100644
--- a/arch/mips/configs/maltasmvp_defconfig
+++ b/arch/mips/configs/maltasmvp_defconfig
@@ -134,6 +134,8 @@
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_HW_RANDOM=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_FB=y
CONFIG_FIRMWARE_EDID=y
diff --git a/arch/mips/configs/maltasmvp_eva_defconfig b/arch/mips/configs/maltasmvp_eva_defconfig
index 3184600..8e2738b 100644
--- a/arch/mips/configs/maltasmvp_eva_defconfig
+++ b/arch/mips/configs/maltasmvp_eva_defconfig
@@ -137,6 +137,8 @@
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_HW_RANDOM=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_VIDEO_OUTPUT_CONTROL=m
CONFIG_FB=y
diff --git a/arch/mips/configs/maltaup_defconfig b/arch/mips/configs/maltaup_defconfig
index a79107d..6dc4e30 100644
--- a/arch/mips/configs/maltaup_defconfig
+++ b/arch/mips/configs/maltaup_defconfig
@@ -131,6 +131,8 @@
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_HW_RANDOM=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_VIDEO_OUTPUT_CONTROL=m
CONFIG_FB=y
diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig
index 7322157..3d0d9cb 100644
--- a/arch/mips/configs/maltaup_xpa_defconfig
+++ b/arch/mips/configs/maltaup_xpa_defconfig
@@ -231,7 +231,7 @@
CONFIG_MTD_CFI_INTELEXT=y
CONFIG_MTD_CFI_AMDSTD=y
CONFIG_MTD_CFI_STAA=y
-CONFIG_MTD_PHYSMAP=y
+CONFIG_MTD_PHYSMAP_OF=y
CONFIG_MTD_UBI=m
CONFIG_MTD_UBI_GLUEBI=m
CONFIG_BLK_DEV_FD=m
@@ -326,6 +326,8 @@
# CONFIG_SERIO_I8042 is not set
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_SYSCON=y
# CONFIG_HWMON is not set
CONFIG_FB=y
CONFIG_FB_CIRRUS=y
diff --git a/arch/mips/configs/pistachio_defconfig b/arch/mips/configs/pistachio_defconfig
index 8b74291..7d32fbb 100644
--- a/arch/mips/configs/pistachio_defconfig
+++ b/arch/mips/configs/pistachio_defconfig
@@ -29,7 +29,6 @@
CONFIG_EMBEDDED=y
# CONFIG_COMPAT_BRK is not set
CONFIG_PROFILING=y
-CONFIG_CC_STACKPROTECTOR_STRONG=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
CONFIG_MODULE_FORCE_UNLOAD=y
@@ -264,7 +263,6 @@
CONFIG_IMG_MDC_DMA=y
CONFIG_STAGING=y
CONFIG_ASHMEM=y
-# CONFIG_ANDROID_TIMED_OUTPUT is not set
# CONFIG_IOMMU_SUPPORT is not set
CONFIG_MEMORY=y
CONFIG_IIO=y
diff --git a/arch/mips/configs/sead3_defconfig b/arch/mips/configs/sead3_defconfig
deleted file mode 100644
index dae9354..0000000
--- a/arch/mips/configs/sead3_defconfig
+++ /dev/null
@@ -1,121 +0,0 @@
-CONFIG_MIPS_SEAD3=y
-CONFIG_CPU_LITTLE_ENDIAN=y
-CONFIG_CPU_MIPS32_R2=y
-CONFIG_HZ_100=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=15
-CONFIG_EMBEDDED=y
-CONFIG_SLAB=y
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=y
-CONFIG_MODULES=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_INET_DIAG is not set
-# CONFIG_IPV6 is not set
-# CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_DEVTMPFS=y
-CONFIG_MTD=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_INTELEXT=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_UBI=y
-CONFIG_MTD_UBI_GLUEBI=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=m
-CONFIG_SCSI=y
-# CONFIG_SCSI_PROC_FS is not set
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_SG=y
-# CONFIG_SCSI_LOWLEVEL is not set
-CONFIG_NETDEVICES=y
-CONFIG_SMSC911X=y
-# CONFIG_NET_VENDOR_WIZNET is not set
-CONFIG_MARVELL_PHY=y
-CONFIG_DAVICOM_PHY=y
-CONFIG_QSEMI_PHY=y
-CONFIG_LXT_PHY=y
-CONFIG_CICADA_PHY=y
-CONFIG_VITESSE_PHY=y
-CONFIG_SMSC_PHY=y
-CONFIG_BROADCOM_PHY=y
-CONFIG_ICPLUS_PHY=y
-# CONFIG_WLAN is not set
-# CONFIG_INPUT_MOUSEDEV is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-# CONFIG_CONSOLE_TRANSLATIONS is not set
-CONFIG_VT_HW_CONSOLE_BINDING=y
-CONFIG_LEGACY_PTY_COUNT=32
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_NR_UARTS=2
-CONFIG_SERIAL_8250_RUNTIME_UARTS=2
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-# CONFIG_I2C_COMPAT is not set
-CONFIG_I2C_CHARDEV=y
-# CONFIG_I2C_HELPER_AUTO is not set
-CONFIG_SPI=y
-CONFIG_SENSORS_ADT7475=y
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
-CONFIG_LCD_CLASS_DEVICE=y
-CONFIG_BACKLIGHT_CLASS_DEVICE=y
-# CONFIG_VGA_CONSOLE is not set
-CONFIG_USB=y
-CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
-CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_ROOT_HUB_TT=y
-CONFIG_USB_STORAGE=y
-CONFIG_MMC=y
-CONFIG_MMC_DEBUG=y
-CONFIG_MMC_SPI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_M41T80=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_XFS_FS=y
-CONFIG_XFS_QUOTA=y
-CONFIG_XFS_POSIX_ACL=y
-CONFIG_QUOTA=y
-# CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_TMPFS=y
-CONFIG_JFFS2_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_ASCII=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_ISO8859_15=y
-CONFIG_NLS_UTF8=y
-# CONFIG_FTRACE is not set
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_ARC4=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-# CONFIG_CRYPTO_HW is not set
diff --git a/arch/mips/configs/sead3micro_defconfig b/arch/mips/configs/sead3micro_defconfig
deleted file mode 100644
index cd91a77..0000000
--- a/arch/mips/configs/sead3micro_defconfig
+++ /dev/null
@@ -1,122 +0,0 @@
-CONFIG_MIPS_SEAD3=y
-CONFIG_CPU_LITTLE_ENDIAN=y
-CONFIG_CPU_MIPS32_R2=y
-CONFIG_CPU_MICROMIPS=y
-CONFIG_HZ_100=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=15
-CONFIG_EMBEDDED=y
-CONFIG_SLAB=y
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=y
-CONFIG_MODULES=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_INET_DIAG is not set
-# CONFIG_IPV6 is not set
-# CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_DEVTMPFS=y
-CONFIG_MTD=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_INTELEXT=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_UBI=y
-CONFIG_MTD_UBI_GLUEBI=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=m
-CONFIG_SCSI=y
-# CONFIG_SCSI_PROC_FS is not set
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_SG=y
-# CONFIG_SCSI_LOWLEVEL is not set
-CONFIG_NETDEVICES=y
-CONFIG_SMSC911X=y
-# CONFIG_NET_VENDOR_WIZNET is not set
-CONFIG_MARVELL_PHY=y
-CONFIG_DAVICOM_PHY=y
-CONFIG_QSEMI_PHY=y
-CONFIG_LXT_PHY=y
-CONFIG_CICADA_PHY=y
-CONFIG_VITESSE_PHY=y
-CONFIG_SMSC_PHY=y
-CONFIG_BROADCOM_PHY=y
-CONFIG_ICPLUS_PHY=y
-# CONFIG_WLAN is not set
-# CONFIG_INPUT_MOUSEDEV is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-# CONFIG_CONSOLE_TRANSLATIONS is not set
-CONFIG_VT_HW_CONSOLE_BINDING=y
-CONFIG_LEGACY_PTY_COUNT=32
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_NR_UARTS=2
-CONFIG_SERIAL_8250_RUNTIME_UARTS=2
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-# CONFIG_I2C_COMPAT is not set
-CONFIG_I2C_CHARDEV=y
-# CONFIG_I2C_HELPER_AUTO is not set
-CONFIG_SPI=y
-CONFIG_SENSORS_ADT7475=y
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
-CONFIG_LCD_CLASS_DEVICE=y
-CONFIG_BACKLIGHT_CLASS_DEVICE=y
-# CONFIG_VGA_CONSOLE is not set
-CONFIG_USB=y
-CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
-CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_ROOT_HUB_TT=y
-CONFIG_USB_STORAGE=y
-CONFIG_MMC=y
-CONFIG_MMC_DEBUG=y
-CONFIG_MMC_SPI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_M41T80=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_XFS_FS=y
-CONFIG_XFS_QUOTA=y
-CONFIG_XFS_POSIX_ACL=y
-CONFIG_QUOTA=y
-# CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_TMPFS=y
-CONFIG_JFFS2_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_ASCII=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_ISO8859_15=y
-CONFIG_NLS_UTF8=y
-# CONFIG_FTRACE is not set
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_ARC4=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-# CONFIG_CRYPTO_HW is not set
diff --git a/arch/mips/generic/Kconfig b/arch/mips/generic/Kconfig
new file mode 100644
index 0000000..a606b3f
--- /dev/null
+++ b/arch/mips/generic/Kconfig
@@ -0,0 +1,19 @@
+if MIPS_GENERIC
+
+config LEGACY_BOARDS
+ bool
+ help
+ Select this from your board if the board must use a legacy, non-UHI,
+ boot protocol. This will cause the kernel to scan through the list of
+ supported machines calling their detect functions in turn if the
+ kernel is booted without being provided with an FDT via the UHI
+ boot protocol.
+
+config LEGACY_BOARD_SEAD3
+ bool "Support MIPS SEAD-3 boards"
+ select LEGACY_BOARDS
+ help
+ Enable this to include support for booting on MIPS SEAD-3 FPGA-based
+ development boards, which boot using a legacy boot protocol.
+
+endif
diff --git a/arch/mips/generic/Makefile b/arch/mips/generic/Makefile
new file mode 100644
index 0000000..7c66494
--- /dev/null
+++ b/arch/mips/generic/Makefile
@@ -0,0 +1,15 @@
+#
+# Copyright (C) 2016 Imagination Technologies
+# Author: Paul Burton <paul.burton@imgtec.com>
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms of the GNU General Public License as published by the
+# Free Software Foundation; either version 2 of the License, or (at your
+# option) any later version.
+#
+
+obj-y += init.o
+obj-y += irq.o
+obj-y += proc.o
+
+obj-$(CONFIG_LEGACY_BOARD_SEAD3) += board-sead3.o
diff --git a/arch/mips/generic/Platform b/arch/mips/generic/Platform
new file mode 100644
index 0000000..9a30d69
--- /dev/null
+++ b/arch/mips/generic/Platform
@@ -0,0 +1,14 @@
+#
+# Copyright (C) 2016 Imagination Technologies
+# Author: Paul Burton <paul.burton@imgtec.com>
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms of the GNU General Public License as published by the
+# Free Software Foundation; either version 2 of the License, or (at your
+# option) any later version.
+#
+
+platform-$(CONFIG_MIPS_GENERIC) += generic/
+cflags-$(CONFIG_MIPS_GENERIC) += -I$(srctree)/arch/mips/include/asm/mach-generic
+load-$(CONFIG_MIPS_GENERIC) += 0xffffffff80100000
+all-$(CONFIG_MIPS_GENERIC) := vmlinux.gz.itb
diff --git a/arch/mips/generic/board-sead3.c b/arch/mips/generic/board-sead3.c
new file mode 100644
index 0000000..f4ae058
--- /dev/null
+++ b/arch/mips/generic/board-sead3.c
@@ -0,0 +1,376 @@
+/*
+ * Copyright (C) 2016 Imagination Technologies
+ * Author: Paul Burton <paul.burton@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#define pr_fmt(fmt) "sead3: " fmt
+
+#include <linux/errno.h>
+#include <linux/libfdt.h>
+#include <linux/printk.h>
+
+#include <asm/fw/fw.h>
+#include <asm/io.h>
+#include <asm/machine.h>
+
+#define SEAD_CONFIG CKSEG1ADDR(0x1b100110)
+#define SEAD_CONFIG_GIC_PRESENT BIT(1)
+
+#define MIPS_REVISION CKSEG1ADDR(0x1fc00010)
+#define MIPS_REVISION_MACHINE (0xf << 4)
+#define MIPS_REVISION_MACHINE_SEAD3 (0x4 << 4)
+
+static __init bool sead3_detect(void)
+{
+ uint32_t rev;
+
+ rev = __raw_readl((void *)MIPS_REVISION);
+ return (rev & MIPS_REVISION_MACHINE) == MIPS_REVISION_MACHINE_SEAD3;
+}
+
+static __init int append_cmdline(void *fdt)
+{
+ int err, chosen_off;
+
+ /* find or add chosen node */
+ chosen_off = fdt_path_offset(fdt, "/chosen");
+ if (chosen_off == -FDT_ERR_NOTFOUND)
+ chosen_off = fdt_path_offset(fdt, "/chosen@0");
+ if (chosen_off == -FDT_ERR_NOTFOUND)
+ chosen_off = fdt_add_subnode(fdt, 0, "chosen");
+ if (chosen_off < 0) {
+ pr_err("Unable to find or add DT chosen node: %d\n",
+ chosen_off);
+ return chosen_off;
+ }
+
+ err = fdt_setprop_string(fdt, chosen_off, "bootargs", fw_getcmdline());
+ if (err) {
+ pr_err("Unable to set bootargs property: %d\n", err);
+ return err;
+ }
+
+ return 0;
+}
+
+static __init int append_memory(void *fdt)
+{
+ unsigned long phys_memsize, memsize;
+ __be32 mem_array[2];
+ int err, mem_off;
+ char *var;
+
+ /* find memory size from the bootloader environment */
+ var = fw_getenv("memsize");
+ if (var) {
+ err = kstrtoul(var, 0, &phys_memsize);
+ if (err) {
+ pr_err("Failed to read memsize env variable '%s'\n",
+ var);
+ return -EINVAL;
+ }
+ } else {
+ pr_warn("The bootloader didn't provide memsize: defaulting to 32MB\n");
+ phys_memsize = 32 << 20;
+ }
+
+ /* default to using all available RAM */
+ memsize = phys_memsize;
+
+ /* allow the user to override the usable memory */
+ var = strstr(arcs_cmdline, "memsize=");
+ if (var)
+ memsize = memparse(var + strlen("memsize="), NULL);
+
+ /* if the user says there's more RAM than we thought, believe them */
+ phys_memsize = max_t(unsigned long, phys_memsize, memsize);
+
+ /* find or add a memory node */
+ mem_off = fdt_path_offset(fdt, "/memory");
+ if (mem_off == -FDT_ERR_NOTFOUND)
+ mem_off = fdt_add_subnode(fdt, 0, "memory");
+ if (mem_off < 0) {
+ pr_err("Unable to find or add memory DT node: %d\n", mem_off);
+ return mem_off;
+ }
+
+ err = fdt_setprop_string(fdt, mem_off, "device_type", "memory");
+ if (err) {
+ pr_err("Unable to set memory node device_type: %d\n", err);
+ return err;
+ }
+
+ mem_array[0] = 0;
+ mem_array[1] = cpu_to_be32(phys_memsize);
+ err = fdt_setprop(fdt, mem_off, "reg", mem_array, sizeof(mem_array));
+ if (err) {
+ pr_err("Unable to set memory regs property: %d\n", err);
+ return err;
+ }
+
+ mem_array[0] = 0;
+ mem_array[1] = cpu_to_be32(memsize);
+ err = fdt_setprop(fdt, mem_off, "linux,usable-memory",
+ mem_array, sizeof(mem_array));
+ if (err) {
+ pr_err("Unable to set linux,usable-memory property: %d\n", err);
+ return err;
+ }
+
+ return 0;
+}
+
+static __init int remove_gic(void *fdt)
+{
+ const unsigned int cpu_ehci_int = 2;
+ const unsigned int cpu_uart_int = 4;
+ const unsigned int cpu_eth_int = 6;
+ int gic_off, cpu_off, uart_off, eth_off, ehci_off, err;
+ uint32_t cfg, cpu_phandle;
+
+ /* leave the GIC node intact if a GIC is present */
+ cfg = __raw_readl((uint32_t *)SEAD_CONFIG);
+ if (cfg & SEAD_CONFIG_GIC_PRESENT)
+ return 0;
+
+ gic_off = fdt_node_offset_by_compatible(fdt, -1, "mti,gic");
+ if (gic_off < 0) {
+ pr_err("unable to find DT GIC node: %d\n", gic_off);
+ return gic_off;
+ }
+
+ err = fdt_nop_node(fdt, gic_off);
+ if (err) {
+ pr_err("unable to nop GIC node\n");
+ return err;
+ }
+
+ cpu_off = fdt_node_offset_by_compatible(fdt, -1,
+ "mti,cpu-interrupt-controller");
+ if (cpu_off < 0) {
+ pr_err("unable to find CPU intc node: %d\n", cpu_off);
+ return cpu_off;
+ }
+
+ cpu_phandle = fdt_get_phandle(fdt, cpu_off);
+ if (!cpu_phandle) {
+ pr_err("unable to get CPU intc phandle\n");
+ return -EINVAL;
+ }
+
+ err = fdt_setprop_u32(fdt, 0, "interrupt-parent", cpu_phandle);
+ if (err) {
+ pr_err("unable to set root interrupt-parent: %d\n", err);
+ return err;
+ }
+
+ uart_off = fdt_node_offset_by_compatible(fdt, -1, "ns16550a");
+ while (uart_off >= 0) {
+ err = fdt_setprop_u32(fdt, uart_off, "interrupts",
+ cpu_uart_int);
+ if (err) {
+ pr_err("unable to set UART interrupts property: %d\n",
+ err);
+ return err;
+ }
+
+ uart_off = fdt_node_offset_by_compatible(fdt, uart_off,
+ "ns16550a");
+ }
+ if (uart_off != -FDT_ERR_NOTFOUND) {
+ pr_err("error searching for UART DT node: %d\n", uart_off);
+ return uart_off;
+ }
+
+ eth_off = fdt_node_offset_by_compatible(fdt, -1, "smsc,lan9115");
+ if (eth_off < 0) {
+ pr_err("unable to find ethernet DT node: %d\n", eth_off);
+ return eth_off;
+ }
+
+ err = fdt_setprop_u32(fdt, eth_off, "interrupts", cpu_eth_int);
+ if (err) {
+ pr_err("unable to set ethernet interrupts property: %d\n", err);
+ return err;
+ }
+
+ ehci_off = fdt_node_offset_by_compatible(fdt, -1, "generic-ehci");
+ if (ehci_off < 0) {
+ pr_err("unable to find EHCI DT node: %d\n", ehci_off);
+ return ehci_off;
+ }
+
+ err = fdt_setprop_u32(fdt, ehci_off, "interrupts", cpu_ehci_int);
+ if (err) {
+ pr_err("unable to set EHCI interrupts property: %d\n", err);
+ return err;
+ }
+
+ return 0;
+}
+
+static __init int serial_config(void *fdt)
+{
+ const char *yamontty, *mode_var;
+ char mode_var_name[9], path[18], parity;
+ unsigned int uart, baud, stop_bits;
+ bool hw_flow;
+ int chosen_off, err;
+
+ yamontty = fw_getenv("yamontty");
+ if (!yamontty || !strcmp(yamontty, "tty0")) {
+ uart = 0;
+ } else if (!strcmp(yamontty, "tty1")) {
+ uart = 1;
+ } else {
+ pr_warn("yamontty environment variable '%s' invalid\n",
+ yamontty);
+ uart = 0;
+ }
+
+ baud = stop_bits = 0;
+ parity = 0;
+ hw_flow = false;
+
+ snprintf(mode_var_name, sizeof(mode_var_name), "modetty%u", uart);
+ mode_var = fw_getenv(mode_var_name);
+ if (mode_var) {
+ while (mode_var[0] >= '0' && mode_var[0] <= '9') {
+ baud *= 10;
+ baud += mode_var[0] - '0';
+ mode_var++;
+ }
+ if (mode_var[0] == ',')
+ mode_var++;
+ if (mode_var[0])
+ parity = mode_var[0];
+ if (mode_var[0] == ',')
+ mode_var++;
+ if (mode_var[0])
+ stop_bits = mode_var[0] - '0';
+ if (mode_var[0] == ',')
+ mode_var++;
+ if (!strcmp(mode_var, "hw"))
+ hw_flow = true;
+ }
+
+ if (!baud)
+ baud = 38400;
+
+ if (parity != 'e' && parity != 'n' && parity != 'o')
+ parity = 'n';
+
+ if (stop_bits != 7 && stop_bits != 8)
+ stop_bits = 8;
+
+ WARN_ON(snprintf(path, sizeof(path), "uart%u:%u%c%u%s",
+ uart, baud, parity, stop_bits,
+ hw_flow ? "r" : "") >= sizeof(path));
+
+ /* find or add chosen node */
+ chosen_off = fdt_path_offset(fdt, "/chosen");
+ if (chosen_off == -FDT_ERR_NOTFOUND)
+ chosen_off = fdt_path_offset(fdt, "/chosen@0");
+ if (chosen_off == -FDT_ERR_NOTFOUND)
+ chosen_off = fdt_add_subnode(fdt, 0, "chosen");
+ if (chosen_off < 0) {
+ pr_err("Unable to find or add DT chosen node: %d\n",
+ chosen_off);
+ return chosen_off;
+ }
+
+ err = fdt_setprop_string(fdt, chosen_off, "stdout-path", path);
+ if (err) {
+ pr_err("Unable to set stdout-path property: %d\n", err);
+ return err;
+ }
+
+ return 0;
+}
+
+static __init const void *sead3_fixup_fdt(const void *fdt,
+ const void *match_data)
+{
+ static unsigned char fdt_buf[16 << 10] __initdata;
+ int err;
+
+ if (fdt_check_header(fdt))
+ panic("Corrupt DT");
+
+ /* if this isn't SEAD3, something went wrong */
+ BUG_ON(fdt_node_check_compatible(fdt, 0, "mti,sead-3"));
+
+ fw_init_cmdline();
+
+ err = fdt_open_into(fdt, fdt_buf, sizeof(fdt_buf));
+ if (err)
+ panic("Unable to open FDT: %d", err);
+
+ err = append_cmdline(fdt_buf);
+ if (err)
+ panic("Unable to patch FDT: %d", err);
+
+ err = append_memory(fdt_buf);
+ if (err)
+ panic("Unable to patch FDT: %d", err);
+
+ err = remove_gic(fdt_buf);
+ if (err)
+ panic("Unable to patch FDT: %d", err);
+
+ err = serial_config(fdt_buf);
+ if (err)
+ panic("Unable to patch FDT: %d", err);
+
+ err = fdt_pack(fdt_buf);
+ if (err)
+ panic("Unable to pack FDT: %d\n", err);
+
+ return fdt_buf;
+}
+
+static __init unsigned int sead3_measure_hpt_freq(void)
+{
+ void __iomem *status_reg = (void __iomem *)0xbf000410;
+ unsigned int freq, orig, tick = 0;
+ unsigned long flags;
+
+ local_irq_save(flags);
+
+ orig = readl(status_reg) & 0x2; /* get original sample */
+ /* wait for transition */
+ while ((readl(status_reg) & 0x2) == orig)
+ ;
+ orig = orig ^ 0x2; /* flip the bit */
+
+ write_c0_count(0);
+
+ /* wait 1 second (the sampling clock transitions every 10ms) */
+ while (tick < 100) {
+ /* wait for transition */
+ while ((readl(status_reg) & 0x2) == orig)
+ ;
+ orig = orig ^ 0x2; /* flip the bit */
+ tick++;
+ }
+
+ freq = read_c0_count();
+
+ local_irq_restore(flags);
+
+ return freq;
+}
+
+extern char __dtb_sead3_begin[];
+
+MIPS_MACHINE(sead3) = {
+ .fdt = __dtb_sead3_begin,
+ .detect = sead3_detect,
+ .fixup_fdt = sead3_fixup_fdt,
+ .measure_hpt_freq = sead3_measure_hpt_freq,
+};
diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c
new file mode 100644
index 0000000..d493ccb
--- /dev/null
+++ b/arch/mips/generic/init.c
@@ -0,0 +1,180 @@
+/*
+ * Copyright (C) 2016 Imagination Technologies
+ * Author: Paul Burton <paul.burton@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/clocksource.h>
+#include <linux/init.h>
+#include <linux/irqchip.h>
+#include <linux/of_fdt.h>
+#include <linux/of_platform.h>
+
+#include <asm/fw/fw.h>
+#include <asm/irq_cpu.h>
+#include <asm/machine.h>
+#include <asm/mips-cpc.h>
+#include <asm/prom.h>
+#include <asm/smp-ops.h>
+#include <asm/time.h>
+
+static __initdata const void *fdt;
+static __initdata const struct mips_machine *mach;
+static __initdata const void *mach_match_data;
+
+void __init prom_init(void)
+{
+ plat_get_fdt();
+ BUG_ON(!fdt);
+}
+
+void __init *plat_get_fdt(void)
+{
+ const struct mips_machine *check_mach;
+ const struct of_device_id *match;
+
+ if (fdt)
+ /* Already set up */
+ return (void *)fdt;
+
+ if ((fw_arg0 == -2) && !fdt_check_header((void *)fw_arg1)) {
+ /*
+ * We booted using the UHI boot protocol, so we have been
+ * provided with the appropriate device tree for the board.
+ * Make use of it & search for any machine struct based upon
+ * the root compatible string.
+ */
+ fdt = (void *)fw_arg1;
+
+ for_each_mips_machine(check_mach) {
+ match = mips_machine_is_compatible(check_mach, fdt);
+ if (match) {
+ mach = check_mach;
+ mach_match_data = match->data;
+ break;
+ }
+ }
+ } else if (IS_ENABLED(CONFIG_LEGACY_BOARDS)) {
+ /*
+ * We weren't booted using the UHI boot protocol, but do
+ * support some number of boards with legacy boot protocols.
+ * Attempt to find the right one.
+ */
+ for_each_mips_machine(check_mach) {
+ if (!check_mach->detect)
+ continue;
+
+ if (!check_mach->detect())
+ continue;
+
+ mach = check_mach;
+ }
+
+ /*
+ * If we don't recognise the machine then we can't continue, so
+ * die here.
+ */
+ BUG_ON(!mach);
+
+ /* Retrieve the machine's FDT */
+ fdt = mach->fdt;
+ }
+ return (void *)fdt;
+}
+
+void __init plat_mem_setup(void)
+{
+ if (mach && mach->fixup_fdt)
+ fdt = mach->fixup_fdt(fdt, mach_match_data);
+
+ strlcpy(arcs_cmdline, boot_command_line, COMMAND_LINE_SIZE);
+ __dt_setup_arch((void *)fdt);
+}
+
+void __init device_tree_init(void)
+{
+ int err;
+
+ unflatten_and_copy_device_tree();
+ mips_cpc_probe();
+
+ err = register_cps_smp_ops();
+ if (err)
+ err = register_up_smp_ops();
+}
+
+void __init plat_time_init(void)
+{
+ struct device_node *np;
+ struct clk *clk;
+
+ of_clk_init(NULL);
+
+ if (!cpu_has_counter) {
+ mips_hpt_frequency = 0;
+ } else if (mach && mach->measure_hpt_freq) {
+ mips_hpt_frequency = mach->measure_hpt_freq();
+ } else {
+ np = of_get_cpu_node(0, NULL);
+ if (!np) {
+ pr_err("Failed to get CPU node\n");
+ return;
+ }
+
+ clk = of_clk_get(np, 0);
+ if (IS_ERR(clk)) {
+ pr_err("Failed to get CPU clock: %ld\n", PTR_ERR(clk));
+ return;
+ }
+
+ mips_hpt_frequency = clk_get_rate(clk);
+ clk_put(clk);
+
+ switch (boot_cpu_type()) {
+ case CPU_20KC:
+ case CPU_25KF:
+ /* The counter runs at the CPU clock rate */
+ break;
+ default:
+ /* The counter runs at half the CPU clock rate */
+ mips_hpt_frequency /= 2;
+ break;
+ }
+ }
+
+ clocksource_probe();
+}
+
+void __init arch_init_irq(void)
+{
+ struct device_node *intc_node;
+
+ intc_node = of_find_compatible_node(NULL, NULL,
+ "mti,cpu-interrupt-controller");
+ if (!cpu_has_veic && !intc_node)
+ mips_cpu_irq_init();
+
+ irqchip_init();
+}
+
+static int __init publish_devices(void)
+{
+ if (!of_have_populated_dt())
+ panic("Device-tree not present");
+
+ if (of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL))
+ panic("Failed to populate DT");
+
+ return 0;
+}
+arch_initcall(publish_devices);
+
+void __init prom_free_prom_memory(void)
+{
+}
diff --git a/arch/mips/generic/irq.c b/arch/mips/generic/irq.c
new file mode 100644
index 0000000..14064bd
--- /dev/null
+++ b/arch/mips/generic/irq.c
@@ -0,0 +1,64 @@
+/*
+ * Copyright (C) 2016 Imagination Technologies
+ * Author: Paul Burton <paul.burton@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/clocksource.h>
+#include <linux/init.h>
+#include <linux/irqchip/mips-gic.h>
+#include <linux/types.h>
+
+#include <asm/irq.h>
+
+int get_c0_fdc_int(void)
+{
+ int mips_cpu_fdc_irq;
+
+ if (cpu_has_veic)
+ panic("Unimplemented!");
+ else if (gic_present)
+ mips_cpu_fdc_irq = gic_get_c0_fdc_int();
+ else if (cp0_fdc_irq >= 0)
+ mips_cpu_fdc_irq = MIPS_CPU_IRQ_BASE + cp0_fdc_irq;
+ else
+ mips_cpu_fdc_irq = -1;
+
+ return mips_cpu_fdc_irq;
+}
+
+int get_c0_perfcount_int(void)
+{
+ int mips_cpu_perf_irq;
+
+ if (cpu_has_veic)
+ panic("Unimplemented!");
+ else if (gic_present)
+ mips_cpu_perf_irq = gic_get_c0_perfcount_int();
+ else if (cp0_perfcount_irq >= 0)
+ mips_cpu_perf_irq = MIPS_CPU_IRQ_BASE + cp0_perfcount_irq;
+ else
+ mips_cpu_perf_irq = -1;
+
+ return mips_cpu_perf_irq;
+}
+
+unsigned int get_c0_compare_int(void)
+{
+ int mips_cpu_timer_irq;
+
+ if (cpu_has_veic)
+ panic("Unimplemented!");
+ else if (gic_present)
+ mips_cpu_timer_irq = gic_get_c0_compare_int();
+ else
+ mips_cpu_timer_irq = MIPS_CPU_IRQ_BASE + cp0_compare_irq;
+
+ return mips_cpu_timer_irq;
+}
diff --git a/arch/mips/generic/proc.c b/arch/mips/generic/proc.c
new file mode 100644
index 0000000..42b3325
--- /dev/null
+++ b/arch/mips/generic/proc.c
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2016 Imagination Technologies
+ * Author: Paul Burton <paul.burton@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/of.h>
+
+#include <asm/bootinfo.h>
+
+const char *get_system_type(void)
+{
+ const char *str;
+ int err;
+
+ err = of_property_read_string(of_root, "model", &str);
+ if (!err)
+ return str;
+
+ err = of_property_read_string_index(of_root, "compatible", 0, &str);
+ if (!err)
+ return str;
+
+ return "Unknown";
+}
diff --git a/arch/mips/generic/vmlinux.its.S b/arch/mips/generic/vmlinux.its.S
new file mode 100644
index 0000000..f67fbf1
--- /dev/null
+++ b/arch/mips/generic/vmlinux.its.S
@@ -0,0 +1,31 @@
+/dts-v1/;
+
+/ {
+ description = KERNEL_NAME;
+ #address-cells = <ADDR_CELLS>;
+
+ images {
+ kernel@0 {
+ description = KERNEL_NAME;
+ data = /incbin/(VMLINUX_BINARY);
+ type = "kernel";
+ arch = "mips";
+ os = "linux";
+ compression = VMLINUX_COMPRESSION;
+ load = /bits/ ADDR_BITS <VMLINUX_LOAD_ADDRESS>;
+ entry = /bits/ ADDR_BITS <VMLINUX_ENTRY_ADDRESS>;
+ hash@0 {
+ algo = "sha1";
+ };
+ };
+ };
+
+ configurations {
+ default = "conf@default";
+
+ conf@default {
+ description = "Generic Linux kernel";
+ kernel = "kernel@0";
+ };
+ };
+};
diff --git a/arch/mips/include/asm/addrspace.h b/arch/mips/include/asm/addrspace.h
index c5b04e7..4856adc 100644
--- a/arch/mips/include/asm/addrspace.h
+++ b/arch/mips/include/asm/addrspace.h
@@ -126,8 +126,7 @@
#define PHYS_TO_XKSEG_UNCACHED(p) PHYS_TO_XKPHYS(K_CALG_UNCACHED, (p))
#define PHYS_TO_XKSEG_CACHED(p) PHYS_TO_XKPHYS(K_CALG_COH_SHAREABLE, (p))
#define XKPHYS_TO_PHYS(p) ((p) & TO_PHYS_MASK)
-#define PHYS_TO_XKPHYS(cm, a) (_CONST64_(0x8000000000000000) | \
- (_CONST64_(cm) << 59) | (a))
+#define PHYS_TO_XKPHYS(cm, a) (XKPHYS | (_ACAST64_(cm) << 59) | (a))
/*
* The ultimate limited of the 64-bit MIPS architecture: 2 bits for selecting
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index d296633..a5eb1bb 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -10,6 +10,102 @@
#include <asm/addrspace.h>
+/*
+ * Sync types defined by the MIPS architecture (document MD00087 table 6.5)
+ * These values are used with the sync instruction to perform memory barriers.
+ * Types of ordering guarantees available through the SYNC instruction:
+ * - Completion Barriers
+ * - Ordering Barriers
+ * As compared to the completion barrier, the ordering barrier is a
+ * lighter-weight operation as it does not require the specified instructions
+ * before the SYNC to be already completed. Instead it only requires that those
+ * specified instructions which are subsequent to the SYNC in the instruction
+ * stream are never re-ordered for processing ahead of the specified
+ * instructions which are before the SYNC in the instruction stream.
+ * This potentially reduces how many cycles the barrier instruction must stall
+ * before it completes.
+ * Implementations that do not use any of the non-zero values of stype to define
+ * different barriers, such as ordering barriers, must make those stype values
+ * act the same as stype zero.
+ */
+
+/*
+ * Completion barriers:
+ * - Every synchronizable specified memory instruction (loads or stores or both)
+ * that occurs in the instruction stream before the SYNC instruction must be
+ * already globally performed before any synchronizable specified memory
+ * instructions that occur after the SYNC are allowed to be performed, with
+ * respect to any other processor or coherent I/O module.
+ *
+ * - The barrier does not guarantee the order in which instruction fetches are
+ * performed.
+ *
+ * - A stype value of zero will always be defined such that it performs the most
+ * complete set of synchronization operations that are defined.This means
+ * stype zero always does a completion barrier that affects both loads and
+ * stores preceding the SYNC instruction and both loads and stores that are
+ * subsequent to the SYNC instruction. Non-zero values of stype may be defined
+ * by the architecture or specific implementations to perform synchronization
+ * behaviors that are less complete than that of stype zero. If an
+ * implementation does not use one of these non-zero values to define a
+ * different synchronization behavior, then that non-zero value of stype must
+ * act the same as stype zero completion barrier. This allows software written
+ * for an implementation with a lighter-weight barrier to work on another
+ * implementation which only implements the stype zero completion barrier.
+ *
+ * - A completion barrier is required, potentially in conjunction with SSNOP (in
+ * Release 1 of the Architecture) or EHB (in Release 2 of the Architecture),
+ * to guarantee that memory reference results are visible across operating
+ * mode changes. For example, a completion barrier is required on some
+ * implementations on entry to and exit from Debug Mode to guarantee that
+ * memory effects are handled correctly.
+ */
+
+/*
+ * stype 0 - A completion barrier that affects preceding loads and stores and
+ * subsequent loads and stores.
+ * Older instructions which must reach the load/store ordering point before the
+ * SYNC instruction completes: Loads, Stores
+ * Younger instructions which must reach the load/store ordering point only
+ * after the SYNC instruction completes: Loads, Stores
+ * Older instructions which must be globally performed when the SYNC instruction
+ * completes: Loads, Stores
+ */
+#define STYPE_SYNC 0x0
+
+/*
+ * Ordering barriers:
+ * - Every synchronizable specified memory instruction (loads or stores or both)
+ * that occurs in the instruction stream before the SYNC instruction must
+ * reach a stage in the load/store datapath after which no instruction
+ * re-ordering is possible before any synchronizable specified memory
+ * instruction which occurs after the SYNC instruction in the instruction
+ * stream reaches the same stage in the load/store datapath.
+ *
+ * - If any memory instruction before the SYNC instruction in program order,
+ * generates a memory request to the external memory and any memory
+ * instruction after the SYNC instruction in program order also generates a
+ * memory request to external memory, the memory request belonging to the
+ * older instruction must be globally performed before the time the memory
+ * request belonging to the younger instruction is globally performed.
+ *
+ * - The barrier does not guarantee the order in which instruction fetches are
+ * performed.
+ */
+
+/*
+ * stype 0x10 - An ordering barrier that affects preceding loads and stores and
+ * subsequent loads and stores.
+ * Older instructions which must reach the load/store ordering point before the
+ * SYNC instruction completes: Loads, Stores
+ * Younger instructions which must reach the load/store ordering point only
+ * after the SYNC instruction completes: Loads, Stores
+ * Older instructions which must be globally performed when the SYNC instruction
+ * completes: N/A
+ */
+#define STYPE_SYNC_MB 0x10
+
+
#ifdef CONFIG_CPU_HAS_SYNC
#define __sync() \
__asm__ __volatile__( \
diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h
index 34ed22e..4812d1f 100644
--- a/arch/mips/include/asm/cacheflush.h
+++ b/arch/mips/include/asm/cacheflush.h
@@ -28,6 +28,7 @@
* - flush_cache_sigtramp() flush signal trampoline
* - flush_icache_all() flush the entire instruction cache
* - flush_data_cache_page() flushes a page from the data cache
+ * - __flush_icache_user_range(start, end) flushes range of user instructions
*/
/*
@@ -80,6 +81,10 @@ static inline void flush_icache_page(struct vm_area_struct *vma,
extern void (*flush_icache_range)(unsigned long start, unsigned long end);
extern void (*local_flush_icache_range)(unsigned long start, unsigned long end);
+extern void (*__flush_icache_user_range)(unsigned long start,
+ unsigned long end);
+extern void (*__local_flush_icache_user_range)(unsigned long start,
+ unsigned long end);
extern void (*__flush_cache_vmap)(void);
diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h
index fbe1881..bdd6dc1 100644
--- a/arch/mips/include/asm/cpu-type.h
+++ b/arch/mips/include/asm/cpu-type.h
@@ -24,7 +24,8 @@ static inline int __pure __get_cpu_type(const int cpu_type)
case CPU_LOONGSON3:
#endif
-#ifdef CONFIG_SYS_HAS_CPU_LOONGSON1B
+#if defined(CONFIG_SYS_HAS_CPU_LOONGSON1B) || \
+ defined(CONFIG_SYS_HAS_CPU_LOONGSON1C)
case CPU_LOONGSON1:
#endif
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index f672df8..9a83724 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -240,6 +240,7 @@
#define PRID_REV_VR4130 0x0080
#define PRID_REV_34K_V1_0_2 0x0022
#define PRID_REV_LOONGSON1B 0x0020
+#define PRID_REV_LOONGSON1C 0x0020 /* Same as Loongson-1B */
#define PRID_REV_LOONGSON2E 0x0002
#define PRID_REV_LOONGSON2F 0x0003
#define PRID_REV_LOONGSON3A_R1 0x0005
diff --git a/arch/mips/include/asm/device.h b/arch/mips/include/asm/device.h
index c94fafb..21c2082 100644
--- a/arch/mips/include/asm/device.h
+++ b/arch/mips/include/asm/device.h
@@ -11,6 +11,11 @@ struct dma_map_ops;
struct dev_archdata {
/* DMA operations on that device */
struct dma_map_ops *dma_ops;
+
+#ifdef CONFIG_DMA_PERDEV_COHERENT
+ /* Non-zero if DMA is coherent with CPU caches */
+ bool dma_coherent;
+#endif
};
struct pdev_archdata {
diff --git a/arch/mips/include/asm/dma-coherence.h b/arch/mips/include/asm/dma-coherence.h
index bc5e85d..72d0eab 100644
--- a/arch/mips/include/asm/dma-coherence.h
+++ b/arch/mips/include/asm/dma-coherence.h
@@ -9,14 +9,22 @@
#ifndef __ASM_DMA_COHERENCE_H
#define __ASM_DMA_COHERENCE_H
-#ifdef CONFIG_DMA_MAYBE_COHERENT
-extern int coherentio;
+enum coherent_io_user_state {
+ IO_COHERENCE_DEFAULT,
+ IO_COHERENCE_ENABLED,
+ IO_COHERENCE_DISABLED,
+};
+
+#if defined(CONFIG_DMA_PERDEV_COHERENT)
+/* Don't provide (hw_)coherentio to avoid misuse */
+#elif defined(CONFIG_DMA_MAYBE_COHERENT)
+extern enum coherent_io_user_state coherentio;
extern int hw_coherentio;
#else
#ifdef CONFIG_DMA_COHERENT
-#define coherentio 1
+#define coherentio IO_COHERENCE_ENABLED
#else
-#define coherentio 0
+#define coherentio IO_COHERENCE_DISABLED
#endif
#define hw_coherentio 0
#endif /* CONFIG_DMA_MAYBE_COHERENT */
diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index 12fa79e..7aa71b9 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -32,4 +32,14 @@ static inline void dma_mark_clean(void *addr, size_t size) {}
extern void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
enum dma_data_direction direction);
+#define arch_setup_dma_ops arch_setup_dma_ops
+static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
+ u64 size, const struct iommu_ops *iommu,
+ bool coherent)
+{
+#ifdef CONFIG_DMA_PERDEV_COHERENT
+ dev->archdata.dma_coherent = coherent;
+#endif
+}
+
#endif /* _ASM_DMA_MAPPING_H */
diff --git a/arch/mips/include/asm/fpu_emulator.h b/arch/mips/include/asm/fpu_emulator.h
index 355dc25..c05369e 100644
--- a/arch/mips/include/asm/fpu_emulator.h
+++ b/arch/mips/include/asm/fpu_emulator.h
@@ -63,6 +63,8 @@ do { \
extern int fpu_emulator_cop1Handler(struct pt_regs *xcp,
struct mips_fpu_struct *ctx, int has_fpu,
void *__user *fault_addr);
+void force_fcr31_sig(unsigned long fcr31, void __user *fault_addr,
+ struct task_struct *tsk);
int process_fpemu_return(int sig, void __user *fault_addr,
unsigned long fcr31);
int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
@@ -81,4 +83,15 @@ static inline void fpu_emulator_init_fpu(void)
set_fpr64(&t->thread.fpu.fpr[i], 0, SIGNALLING_NAN);
}
+/*
+ * Mask the FCSR Cause bits according to the Enable bits, observing
+ * that Unimplemented is always enabled.
+ */
+static inline unsigned long mask_fcr31_x(unsigned long fcr31)
+{
+ return fcr31 & (FPU_CSR_UNI_X |
+ ((fcr31 & FPU_CSR_ALL_E) <<
+ (ffs(FPU_CSR_ALL_X) - ffs(FPU_CSR_ALL_E))));
+}
+
#endif /* _ASM_FPU_EMULATOR_H */
diff --git a/arch/mips/include/asm/i8259.h b/arch/mips/include/asm/i8259.h
index a7fbcd6..32229c7 100644
--- a/arch/mips/include/asm/i8259.h
+++ b/arch/mips/include/asm/i8259.h
@@ -37,12 +37,22 @@
extern raw_spinlock_t i8259A_lock;
-extern int i8259A_irq_pending(unsigned int irq);
extern void make_8259A_irq(unsigned int irq);
extern void init_i8259_irqs(void);
extern int i8259_of_init(struct device_node *node, struct device_node *parent);
+/**
+ * i8159_set_poll() - Override the i8259 polling function
+ * @poll: pointer to platform-specific polling function
+ *
+ * Call this to override the generic i8259 polling function, which directly
+ * accesses i8259 registers, with a platform specific one which may be faster
+ * in cases where hardware provides a more optimal means of polling for an
+ * interrupt.
+ */
+extern void i8259_set_poll(int (*poll)(void));
+
/*
* Do the traditional i8259 interrupt polling thing. This is for the few
* cases where no better interrupt acknowledge method is available and we
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 07f58cf..bebec37 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -293,7 +293,10 @@ struct kvm_vcpu_arch {
/* Host KSEG0 address of the EI/DI offset */
void *kseg0_commpage;
- u32 io_gpr; /* GPR used as IO source/target */
+ /* Resume PC after MMIO completion */
+ unsigned long io_pc;
+ /* GPR used as IO source/target */
+ u32 io_gpr;
struct hrtimer comparecount_timer;
/* Count timer control KVM register */
@@ -315,8 +318,6 @@ struct kvm_vcpu_arch {
/* Bitmask of pending exceptions to be cleared */
unsigned long pending_exceptions_clr;
- u32 pending_load_cause;
-
/* Save/Restore the entryhi register when are are preempted/scheduled back in */
unsigned long preempt_entryhi;
diff --git a/arch/mips/include/asm/mach-generic/dma-coherence.h b/arch/mips/include/asm/mach-generic/dma-coherence.h
index 0f8a354..61addb1 100644
--- a/arch/mips/include/asm/mach-generic/dma-coherence.h
+++ b/arch/mips/include/asm/mach-generic/dma-coherence.h
@@ -49,7 +49,19 @@ static inline int plat_dma_supported(struct device *dev, u64 mask)
static inline int plat_device_is_coherent(struct device *dev)
{
- return coherentio;
+#ifdef CONFIG_DMA_PERDEV_COHERENT
+ return dev->archdata.dma_coherent;
+#else
+ switch (coherentio) {
+ default:
+ case IO_COHERENCE_DEFAULT:
+ return hw_coherentio;
+ case IO_COHERENCE_ENABLED:
+ return 1;
+ case IO_COHERENCE_DISABLED:
+ return 0;
+ }
+#endif
}
#ifndef plat_post_dma_flush
diff --git a/arch/mips/include/asm/mach-generic/floppy.h b/arch/mips/include/asm/mach-generic/floppy.h
index e2561d9..9ec2f6a 100644
--- a/arch/mips/include/asm/mach-generic/floppy.h
+++ b/arch/mips/include/asm/mach-generic/floppy.h
@@ -115,11 +115,7 @@ static inline unsigned long fd_getfdaddr1(void)
static inline unsigned long fd_dma_mem_alloc(unsigned long size)
{
- unsigned long mem;
-
- mem = __get_dma_pages(GFP_KERNEL, get_order(size));
-
- return mem;
+ return __get_dma_pages(GFP_KERNEL, get_order(size));
}
static inline void fd_dma_mem_free(unsigned long addr, unsigned long size)
diff --git a/arch/mips/include/asm/mach-generic/spaces.h b/arch/mips/include/asm/mach-generic/spaces.h
index afc96ec..952b0fd 100644
--- a/arch/mips/include/asm/mach-generic/spaces.h
+++ b/arch/mips/include/asm/mach-generic/spaces.h
@@ -12,6 +12,8 @@
#include <linux/const.h>
+#include <asm/mipsregs.h>
+
/*
* This gives the physical RAM offset.
*/
@@ -52,11 +54,7 @@
#ifdef CONFIG_64BIT
#ifndef CAC_BASE
-#ifdef CONFIG_DMA_NONCOHERENT
-#define CAC_BASE _AC(0x9800000000000000, UL)
-#else
-#define CAC_BASE _AC(0xa800000000000000, UL)
-#endif
+#define CAC_BASE PHYS_TO_XKPHYS(read_c0_config() & CONF_CM_CMASK, 0)
#endif
#ifndef IO_BASE
diff --git a/arch/mips/include/asm/mach-ip27/spaces.h b/arch/mips/include/asm/mach-ip27/spaces.h
index b18802a..4775a11 100644
--- a/arch/mips/include/asm/mach-ip27/spaces.h
+++ b/arch/mips/include/asm/mach-ip27/spaces.h
@@ -19,6 +19,7 @@
#define IO_BASE 0x9200000000000000
#define MSPEC_BASE 0x9400000000000000
#define UNCAC_BASE 0x9600000000000000
+#define CAC_BASE 0xa800000000000000
#define TO_MSPEC(x) (MSPEC_BASE | ((x) & TO_PHYS_MASK))
#define TO_HSPEC(x) (HSPEC_BASE | ((x) & TO_PHYS_MASK))
diff --git a/arch/mips/include/asm/mach-loongson32/irq.h b/arch/mips/include/asm/mach-loongson32/irq.h
index c1c7441..8c01b30 100644
--- a/arch/mips/include/asm/mach-loongson32/irq.h
+++ b/arch/mips/include/asm/mach-loongson32/irq.h
@@ -36,9 +36,14 @@
#define LS1X_IRQ(n, x) (LS1X_IRQ_BASE + (n << 5) + (x))
#define LS1X_UART0_IRQ LS1X_IRQ(0, 2)
+#if defined(CONFIG_LOONGSON1_LS1B)
#define LS1X_UART1_IRQ LS1X_IRQ(0, 3)
#define LS1X_UART2_IRQ LS1X_IRQ(0, 4)
#define LS1X_UART3_IRQ LS1X_IRQ(0, 5)
+#elif defined(CONFIG_LOONGSON1_LS1C)
+#define LS1X_UART1_IRQ LS1X_IRQ(0, 4)
+#define LS1X_UART2_IRQ LS1X_IRQ(0, 5)
+#endif
#define LS1X_CAN0_IRQ LS1X_IRQ(0, 6)
#define LS1X_CAN1_IRQ LS1X_IRQ(0, 7)
#define LS1X_SPI0_IRQ LS1X_IRQ(0, 8)
@@ -47,6 +52,9 @@
#define LS1X_DMA0_IRQ LS1X_IRQ(0, 13)
#define LS1X_DMA1_IRQ LS1X_IRQ(0, 14)
#define LS1X_DMA2_IRQ LS1X_IRQ(0, 15)
+#if defined(CONFIG_LOONGSON1_LS1C)
+#define LS1X_NAND_IRQ LS1X_IRQ(0, 16)
+#endif
#define LS1X_PWM0_IRQ LS1X_IRQ(0, 17)
#define LS1X_PWM1_IRQ LS1X_IRQ(0, 18)
#define LS1X_PWM2_IRQ LS1X_IRQ(0, 19)
@@ -54,18 +62,49 @@
#define LS1X_RTC_INT0_IRQ LS1X_IRQ(0, 21)
#define LS1X_RTC_INT1_IRQ LS1X_IRQ(0, 22)
#define LS1X_RTC_INT2_IRQ LS1X_IRQ(0, 23)
+#if defined(CONFIG_LOONGSON1_LS1B)
#define LS1X_TOY_INT0_IRQ LS1X_IRQ(0, 24)
#define LS1X_TOY_INT1_IRQ LS1X_IRQ(0, 25)
#define LS1X_TOY_INT2_IRQ LS1X_IRQ(0, 26)
#define LS1X_RTC_TICK_IRQ LS1X_IRQ(0, 27)
#define LS1X_TOY_TICK_IRQ LS1X_IRQ(0, 28)
+#define LS1X_UART4_IRQ LS1X_IRQ(0, 29)
+#define LS1X_UART5_IRQ LS1X_IRQ(0, 30)
+#elif defined(CONFIG_LOONGSON1_LS1C)
+#define LS1X_UART3_IRQ LS1X_IRQ(0, 29)
+#define LS1X_ADC_IRQ LS1X_IRQ(0, 30)
+#define LS1X_SDIO_IRQ LS1X_IRQ(0, 31)
+#endif
#define LS1X_EHCI_IRQ LS1X_IRQ(1, 0)
#define LS1X_OHCI_IRQ LS1X_IRQ(1, 1)
+#if defined(CONFIG_LOONGSON1_LS1B)
#define LS1X_GMAC0_IRQ LS1X_IRQ(1, 2)
#define LS1X_GMAC1_IRQ LS1X_IRQ(1, 3)
+#elif defined(CONFIG_LOONGSON1_LS1C)
+#define LS1X_OTG_IRQ LS1X_IRQ(1, 2)
+#define LS1X_GMAC0_IRQ LS1X_IRQ(1, 3)
+#define LS1X_CAM_IRQ LS1X_IRQ(1, 4)
+#define LS1X_UART4_IRQ LS1X_IRQ(1, 5)
+#define LS1X_UART5_IRQ LS1X_IRQ(1, 6)
+#define LS1X_UART6_IRQ LS1X_IRQ(1, 7)
+#define LS1X_UART7_IRQ LS1X_IRQ(1, 8)
+#define LS1X_UART8_IRQ LS1X_IRQ(1, 9)
+#define LS1X_UART9_IRQ LS1X_IRQ(1, 13)
+#define LS1X_UART10_IRQ LS1X_IRQ(1, 14)
+#define LS1X_UART11_IRQ LS1X_IRQ(1, 15)
+#define LS1X_I2C0_IRQ LS1X_IRQ(1, 17)
+#define LS1X_I2C1_IRQ LS1X_IRQ(1, 18)
+#define LS1X_I2C2_IRQ LS1X_IRQ(1, 19)
+#endif
-#define LS1X_IRQS (LS1X_IRQ(4, 31) + 1 - LS1X_IRQ_BASE)
+#if defined(CONFIG_LOONGSON1_LS1B)
+#define INTN 4
+#elif defined(CONFIG_LOONGSON1_LS1C)
+#define INTN 5
+#endif
+
+#define LS1X_IRQS (LS1X_IRQ(INTN, 31) + 1 - LS1X_IRQ_BASE)
#define NR_IRQS (MIPS_CPU_IRQS + LS1X_IRQS)
diff --git a/arch/mips/include/asm/mach-loongson32/loongson1.h b/arch/mips/include/asm/mach-loongson32/loongson1.h
index 978f6df..3584c40 100644
--- a/arch/mips/include/asm/mach-loongson32/loongson1.h
+++ b/arch/mips/include/asm/mach-loongson32/loongson1.h
@@ -12,7 +12,11 @@
#ifndef __ASM_MACH_LOONGSON32_LOONGSON1_H
#define __ASM_MACH_LOONGSON32_LOONGSON1_H
+#if defined(CONFIG_LOONGSON1_LS1B)
#define DEFAULT_MEMSIZE 256 /* If no memsize provided */
+#elif defined(CONFIG_LOONGSON1_LS1C)
+#define DEFAULT_MEMSIZE 32
+#endif
/* Loongson 1 Register Bases */
#define LS1X_MUX_BASE 0x1fd00420
@@ -20,6 +24,7 @@
#define LS1X_GPIO0_BASE 0x1fd010c0
#define LS1X_GPIO1_BASE 0x1fd010c4
#define LS1X_DMAC_BASE 0x1fd01160
+#define LS1X_CBUS_BASE 0x1fd011c0
#define LS1X_EHCI_BASE 0x1fe00000
#define LS1X_OHCI_BASE 0x1fe08000
#define LS1X_GMAC0_BASE 0x1fe10000
diff --git a/arch/mips/include/asm/mach-loongson32/platform.h b/arch/mips/include/asm/mach-loongson32/platform.h
index 672531a..7adc313 100644
--- a/arch/mips/include/asm/mach-loongson32/platform.h
+++ b/arch/mips/include/asm/mach-loongson32/platform.h
@@ -30,5 +30,6 @@ void __init ls1x_clk_init(void);
void __init ls1x_dma_set_platdata(struct plat_ls1x_dma *pdata);
void __init ls1x_nand_set_platdata(struct plat_ls1x_nand *pdata);
void __init ls1x_serial_set_uartclk(struct platform_device *pdev);
+void __init ls1x_rtc_set_extclk(struct platform_device *pdev);
#endif /* __ASM_MACH_LOONGSON32_PLATFORM_H */
diff --git a/arch/mips/include/asm/mach-loongson32/regs-clk.h b/arch/mips/include/asm/mach-loongson32/regs-clk.h
index 4d56fc3..e5e8f11 100644
--- a/arch/mips/include/asm/mach-loongson32/regs-clk.h
+++ b/arch/mips/include/asm/mach-loongson32/regs-clk.h
@@ -18,6 +18,7 @@
#define LS1X_CLK_PLL_FREQ LS1X_CLK_REG(0x0)
#define LS1X_CLK_PLL_DIV LS1X_CLK_REG(0x4)
+#if defined(CONFIG_LOONGSON1_LS1B)
/* Clock PLL Divisor Register Bits */
#define DIV_DC_EN BIT(31)
#define DIV_DC_RST BIT(30)
@@ -48,4 +49,37 @@
#define BYPASS_DDR_WIDTH 1
#define BYPASS_CPU_WIDTH 1
+#elif defined(CONFIG_LOONGSON1_LS1C)
+/* PLL/SDRAM Frequency configuration register Bits */
+#define PLL_VALID BIT(31)
+#define FRAC_N GENMASK(23, 16)
+#define RST_TIME GENMASK(3, 2)
+#define SDRAM_DIV GENMASK(1, 0)
+
+/* CPU/CAMERA/DC Frequency configuration register Bits */
+#define DIV_DC_EN BIT(31)
+#define DIV_DC GENMASK(30, 24)
+#define DIV_CAM_EN BIT(23)
+#define DIV_CAM GENMASK(22, 16)
+#define DIV_CPU_EN BIT(15)
+#define DIV_CPU GENMASK(14, 8)
+#define DIV_DC_SEL_EN BIT(5)
+#define DIV_DC_SEL BIT(4)
+#define DIV_CAM_SEL_EN BIT(3)
+#define DIV_CAM_SEL BIT(2)
+#define DIV_CPU_SEL_EN BIT(1)
+#define DIV_CPU_SEL BIT(0)
+
+#define DIV_DC_SHIFT 24
+#define DIV_CAM_SHIFT 16
+#define DIV_CPU_SHIFT 8
+#define DIV_DDR_SHIFT 0
+
+#define DIV_DC_WIDTH 7
+#define DIV_CAM_WIDTH 7
+#define DIV_CPU_WIDTH 7
+#define DIV_DDR_WIDTH 2
+
+#endif
+
#endif /* __ASM_MACH_LOONGSON32_REGS_CLK_H */
diff --git a/arch/mips/include/asm/mach-loongson32/regs-mux.h b/arch/mips/include/asm/mach-loongson32/regs-mux.h
index 7c394f9..4a0bdeb 100644
--- a/arch/mips/include/asm/mach-loongson32/regs-mux.h
+++ b/arch/mips/include/asm/mach-loongson32/regs-mux.h
@@ -18,6 +18,7 @@
#define LS1X_MUX_CTRL0 LS1X_MUX_REG(0x0)
#define LS1X_MUX_CTRL1 LS1X_MUX_REG(0x4)
+#if defined(CONFIG_LOONGSON1_LS1B)
/* MUX CTRL0 Register Bits */
#define UART0_USE_PWM23 BIT(28)
#define UART0_USE_PWM01 BIT(27)
@@ -64,4 +65,64 @@
#define GMAC1_USE_PWM23 BIT(1)
#define GMAC0_USE_PWM01 BIT(0)
+#elif defined(CONFIG_LOONGSON1_LS1C)
+
+/* SHUT_CTRL Register Bits */
+#define UART_SPLIT GENMASK(31, 30)
+#define OUTPUT_CLK GENMASK(29, 26)
+#define ADC_SHUT BIT(25)
+#define SDIO_SHUT BIT(24)
+#define DMA2_SHUT BIT(23)
+#define DMA1_SHUT BIT(22)
+#define DMA0_SHUT BIT(21)
+#define SPI1_SHUT BIT(20)
+#define SPI0_SHUT BIT(19)
+#define I2C2_SHUT BIT(18)
+#define I2C1_SHUT BIT(17)
+#define I2C0_SHUT BIT(16)
+#define AC97_SHUT BIT(15)
+#define I2S_SHUT BIT(14)
+#define UART3_SHUT BIT(13)
+#define UART2_SHUT BIT(12)
+#define UART1_SHUT BIT(11)
+#define UART0_SHUT BIT(10)
+#define CAN1_SHUT BIT(9)
+#define CAN0_SHUT BIT(8)
+#define ECC_SHUT BIT(7)
+#define GMAC_SHUT BIT(6)
+#define USBHOST_SHUT BIT(5)
+#define USBOTG_SHUT BIT(4)
+#define SDRAM_SHUT BIT(3)
+#define SRAM_SHUT BIT(2)
+#define CAM_SHUT BIT(1)
+#define LCD_SHUT BIT(0)
+
+#define UART_SPLIT_SHIFT 30
+#define OUTPUT_CLK_SHIFT 26
+
+/* MISC_CTRL Register Bits */
+#define USBHOST_RSTN BIT(31)
+#define PHY_INTF_SELI GENMASK(30, 28)
+#define AC97_EN BIT(25)
+#define SDIO_DMA_EN GENMASK(24, 23)
+#define ADC_DMA_EN BIT(22)
+#define SDIO_USE_SPI1 BIT(17)
+#define SDIO_USE_SPI0 BIT(16)
+#define SRAM_CTRL GENMASK(15, 0)
+
+#define PHY_INTF_SELI_SHIFT 28
+#define SDIO_DMA_EN_SHIFT 23
+#define SRAM_CTRL_SHIFT 0
+
+#define LS1X_CBUS_REG(n, x) \
+ ((void __iomem *)KSEG1ADDR(LS1X_CBUS_BASE + (n * 0x04) + (x)))
+
+#define LS1X_CBUS_FIRST(n) LS1X_CBUS_REG(n, 0x00)
+#define LS1X_CBUS_SECOND(n) LS1X_CBUS_REG(n, 0x10)
+#define LS1X_CBUS_THIRD(n) LS1X_CBUS_REG(n, 0x20)
+#define LS1X_CBUS_FOURTHT(n) LS1X_CBUS_REG(n, 0x30)
+#define LS1X_CBUS_FIFTHT(n) LS1X_CBUS_REG(n, 0x40)
+
+#endif
+
#endif /* __ASM_MACH_LOONGSON32_REGS_MUX_H */
diff --git a/arch/mips/include/asm/mach-sead3/cpu-feature-overrides.h b/arch/mips/include/asm/mach-sead3/cpu-feature-overrides.h
deleted file mode 100644
index bfbd703..0000000
--- a/arch/mips/include/asm/mach-sead3/cpu-feature-overrides.h
+++ /dev/null
@@ -1,72 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2003, 2004 Chris Dearman
- * Copyright (C) 2005 Ralf Baechle (ralf@linux-mips.org)
- */
-#ifndef __ASM_MACH_MIPS_CPU_FEATURE_OVERRIDES_H
-#define __ASM_MACH_MIPS_CPU_FEATURE_OVERRIDES_H
-
-
-/*
- * CPU feature overrides for MIPS boards
- */
-#ifdef CONFIG_CPU_MIPS32
-#define cpu_has_tlb 1
-#define cpu_has_4kex 1
-#define cpu_has_4k_cache 1
-/* #define cpu_has_fpu ? */
-/* #define cpu_has_32fpr ? */
-#define cpu_has_counter 1
-/* #define cpu_has_watch ? */
-#define cpu_has_divec 1
-#define cpu_has_vce 0
-/* #define cpu_has_cache_cdex_p ? */
-/* #define cpu_has_cache_cdex_s ? */
-/* #define cpu_has_prefetch ? */
-#define cpu_has_mcheck 1
-/* #define cpu_has_ejtag ? */
-#ifdef CONFIG_CPU_MICROMIPS
-#define cpu_has_llsc 0
-#else
-#define cpu_has_llsc 1
-#endif
-/* #define cpu_has_vtag_icache ? */
-/* #define cpu_has_dc_aliases ? */
-/* #define cpu_has_ic_fills_f_dc ? */
-#define cpu_has_nofpuex 0
-/* #define cpu_has_64bits ? */
-/* #define cpu_has_64bit_zero_reg ? */
-/* #define cpu_has_inclusive_pcaches ? */
-#define cpu_icache_snoops_remote_store 1
-#endif
-
-#ifdef CONFIG_CPU_MIPS64
-#define cpu_has_tlb 1
-#define cpu_has_4kex 1
-#define cpu_has_4k_cache 1
-/* #define cpu_has_fpu ? */
-/* #define cpu_has_32fpr ? */
-#define cpu_has_counter 1
-/* #define cpu_has_watch ? */
-#define cpu_has_divec 1
-#define cpu_has_vce 0
-/* #define cpu_has_cache_cdex_p ? */
-/* #define cpu_has_cache_cdex_s ? */
-/* #define cpu_has_prefetch ? */
-#define cpu_has_mcheck 1
-/* #define cpu_has_ejtag ? */
-#define cpu_has_llsc 1
-/* #define cpu_has_vtag_icache ? */
-/* #define cpu_has_dc_aliases ? */
-/* #define cpu_has_ic_fills_f_dc ? */
-#define cpu_has_nofpuex 0
-/* #define cpu_has_64bits ? */
-/* #define cpu_has_64bit_zero_reg ? */
-/* #define cpu_has_inclusive_pcaches ? */
-#define cpu_icache_snoops_remote_store 1
-#endif
-
-#endif /* __ASM_MACH_MIPS_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/mach-sead3/irq.h b/arch/mips/include/asm/mach-sead3/irq.h
deleted file mode 100644
index 5d154cf..0000000
--- a/arch/mips/include/asm/mach-sead3/irq.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef __ASM_MACH_MIPS_IRQ_H
-#define __ASM_MACH_MIPS_IRQ_H
-
-#define NR_IRQS 256
-
-
-#include_next <irq.h>
-
-#endif /* __ASM_MACH_MIPS_IRQ_H */
diff --git a/arch/mips/include/asm/mach-sead3/kernel-entry-init.h b/arch/mips/include/asm/mach-sead3/kernel-entry-init.h
deleted file mode 100644
index 6cccd4d..0000000
--- a/arch/mips/include/asm/mach-sead3/kernel-entry-init.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Chris Dearman (chris@mips.com)
- * Copyright (C) 2007 Mips Technologies, Inc.
- */
-#ifndef __ASM_MACH_MIPS_KERNEL_ENTRY_INIT_H
-#define __ASM_MACH_MIPS_KERNEL_ENTRY_INIT_H
-
- .macro kernel_entry_setup
- .endm
-
-/*
- * Do SMP slave processor setup necessary before we can safely execute C code.
- */
- .macro smp_slave_setup
- .endm
-
-#endif /* __ASM_MACH_MIPS_KERNEL_ENTRY_INIT_H */
diff --git a/arch/mips/include/asm/mach-sead3/war.h b/arch/mips/include/asm/mach-sead3/war.h
deleted file mode 100644
index d068fc4..0000000
--- a/arch/mips/include/asm/mach-sead3/war.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2002, 2004, 2007 by Ralf Baechle <ralf@linux-mips.org>
- */
-#ifndef __ASM_MIPS_MACH_MIPS_WAR_H
-#define __ASM_MIPS_MACH_MIPS_WAR_H
-
-#define R4600_V1_INDEX_ICACHEOP_WAR 0
-#define R4600_V1_HIT_CACHEOP_WAR 0
-#define R4600_V2_HIT_CACHEOP_WAR 0
-#define R5432_CP0_INTERRUPT_WAR 0
-#define BCM1250_M3_WAR 0
-#define SIBYTE_1956_WAR 0
-#define MIPS4K_ICACHE_REFILL_WAR 1
-#define MIPS_CACHE_SYNC_WAR 1
-#define TX49XX_ICACHE_INDEX_INV_WAR 0
-#define ICACHE_REFILLS_WORKAROUND_WAR 1
-#define R10000_LLSC_WAR 0
-#define MIPS34K_MISSED_ITLB_WAR 0
-
-#endif /* __ASM_MIPS_MACH_MIPS_WAR_H */
diff --git a/arch/mips/include/asm/machine.h b/arch/mips/include/asm/machine.h
new file mode 100644
index 0000000..6b444cd
--- /dev/null
+++ b/arch/mips/include/asm/machine.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright (C) 2016 Imagination Technologies
+ * Author: Paul Burton <paul.burton@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#ifndef __MIPS_ASM_MACHINE_H__
+#define __MIPS_ASM_MACHINE_H__
+
+#include <linux/libfdt.h>
+#include <linux/of.h>
+
+struct mips_machine {
+ const struct of_device_id *matches;
+ const void *fdt;
+ bool (*detect)(void);
+ const void *(*fixup_fdt)(const void *fdt, const void *match_data);
+ unsigned int (*measure_hpt_freq)(void);
+};
+
+extern long __mips_machines_start;
+extern long __mips_machines_end;
+
+#define MIPS_MACHINE(name) \
+ static const struct mips_machine __mips_mach_##name \
+ __used __section(.mips.machines.init)
+
+#define for_each_mips_machine(mach) \
+ for ((mach) = (struct mips_machine *)&__mips_machines_start; \
+ (mach) < (struct mips_machine *)&__mips_machines_end; \
+ (mach)++)
+
+/**
+ * mips_machine_is_compatible() - check if a machine is compatible with an FDT
+ * @mach: the machine struct to check
+ * @fdt: the FDT to check for compatibility with
+ *
+ * Check whether the given machine @mach is compatible with the given flattened
+ * device tree @fdt, based upon the compatibility property of the root node.
+ *
+ * Return: the device id matched if any, else NULL
+ */
+static inline const struct of_device_id *
+mips_machine_is_compatible(const struct mips_machine *mach, const void *fdt)
+{
+ const struct of_device_id *match;
+
+ if (!mach->matches)
+ return NULL;
+
+ for (match = mach->matches; match->compatible; match++) {
+ if (fdt_node_check_compatible(fdt, 0, match->compatible) == 0)
+ return match;
+ }
+
+ return NULL;
+}
+
+#endif /* __MIPS_ASM_MACHINE_H__ */
diff --git a/arch/mips/include/asm/mips-boards/sead3int.h b/arch/mips/include/asm/mips-boards/sead3int.h
deleted file mode 100644
index 8932c7d..0000000
--- a/arch/mips/include/asm/mips-boards/sead3int.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2000,2012 MIPS Technologies, Inc. All rights reserved.
- * Douglas Leung <douglas@mips.com>
- * Steven J. Hill <sjhill@mips.com>
- */
-#ifndef _MIPS_SEAD3INT_H
-#define _MIPS_SEAD3INT_H
-
-#include <linux/irqchip/mips-gic.h>
-
-/* SEAD-3 GIC address space definitions. */
-#define GIC_BASE_ADDR 0x1b1c0000
-#define GIC_ADDRSPACE_SZ (128 * 1024)
-
-/* CPU interrupt offsets */
-#define CPU_INT_GIC 2
-#define CPU_INT_EHCI 2
-#define CPU_INT_UART0 4
-#define CPU_INT_UART1 4
-#define CPU_INT_NET 6
-
-/* GIC interrupt offsets */
-#define GIC_INT_NET GIC_SHARED_TO_HWIRQ(0)
-#define GIC_INT_UART1 GIC_SHARED_TO_HWIRQ(2)
-#define GIC_INT_UART0 GIC_SHARED_TO_HWIRQ(3)
-#define GIC_INT_EHCI GIC_SHARED_TO_HWIRQ(5)
-
-#endif /* !(_MIPS_SEAD3INT_H) */
diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h
index 4fafeef..2e41807 100644
--- a/arch/mips/include/asm/mips-cm.h
+++ b/arch/mips/include/asm/mips-cm.h
@@ -359,6 +359,7 @@ BUILD_CM_Cx_R_(tcid_8_priority, 0x80)
/* GCR_Cx_COHERENCE register fields */
#define CM_GCR_Cx_COHERENCE_COHDOMAINEN_SHF 0
#define CM_GCR_Cx_COHERENCE_COHDOMAINEN_MSK (_ULCAST_(0xff) << 0)
+#define CM3_GCR_Cx_COHERENCE_COHEN_MSK (_ULCAST_(0x1) << 0)
/* GCR_Cx_CONFIG register fields */
#define CM_GCR_Cx_CONFIG_IOCUTYPE_SHF 10
diff --git a/arch/mips/include/asm/octeon/cvmx-helper-board.h b/arch/mips/include/asm/octeon/cvmx-helper-board.h
index cda93ae..b4d19c21 100644
--- a/arch/mips/include/asm/octeon/cvmx-helper-board.h
+++ b/arch/mips/include/asm/octeon/cvmx-helper-board.h
@@ -58,16 +58,6 @@ typedef enum {
#define CVMX_HELPER_BOARD_MGMT_IPD_PORT -10
/**
- * cvmx_override_board_link_get(int ipd_port) is a function
- * pointer. It is meant to allow customization of the process of
- * talking to a PHY to determine link speed. It is called every
- * time a PHY must be polled for link status. Users should set
- * this pointer to a function before calling any cvmx-helper
- * operations.
- */
-extern cvmx_helper_link_info_t(*cvmx_override_board_link_get) (int ipd_port);
-
-/**
* Return the MII PHY address associated with the given IPD
* port. A result of -1 means there isn't a MII capable PHY
* connected to this port. On chips supporting multiple MII
@@ -86,26 +76,6 @@ extern cvmx_helper_link_info_t(*cvmx_override_board_link_get) (int ipd_port);
extern int cvmx_helper_board_get_mii_address(int ipd_port);
/**
- * This function as a board specific method of changing the PHY
- * speed, duplex, and autonegotiation. This programs the PHY and
- * not Octeon. This can be used to force Octeon's links to
- * specific settings.
- *
- * @phy_addr: The address of the PHY to program
- * @link_flags:
- * Flags to control autonegotiation. Bit 0 is autonegotiation
- * enable/disable to maintain backward compatibility.
- * @link_info: Link speed to program. If the speed is zero and autonegotiation
- * is enabled, all possible negotiation speeds are advertised.
- *
- * Returns Zero on success, negative on failure
- */
-int cvmx_helper_board_link_set_phy(int phy_addr,
- cvmx_helper_board_set_phy_link_flags_types_t
- link_flags,
- cvmx_helper_link_info_t link_info);
-
-/**
* This function is the board specific method of determining an
* ethernet ports link speed. Most Octeon boards have Marvell PHYs
* and are handled by the fall through case. This function must be
diff --git a/arch/mips/include/asm/octeon/cvmx-mdio.h b/arch/mips/include/asm/octeon/cvmx-mdio.h
deleted file mode 100644
index 9f6a4f3..0000000
--- a/arch/mips/include/asm/octeon/cvmx-mdio.h
+++ /dev/null
@@ -1,506 +0,0 @@
-/***********************license start***************
- * Author: Cavium Networks
- *
- * Contact: support@caviumnetworks.com
- * This file is part of the OCTEON SDK
- *
- * Copyright (c) 2003-2008 Cavium Networks
- *
- * This file is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, Version 2, as
- * published by the Free Software Foundation.
- *
- * This file is distributed in the hope that it will be useful, but
- * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
- * NONINFRINGEMENT. See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this file; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- * or visit http://www.gnu.org/licenses/.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium Networks for more information
- ***********************license end**************************************/
-
-/*
- *
- * Interface to the SMI/MDIO hardware, including support for both IEEE 802.3
- * clause 22 and clause 45 operations.
- *
- */
-
-#ifndef __CVMX_MIO_H__
-#define __CVMX_MIO_H__
-
-#include <asm/octeon/cvmx-smix-defs.h>
-
-/**
- * PHY register 0 from the 802.3 spec
- */
-#define CVMX_MDIO_PHY_REG_CONTROL 0
-typedef union {
- uint16_t u16;
- struct {
- uint16_t reset:1;
- uint16_t loopback:1;
- uint16_t speed_lsb:1;
- uint16_t autoneg_enable:1;
- uint16_t power_down:1;
- uint16_t isolate:1;
- uint16_t restart_autoneg:1;
- uint16_t duplex:1;
- uint16_t collision_test:1;
- uint16_t speed_msb:1;
- uint16_t unidirectional_enable:1;
- uint16_t reserved_0_4:5;
- } s;
-} cvmx_mdio_phy_reg_control_t;
-
-/**
- * PHY register 1 from the 802.3 spec
- */
-#define CVMX_MDIO_PHY_REG_STATUS 1
-typedef union {
- uint16_t u16;
- struct {
- uint16_t capable_100base_t4:1;
- uint16_t capable_100base_x_full:1;
- uint16_t capable_100base_x_half:1;
- uint16_t capable_10_full:1;
- uint16_t capable_10_half:1;
- uint16_t capable_100base_t2_full:1;
- uint16_t capable_100base_t2_half:1;
- uint16_t capable_extended_status:1;
- uint16_t capable_unidirectional:1;
- uint16_t capable_mf_preamble_suppression:1;
- uint16_t autoneg_complete:1;
- uint16_t remote_fault:1;
- uint16_t capable_autoneg:1;
- uint16_t link_status:1;
- uint16_t jabber_detect:1;
- uint16_t capable_extended_registers:1;
-
- } s;
-} cvmx_mdio_phy_reg_status_t;
-
-/**
- * PHY register 2 from the 802.3 spec
- */
-#define CVMX_MDIO_PHY_REG_ID1 2
-typedef union {
- uint16_t u16;
- struct {
- uint16_t oui_bits_3_18;
- } s;
-} cvmx_mdio_phy_reg_id1_t;
-
-/**
- * PHY register 3 from the 802.3 spec
- */
-#define CVMX_MDIO_PHY_REG_ID2 3
-typedef union {
- uint16_t u16;
- struct {
- uint16_t oui_bits_19_24:6;
- uint16_t model:6;
- uint16_t revision:4;
- } s;
-} cvmx_mdio_phy_reg_id2_t;
-
-/**
- * PHY register 4 from the 802.3 spec
- */
-#define CVMX_MDIO_PHY_REG_AUTONEG_ADVER 4
-typedef union {
- uint16_t u16;
- struct {
- uint16_t next_page:1;
- uint16_t reserved_14:1;
- uint16_t remote_fault:1;
- uint16_t reserved_12:1;
- uint16_t asymmetric_pause:1;
- uint16_t pause:1;
- uint16_t advert_100base_t4:1;
- uint16_t advert_100base_tx_full:1;
- uint16_t advert_100base_tx_half:1;
- uint16_t advert_10base_tx_full:1;
- uint16_t advert_10base_tx_half:1;
- uint16_t selector:5;
- } s;
-} cvmx_mdio_phy_reg_autoneg_adver_t;
-
-/**
- * PHY register 5 from the 802.3 spec
- */
-#define CVMX_MDIO_PHY_REG_LINK_PARTNER_ABILITY 5
-typedef union {
- uint16_t u16;
- struct {
- uint16_t next_page:1;
- uint16_t ack:1;
- uint16_t remote_fault:1;
- uint16_t reserved_12:1;
- uint16_t asymmetric_pause:1;
- uint16_t pause:1;
- uint16_t advert_100base_t4:1;
- uint16_t advert_100base_tx_full:1;
- uint16_t advert_100base_tx_half:1;
- uint16_t advert_10base_tx_full:1;
- uint16_t advert_10base_tx_half:1;
- uint16_t selector:5;
- } s;
-} cvmx_mdio_phy_reg_link_partner_ability_t;
-
-/**
- * PHY register 6 from the 802.3 spec
- */
-#define CVMX_MDIO_PHY_REG_AUTONEG_EXPANSION 6
-typedef union {
- uint16_t u16;
- struct {
- uint16_t reserved_5_15:11;
- uint16_t parallel_detection_fault:1;
- uint16_t link_partner_next_page_capable:1;
- uint16_t local_next_page_capable:1;
- uint16_t page_received:1;
- uint16_t link_partner_autoneg_capable:1;
-
- } s;
-} cvmx_mdio_phy_reg_autoneg_expansion_t;
-
-/**
- * PHY register 9 from the 802.3 spec
- */
-#define CVMX_MDIO_PHY_REG_CONTROL_1000 9
-typedef union {
- uint16_t u16;
- struct {
- uint16_t test_mode:3;
- uint16_t manual_master_slave:1;
- uint16_t master:1;
- uint16_t port_type:1;
- uint16_t advert_1000base_t_full:1;
- uint16_t advert_1000base_t_half:1;
- uint16_t reserved_0_7:8;
- } s;
-} cvmx_mdio_phy_reg_control_1000_t;
-
-/**
- * PHY register 10 from the 802.3 spec
- */
-#define CVMX_MDIO_PHY_REG_STATUS_1000 10
-typedef union {
- uint16_t u16;
- struct {
- uint16_t master_slave_fault:1;
- uint16_t is_master:1;
- uint16_t local_receiver_ok:1;
- uint16_t remote_receiver_ok:1;
- uint16_t remote_capable_1000base_t_full:1;
- uint16_t remote_capable_1000base_t_half:1;
- uint16_t reserved_8_9:2;
- uint16_t idle_error_count:8;
- } s;
-} cvmx_mdio_phy_reg_status_1000_t;
-
-/**
- * PHY register 15 from the 802.3 spec
- */
-#define CVMX_MDIO_PHY_REG_EXTENDED_STATUS 15
-typedef union {
- uint16_t u16;
- struct {
- uint16_t capable_1000base_x_full:1;
- uint16_t capable_1000base_x_half:1;
- uint16_t capable_1000base_t_full:1;
- uint16_t capable_1000base_t_half:1;
- uint16_t reserved_0_11:12;
- } s;
-} cvmx_mdio_phy_reg_extended_status_t;
-
-/**
- * PHY register 13 from the 802.3 spec
- */
-#define CVMX_MDIO_PHY_REG_MMD_CONTROL 13
-typedef union {
- uint16_t u16;
- struct {
- uint16_t function:2;
- uint16_t reserved_5_13:9;
- uint16_t devad:5;
- } s;
-} cvmx_mdio_phy_reg_mmd_control_t;
-
-/**
- * PHY register 14 from the 802.3 spec
- */
-#define CVMX_MDIO_PHY_REG_MMD_ADDRESS_DATA 14
-typedef union {
- uint16_t u16;
- struct {
- uint16_t address_data:16;
- } s;
-} cvmx_mdio_phy_reg_mmd_address_data_t;
-
-/* Operating request encodings. */
-#define MDIO_CLAUSE_22_WRITE 0
-#define MDIO_CLAUSE_22_READ 1
-
-#define MDIO_CLAUSE_45_ADDRESS 0
-#define MDIO_CLAUSE_45_WRITE 1
-#define MDIO_CLAUSE_45_READ_INC 2
-#define MDIO_CLAUSE_45_READ 3
-
-/* MMD identifiers, mostly for accessing devices within XENPAK modules. */
-#define CVMX_MMD_DEVICE_PMA_PMD 1
-#define CVMX_MMD_DEVICE_WIS 2
-#define CVMX_MMD_DEVICE_PCS 3
-#define CVMX_MMD_DEVICE_PHY_XS 4
-#define CVMX_MMD_DEVICE_DTS_XS 5
-#define CVMX_MMD_DEVICE_TC 6
-#define CVMX_MMD_DEVICE_CL22_EXT 29
-#define CVMX_MMD_DEVICE_VENDOR_1 30
-#define CVMX_MMD_DEVICE_VENDOR_2 31
-
-/* Helper function to put MDIO interface into clause 45 mode */
-static inline void __cvmx_mdio_set_clause45_mode(int bus_id)
-{
- union cvmx_smix_clk smi_clk;
- /* Put bus into clause 45 mode */
- smi_clk.u64 = cvmx_read_csr(CVMX_SMIX_CLK(bus_id));
- smi_clk.s.mode = 1;
- smi_clk.s.preamble = 1;
- cvmx_write_csr(CVMX_SMIX_CLK(bus_id), smi_clk.u64);
-}
-
-/* Helper function to put MDIO interface into clause 22 mode */
-static inline void __cvmx_mdio_set_clause22_mode(int bus_id)
-{
- union cvmx_smix_clk smi_clk;
- /* Put bus into clause 22 mode */
- smi_clk.u64 = cvmx_read_csr(CVMX_SMIX_CLK(bus_id));
- smi_clk.s.mode = 0;
- cvmx_write_csr(CVMX_SMIX_CLK(bus_id), smi_clk.u64);
-}
-
-/**
- * Perform an MII read. This function is used to read PHY
- * registers controlling auto negotiation.
- *
- * @bus_id: MDIO bus number. Zero on most chips, but some chips (ex CN56XX)
- * support multiple busses.
- * @phy_id: The MII phy id
- * @location: Register location to read
- *
- * Returns Result from the read or -1 on failure
- */
-static inline int cvmx_mdio_read(int bus_id, int phy_id, int location)
-{
- union cvmx_smix_cmd smi_cmd;
- union cvmx_smix_rd_dat smi_rd;
- int timeout = 1000;
-
- if (octeon_has_feature(OCTEON_FEATURE_MDIO_CLAUSE_45))
- __cvmx_mdio_set_clause22_mode(bus_id);
-
- smi_cmd.u64 = 0;
- smi_cmd.s.phy_op = MDIO_CLAUSE_22_READ;
- smi_cmd.s.phy_adr = phy_id;
- smi_cmd.s.reg_adr = location;
- cvmx_write_csr(CVMX_SMIX_CMD(bus_id), smi_cmd.u64);
-
- do {
- cvmx_wait(1000);
- smi_rd.u64 = cvmx_read_csr(CVMX_SMIX_RD_DAT(bus_id));
- } while (smi_rd.s.pending && timeout--);
-
- if (smi_rd.s.val)
- return smi_rd.s.dat;
- else
- return -1;
-}
-
-/**
- * Perform an MII write. This function is used to write PHY
- * registers controlling auto negotiation.
- *
- * @bus_id: MDIO bus number. Zero on most chips, but some chips (ex CN56XX)
- * support multiple busses.
- * @phy_id: The MII phy id
- * @location: Register location to write
- * @val: Value to write
- *
- * Returns -1 on error
- * 0 on success
- */
-static inline int cvmx_mdio_write(int bus_id, int phy_id, int location, int val)
-{
- union cvmx_smix_cmd smi_cmd;
- union cvmx_smix_wr_dat smi_wr;
- int timeout = 1000;
-
- if (octeon_has_feature(OCTEON_FEATURE_MDIO_CLAUSE_45))
- __cvmx_mdio_set_clause22_mode(bus_id);
-
- smi_wr.u64 = 0;
- smi_wr.s.dat = val;
- cvmx_write_csr(CVMX_SMIX_WR_DAT(bus_id), smi_wr.u64);
-
- smi_cmd.u64 = 0;
- smi_cmd.s.phy_op = MDIO_CLAUSE_22_WRITE;
- smi_cmd.s.phy_adr = phy_id;
- smi_cmd.s.reg_adr = location;
- cvmx_write_csr(CVMX_SMIX_CMD(bus_id), smi_cmd.u64);
-
- do {
- cvmx_wait(1000);
- smi_wr.u64 = cvmx_read_csr(CVMX_SMIX_WR_DAT(bus_id));
- } while (smi_wr.s.pending && --timeout);
- if (timeout <= 0)
- return -1;
-
- return 0;
-}
-
-/**
- * Perform an IEEE 802.3 clause 45 MII read. This function is used to
- * read PHY registers controlling auto negotiation.
- *
- * @bus_id: MDIO bus number. Zero on most chips, but some chips (ex CN56XX)
- * support multiple busses.
- * @phy_id: The MII phy id
- * @device: MDIO Managable Device (MMD) id
- * @location: Register location to read
- *
- * Returns Result from the read or -1 on failure
- */
-
-static inline int cvmx_mdio_45_read(int bus_id, int phy_id, int device,
- int location)
-{
- union cvmx_smix_cmd smi_cmd;
- union cvmx_smix_rd_dat smi_rd;
- union cvmx_smix_wr_dat smi_wr;
- int timeout = 1000;
-
- if (!octeon_has_feature(OCTEON_FEATURE_MDIO_CLAUSE_45))
- return -1;
-
- __cvmx_mdio_set_clause45_mode(bus_id);
-
- smi_wr.u64 = 0;
- smi_wr.s.dat = location;
- cvmx_write_csr(CVMX_SMIX_WR_DAT(bus_id), smi_wr.u64);
-
- smi_cmd.u64 = 0;
- smi_cmd.s.phy_op = MDIO_CLAUSE_45_ADDRESS;
- smi_cmd.s.phy_adr = phy_id;
- smi_cmd.s.reg_adr = device;
- cvmx_write_csr(CVMX_SMIX_CMD(bus_id), smi_cmd.u64);
-
- do {
- cvmx_wait(1000);
- smi_wr.u64 = cvmx_read_csr(CVMX_SMIX_WR_DAT(bus_id));
- } while (smi_wr.s.pending && --timeout);
- if (timeout <= 0) {
- cvmx_dprintf("cvmx_mdio_45_read: bus_id %d phy_id %2d "
- "device %2d register %2d TIME OUT(address)\n",
- bus_id, phy_id, device, location);
- return -1;
- }
-
- smi_cmd.u64 = 0;
- smi_cmd.s.phy_op = MDIO_CLAUSE_45_READ;
- smi_cmd.s.phy_adr = phy_id;
- smi_cmd.s.reg_adr = device;
- cvmx_write_csr(CVMX_SMIX_CMD(bus_id), smi_cmd.u64);
-
- do {
- cvmx_wait(1000);
- smi_rd.u64 = cvmx_read_csr(CVMX_SMIX_RD_DAT(bus_id));
- } while (smi_rd.s.pending && --timeout);
-
- if (timeout <= 0) {
- cvmx_dprintf("cvmx_mdio_45_read: bus_id %d phy_id %2d "
- "device %2d register %2d TIME OUT(data)\n",
- bus_id, phy_id, device, location);
- return -1;
- }
-
- if (smi_rd.s.val)
- return smi_rd.s.dat;
- else {
- cvmx_dprintf("cvmx_mdio_45_read: bus_id %d phy_id %2d "
- "device %2d register %2d INVALID READ\n",
- bus_id, phy_id, device, location);
- return -1;
- }
-}
-
-/**
- * Perform an IEEE 802.3 clause 45 MII write. This function is used to
- * write PHY registers controlling auto negotiation.
- *
- * @bus_id: MDIO bus number. Zero on most chips, but some chips (ex CN56XX)
- * support multiple busses.
- * @phy_id: The MII phy id
- * @device: MDIO Managable Device (MMD) id
- * @location: Register location to write
- * @val: Value to write
- *
- * Returns -1 on error
- * 0 on success
- */
-static inline int cvmx_mdio_45_write(int bus_id, int phy_id, int device,
- int location, int val)
-{
- union cvmx_smix_cmd smi_cmd;
- union cvmx_smix_wr_dat smi_wr;
- int timeout = 1000;
-
- if (!octeon_has_feature(OCTEON_FEATURE_MDIO_CLAUSE_45))
- return -1;
-
- __cvmx_mdio_set_clause45_mode(bus_id);
-
- smi_wr.u64 = 0;
- smi_wr.s.dat = location;
- cvmx_write_csr(CVMX_SMIX_WR_DAT(bus_id), smi_wr.u64);
-
- smi_cmd.u64 = 0;
- smi_cmd.s.phy_op = MDIO_CLAUSE_45_ADDRESS;
- smi_cmd.s.phy_adr = phy_id;
- smi_cmd.s.reg_adr = device;
- cvmx_write_csr(CVMX_SMIX_CMD(bus_id), smi_cmd.u64);
-
- do {
- cvmx_wait(1000);
- smi_wr.u64 = cvmx_read_csr(CVMX_SMIX_WR_DAT(bus_id));
- } while (smi_wr.s.pending && --timeout);
- if (timeout <= 0)
- return -1;
-
- smi_wr.u64 = 0;
- smi_wr.s.dat = val;
- cvmx_write_csr(CVMX_SMIX_WR_DAT(bus_id), smi_wr.u64);
-
- smi_cmd.u64 = 0;
- smi_cmd.s.phy_op = MDIO_CLAUSE_45_WRITE;
- smi_cmd.s.phy_adr = phy_id;
- smi_cmd.s.reg_adr = device;
- cvmx_write_csr(CVMX_SMIX_CMD(bus_id), smi_cmd.u64);
-
- do {
- cvmx_wait(1000);
- smi_wr.u64 = cvmx_read_csr(CVMX_SMIX_WR_DAT(bus_id));
- } while (smi_wr.s.pending && --timeout);
- if (timeout <= 0)
- return -1;
-
- return 0;
-}
-
-#endif
diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h
index 9b63cd4..30d1129 100644
--- a/arch/mips/include/asm/pci.h
+++ b/arch/mips/include/asm/pci.h
@@ -17,15 +17,18 @@
*/
#include <linux/ioport.h>
+#include <linux/list.h>
#include <linux/of.h>
+#ifdef CONFIG_PCI_DRIVERS_LEGACY
+
/*
* Each pci channel is a top-level PCI bus seem by CPU. A machine with
* multiple PCI channels may have multiple PCI host controllers or a
* single controller supporting multiple channels.
*/
struct pci_controller {
- struct pci_controller *next;
+ struct list_head list;
struct pci_bus *bus;
struct device_node *of_node;
@@ -38,10 +41,12 @@ struct pci_controller {
struct resource *busn_resource;
unsigned long busn_offset;
+#ifndef CONFIG_PCI_DOMAINS_GENERIC
unsigned int index;
/* For compatibility with current (as of July 2003) pciutils
and XFree86. Eventually will be removed. */
unsigned int need_domain_info;
+#endif
/* Optional access methods for reading/writing the bus number
of the PCI controller */
@@ -59,12 +64,43 @@ extern void register_pci_controller(struct pci_controller *hose);
*/
extern int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin);
+/* Do platform specific device initialization at pci_enable_device() time */
+extern int pcibios_plat_dev_init(struct pci_dev *dev);
+
+extern char * (*pcibios_plat_setup)(char *str);
+
+#ifdef CONFIG_OF
+/* this function parses memory ranges from a device node */
+extern void pci_load_of_ranges(struct pci_controller *hose,
+ struct device_node *node);
+#else
+static inline void pci_load_of_ranges(struct pci_controller *hose,
+ struct device_node *node) {}
+#endif
+
+#ifdef CONFIG_PCI_DOMAINS_GENERIC
+static inline void set_pci_need_domain_info(struct pci_controller *hose,
+ int need_domain_info)
+{
+ /* nothing to do */
+}
+#elif defined(CONFIG_PCI_DOMAINS)
+static inline void set_pci_need_domain_info(struct pci_controller *hose,
+ int need_domain_info)
+{
+ hose->need_domain_info = need_domain_info;
+}
+#endif /* CONFIG_PCI_DOMAINS */
+
+#endif
/* Can be used to override the logic in pci_scan_bus for skipping
already-configured bus numbers - to be used for buggy BIOSes
or architectures with incomplete PCI setup by the loader */
-
-extern unsigned int pcibios_assign_all_busses(void);
+static inline unsigned int pcibios_assign_all_busses(void)
+{
+ return 1;
+}
extern unsigned long PCIBIOS_MIN_IO;
extern unsigned long PCIBIOS_MIN_MEM;
@@ -100,7 +136,12 @@ struct pci_dev;
*/
#define PCI_DMA_BUS_IS_PHYS (1)
-#ifdef CONFIG_PCI_DOMAINS
+#ifdef CONFIG_PCI_DOMAINS_GENERIC
+static inline int pci_proc_domain(struct pci_bus *bus)
+{
+ return pci_domain_nr(bus);
+}
+#elif defined(CONFIG_PCI_DOMAINS)
#define pci_domain_nr(bus) ((struct pci_controller *)(bus)->sysdata)->index
static inline int pci_proc_domain(struct pci_bus *bus)
@@ -121,15 +162,4 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
return channel ? 15 : 14;
}
-extern char * (*pcibios_plat_setup)(char *str);
-
-#ifdef CONFIG_OF
-/* this function parses memory ranges from a device node */
-extern void pci_load_of_ranges(struct pci_controller *hose,
- struct device_node *node);
-#else
-static inline void pci_load_of_ranges(struct pci_controller *hose,
- struct device_node *node) {}
-#endif
-
#endif /* _ASM_PCI_H */
diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h
index 93c079a..a03e869 100644
--- a/arch/mips/include/asm/pgalloc.h
+++ b/arch/mips/include/asm/pgalloc.h
@@ -67,11 +67,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
unsigned long address)
{
- pte_t *pte;
-
- pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER);
-
- return pte;
+ return (pte_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, PTE_ORDER);
}
static inline struct page *pte_alloc_one(struct mm_struct *mm,
diff --git a/arch/mips/include/asm/pm-cps.h b/arch/mips/include/asm/pm-cps.h
index 625eda5..89d58d8 100644
--- a/arch/mips/include/asm/pm-cps.h
+++ b/arch/mips/include/asm/pm-cps.h
@@ -13,10 +13,12 @@
/*
* The CM & CPC can only handle coherence & power control on a per-core basis,
- * thus in an MT system the VPEs within each core are coupled and can only
+ * thus in an MT system the VP(E)s within each core are coupled and can only
* enter or exit states requiring CM or CPC assistance in unison.
*/
-#ifdef CONFIG_MIPS_MT
+#if defined(CONFIG_CPU_MIPSR6)
+# define coupled_coherence cpu_has_vp
+#elif defined(CONFIG_MIPS_MT)
# define coupled_coherence cpu_has_mipsmt
#else
# define coupled_coherence 0
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index f6fc6aa..b657861 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -152,7 +152,7 @@ static inline int is_syscall_success(struct pt_regs *regs)
static inline long regs_return_value(struct pt_regs *regs)
{
- if (is_syscall_success(regs))
+ if (is_syscall_success(regs) || !user_mode(regs))
return regs->regs[2];
else
return -regs->regs[2];
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index 8bc6c70..060f23f 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -85,6 +85,20 @@ static inline void __cpu_die(unsigned int cpu)
extern void play_dead(void);
#endif
+/*
+ * This function will set up the necessary IPIs for Linux to communicate
+ * with the CPUs in mask.
+ * Return 0 on success.
+ */
+int mips_smp_ipi_allocate(const struct cpumask *mask);
+
+/*
+ * This function will free up IPIs allocated with mips_smp_ipi_allocate to the
+ * CPUs in mask, which must be a subset of the IPIs that have been configured.
+ * Return 0 on success.
+ */
+int mips_smp_ipi_free(const struct cpumask *mask);
+
static inline void arch_send_call_function_single_ipi(int cpu)
{
extern struct plat_smp_ops *mp_ops; /* private */
diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h
index ebb5c0f..c0ae279 100644
--- a/arch/mips/include/asm/switch_to.h
+++ b/arch/mips/include/asm/switch_to.h
@@ -76,6 +76,22 @@ do { if (cpu_has_rw_llb) { \
} while (0)
/*
+ * Check FCSR for any unmasked exceptions pending set with `ptrace',
+ * clear them and send a signal.
+ */
+#define __sanitize_fcr31(next) \
+do { \
+ unsigned long fcr31 = mask_fcr31_x(next->thread.fpu.fcr31); \
+ void __user *pc; \
+ \
+ if (unlikely(fcr31)) { \
+ pc = (void __user *)task_pt_regs(next)->cp0_epc; \
+ next->thread.fpu.fcr31 &= ~fcr31; \
+ force_fcr31_sig(fcr31, pc, next); \
+ } \
+} while (0)
+
+/*
* For newly created kernel threads switch_to() will return to
* ret_from_kernel_thread, newly created user threads to ret_from_fork.
* That is, everything following resume() will be skipped for new threads.
@@ -85,6 +101,8 @@ do { if (cpu_has_rw_llb) { \
do { \
__mips_mt_fpaff_switch_to(prev); \
lose_fpu_inatomic(1, prev); \
+ if (tsk_used_math(next)) \
+ __sanitize_fcr31(next); \
if (cpu_has_dsp) { \
__save_dsp(prev); \
__restore_dsp(next); \
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index 4daf839..89fa5c0b 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -859,7 +859,10 @@ extern size_t __copy_user(void *__to, const void *__from, size_t __n);
__cu_to = (to); \
__cu_from = (from); \
__cu_len = (n); \
+ \
+ check_object_size(__cu_from, __cu_len, true); \
might_fault(); \
+ \
if (eva_kernel_access()) \
__cu_len = __invoke_copy_to_kernel(__cu_to, __cu_from, \
__cu_len); \
@@ -880,6 +883,9 @@ extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
__cu_to = (to); \
__cu_from = (from); \
__cu_len = (n); \
+ \
+ check_object_size(__cu_from, __cu_len, true); \
+ \
if (eva_kernel_access()) \
__cu_len = __invoke_copy_to_kernel(__cu_to, __cu_from, \
__cu_len); \
@@ -898,6 +904,9 @@ extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
__cu_to = (to); \
__cu_from = (from); \
__cu_len = (n); \
+ \
+ check_object_size(__cu_to, __cu_len, false); \
+ \
if (eva_kernel_access()) \
__cu_len = __invoke_copy_from_kernel_inatomic(__cu_to, \
__cu_from,\
@@ -932,6 +941,9 @@ extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
__cu_to = (to); \
__cu_from = (from); \
__cu_len = (n); \
+ \
+ check_object_size(__cu_from, __cu_len, true); \
+ \
if (eva_kernel_access()) { \
__cu_len = __invoke_copy_to_kernel(__cu_to, \
__cu_from, \
@@ -1124,6 +1136,9 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n);
__cu_to = (to); \
__cu_from = (from); \
__cu_len = (n); \
+ \
+ check_object_size(__cu_to, __cu_len, false); \
+ \
if (eva_kernel_access()) { \
__cu_len = __invoke_copy_from_kernel(__cu_to, \
__cu_from, \
@@ -1162,6 +1177,9 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n);
__cu_to = (to); \
__cu_from = (from); \
__cu_len = (n); \
+ \
+ check_object_size(__cu_to, __cu_len, false); \
+ \
if (eva_kernel_access()) { \
__cu_len = __invoke_copy_from_kernel(__cu_to, \
__cu_from, \
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index 24ad815..3e940db 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -383,16 +383,20 @@
#define __NR_copy_file_range (__NR_Linux + 360)
#define __NR_preadv2 (__NR_Linux + 361)
#define __NR_pwritev2 (__NR_Linux + 362)
+#define __NR_pkey_mprotect (__NR_Linux + 363)
+#define __NR_pkey_alloc (__NR_Linux + 364)
+#define __NR_pkey_free (__NR_Linux + 365)
+
/*
* Offset of the last Linux o32 flavoured syscall
*/
-#define __NR_Linux_syscalls 362
+#define __NR_Linux_syscalls 365
#endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
#define __NR_O32_Linux 4000
-#define __NR_O32_Linux_syscalls 362
+#define __NR_O32_Linux_syscalls 365
#if _MIPS_SIM == _MIPS_SIM_ABI64
@@ -723,16 +727,19 @@
#define __NR_copy_file_range (__NR_Linux + 320)
#define __NR_preadv2 (__NR_Linux + 321)
#define __NR_pwritev2 (__NR_Linux + 322)
+#define __NR_pkey_mprotect (__NR_Linux + 323)
+#define __NR_pkey_alloc (__NR_Linux + 324)
+#define __NR_pkey_free (__NR_Linux + 325)
/*
* Offset of the last Linux 64-bit flavoured syscall
*/
-#define __NR_Linux_syscalls 322
+#define __NR_Linux_syscalls 325
#endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
#define __NR_64_Linux 5000
-#define __NR_64_Linux_syscalls 322
+#define __NR_64_Linux_syscalls 325
#if _MIPS_SIM == _MIPS_SIM_NABI32
@@ -1067,15 +1074,18 @@
#define __NR_copy_file_range (__NR_Linux + 324)
#define __NR_preadv2 (__NR_Linux + 325)
#define __NR_pwritev2 (__NR_Linux + 326)
+#define __NR_pkey_mprotect (__NR_Linux + 327)
+#define __NR_pkey_alloc (__NR_Linux + 328)
+#define __NR_pkey_free (__NR_Linux + 329)
/*
* Offset of the last N32 flavoured syscall
*/
-#define __NR_Linux_syscalls 326
+#define __NR_Linux_syscalls 329
#endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
#define __NR_N32_Linux 6000
-#define __NR_N32_Linux_syscalls 326
+#define __NR_N32_Linux_syscalls 329
#endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c
index 58ad63d..9c7f3e1 100644
--- a/arch/mips/kernel/binfmt_elfn32.c
+++ b/arch/mips/kernel/binfmt_elfn32.c
@@ -1,5 +1,6 @@
/*
* Support for n32 Linux/MIPS ELF binaries.
+ * Author: Ralf Baechle (ralf@linux-mips.org)
*
* Copyright (C) 1999, 2001 Ralf Baechle
* Copyright (C) 1999, 2001 Silicon Graphics, Inc.
@@ -37,7 +38,6 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
#define ELF_ET_DYN_BASE (TASK32_SIZE / 3 * 2)
#include <asm/processor.h>
-#include <linux/module.h>
#include <linux/elfcore.h>
#include <linux/compat.h>
#include <linux/math64.h>
@@ -96,12 +96,6 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value)
#define ELF_CORE_EFLAGS EF_MIPS_ABI2
-MODULE_DESCRIPTION("Binary format loader for compatibility with n32 Linux/MIPS binaries");
-MODULE_AUTHOR("Ralf Baechle (ralf@linux-mips.org)");
-
-#undef MODULE_DESCRIPTION
-#undef MODULE_AUTHOR
-
#undef TASK_SIZE
#define TASK_SIZE TASK_SIZE32
diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c
index 49fb881..1ab3432 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -1,5 +1,6 @@
/*
* Support for o32 Linux/MIPS ELF binaries.
+ * Author: Ralf Baechle (ralf@linux-mips.org)
*
* Copyright (C) 1999, 2001 Ralf Baechle
* Copyright (C) 1999, 2001 Silicon Graphics, Inc.
@@ -42,7 +43,6 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
#include <asm/processor.h>
-#include <linux/module.h>
#include <linux/elfcore.h>
#include <linux/compat.h>
#include <linux/math64.h>
@@ -99,12 +99,6 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value)
value->tv_usec = rem / NSEC_PER_USEC;
}
-MODULE_DESCRIPTION("Binary format loader for compatibility with o32 Linux/MIPS binaries");
-MODULE_AUTHOR("Ralf Baechle (ralf@linux-mips.org)");
-
-#undef MODULE_DESCRIPTION
-#undef MODULE_AUTHOR
-
#undef TASK_SIZE
#define TASK_SIZE TASK_SIZE32
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index 46c227f..12c7181 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -9,7 +9,7 @@
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/signal.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <asm/branch.h>
#include <asm/cpu.h>
#include <asm/cpu-features.h>
@@ -866,3 +866,37 @@ int __compute_return_epc(struct pt_regs *regs)
force_sig(SIGBUS, current);
return -EFAULT;
}
+
+#if (defined CONFIG_KPROBES) || (defined CONFIG_UPROBES)
+
+int __insn_is_compact_branch(union mips_instruction insn)
+{
+ if (!cpu_has_mips_r6)
+ return 0;
+
+ switch (insn.i_format.opcode) {
+ case blezl_op:
+ case bgtzl_op:
+ case blez_op:
+ case bgtz_op:
+ /*
+ * blez[l] and bgtz[l] opcodes with non-zero rt
+ * are MIPS R6 compact branches
+ */
+ if (insn.i_format.rt)
+ return 1;
+ break;
+ case bc6_op:
+ case balc6_op:
+ case pop10_op:
+ case pop30_op:
+ case pop66_op:
+ case pop76_op:
+ return 1;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(__insn_is_compact_branch);
+
+#endif /* CONFIG_KPROBES || CONFIG_UPROBES */
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index 212f46f..f5c8bce 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -32,7 +32,8 @@
#include <asm/ptrace.h>
#include <asm/branch.h>
#include <asm/break.h>
-#include <asm/inst.h>
+
+#include "probes-common.h"
static const union mips_instruction breakpoint_insn = {
.b_format = {
@@ -55,63 +56,7 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
static int __kprobes insn_has_delayslot(union mips_instruction insn)
{
- switch (insn.i_format.opcode) {
-
- /*
- * This group contains:
- * jr and jalr are in r_format format.
- */
- case spec_op:
- switch (insn.r_format.func) {
- case jr_op:
- case jalr_op:
- break;
- default:
- goto insn_ok;
- }
-
- /*
- * This group contains:
- * bltz_op, bgez_op, bltzl_op, bgezl_op,
- * bltzal_op, bgezal_op, bltzall_op, bgezall_op.
- */
- case bcond_op:
-
- /*
- * These are unconditional and in j_format.
- */
- case jal_op:
- case j_op:
-
- /*
- * These are conditional and in i_format.
- */
- case beq_op:
- case beql_op:
- case bne_op:
- case bnel_op:
- case blez_op:
- case blezl_op:
- case bgtz_op:
- case bgtzl_op:
-
- /*
- * These are the FPA/cp1 branch instructions.
- */
- case cop1_op:
-
-#ifdef CONFIG_CPU_CAVIUM_OCTEON
- case lwc2_op: /* This is bbit0 on Octeon */
- case ldc2_op: /* This is bbit032 on Octeon */
- case swc2_op: /* This is bbit1 on Octeon */
- case sdc2_op: /* This is bbit132 on Octeon */
-#endif
- return 1;
- default:
- break;
- }
-insn_ok:
- return 0;
+ return __insn_has_delay_slot(insn);
}
/*
@@ -161,6 +106,12 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
goto out;
}
+ if (__insn_is_compact_branch(insn)) {
+ pr_notice("Kprobes for compact branches are not supported\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
/* insn: must be on special executable page on mips. */
p->ainsn.insn = get_insn_slot();
if (!p->ainsn.insn) {
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 0b29646..50fb625 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -26,7 +26,6 @@
#include <linux/utsname.h>
#include <linux/personality.h>
#include <linux/dnotify.h>
-#include <linux/module.h>
#include <linux/binfmts.h>
#include <linux/security.h>
#include <linux/compat.h>
diff --git a/arch/mips/kernel/mips-cpc.c b/arch/mips/kernel/mips-cpc.c
index 566b8d2..a4964c3 100644
--- a/arch/mips/kernel/mips-cpc.c
+++ b/arch/mips/kernel/mips-cpc.c
@@ -21,6 +21,11 @@ static DEFINE_PER_CPU_ALIGNED(spinlock_t, cpc_core_lock);
static DEFINE_PER_CPU_ALIGNED(unsigned long, cpc_core_lock_flags);
+phys_addr_t __weak mips_cpc_default_phys_base(void)
+{
+ return 0;
+}
+
/**
* mips_cpc_phys_base - retrieve the physical base address of the CPC
*
@@ -43,8 +48,12 @@ static phys_addr_t mips_cpc_phys_base(void)
if (cpc_base & CM_GCR_CPC_BASE_CPCEN_MSK)
return cpc_base & CM_GCR_CPC_BASE_CPCBASE_MSK;
- /* Otherwise, give it the default address & enable it */
+ /* Otherwise, use the default address */
cpc_base = mips_cpc_default_phys_base();
+ if (!cpc_base)
+ return cpc_base;
+
+ /* Enable the CPC, mapped at the default address */
write_gcr_cpc_base(cpc_base | CM_GCR_CPC_BASE_CPCEN_MSK);
return cpc_base;
}
@@ -52,7 +61,7 @@ static phys_addr_t mips_cpc_phys_base(void)
int mips_cpc_probe(void)
{
phys_addr_t addr;
- unsigned cpu;
+ unsigned int cpu;
for_each_possible_cpu(cpu)
spin_lock_init(&per_cpu(cpc_core_lock, cpu));
@@ -70,7 +79,12 @@ int mips_cpc_probe(void)
void mips_cpc_lock_other(unsigned int core)
{
- unsigned curr_core;
+ unsigned int curr_core;
+
+ if (mips_cm_revision() >= CM_REV_CM3)
+ /* Systems with CM >= 3 lock the CPC via mips_cm_lock_other */
+ return;
+
preempt_disable();
curr_core = current_cpu_data.core;
spin_lock_irqsave(&per_cpu(cpc_core_lock, curr_core),
@@ -86,7 +100,13 @@ void mips_cpc_lock_other(unsigned int core)
void mips_cpc_unlock_other(void)
{
- unsigned curr_core = current_cpu_data.core;
+ unsigned int curr_core;
+
+ if (mips_cm_revision() >= CM_REV_CM3)
+ /* Systems with CM >= 3 lock the CPC via mips_cm_lock_other */
+ return;
+
+ curr_core = current_cpu_data.core;
spin_unlock_irqrestore(&per_cpu(cpc_core_lock, curr_core),
per_cpu(cpc_core_lock_flags, curr_core));
preempt_enable();
diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c
index 0a7e10b..bd09853 100644
--- a/arch/mips/kernel/mips-r2-to-r6-emul.c
+++ b/arch/mips/kernel/mips-r2-to-r6-emul.c
@@ -15,7 +15,6 @@
#include <linux/debugfs.h>
#include <linux/init.h>
#include <linux/kernel.h>
-#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/seq_file.h>
@@ -900,7 +899,7 @@ static inline int mipsr2_find_op_func(struct pt_regs *regs, u32 inst,
* mipsr2_decoder: Decode and emulate a MIPS R2 instruction
* @regs: Process register set
* @inst: Instruction to decode and emulate
- * @fcr31: Floating Point Control and Status Register returned
+ * @fcr31: Floating Point Control and Status Register Cause bits returned
*/
int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
{
@@ -1173,13 +1172,13 @@ int mipsr2_decoder(struct pt_regs *regs, u32 inst, unsigned long *fcr31)
err = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 0,
&fault_addr);
- *fcr31 = current->thread.fpu.fcr31;
/*
- * We can't allow the emulated instruction to leave any of
- * the cause bits set in $fcr31.
+ * We can't allow the emulated instruction to leave any
+ * enabled Cause bits set in $fcr31.
*/
- current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X;
+ *fcr31 = res = mask_fcr31_x(current->thread.fpu.fcr31);
+ current->thread.fpu.fcr31 &= ~res;
/*
* this is a tricky issue - lose_fpu() uses LL/SC atomics
diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c
index 79850e3..94627a3 100644
--- a/arch/mips/kernel/module.c
+++ b/arch/mips/kernel/module.c
@@ -20,6 +20,7 @@
#undef DEBUG
+#include <linux/extable.h>
#include <linux/moduleloader.h>
#include <linux/elf.h>
#include <linux/mm.h>
diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c
index 5b31a94..7cf653e 100644
--- a/arch/mips/kernel/pm-cps.c
+++ b/arch/mips/kernel/pm-cps.c
@@ -8,6 +8,7 @@
* option) any later version.
*/
+#include <linux/cpuhotplug.h>
#include <linux/init.h>
#include <linux/percpu.h>
#include <linux/slab.h>
@@ -70,13 +71,8 @@ static DEFINE_PER_CPU_ALIGNED(atomic_t, pm_barrier);
DEFINE_PER_CPU_ALIGNED(struct mips_static_suspend_state, cps_cpu_state);
/* A somewhat arbitrary number of labels & relocs for uasm */
-static struct uasm_label labels[32] __initdata;
-static struct uasm_reloc relocs[32] __initdata;
-
-/* CPU dependant sync types */
-static unsigned stype_intervention;
-static unsigned stype_memory;
-static unsigned stype_ordering;
+static struct uasm_label labels[32];
+static struct uasm_reloc relocs[32];
enum mips_reg {
zero, at, v0, v1, a0, a1, a2, a3,
@@ -134,7 +130,7 @@ int cps_pm_enter_state(enum cps_pm_state state)
return -EINVAL;
/* Calculate which coupled CPUs (VPEs) are online */
-#ifdef CONFIG_MIPS_MT
+#if defined(CONFIG_MIPS_MT) || defined(CONFIG_CPU_MIPSR6)
if (cpu_online(cpu)) {
cpumask_and(coupled_mask, cpu_online_mask,
&cpu_sibling_map[cpu]);
@@ -198,10 +194,10 @@ int cps_pm_enter_state(enum cps_pm_state state)
return 0;
}
-static void __init cps_gen_cache_routine(u32 **pp, struct uasm_label **pl,
- struct uasm_reloc **pr,
- const struct cache_desc *cache,
- unsigned op, int lbl)
+static void cps_gen_cache_routine(u32 **pp, struct uasm_label **pl,
+ struct uasm_reloc **pr,
+ const struct cache_desc *cache,
+ unsigned op, int lbl)
{
unsigned cache_size = cache->ways << cache->waybit;
unsigned i;
@@ -242,10 +238,10 @@ static void __init cps_gen_cache_routine(u32 **pp, struct uasm_label **pl,
uasm_i_nop(pp);
}
-static int __init cps_gen_flush_fsb(u32 **pp, struct uasm_label **pl,
- struct uasm_reloc **pr,
- const struct cpuinfo_mips *cpu_info,
- int lbl)
+static int cps_gen_flush_fsb(u32 **pp, struct uasm_label **pl,
+ struct uasm_reloc **pr,
+ const struct cpuinfo_mips *cpu_info,
+ int lbl)
{
unsigned i, fsb_size = 8;
unsigned num_loads = (fsb_size * 3) / 2;
@@ -272,14 +268,9 @@ static int __init cps_gen_flush_fsb(u32 **pp, struct uasm_label **pl,
/* On older ones it's unavailable */
return -1;
- /* CPUs which do not require the workaround */
- case CPU_P5600:
- case CPU_I6400:
- return 0;
-
default:
- WARN_ONCE(1, "pm-cps: FSB flush unsupported for this CPU\n");
- return -1;
+ /* Assume that the CPU does not need this workaround */
+ return 0;
}
/*
@@ -320,8 +311,8 @@ static int __init cps_gen_flush_fsb(u32 **pp, struct uasm_label **pl,
i * line_size * line_stride, t0);
}
- /* Completion barrier */
- uasm_i_sync(pp, stype_memory);
+ /* Barrier ensuring previous cache invalidates are complete */
+ uasm_i_sync(pp, STYPE_SYNC);
uasm_i_ehb(pp);
/* Check whether the pipeline stalled due to the FSB being full */
@@ -340,9 +331,9 @@ static int __init cps_gen_flush_fsb(u32 **pp, struct uasm_label **pl,
return 0;
}
-static void __init cps_gen_set_top_bit(u32 **pp, struct uasm_label **pl,
- struct uasm_reloc **pr,
- unsigned r_addr, int lbl)
+static void cps_gen_set_top_bit(u32 **pp, struct uasm_label **pl,
+ struct uasm_reloc **pr,
+ unsigned r_addr, int lbl)
{
uasm_i_lui(pp, t0, uasm_rel_hi(0x80000000));
uasm_build_label(pl, *pp, lbl);
@@ -353,7 +344,7 @@ static void __init cps_gen_set_top_bit(u32 **pp, struct uasm_label **pl,
uasm_i_nop(pp);
}
-static void * __init cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
+static void *cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
{
struct uasm_label *l = labels;
struct uasm_reloc *r = relocs;
@@ -411,7 +402,7 @@ static void * __init cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
if (coupled_coherence) {
/* Increment ready_count */
- uasm_i_sync(&p, stype_ordering);
+ uasm_i_sync(&p, STYPE_SYNC_MB);
uasm_build_label(&l, p, lbl_incready);
uasm_i_ll(&p, t1, 0, r_nc_count);
uasm_i_addiu(&p, t2, t1, 1);
@@ -419,8 +410,8 @@ static void * __init cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
uasm_il_beqz(&p, &r, t2, lbl_incready);
uasm_i_addiu(&p, t1, t1, 1);
- /* Ordering barrier */
- uasm_i_sync(&p, stype_ordering);
+ /* Barrier ensuring all CPUs see the updated r_nc_count value */
+ uasm_i_sync(&p, STYPE_SYNC_MB);
/*
* If this is the last VPE to become ready for non-coherence
@@ -441,7 +432,8 @@ static void * __init cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
uasm_i_lw(&p, t0, 0, r_nc_count);
uasm_il_bltz(&p, &r, t0, lbl_secondary_cont);
uasm_i_ehb(&p);
- uasm_i_yield(&p, zero, t1);
+ if (cpu_has_mipsmt)
+ uasm_i_yield(&p, zero, t1);
uasm_il_b(&p, &r, lbl_poll_cont);
uasm_i_nop(&p);
} else {
@@ -449,8 +441,21 @@ static void * __init cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
* The core will lose power & this VPE will not continue
* so it can simply halt here.
*/
- uasm_i_addiu(&p, t0, zero, TCHALT_H);
- uasm_i_mtc0(&p, t0, 2, 4);
+ if (cpu_has_mipsmt) {
+ /* Halt the VPE via C0 tchalt register */
+ uasm_i_addiu(&p, t0, zero, TCHALT_H);
+ uasm_i_mtc0(&p, t0, 2, 4);
+ } else if (cpu_has_vp) {
+ /* Halt the VP via the CPC VP_STOP register */
+ unsigned int vpe_id;
+
+ vpe_id = cpu_vpe_id(&cpu_data[cpu]);
+ uasm_i_addiu(&p, t0, zero, 1 << vpe_id);
+ UASM_i_LA(&p, t1, (long)addr_cpc_cl_vp_stop());
+ uasm_i_sw(&p, t0, 0, t1);
+ } else {
+ BUG();
+ }
uasm_build_label(&l, p, lbl_secondary_hang);
uasm_il_b(&p, &r, lbl_secondary_hang);
uasm_i_nop(&p);
@@ -472,22 +477,24 @@ static void * __init cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
cps_gen_cache_routine(&p, &l, &r, &cpu_data[cpu].dcache,
Index_Writeback_Inv_D, lbl_flushdcache);
- /* Completion barrier */
- uasm_i_sync(&p, stype_memory);
+ /* Barrier ensuring previous cache invalidates are complete */
+ uasm_i_sync(&p, STYPE_SYNC);
uasm_i_ehb(&p);
- /*
- * Disable all but self interventions. The load from COHCTL is defined
- * by the interAptiv & proAptiv SUMs as ensuring that the operation
- * resulting from the preceding store is complete.
- */
- uasm_i_addiu(&p, t0, zero, 1 << cpu_data[cpu].core);
- uasm_i_sw(&p, t0, 0, r_pcohctl);
- uasm_i_lw(&p, t0, 0, r_pcohctl);
+ if (mips_cm_revision() < CM_REV_CM3) {
+ /*
+ * Disable all but self interventions. The load from COHCTL is
+ * defined by the interAptiv & proAptiv SUMs as ensuring that the
+ * operation resulting from the preceding store is complete.
+ */
+ uasm_i_addiu(&p, t0, zero, 1 << cpu_data[cpu].core);
+ uasm_i_sw(&p, t0, 0, r_pcohctl);
+ uasm_i_lw(&p, t0, 0, r_pcohctl);
- /* Sync to ensure previous interventions are complete */
- uasm_i_sync(&p, stype_intervention);
- uasm_i_ehb(&p);
+ /* Barrier to ensure write to coherence control is complete */
+ uasm_i_sync(&p, STYPE_SYNC);
+ uasm_i_ehb(&p);
+ }
/* Disable coherence */
uasm_i_sw(&p, zero, 0, r_pcohctl);
@@ -531,8 +538,8 @@ static void * __init cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
goto gen_done;
}
- /* Completion barrier */
- uasm_i_sync(&p, stype_memory);
+ /* Barrier to ensure write to CPC command is complete */
+ uasm_i_sync(&p, STYPE_SYNC);
uasm_i_ehb(&p);
}
@@ -562,26 +569,29 @@ static void * __init cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
* will run this. The first will actually re-enable coherence & the
* rest will just be performing a rather unusual nop.
*/
- uasm_i_addiu(&p, t0, zero, CM_GCR_Cx_COHERENCE_COHDOMAINEN_MSK);
+ uasm_i_addiu(&p, t0, zero, mips_cm_revision() < CM_REV_CM3
+ ? CM_GCR_Cx_COHERENCE_COHDOMAINEN_MSK
+ : CM3_GCR_Cx_COHERENCE_COHEN_MSK);
+
uasm_i_sw(&p, t0, 0, r_pcohctl);
uasm_i_lw(&p, t0, 0, r_pcohctl);
- /* Completion barrier */
- uasm_i_sync(&p, stype_memory);
+ /* Barrier to ensure write to coherence control is complete */
+ uasm_i_sync(&p, STYPE_SYNC);
uasm_i_ehb(&p);
if (coupled_coherence && (state == CPS_PM_NC_WAIT)) {
/* Decrement ready_count */
uasm_build_label(&l, p, lbl_decready);
- uasm_i_sync(&p, stype_ordering);
+ uasm_i_sync(&p, STYPE_SYNC_MB);
uasm_i_ll(&p, t1, 0, r_nc_count);
uasm_i_addiu(&p, t2, t1, -1);
uasm_i_sc(&p, t2, 0, r_nc_count);
uasm_il_beqz(&p, &r, t2, lbl_decready);
uasm_i_andi(&p, v0, t1, (1 << fls(smp_num_siblings)) - 1);
- /* Ordering barrier */
- uasm_i_sync(&p, stype_ordering);
+ /* Barrier ensuring all CPUs see the updated r_nc_count value */
+ uasm_i_sync(&p, STYPE_SYNC_MB);
}
if (coupled_coherence && (state == CPS_PM_CLOCK_GATED)) {
@@ -602,8 +612,8 @@ static void * __init cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
*/
uasm_build_label(&l, p, lbl_secondary_cont);
- /* Ordering barrier */
- uasm_i_sync(&p, stype_ordering);
+ /* Barrier ensuring all CPUs see the updated r_nc_count value */
+ uasm_i_sync(&p, STYPE_SYNC_MB);
}
/* The core is coherent, time to return to C code */
@@ -628,7 +638,7 @@ static void * __init cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
return NULL;
}
-static int __init cps_gen_core_entries(unsigned cpu)
+static int cps_pm_online_cpu(unsigned int cpu)
{
enum cps_pm_state state;
unsigned core = cpu_data[cpu].core;
@@ -670,29 +680,10 @@ static int __init cps_gen_core_entries(unsigned cpu)
static int __init cps_pm_init(void)
{
- unsigned cpu;
- int err;
-
- /* Detect appropriate sync types for the system */
- switch (current_cpu_data.cputype) {
- case CPU_INTERAPTIV:
- case CPU_PROAPTIV:
- case CPU_M5150:
- case CPU_P5600:
- case CPU_I6400:
- stype_intervention = 0x2;
- stype_memory = 0x3;
- stype_ordering = 0x10;
- break;
-
- default:
- pr_warn("Power management is using heavyweight sync 0\n");
- }
-
/* A CM is required for all non-coherent states */
if (!mips_cm_present()) {
pr_warn("pm-cps: no CM, non-coherent states unavailable\n");
- goto out;
+ return 0;
}
/*
@@ -722,12 +713,7 @@ static int __init cps_pm_init(void)
pr_warn("pm-cps: no CPC, clock & power gating unavailable\n");
}
- for_each_present_cpu(cpu) {
- err = cps_gen_core_entries(cpu);
- if (err)
- return err;
- }
-out:
- return 0;
+ return cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_PM_CPS_CPU_ONLINE",
+ cps_pm_online_cpu, NULL);
}
arch_initcall(cps_pm_init);
diff --git a/arch/mips/kernel/probes-common.h b/arch/mips/kernel/probes-common.h
new file mode 100644
index 0000000..dd08e41
--- /dev/null
+++ b/arch/mips/kernel/probes-common.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2016 Imagination Technologies
+ * Author: Marcin Nowakowski <marcin.nowakowski@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#ifndef __PROBES_COMMON_H
+#define __PROBES_COMMON_H
+
+#include <asm/inst.h>
+
+int __insn_is_compact_branch(union mips_instruction insn);
+
+static inline int __insn_has_delay_slot(const union mips_instruction insn)
+{
+ switch (insn.i_format.opcode) {
+ /*
+ * jr and jalr are in r_format format.
+ */
+ case spec_op:
+ switch (insn.r_format.func) {
+ case jalr_op:
+ case jr_op:
+ return 1;
+ }
+ break;
+
+ /*
+ * This group contains:
+ * bltz_op, bgez_op, bltzl_op, bgezl_op,
+ * bltzal_op, bgezal_op, bltzall_op, bgezall_op.
+ */
+ case bcond_op:
+ switch (insn.i_format.rt) {
+ case bltz_op:
+ case bltzl_op:
+ case bgez_op:
+ case bgezl_op:
+ case bltzal_op:
+ case bltzall_op:
+ case bgezal_op:
+ case bgezall_op:
+ case bposge32_op:
+ return 1;
+ }
+ break;
+
+ /*
+ * These are unconditional and in j_format.
+ */
+ case jal_op:
+ case j_op:
+ case beq_op:
+ case beql_op:
+ case bne_op:
+ case bnel_op:
+ case blez_op: /* not really i_format */
+ case blezl_op:
+ case bgtz_op:
+ case bgtzl_op:
+ return 1;
+
+ /*
+ * And now the FPA/cp1 branch instructions.
+ */
+ case cop1_op:
+#ifdef CONFIG_CPU_CAVIUM_OCTEON
+ case lwc2_op: /* This is bbit0 on Octeon */
+ case ldc2_op: /* This is bbit032 on Octeon */
+ case swc2_op: /* This is bbit1 on Octeon */
+ case sdc2_op: /* This is bbit132 on Octeon */
+#endif
+ return 1;
+ }
+
+ return 0;
+}
+
+#endif /* __PROBES_COMMON_H */
diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c
index 97dc01b..4eff2ae 100644
--- a/arch/mips/kernel/proc.c
+++ b/arch/mips/kernel/proc.c
@@ -135,6 +135,13 @@ static int show_cpuinfo(struct seq_file *m, void *v)
seq_printf(m, "package\t\t\t: %d\n", cpu_data[n].package);
seq_printf(m, "core\t\t\t: %d\n", cpu_data[n].core);
+#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_CPU_MIPSR6)
+ if (cpu_has_mipsmt)
+ seq_printf(m, "VPE\t\t\t: %d\n", cpu_data[n].vpe_id);
+ else if (cpu_has_vp)
+ seq_printf(m, "VP\t\t\t: %d\n", cpu_data[n].vpe_id);
+#endif
+
sprintf(fmt, "VCE%%c exceptions\t\t: %s\n",
cpu_has_vce ? "%u" : "not available");
seq_printf(m, fmt, 'D', vced_count);
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 6103b24..a92994d 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -79,16 +79,15 @@ void ptrace_disable(struct task_struct *child)
}
/*
- * Poke at FCSR according to its mask. Don't set the cause bits as
- * this is currently not handled correctly in FP context restoration
- * and will cause an oops if a corresponding enable bit is set.
+ * Poke at FCSR according to its mask. Set the Cause bits even
+ * if a corresponding Enable bit is set. This will be noticed at
+ * the time the thread is switched to and SIGFPE thrown accordingly.
*/
static void ptrace_setfcr31(struct task_struct *child, u32 value)
{
u32 fcr31;
u32 mask;
- value &= ~FPU_CSR_ALL_X;
fcr31 = child->thread.fpu.fcr31;
mask = boot_cpu_data.fpu_msk31;
child->thread.fpu.fcr31 = (value & ~mask) | (fcr31 & mask);
@@ -817,6 +816,7 @@ long arch_ptrace(struct task_struct *child, long request,
break;
#endif
case FPC_CSR:
+ init_fp_ctx(child);
ptrace_setfcr31(child, data);
break;
case DSP_BASE ... DSP_BASE + 5: {
diff --git a/arch/mips/kernel/ptrace32.c b/arch/mips/kernel/ptrace32.c
index 283b5a1..7e71a4e 100644
--- a/arch/mips/kernel/ptrace32.c
+++ b/arch/mips/kernel/ptrace32.c
@@ -70,7 +70,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
break;
copied = access_process_vm(child, (u64)addrOthers, &tmp,
- sizeof(tmp), 0);
+ sizeof(tmp), FOLL_FORCE);
if (copied != sizeof(tmp))
break;
ret = put_user(tmp, (u32 __user *) (unsigned long) data);
@@ -179,7 +179,8 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
break;
ret = 0;
if (access_process_vm(child, (u64)addrOthers, &data,
- sizeof(data), 1) == sizeof(data))
+ sizeof(data),
+ FOLL_FORCE | FOLL_WRITE) == sizeof(data))
break;
ret = -EIO;
break;
diff --git a/arch/mips/kernel/r2300_fpu.S b/arch/mips/kernel/r2300_fpu.S
index b4ac637..918f2f6 100644
--- a/arch/mips/kernel/r2300_fpu.S
+++ b/arch/mips/kernel/r2300_fpu.S
@@ -21,106 +21,84 @@
#define EX(a,b) \
9: a,##b; \
.section __ex_table,"a"; \
+ PTR 9b,fault; \
+ .previous
+
+#define EX2(a,b) \
+9: a,##b; \
+ .section __ex_table,"a"; \
PTR 9b,bad_stack; \
+ PTR 9b+4,bad_stack; \
.previous
.set noreorder
.set mips1
- /* Save floating point context */
+
+/**
+ * _save_fp_context() - save FP context from the FPU
+ * @a0 - pointer to fpregs field of sigcontext
+ * @a1 - pointer to fpc_csr field of sigcontext
+ *
+ * Save FP context, including the 32 FP data registers and the FP
+ * control & status register, from the FPU to signal context.
+ */
LEAF(_save_fp_context)
.set push
SET_HARDFLOAT
li v0, 0 # assume success
- cfc1 t1,fcr31
- EX(swc1 $f0,(SC_FPREGS+0)(a0))
- EX(swc1 $f1,(SC_FPREGS+8)(a0))
- EX(swc1 $f2,(SC_FPREGS+16)(a0))
- EX(swc1 $f3,(SC_FPREGS+24)(a0))
- EX(swc1 $f4,(SC_FPREGS+32)(a0))
- EX(swc1 $f5,(SC_FPREGS+40)(a0))
- EX(swc1 $f6,(SC_FPREGS+48)(a0))
- EX(swc1 $f7,(SC_FPREGS+56)(a0))
- EX(swc1 $f8,(SC_FPREGS+64)(a0))
- EX(swc1 $f9,(SC_FPREGS+72)(a0))
- EX(swc1 $f10,(SC_FPREGS+80)(a0))
- EX(swc1 $f11,(SC_FPREGS+88)(a0))
- EX(swc1 $f12,(SC_FPREGS+96)(a0))
- EX(swc1 $f13,(SC_FPREGS+104)(a0))
- EX(swc1 $f14,(SC_FPREGS+112)(a0))
- EX(swc1 $f15,(SC_FPREGS+120)(a0))
- EX(swc1 $f16,(SC_FPREGS+128)(a0))
- EX(swc1 $f17,(SC_FPREGS+136)(a0))
- EX(swc1 $f18,(SC_FPREGS+144)(a0))
- EX(swc1 $f19,(SC_FPREGS+152)(a0))
- EX(swc1 $f20,(SC_FPREGS+160)(a0))
- EX(swc1 $f21,(SC_FPREGS+168)(a0))
- EX(swc1 $f22,(SC_FPREGS+176)(a0))
- EX(swc1 $f23,(SC_FPREGS+184)(a0))
- EX(swc1 $f24,(SC_FPREGS+192)(a0))
- EX(swc1 $f25,(SC_FPREGS+200)(a0))
- EX(swc1 $f26,(SC_FPREGS+208)(a0))
- EX(swc1 $f27,(SC_FPREGS+216)(a0))
- EX(swc1 $f28,(SC_FPREGS+224)(a0))
- EX(swc1 $f29,(SC_FPREGS+232)(a0))
- EX(swc1 $f30,(SC_FPREGS+240)(a0))
- EX(swc1 $f31,(SC_FPREGS+248)(a0))
- EX(sw t1,(SC_FPC_CSR)(a0))
- cfc1 t0,$0 # implementation/version
+ cfc1 t1, fcr31
+ EX2(s.d $f0, 0(a0))
+ EX2(s.d $f2, 16(a0))
+ EX2(s.d $f4, 32(a0))
+ EX2(s.d $f6, 48(a0))
+ EX2(s.d $f8, 64(a0))
+ EX2(s.d $f10, 80(a0))
+ EX2(s.d $f12, 96(a0))
+ EX2(s.d $f14, 112(a0))
+ EX2(s.d $f16, 128(a0))
+ EX2(s.d $f18, 144(a0))
+ EX2(s.d $f20, 160(a0))
+ EX2(s.d $f22, 176(a0))
+ EX2(s.d $f24, 192(a0))
+ EX2(s.d $f26, 208(a0))
+ EX2(s.d $f28, 224(a0))
+ EX2(s.d $f30, 240(a0))
jr ra
+ EX(sw t1, (a1))
.set pop
- .set nomacro
- EX(sw t0,(SC_FPC_EIR)(a0))
- .set macro
END(_save_fp_context)
-/*
- * Restore FPU state:
- * - fp gp registers
- * - cp1 status/control register
+/**
+ * _restore_fp_context() - restore FP context to the FPU
+ * @a0 - pointer to fpregs field of sigcontext
+ * @a1 - pointer to fpc_csr field of sigcontext
*
- * We base the decision which registers to restore from the signal stack
- * frame on the current content of c0_status, not on the content of the
- * stack frame which might have been changed by the user.
+ * Restore FP context, including the 32 FP data registers and the FP
+ * control & status register, from signal context to the FPU.
*/
LEAF(_restore_fp_context)
.set push
SET_HARDFLOAT
li v0, 0 # assume success
- EX(lw t0,(SC_FPC_CSR)(a0))
- EX(lwc1 $f0,(SC_FPREGS+0)(a0))
- EX(lwc1 $f1,(SC_FPREGS+8)(a0))
- EX(lwc1 $f2,(SC_FPREGS+16)(a0))
- EX(lwc1 $f3,(SC_FPREGS+24)(a0))
- EX(lwc1 $f4,(SC_FPREGS+32)(a0))
- EX(lwc1 $f5,(SC_FPREGS+40)(a0))
- EX(lwc1 $f6,(SC_FPREGS+48)(a0))
- EX(lwc1 $f7,(SC_FPREGS+56)(a0))
- EX(lwc1 $f8,(SC_FPREGS+64)(a0))
- EX(lwc1 $f9,(SC_FPREGS+72)(a0))
- EX(lwc1 $f10,(SC_FPREGS+80)(a0))
- EX(lwc1 $f11,(SC_FPREGS+88)(a0))
- EX(lwc1 $f12,(SC_FPREGS+96)(a0))
- EX(lwc1 $f13,(SC_FPREGS+104)(a0))
- EX(lwc1 $f14,(SC_FPREGS+112)(a0))
- EX(lwc1 $f15,(SC_FPREGS+120)(a0))
- EX(lwc1 $f16,(SC_FPREGS+128)(a0))
- EX(lwc1 $f17,(SC_FPREGS+136)(a0))
- EX(lwc1 $f18,(SC_FPREGS+144)(a0))
- EX(lwc1 $f19,(SC_FPREGS+152)(a0))
- EX(lwc1 $f20,(SC_FPREGS+160)(a0))
- EX(lwc1 $f21,(SC_FPREGS+168)(a0))
- EX(lwc1 $f22,(SC_FPREGS+176)(a0))
- EX(lwc1 $f23,(SC_FPREGS+184)(a0))
- EX(lwc1 $f24,(SC_FPREGS+192)(a0))
- EX(lwc1 $f25,(SC_FPREGS+200)(a0))
- EX(lwc1 $f26,(SC_FPREGS+208)(a0))
- EX(lwc1 $f27,(SC_FPREGS+216)(a0))
- EX(lwc1 $f28,(SC_FPREGS+224)(a0))
- EX(lwc1 $f29,(SC_FPREGS+232)(a0))
- EX(lwc1 $f30,(SC_FPREGS+240)(a0))
- EX(lwc1 $f31,(SC_FPREGS+248)(a0))
+ EX(lw t0, (a1))
+ EX2(l.d $f0, 0(a0))
+ EX2(l.d $f2, 16(a0))
+ EX2(l.d $f4, 32(a0))
+ EX2(l.d $f6, 48(a0))
+ EX2(l.d $f8, 64(a0))
+ EX2(l.d $f10, 80(a0))
+ EX2(l.d $f12, 96(a0))
+ EX2(l.d $f14, 112(a0))
+ EX2(l.d $f16, 128(a0))
+ EX2(l.d $f18, 144(a0))
+ EX2(l.d $f20, 160(a0))
+ EX2(l.d $f22, 176(a0))
+ EX2(l.d $f24, 192(a0))
+ EX2(l.d $f26, 208(a0))
+ EX2(l.d $f28, 224(a0))
+ EX2(l.d $f30, 240(a0))
jr ra
- ctc1 t0,fcr31
+ ctc1 t0, fcr31
.set pop
END(_restore_fp_context)
.set reorder
diff --git a/arch/mips/kernel/r6000_fpu.S b/arch/mips/kernel/r6000_fpu.S
index 4707738..9cc7bfa 100644
--- a/arch/mips/kernel/r6000_fpu.S
+++ b/arch/mips/kernel/r6000_fpu.S
@@ -21,7 +21,14 @@
.set push
SET_HARDFLOAT
- /* Save floating point context */
+/**
+ * _save_fp_context() - save FP context from the FPU
+ * @a0 - pointer to fpregs field of sigcontext
+ * @a1 - pointer to fpc_csr field of sigcontext
+ *
+ * Save FP context, including the 32 FP data registers and the FP
+ * control & status register, from the FPU to signal context.
+ */
LEAF(_save_fp_context)
mfc0 t0,CP0_STATUS
sll t0,t0,2
@@ -30,59 +37,59 @@
cfc1 t1,fcr31
/* Store the 16 double precision registers */
- sdc1 $f0,(SC_FPREGS+0)(a0)
- sdc1 $f2,(SC_FPREGS+16)(a0)
- sdc1 $f4,(SC_FPREGS+32)(a0)
- sdc1 $f6,(SC_FPREGS+48)(a0)
- sdc1 $f8,(SC_FPREGS+64)(a0)
- sdc1 $f10,(SC_FPREGS+80)(a0)
- sdc1 $f12,(SC_FPREGS+96)(a0)
- sdc1 $f14,(SC_FPREGS+112)(a0)
- sdc1 $f16,(SC_FPREGS+128)(a0)
- sdc1 $f18,(SC_FPREGS+144)(a0)
- sdc1 $f20,(SC_FPREGS+160)(a0)
- sdc1 $f22,(SC_FPREGS+176)(a0)
- sdc1 $f24,(SC_FPREGS+192)(a0)
- sdc1 $f26,(SC_FPREGS+208)(a0)
- sdc1 $f28,(SC_FPREGS+224)(a0)
- sdc1 $f30,(SC_FPREGS+240)(a0)
+ sdc1 $f0,0(a0)
+ sdc1 $f2,16(a0)
+ sdc1 $f4,32(a0)
+ sdc1 $f6,48(a0)
+ sdc1 $f8,64(a0)
+ sdc1 $f10,80(a0)
+ sdc1 $f12,96(a0)
+ sdc1 $f14,112(a0)
+ sdc1 $f16,128(a0)
+ sdc1 $f18,144(a0)
+ sdc1 $f20,160(a0)
+ sdc1 $f22,176(a0)
+ sdc1 $f24,192(a0)
+ sdc1 $f26,208(a0)
+ sdc1 $f28,224(a0)
+ sdc1 $f30,240(a0)
jr ra
- sw t0,SC_FPC_CSR(a0)
+ sw t0,(a1)
1: jr ra
nop
END(_save_fp_context)
-/* Restore FPU state:
- * - fp gp registers
- * - cp1 status/control register
+/**
+ * _restore_fp_context() - restore FP context to the FPU
+ * @a0 - pointer to fpregs field of sigcontext
+ * @a1 - pointer to fpc_csr field of sigcontext
*
- * We base the decision which registers to restore from the signal stack
- * frame on the current content of c0_status, not on the content of the
- * stack frame which might have been changed by the user.
+ * Restore FP context, including the 32 FP data registers and the FP
+ * control & status register, from signal context to the FPU.
*/
LEAF(_restore_fp_context)
mfc0 t0,CP0_STATUS
sll t0,t0,2
bgez t0,1f
- lw t0,SC_FPC_CSR(a0)
+ lw t0,(a1)
/* Restore the 16 double precision registers */
- ldc1 $f0,(SC_FPREGS+0)(a0)
- ldc1 $f2,(SC_FPREGS+16)(a0)
- ldc1 $f4,(SC_FPREGS+32)(a0)
- ldc1 $f6,(SC_FPREGS+48)(a0)
- ldc1 $f8,(SC_FPREGS+64)(a0)
- ldc1 $f10,(SC_FPREGS+80)(a0)
- ldc1 $f12,(SC_FPREGS+96)(a0)
- ldc1 $f14,(SC_FPREGS+112)(a0)
- ldc1 $f16,(SC_FPREGS+128)(a0)
- ldc1 $f18,(SC_FPREGS+144)(a0)
- ldc1 $f20,(SC_FPREGS+160)(a0)
- ldc1 $f22,(SC_FPREGS+176)(a0)
- ldc1 $f24,(SC_FPREGS+192)(a0)
- ldc1 $f26,(SC_FPREGS+208)(a0)
- ldc1 $f28,(SC_FPREGS+224)(a0)
- ldc1 $f30,(SC_FPREGS+240)(a0)
+ ldc1 $f0,0(a0)
+ ldc1 $f2,16(a0)
+ ldc1 $f4,32(a0)
+ ldc1 $f6,48(a0)
+ ldc1 $f8,64(a0)
+ ldc1 $f10,80(a0)
+ ldc1 $f12,96(a0)
+ ldc1 $f14,112(a0)
+ ldc1 $f16,128(a0)
+ ldc1 $f18,144(a0)
+ ldc1 $f20,160(a0)
+ ldc1 $f22,176(a0)
+ ldc1 $f24,192(a0)
+ ldc1 $f26,208(a0)
+ ldc1 $f28,224(a0)
+ ldc1 $f30,240(a0)
jr ra
ctc1 t0,fcr31
1: jr ra
diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c
index ca1cc30..1958910 100644
--- a/arch/mips/kernel/relocate.c
+++ b/arch/mips/kernel/relocate.c
@@ -200,7 +200,7 @@ static inline __init unsigned long get_random_boot(void)
#if defined(CONFIG_USE_OF)
/* Get any additional entropy passed in device tree */
- {
+ if (initial_boot_params) {
int node, len;
u64 *prop;
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index c8e43e0..c29d397 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -597,3 +597,6 @@
PTR sys_copy_file_range /* 4360 */
PTR sys_preadv2
PTR sys_pwritev2
+ PTR sys_pkey_mprotect
+ PTR sys_pkey_alloc
+ PTR sys_pkey_free /* 4365 */
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index e6ede12..0687f96 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -435,4 +435,7 @@
PTR sys_copy_file_range /* 5320 */
PTR sys_preadv2
PTR sys_pwritev2
+ PTR sys_pkey_mprotect
+ PTR sys_pkey_alloc
+ PTR sys_pkey_free /* 5325 */
.size sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 51d3988..0331ba3 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -430,4 +430,7 @@
PTR sys_copy_file_range
PTR compat_sys_preadv2 /* 6325 */
PTR compat_sys_pwritev2
+ PTR sys_pkey_mprotect
+ PTR sys_pkey_alloc
+ PTR sys_pkey_free
.size sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 6efa713..5a47042 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -585,4 +585,7 @@
PTR sys_copy_file_range /* 4360 */
PTR compat_sys_preadv2
PTR compat_sys_pwritev2
+ PTR sys_pkey_mprotect
+ PTR sys_pkey_alloc
+ PTR sys_pkey_free /* 4365 */
.size sys32_call_table,.-sys32_call_table
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 0d57909..f66e5ce 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -368,6 +368,19 @@ static void __init bootmem_init(void)
end = PFN_DOWN(boot_mem_map.map[i].addr
+ boot_mem_map.map[i].size);
+#ifndef CONFIG_HIGHMEM
+ /*
+ * Skip highmem here so we get an accurate max_low_pfn if low
+ * memory stops short of high memory.
+ * If the region overlaps HIGHMEM_START, end is clipped so
+ * max_pfn excludes the highmem portion.
+ */
+ if (start >= PFN_DOWN(HIGHMEM_START))
+ continue;
+ if (end > PFN_DOWN(HIGHMEM_START))
+ end = PFN_DOWN(HIGHMEM_START);
+#endif
+
if (end > max_low_pfn)
max_low_pfn = end;
if (start < min_low_pfn)
diff --git a/arch/mips/kernel/smp-gic.c b/arch/mips/kernel/smp-gic.c
deleted file mode 100644
index 9b63829..0000000
--- a/arch/mips/kernel/smp-gic.c
+++ /dev/null
@@ -1,66 +0,0 @@
-/*
- * Copyright (C) 2013 Imagination Technologies
- * Author: Paul Burton <paul.burton@imgtec.com>
- *
- * Based on smp-cmp.c:
- * Copyright (C) 2007 MIPS Technologies, Inc.
- * Author: Chris Dearman (chris@mips.com)
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- */
-
-#include <linux/irqchip/mips-gic.h>
-#include <linux/printk.h>
-
-#include <asm/mips-cpc.h>
-#include <asm/smp-ops.h>
-
-void gic_send_ipi_single(int cpu, unsigned int action)
-{
- unsigned long flags;
- unsigned int intr;
- unsigned int core = cpu_data[cpu].core;
-
- pr_debug("CPU%d: %s cpu %d action %u status %08x\n",
- smp_processor_id(), __func__, cpu, action, read_c0_status());
-
- local_irq_save(flags);
-
- switch (action) {
- case SMP_CALL_FUNCTION:
- intr = plat_ipi_call_int_xlate(cpu);
- break;
-
- case SMP_RESCHEDULE_YOURSELF:
- intr = plat_ipi_resched_int_xlate(cpu);
- break;
-
- default:
- BUG();
- }
-
- gic_send_ipi(intr);
-
- if (mips_cpc_present() && (core != current_cpu_data.core)) {
- while (!cpumask_test_cpu(cpu, &cpu_coherent_mask)) {
- mips_cm_lock_other(core, 0);
- mips_cpc_lock_other(core);
- write_cpc_co_cmd(CPC_Cx_CMD_PWRUP);
- mips_cpc_unlock_other();
- mips_cm_unlock_other();
- }
- }
-
- local_irq_restore(flags);
-}
-
-void gic_send_ipi_mask(const struct cpumask *mask, unsigned int action)
-{
- unsigned int i;
-
- for_each_cpu(i, mask)
- gic_send_ipi_single(i, action);
-}
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index 4f9570a..e077ea3 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -289,26 +289,3 @@ struct plat_smp_ops vsmp_smp_ops = {
.prepare_cpus = vsmp_prepare_cpus,
};
-#ifdef CONFIG_PROC_FS
-static int proc_cpuinfo_chain_call(struct notifier_block *nfb,
- unsigned long action_unused, void *data)
-{
- struct proc_cpuinfo_notifier_args *pcn = data;
- struct seq_file *m = pcn->m;
- unsigned long n = pcn->n;
-
- if (!cpu_has_mipsmt)
- return NOTIFY_OK;
-
- seq_printf(m, "VPE\t\t\t: %d\n", cpu_data[n].vpe_id);
-
- return NOTIFY_OK;
-}
-
-static int __init proc_cpuinfo_notifier_init(void)
-{
- return proc_cpuinfo_notifier(proc_cpuinfo_chain_call, 0);
-}
-
-subsys_initcall(proc_cpuinfo_notifier_init);
-#endif
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index b0baf48..7ebb191 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -25,7 +25,7 @@
#include <linux/smp.h>
#include <linux/spinlock.h>
#include <linux/threads.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/time.h>
#include <linux/timex.h>
#include <linux/sched.h>
@@ -192,9 +192,11 @@ void mips_smp_send_ipi_mask(const struct cpumask *mask, unsigned int action)
continue;
while (!cpumask_test_cpu(cpu, &cpu_coherent_mask)) {
+ mips_cm_lock_other(core, 0);
mips_cpc_lock_other(core);
write_cpc_co_cmd(CPC_Cx_CMD_PWRUP);
mips_cpc_unlock_other();
+ mips_cm_unlock_other();
}
}
}
@@ -229,7 +231,7 @@ static struct irqaction irq_call = {
.name = "IPI call"
};
-static __init void smp_ipi_init_one(unsigned int virq,
+static void smp_ipi_init_one(unsigned int virq,
struct irqaction *action)
{
int ret;
@@ -239,9 +241,11 @@ static __init void smp_ipi_init_one(unsigned int virq,
BUG_ON(ret);
}
-static int __init mips_smp_ipi_init(void)
+static unsigned int call_virq, sched_virq;
+
+int mips_smp_ipi_allocate(const struct cpumask *mask)
{
- unsigned int call_virq, sched_virq;
+ int virq;
struct irq_domain *ipidomain;
struct device_node *node;
@@ -268,16 +272,20 @@ static int __init mips_smp_ipi_init(void)
if (!ipidomain)
return 0;
- call_virq = irq_reserve_ipi(ipidomain, cpu_possible_mask);
- BUG_ON(!call_virq);
+ virq = irq_reserve_ipi(ipidomain, mask);
+ BUG_ON(!virq);
+ if (!call_virq)
+ call_virq = virq;
- sched_virq = irq_reserve_ipi(ipidomain, cpu_possible_mask);
- BUG_ON(!sched_virq);
+ virq = irq_reserve_ipi(ipidomain, mask);
+ BUG_ON(!virq);
+ if (!sched_virq)
+ sched_virq = virq;
if (irq_domain_is_ipi_per_cpu(ipidomain)) {
int cpu;
- for_each_cpu(cpu, cpu_possible_mask) {
+ for_each_cpu(cpu, mask) {
smp_ipi_init_one(call_virq + cpu, &irq_call);
smp_ipi_init_one(sched_virq + cpu, &irq_resched);
}
@@ -286,6 +294,45 @@ static int __init mips_smp_ipi_init(void)
smp_ipi_init_one(sched_virq, &irq_resched);
}
+ return 0;
+}
+
+int mips_smp_ipi_free(const struct cpumask *mask)
+{
+ struct irq_domain *ipidomain;
+ struct device_node *node;
+
+ node = of_irq_find_parent(of_root);
+ ipidomain = irq_find_matching_host(node, DOMAIN_BUS_IPI);
+
+ /*
+ * Some platforms have half DT setup. So if we found irq node but
+ * didn't find an ipidomain, try to search for one that is not in the
+ * DT.
+ */
+ if (node && !ipidomain)
+ ipidomain = irq_find_matching_host(NULL, DOMAIN_BUS_IPI);
+
+ BUG_ON(!ipidomain);
+
+ if (irq_domain_is_ipi_per_cpu(ipidomain)) {
+ int cpu;
+
+ for_each_cpu(cpu, mask) {
+ remove_irq(call_virq + cpu, &irq_call);
+ remove_irq(sched_virq + cpu, &irq_resched);
+ }
+ }
+ irq_destroy_ipi(call_virq, mask);
+ irq_destroy_ipi(sched_virq, mask);
+ return 0;
+}
+
+
+static int __init mips_smp_ipi_init(void)
+{
+ mips_smp_ipi_allocate(cpu_possible_mask);
+
call_desc = irq_to_desc(call_virq);
sched_desc = irq_to_desc(sched_virq);
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 3de85be..3905003 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -21,6 +21,7 @@
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/smp.h>
@@ -48,6 +49,7 @@
#include <asm/fpu.h>
#include <asm/fpu_emulator.h>
#include <asm/idle.h>
+#include <asm/mips-cm.h>
#include <asm/mips-r2-to-r6-emul.h>
#include <asm/mipsregs.h>
#include <asm/mipsmtregs.h>
@@ -154,7 +156,7 @@ static void show_backtrace(struct task_struct *task, const struct pt_regs *regs)
print_ip_sym(pc);
pc = unwind_stack(task, &sp, pc, &ra);
} while (pc);
- printk("\n");
+ pr_cont("\n");
}
/*
@@ -172,22 +174,24 @@ static void show_stacktrace(struct task_struct *task,
printk("Stack :");
i = 0;
while ((unsigned long) sp & (PAGE_SIZE - 1)) {
- if (i && ((i % (64 / field)) == 0))
- printk("\n ");
+ if (i && ((i % (64 / field)) == 0)) {
+ pr_cont("\n");
+ printk(" ");
+ }
if (i > 39) {
- printk(" ...");
+ pr_cont(" ...");
break;
}
if (__get_user(stackdata, sp++)) {
- printk(" (Bad stack address)");
+ pr_cont(" (Bad stack address)");
break;
}
- printk(" %0*lx", field, stackdata);
+ pr_cont(" %0*lx", field, stackdata);
i++;
}
- printk("\n");
+ pr_cont("\n");
show_backtrace(task, regs);
}
@@ -227,18 +231,19 @@ static void show_code(unsigned int __user *pc)
long i;
unsigned short __user *pc16 = NULL;
- printk("\nCode:");
+ printk("Code:");
if ((unsigned long)pc & 1)
pc16 = (unsigned short __user *)((unsigned long)pc & ~1);
for(i = -3 ; i < 6 ; i++) {
unsigned int insn;
if (pc16 ? __get_user(insn, pc16 + i) : __get_user(insn, pc + i)) {
- printk(" (Bad address in epc)\n");
+ pr_cont(" (Bad address in epc)\n");
break;
}
- printk("%c%0*x%c", (i?' ':'<'), pc16 ? 4 : 8, insn, (i?' ':'>'));
+ pr_cont("%c%0*x%c", (i?' ':'<'), pc16 ? 4 : 8, insn, (i?' ':'>'));
}
+ pr_cont("\n");
}
static void __show_regs(const struct pt_regs *regs)
@@ -257,15 +262,15 @@ static void __show_regs(const struct pt_regs *regs)
if ((i % 4) == 0)
printk("$%2d :", i);
if (i == 0)
- printk(" %0*lx", field, 0UL);
+ pr_cont(" %0*lx", field, 0UL);
else if (i == 26 || i == 27)
- printk(" %*s", field, "");
+ pr_cont(" %*s", field, "");
else
- printk(" %0*lx", field, regs->regs[i]);
+ pr_cont(" %0*lx", field, regs->regs[i]);
i++;
if ((i % 4) == 0)
- printk("\n");
+ pr_cont("\n");
}
#ifdef CONFIG_CPU_HAS_SMARTMIPS
@@ -286,46 +291,46 @@ static void __show_regs(const struct pt_regs *regs)
if (cpu_has_3kex) {
if (regs->cp0_status & ST0_KUO)
- printk("KUo ");
+ pr_cont("KUo ");
if (regs->cp0_status & ST0_IEO)
- printk("IEo ");
+ pr_cont("IEo ");
if (regs->cp0_status & ST0_KUP)
- printk("KUp ");
+ pr_cont("KUp ");
if (regs->cp0_status & ST0_IEP)
- printk("IEp ");
+ pr_cont("IEp ");
if (regs->cp0_status & ST0_KUC)
- printk("KUc ");
+ pr_cont("KUc ");
if (regs->cp0_status & ST0_IEC)
- printk("IEc ");
+ pr_cont("IEc ");
} else if (cpu_has_4kex) {
if (regs->cp0_status & ST0_KX)
- printk("KX ");
+ pr_cont("KX ");
if (regs->cp0_status & ST0_SX)
- printk("SX ");
+ pr_cont("SX ");
if (regs->cp0_status & ST0_UX)
- printk("UX ");
+ pr_cont("UX ");
switch (regs->cp0_status & ST0_KSU) {
case KSU_USER:
- printk("USER ");
+ pr_cont("USER ");
break;
case KSU_SUPERVISOR:
- printk("SUPERVISOR ");
+ pr_cont("SUPERVISOR ");
break;
case KSU_KERNEL:
- printk("KERNEL ");
+ pr_cont("KERNEL ");
break;
default:
- printk("BAD_MODE ");
+ pr_cont("BAD_MODE ");
break;
}
if (regs->cp0_status & ST0_ERL)
- printk("ERL ");
+ pr_cont("ERL ");
if (regs->cp0_status & ST0_EXL)
- printk("EXL ");
+ pr_cont("EXL ");
if (regs->cp0_status & ST0_IE)
- printk("IE ");
+ pr_cont("IE ");
}
- printk("\n");
+ pr_cont("\n");
exccode = (cause & CAUSEF_EXCCODE) >> CAUSEB_EXCCODE;
printk("Cause : %08x (ExcCode %02x)\n", cause, exccode);
@@ -444,6 +449,8 @@ asmlinkage void do_be(struct pt_regs *regs)
if (board_be_handler)
action = board_be_handler(regs, fixup != NULL);
+ else
+ mips_cm_error_report();
switch (action) {
case MIPS_BE_DISCARD:
@@ -701,6 +708,32 @@ asmlinkage void do_ov(struct pt_regs *regs)
exception_exit(prev_state);
}
+/*
+ * Send SIGFPE according to FCSR Cause bits, which must have already
+ * been masked against Enable bits. This is impotant as Inexact can
+ * happen together with Overflow or Underflow, and `ptrace' can set
+ * any bits.
+ */
+void force_fcr31_sig(unsigned long fcr31, void __user *fault_addr,
+ struct task_struct *tsk)
+{
+ struct siginfo si = { .si_addr = fault_addr, .si_signo = SIGFPE };
+
+ if (fcr31 & FPU_CSR_INV_X)
+ si.si_code = FPE_FLTINV;
+ else if (fcr31 & FPU_CSR_DIV_X)
+ si.si_code = FPE_FLTDIV;
+ else if (fcr31 & FPU_CSR_OVF_X)
+ si.si_code = FPE_FLTOVF;
+ else if (fcr31 & FPU_CSR_UDF_X)
+ si.si_code = FPE_FLTUND;
+ else if (fcr31 & FPU_CSR_INE_X)
+ si.si_code = FPE_FLTRES;
+ else
+ si.si_code = __SI_FAULT;
+ force_sig_info(SIGFPE, &si, tsk);
+}
+
int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
{
struct siginfo si = { 0 };
@@ -711,27 +744,7 @@ int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
return 0;
case SIGFPE:
- si.si_addr = fault_addr;
- si.si_signo = sig;
- /*
- * Inexact can happen together with Overflow or Underflow.
- * Respect the mask to deliver the correct exception.
- */
- fcr31 &= (fcr31 & FPU_CSR_ALL_E) <<
- (ffs(FPU_CSR_ALL_X) - ffs(FPU_CSR_ALL_E));
- if (fcr31 & FPU_CSR_INV_X)
- si.si_code = FPE_FLTINV;
- else if (fcr31 & FPU_CSR_DIV_X)
- si.si_code = FPE_FLTDIV;
- else if (fcr31 & FPU_CSR_OVF_X)
- si.si_code = FPE_FLTOVF;
- else if (fcr31 & FPU_CSR_UDF_X)
- si.si_code = FPE_FLTUND;
- else if (fcr31 & FPU_CSR_INE_X)
- si.si_code = FPE_FLTRES;
- else
- si.si_code = __SI_FAULT;
- force_sig_info(sig, &si, current);
+ force_fcr31_sig(fcr31, fault_addr, current);
return 1;
case SIGBUS:
@@ -795,13 +808,13 @@ static int simulate_fp(struct pt_regs *regs, unsigned int opcode,
/* Run the emulator */
sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1,
&fault_addr);
- fcr31 = current->thread.fpu.fcr31;
/*
- * We can't allow the emulated instruction to leave any of
- * the cause bits set in $fcr31.
+ * We can't allow the emulated instruction to leave any
+ * enabled Cause bits set in $fcr31.
*/
- current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X;
+ fcr31 = mask_fcr31_x(current->thread.fpu.fcr31);
+ current->thread.fpu.fcr31 &= ~fcr31;
/* Restore the hardware register state */
own_fpu(1);
@@ -827,7 +840,7 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
goto out;
/* Clear FCSR.Cause before enabling interrupts */
- write_32bit_cp1_register(CP1_STATUS, fcr31 & ~FPU_CSR_ALL_X);
+ write_32bit_cp1_register(CP1_STATUS, fcr31 & ~mask_fcr31_x(fcr31));
local_irq_enable();
die_if_kernel("FP exception in kernel code", regs);
@@ -849,13 +862,13 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
/* Run the emulator */
sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1,
&fault_addr);
- fcr31 = current->thread.fpu.fcr31;
/*
- * We can't allow the emulated instruction to leave any of
- * the cause bits set in $fcr31.
+ * We can't allow the emulated instruction to leave any
+ * enabled Cause bits set in $fcr31.
*/
- current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X;
+ fcr31 = mask_fcr31_x(current->thread.fpu.fcr31);
+ current->thread.fpu.fcr31 &= ~fcr31;
/* Restore the hardware register state */
own_fpu(1); /* Using the FPU again. */
@@ -1420,13 +1433,13 @@ asmlinkage void do_cpu(struct pt_regs *regs)
sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 0,
&fault_addr);
- fcr31 = current->thread.fpu.fcr31;
/*
* We can't allow the emulated instruction to leave
- * any of the cause bits set in $fcr31.
+ * any enabled Cause bits set in $fcr31.
*/
- current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X;
+ fcr31 = mask_fcr31_x(current->thread.fpu.fcr31);
+ current->thread.fpu.fcr31 &= ~fcr31;
/* Send a signal if required. */
if (!process_fpemu_return(sig, fault_addr, fcr31) && !err)
@@ -2091,6 +2104,14 @@ static void configure_exception_vector(void)
{
if (cpu_has_veic || cpu_has_vint) {
unsigned long sr = set_c0_status(ST0_BEV);
+ /* If available, use WG to set top bits of EBASE */
+ if (cpu_has_ebase_wg) {
+#ifdef CONFIG_64BIT
+ write_c0_ebase_64(ebase | MIPS_EBASE_WG);
+#else
+ write_c0_ebase(ebase | MIPS_EBASE_WG);
+#endif
+ }
write_c0_ebase(ebase);
write_c0_status(sr);
/* Setting vector spacing enables EI/VI mode */
@@ -2127,8 +2148,17 @@ void per_cpu_trap_init(bool is_boot_cpu)
* We shouldn't trust a secondary core has a sane EBASE register
* so use the one calculated by the boot CPU.
*/
- if (!is_boot_cpu)
+ if (!is_boot_cpu) {
+ /* If available, use WG to set top bits of EBASE */
+ if (cpu_has_ebase_wg) {
+#ifdef CONFIG_64BIT
+ write_c0_ebase_64(ebase | MIPS_EBASE_WG);
+#else
+ write_c0_ebase(ebase | MIPS_EBASE_WG);
+#endif
+ }
write_c0_ebase(ebase);
+ }
cp0_compare_irq_shift = CAUSEB_TI - CAUSEB_IP;
cp0_compare_irq = (read_c0_intctl() >> INTCTLB_IPTI) & 7;
@@ -2209,13 +2239,39 @@ void __init trap_init(void)
if (cpu_has_veic || cpu_has_vint) {
unsigned long size = 0x200 + VECTORSPACING*64;
+ phys_addr_t ebase_pa;
+
ebase = (unsigned long)
__alloc_bootmem(size, 1 << fls(size), 0);
+
+ /*
+ * Try to ensure ebase resides in KSeg0 if possible.
+ *
+ * It shouldn't generally be in XKPhys on MIPS64 to avoid
+ * hitting a poorly defined exception base for Cache Errors.
+ * The allocation is likely to be in the low 512MB of physical,
+ * in which case we should be able to convert to KSeg0.
+ *
+ * EVA is special though as it allows segments to be rearranged
+ * and to become uncached during cache error handling.
+ */
+ ebase_pa = __pa(ebase);
+ if (!IS_ENABLED(CONFIG_EVA) && !WARN_ON(ebase_pa >= 0x20000000))
+ ebase = CKSEG0ADDR(ebase_pa);
} else {
ebase = CAC_BASE;
- if (cpu_has_mips_r2_r6)
- ebase += (read_c0_ebase() & 0x3ffff000);
+ if (cpu_has_mips_r2_r6) {
+ if (cpu_has_ebase_wg) {
+#ifdef CONFIG_64BIT
+ ebase = (read_c0_ebase_64() & ~0xfff);
+#else
+ ebase = (read_c0_ebase() & ~0xfff);
+#endif
+ } else {
+ ebase += (read_c0_ebase() & 0x3ffff000);
+ }
+ }
}
if (cpu_has_mmips) {
diff --git a/arch/mips/kernel/uprobes.c b/arch/mips/kernel/uprobes.c
index 4c7c155..dbb9174 100644
--- a/arch/mips/kernel/uprobes.c
+++ b/arch/mips/kernel/uprobes.c
@@ -8,71 +8,12 @@
#include <asm/branch.h>
#include <asm/cpu-features.h>
#include <asm/ptrace.h>
-#include <asm/inst.h>
+
+#include "probes-common.h"
static inline int insn_has_delay_slot(const union mips_instruction insn)
{
- switch (insn.i_format.opcode) {
- /*
- * jr and jalr are in r_format format.
- */
- case spec_op:
- switch (insn.r_format.func) {
- case jalr_op:
- case jr_op:
- return 1;
- }
- break;
-
- /*
- * This group contains:
- * bltz_op, bgez_op, bltzl_op, bgezl_op,
- * bltzal_op, bgezal_op, bltzall_op, bgezall_op.
- */
- case bcond_op:
- switch (insn.i_format.rt) {
- case bltz_op:
- case bltzl_op:
- case bgez_op:
- case bgezl_op:
- case bltzal_op:
- case bltzall_op:
- case bgezal_op:
- case bgezall_op:
- case bposge32_op:
- return 1;
- }
- break;
-
- /*
- * These are unconditional and in j_format.
- */
- case jal_op:
- case j_op:
- case beq_op:
- case beql_op:
- case bne_op:
- case bnel_op:
- case blez_op: /* not really i_format */
- case blezl_op:
- case bgtz_op:
- case bgtzl_op:
- return 1;
-
- /*
- * And now the FPA/cp1 branch instructions.
- */
- case cop1_op:
-#ifdef CONFIG_CPU_CAVIUM_OCTEON
- case lwc2_op: /* This is bbit0 on Octeon */
- case ldc2_op: /* This is bbit032 on Octeon */
- case swc2_op: /* This is bbit1 on Octeon */
- case sdc2_op: /* This is bbit132 on Octeon */
-#endif
- return 1;
- }
-
- return 0;
+ return __insn_has_delay_slot(insn);
}
/**
@@ -95,6 +36,12 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *aup,
return -EINVAL;
inst.word = aup->insn[0];
+
+ if (__insn_is_compact_branch(inst)) {
+ pr_notice("Uprobes for compact branches are not supported\n");
+ return -EINVAL;
+ }
+
aup->ixol[0] = aup->insn[insn_has_delay_slot(inst)];
aup->ixol[1] = UPROBE_BRK_UPROBE_XOL; /* NOP */
@@ -282,19 +229,14 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm,
void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
void *src, unsigned long len)
{
- void *kaddr;
+ unsigned long kaddr, kstart;
/* Initialize the slot */
- kaddr = kmap_atomic(page);
- memcpy(kaddr + (vaddr & ~PAGE_MASK), src, len);
- kunmap_atomic(kaddr);
-
- /*
- * The MIPS version of flush_icache_range will operate safely on
- * user space addresses and more importantly, it doesn't require a
- * VMA argument.
- */
- flush_icache_range(vaddr, vaddr + len);
+ kaddr = (unsigned long)kmap_atomic(page);
+ kstart = kaddr + (vaddr & ~PAGE_MASK);
+ memcpy((void *)kstart, src, len);
+ flush_icache_range(kstart, kstart + len);
+ kunmap_atomic((void *)kaddr);
}
/**
diff --git a/arch/mips/kvm/commpage.c b/arch/mips/kvm/commpage.c
index a36b77e..f436299 100644
--- a/arch/mips/kvm/commpage.c
+++ b/arch/mips/kvm/commpage.c
@@ -12,7 +12,6 @@
#include <linux/errno.h>
#include <linux/err.h>
-#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
#include <linux/bootmem.h>
diff --git a/arch/mips/kvm/dyntrans.c b/arch/mips/kvm/dyntrans.c
index d280894..010cef2 100644
--- a/arch/mips/kvm/dyntrans.c
+++ b/arch/mips/kvm/dyntrans.c
@@ -13,7 +13,6 @@
#include <linux/err.h>
#include <linux/highmem.h>
#include <linux/kvm_host.h>
-#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
#include <linux/bootmem.h>
@@ -45,8 +44,8 @@ static int kvm_mips_trans_replace(struct kvm_vcpu *vcpu, u32 *opc,
} else if (KVM_GUEST_KSEGX((unsigned long) opc) == KVM_GUEST_KSEG23) {
local_irq_save(flags);
memcpy((void *)opc, (void *)&replace, sizeof(u32));
- local_flush_icache_range((unsigned long)opc,
- (unsigned long)opc + 32);
+ __local_flush_icache_user_range((unsigned long)opc,
+ (unsigned long)opc + 32);
local_irq_restore(flags);
} else {
kvm_err("%s: Invalid address: %p\n", __func__, opc);
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index 4db4c03..aa09374 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -13,7 +13,6 @@
#include <linux/err.h>
#include <linux/ktime.h>
#include <linux/kvm_host.h>
-#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
#include <linux/bootmem.h>
@@ -791,15 +790,15 @@ enum emulation_result kvm_mips_emul_eret(struct kvm_vcpu *vcpu)
struct mips_coproc *cop0 = vcpu->arch.cop0;
enum emulation_result er = EMULATE_DONE;
- if (kvm_read_c0_guest_status(cop0) & ST0_EXL) {
+ if (kvm_read_c0_guest_status(cop0) & ST0_ERL) {
+ kvm_clear_c0_guest_status(cop0, ST0_ERL);
+ vcpu->arch.pc = kvm_read_c0_guest_errorepc(cop0);
+ } else if (kvm_read_c0_guest_status(cop0) & ST0_EXL) {
kvm_debug("[%#lx] ERET to %#lx\n", vcpu->arch.pc,
kvm_read_c0_guest_epc(cop0));
kvm_clear_c0_guest_status(cop0, ST0_EXL);
vcpu->arch.pc = kvm_read_c0_guest_epc(cop0);
- } else if (kvm_read_c0_guest_status(cop0) & ST0_ERL) {
- kvm_clear_c0_guest_status(cop0, ST0_ERL);
- vcpu->arch.pc = kvm_read_c0_guest_errorepc(cop0);
} else {
kvm_err("[%#lx] ERET when MIPS_SR_EXL|MIPS_SR_ERL == 0\n",
vcpu->arch.pc);
@@ -1529,13 +1528,25 @@ enum emulation_result kvm_mips_emulate_load(union mips_instruction inst,
struct kvm_vcpu *vcpu)
{
enum emulation_result er = EMULATE_DO_MMIO;
+ unsigned long curr_pc;
u32 op, rt;
u32 bytes;
rt = inst.i_format.rt;
op = inst.i_format.opcode;
- vcpu->arch.pending_load_cause = cause;
+ /*
+ * Find the resume PC now while we have safe and easy access to the
+ * prior branch instruction, and save it for
+ * kvm_mips_complete_mmio_load() to restore later.
+ */
+ curr_pc = vcpu->arch.pc;
+ er = update_pc(vcpu, cause);
+ if (er == EMULATE_FAIL)
+ return er;
+ vcpu->arch.io_pc = vcpu->arch.pc;
+ vcpu->arch.pc = curr_pc;
+
vcpu->arch.io_gpr = rt;
switch (op) {
@@ -2495,9 +2506,8 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
goto done;
}
- er = update_pc(vcpu, vcpu->arch.pending_load_cause);
- if (er == EMULATE_FAIL)
- return er;
+ /* Restore saved resume PC */
+ vcpu->arch.pc = vcpu->arch.io_pc;
switch (run->mmio.len) {
case 4:
@@ -2519,11 +2529,6 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
break;
}
- if (vcpu->arch.pending_load_cause & CAUSEF_BD)
- kvm_debug("[%#lx] Completing %d byte BD Load to gpr %d (0x%08lx) type %d\n",
- vcpu->arch.pc, run->mmio.len, vcpu->arch.io_gpr, *gpr,
- vcpu->mmio_needed);
-
done:
return er;
}
diff --git a/arch/mips/kvm/interrupt.c b/arch/mips/kvm/interrupt.c
index ad28dac..e88403b 100644
--- a/arch/mips/kvm/interrupt.c
+++ b/arch/mips/kvm/interrupt.c
@@ -11,7 +11,6 @@
#include <linux/errno.h>
#include <linux/err.h>
-#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
#include <linux/bootmem.h>
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index ce96149..06a60b1 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -14,6 +14,7 @@
#include <linux/err.h>
#include <linux/kdebug.h>
#include <linux/module.h>
+#include <linux/uaccess.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
#include <linux/bootmem.h>
@@ -425,7 +426,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
static void kvm_mips_check_asids(struct kvm_vcpu *vcpu)
{
struct mips_coproc *cop0 = vcpu->arch.cop0;
- int cpu = smp_processor_id();
+ int i, cpu = smp_processor_id();
unsigned int gasid;
/*
@@ -441,6 +442,9 @@ static void kvm_mips_check_asids(struct kvm_vcpu *vcpu)
vcpu);
vcpu->arch.guest_user_asid[cpu] =
vcpu->arch.guest_user_mm.context.asid[cpu];
+ for_each_possible_cpu(i)
+ if (i != cpu)
+ vcpu->arch.guest_user_asid[cpu] = 0;
vcpu->arch.last_user_gasid = gasid;
}
}
diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c
index 03883ba..3b677c8 100644
--- a/arch/mips/kvm/mmu.c
+++ b/arch/mips/kvm/mmu.c
@@ -260,13 +260,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
if ((vcpu->arch.guest_user_asid[cpu] ^ asid_cache(cpu)) &
asid_version_mask(cpu)) {
- u32 gasid = kvm_read_c0_guest_entryhi(vcpu->arch.cop0) &
- KVM_ENTRYHI_ASID;
-
kvm_get_new_mmu_context(&vcpu->arch.guest_user_mm, cpu, vcpu);
vcpu->arch.guest_user_asid[cpu] =
vcpu->arch.guest_user_mm.context.asid[cpu];
- vcpu->arch.last_user_gasid = gasid;
newasid++;
kvm_debug("[%d]: cpu_context: %#lx\n", cpu,
diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c
index 3a5484f..3b20441 100644
--- a/arch/mips/kvm/trap_emul.c
+++ b/arch/mips/kvm/trap_emul.c
@@ -11,7 +11,6 @@
#include <linux/errno.h>
#include <linux/err.h>
-#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/kvm_host.h>
diff --git a/arch/mips/lantiq/xway/vmmc.c b/arch/mips/lantiq/xway/vmmc.c
index 4625495..577ec81 100644
--- a/arch/mips/lantiq/xway/vmmc.c
+++ b/arch/mips/lantiq/xway/vmmc.c
@@ -6,7 +6,7 @@
* Copyright (C) 2012 John Crispin <john@phrozen.org>
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/of_platform.h>
#include <linux/of_gpio.h>
#include <linux/dma-mapping.h>
@@ -55,7 +55,6 @@ static const struct of_device_id vmmc_match[] = {
{ .compatible = "lantiq,vmmc-xway" },
{},
};
-MODULE_DEVICE_TABLE(of, vmmc_match);
static struct platform_driver vmmc_driver = {
.probe = vmmc_probe,
@@ -64,5 +63,4 @@ static struct platform_driver vmmc_driver = {
.of_match_table = vmmc_match,
},
};
-
-module_platform_driver(vmmc_driver);
+builtin_platform_driver(vmmc_driver);
diff --git a/arch/mips/lantiq/xway/xrx200_phy_fw.c b/arch/mips/lantiq/xway/xrx200_phy_fw.c
index 71e518c..f0a0f2d 100644
--- a/arch/mips/lantiq/xway/xrx200_phy_fw.c
+++ b/arch/mips/lantiq/xway/xrx200_phy_fw.c
@@ -1,4 +1,7 @@
/*
+ * Lantiq XRX200 PHY Firmware Loader
+ * Author: John Crispin
+ *
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
* by the Free Software Foundation.
@@ -8,7 +11,6 @@
#include <linux/delay.h>
#include <linux/dma-mapping.h>
-#include <linux/module.h>
#include <linux/firmware.h>
#include <linux/of_platform.h>
@@ -100,7 +102,6 @@ static const struct of_device_id xway_phy_match[] = {
{ .compatible = "lantiq,phy-xrx200" },
{},
};
-MODULE_DEVICE_TABLE(of, xway_phy_match);
static struct platform_driver xway_phy_driver = {
.probe = xway_phy_fw_probe,
@@ -109,9 +110,4 @@ static struct platform_driver xway_phy_driver = {
.of_match_table = xway_phy_match,
},
};
-
-module_platform_driver(xway_phy_driver);
-
-MODULE_AUTHOR("John Crispin <john@phrozen.org>");
-MODULE_DESCRIPTION("Lantiq XRX200 PHY Firmware Loader");
-MODULE_LICENSE("GPL");
+builtin_platform_driver(xway_phy_driver);
diff --git a/arch/mips/lib/ashldi3.c b/arch/mips/lib/ashldi3.c
index 927dc94..c3e2205 100644
--- a/arch/mips/lib/ashldi3.c
+++ b/arch/mips/lib/ashldi3.c
@@ -1,4 +1,4 @@
-#include <linux/module.h>
+#include <linux/export.h>
#include "libgcc.h"
diff --git a/arch/mips/lib/ashrdi3.c b/arch/mips/lib/ashrdi3.c
index 9fdf1a5..1745602 100644
--- a/arch/mips/lib/ashrdi3.c
+++ b/arch/mips/lib/ashrdi3.c
@@ -1,4 +1,4 @@
-#include <linux/module.h>
+#include <linux/export.h>
#include "libgcc.h"
diff --git a/arch/mips/lib/bswapdi.c b/arch/mips/lib/bswapdi.c
index e3e77aa..a811414 100644
--- a/arch/mips/lib/bswapdi.c
+++ b/arch/mips/lib/bswapdi.c
@@ -1,4 +1,5 @@
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/compiler.h>
unsigned long long notrace __bswapdi2(unsigned long long u)
{
diff --git a/arch/mips/lib/bswapsi.c b/arch/mips/lib/bswapsi.c
index 530a8af..106fd97 100644
--- a/arch/mips/lib/bswapsi.c
+++ b/arch/mips/lib/bswapsi.c
@@ -1,4 +1,5 @@
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/compiler.h>
unsigned int notrace __bswapsi2(unsigned int u)
{
diff --git a/arch/mips/lib/cmpdi2.c b/arch/mips/lib/cmpdi2.c
index 06857da..9d849d8 100644
--- a/arch/mips/lib/cmpdi2.c
+++ b/arch/mips/lib/cmpdi2.c
@@ -1,4 +1,4 @@
-#include <linux/module.h>
+#include <linux/export.h>
#include "libgcc.h"
diff --git a/arch/mips/lib/delay.c b/arch/mips/lib/delay.c
index 21d27c6..2307a3c 100644
--- a/arch/mips/lib/delay.c
+++ b/arch/mips/lib/delay.c
@@ -8,7 +8,7 @@
* Copyright (C) 1999, 2000 Silicon Graphics, Inc.
* Copyright (C) 2007, 2014 Maciej W. Rozycki
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/param.h>
#include <linux/smp.h>
#include <linux/stringify.h>
diff --git a/arch/mips/lib/dump_tlb.c b/arch/mips/lib/dump_tlb.c
index 0f80b93..6eb50a7 100644
--- a/arch/mips/lib/dump_tlb.c
+++ b/arch/mips/lib/dump_tlb.c
@@ -135,42 +135,42 @@ static void dump_tlb(int first, int last)
c0 = (entrylo0 & ENTRYLO_C) >> ENTRYLO_C_SHIFT;
c1 = (entrylo1 & ENTRYLO_C) >> ENTRYLO_C_SHIFT;
- printk("va=%0*lx asid=%0*lx",
- vwidth, (entryhi & ~0x1fffUL),
- asidwidth, entryhi & asidmask);
+ pr_cont("va=%0*lx asid=%0*lx",
+ vwidth, (entryhi & ~0x1fffUL),
+ asidwidth, entryhi & asidmask);
if (cpu_has_guestid)
- printk(" gid=%02lx",
- (guestctl1 & MIPS_GCTL1_RID)
+ pr_cont(" gid=%02lx",
+ (guestctl1 & MIPS_GCTL1_RID)
>> MIPS_GCTL1_RID_SHIFT);
/* RI/XI are in awkward places, so mask them off separately */
pa = entrylo0 & ~(MIPS_ENTRYLO_RI | MIPS_ENTRYLO_XI);
if (xpa)
pa |= (unsigned long long)readx_c0_entrylo0() << 30;
pa = (pa << 6) & PAGE_MASK;
- printk("\n\t[");
+ pr_cont("\n\t[");
if (cpu_has_rixi)
- printk("ri=%d xi=%d ",
- (entrylo0 & MIPS_ENTRYLO_RI) ? 1 : 0,
- (entrylo0 & MIPS_ENTRYLO_XI) ? 1 : 0);
- printk("pa=%0*llx c=%d d=%d v=%d g=%d] [",
- pwidth, pa, c0,
- (entrylo0 & ENTRYLO_D) ? 1 : 0,
- (entrylo0 & ENTRYLO_V) ? 1 : 0,
- (entrylo0 & ENTRYLO_G) ? 1 : 0);
+ pr_cont("ri=%d xi=%d ",
+ (entrylo0 & MIPS_ENTRYLO_RI) ? 1 : 0,
+ (entrylo0 & MIPS_ENTRYLO_XI) ? 1 : 0);
+ pr_cont("pa=%0*llx c=%d d=%d v=%d g=%d] [",
+ pwidth, pa, c0,
+ (entrylo0 & ENTRYLO_D) ? 1 : 0,
+ (entrylo0 & ENTRYLO_V) ? 1 : 0,
+ (entrylo0 & ENTRYLO_G) ? 1 : 0);
/* RI/XI are in awkward places, so mask them off separately */
pa = entrylo1 & ~(MIPS_ENTRYLO_RI | MIPS_ENTRYLO_XI);
if (xpa)
pa |= (unsigned long long)readx_c0_entrylo1() << 30;
pa = (pa << 6) & PAGE_MASK;
if (cpu_has_rixi)
- printk("ri=%d xi=%d ",
- (entrylo1 & MIPS_ENTRYLO_RI) ? 1 : 0,
- (entrylo1 & MIPS_ENTRYLO_XI) ? 1 : 0);
- printk("pa=%0*llx c=%d d=%d v=%d g=%d]\n",
- pwidth, pa, c1,
- (entrylo1 & ENTRYLO_D) ? 1 : 0,
- (entrylo1 & ENTRYLO_V) ? 1 : 0,
- (entrylo1 & ENTRYLO_G) ? 1 : 0);
+ pr_cont("ri=%d xi=%d ",
+ (entrylo1 & MIPS_ENTRYLO_RI) ? 1 : 0,
+ (entrylo1 & MIPS_ENTRYLO_XI) ? 1 : 0);
+ pr_cont("pa=%0*llx c=%d d=%d v=%d g=%d]\n",
+ pwidth, pa, c1,
+ (entrylo1 & ENTRYLO_D) ? 1 : 0,
+ (entrylo1 & ENTRYLO_V) ? 1 : 0,
+ (entrylo1 & ENTRYLO_G) ? 1 : 0);
}
printk("\n");
diff --git a/arch/mips/lib/iomap-pci.c b/arch/mips/lib/iomap-pci.c
index fd35daa..8ed3f25 100644
--- a/arch/mips/lib/iomap-pci.c
+++ b/arch/mips/lib/iomap-pci.c
@@ -7,9 +7,11 @@
* written by Ralf Baechle <ralf@linux-mips.org>
*/
#include <linux/pci.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <asm/io.h>
+#ifdef CONFIG_PCI_DRIVERS_LEGACY
+
void __iomem *__pci_ioport_map(struct pci_dev *dev,
unsigned long port, unsigned int nr)
{
@@ -40,6 +42,8 @@ void __iomem *__pci_ioport_map(struct pci_dev *dev,
return (void __iomem *) (ctrl->io_map_base + port);
}
+#endif /* CONFIG_PCI_DRIVERS_LEGACY */
+
void pci_iounmap(struct pci_dev *dev, void __iomem * addr)
{
iounmap(addr);
diff --git a/arch/mips/lib/iomap.c b/arch/mips/lib/iomap.c
index 8e7e378..9daa924 100644
--- a/arch/mips/lib/iomap.c
+++ b/arch/mips/lib/iomap.c
@@ -6,7 +6,7 @@
* (C) Copyright 2007 MIPS Technologies, Inc.
* written by Ralf Baechle <ralf@linux-mips.org>
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <asm/io.h>
/*
diff --git a/arch/mips/lib/lshrdi3.c b/arch/mips/lib/lshrdi3.c
index 3645474..221167c 100644
--- a/arch/mips/lib/lshrdi3.c
+++ b/arch/mips/lib/lshrdi3.c
@@ -1,4 +1,4 @@
-#include <linux/module.h>
+#include <linux/export.h>
#include "libgcc.h"
diff --git a/arch/mips/lib/r3k_dump_tlb.c b/arch/mips/lib/r3k_dump_tlb.c
index 744f4a7..85b4086 100644
--- a/arch/mips/lib/r3k_dump_tlb.c
+++ b/arch/mips/lib/r3k_dump_tlb.c
@@ -53,15 +53,15 @@ static void dump_tlb(int first, int last)
*/
printk("Index: %2d ", i);
- printk("va=%08lx asid=%08lx"
- " [pa=%06lx n=%d d=%d v=%d g=%d]",
- entryhi & PAGE_MASK,
- entryhi & asid_mask,
- entrylo0 & PAGE_MASK,
- (entrylo0 & R3K_ENTRYLO_N) ? 1 : 0,
- (entrylo0 & R3K_ENTRYLO_D) ? 1 : 0,
- (entrylo0 & R3K_ENTRYLO_V) ? 1 : 0,
- (entrylo0 & R3K_ENTRYLO_G) ? 1 : 0);
+ pr_cont("va=%08lx asid=%08lx"
+ " [pa=%06lx n=%d d=%d v=%d g=%d]",
+ entryhi & PAGE_MASK,
+ entryhi & asid_mask,
+ entrylo0 & PAGE_MASK,
+ (entrylo0 & R3K_ENTRYLO_N) ? 1 : 0,
+ (entrylo0 & R3K_ENTRYLO_D) ? 1 : 0,
+ (entrylo0 & R3K_ENTRYLO_V) ? 1 : 0,
+ (entrylo0 & R3K_ENTRYLO_G) ? 1 : 0);
}
}
printk("\n");
diff --git a/arch/mips/lib/ucmpdi2.c b/arch/mips/lib/ucmpdi2.c
index bd599f5..08067fa 100644
--- a/arch/mips/lib/ucmpdi2.c
+++ b/arch/mips/lib/ucmpdi2.c
@@ -1,4 +1,4 @@
-#include <linux/module.h>
+#include <linux/export.h>
#include "libgcc.h"
diff --git a/arch/mips/loongson32/Kconfig b/arch/mips/loongson32/Kconfig
index 7704f20..3c0c2f2 100644
--- a/arch/mips/loongson32/Kconfig
+++ b/arch/mips/loongson32/Kconfig
@@ -19,6 +19,21 @@
select USE_GENERIC_EARLY_PRINTK_8250
select COMMON_CLK
+config LOONGSON1_LS1C
+ bool "Loongson LS1C board"
+ select CEVT_R4K if !MIPS_EXTERNAL_TIMER
+ select CSRC_R4K if !MIPS_EXTERNAL_TIMER
+ select SYS_HAS_CPU_LOONGSON1C
+ select DMA_NONCOHERENT
+ select BOOT_ELF32
+ select IRQ_MIPS_CPU
+ select SYS_SUPPORTS_32BIT_KERNEL
+ select SYS_SUPPORTS_LITTLE_ENDIAN
+ select SYS_SUPPORTS_HIGHMEM
+ select SYS_SUPPORTS_MIPS16
+ select SYS_HAS_EARLY_PRINTK
+ select USE_GENERIC_EARLY_PRINTK_8250
+ select COMMON_CLK
endchoice
menuconfig CEVT_CSRC_LS1X
diff --git a/arch/mips/loongson32/Makefile b/arch/mips/loongson32/Makefile
index 5f4bd6e..1ab2c5b 100644
--- a/arch/mips/loongson32/Makefile
+++ b/arch/mips/loongson32/Makefile
@@ -9,3 +9,9 @@
#
obj-$(CONFIG_LOONGSON1_LS1B) += ls1b/
+
+#
+# Loongson LS1C board
+#
+
+obj-$(CONFIG_LOONGSON1_LS1C) += ls1c/
diff --git a/arch/mips/loongson32/Platform b/arch/mips/loongson32/Platform
index ebb6dc2..ffe01c6 100644
--- a/arch/mips/loongson32/Platform
+++ b/arch/mips/loongson32/Platform
@@ -5,3 +5,4 @@
platform-$(CONFIG_MACH_LOONGSON32) += loongson32/
cflags-$(CONFIG_MACH_LOONGSON32) += -I$(srctree)/arch/mips/include/asm/mach-loongson32
load-$(CONFIG_LOONGSON1_LS1B) += 0xffffffff80100000
+load-$(CONFIG_LOONGSON1_LS1C) += 0xffffffff80100000
diff --git a/arch/mips/loongson32/common/irq.c b/arch/mips/loongson32/common/irq.c
index 455a770..635a4ab 100644
--- a/arch/mips/loongson32/common/irq.c
+++ b/arch/mips/loongson32/common/irq.c
@@ -62,12 +62,58 @@ static void ls1x_irq_unmask(struct irq_data *d)
| (1 << bit), LS1X_INTC_INTIEN(n));
}
+static int ls1x_irq_settype(struct irq_data *d, unsigned int type)
+{
+ unsigned int bit = (d->irq - LS1X_IRQ_BASE) & 0x1f;
+ unsigned int n = (d->irq - LS1X_IRQ_BASE) >> 5;
+
+ switch (type) {
+ case IRQ_TYPE_LEVEL_HIGH:
+ __raw_writel(__raw_readl(LS1X_INTC_INTPOL(n))
+ | (1 << bit), LS1X_INTC_INTPOL(n));
+ __raw_writel(__raw_readl(LS1X_INTC_INTEDGE(n))
+ & ~(1 << bit), LS1X_INTC_INTEDGE(n));
+ break;
+ case IRQ_TYPE_LEVEL_LOW:
+ __raw_writel(__raw_readl(LS1X_INTC_INTPOL(n))
+ & ~(1 << bit), LS1X_INTC_INTPOL(n));
+ __raw_writel(__raw_readl(LS1X_INTC_INTEDGE(n))
+ & ~(1 << bit), LS1X_INTC_INTEDGE(n));
+ break;
+ case IRQ_TYPE_EDGE_RISING:
+ __raw_writel(__raw_readl(LS1X_INTC_INTPOL(n))
+ | (1 << bit), LS1X_INTC_INTPOL(n));
+ __raw_writel(__raw_readl(LS1X_INTC_INTEDGE(n))
+ | (1 << bit), LS1X_INTC_INTEDGE(n));
+ break;
+ case IRQ_TYPE_EDGE_FALLING:
+ __raw_writel(__raw_readl(LS1X_INTC_INTPOL(n))
+ & ~(1 << bit), LS1X_INTC_INTPOL(n));
+ __raw_writel(__raw_readl(LS1X_INTC_INTEDGE(n))
+ | (1 << bit), LS1X_INTC_INTEDGE(n));
+ break;
+ case IRQ_TYPE_EDGE_BOTH:
+ __raw_writel(__raw_readl(LS1X_INTC_INTPOL(n))
+ & ~(1 << bit), LS1X_INTC_INTPOL(n));
+ __raw_writel(__raw_readl(LS1X_INTC_INTEDGE(n))
+ | (1 << bit), LS1X_INTC_INTEDGE(n));
+ break;
+ case IRQ_TYPE_NONE:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static struct irq_chip ls1x_irq_chip = {
.name = "LS1X-INTC",
.irq_ack = ls1x_irq_ack,
.irq_mask = ls1x_irq_mask,
.irq_mask_ack = ls1x_irq_mask_ack,
.irq_unmask = ls1x_irq_unmask,
+ .irq_set_type = ls1x_irq_settype,
};
static void ls1x_irq_dispatch(int n)
@@ -107,7 +153,7 @@ asmlinkage void plat_irq_dispatch(void)
}
-struct irqaction cascade_irqaction = {
+static struct irqaction cascade_irqaction = {
.handler = no_action,
.name = "cascade",
.flags = IRQF_NO_THREAD,
@@ -120,7 +166,7 @@ static void __init ls1x_irq_init(int base)
/* Disable interrupts and clear pending,
* setup all IRQs as high level triggered
*/
- for (n = 0; n < 4; n++) {
+ for (n = 0; n < INTN; n++) {
__raw_writel(0x0, LS1X_INTC_INTIEN(n));
__raw_writel(0xffffffff, LS1X_INTC_INTCLR(n));
__raw_writel(0xffffffff, LS1X_INTC_INTPOL(n));
@@ -129,7 +175,7 @@ static void __init ls1x_irq_init(int base)
}
- for (n = base; n < LS1X_IRQS; n++) {
+ for (n = base; n < NR_IRQS; n++) {
irq_set_chip_and_handler(n, &ls1x_irq_chip,
handle_level_irq);
}
@@ -138,6 +184,9 @@ static void __init ls1x_irq_init(int base)
setup_irq(INT1_IRQ, &cascade_irqaction);
setup_irq(INT2_IRQ, &cascade_irqaction);
setup_irq(INT3_IRQ, &cascade_irqaction);
+#if defined(CONFIG_LOONGSON1_LS1C)
+ setup_irq(INT4_IRQ, &cascade_irqaction);
+#endif
}
void __init arch_init_irq(void)
diff --git a/arch/mips/loongson32/common/platform.c b/arch/mips/loongson32/common/platform.c
index f2c714d..beff085 100644
--- a/arch/mips/loongson32/common/platform.c
+++ b/arch/mips/loongson32/common/platform.c
@@ -17,11 +17,16 @@
#include <linux/stmmac.h>
#include <linux/usb/ehci_pdriver.h>
+#include <platform.h>
#include <loongson1.h>
#include <cpufreq.h>
#include <dma.h>
#include <nand.h>
+#define LS1X_RTC_CTRL ((void __iomem *)KSEG1ADDR(LS1X_RTC_BASE + 0x40))
+#define RTC_EXTCLK_OK (BIT(5) | BIT(8))
+#define RTC_EXTCLK_EN BIT(8)
+
/* 8250/16550 compatible UART */
#define LS1X_UART(_id) \
{ \
@@ -65,6 +70,15 @@ void __init ls1x_serial_set_uartclk(struct platform_device *pdev)
p->uartclk = clk_get_rate(clk);
}
+void __init ls1x_rtc_set_extclk(struct platform_device *pdev)
+{
+ u32 val;
+
+ val = __raw_readl(LS1X_RTC_CTRL);
+ if (!(val & RTC_EXTCLK_OK))
+ __raw_writel(val | RTC_EXTCLK_EN, LS1X_RTC_CTRL);
+}
+
/* CPUFreq */
static struct plat_ls1x_cpufreq ls1x_cpufreq_pdata = {
.clk_name = "cpu_clk",
@@ -132,6 +146,7 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv)
val = __raw_readl(LS1X_MUX_CTRL1);
+#if defined(CONFIG_LOONGSON1_LS1B)
plat_dat = dev_get_platdata(&pdev->dev);
if (plat_dat->bus_id) {
__raw_writel(__raw_readl(LS1X_MUX_CTRL0) | GMAC1_USE_UART1 |
@@ -165,6 +180,17 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv)
val &= ~GMAC0_SHUT;
}
__raw_writel(val, LS1X_MUX_CTRL1);
+#elif defined(CONFIG_LOONGSON1_LS1C)
+ plat_dat = dev_get_platdata(&pdev->dev);
+
+ val &= ~PHY_INTF_SELI;
+ if (plat_dat->interface == PHY_INTERFACE_MODE_RMII)
+ val |= 0x4 << PHY_INTF_SELI_SHIFT;
+ __raw_writel(val, LS1X_MUX_CTRL1);
+
+ val = __raw_readl(LS1X_MUX_CTRL0);
+ __raw_writel(val & (~GMAC_SHUT), LS1X_MUX_CTRL0);
+#endif
return 0;
}
@@ -172,7 +198,11 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv)
static struct plat_stmmacenet_data ls1x_eth0_pdata = {
.bus_id = 0,
.phy_addr = -1,
+#if defined(CONFIG_LOONGSON1_LS1B)
.interface = PHY_INTERFACE_MODE_MII,
+#elif defined(CONFIG_LOONGSON1_LS1C)
+ .interface = PHY_INTERFACE_MODE_RMII,
+#endif
.mdio_bus_data = &ls1x_mdio_bus_data,
.dma_cfg = &ls1x_eth_dma_cfg,
.has_gmac = 1,
@@ -203,6 +233,7 @@ struct platform_device ls1x_eth0_pdev = {
},
};
+#ifdef CONFIG_LOONGSON1_LS1B
static struct plat_stmmacenet_data ls1x_eth1_pdata = {
.bus_id = 1,
.phy_addr = -1,
@@ -236,6 +267,7 @@ struct platform_device ls1x_eth1_pdev = {
.platform_data = &ls1x_eth1_pdata,
},
};
+#endif /* CONFIG_LOONGSON1_LS1B */
/* GPIO */
static struct resource ls1x_gpio0_resources[] = {
diff --git a/arch/mips/loongson32/common/setup.c b/arch/mips/loongson32/common/setup.c
index 62f41af..1640744 100644
--- a/arch/mips/loongson32/common/setup.c
+++ b/arch/mips/loongson32/common/setup.c
@@ -22,7 +22,11 @@ const char *get_system_type(void)
switch (processor_id & PRID_REV_MASK) {
case PRID_REV_LOONGSON1B:
+#if defined(CONFIG_LOONGSON1_LS1B)
return "LOONGSON LS1B";
+#elif defined(CONFIG_LOONGSON1_LS1C)
+ return "LOONGSON LS1C";
+#endif
default:
return "LOONGSON (unknown)";
}
diff --git a/arch/mips/loongson32/ls1c/Makefile b/arch/mips/loongson32/ls1c/Makefile
new file mode 100644
index 0000000..a92c6cd
--- /dev/null
+++ b/arch/mips/loongson32/ls1c/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for loongson1C based machines.
+#
+
+obj-y += board.o
diff --git a/arch/mips/loongson32/ls1c/board.c b/arch/mips/loongson32/ls1c/board.c
new file mode 100644
index 0000000..a96bed5
--- /dev/null
+++ b/arch/mips/loongson32/ls1c/board.c
@@ -0,0 +1,27 @@
+/*
+ * Copyright (c) 2016 Yang Ling <gnaygnil@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <platform.h>
+
+static struct platform_device *ls1c_platform_devices[] __initdata = {
+ &ls1x_uart_pdev,
+ &ls1x_eth0_pdev,
+ &ls1x_rtc_pdev,
+};
+
+static int __init ls1c_platform_init(void)
+{
+ ls1x_serial_set_uartclk(&ls1x_uart_pdev);
+ ls1x_rtc_set_extclk(&ls1x_rtc_pdev);
+
+ return platform_add_devices(ls1c_platform_devices,
+ ARRAY_SIZE(ls1c_platform_devices));
+}
+
+arch_initcall(ls1c_platform_init);
diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c
index 05b1d7c..0e45b06 100644
--- a/arch/mips/mm/c-octeon.c
+++ b/arch/mips/mm/c-octeon.c
@@ -294,6 +294,8 @@ void octeon_cache_init(void)
flush_data_cache_page = octeon_flush_data_cache_page;
flush_icache_range = octeon_flush_icache_range;
local_flush_icache_range = local_octeon_flush_icache_range;
+ __flush_icache_user_range = octeon_flush_icache_range;
+ __local_flush_icache_user_range = local_octeon_flush_icache_range;
__flush_kernel_vmap_range = octeon_flush_kernel_vmap_range;
diff --git a/arch/mips/mm/c-r3k.c b/arch/mips/mm/c-r3k.c
index 135ec31..21e4e66 100644
--- a/arch/mips/mm/c-r3k.c
+++ b/arch/mips/mm/c-r3k.c
@@ -325,6 +325,8 @@ void r3k_cache_init(void)
flush_cache_page = r3k_flush_cache_page;
flush_icache_range = r3k_flush_icache_range;
local_flush_icache_range = r3k_flush_icache_range;
+ __flush_icache_user_range = r3k_flush_icache_range;
+ __local_flush_icache_user_range = r3k_flush_icache_range;
__flush_kernel_vmap_range = r3k_flush_kernel_vmap_range;
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index fa7d8d3..88cfaf8 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -17,7 +17,7 @@
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/mm.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/bitops.h>
#include <asm/bcache.h>
@@ -722,11 +722,13 @@ struct flush_icache_range_args {
unsigned long start;
unsigned long end;
unsigned int type;
+ bool user;
};
static inline void __local_r4k_flush_icache_range(unsigned long start,
unsigned long end,
- unsigned int type)
+ unsigned int type,
+ bool user)
{
if (!cpu_has_ic_fills_f_dc) {
if (type == R4K_INDEX ||
@@ -734,7 +736,10 @@ static inline void __local_r4k_flush_icache_range(unsigned long start,
r4k_blast_dcache();
} else {
R4600_HIT_CACHEOP_WAR_IMPL;
- protected_blast_dcache_range(start, end);
+ if (user)
+ protected_blast_dcache_range(start, end);
+ else
+ blast_dcache_range(start, end);
}
}
@@ -748,27 +753,25 @@ static inline void __local_r4k_flush_icache_range(unsigned long start,
break;
default:
- protected_blast_icache_range(start, end);
+ if (user)
+ protected_blast_icache_range(start, end);
+ else
+ blast_icache_range(start, end);
break;
}
}
-#ifdef CONFIG_EVA
- /*
- * Due to all possible segment mappings, there might cache aliases
- * caused by the bootloader being in non-EVA mode, and the CPU switching
- * to EVA during early kernel init. It's best to flush the scache
- * to avoid having secondary cores fetching stale data and lead to
- * kernel crashes.
- */
- bc_wback_inv(start, (end - start));
- __sync();
-#endif
}
static inline void local_r4k_flush_icache_range(unsigned long start,
unsigned long end)
{
- __local_r4k_flush_icache_range(start, end, R4K_HIT | R4K_INDEX);
+ __local_r4k_flush_icache_range(start, end, R4K_HIT | R4K_INDEX, false);
+}
+
+static inline void local_r4k_flush_icache_user_range(unsigned long start,
+ unsigned long end)
+{
+ __local_r4k_flush_icache_range(start, end, R4K_HIT | R4K_INDEX, true);
}
static inline void local_r4k_flush_icache_range_ipi(void *args)
@@ -777,11 +780,13 @@ static inline void local_r4k_flush_icache_range_ipi(void *args)
unsigned long start = fir_args->start;
unsigned long end = fir_args->end;
unsigned int type = fir_args->type;
+ bool user = fir_args->user;
- __local_r4k_flush_icache_range(start, end, type);
+ __local_r4k_flush_icache_range(start, end, type, user);
}
-static void r4k_flush_icache_range(unsigned long start, unsigned long end)
+static void __r4k_flush_icache_range(unsigned long start, unsigned long end,
+ bool user)
{
struct flush_icache_range_args args;
unsigned long size, cache_size;
@@ -789,6 +794,7 @@ static void r4k_flush_icache_range(unsigned long start, unsigned long end)
args.start = start;
args.end = end;
args.type = R4K_HIT | R4K_INDEX;
+ args.user = user;
/*
* Indexed cache ops require an SMP call.
@@ -814,6 +820,16 @@ static void r4k_flush_icache_range(unsigned long start, unsigned long end)
instruction_hazard();
}
+static void r4k_flush_icache_range(unsigned long start, unsigned long end)
+{
+ return __r4k_flush_icache_range(start, end, false);
+}
+
+static void r4k_flush_icache_user_range(unsigned long start, unsigned long end)
+{
+ return __r4k_flush_icache_range(start, end, true);
+}
+
#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
@@ -1915,9 +1931,16 @@ void r4k_cache_init(void)
flush_data_cache_page = r4k_flush_data_cache_page;
flush_icache_range = r4k_flush_icache_range;
local_flush_icache_range = local_r4k_flush_icache_range;
+ __flush_icache_user_range = r4k_flush_icache_user_range;
+ __local_flush_icache_user_range = local_r4k_flush_icache_user_range;
#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
- if (coherentio) {
+# if defined(CONFIG_DMA_PERDEV_COHERENT)
+ if (0) {
+# else
+ if ((coherentio == IO_COHERENCE_ENABLED) ||
+ ((coherentio == IO_COHERENCE_DEFAULT) && hw_coherentio)) {
+# endif
_dma_cache_wback_inv = (void *)cache_noop;
_dma_cache_wback = (void *)cache_noop;
_dma_cache_inv = (void *)cache_noop;
diff --git a/arch/mips/mm/c-tx39.c b/arch/mips/mm/c-tx39.c
index 596e184..5c28258 100644
--- a/arch/mips/mm/c-tx39.c
+++ b/arch/mips/mm/c-tx39.c
@@ -411,6 +411,9 @@ void tx39_cache_init(void)
break;
}
+ __flush_icache_user_range = flush_icache_range;
+ __local_flush_icache_user_range = local_flush_icache_range;
+
current_cpu_data.icache.waysize = icache_size / current_cpu_data.icache.ways;
current_cpu_data.dcache.waysize = dcache_size / current_cpu_data.dcache.ways;
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index bf04c6c..6db3413 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -10,7 +10,7 @@
#include <linux/fcntl.h>
#include <linux/kernel.h>
#include <linux/linkage.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/sched.h>
#include <linux/syscalls.h>
#include <linux/mm.h>
@@ -33,6 +33,10 @@ void (*flush_icache_range)(unsigned long start, unsigned long end);
EXPORT_SYMBOL_GPL(flush_icache_range);
void (*local_flush_icache_range)(unsigned long start, unsigned long end);
EXPORT_SYMBOL_GPL(local_flush_icache_range);
+void (*__flush_icache_user_range)(unsigned long start, unsigned long end);
+EXPORT_SYMBOL_GPL(__flush_icache_user_range);
+void (*__local_flush_icache_user_range)(unsigned long start, unsigned long end);
+EXPORT_SYMBOL_GPL(__local_flush_icache_user_range);
void (*__flush_cache_vmap)(void);
void (*__flush_cache_vunmap)(void);
@@ -74,7 +78,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
if (!access_ok(VERIFY_WRITE, (void __user *) addr, bytes))
return -EFAULT;
- flush_icache_range(addr, addr + bytes);
+ __flush_icache_user_range(addr, addr + bytes);
return 0;
}
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index b2eadd6..46d5696 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -11,7 +11,7 @@
#include <linux/types.h>
#include <linux/dma-mapping.h>
#include <linux/mm.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/scatterlist.h>
#include <linux/string.h>
#include <linux/gfp.h>
@@ -24,14 +24,15 @@
#include <dma-coherence.h>
-#ifdef CONFIG_DMA_MAYBE_COHERENT
-int coherentio = 0; /* User defined DMA coherency from command line. */
+#if defined(CONFIG_DMA_MAYBE_COHERENT) && !defined(CONFIG_DMA_PERDEV_COHERENT)
+/* User defined DMA coherency from command line. */
+enum coherent_io_user_state coherentio = IO_COHERENCE_DEFAULT;
EXPORT_SYMBOL_GPL(coherentio);
int hw_coherentio = 0; /* Actual hardware supported DMA coherency setting. */
static int __init setcoherentio(char *str)
{
- coherentio = 1;
+ coherentio = IO_COHERENCE_ENABLED;
pr_info("Hardware DMA cache coherency (command line)\n");
return 0;
}
@@ -39,7 +40,7 @@ early_param("coherentio", setcoherentio);
static int __init setnocoherentio(char *str)
{
- coherentio = 0;
+ coherentio = IO_COHERENCE_DISABLED;
pr_info("Software DMA cache coherency (command line)\n");
return 0;
}
@@ -160,8 +161,7 @@ static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
*dma_handle = plat_map_dma_mem(dev, ret, size);
if (!plat_device_is_coherent(dev)) {
dma_cache_wback_inv((unsigned long) ret, size);
- if (!hw_coherentio)
- ret = UNCAC_ADDR(ret);
+ ret = UNCAC_ADDR(ret);
}
return ret;
@@ -189,7 +189,7 @@ static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr,
plat_unmap_dma_mem(dev, dma_handle, size, DMA_BIDIRECTIONAL);
- if (!plat_device_is_coherent(dev) && !hw_coherentio)
+ if (!plat_device_is_coherent(dev))
addr = CAC_ADDR(addr);
page = virt_to_page((void *) addr);
@@ -209,7 +209,7 @@ static int mips_dma_mmap(struct device *dev, struct vm_area_struct *vma,
unsigned long pfn;
int ret = -ENXIO;
- if (!plat_device_is_coherent(dev) && !hw_coherentio)
+ if (!plat_device_is_coherent(dev))
addr = CAC_ADDR(addr);
pfn = page_to_pfn(virt_to_page((void *)addr));
diff --git a/arch/mips/mm/extable.c b/arch/mips/mm/extable.c
index 9d25d2b..e474fa2 100644
--- a/arch/mips/mm/extable.c
+++ b/arch/mips/mm/extable.c
@@ -5,7 +5,7 @@
*
* Copyright (C) 1997, 99, 2001 - 2004 Ralf Baechle <ralf@linux-mips.org>
*/
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/spinlock.h>
#include <asm/branch.h>
#include <asm/uaccess.h>
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 9560ad7..d56a855 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -18,7 +18,6 @@
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/smp.h>
-#include <linux/module.h>
#include <linux/kprobes.h>
#include <linux/perf_event.h>
#include <linux/uaccess.h>
diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c
index 42d124f..d8c3c15 100644
--- a/arch/mips/mm/gup.c
+++ b/arch/mips/mm/gup.c
@@ -287,7 +287,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
pages += nr;
ret = get_user_pages_unlocked(start, (end - start) >> PAGE_SHIFT,
- write, 0, pages);
+ pages, write ? FOLL_WRITE : 0);
/* Have to be a bit careful with return values */
if (nr > 0) {
diff --git a/arch/mips/mm/highmem.c b/arch/mips/mm/highmem.c
index d7258a1..f13f510 100644
--- a/arch/mips/mm/highmem.c
+++ b/arch/mips/mm/highmem.c
@@ -1,5 +1,6 @@
#include <linux/compiler.h>
-#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/export.h>
#include <linux/highmem.h>
#include <linux/sched.h>
#include <linux/smp.h>
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 72f7478..3a6edec 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -10,7 +10,7 @@
*/
#include <linux/bug.h>
#include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/smp.h>
diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c
index 8d5008c..1f18962 100644
--- a/arch/mips/mm/ioremap.c
+++ b/arch/mips/mm/ioremap.c
@@ -6,7 +6,7 @@
* (C) Copyright 1995 1996 Linus Torvalds
* (C) Copyright 2001, 2002 Ralf Baechle
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <asm/addrspace.h>
#include <asm/byteorder.h>
#include <linux/sched.h>
diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c
index 3530376..d08ea3f 100644
--- a/arch/mips/mm/mmap.c
+++ b/arch/mips/mm/mmap.c
@@ -10,7 +10,7 @@
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/mman.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/personality.h>
#include <linux/random.h>
#include <linux/sched.h>
diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c
index c41953c..6f804f5 100644
--- a/arch/mips/mm/page.c
+++ b/arch/mips/mm/page.c
@@ -12,7 +12,6 @@
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/mm.h>
-#include <linux/module.h>
#include <linux/proc_fs.h>
#include <asm/bugs.h>
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index e8b335c..bba9c14 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -14,7 +14,7 @@
#include <linux/smp.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <asm/cpu.h>
#include <asm/cpu-type.h>
@@ -67,8 +67,11 @@ void local_flush_tlb_all(void)
entry = read_c0_wired();
- /* Blast 'em all away. */
- if (cpu_has_tlbinv) {
+ /*
+ * Blast 'em all away.
+ * If there are any wired entries, fall back to iterating
+ */
+ if (cpu_has_tlbinv && !entry) {
if (current_cpu_data.tlbsizevtlb) {
write_c0_index(0);
mtc0_tlbw_hazard();
diff --git a/arch/mips/mti-malta/malta-dt.c b/arch/mips/mti-malta/malta-dt.c
index 47a2288..4822943 100644
--- a/arch/mips/mti-malta/malta-dt.c
+++ b/arch/mips/mti-malta/malta-dt.c
@@ -17,18 +17,3 @@ void __init device_tree_init(void)
{
unflatten_and_copy_device_tree();
}
-
-static const struct of_device_id bus_ids[] __initconst = {
- { .compatible = "simple-bus", },
- { .compatible = "isa", },
- {},
-};
-
-static int __init publish_devices(void)
-{
- if (!of_have_populated_dt())
- return 0;
-
- return of_platform_bus_probe(NULL, bus_ids, NULL);
-}
-device_initcall(publish_devices);
diff --git a/arch/mips/mti-malta/malta-dtshim.c b/arch/mips/mti-malta/malta-dtshim.c
index 151f488..c398582 100644
--- a/arch/mips/mti-malta/malta-dtshim.c
+++ b/arch/mips/mti-malta/malta-dtshim.c
@@ -13,18 +13,66 @@
#include <linux/libfdt.h>
#include <linux/of_fdt.h>
#include <linux/sizes.h>
+#include <asm/addrspace.h>
#include <asm/bootinfo.h>
#include <asm/fw/fw.h>
+#include <asm/mips-boards/generic.h>
+#include <asm/mips-boards/malta.h>
+#include <asm/mips-cm.h>
#include <asm/page.h>
+#define ROCIT_REG_BASE 0x1f403000
+#define ROCIT_CONFIG_GEN1 (ROCIT_REG_BASE + 0x04)
+#define ROCIT_CONFIG_GEN1_MEMMAP_SHIFT 8
+#define ROCIT_CONFIG_GEN1_MEMMAP_MASK (0xf << 8)
+
static unsigned char fdt_buf[16 << 10] __initdata;
/* determined physical memory size, not overridden by command line args */
extern unsigned long physical_memsize;
-#define MAX_MEM_ARRAY_ENTRIES 1
+enum mem_map {
+ MEM_MAP_V1 = 0,
+ MEM_MAP_V2,
+};
-static unsigned __init gen_fdt_mem_array(__be32 *mem_array, unsigned long size)
+#define MAX_MEM_ARRAY_ENTRIES 2
+
+static __init int malta_scon(void)
+{
+ int scon = MIPS_REVISION_SCONID;
+
+ if (scon != MIPS_REVISION_SCON_OTHER)
+ return scon;
+
+ switch (MIPS_REVISION_CORID) {
+ case MIPS_REVISION_CORID_QED_RM5261:
+ case MIPS_REVISION_CORID_CORE_LV:
+ case MIPS_REVISION_CORID_CORE_FPGA:
+ case MIPS_REVISION_CORID_CORE_FPGAR2:
+ return MIPS_REVISION_SCON_GT64120;
+
+ case MIPS_REVISION_CORID_CORE_EMUL_BON:
+ case MIPS_REVISION_CORID_BONITO64:
+ case MIPS_REVISION_CORID_CORE_20K:
+ return MIPS_REVISION_SCON_BONITO;
+
+ case MIPS_REVISION_CORID_CORE_MSC:
+ case MIPS_REVISION_CORID_CORE_FPGA2:
+ case MIPS_REVISION_CORID_CORE_24K:
+ return MIPS_REVISION_SCON_SOCIT;
+
+ case MIPS_REVISION_CORID_CORE_FPGA3:
+ case MIPS_REVISION_CORID_CORE_FPGA4:
+ case MIPS_REVISION_CORID_CORE_FPGA5:
+ case MIPS_REVISION_CORID_CORE_EMUL_MSC:
+ default:
+ return MIPS_REVISION_SCON_ROCIT;
+ }
+}
+
+static unsigned __init gen_fdt_mem_array(__be32 *mem_array, unsigned long size,
+ enum mem_map map)
{
unsigned long size_preio;
unsigned entries;
@@ -39,11 +87,47 @@ static unsigned __init gen_fdt_mem_array(__be32 *mem_array, unsigned long size)
* DDR but limits it to 2GB.
*/
mem_array[1] = cpu_to_be32(size);
- } else {
- size_preio = min_t(unsigned long, size, SZ_256M);
- mem_array[1] = cpu_to_be32(size_preio);
+ goto done;
}
+ size_preio = min_t(unsigned long, size, SZ_256M);
+ mem_array[1] = cpu_to_be32(size_preio);
+ size -= size_preio;
+ if (!size)
+ goto done;
+
+ if (map == MEM_MAP_V2) {
+ /*
+ * We have a flat 32 bit physical memory map with DDR filling
+ * all 4GB of the memory map, apart from the I/O region which
+ * obscures 256MB from 0x10000000-0x1fffffff.
+ *
+ * Therefore we discard the 256MB behind the I/O region.
+ */
+ if (size <= SZ_256M)
+ goto done;
+ size -= SZ_256M;
+
+ /* Make use of the memory following the I/O region */
+ entries++;
+ mem_array[2] = cpu_to_be32(PHYS_OFFSET + SZ_512M);
+ mem_array[3] = cpu_to_be32(size);
+ } else {
+ /*
+ * We have a 32 bit physical memory map with a 2GB DDR region
+ * aliased in the upper & lower halves of it. The I/O region
+ * obscures 256MB from 0x10000000-0x1fffffff in the low alias
+ * but the DDR it obscures is accessible via the high alias.
+ *
+ * Simply access everything beyond the lowest 256MB of DDR using
+ * the high alias.
+ */
+ entries++;
+ mem_array[2] = cpu_to_be32(PHYS_OFFSET + SZ_2G + SZ_256M);
+ mem_array[3] = cpu_to_be32(size);
+ }
+
+done:
BUG_ON(entries > MAX_MEM_ARRAY_ENTRIES);
return entries;
}
@@ -54,6 +138,8 @@ static void __init append_memory(void *fdt, int root_off)
unsigned long memsize;
unsigned mem_entries;
int i, err, mem_off;
+ enum mem_map mem_map;
+ u32 config;
char *var, param_name[10], *var_names[] = {
"ememsize", "memsize",
};
@@ -106,6 +192,20 @@ static void __init append_memory(void *fdt, int root_off)
/* if the user says there's more RAM than we thought, believe them */
physical_memsize = max_t(unsigned long, physical_memsize, memsize);
+ /* detect the memory map in use */
+ if (malta_scon() == MIPS_REVISION_SCON_ROCIT) {
+ /* ROCit has a register indicating the memory map in use */
+ config = readl((void __iomem *)CKSEG1ADDR(ROCIT_CONFIG_GEN1));
+ mem_map = config & ROCIT_CONFIG_GEN1_MEMMAP_MASK;
+ mem_map >>= ROCIT_CONFIG_GEN1_MEMMAP_SHIFT;
+ } else {
+ /* if not using ROCit, presume the v1 memory map */
+ mem_map = MEM_MAP_V1;
+ }
+ if (mem_map > MEM_MAP_V2)
+ panic("Unsupported physical memory map v%u detected",
+ (unsigned int)mem_map);
+
/* append memory to the DT */
mem_off = fdt_add_subnode(fdt, root_off, "memory");
if (mem_off < 0)
@@ -115,19 +215,93 @@ static void __init append_memory(void *fdt, int root_off)
if (err)
panic("Unable to set memory node device_type: %d", err);
- mem_entries = gen_fdt_mem_array(mem_array, physical_memsize);
+ mem_entries = gen_fdt_mem_array(mem_array, physical_memsize, mem_map);
err = fdt_setprop(fdt, mem_off, "reg", mem_array,
mem_entries * 2 * sizeof(mem_array[0]));
if (err)
panic("Unable to set memory regs property: %d", err);
- mem_entries = gen_fdt_mem_array(mem_array, memsize);
+ mem_entries = gen_fdt_mem_array(mem_array, memsize, mem_map);
err = fdt_setprop(fdt, mem_off, "linux,usable-memory", mem_array,
mem_entries * 2 * sizeof(mem_array[0]));
if (err)
panic("Unable to set linux,usable-memory property: %d", err);
}
+static void __init remove_gic(void *fdt)
+{
+ int err, gic_off, i8259_off, cpu_off;
+ void __iomem *biu_base;
+ uint32_t cpu_phandle, sc_cfg;
+
+ /* if we have a CM which reports a GIC is present, leave the DT alone */
+ err = mips_cm_probe();
+ if (!err && (read_gcr_gic_status() & CM_GCR_GIC_STATUS_GICEX_MSK))
+ return;
+
+ if (malta_scon() == MIPS_REVISION_SCON_ROCIT) {
+ /*
+ * On systems using the RocIT system controller a GIC may be
+ * present without a CM. Detect whether that is the case.
+ */
+ biu_base = ioremap_nocache(MSC01_BIU_REG_BASE,
+ MSC01_BIU_ADDRSPACE_SZ);
+ sc_cfg = __raw_readl(biu_base + MSC01_SC_CFG_OFS);
+ if (sc_cfg & MSC01_SC_CFG_GICPRES_MSK) {
+ /* enable the GIC at the system controller level */
+ sc_cfg |= BIT(MSC01_SC_CFG_GICENA_SHF);
+ __raw_writel(sc_cfg, biu_base + MSC01_SC_CFG_OFS);
+ return;
+ }
+ }
+
+ gic_off = fdt_node_offset_by_compatible(fdt, -1, "mti,gic");
+ if (gic_off < 0) {
+ pr_warn("malta-dtshim: unable to find DT GIC node: %d\n",
+ gic_off);
+ return;
+ }
+
+ err = fdt_nop_node(fdt, gic_off);
+ if (err)
+ pr_warn("malta-dtshim: unable to nop GIC node\n");
+
+ i8259_off = fdt_node_offset_by_compatible(fdt, -1, "intel,i8259");
+ if (i8259_off < 0) {
+ pr_warn("malta-dtshim: unable to find DT i8259 node: %d\n",
+ i8259_off);
+ return;
+ }
+
+ cpu_off = fdt_node_offset_by_compatible(fdt, -1,
+ "mti,cpu-interrupt-controller");
+ if (cpu_off < 0) {
+ pr_warn("malta-dtshim: unable to find CPU intc node: %d\n",
+ cpu_off);
+ return;
+ }
+
+ cpu_phandle = fdt_get_phandle(fdt, cpu_off);
+ if (!cpu_phandle) {
+ pr_warn("malta-dtshim: unable to get CPU intc phandle\n");
+ return;
+ }
+
+ err = fdt_setprop_u32(fdt, i8259_off, "interrupt-parent", cpu_phandle);
+ if (err) {
+ pr_warn("malta-dtshim: unable to set i8259 interrupt-parent: %d\n",
+ err);
+ return;
+ }
+
+ err = fdt_setprop_u32(fdt, i8259_off, "interrupts", 2);
+ if (err) {
+ pr_warn("malta-dtshim: unable to set i8259 interrupts: %d\n",
+ err);
+ return;
+ }
+}
+
void __init *malta_dt_shim(void *fdt)
{
int root_off, len, err;
@@ -153,6 +327,7 @@ void __init *malta_dt_shim(void *fdt)
return fdt;
append_memory(fdt_buf, root_off);
+ remove_gic(fdt_buf);
err = fdt_pack(fdt_buf);
if (err)
diff --git a/arch/mips/mti-malta/malta-init.c b/arch/mips/mti-malta/malta-init.c
index dc2c521..0f3b881 100644
--- a/arch/mips/mti-malta/malta-init.c
+++ b/arch/mips/mti-malta/malta-init.c
@@ -14,6 +14,7 @@
#include <linux/init.h>
#include <linux/string.h>
#include <linux/kernel.h>
+#include <linux/pci_regs.h>
#include <linux/serial_core.h>
#include <asm/cacheflush.h>
@@ -242,23 +243,19 @@ void __init prom_init(void)
MSC01_PCI_SWAP_BYTESWAP << MSC01_PCI_SWAP_MEM_SHF |
MSC01_PCI_SWAP_BYTESWAP << MSC01_PCI_SWAP_BAR0_SHF);
#endif
-#ifndef CONFIG_EVA
- /* Fix up target memory mapping. */
- MSC_READ(MSC01_PCI_BAR0, mask);
- MSC_WRITE(MSC01_PCI_P2SCMSKL, mask & MSC01_PCI_BAR0_SIZE_MSK);
-#else
+
/*
* Setup the Malta max (2GB) memory for PCI DMA in host bridge
- * in transparent addressing mode, starting from 0x80000000.
+ * in transparent addressing mode.
*/
- mask = PHYS_OFFSET | (1<<3);
+ mask = PHYS_OFFSET | PCI_BASE_ADDRESS_MEM_PREFETCH;
MSC_WRITE(MSC01_PCI_BAR0, mask);
-
- mask = PHYS_OFFSET;
MSC_WRITE(MSC01_PCI_HEAD4, mask);
+
+ mask &= MSC01_PCI_BAR0_SIZE_MSK;
MSC_WRITE(MSC01_PCI_P2SCMSKL, mask);
MSC_WRITE(MSC01_PCI_P2SCMAPL, mask);
-#endif
+
/* Don't handle target retries indefinitely. */
if ((data & MSC01_PCI_CFG_MAXRTRY_MSK) ==
MSC01_PCI_CFG_MAXRTRY_MSK)
diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c
index c6a6c7a..cb675ec 100644
--- a/arch/mips/mti-malta/malta-int.c
+++ b/arch/mips/mti-malta/malta-int.c
@@ -14,11 +14,13 @@
*/
#include <linux/init.h>
#include <linux/irq.h>
+#include <linux/irqchip.h>
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/irqchip/mips-gic.h>
+#include <linux/of_irq.h>
#include <linux/kernel_stat.h>
#include <linux/kernel.h>
#include <linux/random.h>
@@ -37,10 +39,6 @@
#include <asm/setup.h>
#include <asm/rtlx.h>
-static void __iomem *_msc01_biu_base;
-
-static DEFINE_RAW_SPINLOCK(mips_irq_lock);
-
static inline int mips_pcibios_iack(void)
{
int irq;
@@ -85,49 +83,6 @@ static inline int mips_pcibios_iack(void)
return irq;
}
-static inline int get_int(void)
-{
- unsigned long flags;
- int irq;
- raw_spin_lock_irqsave(&mips_irq_lock, flags);
-
- irq = mips_pcibios_iack();
-
- /*
- * The only way we can decide if an interrupt is spurious
- * is by checking the 8259 registers. This needs a spinlock
- * on an SMP system, so leave it up to the generic code...
- */
-
- raw_spin_unlock_irqrestore(&mips_irq_lock, flags);
-
- return irq;
-}
-
-static void malta_hw0_irqdispatch(void)
-{
- int irq;
-
- irq = get_int();
- if (irq < 0) {
- /* interrupt has already been cleared */
- return;
- }
-
- do_IRQ(MALTA_INT_BASE + irq);
-
-#ifdef CONFIG_MIPS_VPE_APSP_API_MT
- if (aprp_hook)
- aprp_hook();
-#endif
-}
-
-static irqreturn_t i8259_handler(int irq, void *dev_id)
-{
- malta_hw0_irqdispatch();
- return IRQ_HANDLED;
-}
-
static void corehi_irqdispatch(void)
{
unsigned int intedge, intsteer, pcicmd, pcibadaddr;
@@ -240,12 +195,6 @@ static struct irqaction irq_call = {
};
#endif /* CONFIG_MIPS_MT_SMP */
-static struct irqaction i8259irq = {
- .handler = i8259_handler,
- .name = "XT-PIC cascade",
- .flags = IRQF_NO_THREAD,
-};
-
static struct irqaction corehi_irqaction = {
.handler = corehi_handler,
.name = "CoreHi",
@@ -281,28 +230,10 @@ void __init arch_init_ipiirq(int irq, struct irqaction *action)
void __init arch_init_irq(void)
{
- int corehi_irq, i8259_irq;
+ int corehi_irq;
- init_i8259_irqs();
-
- if (!cpu_has_veic)
- mips_cpu_irq_init();
-
- if (mips_cm_present()) {
- write_gcr_gic_base(GIC_BASE_ADDR | CM_GCR_GIC_BASE_GICEN_MSK);
- gic_present = 1;
- } else {
- if (mips_revision_sconid == MIPS_REVISION_SCON_ROCIT) {
- _msc01_biu_base = ioremap_nocache(MSC01_BIU_REG_BASE,
- MSC01_BIU_ADDRSPACE_SZ);
- gic_present =
- (__raw_readl(_msc01_biu_base + MSC01_SC_CFG_OFS) &
- MSC01_SC_CFG_GICPRES_MSK) >>
- MSC01_SC_CFG_GICPRES_SHF;
- }
- }
- if (gic_present)
- pr_debug("GIC present\n");
+ i8259_set_poll(mips_pcibios_iack);
+ irqchip_init();
switch (mips_revision_sconid) {
case MIPS_REVISION_SCON_SOCIT:
@@ -330,18 +261,6 @@ void __init arch_init_irq(void)
}
if (gic_present) {
- int i;
-
- gic_init(GIC_BASE_ADDR, GIC_ADDRSPACE_SZ, MIPSCPU_INT_GIC,
- MIPS_GIC_IRQ_BASE);
- if (!mips_cm_present()) {
- /* Enable the GIC */
- i = __raw_readl(_msc01_biu_base + MSC01_SC_CFG_OFS);
- __raw_writel(i | (0x1 << MSC01_SC_CFG_GICENA_SHF),
- _msc01_biu_base + MSC01_SC_CFG_OFS);
- pr_debug("GIC Enabled\n");
- }
- i8259_irq = MIPS_GIC_IRQ_BASE + GIC_INT_I8259A;
corehi_irq = MIPS_CPU_IRQ_BASE + MIPSCPU_INT_COREHI;
} else {
#if defined(CONFIG_MIPS_MT_SMP)
@@ -361,33 +280,13 @@ void __init arch_init_irq(void)
arch_init_ipiirq(cpu_ipi_call_irq, &irq_call);
#endif
if (cpu_has_veic) {
- set_vi_handler(MSC01E_INT_I8259A,
- malta_hw0_irqdispatch);
set_vi_handler(MSC01E_INT_COREHI,
corehi_irqdispatch);
- i8259_irq = MSC01E_INT_BASE + MSC01E_INT_I8259A;
corehi_irq = MSC01E_INT_BASE + MSC01E_INT_COREHI;
} else {
- i8259_irq = MIPS_CPU_IRQ_BASE + MIPSCPU_INT_I8259A;
corehi_irq = MIPS_CPU_IRQ_BASE + MIPSCPU_INT_COREHI;
}
}
- setup_irq(i8259_irq, &i8259irq);
setup_irq(corehi_irq, &corehi_irqaction);
}
-
-void malta_be_init(void)
-{
- /* Could change CM error mask register. */
-}
-
-int malta_be_handler(struct pt_regs *regs, int is_fixup)
-{
- /* This duplicates the handling in do_be which seems wrong */
- int retval = is_fixup ? MIPS_BE_FIXUP : MIPS_BE_FATAL;
-
- mips_cm_error_report();
-
- return retval;
-}
diff --git a/arch/mips/mti-malta/malta-platform.c b/arch/mips/mti-malta/malta-platform.c
index e1dd1c1..516e123 100644
--- a/arch/mips/mti-malta/malta-platform.c
+++ b/arch/mips/mti-malta/malta-platform.c
@@ -23,14 +23,10 @@
*/
#include <linux/init.h>
#include <linux/serial_8250.h>
-#include <linux/mc146818rtc.h>
#include <linux/module.h>
#include <linux/irq.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/physmap.h>
#include <linux/platform_device.h>
#include <asm/mips-boards/maltaint.h>
-#include <mtd/mtd-abi.h>
#define SMC_PORT(base, int) \
{ \
@@ -68,80 +64,13 @@ static struct platform_device malta_uart8250_device = {
},
};
-struct resource malta_rtc_resources[] = {
- {
- .start = RTC_PORT(0),
- .end = RTC_PORT(7),
- .flags = IORESOURCE_IO,
- }, {
- .start = RTC_IRQ,
- .end = RTC_IRQ,
- .flags = IORESOURCE_IRQ,
- }
-};
-
-static struct platform_device malta_rtc_device = {
- .name = "rtc_cmos",
- .id = -1,
- .resource = malta_rtc_resources,
- .num_resources = ARRAY_SIZE(malta_rtc_resources),
-};
-
-static struct mtd_partition malta_mtd_partitions[] = {
- {
- .name = "YAMON",
- .offset = 0x0,
- .size = 0x100000,
- .mask_flags = MTD_WRITEABLE
- }, {
- .name = "User FS",
- .offset = 0x100000,
- .size = 0x2e0000
- }, {
- .name = "Board Config",
- .offset = 0x3e0000,
- .size = 0x020000,
- .mask_flags = MTD_WRITEABLE
- }
-};
-
-static struct physmap_flash_data malta_flash_data = {
- .width = 4,
- .nr_parts = ARRAY_SIZE(malta_mtd_partitions),
- .parts = malta_mtd_partitions
-};
-
-static struct resource malta_flash_resource = {
- .start = 0x1e000000,
- .end = 0x1e3fffff,
- .flags = IORESOURCE_MEM
-};
-
-static struct platform_device malta_flash_device = {
- .name = "physmap-flash",
- .id = 0,
- .dev = {
- .platform_data = &malta_flash_data,
- },
- .num_resources = 1,
- .resource = &malta_flash_resource,
-};
-
static struct platform_device *malta_devices[] __initdata = {
&malta_uart8250_device,
- &malta_rtc_device,
- &malta_flash_device,
};
static int __init malta_add_devices(void)
{
- int err;
-
- err = platform_add_devices(malta_devices, ARRAY_SIZE(malta_devices));
- if (err)
- return err;
-
- return 0;
+ return platform_add_devices(malta_devices, ARRAY_SIZE(malta_devices));
}
device_initcall(malta_add_devices);
diff --git a/arch/mips/mti-malta/malta-reset.c b/arch/mips/mti-malta/malta-reset.c
index 2fd2cc2..dd6f62a 100644
--- a/arch/mips/mti-malta/malta-reset.c
+++ b/arch/mips/mti-malta/malta-reset.c
@@ -8,38 +8,21 @@
*/
#include <linux/io.h>
#include <linux/pm.h>
+#include <linux/reboot.h>
#include <asm/reboot.h>
#include <asm/mach-malta/malta-pm.h>
-#define SOFTRES_REG 0x1f000500
-#define GORESET 0x42
-
-static void mips_machine_restart(char *command)
-{
- unsigned int __iomem *softres_reg =
- ioremap(SOFTRES_REG, sizeof(unsigned int));
-
- __raw_writel(GORESET, softres_reg);
-}
-
-static void mips_machine_halt(void)
-{
- while (true);
-}
-
static void mips_machine_power_off(void)
{
mips_pm_suspend(PIIX4_FUNC3IO_PMCNTRL_SUS_TYP_SOFF);
pr_info("Failed to power down, resetting\n");
- mips_machine_restart(NULL);
+ machine_restart(NULL);
}
static int __init mips_reboot_setup(void)
{
- _machine_restart = mips_machine_restart;
- _machine_halt = mips_machine_halt;
pm_power_off = mips_machine_power_off;
return 0;
diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c
index 7e7364b..a01d5de 100644
--- a/arch/mips/mti-malta/malta-setup.c
+++ b/arch/mips/mti-malta/malta-setup.c
@@ -42,9 +42,6 @@
#define ROCIT_CONFIG_GEN0 0x1f403000
#define ROCIT_CONFIG_GEN0_PCI_IOCU BIT(7)
-extern void malta_be_init(void);
-extern int malta_be_handler(struct pt_regs *regs, int is_fixup);
-
static struct resource standard_io_resources[] = {
{
.name = "dma1",
@@ -154,12 +151,12 @@ static void __init plat_setup_iocoherency(void)
* coherency instead.
*/
if (plat_enable_iocoherency()) {
- if (coherentio == 0)
+ if (coherentio == IO_COHERENCE_DISABLED)
pr_info("Hardware DMA cache coherency disabled\n");
else
pr_info("Hardware DMA cache coherency enabled\n");
} else {
- if (coherentio == 1)
+ if (coherentio == IO_COHERENCE_ENABLED)
pr_info("Hardware DMA cache coherency unsupported, but enabled from command line!\n");
else
pr_info("Software DMA cache coherency enabled\n");
@@ -301,7 +298,4 @@ void __init plat_mem_setup(void)
#if defined(CONFIG_VT) && defined(CONFIG_VGA_CONSOLE)
screen_info_setup();
#endif
-
- board_be_init = malta_be_init;
- board_be_handler = malta_be_handler;
}
diff --git a/arch/mips/mti-sead3/Makefile b/arch/mips/mti-sead3/Makefile
deleted file mode 100644
index 7a584e0..0000000
--- a/arch/mips/mti-sead3/Makefile
+++ /dev/null
@@ -1,15 +0,0 @@
-#
-# Carsten Langgaard, carstenl@mips.com
-# Copyright (C) 1999,2000 MIPS Technologies, Inc. All rights reserved.
-#
-# Copyright (C) 2008 Wind River Systems, Inc.
-# written by Ralf Baechle <ralf@linux-mips.org>
-#
-# Copyright (C) 2012 MIPS Technoligies, Inc. All rights reserved.
-# Steven J. Hill <sjhill@mips.com>
-#
-obj-y := sead3-lcd.o sead3-display.o sead3-init.o \
- sead3-int.o sead3-platform.o sead3-reset.o \
- sead3-setup.o sead3-time.o
-
-obj-$(CONFIG_EARLY_PRINTK) += sead3-console.o
diff --git a/arch/mips/mti-sead3/Platform b/arch/mips/mti-sead3/Platform
deleted file mode 100644
index 3870924..0000000
--- a/arch/mips/mti-sead3/Platform
+++ /dev/null
@@ -1,7 +0,0 @@
-#
-# MIPS SEAD-3 board
-#
-platform-$(CONFIG_MIPS_SEAD3) += mti-sead3/
-cflags-$(CONFIG_MIPS_SEAD3) += -I$(srctree)/arch/mips/include/asm/mach-sead3
-load-$(CONFIG_MIPS_SEAD3) += 0xffffffff80100000
-all-$(CONFIG_MIPS_SEAD3) := $(COMPRESSION_FNAME).srec
diff --git a/arch/mips/mti-sead3/sead3-console.c b/arch/mips/mti-sead3/sead3-console.c
deleted file mode 100644
index 031f47d..0000000
--- a/arch/mips/mti-sead3/sead3-console.c
+++ /dev/null
@@ -1,46 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved.
- */
-#include <linux/init.h>
-#include <linux/console.h>
-#include <linux/serial_reg.h>
-#include <linux/io.h>
-
-#define SEAD_UART1_REGS_BASE 0xbf000800 /* ttyS1 = DB9 port */
-#define SEAD_UART0_REGS_BASE 0xbf000900 /* ttyS0 = USB port */
-#define PORT(base_addr, offset) ((unsigned int __iomem *)(base_addr+(offset)*4))
-
-static char console_port = 1;
-
-static inline unsigned int serial_in(int offset, unsigned int base_addr)
-{
- return __raw_readl(PORT(base_addr, offset)) & 0xff;
-}
-
-static inline void serial_out(int offset, int value, unsigned int base_addr)
-{
- __raw_writel(value, PORT(base_addr, offset));
-}
-
-void __init fw_init_early_console(char port)
-{
- console_port = port;
-}
-
-int prom_putchar(char c)
-{
- unsigned int base_addr;
-
- base_addr = console_port ? SEAD_UART1_REGS_BASE : SEAD_UART0_REGS_BASE;
-
- while ((serial_in(UART_LSR, base_addr) & UART_LSR_THRE) == 0)
- ;
-
- serial_out(UART_TX, c, base_addr);
-
- return 1;
-}
diff --git a/arch/mips/mti-sead3/sead3-display.c b/arch/mips/mti-sead3/sead3-display.c
deleted file mode 100644
index 9487599..0000000
--- a/arch/mips/mti-sead3/sead3-display.c
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved.
- */
-#include <linux/timer.h>
-#include <linux/io.h>
-#include <asm/mips-boards/generic.h>
-
-static unsigned int display_count;
-static unsigned int max_display_count;
-
-#define LCD_DISPLAY_POS_BASE 0x1f000400
-#define DISPLAY_LCDINSTRUCTION (0*2)
-#define DISPLAY_LCDDATA (1*2)
-#define DISPLAY_CPLDSTATUS (2*2)
-#define DISPLAY_CPLDDATA (3*2)
-#define LCD_SETDDRAM 0x80
-#define LCD_IR_BF 0x80
-
-const char display_string[] = " LINUX ON SEAD3 ";
-
-static void scroll_display_message(unsigned long data);
-static DEFINE_TIMER(mips_scroll_timer, scroll_display_message, HZ, 0);
-
-static void lcd_wait(unsigned int __iomem *display)
-{
- /* Wait for CPLD state machine to become idle. */
- do { } while (__raw_readl(display + DISPLAY_CPLDSTATUS) & 1);
-
- do {
- __raw_readl(display + DISPLAY_LCDINSTRUCTION);
-
- /* Wait for CPLD state machine to become idle. */
- do { } while (__raw_readl(display + DISPLAY_CPLDSTATUS) & 1);
- } while (__raw_readl(display + DISPLAY_CPLDDATA) & LCD_IR_BF);
-}
-
-void mips_display_message(const char *str)
-{
- static unsigned int __iomem *display;
- char ch;
- int i;
-
- if (unlikely(display == NULL))
- display = ioremap_nocache(LCD_DISPLAY_POS_BASE,
- (8 * sizeof(int)));
-
- for (i = 0; i < 16; i++) {
- if (*str)
- ch = *str++;
- else
- ch = ' ';
- lcd_wait(display);
- __raw_writel((LCD_SETDDRAM | i),
- (display + DISPLAY_LCDINSTRUCTION));
- lcd_wait(display);
- __raw_writel(ch, display + DISPLAY_LCDDATA);
- }
-}
-
-static void scroll_display_message(unsigned long data)
-{
- mips_display_message(&display_string[display_count++]);
- if (display_count == max_display_count)
- display_count = 0;
- mod_timer(&mips_scroll_timer, jiffies + HZ);
-}
-
-void mips_scroll_message(void)
-{
- del_timer_sync(&mips_scroll_timer);
- max_display_count = strlen(display_string) + 1 - 16;
- mod_timer(&mips_scroll_timer, jiffies + 1);
-}
diff --git a/arch/mips/mti-sead3/sead3-init.c b/arch/mips/mti-sead3/sead3-init.c
deleted file mode 100644
index 3572ea3..0000000
--- a/arch/mips/mti-sead3/sead3-init.c
+++ /dev/null
@@ -1,152 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved.
- */
-#include <linux/init.h>
-#include <linux/io.h>
-
-#include <asm/bootinfo.h>
-#include <asm/cacheflush.h>
-#include <asm/traps.h>
-#include <asm/mips-boards/generic.h>
-#include <asm/fw/fw.h>
-
-extern char except_vec_nmi;
-extern char except_vec_ejtag_debug;
-
-#ifdef CONFIG_SERIAL_8250_CONSOLE
-static void __init console_config(void)
-{
- char console_string[40];
- int baud = 0;
- char parity = '\0', bits = '\0', flow = '\0';
- char *s;
-
- if ((strstr(fw_getcmdline(), "console=")) == NULL) {
- s = fw_getenv("modetty0");
- if (s) {
- while (*s >= '0' && *s <= '9')
- baud = baud*10 + *s++ - '0';
- if (*s == ',')
- s++;
- if (*s)
- parity = *s++;
- if (*s == ',')
- s++;
- if (*s)
- bits = *s++;
- if (*s == ',')
- s++;
- if (*s == 'h')
- flow = 'r';
- }
- if (baud == 0)
- baud = 38400;
- if (parity != 'n' && parity != 'o' && parity != 'e')
- parity = 'n';
- if (bits != '7' && bits != '8')
- bits = '8';
- if (flow == '\0')
- flow = 'r';
- sprintf(console_string, " console=ttyS0,%d%c%c%c", baud,
- parity, bits, flow);
- strcat(fw_getcmdline(), console_string);
- }
-}
-#endif
-
-static void __init mips_nmi_setup(void)
-{
- void *base;
-
- base = cpu_has_veic ?
- (void *)(CAC_BASE + 0xa80) :
- (void *)(CAC_BASE + 0x380);
-#ifdef CONFIG_CPU_MICROMIPS
- /*
- * Decrement the exception vector address by one for microMIPS.
- */
- memcpy(base, (&except_vec_nmi - 1), 0x80);
-
- /*
- * This is a hack. We do not know if the boot loader was built with
- * microMIPS instructions or not. If it was not, the NMI exception
- * code at 0x80000a80 will be taken in MIPS32 mode. The hand coded
- * assembly below forces us into microMIPS mode if we are a pure
- * microMIPS kernel. The assembly instructions are:
- *
- * 3C1A8000 lui k0,0x8000
- * 375A0381 ori k0,k0,0x381
- * 03400008 jr k0
- * 00000000 nop
- *
- * The mode switch occurs by jumping to the unaligned exception
- * vector address at 0x80000381 which would have been 0x80000380
- * in MIPS32 mode. The jump to the unaligned address transitions
- * us into microMIPS mode.
- */
- if (!cpu_has_veic) {
- void *base2 = (void *)(CAC_BASE + 0xa80);
- *((unsigned int *)base2) = 0x3c1a8000;
- *((unsigned int *)base2 + 1) = 0x375a0381;
- *((unsigned int *)base2 + 2) = 0x03400008;
- *((unsigned int *)base2 + 3) = 0x00000000;
- flush_icache_range((unsigned long)base2,
- (unsigned long)base2 + 0x10);
- }
-#else
- memcpy(base, &except_vec_nmi, 0x80);
-#endif
- flush_icache_range((unsigned long)base, (unsigned long)base + 0x80);
-}
-
-static void __init mips_ejtag_setup(void)
-{
- void *base;
-
- base = cpu_has_veic ?
- (void *)(CAC_BASE + 0xa00) :
- (void *)(CAC_BASE + 0x300);
-#ifdef CONFIG_CPU_MICROMIPS
- /* Deja vu... */
- memcpy(base, (&except_vec_ejtag_debug - 1), 0x80);
- if (!cpu_has_veic) {
- void *base2 = (void *)(CAC_BASE + 0xa00);
- *((unsigned int *)base2) = 0x3c1a8000;
- *((unsigned int *)base2 + 1) = 0x375a0301;
- *((unsigned int *)base2 + 2) = 0x03400008;
- *((unsigned int *)base2 + 3) = 0x00000000;
- flush_icache_range((unsigned long)base2,
- (unsigned long)base2 + 0x10);
- }
-#else
- memcpy(base, &except_vec_ejtag_debug, 0x80);
-#endif
- flush_icache_range((unsigned long)base, (unsigned long)base + 0x80);
-}
-
-void __init prom_init(void)
-{
- board_nmi_handler_setup = mips_nmi_setup;
- board_ejtag_handler_setup = mips_ejtag_setup;
-
- fw_init_cmdline();
-#ifdef CONFIG_EARLY_PRINTK
- if ((strstr(fw_getcmdline(), "console=ttyS0")) != NULL)
- fw_init_early_console(0);
- else if ((strstr(fw_getcmdline(), "console=ttyS1")) != NULL)
- fw_init_early_console(1);
-#endif
-#ifdef CONFIG_SERIAL_8250_CONSOLE
- if ((strstr(fw_getcmdline(), "console=")) == NULL)
- strcat(fw_getcmdline(), " console=ttyS0,38400n8r");
- console_config();
-#endif
-}
-
-void __init prom_free_prom_memory(void)
-{
-}
diff --git a/arch/mips/mti-sead3/sead3-int.c b/arch/mips/mti-sead3/sead3-int.c
deleted file mode 100644
index e31e17f..0000000
--- a/arch/mips/mti-sead3/sead3-int.c
+++ /dev/null
@@ -1,42 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved.
- */
-#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/irqchip/mips-gic.h>
-#include <linux/io.h>
-
-#include <asm/irq_cpu.h>
-#include <asm/setup.h>
-
-#include <asm/mips-boards/sead3int.h>
-
-#define SEAD_CONFIG_GIC_PRESENT_SHF 1
-#define SEAD_CONFIG_GIC_PRESENT_MSK (1 << SEAD_CONFIG_GIC_PRESENT_SHF)
-#define SEAD_CONFIG_BASE 0x1b100110
-#define SEAD_CONFIG_SIZE 4
-
-static void __iomem *sead3_config_reg;
-
-void __init arch_init_irq(void)
-{
- if (!cpu_has_veic)
- mips_cpu_irq_init();
-
- sead3_config_reg = ioremap_nocache(SEAD_CONFIG_BASE, SEAD_CONFIG_SIZE);
- gic_present = (__raw_readl(sead3_config_reg) &
- SEAD_CONFIG_GIC_PRESENT_MSK) >>
- SEAD_CONFIG_GIC_PRESENT_SHF;
- pr_info("GIC: %spresent\n", (gic_present) ? "" : "not ");
- pr_info("EIC: %s\n",
- (current_cpu_data.options & MIPS_CPU_VEIC) ? "on" : "off");
-
- if (gic_present)
- gic_init(GIC_BASE_ADDR, GIC_ADDRSPACE_SZ, CPU_INT_GIC,
- MIPS_GIC_IRQ_BASE);
-}
-
diff --git a/arch/mips/mti-sead3/sead3-lcd.c b/arch/mips/mti-sead3/sead3-lcd.c
deleted file mode 100644
index 10b10ed2..0000000
--- a/arch/mips/mti-sead3/sead3-lcd.c
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved.
- */
-#include <linux/init.h>
-#include <linux/platform_device.h>
-
-static struct resource __initdata sead3_lcd_resource = {
- .start = 0x1f000400,
- .end = 0x1f00041f,
- .flags = IORESOURCE_MEM,
-};
-
-static __init int sead3_lcd_add(void)
-{
- struct platform_device *pdev;
- int retval;
-
- /* SEAD-3 and Cobalt platforms use same display type. */
- pdev = platform_device_alloc("cobalt-lcd", -1);
- if (!pdev)
- return -ENOMEM;
-
- retval = platform_device_add_resources(pdev, &sead3_lcd_resource, 1);
- if (retval)
- goto err_free_device;
-
- retval = platform_device_add(pdev);
- if (retval)
- goto err_free_device;
-
- return 0;
-
-err_free_device:
- platform_device_put(pdev);
-
- return retval;
-}
-
-device_initcall(sead3_lcd_add);
diff --git a/arch/mips/mti-sead3/sead3-platform.c b/arch/mips/mti-sead3/sead3-platform.c
deleted file mode 100644
index 73b73ef..0000000
--- a/arch/mips/mti-sead3/sead3-platform.c
+++ /dev/null
@@ -1,223 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved.
- */
-#include <linux/dma-mapping.h>
-#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/irqchip/mips-gic.h>
-#include <linux/leds.h>
-#include <linux/mtd/physmap.h>
-#include <linux/platform_device.h>
-#include <linux/serial_8250.h>
-#include <linux/smsc911x.h>
-
-#include <asm/mips-boards/sead3int.h>
-
-#define UART(base) \
-{ \
- .mapbase = base, \
- .irq = -1, \
- .uartclk = 14745600, \
- .iotype = UPIO_MEM32, \
- .flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_IOREMAP, \
- .regshift = 2, \
-}
-
-static struct plat_serial8250_port uart8250_data[] = {
- UART(0x1f000900), /* ttyS0 = USB */
- UART(0x1f000800), /* ttyS1 = RS232 */
- { },
-};
-
-static struct platform_device uart8250_device = {
- .name = "serial8250",
- .id = PLAT8250_DEV_PLATFORM2,
- .dev = {
- .platform_data = uart8250_data,
- },
-};
-
-static struct smsc911x_platform_config sead3_smsc911x_data = {
- .irq_polarity = SMSC911X_IRQ_POLARITY_ACTIVE_LOW,
- .irq_type = SMSC911X_IRQ_TYPE_PUSH_PULL,
- .flags = SMSC911X_USE_32BIT | SMSC911X_SAVE_MAC_ADDRESS,
- .phy_interface = PHY_INTERFACE_MODE_MII,
-};
-
-static struct resource sead3_net_resources[] = {
- {
- .start = 0x1f010000,
- .end = 0x1f01ffff,
- .flags = IORESOURCE_MEM
- }, {
- .flags = IORESOURCE_IRQ
- }
-};
-
-static struct platform_device sead3_net_device = {
- .name = "smsc911x",
- .id = 0,
- .dev = {
- .platform_data = &sead3_smsc911x_data,
- },
- .num_resources = ARRAY_SIZE(sead3_net_resources),
- .resource = sead3_net_resources
-};
-
-static struct mtd_partition sead3_mtd_partitions[] = {
- {
- .name = "User FS",
- .offset = 0x00000000,
- .size = 0x01fc0000,
- }, {
- .name = "Board Config",
- .offset = 0x01fc0000,
- .size = 0x00040000,
- .mask_flags = MTD_WRITEABLE
- },
-};
-
-static struct physmap_flash_data sead3_flash_data = {
- .width = 4,
- .nr_parts = ARRAY_SIZE(sead3_mtd_partitions),
- .parts = sead3_mtd_partitions
-};
-
-static struct resource sead3_flash_resource = {
- .start = 0x1c000000,
- .end = 0x1dffffff,
- .flags = IORESOURCE_MEM
-};
-
-static struct platform_device sead3_flash = {
- .name = "physmap-flash",
- .id = 0,
- .dev = {
- .platform_data = &sead3_flash_data,
- },
- .num_resources = 1,
- .resource = &sead3_flash_resource,
-};
-
-#define LEDFLAGS(bits, shift) \
- ((bits << 8) | (shift << 8))
-
-#define LEDBITS(id, shift, bits) \
- .name = id #shift, \
- .flags = LEDFLAGS(bits, shift)
-
-static struct led_info led_data_info[] = {
- { LEDBITS("bit", 0, 1) },
- { LEDBITS("bit", 1, 1) },
- { LEDBITS("bit", 2, 1) },
- { LEDBITS("bit", 3, 1) },
- { LEDBITS("bit", 4, 1) },
- { LEDBITS("bit", 5, 1) },
- { LEDBITS("bit", 6, 1) },
- { LEDBITS("bit", 7, 1) },
- { LEDBITS("all", 0, 8) },
-};
-
-static struct led_platform_data led_data = {
- .num_leds = ARRAY_SIZE(led_data_info),
- .leds = led_data_info
-};
-
-static struct resource pled_resources[] = {
- {
- .start = 0x1f000210,
- .end = 0x1f000217,
- .flags = IORESOURCE_MEM
- }
-};
-
-static struct platform_device pled_device = {
- .name = "sead3::pled",
- .id = 0,
- .dev = {
- .platform_data = &led_data,
- },
- .num_resources = ARRAY_SIZE(pled_resources),
- .resource = pled_resources
-};
-
-
-static struct resource fled_resources[] = {
- {
- .start = 0x1f000218,
- .end = 0x1f00021f,
- .flags = IORESOURCE_MEM
- }
-};
-
-static struct platform_device fled_device = {
- .name = "sead3::fled",
- .id = 0,
- .dev = {
- .platform_data = &led_data,
- },
- .num_resources = ARRAY_SIZE(fled_resources),
- .resource = fled_resources
-};
-
-static struct platform_device sead3_led_device = {
- .name = "sead3-led",
- .id = -1,
-};
-
-static struct resource ehci_resources[] = {
- {
- .start = 0x1b200000,
- .end = 0x1b200fff,
- .flags = IORESOURCE_MEM
- }, {
- .flags = IORESOURCE_IRQ
- }
-};
-
-static u64 sead3_usbdev_dma_mask = DMA_BIT_MASK(32);
-
-static struct platform_device ehci_device = {
- .name = "sead3-ehci",
- .id = 0,
- .dev = {
- .dma_mask = &sead3_usbdev_dma_mask,
- .coherent_dma_mask = DMA_BIT_MASK(32)
- },
- .num_resources = ARRAY_SIZE(ehci_resources),
- .resource = ehci_resources
-};
-
-static struct platform_device *sead3_platform_devices[] __initdata = {
- &uart8250_device,
- &sead3_flash,
- &pled_device,
- &fled_device,
- &sead3_led_device,
- &ehci_device,
- &sead3_net_device,
-};
-
-static int __init sead3_platforms_device_init(void)
-{
- if (gic_present) {
- uart8250_data[0].irq = MIPS_GIC_IRQ_BASE + GIC_INT_UART0;
- uart8250_data[1].irq = MIPS_GIC_IRQ_BASE + GIC_INT_UART1;
- ehci_resources[1].start = MIPS_GIC_IRQ_BASE + GIC_INT_EHCI;
- sead3_net_resources[1].start = MIPS_GIC_IRQ_BASE + GIC_INT_NET;
- } else {
- uart8250_data[0].irq = MIPS_CPU_IRQ_BASE + CPU_INT_UART0;
- uart8250_data[1].irq = MIPS_CPU_IRQ_BASE + CPU_INT_UART1;
- ehci_resources[1].start = MIPS_CPU_IRQ_BASE + CPU_INT_EHCI;
- sead3_net_resources[1].start = MIPS_CPU_IRQ_BASE + CPU_INT_NET;
- }
-
- return platform_add_devices(sead3_platform_devices,
- ARRAY_SIZE(sead3_platform_devices));
-}
-
-device_initcall(sead3_platforms_device_init);
diff --git a/arch/mips/mti-sead3/sead3-reset.c b/arch/mips/mti-sead3/sead3-reset.c
deleted file mode 100644
index e6fb244..0000000
--- a/arch/mips/mti-sead3/sead3-reset.c
+++ /dev/null
@@ -1,40 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved.
- */
-#include <linux/io.h>
-#include <linux/pm.h>
-
-#include <asm/reboot.h>
-
-#define SOFTRES_REG 0x1f000050
-#define GORESET 0x4d
-
-static void mips_machine_restart(char *command)
-{
- unsigned int __iomem *softres_reg =
- ioremap(SOFTRES_REG, sizeof(unsigned int));
-
- __raw_writel(GORESET, softres_reg);
-}
-
-static void mips_machine_halt(void)
-{
- unsigned int __iomem *softres_reg =
- ioremap(SOFTRES_REG, sizeof(unsigned int));
-
- __raw_writel(GORESET, softres_reg);
-}
-
-static int __init mips_reboot_setup(void)
-{
- _machine_restart = mips_machine_restart;
- _machine_halt = mips_machine_halt;
- pm_power_off = mips_machine_halt;
-
- return 0;
-}
-arch_initcall(mips_reboot_setup);
diff --git a/arch/mips/mti-sead3/sead3-setup.c b/arch/mips/mti-sead3/sead3-setup.c
deleted file mode 100644
index edfcaf0..0000000
--- a/arch/mips/mti-sead3/sead3-setup.c
+++ /dev/null
@@ -1,108 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved.
- * Copyright (C) 2013 Imagination Technologies Ltd.
- */
-#include <linux/init.h>
-#include <linux/libfdt.h>
-#include <linux/of_fdt.h>
-
-#include <asm/prom.h>
-#include <asm/fw/fw.h>
-
-#include <asm/mips-boards/generic.h>
-
-const char *get_system_type(void)
-{
- return "MIPS SEAD3";
-}
-
-static uint32_t get_memsize_from_cmdline(void)
-{
- int memsize = 0;
- char *p = arcs_cmdline;
- char *s = "memsize=";
-
- p = strstr(p, s);
- if (p) {
- p += strlen(s);
- memsize = memparse(p, NULL);
- }
-
- return memsize;
-}
-
-static uint32_t get_memsize_from_env(void)
-{
- int memsize = 0;
- char *p;
-
- p = fw_getenv("memsize");
- if (p)
- memsize = memparse(p, NULL);
-
- return memsize;
-}
-
-static uint32_t get_memsize(void)
-{
- uint32_t memsize;
-
- memsize = get_memsize_from_cmdline();
- if (memsize)
- return memsize;
-
- return get_memsize_from_env();
-}
-
-static void __init parse_memsize_param(void)
-{
- int offset;
- const uint64_t *prop_value;
- int prop_len;
- uint32_t memsize = get_memsize();
-
- if (!memsize)
- return;
-
- offset = fdt_path_offset(__dtb_start, "/memory");
- if (offset > 0) {
- uint64_t new_value;
- /*
- * reg contains 2 32-bits BE values, offset and size. We just
- * want to replace the size value without affecting the offset
- */
- prop_value = fdt_getprop(__dtb_start, offset, "reg", &prop_len);
- new_value = be64_to_cpu(*prop_value);
- new_value = (new_value & ~0xffffffffllu) | memsize;
- fdt_setprop_inplace_u64(__dtb_start, offset, "reg", new_value);
- }
-}
-
-void __init *plat_get_fdt(void)
-{
- return (void *)__dtb_start;
-}
-
-void __init plat_mem_setup(void)
-{
- /* allow command line/bootloader env to override memory size in DT */
- parse_memsize_param();
-
- /*
- * Load the builtin devicetree. This causes the chosen node to be
- * parsed resulting in our memory appearing
- */
- __dt_setup_arch(__dtb_start);
-}
-
-void __init device_tree_init(void)
-{
- if (!initial_boot_params)
- return;
-
- unflatten_and_copy_device_tree();
-}
diff --git a/arch/mips/mti-sead3/sead3-time.c b/arch/mips/mti-sead3/sead3-time.c
deleted file mode 100644
index a120b7a..0000000
--- a/arch/mips/mti-sead3/sead3-time.c
+++ /dev/null
@@ -1,99 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved.
- */
-#include <linux/init.h>
-#include <linux/irqchip/mips-gic.h>
-
-#include <asm/cpu.h>
-#include <asm/setup.h>
-#include <asm/time.h>
-#include <asm/irq.h>
-#include <asm/mips-boards/generic.h>
-
-static void __iomem *status_reg = (void __iomem *)0xbf000410;
-
-/*
- * Estimate CPU frequency. Sets mips_hpt_frequency as a side-effect.
- */
-static unsigned int __init estimate_cpu_frequency(void)
-{
- unsigned int prid = read_c0_prid() & (PRID_COMP_MASK | PRID_IMP_MASK);
- unsigned int tick = 0;
- unsigned int freq;
- unsigned int orig;
- unsigned long flags;
-
- local_irq_save(flags);
-
- orig = readl(status_reg) & 0x2; /* get original sample */
- /* wait for transition */
- while ((readl(status_reg) & 0x2) == orig)
- ;
- orig = orig ^ 0x2; /* flip the bit */
-
- write_c0_count(0);
-
- /* wait 1 second (the sampling clock transitions every 10ms) */
- while (tick < 100) {
- /* wait for transition */
- while ((readl(status_reg) & 0x2) == orig)
- ;
- orig = orig ^ 0x2; /* flip the bit */
- tick++;
- }
-
- freq = read_c0_count();
-
- local_irq_restore(flags);
-
- mips_hpt_frequency = freq;
-
- /* Adjust for processor */
- if ((prid != (PRID_COMP_MIPS | PRID_IMP_20KC)) &&
- (prid != (PRID_COMP_MIPS | PRID_IMP_25KF)))
- freq *= 2;
-
- freq += 5000; /* rounding */
- freq -= freq%10000;
-
- return freq ;
-}
-
-void read_persistent_clock(struct timespec *ts)
-{
- ts->tv_sec = 0;
- ts->tv_nsec = 0;
-}
-
-int get_c0_perfcount_int(void)
-{
- if (gic_present)
- return gic_get_c0_perfcount_int();
- if (cp0_perfcount_irq >= 0)
- return MIPS_CPU_IRQ_BASE + cp0_perfcount_irq;
- return -1;
-}
-EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
-
-unsigned int get_c0_compare_int(void)
-{
- if (gic_present)
- return gic_get_c0_compare_int();
- return MIPS_CPU_IRQ_BASE + cp0_compare_irq;
-}
-
-void __init plat_time_init(void)
-{
- unsigned int est_freq;
-
- est_freq = estimate_cpu_frequency();
-
- pr_debug("CPU frequency %d.%02d MHz\n", (est_freq / 1000000),
- (est_freq % 1000000) * 100 / 1000000);
-
- mips_scroll_message();
-}
diff --git a/arch/mips/pci/Makefile b/arch/mips/pci/Makefile
index 139ad1d..4b82148 100644
--- a/arch/mips/pci/Makefile
+++ b/arch/mips/pci/Makefile
@@ -3,6 +3,8 @@
#
obj-y += pci.o
+obj-$(CONFIG_PCI_DRIVERS_LEGACY)+= pci-legacy.o
+obj-$(CONFIG_PCI_DRIVERS_GENERIC)+= pci-generic.o
#
# PCI bus host bridge specific code
diff --git a/arch/mips/pci/pci-alchemy.c b/arch/mips/pci/pci-alchemy.c
index c8994c1..e99ca77 100644
--- a/arch/mips/pci/pci-alchemy.c
+++ b/arch/mips/pci/pci-alchemy.c
@@ -429,7 +429,8 @@ static int alchemy_pci_probe(struct platform_device *pdev)
/* Au1500 revisions older than AD have borked coherent PCI */
if ((alchemy_get_cputype() == ALCHEMY_CPU_AU1500) &&
- (read_c0_prid() < 0x01030202) && !coherentio) {
+ (read_c0_prid() < 0x01030202) &&
+ (coherentio == IO_COHERENCE_DISABLED)) {
val = __raw_readl(ctx->regs + PCI_REG_CONFIG);
val |= PCI_CONFIG_NC;
__raw_writel(val, ctx->regs + PCI_REG_CONFIG);
diff --git a/arch/mips/pci/pci-ar71xx.c b/arch/mips/pci/pci-ar71xx.c
index 7db963d..bdf87b4 100644
--- a/arch/mips/pci/pci-ar71xx.c
+++ b/arch/mips/pci/pci-ar71xx.c
@@ -18,7 +18,7 @@
#include <linux/pci.h>
#include <linux/pci_regs.h>
#include <linux/interrupt.h>
-#include <linux/module.h>
+#include <linux/init.h>
#include <linux/platform_device.h>
#include <asm/mach-ath79/ar71xx_regs.h>
diff --git a/arch/mips/pci/pci-ar724x.c b/arch/mips/pci/pci-ar724x.c
index 2013dad..1e23c8d 100644
--- a/arch/mips/pci/pci-ar724x.c
+++ b/arch/mips/pci/pci-ar724x.c
@@ -11,7 +11,7 @@
#include <linux/irq.h>
#include <linux/pci.h>
-#include <linux/module.h>
+#include <linux/init.h>
#include <linux/platform_device.h>
#include <asm/mach-ath79/ath79.h>
#include <asm/mach-ath79/ar71xx_regs.h>
diff --git a/arch/mips/pci/pci-generic.c b/arch/mips/pci/pci-generic.c
new file mode 100644
index 0000000..dce304d
--- /dev/null
+++ b/arch/mips/pci/pci-generic.c
@@ -0,0 +1,52 @@
+/*
+ * Copyright (C) 2016 Imagination Technologies
+ * Author: Paul Burton <paul.burton@imgtec.com>
+ *
+ * pcibios_align_resource taken from arch/arm/kernel/bios32.c.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/pci.h>
+
+/*
+ * We need to avoid collisions with `mirrored' VGA ports
+ * and other strange ISA hardware, so we always want the
+ * addresses to be allocated in the 0x000-0x0ff region
+ * modulo 0x400.
+ *
+ * Why? Because some silly external IO cards only decode
+ * the low 10 bits of the IO address. The 0x00-0xff region
+ * is reserved for motherboard devices that decode all 16
+ * bits, so it's ok to allocate at, say, 0x2800-0x28ff,
+ * but we want to try to avoid allocating at 0x2900-0x2bff
+ * which might have be mirrored at 0x0100-0x03ff..
+ */
+resource_size_t pcibios_align_resource(void *data, const struct resource *res,
+ resource_size_t size, resource_size_t align)
+{
+ struct pci_dev *dev = data;
+ resource_size_t start = res->start;
+ struct pci_host_bridge *host_bridge;
+
+ if (res->flags & IORESOURCE_IO && start & 0x300)
+ start = (start + 0x3ff) & ~0x3ff;
+
+ start = (start + align - 1) & ~(align - 1);
+
+ host_bridge = pci_find_host_bridge(dev->bus);
+
+ if (host_bridge->align_resource)
+ return host_bridge->align_resource(dev, res,
+ start, size, align);
+
+ return start;
+}
+
+void pcibios_fixup_bus(struct pci_bus *bus)
+{
+ pci_read_bridge_bases(bus);
+}
diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c
index b9deab1..f18f887 100644
--- a/arch/mips/pci/pci-lantiq.c
+++ b/arch/mips/pci/pci-lantiq.c
@@ -13,7 +13,6 @@
#include <linux/delay.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
-#include <linux/module.h>
#include <linux/clk.h>
#include <linux/of_platform.h>
#include <linux/of_gpio.h>
@@ -234,7 +233,6 @@ static const struct of_device_id ltq_pci_match[] = {
{ .compatible = "lantiq,pci-xway" },
{},
};
-MODULE_DEVICE_TABLE(of, ltq_pci_match);
static struct platform_driver ltq_pci_driver = {
.probe = ltq_pci_probe,
diff --git a/arch/mips/pci/pci-legacy.c b/arch/mips/pci/pci-legacy.c
new file mode 100644
index 0000000..014649b
--- /dev/null
+++ b/arch/mips/pci/pci-legacy.c
@@ -0,0 +1,302 @@
+/*
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * Copyright (C) 2003, 04, 11 Ralf Baechle (ralf@linux-mips.org)
+ * Copyright (C) 2011 Wind River Systems,
+ * written by Ralf Baechle (ralf@linux-mips.org)
+ */
+#include <linux/bug.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/bootmem.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/of_address.h>
+
+#include <asm/cpu-info.h>
+
+/*
+ * If PCI_PROBE_ONLY in pci_flags is set, we don't change any PCI resource
+ * assignments.
+ */
+
+/*
+ * The PCI controller list.
+ */
+static LIST_HEAD(controllers);
+
+static int pci_initialized;
+
+/*
+ * We need to avoid collisions with `mirrored' VGA ports
+ * and other strange ISA hardware, so we always want the
+ * addresses to be allocated in the 0x000-0x0ff region
+ * modulo 0x400.
+ *
+ * Why? Because some silly external IO cards only decode
+ * the low 10 bits of the IO address. The 0x00-0xff region
+ * is reserved for motherboard devices that decode all 16
+ * bits, so it's ok to allocate at, say, 0x2800-0x28ff,
+ * but we want to try to avoid allocating at 0x2900-0x2bff
+ * which might have be mirrored at 0x0100-0x03ff..
+ */
+resource_size_t
+pcibios_align_resource(void *data, const struct resource *res,
+ resource_size_t size, resource_size_t align)
+{
+ struct pci_dev *dev = data;
+ struct pci_controller *hose = dev->sysdata;
+ resource_size_t start = res->start;
+
+ if (res->flags & IORESOURCE_IO) {
+ /* Make sure we start at our min on all hoses */
+ if (start < PCIBIOS_MIN_IO + hose->io_resource->start)
+ start = PCIBIOS_MIN_IO + hose->io_resource->start;
+
+ /*
+ * Put everything into 0x00-0xff region modulo 0x400
+ */
+ if (start & 0x300)
+ start = (start + 0x3ff) & ~0x3ff;
+ } else if (res->flags & IORESOURCE_MEM) {
+ /* Make sure we start at our min on all hoses */
+ if (start < PCIBIOS_MIN_MEM + hose->mem_resource->start)
+ start = PCIBIOS_MIN_MEM + hose->mem_resource->start;
+ }
+
+ return start;
+}
+
+static void pcibios_scanbus(struct pci_controller *hose)
+{
+ static int next_busno;
+ static int need_domain_info;
+ LIST_HEAD(resources);
+ struct pci_bus *bus;
+
+ if (hose->get_busno && pci_has_flag(PCI_PROBE_ONLY))
+ next_busno = (*hose->get_busno)();
+
+ pci_add_resource_offset(&resources,
+ hose->mem_resource, hose->mem_offset);
+ pci_add_resource_offset(&resources,
+ hose->io_resource, hose->io_offset);
+ pci_add_resource_offset(&resources,
+ hose->busn_resource, hose->busn_offset);
+ bus = pci_scan_root_bus(NULL, next_busno, hose->pci_ops, hose,
+ &resources);
+ hose->bus = bus;
+
+ need_domain_info = need_domain_info || pci_domain_nr(bus);
+ set_pci_need_domain_info(hose, need_domain_info);
+
+ if (!bus) {
+ pci_free_resource_list(&resources);
+ return;
+ }
+
+ next_busno = bus->busn_res.end + 1;
+ /* Don't allow 8-bit bus number overflow inside the hose -
+ reserve some space for bridges. */
+ if (next_busno > 224) {
+ next_busno = 0;
+ need_domain_info = 1;
+ }
+
+ /*
+ * We insert PCI resources into the iomem_resource and
+ * ioport_resource trees in either pci_bus_claim_resources()
+ * or pci_bus_assign_resources().
+ */
+ if (pci_has_flag(PCI_PROBE_ONLY)) {
+ pci_bus_claim_resources(bus);
+ } else {
+ pci_bus_size_bridges(bus);
+ pci_bus_assign_resources(bus);
+ }
+ pci_bus_add_devices(bus);
+}
+
+#ifdef CONFIG_OF
+void pci_load_of_ranges(struct pci_controller *hose, struct device_node *node)
+{
+ struct of_pci_range range;
+ struct of_pci_range_parser parser;
+
+ pr_info("PCI host bridge %s ranges:\n", node->full_name);
+ hose->of_node = node;
+
+ if (of_pci_range_parser_init(&parser, node))
+ return;
+
+ for_each_of_pci_range(&parser, &range) {
+ struct resource *res = NULL;
+
+ switch (range.flags & IORESOURCE_TYPE_BITS) {
+ case IORESOURCE_IO:
+ pr_info(" IO 0x%016llx..0x%016llx\n",
+ range.cpu_addr,
+ range.cpu_addr + range.size - 1);
+ hose->io_map_base =
+ (unsigned long)ioremap(range.cpu_addr,
+ range.size);
+ res = hose->io_resource;
+ break;
+ case IORESOURCE_MEM:
+ pr_info(" MEM 0x%016llx..0x%016llx\n",
+ range.cpu_addr,
+ range.cpu_addr + range.size - 1);
+ res = hose->mem_resource;
+ break;
+ }
+ if (res != NULL)
+ of_pci_range_to_resource(&range, node, res);
+ }
+}
+
+struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus)
+{
+ struct pci_controller *hose = bus->sysdata;
+
+ return of_node_get(hose->of_node);
+}
+#endif
+
+static DEFINE_MUTEX(pci_scan_mutex);
+
+void register_pci_controller(struct pci_controller *hose)
+{
+ struct resource *parent;
+
+ parent = hose->mem_resource->parent;
+ if (!parent)
+ parent = &iomem_resource;
+
+ if (request_resource(parent, hose->mem_resource) < 0)
+ goto out;
+
+ parent = hose->io_resource->parent;
+ if (!parent)
+ parent = &ioport_resource;
+
+ if (request_resource(parent, hose->io_resource) < 0) {
+ release_resource(hose->mem_resource);
+ goto out;
+ }
+
+ INIT_LIST_HEAD(&hose->list);
+ list_add(&hose->list, &controllers);
+
+ /*
+ * Do not panic here but later - this might happen before console init.
+ */
+ if (!hose->io_map_base) {
+ printk(KERN_WARNING
+ "registering PCI controller with io_map_base unset\n");
+ }
+
+ /*
+ * Scan the bus if it is register after the PCI subsystem
+ * initialization.
+ */
+ if (pci_initialized) {
+ mutex_lock(&pci_scan_mutex);
+ pcibios_scanbus(hose);
+ mutex_unlock(&pci_scan_mutex);
+ }
+
+ return;
+
+out:
+ printk(KERN_WARNING
+ "Skipping PCI bus scan due to resource conflict\n");
+}
+
+static int __init pcibios_init(void)
+{
+ struct pci_controller *hose;
+
+ /* Scan all of the recorded PCI controllers. */
+ list_for_each_entry(hose, &controllers, list)
+ pcibios_scanbus(hose);
+
+ pci_fixup_irqs(pci_common_swizzle, pcibios_map_irq);
+
+ pci_initialized = 1;
+
+ return 0;
+}
+
+subsys_initcall(pcibios_init);
+
+static int pcibios_enable_resources(struct pci_dev *dev, int mask)
+{
+ u16 cmd, old_cmd;
+ int idx;
+ struct resource *r;
+
+ pci_read_config_word(dev, PCI_COMMAND, &cmd);
+ old_cmd = cmd;
+ for (idx=0; idx < PCI_NUM_RESOURCES; idx++) {
+ /* Only set up the requested stuff */
+ if (!(mask & (1<<idx)))
+ continue;
+
+ r = &dev->resource[idx];
+ if (!(r->flags & (IORESOURCE_IO | IORESOURCE_MEM)))
+ continue;
+ if ((idx == PCI_ROM_RESOURCE) &&
+ (!(r->flags & IORESOURCE_ROM_ENABLE)))
+ continue;
+ if (!r->start && r->end) {
+ printk(KERN_ERR "PCI: Device %s not available "
+ "because of resource collisions\n",
+ pci_name(dev));
+ return -EINVAL;
+ }
+ if (r->flags & IORESOURCE_IO)
+ cmd |= PCI_COMMAND_IO;
+ if (r->flags & IORESOURCE_MEM)
+ cmd |= PCI_COMMAND_MEMORY;
+ }
+ if (cmd != old_cmd) {
+ printk("PCI: Enabling device %s (%04x -> %04x)\n",
+ pci_name(dev), old_cmd, cmd);
+ pci_write_config_word(dev, PCI_COMMAND, cmd);
+ }
+ return 0;
+}
+
+int pcibios_enable_device(struct pci_dev *dev, int mask)
+{
+ int err;
+
+ if ((err = pcibios_enable_resources(dev, mask)) < 0)
+ return err;
+
+ return pcibios_plat_dev_init(dev);
+}
+
+void pcibios_fixup_bus(struct pci_bus *bus)
+{
+ struct pci_dev *dev = bus->self;
+
+ if (pci_has_flag(PCI_PROBE_ONLY) && dev &&
+ (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) {
+ pci_read_bridge_bases(bus);
+ }
+}
+
+char * (*pcibios_plat_setup)(char *str) __initdata;
+
+char *__init pcibios_setup(char *str)
+{
+ if (pcibios_plat_setup)
+ return pcibios_plat_setup(str);
+ return str;
+}
diff --git a/arch/mips/pci/pci-mt7620.c b/arch/mips/pci/pci-mt7620.c
index 6ce8162..628c513 100644
--- a/arch/mips/pci/pci-mt7620.c
+++ b/arch/mips/pci/pci-mt7620.c
@@ -15,7 +15,6 @@
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
-#include <linux/module.h>
#include <linux/of.h>
#include <linux/of_irq.h>
#include <linux/of_pci.h>
@@ -407,13 +406,11 @@ static const struct of_device_id mt7620_pci_ids[] = {
{ .compatible = "mediatek,mt7620-pci" },
{},
};
-MODULE_DEVICE_TABLE(of, mt7620_pci_ids);
static struct platform_driver mt7620_pci_driver = {
.probe = mt7620_pci_probe,
.driver = {
.name = "mt7620-pci",
- .owner = THIS_MODULE,
.of_match_table = of_match_ptr(mt7620_pci_ids),
},
};
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index c258cd4..308d051 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -204,6 +204,8 @@ const char *octeon_get_pci_interrupts(void)
* Interrupt Number (INTA# = 0, INTB# = 1, INTC# = 2, and
* INTD# = 3)
*/
+ if (of_machine_is_compatible("dlink,dsr-500n"))
+ return "CCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC";
switch (octeon_bootinfo->board_type) {
case CVMX_BOARD_TYPE_NAO38:
/* This is really the NAC38 */
diff --git a/arch/mips/pci/pci-rt2880.c b/arch/mips/pci/pci-rt2880.c
index f2a1050..d6360fe 100644
--- a/arch/mips/pci/pci-rt2880.c
+++ b/arch/mips/pci/pci-rt2880.c
@@ -16,7 +16,6 @@
#include <linux/pci.h>
#include <linux/io.h>
#include <linux/init.h>
-#include <linux/module.h>
#include <linux/of_platform.h>
#include <linux/of_irq.h>
#include <linux/of_pci.h>
@@ -260,7 +259,6 @@ static const struct of_device_id rt288x_pci_match[] = {
{ .compatible = "ralink,rt288x-pci" },
{},
};
-MODULE_DEVICE_TABLE(of, rt288x_pci_match);
static struct platform_driver rt288x_pci_driver = {
.probe = rt288x_pci_probe,
diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c
index 53a42b0..3520e9b 100644
--- a/arch/mips/pci/pci-rt3883.c
+++ b/arch/mips/pci/pci-rt3883.c
@@ -16,7 +16,6 @@
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
-#include <linux/module.h>
#include <linux/of.h>
#include <linux/of_irq.h>
#include <linux/of_pci.h>
@@ -580,7 +579,6 @@ static const struct of_device_id rt3883_pci_ids[] = {
{ .compatible = "ralink,rt3883-pci" },
{},
};
-MODULE_DEVICE_TABLE(of, rt3883_pci_ids);
static struct platform_driver rt3883_pci_driver = {
.probe = rt3883_pci_probe,
diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c
index b4c02f2..f6325fa 100644
--- a/arch/mips/pci/pci.c
+++ b/arch/mips/pci/pci.c
@@ -20,208 +20,13 @@
#include <asm/cpu-info.h>
-/*
- * If PCI_PROBE_ONLY in pci_flags is set, we don't change any PCI resource
- * assignments.
- */
-
-/*
- * The PCI controller list.
- */
-
-static struct pci_controller *hose_head, **hose_tail = &hose_head;
-
unsigned long PCIBIOS_MIN_IO;
+EXPORT_SYMBOL(PCIBIOS_MIN_IO);
+
unsigned long PCIBIOS_MIN_MEM;
+EXPORT_SYMBOL(PCIBIOS_MIN_MEM);
-static int pci_initialized;
-
-/*
- * We need to avoid collisions with `mirrored' VGA ports
- * and other strange ISA hardware, so we always want the
- * addresses to be allocated in the 0x000-0x0ff region
- * modulo 0x400.
- *
- * Why? Because some silly external IO cards only decode
- * the low 10 bits of the IO address. The 0x00-0xff region
- * is reserved for motherboard devices that decode all 16
- * bits, so it's ok to allocate at, say, 0x2800-0x28ff,
- * but we want to try to avoid allocating at 0x2900-0x2bff
- * which might have be mirrored at 0x0100-0x03ff..
- */
-resource_size_t
-pcibios_align_resource(void *data, const struct resource *res,
- resource_size_t size, resource_size_t align)
-{
- struct pci_dev *dev = data;
- struct pci_controller *hose = dev->sysdata;
- resource_size_t start = res->start;
-
- if (res->flags & IORESOURCE_IO) {
- /* Make sure we start at our min on all hoses */
- if (start < PCIBIOS_MIN_IO + hose->io_resource->start)
- start = PCIBIOS_MIN_IO + hose->io_resource->start;
-
- /*
- * Put everything into 0x00-0xff region modulo 0x400
- */
- if (start & 0x300)
- start = (start + 0x3ff) & ~0x3ff;
- } else if (res->flags & IORESOURCE_MEM) {
- /* Make sure we start at our min on all hoses */
- if (start < PCIBIOS_MIN_MEM + hose->mem_resource->start)
- start = PCIBIOS_MIN_MEM + hose->mem_resource->start;
- }
-
- return start;
-}
-
-static void pcibios_scanbus(struct pci_controller *hose)
-{
- static int next_busno;
- static int need_domain_info;
- LIST_HEAD(resources);
- struct pci_bus *bus;
-
- if (hose->get_busno && pci_has_flag(PCI_PROBE_ONLY))
- next_busno = (*hose->get_busno)();
-
- pci_add_resource_offset(&resources,
- hose->mem_resource, hose->mem_offset);
- pci_add_resource_offset(&resources,
- hose->io_resource, hose->io_offset);
- pci_add_resource_offset(&resources,
- hose->busn_resource, hose->busn_offset);
- bus = pci_scan_root_bus(NULL, next_busno, hose->pci_ops, hose,
- &resources);
- hose->bus = bus;
-
- need_domain_info = need_domain_info || hose->index;
- hose->need_domain_info = need_domain_info;
-
- if (!bus) {
- pci_free_resource_list(&resources);
- return;
- }
-
- next_busno = bus->busn_res.end + 1;
- /* Don't allow 8-bit bus number overflow inside the hose -
- reserve some space for bridges. */
- if (next_busno > 224) {
- next_busno = 0;
- need_domain_info = 1;
- }
-
- /*
- * We insert PCI resources into the iomem_resource and
- * ioport_resource trees in either pci_bus_claim_resources()
- * or pci_bus_assign_resources().
- */
- if (pci_has_flag(PCI_PROBE_ONLY)) {
- pci_bus_claim_resources(bus);
- } else {
- pci_bus_size_bridges(bus);
- pci_bus_assign_resources(bus);
- }
- pci_bus_add_devices(bus);
-}
-
-#ifdef CONFIG_OF
-void pci_load_of_ranges(struct pci_controller *hose, struct device_node *node)
-{
- struct of_pci_range range;
- struct of_pci_range_parser parser;
-
- pr_info("PCI host bridge %s ranges:\n", node->full_name);
- hose->of_node = node;
-
- if (of_pci_range_parser_init(&parser, node))
- return;
-
- for_each_of_pci_range(&parser, &range) {
- struct resource *res = NULL;
-
- switch (range.flags & IORESOURCE_TYPE_BITS) {
- case IORESOURCE_IO:
- pr_info(" IO 0x%016llx..0x%016llx\n",
- range.cpu_addr,
- range.cpu_addr + range.size - 1);
- hose->io_map_base =
- (unsigned long)ioremap(range.cpu_addr,
- range.size);
- res = hose->io_resource;
- break;
- case IORESOURCE_MEM:
- pr_info(" MEM 0x%016llx..0x%016llx\n",
- range.cpu_addr,
- range.cpu_addr + range.size - 1);
- res = hose->mem_resource;
- break;
- }
- if (res != NULL)
- of_pci_range_to_resource(&range, node, res);
- }
-}
-
-struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus)
-{
- struct pci_controller *hose = bus->sysdata;
-
- return of_node_get(hose->of_node);
-}
-#endif
-
-static DEFINE_MUTEX(pci_scan_mutex);
-
-void register_pci_controller(struct pci_controller *hose)
-{
- struct resource *parent;
-
- parent = hose->mem_resource->parent;
- if (!parent)
- parent = &iomem_resource;
-
- if (request_resource(parent, hose->mem_resource) < 0)
- goto out;
-
- parent = hose->io_resource->parent;
- if (!parent)
- parent = &ioport_resource;
-
- if (request_resource(parent, hose->io_resource) < 0) {
- release_resource(hose->mem_resource);
- goto out;
- }
-
- *hose_tail = hose;
- hose_tail = &hose->next;
-
- /*
- * Do not panic here but later - this might happen before console init.
- */
- if (!hose->io_map_base) {
- printk(KERN_WARNING
- "registering PCI controller with io_map_base unset\n");
- }
-
- /*
- * Scan the bus if it is register after the PCI subsystem
- * initialization.
- */
- if (pci_initialized) {
- mutex_lock(&pci_scan_mutex);
- pcibios_scanbus(hose);
- mutex_unlock(&pci_scan_mutex);
- }
-
- return;
-
-out:
- printk(KERN_WARNING
- "Skipping PCI bus scan due to resource conflict\n");
-}
-
-static void __init pcibios_set_cache_line_size(void)
+static int __init pcibios_set_cache_line_size(void)
{
struct cpuinfo_mips *c = ¤t_cpu_data;
unsigned int lsize;
@@ -239,92 +44,9 @@ static void __init pcibios_set_cache_line_size(void)
pci_dfl_cache_line_size = lsize >> 2;
pr_debug("PCI: pci_cache_line_size set to %d bytes\n", lsize);
-}
-
-static int __init pcibios_init(void)
-{
- struct pci_controller *hose;
-
- pcibios_set_cache_line_size();
-
- /* Scan all of the recorded PCI controllers. */
- for (hose = hose_head; hose; hose = hose->next)
- pcibios_scanbus(hose);
-
- pci_fixup_irqs(pci_common_swizzle, pcibios_map_irq);
-
- pci_initialized = 1;
-
return 0;
}
-
-subsys_initcall(pcibios_init);
-
-static int pcibios_enable_resources(struct pci_dev *dev, int mask)
-{
- u16 cmd, old_cmd;
- int idx;
- struct resource *r;
-
- pci_read_config_word(dev, PCI_COMMAND, &cmd);
- old_cmd = cmd;
- for (idx=0; idx < PCI_NUM_RESOURCES; idx++) {
- /* Only set up the requested stuff */
- if (!(mask & (1<<idx)))
- continue;
-
- r = &dev->resource[idx];
- if (!(r->flags & (IORESOURCE_IO | IORESOURCE_MEM)))
- continue;
- if ((idx == PCI_ROM_RESOURCE) &&
- (!(r->flags & IORESOURCE_ROM_ENABLE)))
- continue;
- if (!r->start && r->end) {
- printk(KERN_ERR "PCI: Device %s not available "
- "because of resource collisions\n",
- pci_name(dev));
- return -EINVAL;
- }
- if (r->flags & IORESOURCE_IO)
- cmd |= PCI_COMMAND_IO;
- if (r->flags & IORESOURCE_MEM)
- cmd |= PCI_COMMAND_MEMORY;
- }
- if (cmd != old_cmd) {
- printk("PCI: Enabling device %s (%04x -> %04x)\n",
- pci_name(dev), old_cmd, cmd);
- pci_write_config_word(dev, PCI_COMMAND, cmd);
- }
- return 0;
-}
-
-unsigned int pcibios_assign_all_busses(void)
-{
- return 1;
-}
-
-int pcibios_enable_device(struct pci_dev *dev, int mask)
-{
- int err;
-
- if ((err = pcibios_enable_resources(dev, mask)) < 0)
- return err;
-
- return pcibios_plat_dev_init(dev);
-}
-
-void pcibios_fixup_bus(struct pci_bus *bus)
-{
- struct pci_dev *dev = bus->self;
-
- if (pci_has_flag(PCI_PROBE_ONLY) && dev &&
- (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) {
- pci_read_bridge_bases(bus);
- }
-}
-
-EXPORT_SYMBOL(PCIBIOS_MIN_IO);
-EXPORT_SYMBOL(PCIBIOS_MIN_MEM);
+arch_initcall(pcibios_set_cache_line_size);
void pci_resource_to_user(const struct pci_dev *dev, int bar,
const struct resource *rsrc, resource_size_t *start,
@@ -359,12 +81,3 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
vma->vm_end - vma->vm_start, vma->vm_page_prot);
}
-
-char * (*pcibios_plat_setup)(char *str) __initdata;
-
-char *__init pcibios_setup(char *str)
-{
- if (pcibios_plat_setup)
- return pcibios_plat_setup(str);
- return str;
-}
diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c
index 99f3db4..9f672ce 100644
--- a/arch/mips/pci/pcie-octeon.c
+++ b/arch/mips/pci/pcie-octeon.c
@@ -11,7 +11,7 @@
#include <linux/interrupt.h>
#include <linux/time.h>
#include <linux/delay.h>
-#include <linux/module.h>
+#include <linux/moduleparam.h>
#include <asm/octeon/octeon.h>
#include <asm/octeon/cvmx-npei-defs.h>
diff --git a/arch/mips/pnx833x/common/platform.c b/arch/mips/pnx833x/common/platform.c
index 3cd3577..7cf4eb5 100644
--- a/arch/mips/pnx833x/common/platform.c
+++ b/arch/mips/pnx833x/common/platform.c
@@ -232,12 +232,8 @@ static struct platform_device *pnx833x_platform_devices[] __initdata = {
static int __init pnx833x_platform_init(void)
{
- int res;
-
- res = platform_add_devices(pnx833x_platform_devices,
- ARRAY_SIZE(pnx833x_platform_devices));
-
- return res;
+ return platform_add_devices(pnx833x_platform_devices,
+ ARRAY_SIZE(pnx833x_platform_devices));
}
arch_initcall(pnx833x_platform_init);
diff --git a/arch/mips/ralink/timer.c b/arch/mips/ralink/timer.c
index b0343ff..8077ff3 100644
--- a/arch/mips/ralink/timer.c
+++ b/arch/mips/ralink/timer.c
@@ -1,4 +1,7 @@
/*
+ * Ralink RT2880 timer
+ * Author: John Crispin
+ *
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
* by the Free Software Foundation.
@@ -6,7 +9,6 @@
* Copyright (C) 2013 John Crispin <john@phrozen.org>
*/
-#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/interrupt.h>
#include <linux/timer.h>
@@ -152,33 +154,17 @@ static int rt_timer_probe(struct platform_device *pdev)
return 0;
}
-static int rt_timer_remove(struct platform_device *pdev)
-{
- struct rt_timer *rt = platform_get_drvdata(pdev);
-
- rt_timer_disable(rt);
- rt_timer_free(rt);
-
- return 0;
-}
-
static const struct of_device_id rt_timer_match[] = {
{ .compatible = "ralink,rt2880-timer" },
{},
};
-MODULE_DEVICE_TABLE(of, rt_timer_match);
static struct platform_driver rt_timer_driver = {
.probe = rt_timer_probe,
- .remove = rt_timer_remove,
.driver = {
- .name = "rt-timer",
- .of_match_table = rt_timer_match
+ .name = "rt-timer",
+ .of_match_table = rt_timer_match,
+ .suppress_bind_attrs = true,
},
};
-
-module_platform_driver(rt_timer_driver);
-
-MODULE_DESCRIPTION("Ralink RT2880 timer");
-MODULE_AUTHOR("John Crispin <john@phrozen.org");
-MODULE_LICENSE("GPL");
+builtin_platform_driver(rt_timer_driver);
diff --git a/arch/mips/txx9/Kconfig b/arch/mips/txx9/Kconfig
index 8c337d6..4292347 100644
--- a/arch/mips/txx9/Kconfig
+++ b/arch/mips/txx9/Kconfig
@@ -20,7 +20,7 @@
select SYS_SUPPORTS_32BIT_KERNEL
select SYS_SUPPORTS_LITTLE_ENDIAN
select SYS_SUPPORTS_BIG_ENDIAN
- select HAVE_CLK
+ select COMMON_CLK
config TOSHIBA_JMR3927
bool "Toshiba JMR-TX3927 board"
diff --git a/arch/mips/txx9/generic/pci.c b/arch/mips/txx9/generic/pci.c
index 1f6bc9a..285d84e 100644
--- a/arch/mips/txx9/generic/pci.c
+++ b/arch/mips/txx9/generic/pci.c
@@ -29,12 +29,8 @@ static int __init
early_read_config_word(struct pci_controller *hose,
int top_bus, int bus, int devfn, int offset, u16 *value)
{
- struct pci_dev fake_dev;
struct pci_bus fake_bus;
- fake_dev.bus = &fake_bus;
- fake_dev.sysdata = hose;
- fake_dev.devfn = devfn;
fake_bus.number = bus;
fake_bus.sysdata = hose;
fake_bus.ops = hose->pci_ops;
@@ -45,7 +41,7 @@ early_read_config_word(struct pci_controller *hose,
else
fake_bus.parent = NULL;
- return pci_read_config_word(&fake_dev, offset, value);
+ return pci_bus_read_config_word(&fake_bus, devfn, offset, value);
}
int __init txx9_pci66_check(struct pci_controller *hose, int top_bus,
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index ada92db..a1d98b5 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -15,7 +15,8 @@
#include <linux/interrupt.h>
#include <linux/string.h>
#include <linux/module.h>
-#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
#include <linux/err.h>
#include <linux/gpio/driver.h>
#include <linux/platform_device.h>
@@ -83,40 +84,6 @@ int txx9_ccfg_toeon __initdata;
int txx9_ccfg_toeon __initdata = 1;
#endif
-/* Minimum CLK support */
-
-struct clk *clk_get(struct device *dev, const char *id)
-{
- if (!strcmp(id, "spi-baseclk"))
- return (struct clk *)((unsigned long)txx9_gbus_clock / 2 / 2);
- if (!strcmp(id, "imbus_clk"))
- return (struct clk *)((unsigned long)txx9_gbus_clock / 2);
- return ERR_PTR(-ENOENT);
-}
-EXPORT_SYMBOL(clk_get);
-
-int clk_enable(struct clk *clk)
-{
- return 0;
-}
-EXPORT_SYMBOL(clk_enable);
-
-void clk_disable(struct clk *clk)
-{
-}
-EXPORT_SYMBOL(clk_disable);
-
-unsigned long clk_get_rate(struct clk *clk)
-{
- return (unsigned long)clk;
-}
-EXPORT_SYMBOL(clk_get_rate);
-
-void clk_put(struct clk *clk)
-{
-}
-EXPORT_SYMBOL(clk_put);
-
#define BOARD_VEC(board) extern struct txx9_board_vec board;
#include <asm/txx9/boards.h>
#undef BOARD_VEC
@@ -560,8 +527,41 @@ void __init plat_time_init(void)
txx9_board_vec->time_init();
}
+static void txx9_clk_init(void)
+{
+ struct clk_hw *hw;
+ int error;
+
+ hw = clk_hw_register_fixed_rate(NULL, "gbus", NULL, 0, txx9_gbus_clock);
+ if (IS_ERR(hw)) {
+ error = PTR_ERR(hw);
+ goto fail;
+ }
+
+ hw = clk_hw_register_fixed_factor(NULL, "imbus", "gbus", 0, 1, 2);
+ error = clk_hw_register_clkdev(hw, "imbus_clk", NULL);
+ if (error)
+ goto fail;
+
+#ifdef CONFIG_CPU_TX49XX
+ if (TX4938_REV_PCODE() == 0x4938) {
+ hw = clk_hw_register_fixed_factor(NULL, "spi", "gbus", 0, 1, 4);
+ error = clk_hw_register_clkdev(hw, "spi-baseclk", NULL);
+ if (error)
+ goto fail;
+ }
+#endif
+
+ return;
+
+fail:
+ pr_err("Failed to register clocks: %d\n", error);
+}
+
static int __init _txx9_arch_init(void)
{
+ txx9_clk_init();
+
if (txx9_board_vec->arch_init)
txx9_board_vec->arch_init();
return 0;
diff --git a/arch/mips/txx9/generic/setup_tx3927.c b/arch/mips/txx9/generic/setup_tx3927.c
index 110e05c..d3b83a9 100644
--- a/arch/mips/txx9/generic/setup_tx3927.c
+++ b/arch/mips/txx9/generic/setup_tx3927.c
@@ -92,7 +92,6 @@ void __init tx3927_setup(void)
/* PIO */
__raw_writel(0, &tx3927_pioptr->maskcpu);
__raw_writel(0, &tx3927_pioptr->maskext);
- txx9_gpio_init(TX3927_PIO_REG, 0, 16);
conf = read_c0_conf();
if (conf & TX39_CONF_DCE) {
diff --git a/arch/mips/txx9/generic/setup_tx4927.c b/arch/mips/txx9/generic/setup_tx4927.c
index a4664cb..8d80115 100644
--- a/arch/mips/txx9/generic/setup_tx4927.c
+++ b/arch/mips/txx9/generic/setup_tx4927.c
@@ -215,7 +215,6 @@ void __init tx4927_setup(void)
txx9_tmr_init(TX4927_TMR_REG(i) & 0xfffffffffULL);
/* PIO */
- txx9_gpio_init(TX4927_PIO_REG & 0xfffffffffULL, 0, TX4927_NUM_PIO);
__raw_writel(0, &tx4927_pioptr->maskcpu);
__raw_writel(0, &tx4927_pioptr->maskext);
diff --git a/arch/mips/txx9/generic/setup_tx4938.c b/arch/mips/txx9/generic/setup_tx4938.c
index 58cdb2a..ba265bf 100644
--- a/arch/mips/txx9/generic/setup_tx4938.c
+++ b/arch/mips/txx9/generic/setup_tx4938.c
@@ -241,7 +241,6 @@ void __init tx4938_setup(void)
txx9_tmr_init(TX4938_TMR_REG(i) & 0xfffffffffULL);
/* PIO */
- txx9_gpio_init(TX4938_PIO_REG & 0xfffffffffULL, 0, TX4938_NUM_PIO);
__raw_writel(0, &tx4938_pioptr->maskcpu);
__raw_writel(0, &tx4938_pioptr->maskext);
diff --git a/arch/mips/txx9/jmr3927/setup.c b/arch/mips/txx9/jmr3927/setup.c
index 3206f76..a455166 100644
--- a/arch/mips/txx9/jmr3927/setup.c
+++ b/arch/mips/txx9/jmr3927/setup.c
@@ -142,8 +142,6 @@ static void __init jmr3927_board_init(void)
/* PIO[15:12] connected to LEDs */
__raw_writel(0x0000f000, &tx3927_pioptr->dir);
- gpio_request(11, "dipsw1");
- gpio_request(10, "dipsw2");
jmr3927_pci_setup();
@@ -204,6 +202,14 @@ static void __init jmr3927_device_init(void)
txx9_iocled_init(iocled_base, -1, 8, 1, "green", NULL);
}
+static void __init jmr3927_arch_init(void)
+{
+ txx9_gpio_init(TX3927_PIO_REG, 0, 16);
+
+ gpio_request(11, "dipsw1");
+ gpio_request(10, "dipsw2");
+}
+
struct txx9_board_vec jmr3927_vec __initdata = {
.system = "Toshiba JMR_TX3927",
.prom_init = jmr3927_prom_init,
@@ -211,6 +217,7 @@ struct txx9_board_vec jmr3927_vec __initdata = {
.irq_setup = jmr3927_irq_setup,
.time_init = jmr3927_time_init,
.device_init = jmr3927_device_init,
+ .arch_init = jmr3927_arch_init,
#ifdef CONFIG_PCI
.pci_map_irq = jmr3927_pci_map_irq,
#endif
diff --git a/arch/mips/txx9/rbtx4927/setup.c b/arch/mips/txx9/rbtx4927/setup.c
index 3c516ef..f5b367e 100644
--- a/arch/mips/txx9/rbtx4927/setup.c
+++ b/arch/mips/txx9/rbtx4927/setup.c
@@ -52,6 +52,7 @@
#include <linux/leds.h>
#include <asm/io.h>
#include <asm/reboot.h>
+#include <asm/txx9pio.h>
#include <asm/txx9/generic.h>
#include <asm/txx9/pci.h>
#include <asm/txx9/rbtx4927.h>
@@ -151,20 +152,37 @@ static void __init tx4937_pci_setup(void)
}
tx4938_setup_pcierr_irq();
}
+#else
+static inline void tx4927_pci_setup(void) {}
+static inline void tx4937_pci_setup(void) {}
+#endif /* CONFIG_PCI */
+
+static void __init rbtx4927_gpio_init(void)
+{
+ /* TX4927-SIO DTR on (PIO[15]) */
+ gpio_request(15, "sio-dtr");
+ gpio_direction_output(15, 1);
+
+ tx4927_sio_init(0, 0);
+}
static void __init rbtx4927_arch_init(void)
{
+ txx9_gpio_init(TX4927_PIO_REG & 0xfffffffffULL, 0, TX4927_NUM_PIO);
+
+ rbtx4927_gpio_init();
+
tx4927_pci_setup();
}
static void __init rbtx4937_arch_init(void)
{
+ txx9_gpio_init(TX4938_PIO_REG & 0xfffffffffULL, 0, TX4938_NUM_PIO);
+
+ rbtx4927_gpio_init();
+
tx4937_pci_setup();
}
-#else
-#define rbtx4927_arch_init NULL
-#define rbtx4937_arch_init NULL
-#endif /* CONFIG_PCI */
static void toshiba_rbtx4927_restart(char *command)
{
@@ -205,12 +223,6 @@ static void __init rbtx4927_mem_setup(void)
#else
set_io_port_base(KSEG1 + RBTX4927_ISA_IO_OFFSET);
#endif
-
- /* TX4927-SIO DTR on (PIO[15]) */
- gpio_request(15, "sio-dtr");
- gpio_direction_output(15, 1);
-
- tx4927_sio_init(0, 0);
}
static void __init rbtx4927_clock_init(void)
diff --git a/arch/mips/txx9/rbtx4938/setup.c b/arch/mips/txx9/rbtx4938/setup.c
index 54de668..07939ed 100644
--- a/arch/mips/txx9/rbtx4938/setup.c
+++ b/arch/mips/txx9/rbtx4938/setup.c
@@ -336,6 +336,7 @@ static void __init rbtx4938_mtd_init(void)
static void __init rbtx4938_arch_init(void)
{
+ txx9_gpio_init(TX4938_PIO_REG & 0xfffffffffULL, 0, TX4938_NUM_PIO);
gpiochip_add_data(&rbtx4938_spi_gpio_chip, NULL);
rbtx4938_pci_setup();
rbtx4938_spi_init();
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index 3b4538e..c3dc12a 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -13,8 +13,6 @@
-DDISABLE_BRANCH_PROFILING \
$(call cc-option, -fno-stack-protector)
aflags-vdso := $(ccflags-vdso) \
- $(filter -I%,$(KBUILD_CFLAGS)) \
- $(filter -E%,$(KBUILD_CFLAGS)) \
-D__ASSEMBLY__ -Wa,-gdwarf-2
#
@@ -82,7 +80,7 @@
$(obj-vdso): KBUILD_CFLAGS := $(cflags-vdso) $(native-abi)
$(obj-vdso): KBUILD_AFLAGS := $(aflags-vdso) $(native-abi)
-$(obj)/vdso.lds: KBUILD_CPPFLAGS := $(native-abi)
+$(obj)/vdso.lds: KBUILD_CPPFLAGS := $(ccflags-vdso) $(native-abi)
$(obj)/vdso.so.dbg.raw: $(obj)/vdso.lds $(obj-vdso) FORCE
$(call if_changed,vdsold)
diff --git a/arch/nios2/kernel/time.c b/arch/nios2/kernel/time.c
index d9563dd..746bf5c 100644
--- a/arch/nios2/kernel/time.c
+++ b/arch/nios2/kernel/time.c
@@ -324,6 +324,7 @@ static int __init nios2_time_init(struct device_node *timer)
ret = nios2_clocksource_init(timer);
break;
default:
+ ret = 0;
break;
}
diff --git a/arch/openrisc/include/asm/cache.h b/arch/openrisc/include/asm/cache.h
index 4ce7a01..5f55da9 100644
--- a/arch/openrisc/include/asm/cache.h
+++ b/arch/openrisc/include/asm/cache.h
@@ -23,6 +23,8 @@
* they shouldn't be hard-coded!
*/
+#define __ro_after_init __read_mostly
+
#define L1_CACHE_BYTES 16
#define L1_CACHE_SHIFT 4
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index a9b9407..6b0741e 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -368,7 +368,9 @@
#define __IGNORE_select /* newselect */
#define __IGNORE_fadvise64 /* fadvise64_64 */
-
+#define __IGNORE_pkey_mprotect
+#define __IGNORE_pkey_alloc
+#define __IGNORE_pkey_free
#define LINUX_GATEWAY_ADDR 0x100
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index f815066..700e2d2 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -873,11 +873,11 @@ static void print_parisc_device(struct parisc_device *dev)
if (dev->num_addrs) {
int k;
- printk(", additional addresses: ");
+ pr_cont(", additional addresses: ");
for (k = 0; k < dev->num_addrs; k++)
- printk("0x%lx ", dev->addr[k]);
+ pr_cont("0x%lx ", dev->addr[k]);
}
- printk("\n");
+ pr_cont("\n");
}
/**
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index d03422e..23de307 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -100,14 +100,12 @@
.endr
/* This address must remain fixed at 0x100 for glibc's syscalls to work */
- .align 256
+ .align LINUX_GATEWAY_ADDR
linux_gateway_entry:
gate .+8, %r0 /* become privileged */
mtsp %r0,%sr4 /* get kernel space into sr4 */
mtsp %r0,%sr5 /* get kernel space into sr5 */
mtsp %r0,%sr6 /* get kernel space into sr6 */
- mfsp %sr7,%r1 /* save user sr7 */
- mtsp %r1,%sr3 /* and store it in sr3 */
#ifdef CONFIG_64BIT
/* for now we can *always* set the W bit on entry to the syscall
@@ -133,6 +131,14 @@
depdi 0, 31, 32, %r21
1:
#endif
+
+ /* We use a rsm/ssm pair to prevent sr3 from being clobbered
+ * by external interrupts.
+ */
+ mfsp %sr7,%r1 /* save user sr7 */
+ rsm PSW_SM_I, %r0 /* disable interrupts */
+ mtsp %r1,%sr3 /* and store it in sr3 */
+
mfctl %cr30,%r1
xor %r1,%r30,%r30 /* ye olde xor trick */
xor %r1,%r30,%r1
@@ -147,6 +153,7 @@
*/
mtsp %r0,%sr7 /* get kernel space into sr7 */
+ ssm PSW_SM_I, %r0 /* enable interrupts */
STREGM %r1,FRAME_SIZE(%r30) /* save r1 (usp) here for now */
mfctl %cr30,%r1 /* get task ptr in %r1 */
LDREG TI_TASK(%r1),%r1
@@ -474,11 +481,6 @@
comiclr,>> __NR_lws_entries, %r20, %r0
b,n lws_exit_nosys
- /* WARNING: Trashing sr2 and sr3 */
- mfsp %sr7,%r1 /* get userspace into sr3 */
- mtsp %r1,%sr3
- mtsp %r0,%sr2 /* get kernel space into sr2 */
-
/* Load table start */
ldil L%lws_table, %r1
ldo R%lws_table(%r1), %r28 /* Scratch use of r28 */
@@ -627,9 +629,9 @@
stw %r1, 4(%sr2,%r20)
#endif
/* The load and store could fail */
-1: ldw,ma 0(%sr3,%r26), %r28
+1: ldw,ma 0(%r26), %r28
sub,<> %r28, %r25, %r0
-2: stw,ma %r24, 0(%sr3,%r26)
+2: stw,ma %r24, 0(%r26)
/* Free lock */
stw,ma %r20, 0(%sr2,%r20)
#if ENABLE_LWS_DEBUG
@@ -706,9 +708,9 @@
nop
/* 8bit load */
-4: ldb 0(%sr3,%r25), %r25
+4: ldb 0(%r25), %r25
b cas2_lock_start
-5: ldb 0(%sr3,%r24), %r24
+5: ldb 0(%r24), %r24
nop
nop
nop
@@ -716,9 +718,9 @@
nop
/* 16bit load */
-6: ldh 0(%sr3,%r25), %r25
+6: ldh 0(%r25), %r25
b cas2_lock_start
-7: ldh 0(%sr3,%r24), %r24
+7: ldh 0(%r24), %r24
nop
nop
nop
@@ -726,9 +728,9 @@
nop
/* 32bit load */
-8: ldw 0(%sr3,%r25), %r25
+8: ldw 0(%r25), %r25
b cas2_lock_start
-9: ldw 0(%sr3,%r24), %r24
+9: ldw 0(%r24), %r24
nop
nop
nop
@@ -737,14 +739,14 @@
/* 64bit load */
#ifdef CONFIG_64BIT
-10: ldd 0(%sr3,%r25), %r25
-11: ldd 0(%sr3,%r24), %r24
+10: ldd 0(%r25), %r25
+11: ldd 0(%r24), %r24
#else
/* Load new value into r22/r23 - high/low */
-10: ldw 0(%sr3,%r25), %r22
-11: ldw 4(%sr3,%r25), %r23
+10: ldw 0(%r25), %r22
+11: ldw 4(%r25), %r23
/* Load new value into fr4 for atomic store later */
-12: flddx 0(%sr3,%r24), %fr4
+12: flddx 0(%r24), %fr4
#endif
cas2_lock_start:
@@ -794,30 +796,30 @@
ldo 1(%r0),%r28
/* 8bit CAS */
-13: ldb,ma 0(%sr3,%r26), %r29
+13: ldb,ma 0(%r26), %r29
sub,= %r29, %r25, %r0
b,n cas2_end
-14: stb,ma %r24, 0(%sr3,%r26)
+14: stb,ma %r24, 0(%r26)
b cas2_end
copy %r0, %r28
nop
nop
/* 16bit CAS */
-15: ldh,ma 0(%sr3,%r26), %r29
+15: ldh,ma 0(%r26), %r29
sub,= %r29, %r25, %r0
b,n cas2_end
-16: sth,ma %r24, 0(%sr3,%r26)
+16: sth,ma %r24, 0(%r26)
b cas2_end
copy %r0, %r28
nop
nop
/* 32bit CAS */
-17: ldw,ma 0(%sr3,%r26), %r29
+17: ldw,ma 0(%r26), %r29
sub,= %r29, %r25, %r0
b,n cas2_end
-18: stw,ma %r24, 0(%sr3,%r26)
+18: stw,ma %r24, 0(%r26)
b cas2_end
copy %r0, %r28
nop
@@ -825,22 +827,22 @@
/* 64bit CAS */
#ifdef CONFIG_64BIT
-19: ldd,ma 0(%sr3,%r26), %r29
+19: ldd,ma 0(%r26), %r29
sub,*= %r29, %r25, %r0
b,n cas2_end
-20: std,ma %r24, 0(%sr3,%r26)
+20: std,ma %r24, 0(%r26)
copy %r0, %r28
#else
/* Compare first word */
-19: ldw,ma 0(%sr3,%r26), %r29
+19: ldw,ma 0(%r26), %r29
sub,= %r29, %r22, %r0
b,n cas2_end
/* Compare second word */
-20: ldw,ma 4(%sr3,%r26), %r29
+20: ldw,ma 4(%r26), %r29
sub,= %r29, %r23, %r0
b,n cas2_end
/* Perform the store */
-21: fstdx %fr4, 0(%sr3,%r26)
+21: fstdx %fr4, 0(%r26)
copy %r0, %r28
#endif
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 50d020a..617dece 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -318,12 +318,12 @@
PHONY += corenet32_smp_defconfig
corenet32_smp_defconfig:
$(call merge_into_defconfig,corenet_basic_defconfig,\
- 85xx-32bit 85xx-smp 85xx-hw fsl-emb-nonhw)
+ 85xx-32bit 85xx-smp 85xx-hw fsl-emb-nonhw dpaa)
PHONY += corenet64_smp_defconfig
corenet64_smp_defconfig:
$(call merge_into_defconfig,corenet_basic_defconfig,\
- 85xx-64bit 85xx-smp altivec 85xx-hw fsl-emb-nonhw)
+ 85xx-64bit 85xx-smp altivec 85xx-hw fsl-emb-nonhw dpaa)
PHONY += mpc86xx_defconfig
mpc86xx_defconfig:
diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c
index f7a184b..57d42d1 100644
--- a/arch/powerpc/boot/main.c
+++ b/arch/powerpc/boot/main.c
@@ -32,9 +32,16 @@ static struct addr_range prep_kernel(void)
void *addr = 0;
struct elf_info ei;
long len;
+ int uncompressed_image = 0;
- partial_decompress(vmlinuz_addr, vmlinuz_size,
+ len = partial_decompress(vmlinuz_addr, vmlinuz_size,
elfheader, sizeof(elfheader), 0);
+ /* assume uncompressed data if -1 is returned */
+ if (len == -1) {
+ uncompressed_image = 1;
+ memcpy(elfheader, vmlinuz_addr, sizeof(elfheader));
+ printf("No valid compressed data found, assume uncompressed data\n\r");
+ }
if (!parse_elf64(elfheader, &ei) && !parse_elf32(elfheader, &ei))
fatal("Error: not a valid PPC32 or PPC64 ELF file!\n\r");
@@ -67,6 +74,13 @@ static struct addr_range prep_kernel(void)
"device tree\n\r");
}
+ if (uncompressed_image) {
+ memcpy(addr, vmlinuz_addr + ei.elfoffset, ei.loadsize);
+ printf("0x%lx bytes of uncompressed data copied\n\r",
+ ei.loadsize);
+ goto out;
+ }
+
/* Finally, decompress the kernel */
printf("Decompressing (0x%p <- 0x%p:0x%p)...\n\r", addr,
vmlinuz_addr, vmlinuz_addr+vmlinuz_size);
@@ -82,7 +96,7 @@ static struct addr_range prep_kernel(void)
len, ei.loadsize);
printf("Done! Decompressed 0x%lx bytes\n\r", len);
-
+out:
flush_cache(addr, ei.loadsize);
return (struct addr_range){addr, ei.memsize};
diff --git a/arch/powerpc/configs/dpaa.config b/arch/powerpc/configs/dpaa.config
new file mode 100644
index 0000000..2fe76f5
--- /dev/null
+++ b/arch/powerpc/configs/dpaa.config
@@ -0,0 +1,4 @@
+CONFIG_FSL_DPAA=y
+CONFIG_FSL_PAMU=y
+CONFIG_FSL_FMAN=y
+CONFIG_FSL_DPAA_ETH=y
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index ab9f4e0..5c4fbc8 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -1,5 +1,6 @@
generic-y += clkdev.h
generic-y += div64.h
+generic-y += export.h
generic-y += irq_regs.h
generic-y += irq_work.h
generic-y += local64.h
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index ee655ed..1e8fceb 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -53,10 +53,8 @@ static inline __sum16 csum_fold(__wsum sum)
return (__force __sum16)(~((__force u32)sum + tmp) >> 16);
}
-static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
- unsigned short len,
- unsigned short proto,
- __wsum sum)
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+ __u8 proto, __wsum sum)
{
#ifdef __powerpc64__
unsigned long s = (__force u32)sum;
@@ -83,10 +81,8 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
* computes the checksum of the TCP/UDP pseudo-header
* returns a 16-bit checksum, already complemented
*/
-static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
- unsigned short len,
- unsigned short proto,
- __wsum sum)
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
+ __u8 proto, __wsum sum)
{
return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
}
diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
index 01b8a13..3919332 100644
--- a/arch/powerpc/include/asm/cpuidle.h
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -26,7 +26,7 @@ extern u64 pnv_first_deep_stop_state;
std r0,0(r1); \
ptesync; \
ld r0,0(r1); \
-1: cmp cr0,r0,r0; \
+1: cmpd cr0,r0,r0; \
bne 1b; \
IDLE_INST; \
b .
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index f752e6f..ab68d0e 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -43,6 +43,7 @@ extern int machine_check_e500mc(struct pt_regs *regs);
extern int machine_check_e500(struct pt_regs *regs);
extern int machine_check_e200(struct pt_regs *regs);
extern int machine_check_47x(struct pt_regs *regs);
+int machine_check_8xx(struct pt_regs *regs);
extern void cpu_down_flush_e500v2(void);
extern void cpu_down_flush_e500mc(void);
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 2e4e7d8..84d49b1 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -93,6 +93,10 @@
ld reg,PACAKBASE(r13); /* get high part of &label */ \
ori reg,reg,(FIXED_SYMBOL_ABS_ADDR(label))@l;
+#define __LOAD_HANDLER(reg, label) \
+ ld reg,PACAKBASE(r13); \
+ ori reg,reg,(ABS_ADDR(label))@l;
+
/* Exception register prefixes */
#define EXC_HV H
#define EXC_STD
@@ -208,6 +212,18 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
#define kvmppc_interrupt kvmppc_interrupt_pr
#endif
+#ifdef CONFIG_RELOCATABLE
+#define BRANCH_TO_COMMON(reg, label) \
+ __LOAD_HANDLER(reg, label); \
+ mtctr reg; \
+ bctr
+
+#else
+#define BRANCH_TO_COMMON(reg, label) \
+ b label
+
+#endif
+
#define __KVM_HANDLER_PROLOG(area, n) \
BEGIN_FTR_SECTION_NESTED(947) \
ld r10,area+EX_CFAR(r13); \
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index c7d82ff..eba6041 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -155,6 +155,8 @@ static inline unsigned long arch_local_irq_save(void)
unsigned long flags = arch_local_save_flags();
#ifdef CONFIG_BOOKE
asm volatile("wrteei 0" : : : "memory");
+#elif defined(CONFIG_PPC_8xx)
+ wrtspr(SPRN_EID);
#else
SET_MSR_EE(flags & ~MSR_EE);
#endif
@@ -165,6 +167,8 @@ static inline void arch_local_irq_disable(void)
{
#ifdef CONFIG_BOOKE
asm volatile("wrteei 0" : : : "memory");
+#elif defined(CONFIG_PPC_8xx)
+ wrtspr(SPRN_EID);
#else
arch_local_irq_save();
#endif
@@ -174,6 +178,8 @@ static inline void arch_local_irq_enable(void)
{
#ifdef CONFIG_BOOKE
asm volatile("wrteei 1" : : : "memory");
+#elif defined(CONFIG_PPC_8xx)
+ wrtspr(SPRN_EIE);
#else
unsigned long msr = mfmsr();
SET_MSR_EE(msr | MSR_EE);
diff --git a/arch/powerpc/include/asm/libata-portmap.h b/arch/powerpc/include/asm/libata-portmap.h
index 4d85180..4396db5 100644
--- a/arch/powerpc/include/asm/libata-portmap.h
+++ b/arch/powerpc/include/asm/libata-portmap.h
@@ -1,12 +1,8 @@
#ifndef __ASM_POWERPC_LIBATA_PORTMAP_H
#define __ASM_POWERPC_LIBATA_PORTMAP_H
-#define ATA_PRIMARY_CMD 0x1F0
-#define ATA_PRIMARY_CTL 0x3F6
#define ATA_PRIMARY_IRQ(dev) pci_get_legacy_ide_irq(dev, 0)
-#define ATA_SECONDARY_CMD 0x170
-#define ATA_SECONDARY_CTL 0x376
#define ATA_SECONDARY_IRQ(dev) pci_get_legacy_ide_irq(dev, 1)
#endif
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 54ff8ce..0132831 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -152,6 +152,7 @@
#define PPC_INST_LWSYNC 0x7c2004ac
#define PPC_INST_SYNC 0x7c0004ac
#define PPC_INST_SYNC_MASK 0xfc0007fe
+#define PPC_INST_ISYNC 0x4c00012c
#define PPC_INST_LXVD2X 0x7c000698
#define PPC_INST_MCRXR 0x7c000400
#define PPC_INST_MCRXR_MASK 0xfc0007fe
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 2a62078..9cd4e8c 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1250,6 +1250,8 @@ static inline void mtmsr_isync(unsigned long val)
: "r" ((unsigned long)(v)) \
: "memory")
#endif
+#define wrtspr(rn) asm volatile("mtspr " __stringify(rn) ",0" : \
+ : : "memory")
extern unsigned long msr_check_and_set(unsigned long bits);
extern bool strict_msr_control;
diff --git a/arch/powerpc/include/asm/reg_8xx.h b/arch/powerpc/include/asm/reg_8xx.h
index 94d01f8..0197e12 100644
--- a/arch/powerpc/include/asm/reg_8xx.h
+++ b/arch/powerpc/include/asm/reg_8xx.h
@@ -25,6 +25,10 @@
#define SPRN_MD_RAM0 825
#define SPRN_MD_RAM1 826
+/* Special MSR manipulation registers */
+#define SPRN_EIE 80 /* External interrupt enable (EE=1, RI=1) */
+#define SPRN_EID 81 /* External interrupt disable (EE=0, RI=1) */
+
/* Commands. Only the first few are available to the instruction cache.
*/
#define IDC_ENABLE 0x02000000 /* Cache enable */
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index f6f68f7..99e1397 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -52,11 +52,23 @@ static inline int mm_is_core_local(struct mm_struct *mm)
return cpumask_subset(mm_cpumask(mm),
topology_sibling_cpumask(smp_processor_id()));
}
+
+static inline int mm_is_thread_local(struct mm_struct *mm)
+{
+ return cpumask_equal(mm_cpumask(mm),
+ cpumask_of(smp_processor_id()));
+}
+
#else
static inline int mm_is_core_local(struct mm_struct *mm)
{
return 1;
}
+
+static inline int mm_is_thread_local(struct mm_struct *mm)
+{
+ return 1;
+}
#endif
#endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index cf12c58..e8cdfec 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -16,6 +16,10 @@
#define __NR__exit __NR_exit
+#define __IGNORE_pkey_mprotect
+#define __IGNORE_pkey_alloc
+#define __IGNORE_pkey_free
+
#ifndef __ASSEMBLY__
#include <linux/types.h>
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index aded29a..1925341 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -14,6 +14,11 @@
CFLAGS_btext.o += -fPIC
endif
+CFLAGS_cputable.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+CFLAGS_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
+
ifdef CONFIG_FUNCTION_TRACER
# Do not trace early boot code
CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
@@ -90,10 +95,6 @@
obj-$(CONFIG_PPC32) += entry_32.o setup_32.o
obj-$(CONFIG_PPC64) += dma-iommu.o iommu.o
obj-$(CONFIG_KGDB) += kgdb.o
-obj-$(CONFIG_MODULES) += ppc_ksyms.o
-ifeq ($(CONFIG_PPC32),y)
-obj-$(CONFIG_MODULES) += ppc_ksyms_32.o
-endif
obj-$(CONFIG_BOOTX_TEXT) += btext.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_KPROBES) += kprobes.o
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 6c4646a..6a82ef0 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -1248,6 +1248,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.mmu_features = MMU_FTR_TYPE_8xx,
.icache_bsize = 16,
.dcache_bsize = 16,
+ .machine_check = machine_check_8xx,
.platform = "ppc823",
},
#endif /* CONFIG_8xx */
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 83428a2..3841d74 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -33,6 +33,7 @@
#include <asm/unistd.h>
#include <asm/ftrace.h>
#include <asm/ptrace.h>
+#include <asm/export.h>
/*
* MSR_KERNEL is > 0x10000 on 4xx/Book-E since it include MSR_CE.
@@ -1358,6 +1359,7 @@
MCOUNT_RESTORE_FRAME
bctr
#endif
+EXPORT_SYMBOL(_mcount)
_GLOBAL(ftrace_stub)
blr
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 51df82b..6432d4b 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -38,6 +38,7 @@
#include <asm/context_tracking.h>
#include <asm/tm.h>
#include <asm/ppc-opcode.h>
+#include <asm/export.h>
/*
* System calls.
@@ -1177,6 +1178,7 @@
#ifdef CONFIG_DYNAMIC_FTRACE
_GLOBAL(mcount)
_GLOBAL(_mcount)
+EXPORT_SYMBOL(_mcount)
mflr r12
mtctr r12
mtlr r0
@@ -1413,6 +1415,7 @@
#else
_GLOBAL_TOC(_mcount)
+EXPORT_SYMBOL(_mcount)
/* Taken from output of objdump from lib64/glibc */
mflr r3
ld r11, 0(r1)
diff --git a/arch/powerpc/kernel/epapr_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S
index 9f1ebf7..52ca247 100644
--- a/arch/powerpc/kernel/epapr_hcalls.S
+++ b/arch/powerpc/kernel/epapr_hcalls.S
@@ -16,6 +16,7 @@
#include <asm/ppc_asm.h>
#include <asm/asm-compat.h>
#include <asm/asm-offsets.h>
+#include <asm/export.h>
#ifndef CONFIG_PPC64
/* epapr_ev_idle() was derived from e500_idle() */
@@ -53,3 +54,4 @@
nop
nop
blr
+EXPORT_SYMBOL(epapr_hypercall_start)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 08992f8..08ba447 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -95,19 +95,35 @@
/* No virt vectors corresponding with 0x0..0x100 */
EXC_VIRT_NONE(0x4000, 0x4100)
+
+#ifdef CONFIG_PPC_P7_NAP
+ /*
+ * If running native on arch 2.06 or later, check if we are waking up
+ * from nap/sleep/winkle, and branch to idle handler.
+ */
+#define IDLETEST(n) \
+ BEGIN_FTR_SECTION ; \
+ mfspr r10,SPRN_SRR1 ; \
+ rlwinm. r10,r10,47-31,30,31 ; \
+ beq- 1f ; \
+ cmpwi cr3,r10,2 ; \
+ BRANCH_TO_COMMON(r10, system_reset_idle_common) ; \
+1: \
+ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+#else
+#define IDLETEST NOTEST
+#endif
+
EXC_REAL_BEGIN(system_reset, 0x100, 0x200)
SET_SCRATCH0(r13)
-#ifdef CONFIG_PPC_P7_NAP
-BEGIN_FTR_SECTION
- /* Running native on arch 2.06 or later, check if we are
- * waking up from nap/sleep/winkle.
- */
- mfspr r13,SPRN_SRR1
- rlwinm. r13,r13,47-31,30,31
- beq 9f
+ EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
+ IDLETEST, 0x100)
- cmpwi cr3,r13,2
- GET_PACA(r13)
+EXC_REAL_END(system_reset, 0x100, 0x200)
+EXC_VIRT_NONE(0x4100, 0x4200)
+
+#ifdef CONFIG_PPC_P7_NAP
+EXC_COMMON_BEGIN(system_reset_idle_common)
bl pnv_restore_hyp_resource
li r0,PNV_THREAD_RUNNING
@@ -130,14 +146,8 @@
blt cr3,2f
b pnv_wakeup_loss
2: b pnv_wakeup_noloss
+#endif
-9:
-END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-#endif /* CONFIG_PPC_P7_NAP */
- EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
- NOTEST, 0x100)
-EXC_REAL_END(system_reset, 0x100, 0x200)
-EXC_VIRT_NONE(0x4100, 0x4200)
EXC_COMMON(system_reset_common, 0x100, system_reset_exception)
#ifdef CONFIG_PPC_PSERIES
@@ -817,10 +827,8 @@
TRAMP_KVM(PACA_EXGEN, 0xb00)
EXC_COMMON(trap_0b_common, 0xb00, unknown_exception)
-
-#define LOAD_SYSCALL_HANDLER(reg) \
- ld reg,PACAKBASE(r13); \
- ori reg,reg,(ABS_ADDR(system_call_common))@l;
+#define LOAD_SYSCALL_HANDLER(reg) \
+ __LOAD_HANDLER(reg, system_call_common)
/* Syscall routine is used twice, in reloc-off and reloc-on paths */
#define SYSCALL_PSERIES_1 \
@@ -1377,7 +1385,7 @@
DEFINE_FIXED_SYMBOL(__end_interrupts)
#ifdef CONFIG_PPC_970_NAP
-TRAMP_REAL_BEGIN(power4_fixup_nap)
+EXC_COMMON_BEGIN(power4_fixup_nap)
andc r9,r9,r10
std r9,TI_LOCAL_FLAGS(r11)
ld r10,_LINK(r1) /* make idle task do the */
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index 08d14b0..6c509f3 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -24,6 +24,7 @@
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#include <asm/ptrace.h>
+#include <asm/export.h>
#ifdef CONFIG_VSX
#define __REST_32FPVSRS(n,c,base) \
@@ -59,6 +60,7 @@
MTFSF_L(fr0)
REST_32FPVSRS(0, R4, R3)
blr
+EXPORT_SYMBOL(load_fp_state)
/*
* Store FP state into memory, including FPSCR
@@ -69,6 +71,7 @@
mffs fr0
stfd fr0,FPSTATE_FPSCR(r3)
blr
+EXPORT_SYMBOL(store_fp_state)
/*
* This task wants to use the FPU now.
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index a3f821e..9d96354 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -34,6 +34,7 @@
#include <asm/ptrace.h>
#include <asm/bug.h>
#include <asm/kvm_book3s_asm.h>
+#include <asm/export.h>
/* 601 only have IBAT; cr0.eq is set on 601 when using this macro */
#define LOAD_BAT(n, reg, RA, RB) \
@@ -738,6 +739,7 @@
.globl mol_trampoline
.set mol_trampoline, i0x2f00
+ EXPORT_SYMBOL(mol_trampoline)
. = 0x3000
@@ -1045,6 +1047,7 @@
4: trap
EMIT_BUG_ENTRY 4b,__FILE__,__LINE__,0
blr
+EXPORT_SYMBOL(switch_mmu_context)
/*
* An undocumented "feature" of 604e requires that the v bit
@@ -1272,6 +1275,7 @@
.globl empty_zero_page
empty_zero_page:
.space 4096
+EXPORT_SYMBOL(empty_zero_page)
.globl swapper_pg_dir
swapper_pg_dir:
@@ -1285,6 +1289,7 @@
.long 0, 0, 0, 0, 0, 0, 0, 0
.long 0, 0, 0, 0, 0, 0, 0, 0
.long 0, 0, 0, 0, 0, 0, 0, 0
+EXPORT_SYMBOL(intercept_table)
/* Room for two PTE pointers, usually the kernel and current user pointers
* to their respective root page table.
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index 7d7d863..41374a4 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -41,6 +41,7 @@
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#include <asm/ptrace.h>
+#include <asm/export.h>
/* As with the other PowerPC ports, it is expected that when code
* execution begins here, the following registers contain valid, yet
@@ -971,6 +972,7 @@
.globl empty_zero_page
empty_zero_page:
.space 4096
+EXPORT_SYMBOL(empty_zero_page)
.globl swapper_pg_dir
swapper_pg_dir:
.space PGD_TABLE_SIZE
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 9cdf5c7..37e4a7c 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -39,6 +39,7 @@
#include <asm/asm-offsets.h>
#include <asm/ptrace.h>
#include <asm/synch.h>
+#include <asm/export.h>
#include "head_booke.h"
@@ -1254,6 +1255,7 @@
.globl empty_zero_page
empty_zero_page:
.space PAGE_SIZE
+EXPORT_SYMBOL(empty_zero_page)
/*
* To support >32-bit physical addresses, we use an 8KB pgdir.
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 79da0641..04c546e 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -43,6 +43,7 @@
#include <asm/hw_irq.h>
#include <asm/cputhreads.h>
#include <asm/ppc-opcode.h>
+#include <asm/export.h>
/* The physical memory is laid out such that the secondary processor
* spin code sits at 0x0000...0x00ff. On server, the vectors follow
@@ -1002,3 +1003,4 @@
.globl empty_zero_page
empty_zero_page:
.space PAGE_SIZE
+EXPORT_SYMBOL(empty_zero_page)
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 3a185c5..fb133a1 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -31,6 +31,7 @@
#include <asm/asm-offsets.h>
#include <asm/ptrace.h>
#include <asm/fixmap.h>
+#include <asm/export.h>
/* Macro to make the code more readable. */
#ifdef CONFIG_8xx_CPU6
@@ -226,7 +227,7 @@
ret_from_except)
/* System reset */
- EXCEPTION(0x100, Reset, unknown_exception, EXC_XFER_STD)
+ EXCEPTION(0x100, Reset, system_reset_exception, EXC_XFER_STD)
/* Machine check */
. = 0x200
@@ -321,7 +322,7 @@
#endif
InstructionTLBMiss:
-#ifdef CONFIG_8xx_CPU6
+#if defined(CONFIG_8xx_CPU6) || defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC)
mtspr SPRN_SPRG_SCRATCH2, r3
#endif
EXCEPTION_PROLOG_0
@@ -329,23 +330,20 @@
/* If we are faulting a kernel address, we have to use the
* kernel page tables.
*/
+ mfspr r10, SPRN_SRR0 /* Get effective address of fault */
+ INVALIDATE_ADJACENT_PAGES_CPU15(r11, r10)
#if defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC)
/* Only modules will cause ITLB Misses as we always
* pin the first 8MB of kernel memory */
- mfspr r11, SPRN_SRR0 /* Get effective address of fault */
- INVALIDATE_ADJACENT_PAGES_CPU15(r10, r11)
- mfcr r10
- IS_KERNEL(r11, r11)
+ mfcr r3
+ IS_KERNEL(r11, r10)
+#endif
mfspr r11, SPRN_M_TW /* Get level 1 table */
+#if defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC)
BRANCH_UNLESS_KERNEL(3f)
lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha
3:
- mtcr r10
- mfspr r10, SPRN_SRR0 /* Get effective address of fault */
-#else
- mfspr r10, SPRN_SRR0 /* Get effective address of fault */
- INVALIDATE_ADJACENT_PAGES_CPU15(r11, r10)
- mfspr r11, SPRN_M_TW /* Get level 1 table base address */
+ mtcr r3
#endif
/* Insert level 1 index */
rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
@@ -377,58 +375,39 @@
MTSPR_CPU6(SPRN_MI_RPN, r10, r3) /* Update TLB entry */
/* Restore registers */
-#ifdef CONFIG_8xx_CPU6
+#if defined(CONFIG_8xx_CPU6) || defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC)
mfspr r3, SPRN_SPRG_SCRATCH2
#endif
EXCEPTION_EPILOG_0
rfi
-/*
- * Bottom part of DataStoreTLBMiss handler for IMMR area
- * not enough space in the DataStoreTLBMiss area
- */
-DTLBMissIMMR:
- mtcr r10
- /* Set 512k byte guarded page and mark it valid */
- li r10, MD_PS512K | MD_GUARDED | MD_SVALID
- MTSPR_CPU6(SPRN_MD_TWC, r10, r11)
- mfspr r10, SPRN_IMMR /* Get current IMMR */
- rlwinm r10, r10, 0, 0xfff80000 /* Get 512 kbytes boundary */
- ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY | \
- _PAGE_PRESENT | _PAGE_NO_CACHE
- MTSPR_CPU6(SPRN_MD_RPN, r10, r11) /* Update TLB entry */
-
- li r11, RPN_PATTERN
- mtspr SPRN_DAR, r11 /* Tag DAR */
- EXCEPTION_EPILOG_0
- rfi
-
. = 0x1200
DataStoreTLBMiss:
+ mtspr SPRN_SPRG_SCRATCH2, r3
EXCEPTION_PROLOG_0
- mfcr r10
+ mfcr r3
/* If we are faulting a kernel address, we have to use the
* kernel page tables.
*/
- mfspr r11, SPRN_MD_EPN
- rlwinm r11, r11, 16, 0xfff8
+ mfspr r10, SPRN_MD_EPN
+ rlwinm r10, r10, 16, 0xfff8
+ cmpli cr0, r10, PAGE_OFFSET@h
+ mfspr r11, SPRN_M_TW /* Get level 1 table */
+ blt+ 3f
#ifndef CONFIG_PIN_TLB_IMMR
- cmpli cr0, r11, VIRT_IMMR_BASE@h
+ cmpli cr0, r10, VIRT_IMMR_BASE@h
#endif
- cmpli cr7, r11, PAGE_OFFSET@h
+_ENTRY(DTLBMiss_cmp)
+ cmpli cr7, r10, (PAGE_OFFSET + 0x1800000)@h
+ lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha
#ifndef CONFIG_PIN_TLB_IMMR
_ENTRY(DTLBMiss_jmp)
beq- DTLBMissIMMR
#endif
- bge- cr7, 4f
-
- mfspr r11, SPRN_M_TW /* Get level 1 table */
+ blt cr7, DTLBMissLinear
3:
- mtcr r10
-#ifdef CONFIG_8xx_CPU6
- mtspr SPRN_SPRG_SCRATCH2, r3
-#endif
+ mtcr r3
mfspr r10, SPRN_MD_EPN
/* Insert level 1 index */
@@ -481,30 +460,7 @@
MTSPR_CPU6(SPRN_MD_RPN, r10, r3) /* Update TLB entry */
/* Restore registers */
-#ifdef CONFIG_8xx_CPU6
mfspr r3, SPRN_SPRG_SCRATCH2
-#endif
- mtspr SPRN_DAR, r11 /* Tag DAR */
- EXCEPTION_EPILOG_0
- rfi
-
-4:
-_ENTRY(DTLBMiss_cmp)
- cmpli cr0, r11, (PAGE_OFFSET + 0x1800000)@h
- lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha
- bge- 3b
-
- mtcr r10
- /* Set 8M byte page and mark it valid */
- li r10, MD_PS8MEG | MD_SVALID
- MTSPR_CPU6(SPRN_MD_TWC, r10, r11)
- mfspr r10, SPRN_MD_EPN
- rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */
- ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY | \
- _PAGE_PRESENT
- MTSPR_CPU6(SPRN_MD_RPN, r10, r11) /* Update TLB entry */
-
- li r11, RPN_PATTERN
mtspr SPRN_DAR, r11 /* Tag DAR */
EXCEPTION_EPILOG_0
rfi
@@ -570,6 +526,43 @@
. = 0x2000
+/*
+ * Bottom part of DataStoreTLBMiss handlers for IMMR area and linear RAM.
+ * not enough space in the DataStoreTLBMiss area.
+ */
+DTLBMissIMMR:
+ mtcr r3
+ /* Set 512k byte guarded page and mark it valid */
+ li r10, MD_PS512K | MD_GUARDED | MD_SVALID
+ MTSPR_CPU6(SPRN_MD_TWC, r10, r11)
+ mfspr r10, SPRN_IMMR /* Get current IMMR */
+ rlwinm r10, r10, 0, 0xfff80000 /* Get 512 kbytes boundary */
+ ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY | \
+ _PAGE_PRESENT | _PAGE_NO_CACHE
+ MTSPR_CPU6(SPRN_MD_RPN, r10, r11) /* Update TLB entry */
+
+ li r11, RPN_PATTERN
+ mtspr SPRN_DAR, r11 /* Tag DAR */
+ mfspr r3, SPRN_SPRG_SCRATCH2
+ EXCEPTION_EPILOG_0
+ rfi
+
+DTLBMissLinear:
+ mtcr r3
+ /* Set 8M byte page and mark it valid */
+ li r11, MD_PS8MEG | MD_SVALID
+ MTSPR_CPU6(SPRN_MD_TWC, r11, r3)
+ rlwinm r10, r10, 16, 0x0f800000 /* 8xx supports max 256Mb RAM */
+ ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY | \
+ _PAGE_PRESENT
+ MTSPR_CPU6(SPRN_MD_RPN, r10, r11) /* Update TLB entry */
+
+ li r11, RPN_PATTERN
+ mtspr SPRN_DAR, r11 /* Tag DAR */
+ mfspr r3, SPRN_SPRG_SCRATCH2
+ EXCEPTION_EPILOG_0
+ rfi
+
/* This is the procedure to calculate the data EA for buggy dcbx,dcbi instructions
* by decoding the registers used by the dcbx instruction and adding them.
* DAR is set to the calculated address.
@@ -586,7 +579,9 @@
rlwinm r11, r10, 16, 0xfff8
_ENTRY(FixupDAR_cmp)
cmpli cr7, r11, (PAGE_OFFSET + 0x1800000)@h
- blt- cr7, 200f
+ /* create physical page address from effective address */
+ tophys(r11, r10)
+ blt- cr7, 201f
lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha
/* Insert level 1 index */
3: rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
@@ -616,10 +611,6 @@
141: mfspr r10,SPRN_SPRG_SCRATCH2
b DARFixed /* Nope, go back to normal TLB processing */
- /* create physical page address from effective address */
-200: tophys(r11, r10)
- b 201b
-
144: mfspr r10, SPRN_DSISR
rlwinm r10, r10,0,7,5 /* Clear store bit for buggy dcbst insn */
mtspr SPRN_DSISR, r10
@@ -894,6 +885,7 @@
.align PAGE_SHIFT
empty_zero_page:
.space PAGE_SIZE
+EXPORT_SYMBOL(empty_zero_page)
.globl swapper_pg_dir
swapper_pg_dir:
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 3bfa315..bf4c602 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -42,6 +42,7 @@
#include <asm/asm-offsets.h>
#include <asm/cache.h>
#include <asm/ptrace.h>
+#include <asm/export.h>
#include "head_booke.h"
/* As with the other PowerPC ports, it is expected that when code
@@ -1223,6 +1224,7 @@
.globl empty_zero_page
empty_zero_page:
.space 4096
+EXPORT_SYMBOL(empty_zero_page)
.globl swapper_pg_dir
swapper_pg_dir:
.space PGD_TABLE_SIZE
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 9781c69..03d089b 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -275,7 +275,7 @@ int hw_breakpoint_handler(struct die_args *args)
if (!stepped) {
WARN(1, "Unable to handle hardware breakpoint. Breakpoint at "
"0x%lx will be disabled.", info->address);
- perf_event_disable(bp);
+ perf_event_disable_inatomic(bp);
goto out;
}
/*
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index bd739fe..72dac0b 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -90,6 +90,7 @@
* Threads will spin in HMT_LOW until the lock bit is cleared.
* r14 - pointer to core_idle_state
* r15 - used to load contents of core_idle_state
+ * r9 - used as a temporary variable
*/
core_idle_lock_held:
@@ -99,6 +100,8 @@
bne 3b
HMT_MEDIUM
lwarx r15,0,r14
+ andi. r9,r15,PNV_CORE_IDLE_LOCK_BIT
+ bne core_idle_lock_held
blr
/*
@@ -163,12 +166,6 @@
std r9,_MSR(r1)
std r1,PACAR1(r13)
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
- /* Tell KVM we're entering idle */
- li r4,KVM_HWTHREAD_IN_IDLE
- stb r4,HSTATE_HWTHREAD_STATE(r13)
-#endif
-
/*
* Go to real mode to do the nap, as required by the architecture.
* Also, we need to be in real mode before setting hwthread_state,
@@ -185,6 +182,26 @@
.globl pnv_enter_arch207_idle_mode
pnv_enter_arch207_idle_mode:
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ /* Tell KVM we're entering idle */
+ li r4,KVM_HWTHREAD_IN_IDLE
+ /******************************************************/
+ /* N O T E W E L L ! ! ! N O T E W E L L */
+ /* The following store to HSTATE_HWTHREAD_STATE(r13) */
+ /* MUST occur in real mode, i.e. with the MMU off, */
+ /* and the MMU must stay off until we clear this flag */
+ /* and test HSTATE_HWTHREAD_REQ(r13) in the system */
+ /* reset interrupt vector in exceptions-64s.S. */
+ /* The reason is that another thread can switch the */
+ /* MMU to a guest context whenever this flag is set */
+ /* to KVM_HWTHREAD_IN_IDLE, and if the MMU was on, */
+ /* that would potentially cause this thread to start */
+ /* executing instructions from guest memory in */
+ /* hypervisor mode, leading to a host crash or data */
+ /* corruption, or worse. */
+ /******************************************************/
+ stb r4,HSTATE_HWTHREAD_STATE(r13)
+#endif
stb r3,PACA_THREAD_IDLE_STATE(r13)
cmpwi cr3,r3,PNV_THREAD_SLEEP
bge cr3,2f
@@ -250,6 +267,12 @@
* r3 - requested stop state
*/
power_enter_stop:
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ /* Tell KVM we're entering idle */
+ li r4,KVM_HWTHREAD_IN_IDLE
+ /* DO THIS IN REAL MODE! See comment above. */
+ stb r4,HSTATE_HWTHREAD_STATE(r13)
+#endif
/*
* Check if the requested state is a deep idle state.
*/
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 0d43219..384357c 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -18,6 +18,7 @@
#include <asm/unistd.h>
#include <asm/asm-compat.h>
#include <asm/asm-offsets.h>
+#include <asm/export.h>
.text
@@ -118,3 +119,4 @@
_GLOBAL(current_stack_pointer)
PPC_LL r3,0(r1)
blr
+EXPORT_SYMBOL(current_stack_pointer)
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 03756ff..93cf7a5 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -33,6 +33,7 @@
#include <asm/kexec.h>
#include <asm/bug.h>
#include <asm/ptrace.h>
+#include <asm/export.h>
.text
@@ -319,6 +320,7 @@
#endif /* CONFIG_4xx */
isync
blr
+EXPORT_SYMBOL(flush_instruction_cache)
#endif /* CONFIG_PPC_8xx */
/*
@@ -359,6 +361,7 @@
isync
blr
_ASM_NOKPROBE_SYMBOL(flush_icache_range)
+EXPORT_SYMBOL(flush_icache_range)
/*
* Flush a particular page from the data cache to RAM.
@@ -497,6 +500,7 @@
li r0,MAX_COPY_PREFETCH
li r11,4
b 2b
+EXPORT_SYMBOL(copy_page)
/*
* Extended precision shifts.
@@ -524,6 +528,7 @@
sraw r3,r3,r5 # MSW = MSW >> count
or r4,r4,r7 # LSW |= t2
blr
+EXPORT_SYMBOL(__ashrdi3)
_GLOBAL(__ashldi3)
subfic r6,r5,32
@@ -535,6 +540,7 @@
slw r4,r4,r5 # LSW = LSW << count
or r3,r3,r7 # MSW |= t2
blr
+EXPORT_SYMBOL(__ashldi3)
_GLOBAL(__lshrdi3)
subfic r6,r5,32
@@ -546,6 +552,7 @@
srw r3,r3,r5 # MSW = MSW >> count
or r4,r4,r7 # LSW |= t2
blr
+EXPORT_SYMBOL(__lshrdi3)
/*
* 64-bit comparison: __cmpdi2(s64 a, s64 b)
@@ -561,6 +568,7 @@
bltlr
li r3,2
blr
+EXPORT_SYMBOL(__cmpdi2)
/*
* 64-bit comparison: __ucmpdi2(u64 a, u64 b)
* Returns 0 if a < b, 1 if a == b, 2 if a > b.
@@ -575,6 +583,7 @@
bltlr
li r3,2
blr
+EXPORT_SYMBOL(__ucmpdi2)
_GLOBAL(__bswapdi2)
rotlwi r9,r4,8
@@ -586,6 +595,7 @@
mr r3,r9
mr r4,r10
blr
+EXPORT_SYMBOL(__bswapdi2)
#ifdef CONFIG_SMP
_GLOBAL(start_secondary_resume)
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 9f0bed2..4f17867 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -27,6 +27,7 @@
#include <asm/kexec.h>
#include <asm/ptrace.h>
#include <asm/mmu.h>
+#include <asm/export.h>
.text
@@ -110,6 +111,7 @@
isync
blr
_ASM_NOKPROBE_SYMBOL(flush_icache_range)
+EXPORT_SYMBOL(flush_icache_range)
/*
* Like above, but only do the D-cache.
@@ -140,6 +142,7 @@
bdnz 0b
sync
blr
+EXPORT_SYMBOL(flush_dcache_range)
/*
* Like above, but works on non-mapped physical addresses.
@@ -243,6 +246,7 @@
blr
_GLOBAL(__bswapdi2)
+EXPORT_SYMBOL(__bswapdi2)
srdi r8,r3,32
rlwinm r7,r3,8,0xffffffff
rlwimi r7,r3,24,0,7
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 95d3769..74bec54 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -56,6 +56,7 @@ static DECLARE_BITMAP(phb_bitmap, MAX_PHBS);
/* ISA Memory physical address */
resource_size_t isa_mem_base;
+EXPORT_SYMBOL(isa_mem_base);
static struct dma_map_ops *pci_dma_ops = &dma_direct_ops;
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 1f793003..678f87a 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -32,6 +32,8 @@
unsigned long isa_io_base = 0;
unsigned long pci_dram_offset = 0;
int pcibios_assign_bus_offset = 1;
+EXPORT_SYMBOL(isa_io_base);
+EXPORT_SYMBOL(pci_dram_offset);
void pcibios_make_OF_bus_map(void);
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
deleted file mode 100644
index 9f01e28..0000000
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ /dev/null
@@ -1,37 +0,0 @@
-#include <linux/ftrace.h>
-#include <linux/mm.h>
-
-#include <asm/processor.h>
-#include <asm/switch_to.h>
-#include <asm/cacheflush.h>
-#include <asm/epapr_hcalls.h>
-
-#ifdef CONFIG_PPC64
-EXPORT_SYMBOL(flush_dcache_range);
-#endif
-EXPORT_SYMBOL(flush_icache_range);
-
-EXPORT_SYMBOL(empty_zero_page);
-
-long long __bswapdi2(long long);
-EXPORT_SYMBOL(__bswapdi2);
-
-#ifdef CONFIG_FUNCTION_TRACER
-EXPORT_SYMBOL(_mcount);
-#endif
-
-#ifdef CONFIG_PPC_FPU
-EXPORT_SYMBOL(load_fp_state);
-EXPORT_SYMBOL(store_fp_state);
-#endif
-
-#ifdef CONFIG_ALTIVEC
-EXPORT_SYMBOL(load_vr_state);
-EXPORT_SYMBOL(store_vr_state);
-#endif
-
-#ifdef CONFIG_EPAPR_PARAVIRT
-EXPORT_SYMBOL(epapr_hypercall_start);
-#endif
-
-EXPORT_SYMBOL(current_stack_pointer);
diff --git a/arch/powerpc/kernel/ppc_ksyms_32.c b/arch/powerpc/kernel/ppc_ksyms_32.c
deleted file mode 100644
index 2bfaafe..0000000
--- a/arch/powerpc/kernel/ppc_ksyms_32.c
+++ /dev/null
@@ -1,60 +0,0 @@
-#include <linux/export.h>
-#include <linux/smp.h>
-
-#include <asm/page.h>
-#include <asm/dma.h>
-#include <asm/io.h>
-#include <asm/hw_irq.h>
-#include <asm/time.h>
-#include <asm/mmu_context.h>
-#include <asm/pgtable.h>
-#include <asm/dcr.h>
-
-EXPORT_SYMBOL(ISA_DMA_THRESHOLD);
-EXPORT_SYMBOL(DMA_MODE_READ);
-EXPORT_SYMBOL(DMA_MODE_WRITE);
-
-#if defined(CONFIG_PCI)
-EXPORT_SYMBOL(isa_io_base);
-EXPORT_SYMBOL(isa_mem_base);
-EXPORT_SYMBOL(pci_dram_offset);
-#endif
-
-#ifdef CONFIG_SMP
-EXPORT_SYMBOL(smp_hw_index);
-#endif
-
-long long __ashrdi3(long long, int);
-long long __ashldi3(long long, int);
-long long __lshrdi3(long long, int);
-int __ucmpdi2(unsigned long long, unsigned long long);
-int __cmpdi2(long long, long long);
-EXPORT_SYMBOL(__ashrdi3);
-EXPORT_SYMBOL(__ashldi3);
-EXPORT_SYMBOL(__lshrdi3);
-EXPORT_SYMBOL(__ucmpdi2);
-EXPORT_SYMBOL(__cmpdi2);
-
-EXPORT_SYMBOL(timer_interrupt);
-EXPORT_SYMBOL(tb_ticks_per_jiffy);
-
-EXPORT_SYMBOL(switch_mmu_context);
-
-#ifdef CONFIG_PPC_STD_MMU_32
-extern long mol_trampoline;
-EXPORT_SYMBOL(mol_trampoline); /* For MOL */
-EXPORT_SYMBOL(flush_hash_pages); /* For MOL */
-#ifdef CONFIG_SMP
-extern int mmu_hash_lock;
-EXPORT_SYMBOL(mmu_hash_lock); /* For MOL */
-#endif /* CONFIG_SMP */
-extern long *intercept_table;
-EXPORT_SYMBOL(intercept_table);
-#endif /* CONFIG_PPC_STD_MMU_32 */
-
-#ifdef CONFIG_PPC_DCR_NATIVE
-EXPORT_SYMBOL(__mtdcr);
-EXPORT_SYMBOL(__mfdcr);
-#endif
-
-EXPORT_SYMBOL(flush_instruction_cache);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 9e7c10f..ce6dc61 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1012,7 +1012,7 @@ void restore_tm_state(struct pt_regs *regs)
/* Ensure that restore_math() will restore */
if (msr_diff & MSR_FP)
current->thread.load_fp = 1;
-#ifdef CONFIG_ALIVEC
+#ifdef CONFIG_ALTIVEC
if (cpu_has_feature(CPU_FTR_ALTIVEC) && msr_diff & MSR_VEC)
current->thread.load_vec = 1;
#endif
diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c
index f52b7db3..010b7b3 100644
--- a/arch/powerpc/kernel/ptrace32.c
+++ b/arch/powerpc/kernel/ptrace32.c
@@ -74,7 +74,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
break;
copied = access_process_vm(child, (u64)addrOthers, &tmp,
- sizeof(tmp), 0);
+ sizeof(tmp), FOLL_FORCE);
if (copied != sizeof(tmp))
break;
ret = put_user(tmp, (u32 __user *)data);
@@ -179,7 +179,8 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
break;
ret = 0;
if (access_process_vm(child, (u64)addrOthers, &tmp,
- sizeof(tmp), 1) == sizeof(tmp))
+ sizeof(tmp),
+ FOLL_FORCE | FOLL_WRITE) == sizeof(tmp))
break;
ret = -EIO;
break;
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index dba265c..270ee30 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -131,15 +131,26 @@ void machine_shutdown(void)
ppc_md.machine_shutdown();
}
+static void machine_hang(void)
+{
+ pr_emerg("System Halted, OK to turn off power\n");
+ local_irq_disable();
+ while (1)
+ ;
+}
+
void machine_restart(char *cmd)
{
machine_shutdown();
if (ppc_md.restart)
ppc_md.restart(cmd);
+
smp_send_stop();
- printk(KERN_EMERG "System Halted, OK to turn off power\n");
- local_irq_disable();
- while (1) ;
+
+ do_kernel_restart(cmd);
+ mdelay(1000);
+
+ machine_hang();
}
void machine_power_off(void)
@@ -147,10 +158,9 @@ void machine_power_off(void)
machine_shutdown();
if (pm_power_off)
pm_power_off();
+
smp_send_stop();
- printk(KERN_EMERG "System Halted, OK to turn off power\n");
- local_irq_disable();
- while (1) ;
+ machine_hang();
}
/* Used by the G5 thermal driver */
EXPORT_SYMBOL_GPL(machine_power_off);
@@ -163,10 +173,9 @@ void machine_halt(void)
machine_shutdown();
if (ppc_md.halt)
ppc_md.halt();
+
smp_send_stop();
- printk(KERN_EMERG "System Halted, OK to turn off power\n");
- local_irq_disable();
- while (1) ;
+ machine_hang();
}
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 24ec3ea..5fe7918 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -16,6 +16,7 @@
#include <linux/cpu.h>
#include <linux/console.h>
#include <linux/memblock.h>
+#include <linux/export.h>
#include <asm/io.h>
#include <asm/prom.h>
@@ -47,11 +48,16 @@ int boot_cpuid_phys;
EXPORT_SYMBOL_GPL(boot_cpuid_phys);
int smp_hw_index[NR_CPUS];
+EXPORT_SYMBOL(smp_hw_index);
unsigned long ISA_DMA_THRESHOLD;
unsigned int DMA_MODE_READ;
unsigned int DMA_MODE_WRITE;
+EXPORT_SYMBOL(ISA_DMA_THRESHOLD);
+EXPORT_SYMBOL(DMA_MODE_READ);
+EXPORT_SYMBOL(DMA_MODE_WRITE);
+
/*
* These are used in binfmt_elf.c to put aux entries on the stack
* for each elf executable being started.
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 67859b7..bc3f7d0 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -596,6 +596,7 @@ void timer_interrupt(struct pt_regs * regs)
irq_exit();
set_irq_regs(old_regs);
}
+EXPORT_SYMBOL(timer_interrupt);
/*
* Hypervisor decrementer interrupts shouldn't occur but are sometimes
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index a1f8f56..023a462 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -273,7 +273,6 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
force_sig_info(signr, &info, current);
}
-#ifdef CONFIG_PPC64
void system_reset_exception(struct pt_regs *regs)
{
/* See if any machine dependent calls */
@@ -291,6 +290,7 @@ void system_reset_exception(struct pt_regs *regs)
/* What should we do here? We could issue a shutdown or hard reset. */
}
+#ifdef CONFIG_PPC64
/*
* This function is called in real mode. Strictly no printk's please.
*
@@ -352,12 +352,11 @@ static inline int check_io_access(struct pt_regs *regs)
* For the debug message, we look at the preceding
* load or store.
*/
- if (*nip == 0x60000000) /* nop */
+ if (*nip == PPC_INST_NOP)
nip -= 2;
- else if (*nip == 0x4c00012c) /* isync */
+ else if (*nip == PPC_INST_ISYNC)
--nip;
- if (*nip == 0x7c0004ac || (*nip >> 26) == 3) {
- /* sync or twi */
+ if (*nip == PPC_INST_SYNC || (*nip >> 26) == OP_TRAP) {
unsigned int rb;
--nip;
@@ -668,6 +667,31 @@ int machine_check_e200(struct pt_regs *regs)
return 0;
}
+#elif defined(CONFIG_PPC_8xx)
+int machine_check_8xx(struct pt_regs *regs)
+{
+ unsigned long reason = get_mc_reason(regs);
+
+ pr_err("Machine check in kernel mode.\n");
+ pr_err("Caused by (from SRR1=%lx): ", reason);
+ if (reason & 0x40000000)
+ pr_err("Fetch error at address %lx\n", regs->nip);
+ else
+ pr_err("Data access error at address %lx\n", regs->dar);
+
+#ifdef CONFIG_PCI
+ /* the qspan pci read routines can cause machine checks -- Cort
+ *
+ * yuck !!! that totally needs to go away ! There are better ways
+ * to deal with that than having a wart in the mcheck handler.
+ * -- BenH
+ */
+ bad_page_fault(regs, regs->dar, SIGBUS);
+ return 1;
+#else
+ return 0;
+#endif
+}
#else
int machine_check_generic(struct pt_regs *regs)
{
@@ -727,17 +751,6 @@ void machine_check_exception(struct pt_regs *regs)
if (recover > 0)
goto bail;
-#if defined(CONFIG_8xx) && defined(CONFIG_PCI)
- /* the qspan pci read routines can cause machine checks -- Cort
- *
- * yuck !!! that totally needs to go away ! There are better ways
- * to deal with that than having a wart in the mcheck handler.
- * -- BenH
- */
- bad_page_fault(regs, regs->dar, SIGBUS);
- goto bail;
-#endif
-
if (debugger_fault_handler(regs))
goto bail;
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index bc85bdf..0c123f3 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -6,6 +6,7 @@
#include <asm/thread_info.h>
#include <asm/page.h>
#include <asm/ptrace.h>
+#include <asm/export.h>
/*
* Load state from memory into VMX registers including VSCR.
@@ -17,6 +18,7 @@
mtvscr v0
REST_32VRS(0,r4,r3)
blr
+EXPORT_SYMBOL(load_vr_state)
/*
* Store VMX state into memory, including VSCR.
@@ -28,6 +30,7 @@
li r4, VRSTATE_VSCR
stvx v0, r4, r3
blr
+EXPORT_SYMBOL(store_vr_state)
/*
* Disable VMX for the task which had it previously,
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index 82ff5de..a0ea63a 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -23,6 +23,7 @@
#include <asm/ppc-opcode.h>
#include <asm/pnv-pci.h>
#include <asm/opal.h>
+#include <asm/smp.h>
#include "book3s_xics.h"
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index ad52900..309361e8 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -9,7 +9,7 @@
CFLAGS_REMOVE_code-patching.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_feature-fixups.o = $(CC_FLAGS_FTRACE)
-obj-y += string.o alloc.o crtsavres.o ppc_ksyms.o code-patching.o \
+obj-y += string.o alloc.o crtsavres.o code-patching.o \
feature-fixups.o
obj-$(CONFIG_PPC32) += div64.o copy_32.o
diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S
index aa8214f..ea29a5d 100644
--- a/arch/powerpc/lib/checksum_32.S
+++ b/arch/powerpc/lib/checksum_32.S
@@ -17,6 +17,7 @@
#include <asm/cache.h>
#include <asm/errno.h>
#include <asm/ppc_asm.h>
+#include <asm/export.h>
.text
@@ -68,6 +69,7 @@
adde r5,r5,r0
5: addze r3,r5 /* add in final carry */
blr
+EXPORT_SYMBOL(__csum_partial)
/*
* Computes the checksum of a memory block at src, length len,
@@ -297,3 +299,4 @@
.long 41b,dst_error
.long 50b,src_error
.long 51b,dst_error
+EXPORT_SYMBOL(csum_partial_copy_generic)
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index fdec6e6..fd91766 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -16,6 +16,7 @@
#include <asm/processor.h>
#include <asm/errno.h>
#include <asm/ppc_asm.h>
+#include <asm/export.h>
/*
* Computes the checksum of a memory block at buff, length len,
@@ -176,6 +177,7 @@
add r3,r4,r0
srdi r3,r3,32
blr
+EXPORT_SYMBOL(__csum_partial)
.macro srcnr
@@ -430,3 +432,4 @@
li r6,-EFAULT
stw r6,0(r8)
blr
+EXPORT_SYMBOL(csum_partial_copy_generic)
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index 99f37f2..40cce33 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -12,6 +12,7 @@
#include <asm/cache.h>
#include <asm/errno.h>
#include <asm/ppc_asm.h>
+#include <asm/export.h>
#define COPY_16_BYTES \
lwz r7,4(r4); \
@@ -92,6 +93,7 @@
subf r6,r0,r6
cmplwi 0,r4,0
bne 2f /* Use normal procedure if r4 is not zero */
+EXPORT_SYMBOL(memset)
_GLOBAL(memset_nocache_branch)
b 2f /* Skip optimised bloc until cache is enabled */
@@ -216,6 +218,8 @@
stbu r0,1(r6)
bdnz 40b
65: blr
+EXPORT_SYMBOL(memcpy)
+EXPORT_SYMBOL(memmove)
generic_memcpy:
srwi. r7,r5,3
@@ -507,3 +511,4 @@
.long 112b,120b
.long 114b,120b
.text
+EXPORT_SYMBOL(__copy_tofrom_user)
diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S
index a3c4dc4..21367b3 100644
--- a/arch/powerpc/lib/copypage_64.S
+++ b/arch/powerpc/lib/copypage_64.S
@@ -10,6 +10,7 @@
#include <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
+#include <asm/export.h>
.section ".toc","aw"
PPC64_CACHES:
@@ -110,3 +111,4 @@
std r11,120(r3)
std r12,128(r3)
blr
+EXPORT_SYMBOL(copy_page)
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index f09899e..60386b2 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -8,6 +8,7 @@
*/
#include <asm/processor.h>
#include <asm/ppc_asm.h>
+#include <asm/export.h>
#ifdef __BIG_ENDIAN__
#define sLd sld /* Shift towards low-numbered address. */
@@ -359,6 +360,7 @@
addi r3,r3,8
171:
177:
+179:
addi r3,r3,8
370:
372:
@@ -373,7 +375,6 @@
173:
174:
175:
-179:
181:
184:
186:
@@ -671,3 +672,4 @@
.llong 89b,100b
.llong 90b,100b
.llong 91b,100b
+EXPORT_SYMBOL(__copy_tofrom_user)
diff --git a/arch/powerpc/lib/hweight_64.S b/arch/powerpc/lib/hweight_64.S
index 19e6600..3de7ac1 100644
--- a/arch/powerpc/lib/hweight_64.S
+++ b/arch/powerpc/lib/hweight_64.S
@@ -19,6 +19,7 @@
*/
#include <asm/processor.h>
#include <asm/ppc_asm.h>
+#include <asm/export.h>
/* Note: This code relies on -mminimal-toc */
@@ -32,6 +33,7 @@
clrldi r3,r3,64-8
blr
ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
+EXPORT_SYMBOL(__arch_hweight8)
_GLOBAL(__arch_hweight16)
BEGIN_FTR_SECTION
@@ -54,6 +56,7 @@
blr
ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 50)
ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
+EXPORT_SYMBOL(__arch_hweight16)
_GLOBAL(__arch_hweight32)
BEGIN_FTR_SECTION
@@ -79,6 +82,7 @@
blr
ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 51)
ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
+EXPORT_SYMBOL(__arch_hweight32)
_GLOBAL(__arch_hweight64)
BEGIN_FTR_SECTION
@@ -108,3 +112,4 @@
blr
ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 52)
ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
+EXPORT_SYMBOL(__arch_hweight64)
diff --git a/arch/powerpc/lib/mem_64.S b/arch/powerpc/lib/mem_64.S
index eda7a96..85fa986 100644
--- a/arch/powerpc/lib/mem_64.S
+++ b/arch/powerpc/lib/mem_64.S
@@ -11,6 +11,7 @@
#include <asm/processor.h>
#include <asm/errno.h>
#include <asm/ppc_asm.h>
+#include <asm/export.h>
_GLOBAL(memset)
neg r0,r3
@@ -77,6 +78,7 @@
10: bflr 31
stb r4,0(r6)
blr
+EXPORT_SYMBOL(memset)
_GLOBAL_TOC(memmove)
cmplw 0,r3,r4
@@ -119,3 +121,4 @@
beq 2b
mtctr r7
b 1b
+EXPORT_SYMBOL(memmove)
diff --git a/arch/powerpc/lib/memcmp_64.S b/arch/powerpc/lib/memcmp_64.S
index 8953d23..d75d18b 100644
--- a/arch/powerpc/lib/memcmp_64.S
+++ b/arch/powerpc/lib/memcmp_64.S
@@ -8,6 +8,7 @@
* 2 of the License, or (at your option) any later version.
*/
#include <asm/ppc_asm.h>
+#include <asm/export.h>
#define off8 r6
#define off16 r7
@@ -231,3 +232,4 @@
ld r28,-32(r1)
ld r27,-40(r1)
blr
+EXPORT_SYMBOL(memcmp)
diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S
index 32a06ec..f4d6088 100644
--- a/arch/powerpc/lib/memcpy_64.S
+++ b/arch/powerpc/lib/memcpy_64.S
@@ -8,6 +8,7 @@
*/
#include <asm/processor.h>
#include <asm/ppc_asm.h>
+#include <asm/export.h>
.align 7
_GLOBAL_TOC(memcpy)
@@ -219,3 +220,4 @@
4: ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) /* return dest pointer */
blr
#endif
+EXPORT_SYMBOL(memcpy)
diff --git a/arch/powerpc/lib/ppc_ksyms.c b/arch/powerpc/lib/ppc_ksyms.c
deleted file mode 100644
index ae69d84..0000000
--- a/arch/powerpc/lib/ppc_ksyms.c
+++ /dev/null
@@ -1,29 +0,0 @@
-#include <linux/string.h>
-#include <linux/uaccess.h>
-#include <linux/bitops.h>
-#include <net/checksum.h>
-
-EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memmove);
-EXPORT_SYMBOL(memcmp);
-EXPORT_SYMBOL(memchr);
-
-EXPORT_SYMBOL(strncpy);
-EXPORT_SYMBOL(strncmp);
-
-#ifndef CONFIG_GENERIC_CSUM
-EXPORT_SYMBOL(__csum_partial);
-EXPORT_SYMBOL(csum_partial_copy_generic);
-#endif
-
-EXPORT_SYMBOL(__copy_tofrom_user);
-EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(copy_page);
-
-#ifdef CONFIG_PPC64
-EXPORT_SYMBOL(__arch_hweight8);
-EXPORT_SYMBOL(__arch_hweight16);
-EXPORT_SYMBOL(__arch_hweight32);
-EXPORT_SYMBOL(__arch_hweight64);
-#endif
diff --git a/arch/powerpc/lib/string.S b/arch/powerpc/lib/string.S
index beabc68..d13e076 100644
--- a/arch/powerpc/lib/string.S
+++ b/arch/powerpc/lib/string.S
@@ -11,6 +11,7 @@
#include <asm/processor.h>
#include <asm/errno.h>
#include <asm/ppc_asm.h>
+#include <asm/export.h>
.section __ex_table,"a"
PPC_LONG_ALIGN
@@ -36,6 +37,7 @@
2: stbu r0,1(r6) /* clear it out if so */
bdnz 2b
blr
+EXPORT_SYMBOL(strncpy)
_GLOBAL(strncmp)
PPC_LCMPI 0,r5,0
@@ -53,6 +55,7 @@
blr
2: li r3,0
blr
+EXPORT_SYMBOL(strncmp)
#ifdef CONFIG_PPC32
_GLOBAL(memcmp)
@@ -68,6 +71,7 @@
blr
2: li r3,0
blr
+EXPORT_SYMBOL(memcmp)
#endif
_GLOBAL(memchr)
@@ -82,6 +86,7 @@
beqlr
2: li r3,0
blr
+EXPORT_SYMBOL(memchr)
#ifdef CONFIG_PPC32
_GLOBAL(__clear_user)
@@ -125,4 +130,5 @@
PPC_LONG 1b,91b
PPC_LONG 8b,92b
.text
+EXPORT_SYMBOL(__clear_user)
#endif
diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S
index 7bd9549..57ace35 100644
--- a/arch/powerpc/lib/string_64.S
+++ b/arch/powerpc/lib/string_64.S
@@ -20,6 +20,7 @@
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
+#include <asm/export.h>
.section ".toc","aw"
PPC64_CACHES:
@@ -200,3 +201,4 @@
cmpdi r4,32
blt .Lshort_clear
b .Lmedium_clear
+EXPORT_SYMBOL(__clear_user)
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index bb03542..362954f 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -106,6 +106,8 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
switch (REGION_ID(ea)) {
case USER_REGION_ID:
pr_devel("%s: 0x%llx -- USER_REGION_ID\n", __func__, ea);
+ if (mm == NULL)
+ return 1;
psize = get_slice_psize(mm, ea);
ssize = user_segment_size(ea);
vsid = get_vsid(mm->context.id, ea, ssize);
diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S
index 115347f..09cc50c 100644
--- a/arch/powerpc/mm/hash_low_32.S
+++ b/arch/powerpc/mm/hash_low_32.S
@@ -26,6 +26,7 @@
#include <asm/ppc_asm.h>
#include <asm/thread_info.h>
#include <asm/asm-offsets.h>
+#include <asm/export.h>
#ifdef CONFIG_SMP
.section .bss
@@ -33,6 +34,7 @@
.globl mmu_hash_lock
mmu_hash_lock:
.space 4
+EXPORT_SYMBOL(mmu_hash_lock)
#endif /* CONFIG_SMP */
/*
@@ -575,6 +577,7 @@
rlwinm r8,r8,0,31,29 /* clear HASHPTE bit */
stwcx. r8,0,r5 /* update the pte */
bne- 33b
+EXPORT_SYMBOL(flush_hash_pages)
/* Get the address of the primary PTE group in the hash table (r3) */
_GLOBAL(flush_hash_patch_A)
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 90480e2..44d3c3a 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -529,7 +529,7 @@ static bool might_have_hea(void)
*/
#ifdef CONFIG_IBMEBUS
return !cpu_has_feature(CPU_FTR_ARCH_207S) &&
- !firmware_has_feature(FW_FEATURE_SPLPAR);
+ firmware_has_feature(FW_FEATURE_SPLPAR);
#else
return false;
#endif
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 75b9cd6..a51c188 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -845,7 +845,7 @@ void __init dump_numa_cpu_topology(void)
return;
for_each_online_node(node) {
- printk(KERN_DEBUG "Node %d CPUs:", node);
+ pr_info("Node %d CPUs:", node);
count = 0;
/*
@@ -856,52 +856,18 @@ void __init dump_numa_cpu_topology(void)
if (cpumask_test_cpu(cpu,
node_to_cpumask_map[node])) {
if (count == 0)
- printk(" %u", cpu);
+ pr_cont(" %u", cpu);
++count;
} else {
if (count > 1)
- printk("-%u", cpu - 1);
+ pr_cont("-%u", cpu - 1);
count = 0;
}
}
if (count > 1)
- printk("-%u", nr_cpu_ids - 1);
- printk("\n");
- }
-}
-
-static void __init dump_numa_memory_topology(void)
-{
- unsigned int node;
- unsigned int count;
-
- if (min_common_depth == -1 || !numa_enabled)
- return;
-
- for_each_online_node(node) {
- unsigned long i;
-
- printk(KERN_DEBUG "Node %d Memory:", node);
-
- count = 0;
-
- for (i = 0; i < memblock_end_of_DRAM();
- i += (1 << SECTION_SIZE_BITS)) {
- if (early_pfn_to_nid(i >> PAGE_SHIFT) == node) {
- if (count == 0)
- printk(" 0x%lx", i);
- ++count;
- } else {
- if (count > 0)
- printk("-0x%lx", i);
- count = 0;
- }
- }
-
- if (count > 0)
- printk("-0x%lx", i);
- printk("\n");
+ pr_cont("-%u", nr_cpu_ids - 1);
+ pr_cont("\n");
}
}
@@ -947,8 +913,6 @@ void __init initmem_init(void)
if (parse_numa_properties())
setup_nonnuma();
- else
- dump_numa_memory_topology();
memblock_dump_all();
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 0e49ec5..bda8c43 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -175,7 +175,7 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
if (unlikely(pid == MMU_NO_CONTEXT))
goto no_context;
- if (!mm_is_core_local(mm)) {
+ if (!mm_is_thread_local(mm)) {
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
if (lock_tlbie)
@@ -201,7 +201,7 @@ void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
if (unlikely(pid == MMU_NO_CONTEXT))
goto no_context;
- if (!mm_is_core_local(mm)) {
+ if (!mm_is_thread_local(mm)) {
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
if (lock_tlbie)
@@ -226,7 +226,7 @@ void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
pid = mm ? mm->context.id : 0;
if (unlikely(pid == MMU_NO_CONTEXT))
goto bail;
- if (!mm_is_core_local(mm)) {
+ if (!mm_is_thread_local(mm)) {
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
if (lock_tlbie)
@@ -321,7 +321,7 @@ void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
{
unsigned long pid;
unsigned long addr;
- int local = mm_is_core_local(mm);
+ int local = mm_is_thread_local(mm);
unsigned long ap = mmu_get_ap(psize);
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
unsigned long page_size = 1UL << mmu_psize_defs[psize].shift;
diff --git a/arch/powerpc/platforms/82xx/Kconfig b/arch/powerpc/platforms/82xx/Kconfig
index 7c7df400..994d1a9 100644
--- a/arch/powerpc/platforms/82xx/Kconfig
+++ b/arch/powerpc/platforms/82xx/Kconfig
@@ -30,8 +30,8 @@
select 8272
select 8260
select FSL_SOC
- select PHYLIB
- select MDIO_BITBANG
+ select PHYLIB if NETDEVICES
+ select MDIO_BITBANG if PHYLIB
help
This enables support for the Embedded Planet EP8248E board.
diff --git a/arch/powerpc/platforms/82xx/ep8248e.c b/arch/powerpc/platforms/82xx/ep8248e.c
index cdab847..8fec050 100644
--- a/arch/powerpc/platforms/82xx/ep8248e.c
+++ b/arch/powerpc/platforms/82xx/ep8248e.c
@@ -298,7 +298,9 @@ static const struct of_device_id of_bus_ids[] __initconst = {
static int __init declare_of_platform_devices(void)
{
of_platform_bus_probe(NULL, of_bus_ids, NULL);
- platform_driver_register(&ep8248e_mdio_driver);
+
+ if (IS_ENABLED(CONFIG_MDIO_BITBANG))
+ platform_driver_register(&ep8248e_mdio_driver);
return 0;
}
diff --git a/arch/powerpc/platforms/83xx/asp834x.c b/arch/powerpc/platforms/83xx/asp834x.c
index 17e5433..575afd6 100644
--- a/arch/powerpc/platforms/83xx/asp834x.c
+++ b/arch/powerpc/platforms/83xx/asp834x.c
@@ -30,9 +30,7 @@
*/
static void __init asp834x_setup_arch(void)
{
- if (ppc_md.progress)
- ppc_md.progress("asp834x_setup_arch()", 0);
-
+ mpc83xx_setup_arch();
mpc834x_usb_cfg();
}
diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c
index e7fbd63..d8642a4 100644
--- a/arch/powerpc/platforms/83xx/km83xx.c
+++ b/arch/powerpc/platforms/83xx/km83xx.c
@@ -130,10 +130,7 @@ static void __init mpc83xx_km_setup_arch(void)
struct device_node *np;
#endif
- if (ppc_md.progress)
- ppc_md.progress("kmpbec83xx_setup_arch()", 0);
-
- mpc83xx_setup_pci();
+ mpc83xx_setup_arch();
#ifdef CONFIG_QUICC_ENGINE
np = of_find_node_by_name(NULL, "par_io");
diff --git a/arch/powerpc/platforms/83xx/misc.c b/arch/powerpc/platforms/83xx/misc.c
index 8899aa9..d75c981 100644
--- a/arch/powerpc/platforms/83xx/misc.c
+++ b/arch/powerpc/platforms/83xx/misc.c
@@ -142,3 +142,11 @@ void __init mpc83xx_setup_pci(void)
mpc83xx_add_bridge(np);
}
#endif
+
+void __init mpc83xx_setup_arch(void)
+{
+ if (ppc_md.progress)
+ ppc_md.progress("mpc83xx_setup_arch()", 0);
+
+ mpc83xx_setup_pci();
+}
diff --git a/arch/powerpc/platforms/83xx/mpc830x_rdb.c b/arch/powerpc/platforms/83xx/mpc830x_rdb.c
index 040d5d0..272c41c 100644
--- a/arch/powerpc/platforms/83xx/mpc830x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc830x_rdb.c
@@ -27,10 +27,7 @@
*/
static void __init mpc830x_rdb_setup_arch(void)
{
- if (ppc_md.progress)
- ppc_md.progress("mpc830x_rdb_setup_arch()", 0);
-
- mpc83xx_setup_pci();
+ mpc83xx_setup_arch();
mpc831x_usb_cfg();
}
diff --git a/arch/powerpc/platforms/83xx/mpc831x_rdb.c b/arch/powerpc/platforms/83xx/mpc831x_rdb.c
index 40e0d83..fd80fd5 100644
--- a/arch/powerpc/platforms/83xx/mpc831x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc831x_rdb.c
@@ -28,10 +28,7 @@
*/
static void __init mpc831x_rdb_setup_arch(void)
{
- if (ppc_md.progress)
- ppc_md.progress("mpc831x_rdb_setup_arch()", 0);
-
- mpc83xx_setup_pci();
+ mpc83xx_setup_arch();
mpc831x_usb_cfg();
}
diff --git a/arch/powerpc/platforms/83xx/mpc832x_mds.c b/arch/powerpc/platforms/83xx/mpc832x_mds.c
index cdfa47c..bb7b25a 100644
--- a/arch/powerpc/platforms/83xx/mpc832x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc832x_mds.c
@@ -58,8 +58,7 @@ static void __init mpc832x_sys_setup_arch(void)
struct device_node *np;
u8 __iomem *bcsr_regs = NULL;
- if (ppc_md.progress)
- ppc_md.progress("mpc832x_sys_setup_arch()", 0);
+ mpc83xx_setup_arch();
/* Map BCSR area */
np = of_find_node_by_name(NULL, "bcsr");
@@ -71,8 +70,6 @@ static void __init mpc832x_sys_setup_arch(void)
of_node_put(np);
}
- mpc83xx_setup_pci();
-
#ifdef CONFIG_QUICC_ENGINE
if ((np = of_find_node_by_name(NULL, "par_io")) != NULL) {
par_io_init(np);
diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c
index 0d6a62f..d7c9b18 100644
--- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c
@@ -197,10 +197,7 @@ static void __init mpc832x_rdb_setup_arch(void)
struct device_node *np;
#endif
- if (ppc_md.progress)
- ppc_md.progress("mpc832x_rdb_setup_arch()", 0);
-
- mpc83xx_setup_pci();
+ mpc83xx_setup_arch();
#ifdef CONFIG_QUICC_ENGINE
if ((np = of_find_node_by_name(NULL, "par_io")) != NULL) {
diff --git a/arch/powerpc/platforms/83xx/mpc834x_itx.c b/arch/powerpc/platforms/83xx/mpc834x_itx.c
index 8fd0c1e..73a5267d 100644
--- a/arch/powerpc/platforms/83xx/mpc834x_itx.c
+++ b/arch/powerpc/platforms/83xx/mpc834x_itx.c
@@ -57,10 +57,7 @@ machine_device_initcall(mpc834x_itx, mpc834x_itx_declare_of_platform_devices);
*/
static void __init mpc834x_itx_setup_arch(void)
{
- if (ppc_md.progress)
- ppc_md.progress("mpc834x_itx_setup_arch()", 0);
-
- mpc83xx_setup_pci();
+ mpc83xx_setup_arch();
mpc834x_usb_cfg();
}
diff --git a/arch/powerpc/platforms/83xx/mpc834x_mds.c b/arch/powerpc/platforms/83xx/mpc834x_mds.c
index eeaee61..009cfc1 100644
--- a/arch/powerpc/platforms/83xx/mpc834x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc834x_mds.c
@@ -76,10 +76,7 @@ static int mpc834xemds_usb_cfg(void)
*/
static void __init mpc834x_mds_setup_arch(void)
{
- if (ppc_md.progress)
- ppc_md.progress("mpc834x_mds_setup_arch()", 0);
-
- mpc83xx_setup_pci();
+ mpc83xx_setup_arch();
mpc834xemds_usb_cfg();
}
diff --git a/arch/powerpc/platforms/83xx/mpc836x_mds.c b/arch/powerpc/platforms/83xx/mpc836x_mds.c
index dacf4c2..4fc3051 100644
--- a/arch/powerpc/platforms/83xx/mpc836x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc836x_mds.c
@@ -66,8 +66,7 @@ static void __init mpc836x_mds_setup_arch(void)
struct device_node *np;
u8 __iomem *bcsr_regs = NULL;
- if (ppc_md.progress)
- ppc_md.progress("mpc836x_mds_setup_arch()", 0);
+ mpc83xx_setup_arch();
/* Map BCSR area */
np = of_find_node_by_name(NULL, "bcsr");
@@ -79,8 +78,6 @@ static void __init mpc836x_mds_setup_arch(void)
of_node_put(np);
}
- mpc83xx_setup_pci();
-
#ifdef CONFIG_QUICC_ENGINE
if ((np = of_find_node_by_name(NULL, "par_io")) != NULL) {
par_io_init(np);
diff --git a/arch/powerpc/platforms/83xx/mpc836x_rdk.c b/arch/powerpc/platforms/83xx/mpc836x_rdk.c
index cf67ac9..93f024f 100644
--- a/arch/powerpc/platforms/83xx/mpc836x_rdk.c
+++ b/arch/powerpc/platforms/83xx/mpc836x_rdk.c
@@ -31,10 +31,7 @@ machine_device_initcall(mpc836x_rdk, mpc83xx_declare_of_platform_devices);
static void __init mpc836x_rdk_setup_arch(void)
{
- if (ppc_md.progress)
- ppc_md.progress("mpc836x_rdk_setup_arch()", 0);
-
- mpc83xx_setup_pci();
+ mpc83xx_setup_arch();
}
/*
diff --git a/arch/powerpc/platforms/83xx/mpc837x_mds.c b/arch/powerpc/platforms/83xx/mpc837x_mds.c
index 652b97d..3b34cc1 100644
--- a/arch/powerpc/platforms/83xx/mpc837x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc837x_mds.c
@@ -79,10 +79,7 @@ static int mpc837xmds_usb_cfg(void)
*/
static void __init mpc837x_mds_setup_arch(void)
{
- if (ppc_md.progress)
- ppc_md.progress("mpc837x_mds_setup_arch()", 0);
-
- mpc83xx_setup_pci();
+ mpc83xx_setup_arch();
mpc837xmds_usb_cfg();
}
diff --git a/arch/powerpc/platforms/83xx/mpc837x_rdb.c b/arch/powerpc/platforms/83xx/mpc837x_rdb.c
index 667731d..0c55fa6 100644
--- a/arch/powerpc/platforms/83xx/mpc837x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc837x_rdb.c
@@ -50,10 +50,7 @@ static void mpc837x_rdb_sd_cfg(void)
*/
static void __init mpc837x_rdb_setup_arch(void)
{
- if (ppc_md.progress)
- ppc_md.progress("mpc837x_rdb_setup_arch()", 0);
-
- mpc83xx_setup_pci();
+ mpc83xx_setup_arch();
mpc837x_usb_cfg();
mpc837x_rdb_sd_cfg();
}
diff --git a/arch/powerpc/platforms/83xx/mpc83xx.h b/arch/powerpc/platforms/83xx/mpc83xx.h
index ad48419..636eb9d 100644
--- a/arch/powerpc/platforms/83xx/mpc83xx.h
+++ b/arch/powerpc/platforms/83xx/mpc83xx.h
@@ -86,5 +86,6 @@ extern void mpc83xx_setup_pci(void);
#endif
extern int mpc83xx_declare_of_platform_devices(void);
+extern void mpc83xx_setup_arch(void);
#endif /* __MPC83XX_H__ */
diff --git a/arch/powerpc/platforms/83xx/sbc834x.c b/arch/powerpc/platforms/83xx/sbc834x.c
index b867e88..cb4bdab 100644
--- a/arch/powerpc/platforms/83xx/sbc834x.c
+++ b/arch/powerpc/platforms/83xx/sbc834x.c
@@ -47,10 +47,7 @@
*/
static void __init sbc834x_setup_arch(void)
{
- if (ppc_md.progress)
- ppc_md.progress("sbc834x_setup_arch()", 0);
-
- mpc83xx_setup_pci();
+ mpc83xx_setup_arch();
}
machine_device_initcall(sbc834x, mpc83xx_declare_of_platform_devices);
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index df25a3e..9dc1d28 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -72,7 +72,7 @@
config MPC85xx_MDS
bool "Freescale MPC85xx MDS"
select DEFAULT_UIMAGE
- select PHYLIB
+ select PHYLIB if NETDEVICES
select HAS_RAPIDIO
select SWIOTLB
help
diff --git a/arch/powerpc/platforms/85xx/bsc913x_qds.c b/arch/powerpc/platforms/85xx/bsc913x_qds.c
index 07dd6ae..d2f4556 100644
--- a/arch/powerpc/platforms/85xx/bsc913x_qds.c
+++ b/arch/powerpc/platforms/85xx/bsc913x_qds.c
@@ -72,7 +72,6 @@ define_machine(bsc9132_qds) {
.pcibios_fixup_bus = fsl_pcibios_fixup_bus,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/bsc913x_rdb.c b/arch/powerpc/platforms/85xx/bsc913x_rdb.c
index e48f671..0ffdb4a 100644
--- a/arch/powerpc/platforms/85xx/bsc913x_rdb.c
+++ b/arch/powerpc/platforms/85xx/bsc913x_rdb.c
@@ -59,7 +59,6 @@ define_machine(bsc9131_rdb) {
.setup_arch = bsc913x_rdb_setup_arch,
.init_IRQ = bsc913x_rdb_pic_init,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/c293pcie.c b/arch/powerpc/platforms/85xx/c293pcie.c
index 3b9e3f0..4df1b40 100644
--- a/arch/powerpc/platforms/85xx/c293pcie.c
+++ b/arch/powerpc/platforms/85xx/c293pcie.c
@@ -65,7 +65,6 @@ define_machine(c293_pcie) {
.setup_arch = c293_pcie_setup_arch,
.init_IRQ = c293_pcie_pic_init,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c
index 3a6a84f..1179115 100644
--- a/arch/powerpc/platforms/85xx/corenet_generic.c
+++ b/arch/powerpc/platforms/85xx/corenet_generic.c
@@ -225,7 +225,6 @@ define_machine(corenet_generic) {
#else
.get_irq = mpic_get_coreint_irq,
#endif
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
#ifdef CONFIG_PPC64
diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c
index 14af36a..f29c6f0 100644
--- a/arch/powerpc/platforms/85xx/ge_imp3a.c
+++ b/arch/powerpc/platforms/85xx/ge_imp3a.c
@@ -215,7 +215,6 @@ define_machine(ge_imp3a) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index 6ba687f..94a7f92 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -77,7 +77,6 @@ define_machine(mpc8536_ds) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ads.c b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
index 8756715..f3e055f 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ads.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
@@ -170,7 +170,6 @@ define_machine(mpc85xx_ads) {
.init_IRQ = mpc85xx_ads_pic_init,
.show_cpuinfo = mpc85xx_ads_show_cpuinfo,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
index 86f2015..224db30 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
@@ -83,7 +83,8 @@ static int mpc85xx_exclude_device(struct pci_controller *hose,
return PCIBIOS_SUCCESSFUL;
}
-static void __noreturn mpc85xx_cds_restart(char *cmd)
+static int mpc85xx_cds_restart(struct notifier_block *this,
+ unsigned long mode, void *cmd)
{
struct pci_dev *dev;
u_char tmp;
@@ -108,12 +109,25 @@ static void __noreturn mpc85xx_cds_restart(char *cmd)
}
/*
- * If we can't find the VIA chip (maybe the P2P bridge is disabled)
- * or the VIA chip reset didn't work, just use the default reset.
+ * If we can't find the VIA chip (maybe the P2P bridge is
+ * disabled) or the VIA chip reset didn't work, just return
+ * and let default reset sequence happen.
*/
- fsl_rstcr_restart(NULL);
+ return NOTIFY_DONE;
}
+static int mpc85xx_cds_restart_register(void)
+{
+ static struct notifier_block restart_handler;
+
+ restart_handler.notifier_call = mpc85xx_cds_restart;
+ restart_handler.priority = 192;
+
+ return register_restart_handler(&restart_handler);
+}
+machine_arch_initcall(mpc85xx_cds, mpc85xx_cds_restart_register);
+
+
static void __init mpc85xx_cds_pci_irq_fixup(struct pci_dev *dev)
{
u_char c;
@@ -380,11 +394,8 @@ define_machine(mpc85xx_cds) {
.show_cpuinfo = mpc85xx_cds_show_cpuinfo,
.get_irq = mpic_get_irq,
#ifdef CONFIG_PCI
- .restart = mpc85xx_cds_restart,
.pcibios_fixup_bus = mpc85xx_cds_fixup_bus,
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
-#else
- .restart = fsl_rstcr_restart,
#endif
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
index ed69c7e..dc9e035 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
@@ -204,7 +204,6 @@ define_machine(mpc8544_ds) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
@@ -219,7 +218,6 @@ define_machine(mpc8572_ds) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
@@ -234,7 +232,6 @@ define_machine(p2020_ds) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index fa9cd71..d7e440e 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -63,6 +63,8 @@
#define DBG(fmt...)
#endif
+#if IS_BUILTIN(CONFIG_PHYLIB)
+
#define MV88E1111_SCR 0x10
#define MV88E1111_SCR_125CLK 0x0010
static int mpc8568_fixup_125_clock(struct phy_device *phydev)
@@ -152,6 +154,8 @@ static int mpc8568_mds_phy_fixups(struct phy_device *phydev)
return err;
}
+#endif
+
/* ************************************************************************
*
* Setup the architecture
@@ -313,6 +317,7 @@ static void __init mpc85xx_mds_setup_arch(void)
swiotlb_detect_4g();
}
+#if IS_BUILTIN(CONFIG_PHYLIB)
static int __init board_fixups(void)
{
@@ -342,9 +347,12 @@ static int __init board_fixups(void)
return 0;
}
+
machine_arch_initcall(mpc8568_mds, board_fixups);
machine_arch_initcall(mpc8569_mds, board_fixups);
+#endif
+
static int __init mpc85xx_publish_devices(void)
{
if (machine_is(mpc8568_mds))
@@ -385,7 +393,6 @@ define_machine(mpc8568_mds) {
.setup_arch = mpc85xx_mds_setup_arch,
.init_IRQ = mpc85xx_mds_pic_init,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
#ifdef CONFIG_PCI
@@ -405,7 +412,6 @@ define_machine(mpc8569_mds) {
.setup_arch = mpc85xx_mds_setup_arch,
.init_IRQ = mpc85xx_mds_pic_init,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
#ifdef CONFIG_PCI
@@ -426,7 +432,6 @@ define_machine(p1021_mds) {
.setup_arch = mpc85xx_mds_setup_arch,
.init_IRQ = mpc85xx_mds_pic_init,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
#ifdef CONFIG_PCI
@@ -434,4 +439,3 @@ define_machine(p1021_mds) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
};
-
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
index c1499cb..1006950 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
@@ -213,7 +213,6 @@ define_machine(p2020_rdb) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
@@ -228,7 +227,6 @@ define_machine(p1020_rdb) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
@@ -243,7 +241,6 @@ define_machine(p1021_rdb_pc) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
@@ -258,7 +255,6 @@ define_machine(p2020_rdb_pc) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
@@ -273,7 +269,6 @@ define_machine(p1025_rdb) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
@@ -288,7 +283,6 @@ define_machine(p1020_mbg_pc) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
@@ -303,7 +297,6 @@ define_machine(p1020_utm_pc) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
@@ -318,7 +311,6 @@ define_machine(p1020_rdb_pc) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
@@ -333,7 +325,6 @@ define_machine(p1020_rdb_pd) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
@@ -348,7 +339,6 @@ define_machine(p1024_rdb) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/mvme2500.c b/arch/powerpc/platforms/85xx/mvme2500.c
index acc3d0d..d5af072 100644
--- a/arch/powerpc/platforms/85xx/mvme2500.c
+++ b/arch/powerpc/platforms/85xx/mvme2500.c
@@ -66,7 +66,6 @@ define_machine(mvme2500) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c
index 661d7b5..78d13b3 100644
--- a/arch/powerpc/platforms/85xx/p1010rdb.c
+++ b/arch/powerpc/platforms/85xx/p1010rdb.c
@@ -79,7 +79,6 @@ define_machine(p1010_rdb) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 63568d6..0908abd 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -568,7 +568,6 @@ define_machine(p1022_ds) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c
index 2f29436..276e00a 100644
--- a/arch/powerpc/platforms/85xx/p1022_rdk.c
+++ b/arch/powerpc/platforms/85xx/p1022_rdk.c
@@ -148,7 +148,6 @@ define_machine(p1022_rdk) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/p1023_rdb.c b/arch/powerpc/platforms/85xx/p1023_rdb.c
index 40d8de5..3e8cd032 100644
--- a/arch/powerpc/platforms/85xx/p1023_rdb.c
+++ b/arch/powerpc/platforms/85xx/p1023_rdb.c
@@ -110,7 +110,6 @@ define_machine(p1023_rdb) {
.setup_arch = mpc85xx_rdb_setup_arch,
.init_IRQ = mpc85xx_rdb_pic_init,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
#ifdef CONFIG_PCI
diff --git a/arch/powerpc/platforms/85xx/ppa8548.c b/arch/powerpc/platforms/85xx/ppa8548.c
index 2410167..33c5ba6 100644
--- a/arch/powerpc/platforms/85xx/ppa8548.c
+++ b/arch/powerpc/platforms/85xx/ppa8548.c
@@ -91,7 +91,6 @@ define_machine(ppa8548) {
.init_IRQ = ppa8548_pic_init,
.show_cpuinfo = ppa8548_show_cpuinfo,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c
index 50d7458..b63a854 100644
--- a/arch/powerpc/platforms/85xx/qemu_e500.c
+++ b/arch/powerpc/platforms/85xx/qemu_e500.c
@@ -77,7 +77,6 @@ define_machine(qemu_e500) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_coreint_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/sbc8548.c b/arch/powerpc/platforms/85xx/sbc8548.c
index 62b6c45..2c67084 100644
--- a/arch/powerpc/platforms/85xx/sbc8548.c
+++ b/arch/powerpc/platforms/85xx/sbc8548.c
@@ -130,7 +130,6 @@ define_machine(sbc8548) {
.init_IRQ = sbc8548_pic_init,
.show_cpuinfo = sbc8548_show_cpuinfo,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
#ifdef CONFIG_PCI
.pcibios_fixup_bus = fsl_pcibios_fixup_bus,
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c
index 79fd0df..21d6aaa 100644
--- a/arch/powerpc/platforms/85xx/sgy_cts1000.c
+++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c
@@ -38,18 +38,18 @@ static void gpio_halt_wfn(struct work_struct *work)
}
static DECLARE_WORK(gpio_halt_wq, gpio_halt_wfn);
-static void gpio_halt_cb(void)
+static void __noreturn gpio_halt_cb(void)
{
enum of_gpio_flags flags;
int trigger, gpio;
if (!halt_node)
- return;
+ panic("No reset GPIO information was provided in DT\n");
gpio = of_get_gpio_flags(halt_node, 0, &flags);
if (!gpio_is_valid(gpio))
- return;
+ panic("Provided GPIO is invalid\n");
trigger = (flags == OF_GPIO_ACTIVE_LOW);
@@ -57,6 +57,8 @@ static void gpio_halt_cb(void)
/* Probably wont return */
gpio_set_value(gpio, trigger);
+
+ panic("Halt failed\n");
}
/* This IRQ means someone pressed the power button and it is waiting for us
diff --git a/arch/powerpc/platforms/85xx/socrates.c b/arch/powerpc/platforms/85xx/socrates.c
index cd255ac..8da4ed9 100644
--- a/arch/powerpc/platforms/85xx/socrates.c
+++ b/arch/powerpc/platforms/85xx/socrates.c
@@ -91,7 +91,6 @@ define_machine(socrates) {
.setup_arch = socrates_setup_arch,
.init_IRQ = socrates_pic_init,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/stx_gp3.c b/arch/powerpc/platforms/85xx/stx_gp3.c
index 91b824c..1a1d44e 100644
--- a/arch/powerpc/platforms/85xx/stx_gp3.c
+++ b/arch/powerpc/platforms/85xx/stx_gp3.c
@@ -103,7 +103,6 @@ define_machine(stx_gp3) {
.init_IRQ = stx_gp3_pic_init,
.show_cpuinfo = stx_gp3_show_cpuinfo,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/tqm85xx.c b/arch/powerpc/platforms/85xx/tqm85xx.c
index b7c5445..9fc20a3 100644
--- a/arch/powerpc/platforms/85xx/tqm85xx.c
+++ b/arch/powerpc/platforms/85xx/tqm85xx.c
@@ -132,7 +132,6 @@ define_machine(tqm85xx) {
.init_IRQ = tqm85xx_pic_init,
.show_cpuinfo = tqm85xx_show_cpuinfo,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/twr_p102x.c b/arch/powerpc/platforms/85xx/twr_p102x.c
index 1bc02a8..360f625 100644
--- a/arch/powerpc/platforms/85xx/twr_p102x.c
+++ b/arch/powerpc/platforms/85xx/twr_p102x.c
@@ -140,7 +140,6 @@ define_machine(twr_p1025) {
.pcibios_fixup_bus = fsl_pcibios_fixup_bus,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
index cf0c70f..cd6ce84 100644
--- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c
+++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
@@ -167,7 +167,6 @@ define_machine(xes_mpc8572) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
@@ -182,7 +181,6 @@ define_machine(xes_mpc8548) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
@@ -197,7 +195,6 @@ define_machine(xes_mpc8540) {
.pcibios_fixup_phb = fsl_pcibios_fixup_phb,
#endif
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c
index ef684af..6b99300 100644
--- a/arch/powerpc/platforms/86xx/gef_ppc9a.c
+++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c
@@ -204,7 +204,6 @@ define_machine(gef_ppc9a) {
.init_IRQ = gef_ppc9a_init_irq,
.show_cpuinfo = gef_ppc9a_show_cpuinfo,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.time_init = mpc86xx_time_init,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c
index 67dd0c2..8cdeca0 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc310.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc310.c
@@ -191,7 +191,6 @@ define_machine(gef_sbc310) {
.init_IRQ = gef_sbc310_init_irq,
.show_cpuinfo = gef_sbc310_show_cpuinfo,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.time_init = mpc86xx_time_init,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c
index 8050269..da8723a 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc610.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc610.c
@@ -181,7 +181,6 @@ define_machine(gef_sbc610) {
.init_IRQ = gef_sbc610_init_irq,
.show_cpuinfo = gef_sbc610_show_cpuinfo,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.time_init = mpc86xx_time_init,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
index fef0582..a5d73fa 100644
--- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
+++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
@@ -331,7 +331,6 @@ define_machine(mpc86xx_hpcd) {
.setup_arch = mpc86xx_hpcd_setup_arch,
.init_IRQ = mpc86xx_init_irq,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.time_init = mpc86xx_time_init,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
index 5ae42a0..a0e989e 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
@@ -130,7 +130,6 @@ define_machine(mpc86xx_hpcn) {
.init_IRQ = mpc86xx_init_irq,
.show_cpuinfo = mpc86xx_hpcn_show_cpuinfo,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.time_init = mpc86xx_time_init,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
diff --git a/arch/powerpc/platforms/86xx/mvme7100.c b/arch/powerpc/platforms/86xx/mvme7100.c
index addb41e..835352e 100644
--- a/arch/powerpc/platforms/86xx/mvme7100.c
+++ b/arch/powerpc/platforms/86xx/mvme7100.c
@@ -111,7 +111,6 @@ define_machine(mvme7100) {
.setup_arch = mvme7100_setup_arch,
.init_IRQ = mpc86xx_init_irq,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.time_init = mpc86xx_time_init,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
diff --git a/arch/powerpc/platforms/86xx/sbc8641d.c b/arch/powerpc/platforms/86xx/sbc8641d.c
index 52af573..93db35d 100644
--- a/arch/powerpc/platforms/86xx/sbc8641d.c
+++ b/arch/powerpc/platforms/86xx/sbc8641d.c
@@ -82,7 +82,6 @@ define_machine(sbc8641) {
.init_IRQ = mpc86xx_init_irq,
.show_cpuinfo = sbc8641_show_cpuinfo,
.get_irq = mpic_get_irq,
- .restart = fsl_rstcr_restart,
.time_init = mpc86xx_time_init,
.calibrate_decr = generic_calibrate_decr,
.progress = udbg_progress,
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 86707e6..aa35245 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -393,7 +393,7 @@ static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
unsigned long *vpn, int count,
int psize, int ssize)
{
- unsigned long param[8];
+ unsigned long param[PLPAR_HCALL9_BUFSIZE];
int i = 0, pix = 0, rc;
unsigned long flags = 0;
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
@@ -522,7 +522,7 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
unsigned long flags = 0;
struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
- unsigned long param[9];
+ unsigned long param[PLPAR_HCALL9_BUFSIZE];
unsigned long hash, index, shift, hidx, slot;
real_pte_t pte;
int psize, ssize;
diff --git a/arch/powerpc/relocs_check.sh b/arch/powerpc/relocs_check.sh
index 2e4ebd0..ec2d5c8 100755
--- a/arch/powerpc/relocs_check.sh
+++ b/arch/powerpc/relocs_check.sh
@@ -30,6 +30,7 @@
# On PPC64:
# R_PPC64_RELATIVE, R_PPC64_NONE
# R_PPC64_ADDR64 mach_<name>
+ # R_PPC64_ADDR64 __crc_<name>
# On PPC:
# R_PPC_RELATIVE, R_PPC_ADDR16_HI,
# R_PPC_ADDR16_HA,R_PPC_ADDR16_LO,
@@ -41,7 +42,8 @@
R_PPC_ADDR16_HA
R_PPC_RELATIVE
R_PPC_NONE' |
- grep -E -v '\<R_PPC64_ADDR64[[:space:]]+mach_'
+ grep -E -v '\<R_PPC64_ADDR64[[:space:]]+mach_' |
+ grep -E -v '\<R_PPC64_ADDR64[[:space:]]+__crc_'
)
if [ -z "$bad_relocs" ]; then
diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c
index 3c0eb9b..986cd11 100644
--- a/arch/powerpc/sysdev/cpm1.c
+++ b/arch/powerpc/sysdev/cpm1.c
@@ -233,8 +233,6 @@ void __init cpm_reset(void)
else
out_be32(&siu_conf->sc_sdcr, 1);
immr_unmap(siu_conf);
-
- cpm_muram_init();
}
static DEFINE_SPINLOCK(cmd_lock);
diff --git a/arch/powerpc/sysdev/cpm2.c b/arch/powerpc/sysdev/cpm2.c
index 8dc1e24..f78ff84 100644
--- a/arch/powerpc/sysdev/cpm2.c
+++ b/arch/powerpc/sysdev/cpm2.c
@@ -66,10 +66,6 @@ void __init cpm2_reset(void)
cpm2_immr = ioremap(get_immrbase(), CPM_MAP_SIZE);
#endif
- /* Reclaim the DP memory for our use.
- */
- cpm_muram_init();
-
/* Tell everyone where the comm processor resides.
*/
cpmp = &cpm2_immr->im_cpm;
diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c
index 947f420..51bf749 100644
--- a/arch/powerpc/sysdev/cpm_common.c
+++ b/arch/powerpc/sysdev/cpm_common.c
@@ -37,6 +37,21 @@
#include <linux/of_gpio.h>
#endif
+static int __init cpm_init(void)
+{
+ struct device_node *np;
+
+ np = of_find_compatible_node(NULL, NULL, "fsl,cpm1");
+ if (!np)
+ np = of_find_compatible_node(NULL, NULL, "fsl,cpm2");
+ if (!np)
+ return -ENODEV;
+ cpm_muram_init();
+ of_node_put(np);
+ return 0;
+}
+subsys_initcall(cpm_init);
+
#ifdef CONFIG_PPC_EARLY_DEBUG_CPM
static u32 __iomem *cpm_udbg_txdesc;
static u8 __iomem *cpm_udbg_txbuf;
diff --git a/arch/powerpc/sysdev/dcr-low.S b/arch/powerpc/sysdev/dcr-low.S
index d3098ef..e687bb2 100644
--- a/arch/powerpc/sysdev/dcr-low.S
+++ b/arch/powerpc/sysdev/dcr-low.S
@@ -12,6 +12,7 @@
#include <asm/ppc_asm.h>
#include <asm/processor.h>
#include <asm/bug.h>
+#include <asm/export.h>
#define DCR_ACCESS_PROLOG(table) \
cmpli cr0,r3,1024; \
@@ -28,9 +29,11 @@
_GLOBAL(__mfdcr)
DCR_ACCESS_PROLOG(__mfdcr_table)
+EXPORT_SYMBOL(__mfdcr)
_GLOBAL(__mtdcr)
DCR_ACCESS_PROLOG(__mtdcr_table)
+EXPORT_SYMBOL(__mtdcr)
__mfdcr_table:
mfdcr r3,0; blr
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 0ef9df4..d3a5974 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -111,8 +111,7 @@ static struct pci_ops fsl_indirect_pcie_ops =
.write = indirect_write_config,
};
-#define MAX_PHYS_ADDR_BITS 40
-static u64 pci64_dma_offset = 1ull << MAX_PHYS_ADDR_BITS;
+static u64 pci64_dma_offset;
#ifdef CONFIG_SWIOTLB
static void setup_swiotlb_ops(struct pci_controller *hose)
@@ -132,12 +131,10 @@ static int fsl_pci_dma_set_mask(struct device *dev, u64 dma_mask)
return -EIO;
/*
- * Fixup PCI devices that are able to DMA to above the physical
- * address width of the SoC such that we can address any internal
- * SoC address from across PCI if needed
+ * Fix up PCI devices that are able to DMA to the large inbound
+ * mapping that allows addressing any RAM address from across PCI.
*/
- if ((dev_is_pci(dev)) &&
- dma_mask >= DMA_BIT_MASK(MAX_PHYS_ADDR_BITS)) {
+ if (dev_is_pci(dev) && dma_mask >= pci64_dma_offset * 2 - 1) {
set_dma_ops(dev, &dma_direct_ops);
set_dma_offset(dev, pci64_dma_offset);
}
@@ -387,6 +384,7 @@ static void setup_pci_atmu(struct pci_controller *hose)
mem_log++;
piwar = (piwar & ~PIWAR_SZ_MASK) | (mem_log - 1);
+ pci64_dma_offset = 1ULL << mem_log;
if (setup_inbound) {
/* Setup inbound memory window */
diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index a09ca70..d93056e 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -29,6 +29,7 @@
#include <linux/fsl_devices.h>
#include <linux/fs_enet_pd.h>
#include <linux/fs_uart_pd.h>
+#include <linux/reboot.h>
#include <linux/atomic.h>
#include <asm/io.h>
@@ -180,23 +181,38 @@ EXPORT_SYMBOL(get_baudrate);
#if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx)
static __be32 __iomem *rstcr;
+static int fsl_rstcr_restart(struct notifier_block *this,
+ unsigned long mode, void *cmd)
+{
+ local_irq_disable();
+ /* set reset control register */
+ out_be32(rstcr, 0x2); /* HRESET_REQ */
+
+ return NOTIFY_DONE;
+}
+
static int __init setup_rstcr(void)
{
struct device_node *np;
+ static struct notifier_block restart_handler = {
+ .notifier_call = fsl_rstcr_restart,
+ .priority = 128,
+ };
+
for_each_node_by_name(np, "global-utilities") {
if ((of_get_property(np, "fsl,has-rstcr", NULL))) {
rstcr = of_iomap(np, 0) + 0xb0;
- if (!rstcr)
+ if (!rstcr) {
printk (KERN_ERR "Error: reset control "
"register not mapped!\n");
+ } else {
+ register_restart_handler(&restart_handler);
+ }
break;
}
}
- if (!rstcr && ppc_md.restart == fsl_rstcr_restart)
- printk(KERN_ERR "No RSTCR register, warm reboot won't work\n");
-
of_node_put(np);
return 0;
@@ -204,15 +220,6 @@ static int __init setup_rstcr(void)
arch_initcall(setup_rstcr);
-void __noreturn fsl_rstcr_restart(char *cmd)
-{
- local_irq_disable();
- if (rstcr)
- /* set reset control register */
- out_be32(rstcr, 0x2); /* HRESET_REQ */
-
- while (1) ;
-}
#endif
#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
diff --git a/arch/powerpc/sysdev/fsl_soc.h b/arch/powerpc/sysdev/fsl_soc.h
index 433566a..d73daa4 100644
--- a/arch/powerpc/sysdev/fsl_soc.h
+++ b/arch/powerpc/sysdev/fsl_soc.h
@@ -19,8 +19,6 @@ extern u32 fsl_get_sys_freq(void);
struct spi_board_info;
struct device_node;
-extern void __noreturn fsl_rstcr_restart(char *cmd);
-
/* The different ports that the DIU can be connected to */
enum fsl_diu_monitor_port {
FSL_DIU_PORT_DVI, /* DVI */
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 4d48cec..b9aac95 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -1249,7 +1249,7 @@ struct mpic * __init mpic_alloc(struct device_node *node,
/* Pick the physical address from the device tree if unspecified */
if (!phys_addr) {
/* Check if it is DCR-based */
- if (of_get_property(node, "dcr-reg", NULL)) {
+ if (of_property_read_bool(node, "dcr-reg")) {
flags |= MPIC_USES_DCR;
} else {
struct resource r;
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index 28f03ca..794bebb 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -363,11 +363,11 @@ static void *diag204_store(void)
static int diag224_get_name_table(void)
{
/* memory must be below 2GB */
- diag224_cpu_names = kmalloc(PAGE_SIZE, GFP_KERNEL | GFP_DMA);
+ diag224_cpu_names = (char *) __get_free_page(GFP_KERNEL | GFP_DMA);
if (!diag224_cpu_names)
return -ENOMEM;
if (diag224(diag224_cpu_names)) {
- kfree(diag224_cpu_names);
+ free_page((unsigned long) diag224_cpu_names);
return -EOPNOTSUPP;
}
EBCASC(diag224_cpu_names + 16, (*diag224_cpu_names + 1) * 16);
@@ -376,7 +376,7 @@ static int diag224_get_name_table(void)
static void diag224_delete_name_table(void)
{
- kfree(diag224_cpu_names);
+ free_page((unsigned long) diag224_cpu_names);
}
static int diag224_idx2name(int index, char *name)
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 9043d2e..20f196b 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -1,6 +1,7 @@
generic-y += clkdev.h
+generic-y += export.h
generic-y += irq_work.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index 64053d9..836c562 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -12,9 +12,7 @@
#ifndef __ASSEMBLY__
-unsigned long return_address(int depth);
-
-#define ftrace_return_address(n) return_address(n)
+#define ftrace_return_address(n) __builtin_return_address(n)
void _mcount(void);
void ftrace_caller(void);
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 0332317..602af69 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -192,7 +192,7 @@ struct task_struct;
struct mm_struct;
struct seq_file;
-typedef int (*dump_trace_func_t)(void *data, unsigned long address);
+typedef int (*dump_trace_func_t)(void *data, unsigned long address, int reliable);
void dump_trace(dump_trace_func_t func, void *data,
struct task_struct *task, unsigned long sp);
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 02613ba..3066031 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -9,6 +9,9 @@
#include <uapi/asm/unistd.h>
#define __IGNORE_time
+#define __IGNORE_pkey_mprotect
+#define __IGNORE_pkey_alloc
+#define __IGNORE_pkey_free
#define __ARCH_WANT_OLD_READDIR
#define __ARCH_WANT_SYS_ALARM
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 72ccc41..1f0fe98 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -61,7 +61,7 @@
extra-y += head.o head64.o vmlinux.lds
-obj-$(CONFIG_MODULES) += s390_ksyms.o module.o
+obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_SCHED_TOPOLOGY) += topology.o
obj-$(CONFIG_HIBERNATION) += suspend.o swsusp.o
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 43446fa..c74c592 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -2014,12 +2014,12 @@ void show_code(struct pt_regs *regs)
*ptr++ = '\t';
ptr += print_insn(ptr, code + start, addr);
start += opsize;
- printk("%s", buffer);
+ pr_cont("%s", buffer);
ptr = buffer;
ptr += sprintf(ptr, "\n ");
hops++;
}
- printk("\n");
+ pr_cont("\n");
}
void print_fn_code(unsigned char *code, unsigned long len)
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 6693383..55d4fe1 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -38,10 +38,10 @@ __dump_trace(dump_trace_func_t func, void *data, unsigned long sp,
if (sp < low || sp > high - sizeof(*sf))
return sp;
sf = (struct stack_frame *) sp;
+ if (func(data, sf->gprs[8], 0))
+ return sp;
/* Follow the backchain. */
while (1) {
- if (func(data, sf->gprs[8]))
- return sp;
low = sp;
sp = sf->back_chain;
if (!sp)
@@ -49,6 +49,8 @@ __dump_trace(dump_trace_func_t func, void *data, unsigned long sp,
if (sp <= low || sp > high - sizeof(*sf))
return sp;
sf = (struct stack_frame *) sp;
+ if (func(data, sf->gprs[8], 1))
+ return sp;
}
/* Zero backchain detected, check for interrupt frame. */
sp = (unsigned long) (sf + 1);
@@ -56,7 +58,7 @@ __dump_trace(dump_trace_func_t func, void *data, unsigned long sp,
return sp;
regs = (struct pt_regs *) sp;
if (!user_mode(regs)) {
- if (func(data, regs->psw.addr))
+ if (func(data, regs->psw.addr, 1))
return sp;
}
low = sp;
@@ -85,33 +87,12 @@ void dump_trace(dump_trace_func_t func, void *data, struct task_struct *task,
}
EXPORT_SYMBOL_GPL(dump_trace);
-struct return_address_data {
- unsigned long address;
- int depth;
-};
-
-static int __return_address(void *data, unsigned long address)
+static int show_address(void *data, unsigned long address, int reliable)
{
- struct return_address_data *rd = data;
-
- if (rd->depth--)
- return 0;
- rd->address = address;
- return 1;
-}
-
-unsigned long return_address(int depth)
-{
- struct return_address_data rd = { .depth = depth + 2 };
-
- dump_trace(__return_address, &rd, NULL, current_stack_pointer());
- return rd.address;
-}
-EXPORT_SYMBOL_GPL(return_address);
-
-static int show_address(void *data, unsigned long address)
-{
- printk("([<%016lx>] %pSR)\n", address, (void *)address);
+ if (reliable)
+ printk(" [<%016lx>] %pSR \n", address, (void *)address);
+ else
+ printk("([<%016lx>] %pSR)\n", address, (void *)address);
return 0;
}
@@ -138,14 +119,14 @@ void show_stack(struct task_struct *task, unsigned long *sp)
else
stack = (unsigned long *)task->thread.ksp;
}
+ printk(KERN_DEFAULT "Stack:\n");
for (i = 0; i < 20; i++) {
if (((addr_t) stack & (THREAD_SIZE-1)) == 0)
break;
- if ((i * sizeof(long) % 32) == 0)
- printk("%s ", i == 0 ? "" : "\n");
- printk("%016lx ", *stack++);
+ if (i % 4 == 0)
+ printk(KERN_DEFAULT " ");
+ pr_cont("%016lx%c", *stack++, i % 4 == 3 ? '\n' : ' ');
}
- printk("\n");
show_trace(task, (unsigned long)sp);
}
@@ -163,13 +144,13 @@ void show_registers(struct pt_regs *regs)
mode = user_mode(regs) ? "User" : "Krnl";
printk("%s PSW : %p %p", mode, (void *)regs->psw.mask, (void *)regs->psw.addr);
if (!user_mode(regs))
- printk(" (%pSR)", (void *)regs->psw.addr);
- printk("\n");
+ pr_cont(" (%pSR)", (void *)regs->psw.addr);
+ pr_cont("\n");
printk(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x "
"P:%x AS:%x CC:%x PM:%x", psw->r, psw->t, psw->i, psw->e,
psw->key, psw->m, psw->w, psw->p, psw->as, psw->cc, psw->pm);
- printk(" RI:%x EA:%x", psw->ri, psw->eaba);
- printk("\n%s GPRS: %016lx %016lx %016lx %016lx\n", mode,
+ pr_cont(" RI:%x EA:%x\n", psw->ri, psw->eaba);
+ printk("%s GPRS: %016lx %016lx %016lx %016lx\n", mode,
regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]);
printk(" %016lx %016lx %016lx %016lx\n",
regs->gprs[4], regs->gprs[5], regs->gprs[6], regs->gprs[7]);
@@ -205,14 +186,14 @@ void die(struct pt_regs *regs, const char *str)
printk("%s: %04x ilc:%d [#%d] ", str, regs->int_code & 0xffff,
regs->int_code >> 17, ++die_counter);
#ifdef CONFIG_PREEMPT
- printk("PREEMPT ");
+ pr_cont("PREEMPT ");
#endif
#ifdef CONFIG_SMP
- printk("SMP ");
+ pr_cont("SMP ");
#endif
if (debug_pagealloc_enabled())
- printk("DEBUG_PAGEALLOC");
- printk("\n");
+ pr_cont("DEBUG_PAGEALLOC");
+ pr_cont("\n");
notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV);
print_modules();
show_regs(regs);
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index c51650a..49a3073 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -23,6 +23,7 @@
#include <asm/vx-insn.h>
#include <asm/setup.h>
#include <asm/nmi.h>
+#include <asm/export.h>
__PT_R0 = __PT_GPRS
__PT_R1 = __PT_GPRS + 8
@@ -259,6 +260,8 @@
EX_TABLE(.Lrewind_pad,.Lsie_fault)
EX_TABLE(sie_exit,.Lsie_fault)
+EXPORT_SYMBOL(sie64a)
+EXPORT_SYMBOL(sie_exit)
#endif
/*
@@ -825,6 +828,9 @@
oi __LC_CPU_FLAGS+7,_CIF_FPU
br %r14
.Lsave_fpu_regs_end:
+#if IS_ENABLED(CONFIG_KVM)
+EXPORT_SYMBOL(save_fpu_regs)
+#endif
/*
* Load floating-point controls and floating-point or vector registers.
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index e499370..9a17e44 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -9,6 +9,7 @@
#include <asm/asm-offsets.h>
#include <asm/ftrace.h>
#include <asm/ptrace.h>
+#include <asm/export.h>
.section .kprobes.text, "ax"
@@ -23,6 +24,8 @@
ENTRY(_mcount)
br %r14
+EXPORT_SYMBOL(_mcount)
+
ENTRY(ftrace_caller)
.globl ftrace_regs_caller
.set ftrace_regs_caller,ftrace_caller
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 17431f6..955a7b6 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -222,7 +222,7 @@ static int __init service_level_perf_register(void)
}
arch_initcall(service_level_perf_register);
-static int __perf_callchain_kernel(void *data, unsigned long address)
+static int __perf_callchain_kernel(void *data, unsigned long address, int reliable)
{
struct perf_callchain_entry_ctx *entry = data;
diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c
deleted file mode 100644
index e67453b..0000000
--- a/arch/s390/kernel/s390_ksyms.c
+++ /dev/null
@@ -1,15 +0,0 @@
-#include <linux/module.h>
-#include <linux/kvm_host.h>
-#include <asm/fpu/api.h>
-#include <asm/ftrace.h>
-
-#ifdef CONFIG_FUNCTION_TRACER
-EXPORT_SYMBOL(_mcount);
-#endif
-#if IS_ENABLED(CONFIG_KVM)
-EXPORT_SYMBOL(sie64a);
-EXPORT_SYMBOL(sie_exit);
-EXPORT_SYMBOL(save_fpu_regs);
-#endif
-EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(memset);
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index 44f84b2..355db9d 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -27,12 +27,12 @@ static int __save_address(void *data, unsigned long address, int nosched)
return 1;
}
-static int save_address(void *data, unsigned long address)
+static int save_address(void *data, unsigned long address, int reliable)
{
return __save_address(data, address, 0);
}
-static int save_address_nosched(void *data, unsigned long address)
+static int save_address_nosched(void *data, unsigned long address, int reliable)
{
return __save_address(data, address, 1);
}
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 000e6e91..3667d20 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -62,9 +62,11 @@
. = ALIGN(PAGE_SIZE);
__start_ro_after_init = .;
+ __start_data_ro_after_init = .;
.data..ro_after_init : {
*(.data..ro_after_init)
}
+ __end_data_ro_after_init = .;
EXCEPTION_TABLE(16)
. = ALIGN(PAGE_SIZE);
__end_ro_after_init = .;
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 1cab8a1..7a27eeb 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -119,8 +119,13 @@ static int handle_validity(struct kvm_vcpu *vcpu)
vcpu->stat.exit_validity++;
trace_kvm_s390_intercept_validity(vcpu, viwhy);
- WARN_ONCE(true, "kvm: unhandled validity intercept 0x%x\n", viwhy);
- return -EOPNOTSUPP;
+ KVM_EVENT(3, "validity intercept 0x%x for pid %u (kvm 0x%pK)", viwhy,
+ current->pid, vcpu->kvm);
+
+ /* do not warn on invalid runtime instrumentation mode */
+ WARN_ONCE(viwhy != 0x44, "kvm: unhandled validity intercept 0x%x\n",
+ viwhy);
+ return -EINVAL;
}
static int handle_instruction(struct kvm_vcpu *vcpu)
diff --git a/arch/s390/kvm/sthyi.c b/arch/s390/kvm/sthyi.c
index bd98b7d..05c98bb 100644
--- a/arch/s390/kvm/sthyi.c
+++ b/arch/s390/kvm/sthyi.c
@@ -315,7 +315,7 @@ static void fill_diag(struct sthyi_sctns *sctns)
if (r < 0)
goto out;
- diag224_buf = kmalloc(PAGE_SIZE, GFP_KERNEL | GFP_DMA);
+ diag224_buf = (void *)__get_free_page(GFP_KERNEL | GFP_DMA);
if (!diag224_buf || diag224(diag224_buf))
goto out;
@@ -378,7 +378,7 @@ static void fill_diag(struct sthyi_sctns *sctns)
sctns->par.infpval1 |= PAR_WGHT_VLD;
out:
- kfree(diag224_buf);
+ free_page((unsigned long)diag224_buf);
vfree(diag204_buf);
}
diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index c6d553e..be9fa65 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -5,6 +5,7 @@
*/
#include <linux/linkage.h>
+#include <asm/export.h>
/*
* memset implementation
@@ -60,6 +61,7 @@
xc 0(1,%r1),0(%r1)
.Lmemset_mvc:
mvc 1(1,%r1),0(%r1)
+EXPORT_SYMBOL(memset)
/*
* memcpy implementation
@@ -86,3 +88,4 @@
j .Lmemcpy_rest
.Lmemcpy_mvc:
mvc 0(1,%r1),0(%r3)
+EXPORT_SYMBOL(memcpy)
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index adb0c34..18d4107e 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -266,7 +266,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
/* Try to get the remaining pages with get_user_pages */
start += nr << PAGE_SHIFT;
pages += nr;
- ret = get_user_pages_unlocked(start, nr_pages - nr, write, 0, pages);
+ ret = get_user_pages_unlocked(start, nr_pages - nr, pages,
+ write ? FOLL_WRITE : 0);
/* Have to be a bit careful with return values */
if (nr > 0)
ret = (ret < 0) ? nr : ret + nr;
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index cd404aa..4a0c5bc 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -217,6 +217,7 @@ static __init int setup_hugepagesz(char *opt)
} else if (MACHINE_HAS_EDAT2 && size == PUD_SIZE) {
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
} else {
+ hugetlb_bad_size();
pr_err("hugepagesz= specifies an unsupported page size %s\n",
string);
return 0;
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index f56a39b..b3e9d18 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -151,36 +151,40 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
#ifdef CONFIG_MEMORY_HOTPLUG
int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
{
- unsigned long normal_end_pfn = PFN_DOWN(memblock_end_of_DRAM());
- unsigned long dma_end_pfn = PFN_DOWN(MAX_DMA_ADDRESS);
+ unsigned long zone_start_pfn, zone_end_pfn, nr_pages;
unsigned long start_pfn = PFN_DOWN(start);
unsigned long size_pages = PFN_DOWN(size);
- unsigned long nr_pages;
- int rc, zone_enum;
+ pg_data_t *pgdat = NODE_DATA(nid);
+ struct zone *zone;
+ int rc, i;
rc = vmem_add_mapping(start, size);
if (rc)
return rc;
- while (size_pages > 0) {
- if (start_pfn < dma_end_pfn) {
- nr_pages = (start_pfn + size_pages > dma_end_pfn) ?
- dma_end_pfn - start_pfn : size_pages;
- zone_enum = ZONE_DMA;
- } else if (start_pfn < normal_end_pfn) {
- nr_pages = (start_pfn + size_pages > normal_end_pfn) ?
- normal_end_pfn - start_pfn : size_pages;
- zone_enum = ZONE_NORMAL;
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ zone = pgdat->node_zones + i;
+ if (zone_idx(zone) != ZONE_MOVABLE) {
+ /* Add range within existing zone limits, if possible */
+ zone_start_pfn = zone->zone_start_pfn;
+ zone_end_pfn = zone->zone_start_pfn +
+ zone->spanned_pages;
} else {
- nr_pages = size_pages;
- zone_enum = ZONE_MOVABLE;
+ /* Add remaining range to ZONE_MOVABLE */
+ zone_start_pfn = start_pfn;
+ zone_end_pfn = start_pfn + size_pages;
}
- rc = __add_pages(nid, NODE_DATA(nid)->node_zones + zone_enum,
- start_pfn, size_pages);
+ if (start_pfn < zone_start_pfn || start_pfn >= zone_end_pfn)
+ continue;
+ nr_pages = (start_pfn + size_pages > zone_end_pfn) ?
+ zone_end_pfn - start_pfn : size_pages;
+ rc = __add_pages(nid, zone, start_pfn, nr_pages);
if (rc)
break;
start_pfn += nr_pages;
size_pages -= nr_pages;
+ if (!size_pages)
+ break;
}
if (rc)
vmem_remove_mapping(start, size);
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 16f4c39..9a4de45 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -13,7 +13,7 @@
#include <linux/init.h>
#include <asm/processor.h>
-static int __s390_backtrace(void *data, unsigned long address)
+static int __s390_backtrace(void *data, unsigned long address, int reliable)
{
unsigned int *depth = data;
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 7350c8b..6b2f72f 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -423,7 +423,7 @@ static int __s390_dma_map_sg(struct device *dev, struct scatterlist *sg,
dma_addr_t dma_addr_base, dma_addr;
int flags = ZPCI_PTE_VALID;
struct scatterlist *s;
- unsigned long pa;
+ unsigned long pa = 0;
int ret;
size = PAGE_ALIGN(size);
diff --git a/arch/score/kernel/ptrace.c b/arch/score/kernel/ptrace.c
index 5583618..4f7314d 100644
--- a/arch/score/kernel/ptrace.c
+++ b/arch/score/kernel/ptrace.c
@@ -131,7 +131,7 @@ read_tsk_long(struct task_struct *child,
{
int copied;
- copied = access_process_vm(child, addr, res, sizeof(*res), 0);
+ copied = access_process_vm(child, addr, res, sizeof(*res), FOLL_FORCE);
return copied != sizeof(*res) ? -EIO : 0;
}
@@ -142,7 +142,7 @@ read_tsk_short(struct task_struct *child,
{
int copied;
- copied = access_process_vm(child, addr, res, sizeof(*res), 0);
+ copied = access_process_vm(child, addr, res, sizeof(*res), FOLL_FORCE);
return copied != sizeof(*res) ? -EIO : 0;
}
@@ -153,7 +153,8 @@ write_tsk_short(struct task_struct *child,
{
int copied;
- copied = access_process_vm(child, addr, &val, sizeof(val), 1);
+ copied = access_process_vm(child, addr, &val, sizeof(val),
+ FOLL_FORCE | FOLL_WRITE);
return copied != sizeof(val) ? -EIO : 0;
}
@@ -164,7 +165,8 @@ write_tsk_long(struct task_struct *child,
{
int copied;
- copied = access_process_vm(child, addr, &val, sizeof(val), 1);
+ copied = access_process_vm(child, addr, &val, sizeof(val),
+ FOLL_FORCE | FOLL_WRITE);
return copied != sizeof(val) ? -EIO : 0;
}
diff --git a/arch/score/kernel/traps.c b/arch/score/kernel/traps.c
index 1517a7d..5cea1e7 100644
--- a/arch/score/kernel/traps.c
+++ b/arch/score/kernel/traps.c
@@ -29,6 +29,7 @@
#include <asm/cacheflush.h>
#include <asm/irq.h>
#include <asm/irq_regs.h>
+#include <asm/uaccess.h>
unsigned long exception_handlers[32];
diff --git a/arch/sh/Makefile b/arch/sh/Makefile
index 0047666..336f33a 100644
--- a/arch/sh/Makefile
+++ b/arch/sh/Makefile
@@ -31,7 +31,7 @@
endif
cflags-$(CONFIG_CPU_SH2) := $(call cc-option,-m2,)
-cflags-$(CONFIG_CPU_J2) := $(call cc-option,-mj2,)
+cflags-$(CONFIG_CPU_J2) += $(call cc-option,-mj2,)
cflags-$(CONFIG_CPU_SH2A) += $(call cc-option,-m2a,) \
$(call cc-option,-m2a-nofpu,) \
$(call cc-option,-m4-nofpu,)
diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig
index e9c2c42..4e21949 100644
--- a/arch/sh/boards/Kconfig
+++ b/arch/sh/boards/Kconfig
@@ -22,6 +22,16 @@
have sufficient driver coverage to use this option; do not
select it if you are using original SuperH hardware.
+config SH_JCORE_SOC
+ bool "J-Core SoC"
+ depends on SH_DEVICE_TREE && (CPU_SH2 || CPU_J2)
+ select CLKSRC_JCORE_PIT
+ select JCORE_AIC
+ default y if CPU_J2
+ help
+ Select this option to include drivers core components of the
+ J-Core SoC, including interrupt controllers and timers.
+
config SH_SOLUTION_ENGINE
bool "SolutionEngine"
select SOLUTION_ENGINE
diff --git a/arch/sh/configs/j2_defconfig b/arch/sh/configs/j2_defconfig
index 94d1eca..2eb81ebe 100644
--- a/arch/sh/configs/j2_defconfig
+++ b/arch/sh/configs/j2_defconfig
@@ -8,6 +8,7 @@
CONFIG_MEMORY_SIZE=0x04000000
CONFIG_CPU_BIG_ENDIAN=y
CONFIG_SH_DEVICE_TREE=y
+CONFIG_SH_JCORE_SOC=y
CONFIG_HZ_100=y
CONFIG_CMDLINE_OVERWRITE=y
CONFIG_CMDLINE="console=ttyUL0 earlycon"
@@ -20,6 +21,7 @@
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
CONFIG_NETDEVICES=y
+CONFIG_SERIAL_EARLYCON=y
CONFIG_SERIAL_UARTLITE=y
CONFIG_SERIAL_UARTLITE_CONSOLE=y
CONFIG_I2C=y
diff --git a/arch/sh/mm/gup.c b/arch/sh/mm/gup.c
index 40fa6c8..063c298 100644
--- a/arch/sh/mm/gup.c
+++ b/arch/sh/mm/gup.c
@@ -258,7 +258,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
pages += nr;
ret = get_user_pages_unlocked(start,
- (end - start) >> PAGE_SHIFT, write, 0, pages);
+ (end - start) >> PAGE_SHIFT, pages,
+ write ? FOLL_WRITE : 0);
/* Have to be a bit careful with return values */
if (nr > 0) {
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index 6024c26..cfc9180 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -6,6 +6,7 @@
generic-y += div64.h
generic-y += emergency-restart.h
generic-y += exec.h
+generic-y += export.h
generic-y += irq_regs.h
generic-y += irq_work.h
generic-y += linkage.h
diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h
index a6cfdab..5b0ed48 100644
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@@ -24,9 +24,10 @@ typedef struct {
unsigned int icache_line_size;
unsigned int ecache_size;
unsigned int ecache_line_size;
- unsigned short sock_id;
+ unsigned short sock_id; /* physical package */
unsigned short core_id;
- int proc_id;
+ unsigned short max_cache_id; /* groupings of highest shared cache */
+ unsigned short proc_id; /* strand (aka HW thread) id */
} cpuinfo_sparc;
DECLARE_PER_CPU(cpuinfo_sparc, __cpu_data);
diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h
index d9c5876..8011e79 100644
--- a/arch/sparc/include/asm/spinlock_32.h
+++ b/arch/sparc/include/asm/spinlock_32.h
@@ -134,7 +134,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
*(volatile __u32 *)&lp->lock = ~0U;
}
-static void inline arch_write_unlock(arch_rwlock_t *lock)
+static inline void arch_write_unlock(arch_rwlock_t *lock)
{
__asm__ __volatile__(
" st %%g0, [%0]"
diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h
index 87990b7..07c9f2e 100644
--- a/arch/sparc/include/asm/spinlock_64.h
+++ b/arch/sparc/include/asm/spinlock_64.h
@@ -96,7 +96,7 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long fla
/* Multi-reader locks, these are much saner than the 32-bit Sparc ones... */
-static void inline arch_read_lock(arch_rwlock_t *lock)
+static inline void arch_read_lock(arch_rwlock_t *lock)
{
unsigned long tmp1, tmp2;
@@ -119,7 +119,7 @@ static void inline arch_read_lock(arch_rwlock_t *lock)
: "memory");
}
-static int inline arch_read_trylock(arch_rwlock_t *lock)
+static inline int arch_read_trylock(arch_rwlock_t *lock)
{
int tmp1, tmp2;
@@ -140,7 +140,7 @@ static int inline arch_read_trylock(arch_rwlock_t *lock)
return tmp1;
}
-static void inline arch_read_unlock(arch_rwlock_t *lock)
+static inline void arch_read_unlock(arch_rwlock_t *lock)
{
unsigned long tmp1, tmp2;
@@ -156,7 +156,7 @@ static void inline arch_read_unlock(arch_rwlock_t *lock)
: "memory");
}
-static void inline arch_write_lock(arch_rwlock_t *lock)
+static inline void arch_write_lock(arch_rwlock_t *lock)
{
unsigned long mask, tmp1, tmp2;
@@ -181,7 +181,7 @@ static void inline arch_write_lock(arch_rwlock_t *lock)
: "memory");
}
-static void inline arch_write_unlock(arch_rwlock_t *lock)
+static inline void arch_write_unlock(arch_rwlock_t *lock)
{
__asm__ __volatile__(
" stw %%g0, [%0]"
@@ -190,7 +190,7 @@ static void inline arch_write_unlock(arch_rwlock_t *lock)
: "memory");
}
-static int inline arch_write_trylock(arch_rwlock_t *lock)
+static inline int arch_write_trylock(arch_rwlock_t *lock)
{
unsigned long mask, tmp1, tmp2, result;
diff --git a/arch/sparc/include/asm/string.h b/arch/sparc/include/asm/string.h
index 98b72a0..86f34be 100644
--- a/arch/sparc/include/asm/string.h
+++ b/arch/sparc/include/asm/string.h
@@ -5,4 +5,38 @@
#else
#include <asm/string_32.h>
#endif
+
+/* First the mem*() things. */
+#define __HAVE_ARCH_MEMMOVE
+void *memmove(void *, const void *, __kernel_size_t);
+
+#define __HAVE_ARCH_MEMCPY
+#define memcpy(t, f, n) __builtin_memcpy(t, f, n)
+
+#define __HAVE_ARCH_MEMSET
+#define memset(s, c, count) __builtin_memset(s, c, count)
+
+#define __HAVE_ARCH_MEMSCAN
+
+#define memscan(__arg0, __char, __arg2) \
+({ \
+ void *__memscan_zero(void *, size_t); \
+ void *__memscan_generic(void *, int, size_t); \
+ void *__retval, *__addr = (__arg0); \
+ size_t __size = (__arg2); \
+ \
+ if(__builtin_constant_p(__char) && !(__char)) \
+ __retval = __memscan_zero(__addr, __size); \
+ else \
+ __retval = __memscan_generic(__addr, (__char), __size); \
+ \
+ __retval; \
+})
+
+#define __HAVE_ARCH_MEMCMP
+int memcmp(const void *,const void *,__kernel_size_t);
+
+#define __HAVE_ARCH_STRNCMP
+int strncmp(const char *, const char *, __kernel_size_t);
+
#endif
diff --git a/arch/sparc/include/asm/string_32.h b/arch/sparc/include/asm/string_32.h
index 69974e9..6494124 100644
--- a/arch/sparc/include/asm/string_32.h
+++ b/arch/sparc/include/asm/string_32.h
@@ -11,60 +11,4 @@
#include <asm/page.h>
-/* Really, userland/ksyms should not see any of this stuff. */
-
-#ifdef __KERNEL__
-
-void __memmove(void *,const void *,__kernel_size_t);
-
-#ifndef EXPORT_SYMTAB_STROPS
-
-/* First the mem*() things. */
-#define __HAVE_ARCH_MEMMOVE
-#undef memmove
-#define memmove(_to, _from, _n) \
-({ \
- void *_t = (_to); \
- __memmove(_t, (_from), (_n)); \
- _t; \
-})
-
-#define __HAVE_ARCH_MEMCPY
-#define memcpy(t, f, n) __builtin_memcpy(t, f, n)
-
-#define __HAVE_ARCH_MEMSET
-#define memset(s, c, count) __builtin_memset(s, c, count)
-
-#define __HAVE_ARCH_MEMSCAN
-
-#undef memscan
-#define memscan(__arg0, __char, __arg2) \
-({ \
- void *__memscan_zero(void *, size_t); \
- void *__memscan_generic(void *, int, size_t); \
- void *__retval, *__addr = (__arg0); \
- size_t __size = (__arg2); \
- \
- if(__builtin_constant_p(__char) && !(__char)) \
- __retval = __memscan_zero(__addr, __size); \
- else \
- __retval = __memscan_generic(__addr, (__char), __size); \
- \
- __retval; \
-})
-
-#define __HAVE_ARCH_MEMCMP
-int memcmp(const void *,const void *,__kernel_size_t);
-
-/* Now the str*() stuff... */
-#define __HAVE_ARCH_STRLEN
-__kernel_size_t strlen(const char *);
-
-#define __HAVE_ARCH_STRNCMP
-int strncmp(const char *, const char *, __kernel_size_t);
-
-#endif /* !EXPORT_SYMTAB_STROPS */
-
-#endif /* __KERNEL__ */
-
#endif /* !(__SPARC_STRING_H__) */
diff --git a/arch/sparc/include/asm/string_64.h b/arch/sparc/include/asm/string_64.h
index 5936b8f..6b9ccb3 100644
--- a/arch/sparc/include/asm/string_64.h
+++ b/arch/sparc/include/asm/string_64.h
@@ -9,54 +9,10 @@
#ifndef __SPARC64_STRING_H__
#define __SPARC64_STRING_H__
-/* Really, userland/ksyms should not see any of this stuff. */
-
-#ifdef __KERNEL__
-
#include <asm/asi.h>
-#ifndef EXPORT_SYMTAB_STROPS
-
-/* First the mem*() things. */
-#define __HAVE_ARCH_MEMMOVE
-void *memmove(void *, const void *, __kernel_size_t);
-
-#define __HAVE_ARCH_MEMCPY
-#define memcpy(t, f, n) __builtin_memcpy(t, f, n)
-
-#define __HAVE_ARCH_MEMSET
-#define memset(s, c, count) __builtin_memset(s, c, count)
-
-#define __HAVE_ARCH_MEMSCAN
-
-#undef memscan
-#define memscan(__arg0, __char, __arg2) \
-({ \
- void *__memscan_zero(void *, size_t); \
- void *__memscan_generic(void *, int, size_t); \
- void *__retval, *__addr = (__arg0); \
- size_t __size = (__arg2); \
- \
- if(__builtin_constant_p(__char) && !(__char)) \
- __retval = __memscan_zero(__addr, __size); \
- else \
- __retval = __memscan_generic(__addr, (__char), __size); \
- \
- __retval; \
-})
-
-#define __HAVE_ARCH_MEMCMP
-int memcmp(const void *,const void *,__kernel_size_t);
-
/* Now the str*() stuff... */
#define __HAVE_ARCH_STRLEN
__kernel_size_t strlen(const char *);
-#define __HAVE_ARCH_STRNCMP
-int strncmp(const char *, const char *, __kernel_size_t);
-
-#endif /* !EXPORT_SYMTAB_STROPS */
-
-#endif /* __KERNEL__ */
-
#endif /* !(__SPARC64_STRING_H__) */
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index bec481a..7b4898a 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -44,14 +44,20 @@ int __node_distance(int, int);
#define topology_physical_package_id(cpu) (cpu_data(cpu).proc_id)
#define topology_core_id(cpu) (cpu_data(cpu).core_id)
#define topology_core_cpumask(cpu) (&cpu_core_sib_map[cpu])
+#define topology_core_cache_cpumask(cpu) (&cpu_core_sib_cache_map[cpu])
#define topology_sibling_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu))
#endif /* CONFIG_SMP */
extern cpumask_t cpu_core_map[NR_CPUS];
extern cpumask_t cpu_core_sib_map[NR_CPUS];
+extern cpumask_t cpu_core_sib_cache_map[NR_CPUS];
+
+/**
+ * Return cores that shares the last level cache.
+ */
static inline const struct cpumask *cpu_coregroup_mask(int cpu)
{
- return &cpu_core_map[cpu];
+ return &cpu_core_sib_cache_map[cpu];
}
#endif /* _ASM_SPARC64_TOPOLOGY_H */
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index b68acc5..5373136 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -82,7 +82,6 @@ static inline int access_ok(int type, const void __user * addr, unsigned long si
return 1;
}
-void __ret_efault(void);
void __retl_efault(void);
/* Uh, these should become the main single-value transfer routines..
@@ -189,55 +188,34 @@ int __get_user_bad(void);
unsigned long __must_check ___copy_from_user(void *to,
const void __user *from,
unsigned long size);
-unsigned long copy_from_user_fixup(void *to, const void __user *from,
- unsigned long size);
static inline unsigned long __must_check
copy_from_user(void *to, const void __user *from, unsigned long size)
{
- unsigned long ret;
-
check_object_size(to, size, false);
- ret = ___copy_from_user(to, from, size);
- if (unlikely(ret))
- ret = copy_from_user_fixup(to, from, size);
-
- return ret;
+ return ___copy_from_user(to, from, size);
}
#define __copy_from_user copy_from_user
unsigned long __must_check ___copy_to_user(void __user *to,
const void *from,
unsigned long size);
-unsigned long copy_to_user_fixup(void __user *to, const void *from,
- unsigned long size);
static inline unsigned long __must_check
copy_to_user(void __user *to, const void *from, unsigned long size)
{
- unsigned long ret;
-
check_object_size(from, size, true);
- ret = ___copy_to_user(to, from, size);
- if (unlikely(ret))
- ret = copy_to_user_fixup(to, from, size);
- return ret;
+ return ___copy_to_user(to, from, size);
}
#define __copy_to_user copy_to_user
unsigned long __must_check ___copy_in_user(void __user *to,
const void __user *from,
unsigned long size);
-unsigned long copy_in_user_fixup(void __user *to, void __user *from,
- unsigned long size);
static inline unsigned long __must_check
copy_in_user(void __user *to, void __user *from, unsigned long size)
{
- unsigned long ret = ___copy_in_user(to, from, size);
-
- if (unlikely(ret))
- ret = copy_in_user_fixup(to, from, size);
- return ret;
+ return ___copy_in_user(to, from, size);
}
#define __copy_in_user copy_in_user
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index fdb1332..fa3c02d 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -86,7 +86,7 @@
obj-$(CONFIG_SUN_PM) += apc.o pmc.o
obj-$(CONFIG_MODULES) += module.o
-obj-$(CONFIG_MODULES) += sparc_ksyms_$(BITS).o
+obj-$(CONFIG_MODULES) += sparc_ksyms.o
obj-$(CONFIG_SPARC_LED) += led.o
obj-$(CONFIG_KGDB) += kgdb_$(BITS).o
diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S
index 07918ab..d85bdb9 100644
--- a/arch/sparc/kernel/entry.S
+++ b/arch/sparc/kernel/entry.S
@@ -29,6 +29,7 @@
#include <asm/unistd.h>
#include <asm/asmmacro.h>
+#include <asm/export.h>
#define curptr g6
@@ -1207,6 +1208,8 @@
ret
restore
+EXPORT_SYMBOL(__udelay)
+EXPORT_SYMBOL(__ndelay)
/* Handle a software breakpoint */
/* We have to inform parent that child has stopped */
diff --git a/arch/sparc/kernel/head_32.S b/arch/sparc/kernel/head_32.S
index 3d92c0a..7bb317b 100644
--- a/arch/sparc/kernel/head_32.S
+++ b/arch/sparc/kernel/head_32.S
@@ -24,6 +24,7 @@
#include <asm/thread_info.h> /* TI_UWINMASK */
#include <asm/errno.h>
#include <asm/pgtsrmmu.h> /* SRMMU_PGDIR_SHIFT */
+#include <asm/export.h>
.data
/* The following are used with the prom_vector node-ops to figure out
@@ -60,6 +61,7 @@
*/
.globl empty_zero_page
empty_zero_page: .skip PAGE_SIZE
+EXPORT_SYMBOL(empty_zero_page)
.global root_flags
.global ram_flags
@@ -813,3 +815,4 @@
__ret_efault:
ret
restore %g0, -EFAULT, %o0
+EXPORT_SYMBOL(__ret_efault)
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index a076b42..6aa3da1 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -32,7 +32,8 @@
#include <asm/estate.h>
#include <asm/sfafsr.h>
#include <asm/unistd.h>
-
+#include <asm/export.h>
+
/* This section from from _start to sparc64_boot_end should fit into
* 0x0000000000404000 to 0x0000000000408000.
*/
@@ -143,6 +144,7 @@
.skip 64
prom_root_node:
.word 0
+EXPORT_SYMBOL(prom_root_node)
prom_mmu_ihandle_cache:
.word 0
prom_boot_mapped_pc:
@@ -158,6 +160,7 @@
.word 0
sun4v_chip_type:
.word SUN4V_CHIP_INVALID
+EXPORT_SYMBOL(sun4v_chip_type)
1:
rd %pc, %l0
@@ -920,49 +923,14 @@
.globl prom_tba, tlb_type
prom_tba: .xword 0
tlb_type: .word 0 /* Must NOT end up in BSS */
+EXPORT_SYMBOL(tlb_type)
.section ".fixup",#alloc,#execinstr
- .globl __ret_efault, __retl_efault, __ret_one, __retl_one
-ENTRY(__ret_efault)
- ret
- restore %g0, -EFAULT, %o0
-ENDPROC(__ret_efault)
-
ENTRY(__retl_efault)
retl
mov -EFAULT, %o0
ENDPROC(__retl_efault)
-ENTRY(__retl_one)
- retl
- mov 1, %o0
-ENDPROC(__retl_one)
-
-ENTRY(__retl_one_fp)
- VISExitHalf
- retl
- mov 1, %o0
-ENDPROC(__retl_one_fp)
-
-ENTRY(__ret_one_asi)
- wr %g0, ASI_AIUS, %asi
- ret
- restore %g0, 1, %o0
-ENDPROC(__ret_one_asi)
-
-ENTRY(__retl_one_asi)
- wr %g0, ASI_AIUS, %asi
- retl
- mov 1, %o0
-ENDPROC(__retl_one_asi)
-
-ENTRY(__retl_one_asi_fp)
- wr %g0, ASI_AIUS, %asi
- VISExitHalf
- retl
- mov 1, %o0
-ENDPROC(__retl_one_asi_fp)
-
ENTRY(__retl_o1)
retl
mov %o1, %o0
diff --git a/arch/sparc/kernel/helpers.S b/arch/sparc/kernel/helpers.S
index 314dd0c..e4e5b83 100644
--- a/arch/sparc/kernel/helpers.S
+++ b/arch/sparc/kernel/helpers.S
@@ -15,6 +15,7 @@
2: retl
nop
.size __flushw_user,.-__flushw_user
+EXPORT_SYMBOL(__flushw_user)
/* Flush %fp and %i7 to the stack for all register
* windows active inside of the cpu. This allows
@@ -61,3 +62,4 @@
.size hard_smp_processor_id,.-hard_smp_processor_id
#endif
.size real_hard_smp_processor_id,.-real_hard_smp_processor_id
+EXPORT_SYMBOL_GPL(real_hard_smp_processor_id)
diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S
index d127130..4116ee5 100644
--- a/arch/sparc/kernel/hvcalls.S
+++ b/arch/sparc/kernel/hvcalls.S
@@ -343,6 +343,7 @@
0: retl
nop
ENDPROC(sun4v_mach_set_watchdog)
+EXPORT_SYMBOL(sun4v_mach_set_watchdog)
/* No inputs and does not return. */
ENTRY(sun4v_mach_sir)
@@ -776,6 +777,7 @@
retl
nop
ENDPROC(sun4v_niagara_getperf)
+EXPORT_SYMBOL(sun4v_niagara_getperf)
ENTRY(sun4v_niagara_setperf)
mov HV_FAST_SET_PERFREG, %o5
@@ -783,6 +785,7 @@
retl
nop
ENDPROC(sun4v_niagara_setperf)
+EXPORT_SYMBOL(sun4v_niagara_setperf)
ENTRY(sun4v_niagara2_getperf)
mov %o0, %o4
@@ -792,6 +795,7 @@
retl
nop
ENDPROC(sun4v_niagara2_getperf)
+EXPORT_SYMBOL(sun4v_niagara2_getperf)
ENTRY(sun4v_niagara2_setperf)
mov HV_FAST_N2_SET_PERFREG, %o5
@@ -799,6 +803,7 @@
retl
nop
ENDPROC(sun4v_niagara2_setperf)
+EXPORT_SYMBOL(sun4v_niagara2_setperf)
ENTRY(sun4v_reboot_data_set)
mov HV_FAST_REBOOT_DATA_SET, %o5
diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c
index 59bbeff..07933b9 100644
--- a/arch/sparc/kernel/jump_label.c
+++ b/arch/sparc/kernel/jump_label.c
@@ -13,19 +13,30 @@
void arch_jump_label_transform(struct jump_entry *entry,
enum jump_label_type type)
{
- u32 val;
u32 *insn = (u32 *) (unsigned long) entry->code;
+ u32 val;
if (type == JUMP_LABEL_JMP) {
s32 off = (s32)entry->target - (s32)entry->code;
+ bool use_v9_branch = false;
+
+ BUG_ON(off & 3);
#ifdef CONFIG_SPARC64
- /* ba,pt %xcc, . + (off << 2) */
- val = 0x10680000 | ((u32) off >> 2);
-#else
- /* ba . + (off << 2) */
- val = 0x10800000 | ((u32) off >> 2);
+ if (off <= 0xfffff && off >= -0x100000)
+ use_v9_branch = true;
#endif
+ if (use_v9_branch) {
+ /* WDISP19 - target is . + immed << 2 */
+ /* ba,pt %xcc, . + off */
+ val = 0x10680000 | (((u32) off >> 2) & 0x7ffff);
+ } else {
+ /* WDISP22 - target is . + immed << 2 */
+ BUG_ON(off > 0x7fffff);
+ BUG_ON(off < -0x800000);
+ /* ba . + off */
+ val = 0x10800000 | (((u32) off >> 2) & 0x3fffff);
+ }
} else {
val = 0x01000000;
}
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index 1122886..8a6982d 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -645,13 +645,20 @@ static void __mark_core_id(struct mdesc_handle *hp, u64 node,
cpu_data(*id).core_id = core_id;
}
-static void __mark_sock_id(struct mdesc_handle *hp, u64 node,
- int sock_id)
+static void __mark_max_cache_id(struct mdesc_handle *hp, u64 node,
+ int max_cache_id)
{
const u64 *id = mdesc_get_property(hp, node, "id", NULL);
- if (*id < num_possible_cpus())
- cpu_data(*id).sock_id = sock_id;
+ if (*id < num_possible_cpus()) {
+ cpu_data(*id).max_cache_id = max_cache_id;
+
+ /**
+ * On systems without explicit socket descriptions socket
+ * is max_cache_id
+ */
+ cpu_data(*id).sock_id = max_cache_id;
+ }
}
static void mark_core_ids(struct mdesc_handle *hp, u64 mp,
@@ -660,10 +667,11 @@ static void mark_core_ids(struct mdesc_handle *hp, u64 mp,
find_back_node_value(hp, mp, "cpu", __mark_core_id, core_id, 10);
}
-static void mark_sock_ids(struct mdesc_handle *hp, u64 mp,
- int sock_id)
+static void mark_max_cache_ids(struct mdesc_handle *hp, u64 mp,
+ int max_cache_id)
{
- find_back_node_value(hp, mp, "cpu", __mark_sock_id, sock_id, 10);
+ find_back_node_value(hp, mp, "cpu", __mark_max_cache_id,
+ max_cache_id, 10);
}
static void set_core_ids(struct mdesc_handle *hp)
@@ -694,14 +702,15 @@ static void set_core_ids(struct mdesc_handle *hp)
}
}
-static int set_sock_ids_by_cache(struct mdesc_handle *hp, int level)
+static int set_max_cache_ids_by_cache(struct mdesc_handle *hp, int level)
{
u64 mp;
int idx = 1;
int fnd = 0;
- /* Identify unique sockets by looking for cpus backpointed to by
- * shared level n caches.
+ /**
+ * Identify unique highest level of shared cache by looking for cpus
+ * backpointed to by shared level N caches.
*/
mdesc_for_each_node_by_name(hp, mp, "cache") {
const u64 *cur_lvl;
@@ -709,8 +718,7 @@ static int set_sock_ids_by_cache(struct mdesc_handle *hp, int level)
cur_lvl = mdesc_get_property(hp, mp, "level", NULL);
if (*cur_lvl != level)
continue;
-
- mark_sock_ids(hp, mp, idx);
+ mark_max_cache_ids(hp, mp, idx);
idx++;
fnd = 1;
}
@@ -745,15 +753,17 @@ static void set_sock_ids(struct mdesc_handle *hp)
{
u64 mp;
- /* If machine description exposes sockets data use it.
- * Otherwise fallback to use shared L3 or L2 caches.
+ /**
+ * Find the highest level of shared cache which pre-T7 is also
+ * the socket.
*/
+ if (!set_max_cache_ids_by_cache(hp, 3))
+ set_max_cache_ids_by_cache(hp, 2);
+
+ /* If machine description exposes sockets data use it.*/
mp = mdesc_node_by_name(hp, MDESC_NODE_NULL, "sockets");
if (mp != MDESC_NODE_NULL)
- return set_sock_ids_by_socket(hp, mp);
-
- if (!set_sock_ids_by_cache(hp, 3))
- set_sock_ids_by_cache(hp, 2);
+ set_sock_ids_by_socket(hp, mp);
}
static void mark_proc_ids(struct mdesc_handle *hp, u64 mp, int proc_id)
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index 9ddc492..ac082dd 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -127,7 +127,8 @@ static int get_from_target(struct task_struct *target, unsigned long uaddr,
if (copy_from_user(kbuf, (void __user *) uaddr, len))
return -EFAULT;
} else {
- int len2 = access_process_vm(target, uaddr, kbuf, len, 0);
+ int len2 = access_process_vm(target, uaddr, kbuf, len,
+ FOLL_FORCE);
if (len2 != len)
return -EFAULT;
}
@@ -141,7 +142,8 @@ static int set_to_target(struct task_struct *target, unsigned long uaddr,
if (copy_to_user((void __user *) uaddr, kbuf, len))
return -EFAULT;
} else {
- int len2 = access_process_vm(target, uaddr, kbuf, len, 1);
+ int len2 = access_process_vm(target, uaddr, kbuf, len,
+ FOLL_FORCE | FOLL_WRITE);
if (len2 != len)
return -EFAULT;
}
@@ -505,7 +507,8 @@ static int genregs32_get(struct task_struct *target,
if (access_process_vm(target,
(unsigned long)
®_window[pos],
- k, sizeof(*k), 0)
+ k, sizeof(*k),
+ FOLL_FORCE)
!= sizeof(*k))
return -EFAULT;
k++;
@@ -531,12 +534,14 @@ static int genregs32_get(struct task_struct *target,
if (access_process_vm(target,
(unsigned long)
®_window[pos],
- ®, sizeof(reg), 0)
+ ®, sizeof(reg),
+ FOLL_FORCE)
!= sizeof(reg))
return -EFAULT;
if (access_process_vm(target,
(unsigned long) u,
- ®, sizeof(reg), 1)
+ ®, sizeof(reg),
+ FOLL_FORCE | FOLL_WRITE)
!= sizeof(reg))
return -EFAULT;
pos++;
@@ -615,7 +620,8 @@ static int genregs32_set(struct task_struct *target,
(unsigned long)
®_window[pos],
(void *) k,
- sizeof(*k), 1)
+ sizeof(*k),
+ FOLL_FORCE | FOLL_WRITE)
!= sizeof(*k))
return -EFAULT;
k++;
@@ -642,13 +648,15 @@ static int genregs32_set(struct task_struct *target,
if (access_process_vm(target,
(unsigned long)
u,
- ®, sizeof(reg), 0)
+ ®, sizeof(reg),
+ FOLL_FORCE)
!= sizeof(reg))
return -EFAULT;
if (access_process_vm(target,
(unsigned long)
®_window[pos],
- ®, sizeof(reg), 1)
+ ®, sizeof(reg),
+ FOLL_FORCE | FOLL_WRITE)
!= sizeof(reg))
return -EFAULT;
pos++;
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index d3035ba..8182f7c 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -63,9 +63,13 @@ cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
cpumask_t cpu_core_sib_map[NR_CPUS] __read_mostly = {
[0 ... NR_CPUS-1] = CPU_MASK_NONE };
+cpumask_t cpu_core_sib_cache_map[NR_CPUS] __read_mostly = {
+ [0 ... NR_CPUS - 1] = CPU_MASK_NONE };
+
EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
EXPORT_SYMBOL(cpu_core_map);
EXPORT_SYMBOL(cpu_core_sib_map);
+EXPORT_SYMBOL(cpu_core_sib_cache_map);
static cpumask_t smp_commenced_mask;
@@ -1265,6 +1269,10 @@ void smp_fill_in_sib_core_maps(void)
unsigned int j;
for_each_present_cpu(j) {
+ if (cpu_data(i).max_cache_id ==
+ cpu_data(j).max_cache_id)
+ cpumask_set_cpu(j, &cpu_core_sib_cache_map[i]);
+
if (cpu_data(i).sock_id == cpu_data(j).sock_id)
cpumask_set_cpu(j, &cpu_core_sib_map[i]);
}
diff --git a/arch/sparc/kernel/sparc_ksyms.c b/arch/sparc/kernel/sparc_ksyms.c
new file mode 100644
index 0000000..09aa69e
--- /dev/null
+++ b/arch/sparc/kernel/sparc_ksyms.c
@@ -0,0 +1,12 @@
+/*
+ * arch/sparc/kernel/ksyms.c: Sparc specific ksyms support.
+ *
+ * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
+ * Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be)
+ */
+
+#include <linux/init.h>
+#include <linux/export.h>
+
+/* This is needed only for drivers/sbus/char/openprom.c */
+EXPORT_SYMBOL(saved_command_line);
diff --git a/arch/sparc/kernel/sparc_ksyms_32.c b/arch/sparc/kernel/sparc_ksyms_32.c
deleted file mode 100644
index bf4ccb1..0000000
--- a/arch/sparc/kernel/sparc_ksyms_32.c
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * arch/sparc/kernel/ksyms.c: Sparc specific ksyms support.
- *
- * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
- * Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be)
- */
-
-#include <linux/module.h>
-
-#include <asm/pgtable.h>
-#include <asm/uaccess.h>
-#include <asm/delay.h>
-#include <asm/head.h>
-#include <asm/dma.h>
-
-struct poll {
- int fd;
- short events;
- short revents;
-};
-
-/* from entry.S */
-EXPORT_SYMBOL(__udelay);
-EXPORT_SYMBOL(__ndelay);
-
-/* from head_32.S */
-EXPORT_SYMBOL(__ret_efault);
-EXPORT_SYMBOL(empty_zero_page);
-
-/* Exporting a symbol from /init/main.c */
-EXPORT_SYMBOL(saved_command_line);
diff --git a/arch/sparc/kernel/sparc_ksyms_64.c b/arch/sparc/kernel/sparc_ksyms_64.c
deleted file mode 100644
index 9e034f2..0000000
--- a/arch/sparc/kernel/sparc_ksyms_64.c
+++ /dev/null
@@ -1,53 +0,0 @@
-/* arch/sparc64/kernel/sparc64_ksyms.c: Sparc64 specific ksyms support.
- *
- * Copyright (C) 1996, 2007 David S. Miller (davem@davemloft.net)
- * Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be)
- * Copyright (C) 1999 Jakub Jelinek (jj@ultra.linux.cz)
- */
-
-#include <linux/export.h>
-#include <linux/pci.h>
-#include <linux/bitops.h>
-
-#include <asm/cpudata.h>
-#include <asm/uaccess.h>
-#include <asm/spitfire.h>
-#include <asm/oplib.h>
-#include <asm/hypervisor.h>
-#include <asm/cacheflush.h>
-
-struct poll {
- int fd;
- short events;
- short revents;
-};
-
-/* from helpers.S */
-EXPORT_SYMBOL(__flushw_user);
-EXPORT_SYMBOL_GPL(real_hard_smp_processor_id);
-
-/* from head_64.S */
-EXPORT_SYMBOL(__ret_efault);
-EXPORT_SYMBOL(tlb_type);
-EXPORT_SYMBOL(sun4v_chip_type);
-EXPORT_SYMBOL(prom_root_node);
-
-/* from hvcalls.S */
-EXPORT_SYMBOL(sun4v_niagara_getperf);
-EXPORT_SYMBOL(sun4v_niagara_setperf);
-EXPORT_SYMBOL(sun4v_niagara2_getperf);
-EXPORT_SYMBOL(sun4v_niagara2_setperf);
-EXPORT_SYMBOL(sun4v_mach_set_watchdog);
-
-/* from hweight.S */
-EXPORT_SYMBOL(__arch_hweight8);
-EXPORT_SYMBOL(__arch_hweight16);
-EXPORT_SYMBOL(__arch_hweight32);
-EXPORT_SYMBOL(__arch_hweight64);
-
-/* from ffs_ffz.S */
-EXPORT_SYMBOL(ffs);
-EXPORT_SYMBOL(__ffs);
-
-/* Exporting a symbol from /init/main.c */
-EXPORT_SYMBOL(saved_command_line);
diff --git a/arch/sparc/lib/GENcopy_from_user.S b/arch/sparc/lib/GENcopy_from_user.S
index b7d0bd6..69a439f 100644
--- a/arch/sparc/lib/GENcopy_from_user.S
+++ b/arch/sparc/lib/GENcopy_from_user.S
@@ -3,11 +3,11 @@
* Copyright (C) 2007 David S. Miller (davem@davemloft.net)
*/
-#define EX_LD(x) \
+#define EX_LD(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one; \
+ .word 98b, y; \
.text; \
.align 4;
diff --git a/arch/sparc/lib/GENcopy_to_user.S b/arch/sparc/lib/GENcopy_to_user.S
index 780550e..9947427 100644
--- a/arch/sparc/lib/GENcopy_to_user.S
+++ b/arch/sparc/lib/GENcopy_to_user.S
@@ -3,11 +3,11 @@
* Copyright (C) 2007 David S. Miller (davem@davemloft.net)
*/
-#define EX_ST(x) \
+#define EX_ST(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one; \
+ .word 98b, y; \
.text; \
.align 4;
diff --git a/arch/sparc/lib/GENmemcpy.S b/arch/sparc/lib/GENmemcpy.S
index 89358ee..059ea24 100644
--- a/arch/sparc/lib/GENmemcpy.S
+++ b/arch/sparc/lib/GENmemcpy.S
@@ -4,21 +4,18 @@
*/
#ifdef __KERNEL__
+#include <linux/linkage.h>
#define GLOBAL_SPARE %g7
#else
#define GLOBAL_SPARE %g5
#endif
#ifndef EX_LD
-#define EX_LD(x) x
+#define EX_LD(x,y) x
#endif
#ifndef EX_ST
-#define EX_ST(x) x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x) x
+#define EX_ST(x,y) x
#endif
#ifndef LOAD
@@ -45,6 +42,29 @@
.register %g3,#scratch
.text
+
+#ifndef EX_RETVAL
+#define EX_RETVAL(x) x
+ENTRY(GEN_retl_o4_1)
+ add %o4, %o2, %o4
+ retl
+ add %o4, 1, %o0
+ENDPROC(GEN_retl_o4_1)
+ENTRY(GEN_retl_g1_8)
+ add %g1, %o2, %g1
+ retl
+ add %g1, 8, %o0
+ENDPROC(GEN_retl_g1_8)
+ENTRY(GEN_retl_o2_4)
+ retl
+ add %o2, 4, %o0
+ENDPROC(GEN_retl_o2_4)
+ENTRY(GEN_retl_o2_1)
+ retl
+ add %o2, 1, %o0
+ENDPROC(GEN_retl_o2_1)
+#endif
+
.align 64
.globl FUNC_NAME
@@ -73,8 +93,8 @@
sub %g0, %o4, %o4
sub %o2, %o4, %o2
1: subcc %o4, 1, %o4
- EX_LD(LOAD(ldub, %o1, %g1))
- EX_ST(STORE(stb, %g1, %o0))
+ EX_LD(LOAD(ldub, %o1, %g1),GEN_retl_o4_1)
+ EX_ST(STORE(stb, %g1, %o0),GEN_retl_o4_1)
add %o1, 1, %o1
bne,pt %XCC, 1b
add %o0, 1, %o0
@@ -82,8 +102,8 @@
andn %o2, 0x7, %g1
sub %o2, %g1, %o2
1: subcc %g1, 0x8, %g1
- EX_LD(LOAD(ldx, %o1, %g2))
- EX_ST(STORE(stx, %g2, %o0))
+ EX_LD(LOAD(ldx, %o1, %g2),GEN_retl_g1_8)
+ EX_ST(STORE(stx, %g2, %o0),GEN_retl_g1_8)
add %o1, 0x8, %o1
bne,pt %XCC, 1b
add %o0, 0x8, %o0
@@ -100,8 +120,8 @@
1:
subcc %o2, 4, %o2
- EX_LD(LOAD(lduw, %o1, %g1))
- EX_ST(STORE(stw, %g1, %o1 + %o3))
+ EX_LD(LOAD(lduw, %o1, %g1),GEN_retl_o2_4)
+ EX_ST(STORE(stw, %g1, %o1 + %o3),GEN_retl_o2_4)
bgu,pt %XCC, 1b
add %o1, 4, %o1
@@ -111,8 +131,8 @@
.align 32
90:
subcc %o2, 1, %o2
- EX_LD(LOAD(ldub, %o1, %g1))
- EX_ST(STORE(stb, %g1, %o1 + %o3))
+ EX_LD(LOAD(ldub, %o1, %g1),GEN_retl_o2_1)
+ EX_ST(STORE(stb, %g1, %o1 + %o3),GEN_retl_o2_1)
bgu,pt %XCC, 90b
add %o1, 1, %o1
retl
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index 3269b02..69912d2 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -38,10 +38,9 @@
lib-$(CONFIG_SPARC64) += GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o
lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o
-lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o
+lib-$(CONFIG_SPARC64) += copy_in_user.o memmove.o
lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o
obj-$(CONFIG_SPARC64) += iomap.o
obj-$(CONFIG_SPARC32) += atomic32.o ucmpdi2.o
-obj-y += ksyms.o
obj-$(CONFIG_SPARC64) += PeeCeeI.o
diff --git a/arch/sparc/lib/NG2copy_from_user.S b/arch/sparc/lib/NG2copy_from_user.S
index d5242b8..b79a699 100644
--- a/arch/sparc/lib/NG2copy_from_user.S
+++ b/arch/sparc/lib/NG2copy_from_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 2007 David S. Miller (davem@davemloft.net)
*/
-#define EX_LD(x) \
+#define EX_LD(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi;\
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_LD_FP(x) \
+#define EX_LD_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi_fp;\
+ .word 98b, y##_fp; \
.text; \
.align 4;
diff --git a/arch/sparc/lib/NG2copy_to_user.S b/arch/sparc/lib/NG2copy_to_user.S
index 4e962d9..dcec55f 100644
--- a/arch/sparc/lib/NG2copy_to_user.S
+++ b/arch/sparc/lib/NG2copy_to_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 2007 David S. Miller (davem@davemloft.net)
*/
-#define EX_ST(x) \
+#define EX_ST(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi;\
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_ST_FP(x) \
+#define EX_ST_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi_fp;\
+ .word 98b, y##_fp; \
.text; \
.align 4;
diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index d5f585d..c629dbd 100644
--- a/arch/sparc/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
@@ -4,6 +4,7 @@
*/
#ifdef __KERNEL__
+#include <linux/linkage.h>
#include <asm/visasm.h>
#include <asm/asi.h>
#define GLOBAL_SPARE %g7
@@ -32,21 +33,17 @@
#endif
#ifndef EX_LD
-#define EX_LD(x) x
+#define EX_LD(x,y) x
#endif
#ifndef EX_LD_FP
-#define EX_LD_FP(x) x
+#define EX_LD_FP(x,y) x
#endif
#ifndef EX_ST
-#define EX_ST(x) x
+#define EX_ST(x,y) x
#endif
#ifndef EX_ST_FP
-#define EX_ST_FP(x) x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x) x
+#define EX_ST_FP(x,y) x
#endif
#ifndef LOAD
@@ -140,45 +137,110 @@
fsrc2 %x6, %f12; \
fsrc2 %x7, %f14;
#define FREG_LOAD_1(base, x0) \
- EX_LD_FP(LOAD(ldd, base + 0x00, %x0))
+ EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1)
#define FREG_LOAD_2(base, x0, x1) \
- EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
- EX_LD_FP(LOAD(ldd, base + 0x08, %x1));
+ EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1);
#define FREG_LOAD_3(base, x0, x1, x2) \
- EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
- EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
- EX_LD_FP(LOAD(ldd, base + 0x10, %x2));
+ EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1);
#define FREG_LOAD_4(base, x0, x1, x2, x3) \
- EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
- EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
- EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
- EX_LD_FP(LOAD(ldd, base + 0x18, %x3));
+ EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1);
#define FREG_LOAD_5(base, x0, x1, x2, x3, x4) \
- EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
- EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
- EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
- EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
- EX_LD_FP(LOAD(ldd, base + 0x20, %x4));
+ EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1);
#define FREG_LOAD_6(base, x0, x1, x2, x3, x4, x5) \
- EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
- EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
- EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
- EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
- EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \
- EX_LD_FP(LOAD(ldd, base + 0x28, %x5));
+ EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x28, %x5), NG2_retl_o2_plus_g1);
#define FREG_LOAD_7(base, x0, x1, x2, x3, x4, x5, x6) \
- EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \
- EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \
- EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \
- EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \
- EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \
- EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); \
- EX_LD_FP(LOAD(ldd, base + 0x30, %x6));
+ EX_LD_FP(LOAD(ldd, base + 0x00, %x0), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x08, %x1), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x10, %x2), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x18, %x3), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x20, %x4), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x28, %x5), NG2_retl_o2_plus_g1); \
+ EX_LD_FP(LOAD(ldd, base + 0x30, %x6), NG2_retl_o2_plus_g1);
.register %g2,#scratch
.register %g3,#scratch
.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x) x
+__restore_fp:
+ VISExitHalf
+__restore_asi:
+ retl
+ wr %g0, ASI_AIUS, %asi
+ENTRY(NG2_retl_o2)
+ ba,pt %xcc, __restore_asi
+ mov %o2, %o0
+ENDPROC(NG2_retl_o2)
+ENTRY(NG2_retl_o2_plus_1)
+ ba,pt %xcc, __restore_asi
+ add %o2, 1, %o0
+ENDPROC(NG2_retl_o2_plus_1)
+ENTRY(NG2_retl_o2_plus_4)
+ ba,pt %xcc, __restore_asi
+ add %o2, 4, %o0
+ENDPROC(NG2_retl_o2_plus_4)
+ENTRY(NG2_retl_o2_plus_8)
+ ba,pt %xcc, __restore_asi
+ add %o2, 8, %o0
+ENDPROC(NG2_retl_o2_plus_8)
+ENTRY(NG2_retl_o2_plus_o4_plus_1)
+ add %o4, 1, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG2_retl_o2_plus_o4_plus_1)
+ENTRY(NG2_retl_o2_plus_o4_plus_8)
+ add %o4, 8, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG2_retl_o2_plus_o4_plus_8)
+ENTRY(NG2_retl_o2_plus_o4_plus_16)
+ add %o4, 16, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG2_retl_o2_plus_o4_plus_16)
+ENTRY(NG2_retl_o2_plus_g1_fp)
+ ba,pt %xcc, __restore_fp
+ add %o2, %g1, %o0
+ENDPROC(NG2_retl_o2_plus_g1_fp)
+ENTRY(NG2_retl_o2_plus_g1_plus_64_fp)
+ add %g1, 64, %g1
+ ba,pt %xcc, __restore_fp
+ add %o2, %g1, %o0
+ENDPROC(NG2_retl_o2_plus_g1_plus_64_fp)
+ENTRY(NG2_retl_o2_plus_g1_plus_1)
+ add %g1, 1, %g1
+ ba,pt %xcc, __restore_asi
+ add %o2, %g1, %o0
+ENDPROC(NG2_retl_o2_plus_g1_plus_1)
+ENTRY(NG2_retl_o2_and_7_plus_o4)
+ and %o2, 7, %o2
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG2_retl_o2_and_7_plus_o4)
+ENTRY(NG2_retl_o2_and_7_plus_o4_plus_8)
+ and %o2, 7, %o2
+ add %o4, 8, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG2_retl_o2_and_7_plus_o4_plus_8)
+#endif
+
.align 64
.globl FUNC_NAME
@@ -230,8 +292,8 @@
sub %g0, %o4, %o4 ! bytes to align dst
sub %o2, %o4, %o2
1: subcc %o4, 1, %o4
- EX_LD(LOAD(ldub, %o1, %g1))
- EX_ST(STORE(stb, %g1, %o0))
+ EX_LD(LOAD(ldub, %o1, %g1), NG2_retl_o2_plus_o4_plus_1)
+ EX_ST(STORE(stb, %g1, %o0), NG2_retl_o2_plus_o4_plus_1)
add %o1, 1, %o1
bne,pt %XCC, 1b
add %o0, 1, %o0
@@ -281,11 +343,11 @@
nop
/* fall through for 0 < low bits < 8 */
110: sub %o4, 64, %g2
- EX_LD_FP(LOAD_BLK(%g2, %f0))
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+ EX_LD_FP(LOAD_BLK(%g2, %f0), NG2_retl_o2_plus_g1)
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f14, f16)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_8(f16, f18, f20, f22, f24, f26, f28, f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -296,10 +358,10 @@
120: sub %o4, 56, %g2
FREG_LOAD_7(%g2, f0, f2, f4, f6, f8, f10, f12)
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f16, f18)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_7(f18, f20, f22, f24, f26, f28, f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -310,10 +372,10 @@
130: sub %o4, 48, %g2
FREG_LOAD_6(%g2, f0, f2, f4, f6, f8, f10)
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f2, f4, f6, f8, f10, f16, f18, f20)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_6(f20, f22, f24, f26, f28, f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -324,10 +386,10 @@
140: sub %o4, 40, %g2
FREG_LOAD_5(%g2, f0, f2, f4, f6, f8)
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f2, f4, f6, f8, f16, f18, f20, f22)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_5(f22, f24, f26, f28, f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -338,10 +400,10 @@
150: sub %o4, 32, %g2
FREG_LOAD_4(%g2, f0, f2, f4, f6)
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f2, f4, f6, f16, f18, f20, f22, f24)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_4(f24, f26, f28, f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -352,10 +414,10 @@
160: sub %o4, 24, %g2
FREG_LOAD_3(%g2, f0, f2, f4)
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f2, f4, f16, f18, f20, f22, f24, f26)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_3(f26, f28, f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -366,10 +428,10 @@
170: sub %o4, 16, %g2
FREG_LOAD_2(%g2, f0, f2)
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f2, f16, f18, f20, f22, f24, f26, f28)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_2(f28, f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -380,10 +442,10 @@
180: sub %o4, 8, %g2
FREG_LOAD_1(%g2, f0)
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
- EX_LD_FP(LOAD_BLK(%o4, %f16))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
+ EX_LD_FP(LOAD_BLK(%o4, %f16), NG2_retl_o2_plus_g1)
FREG_FROB(f0, f16, f18, f20, f22, f24, f26, f28, f30)
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1)
FREG_MOVE_1(f30)
subcc %g1, 64, %g1
add %o4, 64, %o4
@@ -393,10 +455,10 @@
nop
190:
-1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3))
+1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3), NG2_retl_o2_plus_g1)
subcc %g1, 64, %g1
- EX_LD_FP(LOAD_BLK(%o4, %f0))
- EX_ST_FP(STORE_BLK(%f0, %o4 + %g3))
+ EX_LD_FP(LOAD_BLK(%o4, %f0), NG2_retl_o2_plus_g1_plus_64)
+ EX_ST_FP(STORE_BLK(%f0, %o4 + %g3), NG2_retl_o2_plus_g1_plus_64)
add %o4, 64, %o4
bne,pt %xcc, 1b
LOAD(prefetch, %o4 + 64, #one_read)
@@ -423,28 +485,28 @@
andn %o2, 0xf, %o4
and %o2, 0xf, %o2
1: subcc %o4, 0x10, %o4
- EX_LD(LOAD(ldx, %o1, %o5))
+ EX_LD(LOAD(ldx, %o1, %o5), NG2_retl_o2_plus_o4_plus_16)
add %o1, 0x08, %o1
- EX_LD(LOAD(ldx, %o1, %g1))
+ EX_LD(LOAD(ldx, %o1, %g1), NG2_retl_o2_plus_o4_plus_16)
sub %o1, 0x08, %o1
- EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE))
+ EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_o4_plus_16)
add %o1, 0x8, %o1
- EX_ST(STORE(stx, %g1, %o1 + GLOBAL_SPARE))
+ EX_ST(STORE(stx, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_o4_plus_8)
bgu,pt %XCC, 1b
add %o1, 0x8, %o1
73: andcc %o2, 0x8, %g0
be,pt %XCC, 1f
nop
sub %o2, 0x8, %o2
- EX_LD(LOAD(ldx, %o1, %o5))
- EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE))
+ EX_LD(LOAD(ldx, %o1, %o5), NG2_retl_o2_plus_8)
+ EX_ST(STORE(stx, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_8)
add %o1, 0x8, %o1
1: andcc %o2, 0x4, %g0
be,pt %XCC, 1f
nop
sub %o2, 0x4, %o2
- EX_LD(LOAD(lduw, %o1, %o5))
- EX_ST(STORE(stw, %o5, %o1 + GLOBAL_SPARE))
+ EX_LD(LOAD(lduw, %o1, %o5), NG2_retl_o2_plus_4)
+ EX_ST(STORE(stw, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_4)
add %o1, 0x4, %o1
1: cmp %o2, 0
be,pt %XCC, 85f
@@ -460,8 +522,8 @@
sub %o2, %g1, %o2
1: subcc %g1, 1, %g1
- EX_LD(LOAD(ldub, %o1, %o5))
- EX_ST(STORE(stb, %o5, %o1 + GLOBAL_SPARE))
+ EX_LD(LOAD(ldub, %o1, %o5), NG2_retl_o2_plus_g1_plus_1)
+ EX_ST(STORE(stb, %o5, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_g1_plus_1)
bgu,pt %icc, 1b
add %o1, 1, %o1
@@ -477,16 +539,16 @@
8: mov 64, GLOBAL_SPARE
andn %o1, 0x7, %o1
- EX_LD(LOAD(ldx, %o1, %g2))
+ EX_LD(LOAD(ldx, %o1, %g2), NG2_retl_o2)
sub GLOBAL_SPARE, %g1, GLOBAL_SPARE
andn %o2, 0x7, %o4
sllx %g2, %g1, %g2
1: add %o1, 0x8, %o1
- EX_LD(LOAD(ldx, %o1, %g3))
+ EX_LD(LOAD(ldx, %o1, %g3), NG2_retl_o2_and_7_plus_o4)
subcc %o4, 0x8, %o4
srlx %g3, GLOBAL_SPARE, %o5
or %o5, %g2, %o5
- EX_ST(STORE(stx, %o5, %o0))
+ EX_ST(STORE(stx, %o5, %o0), NG2_retl_o2_and_7_plus_o4_plus_8)
add %o0, 0x8, %o0
bgu,pt %icc, 1b
sllx %g3, %g1, %g2
@@ -506,8 +568,8 @@
1:
subcc %o2, 4, %o2
- EX_LD(LOAD(lduw, %o1, %g1))
- EX_ST(STORE(stw, %g1, %o1 + GLOBAL_SPARE))
+ EX_LD(LOAD(lduw, %o1, %g1), NG2_retl_o2_plus_4)
+ EX_ST(STORE(stw, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_4)
bgu,pt %XCC, 1b
add %o1, 4, %o1
@@ -517,8 +579,8 @@
.align 32
90:
subcc %o2, 1, %o2
- EX_LD(LOAD(ldub, %o1, %g1))
- EX_ST(STORE(stb, %g1, %o1 + GLOBAL_SPARE))
+ EX_LD(LOAD(ldub, %o1, %g1), NG2_retl_o2_plus_1)
+ EX_ST(STORE(stb, %g1, %o1 + GLOBAL_SPARE), NG2_retl_o2_plus_1)
bgu,pt %XCC, 90b
add %o1, 1, %o1
retl
diff --git a/arch/sparc/lib/NG4copy_from_user.S b/arch/sparc/lib/NG4copy_from_user.S
index 2e8ee7a..16a286c 100644
--- a/arch/sparc/lib/NG4copy_from_user.S
+++ b/arch/sparc/lib/NG4copy_from_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 2012 David S. Miller (davem@davemloft.net)
*/
-#define EX_LD(x) \
+#define EX_LD(x, y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi;\
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_LD_FP(x) \
+#define EX_LD_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi_fp;\
+ .word 98b, y##_fp; \
.text; \
.align 4;
diff --git a/arch/sparc/lib/NG4copy_to_user.S b/arch/sparc/lib/NG4copy_to_user.S
index be0bf45..6b0276f 100644
--- a/arch/sparc/lib/NG4copy_to_user.S
+++ b/arch/sparc/lib/NG4copy_to_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 2012 David S. Miller (davem@davemloft.net)
*/
-#define EX_ST(x) \
+#define EX_ST(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi;\
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_ST_FP(x) \
+#define EX_ST_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_asi_fp;\
+ .word 98b, y##_fp; \
.text; \
.align 4;
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 8e13ee1..75bb93b 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -4,6 +4,7 @@
*/
#ifdef __KERNEL__
+#include <linux/linkage.h>
#include <asm/visasm.h>
#include <asm/asi.h>
#define GLOBAL_SPARE %g7
@@ -46,22 +47,19 @@
#endif
#ifndef EX_LD
-#define EX_LD(x) x
+#define EX_LD(x,y) x
#endif
#ifndef EX_LD_FP
-#define EX_LD_FP(x) x
+#define EX_LD_FP(x,y) x
#endif
#ifndef EX_ST
-#define EX_ST(x) x
+#define EX_ST(x,y) x
#endif
#ifndef EX_ST_FP
-#define EX_ST_FP(x) x
+#define EX_ST_FP(x,y) x
#endif
-#ifndef EX_RETVAL
-#define EX_RETVAL(x) x
-#endif
#ifndef LOAD
#define LOAD(type,addr,dest) type [addr], dest
@@ -94,6 +92,158 @@
.register %g3,#scratch
.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x) x
+__restore_asi_fp:
+ VISExitHalf
+__restore_asi:
+ retl
+ wr %g0, ASI_AIUS, %asi
+
+ENTRY(NG4_retl_o2)
+ ba,pt %xcc, __restore_asi
+ mov %o2, %o0
+ENDPROC(NG4_retl_o2)
+ENTRY(NG4_retl_o2_plus_1)
+ ba,pt %xcc, __restore_asi
+ add %o2, 1, %o0
+ENDPROC(NG4_retl_o2_plus_1)
+ENTRY(NG4_retl_o2_plus_4)
+ ba,pt %xcc, __restore_asi
+ add %o2, 4, %o0
+ENDPROC(NG4_retl_o2_plus_4)
+ENTRY(NG4_retl_o2_plus_o5)
+ ba,pt %xcc, __restore_asi
+ add %o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5)
+ENTRY(NG4_retl_o2_plus_o5_plus_4)
+ add %o5, 4, %o5
+ ba,pt %xcc, __restore_asi
+ add %o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_4)
+ENTRY(NG4_retl_o2_plus_o5_plus_8)
+ add %o5, 8, %o5
+ ba,pt %xcc, __restore_asi
+ add %o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_8)
+ENTRY(NG4_retl_o2_plus_o5_plus_16)
+ add %o5, 16, %o5
+ ba,pt %xcc, __restore_asi
+ add %o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_16)
+ENTRY(NG4_retl_o2_plus_o5_plus_24)
+ add %o5, 24, %o5
+ ba,pt %xcc, __restore_asi
+ add %o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_24)
+ENTRY(NG4_retl_o2_plus_o5_plus_32)
+ add %o5, 32, %o5
+ ba,pt %xcc, __restore_asi
+ add %o2, %o5, %o0
+ENDPROC(NG4_retl_o2_plus_o5_plus_32)
+ENTRY(NG4_retl_o2_plus_g1)
+ ba,pt %xcc, __restore_asi
+ add %o2, %g1, %o0
+ENDPROC(NG4_retl_o2_plus_g1)
+ENTRY(NG4_retl_o2_plus_g1_plus_1)
+ add %g1, 1, %g1
+ ba,pt %xcc, __restore_asi
+ add %o2, %g1, %o0
+ENDPROC(NG4_retl_o2_plus_g1_plus_1)
+ENTRY(NG4_retl_o2_plus_g1_plus_8)
+ add %g1, 8, %g1
+ ba,pt %xcc, __restore_asi
+ add %o2, %g1, %o0
+ENDPROC(NG4_retl_o2_plus_g1_plus_8)
+ENTRY(NG4_retl_o2_plus_o4)
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4)
+ENTRY(NG4_retl_o2_plus_o4_plus_8)
+ add %o4, 8, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_8)
+ENTRY(NG4_retl_o2_plus_o4_plus_16)
+ add %o4, 16, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_16)
+ENTRY(NG4_retl_o2_plus_o4_plus_24)
+ add %o4, 24, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_24)
+ENTRY(NG4_retl_o2_plus_o4_plus_32)
+ add %o4, 32, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_32)
+ENTRY(NG4_retl_o2_plus_o4_plus_40)
+ add %o4, 40, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_40)
+ENTRY(NG4_retl_o2_plus_o4_plus_48)
+ add %o4, 48, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_48)
+ENTRY(NG4_retl_o2_plus_o4_plus_56)
+ add %o4, 56, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_56)
+ENTRY(NG4_retl_o2_plus_o4_plus_64)
+ add %o4, 64, %o4
+ ba,pt %xcc, __restore_asi
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_64)
+ENTRY(NG4_retl_o2_plus_o4_fp)
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_8_fp)
+ add %o4, 8, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_8_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_16_fp)
+ add %o4, 16, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_16_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_24_fp)
+ add %o4, 24, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_24_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_32_fp)
+ add %o4, 32, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_32_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_40_fp)
+ add %o4, 40, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_40_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_48_fp)
+ add %o4, 48, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_48_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_56_fp)
+ add %o4, 56, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_56_fp)
+ENTRY(NG4_retl_o2_plus_o4_plus_64_fp)
+ add %o4, 64, %o4
+ ba,pt %xcc, __restore_asi_fp
+ add %o2, %o4, %o0
+ENDPROC(NG4_retl_o2_plus_o4_plus_64_fp)
+#endif
.align 64
.globl FUNC_NAME
@@ -124,12 +274,13 @@
brz,pt %g1, 51f
sub %o2, %g1, %o2
-1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2))
+
+1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1)
add %o1, 1, %o1
subcc %g1, 1, %g1
add %o0, 1, %o0
bne,pt %icc, 1b
- EX_ST(STORE(stb, %g2, %o0 - 0x01))
+ EX_ST(STORE(stb, %g2, %o0 - 0x01), NG4_retl_o2_plus_g1_plus_1)
51: LOAD(prefetch, %o1 + 0x040, #n_reads_strong)
LOAD(prefetch, %o1 + 0x080, #n_reads_strong)
@@ -154,43 +305,43 @@
brz,pt %g1, .Llarge_aligned
sub %o2, %g1, %o2
-1: EX_LD(LOAD(ldx, %o1 + 0x00, %g2))
+1: EX_LD(LOAD(ldx, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1)
add %o1, 8, %o1
subcc %g1, 8, %g1
add %o0, 8, %o0
bne,pt %icc, 1b
- EX_ST(STORE(stx, %g2, %o0 - 0x08))
+ EX_ST(STORE(stx, %g2, %o0 - 0x08), NG4_retl_o2_plus_g1_plus_8)
.Llarge_aligned:
/* len >= 0x80 && src 8-byte aligned && dest 8-byte aligned */
andn %o2, 0x3f, %o4
sub %o2, %o4, %o2
-1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
+1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o4)
add %o1, 0x40, %o1
- EX_LD(LOAD(ldx, %o1 - 0x38, %g2))
+ EX_LD(LOAD(ldx, %o1 - 0x38, %g2), NG4_retl_o2_plus_o4)
subcc %o4, 0x40, %o4
- EX_LD(LOAD(ldx, %o1 - 0x30, %g3))
- EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE))
- EX_LD(LOAD(ldx, %o1 - 0x20, %o5))
- EX_ST(STORE_INIT(%g1, %o0))
+ EX_LD(LOAD(ldx, %o1 - 0x30, %g3), NG4_retl_o2_plus_o4_plus_64)
+ EX_LD(LOAD(ldx, %o1 - 0x28, GLOBAL_SPARE), NG4_retl_o2_plus_o4_plus_64)
+ EX_LD(LOAD(ldx, %o1 - 0x20, %o5), NG4_retl_o2_plus_o4_plus_64)
+ EX_ST(STORE_INIT(%g1, %o0), NG4_retl_o2_plus_o4_plus_64)
add %o0, 0x08, %o0
- EX_ST(STORE_INIT(%g2, %o0))
+ EX_ST(STORE_INIT(%g2, %o0), NG4_retl_o2_plus_o4_plus_56)
add %o0, 0x08, %o0
- EX_LD(LOAD(ldx, %o1 - 0x18, %g2))
- EX_ST(STORE_INIT(%g3, %o0))
+ EX_LD(LOAD(ldx, %o1 - 0x18, %g2), NG4_retl_o2_plus_o4_plus_48)
+ EX_ST(STORE_INIT(%g3, %o0), NG4_retl_o2_plus_o4_plus_48)
add %o0, 0x08, %o0
- EX_LD(LOAD(ldx, %o1 - 0x10, %g3))
- EX_ST(STORE_INIT(GLOBAL_SPARE, %o0))
+ EX_LD(LOAD(ldx, %o1 - 0x10, %g3), NG4_retl_o2_plus_o4_plus_40)
+ EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), NG4_retl_o2_plus_o4_plus_40)
add %o0, 0x08, %o0
- EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE))
- EX_ST(STORE_INIT(%o5, %o0))
+ EX_LD(LOAD(ldx, %o1 - 0x08, GLOBAL_SPARE), NG4_retl_o2_plus_o4_plus_32)
+ EX_ST(STORE_INIT(%o5, %o0), NG4_retl_o2_plus_o4_plus_32)
add %o0, 0x08, %o0
- EX_ST(STORE_INIT(%g2, %o0))
+ EX_ST(STORE_INIT(%g2, %o0), NG4_retl_o2_plus_o4_plus_24)
add %o0, 0x08, %o0
- EX_ST(STORE_INIT(%g3, %o0))
+ EX_ST(STORE_INIT(%g3, %o0), NG4_retl_o2_plus_o4_plus_16)
add %o0, 0x08, %o0
- EX_ST(STORE_INIT(GLOBAL_SPARE, %o0))
+ EX_ST(STORE_INIT(GLOBAL_SPARE, %o0), NG4_retl_o2_plus_o4_plus_8)
add %o0, 0x08, %o0
bne,pt %icc, 1b
LOAD(prefetch, %o1 + 0x200, #n_reads_strong)
@@ -216,17 +367,17 @@
sub %o2, %o4, %o2
alignaddr %o1, %g0, %g1
add %o1, %o4, %o1
- EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0))
-1: EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2))
+ EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0), NG4_retl_o2_plus_o4)
+1: EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2), NG4_retl_o2_plus_o4)
subcc %o4, 0x40, %o4
- EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4))
- EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6))
- EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8))
- EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10))
- EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12))
- EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14))
+ EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4), NG4_retl_o2_plus_o4_plus_64)
+ EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6), NG4_retl_o2_plus_o4_plus_64)
+ EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8), NG4_retl_o2_plus_o4_plus_64)
+ EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10), NG4_retl_o2_plus_o4_plus_64)
+ EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12), NG4_retl_o2_plus_o4_plus_64)
+ EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14), NG4_retl_o2_plus_o4_plus_64)
faligndata %f0, %f2, %f16
- EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0))
+ EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0), NG4_retl_o2_plus_o4_plus_64)
faligndata %f2, %f4, %f18
add %g1, 0x40, %g1
faligndata %f4, %f6, %f20
@@ -235,14 +386,14 @@
faligndata %f10, %f12, %f26
faligndata %f12, %f14, %f28
faligndata %f14, %f0, %f30
- EX_ST_FP(STORE(std, %f16, %o0 + 0x00))
- EX_ST_FP(STORE(std, %f18, %o0 + 0x08))
- EX_ST_FP(STORE(std, %f20, %o0 + 0x10))
- EX_ST_FP(STORE(std, %f22, %o0 + 0x18))
- EX_ST_FP(STORE(std, %f24, %o0 + 0x20))
- EX_ST_FP(STORE(std, %f26, %o0 + 0x28))
- EX_ST_FP(STORE(std, %f28, %o0 + 0x30))
- EX_ST_FP(STORE(std, %f30, %o0 + 0x38))
+ EX_ST_FP(STORE(std, %f16, %o0 + 0x00), NG4_retl_o2_plus_o4_plus_64)
+ EX_ST_FP(STORE(std, %f18, %o0 + 0x08), NG4_retl_o2_plus_o4_plus_56)
+ EX_ST_FP(STORE(std, %f20, %o0 + 0x10), NG4_retl_o2_plus_o4_plus_48)
+ EX_ST_FP(STORE(std, %f22, %o0 + 0x18), NG4_retl_o2_plus_o4_plus_40)
+ EX_ST_FP(STORE(std, %f24, %o0 + 0x20), NG4_retl_o2_plus_o4_plus_32)
+ EX_ST_FP(STORE(std, %f26, %o0 + 0x28), NG4_retl_o2_plus_o4_plus_24)
+ EX_ST_FP(STORE(std, %f28, %o0 + 0x30), NG4_retl_o2_plus_o4_plus_16)
+ EX_ST_FP(STORE(std, %f30, %o0 + 0x38), NG4_retl_o2_plus_o4_plus_8)
add %o0, 0x40, %o0
bne,pt %icc, 1b
LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
@@ -270,37 +421,38 @@
andncc %o2, 0x20 - 1, %o5
be,pn %icc, 2f
sub %o2, %o5, %o2
-1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
- EX_LD(LOAD(ldx, %o1 + 0x08, %g2))
- EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE))
- EX_LD(LOAD(ldx, %o1 + 0x18, %o4))
+1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5)
+ EX_LD(LOAD(ldx, %o1 + 0x08, %g2), NG4_retl_o2_plus_o5)
+ EX_LD(LOAD(ldx, %o1 + 0x10, GLOBAL_SPARE), NG4_retl_o2_plus_o5)
+ EX_LD(LOAD(ldx, %o1 + 0x18, %o4), NG4_retl_o2_plus_o5)
add %o1, 0x20, %o1
subcc %o5, 0x20, %o5
- EX_ST(STORE(stx, %g1, %o0 + 0x00))
- EX_ST(STORE(stx, %g2, %o0 + 0x08))
- EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10))
- EX_ST(STORE(stx, %o4, %o0 + 0x18))
+ EX_ST(STORE(stx, %g1, %o0 + 0x00), NG4_retl_o2_plus_o5_plus_32)
+ EX_ST(STORE(stx, %g2, %o0 + 0x08), NG4_retl_o2_plus_o5_plus_24)
+ EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x10), NG4_retl_o2_plus_o5_plus_24)
+ EX_ST(STORE(stx, %o4, %o0 + 0x18), NG4_retl_o2_plus_o5_plus_8)
bne,pt %icc, 1b
add %o0, 0x20, %o0
2: andcc %o2, 0x18, %o5
be,pt %icc, 3f
sub %o2, %o5, %o2
-1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1))
+
+1: EX_LD(LOAD(ldx, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5)
add %o1, 0x08, %o1
add %o0, 0x08, %o0
subcc %o5, 0x08, %o5
bne,pt %icc, 1b
- EX_ST(STORE(stx, %g1, %o0 - 0x08))
+ EX_ST(STORE(stx, %g1, %o0 - 0x08), NG4_retl_o2_plus_o5_plus_8)
3: brz,pt %o2, .Lexit
cmp %o2, 0x04
bl,pn %icc, .Ltiny
nop
- EX_LD(LOAD(lduw, %o1 + 0x00, %g1))
+ EX_LD(LOAD(lduw, %o1 + 0x00, %g1), NG4_retl_o2)
add %o1, 0x04, %o1
add %o0, 0x04, %o0
subcc %o2, 0x04, %o2
bne,pn %icc, .Ltiny
- EX_ST(STORE(stw, %g1, %o0 - 0x04))
+ EX_ST(STORE(stw, %g1, %o0 - 0x04), NG4_retl_o2_plus_4)
ba,a,pt %icc, .Lexit
.Lmedium_unaligned:
/* First get dest 8 byte aligned. */
@@ -309,12 +461,12 @@
brz,pt %g1, 2f
sub %o2, %g1, %o2
-1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2))
+1: EX_LD(LOAD(ldub, %o1 + 0x00, %g2), NG4_retl_o2_plus_g1)
add %o1, 1, %o1
subcc %g1, 1, %g1
add %o0, 1, %o0
bne,pt %icc, 1b
- EX_ST(STORE(stb, %g2, %o0 - 0x01))
+ EX_ST(STORE(stb, %g2, %o0 - 0x01), NG4_retl_o2_plus_g1_plus_1)
2:
and %o1, 0x7, %g1
brz,pn %g1, .Lmedium_noprefetch
@@ -322,16 +474,16 @@
mov 64, %g2
sub %g2, %g1, %g2
andn %o1, 0x7, %o1
- EX_LD(LOAD(ldx, %o1 + 0x00, %o4))
+ EX_LD(LOAD(ldx, %o1 + 0x00, %o4), NG4_retl_o2)
sllx %o4, %g1, %o4
andn %o2, 0x08 - 1, %o5
sub %o2, %o5, %o2
-1: EX_LD(LOAD(ldx, %o1 + 0x08, %g3))
+1: EX_LD(LOAD(ldx, %o1 + 0x08, %g3), NG4_retl_o2_plus_o5)
add %o1, 0x08, %o1
subcc %o5, 0x08, %o5
srlx %g3, %g2, GLOBAL_SPARE
or GLOBAL_SPARE, %o4, GLOBAL_SPARE
- EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00))
+ EX_ST(STORE(stx, GLOBAL_SPARE, %o0 + 0x00), NG4_retl_o2_plus_o5_plus_8)
add %o0, 0x08, %o0
bne,pt %icc, 1b
sllx %g3, %g1, %o4
@@ -342,17 +494,17 @@
ba,pt %icc, .Lsmall_unaligned
.Ltiny:
- EX_LD(LOAD(ldub, %o1 + 0x00, %g1))
+ EX_LD(LOAD(ldub, %o1 + 0x00, %g1), NG4_retl_o2)
subcc %o2, 1, %o2
be,pn %icc, .Lexit
- EX_ST(STORE(stb, %g1, %o0 + 0x00))
- EX_LD(LOAD(ldub, %o1 + 0x01, %g1))
+ EX_ST(STORE(stb, %g1, %o0 + 0x00), NG4_retl_o2_plus_1)
+ EX_LD(LOAD(ldub, %o1 + 0x01, %g1), NG4_retl_o2)
subcc %o2, 1, %o2
be,pn %icc, .Lexit
- EX_ST(STORE(stb, %g1, %o0 + 0x01))
- EX_LD(LOAD(ldub, %o1 + 0x02, %g1))
+ EX_ST(STORE(stb, %g1, %o0 + 0x01), NG4_retl_o2_plus_1)
+ EX_LD(LOAD(ldub, %o1 + 0x02, %g1), NG4_retl_o2)
ba,pt %icc, .Lexit
- EX_ST(STORE(stb, %g1, %o0 + 0x02))
+ EX_ST(STORE(stb, %g1, %o0 + 0x02), NG4_retl_o2)
.Lsmall:
andcc %g2, 0x3, %g0
@@ -360,22 +512,22 @@
andn %o2, 0x4 - 1, %o5
sub %o2, %o5, %o2
1:
- EX_LD(LOAD(lduw, %o1 + 0x00, %g1))
+ EX_LD(LOAD(lduw, %o1 + 0x00, %g1), NG4_retl_o2_plus_o5)
add %o1, 0x04, %o1
subcc %o5, 0x04, %o5
add %o0, 0x04, %o0
bne,pt %icc, 1b
- EX_ST(STORE(stw, %g1, %o0 - 0x04))
+ EX_ST(STORE(stw, %g1, %o0 - 0x04), NG4_retl_o2_plus_o5_plus_4)
brz,pt %o2, .Lexit
nop
ba,a,pt %icc, .Ltiny
.Lsmall_unaligned:
-1: EX_LD(LOAD(ldub, %o1 + 0x00, %g1))
+1: EX_LD(LOAD(ldub, %o1 + 0x00, %g1), NG4_retl_o2)
add %o1, 1, %o1
add %o0, 1, %o0
subcc %o2, 1, %o2
bne,pt %icc, 1b
- EX_ST(STORE(stb, %g1, %o0 - 0x01))
+ EX_ST(STORE(stb, %g1, %o0 - 0x01), NG4_retl_o2_plus_1)
ba,a,pt %icc, .Lexit
.size FUNC_NAME, .-FUNC_NAME
diff --git a/arch/sparc/lib/NGcopy_from_user.S b/arch/sparc/lib/NGcopy_from_user.S
index 5d1e4d1..9cd42fc 100644
--- a/arch/sparc/lib/NGcopy_from_user.S
+++ b/arch/sparc/lib/NGcopy_from_user.S
@@ -3,11 +3,11 @@
* Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net)
*/
-#define EX_LD(x) \
+#define EX_LD(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __ret_one_asi;\
+ .word 98b, y; \
.text; \
.align 4;
diff --git a/arch/sparc/lib/NGcopy_to_user.S b/arch/sparc/lib/NGcopy_to_user.S
index ff630dc..5c358af 100644
--- a/arch/sparc/lib/NGcopy_to_user.S
+++ b/arch/sparc/lib/NGcopy_to_user.S
@@ -3,11 +3,11 @@
* Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net)
*/
-#define EX_ST(x) \
+#define EX_ST(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __ret_one_asi;\
+ .word 98b, y; \
.text; \
.align 4;
diff --git a/arch/sparc/lib/NGmemcpy.S b/arch/sparc/lib/NGmemcpy.S
index 96a14ca..d88c4ed 100644
--- a/arch/sparc/lib/NGmemcpy.S
+++ b/arch/sparc/lib/NGmemcpy.S
@@ -4,6 +4,7 @@
*/
#ifdef __KERNEL__
+#include <linux/linkage.h>
#include <asm/asi.h>
#include <asm/thread_info.h>
#define GLOBAL_SPARE %g7
@@ -27,15 +28,11 @@
#endif
#ifndef EX_LD
-#define EX_LD(x) x
+#define EX_LD(x,y) x
#endif
#ifndef EX_ST
-#define EX_ST(x) x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x) x
+#define EX_ST(x,y) x
#endif
#ifndef LOAD
@@ -79,6 +76,92 @@
.register %g3,#scratch
.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x) x
+__restore_asi:
+ ret
+ wr %g0, ASI_AIUS, %asi
+ restore
+ENTRY(NG_ret_i2_plus_i4_plus_1)
+ ba,pt %xcc, __restore_asi
+ add %i2, %i5, %i0
+ENDPROC(NG_ret_i2_plus_i4_plus_1)
+ENTRY(NG_ret_i2_plus_g1)
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1)
+ENTRY(NG_ret_i2_plus_g1_minus_8)
+ sub %g1, 8, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_8)
+ENTRY(NG_ret_i2_plus_g1_minus_16)
+ sub %g1, 16, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_16)
+ENTRY(NG_ret_i2_plus_g1_minus_24)
+ sub %g1, 24, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_24)
+ENTRY(NG_ret_i2_plus_g1_minus_32)
+ sub %g1, 32, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_32)
+ENTRY(NG_ret_i2_plus_g1_minus_40)
+ sub %g1, 40, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_40)
+ENTRY(NG_ret_i2_plus_g1_minus_48)
+ sub %g1, 48, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_48)
+ENTRY(NG_ret_i2_plus_g1_minus_56)
+ sub %g1, 56, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_minus_56)
+ENTRY(NG_ret_i2_plus_i4)
+ ba,pt %xcc, __restore_asi
+ add %i2, %i4, %i0
+ENDPROC(NG_ret_i2_plus_i4)
+ENTRY(NG_ret_i2_plus_i4_minus_8)
+ sub %i4, 8, %i4
+ ba,pt %xcc, __restore_asi
+ add %i2, %i4, %i0
+ENDPROC(NG_ret_i2_plus_i4_minus_8)
+ENTRY(NG_ret_i2_plus_8)
+ ba,pt %xcc, __restore_asi
+ add %i2, 8, %i0
+ENDPROC(NG_ret_i2_plus_8)
+ENTRY(NG_ret_i2_plus_4)
+ ba,pt %xcc, __restore_asi
+ add %i2, 4, %i0
+ENDPROC(NG_ret_i2_plus_4)
+ENTRY(NG_ret_i2_plus_1)
+ ba,pt %xcc, __restore_asi
+ add %i2, 1, %i0
+ENDPROC(NG_ret_i2_plus_1)
+ENTRY(NG_ret_i2_plus_g1_plus_1)
+ add %g1, 1, %g1
+ ba,pt %xcc, __restore_asi
+ add %i2, %g1, %i0
+ENDPROC(NG_ret_i2_plus_g1_plus_1)
+ENTRY(NG_ret_i2)
+ ba,pt %xcc, __restore_asi
+ mov %i2, %i0
+ENDPROC(NG_ret_i2)
+ENTRY(NG_ret_i2_and_7_plus_i4)
+ and %i2, 7, %i2
+ ba,pt %xcc, __restore_asi
+ add %i2, %i4, %i0
+ENDPROC(NG_ret_i2_and_7_plus_i4)
+#endif
+
.align 64
.globl FUNC_NAME
@@ -126,8 +209,8 @@
sub %g0, %i4, %i4 ! bytes to align dst
sub %i2, %i4, %i2
1: subcc %i4, 1, %i4
- EX_LD(LOAD(ldub, %i1, %g1))
- EX_ST(STORE(stb, %g1, %o0))
+ EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_i4_plus_1)
+ EX_ST(STORE(stb, %g1, %o0), NG_ret_i2_plus_i4_plus_1)
add %i1, 1, %i1
bne,pt %XCC, 1b
add %o0, 1, %o0
@@ -160,7 +243,7 @@
and %i4, 0x7, GLOBAL_SPARE
sll GLOBAL_SPARE, 3, GLOBAL_SPARE
mov 64, %i5
- EX_LD(LOAD_TWIN(%i1, %g2, %g3))
+ EX_LD(LOAD_TWIN(%i1, %g2, %g3), NG_ret_i2_plus_g1)
sub %i5, GLOBAL_SPARE, %i5
mov 16, %o4
mov 32, %o5
@@ -178,31 +261,31 @@
srlx WORD3, PRE_SHIFT, TMP; \
or WORD2, TMP, WORD2;
-8: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3))
+8: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1)
MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1)
LOAD(prefetch, %i1 + %i3, #one_read)
- EX_ST(STORE_INIT(%g2, %o0 + 0x00))
- EX_ST(STORE_INIT(%g3, %o0 + 0x08))
+ EX_ST(STORE_INIT(%g2, %o0 + 0x00), NG_ret_i2_plus_g1)
+ EX_ST(STORE_INIT(%g3, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
- EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3))
+ EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16)
MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1)
- EX_ST(STORE_INIT(%o2, %o0 + 0x10))
- EX_ST(STORE_INIT(%o3, %o0 + 0x18))
+ EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+ EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
- EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+ EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1)
- EX_ST(STORE_INIT(%g2, %o0 + 0x20))
- EX_ST(STORE_INIT(%g3, %o0 + 0x28))
+ EX_ST(STORE_INIT(%g2, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+ EX_ST(STORE_INIT(%g3, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
- EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3))
+ EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48)
add %i1, 64, %i1
MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1)
- EX_ST(STORE_INIT(%o2, %o0 + 0x30))
- EX_ST(STORE_INIT(%o3, %o0 + 0x38))
+ EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+ EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
subcc %g1, 64, %g1
bne,pt %XCC, 8b
@@ -211,31 +294,31 @@
ba,pt %XCC, 60f
add %i1, %i4, %i1
-9: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3))
+9: EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3), NG_ret_i2_plus_g1)
MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1)
LOAD(prefetch, %i1 + %i3, #one_read)
- EX_ST(STORE_INIT(%g3, %o0 + 0x00))
- EX_ST(STORE_INIT(%o2, %o0 + 0x08))
+ EX_ST(STORE_INIT(%g3, %o0 + 0x00), NG_ret_i2_plus_g1)
+ EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
- EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3))
+ EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3), NG_ret_i2_plus_g1_minus_16)
MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1)
- EX_ST(STORE_INIT(%o3, %o0 + 0x10))
- EX_ST(STORE_INIT(%g2, %o0 + 0x18))
+ EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+ EX_ST(STORE_INIT(%g2, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
- EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+ EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1)
- EX_ST(STORE_INIT(%g3, %o0 + 0x20))
- EX_ST(STORE_INIT(%o2, %o0 + 0x28))
+ EX_ST(STORE_INIT(%g3, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+ EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
- EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3))
+ EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3), NG_ret_i2_plus_g1_minus_48)
add %i1, 64, %i1
MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1)
- EX_ST(STORE_INIT(%o3, %o0 + 0x30))
- EX_ST(STORE_INIT(%g2, %o0 + 0x38))
+ EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+ EX_ST(STORE_INIT(%g2, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
subcc %g1, 64, %g1
bne,pt %XCC, 9b
@@ -249,25 +332,25 @@
* one twin load ahead, then add 8 back into source when
* we finish the loop.
*/
- EX_LD(LOAD_TWIN(%i1, %o4, %o5))
+ EX_LD(LOAD_TWIN(%i1, %o4, %o5), NG_ret_i2_plus_g1)
mov 16, %o7
mov 32, %g2
mov 48, %g3
mov 64, %o1
-1: EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+1: EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1)
LOAD(prefetch, %i1 + %o1, #one_read)
- EX_ST(STORE_INIT(%o5, %o0 + 0x00)) ! initializes cache line
- EX_ST(STORE_INIT(%o2, %o0 + 0x08))
- EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5))
- EX_ST(STORE_INIT(%o3, %o0 + 0x10))
- EX_ST(STORE_INIT(%o4, %o0 + 0x18))
- EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3))
- EX_ST(STORE_INIT(%o5, %o0 + 0x20))
- EX_ST(STORE_INIT(%o2, %o0 + 0x28))
- EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5))
+ EX_ST(STORE_INIT(%o5, %o0 + 0x00), NG_ret_i2_plus_g1) ! initializes cache line
+ EX_ST(STORE_INIT(%o2, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
+ EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16)
+ EX_ST(STORE_INIT(%o3, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+ EX_ST(STORE_INIT(%o4, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
+ EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
+ EX_ST(STORE_INIT(%o5, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+ EX_ST(STORE_INIT(%o2, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
+ EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5), NG_ret_i2_plus_g1_minus_48)
add %i1, 64, %i1
- EX_ST(STORE_INIT(%o3, %o0 + 0x30))
- EX_ST(STORE_INIT(%o4, %o0 + 0x38))
+ EX_ST(STORE_INIT(%o3, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+ EX_ST(STORE_INIT(%o4, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
subcc %g1, 64, %g1
bne,pt %XCC, 1b
add %o0, 64, %o0
@@ -282,20 +365,20 @@
mov 32, %g2
mov 48, %g3
mov 64, %o1
-1: EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5))
- EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+1: EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5), NG_ret_i2_plus_g1)
+ EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3), NG_ret_i2_plus_g1)
LOAD(prefetch, %i1 + %o1, #one_read)
- EX_ST(STORE_INIT(%o4, %o0 + 0x00)) ! initializes cache line
- EX_ST(STORE_INIT(%o5, %o0 + 0x08))
- EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5))
- EX_ST(STORE_INIT(%o2, %o0 + 0x10))
- EX_ST(STORE_INIT(%o3, %o0 + 0x18))
- EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3))
+ EX_ST(STORE_INIT(%o4, %o0 + 0x00), NG_ret_i2_plus_g1) ! initializes cache line
+ EX_ST(STORE_INIT(%o5, %o0 + 0x08), NG_ret_i2_plus_g1_minus_8)
+ EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5), NG_ret_i2_plus_g1_minus_16)
+ EX_ST(STORE_INIT(%o2, %o0 + 0x10), NG_ret_i2_plus_g1_minus_16)
+ EX_ST(STORE_INIT(%o3, %o0 + 0x18), NG_ret_i2_plus_g1_minus_24)
+ EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3), NG_ret_i2_plus_g1_minus_32)
add %i1, 64, %i1
- EX_ST(STORE_INIT(%o4, %o0 + 0x20))
- EX_ST(STORE_INIT(%o5, %o0 + 0x28))
- EX_ST(STORE_INIT(%o2, %o0 + 0x30))
- EX_ST(STORE_INIT(%o3, %o0 + 0x38))
+ EX_ST(STORE_INIT(%o4, %o0 + 0x20), NG_ret_i2_plus_g1_minus_32)
+ EX_ST(STORE_INIT(%o5, %o0 + 0x28), NG_ret_i2_plus_g1_minus_40)
+ EX_ST(STORE_INIT(%o2, %o0 + 0x30), NG_ret_i2_plus_g1_minus_48)
+ EX_ST(STORE_INIT(%o3, %o0 + 0x38), NG_ret_i2_plus_g1_minus_56)
subcc %g1, 64, %g1
bne,pt %XCC, 1b
add %o0, 64, %o0
@@ -321,28 +404,28 @@
andn %i2, 0xf, %i4
and %i2, 0xf, %i2
1: subcc %i4, 0x10, %i4
- EX_LD(LOAD(ldx, %i1, %o4))
+ EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_i4)
add %i1, 0x08, %i1
- EX_LD(LOAD(ldx, %i1, %g1))
+ EX_LD(LOAD(ldx, %i1, %g1), NG_ret_i2_plus_i4)
sub %i1, 0x08, %i1
- EX_ST(STORE(stx, %o4, %i1 + %i3))
+ EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_i4)
add %i1, 0x8, %i1
- EX_ST(STORE(stx, %g1, %i1 + %i3))
+ EX_ST(STORE(stx, %g1, %i1 + %i3), NG_ret_i2_plus_i4_minus_8)
bgu,pt %XCC, 1b
add %i1, 0x8, %i1
73: andcc %i2, 0x8, %g0
be,pt %XCC, 1f
nop
sub %i2, 0x8, %i2
- EX_LD(LOAD(ldx, %i1, %o4))
- EX_ST(STORE(stx, %o4, %i1 + %i3))
+ EX_LD(LOAD(ldx, %i1, %o4), NG_ret_i2_plus_8)
+ EX_ST(STORE(stx, %o4, %i1 + %i3), NG_ret_i2_plus_8)
add %i1, 0x8, %i1
1: andcc %i2, 0x4, %g0
be,pt %XCC, 1f
nop
sub %i2, 0x4, %i2
- EX_LD(LOAD(lduw, %i1, %i5))
- EX_ST(STORE(stw, %i5, %i1 + %i3))
+ EX_LD(LOAD(lduw, %i1, %i5), NG_ret_i2_plus_4)
+ EX_ST(STORE(stw, %i5, %i1 + %i3), NG_ret_i2_plus_4)
add %i1, 0x4, %i1
1: cmp %i2, 0
be,pt %XCC, 85f
@@ -358,8 +441,8 @@
sub %i2, %g1, %i2
1: subcc %g1, 1, %g1
- EX_LD(LOAD(ldub, %i1, %i5))
- EX_ST(STORE(stb, %i5, %i1 + %i3))
+ EX_LD(LOAD(ldub, %i1, %i5), NG_ret_i2_plus_g1_plus_1)
+ EX_ST(STORE(stb, %i5, %i1 + %i3), NG_ret_i2_plus_g1_plus_1)
bgu,pt %icc, 1b
add %i1, 1, %i1
@@ -375,16 +458,16 @@
8: mov 64, %i3
andn %i1, 0x7, %i1
- EX_LD(LOAD(ldx, %i1, %g2))
+ EX_LD(LOAD(ldx, %i1, %g2), NG_ret_i2)
sub %i3, %g1, %i3
andn %i2, 0x7, %i4
sllx %g2, %g1, %g2
1: add %i1, 0x8, %i1
- EX_LD(LOAD(ldx, %i1, %g3))
+ EX_LD(LOAD(ldx, %i1, %g3), NG_ret_i2_and_7_plus_i4)
subcc %i4, 0x8, %i4
srlx %g3, %i3, %i5
or %i5, %g2, %i5
- EX_ST(STORE(stx, %i5, %o0))
+ EX_ST(STORE(stx, %i5, %o0), NG_ret_i2_and_7_plus_i4)
add %o0, 0x8, %o0
bgu,pt %icc, 1b
sllx %g3, %g1, %g2
@@ -404,8 +487,8 @@
1:
subcc %i2, 4, %i2
- EX_LD(LOAD(lduw, %i1, %g1))
- EX_ST(STORE(stw, %g1, %i1 + %i3))
+ EX_LD(LOAD(lduw, %i1, %g1), NG_ret_i2_plus_4)
+ EX_ST(STORE(stw, %g1, %i1 + %i3), NG_ret_i2_plus_4)
bgu,pt %XCC, 1b
add %i1, 4, %i1
@@ -415,8 +498,8 @@
.align 32
90:
subcc %i2, 1, %i2
- EX_LD(LOAD(ldub, %i1, %g1))
- EX_ST(STORE(stb, %g1, %i1 + %i3))
+ EX_LD(LOAD(ldub, %i1, %g1), NG_ret_i2_plus_1)
+ EX_ST(STORE(stb, %g1, %i1 + %i3), NG_ret_i2_plus_1)
bgu,pt %XCC, 90b
add %i1, 1, %i1
ret
diff --git a/arch/sparc/lib/U1copy_from_user.S b/arch/sparc/lib/U1copy_from_user.S
index ecc5692..bb6ff73 100644
--- a/arch/sparc/lib/U1copy_from_user.S
+++ b/arch/sparc/lib/U1copy_from_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
*/
-#define EX_LD(x) \
+#define EX_LD(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one; \
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_LD_FP(x) \
+#define EX_LD_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_fp;\
+ .word 98b, y; \
.text; \
.align 4;
diff --git a/arch/sparc/lib/U1copy_to_user.S b/arch/sparc/lib/U1copy_to_user.S
index 9eea392..ed92ce73 100644
--- a/arch/sparc/lib/U1copy_to_user.S
+++ b/arch/sparc/lib/U1copy_to_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
*/
-#define EX_ST(x) \
+#define EX_ST(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one; \
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_ST_FP(x) \
+#define EX_ST_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_fp;\
+ .word 98b, y; \
.text; \
.align 4;
diff --git a/arch/sparc/lib/U1memcpy.S b/arch/sparc/lib/U1memcpy.S
index 3e6209e..4f0d50b 100644
--- a/arch/sparc/lib/U1memcpy.S
+++ b/arch/sparc/lib/U1memcpy.S
@@ -5,8 +5,10 @@
*/
#ifdef __KERNEL__
+#include <linux/linkage.h>
#include <asm/visasm.h>
#include <asm/asi.h>
+#include <asm/export.h>
#define GLOBAL_SPARE g7
#else
#define GLOBAL_SPARE g5
@@ -23,21 +25,17 @@
#endif
#ifndef EX_LD
-#define EX_LD(x) x
+#define EX_LD(x,y) x
#endif
#ifndef EX_LD_FP
-#define EX_LD_FP(x) x
+#define EX_LD_FP(x,y) x
#endif
#ifndef EX_ST
-#define EX_ST(x) x
+#define EX_ST(x,y) x
#endif
#ifndef EX_ST_FP
-#define EX_ST_FP(x) x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x) x
+#define EX_ST_FP(x,y) x
#endif
#ifndef LOAD
@@ -78,53 +76,169 @@
faligndata %f7, %f8, %f60; \
faligndata %f8, %f9, %f62;
-#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, len, jmptgt) \
- EX_LD_FP(LOAD_BLK(%src, %fdest)); \
- EX_ST_FP(STORE_BLK(%fsrc, %dest)); \
- add %src, 0x40, %src; \
- subcc %len, 0x40, %len; \
- be,pn %xcc, jmptgt; \
- add %dest, 0x40, %dest; \
+#define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, jmptgt) \
+ EX_LD_FP(LOAD_BLK(%src, %fdest), U1_gs_80_fp); \
+ EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_80_fp); \
+ add %src, 0x40, %src; \
+ subcc %GLOBAL_SPARE, 0x40, %GLOBAL_SPARE; \
+ be,pn %xcc, jmptgt; \
+ add %dest, 0x40, %dest; \
-#define LOOP_CHUNK1(src, dest, len, branch_dest) \
- MAIN_LOOP_CHUNK(src, dest, f0, f48, len, branch_dest)
-#define LOOP_CHUNK2(src, dest, len, branch_dest) \
- MAIN_LOOP_CHUNK(src, dest, f16, f48, len, branch_dest)
-#define LOOP_CHUNK3(src, dest, len, branch_dest) \
- MAIN_LOOP_CHUNK(src, dest, f32, f48, len, branch_dest)
+#define LOOP_CHUNK1(src, dest, branch_dest) \
+ MAIN_LOOP_CHUNK(src, dest, f0, f48, branch_dest)
+#define LOOP_CHUNK2(src, dest, branch_dest) \
+ MAIN_LOOP_CHUNK(src, dest, f16, f48, branch_dest)
+#define LOOP_CHUNK3(src, dest, branch_dest) \
+ MAIN_LOOP_CHUNK(src, dest, f32, f48, branch_dest)
#define DO_SYNC membar #Sync;
#define STORE_SYNC(dest, fsrc) \
- EX_ST_FP(STORE_BLK(%fsrc, %dest)); \
+ EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_80_fp); \
add %dest, 0x40, %dest; \
DO_SYNC
#define STORE_JUMP(dest, fsrc, target) \
- EX_ST_FP(STORE_BLK(%fsrc, %dest)); \
+ EX_ST_FP(STORE_BLK(%fsrc, %dest), U1_gs_40_fp); \
add %dest, 0x40, %dest; \
ba,pt %xcc, target; \
nop;
-#define FINISH_VISCHUNK(dest, f0, f1, left) \
- subcc %left, 8, %left;\
- bl,pn %xcc, 95f; \
- faligndata %f0, %f1, %f48; \
- EX_ST_FP(STORE(std, %f48, %dest)); \
+#define FINISH_VISCHUNK(dest, f0, f1) \
+ subcc %g3, 8, %g3; \
+ bl,pn %xcc, 95f; \
+ faligndata %f0, %f1, %f48; \
+ EX_ST_FP(STORE(std, %f48, %dest), U1_g3_8_fp); \
add %dest, 8, %dest;
-#define UNEVEN_VISCHUNK_LAST(dest, f0, f1, left) \
- subcc %left, 8, %left; \
- bl,pn %xcc, 95f; \
+#define UNEVEN_VISCHUNK_LAST(dest, f0, f1) \
+ subcc %g3, 8, %g3; \
+ bl,pn %xcc, 95f; \
fsrc2 %f0, %f1;
-#define UNEVEN_VISCHUNK(dest, f0, f1, left) \
- UNEVEN_VISCHUNK_LAST(dest, f0, f1, left) \
+#define UNEVEN_VISCHUNK(dest, f0, f1) \
+ UNEVEN_VISCHUNK_LAST(dest, f0, f1) \
ba,a,pt %xcc, 93f;
.register %g2,#scratch
.register %g3,#scratch
.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x) x
+ENTRY(U1_g1_1_fp)
+ VISExitHalf
+ add %g1, 1, %g1
+ add %g1, %g2, %g1
+ retl
+ add %g1, %o2, %o0
+ENDPROC(U1_g1_1_fp)
+ENTRY(U1_g2_0_fp)
+ VISExitHalf
+ retl
+ add %g2, %o2, %o0
+ENDPROC(U1_g2_0_fp)
+ENTRY(U1_g2_8_fp)
+ VISExitHalf
+ add %g2, 8, %g2
+ retl
+ add %g2, %o2, %o0
+ENDPROC(U1_g2_8_fp)
+ENTRY(U1_gs_0_fp)
+ VISExitHalf
+ add %GLOBAL_SPARE, %g3, %o0
+ retl
+ add %o0, %o2, %o0
+ENDPROC(U1_gs_0_fp)
+ENTRY(U1_gs_80_fp)
+ VISExitHalf
+ add %GLOBAL_SPARE, 0x80, %GLOBAL_SPARE
+ add %GLOBAL_SPARE, %g3, %o0
+ retl
+ add %o0, %o2, %o0
+ENDPROC(U1_gs_80_fp)
+ENTRY(U1_gs_40_fp)
+ VISExitHalf
+ add %GLOBAL_SPARE, 0x40, %GLOBAL_SPARE
+ add %GLOBAL_SPARE, %g3, %o0
+ retl
+ add %o0, %o2, %o0
+ENDPROC(U1_gs_40_fp)
+ENTRY(U1_g3_0_fp)
+ VISExitHalf
+ retl
+ add %g3, %o2, %o0
+ENDPROC(U1_g3_0_fp)
+ENTRY(U1_g3_8_fp)
+ VISExitHalf
+ add %g3, 8, %g3
+ retl
+ add %g3, %o2, %o0
+ENDPROC(U1_g3_8_fp)
+ENTRY(U1_o2_0_fp)
+ VISExitHalf
+ retl
+ mov %o2, %o0
+ENDPROC(U1_o2_0_fp)
+ENTRY(U1_o2_1_fp)
+ VISExitHalf
+ retl
+ add %o2, 1, %o0
+ENDPROC(U1_o2_1_fp)
+ENTRY(U1_gs_0)
+ VISExitHalf
+ retl
+ add %GLOBAL_SPARE, %o2, %o0
+ENDPROC(U1_gs_0)
+ENTRY(U1_gs_8)
+ VISExitHalf
+ add %GLOBAL_SPARE, %o2, %GLOBAL_SPARE
+ retl
+ add %GLOBAL_SPARE, 0x8, %o0
+ENDPROC(U1_gs_8)
+ENTRY(U1_gs_10)
+ VISExitHalf
+ add %GLOBAL_SPARE, %o2, %GLOBAL_SPARE
+ retl
+ add %GLOBAL_SPARE, 0x10, %o0
+ENDPROC(U1_gs_10)
+ENTRY(U1_o2_0)
+ retl
+ mov %o2, %o0
+ENDPROC(U1_o2_0)
+ENTRY(U1_o2_8)
+ retl
+ add %o2, 8, %o0
+ENDPROC(U1_o2_8)
+ENTRY(U1_o2_4)
+ retl
+ add %o2, 4, %o0
+ENDPROC(U1_o2_4)
+ENTRY(U1_o2_1)
+ retl
+ add %o2, 1, %o0
+ENDPROC(U1_o2_1)
+ENTRY(U1_g1_0)
+ retl
+ add %g1, %o2, %o0
+ENDPROC(U1_g1_0)
+ENTRY(U1_g1_1)
+ add %g1, 1, %g1
+ retl
+ add %g1, %o2, %o0
+ENDPROC(U1_g1_1)
+ENTRY(U1_gs_0_o2_adj)
+ and %o2, 7, %o2
+ retl
+ add %GLOBAL_SPARE, %o2, %o0
+ENDPROC(U1_gs_0_o2_adj)
+ENTRY(U1_gs_8_o2_adj)
+ and %o2, 7, %o2
+ add %GLOBAL_SPARE, 8, %GLOBAL_SPARE
+ retl
+ add %GLOBAL_SPARE, %o2, %o0
+ENDPROC(U1_gs_8_o2_adj)
+#endif
+
.align 64
.globl FUNC_NAME
@@ -166,8 +280,8 @@
and %g2, 0x38, %g2
1: subcc %g1, 0x1, %g1
- EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3))
- EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE))
+ EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3), U1_g1_1_fp)
+ EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE), U1_g1_1_fp)
bgu,pt %XCC, 1b
add %o1, 0x1, %o1
@@ -178,20 +292,20 @@
be,pt %icc, 3f
alignaddr %o1, %g0, %o1
- EX_LD_FP(LOAD(ldd, %o1, %f4))
-1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6))
+ EX_LD_FP(LOAD(ldd, %o1, %f4), U1_g2_0_fp)
+1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6), U1_g2_0_fp)
add %o1, 0x8, %o1
subcc %g2, 0x8, %g2
faligndata %f4, %f6, %f0
- EX_ST_FP(STORE(std, %f0, %o0))
+ EX_ST_FP(STORE(std, %f0, %o0), U1_g2_8_fp)
be,pn %icc, 3f
add %o0, 0x8, %o0
- EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4), U1_g2_0_fp)
add %o1, 0x8, %o1
subcc %g2, 0x8, %g2
faligndata %f6, %f4, %f0
- EX_ST_FP(STORE(std, %f0, %o0))
+ EX_ST_FP(STORE(std, %f0, %o0), U1_g2_8_fp)
bne,pt %icc, 1b
add %o0, 0x8, %o0
@@ -214,13 +328,13 @@
add %g1, %GLOBAL_SPARE, %g1
subcc %o2, %g3, %o2
- EX_LD_FP(LOAD_BLK(%o1, %f0))
+ EX_LD_FP(LOAD_BLK(%o1, %f0), U1_gs_0_fp)
add %o1, 0x40, %o1
add %g1, %g3, %g1
- EX_LD_FP(LOAD_BLK(%o1, %f16))
+ EX_LD_FP(LOAD_BLK(%o1, %f16), U1_gs_0_fp)
add %o1, 0x40, %o1
sub %GLOBAL_SPARE, 0x80, %GLOBAL_SPARE
- EX_LD_FP(LOAD_BLK(%o1, %f32))
+ EX_LD_FP(LOAD_BLK(%o1, %f32), U1_gs_80_fp)
add %o1, 0x40, %o1
/* There are 8 instances of the unrolled loop,
@@ -240,11 +354,11 @@
.align 64
1: FREG_FROB(f0, f2, f4, f6, f8, f10,f12,f14,f16)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f32,f34,f36,f38,f40,f42,f44,f46,f0)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f0, %f2, %f48
1: FREG_FROB(f16,f18,f20,f22,f24,f26,f28,f30,f32)
@@ -261,11 +375,11 @@
STORE_JUMP(o0, f48, 56f)
1: FREG_FROB(f2, f4, f6, f8, f10,f12,f14,f16,f18)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f34,f36,f38,f40,f42,f44,f46,f0, f2)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f2, %f4, %f48
1: FREG_FROB(f18,f20,f22,f24,f26,f28,f30,f32,f34)
@@ -282,11 +396,11 @@
STORE_JUMP(o0, f48, 57f)
1: FREG_FROB(f4, f6, f8, f10,f12,f14,f16,f18,f20)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f36,f38,f40,f42,f44,f46,f0, f2, f4)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f4, %f6, %f48
1: FREG_FROB(f20,f22,f24,f26,f28,f30,f32,f34,f36)
@@ -303,11 +417,11 @@
STORE_JUMP(o0, f48, 58f)
1: FREG_FROB(f6, f8, f10,f12,f14,f16,f18,f20,f22)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f38,f40,f42,f44,f46,f0, f2, f4, f6)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f6, %f8, %f48
1: FREG_FROB(f22,f24,f26,f28,f30,f32,f34,f36,f38)
@@ -324,11 +438,11 @@
STORE_JUMP(o0, f48, 59f)
1: FREG_FROB(f8, f10,f12,f14,f16,f18,f20,f22,f24)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f40,f42,f44,f46,f0, f2, f4, f6, f8)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f8, %f10, %f48
1: FREG_FROB(f24,f26,f28,f30,f32,f34,f36,f38,f40)
@@ -345,11 +459,11 @@
STORE_JUMP(o0, f48, 60f)
1: FREG_FROB(f10,f12,f14,f16,f18,f20,f22,f24,f26)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f42,f44,f46,f0, f2, f4, f6, f8, f10)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f10, %f12, %f48
1: FREG_FROB(f26,f28,f30,f32,f34,f36,f38,f40,f42)
@@ -366,11 +480,11 @@
STORE_JUMP(o0, f48, 61f)
1: FREG_FROB(f12,f14,f16,f18,f20,f22,f24,f26,f28)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f44,f46,f0, f2, f4, f6, f8, f10,f12)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f12, %f14, %f48
1: FREG_FROB(f28,f30,f32,f34,f36,f38,f40,f42,f44)
@@ -387,11 +501,11 @@
STORE_JUMP(o0, f48, 62f)
1: FREG_FROB(f14,f16,f18,f20,f22,f24,f26,f28,f30)
- LOOP_CHUNK1(o1, o0, GLOBAL_SPARE, 1f)
+ LOOP_CHUNK1(o1, o0, 1f)
FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
- LOOP_CHUNK2(o1, o0, GLOBAL_SPARE, 2f)
+ LOOP_CHUNK2(o1, o0, 2f)
FREG_FROB(f46,f0, f2, f4, f6, f8, f10,f12,f14)
- LOOP_CHUNK3(o1, o0, GLOBAL_SPARE, 3f)
+ LOOP_CHUNK3(o1, o0, 3f)
ba,pt %xcc, 1b+4
faligndata %f14, %f16, %f48
1: FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
@@ -407,53 +521,53 @@
FREG_FROB(f30,f32,f34,f36,f38,f40,f42,f44,f46)
STORE_JUMP(o0, f48, 63f)
-40: FINISH_VISCHUNK(o0, f0, f2, g3)
-41: FINISH_VISCHUNK(o0, f2, f4, g3)
-42: FINISH_VISCHUNK(o0, f4, f6, g3)
-43: FINISH_VISCHUNK(o0, f6, f8, g3)
-44: FINISH_VISCHUNK(o0, f8, f10, g3)
-45: FINISH_VISCHUNK(o0, f10, f12, g3)
-46: FINISH_VISCHUNK(o0, f12, f14, g3)
-47: UNEVEN_VISCHUNK(o0, f14, f0, g3)
-48: FINISH_VISCHUNK(o0, f16, f18, g3)
-49: FINISH_VISCHUNK(o0, f18, f20, g3)
-50: FINISH_VISCHUNK(o0, f20, f22, g3)
-51: FINISH_VISCHUNK(o0, f22, f24, g3)
-52: FINISH_VISCHUNK(o0, f24, f26, g3)
-53: FINISH_VISCHUNK(o0, f26, f28, g3)
-54: FINISH_VISCHUNK(o0, f28, f30, g3)
-55: UNEVEN_VISCHUNK(o0, f30, f0, g3)
-56: FINISH_VISCHUNK(o0, f32, f34, g3)
-57: FINISH_VISCHUNK(o0, f34, f36, g3)
-58: FINISH_VISCHUNK(o0, f36, f38, g3)
-59: FINISH_VISCHUNK(o0, f38, f40, g3)
-60: FINISH_VISCHUNK(o0, f40, f42, g3)
-61: FINISH_VISCHUNK(o0, f42, f44, g3)
-62: FINISH_VISCHUNK(o0, f44, f46, g3)
-63: UNEVEN_VISCHUNK_LAST(o0, f46, f0, g3)
+40: FINISH_VISCHUNK(o0, f0, f2)
+41: FINISH_VISCHUNK(o0, f2, f4)
+42: FINISH_VISCHUNK(o0, f4, f6)
+43: FINISH_VISCHUNK(o0, f6, f8)
+44: FINISH_VISCHUNK(o0, f8, f10)
+45: FINISH_VISCHUNK(o0, f10, f12)
+46: FINISH_VISCHUNK(o0, f12, f14)
+47: UNEVEN_VISCHUNK(o0, f14, f0)
+48: FINISH_VISCHUNK(o0, f16, f18)
+49: FINISH_VISCHUNK(o0, f18, f20)
+50: FINISH_VISCHUNK(o0, f20, f22)
+51: FINISH_VISCHUNK(o0, f22, f24)
+52: FINISH_VISCHUNK(o0, f24, f26)
+53: FINISH_VISCHUNK(o0, f26, f28)
+54: FINISH_VISCHUNK(o0, f28, f30)
+55: UNEVEN_VISCHUNK(o0, f30, f0)
+56: FINISH_VISCHUNK(o0, f32, f34)
+57: FINISH_VISCHUNK(o0, f34, f36)
+58: FINISH_VISCHUNK(o0, f36, f38)
+59: FINISH_VISCHUNK(o0, f38, f40)
+60: FINISH_VISCHUNK(o0, f40, f42)
+61: FINISH_VISCHUNK(o0, f42, f44)
+62: FINISH_VISCHUNK(o0, f44, f46)
+63: UNEVEN_VISCHUNK_LAST(o0, f46, f0)
-93: EX_LD_FP(LOAD(ldd, %o1, %f2))
+93: EX_LD_FP(LOAD(ldd, %o1, %f2), U1_g3_0_fp)
add %o1, 8, %o1
subcc %g3, 8, %g3
faligndata %f0, %f2, %f8
- EX_ST_FP(STORE(std, %f8, %o0))
+ EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp)
bl,pn %xcc, 95f
add %o0, 8, %o0
- EX_LD_FP(LOAD(ldd, %o1, %f0))
+ EX_LD_FP(LOAD(ldd, %o1, %f0), U1_g3_0_fp)
add %o1, 8, %o1
subcc %g3, 8, %g3
faligndata %f2, %f0, %f8
- EX_ST_FP(STORE(std, %f8, %o0))
+ EX_ST_FP(STORE(std, %f8, %o0), U1_g3_8_fp)
bge,pt %xcc, 93b
add %o0, 8, %o0
95: brz,pt %o2, 2f
mov %g1, %o1
-1: EX_LD_FP(LOAD(ldub, %o1, %o3))
+1: EX_LD_FP(LOAD(ldub, %o1, %o3), U1_o2_0_fp)
add %o1, 1, %o1
subcc %o2, 1, %o2
- EX_ST_FP(STORE(stb, %o3, %o0))
+ EX_ST_FP(STORE(stb, %o3, %o0), U1_o2_1_fp)
bne,pt %xcc, 1b
add %o0, 1, %o0
@@ -469,27 +583,27 @@
72: andn %o2, 0xf, %GLOBAL_SPARE
and %o2, 0xf, %o2
-1: EX_LD(LOAD(ldx, %o1 + 0x00, %o5))
- EX_LD(LOAD(ldx, %o1 + 0x08, %g1))
+1: EX_LD(LOAD(ldx, %o1 + 0x00, %o5), U1_gs_0)
+ EX_LD(LOAD(ldx, %o1 + 0x08, %g1), U1_gs_0)
subcc %GLOBAL_SPARE, 0x10, %GLOBAL_SPARE
- EX_ST(STORE(stx, %o5, %o1 + %o3))
+ EX_ST(STORE(stx, %o5, %o1 + %o3), U1_gs_10)
add %o1, 0x8, %o1
- EX_ST(STORE(stx, %g1, %o1 + %o3))
+ EX_ST(STORE(stx, %g1, %o1 + %o3), U1_gs_8)
bgu,pt %XCC, 1b
add %o1, 0x8, %o1
73: andcc %o2, 0x8, %g0
be,pt %XCC, 1f
nop
- EX_LD(LOAD(ldx, %o1, %o5))
+ EX_LD(LOAD(ldx, %o1, %o5), U1_o2_0)
sub %o2, 0x8, %o2
- EX_ST(STORE(stx, %o5, %o1 + %o3))
+ EX_ST(STORE(stx, %o5, %o1 + %o3), U1_o2_8)
add %o1, 0x8, %o1
1: andcc %o2, 0x4, %g0
be,pt %XCC, 1f
nop
- EX_LD(LOAD(lduw, %o1, %o5))
+ EX_LD(LOAD(lduw, %o1, %o5), U1_o2_0)
sub %o2, 0x4, %o2
- EX_ST(STORE(stw, %o5, %o1 + %o3))
+ EX_ST(STORE(stw, %o5, %o1 + %o3), U1_o2_4)
add %o1, 0x4, %o1
1: cmp %o2, 0
be,pt %XCC, 85f
@@ -503,9 +617,9 @@
sub %g0, %g1, %g1
sub %o2, %g1, %o2
-1: EX_LD(LOAD(ldub, %o1, %o5))
+1: EX_LD(LOAD(ldub, %o1, %o5), U1_g1_0)
subcc %g1, 1, %g1
- EX_ST(STORE(stb, %o5, %o1 + %o3))
+ EX_ST(STORE(stb, %o5, %o1 + %o3), U1_g1_1)
bgu,pt %icc, 1b
add %o1, 1, %o1
@@ -521,16 +635,16 @@
8: mov 64, %o3
andn %o1, 0x7, %o1
- EX_LD(LOAD(ldx, %o1, %g2))
+ EX_LD(LOAD(ldx, %o1, %g2), U1_o2_0)
sub %o3, %g1, %o3
andn %o2, 0x7, %GLOBAL_SPARE
sllx %g2, %g1, %g2
-1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3))
+1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3), U1_gs_0_o2_adj)
subcc %GLOBAL_SPARE, 0x8, %GLOBAL_SPARE
add %o1, 0x8, %o1
srlx %g3, %o3, %o5
or %o5, %g2, %o5
- EX_ST(STORE(stx, %o5, %o0))
+ EX_ST(STORE(stx, %o5, %o0), U1_gs_8_o2_adj)
add %o0, 0x8, %o0
bgu,pt %icc, 1b
sllx %g3, %g1, %g2
@@ -548,9 +662,9 @@
bne,pn %XCC, 90f
sub %o0, %o1, %o3
-1: EX_LD(LOAD(lduw, %o1, %g1))
+1: EX_LD(LOAD(lduw, %o1, %g1), U1_o2_0)
subcc %o2, 4, %o2
- EX_ST(STORE(stw, %g1, %o1 + %o3))
+ EX_ST(STORE(stw, %g1, %o1 + %o3), U1_o2_4)
bgu,pt %XCC, 1b
add %o1, 4, %o1
@@ -558,12 +672,13 @@
mov EX_RETVAL(%o4), %o0
.align 32
-90: EX_LD(LOAD(ldub, %o1, %g1))
+90: EX_LD(LOAD(ldub, %o1, %g1), U1_o2_0)
subcc %o2, 1, %o2
- EX_ST(STORE(stb, %g1, %o1 + %o3))
+ EX_ST(STORE(stb, %g1, %o1 + %o3), U1_o2_1)
bgu,pt %XCC, 90b
add %o1, 1, %o1
retl
mov EX_RETVAL(%o4), %o0
.size FUNC_NAME, .-FUNC_NAME
+EXPORT_SYMBOL(FUNC_NAME)
diff --git a/arch/sparc/lib/U3copy_from_user.S b/arch/sparc/lib/U3copy_from_user.S
index 88ad73d..db73010 100644
--- a/arch/sparc/lib/U3copy_from_user.S
+++ b/arch/sparc/lib/U3copy_from_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
*/
-#define EX_LD(x) \
+#define EX_LD(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one; \
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_LD_FP(x) \
+#define EX_LD_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_fp;\
+ .word 98b, y##_fp; \
.text; \
.align 4;
diff --git a/arch/sparc/lib/U3copy_to_user.S b/arch/sparc/lib/U3copy_to_user.S
index 845139d..c4ee858 100644
--- a/arch/sparc/lib/U3copy_to_user.S
+++ b/arch/sparc/lib/U3copy_to_user.S
@@ -3,19 +3,19 @@
* Copyright (C) 1999, 2000, 2004 David S. Miller (davem@redhat.com)
*/
-#define EX_ST(x) \
+#define EX_ST(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one; \
+ .word 98b, y; \
.text; \
.align 4;
-#define EX_ST_FP(x) \
+#define EX_ST_FP(x,y) \
98: x; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one_fp;\
+ .word 98b, y##_fp; \
.text; \
.align 4;
diff --git a/arch/sparc/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S
index 491ee69..54f9870 100644
--- a/arch/sparc/lib/U3memcpy.S
+++ b/arch/sparc/lib/U3memcpy.S
@@ -4,6 +4,7 @@
*/
#ifdef __KERNEL__
+#include <linux/linkage.h>
#include <asm/visasm.h>
#include <asm/asi.h>
#define GLOBAL_SPARE %g7
@@ -22,21 +23,17 @@
#endif
#ifndef EX_LD
-#define EX_LD(x) x
+#define EX_LD(x,y) x
#endif
#ifndef EX_LD_FP
-#define EX_LD_FP(x) x
+#define EX_LD_FP(x,y) x
#endif
#ifndef EX_ST
-#define EX_ST(x) x
+#define EX_ST(x,y) x
#endif
#ifndef EX_ST_FP
-#define EX_ST_FP(x) x
-#endif
-
-#ifndef EX_RETVAL
-#define EX_RETVAL(x) x
+#define EX_ST_FP(x,y) x
#endif
#ifndef LOAD
@@ -77,6 +74,87 @@
*/
.text
+#ifndef EX_RETVAL
+#define EX_RETVAL(x) x
+__restore_fp:
+ VISExitHalf
+ retl
+ nop
+ENTRY(U3_retl_o2_plus_g2_plus_g1_plus_1_fp)
+ add %g1, 1, %g1
+ add %g2, %g1, %g2
+ ba,pt %xcc, __restore_fp
+ add %o2, %g2, %o0
+ENDPROC(U3_retl_o2_plus_g2_plus_g1_plus_1_fp)
+ENTRY(U3_retl_o2_plus_g2_fp)
+ ba,pt %xcc, __restore_fp
+ add %o2, %g2, %o0
+ENDPROC(U3_retl_o2_plus_g2_fp)
+ENTRY(U3_retl_o2_plus_g2_plus_8_fp)
+ add %g2, 8, %g2
+ ba,pt %xcc, __restore_fp
+ add %o2, %g2, %o0
+ENDPROC(U3_retl_o2_plus_g2_plus_8_fp)
+ENTRY(U3_retl_o2)
+ retl
+ mov %o2, %o0
+ENDPROC(U3_retl_o2)
+ENTRY(U3_retl_o2_plus_1)
+ retl
+ add %o2, 1, %o0
+ENDPROC(U3_retl_o2_plus_1)
+ENTRY(U3_retl_o2_plus_4)
+ retl
+ add %o2, 4, %o0
+ENDPROC(U3_retl_o2_plus_4)
+ENTRY(U3_retl_o2_plus_8)
+ retl
+ add %o2, 8, %o0
+ENDPROC(U3_retl_o2_plus_8)
+ENTRY(U3_retl_o2_plus_g1_plus_1)
+ add %g1, 1, %g1
+ retl
+ add %o2, %g1, %o0
+ENDPROC(U3_retl_o2_plus_g1_plus_1)
+ENTRY(U3_retl_o2_fp)
+ ba,pt %xcc, __restore_fp
+ mov %o2, %o0
+ENDPROC(U3_retl_o2_fp)
+ENTRY(U3_retl_o2_plus_o3_sll_6_plus_0x80_fp)
+ sll %o3, 6, %o3
+ add %o3, 0x80, %o3
+ ba,pt %xcc, __restore_fp
+ add %o2, %o3, %o0
+ENDPROC(U3_retl_o2_plus_o3_sll_6_plus_0x80_fp)
+ENTRY(U3_retl_o2_plus_o3_sll_6_plus_0x40_fp)
+ sll %o3, 6, %o3
+ add %o3, 0x40, %o3
+ ba,pt %xcc, __restore_fp
+ add %o2, %o3, %o0
+ENDPROC(U3_retl_o2_plus_o3_sll_6_plus_0x40_fp)
+ENTRY(U3_retl_o2_plus_GS_plus_0x10)
+ add GLOBAL_SPARE, 0x10, GLOBAL_SPARE
+ retl
+ add %o2, GLOBAL_SPARE, %o0
+ENDPROC(U3_retl_o2_plus_GS_plus_0x10)
+ENTRY(U3_retl_o2_plus_GS_plus_0x08)
+ add GLOBAL_SPARE, 0x08, GLOBAL_SPARE
+ retl
+ add %o2, GLOBAL_SPARE, %o0
+ENDPROC(U3_retl_o2_plus_GS_plus_0x08)
+ENTRY(U3_retl_o2_and_7_plus_GS)
+ and %o2, 7, %o2
+ retl
+ add %o2, GLOBAL_SPARE, %o2
+ENDPROC(U3_retl_o2_and_7_plus_GS)
+ENTRY(U3_retl_o2_and_7_plus_GS_plus_8)
+ add GLOBAL_SPARE, 8, GLOBAL_SPARE
+ and %o2, 7, %o2
+ retl
+ add %o2, GLOBAL_SPARE, %o2
+ENDPROC(U3_retl_o2_and_7_plus_GS_plus_8)
+#endif
+
.align 64
/* The cheetah's flexible spine, oversized liver, enlarged heart,
@@ -126,8 +204,8 @@
and %g2, 0x38, %g2
1: subcc %g1, 0x1, %g1
- EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3))
- EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE))
+ EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3), U3_retl_o2_plus_g2_plus_g1_plus_1)
+ EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE), U3_retl_o2_plus_g2_plus_g1_plus_1)
bgu,pt %XCC, 1b
add %o1, 0x1, %o1
@@ -138,20 +216,20 @@
be,pt %icc, 3f
alignaddr %o1, %g0, %o1
- EX_LD_FP(LOAD(ldd, %o1, %f4))
-1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6))
+ EX_LD_FP(LOAD(ldd, %o1, %f4), U3_retl_o2_plus_g2)
+1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6), U3_retl_o2_plus_g2)
add %o1, 0x8, %o1
subcc %g2, 0x8, %g2
faligndata %f4, %f6, %f0
- EX_ST_FP(STORE(std, %f0, %o0))
+ EX_ST_FP(STORE(std, %f0, %o0), U3_retl_o2_plus_g2_plus_8)
be,pn %icc, 3f
add %o0, 0x8, %o0
- EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4), U3_retl_o2_plus_g2)
add %o1, 0x8, %o1
subcc %g2, 0x8, %g2
faligndata %f6, %f4, %f2
- EX_ST_FP(STORE(std, %f2, %o0))
+ EX_ST_FP(STORE(std, %f2, %o0), U3_retl_o2_plus_g2_plus_8)
bne,pt %icc, 1b
add %o0, 0x8, %o0
@@ -161,25 +239,25 @@
LOAD(prefetch, %o1 + 0x080, #one_read)
LOAD(prefetch, %o1 + 0x0c0, #one_read)
LOAD(prefetch, %o1 + 0x100, #one_read)
- EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0), U3_retl_o2)
LOAD(prefetch, %o1 + 0x140, #one_read)
- EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2)
LOAD(prefetch, %o1 + 0x180, #one_read)
- EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2)
LOAD(prefetch, %o1 + 0x1c0, #one_read)
faligndata %f0, %f2, %f16
- EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2)
faligndata %f2, %f4, %f18
- EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2)
faligndata %f4, %f6, %f20
- EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2)
faligndata %f6, %f8, %f22
- EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2)
faligndata %f8, %f10, %f24
- EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2)
faligndata %f10, %f12, %f26
- EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2)
subcc GLOBAL_SPARE, 0x80, GLOBAL_SPARE
add %o1, 0x40, %o1
@@ -190,26 +268,26 @@
.align 64
1:
- EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2_plus_o3_sll_6_plus_0x80)
faligndata %f12, %f14, %f28
- EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2_plus_o3_sll_6_plus_0x80)
faligndata %f14, %f0, %f30
- EX_ST_FP(STORE_BLK(%f16, %o0))
- EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
+ EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x80)
+ EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f0, %f2, %f16
add %o0, 0x40, %o0
- EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f2, %f4, %f18
- EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f4, %f6, %f20
- EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2_plus_o3_sll_6_plus_0x40)
subcc %o3, 0x01, %o3
faligndata %f6, %f8, %f22
- EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2_plus_o3_sll_6_plus_0x80)
faligndata %f8, %f10, %f24
- EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2_plus_o3_sll_6_plus_0x80)
LOAD(prefetch, %o1 + 0x1c0, #one_read)
faligndata %f10, %f12, %f26
bg,pt %XCC, 1b
@@ -217,29 +295,29 @@
/* Finally we copy the last full 64-byte block. */
2:
- EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2), U3_retl_o2_plus_o3_sll_6_plus_0x80)
faligndata %f12, %f14, %f28
- EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4), U3_retl_o2_plus_o3_sll_6_plus_0x80)
faligndata %f14, %f0, %f30
- EX_ST_FP(STORE_BLK(%f16, %o0))
- EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6))
+ EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x80)
+ EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f0, %f2, %f16
- EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f2, %f4, %f18
- EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f4, %f6, %f20
- EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f6, %f8, %f22
- EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14), U3_retl_o2_plus_o3_sll_6_plus_0x40)
faligndata %f8, %f10, %f24
cmp %g1, 0
be,pt %XCC, 1f
add %o0, 0x40, %o0
- EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0), U3_retl_o2_plus_o3_sll_6_plus_0x40)
1: faligndata %f10, %f12, %f26
faligndata %f12, %f14, %f28
faligndata %f14, %f0, %f30
- EX_ST_FP(STORE_BLK(%f16, %o0))
+ EX_ST_FP(STORE_BLK(%f16, %o0), U3_retl_o2_plus_o3_sll_6_plus_0x40)
add %o0, 0x40, %o0
add %o1, 0x40, %o1
membar #Sync
@@ -259,20 +337,20 @@
sub %o2, %g2, %o2
be,a,pt %XCC, 1f
- EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0), U3_retl_o2_plus_g2)
-1: EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2))
+1: EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2), U3_retl_o2_plus_g2)
add %o1, 0x8, %o1
subcc %g2, 0x8, %g2
faligndata %f0, %f2, %f8
- EX_ST_FP(STORE(std, %f8, %o0))
+ EX_ST_FP(STORE(std, %f8, %o0), U3_retl_o2_plus_g2_plus_8)
be,pn %XCC, 2f
add %o0, 0x8, %o0
- EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0))
+ EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0), U3_retl_o2_plus_g2)
add %o1, 0x8, %o1
subcc %g2, 0x8, %g2
faligndata %f2, %f0, %f8
- EX_ST_FP(STORE(std, %f8, %o0))
+ EX_ST_FP(STORE(std, %f8, %o0), U3_retl_o2_plus_g2_plus_8)
bne,pn %XCC, 1b
add %o0, 0x8, %o0
@@ -292,30 +370,33 @@
andcc %o2, 0x8, %g0
be,pt %icc, 1f
nop
- EX_LD(LOAD(ldx, %o1, %o5))
- EX_ST(STORE(stx, %o5, %o1 + %o3))
+ EX_LD(LOAD(ldx, %o1, %o5), U3_retl_o2)
+ EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2)
add %o1, 0x8, %o1
+ sub %o2, 8, %o2
1: andcc %o2, 0x4, %g0
be,pt %icc, 1f
nop
- EX_LD(LOAD(lduw, %o1, %o5))
- EX_ST(STORE(stw, %o5, %o1 + %o3))
+ EX_LD(LOAD(lduw, %o1, %o5), U3_retl_o2)
+ EX_ST(STORE(stw, %o5, %o1 + %o3), U3_retl_o2)
add %o1, 0x4, %o1
+ sub %o2, 4, %o2
1: andcc %o2, 0x2, %g0
be,pt %icc, 1f
nop
- EX_LD(LOAD(lduh, %o1, %o5))
- EX_ST(STORE(sth, %o5, %o1 + %o3))
+ EX_LD(LOAD(lduh, %o1, %o5), U3_retl_o2)
+ EX_ST(STORE(sth, %o5, %o1 + %o3), U3_retl_o2)
add %o1, 0x2, %o1
+ sub %o2, 2, %o2
1: andcc %o2, 0x1, %g0
be,pt %icc, 85f
nop
- EX_LD(LOAD(ldub, %o1, %o5))
+ EX_LD(LOAD(ldub, %o1, %o5), U3_retl_o2)
ba,pt %xcc, 85f
- EX_ST(STORE(stb, %o5, %o1 + %o3))
+ EX_ST(STORE(stb, %o5, %o1 + %o3), U3_retl_o2)
.align 64
70: /* 16 < len <= 64 */
@@ -326,26 +407,26 @@
andn %o2, 0xf, GLOBAL_SPARE
and %o2, 0xf, %o2
1: subcc GLOBAL_SPARE, 0x10, GLOBAL_SPARE
- EX_LD(LOAD(ldx, %o1 + 0x00, %o5))
- EX_LD(LOAD(ldx, %o1 + 0x08, %g1))
- EX_ST(STORE(stx, %o5, %o1 + %o3))
+ EX_LD(LOAD(ldx, %o1 + 0x00, %o5), U3_retl_o2_plus_GS_plus_0x10)
+ EX_LD(LOAD(ldx, %o1 + 0x08, %g1), U3_retl_o2_plus_GS_plus_0x10)
+ EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2_plus_GS_plus_0x10)
add %o1, 0x8, %o1
- EX_ST(STORE(stx, %g1, %o1 + %o3))
+ EX_ST(STORE(stx, %g1, %o1 + %o3), U3_retl_o2_plus_GS_plus_0x08)
bgu,pt %XCC, 1b
add %o1, 0x8, %o1
73: andcc %o2, 0x8, %g0
be,pt %XCC, 1f
nop
sub %o2, 0x8, %o2
- EX_LD(LOAD(ldx, %o1, %o5))
- EX_ST(STORE(stx, %o5, %o1 + %o3))
+ EX_LD(LOAD(ldx, %o1, %o5), U3_retl_o2_plus_8)
+ EX_ST(STORE(stx, %o5, %o1 + %o3), U3_retl_o2_plus_8)
add %o1, 0x8, %o1
1: andcc %o2, 0x4, %g0
be,pt %XCC, 1f
nop
sub %o2, 0x4, %o2
- EX_LD(LOAD(lduw, %o1, %o5))
- EX_ST(STORE(stw, %o5, %o1 + %o3))
+ EX_LD(LOAD(lduw, %o1, %o5), U3_retl_o2_plus_4)
+ EX_ST(STORE(stw, %o5, %o1 + %o3), U3_retl_o2_plus_4)
add %o1, 0x4, %o1
1: cmp %o2, 0
be,pt %XCC, 85f
@@ -361,8 +442,8 @@
sub %o2, %g1, %o2
1: subcc %g1, 1, %g1
- EX_LD(LOAD(ldub, %o1, %o5))
- EX_ST(STORE(stb, %o5, %o1 + %o3))
+ EX_LD(LOAD(ldub, %o1, %o5), U3_retl_o2_plus_g1_plus_1)
+ EX_ST(STORE(stb, %o5, %o1 + %o3), U3_retl_o2_plus_g1_plus_1)
bgu,pt %icc, 1b
add %o1, 1, %o1
@@ -378,16 +459,16 @@
8: mov 64, %o3
andn %o1, 0x7, %o1
- EX_LD(LOAD(ldx, %o1, %g2))
+ EX_LD(LOAD(ldx, %o1, %g2), U3_retl_o2)
sub %o3, %g1, %o3
andn %o2, 0x7, GLOBAL_SPARE
sllx %g2, %g1, %g2
-1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3))
+1: EX_LD(LOAD(ldx, %o1 + 0x8, %g3), U3_retl_o2_and_7_plus_GS)
subcc GLOBAL_SPARE, 0x8, GLOBAL_SPARE
add %o1, 0x8, %o1
srlx %g3, %o3, %o5
or %o5, %g2, %o5
- EX_ST(STORE(stx, %o5, %o0))
+ EX_ST(STORE(stx, %o5, %o0), U3_retl_o2_and_7_plus_GS_plus_8)
add %o0, 0x8, %o0
bgu,pt %icc, 1b
sllx %g3, %g1, %g2
@@ -407,8 +488,8 @@
1:
subcc %o2, 4, %o2
- EX_LD(LOAD(lduw, %o1, %g1))
- EX_ST(STORE(stw, %g1, %o1 + %o3))
+ EX_LD(LOAD(lduw, %o1, %g1), U3_retl_o2_plus_4)
+ EX_ST(STORE(stw, %g1, %o1 + %o3), U3_retl_o2_plus_4)
bgu,pt %XCC, 1b
add %o1, 4, %o1
@@ -418,8 +499,8 @@
.align 32
90:
subcc %o2, 1, %o2
- EX_LD(LOAD(ldub, %o1, %g1))
- EX_ST(STORE(stb, %g1, %o1 + %o3))
+ EX_LD(LOAD(ldub, %o1, %g1), U3_retl_o2_plus_1)
+ EX_ST(STORE(stb, %g1, %o1 + %o3), U3_retl_o2_plus_1)
bgu,pt %XCC, 90b
add %o1, 1, %o1
retl
diff --git a/arch/sparc/lib/VISsave.S b/arch/sparc/lib/VISsave.S
index 62c2647b..1c7b6a3 100644
--- a/arch/sparc/lib/VISsave.S
+++ b/arch/sparc/lib/VISsave.S
@@ -13,6 +13,7 @@
#include <asm/ptrace.h>
#include <asm/visasm.h>
#include <asm/thread_info.h>
+#include <asm/export.h>
/* On entry: %o5=current FPRS value, %g7 is callers address */
/* May clobber %o5, %g1, %g2, %g3, %g7, %icc, %xcc */
@@ -79,3 +80,4 @@
80: jmpl %g7 + %g0, %g0
nop
ENDPROC(VISenter)
+EXPORT_SYMBOL(VISenter)
diff --git a/arch/sparc/lib/ashldi3.S b/arch/sparc/lib/ashldi3.S
index 86f60de..c8b1cf7 100644
--- a/arch/sparc/lib/ashldi3.S
+++ b/arch/sparc/lib/ashldi3.S
@@ -6,6 +6,7 @@
*/
#include <linux/linkage.h>
+#include <asm/export.h>
.text
ENTRY(__ashldi3)
@@ -33,3 +34,4 @@
retl
nop
ENDPROC(__ashldi3)
+EXPORT_SYMBOL(__ashldi3)
diff --git a/arch/sparc/lib/ashrdi3.S b/arch/sparc/lib/ashrdi3.S
index 6eb8ba2..4310256 100644
--- a/arch/sparc/lib/ashrdi3.S
+++ b/arch/sparc/lib/ashrdi3.S
@@ -6,6 +6,7 @@
*/
#include <linux/linkage.h>
+#include <asm/export.h>
.text
ENTRY(__ashrdi3)
@@ -35,3 +36,4 @@
jmpl %o7 + 8, %g0
nop
ENDPROC(__ashrdi3)
+EXPORT_SYMBOL(__ashrdi3)
diff --git a/arch/sparc/lib/atomic_64.S b/arch/sparc/lib/atomic_64.S
index a5c5a02..1c6a1bd 100644
--- a/arch/sparc/lib/atomic_64.S
+++ b/arch/sparc/lib/atomic_64.S
@@ -6,6 +6,7 @@
#include <linux/linkage.h>
#include <asm/asi.h>
#include <asm/backoff.h>
+#include <asm/export.h>
.text
@@ -29,6 +30,7 @@
nop; \
2: BACKOFF_SPIN(%o2, %o3, 1b); \
ENDPROC(atomic_##op); \
+EXPORT_SYMBOL(atomic_##op);
#define ATOMIC_OP_RETURN(op) \
ENTRY(atomic_##op##_return) /* %o0 = increment, %o1 = atomic_ptr */ \
@@ -42,7 +44,8 @@
retl; \
sra %g1, 0, %o0; \
2: BACKOFF_SPIN(%o2, %o3, 1b); \
-ENDPROC(atomic_##op##_return);
+ENDPROC(atomic_##op##_return); \
+EXPORT_SYMBOL(atomic_##op##_return);
#define ATOMIC_FETCH_OP(op) \
ENTRY(atomic_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */ \
@@ -56,7 +59,8 @@
retl; \
sra %g1, 0, %o0; \
2: BACKOFF_SPIN(%o2, %o3, 1b); \
-ENDPROC(atomic_fetch_##op);
+ENDPROC(atomic_fetch_##op); \
+EXPORT_SYMBOL(atomic_fetch_##op);
#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
@@ -88,6 +92,7 @@
nop; \
2: BACKOFF_SPIN(%o2, %o3, 1b); \
ENDPROC(atomic64_##op); \
+EXPORT_SYMBOL(atomic64_##op);
#define ATOMIC64_OP_RETURN(op) \
ENTRY(atomic64_##op##_return) /* %o0 = increment, %o1 = atomic_ptr */ \
@@ -101,7 +106,8 @@
retl; \
op %g1, %o0, %o0; \
2: BACKOFF_SPIN(%o2, %o3, 1b); \
-ENDPROC(atomic64_##op##_return);
+ENDPROC(atomic64_##op##_return); \
+EXPORT_SYMBOL(atomic64_##op##_return);
#define ATOMIC64_FETCH_OP(op) \
ENTRY(atomic64_fetch_##op) /* %o0 = increment, %o1 = atomic_ptr */ \
@@ -115,7 +121,8 @@
retl; \
mov %g1, %o0; \
2: BACKOFF_SPIN(%o2, %o3, 1b); \
-ENDPROC(atomic64_fetch_##op);
+ENDPROC(atomic64_fetch_##op); \
+EXPORT_SYMBOL(atomic64_fetch_##op);
#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) ATOMIC64_FETCH_OP(op)
@@ -147,3 +154,4 @@
sub %g1, 1, %o0
2: BACKOFF_SPIN(%o2, %o3, 1b)
ENDPROC(atomic64_dec_if_positive)
+EXPORT_SYMBOL(atomic64_dec_if_positive)
diff --git a/arch/sparc/lib/bitops.S b/arch/sparc/lib/bitops.S
index 36f72cc..7031bf1 100644
--- a/arch/sparc/lib/bitops.S
+++ b/arch/sparc/lib/bitops.S
@@ -6,6 +6,7 @@
#include <linux/linkage.h>
#include <asm/asi.h>
#include <asm/backoff.h>
+#include <asm/export.h>
.text
@@ -29,6 +30,7 @@
nop
2: BACKOFF_SPIN(%o3, %o4, 1b)
ENDPROC(test_and_set_bit)
+EXPORT_SYMBOL(test_and_set_bit)
ENTRY(test_and_clear_bit) /* %o0=nr, %o1=addr */
BACKOFF_SETUP(%o3)
@@ -50,6 +52,7 @@
nop
2: BACKOFF_SPIN(%o3, %o4, 1b)
ENDPROC(test_and_clear_bit)
+EXPORT_SYMBOL(test_and_clear_bit)
ENTRY(test_and_change_bit) /* %o0=nr, %o1=addr */
BACKOFF_SETUP(%o3)
@@ -71,6 +74,7 @@
nop
2: BACKOFF_SPIN(%o3, %o4, 1b)
ENDPROC(test_and_change_bit)
+EXPORT_SYMBOL(test_and_change_bit)
ENTRY(set_bit) /* %o0=nr, %o1=addr */
BACKOFF_SETUP(%o3)
@@ -90,6 +94,7 @@
nop
2: BACKOFF_SPIN(%o3, %o4, 1b)
ENDPROC(set_bit)
+EXPORT_SYMBOL(set_bit)
ENTRY(clear_bit) /* %o0=nr, %o1=addr */
BACKOFF_SETUP(%o3)
@@ -109,6 +114,7 @@
nop
2: BACKOFF_SPIN(%o3, %o4, 1b)
ENDPROC(clear_bit)
+EXPORT_SYMBOL(clear_bit)
ENTRY(change_bit) /* %o0=nr, %o1=addr */
BACKOFF_SETUP(%o3)
@@ -128,3 +134,4 @@
nop
2: BACKOFF_SPIN(%o3, %o4, 1b)
ENDPROC(change_bit)
+EXPORT_SYMBOL(change_bit)
diff --git a/arch/sparc/lib/blockops.S b/arch/sparc/lib/blockops.S
index 3c77101..1f2692d5 100644
--- a/arch/sparc/lib/blockops.S
+++ b/arch/sparc/lib/blockops.S
@@ -6,6 +6,7 @@
#include <linux/linkage.h>
#include <asm/page.h>
+#include <asm/export.h>
/* Zero out 64 bytes of memory at (buf + offset).
* Assumes %g1 contains zero.
@@ -64,6 +65,7 @@
retl
nop
ENDPROC(bzero_1page)
+EXPORT_SYMBOL(bzero_1page)
ENTRY(__copy_1page)
/* NOTE: If you change the number of insns of this routine, please check
@@ -87,3 +89,4 @@
retl
nop
ENDPROC(__copy_1page)
+EXPORT_SYMBOL(__copy_1page)
diff --git a/arch/sparc/lib/bzero.S b/arch/sparc/lib/bzero.S
index 8c05811..3bb1914 100644
--- a/arch/sparc/lib/bzero.S
+++ b/arch/sparc/lib/bzero.S
@@ -5,6 +5,7 @@
*/
#include <linux/linkage.h>
+#include <asm/export.h>
.text
@@ -78,6 +79,8 @@
mov %o3, %o0
ENDPROC(__bzero)
ENDPROC(memset)
+EXPORT_SYMBOL(__bzero)
+EXPORT_SYMBOL(memset)
#define EX_ST(x,y) \
98: x,y; \
@@ -143,3 +146,4 @@
retl
clr %o0
ENDPROC(__clear_user)
+EXPORT_SYMBOL(__clear_user)
diff --git a/arch/sparc/lib/checksum_32.S b/arch/sparc/lib/checksum_32.S
index 0084c33..c9d8b62 100644
--- a/arch/sparc/lib/checksum_32.S
+++ b/arch/sparc/lib/checksum_32.S
@@ -14,6 +14,7 @@
*/
#include <asm/errno.h>
+#include <asm/export.h>
#define CSUM_BIGCHUNK(buf, offset, sum, t0, t1, t2, t3, t4, t5) \
ldd [buf + offset + 0x00], t0; \
@@ -104,6 +105,7 @@
* buffer of size 0x20. Follow the code path for that case.
*/
.globl csum_partial
+ EXPORT_SYMBOL(csum_partial)
csum_partial: /* %o0=buf, %o1=len, %o2=sum */
andcc %o0, 0x7, %g0 ! alignment problems?
bne csum_partial_fix_alignment ! yep, handle it
@@ -335,6 +337,7 @@
*/
.align 8
.globl __csum_partial_copy_sparc_generic
+ EXPORT_SYMBOL(__csum_partial_copy_sparc_generic)
__csum_partial_copy_sparc_generic:
/* %o0=src, %o1=dest, %g1=len, %g7=sum */
xor %o0, %o1, %o4 ! get changing bits
diff --git a/arch/sparc/lib/checksum_64.S b/arch/sparc/lib/checksum_64.S
index 1d230f6..f673217 100644
--- a/arch/sparc/lib/checksum_64.S
+++ b/arch/sparc/lib/checksum_64.S
@@ -13,6 +13,7 @@
* BSD4.4 portable checksum routine
*/
+#include <asm/export.h>
.text
csum_partial_fix_alignment:
@@ -37,6 +38,7 @@
.align 32
.globl csum_partial
+ EXPORT_SYMBOL(csum_partial)
csum_partial: /* %o0=buff, %o1=len, %o2=sum */
prefetch [%o0 + 0x000], #n_reads
clr %o4
diff --git a/arch/sparc/lib/clear_page.S b/arch/sparc/lib/clear_page.S
index 46272df..f30d6b7 100644
--- a/arch/sparc/lib/clear_page.S
+++ b/arch/sparc/lib/clear_page.S
@@ -10,6 +10,7 @@
#include <asm/pgtable.h>
#include <asm/spitfire.h>
#include <asm/head.h>
+#include <asm/export.h>
/* What we used to do was lock a TLB entry into a specific
* TLB slot, clear the page with interrupts disabled, then
@@ -26,6 +27,7 @@
.text
.globl _clear_page
+ EXPORT_SYMBOL(_clear_page)
_clear_page: /* %o0=dest */
ba,pt %xcc, clear_page_common
clr %o4
@@ -35,6 +37,7 @@
*/
.align 32
.globl clear_user_page
+ EXPORT_SYMBOL(clear_user_page)
clear_user_page: /* %o0=dest, %o1=vaddr */
lduw [%g6 + TI_PRE_COUNT], %o2
sethi %hi(PAGE_OFFSET), %g2
diff --git a/arch/sparc/lib/copy_in_user.S b/arch/sparc/lib/copy_in_user.S
index 302c0e6..0252b21 100644
--- a/arch/sparc/lib/copy_in_user.S
+++ b/arch/sparc/lib/copy_in_user.S
@@ -5,21 +5,37 @@
#include <linux/linkage.h>
#include <asm/asi.h>
+#include <asm/export.h>
#define XCC xcc
-#define EX(x,y) \
+#define EX(x,y,z) \
98: x,y; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_one; \
+ .word 98b, z; \
.text; \
.align 4;
+#define EX_O4(x,y) EX(x,y,__retl_o4_plus_8)
+#define EX_O2_4(x,y) EX(x,y,__retl_o2_plus_4)
+#define EX_O2_1(x,y) EX(x,y,__retl_o2_plus_1)
+
.register %g2,#scratch
.register %g3,#scratch
.text
+__retl_o4_plus_8:
+ add %o4, %o2, %o4
+ retl
+ add %o4, 8, %o0
+__retl_o2_plus_4:
+ retl
+ add %o2, 4, %o0
+__retl_o2_plus_1:
+ retl
+ add %o2, 1, %o0
+
.align 32
/* Don't try to get too fancy here, just nice and
@@ -44,8 +60,8 @@
andn %o2, 0x7, %o4
and %o2, 0x7, %o2
1: subcc %o4, 0x8, %o4
- EX(ldxa [%o1] %asi, %o5)
- EX(stxa %o5, [%o0] %asi)
+ EX_O4(ldxa [%o1] %asi, %o5)
+ EX_O4(stxa %o5, [%o0] %asi)
add %o1, 0x8, %o1
bgu,pt %XCC, 1b
add %o0, 0x8, %o0
@@ -53,8 +69,8 @@
be,pt %XCC, 1f
nop
sub %o2, 0x4, %o2
- EX(lduwa [%o1] %asi, %o5)
- EX(stwa %o5, [%o0] %asi)
+ EX_O2_4(lduwa [%o1] %asi, %o5)
+ EX_O2_4(stwa %o5, [%o0] %asi)
add %o1, 0x4, %o1
add %o0, 0x4, %o0
1: cmp %o2, 0
@@ -70,8 +86,8 @@
82:
subcc %o2, 4, %o2
- EX(lduwa [%o1] %asi, %g1)
- EX(stwa %g1, [%o0] %asi)
+ EX_O2_4(lduwa [%o1] %asi, %g1)
+ EX_O2_4(stwa %g1, [%o0] %asi)
add %o1, 4, %o1
bgu,pt %XCC, 82b
add %o0, 4, %o0
@@ -82,11 +98,12 @@
.align 32
90:
subcc %o2, 1, %o2
- EX(lduba [%o1] %asi, %g1)
- EX(stba %g1, [%o0] %asi)
+ EX_O2_1(lduba [%o1] %asi, %g1)
+ EX_O2_1(stba %g1, [%o0] %asi)
add %o1, 1, %o1
bgu,pt %XCC, 90b
add %o0, 1, %o0
retl
clr %o0
ENDPROC(___copy_in_user)
+EXPORT_SYMBOL(___copy_in_user)
diff --git a/arch/sparc/lib/copy_page.S b/arch/sparc/lib/copy_page.S
index dd16c61..7197b72 100644
--- a/arch/sparc/lib/copy_page.S
+++ b/arch/sparc/lib/copy_page.S
@@ -10,6 +10,7 @@
#include <asm/pgtable.h>
#include <asm/spitfire.h>
#include <asm/head.h>
+#include <asm/export.h>
/* What we used to do was lock a TLB entry into a specific
* TLB slot, clear the page with interrupts disabled, then
@@ -44,6 +45,7 @@
.align 32
.globl copy_user_page
.type copy_user_page,#function
+ EXPORT_SYMBOL(copy_user_page)
copy_user_page: /* %o0=dest, %o1=src, %o2=vaddr */
lduw [%g6 + TI_PRE_COUNT], %o4
sethi %hi(PAGE_OFFSET), %g2
diff --git a/arch/sparc/lib/copy_user.S b/arch/sparc/lib/copy_user.S
index ef095b6..cea644d 100644
--- a/arch/sparc/lib/copy_user.S
+++ b/arch/sparc/lib/copy_user.S
@@ -15,6 +15,7 @@
#include <asm/asmmacro.h>
#include <asm/page.h>
#include <asm/thread_info.h>
+#include <asm/export.h>
/* Work around cpp -rob */
#define ALLOC #alloc
@@ -119,6 +120,7 @@
__copy_user_begin:
.globl __copy_user
+ EXPORT_SYMBOL(__copy_user)
dword_align:
andcc %o1, 1, %g0
be 4f
diff --git a/arch/sparc/lib/csum_copy.S b/arch/sparc/lib/csum_copy.S
index e566c77..0ecbafc 100644
--- a/arch/sparc/lib/csum_copy.S
+++ b/arch/sparc/lib/csum_copy.S
@@ -3,6 +3,8 @@
* Copyright (C) 2005 David S. Miller <davem@davemloft.net>
*/
+#include <asm/export.h>
+
#ifdef __KERNEL__
#define GLOBAL_SPARE %g7
#else
@@ -63,6 +65,7 @@
add %o5, %o4, %o4
.globl FUNC_NAME
+ EXPORT_SYMBOL(FUNC_NAME)
FUNC_NAME: /* %o0=src, %o1=dst, %o2=len, %o3=sum */
LOAD(prefetch, %o0 + 0x000, #n_reads)
xor %o0, %o1, %g1
diff --git a/arch/sparc/lib/divdi3.S b/arch/sparc/lib/divdi3.S
index 9614b48..a2b5a97 100644
--- a/arch/sparc/lib/divdi3.S
+++ b/arch/sparc/lib/divdi3.S
@@ -17,6 +17,7 @@
the Free Software Foundation, 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA. */
+#include <asm/export.h>
.text
.align 4
.globl __divdi3
@@ -279,3 +280,4 @@
.LL81:
ret
restore
+EXPORT_SYMBOL(__divdi3)
diff --git a/arch/sparc/lib/ffs.S b/arch/sparc/lib/ffs.S
index b39389f..23aab14 100644
--- a/arch/sparc/lib/ffs.S
+++ b/arch/sparc/lib/ffs.S
@@ -1,4 +1,5 @@
#include <linux/linkage.h>
+#include <asm/export.h>
.register %g2,#scratch
@@ -65,6 +66,8 @@
add %o2, %g1, %o0
ENDPROC(ffs)
ENDPROC(__ffs)
+EXPORT_SYMBOL(__ffs)
+EXPORT_SYMBOL(ffs)
.section .popc_6insn_patch, "ax"
.word ffs
diff --git a/arch/sparc/lib/hweight.S b/arch/sparc/lib/hweight.S
index 95414e0..f9985f1 100644
--- a/arch/sparc/lib/hweight.S
+++ b/arch/sparc/lib/hweight.S
@@ -1,4 +1,5 @@
#include <linux/linkage.h>
+#include <asm/export.h>
.text
.align 32
@@ -7,6 +8,7 @@
nop
nop
ENDPROC(__arch_hweight8)
+EXPORT_SYMBOL(__arch_hweight8)
.section .popc_3insn_patch, "ax"
.word __arch_hweight8
sllx %o0, 64-8, %g1
@@ -19,6 +21,7 @@
nop
nop
ENDPROC(__arch_hweight16)
+EXPORT_SYMBOL(__arch_hweight16)
.section .popc_3insn_patch, "ax"
.word __arch_hweight16
sllx %o0, 64-16, %g1
@@ -31,6 +34,7 @@
nop
nop
ENDPROC(__arch_hweight32)
+EXPORT_SYMBOL(__arch_hweight32)
.section .popc_3insn_patch, "ax"
.word __arch_hweight32
sllx %o0, 64-32, %g1
@@ -43,6 +47,7 @@
nop
nop
ENDPROC(__arch_hweight64)
+EXPORT_SYMBOL(__arch_hweight64)
.section .popc_3insn_patch, "ax"
.word __arch_hweight64
retl
diff --git a/arch/sparc/lib/ipcsum.S b/arch/sparc/lib/ipcsum.S
index 4742d59..5d61648 100644
--- a/arch/sparc/lib/ipcsum.S
+++ b/arch/sparc/lib/ipcsum.S
@@ -1,4 +1,5 @@
#include <linux/linkage.h>
+#include <asm/export.h>
.text
ENTRY(ip_fast_csum) /* %o0 = iph, %o1 = ihl */
@@ -31,3 +32,4 @@
retl
and %o2, %o1, %o0
ENDPROC(ip_fast_csum)
+EXPORT_SYMBOL(ip_fast_csum)
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
deleted file mode 100644
index de5e978..0000000
--- a/arch/sparc/lib/ksyms.c
+++ /dev/null
@@ -1,174 +0,0 @@
-/*
- * Export of symbols defined in assembler
- */
-
-/* Tell string.h we don't want memcpy etc. as cpp defines */
-#define EXPORT_SYMTAB_STROPS
-
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/types.h>
-
-#include <asm/checksum.h>
-#include <asm/uaccess.h>
-#include <asm/ftrace.h>
-
-/* string functions */
-EXPORT_SYMBOL(strlen);
-EXPORT_SYMBOL(strncmp);
-
-/* mem* functions */
-extern void *__memscan_zero(void *, size_t);
-extern void *__memscan_generic(void *, int, size_t);
-extern void *__bzero(void *, size_t);
-
-EXPORT_SYMBOL(memscan);
-EXPORT_SYMBOL(__memscan_zero);
-EXPORT_SYMBOL(__memscan_generic);
-EXPORT_SYMBOL(memcmp);
-EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memmove);
-EXPORT_SYMBOL(__bzero);
-
-/* Networking helper routines. */
-EXPORT_SYMBOL(csum_partial);
-
-#ifdef CONFIG_MCOUNT
-EXPORT_SYMBOL(_mcount);
-#endif
-
-/*
- * sparc
- */
-#ifdef CONFIG_SPARC32
-extern int __ashrdi3(int, int);
-extern int __ashldi3(int, int);
-extern int __lshrdi3(int, int);
-extern int __muldi3(int, int);
-extern int __divdi3(int, int);
-
-extern void (*__copy_1page)(void *, const void *);
-extern void (*bzero_1page)(void *);
-
-extern void ___rw_read_enter(void);
-extern void ___rw_read_try(void);
-extern void ___rw_read_exit(void);
-extern void ___rw_write_enter(void);
-
-/* Networking helper routines. */
-EXPORT_SYMBOL(__csum_partial_copy_sparc_generic);
-
-/* Special internal versions of library functions. */
-EXPORT_SYMBOL(__copy_1page);
-EXPORT_SYMBOL(__memmove);
-EXPORT_SYMBOL(bzero_1page);
-
-/* Moving data to/from/in userspace. */
-EXPORT_SYMBOL(__copy_user);
-
-/* Used by asm/spinlock.h */
-#ifdef CONFIG_SMP
-EXPORT_SYMBOL(___rw_read_enter);
-EXPORT_SYMBOL(___rw_read_try);
-EXPORT_SYMBOL(___rw_read_exit);
-EXPORT_SYMBOL(___rw_write_enter);
-#endif
-
-EXPORT_SYMBOL(__ashrdi3);
-EXPORT_SYMBOL(__ashldi3);
-EXPORT_SYMBOL(__lshrdi3);
-EXPORT_SYMBOL(__muldi3);
-EXPORT_SYMBOL(__divdi3);
-#endif
-
-/*
- * sparc64
- */
-#ifdef CONFIG_SPARC64
-/* Networking helper routines. */
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
-EXPORT_SYMBOL(__csum_partial_copy_from_user);
-EXPORT_SYMBOL(__csum_partial_copy_to_user);
-EXPORT_SYMBOL(ip_fast_csum);
-
-/* Moving data to/from/in userspace. */
-EXPORT_SYMBOL(___copy_to_user);
-EXPORT_SYMBOL(___copy_from_user);
-EXPORT_SYMBOL(___copy_in_user);
-EXPORT_SYMBOL(__clear_user);
-
-/* Atomic counter implementation. */
-#define ATOMIC_OP(op) \
-EXPORT_SYMBOL(atomic_##op); \
-EXPORT_SYMBOL(atomic64_##op);
-
-#define ATOMIC_OP_RETURN(op) \
-EXPORT_SYMBOL(atomic_##op##_return); \
-EXPORT_SYMBOL(atomic64_##op##_return);
-
-#define ATOMIC_FETCH_OP(op) \
-EXPORT_SYMBOL(atomic_fetch_##op); \
-EXPORT_SYMBOL(atomic64_fetch_##op);
-
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
-
-ATOMIC_OPS(add)
-ATOMIC_OPS(sub)
-
-#undef ATOMIC_OPS
-#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op)
-
-ATOMIC_OPS(and)
-ATOMIC_OPS(or)
-ATOMIC_OPS(xor)
-
-#undef ATOMIC_OPS
-#undef ATOMIC_FETCH_OP
-#undef ATOMIC_OP_RETURN
-#undef ATOMIC_OP
-
-EXPORT_SYMBOL(atomic64_dec_if_positive);
-
-/* Atomic bit operations. */
-EXPORT_SYMBOL(test_and_set_bit);
-EXPORT_SYMBOL(test_and_clear_bit);
-EXPORT_SYMBOL(test_and_change_bit);
-EXPORT_SYMBOL(set_bit);
-EXPORT_SYMBOL(clear_bit);
-EXPORT_SYMBOL(change_bit);
-
-/* Special internal versions of library functions. */
-EXPORT_SYMBOL(_clear_page);
-EXPORT_SYMBOL(clear_user_page);
-EXPORT_SYMBOL(copy_user_page);
-
-/* RAID code needs this */
-void VISenter(void);
-EXPORT_SYMBOL(VISenter);
-
-extern void xor_vis_2(unsigned long, unsigned long *, unsigned long *);
-extern void xor_vis_3(unsigned long, unsigned long *, unsigned long *,
- unsigned long *);
-extern void xor_vis_4(unsigned long, unsigned long *, unsigned long *,
- unsigned long *, unsigned long *);
-extern void xor_vis_5(unsigned long, unsigned long *, unsigned long *,
- unsigned long *, unsigned long *, unsigned long *);
-EXPORT_SYMBOL(xor_vis_2);
-EXPORT_SYMBOL(xor_vis_3);
-EXPORT_SYMBOL(xor_vis_4);
-EXPORT_SYMBOL(xor_vis_5);
-
-extern void xor_niagara_2(unsigned long, unsigned long *, unsigned long *);
-extern void xor_niagara_3(unsigned long, unsigned long *, unsigned long *,
- unsigned long *);
-extern void xor_niagara_4(unsigned long, unsigned long *, unsigned long *,
- unsigned long *, unsigned long *);
-extern void xor_niagara_5(unsigned long, unsigned long *, unsigned long *,
- unsigned long *, unsigned long *, unsigned long *);
-
-EXPORT_SYMBOL(xor_niagara_2);
-EXPORT_SYMBOL(xor_niagara_3);
-EXPORT_SYMBOL(xor_niagara_4);
-EXPORT_SYMBOL(xor_niagara_5);
-#endif
diff --git a/arch/sparc/lib/locks.S b/arch/sparc/lib/locks.S
index 64f53f2..f38c4e5 100644
--- a/arch/sparc/lib/locks.S
+++ b/arch/sparc/lib/locks.S
@@ -10,6 +10,7 @@
#include <asm/psr.h>
#include <asm/smp.h>
#include <asm/spinlock.h>
+#include <asm/export.h>
.text
.align 4
@@ -48,6 +49,7 @@
ld [%g1], %g2
.globl ___rw_read_enter
+EXPORT_SYMBOL(___rw_read_enter)
___rw_read_enter:
orcc %g2, 0x0, %g0
bne,a ___rw_read_enter_spin_on_wlock
@@ -59,6 +61,7 @@
mov %g4, %o7
.globl ___rw_read_exit
+EXPORT_SYMBOL(___rw_read_exit)
___rw_read_exit:
orcc %g2, 0x0, %g0
bne,a ___rw_read_exit_spin_on_wlock
@@ -70,6 +73,7 @@
mov %g4, %o7
.globl ___rw_read_try
+EXPORT_SYMBOL(___rw_read_try)
___rw_read_try:
orcc %g2, 0x0, %g0
bne ___rw_read_try_spin_on_wlock
@@ -81,6 +85,7 @@
mov %g4, %o7
.globl ___rw_write_enter
+EXPORT_SYMBOL(___rw_write_enter)
___rw_write_enter:
orcc %g2, 0x0, %g0
bne ___rw_write_enter_spin_on_wlock
diff --git a/arch/sparc/lib/lshrdi3.S b/arch/sparc/lib/lshrdi3.S
index 60ebc7c..c9b9373 100644
--- a/arch/sparc/lib/lshrdi3.S
+++ b/arch/sparc/lib/lshrdi3.S
@@ -1,4 +1,5 @@
#include <linux/linkage.h>
+#include <asm/export.h>
ENTRY(__lshrdi3)
cmp %o2, 0
@@ -25,3 +26,4 @@
retl
nop
ENDPROC(__lshrdi3)
+EXPORT_SYMBOL(__lshrdi3)
diff --git a/arch/sparc/lib/mcount.S b/arch/sparc/lib/mcount.S
index 0b0ed4d..194f383 100644
--- a/arch/sparc/lib/mcount.S
+++ b/arch/sparc/lib/mcount.S
@@ -6,6 +6,7 @@
*/
#include <linux/linkage.h>
+#include <asm/export.h>
/*
* This is the main variant and is called by C code. GCC's -pg option
@@ -16,6 +17,7 @@
.align 32
.globl _mcount
.type _mcount,#function
+ EXPORT_SYMBOL(_mcount)
.globl mcount
.type mcount,#function
_mcount:
diff --git a/arch/sparc/lib/memcmp.S b/arch/sparc/lib/memcmp.S
index efa106c..cee7f30 100644
--- a/arch/sparc/lib/memcmp.S
+++ b/arch/sparc/lib/memcmp.S
@@ -6,6 +6,7 @@
#include <linux/linkage.h>
#include <asm/asm.h>
+#include <asm/export.h>
.text
ENTRY(memcmp)
@@ -25,3 +26,4 @@
2: retl
mov 0, %o0
ENDPROC(memcmp)
+EXPORT_SYMBOL(memcmp)
diff --git a/arch/sparc/lib/memcpy.S b/arch/sparc/lib/memcpy.S
index 4d8c497..8913fea 100644
--- a/arch/sparc/lib/memcpy.S
+++ b/arch/sparc/lib/memcpy.S
@@ -7,6 +7,7 @@
* Copyright (C) 1996 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
*/
+#include <asm/export.h>
#define FUNC(x) \
.globl x; \
.type x,@function; \
@@ -58,93 +59,11 @@
stb %t0, [%dst - (offset) - 0x02]; \
stb %t1, [%dst - (offset) - 0x01];
-/* Both these macros have to start with exactly the same insn */
-#define RMOVE_BIGCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
- ldd [%src - (offset) - 0x20], %t0; \
- ldd [%src - (offset) - 0x18], %t2; \
- ldd [%src - (offset) - 0x10], %t4; \
- ldd [%src - (offset) - 0x08], %t6; \
- st %t0, [%dst - (offset) - 0x20]; \
- st %t1, [%dst - (offset) - 0x1c]; \
- st %t2, [%dst - (offset) - 0x18]; \
- st %t3, [%dst - (offset) - 0x14]; \
- st %t4, [%dst - (offset) - 0x10]; \
- st %t5, [%dst - (offset) - 0x0c]; \
- st %t6, [%dst - (offset) - 0x08]; \
- st %t7, [%dst - (offset) - 0x04];
-
-#define RMOVE_BIGALIGNCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
- ldd [%src - (offset) - 0x20], %t0; \
- ldd [%src - (offset) - 0x18], %t2; \
- ldd [%src - (offset) - 0x10], %t4; \
- ldd [%src - (offset) - 0x08], %t6; \
- std %t0, [%dst - (offset) - 0x20]; \
- std %t2, [%dst - (offset) - 0x18]; \
- std %t4, [%dst - (offset) - 0x10]; \
- std %t6, [%dst - (offset) - 0x08];
-
-#define RMOVE_LASTCHUNK(src, dst, offset, t0, t1, t2, t3) \
- ldd [%src + (offset) + 0x00], %t0; \
- ldd [%src + (offset) + 0x08], %t2; \
- st %t0, [%dst + (offset) + 0x00]; \
- st %t1, [%dst + (offset) + 0x04]; \
- st %t2, [%dst + (offset) + 0x08]; \
- st %t3, [%dst + (offset) + 0x0c];
-
-#define RMOVE_SHORTCHUNK(src, dst, offset, t0, t1) \
- ldub [%src + (offset) + 0x00], %t0; \
- ldub [%src + (offset) + 0x01], %t1; \
- stb %t0, [%dst + (offset) + 0x00]; \
- stb %t1, [%dst + (offset) + 0x01];
-
-#define SMOVE_CHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, prev, shil, shir, offset2) \
- ldd [%src + (offset) + 0x00], %t0; \
- ldd [%src + (offset) + 0x08], %t2; \
- srl %t0, shir, %t5; \
- srl %t1, shir, %t6; \
- sll %t0, shil, %t0; \
- or %t5, %prev, %t5; \
- sll %t1, shil, %prev; \
- or %t6, %t0, %t0; \
- srl %t2, shir, %t1; \
- srl %t3, shir, %t6; \
- sll %t2, shil, %t2; \
- or %t1, %prev, %t1; \
- std %t4, [%dst + (offset) + (offset2) - 0x04]; \
- std %t0, [%dst + (offset) + (offset2) + 0x04]; \
- sll %t3, shil, %prev; \
- or %t6, %t2, %t4;
-
-#define SMOVE_ALIGNCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, prev, shil, shir, offset2) \
- ldd [%src + (offset) + 0x00], %t0; \
- ldd [%src + (offset) + 0x08], %t2; \
- srl %t0, shir, %t4; \
- srl %t1, shir, %t5; \
- sll %t0, shil, %t6; \
- or %t4, %prev, %t0; \
- sll %t1, shil, %prev; \
- or %t5, %t6, %t1; \
- srl %t2, shir, %t4; \
- srl %t3, shir, %t5; \
- sll %t2, shil, %t6; \
- or %t4, %prev, %t2; \
- sll %t3, shil, %prev; \
- or %t5, %t6, %t3; \
- std %t0, [%dst + (offset) + (offset2) + 0x00]; \
- std %t2, [%dst + (offset) + (offset2) + 0x08];
-
.text
.align 4
-0:
- retl
- nop ! Only bcopy returns here and it retuns void...
-
-#ifdef __KERNEL__
-FUNC(amemmove)
-FUNC(__memmove)
-#endif
FUNC(memmove)
+EXPORT_SYMBOL(memmove)
cmp %o0, %o1
mov %o0, %g7
bleu 9f
@@ -202,6 +121,7 @@
add %o0, 2, %o0
FUNC(memcpy) /* %o0=dst %o1=src %o2=len */
+EXPORT_SYMBOL(memcpy)
sub %o0, %o1, %o4
mov %o0, %g7
diff --git a/arch/sparc/lib/memmove.S b/arch/sparc/lib/memmove.S
index 857ad4f..012cdb6 100644
--- a/arch/sparc/lib/memmove.S
+++ b/arch/sparc/lib/memmove.S
@@ -5,6 +5,7 @@
*/
#include <linux/linkage.h>
+#include <asm/export.h>
.text
ENTRY(memmove) /* o0=dst o1=src o2=len */
@@ -57,3 +58,4 @@
stb %g7, [%o0 - 0x1]
ba,a,pt %xcc, 99b
ENDPROC(memmove)
+EXPORT_SYMBOL(memmove)
diff --git a/arch/sparc/lib/memscan_32.S b/arch/sparc/lib/memscan_32.S
index 4ff1657..51ce690 100644
--- a/arch/sparc/lib/memscan_32.S
+++ b/arch/sparc/lib/memscan_32.S
@@ -4,6 +4,8 @@
* Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
*/
+#include <asm/export.h>
+
/* In essence, this is just a fancy strlen. */
#define LO_MAGIC 0x01010101
@@ -13,6 +15,8 @@
.align 4
.globl __memscan_zero, __memscan_generic
.globl memscan
+EXPORT_SYMBOL(__memscan_zero)
+EXPORT_SYMBOL(__memscan_generic)
__memscan_zero:
/* %o0 = addr, %o1 = size */
cmp %o1, 0
diff --git a/arch/sparc/lib/memscan_64.S b/arch/sparc/lib/memscan_64.S
index 5686dfa..daa96f4 100644
--- a/arch/sparc/lib/memscan_64.S
+++ b/arch/sparc/lib/memscan_64.S
@@ -5,6 +5,8 @@
* Copyright (C) 1998 David S. Miller (davem@redhat.com)
*/
+ #include <asm/export.h>
+
#define HI_MAGIC 0x8080808080808080
#define LO_MAGIC 0x0101010101010101
#define ASI_PL 0x88
@@ -13,6 +15,8 @@
.align 32
.globl __memscan_zero, __memscan_generic
.globl memscan
+ EXPORT_SYMBOL(__memscan_zero)
+ EXPORT_SYMBOL(__memscan_generic)
__memscan_zero:
/* %o0 = bufp, %o1 = size */
diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S
index f75e690..bb539b4 100644
--- a/arch/sparc/lib/memset.S
+++ b/arch/sparc/lib/memset.S
@@ -9,6 +9,7 @@
*/
#include <asm/ptrace.h>
+#include <asm/export.h>
/* Work around cpp -rob */
#define ALLOC #alloc
@@ -63,6 +64,8 @@
.globl __bzero
.globl memset
+ EXPORT_SYMBOL(__bzero)
+ EXPORT_SYMBOL(memset)
.globl __memset_start, __memset_end
__memset_start:
memset:
diff --git a/arch/sparc/lib/muldi3.S b/arch/sparc/lib/muldi3.S
index 9794939..17a0f49 100644
--- a/arch/sparc/lib/muldi3.S
+++ b/arch/sparc/lib/muldi3.S
@@ -17,6 +17,7 @@
the Free Software Foundation, 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA. */
+#include <asm/export.h>
.text
.align 4
.globl __muldi3
@@ -74,3 +75,4 @@
add %l2, %l0, %i0
ret
restore %g0, %l3, %o1
+EXPORT_SYMBOL(__muldi3)
diff --git a/arch/sparc/lib/strlen.S b/arch/sparc/lib/strlen.S
index 536f835..ca0e707 100644
--- a/arch/sparc/lib/strlen.S
+++ b/arch/sparc/lib/strlen.S
@@ -7,6 +7,7 @@
#include <linux/linkage.h>
#include <asm/asm.h>
+#include <asm/export.h>
#define LO_MAGIC 0x01010101
#define HI_MAGIC 0x80808080
@@ -78,3 +79,4 @@
retl
mov 2, %o0
ENDPROC(strlen)
+EXPORT_SYMBOL(strlen)
diff --git a/arch/sparc/lib/strncmp_32.S b/arch/sparc/lib/strncmp_32.S
index c0d1b56..e3fe014 100644
--- a/arch/sparc/lib/strncmp_32.S
+++ b/arch/sparc/lib/strncmp_32.S
@@ -4,6 +4,7 @@
*/
#include <linux/linkage.h>
+#include <asm/export.h>
.text
ENTRY(strncmp)
@@ -116,3 +117,4 @@
retl
sub %o3, %o0, %o0
ENDPROC(strncmp)
+EXPORT_SYMBOL(strncmp)
diff --git a/arch/sparc/lib/strncmp_64.S b/arch/sparc/lib/strncmp_64.S
index 0656627..efb5f88 100644
--- a/arch/sparc/lib/strncmp_64.S
+++ b/arch/sparc/lib/strncmp_64.S
@@ -6,6 +6,7 @@
#include <linux/linkage.h>
#include <asm/asi.h>
+#include <asm/export.h>
.text
ENTRY(strncmp)
@@ -28,3 +29,4 @@
retl
clr %o0
ENDPROC(strncmp)
+EXPORT_SYMBOL(strncmp)
diff --git a/arch/sparc/lib/user_fixup.c b/arch/sparc/lib/user_fixup.c
deleted file mode 100644
index ac96ae2..0000000
--- a/arch/sparc/lib/user_fixup.c
+++ /dev/null
@@ -1,71 +0,0 @@
-/* user_fixup.c: Fix up user copy faults.
- *
- * Copyright (C) 2004 David S. Miller <davem@redhat.com>
- */
-
-#include <linux/compiler.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/module.h>
-
-#include <asm/uaccess.h>
-
-/* Calculating the exact fault address when using
- * block loads and stores can be very complicated.
- *
- * Instead of trying to be clever and handling all
- * of the cases, just fix things up simply here.
- */
-
-static unsigned long compute_size(unsigned long start, unsigned long size, unsigned long *offset)
-{
- unsigned long fault_addr = current_thread_info()->fault_address;
- unsigned long end = start + size;
-
- if (fault_addr < start || fault_addr >= end) {
- *offset = 0;
- } else {
- *offset = fault_addr - start;
- size = end - fault_addr;
- }
- return size;
-}
-
-unsigned long copy_from_user_fixup(void *to, const void __user *from, unsigned long size)
-{
- unsigned long offset;
-
- size = compute_size((unsigned long) from, size, &offset);
- if (likely(size))
- memset(to + offset, 0, size);
-
- return size;
-}
-EXPORT_SYMBOL(copy_from_user_fixup);
-
-unsigned long copy_to_user_fixup(void __user *to, const void *from, unsigned long size)
-{
- unsigned long offset;
-
- return compute_size((unsigned long) to, size, &offset);
-}
-EXPORT_SYMBOL(copy_to_user_fixup);
-
-unsigned long copy_in_user_fixup(void __user *to, void __user *from, unsigned long size)
-{
- unsigned long fault_addr = current_thread_info()->fault_address;
- unsigned long start = (unsigned long) to;
- unsigned long end = start + size;
-
- if (fault_addr >= start && fault_addr < end)
- return end - fault_addr;
-
- start = (unsigned long) from;
- end = start + size;
- if (fault_addr >= start && fault_addr < end)
- return end - fault_addr;
-
- return size;
-}
-EXPORT_SYMBOL(copy_in_user_fixup);
diff --git a/arch/sparc/lib/xor.S b/arch/sparc/lib/xor.S
index 2c05641..45a49cb 100644
--- a/arch/sparc/lib/xor.S
+++ b/arch/sparc/lib/xor.S
@@ -13,6 +13,7 @@
#include <asm/asi.h>
#include <asm/dcu.h>
#include <asm/spitfire.h>
+#include <asm/export.h>
/*
* Requirements:
@@ -90,6 +91,7 @@
retl
wr %g0, 0, %fprs
ENDPROC(xor_vis_2)
+EXPORT_SYMBOL(xor_vis_2)
ENTRY(xor_vis_3)
rd %fprs, %o5
@@ -156,6 +158,7 @@
retl
wr %g0, 0, %fprs
ENDPROC(xor_vis_3)
+EXPORT_SYMBOL(xor_vis_3)
ENTRY(xor_vis_4)
rd %fprs, %o5
@@ -241,6 +244,7 @@
retl
wr %g0, 0, %fprs
ENDPROC(xor_vis_4)
+EXPORT_SYMBOL(xor_vis_4)
ENTRY(xor_vis_5)
save %sp, -192, %sp
@@ -347,6 +351,7 @@
ret
restore
ENDPROC(xor_vis_5)
+EXPORT_SYMBOL(xor_vis_5)
/* Niagara versions. */
ENTRY(xor_niagara_2) /* %o0=bytes, %o1=dest, %o2=src */
@@ -393,6 +398,7 @@
ret
restore
ENDPROC(xor_niagara_2)
+EXPORT_SYMBOL(xor_niagara_2)
ENTRY(xor_niagara_3) /* %o0=bytes, %o1=dest, %o2=src1, %o3=src2 */
save %sp, -192, %sp
@@ -454,6 +460,7 @@
ret
restore
ENDPROC(xor_niagara_3)
+EXPORT_SYMBOL(xor_niagara_3)
ENTRY(xor_niagara_4) /* %o0=bytes, %o1=dest, %o2=src1, %o3=src2, %o4=src3 */
save %sp, -192, %sp
@@ -536,6 +543,7 @@
ret
restore
ENDPROC(xor_niagara_4)
+EXPORT_SYMBOL(xor_niagara_4)
ENTRY(xor_niagara_5) /* %o0=bytes, %o1=dest, %o2=src1, %o3=src2, %o4=src3, %o5=src4 */
save %sp, -192, %sp
@@ -634,3 +642,4 @@
ret
restore
ENDPROC(xor_niagara_5)
+EXPORT_SYMBOL(xor_niagara_5)
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
index 4e06750..cd0e32b 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -238,7 +238,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
pages += nr;
ret = get_user_pages_unlocked(start,
- (end - start) >> PAGE_SHIFT, write, 0, pages);
+ (end - start) >> PAGE_SHIFT, pages,
+ write ? FOLL_WRITE : 0);
/* Have to be a bit careful with return values */
if (nr > 0) {
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index f2b7711..e20fbba 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -27,6 +27,20 @@ static inline int tag_compare(unsigned long tag, unsigned long vaddr)
return (tag == (vaddr >> 22));
}
+static void flush_tsb_kernel_range_scan(unsigned long start, unsigned long end)
+{
+ unsigned long idx;
+
+ for (idx = 0; idx < KERNEL_TSB_NENTRIES; idx++) {
+ struct tsb *ent = &swapper_tsb[idx];
+ unsigned long match = idx << 13;
+
+ match |= (ent->tag << 22);
+ if (match >= start && match < end)
+ ent->tag = (1UL << TSB_TAG_INVALID_BIT);
+ }
+}
+
/* TSB flushes need only occur on the processor initiating the address
* space modification, not on each cpu the address space has run on.
* Only the TLB flush needs that treatment.
@@ -36,6 +50,9 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end)
{
unsigned long v;
+ if ((end - start) >> PAGE_SHIFT >= 2 * KERNEL_TSB_NENTRIES)
+ return flush_tsb_kernel_range_scan(start, end);
+
for (v = start; v < end; v += PAGE_SIZE) {
unsigned long hash = tsb_hash(v, PAGE_SHIFT,
KERNEL_TSB_NENTRIES);
diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S
index b4f4733..5d2fd6c 100644
--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -30,7 +30,7 @@
.text
.align 32
.globl __flush_tlb_mm
-__flush_tlb_mm: /* 18 insns */
+__flush_tlb_mm: /* 19 insns */
/* %o0=(ctx & TAG_CONTEXT_BITS), %o1=SECONDARY_CONTEXT */
ldxa [%o1] ASI_DMMU, %g2
cmp %g2, %o0
@@ -81,7 +81,7 @@
.align 32
.globl __flush_tlb_pending
-__flush_tlb_pending: /* 26 insns */
+__flush_tlb_pending: /* 27 insns */
/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
rdpr %pstate, %g7
sllx %o1, 3, %o1
@@ -113,12 +113,14 @@
.align 32
.globl __flush_tlb_kernel_range
-__flush_tlb_kernel_range: /* 16 insns */
+__flush_tlb_kernel_range: /* 31 insns */
/* %o0=start, %o1=end */
cmp %o0, %o1
be,pn %xcc, 2f
+ sub %o1, %o0, %o3
+ srlx %o3, 18, %o4
+ brnz,pn %o4, __spitfire_flush_tlb_kernel_range_slow
sethi %hi(PAGE_SIZE), %o4
- sub %o1, %o0, %o3
sub %o3, %o4, %o3
or %o0, 0x20, %o0 ! Nucleus
1: stxa %g0, [%o0 + %o3] ASI_DMMU_DEMAP
@@ -131,6 +133,41 @@
retl
nop
nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+
+__spitfire_flush_tlb_kernel_range_slow:
+ mov 63 * 8, %o4
+1: ldxa [%o4] ASI_ITLB_DATA_ACCESS, %o3
+ andcc %o3, 0x40, %g0 /* _PAGE_L_4U */
+ bne,pn %xcc, 2f
+ mov TLB_TAG_ACCESS, %o3
+ stxa %g0, [%o3] ASI_IMMU
+ stxa %g0, [%o4] ASI_ITLB_DATA_ACCESS
+ membar #Sync
+2: ldxa [%o4] ASI_DTLB_DATA_ACCESS, %o3
+ andcc %o3, 0x40, %g0
+ bne,pn %xcc, 2f
+ mov TLB_TAG_ACCESS, %o3
+ stxa %g0, [%o3] ASI_DMMU
+ stxa %g0, [%o4] ASI_DTLB_DATA_ACCESS
+ membar #Sync
+2: sub %o4, 8, %o4
+ brgez,pt %o4, 1b
+ nop
+ retl
+ nop
__spitfire_flush_tlb_mm_slow:
rdpr %pstate, %g1
@@ -285,6 +322,40 @@
retl
wrpr %g7, 0x0, %pstate
+__cheetah_flush_tlb_kernel_range: /* 31 insns */
+ /* %o0=start, %o1=end */
+ cmp %o0, %o1
+ be,pn %xcc, 2f
+ sub %o1, %o0, %o3
+ srlx %o3, 18, %o4
+ brnz,pn %o4, 3f
+ sethi %hi(PAGE_SIZE), %o4
+ sub %o3, %o4, %o3
+ or %o0, 0x20, %o0 ! Nucleus
+1: stxa %g0, [%o0 + %o3] ASI_DMMU_DEMAP
+ stxa %g0, [%o0 + %o3] ASI_IMMU_DEMAP
+ membar #Sync
+ brnz,pt %o3, 1b
+ sub %o3, %o4, %o3
+2: sethi %hi(KERNBASE), %o3
+ flush %o3
+ retl
+ nop
+3: mov 0x80, %o4
+ stxa %g0, [%o4] ASI_DMMU_DEMAP
+ membar #Sync
+ stxa %g0, [%o4] ASI_IMMU_DEMAP
+ membar #Sync
+ retl
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+
#ifdef DCACHE_ALIASING_POSSIBLE
__cheetah_flush_dcache_page: /* 11 insns */
sethi %hi(PAGE_OFFSET), %g1
@@ -309,19 +380,28 @@
ret
restore
-__hypervisor_flush_tlb_mm: /* 10 insns */
+__hypervisor_flush_tlb_mm: /* 19 insns */
mov %o0, %o2 /* ARG2: mmu context */
mov 0, %o0 /* ARG0: CPU lists unimplemented */
mov 0, %o1 /* ARG1: CPU lists unimplemented */
mov HV_MMU_ALL, %o3 /* ARG3: flags */
mov HV_FAST_MMU_DEMAP_CTX, %o5
ta HV_FAST_TRAP
- brnz,pn %o0, __hypervisor_tlb_tl0_error
+ brnz,pn %o0, 1f
mov HV_FAST_MMU_DEMAP_CTX, %o1
retl
nop
+1: sethi %hi(__hypervisor_tlb_tl0_error), %o5
+ jmpl %o5 + %lo(__hypervisor_tlb_tl0_error), %g0
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
-__hypervisor_flush_tlb_page: /* 11 insns */
+__hypervisor_flush_tlb_page: /* 22 insns */
/* %o0 = context, %o1 = vaddr */
mov %o0, %g2
mov %o1, %o0 /* ARG0: vaddr + IMMU-bit */
@@ -330,12 +410,23 @@
srlx %o0, PAGE_SHIFT, %o0
sllx %o0, PAGE_SHIFT, %o0
ta HV_MMU_UNMAP_ADDR_TRAP
- brnz,pn %o0, __hypervisor_tlb_tl0_error
+ brnz,pn %o0, 1f
mov HV_MMU_UNMAP_ADDR_TRAP, %o1
retl
nop
+1: sethi %hi(__hypervisor_tlb_tl0_error), %o2
+ jmpl %o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
-__hypervisor_flush_tlb_pending: /* 16 insns */
+__hypervisor_flush_tlb_pending: /* 27 insns */
/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
sllx %o1, 3, %g1
mov %o2, %g2
@@ -347,31 +438,57 @@
srlx %o0, PAGE_SHIFT, %o0
sllx %o0, PAGE_SHIFT, %o0
ta HV_MMU_UNMAP_ADDR_TRAP
- brnz,pn %o0, __hypervisor_tlb_tl0_error
+ brnz,pn %o0, 1f
mov HV_MMU_UNMAP_ADDR_TRAP, %o1
brnz,pt %g1, 1b
nop
retl
nop
+1: sethi %hi(__hypervisor_tlb_tl0_error), %o2
+ jmpl %o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
-__hypervisor_flush_tlb_kernel_range: /* 16 insns */
+__hypervisor_flush_tlb_kernel_range: /* 31 insns */
/* %o0=start, %o1=end */
cmp %o0, %o1
be,pn %xcc, 2f
- sethi %hi(PAGE_SIZE), %g3
- mov %o0, %g1
- sub %o1, %g1, %g2
+ sub %o1, %o0, %g2
+ srlx %g2, 18, %g3
+ brnz,pn %g3, 4f
+ mov %o0, %g1
+ sethi %hi(PAGE_SIZE), %g3
sub %g2, %g3, %g2
1: add %g1, %g2, %o0 /* ARG0: virtual address */
mov 0, %o1 /* ARG1: mmu context */
mov HV_MMU_ALL, %o2 /* ARG2: flags */
ta HV_MMU_UNMAP_ADDR_TRAP
- brnz,pn %o0, __hypervisor_tlb_tl0_error
+ brnz,pn %o0, 3f
mov HV_MMU_UNMAP_ADDR_TRAP, %o1
brnz,pt %g2, 1b
sub %g2, %g3, %g2
2: retl
nop
+3: sethi %hi(__hypervisor_tlb_tl0_error), %o2
+ jmpl %o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+ nop
+4: mov 0, %o0 /* ARG0: CPU lists unimplemented */
+ mov 0, %o1 /* ARG1: CPU lists unimplemented */
+ mov 0, %o2 /* ARG2: mmu context == nucleus */
+ mov HV_MMU_ALL, %o3 /* ARG3: flags */
+ mov HV_FAST_MMU_DEMAP_CTX, %o5
+ ta HV_FAST_TRAP
+ brnz,pn %o0, 3b
+ mov HV_FAST_MMU_DEMAP_CTX, %o1
+ retl
+ nop
#ifdef DCACHE_ALIASING_POSSIBLE
/* XXX Niagara and friends have an 8K cache, so no aliasing is
@@ -394,43 +511,6 @@
retl
nop
- .globl cheetah_patch_cachetlbops
-cheetah_patch_cachetlbops:
- save %sp, -128, %sp
-
- sethi %hi(__flush_tlb_mm), %o0
- or %o0, %lo(__flush_tlb_mm), %o0
- sethi %hi(__cheetah_flush_tlb_mm), %o1
- or %o1, %lo(__cheetah_flush_tlb_mm), %o1
- call tlb_patch_one
- mov 19, %o2
-
- sethi %hi(__flush_tlb_page), %o0
- or %o0, %lo(__flush_tlb_page), %o0
- sethi %hi(__cheetah_flush_tlb_page), %o1
- or %o1, %lo(__cheetah_flush_tlb_page), %o1
- call tlb_patch_one
- mov 22, %o2
-
- sethi %hi(__flush_tlb_pending), %o0
- or %o0, %lo(__flush_tlb_pending), %o0
- sethi %hi(__cheetah_flush_tlb_pending), %o1
- or %o1, %lo(__cheetah_flush_tlb_pending), %o1
- call tlb_patch_one
- mov 27, %o2
-
-#ifdef DCACHE_ALIASING_POSSIBLE
- sethi %hi(__flush_dcache_page), %o0
- or %o0, %lo(__flush_dcache_page), %o0
- sethi %hi(__cheetah_flush_dcache_page), %o1
- or %o1, %lo(__cheetah_flush_dcache_page), %o1
- call tlb_patch_one
- mov 11, %o2
-#endif /* DCACHE_ALIASING_POSSIBLE */
-
- ret
- restore
-
#ifdef CONFIG_SMP
/* These are all called by the slaves of a cross call, at
* trap level 1, with interrupts fully disabled.
@@ -447,7 +527,7 @@
*/
.align 32
.globl xcall_flush_tlb_mm
-xcall_flush_tlb_mm: /* 21 insns */
+xcall_flush_tlb_mm: /* 24 insns */
mov PRIMARY_CONTEXT, %g2
ldxa [%g2] ASI_DMMU, %g3
srlx %g3, CTX_PGSZ1_NUC_SHIFT, %g4
@@ -469,9 +549,12 @@
nop
nop
nop
+ nop
+ nop
+ nop
.globl xcall_flush_tlb_page
-xcall_flush_tlb_page: /* 17 insns */
+xcall_flush_tlb_page: /* 20 insns */
/* %g5=context, %g1=vaddr */
mov PRIMARY_CONTEXT, %g4
ldxa [%g4] ASI_DMMU, %g2
@@ -490,15 +573,20 @@
retry
nop
nop
+ nop
+ nop
+ nop
.globl xcall_flush_tlb_kernel_range
-xcall_flush_tlb_kernel_range: /* 25 insns */
+xcall_flush_tlb_kernel_range: /* 44 insns */
sethi %hi(PAGE_SIZE - 1), %g2
or %g2, %lo(PAGE_SIZE - 1), %g2
andn %g1, %g2, %g1
andn %g7, %g2, %g7
sub %g7, %g1, %g3
- add %g2, 1, %g2
+ srlx %g3, 18, %g2
+ brnz,pn %g2, 2f
+ add %g2, 1, %g2
sub %g3, %g2, %g3
or %g1, 0x20, %g1 ! Nucleus
1: stxa %g0, [%g1 + %g3] ASI_DMMU_DEMAP
@@ -507,8 +595,25 @@
brnz,pt %g3, 1b
sub %g3, %g2, %g3
retry
- nop
- nop
+2: mov 63 * 8, %g1
+1: ldxa [%g1] ASI_ITLB_DATA_ACCESS, %g2
+ andcc %g2, 0x40, %g0 /* _PAGE_L_4U */
+ bne,pn %xcc, 2f
+ mov TLB_TAG_ACCESS, %g2
+ stxa %g0, [%g2] ASI_IMMU
+ stxa %g0, [%g1] ASI_ITLB_DATA_ACCESS
+ membar #Sync
+2: ldxa [%g1] ASI_DTLB_DATA_ACCESS, %g2
+ andcc %g2, 0x40, %g0
+ bne,pn %xcc, 2f
+ mov TLB_TAG_ACCESS, %g2
+ stxa %g0, [%g2] ASI_DMMU
+ stxa %g0, [%g1] ASI_DTLB_DATA_ACCESS
+ membar #Sync
+2: sub %g1, 8, %g1
+ brgez,pt %g1, 1b
+ nop
+ retry
nop
nop
nop
@@ -637,6 +742,52 @@
retry
+__cheetah_xcall_flush_tlb_kernel_range: /* 44 insns */
+ sethi %hi(PAGE_SIZE - 1), %g2
+ or %g2, %lo(PAGE_SIZE - 1), %g2
+ andn %g1, %g2, %g1
+ andn %g7, %g2, %g7
+ sub %g7, %g1, %g3
+ srlx %g3, 18, %g2
+ brnz,pn %g2, 2f
+ add %g2, 1, %g2
+ sub %g3, %g2, %g3
+ or %g1, 0x20, %g1 ! Nucleus
+1: stxa %g0, [%g1 + %g3] ASI_DMMU_DEMAP
+ stxa %g0, [%g1 + %g3] ASI_IMMU_DEMAP
+ membar #Sync
+ brnz,pt %g3, 1b
+ sub %g3, %g2, %g3
+ retry
+2: mov 0x80, %g2
+ stxa %g0, [%g2] ASI_DMMU_DEMAP
+ membar #Sync
+ stxa %g0, [%g2] ASI_IMMU_DEMAP
+ membar #Sync
+ retry
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+
#ifdef DCACHE_ALIASING_POSSIBLE
.align 32
.globl xcall_flush_dcache_page_cheetah
@@ -700,7 +851,7 @@
ba,a,pt %xcc, rtrap
.globl __hypervisor_xcall_flush_tlb_mm
-__hypervisor_xcall_flush_tlb_mm: /* 21 insns */
+__hypervisor_xcall_flush_tlb_mm: /* 24 insns */
/* %g5=ctx, g1,g2,g3,g4,g7=scratch, %g6=unusable */
mov %o0, %g2
mov %o1, %g3
@@ -714,7 +865,7 @@
mov HV_FAST_MMU_DEMAP_CTX, %o5
ta HV_FAST_TRAP
mov HV_FAST_MMU_DEMAP_CTX, %g6
- brnz,pn %o0, __hypervisor_tlb_xcall_error
+ brnz,pn %o0, 1f
mov %o0, %g5
mov %g2, %o0
mov %g3, %o1
@@ -723,9 +874,12 @@
mov %g7, %o5
membar #Sync
retry
+1: sethi %hi(__hypervisor_tlb_xcall_error), %g4
+ jmpl %g4 + %lo(__hypervisor_tlb_xcall_error), %g0
+ nop
.globl __hypervisor_xcall_flush_tlb_page
-__hypervisor_xcall_flush_tlb_page: /* 17 insns */
+__hypervisor_xcall_flush_tlb_page: /* 20 insns */
/* %g5=ctx, %g1=vaddr */
mov %o0, %g2
mov %o1, %g3
@@ -737,42 +891,64 @@
sllx %o0, PAGE_SHIFT, %o0
ta HV_MMU_UNMAP_ADDR_TRAP
mov HV_MMU_UNMAP_ADDR_TRAP, %g6
- brnz,a,pn %o0, __hypervisor_tlb_xcall_error
+ brnz,a,pn %o0, 1f
mov %o0, %g5
mov %g2, %o0
mov %g3, %o1
mov %g4, %o2
membar #Sync
retry
+1: sethi %hi(__hypervisor_tlb_xcall_error), %g4
+ jmpl %g4 + %lo(__hypervisor_tlb_xcall_error), %g0
+ nop
.globl __hypervisor_xcall_flush_tlb_kernel_range
-__hypervisor_xcall_flush_tlb_kernel_range: /* 25 insns */
+__hypervisor_xcall_flush_tlb_kernel_range: /* 44 insns */
/* %g1=start, %g7=end, g2,g3,g4,g5,g6=scratch */
sethi %hi(PAGE_SIZE - 1), %g2
or %g2, %lo(PAGE_SIZE - 1), %g2
andn %g1, %g2, %g1
andn %g7, %g2, %g7
sub %g7, %g1, %g3
+ srlx %g3, 18, %g7
add %g2, 1, %g2
sub %g3, %g2, %g3
mov %o0, %g2
mov %o1, %g4
- mov %o2, %g7
+ brnz,pn %g7, 2f
+ mov %o2, %g7
1: add %g1, %g3, %o0 /* ARG0: virtual address */
mov 0, %o1 /* ARG1: mmu context */
mov HV_MMU_ALL, %o2 /* ARG2: flags */
ta HV_MMU_UNMAP_ADDR_TRAP
mov HV_MMU_UNMAP_ADDR_TRAP, %g6
- brnz,pn %o0, __hypervisor_tlb_xcall_error
+ brnz,pn %o0, 1f
mov %o0, %g5
sethi %hi(PAGE_SIZE), %o2
brnz,pt %g3, 1b
sub %g3, %o2, %g3
- mov %g2, %o0
+5: mov %g2, %o0
mov %g4, %o1
mov %g7, %o2
membar #Sync
retry
+1: sethi %hi(__hypervisor_tlb_xcall_error), %g4
+ jmpl %g4 + %lo(__hypervisor_tlb_xcall_error), %g0
+ nop
+2: mov %o3, %g1
+ mov %o5, %g3
+ mov 0, %o0 /* ARG0: CPU lists unimplemented */
+ mov 0, %o1 /* ARG1: CPU lists unimplemented */
+ mov 0, %o2 /* ARG2: mmu context == nucleus */
+ mov HV_MMU_ALL, %o3 /* ARG3: flags */
+ mov HV_FAST_MMU_DEMAP_CTX, %o5
+ ta HV_FAST_TRAP
+ mov %g1, %o3
+ brz,pt %o0, 5b
+ mov %g3, %o5
+ mov HV_FAST_MMU_DEMAP_CTX, %g6
+ ba,pt %xcc, 1b
+ clr %g5
/* These just get rescheduled to PIL vectors. */
.globl xcall_call_function
@@ -809,6 +985,58 @@
#endif /* CONFIG_SMP */
+ .globl cheetah_patch_cachetlbops
+cheetah_patch_cachetlbops:
+ save %sp, -128, %sp
+
+ sethi %hi(__flush_tlb_mm), %o0
+ or %o0, %lo(__flush_tlb_mm), %o0
+ sethi %hi(__cheetah_flush_tlb_mm), %o1
+ or %o1, %lo(__cheetah_flush_tlb_mm), %o1
+ call tlb_patch_one
+ mov 19, %o2
+
+ sethi %hi(__flush_tlb_page), %o0
+ or %o0, %lo(__flush_tlb_page), %o0
+ sethi %hi(__cheetah_flush_tlb_page), %o1
+ or %o1, %lo(__cheetah_flush_tlb_page), %o1
+ call tlb_patch_one
+ mov 22, %o2
+
+ sethi %hi(__flush_tlb_pending), %o0
+ or %o0, %lo(__flush_tlb_pending), %o0
+ sethi %hi(__cheetah_flush_tlb_pending), %o1
+ or %o1, %lo(__cheetah_flush_tlb_pending), %o1
+ call tlb_patch_one
+ mov 27, %o2
+
+ sethi %hi(__flush_tlb_kernel_range), %o0
+ or %o0, %lo(__flush_tlb_kernel_range), %o0
+ sethi %hi(__cheetah_flush_tlb_kernel_range), %o1
+ or %o1, %lo(__cheetah_flush_tlb_kernel_range), %o1
+ call tlb_patch_one
+ mov 31, %o2
+
+#ifdef DCACHE_ALIASING_POSSIBLE
+ sethi %hi(__flush_dcache_page), %o0
+ or %o0, %lo(__flush_dcache_page), %o0
+ sethi %hi(__cheetah_flush_dcache_page), %o1
+ or %o1, %lo(__cheetah_flush_dcache_page), %o1
+ call tlb_patch_one
+ mov 11, %o2
+#endif /* DCACHE_ALIASING_POSSIBLE */
+
+#ifdef CONFIG_SMP
+ sethi %hi(xcall_flush_tlb_kernel_range), %o0
+ or %o0, %lo(xcall_flush_tlb_kernel_range), %o0
+ sethi %hi(__cheetah_xcall_flush_tlb_kernel_range), %o1
+ or %o1, %lo(__cheetah_xcall_flush_tlb_kernel_range), %o1
+ call tlb_patch_one
+ mov 44, %o2
+#endif /* CONFIG_SMP */
+
+ ret
+ restore
.globl hypervisor_patch_cachetlbops
hypervisor_patch_cachetlbops:
@@ -819,28 +1047,28 @@
sethi %hi(__hypervisor_flush_tlb_mm), %o1
or %o1, %lo(__hypervisor_flush_tlb_mm), %o1
call tlb_patch_one
- mov 10, %o2
+ mov 19, %o2
sethi %hi(__flush_tlb_page), %o0
or %o0, %lo(__flush_tlb_page), %o0
sethi %hi(__hypervisor_flush_tlb_page), %o1
or %o1, %lo(__hypervisor_flush_tlb_page), %o1
call tlb_patch_one
- mov 11, %o2
+ mov 22, %o2
sethi %hi(__flush_tlb_pending), %o0
or %o0, %lo(__flush_tlb_pending), %o0
sethi %hi(__hypervisor_flush_tlb_pending), %o1
or %o1, %lo(__hypervisor_flush_tlb_pending), %o1
call tlb_patch_one
- mov 16, %o2
+ mov 27, %o2
sethi %hi(__flush_tlb_kernel_range), %o0
or %o0, %lo(__flush_tlb_kernel_range), %o0
sethi %hi(__hypervisor_flush_tlb_kernel_range), %o1
or %o1, %lo(__hypervisor_flush_tlb_kernel_range), %o1
call tlb_patch_one
- mov 16, %o2
+ mov 31, %o2
#ifdef DCACHE_ALIASING_POSSIBLE
sethi %hi(__flush_dcache_page), %o0
@@ -857,21 +1085,21 @@
sethi %hi(__hypervisor_xcall_flush_tlb_mm), %o1
or %o1, %lo(__hypervisor_xcall_flush_tlb_mm), %o1
call tlb_patch_one
- mov 21, %o2
+ mov 24, %o2
sethi %hi(xcall_flush_tlb_page), %o0
or %o0, %lo(xcall_flush_tlb_page), %o0
sethi %hi(__hypervisor_xcall_flush_tlb_page), %o1
or %o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1
call tlb_patch_one
- mov 17, %o2
+ mov 20, %o2
sethi %hi(xcall_flush_tlb_kernel_range), %o0
or %o0, %lo(xcall_flush_tlb_kernel_range), %o0
sethi %hi(__hypervisor_xcall_flush_tlb_kernel_range), %o1
or %o1, %lo(__hypervisor_xcall_flush_tlb_kernel_range), %o1
call tlb_patch_one
- mov 25, %o2
+ mov 44, %o2
#endif /* CONFIG_SMP */
ret
diff --git a/arch/tile/include/asm/cache.h b/arch/tile/include/asm/cache.h
index 6160761..4810e48 100644
--- a/arch/tile/include/asm/cache.h
+++ b/arch/tile/include/asm/cache.h
@@ -61,4 +61,7 @@
*/
#define __write_once __read_mostly
+/* __ro_after_init is the generic name for the tile arch __write_once. */
+#define __ro_after_init __read_mostly
+
#endif /* _ASM_TILE_CACHE_H */
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 0ab5ee1..aa8b067 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -888,7 +888,7 @@ static int helper_rfc4106_encrypt(struct aead_request *req)
unsigned long auth_tag_len = crypto_aead_authsize(tfm);
u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
struct scatter_walk src_sg_walk;
- struct scatter_walk dst_sg_walk;
+ struct scatter_walk dst_sg_walk = {};
unsigned int i;
/* Assuming we are supporting rfc4106 64-bit extended */
@@ -968,7 +968,7 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
u8 authTag[16];
struct scatter_walk src_sg_walk;
- struct scatter_walk dst_sg_walk;
+ struct scatter_walk dst_sg_walk = {};
unsigned int i;
if (unlikely(req->assoclen != 16 && req->assoclen != 20))
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index 77f28ce..9976fce 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -5,8 +5,8 @@
OBJECT_FILES_NON_STANDARD_entry_$(BITS).o := y
OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y
-CFLAGS_syscall_64.o += -Wno-override-init
-CFLAGS_syscall_32.o += -Wno-override-init
+CFLAGS_syscall_64.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_syscall_32.o += $(call cc-option,-Wno-override-init,)
obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
obj-y += common.o
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index b75a8bc..21b352a 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -44,6 +44,7 @@
#include <asm/alternative-asm.h>
#include <asm/asm.h>
#include <asm/smap.h>
+#include <asm/export.h>
.section .entry.text, "ax"
@@ -991,6 +992,7 @@
jmp ftrace_stub
END(mcount)
#endif /* CONFIG_DYNAMIC_FTRACE */
+EXPORT_SYMBOL(mcount)
#endif /* CONFIG_FUNCTION_TRACER */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index c98ec2ef..ef766a3 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -35,6 +35,7 @@
#include <asm/asm.h>
#include <asm/smap.h>
#include <asm/pgtable_types.h>
+#include <asm/export.h>
#include <linux/err.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
@@ -875,6 +876,7 @@
popfq
ret
END(native_load_gs_index)
+EXPORT_SYMBOL(native_load_gs_index)
_ASM_EXTABLE(.Lgs_change, bad_gs)
.section .fixup, "ax"
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index ff6ef7b..2b36185 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -389,5 +389,3 @@
380 i386 pkey_mprotect sys_pkey_mprotect
381 i386 pkey_alloc sys_pkey_alloc
382 i386 pkey_free sys_pkey_free
-#383 i386 pkey_get sys_pkey_get
-#384 i386 pkey_set sys_pkey_set
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 2f024d0..e93ef0b 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -338,8 +338,6 @@
329 common pkey_mprotect sys_pkey_mprotect
330 common pkey_alloc sys_pkey_alloc
331 common pkey_free sys_pkey_free
-#332 common pkey_get sys_pkey_get
-#333 common pkey_set sys_pkey_set
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S
index e5a1711..fee6bc7 100644
--- a/arch/x86/entry/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -6,6 +6,7 @@
*/
#include <linux/linkage.h>
#include <asm/asm.h>
+ #include <asm/export.h>
/* put return address in eax (arg1) */
.macro THUNK name, func, put_ret_addr_in_eax=0
@@ -36,5 +37,7 @@
#ifdef CONFIG_PREEMPT
THUNK ___preempt_schedule, preempt_schedule
THUNK ___preempt_schedule_notrace, preempt_schedule_notrace
+ EXPORT_SYMBOL(___preempt_schedule)
+ EXPORT_SYMBOL(___preempt_schedule_notrace)
#endif
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index 627ecbc..be36bf4 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -8,6 +8,7 @@
#include <linux/linkage.h>
#include "calling.h"
#include <asm/asm.h>
+#include <asm/export.h>
/* rdi: arg1 ... normal C conventions. rax is saved/restored. */
.macro THUNK name, func, put_ret_addr_in_rdi=0
@@ -49,6 +50,8 @@
#ifdef CONFIG_PREEMPT
THUNK ___preempt_schedule, preempt_schedule
THUNK ___preempt_schedule_notrace, preempt_schedule_notrace
+ EXPORT_SYMBOL(___preempt_schedule)
+ EXPORT_SYMBOL(___preempt_schedule_notrace)
#endif
#if defined(CONFIG_TRACE_IRQFLAGS) \
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a3a9eb8..a74a2db 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3607,10 +3607,14 @@ __init int intel_pmu_init(void)
/*
* Quirk: v2 perfmon does not report fixed-purpose events, so
- * assume at least 3 events:
+ * assume at least 3 events, when not running in a hypervisor:
*/
- if (version > 1)
- x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3);
+ if (version > 1) {
+ int assume = 3 * !boot_cpu_has(X86_FEATURE_HYPERVISOR);
+
+ x86_pmu.num_counters_fixed =
+ max((int)edx.split.num_counters_fixed, assume);
+ }
if (boot_cpu_has(X86_FEATURE_PDCM)) {
u64 capabilities;
@@ -3898,6 +3902,7 @@ __init int intel_pmu_init(void)
break;
case INTEL_FAM6_XEON_PHI_KNL:
+ case INTEL_FAM6_XEON_PHI_KNM:
memcpy(hw_cache_event_ids,
slm_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs,
@@ -3912,7 +3917,7 @@ __init int intel_pmu_init(void)
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
- pr_cont("Knights Landing events, ");
+ pr_cont("Knights Landing/Mill events, ");
break;
case INTEL_FAM6_SKYLAKE_MOBILE:
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 3ca87b5..4f5ac72 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -48,7 +48,8 @@
* Scope: Core
* MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
* perf code: 0x02
- * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
+ * SKL,KNL
* Scope: Core
* MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
* perf code: 0x03
@@ -56,15 +57,16 @@
* Scope: Core
* MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter.
* perf code: 0x00
- * Available model: SNB,IVB,HSW,BDW,SKL
+ * Available model: SNB,IVB,HSW,BDW,SKL,KNL
* Scope: Package (physical package)
* MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter.
* perf code: 0x01
- * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL
* Scope: Package (physical package)
* MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter.
* perf code: 0x02
- * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
+ * SKL,KNL
* Scope: Package (physical package)
* MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter.
* perf code: 0x03
@@ -118,6 +120,7 @@ struct cstate_model {
/* Quirk flags */
#define SLM_PKG_C6_USE_C7_MSR (1UL << 0)
+#define KNL_CORE_C6_MSR (1UL << 1)
struct perf_cstate_msr {
u64 msr;
@@ -488,6 +491,18 @@ static const struct cstate_model slm_cstates __initconst = {
.quirks = SLM_PKG_C6_USE_C7_MSR,
};
+
+static const struct cstate_model knl_cstates __initconst = {
+ .core_events = BIT(PERF_CSTATE_CORE_C6_RES),
+
+ .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) |
+ BIT(PERF_CSTATE_PKG_C3_RES) |
+ BIT(PERF_CSTATE_PKG_C6_RES),
+ .quirks = KNL_CORE_C6_MSR,
+};
+
+
+
#define X86_CSTATES_MODEL(model, states) \
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) }
@@ -523,6 +538,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
+
+ X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
@@ -558,6 +575,11 @@ static int __init cstate_probe(const struct cstate_model *cm)
if (cm->quirks & SLM_PKG_C6_USE_C7_MSR)
pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY;
+ /* KNL has different MSR for CORE C6 */
+ if (cm->quirks & KNL_CORE_C6_MSR)
+ pkg_msr[PERF_CSTATE_CORE_C6_RES].msr = MSR_KNL_CORE_C6_RESIDENCY;
+
+
has_cstate_core = cstate_probe_msr(cm->core_events,
PERF_CSTATE_CORE_EVENT_MAX,
core_msr, core_events_attrs);
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index fc6cf21..81b321a 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -458,8 +458,8 @@ void intel_pmu_lbr_del(struct perf_event *event)
if (!x86_pmu.lbr_nr)
return;
- if (branch_user_callstack(cpuc->br_sel) && event->ctx &&
- event->ctx->task_ctx_data) {
+ if (branch_user_callstack(cpuc->br_sel) &&
+ event->ctx->task_ctx_data) {
task_ctx = event->ctx->task_ctx_data;
task_ctx->lbr_callstack_users--;
}
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index b0f0e83..0a535ce 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -763,6 +763,7 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_rapl_init),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init),
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index d9844cc..efca268 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1349,6 +1349,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, bdx_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, bdx_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init),
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 5f845ee..81195cc 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -8,8 +8,12 @@
#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00
#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04
#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604
-#define PCI_DEVICE_ID_INTEL_SKL_IMC 0x191f
-#define PCI_DEVICE_ID_INTEL_SKL_U_IMC 0x190c
+#define PCI_DEVICE_ID_INTEL_SKL_U_IMC 0x1904
+#define PCI_DEVICE_ID_INTEL_SKL_Y_IMC 0x190c
+#define PCI_DEVICE_ID_INTEL_SKL_HD_IMC 0x1900
+#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910
+#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f
+#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
@@ -616,13 +620,29 @@ static const struct pci_device_id bdw_uncore_pci_ids[] = {
static const struct pci_device_id skl_uncore_pci_ids[] = {
{ /* IMC */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_IMC),
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_Y_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
{ /* IMC */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_U_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HD_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SD_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
{ /* end: all zeroes */ },
};
@@ -666,8 +686,12 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */
IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */
IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */
- IMC_DEV(SKL_IMC, &skl_uncore_pci_driver), /* 6th Gen Core */
+ IMC_DEV(SKL_Y_IMC, &skl_uncore_pci_driver), /* 6th Gen Core Y */
IMC_DEV(SKL_U_IMC, &skl_uncore_pci_driver), /* 6th Gen Core U */
+ IMC_DEV(SKL_HD_IMC, &skl_uncore_pci_driver), /* 6th Gen Core H Dual Core */
+ IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core H Quad Core */
+ IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Dual Core */
+ IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Quad Core */
{ /* end marker */ }
};
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 1188bc8..a396292 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -194,6 +194,8 @@
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
+#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/arch/x86/include/asm/export.h b/arch/x86/include/asm/export.h
new file mode 100644
index 0000000..138de56
--- /dev/null
+++ b/arch/x86/include/asm/export.h
@@ -0,0 +1,4 @@
+#ifdef CONFIG_64BIT
+#define KSYM_ALIGN 16
+#endif
+#include <asm-generic/export.h>
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 9ae5ab8..34a46dc 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -64,5 +64,6 @@
/* Xeon Phi */
#define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */
+#define INTEL_FAM6_XEON_PHI_KNM 0x85 /* Knights Mill */
#endif /* _ASM_X86_INTEL_FAMILY_H */
diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index 5b6753d..49da9f4 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -17,6 +17,7 @@
extern int intel_mid_pci_init(void);
extern int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state);
+extern pci_power_t intel_mid_pci_get_power_state(struct pci_dev *pdev);
extern void intel_mid_pwr_power_off(void);
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index de25aad..d34bd37 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -351,4 +351,10 @@ extern void arch_phys_wc_del(int handle);
#define arch_phys_wc_add arch_phys_wc_add
#endif
+#ifdef CONFIG_X86_PAT
+extern int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size);
+extern void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size);
+#define arch_io_reserve_memtype_wc arch_io_reserve_memtype_wc
+#endif
+
#endif /* _ASM_X86_IO_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4b20f73..bdde807 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -948,7 +948,6 @@ struct kvm_x86_ops {
int (*get_lpage_level)(void);
bool (*rdtscp_supported)(void);
bool (*invpcid_supported)(void);
- void (*adjust_tsc_offset_guest)(struct kvm_vcpu *vcpu, s64 adjustment);
void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
@@ -958,8 +957,6 @@ struct kvm_x86_ops {
void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
- u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu, u64 host_tsc);
-
void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
int (*check_intercept)(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 56f4c66..78f3760 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -88,7 +88,6 @@
#define MSR_IA32_RTIT_CTL 0x00000570
#define MSR_IA32_RTIT_STATUS 0x00000571
-#define MSR_IA32_RTIT_STATUS 0x00000571
#define MSR_IA32_RTIT_ADDR0_A 0x00000580
#define MSR_IA32_RTIT_ADDR0_B 0x00000581
#define MSR_IA32_RTIT_ADDR1_A 0x00000582
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e02e3f8..84f58de 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -521,7 +521,8 @@ do { \
static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr,
const unsigned long __percpu *addr)
{
- unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG;
+ unsigned long __percpu *a =
+ (unsigned long __percpu *)addr + nr / BITS_PER_LONG;
#ifdef CONFIG_X86_64
return ((1UL << (nr % BITS_PER_LONG)) & raw_cpu_read_8(*a)) != 0;
@@ -538,7 +539,7 @@ static inline bool x86_this_cpu_variable_test_bit(int nr,
asm volatile("bt "__percpu_arg(2)",%1\n\t"
CC_SET(c)
: CC_OUT(c) (oldbit)
- : "m" (*(unsigned long *)addr), "Ir" (nr));
+ : "m" (*(unsigned long __percpu *)addr), "Ir" (nr));
return oldbit;
}
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index 3d33a71..a34e0d4 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -103,8 +103,10 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem)
({ \
long tmp; \
struct rw_semaphore* ret; \
+ register void *__sp asm(_ASM_SP); \
+ \
asm volatile("# beginning down_write\n\t" \
- LOCK_PREFIX " xadd %1,(%3)\n\t" \
+ LOCK_PREFIX " xadd %1,(%4)\n\t" \
/* adds 0xffff0001, returns the old value */ \
" test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \
/* was the active mask 0 before? */\
@@ -112,7 +114,7 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem)
" call " slow_path "\n" \
"1:\n" \
"# ending down_write" \
- : "+m" (sem->count), "=d" (tmp), "=a" (ret) \
+ : "+m" (sem->count), "=d" (tmp), "=a" (ret), "+r" (__sp) \
: "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \
: "memory", "cc"); \
ret; \
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 2aaca53..ad6f5eb0 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -52,6 +52,15 @@ struct task_struct;
#include <asm/cpufeature.h>
#include <linux/atomic.h>
+struct thread_info {
+ unsigned long flags; /* low level flags */
+};
+
+#define INIT_THREAD_INFO(tsk) \
+{ \
+ .flags = 0, \
+}
+
#define init_stack (init_thread_union.stack)
#else /* !__ASSEMBLY__ */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 4dd5d50..79076d7 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -46,9 +46,7 @@
obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o
obj-$(CONFIG_IRQ_WORK) += irq_work.o
obj-y += probe_roms.o
-obj-$(CONFIG_X86_32) += i386_ksyms_32.o
-obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
-obj-$(CONFIG_X86_64) += mcount_64.o
+obj-$(CONFIG_X86_64) += sys_x86_64.o mcount_64.o
obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o
obj-$(CONFIG_SYSFS) += ksysfs.o
obj-y += bootflag.o e820.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 8a5abaa..931ced8 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -454,6 +454,7 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger,
polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK;
mp_override_legacy_irq(bus_irq, polarity, trigger, gsi);
+ acpi_penalize_sci_irq(bus_irq, trigger, polarity);
/*
* stash over-ride to indicate we've been here
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index c7364bd..51287cd 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1042,8 +1042,11 @@ static int apm_get_power_status(u_short *status, u_short *bat, u_short *life)
if (apm_info.get_power_status_broken)
return APM_32_UNSUPPORTED;
- if (apm_bios_call(&call))
+ if (apm_bios_call(&call)) {
+ if (!call.err)
+ return APM_NO_ERROR;
return call.err;
+ }
*status = call.ebx;
*bat = call.ecx;
if (apm_info.get_power_status_swabinminutes) {
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index b81fe2d..1e81a37 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -347,7 +347,6 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
#ifdef CONFIG_SMP
unsigned bits;
int cpu = smp_processor_id();
- unsigned int socket_id, core_complex_id;
bits = c->x86_coreid_bits;
/* Low order bits define the core id (index of core in socket) */
@@ -365,10 +364,7 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
if (c->x86 != 0x17 || !cpuid_edx(0x80000006))
return;
- socket_id = (c->apicid >> bits) - 1;
- core_complex_id = (c->apicid & ((1 << bits) - 1)) >> 3;
-
- per_cpu(cpu_llc_id, cpu) = (socket_id << 3) | core_complex_id;
+ per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
#endif
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9bd910a..cc9e980 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -979,6 +979,35 @@ static void x86_init_cache_qos(struct cpuinfo_x86 *c)
}
/*
+ * The physical to logical package id mapping is initialized from the
+ * acpi/mptables information. Make sure that CPUID actually agrees with
+ * that.
+ */
+static void sanitize_package_id(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+ unsigned int pkg, apicid, cpu = smp_processor_id();
+
+ apicid = apic->cpu_present_to_apicid(cpu);
+ pkg = apicid >> boot_cpu_data.x86_coreid_bits;
+
+ if (apicid != c->initial_apicid) {
+ pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x CPUID: %x\n",
+ cpu, apicid, c->initial_apicid);
+ c->initial_apicid = apicid;
+ }
+ if (pkg != c->phys_proc_id) {
+ pr_err(FW_BUG "CPU%u: Using firmware package id %u instead of %u\n",
+ cpu, pkg, c->phys_proc_id);
+ c->phys_proc_id = pkg;
+ }
+ c->logical_proc_id = topology_phys_to_logical_pkg(pkg);
+#else
+ c->logical_proc_id = 0;
+#endif
+}
+
+/*
* This does the hard work of actually picking apart the CPU stuff...
*/
static void identify_cpu(struct cpuinfo_x86 *c)
@@ -1103,8 +1132,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
#ifdef CONFIG_NUMA
numa_add_cpu(smp_processor_id());
#endif
- /* The boot/hotplug time assigment got cleared, restore it */
- c->logical_proc_id = topology_phys_to_logical_pkg(c->phys_proc_id);
+ sanitize_package_id(c);
}
/*
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 620ab06..017bda1 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -429,7 +429,7 @@ int __init save_microcode_in_initrd_amd(void)
* We need the physical address of the container for both bitness since
* boot_params.hdr.ramdisk_image is a physical address.
*/
- cont = __pa(container);
+ cont = __pa_nodebug(container);
cont_va = container;
#endif
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 8cb57df..1db8dc4 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -32,6 +32,8 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_INTEL_PT, CR_EBX,25, 0x00000007, 0 },
+ { X86_FEATURE_AVX512_4VNNIW, CR_EDX, 2, 0x00000007, 0 },
+ { X86_FEATURE_AVX512_4FMAPS, CR_EDX, 3, 0x00000007, 0 },
{ X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 },
{ X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 },
{ X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 },
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 8116057..5130985 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -27,6 +27,7 @@
#include <asm/div64.h>
#include <asm/x86_init.h>
#include <asm/hypervisor.h>
+#include <asm/timer.h>
#include <asm/apic.h>
#define CPUID_VMWARE_INFO_LEAF 0x40000000
@@ -94,6 +95,10 @@ static void __init vmware_platform_setup(void)
} else {
pr_warn("Failed to get TSC freq from the hypervisor\n");
}
+
+#ifdef CONFIG_X86_IO_APIC
+ no_timer_check = 1;
+#endif
}
/*
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index b85fe5f..90e8dde 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -350,7 +350,7 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
* continue building up new bios map based on this
* information
*/
- if (current_type != last_type) {
+ if (current_type != last_type || current_type == E820_PRAM) {
if (last_type != 0) {
new_bios[new_bios_entry].size =
change_point[chgidx]->addr - last_addr;
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 124aa5c..095ef7d 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -74,6 +74,8 @@ void fpu__xstate_clear_all_cpu_caps(void)
setup_clear_cpu_cap(X86_FEATURE_MPX);
setup_clear_cpu_cap(X86_FEATURE_XGETBV1);
setup_clear_cpu_cap(X86_FEATURE_PKU);
+ setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW);
+ setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS);
}
/*
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 5f40126..b6b2f02 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -23,6 +23,7 @@
#include <asm/percpu.h>
#include <asm/nops.h>
#include <asm/bootparam.h>
+#include <asm/export.h>
/* Physical address */
#define pa(X) ((X) - __PAGE_OFFSET)
@@ -673,6 +674,7 @@
.fill 4096,1,0
ENTRY(swapper_pg_dir)
.fill 1024,4,0
+EXPORT_SYMBOL(empty_zero_page)
/*
* This starts the data section.
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index c98a559..b4421cc 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -21,6 +21,7 @@
#include <asm/percpu.h>
#include <asm/nops.h>
#include "../entry/calling.h"
+#include <asm/export.h>
#ifdef CONFIG_PARAVIRT
#include <asm/asm-offsets.h>
@@ -486,10 +487,12 @@
ENTRY(phys_base)
/* This must match the first entry in level2_kernel_pgt */
.quad 0x0000000000000000
+EXPORT_SYMBOL(phys_base)
#include "../../x86/xen/xen-head.S"
__PAGE_ALIGNED_BSS
NEXT_PAGE(empty_zero_page)
.skip PAGE_SIZE
+EXPORT_SYMBOL(empty_zero_page)
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
deleted file mode 100644
index 1f9b878..0000000
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ /dev/null
@@ -1,47 +0,0 @@
-#include <linux/export.h>
-#include <linux/spinlock_types.h>
-
-#include <asm/checksum.h>
-#include <asm/pgtable.h>
-#include <asm/desc.h>
-#include <asm/ftrace.h>
-
-#ifdef CONFIG_FUNCTION_TRACER
-/* mcount is defined in assembly */
-EXPORT_SYMBOL(mcount);
-#endif
-
-/*
- * Note, this is a prototype to get at the symbol for
- * the export, but dont use it from C code, it is used
- * by assembly code and is not using C calling convention!
- */
-#ifndef CONFIG_X86_CMPXCHG64
-extern void cmpxchg8b_emu(void);
-EXPORT_SYMBOL(cmpxchg8b_emu);
-#endif
-
-/* Networking helper routines. */
-EXPORT_SYMBOL(csum_partial_copy_generic);
-
-EXPORT_SYMBOL(__get_user_1);
-EXPORT_SYMBOL(__get_user_2);
-EXPORT_SYMBOL(__get_user_4);
-EXPORT_SYMBOL(__get_user_8);
-
-EXPORT_SYMBOL(__put_user_1);
-EXPORT_SYMBOL(__put_user_2);
-EXPORT_SYMBOL(__put_user_4);
-EXPORT_SYMBOL(__put_user_8);
-
-EXPORT_SYMBOL(strstr);
-
-EXPORT_SYMBOL(csum_partial);
-EXPORT_SYMBOL(empty_zero_page);
-
-#ifdef CONFIG_PREEMPT
-EXPORT_SYMBOL(___preempt_schedule);
-EXPORT_SYMBOL(___preempt_schedule_notrace);
-#endif
-
-EXPORT_SYMBOL(__sw_hweight32);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 28cee01..d9d8d16 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -50,6 +50,7 @@
#include <linux/kallsyms.h>
#include <linux/ftrace.h>
#include <linux/frame.h>
+#include <linux/kasan.h>
#include <asm/text-patching.h>
#include <asm/cacheflush.h>
@@ -1057,9 +1058,10 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
* tailcall optimization. So, to be absolutely safe
* we also save and restore enough stack bytes to cover
* the argument area.
+ * Use __memcpy() to avoid KASAN stack out-of-bounds reports as we copy
+ * raw stack chunk with redzones:
*/
- memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr,
- MIN_STACK_SIZE(addr));
+ __memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr));
regs->flags &= ~X86_EFLAGS_IF;
trace_hardirqs_off();
regs->ip = (unsigned long)(jp->entry);
@@ -1080,6 +1082,9 @@ void jprobe_return(void)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+ /* Unpoison stack redzones in the frames we are going to jump over. */
+ kasan_unpoison_stack_above_sp_to(kcb->jprobe_saved_sp);
+
asm volatile (
#ifdef CONFIG_X86_64
" xchg %%rbx,%%rsp \n"
@@ -1118,7 +1123,7 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
/* It's OK to start function graph tracing again */
unpause_graph_tracing();
*regs = kcb->jprobe_saved_regs;
- memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
+ __memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
preempt_enable_no_resched();
return 1;
}
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index 6192422..7b0d3da 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/mcount_64.S
@@ -7,6 +7,7 @@
#include <linux/linkage.h>
#include <asm/ptrace.h>
#include <asm/ftrace.h>
+#include <asm/export.h>
.code64
@@ -17,8 +18,10 @@
#ifdef CC_USING_FENTRY
# define function_hook __fentry__
+EXPORT_SYMBOL(__fentry__)
#else
# define function_hook mcount
+EXPORT_SYMBOL(mcount)
#endif
/* All cases save the original rbp (8 bytes) */
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 51402a7..0bee04d 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -625,8 +625,6 @@ static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev)
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3,
amd_disable_seq_and_redirect_scrub);
-#endif
-
#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE)
#include <linux/jump_label.h>
#include <asm/string_64.h>
@@ -657,3 +655,4 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, quirk_intel_brickland_xeon_ras_cap);
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2083, quirk_intel_purley_xeon_ras_cap);
#endif
+#endif
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index bbfbca5..9c337b0 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1221,11 +1221,16 @@ void __init setup_arch(char **cmdline_p)
*/
get_smp_config();
+ /*
+ * Systems w/o ACPI and mptables might not have it mapped the local
+ * APIC yet, but prefill_possible_map() might need to access it.
+ */
+ init_apic_mappings();
+
prefill_possible_map();
init_cpu_to_node();
- init_apic_mappings();
io_apic_init_mappings();
kvm_guest_init();
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index 40df337..ec1f756 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -105,9 +105,6 @@ void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact)
/* Don't let flags to be set from userspace */
act->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI);
- if (user_64bit_mode(current_pt_regs()))
- return;
-
if (in_ia32_syscall())
act->sa.sa_flags |= SA_IA32_ABI;
if (in_x32_syscall())
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 68f8cc2..c00cb64 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -261,8 +261,10 @@ static inline void __smp_reschedule_interrupt(void)
__visible void smp_reschedule_interrupt(struct pt_regs *regs)
{
+ irq_enter();
ack_APIC_irq();
__smp_reschedule_interrupt();
+ irq_exit();
/*
* KVM uses this interrupt to force a cpu out of guest mode
*/
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 951f093..42f5eb7 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1409,15 +1409,17 @@ __init void prefill_possible_map(void)
/* No boot processor was found in mptable or ACPI MADT */
if (!num_processors) {
- int apicid = boot_cpu_physical_apicid;
- int cpu = hard_smp_processor_id();
+ if (boot_cpu_has(X86_FEATURE_APIC)) {
+ int apicid = boot_cpu_physical_apicid;
+ int cpu = hard_smp_processor_id();
- pr_warn("Boot CPU (id %d) not listed by BIOS\n", cpu);
+ pr_warn("Boot CPU (id %d) not listed by BIOS\n", cpu);
- /* Make sure boot cpu is enumerated */
- if (apic->cpu_present_to_apicid(0) == BAD_APICID &&
- apic->apic_id_valid(apicid))
- generic_processor_info(apicid, boot_cpu_apic_version);
+ /* Make sure boot cpu is enumerated */
+ if (apic->cpu_present_to_apicid(0) == BAD_APICID &&
+ apic->apic_id_valid(apicid))
+ generic_processor_info(apicid, boot_cpu_apic_version);
+ }
if (!num_processors)
num_processors = 1;
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index c9a0738..a23ce84 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -57,7 +57,8 @@ static int is_setting_trap_flag(struct task_struct *child, struct pt_regs *regs)
unsigned char opcode[15];
unsigned long addr = convert_ip_to_linear(child, regs);
- copied = access_process_vm(child, addr, opcode, sizeof(opcode), 0);
+ copied = access_process_vm(child, addr, opcode, sizeof(opcode),
+ FOLL_FORCE);
for (i = 0; i < copied; i++) {
switch (opcode[i]) {
/* popf and iret */
diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c
index 9298993..2d721e5 100644
--- a/arch/x86/kernel/unwind_guess.c
+++ b/arch/x86/kernel/unwind_guess.c
@@ -47,7 +47,14 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
get_stack_info(first_frame, state->task, &state->stack_info,
&state->stack_mask);
- if (!__kernel_text_address(*first_frame))
+ /*
+ * The caller can provide the address of the first frame directly
+ * (first_frame) or indirectly (regs->sp) to indicate which stack frame
+ * to start unwinding at. Skip ahead until we reach it.
+ */
+ if (!unwind_done(state) &&
+ (!on_stack(&state->stack_info, first_frame, sizeof(long)) ||
+ !__kernel_text_address(*first_frame)))
unwind_next_frame(state);
}
EXPORT_SYMBOL_GPL(__unwind_start);
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
deleted file mode 100644
index b2cee3d1..0000000
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ /dev/null
@@ -1,85 +0,0 @@
-/* Exports for assembly files.
- All C exports should go in the respective C files. */
-
-#include <linux/export.h>
-#include <linux/spinlock_types.h>
-#include <linux/smp.h>
-
-#include <net/checksum.h>
-
-#include <asm/processor.h>
-#include <asm/pgtable.h>
-#include <asm/uaccess.h>
-#include <asm/desc.h>
-#include <asm/ftrace.h>
-
-#ifdef CONFIG_FUNCTION_TRACER
-/* mcount and __fentry__ are defined in assembly */
-#ifdef CC_USING_FENTRY
-EXPORT_SYMBOL(__fentry__);
-#else
-EXPORT_SYMBOL(mcount);
-#endif
-#endif
-
-EXPORT_SYMBOL(__get_user_1);
-EXPORT_SYMBOL(__get_user_2);
-EXPORT_SYMBOL(__get_user_4);
-EXPORT_SYMBOL(__get_user_8);
-EXPORT_SYMBOL(__put_user_1);
-EXPORT_SYMBOL(__put_user_2);
-EXPORT_SYMBOL(__put_user_4);
-EXPORT_SYMBOL(__put_user_8);
-
-EXPORT_SYMBOL(copy_user_generic_string);
-EXPORT_SYMBOL(copy_user_generic_unrolled);
-EXPORT_SYMBOL(copy_user_enhanced_fast_string);
-EXPORT_SYMBOL(__copy_user_nocache);
-EXPORT_SYMBOL(_copy_from_user);
-EXPORT_SYMBOL(_copy_to_user);
-
-EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled);
-
-EXPORT_SYMBOL(copy_page);
-EXPORT_SYMBOL(clear_page);
-
-EXPORT_SYMBOL(csum_partial);
-
-EXPORT_SYMBOL(__sw_hweight32);
-EXPORT_SYMBOL(__sw_hweight64);
-
-/*
- * Export string functions. We normally rely on gcc builtin for most of these,
- * but gcc sometimes decides not to inline them.
- */
-#undef memcpy
-#undef memset
-#undef memmove
-
-extern void *__memset(void *, int, __kernel_size_t);
-extern void *__memcpy(void *, const void *, __kernel_size_t);
-extern void *__memmove(void *, const void *, __kernel_size_t);
-extern void *memset(void *, int, __kernel_size_t);
-extern void *memcpy(void *, const void *, __kernel_size_t);
-extern void *memmove(void *, const void *, __kernel_size_t);
-
-EXPORT_SYMBOL(__memset);
-EXPORT_SYMBOL(__memcpy);
-EXPORT_SYMBOL(__memmove);
-
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(memmove);
-
-#ifndef CONFIG_DEBUG_VIRTUAL
-EXPORT_SYMBOL(phys_base);
-#endif
-EXPORT_SYMBOL(empty_zero_page);
-#ifndef CONFIG_PARAVIRT
-EXPORT_SYMBOL(native_load_gs_index);
-#endif
-
-#ifdef CONFIG_PREEMPT
-EXPORT_SYMBOL(___preempt_schedule);
-EXPORT_SYMBOL(___preempt_schedule_notrace);
-#endif
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 4e95d3e..cbd7b92 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -5045,7 +5045,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
/* Decode and fetch the destination operand: register or memory. */
rc = decode_operand(ctxt, &ctxt->dst, (ctxt->d >> DstShift) & OpMask);
- if (ctxt->rip_relative)
+ if (ctxt->rip_relative && likely(ctxt->memopp))
ctxt->memopp->addr.mem.ea = address_mask(ctxt,
ctxt->memopp->addr.mem.ea + ctxt->_eip);
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index c7220ba..1a22de7 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -594,7 +594,7 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
ioapic->irr = 0;
ioapic->irr_delivered = 0;
ioapic->id = 0;
- memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS);
+ memset(ioapic->irq_eoi, 0x00, sizeof(ioapic->irq_eoi));
rtc_irq_eoi_tracking_reset(ioapic);
}
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index f8157a3..8ca1eca 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1138,21 +1138,6 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
}
-static void svm_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment)
-{
- struct vcpu_svm *svm = to_svm(vcpu);
-
- svm->vmcb->control.tsc_offset += adjustment;
- if (is_guest_mode(vcpu))
- svm->nested.hsave->control.tsc_offset += adjustment;
- else
- trace_kvm_write_tsc_offset(vcpu->vcpu_id,
- svm->vmcb->control.tsc_offset - adjustment,
- svm->vmcb->control.tsc_offset);
-
- mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
-}
-
static void avic_init_vmcb(struct vcpu_svm *svm)
{
struct vmcb *vmcb = svm->vmcb;
@@ -3449,12 +3434,6 @@ static int cr8_write_interception(struct vcpu_svm *svm)
return 0;
}
-static u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
-{
- struct vmcb *vmcb = get_host_vmcb(to_svm(vcpu));
- return vmcb->control.tsc_offset + host_tsc;
-}
-
static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -5422,8 +5401,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.has_wbinvd_exit = svm_has_wbinvd_exit,
.write_tsc_offset = svm_write_tsc_offset,
- .adjust_tsc_offset_guest = svm_adjust_tsc_offset_guest,
- .read_l1_tsc = svm_read_l1_tsc,
.set_tdp_cr3 = set_tdp_cr3,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index cf1b16d..5382b82 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -187,6 +187,7 @@ struct vmcs {
*/
struct loaded_vmcs {
struct vmcs *vmcs;
+ struct vmcs *shadow_vmcs;
int cpu;
int launched;
struct list_head loaded_vmcss_on_cpu_link;
@@ -411,7 +412,6 @@ struct nested_vmx {
* memory during VMXOFF, VMCLEAR, VMPTRLD.
*/
struct vmcs12 *cached_vmcs12;
- struct vmcs *current_shadow_vmcs;
/*
* Indicates if the shadow vmcs must be updated with the
* data hold by vmcs12
@@ -421,7 +421,6 @@ struct nested_vmx {
/* vmcs02_list cache of VMCSs recently used to run L2 guests */
struct list_head vmcs02_pool;
int vmcs02_num;
- u64 vmcs01_tsc_offset;
bool change_vmcs01_virtual_x2apic_mode;
/* L2 must run next, and mustn't decide to exit to L1. */
bool nested_run_pending;
@@ -1419,6 +1418,8 @@ static void vmcs_clear(struct vmcs *vmcs)
static inline void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs)
{
vmcs_clear(loaded_vmcs->vmcs);
+ if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched)
+ vmcs_clear(loaded_vmcs->shadow_vmcs);
loaded_vmcs->cpu = -1;
loaded_vmcs->launched = 0;
}
@@ -2605,20 +2606,6 @@ static u64 guest_read_tsc(struct kvm_vcpu *vcpu)
}
/*
- * Like guest_read_tsc, but always returns L1's notion of the timestamp
- * counter, even if a nested guest (L2) is currently running.
- */
-static u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
-{
- u64 tsc_offset;
-
- tsc_offset = is_guest_mode(vcpu) ?
- to_vmx(vcpu)->nested.vmcs01_tsc_offset :
- vmcs_read64(TSC_OFFSET);
- return host_tsc + tsc_offset;
-}
-
-/*
* writes 'offset' into guest's timestamp counter offset register
*/
static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
@@ -2631,7 +2618,6 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
* to the newly set TSC to get L2's TSC.
*/
struct vmcs12 *vmcs12;
- to_vmx(vcpu)->nested.vmcs01_tsc_offset = offset;
/* recalculate vmcs02.TSC_OFFSET: */
vmcs12 = get_vmcs12(vcpu);
vmcs_write64(TSC_OFFSET, offset +
@@ -2644,19 +2630,6 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
}
}
-static void vmx_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment)
-{
- u64 offset = vmcs_read64(TSC_OFFSET);
-
- vmcs_write64(TSC_OFFSET, offset + adjustment);
- if (is_guest_mode(vcpu)) {
- /* Even when running L2, the adjustment needs to apply to L1 */
- to_vmx(vcpu)->nested.vmcs01_tsc_offset += adjustment;
- } else
- trace_kvm_write_tsc_offset(vcpu->vcpu_id, offset,
- offset + adjustment);
-}
-
static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best = kvm_find_cpuid_entry(vcpu, 1, 0);
@@ -3562,6 +3535,7 @@ static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
loaded_vmcs_clear(loaded_vmcs);
free_vmcs(loaded_vmcs->vmcs);
loaded_vmcs->vmcs = NULL;
+ WARN_ON(loaded_vmcs->shadow_vmcs != NULL);
}
static void free_kvm_area(void)
@@ -6696,6 +6670,7 @@ static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx)
if (!item)
return NULL;
item->vmcs02.vmcs = alloc_vmcs();
+ item->vmcs02.shadow_vmcs = NULL;
if (!item->vmcs02.vmcs) {
kfree(item);
return NULL;
@@ -7072,7 +7047,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
shadow_vmcs->revision_id |= (1u << 31);
/* init shadow vmcs */
vmcs_clear(shadow_vmcs);
- vmx->nested.current_shadow_vmcs = shadow_vmcs;
+ vmx->vmcs01.shadow_vmcs = shadow_vmcs;
}
INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool));
@@ -7174,8 +7149,11 @@ static void free_nested(struct vcpu_vmx *vmx)
free_page((unsigned long)vmx->nested.msr_bitmap);
vmx->nested.msr_bitmap = NULL;
}
- if (enable_shadow_vmcs)
- free_vmcs(vmx->nested.current_shadow_vmcs);
+ if (enable_shadow_vmcs) {
+ vmcs_clear(vmx->vmcs01.shadow_vmcs);
+ free_vmcs(vmx->vmcs01.shadow_vmcs);
+ vmx->vmcs01.shadow_vmcs = NULL;
+ }
kfree(vmx->nested.cached_vmcs12);
/* Unpin physical memory we referred to in current vmcs02 */
if (vmx->nested.apic_access_page) {
@@ -7352,7 +7330,7 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
int i;
unsigned long field;
u64 field_value;
- struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs;
+ struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
const unsigned long *fields = shadow_read_write_fields;
const int num_fields = max_shadow_read_write_fields;
@@ -7401,7 +7379,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
int i, q;
unsigned long field;
u64 field_value = 0;
- struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs;
+ struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
vmcs_load(shadow_vmcs);
@@ -7591,7 +7569,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
SECONDARY_EXEC_SHADOW_VMCS);
vmcs_write64(VMCS_LINK_POINTER,
- __pa(vmx->nested.current_shadow_vmcs));
+ __pa(vmx->vmcs01.shadow_vmcs));
vmx->nested.sync_shadow_vmcs = true;
}
}
@@ -7659,7 +7637,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
types = (vmx->nested.nested_vmx_ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
- if (!(types & (1UL << type))) {
+ if (type >= 32 || !(types & (1 << type))) {
nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
skip_emulated_instruction(vcpu);
@@ -7722,7 +7700,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
types = (vmx->nested.nested_vmx_vpid_caps >> 8) & 0x7;
- if (!(types & (1UL << type))) {
+ if (type >= 32 || !(types & (1 << type))) {
nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
skip_emulated_instruction(vcpu);
@@ -9156,6 +9134,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
vmx->loaded_vmcs = &vmx->vmcs01;
vmx->loaded_vmcs->vmcs = alloc_vmcs();
+ vmx->loaded_vmcs->shadow_vmcs = NULL;
if (!vmx->loaded_vmcs->vmcs)
goto free_msrs;
if (!vmm_exclusive)
@@ -10061,9 +10040,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
vmcs_write64(TSC_OFFSET,
- vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset);
+ vcpu->arch.tsc_offset + vmcs12->tsc_offset);
else
- vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
+ vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
if (kvm_has_tsc_control)
decache_tsc_multiplier(vmx);
@@ -10293,8 +10272,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
enter_guest_mode(vcpu);
- vmx->nested.vmcs01_tsc_offset = vmcs_read64(TSC_OFFSET);
-
if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
@@ -10818,7 +10795,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
load_vmcs12_host_state(vcpu, vmcs12);
/* Update any VMCS fields that might have changed while L2 ran */
- vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
+ vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
if (vmx->hv_deadline_tsc == -1)
vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
PIN_BASED_VMX_PREEMPTION_TIMER);
@@ -11339,8 +11316,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
.write_tsc_offset = vmx_write_tsc_offset,
- .adjust_tsc_offset_guest = vmx_adjust_tsc_offset_guest,
- .read_l1_tsc = vmx_read_l1_tsc,
.set_tdp_cr3 = vmx_set_cr3,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6c633de..3017de0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1409,7 +1409,7 @@ static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
{
- return kvm_x86_ops->read_l1_tsc(vcpu, kvm_scale_tsc(vcpu, host_tsc));
+ return vcpu->arch.tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
}
EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
@@ -1547,7 +1547,7 @@ EXPORT_SYMBOL_GPL(kvm_write_tsc);
static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
s64 adjustment)
{
- kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment);
+ kvm_vcpu_write_tsc_offset(vcpu, vcpu->arch.tsc_offset + adjustment);
}
static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)
@@ -1555,7 +1555,7 @@ static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)
if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio)
WARN_ON(adjustment < 0);
adjustment = kvm_scale_tsc(vcpu, (u64) adjustment);
- kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment);
+ adjust_tsc_offset_guest(vcpu, adjustment);
}
#ifdef CONFIG_X86_64
@@ -2262,7 +2262,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
/* Drop writes to this legacy MSR -- see rdmsr
* counterpart for further detail.
*/
- vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data);
+ vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", msr, data);
break;
case MSR_AMD64_OSVW_ID_LENGTH:
if (!guest_cpuid_has_osvw(vcpu))
@@ -2280,11 +2280,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if (kvm_pmu_is_valid_msr(vcpu, msr))
return kvm_pmu_set_msr(vcpu, msr_info);
if (!ignore_msrs) {
- vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n",
+ vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data 0x%llx\n",
msr, data);
return 1;
} else {
- vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n",
+ vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n",
msr, data);
break;
}
@@ -5733,13 +5733,13 @@ static int kvmclock_cpu_online(unsigned int cpu)
static void kvm_timer_init(void)
{
- int cpu;
-
max_tsc_khz = tsc_khz;
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
#ifdef CONFIG_CPU_FREQ
struct cpufreq_policy policy;
+ int cpu;
+
memset(&policy, 0, sizeof(policy));
cpu = get_cpu();
cpufreq_get_policy(&policy, cpu);
@@ -7410,10 +7410,12 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
{
+ void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask;
+
kvmclock_reset(vcpu);
- free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
kvm_x86_ops->vcpu_free(vcpu);
+ free_cpumask_var(wbinvd_dirty_mask);
}
struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index c1e6232..4d34bb5 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -28,6 +28,7 @@
#include <linux/linkage.h>
#include <asm/errno.h>
#include <asm/asm.h>
+#include <asm/export.h>
/*
* computes a partial checksum, e.g. for TCP/UDP fragments
@@ -251,6 +252,7 @@
ENDPROC(csum_partial)
#endif
+EXPORT_SYMBOL(csum_partial)
/*
unsigned int csum_partial_copy_generic (const char *src, char *dst,
@@ -490,3 +492,4 @@
#undef ROUND1
#endif
+EXPORT_SYMBOL(csum_partial_copy_generic)
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index 65be7cf..5e2af3a 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,6 +1,7 @@
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
#include <asm/alternative-asm.h>
+#include <asm/export.h>
/*
* Most CPUs support enhanced REP MOVSB/STOSB instructions. It is
@@ -23,6 +24,7 @@
rep stosq
ret
ENDPROC(clear_page)
+EXPORT_SYMBOL(clear_page)
ENTRY(clear_page_orig)
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index ad53497..03a186f 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -7,6 +7,7 @@
*/
#include <linux/linkage.h>
+#include <asm/export.h>
.text
@@ -48,3 +49,4 @@
ret
ENDPROC(cmpxchg8b_emu)
+EXPORT_SYMBOL(cmpxchg8b_emu)
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index 24ef1c2..e850815 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -3,6 +3,7 @@
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
#include <asm/alternative-asm.h>
+#include <asm/export.h>
/*
* Some CPUs run faster using the string copy instructions (sane microcode).
@@ -17,6 +18,7 @@
rep movsq
ret
ENDPROC(copy_page)
+EXPORT_SYMBOL(copy_page)
ENTRY(copy_page_regs)
subq $2*8, %rsp
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index bf603eb..d376e4b 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -14,6 +14,7 @@
#include <asm/alternative-asm.h>
#include <asm/asm.h>
#include <asm/smap.h>
+#include <asm/export.h>
/* Standard copy_to_user with segment limit checking */
ENTRY(_copy_to_user)
@@ -29,6 +30,7 @@
"jmp copy_user_enhanced_fast_string", \
X86_FEATURE_ERMS
ENDPROC(_copy_to_user)
+EXPORT_SYMBOL(_copy_to_user)
/* Standard copy_from_user with segment limit checking */
ENTRY(_copy_from_user)
@@ -44,6 +46,8 @@
"jmp copy_user_enhanced_fast_string", \
X86_FEATURE_ERMS
ENDPROC(_copy_from_user)
+EXPORT_SYMBOL(_copy_from_user)
+
.section .fixup,"ax"
/* must zero dest */
@@ -155,6 +159,7 @@
_ASM_EXTABLE(21b,50b)
_ASM_EXTABLE(22b,50b)
ENDPROC(copy_user_generic_unrolled)
+EXPORT_SYMBOL(copy_user_generic_unrolled)
/* Some CPUs run faster using the string copy instructions.
* This is also a lot simpler. Use them when possible.
@@ -200,6 +205,7 @@
_ASM_EXTABLE(1b,11b)
_ASM_EXTABLE(3b,12b)
ENDPROC(copy_user_generic_string)
+EXPORT_SYMBOL(copy_user_generic_string)
/*
* Some CPUs are adding enhanced REP MOVSB/STOSB instructions.
@@ -229,6 +235,7 @@
_ASM_EXTABLE(1b,12b)
ENDPROC(copy_user_enhanced_fast_string)
+EXPORT_SYMBOL(copy_user_enhanced_fast_string)
/*
* copy_user_nocache - Uncached memory copy with exception handling
@@ -379,3 +386,4 @@
_ASM_EXTABLE(40b,.L_fixup_1b_copy)
_ASM_EXTABLE(41b,.L_fixup_1b_copy)
ENDPROC(__copy_user_nocache)
+EXPORT_SYMBOL(__copy_user_nocache)
diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
index 9a7fe6a..378e5d5 100644
--- a/arch/x86/lib/csum-partial_64.c
+++ b/arch/x86/lib/csum-partial_64.c
@@ -135,6 +135,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum)
return (__force __wsum)add32_with_carry(do_csum(buff, len),
(__force u32)sum);
}
+EXPORT_SYMBOL(csum_partial);
/*
* this routine is used for miscellaneous IP-like checksums, mainly
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 0ef5128..37b62d4 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -32,6 +32,7 @@
#include <asm/thread_info.h>
#include <asm/asm.h>
#include <asm/smap.h>
+#include <asm/export.h>
.text
ENTRY(__get_user_1)
@@ -44,6 +45,7 @@
ASM_CLAC
ret
ENDPROC(__get_user_1)
+EXPORT_SYMBOL(__get_user_1)
ENTRY(__get_user_2)
add $1,%_ASM_AX
@@ -57,6 +59,7 @@
ASM_CLAC
ret
ENDPROC(__get_user_2)
+EXPORT_SYMBOL(__get_user_2)
ENTRY(__get_user_4)
add $3,%_ASM_AX
@@ -70,6 +73,7 @@
ASM_CLAC
ret
ENDPROC(__get_user_4)
+EXPORT_SYMBOL(__get_user_4)
ENTRY(__get_user_8)
#ifdef CONFIG_X86_64
@@ -97,6 +101,7 @@
ret
#endif
ENDPROC(__get_user_8)
+EXPORT_SYMBOL(__get_user_8)
bad_get_user:
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
index 8a602a1..23d893c 100644
--- a/arch/x86/lib/hweight.S
+++ b/arch/x86/lib/hweight.S
@@ -1,4 +1,5 @@
#include <linux/linkage.h>
+#include <asm/export.h>
#include <asm/asm.h>
@@ -32,6 +33,7 @@
__ASM_SIZE(pop,) %__ASM_REG(dx)
ret
ENDPROC(__sw_hweight32)
+EXPORT_SYMBOL(__sw_hweight32)
ENTRY(__sw_hweight64)
#ifdef CONFIG_X86_64
@@ -77,3 +79,4 @@
ret
#endif
ENDPROC(__sw_hweight64)
+EXPORT_SYMBOL(__sw_hweight64)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 49e6eba..779782f 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -4,6 +4,7 @@
#include <asm/errno.h>
#include <asm/cpufeatures.h>
#include <asm/alternative-asm.h>
+#include <asm/export.h>
/*
* We build a jump to memcpy_orig by default which gets NOPped out on
@@ -40,6 +41,8 @@
ret
ENDPROC(memcpy)
ENDPROC(__memcpy)
+EXPORT_SYMBOL(memcpy)
+EXPORT_SYMBOL(__memcpy)
/*
* memcpy_erms() - enhanced fast string memcpy. This is faster and
@@ -274,6 +277,7 @@
xorq %rax, %rax
ret
ENDPROC(memcpy_mcsafe_unrolled)
+EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled)
.section .fixup, "ax"
/* Return -EFAULT for any failure */
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 90ce01b..15de86c 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -8,6 +8,7 @@
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
#include <asm/alternative-asm.h>
+#include <asm/export.h>
#undef memmove
@@ -207,3 +208,5 @@
retq
ENDPROC(__memmove)
ENDPROC(memmove)
+EXPORT_SYMBOL(__memmove)
+EXPORT_SYMBOL(memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index e1229ec..55b95db 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -3,6 +3,7 @@
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
#include <asm/alternative-asm.h>
+#include <asm/export.h>
.weak memset
@@ -43,6 +44,8 @@
ret
ENDPROC(memset)
ENDPROC(__memset)
+EXPORT_SYMBOL(memset)
+EXPORT_SYMBOL(__memset)
/*
* ISO C memset - set a memory block to a byte value. This function uses
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index c891ece..cd5d716 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -15,6 +15,7 @@
#include <asm/errno.h>
#include <asm/asm.h>
#include <asm/smap.h>
+#include <asm/export.h>
/*
@@ -43,6 +44,7 @@
xor %eax,%eax
EXIT
ENDPROC(__put_user_1)
+EXPORT_SYMBOL(__put_user_1)
ENTRY(__put_user_2)
ENTER
@@ -55,6 +57,7 @@
xor %eax,%eax
EXIT
ENDPROC(__put_user_2)
+EXPORT_SYMBOL(__put_user_2)
ENTRY(__put_user_4)
ENTER
@@ -67,6 +70,7 @@
xor %eax,%eax
EXIT
ENDPROC(__put_user_4)
+EXPORT_SYMBOL(__put_user_4)
ENTRY(__put_user_8)
ENTER
@@ -82,6 +86,7 @@
xor %eax,%eax
EXIT
ENDPROC(__put_user_8)
+EXPORT_SYMBOL(__put_user_8)
bad_put_user:
movl $-EFAULT,%eax
diff --git a/arch/x86/lib/strstr_32.c b/arch/x86/lib/strstr_32.c
index 8e2d55f..a03b1c7 100644
--- a/arch/x86/lib/strstr_32.c
+++ b/arch/x86/lib/strstr_32.c
@@ -1,4 +1,5 @@
#include <linux/string.h>
+#include <linux/export.h>
char *strstr(const char *cs, const char *ct)
{
@@ -28,4 +29,4 @@ __asm__ __volatile__(
: "dx", "di");
return __res;
}
-
+EXPORT_SYMBOL(strstr);
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index b8b6a60..0d4fb3e 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -435,7 +435,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
ret = get_user_pages_unlocked(start,
(end - start) >> PAGE_SHIFT,
- write, 0, pages);
+ pages, write ? FOLL_WRITE : 0);
/* Have to be a bit careful with return values */
if (nr > 0) {
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index ddd2661..887e571 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -104,10 +104,10 @@ void __init kernel_randomize_memory(void)
* consistent with the vaddr_start/vaddr_end variables.
*/
BUILD_BUG_ON(vaddr_start >= vaddr_end);
- BUILD_BUG_ON(config_enabled(CONFIG_X86_ESPFIX64) &&
+ BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_ESPFIX64) &&
vaddr_end >= EFI_VA_START);
- BUILD_BUG_ON((config_enabled(CONFIG_X86_ESPFIX64) ||
- config_enabled(CONFIG_EFI)) &&
+ BUILD_BUG_ON((IS_ENABLED(CONFIG_X86_ESPFIX64) ||
+ IS_ENABLED(CONFIG_EFI)) &&
vaddr_end >= __START_KERNEL_map);
BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 8047687..e4f8009 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -544,10 +544,9 @@ static int mpx_resolve_fault(long __user *addr, int write)
{
long gup_ret;
int nr_pages = 1;
- int force = 0;
- gup_ret = get_user_pages((unsigned long)addr, nr_pages, write,
- force, NULL, NULL);
+ gup_ret = get_user_pages((unsigned long)addr, nr_pages,
+ write ? FOLL_WRITE : 0, NULL, NULL);
/*
* get_user_pages() returns number of pages gotten.
* 0 means we failed to fault in and get anything,
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 170cc4f..83e701f 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -730,6 +730,20 @@ void io_free_memtype(resource_size_t start, resource_size_t end)
free_memtype(start, end);
}
+int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size)
+{
+ enum page_cache_mode type = _PAGE_CACHE_MODE_WC;
+
+ return io_reserve_memtype(start, start + size, &type);
+}
+EXPORT_SYMBOL(arch_io_reserve_memtype_wc);
+
+void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size)
+{
+ io_free_memtype(start, start + size);
+}
+EXPORT_SYMBOL(arch_io_free_memtype_wc);
+
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot)
{
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index bf99aa7..936a488 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -861,7 +861,7 @@ static void __init __efi_enter_virtual_mode(void)
int count = 0, pg_shift = 0;
void *new_memmap = NULL;
efi_status_t status;
- phys_addr_t pa;
+ unsigned long pa;
efi.systab = NULL;
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 58b0f80..319148b 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -31,6 +31,7 @@
#include <linux/io.h>
#include <linux/reboot.h>
#include <linux/slab.h>
+#include <linux/ucs2_string.h>
#include <asm/setup.h>
#include <asm/page.h>
@@ -211,6 +212,35 @@ void efi_sync_low_kernel_mappings(void)
memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);
}
+/*
+ * Wrapper for slow_virt_to_phys() that handles NULL addresses.
+ */
+static inline phys_addr_t
+virt_to_phys_or_null_size(void *va, unsigned long size)
+{
+ bool bad_size;
+
+ if (!va)
+ return 0;
+
+ if (virt_addr_valid(va))
+ return virt_to_phys(va);
+
+ /*
+ * A fully aligned variable on the stack is guaranteed not to
+ * cross a page bounary. Try to catch strings on the stack by
+ * checking that 'size' is a power of two.
+ */
+ bad_size = size > PAGE_SIZE || !is_power_of_2(size);
+
+ WARN_ON(!IS_ALIGNED((unsigned long)va, size) || bad_size);
+
+ return slow_virt_to_phys(va);
+}
+
+#define virt_to_phys_or_null(addr) \
+ virt_to_phys_or_null_size((addr), sizeof(*(addr)))
+
int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
{
unsigned long pfn, text;
@@ -494,8 +524,8 @@ static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc)
spin_lock(&rtc_lock);
- phys_tm = virt_to_phys(tm);
- phys_tc = virt_to_phys(tc);
+ phys_tm = virt_to_phys_or_null(tm);
+ phys_tc = virt_to_phys_or_null(tc);
status = efi_thunk(get_time, phys_tm, phys_tc);
@@ -511,7 +541,7 @@ static efi_status_t efi_thunk_set_time(efi_time_t *tm)
spin_lock(&rtc_lock);
- phys_tm = virt_to_phys(tm);
+ phys_tm = virt_to_phys_or_null(tm);
status = efi_thunk(set_time, phys_tm);
@@ -529,9 +559,9 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
spin_lock(&rtc_lock);
- phys_enabled = virt_to_phys(enabled);
- phys_pending = virt_to_phys(pending);
- phys_tm = virt_to_phys(tm);
+ phys_enabled = virt_to_phys_or_null(enabled);
+ phys_pending = virt_to_phys_or_null(pending);
+ phys_tm = virt_to_phys_or_null(tm);
status = efi_thunk(get_wakeup_time, phys_enabled,
phys_pending, phys_tm);
@@ -549,7 +579,7 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
spin_lock(&rtc_lock);
- phys_tm = virt_to_phys(tm);
+ phys_tm = virt_to_phys_or_null(tm);
status = efi_thunk(set_wakeup_time, enabled, phys_tm);
@@ -558,6 +588,10 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
return status;
}
+static unsigned long efi_name_size(efi_char16_t *name)
+{
+ return ucs2_strsize(name, EFI_VAR_NAME_LEN) + 1;
+}
static efi_status_t
efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
@@ -567,11 +601,11 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
u32 phys_name, phys_vendor, phys_attr;
u32 phys_data_size, phys_data;
- phys_data_size = virt_to_phys(data_size);
- phys_vendor = virt_to_phys(vendor);
- phys_name = virt_to_phys(name);
- phys_attr = virt_to_phys(attr);
- phys_data = virt_to_phys(data);
+ phys_data_size = virt_to_phys_or_null(data_size);
+ phys_vendor = virt_to_phys_or_null(vendor);
+ phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
+ phys_attr = virt_to_phys_or_null(attr);
+ phys_data = virt_to_phys_or_null_size(data, *data_size);
status = efi_thunk(get_variable, phys_name, phys_vendor,
phys_attr, phys_data_size, phys_data);
@@ -586,9 +620,9 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
u32 phys_name, phys_vendor, phys_data;
efi_status_t status;
- phys_name = virt_to_phys(name);
- phys_vendor = virt_to_phys(vendor);
- phys_data = virt_to_phys(data);
+ phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
+ phys_vendor = virt_to_phys_or_null(vendor);
+ phys_data = virt_to_phys_or_null_size(data, data_size);
/* If data_size is > sizeof(u32) we've got problems */
status = efi_thunk(set_variable, phys_name, phys_vendor,
@@ -605,9 +639,9 @@ efi_thunk_get_next_variable(unsigned long *name_size,
efi_status_t status;
u32 phys_name_size, phys_name, phys_vendor;
- phys_name_size = virt_to_phys(name_size);
- phys_vendor = virt_to_phys(vendor);
- phys_name = virt_to_phys(name);
+ phys_name_size = virt_to_phys_or_null(name_size);
+ phys_vendor = virt_to_phys_or_null(vendor);
+ phys_name = virt_to_phys_or_null_size(name, *name_size);
status = efi_thunk(get_next_variable, phys_name_size,
phys_name, phys_vendor);
@@ -621,7 +655,7 @@ efi_thunk_get_next_high_mono_count(u32 *count)
efi_status_t status;
u32 phys_count;
- phys_count = virt_to_phys(count);
+ phys_count = virt_to_phys_or_null(count);
status = efi_thunk(get_next_high_mono_count, phys_count);
return status;
@@ -633,7 +667,7 @@ efi_thunk_reset_system(int reset_type, efi_status_t status,
{
u32 phys_data;
- phys_data = virt_to_phys(data);
+ phys_data = virt_to_phys_or_null_size(data, data_size);
efi_thunk(reset_system, reset_type, status, data_size, phys_data);
}
@@ -661,9 +695,9 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space,
if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
return EFI_UNSUPPORTED;
- phys_storage = virt_to_phys(storage_space);
- phys_remaining = virt_to_phys(remaining_space);
- phys_max = virt_to_phys(max_variable_size);
+ phys_storage = virt_to_phys_or_null(storage_space);
+ phys_remaining = virt_to_phys_or_null(remaining_space);
+ phys_max = virt_to_phys_or_null(max_variable_size);
status = efi_thunk(query_variable_info, attr, phys_storage,
phys_remaining, phys_max);
diff --git a/arch/x86/platform/intel-mid/pwr.c b/arch/x86/platform/intel-mid/pwr.c
index 5d3b45a..67375dd 100644
--- a/arch/x86/platform/intel-mid/pwr.c
+++ b/arch/x86/platform/intel-mid/pwr.c
@@ -272,6 +272,25 @@ int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state)
}
EXPORT_SYMBOL_GPL(intel_mid_pci_set_power_state);
+pci_power_t intel_mid_pci_get_power_state(struct pci_dev *pdev)
+{
+ struct mid_pwr *pwr = midpwr;
+ int id, reg, bit;
+ u32 power;
+
+ if (!pwr || !pwr->available)
+ return PCI_UNKNOWN;
+
+ id = intel_mid_pwr_get_lss_id(pdev);
+ if (id < 0)
+ return PCI_UNKNOWN;
+
+ reg = (id * LSS_PWS_BITS) / 32;
+ bit = (id * LSS_PWS_BITS) % 32;
+ power = mid_pwr_get_state(pwr, reg);
+ return (__force pci_power_t)((power >> bit) & 3);
+}
+
void intel_mid_pwr_power_off(void)
{
struct mid_pwr *pwr = midpwr;
diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c
index b4d5e95..4a6a5a2 100644
--- a/arch/x86/platform/uv/bios_uv.c
+++ b/arch/x86/platform/uv/bios_uv.c
@@ -40,7 +40,15 @@ s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
*/
return BIOS_STATUS_UNIMPLEMENTED;
- ret = efi_call_virt_pointer(tab, function, (u64)which, a1, a2, a3, a4, a5);
+ /*
+ * If EFI_OLD_MEMMAP is set, we need to fall back to using our old EFI
+ * callback method, which uses efi_call() directly, with the kernel page tables:
+ */
+ if (unlikely(test_bit(EFI_OLD_MEMMAP, &efi.flags)))
+ ret = efi_call((void *)__va(tab->function), (u64)which, a1, a2, a3, a4, a5);
+ else
+ ret = efi_call_virt_pointer(tab, function, (u64)which, a1, a2, a3, a4, a5);
+
return ret;
}
EXPORT_SYMBOL_GPL(uv_bios_call);
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
index 3ee2bb6..e7e7055 100644
--- a/arch/x86/um/Makefile
+++ b/arch/x86/um/Makefile
@@ -8,7 +8,7 @@
BITS := 64
endif
-obj-y = bug.o bugs_$(BITS).o delay.o fault.o ksyms.o ldt.o \
+obj-y = bug.o bugs_$(BITS).o delay.o fault.o ldt.o \
ptrace_$(BITS).o ptrace_user.o setjmp_$(BITS).o signal.o \
stub_$(BITS).o stub_segv.o \
sys_call_table_$(BITS).o sysrq_$(BITS).o tls_$(BITS).o \
diff --git a/arch/x86/um/checksum_32.S b/arch/x86/um/checksum_32.S
index fa4b8b9..b9933eb 100644
--- a/arch/x86/um/checksum_32.S
+++ b/arch/x86/um/checksum_32.S
@@ -27,6 +27,7 @@
#include <asm/errno.h>
#include <asm/asm.h>
+#include <asm/export.h>
/*
* computes a partial checksum, e.g. for TCP/UDP fragments
@@ -214,3 +215,4 @@
ret
#endif
+ EXPORT_SYMBOL(csum_partial)
diff --git a/arch/x86/um/ksyms.c b/arch/x86/um/ksyms.c
deleted file mode 100644
index 2e8f43e..0000000
--- a/arch/x86/um/ksyms.c
+++ /dev/null
@@ -1,13 +0,0 @@
-#include <linux/module.h>
-#include <asm/string.h>
-#include <asm/checksum.h>
-
-#ifndef CONFIG_X86_32
-/*XXX: we need them because they would be exported by x86_64 */
-#if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4
-EXPORT_SYMBOL(memcpy);
-#else
-EXPORT_SYMBOL(__memcpy);
-#endif
-#endif
-EXPORT_SYMBOL(csum_partial);
diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c
index 5766ead..60a5a5a 100644
--- a/arch/x86/um/ptrace_32.c
+++ b/arch/x86/um/ptrace_32.c
@@ -36,7 +36,8 @@ int is_syscall(unsigned long addr)
* slow, but that doesn't matter, since it will be called only
* in case of singlestepping, if copy_from_user failed.
*/
- n = access_process_vm(current, addr, &instr, sizeof(instr), 0);
+ n = access_process_vm(current, addr, &instr, sizeof(instr),
+ FOLL_FORCE);
if (n != sizeof(instr)) {
printk(KERN_ERR "is_syscall : failed to read "
"instruction from 0x%lx\n", addr);
diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c
index 0b5c184..e30202b 100644
--- a/arch/x86/um/ptrace_64.c
+++ b/arch/x86/um/ptrace_64.c
@@ -212,7 +212,8 @@ int is_syscall(unsigned long addr)
* slow, but that doesn't matter, since it will be called only
* in case of singlestepping, if copy_from_user failed.
*/
- n = access_process_vm(current, addr, &instr, sizeof(instr), 0);
+ n = access_process_vm(current, addr, &instr, sizeof(instr),
+ FOLL_FORCE);
if (n != sizeof(instr)) {
printk("is_syscall : failed to read instruction from "
"0x%lx\n", addr);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c0fdd57..bdd8556 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1837,6 +1837,7 @@ static void __init init_hvm_pv_info(void)
xen_domain_type = XEN_HVM_DOMAIN;
}
+#endif
static int xen_cpu_up_prepare(unsigned int cpu)
{
@@ -1887,6 +1888,7 @@ static int xen_cpu_up_online(unsigned int cpu)
return 0;
}
+#ifdef CONFIG_XEN_PVHVM
#ifdef CONFIG_KEXEC_CORE
static void xen_hvm_shutdown(void)
{
diff --git a/block/badblocks.c b/block/badblocks.c
index 7be53cb..6ebcef2 100644
--- a/block/badblocks.c
+++ b/block/badblocks.c
@@ -133,6 +133,26 @@ int badblocks_check(struct badblocks *bb, sector_t s, int sectors,
}
EXPORT_SYMBOL_GPL(badblocks_check);
+static void badblocks_update_acked(struct badblocks *bb)
+{
+ u64 *p = bb->page;
+ int i;
+ bool unacked = false;
+
+ if (!bb->unacked_exist)
+ return;
+
+ for (i = 0; i < bb->count ; i++) {
+ if (!BB_ACK(p[i])) {
+ unacked = true;
+ break;
+ }
+ }
+
+ if (!unacked)
+ bb->unacked_exist = 0;
+}
+
/**
* badblocks_set() - Add a range of bad blocks to the table.
* @bb: the badblocks structure that holds all badblock information
@@ -294,6 +314,8 @@ int badblocks_set(struct badblocks *bb, sector_t s, int sectors,
bb->changed = 1;
if (!acknowledged)
bb->unacked_exist = 1;
+ else
+ badblocks_update_acked(bb);
write_sequnlock_irqrestore(&bb->lock, flags);
return rv;
@@ -354,7 +376,8 @@ int badblocks_clear(struct badblocks *bb, sector_t s, int sectors)
* current range. Earlier ranges could also overlap,
* but only this one can overlap the end of the range.
*/
- if (BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > target) {
+ if ((BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > target) &&
+ (BB_OFFSET(p[lo]) < target)) {
/* Partial overlap, leave the tail of this range */
int ack = BB_ACK(p[lo]);
sector_t a = BB_OFFSET(p[lo]);
@@ -377,7 +400,8 @@ int badblocks_clear(struct badblocks *bb, sector_t s, int sectors)
lo--;
}
while (lo >= 0 &&
- BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) {
+ (BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) &&
+ (BB_OFFSET(p[lo]) < target)) {
/* This range does overlap */
if (BB_OFFSET(p[lo]) < s) {
/* Keep the early parts of this range. */
@@ -399,6 +423,7 @@ int badblocks_clear(struct badblocks *bb, sector_t s, int sectors)
}
}
+ badblocks_update_acked(bb);
bb->changed = 1;
out:
write_sequnlock_irq(&bb->lock);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index dd38e5c..b08ccbb 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1340,10 +1340,8 @@ int blkcg_policy_register(struct blkcg_policy *pol)
struct blkcg_policy_data *cpd;
cpd = pol->cpd_alloc_fn(GFP_KERNEL);
- if (!cpd) {
- mutex_unlock(&blkcg_pol_mutex);
+ if (!cpd)
goto err_free_cpds;
- }
blkcg->cpd[pol->plid] = cpd;
cpd->blkcg = blkcg;
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 6a14b68..3c882cb 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -343,6 +343,34 @@ static void flush_data_end_io(struct request *rq, int error)
struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
/*
+ * Updating q->in_flight[] here for making this tag usable
+ * early. Because in blk_queue_start_tag(),
+ * q->in_flight[BLK_RW_ASYNC] is used to limit async I/O and
+ * reserve tags for sync I/O.
+ *
+ * More importantly this way can avoid the following I/O
+ * deadlock:
+ *
+ * - suppose there are 40 fua requests comming to flush queue
+ * and queue depth is 31
+ * - 30 rqs are scheduled then blk_queue_start_tag() can't alloc
+ * tag for async I/O any more
+ * - all the 30 rqs are completed before FLUSH_PENDING_TIMEOUT
+ * and flush_data_end_io() is called
+ * - the other rqs still can't go ahead if not updating
+ * q->in_flight[BLK_RW_ASYNC] here, meantime these rqs
+ * are held in flush data queue and make no progress of
+ * handling post flush rq
+ * - only after the post flush rq is handled, all these rqs
+ * can be completed
+ */
+
+ elv_completed_request(q, rq);
+
+ /* for avoiding double accounting */
+ rq->cmd_flags &= ~REQ_STARTED;
+
+ /*
* After populating an empty queue, kick it to avoid stall. Read
* the comment in flush_end_io().
*/
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ddc2eed..f3d27a6 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1217,9 +1217,9 @@ static struct request *blk_mq_map_request(struct request_queue *q,
blk_mq_set_alloc_data(&alloc_data, q, 0, ctx, hctx);
rq = __blk_mq_alloc_request(&alloc_data, op, op_flags);
- hctx->queued++;
- data->hctx = hctx;
- data->ctx = ctx;
+ data->hctx = alloc_data.hctx;
+ data->ctx = alloc_data.ctx;
+ data->hctx->queued++;
return rq;
}
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 96631e6..06cf980 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -18,7 +18,7 @@ static DEFINE_PER_CPU(struct list_head, blk_cpu_done);
* Softirq action handler - move entries to local list and loop over them
* while passing them to the queue registered handler.
*/
-static void blk_done_softirq(struct softirq_action *h)
+static __latent_entropy void blk_done_softirq(struct softirq_action *h)
{
struct list_head *cpu_list, local_list;
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 80a0f1a..8948392 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -132,28 +132,27 @@ static void aead_wmem_wakeup(struct sock *sk)
static int aead_wait_for_data(struct sock *sk, unsigned flags)
{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct alg_sock *ask = alg_sk(sk);
struct aead_ctx *ctx = ask->private;
long timeout;
- DEFINE_WAIT(wait);
int err = -ERESTARTSYS;
if (flags & MSG_DONTWAIT)
return -EAGAIN;
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
-
+ add_wait_queue(sk_sleep(sk), &wait);
for (;;) {
if (signal_pending(current))
break;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
timeout = MAX_SCHEDULE_TIMEOUT;
- if (sk_wait_event(sk, &timeout, !ctx->more)) {
+ if (sk_wait_event(sk, &timeout, !ctx->more, &wait)) {
err = 0;
break;
}
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 28556fc..1e38aaa 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -199,26 +199,26 @@ static void skcipher_free_sgl(struct sock *sk)
static int skcipher_wait_for_wmem(struct sock *sk, unsigned flags)
{
- long timeout;
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
int err = -ERESTARTSYS;
+ long timeout;
if (flags & MSG_DONTWAIT)
return -EAGAIN;
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
+ add_wait_queue(sk_sleep(sk), &wait);
for (;;) {
if (signal_pending(current))
break;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
timeout = MAX_SCHEDULE_TIMEOUT;
- if (sk_wait_event(sk, &timeout, skcipher_writable(sk))) {
+ if (sk_wait_event(sk, &timeout, skcipher_writable(sk), &wait)) {
err = 0;
break;
}
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
return err;
}
@@ -242,10 +242,10 @@ static void skcipher_wmem_wakeup(struct sock *sk)
static int skcipher_wait_for_data(struct sock *sk, unsigned flags)
{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct alg_sock *ask = alg_sk(sk);
struct skcipher_ctx *ctx = ask->private;
long timeout;
- DEFINE_WAIT(wait);
int err = -ERESTARTSYS;
if (flags & MSG_DONTWAIT) {
@@ -254,17 +254,17 @@ static int skcipher_wait_for_data(struct sock *sk, unsigned flags)
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ add_wait_queue(sk_sleep(sk), &wait);
for (;;) {
if (signal_pending(current))
break;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
timeout = MAX_SCHEDULE_TIMEOUT;
- if (sk_wait_event(sk, &timeout, ctx->used)) {
+ if (sk_wait_event(sk, &timeout, ctx->used, &wait)) {
err = 0;
break;
}
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
diff --git a/drivers/Makefile b/drivers/Makefile
index f0afdfb..194d20b 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -21,7 +21,7 @@
obj-y += idle/
# IPMI must come before ACPI in order to provide IPMI opregion support
-obj-$(CONFIG_IPMI_HANDLER) += char/ipmi/
+obj-y += char/ipmi/
obj-$(CONFIG_ACPI) += acpi/
obj-$(CONFIG_SFI) += sfi/
diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c
index d58fbf7..7dd7092 100644
--- a/drivers/acpi/acpi_apd.c
+++ b/drivers/acpi/acpi_apd.c
@@ -122,7 +122,7 @@ static int acpi_apd_create_device(struct acpi_device *adev,
int ret;
if (!dev_desc) {
- pdev = acpi_create_platform_device(adev);
+ pdev = acpi_create_platform_device(adev, NULL);
return IS_ERR_OR_NULL(pdev) ? PTR_ERR(pdev) : 1;
}
@@ -139,14 +139,8 @@ static int acpi_apd_create_device(struct acpi_device *adev,
goto err_out;
}
- if (dev_desc->properties) {
- ret = device_add_properties(&adev->dev, dev_desc->properties);
- if (ret)
- goto err_out;
- }
-
adev->driver_data = pdata;
- pdev = acpi_create_platform_device(adev);
+ pdev = acpi_create_platform_device(adev, dev_desc->properties);
if (!IS_ERR_OR_NULL(pdev))
return 1;
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 5520102..373657f 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -395,7 +395,7 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
dev_desc = (const struct lpss_device_desc *)id->driver_data;
if (!dev_desc) {
- pdev = acpi_create_platform_device(adev);
+ pdev = acpi_create_platform_device(adev, NULL);
return IS_ERR_OR_NULL(pdev) ? PTR_ERR(pdev) : 1;
}
pdata = kzalloc(sizeof(*pdata), GFP_KERNEL);
@@ -451,14 +451,8 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
goto err_out;
}
- if (dev_desc->properties) {
- ret = device_add_properties(&adev->dev, dev_desc->properties);
- if (ret)
- goto err_out;
- }
-
adev->driver_data = pdata;
- pdev = acpi_create_platform_device(adev);
+ pdev = acpi_create_platform_device(adev, dev_desc->properties);
if (!IS_ERR_OR_NULL(pdev)) {
return 1;
}
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index 8ea8211..eb76a4c 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -26,6 +26,7 @@
#include <linux/slab.h>
#include <linux/acpi.h>
#include <asm/mwait.h>
+#include <xen/xen.h>
#define ACPI_PROCESSOR_AGGREGATOR_CLASS "acpi_pad"
#define ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME "Processor Aggregator"
@@ -477,6 +478,10 @@ static struct acpi_driver acpi_pad_driver = {
static int __init acpi_pad_init(void)
{
+ /* Xen ACPI PAD is used when running as Xen Dom0. */
+ if (xen_initial_domain())
+ return -ENODEV;
+
power_saving_mwait_init();
if (power_saving_mwait_eax == 0)
return -EINVAL;
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index b200ae1..b4c1a6a 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -50,6 +50,7 @@ static void acpi_platform_fill_resource(struct acpi_device *adev,
/**
* acpi_create_platform_device - Create platform device for ACPI device node
* @adev: ACPI device node to create a platform device for.
+ * @properties: Optional collection of build-in properties.
*
* Check if the given @adev can be represented as a platform device and, if
* that's the case, create and register a platform device, populate its common
@@ -57,7 +58,8 @@ static void acpi_platform_fill_resource(struct acpi_device *adev,
*
* Name of the platform device will be the same as @adev's.
*/
-struct platform_device *acpi_create_platform_device(struct acpi_device *adev)
+struct platform_device *acpi_create_platform_device(struct acpi_device *adev,
+ struct property_entry *properties)
{
struct platform_device *pdev = NULL;
struct platform_device_info pdevinfo;
@@ -106,6 +108,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev)
pdevinfo.res = resources;
pdevinfo.num_res = count;
pdevinfo.fwnode = acpi_fwnode_handle(adev);
+ pdevinfo.properties = properties;
if (acpi_dma_supported(adev))
pdevinfo.dma_mask = DMA_BIT_MASK(32);
diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c
index f1e6dcc..54d48b9 100644
--- a/drivers/acpi/acpica/dsinit.c
+++ b/drivers/acpi/acpica/dsinit.c
@@ -46,6 +46,7 @@
#include "acdispat.h"
#include "acnamesp.h"
#include "actables.h"
+#include "acinterp.h"
#define _COMPONENT ACPI_DISPATCHER
ACPI_MODULE_NAME("dsinit")
@@ -214,23 +215,17 @@ acpi_ds_initialize_objects(u32 table_index,
/* Walk entire namespace from the supplied root */
- status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
- if (ACPI_FAILURE(status)) {
- return_ACPI_STATUS(status);
- }
-
/*
* We don't use acpi_walk_namespace since we do not want to acquire
* the namespace reader lock.
*/
status =
acpi_ns_walk_namespace(ACPI_TYPE_ANY, start_node, ACPI_UINT32_MAX,
- ACPI_NS_WALK_UNLOCK, acpi_ds_init_one_object,
- NULL, &info, NULL);
+ 0, acpi_ds_init_one_object, NULL, &info,
+ NULL);
if (ACPI_FAILURE(status)) {
ACPI_EXCEPTION((AE_INFO, status, "During WalkNamespace"));
}
- (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
status = acpi_get_table_by_index(table_index, &table);
if (ACPI_FAILURE(status)) {
diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c
index 32e9ddc..2b3210f 100644
--- a/drivers/acpi/acpica/dsmethod.c
+++ b/drivers/acpi/acpica/dsmethod.c
@@ -99,14 +99,11 @@ acpi_ds_auto_serialize_method(struct acpi_namespace_node *node,
"Method auto-serialization parse [%4.4s] %p\n",
acpi_ut_get_node_name(node), node));
- acpi_ex_enter_interpreter();
-
/* Create/Init a root op for the method parse tree */
op = acpi_ps_alloc_op(AML_METHOD_OP, obj_desc->method.aml_start);
if (!op) {
- status = AE_NO_MEMORY;
- goto unlock;
+ return_ACPI_STATUS(AE_NO_MEMORY);
}
acpi_ps_set_name(op, node->name.integer);
@@ -118,8 +115,7 @@ acpi_ds_auto_serialize_method(struct acpi_namespace_node *node,
acpi_ds_create_walk_state(node->owner_id, NULL, NULL, NULL);
if (!walk_state) {
acpi_ps_free_op(op);
- status = AE_NO_MEMORY;
- goto unlock;
+ return_ACPI_STATUS(AE_NO_MEMORY);
}
status = acpi_ds_init_aml_walk(walk_state, op, node,
@@ -138,8 +134,6 @@ acpi_ds_auto_serialize_method(struct acpi_namespace_node *node,
status = acpi_ps_parse_aml(walk_state);
acpi_ps_delete_parse_tree(op);
-unlock:
- acpi_ex_exit_interpreter();
return_ACPI_STATUS(status);
}
@@ -731,26 +725,6 @@ acpi_ds_terminate_control_method(union acpi_operand_object *method_desc,
acpi_ds_method_data_delete_all(walk_state);
/*
- * If method is serialized, release the mutex and restore the
- * current sync level for this thread
- */
- if (method_desc->method.mutex) {
-
- /* Acquisition Depth handles recursive calls */
-
- method_desc->method.mutex->mutex.acquisition_depth--;
- if (!method_desc->method.mutex->mutex.acquisition_depth) {
- walk_state->thread->current_sync_level =
- method_desc->method.mutex->mutex.
- original_sync_level;
-
- acpi_os_release_mutex(method_desc->method.
- mutex->mutex.os_mutex);
- method_desc->method.mutex->mutex.thread_id = 0;
- }
- }
-
- /*
* Delete any namespace objects created anywhere within the
* namespace by the execution of this method. Unless:
* 1) This method is a module-level executable code method, in which
@@ -786,6 +760,26 @@ acpi_ds_terminate_control_method(union acpi_operand_object *method_desc,
~ACPI_METHOD_MODIFIED_NAMESPACE;
}
}
+
+ /*
+ * If method is serialized, release the mutex and restore the
+ * current sync level for this thread
+ */
+ if (method_desc->method.mutex) {
+
+ /* Acquisition Depth handles recursive calls */
+
+ method_desc->method.mutex->mutex.acquisition_depth--;
+ if (!method_desc->method.mutex->mutex.acquisition_depth) {
+ walk_state->thread->current_sync_level =
+ method_desc->method.mutex->mutex.
+ original_sync_level;
+
+ acpi_os_release_mutex(method_desc->method.
+ mutex->mutex.os_mutex);
+ method_desc->method.mutex->mutex.thread_id = 0;
+ }
+ }
}
/* Decrement the thread count on the method */
diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c
index 028b22a..e362182 100644
--- a/drivers/acpi/acpica/dswload2.c
+++ b/drivers/acpi/acpica/dswload2.c
@@ -607,11 +607,9 @@ acpi_status acpi_ds_load2_end_op(struct acpi_walk_state *walk_state)
}
}
- acpi_ex_exit_interpreter();
status =
acpi_ev_initialize_region
(acpi_ns_get_attached_object(node), FALSE);
- acpi_ex_enter_interpreter();
if (ACPI_FAILURE(status)) {
/*
diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c
index 3843f1f..75ddd16 100644
--- a/drivers/acpi/acpica/evrgnini.c
+++ b/drivers/acpi/acpica/evrgnini.c
@@ -45,6 +45,7 @@
#include "accommon.h"
#include "acevents.h"
#include "acnamesp.h"
+#include "acinterp.h"
#define _COMPONENT ACPI_EVENTS
ACPI_MODULE_NAME("evrgnini")
@@ -597,9 +598,11 @@ acpi_ev_initialize_region(union acpi_operand_object *region_obj,
}
}
+ acpi_ex_exit_interpreter();
status =
acpi_ev_execute_reg_method(region_obj,
ACPI_REG_CONNECT);
+ acpi_ex_enter_interpreter();
if (acpi_ns_locked) {
status =
diff --git a/drivers/acpi/acpica/nsload.c b/drivers/acpi/acpica/nsload.c
index 334d3c5..d1f2014 100644
--- a/drivers/acpi/acpica/nsload.c
+++ b/drivers/acpi/acpica/nsload.c
@@ -137,7 +137,9 @@ acpi_ns_load_table(u32 table_index, struct acpi_namespace_node *node)
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
"**** Begin Table Object Initialization\n"));
+ acpi_ex_enter_interpreter();
status = acpi_ds_initialize_objects(table_index, node);
+ acpi_ex_exit_interpreter();
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
"**** Completed Table Object Initialization\n"));
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index f0a029e..0d099a2 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -662,7 +662,7 @@ static int ghes_proc(struct ghes *ghes)
ghes_do_proc(ghes, ghes->estatus);
out:
ghes_clear_estatus(ghes);
- return 0;
+ return rc;
}
static void ghes_add_timer(struct ghes *ghes)
diff --git a/drivers/acpi/dptf/int340x_thermal.c b/drivers/acpi/dptf/int340x_thermal.c
index 33505c6..8636409 100644
--- a/drivers/acpi/dptf/int340x_thermal.c
+++ b/drivers/acpi/dptf/int340x_thermal.c
@@ -34,11 +34,11 @@ static int int340x_thermal_handler_attach(struct acpi_device *adev,
const struct acpi_device_id *id)
{
if (IS_ENABLED(CONFIG_INT340X_THERMAL))
- acpi_create_platform_device(adev);
+ acpi_create_platform_device(adev, NULL);
/* Intel SoC DTS thermal driver needs INT3401 to set IRQ descriptor */
else if (IS_ENABLED(CONFIG_INTEL_SOC_DTS_THERMAL) &&
id->driver_data == INT3401_DEVICE)
- acpi_create_platform_device(adev);
+ acpi_create_platform_device(adev, NULL);
return 1;
}
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 6805310..48e19d0 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -526,6 +526,7 @@ static void acpi_ec_enable_event(struct acpi_ec *ec)
acpi_ec_clear(ec);
}
+#ifdef CONFIG_PM_SLEEP
static bool acpi_ec_query_flushed(struct acpi_ec *ec)
{
bool flushed;
@@ -557,6 +558,7 @@ static void acpi_ec_disable_event(struct acpi_ec *ec)
spin_unlock_irqrestore(&ec->lock, flags);
__acpi_ec_flush_event(ec);
}
+#endif /* CONFIG_PM_SLEEP */
static bool acpi_ec_guard_event(struct acpi_ec *ec)
{
diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c
index 384cfc3..6cf4988 100644
--- a/drivers/acpi/fan.c
+++ b/drivers/acpi/fan.c
@@ -129,8 +129,18 @@ static int fan_get_state_acpi4(struct acpi_device *device, unsigned long *state)
control = obj->package.elements[1].integer.value;
for (i = 0; i < fan->fps_count; i++) {
- if (control == fan->fps[i].control)
+ /*
+ * When Fine Grain Control is set, return the state
+ * corresponding to maximum fan->fps[i].control
+ * value compared to the current speed. Here the
+ * fan->fps[] is sorted array with increasing speed.
+ */
+ if (fan->fif.fine_grain_ctrl && control < fan->fps[i].control) {
+ i = (i > 0) ? i - 1 : 0;
break;
+ } else if (control == fan->fps[i].control) {
+ break;
+ }
}
if (i == fan->fps_count) {
dev_dbg(&device->dev, "Invalid control value returned\n");
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 4305ee9..416953a 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -162,11 +162,18 @@ void acpi_os_vprintf(const char *fmt, va_list args)
if (acpi_in_debugger) {
kdb_printf("%s", buffer);
} else {
- printk(KERN_CONT "%s", buffer);
+ if (printk_get_level(buffer))
+ printk("%s", buffer);
+ else
+ printk(KERN_CONT "%s", buffer);
}
#else
- if (acpi_debugger_write_log(buffer) < 0)
- printk(KERN_CONT "%s", buffer);
+ if (acpi_debugger_write_log(buffer) < 0) {
+ if (printk_get_level(buffer))
+ printk("%s", buffer);
+ else
+ printk(KERN_CONT "%s", buffer);
+ }
#endif
}
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index c983bf7..bc3d914 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -87,6 +87,7 @@ struct acpi_pci_link {
static LIST_HEAD(acpi_link_list);
static DEFINE_MUTEX(acpi_link_lock);
+static int sci_irq = -1, sci_penalty;
/* --------------------------------------------------------------------------
PCI Link Device Management
@@ -496,25 +497,13 @@ static int acpi_irq_get_penalty(int irq)
{
int penalty = 0;
- /*
- * Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict
- * with PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be
- * use for PCI IRQs.
- */
- if (irq == acpi_gbl_FADT.sci_interrupt) {
- u32 type = irq_get_trigger_type(irq) & IRQ_TYPE_SENSE_MASK;
-
- if (type != IRQ_TYPE_LEVEL_LOW)
- penalty += PIRQ_PENALTY_ISA_ALWAYS;
- else
- penalty += PIRQ_PENALTY_PCI_USING;
- }
+ if (irq == sci_irq)
+ penalty += sci_penalty;
if (irq < ACPI_MAX_ISA_IRQS)
return penalty + acpi_isa_irq_penalty[irq];
- penalty += acpi_irq_pci_sharing_penalty(irq);
- return penalty;
+ return penalty + acpi_irq_pci_sharing_penalty(irq);
}
int __init acpi_irq_penalty_init(void)
@@ -619,6 +608,10 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link)
acpi_device_bid(link->device));
return -ENODEV;
} else {
+ if (link->irq.active < ACPI_MAX_ISA_IRQS)
+ acpi_isa_irq_penalty[link->irq.active] +=
+ PIRQ_PENALTY_PCI_USING;
+
printk(KERN_WARNING PREFIX "%s [%s] enabled at IRQ %d\n",
acpi_device_name(link->device),
acpi_device_bid(link->device), link->irq.active);
@@ -849,7 +842,7 @@ static int __init acpi_irq_penalty_update(char *str, int used)
continue;
if (used)
- new_penalty = acpi_irq_get_penalty(irq) +
+ new_penalty = acpi_isa_irq_penalty[irq] +
PIRQ_PENALTY_ISA_USED;
else
new_penalty = 0;
@@ -871,7 +864,7 @@ static int __init acpi_irq_penalty_update(char *str, int used)
void acpi_penalize_isa_irq(int irq, int active)
{
if ((irq >= 0) && (irq < ARRAY_SIZE(acpi_isa_irq_penalty)))
- acpi_isa_irq_penalty[irq] = acpi_irq_get_penalty(irq) +
+ acpi_isa_irq_penalty[irq] +=
(active ? PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING);
}
@@ -881,6 +874,17 @@ bool acpi_isa_irq_available(int irq)
acpi_irq_get_penalty(irq) < PIRQ_PENALTY_ISA_ALWAYS);
}
+void acpi_penalize_sci_irq(int irq, int trigger, int polarity)
+{
+ sci_irq = irq;
+
+ if (trigger == ACPI_MADT_TRIGGER_LEVEL &&
+ polarity == ACPI_MADT_POLARITY_ACTIVE_LOW)
+ sci_penalty = PIRQ_PENALTY_PCI_USING;
+ else
+ sci_penalty = PIRQ_PENALTY_ISA_ALWAYS;
+}
+
/*
* Over-ride default table to reserve additional IRQs for use by ISA
* e.g. acpi_irq_isa=5
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index f2fd3fe..03f5ec1 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -468,10 +468,11 @@ static int acpi_data_get_property_array(struct acpi_device_data *data,
}
/**
- * acpi_data_get_property_reference - returns handle to the referenced object
- * @data: ACPI device data object containing the property
+ * __acpi_node_get_property_reference - returns handle to the referenced object
+ * @fwnode: Firmware node to get the property from
* @propname: Name of the property
* @index: Index of the reference to return
+ * @num_args: Maximum number of arguments after each reference
* @args: Location to store the returned reference with optional arguments
*
* Find property with @name, verifify that it is a package containing at least
@@ -482,17 +483,40 @@ static int acpi_data_get_property_array(struct acpi_device_data *data,
* If there's more than one reference in the property value package, @index is
* used to select the one to return.
*
+ * It is possible to leave holes in the property value set like in the
+ * example below:
+ *
+ * Package () {
+ * "cs-gpios",
+ * Package () {
+ * ^GPIO, 19, 0, 0,
+ * ^GPIO, 20, 0, 0,
+ * 0,
+ * ^GPIO, 21, 0, 0,
+ * }
+ * }
+ *
+ * Calling this function with index %2 return %-ENOENT and with index %3
+ * returns the last entry. If the property does not contain any more values
+ * %-ENODATA is returned. The NULL entry must be single integer and
+ * preferably contain value %0.
+ *
* Return: %0 on success, negative error code on failure.
*/
-static int acpi_data_get_property_reference(struct acpi_device_data *data,
- const char *propname, size_t index,
- struct acpi_reference_args *args)
+int __acpi_node_get_property_reference(struct fwnode_handle *fwnode,
+ const char *propname, size_t index, size_t num_args,
+ struct acpi_reference_args *args)
{
const union acpi_object *element, *end;
const union acpi_object *obj;
+ struct acpi_device_data *data;
struct acpi_device *device;
int ret, idx = 0;
+ data = acpi_device_data_of_node(fwnode);
+ if (!data)
+ return -EINVAL;
+
ret = acpi_data_get_property(data, propname, ACPI_TYPE_ANY, &obj);
if (ret)
return ret;
@@ -532,59 +556,54 @@ static int acpi_data_get_property_reference(struct acpi_device_data *data,
while (element < end) {
u32 nargs, i;
- if (element->type != ACPI_TYPE_LOCAL_REFERENCE)
- return -EPROTO;
+ if (element->type == ACPI_TYPE_LOCAL_REFERENCE) {
+ ret = acpi_bus_get_device(element->reference.handle,
+ &device);
+ if (ret)
+ return -ENODEV;
- ret = acpi_bus_get_device(element->reference.handle, &device);
- if (ret)
- return -ENODEV;
+ nargs = 0;
+ element++;
- element++;
- nargs = 0;
+ /* assume following integer elements are all args */
+ for (i = 0; element + i < end && i < num_args; i++) {
+ int type = element[i].type;
- /* assume following integer elements are all args */
- for (i = 0; element + i < end; i++) {
- int type = element[i].type;
+ if (type == ACPI_TYPE_INTEGER)
+ nargs++;
+ else if (type == ACPI_TYPE_LOCAL_REFERENCE)
+ break;
+ else
+ return -EPROTO;
+ }
- if (type == ACPI_TYPE_INTEGER)
- nargs++;
- else if (type == ACPI_TYPE_LOCAL_REFERENCE)
- break;
- else
+ if (nargs > MAX_ACPI_REFERENCE_ARGS)
return -EPROTO;
+
+ if (idx == index) {
+ args->adev = device;
+ args->nargs = nargs;
+ for (i = 0; i < nargs; i++)
+ args->args[i] = element[i].integer.value;
+
+ return 0;
+ }
+
+ element += nargs;
+ } else if (element->type == ACPI_TYPE_INTEGER) {
+ if (idx == index)
+ return -ENOENT;
+ element++;
+ } else {
+ return -EPROTO;
}
- if (idx++ == index) {
- args->adev = device;
- args->nargs = nargs;
- for (i = 0; i < nargs; i++)
- args->args[i] = element[i].integer.value;
-
- return 0;
- }
-
- element += nargs;
+ idx++;
}
- return -EPROTO;
+ return -ENODATA;
}
-
-/**
- * acpi_node_get_property_reference - get a handle to the referenced object.
- * @fwnode: Firmware node to get the property from.
- * @propname: Name of the property.
- * @index: Index of the reference to return.
- * @args: Location to store the returned reference with optional arguments.
- */
-int acpi_node_get_property_reference(struct fwnode_handle *fwnode,
- const char *name, size_t index,
- struct acpi_reference_args *args)
-{
- struct acpi_device_data *data = acpi_device_data_of_node(fwnode);
-
- return data ? acpi_data_get_property_reference(data, name, index, args) : -EINVAL;
-}
-EXPORT_SYMBOL_GPL(acpi_node_get_property_reference);
+EXPORT_SYMBOL_GPL(__acpi_node_get_property_reference);
static int acpi_data_prop_read_single(struct acpi_device_data *data,
const char *propname,
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 035ac64..3d1856f 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1734,7 +1734,7 @@ static void acpi_default_enumeration(struct acpi_device *device)
&is_spi_i2c_slave);
acpi_dev_free_resource_list(&resource_list);
if (!is_spi_i2c_slave) {
- acpi_create_platform_device(device);
+ acpi_create_platform_device(device, NULL);
acpi_device_set_enumerated(device);
} else {
blocking_notifier_call_chain(&acpi_reconfig_chain,
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 562af94..3c71b98 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -1002,7 +1002,7 @@ static int binder_dec_node(struct binder_node *node, int strong, int internal)
static struct binder_ref *binder_get_ref(struct binder_proc *proc,
- uint32_t desc)
+ u32 desc, bool need_strong_ref)
{
struct rb_node *n = proc->refs_by_desc.rb_node;
struct binder_ref *ref;
@@ -1010,12 +1010,16 @@ static struct binder_ref *binder_get_ref(struct binder_proc *proc,
while (n) {
ref = rb_entry(n, struct binder_ref, rb_node_desc);
- if (desc < ref->desc)
+ if (desc < ref->desc) {
n = n->rb_left;
- else if (desc > ref->desc)
+ } else if (desc > ref->desc) {
n = n->rb_right;
- else
+ } else if (need_strong_ref && !ref->strong) {
+ binder_user_error("tried to use weak ref as strong ref\n");
+ return NULL;
+ } else {
return ref;
+ }
}
return NULL;
}
@@ -1285,7 +1289,10 @@ static void binder_transaction_buffer_release(struct binder_proc *proc,
} break;
case BINDER_TYPE_HANDLE:
case BINDER_TYPE_WEAK_HANDLE: {
- struct binder_ref *ref = binder_get_ref(proc, fp->handle);
+ struct binder_ref *ref;
+
+ ref = binder_get_ref(proc, fp->handle,
+ fp->type == BINDER_TYPE_HANDLE);
if (ref == NULL) {
pr_err("transaction release %d bad handle %d\n",
@@ -1380,7 +1387,7 @@ static void binder_transaction(struct binder_proc *proc,
if (tr->target.handle) {
struct binder_ref *ref;
- ref = binder_get_ref(proc, tr->target.handle);
+ ref = binder_get_ref(proc, tr->target.handle, true);
if (ref == NULL) {
binder_user_error("%d:%d got transaction to invalid handle\n",
proc->pid, thread->pid);
@@ -1577,7 +1584,9 @@ static void binder_transaction(struct binder_proc *proc,
fp->type = BINDER_TYPE_HANDLE;
else
fp->type = BINDER_TYPE_WEAK_HANDLE;
+ fp->binder = 0;
fp->handle = ref->desc;
+ fp->cookie = 0;
binder_inc_ref(ref, fp->type == BINDER_TYPE_HANDLE,
&thread->todo);
@@ -1589,7 +1598,10 @@ static void binder_transaction(struct binder_proc *proc,
} break;
case BINDER_TYPE_HANDLE:
case BINDER_TYPE_WEAK_HANDLE: {
- struct binder_ref *ref = binder_get_ref(proc, fp->handle);
+ struct binder_ref *ref;
+
+ ref = binder_get_ref(proc, fp->handle,
+ fp->type == BINDER_TYPE_HANDLE);
if (ref == NULL) {
binder_user_error("%d:%d got transaction with invalid handle, %d\n",
@@ -1624,7 +1636,9 @@ static void binder_transaction(struct binder_proc *proc,
return_error = BR_FAILED_REPLY;
goto err_binder_get_ref_for_node_failed;
}
+ fp->binder = 0;
fp->handle = new_ref->desc;
+ fp->cookie = 0;
binder_inc_ref(new_ref, fp->type == BINDER_TYPE_HANDLE, NULL);
trace_binder_transaction_ref_to_ref(t, ref,
new_ref);
@@ -1678,6 +1692,7 @@ static void binder_transaction(struct binder_proc *proc,
binder_debug(BINDER_DEBUG_TRANSACTION,
" fd %d -> %d\n", fp->handle, target_fd);
/* TODO: fput? */
+ fp->binder = 0;
fp->handle = target_fd;
} break;
@@ -1800,7 +1815,9 @@ static int binder_thread_write(struct binder_proc *proc,
ref->desc);
}
} else
- ref = binder_get_ref(proc, target);
+ ref = binder_get_ref(proc, target,
+ cmd == BC_ACQUIRE ||
+ cmd == BC_RELEASE);
if (ref == NULL) {
binder_user_error("%d:%d refcount change on invalid ref %d\n",
proc->pid, thread->pid, target);
@@ -1996,7 +2013,7 @@ static int binder_thread_write(struct binder_proc *proc,
if (get_user(cookie, (binder_uintptr_t __user *)ptr))
return -EFAULT;
ptr += sizeof(binder_uintptr_t);
- ref = binder_get_ref(proc, target);
+ ref = binder_get_ref(proc, target, false);
if (ref == NULL) {
binder_user_error("%d:%d %s invalid ref %d\n",
proc->pid, thread->pid,
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 90eabaf..9669fc7 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1400,142 +1400,59 @@ static irqreturn_t ahci_thunderx_irq_handler(int irq, void *dev_instance)
}
#endif
-/*
- * ahci_init_msix() - optionally enable per-port MSI-X otherwise defer
- * to single msi.
- */
-static int ahci_init_msix(struct pci_dev *pdev, unsigned int n_ports,
- struct ahci_host_priv *hpriv, unsigned long flags)
+static int ahci_get_irq_vector(struct ata_host *host, int port)
{
- int nvec, i, rc;
-
- /* Do not init MSI-X if MSI is disabled for the device */
- if (hpriv->flags & AHCI_HFLAG_NO_MSI)
- return -ENODEV;
-
- nvec = pci_msix_vec_count(pdev);
- if (nvec < 0)
- return nvec;
-
- /*
- * Proper MSI-X implementations will have a vector per-port.
- * Barring that, we prefer single-MSI over single-MSIX. If this
- * check fails (not enough MSI-X vectors for all ports) we will
- * be called again with the flag clear iff ahci_init_msi()
- * fails.
- */
- if (flags & AHCI_HFLAG_MULTI_MSIX) {
- if (nvec < n_ports)
- return -ENODEV;
- nvec = n_ports;
- } else if (nvec) {
- nvec = 1;
- } else {
- /*
- * Emit dev_err() since this was the non-legacy irq
- * method of last resort.
- */
- rc = -ENODEV;
- goto fail;
- }
-
- for (i = 0; i < nvec; i++)
- hpriv->msix[i].entry = i;
- rc = pci_enable_msix_exact(pdev, hpriv->msix, nvec);
- if (rc < 0)
- goto fail;
-
- if (nvec > 1)
- hpriv->flags |= AHCI_HFLAG_MULTI_MSIX;
- hpriv->irq = hpriv->msix[0].vector; /* for single msi-x */
-
- return nvec;
-fail:
- dev_err(&pdev->dev,
- "failed to enable MSI-X with error %d, # of vectors: %d\n",
- rc, nvec);
-
- return rc;
+ return pci_irq_vector(to_pci_dev(host->dev), port);
}
static int ahci_init_msi(struct pci_dev *pdev, unsigned int n_ports,
struct ahci_host_priv *hpriv)
{
- int rc, nvec;
+ int nvec;
if (hpriv->flags & AHCI_HFLAG_NO_MSI)
return -ENODEV;
- nvec = pci_msi_vec_count(pdev);
- if (nvec < 0)
- return nvec;
-
/*
* If number of MSIs is less than number of ports then Sharing Last
* Message mode could be enforced. In this case assume that advantage
* of multipe MSIs is negated and use single MSI mode instead.
*/
- if (nvec < n_ports)
- goto single_msi;
+ if (n_ports > 1) {
+ nvec = pci_alloc_irq_vectors(pdev, n_ports, INT_MAX,
+ PCI_IRQ_MSIX | PCI_IRQ_MSI);
+ if (nvec > 0) {
+ if (!(readl(hpriv->mmio + HOST_CTL) & HOST_MRSM)) {
+ hpriv->get_irq_vector = ahci_get_irq_vector;
+ hpriv->flags |= AHCI_HFLAG_MULTI_MSI;
+ return nvec;
+ }
- rc = pci_enable_msi_exact(pdev, nvec);
- if (rc == -ENOSPC)
- goto single_msi;
- if (rc < 0)
- return rc;
+ /*
+ * Fallback to single MSI mode if the controller
+ * enforced MRSM mode.
+ */
+ printk(KERN_INFO
+ "ahci: MRSM is on, fallback to single MSI\n");
+ pci_free_irq_vectors(pdev);
+ }
- /* fallback to single MSI mode if the controller enforced MRSM mode */
- if (readl(hpriv->mmio + HOST_CTL) & HOST_MRSM) {
- pci_disable_msi(pdev);
- printk(KERN_INFO "ahci: MRSM is on, fallback to single MSI\n");
- goto single_msi;
+ /*
+ * -ENOSPC indicated we don't have enough vectors. Don't bother
+ * trying a single vectors for any other error:
+ */
+ if (nvec < 0 && nvec != -ENOSPC)
+ return nvec;
}
- if (nvec > 1)
- hpriv->flags |= AHCI_HFLAG_MULTI_MSI;
-
- goto out;
-
-single_msi:
- nvec = 1;
-
- rc = pci_enable_msi(pdev);
- if (rc < 0)
- return rc;
-out:
- hpriv->irq = pdev->irq;
-
- return nvec;
-}
-
-static int ahci_init_interrupts(struct pci_dev *pdev, unsigned int n_ports,
- struct ahci_host_priv *hpriv)
-{
- int nvec;
-
/*
- * Try to enable per-port MSI-X. If the host is not capable
- * fall back to single MSI before finally attempting single
- * MSI-X.
+ * If the host is not capable of supporting per-port vectors, fall
+ * back to single MSI before finally attempting single MSI-X.
*/
- nvec = ahci_init_msix(pdev, n_ports, hpriv, AHCI_HFLAG_MULTI_MSIX);
- if (nvec >= 0)
+ nvec = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
+ if (nvec == 1)
return nvec;
-
- nvec = ahci_init_msi(pdev, n_ports, hpriv);
- if (nvec >= 0)
- return nvec;
-
- /* try single-msix */
- nvec = ahci_init_msix(pdev, n_ports, hpriv, 0);
- if (nvec >= 0)
- return nvec;
-
- /* legacy intx interrupts */
- pci_intx(pdev, 1);
- hpriv->irq = pdev->irq;
-
- return 0;
+ return pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSIX);
}
static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
@@ -1698,11 +1615,12 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
if (!host)
return -ENOMEM;
host->private_data = hpriv;
- hpriv->msix = devm_kzalloc(&pdev->dev,
- sizeof(struct msix_entry) * n_ports, GFP_KERNEL);
- if (!hpriv->msix)
- return -ENOMEM;
- ahci_init_interrupts(pdev, n_ports, hpriv);
+
+ if (ahci_init_msi(pdev, n_ports, hpriv) < 0) {
+ /* legacy intx interrupts */
+ pci_intx(pdev, 1);
+ }
+ hpriv->irq = pci_irq_vector(pdev, 0);
if (!(hpriv->cap & HOST_CAP_SSS) || ahci_ignore_sss)
host->flags |= ATA_HOST_PARALLEL_SCAN;
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 70b06bc..0cc08f8 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -242,12 +242,10 @@ enum {
AHCI_HFLAG_NO_FBS = (1 << 18), /* no FBS */
#ifdef CONFIG_PCI_MSI
- AHCI_HFLAG_MULTI_MSI = (1 << 20), /* multiple PCI MSIs */
- AHCI_HFLAG_MULTI_MSIX = (1 << 21), /* per-port MSI-X */
+ AHCI_HFLAG_MULTI_MSI = (1 << 20), /* per-port MSI(-X) */
#else
/* compile out MSI infrastructure */
AHCI_HFLAG_MULTI_MSI = 0,
- AHCI_HFLAG_MULTI_MSIX = 0,
#endif
AHCI_HFLAG_WAKE_BEFORE_STOP = (1 << 22), /* wake before DMA stop */
@@ -351,7 +349,6 @@ struct ahci_host_priv {
* the PHY position in this array.
*/
struct phy **phys;
- struct msix_entry *msix; /* Optional MSI-X support */
unsigned nports; /* Number of ports */
void *plat_data; /* Other platform data */
unsigned int irq; /* interrupt line */
@@ -362,22 +359,11 @@ struct ahci_host_priv {
*/
void (*start_engine)(struct ata_port *ap);
irqreturn_t (*irq_handler)(int irq, void *dev_instance);
-};
-#ifdef CONFIG_PCI_MSI
-static inline int ahci_irq_vector(struct ahci_host_priv *hpriv, int port)
-{
- if (hpriv->flags & AHCI_HFLAG_MULTI_MSIX)
- return hpriv->msix[port].vector;
- else
- return hpriv->irq + port;
-}
-#else
-static inline int ahci_irq_vector(struct ahci_host_priv *hpriv, int port)
-{
- return hpriv->irq;
-}
-#endif
+ /* only required for per-port MSI(-X) support */
+ int (*get_irq_vector)(struct ata_host *host,
+ int port);
+};
extern int ahci_ignore_sss;
diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c
index 7bdee9b..1eba8df 100644
--- a/drivers/ata/ahci_qoriq.c
+++ b/drivers/ata/ahci_qoriq.c
@@ -30,24 +30,23 @@
#define PORT_PHY3 0xB0
#define PORT_PHY4 0xB4
#define PORT_PHY5 0xB8
+#define PORT_AXICC 0xBC
#define PORT_TRANS 0xC8
/* port register default value */
#define AHCI_PORT_PHY_1_CFG 0xa003fffe
#define AHCI_PORT_TRANS_CFG 0x08000029
+#define AHCI_PORT_AXICC_CFG 0x3fffffff
/* for ls1021a */
#define LS1021A_PORT_PHY2 0x28183414
#define LS1021A_PORT_PHY3 0x0e080e06
#define LS1021A_PORT_PHY4 0x064a080b
#define LS1021A_PORT_PHY5 0x2aa86470
+#define LS1021A_AXICC_ADDR 0xC0
#define SATA_ECC_DISABLE 0x00020000
-/* for ls1043a */
-#define LS1043A_PORT_PHY2 0x28184d1f
-#define LS1043A_PORT_PHY3 0x0e081509
-
enum ahci_qoriq_type {
AHCI_LS1021A,
AHCI_LS1043A,
@@ -137,7 +136,7 @@ static struct ata_port_operations ahci_qoriq_ops = {
.hardreset = ahci_qoriq_hardreset,
};
-static struct ata_port_info ahci_qoriq_port_info = {
+static const struct ata_port_info ahci_qoriq_port_info = {
.flags = AHCI_FLAG_COMMON | ATA_FLAG_NCQ,
.pio_mask = ATA_PIO4,
.udma_mask = ATA_UDMA6,
@@ -162,18 +161,19 @@ static int ahci_qoriq_phy_init(struct ahci_host_priv *hpriv)
writel(LS1021A_PORT_PHY4, reg_base + PORT_PHY4);
writel(LS1021A_PORT_PHY5, reg_base + PORT_PHY5);
writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
+ writel(AHCI_PORT_AXICC_CFG, reg_base + LS1021A_AXICC_ADDR);
break;
case AHCI_LS1043A:
writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
- writel(LS1043A_PORT_PHY2, reg_base + PORT_PHY2);
- writel(LS1043A_PORT_PHY3, reg_base + PORT_PHY3);
writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
+ writel(AHCI_PORT_AXICC_CFG, reg_base + PORT_AXICC);
break;
case AHCI_LS2080A:
writel(AHCI_PORT_PHY_1_CFG, reg_base + PORT_PHY1);
writel(AHCI_PORT_TRANS_CFG, reg_base + PORT_TRANS);
+ writel(AHCI_PORT_AXICC_CFG, reg_base + PORT_AXICC);
break;
}
@@ -221,12 +221,6 @@ static int ahci_qoriq_probe(struct platform_device *pdev)
if (rc)
goto disable_resources;
- /* Workaround for ls2080a */
- if (qoriq_priv->type == AHCI_LS2080A) {
- hpriv->flags |= AHCI_HFLAG_NO_NCQ;
- ahci_qoriq_port_info.flags &= ~ATA_FLAG_NCQ;
- }
-
rc = ahci_platform_init_host(pdev, hpriv, &ahci_qoriq_port_info,
&ahci_qoriq_sht);
if (rc)
diff --git a/drivers/ata/ahci_st.c b/drivers/ata/ahci_st.c
index 8ff428f..bc345f2 100644
--- a/drivers/ata/ahci_st.c
+++ b/drivers/ata/ahci_st.c
@@ -147,6 +147,7 @@ static struct scsi_host_template ahci_platform_sht = {
static int st_ahci_probe(struct platform_device *pdev)
{
+ struct device *dev = &pdev->dev;
struct st_ahci_drv_data *drv_data;
struct ahci_host_priv *hpriv;
int err;
@@ -170,6 +171,9 @@ static int st_ahci_probe(struct platform_device *pdev)
st_ahci_configure_oob(hpriv->mmio);
+ of_property_read_u32(dev->of_node,
+ "ports-implemented", &hpriv->force_port_map);
+
err = ahci_platform_init_host(pdev, hpriv, &st_ahci_port_info,
&ahci_platform_sht);
if (err) {
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index dcf2c72..0d028ea 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -2520,7 +2520,7 @@ static int ahci_host_activate_multi_irqs(struct ata_host *host,
*/
for (i = 0; i < host->n_ports; i++) {
struct ahci_port_priv *pp = host->ports[i]->private_data;
- int irq = ahci_irq_vector(hpriv, i);
+ int irq = hpriv->get_irq_vector(host, i);
/* Do not receive interrupts sent by dummy ports */
if (!pp) {
@@ -2556,10 +2556,15 @@ int ahci_host_activate(struct ata_host *host, struct scsi_host_template *sht)
int irq = hpriv->irq;
int rc;
- if (hpriv->flags & (AHCI_HFLAG_MULTI_MSI | AHCI_HFLAG_MULTI_MSIX)) {
+ if (hpriv->flags & AHCI_HFLAG_MULTI_MSI) {
if (hpriv->irq_handler)
dev_warn(host->dev,
"both AHCI_HFLAG_MULTI_MSI flag set and custom irq handler implemented\n");
+ if (!hpriv->get_irq_vector) {
+ dev_err(host->dev,
+ "AHCI_HFLAG_MULTI_MSI requires ->get_irq_vector!\n");
+ return -EIO;
+ }
rc = ahci_host_activate_multi_irqs(host, sht);
} else {
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index e207b33..9cceb4a 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1159,8 +1159,6 @@ static void ata_scsi_sdev_config(struct scsi_device *sdev)
{
sdev->use_10_for_rw = 1;
sdev->use_10_for_ms = 1;
- sdev->no_report_opcodes = 1;
- sdev->no_write_same = 1;
/* Schedule policy is determined by ->qc_defer() callback and
* it needs to see every deferred qc. Set dev_blocked to 1 to
@@ -3282,18 +3280,125 @@ static unsigned int ata_scsi_pass_thru(struct ata_queued_cmd *qc)
return 1;
}
+/**
+ * ata_format_dsm_trim_descr() - SATL Write Same to DSM Trim
+ * @cmd: SCSI command being translated
+ * @trmax: Maximum number of entries that will fit in sector_size bytes.
+ * @sector: Starting sector
+ * @count: Total Range of request in logical sectors
+ *
+ * Rewrite the WRITE SAME descriptor to be a DSM TRIM little-endian formatted
+ * descriptor.
+ *
+ * Upto 64 entries of the format:
+ * 63:48 Range Length
+ * 47:0 LBA
+ *
+ * Range Length of 0 is ignored.
+ * LBA's should be sorted order and not overlap.
+ *
+ * NOTE: this is the same format as ADD LBA(S) TO NV CACHE PINNED SET
+ *
+ * Return: Number of bytes copied into sglist.
+ */
+static size_t ata_format_dsm_trim_descr(struct scsi_cmnd *cmd, u32 trmax,
+ u64 sector, u32 count)
+{
+ struct scsi_device *sdp = cmd->device;
+ size_t len = sdp->sector_size;
+ size_t r;
+ __le64 *buf;
+ u32 i = 0;
+ unsigned long flags;
+
+ WARN_ON(len > ATA_SCSI_RBUF_SIZE);
+
+ if (len > ATA_SCSI_RBUF_SIZE)
+ len = ATA_SCSI_RBUF_SIZE;
+
+ spin_lock_irqsave(&ata_scsi_rbuf_lock, flags);
+ buf = ((void *)ata_scsi_rbuf);
+ memset(buf, 0, len);
+ while (i < trmax) {
+ u64 entry = sector |
+ ((u64)(count > 0xffff ? 0xffff : count) << 48);
+ buf[i++] = __cpu_to_le64(entry);
+ if (count <= 0xffff)
+ break;
+ count -= 0xffff;
+ sector += 0xffff;
+ }
+ r = sg_copy_from_buffer(scsi_sglist(cmd), scsi_sg_count(cmd), buf, len);
+ spin_unlock_irqrestore(&ata_scsi_rbuf_lock, flags);
+
+ return r;
+}
+
+/**
+ * ata_format_dsm_trim_descr() - SATL Write Same to ATA SCT Write Same
+ * @cmd: SCSI command being translated
+ * @lba: Starting sector
+ * @num: Number of sectors to be zero'd.
+ *
+ * Rewrite the WRITE SAME payload to be an SCT Write Same formatted
+ * descriptor.
+ * NOTE: Writes a pattern (0's) in the foreground.
+ *
+ * Return: Number of bytes copied into sglist.
+ */
+static size_t ata_format_sct_write_same(struct scsi_cmnd *cmd, u64 lba, u64 num)
+{
+ struct scsi_device *sdp = cmd->device;
+ size_t len = sdp->sector_size;
+ size_t r;
+ u16 *buf;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ata_scsi_rbuf_lock, flags);
+ buf = ((void *)ata_scsi_rbuf);
+
+ put_unaligned_le16(0x0002, &buf[0]); /* SCT_ACT_WRITE_SAME */
+ put_unaligned_le16(0x0101, &buf[1]); /* WRITE PTRN FG */
+ put_unaligned_le64(lba, &buf[2]);
+ put_unaligned_le64(num, &buf[6]);
+ put_unaligned_le32(0u, &buf[10]); /* pattern */
+
+ WARN_ON(len > ATA_SCSI_RBUF_SIZE);
+
+ if (len > ATA_SCSI_RBUF_SIZE)
+ len = ATA_SCSI_RBUF_SIZE;
+
+ r = sg_copy_from_buffer(scsi_sglist(cmd), scsi_sg_count(cmd), buf, len);
+ spin_unlock_irqrestore(&ata_scsi_rbuf_lock, flags);
+
+ return r;
+}
+
+/**
+ * ata_scsi_write_same_xlat() - SATL Write Same to ATA SCT Write Same
+ * @qc: Command to be translated
+ *
+ * Translate a SCSI WRITE SAME command to be either a DSM TRIM command or
+ * an SCT Write Same command.
+ * Based on WRITE SAME has the UNMAP flag
+ * When set translate to DSM TRIM
+ * When clear translate to SCT Write Same
+ */
static unsigned int ata_scsi_write_same_xlat(struct ata_queued_cmd *qc)
{
struct ata_taskfile *tf = &qc->tf;
struct scsi_cmnd *scmd = qc->scsicmd;
+ struct scsi_device *sdp = scmd->device;
+ size_t len = sdp->sector_size;
struct ata_device *dev = qc->dev;
const u8 *cdb = scmd->cmnd;
u64 block;
u32 n_block;
+ const u32 trmax = len >> 3;
u32 size;
- void *buf;
u16 fp;
u8 bp = 0xff;
+ u8 unmap = cdb[1] & 0x8;
/* we may not issue DMA commands if no DMA mode is set */
if (unlikely(!dev->dma_mode))
@@ -3305,11 +3410,26 @@ static unsigned int ata_scsi_write_same_xlat(struct ata_queued_cmd *qc)
}
scsi_16_lba_len(cdb, &block, &n_block);
- /* for now we only support WRITE SAME with the unmap bit set */
- if (unlikely(!(cdb[1] & 0x8))) {
- fp = 1;
- bp = 3;
- goto invalid_fld;
+ if (unmap) {
+ /* If trim is not enabled the cmd is invalid. */
+ if ((dev->horkage & ATA_HORKAGE_NOTRIM) ||
+ !ata_id_has_trim(dev->id)) {
+ fp = 1;
+ bp = 3;
+ goto invalid_fld;
+ }
+ /* If the request is too large the cmd is invalid */
+ if (n_block > 0xffff * trmax) {
+ fp = 2;
+ goto invalid_fld;
+ }
+ } else {
+ /* If write same is not available the cmd is invalid */
+ if (!ata_id_sct_write_same(dev->id)) {
+ fp = 1;
+ bp = 3;
+ goto invalid_fld;
+ }
}
/*
@@ -3319,32 +3439,54 @@ static unsigned int ata_scsi_write_same_xlat(struct ata_queued_cmd *qc)
if (!scsi_sg_count(scmd))
goto invalid_param_len;
- buf = page_address(sg_page(scsi_sglist(scmd)));
+ /*
+ * size must match sector size in bytes
+ * For DATA SET MANAGEMENT TRIM in ACS-2 nsect (aka count)
+ * is defined as number of 512 byte blocks to be transferred.
+ */
+ if (unmap) {
+ size = ata_format_dsm_trim_descr(scmd, trmax, block, n_block);
+ if (size != len)
+ goto invalid_param_len;
- if (n_block <= 65535 * ATA_MAX_TRIM_RNUM) {
- size = ata_set_lba_range_entries(buf, ATA_MAX_TRIM_RNUM, block, n_block);
+ if (ata_ncq_enabled(dev) && ata_fpdma_dsm_supported(dev)) {
+ /* Newer devices support queued TRIM commands */
+ tf->protocol = ATA_PROT_NCQ;
+ tf->command = ATA_CMD_FPDMA_SEND;
+ tf->hob_nsect = ATA_SUBCMD_FPDMA_SEND_DSM & 0x1f;
+ tf->nsect = qc->tag << 3;
+ tf->hob_feature = (size / 512) >> 8;
+ tf->feature = size / 512;
+
+ tf->auxiliary = 1;
+ } else {
+ tf->protocol = ATA_PROT_DMA;
+ tf->hob_feature = 0;
+ tf->feature = ATA_DSM_TRIM;
+ tf->hob_nsect = (size / 512) >> 8;
+ tf->nsect = size / 512;
+ tf->command = ATA_CMD_DSM;
+ }
} else {
- fp = 2;
- goto invalid_fld;
- }
+ size = ata_format_sct_write_same(scmd, block, n_block);
+ if (size != len)
+ goto invalid_param_len;
- if (ata_ncq_enabled(dev) && ata_fpdma_dsm_supported(dev)) {
- /* Newer devices support queued TRIM commands */
- tf->protocol = ATA_PROT_NCQ;
- tf->command = ATA_CMD_FPDMA_SEND;
- tf->hob_nsect = ATA_SUBCMD_FPDMA_SEND_DSM & 0x1f;
- tf->nsect = qc->tag << 3;
- tf->hob_feature = (size / 512) >> 8;
- tf->feature = size / 512;
-
- tf->auxiliary = 1;
- } else {
- tf->protocol = ATA_PROT_DMA;
tf->hob_feature = 0;
- tf->feature = ATA_DSM_TRIM;
- tf->hob_nsect = (size / 512) >> 8;
- tf->nsect = size / 512;
- tf->command = ATA_CMD_DSM;
+ tf->feature = 0;
+ tf->hob_nsect = 0;
+ tf->nsect = 1;
+ tf->lbah = 0;
+ tf->lbam = 0;
+ tf->lbal = ATA_CMD_STANDBYNOW1;
+ tf->hob_lbah = 0;
+ tf->hob_lbam = 0;
+ tf->hob_lbal = 0;
+ tf->device = ATA_CMD_STANDBYNOW1;
+ tf->protocol = ATA_PROT_DMA;
+ tf->command = ATA_CMD_WRITE_LOG_DMA_EXT;
+ if (unlikely(dev->flags & ATA_DFLAG_PIO))
+ tf->command = ATA_CMD_WRITE_LOG_EXT;
}
tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE | ATA_TFLAG_LBA48 |
@@ -3368,6 +3510,76 @@ static unsigned int ata_scsi_write_same_xlat(struct ata_queued_cmd *qc)
}
/**
+ * ata_scsiop_maint_in - Simulate a subset of MAINTENANCE_IN
+ * @args: device MAINTENANCE_IN data / SCSI command of interest.
+ * @rbuf: Response buffer, to which simulated SCSI cmd output is sent.
+ *
+ * Yields a subset to satisfy scsi_report_opcode()
+ *
+ * LOCKING:
+ * spin_lock_irqsave(host lock)
+ */
+static unsigned int ata_scsiop_maint_in(struct ata_scsi_args *args, u8 *rbuf)
+{
+ struct ata_device *dev = args->dev;
+ u8 *cdb = args->cmd->cmnd;
+ u8 supported = 0;
+ unsigned int err = 0;
+
+ if (cdb[2] != 1) {
+ ata_dev_warn(dev, "invalid command format %d\n", cdb[2]);
+ err = 2;
+ goto out;
+ }
+ switch (cdb[3]) {
+ case INQUIRY:
+ case MODE_SENSE:
+ case MODE_SENSE_10:
+ case READ_CAPACITY:
+ case SERVICE_ACTION_IN_16:
+ case REPORT_LUNS:
+ case REQUEST_SENSE:
+ case SYNCHRONIZE_CACHE:
+ case REZERO_UNIT:
+ case SEEK_6:
+ case SEEK_10:
+ case TEST_UNIT_READY:
+ case SEND_DIAGNOSTIC:
+ case MAINTENANCE_IN:
+ case READ_6:
+ case READ_10:
+ case READ_16:
+ case WRITE_6:
+ case WRITE_10:
+ case WRITE_16:
+ case ATA_12:
+ case ATA_16:
+ case VERIFY:
+ case VERIFY_16:
+ case MODE_SELECT:
+ case MODE_SELECT_10:
+ case START_STOP:
+ supported = 3;
+ break;
+ case WRITE_SAME_16:
+ if (!ata_id_sct_write_same(dev->id))
+ break;
+ /* fallthrough: if SCT ... only enable for ZBC */
+ case ZBC_IN:
+ case ZBC_OUT:
+ if (ata_id_zoned_cap(dev->id) ||
+ dev->class == ATA_DEV_ZAC)
+ supported = 3;
+ break;
+ default:
+ break;
+ }
+out:
+ rbuf[1] = supported; /* supported */
+ return err;
+}
+
+/**
* ata_scsi_report_zones_complete - convert ATA output
* @qc: command structure returning the data
*
@@ -3610,7 +3822,7 @@ static int ata_mselect_caching(struct ata_queued_cmd *qc,
{
struct ata_taskfile *tf = &qc->tf;
struct ata_device *dev = qc->dev;
- char mpage[CACHE_MPAGE_LEN];
+ u8 mpage[CACHE_MPAGE_LEN];
u8 wce;
int i;
@@ -3666,7 +3878,7 @@ static int ata_mselect_control(struct ata_queued_cmd *qc,
const u8 *buf, int len, u16 *fp)
{
struct ata_device *dev = qc->dev;
- char mpage[CONTROL_MPAGE_LEN];
+ u8 mpage[CONTROL_MPAGE_LEN];
u8 d_sense;
int i;
@@ -3701,8 +3913,6 @@ static int ata_mselect_control(struct ata_queued_cmd *qc,
dev->flags |= ATA_DFLAG_D_SENSE;
else
dev->flags &= ~ATA_DFLAG_D_SENSE;
- qc->scsicmd->result = SAM_STAT_GOOD;
- qc->scsicmd->scsi_done(qc->scsicmd);
return 0;
}
@@ -3829,6 +4039,8 @@ static unsigned int ata_scsi_mode_select_xlat(struct ata_queued_cmd *qc)
if (ata_mselect_control(qc, p, pg_len, &fp) < 0) {
fp += hdr_len + bd_len;
goto invalid_param;
+ } else {
+ goto skip; /* No ATA command to send */
}
break;
default: /* invalid page code */
@@ -4147,6 +4359,13 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd)
ata_scsi_invalid_field(dev, cmd, 1);
break;
+ case MAINTENANCE_IN:
+ if (scsicmd[1] == MI_REPORT_SUPPORTED_OPERATION_CODES)
+ ata_scsi_rbuf_fill(&args, ata_scsiop_maint_in);
+ else
+ ata_scsi_invalid_field(dev, cmd, 1);
+ break;
+
/* all other commands */
default:
ata_scsi_set_sense(dev, cmd, ILLEGAL_REQUEST, 0x20, 0x0);
@@ -4179,7 +4398,6 @@ int ata_scsi_add_hosts(struct ata_host *host, struct scsi_host_template *sht)
shost->max_lun = 1;
shost->max_channel = 1;
shost->max_cmd_len = 16;
- shost->no_write_same = 1;
/* Schedule policy is determined by ->qc_defer()
* callback and it needs to see every deferred qc.
diff --git a/drivers/ata/pata_at91.c b/drivers/ata/pata_at91.c
index 9f27b14..1611e0e 100644
--- a/drivers/ata/pata_at91.c
+++ b/drivers/ata/pata_at91.c
@@ -347,10 +347,8 @@ static int at91sam9_smc_fields_init(struct device *dev)
field.reg = AT91SAM9_SMC_MODE(AT91SAM9_SMC_GENERIC);
fields.mode = devm_regmap_field_alloc(dev, smc, field);
- if (IS_ERR(fields.mode))
- return PTR_ERR(fields.mode);
- return 0;
+ return PTR_ERR_OR_ZERO(fields.mode);
}
static int pata_at91_probe(struct platform_device *pdev)
diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c
index 2724595..475a006 100644
--- a/drivers/ata/pata_octeon_cf.c
+++ b/drivers/ata/pata_octeon_cf.c
@@ -152,8 +152,7 @@ static void octeon_cf_set_piomode(struct ata_port *ap, struct ata_device *dev)
div = 8;
T = (int)((1000000000000LL * div) / octeon_get_io_clock_rate());
- if (ata_timing_compute(dev, dev->pio_mode, &timing, T, T))
- BUG();
+ BUG_ON(ata_timing_compute(dev, dev->pio_mode, &timing, T, T));
t1 = timing.setup;
if (t1)
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 745489a..efc48bf 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -1727,15 +1727,13 @@ static int mv_port_start(struct ata_port *ap)
return -ENOMEM;
ap->private_data = pp;
- pp->crqb = dma_pool_alloc(hpriv->crqb_pool, GFP_KERNEL, &pp->crqb_dma);
+ pp->crqb = dma_pool_zalloc(hpriv->crqb_pool, GFP_KERNEL, &pp->crqb_dma);
if (!pp->crqb)
return -ENOMEM;
- memset(pp->crqb, 0, MV_CRQB_Q_SZ);
- pp->crpb = dma_pool_alloc(hpriv->crpb_pool, GFP_KERNEL, &pp->crpb_dma);
+ pp->crpb = dma_pool_zalloc(hpriv->crpb_pool, GFP_KERNEL, &pp->crpb_dma);
if (!pp->crpb)
goto out_port_free_dma_mem;
- memset(pp->crpb, 0, MV_CRPB_Q_SZ);
/* 6041/6081 Rev. "C0" (and newer) are okay with async notify */
if (hpriv->hp_flags & MV_HP_ERRATA_60X1C0)
diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c
index 6ac2b2b..5ad037c 100644
--- a/drivers/atm/solos-pci.c
+++ b/drivers/atm/solos-pci.c
@@ -584,7 +584,7 @@ static ssize_t hardware_show(struct device *dev, struct device_attribute *attr,
return sprintf(buf, "%d\n", data32);
}
-static DEVICE_ATTR(console, 0644, console_show, console_store);
+static DEVICE_ATTR_RW(console);
#define SOLOS_ATTR_RO(x) static DEVICE_ATTR(x, 0444, solos_param_show, NULL);
diff --git a/drivers/auxdisplay/Kconfig b/drivers/auxdisplay/Kconfig
index c07e725..10e1b9e 100644
--- a/drivers/auxdisplay/Kconfig
+++ b/drivers/auxdisplay/Kconfig
@@ -119,4 +119,13 @@
If you compile this as a module, you can still override this
value using the module parameters.
+config IMG_ASCII_LCD
+ tristate "Imagination Technologies ASCII LCD Display"
+ default y if MIPS_MALTA || MIPS_SEAD3
+ select SYSCON
+ help
+ Enable this to support the simple ASCII LCD displays found on
+ development boards such as the MIPS Boston, MIPS Malta & MIPS SEAD3
+ from Imagination Technologies.
+
endif # AUXDISPLAY
diff --git a/drivers/auxdisplay/Makefile b/drivers/auxdisplay/Makefile
index 8a8936a..3127175 100644
--- a/drivers/auxdisplay/Makefile
+++ b/drivers/auxdisplay/Makefile
@@ -4,3 +4,4 @@
obj-$(CONFIG_KS0108) += ks0108.o
obj-$(CONFIG_CFAG12864B) += cfag12864b.o cfag12864bfb.o
+obj-$(CONFIG_IMG_ASCII_LCD) += img-ascii-lcd.o
diff --git a/drivers/auxdisplay/img-ascii-lcd.c b/drivers/auxdisplay/img-ascii-lcd.c
new file mode 100644
index 0000000..bf43b5d
--- /dev/null
+++ b/drivers/auxdisplay/img-ascii-lcd.c
@@ -0,0 +1,443 @@
+/*
+ * Copyright (C) 2016 Imagination Technologies
+ * Author: Paul Burton <paul.burton@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <generated/utsrelease.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+
+struct img_ascii_lcd_ctx;
+
+/**
+ * struct img_ascii_lcd_config - Configuration information about an LCD model
+ * @num_chars: the number of characters the LCD can display
+ * @external_regmap: true if registers are in a system controller, else false
+ * @update: function called to update the LCD
+ */
+struct img_ascii_lcd_config {
+ unsigned int num_chars;
+ bool external_regmap;
+ void (*update)(struct img_ascii_lcd_ctx *ctx);
+};
+
+/**
+ * struct img_ascii_lcd_ctx - Private data structure
+ * @pdev: the ASCII LCD platform device
+ * @base: the base address of the LCD registers
+ * @regmap: the regmap through which LCD registers are accessed
+ * @offset: the offset within regmap to the start of the LCD registers
+ * @cfg: pointer to the LCD model configuration
+ * @message: the full message to display or scroll on the LCD
+ * @message_len: the length of the @message string
+ * @scroll_pos: index of the first character of @message currently displayed
+ * @scroll_rate: scroll interval in jiffies
+ * @timer: timer used to implement scrolling
+ * @curr: the string currently displayed on the LCD
+ */
+struct img_ascii_lcd_ctx {
+ struct platform_device *pdev;
+ union {
+ void __iomem *base;
+ struct regmap *regmap;
+ };
+ u32 offset;
+ const struct img_ascii_lcd_config *cfg;
+ char *message;
+ unsigned int message_len;
+ unsigned int scroll_pos;
+ unsigned int scroll_rate;
+ struct timer_list timer;
+ char curr[] __aligned(8);
+};
+
+/*
+ * MIPS Boston development board
+ */
+
+static void boston_update(struct img_ascii_lcd_ctx *ctx)
+{
+ ulong val;
+
+#if BITS_PER_LONG == 64
+ val = *((u64 *)&ctx->curr[0]);
+ __raw_writeq(val, ctx->base);
+#elif BITS_PER_LONG == 32
+ val = *((u32 *)&ctx->curr[0]);
+ __raw_writel(val, ctx->base);
+ val = *((u32 *)&ctx->curr[4]);
+ __raw_writel(val, ctx->base + 4);
+#else
+# error Not 32 or 64 bit
+#endif
+}
+
+static struct img_ascii_lcd_config boston_config = {
+ .num_chars = 8,
+ .update = boston_update,
+};
+
+/*
+ * MIPS Malta development board
+ */
+
+static void malta_update(struct img_ascii_lcd_ctx *ctx)
+{
+ unsigned int i;
+ int err;
+
+ for (i = 0; i < ctx->cfg->num_chars; i++) {
+ err = regmap_write(ctx->regmap,
+ ctx->offset + (i * 8), ctx->curr[i]);
+ if (err)
+ break;
+ }
+
+ if (unlikely(err))
+ pr_err_ratelimited("Failed to update LCD display: %d\n", err);
+}
+
+static struct img_ascii_lcd_config malta_config = {
+ .num_chars = 8,
+ .external_regmap = true,
+ .update = malta_update,
+};
+
+/*
+ * MIPS SEAD3 development board
+ */
+
+enum {
+ SEAD3_REG_LCD_CTRL = 0x00,
+#define SEAD3_REG_LCD_CTRL_SETDRAM BIT(7)
+ SEAD3_REG_LCD_DATA = 0x08,
+ SEAD3_REG_CPLD_STATUS = 0x10,
+#define SEAD3_REG_CPLD_STATUS_BUSY BIT(0)
+ SEAD3_REG_CPLD_DATA = 0x18,
+#define SEAD3_REG_CPLD_DATA_BUSY BIT(7)
+};
+
+static int sead3_wait_sm_idle(struct img_ascii_lcd_ctx *ctx)
+{
+ unsigned int status;
+ int err;
+
+ do {
+ err = regmap_read(ctx->regmap,
+ ctx->offset + SEAD3_REG_CPLD_STATUS,
+ &status);
+ if (err)
+ return err;
+ } while (status & SEAD3_REG_CPLD_STATUS_BUSY);
+
+ return 0;
+
+}
+
+static int sead3_wait_lcd_idle(struct img_ascii_lcd_ctx *ctx)
+{
+ unsigned int cpld_data;
+ int err;
+
+ err = sead3_wait_sm_idle(ctx);
+ if (err)
+ return err;
+
+ do {
+ err = regmap_read(ctx->regmap,
+ ctx->offset + SEAD3_REG_LCD_CTRL,
+ &cpld_data);
+ if (err)
+ return err;
+
+ err = sead3_wait_sm_idle(ctx);
+ if (err)
+ return err;
+
+ err = regmap_read(ctx->regmap,
+ ctx->offset + SEAD3_REG_CPLD_DATA,
+ &cpld_data);
+ if (err)
+ return err;
+ } while (cpld_data & SEAD3_REG_CPLD_DATA_BUSY);
+
+ return 0;
+}
+
+static void sead3_update(struct img_ascii_lcd_ctx *ctx)
+{
+ unsigned int i;
+ int err;
+
+ for (i = 0; i < ctx->cfg->num_chars; i++) {
+ err = sead3_wait_lcd_idle(ctx);
+ if (err)
+ break;
+
+ err = regmap_write(ctx->regmap,
+ ctx->offset + SEAD3_REG_LCD_CTRL,
+ SEAD3_REG_LCD_CTRL_SETDRAM | i);
+ if (err)
+ break;
+
+ err = sead3_wait_lcd_idle(ctx);
+ if (err)
+ break;
+
+ err = regmap_write(ctx->regmap,
+ ctx->offset + SEAD3_REG_LCD_DATA,
+ ctx->curr[i]);
+ if (err)
+ break;
+ }
+
+ if (unlikely(err))
+ pr_err_ratelimited("Failed to update LCD display: %d\n", err);
+}
+
+static struct img_ascii_lcd_config sead3_config = {
+ .num_chars = 16,
+ .external_regmap = true,
+ .update = sead3_update,
+};
+
+static const struct of_device_id img_ascii_lcd_matches[] = {
+ { .compatible = "img,boston-lcd", .data = &boston_config },
+ { .compatible = "mti,malta-lcd", .data = &malta_config },
+ { .compatible = "mti,sead3-lcd", .data = &sead3_config },
+};
+
+/**
+ * img_ascii_lcd_scroll() - scroll the display by a character
+ * @arg: really a pointer to the private data structure
+ *
+ * Scroll the current message along the LCD by one character, rearming the
+ * timer if required.
+ */
+static void img_ascii_lcd_scroll(unsigned long arg)
+{
+ struct img_ascii_lcd_ctx *ctx = (struct img_ascii_lcd_ctx *)arg;
+ unsigned int i, ch = ctx->scroll_pos;
+ unsigned int num_chars = ctx->cfg->num_chars;
+
+ /* update the current message string */
+ for (i = 0; i < num_chars;) {
+ /* copy as many characters from the string as possible */
+ for (; i < num_chars && ch < ctx->message_len; i++, ch++)
+ ctx->curr[i] = ctx->message[ch];
+
+ /* wrap around to the start of the string */
+ ch = 0;
+ }
+
+ /* update the LCD */
+ ctx->cfg->update(ctx);
+
+ /* move on to the next character */
+ ctx->scroll_pos++;
+ ctx->scroll_pos %= ctx->message_len;
+
+ /* rearm the timer */
+ if (ctx->message_len > ctx->cfg->num_chars)
+ mod_timer(&ctx->timer, jiffies + ctx->scroll_rate);
+}
+
+/**
+ * img_ascii_lcd_display() - set the message to be displayed
+ * @ctx: pointer to the private data structure
+ * @msg: the message to display
+ * @count: length of msg, or -1
+ *
+ * Display a new message @msg on the LCD. @msg can be longer than the number of
+ * characters the LCD can display, in which case it will begin scrolling across
+ * the LCD display.
+ *
+ * Return: 0 on success, -ENOMEM on memory allocation failure
+ */
+static int img_ascii_lcd_display(struct img_ascii_lcd_ctx *ctx,
+ const char *msg, ssize_t count)
+{
+ char *new_msg;
+
+ /* stop the scroll timer */
+ del_timer_sync(&ctx->timer);
+
+ if (count == -1)
+ count = strlen(msg);
+
+ /* if the string ends with a newline, trim it */
+ if (msg[count - 1] == '\n')
+ count--;
+
+ new_msg = devm_kmalloc(&ctx->pdev->dev, count + 1, GFP_KERNEL);
+ if (!new_msg)
+ return -ENOMEM;
+
+ memcpy(new_msg, msg, count);
+ new_msg[count] = 0;
+
+ if (ctx->message)
+ devm_kfree(&ctx->pdev->dev, ctx->message);
+
+ ctx->message = new_msg;
+ ctx->message_len = count;
+ ctx->scroll_pos = 0;
+
+ /* update the LCD */
+ img_ascii_lcd_scroll((unsigned long)ctx);
+
+ return 0;
+}
+
+/**
+ * message_show() - read message via sysfs
+ * @dev: the LCD device
+ * @attr: the LCD message attribute
+ * @buf: the buffer to read the message into
+ *
+ * Read the current message being displayed or scrolled across the LCD display
+ * into @buf, for reads from sysfs.
+ *
+ * Return: the number of characters written to @buf
+ */
+static ssize_t message_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct img_ascii_lcd_ctx *ctx = dev_get_drvdata(dev);
+
+ return sprintf(buf, "%s\n", ctx->message);
+}
+
+/**
+ * message_store() - write a new message via sysfs
+ * @dev: the LCD device
+ * @attr: the LCD message attribute
+ * @buf: the buffer containing the new message
+ * @count: the size of the message in @buf
+ *
+ * Write a new message to display or scroll across the LCD display from sysfs.
+ *
+ * Return: the size of the message on success, else -ERRNO
+ */
+static ssize_t message_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct img_ascii_lcd_ctx *ctx = dev_get_drvdata(dev);
+ int err;
+
+ err = img_ascii_lcd_display(ctx, buf, count);
+ return err ?: count;
+}
+
+static DEVICE_ATTR_RW(message);
+
+/**
+ * img_ascii_lcd_probe() - probe an LCD display device
+ * @pdev: the LCD platform device
+ *
+ * Probe an LCD display device, ensuring that we have the required resources in
+ * order to access the LCD & setting up private data as well as sysfs files.
+ *
+ * Return: 0 on success, else -ERRNO
+ */
+static int img_ascii_lcd_probe(struct platform_device *pdev)
+{
+ const struct of_device_id *match;
+ const struct img_ascii_lcd_config *cfg;
+ struct img_ascii_lcd_ctx *ctx;
+ struct resource *res;
+ int err;
+
+ match = of_match_device(img_ascii_lcd_matches, &pdev->dev);
+ if (!match)
+ return -ENODEV;
+
+ cfg = match->data;
+ ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx) + cfg->num_chars,
+ GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ if (cfg->external_regmap) {
+ ctx->regmap = syscon_node_to_regmap(pdev->dev.parent->of_node);
+ if (IS_ERR(ctx->regmap))
+ return PTR_ERR(ctx->regmap);
+
+ if (of_property_read_u32(pdev->dev.of_node, "offset",
+ &ctx->offset))
+ return -EINVAL;
+ } else {
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ ctx->base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(ctx->base))
+ return PTR_ERR(ctx->base);
+ }
+
+ ctx->pdev = pdev;
+ ctx->cfg = cfg;
+ ctx->message = NULL;
+ ctx->scroll_pos = 0;
+ ctx->scroll_rate = HZ / 2;
+
+ /* initialise a timer for scrolling the message */
+ init_timer(&ctx->timer);
+ ctx->timer.function = img_ascii_lcd_scroll;
+ ctx->timer.data = (unsigned long)ctx;
+
+ platform_set_drvdata(pdev, ctx);
+
+ /* display a default message */
+ err = img_ascii_lcd_display(ctx, "Linux " UTS_RELEASE " ", -1);
+ if (err)
+ goto out_del_timer;
+
+ err = device_create_file(&pdev->dev, &dev_attr_message);
+ if (err)
+ goto out_del_timer;
+
+ return 0;
+out_del_timer:
+ del_timer_sync(&ctx->timer);
+ return err;
+}
+
+/**
+ * img_ascii_lcd_remove() - remove an LCD display device
+ * @pdev: the LCD platform device
+ *
+ * Remove an LCD display device, freeing private resources & ensuring that the
+ * driver stops using the LCD display registers.
+ *
+ * Return: 0
+ */
+static int img_ascii_lcd_remove(struct platform_device *pdev)
+{
+ struct img_ascii_lcd_ctx *ctx = platform_get_drvdata(pdev);
+
+ device_remove_file(&pdev->dev, &dev_attr_message);
+ del_timer_sync(&ctx->timer);
+ return 0;
+}
+
+static struct platform_driver img_ascii_lcd_driver = {
+ .driver = {
+ .name = "img-ascii-lcd",
+ .of_match_table = img_ascii_lcd_matches,
+ },
+ .probe = img_ascii_lcd_probe,
+ .remove = img_ascii_lcd_remove,
+};
+module_platform_driver(img_ascii_lcd_driver);
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index fdf44ca..d02e7c0 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -213,14 +213,16 @@
If you are unsure about this, Say N here.
config DEBUG_TEST_DRIVER_REMOVE
- bool "Test driver remove calls during probe"
+ bool "Test driver remove calls during probe (UNSTABLE)"
depends on DEBUG_KERNEL
help
Say Y here if you want the Driver core to test driver remove functions
by calling probe, remove, probe. This tests the remove path without
having to unbind the driver or unload the driver module.
- If you are unsure about this, say N here.
+ This option is expected to find errors and may render your system
+ unusable. You should say N here unless you are explicitly looking to
+ test this functionality.
config SYS_HYPERVISOR
bool
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index d22a726..d76cd97 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -324,7 +324,8 @@ static int really_probe(struct device *dev, struct device_driver *drv)
{
int ret = -EPROBE_DEFER;
int local_trigger_count = atomic_read(&deferred_trigger_count);
- bool test_remove = IS_ENABLED(CONFIG_DEBUG_TEST_DRIVER_REMOVE);
+ bool test_remove = IS_ENABLED(CONFIG_DEBUG_TEST_DRIVER_REMOVE) &&
+ !drv->suppress_bind_attrs;
if (defer_all_probes) {
/*
@@ -383,7 +384,7 @@ static int really_probe(struct device *dev, struct device_driver *drv)
if (test_remove) {
test_remove = false;
- if (dev->bus && dev->bus->remove)
+ if (dev->bus->remove)
dev->bus->remove(dev);
else if (drv->remove)
drv->remove(dev);
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index 8fc654f..71d5770 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -10,6 +10,7 @@
#include <linux/device.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/percpu.h>
#include "base.h"
@@ -985,3 +986,68 @@ void devm_free_pages(struct device *dev, unsigned long addr)
&devres));
}
EXPORT_SYMBOL_GPL(devm_free_pages);
+
+static void devm_percpu_release(struct device *dev, void *pdata)
+{
+ void __percpu *p;
+
+ p = *(void __percpu **)pdata;
+ free_percpu(p);
+}
+
+static int devm_percpu_match(struct device *dev, void *data, void *p)
+{
+ struct devres *devr = container_of(data, struct devres, data);
+
+ return *(void **)devr->data == p;
+}
+
+/**
+ * __devm_alloc_percpu - Resource-managed alloc_percpu
+ * @dev: Device to allocate per-cpu memory for
+ * @size: Size of per-cpu memory to allocate
+ * @align: Alignment of per-cpu memory to allocate
+ *
+ * Managed alloc_percpu. Per-cpu memory allocated with this function is
+ * automatically freed on driver detach.
+ *
+ * RETURNS:
+ * Pointer to allocated memory on success, NULL on failure.
+ */
+void __percpu *__devm_alloc_percpu(struct device *dev, size_t size,
+ size_t align)
+{
+ void *p;
+ void __percpu *pcpu;
+
+ pcpu = __alloc_percpu(size, align);
+ if (!pcpu)
+ return NULL;
+
+ p = devres_alloc(devm_percpu_release, sizeof(void *), GFP_KERNEL);
+ if (!p) {
+ free_percpu(pcpu);
+ return NULL;
+ }
+
+ *(void __percpu **)p = pcpu;
+
+ devres_add(dev, p);
+
+ return pcpu;
+}
+EXPORT_SYMBOL_GPL(__devm_alloc_percpu);
+
+/**
+ * devm_free_percpu - Resource-managed free_percpu
+ * @dev: Device this memory belongs to
+ * @pdata: Per-cpu memory to free
+ *
+ * Free memory allocated with devm_alloc_percpu().
+ */
+void devm_free_percpu(struct device *dev, void __percpu *pdata)
+{
+ WARN_ON(devres_destroy(dev, devm_percpu_release, devm_percpu_match,
+ (void *)pdata));
+}
+EXPORT_SYMBOL_GPL(devm_free_percpu);
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index e44944f..2932a5b 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1027,6 +1027,8 @@ static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool a
TRACE_DEVICE(dev);
TRACE_SUSPEND(0);
+ dpm_wait_for_children(dev, async);
+
if (async_error)
goto Complete;
@@ -1038,8 +1040,6 @@ static int __device_suspend_noirq(struct device *dev, pm_message_t state, bool a
if (dev->power.syscore || dev->power.direct_complete)
goto Complete;
- dpm_wait_for_children(dev, async);
-
if (dev->pm_domain) {
info = "noirq power domain ";
callback = pm_noirq_op(&dev->pm_domain->ops, state);
@@ -1174,6 +1174,8 @@ static int __device_suspend_late(struct device *dev, pm_message_t state, bool as
__pm_runtime_disable(dev, false);
+ dpm_wait_for_children(dev, async);
+
if (async_error)
goto Complete;
@@ -1185,8 +1187,6 @@ static int __device_suspend_late(struct device *dev, pm_message_t state, bool as
if (dev->power.syscore || dev->power.direct_complete)
goto Complete;
- dpm_wait_for_children(dev, async);
-
if (dev->pm_domain) {
info = "late power domain ";
callback = pm_late_early_op(&dev->pm_domain->ops, state);
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index 811e11c..0809cda9 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -2954,7 +2954,7 @@ DAC960_DetectController(struct pci_dev *PCI_Device,
case DAC960_PD_Controller:
if (!request_region(Controller->IO_Address, 0x80,
Controller->FullModelName)) {
- DAC960_Error("IO port 0x%d busy for Controller at\n",
+ DAC960_Error("IO port 0x%lx busy for Controller at\n",
Controller, Controller->IO_Address);
goto Failure;
}
@@ -2990,7 +2990,7 @@ DAC960_DetectController(struct pci_dev *PCI_Device,
case DAC960_P_Controller:
if (!request_region(Controller->IO_Address, 0x80,
Controller->FullModelName)){
- DAC960_Error("IO port 0x%d busy for Controller at\n",
+ DAC960_Error("IO port 0x%lx busy for Controller at\n",
Controller, Controller->IO_Address);
goto Failure;
}
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index ab19adb..3c606c0 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -853,45 +853,6 @@ rqbiocnt(struct request *r)
return n;
}
-/* This can be removed if we are certain that no users of the block
- * layer will ever use zero-count pages in bios. Otherwise we have to
- * protect against the put_page sometimes done by the network layer.
- *
- * See http://oss.sgi.com/archives/xfs/2007-01/msg00594.html for
- * discussion.
- *
- * We cannot use get_page in the workaround, because it insists on a
- * positive page count as a precondition. So we use _refcount directly.
- */
-static void
-bio_pageinc(struct bio *bio)
-{
- struct bio_vec bv;
- struct page *page;
- struct bvec_iter iter;
-
- bio_for_each_segment(bv, bio, iter) {
- /* Non-zero page count for non-head members of
- * compound pages is no longer allowed by the kernel.
- */
- page = compound_head(bv.bv_page);
- page_ref_inc(page);
- }
-}
-
-static void
-bio_pagedec(struct bio *bio)
-{
- struct page *page;
- struct bio_vec bv;
- struct bvec_iter iter;
-
- bio_for_each_segment(bv, bio, iter) {
- page = compound_head(bv.bv_page);
- page_ref_dec(page);
- }
-}
-
static void
bufinit(struct buf *buf, struct request *rq, struct bio *bio)
{
@@ -899,7 +860,6 @@ bufinit(struct buf *buf, struct request *rq, struct bio *bio)
buf->rq = rq;
buf->bio = bio;
buf->iter = bio->bi_iter;
- bio_pageinc(bio);
}
static struct buf *
@@ -1127,7 +1087,6 @@ aoe_end_buf(struct aoedev *d, struct buf *buf)
if (buf == d->ip.buf)
d->ip.buf = NULL;
rq = buf->rq;
- bio_pagedec(buf->bio);
mempool_free(buf, d->bufpool);
n = (unsigned long) rq->special;
rq->special = (void *) --n;
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 100be55..8348272 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1871,7 +1871,7 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock,
drbd_update_congested(connection);
}
do {
- rv = kernel_sendmsg(sock, &msg, &iov, 1, size);
+ rv = kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len);
if (rv == -EAGAIN) {
if (we_should_drop_the_connection(connection, sock))
break;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index ba405b5..7a10487 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -164,7 +164,7 @@ static void sock_shutdown(struct nbd_device *nbd)
spin_lock(&nbd->sock_lock);
if (!nbd->sock) {
- spin_unlock_irq(&nbd->sock_lock);
+ spin_unlock(&nbd->sock_lock);
return;
}
@@ -599,7 +599,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
return -EINVAL;
sreq = blk_mq_alloc_request(bdev_get_queue(bdev), WRITE, 0);
- if (!sreq)
+ if (IS_ERR(sreq))
return -ENOMEM;
mutex_unlock(&nbd->tx_lock);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index abb7162..7b274ff 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -415,15 +415,15 @@ struct rbd_device {
};
/*
- * Flag bits for rbd_dev->flags. If atomicity is required,
- * rbd_dev->lock is used to protect access.
- *
- * Currently, only the "removing" flag (which is coupled with the
- * "open_count" field) requires atomic access.
+ * Flag bits for rbd_dev->flags:
+ * - REMOVING (which is coupled with rbd_dev->open_count) is protected
+ * by rbd_dev->lock
+ * - BLACKLISTED is protected by rbd_dev->lock_rwsem
*/
enum rbd_dev_flags {
RBD_DEV_FLAG_EXISTS, /* mapped snapshot has not been deleted */
RBD_DEV_FLAG_REMOVING, /* this mapping is being removed */
+ RBD_DEV_FLAG_BLACKLISTED, /* our ceph_client is blacklisted */
};
static DEFINE_MUTEX(client_mutex); /* Serialize client creation */
@@ -3926,6 +3926,7 @@ static void rbd_reregister_watch(struct work_struct *work)
struct rbd_device *rbd_dev = container_of(to_delayed_work(work),
struct rbd_device, watch_dwork);
bool was_lock_owner = false;
+ bool need_to_wake = false;
int ret;
dout("%s rbd_dev %p\n", __func__, rbd_dev);
@@ -3935,19 +3936,27 @@ static void rbd_reregister_watch(struct work_struct *work)
was_lock_owner = rbd_release_lock(rbd_dev);
mutex_lock(&rbd_dev->watch_mutex);
- if (rbd_dev->watch_state != RBD_WATCH_STATE_ERROR)
- goto fail_unlock;
+ if (rbd_dev->watch_state != RBD_WATCH_STATE_ERROR) {
+ mutex_unlock(&rbd_dev->watch_mutex);
+ goto out;
+ }
ret = __rbd_register_watch(rbd_dev);
if (ret) {
rbd_warn(rbd_dev, "failed to reregister watch: %d", ret);
- if (ret != -EBLACKLISTED)
+ if (ret == -EBLACKLISTED || ret == -ENOENT) {
+ set_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags);
+ need_to_wake = true;
+ } else {
queue_delayed_work(rbd_dev->task_wq,
&rbd_dev->watch_dwork,
RBD_RETRY_DELAY);
- goto fail_unlock;
+ }
+ mutex_unlock(&rbd_dev->watch_mutex);
+ goto out;
}
+ need_to_wake = true;
rbd_dev->watch_state = RBD_WATCH_STATE_REGISTERED;
rbd_dev->watch_cookie = rbd_dev->watch_handle->linger_id;
mutex_unlock(&rbd_dev->watch_mutex);
@@ -3963,13 +3972,10 @@ static void rbd_reregister_watch(struct work_struct *work)
ret);
}
+out:
up_write(&rbd_dev->lock_rwsem);
- wake_requests(rbd_dev, true);
- return;
-
-fail_unlock:
- mutex_unlock(&rbd_dev->watch_mutex);
- up_write(&rbd_dev->lock_rwsem);
+ if (need_to_wake)
+ wake_requests(rbd_dev, true);
}
/*
@@ -4074,7 +4080,9 @@ static void rbd_wait_state_locked(struct rbd_device *rbd_dev)
up_read(&rbd_dev->lock_rwsem);
schedule();
down_read(&rbd_dev->lock_rwsem);
- } while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED);
+ } while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
+ !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags));
+
finish_wait(&rbd_dev->lock_waitq, &wait);
}
@@ -4166,8 +4174,16 @@ static void rbd_queue_workfn(struct work_struct *work)
if (must_be_locked) {
down_read(&rbd_dev->lock_rwsem);
- if (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED)
+ if (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
+ !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags))
rbd_wait_state_locked(rbd_dev);
+
+ WARN_ON((rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED) ^
+ !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags));
+ if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
+ result = -EBLACKLISTED;
+ goto err_unlock;
+ }
}
img_request = rbd_img_request_create(rbd_dev, offset, length, op_type,
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 2dc5c96..5545a67 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -376,7 +376,7 @@ static void virtblk_config_changed(struct virtio_device *vdev)
static int init_vq(struct virtio_blk *vblk)
{
- int err = 0;
+ int err;
int i;
vq_callback_t **callbacks;
const char **names;
@@ -390,13 +390,13 @@ static int init_vq(struct virtio_blk *vblk)
if (err)
num_vqs = 1;
- vblk->vqs = kmalloc(sizeof(*vblk->vqs) * num_vqs, GFP_KERNEL);
+ vblk->vqs = kmalloc_array(num_vqs, sizeof(*vblk->vqs), GFP_KERNEL);
if (!vblk->vqs)
return -ENOMEM;
- names = kmalloc(sizeof(*names) * num_vqs, GFP_KERNEL);
- callbacks = kmalloc(sizeof(*callbacks) * num_vqs, GFP_KERNEL);
- vqs = kmalloc(sizeof(*vqs) * num_vqs, GFP_KERNEL);
+ names = kmalloc_array(num_vqs, sizeof(*names), GFP_KERNEL);
+ callbacks = kmalloc_array(num_vqs, sizeof(*callbacks), GFP_KERNEL);
+ vqs = kmalloc_array(num_vqs, sizeof(*vqs), GFP_KERNEL);
if (!names || !callbacks || !vqs) {
err = -ENOMEM;
goto out;
diff --git a/drivers/bluetooth/btwilink.c b/drivers/bluetooth/btwilink.c
index ef51c9c..b6bb58c 100644
--- a/drivers/bluetooth/btwilink.c
+++ b/drivers/bluetooth/btwilink.c
@@ -310,7 +310,7 @@ static int bt_ti_probe(struct platform_device *pdev)
BT_DBG("HCI device registered (hdev %p)", hdev);
dev_set_drvdata(&pdev->dev, hst);
- return err;
+ return 0;
}
static int bt_ti_remove(struct platform_device *pdev)
diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index 5ccb90e..8f6c23c 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -643,6 +643,14 @@ static const struct dmi_system_id bcm_wrong_irq_dmi_table[] = {
},
.driver_data = &acpi_active_low,
},
+ { /* Handle ThinkPad 8 tablets with BCM2E55 chipset ACPI ID */
+ .ident = "Lenovo ThinkPad 8",
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "ThinkPad 8"),
+ },
+ .driver_data = &acpi_active_low,
+ },
{ }
};
diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig
index 7010dca..7875105 100644
--- a/drivers/bus/Kconfig
+++ b/drivers/bus/Kconfig
@@ -111,6 +111,7 @@
config QCOM_EBI2
bool "Qualcomm External Bus Interface 2 (EBI2)"
depends on HAS_IOMEM
+ depends on ARCH_QCOM || COMPILE_TEST
help
Say y here to enable support for the Qualcomm External Bus
Interface 2, which can be used to connect things like NAND Flash,
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index 4827945..d2d2c89 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -84,14 +84,14 @@ static size_t rng_buffer_size(void)
static void add_early_randomness(struct hwrng *rng)
{
- unsigned char bytes[16];
int bytes_read;
+ size_t size = min_t(size_t, 16, rng_buffer_size());
mutex_lock(&reading_mutex);
- bytes_read = rng_get_data(rng, bytes, sizeof(bytes), 1);
+ bytes_read = rng_get_data(rng, rng_buffer, size, 1);
mutex_unlock(&reading_mutex);
if (bytes_read > 0)
- add_device_randomness(bytes, bytes_read);
+ add_device_randomness(rng_buffer, bytes_read);
}
static inline void cleanup_rng(struct kref *kref)
diff --git a/drivers/char/ipmi/Kconfig b/drivers/char/ipmi/Kconfig
index 5a9350b..7f81665 100644
--- a/drivers/char/ipmi/Kconfig
+++ b/drivers/char/ipmi/Kconfig
@@ -76,3 +76,11 @@
the IPMI management controller is capable of this.
endif # IPMI_HANDLER
+
+config ASPEED_BT_IPMI_BMC
+ depends on ARCH_ASPEED
+ tristate "BT IPMI bmc driver"
+ help
+ Provides a driver for the BT (Block Transfer) IPMI interface
+ found on Aspeed SOCs (AST2400 and AST2500). The driver
+ implements the BMC side of the BT interface.
diff --git a/drivers/char/ipmi/Makefile b/drivers/char/ipmi/Makefile
index f3ffde1..0d98cd9 100644
--- a/drivers/char/ipmi/Makefile
+++ b/drivers/char/ipmi/Makefile
@@ -11,3 +11,4 @@
obj-$(CONFIG_IPMI_POWERNV) += ipmi_powernv.o
obj-$(CONFIG_IPMI_WATCHDOG) += ipmi_watchdog.o
obj-$(CONFIG_IPMI_POWEROFF) += ipmi_poweroff.o
+obj-$(CONFIG_ASPEED_BT_IPMI_BMC) += bt-bmc.o
diff --git a/drivers/char/ipmi/bt-bmc.c b/drivers/char/ipmi/bt-bmc.c
new file mode 100644
index 0000000..b49e613
--- /dev/null
+++ b/drivers/char/ipmi/bt-bmc.c
@@ -0,0 +1,505 @@
+/*
+ * Copyright (c) 2015-2016, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/atomic.h>
+#include <linux/bt-bmc.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/poll.h>
+#include <linux/sched.h>
+#include <linux/timer.h>
+
+/*
+ * This is a BMC device used to communicate to the host
+ */
+#define DEVICE_NAME "ipmi-bt-host"
+
+#define BT_IO_BASE 0xe4
+#define BT_IRQ 10
+
+#define BT_CR0 0x0
+#define BT_CR0_IO_BASE 16
+#define BT_CR0_IRQ 12
+#define BT_CR0_EN_CLR_SLV_RDP 0x8
+#define BT_CR0_EN_CLR_SLV_WRP 0x4
+#define BT_CR0_ENABLE_IBT 0x1
+#define BT_CR1 0x4
+#define BT_CR1_IRQ_H2B 0x01
+#define BT_CR1_IRQ_HBUSY 0x40
+#define BT_CR2 0x8
+#define BT_CR2_IRQ_H2B 0x01
+#define BT_CR2_IRQ_HBUSY 0x40
+#define BT_CR3 0xc
+#define BT_CTRL 0x10
+#define BT_CTRL_B_BUSY 0x80
+#define BT_CTRL_H_BUSY 0x40
+#define BT_CTRL_OEM0 0x20
+#define BT_CTRL_SMS_ATN 0x10
+#define BT_CTRL_B2H_ATN 0x08
+#define BT_CTRL_H2B_ATN 0x04
+#define BT_CTRL_CLR_RD_PTR 0x02
+#define BT_CTRL_CLR_WR_PTR 0x01
+#define BT_BMC2HOST 0x14
+#define BT_INTMASK 0x18
+#define BT_INTMASK_B2H_IRQEN 0x01
+#define BT_INTMASK_B2H_IRQ 0x02
+#define BT_INTMASK_BMC_HWRST 0x80
+
+#define BT_BMC_BUFFER_SIZE 256
+
+struct bt_bmc {
+ struct device dev;
+ struct miscdevice miscdev;
+ void __iomem *base;
+ int irq;
+ wait_queue_head_t queue;
+ struct timer_list poll_timer;
+ struct mutex mutex;
+};
+
+static atomic_t open_count = ATOMIC_INIT(0);
+
+static u8 bt_inb(struct bt_bmc *bt_bmc, int reg)
+{
+ return ioread8(bt_bmc->base + reg);
+}
+
+static void bt_outb(struct bt_bmc *bt_bmc, u8 data, int reg)
+{
+ iowrite8(data, bt_bmc->base + reg);
+}
+
+static void clr_rd_ptr(struct bt_bmc *bt_bmc)
+{
+ bt_outb(bt_bmc, BT_CTRL_CLR_RD_PTR, BT_CTRL);
+}
+
+static void clr_wr_ptr(struct bt_bmc *bt_bmc)
+{
+ bt_outb(bt_bmc, BT_CTRL_CLR_WR_PTR, BT_CTRL);
+}
+
+static void clr_h2b_atn(struct bt_bmc *bt_bmc)
+{
+ bt_outb(bt_bmc, BT_CTRL_H2B_ATN, BT_CTRL);
+}
+
+static void set_b_busy(struct bt_bmc *bt_bmc)
+{
+ if (!(bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_B_BUSY))
+ bt_outb(bt_bmc, BT_CTRL_B_BUSY, BT_CTRL);
+}
+
+static void clr_b_busy(struct bt_bmc *bt_bmc)
+{
+ if (bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_B_BUSY)
+ bt_outb(bt_bmc, BT_CTRL_B_BUSY, BT_CTRL);
+}
+
+static void set_b2h_atn(struct bt_bmc *bt_bmc)
+{
+ bt_outb(bt_bmc, BT_CTRL_B2H_ATN, BT_CTRL);
+}
+
+static u8 bt_read(struct bt_bmc *bt_bmc)
+{
+ return bt_inb(bt_bmc, BT_BMC2HOST);
+}
+
+static ssize_t bt_readn(struct bt_bmc *bt_bmc, u8 *buf, size_t n)
+{
+ int i;
+
+ for (i = 0; i < n; i++)
+ buf[i] = bt_read(bt_bmc);
+ return n;
+}
+
+static void bt_write(struct bt_bmc *bt_bmc, u8 c)
+{
+ bt_outb(bt_bmc, c, BT_BMC2HOST);
+}
+
+static ssize_t bt_writen(struct bt_bmc *bt_bmc, u8 *buf, size_t n)
+{
+ int i;
+
+ for (i = 0; i < n; i++)
+ bt_write(bt_bmc, buf[i]);
+ return n;
+}
+
+static void set_sms_atn(struct bt_bmc *bt_bmc)
+{
+ bt_outb(bt_bmc, BT_CTRL_SMS_ATN, BT_CTRL);
+}
+
+static struct bt_bmc *file_bt_bmc(struct file *file)
+{
+ return container_of(file->private_data, struct bt_bmc, miscdev);
+}
+
+static int bt_bmc_open(struct inode *inode, struct file *file)
+{
+ struct bt_bmc *bt_bmc = file_bt_bmc(file);
+
+ if (atomic_inc_return(&open_count) == 1) {
+ clr_b_busy(bt_bmc);
+ return 0;
+ }
+
+ atomic_dec(&open_count);
+ return -EBUSY;
+}
+
+/*
+ * The BT (Block Transfer) interface means that entire messages are
+ * buffered by the host before a notification is sent to the BMC that
+ * there is data to be read. The first byte is the length and the
+ * message data follows. The read operation just tries to capture the
+ * whole before returning it to userspace.
+ *
+ * BT Message format :
+ *
+ * Byte 1 Byte 2 Byte 3 Byte 4 Byte 5:N
+ * Length NetFn/LUN Seq Cmd Data
+ *
+ */
+static ssize_t bt_bmc_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct bt_bmc *bt_bmc = file_bt_bmc(file);
+ u8 len;
+ int len_byte = 1;
+ u8 kbuffer[BT_BMC_BUFFER_SIZE];
+ ssize_t ret = 0;
+ ssize_t nread;
+
+ if (!access_ok(VERIFY_WRITE, buf, count))
+ return -EFAULT;
+
+ WARN_ON(*ppos);
+
+ if (wait_event_interruptible(bt_bmc->queue,
+ bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_H2B_ATN))
+ return -ERESTARTSYS;
+
+ mutex_lock(&bt_bmc->mutex);
+
+ if (unlikely(!(bt_inb(bt_bmc, BT_CTRL) & BT_CTRL_H2B_ATN))) {
+ ret = -EIO;
+ goto out_unlock;
+ }
+
+ set_b_busy(bt_bmc);
+ clr_h2b_atn(bt_bmc);
+ clr_rd_ptr(bt_bmc);
+
+ /*
+ * The BT frames start with the message length, which does not
+ * include the length byte.
+ */
+ kbuffer[0] = bt_read(bt_bmc);
+ len = kbuffer[0];
+
+ /* We pass the length back to userspace as well */
+ if (len + 1 > count)
+ len = count - 1;
+
+ while (len) {
+ nread = min_t(ssize_t, len, sizeof(kbuffer) - len_byte);
+
+ bt_readn(bt_bmc, kbuffer + len_byte, nread);
+
+ if (copy_to_user(buf, kbuffer, nread + len_byte)) {
+ ret = -EFAULT;
+ break;
+ }
+ len -= nread;
+ buf += nread + len_byte;
+ ret += nread + len_byte;
+ len_byte = 0;
+ }
+
+ clr_b_busy(bt_bmc);
+
+out_unlock:
+ mutex_unlock(&bt_bmc->mutex);
+ return ret;
+}
+
+/*
+ * BT Message response format :
+ *
+ * Byte 1 Byte 2 Byte 3 Byte 4 Byte 5 Byte 6:N
+ * Length NetFn/LUN Seq Cmd Code Data
+ */
+static ssize_t bt_bmc_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct bt_bmc *bt_bmc = file_bt_bmc(file);
+ u8 kbuffer[BT_BMC_BUFFER_SIZE];
+ ssize_t ret = 0;
+ ssize_t nwritten;
+
+ /*
+ * send a minimum response size
+ */
+ if (count < 5)
+ return -EINVAL;
+
+ if (!access_ok(VERIFY_READ, buf, count))
+ return -EFAULT;
+
+ WARN_ON(*ppos);
+
+ /*
+ * There's no interrupt for clearing bmc busy so we have to
+ * poll
+ */
+ if (wait_event_interruptible(bt_bmc->queue,
+ !(bt_inb(bt_bmc, BT_CTRL) &
+ (BT_CTRL_H_BUSY | BT_CTRL_B2H_ATN))))
+ return -ERESTARTSYS;
+
+ mutex_lock(&bt_bmc->mutex);
+
+ if (unlikely(bt_inb(bt_bmc, BT_CTRL) &
+ (BT_CTRL_H_BUSY | BT_CTRL_B2H_ATN))) {
+ ret = -EIO;
+ goto out_unlock;
+ }
+
+ clr_wr_ptr(bt_bmc);
+
+ while (count) {
+ nwritten = min_t(ssize_t, count, sizeof(kbuffer));
+ if (copy_from_user(&kbuffer, buf, nwritten)) {
+ ret = -EFAULT;
+ break;
+ }
+
+ bt_writen(bt_bmc, kbuffer, nwritten);
+
+ count -= nwritten;
+ buf += nwritten;
+ ret += nwritten;
+ }
+
+ set_b2h_atn(bt_bmc);
+
+out_unlock:
+ mutex_unlock(&bt_bmc->mutex);
+ return ret;
+}
+
+static long bt_bmc_ioctl(struct file *file, unsigned int cmd,
+ unsigned long param)
+{
+ struct bt_bmc *bt_bmc = file_bt_bmc(file);
+
+ switch (cmd) {
+ case BT_BMC_IOCTL_SMS_ATN:
+ set_sms_atn(bt_bmc);
+ return 0;
+ }
+ return -EINVAL;
+}
+
+static int bt_bmc_release(struct inode *inode, struct file *file)
+{
+ struct bt_bmc *bt_bmc = file_bt_bmc(file);
+
+ atomic_dec(&open_count);
+ set_b_busy(bt_bmc);
+ return 0;
+}
+
+static unsigned int bt_bmc_poll(struct file *file, poll_table *wait)
+{
+ struct bt_bmc *bt_bmc = file_bt_bmc(file);
+ unsigned int mask = 0;
+ u8 ctrl;
+
+ poll_wait(file, &bt_bmc->queue, wait);
+
+ ctrl = bt_inb(bt_bmc, BT_CTRL);
+
+ if (ctrl & BT_CTRL_H2B_ATN)
+ mask |= POLLIN;
+
+ if (!(ctrl & (BT_CTRL_H_BUSY | BT_CTRL_B2H_ATN)))
+ mask |= POLLOUT;
+
+ return mask;
+}
+
+static const struct file_operations bt_bmc_fops = {
+ .owner = THIS_MODULE,
+ .open = bt_bmc_open,
+ .read = bt_bmc_read,
+ .write = bt_bmc_write,
+ .release = bt_bmc_release,
+ .poll = bt_bmc_poll,
+ .unlocked_ioctl = bt_bmc_ioctl,
+};
+
+static void poll_timer(unsigned long data)
+{
+ struct bt_bmc *bt_bmc = (void *)data;
+
+ bt_bmc->poll_timer.expires += msecs_to_jiffies(500);
+ wake_up(&bt_bmc->queue);
+ add_timer(&bt_bmc->poll_timer);
+}
+
+static irqreturn_t bt_bmc_irq(int irq, void *arg)
+{
+ struct bt_bmc *bt_bmc = arg;
+ u32 reg;
+
+ reg = ioread32(bt_bmc->base + BT_CR2);
+ reg &= BT_CR2_IRQ_H2B | BT_CR2_IRQ_HBUSY;
+ if (!reg)
+ return IRQ_NONE;
+
+ /* ack pending IRQs */
+ iowrite32(reg, bt_bmc->base + BT_CR2);
+
+ wake_up(&bt_bmc->queue);
+ return IRQ_HANDLED;
+}
+
+static int bt_bmc_config_irq(struct bt_bmc *bt_bmc,
+ struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ u32 reg;
+ int rc;
+
+ bt_bmc->irq = platform_get_irq(pdev, 0);
+ if (!bt_bmc->irq)
+ return -ENODEV;
+
+ rc = devm_request_irq(dev, bt_bmc->irq, bt_bmc_irq, IRQF_SHARED,
+ DEVICE_NAME, bt_bmc);
+ if (rc < 0) {
+ dev_warn(dev, "Unable to request IRQ %d\n", bt_bmc->irq);
+ bt_bmc->irq = 0;
+ return rc;
+ }
+
+ /*
+ * Configure IRQs on the bmc clearing the H2B and HBUSY bits;
+ * H2B will be asserted when the bmc has data for us; HBUSY
+ * will be cleared (along with B2H) when we can write the next
+ * message to the BT buffer
+ */
+ reg = ioread32(bt_bmc->base + BT_CR1);
+ reg |= BT_CR1_IRQ_H2B | BT_CR1_IRQ_HBUSY;
+ iowrite32(reg, bt_bmc->base + BT_CR1);
+
+ return 0;
+}
+
+static int bt_bmc_probe(struct platform_device *pdev)
+{
+ struct bt_bmc *bt_bmc;
+ struct device *dev;
+ struct resource *res;
+ int rc;
+
+ if (!pdev || !pdev->dev.of_node)
+ return -ENODEV;
+
+ dev = &pdev->dev;
+ dev_info(dev, "Found bt bmc device\n");
+
+ bt_bmc = devm_kzalloc(dev, sizeof(*bt_bmc), GFP_KERNEL);
+ if (!bt_bmc)
+ return -ENOMEM;
+
+ dev_set_drvdata(&pdev->dev, bt_bmc);
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ bt_bmc->base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(bt_bmc->base))
+ return PTR_ERR(bt_bmc->base);
+
+ mutex_init(&bt_bmc->mutex);
+ init_waitqueue_head(&bt_bmc->queue);
+
+ bt_bmc->miscdev.minor = MISC_DYNAMIC_MINOR,
+ bt_bmc->miscdev.name = DEVICE_NAME,
+ bt_bmc->miscdev.fops = &bt_bmc_fops,
+ bt_bmc->miscdev.parent = dev;
+ rc = misc_register(&bt_bmc->miscdev);
+ if (rc) {
+ dev_err(dev, "Unable to register misc device\n");
+ return rc;
+ }
+
+ bt_bmc_config_irq(bt_bmc, pdev);
+
+ if (bt_bmc->irq) {
+ dev_info(dev, "Using IRQ %d\n", bt_bmc->irq);
+ } else {
+ dev_info(dev, "No IRQ; using timer\n");
+ setup_timer(&bt_bmc->poll_timer, poll_timer,
+ (unsigned long)bt_bmc);
+ bt_bmc->poll_timer.expires = jiffies + msecs_to_jiffies(10);
+ add_timer(&bt_bmc->poll_timer);
+ }
+
+ iowrite32((BT_IO_BASE << BT_CR0_IO_BASE) |
+ (BT_IRQ << BT_CR0_IRQ) |
+ BT_CR0_EN_CLR_SLV_RDP |
+ BT_CR0_EN_CLR_SLV_WRP |
+ BT_CR0_ENABLE_IBT,
+ bt_bmc->base + BT_CR0);
+
+ clr_b_busy(bt_bmc);
+
+ return 0;
+}
+
+static int bt_bmc_remove(struct platform_device *pdev)
+{
+ struct bt_bmc *bt_bmc = dev_get_drvdata(&pdev->dev);
+
+ misc_deregister(&bt_bmc->miscdev);
+ if (!bt_bmc->irq)
+ del_timer_sync(&bt_bmc->poll_timer);
+ return 0;
+}
+
+static const struct of_device_id bt_bmc_match[] = {
+ { .compatible = "aspeed,ast2400-bt-bmc" },
+ { },
+};
+
+static struct platform_driver bt_bmc_driver = {
+ .driver = {
+ .name = DEVICE_NAME,
+ .of_match_table = bt_bmc_match,
+ },
+ .probe = bt_bmc_probe,
+ .remove = bt_bmc_remove,
+};
+
+module_platform_driver(bt_bmc_driver);
+
+MODULE_DEVICE_TABLE(of, bt_bmc_match);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Alistair Popple <alistair@popple.id.au>");
+MODULE_DESCRIPTION("Linux device interface to the BT interface");
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index d8619998..fcdd886 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -2891,11 +2891,11 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers,
intf->curr_channel = IPMI_MAX_CHANNELS;
}
+ rv = ipmi_bmc_register(intf, i);
+
if (rv == 0)
rv = add_proc_entries(intf, i);
- rv = ipmi_bmc_register(intf, i);
-
out:
if (rv) {
if (intf->proc_dir)
@@ -2982,8 +2982,6 @@ int ipmi_unregister_smi(ipmi_smi_t intf)
int intf_num = intf->intf_num;
ipmi_user_t user;
- ipmi_bmc_unregister(intf);
-
mutex_lock(&smi_watchers_mutex);
mutex_lock(&ipmi_interfaces_mutex);
intf->intf_num = -1;
@@ -3007,6 +3005,7 @@ int ipmi_unregister_smi(ipmi_smi_t intf)
mutex_unlock(&ipmi_interfaces_mutex);
remove_proc_entries(intf);
+ ipmi_bmc_unregister(intf);
/*
* Call all the watcher interfaces to tell them that
diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c
index d233688..6af1ce0 100644
--- a/drivers/char/ppdev.c
+++ b/drivers/char/ppdev.c
@@ -748,10 +748,7 @@ static int pp_release(struct inode *inode, struct file *file)
}
if (pp->pdev) {
- const char *name = pp->pdev->name;
-
parport_unregister_device(pp->pdev);
- kfree(name);
pp->pdev = NULL;
pr_debug(CHRDEV "%x: unregistered pardevice\n", minor);
}
diff --git a/drivers/char/random.c b/drivers/char/random.c
index d131e15..d6876d5 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -479,8 +479,8 @@ static ssize_t _extract_entropy(struct entropy_store *r, void *buf,
static void crng_reseed(struct crng_state *crng, struct entropy_store *r);
static void push_to_pool(struct work_struct *work);
-static __u32 input_pool_data[INPUT_POOL_WORDS];
-static __u32 blocking_pool_data[OUTPUT_POOL_WORDS];
+static __u32 input_pool_data[INPUT_POOL_WORDS] __latent_entropy;
+static __u32 blocking_pool_data[OUTPUT_POOL_WORDS] __latent_entropy;
static struct entropy_store input_pool = {
.poolinfo = &poolinfo_table[0],
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 8de6187..3a9149c 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -813,9 +813,6 @@ int tpm_do_selftest(struct tpm_chip *chip)
continue;
}
- if (rc < TPM_HEADER_SIZE)
- return -EFAULT;
-
if (rc == TPM_ERR_DISABLED || rc == TPM_ERR_DEACTIVATED) {
dev_info(&chip->dev,
"TPM is disabled/deactivated (0x%X)\n", rc);
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index d433b1d..5649234 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1539,19 +1539,29 @@ static void remove_port_data(struct port *port)
spin_lock_irq(&port->inbuf_lock);
/* Remove unused data this port might have received. */
discard_port_data(port);
+ spin_unlock_irq(&port->inbuf_lock);
/* Remove buffers we queued up for the Host to send us data in. */
- while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
- free_buf(buf, true);
- spin_unlock_irq(&port->inbuf_lock);
+ do {
+ spin_lock_irq(&port->inbuf_lock);
+ buf = virtqueue_detach_unused_buf(port->in_vq);
+ spin_unlock_irq(&port->inbuf_lock);
+ if (buf)
+ free_buf(buf, true);
+ } while (buf);
spin_lock_irq(&port->outvq_lock);
reclaim_consumed_buffers(port);
+ spin_unlock_irq(&port->outvq_lock);
/* Free pending buffers from the out-queue. */
- while ((buf = virtqueue_detach_unused_buf(port->out_vq)))
- free_buf(buf, true);
- spin_unlock_irq(&port->outvq_lock);
+ do {
+ spin_lock_irq(&port->outvq_lock);
+ buf = virtqueue_detach_unused_buf(port->out_vq);
+ spin_unlock_irq(&port->outvq_lock);
+ if (buf)
+ free_buf(buf, true);
+ } while (buf);
}
/*
diff --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c
index 190122e64..85a449c 100644
--- a/drivers/clk/at91/clk-programmable.c
+++ b/drivers/clk/at91/clk-programmable.c
@@ -203,7 +203,7 @@ at91_clk_register_programmable(struct regmap *regmap,
ret = clk_hw_register(NULL, &prog->hw);
if (ret) {
kfree(prog);
- hw = &prog->hw;
+ hw = ERR_PTR(ret);
}
return hw;
diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c
index b68bf57..8c7763f 100644
--- a/drivers/clk/bcm/clk-bcm2835.c
+++ b/drivers/clk/bcm/clk-bcm2835.c
@@ -502,8 +502,12 @@ static long bcm2835_pll_rate_from_divisors(unsigned long parent_rate,
static long bcm2835_pll_round_rate(struct clk_hw *hw, unsigned long rate,
unsigned long *parent_rate)
{
+ struct bcm2835_pll *pll = container_of(hw, struct bcm2835_pll, hw);
+ const struct bcm2835_pll_data *data = pll->data;
u32 ndiv, fdiv;
+ rate = clamp(rate, data->min_rate, data->max_rate);
+
bcm2835_pll_choose_ndiv_and_fdiv(rate, *parent_rate, &ndiv, &fdiv);
return bcm2835_pll_rate_from_divisors(*parent_rate, ndiv, fdiv, 1);
@@ -608,13 +612,6 @@ static int bcm2835_pll_set_rate(struct clk_hw *hw,
u32 ana[4];
int i;
- if (rate < data->min_rate || rate > data->max_rate) {
- dev_err(cprman->dev, "%s: rate out of spec: %lu vs (%lu, %lu)\n",
- clk_hw_get_name(hw), rate,
- data->min_rate, data->max_rate);
- return -EINVAL;
- }
-
if (rate > data->max_fb_rate) {
use_fb_prediv = true;
rate /= 2;
diff --git a/drivers/clk/clk-max77686.c b/drivers/clk/clk-max77686.c
index b637f59..eb953d3 100644
--- a/drivers/clk/clk-max77686.c
+++ b/drivers/clk/clk-max77686.c
@@ -216,6 +216,7 @@ static int max77686_clk_probe(struct platform_device *pdev)
return -EINVAL;
}
+ drv_data->num_clks = num_clks;
drv_data->max_clk_data = devm_kcalloc(dev, num_clks,
sizeof(*drv_data->max_clk_data),
GFP_KERNEL);
diff --git a/drivers/clk/clk-qoriq.c b/drivers/clk/clk-qoriq.c
index 20b1055..80ae2a5 100644
--- a/drivers/clk/clk-qoriq.c
+++ b/drivers/clk/clk-qoriq.c
@@ -700,6 +700,7 @@ static struct clk * __init create_mux_common(struct clockgen *cg,
struct mux_hwclock *hwc,
const struct clk_ops *ops,
unsigned long min_rate,
+ unsigned long max_rate,
unsigned long pct80_rate,
const char *fmt, int idx)
{
@@ -728,6 +729,8 @@ static struct clk * __init create_mux_common(struct clockgen *cg,
continue;
if (rate < min_rate)
continue;
+ if (rate > max_rate)
+ continue;
parent_names[j] = div->name;
hwc->parent_to_clksel[j] = i;
@@ -759,7 +762,7 @@ static struct clk * __init create_one_cmux(struct clockgen *cg, int idx)
struct mux_hwclock *hwc;
const struct clockgen_pll_div *div;
unsigned long plat_rate, min_rate;
- u64 pct80_rate;
+ u64 max_rate, pct80_rate;
u32 clksel;
hwc = kzalloc(sizeof(*hwc), GFP_KERNEL);
@@ -787,8 +790,8 @@ static struct clk * __init create_one_cmux(struct clockgen *cg, int idx)
return NULL;
}
- pct80_rate = clk_get_rate(div->clk);
- pct80_rate *= 8;
+ max_rate = clk_get_rate(div->clk);
+ pct80_rate = max_rate * 8;
do_div(pct80_rate, 10);
plat_rate = clk_get_rate(cg->pll[PLATFORM_PLL].div[PLL_DIV1].clk);
@@ -798,7 +801,7 @@ static struct clk * __init create_one_cmux(struct clockgen *cg, int idx)
else
min_rate = plat_rate / 2;
- return create_mux_common(cg, hwc, &cmux_ops, min_rate,
+ return create_mux_common(cg, hwc, &cmux_ops, min_rate, max_rate,
pct80_rate, "cg-cmux%d", idx);
}
@@ -813,7 +816,7 @@ static struct clk * __init create_one_hwaccel(struct clockgen *cg, int idx)
hwc->reg = cg->regs + 0x20 * idx + 0x10;
hwc->info = cg->info.hwaccel[idx];
- return create_mux_common(cg, hwc, &hwaccel_ops, 0, 0,
+ return create_mux_common(cg, hwc, &hwaccel_ops, 0, ULONG_MAX, 0,
"cg-hwaccel%d", idx);
}
diff --git a/drivers/clk/clk-xgene.c b/drivers/clk/clk-xgene.c
index 5daddf5..bc37030 100644
--- a/drivers/clk/clk-xgene.c
+++ b/drivers/clk/clk-xgene.c
@@ -463,22 +463,20 @@ static int xgene_clk_enable(struct clk_hw *hw)
struct xgene_clk *pclk = to_xgene_clk(hw);
unsigned long flags = 0;
u32 data;
- phys_addr_t reg;
if (pclk->lock)
spin_lock_irqsave(pclk->lock, flags);
if (pclk->param.csr_reg != NULL) {
pr_debug("%s clock enabled\n", clk_hw_get_name(hw));
- reg = __pa(pclk->param.csr_reg);
/* First enable the clock */
data = xgene_clk_read(pclk->param.csr_reg +
pclk->param.reg_clk_offset);
data |= pclk->param.reg_clk_mask;
xgene_clk_write(data, pclk->param.csr_reg +
pclk->param.reg_clk_offset);
- pr_debug("%s clock PADDR base %pa clk offset 0x%08X mask 0x%08X value 0x%08X\n",
- clk_hw_get_name(hw), ®,
+ pr_debug("%s clk offset 0x%08X mask 0x%08X value 0x%08X\n",
+ clk_hw_get_name(hw),
pclk->param.reg_clk_offset, pclk->param.reg_clk_mask,
data);
@@ -488,8 +486,8 @@ static int xgene_clk_enable(struct clk_hw *hw)
data &= ~pclk->param.reg_csr_mask;
xgene_clk_write(data, pclk->param.csr_reg +
pclk->param.reg_csr_offset);
- pr_debug("%s CSR RESET PADDR base %pa csr offset 0x%08X mask 0x%08X value 0x%08X\n",
- clk_hw_get_name(hw), ®,
+ pr_debug("%s csr offset 0x%08X mask 0x%08X value 0x%08X\n",
+ clk_hw_get_name(hw),
pclk->param.reg_csr_offset, pclk->param.reg_csr_mask,
data);
}
diff --git a/drivers/clk/hisilicon/clk-hi6220.c b/drivers/clk/hisilicon/clk-hi6220.c
index fe364e6..c0e8e1f 100644
--- a/drivers/clk/hisilicon/clk-hi6220.c
+++ b/drivers/clk/hisilicon/clk-hi6220.c
@@ -195,7 +195,7 @@ static void __init hi6220_clk_sys_init(struct device_node *np)
hi6220_clk_register_divider(hi6220_div_clks_sys,
ARRAY_SIZE(hi6220_div_clks_sys), clk_data);
}
-CLK_OF_DECLARE(hi6220_clk_sys, "hisilicon,hi6220-sysctrl", hi6220_clk_sys_init);
+CLK_OF_DECLARE_DRIVER(hi6220_clk_sys, "hisilicon,hi6220-sysctrl", hi6220_clk_sys_init);
/* clocks in media controller */
@@ -252,7 +252,7 @@ static void __init hi6220_clk_media_init(struct device_node *np)
hi6220_clk_register_divider(hi6220_div_clks_media,
ARRAY_SIZE(hi6220_div_clks_media), clk_data);
}
-CLK_OF_DECLARE(hi6220_clk_media, "hisilicon,hi6220-mediactrl", hi6220_clk_media_init);
+CLK_OF_DECLARE_DRIVER(hi6220_clk_media, "hisilicon,hi6220-mediactrl", hi6220_clk_media_init);
/* clocks in pmctrl */
diff --git a/drivers/clk/imx/clk-pllv3.c b/drivers/clk/imx/clk-pllv3.c
index 19f9b62..7a6acc3 100644
--- a/drivers/clk/imx/clk-pllv3.c
+++ b/drivers/clk/imx/clk-pllv3.c
@@ -223,7 +223,7 @@ static unsigned long clk_pllv3_av_recalc_rate(struct clk_hw *hw,
temp64 *= mfn;
do_div(temp64, mfd);
- return (parent_rate * div) + (u32)temp64;
+ return parent_rate * div + (unsigned long)temp64;
}
static long clk_pllv3_av_round_rate(struct clk_hw *hw, unsigned long rate,
@@ -247,7 +247,11 @@ static long clk_pllv3_av_round_rate(struct clk_hw *hw, unsigned long rate,
do_div(temp64, parent_rate);
mfn = temp64;
- return parent_rate * div + parent_rate * mfn / mfd;
+ temp64 = (u64)parent_rate;
+ temp64 *= mfn;
+ do_div(temp64, mfd);
+
+ return parent_rate * div + (unsigned long)temp64;
}
static int clk_pllv3_av_set_rate(struct clk_hw *hw, unsigned long rate,
diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig
index 380c372..f042bd2 100644
--- a/drivers/clk/mediatek/Kconfig
+++ b/drivers/clk/mediatek/Kconfig
@@ -8,6 +8,7 @@
config COMMON_CLK_MT8135
bool "Clock driver for Mediatek MT8135"
+ depends on ARCH_MEDIATEK || COMPILE_TEST
select COMMON_CLK_MEDIATEK
default ARCH_MEDIATEK
---help---
@@ -15,6 +16,7 @@
config COMMON_CLK_MT8173
bool "Clock driver for Mediatek MT8173"
+ depends on ARCH_MEDIATEK || COMPILE_TEST
select COMMON_CLK_MEDIATEK
default ARCH_MEDIATEK
---help---
diff --git a/drivers/clk/mmp/clk-of-mmp2.c b/drivers/clk/mmp/clk-of-mmp2.c
index 3a51fff..9adaf48 100644
--- a/drivers/clk/mmp/clk-of-mmp2.c
+++ b/drivers/clk/mmp/clk-of-mmp2.c
@@ -313,7 +313,7 @@ static void __init mmp2_clk_init(struct device_node *np)
}
pxa_unit->apmu_base = of_iomap(np, 1);
- if (!pxa_unit->mpmu_base) {
+ if (!pxa_unit->apmu_base) {
pr_err("failed to map apmu registers\n");
return;
}
diff --git a/drivers/clk/mmp/clk-of-pxa168.c b/drivers/clk/mmp/clk-of-pxa168.c
index 87f2317..f110c02 100644
--- a/drivers/clk/mmp/clk-of-pxa168.c
+++ b/drivers/clk/mmp/clk-of-pxa168.c
@@ -262,7 +262,7 @@ static void __init pxa168_clk_init(struct device_node *np)
}
pxa_unit->apmu_base = of_iomap(np, 1);
- if (!pxa_unit->mpmu_base) {
+ if (!pxa_unit->apmu_base) {
pr_err("failed to map apmu registers\n");
return;
}
diff --git a/drivers/clk/mmp/clk-of-pxa910.c b/drivers/clk/mmp/clk-of-pxa910.c
index e22a67f..64d1ef4 100644
--- a/drivers/clk/mmp/clk-of-pxa910.c
+++ b/drivers/clk/mmp/clk-of-pxa910.c
@@ -282,7 +282,7 @@ static void __init pxa910_clk_init(struct device_node *np)
}
pxa_unit->apmu_base = of_iomap(np, 1);
- if (!pxa_unit->mpmu_base) {
+ if (!pxa_unit->apmu_base) {
pr_err("failed to map apmu registers\n");
return;
}
@@ -294,7 +294,7 @@ static void __init pxa910_clk_init(struct device_node *np)
}
pxa_unit->apbcp_base = of_iomap(np, 3);
- if (!pxa_unit->mpmu_base) {
+ if (!pxa_unit->apbcp_base) {
pr_err("failed to map apbcp registers\n");
return;
}
diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c
index 45905fc..cecb0fd 100644
--- a/drivers/clk/mvebu/armada-37xx-periph.c
+++ b/drivers/clk/mvebu/armada-37xx-periph.c
@@ -305,7 +305,7 @@ static const struct of_device_id armada_3700_periph_clock_of_match[] = {
};
static int armada_3700_add_composite_clk(const struct clk_periph_data *data,
void __iomem *reg, spinlock_t *lock,
- struct device *dev, struct clk_hw *hw)
+ struct device *dev, struct clk_hw **hw)
{
const struct clk_ops *mux_ops = NULL, *gate_ops = NULL,
*rate_ops = NULL;
@@ -329,6 +329,7 @@ static int armada_3700_add_composite_clk(const struct clk_periph_data *data,
gate->lock = lock;
gate_ops = gate_hw->init->ops;
gate->reg = reg + (u64)gate->reg;
+ gate->flags = CLK_GATE_SET_TO_DISABLE;
}
if (data->rate_hw) {
@@ -353,13 +354,13 @@ static int armada_3700_add_composite_clk(const struct clk_periph_data *data,
}
}
- hw = clk_hw_register_composite(dev, data->name, data->parent_names,
+ *hw = clk_hw_register_composite(dev, data->name, data->parent_names,
data->num_parents, mux_hw,
mux_ops, rate_hw, rate_ops,
gate_hw, gate_ops, CLK_IGNORE_UNUSED);
- if (IS_ERR(hw))
- return PTR_ERR(hw);
+ if (IS_ERR(*hw))
+ return PTR_ERR(*hw);
return 0;
}
@@ -400,7 +401,7 @@ static int armada_3700_periph_clock_probe(struct platform_device *pdev)
spin_lock_init(&driver_data->lock);
for (i = 0; i < num_periph; i++) {
- struct clk_hw *hw = driver_data->hw_data->hws[i];
+ struct clk_hw **hw = &driver_data->hw_data->hws[i];
if (armada_3700_add_composite_clk(&data[i], reg,
&driver_data->lock, dev, hw))
diff --git a/drivers/clk/rockchip/clk-ddr.c b/drivers/clk/rockchip/clk-ddr.c
index 8feba93..e807535 100644
--- a/drivers/clk/rockchip/clk-ddr.c
+++ b/drivers/clk/rockchip/clk-ddr.c
@@ -144,11 +144,8 @@ struct clk *rockchip_clk_register_ddrclk(const char *name, int flags,
ddrclk->ddr_flag = ddr_flag;
clk = clk_register(NULL, &ddrclk->hw);
- if (IS_ERR(clk)) {
- pr_err("%s: could not register ddrclk %s\n", __func__, name);
+ if (IS_ERR(clk))
kfree(ddrclk);
- return NULL;
- }
return clk;
}
diff --git a/drivers/clk/samsung/clk-exynos-audss.c b/drivers/clk/samsung/clk-exynos-audss.c
index 51d152f..17e68a7 100644
--- a/drivers/clk/samsung/clk-exynos-audss.c
+++ b/drivers/clk/samsung/clk-exynos-audss.c
@@ -106,6 +106,7 @@ static const struct of_device_id exynos_audss_clk_of_match[] = {
},
{ },
};
+MODULE_DEVICE_TABLE(of, exynos_audss_clk_of_match);
static void exynos_audss_clk_teardown(void)
{
diff --git a/drivers/clk/samsung/clk-exynos-clkout.c b/drivers/clk/samsung/clk-exynos-clkout.c
index 96fab6c..6c6afb87 100644
--- a/drivers/clk/samsung/clk-exynos-clkout.c
+++ b/drivers/clk/samsung/clk-exynos-clkout.c
@@ -132,28 +132,34 @@ static void __init exynos_clkout_init(struct device_node *node, u32 mux_mask)
pr_err("%s: failed to register clkout clock\n", __func__);
}
+/*
+ * We use CLK_OF_DECLARE_DRIVER initialization method to avoid setting
+ * the OF_POPULATED flag on the pmu device tree node, so later the
+ * Exynos PMU platform device can be properly probed with PMU driver.
+ */
+
static void __init exynos4_clkout_init(struct device_node *node)
{
exynos_clkout_init(node, EXYNOS4_CLKOUT_MUX_MASK);
}
-CLK_OF_DECLARE(exynos4210_clkout, "samsung,exynos4210-pmu",
+CLK_OF_DECLARE_DRIVER(exynos4210_clkout, "samsung,exynos4210-pmu",
exynos4_clkout_init);
-CLK_OF_DECLARE(exynos4212_clkout, "samsung,exynos4212-pmu",
+CLK_OF_DECLARE_DRIVER(exynos4212_clkout, "samsung,exynos4212-pmu",
exynos4_clkout_init);
-CLK_OF_DECLARE(exynos4412_clkout, "samsung,exynos4412-pmu",
+CLK_OF_DECLARE_DRIVER(exynos4412_clkout, "samsung,exynos4412-pmu",
exynos4_clkout_init);
-CLK_OF_DECLARE(exynos3250_clkout, "samsung,exynos3250-pmu",
+CLK_OF_DECLARE_DRIVER(exynos3250_clkout, "samsung,exynos3250-pmu",
exynos4_clkout_init);
static void __init exynos5_clkout_init(struct device_node *node)
{
exynos_clkout_init(node, EXYNOS5_CLKOUT_MUX_MASK);
}
-CLK_OF_DECLARE(exynos5250_clkout, "samsung,exynos5250-pmu",
+CLK_OF_DECLARE_DRIVER(exynos5250_clkout, "samsung,exynos5250-pmu",
exynos5_clkout_init);
-CLK_OF_DECLARE(exynos5410_clkout, "samsung,exynos5410-pmu",
+CLK_OF_DECLARE_DRIVER(exynos5410_clkout, "samsung,exynos5410-pmu",
exynos5_clkout_init);
-CLK_OF_DECLARE(exynos5420_clkout, "samsung,exynos5420-pmu",
+CLK_OF_DECLARE_DRIVER(exynos5420_clkout, "samsung,exynos5420-pmu",
exynos5_clkout_init);
-CLK_OF_DECLARE(exynos5433_clkout, "samsung,exynos5433-pmu",
+CLK_OF_DECLARE_DRIVER(exynos5433_clkout, "samsung,exynos5433-pmu",
exynos5_clkout_init);
diff --git a/drivers/clk/uniphier/clk-uniphier-core.c b/drivers/clk/uniphier/clk-uniphier-core.c
index 5ffb898..26c53f7 100644
--- a/drivers/clk/uniphier/clk-uniphier-core.c
+++ b/drivers/clk/uniphier/clk-uniphier-core.c
@@ -79,7 +79,7 @@ static int uniphier_clk_probe(struct platform_device *pdev)
hw_data->num = clk_num;
/* avoid returning NULL for unused idx */
- for (; clk_num >= 0; clk_num--)
+ while (--clk_num >= 0)
hw_data->hws[clk_num] = ERR_PTR(-EINVAL);
for (p = data; p->name; p++) {
@@ -111,6 +111,10 @@ static int uniphier_clk_remove(struct platform_device *pdev)
static const struct of_device_id uniphier_clk_match[] = {
/* System clock */
{
+ .compatible = "socionext,uniphier-sld3-clock",
+ .data = uniphier_sld3_sys_clk_data,
+ },
+ {
.compatible = "socionext,uniphier-ld4-clock",
.data = uniphier_ld4_sys_clk_data,
},
@@ -138,7 +142,7 @@ static const struct of_device_id uniphier_clk_match[] = {
.compatible = "socionext,uniphier-ld20-clock",
.data = uniphier_ld20_sys_clk_data,
},
- /* Media I/O clock */
+ /* Media I/O clock, SD clock */
{
.compatible = "socionext,uniphier-sld3-mio-clock",
.data = uniphier_sld3_mio_clk_data,
@@ -156,20 +160,20 @@ static const struct of_device_id uniphier_clk_match[] = {
.data = uniphier_sld3_mio_clk_data,
},
{
- .compatible = "socionext,uniphier-pro5-mio-clock",
- .data = uniphier_pro5_mio_clk_data,
+ .compatible = "socionext,uniphier-pro5-sd-clock",
+ .data = uniphier_pro5_sd_clk_data,
},
{
- .compatible = "socionext,uniphier-pxs2-mio-clock",
- .data = uniphier_pro5_mio_clk_data,
+ .compatible = "socionext,uniphier-pxs2-sd-clock",
+ .data = uniphier_pro5_sd_clk_data,
},
{
.compatible = "socionext,uniphier-ld11-mio-clock",
.data = uniphier_sld3_mio_clk_data,
},
{
- .compatible = "socionext,uniphier-ld20-mio-clock",
- .data = uniphier_pro5_mio_clk_data,
+ .compatible = "socionext,uniphier-ld20-sd-clock",
+ .data = uniphier_pro5_sd_clk_data,
},
/* Peripheral clock */
{
diff --git a/drivers/clk/uniphier/clk-uniphier-mio.c b/drivers/clk/uniphier/clk-uniphier-mio.c
index 6aa7ec7..218d20f 100644
--- a/drivers/clk/uniphier/clk-uniphier-mio.c
+++ b/drivers/clk/uniphier/clk-uniphier-mio.c
@@ -93,7 +93,7 @@ const struct uniphier_clk_data uniphier_sld3_mio_clk_data[] = {
{ /* sentinel */ }
};
-const struct uniphier_clk_data uniphier_pro5_mio_clk_data[] = {
+const struct uniphier_clk_data uniphier_pro5_sd_clk_data[] = {
UNIPHIER_MIO_CLK_SD_FIXED,
UNIPHIER_MIO_CLK_SD(0, 0),
UNIPHIER_MIO_CLK_SD(1, 1),
diff --git a/drivers/clk/uniphier/clk-uniphier-mux.c b/drivers/clk/uniphier/clk-uniphier-mux.c
index 15a2f2c..2c243a8 100644
--- a/drivers/clk/uniphier/clk-uniphier-mux.c
+++ b/drivers/clk/uniphier/clk-uniphier-mux.c
@@ -42,7 +42,7 @@ static u8 uniphier_clk_mux_get_parent(struct clk_hw *hw)
struct uniphier_clk_mux *mux = to_uniphier_clk_mux(hw);
int num_parents = clk_hw_get_num_parents(hw);
int ret;
- u32 val;
+ unsigned int val;
u8 i;
ret = regmap_read(mux->regmap, mux->reg, &val);
diff --git a/drivers/clk/uniphier/clk-uniphier.h b/drivers/clk/uniphier/clk-uniphier.h
index 3ae1840..0244dba 100644
--- a/drivers/clk/uniphier/clk-uniphier.h
+++ b/drivers/clk/uniphier/clk-uniphier.h
@@ -115,7 +115,7 @@ extern const struct uniphier_clk_data uniphier_pxs2_sys_clk_data[];
extern const struct uniphier_clk_data uniphier_ld11_sys_clk_data[];
extern const struct uniphier_clk_data uniphier_ld20_sys_clk_data[];
extern const struct uniphier_clk_data uniphier_sld3_mio_clk_data[];
-extern const struct uniphier_clk_data uniphier_pro5_mio_clk_data[];
+extern const struct uniphier_clk_data uniphier_pro5_sd_clk_data[];
extern const struct uniphier_clk_data uniphier_ld4_peri_clk_data[];
extern const struct uniphier_clk_data uniphier_pro4_peri_clk_data[];
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 2451908..e2c6e43 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -417,6 +417,16 @@
config SYS_SUPPORTS_EM_STI
bool
+config CLKSRC_JCORE_PIT
+ bool "J-Core PIT timer driver" if COMPILE_TEST
+ depends on OF
+ depends on GENERIC_CLOCKEVENTS
+ depends on HAS_IOMEM
+ select CLKSRC_MMIO
+ help
+ This enables build of clocksource and clockevent driver for
+ the integrated PIT in the J-Core synthesizable, open source SoC.
+
config SH_TIMER_CMT
bool "Renesas CMT timer driver" if COMPILE_TEST
depends on GENERIC_CLOCKEVENTS
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index fd9d6df..cf87f40 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -5,6 +5,7 @@
obj-$(CONFIG_X86_PM_TIMER) += acpi_pm.o
obj-$(CONFIG_SCx200HR_TIMER) += scx200_hrt.o
obj-$(CONFIG_CS5535_CLOCK_EVENT_SRC) += cs5535-clockevt.o
+obj-$(CONFIG_CLKSRC_JCORE_PIT) += jcore-pit.o
obj-$(CONFIG_SH_TIMER_CMT) += sh_cmt.o
obj-$(CONFIG_SH_TIMER_MTU2) += sh_mtu2.o
obj-$(CONFIG_SH_TIMER_TMU) += sh_tmu.o
diff --git a/drivers/clocksource/jcore-pit.c b/drivers/clocksource/jcore-pit.c
new file mode 100644
index 0000000..54e1665
--- /dev/null
+++ b/drivers/clocksource/jcore-pit.c
@@ -0,0 +1,249 @@
+/*
+ * J-Core SoC PIT/clocksource driver
+ *
+ * Copyright (C) 2015-2016 Smart Energy Instruments, Inc.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/sched_clock.h>
+#include <linux/cpu.h>
+#include <linux/cpuhotplug.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#define PIT_IRQ_SHIFT 12
+#define PIT_PRIO_SHIFT 20
+#define PIT_ENABLE_SHIFT 26
+#define PIT_PRIO_MASK 0xf
+
+#define REG_PITEN 0x00
+#define REG_THROT 0x10
+#define REG_COUNT 0x14
+#define REG_BUSPD 0x18
+#define REG_SECHI 0x20
+#define REG_SECLO 0x24
+#define REG_NSEC 0x28
+
+struct jcore_pit {
+ struct clock_event_device ced;
+ void __iomem *base;
+ unsigned long periodic_delta;
+ u32 enable_val;
+};
+
+static void __iomem *jcore_pit_base;
+static struct jcore_pit __percpu *jcore_pit_percpu;
+
+static notrace u64 jcore_sched_clock_read(void)
+{
+ u32 seclo, nsec, seclo0;
+ __iomem void *base = jcore_pit_base;
+
+ seclo = readl(base + REG_SECLO);
+ do {
+ seclo0 = seclo;
+ nsec = readl(base + REG_NSEC);
+ seclo = readl(base + REG_SECLO);
+ } while (seclo0 != seclo);
+
+ return seclo * NSEC_PER_SEC + nsec;
+}
+
+static cycle_t jcore_clocksource_read(struct clocksource *cs)
+{
+ return jcore_sched_clock_read();
+}
+
+static int jcore_pit_disable(struct jcore_pit *pit)
+{
+ writel(0, pit->base + REG_PITEN);
+ return 0;
+}
+
+static int jcore_pit_set(unsigned long delta, struct jcore_pit *pit)
+{
+ jcore_pit_disable(pit);
+ writel(delta, pit->base + REG_THROT);
+ writel(pit->enable_val, pit->base + REG_PITEN);
+ return 0;
+}
+
+static int jcore_pit_set_state_shutdown(struct clock_event_device *ced)
+{
+ struct jcore_pit *pit = container_of(ced, struct jcore_pit, ced);
+
+ return jcore_pit_disable(pit);
+}
+
+static int jcore_pit_set_state_oneshot(struct clock_event_device *ced)
+{
+ struct jcore_pit *pit = container_of(ced, struct jcore_pit, ced);
+
+ return jcore_pit_disable(pit);
+}
+
+static int jcore_pit_set_state_periodic(struct clock_event_device *ced)
+{
+ struct jcore_pit *pit = container_of(ced, struct jcore_pit, ced);
+
+ return jcore_pit_set(pit->periodic_delta, pit);
+}
+
+static int jcore_pit_set_next_event(unsigned long delta,
+ struct clock_event_device *ced)
+{
+ struct jcore_pit *pit = container_of(ced, struct jcore_pit, ced);
+
+ return jcore_pit_set(delta, pit);
+}
+
+static int jcore_pit_local_init(unsigned cpu)
+{
+ struct jcore_pit *pit = this_cpu_ptr(jcore_pit_percpu);
+ unsigned buspd, freq;
+
+ pr_info("Local J-Core PIT init on cpu %u\n", cpu);
+
+ buspd = readl(pit->base + REG_BUSPD);
+ freq = DIV_ROUND_CLOSEST(NSEC_PER_SEC, buspd);
+ pit->periodic_delta = DIV_ROUND_CLOSEST(NSEC_PER_SEC, HZ * buspd);
+
+ clockevents_config_and_register(&pit->ced, freq, 1, ULONG_MAX);
+
+ return 0;
+}
+
+static irqreturn_t jcore_timer_interrupt(int irq, void *dev_id)
+{
+ struct jcore_pit *pit = this_cpu_ptr(dev_id);
+
+ if (clockevent_state_oneshot(&pit->ced))
+ jcore_pit_disable(pit);
+
+ pit->ced.event_handler(&pit->ced);
+
+ return IRQ_HANDLED;
+}
+
+static int __init jcore_pit_init(struct device_node *node)
+{
+ int err;
+ unsigned pit_irq, cpu;
+ unsigned long hwirq;
+ u32 irqprio, enable_val;
+
+ jcore_pit_base = of_iomap(node, 0);
+ if (!jcore_pit_base) {
+ pr_err("Error: Cannot map base address for J-Core PIT\n");
+ return -ENXIO;
+ }
+
+ pit_irq = irq_of_parse_and_map(node, 0);
+ if (!pit_irq) {
+ pr_err("Error: J-Core PIT has no IRQ\n");
+ return -ENXIO;
+ }
+
+ pr_info("Initializing J-Core PIT at %p IRQ %d\n",
+ jcore_pit_base, pit_irq);
+
+ err = clocksource_mmio_init(jcore_pit_base, "jcore_pit_cs",
+ NSEC_PER_SEC, 400, 32,
+ jcore_clocksource_read);
+ if (err) {
+ pr_err("Error registering clocksource device: %d\n", err);
+ return err;
+ }
+
+ sched_clock_register(jcore_sched_clock_read, 32, NSEC_PER_SEC);
+
+ jcore_pit_percpu = alloc_percpu(struct jcore_pit);
+ if (!jcore_pit_percpu) {
+ pr_err("Failed to allocate memory for clock event device\n");
+ return -ENOMEM;
+ }
+
+ err = request_irq(pit_irq, jcore_timer_interrupt,
+ IRQF_TIMER | IRQF_PERCPU,
+ "jcore_pit", jcore_pit_percpu);
+ if (err) {
+ pr_err("pit irq request failed: %d\n", err);
+ free_percpu(jcore_pit_percpu);
+ return err;
+ }
+
+ /*
+ * The J-Core PIT is not hard-wired to a particular IRQ, but
+ * integrated with the interrupt controller such that the IRQ it
+ * generates is programmable, as follows:
+ *
+ * The bit layout of the PIT enable register is:
+ *
+ * .....e..ppppiiiiiiii............
+ *
+ * where the .'s indicate unrelated/unused bits, e is enable,
+ * p is priority, and i is hard irq number.
+ *
+ * For the PIT included in AIC1 (obsolete but still in use),
+ * any hard irq (trap number) can be programmed via the 8
+ * iiiiiiii bits, and a priority (0-15) is programmable
+ * separately in the pppp bits.
+ *
+ * For the PIT included in AIC2 (current), the programming
+ * interface is equivalent modulo interrupt mapping. This is
+ * why a different compatible tag was not used. However only
+ * traps 64-127 (the ones actually intended to be used for
+ * interrupts, rather than syscalls/exceptions/etc.) can be
+ * programmed (the high 2 bits of i are ignored) and the
+ * priority pppp is <<2'd and or'd onto the irq number. This
+ * choice seems to have been made on the hardware engineering
+ * side under an assumption that preserving old AIC1 priority
+ * mappings was important. Future models will likely ignore
+ * the pppp field.
+ */
+ hwirq = irq_get_irq_data(pit_irq)->hwirq;
+ irqprio = (hwirq >> 2) & PIT_PRIO_MASK;
+ enable_val = (1U << PIT_ENABLE_SHIFT)
+ | (hwirq << PIT_IRQ_SHIFT)
+ | (irqprio << PIT_PRIO_SHIFT);
+
+ for_each_present_cpu(cpu) {
+ struct jcore_pit *pit = per_cpu_ptr(jcore_pit_percpu, cpu);
+
+ pit->base = of_iomap(node, cpu);
+ if (!pit->base) {
+ pr_err("Unable to map PIT for cpu %u\n", cpu);
+ continue;
+ }
+
+ pit->ced.name = "jcore_pit";
+ pit->ced.features = CLOCK_EVT_FEAT_PERIODIC
+ | CLOCK_EVT_FEAT_ONESHOT
+ | CLOCK_EVT_FEAT_PERCPU;
+ pit->ced.cpumask = cpumask_of(cpu);
+ pit->ced.rating = 400;
+ pit->ced.irq = pit_irq;
+ pit->ced.set_state_shutdown = jcore_pit_set_state_shutdown;
+ pit->ced.set_state_periodic = jcore_pit_set_state_periodic;
+ pit->ced.set_state_oneshot = jcore_pit_set_state_oneshot;
+ pit->ced.set_next_event = jcore_pit_set_next_event;
+
+ pit->enable_val = enable_val;
+ }
+
+ cpuhp_setup_state(CPUHP_AP_JCORE_TIMER_STARTING,
+ "AP_JCORE_TIMER_STARTING",
+ jcore_pit_local_init, NULL);
+
+ return 0;
+}
+
+CLOCKSOURCE_OF_DECLARE(jcore_pit, "jcore,pit", jcore_pit_init);
diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
index c184eb8..4f87f3e 100644
--- a/drivers/clocksource/timer-sun5i.c
+++ b/drivers/clocksource/timer-sun5i.c
@@ -152,6 +152,13 @@ static irqreturn_t sun5i_timer_interrupt(int irq, void *dev_id)
return IRQ_HANDLED;
}
+static cycle_t sun5i_clksrc_read(struct clocksource *clksrc)
+{
+ struct sun5i_timer_clksrc *cs = to_sun5i_timer_clksrc(clksrc);
+
+ return ~readl(cs->timer.base + TIMER_CNTVAL_LO_REG(1));
+}
+
static int sun5i_rate_cb_clksrc(struct notifier_block *nb,
unsigned long event, void *data)
{
@@ -210,8 +217,13 @@ static int __init sun5i_setup_clocksource(struct device_node *node,
writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD,
base + TIMER_CTL_REG(1));
- ret = clocksource_mmio_init(base + TIMER_CNTVAL_LO_REG(1), node->name,
- rate, 340, 32, clocksource_mmio_readl_down);
+ cs->clksrc.name = node->name;
+ cs->clksrc.rating = 340;
+ cs->clksrc.read = sun5i_clksrc_read;
+ cs->clksrc.mask = CLOCKSOURCE_MASK(32);
+ cs->clksrc.flags = CLOCK_SOURCE_IS_CONTINUOUS;
+
+ ret = clocksource_register_hz(&cs->clksrc, rate);
if (ret) {
pr_err("Couldn't register clock source.\n");
goto err_remove_notifier;
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 1b2f28f..4852d9e 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -80,11 +80,17 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
{
struct cppc_cpudata *cpu;
struct cpufreq_freqs freqs;
+ u32 desired_perf;
int ret = 0;
cpu = all_cpu_data[policy->cpu];
- cpu->perf_ctrls.desired_perf = (u64)target_freq * policy->max / cppc_dmi_max_khz;
+ desired_perf = (u64)target_freq * cpu->perf_caps.highest_perf / cppc_dmi_max_khz;
+ /* Return if it is exactly the same perf */
+ if (desired_perf == cpu->perf_ctrls.desired_perf)
+ return ret;
+
+ cpu->perf_ctrls.desired_perf = desired_perf;
freqs.old = policy->cur;
freqs.new = target_freq;
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 18da4f8..1347589 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -17,6 +17,7 @@
struct cs_policy_dbs_info {
struct policy_dbs_info policy_dbs;
unsigned int down_skip;
+ unsigned int requested_freq;
};
static inline struct cs_policy_dbs_info *to_dbs_info(struct policy_dbs_info *policy_dbs)
@@ -61,6 +62,7 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
{
struct policy_dbs_info *policy_dbs = policy->governor_data;
struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy_dbs);
+ unsigned int requested_freq = dbs_info->requested_freq;
struct dbs_data *dbs_data = policy_dbs->dbs_data;
struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
unsigned int load = dbs_update(policy);
@@ -72,10 +74,16 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
if (cs_tuners->freq_step == 0)
goto out;
+ /*
+ * If requested_freq is out of range, it is likely that the limits
+ * changed in the meantime, so fall back to current frequency in that
+ * case.
+ */
+ if (requested_freq > policy->max || requested_freq < policy->min)
+ requested_freq = policy->cur;
+
/* Check for frequency increase */
if (load > dbs_data->up_threshold) {
- unsigned int requested_freq = policy->cur;
-
dbs_info->down_skip = 0;
/* if we are already at full speed then break out early */
@@ -83,8 +91,11 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
goto out;
requested_freq += get_freq_target(cs_tuners, policy);
+ if (requested_freq > policy->max)
+ requested_freq = policy->max;
__cpufreq_driver_target(policy, requested_freq, CPUFREQ_RELATION_H);
+ dbs_info->requested_freq = requested_freq;
goto out;
}
@@ -95,7 +106,7 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
/* Check for frequency decrease */
if (load < cs_tuners->down_threshold) {
- unsigned int freq_target, requested_freq = policy->cur;
+ unsigned int freq_target;
/*
* if we cannot reduce the frequency anymore, break out early
*/
@@ -109,6 +120,7 @@ static unsigned int cs_dbs_timer(struct cpufreq_policy *policy)
requested_freq = policy->min;
__cpufreq_driver_target(policy, requested_freq, CPUFREQ_RELATION_L);
+ dbs_info->requested_freq = requested_freq;
}
out:
@@ -287,6 +299,7 @@ static void cs_start(struct cpufreq_policy *policy)
struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
dbs_info->down_skip = 0;
+ dbs_info->requested_freq = policy->cur;
}
static struct dbs_governor cs_governor = {
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 806f203..4737520 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -179,6 +179,7 @@ struct _pid {
/**
* struct cpudata - Per CPU instance data storage
* @cpu: CPU number for this instance data
+ * @policy: CPUFreq policy value
* @update_util: CPUFreq utility callback information
* @update_util_set: CPUFreq utility callback is set
* @iowait_boost: iowait-related boost fraction
@@ -201,6 +202,7 @@ struct _pid {
struct cpudata {
int cpu;
+ unsigned int policy;
struct update_util_data update_util;
bool update_util_set;
@@ -225,7 +227,7 @@ struct cpudata {
static struct cpudata **all_cpu_data;
/**
- * struct pid_adjust_policy - Stores static PID configuration data
+ * struct pstate_adjust_policy - Stores static PID configuration data
* @sample_rate_ms: PID calculation sample rate in ms
* @sample_rate_ns: Sample rate calculation in ns
* @deadband: PID deadband
@@ -562,12 +564,12 @@ static void intel_pstate_hwp_set(const struct cpumask *cpumask)
int min, hw_min, max, hw_max, cpu, range, adj_range;
u64 value, cap;
- rdmsrl(MSR_HWP_CAPABILITIES, cap);
- hw_min = HWP_LOWEST_PERF(cap);
- hw_max = HWP_HIGHEST_PERF(cap);
- range = hw_max - hw_min;
-
for_each_cpu(cpu, cpumask) {
+ rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
+ hw_min = HWP_LOWEST_PERF(cap);
+ hw_max = HWP_HIGHEST_PERF(cap);
+ range = hw_max - hw_min;
+
rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
adj_range = limits->min_perf_pct * range / 100;
min = hw_min + adj_range;
@@ -1142,10 +1144,8 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
}
-static void intel_pstate_set_min_pstate(struct cpudata *cpu)
+static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
{
- int pstate = cpu->pstate.min_pstate;
-
trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
cpu->pstate.current_pstate = pstate;
/*
@@ -1157,6 +1157,20 @@ static void intel_pstate_set_min_pstate(struct cpudata *cpu)
pstate_funcs.get_val(cpu, pstate));
}
+static void intel_pstate_set_min_pstate(struct cpudata *cpu)
+{
+ intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
+}
+
+static void intel_pstate_max_within_limits(struct cpudata *cpu)
+{
+ int min_pstate, max_pstate;
+
+ update_turbo_state();
+ intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate);
+ intel_pstate_set_pstate(cpu, max_pstate);
+}
+
static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
{
cpu->pstate.min_pstate = pstate_funcs.get_min();
@@ -1232,6 +1246,7 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
{
struct sample *sample = &cpu->sample;
int32_t busy_frac, boost;
+ int target, avg_pstate;
busy_frac = div_fp(sample->mperf, sample->tsc);
@@ -1242,7 +1257,26 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
busy_frac = boost;
sample->busy_scaled = busy_frac * 100;
- return get_avg_pstate(cpu) - pid_calc(&cpu->pid, sample->busy_scaled);
+
+ target = limits->no_turbo || limits->turbo_disabled ?
+ cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
+ target += target >> 2;
+ target = mul_fp(target, busy_frac);
+ if (target < cpu->pstate.min_pstate)
+ target = cpu->pstate.min_pstate;
+
+ /*
+ * If the average P-state during the previous cycle was higher than the
+ * current target, add 50% of the difference to the target to reduce
+ * possible performance oscillations and offset possible performance
+ * loss related to moving the workload from one CPU to another within
+ * a package/module.
+ */
+ avg_pstate = get_avg_pstate(cpu);
+ if (avg_pstate > target)
+ target += (avg_pstate - target) >> 1;
+
+ return target;
}
static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
@@ -1251,10 +1285,11 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
u64 duration_ns;
/*
- * perf_scaled is the average performance during the last sampling
- * period scaled by the ratio of the maximum P-state to the P-state
- * requested last time (in percent). That measures the system's
- * response to the previous P-state selection.
+ * perf_scaled is the ratio of the average P-state during the last
+ * sampling period to the P-state requested last time (in percent).
+ *
+ * That measures the system's response to the previous P-state
+ * selection.
*/
max_pstate = cpu->pstate.max_pstate_physical;
current_pstate = cpu->pstate.current_pstate;
@@ -1304,7 +1339,8 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
from = cpu->pstate.current_pstate;
- target_pstate = pstate_funcs.get_target_pstate(cpu);
+ target_pstate = cpu->policy == CPUFREQ_POLICY_PERFORMANCE ?
+ cpu->pstate.turbo_pstate : pstate_funcs.get_target_pstate(cpu);
intel_pstate_update_pstate(cpu, target_pstate);
@@ -1470,7 +1506,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
pr_debug("set_policy cpuinfo.max %u policy->max %u\n",
policy->cpuinfo.max_freq, policy->max);
- cpu = all_cpu_data[0];
+ cpu = all_cpu_data[policy->cpu];
+ cpu->policy = policy->policy;
+
if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
policy->max < policy->cpuinfo.max_freq &&
policy->max > cpu->pstate.max_pstate * cpu->pstate.scaling) {
@@ -1478,7 +1516,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
policy->max = policy->cpuinfo.max_freq;
}
- if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
+ if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
limits = &performance_limits;
if (policy->max >= policy->cpuinfo.max_freq) {
pr_debug("set performance\n");
@@ -1514,6 +1552,15 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
limits->max_perf = round_up(limits->max_perf, FRAC_BITS);
out:
+ if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
+ /*
+ * NOHZ_FULL CPUs need this as the governor callback may not
+ * be invoked on them.
+ */
+ intel_pstate_clear_update_util_hook(policy->cpu);
+ intel_pstate_max_within_limits(cpu);
+ }
+
intel_pstate_set_update_util_hook(policy->cpu);
intel_pstate_hwp_set_policy(policy);
diff --git a/drivers/cpuidle/Kconfig.mips b/drivers/cpuidle/Kconfig.mips
index 4102be0..512ee37 100644
--- a/drivers/cpuidle/Kconfig.mips
+++ b/drivers/cpuidle/Kconfig.mips
@@ -5,7 +5,7 @@
bool "CPU Idle driver for MIPS CPS platforms"
depends on CPU_IDLE && MIPS_CPS
depends on SYS_SUPPORTS_MIPS_CPS
- select ARCH_NEEDS_CPU_IDLE_COUPLED if MIPS_MT
+ select ARCH_NEEDS_CPU_IDLE_COUPLED if MIPS_MT || CPU_MIPSR6
select GENERIC_CLOCKEVENTS_BROADCAST if SMP
select MIPS_CPS_PM
default y
diff --git a/drivers/cpuidle/cpuidle-cps.c b/drivers/cpuidle/cpuidle-cps.c
index 1adb698..926ba98 100644
--- a/drivers/cpuidle/cpuidle-cps.c
+++ b/drivers/cpuidle/cpuidle-cps.c
@@ -163,7 +163,7 @@ static int __init cps_cpuidle_init(void)
core = cpu_data[cpu].core;
device = &per_cpu(cpuidle_dev, cpu);
device->cpu = cpu;
-#ifdef CONFIG_MIPS_MT
+#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED
cpumask_copy(&device->coupled_cpus, &cpu_sibling_map[cpu]);
#endif
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index e4ddb92..56b1538 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -592,16 +592,18 @@ static int chcr_aes_cbc_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
static int cxgb4_is_crypto_q_full(struct net_device *dev, unsigned int idx)
{
- int ret = 0;
- struct sge_ofld_txq *q;
struct adapter *adap = netdev2adap(dev);
+ struct sge_uld_txq_info *txq_info =
+ adap->sge.uld_txq_info[CXGB4_TX_CRYPTO];
+ struct sge_uld_txq *txq;
+ int ret = 0;
local_bh_disable();
- q = &adap->sge.ofldtxq[idx];
- spin_lock(&q->sendq.lock);
- if (q->full)
+ txq = &txq_info->uldtxq[idx];
+ spin_lock(&txq->sendq.lock);
+ if (txq->full)
ret = -1;
- spin_unlock(&q->sendq.lock);
+ spin_unlock(&txq->sendq.lock);
local_bh_enable();
return ret;
}
@@ -674,11 +676,11 @@ static int chcr_device_init(struct chcr_context *ctx)
}
u_ctx = ULD_CTX(ctx);
rxq_perchan = u_ctx->lldi.nrxq / u_ctx->lldi.nchan;
- ctx->dev->tx_channel_id = 0;
rxq_idx = ctx->dev->tx_channel_id * rxq_perchan;
rxq_idx += id % rxq_perchan;
spin_lock(&ctx->dev->lock_chcr_dev);
ctx->tx_channel_id = rxq_idx;
+ ctx->dev->tx_channel_id = !ctx->dev->tx_channel_id;
spin_unlock(&ctx->dev->lock_chcr_dev);
}
out:
diff --git a/drivers/crypto/chelsio/chcr_core.c b/drivers/crypto/chelsio/chcr_core.c
index fb5f9bb..4d7f670 100644
--- a/drivers/crypto/chelsio/chcr_core.c
+++ b/drivers/crypto/chelsio/chcr_core.c
@@ -42,6 +42,7 @@ static chcr_handler_func work_handlers[NUM_CPL_CMDS] = {
static struct cxgb4_uld_info chcr_uld_info = {
.name = DRV_MODULE_NAME,
.nrxq = MAX_ULD_QSETS,
+ .ntxq = MAX_ULD_QSETS,
.rxq_size = 1024,
.add = chcr_uld_add,
.state_change = chcr_uld_state_change,
@@ -126,7 +127,7 @@ static int cpl_fw6_pld_handler(struct chcr_dev *dev,
int chcr_send_wr(struct sk_buff *skb)
{
- return cxgb4_ofld_send(skb->dev, skb);
+ return cxgb4_crypto_send(skb->dev, skb);
}
static void *chcr_uld_add(const struct cxgb4_lld_info *lld)
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index daadd20a..3e2ab3b 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -14,7 +14,7 @@
config DEV_DAX_PMEM
tristate "PMEM DAX: direct access to persistent memory"
- depends on NVDIMM_DAX
+ depends on LIBNVDIMM && NVDIMM_DAX
default DEV_DAX
help
Support raw access to persistent memory. Note that this
diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index 9630d88..4a15fa5 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -44,7 +44,6 @@ static void dax_pmem_percpu_exit(void *data)
dev_dbg(dax_pmem->dev, "%s\n", __func__);
percpu_ref_exit(ref);
- wait_for_completion(&dax_pmem->cmp);
}
static void dax_pmem_percpu_kill(void *data)
@@ -54,6 +53,7 @@ static void dax_pmem_percpu_kill(void *data)
dev_dbg(dax_pmem->dev, "%s\n", __func__);
percpu_ref_kill(ref);
+ wait_for_completion(&dax_pmem->cmp);
}
static int dax_pmem_probe(struct device *dev)
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 478006b..bf3ea76 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -137,6 +137,10 @@ static int devfreq_update_status(struct devfreq *devfreq, unsigned long freq)
cur_time = jiffies;
+ /* Immediately exit if previous_freq is not initialized yet. */
+ if (!devfreq->previous_freq)
+ goto out;
+
prev_lev = devfreq_get_freq_level(devfreq, devfreq->previous_freq);
if (prev_lev < 0) {
ret = prev_lev;
@@ -594,17 +598,19 @@ struct devfreq *devfreq_add_device(struct device *dev,
if (devfreq->governor)
err = devfreq->governor->event_handler(devfreq,
DEVFREQ_GOV_START, NULL);
- mutex_unlock(&devfreq_list_lock);
if (err) {
dev_err(dev, "%s: Unable to start governor for the device\n",
__func__);
goto err_init;
}
+ mutex_unlock(&devfreq_list_lock);
return devfreq;
err_init:
list_del(&devfreq->node);
+ mutex_unlock(&devfreq_list_lock);
+
device_unregister(&devfreq->dev);
err_out:
return ERR_PTR(err);
diff --git a/drivers/devfreq/event/Kconfig b/drivers/devfreq/event/Kconfig
index 0fdae86..cd94980 100644
--- a/drivers/devfreq/event/Kconfig
+++ b/drivers/devfreq/event/Kconfig
@@ -17,6 +17,7 @@
tristate "EXYNOS NoC (Network On Chip) Probe DEVFREQ event Driver"
depends on ARCH_EXYNOS || COMPILE_TEST
select PM_OPP
+ select REGMAP_MMIO
help
This add the devfreq-event driver for Exynos SoC. It provides NoC
(Network on Chip) Probe counters to measure the bandwidth of AXI bus.
diff --git a/drivers/devfreq/event/exynos-nocp.c b/drivers/devfreq/event/exynos-nocp.c
index a584140..49e712a 100644
--- a/drivers/devfreq/event/exynos-nocp.c
+++ b/drivers/devfreq/event/exynos-nocp.c
@@ -176,9 +176,6 @@ static int exynos_nocp_get_event(struct devfreq_event_dev *edev,
return 0;
out:
- edata->load_count = 0;
- edata->total_count = 0;
-
dev_err(nocp->dev, "Failed to read the counter of NoC probe device\n");
return ret;
diff --git a/drivers/extcon/extcon-qcom-spmi-misc.c b/drivers/extcon/extcon-qcom-spmi-misc.c
index ca957a5..b8cde09 100644
--- a/drivers/extcon/extcon-qcom-spmi-misc.c
+++ b/drivers/extcon/extcon-qcom-spmi-misc.c
@@ -51,7 +51,7 @@ static void qcom_usb_extcon_detect_cable(struct work_struct *work)
if (ret)
return;
- extcon_set_state(info->edev, EXTCON_USB_HOST, !id);
+ extcon_set_state_sync(info->edev, EXTCON_USB_HOST, !id);
}
static irqreturn_t qcom_usb_irq_handler(int irq, void *dev_id)
diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c
index 03715e7..5d36402 100644
--- a/drivers/firewire/net.c
+++ b/drivers/firewire/net.c
@@ -73,13 +73,13 @@ struct rfc2734_header {
#define fwnet_get_hdr_lf(h) (((h)->w0 & 0xc0000000) >> 30)
#define fwnet_get_hdr_ether_type(h) (((h)->w0 & 0x0000ffff))
-#define fwnet_get_hdr_dg_size(h) (((h)->w0 & 0x0fff0000) >> 16)
+#define fwnet_get_hdr_dg_size(h) ((((h)->w0 & 0x0fff0000) >> 16) + 1)
#define fwnet_get_hdr_fg_off(h) (((h)->w0 & 0x00000fff))
#define fwnet_get_hdr_dgl(h) (((h)->w1 & 0xffff0000) >> 16)
-#define fwnet_set_hdr_lf(lf) ((lf) << 30)
+#define fwnet_set_hdr_lf(lf) ((lf) << 30)
#define fwnet_set_hdr_ether_type(et) (et)
-#define fwnet_set_hdr_dg_size(dgs) ((dgs) << 16)
+#define fwnet_set_hdr_dg_size(dgs) (((dgs) - 1) << 16)
#define fwnet_set_hdr_fg_off(fgo) (fgo)
#define fwnet_set_hdr_dgl(dgl) ((dgl) << 16)
@@ -578,6 +578,9 @@ static int fwnet_incoming_packet(struct fwnet_device *dev, __be32 *buf, int len,
int retval;
u16 ether_type;
+ if (len <= RFC2374_UNFRAG_HDR_SIZE)
+ return 0;
+
hdr.w0 = be32_to_cpu(buf[0]);
lf = fwnet_get_hdr_lf(&hdr);
if (lf == RFC2374_HDR_UNFRAG) {
@@ -602,7 +605,12 @@ static int fwnet_incoming_packet(struct fwnet_device *dev, __be32 *buf, int len,
return fwnet_finish_incoming_packet(net, skb, source_node_id,
is_broadcast, ether_type);
}
+
/* A datagram fragment has been received, now the fun begins. */
+
+ if (len <= RFC2374_FRAG_HDR_SIZE)
+ return 0;
+
hdr.w1 = ntohl(buf[1]);
buf += 2;
len -= RFC2374_FRAG_HDR_SIZE;
@@ -614,7 +622,10 @@ static int fwnet_incoming_packet(struct fwnet_device *dev, __be32 *buf, int len,
fg_off = fwnet_get_hdr_fg_off(&hdr);
}
datagram_label = fwnet_get_hdr_dgl(&hdr);
- dg_size = fwnet_get_hdr_dg_size(&hdr); /* ??? + 1 */
+ dg_size = fwnet_get_hdr_dg_size(&hdr);
+
+ if (fg_off + len > dg_size)
+ return 0;
spin_lock_irqsave(&dev->lock, flags);
@@ -722,6 +733,22 @@ static void fwnet_receive_packet(struct fw_card *card, struct fw_request *r,
fw_send_response(card, r, rcode);
}
+static int gasp_source_id(__be32 *p)
+{
+ return be32_to_cpu(p[0]) >> 16;
+}
+
+static u32 gasp_specifier_id(__be32 *p)
+{
+ return (be32_to_cpu(p[0]) & 0xffff) << 8 |
+ (be32_to_cpu(p[1]) & 0xff000000) >> 24;
+}
+
+static u32 gasp_version(__be32 *p)
+{
+ return be32_to_cpu(p[1]) & 0xffffff;
+}
+
static void fwnet_receive_broadcast(struct fw_iso_context *context,
u32 cycle, size_t header_length, void *header, void *data)
{
@@ -731,9 +758,6 @@ static void fwnet_receive_broadcast(struct fw_iso_context *context,
__be32 *buf_ptr;
int retval;
u32 length;
- u16 source_node_id;
- u32 specifier_id;
- u32 ver;
unsigned long offset;
unsigned long flags;
@@ -750,22 +774,17 @@ static void fwnet_receive_broadcast(struct fw_iso_context *context,
spin_unlock_irqrestore(&dev->lock, flags);
- specifier_id = (be32_to_cpu(buf_ptr[0]) & 0xffff) << 8
- | (be32_to_cpu(buf_ptr[1]) & 0xff000000) >> 24;
- ver = be32_to_cpu(buf_ptr[1]) & 0xffffff;
- source_node_id = be32_to_cpu(buf_ptr[0]) >> 16;
-
- if (specifier_id == IANA_SPECIFIER_ID &&
- (ver == RFC2734_SW_VERSION
+ if (length > IEEE1394_GASP_HDR_SIZE &&
+ gasp_specifier_id(buf_ptr) == IANA_SPECIFIER_ID &&
+ (gasp_version(buf_ptr) == RFC2734_SW_VERSION
#if IS_ENABLED(CONFIG_IPV6)
- || ver == RFC3146_SW_VERSION
+ || gasp_version(buf_ptr) == RFC3146_SW_VERSION
#endif
- )) {
- buf_ptr += 2;
- length -= IEEE1394_GASP_HDR_SIZE;
- fwnet_incoming_packet(dev, buf_ptr, length, source_node_id,
+ ))
+ fwnet_incoming_packet(dev, buf_ptr + 2,
+ length - IEEE1394_GASP_HDR_SIZE,
+ gasp_source_id(buf_ptr),
context->card->generation, true);
- }
packet.payload_length = dev->rcv_buffer_size;
packet.interrupt = 1;
@@ -1465,7 +1484,7 @@ static int fwnet_probe(struct fw_unit *unit,
net->mtu = 1500U;
net->min_mtu = ETH_MIN_MTU;
- net->max_mtu = ETH_MAX_MTU;
+ net->max_mtu = 0xfff;
/* Set our hardware address while we're at it */
ha = (union fwnet_hwaddr *)net->dev_addr;
diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c
index 631c977..180f0a9 100644
--- a/drivers/firewire/nosy.c
+++ b/drivers/firewire/nosy.c
@@ -566,6 +566,11 @@ add_card(struct pci_dev *dev, const struct pci_device_id *unused)
lynx->registers = ioremap_nocache(pci_resource_start(dev, 0),
PCILYNX_MAX_REGISTER);
+ if (lynx->registers == NULL) {
+ dev_err(&dev->dev, "Failed to map registers\n");
+ ret = -ENOMEM;
+ goto fail_deallocate_lynx;
+ }
lynx->rcv_start_pcl = pci_alloc_consistent(lynx->pci_device,
sizeof(struct pcl), &lynx->rcv_start_pcl_bus);
@@ -578,7 +583,7 @@ add_card(struct pci_dev *dev, const struct pci_device_id *unused)
lynx->rcv_buffer == NULL) {
dev_err(&dev->dev, "Failed to allocate receive buffer\n");
ret = -ENOMEM;
- goto fail_deallocate;
+ goto fail_deallocate_buffers;
}
lynx->rcv_start_pcl->next = cpu_to_le32(lynx->rcv_pcl_bus);
lynx->rcv_pcl->next = cpu_to_le32(PCL_NEXT_INVALID);
@@ -641,7 +646,7 @@ add_card(struct pci_dev *dev, const struct pci_device_id *unused)
dev_err(&dev->dev,
"Failed to allocate shared interrupt %d\n", dev->irq);
ret = -EIO;
- goto fail_deallocate;
+ goto fail_deallocate_buffers;
}
lynx->misc.parent = &dev->dev;
@@ -668,7 +673,7 @@ add_card(struct pci_dev *dev, const struct pci_device_id *unused)
reg_write(lynx, PCI_INT_ENABLE, 0);
free_irq(lynx->pci_device->irq, lynx);
-fail_deallocate:
+fail_deallocate_buffers:
if (lynx->rcv_start_pcl)
pci_free_consistent(lynx->pci_device, sizeof(struct pcl),
lynx->rcv_start_pcl, lynx->rcv_start_pcl_bus);
@@ -679,6 +684,8 @@ add_card(struct pci_dev *dev, const struct pci_device_id *unused)
pci_free_consistent(lynx->pci_device, PAGE_SIZE,
lynx->rcv_buffer, lynx->rcv_buffer_bus);
iounmap(lynx->registers);
+
+fail_deallocate_lynx:
kfree(lynx);
fail_disable:
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index c069451..5e23e2d 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -11,7 +11,7 @@
-mno-mmx -mno-sse
cflags-$(CONFIG_ARM64) := $(subst -pg,,$(KBUILD_CFLAGS))
-cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) \
+cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) -g0 \
-fno-builtin -fpic -mno-single-pic-base
cflags-$(CONFIG_EFI_ARMSTUB) += -I$(srctree)/scripts/dtc/libfdt
@@ -79,5 +79,6 @@
# decompressor. So move our .data to .data.efistub, which is preserved
# explicitly by the decompressor linker script.
#
-STUBCOPY_FLAGS-$(CONFIG_ARM) += --rename-section .data=.data.efistub
+STUBCOPY_FLAGS-$(CONFIG_ARM) += --rename-section .data=.data.efistub \
+ -R ___ksymtab+sort -R ___kcrctab+sort
STUBCOPY_RELOC-$(CONFIG_ARM) := R_ARM_ABS
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 26ee00f..d011cb8 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -284,7 +284,7 @@
config GPIO_MOCKUP
tristate "GPIO Testing Driver"
- depends on GPIOLIB
+ depends on GPIOLIB && SYSFS
select GPIO_SYSFS
help
This enables GPIO Testing driver, which provides a way to test GPIO
diff --git a/drivers/gpio/gpio-ath79.c b/drivers/gpio/gpio-ath79.c
index 9457e20..dc37dbe 100644
--- a/drivers/gpio/gpio-ath79.c
+++ b/drivers/gpio/gpio-ath79.c
@@ -219,6 +219,7 @@ static const struct of_device_id ath79_gpio_of_match[] = {
{ .compatible = "qca,ar9340-gpio" },
{},
};
+MODULE_DEVICE_TABLE(of, ath79_gpio_of_match);
static int ath79_gpio_probe(struct platform_device *pdev)
{
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index 425501c..793518a 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -239,7 +239,7 @@ static int mpc8xxx_gpio_irq_map(struct irq_domain *h, unsigned int irq,
irq_hw_number_t hwirq)
{
irq_set_chip_data(irq, h->host_data);
- irq_set_chip_and_handler(irq, &mpc8xxx_irq_chip, handle_level_irq);
+ irq_set_chip_and_handler(irq, &mpc8xxx_irq_chip, handle_edge_irq);
return 0;
}
diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c
index cd5dc27..1ed6132 100644
--- a/drivers/gpio/gpio-mvebu.c
+++ b/drivers/gpio/gpio-mvebu.c
@@ -293,10 +293,10 @@ static void mvebu_gpio_irq_ack(struct irq_data *d)
{
struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
struct mvebu_gpio_chip *mvchip = gc->private;
- u32 mask = ~(1 << (d->irq - gc->irq_base));
+ u32 mask = d->mask;
irq_gc_lock(gc);
- writel_relaxed(mask, mvebu_gpioreg_edge_cause(mvchip));
+ writel_relaxed(~mask, mvebu_gpioreg_edge_cause(mvchip));
irq_gc_unlock(gc);
}
@@ -305,7 +305,7 @@ static void mvebu_gpio_edge_irq_mask(struct irq_data *d)
struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
struct mvebu_gpio_chip *mvchip = gc->private;
struct irq_chip_type *ct = irq_data_get_chip_type(d);
- u32 mask = 1 << (d->irq - gc->irq_base);
+ u32 mask = d->mask;
irq_gc_lock(gc);
ct->mask_cache_priv &= ~mask;
@@ -319,8 +319,7 @@ static void mvebu_gpio_edge_irq_unmask(struct irq_data *d)
struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
struct mvebu_gpio_chip *mvchip = gc->private;
struct irq_chip_type *ct = irq_data_get_chip_type(d);
-
- u32 mask = 1 << (d->irq - gc->irq_base);
+ u32 mask = d->mask;
irq_gc_lock(gc);
ct->mask_cache_priv |= mask;
@@ -333,8 +332,7 @@ static void mvebu_gpio_level_irq_mask(struct irq_data *d)
struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
struct mvebu_gpio_chip *mvchip = gc->private;
struct irq_chip_type *ct = irq_data_get_chip_type(d);
-
- u32 mask = 1 << (d->irq - gc->irq_base);
+ u32 mask = d->mask;
irq_gc_lock(gc);
ct->mask_cache_priv &= ~mask;
@@ -347,8 +345,7 @@ static void mvebu_gpio_level_irq_unmask(struct irq_data *d)
struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
struct mvebu_gpio_chip *mvchip = gc->private;
struct irq_chip_type *ct = irq_data_get_chip_type(d);
-
- u32 mask = 1 << (d->irq - gc->irq_base);
+ u32 mask = d->mask;
irq_gc_lock(gc);
ct->mask_cache_priv |= mask;
@@ -462,7 +459,7 @@ static void mvebu_gpio_irq_handler(struct irq_desc *desc)
for (i = 0; i < mvchip->chip.ngpio; i++) {
int irq;
- irq = mvchip->irqbase + i;
+ irq = irq_find_mapping(mvchip->domain, i);
if (!(cause & (1 << i)))
continue;
@@ -655,6 +652,7 @@ static int mvebu_gpio_probe(struct platform_device *pdev)
struct irq_chip_type *ct;
struct clk *clk;
unsigned int ngpios;
+ bool have_irqs;
int soc_variant;
int i, cpu, id;
int err;
@@ -665,6 +663,9 @@ static int mvebu_gpio_probe(struct platform_device *pdev)
else
soc_variant = MVEBU_GPIO_SOC_VARIANT_ORION;
+ /* Some gpio controllers do not provide irq support */
+ have_irqs = of_irq_count(np) != 0;
+
mvchip = devm_kzalloc(&pdev->dev, sizeof(struct mvebu_gpio_chip),
GFP_KERNEL);
if (!mvchip)
@@ -697,7 +698,8 @@ static int mvebu_gpio_probe(struct platform_device *pdev)
mvchip->chip.get = mvebu_gpio_get;
mvchip->chip.direction_output = mvebu_gpio_direction_output;
mvchip->chip.set = mvebu_gpio_set;
- mvchip->chip.to_irq = mvebu_gpio_to_irq;
+ if (have_irqs)
+ mvchip->chip.to_irq = mvebu_gpio_to_irq;
mvchip->chip.base = id * MVEBU_MAX_GPIO_PER_BANK;
mvchip->chip.ngpio = ngpios;
mvchip->chip.can_sleep = false;
@@ -758,34 +760,30 @@ static int mvebu_gpio_probe(struct platform_device *pdev)
devm_gpiochip_add_data(&pdev->dev, &mvchip->chip, mvchip);
/* Some gpio controllers do not provide irq support */
- if (!of_irq_count(np))
+ if (!have_irqs)
return 0;
- /* Setup the interrupt handlers. Each chip can have up to 4
- * interrupt handlers, with each handler dealing with 8 GPIO
- * pins. */
- for (i = 0; i < 4; i++) {
- int irq = platform_get_irq(pdev, i);
-
- if (irq < 0)
- continue;
- irq_set_chained_handler_and_data(irq, mvebu_gpio_irq_handler,
- mvchip);
+ mvchip->domain =
+ irq_domain_add_linear(np, ngpios, &irq_generic_chip_ops, NULL);
+ if (!mvchip->domain) {
+ dev_err(&pdev->dev, "couldn't allocate irq domain %s (DT).\n",
+ mvchip->chip.label);
+ return -ENODEV;
}
- mvchip->irqbase = irq_alloc_descs(-1, 0, ngpios, -1);
- if (mvchip->irqbase < 0) {
- dev_err(&pdev->dev, "no irqs\n");
- return mvchip->irqbase;
+ err = irq_alloc_domain_generic_chips(
+ mvchip->domain, ngpios, 2, np->name, handle_level_irq,
+ IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_LEVEL, 0, 0);
+ if (err) {
+ dev_err(&pdev->dev, "couldn't allocate irq chips %s (DT).\n",
+ mvchip->chip.label);
+ goto err_domain;
}
- gc = irq_alloc_generic_chip("mvebu_gpio_irq", 2, mvchip->irqbase,
- mvchip->membase, handle_level_irq);
- if (!gc) {
- dev_err(&pdev->dev, "Cannot allocate generic irq_chip\n");
- return -ENOMEM;
- }
-
+ /* NOTE: The common accessors cannot be used because of the percpu
+ * access to the mask registers
+ */
+ gc = irq_get_domain_generic_chip(mvchip->domain, 0);
gc->private = mvchip;
ct = &gc->chip_types[0];
ct->type = IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_LEVEL_LOW;
@@ -803,27 +801,23 @@ static int mvebu_gpio_probe(struct platform_device *pdev)
ct->handler = handle_edge_irq;
ct->chip.name = mvchip->chip.label;
- irq_setup_generic_chip(gc, IRQ_MSK(ngpios), 0,
- IRQ_NOREQUEST, IRQ_LEVEL | IRQ_NOPROBE);
+ /* Setup the interrupt handlers. Each chip can have up to 4
+ * interrupt handlers, with each handler dealing with 8 GPIO
+ * pins.
+ */
+ for (i = 0; i < 4; i++) {
+ int irq = platform_get_irq(pdev, i);
- /* Setup irq domain on top of the generic chip. */
- mvchip->domain = irq_domain_add_simple(np, mvchip->chip.ngpio,
- mvchip->irqbase,
- &irq_domain_simple_ops,
- mvchip);
- if (!mvchip->domain) {
- dev_err(&pdev->dev, "couldn't allocate irq domain %s (DT).\n",
- mvchip->chip.label);
- err = -ENODEV;
- goto err_generic_chip;
+ if (irq < 0)
+ continue;
+ irq_set_chained_handler_and_data(irq, mvebu_gpio_irq_handler,
+ mvchip);
}
return 0;
-err_generic_chip:
- irq_remove_generic_chip(gc, IRQ_MSK(ngpios), IRQ_NOREQUEST,
- IRQ_LEVEL | IRQ_NOPROBE);
- kfree(gc);
+err_domain:
+ irq_domain_remove(mvchip->domain);
return err;
}
diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c
index b9daa0b..ee17248 100644
--- a/drivers/gpio/gpio-mxs.c
+++ b/drivers/gpio/gpio-mxs.c
@@ -308,8 +308,10 @@ static int mxs_gpio_probe(struct platform_device *pdev)
writel(~0U, port->base + PINCTRL_IRQSTAT(port) + MXS_CLR);
irq_base = irq_alloc_descs(-1, 0, 32, numa_node_id());
- if (irq_base < 0)
- return irq_base;
+ if (irq_base < 0) {
+ err = irq_base;
+ goto out_iounmap;
+ }
port->domain = irq_domain_add_legacy(np, 32, irq_base, 0,
&irq_domain_simple_ops, NULL);
@@ -349,6 +351,8 @@ static int mxs_gpio_probe(struct platform_device *pdev)
irq_domain_remove(port->domain);
out_irqdesc_free:
irq_free_descs(irq_base, 32);
+out_iounmap:
+ iounmap(port->base);
return err;
}
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 45c8817..e422568 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -794,6 +794,22 @@ static int pca953x_probe(struct i2c_client *client,
}
mutex_init(&chip->i2c_lock);
+ /*
+ * In case we have an i2c-mux controlled by a GPIO provided by an
+ * expander using the same driver higher on the device tree, read the
+ * i2c adapter nesting depth and use the retrieved value as lockdep
+ * subclass for chip->i2c_lock.
+ *
+ * REVISIT: This solution is not complete. It protects us from lockdep
+ * false positives when the expander controlling the i2c-mux is on
+ * a different level on the device tree, but not when it's on the same
+ * level on a different branch (in which case the subclass number
+ * would be the same).
+ *
+ * TODO: Once a correct solution is developed, a similar fix should be
+ * applied to all other i2c-controlled GPIO expanders (and potentially
+ * regmap-i2c).
+ */
lockdep_set_subclass(&chip->i2c_lock,
i2c_adapter_depth(client->adapter));
diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c
index e7d422a..5b00427 100644
--- a/drivers/gpio/gpio-stmpe.c
+++ b/drivers/gpio/gpio-stmpe.c
@@ -409,7 +409,7 @@ static irqreturn_t stmpe_gpio_irq(int irq, void *dev)
* 801/1801/1600, bits are cleared when read.
* Edge detect register is not present on 801/1600/1801
*/
- if (stmpe->partnum != STMPE801 || stmpe->partnum != STMPE1600 ||
+ if (stmpe->partnum != STMPE801 && stmpe->partnum != STMPE1600 &&
stmpe->partnum != STMPE1801) {
stmpe_reg_write(stmpe, statmsbreg + i, status[i]);
stmpe_reg_write(stmpe,
diff --git a/drivers/gpio/gpio-ts4800.c b/drivers/gpio/gpio-ts4800.c
index 9925611..c2a80b4 100644
--- a/drivers/gpio/gpio-ts4800.c
+++ b/drivers/gpio/gpio-ts4800.c
@@ -66,6 +66,7 @@ static const struct of_device_id ts4800_gpio_of_match[] = {
{ .compatible = "technologic,ts4800-gpio", },
{},
};
+MODULE_DEVICE_TABLE(of, ts4800_gpio_of_match);
static struct platform_driver ts4800_gpio_driver = {
.driver = {
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 58ece20..72a4b32 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -653,14 +653,17 @@ int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
{
int idx, i;
unsigned int irq_flags;
+ int ret = -ENOENT;
for (i = 0, idx = 0; idx <= index; i++) {
struct acpi_gpio_info info;
struct gpio_desc *desc;
desc = acpi_get_gpiod_by_index(adev, NULL, i, &info);
- if (IS_ERR(desc))
+ if (IS_ERR(desc)) {
+ ret = PTR_ERR(desc);
break;
+ }
if (info.gpioint && idx++ == index) {
int irq = gpiod_to_irq(desc);
@@ -679,7 +682,7 @@ int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
}
}
- return -ENOENT;
+ return ret;
}
EXPORT_SYMBOL_GPL(acpi_dev_gpio_irq_get);
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index ecad3f0..193f15d 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -26,14 +26,18 @@
#include "gpiolib.h"
-static int of_gpiochip_match_node(struct gpio_chip *chip, void *data)
+static int of_gpiochip_match_node_and_xlate(struct gpio_chip *chip, void *data)
{
- return chip->gpiodev->dev.of_node == data;
+ struct of_phandle_args *gpiospec = data;
+
+ return chip->gpiodev->dev.of_node == gpiospec->np &&
+ chip->of_xlate(chip, gpiospec, NULL) >= 0;
}
-static struct gpio_chip *of_find_gpiochip_by_node(struct device_node *np)
+static struct gpio_chip *of_find_gpiochip_by_xlate(
+ struct of_phandle_args *gpiospec)
{
- return gpiochip_find(np, of_gpiochip_match_node);
+ return gpiochip_find(gpiospec, of_gpiochip_match_node_and_xlate);
}
static struct gpio_desc *of_xlate_and_get_gpiod_flags(struct gpio_chip *chip,
@@ -79,7 +83,7 @@ struct gpio_desc *of_get_named_gpiod_flags(struct device_node *np,
return ERR_PTR(ret);
}
- chip = of_find_gpiochip_by_node(gpiospec.np);
+ chip = of_find_gpiochip_by_xlate(&gpiospec);
if (!chip) {
desc = ERR_PTR(-EPROBE_DEFER);
goto out;
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index f0fc3a0..93ed0e0 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -21,6 +21,7 @@
#include <linux/uaccess.h>
#include <linux/compat.h>
#include <linux/anon_inodes.h>
+#include <linux/file.h>
#include <linux/kfifo.h>
#include <linux/poll.h>
#include <linux/timekeeping.h>
@@ -333,6 +334,13 @@ struct linehandle_state {
u32 numdescs;
};
+#define GPIOHANDLE_REQUEST_VALID_FLAGS \
+ (GPIOHANDLE_REQUEST_INPUT | \
+ GPIOHANDLE_REQUEST_OUTPUT | \
+ GPIOHANDLE_REQUEST_ACTIVE_LOW | \
+ GPIOHANDLE_REQUEST_OPEN_DRAIN | \
+ GPIOHANDLE_REQUEST_OPEN_SOURCE)
+
static long linehandle_ioctl(struct file *filep, unsigned int cmd,
unsigned long arg)
{
@@ -344,6 +352,8 @@ static long linehandle_ioctl(struct file *filep, unsigned int cmd,
if (cmd == GPIOHANDLE_GET_LINE_VALUES_IOCTL) {
int val;
+ memset(&ghd, 0, sizeof(ghd));
+
/* TODO: check if descriptors are really input */
for (i = 0; i < lh->numdescs; i++) {
val = gpiod_get_value_cansleep(lh->descs[i]);
@@ -414,6 +424,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
{
struct gpiohandle_request handlereq;
struct linehandle_state *lh;
+ struct file *file;
int fd, i, ret;
if (copy_from_user(&handlereq, ip, sizeof(handlereq)))
@@ -444,6 +455,17 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
u32 lflags = handlereq.flags;
struct gpio_desc *desc;
+ if (offset >= gdev->ngpio) {
+ ret = -EINVAL;
+ goto out_free_descs;
+ }
+
+ /* Return an error if a unknown flag is set */
+ if (lflags & ~GPIOHANDLE_REQUEST_VALID_FLAGS) {
+ ret = -EINVAL;
+ goto out_free_descs;
+ }
+
desc = &gdev->descs[offset];
ret = gpiod_request(desc, lh->label);
if (ret)
@@ -479,26 +501,41 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
i--;
lh->numdescs = handlereq.lines;
- fd = anon_inode_getfd("gpio-linehandle",
- &linehandle_fileops,
- lh,
- O_RDONLY | O_CLOEXEC);
+ fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC);
if (fd < 0) {
ret = fd;
goto out_free_descs;
}
+ file = anon_inode_getfile("gpio-linehandle",
+ &linehandle_fileops,
+ lh,
+ O_RDONLY | O_CLOEXEC);
+ if (IS_ERR(file)) {
+ ret = PTR_ERR(file);
+ goto out_put_unused_fd;
+ }
+
handlereq.fd = fd;
if (copy_to_user(ip, &handlereq, sizeof(handlereq))) {
- ret = -EFAULT;
- goto out_free_descs;
+ /*
+ * fput() will trigger the release() callback, so do not go onto
+ * the regular error cleanup path here.
+ */
+ fput(file);
+ put_unused_fd(fd);
+ return -EFAULT;
}
+ fd_install(fd, file);
+
dev_dbg(&gdev->dev, "registered chardev handle for %d lines\n",
lh->numdescs);
return 0;
+out_put_unused_fd:
+ put_unused_fd(fd);
out_free_descs:
for (; i >= 0; i--)
gpiod_free(lh->descs[i]);
@@ -536,6 +573,10 @@ struct lineevent_state {
struct mutex read_lock;
};
+#define GPIOEVENT_REQUEST_VALID_FLAGS \
+ (GPIOEVENT_REQUEST_RISING_EDGE | \
+ GPIOEVENT_REQUEST_FALLING_EDGE)
+
static unsigned int lineevent_poll(struct file *filep,
struct poll_table_struct *wait)
{
@@ -623,6 +664,8 @@ static long lineevent_ioctl(struct file *filep, unsigned int cmd,
if (cmd == GPIOHANDLE_GET_LINE_VALUES_IOCTL) {
int val;
+ memset(&ghd, 0, sizeof(ghd));
+
val = gpiod_get_value_cansleep(le->desc);
if (val < 0)
return val;
@@ -695,6 +738,7 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
struct gpioevent_request eventreq;
struct lineevent_state *le;
struct gpio_desc *desc;
+ struct file *file;
u32 offset;
u32 lflags;
u32 eflags;
@@ -726,6 +770,18 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
lflags = eventreq.handleflags;
eflags = eventreq.eventflags;
+ if (offset >= gdev->ngpio) {
+ ret = -EINVAL;
+ goto out_free_label;
+ }
+
+ /* Return an error if a unknown flag is set */
+ if ((lflags & ~GPIOHANDLE_REQUEST_VALID_FLAGS) ||
+ (eflags & ~GPIOEVENT_REQUEST_VALID_FLAGS)) {
+ ret = -EINVAL;
+ goto out_free_label;
+ }
+
/* This is just wrong: we don't look for events on output lines */
if (lflags & GPIOHANDLE_REQUEST_OUTPUT) {
ret = -EINVAL;
@@ -777,23 +833,38 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
if (ret)
goto out_free_desc;
- fd = anon_inode_getfd("gpio-event",
- &lineevent_fileops,
- le,
- O_RDONLY | O_CLOEXEC);
+ fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC);
if (fd < 0) {
ret = fd;
goto out_free_irq;
}
+ file = anon_inode_getfile("gpio-event",
+ &lineevent_fileops,
+ le,
+ O_RDONLY | O_CLOEXEC);
+ if (IS_ERR(file)) {
+ ret = PTR_ERR(file);
+ goto out_put_unused_fd;
+ }
+
eventreq.fd = fd;
if (copy_to_user(ip, &eventreq, sizeof(eventreq))) {
- ret = -EFAULT;
- goto out_free_irq;
+ /*
+ * fput() will trigger the release() callback, so do not go onto
+ * the regular error cleanup path here.
+ */
+ fput(file);
+ put_unused_fd(fd);
+ return -EFAULT;
}
+ fd_install(fd, file);
+
return 0;
+out_put_unused_fd:
+ put_unused_fd(fd);
out_free_irq:
free_irq(le->irq, le);
out_free_desc:
@@ -823,6 +894,8 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
if (cmd == GPIO_GET_CHIPINFO_IOCTL) {
struct gpiochip_info chipinfo;
+ memset(&chipinfo, 0, sizeof(chipinfo));
+
strncpy(chipinfo.name, dev_name(&gdev->dev),
sizeof(chipinfo.name));
chipinfo.name[sizeof(chipinfo.name)-1] = '\0';
@@ -839,7 +912,7 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
if (copy_from_user(&lineinfo, ip, sizeof(lineinfo)))
return -EFAULT;
- if (lineinfo.line_offset > gdev->ngpio)
+ if (lineinfo.line_offset >= gdev->ngpio)
return -EINVAL;
desc = &gdev->descs[lineinfo.line_offset];
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index 892d60f..2057683 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -395,9 +395,12 @@ static int acp_hw_fini(void *handle)
{
int i, ret;
struct device *dev;
-
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ /* return early if no ACP */
+ if (!adev->acp.acp_genpd)
+ return 0;
+
for (i = 0; i < ACP_DEVS ; i++) {
dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
ret = pm_genpd_remove_device(&adev->acp.acp_genpd->gpd, dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index 7a8bfa3..6629762 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -795,10 +795,19 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
if (!adev->pm.fw) {
switch (adev->asic_type) {
case CHIP_TOPAZ:
- strcpy(fw_name, "amdgpu/topaz_smc.bin");
+ if (((adev->pdev->device == 0x6900) && (adev->pdev->revision == 0x81)) ||
+ ((adev->pdev->device == 0x6900) && (adev->pdev->revision == 0x83)) ||
+ ((adev->pdev->device == 0x6907) && (adev->pdev->revision == 0x87)))
+ strcpy(fw_name, "amdgpu/topaz_k_smc.bin");
+ else
+ strcpy(fw_name, "amdgpu/topaz_smc.bin");
break;
case CHIP_TONGA:
- strcpy(fw_name, "amdgpu/tonga_smc.bin");
+ if (((adev->pdev->device == 0x6939) && (adev->pdev->revision == 0xf1)) ||
+ ((adev->pdev->device == 0x6938) && (adev->pdev->revision == 0xf1)))
+ strcpy(fw_name, "amdgpu/tonga_k_smc.bin");
+ else
+ strcpy(fw_name, "amdgpu/tonga_smc.bin");
break;
case CHIP_FIJI:
strcpy(fw_name, "amdgpu/fiji_smc.bin");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 2e3a054..086aa5c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -765,14 +765,20 @@ amdgpu_connector_lvds_detect(struct drm_connector *connector, bool force)
return ret;
}
+static void amdgpu_connector_unregister(struct drm_connector *connector)
+{
+ struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
+
+ if (amdgpu_connector->ddc_bus && amdgpu_connector->ddc_bus->has_aux) {
+ drm_dp_aux_unregister(&amdgpu_connector->ddc_bus->aux);
+ amdgpu_connector->ddc_bus->has_aux = false;
+ }
+}
+
static void amdgpu_connector_destroy(struct drm_connector *connector)
{
struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
- if (amdgpu_connector->ddc_bus->has_aux) {
- drm_dp_aux_unregister(&amdgpu_connector->ddc_bus->aux);
- amdgpu_connector->ddc_bus->has_aux = false;
- }
amdgpu_connector_free_edid(connector);
kfree(amdgpu_connector->con_priv);
drm_connector_unregister(connector);
@@ -826,6 +832,7 @@ static const struct drm_connector_funcs amdgpu_connector_lvds_funcs = {
.dpms = drm_helper_connector_dpms,
.detect = amdgpu_connector_lvds_detect,
.fill_modes = drm_helper_probe_single_connector_modes,
+ .early_unregister = amdgpu_connector_unregister,
.destroy = amdgpu_connector_destroy,
.set_property = amdgpu_connector_set_lcd_property,
};
@@ -936,6 +943,7 @@ static const struct drm_connector_funcs amdgpu_connector_vga_funcs = {
.dpms = drm_helper_connector_dpms,
.detect = amdgpu_connector_vga_detect,
.fill_modes = drm_helper_probe_single_connector_modes,
+ .early_unregister = amdgpu_connector_unregister,
.destroy = amdgpu_connector_destroy,
.set_property = amdgpu_connector_set_property,
};
@@ -1203,6 +1211,7 @@ static const struct drm_connector_funcs amdgpu_connector_dvi_funcs = {
.detect = amdgpu_connector_dvi_detect,
.fill_modes = drm_helper_probe_single_connector_modes,
.set_property = amdgpu_connector_set_property,
+ .early_unregister = amdgpu_connector_unregister,
.destroy = amdgpu_connector_destroy,
.force = amdgpu_connector_dvi_force,
};
@@ -1493,6 +1502,7 @@ static const struct drm_connector_funcs amdgpu_connector_dp_funcs = {
.detect = amdgpu_connector_dp_detect,
.fill_modes = drm_helper_probe_single_connector_modes,
.set_property = amdgpu_connector_set_property,
+ .early_unregister = amdgpu_connector_unregister,
.destroy = amdgpu_connector_destroy,
.force = amdgpu_connector_dvi_force,
};
@@ -1502,6 +1512,7 @@ static const struct drm_connector_funcs amdgpu_connector_edp_funcs = {
.detect = amdgpu_connector_dp_detect,
.fill_modes = drm_helper_probe_single_connector_modes,
.set_property = amdgpu_connector_set_lcd_property,
+ .early_unregister = amdgpu_connector_unregister,
.destroy = amdgpu_connector_destroy,
.force = amdgpu_connector_dvi_force,
};
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index b0f6e69..82dc8d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -519,7 +519,8 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
r = ttm_eu_reserve_buffers(&p->ticket, &p->validated, true,
&duplicates);
if (unlikely(r != 0)) {
- DRM_ERROR("ttm_eu_reserve_buffers failed.\n");
+ if (r != -ERESTARTSYS)
+ DRM_ERROR("ttm_eu_reserve_buffers failed.\n");
goto error_free_pages;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index e203e55..a5e2fcb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -43,6 +43,9 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev, struct amdgpu_ctx *ctx)
ctx->rings[i].sequence = 1;
ctx->rings[i].fences = &ctx->fences[amdgpu_sched_jobs * i];
}
+
+ ctx->reset_counter = atomic_read(&adev->gpu_reset_counter);
+
/* create context entity for each ring */
for (i = 0; i < adev->num_rings; i++) {
struct amdgpu_ring *ring = adev->rings[i];
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7dbe85d..7ca07e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1408,16 +1408,6 @@ static int amdgpu_late_init(struct amdgpu_device *adev)
for (i = 0; i < adev->num_ip_blocks; i++) {
if (!adev->ip_block_status[i].valid)
continue;
- if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_UVD ||
- adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_VCE)
- continue;
- /* enable clockgating to save power */
- r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
- AMD_CG_STATE_GATE);
- if (r) {
- DRM_ERROR("set_clockgating_state(gate) of IP block <%s> failed %d\n", adev->ip_blocks[i].funcs->name, r);
- return r;
- }
if (adev->ip_blocks[i].funcs->late_init) {
r = adev->ip_blocks[i].funcs->late_init((void *)adev);
if (r) {
@@ -1426,6 +1416,18 @@ static int amdgpu_late_init(struct amdgpu_device *adev)
}
adev->ip_block_status[i].late_initialized = true;
}
+ /* skip CG for VCE/UVD, it's handled specially */
+ if (adev->ip_blocks[i].type != AMD_IP_BLOCK_TYPE_UVD &&
+ adev->ip_blocks[i].type != AMD_IP_BLOCK_TYPE_VCE) {
+ /* enable clockgating to save power */
+ r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
+ AMD_CG_STATE_GATE);
+ if (r) {
+ DRM_ERROR("set_clockgating_state(gate) of IP block <%s> failed %d\n",
+ adev->ip_blocks[i].funcs->name, r);
+ return r;
+ }
+ }
}
return 0;
@@ -1435,6 +1437,30 @@ static int amdgpu_fini(struct amdgpu_device *adev)
{
int i, r;
+ /* need to disable SMC first */
+ for (i = 0; i < adev->num_ip_blocks; i++) {
+ if (!adev->ip_block_status[i].hw)
+ continue;
+ if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_SMC) {
+ /* ungate blocks before hw fini so that we can shutdown the blocks safely */
+ r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
+ AMD_CG_STATE_UNGATE);
+ if (r) {
+ DRM_ERROR("set_clockgating_state(ungate) of IP block <%s> failed %d\n",
+ adev->ip_blocks[i].funcs->name, r);
+ return r;
+ }
+ r = adev->ip_blocks[i].funcs->hw_fini((void *)adev);
+ /* XXX handle errors */
+ if (r) {
+ DRM_DEBUG("hw_fini of IP block <%s> failed %d\n",
+ adev->ip_blocks[i].funcs->name, r);
+ }
+ adev->ip_block_status[i].hw = false;
+ break;
+ }
+ }
+
for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
if (!adev->ip_block_status[i].hw)
continue;
@@ -1933,6 +1959,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
/* evict remaining vram memory */
amdgpu_bo_evict_vram(adev);
+ amdgpu_atombios_scratch_regs_save(adev);
pci_save_state(dev->pdev);
if (suspend) {
/* Shut down the device */
@@ -1984,6 +2011,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
return r;
}
}
+ amdgpu_atombios_scratch_regs_restore(adev);
/* post card */
if (!amdgpu_card_posted(adev) || !resume) {
@@ -2073,7 +2101,8 @@ static bool amdgpu_check_soft_reset(struct amdgpu_device *adev)
if (!adev->ip_block_status[i].valid)
continue;
if (adev->ip_blocks[i].funcs->check_soft_reset)
- adev->ip_blocks[i].funcs->check_soft_reset(adev);
+ adev->ip_block_status[i].hang =
+ adev->ip_blocks[i].funcs->check_soft_reset(adev);
if (adev->ip_block_status[i].hang) {
DRM_INFO("IP block:%d is hang!\n", i);
asic_hang = true;
@@ -2102,12 +2131,20 @@ static int amdgpu_pre_soft_reset(struct amdgpu_device *adev)
static bool amdgpu_need_full_reset(struct amdgpu_device *adev)
{
- if (adev->ip_block_status[AMD_IP_BLOCK_TYPE_GMC].hang ||
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_SMC].hang ||
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_ACP].hang ||
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_DCE].hang) {
- DRM_INFO("Some block need full reset!\n");
- return true;
+ int i;
+
+ for (i = 0; i < adev->num_ip_blocks; i++) {
+ if (!adev->ip_block_status[i].valid)
+ continue;
+ if ((adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_GMC) ||
+ (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_SMC) ||
+ (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_ACP) ||
+ (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_DCE)) {
+ if (adev->ip_block_status[i].hang) {
+ DRM_INFO("Some block need full reset!\n");
+ return true;
+ }
+ }
}
return false;
}
@@ -2233,8 +2270,6 @@ int amdgpu_gpu_reset(struct amdgpu_device *adev)
}
if (need_full_reset) {
- /* save scratch */
- amdgpu_atombios_scratch_regs_save(adev);
r = amdgpu_suspend(adev);
retry:
@@ -2244,8 +2279,9 @@ int amdgpu_gpu_reset(struct amdgpu_device *adev)
amdgpu_display_stop_mc_access(adev, &save);
amdgpu_wait_for_idle(adev, AMD_IP_BLOCK_TYPE_GMC);
}
-
+ amdgpu_atombios_scratch_regs_save(adev);
r = amdgpu_asic_reset(adev);
+ amdgpu_atombios_scratch_regs_restore(adev);
/* post card */
amdgpu_atom_asic_init(adev->mode_info.atom_context);
@@ -2253,8 +2289,6 @@ int amdgpu_gpu_reset(struct amdgpu_device *adev)
dev_info(adev->dev, "GPU reset succeeded, trying to resume\n");
r = amdgpu_resume(adev);
}
- /* restore scratch */
- amdgpu_atombios_scratch_regs_restore(adev);
}
if (!r) {
amdgpu_irq_gpu_reset_resume_helper(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
index fe36caf..14f57d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
@@ -113,24 +113,26 @@ void amdgpu_dpm_print_ps_status(struct amdgpu_device *adev,
printk("\n");
}
+
u32 amdgpu_dpm_get_vblank_time(struct amdgpu_device *adev)
{
struct drm_device *dev = adev->ddev;
struct drm_crtc *crtc;
struct amdgpu_crtc *amdgpu_crtc;
- u32 line_time_us, vblank_lines;
+ u32 vblank_in_pixels;
u32 vblank_time_us = 0xffffffff; /* if the displays are off, vblank time is max */
if (adev->mode_info.num_crtc && adev->mode_info.mode_config_initialized) {
list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
amdgpu_crtc = to_amdgpu_crtc(crtc);
if (crtc->enabled && amdgpu_crtc->enabled && amdgpu_crtc->hw_mode.clock) {
- line_time_us = (amdgpu_crtc->hw_mode.crtc_htotal * 1000) /
- amdgpu_crtc->hw_mode.clock;
- vblank_lines = amdgpu_crtc->hw_mode.crtc_vblank_end -
+ vblank_in_pixels =
+ amdgpu_crtc->hw_mode.crtc_htotal *
+ (amdgpu_crtc->hw_mode.crtc_vblank_end -
amdgpu_crtc->hw_mode.crtc_vdisplay +
- (amdgpu_crtc->v_border * 2);
- vblank_time_us = vblank_lines * line_time_us;
+ (amdgpu_crtc->v_border * 2));
+
+ vblank_time_us = vblank_in_pixels * 1000 / amdgpu_crtc->hw_mode.clock;
break;
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 71ed27e..02ff0747 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -735,8 +735,20 @@ static struct pci_driver amdgpu_kms_pci_driver = {
static int __init amdgpu_init(void)
{
- amdgpu_sync_init();
- amdgpu_fence_slab_init();
+ int r;
+
+ r = amdgpu_sync_init();
+ if (r)
+ goto error_sync;
+
+ r = amdgpu_fence_slab_init();
+ if (r)
+ goto error_fence;
+
+ r = amd_sched_fence_slab_init();
+ if (r)
+ goto error_sched;
+
if (vgacon_text_force()) {
DRM_ERROR("VGACON disables amdgpu kernel modesetting.\n");
return -EINVAL;
@@ -748,6 +760,15 @@ static int __init amdgpu_init(void)
amdgpu_register_atpx_handler();
/* let modprobe override vga console setting */
return drm_pci_init(driver, pdriver);
+
+error_sched:
+ amdgpu_fence_slab_fini();
+
+error_fence:
+ amdgpu_sync_fini();
+
+error_sync:
+ return r;
}
static void __exit amdgpu_exit(void)
@@ -756,6 +777,7 @@ static void __exit amdgpu_exit(void)
drm_pci_exit(driver, pdriver);
amdgpu_unregister_atpx_handler();
amdgpu_sync_fini();
+ amd_sched_fence_slab_fini();
amdgpu_fence_slab_fini();
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 3a2e42f..77b34ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -68,6 +68,7 @@ int amdgpu_fence_slab_init(void)
void amdgpu_fence_slab_fini(void)
{
+ rcu_barrier();
kmem_cache_destroy(amdgpu_fence_slab);
}
/*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 278708f..9fa8098 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -239,6 +239,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
if (r) {
adev->irq.installed = false;
flush_work(&adev->hotplug_work);
+ cancel_work_sync(&adev->reset_work);
return r;
}
@@ -264,6 +265,7 @@ void amdgpu_irq_fini(struct amdgpu_device *adev)
if (adev->irq.msi_enabled)
pci_disable_msi(adev->pdev);
flush_work(&adev->hotplug_work);
+ cancel_work_sync(&adev->reset_work);
}
for (i = 0; i < AMDGPU_MAX_IRQ_SRC_ID; ++i) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index c2c7fb1..3938fca 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -99,6 +99,8 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
if ((amdgpu_runtime_pm != 0) &&
amdgpu_has_atpx() &&
+ (amdgpu_is_atpx_hybrid() ||
+ amdgpu_has_atpx_dgpu_power_cntl()) &&
((flags & AMD_IS_APU) == 0))
flags |= AMD_IS_PX;
@@ -459,10 +461,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
/* return all clocks in KHz */
dev_info.gpu_counter_freq = amdgpu_asic_get_xclk(adev) * 10;
if (adev->pm.dpm_enabled) {
- dev_info.max_engine_clock =
- adev->pm.dpm.dyn_state.max_clock_voltage_on_ac.sclk * 10;
- dev_info.max_memory_clock =
- adev->pm.dpm.dyn_state.max_clock_voltage_on_ac.mclk * 10;
+ dev_info.max_engine_clock = amdgpu_dpm_get_sclk(adev, false) * 10;
+ dev_info.max_memory_clock = amdgpu_dpm_get_mclk(adev, false) * 10;
} else {
dev_info.max_engine_clock = adev->pm.default_sclk * 10;
dev_info.max_memory_clock = adev->pm.default_mclk * 10;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index aa074fa..f3efb1c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -754,6 +754,10 @@ static const char *amdgpu_vram_names[] = {
int amdgpu_bo_init(struct amdgpu_device *adev)
{
+ /* reserve PAT memory space to WC for VRAM */
+ arch_io_reserve_memtype_wc(adev->mc.aper_base,
+ adev->mc.aper_size);
+
/* Add an MTRR for the VRAM */
adev->mc.vram_mtrr = arch_phys_wc_add(adev->mc.aper_base,
adev->mc.aper_size);
@@ -769,6 +773,7 @@ void amdgpu_bo_fini(struct amdgpu_device *adev)
{
amdgpu_ttm_fini(adev);
arch_phys_wc_del(adev->mc.vram_mtrr);
+ arch_io_free_memtype_wc(adev->mc.aper_base, adev->mc.aper_size);
}
int amdgpu_bo_fbdev_mmap(struct amdgpu_bo *bo,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index e1fa873..3cb5e90 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -345,8 +345,8 @@ static int amdgpu_debugfs_ring_init(struct amdgpu_device *adev,
ent = debugfs_create_file(name,
S_IFREG | S_IRUGO, root,
ring, &amdgpu_debugfs_ring_fops);
- if (IS_ERR(ent))
- return PTR_ERR(ent);
+ if (!ent)
+ return -ENOMEM;
i_size_write(ent->d_inode, ring->ring_size + 12);
ring->ent = ent;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 887483b..dcaf691 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -555,10 +555,13 @@ struct amdgpu_ttm_tt {
int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
{
struct amdgpu_ttm_tt *gtt = (void *)ttm;
- int write = !(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY);
+ unsigned int flags = 0;
unsigned pinned = 0;
int r;
+ if (!(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY))
+ flags |= FOLL_WRITE;
+
if (gtt->userflags & AMDGPU_GEM_USERPTR_ANONONLY) {
/* check that we only use anonymous memory
to prevent problems with writeback */
@@ -581,7 +584,7 @@ int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
list_add(&guptask.list, >t->guptasks);
spin_unlock(>t->guptasklock);
- r = get_user_pages(userptr, num_pages, write, 0, p, NULL);
+ r = get_user_pages(userptr, num_pages, flags, p, NULL);
spin_lock(>t->guptasklock);
list_del(&guptask.list);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 06f2432..968c426 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1758,5 +1758,6 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev)
fence_put(adev->vm_manager.ids[i].first);
amdgpu_sync_free(&adev->vm_manager.ids[i].active);
fence_put(id->flushed_updates);
+ fence_put(id->last_flush);
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index 1d8c375..5be788b 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -4075,7 +4075,7 @@ static int ci_enable_uvd_dpm(struct amdgpu_device *adev, bool enable)
pi->dpm_level_enable_mask.mclk_dpm_enable_mask);
}
} else {
- if (pi->last_mclk_dpm_enable_mask & 0x1) {
+ if (pi->uvd_enabled) {
pi->uvd_enabled = false;
pi->dpm_level_enable_mask.mclk_dpm_enable_mask |= 1;
amdgpu_ci_send_msg_to_smc_with_parameter(adev,
@@ -6236,6 +6236,8 @@ static int ci_dpm_sw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ flush_work(&adev->pm.dpm.thermal.work);
+
mutex_lock(&adev->pm.mutex);
amdgpu_pm_sysfs_fini(adev);
ci_dpm_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
index f80a083..3c082e14 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
@@ -1514,14 +1514,16 @@ static int cz_dpm_set_powergating_state(void *handle,
return 0;
}
-/* borrowed from KV, need future unify */
static int cz_dpm_get_temperature(struct amdgpu_device *adev)
{
int actual_temp = 0;
- uint32_t temp = RREG32_SMC(0xC0300E0C);
+ uint32_t val = RREG32_SMC(ixTHM_TCON_CUR_TMP);
+ uint32_t temp = REG_GET_FIELD(val, THM_TCON_CUR_TMP, CUR_TEMP);
- if (temp)
+ if (REG_GET_FIELD(val, THM_TCON_CUR_TMP, CUR_TEMP_RANGE_SEL))
actual_temp = 1000 * ((temp / 8) - 49);
+ else
+ actual_temp = 1000 * (temp / 8);
return actual_temp;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 613ebb7..9260cae 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -3151,10 +3151,6 @@ static int dce_v10_0_hw_fini(void *handle)
static int dce_v10_0_suspend(void *handle)
{
- struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
- amdgpu_atombios_scratch_regs_save(adev);
-
return dce_v10_0_hw_fini(handle);
}
@@ -3165,8 +3161,6 @@ static int dce_v10_0_resume(void *handle)
ret = dce_v10_0_hw_init(handle);
- amdgpu_atombios_scratch_regs_restore(adev);
-
/* turn on the BL */
if (adev->mode_info.bl_encoder) {
u8 bl_level = amdgpu_display_backlight_get_level(adev,
@@ -3188,16 +3182,11 @@ static int dce_v10_0_wait_for_idle(void *handle)
return 0;
}
-static int dce_v10_0_check_soft_reset(void *handle)
+static bool dce_v10_0_check_soft_reset(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (dce_v10_0_is_display_hung(adev))
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_DCE].hang = true;
- else
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_DCE].hang = false;
-
- return 0;
+ return dce_v10_0_is_display_hung(adev);
}
static int dce_v10_0_soft_reset(void *handle)
@@ -3205,9 +3194,6 @@ static int dce_v10_0_soft_reset(void *handle)
u32 srbm_soft_reset = 0, tmp;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_DCE].hang)
- return 0;
-
if (dce_v10_0_is_display_hung(adev))
srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_DC_MASK;
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index f264b8f..367739b 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -3215,10 +3215,6 @@ static int dce_v11_0_hw_fini(void *handle)
static int dce_v11_0_suspend(void *handle)
{
- struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
- amdgpu_atombios_scratch_regs_save(adev);
-
return dce_v11_0_hw_fini(handle);
}
@@ -3229,8 +3225,6 @@ static int dce_v11_0_resume(void *handle)
ret = dce_v11_0_hw_init(handle);
- amdgpu_atombios_scratch_regs_restore(adev);
-
/* turn on the BL */
if (adev->mode_info.bl_encoder) {
u8 bl_level = amdgpu_display_backlight_get_level(adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index b948d6c..15f9fc0 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -2482,10 +2482,6 @@ static int dce_v6_0_hw_fini(void *handle)
static int dce_v6_0_suspend(void *handle)
{
- struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
- amdgpu_atombios_scratch_regs_save(adev);
-
return dce_v6_0_hw_fini(handle);
}
@@ -2496,8 +2492,6 @@ static int dce_v6_0_resume(void *handle)
ret = dce_v6_0_hw_init(handle);
- amdgpu_atombios_scratch_regs_restore(adev);
-
/* turn on the BL */
if (adev->mode_info.bl_encoder) {
u8 bl_level = amdgpu_display_backlight_get_level(adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 5966166..8c4d808 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -3033,10 +3033,6 @@ static int dce_v8_0_hw_fini(void *handle)
static int dce_v8_0_suspend(void *handle)
{
- struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
- amdgpu_atombios_scratch_regs_save(adev);
-
return dce_v8_0_hw_fini(handle);
}
@@ -3047,8 +3043,6 @@ static int dce_v8_0_resume(void *handle)
ret = dce_v8_0_hw_init(handle);
- amdgpu_atombios_scratch_regs_restore(adev);
-
/* turn on the BL */
if (adev->mode_info.bl_encoder) {
u8 bl_level = amdgpu_display_backlight_get_level(adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 6c6ff57..bb97182 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -640,7 +640,6 @@ static const u32 stoney_mgcg_cgcg_init[] =
mmCP_MEM_SLP_CNTL, 0xffffffff, 0x00020201,
mmRLC_MEM_SLP_CNTL, 0xffffffff, 0x00020201,
mmCGTS_SM_CTRL_REG, 0xffffffff, 0x96940200,
- mmATC_MISC_CG, 0xffffffff, 0x000c0200,
};
static void gfx_v8_0_set_ring_funcs(struct amdgpu_device *adev);
@@ -4087,14 +4086,21 @@ static int gfx_v8_0_rlc_load_microcode(struct amdgpu_device *adev)
static int gfx_v8_0_rlc_resume(struct amdgpu_device *adev)
{
int r;
+ u32 tmp;
gfx_v8_0_rlc_stop(adev);
/* disable CG */
- WREG32(mmRLC_CGCG_CGLS_CTRL, 0);
+ tmp = RREG32(mmRLC_CGCG_CGLS_CTRL);
+ tmp &= ~(RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK |
+ RLC_CGCG_CGLS_CTRL__CGLS_EN_MASK);
+ WREG32(mmRLC_CGCG_CGLS_CTRL, tmp);
if (adev->asic_type == CHIP_POLARIS11 ||
- adev->asic_type == CHIP_POLARIS10)
- WREG32(mmRLC_CGCG_CGLS_CTRL_3D, 0);
+ adev->asic_type == CHIP_POLARIS10) {
+ tmp = RREG32(mmRLC_CGCG_CGLS_CTRL_3D);
+ tmp &= ~0x3;
+ WREG32(mmRLC_CGCG_CGLS_CTRL_3D, tmp);
+ }
/* disable PG */
WREG32(mmRLC_PG_CNTL, 0);
@@ -5137,7 +5143,7 @@ static int gfx_v8_0_wait_for_idle(void *handle)
return -ETIMEDOUT;
}
-static int gfx_v8_0_check_soft_reset(void *handle)
+static bool gfx_v8_0_check_soft_reset(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
@@ -5189,16 +5195,14 @@ static int gfx_v8_0_check_soft_reset(void *handle)
SRBM_SOFT_RESET, SOFT_RESET_SEM, 1);
if (grbm_soft_reset || srbm_soft_reset) {
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_GFX].hang = true;
adev->gfx.grbm_soft_reset = grbm_soft_reset;
adev->gfx.srbm_soft_reset = srbm_soft_reset;
+ return true;
} else {
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_GFX].hang = false;
adev->gfx.grbm_soft_reset = 0;
adev->gfx.srbm_soft_reset = 0;
+ return false;
}
-
- return 0;
}
static void gfx_v8_0_inactive_hqd(struct amdgpu_device *adev,
@@ -5226,7 +5230,8 @@ static int gfx_v8_0_pre_soft_reset(void *handle)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_GFX].hang)
+ if ((!adev->gfx.grbm_soft_reset) &&
+ (!adev->gfx.srbm_soft_reset))
return 0;
grbm_soft_reset = adev->gfx.grbm_soft_reset;
@@ -5264,7 +5269,8 @@ static int gfx_v8_0_soft_reset(void *handle)
u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
u32 tmp;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_GFX].hang)
+ if ((!adev->gfx.grbm_soft_reset) &&
+ (!adev->gfx.srbm_soft_reset))
return 0;
grbm_soft_reset = adev->gfx.grbm_soft_reset;
@@ -5334,7 +5340,8 @@ static int gfx_v8_0_post_soft_reset(void *handle)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
u32 grbm_soft_reset = 0, srbm_soft_reset = 0;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_GFX].hang)
+ if ((!adev->gfx.grbm_soft_reset) &&
+ (!adev->gfx.srbm_soft_reset))
return 0;
grbm_soft_reset = adev->gfx.grbm_soft_reset;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 1b319f5..a16b220 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -100,6 +100,7 @@ static const u32 cz_mgcg_cgcg_init[] =
static const u32 stoney_mgcg_cgcg_init[] =
{
+ mmATC_MISC_CG, 0xffffffff, 0x000c0200,
mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104
};
@@ -1099,7 +1100,7 @@ static int gmc_v8_0_wait_for_idle(void *handle)
}
-static int gmc_v8_0_check_soft_reset(void *handle)
+static bool gmc_v8_0_check_soft_reset(void *handle)
{
u32 srbm_soft_reset = 0;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1116,20 +1117,19 @@ static int gmc_v8_0_check_soft_reset(void *handle)
SRBM_SOFT_RESET, SOFT_RESET_MC, 1);
}
if (srbm_soft_reset) {
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_GMC].hang = true;
adev->mc.srbm_soft_reset = srbm_soft_reset;
+ return true;
} else {
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_GMC].hang = false;
adev->mc.srbm_soft_reset = 0;
+ return false;
}
- return 0;
}
static int gmc_v8_0_pre_soft_reset(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_GMC].hang)
+ if (!adev->mc.srbm_soft_reset)
return 0;
gmc_v8_0_mc_stop(adev, &adev->mc.save);
@@ -1145,7 +1145,7 @@ static int gmc_v8_0_soft_reset(void *handle)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
u32 srbm_soft_reset;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_GMC].hang)
+ if (!adev->mc.srbm_soft_reset)
return 0;
srbm_soft_reset = adev->mc.srbm_soft_reset;
@@ -1175,7 +1175,7 @@ static int gmc_v8_0_post_soft_reset(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_GMC].hang)
+ if (!adev->mc.srbm_soft_reset)
return 0;
gmc_v8_0_mc_resume(adev, &adev->mc.save);
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index f8618a3..71d2856 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -3063,6 +3063,8 @@ static int kv_dpm_sw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ flush_work(&adev->pm.dpm.thermal.work);
+
mutex_lock(&adev->pm.mutex);
amdgpu_pm_sysfs_fini(adev);
kv_dpm_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index f325fd8..a9d1094 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -1268,7 +1268,7 @@ static int sdma_v3_0_wait_for_idle(void *handle)
return -ETIMEDOUT;
}
-static int sdma_v3_0_check_soft_reset(void *handle)
+static bool sdma_v3_0_check_soft_reset(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
u32 srbm_soft_reset = 0;
@@ -1281,14 +1281,12 @@ static int sdma_v3_0_check_soft_reset(void *handle)
}
if (srbm_soft_reset) {
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_SDMA].hang = true;
adev->sdma.srbm_soft_reset = srbm_soft_reset;
+ return true;
} else {
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_SDMA].hang = false;
adev->sdma.srbm_soft_reset = 0;
+ return false;
}
-
- return 0;
}
static int sdma_v3_0_pre_soft_reset(void *handle)
@@ -1296,7 +1294,7 @@ static int sdma_v3_0_pre_soft_reset(void *handle)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
u32 srbm_soft_reset = 0;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_SDMA].hang)
+ if (!adev->sdma.srbm_soft_reset)
return 0;
srbm_soft_reset = adev->sdma.srbm_soft_reset;
@@ -1315,7 +1313,7 @@ static int sdma_v3_0_post_soft_reset(void *handle)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
u32 srbm_soft_reset = 0;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_SDMA].hang)
+ if (!adev->sdma.srbm_soft_reset)
return 0;
srbm_soft_reset = adev->sdma.srbm_soft_reset;
@@ -1335,7 +1333,7 @@ static int sdma_v3_0_soft_reset(void *handle)
u32 srbm_soft_reset = 0;
u32 tmp;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_SDMA].hang)
+ if (!adev->sdma.srbm_soft_reset)
return 0;
srbm_soft_reset = adev->sdma.srbm_soft_reset;
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index 8bd0892..d6f85b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -3477,6 +3477,49 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
int i;
struct si_dpm_quirk *p = si_dpm_quirk_list;
+ /* limit all SI kickers */
+ if (adev->asic_type == CHIP_PITCAIRN) {
+ if ((adev->pdev->revision == 0x81) ||
+ (adev->pdev->device == 0x6810) ||
+ (adev->pdev->device == 0x6811) ||
+ (adev->pdev->device == 0x6816) ||
+ (adev->pdev->device == 0x6817) ||
+ (adev->pdev->device == 0x6806))
+ max_mclk = 120000;
+ } else if (adev->asic_type == CHIP_VERDE) {
+ if ((adev->pdev->revision == 0x81) ||
+ (adev->pdev->revision == 0x83) ||
+ (adev->pdev->revision == 0x87) ||
+ (adev->pdev->device == 0x6820) ||
+ (adev->pdev->device == 0x6821) ||
+ (adev->pdev->device == 0x6822) ||
+ (adev->pdev->device == 0x6823) ||
+ (adev->pdev->device == 0x682A) ||
+ (adev->pdev->device == 0x682B)) {
+ max_sclk = 75000;
+ max_mclk = 80000;
+ }
+ } else if (adev->asic_type == CHIP_OLAND) {
+ if ((adev->pdev->revision == 0xC7) ||
+ (adev->pdev->revision == 0x80) ||
+ (adev->pdev->revision == 0x81) ||
+ (adev->pdev->revision == 0x83) ||
+ (adev->pdev->device == 0x6604) ||
+ (adev->pdev->device == 0x6605)) {
+ max_sclk = 75000;
+ max_mclk = 80000;
+ }
+ } else if (adev->asic_type == CHIP_HAINAN) {
+ if ((adev->pdev->revision == 0x81) ||
+ (adev->pdev->revision == 0x83) ||
+ (adev->pdev->revision == 0xC3) ||
+ (adev->pdev->device == 0x6664) ||
+ (adev->pdev->device == 0x6665) ||
+ (adev->pdev->device == 0x6667)) {
+ max_sclk = 75000;
+ max_mclk = 80000;
+ }
+ }
/* Apply dpm quirks */
while (p && p->chip_device != 0) {
if (adev->pdev->vendor == p->chip_vendor &&
@@ -3489,16 +3532,6 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
}
++p;
}
- /* limit mclk on all R7 370 parts for stability */
- if (adev->pdev->device == 0x6811 &&
- adev->pdev->revision == 0x81)
- max_mclk = 120000;
- /* limit sclk/mclk on Jet parts for stability */
- if (adev->pdev->device == 0x6665 &&
- adev->pdev->revision == 0xc3) {
- max_sclk = 75000;
- max_mclk = 80000;
- }
if (rps->vce_active) {
rps->evclk = adev->pm.dpm.vce_states[adev->pm.dpm.vce_level].evclk;
@@ -7771,6 +7804,8 @@ static int si_dpm_sw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ flush_work(&adev->pm.dpm.thermal.work);
+
mutex_lock(&adev->pm.mutex);
amdgpu_pm_sysfs_fini(adev);
si_dpm_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
index d127d59..b4ea229 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
@@ -373,7 +373,7 @@ static int tonga_ih_wait_for_idle(void *handle)
return -ETIMEDOUT;
}
-static int tonga_ih_check_soft_reset(void *handle)
+static bool tonga_ih_check_soft_reset(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
u32 srbm_soft_reset = 0;
@@ -384,21 +384,19 @@ static int tonga_ih_check_soft_reset(void *handle)
SOFT_RESET_IH, 1);
if (srbm_soft_reset) {
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_IH].hang = true;
adev->irq.srbm_soft_reset = srbm_soft_reset;
+ return true;
} else {
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_IH].hang = false;
adev->irq.srbm_soft_reset = 0;
+ return false;
}
-
- return 0;
}
static int tonga_ih_pre_soft_reset(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_IH].hang)
+ if (!adev->irq.srbm_soft_reset)
return 0;
return tonga_ih_hw_fini(adev);
@@ -408,7 +406,7 @@ static int tonga_ih_post_soft_reset(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_IH].hang)
+ if (!adev->irq.srbm_soft_reset)
return 0;
return tonga_ih_hw_init(adev);
@@ -419,7 +417,7 @@ static int tonga_ih_soft_reset(void *handle)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
u32 srbm_soft_reset;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_IH].hang)
+ if (!adev->irq.srbm_soft_reset)
return 0;
srbm_soft_reset = adev->irq.srbm_soft_reset;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index e0fd9f2..ab3df6d 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -770,7 +770,7 @@ static int uvd_v6_0_wait_for_idle(void *handle)
}
#define AMDGPU_UVD_STATUS_BUSY_MASK 0xfd
-static int uvd_v6_0_check_soft_reset(void *handle)
+static bool uvd_v6_0_check_soft_reset(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
u32 srbm_soft_reset = 0;
@@ -782,19 +782,19 @@ static int uvd_v6_0_check_soft_reset(void *handle)
srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_UVD, 1);
if (srbm_soft_reset) {
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_UVD].hang = true;
adev->uvd.srbm_soft_reset = srbm_soft_reset;
+ return true;
} else {
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_UVD].hang = false;
adev->uvd.srbm_soft_reset = 0;
+ return false;
}
- return 0;
}
+
static int uvd_v6_0_pre_soft_reset(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_UVD].hang)
+ if (!adev->uvd.srbm_soft_reset)
return 0;
uvd_v6_0_stop(adev);
@@ -806,7 +806,7 @@ static int uvd_v6_0_soft_reset(void *handle)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
u32 srbm_soft_reset;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_UVD].hang)
+ if (!adev->uvd.srbm_soft_reset)
return 0;
srbm_soft_reset = adev->uvd.srbm_soft_reset;
@@ -836,7 +836,7 @@ static int uvd_v6_0_post_soft_reset(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_UVD].hang)
+ if (!adev->uvd.srbm_soft_reset)
return 0;
mdelay(5);
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 3f6db4e..6feed72 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -52,6 +52,8 @@
#define VCE_V3_0_STACK_SIZE (64 * 1024)
#define VCE_V3_0_DATA_SIZE ((16 * 1024 * AMDGPU_MAX_VCE_HANDLES) + (52 * 1024))
+#define FW_52_8_3 ((52 << 24) | (8 << 16) | (3 << 8))
+
static void vce_v3_0_mc_resume(struct amdgpu_device *adev, int idx);
static void vce_v3_0_set_ring_funcs(struct amdgpu_device *adev);
static void vce_v3_0_set_irq_funcs(struct amdgpu_device *adev);
@@ -382,6 +384,10 @@ static int vce_v3_0_sw_init(void *handle)
if (r)
return r;
+ /* 52.8.3 required for 3 ring support */
+ if (adev->vce.fw_version < FW_52_8_3)
+ adev->vce.num_rings = 2;
+
r = amdgpu_vce_resume(adev);
if (r)
return r;
@@ -561,7 +567,7 @@ static int vce_v3_0_wait_for_idle(void *handle)
#define AMDGPU_VCE_STATUS_BUSY_MASK (VCE_STATUS_VCPU_REPORT_AUTO_BUSY_MASK | \
VCE_STATUS_VCPU_REPORT_RB0_BUSY_MASK)
-static int vce_v3_0_check_soft_reset(void *handle)
+static bool vce_v3_0_check_soft_reset(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
u32 srbm_soft_reset = 0;
@@ -591,16 +597,15 @@ static int vce_v3_0_check_soft_reset(void *handle)
srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE1, 1);
}
WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0);
+ mutex_unlock(&adev->grbm_idx_mutex);
if (srbm_soft_reset) {
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_VCE].hang = true;
adev->vce.srbm_soft_reset = srbm_soft_reset;
+ return true;
} else {
- adev->ip_block_status[AMD_IP_BLOCK_TYPE_VCE].hang = false;
adev->vce.srbm_soft_reset = 0;
+ return false;
}
- mutex_unlock(&adev->grbm_idx_mutex);
- return 0;
}
static int vce_v3_0_soft_reset(void *handle)
@@ -608,7 +613,7 @@ static int vce_v3_0_soft_reset(void *handle)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
u32 srbm_soft_reset;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_VCE].hang)
+ if (!adev->vce.srbm_soft_reset)
return 0;
srbm_soft_reset = adev->vce.srbm_soft_reset;
@@ -638,7 +643,7 @@ static int vce_v3_0_pre_soft_reset(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_VCE].hang)
+ if (!adev->vce.srbm_soft_reset)
return 0;
mdelay(5);
@@ -651,7 +656,7 @@ static int vce_v3_0_post_soft_reset(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- if (!adev->ip_block_status[AMD_IP_BLOCK_TYPE_VCE].hang)
+ if (!adev->vce.srbm_soft_reset)
return 0;
mdelay(5);
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index c0d9aad..f62f1a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -80,7 +80,9 @@
#include "dce_virtual.h"
MODULE_FIRMWARE("amdgpu/topaz_smc.bin");
+MODULE_FIRMWARE("amdgpu/topaz_k_smc.bin");
MODULE_FIRMWARE("amdgpu/tonga_smc.bin");
+MODULE_FIRMWARE("amdgpu/tonga_k_smc.bin");
MODULE_FIRMWARE("amdgpu/fiji_smc.bin");
MODULE_FIRMWARE("amdgpu/polaris10_smc.bin");
MODULE_FIRMWARE("amdgpu/polaris10_smc_sk.bin");
@@ -1651,7 +1653,7 @@ static int vi_common_early_init(void *handle)
AMD_CG_SUPPORT_SDMA_MGCG |
AMD_CG_SUPPORT_SDMA_LS |
AMD_CG_SUPPORT_VCE_MGCG;
- adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |
+ adev->pg_flags = AMD_PG_SUPPORT_GFX_PG |
AMD_PG_SUPPORT_GFX_SMG |
AMD_PG_SUPPORT_GFX_PIPELINE |
AMD_PG_SUPPORT_UVD |
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index c934b78c..bec8125 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -165,7 +165,7 @@ struct amd_ip_funcs {
/* poll for idle */
int (*wait_for_idle)(void *handle);
/* check soft reset the IP block */
- int (*check_soft_reset)(void *handle);
+ bool (*check_soft_reset)(void *handle);
/* pre soft reset the IP block */
int (*pre_soft_reset)(void *handle);
/* soft reset the IP block */
diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c
index 92b1178..8cee4e0 100644
--- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c
+++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c
@@ -49,6 +49,7 @@ static const pem_event_action * const uninitialize_event[] = {
uninitialize_display_phy_access_tasks,
disable_gfx_voltage_island_power_gating_tasks,
disable_gfx_clock_gating_tasks,
+ uninitialize_thermal_controller_tasks,
set_boot_state_tasks,
adjust_power_state_tasks,
disable_dynamic_state_management_tasks,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
index 7e4fcbb..9604249 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
@@ -1785,6 +1785,21 @@ static int cz_get_max_high_clocks(struct pp_hwmgr *hwmgr, struct amd_pp_simple_c
return 0;
}
+static int cz_thermal_get_temperature(struct pp_hwmgr *hwmgr)
+{
+ int actual_temp = 0;
+ uint32_t val = cgs_read_ind_register(hwmgr->device,
+ CGS_IND_REG__SMC, ixTHM_TCON_CUR_TMP);
+ uint32_t temp = PHM_GET_FIELD(val, THM_TCON_CUR_TMP, CUR_TEMP);
+
+ if (PHM_GET_FIELD(val, THM_TCON_CUR_TMP, CUR_TEMP_RANGE_SEL))
+ actual_temp = ((temp / 8) - 49) * PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ else
+ actual_temp = (temp / 8) * PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+
+ return actual_temp;
+}
+
static int cz_read_sensor(struct pp_hwmgr *hwmgr, int idx, int32_t *value)
{
struct cz_hwmgr *cz_hwmgr = (struct cz_hwmgr *)(hwmgr->backend);
@@ -1881,6 +1896,9 @@ static int cz_read_sensor(struct pp_hwmgr *hwmgr, int idx, int32_t *value)
case AMDGPU_PP_SENSOR_VCE_POWER:
*value = cz_hwmgr->vce_power_gated ? 0 : 1;
return 0;
+ case AMDGPU_PP_SENSOR_GPU_TEMP:
+ *value = cz_thermal_get_temperature(hwmgr);
+ return 0;
default:
return -EINVAL;
}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
index 14f8c1f..0723758 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
@@ -272,7 +272,7 @@ bool phm_check_smc_update_required_for_display_configuration(struct pp_hwmgr *hw
PHM_FUNC_CHECK(hwmgr);
if (hwmgr->hwmgr_func->check_smc_update_required_for_display_configuration == NULL)
- return -EINVAL;
+ return false;
return hwmgr->hwmgr_func->check_smc_update_required_for_display_configuration(hwmgr);
}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index 1167205..e03dcb6 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -710,13 +710,15 @@ int phm_get_voltage_evv_on_sclk(struct pp_hwmgr *hwmgr, uint8_t voltage_type,
uint32_t vol;
int ret = 0;
- if (hwmgr->chip_id < CHIP_POLARIS10) {
- atomctrl_get_voltage_evv_on_sclk(hwmgr, voltage_type, sclk, id, voltage);
+ if (hwmgr->chip_id < CHIP_TONGA) {
+ ret = atomctrl_get_voltage_evv(hwmgr, id, voltage);
+ } else if (hwmgr->chip_id < CHIP_POLARIS10) {
+ ret = atomctrl_get_voltage_evv_on_sclk(hwmgr, voltage_type, sclk, id, voltage);
if (*voltage >= 2000 || *voltage == 0)
*voltage = 1150;
} else {
ret = atomctrl_get_voltage_evv_on_sclk_ai(hwmgr, voltage_type, sclk, id, &vol);
- *voltage = (uint16_t)vol/100;
+ *voltage = (uint16_t)(vol/100);
}
return ret;
}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
index 1126bd4..0894527 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
@@ -1320,7 +1320,8 @@ int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_
if (0 != result)
return result;
- *voltage = le32_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)(&get_voltage_info_param_space))->ulVoltageLevel);
+ *voltage = le32_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)
+ (&get_voltage_info_param_space))->ulVoltageLevel);
return result;
}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c b/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
index 7de701d..4477c55 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
@@ -1201,12 +1201,15 @@ static uint32_t make_classification_flags(struct pp_hwmgr *hwmgr,
static int ppt_get_num_of_vce_state_table_entries_v1_0(struct pp_hwmgr *hwmgr)
{
const ATOM_Tonga_POWERPLAYTABLE *pp_table = get_powerplay_table(hwmgr);
- const ATOM_Tonga_VCE_State_Table *vce_state_table =
- (ATOM_Tonga_VCE_State_Table *)(((unsigned long)pp_table) + le16_to_cpu(pp_table->usVCEStateTableOffset));
+ const ATOM_Tonga_VCE_State_Table *vce_state_table;
- if (vce_state_table == NULL)
+
+ if (pp_table == NULL)
return 0;
+ vce_state_table = (void *)pp_table +
+ le16_to_cpu(pp_table->usVCEStateTableOffset);
+
return vce_state_table->ucNumEntries;
}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index 508245d..b0c929dd 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -1030,20 +1030,19 @@ static int smu7_disable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr)
struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
/* disable SCLK dpm */
- if (!data->sclk_dpm_key_disabled)
- PP_ASSERT_WITH_CODE(
- (smum_send_msg_to_smc(hwmgr->smumgr,
- PPSMC_MSG_DPM_Disable) == 0),
- "Failed to disable SCLK DPM!",
- return -EINVAL);
+ if (!data->sclk_dpm_key_disabled) {
+ PP_ASSERT_WITH_CODE(true == smum_is_dpm_running(hwmgr),
+ "Trying to disable SCLK DPM when DPM is disabled",
+ return 0);
+ smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_DPM_Disable);
+ }
/* disable MCLK dpm */
if (!data->mclk_dpm_key_disabled) {
- PP_ASSERT_WITH_CODE(
- (smum_send_msg_to_smc(hwmgr->smumgr,
- PPSMC_MSG_MCLKDPM_Disable) == 0),
- "Failed to disable MCLK DPM!",
- return -EINVAL);
+ PP_ASSERT_WITH_CODE(true == smum_is_dpm_running(hwmgr),
+ "Trying to disable MCLK DPM when DPM is disabled",
+ return 0);
+ smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_MCLKDPM_Disable);
}
return 0;
@@ -1069,10 +1068,13 @@ static int smu7_stop_dpm(struct pp_hwmgr *hwmgr)
return -EINVAL);
}
- if (smu7_disable_sclk_mclk_dpm(hwmgr)) {
- printk(KERN_ERR "Failed to disable Sclk DPM and Mclk DPM!");
- return -EINVAL;
- }
+ smu7_disable_sclk_mclk_dpm(hwmgr);
+
+ PP_ASSERT_WITH_CODE(true == smum_is_dpm_running(hwmgr),
+ "Trying to disable voltage DPM when DPM is disabled",
+ return 0);
+
+ smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_Voltage_Cntl_Disable);
return 0;
}
@@ -1166,8 +1168,8 @@ int smu7_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
tmp_result = (!smum_is_dpm_running(hwmgr)) ? 0 : -1;
PP_ASSERT_WITH_CODE(tmp_result == 0,
- "DPM is already running right now, no need to enable DPM!",
- return 0);
+ "DPM is already running",
+ );
if (smu7_voltage_control(hwmgr)) {
tmp_result = smu7_enable_voltage_control(hwmgr);
@@ -1226,7 +1228,7 @@ int smu7_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
PP_ASSERT_WITH_CODE((0 == tmp_result),
"Failed to enable VR hot GPIO interrupt!", result = tmp_result);
- smum_send_msg_to_smc(hwmgr->smumgr, (PPSMC_Msg)PPSMC_HasDisplay);
+ smum_send_msg_to_smc(hwmgr->smumgr, (PPSMC_Msg)PPSMC_NoDisplay);
tmp_result = smu7_enable_sclk_control(hwmgr);
PP_ASSERT_WITH_CODE((0 == tmp_result),
@@ -1306,6 +1308,12 @@ int smu7_disable_dpm_tasks(struct pp_hwmgr *hwmgr)
PP_ASSERT_WITH_CODE((tmp_result == 0),
"Failed to disable thermal auto throttle!", result = tmp_result);
+ if (1 == PHM_READ_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, FEATURE_STATUS, AVS_ON)) {
+ PP_ASSERT_WITH_CODE((0 == smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_DisableAvfs)),
+ "Failed to disable AVFS!",
+ return -EINVAL);
+ }
+
tmp_result = smu7_stop_dpm(hwmgr);
PP_ASSERT_WITH_CODE((tmp_result == 0),
"Failed to stop DPM!", result = tmp_result);
@@ -1452,17 +1460,19 @@ static int smu7_get_evv_voltages(struct pp_hwmgr *hwmgr)
struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table = NULL;
- if (table_info != NULL)
- sclk_table = table_info->vdd_dep_on_sclk;
-
for (i = 0; i < SMU7_MAX_LEAKAGE_COUNT; i++) {
vv_id = ATOM_VIRTUAL_VOLTAGE_ID0 + i;
if (data->vdd_gfx_control == SMU7_VOLTAGE_CONTROL_BY_SVID2) {
- if (0 == phm_get_sclk_for_voltage_evv(hwmgr,
+ if ((hwmgr->pp_table_version == PP_TABLE_V1)
+ && !phm_get_sclk_for_voltage_evv(hwmgr,
table_info->vddgfx_lookup_table, vv_id, &sclk)) {
if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
PHM_PlatformCaps_ClockStretcher)) {
+ if (table_info == NULL)
+ return -EINVAL;
+ sclk_table = table_info->vdd_dep_on_sclk;
+
for (j = 1; j < sclk_table->count; j++) {
if (sclk_table->entries[j].clk == sclk &&
sclk_table->entries[j].cks_enable == 0) {
@@ -1488,12 +1498,15 @@ static int smu7_get_evv_voltages(struct pp_hwmgr *hwmgr)
}
}
} else {
-
if ((hwmgr->pp_table_version == PP_TABLE_V0)
|| !phm_get_sclk_for_voltage_evv(hwmgr,
table_info->vddc_lookup_table, vv_id, &sclk)) {
if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
PHM_PlatformCaps_ClockStretcher)) {
+ if (table_info == NULL)
+ return -EINVAL;
+ sclk_table = table_info->vdd_dep_on_sclk;
+
for (j = 1; j < sclk_table->count; j++) {
if (sclk_table->entries[j].clk == sclk &&
sclk_table->entries[j].cks_enable == 0) {
@@ -2117,15 +2130,20 @@ static int smu7_patch_acp_vddc(struct pp_hwmgr *hwmgr,
}
static int smu7_patch_limits_vddc(struct pp_hwmgr *hwmgr,
- struct phm_clock_and_voltage_limits *tab)
+ struct phm_clock_and_voltage_limits *tab)
{
+ uint32_t vddc, vddci;
struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
if (tab) {
- smu7_patch_ppt_v0_with_vdd_leakage(hwmgr, (uint32_t *)&tab->vddc,
- &data->vddc_leakage);
- smu7_patch_ppt_v0_with_vdd_leakage(hwmgr, (uint32_t *)&tab->vddci,
- &data->vddci_leakage);
+ vddc = tab->vddc;
+ smu7_patch_ppt_v0_with_vdd_leakage(hwmgr, &vddc,
+ &data->vddc_leakage);
+ tab->vddc = vddc;
+ vddci = tab->vddci;
+ smu7_patch_ppt_v0_with_vdd_leakage(hwmgr, &vddci,
+ &data->vddci_leakage);
+ tab->vddci = vddci;
}
return 0;
@@ -3802,13 +3820,15 @@ static inline bool smu7_are_power_levels_equal(const struct smu7_performance_lev
int smu7_check_states_equal(struct pp_hwmgr *hwmgr, const struct pp_hw_power_state *pstate1, const struct pp_hw_power_state *pstate2, bool *equal)
{
- const struct smu7_power_state *psa = cast_const_phw_smu7_power_state(pstate1);
- const struct smu7_power_state *psb = cast_const_phw_smu7_power_state(pstate2);
+ const struct smu7_power_state *psa;
+ const struct smu7_power_state *psb;
int i;
if (pstate1 == NULL || pstate2 == NULL || equal == NULL)
return -EINVAL;
+ psa = cast_const_phw_smu7_power_state(pstate1);
+ psb = cast_const_phw_smu7_power_state(pstate2);
/* If the two states don't even have the same number of performance levels they cannot be the same state. */
if (psa->performance_level_count != psb->performance_level_count) {
*equal = false;
@@ -4213,18 +4233,26 @@ static int smu7_get_sclks(struct pp_hwmgr *hwmgr, struct amd_pp_clocks *clocks)
{
struct phm_ppt_v1_information *table_info =
(struct phm_ppt_v1_information *)hwmgr->pptable;
- struct phm_ppt_v1_clock_voltage_dependency_table *dep_sclk_table;
+ struct phm_ppt_v1_clock_voltage_dependency_table *dep_sclk_table = NULL;
+ struct phm_clock_voltage_dependency_table *sclk_table;
int i;
- if (table_info == NULL)
- return -EINVAL;
-
- dep_sclk_table = table_info->vdd_dep_on_sclk;
-
- for (i = 0; i < dep_sclk_table->count; i++) {
- clocks->clock[i] = dep_sclk_table->entries[i].clk;
- clocks->count++;
+ if (hwmgr->pp_table_version == PP_TABLE_V1) {
+ if (table_info == NULL || table_info->vdd_dep_on_sclk == NULL)
+ return -EINVAL;
+ dep_sclk_table = table_info->vdd_dep_on_sclk;
+ for (i = 0; i < dep_sclk_table->count; i++) {
+ clocks->clock[i] = dep_sclk_table->entries[i].clk;
+ clocks->count++;
+ }
+ } else if (hwmgr->pp_table_version == PP_TABLE_V0) {
+ sclk_table = hwmgr->dyn_state.vddc_dependency_on_sclk;
+ for (i = 0; i < sclk_table->count; i++) {
+ clocks->clock[i] = sclk_table->entries[i].clk;
+ clocks->count++;
+ }
}
+
return 0;
}
@@ -4246,17 +4274,24 @@ static int smu7_get_mclks(struct pp_hwmgr *hwmgr, struct amd_pp_clocks *clocks)
(struct phm_ppt_v1_information *)hwmgr->pptable;
struct phm_ppt_v1_clock_voltage_dependency_table *dep_mclk_table;
int i;
+ struct phm_clock_voltage_dependency_table *mclk_table;
- if (table_info == NULL)
- return -EINVAL;
-
- dep_mclk_table = table_info->vdd_dep_on_mclk;
-
- for (i = 0; i < dep_mclk_table->count; i++) {
- clocks->clock[i] = dep_mclk_table->entries[i].clk;
- clocks->latency[i] = smu7_get_mem_latency(hwmgr,
+ if (hwmgr->pp_table_version == PP_TABLE_V1) {
+ if (table_info == NULL)
+ return -EINVAL;
+ dep_mclk_table = table_info->vdd_dep_on_mclk;
+ for (i = 0; i < dep_mclk_table->count; i++) {
+ clocks->clock[i] = dep_mclk_table->entries[i].clk;
+ clocks->latency[i] = smu7_get_mem_latency(hwmgr,
dep_mclk_table->entries[i].clk);
- clocks->count++;
+ clocks->count++;
+ }
+ } else if (hwmgr->pp_table_version == PP_TABLE_V0) {
+ mclk_table = hwmgr->dyn_state.vddc_dependency_on_mclk;
+ for (i = 0; i < mclk_table->count; i++) {
+ clocks->clock[i] = mclk_table->entries[i].clk;
+ clocks->count++;
+ }
}
return 0;
}
@@ -4324,6 +4359,7 @@ static const struct pp_hwmgr_func smu7_hwmgr_funcs = {
.set_mclk_od = smu7_set_mclk_od,
.get_clock_by_type = smu7_get_clock_by_type,
.read_sensor = smu7_read_sensor,
+ .dynamic_state_management_disable = smu7_disable_dpm_tasks,
};
uint8_t smu7_get_sleep_divider_id_from_clock(uint32_t clock,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_thermal.c
index fb6c6f6..29d0319 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_thermal.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_thermal.c
@@ -30,7 +30,7 @@ int smu7_fan_ctrl_get_fan_speed_info(struct pp_hwmgr *hwmgr,
struct phm_fan_speed_info *fan_speed_info)
{
if (hwmgr->thermal_controller.fanInfo.bNoFan)
- return 0;
+ return -ENODEV;
fan_speed_info->supports_percent_read = true;
fan_speed_info->supports_percent_write = true;
@@ -60,7 +60,7 @@ int smu7_fan_ctrl_get_fan_speed_percent(struct pp_hwmgr *hwmgr,
uint64_t tmp64;
if (hwmgr->thermal_controller.fanInfo.bNoFan)
- return 0;
+ return -ENODEV;
duty100 = PHM_READ_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
CG_FDO_CTRL1, FMAX_DUTY100);
@@ -89,7 +89,7 @@ int smu7_fan_ctrl_get_fan_speed_rpm(struct pp_hwmgr *hwmgr, uint32_t *speed)
if (hwmgr->thermal_controller.fanInfo.bNoFan ||
(hwmgr->thermal_controller.fanInfo.
ucTachometerPulsesPerRevolution == 0))
- return 0;
+ return -ENODEV;
tach_period = PHM_READ_VFPF_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
CG_TACH_STATUS, TACH_PERIOD);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smc.c b/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smc.c
index eda802b..8c889ca 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smc.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smc.c
@@ -2458,7 +2458,7 @@ static int iceland_set_mc_special_registers(struct pp_hwmgr *hwmgr,
PP_ASSERT_WITH_CODE((j <= SMU71_DISCRETE_MC_REGISTER_ARRAY_SIZE),
"Invalid VramInfo table.", return -EINVAL);
- if (!data->is_memory_gddr5) {
+ if (!data->is_memory_gddr5 && j < SMU71_DISCRETE_MC_REGISTER_ARRAY_SIZE) {
table->mc_reg_address[j].s1 = mmMC_PMG_AUTO_CMD;
table->mc_reg_address[j].s0 = mmMC_PMG_AUTO_CMD;
for (k = 0; k < table->num_entries; k++) {
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index 963a24d..ffe1f85 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -34,9 +34,6 @@ static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity);
static void amd_sched_wakeup(struct amd_gpu_scheduler *sched);
static void amd_sched_process_job(struct fence *f, struct fence_cb *cb);
-struct kmem_cache *sched_fence_slab;
-atomic_t sched_fence_slab_ref = ATOMIC_INIT(0);
-
/* Initialize a given run queue struct */
static void amd_sched_rq_init(struct amd_sched_rq *rq)
{
@@ -618,13 +615,6 @@ int amd_sched_init(struct amd_gpu_scheduler *sched,
INIT_LIST_HEAD(&sched->ring_mirror_list);
spin_lock_init(&sched->job_list_lock);
atomic_set(&sched->hw_rq_count, 0);
- if (atomic_inc_return(&sched_fence_slab_ref) == 1) {
- sched_fence_slab = kmem_cache_create(
- "amd_sched_fence", sizeof(struct amd_sched_fence), 0,
- SLAB_HWCACHE_ALIGN, NULL);
- if (!sched_fence_slab)
- return -ENOMEM;
- }
/* Each scheduler will run on a seperate kernel thread */
sched->thread = kthread_run(amd_sched_main, sched, sched->name);
@@ -645,6 +635,4 @@ void amd_sched_fini(struct amd_gpu_scheduler *sched)
{
if (sched->thread)
kthread_stop(sched->thread);
- if (atomic_dec_and_test(&sched_fence_slab_ref))
- kmem_cache_destroy(sched_fence_slab);
}
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
index 7cbbbfb..51068e6 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
@@ -30,9 +30,6 @@
struct amd_gpu_scheduler;
struct amd_sched_rq;
-extern struct kmem_cache *sched_fence_slab;
-extern atomic_t sched_fence_slab_ref;
-
/**
* A scheduler entity is a wrapper around a job queue or a group
* of other entities. Entities take turns emitting jobs from their
@@ -145,6 +142,9 @@ void amd_sched_entity_fini(struct amd_gpu_scheduler *sched,
struct amd_sched_entity *entity);
void amd_sched_entity_push_job(struct amd_sched_job *sched_job);
+int amd_sched_fence_slab_init(void);
+void amd_sched_fence_slab_fini(void);
+
struct amd_sched_fence *amd_sched_fence_create(
struct amd_sched_entity *s_entity, void *owner);
void amd_sched_fence_scheduled(struct amd_sched_fence *fence);
diff --git a/drivers/gpu/drm/amd/scheduler/sched_fence.c b/drivers/gpu/drm/amd/scheduler/sched_fence.c
index 6b63bea..88fc2d6 100644
--- a/drivers/gpu/drm/amd/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/amd/scheduler/sched_fence.c
@@ -27,6 +27,25 @@
#include <drm/drmP.h>
#include "gpu_scheduler.h"
+static struct kmem_cache *sched_fence_slab;
+
+int amd_sched_fence_slab_init(void)
+{
+ sched_fence_slab = kmem_cache_create(
+ "amd_sched_fence", sizeof(struct amd_sched_fence), 0,
+ SLAB_HWCACHE_ALIGN, NULL);
+ if (!sched_fence_slab)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void amd_sched_fence_slab_fini(void)
+{
+ rcu_barrier();
+ kmem_cache_destroy(sched_fence_slab);
+}
+
struct amd_sched_fence *amd_sched_fence_create(struct amd_sched_entity *entity,
void *owner)
{
@@ -103,7 +122,7 @@ static void amd_sched_fence_free(struct rcu_head *rcu)
}
/**
- * amd_sched_fence_release - callback that fence can be freed
+ * amd_sched_fence_release_scheduled - callback that fence can be freed
*
* @fence: fence
*
@@ -118,7 +137,7 @@ static void amd_sched_fence_release_scheduled(struct fence *f)
}
/**
- * amd_sched_fence_release_scheduled - drop extra reference
+ * amd_sched_fence_release_finished - drop extra reference
*
* @f: fence
*
diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 2f58e9e..a51f8cb 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -332,17 +332,19 @@ static void armada_drm_crtc_dpms(struct drm_crtc *crtc, int dpms)
{
struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
- if (dcrtc->dpms != dpms) {
- dcrtc->dpms = dpms;
- if (!IS_ERR(dcrtc->clk) && !dpms_blanked(dpms))
- WARN_ON(clk_prepare_enable(dcrtc->clk));
- armada_drm_crtc_update(dcrtc);
- if (!IS_ERR(dcrtc->clk) && dpms_blanked(dpms))
- clk_disable_unprepare(dcrtc->clk);
+ if (dpms_blanked(dcrtc->dpms) != dpms_blanked(dpms)) {
if (dpms_blanked(dpms))
armada_drm_vblank_off(dcrtc);
- else
+ else if (!IS_ERR(dcrtc->clk))
+ WARN_ON(clk_prepare_enable(dcrtc->clk));
+ dcrtc->dpms = dpms;
+ armada_drm_crtc_update(dcrtc);
+ if (!dpms_blanked(dpms))
drm_crtc_vblank_on(&dcrtc->crtc);
+ else if (!IS_ERR(dcrtc->clk))
+ clk_disable_unprepare(dcrtc->clk);
+ } else if (dcrtc->dpms != dpms) {
+ dcrtc->dpms = dpms;
}
}
diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index 608df4c..0743e65 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/drivers/gpu/drm/ast/ast_ttm.c
@@ -267,6 +267,8 @@ int ast_mm_init(struct ast_private *ast)
return ret;
}
+ arch_io_reserve_memtype_wc(pci_resource_start(dev->pdev, 0),
+ pci_resource_len(dev->pdev, 0));
ast->fb_mtrr = arch_phys_wc_add(pci_resource_start(dev->pdev, 0),
pci_resource_len(dev->pdev, 0));
@@ -275,11 +277,15 @@ int ast_mm_init(struct ast_private *ast)
void ast_mm_fini(struct ast_private *ast)
{
+ struct drm_device *dev = ast->dev;
+
ttm_bo_device_release(&ast->ttm.bdev);
ast_ttm_global_release(ast);
arch_phys_wc_del(ast->fb_mtrr);
+ arch_io_free_memtype_wc(pci_resource_start(dev->pdev, 0),
+ pci_resource_len(dev->pdev, 0));
}
void ast_ttm_placement(struct ast_bo *bo, int domain)
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index bb2438d..5e7e63c 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
@@ -267,6 +267,9 @@ int cirrus_mm_init(struct cirrus_device *cirrus)
return ret;
}
+ arch_io_reserve_memtype_wc(pci_resource_start(dev->pdev, 0),
+ pci_resource_len(dev->pdev, 0));
+
cirrus->fb_mtrr = arch_phys_wc_add(pci_resource_start(dev->pdev, 0),
pci_resource_len(dev->pdev, 0));
@@ -276,6 +279,8 @@ int cirrus_mm_init(struct cirrus_device *cirrus)
void cirrus_mm_fini(struct cirrus_device *cirrus)
{
+ struct drm_device *dev = cirrus->dev;
+
if (!cirrus->mm_inited)
return;
@@ -285,6 +290,8 @@ void cirrus_mm_fini(struct cirrus_device *cirrus)
arch_phys_wc_del(cirrus->fb_mtrr);
cirrus->fb_mtrr = 0;
+ arch_io_free_memtype_wc(pci_resource_start(dev->pdev, 0),
+ pci_resource_len(dev->pdev, 0));
}
void cirrus_ttm_placement(struct cirrus_bo *bo, int domain)
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 2373960..e6862a7 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -420,18 +420,21 @@ drm_atomic_replace_property_blob_from_id(struct drm_crtc *crtc,
ssize_t expected_size,
bool *replaced)
{
- struct drm_device *dev = crtc->dev;
struct drm_property_blob *new_blob = NULL;
if (blob_id != 0) {
- new_blob = drm_property_lookup_blob(dev, blob_id);
+ new_blob = drm_property_lookup_blob(crtc->dev, blob_id);
if (new_blob == NULL)
return -EINVAL;
- if (expected_size > 0 && expected_size != new_blob->length)
+
+ if (expected_size > 0 && expected_size != new_blob->length) {
+ drm_property_unreference_blob(new_blob);
return -EINVAL;
+ }
}
drm_atomic_replace_property_blob(blob, new_blob, replaced);
+ drm_property_unreference_blob(new_blob);
return 0;
}
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index c3f8347..21f9926 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -594,10 +594,6 @@ drm_atomic_helper_check_planes(struct drm_device *dev,
struct drm_plane_state *plane_state;
int i, ret = 0;
- ret = drm_atomic_normalize_zpos(dev, state);
- if (ret)
- return ret;
-
for_each_plane_in_state(state, plane, plane_state, i) {
const struct drm_plane_helper_funcs *funcs;
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 04e4571..aa64448 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -914,6 +914,7 @@ static void drm_dp_destroy_port(struct kref *kref)
/* no need to clean up vcpi
* as if we have no connector we never setup a vcpi */
drm_dp_port_teardown_pdt(port, port->pdt);
+ port->pdt = DP_PEER_DEVICE_NONE;
}
kfree(port);
}
@@ -1159,7 +1160,9 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb,
drm_dp_put_port(port);
goto out;
}
- if (port->port_num >= DP_MST_LOGICAL_PORT_0) {
+ if ((port->pdt == DP_PEER_DEVICE_DP_LEGACY_CONV ||
+ port->pdt == DP_PEER_DEVICE_SST_SINK) &&
+ port->port_num >= DP_MST_LOGICAL_PORT_0) {
port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc);
drm_mode_connector_set_tile_property(port->connector);
}
@@ -2919,6 +2922,7 @@ static void drm_dp_destroy_connector_work(struct work_struct *work)
mgr->cbs->destroy_connector(mgr, port->connector);
drm_dp_port_teardown_pdt(port, port->pdt);
+ port->pdt = DP_PEER_DEVICE_NONE;
if (!port->input && port->vcpi.vcpi > 0) {
drm_dp_mst_reset_vcpi_slots(mgr, port);
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 03414bd..6c75e62 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -131,7 +131,12 @@ int drm_fb_helper_single_add_all_connectors(struct drm_fb_helper *fb_helper)
return 0;
fail:
for (i = 0; i < fb_helper->connector_count; i++) {
- kfree(fb_helper->connector_info[i]);
+ struct drm_fb_helper_connector *fb_helper_connector =
+ fb_helper->connector_info[i];
+
+ drm_connector_unreference(fb_helper_connector->connector);
+
+ kfree(fb_helper_connector);
fb_helper->connector_info[i] = NULL;
}
fb_helper->connector_count = 0;
@@ -603,6 +608,24 @@ int drm_fb_helper_blank(int blank, struct fb_info *info)
}
EXPORT_SYMBOL(drm_fb_helper_blank);
+static void drm_fb_helper_modeset_release(struct drm_fb_helper *helper,
+ struct drm_mode_set *modeset)
+{
+ int i;
+
+ for (i = 0; i < modeset->num_connectors; i++) {
+ drm_connector_unreference(modeset->connectors[i]);
+ modeset->connectors[i] = NULL;
+ }
+ modeset->num_connectors = 0;
+
+ drm_mode_destroy(helper->dev, modeset->mode);
+ modeset->mode = NULL;
+
+ /* FIXME should hold a ref? */
+ modeset->fb = NULL;
+}
+
static void drm_fb_helper_crtc_free(struct drm_fb_helper *helper)
{
int i;
@@ -612,10 +635,12 @@ static void drm_fb_helper_crtc_free(struct drm_fb_helper *helper)
kfree(helper->connector_info[i]);
}
kfree(helper->connector_info);
+
for (i = 0; i < helper->crtc_count; i++) {
- kfree(helper->crtc_info[i].mode_set.connectors);
- if (helper->crtc_info[i].mode_set.mode)
- drm_mode_destroy(helper->dev, helper->crtc_info[i].mode_set.mode);
+ struct drm_mode_set *modeset = &helper->crtc_info[i].mode_set;
+
+ drm_fb_helper_modeset_release(helper, modeset);
+ kfree(modeset->connectors);
}
kfree(helper->crtc_info);
}
@@ -644,7 +669,9 @@ static void drm_fb_helper_dirty_work(struct work_struct *work)
clip->x2 = clip->y2 = 0;
spin_unlock_irqrestore(&helper->dirty_lock, flags);
- helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, &clip_copy, 1);
+ /* call dirty callback only when it has been really touched */
+ if (clip_copy.x1 < clip_copy.x2 && clip_copy.y1 < clip_copy.y2)
+ helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, &clip_copy, 1);
}
/**
@@ -2088,7 +2115,6 @@ static void drm_setup_crtcs(struct drm_fb_helper *fb_helper)
struct drm_fb_helper_crtc **crtcs;
struct drm_display_mode **modes;
struct drm_fb_offset *offsets;
- struct drm_mode_set *modeset;
bool *enabled;
int width, height;
int i;
@@ -2136,45 +2162,35 @@ static void drm_setup_crtcs(struct drm_fb_helper *fb_helper)
/* need to set the modesets up here for use later */
/* fill out the connector<->crtc mappings into the modesets */
- for (i = 0; i < fb_helper->crtc_count; i++) {
- modeset = &fb_helper->crtc_info[i].mode_set;
- modeset->num_connectors = 0;
- modeset->fb = NULL;
- }
+ for (i = 0; i < fb_helper->crtc_count; i++)
+ drm_fb_helper_modeset_release(fb_helper,
+ &fb_helper->crtc_info[i].mode_set);
for (i = 0; i < fb_helper->connector_count; i++) {
struct drm_display_mode *mode = modes[i];
struct drm_fb_helper_crtc *fb_crtc = crtcs[i];
struct drm_fb_offset *offset = &offsets[i];
- modeset = &fb_crtc->mode_set;
+ struct drm_mode_set *modeset = &fb_crtc->mode_set;
if (mode && fb_crtc) {
+ struct drm_connector *connector =
+ fb_helper->connector_info[i]->connector;
+
DRM_DEBUG_KMS("desired mode %s set on crtc %d (%d,%d)\n",
mode->name, fb_crtc->mode_set.crtc->base.id, offset->x, offset->y);
+
fb_crtc->desired_mode = mode;
fb_crtc->x = offset->x;
fb_crtc->y = offset->y;
- if (modeset->mode)
- drm_mode_destroy(dev, modeset->mode);
modeset->mode = drm_mode_duplicate(dev,
fb_crtc->desired_mode);
- modeset->connectors[modeset->num_connectors++] = fb_helper->connector_info[i]->connector;
+ drm_connector_reference(connector);
+ modeset->connectors[modeset->num_connectors++] = connector;
modeset->fb = fb_helper->fb;
modeset->x = offset->x;
modeset->y = offset->y;
}
}
-
- /* Clear out any old modes if there are no more connected outputs. */
- for (i = 0; i < fb_helper->crtc_count; i++) {
- modeset = &fb_helper->crtc_info[i].mode_set;
- if (modeset->num_connectors == 0) {
- BUG_ON(modeset->fb);
- if (modeset->mode)
- drm_mode_destroy(dev, modeset->mode);
- modeset->mode = NULL;
- }
- }
out:
kfree(crtcs);
kfree(modes);
diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c
index 1df2d33..ffb2ab3 100644
--- a/drivers/gpu/drm/drm_info.c
+++ b/drivers/gpu/drm/drm_info.c
@@ -54,9 +54,6 @@ int drm_name_info(struct seq_file *m, void *data)
mutex_lock(&dev->master_mutex);
master = dev->master;
- if (!master)
- goto out_unlock;
-
seq_printf(m, "%s", dev->driver->name);
if (dev->dev)
seq_printf(m, " dev=%s", dev_name(dev->dev));
@@ -65,7 +62,6 @@ int drm_name_info(struct seq_file *m, void *data)
if (dev->unique)
seq_printf(m, " unique=%s", dev->unique);
seq_printf(m, "\n");
-out_unlock:
mutex_unlock(&dev->master_mutex);
return 0;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
index cb86c7e..d923013 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
@@ -329,20 +329,34 @@ void etnaviv_buffer_queue(struct etnaviv_gpu *gpu, unsigned int event,
/*
* Append a LINK to the submitted command buffer to return to
* the ring buffer. return_target is the ring target address.
- * We need three dwords: event, wait, link.
+ * We need at most 7 dwords in the return target: 2 cache flush +
+ * 2 semaphore stall + 1 event + 1 wait + 1 link.
*/
- return_dwords = 3;
+ return_dwords = 7;
return_target = etnaviv_buffer_reserve(gpu, buffer, return_dwords);
CMD_LINK(cmdbuf, return_dwords, return_target);
/*
- * Append event, wait and link pointing back to the wait
- * command to the ring buffer.
+ * Append a cache flush, stall, event, wait and link pointing back to
+ * the wait command to the ring buffer.
*/
+ if (gpu->exec_state == ETNA_PIPE_2D) {
+ CMD_LOAD_STATE(buffer, VIVS_GL_FLUSH_CACHE,
+ VIVS_GL_FLUSH_CACHE_PE2D);
+ } else {
+ CMD_LOAD_STATE(buffer, VIVS_GL_FLUSH_CACHE,
+ VIVS_GL_FLUSH_CACHE_DEPTH |
+ VIVS_GL_FLUSH_CACHE_COLOR);
+ CMD_LOAD_STATE(buffer, VIVS_TS_FLUSH_CACHE,
+ VIVS_TS_FLUSH_CACHE_FLUSH);
+ }
+ CMD_SEM(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_PE);
+ CMD_STALL(buffer, SYNC_RECIPIENT_FE, SYNC_RECIPIENT_PE);
CMD_LOAD_STATE(buffer, VIVS_GL_EVENT, VIVS_GL_EVENT_EVENT_ID(event) |
VIVS_GL_EVENT_FROM_PE);
CMD_WAIT(buffer);
- CMD_LINK(buffer, 2, return_target + 8);
+ CMD_LINK(buffer, 2, etnaviv_iommu_get_cmdbuf_va(gpu, buffer) +
+ buffer->user_size - 4);
if (drm_debug & DRM_UT_DRIVER)
pr_info("stream link to 0x%08x @ 0x%08x %p\n",
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 5ce3603..0370b84 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -748,19 +748,22 @@ static struct page **etnaviv_gem_userptr_do_get_pages(
int ret = 0, pinned, npages = etnaviv_obj->base.size >> PAGE_SHIFT;
struct page **pvec;
uintptr_t ptr;
+ unsigned int flags = 0;
pvec = drm_malloc_ab(npages, sizeof(struct page *));
if (!pvec)
return ERR_PTR(-ENOMEM);
+ if (!etnaviv_obj->userptr.ro)
+ flags |= FOLL_WRITE;
+
pinned = 0;
ptr = etnaviv_obj->userptr.ptr;
down_read(&mm->mmap_sem);
while (pinned < npages) {
ret = get_user_pages_remote(task, mm, ptr, npages - pinned,
- !etnaviv_obj->userptr.ro, 0,
- pvec + pinned, NULL);
+ flags, pvec + pinned, NULL);
if (ret < 0)
break;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
index d3796ed..169ac96 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
@@ -330,7 +330,8 @@ u32 etnaviv_iommu_get_cmdbuf_va(struct etnaviv_gpu *gpu,
return (u32)buf->vram_node.start;
mutex_lock(&mmu->lock);
- ret = etnaviv_iommu_find_iova(mmu, &buf->vram_node, buf->size);
+ ret = etnaviv_iommu_find_iova(mmu, &buf->vram_node,
+ buf->size + SZ_64K);
if (ret < 0) {
mutex_unlock(&mmu->lock);
return 0;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index def78c8..f86e7c8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -262,6 +262,26 @@ int exynos_atomic_commit(struct drm_device *dev, struct drm_atomic_state *state,
return 0;
}
+int exynos_atomic_check(struct drm_device *dev,
+ struct drm_atomic_state *state)
+{
+ int ret;
+
+ ret = drm_atomic_helper_check_modeset(dev, state);
+ if (ret)
+ return ret;
+
+ ret = drm_atomic_normalize_zpos(dev, state);
+ if (ret)
+ return ret;
+
+ ret = drm_atomic_helper_check_planes(dev, state);
+ if (ret)
+ return ret;
+
+ return ret;
+}
+
static int exynos_drm_open(struct drm_device *dev, struct drm_file *file)
{
struct drm_exynos_file_private *file_priv;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index d215149..80c4d5b 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -301,6 +301,7 @@ static inline int exynos_dpi_bind(struct drm_device *dev,
int exynos_atomic_commit(struct drm_device *dev, struct drm_atomic_state *state,
bool nonblock);
+int exynos_atomic_check(struct drm_device *dev, struct drm_atomic_state *state);
extern struct platform_driver fimd_driver;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index 40ce841..23cce0a 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -190,7 +190,7 @@ dma_addr_t exynos_drm_fb_dma_addr(struct drm_framebuffer *fb, int index)
static const struct drm_mode_config_funcs exynos_drm_mode_config_funcs = {
.fb_create = exynos_user_fb_create,
.output_poll_changed = exynos_drm_output_poll_changed,
- .atomic_check = drm_atomic_helper_check,
+ .atomic_check = exynos_atomic_check,
.atomic_commit = exynos_atomic_commit,
};
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index aa92dec..fbd13fa 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -488,7 +488,8 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
goto err_free;
}
- ret = get_vaddr_frames(start, npages, true, true, g2d_userptr->vec);
+ ret = get_vaddr_frames(start, npages, FOLL_FORCE | FOLL_WRITE,
+ g2d_userptr->vec);
if (ret != npages) {
DRM_ERROR("failed to get user pages from userptr.\n");
if (ret < 0)
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c
index 3371635..b2d5e18 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c
@@ -51,6 +51,7 @@ static void fsl_dcu_drm_disable_crtc(struct drm_crtc *crtc)
DCU_MODE_DCU_MODE(DCU_MODE_OFF));
regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE,
DCU_UPDATE_MODE_READREG);
+ clk_disable_unprepare(fsl_dev->pix_clk);
}
static void fsl_dcu_drm_crtc_enable(struct drm_crtc *crtc)
@@ -58,6 +59,7 @@ static void fsl_dcu_drm_crtc_enable(struct drm_crtc *crtc)
struct drm_device *dev = crtc->dev;
struct fsl_dcu_drm_device *fsl_dev = dev->dev_private;
+ clk_prepare_enable(fsl_dev->pix_clk);
regmap_update_bits(fsl_dev->regmap, DCU_DCU_MODE,
DCU_MODE_DCU_MODE_MASK,
DCU_MODE_DCU_MODE(DCU_MODE_NORMAL));
@@ -116,8 +118,6 @@ static void fsl_dcu_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
DCU_THRESHOLD_LS_BF_VS(BF_VS_VAL) |
DCU_THRESHOLD_OUT_BUF_HIGH(BUF_MAX_VAL) |
DCU_THRESHOLD_OUT_BUF_LOW(BUF_MIN_VAL));
- regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE,
- DCU_UPDATE_MODE_READREG);
return;
}
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
index 0884c45..e04efbe 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
@@ -267,12 +267,8 @@ static int fsl_dcu_drm_pm_resume(struct device *dev)
return ret;
}
- ret = clk_prepare_enable(fsl_dev->pix_clk);
- if (ret < 0) {
- dev_err(dev, "failed to enable pix clk\n");
- goto disable_dcu_clk;
- }
-
+ if (fsl_dev->tcon)
+ fsl_tcon_bypass_enable(fsl_dev->tcon);
fsl_dcu_drm_init_planes(fsl_dev->drm);
drm_atomic_helper_resume(fsl_dev->drm, fsl_dev->state);
@@ -284,10 +280,6 @@ static int fsl_dcu_drm_pm_resume(struct device *dev)
enable_irq(fsl_dev->irq);
return 0;
-
-disable_dcu_clk:
- clk_disable_unprepare(fsl_dev->clk);
- return ret;
}
#endif
@@ -401,18 +393,12 @@ static int fsl_dcu_drm_probe(struct platform_device *pdev)
goto disable_clk;
}
- ret = clk_prepare_enable(fsl_dev->pix_clk);
- if (ret < 0) {
- dev_err(dev, "failed to enable pix clk\n");
- goto unregister_pix_clk;
- }
-
fsl_dev->tcon = fsl_tcon_init(dev);
drm = drm_dev_alloc(driver, dev);
if (IS_ERR(drm)) {
ret = PTR_ERR(drm);
- goto disable_pix_clk;
+ goto unregister_pix_clk;
}
fsl_dev->dev = dev;
@@ -433,8 +419,6 @@ static int fsl_dcu_drm_probe(struct platform_device *pdev)
unref:
drm_dev_unref(drm);
-disable_pix_clk:
- clk_disable_unprepare(fsl_dev->pix_clk);
unregister_pix_clk:
clk_unregister(fsl_dev->pix_clk);
disable_clk:
@@ -447,7 +431,6 @@ static int fsl_dcu_drm_remove(struct platform_device *pdev)
struct fsl_dcu_drm_device *fsl_dev = platform_get_drvdata(pdev);
clk_disable_unprepare(fsl_dev->clk);
- clk_disable_unprepare(fsl_dev->pix_clk);
clk_unregister(fsl_dev->pix_clk);
drm_put_dev(fsl_dev->drm);
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
index a7e5486..9e6f7d8 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
@@ -211,11 +211,6 @@ void fsl_dcu_drm_init_planes(struct drm_device *dev)
for (j = 1; j <= fsl_dev->soc->layer_regs; j++)
regmap_write(fsl_dev->regmap, DCU_CTRLDESCLN(i, j), 0);
}
- regmap_update_bits(fsl_dev->regmap, DCU_DCU_MODE,
- DCU_MODE_DCU_MODE_MASK,
- DCU_MODE_DCU_MODE(DCU_MODE_OFF));
- regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE,
- DCU_UPDATE_MODE_READREG);
}
struct drm_plane *fsl_dcu_drm_primary_create_plane(struct drm_device *dev)
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
index 26edcc8..e1dd75b 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
@@ -20,38 +20,6 @@
#include "fsl_dcu_drm_drv.h"
#include "fsl_tcon.h"
-static int
-fsl_dcu_drm_encoder_atomic_check(struct drm_encoder *encoder,
- struct drm_crtc_state *crtc_state,
- struct drm_connector_state *conn_state)
-{
- return 0;
-}
-
-static void fsl_dcu_drm_encoder_disable(struct drm_encoder *encoder)
-{
- struct drm_device *dev = encoder->dev;
- struct fsl_dcu_drm_device *fsl_dev = dev->dev_private;
-
- if (fsl_dev->tcon)
- fsl_tcon_bypass_disable(fsl_dev->tcon);
-}
-
-static void fsl_dcu_drm_encoder_enable(struct drm_encoder *encoder)
-{
- struct drm_device *dev = encoder->dev;
- struct fsl_dcu_drm_device *fsl_dev = dev->dev_private;
-
- if (fsl_dev->tcon)
- fsl_tcon_bypass_enable(fsl_dev->tcon);
-}
-
-static const struct drm_encoder_helper_funcs encoder_helper_funcs = {
- .atomic_check = fsl_dcu_drm_encoder_atomic_check,
- .disable = fsl_dcu_drm_encoder_disable,
- .enable = fsl_dcu_drm_encoder_enable,
-};
-
static void fsl_dcu_drm_encoder_destroy(struct drm_encoder *encoder)
{
drm_encoder_cleanup(encoder);
@@ -68,13 +36,16 @@ int fsl_dcu_drm_encoder_create(struct fsl_dcu_drm_device *fsl_dev,
int ret;
encoder->possible_crtcs = 1;
+
+ /* Use bypass mode for parallel RGB/LVDS encoder */
+ if (fsl_dev->tcon)
+ fsl_tcon_bypass_enable(fsl_dev->tcon);
+
ret = drm_encoder_init(fsl_dev->drm, encoder, &encoder_funcs,
DRM_MODE_ENCODER_LVDS, NULL);
if (ret < 0)
return ret;
- drm_encoder_helper_add(encoder, &encoder_helper_funcs);
-
return 0;
}
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index bfb2efd..18dfdd5 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1447,8 +1447,6 @@ static int i915_drm_suspend(struct drm_device *dev)
dev_priv->suspend_count++;
- intel_display_set_init_power(dev_priv, false);
-
intel_csr_ucode_suspend(dev_priv);
out:
@@ -1466,6 +1464,8 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation)
disable_rpm_wakeref_asserts(dev_priv);
+ intel_display_set_init_power(dev_priv, false);
+
fw_csr = !IS_BROXTON(dev_priv) &&
suspend_to_idle(dev_priv) && dev_priv->csr.dmc_payload;
/*
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 8b9ee4e..685e9e06 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2883,6 +2883,11 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
extern long i915_compat_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg);
#endif
+extern const struct dev_pm_ops i915_pm_ops;
+
+extern int i915_driver_load(struct pci_dev *pdev,
+ const struct pci_device_id *ent);
+extern void i915_driver_unload(struct drm_device *dev);
extern int intel_gpu_reset(struct drm_i915_private *dev_priv, u32 engine_mask);
extern bool intel_has_gpu_reset(struct drm_i915_private *dev_priv);
extern void i915_reset(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 947e82c..91ab7e9 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1806,7 +1806,7 @@ int i915_gem_fault(struct vm_area_struct *area, struct vm_fault *vmf)
/* Use a partial view if it is bigger than available space */
chunk_size = MIN_CHUNK_PAGES;
if (i915_gem_object_is_tiled(obj))
- chunk_size = max(chunk_size, tile_row_pages(obj));
+ chunk_size = roundup(chunk_size, tile_row_pages(obj));
memset(&view, 0, sizeof(view));
view.type = I915_GGTT_VIEW_PARTIAL;
@@ -3543,15 +3543,27 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
if (view->type == I915_GGTT_VIEW_NORMAL)
vma = i915_gem_object_ggtt_pin(obj, view, 0, alignment,
PIN_MAPPABLE | PIN_NONBLOCK);
- if (IS_ERR(vma))
- vma = i915_gem_object_ggtt_pin(obj, view, 0, alignment, 0);
+ if (IS_ERR(vma)) {
+ struct drm_i915_private *i915 = to_i915(obj->base.dev);
+ unsigned int flags;
+
+ /* Valleyview is definitely limited to scanning out the first
+ * 512MiB. Lets presume this behaviour was inherited from the
+ * g4x display engine and that all earlier gen are similarly
+ * limited. Testing suggests that it is a little more
+ * complicated than this. For example, Cherryview appears quite
+ * happy to scanout from anywhere within its global aperture.
+ */
+ flags = 0;
+ if (HAS_GMCH_DISPLAY(i915))
+ flags = PIN_MAPPABLE;
+ vma = i915_gem_object_ggtt_pin(obj, view, 0, alignment, flags);
+ }
if (IS_ERR(vma))
goto err_unpin_display;
vma->display_alignment = max_t(u64, vma->display_alignment, alignment);
- WARN_ON(obj->pin_display > i915_vma_pin_count(vma));
-
i915_gem_object_flush_cpu_write_domain(obj);
old_write_domain = obj->base.write_domain;
@@ -3588,7 +3600,6 @@ i915_gem_object_unpin_from_display_plane(struct i915_vma *vma)
list_move_tail(&vma->vm_link, &vma->vm->inactive_list);
i915_vma_unpin(vma);
- WARN_ON(vma->obj->pin_display > i915_vma_pin_count(vma));
}
/**
@@ -3745,7 +3756,12 @@ void __i915_vma_set_map_and_fenceable(struct i915_vma *vma)
mappable = (vma->node.start + fence_size <=
dev_priv->ggtt.mappable_end);
- if (mappable && fenceable)
+ /*
+ * Explicitly disable for rotated VMA since the display does not
+ * need the fence and the VMA is not accessible to other users.
+ */
+ if (mappable && fenceable &&
+ vma->ggtt_view.type != I915_GGTT_VIEW_ROTATED)
vma->flags |= I915_VMA_CAN_FENCE;
else
vma->flags &= ~I915_VMA_CAN_FENCE;
diff --git a/drivers/gpu/drm/i915/i915_gem_fence.c b/drivers/gpu/drm/i915/i915_gem_fence.c
index 8df1fa7..2c7ba0e 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence.c
@@ -290,6 +290,8 @@ i915_vma_put_fence(struct i915_vma *vma)
{
struct drm_i915_fence_reg *fence = vma->fence;
+ assert_rpm_wakelock_held(to_i915(vma->vm->dev));
+
if (!fence)
return 0;
@@ -341,6 +343,8 @@ i915_vma_get_fence(struct i915_vma *vma)
struct drm_i915_fence_reg *fence;
struct i915_vma *set = i915_gem_object_is_tiled(vma->obj) ? vma : NULL;
+ assert_rpm_wakelock_held(to_i915(vma->vm->dev));
+
/* Just update our place in the LRU if our fence is getting reused. */
if (vma->fence) {
fence = vma->fence;
@@ -371,6 +375,12 @@ void i915_gem_restore_fences(struct drm_device *dev)
struct drm_i915_private *dev_priv = to_i915(dev);
int i;
+ /* Note that this may be called outside of struct_mutex, by
+ * runtime suspend/resume. The barrier we require is enforced by
+ * rpm itself - all access to fences/GTT are only within an rpm
+ * wakeref, and to acquire that wakeref you must pass through here.
+ */
+
for (i = 0; i < dev_priv->num_fence_regs; i++) {
struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i];
struct i915_vma *vma = reg->vma;
@@ -379,10 +389,17 @@ void i915_gem_restore_fences(struct drm_device *dev)
* Commit delayed tiling changes if we have an object still
* attached to the fence, otherwise just clear the fence.
*/
- if (vma && !i915_gem_object_is_tiled(vma->obj))
- vma = NULL;
+ if (vma && !i915_gem_object_is_tiled(vma->obj)) {
+ GEM_BUG_ON(!reg->dirty);
+ GEM_BUG_ON(vma->obj->fault_mappable);
- fence_update(reg, vma);
+ list_move(®->link, &dev_priv->mm.fence_list);
+ vma->fence = NULL;
+ vma = NULL;
+ }
+
+ fence_write(reg, vma);
+ reg->vma = vma;
}
}
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index e537930..c6f780f 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -508,6 +508,10 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
pvec = drm_malloc_gfp(npages, sizeof(struct page *), GFP_TEMPORARY);
if (pvec != NULL) {
struct mm_struct *mm = obj->userptr.mm->mm;
+ unsigned int flags = 0;
+
+ if (!obj->userptr.read_only)
+ flags |= FOLL_WRITE;
ret = -EFAULT;
if (atomic_inc_not_zero(&mm->mm_users)) {
@@ -517,7 +521,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
(work->task, mm,
obj->userptr.ptr + pinned * PAGE_SIZE,
npages - pinned,
- !obj->userptr.read_only, 0,
+ flags,
pvec + pinned, NULL);
if (ret < 0)
break;
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 687c768..31e6edd 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -431,9 +431,6 @@ static const struct pci_device_id pciidlist[] = {
};
MODULE_DEVICE_TABLE(pci, pciidlist);
-extern int i915_driver_load(struct pci_dev *pdev,
- const struct pci_device_id *ent);
-
static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
{
struct intel_device_info *intel_info =
@@ -463,8 +460,6 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
return i915_driver_load(pdev, ent);
}
-extern void i915_driver_unload(struct drm_device *dev);
-
static void i915_pci_remove(struct pci_dev *pdev)
{
struct drm_device *dev = pci_get_drvdata(pdev);
@@ -473,8 +468,6 @@ static void i915_pci_remove(struct pci_dev *pdev)
drm_dev_unref(dev);
}
-extern const struct dev_pm_ops i915_pm_ops;
-
static struct pci_driver i915_pci_driver = {
.name = DRIVER_NAME,
.id_table = pciidlist,
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index c6e69e4..1f8af87 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -1031,6 +1031,77 @@ static u8 translate_iboost(u8 val)
return mapping[val];
}
+static void sanitize_ddc_pin(struct drm_i915_private *dev_priv,
+ enum port port)
+{
+ const struct ddi_vbt_port_info *info =
+ &dev_priv->vbt.ddi_port_info[port];
+ enum port p;
+
+ if (!info->alternate_ddc_pin)
+ return;
+
+ for_each_port_masked(p, (1 << port) - 1) {
+ struct ddi_vbt_port_info *i = &dev_priv->vbt.ddi_port_info[p];
+
+ if (info->alternate_ddc_pin != i->alternate_ddc_pin)
+ continue;
+
+ DRM_DEBUG_KMS("port %c trying to use the same DDC pin (0x%x) as port %c, "
+ "disabling port %c DVI/HDMI support\n",
+ port_name(p), i->alternate_ddc_pin,
+ port_name(port), port_name(p));
+
+ /*
+ * If we have multiple ports supposedly sharing the
+ * pin, then dvi/hdmi couldn't exist on the shared
+ * port. Otherwise they share the same ddc bin and
+ * system couldn't communicate with them separately.
+ *
+ * Due to parsing the ports in alphabetical order,
+ * a higher port will always clobber a lower one.
+ */
+ i->supports_dvi = false;
+ i->supports_hdmi = false;
+ i->alternate_ddc_pin = 0;
+ }
+}
+
+static void sanitize_aux_ch(struct drm_i915_private *dev_priv,
+ enum port port)
+{
+ const struct ddi_vbt_port_info *info =
+ &dev_priv->vbt.ddi_port_info[port];
+ enum port p;
+
+ if (!info->alternate_aux_channel)
+ return;
+
+ for_each_port_masked(p, (1 << port) - 1) {
+ struct ddi_vbt_port_info *i = &dev_priv->vbt.ddi_port_info[p];
+
+ if (info->alternate_aux_channel != i->alternate_aux_channel)
+ continue;
+
+ DRM_DEBUG_KMS("port %c trying to use the same AUX CH (0x%x) as port %c, "
+ "disabling port %c DP support\n",
+ port_name(p), i->alternate_aux_channel,
+ port_name(port), port_name(p));
+
+ /*
+ * If we have multiple ports supposedlt sharing the
+ * aux channel, then DP couldn't exist on the shared
+ * port. Otherwise they share the same aux channel
+ * and system couldn't communicate with them separately.
+ *
+ * Due to parsing the ports in alphabetical order,
+ * a higher port will always clobber a lower one.
+ */
+ i->supports_dp = false;
+ i->alternate_aux_channel = 0;
+ }
+}
+
static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
const struct bdb_header *bdb)
{
@@ -1105,54 +1176,15 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
DRM_DEBUG_KMS("Port %c is internal DP\n", port_name(port));
if (is_dvi) {
- if (port == PORT_E) {
- info->alternate_ddc_pin = ddc_pin;
- /* if DDIE share ddc pin with other port, then
- * dvi/hdmi couldn't exist on the shared port.
- * Otherwise they share the same ddc bin and system
- * couldn't communicate with them seperately. */
- if (ddc_pin == DDC_PIN_B) {
- dev_priv->vbt.ddi_port_info[PORT_B].supports_dvi = 0;
- dev_priv->vbt.ddi_port_info[PORT_B].supports_hdmi = 0;
- } else if (ddc_pin == DDC_PIN_C) {
- dev_priv->vbt.ddi_port_info[PORT_C].supports_dvi = 0;
- dev_priv->vbt.ddi_port_info[PORT_C].supports_hdmi = 0;
- } else if (ddc_pin == DDC_PIN_D) {
- dev_priv->vbt.ddi_port_info[PORT_D].supports_dvi = 0;
- dev_priv->vbt.ddi_port_info[PORT_D].supports_hdmi = 0;
- }
- } else if (ddc_pin == DDC_PIN_B && port != PORT_B)
- DRM_DEBUG_KMS("Unexpected DDC pin for port B\n");
- else if (ddc_pin == DDC_PIN_C && port != PORT_C)
- DRM_DEBUG_KMS("Unexpected DDC pin for port C\n");
- else if (ddc_pin == DDC_PIN_D && port != PORT_D)
- DRM_DEBUG_KMS("Unexpected DDC pin for port D\n");
+ info->alternate_ddc_pin = ddc_pin;
+
+ sanitize_ddc_pin(dev_priv, port);
}
if (is_dp) {
- if (port == PORT_E) {
- info->alternate_aux_channel = aux_channel;
- /* if DDIE share aux channel with other port, then
- * DP couldn't exist on the shared port. Otherwise
- * they share the same aux channel and system
- * couldn't communicate with them seperately. */
- if (aux_channel == DP_AUX_A)
- dev_priv->vbt.ddi_port_info[PORT_A].supports_dp = 0;
- else if (aux_channel == DP_AUX_B)
- dev_priv->vbt.ddi_port_info[PORT_B].supports_dp = 0;
- else if (aux_channel == DP_AUX_C)
- dev_priv->vbt.ddi_port_info[PORT_C].supports_dp = 0;
- else if (aux_channel == DP_AUX_D)
- dev_priv->vbt.ddi_port_info[PORT_D].supports_dp = 0;
- }
- else if (aux_channel == DP_AUX_A && port != PORT_A)
- DRM_DEBUG_KMS("Unexpected AUX channel for port A\n");
- else if (aux_channel == DP_AUX_B && port != PORT_B)
- DRM_DEBUG_KMS("Unexpected AUX channel for port B\n");
- else if (aux_channel == DP_AUX_C && port != PORT_C)
- DRM_DEBUG_KMS("Unexpected AUX channel for port C\n");
- else if (aux_channel == DP_AUX_D && port != PORT_D)
- DRM_DEBUG_KMS("Unexpected AUX channel for port D\n");
+ info->alternate_aux_channel = aux_channel;
+
+ sanitize_aux_ch(dev_priv, port);
}
if (bdb->version >= 158) {
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 73b6858..1b20e16 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -192,7 +192,7 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu;
const int s_max = 3, ss_max = 3, eu_max = 8;
int s, ss;
- u32 fuse2, eu_disable[s_max];
+ u32 fuse2, eu_disable[3]; /* s_max */
fuse2 = I915_READ(GEN8_FUSE2);
sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index fbcfed6..81c1149 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2978,7 +2978,8 @@ int skl_check_plane_surface(struct intel_plane_state *plane_state)
/* Rotate src coordinates to match rotated GTT view */
if (intel_rotation_90_or_270(rotation))
drm_rect_rotate(&plane_state->base.src,
- fb->width, fb->height, DRM_ROTATE_270);
+ fb->width << 16, fb->height << 16,
+ DRM_ROTATE_270);
/*
* Handle the AUX surface first since
@@ -10242,6 +10243,29 @@ static void bxt_modeset_commit_cdclk(struct drm_atomic_state *old_state)
bxt_set_cdclk(to_i915(dev), req_cdclk);
}
+static int bdw_adjust_min_pipe_pixel_rate(struct intel_crtc_state *crtc_state,
+ int pixel_rate)
+{
+ struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+
+ /* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */
+ if (IS_BROADWELL(dev_priv) && crtc_state->ips_enabled)
+ pixel_rate = DIV_ROUND_UP(pixel_rate * 100, 95);
+
+ /* BSpec says "Do not use DisplayPort with CDCLK less than
+ * 432 MHz, audio enabled, port width x4, and link rate
+ * HBR2 (5.4 GHz), or else there may be audio corruption or
+ * screen corruption."
+ */
+ if (intel_crtc_has_dp_encoder(crtc_state) &&
+ crtc_state->has_audio &&
+ crtc_state->port_clock >= 540000 &&
+ crtc_state->lane_count == 4)
+ pixel_rate = max(432000, pixel_rate);
+
+ return pixel_rate;
+}
+
/* compute the max rate for new configuration */
static int ilk_max_pixel_rate(struct drm_atomic_state *state)
{
@@ -10267,9 +10291,9 @@ static int ilk_max_pixel_rate(struct drm_atomic_state *state)
pixel_rate = ilk_pipe_pixel_rate(crtc_state);
- /* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */
- if (IS_BROADWELL(dev_priv) && crtc_state->ips_enabled)
- pixel_rate = DIV_ROUND_UP(pixel_rate * 100, 95);
+ if (IS_BROADWELL(dev_priv) || IS_GEN9(dev_priv))
+ pixel_rate = bdw_adjust_min_pipe_pixel_rate(crtc_state,
+ pixel_rate);
intel_state->min_pixclk[i] = pixel_rate;
}
@@ -14310,7 +14334,7 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
for_each_plane_in_state(state, plane, plane_state, i) {
struct intel_plane_state *intel_plane_state =
- to_intel_plane_state(plane_state);
+ to_intel_plane_state(plane->state);
if (!intel_plane_state->wait_req)
continue;
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 14a3cf0..3581b5a 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1108,6 +1108,44 @@ intel_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
return ret;
}
+static enum port intel_aux_port(struct drm_i915_private *dev_priv,
+ enum port port)
+{
+ const struct ddi_vbt_port_info *info =
+ &dev_priv->vbt.ddi_port_info[port];
+ enum port aux_port;
+
+ if (!info->alternate_aux_channel) {
+ DRM_DEBUG_KMS("using AUX %c for port %c (platform default)\n",
+ port_name(port), port_name(port));
+ return port;
+ }
+
+ switch (info->alternate_aux_channel) {
+ case DP_AUX_A:
+ aux_port = PORT_A;
+ break;
+ case DP_AUX_B:
+ aux_port = PORT_B;
+ break;
+ case DP_AUX_C:
+ aux_port = PORT_C;
+ break;
+ case DP_AUX_D:
+ aux_port = PORT_D;
+ break;
+ default:
+ MISSING_CASE(info->alternate_aux_channel);
+ aux_port = PORT_A;
+ break;
+ }
+
+ DRM_DEBUG_KMS("using AUX %c for port %c (VBT)\n",
+ port_name(aux_port), port_name(port));
+
+ return aux_port;
+}
+
static i915_reg_t g4x_aux_ctl_reg(struct drm_i915_private *dev_priv,
enum port port)
{
@@ -1168,36 +1206,9 @@ static i915_reg_t ilk_aux_data_reg(struct drm_i915_private *dev_priv,
}
}
-/*
- * On SKL we don't have Aux for port E so we rely
- * on VBT to set a proper alternate aux channel.
- */
-static enum port skl_porte_aux_port(struct drm_i915_private *dev_priv)
-{
- const struct ddi_vbt_port_info *info =
- &dev_priv->vbt.ddi_port_info[PORT_E];
-
- switch (info->alternate_aux_channel) {
- case DP_AUX_A:
- return PORT_A;
- case DP_AUX_B:
- return PORT_B;
- case DP_AUX_C:
- return PORT_C;
- case DP_AUX_D:
- return PORT_D;
- default:
- MISSING_CASE(info->alternate_aux_channel);
- return PORT_A;
- }
-}
-
static i915_reg_t skl_aux_ctl_reg(struct drm_i915_private *dev_priv,
enum port port)
{
- if (port == PORT_E)
- port = skl_porte_aux_port(dev_priv);
-
switch (port) {
case PORT_A:
case PORT_B:
@@ -1213,9 +1224,6 @@ static i915_reg_t skl_aux_ctl_reg(struct drm_i915_private *dev_priv,
static i915_reg_t skl_aux_data_reg(struct drm_i915_private *dev_priv,
enum port port, int index)
{
- if (port == PORT_E)
- port = skl_porte_aux_port(dev_priv);
-
switch (port) {
case PORT_A:
case PORT_B:
@@ -1253,7 +1261,8 @@ static i915_reg_t intel_aux_data_reg(struct drm_i915_private *dev_priv,
static void intel_aux_reg_init(struct intel_dp *intel_dp)
{
struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
- enum port port = dp_to_dig_port(intel_dp)->port;
+ enum port port = intel_aux_port(dev_priv,
+ dp_to_dig_port(intel_dp)->port);
int i;
intel_dp->aux_ch_ctl_reg = intel_aux_ctl_reg(dev_priv, port);
@@ -3551,8 +3560,8 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp)
/* Read the eDP Display control capabilities registers */
if ((intel_dp->dpcd[DP_EDP_CONFIGURATION_CAP] & DP_DPCD_DISPLAY_CONTROL_CAPABLE) &&
drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_DPCD_REV,
- intel_dp->edp_dpcd, sizeof(intel_dp->edp_dpcd) ==
- sizeof(intel_dp->edp_dpcd)))
+ intel_dp->edp_dpcd, sizeof(intel_dp->edp_dpcd)) ==
+ sizeof(intel_dp->edp_dpcd))
DRM_DEBUG_KMS("EDP DPCD : %*ph\n", (int) sizeof(intel_dp->edp_dpcd),
intel_dp->edp_dpcd);
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index faa6762..c43dd9a 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -104,8 +104,10 @@ static int intel_fbc_calculate_cfb_size(struct drm_i915_private *dev_priv,
int lines;
intel_fbc_get_plane_source_size(cache, NULL, &lines);
- if (INTEL_INFO(dev_priv)->gen >= 7)
+ if (INTEL_GEN(dev_priv) == 7)
lines = min(lines, 2048);
+ else if (INTEL_GEN(dev_priv) >= 8)
+ lines = min(lines, 2560);
/* Hardware needs the full buffer stride, not just the active area. */
return lines * cache->fb.stride;
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index f40a35f..13c3061 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1799,6 +1799,50 @@ intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *c
intel_hdmi->aspect_ratio = HDMI_PICTURE_ASPECT_NONE;
}
+static u8 intel_hdmi_ddc_pin(struct drm_i915_private *dev_priv,
+ enum port port)
+{
+ const struct ddi_vbt_port_info *info =
+ &dev_priv->vbt.ddi_port_info[port];
+ u8 ddc_pin;
+
+ if (info->alternate_ddc_pin) {
+ DRM_DEBUG_KMS("Using DDC pin 0x%x for port %c (VBT)\n",
+ info->alternate_ddc_pin, port_name(port));
+ return info->alternate_ddc_pin;
+ }
+
+ switch (port) {
+ case PORT_B:
+ if (IS_BROXTON(dev_priv))
+ ddc_pin = GMBUS_PIN_1_BXT;
+ else
+ ddc_pin = GMBUS_PIN_DPB;
+ break;
+ case PORT_C:
+ if (IS_BROXTON(dev_priv))
+ ddc_pin = GMBUS_PIN_2_BXT;
+ else
+ ddc_pin = GMBUS_PIN_DPC;
+ break;
+ case PORT_D:
+ if (IS_CHERRYVIEW(dev_priv))
+ ddc_pin = GMBUS_PIN_DPD_CHV;
+ else
+ ddc_pin = GMBUS_PIN_DPD;
+ break;
+ default:
+ MISSING_CASE(port);
+ ddc_pin = GMBUS_PIN_DPB;
+ break;
+ }
+
+ DRM_DEBUG_KMS("Using DDC pin 0x%x for port %c (platform default)\n",
+ ddc_pin, port_name(port));
+
+ return ddc_pin;
+}
+
void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
struct intel_connector *intel_connector)
{
@@ -1808,7 +1852,6 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
struct drm_device *dev = intel_encoder->base.dev;
struct drm_i915_private *dev_priv = to_i915(dev);
enum port port = intel_dig_port->port;
- uint8_t alternate_ddc_pin;
DRM_DEBUG_KMS("Adding HDMI connector on port %c\n",
port_name(port));
@@ -1826,12 +1869,10 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
connector->doublescan_allowed = 0;
connector->stereo_allowed = 1;
+ intel_hdmi->ddc_bus = intel_hdmi_ddc_pin(dev_priv, port);
+
switch (port) {
case PORT_B:
- if (IS_BROXTON(dev_priv))
- intel_hdmi->ddc_bus = GMBUS_PIN_1_BXT;
- else
- intel_hdmi->ddc_bus = GMBUS_PIN_DPB;
/*
* On BXT A0/A1, sw needs to activate DDIA HPD logic and
* interrupts to check the external panel connection.
@@ -1842,46 +1883,17 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
intel_encoder->hpd_pin = HPD_PORT_B;
break;
case PORT_C:
- if (IS_BROXTON(dev_priv))
- intel_hdmi->ddc_bus = GMBUS_PIN_2_BXT;
- else
- intel_hdmi->ddc_bus = GMBUS_PIN_DPC;
intel_encoder->hpd_pin = HPD_PORT_C;
break;
case PORT_D:
- if (WARN_ON(IS_BROXTON(dev_priv)))
- intel_hdmi->ddc_bus = GMBUS_PIN_DISABLED;
- else if (IS_CHERRYVIEW(dev_priv))
- intel_hdmi->ddc_bus = GMBUS_PIN_DPD_CHV;
- else
- intel_hdmi->ddc_bus = GMBUS_PIN_DPD;
intel_encoder->hpd_pin = HPD_PORT_D;
break;
case PORT_E:
- /* On SKL PORT E doesn't have seperate GMBUS pin
- * We rely on VBT to set a proper alternate GMBUS pin. */
- alternate_ddc_pin =
- dev_priv->vbt.ddi_port_info[PORT_E].alternate_ddc_pin;
- switch (alternate_ddc_pin) {
- case DDC_PIN_B:
- intel_hdmi->ddc_bus = GMBUS_PIN_DPB;
- break;
- case DDC_PIN_C:
- intel_hdmi->ddc_bus = GMBUS_PIN_DPC;
- break;
- case DDC_PIN_D:
- intel_hdmi->ddc_bus = GMBUS_PIN_DPD;
- break;
- default:
- MISSING_CASE(alternate_ddc_pin);
- }
intel_encoder->hpd_pin = HPD_PORT_E;
break;
- case PORT_A:
- intel_encoder->hpd_pin = HPD_PORT_A;
- /* Internal port only for eDP. */
default:
- BUG();
+ MISSING_CASE(port);
+ return;
}
if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) {
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index a2f751c..db24f89 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3362,13 +3362,15 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
int num_active;
int id, i;
+ /* Clear the partitioning for disabled planes. */
+ memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe]));
+ memset(ddb->y_plane[pipe], 0, sizeof(ddb->y_plane[pipe]));
+
if (WARN_ON(!state))
return 0;
if (!cstate->base.active) {
ddb->pipe[pipe].start = ddb->pipe[pipe].end = 0;
- memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe]));
- memset(ddb->y_plane[pipe], 0, sizeof(ddb->y_plane[pipe]));
return 0;
}
@@ -3468,12 +3470,6 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
return 0;
}
-static uint32_t skl_pipe_pixel_rate(const struct intel_crtc_state *config)
-{
- /* TODO: Take into account the scalers once we support them */
- return config->base.adjusted_mode.crtc_clock;
-}
-
/*
* The max latency should be 257 (max the punit can code is 255 and we add 2us
* for the read latency) and cpp should always be <= 8, so that
@@ -3524,7 +3520,7 @@ static uint32_t skl_adjusted_plane_pixel_rate(const struct intel_crtc_state *cst
* Adjusted plane pixel rate is just the pipe's adjusted pixel rate
* with additional adjustments for plane-specific scaling.
*/
- adjusted_pixel_rate = skl_pipe_pixel_rate(cstate);
+ adjusted_pixel_rate = ilk_pipe_pixel_rate(cstate);
downscale_amount = skl_plane_downscale_amount(pstate);
pixel_rate = adjusted_pixel_rate * downscale_amount >> 16;
@@ -3736,11 +3732,11 @@ skl_compute_linetime_wm(struct intel_crtc_state *cstate)
if (!cstate->base.active)
return 0;
- if (WARN_ON(skl_pipe_pixel_rate(cstate) == 0))
+ if (WARN_ON(ilk_pipe_pixel_rate(cstate) == 0))
return 0;
return DIV_ROUND_UP(8 * cstate->base.adjusted_mode.crtc_htotal * 1000,
- skl_pipe_pixel_rate(cstate));
+ ilk_pipe_pixel_rate(cstate));
}
static void skl_compute_transition_wm(struct intel_crtc_state *cstate,
@@ -4050,6 +4046,12 @@ skl_compute_ddb(struct drm_atomic_state *state)
intel_state->wm_results.dirty_pipes = ~0;
}
+ /*
+ * We're not recomputing for the pipes not included in the commit, so
+ * make sure we start with the current state.
+ */
+ memcpy(ddb, &dev_priv->wm.skl_hw.ddb, sizeof(*ddb));
+
for_each_intel_crtc_mask(dev, intel_crtc, realloc_pipes) {
struct intel_crtc_state *cstate;
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 6c11168..a38c2fe 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -1139,7 +1139,9 @@ static void vlv_display_power_well_deinit(struct drm_i915_private *dev_priv)
intel_power_sequencer_reset(dev_priv);
- intel_hpd_poll_init(dev_priv);
+ /* Prevent us from re-enabling polling on accident in late suspend */
+ if (!dev_priv->drm.dev->power.is_suspended)
+ intel_hpd_poll_init(dev_priv);
}
static void vlv_display_power_well_enable(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 98df09c..9672b57 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -357,8 +357,8 @@ static int imx_drm_bind(struct device *dev)
int ret;
drm = drm_dev_alloc(&imx_drm_driver, dev);
- if (!drm)
- return -ENOMEM;
+ if (IS_ERR(drm))
+ return PTR_ERR(drm);
imxdrm = devm_kzalloc(dev, sizeof(*imxdrm), GFP_KERNEL);
if (!imxdrm) {
@@ -436,9 +436,11 @@ static int imx_drm_bind(struct device *dev)
err_fbhelper:
drm_kms_helper_poll_fini(drm);
+#if IS_ENABLED(CONFIG_DRM_FBDEV_EMULATION)
if (imxdrm->fbhelper)
drm_fbdev_cma_fini(imxdrm->fbhelper);
err_unbind:
+#endif
component_unbind_all(drm->dev, drm);
err_vblank:
drm_vblank_cleanup(drm);
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index 4e1ae3f..6be515a 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -68,6 +68,12 @@ static void ipu_crtc_atomic_disable(struct drm_crtc *crtc,
ipu_dc_disable_channel(ipu_crtc->dc);
ipu_di_disable(ipu_crtc->di);
+ /*
+ * Planes must be disabled before DC clock is removed, as otherwise the
+ * attached IDMACs will be left in undefined state, possibly hanging
+ * the IPU or even system.
+ */
+ drm_atomic_helper_disable_planes_on_crtc(old_crtc_state, false);
ipu_dc_disable(ipu);
spin_lock_irq(&crtc->dev->event_lock);
@@ -77,9 +83,6 @@ static void ipu_crtc_atomic_disable(struct drm_crtc *crtc,
}
spin_unlock_irq(&crtc->dev->event_lock);
- /* always disable planes on the CRTC */
- drm_atomic_helper_disable_planes_on_crtc(old_crtc_state, true);
-
drm_crtc_vblank_off(crtc);
}
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c
index ce22d0a..d5864ed 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.c
+++ b/drivers/gpu/drm/imx/ipuv3-plane.c
@@ -103,11 +103,11 @@ drm_plane_state_to_vbo(struct drm_plane_state *state)
(state->src_x >> 16) / 2 - eba;
}
-static void ipu_plane_atomic_set_base(struct ipu_plane *ipu_plane,
- struct drm_plane_state *old_state)
+static void ipu_plane_atomic_set_base(struct ipu_plane *ipu_plane)
{
struct drm_plane *plane = &ipu_plane->base;
struct drm_plane_state *state = plane->state;
+ struct drm_crtc_state *crtc_state = state->crtc->state;
struct drm_framebuffer *fb = state->fb;
unsigned long eba, ubo, vbo;
int active;
@@ -117,7 +117,7 @@ static void ipu_plane_atomic_set_base(struct ipu_plane *ipu_plane,
switch (fb->pixel_format) {
case DRM_FORMAT_YUV420:
case DRM_FORMAT_YVU420:
- if (old_state->fb)
+ if (!drm_atomic_crtc_needs_modeset(crtc_state))
break;
/*
@@ -149,7 +149,7 @@ static void ipu_plane_atomic_set_base(struct ipu_plane *ipu_plane,
break;
}
- if (old_state->fb) {
+ if (!drm_atomic_crtc_needs_modeset(crtc_state)) {
active = ipu_idmac_get_current_buffer(ipu_plane->ipu_ch);
ipu_cpmem_set_buffer(ipu_plane->ipu_ch, !active, eba);
ipu_idmac_select_buffer(ipu_plane->ipu_ch, !active);
@@ -259,6 +259,7 @@ static int ipu_plane_atomic_check(struct drm_plane *plane,
struct drm_framebuffer *fb = state->fb;
struct drm_framebuffer *old_fb = old_state->fb;
unsigned long eba, ubo, vbo, old_ubo, old_vbo;
+ int hsub, vsub;
/* Ok to disable */
if (!fb)
@@ -355,7 +356,9 @@ static int ipu_plane_atomic_check(struct drm_plane *plane,
if ((ubo > 0xfffff8) || (vbo > 0xfffff8))
return -EINVAL;
- if (old_fb) {
+ if (old_fb &&
+ (old_fb->pixel_format == DRM_FORMAT_YUV420 ||
+ old_fb->pixel_format == DRM_FORMAT_YVU420)) {
old_ubo = drm_plane_state_to_ubo(old_state);
old_vbo = drm_plane_state_to_vbo(old_state);
if (ubo != old_ubo || vbo != old_vbo)
@@ -370,6 +373,16 @@ static int ipu_plane_atomic_check(struct drm_plane *plane,
if (old_fb && old_fb->pitches[1] != fb->pitches[1])
crtc_state->mode_changed = true;
+
+ /*
+ * The x/y offsets must be even in case of horizontal/vertical
+ * chroma subsampling.
+ */
+ hsub = drm_format_horz_chroma_subsampling(fb->pixel_format);
+ vsub = drm_format_vert_chroma_subsampling(fb->pixel_format);
+ if (((state->src_x >> 16) & (hsub - 1)) ||
+ ((state->src_y >> 16) & (vsub - 1)))
+ return -EINVAL;
}
return 0;
@@ -392,7 +405,7 @@ static void ipu_plane_atomic_update(struct drm_plane *plane,
struct drm_crtc_state *crtc_state = state->crtc->state;
if (!drm_atomic_crtc_needs_modeset(crtc_state)) {
- ipu_plane_atomic_set_base(ipu_plane, old_state);
+ ipu_plane_atomic_set_base(ipu_plane);
return;
}
}
@@ -424,6 +437,7 @@ static void ipu_plane_atomic_update(struct drm_plane *plane,
ipu_dp_set_global_alpha(ipu_plane->dp, false, 0, false);
break;
default:
+ ipu_dp_set_global_alpha(ipu_plane->dp, true, 0, true);
break;
}
}
@@ -437,7 +451,7 @@ static void ipu_plane_atomic_update(struct drm_plane *plane,
ipu_cpmem_set_high_priority(ipu_plane->ipu_ch);
ipu_idmac_set_double_buffer(ipu_plane->ipu_ch, 1);
ipu_cpmem_set_stride(ipu_plane->ipu_ch, state->fb->pitches[0]);
- ipu_plane_atomic_set_base(ipu_plane, old_state);
+ ipu_plane_atomic_set_base(ipu_plane);
ipu_plane_enable(ipu_plane);
}
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 919b35f..dcf7d11 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -266,6 +266,9 @@ int mgag200_mm_init(struct mga_device *mdev)
return ret;
}
+ arch_io_reserve_memtype_wc(pci_resource_start(dev->pdev, 0),
+ pci_resource_len(dev->pdev, 0));
+
mdev->fb_mtrr = arch_phys_wc_add(pci_resource_start(dev->pdev, 0),
pci_resource_len(dev->pdev, 0));
@@ -274,10 +277,14 @@ int mgag200_mm_init(struct mga_device *mdev)
void mgag200_mm_fini(struct mga_device *mdev)
{
+ struct drm_device *dev = mdev->dev;
+
ttm_bo_device_release(&mdev->ttm.bdev);
mgag200_ttm_global_release(mdev);
+ arch_io_free_memtype_wc(pci_resource_start(dev->pdev, 0),
+ pci_resource_len(dev->pdev, 0));
arch_phys_wc_del(mdev->fb_mtrr);
mdev->fb_mtrr = 0;
}
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index f05ed0e..6f24002 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -139,6 +139,7 @@ struct msm_dsi_host {
u32 err_work_state;
struct work_struct err_work;
+ struct work_struct hpd_work;
struct workqueue_struct *workqueue;
/* DSI 6G TX buffer*/
@@ -1294,6 +1295,14 @@ static void dsi_sw_reset_restore(struct msm_dsi_host *msm_host)
wmb(); /* make sure dsi controller enabled again */
}
+static void dsi_hpd_worker(struct work_struct *work)
+{
+ struct msm_dsi_host *msm_host =
+ container_of(work, struct msm_dsi_host, hpd_work);
+
+ drm_helper_hpd_irq_event(msm_host->dev);
+}
+
static void dsi_err_worker(struct work_struct *work)
{
struct msm_dsi_host *msm_host =
@@ -1480,7 +1489,7 @@ static int dsi_host_attach(struct mipi_dsi_host *host,
DBG("id=%d", msm_host->id);
if (msm_host->dev)
- drm_helper_hpd_irq_event(msm_host->dev);
+ queue_work(msm_host->workqueue, &msm_host->hpd_work);
return 0;
}
@@ -1494,7 +1503,7 @@ static int dsi_host_detach(struct mipi_dsi_host *host,
DBG("id=%d", msm_host->id);
if (msm_host->dev)
- drm_helper_hpd_irq_event(msm_host->dev);
+ queue_work(msm_host->workqueue, &msm_host->hpd_work);
return 0;
}
@@ -1748,6 +1757,7 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi)
/* setup workqueue */
msm_host->workqueue = alloc_ordered_workqueue("dsi_drm_work", 0);
INIT_WORK(&msm_host->err_work, dsi_err_worker);
+ INIT_WORK(&msm_host->hpd_work, dsi_hpd_worker);
msm_dsi->host = &msm_host->base;
msm_dsi->id = msm_host->id;
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm.c
index 598fdaf..26e3a01 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm.c
@@ -521,6 +521,7 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm)
.parent_names = (const char *[]){ "xo" },
.num_parents = 1,
.name = vco_name,
+ .flags = CLK_IGNORE_UNUSED,
.ops = &clk_ops_dsi_pll_28nm_vco,
};
struct device *dev = &pll_28nm->pdev->dev;
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c
index 38c90e1..4900845 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm_8960.c
@@ -412,6 +412,7 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm)
struct clk_init_data vco_init = {
.parent_names = (const char *[]){ "pxo" },
.num_parents = 1,
+ .flags = CLK_IGNORE_UNUSED,
.ops = &clk_ops_dsi_pll_28nm_vco,
};
struct device *dev = &pll_28nm->pdev->dev;
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c
index aa94a55..143eab4 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c
@@ -702,6 +702,7 @@ static struct clk_init_data pll_init = {
.ops = &hdmi_8996_pll_ops,
.parent_names = hdmi_pll_parents,
.num_parents = ARRAY_SIZE(hdmi_pll_parents),
+ .flags = CLK_IGNORE_UNUSED,
};
int msm_hdmi_pll_8996_init(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c b/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c
index 92da69a..9959075 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_pll_8960.c
@@ -424,6 +424,7 @@ static struct clk_init_data pll_init = {
.ops = &hdmi_pll_ops,
.parent_names = hdmi_pll_parents,
.num_parents = ARRAY_SIZE(hdmi_pll_parents),
+ .flags = CLK_IGNORE_UNUSED,
};
int msm_hdmi_pll_8960_init(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c
index ac9e4cd..8b4e300 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c
@@ -272,7 +272,7 @@ const struct mdp5_cfg_hw msm8x16_config = {
.count = 2,
.base = { 0x14000, 0x16000 },
.caps = MDP_PIPE_CAP_HFLIP | MDP_PIPE_CAP_VFLIP |
- MDP_PIPE_CAP_SCALE | MDP_PIPE_CAP_DECIMATION,
+ MDP_PIPE_CAP_DECIMATION,
},
.pipe_dma = {
.count = 1,
@@ -282,7 +282,7 @@ const struct mdp5_cfg_hw msm8x16_config = {
.lm = {
.count = 2, /* LM0 and LM3 */
.base = { 0x44000, 0x47000 },
- .nb_stages = 5,
+ .nb_stages = 8,
.max_width = 2048,
.max_height = 0xFFFF,
},
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
index fa2be7c..c205c36 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
@@ -223,12 +223,7 @@ static void blend_setup(struct drm_crtc *crtc)
plane_cnt++;
}
- /*
- * If there is no base layer, enable border color.
- * Although it's not possbile in current blend logic,
- * put it here as a reminder.
- */
- if (!pstates[STAGE_BASE] && plane_cnt) {
+ if (!pstates[STAGE_BASE]) {
ctl_blend_flags |= MDP5_CTL_BLEND_OP_FLAG_BORDER_OUT;
DBG("Border Color is enabled");
}
@@ -365,6 +360,15 @@ static int pstate_cmp(const void *a, const void *b)
return pa->state->zpos - pb->state->zpos;
}
+/* is there a helper for this? */
+static bool is_fullscreen(struct drm_crtc_state *cstate,
+ struct drm_plane_state *pstate)
+{
+ return (pstate->crtc_x <= 0) && (pstate->crtc_y <= 0) &&
+ ((pstate->crtc_x + pstate->crtc_w) >= cstate->mode.hdisplay) &&
+ ((pstate->crtc_y + pstate->crtc_h) >= cstate->mode.vdisplay);
+}
+
static int mdp5_crtc_atomic_check(struct drm_crtc *crtc,
struct drm_crtc_state *state)
{
@@ -375,21 +379,11 @@ static int mdp5_crtc_atomic_check(struct drm_crtc *crtc,
struct plane_state pstates[STAGE_MAX + 1];
const struct mdp5_cfg_hw *hw_cfg;
const struct drm_plane_state *pstate;
- int cnt = 0, i;
+ int cnt = 0, base = 0, i;
DBG("%s: check", mdp5_crtc->name);
- /* verify that there are not too many planes attached to crtc
- * and that we don't have conflicting mixer stages:
- */
- hw_cfg = mdp5_cfg_get_hw_config(mdp5_kms->cfg);
drm_atomic_crtc_state_for_each_plane_state(plane, pstate, state) {
- if (cnt >= (hw_cfg->lm.nb_stages)) {
- dev_err(dev->dev, "too many planes!\n");
- return -EINVAL;
- }
-
-
pstates[cnt].plane = plane;
pstates[cnt].state = to_mdp5_plane_state(pstate);
@@ -399,8 +393,24 @@ static int mdp5_crtc_atomic_check(struct drm_crtc *crtc,
/* assign a stage based on sorted zpos property */
sort(pstates, cnt, sizeof(pstates[0]), pstate_cmp, NULL);
+ /* if the bottom-most layer is not fullscreen, we need to use
+ * it for solid-color:
+ */
+ if ((cnt > 0) && !is_fullscreen(state, &pstates[0].state->base))
+ base++;
+
+ /* verify that there are not too many planes attached to crtc
+ * and that we don't have conflicting mixer stages:
+ */
+ hw_cfg = mdp5_cfg_get_hw_config(mdp5_kms->cfg);
+
+ if ((cnt + base) >= hw_cfg->lm.nb_stages) {
+ dev_err(dev->dev, "too many planes!\n");
+ return -EINVAL;
+ }
+
for (i = 0; i < cnt; i++) {
- pstates[i].state->stage = STAGE_BASE + i;
+ pstates[i].state->stage = STAGE_BASE + i + base;
DBG("%s: assign pipe %s on stage=%d", mdp5_crtc->name,
pipe2name(mdp5_plane_pipe(pstates[i].plane)),
pstates[i].state->stage);
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
index 951c002..83bf997 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
@@ -292,8 +292,7 @@ static int mdp5_plane_atomic_check(struct drm_plane *plane,
format = to_mdp_format(msm_framebuffer_format(state->fb));
if (MDP_FORMAT_IS_YUV(format) &&
!pipe_supports_yuv(mdp5_plane->caps)) {
- dev_err(plane->dev->dev,
- "Pipe doesn't support YUV\n");
+ DBG("Pipe doesn't support YUV\n");
return -EINVAL;
}
@@ -301,8 +300,7 @@ static int mdp5_plane_atomic_check(struct drm_plane *plane,
if (!(mdp5_plane->caps & MDP_PIPE_CAP_SCALE) &&
(((state->src_w >> 16) != state->crtc_w) ||
((state->src_h >> 16) != state->crtc_h))) {
- dev_err(plane->dev->dev,
- "Pipe doesn't support scaling (%dx%d -> %dx%d)\n",
+ DBG("Pipe doesn't support scaling (%dx%d -> %dx%d)\n",
state->src_w >> 16, state->src_h >> 16,
state->crtc_w, state->crtc_h);
@@ -313,8 +311,7 @@ static int mdp5_plane_atomic_check(struct drm_plane *plane,
vflip = !!(state->rotation & DRM_REFLECT_Y);
if ((vflip && !(mdp5_plane->caps & MDP_PIPE_CAP_VFLIP)) ||
(hflip && !(mdp5_plane->caps & MDP_PIPE_CAP_HFLIP))) {
- dev_err(plane->dev->dev,
- "Pipe doesn't support flip\n");
+ DBG("Pipe doesn't support flip\n");
return -EINVAL;
}
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index fb5c0b0..46568fc 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -228,7 +228,7 @@ static int msm_drm_uninit(struct device *dev)
flush_workqueue(priv->atomic_wq);
destroy_workqueue(priv->atomic_wq);
- if (kms)
+ if (kms && kms->funcs)
kms->funcs->destroy(kms);
if (gpu) {
diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c
index 283d284..192b2d3 100644
--- a/drivers/gpu/drm/msm/msm_gem_shrinker.c
+++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c
@@ -163,6 +163,9 @@ void msm_gem_shrinker_init(struct drm_device *dev)
void msm_gem_shrinker_cleanup(struct drm_device *dev)
{
struct msm_drm_private *priv = dev->dev_private;
- WARN_ON(unregister_vmap_purge_notifier(&priv->vmap_notifier));
- unregister_shrinker(&priv->shrinker);
+
+ if (priv->shrinker.nr_deferred) {
+ WARN_ON(unregister_vmap_purge_notifier(&priv->vmap_notifier));
+ unregister_shrinker(&priv->shrinker);
+ }
}
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index dc57b62..193573d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -240,7 +240,8 @@ static bool nouveau_pr3_present(struct pci_dev *pdev)
if (!parent_adev)
return false;
- return acpi_has_method(parent_adev->handle, "_PR3");
+ return parent_adev->power.flags.power_resources &&
+ acpi_has_method(parent_adev->handle, "_PR3");
}
static void nouveau_dsm_pci_probe(struct pci_dev *pdev, acpi_handle *dhandle_out,
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 1825dbc..a6dbe82 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -398,6 +398,9 @@ nouveau_ttm_init(struct nouveau_drm *drm)
/* VRAM init */
drm->gem.vram_available = drm->device.info.ram_user;
+ arch_io_reserve_memtype_wc(device->func->resource_addr(device, 1),
+ device->func->resource_size(device, 1));
+
ret = ttm_bo_init_mm(&drm->ttm.bdev, TTM_PL_VRAM,
drm->gem.vram_available >> PAGE_SHIFT);
if (ret) {
@@ -430,6 +433,8 @@ nouveau_ttm_init(struct nouveau_drm *drm)
void
nouveau_ttm_fini(struct nouveau_drm *drm)
{
+ struct nvkm_device *device = nvxx_device(&drm->device);
+
ttm_bo_clean_mm(&drm->ttm.bdev, TTM_PL_VRAM);
ttm_bo_clean_mm(&drm->ttm.bdev, TTM_PL_TT);
@@ -439,4 +444,7 @@ nouveau_ttm_fini(struct nouveau_drm *drm)
arch_phys_wc_del(drm->ttm.mtrr);
drm->ttm.mtrr = 0;
+ arch_io_free_memtype_wc(device->func->resource_addr(device, 1),
+ device->func->resource_size(device, 1));
+
}
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 103fc86..a0d4a05 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1396,9 +1396,7 @@ static void cayman_pcie_gart_fini(struct radeon_device *rdev)
void cayman_cp_int_cntl_setup(struct radeon_device *rdev,
int ring, u32 cp_int_cntl)
{
- u32 srbm_gfx_cntl = RREG32(SRBM_GFX_CNTL) & ~3;
-
- WREG32(SRBM_GFX_CNTL, srbm_gfx_cntl | (ring & 3));
+ WREG32(SRBM_GFX_CNTL, RINGID(ring));
WREG32(CP_INT_CNTL, cp_int_cntl);
}
diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c
index 6a4b020..5a26eb4 100644
--- a/drivers/gpu/drm/radeon/r600_dpm.c
+++ b/drivers/gpu/drm/radeon/r600_dpm.c
@@ -156,19 +156,20 @@ u32 r600_dpm_get_vblank_time(struct radeon_device *rdev)
struct drm_device *dev = rdev->ddev;
struct drm_crtc *crtc;
struct radeon_crtc *radeon_crtc;
- u32 line_time_us, vblank_lines;
+ u32 vblank_in_pixels;
u32 vblank_time_us = 0xffffffff; /* if the displays are off, vblank time is max */
if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) {
list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
radeon_crtc = to_radeon_crtc(crtc);
if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) {
- line_time_us = (radeon_crtc->hw_mode.crtc_htotal * 1000) /
- radeon_crtc->hw_mode.clock;
- vblank_lines = radeon_crtc->hw_mode.crtc_vblank_end -
- radeon_crtc->hw_mode.crtc_vdisplay +
- (radeon_crtc->v_border * 2);
- vblank_time_us = vblank_lines * line_time_us;
+ vblank_in_pixels =
+ radeon_crtc->hw_mode.crtc_htotal *
+ (radeon_crtc->hw_mode.crtc_vblank_end -
+ radeon_crtc->hw_mode.crtc_vdisplay +
+ (radeon_crtc->v_border * 2));
+
+ vblank_time_us = vblank_in_pixels * 1000 / radeon_crtc->hw_mode.clock;
break;
}
}
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 50e96d2..27affbd 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -927,6 +927,16 @@ radeon_lvds_detect(struct drm_connector *connector, bool force)
return ret;
}
+static void radeon_connector_unregister(struct drm_connector *connector)
+{
+ struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+
+ if (radeon_connector->ddc_bus && radeon_connector->ddc_bus->has_aux) {
+ drm_dp_aux_unregister(&radeon_connector->ddc_bus->aux);
+ radeon_connector->ddc_bus->has_aux = false;
+ }
+}
+
static void radeon_connector_destroy(struct drm_connector *connector)
{
struct radeon_connector *radeon_connector = to_radeon_connector(connector);
@@ -984,6 +994,7 @@ static const struct drm_connector_funcs radeon_lvds_connector_funcs = {
.dpms = drm_helper_connector_dpms,
.detect = radeon_lvds_detect,
.fill_modes = drm_helper_probe_single_connector_modes,
+ .early_unregister = radeon_connector_unregister,
.destroy = radeon_connector_destroy,
.set_property = radeon_lvds_set_property,
};
@@ -1111,6 +1122,7 @@ static const struct drm_connector_funcs radeon_vga_connector_funcs = {
.dpms = drm_helper_connector_dpms,
.detect = radeon_vga_detect,
.fill_modes = drm_helper_probe_single_connector_modes,
+ .early_unregister = radeon_connector_unregister,
.destroy = radeon_connector_destroy,
.set_property = radeon_connector_set_property,
};
@@ -1188,6 +1200,7 @@ static const struct drm_connector_funcs radeon_tv_connector_funcs = {
.dpms = drm_helper_connector_dpms,
.detect = radeon_tv_detect,
.fill_modes = drm_helper_probe_single_connector_modes,
+ .early_unregister = radeon_connector_unregister,
.destroy = radeon_connector_destroy,
.set_property = radeon_connector_set_property,
};
@@ -1519,6 +1532,7 @@ static const struct drm_connector_funcs radeon_dvi_connector_funcs = {
.detect = radeon_dvi_detect,
.fill_modes = drm_helper_probe_single_connector_modes,
.set_property = radeon_connector_set_property,
+ .early_unregister = radeon_connector_unregister,
.destroy = radeon_connector_destroy,
.force = radeon_dvi_force,
};
@@ -1832,6 +1846,7 @@ static const struct drm_connector_funcs radeon_dp_connector_funcs = {
.detect = radeon_dp_detect,
.fill_modes = drm_helper_probe_single_connector_modes,
.set_property = radeon_connector_set_property,
+ .early_unregister = radeon_connector_unregister,
.destroy = radeon_connector_destroy,
.force = radeon_dvi_force,
};
@@ -1841,6 +1856,7 @@ static const struct drm_connector_funcs radeon_edp_connector_funcs = {
.detect = radeon_dp_detect,
.fill_modes = drm_helper_probe_single_connector_modes,
.set_property = radeon_lvds_set_property,
+ .early_unregister = radeon_connector_unregister,
.destroy = radeon_connector_destroy,
.force = radeon_dvi_force,
};
@@ -1850,6 +1866,7 @@ static const struct drm_connector_funcs radeon_lvds_bridge_connector_funcs = {
.detect = radeon_dp_detect,
.fill_modes = drm_helper_probe_single_connector_modes,
.set_property = radeon_lvds_set_property,
+ .early_unregister = radeon_connector_unregister,
.destroy = radeon_connector_destroy,
.force = radeon_dvi_force,
};
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index eb92aef..621af06 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -104,6 +104,14 @@ static const char radeon_family_name[][16] = {
"LAST",
};
+#if defined(CONFIG_VGA_SWITCHEROO)
+bool radeon_has_atpx_dgpu_power_cntl(void);
+bool radeon_is_atpx_hybrid(void);
+#else
+static inline bool radeon_has_atpx_dgpu_power_cntl(void) { return false; }
+static inline bool radeon_is_atpx_hybrid(void) { return false; }
+#endif
+
#define RADEON_PX_QUIRK_DISABLE_PX (1 << 0)
#define RADEON_PX_QUIRK_LONG_WAKEUP (1 << 1)
@@ -160,6 +168,11 @@ static void radeon_device_handle_px_quirks(struct radeon_device *rdev)
if (rdev->px_quirk_flags & RADEON_PX_QUIRK_DISABLE_PX)
rdev->flags &= ~RADEON_IS_PX;
+
+ /* disable PX is the system doesn't support dGPU power control or hybrid gfx */
+ if (!radeon_is_atpx_hybrid() &&
+ !radeon_has_atpx_dgpu_power_cntl())
+ rdev->flags &= ~RADEON_IS_PX;
}
/**
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index b8ab30a..cdb8cb56 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -1675,20 +1675,20 @@ int radeon_modeset_init(struct radeon_device *rdev)
void radeon_modeset_fini(struct radeon_device *rdev)
{
- radeon_fbdev_fini(rdev);
+ if (rdev->mode_info.mode_config_initialized) {
+ drm_kms_helper_poll_fini(rdev->ddev);
+ radeon_hpd_fini(rdev);
+ drm_crtc_force_disable_all(rdev->ddev);
+ radeon_fbdev_fini(rdev);
+ radeon_afmt_fini(rdev);
+ drm_mode_config_cleanup(rdev->ddev);
+ rdev->mode_info.mode_config_initialized = false;
+ }
+
kfree(rdev->mode_info.bios_hardcoded_edid);
/* free i2c buses */
radeon_i2c_fini(rdev);
-
- if (rdev->mode_info.mode_config_initialized) {
- radeon_afmt_fini(rdev);
- drm_kms_helper_poll_fini(rdev->ddev);
- radeon_hpd_fini(rdev);
- drm_crtc_force_disable_all(rdev->ddev);
- drm_mode_config_cleanup(rdev->ddev);
- rdev->mode_info.mode_config_initialized = false;
- }
}
static bool is_hdtv_mode(const struct drm_display_mode *mode)
diff --git a/drivers/gpu/drm/radeon/radeon_dp_auxch.c b/drivers/gpu/drm/radeon/radeon_dp_auxch.c
index 2d46564..474a8a18 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_auxch.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_auxch.c
@@ -105,7 +105,7 @@ radeon_dp_aux_transfer_native(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg
tmp &= AUX_HPD_SEL(0x7);
tmp |= AUX_HPD_SEL(chan->rec.hpd);
- tmp |= AUX_EN | AUX_LS_READ_EN | AUX_HPD_DISCON(0x1);
+ tmp |= AUX_EN | AUX_LS_READ_EN;
WREG32(AUX_CONTROL + aux_offset[instance], tmp);
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 91c8f43..00ea000 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -96,9 +96,10 @@
* 2.45.0 - Allow setting shader registers using DMA/COPY packet3 on SI
* 2.46.0 - Add PFP_SYNC_ME support on evergreen
* 2.47.0 - Add UVD_NO_OP register support
+ * 2.48.0 - TA_CS_BC_BASE_ADDR allowed on SI
*/
#define KMS_DRIVER_MAJOR 2
-#define KMS_DRIVER_MINOR 47
+#define KMS_DRIVER_MINOR 48
#define KMS_DRIVER_PATCHLEVEL 0
int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
int radeon_driver_unload_kms(struct drm_device *dev);
diff --git a/drivers/gpu/drm/radeon/radeon_i2c.c b/drivers/gpu/drm/radeon/radeon_i2c.c
index 021aa00..29f7817 100644
--- a/drivers/gpu/drm/radeon/radeon_i2c.c
+++ b/drivers/gpu/drm/radeon/radeon_i2c.c
@@ -982,9 +982,8 @@ void radeon_i2c_destroy(struct radeon_i2c_chan *i2c)
{
if (!i2c)
return;
+ WARN_ON(i2c->has_aux);
i2c_del_adapter(&i2c->adapter);
- if (i2c->has_aux)
- drm_dp_aux_unregister(&i2c->aux);
kfree(i2c);
}
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index be30861..41b72ce 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -446,6 +446,10 @@ void radeon_bo_force_delete(struct radeon_device *rdev)
int radeon_bo_init(struct radeon_device *rdev)
{
+ /* reserve PAT memory space to WC for VRAM */
+ arch_io_reserve_memtype_wc(rdev->mc.aper_base,
+ rdev->mc.aper_size);
+
/* Add an MTRR for the VRAM */
if (!rdev->fastfb_working) {
rdev->mc.vram_mtrr = arch_phys_wc_add(rdev->mc.aper_base,
@@ -463,6 +467,7 @@ void radeon_bo_fini(struct radeon_device *rdev)
{
radeon_ttm_fini(rdev);
arch_phys_wc_del(rdev->mc.vram_mtrr);
+ arch_io_free_memtype_wc(rdev->mc.aper_base, rdev->mc.aper_size);
}
/* Returns how many bytes TTM can move per IB.
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 4552682..3de5e6e 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -566,7 +566,8 @@ static int radeon_ttm_tt_pin_userptr(struct ttm_tt *ttm)
uint64_t userptr = gtt->userptr + pinned * PAGE_SIZE;
struct page **pages = ttm->pages + pinned;
- r = get_user_pages(userptr, num_pages, write, 0, pages, NULL);
+ r = get_user_pages(userptr, num_pages, write ? FOLL_WRITE : 0,
+ pages, NULL);
if (r < 0)
goto release_pages;
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 7ee9aaf..e402be8 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -4431,6 +4431,7 @@ static bool si_vm_reg_valid(u32 reg)
case SPI_CONFIG_CNTL:
case SPI_CONFIG_CNTL_1:
case TA_CNTL_AUX:
+ case TA_CS_BC_BASE_ADDR:
return true;
default:
DRM_ERROR("Invalid register 0x%x in CS\n", reg);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 89bdf20..c4993452 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2999,6 +2999,49 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
int i;
struct si_dpm_quirk *p = si_dpm_quirk_list;
+ /* limit all SI kickers */
+ if (rdev->family == CHIP_PITCAIRN) {
+ if ((rdev->pdev->revision == 0x81) ||
+ (rdev->pdev->device == 0x6810) ||
+ (rdev->pdev->device == 0x6811) ||
+ (rdev->pdev->device == 0x6816) ||
+ (rdev->pdev->device == 0x6817) ||
+ (rdev->pdev->device == 0x6806))
+ max_mclk = 120000;
+ } else if (rdev->family == CHIP_VERDE) {
+ if ((rdev->pdev->revision == 0x81) ||
+ (rdev->pdev->revision == 0x83) ||
+ (rdev->pdev->revision == 0x87) ||
+ (rdev->pdev->device == 0x6820) ||
+ (rdev->pdev->device == 0x6821) ||
+ (rdev->pdev->device == 0x6822) ||
+ (rdev->pdev->device == 0x6823) ||
+ (rdev->pdev->device == 0x682A) ||
+ (rdev->pdev->device == 0x682B)) {
+ max_sclk = 75000;
+ max_mclk = 80000;
+ }
+ } else if (rdev->family == CHIP_OLAND) {
+ if ((rdev->pdev->revision == 0xC7) ||
+ (rdev->pdev->revision == 0x80) ||
+ (rdev->pdev->revision == 0x81) ||
+ (rdev->pdev->revision == 0x83) ||
+ (rdev->pdev->device == 0x6604) ||
+ (rdev->pdev->device == 0x6605)) {
+ max_sclk = 75000;
+ max_mclk = 80000;
+ }
+ } else if (rdev->family == CHIP_HAINAN) {
+ if ((rdev->pdev->revision == 0x81) ||
+ (rdev->pdev->revision == 0x83) ||
+ (rdev->pdev->revision == 0xC3) ||
+ (rdev->pdev->device == 0x6664) ||
+ (rdev->pdev->device == 0x6665) ||
+ (rdev->pdev->device == 0x6667)) {
+ max_sclk = 75000;
+ max_mclk = 80000;
+ }
+ }
/* Apply dpm quirks */
while (p && p->chip_device != 0) {
if (rdev->pdev->vendor == p->chip_vendor &&
@@ -3011,16 +3054,6 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
}
++p;
}
- /* limit mclk on all R7 370 parts for stability */
- if (rdev->pdev->device == 0x6811 &&
- rdev->pdev->revision == 0x81)
- max_mclk = 120000;
- /* limit sclk/mclk on Jet parts for stability */
- if (rdev->pdev->device == 0x6665 &&
- rdev->pdev->revision == 0xc3) {
- max_sclk = 75000;
- max_mclk = 80000;
- }
if (rps->vce_active) {
rps->evclk = rdev->pm.dpm.vce_states[rdev->pm.dpm.vce_level].evclk;
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index eb220ee..65a911d 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -1145,6 +1145,7 @@
#define SPI_LB_CU_MASK 0x9354
#define TA_CNTL_AUX 0x9508
+#define TA_CS_BC_BASE_ADDR 0x950C
#define CC_RB_BACKEND_DISABLE 0x98F4
#define BACKEND_DISABLE(x) ((x) << 16)
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
index bd9c3bb..392c7e6 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
@@ -231,8 +231,16 @@ static int rcar_du_atomic_check(struct drm_device *dev,
struct rcar_du_device *rcdu = dev->dev_private;
int ret;
- ret = drm_atomic_helper_check(dev, state);
- if (ret < 0)
+ ret = drm_atomic_helper_check_modeset(dev, state);
+ if (ret)
+ return ret;
+
+ ret = drm_atomic_normalize_zpos(dev, state);
+ if (ret)
+ return ret;
+
+ ret = drm_atomic_helper_check_planes(dev, state);
+ if (ret)
return ret;
if (rcar_du_has(rcdu, RCAR_DU_FEATURE_VSP1_SOURCE))
diff --git a/drivers/gpu/drm/sti/sti_drv.c b/drivers/gpu/drm/sti/sti_drv.c
index 2784919..9df3085 100644
--- a/drivers/gpu/drm/sti/sti_drv.c
+++ b/drivers/gpu/drm/sti/sti_drv.c
@@ -195,6 +195,26 @@ static void sti_atomic_work(struct work_struct *work)
sti_atomic_complete(private, private->commit.state);
}
+static int sti_atomic_check(struct drm_device *dev,
+ struct drm_atomic_state *state)
+{
+ int ret;
+
+ ret = drm_atomic_helper_check_modeset(dev, state);
+ if (ret)
+ return ret;
+
+ ret = drm_atomic_normalize_zpos(dev, state);
+ if (ret)
+ return ret;
+
+ ret = drm_atomic_helper_check_planes(dev, state);
+ if (ret)
+ return ret;
+
+ return ret;
+}
+
static int sti_atomic_commit(struct drm_device *drm,
struct drm_atomic_state *state, bool nonblock)
{
@@ -248,7 +268,7 @@ static void sti_output_poll_changed(struct drm_device *ddev)
static const struct drm_mode_config_funcs sti_mode_config_funcs = {
.fb_create = drm_fb_cma_create,
.output_poll_changed = sti_output_poll_changed,
- .atomic_check = drm_atomic_helper_check,
+ .atomic_check = sti_atomic_check,
.atomic_commit = sti_atomic_commit,
};
diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c
index 29f0207..873f010 100644
--- a/drivers/gpu/drm/udl/udl_main.c
+++ b/drivers/gpu/drm/udl/udl_main.c
@@ -98,17 +98,23 @@ static int udl_parse_vendor_descriptor(struct drm_device *dev,
static int udl_select_std_channel(struct udl_device *udl)
{
int ret;
- u8 set_def_chn[] = {0x57, 0xCD, 0xDC, 0xA7,
- 0x1C, 0x88, 0x5E, 0x15,
- 0x60, 0xFE, 0xC6, 0x97,
- 0x16, 0x3D, 0x47, 0xF2};
+ static const u8 set_def_chn[] = {0x57, 0xCD, 0xDC, 0xA7,
+ 0x1C, 0x88, 0x5E, 0x15,
+ 0x60, 0xFE, 0xC6, 0x97,
+ 0x16, 0x3D, 0x47, 0xF2};
+ void *sendbuf;
+
+ sendbuf = kmemdup(set_def_chn, sizeof(set_def_chn), GFP_KERNEL);
+ if (!sendbuf)
+ return -ENOMEM;
ret = usb_control_msg(udl->udev,
usb_sndctrlpipe(udl->udev, 0),
NR_USB_REQUEST_CHANNEL,
(USB_DIR_OUT | USB_TYPE_VENDOR), 0, 0,
- set_def_chn, sizeof(set_def_chn),
+ sendbuf, sizeof(set_def_chn),
USB_CTRL_SET_TIMEOUT);
+ kfree(sendbuf);
return ret < 0 ? ret : 0;
}
diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c
index 7e2a12c..1a3ad76 100644
--- a/drivers/gpu/drm/via/via_dmablit.c
+++ b/drivers/gpu/drm/via/via_dmablit.c
@@ -241,8 +241,8 @@ via_lock_all_dma_pages(drm_via_sg_info_t *vsg, drm_via_dmablit_t *xfer)
down_read(¤t->mm->mmap_sem);
ret = get_user_pages((unsigned long)xfer->mem_addr,
vsg->num_pages,
- (vsg->direction == DMA_FROM_DEVICE),
- 0, vsg->pages, NULL);
+ (vsg->direction == DMA_FROM_DEVICE) ? FOLL_WRITE : 0,
+ vsg->pages, NULL);
up_read(¤t->mm->mmap_sem);
if (ret != vsg->num_pages) {
diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c
index 7cf3678..5804870 100644
--- a/drivers/gpu/drm/virtio/virtgpu_display.c
+++ b/drivers/gpu/drm/virtio/virtgpu_display.c
@@ -338,8 +338,7 @@ static void vgdev_atomic_commit_tail(struct drm_atomic_state *state)
drm_atomic_helper_commit_modeset_disables(dev, state);
drm_atomic_helper_commit_modeset_enables(dev, state);
- drm_atomic_helper_commit_planes(dev, state,
- DRM_PLANE_COMMIT_ACTIVE_ONLY);
+ drm_atomic_helper_commit_planes(dev, state, 0);
drm_atomic_helper_commit_hw_done(state);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index e8ae3dc..18061a4 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -241,15 +241,15 @@ static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val,
void *ptr);
MODULE_PARM_DESC(enable_fbdev, "Enable vmwgfx fbdev");
-module_param_named(enable_fbdev, enable_fbdev, int, 0600);
+module_param_named(enable_fbdev, enable_fbdev, int, S_IRUSR | S_IWUSR);
MODULE_PARM_DESC(force_dma_api, "Force using the DMA API for TTM pages");
-module_param_named(force_dma_api, vmw_force_iommu, int, 0600);
+module_param_named(force_dma_api, vmw_force_iommu, int, S_IRUSR | S_IWUSR);
MODULE_PARM_DESC(restrict_iommu, "Try to limit IOMMU usage for TTM pages");
-module_param_named(restrict_iommu, vmw_restrict_iommu, int, 0600);
+module_param_named(restrict_iommu, vmw_restrict_iommu, int, S_IRUSR | S_IWUSR);
MODULE_PARM_DESC(force_coherent, "Force coherent TTM pages");
-module_param_named(force_coherent, vmw_force_coherent, int, 0600);
+module_param_named(force_coherent, vmw_force_coherent, int, S_IRUSR | S_IWUSR);
MODULE_PARM_DESC(restrict_dma_mask, "Restrict DMA mask to 44 bits with IOMMU");
-module_param_named(restrict_dma_mask, vmw_restrict_dma_mask, int, 0600);
+module_param_named(restrict_dma_mask, vmw_restrict_dma_mask, int, S_IRUSR | S_IWUSR);
MODULE_PARM_DESC(assume_16bpp, "Assume 16-bpp when filtering modes");
module_param_named(assume_16bpp, vmw_assume_16bpp, int, 0600);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 070d750..1e59a48 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -43,7 +43,7 @@
#define VMWGFX_DRIVER_DATE "20160210"
#define VMWGFX_DRIVER_MAJOR 2
-#define VMWGFX_DRIVER_MINOR 10
+#define VMWGFX_DRIVER_MINOR 11
#define VMWGFX_DRIVER_PATCHLEVEL 0
#define VMWGFX_FILE_PAGE_OFFSET 0x00100000
#define VMWGFX_FIFO_STATIC_SIZE (1024*1024)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index dc5beff..c7b53d9 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -35,17 +35,37 @@
#define VMW_RES_HT_ORDER 12
/**
+ * enum vmw_resource_relocation_type - Relocation type for resources
+ *
+ * @vmw_res_rel_normal: Traditional relocation. The resource id in the
+ * command stream is replaced with the actual id after validation.
+ * @vmw_res_rel_nop: NOP relocation. The command is unconditionally replaced
+ * with a NOP.
+ * @vmw_res_rel_cond_nop: Conditional NOP relocation. If the resource id
+ * after validation is -1, the command is replaced with a NOP. Otherwise no
+ * action.
+ */
+enum vmw_resource_relocation_type {
+ vmw_res_rel_normal,
+ vmw_res_rel_nop,
+ vmw_res_rel_cond_nop,
+ vmw_res_rel_max
+};
+
+/**
* struct vmw_resource_relocation - Relocation info for resources
*
* @head: List head for the software context's relocation list.
* @res: Non-ref-counted pointer to the resource.
- * @offset: Offset of 4 byte entries into the command buffer where the
+ * @offset: Offset of single byte entries into the command buffer where the
* id that needs fixup is located.
+ * @rel_type: Type of relocation.
*/
struct vmw_resource_relocation {
struct list_head head;
const struct vmw_resource *res;
- unsigned long offset;
+ u32 offset:29;
+ enum vmw_resource_relocation_type rel_type:3;
};
/**
@@ -109,7 +129,18 @@ static int vmw_bo_to_validate_list(struct vmw_sw_context *sw_context,
struct vmw_dma_buffer *vbo,
bool validate_as_mob,
uint32_t *p_val_node);
-
+/**
+ * vmw_ptr_diff - Compute the offset from a to b in bytes
+ *
+ * @a: A starting pointer.
+ * @b: A pointer offset in the same address space.
+ *
+ * Returns: The offset in bytes between the two pointers.
+ */
+static size_t vmw_ptr_diff(void *a, void *b)
+{
+ return (unsigned long) b - (unsigned long) a;
+}
/**
* vmw_resources_unreserve - unreserve resources previously reserved for
@@ -409,11 +440,14 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv,
* @list: Pointer to head of relocation list.
* @res: The resource.
* @offset: Offset into the command buffer currently being parsed where the
- * id that needs fixup is located. Granularity is 4 bytes.
+ * id that needs fixup is located. Granularity is one byte.
+ * @rel_type: Relocation type.
*/
static int vmw_resource_relocation_add(struct list_head *list,
const struct vmw_resource *res,
- unsigned long offset)
+ unsigned long offset,
+ enum vmw_resource_relocation_type
+ rel_type)
{
struct vmw_resource_relocation *rel;
@@ -425,6 +459,7 @@ static int vmw_resource_relocation_add(struct list_head *list,
rel->res = res;
rel->offset = offset;
+ rel->rel_type = rel_type;
list_add_tail(&rel->head, list);
return 0;
@@ -459,11 +494,24 @@ static void vmw_resource_relocations_apply(uint32_t *cb,
{
struct vmw_resource_relocation *rel;
+ /* Validate the struct vmw_resource_relocation member size */
+ BUILD_BUG_ON(SVGA_CB_MAX_SIZE >= (1 << 29));
+ BUILD_BUG_ON(vmw_res_rel_max >= (1 << 3));
+
list_for_each_entry(rel, list, head) {
- if (likely(rel->res != NULL))
- cb[rel->offset] = rel->res->id;
- else
- cb[rel->offset] = SVGA_3D_CMD_NOP;
+ u32 *addr = (u32 *)((unsigned long) cb + rel->offset);
+ switch (rel->rel_type) {
+ case vmw_res_rel_normal:
+ *addr = rel->res->id;
+ break;
+ case vmw_res_rel_nop:
+ *addr = SVGA_3D_CMD_NOP;
+ break;
+ default:
+ if (rel->res->id == -1)
+ *addr = SVGA_3D_CMD_NOP;
+ break;
+ }
}
}
@@ -655,7 +703,9 @@ static int vmw_cmd_res_reloc_add(struct vmw_private *dev_priv,
*p_val = NULL;
ret = vmw_resource_relocation_add(&sw_context->res_relocations,
res,
- id_loc - sw_context->buf_start);
+ vmw_ptr_diff(sw_context->buf_start,
+ id_loc),
+ vmw_res_rel_normal);
if (unlikely(ret != 0))
return ret;
@@ -721,7 +771,8 @@ vmw_cmd_res_check(struct vmw_private *dev_priv,
return vmw_resource_relocation_add
(&sw_context->res_relocations, res,
- id_loc - sw_context->buf_start);
+ vmw_ptr_diff(sw_context->buf_start, id_loc),
+ vmw_res_rel_normal);
}
ret = vmw_user_resource_lookup_handle(dev_priv,
@@ -2143,10 +2194,10 @@ static int vmw_cmd_shader_define(struct vmw_private *dev_priv,
return ret;
return vmw_resource_relocation_add(&sw_context->res_relocations,
- NULL, &cmd->header.id -
- sw_context->buf_start);
-
- return 0;
+ NULL,
+ vmw_ptr_diff(sw_context->buf_start,
+ &cmd->header.id),
+ vmw_res_rel_nop);
}
/**
@@ -2188,10 +2239,10 @@ static int vmw_cmd_shader_destroy(struct vmw_private *dev_priv,
return ret;
return vmw_resource_relocation_add(&sw_context->res_relocations,
- NULL, &cmd->header.id -
- sw_context->buf_start);
-
- return 0;
+ NULL,
+ vmw_ptr_diff(sw_context->buf_start,
+ &cmd->header.id),
+ vmw_res_rel_nop);
}
/**
@@ -2848,8 +2899,7 @@ static int vmw_cmd_dx_cid_check(struct vmw_private *dev_priv,
* @header: Pointer to the command header in the command stream.
*
* Check that the view exists, and if it was not created using this
- * command batch, make sure it's validated (present in the device) so that
- * the remove command will not confuse the device.
+ * command batch, conditionally make this command a NOP.
*/
static int vmw_cmd_dx_view_remove(struct vmw_private *dev_priv,
struct vmw_sw_context *sw_context,
@@ -2877,10 +2927,16 @@ static int vmw_cmd_dx_view_remove(struct vmw_private *dev_priv,
return ret;
/*
- * Add view to the validate list iff it was not created using this
- * command batch.
+ * If the view wasn't created during this command batch, it might
+ * have been removed due to a context swapout, so add a
+ * relocation to conditionally make this command a NOP to avoid
+ * device errors.
*/
- return vmw_view_res_val_add(sw_context, view);
+ return vmw_resource_relocation_add(&sw_context->res_relocations,
+ view,
+ vmw_ptr_diff(sw_context->buf_start,
+ &cmd->header.id),
+ vmw_res_rel_cond_nop);
}
/**
@@ -3029,6 +3085,35 @@ static int vmw_cmd_dx_genmips(struct vmw_private *dev_priv,
cmd->body.shaderResourceViewId);
}
+/**
+ * vmw_cmd_dx_transfer_from_buffer -
+ * Validate an SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER command
+ *
+ * @dev_priv: Pointer to a device private struct.
+ * @sw_context: The software context being used for this batch.
+ * @header: Pointer to the command header in the command stream.
+ */
+static int vmw_cmd_dx_transfer_from_buffer(struct vmw_private *dev_priv,
+ struct vmw_sw_context *sw_context,
+ SVGA3dCmdHeader *header)
+{
+ struct {
+ SVGA3dCmdHeader header;
+ SVGA3dCmdDXTransferFromBuffer body;
+ } *cmd = container_of(header, typeof(*cmd), header);
+ int ret;
+
+ ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
+ user_surface_converter,
+ &cmd->body.srcSid, NULL);
+ if (ret != 0)
+ return ret;
+
+ return vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
+ user_surface_converter,
+ &cmd->body.destSid, NULL);
+}
+
static int vmw_cmd_check_not_3d(struct vmw_private *dev_priv,
struct vmw_sw_context *sw_context,
void *buf, uint32_t *size)
@@ -3379,6 +3464,9 @@ static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = {
&vmw_cmd_buffer_copy_check, true, false, true),
VMW_CMD_DEF(SVGA_3D_CMD_DX_PRED_COPY_REGION,
&vmw_cmd_pred_copy_check, true, false, true),
+ VMW_CMD_DEF(SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER,
+ &vmw_cmd_dx_transfer_from_buffer,
+ true, false, true),
};
static int vmw_cmd_check(struct vmw_private *dev_priv,
@@ -3848,14 +3936,14 @@ static void *vmw_execbuf_cmdbuf(struct vmw_private *dev_priv,
int ret;
*header = NULL;
- if (!dev_priv->cman || kernel_commands)
- return kernel_commands;
-
if (command_size > SVGA_CB_MAX_SIZE) {
DRM_ERROR("Command buffer is too large.\n");
return ERR_PTR(-EINVAL);
}
+ if (!dev_priv->cman || kernel_commands)
+ return kernel_commands;
+
/* If possible, add a little space for fencing. */
cmdbuf_size = command_size + 512;
cmdbuf_size = min_t(size_t, cmdbuf_size, SVGA_CB_MAX_SIZE);
@@ -4232,9 +4320,6 @@ void __vmw_execbuf_release_pinned_bo(struct vmw_private *dev_priv,
ttm_bo_unref(&query_val.bo);
ttm_bo_unref(&pinned_val.bo);
vmw_dmabuf_unreference(&dev_priv->pinned_bo);
- DRM_INFO("Dummy query bo pin count: %d\n",
- dev_priv->dummy_query_bo->pin_count);
-
out_unlock:
return;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 6a328d5..52ca1c9 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -574,10 +574,8 @@ static int vmw_user_dmabuf_synccpu_grab(struct vmw_user_dma_buffer *user_bo,
bool nonblock = !!(flags & drm_vmw_synccpu_dontblock);
long lret;
- if (nonblock)
- return reservation_object_test_signaled_rcu(bo->resv, true) ? 0 : -EBUSY;
-
- lret = reservation_object_wait_timeout_rcu(bo->resv, true, true, MAX_SCHEDULE_TIMEOUT);
+ lret = reservation_object_wait_timeout_rcu(bo->resv, true, true,
+ nonblock ? 0 : MAX_SCHEDULE_TIMEOUT);
if (!lret)
return -EBUSY;
else if (lret < 0)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index c2a721a..b445ce9 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -324,7 +324,7 @@ static void vmw_hw_surface_destroy(struct vmw_resource *res)
if (res->id != -1) {
cmd = vmw_fifo_reserve(dev_priv, vmw_surface_destroy_size());
- if (unlikely(cmd == NULL)) {
+ if (unlikely(!cmd)) {
DRM_ERROR("Failed reserving FIFO space for surface "
"destruction.\n");
return;
@@ -397,7 +397,7 @@ static int vmw_legacy_srf_create(struct vmw_resource *res)
submit_size = vmw_surface_define_size(srf);
cmd = vmw_fifo_reserve(dev_priv, submit_size);
- if (unlikely(cmd == NULL)) {
+ if (unlikely(!cmd)) {
DRM_ERROR("Failed reserving FIFO space for surface "
"creation.\n");
ret = -ENOMEM;
@@ -446,11 +446,10 @@ static int vmw_legacy_srf_dma(struct vmw_resource *res,
uint8_t *cmd;
struct vmw_private *dev_priv = res->dev_priv;
- BUG_ON(val_buf->bo == NULL);
-
+ BUG_ON(!val_buf->bo);
submit_size = vmw_surface_dma_size(srf);
cmd = vmw_fifo_reserve(dev_priv, submit_size);
- if (unlikely(cmd == NULL)) {
+ if (unlikely(!cmd)) {
DRM_ERROR("Failed reserving FIFO space for surface "
"DMA.\n");
return -ENOMEM;
@@ -538,7 +537,7 @@ static int vmw_legacy_srf_destroy(struct vmw_resource *res)
submit_size = vmw_surface_destroy_size();
cmd = vmw_fifo_reserve(dev_priv, submit_size);
- if (unlikely(cmd == NULL)) {
+ if (unlikely(!cmd)) {
DRM_ERROR("Failed reserving FIFO space for surface "
"eviction.\n");
return -ENOMEM;
@@ -578,7 +577,7 @@ static int vmw_surface_init(struct vmw_private *dev_priv,
int ret;
struct vmw_resource *res = &srf->res;
- BUG_ON(res_free == NULL);
+ BUG_ON(!res_free);
if (!dev_priv->has_mob)
vmw_fifo_resource_inc(dev_priv);
ret = vmw_resource_init(dev_priv, res, true, res_free,
@@ -700,7 +699,6 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
struct drm_vmw_surface_create_req *req = &arg->req;
struct drm_vmw_surface_arg *rep = &arg->rep;
struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
- struct drm_vmw_size __user *user_sizes;
int ret;
int i, j;
uint32_t cur_bo_offset;
@@ -748,7 +746,7 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
}
user_srf = kzalloc(sizeof(*user_srf), GFP_KERNEL);
- if (unlikely(user_srf == NULL)) {
+ if (unlikely(!user_srf)) {
ret = -ENOMEM;
goto out_no_user_srf;
}
@@ -763,29 +761,21 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
memcpy(srf->mip_levels, req->mip_levels, sizeof(srf->mip_levels));
srf->num_sizes = num_sizes;
user_srf->size = size;
-
- srf->sizes = kmalloc(srf->num_sizes * sizeof(*srf->sizes), GFP_KERNEL);
- if (unlikely(srf->sizes == NULL)) {
- ret = -ENOMEM;
+ srf->sizes = memdup_user((struct drm_vmw_size __user *)(unsigned long)
+ req->size_addr,
+ sizeof(*srf->sizes) * srf->num_sizes);
+ if (IS_ERR(srf->sizes)) {
+ ret = PTR_ERR(srf->sizes);
goto out_no_sizes;
}
- srf->offsets = kmalloc(srf->num_sizes * sizeof(*srf->offsets),
- GFP_KERNEL);
- if (unlikely(srf->offsets == NULL)) {
+ srf->offsets = kmalloc_array(srf->num_sizes,
+ sizeof(*srf->offsets),
+ GFP_KERNEL);
+ if (unlikely(!srf->offsets)) {
ret = -ENOMEM;
goto out_no_offsets;
}
- user_sizes = (struct drm_vmw_size __user *)(unsigned long)
- req->size_addr;
-
- ret = copy_from_user(srf->sizes, user_sizes,
- srf->num_sizes * sizeof(*srf->sizes));
- if (unlikely(ret != 0)) {
- ret = -EFAULT;
- goto out_no_copy;
- }
-
srf->base_size = *srf->sizes;
srf->autogen_filter = SVGA3D_TEX_FILTER_NONE;
srf->multisample_count = 0;
@@ -923,7 +913,7 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv,
ret = -EINVAL;
base = ttm_base_object_lookup_for_ref(dev_priv->tdev, handle);
- if (unlikely(base == NULL)) {
+ if (unlikely(!base)) {
DRM_ERROR("Could not find surface to reference.\n");
goto out_no_lookup;
}
@@ -1069,7 +1059,7 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
cmd = vmw_fifo_reserve(dev_priv, submit_len);
cmd2 = (typeof(cmd2))cmd;
- if (unlikely(cmd == NULL)) {
+ if (unlikely(!cmd)) {
DRM_ERROR("Failed reserving FIFO space for surface "
"creation.\n");
ret = -ENOMEM;
@@ -1135,7 +1125,7 @@ static int vmw_gb_surface_bind(struct vmw_resource *res,
submit_size = sizeof(*cmd1) + (res->backup_dirty ? sizeof(*cmd2) : 0);
cmd1 = vmw_fifo_reserve(dev_priv, submit_size);
- if (unlikely(cmd1 == NULL)) {
+ if (unlikely(!cmd1)) {
DRM_ERROR("Failed reserving FIFO space for surface "
"binding.\n");
return -ENOMEM;
@@ -1185,7 +1175,7 @@ static int vmw_gb_surface_unbind(struct vmw_resource *res,
submit_size = sizeof(*cmd3) + (readback ? sizeof(*cmd1) : sizeof(*cmd2));
cmd = vmw_fifo_reserve(dev_priv, submit_size);
- if (unlikely(cmd == NULL)) {
+ if (unlikely(!cmd)) {
DRM_ERROR("Failed reserving FIFO space for surface "
"unbinding.\n");
return -ENOMEM;
@@ -1244,7 +1234,7 @@ static int vmw_gb_surface_destroy(struct vmw_resource *res)
vmw_binding_res_list_scrub(&res->binding_head);
cmd = vmw_fifo_reserve(dev_priv, sizeof(*cmd));
- if (unlikely(cmd == NULL)) {
+ if (unlikely(!cmd)) {
DRM_ERROR("Failed reserving FIFO space for surface "
"destruction.\n");
mutex_unlock(&dev_priv->binding_mutex);
@@ -1410,7 +1400,7 @@ int vmw_gb_surface_reference_ioctl(struct drm_device *dev, void *data,
user_srf = container_of(base, struct vmw_user_surface, prime.base);
srf = &user_srf->srf;
- if (srf->res.backup == NULL) {
+ if (!srf->res.backup) {
DRM_ERROR("Shared GB surface is missing a backup buffer.\n");
goto out_bad_resource;
}
@@ -1524,7 +1514,7 @@ int vmw_surface_gb_priv_define(struct drm_device *dev,
}
user_srf = kzalloc(sizeof(*user_srf), GFP_KERNEL);
- if (unlikely(user_srf == NULL)) {
+ if (unlikely(!user_srf)) {
ret = -ENOMEM;
goto out_no_user_srf;
}
diff --git a/drivers/gpu/ipu-v3/ipu-image-convert.c b/drivers/gpu/ipu-v3/ipu-image-convert.c
index 2ba7d43..805b6fa 100644
--- a/drivers/gpu/ipu-v3/ipu-image-convert.c
+++ b/drivers/gpu/ipu-v3/ipu-image-convert.c
@@ -1617,7 +1617,7 @@ ipu_image_convert(struct ipu_soc *ipu, enum ipu_ic_task ic_task,
ctx = ipu_image_convert_prepare(ipu, ic_task, in, out, rot_mode,
complete, complete_context);
if (IS_ERR(ctx))
- return ERR_PTR(PTR_ERR(ctx));
+ return ERR_CAST(ctx);
run = kzalloc(sizeof(*run), GFP_KERNEL);
if (!run) {
diff --git a/drivers/hid/hid-dr.c b/drivers/hid/hid-dr.c
index 8fd4bf7..818ea7d 100644
--- a/drivers/hid/hid-dr.c
+++ b/drivers/hid/hid-dr.c
@@ -234,58 +234,6 @@ static __u8 pid0011_rdesc_fixed[] = {
0xC0 /* End Collection */
};
-static __u8 pid0006_rdesc_fixed[] = {
- 0x05, 0x01, /* Usage Page (Generic Desktop) */
- 0x09, 0x04, /* Usage (Joystick) */
- 0xA1, 0x01, /* Collection (Application) */
- 0xA1, 0x02, /* Collection (Logical) */
- 0x75, 0x08, /* Report Size (8) */
- 0x95, 0x05, /* Report Count (5) */
- 0x15, 0x00, /* Logical Minimum (0) */
- 0x26, 0xFF, 0x00, /* Logical Maximum (255) */
- 0x35, 0x00, /* Physical Minimum (0) */
- 0x46, 0xFF, 0x00, /* Physical Maximum (255) */
- 0x09, 0x30, /* Usage (X) */
- 0x09, 0x33, /* Usage (Ry) */
- 0x09, 0x32, /* Usage (Z) */
- 0x09, 0x31, /* Usage (Y) */
- 0x09, 0x34, /* Usage (Ry) */
- 0x81, 0x02, /* Input (Variable) */
- 0x75, 0x04, /* Report Size (4) */
- 0x95, 0x01, /* Report Count (1) */
- 0x25, 0x07, /* Logical Maximum (7) */
- 0x46, 0x3B, 0x01, /* Physical Maximum (315) */
- 0x65, 0x14, /* Unit (Centimeter) */
- 0x09, 0x39, /* Usage (Hat switch) */
- 0x81, 0x42, /* Input (Variable) */
- 0x65, 0x00, /* Unit (None) */
- 0x75, 0x01, /* Report Size (1) */
- 0x95, 0x0C, /* Report Count (12) */
- 0x25, 0x01, /* Logical Maximum (1) */
- 0x45, 0x01, /* Physical Maximum (1) */
- 0x05, 0x09, /* Usage Page (Button) */
- 0x19, 0x01, /* Usage Minimum (0x01) */
- 0x29, 0x0C, /* Usage Maximum (0x0C) */
- 0x81, 0x02, /* Input (Variable) */
- 0x06, 0x00, 0xFF, /* Usage Page (Vendor Defined) */
- 0x75, 0x01, /* Report Size (1) */
- 0x95, 0x08, /* Report Count (8) */
- 0x25, 0x01, /* Logical Maximum (1) */
- 0x45, 0x01, /* Physical Maximum (1) */
- 0x09, 0x01, /* Usage (0x01) */
- 0x81, 0x02, /* Input (Variable) */
- 0xC0, /* End Collection */
- 0xA1, 0x02, /* Collection (Logical) */
- 0x75, 0x08, /* Report Size (8) */
- 0x95, 0x07, /* Report Count (7) */
- 0x46, 0xFF, 0x00, /* Physical Maximum (255) */
- 0x26, 0xFF, 0x00, /* Logical Maximum (255) */
- 0x09, 0x02, /* Usage (0x02) */
- 0x91, 0x02, /* Output (Variable) */
- 0xC0, /* End Collection */
- 0xC0 /* End Collection */
-};
-
static __u8 *dr_report_fixup(struct hid_device *hdev, __u8 *rdesc,
unsigned int *rsize)
{
@@ -296,16 +244,34 @@ static __u8 *dr_report_fixup(struct hid_device *hdev, __u8 *rdesc,
*rsize = sizeof(pid0011_rdesc_fixed);
}
break;
- case 0x0006:
- if (*rsize == sizeof(pid0006_rdesc_fixed)) {
- rdesc = pid0006_rdesc_fixed;
- *rsize = sizeof(pid0006_rdesc_fixed);
- }
- break;
}
return rdesc;
}
+#define map_abs(c) hid_map_usage(hi, usage, bit, max, EV_ABS, (c))
+#define map_rel(c) hid_map_usage(hi, usage, bit, max, EV_REL, (c))
+
+static int dr_input_mapping(struct hid_device *hdev, struct hid_input *hi,
+ struct hid_field *field, struct hid_usage *usage,
+ unsigned long **bit, int *max)
+{
+ switch (usage->hid) {
+ /*
+ * revert to the old hid-input behavior where axes
+ * can be randomly assigned when hid->usage is reused.
+ */
+ case HID_GD_X: case HID_GD_Y: case HID_GD_Z:
+ case HID_GD_RX: case HID_GD_RY: case HID_GD_RZ:
+ if (field->flags & HID_MAIN_ITEM_RELATIVE)
+ map_rel(usage->hid & 0xf);
+ else
+ map_abs(usage->hid & 0xf);
+ return 1;
+ }
+
+ return 0;
+}
+
static int dr_probe(struct hid_device *hdev, const struct hid_device_id *id)
{
int ret;
@@ -352,6 +318,7 @@ static struct hid_driver dr_driver = {
.id_table = dr_devices,
.report_fixup = dr_report_fixup,
.probe = dr_probe,
+ .input_mapping = dr_input_mapping,
};
module_hid_driver(dr_driver);
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index cd59c79..575aa65 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -64,6 +64,9 @@
#define USB_VENDOR_ID_AKAI 0x2011
#define USB_DEVICE_ID_AKAI_MPKMINI2 0x0715
+#define USB_VENDOR_ID_AKAI_09E8 0x09E8
+#define USB_DEVICE_ID_AKAI_09E8_MIDIMIX 0x0031
+
#define USB_VENDOR_ID_ALCOR 0x058f
#define USB_DEVICE_ID_ALCOR_USBRS232 0x9720
@@ -176,6 +179,7 @@
#define USB_DEVICE_ID_ATEN_4PORTKVM 0x2205
#define USB_DEVICE_ID_ATEN_4PORTKVMC 0x2208
#define USB_DEVICE_ID_ATEN_CS682 0x2213
+#define USB_DEVICE_ID_ATEN_CS692 0x8021
#define USB_VENDOR_ID_ATMEL 0x03eb
#define USB_DEVICE_ID_ATMEL_MULTITOUCH 0x211c
diff --git a/drivers/hid/hid-led.c b/drivers/hid/hid-led.c
index d8d55f3..d3e1ab1 100644
--- a/drivers/hid/hid-led.c
+++ b/drivers/hid/hid-led.c
@@ -100,6 +100,7 @@ struct hidled_device {
const struct hidled_config *config;
struct hid_device *hdev;
struct hidled_rgb *rgb;
+ u8 *buf;
struct mutex lock;
};
@@ -118,13 +119,19 @@ static int hidled_send(struct hidled_device *ldev, __u8 *buf)
mutex_lock(&ldev->lock);
+ /*
+ * buffer provided to hid_hw_raw_request must not be on the stack
+ * and must not be part of a data structure
+ */
+ memcpy(ldev->buf, buf, ldev->config->report_size);
+
if (ldev->config->report_type == RAW_REQUEST)
- ret = hid_hw_raw_request(ldev->hdev, buf[0], buf,
+ ret = hid_hw_raw_request(ldev->hdev, buf[0], ldev->buf,
ldev->config->report_size,
HID_FEATURE_REPORT,
HID_REQ_SET_REPORT);
else if (ldev->config->report_type == OUTPUT_REPORT)
- ret = hid_hw_output_report(ldev->hdev, buf,
+ ret = hid_hw_output_report(ldev->hdev, ldev->buf,
ldev->config->report_size);
else
ret = -EINVAL;
@@ -147,17 +154,21 @@ static int hidled_recv(struct hidled_device *ldev, __u8 *buf)
mutex_lock(&ldev->lock);
- ret = hid_hw_raw_request(ldev->hdev, buf[0], buf,
+ memcpy(ldev->buf, buf, ldev->config->report_size);
+
+ ret = hid_hw_raw_request(ldev->hdev, buf[0], ldev->buf,
ldev->config->report_size,
HID_FEATURE_REPORT,
HID_REQ_SET_REPORT);
if (ret < 0)
goto err;
- ret = hid_hw_raw_request(ldev->hdev, buf[0], buf,
+ ret = hid_hw_raw_request(ldev->hdev, buf[0], ldev->buf,
ldev->config->report_size,
HID_FEATURE_REPORT,
HID_REQ_GET_REPORT);
+
+ memcpy(buf, ldev->buf, ldev->config->report_size);
err:
mutex_unlock(&ldev->lock);
@@ -447,6 +458,10 @@ static int hidled_probe(struct hid_device *hdev, const struct hid_device_id *id)
if (!ldev)
return -ENOMEM;
+ ldev->buf = devm_kmalloc(&hdev->dev, MAX_REPORT_SIZE, GFP_KERNEL);
+ if (!ldev->buf)
+ return -ENOMEM;
+
ret = hid_parse(hdev);
if (ret)
return ret;
diff --git a/drivers/hid/hid-sensor-custom.c b/drivers/hid/hid-sensor-custom.c
index 5614fee..3a84aaf 100644
--- a/drivers/hid/hid-sensor-custom.c
+++ b/drivers/hid/hid-sensor-custom.c
@@ -292,11 +292,11 @@ static ssize_t show_value(struct device *dev, struct device_attribute *attr,
bool input = false;
int value = 0;
- if (sscanf(attr->attr.name, "feature-%d-%x-%s", &index, &usage,
+ if (sscanf(attr->attr.name, "feature-%x-%x-%s", &index, &usage,
name) == 3) {
feature = true;
field_index = index + sensor_inst->input_field_count;
- } else if (sscanf(attr->attr.name, "input-%d-%x-%s", &index, &usage,
+ } else if (sscanf(attr->attr.name, "input-%x-%x-%s", &index, &usage,
name) == 3) {
input = true;
field_index = index;
@@ -398,7 +398,7 @@ static ssize_t store_value(struct device *dev, struct device_attribute *attr,
char name[HID_CUSTOM_NAME_LENGTH];
int value;
- if (sscanf(attr->attr.name, "feature-%d-%x-%s", &index, &usage,
+ if (sscanf(attr->attr.name, "feature-%x-%x-%s", &index, &usage,
name) == 3) {
field_index = index + sensor_inst->input_field_count;
} else
diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index 658a607..c5c3d61 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -251,6 +251,9 @@ int sensor_hub_get_feature(struct hid_sensor_hub_device *hsdev, u32 report_id,
struct sensor_hub_data *data = hid_get_drvdata(hsdev->hdev);
int report_size;
int ret = 0;
+ u8 *val_ptr;
+ int buffer_index = 0;
+ int i;
mutex_lock(&data->mutex);
report = sensor_hub_report(report_id, hsdev->hdev, HID_FEATURE_REPORT);
@@ -271,7 +274,17 @@ int sensor_hub_get_feature(struct hid_sensor_hub_device *hsdev, u32 report_id,
goto done_proc;
}
ret = min(report_size, buffer_size);
- memcpy(buffer, report->field[field_index]->value, ret);
+
+ val_ptr = (u8 *)report->field[field_index]->value;
+ for (i = 0; i < report->field[field_index]->report_count; ++i) {
+ if (buffer_index >= ret)
+ break;
+
+ memcpy(&((u8 *)buffer)[buffer_index], val_ptr,
+ report->field[field_index]->report_size / 8);
+ val_ptr += sizeof(__s32);
+ buffer_index += (report->field[field_index]->report_size / 8);
+ }
done_proc:
mutex_unlock(&data->mutex);
diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c
index e2517c1..0c9ac4d 100644
--- a/drivers/hid/intel-ish-hid/ipc/ipc.c
+++ b/drivers/hid/intel-ish-hid/ipc/ipc.c
@@ -638,6 +638,58 @@ irqreturn_t ish_irq_handler(int irq, void *dev_id)
}
/**
+ * ish_disable_dma() - disable dma communication between host and ISHFW
+ * @dev: ishtp device pointer
+ *
+ * Clear the dma enable bit and wait for dma inactive.
+ *
+ * Return: 0 for success else error code.
+ */
+static int ish_disable_dma(struct ishtp_device *dev)
+{
+ unsigned int dma_delay;
+
+ /* Clear the dma enable bit */
+ ish_reg_write(dev, IPC_REG_ISH_RMP2, 0);
+
+ /* wait for dma inactive */
+ for (dma_delay = 0; dma_delay < MAX_DMA_DELAY &&
+ _ish_read_fw_sts_reg(dev) & (IPC_ISH_IN_DMA);
+ dma_delay += 5)
+ mdelay(5);
+
+ if (dma_delay >= MAX_DMA_DELAY) {
+ dev_err(dev->devc,
+ "Wait for DMA inactive timeout\n");
+ return -EBUSY;
+ }
+
+ return 0;
+}
+
+/**
+ * ish_wakeup() - wakeup ishfw from waiting-for-host state
+ * @dev: ishtp device pointer
+ *
+ * Set the dma enable bit and send a void message to FW,
+ * it wil wakeup FW from waiting-for-host state.
+ */
+static void ish_wakeup(struct ishtp_device *dev)
+{
+ /* Set dma enable bit */
+ ish_reg_write(dev, IPC_REG_ISH_RMP2, IPC_RMP2_DMA_ENABLED);
+
+ /*
+ * Send 0 IPC message so that ISH FW wakes up if it was already
+ * asleep.
+ */
+ ish_reg_write(dev, IPC_REG_HOST2ISH_DRBL, IPC_DRBL_BUSY_BIT);
+
+ /* Flush writes to doorbell and REMAP2 */
+ ish_reg_read(dev, IPC_REG_ISH_HOST_FWSTS);
+}
+
+/**
* _ish_hw_reset() - HW reset
* @dev: ishtp device pointer
*
@@ -649,7 +701,6 @@ static int _ish_hw_reset(struct ishtp_device *dev)
{
struct pci_dev *pdev = dev->pdev;
int rv;
- unsigned int dma_delay;
uint16_t csr;
if (!pdev)
@@ -664,15 +715,8 @@ static int _ish_hw_reset(struct ishtp_device *dev)
return -EINVAL;
}
- /* Now trigger reset to FW */
- ish_reg_write(dev, IPC_REG_ISH_RMP2, 0);
-
- for (dma_delay = 0; dma_delay < MAX_DMA_DELAY &&
- _ish_read_fw_sts_reg(dev) & (IPC_ISH_IN_DMA);
- dma_delay += 5)
- mdelay(5);
-
- if (dma_delay >= MAX_DMA_DELAY) {
+ /* Disable dma communication between FW and host */
+ if (ish_disable_dma(dev)) {
dev_err(&pdev->dev,
"Can't reset - stuck with DMA in-progress\n");
return -EBUSY;
@@ -690,16 +734,8 @@ static int _ish_hw_reset(struct ishtp_device *dev)
csr |= PCI_D0;
pci_write_config_word(pdev, pdev->pm_cap + PCI_PM_CTRL, csr);
- ish_reg_write(dev, IPC_REG_ISH_RMP2, IPC_RMP2_DMA_ENABLED);
-
- /*
- * Send 0 IPC message so that ISH FW wakes up if it was already
- * asleep
- */
- ish_reg_write(dev, IPC_REG_HOST2ISH_DRBL, IPC_DRBL_BUSY_BIT);
-
- /* Flush writes to doorbell and REMAP2 */
- ish_reg_read(dev, IPC_REG_ISH_HOST_FWSTS);
+ /* Now we can enable ISH DMA operation and wakeup ISHFW */
+ ish_wakeup(dev);
return 0;
}
@@ -758,16 +794,9 @@ static int _ish_ipc_reset(struct ishtp_device *dev)
int ish_hw_start(struct ishtp_device *dev)
{
ish_set_host_rdy(dev);
- /* After that we can enable ISH DMA operation */
- ish_reg_write(dev, IPC_REG_ISH_RMP2, IPC_RMP2_DMA_ENABLED);
- /*
- * Send 0 IPC message so that ISH FW wakes up if it was already
- * asleep
- */
- ish_reg_write(dev, IPC_REG_HOST2ISH_DRBL, IPC_DRBL_BUSY_BIT);
- /* Flush write to doorbell */
- ish_reg_read(dev, IPC_REG_ISH_HOST_FWSTS);
+ /* After that we can enable ISH DMA operation and wakeup ISHFW */
+ ish_wakeup(dev);
set_host_ready(dev);
@@ -876,6 +905,21 @@ struct ishtp_device *ish_dev_init(struct pci_dev *pdev)
*/
void ish_device_disable(struct ishtp_device *dev)
{
+ struct pci_dev *pdev = dev->pdev;
+
+ if (!pdev)
+ return;
+
+ /* Disable dma communication between FW and host */
+ if (ish_disable_dma(dev)) {
+ dev_err(&pdev->dev,
+ "Can't reset - stuck with DMA in-progress\n");
+ return;
+ }
+
+ /* Put ISH to D3hot state for power saving */
+ pci_set_power_state(pdev, PCI_D3hot);
+
dev->dev_state = ISHTP_DEV_DISABLED;
ish_clr_host_rdy(dev);
}
diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index 42f0bee..20d647d 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -146,7 +146,7 @@ static int ish_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
pdev->dev_flags |= PCI_DEV_FLAGS_NO_D3;
/* request and enable interrupt */
- ret = request_irq(pdev->irq, ish_irq_handler, IRQF_NO_SUSPEND,
+ ret = request_irq(pdev->irq, ish_irq_handler, IRQF_SHARED,
KBUILD_MODNAME, dev);
if (ret) {
dev_err(&pdev->dev, "ISH: request IRQ failure (%d)\n",
@@ -202,6 +202,7 @@ static void ish_remove(struct pci_dev *pdev)
kfree(ishtp_dev);
}
+#ifdef CONFIG_PM
static struct device *ish_resume_device;
/**
@@ -293,7 +294,6 @@ static int ish_resume(struct device *device)
return 0;
}
-#ifdef CONFIG_PM
static const struct dev_pm_ops ish_pm_ops = {
.suspend = ish_suspend,
.resume = ish_resume,
@@ -301,7 +301,7 @@ static const struct dev_pm_ops ish_pm_ops = {
#define ISHTP_ISH_PM_OPS (&ish_pm_ops)
#else
#define ISHTP_ISH_PM_OPS NULL
-#endif
+#endif /* CONFIG_PM */
static struct pci_driver ish_driver = {
.name = KBUILD_MODNAME,
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 0a0eca5..e6cfd32 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -56,12 +56,14 @@ static const struct hid_blacklist {
{ USB_VENDOR_ID_AIREN, USB_DEVICE_ID_AIREN_SLIMPLUS, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_AKAI, USB_DEVICE_ID_AKAI_MPKMINI2, HID_QUIRK_NO_INIT_REPORTS },
+ { USB_VENDOR_ID_AKAI_09E8, USB_DEVICE_ID_AKAI_09E8_MIDIMIX, HID_QUIRK_NO_INIT_REPORTS },
{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_UC100KM, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_CS124U, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_2PORTKVM, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVM, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVMC, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_CS682, HID_QUIRK_NOGET },
+ { USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_CS692, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FIGHTERSTICK, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_COMBATSTICK, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FLIGHT_SIM_ECLIPSE_YOKE, HID_QUIRK_NOGET },
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 4aa3cb6..bcd0630 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -314,10 +314,14 @@ static void heartbeat_onchannelcallback(void *context)
u8 *hbeat_txf_buf = util_heartbeat.recv_buffer;
struct icmsg_negotiate *negop = NULL;
- vmbus_recvpacket(channel, hbeat_txf_buf,
- PAGE_SIZE, &recvlen, &requestid);
+ while (1) {
- if (recvlen > 0) {
+ vmbus_recvpacket(channel, hbeat_txf_buf,
+ PAGE_SIZE, &recvlen, &requestid);
+
+ if (!recvlen)
+ break;
+
icmsghdrp = (struct icmsg_hdr *)&hbeat_txf_buf[
sizeof(struct vmbuspipe_hdr)];
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index a259e18..0276d2e 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -961,7 +961,7 @@ int vmbus_device_register(struct hv_device *child_device_obj)
{
int ret = 0;
- dev_set_name(&child_device_obj->device, "vmbus-%pUl",
+ dev_set_name(&child_device_obj->device, "%pUl",
child_device_obj->channel->offermsg.offer.if_instance.b);
child_device_obj->device.bus = &hv_bus;
diff --git a/drivers/hwmon/adm9240.c b/drivers/hwmon/adm9240.c
index 98114ce..2fe1828 100644
--- a/drivers/hwmon/adm9240.c
+++ b/drivers/hwmon/adm9240.c
@@ -194,10 +194,10 @@ static struct adm9240_data *adm9240_update_device(struct device *dev)
* 0.5'C per two measurement cycles thus ignore possible
* but unlikely aliasing error on lsb reading. --Grant
*/
- data->temp = ((i2c_smbus_read_byte_data(client,
+ data->temp = (i2c_smbus_read_byte_data(client,
ADM9240_REG_TEMP) << 8) |
i2c_smbus_read_byte_data(client,
- ADM9240_REG_TEMP_CONF)) / 128;
+ ADM9240_REG_TEMP_CONF);
for (i = 0; i < 2; i++) { /* read fans */
data->fan[i] = i2c_smbus_read_byte_data(client,
@@ -263,7 +263,7 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *dummy,
char *buf)
{
struct adm9240_data *data = adm9240_update_device(dev);
- return sprintf(buf, "%d\n", data->temp * 500); /* 9-bit value */
+ return sprintf(buf, "%d\n", data->temp / 128 * 500); /* 9-bit value */
}
static ssize_t show_max(struct device *dev, struct device_attribute *devattr,
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index adae684..a74c075 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -536,8 +536,10 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata,
hwdev->groups = devm_kcalloc(dev, ngroups, sizeof(*groups),
GFP_KERNEL);
- if (!hwdev->groups)
- return ERR_PTR(-ENOMEM);
+ if (!hwdev->groups) {
+ err = -ENOMEM;
+ goto free_hwmon;
+ }
attrs = __hwmon_create_attrs(dev, drvdata, chip);
if (IS_ERR(attrs)) {
diff --git a/drivers/hwmon/max31790.c b/drivers/hwmon/max31790.c
index bef84e0..c1b9275 100644
--- a/drivers/hwmon/max31790.c
+++ b/drivers/hwmon/max31790.c
@@ -268,11 +268,13 @@ static int max31790_read_pwm(struct device *dev, u32 attr, int channel,
long *val)
{
struct max31790_data *data = max31790_update_device(dev);
- u8 fan_config = data->fan_config[channel];
+ u8 fan_config;
if (IS_ERR(data))
return PTR_ERR(data);
+ fan_config = data->fan_config[channel];
+
switch (attr) {
case hwmon_pwm_input:
*val = data->pwm[channel] >> 8;
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 6d94e2e..d252276 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -79,12 +79,12 @@
config I2C_HIX5HD2
tristate "Hix5hd2 high-speed I2C driver"
- depends on ARCH_HIX5HD2 || COMPILE_TEST
+ depends on ARCH_HISI || ARCH_HIX5HD2 || COMPILE_TEST
help
- Say Y here to include support for high-speed I2C controller in the
- Hisilicon based hix5hd2 SoCs.
+ Say Y here to include support for the high-speed I2C controller
+ used in HiSilicon hix5hd2 SoCs.
- This driver can also be built as a module. If so, the module
+ This driver can also be built as a module. If so, the module
will be called i2c-hix5hd2.
config I2C_I801
@@ -589,10 +589,10 @@
config I2C_IMX
tristate "IMX I2C interface"
- depends on ARCH_MXC || ARCH_LAYERSCAPE
+ depends on ARCH_MXC || ARCH_LAYERSCAPE || COLDFIRE
help
Say Y here if you want to use the IIC bus controller on
- the Freescale i.MX/MXC or Layerscape processors.
+ the Freescale i.MX/MXC, Layerscape or ColdFire processors.
This driver can also be built as a module. If so, the module
will be called i2c-imx.
diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c
index 1fe93c4..11e866d 100644
--- a/drivers/i2c/busses/i2c-designware-core.c
+++ b/drivers/i2c/busses/i2c-designware-core.c
@@ -95,6 +95,9 @@
#define DW_IC_STATUS_TFE BIT(2)
#define DW_IC_STATUS_MST_ACTIVITY BIT(5)
+#define DW_IC_SDA_HOLD_RX_SHIFT 16
+#define DW_IC_SDA_HOLD_RX_MASK GENMASK(23, DW_IC_SDA_HOLD_RX_SHIFT)
+
#define DW_IC_ERR_TX_ABRT 0x1
#define DW_IC_TAR_10BITADDR_MASTER BIT(12)
@@ -420,12 +423,20 @@ int i2c_dw_init(struct dw_i2c_dev *dev)
/* Configure SDA Hold Time if required */
reg = dw_readl(dev, DW_IC_COMP_VERSION);
if (reg >= DW_IC_SDA_HOLD_MIN_VERS) {
- if (dev->sda_hold_time) {
- dw_writel(dev, dev->sda_hold_time, DW_IC_SDA_HOLD);
- } else {
+ if (!dev->sda_hold_time) {
/* Keep previous hold time setting if no one set it */
dev->sda_hold_time = dw_readl(dev, DW_IC_SDA_HOLD);
}
+ /*
+ * Workaround for avoiding TX arbitration lost in case I2C
+ * slave pulls SDA down "too quickly" after falling egde of
+ * SCL by enabling non-zero SDA RX hold. Specification says it
+ * extends incoming SDA low to high transition while SCL is
+ * high but it apprears to help also above issue.
+ */
+ if (!(dev->sda_hold_time & DW_IC_SDA_HOLD_RX_MASK))
+ dev->sda_hold_time |= 1 << DW_IC_SDA_HOLD_RX_SHIFT;
+ dw_writel(dev, dev->sda_hold_time, DW_IC_SDA_HOLD);
} else {
dev_warn(dev->dev,
"Hardware too old to adjust SDA hold time.\n");
diff --git a/drivers/i2c/busses/i2c-digicolor.c b/drivers/i2c/busses/i2c-digicolor.c
index 9604024..49f2084 100644
--- a/drivers/i2c/busses/i2c-digicolor.c
+++ b/drivers/i2c/busses/i2c-digicolor.c
@@ -368,6 +368,7 @@ static const struct of_device_id dc_i2c_match[] = {
{ .compatible = "cnxt,cx92755-i2c" },
{ },
};
+MODULE_DEVICE_TABLE(of, dc_i2c_match);
static struct platform_driver dc_i2c_driver = {
.probe = dc_i2c_probe,
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 08847e8..eb3627f 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -146,6 +146,7 @@
#define SMBHSTCFG_HST_EN 1
#define SMBHSTCFG_SMB_SMI_EN 2
#define SMBHSTCFG_I2C_EN 4
+#define SMBHSTCFG_SPD_WD 0x10
/* TCO configuration bits for TCOCTL */
#define TCOCTL_EN 0x0100
@@ -865,9 +866,16 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
block = 1;
break;
case I2C_SMBUS_I2C_BLOCK_DATA:
- /* NB: page 240 of ICH5 datasheet shows that the R/#W
- * bit should be cleared here, even when reading */
- outb_p((addr & 0x7f) << 1, SMBHSTADD(priv));
+ /*
+ * NB: page 240 of ICH5 datasheet shows that the R/#W
+ * bit should be cleared here, even when reading.
+ * However if SPD Write Disable is set (Lynx Point and later),
+ * the read will fail if we don't set the R/#W bit.
+ */
+ outb_p(((addr & 0x7f) << 1) |
+ ((priv->original_hstcfg & SMBHSTCFG_SPD_WD) ?
+ (read_write & 0x01) : 0),
+ SMBHSTADD(priv));
if (read_write == I2C_SMBUS_READ) {
/* NB: page 240 of ICH5 datasheet also shows
* that DATA1 is the cmd field when reading */
@@ -1573,6 +1581,8 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
/* Disable SMBus interrupt feature if SMBus using SMI# */
priv->features &= ~FEATURE_IRQ;
}
+ if (temp & SMBHSTCFG_SPD_WD)
+ dev_info(&dev->dev, "SPD Write Disable is set\n");
/* Clear special mode bits */
if (priv->features & (FEATURE_SMBUS_PEC | FEATURE_BLOCK_BUFFER))
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 592a8f2..47fc1f1 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1009,10 +1009,13 @@ static int i2c_imx_init_recovery_info(struct imx_i2c_struct *i2c_imx,
rinfo->sda_gpio = of_get_named_gpio(pdev->dev.of_node, "sda-gpios", 0);
rinfo->scl_gpio = of_get_named_gpio(pdev->dev.of_node, "scl-gpios", 0);
- if (!gpio_is_valid(rinfo->sda_gpio) ||
- !gpio_is_valid(rinfo->scl_gpio) ||
- IS_ERR(i2c_imx->pinctrl_pins_default) ||
- IS_ERR(i2c_imx->pinctrl_pins_gpio)) {
+ if (rinfo->sda_gpio == -EPROBE_DEFER ||
+ rinfo->scl_gpio == -EPROBE_DEFER) {
+ return -EPROBE_DEFER;
+ } else if (!gpio_is_valid(rinfo->sda_gpio) ||
+ !gpio_is_valid(rinfo->scl_gpio) ||
+ IS_ERR(i2c_imx->pinctrl_pins_default) ||
+ IS_ERR(i2c_imx->pinctrl_pins_gpio)) {
dev_dbg(&pdev->dev, "recovery information incomplete\n");
return 0;
}
diff --git a/drivers/i2c/busses/i2c-jz4780.c b/drivers/i2c/busses/i2c-jz4780.c
index b8ea621..30132c3 100644
--- a/drivers/i2c/busses/i2c-jz4780.c
+++ b/drivers/i2c/busses/i2c-jz4780.c
@@ -729,6 +729,7 @@ static const struct of_device_id jz4780_i2c_of_matches[] = {
{ .compatible = "ingenic,jz4780-i2c", },
{ /* sentinel */ }
};
+MODULE_DEVICE_TABLE(of, jz4780_i2c_of_matches);
static int jz4780_i2c_probe(struct platform_device *pdev)
{
diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c
index 50702c7..df22066 100644
--- a/drivers/i2c/busses/i2c-rk3x.c
+++ b/drivers/i2c/busses/i2c-rk3x.c
@@ -694,6 +694,8 @@ static int rk3x_i2c_v0_calc_timings(unsigned long clk_rate,
t_calc->div_low--;
t_calc->div_high--;
+ /* Give the tuning value 0, that would not update con register */
+ t_calc->tuning = 0;
/* Maximum divider supported by hw is 0xffff */
if (t_calc->div_low > 0xffff) {
t_calc->div_low = 0xffff;
diff --git a/drivers/i2c/busses/i2c-xgene-slimpro.c b/drivers/i2c/busses/i2c-xgene-slimpro.c
index 263685c..05cf192 100644
--- a/drivers/i2c/busses/i2c-xgene-slimpro.c
+++ b/drivers/i2c/busses/i2c-xgene-slimpro.c
@@ -105,7 +105,7 @@ struct slimpro_i2c_dev {
struct mbox_chan *mbox_chan;
struct mbox_client mbox_client;
struct completion rd_complete;
- u8 dma_buffer[I2C_SMBUS_BLOCK_MAX];
+ u8 dma_buffer[I2C_SMBUS_BLOCK_MAX + 1]; /* dma_buffer[0] is used for length */
u32 *resp_msg;
};
diff --git a/drivers/i2c/busses/i2c-xlp9xx.c b/drivers/i2c/busses/i2c-xlp9xx.c
index 2a972ed7..e29ff37 100644
--- a/drivers/i2c/busses/i2c-xlp9xx.c
+++ b/drivers/i2c/busses/i2c-xlp9xx.c
@@ -426,6 +426,7 @@ static const struct of_device_id xlp9xx_i2c_of_match[] = {
{ .compatible = "netlogic,xlp980-i2c", },
{ /* sentinel */ },
};
+MODULE_DEVICE_TABLE(of, xlp9xx_i2c_of_match);
#ifdef CONFIG_ACPI
static const struct acpi_device_id xlp9xx_i2c_acpi_ids[] = {
diff --git a/drivers/i2c/busses/i2c-xlr.c b/drivers/i2c/busses/i2c-xlr.c
index 0968f59..ad17d88 100644
--- a/drivers/i2c/busses/i2c-xlr.c
+++ b/drivers/i2c/busses/i2c-xlr.c
@@ -358,6 +358,7 @@ static const struct of_device_id xlr_i2c_dt_ids[] = {
},
{ }
};
+MODULE_DEVICE_TABLE(of, xlr_i2c_dt_ids);
static int xlr_i2c_probe(struct platform_device *pdev)
{
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 98fffa3..b432b64 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -1680,7 +1680,8 @@ static struct i2c_client *of_i2c_register_device(struct i2c_adapter *adap,
static void of_i2c_register_devices(struct i2c_adapter *adap)
{
- struct device_node *node;
+ struct device_node *bus, *node;
+ struct i2c_client *client;
/* Only register child devices if the adapter has a node pointer set */
if (!adap->dev.of_node)
@@ -1688,11 +1689,24 @@ static void of_i2c_register_devices(struct i2c_adapter *adap)
dev_dbg(&adap->dev, "of_i2c: walking child nodes\n");
- for_each_available_child_of_node(adap->dev.of_node, node) {
+ bus = of_get_child_by_name(adap->dev.of_node, "i2c-bus");
+ if (!bus)
+ bus = of_node_get(adap->dev.of_node);
+
+ for_each_available_child_of_node(bus, node) {
if (of_node_test_and_set_flag(node, OF_POPULATED))
continue;
- of_i2c_register_device(adap, node);
+
+ client = of_i2c_register_device(adap, node);
+ if (IS_ERR(client)) {
+ dev_warn(&adap->dev,
+ "Failed to create I2C device for %s\n",
+ node->full_name);
+ of_node_clear_flag(node, OF_POPULATED);
+ }
}
+
+ of_node_put(bus);
}
static int of_dev_node_match(struct device *dev, void *data)
@@ -2165,6 +2179,7 @@ int i2c_register_driver(struct module *owner, struct i2c_driver *driver)
/* add the driver to the list of i2c drivers in the driver core */
driver->driver.owner = owner;
driver->driver.bus = &i2c_bus_type;
+ INIT_LIST_HEAD(&driver->clients);
/* When registration returns, the driver core
* will have called probe() for all matching-but-unbound devices.
@@ -2175,7 +2190,6 @@ int i2c_register_driver(struct module *owner, struct i2c_driver *driver)
pr_debug("driver [%s] registered\n", driver->driver.name);
- INIT_LIST_HEAD(&driver->clients);
/* Walk the adapters that are already present */
i2c_for_each_dev(driver, __process_new_driver);
@@ -2293,6 +2307,7 @@ static int of_i2c_notify(struct notifier_block *nb, unsigned long action,
if (IS_ERR(client)) {
dev_err(&adap->dev, "failed to create client for '%s'\n",
rd->dn->full_name);
+ of_node_clear_flag(rd->dn, OF_POPULATED);
return notifier_from_errno(PTR_ERR(client));
}
break;
diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c
index da3fb06..ce69048 100644
--- a/drivers/iio/accel/st_accel_core.c
+++ b/drivers/iio/accel/st_accel_core.c
@@ -743,8 +743,8 @@ static int st_accel_read_raw(struct iio_dev *indio_dev,
return IIO_VAL_INT;
case IIO_CHAN_INFO_SCALE:
- *val = 0;
- *val2 = adata->current_fullscale->gain;
+ *val = adata->current_fullscale->gain / 1000000;
+ *val2 = adata->current_fullscale->gain % 1000000;
return IIO_VAL_INT_PLUS_MICRO;
case IIO_CHAN_INFO_SAMP_FREQ:
*val = adata->odr;
@@ -763,9 +763,13 @@ static int st_accel_write_raw(struct iio_dev *indio_dev,
int err;
switch (mask) {
- case IIO_CHAN_INFO_SCALE:
- err = st_sensors_set_fullscale_by_gain(indio_dev, val2);
+ case IIO_CHAN_INFO_SCALE: {
+ int gain;
+
+ gain = val * 1000000 + val2;
+ err = st_sensors_set_fullscale_by_gain(indio_dev, gain);
break;
+ }
case IIO_CHAN_INFO_SAMP_FREQ:
if (val2)
return -EINVAL;
diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 7edcf32..99c0514 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -437,6 +437,8 @@
config TI_ADC081C
tristate "Texas Instruments ADC081C/ADC101C/ADC121C family"
depends on I2C
+ select IIO_BUFFER
+ select IIO_TRIGGERED_BUFFER
help
If you say yes here you get support for Texas Instruments ADC081C,
ADC101C and ADC121C ADC chips.
diff --git a/drivers/iio/chemical/atlas-ph-sensor.c b/drivers/iio/chemical/atlas-ph-sensor.c
index bd321b3..ef761a5 100644
--- a/drivers/iio/chemical/atlas-ph-sensor.c
+++ b/drivers/iio/chemical/atlas-ph-sensor.c
@@ -213,13 +213,14 @@ static int atlas_check_ec_calibration(struct atlas_data *data)
struct device *dev = &data->client->dev;
int ret;
unsigned int val;
+ __be16 rval;
- ret = regmap_bulk_read(data->regmap, ATLAS_REG_EC_PROBE, &val, 2);
+ ret = regmap_bulk_read(data->regmap, ATLAS_REG_EC_PROBE, &rval, 2);
if (ret)
return ret;
- dev_info(dev, "probe set to K = %d.%.2d", be16_to_cpu(val) / 100,
- be16_to_cpu(val) % 100);
+ val = be16_to_cpu(rval);
+ dev_info(dev, "probe set to K = %d.%.2d", val / 100, val % 100);
ret = regmap_read(data->regmap, ATLAS_REG_EC_CALIB_STATUS, &val);
if (ret)
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
index dc33c1d..b5beea53 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c
@@ -30,26 +30,26 @@ static struct {
u32 usage_id;
int unit; /* 0 for default others from HID sensor spec */
int scale_val0; /* scale, whole number */
- int scale_val1; /* scale, fraction in micros */
+ int scale_val1; /* scale, fraction in nanos */
} unit_conversion[] = {
- {HID_USAGE_SENSOR_ACCEL_3D, 0, 9, 806650},
+ {HID_USAGE_SENSOR_ACCEL_3D, 0, 9, 806650000},
{HID_USAGE_SENSOR_ACCEL_3D,
HID_USAGE_SENSOR_UNITS_METERS_PER_SEC_SQRD, 1, 0},
{HID_USAGE_SENSOR_ACCEL_3D,
- HID_USAGE_SENSOR_UNITS_G, 9, 806650},
+ HID_USAGE_SENSOR_UNITS_G, 9, 806650000},
- {HID_USAGE_SENSOR_GYRO_3D, 0, 0, 17453},
+ {HID_USAGE_SENSOR_GYRO_3D, 0, 0, 17453293},
{HID_USAGE_SENSOR_GYRO_3D,
HID_USAGE_SENSOR_UNITS_RADIANS_PER_SECOND, 1, 0},
{HID_USAGE_SENSOR_GYRO_3D,
- HID_USAGE_SENSOR_UNITS_DEGREES_PER_SECOND, 0, 17453},
+ HID_USAGE_SENSOR_UNITS_DEGREES_PER_SECOND, 0, 17453293},
- {HID_USAGE_SENSOR_COMPASS_3D, 0, 0, 1000},
+ {HID_USAGE_SENSOR_COMPASS_3D, 0, 0, 1000000},
{HID_USAGE_SENSOR_COMPASS_3D, HID_USAGE_SENSOR_UNITS_GAUSS, 1, 0},
- {HID_USAGE_SENSOR_INCLINOMETER_3D, 0, 0, 17453},
+ {HID_USAGE_SENSOR_INCLINOMETER_3D, 0, 0, 17453293},
{HID_USAGE_SENSOR_INCLINOMETER_3D,
- HID_USAGE_SENSOR_UNITS_DEGREES, 0, 17453},
+ HID_USAGE_SENSOR_UNITS_DEGREES, 0, 17453293},
{HID_USAGE_SENSOR_INCLINOMETER_3D,
HID_USAGE_SENSOR_UNITS_RADIANS, 1, 0},
@@ -57,7 +57,7 @@ static struct {
{HID_USAGE_SENSOR_ALS, HID_USAGE_SENSOR_UNITS_LUX, 1, 0},
{HID_USAGE_SENSOR_PRESSURE, 0, 100, 0},
- {HID_USAGE_SENSOR_PRESSURE, HID_USAGE_SENSOR_UNITS_PASCAL, 0, 1000},
+ {HID_USAGE_SENSOR_PRESSURE, HID_USAGE_SENSOR_UNITS_PASCAL, 0, 1000000},
};
static int pow_10(unsigned power)
@@ -266,15 +266,15 @@ EXPORT_SYMBOL(hid_sensor_write_raw_hyst_value);
/*
* This fuction applies the unit exponent to the scale.
* For example:
- * 9.806650 ->exp:2-> val0[980]val1[665000]
- * 9.000806 ->exp:2-> val0[900]val1[80600]
- * 0.174535 ->exp:2-> val0[17]val1[453500]
- * 1.001745 ->exp:0-> val0[1]val1[1745]
- * 1.001745 ->exp:2-> val0[100]val1[174500]
- * 1.001745 ->exp:4-> val0[10017]val1[450000]
- * 9.806650 ->exp:-2-> val0[0]val1[98066]
+ * 9.806650000 ->exp:2-> val0[980]val1[665000000]
+ * 9.000806000 ->exp:2-> val0[900]val1[80600000]
+ * 0.174535293 ->exp:2-> val0[17]val1[453529300]
+ * 1.001745329 ->exp:0-> val0[1]val1[1745329]
+ * 1.001745329 ->exp:2-> val0[100]val1[174532900]
+ * 1.001745329 ->exp:4-> val0[10017]val1[453290000]
+ * 9.806650000 ->exp:-2-> val0[0]val1[98066500]
*/
-static void adjust_exponent_micro(int *val0, int *val1, int scale0,
+static void adjust_exponent_nano(int *val0, int *val1, int scale0,
int scale1, int exp)
{
int i;
@@ -285,32 +285,32 @@ static void adjust_exponent_micro(int *val0, int *val1, int scale0,
if (exp > 0) {
*val0 = scale0 * pow_10(exp);
res = 0;
- if (exp > 6) {
+ if (exp > 9) {
*val1 = 0;
return;
}
for (i = 0; i < exp; ++i) {
- x = scale1 / pow_10(5 - i);
+ x = scale1 / pow_10(8 - i);
res += (pow_10(exp - 1 - i) * x);
- scale1 = scale1 % pow_10(5 - i);
+ scale1 = scale1 % pow_10(8 - i);
}
*val0 += res;
*val1 = scale1 * pow_10(exp);
} else if (exp < 0) {
exp = abs(exp);
- if (exp > 6) {
+ if (exp > 9) {
*val0 = *val1 = 0;
return;
}
*val0 = scale0 / pow_10(exp);
rem = scale0 % pow_10(exp);
res = 0;
- for (i = 0; i < (6 - exp); ++i) {
- x = scale1 / pow_10(5 - i);
- res += (pow_10(5 - exp - i) * x);
- scale1 = scale1 % pow_10(5 - i);
+ for (i = 0; i < (9 - exp); ++i) {
+ x = scale1 / pow_10(8 - i);
+ res += (pow_10(8 - exp - i) * x);
+ scale1 = scale1 % pow_10(8 - i);
}
- *val1 = rem * pow_10(6 - exp) + res;
+ *val1 = rem * pow_10(9 - exp) + res;
} else {
*val0 = scale0;
*val1 = scale1;
@@ -332,14 +332,14 @@ int hid_sensor_format_scale(u32 usage_id,
unit_conversion[i].unit == attr_info->units) {
exp = hid_sensor_convert_exponent(
attr_info->unit_expo);
- adjust_exponent_micro(val0, val1,
+ adjust_exponent_nano(val0, val1,
unit_conversion[i].scale_val0,
unit_conversion[i].scale_val1, exp);
break;
}
}
- return IIO_VAL_INT_PLUS_MICRO;
+ return IIO_VAL_INT_PLUS_NANO;
}
EXPORT_SYMBOL(hid_sensor_format_scale);
diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c
index 285a64a..975a1f1 100644
--- a/drivers/iio/common/st_sensors/st_sensors_core.c
+++ b/drivers/iio/common/st_sensors/st_sensors_core.c
@@ -612,7 +612,7 @@ EXPORT_SYMBOL(st_sensors_sysfs_sampling_frequency_avail);
ssize_t st_sensors_sysfs_scale_avail(struct device *dev,
struct device_attribute *attr, char *buf)
{
- int i, len = 0;
+ int i, len = 0, q, r;
struct iio_dev *indio_dev = dev_get_drvdata(dev);
struct st_sensor_data *sdata = iio_priv(indio_dev);
@@ -621,8 +621,10 @@ ssize_t st_sensors_sysfs_scale_avail(struct device *dev,
if (sdata->sensor_settings->fs.fs_avl[i].num == 0)
break;
- len += scnprintf(buf + len, PAGE_SIZE - len, "0.%06u ",
- sdata->sensor_settings->fs.fs_avl[i].gain);
+ q = sdata->sensor_settings->fs.fs_avl[i].gain / 1000000;
+ r = sdata->sensor_settings->fs.fs_avl[i].gain % 1000000;
+
+ len += scnprintf(buf + len, PAGE_SIZE - len, "%u.%06u ", q, r);
}
mutex_unlock(&indio_dev->mlock);
buf[len - 1] = '\n';
diff --git a/drivers/iio/orientation/hid-sensor-rotation.c b/drivers/iio/orientation/hid-sensor-rotation.c
index b98b9d9..a97e802c 100644
--- a/drivers/iio/orientation/hid-sensor-rotation.c
+++ b/drivers/iio/orientation/hid-sensor-rotation.c
@@ -335,6 +335,7 @@ static struct platform_driver hid_dev_rot_platform_driver = {
.id_table = hid_dev_rot_ids,
.driver = {
.name = KBUILD_MODNAME,
+ .pm = &hid_sensor_pm_ops,
},
.probe = hid_dev_rot_probe,
.remove = hid_dev_rot_remove,
diff --git a/drivers/iio/temperature/maxim_thermocouple.c b/drivers/iio/temperature/maxim_thermocouple.c
index 39dd202..f962f31 100644
--- a/drivers/iio/temperature/maxim_thermocouple.c
+++ b/drivers/iio/temperature/maxim_thermocouple.c
@@ -123,22 +123,26 @@ static int maxim_thermocouple_read(struct maxim_thermocouple_data *data,
{
unsigned int storage_bytes = data->chip->read_size;
unsigned int shift = chan->scan_type.shift + (chan->address * 8);
- unsigned int buf;
+ __be16 buf16;
+ __be32 buf32;
int ret;
- ret = spi_read(data->spi, (void *) &buf, storage_bytes);
- if (ret)
- return ret;
-
switch (storage_bytes) {
case 2:
- *val = be16_to_cpu(buf);
+ ret = spi_read(data->spi, (void *)&buf16, storage_bytes);
+ *val = be16_to_cpu(buf16);
break;
case 4:
- *val = be32_to_cpu(buf);
+ ret = spi_read(data->spi, (void *)&buf32, storage_bytes);
+ *val = be32_to_cpu(buf32);
break;
+ default:
+ ret = -EINVAL;
}
+ if (ret)
+ return ret;
+
/* check to be sure this is a valid reading */
if (*val & data->chip->status_bit)
return -EINVAL;
diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 19a418a..fb3fb89 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -89,4 +89,6 @@
source "drivers/infiniband/hw/hfi1/Kconfig"
+source "drivers/infiniband/hw/qedr/Kconfig"
+
endif # INFINIBAND
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 36bf50e..c68f4fe 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -116,7 +116,7 @@ static LIST_HEAD(dev_list);
static LIST_HEAD(listen_any_list);
static DEFINE_MUTEX(lock);
static struct workqueue_struct *cma_wq;
-static int cma_pernet_id;
+static unsigned int cma_pernet_id;
struct cma_pernet {
struct idr tcp_ps;
@@ -1094,47 +1094,47 @@ static void cma_save_ib_info(struct sockaddr *src_addr,
}
}
-static void cma_save_ip4_info(struct sockaddr *src_addr,
- struct sockaddr *dst_addr,
+static void cma_save_ip4_info(struct sockaddr_in *src_addr,
+ struct sockaddr_in *dst_addr,
struct cma_hdr *hdr,
__be16 local_port)
{
- struct sockaddr_in *ip4;
-
if (src_addr) {
- ip4 = (struct sockaddr_in *)src_addr;
- ip4->sin_family = AF_INET;
- ip4->sin_addr.s_addr = hdr->dst_addr.ip4.addr;
- ip4->sin_port = local_port;
+ *src_addr = (struct sockaddr_in) {
+ .sin_family = AF_INET,
+ .sin_addr.s_addr = hdr->dst_addr.ip4.addr,
+ .sin_port = local_port,
+ };
}
if (dst_addr) {
- ip4 = (struct sockaddr_in *)dst_addr;
- ip4->sin_family = AF_INET;
- ip4->sin_addr.s_addr = hdr->src_addr.ip4.addr;
- ip4->sin_port = hdr->port;
+ *dst_addr = (struct sockaddr_in) {
+ .sin_family = AF_INET,
+ .sin_addr.s_addr = hdr->src_addr.ip4.addr,
+ .sin_port = hdr->port,
+ };
}
}
-static void cma_save_ip6_info(struct sockaddr *src_addr,
- struct sockaddr *dst_addr,
+static void cma_save_ip6_info(struct sockaddr_in6 *src_addr,
+ struct sockaddr_in6 *dst_addr,
struct cma_hdr *hdr,
__be16 local_port)
{
- struct sockaddr_in6 *ip6;
-
if (src_addr) {
- ip6 = (struct sockaddr_in6 *)src_addr;
- ip6->sin6_family = AF_INET6;
- ip6->sin6_addr = hdr->dst_addr.ip6;
- ip6->sin6_port = local_port;
+ *src_addr = (struct sockaddr_in6) {
+ .sin6_family = AF_INET6,
+ .sin6_addr = hdr->dst_addr.ip6,
+ .sin6_port = local_port,
+ };
}
if (dst_addr) {
- ip6 = (struct sockaddr_in6 *)dst_addr;
- ip6->sin6_family = AF_INET6;
- ip6->sin6_addr = hdr->src_addr.ip6;
- ip6->sin6_port = hdr->port;
+ *dst_addr = (struct sockaddr_in6) {
+ .sin6_family = AF_INET6,
+ .sin6_addr = hdr->src_addr.ip6,
+ .sin6_port = hdr->port,
+ };
}
}
@@ -1159,10 +1159,12 @@ static int cma_save_ip_info(struct sockaddr *src_addr,
switch (cma_get_ip_ver(hdr)) {
case 4:
- cma_save_ip4_info(src_addr, dst_addr, hdr, port);
+ cma_save_ip4_info((struct sockaddr_in *)src_addr,
+ (struct sockaddr_in *)dst_addr, hdr, port);
break;
case 6:
- cma_save_ip6_info(src_addr, dst_addr, hdr, port);
+ cma_save_ip6_info((struct sockaddr_in6 *)src_addr,
+ (struct sockaddr_in6 *)dst_addr, hdr, port);
break;
default:
return -EAFNOSUPPORT;
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index c68746c..224ad27 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -94,6 +94,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
unsigned long dma_attrs = 0;
struct scatterlist *sg, *sg_list_start;
int need_release = 0;
+ unsigned int gup_flags = FOLL_WRITE;
if (dmasync)
dma_attrs |= DMA_ATTR_WRITE_BARRIER;
@@ -183,6 +184,9 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
if (ret)
goto out;
+ if (!umem->writable)
+ gup_flags |= FOLL_FORCE;
+
need_release = 1;
sg_list_start = umem->sg_head.sgl;
@@ -190,7 +194,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
ret = get_user_pages(cur_base,
min_t(unsigned long, npages,
PAGE_SIZE / sizeof (struct page *)),
- 1, !umem->writable, page_list, vma_list);
+ gup_flags, page_list, vma_list);
if (ret < 0)
goto out;
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 75077a0..1f0fe32 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -527,6 +527,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
u64 off;
int j, k, ret = 0, start_idx, npages = 0;
u64 base_virt_addr;
+ unsigned int flags = 0;
if (access_mask == 0)
return -EINVAL;
@@ -556,6 +557,9 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
goto out_put_task;
}
+ if (access_mask & ODP_WRITE_ALLOWED_BIT)
+ flags |= FOLL_WRITE;
+
start_idx = (user_virt - ib_umem_start(umem)) >> PAGE_SHIFT;
k = start_idx;
@@ -574,8 +578,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
*/
npages = get_user_pages_remote(owning_process, owning_mm,
user_virt, gup_num_pages,
- access_mask & ODP_WRITE_ALLOWED_BIT,
- 0, local_page_list, NULL);
+ flags, local_page_list, NULL);
up_read(&owning_mm->mmap_sem);
if (npages < 0)
diff --git a/drivers/infiniband/hw/Makefile b/drivers/infiniband/hw/Makefile
index 21fe401..e7a5ed9 100644
--- a/drivers/infiniband/hw/Makefile
+++ b/drivers/infiniband/hw/Makefile
@@ -10,3 +10,4 @@
obj-$(CONFIG_INFINIBAND_USNIC) += usnic/
obj-$(CONFIG_INFINIBAND_HFI1) += hfi1/
obj-$(CONFIG_INFINIBAND_HNS) += hns/
+obj-$(CONFIG_INFINIBAND_QEDR) += qedr/
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index 93e3d27..4e5baf4 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -1481,6 +1481,7 @@ static int c4iw_uld_control(void *handle, enum cxgb4_control control, ...)
static struct cxgb4_uld_info c4iw_uld_info = {
.name = DRV_NAME,
.nrxq = MAX_ULD_QSETS,
+ .ntxq = MAX_ULD_QSETS,
.rxq_size = 511,
.ciq = true,
.lro = false,
diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c
index 875597b..0973659 100644
--- a/drivers/infiniband/hw/hns/hns_roce_cq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_cq.c
@@ -83,8 +83,7 @@ static int hns_roce_sw2hw_cq(struct hns_roce_dev *dev,
static int hns_roce_cq_alloc(struct hns_roce_dev *hr_dev, int nent,
struct hns_roce_mtt *hr_mtt,
struct hns_roce_uar *hr_uar,
- struct hns_roce_cq *hr_cq, int vector,
- int collapsed)
+ struct hns_roce_cq *hr_cq, int vector)
{
struct hns_roce_cmd_mailbox *mailbox = NULL;
struct hns_roce_cq_table *cq_table = NULL;
@@ -153,6 +152,9 @@ static int hns_roce_cq_alloc(struct hns_roce_dev *hr_dev, int nent,
hr_cq->cons_index = 0;
hr_cq->uar = hr_uar;
+ atomic_set(&hr_cq->refcount, 1);
+ init_completion(&hr_cq->free);
+
return 0;
err_radix:
@@ -192,6 +194,11 @@ static void hns_roce_free_cq(struct hns_roce_dev *hr_dev,
/* Waiting interrupt process procedure carried out */
synchronize_irq(hr_dev->eq_table.eq[hr_cq->vector].irq);
+ /* wait for all interrupt processed */
+ if (atomic_dec_and_test(&hr_cq->refcount))
+ complete(&hr_cq->free);
+ wait_for_completion(&hr_cq->free);
+
spin_lock_irq(&cq_table->lock);
radix_tree_delete(&cq_table->tree, hr_cq->cqn);
spin_unlock_irq(&cq_table->lock);
@@ -300,10 +307,7 @@ struct ib_cq *hns_roce_ib_create_cq(struct ib_device *ib_dev,
cq_entries = roundup_pow_of_two((unsigned int)cq_entries);
hr_cq->ib_cq.cqe = cq_entries - 1;
- mutex_init(&hr_cq->resize_mutex);
spin_lock_init(&hr_cq->lock);
- hr_cq->hr_resize_buf = NULL;
- hr_cq->resize_umem = NULL;
if (context) {
if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd))) {
@@ -338,8 +342,8 @@ struct ib_cq *hns_roce_ib_create_cq(struct ib_device *ib_dev,
}
/* Allocate cq index, fill cq_context */
- ret = hns_roce_cq_alloc(hr_dev, cq_entries, &hr_cq->hr_buf.hr_mtt,
- uar, hr_cq, vector, 0);
+ ret = hns_roce_cq_alloc(hr_dev, cq_entries, &hr_cq->hr_buf.hr_mtt, uar,
+ hr_cq, vector);
if (ret) {
dev_err(dev, "Creat CQ .Failed to cq_alloc.\n");
goto err_mtt;
@@ -353,12 +357,15 @@ struct ib_cq *hns_roce_ib_create_cq(struct ib_device *ib_dev,
if (context) {
if (ib_copy_to_udata(udata, &hr_cq->cqn, sizeof(u64))) {
ret = -EFAULT;
- goto err_mtt;
+ goto err_cqc;
}
}
return &hr_cq->ib_cq;
+err_cqc:
+ hns_roce_free_cq(hr_dev, hr_cq);
+
err_mtt:
hns_roce_mtt_cleanup(hr_dev, &hr_cq->hr_buf.hr_mtt);
if (context)
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index ea73580..3417315 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -62,7 +62,7 @@
#define HNS_ROCE_AEQE_OF_VEC_NUM 1
/* 4G/4K = 1M */
-#define HNS_ROCE_SL_SHIFT 29
+#define HNS_ROCE_SL_SHIFT 28
#define HNS_ROCE_TCLASS_SHIFT 20
#define HNS_ROCE_FLOW_LABLE_MASK 0xfffff
@@ -74,7 +74,9 @@
#define MR_TYPE_DMA 0x03
#define PKEY_ID 0xffff
+#define GUID_LEN 8
#define NODE_DESC_SIZE 64
+#define DB_REG_OFFSET 0x1000
#define SERV_TYPE_RC 0
#define SERV_TYPE_RD 1
@@ -282,20 +284,11 @@ struct hns_roce_cq_buf {
struct hns_roce_mtt hr_mtt;
};
-struct hns_roce_cq_resize {
- struct hns_roce_cq_buf hr_buf;
- int cqe;
-};
-
struct hns_roce_cq {
struct ib_cq ib_cq;
struct hns_roce_cq_buf hr_buf;
- /* pointer to store information after resize*/
- struct hns_roce_cq_resize *hr_resize_buf;
spinlock_t lock;
- struct mutex resize_mutex;
struct ib_umem *umem;
- struct ib_umem *resize_umem;
void (*comp)(struct hns_roce_cq *);
void (*event)(struct hns_roce_cq *, enum hns_roce_event);
@@ -408,6 +401,7 @@ struct hns_roce_qp {
u32 buff_size;
struct mutex mutex;
u8 port;
+ u8 phy_port;
u8 sl;
u8 resp_depth;
u8 state;
@@ -471,7 +465,6 @@ struct hns_roce_caps {
u32 max_rq_desc_sz; /* 64 */
int max_qp_init_rdma;
int max_qp_dest_rdma;
- int sqp_start;
int num_cqs;
int max_cqes;
int reserved_cqs;
@@ -512,6 +505,8 @@ struct hns_roce_hw {
void (*write_cqc)(struct hns_roce_dev *hr_dev,
struct hns_roce_cq *hr_cq, void *mb_buf, u64 *mtts,
dma_addr_t dma_handle, int nent, u32 vector);
+ int (*clear_hem)(struct hns_roce_dev *hr_dev,
+ struct hns_roce_hem_table *table, int obj);
int (*query_qp)(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr);
int (*modify_qp)(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
@@ -533,7 +528,6 @@ struct hns_roce_dev {
struct hns_roce_uar priv_uar;
const char *irq_names[HNS_ROCE_MAX_IRQ_NUM];
spinlock_t sm_lock;
- spinlock_t cq_db_lock;
spinlock_t bt_cmd_lock;
struct hns_roce_ib_iboe iboe;
diff --git a/drivers/infiniband/hw/hns/hns_roce_eq.c b/drivers/infiniband/hw/hns/hns_roce_eq.c
index 98af7fe..21e21b0 100644
--- a/drivers/infiniband/hw/hns/hns_roce_eq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_eq.c
@@ -66,9 +66,6 @@ static void hns_roce_wq_catas_err_handle(struct hns_roce_dev *hr_dev,
{
struct device *dev = &hr_dev->pdev->dev;
- qpn = roce_get_field(aeqe->event.qp_event.qp,
- HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_M,
- HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_S);
dev_warn(dev, "Local Work Queue Catastrophic Error.\n");
switch (roce_get_field(aeqe->asyn, HNS_ROCE_AEQE_U32_4_EVENT_SUB_TYPE_M,
HNS_ROCE_AEQE_U32_4_EVENT_SUB_TYPE_S)) {
@@ -96,13 +93,6 @@ static void hns_roce_wq_catas_err_handle(struct hns_roce_dev *hr_dev,
default:
break;
}
-
- hns_roce_qp_event(hr_dev, roce_get_field(aeqe->event.qp_event.qp,
- HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_M,
- HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_S),
- roce_get_field(aeqe->asyn,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_M,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_S));
}
static void hns_roce_local_wq_access_err_handle(struct hns_roce_dev *hr_dev,
@@ -111,9 +101,6 @@ static void hns_roce_local_wq_access_err_handle(struct hns_roce_dev *hr_dev,
{
struct device *dev = &hr_dev->pdev->dev;
- qpn = roce_get_field(aeqe->event.qp_event.qp,
- HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_M,
- HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_S);
dev_warn(dev, "Local Access Violation Work Queue Error.\n");
switch (roce_get_field(aeqe->asyn, HNS_ROCE_AEQE_U32_4_EVENT_SUB_TYPE_M,
HNS_ROCE_AEQE_U32_4_EVENT_SUB_TYPE_S)) {
@@ -141,13 +128,69 @@ static void hns_roce_local_wq_access_err_handle(struct hns_roce_dev *hr_dev,
default:
break;
}
+}
- hns_roce_qp_event(hr_dev, roce_get_field(aeqe->event.qp_event.qp,
- HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_M,
- HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_S),
- roce_get_field(aeqe->asyn,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_M,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_S));
+static void hns_roce_qp_err_handle(struct hns_roce_dev *hr_dev,
+ struct hns_roce_aeqe *aeqe,
+ int event_type)
+{
+ struct device *dev = &hr_dev->pdev->dev;
+ int phy_port;
+ int qpn;
+
+ qpn = roce_get_field(aeqe->event.qp_event.qp,
+ HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_M,
+ HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_S);
+ phy_port = roce_get_field(aeqe->event.qp_event.qp,
+ HNS_ROCE_AEQE_EVENT_QP_EVENT_PORT_NUM_M,
+ HNS_ROCE_AEQE_EVENT_QP_EVENT_PORT_NUM_S);
+ if (qpn <= 1)
+ qpn = HNS_ROCE_MAX_PORTS * qpn + phy_port;
+
+ switch (event_type) {
+ case HNS_ROCE_EVENT_TYPE_INV_REQ_LOCAL_WQ_ERROR:
+ dev_warn(dev, "Invalid Req Local Work Queue Error.\n"
+ "QP %d, phy_port %d.\n", qpn, phy_port);
+ break;
+ case HNS_ROCE_EVENT_TYPE_WQ_CATAS_ERROR:
+ hns_roce_wq_catas_err_handle(hr_dev, aeqe, qpn);
+ break;
+ case HNS_ROCE_EVENT_TYPE_LOCAL_WQ_ACCESS_ERROR:
+ hns_roce_local_wq_access_err_handle(hr_dev, aeqe, qpn);
+ break;
+ default:
+ break;
+ }
+
+ hns_roce_qp_event(hr_dev, qpn, event_type);
+}
+
+static void hns_roce_cq_err_handle(struct hns_roce_dev *hr_dev,
+ struct hns_roce_aeqe *aeqe,
+ int event_type)
+{
+ struct device *dev = &hr_dev->pdev->dev;
+ u32 cqn;
+
+ cqn = le32_to_cpu(roce_get_field(aeqe->event.cq_event.cq,
+ HNS_ROCE_AEQE_EVENT_CQ_EVENT_CQ_CQN_M,
+ HNS_ROCE_AEQE_EVENT_CQ_EVENT_CQ_CQN_S));
+
+ switch (event_type) {
+ case HNS_ROCE_EVENT_TYPE_CQ_ACCESS_ERROR:
+ dev_warn(dev, "CQ 0x%x access err.\n", cqn);
+ break;
+ case HNS_ROCE_EVENT_TYPE_CQ_OVERFLOW:
+ dev_warn(dev, "CQ 0x%x overflow\n", cqn);
+ break;
+ case HNS_ROCE_EVENT_TYPE_CQ_ID_INVALID:
+ dev_warn(dev, "CQ 0x%x ID invalid.\n", cqn);
+ break;
+ default:
+ break;
+ }
+
+ hns_roce_cq_event(hr_dev, cqn, event_type);
}
static void hns_roce_db_overflow_handle(struct hns_roce_dev *hr_dev,
@@ -185,7 +228,7 @@ static int hns_roce_aeq_int(struct hns_roce_dev *hr_dev, struct hns_roce_eq *eq)
struct device *dev = &hr_dev->pdev->dev;
struct hns_roce_aeqe *aeqe;
int aeqes_found = 0;
- int qpn = 0;
+ int event_type;
while ((aeqe = next_aeqe_sw(eq))) {
dev_dbg(dev, "aeqe = %p, aeqe->asyn.event_type = 0x%lx\n", aeqe,
@@ -195,9 +238,10 @@ static int hns_roce_aeq_int(struct hns_roce_dev *hr_dev, struct hns_roce_eq *eq)
/* Memory barrier */
rmb();
- switch (roce_get_field(aeqe->asyn,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_M,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_S)) {
+ event_type = roce_get_field(aeqe->asyn,
+ HNS_ROCE_AEQE_U32_4_EVENT_TYPE_M,
+ HNS_ROCE_AEQE_U32_4_EVENT_TYPE_S);
+ switch (event_type) {
case HNS_ROCE_EVENT_TYPE_PATH_MIG:
dev_warn(dev, "PATH MIG not supported\n");
break;
@@ -211,23 +255,9 @@ static int hns_roce_aeq_int(struct hns_roce_dev *hr_dev, struct hns_roce_eq *eq)
dev_warn(dev, "PATH MIG failed\n");
break;
case HNS_ROCE_EVENT_TYPE_INV_REQ_LOCAL_WQ_ERROR:
- dev_warn(dev, "qpn = 0x%lx\n",
- roce_get_field(aeqe->event.qp_event.qp,
- HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_M,
- HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_S));
- hns_roce_qp_event(hr_dev,
- roce_get_field(aeqe->event.qp_event.qp,
- HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_M,
- HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_S),
- roce_get_field(aeqe->asyn,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_M,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_S));
- break;
case HNS_ROCE_EVENT_TYPE_WQ_CATAS_ERROR:
- hns_roce_wq_catas_err_handle(hr_dev, aeqe, qpn);
- break;
case HNS_ROCE_EVENT_TYPE_LOCAL_WQ_ACCESS_ERROR:
- hns_roce_local_wq_access_err_handle(hr_dev, aeqe, qpn);
+ hns_roce_qp_err_handle(hr_dev, aeqe, event_type);
break;
case HNS_ROCE_EVENT_TYPE_SRQ_LIMIT_REACH:
case HNS_ROCE_EVENT_TYPE_SRQ_CATAS_ERROR:
@@ -235,40 +265,9 @@ static int hns_roce_aeq_int(struct hns_roce_dev *hr_dev, struct hns_roce_eq *eq)
dev_warn(dev, "SRQ not support!\n");
break;
case HNS_ROCE_EVENT_TYPE_CQ_ACCESS_ERROR:
- dev_warn(dev, "CQ 0x%lx access err.\n",
- roce_get_field(aeqe->event.cq_event.cq,
- HNS_ROCE_AEQE_EVENT_CQ_EVENT_CQ_CQN_M,
- HNS_ROCE_AEQE_EVENT_CQ_EVENT_CQ_CQN_S));
- hns_roce_cq_event(hr_dev,
- le32_to_cpu(roce_get_field(aeqe->event.cq_event.cq,
- HNS_ROCE_AEQE_EVENT_CQ_EVENT_CQ_CQN_M,
- HNS_ROCE_AEQE_EVENT_CQ_EVENT_CQ_CQN_S)),
- roce_get_field(aeqe->asyn,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_M,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_S));
- break;
case HNS_ROCE_EVENT_TYPE_CQ_OVERFLOW:
- dev_warn(dev, "CQ 0x%lx overflow\n",
- roce_get_field(aeqe->event.cq_event.cq,
- HNS_ROCE_AEQE_EVENT_CQ_EVENT_CQ_CQN_M,
- HNS_ROCE_AEQE_EVENT_CQ_EVENT_CQ_CQN_S));
- hns_roce_cq_event(hr_dev,
- le32_to_cpu(roce_get_field(aeqe->event.cq_event.cq,
- HNS_ROCE_AEQE_EVENT_CQ_EVENT_CQ_CQN_M,
- HNS_ROCE_AEQE_EVENT_CQ_EVENT_CQ_CQN_S)),
- roce_get_field(aeqe->asyn,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_M,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_S));
- break;
case HNS_ROCE_EVENT_TYPE_CQ_ID_INVALID:
- dev_warn(dev, "CQ ID invalid.\n");
- hns_roce_cq_event(hr_dev,
- le32_to_cpu(roce_get_field(aeqe->event.cq_event.cq,
- HNS_ROCE_AEQE_EVENT_CQ_EVENT_CQ_CQN_M,
- HNS_ROCE_AEQE_EVENT_CQ_EVENT_CQ_CQN_S)),
- roce_get_field(aeqe->asyn,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_M,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_S));
+ hns_roce_cq_err_handle(hr_dev, aeqe, event_type);
break;
case HNS_ROCE_EVENT_TYPE_PORT_CHANGE:
dev_warn(dev, "port change.\n");
@@ -290,11 +289,8 @@ static int hns_roce_aeq_int(struct hns_roce_dev *hr_dev, struct hns_roce_eq *eq)
HNS_ROCE_AEQE_EVENT_CE_EVENT_CEQE_CEQN_S));
break;
default:
- dev_warn(dev, "Unhandled event 0x%lx on EQ %d at index %u\n",
- roce_get_field(aeqe->asyn,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_M,
- HNS_ROCE_AEQE_U32_4_EVENT_TYPE_S),
- eq->eqn, eq->cons_index);
+ dev_warn(dev, "Unhandled event %d on EQ %d at index %u\n",
+ event_type, eq->eqn, eq->cons_index);
break;
};
diff --git a/drivers/infiniband/hw/hns/hns_roce_eq.h b/drivers/infiniband/hw/hns/hns_roce_eq.h
index fe43881..c6d212d 100644
--- a/drivers/infiniband/hw/hns/hns_roce_eq.h
+++ b/drivers/infiniband/hw/hns/hns_roce_eq.h
@@ -107,6 +107,10 @@ struct hns_roce_aeqe {
#define HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_M \
(((1UL << 24) - 1) << HNS_ROCE_AEQE_EVENT_QP_EVENT_QP_QPN_S)
+#define HNS_ROCE_AEQE_EVENT_QP_EVENT_PORT_NUM_S 25
+#define HNS_ROCE_AEQE_EVENT_QP_EVENT_PORT_NUM_M \
+ (((1UL << 3) - 1) << HNS_ROCE_AEQE_EVENT_QP_EVENT_PORT_NUM_S)
+
#define HNS_ROCE_AEQE_EVENT_CQ_EVENT_CQ_CQN_S 0
#define HNS_ROCE_AEQE_EVENT_CQ_EVENT_CQ_CQN_M \
(((1UL << 16) - 1) << HNS_ROCE_AEQE_EVENT_CQ_EVENT_CQ_CQN_S)
diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c
index d53d643..250d8f2 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hem.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hem.c
@@ -36,14 +36,10 @@
#include "hns_roce_hem.h"
#include "hns_roce_common.h"
-#define HW_SYNC_TIMEOUT_MSECS 500
-#define HW_SYNC_SLEEP_TIME_INTERVAL 20
-
#define HNS_ROCE_HEM_ALLOC_SIZE (1 << 17)
#define HNS_ROCE_TABLE_CHUNK_SIZE (1 << 17)
#define DMA_ADDR_T_SHIFT 12
-#define BT_CMD_SYNC_SHIFT 31
#define BT_BA_SHIFT 32
struct hns_roce_hem *hns_roce_alloc_hem(struct hns_roce_dev *hr_dev, int npages,
@@ -213,74 +209,6 @@ static int hns_roce_set_hem(struct hns_roce_dev *hr_dev,
return ret;
}
-static int hns_roce_clear_hem(struct hns_roce_dev *hr_dev,
- struct hns_roce_hem_table *table,
- unsigned long obj)
-{
- struct device *dev = &hr_dev->pdev->dev;
- unsigned long end = 0;
- unsigned long flags;
- void __iomem *bt_cmd;
- uint32_t bt_cmd_val[2];
- u32 bt_cmd_h_val = 0;
- int ret = 0;
-
- switch (table->type) {
- case HEM_TYPE_QPC:
- roce_set_field(bt_cmd_h_val, ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_M,
- ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_S, HEM_TYPE_QPC);
- break;
- case HEM_TYPE_MTPT:
- roce_set_field(bt_cmd_h_val, ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_M,
- ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_S,
- HEM_TYPE_MTPT);
- break;
- case HEM_TYPE_CQC:
- roce_set_field(bt_cmd_h_val, ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_M,
- ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_S, HEM_TYPE_CQC);
- break;
- case HEM_TYPE_SRQC:
- roce_set_field(bt_cmd_h_val, ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_M,
- ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_S,
- HEM_TYPE_SRQC);
- break;
- default:
- return ret;
- }
- roce_set_field(bt_cmd_h_val, ROCEE_BT_CMD_H_ROCEE_BT_CMD_IN_MDF_M,
- ROCEE_BT_CMD_H_ROCEE_BT_CMD_IN_MDF_S, obj);
- roce_set_bit(bt_cmd_h_val, ROCEE_BT_CMD_H_ROCEE_BT_CMD_S, 0);
- roce_set_bit(bt_cmd_h_val, ROCEE_BT_CMD_H_ROCEE_BT_CMD_HW_SYNS_S, 1);
- roce_set_field(bt_cmd_h_val, ROCEE_BT_CMD_H_ROCEE_BT_CMD_BA_H_M,
- ROCEE_BT_CMD_H_ROCEE_BT_CMD_BA_H_S, 0);
-
- spin_lock_irqsave(&hr_dev->bt_cmd_lock, flags);
-
- bt_cmd = hr_dev->reg_base + ROCEE_BT_CMD_H_REG;
-
- end = msecs_to_jiffies(HW_SYNC_TIMEOUT_MSECS) + jiffies;
- while (1) {
- if (readl(bt_cmd) >> BT_CMD_SYNC_SHIFT) {
- if (!(time_before(jiffies, end))) {
- dev_err(dev, "Write bt_cmd err,hw_sync is not zero.\n");
- spin_unlock_irqrestore(&hr_dev->bt_cmd_lock,
- flags);
- return -EBUSY;
- }
- } else {
- break;
- }
- msleep(HW_SYNC_SLEEP_TIME_INTERVAL);
- }
-
- bt_cmd_val[0] = 0;
- bt_cmd_val[1] = bt_cmd_h_val;
- hns_roce_write64_k(bt_cmd_val, hr_dev->reg_base + ROCEE_BT_CMD_L_REG);
- spin_unlock_irqrestore(&hr_dev->bt_cmd_lock, flags);
-
- return ret;
-}
-
int hns_roce_table_get(struct hns_roce_dev *hr_dev,
struct hns_roce_hem_table *table, unsigned long obj)
{
@@ -333,7 +261,7 @@ void hns_roce_table_put(struct hns_roce_dev *hr_dev,
if (--table->hem[i]->refcount == 0) {
/* Clear HEM base address */
- if (hns_roce_clear_hem(hr_dev, table, obj))
+ if (hr_dev->hw->clear_hem(hr_dev, table, obj))
dev_warn(dev, "Clear HEM base address failed.\n");
hns_roce_free_hem(hr_dev, table->hem[i]);
@@ -456,7 +384,7 @@ void hns_roce_cleanup_hem_table(struct hns_roce_dev *hr_dev,
for (i = 0; i < table->num_hem; ++i)
if (table->hem[i]) {
- if (hns_roce_clear_hem(hr_dev, table,
+ if (hr_dev->hw->clear_hem(hr_dev, table,
i * HNS_ROCE_TABLE_CHUNK_SIZE / table->obj_size))
dev_err(dev, "Clear HEM base address failed.\n");
diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.h b/drivers/infiniband/hw/hns/hns_roce_hem.h
index ad66175..4357488 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hem.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hem.h
@@ -34,6 +34,10 @@
#ifndef _HNS_ROCE_HEM_H
#define _HNS_ROCE_HEM_H
+#define HW_SYNC_TIMEOUT_MSECS 500
+#define HW_SYNC_SLEEP_TIME_INTERVAL 20
+#define BT_CMD_SYNC_SHIFT 31
+
enum {
/* MAP HEM(Hardware Entry Memory) */
HEM_TYPE_QPC = 0,
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index 399f5de..71232e5 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -73,8 +73,14 @@ int hns_roce_v1_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
u32 ind = 0;
int ret = 0;
- spin_lock_irqsave(&qp->sq.lock, flags);
+ if (unlikely(ibqp->qp_type != IB_QPT_GSI &&
+ ibqp->qp_type != IB_QPT_RC)) {
+ dev_err(dev, "un-supported QP type\n");
+ *bad_wr = NULL;
+ return -EOPNOTSUPP;
+ }
+ spin_lock_irqsave(&qp->sq.lock, flags);
ind = qp->sq_next_wqe;
for (nreq = 0; wr; ++nreq, wr = wr->next) {
if (hns_roce_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq)) {
@@ -162,7 +168,7 @@ int hns_roce_v1_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
roce_set_field(ud_sq_wqe->u32_36,
UD_SEND_WQE_U32_36_SGID_INDEX_M,
UD_SEND_WQE_U32_36_SGID_INDEX_S,
- hns_get_gid_index(hr_dev, qp->port,
+ hns_get_gid_index(hr_dev, qp->phy_port,
ah->av.gid_index));
roce_set_field(ud_sq_wqe->u32_40,
@@ -205,8 +211,7 @@ int hns_roce_v1_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
(wr->send_flags & IB_SEND_FENCE ?
(cpu_to_le32(HNS_ROCE_WQE_FENCE)) : 0);
- wqe = (struct hns_roce_wqe_ctrl_seg *)wqe +
- sizeof(struct hns_roce_wqe_ctrl_seg);
+ wqe += sizeof(struct hns_roce_wqe_ctrl_seg);
switch (wr->opcode) {
case IB_WR_RDMA_READ:
@@ -235,8 +240,7 @@ int hns_roce_v1_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
break;
}
ctrl->flag |= cpu_to_le32(ps_opcode);
- wqe = (struct hns_roce_wqe_raddr_seg *)wqe +
- sizeof(struct hns_roce_wqe_raddr_seg);
+ wqe += sizeof(struct hns_roce_wqe_raddr_seg);
dseg = wqe;
if (wr->send_flags & IB_SEND_INLINE && wr->num_sge) {
@@ -253,8 +257,7 @@ int hns_roce_v1_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
memcpy(wqe, ((void *) (uintptr_t)
wr->sg_list[i].addr),
wr->sg_list[i].length);
- wqe = (struct hns_roce_wqe_raddr_seg *)
- wqe + wr->sg_list[i].length;
+ wqe += wr->sg_list[i].length;
}
ctrl->flag |= HNS_ROCE_WQE_INLINE;
} else {
@@ -266,9 +269,6 @@ int hns_roce_v1_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
HNS_ROCE_WQE_SGE_NUM_BIT);
}
ind++;
- } else {
- dev_dbg(dev, "unSupported QP type\n");
- break;
}
}
@@ -285,7 +285,7 @@ int hns_roce_v1_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
SQ_DOORBELL_U32_4_SQ_HEAD_S,
(qp->sq.head & ((qp->sq.wqe_cnt << 1) - 1)));
roce_set_field(sq_db.u32_4, SQ_DOORBELL_U32_4_PORT_M,
- SQ_DOORBELL_U32_4_PORT_S, qp->port);
+ SQ_DOORBELL_U32_4_PORT_S, qp->phy_port);
roce_set_field(sq_db.u32_8, SQ_DOORBELL_U32_8_QPN_M,
SQ_DOORBELL_U32_8_QPN_S, qp->doorbell_qpn);
roce_set_bit(sq_db.u32_8, SQ_DOORBELL_HW_SYNC_S, 1);
@@ -365,14 +365,14 @@ int hns_roce_v1_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
/* SW update GSI rq header */
reg_val = roce_read(to_hr_dev(ibqp->device),
ROCEE_QP1C_CFG3_0_REG +
- QP1C_CFGN_OFFSET * hr_qp->port);
+ QP1C_CFGN_OFFSET * hr_qp->phy_port);
roce_set_field(reg_val,
ROCEE_QP1C_CFG3_0_ROCEE_QP1C_RQ_HEAD_M,
ROCEE_QP1C_CFG3_0_ROCEE_QP1C_RQ_HEAD_S,
hr_qp->rq.head);
roce_write(to_hr_dev(ibqp->device),
ROCEE_QP1C_CFG3_0_REG +
- QP1C_CFGN_OFFSET * hr_qp->port, reg_val);
+ QP1C_CFGN_OFFSET * hr_qp->phy_port, reg_val);
} else {
rq_db.u32_4 = 0;
rq_db.u32_8 = 0;
@@ -789,6 +789,66 @@ static void hns_roce_port_enable(struct hns_roce_dev *hr_dev, int enable_flag)
}
}
+static int hns_roce_bt_init(struct hns_roce_dev *hr_dev)
+{
+ struct device *dev = &hr_dev->pdev->dev;
+ struct hns_roce_v1_priv *priv;
+ int ret;
+
+ priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+
+ priv->bt_table.qpc_buf.buf = dma_alloc_coherent(dev,
+ HNS_ROCE_BT_RSV_BUF_SIZE, &priv->bt_table.qpc_buf.map,
+ GFP_KERNEL);
+ if (!priv->bt_table.qpc_buf.buf)
+ return -ENOMEM;
+
+ priv->bt_table.mtpt_buf.buf = dma_alloc_coherent(dev,
+ HNS_ROCE_BT_RSV_BUF_SIZE, &priv->bt_table.mtpt_buf.map,
+ GFP_KERNEL);
+ if (!priv->bt_table.mtpt_buf.buf) {
+ ret = -ENOMEM;
+ goto err_failed_alloc_mtpt_buf;
+ }
+
+ priv->bt_table.cqc_buf.buf = dma_alloc_coherent(dev,
+ HNS_ROCE_BT_RSV_BUF_SIZE, &priv->bt_table.cqc_buf.map,
+ GFP_KERNEL);
+ if (!priv->bt_table.cqc_buf.buf) {
+ ret = -ENOMEM;
+ goto err_failed_alloc_cqc_buf;
+ }
+
+ return 0;
+
+err_failed_alloc_cqc_buf:
+ dma_free_coherent(dev, HNS_ROCE_BT_RSV_BUF_SIZE,
+ priv->bt_table.mtpt_buf.buf, priv->bt_table.mtpt_buf.map);
+
+err_failed_alloc_mtpt_buf:
+ dma_free_coherent(dev, HNS_ROCE_BT_RSV_BUF_SIZE,
+ priv->bt_table.qpc_buf.buf, priv->bt_table.qpc_buf.map);
+
+ return ret;
+}
+
+static void hns_roce_bt_free(struct hns_roce_dev *hr_dev)
+{
+ struct device *dev = &hr_dev->pdev->dev;
+ struct hns_roce_v1_priv *priv;
+
+ priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+
+ dma_free_coherent(dev, HNS_ROCE_BT_RSV_BUF_SIZE,
+ priv->bt_table.cqc_buf.buf, priv->bt_table.cqc_buf.map);
+
+ dma_free_coherent(dev, HNS_ROCE_BT_RSV_BUF_SIZE,
+ priv->bt_table.mtpt_buf.buf, priv->bt_table.mtpt_buf.map);
+
+ dma_free_coherent(dev, HNS_ROCE_BT_RSV_BUF_SIZE,
+ priv->bt_table.qpc_buf.buf, priv->bt_table.qpc_buf.map);
+}
+
/**
* hns_roce_v1_reset - reset RoCE
* @hr_dev: RoCE device struct pointer
@@ -879,7 +939,6 @@ void hns_roce_v1_profile(struct hns_roce_dev *hr_dev)
caps->mtt_entry_sz = HNS_ROCE_V1_MTT_ENTRY_SIZE;
caps->cq_entry_sz = HNS_ROCE_V1_CQE_ENTRY_SIZE;
caps->page_size_cap = HNS_ROCE_V1_PAGE_SIZE_SUPPORT;
- caps->sqp_start = 0;
caps->reserved_lkey = 0;
caps->reserved_pds = 0;
caps->reserved_mrws = 1;
@@ -944,8 +1003,18 @@ int hns_roce_v1_init(struct hns_roce_dev *hr_dev)
hns_roce_port_enable(hr_dev, HNS_ROCE_PORT_UP);
+ ret = hns_roce_bt_init(hr_dev);
+ if (ret) {
+ dev_err(dev, "bt init failed!\n");
+ goto error_failed_bt_init;
+ }
+
return 0;
+error_failed_bt_init:
+ hns_roce_port_enable(hr_dev, HNS_ROCE_PORT_DOWN);
+ hns_roce_raq_free(hr_dev);
+
error_failed_raq_init:
hns_roce_db_free(hr_dev);
return ret;
@@ -953,6 +1022,7 @@ int hns_roce_v1_init(struct hns_roce_dev *hr_dev)
void hns_roce_v1_exit(struct hns_roce_dev *hr_dev)
{
+ hns_roce_bt_free(hr_dev);
hns_roce_port_enable(hr_dev, HNS_ROCE_PORT_DOWN);
hns_roce_raq_free(hr_dev);
hns_roce_db_free(hr_dev);
@@ -1192,9 +1262,7 @@ static struct hns_roce_cqe *next_cqe_sw(struct hns_roce_cq *hr_cq)
return get_sw_cqe(hr_cq, hr_cq->cons_index);
}
-void hns_roce_v1_cq_set_ci(struct hns_roce_cq *hr_cq, u32 cons_index,
- spinlock_t *doorbell_lock)
-
+void hns_roce_v1_cq_set_ci(struct hns_roce_cq *hr_cq, u32 cons_index)
{
u32 doorbell[2];
@@ -1254,8 +1322,7 @@ static void __hns_roce_v1_cq_clean(struct hns_roce_cq *hr_cq, u32 qpn,
*/
wmb();
- hns_roce_v1_cq_set_ci(hr_cq, hr_cq->cons_index,
- &to_hr_dev(hr_cq->ib_cq.device)->cq_db_lock);
+ hns_roce_v1_cq_set_ci(hr_cq, hr_cq->cons_index);
}
}
@@ -1485,7 +1552,8 @@ static int hns_roce_v1_poll_one(struct hns_roce_cq *hr_cq,
/* SQ conrespond to CQE */
sq_wqe = get_send_wqe(*cur_qp, roce_get_field(cqe->cqe_byte_4,
CQE_BYTE_4_WQE_INDEX_M,
- CQE_BYTE_4_WQE_INDEX_S));
+ CQE_BYTE_4_WQE_INDEX_S)&
+ ((*cur_qp)->sq.wqe_cnt-1));
switch (sq_wqe->flag & HNS_ROCE_WQE_OPCODE_MASK) {
case HNS_ROCE_WQE_OPCODE_SEND:
wc->opcode = IB_WC_SEND;
@@ -1591,10 +1659,8 @@ int hns_roce_v1_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
break;
}
- if (npolled) {
- hns_roce_v1_cq_set_ci(hr_cq, hr_cq->cons_index,
- &to_hr_dev(ibcq->device)->cq_db_lock);
- }
+ if (npolled)
+ hns_roce_v1_cq_set_ci(hr_cq, hr_cq->cons_index);
spin_unlock_irqrestore(&hr_cq->lock, flags);
@@ -1604,6 +1670,74 @@ int hns_roce_v1_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
return ret;
}
+int hns_roce_v1_clear_hem(struct hns_roce_dev *hr_dev,
+ struct hns_roce_hem_table *table, int obj)
+{
+ struct device *dev = &hr_dev->pdev->dev;
+ struct hns_roce_v1_priv *priv;
+ unsigned long end = 0, flags = 0;
+ uint32_t bt_cmd_val[2] = {0};
+ void __iomem *bt_cmd;
+ u64 bt_ba = 0;
+
+ priv = (struct hns_roce_v1_priv *)hr_dev->hw->priv;
+
+ switch (table->type) {
+ case HEM_TYPE_QPC:
+ roce_set_field(bt_cmd_val[1], ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_M,
+ ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_S, HEM_TYPE_QPC);
+ bt_ba = priv->bt_table.qpc_buf.map >> 12;
+ break;
+ case HEM_TYPE_MTPT:
+ roce_set_field(bt_cmd_val[1], ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_M,
+ ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_S, HEM_TYPE_MTPT);
+ bt_ba = priv->bt_table.mtpt_buf.map >> 12;
+ break;
+ case HEM_TYPE_CQC:
+ roce_set_field(bt_cmd_val[1], ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_M,
+ ROCEE_BT_CMD_H_ROCEE_BT_CMD_MDF_S, HEM_TYPE_CQC);
+ bt_ba = priv->bt_table.cqc_buf.map >> 12;
+ break;
+ case HEM_TYPE_SRQC:
+ dev_dbg(dev, "HEM_TYPE_SRQC not support.\n");
+ return -EINVAL;
+ default:
+ return 0;
+ }
+ roce_set_field(bt_cmd_val[1], ROCEE_BT_CMD_H_ROCEE_BT_CMD_IN_MDF_M,
+ ROCEE_BT_CMD_H_ROCEE_BT_CMD_IN_MDF_S, obj);
+ roce_set_bit(bt_cmd_val[1], ROCEE_BT_CMD_H_ROCEE_BT_CMD_S, 0);
+ roce_set_bit(bt_cmd_val[1], ROCEE_BT_CMD_H_ROCEE_BT_CMD_HW_SYNS_S, 1);
+
+ spin_lock_irqsave(&hr_dev->bt_cmd_lock, flags);
+
+ bt_cmd = hr_dev->reg_base + ROCEE_BT_CMD_H_REG;
+
+ end = msecs_to_jiffies(HW_SYNC_TIMEOUT_MSECS) + jiffies;
+ while (1) {
+ if (readl(bt_cmd) >> BT_CMD_SYNC_SHIFT) {
+ if (!(time_before(jiffies, end))) {
+ dev_err(dev, "Write bt_cmd err,hw_sync is not zero.\n");
+ spin_unlock_irqrestore(&hr_dev->bt_cmd_lock,
+ flags);
+ return -EBUSY;
+ }
+ } else {
+ break;
+ }
+ msleep(HW_SYNC_SLEEP_TIME_INTERVAL);
+ }
+
+ bt_cmd_val[0] = (uint32_t)bt_ba;
+ roce_set_field(bt_cmd_val[1], ROCEE_BT_CMD_H_ROCEE_BT_CMD_BA_H_M,
+ ROCEE_BT_CMD_H_ROCEE_BT_CMD_BA_H_S, bt_ba >> 32);
+ hns_roce_write64_k(bt_cmd_val, hr_dev->reg_base + ROCEE_BT_CMD_L_REG);
+
+ spin_unlock_irqrestore(&hr_dev->bt_cmd_lock, flags);
+
+ return 0;
+}
+
static int hns_roce_v1_qp_modify(struct hns_roce_dev *hr_dev,
struct hns_roce_mtt *mtt,
enum hns_roce_qp_state cur_state,
@@ -1733,13 +1867,10 @@ static int hns_roce_v1_m_sqp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
roce_set_field(context->qp1c_bytes_16, QP1C_BYTES_16_RQ_HEAD_M,
QP1C_BYTES_16_RQ_HEAD_S, hr_qp->rq.head);
roce_set_field(context->qp1c_bytes_16, QP1C_BYTES_16_PORT_NUM_M,
- QP1C_BYTES_16_PORT_NUM_S, hr_qp->port);
+ QP1C_BYTES_16_PORT_NUM_S, hr_qp->phy_port);
roce_set_bit(context->qp1c_bytes_16,
QP1C_BYTES_16_SIGNALING_TYPE_S,
hr_qp->sq_signal_bits);
- roce_set_bit(context->qp1c_bytes_16,
- QP1C_BYTES_16_LOCAL_ENABLE_E2E_CREDIT_S,
- hr_qp->sq_signal_bits);
roce_set_bit(context->qp1c_bytes_16, QP1C_BYTES_16_RQ_BA_FLG_S,
1);
roce_set_bit(context->qp1c_bytes_16, QP1C_BYTES_16_SQ_BA_FLG_S,
@@ -1784,7 +1915,7 @@ static int hns_roce_v1_m_sqp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
/* Copy context to QP1C register */
addr = (u32 *)(hr_dev->reg_base + ROCEE_QP1C_CFG0_0_REG +
- hr_qp->port * sizeof(*context));
+ hr_qp->phy_port * sizeof(*context));
writel(context->qp1c_bytes_4, addr);
writel(context->sq_rq_bt_l, addr + 1);
@@ -1795,15 +1926,16 @@ static int hns_roce_v1_m_sqp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
writel(context->qp1c_bytes_28, addr + 6);
writel(context->qp1c_bytes_32, addr + 7);
writel(context->cur_sq_wqe_ba_l, addr + 8);
+ writel(context->qp1c_bytes_40, addr + 9);
}
/* Modify QP1C status */
reg_val = roce_read(hr_dev, ROCEE_QP1C_CFG0_0_REG +
- hr_qp->port * sizeof(*context));
+ hr_qp->phy_port * sizeof(*context));
roce_set_field(reg_val, ROCEE_QP1C_CFG0_0_ROCEE_QP1C_QP_ST_M,
ROCEE_QP1C_CFG0_0_ROCEE_QP1C_QP_ST_S, new_state);
roce_write(hr_dev, ROCEE_QP1C_CFG0_0_REG +
- hr_qp->port * sizeof(*context), reg_val);
+ hr_qp->phy_port * sizeof(*context), reg_val);
hr_qp->state = new_state;
if (new_state == IB_QPS_RESET) {
@@ -1836,12 +1968,10 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
struct device *dev = &hr_dev->pdev->dev;
struct hns_roce_qp_context *context;
- struct hns_roce_rq_db rq_db;
dma_addr_t dma_handle_2 = 0;
dma_addr_t dma_handle = 0;
uint32_t doorbell[2] = {0};
int rq_pa_start = 0;
- u32 reg_val = 0;
u64 *mtts_2 = NULL;
int ret = -EINVAL;
u64 *mtts = NULL;
@@ -2119,7 +2249,8 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
roce_set_field(context->qpc_bytes_68,
QP_CONTEXT_QPC_BYTES_68_RQ_HEAD_M,
- QP_CONTEXT_QPC_BYTES_68_RQ_HEAD_S, 0);
+ QP_CONTEXT_QPC_BYTES_68_RQ_HEAD_S,
+ hr_qp->rq.head);
roce_set_field(context->qpc_bytes_68,
QP_CONTEXT_QPC_BYTES_68_RQ_CUR_INDEX_M,
QP_CONTEXT_QPC_BYTES_68_RQ_CUR_INDEX_S, 0);
@@ -2186,7 +2317,7 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
roce_set_field(context->qpc_bytes_156,
QP_CONTEXT_QPC_BYTES_156_PORT_NUM_M,
QP_CONTEXT_QPC_BYTES_156_PORT_NUM_S,
- hr_qp->port);
+ hr_qp->phy_port);
roce_set_field(context->qpc_bytes_156,
QP_CONTEXT_QPC_BYTES_156_SL_M,
QP_CONTEXT_QPC_BYTES_156_SL_S, attr->ah_attr.sl);
@@ -2257,20 +2388,17 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
roce_set_bit(context->qpc_bytes_140,
QP_CONTEXT_QPC_BYTES_140_RNR_RETRY_FLG_S, 0);
- roce_set_field(context->qpc_bytes_144,
- QP_CONTEXT_QPC_BYTES_144_QP_STATE_M,
- QP_CONTEXT_QPC_BYTES_144_QP_STATE_S,
- attr->qp_state);
-
roce_set_field(context->qpc_bytes_148,
QP_CONTEXT_QPC_BYTES_148_CHECK_FLAG_M,
QP_CONTEXT_QPC_BYTES_148_CHECK_FLAG_S, 0);
roce_set_field(context->qpc_bytes_148,
QP_CONTEXT_QPC_BYTES_148_RETRY_COUNT_M,
- QP_CONTEXT_QPC_BYTES_148_RETRY_COUNT_S, 0);
+ QP_CONTEXT_QPC_BYTES_148_RETRY_COUNT_S,
+ attr->retry_cnt);
roce_set_field(context->qpc_bytes_148,
QP_CONTEXT_QPC_BYTES_148_RNR_RETRY_COUNT_M,
- QP_CONTEXT_QPC_BYTES_148_RNR_RETRY_COUNT_S, 0);
+ QP_CONTEXT_QPC_BYTES_148_RNR_RETRY_COUNT_S,
+ attr->rnr_retry);
roce_set_field(context->qpc_bytes_148,
QP_CONTEXT_QPC_BYTES_148_LSN_M,
QP_CONTEXT_QPC_BYTES_148_LSN_S, 0x100);
@@ -2281,10 +2409,19 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
QP_CONTEXT_QPC_BYTES_156_RETRY_COUNT_INIT_M,
QP_CONTEXT_QPC_BYTES_156_RETRY_COUNT_INIT_S,
attr->retry_cnt);
- roce_set_field(context->qpc_bytes_156,
- QP_CONTEXT_QPC_BYTES_156_ACK_TIMEOUT_M,
- QP_CONTEXT_QPC_BYTES_156_ACK_TIMEOUT_S,
- attr->timeout);
+ if (attr->timeout < 0x12) {
+ dev_info(dev, "ack timeout value(0x%x) must bigger than 0x12.\n",
+ attr->timeout);
+ roce_set_field(context->qpc_bytes_156,
+ QP_CONTEXT_QPC_BYTES_156_ACK_TIMEOUT_M,
+ QP_CONTEXT_QPC_BYTES_156_ACK_TIMEOUT_S,
+ 0x12);
+ } else {
+ roce_set_field(context->qpc_bytes_156,
+ QP_CONTEXT_QPC_BYTES_156_ACK_TIMEOUT_M,
+ QP_CONTEXT_QPC_BYTES_156_ACK_TIMEOUT_S,
+ attr->timeout);
+ }
roce_set_field(context->qpc_bytes_156,
QP_CONTEXT_QPC_BYTES_156_RNR_RETRY_COUNT_INIT_M,
QP_CONTEXT_QPC_BYTES_156_RNR_RETRY_COUNT_INIT_S,
@@ -2292,7 +2429,7 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
roce_set_field(context->qpc_bytes_156,
QP_CONTEXT_QPC_BYTES_156_PORT_NUM_M,
QP_CONTEXT_QPC_BYTES_156_PORT_NUM_S,
- hr_qp->port);
+ hr_qp->phy_port);
roce_set_field(context->qpc_bytes_156,
QP_CONTEXT_QPC_BYTES_156_SL_M,
QP_CONTEXT_QPC_BYTES_156_SL_S, attr->ah_attr.sl);
@@ -2357,21 +2494,15 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
QP_CONTEXT_QPC_BYTES_188_TX_RETRY_CUR_INDEX_M,
QP_CONTEXT_QPC_BYTES_188_TX_RETRY_CUR_INDEX_S,
0);
- } else if ((cur_state == IB_QPS_INIT && new_state == IB_QPS_RESET) ||
+ } else if (!((cur_state == IB_QPS_INIT && new_state == IB_QPS_RESET) ||
(cur_state == IB_QPS_INIT && new_state == IB_QPS_ERR) ||
(cur_state == IB_QPS_RTR && new_state == IB_QPS_RESET) ||
(cur_state == IB_QPS_RTR && new_state == IB_QPS_ERR) ||
(cur_state == IB_QPS_RTS && new_state == IB_QPS_RESET) ||
(cur_state == IB_QPS_RTS && new_state == IB_QPS_ERR) ||
(cur_state == IB_QPS_ERR && new_state == IB_QPS_RESET) ||
- (cur_state == IB_QPS_ERR && new_state == IB_QPS_ERR)) {
- roce_set_field(context->qpc_bytes_144,
- QP_CONTEXT_QPC_BYTES_144_QP_STATE_M,
- QP_CONTEXT_QPC_BYTES_144_QP_STATE_S,
- attr->qp_state);
-
- } else {
- dev_err(dev, "not support this modify\n");
+ (cur_state == IB_QPS_ERR && new_state == IB_QPS_ERR))) {
+ dev_err(dev, "not support this status migration\n");
goto out;
}
@@ -2397,43 +2528,32 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
if (cur_state == IB_QPS_INIT && new_state == IB_QPS_INIT) {
/* Memory barrier */
wmb();
- if (hr_qp->ibqp.qp_type == IB_QPT_GSI) {
- /* SW update GSI rq header */
- reg_val = roce_read(hr_dev, ROCEE_QP1C_CFG3_0_REG +
- QP1C_CFGN_OFFSET * hr_qp->port);
- roce_set_field(reg_val,
- ROCEE_QP1C_CFG3_0_ROCEE_QP1C_RQ_HEAD_M,
- ROCEE_QP1C_CFG3_0_ROCEE_QP1C_RQ_HEAD_S,
- hr_qp->rq.head);
- roce_write(hr_dev, ROCEE_QP1C_CFG3_0_REG +
- QP1C_CFGN_OFFSET * hr_qp->port, reg_val);
- } else {
- rq_db.u32_4 = 0;
- rq_db.u32_8 = 0;
- roce_set_field(rq_db.u32_4, RQ_DOORBELL_U32_4_RQ_HEAD_M,
- RQ_DOORBELL_U32_4_RQ_HEAD_S,
- hr_qp->rq.head);
- roce_set_field(rq_db.u32_8, RQ_DOORBELL_U32_8_QPN_M,
- RQ_DOORBELL_U32_8_QPN_S, hr_qp->qpn);
- roce_set_field(rq_db.u32_8, RQ_DOORBELL_U32_8_CMD_M,
- RQ_DOORBELL_U32_8_CMD_S, 1);
- roce_set_bit(rq_db.u32_8, RQ_DOORBELL_U32_8_HW_SYNC_S,
- 1);
+ roce_set_field(doorbell[0], RQ_DOORBELL_U32_4_RQ_HEAD_M,
+ RQ_DOORBELL_U32_4_RQ_HEAD_S, hr_qp->rq.head);
+ roce_set_field(doorbell[1], RQ_DOORBELL_U32_8_QPN_M,
+ RQ_DOORBELL_U32_8_QPN_S, hr_qp->qpn);
+ roce_set_field(doorbell[1], RQ_DOORBELL_U32_8_CMD_M,
+ RQ_DOORBELL_U32_8_CMD_S, 1);
+ roce_set_bit(doorbell[1], RQ_DOORBELL_U32_8_HW_SYNC_S, 1);
- doorbell[0] = rq_db.u32_4;
- doorbell[1] = rq_db.u32_8;
-
- hns_roce_write64_k(doorbell, hr_qp->rq.db_reg_l);
+ if (ibqp->uobject) {
+ hr_qp->rq.db_reg_l = hr_dev->reg_base +
+ ROCEE_DB_OTHERS_L_0_REG +
+ DB_REG_OFFSET * hr_dev->priv_uar.index;
}
+
+ hns_roce_write64_k(doorbell, hr_qp->rq.db_reg_l);
}
hr_qp->state = new_state;
if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC)
hr_qp->resp_depth = attr->max_dest_rd_atomic;
- if (attr_mask & IB_QP_PORT)
- hr_qp->port = (attr->port_num - 1);
+ if (attr_mask & IB_QP_PORT) {
+ hr_qp->port = attr->port_num - 1;
+ hr_qp->phy_port = hr_dev->iboe.phy_port[hr_qp->port];
+ }
if (new_state == IB_QPS_RESET && !ibqp->uobject) {
hns_roce_v1_cq_clean(to_hr_cq(ibqp->recv_cq), hr_qp->qpn,
@@ -2789,6 +2909,7 @@ struct hns_roce_hw hns_roce_hw_v1 = {
.set_mtu = hns_roce_v1_set_mtu,
.write_mtpt = hns_roce_v1_write_mtpt,
.write_cqc = hns_roce_v1_write_cqc,
+ .clear_hem = hns_roce_v1_clear_hem,
.modify_qp = hns_roce_v1_modify_qp,
.query_qp = hns_roce_v1_query_qp,
.destroy_qp = hns_roce_v1_destroy_qp,
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.h b/drivers/infiniband/hw/hns/hns_roce_hw_v1.h
index 316b592..539b0a3b 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.h
@@ -102,6 +102,8 @@
#define HNS_ROCE_V1_EXT_ODB_ALFUL \
(HNS_ROCE_V1_EXT_ODB_DEPTH - HNS_ROCE_V1_DB_RSVD)
+#define HNS_ROCE_BT_RSV_BUF_SIZE (1 << 17)
+
#define HNS_ROCE_ODB_POLL_MODE 0
#define HNS_ROCE_SDB_NORMAL_MODE 0
@@ -971,9 +973,16 @@ struct hns_roce_db_table {
struct hns_roce_ext_db *ext_db;
};
+struct hns_roce_bt_table {
+ struct hns_roce_buf_list qpc_buf;
+ struct hns_roce_buf_list mtpt_buf;
+ struct hns_roce_buf_list cqc_buf;
+};
+
struct hns_roce_v1_priv {
struct hns_roce_db_table db_table;
struct hns_roce_raq_table raq_table;
+ struct hns_roce_bt_table bt_table;
};
int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset);
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index f64f0dd..764e35a 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -355,8 +355,7 @@ static int hns_roce_query_device(struct ib_device *ib_dev,
props->max_qp = hr_dev->caps.num_qps;
props->max_qp_wr = hr_dev->caps.max_wqes;
props->device_cap_flags = IB_DEVICE_PORT_ACTIVE_EVENT |
- IB_DEVICE_RC_RNR_NAK_GEN |
- IB_DEVICE_LOCAL_DMA_LKEY;
+ IB_DEVICE_RC_RNR_NAK_GEN;
props->max_sge = hr_dev->caps.max_sq_sg;
props->max_sge_rd = 1;
props->max_cq = hr_dev->caps.num_cqs;
@@ -372,6 +371,25 @@ static int hns_roce_query_device(struct ib_device *ib_dev,
return 0;
}
+static struct net_device *hns_roce_get_netdev(struct ib_device *ib_dev,
+ u8 port_num)
+{
+ struct hns_roce_dev *hr_dev = to_hr_dev(ib_dev);
+ struct net_device *ndev;
+
+ if (port_num < 1 || port_num > hr_dev->caps.num_ports)
+ return NULL;
+
+ rcu_read_lock();
+
+ ndev = hr_dev->iboe.netdevs[port_num - 1];
+ if (ndev)
+ dev_hold(ndev);
+
+ rcu_read_unlock();
+ return ndev;
+}
+
static int hns_roce_query_port(struct ib_device *ib_dev, u8 port_num,
struct ib_port_attr *props)
{
@@ -584,6 +602,7 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
struct device *dev = &hr_dev->pdev->dev;
iboe = &hr_dev->iboe;
+ spin_lock_init(&iboe->lock);
ib_dev = &hr_dev->ib_dev;
strlcpy(ib_dev->name, "hisi_%d", IB_DEVICE_NAME_MAX);
@@ -618,6 +637,7 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
ib_dev->query_port = hns_roce_query_port;
ib_dev->modify_port = hns_roce_modify_port;
ib_dev->get_link_layer = hns_roce_get_link_layer;
+ ib_dev->get_netdev = hns_roce_get_netdev;
ib_dev->query_gid = hns_roce_query_gid;
ib_dev->query_pkey = hns_roce_query_pkey;
ib_dev->alloc_ucontext = hns_roce_alloc_ucontext;
@@ -667,8 +687,6 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
goto error_failed_setup_mtu_gids;
}
- spin_lock_init(&iboe->lock);
-
iboe->nb.notifier_call = hns_roce_netdev_event;
ret = register_netdevice_notifier(&iboe->nb);
if (ret) {
@@ -777,6 +795,15 @@ static int hns_roce_get_cfg(struct hns_roce_dev *hr_dev)
if (IS_ERR(hr_dev->reg_base))
return PTR_ERR(hr_dev->reg_base);
+ /* read the node_guid of IB device from the DT or ACPI */
+ ret = device_property_read_u8_array(dev, "node-guid",
+ (u8 *)&hr_dev->ib_dev.node_guid,
+ GUID_LEN);
+ if (ret) {
+ dev_err(dev, "couldn't get node_guid from DT or ACPI!\n");
+ return ret;
+ }
+
/* get the RoCE associated ethernet ports or netdevices */
for (i = 0; i < HNS_ROCE_MAX_PORTS; i++) {
if (dev_of_node(dev)) {
@@ -923,7 +950,6 @@ static int hns_roce_setup_hca(struct hns_roce_dev *hr_dev)
struct device *dev = &hr_dev->pdev->dev;
spin_lock_init(&hr_dev->sm_lock);
- spin_lock_init(&hr_dev->cq_db_lock);
spin_lock_init(&hr_dev->bt_cmd_lock);
ret = hns_roce_init_uar_table(hr_dev);
diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c
index 59f5e2b..fb87883 100644
--- a/drivers/infiniband/hw/hns/hns_roce_mr.c
+++ b/drivers/infiniband/hw/hns/hns_roce_mr.c
@@ -564,11 +564,14 @@ struct ib_mr *hns_roce_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
if (mr->umem->page_size != HNS_ROCE_HEM_PAGE_SIZE) {
dev_err(dev, "Just support 4K page size but is 0x%x now!\n",
mr->umem->page_size);
+ ret = -EINVAL;
+ goto err_umem;
}
if (n > HNS_ROCE_MAX_MTPT_PBL_NUM) {
dev_err(dev, " MR len %lld err. MR is limited to 4G at most!\n",
length);
+ ret = -EINVAL;
goto err_umem;
}
diff --git a/drivers/infiniband/hw/hns/hns_roce_pd.c b/drivers/infiniband/hw/hns/hns_roce_pd.c
index 16271b5..05db7d5 100644
--- a/drivers/infiniband/hw/hns/hns_roce_pd.c
+++ b/drivers/infiniband/hw/hns/hns_roce_pd.c
@@ -35,19 +35,7 @@
static int hns_roce_pd_alloc(struct hns_roce_dev *hr_dev, unsigned long *pdn)
{
- struct device *dev = &hr_dev->pdev->dev;
- unsigned long pd_number;
- int ret = 0;
-
- ret = hns_roce_bitmap_alloc(&hr_dev->pd_bitmap, &pd_number);
- if (ret == -1) {
- dev_err(dev, "alloc pdn from pdbitmap failed\n");
- return -ENOMEM;
- }
-
- *pdn = pd_number;
-
- return 0;
+ return hns_roce_bitmap_alloc(&hr_dev->pd_bitmap, pdn);
}
static void hns_roce_pd_free(struct hns_roce_dev *hr_dev, unsigned long pdn)
@@ -117,9 +105,15 @@ int hns_roce_uar_alloc(struct hns_roce_dev *hr_dev, struct hns_roce_uar *uar)
if (ret == -1)
return -ENOMEM;
- uar->index = (uar->index - 1) % hr_dev->caps.phy_num_uars + 1;
+ if (uar->index > 0)
+ uar->index = (uar->index - 1) %
+ (hr_dev->caps.phy_num_uars - 1) + 1;
res = platform_get_resource(hr_dev->pdev, IORESOURCE_MEM, 0);
+ if (!res) {
+ dev_err(&hr_dev->pdev->dev, "memory resource not found!\n");
+ return -EINVAL;
+ }
uar->pfn = ((res->start) >> PAGE_SHIFT) + uar->index;
return 0;
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index 645c18d..e86dd8d 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -32,14 +32,14 @@
*/
#include <linux/platform_device.h>
+#include <rdma/ib_addr.h>
#include <rdma/ib_umem.h>
#include "hns_roce_common.h"
#include "hns_roce_device.h"
#include "hns_roce_hem.h"
#include "hns_roce_user.h"
-#define DB_REG_OFFSET 0x1000
-#define SQP_NUM 12
+#define SQP_NUM (2 * HNS_ROCE_MAX_PORTS)
void hns_roce_qp_event(struct hns_roce_dev *hr_dev, u32 qpn, int event_type)
{
@@ -113,16 +113,8 @@ static int hns_roce_reserve_range_qp(struct hns_roce_dev *hr_dev, int cnt,
int align, unsigned long *base)
{
struct hns_roce_qp_table *qp_table = &hr_dev->qp_table;
- int ret = 0;
- unsigned long qpn;
- ret = hns_roce_bitmap_alloc_range(&qp_table->bitmap, cnt, align, &qpn);
- if (ret == -1)
- return -ENOMEM;
-
- *base = qpn;
-
- return 0;
+ return hns_roce_bitmap_alloc_range(&qp_table->bitmap, cnt, align, base);
}
enum hns_roce_qp_state to_hns_roce_state(enum ib_qp_state state)
@@ -255,7 +247,7 @@ void hns_roce_release_range_qp(struct hns_roce_dev *hr_dev, int base_qpn,
{
struct hns_roce_qp_table *qp_table = &hr_dev->qp_table;
- if (base_qpn < (hr_dev->caps.sqp_start + 2 * hr_dev->caps.num_ports))
+ if (base_qpn < SQP_NUM)
return;
hns_roce_bitmap_free_range(&qp_table->bitmap, base_qpn, cnt);
@@ -345,12 +337,10 @@ static int hns_roce_set_user_sq_size(struct hns_roce_dev *hr_dev,
static int hns_roce_set_kernel_sq_size(struct hns_roce_dev *hr_dev,
struct ib_qp_cap *cap,
- enum ib_qp_type type,
struct hns_roce_qp *hr_qp)
{
struct device *dev = &hr_dev->pdev->dev;
u32 max_cnt;
- (void)type;
if (cap->max_send_wr > hr_dev->caps.max_wqes ||
cap->max_send_sge > hr_dev->caps.max_sq_sg ||
@@ -476,7 +466,7 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev,
/* Set SQ size */
ret = hns_roce_set_kernel_sq_size(hr_dev, &init_attr->cap,
- init_attr->qp_type, hr_qp);
+ hr_qp);
if (ret) {
dev_err(dev, "hns_roce_set_kernel_sq_size error!\n");
goto err_out;
@@ -617,21 +607,19 @@ struct ib_qp *hns_roce_create_qp(struct ib_pd *pd,
return ERR_PTR(-ENOMEM);
hr_qp = &hr_sqp->hr_qp;
+ hr_qp->port = init_attr->port_num - 1;
+ hr_qp->phy_port = hr_dev->iboe.phy_port[hr_qp->port];
+ hr_qp->ibqp.qp_num = HNS_ROCE_MAX_PORTS +
+ hr_dev->iboe.phy_port[hr_qp->port];
ret = hns_roce_create_qp_common(hr_dev, pd, init_attr, udata,
- hr_dev->caps.sqp_start +
- hr_dev->caps.num_ports +
- init_attr->port_num - 1, hr_qp);
+ hr_qp->ibqp.qp_num, hr_qp);
if (ret) {
dev_err(dev, "Create GSI QP failed!\n");
kfree(hr_sqp);
return ERR_PTR(ret);
}
- hr_qp->port = (init_attr->port_num - 1);
- hr_qp->ibqp.qp_num = hr_dev->caps.sqp_start +
- hr_dev->caps.num_ports +
- init_attr->port_num - 1;
break;
}
default:{
@@ -670,6 +658,7 @@ int hns_roce_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
struct device *dev = &hr_dev->pdev->dev;
int ret = -EINVAL;
int p;
+ enum ib_mtu active_mtu;
mutex_lock(&hr_qp->mutex);
@@ -700,6 +689,19 @@ int hns_roce_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
}
}
+ if (attr_mask & IB_QP_PATH_MTU) {
+ p = attr_mask & IB_QP_PORT ? (attr->port_num - 1) : hr_qp->port;
+ active_mtu = iboe_get_mtu(hr_dev->iboe.netdevs[p]->mtu);
+
+ if (attr->path_mtu > IB_MTU_2048 ||
+ attr->path_mtu < IB_MTU_256 ||
+ attr->path_mtu > active_mtu) {
+ dev_err(dev, "attr path_mtu(%d)invalid while modify qp",
+ attr->path_mtu);
+ goto out;
+ }
+ }
+
if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC &&
attr->max_rd_atomic > hr_dev->caps.max_qp_init_rdma) {
dev_err(dev, "attr max_rd_atomic invalid.attr->max_rd_atomic=%d\n",
@@ -782,29 +784,11 @@ static void *get_wqe(struct hns_roce_qp *hr_qp, int offset)
void *get_recv_wqe(struct hns_roce_qp *hr_qp, int n)
{
- struct ib_qp *ibqp = &hr_qp->ibqp;
- struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
-
- if ((n < 0) || (n > hr_qp->rq.wqe_cnt)) {
- dev_err(&hr_dev->pdev->dev, "rq wqe index:%d,rq wqe cnt:%d\r\n",
- n, hr_qp->rq.wqe_cnt);
- return NULL;
- }
-
return get_wqe(hr_qp, hr_qp->rq.offset + (n << hr_qp->rq.wqe_shift));
}
void *get_send_wqe(struct hns_roce_qp *hr_qp, int n)
{
- struct ib_qp *ibqp = &hr_qp->ibqp;
- struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
-
- if ((n < 0) || (n > hr_qp->sq.wqe_cnt)) {
- dev_err(&hr_dev->pdev->dev, "sq wqe index:%d,sq wqe cnt:%d\r\n",
- n, hr_qp->sq.wqe_cnt);
- return NULL;
- }
-
return get_wqe(hr_qp, hr_qp->sq.offset + (n << hr_qp->sq.wqe_shift));
}
@@ -837,8 +821,7 @@ int hns_roce_init_qp_table(struct hns_roce_dev *hr_dev)
/* A port include two SQP, six port total 12 */
ret = hns_roce_bitmap_init(&qp_table->bitmap, hr_dev->caps.num_qps,
- hr_dev->caps.num_qps - 1,
- hr_dev->caps.sqp_start + SQP_NUM,
+ hr_dev->caps.num_qps - 1, SQP_NUM,
reserved_from_top);
if (ret) {
dev_err(&hr_dev->pdev->dev, "qp bitmap init failed!error=%d\n",
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 2217477..76ed57f 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1019,7 +1019,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
resp.qp_tab_size = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp);
if (mlx5_core_is_pf(dev->mdev) && MLX5_CAP_GEN(dev->mdev, bf))
resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size);
- resp.cache_line_size = L1_CACHE_BYTES;
+ resp.cache_line_size = cache_line_size();
resp.max_sq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq);
resp.max_rq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq);
resp.max_send_wqebb = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz);
@@ -1771,13 +1771,13 @@ static int mlx5_ib_destroy_flow(struct ib_flow *flow_id)
mutex_lock(&dev->flow_db.lock);
list_for_each_entry_safe(iter, tmp, &handler->list, list) {
- mlx5_del_flow_rule(iter->rule);
+ mlx5_del_flow_rules(iter->rule);
put_flow_table(dev, iter->prio, true);
list_del(&iter->list);
kfree(iter);
}
- mlx5_del_flow_rule(handler->rule);
+ mlx5_del_flow_rules(handler->rule);
put_flow_table(dev, handler->prio, true);
mutex_unlock(&dev->flow_db.lock);
@@ -1857,7 +1857,7 @@ static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev,
ft = mlx5_create_auto_grouped_flow_table(ns, priority,
num_entries,
num_groups,
- 0);
+ 0, 0);
if (!IS_ERR(ft)) {
prio->refcount = 0;
@@ -1877,10 +1877,10 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
{
struct mlx5_flow_table *ft = ft_prio->flow_table;
struct mlx5_ib_flow_handler *handler;
+ struct mlx5_flow_act flow_act = {0};
struct mlx5_flow_spec *spec;
const void *ib_flow = (const void *)flow_attr + sizeof(*flow_attr);
unsigned int spec_index;
- u32 action;
int err = 0;
if (!is_valid_attr(flow_attr))
@@ -1905,12 +1905,12 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
}
spec->match_criteria_enable = get_match_criteria_enable(spec->match_criteria);
- action = dst ? MLX5_FLOW_CONTEXT_ACTION_FWD_DEST :
+ flow_act.action = dst ? MLX5_FLOW_CONTEXT_ACTION_FWD_DEST :
MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
- handler->rule = mlx5_add_flow_rule(ft, spec,
- action,
- MLX5_FS_DEFAULT_FLOW_TAG,
- dst);
+ flow_act.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
+ handler->rule = mlx5_add_flow_rules(ft, spec,
+ &flow_act,
+ dst, 1);
if (IS_ERR(handler->rule)) {
err = PTR_ERR(handler->rule);
@@ -1941,7 +1941,7 @@ static struct mlx5_ib_flow_handler *create_dont_trap_rule(struct mlx5_ib_dev *de
handler_dst = create_flow_rule(dev, ft_prio,
flow_attr, dst);
if (IS_ERR(handler_dst)) {
- mlx5_del_flow_rule(handler->rule);
+ mlx5_del_flow_rules(handler->rule);
ft_prio->refcount--;
kfree(handler);
handler = handler_dst;
@@ -2004,7 +2004,7 @@ static struct mlx5_ib_flow_handler *create_leftovers_rule(struct mlx5_ib_dev *de
&leftovers_specs[LEFTOVERS_UC].flow_attr,
dst);
if (IS_ERR(handler_ucast)) {
- mlx5_del_flow_rule(handler->rule);
+ mlx5_del_flow_rules(handler->rule);
ft_prio->refcount--;
kfree(handler);
handler = handler_ucast;
@@ -2046,7 +2046,7 @@ static struct mlx5_ib_flow_handler *create_sniffer_rule(struct mlx5_ib_dev *dev,
return handler_rx;
err_tx:
- mlx5_del_flow_rule(handler_rx->rule);
+ mlx5_del_flow_rules(handler_rx->rule);
ft_rx->refcount--;
kfree(handler_rx);
err:
@@ -2358,6 +2358,8 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
ibev.event = IB_EVENT_CLIENT_REREGISTER;
port = (u8)param;
break;
+ default:
+ return;
}
ibev.device = &ibdev->ib_dev;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index dcdcd19..d5d0077 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -153,7 +153,7 @@ struct mlx5_ib_flow_handler {
struct list_head list;
struct ib_flow ibflow;
struct mlx5_ib_flow_prio *prio;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
};
struct mlx5_ib_flow_db {
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 41f4c2a..7ce97da 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -52,7 +52,6 @@ enum {
enum {
MLX5_IB_SQ_STRIDE = 6,
- MLX5_IB_CACHE_LINE_SIZE = 64,
};
static const u32 mlx5_ib_opcode[] = {
diff --git a/drivers/infiniband/hw/mthca/mthca_memfree.c b/drivers/infiniband/hw/mthca/mthca_memfree.c
index 6c00d04..c6fe89d 100644
--- a/drivers/infiniband/hw/mthca/mthca_memfree.c
+++ b/drivers/infiniband/hw/mthca/mthca_memfree.c
@@ -472,7 +472,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,
goto out;
}
- ret = get_user_pages(uaddr & PAGE_MASK, 1, 1, 0, pages, NULL);
+ ret = get_user_pages(uaddr & PAGE_MASK, 1, FOLL_WRITE, pages, NULL);
if (ret < 0)
goto out;
diff --git a/drivers/infiniband/hw/qedr/Kconfig b/drivers/infiniband/hw/qedr/Kconfig
new file mode 100644
index 0000000..6c9f392
--- /dev/null
+++ b/drivers/infiniband/hw/qedr/Kconfig
@@ -0,0 +1,8 @@
+config INFINIBAND_QEDR
+ tristate "QLogic RoCE driver"
+ depends on 64BIT && QEDE
+ select QED_LL2
+ select QED_RDMA
+ ---help---
+ This driver provides low-level InfiniBand over Ethernet
+ support for QLogic QED host channel adapters (HCAs).
diff --git a/drivers/infiniband/hw/qedr/Makefile b/drivers/infiniband/hw/qedr/Makefile
new file mode 100644
index 0000000..ba7067c
--- /dev/null
+++ b/drivers/infiniband/hw/qedr/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_INFINIBAND_QEDR) := qedr.o
+
+qedr-y := main.o verbs.o qedr_cm.o
diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
new file mode 100644
index 0000000..7b74d09
--- /dev/null
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -0,0 +1,914 @@
+/* QLogic qedr NIC Driver
+ * Copyright (c) 2015-2016 QLogic Corporation
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and /or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#include <linux/module.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_addr.h>
+#include <rdma/ib_user_verbs.h>
+#include <linux/netdevice.h>
+#include <linux/iommu.h>
+#include <net/addrconf.h>
+#include <linux/qed/qede_roce.h>
+#include <linux/qed/qed_chain.h>
+#include <linux/qed/qed_if.h>
+#include "qedr.h"
+#include "verbs.h"
+#include <rdma/qedr-abi.h>
+
+MODULE_DESCRIPTION("QLogic 40G/100G ROCE Driver");
+MODULE_AUTHOR("QLogic Corporation");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION(QEDR_MODULE_VERSION);
+
+#define QEDR_WQ_MULTIPLIER_DFT (3)
+
+void qedr_ib_dispatch_event(struct qedr_dev *dev, u8 port_num,
+ enum ib_event_type type)
+{
+ struct ib_event ibev;
+
+ ibev.device = &dev->ibdev;
+ ibev.element.port_num = port_num;
+ ibev.event = type;
+
+ ib_dispatch_event(&ibev);
+}
+
+static enum rdma_link_layer qedr_link_layer(struct ib_device *device,
+ u8 port_num)
+{
+ return IB_LINK_LAYER_ETHERNET;
+}
+
+static void qedr_get_dev_fw_str(struct ib_device *ibdev, char *str,
+ size_t str_len)
+{
+ struct qedr_dev *qedr = get_qedr_dev(ibdev);
+ u32 fw_ver = (u32)qedr->attr.fw_ver;
+
+ snprintf(str, str_len, "%d. %d. %d. %d",
+ (fw_ver >> 24) & 0xFF, (fw_ver >> 16) & 0xFF,
+ (fw_ver >> 8) & 0xFF, fw_ver & 0xFF);
+}
+
+static struct net_device *qedr_get_netdev(struct ib_device *dev, u8 port_num)
+{
+ struct qedr_dev *qdev;
+
+ qdev = get_qedr_dev(dev);
+ dev_hold(qdev->ndev);
+
+ /* The HW vendor's device driver must guarantee
+ * that this function returns NULL before the net device reaches
+ * NETDEV_UNREGISTER_FINAL state.
+ */
+ return qdev->ndev;
+}
+
+static int qedr_register_device(struct qedr_dev *dev)
+{
+ strlcpy(dev->ibdev.name, "qedr%d", IB_DEVICE_NAME_MAX);
+
+ dev->ibdev.node_guid = dev->attr.node_guid;
+ memcpy(dev->ibdev.node_desc, QEDR_NODE_DESC, sizeof(QEDR_NODE_DESC));
+ dev->ibdev.owner = THIS_MODULE;
+ dev->ibdev.uverbs_abi_ver = QEDR_ABI_VERSION;
+
+ dev->ibdev.uverbs_cmd_mask = QEDR_UVERBS(GET_CONTEXT) |
+ QEDR_UVERBS(QUERY_DEVICE) |
+ QEDR_UVERBS(QUERY_PORT) |
+ QEDR_UVERBS(ALLOC_PD) |
+ QEDR_UVERBS(DEALLOC_PD) |
+ QEDR_UVERBS(CREATE_COMP_CHANNEL) |
+ QEDR_UVERBS(CREATE_CQ) |
+ QEDR_UVERBS(RESIZE_CQ) |
+ QEDR_UVERBS(DESTROY_CQ) |
+ QEDR_UVERBS(REQ_NOTIFY_CQ) |
+ QEDR_UVERBS(CREATE_QP) |
+ QEDR_UVERBS(MODIFY_QP) |
+ QEDR_UVERBS(QUERY_QP) |
+ QEDR_UVERBS(DESTROY_QP) |
+ QEDR_UVERBS(REG_MR) |
+ QEDR_UVERBS(DEREG_MR) |
+ QEDR_UVERBS(POLL_CQ) |
+ QEDR_UVERBS(POST_SEND) |
+ QEDR_UVERBS(POST_RECV);
+
+ dev->ibdev.phys_port_cnt = 1;
+ dev->ibdev.num_comp_vectors = dev->num_cnq;
+ dev->ibdev.node_type = RDMA_NODE_IB_CA;
+
+ dev->ibdev.query_device = qedr_query_device;
+ dev->ibdev.query_port = qedr_query_port;
+ dev->ibdev.modify_port = qedr_modify_port;
+
+ dev->ibdev.query_gid = qedr_query_gid;
+ dev->ibdev.add_gid = qedr_add_gid;
+ dev->ibdev.del_gid = qedr_del_gid;
+
+ dev->ibdev.alloc_ucontext = qedr_alloc_ucontext;
+ dev->ibdev.dealloc_ucontext = qedr_dealloc_ucontext;
+ dev->ibdev.mmap = qedr_mmap;
+
+ dev->ibdev.alloc_pd = qedr_alloc_pd;
+ dev->ibdev.dealloc_pd = qedr_dealloc_pd;
+
+ dev->ibdev.create_cq = qedr_create_cq;
+ dev->ibdev.destroy_cq = qedr_destroy_cq;
+ dev->ibdev.resize_cq = qedr_resize_cq;
+ dev->ibdev.req_notify_cq = qedr_arm_cq;
+
+ dev->ibdev.create_qp = qedr_create_qp;
+ dev->ibdev.modify_qp = qedr_modify_qp;
+ dev->ibdev.query_qp = qedr_query_qp;
+ dev->ibdev.destroy_qp = qedr_destroy_qp;
+
+ dev->ibdev.query_pkey = qedr_query_pkey;
+
+ dev->ibdev.create_ah = qedr_create_ah;
+ dev->ibdev.destroy_ah = qedr_destroy_ah;
+
+ dev->ibdev.get_dma_mr = qedr_get_dma_mr;
+ dev->ibdev.dereg_mr = qedr_dereg_mr;
+ dev->ibdev.reg_user_mr = qedr_reg_user_mr;
+ dev->ibdev.alloc_mr = qedr_alloc_mr;
+ dev->ibdev.map_mr_sg = qedr_map_mr_sg;
+
+ dev->ibdev.poll_cq = qedr_poll_cq;
+ dev->ibdev.post_send = qedr_post_send;
+ dev->ibdev.post_recv = qedr_post_recv;
+
+ dev->ibdev.process_mad = qedr_process_mad;
+ dev->ibdev.get_port_immutable = qedr_port_immutable;
+ dev->ibdev.get_netdev = qedr_get_netdev;
+
+ dev->ibdev.dma_device = &dev->pdev->dev;
+
+ dev->ibdev.get_link_layer = qedr_link_layer;
+ dev->ibdev.get_dev_fw_str = qedr_get_dev_fw_str;
+
+ return ib_register_device(&dev->ibdev, NULL);
+}
+
+/* This function allocates fast-path status block memory */
+static int qedr_alloc_mem_sb(struct qedr_dev *dev,
+ struct qed_sb_info *sb_info, u16 sb_id)
+{
+ struct status_block *sb_virt;
+ dma_addr_t sb_phys;
+ int rc;
+
+ sb_virt = dma_alloc_coherent(&dev->pdev->dev,
+ sizeof(*sb_virt), &sb_phys, GFP_KERNEL);
+ if (!sb_virt)
+ return -ENOMEM;
+
+ rc = dev->ops->common->sb_init(dev->cdev, sb_info,
+ sb_virt, sb_phys, sb_id,
+ QED_SB_TYPE_CNQ);
+ if (rc) {
+ pr_err("Status block initialization failed\n");
+ dma_free_coherent(&dev->pdev->dev, sizeof(*sb_virt),
+ sb_virt, sb_phys);
+ return rc;
+ }
+
+ return 0;
+}
+
+static void qedr_free_mem_sb(struct qedr_dev *dev,
+ struct qed_sb_info *sb_info, int sb_id)
+{
+ if (sb_info->sb_virt) {
+ dev->ops->common->sb_release(dev->cdev, sb_info, sb_id);
+ dma_free_coherent(&dev->pdev->dev, sizeof(*sb_info->sb_virt),
+ (void *)sb_info->sb_virt, sb_info->sb_phys);
+ }
+}
+
+static void qedr_free_resources(struct qedr_dev *dev)
+{
+ int i;
+
+ for (i = 0; i < dev->num_cnq; i++) {
+ qedr_free_mem_sb(dev, &dev->sb_array[i], dev->sb_start + i);
+ dev->ops->common->chain_free(dev->cdev, &dev->cnq_array[i].pbl);
+ }
+
+ kfree(dev->cnq_array);
+ kfree(dev->sb_array);
+ kfree(dev->sgid_tbl);
+}
+
+static int qedr_alloc_resources(struct qedr_dev *dev)
+{
+ struct qedr_cnq *cnq;
+ __le16 *cons_pi;
+ u16 n_entries;
+ int i, rc;
+
+ dev->sgid_tbl = kzalloc(sizeof(union ib_gid) *
+ QEDR_MAX_SGID, GFP_KERNEL);
+ if (!dev->sgid_tbl)
+ return -ENOMEM;
+
+ spin_lock_init(&dev->sgid_lock);
+
+ /* Allocate Status blocks for CNQ */
+ dev->sb_array = kcalloc(dev->num_cnq, sizeof(*dev->sb_array),
+ GFP_KERNEL);
+ if (!dev->sb_array) {
+ rc = -ENOMEM;
+ goto err1;
+ }
+
+ dev->cnq_array = kcalloc(dev->num_cnq,
+ sizeof(*dev->cnq_array), GFP_KERNEL);
+ if (!dev->cnq_array) {
+ rc = -ENOMEM;
+ goto err2;
+ }
+
+ dev->sb_start = dev->ops->rdma_get_start_sb(dev->cdev);
+
+ /* Allocate CNQ PBLs */
+ n_entries = min_t(u32, QED_RDMA_MAX_CNQ_SIZE, QEDR_ROCE_MAX_CNQ_SIZE);
+ for (i = 0; i < dev->num_cnq; i++) {
+ cnq = &dev->cnq_array[i];
+
+ rc = qedr_alloc_mem_sb(dev, &dev->sb_array[i],
+ dev->sb_start + i);
+ if (rc)
+ goto err3;
+
+ rc = dev->ops->common->chain_alloc(dev->cdev,
+ QED_CHAIN_USE_TO_CONSUME,
+ QED_CHAIN_MODE_PBL,
+ QED_CHAIN_CNT_TYPE_U16,
+ n_entries,
+ sizeof(struct regpair *),
+ &cnq->pbl);
+ if (rc)
+ goto err4;
+
+ cnq->dev = dev;
+ cnq->sb = &dev->sb_array[i];
+ cons_pi = dev->sb_array[i].sb_virt->pi_array;
+ cnq->hw_cons_ptr = &cons_pi[QED_ROCE_PROTOCOL_INDEX];
+ cnq->index = i;
+ sprintf(cnq->name, "qedr%d@pci:%s", i, pci_name(dev->pdev));
+
+ DP_DEBUG(dev, QEDR_MSG_INIT, "cnq[%d].cons=%d\n",
+ i, qed_chain_get_cons_idx(&cnq->pbl));
+ }
+
+ return 0;
+err4:
+ qedr_free_mem_sb(dev, &dev->sb_array[i], dev->sb_start + i);
+err3:
+ for (--i; i >= 0; i--) {
+ dev->ops->common->chain_free(dev->cdev, &dev->cnq_array[i].pbl);
+ qedr_free_mem_sb(dev, &dev->sb_array[i], dev->sb_start + i);
+ }
+ kfree(dev->cnq_array);
+err2:
+ kfree(dev->sb_array);
+err1:
+ kfree(dev->sgid_tbl);
+ return rc;
+}
+
+/* QEDR sysfs interface */
+static ssize_t show_rev(struct device *device, struct device_attribute *attr,
+ char *buf)
+{
+ struct qedr_dev *dev = dev_get_drvdata(device);
+
+ return scnprintf(buf, PAGE_SIZE, "0x%x\n", dev->pdev->vendor);
+}
+
+static ssize_t show_hca_type(struct device *device,
+ struct device_attribute *attr, char *buf)
+{
+ return scnprintf(buf, PAGE_SIZE, "%s\n", "HCA_TYPE_TO_SET");
+}
+
+static DEVICE_ATTR(hw_rev, S_IRUGO, show_rev, NULL);
+static DEVICE_ATTR(hca_type, S_IRUGO, show_hca_type, NULL);
+
+static struct device_attribute *qedr_attributes[] = {
+ &dev_attr_hw_rev,
+ &dev_attr_hca_type
+};
+
+static void qedr_remove_sysfiles(struct qedr_dev *dev)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(qedr_attributes); i++)
+ device_remove_file(&dev->ibdev.dev, qedr_attributes[i]);
+}
+
+static void qedr_pci_set_atomic(struct qedr_dev *dev, struct pci_dev *pdev)
+{
+ struct pci_dev *bridge;
+ u32 val;
+
+ dev->atomic_cap = IB_ATOMIC_NONE;
+
+ bridge = pdev->bus->self;
+ if (!bridge)
+ return;
+
+ /* Check whether we are connected directly or via a switch */
+ while (bridge && bridge->bus->parent) {
+ DP_DEBUG(dev, QEDR_MSG_INIT,
+ "Device is not connected directly to root. bridge->bus->number=%d primary=%d\n",
+ bridge->bus->number, bridge->bus->primary);
+ /* Need to check Atomic Op Routing Supported all the way to
+ * root complex.
+ */
+ pcie_capability_read_dword(bridge, PCI_EXP_DEVCAP2, &val);
+ if (!(val & PCI_EXP_DEVCAP2_ATOMIC_ROUTE)) {
+ pcie_capability_clear_word(pdev,
+ PCI_EXP_DEVCTL2,
+ PCI_EXP_DEVCTL2_ATOMIC_REQ);
+ return;
+ }
+ bridge = bridge->bus->parent->self;
+ }
+ bridge = pdev->bus->self;
+
+ /* according to bridge capability */
+ pcie_capability_read_dword(bridge, PCI_EXP_DEVCAP2, &val);
+ if (val & PCI_EXP_DEVCAP2_ATOMIC_COMP64) {
+ pcie_capability_set_word(pdev, PCI_EXP_DEVCTL2,
+ PCI_EXP_DEVCTL2_ATOMIC_REQ);
+ dev->atomic_cap = IB_ATOMIC_GLOB;
+ } else {
+ pcie_capability_clear_word(pdev, PCI_EXP_DEVCTL2,
+ PCI_EXP_DEVCTL2_ATOMIC_REQ);
+ }
+}
+
+static const struct qed_rdma_ops *qed_ops;
+
+#define HILO_U64(hi, lo) ((((u64)(hi)) << 32) + (lo))
+
+static irqreturn_t qedr_irq_handler(int irq, void *handle)
+{
+ u16 hw_comp_cons, sw_comp_cons;
+ struct qedr_cnq *cnq = handle;
+ struct regpair *cq_handle;
+ struct qedr_cq *cq;
+
+ qed_sb_ack(cnq->sb, IGU_INT_DISABLE, 0);
+
+ qed_sb_update_sb_idx(cnq->sb);
+
+ hw_comp_cons = le16_to_cpu(*cnq->hw_cons_ptr);
+ sw_comp_cons = qed_chain_get_cons_idx(&cnq->pbl);
+
+ /* Align protocol-index and chain reads */
+ rmb();
+
+ while (sw_comp_cons != hw_comp_cons) {
+ cq_handle = (struct regpair *)qed_chain_consume(&cnq->pbl);
+ cq = (struct qedr_cq *)(uintptr_t)HILO_U64(cq_handle->hi,
+ cq_handle->lo);
+
+ if (cq == NULL) {
+ DP_ERR(cnq->dev,
+ "Received NULL CQ cq_handle->hi=%d cq_handle->lo=%d sw_comp_cons=%d hw_comp_cons=%d\n",
+ cq_handle->hi, cq_handle->lo, sw_comp_cons,
+ hw_comp_cons);
+
+ break;
+ }
+
+ if (cq->sig != QEDR_CQ_MAGIC_NUMBER) {
+ DP_ERR(cnq->dev,
+ "Problem with cq signature, cq_handle->hi=%d ch_handle->lo=%d cq=%p\n",
+ cq_handle->hi, cq_handle->lo, cq);
+ break;
+ }
+
+ cq->arm_flags = 0;
+
+ if (cq->ibcq.comp_handler)
+ (*cq->ibcq.comp_handler)
+ (&cq->ibcq, cq->ibcq.cq_context);
+
+ sw_comp_cons = qed_chain_get_cons_idx(&cnq->pbl);
+
+ cnq->n_comp++;
+
+ }
+
+ qed_ops->rdma_cnq_prod_update(cnq->dev->rdma_ctx, cnq->index,
+ sw_comp_cons);
+
+ qed_sb_ack(cnq->sb, IGU_INT_ENABLE, 1);
+
+ return IRQ_HANDLED;
+}
+
+static void qedr_sync_free_irqs(struct qedr_dev *dev)
+{
+ u32 vector;
+ int i;
+
+ for (i = 0; i < dev->int_info.used_cnt; i++) {
+ if (dev->int_info.msix_cnt) {
+ vector = dev->int_info.msix[i * dev->num_hwfns].vector;
+ synchronize_irq(vector);
+ free_irq(vector, &dev->cnq_array[i]);
+ }
+ }
+
+ dev->int_info.used_cnt = 0;
+}
+
+static int qedr_req_msix_irqs(struct qedr_dev *dev)
+{
+ int i, rc = 0;
+
+ if (dev->num_cnq > dev->int_info.msix_cnt) {
+ DP_ERR(dev,
+ "Interrupt mismatch: %d CNQ queues > %d MSI-x vectors\n",
+ dev->num_cnq, dev->int_info.msix_cnt);
+ return -EINVAL;
+ }
+
+ for (i = 0; i < dev->num_cnq; i++) {
+ rc = request_irq(dev->int_info.msix[i * dev->num_hwfns].vector,
+ qedr_irq_handler, 0, dev->cnq_array[i].name,
+ &dev->cnq_array[i]);
+ if (rc) {
+ DP_ERR(dev, "Request cnq %d irq failed\n", i);
+ qedr_sync_free_irqs(dev);
+ } else {
+ DP_DEBUG(dev, QEDR_MSG_INIT,
+ "Requested cnq irq for %s [entry %d]. Cookie is at %p\n",
+ dev->cnq_array[i].name, i,
+ &dev->cnq_array[i]);
+ dev->int_info.used_cnt++;
+ }
+ }
+
+ return rc;
+}
+
+static int qedr_setup_irqs(struct qedr_dev *dev)
+{
+ int rc;
+
+ DP_DEBUG(dev, QEDR_MSG_INIT, "qedr_setup_irqs\n");
+
+ /* Learn Interrupt configuration */
+ rc = dev->ops->rdma_set_rdma_int(dev->cdev, dev->num_cnq);
+ if (rc < 0)
+ return rc;
+
+ rc = dev->ops->rdma_get_rdma_int(dev->cdev, &dev->int_info);
+ if (rc) {
+ DP_DEBUG(dev, QEDR_MSG_INIT, "get_rdma_int failed\n");
+ return rc;
+ }
+
+ if (dev->int_info.msix_cnt) {
+ DP_DEBUG(dev, QEDR_MSG_INIT, "rdma msix_cnt = %d\n",
+ dev->int_info.msix_cnt);
+ rc = qedr_req_msix_irqs(dev);
+ if (rc)
+ return rc;
+ }
+
+ DP_DEBUG(dev, QEDR_MSG_INIT, "qedr_setup_irqs succeeded\n");
+
+ return 0;
+}
+
+static int qedr_set_device_attr(struct qedr_dev *dev)
+{
+ struct qed_rdma_device *qed_attr;
+ struct qedr_device_attr *attr;
+ u32 page_size;
+
+ /* Part 1 - query core capabilities */
+ qed_attr = dev->ops->rdma_query_device(dev->rdma_ctx);
+
+ /* Part 2 - check capabilities */
+ page_size = ~dev->attr.page_size_caps + 1;
+ if (page_size > PAGE_SIZE) {
+ DP_ERR(dev,
+ "Kernel PAGE_SIZE is %ld which is smaller than minimum page size (%d) required by qedr\n",
+ PAGE_SIZE, page_size);
+ return -ENODEV;
+ }
+
+ /* Part 3 - copy and update capabilities */
+ attr = &dev->attr;
+ attr->vendor_id = qed_attr->vendor_id;
+ attr->vendor_part_id = qed_attr->vendor_part_id;
+ attr->hw_ver = qed_attr->hw_ver;
+ attr->fw_ver = qed_attr->fw_ver;
+ attr->node_guid = qed_attr->node_guid;
+ attr->sys_image_guid = qed_attr->sys_image_guid;
+ attr->max_cnq = qed_attr->max_cnq;
+ attr->max_sge = qed_attr->max_sge;
+ attr->max_inline = qed_attr->max_inline;
+ attr->max_sqe = min_t(u32, qed_attr->max_wqe, QEDR_MAX_SQE);
+ attr->max_rqe = min_t(u32, qed_attr->max_wqe, QEDR_MAX_RQE);
+ attr->max_qp_resp_rd_atomic_resc = qed_attr->max_qp_resp_rd_atomic_resc;
+ attr->max_qp_req_rd_atomic_resc = qed_attr->max_qp_req_rd_atomic_resc;
+ attr->max_dev_resp_rd_atomic_resc =
+ qed_attr->max_dev_resp_rd_atomic_resc;
+ attr->max_cq = qed_attr->max_cq;
+ attr->max_qp = qed_attr->max_qp;
+ attr->max_mr = qed_attr->max_mr;
+ attr->max_mr_size = qed_attr->max_mr_size;
+ attr->max_cqe = min_t(u64, qed_attr->max_cqe, QEDR_MAX_CQES);
+ attr->max_mw = qed_attr->max_mw;
+ attr->max_fmr = qed_attr->max_fmr;
+ attr->max_mr_mw_fmr_pbl = qed_attr->max_mr_mw_fmr_pbl;
+ attr->max_mr_mw_fmr_size = qed_attr->max_mr_mw_fmr_size;
+ attr->max_pd = qed_attr->max_pd;
+ attr->max_ah = qed_attr->max_ah;
+ attr->max_pkey = qed_attr->max_pkey;
+ attr->max_srq = qed_attr->max_srq;
+ attr->max_srq_wr = qed_attr->max_srq_wr;
+ attr->dev_caps = qed_attr->dev_caps;
+ attr->page_size_caps = qed_attr->page_size_caps;
+ attr->dev_ack_delay = qed_attr->dev_ack_delay;
+ attr->reserved_lkey = qed_attr->reserved_lkey;
+ attr->bad_pkey_counter = qed_attr->bad_pkey_counter;
+ attr->max_stats_queues = qed_attr->max_stats_queues;
+
+ return 0;
+}
+
+void qedr_unaffiliated_event(void *context,
+ u8 event_code)
+{
+ pr_err("unaffiliated event not implemented yet\n");
+}
+
+void qedr_affiliated_event(void *context, u8 e_code, void *fw_handle)
+{
+#define EVENT_TYPE_NOT_DEFINED 0
+#define EVENT_TYPE_CQ 1
+#define EVENT_TYPE_QP 2
+ struct qedr_dev *dev = (struct qedr_dev *)context;
+ union event_ring_data *data = fw_handle;
+ u64 roce_handle64 = ((u64)data->roce_handle.hi << 32) +
+ data->roce_handle.lo;
+ u8 event_type = EVENT_TYPE_NOT_DEFINED;
+ struct ib_event event;
+ struct ib_cq *ibcq;
+ struct ib_qp *ibqp;
+ struct qedr_cq *cq;
+ struct qedr_qp *qp;
+
+ switch (e_code) {
+ case ROCE_ASYNC_EVENT_CQ_OVERFLOW_ERR:
+ event.event = IB_EVENT_CQ_ERR;
+ event_type = EVENT_TYPE_CQ;
+ break;
+ case ROCE_ASYNC_EVENT_SQ_DRAINED:
+ event.event = IB_EVENT_SQ_DRAINED;
+ event_type = EVENT_TYPE_QP;
+ break;
+ case ROCE_ASYNC_EVENT_QP_CATASTROPHIC_ERR:
+ event.event = IB_EVENT_QP_FATAL;
+ event_type = EVENT_TYPE_QP;
+ break;
+ case ROCE_ASYNC_EVENT_LOCAL_INVALID_REQUEST_ERR:
+ event.event = IB_EVENT_QP_REQ_ERR;
+ event_type = EVENT_TYPE_QP;
+ break;
+ case ROCE_ASYNC_EVENT_LOCAL_ACCESS_ERR:
+ event.event = IB_EVENT_QP_ACCESS_ERR;
+ event_type = EVENT_TYPE_QP;
+ break;
+ default:
+ DP_ERR(dev, "unsupported event %d on handle=%llx\n", e_code,
+ roce_handle64);
+ }
+
+ switch (event_type) {
+ case EVENT_TYPE_CQ:
+ cq = (struct qedr_cq *)(uintptr_t)roce_handle64;
+ if (cq) {
+ ibcq = &cq->ibcq;
+ if (ibcq->event_handler) {
+ event.device = ibcq->device;
+ event.element.cq = ibcq;
+ ibcq->event_handler(&event, ibcq->cq_context);
+ }
+ } else {
+ WARN(1,
+ "Error: CQ event with NULL pointer ibcq. Handle=%llx\n",
+ roce_handle64);
+ }
+ DP_ERR(dev, "CQ event %d on hanlde %p\n", e_code, cq);
+ break;
+ case EVENT_TYPE_QP:
+ qp = (struct qedr_qp *)(uintptr_t)roce_handle64;
+ if (qp) {
+ ibqp = &qp->ibqp;
+ if (ibqp->event_handler) {
+ event.device = ibqp->device;
+ event.element.qp = ibqp;
+ ibqp->event_handler(&event, ibqp->qp_context);
+ }
+ } else {
+ WARN(1,
+ "Error: QP event with NULL pointer ibqp. Handle=%llx\n",
+ roce_handle64);
+ }
+ DP_ERR(dev, "QP event %d on hanlde %p\n", e_code, qp);
+ break;
+ default:
+ break;
+ }
+}
+
+static int qedr_init_hw(struct qedr_dev *dev)
+{
+ struct qed_rdma_add_user_out_params out_params;
+ struct qed_rdma_start_in_params *in_params;
+ struct qed_rdma_cnq_params *cur_pbl;
+ struct qed_rdma_events events;
+ dma_addr_t p_phys_table;
+ u32 page_cnt;
+ int rc = 0;
+ int i;
+
+ in_params = kzalloc(sizeof(*in_params), GFP_KERNEL);
+ if (!in_params) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ in_params->desired_cnq = dev->num_cnq;
+ for (i = 0; i < dev->num_cnq; i++) {
+ cur_pbl = &in_params->cnq_pbl_list[i];
+
+ page_cnt = qed_chain_get_page_cnt(&dev->cnq_array[i].pbl);
+ cur_pbl->num_pbl_pages = page_cnt;
+
+ p_phys_table = qed_chain_get_pbl_phys(&dev->cnq_array[i].pbl);
+ cur_pbl->pbl_ptr = (u64)p_phys_table;
+ }
+
+ events.affiliated_event = qedr_affiliated_event;
+ events.unaffiliated_event = qedr_unaffiliated_event;
+ events.context = dev;
+
+ in_params->events = &events;
+ in_params->cq_mode = QED_RDMA_CQ_MODE_32_BITS;
+ in_params->max_mtu = dev->ndev->mtu;
+ ether_addr_copy(&in_params->mac_addr[0], dev->ndev->dev_addr);
+
+ rc = dev->ops->rdma_init(dev->cdev, in_params);
+ if (rc)
+ goto out;
+
+ rc = dev->ops->rdma_add_user(dev->rdma_ctx, &out_params);
+ if (rc)
+ goto out;
+
+ dev->db_addr = (void *)(uintptr_t)out_params.dpi_addr;
+ dev->db_phys_addr = out_params.dpi_phys_addr;
+ dev->db_size = out_params.dpi_size;
+ dev->dpi = out_params.dpi;
+
+ rc = qedr_set_device_attr(dev);
+out:
+ kfree(in_params);
+ if (rc)
+ DP_ERR(dev, "Init HW Failed rc = %d\n", rc);
+
+ return rc;
+}
+
+void qedr_stop_hw(struct qedr_dev *dev)
+{
+ dev->ops->rdma_remove_user(dev->rdma_ctx, dev->dpi);
+ dev->ops->rdma_stop(dev->rdma_ctx);
+}
+
+static struct qedr_dev *qedr_add(struct qed_dev *cdev, struct pci_dev *pdev,
+ struct net_device *ndev)
+{
+ struct qed_dev_rdma_info dev_info;
+ struct qedr_dev *dev;
+ int rc = 0, i;
+
+ dev = (struct qedr_dev *)ib_alloc_device(sizeof(*dev));
+ if (!dev) {
+ pr_err("Unable to allocate ib device\n");
+ return NULL;
+ }
+
+ DP_DEBUG(dev, QEDR_MSG_INIT, "qedr add device called\n");
+
+ dev->pdev = pdev;
+ dev->ndev = ndev;
+ dev->cdev = cdev;
+
+ qed_ops = qed_get_rdma_ops();
+ if (!qed_ops) {
+ DP_ERR(dev, "Failed to get qed roce operations\n");
+ goto init_err;
+ }
+
+ dev->ops = qed_ops;
+ rc = qed_ops->fill_dev_info(cdev, &dev_info);
+ if (rc)
+ goto init_err;
+
+ dev->num_hwfns = dev_info.common.num_hwfns;
+ dev->rdma_ctx = dev->ops->rdma_get_rdma_ctx(cdev);
+
+ dev->num_cnq = dev->ops->rdma_get_min_cnq_msix(cdev);
+ if (!dev->num_cnq) {
+ DP_ERR(dev, "not enough CNQ resources.\n");
+ goto init_err;
+ }
+
+ dev->wq_multiplier = QEDR_WQ_MULTIPLIER_DFT;
+
+ qedr_pci_set_atomic(dev, pdev);
+
+ rc = qedr_alloc_resources(dev);
+ if (rc)
+ goto init_err;
+
+ rc = qedr_init_hw(dev);
+ if (rc)
+ goto alloc_err;
+
+ rc = qedr_setup_irqs(dev);
+ if (rc)
+ goto irq_err;
+
+ rc = qedr_register_device(dev);
+ if (rc) {
+ DP_ERR(dev, "Unable to allocate register device\n");
+ goto reg_err;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(qedr_attributes); i++)
+ if (device_create_file(&dev->ibdev.dev, qedr_attributes[i]))
+ goto sysfs_err;
+
+ DP_DEBUG(dev, QEDR_MSG_INIT, "qedr driver loaded successfully\n");
+ return dev;
+
+sysfs_err:
+ ib_unregister_device(&dev->ibdev);
+reg_err:
+ qedr_sync_free_irqs(dev);
+irq_err:
+ qedr_stop_hw(dev);
+alloc_err:
+ qedr_free_resources(dev);
+init_err:
+ ib_dealloc_device(&dev->ibdev);
+ DP_ERR(dev, "qedr driver load failed rc=%d\n", rc);
+
+ return NULL;
+}
+
+static void qedr_remove(struct qedr_dev *dev)
+{
+ /* First unregister with stack to stop all the active traffic
+ * of the registered clients.
+ */
+ qedr_remove_sysfiles(dev);
+ ib_unregister_device(&dev->ibdev);
+
+ qedr_stop_hw(dev);
+ qedr_sync_free_irqs(dev);
+ qedr_free_resources(dev);
+ ib_dealloc_device(&dev->ibdev);
+}
+
+static int qedr_close(struct qedr_dev *dev)
+{
+ qedr_ib_dispatch_event(dev, 1, IB_EVENT_PORT_ERR);
+
+ return 0;
+}
+
+static void qedr_shutdown(struct qedr_dev *dev)
+{
+ qedr_close(dev);
+ qedr_remove(dev);
+}
+
+static void qedr_mac_address_change(struct qedr_dev *dev)
+{
+ union ib_gid *sgid = &dev->sgid_tbl[0];
+ u8 guid[8], mac_addr[6];
+ int rc;
+
+ /* Update SGID */
+ ether_addr_copy(&mac_addr[0], dev->ndev->dev_addr);
+ guid[0] = mac_addr[0] ^ 2;
+ guid[1] = mac_addr[1];
+ guid[2] = mac_addr[2];
+ guid[3] = 0xff;
+ guid[4] = 0xfe;
+ guid[5] = mac_addr[3];
+ guid[6] = mac_addr[4];
+ guid[7] = mac_addr[5];
+ sgid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
+ memcpy(&sgid->raw[8], guid, sizeof(guid));
+
+ /* Update LL2 */
+ rc = dev->ops->roce_ll2_set_mac_filter(dev->cdev,
+ dev->gsi_ll2_mac_address,
+ dev->ndev->dev_addr);
+
+ ether_addr_copy(dev->gsi_ll2_mac_address, dev->ndev->dev_addr);
+
+ qedr_ib_dispatch_event(dev, 1, IB_EVENT_GID_CHANGE);
+
+ if (rc)
+ DP_ERR(dev, "Error updating mac filter\n");
+}
+
+/* event handling via NIC driver ensures that all the NIC specific
+ * initialization done before RoCE driver notifies
+ * event to stack.
+ */
+static void qedr_notify(struct qedr_dev *dev, enum qede_roce_event event)
+{
+ switch (event) {
+ case QEDE_UP:
+ qedr_ib_dispatch_event(dev, 1, IB_EVENT_PORT_ACTIVE);
+ break;
+ case QEDE_DOWN:
+ qedr_close(dev);
+ break;
+ case QEDE_CLOSE:
+ qedr_shutdown(dev);
+ break;
+ case QEDE_CHANGE_ADDR:
+ qedr_mac_address_change(dev);
+ break;
+ default:
+ pr_err("Event not supported\n");
+ }
+}
+
+static struct qedr_driver qedr_drv = {
+ .name = "qedr_driver",
+ .add = qedr_add,
+ .remove = qedr_remove,
+ .notify = qedr_notify,
+};
+
+static int __init qedr_init_module(void)
+{
+ return qede_roce_register_driver(&qedr_drv);
+}
+
+static void __exit qedr_exit_module(void)
+{
+ qede_roce_unregister_driver(&qedr_drv);
+}
+
+module_init(qedr_init_module);
+module_exit(qedr_exit_module);
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
new file mode 100644
index 0000000..620badd
--- /dev/null
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -0,0 +1,495 @@
+/* QLogic qedr NIC Driver
+ * Copyright (c) 2015-2016 QLogic Corporation
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and /or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef __QEDR_H__
+#define __QEDR_H__
+
+#include <linux/pci.h>
+#include <rdma/ib_addr.h>
+#include <linux/qed/qed_if.h>
+#include <linux/qed/qed_chain.h>
+#include <linux/qed/qed_roce_if.h>
+#include <linux/qed/qede_roce.h>
+#include "qedr_hsi.h"
+
+#define QEDR_MODULE_VERSION "8.10.10.0"
+#define QEDR_NODE_DESC "QLogic 579xx RoCE HCA"
+#define DP_NAME(dev) ((dev)->ibdev.name)
+
+#define DP_DEBUG(dev, module, fmt, ...) \
+ pr_debug("(%s) " module ": " fmt, \
+ DP_NAME(dev) ? DP_NAME(dev) : "", ## __VA_ARGS__)
+
+#define QEDR_MSG_INIT "INIT"
+#define QEDR_MSG_MISC "MISC"
+#define QEDR_MSG_CQ " CQ"
+#define QEDR_MSG_MR " MR"
+#define QEDR_MSG_RQ " RQ"
+#define QEDR_MSG_SQ " SQ"
+#define QEDR_MSG_QP " QP"
+#define QEDR_MSG_GSI " GSI"
+
+#define QEDR_CQ_MAGIC_NUMBER (0x11223344)
+
+struct qedr_dev;
+
+struct qedr_cnq {
+ struct qedr_dev *dev;
+ struct qed_chain pbl;
+ struct qed_sb_info *sb;
+ char name[32];
+ u64 n_comp;
+ __le16 *hw_cons_ptr;
+ u8 index;
+};
+
+#define QEDR_MAX_SGID 128
+
+struct qedr_device_attr {
+ u32 vendor_id;
+ u32 vendor_part_id;
+ u32 hw_ver;
+ u64 fw_ver;
+ u64 node_guid;
+ u64 sys_image_guid;
+ u8 max_cnq;
+ u8 max_sge;
+ u16 max_inline;
+ u32 max_sqe;
+ u32 max_rqe;
+ u8 max_qp_resp_rd_atomic_resc;
+ u8 max_qp_req_rd_atomic_resc;
+ u64 max_dev_resp_rd_atomic_resc;
+ u32 max_cq;
+ u32 max_qp;
+ u32 max_mr;
+ u64 max_mr_size;
+ u32 max_cqe;
+ u32 max_mw;
+ u32 max_fmr;
+ u32 max_mr_mw_fmr_pbl;
+ u64 max_mr_mw_fmr_size;
+ u32 max_pd;
+ u32 max_ah;
+ u8 max_pkey;
+ u32 max_srq;
+ u32 max_srq_wr;
+ u8 max_srq_sge;
+ u8 max_stats_queues;
+ u32 dev_caps;
+
+ u64 page_size_caps;
+ u8 dev_ack_delay;
+ u32 reserved_lkey;
+ u32 bad_pkey_counter;
+ struct qed_rdma_events events;
+};
+
+struct qedr_dev {
+ struct ib_device ibdev;
+ struct qed_dev *cdev;
+ struct pci_dev *pdev;
+ struct net_device *ndev;
+
+ enum ib_atomic_cap atomic_cap;
+
+ void *rdma_ctx;
+ struct qedr_device_attr attr;
+
+ const struct qed_rdma_ops *ops;
+ struct qed_int_info int_info;
+
+ struct qed_sb_info *sb_array;
+ struct qedr_cnq *cnq_array;
+ int num_cnq;
+ int sb_start;
+
+ void __iomem *db_addr;
+ u64 db_phys_addr;
+ u32 db_size;
+ u16 dpi;
+
+ union ib_gid *sgid_tbl;
+
+ /* Lock for sgid table */
+ spinlock_t sgid_lock;
+
+ u64 guid;
+
+ u32 dp_module;
+ u8 dp_level;
+ u8 num_hwfns;
+ uint wq_multiplier;
+ u8 gsi_ll2_mac_address[ETH_ALEN];
+ int gsi_qp_created;
+ struct qedr_cq *gsi_sqcq;
+ struct qedr_cq *gsi_rqcq;
+ struct qedr_qp *gsi_qp;
+};
+
+#define QEDR_MAX_SQ_PBL (0x8000)
+#define QEDR_MAX_SQ_PBL_ENTRIES (0x10000 / sizeof(void *))
+#define QEDR_SQE_ELEMENT_SIZE (sizeof(struct rdma_sq_sge))
+#define QEDR_MAX_SQE_ELEMENTS_PER_SQE (ROCE_REQ_MAX_SINGLE_SQ_WQE_SIZE / \
+ QEDR_SQE_ELEMENT_SIZE)
+#define QEDR_MAX_SQE_ELEMENTS_PER_PAGE ((RDMA_RING_PAGE_SIZE) / \
+ QEDR_SQE_ELEMENT_SIZE)
+#define QEDR_MAX_SQE ((QEDR_MAX_SQ_PBL_ENTRIES) *\
+ (RDMA_RING_PAGE_SIZE) / \
+ (QEDR_SQE_ELEMENT_SIZE) /\
+ (QEDR_MAX_SQE_ELEMENTS_PER_SQE))
+/* RQ */
+#define QEDR_MAX_RQ_PBL (0x2000)
+#define QEDR_MAX_RQ_PBL_ENTRIES (0x10000 / sizeof(void *))
+#define QEDR_RQE_ELEMENT_SIZE (sizeof(struct rdma_rq_sge))
+#define QEDR_MAX_RQE_ELEMENTS_PER_RQE (RDMA_MAX_SGE_PER_RQ_WQE)
+#define QEDR_MAX_RQE_ELEMENTS_PER_PAGE ((RDMA_RING_PAGE_SIZE) / \
+ QEDR_RQE_ELEMENT_SIZE)
+#define QEDR_MAX_RQE ((QEDR_MAX_RQ_PBL_ENTRIES) *\
+ (RDMA_RING_PAGE_SIZE) / \
+ (QEDR_RQE_ELEMENT_SIZE) /\
+ (QEDR_MAX_RQE_ELEMENTS_PER_RQE))
+
+#define QEDR_CQE_SIZE (sizeof(union rdma_cqe))
+#define QEDR_MAX_CQE_PBL_SIZE (512 * 1024)
+#define QEDR_MAX_CQE_PBL_ENTRIES (((QEDR_MAX_CQE_PBL_SIZE) / \
+ sizeof(u64)) - 1)
+#define QEDR_MAX_CQES ((u32)((QEDR_MAX_CQE_PBL_ENTRIES) * \
+ (QED_CHAIN_PAGE_SIZE) / QEDR_CQE_SIZE))
+
+#define QEDR_ROCE_MAX_CNQ_SIZE (0x4000)
+
+#define QEDR_MAX_PORT (1)
+
+#define QEDR_UVERBS(CMD_NAME) (1ull << IB_USER_VERBS_CMD_##CMD_NAME)
+
+#define QEDR_ROCE_PKEY_MAX 1
+#define QEDR_ROCE_PKEY_TABLE_LEN 1
+#define QEDR_ROCE_PKEY_DEFAULT 0xffff
+
+struct qedr_pbl {
+ struct list_head list_entry;
+ void *va;
+ dma_addr_t pa;
+};
+
+struct qedr_ucontext {
+ struct ib_ucontext ibucontext;
+ struct qedr_dev *dev;
+ struct qedr_pd *pd;
+ u64 dpi_addr;
+ u64 dpi_phys_addr;
+ u32 dpi_size;
+ u16 dpi;
+
+ struct list_head mm_head;
+
+ /* Lock to protect mm list */
+ struct mutex mm_list_lock;
+};
+
+union db_prod64 {
+ struct rdma_pwm_val32_data data;
+ u64 raw;
+};
+
+enum qedr_cq_type {
+ QEDR_CQ_TYPE_GSI,
+ QEDR_CQ_TYPE_KERNEL,
+ QEDR_CQ_TYPE_USER,
+};
+
+struct qedr_pbl_info {
+ u32 num_pbls;
+ u32 num_pbes;
+ u32 pbl_size;
+ u32 pbe_size;
+ bool two_layered;
+};
+
+struct qedr_userq {
+ struct ib_umem *umem;
+ struct qedr_pbl_info pbl_info;
+ struct qedr_pbl *pbl_tbl;
+ u64 buf_addr;
+ size_t buf_len;
+};
+
+struct qedr_cq {
+ struct ib_cq ibcq;
+
+ enum qedr_cq_type cq_type;
+ u32 sig;
+
+ u16 icid;
+
+ /* Lock to protect completion handler */
+ spinlock_t comp_handler_lock;
+
+ /* Lock to protect multiplem CQ's */
+ spinlock_t cq_lock;
+ u8 arm_flags;
+ struct qed_chain pbl;
+
+ void __iomem *db_addr;
+ union db_prod64 db;
+
+ u8 pbl_toggle;
+ union rdma_cqe *latest_cqe;
+ union rdma_cqe *toggle_cqe;
+
+ u32 cq_cons;
+
+ struct qedr_userq q;
+};
+
+struct qedr_pd {
+ struct ib_pd ibpd;
+ u32 pd_id;
+ struct qedr_ucontext *uctx;
+};
+
+struct qedr_mm {
+ struct {
+ u64 phy_addr;
+ unsigned long len;
+ } key;
+ struct list_head entry;
+};
+
+union db_prod32 {
+ struct rdma_pwm_val16_data data;
+ u32 raw;
+};
+
+struct qedr_qp_hwq_info {
+ /* WQE Elements */
+ struct qed_chain pbl;
+ u64 p_phys_addr_tbl;
+ u32 max_sges;
+
+ /* WQE */
+ u16 prod;
+ u16 cons;
+ u16 wqe_cons;
+ u16 gsi_cons;
+ u16 max_wr;
+
+ /* DB */
+ void __iomem *db;
+ union db_prod32 db_data;
+};
+
+#define QEDR_INC_SW_IDX(p_info, index) \
+ do { \
+ p_info->index = (p_info->index + 1) & \
+ qed_chain_get_capacity(p_info->pbl) \
+ } while (0)
+
+enum qedr_qp_err_bitmap {
+ QEDR_QP_ERR_SQ_FULL = 1,
+ QEDR_QP_ERR_RQ_FULL = 2,
+ QEDR_QP_ERR_BAD_SR = 4,
+ QEDR_QP_ERR_BAD_RR = 8,
+ QEDR_QP_ERR_SQ_PBL_FULL = 16,
+ QEDR_QP_ERR_RQ_PBL_FULL = 32,
+};
+
+struct qedr_qp {
+ struct ib_qp ibqp; /* must be first */
+ struct qedr_dev *dev;
+
+ struct qedr_qp_hwq_info sq;
+ struct qedr_qp_hwq_info rq;
+
+ u32 max_inline_data;
+
+ /* Lock for QP's */
+ spinlock_t q_lock;
+ struct qedr_cq *sq_cq;
+ struct qedr_cq *rq_cq;
+ struct qedr_srq *srq;
+ enum qed_roce_qp_state state;
+ u32 id;
+ struct qedr_pd *pd;
+ enum ib_qp_type qp_type;
+ struct qed_rdma_qp *qed_qp;
+ u32 qp_id;
+ u16 icid;
+ u16 mtu;
+ int sgid_idx;
+ u32 rq_psn;
+ u32 sq_psn;
+ u32 qkey;
+ u32 dest_qp_num;
+
+ /* Relevant to qps created from kernel space only (ULPs) */
+ u8 prev_wqe_size;
+ u16 wqe_cons;
+ u32 err_bitmap;
+ bool signaled;
+
+ /* SQ shadow */
+ struct {
+ u64 wr_id;
+ enum ib_wc_opcode opcode;
+ u32 bytes_len;
+ u8 wqe_size;
+ bool signaled;
+ dma_addr_t icrc_mapping;
+ u32 *icrc;
+ struct qedr_mr *mr;
+ } *wqe_wr_id;
+
+ /* RQ shadow */
+ struct {
+ u64 wr_id;
+ struct ib_sge sg_list[RDMA_MAX_SGE_PER_RQ_WQE];
+ u8 wqe_size;
+
+ u8 smac[ETH_ALEN];
+ u16 vlan_id;
+ int rc;
+ } *rqe_wr_id;
+
+ /* Relevant to qps created from user space only (applications) */
+ struct qedr_userq usq;
+ struct qedr_userq urq;
+};
+
+struct qedr_ah {
+ struct ib_ah ibah;
+ struct ib_ah_attr attr;
+};
+
+enum qedr_mr_type {
+ QEDR_MR_USER,
+ QEDR_MR_KERNEL,
+ QEDR_MR_DMA,
+ QEDR_MR_FRMR,
+};
+
+struct mr_info {
+ struct qedr_pbl *pbl_table;
+ struct qedr_pbl_info pbl_info;
+ struct list_head free_pbl_list;
+ struct list_head inuse_pbl_list;
+ u32 completed;
+ u32 completed_handled;
+};
+
+struct qedr_mr {
+ struct ib_mr ibmr;
+ struct ib_umem *umem;
+
+ struct qed_rdma_register_tid_in_params hw_mr;
+ enum qedr_mr_type type;
+
+ struct qedr_dev *dev;
+ struct mr_info info;
+
+ u64 *pages;
+ u32 npages;
+};
+
+#define SET_FIELD2(value, name, flag) ((value) |= ((flag) << (name ## _SHIFT)))
+
+#define QEDR_RESP_IMM (RDMA_CQE_RESPONDER_IMM_FLG_MASK << \
+ RDMA_CQE_RESPONDER_IMM_FLG_SHIFT)
+#define QEDR_RESP_RDMA (RDMA_CQE_RESPONDER_RDMA_FLG_MASK << \
+ RDMA_CQE_RESPONDER_RDMA_FLG_SHIFT)
+#define QEDR_RESP_RDMA_IMM (QEDR_RESP_IMM | QEDR_RESP_RDMA)
+
+static inline void qedr_inc_sw_cons(struct qedr_qp_hwq_info *info)
+{
+ info->cons = (info->cons + 1) % info->max_wr;
+ info->wqe_cons++;
+}
+
+static inline void qedr_inc_sw_prod(struct qedr_qp_hwq_info *info)
+{
+ info->prod = (info->prod + 1) % info->max_wr;
+}
+
+static inline int qedr_get_dmac(struct qedr_dev *dev,
+ struct ib_ah_attr *ah_attr, u8 *mac_addr)
+{
+ union ib_gid zero_sgid = { { 0 } };
+ struct in6_addr in6;
+
+ if (!memcmp(&ah_attr->grh.dgid, &zero_sgid, sizeof(union ib_gid))) {
+ DP_ERR(dev, "Local port GID not supported\n");
+ eth_zero_addr(mac_addr);
+ return -EINVAL;
+ }
+
+ memcpy(&in6, ah_attr->grh.dgid.raw, sizeof(in6));
+ ether_addr_copy(mac_addr, ah_attr->dmac);
+
+ return 0;
+}
+
+static inline
+struct qedr_ucontext *get_qedr_ucontext(struct ib_ucontext *ibucontext)
+{
+ return container_of(ibucontext, struct qedr_ucontext, ibucontext);
+}
+
+static inline struct qedr_dev *get_qedr_dev(struct ib_device *ibdev)
+{
+ return container_of(ibdev, struct qedr_dev, ibdev);
+}
+
+static inline struct qedr_pd *get_qedr_pd(struct ib_pd *ibpd)
+{
+ return container_of(ibpd, struct qedr_pd, ibpd);
+}
+
+static inline struct qedr_cq *get_qedr_cq(struct ib_cq *ibcq)
+{
+ return container_of(ibcq, struct qedr_cq, ibcq);
+}
+
+static inline struct qedr_qp *get_qedr_qp(struct ib_qp *ibqp)
+{
+ return container_of(ibqp, struct qedr_qp, ibqp);
+}
+
+static inline struct qedr_ah *get_qedr_ah(struct ib_ah *ibah)
+{
+ return container_of(ibah, struct qedr_ah, ibah);
+}
+
+static inline struct qedr_mr *get_qedr_mr(struct ib_mr *ibmr)
+{
+ return container_of(ibmr, struct qedr_mr, ibmr);
+}
+#endif
diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_cm.c
new file mode 100644
index 0000000..63890eb
--- /dev/null
+++ b/drivers/infiniband/hw/qedr/qedr_cm.c
@@ -0,0 +1,622 @@
+/* QLogic qedr NIC Driver
+ * Copyright (c) 2015-2016 QLogic Corporation
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and /or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#include <linux/dma-mapping.h>
+#include <linux/crc32.h>
+#include <linux/iommu.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/udp.h>
+
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_user_verbs.h>
+#include <rdma/iw_cm.h>
+#include <rdma/ib_umem.h>
+#include <rdma/ib_addr.h>
+#include <rdma/ib_cache.h>
+
+#include "qedr_hsi.h"
+#include <linux/qed/qed_if.h>
+#include <linux/qed/qed_roce_if.h>
+#include "qedr.h"
+#include "qedr_hsi.h"
+#include "verbs.h"
+#include <rdma/qedr-abi.h>
+#include "qedr_hsi.h"
+#include "qedr_cm.h"
+
+void qedr_inc_sw_gsi_cons(struct qedr_qp_hwq_info *info)
+{
+ info->gsi_cons = (info->gsi_cons + 1) % info->max_wr;
+}
+
+void qedr_store_gsi_qp_cq(struct qedr_dev *dev, struct qedr_qp *qp,
+ struct ib_qp_init_attr *attrs)
+{
+ dev->gsi_qp_created = 1;
+ dev->gsi_sqcq = get_qedr_cq(attrs->send_cq);
+ dev->gsi_rqcq = get_qedr_cq(attrs->recv_cq);
+ dev->gsi_qp = qp;
+}
+
+void qedr_ll2_tx_cb(void *_qdev, struct qed_roce_ll2_packet *pkt)
+{
+ struct qedr_dev *dev = (struct qedr_dev *)_qdev;
+ struct qedr_cq *cq = dev->gsi_sqcq;
+ struct qedr_qp *qp = dev->gsi_qp;
+ unsigned long flags;
+
+ DP_DEBUG(dev, QEDR_MSG_GSI,
+ "LL2 TX CB: gsi_sqcq=%p, gsi_rqcq=%p, gsi_cons=%d, ibcq_comp=%s\n",
+ dev->gsi_sqcq, dev->gsi_rqcq, qp->sq.gsi_cons,
+ cq->ibcq.comp_handler ? "Yes" : "No");
+
+ dma_free_coherent(&dev->pdev->dev, pkt->header.len, pkt->header.vaddr,
+ pkt->header.baddr);
+ kfree(pkt);
+
+ spin_lock_irqsave(&qp->q_lock, flags);
+ qedr_inc_sw_gsi_cons(&qp->sq);
+ spin_unlock_irqrestore(&qp->q_lock, flags);
+
+ if (cq->ibcq.comp_handler) {
+ spin_lock_irqsave(&cq->comp_handler_lock, flags);
+ (*cq->ibcq.comp_handler) (&cq->ibcq, cq->ibcq.cq_context);
+ spin_unlock_irqrestore(&cq->comp_handler_lock, flags);
+ }
+}
+
+void qedr_ll2_rx_cb(void *_dev, struct qed_roce_ll2_packet *pkt,
+ struct qed_roce_ll2_rx_params *params)
+{
+ struct qedr_dev *dev = (struct qedr_dev *)_dev;
+ struct qedr_cq *cq = dev->gsi_rqcq;
+ struct qedr_qp *qp = dev->gsi_qp;
+ unsigned long flags;
+
+ spin_lock_irqsave(&qp->q_lock, flags);
+
+ qp->rqe_wr_id[qp->rq.gsi_cons].rc = params->rc;
+ qp->rqe_wr_id[qp->rq.gsi_cons].vlan_id = params->vlan_id;
+ qp->rqe_wr_id[qp->rq.gsi_cons].sg_list[0].length = pkt->payload[0].len;
+ ether_addr_copy(qp->rqe_wr_id[qp->rq.gsi_cons].smac, params->smac);
+
+ qedr_inc_sw_gsi_cons(&qp->rq);
+
+ spin_unlock_irqrestore(&qp->q_lock, flags);
+
+ if (cq->ibcq.comp_handler) {
+ spin_lock_irqsave(&cq->comp_handler_lock, flags);
+ (*cq->ibcq.comp_handler) (&cq->ibcq, cq->ibcq.cq_context);
+ spin_unlock_irqrestore(&cq->comp_handler_lock, flags);
+ }
+}
+
+static void qedr_destroy_gsi_cq(struct qedr_dev *dev,
+ struct ib_qp_init_attr *attrs)
+{
+ struct qed_rdma_destroy_cq_in_params iparams;
+ struct qed_rdma_destroy_cq_out_params oparams;
+ struct qedr_cq *cq;
+
+ cq = get_qedr_cq(attrs->send_cq);
+ iparams.icid = cq->icid;
+ dev->ops->rdma_destroy_cq(dev->rdma_ctx, &iparams, &oparams);
+ dev->ops->common->chain_free(dev->cdev, &cq->pbl);
+
+ cq = get_qedr_cq(attrs->recv_cq);
+ /* if a dedicated recv_cq was used, delete it too */
+ if (iparams.icid != cq->icid) {
+ iparams.icid = cq->icid;
+ dev->ops->rdma_destroy_cq(dev->rdma_ctx, &iparams, &oparams);
+ dev->ops->common->chain_free(dev->cdev, &cq->pbl);
+ }
+}
+
+static inline int qedr_check_gsi_qp_attrs(struct qedr_dev *dev,
+ struct ib_qp_init_attr *attrs)
+{
+ if (attrs->cap.max_recv_sge > QEDR_GSI_MAX_RECV_SGE) {
+ DP_ERR(dev,
+ " create gsi qp: failed. max_recv_sge is larger the max %d>%d\n",
+ attrs->cap.max_recv_sge, QEDR_GSI_MAX_RECV_SGE);
+ return -EINVAL;
+ }
+
+ if (attrs->cap.max_recv_wr > QEDR_GSI_MAX_RECV_WR) {
+ DP_ERR(dev,
+ " create gsi qp: failed. max_recv_wr is too large %d>%d\n",
+ attrs->cap.max_recv_wr, QEDR_GSI_MAX_RECV_WR);
+ return -EINVAL;
+ }
+
+ if (attrs->cap.max_send_wr > QEDR_GSI_MAX_SEND_WR) {
+ DP_ERR(dev,
+ " create gsi qp: failed. max_send_wr is too large %d>%d\n",
+ attrs->cap.max_send_wr, QEDR_GSI_MAX_SEND_WR);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+struct ib_qp *qedr_create_gsi_qp(struct qedr_dev *dev,
+ struct ib_qp_init_attr *attrs,
+ struct qedr_qp *qp)
+{
+ struct qed_roce_ll2_params ll2_params;
+ int rc;
+
+ rc = qedr_check_gsi_qp_attrs(dev, attrs);
+ if (rc)
+ return ERR_PTR(rc);
+
+ /* configure and start LL2 */
+ memset(&ll2_params, 0, sizeof(ll2_params));
+ ll2_params.max_tx_buffers = attrs->cap.max_send_wr;
+ ll2_params.max_rx_buffers = attrs->cap.max_recv_wr;
+ ll2_params.cbs.tx_cb = qedr_ll2_tx_cb;
+ ll2_params.cbs.rx_cb = qedr_ll2_rx_cb;
+ ll2_params.cb_cookie = (void *)dev;
+ ll2_params.mtu = dev->ndev->mtu;
+ ether_addr_copy(ll2_params.mac_address, dev->ndev->dev_addr);
+ rc = dev->ops->roce_ll2_start(dev->cdev, &ll2_params);
+ if (rc) {
+ DP_ERR(dev, "create gsi qp: failed on ll2 start. rc=%d\n", rc);
+ return ERR_PTR(rc);
+ }
+
+ /* create QP */
+ qp->ibqp.qp_num = 1;
+ qp->rq.max_wr = attrs->cap.max_recv_wr;
+ qp->sq.max_wr = attrs->cap.max_send_wr;
+
+ qp->rqe_wr_id = kcalloc(qp->rq.max_wr, sizeof(*qp->rqe_wr_id),
+ GFP_KERNEL);
+ if (!qp->rqe_wr_id)
+ goto err;
+ qp->wqe_wr_id = kcalloc(qp->sq.max_wr, sizeof(*qp->wqe_wr_id),
+ GFP_KERNEL);
+ if (!qp->wqe_wr_id)
+ goto err;
+
+ qedr_store_gsi_qp_cq(dev, qp, attrs);
+ ether_addr_copy(dev->gsi_ll2_mac_address, dev->ndev->dev_addr);
+
+ /* the GSI CQ is handled by the driver so remove it from the FW */
+ qedr_destroy_gsi_cq(dev, attrs);
+ dev->gsi_rqcq->cq_type = QEDR_CQ_TYPE_GSI;
+ dev->gsi_rqcq->cq_type = QEDR_CQ_TYPE_GSI;
+
+ DP_DEBUG(dev, QEDR_MSG_GSI, "created GSI QP %p\n", qp);
+
+ return &qp->ibqp;
+
+err:
+ kfree(qp->rqe_wr_id);
+
+ rc = dev->ops->roce_ll2_stop(dev->cdev);
+ if (rc)
+ DP_ERR(dev, "create gsi qp: failed destroy on create\n");
+
+ return ERR_PTR(-ENOMEM);
+}
+
+int qedr_destroy_gsi_qp(struct qedr_dev *dev)
+{
+ int rc;
+
+ rc = dev->ops->roce_ll2_stop(dev->cdev);
+ if (rc)
+ DP_ERR(dev, "destroy gsi qp: failed (rc=%d)\n", rc);
+ else
+ DP_DEBUG(dev, QEDR_MSG_GSI, "destroy gsi qp: success\n");
+
+ return rc;
+}
+
+#define QEDR_MAX_UD_HEADER_SIZE (100)
+#define QEDR_GSI_QPN (1)
+static inline int qedr_gsi_build_header(struct qedr_dev *dev,
+ struct qedr_qp *qp,
+ struct ib_send_wr *swr,
+ struct ib_ud_header *udh,
+ int *roce_mode)
+{
+ bool has_vlan = false, has_grh_ipv6 = true;
+ struct ib_ah_attr *ah_attr = &get_qedr_ah(ud_wr(swr)->ah)->attr;
+ struct ib_global_route *grh = &ah_attr->grh;
+ union ib_gid sgid;
+ int send_size = 0;
+ u16 vlan_id = 0;
+ u16 ether_type;
+ struct ib_gid_attr sgid_attr;
+ int rc;
+ int ip_ver = 0;
+
+ bool has_udp = false;
+ int i;
+
+ send_size = 0;
+ for (i = 0; i < swr->num_sge; ++i)
+ send_size += swr->sg_list[i].length;
+
+ rc = ib_get_cached_gid(qp->ibqp.device, ah_attr->port_num,
+ grh->sgid_index, &sgid, &sgid_attr);
+ if (rc) {
+ DP_ERR(dev,
+ "gsi post send: failed to get cached GID (port=%d, ix=%d)\n",
+ ah_attr->port_num, grh->sgid_index);
+ return rc;
+ }
+
+ vlan_id = rdma_vlan_dev_vlan_id(sgid_attr.ndev);
+ if (vlan_id < VLAN_CFI_MASK)
+ has_vlan = true;
+ if (sgid_attr.ndev)
+ dev_put(sgid_attr.ndev);
+
+ if (!memcmp(&sgid, &zgid, sizeof(sgid))) {
+ DP_ERR(dev, "gsi post send: GID not found GID index %d\n",
+ ah_attr->grh.sgid_index);
+ return -ENOENT;
+ }
+
+ has_udp = (sgid_attr.gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP);
+ if (!has_udp) {
+ /* RoCE v1 */
+ ether_type = ETH_P_ROCE;
+ *roce_mode = ROCE_V1;
+ } else if (ipv6_addr_v4mapped((struct in6_addr *)&sgid)) {
+ /* RoCE v2 IPv4 */
+ ip_ver = 4;
+ ether_type = ETH_P_IP;
+ has_grh_ipv6 = false;
+ *roce_mode = ROCE_V2_IPV4;
+ } else {
+ /* RoCE v2 IPv6 */
+ ip_ver = 6;
+ ether_type = ETH_P_IPV6;
+ *roce_mode = ROCE_V2_IPV6;
+ }
+
+ rc = ib_ud_header_init(send_size, false, true, has_vlan,
+ has_grh_ipv6, ip_ver, has_udp, 0, udh);
+ if (rc) {
+ DP_ERR(dev, "gsi post send: failed to init header\n");
+ return rc;
+ }
+
+ /* ENET + VLAN headers */
+ ether_addr_copy(udh->eth.dmac_h, ah_attr->dmac);
+ ether_addr_copy(udh->eth.smac_h, dev->ndev->dev_addr);
+ if (has_vlan) {
+ udh->eth.type = htons(ETH_P_8021Q);
+ udh->vlan.tag = htons(vlan_id);
+ udh->vlan.type = htons(ether_type);
+ } else {
+ udh->eth.type = htons(ether_type);
+ }
+
+ /* BTH */
+ udh->bth.solicited_event = !!(swr->send_flags & IB_SEND_SOLICITED);
+ udh->bth.pkey = QEDR_ROCE_PKEY_DEFAULT;
+ udh->bth.destination_qpn = htonl(ud_wr(swr)->remote_qpn);
+ udh->bth.psn = htonl((qp->sq_psn++) & ((1 << 24) - 1));
+ udh->bth.opcode = IB_OPCODE_UD_SEND_ONLY;
+
+ /* DETH */
+ udh->deth.qkey = htonl(0x80010000);
+ udh->deth.source_qpn = htonl(QEDR_GSI_QPN);
+
+ if (has_grh_ipv6) {
+ /* GRH / IPv6 header */
+ udh->grh.traffic_class = grh->traffic_class;
+ udh->grh.flow_label = grh->flow_label;
+ udh->grh.hop_limit = grh->hop_limit;
+ udh->grh.destination_gid = grh->dgid;
+ memcpy(&udh->grh.source_gid.raw, &sgid.raw,
+ sizeof(udh->grh.source_gid.raw));
+ } else {
+ /* IPv4 header */
+ u32 ipv4_addr;
+
+ udh->ip4.protocol = IPPROTO_UDP;
+ udh->ip4.tos = htonl(ah_attr->grh.flow_label);
+ udh->ip4.frag_off = htons(IP_DF);
+ udh->ip4.ttl = ah_attr->grh.hop_limit;
+
+ ipv4_addr = qedr_get_ipv4_from_gid(sgid.raw);
+ udh->ip4.saddr = ipv4_addr;
+ ipv4_addr = qedr_get_ipv4_from_gid(ah_attr->grh.dgid.raw);
+ udh->ip4.daddr = ipv4_addr;
+ /* note: checksum is calculated by the device */
+ }
+
+ /* UDP */
+ if (has_udp) {
+ udh->udp.sport = htons(QEDR_ROCE_V2_UDP_SPORT);
+ udh->udp.dport = htons(ROCE_V2_UDP_DPORT);
+ udh->udp.csum = 0;
+ /* UDP length is untouched hence is zero */
+ }
+ return 0;
+}
+
+static inline int qedr_gsi_build_packet(struct qedr_dev *dev,
+ struct qedr_qp *qp,
+ struct ib_send_wr *swr,
+ struct qed_roce_ll2_packet **p_packet)
+{
+ u8 ud_header_buffer[QEDR_MAX_UD_HEADER_SIZE];
+ struct qed_roce_ll2_packet *packet;
+ struct pci_dev *pdev = dev->pdev;
+ int roce_mode, header_size;
+ struct ib_ud_header udh;
+ int i, rc;
+
+ *p_packet = NULL;
+
+ rc = qedr_gsi_build_header(dev, qp, swr, &udh, &roce_mode);
+ if (rc)
+ return rc;
+
+ header_size = ib_ud_header_pack(&udh, &ud_header_buffer);
+
+ packet = kzalloc(sizeof(*packet), GFP_ATOMIC);
+ if (!packet)
+ return -ENOMEM;
+
+ packet->header.vaddr = dma_alloc_coherent(&pdev->dev, header_size,
+ &packet->header.baddr,
+ GFP_ATOMIC);
+ if (!packet->header.vaddr) {
+ kfree(packet);
+ return -ENOMEM;
+ }
+
+ if (ether_addr_equal(udh.eth.smac_h, udh.eth.dmac_h))
+ packet->tx_dest = QED_ROCE_LL2_TX_DEST_NW;
+ else
+ packet->tx_dest = QED_ROCE_LL2_TX_DEST_LB;
+
+ packet->roce_mode = roce_mode;
+ memcpy(packet->header.vaddr, ud_header_buffer, header_size);
+ packet->header.len = header_size;
+ packet->n_seg = swr->num_sge;
+ for (i = 0; i < packet->n_seg; i++) {
+ packet->payload[i].baddr = swr->sg_list[i].addr;
+ packet->payload[i].len = swr->sg_list[i].length;
+ }
+
+ *p_packet = packet;
+
+ return 0;
+}
+
+int qedr_gsi_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
+ struct ib_send_wr **bad_wr)
+{
+ struct qed_roce_ll2_packet *pkt = NULL;
+ struct qedr_qp *qp = get_qedr_qp(ibqp);
+ struct qed_roce_ll2_tx_params params;
+ struct qedr_dev *dev = qp->dev;
+ unsigned long flags;
+ int rc;
+
+ if (qp->state != QED_ROCE_QP_STATE_RTS) {
+ *bad_wr = wr;
+ DP_ERR(dev,
+ "gsi post recv: failed to post rx buffer. state is %d and not QED_ROCE_QP_STATE_RTS\n",
+ qp->state);
+ return -EINVAL;
+ }
+
+ if (wr->num_sge > RDMA_MAX_SGE_PER_SQ_WQE) {
+ DP_ERR(dev, "gsi post send: num_sge is too large (%d>%d)\n",
+ wr->num_sge, RDMA_MAX_SGE_PER_SQ_WQE);
+ rc = -EINVAL;
+ goto err;
+ }
+
+ if (wr->opcode != IB_WR_SEND) {
+ DP_ERR(dev,
+ "gsi post send: failed due to unsupported opcode %d\n",
+ wr->opcode);
+ rc = -EINVAL;
+ goto err;
+ }
+
+ memset(¶ms, 0, sizeof(params));
+
+ spin_lock_irqsave(&qp->q_lock, flags);
+
+ rc = qedr_gsi_build_packet(dev, qp, wr, &pkt);
+ if (rc) {
+ spin_unlock_irqrestore(&qp->q_lock, flags);
+ goto err;
+ }
+
+ rc = dev->ops->roce_ll2_tx(dev->cdev, pkt, ¶ms);
+ if (!rc) {
+ qp->wqe_wr_id[qp->sq.prod].wr_id = wr->wr_id;
+ qedr_inc_sw_prod(&qp->sq);
+ DP_DEBUG(qp->dev, QEDR_MSG_GSI,
+ "gsi post send: opcode=%d, in_irq=%ld, irqs_disabled=%d, wr_id=%llx\n",
+ wr->opcode, in_irq(), irqs_disabled(), wr->wr_id);
+ } else {
+ if (rc == QED_ROCE_TX_HEAD_FAILURE) {
+ /* TX failed while posting header - release resources */
+ dma_free_coherent(&dev->pdev->dev, pkt->header.len,
+ pkt->header.vaddr, pkt->header.baddr);
+ kfree(pkt);
+ } else if (rc == QED_ROCE_TX_FRAG_FAILURE) {
+ /* NTD since TX failed while posting a fragment. We will
+ * release the resources on TX callback
+ */
+ }
+
+ DP_ERR(dev, "gsi post send: failed to transmit (rc=%d)\n", rc);
+ rc = -EAGAIN;
+ *bad_wr = wr;
+ }
+
+ spin_unlock_irqrestore(&qp->q_lock, flags);
+
+ if (wr->next) {
+ DP_ERR(dev,
+ "gsi post send: failed second WR. Only one WR may be passed at a time\n");
+ *bad_wr = wr->next;
+ rc = -EINVAL;
+ }
+
+ return rc;
+
+err:
+ *bad_wr = wr;
+ return rc;
+}
+
+int qedr_gsi_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
+ struct ib_recv_wr **bad_wr)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibqp->device);
+ struct qedr_qp *qp = get_qedr_qp(ibqp);
+ struct qed_roce_ll2_buffer buf;
+ unsigned long flags;
+ int status = 0;
+ int rc;
+
+ if ((qp->state != QED_ROCE_QP_STATE_RTR) &&
+ (qp->state != QED_ROCE_QP_STATE_RTS)) {
+ *bad_wr = wr;
+ DP_ERR(dev,
+ "gsi post recv: failed to post rx buffer. state is %d and not QED_ROCE_QP_STATE_RTR/S\n",
+ qp->state);
+ return -EINVAL;
+ }
+
+ memset(&buf, 0, sizeof(buf));
+
+ spin_lock_irqsave(&qp->q_lock, flags);
+
+ while (wr) {
+ if (wr->num_sge > QEDR_GSI_MAX_RECV_SGE) {
+ DP_ERR(dev,
+ "gsi post recv: failed to post rx buffer. too many sges %d>%d\n",
+ wr->num_sge, QEDR_GSI_MAX_RECV_SGE);
+ goto err;
+ }
+
+ buf.baddr = wr->sg_list[0].addr;
+ buf.len = wr->sg_list[0].length;
+
+ rc = dev->ops->roce_ll2_post_rx_buffer(dev->cdev, &buf, 0, 1);
+ if (rc) {
+ DP_ERR(dev,
+ "gsi post recv: failed to post rx buffer (rc=%d)\n",
+ rc);
+ goto err;
+ }
+
+ memset(&qp->rqe_wr_id[qp->rq.prod], 0,
+ sizeof(qp->rqe_wr_id[qp->rq.prod]));
+ qp->rqe_wr_id[qp->rq.prod].sg_list[0] = wr->sg_list[0];
+ qp->rqe_wr_id[qp->rq.prod].wr_id = wr->wr_id;
+
+ qedr_inc_sw_prod(&qp->rq);
+
+ wr = wr->next;
+ }
+
+ spin_unlock_irqrestore(&qp->q_lock, flags);
+
+ return status;
+err:
+ spin_unlock_irqrestore(&qp->q_lock, flags);
+ *bad_wr = wr;
+ return -ENOMEM;
+}
+
+int qedr_gsi_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibcq->device);
+ struct qedr_cq *cq = get_qedr_cq(ibcq);
+ struct qedr_qp *qp = dev->gsi_qp;
+ unsigned long flags;
+ int i = 0;
+
+ spin_lock_irqsave(&cq->cq_lock, flags);
+
+ while (i < num_entries && qp->rq.cons != qp->rq.gsi_cons) {
+ memset(&wc[i], 0, sizeof(*wc));
+
+ wc[i].qp = &qp->ibqp;
+ wc[i].wr_id = qp->rqe_wr_id[qp->rq.cons].wr_id;
+ wc[i].opcode = IB_WC_RECV;
+ wc[i].pkey_index = 0;
+ wc[i].status = (qp->rqe_wr_id[qp->rq.cons].rc) ?
+ IB_WC_GENERAL_ERR : IB_WC_SUCCESS;
+ /* 0 - currently only one recv sg is supported */
+ wc[i].byte_len = qp->rqe_wr_id[qp->rq.cons].sg_list[0].length;
+ wc[i].wc_flags |= IB_WC_GRH | IB_WC_IP_CSUM_OK;
+ ether_addr_copy(wc[i].smac, qp->rqe_wr_id[qp->rq.cons].smac);
+ wc[i].wc_flags |= IB_WC_WITH_SMAC;
+ if (qp->rqe_wr_id[qp->rq.cons].vlan_id) {
+ wc[i].wc_flags |= IB_WC_WITH_VLAN;
+ wc[i].vlan_id = qp->rqe_wr_id[qp->rq.cons].vlan_id;
+ }
+
+ qedr_inc_sw_cons(&qp->rq);
+ i++;
+ }
+
+ while (i < num_entries && qp->sq.cons != qp->sq.gsi_cons) {
+ memset(&wc[i], 0, sizeof(*wc));
+
+ wc[i].qp = &qp->ibqp;
+ wc[i].wr_id = qp->wqe_wr_id[qp->sq.cons].wr_id;
+ wc[i].opcode = IB_WC_SEND;
+ wc[i].status = IB_WC_SUCCESS;
+
+ qedr_inc_sw_cons(&qp->sq);
+ i++;
+ }
+
+ spin_unlock_irqrestore(&cq->cq_lock, flags);
+
+ DP_DEBUG(dev, QEDR_MSG_GSI,
+ "gsi poll_cq: requested entries=%d, actual=%d, qp->rq.cons=%d, qp->rq.gsi_cons=%x, qp->sq.cons=%d, qp->sq.gsi_cons=%d, qp_num=%d\n",
+ num_entries, i, qp->rq.cons, qp->rq.gsi_cons, qp->sq.cons,
+ qp->sq.gsi_cons, qp->ibqp.qp_num);
+
+ return i;
+}
diff --git a/drivers/infiniband/hw/qedr/qedr_cm.h b/drivers/infiniband/hw/qedr/qedr_cm.h
new file mode 100644
index 0000000..9ba6e15
--- /dev/null
+++ b/drivers/infiniband/hw/qedr/qedr_cm.h
@@ -0,0 +1,61 @@
+/* QLogic qedr NIC Driver
+ * Copyright (c) 2015-2016 QLogic Corporation
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and /or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef LINUX_QEDR_CM_H_
+#define LINUX_QEDR_CM_H_
+
+#define QEDR_GSI_MAX_RECV_WR (4096)
+#define QEDR_GSI_MAX_SEND_WR (4096)
+
+#define QEDR_GSI_MAX_RECV_SGE (1) /* LL2 FW limitation */
+
+#define ETH_P_ROCE (0x8915)
+#define QEDR_ROCE_V2_UDP_SPORT (0000)
+
+static inline u32 qedr_get_ipv4_from_gid(u8 *gid)
+{
+ return *(u32 *)(void *)&gid[12];
+}
+
+/* RDMA CM */
+int qedr_gsi_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
+int qedr_gsi_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
+ struct ib_recv_wr **bad_wr);
+int qedr_gsi_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
+ struct ib_send_wr **bad_wr);
+struct ib_qp *qedr_create_gsi_qp(struct qedr_dev *dev,
+ struct ib_qp_init_attr *attrs,
+ struct qedr_qp *qp);
+void qedr_store_gsi_qp_cq(struct qedr_dev *dev,
+ struct qedr_qp *qp, struct ib_qp_init_attr *attrs);
+int qedr_destroy_gsi_qp(struct qedr_dev *dev);
+void qedr_inc_sw_gsi_cons(struct qedr_qp_hwq_info *info);
+#endif
diff --git a/drivers/infiniband/hw/qedr/qedr_hsi.h b/drivers/infiniband/hw/qedr/qedr_hsi.h
new file mode 100644
index 0000000..66d2752
--- /dev/null
+++ b/drivers/infiniband/hw/qedr/qedr_hsi.h
@@ -0,0 +1,56 @@
+/* QLogic qedr NIC Driver
+ * Copyright (c) 2015-2016 QLogic Corporation
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and /or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef __QED_HSI_ROCE__
+#define __QED_HSI_ROCE__
+
+#include <linux/qed/common_hsi.h>
+#include <linux/qed/roce_common.h>
+#include "qedr_hsi_rdma.h"
+
+/* Affiliated asynchronous events / errors enumeration */
+enum roce_async_events_type {
+ ROCE_ASYNC_EVENT_NONE = 0,
+ ROCE_ASYNC_EVENT_COMM_EST = 1,
+ ROCE_ASYNC_EVENT_SQ_DRAINED,
+ ROCE_ASYNC_EVENT_SRQ_LIMIT,
+ ROCE_ASYNC_EVENT_LAST_WQE_REACHED,
+ ROCE_ASYNC_EVENT_CQ_ERR,
+ ROCE_ASYNC_EVENT_LOCAL_INVALID_REQUEST_ERR,
+ ROCE_ASYNC_EVENT_LOCAL_CATASTROPHIC_ERR,
+ ROCE_ASYNC_EVENT_LOCAL_ACCESS_ERR,
+ ROCE_ASYNC_EVENT_QP_CATASTROPHIC_ERR,
+ ROCE_ASYNC_EVENT_CQ_OVERFLOW_ERR,
+ ROCE_ASYNC_EVENT_SRQ_EMPTY,
+ MAX_ROCE_ASYNC_EVENTS_TYPE
+};
+
+#endif /* __QED_HSI_ROCE__ */
diff --git a/drivers/infiniband/hw/qedr/qedr_hsi_rdma.h b/drivers/infiniband/hw/qedr/qedr_hsi_rdma.h
new file mode 100644
index 0000000..5c98d20
--- /dev/null
+++ b/drivers/infiniband/hw/qedr/qedr_hsi_rdma.h
@@ -0,0 +1,748 @@
+/* QLogic qedr NIC Driver
+ * Copyright (c) 2015-2016 QLogic Corporation
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and /or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef __QED_HSI_RDMA__
+#define __QED_HSI_RDMA__
+
+#include <linux/qed/rdma_common.h>
+
+/* rdma completion notification queue element */
+struct rdma_cnqe {
+ struct regpair cq_handle;
+};
+
+struct rdma_cqe_responder {
+ struct regpair srq_wr_id;
+ struct regpair qp_handle;
+ __le32 imm_data_or_inv_r_Key;
+ __le32 length;
+ __le32 imm_data_hi;
+ __le16 rq_cons;
+ u8 flags;
+#define RDMA_CQE_RESPONDER_TOGGLE_BIT_MASK 0x1
+#define RDMA_CQE_RESPONDER_TOGGLE_BIT_SHIFT 0
+#define RDMA_CQE_RESPONDER_TYPE_MASK 0x3
+#define RDMA_CQE_RESPONDER_TYPE_SHIFT 1
+#define RDMA_CQE_RESPONDER_INV_FLG_MASK 0x1
+#define RDMA_CQE_RESPONDER_INV_FLG_SHIFT 3
+#define RDMA_CQE_RESPONDER_IMM_FLG_MASK 0x1
+#define RDMA_CQE_RESPONDER_IMM_FLG_SHIFT 4
+#define RDMA_CQE_RESPONDER_RDMA_FLG_MASK 0x1
+#define RDMA_CQE_RESPONDER_RDMA_FLG_SHIFT 5
+#define RDMA_CQE_RESPONDER_RESERVED2_MASK 0x3
+#define RDMA_CQE_RESPONDER_RESERVED2_SHIFT 6
+ u8 status;
+};
+
+struct rdma_cqe_requester {
+ __le16 sq_cons;
+ __le16 reserved0;
+ __le32 reserved1;
+ struct regpair qp_handle;
+ struct regpair reserved2;
+ __le32 reserved3;
+ __le16 reserved4;
+ u8 flags;
+#define RDMA_CQE_REQUESTER_TOGGLE_BIT_MASK 0x1
+#define RDMA_CQE_REQUESTER_TOGGLE_BIT_SHIFT 0
+#define RDMA_CQE_REQUESTER_TYPE_MASK 0x3
+#define RDMA_CQE_REQUESTER_TYPE_SHIFT 1
+#define RDMA_CQE_REQUESTER_RESERVED5_MASK 0x1F
+#define RDMA_CQE_REQUESTER_RESERVED5_SHIFT 3
+ u8 status;
+};
+
+struct rdma_cqe_common {
+ struct regpair reserved0;
+ struct regpair qp_handle;
+ __le16 reserved1[7];
+ u8 flags;
+#define RDMA_CQE_COMMON_TOGGLE_BIT_MASK 0x1
+#define RDMA_CQE_COMMON_TOGGLE_BIT_SHIFT 0
+#define RDMA_CQE_COMMON_TYPE_MASK 0x3
+#define RDMA_CQE_COMMON_TYPE_SHIFT 1
+#define RDMA_CQE_COMMON_RESERVED2_MASK 0x1F
+#define RDMA_CQE_COMMON_RESERVED2_SHIFT 3
+ u8 status;
+};
+
+/* rdma completion queue element */
+union rdma_cqe {
+ struct rdma_cqe_responder resp;
+ struct rdma_cqe_requester req;
+ struct rdma_cqe_common cmn;
+};
+
+/* * CQE requester status enumeration */
+enum rdma_cqe_requester_status_enum {
+ RDMA_CQE_REQ_STS_OK,
+ RDMA_CQE_REQ_STS_BAD_RESPONSE_ERR,
+ RDMA_CQE_REQ_STS_LOCAL_LENGTH_ERR,
+ RDMA_CQE_REQ_STS_LOCAL_QP_OPERATION_ERR,
+ RDMA_CQE_REQ_STS_LOCAL_PROTECTION_ERR,
+ RDMA_CQE_REQ_STS_MEMORY_MGT_OPERATION_ERR,
+ RDMA_CQE_REQ_STS_REMOTE_INVALID_REQUEST_ERR,
+ RDMA_CQE_REQ_STS_REMOTE_ACCESS_ERR,
+ RDMA_CQE_REQ_STS_REMOTE_OPERATION_ERR,
+ RDMA_CQE_REQ_STS_RNR_NAK_RETRY_CNT_ERR,
+ RDMA_CQE_REQ_STS_TRANSPORT_RETRY_CNT_ERR,
+ RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR,
+ MAX_RDMA_CQE_REQUESTER_STATUS_ENUM
+};
+
+/* CQE responder status enumeration */
+enum rdma_cqe_responder_status_enum {
+ RDMA_CQE_RESP_STS_OK,
+ RDMA_CQE_RESP_STS_LOCAL_ACCESS_ERR,
+ RDMA_CQE_RESP_STS_LOCAL_LENGTH_ERR,
+ RDMA_CQE_RESP_STS_LOCAL_QP_OPERATION_ERR,
+ RDMA_CQE_RESP_STS_LOCAL_PROTECTION_ERR,
+ RDMA_CQE_RESP_STS_MEMORY_MGT_OPERATION_ERR,
+ RDMA_CQE_RESP_STS_REMOTE_INVALID_REQUEST_ERR,
+ RDMA_CQE_RESP_STS_WORK_REQUEST_FLUSHED_ERR,
+ MAX_RDMA_CQE_RESPONDER_STATUS_ENUM
+};
+
+/* CQE type enumeration */
+enum rdma_cqe_type {
+ RDMA_CQE_TYPE_REQUESTER,
+ RDMA_CQE_TYPE_RESPONDER_RQ,
+ RDMA_CQE_TYPE_RESPONDER_SRQ,
+ RDMA_CQE_TYPE_INVALID,
+ MAX_RDMA_CQE_TYPE
+};
+
+struct rdma_sq_sge {
+ __le32 length;
+ struct regpair addr;
+ __le32 l_key;
+};
+
+struct rdma_rq_sge {
+ struct regpair addr;
+ __le32 length;
+ __le32 flags;
+#define RDMA_RQ_SGE_L_KEY_MASK 0x3FFFFFF
+#define RDMA_RQ_SGE_L_KEY_SHIFT 0
+#define RDMA_RQ_SGE_NUM_SGES_MASK 0x7
+#define RDMA_RQ_SGE_NUM_SGES_SHIFT 26
+#define RDMA_RQ_SGE_RESERVED0_MASK 0x7
+#define RDMA_RQ_SGE_RESERVED0_SHIFT 29
+};
+
+struct rdma_srq_sge {
+ struct regpair addr;
+ __le32 length;
+ __le32 l_key;
+};
+
+/* Rdma doorbell data for SQ and RQ */
+struct rdma_pwm_val16_data {
+ __le16 icid;
+ __le16 value;
+};
+
+union rdma_pwm_val16_data_union {
+ struct rdma_pwm_val16_data as_struct;
+ __le32 as_dword;
+};
+
+/* Rdma doorbell data for CQ */
+struct rdma_pwm_val32_data {
+ __le16 icid;
+ u8 agg_flags;
+ u8 params;
+#define RDMA_PWM_VAL32_DATA_AGG_CMD_MASK 0x3
+#define RDMA_PWM_VAL32_DATA_AGG_CMD_SHIFT 0
+#define RDMA_PWM_VAL32_DATA_BYPASS_EN_MASK 0x1
+#define RDMA_PWM_VAL32_DATA_BYPASS_EN_SHIFT 2
+#define RDMA_PWM_VAL32_DATA_RESERVED_MASK 0x1F
+#define RDMA_PWM_VAL32_DATA_RESERVED_SHIFT 3
+ __le32 value;
+};
+
+/* DIF Block size options */
+enum rdma_dif_block_size {
+ RDMA_DIF_BLOCK_512 = 0,
+ RDMA_DIF_BLOCK_4096 = 1,
+ MAX_RDMA_DIF_BLOCK_SIZE
+};
+
+/* DIF CRC initial value */
+enum rdma_dif_crc_seed {
+ RDMA_DIF_CRC_SEED_0000 = 0,
+ RDMA_DIF_CRC_SEED_FFFF = 1,
+ MAX_RDMA_DIF_CRC_SEED
+};
+
+/* RDMA DIF Error Result Structure */
+struct rdma_dif_error_result {
+ __le32 error_intervals;
+ __le32 dif_error_1st_interval;
+ u8 flags;
+#define RDMA_DIF_ERROR_RESULT_DIF_ERROR_TYPE_CRC_MASK 0x1
+#define RDMA_DIF_ERROR_RESULT_DIF_ERROR_TYPE_CRC_SHIFT 0
+#define RDMA_DIF_ERROR_RESULT_DIF_ERROR_TYPE_APP_TAG_MASK 0x1
+#define RDMA_DIF_ERROR_RESULT_DIF_ERROR_TYPE_APP_TAG_SHIFT 1
+#define RDMA_DIF_ERROR_RESULT_DIF_ERROR_TYPE_REF_TAG_MASK 0x1
+#define RDMA_DIF_ERROR_RESULT_DIF_ERROR_TYPE_REF_TAG_SHIFT 2
+#define RDMA_DIF_ERROR_RESULT_RESERVED0_MASK 0xF
+#define RDMA_DIF_ERROR_RESULT_RESERVED0_SHIFT 3
+#define RDMA_DIF_ERROR_RESULT_TOGGLE_BIT_MASK 0x1
+#define RDMA_DIF_ERROR_RESULT_TOGGLE_BIT_SHIFT 7
+ u8 reserved1[55];
+};
+
+/* DIF IO direction */
+enum rdma_dif_io_direction_flg {
+ RDMA_DIF_DIR_RX = 0,
+ RDMA_DIF_DIR_TX = 1,
+ MAX_RDMA_DIF_IO_DIRECTION_FLG
+};
+
+/* RDMA DIF Runt Result Structure */
+struct rdma_dif_runt_result {
+ __le16 guard_tag;
+ __le16 reserved[3];
+};
+
+/* Memory window type enumeration */
+enum rdma_mw_type {
+ RDMA_MW_TYPE_1,
+ RDMA_MW_TYPE_2A,
+ MAX_RDMA_MW_TYPE
+};
+
+struct rdma_sq_atomic_wqe {
+ __le32 reserved1;
+ __le32 length;
+ __le32 xrc_srq;
+ u8 req_type;
+ u8 flags;
+#define RDMA_SQ_ATOMIC_WQE_COMP_FLG_MASK 0x1
+#define RDMA_SQ_ATOMIC_WQE_COMP_FLG_SHIFT 0
+#define RDMA_SQ_ATOMIC_WQE_RD_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_ATOMIC_WQE_RD_FENCE_FLG_SHIFT 1
+#define RDMA_SQ_ATOMIC_WQE_INV_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_ATOMIC_WQE_INV_FENCE_FLG_SHIFT 2
+#define RDMA_SQ_ATOMIC_WQE_SE_FLG_MASK 0x1
+#define RDMA_SQ_ATOMIC_WQE_SE_FLG_SHIFT 3
+#define RDMA_SQ_ATOMIC_WQE_INLINE_FLG_MASK 0x1
+#define RDMA_SQ_ATOMIC_WQE_INLINE_FLG_SHIFT 4
+#define RDMA_SQ_ATOMIC_WQE_DIF_ON_HOST_FLG_MASK 0x1
+#define RDMA_SQ_ATOMIC_WQE_DIF_ON_HOST_FLG_SHIFT 5
+#define RDMA_SQ_ATOMIC_WQE_RESERVED0_MASK 0x3
+#define RDMA_SQ_ATOMIC_WQE_RESERVED0_SHIFT 6
+ u8 wqe_size;
+ u8 prev_wqe_size;
+ struct regpair remote_va;
+ __le32 r_key;
+ __le32 reserved2;
+ struct regpair cmp_data;
+ struct regpair swap_data;
+};
+
+/* First element (16 bytes) of atomic wqe */
+struct rdma_sq_atomic_wqe_1st {
+ __le32 reserved1;
+ __le32 length;
+ __le32 xrc_srq;
+ u8 req_type;
+ u8 flags;
+#define RDMA_SQ_ATOMIC_WQE_1ST_COMP_FLG_MASK 0x1
+#define RDMA_SQ_ATOMIC_WQE_1ST_COMP_FLG_SHIFT 0
+#define RDMA_SQ_ATOMIC_WQE_1ST_RD_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_ATOMIC_WQE_1ST_RD_FENCE_FLG_SHIFT 1
+#define RDMA_SQ_ATOMIC_WQE_1ST_INV_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_ATOMIC_WQE_1ST_INV_FENCE_FLG_SHIFT 2
+#define RDMA_SQ_ATOMIC_WQE_1ST_SE_FLG_MASK 0x1
+#define RDMA_SQ_ATOMIC_WQE_1ST_SE_FLG_SHIFT 3
+#define RDMA_SQ_ATOMIC_WQE_1ST_INLINE_FLG_MASK 0x1
+#define RDMA_SQ_ATOMIC_WQE_1ST_INLINE_FLG_SHIFT 4
+#define RDMA_SQ_ATOMIC_WQE_1ST_RESERVED0_MASK 0x7
+#define RDMA_SQ_ATOMIC_WQE_1ST_RESERVED0_SHIFT 5
+ u8 wqe_size;
+ u8 prev_wqe_size;
+};
+
+/* Second element (16 bytes) of atomic wqe */
+struct rdma_sq_atomic_wqe_2nd {
+ struct regpair remote_va;
+ __le32 r_key;
+ __le32 reserved2;
+};
+
+/* Third element (16 bytes) of atomic wqe */
+struct rdma_sq_atomic_wqe_3rd {
+ struct regpair cmp_data;
+ struct regpair swap_data;
+};
+
+struct rdma_sq_bind_wqe {
+ struct regpair addr;
+ __le32 l_key;
+ u8 req_type;
+ u8 flags;
+#define RDMA_SQ_BIND_WQE_COMP_FLG_MASK 0x1
+#define RDMA_SQ_BIND_WQE_COMP_FLG_SHIFT 0
+#define RDMA_SQ_BIND_WQE_RD_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_BIND_WQE_RD_FENCE_FLG_SHIFT 1
+#define RDMA_SQ_BIND_WQE_INV_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_BIND_WQE_INV_FENCE_FLG_SHIFT 2
+#define RDMA_SQ_BIND_WQE_SE_FLG_MASK 0x1
+#define RDMA_SQ_BIND_WQE_SE_FLG_SHIFT 3
+#define RDMA_SQ_BIND_WQE_INLINE_FLG_MASK 0x1
+#define RDMA_SQ_BIND_WQE_INLINE_FLG_SHIFT 4
+#define RDMA_SQ_BIND_WQE_RESERVED0_MASK 0x7
+#define RDMA_SQ_BIND_WQE_RESERVED0_SHIFT 5
+ u8 wqe_size;
+ u8 prev_wqe_size;
+ u8 bind_ctrl;
+#define RDMA_SQ_BIND_WQE_ZERO_BASED_MASK 0x1
+#define RDMA_SQ_BIND_WQE_ZERO_BASED_SHIFT 0
+#define RDMA_SQ_BIND_WQE_MW_TYPE_MASK 0x1
+#define RDMA_SQ_BIND_WQE_MW_TYPE_SHIFT 1
+#define RDMA_SQ_BIND_WQE_RESERVED1_MASK 0x3F
+#define RDMA_SQ_BIND_WQE_RESERVED1_SHIFT 2
+ u8 access_ctrl;
+#define RDMA_SQ_BIND_WQE_REMOTE_READ_MASK 0x1
+#define RDMA_SQ_BIND_WQE_REMOTE_READ_SHIFT 0
+#define RDMA_SQ_BIND_WQE_REMOTE_WRITE_MASK 0x1
+#define RDMA_SQ_BIND_WQE_REMOTE_WRITE_SHIFT 1
+#define RDMA_SQ_BIND_WQE_ENABLE_ATOMIC_MASK 0x1
+#define RDMA_SQ_BIND_WQE_ENABLE_ATOMIC_SHIFT 2
+#define RDMA_SQ_BIND_WQE_LOCAL_READ_MASK 0x1
+#define RDMA_SQ_BIND_WQE_LOCAL_READ_SHIFT 3
+#define RDMA_SQ_BIND_WQE_LOCAL_WRITE_MASK 0x1
+#define RDMA_SQ_BIND_WQE_LOCAL_WRITE_SHIFT 4
+#define RDMA_SQ_BIND_WQE_RESERVED2_MASK 0x7
+#define RDMA_SQ_BIND_WQE_RESERVED2_SHIFT 5
+ u8 reserved3;
+ u8 length_hi;
+ __le32 length_lo;
+ __le32 parent_l_key;
+ __le32 reserved4;
+};
+
+/* First element (16 bytes) of bind wqe */
+struct rdma_sq_bind_wqe_1st {
+ struct regpair addr;
+ __le32 l_key;
+ u8 req_type;
+ u8 flags;
+#define RDMA_SQ_BIND_WQE_1ST_COMP_FLG_MASK 0x1
+#define RDMA_SQ_BIND_WQE_1ST_COMP_FLG_SHIFT 0
+#define RDMA_SQ_BIND_WQE_1ST_RD_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_BIND_WQE_1ST_RD_FENCE_FLG_SHIFT 1
+#define RDMA_SQ_BIND_WQE_1ST_INV_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_BIND_WQE_1ST_INV_FENCE_FLG_SHIFT 2
+#define RDMA_SQ_BIND_WQE_1ST_SE_FLG_MASK 0x1
+#define RDMA_SQ_BIND_WQE_1ST_SE_FLG_SHIFT 3
+#define RDMA_SQ_BIND_WQE_1ST_INLINE_FLG_MASK 0x1
+#define RDMA_SQ_BIND_WQE_1ST_INLINE_FLG_SHIFT 4
+#define RDMA_SQ_BIND_WQE_1ST_RESERVED0_MASK 0x7
+#define RDMA_SQ_BIND_WQE_1ST_RESERVED0_SHIFT 5
+ u8 wqe_size;
+ u8 prev_wqe_size;
+};
+
+/* Second element (16 bytes) of bind wqe */
+struct rdma_sq_bind_wqe_2nd {
+ u8 bind_ctrl;
+#define RDMA_SQ_BIND_WQE_2ND_ZERO_BASED_MASK 0x1
+#define RDMA_SQ_BIND_WQE_2ND_ZERO_BASED_SHIFT 0
+#define RDMA_SQ_BIND_WQE_2ND_MW_TYPE_MASK 0x1
+#define RDMA_SQ_BIND_WQE_2ND_MW_TYPE_SHIFT 1
+#define RDMA_SQ_BIND_WQE_2ND_RESERVED1_MASK 0x3F
+#define RDMA_SQ_BIND_WQE_2ND_RESERVED1_SHIFT 2
+ u8 access_ctrl;
+#define RDMA_SQ_BIND_WQE_2ND_REMOTE_READ_MASK 0x1
+#define RDMA_SQ_BIND_WQE_2ND_REMOTE_READ_SHIFT 0
+#define RDMA_SQ_BIND_WQE_2ND_REMOTE_WRITE_MASK 0x1
+#define RDMA_SQ_BIND_WQE_2ND_REMOTE_WRITE_SHIFT 1
+#define RDMA_SQ_BIND_WQE_2ND_ENABLE_ATOMIC_MASK 0x1
+#define RDMA_SQ_BIND_WQE_2ND_ENABLE_ATOMIC_SHIFT 2
+#define RDMA_SQ_BIND_WQE_2ND_LOCAL_READ_MASK 0x1
+#define RDMA_SQ_BIND_WQE_2ND_LOCAL_READ_SHIFT 3
+#define RDMA_SQ_BIND_WQE_2ND_LOCAL_WRITE_MASK 0x1
+#define RDMA_SQ_BIND_WQE_2ND_LOCAL_WRITE_SHIFT 4
+#define RDMA_SQ_BIND_WQE_2ND_RESERVED2_MASK 0x7
+#define RDMA_SQ_BIND_WQE_2ND_RESERVED2_SHIFT 5
+ u8 reserved3;
+ u8 length_hi;
+ __le32 length_lo;
+ __le32 parent_l_key;
+ __le32 reserved4;
+};
+
+/* Structure with only the SQ WQE common
+ * fields. Size is of one SQ element (16B)
+ */
+struct rdma_sq_common_wqe {
+ __le32 reserved1[3];
+ u8 req_type;
+ u8 flags;
+#define RDMA_SQ_COMMON_WQE_COMP_FLG_MASK 0x1
+#define RDMA_SQ_COMMON_WQE_COMP_FLG_SHIFT 0
+#define RDMA_SQ_COMMON_WQE_RD_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_COMMON_WQE_RD_FENCE_FLG_SHIFT 1
+#define RDMA_SQ_COMMON_WQE_INV_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_COMMON_WQE_INV_FENCE_FLG_SHIFT 2
+#define RDMA_SQ_COMMON_WQE_SE_FLG_MASK 0x1
+#define RDMA_SQ_COMMON_WQE_SE_FLG_SHIFT 3
+#define RDMA_SQ_COMMON_WQE_INLINE_FLG_MASK 0x1
+#define RDMA_SQ_COMMON_WQE_INLINE_FLG_SHIFT 4
+#define RDMA_SQ_COMMON_WQE_RESERVED0_MASK 0x7
+#define RDMA_SQ_COMMON_WQE_RESERVED0_SHIFT 5
+ u8 wqe_size;
+ u8 prev_wqe_size;
+};
+
+struct rdma_sq_fmr_wqe {
+ struct regpair addr;
+ __le32 l_key;
+ u8 req_type;
+ u8 flags;
+#define RDMA_SQ_FMR_WQE_COMP_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_COMP_FLG_SHIFT 0
+#define RDMA_SQ_FMR_WQE_RD_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_RD_FENCE_FLG_SHIFT 1
+#define RDMA_SQ_FMR_WQE_INV_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_INV_FENCE_FLG_SHIFT 2
+#define RDMA_SQ_FMR_WQE_SE_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_SE_FLG_SHIFT 3
+#define RDMA_SQ_FMR_WQE_INLINE_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_INLINE_FLG_SHIFT 4
+#define RDMA_SQ_FMR_WQE_DIF_ON_HOST_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_DIF_ON_HOST_FLG_SHIFT 5
+#define RDMA_SQ_FMR_WQE_RESERVED0_MASK 0x3
+#define RDMA_SQ_FMR_WQE_RESERVED0_SHIFT 6
+ u8 wqe_size;
+ u8 prev_wqe_size;
+ u8 fmr_ctrl;
+#define RDMA_SQ_FMR_WQE_PAGE_SIZE_LOG_MASK 0x1F
+#define RDMA_SQ_FMR_WQE_PAGE_SIZE_LOG_SHIFT 0
+#define RDMA_SQ_FMR_WQE_ZERO_BASED_MASK 0x1
+#define RDMA_SQ_FMR_WQE_ZERO_BASED_SHIFT 5
+#define RDMA_SQ_FMR_WQE_BIND_EN_MASK 0x1
+#define RDMA_SQ_FMR_WQE_BIND_EN_SHIFT 6
+#define RDMA_SQ_FMR_WQE_RESERVED1_MASK 0x1
+#define RDMA_SQ_FMR_WQE_RESERVED1_SHIFT 7
+ u8 access_ctrl;
+#define RDMA_SQ_FMR_WQE_REMOTE_READ_MASK 0x1
+#define RDMA_SQ_FMR_WQE_REMOTE_READ_SHIFT 0
+#define RDMA_SQ_FMR_WQE_REMOTE_WRITE_MASK 0x1
+#define RDMA_SQ_FMR_WQE_REMOTE_WRITE_SHIFT 1
+#define RDMA_SQ_FMR_WQE_ENABLE_ATOMIC_MASK 0x1
+#define RDMA_SQ_FMR_WQE_ENABLE_ATOMIC_SHIFT 2
+#define RDMA_SQ_FMR_WQE_LOCAL_READ_MASK 0x1
+#define RDMA_SQ_FMR_WQE_LOCAL_READ_SHIFT 3
+#define RDMA_SQ_FMR_WQE_LOCAL_WRITE_MASK 0x1
+#define RDMA_SQ_FMR_WQE_LOCAL_WRITE_SHIFT 4
+#define RDMA_SQ_FMR_WQE_RESERVED2_MASK 0x7
+#define RDMA_SQ_FMR_WQE_RESERVED2_SHIFT 5
+ u8 reserved3;
+ u8 length_hi;
+ __le32 length_lo;
+ struct regpair pbl_addr;
+ __le32 dif_base_ref_tag;
+ __le16 dif_app_tag;
+ __le16 dif_app_tag_mask;
+ __le16 dif_runt_crc_value;
+ __le16 dif_flags;
+#define RDMA_SQ_FMR_WQE_DIF_IO_DIRECTION_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_DIF_IO_DIRECTION_FLG_SHIFT 0
+#define RDMA_SQ_FMR_WQE_DIF_BLOCK_SIZE_MASK 0x1
+#define RDMA_SQ_FMR_WQE_DIF_BLOCK_SIZE_SHIFT 1
+#define RDMA_SQ_FMR_WQE_DIF_RUNT_VALID_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_DIF_RUNT_VALID_FLG_SHIFT 2
+#define RDMA_SQ_FMR_WQE_DIF_VALIDATE_CRC_GUARD_MASK 0x1
+#define RDMA_SQ_FMR_WQE_DIF_VALIDATE_CRC_GUARD_SHIFT 3
+#define RDMA_SQ_FMR_WQE_DIF_VALIDATE_REF_TAG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_DIF_VALIDATE_REF_TAG_SHIFT 4
+#define RDMA_SQ_FMR_WQE_DIF_VALIDATE_APP_TAG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_DIF_VALIDATE_APP_TAG_SHIFT 5
+#define RDMA_SQ_FMR_WQE_DIF_CRC_SEED_MASK 0x1
+#define RDMA_SQ_FMR_WQE_DIF_CRC_SEED_SHIFT 6
+#define RDMA_SQ_FMR_WQE_RESERVED4_MASK 0x1FF
+#define RDMA_SQ_FMR_WQE_RESERVED4_SHIFT 7
+ __le32 Reserved5;
+};
+
+/* First element (16 bytes) of fmr wqe */
+struct rdma_sq_fmr_wqe_1st {
+ struct regpair addr;
+ __le32 l_key;
+ u8 req_type;
+ u8 flags;
+#define RDMA_SQ_FMR_WQE_1ST_COMP_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_1ST_COMP_FLG_SHIFT 0
+#define RDMA_SQ_FMR_WQE_1ST_RD_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_1ST_RD_FENCE_FLG_SHIFT 1
+#define RDMA_SQ_FMR_WQE_1ST_INV_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_1ST_INV_FENCE_FLG_SHIFT 2
+#define RDMA_SQ_FMR_WQE_1ST_SE_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_1ST_SE_FLG_SHIFT 3
+#define RDMA_SQ_FMR_WQE_1ST_INLINE_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_1ST_INLINE_FLG_SHIFT 4
+#define RDMA_SQ_FMR_WQE_1ST_DIF_ON_HOST_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_1ST_DIF_ON_HOST_FLG_SHIFT 5
+#define RDMA_SQ_FMR_WQE_1ST_RESERVED0_MASK 0x3
+#define RDMA_SQ_FMR_WQE_1ST_RESERVED0_SHIFT 6
+ u8 wqe_size;
+ u8 prev_wqe_size;
+};
+
+/* Second element (16 bytes) of fmr wqe */
+struct rdma_sq_fmr_wqe_2nd {
+ u8 fmr_ctrl;
+#define RDMA_SQ_FMR_WQE_2ND_PAGE_SIZE_LOG_MASK 0x1F
+#define RDMA_SQ_FMR_WQE_2ND_PAGE_SIZE_LOG_SHIFT 0
+#define RDMA_SQ_FMR_WQE_2ND_ZERO_BASED_MASK 0x1
+#define RDMA_SQ_FMR_WQE_2ND_ZERO_BASED_SHIFT 5
+#define RDMA_SQ_FMR_WQE_2ND_BIND_EN_MASK 0x1
+#define RDMA_SQ_FMR_WQE_2ND_BIND_EN_SHIFT 6
+#define RDMA_SQ_FMR_WQE_2ND_RESERVED1_MASK 0x1
+#define RDMA_SQ_FMR_WQE_2ND_RESERVED1_SHIFT 7
+ u8 access_ctrl;
+#define RDMA_SQ_FMR_WQE_2ND_REMOTE_READ_MASK 0x1
+#define RDMA_SQ_FMR_WQE_2ND_REMOTE_READ_SHIFT 0
+#define RDMA_SQ_FMR_WQE_2ND_REMOTE_WRITE_MASK 0x1
+#define RDMA_SQ_FMR_WQE_2ND_REMOTE_WRITE_SHIFT 1
+#define RDMA_SQ_FMR_WQE_2ND_ENABLE_ATOMIC_MASK 0x1
+#define RDMA_SQ_FMR_WQE_2ND_ENABLE_ATOMIC_SHIFT 2
+#define RDMA_SQ_FMR_WQE_2ND_LOCAL_READ_MASK 0x1
+#define RDMA_SQ_FMR_WQE_2ND_LOCAL_READ_SHIFT 3
+#define RDMA_SQ_FMR_WQE_2ND_LOCAL_WRITE_MASK 0x1
+#define RDMA_SQ_FMR_WQE_2ND_LOCAL_WRITE_SHIFT 4
+#define RDMA_SQ_FMR_WQE_2ND_RESERVED2_MASK 0x7
+#define RDMA_SQ_FMR_WQE_2ND_RESERVED2_SHIFT 5
+ u8 reserved3;
+ u8 length_hi;
+ __le32 length_lo;
+ struct regpair pbl_addr;
+};
+
+/* Third element (16 bytes) of fmr wqe */
+struct rdma_sq_fmr_wqe_3rd {
+ __le32 dif_base_ref_tag;
+ __le16 dif_app_tag;
+ __le16 dif_app_tag_mask;
+ __le16 dif_runt_crc_value;
+ __le16 dif_flags;
+#define RDMA_SQ_FMR_WQE_3RD_DIF_IO_DIRECTION_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_3RD_DIF_IO_DIRECTION_FLG_SHIFT 0
+#define RDMA_SQ_FMR_WQE_3RD_DIF_BLOCK_SIZE_MASK 0x1
+#define RDMA_SQ_FMR_WQE_3RD_DIF_BLOCK_SIZE_SHIFT 1
+#define RDMA_SQ_FMR_WQE_3RD_DIF_RUNT_VALID_FLG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_3RD_DIF_RUNT_VALID_FLG_SHIFT 2
+#define RDMA_SQ_FMR_WQE_3RD_DIF_VALIDATE_CRC_GUARD_MASK 0x1
+#define RDMA_SQ_FMR_WQE_3RD_DIF_VALIDATE_CRC_GUARD_SHIFT 3
+#define RDMA_SQ_FMR_WQE_3RD_DIF_VALIDATE_REF_TAG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_3RD_DIF_VALIDATE_REF_TAG_SHIFT 4
+#define RDMA_SQ_FMR_WQE_3RD_DIF_VALIDATE_APP_TAG_MASK 0x1
+#define RDMA_SQ_FMR_WQE_3RD_DIF_VALIDATE_APP_TAG_SHIFT 5
+#define RDMA_SQ_FMR_WQE_3RD_DIF_CRC_SEED_MASK 0x1
+#define RDMA_SQ_FMR_WQE_3RD_DIF_CRC_SEED_SHIFT 6
+#define RDMA_SQ_FMR_WQE_3RD_RESERVED4_MASK 0x1FF
+#define RDMA_SQ_FMR_WQE_3RD_RESERVED4_SHIFT 7
+ __le32 Reserved5;
+};
+
+struct rdma_sq_local_inv_wqe {
+ struct regpair reserved;
+ __le32 inv_l_key;
+ u8 req_type;
+ u8 flags;
+#define RDMA_SQ_LOCAL_INV_WQE_COMP_FLG_MASK 0x1
+#define RDMA_SQ_LOCAL_INV_WQE_COMP_FLG_SHIFT 0
+#define RDMA_SQ_LOCAL_INV_WQE_RD_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_LOCAL_INV_WQE_RD_FENCE_FLG_SHIFT 1
+#define RDMA_SQ_LOCAL_INV_WQE_INV_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_LOCAL_INV_WQE_INV_FENCE_FLG_SHIFT 2
+#define RDMA_SQ_LOCAL_INV_WQE_SE_FLG_MASK 0x1
+#define RDMA_SQ_LOCAL_INV_WQE_SE_FLG_SHIFT 3
+#define RDMA_SQ_LOCAL_INV_WQE_INLINE_FLG_MASK 0x1
+#define RDMA_SQ_LOCAL_INV_WQE_INLINE_FLG_SHIFT 4
+#define RDMA_SQ_LOCAL_INV_WQE_DIF_ON_HOST_FLG_MASK 0x1
+#define RDMA_SQ_LOCAL_INV_WQE_DIF_ON_HOST_FLG_SHIFT 5
+#define RDMA_SQ_LOCAL_INV_WQE_RESERVED0_MASK 0x3
+#define RDMA_SQ_LOCAL_INV_WQE_RESERVED0_SHIFT 6
+ u8 wqe_size;
+ u8 prev_wqe_size;
+};
+
+struct rdma_sq_rdma_wqe {
+ __le32 imm_data;
+ __le32 length;
+ __le32 xrc_srq;
+ u8 req_type;
+ u8 flags;
+#define RDMA_SQ_RDMA_WQE_COMP_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_COMP_FLG_SHIFT 0
+#define RDMA_SQ_RDMA_WQE_RD_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_RD_FENCE_FLG_SHIFT 1
+#define RDMA_SQ_RDMA_WQE_INV_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_INV_FENCE_FLG_SHIFT 2
+#define RDMA_SQ_RDMA_WQE_SE_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_SE_FLG_SHIFT 3
+#define RDMA_SQ_RDMA_WQE_INLINE_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_INLINE_FLG_SHIFT 4
+#define RDMA_SQ_RDMA_WQE_DIF_ON_HOST_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_DIF_ON_HOST_FLG_SHIFT 5
+#define RDMA_SQ_RDMA_WQE_RESERVED0_MASK 0x3
+#define RDMA_SQ_RDMA_WQE_RESERVED0_SHIFT 6
+ u8 wqe_size;
+ u8 prev_wqe_size;
+ struct regpair remote_va;
+ __le32 r_key;
+ u8 dif_flags;
+#define RDMA_SQ_RDMA_WQE_DIF_BLOCK_SIZE_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_DIF_BLOCK_SIZE_SHIFT 0
+#define RDMA_SQ_RDMA_WQE_DIF_FIRST_RDMA_IN_IO_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_DIF_FIRST_RDMA_IN_IO_FLG_SHIFT 1
+#define RDMA_SQ_RDMA_WQE_DIF_LAST_RDMA_IN_IO_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_DIF_LAST_RDMA_IN_IO_FLG_SHIFT 2
+#define RDMA_SQ_RDMA_WQE_RESERVED1_MASK 0x1F
+#define RDMA_SQ_RDMA_WQE_RESERVED1_SHIFT 3
+ u8 reserved2[3];
+};
+
+/* First element (16 bytes) of rdma wqe */
+struct rdma_sq_rdma_wqe_1st {
+ __le32 imm_data;
+ __le32 length;
+ __le32 xrc_srq;
+ u8 req_type;
+ u8 flags;
+#define RDMA_SQ_RDMA_WQE_1ST_COMP_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_1ST_COMP_FLG_SHIFT 0
+#define RDMA_SQ_RDMA_WQE_1ST_RD_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_1ST_RD_FENCE_FLG_SHIFT 1
+#define RDMA_SQ_RDMA_WQE_1ST_INV_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_1ST_INV_FENCE_FLG_SHIFT 2
+#define RDMA_SQ_RDMA_WQE_1ST_SE_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_1ST_SE_FLG_SHIFT 3
+#define RDMA_SQ_RDMA_WQE_1ST_INLINE_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_1ST_INLINE_FLG_SHIFT 4
+#define RDMA_SQ_RDMA_WQE_1ST_DIF_ON_HOST_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_1ST_DIF_ON_HOST_FLG_SHIFT 5
+#define RDMA_SQ_RDMA_WQE_1ST_RESERVED0_MASK 0x3
+#define RDMA_SQ_RDMA_WQE_1ST_RESERVED0_SHIFT 6
+ u8 wqe_size;
+ u8 prev_wqe_size;
+};
+
+/* Second element (16 bytes) of rdma wqe */
+struct rdma_sq_rdma_wqe_2nd {
+ struct regpair remote_va;
+ __le32 r_key;
+ u8 dif_flags;
+#define RDMA_SQ_RDMA_WQE_2ND_DIF_BLOCK_SIZE_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_2ND_DIF_BLOCK_SIZE_SHIFT 0
+#define RDMA_SQ_RDMA_WQE_2ND_DIF_FIRST_SEGMENT_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_2ND_DIF_FIRST_SEGMENT_FLG_SHIFT 1
+#define RDMA_SQ_RDMA_WQE_2ND_DIF_LAST_SEGMENT_FLG_MASK 0x1
+#define RDMA_SQ_RDMA_WQE_2ND_DIF_LAST_SEGMENT_FLG_SHIFT 2
+#define RDMA_SQ_RDMA_WQE_2ND_RESERVED1_MASK 0x1F
+#define RDMA_SQ_RDMA_WQE_2ND_RESERVED1_SHIFT 3
+ u8 reserved2[3];
+};
+
+/* SQ WQE req type enumeration */
+enum rdma_sq_req_type {
+ RDMA_SQ_REQ_TYPE_SEND,
+ RDMA_SQ_REQ_TYPE_SEND_WITH_IMM,
+ RDMA_SQ_REQ_TYPE_SEND_WITH_INVALIDATE,
+ RDMA_SQ_REQ_TYPE_RDMA_WR,
+ RDMA_SQ_REQ_TYPE_RDMA_WR_WITH_IMM,
+ RDMA_SQ_REQ_TYPE_RDMA_RD,
+ RDMA_SQ_REQ_TYPE_ATOMIC_CMP_AND_SWAP,
+ RDMA_SQ_REQ_TYPE_ATOMIC_ADD,
+ RDMA_SQ_REQ_TYPE_LOCAL_INVALIDATE,
+ RDMA_SQ_REQ_TYPE_FAST_MR,
+ RDMA_SQ_REQ_TYPE_BIND,
+ RDMA_SQ_REQ_TYPE_INVALID,
+ MAX_RDMA_SQ_REQ_TYPE
+};
+
+struct rdma_sq_send_wqe {
+ __le32 inv_key_or_imm_data;
+ __le32 length;
+ __le32 xrc_srq;
+ u8 req_type;
+ u8 flags;
+#define RDMA_SQ_SEND_WQE_COMP_FLG_MASK 0x1
+#define RDMA_SQ_SEND_WQE_COMP_FLG_SHIFT 0
+#define RDMA_SQ_SEND_WQE_RD_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_SEND_WQE_RD_FENCE_FLG_SHIFT 1
+#define RDMA_SQ_SEND_WQE_INV_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_SEND_WQE_INV_FENCE_FLG_SHIFT 2
+#define RDMA_SQ_SEND_WQE_SE_FLG_MASK 0x1
+#define RDMA_SQ_SEND_WQE_SE_FLG_SHIFT 3
+#define RDMA_SQ_SEND_WQE_INLINE_FLG_MASK 0x1
+#define RDMA_SQ_SEND_WQE_INLINE_FLG_SHIFT 4
+#define RDMA_SQ_SEND_WQE_DIF_ON_HOST_FLG_MASK 0x1
+#define RDMA_SQ_SEND_WQE_DIF_ON_HOST_FLG_SHIFT 5
+#define RDMA_SQ_SEND_WQE_RESERVED0_MASK 0x3
+#define RDMA_SQ_SEND_WQE_RESERVED0_SHIFT 6
+ u8 wqe_size;
+ u8 prev_wqe_size;
+ __le32 reserved1[4];
+};
+
+struct rdma_sq_send_wqe_1st {
+ __le32 inv_key_or_imm_data;
+ __le32 length;
+ __le32 xrc_srq;
+ u8 req_type;
+ u8 flags;
+#define RDMA_SQ_SEND_WQE_1ST_COMP_FLG_MASK 0x1
+#define RDMA_SQ_SEND_WQE_1ST_COMP_FLG_SHIFT 0
+#define RDMA_SQ_SEND_WQE_1ST_RD_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_SEND_WQE_1ST_RD_FENCE_FLG_SHIFT 1
+#define RDMA_SQ_SEND_WQE_1ST_INV_FENCE_FLG_MASK 0x1
+#define RDMA_SQ_SEND_WQE_1ST_INV_FENCE_FLG_SHIFT 2
+#define RDMA_SQ_SEND_WQE_1ST_SE_FLG_MASK 0x1
+#define RDMA_SQ_SEND_WQE_1ST_SE_FLG_SHIFT 3
+#define RDMA_SQ_SEND_WQE_1ST_INLINE_FLG_MASK 0x1
+#define RDMA_SQ_SEND_WQE_1ST_INLINE_FLG_SHIFT 4
+#define RDMA_SQ_SEND_WQE_1ST_RESERVED0_MASK 0x7
+#define RDMA_SQ_SEND_WQE_1ST_RESERVED0_SHIFT 5
+ u8 wqe_size;
+ u8 prev_wqe_size;
+};
+
+struct rdma_sq_send_wqe_2st {
+ __le32 reserved1[4];
+};
+
+#endif /* __QED_HSI_RDMA__ */
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
new file mode 100644
index 0000000..a615142
--- /dev/null
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -0,0 +1,3547 @@
+/* QLogic qedr NIC Driver
+ * Copyright (c) 2015-2016 QLogic Corporation
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and /or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#include <linux/dma-mapping.h>
+#include <linux/crc32.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/udp.h>
+#include <linux/iommu.h>
+
+#include <rdma/ib_verbs.h>
+#include <rdma/ib_user_verbs.h>
+#include <rdma/iw_cm.h>
+#include <rdma/ib_umem.h>
+#include <rdma/ib_addr.h>
+#include <rdma/ib_cache.h>
+
+#include "qedr_hsi.h"
+#include <linux/qed/qed_if.h>
+#include "qedr.h"
+#include "verbs.h"
+#include <rdma/qedr-abi.h>
+#include "qedr_cm.h"
+
+#define DB_ADDR_SHIFT(addr) ((addr) << DB_PWM_ADDR_OFFSET_SHIFT)
+
+int qedr_query_pkey(struct ib_device *ibdev, u8 port, u16 index, u16 *pkey)
+{
+ if (index > QEDR_ROCE_PKEY_TABLE_LEN)
+ return -EINVAL;
+
+ *pkey = QEDR_ROCE_PKEY_DEFAULT;
+ return 0;
+}
+
+int qedr_query_gid(struct ib_device *ibdev, u8 port, int index,
+ union ib_gid *sgid)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibdev);
+ int rc = 0;
+
+ if (!rdma_cap_roce_gid_table(ibdev, port))
+ return -ENODEV;
+
+ rc = ib_get_cached_gid(ibdev, port, index, sgid, NULL);
+ if (rc == -EAGAIN) {
+ memcpy(sgid, &zgid, sizeof(*sgid));
+ return 0;
+ }
+
+ DP_DEBUG(dev, QEDR_MSG_INIT, "query gid: index=%d %llx:%llx\n", index,
+ sgid->global.interface_id, sgid->global.subnet_prefix);
+
+ return rc;
+}
+
+int qedr_add_gid(struct ib_device *device, u8 port_num,
+ unsigned int index, const union ib_gid *gid,
+ const struct ib_gid_attr *attr, void **context)
+{
+ if (!rdma_cap_roce_gid_table(device, port_num))
+ return -EINVAL;
+
+ if (port_num > QEDR_MAX_PORT)
+ return -EINVAL;
+
+ if (!context)
+ return -EINVAL;
+
+ return 0;
+}
+
+int qedr_del_gid(struct ib_device *device, u8 port_num,
+ unsigned int index, void **context)
+{
+ if (!rdma_cap_roce_gid_table(device, port_num))
+ return -EINVAL;
+
+ if (port_num > QEDR_MAX_PORT)
+ return -EINVAL;
+
+ if (!context)
+ return -EINVAL;
+
+ return 0;
+}
+
+int qedr_query_device(struct ib_device *ibdev,
+ struct ib_device_attr *attr, struct ib_udata *udata)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibdev);
+ struct qedr_device_attr *qattr = &dev->attr;
+
+ if (!dev->rdma_ctx) {
+ DP_ERR(dev,
+ "qedr_query_device called with invalid params rdma_ctx=%p\n",
+ dev->rdma_ctx);
+ return -EINVAL;
+ }
+
+ memset(attr, 0, sizeof(*attr));
+
+ attr->fw_ver = qattr->fw_ver;
+ attr->sys_image_guid = qattr->sys_image_guid;
+ attr->max_mr_size = qattr->max_mr_size;
+ attr->page_size_cap = qattr->page_size_caps;
+ attr->vendor_id = qattr->vendor_id;
+ attr->vendor_part_id = qattr->vendor_part_id;
+ attr->hw_ver = qattr->hw_ver;
+ attr->max_qp = qattr->max_qp;
+ attr->max_qp_wr = max_t(u32, qattr->max_sqe, qattr->max_rqe);
+ attr->device_cap_flags = IB_DEVICE_CURR_QP_STATE_MOD |
+ IB_DEVICE_RC_RNR_NAK_GEN |
+ IB_DEVICE_LOCAL_DMA_LKEY | IB_DEVICE_MEM_MGT_EXTENSIONS;
+
+ attr->max_sge = qattr->max_sge;
+ attr->max_sge_rd = qattr->max_sge;
+ attr->max_cq = qattr->max_cq;
+ attr->max_cqe = qattr->max_cqe;
+ attr->max_mr = qattr->max_mr;
+ attr->max_mw = qattr->max_mw;
+ attr->max_pd = qattr->max_pd;
+ attr->atomic_cap = dev->atomic_cap;
+ attr->max_fmr = qattr->max_fmr;
+ attr->max_map_per_fmr = 16;
+ attr->max_qp_init_rd_atom =
+ 1 << (fls(qattr->max_qp_req_rd_atomic_resc) - 1);
+ attr->max_qp_rd_atom =
+ min(1 << (fls(qattr->max_qp_resp_rd_atomic_resc) - 1),
+ attr->max_qp_init_rd_atom);
+
+ attr->max_srq = qattr->max_srq;
+ attr->max_srq_sge = qattr->max_srq_sge;
+ attr->max_srq_wr = qattr->max_srq_wr;
+
+ attr->local_ca_ack_delay = qattr->dev_ack_delay;
+ attr->max_fast_reg_page_list_len = qattr->max_mr / 8;
+ attr->max_pkeys = QEDR_ROCE_PKEY_MAX;
+ attr->max_ah = qattr->max_ah;
+
+ return 0;
+}
+
+#define QEDR_SPEED_SDR (1)
+#define QEDR_SPEED_DDR (2)
+#define QEDR_SPEED_QDR (4)
+#define QEDR_SPEED_FDR10 (8)
+#define QEDR_SPEED_FDR (16)
+#define QEDR_SPEED_EDR (32)
+
+static inline void get_link_speed_and_width(int speed, u8 *ib_speed,
+ u8 *ib_width)
+{
+ switch (speed) {
+ case 1000:
+ *ib_speed = QEDR_SPEED_SDR;
+ *ib_width = IB_WIDTH_1X;
+ break;
+ case 10000:
+ *ib_speed = QEDR_SPEED_QDR;
+ *ib_width = IB_WIDTH_1X;
+ break;
+
+ case 20000:
+ *ib_speed = QEDR_SPEED_DDR;
+ *ib_width = IB_WIDTH_4X;
+ break;
+
+ case 25000:
+ *ib_speed = QEDR_SPEED_EDR;
+ *ib_width = IB_WIDTH_1X;
+ break;
+
+ case 40000:
+ *ib_speed = QEDR_SPEED_QDR;
+ *ib_width = IB_WIDTH_4X;
+ break;
+
+ case 50000:
+ *ib_speed = QEDR_SPEED_QDR;
+ *ib_width = IB_WIDTH_4X;
+ break;
+
+ case 100000:
+ *ib_speed = QEDR_SPEED_EDR;
+ *ib_width = IB_WIDTH_4X;
+ break;
+
+ default:
+ /* Unsupported */
+ *ib_speed = QEDR_SPEED_SDR;
+ *ib_width = IB_WIDTH_1X;
+ }
+}
+
+int qedr_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr *attr)
+{
+ struct qedr_dev *dev;
+ struct qed_rdma_port *rdma_port;
+
+ dev = get_qedr_dev(ibdev);
+ if (port > 1) {
+ DP_ERR(dev, "invalid_port=0x%x\n", port);
+ return -EINVAL;
+ }
+
+ if (!dev->rdma_ctx) {
+ DP_ERR(dev, "rdma_ctx is NULL\n");
+ return -EINVAL;
+ }
+
+ rdma_port = dev->ops->rdma_query_port(dev->rdma_ctx);
+ memset(attr, 0, sizeof(*attr));
+
+ if (rdma_port->port_state == QED_RDMA_PORT_UP) {
+ attr->state = IB_PORT_ACTIVE;
+ attr->phys_state = 5;
+ } else {
+ attr->state = IB_PORT_DOWN;
+ attr->phys_state = 3;
+ }
+ attr->max_mtu = IB_MTU_4096;
+ attr->active_mtu = iboe_get_mtu(dev->ndev->mtu);
+ attr->lid = 0;
+ attr->lmc = 0;
+ attr->sm_lid = 0;
+ attr->sm_sl = 0;
+ attr->port_cap_flags = IB_PORT_IP_BASED_GIDS;
+ attr->gid_tbl_len = QEDR_MAX_SGID;
+ attr->pkey_tbl_len = QEDR_ROCE_PKEY_TABLE_LEN;
+ attr->bad_pkey_cntr = rdma_port->pkey_bad_counter;
+ attr->qkey_viol_cntr = 0;
+ get_link_speed_and_width(rdma_port->link_speed,
+ &attr->active_speed, &attr->active_width);
+ attr->max_msg_sz = rdma_port->max_msg_size;
+ attr->max_vl_num = 4;
+
+ return 0;
+}
+
+int qedr_modify_port(struct ib_device *ibdev, u8 port, int mask,
+ struct ib_port_modify *props)
+{
+ struct qedr_dev *dev;
+
+ dev = get_qedr_dev(ibdev);
+ if (port > 1) {
+ DP_ERR(dev, "invalid_port=0x%x\n", port);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int qedr_add_mmap(struct qedr_ucontext *uctx, u64 phy_addr,
+ unsigned long len)
+{
+ struct qedr_mm *mm;
+
+ mm = kzalloc(sizeof(*mm), GFP_KERNEL);
+ if (!mm)
+ return -ENOMEM;
+
+ mm->key.phy_addr = phy_addr;
+ /* This function might be called with a length which is not a multiple
+ * of PAGE_SIZE, while the mapping is PAGE_SIZE grained and the kernel
+ * forces this granularity by increasing the requested size if needed.
+ * When qedr_mmap is called, it will search the list with the updated
+ * length as a key. To prevent search failures, the length is rounded up
+ * in advance to PAGE_SIZE.
+ */
+ mm->key.len = roundup(len, PAGE_SIZE);
+ INIT_LIST_HEAD(&mm->entry);
+
+ mutex_lock(&uctx->mm_list_lock);
+ list_add(&mm->entry, &uctx->mm_head);
+ mutex_unlock(&uctx->mm_list_lock);
+
+ DP_DEBUG(uctx->dev, QEDR_MSG_MISC,
+ "added (addr=0x%llx,len=0x%lx) for ctx=%p\n",
+ (unsigned long long)mm->key.phy_addr,
+ (unsigned long)mm->key.len, uctx);
+
+ return 0;
+}
+
+static bool qedr_search_mmap(struct qedr_ucontext *uctx, u64 phy_addr,
+ unsigned long len)
+{
+ bool found = false;
+ struct qedr_mm *mm;
+
+ mutex_lock(&uctx->mm_list_lock);
+ list_for_each_entry(mm, &uctx->mm_head, entry) {
+ if (len != mm->key.len || phy_addr != mm->key.phy_addr)
+ continue;
+
+ found = true;
+ break;
+ }
+ mutex_unlock(&uctx->mm_list_lock);
+ DP_DEBUG(uctx->dev, QEDR_MSG_MISC,
+ "searched for (addr=0x%llx,len=0x%lx) for ctx=%p, result=%d\n",
+ mm->key.phy_addr, mm->key.len, uctx, found);
+
+ return found;
+}
+
+struct ib_ucontext *qedr_alloc_ucontext(struct ib_device *ibdev,
+ struct ib_udata *udata)
+{
+ int rc;
+ struct qedr_ucontext *ctx;
+ struct qedr_alloc_ucontext_resp uresp;
+ struct qedr_dev *dev = get_qedr_dev(ibdev);
+ struct qed_rdma_add_user_out_params oparams;
+
+ if (!udata)
+ return ERR_PTR(-EFAULT);
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return ERR_PTR(-ENOMEM);
+
+ rc = dev->ops->rdma_add_user(dev->rdma_ctx, &oparams);
+ if (rc) {
+ DP_ERR(dev,
+ "failed to allocate a DPI for a new RoCE application, rc=%d. To overcome this consider to increase the number of DPIs, increase the doorbell BAR size or just close unnecessary RoCE applications. In order to increase the number of DPIs consult the qedr readme\n",
+ rc);
+ goto err;
+ }
+
+ ctx->dpi = oparams.dpi;
+ ctx->dpi_addr = oparams.dpi_addr;
+ ctx->dpi_phys_addr = oparams.dpi_phys_addr;
+ ctx->dpi_size = oparams.dpi_size;
+ INIT_LIST_HEAD(&ctx->mm_head);
+ mutex_init(&ctx->mm_list_lock);
+
+ memset(&uresp, 0, sizeof(uresp));
+
+ uresp.db_pa = ctx->dpi_phys_addr;
+ uresp.db_size = ctx->dpi_size;
+ uresp.max_send_wr = dev->attr.max_sqe;
+ uresp.max_recv_wr = dev->attr.max_rqe;
+ uresp.max_srq_wr = dev->attr.max_srq_wr;
+ uresp.sges_per_send_wr = QEDR_MAX_SQE_ELEMENTS_PER_SQE;
+ uresp.sges_per_recv_wr = QEDR_MAX_RQE_ELEMENTS_PER_RQE;
+ uresp.sges_per_srq_wr = dev->attr.max_srq_sge;
+ uresp.max_cqes = QEDR_MAX_CQES;
+
+ rc = ib_copy_to_udata(udata, &uresp, sizeof(uresp));
+ if (rc)
+ goto err;
+
+ ctx->dev = dev;
+
+ rc = qedr_add_mmap(ctx, ctx->dpi_phys_addr, ctx->dpi_size);
+ if (rc)
+ goto err;
+
+ DP_DEBUG(dev, QEDR_MSG_INIT, "Allocating user context %p\n",
+ &ctx->ibucontext);
+ return &ctx->ibucontext;
+
+err:
+ kfree(ctx);
+ return ERR_PTR(rc);
+}
+
+int qedr_dealloc_ucontext(struct ib_ucontext *ibctx)
+{
+ struct qedr_ucontext *uctx = get_qedr_ucontext(ibctx);
+ struct qedr_mm *mm, *tmp;
+ int status = 0;
+
+ DP_DEBUG(uctx->dev, QEDR_MSG_INIT, "Deallocating user context %p\n",
+ uctx);
+ uctx->dev->ops->rdma_remove_user(uctx->dev->rdma_ctx, uctx->dpi);
+
+ list_for_each_entry_safe(mm, tmp, &uctx->mm_head, entry) {
+ DP_DEBUG(uctx->dev, QEDR_MSG_MISC,
+ "deleted (addr=0x%llx,len=0x%lx) for ctx=%p\n",
+ mm->key.phy_addr, mm->key.len, uctx);
+ list_del(&mm->entry);
+ kfree(mm);
+ }
+
+ kfree(uctx);
+ return status;
+}
+
+int qedr_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
+{
+ struct qedr_ucontext *ucontext = get_qedr_ucontext(context);
+ struct qedr_dev *dev = get_qedr_dev(context->device);
+ unsigned long vm_page = vma->vm_pgoff << PAGE_SHIFT;
+ u64 unmapped_db = dev->db_phys_addr;
+ unsigned long len = (vma->vm_end - vma->vm_start);
+ int rc = 0;
+ bool found;
+
+ DP_DEBUG(dev, QEDR_MSG_INIT,
+ "qedr_mmap called vm_page=0x%lx vm_pgoff=0x%lx unmapped_db=0x%llx db_size=%x, len=%lx\n",
+ vm_page, vma->vm_pgoff, unmapped_db, dev->db_size, len);
+ if (vma->vm_start & (PAGE_SIZE - 1)) {
+ DP_ERR(dev, "Vma_start not page aligned = %ld\n",
+ vma->vm_start);
+ return -EINVAL;
+ }
+
+ found = qedr_search_mmap(ucontext, vm_page, len);
+ if (!found) {
+ DP_ERR(dev, "Vma_pgoff not found in mapped array = %ld\n",
+ vma->vm_pgoff);
+ return -EINVAL;
+ }
+
+ DP_DEBUG(dev, QEDR_MSG_INIT, "Mapping doorbell bar\n");
+
+ if ((vm_page >= unmapped_db) && (vm_page <= (unmapped_db +
+ dev->db_size))) {
+ DP_DEBUG(dev, QEDR_MSG_INIT, "Mapping doorbell bar\n");
+ if (vma->vm_flags & VM_READ) {
+ DP_ERR(dev, "Trying to map doorbell bar for read\n");
+ return -EPERM;
+ }
+
+ vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+
+ rc = io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+ PAGE_SIZE, vma->vm_page_prot);
+ } else {
+ DP_DEBUG(dev, QEDR_MSG_INIT, "Mapping chains\n");
+ rc = remap_pfn_range(vma, vma->vm_start,
+ vma->vm_pgoff, len, vma->vm_page_prot);
+ }
+ DP_DEBUG(dev, QEDR_MSG_INIT, "qedr_mmap return code: %d\n", rc);
+ return rc;
+}
+
+struct ib_pd *qedr_alloc_pd(struct ib_device *ibdev,
+ struct ib_ucontext *context, struct ib_udata *udata)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibdev);
+ struct qedr_ucontext *uctx = NULL;
+ struct qedr_alloc_pd_uresp uresp;
+ struct qedr_pd *pd;
+ u16 pd_id;
+ int rc;
+
+ DP_DEBUG(dev, QEDR_MSG_INIT, "Function called from: %s\n",
+ (udata && context) ? "User Lib" : "Kernel");
+
+ if (!dev->rdma_ctx) {
+ DP_ERR(dev, "invlaid RDMA context\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+ if (!pd)
+ return ERR_PTR(-ENOMEM);
+
+ dev->ops->rdma_alloc_pd(dev->rdma_ctx, &pd_id);
+
+ uresp.pd_id = pd_id;
+ pd->pd_id = pd_id;
+
+ if (udata && context) {
+ rc = ib_copy_to_udata(udata, &uresp, sizeof(uresp));
+ if (rc)
+ DP_ERR(dev, "copy error pd_id=0x%x.\n", pd_id);
+ uctx = get_qedr_ucontext(context);
+ uctx->pd = pd;
+ pd->uctx = uctx;
+ }
+
+ return &pd->ibpd;
+}
+
+int qedr_dealloc_pd(struct ib_pd *ibpd)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibpd->device);
+ struct qedr_pd *pd = get_qedr_pd(ibpd);
+
+ if (!pd)
+ pr_err("Invalid PD received in dealloc_pd\n");
+
+ DP_DEBUG(dev, QEDR_MSG_INIT, "Deallocating PD %d\n", pd->pd_id);
+ dev->ops->rdma_dealloc_pd(dev->rdma_ctx, pd->pd_id);
+
+ kfree(pd);
+
+ return 0;
+}
+
+static void qedr_free_pbl(struct qedr_dev *dev,
+ struct qedr_pbl_info *pbl_info, struct qedr_pbl *pbl)
+{
+ struct pci_dev *pdev = dev->pdev;
+ int i;
+
+ for (i = 0; i < pbl_info->num_pbls; i++) {
+ if (!pbl[i].va)
+ continue;
+ dma_free_coherent(&pdev->dev, pbl_info->pbl_size,
+ pbl[i].va, pbl[i].pa);
+ }
+
+ kfree(pbl);
+}
+
+#define MIN_FW_PBL_PAGE_SIZE (4 * 1024)
+#define MAX_FW_PBL_PAGE_SIZE (64 * 1024)
+
+#define NUM_PBES_ON_PAGE(_page_size) (_page_size / sizeof(u64))
+#define MAX_PBES_ON_PAGE NUM_PBES_ON_PAGE(MAX_FW_PBL_PAGE_SIZE)
+#define MAX_PBES_TWO_LAYER (MAX_PBES_ON_PAGE * MAX_PBES_ON_PAGE)
+
+static struct qedr_pbl *qedr_alloc_pbl_tbl(struct qedr_dev *dev,
+ struct qedr_pbl_info *pbl_info,
+ gfp_t flags)
+{
+ struct pci_dev *pdev = dev->pdev;
+ struct qedr_pbl *pbl_table;
+ dma_addr_t *pbl_main_tbl;
+ dma_addr_t pa;
+ void *va;
+ int i;
+
+ pbl_table = kcalloc(pbl_info->num_pbls, sizeof(*pbl_table), flags);
+ if (!pbl_table)
+ return ERR_PTR(-ENOMEM);
+
+ for (i = 0; i < pbl_info->num_pbls; i++) {
+ va = dma_alloc_coherent(&pdev->dev, pbl_info->pbl_size,
+ &pa, flags);
+ if (!va)
+ goto err;
+
+ memset(va, 0, pbl_info->pbl_size);
+ pbl_table[i].va = va;
+ pbl_table[i].pa = pa;
+ }
+
+ /* Two-Layer PBLs, if we have more than one pbl we need to initialize
+ * the first one with physical pointers to all of the rest
+ */
+ pbl_main_tbl = (dma_addr_t *)pbl_table[0].va;
+ for (i = 0; i < pbl_info->num_pbls - 1; i++)
+ pbl_main_tbl[i] = pbl_table[i + 1].pa;
+
+ return pbl_table;
+
+err:
+ for (i--; i >= 0; i--)
+ dma_free_coherent(&pdev->dev, pbl_info->pbl_size,
+ pbl_table[i].va, pbl_table[i].pa);
+
+ qedr_free_pbl(dev, pbl_info, pbl_table);
+
+ return ERR_PTR(-ENOMEM);
+}
+
+static int qedr_prepare_pbl_tbl(struct qedr_dev *dev,
+ struct qedr_pbl_info *pbl_info,
+ u32 num_pbes, int two_layer_capable)
+{
+ u32 pbl_capacity;
+ u32 pbl_size;
+ u32 num_pbls;
+
+ if ((num_pbes > MAX_PBES_ON_PAGE) && two_layer_capable) {
+ if (num_pbes > MAX_PBES_TWO_LAYER) {
+ DP_ERR(dev, "prepare pbl table: too many pages %d\n",
+ num_pbes);
+ return -EINVAL;
+ }
+
+ /* calculate required pbl page size */
+ pbl_size = MIN_FW_PBL_PAGE_SIZE;
+ pbl_capacity = NUM_PBES_ON_PAGE(pbl_size) *
+ NUM_PBES_ON_PAGE(pbl_size);
+
+ while (pbl_capacity < num_pbes) {
+ pbl_size *= 2;
+ pbl_capacity = pbl_size / sizeof(u64);
+ pbl_capacity = pbl_capacity * pbl_capacity;
+ }
+
+ num_pbls = DIV_ROUND_UP(num_pbes, NUM_PBES_ON_PAGE(pbl_size));
+ num_pbls++; /* One for the layer0 ( points to the pbls) */
+ pbl_info->two_layered = true;
+ } else {
+ /* One layered PBL */
+ num_pbls = 1;
+ pbl_size = max_t(u32, MIN_FW_PBL_PAGE_SIZE,
+ roundup_pow_of_two((num_pbes * sizeof(u64))));
+ pbl_info->two_layered = false;
+ }
+
+ pbl_info->num_pbls = num_pbls;
+ pbl_info->pbl_size = pbl_size;
+ pbl_info->num_pbes = num_pbes;
+
+ DP_DEBUG(dev, QEDR_MSG_MR,
+ "prepare pbl table: num_pbes=%d, num_pbls=%d, pbl_size=%d\n",
+ pbl_info->num_pbes, pbl_info->num_pbls, pbl_info->pbl_size);
+
+ return 0;
+}
+
+static void qedr_populate_pbls(struct qedr_dev *dev, struct ib_umem *umem,
+ struct qedr_pbl *pbl,
+ struct qedr_pbl_info *pbl_info)
+{
+ int shift, pg_cnt, pages, pbe_cnt, total_num_pbes = 0;
+ struct qedr_pbl *pbl_tbl;
+ struct scatterlist *sg;
+ struct regpair *pbe;
+ int entry;
+ u32 addr;
+
+ if (!pbl_info->num_pbes)
+ return;
+
+ /* If we have a two layered pbl, the first pbl points to the rest
+ * of the pbls and the first entry lays on the second pbl in the table
+ */
+ if (pbl_info->two_layered)
+ pbl_tbl = &pbl[1];
+ else
+ pbl_tbl = pbl;
+
+ pbe = (struct regpair *)pbl_tbl->va;
+ if (!pbe) {
+ DP_ERR(dev, "cannot populate PBL due to a NULL PBE\n");
+ return;
+ }
+
+ pbe_cnt = 0;
+
+ shift = ilog2(umem->page_size);
+
+ for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
+ pages = sg_dma_len(sg) >> shift;
+ for (pg_cnt = 0; pg_cnt < pages; pg_cnt++) {
+ /* store the page address in pbe */
+ pbe->lo = cpu_to_le32(sg_dma_address(sg) +
+ umem->page_size * pg_cnt);
+ addr = upper_32_bits(sg_dma_address(sg) +
+ umem->page_size * pg_cnt);
+ pbe->hi = cpu_to_le32(addr);
+ pbe_cnt++;
+ total_num_pbes++;
+ pbe++;
+
+ if (total_num_pbes == pbl_info->num_pbes)
+ return;
+
+ /* If the given pbl is full storing the pbes,
+ * move to next pbl.
+ */
+ if (pbe_cnt == (pbl_info->pbl_size / sizeof(u64))) {
+ pbl_tbl++;
+ pbe = (struct regpair *)pbl_tbl->va;
+ pbe_cnt = 0;
+ }
+ }
+ }
+}
+
+static int qedr_copy_cq_uresp(struct qedr_dev *dev,
+ struct qedr_cq *cq, struct ib_udata *udata)
+{
+ struct qedr_create_cq_uresp uresp;
+ int rc;
+
+ memset(&uresp, 0, sizeof(uresp));
+
+ uresp.db_offset = DB_ADDR_SHIFT(DQ_PWM_OFFSET_UCM_RDMA_CQ_CONS_32BIT);
+ uresp.icid = cq->icid;
+
+ rc = ib_copy_to_udata(udata, &uresp, sizeof(uresp));
+ if (rc)
+ DP_ERR(dev, "copy error cqid=0x%x.\n", cq->icid);
+
+ return rc;
+}
+
+static void consume_cqe(struct qedr_cq *cq)
+{
+ if (cq->latest_cqe == cq->toggle_cqe)
+ cq->pbl_toggle ^= RDMA_CQE_REQUESTER_TOGGLE_BIT_MASK;
+
+ cq->latest_cqe = qed_chain_consume(&cq->pbl);
+}
+
+static inline int qedr_align_cq_entries(int entries)
+{
+ u64 size, aligned_size;
+
+ /* We allocate an extra entry that we don't report to the FW. */
+ size = (entries + 1) * QEDR_CQE_SIZE;
+ aligned_size = ALIGN(size, PAGE_SIZE);
+
+ return aligned_size / QEDR_CQE_SIZE;
+}
+
+static inline int qedr_init_user_queue(struct ib_ucontext *ib_ctx,
+ struct qedr_dev *dev,
+ struct qedr_userq *q,
+ u64 buf_addr, size_t buf_len,
+ int access, int dmasync)
+{
+ int page_cnt;
+ int rc;
+
+ q->buf_addr = buf_addr;
+ q->buf_len = buf_len;
+ q->umem = ib_umem_get(ib_ctx, q->buf_addr, q->buf_len, access, dmasync);
+ if (IS_ERR(q->umem)) {
+ DP_ERR(dev, "create user queue: failed ib_umem_get, got %ld\n",
+ PTR_ERR(q->umem));
+ return PTR_ERR(q->umem);
+ }
+
+ page_cnt = ib_umem_page_count(q->umem);
+ rc = qedr_prepare_pbl_tbl(dev, &q->pbl_info, page_cnt, 0);
+ if (rc)
+ goto err0;
+
+ q->pbl_tbl = qedr_alloc_pbl_tbl(dev, &q->pbl_info, GFP_KERNEL);
+ if (IS_ERR_OR_NULL(q->pbl_tbl))
+ goto err0;
+
+ qedr_populate_pbls(dev, q->umem, q->pbl_tbl, &q->pbl_info);
+
+ return 0;
+
+err0:
+ ib_umem_release(q->umem);
+
+ return rc;
+}
+
+static inline void qedr_init_cq_params(struct qedr_cq *cq,
+ struct qedr_ucontext *ctx,
+ struct qedr_dev *dev, int vector,
+ int chain_entries, int page_cnt,
+ u64 pbl_ptr,
+ struct qed_rdma_create_cq_in_params
+ *params)
+{
+ memset(params, 0, sizeof(*params));
+ params->cq_handle_hi = upper_32_bits((uintptr_t)cq);
+ params->cq_handle_lo = lower_32_bits((uintptr_t)cq);
+ params->cnq_id = vector;
+ params->cq_size = chain_entries - 1;
+ params->dpi = (ctx) ? ctx->dpi : dev->dpi;
+ params->pbl_num_pages = page_cnt;
+ params->pbl_ptr = pbl_ptr;
+ params->pbl_two_level = 0;
+}
+
+static void doorbell_cq(struct qedr_cq *cq, u32 cons, u8 flags)
+{
+ /* Flush data before signalling doorbell */
+ wmb();
+ cq->db.data.agg_flags = flags;
+ cq->db.data.value = cpu_to_le32(cons);
+ writeq(cq->db.raw, cq->db_addr);
+
+ /* Make sure write would stick */
+ mmiowb();
+}
+
+int qedr_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
+{
+ struct qedr_cq *cq = get_qedr_cq(ibcq);
+ unsigned long sflags;
+
+ if (cq->cq_type == QEDR_CQ_TYPE_GSI)
+ return 0;
+
+ spin_lock_irqsave(&cq->cq_lock, sflags);
+
+ cq->arm_flags = 0;
+
+ if (flags & IB_CQ_SOLICITED)
+ cq->arm_flags |= DQ_UCM_ROCE_CQ_ARM_SE_CF_CMD;
+
+ if (flags & IB_CQ_NEXT_COMP)
+ cq->arm_flags |= DQ_UCM_ROCE_CQ_ARM_CF_CMD;
+
+ doorbell_cq(cq, cq->cq_cons - 1, cq->arm_flags);
+
+ spin_unlock_irqrestore(&cq->cq_lock, sflags);
+
+ return 0;
+}
+
+struct ib_cq *qedr_create_cq(struct ib_device *ibdev,
+ const struct ib_cq_init_attr *attr,
+ struct ib_ucontext *ib_ctx, struct ib_udata *udata)
+{
+ struct qedr_ucontext *ctx = get_qedr_ucontext(ib_ctx);
+ struct qed_rdma_destroy_cq_out_params destroy_oparams;
+ struct qed_rdma_destroy_cq_in_params destroy_iparams;
+ struct qedr_dev *dev = get_qedr_dev(ibdev);
+ struct qed_rdma_create_cq_in_params params;
+ struct qedr_create_cq_ureq ureq;
+ int vector = attr->comp_vector;
+ int entries = attr->cqe;
+ struct qedr_cq *cq;
+ int chain_entries;
+ int page_cnt;
+ u64 pbl_ptr;
+ u16 icid;
+ int rc;
+
+ DP_DEBUG(dev, QEDR_MSG_INIT,
+ "create_cq: called from %s. entries=%d, vector=%d\n",
+ udata ? "User Lib" : "Kernel", entries, vector);
+
+ if (entries > QEDR_MAX_CQES) {
+ DP_ERR(dev,
+ "create cq: the number of entries %d is too high. Must be equal or below %d.\n",
+ entries, QEDR_MAX_CQES);
+ return ERR_PTR(-EINVAL);
+ }
+
+ chain_entries = qedr_align_cq_entries(entries);
+ chain_entries = min_t(int, chain_entries, QEDR_MAX_CQES);
+
+ cq = kzalloc(sizeof(*cq), GFP_KERNEL);
+ if (!cq)
+ return ERR_PTR(-ENOMEM);
+
+ if (udata) {
+ memset(&ureq, 0, sizeof(ureq));
+ if (ib_copy_from_udata(&ureq, udata, sizeof(ureq))) {
+ DP_ERR(dev,
+ "create cq: problem copying data from user space\n");
+ goto err0;
+ }
+
+ if (!ureq.len) {
+ DP_ERR(dev,
+ "create cq: cannot create a cq with 0 entries\n");
+ goto err0;
+ }
+
+ cq->cq_type = QEDR_CQ_TYPE_USER;
+
+ rc = qedr_init_user_queue(ib_ctx, dev, &cq->q, ureq.addr,
+ ureq.len, IB_ACCESS_LOCAL_WRITE, 1);
+ if (rc)
+ goto err0;
+
+ pbl_ptr = cq->q.pbl_tbl->pa;
+ page_cnt = cq->q.pbl_info.num_pbes;
+ } else {
+ cq->cq_type = QEDR_CQ_TYPE_KERNEL;
+
+ rc = dev->ops->common->chain_alloc(dev->cdev,
+ QED_CHAIN_USE_TO_CONSUME,
+ QED_CHAIN_MODE_PBL,
+ QED_CHAIN_CNT_TYPE_U32,
+ chain_entries,
+ sizeof(union rdma_cqe),
+ &cq->pbl);
+ if (rc)
+ goto err1;
+
+ page_cnt = qed_chain_get_page_cnt(&cq->pbl);
+ pbl_ptr = qed_chain_get_pbl_phys(&cq->pbl);
+ }
+
+ qedr_init_cq_params(cq, ctx, dev, vector, chain_entries, page_cnt,
+ pbl_ptr, ¶ms);
+
+ rc = dev->ops->rdma_create_cq(dev->rdma_ctx, ¶ms, &icid);
+ if (rc)
+ goto err2;
+
+ cq->icid = icid;
+ cq->sig = QEDR_CQ_MAGIC_NUMBER;
+ spin_lock_init(&cq->cq_lock);
+
+ if (ib_ctx) {
+ rc = qedr_copy_cq_uresp(dev, cq, udata);
+ if (rc)
+ goto err3;
+ } else {
+ /* Generate doorbell address. */
+ cq->db_addr = dev->db_addr +
+ DB_ADDR_SHIFT(DQ_PWM_OFFSET_UCM_RDMA_CQ_CONS_32BIT);
+ cq->db.data.icid = cq->icid;
+ cq->db.data.params = DB_AGG_CMD_SET <<
+ RDMA_PWM_VAL32_DATA_AGG_CMD_SHIFT;
+
+ /* point to the very last element, passing it we will toggle */
+ cq->toggle_cqe = qed_chain_get_last_elem(&cq->pbl);
+ cq->pbl_toggle = RDMA_CQE_REQUESTER_TOGGLE_BIT_MASK;
+ cq->latest_cqe = NULL;
+ consume_cqe(cq);
+ cq->cq_cons = qed_chain_get_cons_idx_u32(&cq->pbl);
+ }
+
+ DP_DEBUG(dev, QEDR_MSG_CQ,
+ "create cq: icid=0x%0x, addr=%p, size(entries)=0x%0x\n",
+ cq->icid, cq, params.cq_size);
+
+ return &cq->ibcq;
+
+err3:
+ destroy_iparams.icid = cq->icid;
+ dev->ops->rdma_destroy_cq(dev->rdma_ctx, &destroy_iparams,
+ &destroy_oparams);
+err2:
+ if (udata)
+ qedr_free_pbl(dev, &cq->q.pbl_info, cq->q.pbl_tbl);
+ else
+ dev->ops->common->chain_free(dev->cdev, &cq->pbl);
+err1:
+ if (udata)
+ ib_umem_release(cq->q.umem);
+err0:
+ kfree(cq);
+ return ERR_PTR(-EINVAL);
+}
+
+int qedr_resize_cq(struct ib_cq *ibcq, int new_cnt, struct ib_udata *udata)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibcq->device);
+ struct qedr_cq *cq = get_qedr_cq(ibcq);
+
+ DP_ERR(dev, "cq %p RESIZE NOT SUPPORTED\n", cq);
+
+ return 0;
+}
+
+int qedr_destroy_cq(struct ib_cq *ibcq)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibcq->device);
+ struct qed_rdma_destroy_cq_out_params oparams;
+ struct qed_rdma_destroy_cq_in_params iparams;
+ struct qedr_cq *cq = get_qedr_cq(ibcq);
+
+ DP_DEBUG(dev, QEDR_MSG_CQ, "destroy cq: cq_id %d", cq->icid);
+
+ /* GSIs CQs are handled by driver, so they don't exist in the FW */
+ if (cq->cq_type != QEDR_CQ_TYPE_GSI) {
+ iparams.icid = cq->icid;
+ dev->ops->rdma_destroy_cq(dev->rdma_ctx, &iparams, &oparams);
+ dev->ops->common->chain_free(dev->cdev, &cq->pbl);
+ }
+
+ if (ibcq->uobject && ibcq->uobject->context) {
+ qedr_free_pbl(dev, &cq->q.pbl_info, cq->q.pbl_tbl);
+ ib_umem_release(cq->q.umem);
+ }
+
+ kfree(cq);
+
+ return 0;
+}
+
+static inline int get_gid_info_from_table(struct ib_qp *ibqp,
+ struct ib_qp_attr *attr,
+ int attr_mask,
+ struct qed_rdma_modify_qp_in_params
+ *qp_params)
+{
+ enum rdma_network_type nw_type;
+ struct ib_gid_attr gid_attr;
+ union ib_gid gid;
+ u32 ipv4_addr;
+ int rc = 0;
+ int i;
+
+ rc = ib_get_cached_gid(ibqp->device, attr->ah_attr.port_num,
+ attr->ah_attr.grh.sgid_index, &gid, &gid_attr);
+ if (rc)
+ return rc;
+
+ if (!memcmp(&gid, &zgid, sizeof(gid)))
+ return -ENOENT;
+
+ if (gid_attr.ndev) {
+ qp_params->vlan_id = rdma_vlan_dev_vlan_id(gid_attr.ndev);
+
+ dev_put(gid_attr.ndev);
+ nw_type = ib_gid_to_network_type(gid_attr.gid_type, &gid);
+ switch (nw_type) {
+ case RDMA_NETWORK_IPV6:
+ memcpy(&qp_params->sgid.bytes[0], &gid.raw[0],
+ sizeof(qp_params->sgid));
+ memcpy(&qp_params->dgid.bytes[0],
+ &attr->ah_attr.grh.dgid,
+ sizeof(qp_params->dgid));
+ qp_params->roce_mode = ROCE_V2_IPV6;
+ SET_FIELD(qp_params->modify_flags,
+ QED_ROCE_MODIFY_QP_VALID_ROCE_MODE, 1);
+ break;
+ case RDMA_NETWORK_IB:
+ memcpy(&qp_params->sgid.bytes[0], &gid.raw[0],
+ sizeof(qp_params->sgid));
+ memcpy(&qp_params->dgid.bytes[0],
+ &attr->ah_attr.grh.dgid,
+ sizeof(qp_params->dgid));
+ qp_params->roce_mode = ROCE_V1;
+ break;
+ case RDMA_NETWORK_IPV4:
+ memset(&qp_params->sgid, 0, sizeof(qp_params->sgid));
+ memset(&qp_params->dgid, 0, sizeof(qp_params->dgid));
+ ipv4_addr = qedr_get_ipv4_from_gid(gid.raw);
+ qp_params->sgid.ipv4_addr = ipv4_addr;
+ ipv4_addr =
+ qedr_get_ipv4_from_gid(attr->ah_attr.grh.dgid.raw);
+ qp_params->dgid.ipv4_addr = ipv4_addr;
+ SET_FIELD(qp_params->modify_flags,
+ QED_ROCE_MODIFY_QP_VALID_ROCE_MODE, 1);
+ qp_params->roce_mode = ROCE_V2_IPV4;
+ break;
+ }
+ }
+
+ for (i = 0; i < 4; i++) {
+ qp_params->sgid.dwords[i] = ntohl(qp_params->sgid.dwords[i]);
+ qp_params->dgid.dwords[i] = ntohl(qp_params->dgid.dwords[i]);
+ }
+
+ if (qp_params->vlan_id >= VLAN_CFI_MASK)
+ qp_params->vlan_id = 0;
+
+ return 0;
+}
+
+static void qedr_cleanup_user_sq(struct qedr_dev *dev, struct qedr_qp *qp)
+{
+ qedr_free_pbl(dev, &qp->usq.pbl_info, qp->usq.pbl_tbl);
+ ib_umem_release(qp->usq.umem);
+}
+
+static void qedr_cleanup_user_rq(struct qedr_dev *dev, struct qedr_qp *qp)
+{
+ qedr_free_pbl(dev, &qp->urq.pbl_info, qp->urq.pbl_tbl);
+ ib_umem_release(qp->urq.umem);
+}
+
+static void qedr_cleanup_kernel_sq(struct qedr_dev *dev, struct qedr_qp *qp)
+{
+ dev->ops->common->chain_free(dev->cdev, &qp->sq.pbl);
+ kfree(qp->wqe_wr_id);
+}
+
+static void qedr_cleanup_kernel_rq(struct qedr_dev *dev, struct qedr_qp *qp)
+{
+ dev->ops->common->chain_free(dev->cdev, &qp->rq.pbl);
+ kfree(qp->rqe_wr_id);
+}
+
+static int qedr_check_qp_attrs(struct ib_pd *ibpd, struct qedr_dev *dev,
+ struct ib_qp_init_attr *attrs)
+{
+ struct qedr_device_attr *qattr = &dev->attr;
+
+ /* QP0... attrs->qp_type == IB_QPT_GSI */
+ if (attrs->qp_type != IB_QPT_RC && attrs->qp_type != IB_QPT_GSI) {
+ DP_DEBUG(dev, QEDR_MSG_QP,
+ "create qp: unsupported qp type=0x%x requested\n",
+ attrs->qp_type);
+ return -EINVAL;
+ }
+
+ if (attrs->cap.max_send_wr > qattr->max_sqe) {
+ DP_ERR(dev,
+ "create qp: cannot create a SQ with %d elements (max_send_wr=0x%x)\n",
+ attrs->cap.max_send_wr, qattr->max_sqe);
+ return -EINVAL;
+ }
+
+ if (attrs->cap.max_inline_data > qattr->max_inline) {
+ DP_ERR(dev,
+ "create qp: unsupported inline data size=0x%x requested (max_inline=0x%x)\n",
+ attrs->cap.max_inline_data, qattr->max_inline);
+ return -EINVAL;
+ }
+
+ if (attrs->cap.max_send_sge > qattr->max_sge) {
+ DP_ERR(dev,
+ "create qp: unsupported send_sge=0x%x requested (max_send_sge=0x%x)\n",
+ attrs->cap.max_send_sge, qattr->max_sge);
+ return -EINVAL;
+ }
+
+ if (attrs->cap.max_recv_sge > qattr->max_sge) {
+ DP_ERR(dev,
+ "create qp: unsupported recv_sge=0x%x requested (max_recv_sge=0x%x)\n",
+ attrs->cap.max_recv_sge, qattr->max_sge);
+ return -EINVAL;
+ }
+
+ /* Unprivileged user space cannot create special QP */
+ if (ibpd->uobject && attrs->qp_type == IB_QPT_GSI) {
+ DP_ERR(dev,
+ "create qp: userspace can't create special QPs of type=0x%x\n",
+ attrs->qp_type);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void qedr_copy_rq_uresp(struct qedr_create_qp_uresp *uresp,
+ struct qedr_qp *qp)
+{
+ uresp->rq_db_offset = DB_ADDR_SHIFT(DQ_PWM_OFFSET_TCM_ROCE_RQ_PROD);
+ uresp->rq_icid = qp->icid;
+}
+
+static void qedr_copy_sq_uresp(struct qedr_create_qp_uresp *uresp,
+ struct qedr_qp *qp)
+{
+ uresp->sq_db_offset = DB_ADDR_SHIFT(DQ_PWM_OFFSET_XCM_RDMA_SQ_PROD);
+ uresp->sq_icid = qp->icid + 1;
+}
+
+static int qedr_copy_qp_uresp(struct qedr_dev *dev,
+ struct qedr_qp *qp, struct ib_udata *udata)
+{
+ struct qedr_create_qp_uresp uresp;
+ int rc;
+
+ memset(&uresp, 0, sizeof(uresp));
+ qedr_copy_sq_uresp(&uresp, qp);
+ qedr_copy_rq_uresp(&uresp, qp);
+
+ uresp.atomic_supported = dev->atomic_cap != IB_ATOMIC_NONE;
+ uresp.qp_id = qp->qp_id;
+
+ rc = ib_copy_to_udata(udata, &uresp, sizeof(uresp));
+ if (rc)
+ DP_ERR(dev,
+ "create qp: failed a copy to user space with qp icid=0x%x.\n",
+ qp->icid);
+
+ return rc;
+}
+
+static void qedr_set_qp_init_params(struct qedr_dev *dev,
+ struct qedr_qp *qp,
+ struct qedr_pd *pd,
+ struct ib_qp_init_attr *attrs)
+{
+ qp->pd = pd;
+
+ spin_lock_init(&qp->q_lock);
+
+ qp->qp_type = attrs->qp_type;
+ qp->max_inline_data = attrs->cap.max_inline_data;
+ qp->sq.max_sges = attrs->cap.max_send_sge;
+ qp->state = QED_ROCE_QP_STATE_RESET;
+ qp->signaled = (attrs->sq_sig_type == IB_SIGNAL_ALL_WR) ? true : false;
+ qp->sq_cq = get_qedr_cq(attrs->send_cq);
+ qp->rq_cq = get_qedr_cq(attrs->recv_cq);
+ qp->dev = dev;
+
+ DP_DEBUG(dev, QEDR_MSG_QP,
+ "QP params:\tpd = %d, qp_type = %d, max_inline_data = %d, state = %d, signaled = %d, use_srq=%d\n",
+ pd->pd_id, qp->qp_type, qp->max_inline_data,
+ qp->state, qp->signaled, (attrs->srq) ? 1 : 0);
+ DP_DEBUG(dev, QEDR_MSG_QP,
+ "SQ params:\tsq_max_sges = %d, sq_cq_id = %d\n",
+ qp->sq.max_sges, qp->sq_cq->icid);
+ qp->rq.max_sges = attrs->cap.max_recv_sge;
+ DP_DEBUG(dev, QEDR_MSG_QP,
+ "RQ params:\trq_max_sges = %d, rq_cq_id = %d\n",
+ qp->rq.max_sges, qp->rq_cq->icid);
+}
+
+static inline void
+qedr_init_qp_user_params(struct qed_rdma_create_qp_in_params *params,
+ struct qedr_create_qp_ureq *ureq)
+{
+ /* QP handle to be written in CQE */
+ params->qp_handle_lo = ureq->qp_handle_lo;
+ params->qp_handle_hi = ureq->qp_handle_hi;
+}
+
+static inline void
+qedr_init_qp_kernel_doorbell_sq(struct qedr_dev *dev, struct qedr_qp *qp)
+{
+ qp->sq.db = dev->db_addr +
+ DB_ADDR_SHIFT(DQ_PWM_OFFSET_XCM_RDMA_SQ_PROD);
+ qp->sq.db_data.data.icid = qp->icid + 1;
+}
+
+static inline void
+qedr_init_qp_kernel_doorbell_rq(struct qedr_dev *dev, struct qedr_qp *qp)
+{
+ qp->rq.db = dev->db_addr +
+ DB_ADDR_SHIFT(DQ_PWM_OFFSET_TCM_ROCE_RQ_PROD);
+ qp->rq.db_data.data.icid = qp->icid;
+}
+
+static inline int
+qedr_init_qp_kernel_params_rq(struct qedr_dev *dev,
+ struct qedr_qp *qp, struct ib_qp_init_attr *attrs)
+{
+ /* Allocate driver internal RQ array */
+ qp->rqe_wr_id = kcalloc(qp->rq.max_wr, sizeof(*qp->rqe_wr_id),
+ GFP_KERNEL);
+ if (!qp->rqe_wr_id)
+ return -ENOMEM;
+
+ DP_DEBUG(dev, QEDR_MSG_QP, "RQ max_wr set to %d.\n", qp->rq.max_wr);
+
+ return 0;
+}
+
+static inline int
+qedr_init_qp_kernel_params_sq(struct qedr_dev *dev,
+ struct qedr_qp *qp,
+ struct ib_qp_init_attr *attrs,
+ struct qed_rdma_create_qp_in_params *params)
+{
+ u32 temp_max_wr;
+
+ /* Allocate driver internal SQ array */
+ temp_max_wr = attrs->cap.max_send_wr * dev->wq_multiplier;
+ temp_max_wr = min_t(u32, temp_max_wr, dev->attr.max_sqe);
+
+ /* temp_max_wr < attr->max_sqe < u16 so the casting is safe */
+ qp->sq.max_wr = (u16)temp_max_wr;
+ qp->wqe_wr_id = kcalloc(qp->sq.max_wr, sizeof(*qp->wqe_wr_id),
+ GFP_KERNEL);
+ if (!qp->wqe_wr_id)
+ return -ENOMEM;
+
+ DP_DEBUG(dev, QEDR_MSG_QP, "SQ max_wr set to %d.\n", qp->sq.max_wr);
+
+ /* QP handle to be written in CQE */
+ params->qp_handle_lo = lower_32_bits((uintptr_t)qp);
+ params->qp_handle_hi = upper_32_bits((uintptr_t)qp);
+
+ return 0;
+}
+
+static inline int qedr_init_qp_kernel_sq(struct qedr_dev *dev,
+ struct qedr_qp *qp,
+ struct ib_qp_init_attr *attrs)
+{
+ u32 n_sq_elems, n_sq_entries;
+ int rc;
+
+ /* A single work request may take up to QEDR_MAX_SQ_WQE_SIZE elements in
+ * the ring. The ring should allow at least a single WR, even if the
+ * user requested none, due to allocation issues.
+ */
+ n_sq_entries = attrs->cap.max_send_wr;
+ n_sq_entries = min_t(u32, n_sq_entries, dev->attr.max_sqe);
+ n_sq_entries = max_t(u32, n_sq_entries, 1);
+ n_sq_elems = n_sq_entries * QEDR_MAX_SQE_ELEMENTS_PER_SQE;
+ rc = dev->ops->common->chain_alloc(dev->cdev,
+ QED_CHAIN_USE_TO_PRODUCE,
+ QED_CHAIN_MODE_PBL,
+ QED_CHAIN_CNT_TYPE_U32,
+ n_sq_elems,
+ QEDR_SQE_ELEMENT_SIZE,
+ &qp->sq.pbl);
+ if (rc) {
+ DP_ERR(dev, "failed to allocate QP %p SQ\n", qp);
+ return rc;
+ }
+
+ DP_DEBUG(dev, QEDR_MSG_SQ,
+ "SQ Pbl base addr = %llx max_send_wr=%d max_wr=%d capacity=%d, rc=%d\n",
+ qed_chain_get_pbl_phys(&qp->sq.pbl), attrs->cap.max_send_wr,
+ n_sq_entries, qed_chain_get_capacity(&qp->sq.pbl), rc);
+ return 0;
+}
+
+static inline int qedr_init_qp_kernel_rq(struct qedr_dev *dev,
+ struct qedr_qp *qp,
+ struct ib_qp_init_attr *attrs)
+{
+ u32 n_rq_elems, n_rq_entries;
+ int rc;
+
+ /* A single work request may take up to QEDR_MAX_RQ_WQE_SIZE elements in
+ * the ring. There ring should allow at least a single WR, even if the
+ * user requested none, due to allocation issues.
+ */
+ n_rq_entries = max_t(u32, attrs->cap.max_recv_wr, 1);
+ n_rq_elems = n_rq_entries * QEDR_MAX_RQE_ELEMENTS_PER_RQE;
+ rc = dev->ops->common->chain_alloc(dev->cdev,
+ QED_CHAIN_USE_TO_CONSUME_PRODUCE,
+ QED_CHAIN_MODE_PBL,
+ QED_CHAIN_CNT_TYPE_U32,
+ n_rq_elems,
+ QEDR_RQE_ELEMENT_SIZE,
+ &qp->rq.pbl);
+
+ if (rc) {
+ DP_ERR(dev, "failed to allocate memory for QP %p RQ\n", qp);
+ return -ENOMEM;
+ }
+
+ DP_DEBUG(dev, QEDR_MSG_RQ,
+ "RQ Pbl base addr = %llx max_recv_wr=%d max_wr=%d capacity=%d, rc=%d\n",
+ qed_chain_get_pbl_phys(&qp->rq.pbl), attrs->cap.max_recv_wr,
+ n_rq_entries, qed_chain_get_capacity(&qp->rq.pbl), rc);
+
+ /* n_rq_entries < u16 so the casting is safe */
+ qp->rq.max_wr = (u16)n_rq_entries;
+
+ return 0;
+}
+
+static inline void
+qedr_init_qp_in_params_sq(struct qedr_dev *dev,
+ struct qedr_pd *pd,
+ struct qedr_qp *qp,
+ struct ib_qp_init_attr *attrs,
+ struct ib_udata *udata,
+ struct qed_rdma_create_qp_in_params *params)
+{
+ /* QP handle to be written in an async event */
+ params->qp_handle_async_lo = lower_32_bits((uintptr_t)qp);
+ params->qp_handle_async_hi = upper_32_bits((uintptr_t)qp);
+
+ params->signal_all = (attrs->sq_sig_type == IB_SIGNAL_ALL_WR);
+ params->fmr_and_reserved_lkey = !udata;
+ params->pd = pd->pd_id;
+ params->dpi = pd->uctx ? pd->uctx->dpi : dev->dpi;
+ params->sq_cq_id = get_qedr_cq(attrs->send_cq)->icid;
+ params->max_sq_sges = 0;
+ params->stats_queue = 0;
+
+ if (udata) {
+ params->sq_num_pages = qp->usq.pbl_info.num_pbes;
+ params->sq_pbl_ptr = qp->usq.pbl_tbl->pa;
+ } else {
+ params->sq_num_pages = qed_chain_get_page_cnt(&qp->sq.pbl);
+ params->sq_pbl_ptr = qed_chain_get_pbl_phys(&qp->sq.pbl);
+ }
+}
+
+static inline void
+qedr_init_qp_in_params_rq(struct qedr_qp *qp,
+ struct ib_qp_init_attr *attrs,
+ struct ib_udata *udata,
+ struct qed_rdma_create_qp_in_params *params)
+{
+ params->rq_cq_id = get_qedr_cq(attrs->recv_cq)->icid;
+ params->srq_id = 0;
+ params->use_srq = false;
+
+ if (udata) {
+ params->rq_num_pages = qp->urq.pbl_info.num_pbes;
+ params->rq_pbl_ptr = qp->urq.pbl_tbl->pa;
+ } else {
+ params->rq_num_pages = qed_chain_get_page_cnt(&qp->rq.pbl);
+ params->rq_pbl_ptr = qed_chain_get_pbl_phys(&qp->rq.pbl);
+ }
+}
+
+static inline void qedr_qp_user_print(struct qedr_dev *dev, struct qedr_qp *qp)
+{
+ DP_DEBUG(dev, QEDR_MSG_QP,
+ "create qp: successfully created user QP. qp=%p, sq_addr=0x%llx, sq_len=%zd, rq_addr=0x%llx, rq_len=%zd\n",
+ qp, qp->usq.buf_addr, qp->usq.buf_len, qp->urq.buf_addr,
+ qp->urq.buf_len);
+}
+
+static inline int qedr_init_user_qp(struct ib_ucontext *ib_ctx,
+ struct qedr_dev *dev,
+ struct qedr_qp *qp,
+ struct qedr_create_qp_ureq *ureq)
+{
+ int rc;
+
+ /* SQ - read access only (0), dma sync not required (0) */
+ rc = qedr_init_user_queue(ib_ctx, dev, &qp->usq, ureq->sq_addr,
+ ureq->sq_len, 0, 0);
+ if (rc)
+ return rc;
+
+ /* RQ - read access only (0), dma sync not required (0) */
+ rc = qedr_init_user_queue(ib_ctx, dev, &qp->urq, ureq->rq_addr,
+ ureq->rq_len, 0, 0);
+
+ if (rc)
+ qedr_cleanup_user_sq(dev, qp);
+ return rc;
+}
+
+static inline int
+qedr_init_kernel_qp(struct qedr_dev *dev,
+ struct qedr_qp *qp,
+ struct ib_qp_init_attr *attrs,
+ struct qed_rdma_create_qp_in_params *params)
+{
+ int rc;
+
+ rc = qedr_init_qp_kernel_sq(dev, qp, attrs);
+ if (rc) {
+ DP_ERR(dev, "failed to init kernel QP %p SQ\n", qp);
+ return rc;
+ }
+
+ rc = qedr_init_qp_kernel_params_sq(dev, qp, attrs, params);
+ if (rc) {
+ dev->ops->common->chain_free(dev->cdev, &qp->sq.pbl);
+ DP_ERR(dev, "failed to init kernel QP %p SQ params\n", qp);
+ return rc;
+ }
+
+ rc = qedr_init_qp_kernel_rq(dev, qp, attrs);
+ if (rc) {
+ qedr_cleanup_kernel_sq(dev, qp);
+ DP_ERR(dev, "failed to init kernel QP %p RQ\n", qp);
+ return rc;
+ }
+
+ rc = qedr_init_qp_kernel_params_rq(dev, qp, attrs);
+ if (rc) {
+ DP_ERR(dev, "failed to init kernel QP %p RQ params\n", qp);
+ qedr_cleanup_kernel_sq(dev, qp);
+ dev->ops->common->chain_free(dev->cdev, &qp->rq.pbl);
+ return rc;
+ }
+
+ return rc;
+}
+
+struct ib_qp *qedr_create_qp(struct ib_pd *ibpd,
+ struct ib_qp_init_attr *attrs,
+ struct ib_udata *udata)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibpd->device);
+ struct qed_rdma_create_qp_out_params out_params;
+ struct qed_rdma_create_qp_in_params in_params;
+ struct qedr_pd *pd = get_qedr_pd(ibpd);
+ struct ib_ucontext *ib_ctx = NULL;
+ struct qedr_ucontext *ctx = NULL;
+ struct qedr_create_qp_ureq ureq;
+ struct qedr_qp *qp;
+ int rc = 0;
+
+ DP_DEBUG(dev, QEDR_MSG_QP, "create qp: called from %s, pd=%p\n",
+ udata ? "user library" : "kernel", pd);
+
+ rc = qedr_check_qp_attrs(ibpd, dev, attrs);
+ if (rc)
+ return ERR_PTR(rc);
+
+ qp = kzalloc(sizeof(*qp), GFP_KERNEL);
+ if (!qp)
+ return ERR_PTR(-ENOMEM);
+
+ if (attrs->srq)
+ return ERR_PTR(-EINVAL);
+
+ DP_DEBUG(dev, QEDR_MSG_QP,
+ "create qp: sq_cq=%p, sq_icid=%d, rq_cq=%p, rq_icid=%d\n",
+ get_qedr_cq(attrs->send_cq),
+ get_qedr_cq(attrs->send_cq)->icid,
+ get_qedr_cq(attrs->recv_cq),
+ get_qedr_cq(attrs->recv_cq)->icid);
+
+ qedr_set_qp_init_params(dev, qp, pd, attrs);
+
+ if (attrs->qp_type == IB_QPT_GSI) {
+ if (udata) {
+ DP_ERR(dev,
+ "create qp: unexpected udata when creating GSI QP\n");
+ goto err0;
+ }
+ return qedr_create_gsi_qp(dev, attrs, qp);
+ }
+
+ memset(&in_params, 0, sizeof(in_params));
+
+ if (udata) {
+ if (!(udata && ibpd->uobject && ibpd->uobject->context))
+ goto err0;
+
+ ib_ctx = ibpd->uobject->context;
+ ctx = get_qedr_ucontext(ib_ctx);
+
+ memset(&ureq, 0, sizeof(ureq));
+ if (ib_copy_from_udata(&ureq, udata, sizeof(ureq))) {
+ DP_ERR(dev,
+ "create qp: problem copying data from user space\n");
+ goto err0;
+ }
+
+ rc = qedr_init_user_qp(ib_ctx, dev, qp, &ureq);
+ if (rc)
+ goto err0;
+
+ qedr_init_qp_user_params(&in_params, &ureq);
+ } else {
+ rc = qedr_init_kernel_qp(dev, qp, attrs, &in_params);
+ if (rc)
+ goto err0;
+ }
+
+ qedr_init_qp_in_params_sq(dev, pd, qp, attrs, udata, &in_params);
+ qedr_init_qp_in_params_rq(qp, attrs, udata, &in_params);
+
+ qp->qed_qp = dev->ops->rdma_create_qp(dev->rdma_ctx,
+ &in_params, &out_params);
+
+ if (!qp->qed_qp)
+ goto err1;
+
+ qp->qp_id = out_params.qp_id;
+ qp->icid = out_params.icid;
+ qp->ibqp.qp_num = qp->qp_id;
+
+ if (udata) {
+ rc = qedr_copy_qp_uresp(dev, qp, udata);
+ if (rc)
+ goto err2;
+
+ qedr_qp_user_print(dev, qp);
+ } else {
+ qedr_init_qp_kernel_doorbell_sq(dev, qp);
+ qedr_init_qp_kernel_doorbell_rq(dev, qp);
+ }
+
+ DP_DEBUG(dev, QEDR_MSG_QP, "created %s space QP %p\n",
+ udata ? "user" : "kernel", qp);
+
+ return &qp->ibqp;
+
+err2:
+ rc = dev->ops->rdma_destroy_qp(dev->rdma_ctx, qp->qed_qp);
+ if (rc)
+ DP_ERR(dev, "create qp: fatal fault. rc=%d", rc);
+err1:
+ if (udata) {
+ qedr_cleanup_user_sq(dev, qp);
+ qedr_cleanup_user_rq(dev, qp);
+ } else {
+ qedr_cleanup_kernel_sq(dev, qp);
+ qedr_cleanup_kernel_rq(dev, qp);
+ }
+
+err0:
+ kfree(qp);
+
+ return ERR_PTR(-EFAULT);
+}
+
+enum ib_qp_state qedr_get_ibqp_state(enum qed_roce_qp_state qp_state)
+{
+ switch (qp_state) {
+ case QED_ROCE_QP_STATE_RESET:
+ return IB_QPS_RESET;
+ case QED_ROCE_QP_STATE_INIT:
+ return IB_QPS_INIT;
+ case QED_ROCE_QP_STATE_RTR:
+ return IB_QPS_RTR;
+ case QED_ROCE_QP_STATE_RTS:
+ return IB_QPS_RTS;
+ case QED_ROCE_QP_STATE_SQD:
+ return IB_QPS_SQD;
+ case QED_ROCE_QP_STATE_ERR:
+ return IB_QPS_ERR;
+ case QED_ROCE_QP_STATE_SQE:
+ return IB_QPS_SQE;
+ }
+ return IB_QPS_ERR;
+}
+
+enum qed_roce_qp_state qedr_get_state_from_ibqp(enum ib_qp_state qp_state)
+{
+ switch (qp_state) {
+ case IB_QPS_RESET:
+ return QED_ROCE_QP_STATE_RESET;
+ case IB_QPS_INIT:
+ return QED_ROCE_QP_STATE_INIT;
+ case IB_QPS_RTR:
+ return QED_ROCE_QP_STATE_RTR;
+ case IB_QPS_RTS:
+ return QED_ROCE_QP_STATE_RTS;
+ case IB_QPS_SQD:
+ return QED_ROCE_QP_STATE_SQD;
+ case IB_QPS_ERR:
+ return QED_ROCE_QP_STATE_ERR;
+ default:
+ return QED_ROCE_QP_STATE_ERR;
+ }
+}
+
+static void qedr_reset_qp_hwq_info(struct qedr_qp_hwq_info *qph)
+{
+ qed_chain_reset(&qph->pbl);
+ qph->prod = 0;
+ qph->cons = 0;
+ qph->wqe_cons = 0;
+ qph->db_data.data.value = cpu_to_le16(0);
+}
+
+static int qedr_update_qp_state(struct qedr_dev *dev,
+ struct qedr_qp *qp,
+ enum qed_roce_qp_state new_state)
+{
+ int status = 0;
+
+ if (new_state == qp->state)
+ return 1;
+
+ switch (qp->state) {
+ case QED_ROCE_QP_STATE_RESET:
+ switch (new_state) {
+ case QED_ROCE_QP_STATE_INIT:
+ qp->prev_wqe_size = 0;
+ qedr_reset_qp_hwq_info(&qp->sq);
+ qedr_reset_qp_hwq_info(&qp->rq);
+ break;
+ default:
+ status = -EINVAL;
+ break;
+ };
+ break;
+ case QED_ROCE_QP_STATE_INIT:
+ switch (new_state) {
+ case QED_ROCE_QP_STATE_RTR:
+ /* Update doorbell (in case post_recv was
+ * done before move to RTR)
+ */
+ wmb();
+ writel(qp->rq.db_data.raw, qp->rq.db);
+ /* Make sure write takes effect */
+ mmiowb();
+ break;
+ case QED_ROCE_QP_STATE_ERR:
+ break;
+ default:
+ /* Invalid state change. */
+ status = -EINVAL;
+ break;
+ };
+ break;
+ case QED_ROCE_QP_STATE_RTR:
+ /* RTR->XXX */
+ switch (new_state) {
+ case QED_ROCE_QP_STATE_RTS:
+ break;
+ case QED_ROCE_QP_STATE_ERR:
+ break;
+ default:
+ /* Invalid state change. */
+ status = -EINVAL;
+ break;
+ };
+ break;
+ case QED_ROCE_QP_STATE_RTS:
+ /* RTS->XXX */
+ switch (new_state) {
+ case QED_ROCE_QP_STATE_SQD:
+ break;
+ case QED_ROCE_QP_STATE_ERR:
+ break;
+ default:
+ /* Invalid state change. */
+ status = -EINVAL;
+ break;
+ };
+ break;
+ case QED_ROCE_QP_STATE_SQD:
+ /* SQD->XXX */
+ switch (new_state) {
+ case QED_ROCE_QP_STATE_RTS:
+ case QED_ROCE_QP_STATE_ERR:
+ break;
+ default:
+ /* Invalid state change. */
+ status = -EINVAL;
+ break;
+ };
+ break;
+ case QED_ROCE_QP_STATE_ERR:
+ /* ERR->XXX */
+ switch (new_state) {
+ case QED_ROCE_QP_STATE_RESET:
+ break;
+ default:
+ status = -EINVAL;
+ break;
+ };
+ break;
+ default:
+ status = -EINVAL;
+ break;
+ };
+
+ return status;
+}
+
+int qedr_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
+ int attr_mask, struct ib_udata *udata)
+{
+ struct qedr_qp *qp = get_qedr_qp(ibqp);
+ struct qed_rdma_modify_qp_in_params qp_params = { 0 };
+ struct qedr_dev *dev = get_qedr_dev(&qp->dev->ibdev);
+ enum ib_qp_state old_qp_state, new_qp_state;
+ int rc = 0;
+
+ DP_DEBUG(dev, QEDR_MSG_QP,
+ "modify qp: qp %p attr_mask=0x%x, state=%d", qp, attr_mask,
+ attr->qp_state);
+
+ old_qp_state = qedr_get_ibqp_state(qp->state);
+ if (attr_mask & IB_QP_STATE)
+ new_qp_state = attr->qp_state;
+ else
+ new_qp_state = old_qp_state;
+
+ if (!ib_modify_qp_is_ok
+ (old_qp_state, new_qp_state, ibqp->qp_type, attr_mask,
+ IB_LINK_LAYER_ETHERNET)) {
+ DP_ERR(dev,
+ "modify qp: invalid attribute mask=0x%x specified for\n"
+ "qpn=0x%x of type=0x%x old_qp_state=0x%x, new_qp_state=0x%x\n",
+ attr_mask, qp->qp_id, ibqp->qp_type, old_qp_state,
+ new_qp_state);
+ rc = -EINVAL;
+ goto err;
+ }
+
+ /* Translate the masks... */
+ if (attr_mask & IB_QP_STATE) {
+ SET_FIELD(qp_params.modify_flags,
+ QED_RDMA_MODIFY_QP_VALID_NEW_STATE, 1);
+ qp_params.new_state = qedr_get_state_from_ibqp(attr->qp_state);
+ }
+
+ if (attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY)
+ qp_params.sqd_async = true;
+
+ if (attr_mask & IB_QP_PKEY_INDEX) {
+ SET_FIELD(qp_params.modify_flags,
+ QED_ROCE_MODIFY_QP_VALID_PKEY, 1);
+ if (attr->pkey_index >= QEDR_ROCE_PKEY_TABLE_LEN) {
+ rc = -EINVAL;
+ goto err;
+ }
+
+ qp_params.pkey = QEDR_ROCE_PKEY_DEFAULT;
+ }
+
+ if (attr_mask & IB_QP_QKEY)
+ qp->qkey = attr->qkey;
+
+ if (attr_mask & IB_QP_ACCESS_FLAGS) {
+ SET_FIELD(qp_params.modify_flags,
+ QED_RDMA_MODIFY_QP_VALID_RDMA_OPS_EN, 1);
+ qp_params.incoming_rdma_read_en = attr->qp_access_flags &
+ IB_ACCESS_REMOTE_READ;
+ qp_params.incoming_rdma_write_en = attr->qp_access_flags &
+ IB_ACCESS_REMOTE_WRITE;
+ qp_params.incoming_atomic_en = attr->qp_access_flags &
+ IB_ACCESS_REMOTE_ATOMIC;
+ }
+
+ if (attr_mask & (IB_QP_AV | IB_QP_PATH_MTU)) {
+ if (attr_mask & IB_QP_PATH_MTU) {
+ if (attr->path_mtu < IB_MTU_256 ||
+ attr->path_mtu > IB_MTU_4096) {
+ pr_err("error: Only MTU sizes of 256, 512, 1024, 2048 and 4096 are supported by RoCE\n");
+ rc = -EINVAL;
+ goto err;
+ }
+ qp->mtu = min(ib_mtu_enum_to_int(attr->path_mtu),
+ ib_mtu_enum_to_int(iboe_get_mtu
+ (dev->ndev->mtu)));
+ }
+
+ if (!qp->mtu) {
+ qp->mtu =
+ ib_mtu_enum_to_int(iboe_get_mtu(dev->ndev->mtu));
+ pr_err("Fixing zeroed MTU to qp->mtu = %d\n", qp->mtu);
+ }
+
+ SET_FIELD(qp_params.modify_flags,
+ QED_ROCE_MODIFY_QP_VALID_ADDRESS_VECTOR, 1);
+
+ qp_params.traffic_class_tos = attr->ah_attr.grh.traffic_class;
+ qp_params.flow_label = attr->ah_attr.grh.flow_label;
+ qp_params.hop_limit_ttl = attr->ah_attr.grh.hop_limit;
+
+ qp->sgid_idx = attr->ah_attr.grh.sgid_index;
+
+ rc = get_gid_info_from_table(ibqp, attr, attr_mask, &qp_params);
+ if (rc) {
+ DP_ERR(dev,
+ "modify qp: problems with GID index %d (rc=%d)\n",
+ attr->ah_attr.grh.sgid_index, rc);
+ return rc;
+ }
+
+ rc = qedr_get_dmac(dev, &attr->ah_attr,
+ qp_params.remote_mac_addr);
+ if (rc)
+ return rc;
+
+ qp_params.use_local_mac = true;
+ ether_addr_copy(qp_params.local_mac_addr, dev->ndev->dev_addr);
+
+ DP_DEBUG(dev, QEDR_MSG_QP, "dgid=%x:%x:%x:%x\n",
+ qp_params.dgid.dwords[0], qp_params.dgid.dwords[1],
+ qp_params.dgid.dwords[2], qp_params.dgid.dwords[3]);
+ DP_DEBUG(dev, QEDR_MSG_QP, "sgid=%x:%x:%x:%x\n",
+ qp_params.sgid.dwords[0], qp_params.sgid.dwords[1],
+ qp_params.sgid.dwords[2], qp_params.sgid.dwords[3]);
+ DP_DEBUG(dev, QEDR_MSG_QP, "remote_mac=[%pM]\n",
+ qp_params.remote_mac_addr);
+;
+
+ qp_params.mtu = qp->mtu;
+ qp_params.lb_indication = false;
+ }
+
+ if (!qp_params.mtu) {
+ /* Stay with current MTU */
+ if (qp->mtu)
+ qp_params.mtu = qp->mtu;
+ else
+ qp_params.mtu =
+ ib_mtu_enum_to_int(iboe_get_mtu(dev->ndev->mtu));
+ }
+
+ if (attr_mask & IB_QP_TIMEOUT) {
+ SET_FIELD(qp_params.modify_flags,
+ QED_ROCE_MODIFY_QP_VALID_ACK_TIMEOUT, 1);
+
+ qp_params.ack_timeout = attr->timeout;
+ if (attr->timeout) {
+ u32 temp;
+
+ temp = 4096 * (1UL << attr->timeout) / 1000 / 1000;
+ /* FW requires [msec] */
+ qp_params.ack_timeout = temp;
+ } else {
+ /* Infinite */
+ qp_params.ack_timeout = 0;
+ }
+ }
+ if (attr_mask & IB_QP_RETRY_CNT) {
+ SET_FIELD(qp_params.modify_flags,
+ QED_ROCE_MODIFY_QP_VALID_RETRY_CNT, 1);
+ qp_params.retry_cnt = attr->retry_cnt;
+ }
+
+ if (attr_mask & IB_QP_RNR_RETRY) {
+ SET_FIELD(qp_params.modify_flags,
+ QED_ROCE_MODIFY_QP_VALID_RNR_RETRY_CNT, 1);
+ qp_params.rnr_retry_cnt = attr->rnr_retry;
+ }
+
+ if (attr_mask & IB_QP_RQ_PSN) {
+ SET_FIELD(qp_params.modify_flags,
+ QED_ROCE_MODIFY_QP_VALID_RQ_PSN, 1);
+ qp_params.rq_psn = attr->rq_psn;
+ qp->rq_psn = attr->rq_psn;
+ }
+
+ if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC) {
+ if (attr->max_rd_atomic > dev->attr.max_qp_req_rd_atomic_resc) {
+ rc = -EINVAL;
+ DP_ERR(dev,
+ "unsupported max_rd_atomic=%d, supported=%d\n",
+ attr->max_rd_atomic,
+ dev->attr.max_qp_req_rd_atomic_resc);
+ goto err;
+ }
+
+ SET_FIELD(qp_params.modify_flags,
+ QED_RDMA_MODIFY_QP_VALID_MAX_RD_ATOMIC_REQ, 1);
+ qp_params.max_rd_atomic_req = attr->max_rd_atomic;
+ }
+
+ if (attr_mask & IB_QP_MIN_RNR_TIMER) {
+ SET_FIELD(qp_params.modify_flags,
+ QED_ROCE_MODIFY_QP_VALID_MIN_RNR_NAK_TIMER, 1);
+ qp_params.min_rnr_nak_timer = attr->min_rnr_timer;
+ }
+
+ if (attr_mask & IB_QP_SQ_PSN) {
+ SET_FIELD(qp_params.modify_flags,
+ QED_ROCE_MODIFY_QP_VALID_SQ_PSN, 1);
+ qp_params.sq_psn = attr->sq_psn;
+ qp->sq_psn = attr->sq_psn;
+ }
+
+ if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC) {
+ if (attr->max_dest_rd_atomic >
+ dev->attr.max_qp_resp_rd_atomic_resc) {
+ DP_ERR(dev,
+ "unsupported max_dest_rd_atomic=%d, supported=%d\n",
+ attr->max_dest_rd_atomic,
+ dev->attr.max_qp_resp_rd_atomic_resc);
+
+ rc = -EINVAL;
+ goto err;
+ }
+
+ SET_FIELD(qp_params.modify_flags,
+ QED_RDMA_MODIFY_QP_VALID_MAX_RD_ATOMIC_RESP, 1);
+ qp_params.max_rd_atomic_resp = attr->max_dest_rd_atomic;
+ }
+
+ if (attr_mask & IB_QP_DEST_QPN) {
+ SET_FIELD(qp_params.modify_flags,
+ QED_ROCE_MODIFY_QP_VALID_DEST_QP, 1);
+
+ qp_params.dest_qp = attr->dest_qp_num;
+ qp->dest_qp_num = attr->dest_qp_num;
+ }
+
+ if (qp->qp_type != IB_QPT_GSI)
+ rc = dev->ops->rdma_modify_qp(dev->rdma_ctx,
+ qp->qed_qp, &qp_params);
+
+ if (attr_mask & IB_QP_STATE) {
+ if ((qp->qp_type != IB_QPT_GSI) && (!udata))
+ qedr_update_qp_state(dev, qp, qp_params.new_state);
+ qp->state = qp_params.new_state;
+ }
+
+err:
+ return rc;
+}
+
+static int qedr_to_ib_qp_acc_flags(struct qed_rdma_query_qp_out_params *params)
+{
+ int ib_qp_acc_flags = 0;
+
+ if (params->incoming_rdma_write_en)
+ ib_qp_acc_flags |= IB_ACCESS_REMOTE_WRITE;
+ if (params->incoming_rdma_read_en)
+ ib_qp_acc_flags |= IB_ACCESS_REMOTE_READ;
+ if (params->incoming_atomic_en)
+ ib_qp_acc_flags |= IB_ACCESS_REMOTE_ATOMIC;
+ ib_qp_acc_flags |= IB_ACCESS_LOCAL_WRITE;
+ return ib_qp_acc_flags;
+}
+
+int qedr_query_qp(struct ib_qp *ibqp,
+ struct ib_qp_attr *qp_attr,
+ int attr_mask, struct ib_qp_init_attr *qp_init_attr)
+{
+ struct qed_rdma_query_qp_out_params params;
+ struct qedr_qp *qp = get_qedr_qp(ibqp);
+ struct qedr_dev *dev = qp->dev;
+ int rc = 0;
+
+ memset(¶ms, 0, sizeof(params));
+
+ rc = dev->ops->rdma_query_qp(dev->rdma_ctx, qp->qed_qp, ¶ms);
+ if (rc)
+ goto err;
+
+ memset(qp_attr, 0, sizeof(*qp_attr));
+ memset(qp_init_attr, 0, sizeof(*qp_init_attr));
+
+ qp_attr->qp_state = qedr_get_ibqp_state(params.state);
+ qp_attr->cur_qp_state = qedr_get_ibqp_state(params.state);
+ qp_attr->path_mtu = iboe_get_mtu(params.mtu);
+ qp_attr->path_mig_state = IB_MIG_MIGRATED;
+ qp_attr->rq_psn = params.rq_psn;
+ qp_attr->sq_psn = params.sq_psn;
+ qp_attr->dest_qp_num = params.dest_qp;
+
+ qp_attr->qp_access_flags = qedr_to_ib_qp_acc_flags(¶ms);
+
+ qp_attr->cap.max_send_wr = qp->sq.max_wr;
+ qp_attr->cap.max_recv_wr = qp->rq.max_wr;
+ qp_attr->cap.max_send_sge = qp->sq.max_sges;
+ qp_attr->cap.max_recv_sge = qp->rq.max_sges;
+ qp_attr->cap.max_inline_data = qp->max_inline_data;
+ qp_init_attr->cap = qp_attr->cap;
+
+ memcpy(&qp_attr->ah_attr.grh.dgid.raw[0], ¶ms.dgid.bytes[0],
+ sizeof(qp_attr->ah_attr.grh.dgid.raw));
+
+ qp_attr->ah_attr.grh.flow_label = params.flow_label;
+ qp_attr->ah_attr.grh.sgid_index = qp->sgid_idx;
+ qp_attr->ah_attr.grh.hop_limit = params.hop_limit_ttl;
+ qp_attr->ah_attr.grh.traffic_class = params.traffic_class_tos;
+
+ qp_attr->ah_attr.ah_flags = IB_AH_GRH;
+ qp_attr->ah_attr.port_num = 1;
+ qp_attr->ah_attr.sl = 0;
+ qp_attr->timeout = params.timeout;
+ qp_attr->rnr_retry = params.rnr_retry;
+ qp_attr->retry_cnt = params.retry_cnt;
+ qp_attr->min_rnr_timer = params.min_rnr_nak_timer;
+ qp_attr->pkey_index = params.pkey_index;
+ qp_attr->port_num = 1;
+ qp_attr->ah_attr.src_path_bits = 0;
+ qp_attr->ah_attr.static_rate = 0;
+ qp_attr->alt_pkey_index = 0;
+ qp_attr->alt_port_num = 0;
+ qp_attr->alt_timeout = 0;
+ memset(&qp_attr->alt_ah_attr, 0, sizeof(qp_attr->alt_ah_attr));
+
+ qp_attr->sq_draining = (params.state == QED_ROCE_QP_STATE_SQD) ? 1 : 0;
+ qp_attr->max_dest_rd_atomic = params.max_dest_rd_atomic;
+ qp_attr->max_rd_atomic = params.max_rd_atomic;
+ qp_attr->en_sqd_async_notify = (params.sqd_async) ? 1 : 0;
+
+ DP_DEBUG(dev, QEDR_MSG_QP, "QEDR_QUERY_QP: max_inline_data=%d\n",
+ qp_attr->cap.max_inline_data);
+
+err:
+ return rc;
+}
+
+int qedr_destroy_qp(struct ib_qp *ibqp)
+{
+ struct qedr_qp *qp = get_qedr_qp(ibqp);
+ struct qedr_dev *dev = qp->dev;
+ struct ib_qp_attr attr;
+ int attr_mask = 0;
+ int rc = 0;
+
+ DP_DEBUG(dev, QEDR_MSG_QP, "destroy qp: destroying %p, qp type=%d\n",
+ qp, qp->qp_type);
+
+ if (qp->state != (QED_ROCE_QP_STATE_RESET | QED_ROCE_QP_STATE_ERR |
+ QED_ROCE_QP_STATE_INIT)) {
+ attr.qp_state = IB_QPS_ERR;
+ attr_mask |= IB_QP_STATE;
+
+ /* Change the QP state to ERROR */
+ qedr_modify_qp(ibqp, &attr, attr_mask, NULL);
+ }
+
+ if (qp->qp_type != IB_QPT_GSI) {
+ rc = dev->ops->rdma_destroy_qp(dev->rdma_ctx, qp->qed_qp);
+ if (rc)
+ return rc;
+ } else {
+ qedr_destroy_gsi_qp(dev);
+ }
+
+ if (ibqp->uobject && ibqp->uobject->context) {
+ qedr_cleanup_user_sq(dev, qp);
+ qedr_cleanup_user_rq(dev, qp);
+ } else {
+ qedr_cleanup_kernel_sq(dev, qp);
+ qedr_cleanup_kernel_rq(dev, qp);
+ }
+
+ kfree(qp);
+
+ return rc;
+}
+
+struct ib_ah *qedr_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr)
+{
+ struct qedr_ah *ah;
+
+ ah = kzalloc(sizeof(*ah), GFP_ATOMIC);
+ if (!ah)
+ return ERR_PTR(-ENOMEM);
+
+ ah->attr = *attr;
+
+ return &ah->ibah;
+}
+
+int qedr_destroy_ah(struct ib_ah *ibah)
+{
+ struct qedr_ah *ah = get_qedr_ah(ibah);
+
+ kfree(ah);
+ return 0;
+}
+
+static void free_mr_info(struct qedr_dev *dev, struct mr_info *info)
+{
+ struct qedr_pbl *pbl, *tmp;
+
+ if (info->pbl_table)
+ list_add_tail(&info->pbl_table->list_entry,
+ &info->free_pbl_list);
+
+ if (!list_empty(&info->inuse_pbl_list))
+ list_splice(&info->inuse_pbl_list, &info->free_pbl_list);
+
+ list_for_each_entry_safe(pbl, tmp, &info->free_pbl_list, list_entry) {
+ list_del(&pbl->list_entry);
+ qedr_free_pbl(dev, &info->pbl_info, pbl);
+ }
+}
+
+static int init_mr_info(struct qedr_dev *dev, struct mr_info *info,
+ size_t page_list_len, bool two_layered)
+{
+ struct qedr_pbl *tmp;
+ int rc;
+
+ INIT_LIST_HEAD(&info->free_pbl_list);
+ INIT_LIST_HEAD(&info->inuse_pbl_list);
+
+ rc = qedr_prepare_pbl_tbl(dev, &info->pbl_info,
+ page_list_len, two_layered);
+ if (rc)
+ goto done;
+
+ info->pbl_table = qedr_alloc_pbl_tbl(dev, &info->pbl_info, GFP_KERNEL);
+ if (!info->pbl_table) {
+ rc = -ENOMEM;
+ goto done;
+ }
+
+ DP_DEBUG(dev, QEDR_MSG_MR, "pbl_table_pa = %pa\n",
+ &info->pbl_table->pa);
+
+ /* in usual case we use 2 PBLs, so we add one to free
+ * list and allocating another one
+ */
+ tmp = qedr_alloc_pbl_tbl(dev, &info->pbl_info, GFP_KERNEL);
+ if (!tmp) {
+ DP_DEBUG(dev, QEDR_MSG_MR, "Extra PBL is not allocated\n");
+ goto done;
+ }
+
+ list_add_tail(&tmp->list_entry, &info->free_pbl_list);
+
+ DP_DEBUG(dev, QEDR_MSG_MR, "extra pbl_table_pa = %pa\n", &tmp->pa);
+
+done:
+ if (rc)
+ free_mr_info(dev, info);
+
+ return rc;
+}
+
+struct ib_mr *qedr_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 len,
+ u64 usr_addr, int acc, struct ib_udata *udata)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibpd->device);
+ struct qedr_mr *mr;
+ struct qedr_pd *pd;
+ int rc = -ENOMEM;
+
+ pd = get_qedr_pd(ibpd);
+ DP_DEBUG(dev, QEDR_MSG_MR,
+ "qedr_register user mr pd = %d start = %lld, len = %lld, usr_addr = %lld, acc = %d\n",
+ pd->pd_id, start, len, usr_addr, acc);
+
+ if (acc & IB_ACCESS_REMOTE_WRITE && !(acc & IB_ACCESS_LOCAL_WRITE))
+ return ERR_PTR(-EINVAL);
+
+ mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+ if (!mr)
+ return ERR_PTR(rc);
+
+ mr->type = QEDR_MR_USER;
+
+ mr->umem = ib_umem_get(ibpd->uobject->context, start, len, acc, 0);
+ if (IS_ERR(mr->umem)) {
+ rc = -EFAULT;
+ goto err0;
+ }
+
+ rc = init_mr_info(dev, &mr->info, ib_umem_page_count(mr->umem), 1);
+ if (rc)
+ goto err1;
+
+ qedr_populate_pbls(dev, mr->umem, mr->info.pbl_table,
+ &mr->info.pbl_info);
+
+ rc = dev->ops->rdma_alloc_tid(dev->rdma_ctx, &mr->hw_mr.itid);
+ if (rc) {
+ DP_ERR(dev, "roce alloc tid returned an error %d\n", rc);
+ goto err1;
+ }
+
+ /* Index only, 18 bit long, lkey = itid << 8 | key */
+ mr->hw_mr.tid_type = QED_RDMA_TID_REGISTERED_MR;
+ mr->hw_mr.key = 0;
+ mr->hw_mr.pd = pd->pd_id;
+ mr->hw_mr.local_read = 1;
+ mr->hw_mr.local_write = (acc & IB_ACCESS_LOCAL_WRITE) ? 1 : 0;
+ mr->hw_mr.remote_read = (acc & IB_ACCESS_REMOTE_READ) ? 1 : 0;
+ mr->hw_mr.remote_write = (acc & IB_ACCESS_REMOTE_WRITE) ? 1 : 0;
+ mr->hw_mr.remote_atomic = (acc & IB_ACCESS_REMOTE_ATOMIC) ? 1 : 0;
+ mr->hw_mr.mw_bind = false;
+ mr->hw_mr.pbl_ptr = mr->info.pbl_table[0].pa;
+ mr->hw_mr.pbl_two_level = mr->info.pbl_info.two_layered;
+ mr->hw_mr.pbl_page_size_log = ilog2(mr->info.pbl_info.pbl_size);
+ mr->hw_mr.page_size_log = ilog2(mr->umem->page_size);
+ mr->hw_mr.fbo = ib_umem_offset(mr->umem);
+ mr->hw_mr.length = len;
+ mr->hw_mr.vaddr = usr_addr;
+ mr->hw_mr.zbva = false;
+ mr->hw_mr.phy_mr = false;
+ mr->hw_mr.dma_mr = false;
+
+ rc = dev->ops->rdma_register_tid(dev->rdma_ctx, &mr->hw_mr);
+ if (rc) {
+ DP_ERR(dev, "roce register tid returned an error %d\n", rc);
+ goto err2;
+ }
+
+ mr->ibmr.lkey = mr->hw_mr.itid << 8 | mr->hw_mr.key;
+ if (mr->hw_mr.remote_write || mr->hw_mr.remote_read ||
+ mr->hw_mr.remote_atomic)
+ mr->ibmr.rkey = mr->hw_mr.itid << 8 | mr->hw_mr.key;
+
+ DP_DEBUG(dev, QEDR_MSG_MR, "register user mr lkey: %x\n",
+ mr->ibmr.lkey);
+ return &mr->ibmr;
+
+err2:
+ dev->ops->rdma_free_tid(dev->rdma_ctx, mr->hw_mr.itid);
+err1:
+ qedr_free_pbl(dev, &mr->info.pbl_info, mr->info.pbl_table);
+err0:
+ kfree(mr);
+ return ERR_PTR(rc);
+}
+
+int qedr_dereg_mr(struct ib_mr *ib_mr)
+{
+ struct qedr_mr *mr = get_qedr_mr(ib_mr);
+ struct qedr_dev *dev = get_qedr_dev(ib_mr->device);
+ int rc = 0;
+
+ rc = dev->ops->rdma_deregister_tid(dev->rdma_ctx, mr->hw_mr.itid);
+ if (rc)
+ return rc;
+
+ dev->ops->rdma_free_tid(dev->rdma_ctx, mr->hw_mr.itid);
+
+ if ((mr->type != QEDR_MR_DMA) && (mr->type != QEDR_MR_FRMR))
+ qedr_free_pbl(dev, &mr->info.pbl_info, mr->info.pbl_table);
+
+ /* it could be user registered memory. */
+ if (mr->umem)
+ ib_umem_release(mr->umem);
+
+ kfree(mr);
+
+ return rc;
+}
+
+struct qedr_mr *__qedr_alloc_mr(struct ib_pd *ibpd, int max_page_list_len)
+{
+ struct qedr_pd *pd = get_qedr_pd(ibpd);
+ struct qedr_dev *dev = get_qedr_dev(ibpd->device);
+ struct qedr_mr *mr;
+ int rc = -ENOMEM;
+
+ DP_DEBUG(dev, QEDR_MSG_MR,
+ "qedr_alloc_frmr pd = %d max_page_list_len= %d\n", pd->pd_id,
+ max_page_list_len);
+
+ mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+ if (!mr)
+ return ERR_PTR(rc);
+
+ mr->dev = dev;
+ mr->type = QEDR_MR_FRMR;
+
+ rc = init_mr_info(dev, &mr->info, max_page_list_len, 1);
+ if (rc)
+ goto err0;
+
+ rc = dev->ops->rdma_alloc_tid(dev->rdma_ctx, &mr->hw_mr.itid);
+ if (rc) {
+ DP_ERR(dev, "roce alloc tid returned an error %d\n", rc);
+ goto err0;
+ }
+
+ /* Index only, 18 bit long, lkey = itid << 8 | key */
+ mr->hw_mr.tid_type = QED_RDMA_TID_FMR;
+ mr->hw_mr.key = 0;
+ mr->hw_mr.pd = pd->pd_id;
+ mr->hw_mr.local_read = 1;
+ mr->hw_mr.local_write = 0;
+ mr->hw_mr.remote_read = 0;
+ mr->hw_mr.remote_write = 0;
+ mr->hw_mr.remote_atomic = 0;
+ mr->hw_mr.mw_bind = false;
+ mr->hw_mr.pbl_ptr = 0;
+ mr->hw_mr.pbl_two_level = mr->info.pbl_info.two_layered;
+ mr->hw_mr.pbl_page_size_log = ilog2(mr->info.pbl_info.pbl_size);
+ mr->hw_mr.fbo = 0;
+ mr->hw_mr.length = 0;
+ mr->hw_mr.vaddr = 0;
+ mr->hw_mr.zbva = false;
+ mr->hw_mr.phy_mr = true;
+ mr->hw_mr.dma_mr = false;
+
+ rc = dev->ops->rdma_register_tid(dev->rdma_ctx, &mr->hw_mr);
+ if (rc) {
+ DP_ERR(dev, "roce register tid returned an error %d\n", rc);
+ goto err1;
+ }
+
+ mr->ibmr.lkey = mr->hw_mr.itid << 8 | mr->hw_mr.key;
+ mr->ibmr.rkey = mr->ibmr.lkey;
+
+ DP_DEBUG(dev, QEDR_MSG_MR, "alloc frmr: %x\n", mr->ibmr.lkey);
+ return mr;
+
+err1:
+ dev->ops->rdma_free_tid(dev->rdma_ctx, mr->hw_mr.itid);
+err0:
+ kfree(mr);
+ return ERR_PTR(rc);
+}
+
+struct ib_mr *qedr_alloc_mr(struct ib_pd *ibpd,
+ enum ib_mr_type mr_type, u32 max_num_sg)
+{
+ struct qedr_dev *dev;
+ struct qedr_mr *mr;
+
+ if (mr_type != IB_MR_TYPE_MEM_REG)
+ return ERR_PTR(-EINVAL);
+
+ mr = __qedr_alloc_mr(ibpd, max_num_sg);
+
+ if (IS_ERR(mr))
+ return ERR_PTR(-EINVAL);
+
+ dev = mr->dev;
+
+ return &mr->ibmr;
+}
+
+static int qedr_set_page(struct ib_mr *ibmr, u64 addr)
+{
+ struct qedr_mr *mr = get_qedr_mr(ibmr);
+ struct qedr_pbl *pbl_table;
+ struct regpair *pbe;
+ u32 pbes_in_page;
+
+ if (unlikely(mr->npages == mr->info.pbl_info.num_pbes)) {
+ DP_ERR(mr->dev, "qedr_set_page failes when %d\n", mr->npages);
+ return -ENOMEM;
+ }
+
+ DP_DEBUG(mr->dev, QEDR_MSG_MR, "qedr_set_page pages[%d] = 0x%llx\n",
+ mr->npages, addr);
+
+ pbes_in_page = mr->info.pbl_info.pbl_size / sizeof(u64);
+ pbl_table = mr->info.pbl_table + (mr->npages / pbes_in_page);
+ pbe = (struct regpair *)pbl_table->va;
+ pbe += mr->npages % pbes_in_page;
+ pbe->lo = cpu_to_le32((u32)addr);
+ pbe->hi = cpu_to_le32((u32)upper_32_bits(addr));
+
+ mr->npages++;
+
+ return 0;
+}
+
+static void handle_completed_mrs(struct qedr_dev *dev, struct mr_info *info)
+{
+ int work = info->completed - info->completed_handled - 1;
+
+ DP_DEBUG(dev, QEDR_MSG_MR, "Special FMR work = %d\n", work);
+ while (work-- > 0 && !list_empty(&info->inuse_pbl_list)) {
+ struct qedr_pbl *pbl;
+
+ /* Free all the page list that are possible to be freed
+ * (all the ones that were invalidated), under the assumption
+ * that if an FMR was completed successfully that means that
+ * if there was an invalidate operation before it also ended
+ */
+ pbl = list_first_entry(&info->inuse_pbl_list,
+ struct qedr_pbl, list_entry);
+ list_del(&pbl->list_entry);
+ list_add_tail(&pbl->list_entry, &info->free_pbl_list);
+ info->completed_handled++;
+ }
+}
+
+int qedr_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg,
+ int sg_nents, unsigned int *sg_offset)
+{
+ struct qedr_mr *mr = get_qedr_mr(ibmr);
+
+ mr->npages = 0;
+
+ handle_completed_mrs(mr->dev, &mr->info);
+ return ib_sg_to_pages(ibmr, sg, sg_nents, NULL, qedr_set_page);
+}
+
+struct ib_mr *qedr_get_dma_mr(struct ib_pd *ibpd, int acc)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibpd->device);
+ struct qedr_pd *pd = get_qedr_pd(ibpd);
+ struct qedr_mr *mr;
+ int rc;
+
+ mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+ if (!mr)
+ return ERR_PTR(-ENOMEM);
+
+ mr->type = QEDR_MR_DMA;
+
+ rc = dev->ops->rdma_alloc_tid(dev->rdma_ctx, &mr->hw_mr.itid);
+ if (rc) {
+ DP_ERR(dev, "roce alloc tid returned an error %d\n", rc);
+ goto err1;
+ }
+
+ /* index only, 18 bit long, lkey = itid << 8 | key */
+ mr->hw_mr.tid_type = QED_RDMA_TID_REGISTERED_MR;
+ mr->hw_mr.pd = pd->pd_id;
+ mr->hw_mr.local_read = 1;
+ mr->hw_mr.local_write = (acc & IB_ACCESS_LOCAL_WRITE) ? 1 : 0;
+ mr->hw_mr.remote_read = (acc & IB_ACCESS_REMOTE_READ) ? 1 : 0;
+ mr->hw_mr.remote_write = (acc & IB_ACCESS_REMOTE_WRITE) ? 1 : 0;
+ mr->hw_mr.remote_atomic = (acc & IB_ACCESS_REMOTE_ATOMIC) ? 1 : 0;
+ mr->hw_mr.dma_mr = true;
+
+ rc = dev->ops->rdma_register_tid(dev->rdma_ctx, &mr->hw_mr);
+ if (rc) {
+ DP_ERR(dev, "roce register tid returned an error %d\n", rc);
+ goto err2;
+ }
+
+ mr->ibmr.lkey = mr->hw_mr.itid << 8 | mr->hw_mr.key;
+ if (mr->hw_mr.remote_write || mr->hw_mr.remote_read ||
+ mr->hw_mr.remote_atomic)
+ mr->ibmr.rkey = mr->hw_mr.itid << 8 | mr->hw_mr.key;
+
+ DP_DEBUG(dev, QEDR_MSG_MR, "get dma mr: lkey = %x\n", mr->ibmr.lkey);
+ return &mr->ibmr;
+
+err2:
+ dev->ops->rdma_free_tid(dev->rdma_ctx, mr->hw_mr.itid);
+err1:
+ kfree(mr);
+ return ERR_PTR(rc);
+}
+
+static inline int qedr_wq_is_full(struct qedr_qp_hwq_info *wq)
+{
+ return (((wq->prod + 1) % wq->max_wr) == wq->cons);
+}
+
+static int sge_data_len(struct ib_sge *sg_list, int num_sge)
+{
+ int i, len = 0;
+
+ for (i = 0; i < num_sge; i++)
+ len += sg_list[i].length;
+
+ return len;
+}
+
+static void swap_wqe_data64(u64 *p)
+{
+ int i;
+
+ for (i = 0; i < QEDR_SQE_ELEMENT_SIZE / sizeof(u64); i++, p++)
+ *p = cpu_to_be64(cpu_to_le64(*p));
+}
+
+static u32 qedr_prepare_sq_inline_data(struct qedr_dev *dev,
+ struct qedr_qp *qp, u8 *wqe_size,
+ struct ib_send_wr *wr,
+ struct ib_send_wr **bad_wr, u8 *bits,
+ u8 bit)
+{
+ u32 data_size = sge_data_len(wr->sg_list, wr->num_sge);
+ char *seg_prt, *wqe;
+ int i, seg_siz;
+
+ if (data_size > ROCE_REQ_MAX_INLINE_DATA_SIZE) {
+ DP_ERR(dev, "Too much inline data in WR: %d\n", data_size);
+ *bad_wr = wr;
+ return 0;
+ }
+
+ if (!data_size)
+ return data_size;
+
+ *bits |= bit;
+
+ seg_prt = NULL;
+ wqe = NULL;
+ seg_siz = 0;
+
+ /* Copy data inline */
+ for (i = 0; i < wr->num_sge; i++) {
+ u32 len = wr->sg_list[i].length;
+ void *src = (void *)(uintptr_t)wr->sg_list[i].addr;
+
+ while (len > 0) {
+ u32 cur;
+
+ /* New segment required */
+ if (!seg_siz) {
+ wqe = (char *)qed_chain_produce(&qp->sq.pbl);
+ seg_prt = wqe;
+ seg_siz = sizeof(struct rdma_sq_common_wqe);
+ (*wqe_size)++;
+ }
+
+ /* Calculate currently allowed length */
+ cur = min_t(u32, len, seg_siz);
+ memcpy(seg_prt, src, cur);
+
+ /* Update segment variables */
+ seg_prt += cur;
+ seg_siz -= cur;
+
+ /* Update sge variables */
+ src += cur;
+ len -= cur;
+
+ /* Swap fully-completed segments */
+ if (!seg_siz)
+ swap_wqe_data64((u64 *)wqe);
+ }
+ }
+
+ /* swap last not completed segment */
+ if (seg_siz)
+ swap_wqe_data64((u64 *)wqe);
+
+ return data_size;
+}
+
+#define RQ_SGE_SET(sge, vaddr, vlength, vflags) \
+ do { \
+ DMA_REGPAIR_LE(sge->addr, vaddr); \
+ (sge)->length = cpu_to_le32(vlength); \
+ (sge)->flags = cpu_to_le32(vflags); \
+ } while (0)
+
+#define SRQ_HDR_SET(hdr, vwr_id, num_sge) \
+ do { \
+ DMA_REGPAIR_LE(hdr->wr_id, vwr_id); \
+ (hdr)->num_sges = num_sge; \
+ } while (0)
+
+#define SRQ_SGE_SET(sge, vaddr, vlength, vlkey) \
+ do { \
+ DMA_REGPAIR_LE(sge->addr, vaddr); \
+ (sge)->length = cpu_to_le32(vlength); \
+ (sge)->l_key = cpu_to_le32(vlkey); \
+ } while (0)
+
+static u32 qedr_prepare_sq_sges(struct qedr_qp *qp, u8 *wqe_size,
+ struct ib_send_wr *wr)
+{
+ u32 data_size = 0;
+ int i;
+
+ for (i = 0; i < wr->num_sge; i++) {
+ struct rdma_sq_sge *sge = qed_chain_produce(&qp->sq.pbl);
+
+ DMA_REGPAIR_LE(sge->addr, wr->sg_list[i].addr);
+ sge->l_key = cpu_to_le32(wr->sg_list[i].lkey);
+ sge->length = cpu_to_le32(wr->sg_list[i].length);
+ data_size += wr->sg_list[i].length;
+ }
+
+ if (wqe_size)
+ *wqe_size += wr->num_sge;
+
+ return data_size;
+}
+
+static u32 qedr_prepare_sq_rdma_data(struct qedr_dev *dev,
+ struct qedr_qp *qp,
+ struct rdma_sq_rdma_wqe_1st *rwqe,
+ struct rdma_sq_rdma_wqe_2nd *rwqe2,
+ struct ib_send_wr *wr,
+ struct ib_send_wr **bad_wr)
+{
+ rwqe2->r_key = cpu_to_le32(rdma_wr(wr)->rkey);
+ DMA_REGPAIR_LE(rwqe2->remote_va, rdma_wr(wr)->remote_addr);
+
+ if (wr->send_flags & IB_SEND_INLINE) {
+ u8 flags = 0;
+
+ SET_FIELD2(flags, RDMA_SQ_RDMA_WQE_1ST_INLINE_FLG, 1);
+ return qedr_prepare_sq_inline_data(dev, qp, &rwqe->wqe_size, wr,
+ bad_wr, &rwqe->flags, flags);
+ }
+
+ return qedr_prepare_sq_sges(qp, &rwqe->wqe_size, wr);
+}
+
+static u32 qedr_prepare_sq_send_data(struct qedr_dev *dev,
+ struct qedr_qp *qp,
+ struct rdma_sq_send_wqe_1st *swqe,
+ struct rdma_sq_send_wqe_2st *swqe2,
+ struct ib_send_wr *wr,
+ struct ib_send_wr **bad_wr)
+{
+ memset(swqe2, 0, sizeof(*swqe2));
+ if (wr->send_flags & IB_SEND_INLINE) {
+ u8 flags = 0;
+
+ SET_FIELD2(flags, RDMA_SQ_SEND_WQE_INLINE_FLG, 1);
+ return qedr_prepare_sq_inline_data(dev, qp, &swqe->wqe_size, wr,
+ bad_wr, &swqe->flags, flags);
+ }
+
+ return qedr_prepare_sq_sges(qp, &swqe->wqe_size, wr);
+}
+
+static int qedr_prepare_reg(struct qedr_qp *qp,
+ struct rdma_sq_fmr_wqe_1st *fwqe1,
+ struct ib_reg_wr *wr)
+{
+ struct qedr_mr *mr = get_qedr_mr(wr->mr);
+ struct rdma_sq_fmr_wqe_2nd *fwqe2;
+
+ fwqe2 = (struct rdma_sq_fmr_wqe_2nd *)qed_chain_produce(&qp->sq.pbl);
+ fwqe1->addr.hi = upper_32_bits(mr->ibmr.iova);
+ fwqe1->addr.lo = lower_32_bits(mr->ibmr.iova);
+ fwqe1->l_key = wr->key;
+
+ SET_FIELD2(fwqe2->access_ctrl, RDMA_SQ_FMR_WQE_2ND_REMOTE_READ,
+ !!(wr->access & IB_ACCESS_REMOTE_READ));
+ SET_FIELD2(fwqe2->access_ctrl, RDMA_SQ_FMR_WQE_2ND_REMOTE_WRITE,
+ !!(wr->access & IB_ACCESS_REMOTE_WRITE));
+ SET_FIELD2(fwqe2->access_ctrl, RDMA_SQ_FMR_WQE_2ND_ENABLE_ATOMIC,
+ !!(wr->access & IB_ACCESS_REMOTE_ATOMIC));
+ SET_FIELD2(fwqe2->access_ctrl, RDMA_SQ_FMR_WQE_2ND_LOCAL_READ, 1);
+ SET_FIELD2(fwqe2->access_ctrl, RDMA_SQ_FMR_WQE_2ND_LOCAL_WRITE,
+ !!(wr->access & IB_ACCESS_LOCAL_WRITE));
+ fwqe2->fmr_ctrl = 0;
+
+ SET_FIELD2(fwqe2->fmr_ctrl, RDMA_SQ_FMR_WQE_2ND_PAGE_SIZE_LOG,
+ ilog2(mr->ibmr.page_size) - 12);
+
+ fwqe2->length_hi = 0;
+ fwqe2->length_lo = mr->ibmr.length;
+ fwqe2->pbl_addr.hi = upper_32_bits(mr->info.pbl_table->pa);
+ fwqe2->pbl_addr.lo = lower_32_bits(mr->info.pbl_table->pa);
+
+ qp->wqe_wr_id[qp->sq.prod].mr = mr;
+
+ return 0;
+}
+
+enum ib_wc_opcode qedr_ib_to_wc_opcode(enum ib_wr_opcode opcode)
+{
+ switch (opcode) {
+ case IB_WR_RDMA_WRITE:
+ case IB_WR_RDMA_WRITE_WITH_IMM:
+ return IB_WC_RDMA_WRITE;
+ case IB_WR_SEND_WITH_IMM:
+ case IB_WR_SEND:
+ case IB_WR_SEND_WITH_INV:
+ return IB_WC_SEND;
+ case IB_WR_RDMA_READ:
+ return IB_WC_RDMA_READ;
+ case IB_WR_ATOMIC_CMP_AND_SWP:
+ return IB_WC_COMP_SWAP;
+ case IB_WR_ATOMIC_FETCH_AND_ADD:
+ return IB_WC_FETCH_ADD;
+ case IB_WR_REG_MR:
+ return IB_WC_REG_MR;
+ case IB_WR_LOCAL_INV:
+ return IB_WC_LOCAL_INV;
+ default:
+ return IB_WC_SEND;
+ }
+}
+
+inline bool qedr_can_post_send(struct qedr_qp *qp, struct ib_send_wr *wr)
+{
+ int wq_is_full, err_wr, pbl_is_full;
+ struct qedr_dev *dev = qp->dev;
+
+ /* prevent SQ overflow and/or processing of a bad WR */
+ err_wr = wr->num_sge > qp->sq.max_sges;
+ wq_is_full = qedr_wq_is_full(&qp->sq);
+ pbl_is_full = qed_chain_get_elem_left_u32(&qp->sq.pbl) <
+ QEDR_MAX_SQE_ELEMENTS_PER_SQE;
+ if (wq_is_full || err_wr || pbl_is_full) {
+ if (wq_is_full && !(qp->err_bitmap & QEDR_QP_ERR_SQ_FULL)) {
+ DP_ERR(dev,
+ "error: WQ is full. Post send on QP %p failed (this error appears only once)\n",
+ qp);
+ qp->err_bitmap |= QEDR_QP_ERR_SQ_FULL;
+ }
+
+ if (err_wr && !(qp->err_bitmap & QEDR_QP_ERR_BAD_SR)) {
+ DP_ERR(dev,
+ "error: WR is bad. Post send on QP %p failed (this error appears only once)\n",
+ qp);
+ qp->err_bitmap |= QEDR_QP_ERR_BAD_SR;
+ }
+
+ if (pbl_is_full &&
+ !(qp->err_bitmap & QEDR_QP_ERR_SQ_PBL_FULL)) {
+ DP_ERR(dev,
+ "error: WQ PBL is full. Post send on QP %p failed (this error appears only once)\n",
+ qp);
+ qp->err_bitmap |= QEDR_QP_ERR_SQ_PBL_FULL;
+ }
+ return false;
+ }
+ return true;
+}
+
+int __qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
+ struct ib_send_wr **bad_wr)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibqp->device);
+ struct qedr_qp *qp = get_qedr_qp(ibqp);
+ struct rdma_sq_atomic_wqe_1st *awqe1;
+ struct rdma_sq_atomic_wqe_2nd *awqe2;
+ struct rdma_sq_atomic_wqe_3rd *awqe3;
+ struct rdma_sq_send_wqe_2st *swqe2;
+ struct rdma_sq_local_inv_wqe *iwqe;
+ struct rdma_sq_rdma_wqe_2nd *rwqe2;
+ struct rdma_sq_send_wqe_1st *swqe;
+ struct rdma_sq_rdma_wqe_1st *rwqe;
+ struct rdma_sq_fmr_wqe_1st *fwqe1;
+ struct rdma_sq_common_wqe *wqe;
+ u32 length;
+ int rc = 0;
+ bool comp;
+
+ if (!qedr_can_post_send(qp, wr)) {
+ *bad_wr = wr;
+ return -ENOMEM;
+ }
+
+ wqe = qed_chain_produce(&qp->sq.pbl);
+ qp->wqe_wr_id[qp->sq.prod].signaled =
+ !!(wr->send_flags & IB_SEND_SIGNALED) || qp->signaled;
+
+ wqe->flags = 0;
+ SET_FIELD2(wqe->flags, RDMA_SQ_SEND_WQE_SE_FLG,
+ !!(wr->send_flags & IB_SEND_SOLICITED));
+ comp = (!!(wr->send_flags & IB_SEND_SIGNALED)) || qp->signaled;
+ SET_FIELD2(wqe->flags, RDMA_SQ_SEND_WQE_COMP_FLG, comp);
+ SET_FIELD2(wqe->flags, RDMA_SQ_SEND_WQE_RD_FENCE_FLG,
+ !!(wr->send_flags & IB_SEND_FENCE));
+ wqe->prev_wqe_size = qp->prev_wqe_size;
+
+ qp->wqe_wr_id[qp->sq.prod].opcode = qedr_ib_to_wc_opcode(wr->opcode);
+
+ switch (wr->opcode) {
+ case IB_WR_SEND_WITH_IMM:
+ wqe->req_type = RDMA_SQ_REQ_TYPE_SEND_WITH_IMM;
+ swqe = (struct rdma_sq_send_wqe_1st *)wqe;
+ swqe->wqe_size = 2;
+ swqe2 = qed_chain_produce(&qp->sq.pbl);
+
+ swqe->inv_key_or_imm_data = cpu_to_le32(wr->ex.imm_data);
+ length = qedr_prepare_sq_send_data(dev, qp, swqe, swqe2,
+ wr, bad_wr);
+ swqe->length = cpu_to_le32(length);
+ qp->wqe_wr_id[qp->sq.prod].wqe_size = swqe->wqe_size;
+ qp->prev_wqe_size = swqe->wqe_size;
+ qp->wqe_wr_id[qp->sq.prod].bytes_len = swqe->length;
+ break;
+ case IB_WR_SEND:
+ wqe->req_type = RDMA_SQ_REQ_TYPE_SEND;
+ swqe = (struct rdma_sq_send_wqe_1st *)wqe;
+
+ swqe->wqe_size = 2;
+ swqe2 = qed_chain_produce(&qp->sq.pbl);
+ length = qedr_prepare_sq_send_data(dev, qp, swqe, swqe2,
+ wr, bad_wr);
+ swqe->length = cpu_to_le32(length);
+ qp->wqe_wr_id[qp->sq.prod].wqe_size = swqe->wqe_size;
+ qp->prev_wqe_size = swqe->wqe_size;
+ qp->wqe_wr_id[qp->sq.prod].bytes_len = swqe->length;
+ break;
+ case IB_WR_SEND_WITH_INV:
+ wqe->req_type = RDMA_SQ_REQ_TYPE_SEND_WITH_INVALIDATE;
+ swqe = (struct rdma_sq_send_wqe_1st *)wqe;
+ swqe2 = qed_chain_produce(&qp->sq.pbl);
+ swqe->wqe_size = 2;
+ swqe->inv_key_or_imm_data = cpu_to_le32(wr->ex.invalidate_rkey);
+ length = qedr_prepare_sq_send_data(dev, qp, swqe, swqe2,
+ wr, bad_wr);
+ swqe->length = cpu_to_le32(length);
+ qp->wqe_wr_id[qp->sq.prod].wqe_size = swqe->wqe_size;
+ qp->prev_wqe_size = swqe->wqe_size;
+ qp->wqe_wr_id[qp->sq.prod].bytes_len = swqe->length;
+ break;
+
+ case IB_WR_RDMA_WRITE_WITH_IMM:
+ wqe->req_type = RDMA_SQ_REQ_TYPE_RDMA_WR_WITH_IMM;
+ rwqe = (struct rdma_sq_rdma_wqe_1st *)wqe;
+
+ rwqe->wqe_size = 2;
+ rwqe->imm_data = htonl(cpu_to_le32(wr->ex.imm_data));
+ rwqe2 = qed_chain_produce(&qp->sq.pbl);
+ length = qedr_prepare_sq_rdma_data(dev, qp, rwqe, rwqe2,
+ wr, bad_wr);
+ rwqe->length = cpu_to_le32(length);
+ qp->wqe_wr_id[qp->sq.prod].wqe_size = rwqe->wqe_size;
+ qp->prev_wqe_size = rwqe->wqe_size;
+ qp->wqe_wr_id[qp->sq.prod].bytes_len = rwqe->length;
+ break;
+ case IB_WR_RDMA_WRITE:
+ wqe->req_type = RDMA_SQ_REQ_TYPE_RDMA_WR;
+ rwqe = (struct rdma_sq_rdma_wqe_1st *)wqe;
+
+ rwqe->wqe_size = 2;
+ rwqe2 = qed_chain_produce(&qp->sq.pbl);
+ length = qedr_prepare_sq_rdma_data(dev, qp, rwqe, rwqe2,
+ wr, bad_wr);
+ rwqe->length = cpu_to_le32(length);
+ qp->wqe_wr_id[qp->sq.prod].wqe_size = rwqe->wqe_size;
+ qp->prev_wqe_size = rwqe->wqe_size;
+ qp->wqe_wr_id[qp->sq.prod].bytes_len = rwqe->length;
+ break;
+ case IB_WR_RDMA_READ_WITH_INV:
+ DP_ERR(dev,
+ "RDMA READ WITH INVALIDATE not supported\n");
+ *bad_wr = wr;
+ rc = -EINVAL;
+ break;
+
+ case IB_WR_RDMA_READ:
+ wqe->req_type = RDMA_SQ_REQ_TYPE_RDMA_RD;
+ rwqe = (struct rdma_sq_rdma_wqe_1st *)wqe;
+
+ rwqe->wqe_size = 2;
+ rwqe2 = qed_chain_produce(&qp->sq.pbl);
+ length = qedr_prepare_sq_rdma_data(dev, qp, rwqe, rwqe2,
+ wr, bad_wr);
+ rwqe->length = cpu_to_le32(length);
+ qp->wqe_wr_id[qp->sq.prod].wqe_size = rwqe->wqe_size;
+ qp->prev_wqe_size = rwqe->wqe_size;
+ qp->wqe_wr_id[qp->sq.prod].bytes_len = rwqe->length;
+ break;
+
+ case IB_WR_ATOMIC_CMP_AND_SWP:
+ case IB_WR_ATOMIC_FETCH_AND_ADD:
+ awqe1 = (struct rdma_sq_atomic_wqe_1st *)wqe;
+ awqe1->wqe_size = 4;
+
+ awqe2 = qed_chain_produce(&qp->sq.pbl);
+ DMA_REGPAIR_LE(awqe2->remote_va, atomic_wr(wr)->remote_addr);
+ awqe2->r_key = cpu_to_le32(atomic_wr(wr)->rkey);
+
+ awqe3 = qed_chain_produce(&qp->sq.pbl);
+
+ if (wr->opcode == IB_WR_ATOMIC_FETCH_AND_ADD) {
+ wqe->req_type = RDMA_SQ_REQ_TYPE_ATOMIC_ADD;
+ DMA_REGPAIR_LE(awqe3->swap_data,
+ atomic_wr(wr)->compare_add);
+ } else {
+ wqe->req_type = RDMA_SQ_REQ_TYPE_ATOMIC_CMP_AND_SWAP;
+ DMA_REGPAIR_LE(awqe3->swap_data,
+ atomic_wr(wr)->swap);
+ DMA_REGPAIR_LE(awqe3->cmp_data,
+ atomic_wr(wr)->compare_add);
+ }
+
+ qedr_prepare_sq_sges(qp, NULL, wr);
+
+ qp->wqe_wr_id[qp->sq.prod].wqe_size = awqe1->wqe_size;
+ qp->prev_wqe_size = awqe1->wqe_size;
+ break;
+
+ case IB_WR_LOCAL_INV:
+ iwqe = (struct rdma_sq_local_inv_wqe *)wqe;
+ iwqe->wqe_size = 1;
+
+ iwqe->req_type = RDMA_SQ_REQ_TYPE_LOCAL_INVALIDATE;
+ iwqe->inv_l_key = wr->ex.invalidate_rkey;
+ qp->wqe_wr_id[qp->sq.prod].wqe_size = iwqe->wqe_size;
+ qp->prev_wqe_size = iwqe->wqe_size;
+ break;
+ case IB_WR_REG_MR:
+ DP_DEBUG(dev, QEDR_MSG_CQ, "REG_MR\n");
+ wqe->req_type = RDMA_SQ_REQ_TYPE_FAST_MR;
+ fwqe1 = (struct rdma_sq_fmr_wqe_1st *)wqe;
+ fwqe1->wqe_size = 2;
+
+ rc = qedr_prepare_reg(qp, fwqe1, reg_wr(wr));
+ if (rc) {
+ DP_ERR(dev, "IB_REG_MR failed rc=%d\n", rc);
+ *bad_wr = wr;
+ break;
+ }
+
+ qp->wqe_wr_id[qp->sq.prod].wqe_size = fwqe1->wqe_size;
+ qp->prev_wqe_size = fwqe1->wqe_size;
+ break;
+ default:
+ DP_ERR(dev, "invalid opcode 0x%x!\n", wr->opcode);
+ rc = -EINVAL;
+ *bad_wr = wr;
+ break;
+ }
+
+ if (*bad_wr) {
+ u16 value;
+
+ /* Restore prod to its position before
+ * this WR was processed
+ */
+ value = le16_to_cpu(qp->sq.db_data.data.value);
+ qed_chain_set_prod(&qp->sq.pbl, value, wqe);
+
+ /* Restore prev_wqe_size */
+ qp->prev_wqe_size = wqe->prev_wqe_size;
+ rc = -EINVAL;
+ DP_ERR(dev, "POST SEND FAILED\n");
+ }
+
+ return rc;
+}
+
+int qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
+ struct ib_send_wr **bad_wr)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibqp->device);
+ struct qedr_qp *qp = get_qedr_qp(ibqp);
+ unsigned long flags;
+ int rc = 0;
+
+ *bad_wr = NULL;
+
+ if (qp->qp_type == IB_QPT_GSI)
+ return qedr_gsi_post_send(ibqp, wr, bad_wr);
+
+ spin_lock_irqsave(&qp->q_lock, flags);
+
+ if ((qp->state == QED_ROCE_QP_STATE_RESET) ||
+ (qp->state == QED_ROCE_QP_STATE_ERR)) {
+ spin_unlock_irqrestore(&qp->q_lock, flags);
+ *bad_wr = wr;
+ DP_DEBUG(dev, QEDR_MSG_CQ,
+ "QP in wrong state! QP icid=0x%x state %d\n",
+ qp->icid, qp->state);
+ return -EINVAL;
+ }
+
+ if (!wr) {
+ DP_ERR(dev, "Got an empty post send.\n");
+ return -EINVAL;
+ }
+
+ while (wr) {
+ rc = __qedr_post_send(ibqp, wr, bad_wr);
+ if (rc)
+ break;
+
+ qp->wqe_wr_id[qp->sq.prod].wr_id = wr->wr_id;
+
+ qedr_inc_sw_prod(&qp->sq);
+
+ qp->sq.db_data.data.value++;
+
+ wr = wr->next;
+ }
+
+ /* Trigger doorbell
+ * If there was a failure in the first WR then it will be triggered in
+ * vane. However this is not harmful (as long as the producer value is
+ * unchanged). For performance reasons we avoid checking for this
+ * redundant doorbell.
+ */
+ wmb();
+ writel(qp->sq.db_data.raw, qp->sq.db);
+
+ /* Make sure write sticks */
+ mmiowb();
+
+ spin_unlock_irqrestore(&qp->q_lock, flags);
+
+ return rc;
+}
+
+int qedr_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
+ struct ib_recv_wr **bad_wr)
+{
+ struct qedr_qp *qp = get_qedr_qp(ibqp);
+ struct qedr_dev *dev = qp->dev;
+ unsigned long flags;
+ int status = 0;
+
+ if (qp->qp_type == IB_QPT_GSI)
+ return qedr_gsi_post_recv(ibqp, wr, bad_wr);
+
+ spin_lock_irqsave(&qp->q_lock, flags);
+
+ if ((qp->state == QED_ROCE_QP_STATE_RESET) ||
+ (qp->state == QED_ROCE_QP_STATE_ERR)) {
+ spin_unlock_irqrestore(&qp->q_lock, flags);
+ *bad_wr = wr;
+ return -EINVAL;
+ }
+
+ while (wr) {
+ int i;
+
+ if (qed_chain_get_elem_left_u32(&qp->rq.pbl) <
+ QEDR_MAX_RQE_ELEMENTS_PER_RQE ||
+ wr->num_sge > qp->rq.max_sges) {
+ DP_ERR(dev, "Can't post WR (%d < %d) || (%d > %d)\n",
+ qed_chain_get_elem_left_u32(&qp->rq.pbl),
+ QEDR_MAX_RQE_ELEMENTS_PER_RQE, wr->num_sge,
+ qp->rq.max_sges);
+ status = -ENOMEM;
+ *bad_wr = wr;
+ break;
+ }
+ for (i = 0; i < wr->num_sge; i++) {
+ u32 flags = 0;
+ struct rdma_rq_sge *rqe =
+ qed_chain_produce(&qp->rq.pbl);
+
+ /* First one must include the number
+ * of SGE in the list
+ */
+ if (!i)
+ SET_FIELD(flags, RDMA_RQ_SGE_NUM_SGES,
+ wr->num_sge);
+
+ SET_FIELD(flags, RDMA_RQ_SGE_L_KEY,
+ wr->sg_list[i].lkey);
+
+ RQ_SGE_SET(rqe, wr->sg_list[i].addr,
+ wr->sg_list[i].length, flags);
+ }
+
+ /* Special case of no sges. FW requires between 1-4 sges...
+ * in this case we need to post 1 sge with length zero. this is
+ * because rdma write with immediate consumes an RQ.
+ */
+ if (!wr->num_sge) {
+ u32 flags = 0;
+ struct rdma_rq_sge *rqe =
+ qed_chain_produce(&qp->rq.pbl);
+
+ /* First one must include the number
+ * of SGE in the list
+ */
+ SET_FIELD(flags, RDMA_RQ_SGE_L_KEY, 0);
+ SET_FIELD(flags, RDMA_RQ_SGE_NUM_SGES, 1);
+
+ RQ_SGE_SET(rqe, 0, 0, flags);
+ i = 1;
+ }
+
+ qp->rqe_wr_id[qp->rq.prod].wr_id = wr->wr_id;
+ qp->rqe_wr_id[qp->rq.prod].wqe_size = i;
+
+ qedr_inc_sw_prod(&qp->rq);
+
+ /* Flush all the writes before signalling doorbell */
+ wmb();
+
+ qp->rq.db_data.data.value++;
+
+ writel(qp->rq.db_data.raw, qp->rq.db);
+
+ /* Make sure write sticks */
+ mmiowb();
+
+ wr = wr->next;
+ }
+
+ spin_unlock_irqrestore(&qp->q_lock, flags);
+
+ return status;
+}
+
+static int is_valid_cqe(struct qedr_cq *cq, union rdma_cqe *cqe)
+{
+ struct rdma_cqe_requester *resp_cqe = &cqe->req;
+
+ return (resp_cqe->flags & RDMA_CQE_REQUESTER_TOGGLE_BIT_MASK) ==
+ cq->pbl_toggle;
+}
+
+static struct qedr_qp *cqe_get_qp(union rdma_cqe *cqe)
+{
+ struct rdma_cqe_requester *resp_cqe = &cqe->req;
+ struct qedr_qp *qp;
+
+ qp = (struct qedr_qp *)(uintptr_t)HILO_GEN(resp_cqe->qp_handle.hi,
+ resp_cqe->qp_handle.lo,
+ u64);
+ return qp;
+}
+
+static enum rdma_cqe_type cqe_get_type(union rdma_cqe *cqe)
+{
+ struct rdma_cqe_requester *resp_cqe = &cqe->req;
+
+ return GET_FIELD(resp_cqe->flags, RDMA_CQE_REQUESTER_TYPE);
+}
+
+/* Return latest CQE (needs processing) */
+static union rdma_cqe *get_cqe(struct qedr_cq *cq)
+{
+ return cq->latest_cqe;
+}
+
+/* In fmr we need to increase the number of fmr completed counter for the fmr
+ * algorithm determining whether we can free a pbl or not.
+ * we need to perform this whether the work request was signaled or not. for
+ * this purpose we call this function from the condition that checks if a wr
+ * should be skipped, to make sure we don't miss it ( possibly this fmr
+ * operation was not signalted)
+ */
+static inline void qedr_chk_if_fmr(struct qedr_qp *qp)
+{
+ if (qp->wqe_wr_id[qp->sq.cons].opcode == IB_WC_REG_MR)
+ qp->wqe_wr_id[qp->sq.cons].mr->info.completed++;
+}
+
+static int process_req(struct qedr_dev *dev, struct qedr_qp *qp,
+ struct qedr_cq *cq, int num_entries,
+ struct ib_wc *wc, u16 hw_cons, enum ib_wc_status status,
+ int force)
+{
+ u16 cnt = 0;
+
+ while (num_entries && qp->sq.wqe_cons != hw_cons) {
+ if (!qp->wqe_wr_id[qp->sq.cons].signaled && !force) {
+ qedr_chk_if_fmr(qp);
+ /* skip WC */
+ goto next_cqe;
+ }
+
+ /* fill WC */
+ wc->status = status;
+ wc->wc_flags = 0;
+ wc->src_qp = qp->id;
+ wc->qp = &qp->ibqp;
+
+ wc->wr_id = qp->wqe_wr_id[qp->sq.cons].wr_id;
+ wc->opcode = qp->wqe_wr_id[qp->sq.cons].opcode;
+
+ switch (wc->opcode) {
+ case IB_WC_RDMA_WRITE:
+ wc->byte_len = qp->wqe_wr_id[qp->sq.cons].bytes_len;
+ break;
+ case IB_WC_COMP_SWAP:
+ case IB_WC_FETCH_ADD:
+ wc->byte_len = 8;
+ break;
+ case IB_WC_REG_MR:
+ qp->wqe_wr_id[qp->sq.cons].mr->info.completed++;
+ break;
+ default:
+ break;
+ }
+
+ num_entries--;
+ wc++;
+ cnt++;
+next_cqe:
+ while (qp->wqe_wr_id[qp->sq.cons].wqe_size--)
+ qed_chain_consume(&qp->sq.pbl);
+ qedr_inc_sw_cons(&qp->sq);
+ }
+
+ return cnt;
+}
+
+static int qedr_poll_cq_req(struct qedr_dev *dev,
+ struct qedr_qp *qp, struct qedr_cq *cq,
+ int num_entries, struct ib_wc *wc,
+ struct rdma_cqe_requester *req)
+{
+ int cnt = 0;
+
+ switch (req->status) {
+ case RDMA_CQE_REQ_STS_OK:
+ cnt = process_req(dev, qp, cq, num_entries, wc, req->sq_cons,
+ IB_WC_SUCCESS, 0);
+ break;
+ case RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR:
+ DP_ERR(dev,
+ "Error: POLL CQ with RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR. CQ icid=0x%x, QP icid=0x%x\n",
+ cq->icid, qp->icid);
+ cnt = process_req(dev, qp, cq, num_entries, wc, req->sq_cons,
+ IB_WC_WR_FLUSH_ERR, 0);
+ break;
+ default:
+ /* process all WQE before the cosumer */
+ qp->state = QED_ROCE_QP_STATE_ERR;
+ cnt = process_req(dev, qp, cq, num_entries, wc,
+ req->sq_cons - 1, IB_WC_SUCCESS, 0);
+ wc += cnt;
+ /* if we have extra WC fill it with actual error info */
+ if (cnt < num_entries) {
+ enum ib_wc_status wc_status;
+
+ switch (req->status) {
+ case RDMA_CQE_REQ_STS_BAD_RESPONSE_ERR:
+ DP_ERR(dev,
+ "Error: POLL CQ with RDMA_CQE_REQ_STS_BAD_RESPONSE_ERR. CQ icid=0x%x, QP icid=0x%x\n",
+ cq->icid, qp->icid);
+ wc_status = IB_WC_BAD_RESP_ERR;
+ break;
+ case RDMA_CQE_REQ_STS_LOCAL_LENGTH_ERR:
+ DP_ERR(dev,
+ "Error: POLL CQ with RDMA_CQE_REQ_STS_LOCAL_LENGTH_ERR. CQ icid=0x%x, QP icid=0x%x\n",
+ cq->icid, qp->icid);
+ wc_status = IB_WC_LOC_LEN_ERR;
+ break;
+ case RDMA_CQE_REQ_STS_LOCAL_QP_OPERATION_ERR:
+ DP_ERR(dev,
+ "Error: POLL CQ with RDMA_CQE_REQ_STS_LOCAL_QP_OPERATION_ERR. CQ icid=0x%x, QP icid=0x%x\n",
+ cq->icid, qp->icid);
+ wc_status = IB_WC_LOC_QP_OP_ERR;
+ break;
+ case RDMA_CQE_REQ_STS_LOCAL_PROTECTION_ERR:
+ DP_ERR(dev,
+ "Error: POLL CQ with RDMA_CQE_REQ_STS_LOCAL_PROTECTION_ERR. CQ icid=0x%x, QP icid=0x%x\n",
+ cq->icid, qp->icid);
+ wc_status = IB_WC_LOC_PROT_ERR;
+ break;
+ case RDMA_CQE_REQ_STS_MEMORY_MGT_OPERATION_ERR:
+ DP_ERR(dev,
+ "Error: POLL CQ with RDMA_CQE_REQ_STS_MEMORY_MGT_OPERATION_ERR. CQ icid=0x%x, QP icid=0x%x\n",
+ cq->icid, qp->icid);
+ wc_status = IB_WC_MW_BIND_ERR;
+ break;
+ case RDMA_CQE_REQ_STS_REMOTE_INVALID_REQUEST_ERR:
+ DP_ERR(dev,
+ "Error: POLL CQ with RDMA_CQE_REQ_STS_REMOTE_INVALID_REQUEST_ERR. CQ icid=0x%x, QP icid=0x%x\n",
+ cq->icid, qp->icid);
+ wc_status = IB_WC_REM_INV_REQ_ERR;
+ break;
+ case RDMA_CQE_REQ_STS_REMOTE_ACCESS_ERR:
+ DP_ERR(dev,
+ "Error: POLL CQ with RDMA_CQE_REQ_STS_REMOTE_ACCESS_ERR. CQ icid=0x%x, QP icid=0x%x\n",
+ cq->icid, qp->icid);
+ wc_status = IB_WC_REM_ACCESS_ERR;
+ break;
+ case RDMA_CQE_REQ_STS_REMOTE_OPERATION_ERR:
+ DP_ERR(dev,
+ "Error: POLL CQ with RDMA_CQE_REQ_STS_REMOTE_OPERATION_ERR. CQ icid=0x%x, QP icid=0x%x\n",
+ cq->icid, qp->icid);
+ wc_status = IB_WC_REM_OP_ERR;
+ break;
+ case RDMA_CQE_REQ_STS_RNR_NAK_RETRY_CNT_ERR:
+ DP_ERR(dev,
+ "Error: POLL CQ with RDMA_CQE_REQ_STS_RNR_NAK_RETRY_CNT_ERR. CQ icid=0x%x, QP icid=0x%x\n",
+ cq->icid, qp->icid);
+ wc_status = IB_WC_RNR_RETRY_EXC_ERR;
+ break;
+ case RDMA_CQE_REQ_STS_TRANSPORT_RETRY_CNT_ERR:
+ DP_ERR(dev,
+ "Error: POLL CQ with ROCE_CQE_REQ_STS_TRANSPORT_RETRY_CNT_ERR. CQ icid=0x%x, QP icid=0x%x\n",
+ cq->icid, qp->icid);
+ wc_status = IB_WC_RETRY_EXC_ERR;
+ break;
+ default:
+ DP_ERR(dev,
+ "Error: POLL CQ with IB_WC_GENERAL_ERR. CQ icid=0x%x, QP icid=0x%x\n",
+ cq->icid, qp->icid);
+ wc_status = IB_WC_GENERAL_ERR;
+ }
+ cnt += process_req(dev, qp, cq, 1, wc, req->sq_cons,
+ wc_status, 1);
+ }
+ }
+
+ return cnt;
+}
+
+static void __process_resp_one(struct qedr_dev *dev, struct qedr_qp *qp,
+ struct qedr_cq *cq, struct ib_wc *wc,
+ struct rdma_cqe_responder *resp, u64 wr_id)
+{
+ enum ib_wc_status wc_status = IB_WC_SUCCESS;
+ u8 flags;
+
+ wc->opcode = IB_WC_RECV;
+ wc->wc_flags = 0;
+
+ switch (resp->status) {
+ case RDMA_CQE_RESP_STS_LOCAL_ACCESS_ERR:
+ wc_status = IB_WC_LOC_ACCESS_ERR;
+ break;
+ case RDMA_CQE_RESP_STS_LOCAL_LENGTH_ERR:
+ wc_status = IB_WC_LOC_LEN_ERR;
+ break;
+ case RDMA_CQE_RESP_STS_LOCAL_QP_OPERATION_ERR:
+ wc_status = IB_WC_LOC_QP_OP_ERR;
+ break;
+ case RDMA_CQE_RESP_STS_LOCAL_PROTECTION_ERR:
+ wc_status = IB_WC_LOC_PROT_ERR;
+ break;
+ case RDMA_CQE_RESP_STS_MEMORY_MGT_OPERATION_ERR:
+ wc_status = IB_WC_MW_BIND_ERR;
+ break;
+ case RDMA_CQE_RESP_STS_REMOTE_INVALID_REQUEST_ERR:
+ wc_status = IB_WC_REM_INV_RD_REQ_ERR;
+ break;
+ case RDMA_CQE_RESP_STS_OK:
+ wc_status = IB_WC_SUCCESS;
+ wc->byte_len = le32_to_cpu(resp->length);
+
+ flags = resp->flags & QEDR_RESP_RDMA_IMM;
+
+ if (flags == QEDR_RESP_RDMA_IMM)
+ wc->opcode = IB_WC_RECV_RDMA_WITH_IMM;
+
+ if (flags == QEDR_RESP_RDMA_IMM || flags == QEDR_RESP_IMM) {
+ wc->ex.imm_data =
+ le32_to_cpu(resp->imm_data_or_inv_r_Key);
+ wc->wc_flags |= IB_WC_WITH_IMM;
+ }
+ break;
+ default:
+ wc->status = IB_WC_GENERAL_ERR;
+ DP_ERR(dev, "Invalid CQE status detected\n");
+ }
+
+ /* fill WC */
+ wc->status = wc_status;
+ wc->src_qp = qp->id;
+ wc->qp = &qp->ibqp;
+ wc->wr_id = wr_id;
+}
+
+static int process_resp_one(struct qedr_dev *dev, struct qedr_qp *qp,
+ struct qedr_cq *cq, struct ib_wc *wc,
+ struct rdma_cqe_responder *resp)
+{
+ u64 wr_id = qp->rqe_wr_id[qp->rq.cons].wr_id;
+
+ __process_resp_one(dev, qp, cq, wc, resp, wr_id);
+
+ while (qp->rqe_wr_id[qp->rq.cons].wqe_size--)
+ qed_chain_consume(&qp->rq.pbl);
+ qedr_inc_sw_cons(&qp->rq);
+
+ return 1;
+}
+
+static int process_resp_flush(struct qedr_qp *qp, struct qedr_cq *cq,
+ int num_entries, struct ib_wc *wc, u16 hw_cons)
+{
+ u16 cnt = 0;
+
+ while (num_entries && qp->rq.wqe_cons != hw_cons) {
+ /* fill WC */
+ wc->status = IB_WC_WR_FLUSH_ERR;
+ wc->wc_flags = 0;
+ wc->src_qp = qp->id;
+ wc->byte_len = 0;
+ wc->wr_id = qp->rqe_wr_id[qp->rq.cons].wr_id;
+ wc->qp = &qp->ibqp;
+ num_entries--;
+ wc++;
+ cnt++;
+ while (qp->rqe_wr_id[qp->rq.cons].wqe_size--)
+ qed_chain_consume(&qp->rq.pbl);
+ qedr_inc_sw_cons(&qp->rq);
+ }
+
+ return cnt;
+}
+
+static void try_consume_resp_cqe(struct qedr_cq *cq, struct qedr_qp *qp,
+ struct rdma_cqe_responder *resp, int *update)
+{
+ if (le16_to_cpu(resp->rq_cons) == qp->rq.wqe_cons) {
+ consume_cqe(cq);
+ *update |= 1;
+ }
+}
+
+static int qedr_poll_cq_resp(struct qedr_dev *dev, struct qedr_qp *qp,
+ struct qedr_cq *cq, int num_entries,
+ struct ib_wc *wc, struct rdma_cqe_responder *resp,
+ int *update)
+{
+ int cnt;
+
+ if (resp->status == RDMA_CQE_RESP_STS_WORK_REQUEST_FLUSHED_ERR) {
+ cnt = process_resp_flush(qp, cq, num_entries, wc,
+ resp->rq_cons);
+ try_consume_resp_cqe(cq, qp, resp, update);
+ } else {
+ cnt = process_resp_one(dev, qp, cq, wc, resp);
+ consume_cqe(cq);
+ *update |= 1;
+ }
+
+ return cnt;
+}
+
+static void try_consume_req_cqe(struct qedr_cq *cq, struct qedr_qp *qp,
+ struct rdma_cqe_requester *req, int *update)
+{
+ if (le16_to_cpu(req->sq_cons) == qp->sq.wqe_cons) {
+ consume_cqe(cq);
+ *update |= 1;
+ }
+}
+
+int qedr_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibcq->device);
+ struct qedr_cq *cq = get_qedr_cq(ibcq);
+ union rdma_cqe *cqe = cq->latest_cqe;
+ u32 old_cons, new_cons;
+ unsigned long flags;
+ int update = 0;
+ int done = 0;
+
+ if (cq->cq_type == QEDR_CQ_TYPE_GSI)
+ return qedr_gsi_poll_cq(ibcq, num_entries, wc);
+
+ spin_lock_irqsave(&cq->cq_lock, flags);
+ old_cons = qed_chain_get_cons_idx_u32(&cq->pbl);
+ while (num_entries && is_valid_cqe(cq, cqe)) {
+ struct qedr_qp *qp;
+ int cnt = 0;
+
+ /* prevent speculative reads of any field of CQE */
+ rmb();
+
+ qp = cqe_get_qp(cqe);
+ if (!qp) {
+ WARN(1, "Error: CQE QP pointer is NULL. CQE=%p\n", cqe);
+ break;
+ }
+
+ wc->qp = &qp->ibqp;
+
+ switch (cqe_get_type(cqe)) {
+ case RDMA_CQE_TYPE_REQUESTER:
+ cnt = qedr_poll_cq_req(dev, qp, cq, num_entries, wc,
+ &cqe->req);
+ try_consume_req_cqe(cq, qp, &cqe->req, &update);
+ break;
+ case RDMA_CQE_TYPE_RESPONDER_RQ:
+ cnt = qedr_poll_cq_resp(dev, qp, cq, num_entries, wc,
+ &cqe->resp, &update);
+ break;
+ case RDMA_CQE_TYPE_INVALID:
+ default:
+ DP_ERR(dev, "Error: invalid CQE type = %d\n",
+ cqe_get_type(cqe));
+ }
+ num_entries -= cnt;
+ wc += cnt;
+ done += cnt;
+
+ cqe = get_cqe(cq);
+ }
+ new_cons = qed_chain_get_cons_idx_u32(&cq->pbl);
+
+ cq->cq_cons += new_cons - old_cons;
+
+ if (update)
+ /* doorbell notifies abount latest VALID entry,
+ * but chain already point to the next INVALID one
+ */
+ doorbell_cq(cq, cq->cq_cons - 1, cq->arm_flags);
+
+ spin_unlock_irqrestore(&cq->cq_lock, flags);
+ return done;
+}
+
+int qedr_process_mad(struct ib_device *ibdev, int process_mad_flags,
+ u8 port_num,
+ const struct ib_wc *in_wc,
+ const struct ib_grh *in_grh,
+ const struct ib_mad_hdr *mad_hdr,
+ size_t in_mad_size, struct ib_mad_hdr *out_mad,
+ size_t *out_mad_size, u16 *out_mad_pkey_index)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibdev);
+
+ DP_DEBUG(dev, QEDR_MSG_GSI,
+ "QEDR_PROCESS_MAD in_mad %x %x %x %x %x %x %x %x\n",
+ mad_hdr->attr_id, mad_hdr->base_version, mad_hdr->attr_mod,
+ mad_hdr->class_specific, mad_hdr->class_version,
+ mad_hdr->method, mad_hdr->mgmt_class, mad_hdr->status);
+ return IB_MAD_RESULT_SUCCESS;
+}
+
+int qedr_port_immutable(struct ib_device *ibdev, u8 port_num,
+ struct ib_port_immutable *immutable)
+{
+ struct ib_port_attr attr;
+ int err;
+
+ err = qedr_query_port(ibdev, port_num, &attr);
+ if (err)
+ return err;
+
+ immutable->pkey_tbl_len = attr.pkey_tbl_len;
+ immutable->gid_tbl_len = attr.gid_tbl_len;
+ immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE |
+ RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP;
+ immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+ return 0;
+}
diff --git a/drivers/infiniband/hw/qedr/verbs.h b/drivers/infiniband/hw/qedr/verbs.h
new file mode 100644
index 0000000..a9b5e67
--- /dev/null
+++ b/drivers/infiniband/hw/qedr/verbs.h
@@ -0,0 +1,101 @@
+/* QLogic qedr NIC Driver
+ * Copyright (c) 2015-2016 QLogic Corporation
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and /or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef __QEDR_VERBS_H__
+#define __QEDR_VERBS_H__
+
+int qedr_query_device(struct ib_device *ibdev,
+ struct ib_device_attr *attr, struct ib_udata *udata);
+int qedr_query_port(struct ib_device *, u8 port, struct ib_port_attr *props);
+int qedr_modify_port(struct ib_device *, u8 port, int mask,
+ struct ib_port_modify *props);
+
+int qedr_query_gid(struct ib_device *, u8 port, int index, union ib_gid *gid);
+
+int qedr_query_pkey(struct ib_device *, u8 port, u16 index, u16 *pkey);
+
+struct ib_ucontext *qedr_alloc_ucontext(struct ib_device *, struct ib_udata *);
+int qedr_dealloc_ucontext(struct ib_ucontext *);
+
+int qedr_mmap(struct ib_ucontext *, struct vm_area_struct *vma);
+int qedr_del_gid(struct ib_device *device, u8 port_num,
+ unsigned int index, void **context);
+int qedr_add_gid(struct ib_device *device, u8 port_num,
+ unsigned int index, const union ib_gid *gid,
+ const struct ib_gid_attr *attr, void **context);
+struct ib_pd *qedr_alloc_pd(struct ib_device *,
+ struct ib_ucontext *, struct ib_udata *);
+int qedr_dealloc_pd(struct ib_pd *pd);
+
+struct ib_cq *qedr_create_cq(struct ib_device *ibdev,
+ const struct ib_cq_init_attr *attr,
+ struct ib_ucontext *ib_ctx,
+ struct ib_udata *udata);
+int qedr_resize_cq(struct ib_cq *, int cqe, struct ib_udata *);
+int qedr_destroy_cq(struct ib_cq *);
+int qedr_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
+struct ib_qp *qedr_create_qp(struct ib_pd *, struct ib_qp_init_attr *attrs,
+ struct ib_udata *);
+int qedr_modify_qp(struct ib_qp *, struct ib_qp_attr *attr,
+ int attr_mask, struct ib_udata *udata);
+int qedr_query_qp(struct ib_qp *, struct ib_qp_attr *qp_attr,
+ int qp_attr_mask, struct ib_qp_init_attr *);
+int qedr_destroy_qp(struct ib_qp *ibqp);
+
+struct ib_ah *qedr_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr);
+int qedr_destroy_ah(struct ib_ah *ibah);
+
+int qedr_dereg_mr(struct ib_mr *);
+struct ib_mr *qedr_get_dma_mr(struct ib_pd *, int acc);
+
+struct ib_mr *qedr_reg_user_mr(struct ib_pd *, u64 start, u64 length,
+ u64 virt, int acc, struct ib_udata *);
+
+int qedr_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg,
+ int sg_nents, unsigned int *sg_offset);
+
+struct ib_mr *qedr_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type,
+ u32 max_num_sg);
+int qedr_poll_cq(struct ib_cq *, int num_entries, struct ib_wc *wc);
+int qedr_post_send(struct ib_qp *, struct ib_send_wr *,
+ struct ib_send_wr **bad_wr);
+int qedr_post_recv(struct ib_qp *, struct ib_recv_wr *,
+ struct ib_recv_wr **bad_wr);
+int qedr_process_mad(struct ib_device *ibdev, int process_mad_flags,
+ u8 port_num, const struct ib_wc *in_wc,
+ const struct ib_grh *in_grh,
+ const struct ib_mad_hdr *in_mad,
+ size_t in_mad_size, struct ib_mad_hdr *out_mad,
+ size_t *out_mad_size, u16 *out_mad_pkey_index);
+
+int qedr_port_immutable(struct ib_device *ibdev, u8 port_num,
+ struct ib_port_immutable *immutable);
+#endif
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index 2d2b94f..75f0862 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -67,7 +67,8 @@ static int __qib_get_user_pages(unsigned long start_page, size_t num_pages,
for (got = 0; got < num_pages; got += ret) {
ret = get_user_pages(start_page + got * PAGE_SIZE,
- num_pages - got, 1, 1,
+ num_pages - got,
+ FOLL_WRITE | FOLL_FORCE,
p + got, NULL);
if (ret < 0)
goto bail_release;
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index a0b6ebe..1ccee6e 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -111,6 +111,7 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
int i;
int flags;
dma_addr_t pa;
+ unsigned int gup_flags;
if (!can_do_mlock())
return -EPERM;
@@ -135,6 +136,8 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
flags = IOMMU_READ | IOMMU_CACHE;
flags |= (writable) ? IOMMU_WRITE : 0;
+ gup_flags = FOLL_WRITE;
+ gup_flags |= (writable) ? 0 : FOLL_FORCE;
cur_base = addr & PAGE_MASK;
ret = 0;
@@ -142,7 +145,7 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
ret = get_user_pages(cur_base,
min_t(unsigned long, npages,
PAGE_SIZE / sizeof(struct page *)),
- 1, !writable, page_list, NULL);
+ gup_flags, page_list, NULL);
if (ret < 0)
goto out;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 7b8d2d9..da12717 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -63,6 +63,8 @@ enum ipoib_flush_level {
enum {
IPOIB_ENCAP_LEN = 4,
+ IPOIB_PSEUDO_LEN = 20,
+ IPOIB_HARD_LEN = IPOIB_ENCAP_LEN + IPOIB_PSEUDO_LEN,
IPOIB_UD_HEAD_SIZE = IB_GRH_BYTES + IPOIB_ENCAP_LEN,
IPOIB_UD_RX_SG = 2, /* max buffer needed for 4K mtu */
@@ -134,15 +136,21 @@ struct ipoib_header {
u16 reserved;
};
-struct ipoib_cb {
- struct qdisc_skb_cb qdisc_cb;
- u8 hwaddr[INFINIBAND_ALEN];
+struct ipoib_pseudo_header {
+ u8 hwaddr[INFINIBAND_ALEN];
};
-static inline struct ipoib_cb *ipoib_skb_cb(const struct sk_buff *skb)
+static inline void skb_add_pseudo_hdr(struct sk_buff *skb)
{
- BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct ipoib_cb));
- return (struct ipoib_cb *)skb->cb;
+ char *data = skb_push(skb, IPOIB_PSEUDO_LEN);
+
+ /*
+ * only the ipoib header is present now, make room for a dummy
+ * pseudo header and set skb field accordingly
+ */
+ memset(data, 0, IPOIB_PSEUDO_LEN);
+ skb_reset_mac_header(skb);
+ skb_pull(skb, IPOIB_HARD_LEN);
}
/* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 4ad297d..339a1ee 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -63,6 +63,8 @@ MODULE_PARM_DESC(cm_data_debug_level,
#define IPOIB_CM_RX_DELAY (3 * 256 * HZ)
#define IPOIB_CM_RX_UPDATE_MASK (0x3)
+#define IPOIB_CM_RX_RESERVE (ALIGN(IPOIB_HARD_LEN, 16) - IPOIB_ENCAP_LEN)
+
static struct ib_qp_attr ipoib_cm_err_attr = {
.qp_state = IB_QPS_ERR
};
@@ -146,15 +148,15 @@ static struct sk_buff *ipoib_cm_alloc_rx_skb(struct net_device *dev,
struct sk_buff *skb;
int i;
- skb = dev_alloc_skb(IPOIB_CM_HEAD_SIZE + 12);
+ skb = dev_alloc_skb(ALIGN(IPOIB_CM_HEAD_SIZE + IPOIB_PSEUDO_LEN, 16));
if (unlikely(!skb))
return NULL;
/*
- * IPoIB adds a 4 byte header. So we need 12 more bytes to align the
+ * IPoIB adds a IPOIB_ENCAP_LEN byte header, this will align the
* IP header to a multiple of 16.
*/
- skb_reserve(skb, 12);
+ skb_reserve(skb, IPOIB_CM_RX_RESERVE);
mapping[0] = ib_dma_map_single(priv->ca, skb->data, IPOIB_CM_HEAD_SIZE,
DMA_FROM_DEVICE);
@@ -624,9 +626,9 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
if (wc->byte_len < IPOIB_CM_COPYBREAK) {
int dlen = wc->byte_len;
- small_skb = dev_alloc_skb(dlen + 12);
+ small_skb = dev_alloc_skb(dlen + IPOIB_CM_RX_RESERVE);
if (small_skb) {
- skb_reserve(small_skb, 12);
+ skb_reserve(small_skb, IPOIB_CM_RX_RESERVE);
ib_dma_sync_single_for_cpu(priv->ca, rx_ring[wr_id].mapping[0],
dlen, DMA_FROM_DEVICE);
skb_copy_from_linear_data(skb, small_skb->data, dlen);
@@ -663,8 +665,7 @@ void ipoib_cm_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
copied:
skb->protocol = ((struct ipoib_header *) skb->data)->proto;
- skb_reset_mac_header(skb);
- skb_pull(skb, IPOIB_ENCAP_LEN);
+ skb_add_pseudo_hdr(skb);
++dev->stats.rx_packets;
dev->stats.rx_bytes += skb->len;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index be11d5d..830fecb 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -128,16 +128,15 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id)
buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu);
- skb = dev_alloc_skb(buf_size + IPOIB_ENCAP_LEN);
+ skb = dev_alloc_skb(buf_size + IPOIB_HARD_LEN);
if (unlikely(!skb))
return NULL;
/*
- * IB will leave a 40 byte gap for a GRH and IPoIB adds a 4 byte
- * header. So we need 4 more bytes to get to 48 and align the
- * IP header to a multiple of 16.
+ * the IP header will be at IPOIP_HARD_LEN + IB_GRH_BYTES, that is
+ * 64 bytes aligned
*/
- skb_reserve(skb, 4);
+ skb_reserve(skb, sizeof(struct ipoib_pseudo_header));
mapping = priv->rx_ring[id].mapping;
mapping[0] = ib_dma_map_single(priv->ca, skb->data, buf_size,
@@ -253,8 +252,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
skb_pull(skb, IB_GRH_BYTES);
skb->protocol = ((struct ipoib_header *) skb->data)->proto;
- skb_reset_mac_header(skb);
- skb_pull(skb, IPOIB_ENCAP_LEN);
+ skb_add_pseudo_hdr(skb);
++dev->stats.rx_packets;
dev->stats.rx_bytes += skb->len;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index ae5d7cd..c50794f 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -938,9 +938,12 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
ipoib_neigh_free(neigh);
goto err_drop;
}
- if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)
+ if (skb_queue_len(&neigh->queue) <
+ IPOIB_MAX_PATH_REC_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, IPOIB_PSEUDO_LEN);
__skb_queue_tail(&neigh->queue, skb);
- else {
+ } else {
ipoib_warn(priv, "queue length limit %d. Packet drop.\n",
skb_queue_len(&neigh->queue));
goto err_drop;
@@ -977,7 +980,7 @@ static void neigh_add_path(struct sk_buff *skb, u8 *daddr,
}
static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
- struct ipoib_cb *cb)
+ struct ipoib_pseudo_header *phdr)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_path *path;
@@ -985,16 +988,18 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
spin_lock_irqsave(&priv->lock, flags);
- path = __path_find(dev, cb->hwaddr + 4);
+ path = __path_find(dev, phdr->hwaddr + 4);
if (!path || !path->valid) {
int new_path = 0;
if (!path) {
- path = path_rec_create(dev, cb->hwaddr + 4);
+ path = path_rec_create(dev, phdr->hwaddr + 4);
new_path = 1;
}
if (path) {
if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, IPOIB_PSEUDO_LEN);
__skb_queue_tail(&path->queue, skb);
} else {
++dev->stats.tx_dropped;
@@ -1022,10 +1027,12 @@ static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev,
be16_to_cpu(path->pathrec.dlid));
spin_unlock_irqrestore(&priv->lock, flags);
- ipoib_send(dev, skb, path->ah, IPOIB_QPN(cb->hwaddr));
+ ipoib_send(dev, skb, path->ah, IPOIB_QPN(phdr->hwaddr));
return;
} else if ((path->query || !path_rec_start(dev, path)) &&
skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, IPOIB_PSEUDO_LEN);
__skb_queue_tail(&path->queue, skb);
} else {
++dev->stats.tx_dropped;
@@ -1039,13 +1046,15 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_neigh *neigh;
- struct ipoib_cb *cb = ipoib_skb_cb(skb);
+ struct ipoib_pseudo_header *phdr;
struct ipoib_header *header;
unsigned long flags;
+ phdr = (struct ipoib_pseudo_header *) skb->data;
+ skb_pull(skb, sizeof(*phdr));
header = (struct ipoib_header *) skb->data;
- if (unlikely(cb->hwaddr[4] == 0xff)) {
+ if (unlikely(phdr->hwaddr[4] == 0xff)) {
/* multicast, arrange "if" according to probability */
if ((header->proto != htons(ETH_P_IP)) &&
(header->proto != htons(ETH_P_IPV6)) &&
@@ -1058,13 +1067,13 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
/* Add in the P_Key for multicast*/
- cb->hwaddr[8] = (priv->pkey >> 8) & 0xff;
- cb->hwaddr[9] = priv->pkey & 0xff;
+ phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff;
+ phdr->hwaddr[9] = priv->pkey & 0xff;
- neigh = ipoib_neigh_get(dev, cb->hwaddr);
+ neigh = ipoib_neigh_get(dev, phdr->hwaddr);
if (likely(neigh))
goto send_using_neigh;
- ipoib_mcast_send(dev, cb->hwaddr, skb);
+ ipoib_mcast_send(dev, phdr->hwaddr, skb);
return NETDEV_TX_OK;
}
@@ -1073,16 +1082,16 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
case htons(ETH_P_IP):
case htons(ETH_P_IPV6):
case htons(ETH_P_TIPC):
- neigh = ipoib_neigh_get(dev, cb->hwaddr);
+ neigh = ipoib_neigh_get(dev, phdr->hwaddr);
if (unlikely(!neigh)) {
- neigh_add_path(skb, cb->hwaddr, dev);
+ neigh_add_path(skb, phdr->hwaddr, dev);
return NETDEV_TX_OK;
}
break;
case htons(ETH_P_ARP):
case htons(ETH_P_RARP):
/* for unicast ARP and RARP should always perform path find */
- unicast_arp_send(skb, dev, cb);
+ unicast_arp_send(skb, dev, phdr);
return NETDEV_TX_OK;
default:
/* ethertype not supported by IPoIB */
@@ -1099,11 +1108,13 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
goto unref;
}
} else if (neigh->ah) {
- ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(cb->hwaddr));
+ ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(phdr->hwaddr));
goto unref;
}
if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, sizeof(*phdr));
spin_lock_irqsave(&priv->lock, flags);
__skb_queue_tail(&neigh->queue, skb);
spin_unlock_irqrestore(&priv->lock, flags);
@@ -1135,8 +1146,8 @@ static int ipoib_hard_header(struct sk_buff *skb,
unsigned short type,
const void *daddr, const void *saddr, unsigned len)
{
+ struct ipoib_pseudo_header *phdr;
struct ipoib_header *header;
- struct ipoib_cb *cb = ipoib_skb_cb(skb);
header = (struct ipoib_header *) skb_push(skb, sizeof *header);
@@ -1145,12 +1156,13 @@ static int ipoib_hard_header(struct sk_buff *skb,
/*
* we don't rely on dst_entry structure, always stuff the
- * destination address into skb->cb so we can figure out where
+ * destination address into skb hard header so we can figure out where
* to send the packet later.
*/
- memcpy(cb->hwaddr, daddr, INFINIBAND_ALEN);
+ phdr = (struct ipoib_pseudo_header *) skb_push(skb, sizeof(*phdr));
+ memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN);
- return sizeof *header;
+ return IPOIB_HARD_LEN;
}
static void ipoib_set_mcast_list(struct net_device *dev)
@@ -1772,7 +1784,7 @@ void ipoib_setup(struct net_device *dev)
dev->flags |= IFF_BROADCAST | IFF_MULTICAST;
- dev->hard_header_len = IPOIB_ENCAP_LEN;
+ dev->hard_header_len = IPOIB_HARD_LEN;
dev->addr_len = INFINIBAND_ALEN;
dev->type = ARPHRD_INFINIBAND;
dev->tx_queue_len = ipoib_sendq_size * 2;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index d3394b6..1909dd2 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -796,9 +796,11 @@ void ipoib_mcast_send(struct net_device *dev, u8 *daddr, struct sk_buff *skb)
__ipoib_mcast_add(dev, mcast);
list_add_tail(&mcast->list, &priv->multicast_list);
}
- if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE)
+ if (skb_queue_len(&mcast->pkt_queue) < IPOIB_MAX_MCAST_QUEUE) {
+ /* put pseudoheader back on for next time */
+ skb_push(skb, sizeof(struct ipoib_pseudo_header));
skb_queue_tail(&mcast->pkt_queue, skb);
- else {
+ } else {
++dev->stats.tx_dropped;
dev_kfree_skb_any(skb);
}
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 936f07a..6d7de9b 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -103,6 +103,7 @@ static const struct alps_nibble_commands alps_v6_nibble_commands[] = {
6-byte ALPS packet */
#define ALPS_STICK_BITS 0x100 /* separate stick button bits */
#define ALPS_BUTTONPAD 0x200 /* device is a clickpad */
+#define ALPS_DUALPOINT_WITH_PRESSURE 0x400 /* device can report trackpoint pressure */
static const struct alps_model_info alps_model_data[] = {
{ { 0x32, 0x02, 0x14 }, 0x00, { ALPS_PROTO_V2, 0xf8, 0xf8, ALPS_PASS | ALPS_DUALPOINT } }, /* Toshiba Salellite Pro M10 */
@@ -1156,15 +1157,28 @@ static unsigned char alps_get_pkt_id_ss4_v2(unsigned char *byte)
{
unsigned char pkt_id = SS4_PACKET_ID_IDLE;
- if (byte[0] == 0x18 && byte[1] == 0x10 && byte[2] == 0x00 &&
- (byte[3] & 0x88) == 0x08 && byte[4] == 0x10 && byte[5] == 0x00) {
- pkt_id = SS4_PACKET_ID_IDLE;
- } else if (!(byte[3] & 0x10)) {
- pkt_id = SS4_PACKET_ID_ONE;
- } else if (!(byte[3] & 0x20)) {
+ switch (byte[3] & 0x30) {
+ case 0x00:
+ if (byte[0] == 0x18 && byte[1] == 0x10 && byte[2] == 0x00 &&
+ (byte[3] & 0x88) == 0x08 && byte[4] == 0x10 &&
+ byte[5] == 0x00) {
+ pkt_id = SS4_PACKET_ID_IDLE;
+ } else {
+ pkt_id = SS4_PACKET_ID_ONE;
+ }
+ break;
+ case 0x10:
+ /* two-finger finger positions */
pkt_id = SS4_PACKET_ID_TWO;
- } else {
+ break;
+ case 0x20:
+ /* stick pointer */
+ pkt_id = SS4_PACKET_ID_STICK;
+ break;
+ case 0x30:
+ /* third and fourth finger positions */
pkt_id = SS4_PACKET_ID_MULTI;
+ break;
}
return pkt_id;
@@ -1185,7 +1199,13 @@ static int alps_decode_ss4_v2(struct alps_fields *f,
f->mt[0].x = SS4_1F_X_V2(p);
f->mt[0].y = SS4_1F_Y_V2(p);
f->pressure = ((SS4_1F_Z_V2(p)) * 2) & 0x7f;
- f->fingers = 1;
+ /*
+ * When a button is held the device will give us events
+ * with x, y, and pressure of 0. This causes annoying jumps
+ * if a touch is released while the button is held.
+ * Handle this by claiming zero contacts.
+ */
+ f->fingers = f->pressure > 0 ? 1 : 0;
f->first_mp = 0;
f->is_mp = 0;
break;
@@ -1246,16 +1266,40 @@ static int alps_decode_ss4_v2(struct alps_fields *f,
}
break;
+ case SS4_PACKET_ID_STICK:
+ if (!(priv->flags & ALPS_DUALPOINT)) {
+ psmouse_warn(psmouse,
+ "Rejected trackstick packet from non DualPoint device");
+ } else {
+ int x = (s8)(((p[0] & 1) << 7) | (p[1] & 0x7f));
+ int y = (s8)(((p[3] & 1) << 7) | (p[2] & 0x7f));
+ int pressure = (s8)(p[4] & 0x7f);
+
+ input_report_rel(priv->dev2, REL_X, x);
+ input_report_rel(priv->dev2, REL_Y, -y);
+ input_report_abs(priv->dev2, ABS_PRESSURE, pressure);
+ }
+ break;
+
case SS4_PACKET_ID_IDLE:
default:
memset(f, 0, sizeof(struct alps_fields));
break;
}
- f->left = !!(SS4_BTN_V2(p) & 0x01);
- if (!(priv->flags & ALPS_BUTTONPAD)) {
- f->right = !!(SS4_BTN_V2(p) & 0x02);
- f->middle = !!(SS4_BTN_V2(p) & 0x04);
+ /* handle buttons */
+ if (pkt_id == SS4_PACKET_ID_STICK) {
+ f->ts_left = !!(SS4_BTN_V2(p) & 0x01);
+ if (!(priv->flags & ALPS_BUTTONPAD)) {
+ f->ts_right = !!(SS4_BTN_V2(p) & 0x02);
+ f->ts_middle = !!(SS4_BTN_V2(p) & 0x04);
+ }
+ } else {
+ f->left = !!(SS4_BTN_V2(p) & 0x01);
+ if (!(priv->flags & ALPS_BUTTONPAD)) {
+ f->right = !!(SS4_BTN_V2(p) & 0x02);
+ f->middle = !!(SS4_BTN_V2(p) & 0x04);
+ }
}
return 0;
@@ -1266,6 +1310,7 @@ static void alps_process_packet_ss4_v2(struct psmouse *psmouse)
struct alps_data *priv = psmouse->private;
unsigned char *packet = psmouse->packet;
struct input_dev *dev = psmouse->dev;
+ struct input_dev *dev2 = priv->dev2;
struct alps_fields *f = &priv->f;
memset(f, 0, sizeof(struct alps_fields));
@@ -1311,6 +1356,13 @@ static void alps_process_packet_ss4_v2(struct psmouse *psmouse)
input_report_abs(dev, ABS_PRESSURE, f->pressure);
input_sync(dev);
+
+ if (priv->flags & ALPS_DUALPOINT) {
+ input_report_key(dev2, BTN_LEFT, f->ts_left);
+ input_report_key(dev2, BTN_RIGHT, f->ts_right);
+ input_report_key(dev2, BTN_MIDDLE, f->ts_middle);
+ input_sync(dev2);
+ }
}
static bool alps_is_valid_package_ss4_v2(struct psmouse *psmouse)
@@ -2695,6 +2747,10 @@ static int alps_set_protocol(struct psmouse *psmouse,
if (alps_set_defaults_ss4_v2(psmouse, priv))
return -EIO;
+ if (priv->fw_ver[1] == 0x1)
+ priv->flags |= ALPS_DUALPOINT |
+ ALPS_DUALPOINT_WITH_PRESSURE;
+
break;
}
@@ -2767,6 +2823,9 @@ static int alps_identify(struct psmouse *psmouse, struct alps_data *priv)
} else if (e7[0] == 0x73 && e7[1] == 0x03 &&
e7[2] == 0x14 && ec[1] == 0x02) {
protocol = &alps_v8_protocol_data;
+ } else if (e7[0] == 0x73 && e7[1] == 0x03 &&
+ e7[2] == 0x28 && ec[1] == 0x01) {
+ protocol = &alps_v8_protocol_data;
} else {
psmouse_dbg(psmouse,
"Likely not an ALPS touchpad: E7=%3ph, EC=%3ph\n", e7, ec);
@@ -2949,6 +3008,10 @@ int alps_init(struct psmouse *psmouse)
input_set_capability(dev2, EV_REL, REL_X);
input_set_capability(dev2, EV_REL, REL_Y);
+ if (priv->flags & ALPS_DUALPOINT_WITH_PRESSURE) {
+ input_set_capability(dev2, EV_ABS, ABS_PRESSURE);
+ input_set_abs_params(dev2, ABS_PRESSURE, 0, 127, 0, 0);
+ }
input_set_capability(dev2, EV_KEY, BTN_LEFT);
input_set_capability(dev2, EV_KEY, BTN_RIGHT);
input_set_capability(dev2, EV_KEY, BTN_MIDDLE);
diff --git a/drivers/input/mouse/alps.h b/drivers/input/mouse/alps.h
index d37f814..b9417e2 100644
--- a/drivers/input/mouse/alps.h
+++ b/drivers/input/mouse/alps.h
@@ -37,12 +37,14 @@
* or there's button activities.
* SS4_PACKET_ID_TWO: There's two or more fingers on touchpad
* SS4_PACKET_ID_MULTI: There's three or more fingers on touchpad
+ * SS4_PACKET_ID_STICK: A stick pointer packet
*/
enum SS4_PACKET_ID {
SS4_PACKET_ID_IDLE = 0,
SS4_PACKET_ID_ONE,
SS4_PACKET_ID_TWO,
SS4_PACKET_ID_MULTI,
+ SS4_PACKET_ID_STICK,
};
#define SS4_COUNT_PER_ELECTRODE 256
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 08e252a..db7d1d6 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1134,7 +1134,7 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse,
* System76 Pangolin 0x250f01 ? 2 hw buttons
* (*) + 3 trackpoint buttons
* (**) + 0 trackpoint buttons
- * Note: Lenovo L430 and Lenovo L430 have the same fw_version/caps
+ * Note: Lenovo L430 and Lenovo L530 have the same fw_version/caps
*/
static void elantech_set_buttonpad_prop(struct psmouse *psmouse)
{
@@ -1159,6 +1159,13 @@ static const struct dmi_system_id elantech_dmi_has_middle_button[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "CELSIUS H730"),
},
},
+ {
+ /* Fujitsu H760 also has a middle button */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "CELSIUS H760"),
+ },
+ },
#endif
{ }
};
@@ -1503,10 +1510,10 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = {
},
},
{
- /* Fujitsu LIFEBOOK E554 does not work with crc_enabled == 0 */
+ /* Fujitsu H760 does not work with crc_enabled == 0 */
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
- DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E554"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "CELSIUS H760"),
},
},
{
@@ -1517,6 +1524,20 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = {
},
},
{
+ /* Fujitsu LIFEBOOK E554 does not work with crc_enabled == 0 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E554"),
+ },
+ },
+ {
+ /* Fujitsu LIFEBOOK E556 does not work with crc_enabled == 0 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E556"),
+ },
+ },
+ {
/* Fujitsu LIFEBOOK U745 does not work with crc_enabled == 0 */
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
diff --git a/drivers/input/mouse/focaltech.c b/drivers/input/mouse/focaltech.c
index 54eceb3..a7d3968 100644
--- a/drivers/input/mouse/focaltech.c
+++ b/drivers/input/mouse/focaltech.c
@@ -43,7 +43,7 @@ int focaltech_detect(struct psmouse *psmouse, bool set_properties)
if (set_properties) {
psmouse->vendor = "FocalTech";
- psmouse->name = "FocalTech Touchpad";
+ psmouse->name = "Touchpad";
}
return 0;
@@ -146,8 +146,8 @@ static void focaltech_report_state(struct psmouse *psmouse)
}
input_mt_report_pointer_emulation(dev, true);
- input_report_key(psmouse->dev, BTN_LEFT, state->pressed);
- input_sync(psmouse->dev);
+ input_report_key(dev, BTN_LEFT, state->pressed);
+ input_sync(dev);
}
static void focaltech_process_touch_packet(struct psmouse *psmouse,
diff --git a/drivers/input/rmi4/rmi_i2c.c b/drivers/input/rmi4/rmi_i2c.c
index 6f2e0e4..1ebc2c1 100644
--- a/drivers/input/rmi4/rmi_i2c.c
+++ b/drivers/input/rmi4/rmi_i2c.c
@@ -221,6 +221,21 @@ static const struct of_device_id rmi_i2c_of_match[] = {
MODULE_DEVICE_TABLE(of, rmi_i2c_of_match);
#endif
+static void rmi_i2c_regulator_bulk_disable(void *data)
+{
+ struct rmi_i2c_xport *rmi_i2c = data;
+
+ regulator_bulk_disable(ARRAY_SIZE(rmi_i2c->supplies),
+ rmi_i2c->supplies);
+}
+
+static void rmi_i2c_unregister_transport(void *data)
+{
+ struct rmi_i2c_xport *rmi_i2c = data;
+
+ rmi_unregister_transport_device(&rmi_i2c->xport);
+}
+
static int rmi_i2c_probe(struct i2c_client *client,
const struct i2c_device_id *id)
{
@@ -264,6 +279,12 @@ static int rmi_i2c_probe(struct i2c_client *client,
if (retval < 0)
return retval;
+ retval = devm_add_action_or_reset(&client->dev,
+ rmi_i2c_regulator_bulk_disable,
+ rmi_i2c);
+ if (retval)
+ return retval;
+
of_property_read_u32(client->dev.of_node, "syna,startup-delay-ms",
&rmi_i2c->startup_delay);
@@ -294,6 +315,11 @@ static int rmi_i2c_probe(struct i2c_client *client,
client->addr);
return retval;
}
+ retval = devm_add_action_or_reset(&client->dev,
+ rmi_i2c_unregister_transport,
+ rmi_i2c);
+ if (retval)
+ return retval;
retval = rmi_i2c_init_irq(client);
if (retval < 0)
@@ -304,17 +330,6 @@ static int rmi_i2c_probe(struct i2c_client *client,
return 0;
}
-static int rmi_i2c_remove(struct i2c_client *client)
-{
- struct rmi_i2c_xport *rmi_i2c = i2c_get_clientdata(client);
-
- rmi_unregister_transport_device(&rmi_i2c->xport);
- regulator_bulk_disable(ARRAY_SIZE(rmi_i2c->supplies),
- rmi_i2c->supplies);
-
- return 0;
-}
-
#ifdef CONFIG_PM_SLEEP
static int rmi_i2c_suspend(struct device *dev)
{
@@ -431,7 +446,6 @@ static struct i2c_driver rmi_i2c_driver = {
},
.id_table = rmi_id,
.probe = rmi_i2c_probe,
- .remove = rmi_i2c_remove,
};
module_i2c_driver(rmi_i2c_driver);
diff --git a/drivers/input/rmi4/rmi_spi.c b/drivers/input/rmi4/rmi_spi.c
index 55bd1b3..4ebef60 100644
--- a/drivers/input/rmi4/rmi_spi.c
+++ b/drivers/input/rmi4/rmi_spi.c
@@ -396,6 +396,13 @@ static inline int rmi_spi_of_probe(struct spi_device *spi,
}
#endif
+static void rmi_spi_unregister_transport(void *data)
+{
+ struct rmi_spi_xport *rmi_spi = data;
+
+ rmi_unregister_transport_device(&rmi_spi->xport);
+}
+
static int rmi_spi_probe(struct spi_device *spi)
{
struct rmi_spi_xport *rmi_spi;
@@ -464,6 +471,11 @@ static int rmi_spi_probe(struct spi_device *spi)
dev_err(&spi->dev, "failed to register transport.\n");
return retval;
}
+ retval = devm_add_action_or_reset(&spi->dev,
+ rmi_spi_unregister_transport,
+ rmi_spi);
+ if (retval)
+ return retval;
retval = rmi_spi_init_irq(spi);
if (retval < 0)
@@ -473,15 +485,6 @@ static int rmi_spi_probe(struct spi_device *spi)
return 0;
}
-static int rmi_spi_remove(struct spi_device *spi)
-{
- struct rmi_spi_xport *rmi_spi = spi_get_drvdata(spi);
-
- rmi_unregister_transport_device(&rmi_spi->xport);
-
- return 0;
-}
-
#ifdef CONFIG_PM_SLEEP
static int rmi_spi_suspend(struct device *dev)
{
@@ -577,7 +580,6 @@ static struct spi_driver rmi_spi_driver = {
},
.id_table = rmi_id,
.probe = rmi_spi_probe,
- .remove = rmi_spi_remove,
};
module_spi_driver(rmi_spi_driver);
diff --git a/drivers/input/serio/i8042-io.h b/drivers/input/serio/i8042-io.h
index a5eed2a..34da81c 100644
--- a/drivers/input/serio/i8042-io.h
+++ b/drivers/input/serio/i8042-io.h
@@ -81,7 +81,7 @@ static inline int i8042_platform_init(void)
return -EBUSY;
#endif
- i8042_reset = 1;
+ i8042_reset = I8042_RESET_ALWAYS;
return 0;
}
diff --git a/drivers/input/serio/i8042-ip22io.h b/drivers/input/serio/i8042-ip22io.h
index ee1ad27..08a1c10 100644
--- a/drivers/input/serio/i8042-ip22io.h
+++ b/drivers/input/serio/i8042-ip22io.h
@@ -61,7 +61,7 @@ static inline int i8042_platform_init(void)
return -EBUSY;
#endif
- i8042_reset = 1;
+ i8042_reset = I8042_RESET_ALWAYS;
return 0;
}
diff --git a/drivers/input/serio/i8042-ppcio.h b/drivers/input/serio/i8042-ppcio.h
index f708c75..1aabea4 100644
--- a/drivers/input/serio/i8042-ppcio.h
+++ b/drivers/input/serio/i8042-ppcio.h
@@ -44,7 +44,7 @@ static inline void i8042_write_command(int val)
static inline int i8042_platform_init(void)
{
- i8042_reset = 1;
+ i8042_reset = I8042_RESET_ALWAYS;
return 0;
}
diff --git a/drivers/input/serio/i8042-sparcio.h b/drivers/input/serio/i8042-sparcio.h
index afcd1c1..6231d63 100644
--- a/drivers/input/serio/i8042-sparcio.h
+++ b/drivers/input/serio/i8042-sparcio.h
@@ -130,7 +130,7 @@ static int __init i8042_platform_init(void)
}
}
- i8042_reset = 1;
+ i8042_reset = I8042_RESET_ALWAYS;
return 0;
}
diff --git a/drivers/input/serio/i8042-unicore32io.h b/drivers/input/serio/i8042-unicore32io.h
index 73f5cc1..4557475 100644
--- a/drivers/input/serio/i8042-unicore32io.h
+++ b/drivers/input/serio/i8042-unicore32io.h
@@ -61,7 +61,7 @@ static inline int i8042_platform_init(void)
if (!request_mem_region(I8042_REGION_START, I8042_REGION_SIZE, "i8042"))
return -EBUSY;
- i8042_reset = 1;
+ i8042_reset = I8042_RESET_ALWAYS;
return 0;
}
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 68f5f4a..073246c 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -510,6 +510,90 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
{ }
};
+/*
+ * On some Asus laptops, just running self tests cause problems.
+ */
+static const struct dmi_system_id i8042_dmi_noselftest_table[] = {
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "A455LD"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "K401LB"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "K501LB"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "K501LX"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "R409L"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "V502LX"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "X302LA"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "X450LCP"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "X450LD"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "X455LAB"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "X455LDB"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "X455LF"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Z450LA"),
+ },
+ },
+ { }
+};
static const struct dmi_system_id __initconst i8042_dmi_reset_table[] = {
{
/* MSI Wind U-100 */
@@ -793,6 +877,13 @@ static const struct dmi_system_id __initconst i8042_dmi_kbdreset_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "P34"),
},
},
+ {
+ /* Schenker XMG C504 - Elantech touchpad */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "XMG"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "C504"),
+ },
+ },
{ }
};
@@ -1072,12 +1163,18 @@ static int __init i8042_platform_init(void)
return retval;
#if defined(__ia64__)
- i8042_reset = true;
+ i8042_reset = I8042_RESET_ALWAYS;
#endif
#ifdef CONFIG_X86
- if (dmi_check_system(i8042_dmi_reset_table))
- i8042_reset = true;
+ /* Honor module parameter when value is not default */
+ if (i8042_reset == I8042_RESET_DEFAULT) {
+ if (dmi_check_system(i8042_dmi_reset_table))
+ i8042_reset = I8042_RESET_ALWAYS;
+
+ if (dmi_check_system(i8042_dmi_noselftest_table))
+ i8042_reset = I8042_RESET_NEVER;
+ }
if (dmi_check_system(i8042_dmi_noloop_table))
i8042_noloop = true;
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index 405252a..89abfdb 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -48,9 +48,39 @@ static bool i8042_unlock;
module_param_named(unlock, i8042_unlock, bool, 0);
MODULE_PARM_DESC(unlock, "Ignore keyboard lock.");
-static bool i8042_reset;
-module_param_named(reset, i8042_reset, bool, 0);
-MODULE_PARM_DESC(reset, "Reset controller during init and cleanup.");
+enum i8042_controller_reset_mode {
+ I8042_RESET_NEVER,
+ I8042_RESET_ALWAYS,
+ I8042_RESET_ON_S2RAM,
+#define I8042_RESET_DEFAULT I8042_RESET_ON_S2RAM
+};
+static enum i8042_controller_reset_mode i8042_reset = I8042_RESET_DEFAULT;
+static int i8042_set_reset(const char *val, const struct kernel_param *kp)
+{
+ enum i8042_controller_reset_mode *arg = kp->arg;
+ int error;
+ bool reset;
+
+ if (val) {
+ error = kstrtobool(val, &reset);
+ if (error)
+ return error;
+ } else {
+ reset = true;
+ }
+
+ *arg = reset ? I8042_RESET_ALWAYS : I8042_RESET_NEVER;
+ return 0;
+}
+
+static const struct kernel_param_ops param_ops_reset_param = {
+ .flags = KERNEL_PARAM_OPS_FL_NOARG,
+ .set = i8042_set_reset,
+};
+#define param_check_reset_param(name, p) \
+ __param_check(name, p, enum i8042_controller_reset_mode)
+module_param_named(reset, i8042_reset, reset_param, 0);
+MODULE_PARM_DESC(reset, "Reset controller on resume, cleanup or both");
static bool i8042_direct;
module_param_named(direct, i8042_direct, bool, 0);
@@ -1019,7 +1049,7 @@ static int i8042_controller_init(void)
* Reset the controller and reset CRT to the original value set by BIOS.
*/
-static void i8042_controller_reset(bool force_reset)
+static void i8042_controller_reset(bool s2r_wants_reset)
{
i8042_flush();
@@ -1044,8 +1074,10 @@ static void i8042_controller_reset(bool force_reset)
* Reset the controller if requested.
*/
- if (i8042_reset || force_reset)
+ if (i8042_reset == I8042_RESET_ALWAYS ||
+ (i8042_reset == I8042_RESET_ON_S2RAM && s2r_wants_reset)) {
i8042_controller_selftest();
+ }
/*
* Restore the original control register setting.
@@ -1110,7 +1142,7 @@ static void i8042_dritek_enable(void)
* before suspending.
*/
-static int i8042_controller_resume(bool force_reset)
+static int i8042_controller_resume(bool s2r_wants_reset)
{
int error;
@@ -1118,7 +1150,8 @@ static int i8042_controller_resume(bool force_reset)
if (error)
return error;
- if (i8042_reset || force_reset) {
+ if (i8042_reset == I8042_RESET_ALWAYS ||
+ (i8042_reset == I8042_RESET_ON_S2RAM && s2r_wants_reset)) {
error = i8042_controller_selftest();
if (error)
return error;
@@ -1195,7 +1228,7 @@ static int i8042_pm_resume_noirq(struct device *dev)
static int i8042_pm_resume(struct device *dev)
{
- bool force_reset;
+ bool want_reset;
int i;
for (i = 0; i < I8042_NUM_PORTS; i++) {
@@ -1218,9 +1251,9 @@ static int i8042_pm_resume(struct device *dev)
* off control to the platform firmware, otherwise we can simply restore
* the mode.
*/
- force_reset = pm_resume_via_firmware();
+ want_reset = pm_resume_via_firmware();
- return i8042_controller_resume(force_reset);
+ return i8042_controller_resume(want_reset);
}
static int i8042_pm_thaw(struct device *dev)
@@ -1482,7 +1515,7 @@ static int __init i8042_probe(struct platform_device *dev)
i8042_platform_device = dev;
- if (i8042_reset) {
+ if (i8042_reset == I8042_RESET_ALWAYS) {
error = i8042_controller_selftest();
if (error)
return error;
diff --git a/drivers/input/touchscreen/melfas_mip4.c b/drivers/input/touchscreen/melfas_mip4.c
index fb5fb91..552a377 100644
--- a/drivers/input/touchscreen/melfas_mip4.c
+++ b/drivers/input/touchscreen/melfas_mip4.c
@@ -157,6 +157,7 @@ struct mip4_ts {
char phys[32];
char product_name[16];
+ char ic_name[4];
unsigned int max_x;
unsigned int max_y;
@@ -263,6 +264,18 @@ static int mip4_query_device(struct mip4_ts *ts)
dev_dbg(&ts->client->dev, "product name: %.*s\n",
(int)sizeof(ts->product_name), ts->product_name);
+ /* IC name */
+ cmd[0] = MIP4_R0_INFO;
+ cmd[1] = MIP4_R1_INFO_IC_NAME;
+ error = mip4_i2c_xfer(ts, cmd, sizeof(cmd),
+ ts->ic_name, sizeof(ts->ic_name));
+ if (error)
+ dev_warn(&ts->client->dev,
+ "Failed to retrieve IC name: %d\n", error);
+ else
+ dev_dbg(&ts->client->dev, "IC name: %.*s\n",
+ (int)sizeof(ts->ic_name), ts->ic_name);
+
/* Firmware version */
error = mip4_get_fw_version(ts);
if (error)
@@ -1326,7 +1339,7 @@ static ssize_t mip4_sysfs_read_hw_version(struct device *dev,
* paired with current firmware in the chip.
*/
count = snprintf(buf, PAGE_SIZE, "%.*s\n",
- (int)sizeof(ts->product_name), ts->product_name);
+ (int)sizeof(ts->product_name), ts->product_name);
mutex_unlock(&ts->input->mutex);
@@ -1335,9 +1348,30 @@ static ssize_t mip4_sysfs_read_hw_version(struct device *dev,
static DEVICE_ATTR(hw_version, S_IRUGO, mip4_sysfs_read_hw_version, NULL);
+static ssize_t mip4_sysfs_read_ic_name(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct i2c_client *client = to_i2c_client(dev);
+ struct mip4_ts *ts = i2c_get_clientdata(client);
+ size_t count;
+
+ mutex_lock(&ts->input->mutex);
+
+ count = snprintf(buf, PAGE_SIZE, "%.*s\n",
+ (int)sizeof(ts->ic_name), ts->ic_name);
+
+ mutex_unlock(&ts->input->mutex);
+
+ return count;
+}
+
+static DEVICE_ATTR(ic_name, S_IRUGO, mip4_sysfs_read_ic_name, NULL);
+
static struct attribute *mip4_attrs[] = {
&dev_attr_fw_version.attr,
&dev_attr_hw_version.attr,
+ &dev_attr_ic_name.attr,
&dev_attr_update_fw.attr,
NULL,
};
@@ -1538,6 +1572,6 @@ static struct i2c_driver mip4_driver = {
module_i2c_driver(mip4_driver);
MODULE_DESCRIPTION("MELFAS MIP4 Touchscreen");
-MODULE_VERSION("2016.03.12");
+MODULE_VERSION("2016.09.28");
MODULE_AUTHOR("Sangwon Jee <jeesw@melfas.com>");
MODULE_LICENSE("GPL");
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 15c01c3..e6f9b2d 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -2636,17 +2636,26 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
/* And we're up. Go go go! */
of_iommu_set_ops(dev->of_node, &arm_smmu_ops);
#ifdef CONFIG_PCI
- pci_request_acs();
- ret = bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
- if (ret)
- return ret;
+ if (pci_bus_type.iommu_ops != &arm_smmu_ops) {
+ pci_request_acs();
+ ret = bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
+ if (ret)
+ return ret;
+ }
#endif
#ifdef CONFIG_ARM_AMBA
- ret = bus_set_iommu(&amba_bustype, &arm_smmu_ops);
- if (ret)
- return ret;
+ if (amba_bustype.iommu_ops != &arm_smmu_ops) {
+ ret = bus_set_iommu(&amba_bustype, &arm_smmu_ops);
+ if (ret)
+ return ret;
+ }
#endif
- return bus_set_iommu(&platform_bus_type, &arm_smmu_ops);
+ if (platform_bus_type.iommu_ops != &arm_smmu_ops) {
+ ret = bus_set_iommu(&platform_bus_type, &arm_smmu_ops);
+ if (ret)
+ return ret;
+ }
+ return 0;
}
static int arm_smmu_device_remove(struct platform_device *pdev)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index c841eb7..8f72814 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -324,8 +324,10 @@ struct arm_smmu_master_cfg {
#define INVALID_SMENDX -1
#define __fwspec_cfg(fw) ((struct arm_smmu_master_cfg *)fw->iommu_priv)
#define fwspec_smmu(fw) (__fwspec_cfg(fw)->smmu)
+#define fwspec_smendx(fw, i) \
+ (i >= fw->num_ids ? INVALID_SMENDX : __fwspec_cfg(fw)->smendx[i])
#define for_each_cfg_sme(fw, i, idx) \
- for (i = 0; idx = __fwspec_cfg(fw)->smendx[i], i < fw->num_ids; ++i)
+ for (i = 0; idx = fwspec_smendx(fw, i), i < fw->num_ids; ++i)
struct arm_smmu_device {
struct device *dev;
@@ -1228,6 +1230,16 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
return -ENXIO;
}
+ /*
+ * FIXME: The arch/arm DMA API code tries to attach devices to its own
+ * domains between of_xlate() and add_device() - we have no way to cope
+ * with that, so until ARM gets converted to rely on groups and default
+ * domains, just say no (but more politely than by dereferencing NULL).
+ * This should be at least a WARN_ON once that's sorted.
+ */
+ if (!fwspec->iommu_priv)
+ return -ENODEV;
+
smmu = fwspec_smmu(fwspec);
/* Ensure that the domain is finalised */
ret = arm_smmu_init_domain_context(domain, smmu);
@@ -1390,7 +1402,7 @@ static int arm_smmu_add_device(struct device *dev)
fwspec = dev->iommu_fwspec;
if (ret)
goto out_free;
- } else if (fwspec) {
+ } else if (fwspec && fwspec->ops == &arm_smmu_ops) {
smmu = arm_smmu_get_by_node(to_of_node(fwspec->iommu_fwnode));
} else {
return -ENODEV;
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index a4407ea..3965e73 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1711,6 +1711,7 @@ static void disable_dmar_iommu(struct intel_iommu *iommu)
if (!iommu->domains || !iommu->domain_ids)
return;
+again:
spin_lock_irqsave(&device_domain_lock, flags);
list_for_each_entry_safe(info, tmp, &device_domain_list, global) {
struct dmar_domain *domain;
@@ -1723,10 +1724,19 @@ static void disable_dmar_iommu(struct intel_iommu *iommu)
domain = info->domain;
- dmar_remove_one_dev_info(domain, info->dev);
+ __dmar_remove_one_dev_info(info);
- if (!domain_type_is_vm_or_si(domain))
+ if (!domain_type_is_vm_or_si(domain)) {
+ /*
+ * The domain_exit() function can't be called under
+ * device_domain_lock, as it takes this lock itself.
+ * So release the lock here and re-run the loop
+ * afterwards.
+ */
+ spin_unlock_irqrestore(&device_domain_lock, flags);
domain_exit(domain);
+ goto again;
+ }
}
spin_unlock_irqrestore(&device_domain_lock, flags);
diff --git a/drivers/ipack/ipack.c b/drivers/ipack/ipack.c
index c0e7b62..1210244 100644
--- a/drivers/ipack/ipack.c
+++ b/drivers/ipack/ipack.c
@@ -178,7 +178,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
idev->id_vendor, idev->id_device);
}
-ipack_device_attr(id_format, "0x%hhu\n");
+ipack_device_attr(id_format, "0x%hhx\n");
static DEVICE_ATTR_RO(id);
static DEVICE_ATTR_RO(id_device);
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 82b0b5d..bc0af33 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -158,8 +158,8 @@
select IRQ_DOMAIN
config JCORE_AIC
- bool "J-Core integrated AIC"
- depends on OF && (SUPERH || COMPILE_TEST)
+ bool "J-Core integrated AIC" if COMPILE_TEST
+ depends on OF
select IRQ_DOMAIN
help
Support for the J-Core integrated AIC.
diff --git a/drivers/irqchip/irq-eznps.c b/drivers/irqchip/irq-eznps.c
index efbf0e4..2a7a388 100644
--- a/drivers/irqchip/irq-eznps.c
+++ b/drivers/irqchip/irq-eznps.c
@@ -85,7 +85,7 @@ static void nps400_irq_eoi_global(struct irq_data *irqd)
nps_ack_gic();
}
-static void nps400_irq_eoi(struct irq_data *irqd)
+static void nps400_irq_ack(struct irq_data *irqd)
{
unsigned int __maybe_unused irq = irqd_to_hwirq(irqd);
@@ -103,7 +103,7 @@ static struct irq_chip nps400_irq_chip_percpu = {
.name = "NPS400 IC",
.irq_mask = nps400_irq_mask,
.irq_unmask = nps400_irq_unmask,
- .irq_eoi = nps400_irq_eoi,
+ .irq_ack = nps400_irq_ack,
};
static int nps400_irq_map(struct irq_domain *d, unsigned int virq,
@@ -135,7 +135,7 @@ static const struct irq_domain_ops nps400_irq_ops = {
static int __init nps400_of_init(struct device_node *node,
struct device_node *parent)
{
- static struct irq_domain *nps400_root_domain;
+ struct irq_domain *nps400_root_domain;
if (parent) {
pr_err("DeviceTree incore ic not a root irq controller\n");
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 003495d..c5dee30 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1023,7 +1023,7 @@ static void its_free_tables(struct its_node *its)
static int its_alloc_tables(struct its_node *its)
{
- u64 typer = readq_relaxed(its->base + GITS_TYPER);
+ u64 typer = gic_read_typer(its->base + GITS_TYPER);
u32 ids = GITS_TYPER_DEVBITS(typer);
u64 shr = GITS_BASER_InnerShareable;
u64 cache = GITS_BASER_WaWb;
@@ -1198,7 +1198,7 @@ static void its_cpu_init_collection(void)
* We now have to bind each collection to its target
* redistributor.
*/
- if (readq_relaxed(its->base + GITS_TYPER) & GITS_TYPER_PTA) {
+ if (gic_read_typer(its->base + GITS_TYPER) & GITS_TYPER_PTA) {
/*
* This ITS wants the physical address of the
* redistributor.
@@ -1208,7 +1208,7 @@ static void its_cpu_init_collection(void)
/*
* This ITS wants a linear CPU number.
*/
- target = readq_relaxed(gic_data_rdist_rd_base() + GICR_TYPER);
+ target = gic_read_typer(gic_data_rdist_rd_base() + GICR_TYPER);
target = GICR_TYPER_CPU_NUMBER(target) << 16;
}
@@ -1691,7 +1691,7 @@ static int __init its_probe_one(struct resource *res,
INIT_LIST_HEAD(&its->its_device_list);
its->base = its_base;
its->phys_base = res->start;
- its->ite_size = ((readl_relaxed(its_base + GITS_TYPER) >> 4) & 0xf) + 1;
+ its->ite_size = ((gic_read_typer(its_base + GITS_TYPER) >> 4) & 0xf) + 1;
its->numa_node = numa_node;
its->cmd_base = kzalloc(ITS_CMD_QUEUE_SZ, GFP_KERNEL);
@@ -1763,7 +1763,7 @@ static int __init its_probe_one(struct resource *res,
static bool gic_rdists_supports_plpis(void)
{
- return !!(readl_relaxed(gic_data_rdist_rd_base() + GICR_TYPER) & GICR_TYPER_PLPIS);
+ return !!(gic_read_typer(gic_data_rdist_rd_base() + GICR_TYPER) & GICR_TYPER_PLPIS);
}
int its_cpu_init(void)
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 9b81bd8..19d642e 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -153,7 +153,7 @@ static void gic_enable_redist(bool enable)
return; /* No PM support in this redistributor */
}
- while (count--) {
+ while (--count) {
val = readl_relaxed(rbase + GICR_WAKER);
if (enable ^ (bool)(val & GICR_WAKER_ChildrenAsleep))
break;
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 58e5b4e..d6c404b 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1279,7 +1279,7 @@ static bool gic_check_eoimode(struct device_node *node, void __iomem **base)
*/
*base += 0xf000;
cpuif_res.start += 0xf000;
- pr_warn("GIC: Adjusting CPU interface base to %pa",
+ pr_warn("GIC: Adjusting CPU interface base to %pa\n",
&cpuif_res.start);
}
diff --git a/drivers/irqchip/irq-i8259.c b/drivers/irqchip/irq-i8259.c
index 6b304eb..1aec12c 100644
--- a/drivers/irqchip/irq-i8259.c
+++ b/drivers/irqchip/irq-i8259.c
@@ -38,6 +38,7 @@ static void disable_8259A_irq(struct irq_data *d);
static void enable_8259A_irq(struct irq_data *d);
static void mask_and_ack_8259A(struct irq_data *d);
static void init_8259A(int auto_eoi);
+static int (*i8259_poll)(void) = i8259_irq;
static struct irq_chip i8259A_chip = {
.name = "XT-PIC",
@@ -51,6 +52,11 @@ static struct irq_chip i8259A_chip = {
* 8259A PIC functions to handle ISA devices:
*/
+void i8259_set_poll(int (*poll)(void))
+{
+ i8259_poll = poll;
+}
+
/*
* This contains the irq mask for both 8259A irq controllers,
*/
@@ -89,24 +95,6 @@ static void enable_8259A_irq(struct irq_data *d)
raw_spin_unlock_irqrestore(&i8259A_lock, flags);
}
-int i8259A_irq_pending(unsigned int irq)
-{
- unsigned int mask;
- unsigned long flags;
- int ret;
-
- irq -= I8259A_IRQ_BASE;
- mask = 1 << irq;
- raw_spin_lock_irqsave(&i8259A_lock, flags);
- if (irq < 8)
- ret = inb(PIC_MASTER_CMD) & mask;
- else
- ret = inb(PIC_SLAVE_CMD) & (mask >> 8);
- raw_spin_unlock_irqrestore(&i8259A_lock, flags);
-
- return ret;
-}
-
void make_8259A_irq(unsigned int irq)
{
disable_irq_nosync(irq);
@@ -355,7 +343,7 @@ void __init init_i8259_irqs(void)
static void i8259_irq_dispatch(struct irq_desc *desc)
{
struct irq_domain *domain = irq_desc_get_handler_data(desc);
- int hwirq = i8259_irq();
+ int hwirq = i8259_poll();
unsigned int irq;
if (hwirq < 0)
@@ -370,13 +358,15 @@ int __init i8259_of_init(struct device_node *node, struct device_node *parent)
struct irq_domain *domain;
unsigned int parent_irq;
+ domain = __init_i8259_irqs(node);
+
parent_irq = irq_of_parse_and_map(node, 0);
if (!parent_irq) {
pr_err("Failed to map i8259 parent IRQ\n");
+ irq_domain_remove(domain);
return -ENODEV;
}
- domain = __init_i8259_irqs(node);
irq_set_chained_handler_and_data(parent_irq, i8259_irq_dispatch,
domain);
return 0;
diff --git a/drivers/irqchip/irq-jcore-aic.c b/drivers/irqchip/irq-jcore-aic.c
index 84b01de..033bccb 100644
--- a/drivers/irqchip/irq-jcore-aic.c
+++ b/drivers/irqchip/irq-jcore-aic.c
@@ -25,12 +25,30 @@
static struct irq_chip jcore_aic;
+/*
+ * The J-Core AIC1 and AIC2 are cpu-local interrupt controllers and do
+ * not distinguish or use distinct irq number ranges for per-cpu event
+ * interrupts (timer, IPI). Since information to determine whether a
+ * particular irq number should be treated as per-cpu is not available
+ * at mapping time, we use a wrapper handler function which chooses
+ * the right handler at runtime based on whether IRQF_PERCPU was used
+ * when requesting the irq.
+ */
+
+static void handle_jcore_irq(struct irq_desc *desc)
+{
+ if (irqd_is_per_cpu(irq_desc_get_irq_data(desc)))
+ handle_percpu_irq(desc);
+ else
+ handle_simple_irq(desc);
+}
+
static int jcore_aic_irqdomain_map(struct irq_domain *d, unsigned int irq,
irq_hw_number_t hwirq)
{
struct irq_chip *aic = d->host_data;
- irq_set_chip_and_handler(irq, aic, handle_simple_irq);
+ irq_set_chip_and_handler(irq, aic, handle_jcore_irq);
return 0;
}
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 8abde6b..6d53810 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -266,7 +266,7 @@ static struct raid_type {
{"raid10_offset", "raid10 offset (striped mirrors)", 0, 2, 10, ALGORITHM_RAID10_OFFSET},
{"raid10_near", "raid10 near (striped mirrors)", 0, 2, 10, ALGORITHM_RAID10_NEAR},
{"raid10", "raid10 (striped mirrors)", 0, 2, 10, ALGORITHM_RAID10_DEFAULT},
- {"raid4", "raid4 (dedicated last parity disk)", 1, 2, 4, ALGORITHM_PARITY_N}, /* raid4 layout = raid5_n */
+ {"raid4", "raid4 (dedicated first parity disk)", 1, 2, 5, ALGORITHM_PARITY_0}, /* raid4 layout = raid5_0 */
{"raid5_n", "raid5 (dedicated last parity disk)", 1, 2, 5, ALGORITHM_PARITY_N},
{"raid5_ls", "raid5 (left symmetric)", 1, 2, 5, ALGORITHM_LEFT_SYMMETRIC},
{"raid5_rs", "raid5 (right symmetric)", 1, 2, 5, ALGORITHM_RIGHT_SYMMETRIC},
@@ -2087,11 +2087,11 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev)
/*
* No takeover/reshaping, because we don't have the extended v1.9.0 metadata
*/
- if (le32_to_cpu(sb->level) != mddev->level) {
+ if (le32_to_cpu(sb->level) != mddev->new_level) {
DMERR("Reshaping/takeover raid sets not yet supported. (raid level/stripes/size change)");
return -EINVAL;
}
- if (le32_to_cpu(sb->layout) != mddev->layout) {
+ if (le32_to_cpu(sb->layout) != mddev->new_layout) {
DMERR("Reshaping raid sets not yet supported. (raid layout change)");
DMERR(" 0x%X vs 0x%X", le32_to_cpu(sb->layout), mddev->layout);
DMERR(" Old layout: %s w/ %d copies",
@@ -2102,7 +2102,7 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev)
raid10_md_layout_to_copies(mddev->layout));
return -EINVAL;
}
- if (le32_to_cpu(sb->stripe_sectors) != mddev->chunk_sectors) {
+ if (le32_to_cpu(sb->stripe_sectors) != mddev->new_chunk_sectors) {
DMERR("Reshaping raid sets not yet supported. (stripe sectors change)");
return -EINVAL;
}
@@ -2115,6 +2115,8 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev)
return -EINVAL;
}
+ DMINFO("Discovered old metadata format; upgrading to extended metadata format");
+
/* Table line is checked vs. authoritative superblock */
rs_set_new(rs);
}
@@ -2258,7 +2260,8 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev)
if (!mddev->events && super_init_validation(rs, rdev))
return -EINVAL;
- if (le32_to_cpu(sb->compat_features) != FEATURE_FLAG_SUPPORTS_V190) {
+ if (le32_to_cpu(sb->compat_features) &&
+ le32_to_cpu(sb->compat_features) != FEATURE_FLAG_SUPPORTS_V190) {
rs->ti->error = "Unable to assemble array: Unknown flag(s) in compatible feature flags";
return -EINVAL;
}
@@ -3646,7 +3649,7 @@ static void raid_resume(struct dm_target *ti)
static struct target_type raid_target = {
.name = "raid",
- .version = {1, 9, 0},
+ .version = {1, 9, 1},
.module = THIS_MODULE,
.ctr = raid_ctr,
.dtr = raid_dtr,
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index bdf1606..9a8b710 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -145,7 +145,6 @@ static void dispatch_bios(void *context, struct bio_list *bio_list)
struct dm_raid1_bio_record {
struct mirror *m;
- /* if details->bi_bdev == NULL, details were not saved */
struct dm_bio_details details;
region_t write_region;
};
@@ -1200,8 +1199,6 @@ static int mirror_map(struct dm_target *ti, struct bio *bio)
struct dm_raid1_bio_record *bio_record =
dm_per_bio_data(bio, sizeof(struct dm_raid1_bio_record));
- bio_record->details.bi_bdev = NULL;
-
if (rw == WRITE) {
/* Save region for mirror_end_io() handler */
bio_record->write_region = dm_rh_bio_to_region(ms->rh, bio);
@@ -1260,22 +1257,12 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
}
if (error == -EOPNOTSUPP)
- goto out;
+ return error;
if ((error == -EWOULDBLOCK) && (bio->bi_opf & REQ_RAHEAD))
- goto out;
+ return error;
if (unlikely(error)) {
- if (!bio_record->details.bi_bdev) {
- /*
- * There wasn't enough memory to record necessary
- * information for a retry or there was no other
- * mirror in-sync.
- */
- DMERR_LIMIT("Mirror read failed.");
- return -EIO;
- }
-
m = bio_record->m;
DMERR("Mirror read failed from %s. Trying alternative device.",
@@ -1291,7 +1278,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
bd = &bio_record->details;
dm_bio_restore(bd, bio);
- bio_record->details.bi_bdev = NULL;
+ bio->bi_error = 0;
queue_bio(ms, bio, rw);
return DM_ENDIO_INCOMPLETE;
@@ -1299,9 +1286,6 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
DMERR("All replicated volumes dead, failing I/O");
}
-out:
- bio_record->details.bi_bdev = NULL;
-
return error;
}
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index dc75bea..1d0d2ad 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -856,8 +856,11 @@ int dm_old_init_request_queue(struct mapped_device *md)
kthread_init_worker(&md->kworker);
md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker,
"kdmwork-%s", dm_device_name(md));
- if (IS_ERR(md->kworker_task))
- return PTR_ERR(md->kworker_task);
+ if (IS_ERR(md->kworker_task)) {
+ int error = PTR_ERR(md->kworker_task);
+ md->kworker_task = NULL;
+ return error;
+ }
elv_register_queue(md->queue);
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 3e407a9..c4b53b3 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -695,37 +695,32 @@ int dm_table_add_target(struct dm_table *t, const char *type,
tgt->type = dm_get_target_type(type);
if (!tgt->type) {
- DMERR("%s: %s: unknown target type", dm_device_name(t->md),
- type);
+ DMERR("%s: %s: unknown target type", dm_device_name(t->md), type);
return -EINVAL;
}
if (dm_target_needs_singleton(tgt->type)) {
if (t->num_targets) {
- DMERR("%s: target type %s must appear alone in table",
- dm_device_name(t->md), type);
- return -EINVAL;
+ tgt->error = "singleton target type must appear alone in table";
+ goto bad;
}
t->singleton = true;
}
if (dm_target_always_writeable(tgt->type) && !(t->mode & FMODE_WRITE)) {
- DMERR("%s: target type %s may not be included in read-only tables",
- dm_device_name(t->md), type);
- return -EINVAL;
+ tgt->error = "target type may not be included in a read-only table";
+ goto bad;
}
if (t->immutable_target_type) {
if (t->immutable_target_type != tgt->type) {
- DMERR("%s: immutable target type %s cannot be mixed with other target types",
- dm_device_name(t->md), t->immutable_target_type->name);
- return -EINVAL;
+ tgt->error = "immutable target type cannot be mixed with other target types";
+ goto bad;
}
} else if (dm_target_is_immutable(tgt->type)) {
if (t->num_targets) {
- DMERR("%s: immutable target type %s cannot be mixed with other target types",
- dm_device_name(t->md), tgt->type->name);
- return -EINVAL;
+ tgt->error = "immutable target type cannot be mixed with other target types";
+ goto bad;
}
t->immutable_target_type = tgt->type;
}
@@ -740,7 +735,6 @@ int dm_table_add_target(struct dm_table *t, const char *type,
*/
if (!adjoin(t, tgt)) {
tgt->error = "Gap in table";
- r = -EINVAL;
goto bad;
}
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 147af95..ef7bf1d 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1423,8 +1423,6 @@ static void cleanup_mapped_device(struct mapped_device *md)
if (md->bs)
bioset_free(md->bs);
- cleanup_srcu_struct(&md->io_barrier);
-
if (md->disk) {
spin_lock(&_minor_lock);
md->disk->private_data = NULL;
@@ -1436,6 +1434,8 @@ static void cleanup_mapped_device(struct mapped_device *md)
if (md->queue)
blk_cleanup_queue(md->queue);
+ cleanup_srcu_struct(&md->io_barrier);
+
if (md->bdev) {
bdput(md->bdev);
md->bdev = NULL;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index eac84d8..2089d46 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -3887,10 +3887,10 @@ array_state_show(struct mddev *mddev, char *page)
st = read_auto;
break;
case 0:
- if (mddev->in_sync)
- st = clean;
- else if (test_bit(MD_CHANGE_PENDING, &mddev->flags))
+ if (test_bit(MD_CHANGE_PENDING, &mddev->flags))
st = write_pending;
+ else if (mddev->in_sync)
+ st = clean;
else if (mddev->safemode)
st = active_idle;
else
@@ -8144,14 +8144,14 @@ void md_do_sync(struct md_thread *thread)
if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
- mddev->curr_resync > 2) {
+ mddev->curr_resync > 3) {
mddev->curr_resync_completed = mddev->curr_resync;
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
}
mddev->pers->sync_request(mddev, max_sectors, &skipped);
if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
- mddev->curr_resync > 2) {
+ mddev->curr_resync > 3) {
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
if (mddev->curr_resync >= mddev->recovery_cp) {
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 1961d82..29e2df5 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -403,11 +403,14 @@ static void raid1_end_write_request(struct bio *bio)
struct bio *to_put = NULL;
int mirror = find_bio_disk(r1_bio, bio);
struct md_rdev *rdev = conf->mirrors[mirror].rdev;
+ bool discard_error;
+
+ discard_error = bio->bi_error && bio_op(bio) == REQ_OP_DISCARD;
/*
* 'one mirror IO has finished' event handler:
*/
- if (bio->bi_error) {
+ if (bio->bi_error && !discard_error) {
set_bit(WriteErrorSeen, &rdev->flags);
if (!test_and_set_bit(WantReplacement, &rdev->flags))
set_bit(MD_RECOVERY_NEEDED, &
@@ -444,7 +447,7 @@ static void raid1_end_write_request(struct bio *bio)
/* Maybe we can clear some bad blocks. */
if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
- &first_bad, &bad_sectors)) {
+ &first_bad, &bad_sectors) && !discard_error) {
r1_bio->bios[mirror] = IO_MADE_GOOD;
set_bit(R1BIO_MadeGood, &r1_bio->state);
}
@@ -2294,17 +2297,23 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
* This is all done synchronously while the array is
* frozen
*/
+
+ bio = r1_bio->bios[r1_bio->read_disk];
+ bdevname(bio->bi_bdev, b);
+ bio_put(bio);
+ r1_bio->bios[r1_bio->read_disk] = NULL;
+
if (mddev->ro == 0) {
freeze_array(conf, 1);
fix_read_error(conf, r1_bio->read_disk,
r1_bio->sector, r1_bio->sectors);
unfreeze_array(conf);
- } else
- md_error(mddev, conf->mirrors[r1_bio->read_disk].rdev);
+ } else {
+ r1_bio->bios[r1_bio->read_disk] = IO_BLOCKED;
+ }
+
rdev_dec_pending(conf->mirrors[r1_bio->read_disk].rdev, conf->mddev);
- bio = r1_bio->bios[r1_bio->read_disk];
- bdevname(bio->bi_bdev, b);
read_more:
disk = read_balance(conf, r1_bio, &max_sectors);
if (disk == -1) {
@@ -2315,11 +2324,6 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
} else {
const unsigned long do_sync
= r1_bio->master_bio->bi_opf & REQ_SYNC;
- if (bio) {
- r1_bio->bios[r1_bio->read_disk] =
- mddev->ro ? IO_BLOCKED : NULL;
- bio_put(bio);
- }
r1_bio->read_disk = disk;
bio = bio_clone_mddev(r1_bio->master_bio, GFP_NOIO, mddev);
bio_trim(bio, r1_bio->sector - bio->bi_iter.bi_sector,
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index be1a9fc..39fddda 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -447,6 +447,9 @@ static void raid10_end_write_request(struct bio *bio)
struct r10conf *conf = r10_bio->mddev->private;
int slot, repl;
struct md_rdev *rdev = NULL;
+ bool discard_error;
+
+ discard_error = bio->bi_error && bio_op(bio) == REQ_OP_DISCARD;
dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
@@ -460,7 +463,7 @@ static void raid10_end_write_request(struct bio *bio)
/*
* this branch is our 'one mirror IO has finished' event handler:
*/
- if (bio->bi_error) {
+ if (bio->bi_error && !discard_error) {
if (repl)
/* Never record new bad blocks to replacement,
* just fail it.
@@ -503,7 +506,7 @@ static void raid10_end_write_request(struct bio *bio)
if (is_badblock(rdev,
r10_bio->devs[slot].addr,
r10_bio->sectors,
- &first_bad, &bad_sectors)) {
+ &first_bad, &bad_sectors) && !discard_error) {
bio_put(bio);
if (repl)
r10_bio->devs[slot].repl_bio = IO_MADE_GOOD;
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 1b1ab4a..a227a9f 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -1087,7 +1087,7 @@ static int r5l_recovery_log(struct r5l_log *log)
* 1's seq + 10 and let superblock points to meta2. The same recovery will
* not think meta 3 is a valid meta, because its seq doesn't match
*/
- if (ctx.seq > log->last_cp_seq + 1) {
+ if (ctx.seq > log->last_cp_seq) {
int ret;
ret = r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq + 10);
@@ -1096,6 +1096,8 @@ static int r5l_recovery_log(struct r5l_log *log)
log->seq = ctx.seq + 11;
log->log_start = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS);
r5l_write_super(log, ctx.pos);
+ log->last_checkpoint = ctx.pos;
+ log->next_checkpoint = ctx.pos;
} else {
log->log_start = ctx.pos;
log->seq = ctx.seq;
@@ -1154,6 +1156,7 @@ static int r5l_load_log(struct r5l_log *log)
if (create_super) {
log->last_cp_seq = prandom_u32();
cp = 0;
+ r5l_log_write_empty_meta_block(log, cp, log->last_cp_seq);
/*
* Make sure super points to correct address. Log might have
* data very soon. If super hasn't correct log tail address,
@@ -1168,6 +1171,7 @@ static int r5l_load_log(struct r5l_log *log)
if (log->max_free_space > RECLAIM_MAX_FREE_SPACE)
log->max_free_space = RECLAIM_MAX_FREE_SPACE;
log->last_checkpoint = cp;
+ log->next_checkpoint = cp;
__free_page(page);
diff --git a/drivers/media/dvb-frontends/Kconfig b/drivers/media/dvb-frontends/Kconfig
index 0122255..b71b747 100644
--- a/drivers/media/dvb-frontends/Kconfig
+++ b/drivers/media/dvb-frontends/Kconfig
@@ -513,6 +513,11 @@
depends on DVB_CORE
default DVB_AS102
+config DVB_GP8PSK_FE
+ tristate
+ depends on DVB_CORE
+ default DVB_USB_GP8PSK
+
comment "DVB-C (cable) frontends"
depends on DVB_CORE
diff --git a/drivers/media/dvb-frontends/Makefile b/drivers/media/dvb-frontends/Makefile
index e90165a..93921a4 100644
--- a/drivers/media/dvb-frontends/Makefile
+++ b/drivers/media/dvb-frontends/Makefile
@@ -121,6 +121,7 @@
obj-$(CONFIG_DVB_M88RS2000) += m88rs2000.o
obj-$(CONFIG_DVB_AF9033) += af9033.o
obj-$(CONFIG_DVB_AS102_FE) += as102_fe.o
+obj-$(CONFIG_DVB_GP8PSK_FE) += gp8psk-fe.o
obj-$(CONFIG_DVB_TC90522) += tc90522.o
obj-$(CONFIG_DVB_HORUS3A) += horus3a.o
obj-$(CONFIG_DVB_ASCOT2E) += ascot2e.o
diff --git a/drivers/media/usb/dvb-usb/gp8psk-fe.c b/drivers/media/dvb-frontends/gp8psk-fe.c
similarity index 69%
rename from drivers/media/usb/dvb-usb/gp8psk-fe.c
rename to drivers/media/dvb-frontends/gp8psk-fe.c
index db6eb79..93f59bf 100644
--- a/drivers/media/usb/dvb-usb/gp8psk-fe.c
+++ b/drivers/media/dvb-frontends/gp8psk-fe.c
@@ -1,5 +1,5 @@
-/* DVB USB compliant Linux driver for the
- * - GENPIX 8pks/qpsk/DCII USB2.0 DVB-S module
+/*
+ * Frontend driver for the GENPIX 8pks/qpsk/DCII USB2.0 DVB-S module
*
* Copyright (C) 2006,2007 Alan Nisota (alannisota@gmail.com)
* Copyright (C) 2006,2007 Genpix Electronics (genpix@genpix-electronics.com)
@@ -8,17 +8,31 @@
*
* This module is based off the vp7045 and vp702x modules
*
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation, version 2.
- *
- * see Documentation/dvb/README.dvb-usb for more information
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation, version 2.
*/
-#include "gp8psk.h"
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include "gp8psk-fe.h"
+#include "dvb_frontend.h"
+
+static int debug;
+module_param(debug, int, 0644);
+MODULE_PARM_DESC(debug, "Turn on/off debugging (default:off).");
+
+#define dprintk(fmt, arg...) do { \
+ if (debug) \
+ printk(KERN_DEBUG pr_fmt("%s: " fmt), \
+ __func__, ##arg); \
+} while (0)
struct gp8psk_fe_state {
struct dvb_frontend fe;
- struct dvb_usb_device *d;
+ void *priv;
+ const struct gp8psk_fe_ops *ops;
+ bool is_rev1;
u8 lock;
u16 snr;
unsigned long next_status_check;
@@ -29,22 +43,24 @@ static int gp8psk_tuned_to_DCII(struct dvb_frontend *fe)
{
struct gp8psk_fe_state *st = fe->demodulator_priv;
u8 status;
- gp8psk_usb_in_op(st->d, GET_8PSK_CONFIG, 0, 0, &status, 1);
+
+ st->ops->in(st->priv, GET_8PSK_CONFIG, 0, 0, &status, 1);
return status & bmDCtuned;
}
static int gp8psk_set_tuner_mode(struct dvb_frontend *fe, int mode)
{
- struct gp8psk_fe_state *state = fe->demodulator_priv;
- return gp8psk_usb_out_op(state->d, SET_8PSK_CONFIG, mode, 0, NULL, 0);
+ struct gp8psk_fe_state *st = fe->demodulator_priv;
+
+ return st->ops->out(st->priv, SET_8PSK_CONFIG, mode, 0, NULL, 0);
}
static int gp8psk_fe_update_status(struct gp8psk_fe_state *st)
{
u8 buf[6];
if (time_after(jiffies,st->next_status_check)) {
- gp8psk_usb_in_op(st->d, GET_SIGNAL_LOCK, 0,0,&st->lock,1);
- gp8psk_usb_in_op(st->d, GET_SIGNAL_STRENGTH, 0,0,buf,6);
+ st->ops->in(st->priv, GET_SIGNAL_LOCK, 0, 0, &st->lock, 1);
+ st->ops->in(st->priv, GET_SIGNAL_STRENGTH, 0, 0, buf, 6);
st->snr = (buf[1]) << 8 | buf[0];
st->next_status_check = jiffies + (st->status_check_interval*HZ)/1000;
}
@@ -116,13 +132,12 @@ static int gp8psk_fe_get_tune_settings(struct dvb_frontend* fe, struct dvb_front
static int gp8psk_fe_set_frontend(struct dvb_frontend *fe)
{
- struct gp8psk_fe_state *state = fe->demodulator_priv;
+ struct gp8psk_fe_state *st = fe->demodulator_priv;
struct dtv_frontend_properties *c = &fe->dtv_property_cache;
u8 cmd[10];
u32 freq = c->frequency * 1000;
- int gp_product_id = le16_to_cpu(state->d->udev->descriptor.idProduct);
- deb_fe("%s()\n", __func__);
+ dprintk("%s()\n", __func__);
cmd[4] = freq & 0xff;
cmd[5] = (freq >> 8) & 0xff;
@@ -136,21 +151,21 @@ static int gp8psk_fe_set_frontend(struct dvb_frontend *fe)
switch (c->delivery_system) {
case SYS_DVBS:
if (c->modulation != QPSK) {
- deb_fe("%s: unsupported modulation selected (%d)\n",
+ dprintk("%s: unsupported modulation selected (%d)\n",
__func__, c->modulation);
return -EOPNOTSUPP;
}
c->fec_inner = FEC_AUTO;
break;
case SYS_DVBS2: /* kept for backwards compatibility */
- deb_fe("%s: DVB-S2 delivery system selected\n", __func__);
+ dprintk("%s: DVB-S2 delivery system selected\n", __func__);
break;
case SYS_TURBO:
- deb_fe("%s: Turbo-FEC delivery system selected\n", __func__);
+ dprintk("%s: Turbo-FEC delivery system selected\n", __func__);
break;
default:
- deb_fe("%s: unsupported delivery system selected (%d)\n",
+ dprintk("%s: unsupported delivery system selected (%d)\n",
__func__, c->delivery_system);
return -EOPNOTSUPP;
}
@@ -161,9 +176,9 @@ static int gp8psk_fe_set_frontend(struct dvb_frontend *fe)
cmd[3] = (c->symbol_rate >> 24) & 0xff;
switch (c->modulation) {
case QPSK:
- if (gp_product_id == USB_PID_GENPIX_8PSK_REV_1_WARM)
+ if (st->is_rev1)
if (gp8psk_tuned_to_DCII(fe))
- gp8psk_bcm4500_reload(state->d);
+ st->ops->reload(st->priv);
switch (c->fec_inner) {
case FEC_1_2:
cmd[9] = 0; break;
@@ -207,18 +222,18 @@ static int gp8psk_fe_set_frontend(struct dvb_frontend *fe)
cmd[9] = 0;
break;
default: /* Unknown modulation */
- deb_fe("%s: unsupported modulation selected (%d)\n",
+ dprintk("%s: unsupported modulation selected (%d)\n",
__func__, c->modulation);
return -EOPNOTSUPP;
}
- if (gp_product_id == USB_PID_GENPIX_8PSK_REV_1_WARM)
+ if (st->is_rev1)
gp8psk_set_tuner_mode(fe, 0);
- gp8psk_usb_out_op(state->d, TUNE_8PSK, 0, 0, cmd, 10);
+ st->ops->out(st->priv, TUNE_8PSK, 0, 0, cmd, 10);
- state->lock = 0;
- state->next_status_check = jiffies;
- state->status_check_interval = 200;
+ st->lock = 0;
+ st->next_status_check = jiffies;
+ st->status_check_interval = 200;
return 0;
}
@@ -228,9 +243,9 @@ static int gp8psk_fe_send_diseqc_msg (struct dvb_frontend* fe,
{
struct gp8psk_fe_state *st = fe->demodulator_priv;
- deb_fe("%s\n",__func__);
+ dprintk("%s\n", __func__);
- if (gp8psk_usb_out_op(st->d,SEND_DISEQC_COMMAND, m->msg[0], 0,
+ if (st->ops->out(st->priv, SEND_DISEQC_COMMAND, m->msg[0], 0,
m->msg, m->msg_len)) {
return -EINVAL;
}
@@ -243,12 +258,12 @@ static int gp8psk_fe_send_diseqc_burst(struct dvb_frontend *fe,
struct gp8psk_fe_state *st = fe->demodulator_priv;
u8 cmd;
- deb_fe("%s\n",__func__);
+ dprintk("%s\n", __func__);
/* These commands are certainly wrong */
cmd = (burst == SEC_MINI_A) ? 0x00 : 0x01;
- if (gp8psk_usb_out_op(st->d,SEND_DISEQC_COMMAND, cmd, 0,
+ if (st->ops->out(st->priv, SEND_DISEQC_COMMAND, cmd, 0,
&cmd, 0)) {
return -EINVAL;
}
@@ -258,10 +273,10 @@ static int gp8psk_fe_send_diseqc_burst(struct dvb_frontend *fe,
static int gp8psk_fe_set_tone(struct dvb_frontend *fe,
enum fe_sec_tone_mode tone)
{
- struct gp8psk_fe_state* state = fe->demodulator_priv;
+ struct gp8psk_fe_state *st = fe->demodulator_priv;
- if (gp8psk_usb_out_op(state->d,SET_22KHZ_TONE,
- (tone == SEC_TONE_ON), 0, NULL, 0)) {
+ if (st->ops->out(st->priv, SET_22KHZ_TONE,
+ (tone == SEC_TONE_ON), 0, NULL, 0)) {
return -EINVAL;
}
return 0;
@@ -270,9 +285,9 @@ static int gp8psk_fe_set_tone(struct dvb_frontend *fe,
static int gp8psk_fe_set_voltage(struct dvb_frontend *fe,
enum fe_sec_voltage voltage)
{
- struct gp8psk_fe_state* state = fe->demodulator_priv;
+ struct gp8psk_fe_state *st = fe->demodulator_priv;
- if (gp8psk_usb_out_op(state->d,SET_LNB_VOLTAGE,
+ if (st->ops->out(st->priv, SET_LNB_VOLTAGE,
voltage == SEC_VOLTAGE_18, 0, NULL, 0)) {
return -EINVAL;
}
@@ -281,52 +296,60 @@ static int gp8psk_fe_set_voltage(struct dvb_frontend *fe,
static int gp8psk_fe_enable_high_lnb_voltage(struct dvb_frontend* fe, long onoff)
{
- struct gp8psk_fe_state* state = fe->demodulator_priv;
- return gp8psk_usb_out_op(state->d, USE_EXTRA_VOLT, onoff, 0,NULL,0);
+ struct gp8psk_fe_state *st = fe->demodulator_priv;
+
+ return st->ops->out(st->priv, USE_EXTRA_VOLT, onoff, 0, NULL, 0);
}
static int gp8psk_fe_send_legacy_dish_cmd (struct dvb_frontend* fe, unsigned long sw_cmd)
{
- struct gp8psk_fe_state* state = fe->demodulator_priv;
+ struct gp8psk_fe_state *st = fe->demodulator_priv;
u8 cmd = sw_cmd & 0x7f;
- if (gp8psk_usb_out_op(state->d,SET_DN_SWITCH, cmd, 0,
- NULL, 0)) {
+ if (st->ops->out(st->priv, SET_DN_SWITCH, cmd, 0, NULL, 0))
return -EINVAL;
- }
- if (gp8psk_usb_out_op(state->d,SET_LNB_VOLTAGE, !!(sw_cmd & 0x80),
- 0, NULL, 0)) {
+
+ if (st->ops->out(st->priv, SET_LNB_VOLTAGE, !!(sw_cmd & 0x80),
+ 0, NULL, 0))
return -EINVAL;
- }
return 0;
}
static void gp8psk_fe_release(struct dvb_frontend* fe)
{
- struct gp8psk_fe_state *state = fe->demodulator_priv;
- kfree(state);
+ struct gp8psk_fe_state *st = fe->demodulator_priv;
+
+ kfree(st);
}
static struct dvb_frontend_ops gp8psk_fe_ops;
-struct dvb_frontend * gp8psk_fe_attach(struct dvb_usb_device *d)
+struct dvb_frontend *gp8psk_fe_attach(const struct gp8psk_fe_ops *ops,
+ void *priv, bool is_rev1)
{
- struct gp8psk_fe_state *s = kzalloc(sizeof(struct gp8psk_fe_state), GFP_KERNEL);
- if (s == NULL)
- goto error;
+ struct gp8psk_fe_state *st;
- s->d = d;
- memcpy(&s->fe.ops, &gp8psk_fe_ops, sizeof(struct dvb_frontend_ops));
- s->fe.demodulator_priv = s;
+ if (!ops || !ops->in || !ops->out || !ops->reload) {
+ pr_err("Error! gp8psk-fe ops not defined.\n");
+ return NULL;
+ }
- goto success;
-error:
- return NULL;
-success:
- return &s->fe;
+ st = kzalloc(sizeof(struct gp8psk_fe_state), GFP_KERNEL);
+ if (!st)
+ return NULL;
+
+ memcpy(&st->fe.ops, &gp8psk_fe_ops, sizeof(struct dvb_frontend_ops));
+ st->fe.demodulator_priv = st;
+ st->ops = ops;
+ st->priv = priv;
+ st->is_rev1 = is_rev1;
+
+ pr_info("Frontend %sattached\n", is_rev1 ? "revision 1 " : "");
+
+ return &st->fe;
}
-
+EXPORT_SYMBOL_GPL(gp8psk_fe_attach);
static struct dvb_frontend_ops gp8psk_fe_ops = {
.delsys = { SYS_DVBS },
@@ -370,3 +393,8 @@ static struct dvb_frontend_ops gp8psk_fe_ops = {
.dishnetwork_send_legacy_command = gp8psk_fe_send_legacy_dish_cmd,
.enable_high_lnb_voltage = gp8psk_fe_enable_high_lnb_voltage
};
+
+MODULE_AUTHOR("Alan Nisota <alannisota@gamil.com>");
+MODULE_DESCRIPTION("Frontend Driver for Genpix DVB-S");
+MODULE_VERSION("1.1");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/gp8psk-fe.h b/drivers/media/dvb-frontends/gp8psk-fe.h
new file mode 100644
index 0000000..6c7944b
--- /dev/null
+++ b/drivers/media/dvb-frontends/gp8psk-fe.h
@@ -0,0 +1,82 @@
+/*
+ * gp8psk_fe driver
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef GP8PSK_FE_H
+#define GP8PSK_FE_H
+
+#include <linux/types.h>
+
+/* gp8psk commands */
+
+#define GET_8PSK_CONFIG 0x80 /* in */
+#define SET_8PSK_CONFIG 0x81
+#define I2C_WRITE 0x83
+#define I2C_READ 0x84
+#define ARM_TRANSFER 0x85
+#define TUNE_8PSK 0x86
+#define GET_SIGNAL_STRENGTH 0x87 /* in */
+#define LOAD_BCM4500 0x88
+#define BOOT_8PSK 0x89 /* in */
+#define START_INTERSIL 0x8A /* in */
+#define SET_LNB_VOLTAGE 0x8B
+#define SET_22KHZ_TONE 0x8C
+#define SEND_DISEQC_COMMAND 0x8D
+#define SET_DVB_MODE 0x8E
+#define SET_DN_SWITCH 0x8F
+#define GET_SIGNAL_LOCK 0x90 /* in */
+#define GET_FW_VERS 0x92
+#define GET_SERIAL_NUMBER 0x93 /* in */
+#define USE_EXTRA_VOLT 0x94
+#define GET_FPGA_VERS 0x95
+#define CW3K_INIT 0x9d
+
+/* PSK_configuration bits */
+#define bm8pskStarted 0x01
+#define bm8pskFW_Loaded 0x02
+#define bmIntersilOn 0x04
+#define bmDVBmode 0x08
+#define bm22kHz 0x10
+#define bmSEL18V 0x20
+#define bmDCtuned 0x40
+#define bmArmed 0x80
+
+/* Satellite modulation modes */
+#define ADV_MOD_DVB_QPSK 0 /* DVB-S QPSK */
+#define ADV_MOD_TURBO_QPSK 1 /* Turbo QPSK */
+#define ADV_MOD_TURBO_8PSK 2 /* Turbo 8PSK (also used for Trellis 8PSK) */
+#define ADV_MOD_TURBO_16QAM 3 /* Turbo 16QAM (also used for Trellis 8PSK) */
+
+#define ADV_MOD_DCII_C_QPSK 4 /* Digicipher II Combo */
+#define ADV_MOD_DCII_I_QPSK 5 /* Digicipher II I-stream */
+#define ADV_MOD_DCII_Q_QPSK 6 /* Digicipher II Q-stream */
+#define ADV_MOD_DCII_C_OQPSK 7 /* Digicipher II offset QPSK */
+#define ADV_MOD_DSS_QPSK 8 /* DSS (DIRECTV) QPSK */
+#define ADV_MOD_DVB_BPSK 9 /* DVB-S BPSK */
+
+/* firmware revision id's */
+#define GP8PSK_FW_REV1 0x020604
+#define GP8PSK_FW_REV2 0x020704
+#define GP8PSK_FW_VERS(_fw_vers) \
+ ((_fw_vers)[2]<<0x10 | (_fw_vers)[1]<<0x08 | (_fw_vers)[0])
+
+struct gp8psk_fe_ops {
+ int (*in)(void *priv, u8 req, u16 value, u16 index, u8 *b, int blen);
+ int (*out)(void *priv, u8 req, u16 value, u16 index, u8 *b, int blen);
+ int (*reload)(void *priv);
+};
+
+struct dvb_frontend *gp8psk_fe_attach(const struct gp8psk_fe_ops *ops,
+ void *priv, bool is_rev1);
+
+#endif
diff --git a/drivers/media/i2c/ir-kbd-i2c.c b/drivers/media/i2c/ir-kbd-i2c.c
index f95a6bc..cede397 100644
--- a/drivers/media/i2c/ir-kbd-i2c.c
+++ b/drivers/media/i2c/ir-kbd-i2c.c
@@ -118,7 +118,7 @@ static int get_key_haup_common(struct IR_i2c *ir, enum rc_type *protocol,
*protocol = RC_TYPE_RC6_MCE;
dev &= 0x7f;
dprintk(1, "ir hauppauge (rc6-mce): t%d vendor=%d dev=%d code=%d\n",
- toggle, vendor, dev, code);
+ *ptoggle, vendor, dev, code);
} else {
*ptoggle = 0;
*protocol = RC_TYPE_RC6_6A_32;
diff --git a/drivers/media/pci/ivtv/ivtv-udma.c b/drivers/media/pci/ivtv/ivtv-udma.c
index 4769469..2c9232e 100644
--- a/drivers/media/pci/ivtv/ivtv-udma.c
+++ b/drivers/media/pci/ivtv/ivtv-udma.c
@@ -124,8 +124,8 @@ int ivtv_udma_setup(struct ivtv *itv, unsigned long ivtv_dest_addr,
}
/* Get user pages for DMA Xfer */
- err = get_user_pages_unlocked(user_dma.uaddr, user_dma.page_count, 0,
- 1, dma->map);
+ err = get_user_pages_unlocked(user_dma.uaddr, user_dma.page_count,
+ dma->map, FOLL_FORCE);
if (user_dma.page_count != err) {
IVTV_DEBUG_WARN("failed to map user pages, returned %d instead of %d\n",
diff --git a/drivers/media/pci/ivtv/ivtv-yuv.c b/drivers/media/pci/ivtv/ivtv-yuv.c
index b094054..f7299d3 100644
--- a/drivers/media/pci/ivtv/ivtv-yuv.c
+++ b/drivers/media/pci/ivtv/ivtv-yuv.c
@@ -76,11 +76,12 @@ static int ivtv_yuv_prep_user_dma(struct ivtv *itv, struct ivtv_user_dma *dma,
/* Get user pages for DMA Xfer */
y_pages = get_user_pages_unlocked(y_dma.uaddr,
- y_dma.page_count, 0, 1, &dma->map[0]);
+ y_dma.page_count, &dma->map[0], FOLL_FORCE);
uv_pages = 0; /* silence gcc. value is set and consumed only if: */
if (y_pages == y_dma.page_count) {
uv_pages = get_user_pages_unlocked(uv_dma.uaddr,
- uv_dma.page_count, 0, 1, &dma->map[y_pages]);
+ uv_dma.page_count, &dma->map[y_pages],
+ FOLL_FORCE);
}
if (y_pages != y_dma.page_count || uv_pages != uv_dma.page_count) {
diff --git a/drivers/media/platform/omap/omap_vout.c b/drivers/media/platform/omap/omap_vout.c
index e668dde..a31b95c 100644
--- a/drivers/media/platform/omap/omap_vout.c
+++ b/drivers/media/platform/omap/omap_vout.c
@@ -214,7 +214,7 @@ static int omap_vout_get_userptr(struct videobuf_buffer *vb, u32 virtp,
if (!vec)
return -ENOMEM;
- ret = get_vaddr_frames(virtp, 1, true, false, vec);
+ ret = get_vaddr_frames(virtp, 1, FOLL_WRITE, vec);
if (ret != 1) {
frame_vector_destroy(vec);
return -EINVAL;
diff --git a/drivers/media/usb/b2c2/flexcop-usb.c b/drivers/media/usb/b2c2/flexcop-usb.c
index d4bdba6..52bc42d 100644
--- a/drivers/media/usb/b2c2/flexcop-usb.c
+++ b/drivers/media/usb/b2c2/flexcop-usb.c
@@ -73,23 +73,34 @@ static int flexcop_usb_readwrite_dw(struct flexcop_device *fc, u16 wRegOffsPCI,
u8 request_type = (read ? USB_DIR_IN : USB_DIR_OUT) | USB_TYPE_VENDOR;
u8 wAddress = B2C2_FLEX_PCIOFFSET_TO_INTERNALADDR(wRegOffsPCI) |
(read ? 0x80 : 0);
+ int ret;
- int len = usb_control_msg(fc_usb->udev,
+ mutex_lock(&fc_usb->data_mutex);
+ if (!read)
+ memcpy(fc_usb->data, val, sizeof(*val));
+
+ ret = usb_control_msg(fc_usb->udev,
read ? B2C2_USB_CTRL_PIPE_IN : B2C2_USB_CTRL_PIPE_OUT,
request,
request_type, /* 0xc0 read or 0x40 write */
wAddress,
0,
- val,
+ fc_usb->data,
sizeof(u32),
B2C2_WAIT_FOR_OPERATION_RDW * HZ);
- if (len != sizeof(u32)) {
+ if (ret != sizeof(u32)) {
err("error while %s dword from %d (%d).", read ? "reading" :
"writing", wAddress, wRegOffsPCI);
- return -EIO;
+ if (ret >= 0)
+ ret = -EIO;
}
- return 0;
+
+ if (read && ret >= 0)
+ memcpy(val, fc_usb->data, sizeof(*val));
+ mutex_unlock(&fc_usb->data_mutex);
+
+ return ret;
}
/*
* DKT 010817 - add support for V8 memory read/write and flash update
@@ -100,9 +111,14 @@ static int flexcop_usb_v8_memory_req(struct flexcop_usb *fc_usb,
{
u8 request_type = USB_TYPE_VENDOR;
u16 wIndex;
- int nWaitTime, pipe, len;
+ int nWaitTime, pipe, ret;
wIndex = page << 8;
+ if (buflen > sizeof(fc_usb->data)) {
+ err("Buffer size bigger than max URB control message\n");
+ return -EIO;
+ }
+
switch (req) {
case B2C2_USB_READ_V8_MEM:
nWaitTime = B2C2_WAIT_FOR_OPERATION_V8READ;
@@ -127,17 +143,32 @@ static int flexcop_usb_v8_memory_req(struct flexcop_usb *fc_usb,
deb_v8("v8mem: %02x %02x %04x %04x, len: %d\n", request_type, req,
wAddress, wIndex, buflen);
- len = usb_control_msg(fc_usb->udev, pipe,
+ mutex_lock(&fc_usb->data_mutex);
+
+ if ((request_type & USB_ENDPOINT_DIR_MASK) == USB_DIR_OUT)
+ memcpy(fc_usb->data, pbBuffer, buflen);
+
+ ret = usb_control_msg(fc_usb->udev, pipe,
req,
request_type,
wAddress,
wIndex,
- pbBuffer,
+ fc_usb->data,
buflen,
nWaitTime * HZ);
+ if (ret != buflen)
+ ret = -EIO;
- debug_dump(pbBuffer, len, deb_v8);
- return len == buflen ? 0 : -EIO;
+ if (ret >= 0) {
+ ret = 0;
+ if ((request_type & USB_ENDPOINT_DIR_MASK) == USB_DIR_IN)
+ memcpy(pbBuffer, fc_usb->data, buflen);
+ }
+
+ mutex_unlock(&fc_usb->data_mutex);
+
+ debug_dump(pbBuffer, ret, deb_v8);
+ return ret;
}
#define bytes_left_to_read_on_page(paddr,buflen) \
@@ -196,29 +227,6 @@ static int flexcop_usb_get_mac_addr(struct flexcop_device *fc, int extended)
fc->dvb_adapter.proposed_mac, 6);
}
-#if 0
-static int flexcop_usb_utility_req(struct flexcop_usb *fc_usb, int set,
- flexcop_usb_utility_function_t func, u8 extra, u16 wIndex,
- u16 buflen, u8 *pvBuffer)
-{
- u16 wValue;
- u8 request_type = (set ? USB_DIR_OUT : USB_DIR_IN) | USB_TYPE_VENDOR;
- int nWaitTime = 2,
- pipe = set ? B2C2_USB_CTRL_PIPE_OUT : B2C2_USB_CTRL_PIPE_IN, len;
- wValue = (func << 8) | extra;
-
- len = usb_control_msg(fc_usb->udev,pipe,
- B2C2_USB_UTILITY,
- request_type,
- wValue,
- wIndex,
- pvBuffer,
- buflen,
- nWaitTime * HZ);
- return len == buflen ? 0 : -EIO;
-}
-#endif
-
/* usb i2c stuff */
static int flexcop_usb_i2c_req(struct flexcop_i2c_adapter *i2c,
flexcop_usb_request_t req, flexcop_usb_i2c_function_t func,
@@ -226,9 +234,14 @@ static int flexcop_usb_i2c_req(struct flexcop_i2c_adapter *i2c,
{
struct flexcop_usb *fc_usb = i2c->fc->bus_specific;
u16 wValue, wIndex;
- int nWaitTime,pipe,len;
+ int nWaitTime, pipe, ret;
u8 request_type = USB_TYPE_VENDOR;
+ if (buflen > sizeof(fc_usb->data)) {
+ err("Buffer size bigger than max URB control message\n");
+ return -EIO;
+ }
+
switch (func) {
case USB_FUNC_I2C_WRITE:
case USB_FUNC_I2C_MULTIWRITE:
@@ -257,15 +270,32 @@ static int flexcop_usb_i2c_req(struct flexcop_i2c_adapter *i2c,
wValue & 0xff, wValue >> 8,
wIndex & 0xff, wIndex >> 8);
- len = usb_control_msg(fc_usb->udev,pipe,
+ mutex_lock(&fc_usb->data_mutex);
+
+ if ((request_type & USB_ENDPOINT_DIR_MASK) == USB_DIR_OUT)
+ memcpy(fc_usb->data, buf, buflen);
+
+ ret = usb_control_msg(fc_usb->udev, pipe,
req,
request_type,
wValue,
wIndex,
- buf,
+ fc_usb->data,
buflen,
nWaitTime * HZ);
- return len == buflen ? 0 : -EREMOTEIO;
+
+ if (ret != buflen)
+ ret = -EIO;
+
+ if (ret >= 0) {
+ ret = 0;
+ if ((request_type & USB_ENDPOINT_DIR_MASK) == USB_DIR_IN)
+ memcpy(buf, fc_usb->data, buflen);
+ }
+
+ mutex_unlock(&fc_usb->data_mutex);
+
+ return 0;
}
/* actual bus specific access functions,
@@ -516,6 +546,7 @@ static int flexcop_usb_probe(struct usb_interface *intf,
/* general flexcop init */
fc_usb = fc->bus_specific;
fc_usb->fc_dev = fc;
+ mutex_init(&fc_usb->data_mutex);
fc->read_ibi_reg = flexcop_usb_read_ibi_reg;
fc->write_ibi_reg = flexcop_usb_write_ibi_reg;
diff --git a/drivers/media/usb/b2c2/flexcop-usb.h b/drivers/media/usb/b2c2/flexcop-usb.h
index 92529a9..25ad431 100644
--- a/drivers/media/usb/b2c2/flexcop-usb.h
+++ b/drivers/media/usb/b2c2/flexcop-usb.h
@@ -29,6 +29,10 @@ struct flexcop_usb {
u8 tmp_buffer[1023+190];
int tmp_buffer_length;
+
+ /* for URB control messages */
+ u8 data[80];
+ struct mutex data_mutex;
};
#if 0
diff --git a/drivers/media/usb/cpia2/cpia2_usb.c b/drivers/media/usb/cpia2/cpia2_usb.c
index 13620cd..e9100a2 100644
--- a/drivers/media/usb/cpia2/cpia2_usb.c
+++ b/drivers/media/usb/cpia2/cpia2_usb.c
@@ -545,18 +545,30 @@ static void free_sbufs(struct camera_data *cam)
static int write_packet(struct usb_device *udev,
u8 request, u8 * registers, u16 start, size_t size)
{
+ unsigned char *buf;
+ int ret;
+
if (!registers || size <= 0)
return -EINVAL;
- return usb_control_msg(udev,
+ buf = kmalloc(size, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ memcpy(buf, registers, size);
+
+ ret = usb_control_msg(udev,
usb_sndctrlpipe(udev, 0),
request,
USB_TYPE_VENDOR | USB_RECIP_DEVICE,
start, /* value */
0, /* index */
- registers, /* buffer */
+ buf, /* buffer */
size,
HZ);
+
+ kfree(buf);
+ return ret;
}
/****************************************************************************
@@ -567,18 +579,32 @@ static int write_packet(struct usb_device *udev,
static int read_packet(struct usb_device *udev,
u8 request, u8 * registers, u16 start, size_t size)
{
+ unsigned char *buf;
+ int ret;
+
if (!registers || size <= 0)
return -EINVAL;
- return usb_control_msg(udev,
+ buf = kmalloc(size, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ ret = usb_control_msg(udev,
usb_rcvctrlpipe(udev, 0),
request,
USB_DIR_IN|USB_TYPE_VENDOR|USB_RECIP_DEVICE,
start, /* value */
0, /* index */
- registers, /* buffer */
+ buf, /* buffer */
size,
HZ);
+
+ if (ret >= 0)
+ memcpy(registers, buf, size);
+
+ kfree(buf);
+
+ return ret;
}
/******************************************************************************
diff --git a/drivers/media/usb/dvb-usb/Makefile b/drivers/media/usb/dvb-usb/Makefile
index 2a7b5a9..3b3f32b 100644
--- a/drivers/media/usb/dvb-usb/Makefile
+++ b/drivers/media/usb/dvb-usb/Makefile
@@ -8,7 +8,7 @@
dvb-usb-vp702x-objs := vp702x.o vp702x-fe.o
obj-$(CONFIG_DVB_USB_VP702X) += dvb-usb-vp702x.o
-dvb-usb-gp8psk-objs := gp8psk.o gp8psk-fe.o
+dvb-usb-gp8psk-objs := gp8psk.o
obj-$(CONFIG_DVB_USB_GP8PSK) += dvb-usb-gp8psk.o
dvb-usb-dtt200u-objs := dtt200u.o dtt200u-fe.o
diff --git a/drivers/media/usb/dvb-usb/af9005.c b/drivers/media/usb/dvb-usb/af9005.c
index efa782e..7853261 100644
--- a/drivers/media/usb/dvb-usb/af9005.c
+++ b/drivers/media/usb/dvb-usb/af9005.c
@@ -52,17 +52,15 @@ u8 regmask[8] = { 0x01, 0x03, 0x07, 0x0f, 0x1f, 0x3f, 0x7f, 0xff };
struct af9005_device_state {
u8 sequence;
int led_state;
+ unsigned char data[256];
};
static int af9005_generic_read_write(struct dvb_usb_device *d, u16 reg,
int readwrite, int type, u8 * values, int len)
{
struct af9005_device_state *st = d->priv;
- u8 obuf[16] = { 0 };
- u8 ibuf[17] = { 0 };
- u8 command;
- int i;
- int ret;
+ u8 command, seq;
+ int i, ret;
if (len < 1) {
err("generic read/write, less than 1 byte. Makes no sense.");
@@ -73,16 +71,17 @@ static int af9005_generic_read_write(struct dvb_usb_device *d, u16 reg,
return -EINVAL;
}
- obuf[0] = 14; /* rest of buffer length low */
- obuf[1] = 0; /* rest of buffer length high */
+ mutex_lock(&d->data_mutex);
+ st->data[0] = 14; /* rest of buffer length low */
+ st->data[1] = 0; /* rest of buffer length high */
- obuf[2] = AF9005_REGISTER_RW; /* register operation */
- obuf[3] = 12; /* rest of buffer length */
+ st->data[2] = AF9005_REGISTER_RW; /* register operation */
+ st->data[3] = 12; /* rest of buffer length */
- obuf[4] = st->sequence++; /* sequence number */
+ st->data[4] = seq = st->sequence++; /* sequence number */
- obuf[5] = (u8) (reg >> 8); /* register address */
- obuf[6] = (u8) (reg & 0xff);
+ st->data[5] = (u8) (reg >> 8); /* register address */
+ st->data[6] = (u8) (reg & 0xff);
if (type == AF9005_OFDM_REG) {
command = AF9005_CMD_OFDM_REG;
@@ -96,51 +95,52 @@ static int af9005_generic_read_write(struct dvb_usb_device *d, u16 reg,
command |= readwrite;
if (readwrite == AF9005_CMD_WRITE)
for (i = 0; i < len; i++)
- obuf[8 + i] = values[i];
+ st->data[8 + i] = values[i];
else if (type == AF9005_TUNER_REG)
/* read command for tuner, the first byte contains the i2c address */
- obuf[8] = values[0];
- obuf[7] = command;
+ st->data[8] = values[0];
+ st->data[7] = command;
- ret = dvb_usb_generic_rw(d, obuf, 16, ibuf, 17, 0);
+ ret = dvb_usb_generic_rw(d, st->data, 16, st->data, 17, 0);
if (ret)
- return ret;
+ goto ret;
/* sanity check */
- if (ibuf[2] != AF9005_REGISTER_RW_ACK) {
+ if (st->data[2] != AF9005_REGISTER_RW_ACK) {
err("generic read/write, wrong reply code.");
- return -EIO;
+ ret = -EIO;
+ goto ret;
}
- if (ibuf[3] != 0x0d) {
+ if (st->data[3] != 0x0d) {
err("generic read/write, wrong length in reply.");
- return -EIO;
+ ret = -EIO;
+ goto ret;
}
- if (ibuf[4] != obuf[4]) {
+ if (st->data[4] != seq) {
err("generic read/write, wrong sequence in reply.");
- return -EIO;
+ ret = -EIO;
+ goto ret;
}
/*
- Windows driver doesn't check these fields, in fact sometimes
- the register in the reply is different that what has been sent
-
- if (ibuf[5] != obuf[5] || ibuf[6] != obuf[6]) {
- err("generic read/write, wrong register in reply.");
- return -EIO;
- }
- if (ibuf[7] != command) {
- err("generic read/write wrong command in reply.");
- return -EIO;
- }
+ * In thesis, both input and output buffers should have
+ * identical values for st->data[5] to st->data[8].
+ * However, windows driver doesn't check these fields, in fact
+ * sometimes the register in the reply is different that what
+ * has been sent
*/
- if (ibuf[16] != 0x01) {
+ if (st->data[16] != 0x01) {
err("generic read/write wrong status code in reply.");
- return -EIO;
+ ret = -EIO;
+ goto ret;
}
+
if (readwrite == AF9005_CMD_READ)
for (i = 0; i < len; i++)
- values[i] = ibuf[8 + i];
+ values[i] = st->data[8 + i];
- return 0;
+ret:
+ mutex_unlock(&d->data_mutex);
+ return ret;
}
@@ -464,8 +464,7 @@ int af9005_send_command(struct dvb_usb_device *d, u8 command, u8 * wbuf,
struct af9005_device_state *st = d->priv;
int ret, i, packet_len;
- u8 buf[64];
- u8 ibuf[64];
+ u8 seq;
if (wlen < 0) {
err("send command, wlen less than 0 bytes. Makes no sense.");
@@ -480,94 +479,97 @@ int af9005_send_command(struct dvb_usb_device *d, u8 command, u8 * wbuf,
return -EINVAL;
}
packet_len = wlen + 5;
- buf[0] = (u8) (packet_len & 0xff);
- buf[1] = (u8) ((packet_len & 0xff00) >> 8);
- buf[2] = 0x26; /* packet type */
- buf[3] = wlen + 3;
- buf[4] = st->sequence++;
- buf[5] = command;
- buf[6] = wlen;
+ mutex_lock(&d->data_mutex);
+
+ st->data[0] = (u8) (packet_len & 0xff);
+ st->data[1] = (u8) ((packet_len & 0xff00) >> 8);
+
+ st->data[2] = 0x26; /* packet type */
+ st->data[3] = wlen + 3;
+ st->data[4] = seq = st->sequence++;
+ st->data[5] = command;
+ st->data[6] = wlen;
for (i = 0; i < wlen; i++)
- buf[7 + i] = wbuf[i];
- ret = dvb_usb_generic_rw(d, buf, wlen + 7, ibuf, rlen + 7, 0);
- if (ret)
- return ret;
- if (ibuf[2] != 0x27) {
+ st->data[7 + i] = wbuf[i];
+ ret = dvb_usb_generic_rw(d, st->data, wlen + 7, st->data, rlen + 7, 0);
+ if (st->data[2] != 0x27) {
err("send command, wrong reply code.");
- return -EIO;
- }
- if (ibuf[4] != buf[4]) {
+ ret = -EIO;
+ } else if (st->data[4] != seq) {
err("send command, wrong sequence in reply.");
- return -EIO;
- }
- if (ibuf[5] != 0x01) {
+ ret = -EIO;
+ } else if (st->data[5] != 0x01) {
err("send command, wrong status code in reply.");
- return -EIO;
- }
- if (ibuf[6] != rlen) {
+ ret = -EIO;
+ } else if (st->data[6] != rlen) {
err("send command, invalid data length in reply.");
- return -EIO;
+ ret = -EIO;
}
- for (i = 0; i < rlen; i++)
- rbuf[i] = ibuf[i + 7];
- return 0;
+ if (!ret) {
+ for (i = 0; i < rlen; i++)
+ rbuf[i] = st->data[i + 7];
+ }
+
+ mutex_unlock(&d->data_mutex);
+ return ret;
}
int af9005_read_eeprom(struct dvb_usb_device *d, u8 address, u8 * values,
int len)
{
struct af9005_device_state *st = d->priv;
- u8 obuf[16], ibuf[14];
+ u8 seq;
int ret, i;
- memset(obuf, 0, sizeof(obuf));
- memset(ibuf, 0, sizeof(ibuf));
+ mutex_lock(&d->data_mutex);
- obuf[0] = 14; /* length of rest of packet low */
- obuf[1] = 0; /* length of rest of packer high */
+ memset(st->data, 0, sizeof(st->data));
- obuf[2] = 0x2a; /* read/write eeprom */
+ st->data[0] = 14; /* length of rest of packet low */
+ st->data[1] = 0; /* length of rest of packer high */
- obuf[3] = 12; /* size */
+ st->data[2] = 0x2a; /* read/write eeprom */
- obuf[4] = st->sequence++;
+ st->data[3] = 12; /* size */
- obuf[5] = 0; /* read */
+ st->data[4] = seq = st->sequence++;
- obuf[6] = len;
- obuf[7] = address;
- ret = dvb_usb_generic_rw(d, obuf, 16, ibuf, 14, 0);
- if (ret)
- return ret;
- if (ibuf[2] != 0x2b) {
+ st->data[5] = 0; /* read */
+
+ st->data[6] = len;
+ st->data[7] = address;
+ ret = dvb_usb_generic_rw(d, st->data, 16, st->data, 14, 0);
+ if (st->data[2] != 0x2b) {
err("Read eeprom, invalid reply code");
- return -EIO;
- }
- if (ibuf[3] != 10) {
+ ret = -EIO;
+ } else if (st->data[3] != 10) {
err("Read eeprom, invalid reply length");
- return -EIO;
- }
- if (ibuf[4] != obuf[4]) {
+ ret = -EIO;
+ } else if (st->data[4] != seq) {
err("Read eeprom, wrong sequence in reply ");
- return -EIO;
- }
- if (ibuf[5] != 1) {
+ ret = -EIO;
+ } else if (st->data[5] != 1) {
err("Read eeprom, wrong status in reply ");
- return -EIO;
+ ret = -EIO;
}
- for (i = 0; i < len; i++) {
- values[i] = ibuf[6 + i];
+
+ if (!ret) {
+ for (i = 0; i < len; i++)
+ values[i] = st->data[6 + i];
}
- return 0;
+ mutex_unlock(&d->data_mutex);
+
+ return ret;
}
-static int af9005_boot_packet(struct usb_device *udev, int type, u8 * reply)
+static int af9005_boot_packet(struct usb_device *udev, int type, u8 *reply,
+ u8 *buf, int size)
{
- u8 buf[FW_BULKOUT_SIZE + 2];
u16 checksum;
int act_len, i, ret;
- memset(buf, 0, sizeof(buf));
+
+ memset(buf, 0, size);
buf[0] = (u8) (FW_BULKOUT_SIZE & 0xff);
buf[1] = (u8) ((FW_BULKOUT_SIZE >> 8) & 0xff);
switch (type) {
@@ -720,15 +722,21 @@ static int af9005_download_firmware(struct usb_device *udev, const struct firmwa
{
int i, packets, ret, act_len;
- u8 buf[FW_BULKOUT_SIZE + 2];
+ u8 *buf;
u8 reply;
- ret = af9005_boot_packet(udev, FW_CONFIG, &reply);
+ buf = kmalloc(FW_BULKOUT_SIZE + 2, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ ret = af9005_boot_packet(udev, FW_CONFIG, &reply, buf,
+ FW_BULKOUT_SIZE + 2);
if (ret)
- return ret;
+ goto err;
if (reply != 0x01) {
err("before downloading firmware, FW_CONFIG expected 0x01, received 0x%x", reply);
- return -EIO;
+ ret = -EIO;
+ goto err;
}
packets = fw->size / FW_BULKOUT_SIZE;
buf[0] = (u8) (FW_BULKOUT_SIZE & 0xff);
@@ -743,28 +751,35 @@ static int af9005_download_firmware(struct usb_device *udev, const struct firmwa
buf, FW_BULKOUT_SIZE + 2, &act_len, 1000);
if (ret) {
err("firmware download failed at packet %d with code %d", i, ret);
- return ret;
+ goto err;
}
}
- ret = af9005_boot_packet(udev, FW_CONFIRM, &reply);
+ ret = af9005_boot_packet(udev, FW_CONFIRM, &reply,
+ buf, FW_BULKOUT_SIZE + 2);
if (ret)
- return ret;
+ goto err;
if (reply != (u8) (packets & 0xff)) {
err("after downloading firmware, FW_CONFIRM expected 0x%x, received 0x%x", packets & 0xff, reply);
- return -EIO;
+ ret = -EIO;
+ goto err;
}
- ret = af9005_boot_packet(udev, FW_BOOT, &reply);
+ ret = af9005_boot_packet(udev, FW_BOOT, &reply, buf,
+ FW_BULKOUT_SIZE + 2);
if (ret)
- return ret;
- ret = af9005_boot_packet(udev, FW_CONFIG, &reply);
+ goto err;
+ ret = af9005_boot_packet(udev, FW_CONFIG, &reply, buf,
+ FW_BULKOUT_SIZE + 2);
if (ret)
- return ret;
+ goto err;
if (reply != 0x02) {
err("after downloading firmware, FW_CONFIG expected 0x02, received 0x%x", reply);
- return -EIO;
+ ret = -EIO;
+ goto err;
}
- return 0;
+err:
+ kfree(buf);
+ return ret;
}
@@ -823,53 +838,59 @@ static int af9005_rc_query(struct dvb_usb_device *d, u32 * event, int *state)
{
struct af9005_device_state *st = d->priv;
int ret, len;
-
- u8 obuf[5];
- u8 ibuf[256];
+ u8 seq;
*state = REMOTE_NO_KEY_PRESSED;
if (rc_decode == NULL) {
/* it shouldn't never come here */
return 0;
}
+
+ mutex_lock(&d->data_mutex);
+
/* deb_info("rc_query\n"); */
- obuf[0] = 3; /* rest of packet length low */
- obuf[1] = 0; /* rest of packet lentgh high */
- obuf[2] = 0x40; /* read remote */
- obuf[3] = 1; /* rest of packet length */
- obuf[4] = st->sequence++; /* sequence number */
- ret = dvb_usb_generic_rw(d, obuf, 5, ibuf, 256, 0);
+ st->data[0] = 3; /* rest of packet length low */
+ st->data[1] = 0; /* rest of packet lentgh high */
+ st->data[2] = 0x40; /* read remote */
+ st->data[3] = 1; /* rest of packet length */
+ st->data[4] = seq = st->sequence++; /* sequence number */
+ ret = dvb_usb_generic_rw(d, st->data, 5, st->data, 256, 0);
if (ret) {
err("rc query failed");
- return ret;
+ goto ret;
}
- if (ibuf[2] != 0x41) {
+ if (st->data[2] != 0x41) {
err("rc query bad header.");
- return -EIO;
- }
- if (ibuf[4] != obuf[4]) {
+ ret = -EIO;
+ goto ret;
+ } else if (st->data[4] != seq) {
err("rc query bad sequence.");
- return -EIO;
+ ret = -EIO;
+ goto ret;
}
- len = ibuf[5];
+ len = st->data[5];
if (len > 246) {
err("rc query invalid length");
- return -EIO;
+ ret = -EIO;
+ goto ret;
}
if (len > 0) {
deb_rc("rc data (%d) ", len);
- debug_dump((ibuf + 6), len, deb_rc);
- ret = rc_decode(d, &ibuf[6], len, event, state);
+ debug_dump((st->data + 6), len, deb_rc);
+ ret = rc_decode(d, &st->data[6], len, event, state);
if (ret) {
err("rc_decode failed");
- return ret;
+ goto ret;
} else {
deb_rc("rc_decode state %x event %x\n", *state, *event);
if (*state == REMOTE_KEY_REPEAT)
*event = d->last_event;
}
}
- return 0;
+
+ret:
+ mutex_unlock(&d->data_mutex);
+ return ret;
}
static int af9005_power_ctrl(struct dvb_usb_device *d, int onoff)
@@ -953,10 +974,16 @@ static int af9005_identify_state(struct usb_device *udev,
int *cold)
{
int ret;
- u8 reply;
- ret = af9005_boot_packet(udev, FW_CONFIG, &reply);
+ u8 reply, *buf;
+
+ buf = kmalloc(FW_BULKOUT_SIZE + 2, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ ret = af9005_boot_packet(udev, FW_CONFIG, &reply,
+ buf, FW_BULKOUT_SIZE + 2);
if (ret)
- return ret;
+ goto err;
deb_info("result of FW_CONFIG in identify state %d\n", reply);
if (reply == 0x01)
*cold = 1;
@@ -965,7 +992,10 @@ static int af9005_identify_state(struct usb_device *udev,
else
return -EIO;
deb_info("Identify state cold = %d\n", *cold);
- return 0;
+
+err:
+ kfree(buf);
+ return ret;
}
static struct dvb_usb_device_properties af9005_properties;
@@ -974,7 +1004,7 @@ static int af9005_usb_probe(struct usb_interface *intf,
const struct usb_device_id *id)
{
return dvb_usb_device_init(intf, &af9005_properties,
- THIS_MODULE, NULL, adapter_nr);
+ THIS_MODULE, NULL, adapter_nr);
}
enum af9005_usb_table_entry {
diff --git a/drivers/media/usb/dvb-usb/cinergyT2-core.c b/drivers/media/usb/dvb-usb/cinergyT2-core.c
index 9fd1527..290275b 100644
--- a/drivers/media/usb/dvb-usb/cinergyT2-core.c
+++ b/drivers/media/usb/dvb-usb/cinergyT2-core.c
@@ -41,6 +41,7 @@ DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
struct cinergyt2_state {
u8 rc_counter;
+ unsigned char data[64];
};
/* We are missing a release hook with usb_device data */
@@ -50,38 +51,57 @@ static struct dvb_usb_device_properties cinergyt2_properties;
static int cinergyt2_streaming_ctrl(struct dvb_usb_adapter *adap, int enable)
{
- char buf[] = { CINERGYT2_EP1_CONTROL_STREAM_TRANSFER, enable ? 1 : 0 };
- char result[64];
- return dvb_usb_generic_rw(adap->dev, buf, sizeof(buf), result,
- sizeof(result), 0);
+ struct dvb_usb_device *d = adap->dev;
+ struct cinergyt2_state *st = d->priv;
+ int ret;
+
+ mutex_lock(&d->data_mutex);
+ st->data[0] = CINERGYT2_EP1_CONTROL_STREAM_TRANSFER;
+ st->data[1] = enable ? 1 : 0;
+
+ ret = dvb_usb_generic_rw(d, st->data, 2, st->data, 64, 0);
+ mutex_unlock(&d->data_mutex);
+
+ return ret;
}
static int cinergyt2_power_ctrl(struct dvb_usb_device *d, int enable)
{
- char buf[] = { CINERGYT2_EP1_SLEEP_MODE, enable ? 0 : 1 };
- char state[3];
- return dvb_usb_generic_rw(d, buf, sizeof(buf), state, sizeof(state), 0);
+ struct cinergyt2_state *st = d->priv;
+ int ret;
+
+ mutex_lock(&d->data_mutex);
+ st->data[0] = CINERGYT2_EP1_SLEEP_MODE;
+ st->data[1] = enable ? 0 : 1;
+
+ ret = dvb_usb_generic_rw(d, st->data, 2, st->data, 3, 0);
+ mutex_unlock(&d->data_mutex);
+
+ return ret;
}
static int cinergyt2_frontend_attach(struct dvb_usb_adapter *adap)
{
- char query[] = { CINERGYT2_EP1_GET_FIRMWARE_VERSION };
- char state[3];
+ struct dvb_usb_device *d = adap->dev;
+ struct cinergyt2_state *st = d->priv;
int ret;
adap->fe_adap[0].fe = cinergyt2_fe_attach(adap->dev);
- ret = dvb_usb_generic_rw(adap->dev, query, sizeof(query), state,
- sizeof(state), 0);
+ mutex_lock(&d->data_mutex);
+ st->data[0] = CINERGYT2_EP1_GET_FIRMWARE_VERSION;
+
+ ret = dvb_usb_generic_rw(d, st->data, 1, st->data, 3, 0);
if (ret < 0) {
deb_rc("cinergyt2_power_ctrl() Failed to retrieve sleep "
"state info\n");
}
+ mutex_unlock(&d->data_mutex);
/* Copy this pointer as we are gonna need it in the release phase */
cinergyt2_usb_device = adap->dev;
- return 0;
+ return ret;
}
static struct rc_map_table rc_map_cinergyt2_table[] = {
@@ -141,13 +161,18 @@ static int repeatable_keys[] = {
static int cinergyt2_rc_query(struct dvb_usb_device *d, u32 *event, int *state)
{
struct cinergyt2_state *st = d->priv;
- u8 key[5] = {0, 0, 0, 0, 0}, cmd = CINERGYT2_EP1_GET_RC_EVENTS;
- int i;
+ int i, ret;
*state = REMOTE_NO_KEY_PRESSED;
- dvb_usb_generic_rw(d, &cmd, 1, key, sizeof(key), 0);
- if (key[4] == 0xff) {
+ mutex_lock(&d->data_mutex);
+ st->data[0] = CINERGYT2_EP1_GET_RC_EVENTS;
+
+ ret = dvb_usb_generic_rw(d, st->data, 1, st->data, 5, 0);
+ if (ret < 0)
+ goto ret;
+
+ if (st->data[4] == 0xff) {
/* key repeat */
st->rc_counter++;
if (st->rc_counter > RC_REPEAT_DELAY) {
@@ -157,34 +182,36 @@ static int cinergyt2_rc_query(struct dvb_usb_device *d, u32 *event, int *state)
*event = d->last_event;
deb_rc("repeat key, event %x\n",
*event);
- return 0;
+ goto ret;
}
}
deb_rc("repeated key (non repeatable)\n");
}
- return 0;
+ goto ret;
}
/* hack to pass checksum on the custom field */
- key[2] = ~key[1];
- dvb_usb_nec_rc_key_to_event(d, key, event, state);
- if (key[0] != 0) {
+ st->data[2] = ~st->data[1];
+ dvb_usb_nec_rc_key_to_event(d, st->data, event, state);
+ if (st->data[0] != 0) {
if (*event != d->last_event)
st->rc_counter = 0;
- deb_rc("key: %*ph\n", 5, key);
+ deb_rc("key: %*ph\n", 5, st->data);
}
- return 0;
+
+ret:
+ mutex_unlock(&d->data_mutex);
+ return ret;
}
static int cinergyt2_usb_probe(struct usb_interface *intf,
const struct usb_device_id *id)
{
return dvb_usb_device_init(intf, &cinergyt2_properties,
- THIS_MODULE, NULL, adapter_nr);
+ THIS_MODULE, NULL, adapter_nr);
}
-
static struct usb_device_id cinergyt2_usb_table[] = {
{ USB_DEVICE(USB_VID_TERRATEC, 0x0038) },
{ 0 }
diff --git a/drivers/media/usb/dvb-usb/cinergyT2-fe.c b/drivers/media/usb/dvb-usb/cinergyT2-fe.c
index b3ec743..2d29b41 100644
--- a/drivers/media/usb/dvb-usb/cinergyT2-fe.c
+++ b/drivers/media/usb/dvb-usb/cinergyT2-fe.c
@@ -139,32 +139,42 @@ static uint16_t compute_tps(struct dtv_frontend_properties *op)
struct cinergyt2_fe_state {
struct dvb_frontend fe;
struct dvb_usb_device *d;
+
+ unsigned char data[64];
+ struct mutex data_mutex;
+
+ struct dvbt_get_status_msg status;
};
static int cinergyt2_fe_read_status(struct dvb_frontend *fe,
enum fe_status *status)
{
struct cinergyt2_fe_state *state = fe->demodulator_priv;
- struct dvbt_get_status_msg result;
- u8 cmd[] = { CINERGYT2_EP1_GET_TUNER_STATUS };
int ret;
- ret = dvb_usb_generic_rw(state->d, cmd, sizeof(cmd), (u8 *)&result,
- sizeof(result), 0);
+ mutex_lock(&state->data_mutex);
+ state->data[0] = CINERGYT2_EP1_GET_TUNER_STATUS;
+
+ ret = dvb_usb_generic_rw(state->d, state->data, 1,
+ state->data, sizeof(state->status), 0);
+ if (!ret)
+ memcpy(&state->status, state->data, sizeof(state->status));
+ mutex_unlock(&state->data_mutex);
+
if (ret < 0)
return ret;
*status = 0;
- if (0xffff - le16_to_cpu(result.gain) > 30)
+ if (0xffff - le16_to_cpu(state->status.gain) > 30)
*status |= FE_HAS_SIGNAL;
- if (result.lock_bits & (1 << 6))
+ if (state->status.lock_bits & (1 << 6))
*status |= FE_HAS_LOCK;
- if (result.lock_bits & (1 << 5))
+ if (state->status.lock_bits & (1 << 5))
*status |= FE_HAS_SYNC;
- if (result.lock_bits & (1 << 4))
+ if (state->status.lock_bits & (1 << 4))
*status |= FE_HAS_CARRIER;
- if (result.lock_bits & (1 << 1))
+ if (state->status.lock_bits & (1 << 1))
*status |= FE_HAS_VITERBI;
if ((*status & (FE_HAS_CARRIER | FE_HAS_VITERBI | FE_HAS_SYNC)) !=
@@ -177,34 +187,16 @@ static int cinergyt2_fe_read_status(struct dvb_frontend *fe,
static int cinergyt2_fe_read_ber(struct dvb_frontend *fe, u32 *ber)
{
struct cinergyt2_fe_state *state = fe->demodulator_priv;
- struct dvbt_get_status_msg status;
- char cmd[] = { CINERGYT2_EP1_GET_TUNER_STATUS };
- int ret;
- ret = dvb_usb_generic_rw(state->d, cmd, sizeof(cmd), (char *)&status,
- sizeof(status), 0);
- if (ret < 0)
- return ret;
-
- *ber = le32_to_cpu(status.viterbi_error_rate);
+ *ber = le32_to_cpu(state->status.viterbi_error_rate);
return 0;
}
static int cinergyt2_fe_read_unc_blocks(struct dvb_frontend *fe, u32 *unc)
{
struct cinergyt2_fe_state *state = fe->demodulator_priv;
- struct dvbt_get_status_msg status;
- u8 cmd[] = { CINERGYT2_EP1_GET_TUNER_STATUS };
- int ret;
- ret = dvb_usb_generic_rw(state->d, cmd, sizeof(cmd), (u8 *)&status,
- sizeof(status), 0);
- if (ret < 0) {
- err("cinergyt2_fe_read_unc_blocks() Failed! (Error=%d)\n",
- ret);
- return ret;
- }
- *unc = le32_to_cpu(status.uncorrected_block_count);
+ *unc = le32_to_cpu(state->status.uncorrected_block_count);
return 0;
}
@@ -212,35 +204,16 @@ static int cinergyt2_fe_read_signal_strength(struct dvb_frontend *fe,
u16 *strength)
{
struct cinergyt2_fe_state *state = fe->demodulator_priv;
- struct dvbt_get_status_msg status;
- char cmd[] = { CINERGYT2_EP1_GET_TUNER_STATUS };
- int ret;
- ret = dvb_usb_generic_rw(state->d, cmd, sizeof(cmd), (char *)&status,
- sizeof(status), 0);
- if (ret < 0) {
- err("cinergyt2_fe_read_signal_strength() Failed!"
- " (Error=%d)\n", ret);
- return ret;
- }
- *strength = (0xffff - le16_to_cpu(status.gain));
+ *strength = (0xffff - le16_to_cpu(state->status.gain));
return 0;
}
static int cinergyt2_fe_read_snr(struct dvb_frontend *fe, u16 *snr)
{
struct cinergyt2_fe_state *state = fe->demodulator_priv;
- struct dvbt_get_status_msg status;
- char cmd[] = { CINERGYT2_EP1_GET_TUNER_STATUS };
- int ret;
- ret = dvb_usb_generic_rw(state->d, cmd, sizeof(cmd), (char *)&status,
- sizeof(status), 0);
- if (ret < 0) {
- err("cinergyt2_fe_read_snr() Failed! (Error=%d)\n", ret);
- return ret;
- }
- *snr = (status.snr << 8) | status.snr;
+ *snr = (state->status.snr << 8) | state->status.snr;
return 0;
}
@@ -266,34 +239,36 @@ static int cinergyt2_fe_set_frontend(struct dvb_frontend *fe)
{
struct dtv_frontend_properties *fep = &fe->dtv_property_cache;
struct cinergyt2_fe_state *state = fe->demodulator_priv;
- struct dvbt_set_parameters_msg param;
- char result[2];
+ struct dvbt_set_parameters_msg *param;
int err;
- param.cmd = CINERGYT2_EP1_SET_TUNER_PARAMETERS;
- param.tps = cpu_to_le16(compute_tps(fep));
- param.freq = cpu_to_le32(fep->frequency / 1000);
- param.flags = 0;
+ mutex_lock(&state->data_mutex);
+
+ param = (void *)state->data;
+ param->cmd = CINERGYT2_EP1_SET_TUNER_PARAMETERS;
+ param->tps = cpu_to_le16(compute_tps(fep));
+ param->freq = cpu_to_le32(fep->frequency / 1000);
+ param->flags = 0;
switch (fep->bandwidth_hz) {
default:
case 8000000:
- param.bandwidth = 8;
+ param->bandwidth = 8;
break;
case 7000000:
- param.bandwidth = 7;
+ param->bandwidth = 7;
break;
case 6000000:
- param.bandwidth = 6;
+ param->bandwidth = 6;
break;
}
- err = dvb_usb_generic_rw(state->d,
- (char *)¶m, sizeof(param),
- result, sizeof(result), 0);
+ err = dvb_usb_generic_rw(state->d, state->data, sizeof(*param),
+ state->data, 2, 0);
if (err < 0)
err("cinergyt2_fe_set_frontend() Failed! err=%d\n", err);
+ mutex_unlock(&state->data_mutex);
return (err < 0) ? err : 0;
}
@@ -315,6 +290,7 @@ struct dvb_frontend *cinergyt2_fe_attach(struct dvb_usb_device *d)
s->d = d;
memcpy(&s->fe.ops, &cinergyt2_fe_ops, sizeof(struct dvb_frontend_ops));
s->fe.demodulator_priv = s;
+ mutex_init(&s->data_mutex);
return &s->fe;
}
diff --git a/drivers/media/usb/dvb-usb/cxusb.c b/drivers/media/usb/dvb-usb/cxusb.c
index 907ac01..2434030 100644
--- a/drivers/media/usb/dvb-usb/cxusb.c
+++ b/drivers/media/usb/dvb-usb/cxusb.c
@@ -45,9 +45,6 @@
#include "si2168.h"
#include "si2157.h"
-/* Max transfer size done by I2C transfer functions */
-#define MAX_XFER_SIZE 80
-
/* debug */
static int dvb_usb_cxusb_debug;
module_param_named(debug, dvb_usb_cxusb_debug, int, 0644);
@@ -61,23 +58,27 @@ DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
static int cxusb_ctrl_msg(struct dvb_usb_device *d,
u8 cmd, u8 *wbuf, int wlen, u8 *rbuf, int rlen)
{
- int wo = (rbuf == NULL || rlen == 0); /* write-only */
- u8 sndbuf[MAX_XFER_SIZE];
+ struct cxusb_state *st = d->priv;
+ int ret, wo;
- if (1 + wlen > sizeof(sndbuf)) {
- warn("i2c wr: len=%d is too big!\n",
- wlen);
+ if (1 + wlen > MAX_XFER_SIZE) {
+ warn("i2c wr: len=%d is too big!\n", wlen);
return -EOPNOTSUPP;
}
- memset(sndbuf, 0, 1+wlen);
+ wo = (rbuf == NULL || rlen == 0); /* write-only */
- sndbuf[0] = cmd;
- memcpy(&sndbuf[1], wbuf, wlen);
+ mutex_lock(&d->data_mutex);
+ st->data[0] = cmd;
+ memcpy(&st->data[1], wbuf, wlen);
if (wo)
- return dvb_usb_generic_write(d, sndbuf, 1+wlen);
+ ret = dvb_usb_generic_write(d, st->data, 1 + wlen);
else
- return dvb_usb_generic_rw(d, sndbuf, 1+wlen, rbuf, rlen, 0);
+ ret = dvb_usb_generic_rw(d, st->data, 1 + wlen,
+ rbuf, rlen, 0);
+
+ mutex_unlock(&d->data_mutex);
+ return ret;
}
/* GPIO */
diff --git a/drivers/media/usb/dvb-usb/cxusb.h b/drivers/media/usb/dvb-usb/cxusb.h
index 527ff79..18acda1 100644
--- a/drivers/media/usb/dvb-usb/cxusb.h
+++ b/drivers/media/usb/dvb-usb/cxusb.h
@@ -28,10 +28,15 @@
#define CMD_ANALOG 0x50
#define CMD_DIGITAL 0x51
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 80
+
struct cxusb_state {
u8 gpio_write_state[3];
struct i2c_client *i2c_client_demod;
struct i2c_client *i2c_client_tuner;
+
+ unsigned char data[MAX_XFER_SIZE];
};
#endif
diff --git a/drivers/media/usb/dvb-usb/dib0700_core.c b/drivers/media/usb/dvb-usb/dib0700_core.c
index f319665..47ce9d5 100644
--- a/drivers/media/usb/dvb-usb/dib0700_core.c
+++ b/drivers/media/usb/dvb-usb/dib0700_core.c
@@ -213,7 +213,7 @@ static int dib0700_i2c_xfer_new(struct i2c_adapter *adap, struct i2c_msg *msg,
usb_rcvctrlpipe(d->udev, 0),
REQUEST_NEW_I2C_READ,
USB_TYPE_VENDOR | USB_DIR_IN,
- value, index, msg[i].buf,
+ value, index, st->buf,
msg[i].len,
USB_CTRL_GET_TIMEOUT);
if (result < 0) {
@@ -221,6 +221,14 @@ static int dib0700_i2c_xfer_new(struct i2c_adapter *adap, struct i2c_msg *msg,
break;
}
+ if (msg[i].len > sizeof(st->buf)) {
+ deb_info("buffer too small to fit %d bytes\n",
+ msg[i].len);
+ return -EIO;
+ }
+
+ memcpy(msg[i].buf, st->buf, msg[i].len);
+
deb_data("<<< ");
debug_dump(msg[i].buf, msg[i].len, deb_data);
@@ -238,6 +246,13 @@ static int dib0700_i2c_xfer_new(struct i2c_adapter *adap, struct i2c_msg *msg,
/* I2C ctrl + FE bus; */
st->buf[3] = ((gen_mode << 6) & 0xC0) |
((bus_mode << 4) & 0x30);
+
+ if (msg[i].len > sizeof(st->buf) - 4) {
+ deb_info("i2c message to big: %d\n",
+ msg[i].len);
+ return -EIO;
+ }
+
/* The Actual i2c payload */
memcpy(&st->buf[4], msg[i].buf, msg[i].len);
@@ -283,6 +298,11 @@ static int dib0700_i2c_xfer_legacy(struct i2c_adapter *adap,
/* fill in the address */
st->buf[1] = msg[i].addr << 1;
/* fill the buffer */
+ if (msg[i].len > sizeof(st->buf) - 2) {
+ deb_info("i2c xfer to big: %d\n",
+ msg[i].len);
+ return -EIO;
+ }
memcpy(&st->buf[2], msg[i].buf, msg[i].len);
/* write/read request */
@@ -292,13 +312,20 @@ static int dib0700_i2c_xfer_legacy(struct i2c_adapter *adap,
/* special thing in the current firmware: when length is zero the read-failed */
len = dib0700_ctrl_rd(d, st->buf, msg[i].len + 2,
- msg[i+1].buf, msg[i+1].len);
+ st->buf, msg[i + 1].len);
if (len <= 0) {
deb_info("I2C read failed on address 0x%02x\n",
msg[i].addr);
break;
}
+ if (msg[i + 1].len > sizeof(st->buf)) {
+ deb_info("i2c xfer buffer to small for %d\n",
+ msg[i].len);
+ return -EIO;
+ }
+ memcpy(msg[i + 1].buf, st->buf, msg[i + 1].len);
+
msg[i+1].len = len;
i++;
@@ -677,7 +704,7 @@ static void dib0700_rc_urb_completion(struct urb *purb)
struct dvb_usb_device *d = purb->context;
struct dib0700_rc_response *poll_reply;
enum rc_type protocol;
- u32 uninitialized_var(keycode);
+ u32 keycode;
u8 toggle;
deb_info("%s()\n", __func__);
@@ -718,7 +745,8 @@ static void dib0700_rc_urb_completion(struct urb *purb)
poll_reply->nec.data == 0x00 &&
poll_reply->nec.not_data == 0xff) {
poll_reply->data_state = 2;
- break;
+ rc_repeat(d->rc_dev);
+ goto resubmit;
}
if ((poll_reply->nec.data ^ poll_reply->nec.not_data) != 0xff) {
diff --git a/drivers/media/usb/dvb-usb/dib0700_devices.c b/drivers/media/usb/dvb-usb/dib0700_devices.c
index 0857b56..ef1b8ee 100644
--- a/drivers/media/usb/dvb-usb/dib0700_devices.c
+++ b/drivers/media/usb/dvb-usb/dib0700_devices.c
@@ -508,8 +508,6 @@ static int stk7700ph_tuner_attach(struct dvb_usb_adapter *adap)
#define DEFAULT_RC_INTERVAL 50
-static u8 rc_request[] = { REQUEST_POLL_RC, 0 };
-
/*
* This function is used only when firmware is < 1.20 version. Newer
* firmwares use bulk mode, with functions implemented at dib0700_core,
@@ -517,7 +515,6 @@ static u8 rc_request[] = { REQUEST_POLL_RC, 0 };
*/
static int dib0700_rc_query_old_firmware(struct dvb_usb_device *d)
{
- u8 key[4];
enum rc_type protocol;
u32 scancode;
u8 toggle;
@@ -532,39 +529,43 @@ static int dib0700_rc_query_old_firmware(struct dvb_usb_device *d)
return 0;
}
- i = dib0700_ctrl_rd(d, rc_request, 2, key, 4);
+ st->buf[0] = REQUEST_POLL_RC;
+ st->buf[1] = 0;
+
+ i = dib0700_ctrl_rd(d, st->buf, 2, st->buf, 4);
if (i <= 0) {
err("RC Query Failed");
- return -1;
+ return -EIO;
}
/* losing half of KEY_0 events from Philipps rc5 remotes.. */
- if (key[0] == 0 && key[1] == 0 && key[2] == 0 && key[3] == 0)
+ if (st->buf[0] == 0 && st->buf[1] == 0
+ && st->buf[2] == 0 && st->buf[3] == 0)
return 0;
- /* info("%d: %2X %2X %2X %2X",dvb_usb_dib0700_ir_proto,(int)key[3-2],(int)key[3-3],(int)key[3-1],(int)key[3]); */
+ /* info("%d: %2X %2X %2X %2X",dvb_usb_dib0700_ir_proto,(int)st->buf[3 - 2],(int)st->buf[3 - 3],(int)st->buf[3 - 1],(int)st->buf[3]); */
dib0700_rc_setup(d, NULL); /* reset ir sensor data to prevent false events */
switch (d->props.rc.core.protocol) {
case RC_BIT_NEC:
/* NEC protocol sends repeat code as 0 0 0 FF */
- if ((key[3-2] == 0x00) && (key[3-3] == 0x00) &&
- (key[3] == 0xff)) {
+ if ((st->buf[3 - 2] == 0x00) && (st->buf[3 - 3] == 0x00) &&
+ (st->buf[3] == 0xff)) {
rc_repeat(d->rc_dev);
return 0;
}
protocol = RC_TYPE_NEC;
- scancode = RC_SCANCODE_NEC(key[3-2], key[3-3]);
+ scancode = RC_SCANCODE_NEC(st->buf[3 - 2], st->buf[3 - 3]);
toggle = 0;
break;
default:
/* RC-5 protocol changes toggle bit on new keypress */
protocol = RC_TYPE_RC5;
- scancode = RC_SCANCODE_RC5(key[3-2], key[3-3]);
- toggle = key[3-1];
+ scancode = RC_SCANCODE_RC5(st->buf[3 - 2], st->buf[3 - 3]);
+ toggle = st->buf[3 - 1];
break;
}
diff --git a/drivers/media/usb/dvb-usb/dibusb-common.c b/drivers/media/usb/dvb-usb/dibusb-common.c
index 18ed3bf..de3ee25 100644
--- a/drivers/media/usb/dvb-usb/dibusb-common.c
+++ b/drivers/media/usb/dvb-usb/dibusb-common.c
@@ -62,72 +62,117 @@ EXPORT_SYMBOL(dibusb_pid_filter_ctrl);
int dibusb_power_ctrl(struct dvb_usb_device *d, int onoff)
{
- u8 b[3];
+ u8 *b;
int ret;
+
+ b = kmalloc(3, GFP_KERNEL);
+ if (!b)
+ return -ENOMEM;
+
b[0] = DIBUSB_REQ_SET_IOCTL;
b[1] = DIBUSB_IOCTL_CMD_POWER_MODE;
b[2] = onoff ? DIBUSB_IOCTL_POWER_WAKEUP : DIBUSB_IOCTL_POWER_SLEEP;
- ret = dvb_usb_generic_write(d,b,3);
+
+ ret = dvb_usb_generic_write(d, b, 3);
+
+ kfree(b);
+
msleep(10);
+
return ret;
}
EXPORT_SYMBOL(dibusb_power_ctrl);
int dibusb2_0_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff)
{
- u8 b[3] = { 0 };
int ret;
+ u8 *b;
+
+ b = kmalloc(3, GFP_KERNEL);
+ if (!b)
+ return -ENOMEM;
if ((ret = dibusb_streaming_ctrl(adap,onoff)) < 0)
- return ret;
+ goto ret;
if (onoff) {
b[0] = DIBUSB_REQ_SET_STREAMING_MODE;
b[1] = 0x00;
- if ((ret = dvb_usb_generic_write(adap->dev,b,2)) < 0)
- return ret;
+ ret = dvb_usb_generic_write(adap->dev, b, 2);
+ if (ret < 0)
+ goto ret;
}
b[0] = DIBUSB_REQ_SET_IOCTL;
b[1] = onoff ? DIBUSB_IOCTL_CMD_ENABLE_STREAM : DIBUSB_IOCTL_CMD_DISABLE_STREAM;
- return dvb_usb_generic_write(adap->dev,b,3);
+ ret = dvb_usb_generic_write(adap->dev, b, 3);
+
+ret:
+ kfree(b);
+ return ret;
}
EXPORT_SYMBOL(dibusb2_0_streaming_ctrl);
int dibusb2_0_power_ctrl(struct dvb_usb_device *d, int onoff)
{
- if (onoff) {
- u8 b[3] = { DIBUSB_REQ_SET_IOCTL, DIBUSB_IOCTL_CMD_POWER_MODE, DIBUSB_IOCTL_POWER_WAKEUP };
- return dvb_usb_generic_write(d,b,3);
- } else
+ u8 *b;
+ int ret;
+
+ if (!onoff)
return 0;
+
+ b = kmalloc(3, GFP_KERNEL);
+ if (!b)
+ return -ENOMEM;
+
+ b[0] = DIBUSB_REQ_SET_IOCTL;
+ b[1] = DIBUSB_IOCTL_CMD_POWER_MODE;
+ b[2] = DIBUSB_IOCTL_POWER_WAKEUP;
+
+ ret = dvb_usb_generic_write(d, b, 3);
+
+ kfree(b);
+
+ return ret;
}
EXPORT_SYMBOL(dibusb2_0_power_ctrl);
static int dibusb_i2c_msg(struct dvb_usb_device *d, u8 addr,
u8 *wbuf, u16 wlen, u8 *rbuf, u16 rlen)
{
- u8 sndbuf[MAX_XFER_SIZE]; /* lead(1) devaddr,direction(1) addr(2) data(wlen) (len(2) (when reading)) */
- /* write only ? */
- int wo = (rbuf == NULL || rlen == 0),
- len = 2 + wlen + (wo ? 0 : 2);
+ u8 *sndbuf;
+ int ret, wo, len;
- if (4 + wlen > sizeof(sndbuf)) {
+ /* write only ? */
+ wo = (rbuf == NULL || rlen == 0);
+
+ len = 2 + wlen + (wo ? 0 : 2);
+
+ sndbuf = kmalloc(MAX_XFER_SIZE, GFP_KERNEL);
+ if (!sndbuf)
+ return -ENOMEM;
+
+ if (4 + wlen > MAX_XFER_SIZE) {
warn("i2c wr: len=%d is too big!\n", wlen);
- return -EOPNOTSUPP;
+ ret = -EOPNOTSUPP;
+ goto ret;
}
sndbuf[0] = wo ? DIBUSB_REQ_I2C_WRITE : DIBUSB_REQ_I2C_READ;
sndbuf[1] = (addr << 1) | (wo ? 0 : 1);
- memcpy(&sndbuf[2],wbuf,wlen);
+ memcpy(&sndbuf[2], wbuf, wlen);
if (!wo) {
- sndbuf[wlen+2] = (rlen >> 8) & 0xff;
- sndbuf[wlen+3] = rlen & 0xff;
+ sndbuf[wlen + 2] = (rlen >> 8) & 0xff;
+ sndbuf[wlen + 3] = rlen & 0xff;
}
- return dvb_usb_generic_rw(d,sndbuf,len,rbuf,rlen,0);
+ ret = dvb_usb_generic_rw(d, sndbuf, len, rbuf, rlen, 0);
+
+ret:
+ kfree(sndbuf);
+ return ret;
}
/*
@@ -319,11 +364,27 @@ EXPORT_SYMBOL(rc_map_dibusb_table);
int dibusb_rc_query(struct dvb_usb_device *d, u32 *event, int *state)
{
- u8 key[5],cmd = DIBUSB_REQ_POLL_REMOTE;
- dvb_usb_generic_rw(d,&cmd,1,key,5,0);
- dvb_usb_nec_rc_key_to_event(d,key,event,state);
- if (key[0] != 0)
- deb_info("key: %*ph\n", 5, key);
- return 0;
+ u8 *buf;
+ int ret;
+
+ buf = kmalloc(5, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ buf[0] = DIBUSB_REQ_POLL_REMOTE;
+
+ ret = dvb_usb_generic_rw(d, buf, 1, buf, 5, 0);
+ if (ret < 0)
+ goto ret;
+
+ dvb_usb_nec_rc_key_to_event(d, buf, event, state);
+
+ if (buf[0] != 0)
+ deb_info("key: %*ph\n", 5, buf);
+
+ kfree(buf);
+
+ret:
+ return ret;
}
EXPORT_SYMBOL(dibusb_rc_query);
diff --git a/drivers/media/usb/dvb-usb/dibusb.h b/drivers/media/usb/dvb-usb/dibusb.h
index 3f82163..697be2a 100644
--- a/drivers/media/usb/dvb-usb/dibusb.h
+++ b/drivers/media/usb/dvb-usb/dibusb.h
@@ -96,6 +96,9 @@
#define DIBUSB_IOCTL_CMD_ENABLE_STREAM 0x01
#define DIBUSB_IOCTL_CMD_DISABLE_STREAM 0x02
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
struct dibusb_state {
struct dib_fe_xfer_ops ops;
int mt2060_present;
diff --git a/drivers/media/usb/dvb-usb/digitv.c b/drivers/media/usb/dvb-usb/digitv.c
index 6313433..4284f69 100644
--- a/drivers/media/usb/dvb-usb/digitv.c
+++ b/drivers/media/usb/dvb-usb/digitv.c
@@ -28,22 +28,26 @@ DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
static int digitv_ctrl_msg(struct dvb_usb_device *d,
u8 cmd, u8 vv, u8 *wbuf, int wlen, u8 *rbuf, int rlen)
{
- int wo = (rbuf == NULL || rlen == 0); /* write-only */
- u8 sndbuf[7],rcvbuf[7];
- memset(sndbuf,0,7); memset(rcvbuf,0,7);
+ struct digitv_state *st = d->priv;
+ int ret, wo;
- sndbuf[0] = cmd;
- sndbuf[1] = vv;
- sndbuf[2] = wo ? wlen : rlen;
+ wo = (rbuf == NULL || rlen == 0); /* write-only */
+
+ memset(st->sndbuf, 0, 7);
+ memset(st->rcvbuf, 0, 7);
+
+ st->sndbuf[0] = cmd;
+ st->sndbuf[1] = vv;
+ st->sndbuf[2] = wo ? wlen : rlen;
if (wo) {
- memcpy(&sndbuf[3],wbuf,wlen);
- dvb_usb_generic_write(d,sndbuf,7);
+ memcpy(&st->sndbuf[3], wbuf, wlen);
+ ret = dvb_usb_generic_write(d, st->sndbuf, 7);
} else {
- dvb_usb_generic_rw(d,sndbuf,7,rcvbuf,7,10);
- memcpy(rbuf,&rcvbuf[3],rlen);
+ ret = dvb_usb_generic_rw(d, st->sndbuf, 7, st->rcvbuf, 7, 10);
+ memcpy(rbuf, &st->rcvbuf[3], rlen);
}
- return 0;
+ return ret;
}
/* I2C */
diff --git a/drivers/media/usb/dvb-usb/digitv.h b/drivers/media/usb/dvb-usb/digitv.h
index 908c09f..581e09c 100644
--- a/drivers/media/usb/dvb-usb/digitv.h
+++ b/drivers/media/usb/dvb-usb/digitv.h
@@ -5,7 +5,10 @@
#include "dvb-usb.h"
struct digitv_state {
- int is_nxt6000;
+ int is_nxt6000;
+
+ unsigned char sndbuf[7];
+ unsigned char rcvbuf[7];
};
/* protocol (from usblogging and the SDK:
diff --git a/drivers/media/usb/dvb-usb/dtt200u-fe.c b/drivers/media/usb/dvb-usb/dtt200u-fe.c
index c09332b..f5c042b 100644
--- a/drivers/media/usb/dvb-usb/dtt200u-fe.c
+++ b/drivers/media/usb/dvb-usb/dtt200u-fe.c
@@ -18,17 +18,28 @@ struct dtt200u_fe_state {
struct dtv_frontend_properties fep;
struct dvb_frontend frontend;
+
+ unsigned char data[80];
+ struct mutex data_mutex;
};
static int dtt200u_fe_read_status(struct dvb_frontend *fe,
enum fe_status *stat)
{
struct dtt200u_fe_state *state = fe->demodulator_priv;
- u8 st = GET_TUNE_STATUS, b[3];
+ int ret;
- dvb_usb_generic_rw(state->d,&st,1,b,3,0);
+ mutex_lock(&state->data_mutex);
+ state->data[0] = GET_TUNE_STATUS;
- switch (b[0]) {
+ ret = dvb_usb_generic_rw(state->d, state->data, 1, state->data, 3, 0);
+ if (ret < 0) {
+ *stat = 0;
+ mutex_unlock(&state->data_mutex);
+ return ret;
+ }
+
+ switch (state->data[0]) {
case 0x01:
*stat = FE_HAS_SIGNAL | FE_HAS_CARRIER |
FE_HAS_VITERBI | FE_HAS_SYNC | FE_HAS_LOCK;
@@ -41,51 +52,86 @@ static int dtt200u_fe_read_status(struct dvb_frontend *fe,
*stat = 0;
break;
}
+ mutex_unlock(&state->data_mutex);
return 0;
}
static int dtt200u_fe_read_ber(struct dvb_frontend* fe, u32 *ber)
{
struct dtt200u_fe_state *state = fe->demodulator_priv;
- u8 bw = GET_VIT_ERR_CNT,b[3];
- dvb_usb_generic_rw(state->d,&bw,1,b,3,0);
- *ber = (b[0] << 16) | (b[1] << 8) | b[2];
- return 0;
+ int ret;
+
+ mutex_lock(&state->data_mutex);
+ state->data[0] = GET_VIT_ERR_CNT;
+
+ ret = dvb_usb_generic_rw(state->d, state->data, 1, state->data, 3, 0);
+ if (ret >= 0)
+ *ber = (state->data[0] << 16) | (state->data[1] << 8) | state->data[2];
+
+ mutex_unlock(&state->data_mutex);
+ return ret;
}
static int dtt200u_fe_read_unc_blocks(struct dvb_frontend* fe, u32 *unc)
{
struct dtt200u_fe_state *state = fe->demodulator_priv;
- u8 bw = GET_RS_UNCOR_BLK_CNT,b[2];
+ int ret;
- dvb_usb_generic_rw(state->d,&bw,1,b,2,0);
- *unc = (b[0] << 8) | b[1];
- return 0;
+ mutex_lock(&state->data_mutex);
+ state->data[0] = GET_RS_UNCOR_BLK_CNT;
+
+ ret = dvb_usb_generic_rw(state->d, state->data, 1, state->data, 2, 0);
+ if (ret >= 0)
+ *unc = (state->data[0] << 8) | state->data[1];
+
+ mutex_unlock(&state->data_mutex);
+ return ret;
}
static int dtt200u_fe_read_signal_strength(struct dvb_frontend* fe, u16 *strength)
{
struct dtt200u_fe_state *state = fe->demodulator_priv;
- u8 bw = GET_AGC, b;
- dvb_usb_generic_rw(state->d,&bw,1,&b,1,0);
- *strength = (b << 8) | b;
- return 0;
+ int ret;
+
+ mutex_lock(&state->data_mutex);
+ state->data[0] = GET_AGC;
+
+ ret = dvb_usb_generic_rw(state->d, state->data, 1, state->data, 1, 0);
+ if (ret >= 0)
+ *strength = (state->data[0] << 8) | state->data[0];
+
+ mutex_unlock(&state->data_mutex);
+ return ret;
}
static int dtt200u_fe_read_snr(struct dvb_frontend* fe, u16 *snr)
{
struct dtt200u_fe_state *state = fe->demodulator_priv;
- u8 bw = GET_SNR,br;
- dvb_usb_generic_rw(state->d,&bw,1,&br,1,0);
- *snr = ~((br << 8) | br);
- return 0;
+ int ret;
+
+ mutex_lock(&state->data_mutex);
+ state->data[0] = GET_SNR;
+
+ ret = dvb_usb_generic_rw(state->d, state->data, 1, state->data, 1, 0);
+ if (ret >= 0)
+ *snr = ~((state->data[0] << 8) | state->data[0]);
+
+ mutex_unlock(&state->data_mutex);
+ return ret;
}
static int dtt200u_fe_init(struct dvb_frontend* fe)
{
struct dtt200u_fe_state *state = fe->demodulator_priv;
- u8 b = SET_INIT;
- return dvb_usb_generic_write(state->d,&b,1);
+ int ret;
+
+ mutex_lock(&state->data_mutex);
+ state->data[0] = SET_INIT;
+
+ ret = dvb_usb_generic_write(state->d, state->data, 1);
+ mutex_unlock(&state->data_mutex);
+
+ return ret;
}
static int dtt200u_fe_sleep(struct dvb_frontend* fe)
@@ -105,39 +151,40 @@ static int dtt200u_fe_set_frontend(struct dvb_frontend *fe)
{
struct dtv_frontend_properties *fep = &fe->dtv_property_cache;
struct dtt200u_fe_state *state = fe->demodulator_priv;
- int i;
- enum fe_status st;
+ int ret;
u16 freq = fep->frequency / 250000;
- u8 bwbuf[2] = { SET_BANDWIDTH, 0 },freqbuf[3] = { SET_RF_FREQ, 0, 0 };
+ mutex_lock(&state->data_mutex);
+ state->data[0] = SET_BANDWIDTH;
switch (fep->bandwidth_hz) {
case 8000000:
- bwbuf[1] = 8;
+ state->data[1] = 8;
break;
case 7000000:
- bwbuf[1] = 7;
+ state->data[1] = 7;
break;
case 6000000:
- bwbuf[1] = 6;
+ state->data[1] = 6;
break;
default:
- return -EINVAL;
+ ret = -EINVAL;
+ goto ret;
}
- dvb_usb_generic_write(state->d,bwbuf,2);
+ ret = dvb_usb_generic_write(state->d, state->data, 2);
+ if (ret < 0)
+ goto ret;
- freqbuf[1] = freq & 0xff;
- freqbuf[2] = (freq >> 8) & 0xff;
- dvb_usb_generic_write(state->d,freqbuf,3);
+ state->data[0] = SET_RF_FREQ;
+ state->data[1] = freq & 0xff;
+ state->data[2] = (freq >> 8) & 0xff;
+ ret = dvb_usb_generic_write(state->d, state->data, 3);
+ if (ret < 0)
+ goto ret;
- for (i = 0; i < 30; i++) {
- msleep(20);
- dtt200u_fe_read_status(fe, &st);
- if (st & FE_TIMEDOUT)
- continue;
- }
-
- return 0;
+ret:
+ mutex_unlock(&state->data_mutex);
+ return ret;
}
static int dtt200u_fe_get_frontend(struct dvb_frontend* fe,
@@ -169,6 +216,7 @@ struct dvb_frontend* dtt200u_fe_attach(struct dvb_usb_device *d)
deb_info("attaching frontend dtt200u\n");
state->d = d;
+ mutex_init(&state->data_mutex);
memcpy(&state->frontend.ops,&dtt200u_fe_ops,sizeof(struct dvb_frontend_ops));
state->frontend.demodulator_priv = state;
diff --git a/drivers/media/usb/dvb-usb/dtt200u.c b/drivers/media/usb/dvb-usb/dtt200u.c
index d2a01b5..fcbff7f 100644
--- a/drivers/media/usb/dvb-usb/dtt200u.c
+++ b/drivers/media/usb/dvb-usb/dtt200u.c
@@ -20,75 +20,115 @@ MODULE_PARM_DESC(debug, "set debugging level (1=info,xfer=2 (or-able))." DVB_USB
DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
+struct dtt200u_state {
+ unsigned char data[80];
+};
+
static int dtt200u_power_ctrl(struct dvb_usb_device *d, int onoff)
{
- u8 b = SET_INIT;
+ struct dtt200u_state *st = d->priv;
+ int ret = 0;
+
+ mutex_lock(&d->data_mutex);
+
+ st->data[0] = SET_INIT;
if (onoff)
- dvb_usb_generic_write(d,&b,2);
+ ret = dvb_usb_generic_write(d, st->data, 2);
- return 0;
+ mutex_unlock(&d->data_mutex);
+ return ret;
}
static int dtt200u_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff)
{
- u8 b_streaming[2] = { SET_STREAMING, onoff };
- u8 b_rst_pid = RESET_PID_FILTER;
+ struct dvb_usb_device *d = adap->dev;
+ struct dtt200u_state *st = d->priv;
+ int ret;
- dvb_usb_generic_write(adap->dev, b_streaming, 2);
+ mutex_lock(&d->data_mutex);
+ st->data[0] = SET_STREAMING;
+ st->data[1] = onoff;
- if (onoff == 0)
- dvb_usb_generic_write(adap->dev, &b_rst_pid, 1);
- return 0;
+ ret = dvb_usb_generic_write(adap->dev, st->data, 2);
+ if (ret < 0)
+ goto ret;
+
+ if (onoff)
+ goto ret;
+
+ st->data[0] = RESET_PID_FILTER;
+ ret = dvb_usb_generic_write(adap->dev, st->data, 1);
+
+ret:
+ mutex_unlock(&d->data_mutex);
+
+ return ret;
}
static int dtt200u_pid_filter(struct dvb_usb_adapter *adap, int index, u16 pid, int onoff)
{
- u8 b_pid[4];
+ struct dvb_usb_device *d = adap->dev;
+ struct dtt200u_state *st = d->priv;
+ int ret;
+
pid = onoff ? pid : 0;
- b_pid[0] = SET_PID_FILTER;
- b_pid[1] = index;
- b_pid[2] = pid & 0xff;
- b_pid[3] = (pid >> 8) & 0x1f;
+ mutex_lock(&d->data_mutex);
+ st->data[0] = SET_PID_FILTER;
+ st->data[1] = index;
+ st->data[2] = pid & 0xff;
+ st->data[3] = (pid >> 8) & 0x1f;
- return dvb_usb_generic_write(adap->dev, b_pid, 4);
+ ret = dvb_usb_generic_write(adap->dev, st->data, 4);
+ mutex_unlock(&d->data_mutex);
+
+ return ret;
}
static int dtt200u_rc_query(struct dvb_usb_device *d)
{
- u8 key[5],cmd = GET_RC_CODE;
+ struct dtt200u_state *st = d->priv;
u32 scancode;
+ int ret;
- dvb_usb_generic_rw(d,&cmd,1,key,5,0);
- if (key[0] == 1) {
+ mutex_lock(&d->data_mutex);
+ st->data[0] = GET_RC_CODE;
+
+ ret = dvb_usb_generic_rw(d, st->data, 1, st->data, 5, 0);
+ if (ret < 0)
+ goto ret;
+
+ if (st->data[0] == 1) {
enum rc_type proto = RC_TYPE_NEC;
- scancode = key[1];
- if ((u8) ~key[1] != key[2]) {
+ scancode = st->data[1];
+ if ((u8) ~st->data[1] != st->data[2]) {
/* Extended NEC */
scancode = scancode << 8;
- scancode |= key[2];
+ scancode |= st->data[2];
proto = RC_TYPE_NECX;
}
scancode = scancode << 8;
- scancode |= key[3];
+ scancode |= st->data[3];
/* Check command checksum is ok */
- if ((u8) ~key[3] == key[4])
+ if ((u8) ~st->data[3] == st->data[4])
rc_keydown(d->rc_dev, proto, scancode, 0);
else
rc_keyup(d->rc_dev);
- } else if (key[0] == 2) {
+ } else if (st->data[0] == 2) {
rc_repeat(d->rc_dev);
} else {
rc_keyup(d->rc_dev);
}
- if (key[0] != 0)
- deb_info("key: %*ph\n", 5, key);
+ if (st->data[0] != 0)
+ deb_info("st->data: %*ph\n", 5, st->data);
- return 0;
+ret:
+ mutex_unlock(&d->data_mutex);
+ return ret;
}
static int dtt200u_frontend_attach(struct dvb_usb_adapter *adap)
@@ -140,6 +180,8 @@ static struct dvb_usb_device_properties dtt200u_properties = {
.usb_ctrl = CYPRESS_FX2,
.firmware = "dvb-usb-dtt200u-01.fw",
+ .size_of_priv = sizeof(struct dtt200u_state),
+
.num_adapters = 1,
.adapter = {
{
@@ -190,6 +232,8 @@ static struct dvb_usb_device_properties wt220u_properties = {
.usb_ctrl = CYPRESS_FX2,
.firmware = "dvb-usb-wt220u-02.fw",
+ .size_of_priv = sizeof(struct dtt200u_state),
+
.num_adapters = 1,
.adapter = {
{
@@ -240,6 +284,8 @@ static struct dvb_usb_device_properties wt220u_fc_properties = {
.usb_ctrl = CYPRESS_FX2,
.firmware = "dvb-usb-wt220u-fc03.fw",
+ .size_of_priv = sizeof(struct dtt200u_state),
+
.num_adapters = 1,
.adapter = {
{
@@ -290,6 +336,8 @@ static struct dvb_usb_device_properties wt220u_zl0353_properties = {
.usb_ctrl = CYPRESS_FX2,
.firmware = "dvb-usb-wt220u-zl0353-01.fw",
+ .size_of_priv = sizeof(struct dtt200u_state),
+
.num_adapters = 1,
.adapter = {
{
@@ -340,6 +388,8 @@ static struct dvb_usb_device_properties wt220u_miglia_properties = {
.usb_ctrl = CYPRESS_FX2,
.firmware = "dvb-usb-wt220u-miglia-01.fw",
+ .size_of_priv = sizeof(struct dtt200u_state),
+
.num_adapters = 1,
.generic_bulk_ctrl_endpoint = 0x01,
diff --git a/drivers/media/usb/dvb-usb/dtv5100.c b/drivers/media/usb/dvb-usb/dtv5100.c
index 3d11df4..c60fb54 100644
--- a/drivers/media/usb/dvb-usb/dtv5100.c
+++ b/drivers/media/usb/dvb-usb/dtv5100.c
@@ -31,9 +31,14 @@ module_param_named(debug, dvb_usb_dtv5100_debug, int, 0644);
MODULE_PARM_DESC(debug, "set debugging level" DVB_USB_DEBUG_STATUS);
DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
+struct dtv5100_state {
+ unsigned char data[80];
+};
+
static int dtv5100_i2c_msg(struct dvb_usb_device *d, u8 addr,
u8 *wbuf, u16 wlen, u8 *rbuf, u16 rlen)
{
+ struct dtv5100_state *st = d->priv;
u8 request;
u8 type;
u16 value;
@@ -60,9 +65,10 @@ static int dtv5100_i2c_msg(struct dvb_usb_device *d, u8 addr,
}
index = (addr << 8) + wbuf[0];
+ memcpy(st->data, rbuf, rlen);
msleep(1); /* avoid I2C errors */
return usb_control_msg(d->udev, usb_rcvctrlpipe(d->udev, 0), request,
- type, value, index, rbuf, rlen,
+ type, value, index, st->data, rlen,
DTV5100_USB_TIMEOUT);
}
@@ -176,7 +182,7 @@ static struct dvb_usb_device_properties dtv5100_properties = {
.caps = DVB_USB_IS_AN_I2C_ADAPTER,
.usb_ctrl = DEVICE_SPECIFIC,
- .size_of_priv = 0,
+ .size_of_priv = sizeof(struct dtv5100_state),
.num_adapters = 1,
.adapter = {{
diff --git a/drivers/media/usb/dvb-usb/dvb-usb-init.c b/drivers/media/usb/dvb-usb/dvb-usb-init.c
index 3896ba9..8430856 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb-init.c
+++ b/drivers/media/usb/dvb-usb/dvb-usb-init.c
@@ -142,6 +142,7 @@ static int dvb_usb_init(struct dvb_usb_device *d, short *adapter_nums)
{
int ret = 0;
+ mutex_init(&d->data_mutex);
mutex_init(&d->usb_mutex);
mutex_init(&d->i2c_mutex);
diff --git a/drivers/media/usb/dvb-usb/dvb-usb.h b/drivers/media/usb/dvb-usb/dvb-usb.h
index 639c467..107255b 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb.h
+++ b/drivers/media/usb/dvb-usb/dvb-usb.h
@@ -404,8 +404,12 @@ struct dvb_usb_adapter {
* Powered is in/decremented for each call to modify the state.
* @udev: pointer to the device's struct usb_device.
*
- * @usb_mutex: semaphore of USB control messages (reading needs two messages)
- * @i2c_mutex: semaphore for i2c-transfers
+ * @data_mutex: mutex to protect the data structure used to store URB data
+ * @usb_mutex: mutex of USB control messages (reading needs two messages).
+ * Please notice that this mutex is used internally at the generic
+ * URB control functions. So, drivers using dvb_usb_generic_rw() and
+ * derivated functions should not lock it internally.
+ * @i2c_mutex: mutex for i2c-transfers
*
* @i2c_adap: device's i2c_adapter if it uses I2CoverUSB
*
@@ -433,6 +437,7 @@ struct dvb_usb_device {
int powered;
/* locking */
+ struct mutex data_mutex;
struct mutex usb_mutex;
/* i2c */
diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c
index 5fb0c65..2c720cb 100644
--- a/drivers/media/usb/dvb-usb/dw2102.c
+++ b/drivers/media/usb/dvb-usb/dw2102.c
@@ -852,7 +852,7 @@ static int su3000_power_ctrl(struct dvb_usb_device *d, int i)
if (i && !state->initialized) {
state->initialized = 1;
/* reset board */
- dvb_usb_generic_rw(d, obuf, 2, NULL, 0, 0);
+ return dvb_usb_generic_rw(d, obuf, 2, NULL, 0, 0);
}
return 0;
diff --git a/drivers/media/usb/dvb-usb/gp8psk.c b/drivers/media/usb/dvb-usb/gp8psk.c
index 5d0384d..993bb7a 100644
--- a/drivers/media/usb/dvb-usb/gp8psk.c
+++ b/drivers/media/usb/dvb-usb/gp8psk.c
@@ -15,6 +15,7 @@
* see Documentation/dvb/README.dvb-usb for more information
*/
#include "gp8psk.h"
+#include "gp8psk-fe.h"
/* debug */
static char bcm4500_firmware[] = "dvb-usb-gp8psk-02.fw";
@@ -24,14 +25,89 @@ MODULE_PARM_DESC(debug, "set debugging level (1=info,xfer=2,rc=4 (or-able))." DV
DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
+struct gp8psk_state {
+ unsigned char data[80];
+};
+
+static int gp8psk_usb_in_op(struct dvb_usb_device *d, u8 req, u16 value,
+ u16 index, u8 *b, int blen)
+{
+ struct gp8psk_state *st = d->priv;
+ int ret = 0,try = 0;
+
+ if (blen > sizeof(st->data))
+ return -EIO;
+
+ if ((ret = mutex_lock_interruptible(&d->usb_mutex)))
+ return ret;
+
+ while (ret >= 0 && ret != blen && try < 3) {
+ ret = usb_control_msg(d->udev,
+ usb_rcvctrlpipe(d->udev,0),
+ req,
+ USB_TYPE_VENDOR | USB_DIR_IN,
+ value, index, st->data, blen,
+ 2000);
+ deb_info("reading number %d (ret: %d)\n",try,ret);
+ try++;
+ }
+
+ if (ret < 0 || ret != blen) {
+ warn("usb in %d operation failed.", req);
+ ret = -EIO;
+ } else {
+ ret = 0;
+ memcpy(b, st->data, blen);
+ }
+
+ deb_xfer("in: req. %x, val: %x, ind: %x, buffer: ",req,value,index);
+ debug_dump(b,blen,deb_xfer);
+
+ mutex_unlock(&d->usb_mutex);
+
+ return ret;
+}
+
+static int gp8psk_usb_out_op(struct dvb_usb_device *d, u8 req, u16 value,
+ u16 index, u8 *b, int blen)
+{
+ struct gp8psk_state *st = d->priv;
+ int ret;
+
+ deb_xfer("out: req. %x, val: %x, ind: %x, buffer: ",req,value,index);
+ debug_dump(b,blen,deb_xfer);
+
+ if (blen > sizeof(st->data))
+ return -EIO;
+
+ if ((ret = mutex_lock_interruptible(&d->usb_mutex)))
+ return ret;
+
+ memcpy(st->data, b, blen);
+ if (usb_control_msg(d->udev,
+ usb_sndctrlpipe(d->udev,0),
+ req,
+ USB_TYPE_VENDOR | USB_DIR_OUT,
+ value, index, st->data, blen,
+ 2000) != blen) {
+ warn("usb out operation failed.");
+ ret = -EIO;
+ } else
+ ret = 0;
+ mutex_unlock(&d->usb_mutex);
+
+ return ret;
+}
+
+
static int gp8psk_get_fw_version(struct dvb_usb_device *d, u8 *fw_vers)
{
- return (gp8psk_usb_in_op(d, GET_FW_VERS, 0, 0, fw_vers, 6));
+ return gp8psk_usb_in_op(d, GET_FW_VERS, 0, 0, fw_vers, 6);
}
static int gp8psk_get_fpga_version(struct dvb_usb_device *d, u8 *fpga_vers)
{
- return (gp8psk_usb_in_op(d, GET_FPGA_VERS, 0, 0, fpga_vers, 1));
+ return gp8psk_usb_in_op(d, GET_FPGA_VERS, 0, 0, fpga_vers, 1);
}
static void gp8psk_info(struct dvb_usb_device *d)
@@ -51,64 +127,6 @@ static void gp8psk_info(struct dvb_usb_device *d)
info("failed to get FPGA version");
}
-int gp8psk_usb_in_op(struct dvb_usb_device *d, u8 req, u16 value, u16 index, u8 *b, int blen)
-{
- int ret = 0,try = 0;
-
- if ((ret = mutex_lock_interruptible(&d->usb_mutex)))
- return ret;
-
- while (ret >= 0 && ret != blen && try < 3) {
- ret = usb_control_msg(d->udev,
- usb_rcvctrlpipe(d->udev,0),
- req,
- USB_TYPE_VENDOR | USB_DIR_IN,
- value,index,b,blen,
- 2000);
- deb_info("reading number %d (ret: %d)\n",try,ret);
- try++;
- }
-
- if (ret < 0 || ret != blen) {
- warn("usb in %d operation failed.", req);
- ret = -EIO;
- } else
- ret = 0;
-
- deb_xfer("in: req. %x, val: %x, ind: %x, buffer: ",req,value,index);
- debug_dump(b,blen,deb_xfer);
-
- mutex_unlock(&d->usb_mutex);
-
- return ret;
-}
-
-int gp8psk_usb_out_op(struct dvb_usb_device *d, u8 req, u16 value,
- u16 index, u8 *b, int blen)
-{
- int ret;
-
- deb_xfer("out: req. %x, val: %x, ind: %x, buffer: ",req,value,index);
- debug_dump(b,blen,deb_xfer);
-
- if ((ret = mutex_lock_interruptible(&d->usb_mutex)))
- return ret;
-
- if (usb_control_msg(d->udev,
- usb_sndctrlpipe(d->udev,0),
- req,
- USB_TYPE_VENDOR | USB_DIR_OUT,
- value,index,b,blen,
- 2000) != blen) {
- warn("usb out operation failed.");
- ret = -EIO;
- } else
- ret = 0;
- mutex_unlock(&d->usb_mutex);
-
- return ret;
-}
-
static int gp8psk_load_bcm4500fw(struct dvb_usb_device *d)
{
int ret;
@@ -143,6 +161,11 @@ static int gp8psk_load_bcm4500fw(struct dvb_usb_device *d)
err("failed to load bcm4500 firmware.");
goto out_free;
}
+ if (buflen > 64) {
+ err("firmare chunk size bigger than 64 bytes.");
+ goto out_free;
+ }
+
memcpy(buf, ptr, buflen);
if (dvb_usb_generic_write(d, buf, buflen)) {
err("failed to load bcm4500 firmware.");
@@ -206,10 +229,13 @@ static int gp8psk_power_ctrl(struct dvb_usb_device *d, int onoff)
return 0;
}
-int gp8psk_bcm4500_reload(struct dvb_usb_device *d)
+static int gp8psk_bcm4500_reload(struct dvb_usb_device *d)
{
u8 buf;
int gp_product_id = le16_to_cpu(d->udev->descriptor.idProduct);
+
+ deb_xfer("reloading firmware\n");
+
/* Turn off 8psk power */
if (gp8psk_usb_in_op(d, BOOT_8PSK, 0, 0, &buf, 1))
return -EINVAL;
@@ -228,9 +254,47 @@ static int gp8psk_streaming_ctrl(struct dvb_usb_adapter *adap, int onoff)
return gp8psk_usb_out_op(adap->dev, ARM_TRANSFER, onoff, 0 , NULL, 0);
}
+/* Callbacks for gp8psk-fe.c */
+
+static int gp8psk_fe_in(void *priv, u8 req, u16 value,
+ u16 index, u8 *b, int blen)
+{
+ struct dvb_usb_device *d = priv;
+
+ return gp8psk_usb_in_op(d, req, value, index, b, blen);
+}
+
+static int gp8psk_fe_out(void *priv, u8 req, u16 value,
+ u16 index, u8 *b, int blen)
+{
+ struct dvb_usb_device *d = priv;
+
+ return gp8psk_usb_out_op(d, req, value, index, b, blen);
+}
+
+static int gp8psk_fe_reload(void *priv)
+{
+ struct dvb_usb_device *d = priv;
+
+ return gp8psk_bcm4500_reload(d);
+}
+
+const struct gp8psk_fe_ops gp8psk_fe_ops = {
+ .in = gp8psk_fe_in,
+ .out = gp8psk_fe_out,
+ .reload = gp8psk_fe_reload,
+};
+
static int gp8psk_frontend_attach(struct dvb_usb_adapter *adap)
{
- adap->fe_adap[0].fe = gp8psk_fe_attach(adap->dev);
+ struct dvb_usb_device *d = adap->dev;
+ int id = le16_to_cpu(d->udev->descriptor.idProduct);
+ int is_rev1;
+
+ is_rev1 = (id == USB_PID_GENPIX_8PSK_REV_1_WARM) ? true : false;
+
+ adap->fe_adap[0].fe = dvb_attach(gp8psk_fe_attach,
+ &gp8psk_fe_ops, d, is_rev1);
return 0;
}
@@ -265,6 +329,8 @@ static struct dvb_usb_device_properties gp8psk_properties = {
.usb_ctrl = CYPRESS_FX2,
.firmware = "dvb-usb-gp8psk-01.fw",
+ .size_of_priv = sizeof(struct gp8psk_state),
+
.num_adapters = 1,
.adapter = {
{
diff --git a/drivers/media/usb/dvb-usb/gp8psk.h b/drivers/media/usb/dvb-usb/gp8psk.h
index ed32b9d..d8975b8 100644
--- a/drivers/media/usb/dvb-usb/gp8psk.h
+++ b/drivers/media/usb/dvb-usb/gp8psk.h
@@ -24,58 +24,6 @@ extern int dvb_usb_gp8psk_debug;
#define deb_info(args...) dprintk(dvb_usb_gp8psk_debug,0x01,args)
#define deb_xfer(args...) dprintk(dvb_usb_gp8psk_debug,0x02,args)
#define deb_rc(args...) dprintk(dvb_usb_gp8psk_debug,0x04,args)
-#define deb_fe(args...) dprintk(dvb_usb_gp8psk_debug,0x08,args)
-
-/* Twinhan Vendor requests */
-#define TH_COMMAND_IN 0xC0
-#define TH_COMMAND_OUT 0xC1
-
-/* gp8psk commands */
-
-#define GET_8PSK_CONFIG 0x80 /* in */
-#define SET_8PSK_CONFIG 0x81
-#define I2C_WRITE 0x83
-#define I2C_READ 0x84
-#define ARM_TRANSFER 0x85
-#define TUNE_8PSK 0x86
-#define GET_SIGNAL_STRENGTH 0x87 /* in */
-#define LOAD_BCM4500 0x88
-#define BOOT_8PSK 0x89 /* in */
-#define START_INTERSIL 0x8A /* in */
-#define SET_LNB_VOLTAGE 0x8B
-#define SET_22KHZ_TONE 0x8C
-#define SEND_DISEQC_COMMAND 0x8D
-#define SET_DVB_MODE 0x8E
-#define SET_DN_SWITCH 0x8F
-#define GET_SIGNAL_LOCK 0x90 /* in */
-#define GET_FW_VERS 0x92
-#define GET_SERIAL_NUMBER 0x93 /* in */
-#define USE_EXTRA_VOLT 0x94
-#define GET_FPGA_VERS 0x95
-#define CW3K_INIT 0x9d
-
-/* PSK_configuration bits */
-#define bm8pskStarted 0x01
-#define bm8pskFW_Loaded 0x02
-#define bmIntersilOn 0x04
-#define bmDVBmode 0x08
-#define bm22kHz 0x10
-#define bmSEL18V 0x20
-#define bmDCtuned 0x40
-#define bmArmed 0x80
-
-/* Satellite modulation modes */
-#define ADV_MOD_DVB_QPSK 0 /* DVB-S QPSK */
-#define ADV_MOD_TURBO_QPSK 1 /* Turbo QPSK */
-#define ADV_MOD_TURBO_8PSK 2 /* Turbo 8PSK (also used for Trellis 8PSK) */
-#define ADV_MOD_TURBO_16QAM 3 /* Turbo 16QAM (also used for Trellis 8PSK) */
-
-#define ADV_MOD_DCII_C_QPSK 4 /* Digicipher II Combo */
-#define ADV_MOD_DCII_I_QPSK 5 /* Digicipher II I-stream */
-#define ADV_MOD_DCII_Q_QPSK 6 /* Digicipher II Q-stream */
-#define ADV_MOD_DCII_C_OQPSK 7 /* Digicipher II offset QPSK */
-#define ADV_MOD_DSS_QPSK 8 /* DSS (DIRECTV) QPSK */
-#define ADV_MOD_DVB_BPSK 9 /* DVB-S BPSK */
#define GET_USB_SPEED 0x07
@@ -86,15 +34,4 @@ extern int dvb_usb_gp8psk_debug;
#define PRODUCT_STRING_READ 0x0D
#define FW_BCD_VERSION_READ 0x14
-/* firmware revision id's */
-#define GP8PSK_FW_REV1 0x020604
-#define GP8PSK_FW_REV2 0x020704
-#define GP8PSK_FW_VERS(_fw_vers) ((_fw_vers)[2]<<0x10 | (_fw_vers)[1]<<0x08 | (_fw_vers)[0])
-
-extern struct dvb_frontend * gp8psk_fe_attach(struct dvb_usb_device *d);
-extern int gp8psk_usb_in_op(struct dvb_usb_device *d, u8 req, u16 value, u16 index, u8 *b, int blen);
-extern int gp8psk_usb_out_op(struct dvb_usb_device *d, u8 req, u16 value,
- u16 index, u8 *b, int blen);
-extern int gp8psk_bcm4500_reload(struct dvb_usb_device *d);
-
#endif
diff --git a/drivers/media/usb/dvb-usb/nova-t-usb2.c b/drivers/media/usb/dvb-usb/nova-t-usb2.c
index fc7569e..1babd33 100644
--- a/drivers/media/usb/dvb-usb/nova-t-usb2.c
+++ b/drivers/media/usb/dvb-usb/nova-t-usb2.c
@@ -74,22 +74,31 @@ static struct rc_map_table rc_map_haupp_table[] = {
*/
static int nova_t_rc_query(struct dvb_usb_device *d, u32 *event, int *state)
{
- u8 key[5],cmd[2] = { DIBUSB_REQ_POLL_REMOTE, 0x35 }, data,toggle,custom;
+ u8 *buf, data, toggle, custom;
u16 raw;
- int i;
+ int i, ret;
struct dibusb_device_state *st = d->priv;
- dvb_usb_generic_rw(d,cmd,2,key,5,0);
+ buf = kmalloc(5, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ buf[0] = DIBUSB_REQ_POLL_REMOTE;
+ buf[1] = 0x35;
+ ret = dvb_usb_generic_rw(d, buf, 2, buf, 5, 0);
+ if (ret < 0)
+ goto ret;
*state = REMOTE_NO_KEY_PRESSED;
- switch (key[0]) {
+ switch (buf[0]) {
case DIBUSB_RC_HAUPPAUGE_KEY_PRESSED:
- raw = ((key[1] << 8) | key[2]) >> 3;
+ raw = ((buf[1] << 8) | buf[2]) >> 3;
toggle = !!(raw & 0x800);
data = raw & 0x3f;
custom = (raw >> 6) & 0x1f;
- deb_rc("raw key code 0x%02x, 0x%02x, 0x%02x to c: %02x d: %02x toggle: %d\n",key[1],key[2],key[3],custom,data,toggle);
+ deb_rc("raw key code 0x%02x, 0x%02x, 0x%02x to c: %02x d: %02x toggle: %d\n",
+ buf[1], buf[2], buf[3], custom, data, toggle);
for (i = 0; i < ARRAY_SIZE(rc_map_haupp_table); i++) {
if (rc5_data(&rc_map_haupp_table[i]) == data &&
@@ -117,7 +126,9 @@ static int nova_t_rc_query(struct dvb_usb_device *d, u32 *event, int *state)
break;
}
- return 0;
+ret:
+ kfree(buf);
+ return ret;
}
static int nova_t_read_mac_address (struct dvb_usb_device *d, u8 mac[6])
diff --git a/drivers/media/usb/dvb-usb/pctv452e.c b/drivers/media/usb/dvb-usb/pctv452e.c
index c05de1b..07fa08b 100644
--- a/drivers/media/usb/dvb-usb/pctv452e.c
+++ b/drivers/media/usb/dvb-usb/pctv452e.c
@@ -97,48 +97,53 @@ struct pctv452e_state {
u8 c; /* transaction counter, wraps around... */
u8 initialized; /* set to 1 if 0x15 has been sent */
u16 last_rc_key;
+
+ unsigned char data[80];
};
static int tt3650_ci_msg(struct dvb_usb_device *d, u8 cmd, u8 *data,
unsigned int write_len, unsigned int read_len)
{
struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
- u8 buf[64];
u8 id;
unsigned int rlen;
int ret;
- BUG_ON(NULL == data && 0 != (write_len | read_len));
- BUG_ON(write_len > 64 - 4);
- BUG_ON(read_len > 64 - 4);
+ if (!data || (write_len > 64 - 4) || (read_len > 64 - 4)) {
+ err("%s: transfer data invalid", __func__);
+ return -EIO;
+ }
+ mutex_lock(&state->ca_mutex);
id = state->c++;
- buf[0] = SYNC_BYTE_OUT;
- buf[1] = id;
- buf[2] = cmd;
- buf[3] = write_len;
+ state->data[0] = SYNC_BYTE_OUT;
+ state->data[1] = id;
+ state->data[2] = cmd;
+ state->data[3] = write_len;
- memcpy(buf + 4, data, write_len);
+ memcpy(state->data + 4, data, write_len);
rlen = (read_len > 0) ? 64 : 0;
- ret = dvb_usb_generic_rw(d, buf, 4 + write_len,
- buf, rlen, /* delay_ms */ 0);
+ ret = dvb_usb_generic_rw(d, state->data, 4 + write_len,
+ state->data, rlen, /* delay_ms */ 0);
if (0 != ret)
goto failed;
ret = -EIO;
- if (SYNC_BYTE_IN != buf[0] || id != buf[1])
+ if (SYNC_BYTE_IN != state->data[0] || id != state->data[1])
goto failed;
- memcpy(data, buf + 4, read_len);
+ memcpy(data, state->data + 4, read_len);
+ mutex_unlock(&state->ca_mutex);
return 0;
failed:
err("CI error %d; %02X %02X %02X -> %*ph.",
- ret, SYNC_BYTE_OUT, id, cmd, 3, buf);
+ ret, SYNC_BYTE_OUT, id, cmd, 3, state->data);
+ mutex_unlock(&state->ca_mutex);
return ret;
}
@@ -405,52 +410,53 @@ static int pctv452e_i2c_msg(struct dvb_usb_device *d, u8 addr,
u8 *rcv_buf, u8 rcv_len)
{
struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
- u8 buf[64];
u8 id;
int ret;
+ mutex_lock(&state->ca_mutex);
id = state->c++;
ret = -EINVAL;
if (snd_len > 64 - 7 || rcv_len > 64 - 7)
goto failed;
- buf[0] = SYNC_BYTE_OUT;
- buf[1] = id;
- buf[2] = PCTV_CMD_I2C;
- buf[3] = snd_len + 3;
- buf[4] = addr << 1;
- buf[5] = snd_len;
- buf[6] = rcv_len;
+ state->data[0] = SYNC_BYTE_OUT;
+ state->data[1] = id;
+ state->data[2] = PCTV_CMD_I2C;
+ state->data[3] = snd_len + 3;
+ state->data[4] = addr << 1;
+ state->data[5] = snd_len;
+ state->data[6] = rcv_len;
- memcpy(buf + 7, snd_buf, snd_len);
+ memcpy(state->data + 7, snd_buf, snd_len);
- ret = dvb_usb_generic_rw(d, buf, 7 + snd_len,
- buf, /* rcv_len */ 64,
+ ret = dvb_usb_generic_rw(d, state->data, 7 + snd_len,
+ state->data, /* rcv_len */ 64,
/* delay_ms */ 0);
if (ret < 0)
goto failed;
/* TT USB protocol error. */
ret = -EIO;
- if (SYNC_BYTE_IN != buf[0] || id != buf[1])
+ if (SYNC_BYTE_IN != state->data[0] || id != state->data[1])
goto failed;
/* I2C device didn't respond as expected. */
ret = -EREMOTEIO;
- if (buf[5] < snd_len || buf[6] < rcv_len)
+ if (state->data[5] < snd_len || state->data[6] < rcv_len)
goto failed;
- memcpy(rcv_buf, buf + 7, rcv_len);
+ memcpy(rcv_buf, state->data + 7, rcv_len);
+ mutex_unlock(&state->ca_mutex);
return rcv_len;
failed:
- err("I2C error %d; %02X %02X %02X %02X %02X -> "
- "%02X %02X %02X %02X %02X.",
+ err("I2C error %d; %02X %02X %02X %02X %02X -> %*ph",
ret, SYNC_BYTE_OUT, id, addr << 1, snd_len, rcv_len,
- buf[0], buf[1], buf[4], buf[5], buf[6]);
+ 7, state->data);
+ mutex_unlock(&state->ca_mutex);
return ret;
}
@@ -499,8 +505,7 @@ static u32 pctv452e_i2c_func(struct i2c_adapter *adapter)
static int pctv452e_power_ctrl(struct dvb_usb_device *d, int i)
{
struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
- u8 b0[] = { 0xaa, 0, PCTV_CMD_RESET, 1, 0 };
- u8 rx[PCTV_ANSWER_LEN];
+ u8 *rx;
int ret;
info("%s: %d\n", __func__, i);
@@ -511,6 +516,11 @@ static int pctv452e_power_ctrl(struct dvb_usb_device *d, int i)
if (state->initialized)
return 0;
+ rx = kmalloc(PCTV_ANSWER_LEN, GFP_KERNEL);
+ if (!rx)
+ return -ENOMEM;
+
+ mutex_lock(&state->ca_mutex);
/* hmm where shoud this should go? */
ret = usb_set_interface(d->udev, 0, ISOC_INTERFACE_ALTERNATIVE);
if (ret != 0)
@@ -518,65 +528,75 @@ static int pctv452e_power_ctrl(struct dvb_usb_device *d, int i)
__func__, ret);
/* this is a one-time initialization, dont know where to put */
- b0[1] = state->c++;
+ state->data[0] = 0xaa;
+ state->data[1] = state->c++;
+ state->data[2] = PCTV_CMD_RESET;
+ state->data[3] = 1;
+ state->data[4] = 0;
/* reset board */
- ret = dvb_usb_generic_rw(d, b0, sizeof(b0), rx, PCTV_ANSWER_LEN, 0);
+ ret = dvb_usb_generic_rw(d, state->data, 5, rx, PCTV_ANSWER_LEN, 0);
if (ret)
- return ret;
+ goto ret;
- b0[1] = state->c++;
- b0[4] = 1;
+ state->data[1] = state->c++;
+ state->data[4] = 1;
/* reset board (again?) */
- ret = dvb_usb_generic_rw(d, b0, sizeof(b0), rx, PCTV_ANSWER_LEN, 0);
+ ret = dvb_usb_generic_rw(d, state->data, 5, rx, PCTV_ANSWER_LEN, 0);
if (ret)
- return ret;
+ goto ret;
state->initialized = 1;
- return 0;
+ret:
+ mutex_unlock(&state->ca_mutex);
+ kfree(rx);
+ return ret;
}
static int pctv452e_rc_query(struct dvb_usb_device *d)
{
struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
- u8 b[CMD_BUFFER_SIZE];
- u8 rx[PCTV_ANSWER_LEN];
int ret, i;
- u8 id = state->c++;
+ u8 id;
+
+ mutex_lock(&state->ca_mutex);
+ id = state->c++;
/* prepare command header */
- b[0] = SYNC_BYTE_OUT;
- b[1] = id;
- b[2] = PCTV_CMD_IR;
- b[3] = 0;
+ state->data[0] = SYNC_BYTE_OUT;
+ state->data[1] = id;
+ state->data[2] = PCTV_CMD_IR;
+ state->data[3] = 0;
/* send ir request */
- ret = dvb_usb_generic_rw(d, b, 4, rx, PCTV_ANSWER_LEN, 0);
+ ret = dvb_usb_generic_rw(d, state->data, 4,
+ state->data, PCTV_ANSWER_LEN, 0);
if (ret != 0)
- return ret;
+ goto ret;
if (debug > 3) {
- info("%s: read: %2d: %*ph: ", __func__, ret, 3, rx);
- for (i = 0; (i < rx[3]) && ((i+3) < PCTV_ANSWER_LEN); i++)
- info(" %02x", rx[i+3]);
+ info("%s: read: %2d: %*ph: ", __func__, ret, 3, state->data);
+ for (i = 0; (i < state->data[3]) && ((i + 3) < PCTV_ANSWER_LEN); i++)
+ info(" %02x", state->data[i + 3]);
info("\n");
}
- if ((rx[3] == 9) && (rx[12] & 0x01)) {
+ if ((state->data[3] == 9) && (state->data[12] & 0x01)) {
/* got a "press" event */
- state->last_rc_key = RC_SCANCODE_RC5(rx[7], rx[6]);
+ state->last_rc_key = RC_SCANCODE_RC5(state->data[7], state->data[6]);
if (debug > 2)
info("%s: cmd=0x%02x sys=0x%02x\n",
- __func__, rx[6], rx[7]);
+ __func__, state->data[6], state->data[7]);
rc_keydown(d->rc_dev, RC_TYPE_RC5, state->last_rc_key, 0);
} else if (state->last_rc_key) {
rc_keyup(d->rc_dev);
state->last_rc_key = 0;
}
-
- return 0;
+ret:
+ mutex_unlock(&state->ca_mutex);
+ return ret;
}
static int pctv452e_read_mac_address(struct dvb_usb_device *d, u8 mac[6])
diff --git a/drivers/media/usb/dvb-usb/technisat-usb2.c b/drivers/media/usb/dvb-usb/technisat-usb2.c
index d9f3262..4706628 100644
--- a/drivers/media/usb/dvb-usb/technisat-usb2.c
+++ b/drivers/media/usb/dvb-usb/technisat-usb2.c
@@ -89,9 +89,13 @@ struct technisat_usb2_state {
static int technisat_usb2_i2c_access(struct usb_device *udev,
u8 device_addr, u8 *tx, u8 txlen, u8 *rx, u8 rxlen)
{
- u8 b[64];
+ u8 *b;
int ret, actual_length;
+ b = kmalloc(64, GFP_KERNEL);
+ if (!b)
+ return -ENOMEM;
+
deb_i2c("i2c-access: %02x, tx: ", device_addr);
debug_dump(tx, txlen, deb_i2c);
deb_i2c(" ");
@@ -123,7 +127,7 @@ static int technisat_usb2_i2c_access(struct usb_device *udev,
if (ret < 0) {
err("i2c-error: out failed %02x = %d", device_addr, ret);
- return -ENODEV;
+ goto err;
}
ret = usb_bulk_msg(udev,
@@ -131,7 +135,7 @@ static int technisat_usb2_i2c_access(struct usb_device *udev,
b, 64, &actual_length, 1000);
if (ret < 0) {
err("i2c-error: in failed %02x = %d", device_addr, ret);
- return -ENODEV;
+ goto err;
}
if (b[0] != I2C_STATUS_OK) {
@@ -140,7 +144,7 @@ static int technisat_usb2_i2c_access(struct usb_device *udev,
if (!(b[0] == I2C_STATUS_NAK &&
device_addr == 0x60
/* && device_is_technisat_usb2 */))
- return -ENODEV;
+ goto err;
}
deb_i2c("status: %d, ", b[0]);
@@ -154,7 +158,9 @@ static int technisat_usb2_i2c_access(struct usb_device *udev,
deb_i2c("\n");
- return 0;
+err:
+ kfree(b);
+ return ret;
}
static int technisat_usb2_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msg,
diff --git a/drivers/media/usb/s2255/s2255drv.c b/drivers/media/usb/s2255/s2255drv.c
index c3a0e87..f7bb78c 100644
--- a/drivers/media/usb/s2255/s2255drv.c
+++ b/drivers/media/usb/s2255/s2255drv.c
@@ -1901,19 +1901,30 @@ static long s2255_vendor_req(struct s2255_dev *dev, unsigned char Request,
s32 TransferBufferLength, int bOut)
{
int r;
+ unsigned char *buf;
+
+ buf = kmalloc(TransferBufferLength, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
if (!bOut) {
r = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
Request,
USB_TYPE_VENDOR | USB_RECIP_DEVICE |
USB_DIR_IN,
- Value, Index, TransferBuffer,
+ Value, Index, buf,
TransferBufferLength, HZ * 5);
+
+ if (r >= 0)
+ memcpy(TransferBuffer, buf, TransferBufferLength);
} else {
+ memcpy(buf, TransferBuffer, TransferBufferLength);
r = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
Request, USB_TYPE_VENDOR | USB_RECIP_DEVICE,
- Value, Index, TransferBuffer,
+ Value, Index, buf,
TransferBufferLength, HZ * 5);
}
+ kfree(buf);
return r;
}
diff --git a/drivers/media/usb/stkwebcam/stk-webcam.c b/drivers/media/usb/stkwebcam/stk-webcam.c
index db200c9..22a9aae 100644
--- a/drivers/media/usb/stkwebcam/stk-webcam.c
+++ b/drivers/media/usb/stkwebcam/stk-webcam.c
@@ -147,20 +147,26 @@ int stk_camera_write_reg(struct stk_camera *dev, u16 index, u8 value)
int stk_camera_read_reg(struct stk_camera *dev, u16 index, int *value)
{
struct usb_device *udev = dev->udev;
+ unsigned char *buf;
int ret;
+ buf = kmalloc(sizeof(u8), GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
0x00,
USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
0x00,
index,
- (u8 *) value,
+ buf,
sizeof(u8),
500);
- if (ret < 0)
- return ret;
- else
- return 0;
+ if (ret >= 0)
+ memcpy(value, buf, sizeof(u8));
+
+ kfree(buf);
+ return ret;
}
static int stk_start_stream(struct stk_camera *dev)
diff --git a/drivers/media/v4l2-core/Kconfig b/drivers/media/v4l2-core/Kconfig
index 29b3436..367523a 100644
--- a/drivers/media/v4l2-core/Kconfig
+++ b/drivers/media/v4l2-core/Kconfig
@@ -27,7 +27,7 @@
config VIDEO_PCI_SKELETON
tristate "Skeleton PCI V4L2 driver"
- depends on PCI && BUILD_DOCSRC
+ depends on PCI
depends on VIDEO_V4L2 && VIDEOBUF2_CORE
depends on VIDEOBUF2_MEMOPS && VIDEOBUF2_DMA_CONTIG
---help---
diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index f300f06..1db0af6 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -156,6 +156,7 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
{
unsigned long first, last;
int err, rw = 0;
+ unsigned int flags = FOLL_FORCE;
dma->direction = direction;
switch (dma->direction) {
@@ -178,12 +179,14 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
if (NULL == dma->pages)
return -ENOMEM;
+ if (rw == READ)
+ flags |= FOLL_WRITE;
+
dprintk(1, "init user [0x%lx+0x%lx => %d pages]\n",
data, size, dma->nr_pages);
err = get_user_pages(data & PAGE_MASK, dma->nr_pages,
- rw == READ, 1, /* force */
- dma->pages, NULL);
+ flags, dma->pages, NULL);
if (err != dma->nr_pages) {
dma->nr_pages = (err >= 0) ? err : 0;
diff --git a/drivers/media/v4l2-core/videobuf2-memops.c b/drivers/media/v4l2-core/videobuf2-memops.c
index 3c3b517..1cd322e 100644
--- a/drivers/media/v4l2-core/videobuf2-memops.c
+++ b/drivers/media/v4l2-core/videobuf2-memops.c
@@ -42,6 +42,10 @@ struct frame_vector *vb2_create_framevec(unsigned long start,
unsigned long first, last;
unsigned long nr;
struct frame_vector *vec;
+ unsigned int flags = FOLL_FORCE;
+
+ if (write)
+ flags |= FOLL_WRITE;
first = start >> PAGE_SHIFT;
last = (start + length - 1) >> PAGE_SHIFT;
@@ -49,7 +53,7 @@ struct frame_vector *vb2_create_framevec(unsigned long start,
vec = frame_vector_create(nr);
if (!vec)
return ERR_PTR(-ENOMEM);
- ret = get_vaddr_frames(start & PAGE_MASK, nr, write, true, vec);
+ ret = get_vaddr_frames(start & PAGE_MASK, nr, flags, vec);
if (ret < 0)
goto out_destroy;
/* We accept only complete set of PFNs */
diff --git a/drivers/memstick/host/rtsx_usb_ms.c b/drivers/memstick/host/rtsx_usb_ms.c
index d34bc35..2e3cf01 100644
--- a/drivers/memstick/host/rtsx_usb_ms.c
+++ b/drivers/memstick/host/rtsx_usb_ms.c
@@ -524,6 +524,7 @@ static void rtsx_usb_ms_handle_req(struct work_struct *work)
int rc;
if (!host->req) {
+ pm_runtime_get_sync(ms_dev(host));
do {
rc = memstick_next_req(msh, &host->req);
dev_dbg(ms_dev(host), "next req %d\n", rc);
@@ -544,6 +545,7 @@ static void rtsx_usb_ms_handle_req(struct work_struct *work)
host->req->error);
}
} while (!rc);
+ pm_runtime_put(ms_dev(host));
}
}
@@ -570,6 +572,7 @@ static int rtsx_usb_ms_set_param(struct memstick_host *msh,
dev_dbg(ms_dev(host), "%s: param = %d, value = %d\n",
__func__, param, value);
+ pm_runtime_get_sync(ms_dev(host));
mutex_lock(&ucr->dev_mutex);
err = rtsx_usb_card_exclusive_check(ucr, RTSX_USB_MS_CARD);
@@ -635,6 +638,7 @@ static int rtsx_usb_ms_set_param(struct memstick_host *msh,
}
out:
mutex_unlock(&ucr->dev_mutex);
+ pm_runtime_put(ms_dev(host));
/* power-on delay */
if (param == MEMSTICK_POWER && value == MEMSTICK_POWER_ON)
@@ -681,6 +685,7 @@ static int rtsx_usb_detect_ms_card(void *__host)
int err;
for (;;) {
+ pm_runtime_get_sync(ms_dev(host));
mutex_lock(&ucr->dev_mutex);
/* Check pending MS card changes */
@@ -703,6 +708,7 @@ static int rtsx_usb_detect_ms_card(void *__host)
}
poll_again:
+ pm_runtime_put(ms_dev(host));
if (host->eject)
break;
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index f3d34b9..2e5233b 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -229,6 +229,14 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed,
if (ctx->status == STARTED)
goto out; /* already started */
+ /*
+ * Increment the mapped context count for adapter. This also checks
+ * if adapter_context_lock is taken.
+ */
+ rc = cxl_adapter_context_get(ctx->afu->adapter);
+ if (rc)
+ goto out;
+
if (task) {
ctx->pid = get_task_pid(task, PIDTYPE_PID);
ctx->glpid = get_task_pid(task->group_leader, PIDTYPE_PID);
@@ -239,7 +247,10 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed,
cxl_ctx_get();
if ((rc = cxl_ops->attach_process(ctx, kernel, wed, 0))) {
+ put_pid(ctx->glpid);
put_pid(ctx->pid);
+ ctx->glpid = ctx->pid = NULL;
+ cxl_adapter_context_put(ctx->afu->adapter);
cxl_ctx_put();
goto out;
}
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index c466ee2..5e506c1 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -238,6 +238,9 @@ int __detach_context(struct cxl_context *ctx)
put_pid(ctx->glpid);
cxl_ctx_put();
+
+ /* Decrease the attached context count on the adapter */
+ cxl_adapter_context_put(ctx->afu->adapter);
return 0;
}
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 01d372a..a144073 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -618,6 +618,14 @@ struct cxl {
bool perst_select_user;
bool perst_same_image;
bool psl_timebase_synced;
+
+ /*
+ * number of contexts mapped on to this card. Possible values are:
+ * >0: Number of contexts mapped and new one can be mapped.
+ * 0: No active contexts and new ones can be mapped.
+ * -1: No contexts mapped and new ones cannot be mapped.
+ */
+ atomic_t contexts_num;
};
int cxl_pci_alloc_one_irq(struct cxl *adapter);
@@ -944,4 +952,20 @@ bool cxl_pci_is_vphb_device(struct pci_dev *dev);
/* decode AFU error bits in the PSL register PSL_SERR_An */
void cxl_afu_decode_psl_serr(struct cxl_afu *afu, u64 serr);
+
+/*
+ * Increments the number of attached contexts on an adapter.
+ * In case an adapter_context_lock is taken the return -EBUSY.
+ */
+int cxl_adapter_context_get(struct cxl *adapter);
+
+/* Decrements the number of attached contexts on an adapter */
+void cxl_adapter_context_put(struct cxl *adapter);
+
+/* If no active contexts then prevents contexts from being attached */
+int cxl_adapter_context_lock(struct cxl *adapter);
+
+/* Unlock the contexts-lock if taken. Warn and force unlock otherwise */
+void cxl_adapter_context_unlock(struct cxl *adapter);
+
#endif
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index 5fb9894..77080cc 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -194,6 +194,16 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
ctx->mmio_err_ff = !!(work.flags & CXL_START_WORK_ERR_FF);
/*
+ * Increment the mapped context count for adapter. This also checks
+ * if adapter_context_lock is taken.
+ */
+ rc = cxl_adapter_context_get(ctx->afu->adapter);
+ if (rc) {
+ afu_release_irqs(ctx, ctx);
+ goto out;
+ }
+
+ /*
* We grab the PID here and not in the file open to allow for the case
* where a process (master, some daemon, etc) has opened the chardev on
* behalf of another process, so the AFU's mm gets bound to the process
@@ -205,11 +215,16 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
ctx->pid = get_task_pid(current, PIDTYPE_PID);
ctx->glpid = get_task_pid(current->group_leader, PIDTYPE_PID);
+
trace_cxl_attach(ctx, work.work_element_descriptor, work.num_interrupts, amr);
if ((rc = cxl_ops->attach_process(ctx, false, work.work_element_descriptor,
amr))) {
afu_release_irqs(ctx, ctx);
+ cxl_adapter_context_put(ctx->afu->adapter);
+ put_pid(ctx->glpid);
+ put_pid(ctx->pid);
+ ctx->glpid = ctx->pid = NULL;
goto out;
}
diff --git a/drivers/misc/cxl/guest.c b/drivers/misc/cxl/guest.c
index 9aa58a7..3e102cd 100644
--- a/drivers/misc/cxl/guest.c
+++ b/drivers/misc/cxl/guest.c
@@ -1152,6 +1152,9 @@ struct cxl *cxl_guest_init_adapter(struct device_node *np, struct platform_devic
if ((rc = cxl_sysfs_adapter_add(adapter)))
goto err_put1;
+ /* release the context lock as the adapter is configured */
+ cxl_adapter_context_unlock(adapter);
+
return adapter;
err_put1:
diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c
index d9be23b2..62e0dfb 100644
--- a/drivers/misc/cxl/main.c
+++ b/drivers/misc/cxl/main.c
@@ -243,8 +243,10 @@ struct cxl *cxl_alloc_adapter(void)
if (dev_set_name(&adapter->dev, "card%i", adapter->adapter_num))
goto err2;
- return adapter;
+ /* start with context lock taken */
+ atomic_set(&adapter->contexts_num, -1);
+ return adapter;
err2:
cxl_remove_adapter_nr(adapter);
err1:
@@ -286,6 +288,44 @@ int cxl_afu_select_best_mode(struct cxl_afu *afu)
return 0;
}
+int cxl_adapter_context_get(struct cxl *adapter)
+{
+ int rc;
+
+ rc = atomic_inc_unless_negative(&adapter->contexts_num);
+ return rc >= 0 ? 0 : -EBUSY;
+}
+
+void cxl_adapter_context_put(struct cxl *adapter)
+{
+ atomic_dec_if_positive(&adapter->contexts_num);
+}
+
+int cxl_adapter_context_lock(struct cxl *adapter)
+{
+ int rc;
+ /* no active contexts -> contexts_num == 0 */
+ rc = atomic_cmpxchg(&adapter->contexts_num, 0, -1);
+ return rc ? -EBUSY : 0;
+}
+
+void cxl_adapter_context_unlock(struct cxl *adapter)
+{
+ int val = atomic_cmpxchg(&adapter->contexts_num, -1, 0);
+
+ /*
+ * contexts lock taken -> contexts_num == -1
+ * If not true then show a warning and force reset the lock.
+ * This will happen when context_unlock was requested without
+ * doing a context_lock.
+ */
+ if (val != -1) {
+ atomic_set(&adapter->contexts_num, 0);
+ WARN(1, "Adapter context unlocked with %d active contexts",
+ val);
+ }
+}
+
static int __init init_cxl(void)
{
int rc = 0;
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 7afad84..e96be9c 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -1487,6 +1487,8 @@ static int cxl_configure_adapter(struct cxl *adapter, struct pci_dev *dev)
if ((rc = cxl_native_register_psl_err_irq(adapter)))
goto err;
+ /* Release the context lock as adapter is configured */
+ cxl_adapter_context_unlock(adapter);
return 0;
err:
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index b043c20..a8b6d6a 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/drivers/misc/cxl/sysfs.c
@@ -75,12 +75,31 @@ static ssize_t reset_adapter_store(struct device *device,
int val;
rc = sscanf(buf, "%i", &val);
- if ((rc != 1) || (val != 1))
+ if ((rc != 1) || (val != 1 && val != -1))
return -EINVAL;
- if ((rc = cxl_ops->adapter_reset(adapter)))
- return rc;
- return count;
+ /*
+ * See if we can lock the context mapping that's only allowed
+ * when there are no contexts attached to the adapter. Once
+ * taken this will also prevent any context from getting activated.
+ */
+ if (val == 1) {
+ rc = cxl_adapter_context_lock(adapter);
+ if (rc)
+ goto out;
+
+ rc = cxl_ops->adapter_reset(adapter);
+ /* In case reset failed release context lock */
+ if (rc)
+ cxl_adapter_context_unlock(adapter);
+
+ } else if (val == -1) {
+ /* Perform a forced adapter reset */
+ rc = cxl_ops->adapter_reset(adapter);
+ }
+
+out:
+ return rc ? rc : count;
}
static ssize_t load_image_on_perst_show(struct device *device,
diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
index 8a679ec..fc2794b 100644
--- a/drivers/misc/genwqe/card_utils.c
+++ b/drivers/misc/genwqe/card_utils.c
@@ -352,17 +352,27 @@ int genwqe_alloc_sync_sgl(struct genwqe_dev *cd, struct genwqe_sgl *sgl,
if (copy_from_user(sgl->lpage, user_addr + user_size -
sgl->lpage_size, sgl->lpage_size)) {
rc = -EFAULT;
- goto err_out1;
+ goto err_out2;
}
}
return 0;
+ err_out2:
+ __genwqe_free_consistent(cd, PAGE_SIZE, sgl->lpage,
+ sgl->lpage_dma_addr);
+ sgl->lpage = NULL;
+ sgl->lpage_dma_addr = 0;
err_out1:
__genwqe_free_consistent(cd, PAGE_SIZE, sgl->fpage,
sgl->fpage_dma_addr);
+ sgl->fpage = NULL;
+ sgl->fpage_dma_addr = 0;
err_out:
__genwqe_free_consistent(cd, sgl->sgl_size, sgl->sgl,
sgl->sgl_dma_addr);
+ sgl->sgl = NULL;
+ sgl->sgl_dma_addr = 0;
+ sgl->sgl_size = 0;
return -ENOMEM;
}
diff --git a/drivers/misc/mei/bus-fixup.c b/drivers/misc/mei/bus-fixup.c
index e9e6ea3..75b9d4a 100644
--- a/drivers/misc/mei/bus-fixup.c
+++ b/drivers/misc/mei/bus-fixup.c
@@ -178,7 +178,7 @@ static int mei_nfc_if_version(struct mei_cl *cl,
ret = 0;
bytes_recv = __mei_cl_recv(cl, (u8 *)reply, if_version_length);
- if (bytes_recv < 0 || bytes_recv < sizeof(struct mei_nfc_reply)) {
+ if (bytes_recv < if_version_length) {
dev_err(bus->dev, "Could not read IF version\n");
ret = -EIO;
goto err;
diff --git a/drivers/misc/mei/hw-txe.c b/drivers/misc/mei/hw-txe.c
index e6e5e55..60415a2 100644
--- a/drivers/misc/mei/hw-txe.c
+++ b/drivers/misc/mei/hw-txe.c
@@ -981,11 +981,13 @@ static bool mei_txe_check_and_ack_intrs(struct mei_device *dev, bool do_ack)
hisr = mei_txe_br_reg_read(hw, HISR_REG);
aliveness = mei_txe_aliveness_get(dev);
- if (hhisr & IPC_HHIER_SEC && aliveness)
+ if (hhisr & IPC_HHIER_SEC && aliveness) {
ipc_isr = mei_txe_sec_reg_read_silent(hw,
SEC_IPC_HOST_INT_STATUS_REG);
- else
+ } else {
ipc_isr = 0;
+ hhisr &= ~IPC_HHIER_SEC;
+ }
generated = generated ||
(hisr & HISR_INT_STS_MSK) ||
diff --git a/drivers/misc/mic/scif/scif_rma.c b/drivers/misc/mic/scif/scif_rma.c
index e0203b1..f806a44 100644
--- a/drivers/misc/mic/scif/scif_rma.c
+++ b/drivers/misc/mic/scif/scif_rma.c
@@ -1396,8 +1396,7 @@ int __scif_pin_pages(void *addr, size_t len, int *out_prot,
pinned_pages->nr_pages = get_user_pages(
(u64)addr,
nr_pages,
- !!(prot & SCIF_PROT_WRITE),
- 0,
+ (prot & SCIF_PROT_WRITE) ? FOLL_WRITE : 0,
pinned_pages->pages,
NULL);
up_write(&mm->mmap_sem);
diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c
index a2d97b9..6fb773d 100644
--- a/drivers/misc/sgi-gru/grufault.c
+++ b/drivers/misc/sgi-gru/grufault.c
@@ -198,7 +198,7 @@ static int non_atomic_pte_lookup(struct vm_area_struct *vma,
#else
*pageshift = PAGE_SHIFT;
#endif
- if (get_user_pages(vaddr, 1, write, 0, &page, NULL) <= 0)
+ if (get_user_pages(vaddr, 1, write ? FOLL_WRITE : 0, &page, NULL) <= 0)
return -EFAULT;
*paddr = page_to_phys(page);
put_page(page);
diff --git a/drivers/misc/sgi-gru/grumain.c b/drivers/misc/sgi-gru/grumain.c
index 1525870..33741ad 100644
--- a/drivers/misc/sgi-gru/grumain.c
+++ b/drivers/misc/sgi-gru/grumain.c
@@ -283,7 +283,7 @@ static void gru_unload_mm_tracker(struct gru_state *gru,
spin_lock(&gru->gs_asid_lock);
BUG_ON((asids->mt_ctxbitmap & ctxbitmap) != ctxbitmap);
asids->mt_ctxbitmap ^= ctxbitmap;
- gru_dbg(grudev, "gid %d, gts %p, gms %p, ctxnum 0x%d, asidmap 0x%lx\n",
+ gru_dbg(grudev, "gid %d, gts %p, gms %p, ctxnum %d, asidmap 0x%lx\n",
gru->gs_gid, gts, gms, gts->ts_ctxnum, gms->ms_asidmap[0]);
spin_unlock(&gru->gs_asid_lock);
spin_unlock(&gms->ms_asid_lock);
diff --git a/drivers/misc/vmw_vmci/vmci_doorbell.c b/drivers/misc/vmw_vmci/vmci_doorbell.c
index a8cee33..b3fa738 100644
--- a/drivers/misc/vmw_vmci/vmci_doorbell.c
+++ b/drivers/misc/vmw_vmci/vmci_doorbell.c
@@ -431,6 +431,12 @@ int vmci_doorbell_create(struct vmci_handle *handle,
if (vmci_handle_is_invalid(*handle)) {
u32 context_id = vmci_get_context_id();
+ if (context_id == VMCI_INVALID_ID) {
+ pr_warn("Failed to get context ID\n");
+ result = VMCI_ERROR_NO_RESOURCES;
+ goto free_mem;
+ }
+
/* Let resource code allocate a free ID for us */
new_handle = vmci_make_handle(context_id, VMCI_INVALID_ID);
} else {
@@ -525,7 +531,7 @@ int vmci_doorbell_destroy(struct vmci_handle handle)
entry = container_of(resource, struct dbell_entry, resource);
- if (vmci_guest_code_active()) {
+ if (!hlist_unhashed(&entry->node)) {
int result;
dbell_index_table_remove(entry);
diff --git a/drivers/misc/vmw_vmci/vmci_driver.c b/drivers/misc/vmw_vmci/vmci_driver.c
index 896be15..d7eaf1e 100644
--- a/drivers/misc/vmw_vmci/vmci_driver.c
+++ b/drivers/misc/vmw_vmci/vmci_driver.c
@@ -113,5 +113,5 @@ module_exit(vmci_drv_exit);
MODULE_AUTHOR("VMware, Inc.");
MODULE_DESCRIPTION("VMware Virtual Machine Communication Interface.");
-MODULE_VERSION("1.1.4.0-k");
+MODULE_VERSION("1.1.5.0-k");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index c333511..709a872 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -46,6 +46,7 @@
#include <asm/uaccess.h>
#include "queue.h"
+#include "block.h"
MODULE_ALIAS("mmc:block");
#ifdef MODULE_PARAM_PREFIX
@@ -1786,7 +1787,7 @@ static void mmc_blk_packed_hdr_wrq_prep(struct mmc_queue_req *mqrq,
struct mmc_blk_data *md = mq->data;
struct mmc_packed *packed = mqrq->packed;
bool do_rel_wr, do_data_tag;
- u32 *packed_cmd_hdr;
+ __le32 *packed_cmd_hdr;
u8 hdr_blocks;
u8 i = 1;
diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c
index 5a8dc5a..3678220 100644
--- a/drivers/mmc/card/mmc_test.c
+++ b/drivers/mmc/card/mmc_test.c
@@ -2347,7 +2347,7 @@ static int mmc_test_ongoing_transfer(struct mmc_test_card *test,
struct mmc_test_req *rq = mmc_test_req_alloc();
struct mmc_host *host = test->card->host;
struct mmc_test_area *t = &test->area;
- struct mmc_async_req areq;
+ struct mmc_test_async_req test_areq = { .test = test };
struct mmc_request *mrq;
unsigned long timeout;
bool expired = false;
@@ -2363,8 +2363,8 @@ static int mmc_test_ongoing_transfer(struct mmc_test_card *test,
mrq->sbc = &rq->sbc;
mrq->cap_cmd_during_tfr = true;
- areq.mrq = mrq;
- areq.err_check = mmc_test_check_result_async;
+ test_areq.areq.mrq = mrq;
+ test_areq.areq.err_check = mmc_test_check_result_async;
mmc_test_prepare_mrq(test, mrq, t->sg, t->sg_len, dev_addr, t->blocks,
512, write);
@@ -2378,7 +2378,7 @@ static int mmc_test_ongoing_transfer(struct mmc_test_card *test,
/* Start ongoing data request */
if (use_areq) {
- mmc_start_req(host, &areq, &ret);
+ mmc_start_req(host, &test_areq.areq, &ret);
if (ret)
goto out_free;
} else {
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index 3c15a75..342f1e3 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -31,7 +31,7 @@ enum mmc_packed_type {
struct mmc_packed {
struct list_head list;
- u32 cmd_hdr[1024];
+ __le32 cmd_hdr[1024];
unsigned int blocks;
u8 nr_entries;
u8 retries;
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 3486bc7..df19777 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -26,6 +26,8 @@
#include "mmc_ops.h"
#include "sd_ops.h"
+#define DEFAULT_CMD6_TIMEOUT_MS 500
+
static const unsigned int tran_exp[] = {
10000, 100000, 1000000, 10000000,
0, 0, 0, 0
@@ -571,6 +573,7 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
card->erased_byte = 0x0;
/* eMMC v4.5 or later */
+ card->ext_csd.generic_cmd6_time = DEFAULT_CMD6_TIMEOUT_MS;
if (card->ext_csd.rev >= 6) {
card->ext_csd.feature_support |= MMC_DISCARD_FEATURE;
@@ -1263,6 +1266,16 @@ static int mmc_select_hs400es(struct mmc_card *card)
goto out_err;
}
+ if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS400_1_2V)
+ err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120);
+
+ if (err && card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS400_1_8V)
+ err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180);
+
+ /* If fails try again during next card power cycle */
+ if (err)
+ goto out_err;
+
err = mmc_select_bus_width(card);
if (err < 0)
goto out_err;
@@ -1272,6 +1285,8 @@ static int mmc_select_hs400es(struct mmc_card *card)
if (err)
goto out_err;
+ mmc_set_clock(host, card->ext_csd.hs_max_dtr);
+
err = mmc_switch_status(card);
if (err)
goto out_err;
diff --git a/drivers/mmc/host/dw_mmc-pltfm.c b/drivers/mmc/host/dw_mmc-pltfm.c
index c0bb0c7..dbbc430 100644
--- a/drivers/mmc/host/dw_mmc-pltfm.c
+++ b/drivers/mmc/host/dw_mmc-pltfm.c
@@ -46,12 +46,13 @@ int dw_mci_pltfm_register(struct platform_device *pdev,
host->pdata = pdev->dev.platform_data;
regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- /* Get registers' physical base address */
- host->phy_regs = regs->start;
host->regs = devm_ioremap_resource(&pdev->dev, regs);
if (IS_ERR(host->regs))
return PTR_ERR(host->regs);
+ /* Get registers' physical base address */
+ host->phy_regs = regs->start;
+
platform_set_drvdata(pdev, host);
return dw_mci_probe(host);
}
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 4fcbc40..50a674b 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -2940,7 +2940,7 @@ static struct dw_mci_board *dw_mci_parse_dt(struct dw_mci *host)
return ERR_PTR(-ENOMEM);
/* find reset controller when exist */
- pdata->rstc = devm_reset_control_get_optional(dev, NULL);
+ pdata->rstc = devm_reset_control_get_optional(dev, "reset");
if (IS_ERR(pdata->rstc)) {
if (PTR_ERR(pdata->rstc) == -EPROBE_DEFER)
return ERR_PTR(-EPROBE_DEFER);
diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c
index d839147..44ecebd 100644
--- a/drivers/mmc/host/mxs-mmc.c
+++ b/drivers/mmc/host/mxs-mmc.c
@@ -661,13 +661,13 @@ static int mxs_mmc_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, mmc);
+ spin_lock_init(&host->lock);
+
ret = devm_request_irq(&pdev->dev, irq_err, mxs_mmc_irq_handler, 0,
dev_name(&pdev->dev), host);
if (ret)
goto out_free_dma;
- spin_lock_init(&host->lock);
-
ret = mmc_add_host(mmc);
if (ret)
goto out_free_dma;
diff --git a/drivers/mmc/host/rtsx_usb_sdmmc.c b/drivers/mmc/host/rtsx_usb_sdmmc.c
index 4106295..6e9c0f8 100644
--- a/drivers/mmc/host/rtsx_usb_sdmmc.c
+++ b/drivers/mmc/host/rtsx_usb_sdmmc.c
@@ -1138,11 +1138,6 @@ static void sdmmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
dev_dbg(sdmmc_dev(host), "%s\n", __func__);
mutex_lock(&ucr->dev_mutex);
- if (rtsx_usb_card_exclusive_check(ucr, RTSX_USB_SD_CARD)) {
- mutex_unlock(&ucr->dev_mutex);
- return;
- }
-
sd_set_power_mode(host, ios->power_mode);
sd_set_bus_width(host, ios->bus_width);
sd_set_timing(host, ios->timing, &host->ddr_mode);
@@ -1314,6 +1309,7 @@ static void rtsx_usb_update_led(struct work_struct *work)
container_of(work, struct rtsx_usb_sdmmc, led_work);
struct rtsx_ucr *ucr = host->ucr;
+ pm_runtime_get_sync(sdmmc_dev(host));
mutex_lock(&ucr->dev_mutex);
if (host->led.brightness == LED_OFF)
@@ -1322,6 +1318,7 @@ static void rtsx_usb_update_led(struct work_struct *work)
rtsx_usb_turn_on_led(ucr);
mutex_unlock(&ucr->dev_mutex);
+ pm_runtime_put(sdmmc_dev(host));
}
#endif
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 1f54fd8..7123ef9 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -346,7 +346,8 @@ static void esdhc_writel_le(struct sdhci_host *host, u32 val, int reg)
struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host);
u32 data;
- if (unlikely(reg == SDHCI_INT_ENABLE || reg == SDHCI_SIGNAL_ENABLE)) {
+ if (unlikely(reg == SDHCI_INT_ENABLE || reg == SDHCI_SIGNAL_ENABLE ||
+ reg == SDHCI_INT_STATUS)) {
if ((val & SDHCI_INT_CARD_INT) && !esdhc_is_usdhc(imx_data)) {
/*
* Clear and then set D3CD bit to avoid missing the
@@ -555,6 +556,25 @@ static void esdhc_writew_le(struct sdhci_host *host, u16 val, int reg)
esdhc_clrset_le(host, 0xffff, val, reg);
}
+static u8 esdhc_readb_le(struct sdhci_host *host, int reg)
+{
+ u8 ret;
+ u32 val;
+
+ switch (reg) {
+ case SDHCI_HOST_CONTROL:
+ val = readl(host->ioaddr + reg);
+
+ ret = val & SDHCI_CTRL_LED;
+ ret |= (val >> 5) & SDHCI_CTRL_DMA_MASK;
+ ret |= (val & ESDHC_CTRL_4BITBUS);
+ ret |= (val & ESDHC_CTRL_8BITBUS) << 3;
+ return ret;
+ }
+
+ return readb(host->ioaddr + reg);
+}
+
static void esdhc_writeb_le(struct sdhci_host *host, u8 val, int reg)
{
struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
@@ -947,6 +967,7 @@ static void esdhc_set_timeout(struct sdhci_host *host, struct mmc_command *cmd)
static struct sdhci_ops sdhci_esdhc_ops = {
.read_l = esdhc_readl_le,
.read_w = esdhc_readw_le,
+ .read_b = esdhc_readb_le,
.write_l = esdhc_writel_le,
.write_w = esdhc_writew_le,
.write_b = esdhc_writeb_le,
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 8ef44a2a..90ed2e1 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -647,6 +647,7 @@ static int sdhci_msm_probe(struct platform_device *pdev)
if (msm_host->pwr_irq < 0) {
dev_err(&pdev->dev, "Get pwr_irq failed (%d)\n",
msm_host->pwr_irq);
+ ret = msm_host->pwr_irq;
goto clk_disable;
}
diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c
index da8e40a..410a55b 100644
--- a/drivers/mmc/host/sdhci-of-arasan.c
+++ b/drivers/mmc/host/sdhci-of-arasan.c
@@ -250,7 +250,7 @@ static void sdhci_arasan_hs400_enhanced_strobe(struct mmc_host *mmc,
writel(vendor, host->ioaddr + SDHCI_ARASAN_VENDOR_REGISTER);
}
-void sdhci_arasan_reset(struct sdhci_host *host, u8 mask)
+static void sdhci_arasan_reset(struct sdhci_host *host, u8 mask)
{
u8 ctrl;
struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
@@ -265,6 +265,28 @@ void sdhci_arasan_reset(struct sdhci_host *host, u8 mask)
}
}
+static int sdhci_arasan_voltage_switch(struct mmc_host *mmc,
+ struct mmc_ios *ios)
+{
+ switch (ios->signal_voltage) {
+ case MMC_SIGNAL_VOLTAGE_180:
+ /*
+ * Plese don't switch to 1V8 as arasan,5.1 doesn't
+ * actually refer to this setting to indicate the
+ * signal voltage and the state machine will be broken
+ * actually if we force to enable 1V8. That's something
+ * like broken quirk but we could work around here.
+ */
+ return 0;
+ case MMC_SIGNAL_VOLTAGE_330:
+ case MMC_SIGNAL_VOLTAGE_120:
+ /* We don't support 3V3 and 1V2 */
+ break;
+ }
+
+ return -EINVAL;
+}
+
static struct sdhci_ops sdhci_arasan_ops = {
.set_clock = sdhci_arasan_set_clock,
.get_max_clock = sdhci_pltfm_clk_get_max_clock,
@@ -661,6 +683,8 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
host->mmc_host_ops.hs400_enhanced_strobe =
sdhci_arasan_hs400_enhanced_strobe;
+ host->mmc_host_ops.start_signal_voltage_switch =
+ sdhci_arasan_voltage_switch;
}
ret = sdhci_add_host(host);
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 72a1f1f..1d9e00a 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -32,6 +32,14 @@
#include "sdhci-pci.h"
#include "sdhci-pci-o2micro.h"
+static int sdhci_pci_enable_dma(struct sdhci_host *host);
+static void sdhci_pci_set_bus_width(struct sdhci_host *host, int width);
+static void sdhci_pci_hw_reset(struct sdhci_host *host);
+static int sdhci_pci_select_drive_strength(struct sdhci_host *host,
+ struct mmc_card *card,
+ unsigned int max_dtr, int host_drv,
+ int card_drv, int *drv_type);
+
/*****************************************************************************\
* *
* Hardware specific quirk handling *
@@ -390,6 +398,45 @@ static int byt_sd_probe_slot(struct sdhci_pci_slot *slot)
return 0;
}
+#define SDHCI_INTEL_PWR_TIMEOUT_CNT 20
+#define SDHCI_INTEL_PWR_TIMEOUT_UDELAY 100
+
+static void sdhci_intel_set_power(struct sdhci_host *host, unsigned char mode,
+ unsigned short vdd)
+{
+ int cntr;
+ u8 reg;
+
+ sdhci_set_power(host, mode, vdd);
+
+ if (mode == MMC_POWER_OFF)
+ return;
+
+ /*
+ * Bus power might not enable after D3 -> D0 transition due to the
+ * present state not yet having propagated. Retry for up to 2ms.
+ */
+ for (cntr = 0; cntr < SDHCI_INTEL_PWR_TIMEOUT_CNT; cntr++) {
+ reg = sdhci_readb(host, SDHCI_POWER_CONTROL);
+ if (reg & SDHCI_POWER_ON)
+ break;
+ udelay(SDHCI_INTEL_PWR_TIMEOUT_UDELAY);
+ reg |= SDHCI_POWER_ON;
+ sdhci_writeb(host, reg, SDHCI_POWER_CONTROL);
+ }
+}
+
+static const struct sdhci_ops sdhci_intel_byt_ops = {
+ .set_clock = sdhci_set_clock,
+ .set_power = sdhci_intel_set_power,
+ .enable_dma = sdhci_pci_enable_dma,
+ .set_bus_width = sdhci_pci_set_bus_width,
+ .reset = sdhci_reset,
+ .set_uhs_signaling = sdhci_set_uhs_signaling,
+ .hw_reset = sdhci_pci_hw_reset,
+ .select_drive_strength = sdhci_pci_select_drive_strength,
+};
+
static const struct sdhci_pci_fixes sdhci_intel_byt_emmc = {
.allow_runtime_pm = true,
.probe_slot = byt_emmc_probe_slot,
@@ -397,6 +444,7 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_emmc = {
.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400 |
SDHCI_QUIRK2_STOP_WITH_TC,
+ .ops = &sdhci_intel_byt_ops,
};
static const struct sdhci_pci_fixes sdhci_intel_byt_sdio = {
@@ -405,6 +453,7 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_sdio = {
SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
.allow_runtime_pm = true,
.probe_slot = byt_sdio_probe_slot,
+ .ops = &sdhci_intel_byt_ops,
};
static const struct sdhci_pci_fixes sdhci_intel_byt_sd = {
@@ -415,6 +464,7 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_sd = {
.allow_runtime_pm = true,
.own_cd_for_runtime_pm = true,
.probe_slot = byt_sd_probe_slot,
+ .ops = &sdhci_intel_byt_ops,
};
/* Define Host controllers for Intel Merrifield platform */
@@ -1648,7 +1698,9 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot(
}
host->hw_name = "PCI";
- host->ops = &sdhci_pci_ops;
+ host->ops = chip->fixes && chip->fixes->ops ?
+ chip->fixes->ops :
+ &sdhci_pci_ops;
host->quirks = chip->quirks;
host->quirks2 = chip->quirks2;
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index 9c7c08b..6bccf56 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -65,6 +65,8 @@ struct sdhci_pci_fixes {
int (*suspend) (struct sdhci_pci_chip *);
int (*resume) (struct sdhci_pci_chip *);
+
+ const struct sdhci_ops *ops;
};
struct sdhci_pci_slot {
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index dd1938d..d0f5c05 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -315,7 +315,7 @@ static void pxav3_set_power(struct sdhci_host *host, unsigned char mode,
struct mmc_host *mmc = host->mmc;
u8 pwr = host->pwr;
- sdhci_set_power(host, mode, vdd);
+ sdhci_set_power_noreg(host, mode, vdd);
if (host->pwr == pwr)
return;
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 4805566..42ef3eb 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -687,7 +687,7 @@ static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd)
* host->clock is in Hz. target_timeout is in us.
* Hence, us = 1000000 * cycles / Hz. Round up.
*/
- val = 1000000 * data->timeout_clks;
+ val = 1000000ULL * data->timeout_clks;
if (do_div(val, host->clock))
target_timeout++;
target_timeout += val;
@@ -1077,6 +1077,10 @@ void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd)
/* Initially, a command has no error */
cmd->error = 0;
+ if ((host->quirks2 & SDHCI_QUIRK2_STOP_WITH_TC) &&
+ cmd->opcode == MMC_STOP_TRANSMISSION)
+ cmd->flags |= MMC_RSP_BUSY;
+
/* Wait max 10 ms */
timeout = 10;
@@ -1390,8 +1394,8 @@ static void sdhci_set_power_reg(struct sdhci_host *host, unsigned char mode,
sdhci_writeb(host, 0, SDHCI_POWER_CONTROL);
}
-void sdhci_set_power(struct sdhci_host *host, unsigned char mode,
- unsigned short vdd)
+void sdhci_set_power_noreg(struct sdhci_host *host, unsigned char mode,
+ unsigned short vdd)
{
u8 pwr = 0;
@@ -1455,20 +1459,17 @@ void sdhci_set_power(struct sdhci_host *host, unsigned char mode,
mdelay(10);
}
}
-EXPORT_SYMBOL_GPL(sdhci_set_power);
+EXPORT_SYMBOL_GPL(sdhci_set_power_noreg);
-static void __sdhci_set_power(struct sdhci_host *host, unsigned char mode,
- unsigned short vdd)
+void sdhci_set_power(struct sdhci_host *host, unsigned char mode,
+ unsigned short vdd)
{
- struct mmc_host *mmc = host->mmc;
-
- if (host->ops->set_power)
- host->ops->set_power(host, mode, vdd);
- else if (!IS_ERR(mmc->supply.vmmc))
- sdhci_set_power_reg(host, mode, vdd);
+ if (IS_ERR(host->mmc->supply.vmmc))
+ sdhci_set_power_noreg(host, mode, vdd);
else
- sdhci_set_power(host, mode, vdd);
+ sdhci_set_power_reg(host, mode, vdd);
}
+EXPORT_SYMBOL_GPL(sdhci_set_power);
/*****************************************************************************\
* *
@@ -1609,7 +1610,10 @@ static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
}
}
- __sdhci_set_power(host, ios->power_mode, ios->vdd);
+ if (host->ops->set_power)
+ host->ops->set_power(host, ios->power_mode, ios->vdd);
+ else
+ sdhci_set_power(host, ios->power_mode, ios->vdd);
if (host->ops->platform_send_init_74_clocks)
host->ops->platform_send_init_74_clocks(host, ios->power_mode);
@@ -2082,6 +2086,10 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
if (!host->tuning_done) {
pr_info(DRIVER_NAME ": Timeout waiting for Buffer Read Ready interrupt during tuning procedure, falling back to fixed sampling clock\n");
+
+ sdhci_do_reset(host, SDHCI_RESET_CMD);
+ sdhci_do_reset(host, SDHCI_RESET_DATA);
+
ctrl = sdhci_readw(host, SDHCI_HOST_CONTROL2);
ctrl &= ~SDHCI_CTRL_TUNED_CLK;
ctrl &= ~SDHCI_CTRL_EXEC_TUNING;
@@ -2282,10 +2290,8 @@ static bool sdhci_request_done(struct sdhci_host *host)
for (i = 0; i < SDHCI_MAX_MRQS; i++) {
mrq = host->mrqs_done[i];
- if (mrq) {
- host->mrqs_done[i] = NULL;
+ if (mrq)
break;
- }
}
if (!mrq) {
@@ -2316,6 +2322,17 @@ static bool sdhci_request_done(struct sdhci_host *host)
* upon error conditions.
*/
if (sdhci_needs_reset(host, mrq)) {
+ /*
+ * Do not finish until command and data lines are available for
+ * reset. Note there can only be one other mrq, so it cannot
+ * also be in mrqs_done, otherwise host->cmd and host->data_cmd
+ * would both be null.
+ */
+ if (host->cmd || host->data_cmd) {
+ spin_unlock_irqrestore(&host->lock, flags);
+ return true;
+ }
+
/* Some controllers need this kick or reset won't work here */
if (host->quirks & SDHCI_QUIRK_CLOCK_BEFORE_RESET)
/* This is to force an update */
@@ -2323,10 +2340,8 @@ static bool sdhci_request_done(struct sdhci_host *host)
/* Spec says we should do both at the same time, but Ricoh
controllers do not like that. */
- if (!host->cmd)
- sdhci_do_reset(host, SDHCI_RESET_CMD);
- if (!host->data_cmd)
- sdhci_do_reset(host, SDHCI_RESET_DATA);
+ sdhci_do_reset(host, SDHCI_RESET_CMD);
+ sdhci_do_reset(host, SDHCI_RESET_DATA);
host->pending_reset = false;
}
@@ -2334,6 +2349,8 @@ static bool sdhci_request_done(struct sdhci_host *host)
if (!sdhci_has_requests(host))
sdhci_led_deactivate(host);
+ host->mrqs_done[i] = NULL;
+
mmiowb();
spin_unlock_irqrestore(&host->lock, flags);
@@ -2409,7 +2426,7 @@ static void sdhci_timeout_data_timer(unsigned long data)
* *
\*****************************************************************************/
-static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask, u32 *mask)
+static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask)
{
if (!host->cmd) {
/*
@@ -2453,11 +2470,6 @@ static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask, u32 *mask)
return;
}
- if ((host->quirks2 & SDHCI_QUIRK2_STOP_WITH_TC) &&
- !(host->cmd->flags & MMC_RSP_BUSY) && !host->data &&
- host->cmd->opcode == MMC_STOP_TRANSMISSION)
- *mask &= ~SDHCI_INT_DATA_END;
-
if (intmask & SDHCI_INT_RESPONSE)
sdhci_finish_command(host);
}
@@ -2513,9 +2525,6 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask)
if (!host->data) {
struct mmc_command *data_cmd = host->data_cmd;
- if (data_cmd)
- host->data_cmd = NULL;
-
/*
* The "data complete" interrupt is also used to
* indicate that a busy state has ended. See comment
@@ -2523,11 +2532,13 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask)
*/
if (data_cmd && (data_cmd->flags & MMC_RSP_BUSY)) {
if (intmask & SDHCI_INT_DATA_TIMEOUT) {
+ host->data_cmd = NULL;
data_cmd->error = -ETIMEDOUT;
sdhci_finish_mrq(host, data_cmd->mrq);
return;
}
if (intmask & SDHCI_INT_DATA_END) {
+ host->data_cmd = NULL;
/*
* Some cards handle busy-end interrupt
* before the command completed, so make
@@ -2680,8 +2691,7 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
}
if (intmask & SDHCI_INT_CMD_MASK)
- sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK,
- &intmask);
+ sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK);
if (intmask & SDHCI_INT_DATA_MASK)
sdhci_data_irq(host, intmask & SDHCI_INT_DATA_MASK);
@@ -2914,6 +2924,10 @@ int sdhci_runtime_resume_host(struct sdhci_host *host)
spin_unlock_irqrestore(&host->lock, flags);
}
+ if ((mmc->caps2 & MMC_CAP2_HS400_ES) &&
+ mmc->ops->hs400_enhanced_strobe)
+ mmc->ops->hs400_enhanced_strobe(mmc, &mmc->ios);
+
spin_lock_irqsave(&host->lock, flags);
host->runtime_suspended = false;
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index c722cd2..766df17 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -683,6 +683,8 @@ u16 sdhci_calc_clk(struct sdhci_host *host, unsigned int clock,
void sdhci_set_clock(struct sdhci_host *host, unsigned int clock);
void sdhci_set_power(struct sdhci_host *host, unsigned char mode,
unsigned short vdd);
+void sdhci_set_power_noreg(struct sdhci_host *host, unsigned char mode,
+ unsigned short vdd);
void sdhci_set_bus_width(struct sdhci_host *host, int width);
void sdhci_reset(struct sdhci_host *host, u8 mask);
void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing);
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
index 0f68a99..141bd70 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
@@ -161,7 +161,7 @@ int gpmi_init(struct gpmi_nand_data *this)
ret = gpmi_enable_clk(this);
if (ret)
- goto err_out;
+ return ret;
ret = gpmi_reset_block(r->gpmi_regs, false);
if (ret)
goto err_out;
@@ -197,6 +197,7 @@ int gpmi_init(struct gpmi_nand_data *this)
gpmi_disable_clk(this);
return 0;
err_out:
+ gpmi_disable_clk(this);
return ret;
}
@@ -270,7 +271,7 @@ int bch_set_geometry(struct gpmi_nand_data *this)
ret = gpmi_enable_clk(this);
if (ret)
- goto err_out;
+ return ret;
/*
* Due to erratum #2847 of the MX23, the BCH cannot be soft reset on this
@@ -308,6 +309,7 @@ int bch_set_geometry(struct gpmi_nand_data *this)
gpmi_disable_clk(this);
return 0;
err_out:
+ gpmi_disable_clk(this);
return ret;
}
diff --git a/drivers/mtd/nand/mtk_ecc.c b/drivers/mtd/nand/mtk_ecc.c
index d54f666..dbf2562 100644
--- a/drivers/mtd/nand/mtk_ecc.c
+++ b/drivers/mtd/nand/mtk_ecc.c
@@ -86,6 +86,8 @@ struct mtk_ecc {
struct completion done;
struct mutex lock;
u32 sectors;
+
+ u8 eccdata[112];
};
static inline void mtk_ecc_wait_idle(struct mtk_ecc *ecc,
@@ -366,9 +368,8 @@ int mtk_ecc_encode(struct mtk_ecc *ecc, struct mtk_ecc_config *config,
u8 *data, u32 bytes)
{
dma_addr_t addr;
- u8 *p;
- u32 len, i, val;
- int ret = 0;
+ u32 len;
+ int ret;
addr = dma_map_single(ecc->dev, data, bytes, DMA_TO_DEVICE);
ret = dma_mapping_error(ecc->dev, addr);
@@ -393,14 +394,12 @@ int mtk_ecc_encode(struct mtk_ecc *ecc, struct mtk_ecc_config *config,
/* Program ECC bytes to OOB: per sector oob = FDM + ECC + SPARE */
len = (config->strength * ECC_PARITY_BITS + 7) >> 3;
- p = data + bytes;
- /* write the parity bytes generated by the ECC back to the OOB region */
- for (i = 0; i < len; i++) {
- if ((i % 4) == 0)
- val = readl(ecc->regs + ECC_ENCPAR(i / 4));
- p[i] = (val >> ((i % 4) * 8)) & 0xff;
- }
+ /* write the parity bytes generated by the ECC back to temp buffer */
+ __ioread32_copy(ecc->eccdata, ecc->regs + ECC_ENCPAR(0), round_up(len, 4));
+
+ /* copy into possibly unaligned OOB region with actual length */
+ memcpy(data + bytes, ecc->eccdata, len);
timeout:
dma_unmap_single(ecc->dev, addr, bytes, DMA_TO_DEVICE);
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index e5718e5..3bde96a 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -1095,10 +1095,11 @@ static void nand_release_data_interface(struct nand_chip *chip)
/**
* nand_reset - Reset and initialize a NAND device
* @chip: The NAND chip
+ * @chipnr: Internal die id
*
* Returns 0 for success or negative error code otherwise
*/
-int nand_reset(struct nand_chip *chip)
+int nand_reset(struct nand_chip *chip, int chipnr)
{
struct mtd_info *mtd = nand_to_mtd(chip);
int ret;
@@ -1107,9 +1108,17 @@ int nand_reset(struct nand_chip *chip)
if (ret)
return ret;
+ /*
+ * The CS line has to be released before we can apply the new NAND
+ * interface settings, hence this weird ->select_chip() dance.
+ */
+ chip->select_chip(mtd, chipnr);
chip->cmdfunc(mtd, NAND_CMD_RESET, -1, -1);
+ chip->select_chip(mtd, -1);
+ chip->select_chip(mtd, chipnr);
ret = nand_setup_data_interface(chip);
+ chip->select_chip(mtd, -1);
if (ret)
return ret;
@@ -1185,8 +1194,6 @@ int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
/* Shift to get chip number */
chipnr = ofs >> chip->chip_shift;
- chip->select_chip(mtd, chipnr);
-
/*
* Reset the chip.
* If we want to check the WP through READ STATUS and check the bit 7
@@ -1194,7 +1201,9 @@ int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
* some operation can also clear the bit 7 of status register
* eg. erase/program a locked block
*/
- nand_reset(chip);
+ nand_reset(chip, chipnr);
+
+ chip->select_chip(mtd, chipnr);
/* Check, if it is write protected */
if (nand_check_wp(mtd)) {
@@ -1244,8 +1253,6 @@ int nand_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
/* Shift to get chip number */
chipnr = ofs >> chip->chip_shift;
- chip->select_chip(mtd, chipnr);
-
/*
* Reset the chip.
* If we want to check the WP through READ STATUS and check the bit 7
@@ -1253,7 +1260,9 @@ int nand_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
* some operation can also clear the bit 7 of status register
* eg. erase/program a locked block
*/
- nand_reset(chip);
+ nand_reset(chip, chipnr);
+
+ chip->select_chip(mtd, chipnr);
/* Check, if it is write protected */
if (nand_check_wp(mtd)) {
@@ -2940,10 +2949,6 @@ static int nand_do_write_oob(struct mtd_info *mtd, loff_t to,
}
chipnr = (int)(to >> chip->chip_shift);
- chip->select_chip(mtd, chipnr);
-
- /* Shift to get page */
- page = (int)(to >> chip->page_shift);
/*
* Reset the chip. Some chips (like the Toshiba TC5832DC found in one
@@ -2951,7 +2956,12 @@ static int nand_do_write_oob(struct mtd_info *mtd, loff_t to,
* if we don't do this. I have no clue why, but I seem to have 'fixed'
* it in the doc2000 driver in August 1999. dwmw2.
*/
- nand_reset(chip);
+ nand_reset(chip, chipnr);
+
+ chip->select_chip(mtd, chipnr);
+
+ /* Shift to get page */
+ page = (int)(to >> chip->page_shift);
/* Check, if it is write protected */
if (nand_check_wp(mtd)) {
@@ -3984,14 +3994,14 @@ static struct nand_flash_dev *nand_get_flash_type(struct mtd_info *mtd,
int i, maf_idx;
u8 id_data[8];
- /* Select the device */
- chip->select_chip(mtd, 0);
-
/*
* Reset the chip, required by some chips (e.g. Micron MT29FxGxxxxx)
* after power-up.
*/
- nand_reset(chip);
+ nand_reset(chip, 0);
+
+ /* Select the device */
+ chip->select_chip(mtd, 0);
/* Send the command for reading device ID */
chip->cmdfunc(mtd, NAND_CMD_READID, 0x00, -1);
@@ -4329,17 +4339,31 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips,
return PTR_ERR(type);
}
+ /* Initialize the ->data_interface field. */
ret = nand_init_data_interface(chip);
if (ret)
return ret;
+ /*
+ * Setup the data interface correctly on the chip and controller side.
+ * This explicit call to nand_setup_data_interface() is only required
+ * for the first die, because nand_reset() has been called before
+ * ->data_interface and ->default_onfi_timing_mode were set.
+ * For the other dies, nand_reset() will automatically switch to the
+ * best mode for us.
+ */
+ ret = nand_setup_data_interface(chip);
+ if (ret)
+ return ret;
+
chip->select_chip(mtd, -1);
/* Check for a chip array */
for (i = 1; i < maxchips; i++) {
- chip->select_chip(mtd, i);
/* See comment in nand_get_flash_type for reset */
- nand_reset(chip);
+ nand_reset(chip, i);
+
+ chip->select_chip(mtd, i);
/* Send the command for reading device ID */
chip->cmdfunc(mtd, NAND_CMD_READID, 0x00, -1);
/* Read manufacturer and device IDs */
diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c
index 95c4048..388e46b 100644
--- a/drivers/mtd/ubi/eba.c
+++ b/drivers/mtd/ubi/eba.c
@@ -741,6 +741,7 @@ static int try_recover_peb(struct ubi_volume *vol, int pnum, int lnum,
goto out_put;
}
+ vid_hdr = ubi_get_vid_hdr(vidb);
ubi_assert(vid_hdr->vol_type == UBI_VID_DYNAMIC);
mutex_lock(&ubi->buf_mutex);
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index d6384d9..c1f5c29 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -287,7 +287,7 @@ static int update_vol(struct ubi_device *ubi, struct ubi_attach_info *ai,
/* new_aeb is newer */
if (cmp_res & 1) {
- victim = ubi_alloc_aeb(ai, aeb->ec, aeb->pnum);
+ victim = ubi_alloc_aeb(ai, aeb->pnum, aeb->ec);
if (!victim)
return -ENOMEM;
@@ -707,11 +707,11 @@ static int ubi_attach_fastmap(struct ubi_device *ubi,
fmvhdr->vol_type,
be32_to_cpu(fmvhdr->last_eb_bytes));
- if (!av)
- goto fail_bad;
- if (PTR_ERR(av) == -EINVAL) {
- ubi_err(ubi, "volume (ID %i) already exists",
- fmvhdr->vol_id);
+ if (IS_ERR(av)) {
+ if (PTR_ERR(av) == -EEXIST)
+ ubi_err(ubi, "volume (ID %i) already exists",
+ fmvhdr->vol_id);
+
goto fail_bad;
}
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index c9944d8..8029dd4 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -199,7 +199,7 @@ MODULE_PARM_DESC(lp_interval, "The number of seconds between instances where "
atomic_t netpoll_block_tx = ATOMIC_INIT(0);
#endif
-int bond_net_id __read_mostly;
+unsigned int bond_net_id __read_mostly;
static __be32 arp_target[BOND_MAX_ARP_TARGETS];
static int arp_ip_count;
@@ -4080,16 +4080,16 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
return ret;
}
-static int bond_ethtool_get_settings(struct net_device *bond_dev,
- struct ethtool_cmd *ecmd)
+static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev,
+ struct ethtool_link_ksettings *cmd)
{
struct bonding *bond = netdev_priv(bond_dev);
unsigned long speed = 0;
struct list_head *iter;
struct slave *slave;
- ecmd->duplex = DUPLEX_UNKNOWN;
- ecmd->port = PORT_OTHER;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
+ cmd->base.port = PORT_OTHER;
/* Since bond_slave_can_tx returns false for all inactive or down slaves, we
* do not need to check mode. Though link speed might not represent
@@ -4100,12 +4100,12 @@ static int bond_ethtool_get_settings(struct net_device *bond_dev,
if (bond_slave_can_tx(slave)) {
if (slave->speed != SPEED_UNKNOWN)
speed += slave->speed;
- if (ecmd->duplex == DUPLEX_UNKNOWN &&
+ if (cmd->base.duplex == DUPLEX_UNKNOWN &&
slave->duplex != DUPLEX_UNKNOWN)
- ecmd->duplex = slave->duplex;
+ cmd->base.duplex = slave->duplex;
}
}
- ethtool_cmd_speed_set(ecmd, speed ? : SPEED_UNKNOWN);
+ cmd->base.speed = speed ? : SPEED_UNKNOWN;
return 0;
}
@@ -4121,8 +4121,8 @@ static void bond_ethtool_get_drvinfo(struct net_device *bond_dev,
static const struct ethtool_ops bond_ethtool_ops = {
.get_drvinfo = bond_ethtool_get_drvinfo,
- .get_settings = bond_ethtool_get_settings,
.get_link = ethtool_op_get_link,
+ .get_link_ksettings = bond_ethtool_get_link_ksettings,
};
static const struct net_device_ops bond_netdev_ops = {
diff --git a/drivers/net/can/sja1000/plx_pci.c b/drivers/net/can/sja1000/plx_pci.c
index 3eb7430..f8ff25c 100644
--- a/drivers/net/can/sja1000/plx_pci.c
+++ b/drivers/net/can/sja1000/plx_pci.c
@@ -142,6 +142,9 @@ struct plx_pci_card {
#define CTI_PCI_VENDOR_ID 0x12c4
#define CTI_PCI_DEVICE_ID_CRG001 0x0900
+#define MOXA_PCI_VENDOR_ID 0x1393
+#define MOXA_PCI_DEVICE_ID 0x0100
+
static void plx_pci_reset_common(struct pci_dev *pdev);
static void plx9056_pci_reset_common(struct pci_dev *pdev);
static void plx_pci_reset_marathon_pci(struct pci_dev *pdev);
@@ -258,6 +261,14 @@ static struct plx_pci_card_info plx_pci_card_info_elcus = {
/* based on PLX9030 */
};
+static struct plx_pci_card_info plx_pci_card_info_moxa = {
+ "MOXA", 2,
+ PLX_PCI_CAN_CLOCK, PLX_PCI_OCR, PLX_PCI_CDR,
+ {0, 0x00, 0x00}, { {0, 0x00, 0x80}, {1, 0x00, 0x80} },
+ &plx_pci_reset_common
+ /* based on PLX9052 */
+};
+
static const struct pci_device_id plx_pci_tbl[] = {
{
/* Adlink PCI-7841/cPCI-7841 */
@@ -357,6 +368,13 @@ static const struct pci_device_id plx_pci_tbl[] = {
0, 0,
(kernel_ulong_t)&plx_pci_card_info_elcus
},
+ {
+ /* moxa */
+ MOXA_PCI_VENDOR_ID, MOXA_PCI_DEVICE_ID,
+ PCI_ANY_ID, PCI_ANY_ID,
+ 0, 0,
+ (kernel_ulong_t)&plx_pci_card_info_moxa
+ },
{ 0,}
};
MODULE_DEVICE_TABLE(pci, plx_pci_tbl);
diff --git a/drivers/net/cris/eth_v10.c b/drivers/net/cris/eth_v10.c
index e128826..91c876a 100644
--- a/drivers/net/cris/eth_v10.c
+++ b/drivers/net/cris/eth_v10.c
@@ -7,9 +7,6 @@
*
*/
-
-#include <linux/module.h>
-
#include <linux/kernel.h>
#include <linux/delay.h>
#include <linux/types.h>
@@ -411,6 +408,7 @@ etrax_ethernet_init(void)
led_next_time = jiffies;
return 0;
}
+device_initcall(etrax_ethernet_init)
/* set MAC address of the interface. called from the core after a
* SIOCSIFADDR ioctl, and from the bootup above.
@@ -1714,11 +1712,6 @@ e100_netpoll(struct net_device* netdev)
}
#endif
-static int
-etrax_init_module(void)
-{
- return etrax_ethernet_init();
-}
static int __init
e100_boot_setup(char* str)
@@ -1741,5 +1734,3 @@ e100_boot_setup(char* str)
}
__setup("etrax100_eth=", e100_boot_setup);
-
-module_init(etrax_init_module);
diff --git a/drivers/net/dsa/b53/b53_mmap.c b/drivers/net/dsa/b53/b53_mmap.c
index 76fb855..ef63d24 100644
--- a/drivers/net/dsa/b53/b53_mmap.c
+++ b/drivers/net/dsa/b53/b53_mmap.c
@@ -256,6 +256,7 @@ static const struct of_device_id b53_mmap_of_table[] = {
{ .compatible = "brcm,bcm63xx-switch" },
{ /* sentinel */ },
};
+MODULE_DEVICE_TABLE(of, b53_mmap_of_table);
static struct platform_driver b53_mmap_driver = {
.probe = b53_mmap_probe,
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index e218887..e3ee27c 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1133,6 +1133,20 @@ static int bcm_sf2_sw_remove(struct platform_device *pdev)
return 0;
}
+static void bcm_sf2_sw_shutdown(struct platform_device *pdev)
+{
+ struct bcm_sf2_priv *priv = platform_get_drvdata(pdev);
+
+ /* For a kernel about to be kexec'd we want to keep the GPHY on for a
+ * successful MDIO bus scan to occur. If we did turn off the GPHY
+ * before (e.g: port_disable), this will also power it back on.
+ *
+ * Do not rely on kexec_in_progress, just power the PHY on.
+ */
+ if (priv->hw_params.num_gphy == 1)
+ bcm_sf2_gphy_enable_set(priv->dev->ds, true);
+}
+
#ifdef CONFIG_PM_SLEEP
static int bcm_sf2_suspend(struct device *dev)
{
@@ -1158,10 +1172,12 @@ static const struct of_device_id bcm_sf2_of_match[] = {
{ .compatible = "brcm,bcm7445-switch-v4.0" },
{ /* sentinel */ },
};
+MODULE_DEVICE_TABLE(of, bcm_sf2_of_match);
static struct platform_driver bcm_sf2_driver = {
.probe = bcm_sf2_sw_probe,
.remove = bcm_sf2_sw_remove,
+ .shutdown = bcm_sf2_sw_shutdown,
.driver = {
.name = "brcm-sf2",
.of_match_table = bcm_sf2_of_match,
diff --git a/drivers/net/dsa/mv88e6xxx/Kconfig b/drivers/net/dsa/mv88e6xxx/Kconfig
index 4866688..1aaa7a9 100644
--- a/drivers/net/dsa/mv88e6xxx/Kconfig
+++ b/drivers/net/dsa/mv88e6xxx/Kconfig
@@ -1,6 +1,7 @@
config NET_DSA_MV88E6XXX
tristate "Marvell 88E6xxx Ethernet switch fabric support"
depends on NET_DSA
+ select IRQ_DOMAIN
select NET_DSA_TAG_EDSA
select NET_DSA_TAG_DSA
help
diff --git a/drivers/net/dsa/mv88e6xxx/Makefile b/drivers/net/dsa/mv88e6xxx/Makefile
index 10ce820..c36be31 100644
--- a/drivers/net/dsa/mv88e6xxx/Makefile
+++ b/drivers/net/dsa/mv88e6xxx/Makefile
@@ -2,3 +2,4 @@
mv88e6xxx-objs := chip.o
mv88e6xxx-objs += global1.o
mv88e6xxx-$(CONFIG_NET_DSA_MV88E6XXX_GLOBAL2) += global2.o
+mv88e6xxx-objs += port.o
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 72b9dac2..d6d9d66 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -37,6 +37,7 @@
#include "mv88e6xxx.h"
#include "global1.h"
#include "global2.h"
+#include "port.h"
static void assert_reg_lock(struct mv88e6xxx_chip *chip)
{
@@ -221,22 +222,6 @@ int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val)
return 0;
}
-static int mv88e6xxx_port_read(struct mv88e6xxx_chip *chip, int port, int reg,
- u16 *val)
-{
- int addr = chip->info->port_base_addr + port;
-
- return mv88e6xxx_read(chip, addr, reg, val);
-}
-
-static int mv88e6xxx_port_write(struct mv88e6xxx_chip *chip, int port, int reg,
- u16 val)
-{
- int addr = chip->info->port_base_addr + port;
-
- return mv88e6xxx_write(chip, addr, reg, val);
-}
-
static int mv88e6xxx_phy_read(struct mv88e6xxx_chip *chip, int phy,
int reg, u16 *val)
{
@@ -716,6 +701,47 @@ static bool mv88e6xxx_6352_family(struct mv88e6xxx_chip *chip)
return chip->info->family == MV88E6XXX_FAMILY_6352;
}
+static int mv88e6xxx_port_setup_mac(struct mv88e6xxx_chip *chip, int port,
+ int link, int speed, int duplex,
+ phy_interface_t mode)
+{
+ int err;
+
+ if (!chip->info->ops->port_set_link)
+ return 0;
+
+ /* Port's MAC control must not be changed unless the link is down */
+ err = chip->info->ops->port_set_link(chip, port, 0);
+ if (err)
+ return err;
+
+ if (chip->info->ops->port_set_speed) {
+ err = chip->info->ops->port_set_speed(chip, port, speed);
+ if (err && err != -EOPNOTSUPP)
+ goto restore_link;
+ }
+
+ if (chip->info->ops->port_set_duplex) {
+ err = chip->info->ops->port_set_duplex(chip, port, duplex);
+ if (err && err != -EOPNOTSUPP)
+ goto restore_link;
+ }
+
+ if (chip->info->ops->port_set_rgmii_delay) {
+ err = chip->info->ops->port_set_rgmii_delay(chip, port, mode);
+ if (err && err != -EOPNOTSUPP)
+ goto restore_link;
+ }
+
+ err = 0;
+restore_link:
+ if (chip->info->ops->port_set_link(chip, port, link))
+ netdev_err(chip->ds->ports[port].netdev,
+ "failed to restore MAC's link\n");
+
+ return err;
+}
+
/* We expect the switch to perform auto negotiation if there is a real
* phy. However, in the case of a fixed link phy, we force the port
* settings from the fixed link settings.
@@ -724,64 +750,18 @@ static void mv88e6xxx_adjust_link(struct dsa_switch *ds, int port,
struct phy_device *phydev)
{
struct mv88e6xxx_chip *chip = ds->priv;
- u16 reg;
int err;
if (!phy_is_pseudo_fixed_link(phydev))
return;
mutex_lock(&chip->reg_lock);
-
- err = mv88e6xxx_port_read(chip, port, PORT_PCS_CTRL, ®);
- if (err)
- goto out;
-
- reg &= ~(PORT_PCS_CTRL_LINK_UP |
- PORT_PCS_CTRL_FORCE_LINK |
- PORT_PCS_CTRL_DUPLEX_FULL |
- PORT_PCS_CTRL_FORCE_DUPLEX |
- PORT_PCS_CTRL_UNFORCED);
-
- reg |= PORT_PCS_CTRL_FORCE_LINK;
- if (phydev->link)
- reg |= PORT_PCS_CTRL_LINK_UP;
-
- if (mv88e6xxx_6065_family(chip) && phydev->speed > SPEED_100)
- goto out;
-
- switch (phydev->speed) {
- case SPEED_1000:
- reg |= PORT_PCS_CTRL_1000;
- break;
- case SPEED_100:
- reg |= PORT_PCS_CTRL_100;
- break;
- case SPEED_10:
- reg |= PORT_PCS_CTRL_10;
- break;
- default:
- pr_info("Unknown speed");
- goto out;
- }
-
- reg |= PORT_PCS_CTRL_FORCE_DUPLEX;
- if (phydev->duplex == DUPLEX_FULL)
- reg |= PORT_PCS_CTRL_DUPLEX_FULL;
-
- if ((mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip)) &&
- (port >= mv88e6xxx_num_ports(chip) - 2)) {
- if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID)
- reg |= PORT_PCS_CTRL_RGMII_DELAY_RXCLK;
- if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)
- reg |= PORT_PCS_CTRL_RGMII_DELAY_TXCLK;
- if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID)
- reg |= (PORT_PCS_CTRL_RGMII_DELAY_RXCLK |
- PORT_PCS_CTRL_RGMII_DELAY_TXCLK);
- }
- mv88e6xxx_port_write(chip, port, PORT_PCS_CTRL, reg);
-
-out:
+ err = mv88e6xxx_port_setup_mac(chip, port, phydev->link, phydev->speed,
+ phydev->duplex, phydev->interface);
mutex_unlock(&chip->reg_lock);
+
+ if (err && err != -EOPNOTSUPP)
+ netdev_err(ds->ports[port].netdev, "failed to configure MAC\n");
}
static int _mv88e6xxx_stats_wait(struct mv88e6xxx_chip *chip)
@@ -1230,54 +1210,16 @@ static int _mv88e6xxx_atu_remove(struct mv88e6xxx_chip *chip, u16 fid,
return _mv88e6xxx_atu_move(chip, fid, port, 0x0f, static_too);
}
-static const char * const mv88e6xxx_port_state_names[] = {
- [PORT_CONTROL_STATE_DISABLED] = "Disabled",
- [PORT_CONTROL_STATE_BLOCKING] = "Blocking/Listening",
- [PORT_CONTROL_STATE_LEARNING] = "Learning",
- [PORT_CONTROL_STATE_FORWARDING] = "Forwarding",
-};
-
-static int _mv88e6xxx_port_state(struct mv88e6xxx_chip *chip, int port,
- u8 state)
-{
- struct dsa_switch *ds = chip->ds;
- u16 reg;
- int err;
- u8 oldstate;
-
- err = mv88e6xxx_port_read(chip, port, PORT_CONTROL, ®);
- if (err)
- return err;
-
- oldstate = reg & PORT_CONTROL_STATE_MASK;
-
- reg &= ~PORT_CONTROL_STATE_MASK;
- reg |= state;
-
- err = mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg);
- if (err)
- return err;
-
- netdev_dbg(ds->ports[port].netdev, "PortState %s (was %s)\n",
- mv88e6xxx_port_state_names[state],
- mv88e6xxx_port_state_names[oldstate]);
-
- return 0;
-}
-
static int _mv88e6xxx_port_based_vlan_map(struct mv88e6xxx_chip *chip, int port)
{
struct net_device *bridge = chip->ports[port].bridge_dev;
- const u16 mask = (1 << mv88e6xxx_num_ports(chip)) - 1;
struct dsa_switch *ds = chip->ds;
u16 output_ports = 0;
- u16 reg;
- int err;
int i;
/* allow CPU port or DSA link(s) to send frames to every port */
if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) {
- output_ports = mask;
+ output_ports = ~0;
} else {
for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
/* allow sending frames to every group member */
@@ -1293,14 +1235,7 @@ static int _mv88e6xxx_port_based_vlan_map(struct mv88e6xxx_chip *chip, int port)
/* prevent frames from going back out of the port they came in on */
output_ports &= ~BIT(port);
- err = mv88e6xxx_port_read(chip, port, PORT_BASE_VLAN, ®);
- if (err)
- return err;
-
- reg &= ~mask;
- reg |= output_ports & mask;
-
- return mv88e6xxx_port_write(chip, port, PORT_BASE_VLAN, reg);
+ return mv88e6xxx_port_set_vlan_map(chip, port, output_ports);
}
static void mv88e6xxx_port_stp_state_set(struct dsa_switch *ds, int port,
@@ -1328,13 +1263,11 @@ static void mv88e6xxx_port_stp_state_set(struct dsa_switch *ds, int port,
}
mutex_lock(&chip->reg_lock);
- err = _mv88e6xxx_port_state(chip, port, stp_state);
+ err = mv88e6xxx_port_set_state(chip, port, stp_state);
mutex_unlock(&chip->reg_lock);
if (err)
- netdev_err(ds->ports[port].netdev,
- "failed to update state to %s\n",
- mv88e6xxx_port_state_names[stp_state]);
+ netdev_err(ds->ports[port].netdev, "failed to update state\n");
}
static void mv88e6xxx_port_fast_age(struct dsa_switch *ds, int port)
@@ -1350,49 +1283,6 @@ static void mv88e6xxx_port_fast_age(struct dsa_switch *ds, int port)
netdev_err(ds->ports[port].netdev, "failed to flush ATU\n");
}
-static int _mv88e6xxx_port_pvid(struct mv88e6xxx_chip *chip, int port,
- u16 *new, u16 *old)
-{
- struct dsa_switch *ds = chip->ds;
- u16 pvid, reg;
- int err;
-
- err = mv88e6xxx_port_read(chip, port, PORT_DEFAULT_VLAN, ®);
- if (err)
- return err;
-
- pvid = reg & PORT_DEFAULT_VLAN_MASK;
-
- if (new) {
- reg &= ~PORT_DEFAULT_VLAN_MASK;
- reg |= *new & PORT_DEFAULT_VLAN_MASK;
-
- err = mv88e6xxx_port_write(chip, port, PORT_DEFAULT_VLAN, reg);
- if (err)
- return err;
-
- netdev_dbg(ds->ports[port].netdev,
- "DefaultVID %d (was %d)\n", *new, pvid);
- }
-
- if (old)
- *old = pvid;
-
- return 0;
-}
-
-static int _mv88e6xxx_port_pvid_get(struct mv88e6xxx_chip *chip,
- int port, u16 *pvid)
-{
- return _mv88e6xxx_port_pvid(chip, port, NULL, pvid);
-}
-
-static int _mv88e6xxx_port_pvid_set(struct mv88e6xxx_chip *chip,
- int port, u16 pvid)
-{
- return _mv88e6xxx_port_pvid(chip, port, &pvid, NULL);
-}
-
static int _mv88e6xxx_vtu_wait(struct mv88e6xxx_chip *chip)
{
return mv88e6xxx_g1_wait(chip, GLOBAL_VTU_OP, GLOBAL_VTU_OP_BUSY);
@@ -1572,7 +1462,7 @@ static int mv88e6xxx_port_vlan_dump(struct dsa_switch *ds, int port,
mutex_lock(&chip->reg_lock);
- err = _mv88e6xxx_port_pvid_get(chip, port, &pvid);
+ err = mv88e6xxx_port_get_pvid(chip, port, &pvid);
if (err)
goto unlock;
@@ -1736,75 +1626,6 @@ static int _mv88e6xxx_stu_loadpurge(struct mv88e6xxx_chip *chip,
return _mv88e6xxx_vtu_cmd(chip, GLOBAL_VTU_OP_STU_LOAD_PURGE);
}
-static int _mv88e6xxx_port_fid(struct mv88e6xxx_chip *chip, int port,
- u16 *new, u16 *old)
-{
- struct dsa_switch *ds = chip->ds;
- u16 upper_mask;
- u16 fid;
- u16 reg;
- int err;
-
- if (mv88e6xxx_num_databases(chip) == 4096)
- upper_mask = 0xff;
- else if (mv88e6xxx_num_databases(chip) == 256)
- upper_mask = 0xf;
- else
- return -EOPNOTSUPP;
-
- /* Port's default FID bits 3:0 are located in reg 0x06, offset 12 */
- err = mv88e6xxx_port_read(chip, port, PORT_BASE_VLAN, ®);
- if (err)
- return err;
-
- fid = (reg & PORT_BASE_VLAN_FID_3_0_MASK) >> 12;
-
- if (new) {
- reg &= ~PORT_BASE_VLAN_FID_3_0_MASK;
- reg |= (*new << 12) & PORT_BASE_VLAN_FID_3_0_MASK;
-
- err = mv88e6xxx_port_write(chip, port, PORT_BASE_VLAN, reg);
- if (err)
- return err;
- }
-
- /* Port's default FID bits 11:4 are located in reg 0x05, offset 0 */
- err = mv88e6xxx_port_read(chip, port, PORT_CONTROL_1, ®);
- if (err)
- return err;
-
- fid |= (reg & upper_mask) << 4;
-
- if (new) {
- reg &= ~upper_mask;
- reg |= (*new >> 4) & upper_mask;
-
- err = mv88e6xxx_port_write(chip, port, PORT_CONTROL_1, reg);
- if (err)
- return err;
-
- netdev_dbg(ds->ports[port].netdev,
- "FID %d (was %d)\n", *new, fid);
- }
-
- if (old)
- *old = fid;
-
- return 0;
-}
-
-static int _mv88e6xxx_port_fid_get(struct mv88e6xxx_chip *chip,
- int port, u16 *fid)
-{
- return _mv88e6xxx_port_fid(chip, port, NULL, fid);
-}
-
-static int _mv88e6xxx_port_fid_set(struct mv88e6xxx_chip *chip,
- int port, u16 fid)
-{
- return _mv88e6xxx_port_fid(chip, port, &fid, NULL);
-}
-
static int _mv88e6xxx_fid_new(struct mv88e6xxx_chip *chip, u16 *fid)
{
DECLARE_BITMAP(fid_bitmap, MV88E6XXX_N_FID);
@@ -1815,7 +1636,7 @@ static int _mv88e6xxx_fid_new(struct mv88e6xxx_chip *chip, u16 *fid)
/* Set every FID bit used by the (un)bridged ports */
for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
- err = _mv88e6xxx_port_fid_get(chip, i, fid);
+ err = mv88e6xxx_port_get_fid(chip, i, fid);
if (err)
return err;
@@ -1980,48 +1801,19 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port,
return err;
}
-static const char * const mv88e6xxx_port_8021q_mode_names[] = {
- [PORT_CONTROL_2_8021Q_DISABLED] = "Disabled",
- [PORT_CONTROL_2_8021Q_FALLBACK] = "Fallback",
- [PORT_CONTROL_2_8021Q_CHECK] = "Check",
- [PORT_CONTROL_2_8021Q_SECURE] = "Secure",
-};
-
static int mv88e6xxx_port_vlan_filtering(struct dsa_switch *ds, int port,
bool vlan_filtering)
{
struct mv88e6xxx_chip *chip = ds->priv;
- u16 old, new = vlan_filtering ? PORT_CONTROL_2_8021Q_SECURE :
+ u16 mode = vlan_filtering ? PORT_CONTROL_2_8021Q_SECURE :
PORT_CONTROL_2_8021Q_DISABLED;
- u16 reg;
int err;
if (!mv88e6xxx_has(chip, MV88E6XXX_FLAG_VTU))
return -EOPNOTSUPP;
mutex_lock(&chip->reg_lock);
-
- err = mv88e6xxx_port_read(chip, port, PORT_CONTROL_2, ®);
- if (err)
- goto unlock;
-
- old = reg & PORT_CONTROL_2_8021Q_MASK;
-
- if (new != old) {
- reg &= ~PORT_CONTROL_2_8021Q_MASK;
- reg |= new & PORT_CONTROL_2_8021Q_MASK;
-
- err = mv88e6xxx_port_write(chip, port, PORT_CONTROL_2, reg);
- if (err)
- goto unlock;
-
- netdev_dbg(ds->ports[port].netdev, "802.1Q Mode %s (was %s)\n",
- mv88e6xxx_port_8021q_mode_names[new],
- mv88e6xxx_port_8021q_mode_names[old]);
- }
-
- err = 0;
-unlock:
+ err = mv88e6xxx_port_set_8021q_mode(chip, port, mode);
mutex_unlock(&chip->reg_lock);
return err;
@@ -2089,7 +1881,7 @@ static void mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port,
"failed to add VLAN %d%c\n",
vid, untagged ? 'u' : 't');
- if (pvid && _mv88e6xxx_port_pvid_set(chip, port, vlan->vid_end))
+ if (pvid && mv88e6xxx_port_set_pvid(chip, port, vlan->vid_end))
netdev_err(ds->ports[port].netdev, "failed to set PVID %d\n",
vlan->vid_end);
@@ -2144,7 +1936,7 @@ static int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port,
mutex_lock(&chip->reg_lock);
- err = _mv88e6xxx_port_pvid_get(chip, port, &pvid);
+ err = mv88e6xxx_port_get_pvid(chip, port, &pvid);
if (err)
goto unlock;
@@ -2154,7 +1946,7 @@ static int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port,
goto unlock;
if (vid == pvid) {
- err = _mv88e6xxx_port_pvid_set(chip, port, 0);
+ err = mv88e6xxx_port_set_pvid(chip, port, 0);
if (err)
goto unlock;
}
@@ -2265,7 +2057,7 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
/* Null VLAN ID corresponds to the port private database */
if (vid == 0)
- err = _mv88e6xxx_port_fid_get(chip, port, &vlan.fid);
+ err = mv88e6xxx_port_get_fid(chip, port, &vlan.fid);
else
err = _mv88e6xxx_vtu_get(chip, vid, &vlan, false);
if (err)
@@ -2441,7 +2233,7 @@ static int mv88e6xxx_port_db_dump(struct mv88e6xxx_chip *chip, int port,
int err;
/* Dump port's default Filtering Information Database (VLAN ID 0) */
- err = _mv88e6xxx_port_fid_get(chip, port, &fid);
+ err = mv88e6xxx_port_get_fid(chip, port, &fid);
if (err)
return err;
@@ -2541,12 +2333,8 @@ static int mv88e6xxx_switch_reset(struct mv88e6xxx_chip *chip)
/* Set all ports to the disabled state. */
for (i = 0; i < mv88e6xxx_num_ports(chip); i++) {
- err = mv88e6xxx_port_read(chip, i, PORT_CONTROL, ®);
- if (err)
- return err;
-
- err = mv88e6xxx_port_write(chip, i, PORT_CONTROL,
- reg & 0xfffc);
+ err = mv88e6xxx_port_set_state(chip, i,
+ PORT_CONTROL_STATE_DISABLED);
if (err)
return err;
}
@@ -2616,35 +2404,20 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
int err;
u16 reg;
- if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) ||
- mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) ||
- mv88e6xxx_6185_family(chip) || mv88e6xxx_6095_family(chip) ||
- mv88e6xxx_6065_family(chip) || mv88e6xxx_6320_family(chip)) {
- /* MAC Forcing register: don't force link, speed,
- * duplex or flow control state to any particular
- * values on physical ports, but force the CPU port
- * and all DSA ports to their maximum bandwidth and
- * full duplex.
- */
- err = mv88e6xxx_port_read(chip, port, PORT_PCS_CTRL, ®);
- if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) {
- reg &= ~PORT_PCS_CTRL_UNFORCED;
- reg |= PORT_PCS_CTRL_FORCE_LINK |
- PORT_PCS_CTRL_LINK_UP |
- PORT_PCS_CTRL_DUPLEX_FULL |
- PORT_PCS_CTRL_FORCE_DUPLEX;
- if (mv88e6xxx_6065_family(chip))
- reg |= PORT_PCS_CTRL_100;
- else
- reg |= PORT_PCS_CTRL_1000;
- } else {
- reg |= PORT_PCS_CTRL_UNFORCED;
- }
-
- err = mv88e6xxx_port_write(chip, port, PORT_PCS_CTRL, reg);
- if (err)
- return err;
- }
+ /* MAC Forcing register: don't force link, speed, duplex or flow control
+ * state to any particular values on physical ports, but force the CPU
+ * port and all DSA ports to their maximum bandwidth and full duplex.
+ */
+ if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))
+ err = mv88e6xxx_port_setup_mac(chip, port, LINK_FORCED_UP,
+ SPEED_MAX, DUPLEX_FULL,
+ PHY_INTERFACE_MODE_NA);
+ else
+ err = mv88e6xxx_port_setup_mac(chip, port, LINK_UNFORCED,
+ SPEED_UNFORCED, DUPLEX_UNFORCED,
+ PHY_INTERFACE_MODE_NA);
+ if (err)
+ return err;
/* Port Control: disable Drop-on-Unlock, disable Drop-on-Lock,
* disable Header mode, enable IGMP/MLD snooping, disable VLAN
@@ -2848,7 +2621,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
* database, and allow bidirectional communication between the
* CPU and DSA port(s), and the other ports.
*/
- err = _mv88e6xxx_port_fid_set(chip, port, 0);
+ err = mv88e6xxx_port_set_fid(chip, port, 0);
if (err)
return err;
@@ -3367,42 +3140,64 @@ static const struct mv88e6xxx_ops mv88e6085_ops = {
.set_switch_mac = mv88e6xxx_g1_set_switch_mac,
.phy_read = mv88e6xxx_phy_ppu_read,
.phy_write = mv88e6xxx_phy_ppu_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_speed = mv88e6185_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6095_ops = {
.set_switch_mac = mv88e6xxx_g1_set_switch_mac,
.phy_read = mv88e6xxx_phy_ppu_read,
.phy_write = mv88e6xxx_phy_ppu_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_speed = mv88e6185_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6123_ops = {
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_read,
.phy_write = mv88e6xxx_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_speed = mv88e6185_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6131_ops = {
.set_switch_mac = mv88e6xxx_g1_set_switch_mac,
.phy_read = mv88e6xxx_phy_ppu_read,
.phy_write = mv88e6xxx_phy_ppu_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_speed = mv88e6185_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6161_ops = {
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_read,
.phy_write = mv88e6xxx_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_speed = mv88e6185_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6165_ops = {
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_read,
.phy_write = mv88e6xxx_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_speed = mv88e6185_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6171_ops = {
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
+ .port_set_speed = mv88e6185_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6172_ops = {
@@ -3411,12 +3206,20 @@ static const struct mv88e6xxx_ops mv88e6172_ops = {
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
+ .port_set_speed = mv88e6352_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6175_ops = {
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
+ .port_set_speed = mv88e6185_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6176_ops = {
@@ -3425,12 +3228,19 @@ static const struct mv88e6xxx_ops mv88e6176_ops = {
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
+ .port_set_speed = mv88e6352_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6185_ops = {
.set_switch_mac = mv88e6xxx_g1_set_switch_mac,
.phy_read = mv88e6xxx_phy_ppu_read,
.phy_write = mv88e6xxx_phy_ppu_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_speed = mv88e6185_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6240_ops = {
@@ -3439,6 +3249,10 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
+ .port_set_speed = mv88e6352_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6320_ops = {
@@ -3447,6 +3261,9 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_speed = mv88e6185_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6321_ops = {
@@ -3455,18 +3272,29 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_speed = mv88e6185_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6350_ops = {
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
+ .port_set_speed = mv88e6185_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6351_ops = {
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
+ .port_set_speed = mv88e6185_port_set_speed,
};
static const struct mv88e6xxx_ops mv88e6352_ops = {
@@ -3475,6 +3303,10 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
.set_switch_mac = mv88e6xxx_g2_set_switch_mac,
.phy_read = mv88e6xxx_g2_smi_phy_read,
.phy_write = mv88e6xxx_g2_smi_phy_write,
+ .port_set_link = mv88e6xxx_port_set_link,
+ .port_set_duplex = mv88e6xxx_port_set_duplex,
+ .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay,
+ .port_set_speed = mv88e6352_port_set_speed,
};
static const struct mv88e6xxx_info mv88e6xxx_table[] = {
diff --git a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h
index 6f48e58..9296130 100644
--- a/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h
+++ b/drivers/net/dsa/mv88e6xxx/mv88e6xxx.h
@@ -61,16 +61,22 @@
#define PORT_PCS_CTRL 0x01
#define PORT_PCS_CTRL_RGMII_DELAY_RXCLK BIT(15)
#define PORT_PCS_CTRL_RGMII_DELAY_TXCLK BIT(14)
+#define PORT_PCS_CTRL_FORCE_SPEED BIT(13) /* 6390 */
+#define PORT_PCS_CTRL_ALTSPEED BIT(12) /* 6390 */
+#define PORT_PCS_CTRL_200BASE BIT(12) /* 6352 */
#define PORT_PCS_CTRL_FC BIT(7)
#define PORT_PCS_CTRL_FORCE_FC BIT(6)
#define PORT_PCS_CTRL_LINK_UP BIT(5)
#define PORT_PCS_CTRL_FORCE_LINK BIT(4)
#define PORT_PCS_CTRL_DUPLEX_FULL BIT(3)
#define PORT_PCS_CTRL_FORCE_DUPLEX BIT(2)
-#define PORT_PCS_CTRL_10 0x00
-#define PORT_PCS_CTRL_100 0x01
-#define PORT_PCS_CTRL_1000 0x02
-#define PORT_PCS_CTRL_UNFORCED 0x03
+#define PORT_PCS_CTRL_SPEED_MASK (0x03)
+#define PORT_PCS_CTRL_SPEED_10 (0x00)
+#define PORT_PCS_CTRL_SPEED_100 (0x01)
+#define PORT_PCS_CTRL_SPEED_200 (0x02) /* 6065 and non Gb chips */
+#define PORT_PCS_CTRL_SPEED_1000 (0x02)
+#define PORT_PCS_CTRL_SPEED_10000 (0x03) /* 6390X */
+#define PORT_PCS_CTRL_SPEED_UNFORCED (0x03)
#define PORT_PAUSE_CTRL 0x02
#define PORT_SWITCH_ID 0x03
#define PORT_SWITCH_ID_PROD_NUM_6085 0x04a
@@ -727,6 +733,41 @@ struct mv88e6xxx_ops {
u16 *val);
int (*phy_write)(struct mv88e6xxx_chip *chip, int addr, int reg,
u16 val);
+
+ /* RGMII Receive/Transmit Timing Control
+ * Add delay on PHY_INTERFACE_MODE_RGMII_*ID, no delay otherwise.
+ */
+ int (*port_set_rgmii_delay)(struct mv88e6xxx_chip *chip, int port,
+ phy_interface_t mode);
+
+#define LINK_FORCED_DOWN 0
+#define LINK_FORCED_UP 1
+#define LINK_UNFORCED -2
+
+ /* Port's MAC link state
+ * Use LINK_FORCED_UP or LINK_FORCED_DOWN to force link up or down,
+ * or LINK_UNFORCED for normal link detection.
+ */
+ int (*port_set_link)(struct mv88e6xxx_chip *chip, int port, int link);
+
+#define DUPLEX_UNFORCED -2
+
+ /* Port's MAC duplex mode
+ *
+ * Use DUPLEX_HALF or DUPLEX_FULL to force half or full duplex,
+ * or DUPLEX_UNFORCED for normal duplex detection.
+ */
+ int (*port_set_duplex)(struct mv88e6xxx_chip *chip, int port, int dup);
+
+#define SPEED_MAX INT_MAX
+#define SPEED_UNFORCED -2
+
+ /* Port's MAC speed (in Mbps)
+ *
+ * Depending on the chip, 10, 100, 200, 1000, 2500, 10000 are valid.
+ * Use SPEED_UNFORCED for normal detection, SPEED_MAX for max value.
+ */
+ int (*port_set_speed)(struct mv88e6xxx_chip *chip, int port, int speed);
};
enum stat_type {
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
new file mode 100644
index 0000000..af4772d8
--- /dev/null
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -0,0 +1,498 @@
+/*
+ * Marvell 88E6xxx Switch Port Registers support
+ *
+ * Copyright (c) 2008 Marvell Semiconductor
+ *
+ * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "mv88e6xxx.h"
+#include "port.h"
+
+int mv88e6xxx_port_read(struct mv88e6xxx_chip *chip, int port, int reg,
+ u16 *val)
+{
+ int addr = chip->info->port_base_addr + port;
+
+ return mv88e6xxx_read(chip, addr, reg, val);
+}
+
+int mv88e6xxx_port_write(struct mv88e6xxx_chip *chip, int port, int reg,
+ u16 val)
+{
+ int addr = chip->info->port_base_addr + port;
+
+ return mv88e6xxx_write(chip, addr, reg, val);
+}
+
+/* Offset 0x01: MAC (or PCS or Physical) Control Register
+ *
+ * Link, Duplex and Flow Control have one force bit, one value bit.
+ *
+ * For port's MAC speed, ForceSpd (or SpdValue) bits 1:0 program the value.
+ * Alternative values require the 200BASE (or AltSpeed) bit 12 set.
+ * Newer chips need a ForcedSpd bit 13 set to consider the value.
+ */
+
+static int mv88e6xxx_port_set_rgmii_delay(struct mv88e6xxx_chip *chip, int port,
+ phy_interface_t mode)
+{
+ u16 reg;
+ int err;
+
+ err = mv88e6xxx_port_read(chip, port, PORT_PCS_CTRL, ®);
+ if (err)
+ return err;
+
+ reg &= ~(PORT_PCS_CTRL_RGMII_DELAY_RXCLK |
+ PORT_PCS_CTRL_RGMII_DELAY_TXCLK);
+
+ switch (mode) {
+ case PHY_INTERFACE_MODE_RGMII_RXID:
+ reg |= PORT_PCS_CTRL_RGMII_DELAY_RXCLK;
+ break;
+ case PHY_INTERFACE_MODE_RGMII_TXID:
+ reg |= PORT_PCS_CTRL_RGMII_DELAY_TXCLK;
+ break;
+ case PHY_INTERFACE_MODE_RGMII_ID:
+ reg |= PORT_PCS_CTRL_RGMII_DELAY_RXCLK |
+ PORT_PCS_CTRL_RGMII_DELAY_TXCLK;
+ break;
+ case PHY_INTERFACE_MODE_RGMII:
+ break;
+ default:
+ return 0;
+ }
+
+ err = mv88e6xxx_port_write(chip, port, PORT_PCS_CTRL, reg);
+ if (err)
+ return err;
+
+ netdev_dbg(chip->ds->ports[port].netdev, "delay RXCLK %s, TXCLK %s\n",
+ reg & PORT_PCS_CTRL_RGMII_DELAY_RXCLK ? "yes" : "no",
+ reg & PORT_PCS_CTRL_RGMII_DELAY_TXCLK ? "yes" : "no");
+
+ return 0;
+}
+
+int mv88e6352_port_set_rgmii_delay(struct mv88e6xxx_chip *chip, int port,
+ phy_interface_t mode)
+{
+ if (port < 5)
+ return -EOPNOTSUPP;
+
+ return mv88e6xxx_port_set_rgmii_delay(chip, port, mode);
+}
+
+int mv88e6390_port_set_rgmii_delay(struct mv88e6xxx_chip *chip, int port,
+ phy_interface_t mode)
+{
+ if (port != 0)
+ return -EOPNOTSUPP;
+
+ return mv88e6xxx_port_set_rgmii_delay(chip, port, mode);
+}
+
+int mv88e6xxx_port_set_link(struct mv88e6xxx_chip *chip, int port, int link)
+{
+ u16 reg;
+ int err;
+
+ err = mv88e6xxx_port_read(chip, port, PORT_PCS_CTRL, ®);
+ if (err)
+ return err;
+
+ reg &= ~(PORT_PCS_CTRL_FORCE_LINK | PORT_PCS_CTRL_LINK_UP);
+
+ switch (link) {
+ case LINK_FORCED_DOWN:
+ reg |= PORT_PCS_CTRL_FORCE_LINK;
+ break;
+ case LINK_FORCED_UP:
+ reg |= PORT_PCS_CTRL_FORCE_LINK | PORT_PCS_CTRL_LINK_UP;
+ break;
+ case LINK_UNFORCED:
+ /* normal link detection */
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ err = mv88e6xxx_port_write(chip, port, PORT_PCS_CTRL, reg);
+ if (err)
+ return err;
+
+ netdev_dbg(chip->ds->ports[port].netdev, "%s link %s\n",
+ reg & PORT_PCS_CTRL_FORCE_LINK ? "Force" : "Unforce",
+ reg & PORT_PCS_CTRL_LINK_UP ? "up" : "down");
+
+ return 0;
+}
+
+int mv88e6xxx_port_set_duplex(struct mv88e6xxx_chip *chip, int port, int dup)
+{
+ u16 reg;
+ int err;
+
+ err = mv88e6xxx_port_read(chip, port, PORT_PCS_CTRL, ®);
+ if (err)
+ return err;
+
+ reg &= ~(PORT_PCS_CTRL_FORCE_DUPLEX | PORT_PCS_CTRL_DUPLEX_FULL);
+
+ switch (dup) {
+ case DUPLEX_HALF:
+ reg |= PORT_PCS_CTRL_FORCE_DUPLEX;
+ break;
+ case DUPLEX_FULL:
+ reg |= PORT_PCS_CTRL_FORCE_DUPLEX | PORT_PCS_CTRL_DUPLEX_FULL;
+ break;
+ case DUPLEX_UNFORCED:
+ /* normal duplex detection */
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ err = mv88e6xxx_port_write(chip, port, PORT_PCS_CTRL, reg);
+ if (err)
+ return err;
+
+ netdev_dbg(chip->ds->ports[port].netdev, "%s %s duplex\n",
+ reg & PORT_PCS_CTRL_FORCE_DUPLEX ? "Force" : "Unforce",
+ reg & PORT_PCS_CTRL_DUPLEX_FULL ? "full" : "half");
+
+ return 0;
+}
+
+static int mv88e6xxx_port_set_speed(struct mv88e6xxx_chip *chip, int port,
+ int speed, bool alt_bit, bool force_bit)
+{
+ u16 reg, ctrl;
+ int err;
+
+ switch (speed) {
+ case 10:
+ ctrl = PORT_PCS_CTRL_SPEED_10;
+ break;
+ case 100:
+ ctrl = PORT_PCS_CTRL_SPEED_100;
+ break;
+ case 200:
+ if (alt_bit)
+ ctrl = PORT_PCS_CTRL_SPEED_100 | PORT_PCS_CTRL_ALTSPEED;
+ else
+ ctrl = PORT_PCS_CTRL_SPEED_200;
+ break;
+ case 1000:
+ ctrl = PORT_PCS_CTRL_SPEED_1000;
+ break;
+ case 2500:
+ ctrl = PORT_PCS_CTRL_SPEED_1000 | PORT_PCS_CTRL_ALTSPEED;
+ break;
+ case 10000:
+ /* all bits set, fall through... */
+ case SPEED_UNFORCED:
+ ctrl = PORT_PCS_CTRL_SPEED_UNFORCED;
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ err = mv88e6xxx_port_read(chip, port, PORT_PCS_CTRL, ®);
+ if (err)
+ return err;
+
+ reg &= ~PORT_PCS_CTRL_SPEED_MASK;
+ if (alt_bit)
+ reg &= ~PORT_PCS_CTRL_ALTSPEED;
+ if (force_bit) {
+ reg &= ~PORT_PCS_CTRL_FORCE_SPEED;
+ if (speed != SPEED_UNFORCED)
+ ctrl |= PORT_PCS_CTRL_FORCE_SPEED;
+ }
+ reg |= ctrl;
+
+ err = mv88e6xxx_port_write(chip, port, PORT_PCS_CTRL, reg);
+ if (err)
+ return err;
+
+ if (speed)
+ netdev_dbg(chip->ds->ports[port].netdev,
+ "Speed set to %d Mbps\n", speed);
+ else
+ netdev_dbg(chip->ds->ports[port].netdev, "Speed unforced\n");
+
+ return 0;
+}
+
+/* Support 10, 100, 200 Mbps (e.g. 88E6065 family) */
+int mv88e6065_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed)
+{
+ if (speed == SPEED_MAX)
+ speed = 200;
+
+ if (speed > 200)
+ return -EOPNOTSUPP;
+
+ /* Setting 200 Mbps on port 0 to 3 selects 100 Mbps */
+ return mv88e6xxx_port_set_speed(chip, port, speed, false, false);
+}
+
+/* Support 10, 100, 1000 Mbps (e.g. 88E6185 family) */
+int mv88e6185_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed)
+{
+ if (speed == SPEED_MAX)
+ speed = 1000;
+
+ if (speed == 200 || speed > 1000)
+ return -EOPNOTSUPP;
+
+ return mv88e6xxx_port_set_speed(chip, port, speed, false, false);
+}
+
+/* Support 10, 100, 200, 1000 Mbps (e.g. 88E6352 family) */
+int mv88e6352_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed)
+{
+ if (speed == SPEED_MAX)
+ speed = 1000;
+
+ if (speed > 1000)
+ return -EOPNOTSUPP;
+
+ if (speed == 200 && port < 5)
+ return -EOPNOTSUPP;
+
+ return mv88e6xxx_port_set_speed(chip, port, speed, true, false);
+}
+
+/* Support 10, 100, 200, 1000, 2500 Mbps (e.g. 88E6390) */
+int mv88e6390_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed)
+{
+ if (speed == SPEED_MAX)
+ speed = port < 9 ? 1000 : 2500;
+
+ if (speed > 2500)
+ return -EOPNOTSUPP;
+
+ if (speed == 200 && port != 0)
+ return -EOPNOTSUPP;
+
+ if (speed == 2500 && port < 9)
+ return -EOPNOTSUPP;
+
+ return mv88e6xxx_port_set_speed(chip, port, speed, true, true);
+}
+
+/* Support 10, 100, 200, 1000, 2500, 10000 Mbps (e.g. 88E6190X) */
+int mv88e6390x_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed)
+{
+ if (speed == SPEED_MAX)
+ speed = port < 9 ? 1000 : 10000;
+
+ if (speed == 200 && port != 0)
+ return -EOPNOTSUPP;
+
+ if (speed >= 2500 && port < 9)
+ return -EOPNOTSUPP;
+
+ return mv88e6xxx_port_set_speed(chip, port, speed, true, true);
+}
+
+/* Offset 0x04: Port Control Register */
+
+static const char * const mv88e6xxx_port_state_names[] = {
+ [PORT_CONTROL_STATE_DISABLED] = "Disabled",
+ [PORT_CONTROL_STATE_BLOCKING] = "Blocking/Listening",
+ [PORT_CONTROL_STATE_LEARNING] = "Learning",
+ [PORT_CONTROL_STATE_FORWARDING] = "Forwarding",
+};
+
+int mv88e6xxx_port_set_state(struct mv88e6xxx_chip *chip, int port, u8 state)
+{
+ u16 reg;
+ int err;
+
+ err = mv88e6xxx_port_read(chip, port, PORT_CONTROL, ®);
+ if (err)
+ return err;
+
+ reg &= ~PORT_CONTROL_STATE_MASK;
+ reg |= state;
+
+ err = mv88e6xxx_port_write(chip, port, PORT_CONTROL, reg);
+ if (err)
+ return err;
+
+ netdev_dbg(chip->ds->ports[port].netdev, "PortState set to %s\n",
+ mv88e6xxx_port_state_names[state]);
+
+ return 0;
+}
+
+/* Offset 0x05: Port Control 1 */
+
+/* Offset 0x06: Port Based VLAN Map */
+
+int mv88e6xxx_port_set_vlan_map(struct mv88e6xxx_chip *chip, int port, u16 map)
+{
+ const u16 mask = GENMASK(mv88e6xxx_num_ports(chip) - 1, 0);
+ u16 reg;
+ int err;
+
+ err = mv88e6xxx_port_read(chip, port, PORT_BASE_VLAN, ®);
+ if (err)
+ return err;
+
+ reg &= ~mask;
+ reg |= map & mask;
+
+ err = mv88e6xxx_port_write(chip, port, PORT_BASE_VLAN, reg);
+ if (err)
+ return err;
+
+ netdev_dbg(chip->ds->ports[port].netdev, "VLANTable set to %.3x\n",
+ map);
+
+ return 0;
+}
+
+int mv88e6xxx_port_get_fid(struct mv88e6xxx_chip *chip, int port, u16 *fid)
+{
+ const u16 upper_mask = (mv88e6xxx_num_databases(chip) - 1) >> 4;
+ u16 reg;
+ int err;
+
+ /* Port's default FID lower 4 bits are located in reg 0x06, offset 12 */
+ err = mv88e6xxx_port_read(chip, port, PORT_BASE_VLAN, ®);
+ if (err)
+ return err;
+
+ *fid = (reg & 0xf000) >> 12;
+
+ /* Port's default FID upper bits are located in reg 0x05, offset 0 */
+ if (upper_mask) {
+ err = mv88e6xxx_port_read(chip, port, PORT_CONTROL_1, ®);
+ if (err)
+ return err;
+
+ *fid |= (reg & upper_mask) << 4;
+ }
+
+ return 0;
+}
+
+int mv88e6xxx_port_set_fid(struct mv88e6xxx_chip *chip, int port, u16 fid)
+{
+ const u16 upper_mask = (mv88e6xxx_num_databases(chip) - 1) >> 4;
+ u16 reg;
+ int err;
+
+ if (fid >= mv88e6xxx_num_databases(chip))
+ return -EINVAL;
+
+ /* Port's default FID lower 4 bits are located in reg 0x06, offset 12 */
+ err = mv88e6xxx_port_read(chip, port, PORT_BASE_VLAN, ®);
+ if (err)
+ return err;
+
+ reg &= 0x0fff;
+ reg |= (fid & 0x000f) << 12;
+
+ err = mv88e6xxx_port_write(chip, port, PORT_BASE_VLAN, reg);
+ if (err)
+ return err;
+
+ /* Port's default FID upper bits are located in reg 0x05, offset 0 */
+ if (upper_mask) {
+ err = mv88e6xxx_port_read(chip, port, PORT_CONTROL_1, ®);
+ if (err)
+ return err;
+
+ reg &= ~upper_mask;
+ reg |= (fid >> 4) & upper_mask;
+
+ err = mv88e6xxx_port_write(chip, port, PORT_CONTROL_1, reg);
+ if (err)
+ return err;
+ }
+
+ netdev_dbg(chip->ds->ports[port].netdev, "FID set to %u\n", fid);
+
+ return 0;
+}
+
+/* Offset 0x07: Default Port VLAN ID & Priority */
+
+int mv88e6xxx_port_get_pvid(struct mv88e6xxx_chip *chip, int port, u16 *pvid)
+{
+ u16 reg;
+ int err;
+
+ err = mv88e6xxx_port_read(chip, port, PORT_DEFAULT_VLAN, ®);
+ if (err)
+ return err;
+
+ *pvid = reg & PORT_DEFAULT_VLAN_MASK;
+
+ return 0;
+}
+
+int mv88e6xxx_port_set_pvid(struct mv88e6xxx_chip *chip, int port, u16 pvid)
+{
+ u16 reg;
+ int err;
+
+ err = mv88e6xxx_port_read(chip, port, PORT_DEFAULT_VLAN, ®);
+ if (err)
+ return err;
+
+ reg &= ~PORT_DEFAULT_VLAN_MASK;
+ reg |= pvid & PORT_DEFAULT_VLAN_MASK;
+
+ err = mv88e6xxx_port_write(chip, port, PORT_DEFAULT_VLAN, reg);
+ if (err)
+ return err;
+
+ netdev_dbg(chip->ds->ports[port].netdev, "DefaultVID set to %u\n",
+ pvid);
+
+ return 0;
+}
+
+/* Offset 0x08: Port Control 2 Register */
+
+static const char * const mv88e6xxx_port_8021q_mode_names[] = {
+ [PORT_CONTROL_2_8021Q_DISABLED] = "Disabled",
+ [PORT_CONTROL_2_8021Q_FALLBACK] = "Fallback",
+ [PORT_CONTROL_2_8021Q_CHECK] = "Check",
+ [PORT_CONTROL_2_8021Q_SECURE] = "Secure",
+};
+
+int mv88e6xxx_port_set_8021q_mode(struct mv88e6xxx_chip *chip, int port,
+ u16 mode)
+{
+ u16 reg;
+ int err;
+
+ err = mv88e6xxx_port_read(chip, port, PORT_CONTROL_2, ®);
+ if (err)
+ return err;
+
+ reg &= ~PORT_CONTROL_2_8021Q_MASK;
+ reg |= mode & PORT_CONTROL_2_8021Q_MASK;
+
+ err = mv88e6xxx_port_write(chip, port, PORT_CONTROL_2, reg);
+ if (err)
+ return err;
+
+ netdev_dbg(chip->ds->ports[port].netdev, "802.1QMode set to %s\n",
+ mv88e6xxx_port_8021q_mode_names[mode]);
+
+ return 0;
+}
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
new file mode 100644
index 0000000..499129c
--- /dev/null
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -0,0 +1,52 @@
+/*
+ * Marvell 88E6xxx Switch Port Registers support
+ *
+ * Copyright (c) 2008 Marvell Semiconductor
+ *
+ * Copyright (c) 2016 Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _MV88E6XXX_PORT_H
+#define _MV88E6XXX_PORT_H
+
+#include "mv88e6xxx.h"
+
+int mv88e6xxx_port_read(struct mv88e6xxx_chip *chip, int port, int reg,
+ u16 *val);
+int mv88e6xxx_port_write(struct mv88e6xxx_chip *chip, int port, int reg,
+ u16 val);
+
+int mv88e6352_port_set_rgmii_delay(struct mv88e6xxx_chip *chip, int port,
+ phy_interface_t mode);
+int mv88e6390_port_set_rgmii_delay(struct mv88e6xxx_chip *chip, int port,
+ phy_interface_t mode);
+
+int mv88e6xxx_port_set_link(struct mv88e6xxx_chip *chip, int port, int link);
+
+int mv88e6xxx_port_set_duplex(struct mv88e6xxx_chip *chip, int port, int dup);
+
+int mv88e6065_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed);
+int mv88e6185_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed);
+int mv88e6352_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed);
+int mv88e6390_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed);
+int mv88e6390x_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed);
+
+int mv88e6xxx_port_set_state(struct mv88e6xxx_chip *chip, int port, u8 state);
+
+int mv88e6xxx_port_set_vlan_map(struct mv88e6xxx_chip *chip, int port, u16 map);
+
+int mv88e6xxx_port_get_fid(struct mv88e6xxx_chip *chip, int port, u16 *fid);
+int mv88e6xxx_port_set_fid(struct mv88e6xxx_chip *chip, int port, u16 fid);
+
+int mv88e6xxx_port_get_pvid(struct mv88e6xxx_chip *chip, int port, u16 *pvid);
+int mv88e6xxx_port_set_pvid(struct mv88e6xxx_chip *chip, int port, u16 pvid);
+
+int mv88e6xxx_port_set_8021q_mode(struct mv88e6xxx_chip *chip, int port,
+ u16 mode);
+
+#endif /* _MV88E6XXX_PORT_H */
diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c
index 9f9a5f4..a753378 100644
--- a/drivers/net/ethernet/3com/3c509.c
+++ b/drivers/net/ethernet/3com/3c509.c
@@ -1040,67 +1040,68 @@ el3_link_ok(struct net_device *dev)
}
static int
-el3_netdev_get_ecmd(struct net_device *dev, struct ethtool_cmd *ecmd)
+el3_netdev_get_ecmd(struct net_device *dev, struct ethtool_link_ksettings *cmd)
{
u16 tmp;
int ioaddr = dev->base_addr;
+ u32 supported;
EL3WINDOW(0);
/* obtain current transceiver via WN4_MEDIA? */
tmp = inw(ioaddr + WN0_ADDR_CONF);
- ecmd->transceiver = XCVR_INTERNAL;
switch (tmp >> 14) {
case 0:
- ecmd->port = PORT_TP;
+ cmd->base.port = PORT_TP;
break;
case 1:
- ecmd->port = PORT_AUI;
- ecmd->transceiver = XCVR_EXTERNAL;
+ cmd->base.port = PORT_AUI;
break;
case 3:
- ecmd->port = PORT_BNC;
+ cmd->base.port = PORT_BNC;
default:
break;
}
- ecmd->duplex = DUPLEX_HALF;
- ecmd->supported = 0;
+ cmd->base.duplex = DUPLEX_HALF;
+ supported = 0;
tmp = inw(ioaddr + WN0_CONF_CTRL);
if (tmp & (1<<13))
- ecmd->supported |= SUPPORTED_AUI;
+ supported |= SUPPORTED_AUI;
if (tmp & (1<<12))
- ecmd->supported |= SUPPORTED_BNC;
+ supported |= SUPPORTED_BNC;
if (tmp & (1<<9)) {
- ecmd->supported |= SUPPORTED_TP | SUPPORTED_10baseT_Half |
+ supported |= SUPPORTED_TP | SUPPORTED_10baseT_Half |
SUPPORTED_10baseT_Full; /* hmm... */
EL3WINDOW(4);
tmp = inw(ioaddr + WN4_NETDIAG);
if (tmp & FD_ENABLE)
- ecmd->duplex = DUPLEX_FULL;
+ cmd->base.duplex = DUPLEX_FULL;
}
- ethtool_cmd_speed_set(ecmd, SPEED_10);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ cmd->base.speed = SPEED_10;
EL3WINDOW(1);
return 0;
}
static int
-el3_netdev_set_ecmd(struct net_device *dev, struct ethtool_cmd *ecmd)
+el3_netdev_set_ecmd(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
u16 tmp;
int ioaddr = dev->base_addr;
- if (ecmd->speed != SPEED_10)
+ if (cmd->base.speed != SPEED_10)
return -EINVAL;
- if ((ecmd->duplex != DUPLEX_HALF) && (ecmd->duplex != DUPLEX_FULL))
- return -EINVAL;
- if ((ecmd->transceiver != XCVR_INTERNAL) && (ecmd->transceiver != XCVR_EXTERNAL))
+ if ((cmd->base.duplex != DUPLEX_HALF) &&
+ (cmd->base.duplex != DUPLEX_FULL))
return -EINVAL;
/* change XCVR type */
EL3WINDOW(0);
tmp = inw(ioaddr + WN0_ADDR_CONF);
- switch (ecmd->port) {
+ switch (cmd->base.port) {
case PORT_TP:
tmp &= ~(3<<14);
dev->if_port = 0;
@@ -1130,7 +1131,7 @@ el3_netdev_set_ecmd(struct net_device *dev, struct ethtool_cmd *ecmd)
EL3WINDOW(4);
tmp = inw(ioaddr + WN4_NETDIAG);
- if (ecmd->duplex == DUPLEX_FULL)
+ if (cmd->base.duplex == DUPLEX_FULL)
tmp |= FD_ENABLE;
else
tmp &= ~FD_ENABLE;
@@ -1146,24 +1147,26 @@ static void el3_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info
strlcpy(info->version, DRV_VERSION, sizeof(info->version));
}
-static int el3_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int el3_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct el3_private *lp = netdev_priv(dev);
int ret;
spin_lock_irq(&lp->lock);
- ret = el3_netdev_get_ecmd(dev, ecmd);
+ ret = el3_netdev_get_ecmd(dev, cmd);
spin_unlock_irq(&lp->lock);
return ret;
}
-static int el3_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int el3_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct el3_private *lp = netdev_priv(dev);
int ret;
spin_lock_irq(&lp->lock);
- ret = el3_netdev_set_ecmd(dev, ecmd);
+ ret = el3_netdev_set_ecmd(dev, cmd);
spin_unlock_irq(&lp->lock);
return ret;
}
@@ -1191,11 +1194,11 @@ static void el3_set_msglevel(struct net_device *dev, u32 v)
static const struct ethtool_ops ethtool_ops = {
.get_drvinfo = el3_get_drvinfo,
- .get_settings = el3_get_settings,
- .set_settings = el3_set_settings,
.get_link = el3_get_link,
.get_msglevel = el3_get_msglevel,
.set_msglevel = el3_set_msglevel,
+ .get_link_ksettings = el3_get_link_ksettings,
+ .set_link_ksettings = el3_set_link_ksettings,
};
static void
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 3ecf613..b3560a3 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -2907,18 +2907,20 @@ static int vortex_nway_reset(struct net_device *dev)
return mii_nway_restart(&vp->mii);
}
-static int vortex_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int vortex_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct vortex_private *vp = netdev_priv(dev);
- return mii_ethtool_gset(&vp->mii, cmd);
+ return mii_ethtool_get_link_ksettings(&vp->mii, cmd);
}
-static int vortex_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int vortex_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct vortex_private *vp = netdev_priv(dev);
- return mii_ethtool_sset(&vp->mii, cmd);
+ return mii_ethtool_set_link_ksettings(&vp->mii, cmd);
}
static u32 vortex_get_msglevel(struct net_device *dev)
@@ -3031,13 +3033,13 @@ static const struct ethtool_ops vortex_ethtool_ops = {
.set_msglevel = vortex_set_msglevel,
.get_ethtool_stats = vortex_get_ethtool_stats,
.get_sset_count = vortex_get_sset_count,
- .get_settings = vortex_get_settings,
- .set_settings = vortex_set_settings,
.get_link = ethtool_op_get_link,
.nway_reset = vortex_nway_reset,
.get_wol = vortex_get_wol,
.set_wol = vortex_set_wol,
.get_ts_info = ethtool_op_get_ts_info,
+ .get_link_ksettings = vortex_get_link_ksettings,
+ .set_link_ksettings = vortex_set_link_ksettings,
};
#ifdef CONFIG_PCI
diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c
index 506b507..a0cacbe 100644
--- a/drivers/net/ethernet/3com/typhoon.c
+++ b/drivers/net/ethernet/3com/typhoon.c
@@ -996,28 +996,30 @@ typhoon_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
}
static int
-typhoon_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+typhoon_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct typhoon *tp = netdev_priv(dev);
+ u32 supported, advertising = 0;
- cmd->supported = SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full |
+ supported = SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full |
SUPPORTED_Autoneg;
switch (tp->xcvr_select) {
case TYPHOON_XCVR_10HALF:
- cmd->advertising = ADVERTISED_10baseT_Half;
+ advertising = ADVERTISED_10baseT_Half;
break;
case TYPHOON_XCVR_10FULL:
- cmd->advertising = ADVERTISED_10baseT_Full;
+ advertising = ADVERTISED_10baseT_Full;
break;
case TYPHOON_XCVR_100HALF:
- cmd->advertising = ADVERTISED_100baseT_Half;
+ advertising = ADVERTISED_100baseT_Half;
break;
case TYPHOON_XCVR_100FULL:
- cmd->advertising = ADVERTISED_100baseT_Full;
+ advertising = ADVERTISED_100baseT_Full;
break;
case TYPHOON_XCVR_AUTONEG:
- cmd->advertising = ADVERTISED_10baseT_Half |
+ advertising = ADVERTISED_10baseT_Half |
ADVERTISED_10baseT_Full |
ADVERTISED_100baseT_Half |
ADVERTISED_100baseT_Full |
@@ -1026,54 +1028,57 @@ typhoon_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
}
if(tp->capabilities & TYPHOON_FIBER) {
- cmd->supported |= SUPPORTED_FIBRE;
- cmd->advertising |= ADVERTISED_FIBRE;
- cmd->port = PORT_FIBRE;
+ supported |= SUPPORTED_FIBRE;
+ advertising |= ADVERTISED_FIBRE;
+ cmd->base.port = PORT_FIBRE;
} else {
- cmd->supported |= SUPPORTED_10baseT_Half |
+ supported |= SUPPORTED_10baseT_Half |
SUPPORTED_10baseT_Full |
SUPPORTED_TP;
- cmd->advertising |= ADVERTISED_TP;
- cmd->port = PORT_TP;
+ advertising |= ADVERTISED_TP;
+ cmd->base.port = PORT_TP;
}
/* need to get stats to make these link speed/duplex valid */
typhoon_do_get_stats(tp);
- ethtool_cmd_speed_set(cmd, tp->speed);
- cmd->duplex = tp->duplex;
- cmd->phy_address = 0;
- cmd->transceiver = XCVR_INTERNAL;
+ cmd->base.speed = tp->speed;
+ cmd->base.duplex = tp->duplex;
+ cmd->base.phy_address = 0;
if(tp->xcvr_select == TYPHOON_XCVR_AUTONEG)
- cmd->autoneg = AUTONEG_ENABLE;
+ cmd->base.autoneg = AUTONEG_ENABLE;
else
- cmd->autoneg = AUTONEG_DISABLE;
- cmd->maxtxpkt = 1;
- cmd->maxrxpkt = 1;
+ cmd->base.autoneg = AUTONEG_DISABLE;
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
return 0;
}
static int
-typhoon_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+typhoon_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct typhoon *tp = netdev_priv(dev);
- u32 speed = ethtool_cmd_speed(cmd);
+ u32 speed = cmd->base.speed;
struct cmd_desc xp_cmd;
__le16 xcvr;
int err;
err = -EINVAL;
- if (cmd->autoneg == AUTONEG_ENABLE) {
+ if (cmd->base.autoneg == AUTONEG_ENABLE) {
xcvr = TYPHOON_XCVR_AUTONEG;
} else {
- if (cmd->duplex == DUPLEX_HALF) {
+ if (cmd->base.duplex == DUPLEX_HALF) {
if (speed == SPEED_10)
xcvr = TYPHOON_XCVR_10HALF;
else if (speed == SPEED_100)
xcvr = TYPHOON_XCVR_100HALF;
else
goto out;
- } else if (cmd->duplex == DUPLEX_FULL) {
+ } else if (cmd->base.duplex == DUPLEX_FULL) {
if (speed == SPEED_10)
xcvr = TYPHOON_XCVR_10FULL;
else if (speed == SPEED_100)
@@ -1091,12 +1096,12 @@ typhoon_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
goto out;
tp->xcvr_select = xcvr;
- if(cmd->autoneg == AUTONEG_ENABLE) {
+ if (cmd->base.autoneg == AUTONEG_ENABLE) {
tp->speed = 0xff; /* invalid */
tp->duplex = 0xff; /* invalid */
} else {
tp->speed = speed;
- tp->duplex = cmd->duplex;
+ tp->duplex = cmd->base.duplex;
}
out:
@@ -1145,13 +1150,13 @@ typhoon_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ering)
}
static const struct ethtool_ops typhoon_ethtool_ops = {
- .get_settings = typhoon_get_settings,
- .set_settings = typhoon_set_settings,
.get_drvinfo = typhoon_get_drvinfo,
.get_wol = typhoon_get_wol,
.set_wol = typhoon_set_wol,
.get_link = ethtool_op_get_link,
.get_ringparam = typhoon_get_ringparam,
+ .get_link_ksettings = typhoon_get_link_ksettings,
+ .set_link_ksettings = typhoon_set_link_ksettings,
};
static int
diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c
index 4a9a16e..3aaad33 100644
--- a/drivers/net/ethernet/adaptec/starfire.c
+++ b/drivers/net/ethernet/adaptec/starfire.c
@@ -1816,21 +1816,23 @@ static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
}
-static int get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct netdev_private *np = netdev_priv(dev);
spin_lock_irq(&np->lock);
- mii_ethtool_gset(&np->mii_if, ecmd);
+ mii_ethtool_get_link_ksettings(&np->mii_if, cmd);
spin_unlock_irq(&np->lock);
return 0;
}
-static int set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct netdev_private *np = netdev_priv(dev);
int res;
spin_lock_irq(&np->lock);
- res = mii_ethtool_sset(&np->mii_if, ecmd);
+ res = mii_ethtool_set_link_ksettings(&np->mii_if, cmd);
spin_unlock_irq(&np->lock);
check_duplex(dev);
return res;
@@ -1861,12 +1863,12 @@ static void set_msglevel(struct net_device *dev, u32 val)
static const struct ethtool_ops ethtool_ops = {
.begin = check_if_running,
.get_drvinfo = get_drvinfo,
- .get_settings = get_settings,
- .set_settings = set_settings,
.nway_reset = nway_reset,
.get_link = get_link,
.get_msglevel = get_msglevel,
.set_msglevel = set_msglevel,
+ .get_link_ksettings = get_link_ksettings,
+ .set_link_ksettings = set_link_ksettings,
};
static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c
index f8df824..93def92 100644
--- a/drivers/net/ethernet/aeroflex/greth.c
+++ b/drivers/net/ethernet/aeroflex/greth.c
@@ -1290,15 +1290,6 @@ static int greth_mdio_probe(struct net_device *dev)
return 0;
}
-static inline int phy_aneg_done(struct phy_device *phydev)
-{
- int retval;
-
- retval = phy_read(phydev, MII_BMSR);
-
- return (retval < 0) ? retval : (retval & BMSR_ANEGCOMPLETE);
-}
-
static int greth_mdio_init(struct greth_private *greth)
{
int ret;
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index af27f9d..c8f4d26 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -37,6 +37,11 @@
#define EMAC_MAX_FRAME_LEN 0x0600
+#define EMAC_DEFAULT_MSG_ENABLE 0x0000
+static int debug = -1; /* defaults above */;
+module_param(debug, int, 0);
+MODULE_PARM_DESC(debug, "debug message flags");
+
/* Transmit timeout, default 5 seconds. */
static int watchdog = 5000;
module_param(watchdog, int, 0400);
@@ -225,11 +230,27 @@ static void emac_get_drvinfo(struct net_device *dev,
strlcpy(info->bus_info, dev_name(&dev->dev), sizeof(info->bus_info));
}
+static u32 emac_get_msglevel(struct net_device *dev)
+{
+ struct emac_board_info *db = netdev_priv(dev);
+
+ return db->msg_enable;
+}
+
+static void emac_set_msglevel(struct net_device *dev, u32 value)
+{
+ struct emac_board_info *db = netdev_priv(dev);
+
+ db->msg_enable = value;
+}
+
static const struct ethtool_ops emac_ethtool_ops = {
.get_drvinfo = emac_get_drvinfo,
.get_link = ethtool_op_get_link,
.get_link_ksettings = phy_ethtool_get_link_ksettings,
.set_link_ksettings = phy_ethtool_set_link_ksettings,
+ .get_msglevel = emac_get_msglevel,
+ .set_msglevel = emac_set_msglevel,
};
static unsigned int emac_setup(struct net_device *ndev)
@@ -571,8 +592,7 @@ static void emac_rx(struct net_device *dev)
/* A packet ready now & Get status/length */
good_packet = true;
- emac_inblk_32bit(db->membase + EMAC_RX_IO_DATA_REG,
- &rxhdr, sizeof(rxhdr));
+ rxhdr = readl(db->membase + EMAC_RX_IO_DATA_REG);
if (netif_msg_rx_status(db))
dev_dbg(db->dev, "rxhdr: %x\n", *((int *)(&rxhdr)));
@@ -804,6 +824,7 @@ static int emac_probe(struct platform_device *pdev)
db->dev = &pdev->dev;
db->ndev = ndev;
db->pdev = pdev;
+ db->msg_enable = netif_msg_init(debug, EMAC_DEFAULT_MSG_ENABLE);
spin_lock_init(&db->lock);
diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c
index a5c1e29..16f0c70 100644
--- a/drivers/net/ethernet/alteon/acenic.c
+++ b/drivers/net/ethernet/alteon/acenic.c
@@ -429,14 +429,16 @@ static const char version[] =
"acenic.c: v0.92 08/05/2002 Jes Sorensen, linux-acenic@SunSITE.dk\n"
" http://home.cern.ch/~jes/gige/acenic.html\n";
-static int ace_get_settings(struct net_device *, struct ethtool_cmd *);
-static int ace_set_settings(struct net_device *, struct ethtool_cmd *);
+static int ace_get_link_ksettings(struct net_device *,
+ struct ethtool_link_ksettings *);
+static int ace_set_link_ksettings(struct net_device *,
+ const struct ethtool_link_ksettings *);
static void ace_get_drvinfo(struct net_device *, struct ethtool_drvinfo *);
static const struct ethtool_ops ace_ethtool_ops = {
- .get_settings = ace_get_settings,
- .set_settings = ace_set_settings,
.get_drvinfo = ace_get_drvinfo,
+ .get_link_ksettings = ace_get_link_ksettings,
+ .set_link_ksettings = ace_set_link_ksettings,
};
static void ace_watchdog(struct net_device *dev);
@@ -2579,43 +2581,44 @@ static int ace_change_mtu(struct net_device *dev, int new_mtu)
return 0;
}
-static int ace_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int ace_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct ace_private *ap = netdev_priv(dev);
struct ace_regs __iomem *regs = ap->regs;
u32 link;
+ u32 supported;
- memset(ecmd, 0, sizeof(struct ethtool_cmd));
- ecmd->supported =
- (SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full |
- SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full |
- SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full |
- SUPPORTED_Autoneg | SUPPORTED_FIBRE);
+ memset(cmd, 0, sizeof(struct ethtool_link_ksettings));
- ecmd->port = PORT_FIBRE;
- ecmd->transceiver = XCVR_INTERNAL;
+ supported = (SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full |
+ SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full |
+ SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full |
+ SUPPORTED_Autoneg | SUPPORTED_FIBRE);
+
+ cmd->base.port = PORT_FIBRE;
link = readl(®s->GigLnkState);
- if (link & LNK_1000MB)
- ethtool_cmd_speed_set(ecmd, SPEED_1000);
- else {
+ if (link & LNK_1000MB) {
+ cmd->base.speed = SPEED_1000;
+ } else {
link = readl(®s->FastLnkState);
if (link & LNK_100MB)
- ethtool_cmd_speed_set(ecmd, SPEED_100);
+ cmd->base.speed = SPEED_100;
else if (link & LNK_10MB)
- ethtool_cmd_speed_set(ecmd, SPEED_10);
+ cmd->base.speed = SPEED_10;
else
- ethtool_cmd_speed_set(ecmd, 0);
+ cmd->base.speed = 0;
}
if (link & LNK_FULL_DUPLEX)
- ecmd->duplex = DUPLEX_FULL;
+ cmd->base.duplex = DUPLEX_FULL;
else
- ecmd->duplex = DUPLEX_HALF;
+ cmd->base.duplex = DUPLEX_HALF;
if (link & LNK_NEGOTIATE)
- ecmd->autoneg = AUTONEG_ENABLE;
+ cmd->base.autoneg = AUTONEG_ENABLE;
else
- ecmd->autoneg = AUTONEG_DISABLE;
+ cmd->base.autoneg = AUTONEG_DISABLE;
#if 0
/*
@@ -2626,13 +2629,15 @@ static int ace_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
ecmd->txcoal = readl(®s->TuneTxCoalTicks);
ecmd->rxcoal = readl(®s->TuneRxCoalTicks);
#endif
- ecmd->maxtxpkt = readl(®s->TuneMaxTxDesc);
- ecmd->maxrxpkt = readl(®s->TuneMaxRxDesc);
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
return 0;
}
-static int ace_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int ace_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct ace_private *ap = netdev_priv(dev);
struct ace_regs __iomem *regs = ap->regs;
@@ -2655,11 +2660,11 @@ static int ace_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
LNK_RX_FLOW_CTL_Y | LNK_NEG_FCTL;
if (!ACE_IS_TIGON_I(ap))
link |= LNK_TX_FLOW_CTL_Y;
- if (ecmd->autoneg == AUTONEG_ENABLE)
+ if (cmd->base.autoneg == AUTONEG_ENABLE)
link |= LNK_NEGOTIATE;
- if (ethtool_cmd_speed(ecmd) != speed) {
+ if (cmd->base.speed != speed) {
link &= ~(LNK_1000MB | LNK_100MB | LNK_10MB);
- switch (ethtool_cmd_speed(ecmd)) {
+ switch (cmd->base.speed) {
case SPEED_1000:
link |= LNK_1000MB;
break;
@@ -2672,7 +2677,7 @@ static int ace_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
}
}
- if (ecmd->duplex == DUPLEX_FULL)
+ if (cmd->base.duplex == DUPLEX_FULL)
link |= LNK_FULL_DUPLEX;
if (link != ap->link) {
diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig
index 0038709..7ab6efb 100644
--- a/drivers/net/ethernet/amd/Kconfig
+++ b/drivers/net/ethernet/amd/Kconfig
@@ -173,11 +173,13 @@
config AMD_XGBE
tristate "AMD 10GbE Ethernet driver"
- depends on ((OF_NET && OF_ADDRESS) || ACPI) && HAS_IOMEM && HAS_DMA
- depends on ARM64 || COMPILE_TEST
+ depends on ((OF_NET && OF_ADDRESS) || ACPI || PCI) && HAS_IOMEM && HAS_DMA
+ depends on X86 || ARM64 || COMPILE_TEST
select BITREVERSE
select CRC32
select PTP_1588_CLOCK
+ select PHYLIB
+ select AMD_XGBE_HAVE_ECC if X86
---help---
This driver supports the AMD 10GbE Ethernet device found on an
AMD SoC.
@@ -195,4 +197,8 @@
If unsure, say N.
+config AMD_XGBE_HAVE_ECC
+ bool
+ default n
+
endif # NET_VENDOR_AMD
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index 84b4ffb..11cf1e3 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -1421,21 +1421,23 @@ static void amd8111e_get_regs(struct net_device *dev, struct ethtool_regs *regs,
amd8111e_read_regs(lp, buf);
}
-static int amd8111e_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int amd8111e_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct amd8111e_priv *lp = netdev_priv(dev);
spin_lock_irq(&lp->lock);
- mii_ethtool_gset(&lp->mii_if, ecmd);
+ mii_ethtool_get_link_ksettings(&lp->mii_if, cmd);
spin_unlock_irq(&lp->lock);
return 0;
}
-static int amd8111e_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
+static int amd8111e_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct amd8111e_priv *lp = netdev_priv(dev);
int res;
spin_lock_irq(&lp->lock);
- res = mii_ethtool_sset(&lp->mii_if, ecmd);
+ res = mii_ethtool_set_link_ksettings(&lp->mii_if, cmd);
spin_unlock_irq(&lp->lock);
return res;
}
@@ -1482,12 +1484,12 @@ static const struct ethtool_ops ops = {
.get_drvinfo = amd8111e_get_drvinfo,
.get_regs_len = amd8111e_get_regs_len,
.get_regs = amd8111e_get_regs,
- .get_settings = amd8111e_get_settings,
- .set_settings = amd8111e_set_settings,
.nway_reset = amd8111e_nway_reset,
.get_link = amd8111e_get_link,
.get_wol = amd8111e_get_wol,
.set_wol = amd8111e_set_wol,
+ .get_link_ksettings = amd8111e_get_link_ksettings,
+ .set_link_ksettings = amd8111e_set_link_ksettings,
};
/* This function handles all the ethtool ioctls. It gives driver info,
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index adc7ab9..41e58cc 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -677,7 +677,8 @@ static void pcnet32_poll_controller(struct net_device *dev)
}
#endif
-static int pcnet32_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int pcnet32_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct pcnet32_private *lp = netdev_priv(dev);
unsigned long flags;
@@ -685,14 +686,15 @@ static int pcnet32_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
if (lp->mii) {
spin_lock_irqsave(&lp->lock, flags);
- mii_ethtool_gset(&lp->mii_if, cmd);
+ mii_ethtool_get_link_ksettings(&lp->mii_if, cmd);
spin_unlock_irqrestore(&lp->lock, flags);
r = 0;
}
return r;
}
-static int pcnet32_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+static int pcnet32_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct pcnet32_private *lp = netdev_priv(dev);
unsigned long flags;
@@ -700,7 +702,7 @@ static int pcnet32_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
if (lp->mii) {
spin_lock_irqsave(&lp->lock, flags);
- r = mii_ethtool_sset(&lp->mii_if, cmd);
+ r = mii_ethtool_set_link_ksettings(&lp->mii_if, cmd);
spin_unlock_irqrestore(&lp->lock, flags);
}
return r;
@@ -1440,8 +1442,6 @@ static void pcnet32_get_regs(struct net_device *dev, struct ethtool_regs *regs,
}
static const struct ethtool_ops pcnet32_ethtool_ops = {
- .get_settings = pcnet32_get_settings,
- .set_settings = pcnet32_set_settings,
.get_drvinfo = pcnet32_get_drvinfo,
.get_msglevel = pcnet32_get_msglevel,
.set_msglevel = pcnet32_set_msglevel,
@@ -1455,6 +1455,8 @@ static const struct ethtool_ops pcnet32_ethtool_ops = {
.get_regs_len = pcnet32_get_regs_len,
.get_regs = pcnet32_get_regs,
.get_sset_count = pcnet32_get_sset_count,
+ .get_link_ksettings = pcnet32_get_link_ksettings,
+ .set_link_ksettings = pcnet32_set_link_ksettings,
};
/* only probes for non-PCI devices, the rest are handled by
diff --git a/drivers/net/ethernet/amd/xgbe/Makefile b/drivers/net/ethernet/amd/xgbe/Makefile
index 171a7e6..0dea8f5 100644
--- a/drivers/net/ethernet/amd/xgbe/Makefile
+++ b/drivers/net/ethernet/amd/xgbe/Makefile
@@ -2,7 +2,10 @@
amd-xgbe-objs := xgbe-main.o xgbe-drv.o xgbe-dev.o \
xgbe-desc.o xgbe-ethtool.o xgbe-mdio.o \
- xgbe-ptp.o
+ xgbe-ptp.o \
+ xgbe-i2c.o xgbe-phy-v1.o xgbe-phy-v2.o \
+ xgbe-platform.o
+amd-xgbe-$(CONFIG_PCI) += xgbe-pci.o
amd-xgbe-$(CONFIG_AMD_XGBE_DCB) += xgbe-dcb.o
amd-xgbe-$(CONFIG_DEBUG_FS) += xgbe-debugfs.o
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index bbef959..5b7ba25 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -159,6 +159,8 @@
#define DMA_ISR_MACIS_WIDTH 1
#define DMA_ISR_MTLIS_INDEX 16
#define DMA_ISR_MTLIS_WIDTH 1
+#define DMA_MR_INTM_INDEX 12
+#define DMA_MR_INTM_WIDTH 2
#define DMA_MR_SWR_INDEX 0
#define DMA_MR_SWR_WIDTH 1
#define DMA_SBMR_EAME_INDEX 11
@@ -309,6 +311,11 @@
#define MAC_HWF0R 0x011c
#define MAC_HWF1R 0x0120
#define MAC_HWF2R 0x0124
+#define MAC_MDIOSCAR 0x0200
+#define MAC_MDIOSCCDR 0x0204
+#define MAC_MDIOISR 0x0214
+#define MAC_MDIOIER 0x0218
+#define MAC_MDIOCL22R 0x0220
#define MAC_GPIOCR 0x0278
#define MAC_GPIOSR 0x027c
#define MAC_MACA0HR 0x0300
@@ -409,10 +416,34 @@
#define MAC_ISR_MMCTXIS_WIDTH 1
#define MAC_ISR_PMTIS_INDEX 4
#define MAC_ISR_PMTIS_WIDTH 1
+#define MAC_ISR_SMI_INDEX 1
+#define MAC_ISR_SMI_WIDTH 1
#define MAC_ISR_TSIS_INDEX 12
#define MAC_ISR_TSIS_WIDTH 1
#define MAC_MACA1HR_AE_INDEX 31
#define MAC_MACA1HR_AE_WIDTH 1
+#define MAC_MDIOIER_SNGLCOMPIE_INDEX 12
+#define MAC_MDIOIER_SNGLCOMPIE_WIDTH 1
+#define MAC_MDIOISR_SNGLCOMPINT_INDEX 12
+#define MAC_MDIOISR_SNGLCOMPINT_WIDTH 1
+#define MAC_MDIOSCAR_DA_INDEX 21
+#define MAC_MDIOSCAR_DA_WIDTH 5
+#define MAC_MDIOSCAR_PA_INDEX 16
+#define MAC_MDIOSCAR_PA_WIDTH 5
+#define MAC_MDIOSCAR_RA_INDEX 0
+#define MAC_MDIOSCAR_RA_WIDTH 16
+#define MAC_MDIOSCAR_REG_INDEX 0
+#define MAC_MDIOSCAR_REG_WIDTH 21
+#define MAC_MDIOSCCDR_BUSY_INDEX 22
+#define MAC_MDIOSCCDR_BUSY_WIDTH 1
+#define MAC_MDIOSCCDR_CMD_INDEX 16
+#define MAC_MDIOSCCDR_CMD_WIDTH 2
+#define MAC_MDIOSCCDR_CR_INDEX 19
+#define MAC_MDIOSCCDR_CR_WIDTH 3
+#define MAC_MDIOSCCDR_DATA_INDEX 0
+#define MAC_MDIOSCCDR_DATA_WIDTH 16
+#define MAC_MDIOSCCDR_SADDR_INDEX 18
+#define MAC_MDIOSCCDR_SADDR_WIDTH 1
#define MAC_PFR_HMC_INDEX 2
#define MAC_PFR_HMC_WIDTH 1
#define MAC_PFR_HPF_INDEX 10
@@ -790,6 +821,10 @@
#define MTL_Q_RQOMR_RSF_WIDTH 1
#define MTL_Q_RQOMR_RTC_INDEX 0
#define MTL_Q_RQOMR_RTC_WIDTH 2
+#define MTL_Q_TQDR_TRCSTS_INDEX 1
+#define MTL_Q_TQDR_TRCSTS_WIDTH 2
+#define MTL_Q_TQDR_TXQSTS_INDEX 4
+#define MTL_Q_TQDR_TXQSTS_WIDTH 1
#define MTL_Q_TQOMR_FTQ_INDEX 0
#define MTL_Q_TQOMR_FTQ_WIDTH 1
#define MTL_Q_TQOMR_Q2TCMAP_INDEX 8
@@ -852,14 +887,16 @@
#define MTL_TSA_SP 0x00
#define MTL_TSA_ETS 0x02
-/* PCS MMD select register offset
- * The MMD select register is used for accessing PCS registers
- * when the underlying APB3 interface is using indirect addressing.
- * Indirect addressing requires accessing registers in two phases,
- * an address phase and a data phase. The address phases requires
- * writing an address selection value to the MMD select regiesters.
- */
-#define PCS_MMD_SELECT 0xff
+/* PCS register offsets */
+#define PCS_V1_WINDOW_SELECT 0x03fc
+#define PCS_V2_WINDOW_DEF 0x9060
+#define PCS_V2_WINDOW_SELECT 0x9064
+
+/* PCS register entry bit positions and sizes */
+#define PCS_V2_WINDOW_DEF_OFFSET_INDEX 6
+#define PCS_V2_WINDOW_DEF_OFFSET_WIDTH 14
+#define PCS_V2_WINDOW_DEF_SIZE_INDEX 2
+#define PCS_V2_WINDOW_DEF_SIZE_WIDTH 4
/* SerDes integration register offsets */
#define SIR0_KR_RT_1 0x002c
@@ -903,6 +940,198 @@
#define RXTX_REG129_RXDFE_CONFIG_INDEX 14
#define RXTX_REG129_RXDFE_CONFIG_WIDTH 2
+/* MAC Control register offsets */
+#define XP_PROP_0 0x0000
+#define XP_PROP_1 0x0004
+#define XP_PROP_2 0x0008
+#define XP_PROP_3 0x000c
+#define XP_PROP_4 0x0010
+#define XP_PROP_5 0x0014
+#define XP_MAC_ADDR_LO 0x0020
+#define XP_MAC_ADDR_HI 0x0024
+#define XP_ECC_ISR 0x0030
+#define XP_ECC_IER 0x0034
+#define XP_ECC_CNT0 0x003c
+#define XP_ECC_CNT1 0x0040
+#define XP_DRIVER_INT_REQ 0x0060
+#define XP_DRIVER_INT_RO 0x0064
+#define XP_DRIVER_SCRATCH_0 0x0068
+#define XP_DRIVER_SCRATCH_1 0x006c
+#define XP_INT_EN 0x0078
+#define XP_I2C_MUTEX 0x0080
+#define XP_MDIO_MUTEX 0x0084
+
+/* MAC Control register entry bit positions and sizes */
+#define XP_DRIVER_INT_REQ_REQUEST_INDEX 0
+#define XP_DRIVER_INT_REQ_REQUEST_WIDTH 1
+#define XP_DRIVER_INT_RO_STATUS_INDEX 0
+#define XP_DRIVER_INT_RO_STATUS_WIDTH 1
+#define XP_DRIVER_SCRATCH_0_COMMAND_INDEX 0
+#define XP_DRIVER_SCRATCH_0_COMMAND_WIDTH 8
+#define XP_DRIVER_SCRATCH_0_SUB_COMMAND_INDEX 8
+#define XP_DRIVER_SCRATCH_0_SUB_COMMAND_WIDTH 8
+#define XP_ECC_CNT0_RX_DED_INDEX 24
+#define XP_ECC_CNT0_RX_DED_WIDTH 8
+#define XP_ECC_CNT0_RX_SEC_INDEX 16
+#define XP_ECC_CNT0_RX_SEC_WIDTH 8
+#define XP_ECC_CNT0_TX_DED_INDEX 8
+#define XP_ECC_CNT0_TX_DED_WIDTH 8
+#define XP_ECC_CNT0_TX_SEC_INDEX 0
+#define XP_ECC_CNT0_TX_SEC_WIDTH 8
+#define XP_ECC_CNT1_DESC_DED_INDEX 8
+#define XP_ECC_CNT1_DESC_DED_WIDTH 8
+#define XP_ECC_CNT1_DESC_SEC_INDEX 0
+#define XP_ECC_CNT1_DESC_SEC_WIDTH 8
+#define XP_ECC_IER_DESC_DED_INDEX 0
+#define XP_ECC_IER_DESC_DED_WIDTH 1
+#define XP_ECC_IER_DESC_SEC_INDEX 1
+#define XP_ECC_IER_DESC_SEC_WIDTH 1
+#define XP_ECC_IER_RX_DED_INDEX 2
+#define XP_ECC_IER_RX_DED_WIDTH 1
+#define XP_ECC_IER_RX_SEC_INDEX 3
+#define XP_ECC_IER_RX_SEC_WIDTH 1
+#define XP_ECC_IER_TX_DED_INDEX 4
+#define XP_ECC_IER_TX_DED_WIDTH 1
+#define XP_ECC_IER_TX_SEC_INDEX 5
+#define XP_ECC_IER_TX_SEC_WIDTH 1
+#define XP_ECC_ISR_DESC_DED_INDEX 0
+#define XP_ECC_ISR_DESC_DED_WIDTH 1
+#define XP_ECC_ISR_DESC_SEC_INDEX 1
+#define XP_ECC_ISR_DESC_SEC_WIDTH 1
+#define XP_ECC_ISR_RX_DED_INDEX 2
+#define XP_ECC_ISR_RX_DED_WIDTH 1
+#define XP_ECC_ISR_RX_SEC_INDEX 3
+#define XP_ECC_ISR_RX_SEC_WIDTH 1
+#define XP_ECC_ISR_TX_DED_INDEX 4
+#define XP_ECC_ISR_TX_DED_WIDTH 1
+#define XP_ECC_ISR_TX_SEC_INDEX 5
+#define XP_ECC_ISR_TX_SEC_WIDTH 1
+#define XP_I2C_MUTEX_BUSY_INDEX 31
+#define XP_I2C_MUTEX_BUSY_WIDTH 1
+#define XP_I2C_MUTEX_ID_INDEX 29
+#define XP_I2C_MUTEX_ID_WIDTH 2
+#define XP_I2C_MUTEX_ACTIVE_INDEX 0
+#define XP_I2C_MUTEX_ACTIVE_WIDTH 1
+#define XP_MAC_ADDR_HI_VALID_INDEX 31
+#define XP_MAC_ADDR_HI_VALID_WIDTH 1
+#define XP_PROP_0_CONN_TYPE_INDEX 28
+#define XP_PROP_0_CONN_TYPE_WIDTH 3
+#define XP_PROP_0_MDIO_ADDR_INDEX 16
+#define XP_PROP_0_MDIO_ADDR_WIDTH 5
+#define XP_PROP_0_PORT_ID_INDEX 0
+#define XP_PROP_0_PORT_ID_WIDTH 8
+#define XP_PROP_0_PORT_MODE_INDEX 8
+#define XP_PROP_0_PORT_MODE_WIDTH 4
+#define XP_PROP_0_PORT_SPEEDS_INDEX 23
+#define XP_PROP_0_PORT_SPEEDS_WIDTH 4
+#define XP_PROP_1_MAX_RX_DMA_INDEX 24
+#define XP_PROP_1_MAX_RX_DMA_WIDTH 5
+#define XP_PROP_1_MAX_RX_QUEUES_INDEX 8
+#define XP_PROP_1_MAX_RX_QUEUES_WIDTH 5
+#define XP_PROP_1_MAX_TX_DMA_INDEX 16
+#define XP_PROP_1_MAX_TX_DMA_WIDTH 5
+#define XP_PROP_1_MAX_TX_QUEUES_INDEX 0
+#define XP_PROP_1_MAX_TX_QUEUES_WIDTH 5
+#define XP_PROP_2_RX_FIFO_SIZE_INDEX 16
+#define XP_PROP_2_RX_FIFO_SIZE_WIDTH 16
+#define XP_PROP_2_TX_FIFO_SIZE_INDEX 0
+#define XP_PROP_2_TX_FIFO_SIZE_WIDTH 16
+#define XP_PROP_3_GPIO_MASK_INDEX 28
+#define XP_PROP_3_GPIO_MASK_WIDTH 4
+#define XP_PROP_3_GPIO_MOD_ABS_INDEX 20
+#define XP_PROP_3_GPIO_MOD_ABS_WIDTH 4
+#define XP_PROP_3_GPIO_RATE_SELECT_INDEX 16
+#define XP_PROP_3_GPIO_RATE_SELECT_WIDTH 4
+#define XP_PROP_3_GPIO_RX_LOS_INDEX 24
+#define XP_PROP_3_GPIO_RX_LOS_WIDTH 4
+#define XP_PROP_3_GPIO_TX_FAULT_INDEX 12
+#define XP_PROP_3_GPIO_TX_FAULT_WIDTH 4
+#define XP_PROP_3_GPIO_ADDR_INDEX 8
+#define XP_PROP_3_GPIO_ADDR_WIDTH 3
+#define XP_PROP_3_MDIO_RESET_INDEX 0
+#define XP_PROP_3_MDIO_RESET_WIDTH 2
+#define XP_PROP_3_MDIO_RESET_I2C_ADDR_INDEX 8
+#define XP_PROP_3_MDIO_RESET_I2C_ADDR_WIDTH 3
+#define XP_PROP_3_MDIO_RESET_I2C_GPIO_INDEX 12
+#define XP_PROP_3_MDIO_RESET_I2C_GPIO_WIDTH 4
+#define XP_PROP_3_MDIO_RESET_INT_GPIO_INDEX 4
+#define XP_PROP_3_MDIO_RESET_INT_GPIO_WIDTH 2
+#define XP_PROP_4_MUX_ADDR_HI_INDEX 8
+#define XP_PROP_4_MUX_ADDR_HI_WIDTH 5
+#define XP_PROP_4_MUX_ADDR_LO_INDEX 0
+#define XP_PROP_4_MUX_ADDR_LO_WIDTH 3
+#define XP_PROP_4_MUX_CHAN_INDEX 4
+#define XP_PROP_4_MUX_CHAN_WIDTH 3
+#define XP_PROP_4_REDRV_ADDR_INDEX 16
+#define XP_PROP_4_REDRV_ADDR_WIDTH 7
+#define XP_PROP_4_REDRV_IF_INDEX 23
+#define XP_PROP_4_REDRV_IF_WIDTH 1
+#define XP_PROP_4_REDRV_LANE_INDEX 24
+#define XP_PROP_4_REDRV_LANE_WIDTH 3
+#define XP_PROP_4_REDRV_MODEL_INDEX 28
+#define XP_PROP_4_REDRV_MODEL_WIDTH 3
+#define XP_PROP_4_REDRV_PRESENT_INDEX 31
+#define XP_PROP_4_REDRV_PRESENT_WIDTH 1
+
+/* I2C Control register offsets */
+#define IC_CON 0x0000
+#define IC_TAR 0x0004
+#define IC_DATA_CMD 0x0010
+#define IC_INTR_STAT 0x002c
+#define IC_INTR_MASK 0x0030
+#define IC_RAW_INTR_STAT 0x0034
+#define IC_CLR_INTR 0x0040
+#define IC_CLR_TX_ABRT 0x0054
+#define IC_CLR_STOP_DET 0x0060
+#define IC_ENABLE 0x006c
+#define IC_TXFLR 0x0074
+#define IC_RXFLR 0x0078
+#define IC_TX_ABRT_SOURCE 0x0080
+#define IC_ENABLE_STATUS 0x009c
+#define IC_COMP_PARAM_1 0x00f4
+
+/* I2C Control register entry bit positions and sizes */
+#define IC_COMP_PARAM_1_MAX_SPEED_MODE_INDEX 2
+#define IC_COMP_PARAM_1_MAX_SPEED_MODE_WIDTH 2
+#define IC_COMP_PARAM_1_RX_BUFFER_DEPTH_INDEX 8
+#define IC_COMP_PARAM_1_RX_BUFFER_DEPTH_WIDTH 8
+#define IC_COMP_PARAM_1_TX_BUFFER_DEPTH_INDEX 16
+#define IC_COMP_PARAM_1_TX_BUFFER_DEPTH_WIDTH 8
+#define IC_CON_MASTER_MODE_INDEX 0
+#define IC_CON_MASTER_MODE_WIDTH 1
+#define IC_CON_RESTART_EN_INDEX 5
+#define IC_CON_RESTART_EN_WIDTH 1
+#define IC_CON_RX_FIFO_FULL_HOLD_INDEX 9
+#define IC_CON_RX_FIFO_FULL_HOLD_WIDTH 1
+#define IC_CON_SLAVE_DISABLE_INDEX 6
+#define IC_CON_SLAVE_DISABLE_WIDTH 1
+#define IC_CON_SPEED_INDEX 1
+#define IC_CON_SPEED_WIDTH 2
+#define IC_DATA_CMD_CMD_INDEX 8
+#define IC_DATA_CMD_CMD_WIDTH 1
+#define IC_DATA_CMD_STOP_INDEX 9
+#define IC_DATA_CMD_STOP_WIDTH 1
+#define IC_ENABLE_ABORT_INDEX 1
+#define IC_ENABLE_ABORT_WIDTH 1
+#define IC_ENABLE_EN_INDEX 0
+#define IC_ENABLE_EN_WIDTH 1
+#define IC_ENABLE_STATUS_EN_INDEX 0
+#define IC_ENABLE_STATUS_EN_WIDTH 1
+#define IC_INTR_MASK_TX_EMPTY_INDEX 4
+#define IC_INTR_MASK_TX_EMPTY_WIDTH 1
+#define IC_RAW_INTR_STAT_RX_FULL_INDEX 2
+#define IC_RAW_INTR_STAT_RX_FULL_WIDTH 1
+#define IC_RAW_INTR_STAT_STOP_DET_INDEX 9
+#define IC_RAW_INTR_STAT_STOP_DET_WIDTH 1
+#define IC_RAW_INTR_STAT_TX_ABRT_INDEX 6
+#define IC_RAW_INTR_STAT_TX_ABRT_WIDTH 1
+#define IC_RAW_INTR_STAT_TX_EMPTY_INDEX 4
+#define IC_RAW_INTR_STAT_TX_EMPTY_WIDTH 1
+
+/* I2C Control register value */
+#define IC_TX_ABRT_7B_ADDR_NOACK 0x0001
+#define IC_TX_ABRT_ARB_LOST 0x1000
+
/* Descriptor/Packet entry bit positions and sizes */
#define RX_PACKET_ERRORS_CRC_INDEX 2
#define RX_PACKET_ERRORS_CRC_WIDTH 1
@@ -1027,6 +1256,10 @@
#define MDIO_PMA_10GBR_FECCTRL 0x00ab
#endif
+#ifndef MDIO_PCS_DIG_CTRL
+#define MDIO_PCS_DIG_CTRL 0x8000
+#endif
+
#ifndef MDIO_AN_XNP
#define MDIO_AN_XNP 0x0016
#endif
@@ -1047,11 +1280,48 @@
#define MDIO_AN_INT 0x8002
#endif
+#ifndef MDIO_VEND2_AN_ADVERTISE
+#define MDIO_VEND2_AN_ADVERTISE 0x0004
+#endif
+
+#ifndef MDIO_VEND2_AN_LP_ABILITY
+#define MDIO_VEND2_AN_LP_ABILITY 0x0005
+#endif
+
+#ifndef MDIO_VEND2_AN_CTRL
+#define MDIO_VEND2_AN_CTRL 0x8001
+#endif
+
+#ifndef MDIO_VEND2_AN_STAT
+#define MDIO_VEND2_AN_STAT 0x8002
+#endif
+
#ifndef MDIO_CTRL1_SPEED1G
#define MDIO_CTRL1_SPEED1G (MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100)
#endif
+#ifndef MDIO_VEND2_CTRL1_AN_ENABLE
+#define MDIO_VEND2_CTRL1_AN_ENABLE BIT(12)
+#endif
+
+#ifndef MDIO_VEND2_CTRL1_AN_RESTART
+#define MDIO_VEND2_CTRL1_AN_RESTART BIT(9)
+#endif
+
+#ifndef MDIO_VEND2_CTRL1_SS6
+#define MDIO_VEND2_CTRL1_SS6 BIT(6)
+#endif
+
+#ifndef MDIO_VEND2_CTRL1_SS13
+#define MDIO_VEND2_CTRL1_SS13 BIT(13)
+#endif
+
/* MDIO mask values */
+#define XGBE_AN_CL73_INT_CMPLT BIT(0)
+#define XGBE_AN_CL73_INC_LINK BIT(1)
+#define XGBE_AN_CL73_PG_RCV BIT(2)
+#define XGBE_AN_CL73_INT_MASK 0x07
+
#define XGBE_XNP_MCF_NULL_MESSAGE 0x001
#define XGBE_XNP_ACK_PROCESSED BIT(12)
#define XGBE_XNP_MP_FORMATTED BIT(13)
@@ -1060,6 +1330,19 @@
#define XGBE_KR_TRAINING_START BIT(0)
#define XGBE_KR_TRAINING_ENABLE BIT(1)
+#define XGBE_PCS_CL37_BP BIT(12)
+
+#define XGBE_AN_CL37_INT_CMPLT BIT(0)
+#define XGBE_AN_CL37_INT_MASK 0x01
+
+#define XGBE_AN_CL37_HD_MASK 0x40
+#define XGBE_AN_CL37_FD_MASK 0x20
+
+#define XGBE_AN_CL37_PCS_MODE_MASK 0x06
+#define XGBE_AN_CL37_PCS_MODE_BASEX 0x00
+#define XGBE_AN_CL37_PCS_MODE_SGMII 0x04
+#define XGBE_AN_CL37_TX_CONFIG_MASK 0x08
+
/* Bit setting and getting macros
* The get macro will extract the current bit field value from within
* the variable
@@ -1195,12 +1478,28 @@ do { \
/* Macros for building, reading or writing register values or bits
* within the register values of XPCS registers.
*/
-#define XPCS_IOWRITE(_pdata, _off, _val) \
+#define XPCS_GET_BITS(_var, _prefix, _field) \
+ GET_BITS((_var), \
+ _prefix##_##_field##_INDEX, \
+ _prefix##_##_field##_WIDTH)
+
+#define XPCS_SET_BITS(_var, _prefix, _field, _val) \
+ SET_BITS((_var), \
+ _prefix##_##_field##_INDEX, \
+ _prefix##_##_field##_WIDTH, (_val))
+
+#define XPCS32_IOWRITE(_pdata, _off, _val) \
iowrite32(_val, (_pdata)->xpcs_regs + (_off))
-#define XPCS_IOREAD(_pdata, _off) \
+#define XPCS32_IOREAD(_pdata, _off) \
ioread32((_pdata)->xpcs_regs + (_off))
+#define XPCS16_IOWRITE(_pdata, _off, _val) \
+ iowrite16(_val, (_pdata)->xpcs_regs + (_off))
+
+#define XPCS16_IOREAD(_pdata, _off) \
+ ioread16((_pdata)->xpcs_regs + (_off))
+
/* Macros for building, reading or writing register values or bits
* within the register values of SerDes integration registers.
*/
@@ -1278,6 +1577,72 @@ do { \
} while (0)
/* Macros for building, reading or writing register values or bits
+ * within the register values of MAC Control registers.
+ */
+#define XP_GET_BITS(_var, _prefix, _field) \
+ GET_BITS((_var), \
+ _prefix##_##_field##_INDEX, \
+ _prefix##_##_field##_WIDTH)
+
+#define XP_SET_BITS(_var, _prefix, _field, _val) \
+ SET_BITS((_var), \
+ _prefix##_##_field##_INDEX, \
+ _prefix##_##_field##_WIDTH, (_val))
+
+#define XP_IOREAD(_pdata, _reg) \
+ ioread32((_pdata)->xprop_regs + (_reg))
+
+#define XP_IOREAD_BITS(_pdata, _reg, _field) \
+ GET_BITS(XP_IOREAD((_pdata), (_reg)), \
+ _reg##_##_field##_INDEX, \
+ _reg##_##_field##_WIDTH)
+
+#define XP_IOWRITE(_pdata, _reg, _val) \
+ iowrite32((_val), (_pdata)->xprop_regs + (_reg))
+
+#define XP_IOWRITE_BITS(_pdata, _reg, _field, _val) \
+do { \
+ u32 reg_val = XP_IOREAD((_pdata), (_reg)); \
+ SET_BITS(reg_val, \
+ _reg##_##_field##_INDEX, \
+ _reg##_##_field##_WIDTH, (_val)); \
+ XP_IOWRITE((_pdata), (_reg), reg_val); \
+} while (0)
+
+/* Macros for building, reading or writing register values or bits
+ * within the register values of I2C Control registers.
+ */
+#define XI2C_GET_BITS(_var, _prefix, _field) \
+ GET_BITS((_var), \
+ _prefix##_##_field##_INDEX, \
+ _prefix##_##_field##_WIDTH)
+
+#define XI2C_SET_BITS(_var, _prefix, _field, _val) \
+ SET_BITS((_var), \
+ _prefix##_##_field##_INDEX, \
+ _prefix##_##_field##_WIDTH, (_val))
+
+#define XI2C_IOREAD(_pdata, _reg) \
+ ioread32((_pdata)->xi2c_regs + (_reg))
+
+#define XI2C_IOREAD_BITS(_pdata, _reg, _field) \
+ GET_BITS(XI2C_IOREAD((_pdata), (_reg)), \
+ _reg##_##_field##_INDEX, \
+ _reg##_##_field##_WIDTH)
+
+#define XI2C_IOWRITE(_pdata, _reg, _val) \
+ iowrite32((_val), (_pdata)->xi2c_regs + (_reg))
+
+#define XI2C_IOWRITE_BITS(_pdata, _reg, _field, _val) \
+do { \
+ u32 reg_val = XI2C_IOREAD((_pdata), (_reg)); \
+ SET_BITS(reg_val, \
+ _reg##_##_field##_INDEX, \
+ _reg##_##_field##_WIDTH, (_val)); \
+ XI2C_IOWRITE((_pdata), (_reg), reg_val); \
+} while (0)
+
+/* Macros for building, reading or writing register values or bits
* using MDIO. Different from above because of the use of standardized
* Linux include values. No shifting is performed with the bit
* operations, everything works on mask values.
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
index 96f485a..7546b66 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
@@ -153,7 +153,7 @@ static ssize_t xgbe_common_write(const char __user *buffer, size_t count,
int ret;
if (*ppos != 0)
- return 0;
+ return -EINVAL;
if (count >= sizeof(workarea))
return -ENOSPC;
@@ -316,6 +316,126 @@ static const struct file_operations xpcs_reg_value_fops = {
.write = xpcs_reg_value_write,
};
+static ssize_t xprop_reg_addr_read(struct file *filp, char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct xgbe_prv_data *pdata = filp->private_data;
+
+ return xgbe_common_read(buffer, count, ppos, pdata->debugfs_xprop_reg);
+}
+
+static ssize_t xprop_reg_addr_write(struct file *filp,
+ const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct xgbe_prv_data *pdata = filp->private_data;
+
+ return xgbe_common_write(buffer, count, ppos,
+ &pdata->debugfs_xprop_reg);
+}
+
+static ssize_t xprop_reg_value_read(struct file *filp, char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct xgbe_prv_data *pdata = filp->private_data;
+ unsigned int value;
+
+ value = XP_IOREAD(pdata, pdata->debugfs_xprop_reg);
+
+ return xgbe_common_read(buffer, count, ppos, value);
+}
+
+static ssize_t xprop_reg_value_write(struct file *filp,
+ const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct xgbe_prv_data *pdata = filp->private_data;
+ unsigned int value;
+ ssize_t len;
+
+ len = xgbe_common_write(buffer, count, ppos, &value);
+ if (len < 0)
+ return len;
+
+ XP_IOWRITE(pdata, pdata->debugfs_xprop_reg, value);
+
+ return len;
+}
+
+static const struct file_operations xprop_reg_addr_fops = {
+ .owner = THIS_MODULE,
+ .open = simple_open,
+ .read = xprop_reg_addr_read,
+ .write = xprop_reg_addr_write,
+};
+
+static const struct file_operations xprop_reg_value_fops = {
+ .owner = THIS_MODULE,
+ .open = simple_open,
+ .read = xprop_reg_value_read,
+ .write = xprop_reg_value_write,
+};
+
+static ssize_t xi2c_reg_addr_read(struct file *filp, char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct xgbe_prv_data *pdata = filp->private_data;
+
+ return xgbe_common_read(buffer, count, ppos, pdata->debugfs_xi2c_reg);
+}
+
+static ssize_t xi2c_reg_addr_write(struct file *filp,
+ const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct xgbe_prv_data *pdata = filp->private_data;
+
+ return xgbe_common_write(buffer, count, ppos,
+ &pdata->debugfs_xi2c_reg);
+}
+
+static ssize_t xi2c_reg_value_read(struct file *filp, char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct xgbe_prv_data *pdata = filp->private_data;
+ unsigned int value;
+
+ value = XI2C_IOREAD(pdata, pdata->debugfs_xi2c_reg);
+
+ return xgbe_common_read(buffer, count, ppos, value);
+}
+
+static ssize_t xi2c_reg_value_write(struct file *filp,
+ const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ struct xgbe_prv_data *pdata = filp->private_data;
+ unsigned int value;
+ ssize_t len;
+
+ len = xgbe_common_write(buffer, count, ppos, &value);
+ if (len < 0)
+ return len;
+
+ XI2C_IOWRITE(pdata, pdata->debugfs_xi2c_reg, value);
+
+ return len;
+}
+
+static const struct file_operations xi2c_reg_addr_fops = {
+ .owner = THIS_MODULE,
+ .open = simple_open,
+ .read = xi2c_reg_addr_read,
+ .write = xi2c_reg_addr_write,
+};
+
+static const struct file_operations xi2c_reg_value_fops = {
+ .owner = THIS_MODULE,
+ .open = simple_open,
+ .read = xi2c_reg_value_read,
+ .write = xi2c_reg_value_write,
+};
+
void xgbe_debugfs_init(struct xgbe_prv_data *pdata)
{
struct dentry *pfile;
@@ -367,6 +487,38 @@ void xgbe_debugfs_init(struct xgbe_prv_data *pdata)
if (!pfile)
netdev_err(pdata->netdev, "debugfs_create_file failed\n");
+ if (pdata->xprop_regs) {
+ pfile = debugfs_create_file("xprop_register", 0600,
+ pdata->xgbe_debugfs, pdata,
+ &xprop_reg_addr_fops);
+ if (!pfile)
+ netdev_err(pdata->netdev,
+ "debugfs_create_file failed\n");
+
+ pfile = debugfs_create_file("xprop_register_value", 0600,
+ pdata->xgbe_debugfs, pdata,
+ &xprop_reg_value_fops);
+ if (!pfile)
+ netdev_err(pdata->netdev,
+ "debugfs_create_file failed\n");
+ }
+
+ if (pdata->xi2c_regs) {
+ pfile = debugfs_create_file("xi2c_register", 0600,
+ pdata->xgbe_debugfs, pdata,
+ &xi2c_reg_addr_fops);
+ if (!pfile)
+ netdev_err(pdata->netdev,
+ "debugfs_create_file failed\n");
+
+ pfile = debugfs_create_file("xi2c_register_value", 0600,
+ pdata->xgbe_debugfs, pdata,
+ &xi2c_reg_value_fops);
+ if (!pfile)
+ netdev_err(pdata->netdev,
+ "debugfs_create_file failed\n");
+ }
+
kfree(buf);
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index 1babcc1..aaf0350 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -123,6 +123,11 @@
#include "xgbe.h"
#include "xgbe-common.h"
+static inline unsigned int xgbe_get_max_frame(struct xgbe_prv_data *pdata)
+{
+ return pdata->netdev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+}
+
static unsigned int xgbe_usec_to_riwt(struct xgbe_prv_data *pdata,
unsigned int usec)
{
@@ -491,6 +496,27 @@ static void xgbe_config_rss(struct xgbe_prv_data *pdata)
"error configuring RSS, RSS disabled\n");
}
+static bool xgbe_is_pfc_queue(struct xgbe_prv_data *pdata,
+ unsigned int queue)
+{
+ unsigned int prio, tc;
+
+ for (prio = 0; prio < IEEE_8021QAZ_MAX_TCS; prio++) {
+ /* Does this queue handle the priority? */
+ if (pdata->prio2q_map[prio] != queue)
+ continue;
+
+ /* Get the Traffic Class for this priority */
+ tc = pdata->ets->prio_tc[prio];
+
+ /* Check if PFC is enabled for this traffic class */
+ if (pdata->pfc->pfc_en & (1 << tc))
+ return true;
+ }
+
+ return false;
+}
+
static int xgbe_disable_tx_flow_control(struct xgbe_prv_data *pdata)
{
unsigned int max_q_count, q_count;
@@ -528,27 +554,14 @@ static int xgbe_enable_tx_flow_control(struct xgbe_prv_data *pdata)
for (i = 0; i < pdata->rx_q_count; i++) {
unsigned int ehfc = 0;
- if (pfc && ets) {
- unsigned int prio;
-
- for (prio = 0; prio < IEEE_8021QAZ_MAX_TCS; prio++) {
- unsigned int tc;
-
- /* Does this queue handle the priority? */
- if (pdata->prio2q_map[prio] != i)
- continue;
-
- /* Get the Traffic Class for this priority */
- tc = ets->prio_tc[prio];
-
- /* Check if flow control should be enabled */
- if (pfc->pfc_en & (1 << tc)) {
+ if (pdata->rx_rfd[i]) {
+ /* Flow control thresholds are established */
+ if (pfc && ets) {
+ if (xgbe_is_pfc_queue(pdata, i))
ehfc = 1;
- break;
- }
+ } else {
+ ehfc = 1;
}
- } else {
- ehfc = 1;
}
XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, EHFC, ehfc);
@@ -633,6 +646,11 @@ static void xgbe_enable_dma_interrupts(struct xgbe_prv_data *pdata)
unsigned int dma_ch_isr, dma_ch_ier;
unsigned int i;
+ /* Set the interrupt mode if supported */
+ if (pdata->channel_irq_mode)
+ XGMAC_IOWRITE_BITS(pdata, DMA_MR, INTM,
+ pdata->channel_irq_mode);
+
channel = pdata->channel;
for (i = 0; i < pdata->channel_count; i++, channel++) {
/* Clear all the interrupts which are set */
@@ -654,19 +672,21 @@ static void xgbe_enable_dma_interrupts(struct xgbe_prv_data *pdata)
if (channel->tx_ring) {
/* Enable the following Tx interrupts
* TIE - Transmit Interrupt Enable (unless using
- * per channel interrupts)
+ * per channel interrupts in edge triggered
+ * mode)
*/
- if (!pdata->per_channel_irq)
+ if (!pdata->per_channel_irq || pdata->channel_irq_mode)
XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, TIE, 1);
}
if (channel->rx_ring) {
/* Enable following Rx interrupts
* RBUE - Receive Buffer Unavailable Enable
* RIE - Receive Interrupt Enable (unless using
- * per channel interrupts)
+ * per channel interrupts in edge triggered
+ * mode)
*/
XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, RBUE, 1);
- if (!pdata->per_channel_irq)
+ if (!pdata->per_channel_irq || pdata->channel_irq_mode)
XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, RIE, 1);
}
@@ -702,34 +722,90 @@ static void xgbe_enable_mac_interrupts(struct xgbe_prv_data *pdata)
/* Enable all counter interrupts */
XGMAC_IOWRITE_BITS(pdata, MMC_RIER, ALL_INTERRUPTS, 0xffffffff);
XGMAC_IOWRITE_BITS(pdata, MMC_TIER, ALL_INTERRUPTS, 0xffffffff);
+
+ /* Enable MDIO single command completion interrupt */
+ XGMAC_IOWRITE_BITS(pdata, MAC_MDIOIER, SNGLCOMPIE, 1);
}
-static int xgbe_set_gmii_speed(struct xgbe_prv_data *pdata)
+static void xgbe_enable_ecc_interrupts(struct xgbe_prv_data *pdata)
{
- if (XGMAC_IOREAD_BITS(pdata, MAC_TCR, SS) == 0x3)
- return 0;
+ unsigned int ecc_isr, ecc_ier = 0;
- XGMAC_IOWRITE_BITS(pdata, MAC_TCR, SS, 0x3);
+ if (!pdata->vdata->ecc_support)
+ return;
- return 0;
+ /* Clear all the interrupts which are set */
+ ecc_isr = XP_IOREAD(pdata, XP_ECC_ISR);
+ XP_IOWRITE(pdata, XP_ECC_ISR, ecc_isr);
+
+ /* Enable ECC interrupts */
+ XP_SET_BITS(ecc_ier, XP_ECC_IER, TX_DED, 1);
+ XP_SET_BITS(ecc_ier, XP_ECC_IER, TX_SEC, 1);
+ XP_SET_BITS(ecc_ier, XP_ECC_IER, RX_DED, 1);
+ XP_SET_BITS(ecc_ier, XP_ECC_IER, RX_SEC, 1);
+ XP_SET_BITS(ecc_ier, XP_ECC_IER, DESC_DED, 1);
+ XP_SET_BITS(ecc_ier, XP_ECC_IER, DESC_SEC, 1);
+
+ XP_IOWRITE(pdata, XP_ECC_IER, ecc_ier);
}
-static int xgbe_set_gmii_2500_speed(struct xgbe_prv_data *pdata)
+static void xgbe_disable_ecc_ded(struct xgbe_prv_data *pdata)
{
- if (XGMAC_IOREAD_BITS(pdata, MAC_TCR, SS) == 0x2)
- return 0;
+ unsigned int ecc_ier;
- XGMAC_IOWRITE_BITS(pdata, MAC_TCR, SS, 0x2);
+ ecc_ier = XP_IOREAD(pdata, XP_ECC_IER);
- return 0;
+ /* Disable ECC DED interrupts */
+ XP_SET_BITS(ecc_ier, XP_ECC_IER, TX_DED, 0);
+ XP_SET_BITS(ecc_ier, XP_ECC_IER, RX_DED, 0);
+ XP_SET_BITS(ecc_ier, XP_ECC_IER, DESC_DED, 0);
+
+ XP_IOWRITE(pdata, XP_ECC_IER, ecc_ier);
}
-static int xgbe_set_xgmii_speed(struct xgbe_prv_data *pdata)
+static void xgbe_disable_ecc_sec(struct xgbe_prv_data *pdata,
+ enum xgbe_ecc_sec sec)
{
- if (XGMAC_IOREAD_BITS(pdata, MAC_TCR, SS) == 0)
- return 0;
+ unsigned int ecc_ier;
- XGMAC_IOWRITE_BITS(pdata, MAC_TCR, SS, 0);
+ ecc_ier = XP_IOREAD(pdata, XP_ECC_IER);
+
+ /* Disable ECC SEC interrupt */
+ switch (sec) {
+ case XGBE_ECC_SEC_TX:
+ XP_SET_BITS(ecc_ier, XP_ECC_IER, TX_SEC, 0);
+ break;
+ case XGBE_ECC_SEC_RX:
+ XP_SET_BITS(ecc_ier, XP_ECC_IER, RX_SEC, 0);
+ break;
+ case XGBE_ECC_SEC_DESC:
+ XP_SET_BITS(ecc_ier, XP_ECC_IER, DESC_SEC, 0);
+ break;
+ }
+
+ XP_IOWRITE(pdata, XP_ECC_IER, ecc_ier);
+}
+
+static int xgbe_set_speed(struct xgbe_prv_data *pdata, int speed)
+{
+ unsigned int ss;
+
+ switch (speed) {
+ case SPEED_1000:
+ ss = 0x03;
+ break;
+ case SPEED_2500:
+ ss = 0x02;
+ break;
+ case SPEED_10000:
+ ss = 0x00;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (XGMAC_IOREAD_BITS(pdata, MAC_TCR, SS) != ss)
+ XGMAC_IOWRITE_BITS(pdata, MAC_TCR, SS, ss);
return 0;
}
@@ -1019,8 +1095,101 @@ static int xgbe_config_rx_mode(struct xgbe_prv_data *pdata)
return 0;
}
-static int xgbe_read_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
- int mmd_reg)
+static int xgbe_clr_gpio(struct xgbe_prv_data *pdata, unsigned int gpio)
+{
+ unsigned int reg;
+
+ if (gpio > 15)
+ return -EINVAL;
+
+ reg = XGMAC_IOREAD(pdata, MAC_GPIOSR);
+
+ reg &= ~(1 << (gpio + 16));
+ XGMAC_IOWRITE(pdata, MAC_GPIOSR, reg);
+
+ return 0;
+}
+
+static int xgbe_set_gpio(struct xgbe_prv_data *pdata, unsigned int gpio)
+{
+ unsigned int reg;
+
+ if (gpio > 15)
+ return -EINVAL;
+
+ reg = XGMAC_IOREAD(pdata, MAC_GPIOSR);
+
+ reg |= (1 << (gpio + 16));
+ XGMAC_IOWRITE(pdata, MAC_GPIOSR, reg);
+
+ return 0;
+}
+
+static int xgbe_read_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
+ int mmd_reg)
+{
+ unsigned long flags;
+ unsigned int mmd_address, index, offset;
+ int mmd_data;
+
+ if (mmd_reg & MII_ADDR_C45)
+ mmd_address = mmd_reg & ~MII_ADDR_C45;
+ else
+ mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+
+ /* The PCS registers are accessed using mmio. The underlying
+ * management interface uses indirect addressing to access the MMD
+ * register sets. This requires accessing of the PCS register in two
+ * phases, an address phase and a data phase.
+ *
+ * The mmio interface is based on 16-bit offsets and values. All
+ * register offsets must therefore be adjusted by left shifting the
+ * offset 1 bit and reading 16 bits of data.
+ */
+ mmd_address <<= 1;
+ index = mmd_address & ~pdata->xpcs_window_mask;
+ offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask);
+
+ spin_lock_irqsave(&pdata->xpcs_lock, flags);
+ XPCS32_IOWRITE(pdata, PCS_V2_WINDOW_SELECT, index);
+ mmd_data = XPCS16_IOREAD(pdata, offset);
+ spin_unlock_irqrestore(&pdata->xpcs_lock, flags);
+
+ return mmd_data;
+}
+
+static void xgbe_write_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
+ int mmd_reg, int mmd_data)
+{
+ unsigned long flags;
+ unsigned int mmd_address, index, offset;
+
+ if (mmd_reg & MII_ADDR_C45)
+ mmd_address = mmd_reg & ~MII_ADDR_C45;
+ else
+ mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+
+ /* The PCS registers are accessed using mmio. The underlying
+ * management interface uses indirect addressing to access the MMD
+ * register sets. This requires accessing of the PCS register in two
+ * phases, an address phase and a data phase.
+ *
+ * The mmio interface is based on 16-bit offsets and values. All
+ * register offsets must therefore be adjusted by left shifting the
+ * offset 1 bit and writing 16 bits of data.
+ */
+ mmd_address <<= 1;
+ index = mmd_address & ~pdata->xpcs_window_mask;
+ offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask);
+
+ spin_lock_irqsave(&pdata->xpcs_lock, flags);
+ XPCS32_IOWRITE(pdata, PCS_V2_WINDOW_SELECT, index);
+ XPCS16_IOWRITE(pdata, offset, mmd_data);
+ spin_unlock_irqrestore(&pdata->xpcs_lock, flags);
+}
+
+static int xgbe_read_mmd_regs_v1(struct xgbe_prv_data *pdata, int prtad,
+ int mmd_reg)
{
unsigned long flags;
unsigned int mmd_address;
@@ -1041,15 +1210,15 @@ static int xgbe_read_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
* offset 2 bits and reading 32 bits of data.
*/
spin_lock_irqsave(&pdata->xpcs_lock, flags);
- XPCS_IOWRITE(pdata, PCS_MMD_SELECT << 2, mmd_address >> 8);
- mmd_data = XPCS_IOREAD(pdata, (mmd_address & 0xff) << 2);
+ XPCS32_IOWRITE(pdata, PCS_V1_WINDOW_SELECT, mmd_address >> 8);
+ mmd_data = XPCS32_IOREAD(pdata, (mmd_address & 0xff) << 2);
spin_unlock_irqrestore(&pdata->xpcs_lock, flags);
return mmd_data;
}
-static void xgbe_write_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
- int mmd_reg, int mmd_data)
+static void xgbe_write_mmd_regs_v1(struct xgbe_prv_data *pdata, int prtad,
+ int mmd_reg, int mmd_data)
{
unsigned int mmd_address;
unsigned long flags;
@@ -1066,14 +1235,113 @@ static void xgbe_write_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
*
* The mmio interface is based on 32-bit offsets and values. All
* register offsets must therefore be adjusted by left shifting the
- * offset 2 bits and reading 32 bits of data.
+ * offset 2 bits and writing 32 bits of data.
*/
spin_lock_irqsave(&pdata->xpcs_lock, flags);
- XPCS_IOWRITE(pdata, PCS_MMD_SELECT << 2, mmd_address >> 8);
- XPCS_IOWRITE(pdata, (mmd_address & 0xff) << 2, mmd_data);
+ XPCS32_IOWRITE(pdata, PCS_V1_WINDOW_SELECT, mmd_address >> 8);
+ XPCS32_IOWRITE(pdata, (mmd_address & 0xff) << 2, mmd_data);
spin_unlock_irqrestore(&pdata->xpcs_lock, flags);
}
+static int xgbe_read_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
+ int mmd_reg)
+{
+ switch (pdata->vdata->xpcs_access) {
+ case XGBE_XPCS_ACCESS_V1:
+ return xgbe_read_mmd_regs_v1(pdata, prtad, mmd_reg);
+
+ case XGBE_XPCS_ACCESS_V2:
+ default:
+ return xgbe_read_mmd_regs_v2(pdata, prtad, mmd_reg);
+ }
+}
+
+static void xgbe_write_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
+ int mmd_reg, int mmd_data)
+{
+ switch (pdata->vdata->xpcs_access) {
+ case XGBE_XPCS_ACCESS_V1:
+ return xgbe_write_mmd_regs_v1(pdata, prtad, mmd_reg, mmd_data);
+
+ case XGBE_XPCS_ACCESS_V2:
+ default:
+ return xgbe_write_mmd_regs_v2(pdata, prtad, mmd_reg, mmd_data);
+ }
+}
+
+static int xgbe_write_ext_mii_regs(struct xgbe_prv_data *pdata, int addr,
+ int reg, u16 val)
+{
+ unsigned int mdio_sca, mdio_sccd;
+
+ reinit_completion(&pdata->mdio_complete);
+
+ mdio_sca = 0;
+ XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, REG, reg);
+ XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, DA, addr);
+ XGMAC_IOWRITE(pdata, MAC_MDIOSCAR, mdio_sca);
+
+ mdio_sccd = 0;
+ XGMAC_SET_BITS(mdio_sccd, MAC_MDIOSCCDR, DATA, val);
+ XGMAC_SET_BITS(mdio_sccd, MAC_MDIOSCCDR, CMD, 1);
+ XGMAC_SET_BITS(mdio_sccd, MAC_MDIOSCCDR, BUSY, 1);
+ XGMAC_IOWRITE(pdata, MAC_MDIOSCCDR, mdio_sccd);
+
+ if (!wait_for_completion_timeout(&pdata->mdio_complete, HZ)) {
+ netdev_err(pdata->netdev, "mdio write operation timed out\n");
+ return -ETIMEDOUT;
+ }
+
+ return 0;
+}
+
+static int xgbe_read_ext_mii_regs(struct xgbe_prv_data *pdata, int addr,
+ int reg)
+{
+ unsigned int mdio_sca, mdio_sccd;
+
+ reinit_completion(&pdata->mdio_complete);
+
+ mdio_sca = 0;
+ XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, REG, reg);
+ XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, DA, addr);
+ XGMAC_IOWRITE(pdata, MAC_MDIOSCAR, mdio_sca);
+
+ mdio_sccd = 0;
+ XGMAC_SET_BITS(mdio_sccd, MAC_MDIOSCCDR, CMD, 3);
+ XGMAC_SET_BITS(mdio_sccd, MAC_MDIOSCCDR, BUSY, 1);
+ XGMAC_IOWRITE(pdata, MAC_MDIOSCCDR, mdio_sccd);
+
+ if (!wait_for_completion_timeout(&pdata->mdio_complete, HZ)) {
+ netdev_err(pdata->netdev, "mdio read operation timed out\n");
+ return -ETIMEDOUT;
+ }
+
+ return XGMAC_IOREAD_BITS(pdata, MAC_MDIOSCCDR, DATA);
+}
+
+static int xgbe_set_ext_mii_mode(struct xgbe_prv_data *pdata, unsigned int port,
+ enum xgbe_mdio_mode mode)
+{
+ unsigned int reg_val = 0;
+
+ switch (mode) {
+ case XGBE_MDIO_MODE_CL22:
+ if (port > XGMAC_MAX_C22_PORT)
+ return -EINVAL;
+ reg_val |= (1 << port);
+ break;
+ case XGBE_MDIO_MODE_CL45:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ XGMAC_IOWRITE(pdata, MAC_MDIOCL22R, reg_val);
+
+ return 0;
+}
+
static int xgbe_tx_complete(struct xgbe_ring_desc *rdesc)
{
return !XGMAC_GET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, OWN);
@@ -1264,14 +1532,21 @@ static u64 xgbe_get_tstamp_time(struct xgbe_prv_data *pdata)
static u64 xgbe_get_tx_tstamp(struct xgbe_prv_data *pdata)
{
- unsigned int tx_snr;
+ unsigned int tx_snr, tx_ssr;
u64 nsec;
- tx_snr = XGMAC_IOREAD(pdata, MAC_TXSNR);
+ if (pdata->vdata->tx_tstamp_workaround) {
+ tx_snr = XGMAC_IOREAD(pdata, MAC_TXSNR);
+ tx_ssr = XGMAC_IOREAD(pdata, MAC_TXSSR);
+ } else {
+ tx_ssr = XGMAC_IOREAD(pdata, MAC_TXSSR);
+ tx_snr = XGMAC_IOREAD(pdata, MAC_TXSNR);
+ }
+
if (XGMAC_GET_BITS(tx_snr, MAC_TXSNR, TXTSSTSMIS))
return 0;
- nsec = XGMAC_IOREAD(pdata, MAC_TXSSR);
+ nsec = tx_ssr;
nsec *= NSEC_PER_SEC;
nsec += tx_snr;
@@ -1327,106 +1602,6 @@ static int xgbe_config_tstamp(struct xgbe_prv_data *pdata,
return 0;
}
-static void xgbe_config_tc(struct xgbe_prv_data *pdata)
-{
- unsigned int offset, queue, prio;
- u8 i;
-
- netdev_reset_tc(pdata->netdev);
- if (!pdata->num_tcs)
- return;
-
- netdev_set_num_tc(pdata->netdev, pdata->num_tcs);
-
- for (i = 0, queue = 0, offset = 0; i < pdata->num_tcs; i++) {
- while ((queue < pdata->tx_q_count) &&
- (pdata->q2tc_map[queue] == i))
- queue++;
-
- netif_dbg(pdata, drv, pdata->netdev, "TC%u using TXq%u-%u\n",
- i, offset, queue - 1);
- netdev_set_tc_queue(pdata->netdev, i, queue - offset, offset);
- offset = queue;
- }
-
- if (!pdata->ets)
- return;
-
- for (prio = 0; prio < IEEE_8021QAZ_MAX_TCS; prio++)
- netdev_set_prio_tc_map(pdata->netdev, prio,
- pdata->ets->prio_tc[prio]);
-}
-
-static void xgbe_config_dcb_tc(struct xgbe_prv_data *pdata)
-{
- struct ieee_ets *ets = pdata->ets;
- unsigned int total_weight, min_weight, weight;
- unsigned int mask, reg, reg_val;
- unsigned int i, prio;
-
- if (!ets)
- return;
-
- /* Set Tx to deficit weighted round robin scheduling algorithm (when
- * traffic class is using ETS algorithm)
- */
- XGMAC_IOWRITE_BITS(pdata, MTL_OMR, ETSALG, MTL_ETSALG_DWRR);
-
- /* Set Traffic Class algorithms */
- total_weight = pdata->netdev->mtu * pdata->hw_feat.tc_cnt;
- min_weight = total_weight / 100;
- if (!min_weight)
- min_weight = 1;
-
- for (i = 0; i < pdata->hw_feat.tc_cnt; i++) {
- /* Map the priorities to the traffic class */
- mask = 0;
- for (prio = 0; prio < IEEE_8021QAZ_MAX_TCS; prio++) {
- if (ets->prio_tc[prio] == i)
- mask |= (1 << prio);
- }
- mask &= 0xff;
-
- netif_dbg(pdata, drv, pdata->netdev, "TC%u PRIO mask=%#x\n",
- i, mask);
- reg = MTL_TCPM0R + (MTL_TCPM_INC * (i / MTL_TCPM_TC_PER_REG));
- reg_val = XGMAC_IOREAD(pdata, reg);
-
- reg_val &= ~(0xff << ((i % MTL_TCPM_TC_PER_REG) << 3));
- reg_val |= (mask << ((i % MTL_TCPM_TC_PER_REG) << 3));
-
- XGMAC_IOWRITE(pdata, reg, reg_val);
-
- /* Set the traffic class algorithm */
- switch (ets->tc_tsa[i]) {
- case IEEE_8021QAZ_TSA_STRICT:
- netif_dbg(pdata, drv, pdata->netdev,
- "TC%u using SP\n", i);
- XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_TC_ETSCR, TSA,
- MTL_TSA_SP);
- break;
- case IEEE_8021QAZ_TSA_ETS:
- weight = total_weight * ets->tc_tx_bw[i] / 100;
- weight = clamp(weight, min_weight, total_weight);
-
- netif_dbg(pdata, drv, pdata->netdev,
- "TC%u using DWRR (weight %u)\n", i, weight);
- XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_TC_ETSCR, TSA,
- MTL_TSA_ETS);
- XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_TC_QWR, QW,
- weight);
- break;
- }
- }
-
- xgbe_config_tc(pdata);
-}
-
-static void xgbe_config_dcb_pfc(struct xgbe_prv_data *pdata)
-{
- xgbe_config_flow_control(pdata);
-}
-
static void xgbe_tx_start_xmit(struct xgbe_channel *channel,
struct xgbe_ring *ring)
{
@@ -1901,7 +2076,7 @@ static int xgbe_disable_int(struct xgbe_channel *channel,
return 0;
}
-static int xgbe_exit(struct xgbe_prv_data *pdata)
+static int __xgbe_exit(struct xgbe_prv_data *pdata)
{
unsigned int count = 2000;
@@ -1923,6 +2098,20 @@ static int xgbe_exit(struct xgbe_prv_data *pdata)
return 0;
}
+static int xgbe_exit(struct xgbe_prv_data *pdata)
+{
+ int ret;
+
+ /* To guard against possible incorrectly generated interrupts,
+ * issue the software reset twice.
+ */
+ ret = __xgbe_exit(pdata);
+ if (ret)
+ return ret;
+
+ return __xgbe_exit(pdata);
+}
+
static int xgbe_flush_tx_queues(struct xgbe_prv_data *pdata)
{
unsigned int i, count;
@@ -2000,61 +2189,331 @@ static void xgbe_config_mtl_mode(struct xgbe_prv_data *pdata)
XGMAC_IOWRITE_BITS(pdata, MTL_OMR, RAA, MTL_RAA_SP);
}
-static unsigned int xgbe_calculate_per_queue_fifo(unsigned int fifo_size,
- unsigned int queue_count)
+static void xgbe_queue_flow_control_threshold(struct xgbe_prv_data *pdata,
+ unsigned int queue,
+ unsigned int q_fifo_size)
+{
+ unsigned int frame_fifo_size;
+ unsigned int rfa, rfd;
+
+ frame_fifo_size = XGMAC_FLOW_CONTROL_ALIGN(xgbe_get_max_frame(pdata));
+
+ if (pdata->pfcq[queue] && (q_fifo_size > pdata->pfc_rfa)) {
+ /* PFC is active for this queue */
+ rfa = pdata->pfc_rfa;
+ rfd = rfa + frame_fifo_size;
+ if (rfd > XGMAC_FLOW_CONTROL_MAX)
+ rfd = XGMAC_FLOW_CONTROL_MAX;
+ if (rfa >= XGMAC_FLOW_CONTROL_MAX)
+ rfa = XGMAC_FLOW_CONTROL_MAX - XGMAC_FLOW_CONTROL_UNIT;
+ } else {
+ /* This path deals with just maximum frame sizes which are
+ * limited to a jumbo frame of 9,000 (plus headers, etc.)
+ * so we can never exceed the maximum allowable RFA/RFD
+ * values.
+ */
+ if (q_fifo_size <= 2048) {
+ /* rx_rfd to zero to signal no flow control */
+ pdata->rx_rfa[queue] = 0;
+ pdata->rx_rfd[queue] = 0;
+ return;
+ }
+
+ if (q_fifo_size <= 4096) {
+ /* Between 2048 and 4096 */
+ pdata->rx_rfa[queue] = 0; /* Full - 1024 bytes */
+ pdata->rx_rfd[queue] = 1; /* Full - 1536 bytes */
+ return;
+ }
+
+ if (q_fifo_size <= frame_fifo_size) {
+ /* Between 4096 and max-frame */
+ pdata->rx_rfa[queue] = 2; /* Full - 2048 bytes */
+ pdata->rx_rfd[queue] = 5; /* Full - 3584 bytes */
+ return;
+ }
+
+ if (q_fifo_size <= (frame_fifo_size * 3)) {
+ /* Between max-frame and 3 max-frames,
+ * trigger if we get just over a frame of data and
+ * resume when we have just under half a frame left.
+ */
+ rfa = q_fifo_size - frame_fifo_size;
+ rfd = rfa + (frame_fifo_size / 2);
+ } else {
+ /* Above 3 max-frames - trigger when just over
+ * 2 frames of space available
+ */
+ rfa = frame_fifo_size * 2;
+ rfa += XGMAC_FLOW_CONTROL_UNIT;
+ rfd = rfa + frame_fifo_size;
+ }
+ }
+
+ pdata->rx_rfa[queue] = XGMAC_FLOW_CONTROL_VALUE(rfa);
+ pdata->rx_rfd[queue] = XGMAC_FLOW_CONTROL_VALUE(rfd);
+}
+
+static void xgbe_calculate_flow_control_threshold(struct xgbe_prv_data *pdata,
+ unsigned int *fifo)
+{
+ unsigned int q_fifo_size;
+ unsigned int i;
+
+ for (i = 0; i < pdata->rx_q_count; i++) {
+ q_fifo_size = (fifo[i] + 1) * XGMAC_FIFO_UNIT;
+
+ xgbe_queue_flow_control_threshold(pdata, i, q_fifo_size);
+ }
+}
+
+static void xgbe_config_flow_control_threshold(struct xgbe_prv_data *pdata)
+{
+ unsigned int i;
+
+ for (i = 0; i < pdata->rx_q_count; i++) {
+ XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQFCR, RFA,
+ pdata->rx_rfa[i]);
+ XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQFCR, RFD,
+ pdata->rx_rfd[i]);
+ }
+}
+
+static unsigned int xgbe_get_tx_fifo_size(struct xgbe_prv_data *pdata)
+{
+ /* The configured value may not be the actual amount of fifo RAM */
+ return min_t(unsigned int, pdata->tx_max_fifo_size,
+ pdata->hw_feat.tx_fifo_size);
+}
+
+static unsigned int xgbe_get_rx_fifo_size(struct xgbe_prv_data *pdata)
+{
+ /* The configured value may not be the actual amount of fifo RAM */
+ return min_t(unsigned int, pdata->rx_max_fifo_size,
+ pdata->hw_feat.rx_fifo_size);
+}
+
+static void xgbe_calculate_equal_fifo(unsigned int fifo_size,
+ unsigned int queue_count,
+ unsigned int *fifo)
{
unsigned int q_fifo_size;
unsigned int p_fifo;
+ unsigned int i;
- /* Calculate the configured fifo size */
- q_fifo_size = 1 << (fifo_size + 7);
+ q_fifo_size = fifo_size / queue_count;
- /* The configured value may not be the actual amount of fifo RAM */
- q_fifo_size = min_t(unsigned int, XGBE_FIFO_MAX, q_fifo_size);
-
- q_fifo_size = q_fifo_size / queue_count;
-
- /* Each increment in the queue fifo size represents 256 bytes of
- * fifo, with 0 representing 256 bytes. Distribute the fifo equally
- * between the queues.
+ /* Calculate the fifo setting by dividing the queue's fifo size
+ * by the fifo allocation increment (with 0 representing the
+ * base allocation increment so decrement the result by 1).
*/
- p_fifo = q_fifo_size / 256;
+ p_fifo = q_fifo_size / XGMAC_FIFO_UNIT;
if (p_fifo)
p_fifo--;
- return p_fifo;
+ /* Distribute the fifo equally amongst the queues */
+ for (i = 0; i < queue_count; i++)
+ fifo[i] = p_fifo;
+}
+
+static unsigned int xgbe_set_nonprio_fifos(unsigned int fifo_size,
+ unsigned int queue_count,
+ unsigned int *fifo)
+{
+ unsigned int i;
+
+ BUILD_BUG_ON_NOT_POWER_OF_2(XGMAC_FIFO_MIN_ALLOC);
+
+ if (queue_count <= IEEE_8021QAZ_MAX_TCS)
+ return fifo_size;
+
+ /* Rx queues 9 and up are for specialized packets,
+ * such as PTP or DCB control packets, etc. and
+ * don't require a large fifo
+ */
+ for (i = IEEE_8021QAZ_MAX_TCS; i < queue_count; i++) {
+ fifo[i] = (XGMAC_FIFO_MIN_ALLOC / XGMAC_FIFO_UNIT) - 1;
+ fifo_size -= XGMAC_FIFO_MIN_ALLOC;
+ }
+
+ return fifo_size;
+}
+
+static unsigned int xgbe_get_pfc_delay(struct xgbe_prv_data *pdata)
+{
+ unsigned int delay;
+
+ /* If a delay has been provided, use that */
+ if (pdata->pfc->delay)
+ return pdata->pfc->delay / 8;
+
+ /* Allow for two maximum size frames */
+ delay = xgbe_get_max_frame(pdata);
+ delay += XGMAC_ETH_PREAMBLE;
+ delay *= 2;
+
+ /* Allow for PFC frame */
+ delay += XGMAC_PFC_DATA_LEN;
+ delay += ETH_HLEN + ETH_FCS_LEN;
+ delay += XGMAC_ETH_PREAMBLE;
+
+ /* Allow for miscellaneous delays (LPI exit, cable, etc.) */
+ delay += XGMAC_PFC_DELAYS;
+
+ return delay;
+}
+
+static unsigned int xgbe_get_pfc_queues(struct xgbe_prv_data *pdata)
+{
+ unsigned int count, prio_queues;
+ unsigned int i;
+
+ if (!pdata->pfc->pfc_en)
+ return 0;
+
+ count = 0;
+ prio_queues = XGMAC_PRIO_QUEUES(pdata->rx_q_count);
+ for (i = 0; i < prio_queues; i++) {
+ if (!xgbe_is_pfc_queue(pdata, i))
+ continue;
+
+ pdata->pfcq[i] = 1;
+ count++;
+ }
+
+ return count;
+}
+
+static void xgbe_calculate_dcb_fifo(struct xgbe_prv_data *pdata,
+ unsigned int fifo_size,
+ unsigned int *fifo)
+{
+ unsigned int q_fifo_size, rem_fifo, addn_fifo;
+ unsigned int prio_queues;
+ unsigned int pfc_count;
+ unsigned int i;
+
+ q_fifo_size = XGMAC_FIFO_ALIGN(xgbe_get_max_frame(pdata));
+ prio_queues = XGMAC_PRIO_QUEUES(pdata->rx_q_count);
+ pfc_count = xgbe_get_pfc_queues(pdata);
+
+ if (!pfc_count || ((q_fifo_size * prio_queues) > fifo_size)) {
+ /* No traffic classes with PFC enabled or can't do lossless */
+ xgbe_calculate_equal_fifo(fifo_size, prio_queues, fifo);
+ return;
+ }
+
+ /* Calculate how much fifo we have to play with */
+ rem_fifo = fifo_size - (q_fifo_size * prio_queues);
+
+ /* Calculate how much more than base fifo PFC needs, which also
+ * becomes the threshold activation point (RFA)
+ */
+ pdata->pfc_rfa = xgbe_get_pfc_delay(pdata);
+ pdata->pfc_rfa = XGMAC_FLOW_CONTROL_ALIGN(pdata->pfc_rfa);
+
+ if (pdata->pfc_rfa > q_fifo_size) {
+ addn_fifo = pdata->pfc_rfa - q_fifo_size;
+ addn_fifo = XGMAC_FIFO_ALIGN(addn_fifo);
+ } else {
+ addn_fifo = 0;
+ }
+
+ /* Calculate DCB fifo settings:
+ * - distribute remaining fifo between the VLAN priority
+ * queues based on traffic class PFC enablement and overall
+ * priority (0 is lowest priority, so start at highest)
+ */
+ i = prio_queues;
+ while (i > 0) {
+ i--;
+
+ fifo[i] = (q_fifo_size / XGMAC_FIFO_UNIT) - 1;
+
+ if (!pdata->pfcq[i] || !addn_fifo)
+ continue;
+
+ if (addn_fifo > rem_fifo) {
+ netdev_warn(pdata->netdev,
+ "RXq%u cannot set needed fifo size\n", i);
+ if (!rem_fifo)
+ continue;
+
+ addn_fifo = rem_fifo;
+ }
+
+ fifo[i] += (addn_fifo / XGMAC_FIFO_UNIT);
+ rem_fifo -= addn_fifo;
+ }
+
+ if (rem_fifo) {
+ unsigned int inc_fifo = rem_fifo / prio_queues;
+
+ /* Distribute remaining fifo across queues */
+ for (i = 0; i < prio_queues; i++)
+ fifo[i] += (inc_fifo / XGMAC_FIFO_UNIT);
+ }
}
static void xgbe_config_tx_fifo_size(struct xgbe_prv_data *pdata)
{
unsigned int fifo_size;
+ unsigned int fifo[XGBE_MAX_QUEUES];
unsigned int i;
- fifo_size = xgbe_calculate_per_queue_fifo(pdata->hw_feat.tx_fifo_size,
- pdata->tx_q_count);
+ fifo_size = xgbe_get_tx_fifo_size(pdata);
+
+ xgbe_calculate_equal_fifo(fifo_size, pdata->tx_q_count, fifo);
for (i = 0; i < pdata->tx_q_count; i++)
- XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_TQOMR, TQS, fifo_size);
+ XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_TQOMR, TQS, fifo[i]);
netif_info(pdata, drv, pdata->netdev,
"%d Tx hardware queues, %d byte fifo per queue\n",
- pdata->tx_q_count, ((fifo_size + 1) * 256));
+ pdata->tx_q_count, ((fifo[0] + 1) * XGMAC_FIFO_UNIT));
}
static void xgbe_config_rx_fifo_size(struct xgbe_prv_data *pdata)
{
unsigned int fifo_size;
+ unsigned int fifo[XGBE_MAX_QUEUES];
+ unsigned int prio_queues;
unsigned int i;
- fifo_size = xgbe_calculate_per_queue_fifo(pdata->hw_feat.rx_fifo_size,
- pdata->rx_q_count);
+ /* Clear any DCB related fifo/queue information */
+ memset(pdata->pfcq, 0, sizeof(pdata->pfcq));
+ pdata->pfc_rfa = 0;
+
+ fifo_size = xgbe_get_rx_fifo_size(pdata);
+ prio_queues = XGMAC_PRIO_QUEUES(pdata->rx_q_count);
+
+ /* Assign a minimum fifo to the non-VLAN priority queues */
+ fifo_size = xgbe_set_nonprio_fifos(fifo_size, pdata->rx_q_count, fifo);
+
+ if (pdata->pfc && pdata->ets)
+ xgbe_calculate_dcb_fifo(pdata, fifo_size, fifo);
+ else
+ xgbe_calculate_equal_fifo(fifo_size, prio_queues, fifo);
for (i = 0; i < pdata->rx_q_count; i++)
- XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, RQS, fifo_size);
+ XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, RQS, fifo[i]);
- netif_info(pdata, drv, pdata->netdev,
- "%d Rx hardware queues, %d byte fifo per queue\n",
- pdata->rx_q_count, ((fifo_size + 1) * 256));
+ xgbe_calculate_flow_control_threshold(pdata, fifo);
+ xgbe_config_flow_control_threshold(pdata);
+
+ if (pdata->pfc && pdata->ets && pdata->pfc->pfc_en) {
+ netif_info(pdata, drv, pdata->netdev,
+ "%u Rx hardware queues\n", pdata->rx_q_count);
+ for (i = 0; i < pdata->rx_q_count; i++)
+ netif_info(pdata, drv, pdata->netdev,
+ "RxQ%u, %u byte fifo queue\n", i,
+ ((fifo[i] + 1) * XGMAC_FIFO_UNIT));
+ } else {
+ netif_info(pdata, drv, pdata->netdev,
+ "%u Rx hardware queues, %u byte fifo per queue\n",
+ pdata->rx_q_count,
+ ((fifo[0] + 1) * XGMAC_FIFO_UNIT));
+ }
}
static void xgbe_config_queue_mapping(struct xgbe_prv_data *pdata)
@@ -2090,8 +2549,7 @@ static void xgbe_config_queue_mapping(struct xgbe_prv_data *pdata)
}
/* Map the 8 VLAN priority values to available MTL Rx queues */
- prio_queues = min_t(unsigned int, IEEE_8021QAZ_MAX_TCS,
- pdata->rx_q_count);
+ prio_queues = XGMAC_PRIO_QUEUES(pdata->rx_q_count);
ppq = IEEE_8021QAZ_MAX_TCS / prio_queues;
ppq_extra = IEEE_8021QAZ_MAX_TCS % prio_queues;
@@ -2139,16 +2597,120 @@ static void xgbe_config_queue_mapping(struct xgbe_prv_data *pdata)
}
}
-static void xgbe_config_flow_control_threshold(struct xgbe_prv_data *pdata)
+static void xgbe_config_tc(struct xgbe_prv_data *pdata)
{
- unsigned int i;
+ unsigned int offset, queue, prio;
+ u8 i;
- for (i = 0; i < pdata->rx_q_count; i++) {
- /* Activate flow control when less than 4k left in fifo */
- XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQFCR, RFA, 2);
+ netdev_reset_tc(pdata->netdev);
+ if (!pdata->num_tcs)
+ return;
- /* De-activate flow control when more than 6k left in fifo */
- XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQFCR, RFD, 4);
+ netdev_set_num_tc(pdata->netdev, pdata->num_tcs);
+
+ for (i = 0, queue = 0, offset = 0; i < pdata->num_tcs; i++) {
+ while ((queue < pdata->tx_q_count) &&
+ (pdata->q2tc_map[queue] == i))
+ queue++;
+
+ netif_dbg(pdata, drv, pdata->netdev, "TC%u using TXq%u-%u\n",
+ i, offset, queue - 1);
+ netdev_set_tc_queue(pdata->netdev, i, queue - offset, offset);
+ offset = queue;
+ }
+
+ if (!pdata->ets)
+ return;
+
+ for (prio = 0; prio < IEEE_8021QAZ_MAX_TCS; prio++)
+ netdev_set_prio_tc_map(pdata->netdev, prio,
+ pdata->ets->prio_tc[prio]);
+}
+
+static void xgbe_config_dcb_tc(struct xgbe_prv_data *pdata)
+{
+ struct ieee_ets *ets = pdata->ets;
+ unsigned int total_weight, min_weight, weight;
+ unsigned int mask, reg, reg_val;
+ unsigned int i, prio;
+
+ if (!ets)
+ return;
+
+ /* Set Tx to deficit weighted round robin scheduling algorithm (when
+ * traffic class is using ETS algorithm)
+ */
+ XGMAC_IOWRITE_BITS(pdata, MTL_OMR, ETSALG, MTL_ETSALG_DWRR);
+
+ /* Set Traffic Class algorithms */
+ total_weight = pdata->netdev->mtu * pdata->hw_feat.tc_cnt;
+ min_weight = total_weight / 100;
+ if (!min_weight)
+ min_weight = 1;
+
+ for (i = 0; i < pdata->hw_feat.tc_cnt; i++) {
+ /* Map the priorities to the traffic class */
+ mask = 0;
+ for (prio = 0; prio < IEEE_8021QAZ_MAX_TCS; prio++) {
+ if (ets->prio_tc[prio] == i)
+ mask |= (1 << prio);
+ }
+ mask &= 0xff;
+
+ netif_dbg(pdata, drv, pdata->netdev, "TC%u PRIO mask=%#x\n",
+ i, mask);
+ reg = MTL_TCPM0R + (MTL_TCPM_INC * (i / MTL_TCPM_TC_PER_REG));
+ reg_val = XGMAC_IOREAD(pdata, reg);
+
+ reg_val &= ~(0xff << ((i % MTL_TCPM_TC_PER_REG) << 3));
+ reg_val |= (mask << ((i % MTL_TCPM_TC_PER_REG) << 3));
+
+ XGMAC_IOWRITE(pdata, reg, reg_val);
+
+ /* Set the traffic class algorithm */
+ switch (ets->tc_tsa[i]) {
+ case IEEE_8021QAZ_TSA_STRICT:
+ netif_dbg(pdata, drv, pdata->netdev,
+ "TC%u using SP\n", i);
+ XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_TC_ETSCR, TSA,
+ MTL_TSA_SP);
+ break;
+ case IEEE_8021QAZ_TSA_ETS:
+ weight = total_weight * ets->tc_tx_bw[i] / 100;
+ weight = clamp(weight, min_weight, total_weight);
+
+ netif_dbg(pdata, drv, pdata->netdev,
+ "TC%u using DWRR (weight %u)\n", i, weight);
+ XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_TC_ETSCR, TSA,
+ MTL_TSA_ETS);
+ XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_TC_QWR, QW,
+ weight);
+ break;
+ }
+ }
+
+ xgbe_config_tc(pdata);
+}
+
+static void xgbe_config_dcb_pfc(struct xgbe_prv_data *pdata)
+{
+ if (!test_bit(XGBE_DOWN, &pdata->dev_state)) {
+ /* Just stop the Tx queues while Rx fifo is changed */
+ netif_tx_stop_all_queues(pdata->netdev);
+
+ /* Suspend Rx so that fifo's can be adjusted */
+ pdata->hw_if.disable_rx(pdata);
+ }
+
+ xgbe_config_rx_fifo_size(pdata);
+ xgbe_config_flow_control(pdata);
+
+ if (!test_bit(XGBE_DOWN, &pdata->dev_state)) {
+ /* Resume Rx */
+ pdata->hw_if.enable_rx(pdata);
+
+ /* Resume Tx queues */
+ netif_tx_start_all_queues(pdata->netdev);
}
}
@@ -2175,19 +2737,7 @@ static void xgbe_config_jumbo_enable(struct xgbe_prv_data *pdata)
static void xgbe_config_mac_speed(struct xgbe_prv_data *pdata)
{
- switch (pdata->phy_speed) {
- case SPEED_10000:
- xgbe_set_xgmii_speed(pdata);
- break;
-
- case SPEED_2500:
- xgbe_set_gmii_2500_speed(pdata);
- break;
-
- case SPEED_1000:
- xgbe_set_gmii_speed(pdata);
- break;
- }
+ xgbe_set_speed(pdata, pdata->phy_speed);
}
static void xgbe_config_checksum_offload(struct xgbe_prv_data *pdata)
@@ -2223,17 +2773,33 @@ static u64 xgbe_mmc_read(struct xgbe_prv_data *pdata, unsigned int reg_lo)
bool read_hi;
u64 val;
- switch (reg_lo) {
- /* These registers are always 64 bit */
- case MMC_TXOCTETCOUNT_GB_LO:
- case MMC_TXOCTETCOUNT_G_LO:
- case MMC_RXOCTETCOUNT_GB_LO:
- case MMC_RXOCTETCOUNT_G_LO:
- read_hi = true;
- break;
+ if (pdata->vdata->mmc_64bit) {
+ switch (reg_lo) {
+ /* These registers are always 32 bit */
+ case MMC_RXRUNTERROR:
+ case MMC_RXJABBERERROR:
+ case MMC_RXUNDERSIZE_G:
+ case MMC_RXOVERSIZE_G:
+ case MMC_RXWATCHDOGERROR:
+ read_hi = false;
+ break;
- default:
- read_hi = false;
+ default:
+ read_hi = true;
+ }
+ } else {
+ switch (reg_lo) {
+ /* These registers are always 64 bit */
+ case MMC_TXOCTETCOUNT_GB_LO:
+ case MMC_TXOCTETCOUNT_G_LO:
+ case MMC_RXOCTETCOUNT_GB_LO:
+ case MMC_RXOCTETCOUNT_G_LO:
+ read_hi = true;
+ break;
+
+ default:
+ read_hi = false;
+ }
}
val = XGMAC_IOREAD(pdata, reg_lo);
@@ -2563,20 +3129,48 @@ static void xgbe_config_mmc(struct xgbe_prv_data *pdata)
XGMAC_IOWRITE_BITS(pdata, MMC_CR, CR, 1);
}
+static void xgbe_txq_prepare_tx_stop(struct xgbe_prv_data *pdata,
+ unsigned int queue)
+{
+ unsigned int tx_status;
+ unsigned long tx_timeout;
+
+ /* The Tx engine cannot be stopped if it is actively processing
+ * packets. Wait for the Tx queue to empty the Tx fifo. Don't
+ * wait forever though...
+ */
+ tx_timeout = jiffies + (XGBE_DMA_STOP_TIMEOUT * HZ);
+ while (time_before(jiffies, tx_timeout)) {
+ tx_status = XGMAC_MTL_IOREAD(pdata, queue, MTL_Q_TQDR);
+ if ((XGMAC_GET_BITS(tx_status, MTL_Q_TQDR, TRCSTS) != 1) &&
+ (XGMAC_GET_BITS(tx_status, MTL_Q_TQDR, TXQSTS) == 0))
+ break;
+
+ usleep_range(500, 1000);
+ }
+
+ if (!time_before(jiffies, tx_timeout))
+ netdev_info(pdata->netdev,
+ "timed out waiting for Tx queue %u to empty\n",
+ queue);
+}
+
static void xgbe_prepare_tx_stop(struct xgbe_prv_data *pdata,
- struct xgbe_channel *channel)
+ unsigned int queue)
{
unsigned int tx_dsr, tx_pos, tx_qidx;
unsigned int tx_status;
unsigned long tx_timeout;
+ if (XGMAC_GET_BITS(pdata->hw_feat.version, MAC_VR, SNPSVER) > 0x20)
+ return xgbe_txq_prepare_tx_stop(pdata, queue);
+
/* Calculate the status register to read and the position within */
- if (channel->queue_index < DMA_DSRX_FIRST_QUEUE) {
+ if (queue < DMA_DSRX_FIRST_QUEUE) {
tx_dsr = DMA_DSR0;
- tx_pos = (channel->queue_index * DMA_DSR_Q_WIDTH) +
- DMA_DSR0_TPS_START;
+ tx_pos = (queue * DMA_DSR_Q_WIDTH) + DMA_DSR0_TPS_START;
} else {
- tx_qidx = channel->queue_index - DMA_DSRX_FIRST_QUEUE;
+ tx_qidx = queue - DMA_DSRX_FIRST_QUEUE;
tx_dsr = DMA_DSR1 + ((tx_qidx / DMA_DSRX_QPR) * DMA_DSRX_INC);
tx_pos = ((tx_qidx % DMA_DSRX_QPR) * DMA_DSR_Q_WIDTH) +
@@ -2601,7 +3195,7 @@ static void xgbe_prepare_tx_stop(struct xgbe_prv_data *pdata,
if (!time_before(jiffies, tx_timeout))
netdev_info(pdata->netdev,
"timed out waiting for Tx DMA channel %u to stop\n",
- channel->queue_index);
+ queue);
}
static void xgbe_enable_tx(struct xgbe_prv_data *pdata)
@@ -2633,13 +3227,8 @@ static void xgbe_disable_tx(struct xgbe_prv_data *pdata)
unsigned int i;
/* Prepare for Tx DMA channel stop */
- channel = pdata->channel;
- for (i = 0; i < pdata->channel_count; i++, channel++) {
- if (!channel->tx_ring)
- break;
-
- xgbe_prepare_tx_stop(pdata, channel);
- }
+ for (i = 0; i < pdata->tx_q_count; i++)
+ xgbe_prepare_tx_stop(pdata, i);
/* Disable MAC Tx */
XGMAC_IOWRITE_BITS(pdata, MAC_TCR, TE, 0);
@@ -2763,13 +3352,8 @@ static void xgbe_powerdown_tx(struct xgbe_prv_data *pdata)
unsigned int i;
/* Prepare for Tx DMA channel stop */
- channel = pdata->channel;
- for (i = 0; i < pdata->channel_count; i++, channel++) {
- if (!channel->tx_ring)
- break;
-
- xgbe_prepare_tx_stop(pdata, channel);
- }
+ for (i = 0; i < pdata->tx_q_count; i++)
+ xgbe_prepare_tx_stop(pdata, i);
/* Disable MAC Tx */
XGMAC_IOWRITE_BITS(pdata, MAC_TCR, TE, 0);
@@ -2856,12 +3440,10 @@ static int xgbe_init(struct xgbe_prv_data *pdata)
xgbe_config_rx_threshold(pdata, pdata->rx_threshold);
xgbe_config_tx_fifo_size(pdata);
xgbe_config_rx_fifo_size(pdata);
- xgbe_config_flow_control_threshold(pdata);
/*TODO: Error Packet and undersized good Packet forwarding enable
(FEP and FUP)
*/
xgbe_config_dcb_tc(pdata);
- xgbe_config_dcb_pfc(pdata);
xgbe_enable_mtl_interrupts(pdata);
/*
@@ -2877,6 +3459,11 @@ static int xgbe_init(struct xgbe_prv_data *pdata)
xgbe_config_mmc(pdata);
xgbe_enable_mac_interrupts(pdata);
+ /*
+ * Initialize ECC related features
+ */
+ xgbe_enable_ecc_interrupts(pdata);
+
DBGPR("<--xgbe_init\n");
return 0;
@@ -2903,9 +3490,14 @@ void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *hw_if)
hw_if->read_mmd_regs = xgbe_read_mmd_regs;
hw_if->write_mmd_regs = xgbe_write_mmd_regs;
- hw_if->set_gmii_speed = xgbe_set_gmii_speed;
- hw_if->set_gmii_2500_speed = xgbe_set_gmii_2500_speed;
- hw_if->set_xgmii_speed = xgbe_set_xgmii_speed;
+ hw_if->set_speed = xgbe_set_speed;
+
+ hw_if->set_ext_mii_mode = xgbe_set_ext_mii_mode;
+ hw_if->read_ext_mii_regs = xgbe_read_ext_mii_regs;
+ hw_if->write_ext_mii_regs = xgbe_write_ext_mii_regs;
+
+ hw_if->set_gpio = xgbe_set_gpio;
+ hw_if->clr_gpio = xgbe_clr_gpio;
hw_if->enable_tx = xgbe_enable_tx;
hw_if->disable_tx = xgbe_disable_tx;
@@ -2984,5 +3576,9 @@ void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *hw_if)
hw_if->set_rss_hash_key = xgbe_set_rss_hash_key;
hw_if->set_rss_lookup_table = xgbe_set_rss_lookup_table;
+ /* For ECC */
+ hw_if->disable_ecc_ded = xgbe_disable_ecc_ded;
+ hw_if->disable_ecc_sec = xgbe_disable_ecc_sec;
+
DBGPR("<--xgbe_init_function_ptrs\n");
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index c4e6682..155190d 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -114,7 +114,7 @@
* THE POSSIBILITY OF SUCH DAMAGE.
*/
-#include <linux/platform_device.h>
+#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/tcp.h>
#include <linux/if_vlan.h>
@@ -127,8 +127,35 @@
#include "xgbe.h"
#include "xgbe-common.h"
+static unsigned int ecc_sec_info_threshold = 10;
+static unsigned int ecc_sec_warn_threshold = 10000;
+static unsigned int ecc_sec_period = 600;
+static unsigned int ecc_ded_threshold = 2;
+static unsigned int ecc_ded_period = 600;
+
+#ifdef CONFIG_AMD_XGBE_HAVE_ECC
+/* Only expose the ECC parameters if supported */
+module_param(ecc_sec_info_threshold, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(ecc_sec_info_threshold,
+ " ECC corrected error informational threshold setting");
+
+module_param(ecc_sec_warn_threshold, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(ecc_sec_warn_threshold,
+ " ECC corrected error warning threshold setting");
+
+module_param(ecc_sec_period, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(ecc_sec_period, " ECC corrected error period (in seconds)");
+
+module_param(ecc_ded_threshold, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(ecc_ded_threshold, " ECC detected error threshold setting");
+
+module_param(ecc_ded_period, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(ecc_ded_period, " ECC detected error period (in seconds)");
+#endif
+
static int xgbe_one_poll(struct napi_struct *, int);
static int xgbe_all_poll(struct napi_struct *, int);
+static void xgbe_stop(struct xgbe_prv_data *);
static int xgbe_alloc_channels(struct xgbe_prv_data *pdata)
{
@@ -160,18 +187,8 @@ static int xgbe_alloc_channels(struct xgbe_prv_data *pdata)
channel->dma_regs = pdata->xgmac_regs + DMA_CH_BASE +
(DMA_CH_INC * i);
- if (pdata->per_channel_irq) {
- /* Get the DMA interrupt (offset 1) */
- ret = platform_get_irq(pdata->pdev, i + 1);
- if (ret < 0) {
- netdev_err(pdata->netdev,
- "platform_get_irq %u failed\n",
- i + 1);
- goto err_irq;
- }
-
- channel->dma_irq = ret;
- }
+ if (pdata->per_channel_irq)
+ channel->dma_irq = pdata->channel_irq[i];
if (i < pdata->tx_ring_count) {
spin_lock_init(&tx_ring->lock);
@@ -194,9 +211,6 @@ static int xgbe_alloc_channels(struct xgbe_prv_data *pdata)
return 0;
-err_irq:
- kfree(rx_ring);
-
err_rx_ring:
kfree(tx_ring);
@@ -266,48 +280,161 @@ static int xgbe_calc_rx_buf_size(struct net_device *netdev, unsigned int mtu)
return rx_buf_size;
}
-static void xgbe_enable_rx_tx_ints(struct xgbe_prv_data *pdata)
+static void xgbe_enable_rx_tx_int(struct xgbe_prv_data *pdata,
+ struct xgbe_channel *channel)
{
struct xgbe_hw_if *hw_if = &pdata->hw_if;
- struct xgbe_channel *channel;
enum xgbe_int int_id;
+
+ if (channel->tx_ring && channel->rx_ring)
+ int_id = XGMAC_INT_DMA_CH_SR_TI_RI;
+ else if (channel->tx_ring)
+ int_id = XGMAC_INT_DMA_CH_SR_TI;
+ else if (channel->rx_ring)
+ int_id = XGMAC_INT_DMA_CH_SR_RI;
+ else
+ return;
+
+ hw_if->enable_int(channel, int_id);
+}
+
+static void xgbe_enable_rx_tx_ints(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_channel *channel;
unsigned int i;
channel = pdata->channel;
- for (i = 0; i < pdata->channel_count; i++, channel++) {
- if (channel->tx_ring && channel->rx_ring)
- int_id = XGMAC_INT_DMA_CH_SR_TI_RI;
- else if (channel->tx_ring)
- int_id = XGMAC_INT_DMA_CH_SR_TI;
- else if (channel->rx_ring)
- int_id = XGMAC_INT_DMA_CH_SR_RI;
- else
- continue;
+ for (i = 0; i < pdata->channel_count; i++, channel++)
+ xgbe_enable_rx_tx_int(pdata, channel);
+}
- hw_if->enable_int(channel, int_id);
- }
+static void xgbe_disable_rx_tx_int(struct xgbe_prv_data *pdata,
+ struct xgbe_channel *channel)
+{
+ struct xgbe_hw_if *hw_if = &pdata->hw_if;
+ enum xgbe_int int_id;
+
+ if (channel->tx_ring && channel->rx_ring)
+ int_id = XGMAC_INT_DMA_CH_SR_TI_RI;
+ else if (channel->tx_ring)
+ int_id = XGMAC_INT_DMA_CH_SR_TI;
+ else if (channel->rx_ring)
+ int_id = XGMAC_INT_DMA_CH_SR_RI;
+ else
+ return;
+
+ hw_if->disable_int(channel, int_id);
}
static void xgbe_disable_rx_tx_ints(struct xgbe_prv_data *pdata)
{
- struct xgbe_hw_if *hw_if = &pdata->hw_if;
struct xgbe_channel *channel;
- enum xgbe_int int_id;
unsigned int i;
channel = pdata->channel;
- for (i = 0; i < pdata->channel_count; i++, channel++) {
- if (channel->tx_ring && channel->rx_ring)
- int_id = XGMAC_INT_DMA_CH_SR_TI_RI;
- else if (channel->tx_ring)
- int_id = XGMAC_INT_DMA_CH_SR_TI;
- else if (channel->rx_ring)
- int_id = XGMAC_INT_DMA_CH_SR_RI;
- else
- continue;
+ for (i = 0; i < pdata->channel_count; i++, channel++)
+ xgbe_disable_rx_tx_int(pdata, channel);
+}
- hw_if->disable_int(channel, int_id);
+static bool xgbe_ecc_sec(struct xgbe_prv_data *pdata, unsigned long *period,
+ unsigned int *count, const char *area)
+{
+ if (time_before(jiffies, *period)) {
+ (*count)++;
+ } else {
+ *period = jiffies + (ecc_sec_period * HZ);
+ *count = 1;
}
+
+ if (*count > ecc_sec_info_threshold)
+ dev_warn_once(pdata->dev,
+ "%s ECC corrected errors exceed informational threshold\n",
+ area);
+
+ if (*count > ecc_sec_warn_threshold) {
+ dev_warn_once(pdata->dev,
+ "%s ECC corrected errors exceed warning threshold\n",
+ area);
+ return true;
+ }
+
+ return false;
+}
+
+static bool xgbe_ecc_ded(struct xgbe_prv_data *pdata, unsigned long *period,
+ unsigned int *count, const char *area)
+{
+ if (time_before(jiffies, *period)) {
+ (*count)++;
+ } else {
+ *period = jiffies + (ecc_ded_period * HZ);
+ *count = 1;
+ }
+
+ if (*count > ecc_ded_threshold) {
+ netdev_alert(pdata->netdev,
+ "%s ECC detected errors exceed threshold\n",
+ area);
+ return true;
+ }
+
+ return false;
+}
+
+static irqreturn_t xgbe_ecc_isr(int irq, void *data)
+{
+ struct xgbe_prv_data *pdata = data;
+ unsigned int ecc_isr;
+ bool stop = false;
+
+ /* Mask status with only the interrupts we care about */
+ ecc_isr = XP_IOREAD(pdata, XP_ECC_ISR);
+ ecc_isr &= XP_IOREAD(pdata, XP_ECC_IER);
+ netif_dbg(pdata, intr, pdata->netdev, "ECC_ISR=%#010x\n", ecc_isr);
+
+ if (XP_GET_BITS(ecc_isr, XP_ECC_ISR, TX_DED)) {
+ stop |= xgbe_ecc_ded(pdata, &pdata->tx_ded_period,
+ &pdata->tx_ded_count, "TX fifo");
+ }
+
+ if (XP_GET_BITS(ecc_isr, XP_ECC_ISR, RX_DED)) {
+ stop |= xgbe_ecc_ded(pdata, &pdata->rx_ded_period,
+ &pdata->rx_ded_count, "RX fifo");
+ }
+
+ if (XP_GET_BITS(ecc_isr, XP_ECC_ISR, DESC_DED)) {
+ stop |= xgbe_ecc_ded(pdata, &pdata->desc_ded_period,
+ &pdata->desc_ded_count,
+ "descriptor cache");
+ }
+
+ if (stop) {
+ pdata->hw_if.disable_ecc_ded(pdata);
+ schedule_work(&pdata->stopdev_work);
+ goto out;
+ }
+
+ if (XP_GET_BITS(ecc_isr, XP_ECC_ISR, TX_SEC)) {
+ if (xgbe_ecc_sec(pdata, &pdata->tx_sec_period,
+ &pdata->tx_sec_count, "TX fifo"))
+ pdata->hw_if.disable_ecc_sec(pdata, XGBE_ECC_SEC_TX);
+ }
+
+ if (XP_GET_BITS(ecc_isr, XP_ECC_ISR, RX_SEC))
+ if (xgbe_ecc_sec(pdata, &pdata->rx_sec_period,
+ &pdata->rx_sec_count, "RX fifo"))
+ pdata->hw_if.disable_ecc_sec(pdata, XGBE_ECC_SEC_RX);
+
+ if (XP_GET_BITS(ecc_isr, XP_ECC_ISR, DESC_SEC))
+ if (xgbe_ecc_sec(pdata, &pdata->desc_sec_period,
+ &pdata->desc_sec_count, "descriptor cache"))
+ pdata->hw_if.disable_ecc_sec(pdata, XGBE_ECC_SEC_DESC);
+
+out:
+ /* Clear all ECC interrupts */
+ XP_IOWRITE(pdata, XP_ECC_ISR, ecc_isr);
+
+ return IRQ_HANDLED;
}
static irqreturn_t xgbe_isr(int irq, void *data)
@@ -316,7 +443,7 @@ static irqreturn_t xgbe_isr(int irq, void *data)
struct xgbe_hw_if *hw_if = &pdata->hw_if;
struct xgbe_channel *channel;
unsigned int dma_isr, dma_ch_isr;
- unsigned int mac_isr, mac_tssr;
+ unsigned int mac_isr, mac_tssr, mac_mdioisr;
unsigned int i;
/* The DMA interrupt status register also reports MAC and MTL
@@ -353,6 +480,13 @@ static irqreturn_t xgbe_isr(int irq, void *data)
/* Turn on polling */
__napi_schedule_irqoff(&pdata->napi);
}
+ } else {
+ /* Don't clear Rx/Tx status if doing per channel DMA
+ * interrupts, these will be cleared by the ISR for
+ * per channel DMA interrupts.
+ */
+ XGMAC_SET_BITS(dma_ch_isr, DMA_CH_SR, TI, 0);
+ XGMAC_SET_BITS(dma_ch_isr, DMA_CH_SR, RI, 0);
}
if (XGMAC_GET_BITS(dma_ch_isr, DMA_CH_SR, RBU))
@@ -362,13 +496,16 @@ static irqreturn_t xgbe_isr(int irq, void *data)
if (XGMAC_GET_BITS(dma_ch_isr, DMA_CH_SR, FBE))
schedule_work(&pdata->restart_work);
- /* Clear all interrupt signals */
+ /* Clear interrupt signals */
XGMAC_DMA_IOWRITE(channel, DMA_CH_SR, dma_ch_isr);
}
if (XGMAC_GET_BITS(dma_isr, DMA_ISR, MACIS)) {
mac_isr = XGMAC_IOREAD(pdata, MAC_ISR);
+ netif_dbg(pdata, intr, pdata->netdev, "MAC_ISR=%#010x\n",
+ mac_isr);
+
if (XGMAC_GET_BITS(mac_isr, MAC_ISR, MMCTXIS))
hw_if->tx_mmc_int(pdata);
@@ -378,6 +515,9 @@ static irqreturn_t xgbe_isr(int irq, void *data)
if (XGMAC_GET_BITS(mac_isr, MAC_ISR, TSIS)) {
mac_tssr = XGMAC_IOREAD(pdata, MAC_TSSR);
+ netif_dbg(pdata, intr, pdata->netdev,
+ "MAC_TSSR=%#010x\n", mac_tssr);
+
if (XGMAC_GET_BITS(mac_tssr, MAC_TSSR, TXTSC)) {
/* Read Tx Timestamp to clear interrupt */
pdata->tx_tstamp =
@@ -386,8 +526,31 @@ static irqreturn_t xgbe_isr(int irq, void *data)
&pdata->tx_tstamp_work);
}
}
+
+ if (XGMAC_GET_BITS(mac_isr, MAC_ISR, SMI)) {
+ mac_mdioisr = XGMAC_IOREAD(pdata, MAC_MDIOISR);
+
+ netif_dbg(pdata, intr, pdata->netdev,
+ "MAC_MDIOISR=%#010x\n", mac_mdioisr);
+
+ if (XGMAC_GET_BITS(mac_mdioisr, MAC_MDIOISR,
+ SNGLCOMPINT))
+ complete(&pdata->mdio_complete);
+ }
}
+ /* If there is not a separate AN irq, handle it here */
+ if (pdata->dev_irq == pdata->an_irq)
+ pdata->phy_if.an_isr(irq, pdata);
+
+ /* If there is not a separate ECC irq, handle it here */
+ if (pdata->vdata->ecc_support && (pdata->dev_irq == pdata->ecc_irq))
+ xgbe_ecc_isr(irq, pdata);
+
+ /* If there is not a separate I2C irq, handle it here */
+ if (pdata->vdata->i2c_support && (pdata->dev_irq == pdata->i2c_irq))
+ pdata->i2c_if.i2c_isr(irq, pdata);
+
isr_done:
return IRQ_HANDLED;
}
@@ -395,18 +558,29 @@ static irqreturn_t xgbe_isr(int irq, void *data)
static irqreturn_t xgbe_dma_isr(int irq, void *data)
{
struct xgbe_channel *channel = data;
+ struct xgbe_prv_data *pdata = channel->pdata;
+ unsigned int dma_status;
/* Per channel DMA interrupts are enabled, so we use the per
* channel napi structure and not the private data napi structure
*/
if (napi_schedule_prep(&channel->napi)) {
/* Disable Tx and Rx interrupts */
- disable_irq_nosync(channel->dma_irq);
+ if (pdata->channel_irq_mode)
+ xgbe_disable_rx_tx_int(pdata, channel);
+ else
+ disable_irq_nosync(channel->dma_irq);
/* Turn on polling */
__napi_schedule_irqoff(&channel->napi);
}
+ /* Clear Tx/Rx signals */
+ dma_status = 0;
+ XGMAC_SET_BITS(dma_status, DMA_CH_SR, TI, 1);
+ XGMAC_SET_BITS(dma_status, DMA_CH_SR, RI, 1);
+ XGMAC_DMA_IOWRITE(channel, DMA_CH_SR, dma_status);
+
return IRQ_HANDLED;
}
@@ -423,7 +597,10 @@ static void xgbe_tx_timer(unsigned long data)
if (napi_schedule_prep(napi)) {
/* Disable Tx and Rx interrupts */
if (pdata->per_channel_irq)
- disable_irq_nosync(channel->dma_irq);
+ if (pdata->channel_irq_mode)
+ xgbe_disable_rx_tx_int(pdata, channel);
+ else
+ disable_irq_nosync(channel->dma_irq);
else
xgbe_disable_rx_tx_ints(pdata);
@@ -590,6 +767,10 @@ void xgbe_get_all_hw_features(struct xgbe_prv_data *pdata)
hw_feat->tx_ch_cnt++;
hw_feat->tc_cnt++;
+ /* Translate the fifo sizes into actual numbers */
+ hw_feat->rx_fifo_size = 1 << (hw_feat->rx_fifo_size + 7);
+ hw_feat->tx_fifo_size = 1 << (hw_feat->tx_fifo_size + 7);
+
DBGPR("<--xgbe_get_all_hw_features\n");
}
@@ -652,6 +833,16 @@ static int xgbe_request_irqs(struct xgbe_prv_data *pdata)
return ret;
}
+ if (pdata->vdata->ecc_support && (pdata->dev_irq != pdata->ecc_irq)) {
+ ret = devm_request_irq(pdata->dev, pdata->ecc_irq, xgbe_ecc_isr,
+ 0, pdata->ecc_name, pdata);
+ if (ret) {
+ netdev_alert(netdev, "error requesting ecc irq %d\n",
+ pdata->ecc_irq);
+ goto err_dev_irq;
+ }
+ }
+
if (!pdata->per_channel_irq)
return 0;
@@ -668,17 +859,21 @@ static int xgbe_request_irqs(struct xgbe_prv_data *pdata)
if (ret) {
netdev_alert(netdev, "error requesting irq %d\n",
channel->dma_irq);
- goto err_irq;
+ goto err_dma_irq;
}
}
return 0;
-err_irq:
+err_dma_irq:
/* Using an unsigned int, 'i' will go to UINT_MAX and exit */
for (i--, channel--; i < pdata->channel_count; i--, channel--)
devm_free_irq(pdata->dev, channel->dma_irq, channel);
+ if (pdata->vdata->ecc_support && (pdata->dev_irq != pdata->ecc_irq))
+ devm_free_irq(pdata->dev, pdata->ecc_irq, pdata);
+
+err_dev_irq:
devm_free_irq(pdata->dev, pdata->dev_irq, pdata);
return ret;
@@ -691,6 +886,9 @@ static void xgbe_free_irqs(struct xgbe_prv_data *pdata)
devm_free_irq(pdata->dev, pdata->dev_irq, pdata);
+ if (pdata->vdata->ecc_support && (pdata->dev_irq != pdata->ecc_irq))
+ devm_free_irq(pdata->dev, pdata->ecc_irq, pdata);
+
if (!pdata->per_channel_irq)
return;
@@ -778,7 +976,7 @@ static void xgbe_free_rx_data(struct xgbe_prv_data *pdata)
DBGPR("<--xgbe_free_rx_data\n");
}
-static int xgbe_phy_init(struct xgbe_prv_data *pdata)
+static int xgbe_phy_reset(struct xgbe_prv_data *pdata)
{
pdata->phy_link = -1;
pdata->phy_speed = SPEED_UNKNOWN;
@@ -874,16 +1072,16 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
hw_if->init(pdata);
- ret = phy_if->phy_start(pdata);
- if (ret)
- goto err_phy;
-
xgbe_napi_enable(pdata, 1);
ret = xgbe_request_irqs(pdata);
if (ret)
goto err_napi;
+ ret = phy_if->phy_start(pdata);
+ if (ret)
+ goto err_irqs;
+
hw_if->enable_tx(pdata);
hw_if->enable_rx(pdata);
@@ -892,16 +1090,18 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
xgbe_start_timers(pdata);
queue_work(pdata->dev_workqueue, &pdata->service_work);
+ clear_bit(XGBE_STOPPED, &pdata->dev_state);
+
DBGPR("<--xgbe_start\n");
return 0;
+err_irqs:
+ xgbe_free_irqs(pdata);
+
err_napi:
xgbe_napi_disable(pdata, 1);
- phy_if->phy_stop(pdata);
-
-err_phy:
hw_if->exit(pdata);
return ret;
@@ -918,6 +1118,9 @@ static void xgbe_stop(struct xgbe_prv_data *pdata)
DBGPR("-->xgbe_stop\n");
+ if (test_bit(XGBE_STOPPED, &pdata->dev_state))
+ return;
+
netif_tx_stop_all_queues(netdev);
xgbe_stop_timers(pdata);
@@ -943,9 +1146,29 @@ static void xgbe_stop(struct xgbe_prv_data *pdata)
netdev_tx_reset_queue(txq);
}
+ set_bit(XGBE_STOPPED, &pdata->dev_state);
+
DBGPR("<--xgbe_stop\n");
}
+static void xgbe_stopdev(struct work_struct *work)
+{
+ struct xgbe_prv_data *pdata = container_of(work,
+ struct xgbe_prv_data,
+ stopdev_work);
+
+ rtnl_lock();
+
+ xgbe_stop(pdata);
+
+ xgbe_free_tx_data(pdata);
+ xgbe_free_rx_data(pdata);
+
+ rtnl_unlock();
+
+ netdev_alert(pdata->netdev, "device stopped\n");
+}
+
static void xgbe_restart_dev(struct xgbe_prv_data *pdata)
{
DBGPR("-->xgbe_restart_dev\n");
@@ -1292,8 +1515,8 @@ static int xgbe_open(struct net_device *netdev)
DBGPR("-->xgbe_open\n");
- /* Initialize the phy */
- ret = xgbe_phy_init(pdata);
+ /* Reset the phy settings */
+ ret = xgbe_phy_reset(pdata);
if (ret)
return ret;
@@ -1328,6 +1551,7 @@ static int xgbe_open(struct net_device *netdev)
INIT_WORK(&pdata->service_work, xgbe_service);
INIT_WORK(&pdata->restart_work, xgbe_restart);
+ INIT_WORK(&pdata->stopdev_work, xgbe_stopdev);
INIT_WORK(&pdata->tx_tstamp_work, xgbe_tx_tstamp);
xgbe_init_timers(pdata);
@@ -2036,6 +2260,7 @@ static int xgbe_one_poll(struct napi_struct *napi, int budget)
{
struct xgbe_channel *channel = container_of(napi, struct xgbe_channel,
napi);
+ struct xgbe_prv_data *pdata = channel->pdata;
int processed = 0;
DBGPR("-->xgbe_one_poll: budget=%d\n", budget);
@@ -2052,7 +2277,10 @@ static int xgbe_one_poll(struct napi_struct *napi, int budget)
napi_complete_done(napi, processed);
/* Enable Tx and Rx interrupts */
- enable_irq(channel->dma_irq);
+ if (pdata->channel_irq_mode)
+ xgbe_enable_rx_tx_int(pdata, channel);
+ else
+ enable_irq(channel->dma_irq);
}
DBGPR("<--xgbe_one_poll: received = %d\n", processed);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
index 4007b42..920566a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
@@ -272,97 +272,86 @@ static int xgbe_set_pauseparam(struct net_device *netdev,
return ret;
}
-static int xgbe_get_settings(struct net_device *netdev,
- struct ethtool_cmd *cmd)
+static int xgbe_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct xgbe_prv_data *pdata = netdev_priv(netdev);
- cmd->phy_address = pdata->phy.address;
+ cmd->base.phy_address = pdata->phy.address;
- cmd->supported = pdata->phy.supported;
- cmd->advertising = pdata->phy.advertising;
- cmd->lp_advertising = pdata->phy.lp_advertising;
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ pdata->phy.supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ pdata->phy.advertising);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.lp_advertising,
+ pdata->phy.lp_advertising);
- cmd->autoneg = pdata->phy.autoneg;
- ethtool_cmd_speed_set(cmd, pdata->phy.speed);
- cmd->duplex = pdata->phy.duplex;
+ cmd->base.autoneg = pdata->phy.autoneg;
+ cmd->base.speed = pdata->phy.speed;
+ cmd->base.duplex = pdata->phy.duplex;
- cmd->port = PORT_NONE;
- cmd->transceiver = XCVR_INTERNAL;
+ cmd->base.port = PORT_NONE;
return 0;
}
-static int xgbe_set_settings(struct net_device *netdev,
- struct ethtool_cmd *cmd)
+static int xgbe_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
{
struct xgbe_prv_data *pdata = netdev_priv(netdev);
+ u32 advertising;
u32 speed;
int ret;
- speed = ethtool_cmd_speed(cmd);
+ speed = cmd->base.speed;
- if (cmd->phy_address != pdata->phy.address) {
+ if (cmd->base.phy_address != pdata->phy.address) {
netdev_err(netdev, "invalid phy address %hhu\n",
- cmd->phy_address);
+ cmd->base.phy_address);
return -EINVAL;
}
- if ((cmd->autoneg != AUTONEG_ENABLE) &&
- (cmd->autoneg != AUTONEG_DISABLE)) {
+ if ((cmd->base.autoneg != AUTONEG_ENABLE) &&
+ (cmd->base.autoneg != AUTONEG_DISABLE)) {
netdev_err(netdev, "unsupported autoneg %hhu\n",
- cmd->autoneg);
+ cmd->base.autoneg);
return -EINVAL;
}
- if (cmd->autoneg == AUTONEG_DISABLE) {
- switch (speed) {
- case SPEED_10000:
- break;
- case SPEED_2500:
- if (pdata->speed_set != XGBE_SPEEDSET_2500_10000) {
- netdev_err(netdev, "unsupported speed %u\n",
- speed);
- return -EINVAL;
- }
- break;
- case SPEED_1000:
- if (pdata->speed_set != XGBE_SPEEDSET_1000_10000) {
- netdev_err(netdev, "unsupported speed %u\n",
- speed);
- return -EINVAL;
- }
- break;
- default:
+ if (cmd->base.autoneg == AUTONEG_DISABLE) {
+ if (!pdata->phy_if.phy_valid_speed(pdata, speed)) {
netdev_err(netdev, "unsupported speed %u\n", speed);
return -EINVAL;
}
- if (cmd->duplex != DUPLEX_FULL) {
+ if (cmd->base.duplex != DUPLEX_FULL) {
netdev_err(netdev, "unsupported duplex %hhu\n",
- cmd->duplex);
+ cmd->base.duplex);
return -EINVAL;
}
}
+ ethtool_convert_link_mode_to_legacy_u32(&advertising,
+ cmd->link_modes.advertising);
+
netif_dbg(pdata, link, netdev,
"requested advertisement %#x, phy supported %#x\n",
- cmd->advertising, pdata->phy.supported);
+ advertising, pdata->phy.supported);
- cmd->advertising &= pdata->phy.supported;
- if ((cmd->autoneg == AUTONEG_ENABLE) && !cmd->advertising) {
+ advertising &= pdata->phy.supported;
+ if ((cmd->base.autoneg == AUTONEG_ENABLE) && !advertising) {
netdev_err(netdev,
"unsupported requested advertisement\n");
return -EINVAL;
}
ret = 0;
- pdata->phy.autoneg = cmd->autoneg;
+ pdata->phy.autoneg = cmd->base.autoneg;
pdata->phy.speed = speed;
- pdata->phy.duplex = cmd->duplex;
- pdata->phy.advertising = cmd->advertising;
+ pdata->phy.duplex = cmd->base.duplex;
+ pdata->phy.advertising = advertising;
- if (cmd->autoneg == AUTONEG_ENABLE)
+ if (cmd->base.autoneg == AUTONEG_ENABLE)
pdata->phy.advertising |= ADVERTISED_Autoneg;
else
pdata->phy.advertising &= ~ADVERTISED_Autoneg;
@@ -602,8 +591,6 @@ static int xgbe_get_ts_info(struct net_device *netdev,
}
static const struct ethtool_ops xgbe_ethtool_ops = {
- .get_settings = xgbe_get_settings,
- .set_settings = xgbe_set_settings,
.get_drvinfo = xgbe_get_drvinfo,
.get_msglevel = xgbe_get_msglevel,
.set_msglevel = xgbe_set_msglevel,
@@ -621,6 +608,8 @@ static const struct ethtool_ops xgbe_ethtool_ops = {
.get_rxfh = xgbe_get_rxfh,
.set_rxfh = xgbe_set_rxfh,
.get_ts_info = xgbe_get_ts_info,
+ .get_link_ksettings = xgbe_get_link_ksettings,
+ .set_link_ksettings = xgbe_set_link_ksettings,
};
const struct ethtool_ops *xgbe_get_ethtool_ops(void)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
new file mode 100644
index 0000000..0c7088a
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
@@ -0,0 +1,492 @@
+/*
+ * AMD 10Gb Ethernet driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2016 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ * The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ * (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ * Inc. unless otherwise expressly agreed to in writing between Synopsys
+ * and you.
+ *
+ * The Software IS NOT an item of Licensed Software or Licensed Product
+ * under any End User Software License Agreement or Agreement for Licensed
+ * Product with Synopsys or any supplement thereto. Permission is hereby
+ * granted, free of charge, to any person obtaining a copy of this software
+ * annotated with this license and the Software, to deal in the Software
+ * without restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is furnished
+ * to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ * BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ * PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ * THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2016 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Advanced Micro Devices, Inc. nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ * The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ * (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ * Inc. unless otherwise expressly agreed to in writing between Synopsys
+ * and you.
+ *
+ * The Software IS NOT an item of Licensed Software or Licensed Product
+ * under any End User Software License Agreement or Agreement for Licensed
+ * Product with Synopsys or any supplement thereto. Permission is hereby
+ * granted, free of charge, to any person obtaining a copy of this software
+ * annotated with this license and the Software, to deal in the Software
+ * without restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is furnished
+ * to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ * BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ * PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ * THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <linux/kmod.h>
+#include <linux/delay.h>
+#include <linux/completion.h>
+#include <linux/mutex.h>
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+#define XGBE_ABORT_COUNT 500
+#define XGBE_DISABLE_COUNT 1000
+
+#define XGBE_STD_SPEED 1
+
+#define XGBE_INTR_RX_FULL BIT(IC_RAW_INTR_STAT_RX_FULL_INDEX)
+#define XGBE_INTR_TX_EMPTY BIT(IC_RAW_INTR_STAT_TX_EMPTY_INDEX)
+#define XGBE_INTR_TX_ABRT BIT(IC_RAW_INTR_STAT_TX_ABRT_INDEX)
+#define XGBE_INTR_STOP_DET BIT(IC_RAW_INTR_STAT_STOP_DET_INDEX)
+#define XGBE_DEFAULT_INT_MASK (XGBE_INTR_RX_FULL | \
+ XGBE_INTR_TX_EMPTY | \
+ XGBE_INTR_TX_ABRT | \
+ XGBE_INTR_STOP_DET)
+
+#define XGBE_I2C_READ BIT(8)
+#define XGBE_I2C_STOP BIT(9)
+
+static int xgbe_i2c_abort(struct xgbe_prv_data *pdata)
+{
+ unsigned int wait = XGBE_ABORT_COUNT;
+
+ /* Must be enabled to recognize the abort request */
+ XI2C_IOWRITE_BITS(pdata, IC_ENABLE, EN, 1);
+
+ /* Issue the abort */
+ XI2C_IOWRITE_BITS(pdata, IC_ENABLE, ABORT, 1);
+
+ while (wait--) {
+ if (!XI2C_IOREAD_BITS(pdata, IC_ENABLE, ABORT))
+ return 0;
+
+ usleep_range(500, 600);
+ }
+
+ return -EBUSY;
+}
+
+static int xgbe_i2c_set_enable(struct xgbe_prv_data *pdata, bool enable)
+{
+ unsigned int wait = XGBE_DISABLE_COUNT;
+ unsigned int mode = enable ? 1 : 0;
+
+ while (wait--) {
+ XI2C_IOWRITE_BITS(pdata, IC_ENABLE, EN, mode);
+ if (XI2C_IOREAD_BITS(pdata, IC_ENABLE_STATUS, EN) == mode)
+ return 0;
+
+ usleep_range(100, 110);
+ }
+
+ return -EBUSY;
+}
+
+static int xgbe_i2c_disable(struct xgbe_prv_data *pdata)
+{
+ unsigned int ret;
+
+ ret = xgbe_i2c_set_enable(pdata, false);
+ if (ret) {
+ /* Disable failed, try an abort */
+ ret = xgbe_i2c_abort(pdata);
+ if (ret)
+ return ret;
+
+ /* Abort succeeded, try to disable again */
+ ret = xgbe_i2c_set_enable(pdata, false);
+ }
+
+ return ret;
+}
+
+static int xgbe_i2c_enable(struct xgbe_prv_data *pdata)
+{
+ return xgbe_i2c_set_enable(pdata, true);
+}
+
+static void xgbe_i2c_clear_all_interrupts(struct xgbe_prv_data *pdata)
+{
+ XI2C_IOREAD(pdata, IC_CLR_INTR);
+}
+
+static void xgbe_i2c_disable_interrupts(struct xgbe_prv_data *pdata)
+{
+ XI2C_IOWRITE(pdata, IC_INTR_MASK, 0);
+}
+
+static void xgbe_i2c_enable_interrupts(struct xgbe_prv_data *pdata)
+{
+ XI2C_IOWRITE(pdata, IC_INTR_MASK, XGBE_DEFAULT_INT_MASK);
+}
+
+static void xgbe_i2c_write(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_i2c_op_state *state = &pdata->i2c.op_state;
+ unsigned int tx_slots;
+ unsigned int cmd;
+
+ /* Configured to never receive Rx overflows, so fill up Tx fifo */
+ tx_slots = pdata->i2c.tx_fifo_size - XI2C_IOREAD(pdata, IC_TXFLR);
+ while (tx_slots && state->tx_len) {
+ if (state->op->cmd == XGBE_I2C_CMD_READ)
+ cmd = XGBE_I2C_READ;
+ else
+ cmd = *state->tx_buf++;
+
+ if (state->tx_len == 1)
+ XI2C_SET_BITS(cmd, IC_DATA_CMD, STOP, 1);
+
+ XI2C_IOWRITE(pdata, IC_DATA_CMD, cmd);
+
+ tx_slots--;
+ state->tx_len--;
+ }
+
+ /* No more Tx operations, so ignore TX_EMPTY and return */
+ if (!state->tx_len)
+ XI2C_IOWRITE_BITS(pdata, IC_INTR_MASK, TX_EMPTY, 0);
+}
+
+static void xgbe_i2c_read(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_i2c_op_state *state = &pdata->i2c.op_state;
+ unsigned int rx_slots;
+
+ /* Anything to be read? */
+ if (state->op->cmd != XGBE_I2C_CMD_READ)
+ return;
+
+ rx_slots = XI2C_IOREAD(pdata, IC_RXFLR);
+ while (rx_slots && state->rx_len) {
+ *state->rx_buf++ = XI2C_IOREAD(pdata, IC_DATA_CMD);
+ state->rx_len--;
+ rx_slots--;
+ }
+}
+
+static void xgbe_i2c_clear_isr_interrupts(struct xgbe_prv_data *pdata,
+ unsigned int isr)
+{
+ struct xgbe_i2c_op_state *state = &pdata->i2c.op_state;
+
+ if (isr & XGBE_INTR_TX_ABRT) {
+ state->tx_abort_source = XI2C_IOREAD(pdata, IC_TX_ABRT_SOURCE);
+ XI2C_IOREAD(pdata, IC_CLR_TX_ABRT);
+ }
+
+ if (isr & XGBE_INTR_STOP_DET)
+ XI2C_IOREAD(pdata, IC_CLR_STOP_DET);
+}
+
+static irqreturn_t xgbe_i2c_isr(int irq, void *data)
+{
+ struct xgbe_prv_data *pdata = (struct xgbe_prv_data *)data;
+ struct xgbe_i2c_op_state *state = &pdata->i2c.op_state;
+ unsigned int isr;
+
+ isr = XI2C_IOREAD(pdata, IC_RAW_INTR_STAT);
+ netif_dbg(pdata, intr, pdata->netdev,
+ "I2C interrupt received: status=%#010x\n", isr);
+
+ xgbe_i2c_clear_isr_interrupts(pdata, isr);
+
+ if (isr & XGBE_INTR_TX_ABRT) {
+ netif_dbg(pdata, link, pdata->netdev,
+ "I2C TX_ABRT received (%#010x) for target %#04x\n",
+ state->tx_abort_source, state->op->target);
+
+ xgbe_i2c_disable_interrupts(pdata);
+
+ state->ret = -EIO;
+ goto out;
+ }
+
+ /* Check for data in the Rx fifo */
+ xgbe_i2c_read(pdata);
+
+ /* Fill up the Tx fifo next */
+ xgbe_i2c_write(pdata);
+
+out:
+ /* Complete on an error or STOP condition */
+ if (state->ret || XI2C_GET_BITS(isr, IC_RAW_INTR_STAT, STOP_DET))
+ complete(&pdata->i2c_complete);
+
+ return IRQ_HANDLED;
+}
+
+static void xgbe_i2c_set_mode(struct xgbe_prv_data *pdata)
+{
+ unsigned int reg;
+
+ reg = XI2C_IOREAD(pdata, IC_CON);
+ XI2C_SET_BITS(reg, IC_CON, MASTER_MODE, 1);
+ XI2C_SET_BITS(reg, IC_CON, SLAVE_DISABLE, 1);
+ XI2C_SET_BITS(reg, IC_CON, RESTART_EN, 1);
+ XI2C_SET_BITS(reg, IC_CON, SPEED, XGBE_STD_SPEED);
+ XI2C_SET_BITS(reg, IC_CON, RX_FIFO_FULL_HOLD, 1);
+ XI2C_IOWRITE(pdata, IC_CON, reg);
+}
+
+static void xgbe_i2c_get_features(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_i2c *i2c = &pdata->i2c;
+ unsigned int reg;
+
+ reg = XI2C_IOREAD(pdata, IC_COMP_PARAM_1);
+ i2c->max_speed_mode = XI2C_GET_BITS(reg, IC_COMP_PARAM_1,
+ MAX_SPEED_MODE);
+ i2c->rx_fifo_size = XI2C_GET_BITS(reg, IC_COMP_PARAM_1,
+ RX_BUFFER_DEPTH);
+ i2c->tx_fifo_size = XI2C_GET_BITS(reg, IC_COMP_PARAM_1,
+ TX_BUFFER_DEPTH);
+
+ if (netif_msg_probe(pdata))
+ dev_dbg(pdata->dev, "I2C features: %s=%u, %s=%u, %s=%u\n",
+ "MAX_SPEED_MODE", i2c->max_speed_mode,
+ "RX_BUFFER_DEPTH", i2c->rx_fifo_size,
+ "TX_BUFFER_DEPTH", i2c->tx_fifo_size);
+}
+
+static void xgbe_i2c_set_target(struct xgbe_prv_data *pdata, unsigned int addr)
+{
+ XI2C_IOWRITE(pdata, IC_TAR, addr);
+}
+
+static irqreturn_t xgbe_i2c_combined_isr(int irq, struct xgbe_prv_data *pdata)
+{
+ if (!XI2C_IOREAD(pdata, IC_RAW_INTR_STAT))
+ return IRQ_HANDLED;
+
+ return xgbe_i2c_isr(irq, pdata);
+}
+
+static int xgbe_i2c_xfer(struct xgbe_prv_data *pdata, struct xgbe_i2c_op *op)
+{
+ struct xgbe_i2c_op_state *state = &pdata->i2c.op_state;
+ int ret;
+
+ mutex_lock(&pdata->i2c_mutex);
+
+ reinit_completion(&pdata->i2c_complete);
+
+ ret = xgbe_i2c_disable(pdata);
+ if (ret) {
+ netdev_err(pdata->netdev, "failed to disable i2c master\n");
+ goto unlock;
+ }
+
+ xgbe_i2c_set_target(pdata, op->target);
+
+ memset(state, 0, sizeof(*state));
+ state->op = op;
+ state->tx_len = op->len;
+ state->tx_buf = op->buf;
+ state->rx_len = op->len;
+ state->rx_buf = op->buf;
+
+ xgbe_i2c_clear_all_interrupts(pdata);
+ ret = xgbe_i2c_enable(pdata);
+ if (ret) {
+ netdev_err(pdata->netdev, "failed to enable i2c master\n");
+ goto unlock;
+ }
+
+ /* Enabling the interrupts will cause the TX FIFO empty interrupt to
+ * fire and begin to process the command via the ISR.
+ */
+ xgbe_i2c_enable_interrupts(pdata);
+
+ if (!wait_for_completion_timeout(&pdata->i2c_complete, HZ)) {
+ netdev_err(pdata->netdev, "i2c operation timed out\n");
+ ret = -ETIMEDOUT;
+ goto disable;
+ }
+
+ ret = state->ret;
+ if (ret) {
+ if (state->tx_abort_source & IC_TX_ABRT_7B_ADDR_NOACK)
+ ret = -ENOTCONN;
+ else if (state->tx_abort_source & IC_TX_ABRT_ARB_LOST)
+ ret = -EAGAIN;
+ }
+
+disable:
+ xgbe_i2c_disable_interrupts(pdata);
+ xgbe_i2c_disable(pdata);
+
+unlock:
+ mutex_unlock(&pdata->i2c_mutex);
+
+ return ret;
+}
+
+static void xgbe_i2c_stop(struct xgbe_prv_data *pdata)
+{
+ if (!pdata->i2c.started)
+ return;
+
+ netif_dbg(pdata, link, pdata->netdev, "stopping I2C\n");
+
+ pdata->i2c.started = 0;
+
+ xgbe_i2c_disable_interrupts(pdata);
+ xgbe_i2c_disable(pdata);
+ xgbe_i2c_clear_all_interrupts(pdata);
+
+ if (pdata->dev_irq != pdata->i2c_irq)
+ devm_free_irq(pdata->dev, pdata->i2c_irq, pdata);
+}
+
+static int xgbe_i2c_start(struct xgbe_prv_data *pdata)
+{
+ int ret;
+
+ if (pdata->i2c.started)
+ return 0;
+
+ netif_dbg(pdata, link, pdata->netdev, "starting I2C\n");
+
+ /* If we have a separate I2C irq, enable it */
+ if (pdata->dev_irq != pdata->i2c_irq) {
+ ret = devm_request_irq(pdata->dev, pdata->i2c_irq,
+ xgbe_i2c_isr, 0, pdata->i2c_name,
+ pdata);
+ if (ret) {
+ netdev_err(pdata->netdev, "i2c irq request failed\n");
+ return ret;
+ }
+ }
+
+ pdata->i2c.started = 1;
+
+ return 0;
+}
+
+static int xgbe_i2c_init(struct xgbe_prv_data *pdata)
+{
+ int ret;
+
+ xgbe_i2c_disable_interrupts(pdata);
+
+ ret = xgbe_i2c_disable(pdata);
+ if (ret) {
+ dev_err(pdata->dev, "failed to disable i2c master\n");
+ return ret;
+ }
+
+ xgbe_i2c_get_features(pdata);
+
+ xgbe_i2c_set_mode(pdata);
+
+ xgbe_i2c_clear_all_interrupts(pdata);
+
+ return 0;
+}
+
+void xgbe_init_function_ptrs_i2c(struct xgbe_i2c_if *i2c_if)
+{
+ i2c_if->i2c_init = xgbe_i2c_init;
+
+ i2c_if->i2c_start = xgbe_i2c_start;
+ i2c_if->i2c_stop = xgbe_i2c_stop;
+
+ i2c_if->i2c_xfer = xgbe_i2c_xfer;
+
+ i2c_if->i2c_isr = xgbe_i2c_combined_isr;
+}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
index 6997f11..b87a899 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
@@ -116,19 +116,10 @@
#include <linux/module.h>
#include <linux/device.h>
-#include <linux/platform_device.h>
#include <linux/spinlock.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/of_net.h>
-#include <linux/of_address.h>
-#include <linux/of_platform.h>
-#include <linux/clk.h>
-#include <linux/property.h>
-#include <linux/acpi.h>
-#include <linux/mdio.h>
#include "xgbe.h"
#include "xgbe-common.h"
@@ -145,42 +136,6 @@ MODULE_PARM_DESC(debug, " Network interface message level setting");
static const u32 default_msg_level = (NETIF_MSG_LINK | NETIF_MSG_IFDOWN |
NETIF_MSG_IFUP);
-static const u32 xgbe_serdes_blwc[] = {
- XGBE_SPEED_1000_BLWC,
- XGBE_SPEED_2500_BLWC,
- XGBE_SPEED_10000_BLWC,
-};
-
-static const u32 xgbe_serdes_cdr_rate[] = {
- XGBE_SPEED_1000_CDR,
- XGBE_SPEED_2500_CDR,
- XGBE_SPEED_10000_CDR,
-};
-
-static const u32 xgbe_serdes_pq_skew[] = {
- XGBE_SPEED_1000_PQ,
- XGBE_SPEED_2500_PQ,
- XGBE_SPEED_10000_PQ,
-};
-
-static const u32 xgbe_serdes_tx_amp[] = {
- XGBE_SPEED_1000_TXAMP,
- XGBE_SPEED_2500_TXAMP,
- XGBE_SPEED_10000_TXAMP,
-};
-
-static const u32 xgbe_serdes_dfe_tap_cfg[] = {
- XGBE_SPEED_1000_DFE_TAP_CONFIG,
- XGBE_SPEED_2500_DFE_TAP_CONFIG,
- XGBE_SPEED_10000_DFE_TAP_CONFIG,
-};
-
-static const u32 xgbe_serdes_dfe_tap_ena[] = {
- XGBE_SPEED_1000_DFE_TAP_ENABLE,
- XGBE_SPEED_2500_DFE_TAP_ENABLE,
- XGBE_SPEED_10000_DFE_TAP_ENABLE,
-};
-
static void xgbe_default_config(struct xgbe_prv_data *pdata)
{
DBGPR("-->xgbe_default_config\n");
@@ -206,456 +161,124 @@ static void xgbe_init_all_fptrs(struct xgbe_prv_data *pdata)
{
xgbe_init_function_ptrs_dev(&pdata->hw_if);
xgbe_init_function_ptrs_phy(&pdata->phy_if);
+ xgbe_init_function_ptrs_i2c(&pdata->i2c_if);
xgbe_init_function_ptrs_desc(&pdata->desc_if);
+
+ pdata->vdata->init_function_ptrs_phy_impl(&pdata->phy_if);
}
-#ifdef CONFIG_ACPI
-static int xgbe_acpi_support(struct xgbe_prv_data *pdata)
-{
- struct device *dev = pdata->dev;
- u32 property;
- int ret;
-
- /* Obtain the system clock setting */
- ret = device_property_read_u32(dev, XGBE_ACPI_DMA_FREQ, &property);
- if (ret) {
- dev_err(dev, "unable to obtain %s property\n",
- XGBE_ACPI_DMA_FREQ);
- return ret;
- }
- pdata->sysclk_rate = property;
-
- /* Obtain the PTP clock setting */
- ret = device_property_read_u32(dev, XGBE_ACPI_PTP_FREQ, &property);
- if (ret) {
- dev_err(dev, "unable to obtain %s property\n",
- XGBE_ACPI_PTP_FREQ);
- return ret;
- }
- pdata->ptpclk_rate = property;
-
- return 0;
-}
-#else /* CONFIG_ACPI */
-static int xgbe_acpi_support(struct xgbe_prv_data *pdata)
-{
- return -EINVAL;
-}
-#endif /* CONFIG_ACPI */
-
-#ifdef CONFIG_OF
-static int xgbe_of_support(struct xgbe_prv_data *pdata)
-{
- struct device *dev = pdata->dev;
-
- /* Obtain the system clock setting */
- pdata->sysclk = devm_clk_get(dev, XGBE_DMA_CLOCK);
- if (IS_ERR(pdata->sysclk)) {
- dev_err(dev, "dma devm_clk_get failed\n");
- return PTR_ERR(pdata->sysclk);
- }
- pdata->sysclk_rate = clk_get_rate(pdata->sysclk);
-
- /* Obtain the PTP clock setting */
- pdata->ptpclk = devm_clk_get(dev, XGBE_PTP_CLOCK);
- if (IS_ERR(pdata->ptpclk)) {
- dev_err(dev, "ptp devm_clk_get failed\n");
- return PTR_ERR(pdata->ptpclk);
- }
- pdata->ptpclk_rate = clk_get_rate(pdata->ptpclk);
-
- return 0;
-}
-
-static struct platform_device *xgbe_of_get_phy_pdev(struct xgbe_prv_data *pdata)
-{
- struct device *dev = pdata->dev;
- struct device_node *phy_node;
- struct platform_device *phy_pdev;
-
- phy_node = of_parse_phandle(dev->of_node, "phy-handle", 0);
- if (phy_node) {
- /* Old style device tree:
- * The XGBE and PHY resources are separate
- */
- phy_pdev = of_find_device_by_node(phy_node);
- of_node_put(phy_node);
- } else {
- /* New style device tree:
- * The XGBE and PHY resources are grouped together with
- * the PHY resources listed last
- */
- get_device(dev);
- phy_pdev = pdata->pdev;
- }
-
- return phy_pdev;
-}
-#else /* CONFIG_OF */
-static int xgbe_of_support(struct xgbe_prv_data *pdata)
-{
- return -EINVAL;
-}
-
-static struct platform_device *xgbe_of_get_phy_pdev(struct xgbe_prv_data *pdata)
-{
- return NULL;
-}
-#endif /* CONFIG_OF */
-
-static unsigned int xgbe_resource_count(struct platform_device *pdev,
- unsigned int type)
-{
- unsigned int count;
- int i;
-
- for (i = 0, count = 0; i < pdev->num_resources; i++) {
- struct resource *res = &pdev->resource[i];
-
- if (type == resource_type(res))
- count++;
- }
-
- return count;
-}
-
-static struct platform_device *xgbe_get_phy_pdev(struct xgbe_prv_data *pdata)
-{
- struct platform_device *phy_pdev;
-
- if (pdata->use_acpi) {
- get_device(pdata->dev);
- phy_pdev = pdata->pdev;
- } else {
- phy_pdev = xgbe_of_get_phy_pdev(pdata);
- }
-
- return phy_pdev;
-}
-
-static int xgbe_probe(struct platform_device *pdev)
+struct xgbe_prv_data *xgbe_alloc_pdata(struct device *dev)
{
struct xgbe_prv_data *pdata;
struct net_device *netdev;
- struct device *dev = &pdev->dev, *phy_dev;
- struct platform_device *phy_pdev;
- struct resource *res;
- const char *phy_mode;
- unsigned int i, phy_memnum, phy_irqnum;
- enum dev_dma_attr attr;
- int ret;
-
- DBGPR("--> xgbe_probe\n");
netdev = alloc_etherdev_mq(sizeof(struct xgbe_prv_data),
XGBE_MAX_DMA_CHANNELS);
if (!netdev) {
- dev_err(dev, "alloc_etherdev failed\n");
- ret = -ENOMEM;
- goto err_alloc;
+ dev_err(dev, "alloc_etherdev_mq failed\n");
+ return ERR_PTR(-ENOMEM);
}
SET_NETDEV_DEV(netdev, dev);
pdata = netdev_priv(netdev);
pdata->netdev = netdev;
- pdata->pdev = pdev;
- pdata->adev = ACPI_COMPANION(dev);
pdata->dev = dev;
- platform_set_drvdata(pdev, netdev);
spin_lock_init(&pdata->lock);
spin_lock_init(&pdata->xpcs_lock);
mutex_init(&pdata->rss_mutex);
spin_lock_init(&pdata->tstamp_lock);
+ mutex_init(&pdata->i2c_mutex);
+ init_completion(&pdata->i2c_complete);
+ init_completion(&pdata->mdio_complete);
pdata->msg_enable = netif_msg_init(debug, default_msg_level);
set_bit(XGBE_DOWN, &pdata->dev_state);
+ set_bit(XGBE_STOPPED, &pdata->dev_state);
- /* Check if we should use ACPI or DT */
- pdata->use_acpi = dev->of_node ? 0 : 1;
+ return pdata;
+}
- phy_pdev = xgbe_get_phy_pdev(pdata);
- if (!phy_pdev) {
- dev_err(dev, "unable to obtain phy device\n");
- ret = -EINVAL;
- goto err_phydev;
+void xgbe_free_pdata(struct xgbe_prv_data *pdata)
+{
+ struct net_device *netdev = pdata->netdev;
+
+ free_netdev(netdev);
+}
+
+void xgbe_set_counts(struct xgbe_prv_data *pdata)
+{
+ /* Set all the function pointers */
+ xgbe_init_all_fptrs(pdata);
+
+ /* Populate the hardware features */
+ xgbe_get_all_hw_features(pdata);
+
+ /* Set default max values if not provided */
+ if (!pdata->tx_max_channel_count)
+ pdata->tx_max_channel_count = pdata->hw_feat.tx_ch_cnt;
+ if (!pdata->rx_max_channel_count)
+ pdata->rx_max_channel_count = pdata->hw_feat.rx_ch_cnt;
+
+ if (!pdata->tx_max_q_count)
+ pdata->tx_max_q_count = pdata->hw_feat.tx_q_cnt;
+ if (!pdata->rx_max_q_count)
+ pdata->rx_max_q_count = pdata->hw_feat.rx_q_cnt;
+
+ /* Calculate the number of Tx and Rx rings to be created
+ * -Tx (DMA) Channels map 1-to-1 to Tx Queues so set
+ * the number of Tx queues to the number of Tx channels
+ * enabled
+ * -Rx (DMA) Channels do not map 1-to-1 so use the actual
+ * number of Rx queues or maximum allowed
+ */
+ pdata->tx_ring_count = min_t(unsigned int, num_online_cpus(),
+ pdata->hw_feat.tx_ch_cnt);
+ pdata->tx_ring_count = min_t(unsigned int, pdata->tx_ring_count,
+ pdata->tx_max_channel_count);
+ pdata->tx_ring_count = min_t(unsigned int, pdata->tx_ring_count,
+ pdata->tx_max_q_count);
+
+ pdata->tx_q_count = pdata->tx_ring_count;
+
+ pdata->rx_ring_count = min_t(unsigned int, num_online_cpus(),
+ pdata->hw_feat.rx_ch_cnt);
+ pdata->rx_ring_count = min_t(unsigned int, pdata->rx_ring_count,
+ pdata->rx_max_channel_count);
+
+ pdata->rx_q_count = min_t(unsigned int, pdata->hw_feat.rx_q_cnt,
+ pdata->rx_max_q_count);
+
+ if (netif_msg_probe(pdata)) {
+ dev_dbg(pdata->dev, "TX/RX DMA channel count = %u/%u\n",
+ pdata->tx_ring_count, pdata->rx_ring_count);
+ dev_dbg(pdata->dev, "TX/RX hardware queue count = %u/%u\n",
+ pdata->tx_q_count, pdata->rx_q_count);
}
- phy_dev = &phy_pdev->dev;
+}
- if (pdev == phy_pdev) {
- /* New style device tree or ACPI:
- * The XGBE and PHY resources are grouped together with
- * the PHY resources listed last
- */
- phy_memnum = xgbe_resource_count(pdev, IORESOURCE_MEM) - 3;
- phy_irqnum = xgbe_resource_count(pdev, IORESOURCE_IRQ) - 1;
- } else {
- /* Old style device tree:
- * The XGBE and PHY resources are separate
- */
- phy_memnum = 0;
- phy_irqnum = 0;
- }
-
- /* Set and validate the number of descriptors for a ring */
- BUILD_BUG_ON_NOT_POWER_OF_2(XGBE_TX_DESC_CNT);
- pdata->tx_desc_count = XGBE_TX_DESC_CNT;
- if (pdata->tx_desc_count & (pdata->tx_desc_count - 1)) {
- dev_err(dev, "tx descriptor count (%d) is not valid\n",
- pdata->tx_desc_count);
- ret = -EINVAL;
- goto err_io;
- }
- BUILD_BUG_ON_NOT_POWER_OF_2(XGBE_RX_DESC_CNT);
- pdata->rx_desc_count = XGBE_RX_DESC_CNT;
- if (pdata->rx_desc_count & (pdata->rx_desc_count - 1)) {
- dev_err(dev, "rx descriptor count (%d) is not valid\n",
- pdata->rx_desc_count);
- ret = -EINVAL;
- goto err_io;
- }
-
- /* Obtain the mmio areas for the device */
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- pdata->xgmac_regs = devm_ioremap_resource(dev, res);
- if (IS_ERR(pdata->xgmac_regs)) {
- dev_err(dev, "xgmac ioremap failed\n");
- ret = PTR_ERR(pdata->xgmac_regs);
- goto err_io;
- }
- if (netif_msg_probe(pdata))
- dev_dbg(dev, "xgmac_regs = %p\n", pdata->xgmac_regs);
-
- res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
- pdata->xpcs_regs = devm_ioremap_resource(dev, res);
- if (IS_ERR(pdata->xpcs_regs)) {
- dev_err(dev, "xpcs ioremap failed\n");
- ret = PTR_ERR(pdata->xpcs_regs);
- goto err_io;
- }
- if (netif_msg_probe(pdata))
- dev_dbg(dev, "xpcs_regs = %p\n", pdata->xpcs_regs);
-
- res = platform_get_resource(phy_pdev, IORESOURCE_MEM, phy_memnum++);
- pdata->rxtx_regs = devm_ioremap_resource(dev, res);
- if (IS_ERR(pdata->rxtx_regs)) {
- dev_err(dev, "rxtx ioremap failed\n");
- ret = PTR_ERR(pdata->rxtx_regs);
- goto err_io;
- }
- if (netif_msg_probe(pdata))
- dev_dbg(dev, "rxtx_regs = %p\n", pdata->rxtx_regs);
-
- res = platform_get_resource(phy_pdev, IORESOURCE_MEM, phy_memnum++);
- pdata->sir0_regs = devm_ioremap_resource(dev, res);
- if (IS_ERR(pdata->sir0_regs)) {
- dev_err(dev, "sir0 ioremap failed\n");
- ret = PTR_ERR(pdata->sir0_regs);
- goto err_io;
- }
- if (netif_msg_probe(pdata))
- dev_dbg(dev, "sir0_regs = %p\n", pdata->sir0_regs);
-
- res = platform_get_resource(phy_pdev, IORESOURCE_MEM, phy_memnum++);
- pdata->sir1_regs = devm_ioremap_resource(dev, res);
- if (IS_ERR(pdata->sir1_regs)) {
- dev_err(dev, "sir1 ioremap failed\n");
- ret = PTR_ERR(pdata->sir1_regs);
- goto err_io;
- }
- if (netif_msg_probe(pdata))
- dev_dbg(dev, "sir1_regs = %p\n", pdata->sir1_regs);
-
- /* Retrieve the MAC address */
- ret = device_property_read_u8_array(dev, XGBE_MAC_ADDR_PROPERTY,
- pdata->mac_addr,
- sizeof(pdata->mac_addr));
- if (ret || !is_valid_ether_addr(pdata->mac_addr)) {
- dev_err(dev, "invalid %s property\n", XGBE_MAC_ADDR_PROPERTY);
- if (!ret)
- ret = -EINVAL;
- goto err_io;
- }
-
- /* Retrieve the PHY mode - it must be "xgmii" */
- ret = device_property_read_string(dev, XGBE_PHY_MODE_PROPERTY,
- &phy_mode);
- if (ret || strcmp(phy_mode, phy_modes(PHY_INTERFACE_MODE_XGMII))) {
- dev_err(dev, "invalid %s property\n", XGBE_PHY_MODE_PROPERTY);
- if (!ret)
- ret = -EINVAL;
- goto err_io;
- }
- pdata->phy_mode = PHY_INTERFACE_MODE_XGMII;
-
- /* Check for per channel interrupt support */
- if (device_property_present(dev, XGBE_DMA_IRQS_PROPERTY))
- pdata->per_channel_irq = 1;
-
- /* Retrieve the PHY speedset */
- ret = device_property_read_u32(phy_dev, XGBE_SPEEDSET_PROPERTY,
- &pdata->speed_set);
- if (ret) {
- dev_err(dev, "invalid %s property\n", XGBE_SPEEDSET_PROPERTY);
- goto err_io;
- }
-
- switch (pdata->speed_set) {
- case XGBE_SPEEDSET_1000_10000:
- case XGBE_SPEEDSET_2500_10000:
- break;
- default:
- dev_err(dev, "invalid %s property\n", XGBE_SPEEDSET_PROPERTY);
- ret = -EINVAL;
- goto err_io;
- }
-
- /* Retrieve the PHY configuration properties */
- if (device_property_present(phy_dev, XGBE_BLWC_PROPERTY)) {
- ret = device_property_read_u32_array(phy_dev,
- XGBE_BLWC_PROPERTY,
- pdata->serdes_blwc,
- XGBE_SPEEDS);
- if (ret) {
- dev_err(dev, "invalid %s property\n",
- XGBE_BLWC_PROPERTY);
- goto err_io;
- }
- } else {
- memcpy(pdata->serdes_blwc, xgbe_serdes_blwc,
- sizeof(pdata->serdes_blwc));
- }
-
- if (device_property_present(phy_dev, XGBE_CDR_RATE_PROPERTY)) {
- ret = device_property_read_u32_array(phy_dev,
- XGBE_CDR_RATE_PROPERTY,
- pdata->serdes_cdr_rate,
- XGBE_SPEEDS);
- if (ret) {
- dev_err(dev, "invalid %s property\n",
- XGBE_CDR_RATE_PROPERTY);
- goto err_io;
- }
- } else {
- memcpy(pdata->serdes_cdr_rate, xgbe_serdes_cdr_rate,
- sizeof(pdata->serdes_cdr_rate));
- }
-
- if (device_property_present(phy_dev, XGBE_PQ_SKEW_PROPERTY)) {
- ret = device_property_read_u32_array(phy_dev,
- XGBE_PQ_SKEW_PROPERTY,
- pdata->serdes_pq_skew,
- XGBE_SPEEDS);
- if (ret) {
- dev_err(dev, "invalid %s property\n",
- XGBE_PQ_SKEW_PROPERTY);
- goto err_io;
- }
- } else {
- memcpy(pdata->serdes_pq_skew, xgbe_serdes_pq_skew,
- sizeof(pdata->serdes_pq_skew));
- }
-
- if (device_property_present(phy_dev, XGBE_TX_AMP_PROPERTY)) {
- ret = device_property_read_u32_array(phy_dev,
- XGBE_TX_AMP_PROPERTY,
- pdata->serdes_tx_amp,
- XGBE_SPEEDS);
- if (ret) {
- dev_err(dev, "invalid %s property\n",
- XGBE_TX_AMP_PROPERTY);
- goto err_io;
- }
- } else {
- memcpy(pdata->serdes_tx_amp, xgbe_serdes_tx_amp,
- sizeof(pdata->serdes_tx_amp));
- }
-
- if (device_property_present(phy_dev, XGBE_DFE_CFG_PROPERTY)) {
- ret = device_property_read_u32_array(phy_dev,
- XGBE_DFE_CFG_PROPERTY,
- pdata->serdes_dfe_tap_cfg,
- XGBE_SPEEDS);
- if (ret) {
- dev_err(dev, "invalid %s property\n",
- XGBE_DFE_CFG_PROPERTY);
- goto err_io;
- }
- } else {
- memcpy(pdata->serdes_dfe_tap_cfg, xgbe_serdes_dfe_tap_cfg,
- sizeof(pdata->serdes_dfe_tap_cfg));
- }
-
- if (device_property_present(phy_dev, XGBE_DFE_ENA_PROPERTY)) {
- ret = device_property_read_u32_array(phy_dev,
- XGBE_DFE_ENA_PROPERTY,
- pdata->serdes_dfe_tap_ena,
- XGBE_SPEEDS);
- if (ret) {
- dev_err(dev, "invalid %s property\n",
- XGBE_DFE_ENA_PROPERTY);
- goto err_io;
- }
- } else {
- memcpy(pdata->serdes_dfe_tap_ena, xgbe_serdes_dfe_tap_ena,
- sizeof(pdata->serdes_dfe_tap_ena));
- }
-
- /* Obtain device settings unique to ACPI/OF */
- if (pdata->use_acpi)
- ret = xgbe_acpi_support(pdata);
- else
- ret = xgbe_of_support(pdata);
- if (ret)
- goto err_io;
-
- /* Set the DMA coherency values */
- attr = device_get_dma_attr(dev);
- if (attr == DEV_DMA_NOT_SUPPORTED) {
- dev_err(dev, "DMA is not supported");
- ret = -ENODEV;
- goto err_io;
- }
- pdata->coherent = (attr == DEV_DMA_COHERENT);
- if (pdata->coherent) {
- pdata->axdomain = XGBE_DMA_OS_AXDOMAIN;
- pdata->arcache = XGBE_DMA_OS_ARCACHE;
- pdata->awcache = XGBE_DMA_OS_AWCACHE;
- } else {
- pdata->axdomain = XGBE_DMA_SYS_AXDOMAIN;
- pdata->arcache = XGBE_DMA_SYS_ARCACHE;
- pdata->awcache = XGBE_DMA_SYS_AWCACHE;
- }
-
- /* Get the device interrupt */
- ret = platform_get_irq(pdev, 0);
- if (ret < 0) {
- dev_err(dev, "platform_get_irq 0 failed\n");
- goto err_io;
- }
- pdata->dev_irq = ret;
-
- /* Get the auto-negotiation interrupt */
- ret = platform_get_irq(phy_pdev, phy_irqnum++);
- if (ret < 0) {
- dev_err(dev, "platform_get_irq phy 0 failed\n");
- goto err_io;
- }
- pdata->an_irq = ret;
+int xgbe_config_netdev(struct xgbe_prv_data *pdata)
+{
+ struct net_device *netdev = pdata->netdev;
+ struct device *dev = pdata->dev;
+ unsigned int i;
+ int ret;
netdev->irq = pdata->dev_irq;
netdev->base_addr = (unsigned long)pdata->xgmac_regs;
memcpy(netdev->dev_addr, pdata->mac_addr, netdev->addr_len);
- /* Set all the function pointers */
- xgbe_init_all_fptrs(pdata);
+ /* Initialize ECC timestamps */
+ pdata->tx_sec_period = jiffies;
+ pdata->tx_ded_period = jiffies;
+ pdata->rx_sec_period = jiffies;
+ pdata->rx_ded_period = jiffies;
+ pdata->desc_sec_period = jiffies;
+ pdata->desc_ded_period = jiffies;
/* Issue software reset to device */
pdata->hw_if.exit(pdata);
- /* Populate the hardware features */
- xgbe_get_all_hw_features(pdata);
-
/* Set default configuration data */
xgbe_default_config(pdata);
@@ -664,33 +287,46 @@ static int xgbe_probe(struct platform_device *pdev)
DMA_BIT_MASK(pdata->hw_feat.dma_width));
if (ret) {
dev_err(dev, "dma_set_mask_and_coherent failed\n");
- goto err_io;
+ return ret;
}
- /* Calculate the number of Tx and Rx rings to be created
- * -Tx (DMA) Channels map 1-to-1 to Tx Queues so set
- * the number of Tx queues to the number of Tx channels
- * enabled
- * -Rx (DMA) Channels do not map 1-to-1 so use the actual
- * number of Rx queues
- */
- pdata->tx_ring_count = min_t(unsigned int, num_online_cpus(),
- pdata->hw_feat.tx_ch_cnt);
- pdata->tx_q_count = pdata->tx_ring_count;
+ /* Set default max values if not provided */
+ if (!pdata->tx_max_fifo_size)
+ pdata->tx_max_fifo_size = pdata->hw_feat.tx_fifo_size;
+ if (!pdata->rx_max_fifo_size)
+ pdata->rx_max_fifo_size = pdata->hw_feat.rx_fifo_size;
+
+ /* Set and validate the number of descriptors for a ring */
+ BUILD_BUG_ON_NOT_POWER_OF_2(XGBE_TX_DESC_CNT);
+ pdata->tx_desc_count = XGBE_TX_DESC_CNT;
+
+ BUILD_BUG_ON_NOT_POWER_OF_2(XGBE_RX_DESC_CNT);
+ pdata->rx_desc_count = XGBE_RX_DESC_CNT;
+
+ /* Adjust the number of queues based on interrupts assigned */
+ if (pdata->channel_irq_count) {
+ pdata->tx_ring_count = min_t(unsigned int, pdata->tx_ring_count,
+ pdata->channel_irq_count);
+ pdata->rx_ring_count = min_t(unsigned int, pdata->rx_ring_count,
+ pdata->channel_irq_count);
+
+ if (netif_msg_probe(pdata))
+ dev_dbg(pdata->dev,
+ "adjusted TX/RX DMA channel count = %u/%u\n",
+ pdata->tx_ring_count, pdata->rx_ring_count);
+ }
+
+ /* Set the number of queues */
ret = netif_set_real_num_tx_queues(netdev, pdata->tx_ring_count);
if (ret) {
dev_err(dev, "error setting real tx queue count\n");
- goto err_io;
+ return ret;
}
- pdata->rx_ring_count = min_t(unsigned int,
- netif_get_num_default_rss_queues(),
- pdata->hw_feat.rx_ch_cnt);
- pdata->rx_q_count = pdata->hw_feat.rx_q_cnt;
ret = netif_set_real_num_rx_queues(netdev, pdata->rx_ring_count);
if (ret) {
dev_err(dev, "error setting real rx queue count\n");
- goto err_io;
+ return ret;
}
/* Initialize RSS hash key and lookup table */
@@ -705,7 +341,9 @@ static int xgbe_probe(struct platform_device *pdev)
XGMAC_SET_BITS(pdata->rss_options, MAC_RSSCR, UDP4TE, 1);
/* Call MDIO/PHY initialization routine */
- pdata->phy_if.phy_init(pdata);
+ ret = pdata->phy_if.phy_init(pdata);
+ if (ret)
+ return ret;
/* Set device operations */
netdev->netdev_ops = xgbe_get_netdev_ops();
@@ -752,13 +390,21 @@ static int xgbe_probe(struct platform_device *pdev)
ret = register_netdev(netdev);
if (ret) {
dev_err(dev, "net device registration failed\n");
- goto err_io;
+ return ret;
}
/* Create the PHY/ANEG name based on netdev name */
snprintf(pdata->an_name, sizeof(pdata->an_name) - 1, "%s-pcs",
netdev_name(netdev));
+ /* Create the ECC name based on netdev name */
+ snprintf(pdata->ecc_name, sizeof(pdata->ecc_name) - 1, "%s-ecc",
+ netdev_name(netdev));
+
+ /* Create the I2C name based on netdev name */
+ snprintf(pdata->i2c_name, sizeof(pdata->i2c_name) - 1, "%s-i2c",
+ netdev_name(netdev));
+
/* Create workqueues */
pdata->dev_workqueue =
create_singlethread_workqueue(netdev_name(netdev));
@@ -780,11 +426,10 @@ static int xgbe_probe(struct platform_device *pdev)
xgbe_debugfs_init(pdata);
- platform_device_put(phy_pdev);
-
- netdev_notice(netdev, "net device enabled\n");
-
- DBGPR("<-- xgbe_probe\n");
+ netif_dbg(pdata, drv, pdata->netdev, "%u Tx software queues\n",
+ pdata->tx_ring_count);
+ netif_dbg(pdata, drv, pdata->netdev, "%u Rx software queues\n",
+ pdata->rx_ring_count);
return 0;
@@ -794,29 +439,19 @@ static int xgbe_probe(struct platform_device *pdev)
err_netdev:
unregister_netdev(netdev);
-err_io:
- platform_device_put(phy_pdev);
-
-err_phydev:
- free_netdev(netdev);
-
-err_alloc:
- dev_notice(dev, "net device not enabled\n");
-
return ret;
}
-static int xgbe_remove(struct platform_device *pdev)
+void xgbe_deconfig_netdev(struct xgbe_prv_data *pdata)
{
- struct net_device *netdev = platform_get_drvdata(pdev);
- struct xgbe_prv_data *pdata = netdev_priv(netdev);
-
- DBGPR("-->xgbe_remove\n");
+ struct net_device *netdev = pdata->netdev;
xgbe_debugfs_exit(pdata);
xgbe_ptp_unregister(pdata);
+ pdata->phy_if.phy_exit(pdata);
+
flush_workqueue(pdata->an_workqueue);
destroy_workqueue(pdata->an_workqueue);
@@ -824,94 +459,29 @@ static int xgbe_remove(struct platform_device *pdev)
destroy_workqueue(pdata->dev_workqueue);
unregister_netdev(netdev);
+}
- free_netdev(netdev);
+static int __init xgbe_mod_init(void)
+{
+ int ret;
- DBGPR("<--xgbe_remove\n");
+ ret = xgbe_platform_init();
+ if (ret)
+ return ret;
+
+ ret = xgbe_pci_init();
+ if (ret)
+ return ret;
return 0;
}
-#ifdef CONFIG_PM
-static int xgbe_suspend(struct device *dev)
+static void __exit xgbe_mod_exit(void)
{
- struct net_device *netdev = dev_get_drvdata(dev);
- struct xgbe_prv_data *pdata = netdev_priv(netdev);
- int ret = 0;
+ xgbe_pci_exit();
- DBGPR("-->xgbe_suspend\n");
-
- if (netif_running(netdev))
- ret = xgbe_powerdown(netdev, XGMAC_DRIVER_CONTEXT);
-
- pdata->lpm_ctrl = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
- pdata->lpm_ctrl |= MDIO_CTRL1_LPOWER;
- XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, pdata->lpm_ctrl);
-
- DBGPR("<--xgbe_suspend\n");
-
- return ret;
+ xgbe_platform_exit();
}
-static int xgbe_resume(struct device *dev)
-{
- struct net_device *netdev = dev_get_drvdata(dev);
- struct xgbe_prv_data *pdata = netdev_priv(netdev);
- int ret = 0;
-
- DBGPR("-->xgbe_resume\n");
-
- pdata->lpm_ctrl &= ~MDIO_CTRL1_LPOWER;
- XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, pdata->lpm_ctrl);
-
- if (netif_running(netdev)) {
- ret = xgbe_powerup(netdev, XGMAC_DRIVER_CONTEXT);
-
- /* Schedule a restart in case the link or phy state changed
- * while we were powered down.
- */
- schedule_work(&pdata->restart_work);
- }
-
- DBGPR("<--xgbe_resume\n");
-
- return ret;
-}
-#endif /* CONFIG_PM */
-
-#ifdef CONFIG_ACPI
-static const struct acpi_device_id xgbe_acpi_match[] = {
- { "AMDI8001", 0 },
- {},
-};
-
-MODULE_DEVICE_TABLE(acpi, xgbe_acpi_match);
-#endif
-
-#ifdef CONFIG_OF
-static const struct of_device_id xgbe_of_match[] = {
- { .compatible = "amd,xgbe-seattle-v1a", },
- {},
-};
-
-MODULE_DEVICE_TABLE(of, xgbe_of_match);
-#endif
-
-static SIMPLE_DEV_PM_OPS(xgbe_pm_ops, xgbe_suspend, xgbe_resume);
-
-static struct platform_driver xgbe_driver = {
- .driver = {
- .name = "amd-xgbe",
-#ifdef CONFIG_ACPI
- .acpi_match_table = xgbe_acpi_match,
-#endif
-#ifdef CONFIG_OF
- .of_match_table = xgbe_of_match,
-#endif
- .pm = &xgbe_pm_ops,
- },
- .probe = xgbe_probe,
- .remove = xgbe_remove,
-};
-
-module_platform_driver(xgbe_driver);
+module_init(xgbe_mod_init);
+module_exit(xgbe_mod_exit);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 84c5d29..4c5b90e 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -125,7 +125,79 @@
#include "xgbe.h"
#include "xgbe-common.h"
-static void xgbe_an_enable_kr_training(struct xgbe_prv_data *pdata)
+static void xgbe_an37_clear_interrupts(struct xgbe_prv_data *pdata)
+{
+ int reg;
+
+ reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_STAT);
+ reg &= ~XGBE_AN_CL37_INT_MASK;
+ XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_STAT, reg);
+}
+
+static void xgbe_an37_disable_interrupts(struct xgbe_prv_data *pdata)
+{
+ int reg;
+
+ reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_CTRL);
+ reg &= ~XGBE_AN_CL37_INT_MASK;
+ XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_CTRL, reg);
+
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_PCS_DIG_CTRL);
+ reg &= ~XGBE_PCS_CL37_BP;
+ XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_PCS_DIG_CTRL, reg);
+}
+
+static void xgbe_an37_enable_interrupts(struct xgbe_prv_data *pdata)
+{
+ int reg;
+
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_PCS_DIG_CTRL);
+ reg |= XGBE_PCS_CL37_BP;
+ XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_PCS_DIG_CTRL, reg);
+
+ reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_CTRL);
+ reg |= XGBE_AN_CL37_INT_MASK;
+ XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_CTRL, reg);
+}
+
+static void xgbe_an73_clear_interrupts(struct xgbe_prv_data *pdata)
+{
+ XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INT, 0);
+}
+
+static void xgbe_an73_disable_interrupts(struct xgbe_prv_data *pdata)
+{
+ XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INTMASK, 0);
+}
+
+static void xgbe_an73_enable_interrupts(struct xgbe_prv_data *pdata)
+{
+ XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INTMASK, XGBE_AN_CL73_INT_MASK);
+}
+
+static void xgbe_an_enable_interrupts(struct xgbe_prv_data *pdata)
+{
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ xgbe_an73_enable_interrupts(pdata);
+ break;
+ case XGBE_AN_MODE_CL37:
+ case XGBE_AN_MODE_CL37_SGMII:
+ xgbe_an37_enable_interrupts(pdata);
+ break;
+ default:
+ break;
+ }
+}
+
+static void xgbe_an_clear_interrupts_all(struct xgbe_prv_data *pdata)
+{
+ xgbe_an73_clear_interrupts(pdata);
+ xgbe_an37_clear_interrupts(pdata);
+}
+
+static void xgbe_an73_enable_kr_training(struct xgbe_prv_data *pdata)
{
unsigned int reg;
@@ -135,7 +207,7 @@ static void xgbe_an_enable_kr_training(struct xgbe_prv_data *pdata)
XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, reg);
}
-static void xgbe_an_disable_kr_training(struct xgbe_prv_data *pdata)
+static void xgbe_an73_disable_kr_training(struct xgbe_prv_data *pdata)
{
unsigned int reg;
@@ -145,283 +217,192 @@ static void xgbe_an_disable_kr_training(struct xgbe_prv_data *pdata)
XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, reg);
}
-static void xgbe_pcs_power_cycle(struct xgbe_prv_data *pdata)
+static void xgbe_kr_mode(struct xgbe_prv_data *pdata)
{
- unsigned int reg;
-
- reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
-
- reg |= MDIO_CTRL1_LPOWER;
- XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
-
- usleep_range(75, 100);
-
- reg &= ~MDIO_CTRL1_LPOWER;
- XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
-}
-
-static void xgbe_serdes_start_ratechange(struct xgbe_prv_data *pdata)
-{
- /* Assert Rx and Tx ratechange */
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, RATECHANGE, 1);
-}
-
-static void xgbe_serdes_complete_ratechange(struct xgbe_prv_data *pdata)
-{
- unsigned int wait;
- u16 status;
-
- /* Release Rx and Tx ratechange */
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, RATECHANGE, 0);
-
- /* Wait for Rx and Tx ready */
- wait = XGBE_RATECHANGE_COUNT;
- while (wait--) {
- usleep_range(50, 75);
-
- status = XSIR0_IOREAD(pdata, SIR0_STATUS);
- if (XSIR_GET_BITS(status, SIR0_STATUS, RX_READY) &&
- XSIR_GET_BITS(status, SIR0_STATUS, TX_READY))
- goto rx_reset;
- }
-
- netif_dbg(pdata, link, pdata->netdev, "SerDes rx/tx not ready (%#hx)\n",
- status);
-
-rx_reset:
- /* Perform Rx reset for the DFE changes */
- XRXTX_IOWRITE_BITS(pdata, RXTX_REG6, RESETB_RXD, 0);
- XRXTX_IOWRITE_BITS(pdata, RXTX_REG6, RESETB_RXD, 1);
-}
-
-static void xgbe_xgmii_mode(struct xgbe_prv_data *pdata)
-{
- unsigned int reg;
-
/* Enable KR training */
- xgbe_an_enable_kr_training(pdata);
+ xgbe_an73_enable_kr_training(pdata);
/* Set MAC to 10G speed */
- pdata->hw_if.set_xgmii_speed(pdata);
+ pdata->hw_if.set_speed(pdata, SPEED_10000);
- /* Set PCS to KR/10G speed */
- reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL2);
- reg &= ~MDIO_PCS_CTRL2_TYPE;
- reg |= MDIO_PCS_CTRL2_10GBR;
- XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL2, reg);
-
- reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
- reg &= ~MDIO_CTRL1_SPEEDSEL;
- reg |= MDIO_CTRL1_SPEED10G;
- XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
-
- xgbe_pcs_power_cycle(pdata);
-
- /* Set SerDes to 10G speed */
- xgbe_serdes_start_ratechange(pdata);
-
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, DATARATE, XGBE_SPEED_10000_RATE);
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, WORDMODE, XGBE_SPEED_10000_WORD);
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, PLLSEL, XGBE_SPEED_10000_PLL);
-
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, CDR_RATE,
- pdata->serdes_cdr_rate[XGBE_SPEED_10000]);
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, TXAMP,
- pdata->serdes_tx_amp[XGBE_SPEED_10000]);
- XRXTX_IOWRITE_BITS(pdata, RXTX_REG20, BLWC_ENA,
- pdata->serdes_blwc[XGBE_SPEED_10000]);
- XRXTX_IOWRITE_BITS(pdata, RXTX_REG114, PQ_REG,
- pdata->serdes_pq_skew[XGBE_SPEED_10000]);
- XRXTX_IOWRITE_BITS(pdata, RXTX_REG129, RXDFE_CONFIG,
- pdata->serdes_dfe_tap_cfg[XGBE_SPEED_10000]);
- XRXTX_IOWRITE(pdata, RXTX_REG22,
- pdata->serdes_dfe_tap_ena[XGBE_SPEED_10000]);
-
- xgbe_serdes_complete_ratechange(pdata);
-
- netif_dbg(pdata, link, pdata->netdev, "10GbE KR mode set\n");
+ /* Call PHY implementation support to complete rate change */
+ pdata->phy_if.phy_impl.set_mode(pdata, XGBE_MODE_KR);
}
-static void xgbe_gmii_2500_mode(struct xgbe_prv_data *pdata)
+static void xgbe_kx_2500_mode(struct xgbe_prv_data *pdata)
{
- unsigned int reg;
-
/* Disable KR training */
- xgbe_an_disable_kr_training(pdata);
+ xgbe_an73_disable_kr_training(pdata);
/* Set MAC to 2.5G speed */
- pdata->hw_if.set_gmii_2500_speed(pdata);
+ pdata->hw_if.set_speed(pdata, SPEED_2500);
- /* Set PCS to KX/1G speed */
- reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL2);
- reg &= ~MDIO_PCS_CTRL2_TYPE;
- reg |= MDIO_PCS_CTRL2_10GBX;
- XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL2, reg);
-
- reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
- reg &= ~MDIO_CTRL1_SPEEDSEL;
- reg |= MDIO_CTRL1_SPEED1G;
- XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
-
- xgbe_pcs_power_cycle(pdata);
-
- /* Set SerDes to 2.5G speed */
- xgbe_serdes_start_ratechange(pdata);
-
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, DATARATE, XGBE_SPEED_2500_RATE);
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, WORDMODE, XGBE_SPEED_2500_WORD);
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, PLLSEL, XGBE_SPEED_2500_PLL);
-
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, CDR_RATE,
- pdata->serdes_cdr_rate[XGBE_SPEED_2500]);
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, TXAMP,
- pdata->serdes_tx_amp[XGBE_SPEED_2500]);
- XRXTX_IOWRITE_BITS(pdata, RXTX_REG20, BLWC_ENA,
- pdata->serdes_blwc[XGBE_SPEED_2500]);
- XRXTX_IOWRITE_BITS(pdata, RXTX_REG114, PQ_REG,
- pdata->serdes_pq_skew[XGBE_SPEED_2500]);
- XRXTX_IOWRITE_BITS(pdata, RXTX_REG129, RXDFE_CONFIG,
- pdata->serdes_dfe_tap_cfg[XGBE_SPEED_2500]);
- XRXTX_IOWRITE(pdata, RXTX_REG22,
- pdata->serdes_dfe_tap_ena[XGBE_SPEED_2500]);
-
- xgbe_serdes_complete_ratechange(pdata);
-
- netif_dbg(pdata, link, pdata->netdev, "2.5GbE KX mode set\n");
+ /* Call PHY implementation support to complete rate change */
+ pdata->phy_if.phy_impl.set_mode(pdata, XGBE_MODE_KX_2500);
}
-static void xgbe_gmii_mode(struct xgbe_prv_data *pdata)
+static void xgbe_kx_1000_mode(struct xgbe_prv_data *pdata)
{
- unsigned int reg;
-
/* Disable KR training */
- xgbe_an_disable_kr_training(pdata);
+ xgbe_an73_disable_kr_training(pdata);
/* Set MAC to 1G speed */
- pdata->hw_if.set_gmii_speed(pdata);
+ pdata->hw_if.set_speed(pdata, SPEED_1000);
- /* Set PCS to KX/1G speed */
- reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL2);
- reg &= ~MDIO_PCS_CTRL2_TYPE;
- reg |= MDIO_PCS_CTRL2_10GBX;
- XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL2, reg);
-
- reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
- reg &= ~MDIO_CTRL1_SPEEDSEL;
- reg |= MDIO_CTRL1_SPEED1G;
- XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
-
- xgbe_pcs_power_cycle(pdata);
-
- /* Set SerDes to 1G speed */
- xgbe_serdes_start_ratechange(pdata);
-
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, DATARATE, XGBE_SPEED_1000_RATE);
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, WORDMODE, XGBE_SPEED_1000_WORD);
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, PLLSEL, XGBE_SPEED_1000_PLL);
-
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, CDR_RATE,
- pdata->serdes_cdr_rate[XGBE_SPEED_1000]);
- XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, TXAMP,
- pdata->serdes_tx_amp[XGBE_SPEED_1000]);
- XRXTX_IOWRITE_BITS(pdata, RXTX_REG20, BLWC_ENA,
- pdata->serdes_blwc[XGBE_SPEED_1000]);
- XRXTX_IOWRITE_BITS(pdata, RXTX_REG114, PQ_REG,
- pdata->serdes_pq_skew[XGBE_SPEED_1000]);
- XRXTX_IOWRITE_BITS(pdata, RXTX_REG129, RXDFE_CONFIG,
- pdata->serdes_dfe_tap_cfg[XGBE_SPEED_1000]);
- XRXTX_IOWRITE(pdata, RXTX_REG22,
- pdata->serdes_dfe_tap_ena[XGBE_SPEED_1000]);
-
- xgbe_serdes_complete_ratechange(pdata);
-
- netif_dbg(pdata, link, pdata->netdev, "1GbE KX mode set\n");
+ /* Call PHY implementation support to complete rate change */
+ pdata->phy_if.phy_impl.set_mode(pdata, XGBE_MODE_KX_1000);
}
-static void xgbe_cur_mode(struct xgbe_prv_data *pdata,
- enum xgbe_mode *mode)
+static void xgbe_sfi_mode(struct xgbe_prv_data *pdata)
{
- unsigned int reg;
+ /* If a KR re-driver is present, change to KR mode instead */
+ if (pdata->kr_redrv)
+ return xgbe_kr_mode(pdata);
- reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL2);
- if ((reg & MDIO_PCS_CTRL2_TYPE) == MDIO_PCS_CTRL2_10GBR)
- *mode = XGBE_MODE_KR;
- else
- *mode = XGBE_MODE_KX;
+ /* Disable KR training */
+ xgbe_an73_disable_kr_training(pdata);
+
+ /* Set MAC to 10G speed */
+ pdata->hw_if.set_speed(pdata, SPEED_10000);
+
+ /* Call PHY implementation support to complete rate change */
+ pdata->phy_if.phy_impl.set_mode(pdata, XGBE_MODE_SFI);
+}
+
+static void xgbe_x_mode(struct xgbe_prv_data *pdata)
+{
+ /* Disable KR training */
+ xgbe_an73_disable_kr_training(pdata);
+
+ /* Set MAC to 1G speed */
+ pdata->hw_if.set_speed(pdata, SPEED_1000);
+
+ /* Call PHY implementation support to complete rate change */
+ pdata->phy_if.phy_impl.set_mode(pdata, XGBE_MODE_X);
+}
+
+static void xgbe_sgmii_1000_mode(struct xgbe_prv_data *pdata)
+{
+ /* Disable KR training */
+ xgbe_an73_disable_kr_training(pdata);
+
+ /* Set MAC to 1G speed */
+ pdata->hw_if.set_speed(pdata, SPEED_1000);
+
+ /* Call PHY implementation support to complete rate change */
+ pdata->phy_if.phy_impl.set_mode(pdata, XGBE_MODE_SGMII_1000);
+}
+
+static void xgbe_sgmii_100_mode(struct xgbe_prv_data *pdata)
+{
+ /* Disable KR training */
+ xgbe_an73_disable_kr_training(pdata);
+
+ /* Set MAC to 1G speed */
+ pdata->hw_if.set_speed(pdata, SPEED_1000);
+
+ /* Call PHY implementation support to complete rate change */
+ pdata->phy_if.phy_impl.set_mode(pdata, XGBE_MODE_SGMII_100);
+}
+
+static enum xgbe_mode xgbe_cur_mode(struct xgbe_prv_data *pdata)
+{
+ return pdata->phy_if.phy_impl.cur_mode(pdata);
}
static bool xgbe_in_kr_mode(struct xgbe_prv_data *pdata)
{
- enum xgbe_mode mode;
+ return (xgbe_cur_mode(pdata) == XGBE_MODE_KR);
+}
- xgbe_cur_mode(pdata, &mode);
-
- return (mode == XGBE_MODE_KR);
+static void xgbe_change_mode(struct xgbe_prv_data *pdata,
+ enum xgbe_mode mode)
+{
+ switch (mode) {
+ case XGBE_MODE_KX_1000:
+ xgbe_kx_1000_mode(pdata);
+ break;
+ case XGBE_MODE_KX_2500:
+ xgbe_kx_2500_mode(pdata);
+ break;
+ case XGBE_MODE_KR:
+ xgbe_kr_mode(pdata);
+ break;
+ case XGBE_MODE_SGMII_100:
+ xgbe_sgmii_100_mode(pdata);
+ break;
+ case XGBE_MODE_SGMII_1000:
+ xgbe_sgmii_1000_mode(pdata);
+ break;
+ case XGBE_MODE_X:
+ xgbe_x_mode(pdata);
+ break;
+ case XGBE_MODE_SFI:
+ xgbe_sfi_mode(pdata);
+ break;
+ case XGBE_MODE_UNKNOWN:
+ break;
+ default:
+ netif_dbg(pdata, link, pdata->netdev,
+ "invalid operation mode requested (%u)\n", mode);
+ }
}
static void xgbe_switch_mode(struct xgbe_prv_data *pdata)
{
- /* If we are in KR switch to KX, and vice-versa */
- if (xgbe_in_kr_mode(pdata)) {
- if (pdata->speed_set == XGBE_SPEEDSET_1000_10000)
- xgbe_gmii_mode(pdata);
- else
- xgbe_gmii_2500_mode(pdata);
- } else {
- xgbe_xgmii_mode(pdata);
- }
+ xgbe_change_mode(pdata, pdata->phy_if.phy_impl.switch_mode(pdata));
}
static void xgbe_set_mode(struct xgbe_prv_data *pdata,
enum xgbe_mode mode)
{
- enum xgbe_mode cur_mode;
+ if (mode == xgbe_cur_mode(pdata))
+ return;
- xgbe_cur_mode(pdata, &cur_mode);
- if (mode != cur_mode)
- xgbe_switch_mode(pdata);
+ xgbe_change_mode(pdata, mode);
}
-static bool xgbe_use_xgmii_mode(struct xgbe_prv_data *pdata)
+static bool xgbe_use_mode(struct xgbe_prv_data *pdata,
+ enum xgbe_mode mode)
{
- if (pdata->phy.autoneg == AUTONEG_ENABLE) {
- if (pdata->phy.advertising & ADVERTISED_10000baseKR_Full)
- return true;
- } else {
- if (pdata->phy.speed == SPEED_10000)
- return true;
- }
-
- return false;
+ return pdata->phy_if.phy_impl.use_mode(pdata, mode);
}
-static bool xgbe_use_gmii_2500_mode(struct xgbe_prv_data *pdata)
+static void xgbe_an37_set(struct xgbe_prv_data *pdata, bool enable,
+ bool restart)
{
- if (pdata->phy.autoneg == AUTONEG_ENABLE) {
- if (pdata->phy.advertising & ADVERTISED_2500baseX_Full)
- return true;
- } else {
- if (pdata->phy.speed == SPEED_2500)
- return true;
- }
+ unsigned int reg;
- return false;
+ reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_CTRL1);
+ reg &= ~MDIO_VEND2_CTRL1_AN_ENABLE;
+
+ if (enable)
+ reg |= MDIO_VEND2_CTRL1_AN_ENABLE;
+
+ if (restart)
+ reg |= MDIO_VEND2_CTRL1_AN_RESTART;
+
+ XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_CTRL1, reg);
}
-static bool xgbe_use_gmii_mode(struct xgbe_prv_data *pdata)
+static void xgbe_an37_restart(struct xgbe_prv_data *pdata)
{
- if (pdata->phy.autoneg == AUTONEG_ENABLE) {
- if (pdata->phy.advertising & ADVERTISED_1000baseKX_Full)
- return true;
- } else {
- if (pdata->phy.speed == SPEED_1000)
- return true;
- }
+ xgbe_an37_enable_interrupts(pdata);
+ xgbe_an37_set(pdata, true, true);
- return false;
+ netif_dbg(pdata, link, pdata->netdev, "CL37 AN enabled/restarted\n");
}
-static void xgbe_set_an(struct xgbe_prv_data *pdata, bool enable, bool restart)
+static void xgbe_an37_disable(struct xgbe_prv_data *pdata)
+{
+ xgbe_an37_set(pdata, false, false);
+ xgbe_an37_disable_interrupts(pdata);
+
+ netif_dbg(pdata, link, pdata->netdev, "CL37 AN disabled\n");
+}
+
+static void xgbe_an73_set(struct xgbe_prv_data *pdata, bool enable,
+ bool restart)
{
unsigned int reg;
@@ -437,22 +418,62 @@ static void xgbe_set_an(struct xgbe_prv_data *pdata, bool enable, bool restart)
XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_CTRL1, reg);
}
-static void xgbe_restart_an(struct xgbe_prv_data *pdata)
+static void xgbe_an73_restart(struct xgbe_prv_data *pdata)
{
- xgbe_set_an(pdata, true, true);
+ xgbe_an73_enable_interrupts(pdata);
+ xgbe_an73_set(pdata, true, true);
- netif_dbg(pdata, link, pdata->netdev, "AN enabled/restarted\n");
+ netif_dbg(pdata, link, pdata->netdev, "CL73 AN enabled/restarted\n");
}
-static void xgbe_disable_an(struct xgbe_prv_data *pdata)
+static void xgbe_an73_disable(struct xgbe_prv_data *pdata)
{
- xgbe_set_an(pdata, false, false);
+ xgbe_an73_set(pdata, false, false);
+ xgbe_an73_disable_interrupts(pdata);
- netif_dbg(pdata, link, pdata->netdev, "AN disabled\n");
+ netif_dbg(pdata, link, pdata->netdev, "CL73 AN disabled\n");
}
-static enum xgbe_an xgbe_an_tx_training(struct xgbe_prv_data *pdata,
- enum xgbe_rx *state)
+static void xgbe_an_restart(struct xgbe_prv_data *pdata)
+{
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ xgbe_an73_restart(pdata);
+ break;
+ case XGBE_AN_MODE_CL37:
+ case XGBE_AN_MODE_CL37_SGMII:
+ xgbe_an37_restart(pdata);
+ break;
+ default:
+ break;
+ }
+}
+
+static void xgbe_an_disable(struct xgbe_prv_data *pdata)
+{
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ xgbe_an73_disable(pdata);
+ break;
+ case XGBE_AN_MODE_CL37:
+ case XGBE_AN_MODE_CL37_SGMII:
+ xgbe_an37_disable(pdata);
+ break;
+ default:
+ break;
+ }
+}
+
+static void xgbe_an_disable_all(struct xgbe_prv_data *pdata)
+{
+ xgbe_an73_disable(pdata);
+ xgbe_an37_disable(pdata);
+}
+
+static enum xgbe_an xgbe_an73_tx_training(struct xgbe_prv_data *pdata,
+ enum xgbe_rx *state)
{
unsigned int ad_reg, lp_reg, reg;
@@ -476,13 +497,15 @@ static enum xgbe_an xgbe_an_tx_training(struct xgbe_prv_data *pdata,
/* Start KR training */
reg = XMDIO_READ(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL);
if (reg & XGBE_KR_TRAINING_ENABLE) {
- XSIR0_IOWRITE_BITS(pdata, SIR0_KR_RT_1, RESET, 1);
+ if (pdata->phy_if.phy_impl.kr_training_pre)
+ pdata->phy_if.phy_impl.kr_training_pre(pdata);
reg |= XGBE_KR_TRAINING_START;
XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL,
reg);
- XSIR0_IOWRITE_BITS(pdata, SIR0_KR_RT_1, RESET, 0);
+ if (pdata->phy_if.phy_impl.kr_training_post)
+ pdata->phy_if.phy_impl.kr_training_post(pdata);
netif_dbg(pdata, link, pdata->netdev,
"KR training initiated\n");
@@ -491,8 +514,8 @@ static enum xgbe_an xgbe_an_tx_training(struct xgbe_prv_data *pdata,
return XGBE_AN_PAGE_RECEIVED;
}
-static enum xgbe_an xgbe_an_tx_xnp(struct xgbe_prv_data *pdata,
- enum xgbe_rx *state)
+static enum xgbe_an xgbe_an73_tx_xnp(struct xgbe_prv_data *pdata,
+ enum xgbe_rx *state)
{
u16 msg;
@@ -508,8 +531,8 @@ static enum xgbe_an xgbe_an_tx_xnp(struct xgbe_prv_data *pdata,
return XGBE_AN_PAGE_RECEIVED;
}
-static enum xgbe_an xgbe_an_rx_bpa(struct xgbe_prv_data *pdata,
- enum xgbe_rx *state)
+static enum xgbe_an xgbe_an73_rx_bpa(struct xgbe_prv_data *pdata,
+ enum xgbe_rx *state)
{
unsigned int link_support;
unsigned int reg, ad_reg, lp_reg;
@@ -528,12 +551,12 @@ static enum xgbe_an xgbe_an_rx_bpa(struct xgbe_prv_data *pdata,
return ((ad_reg & XGBE_XNP_NP_EXCHANGE) ||
(lp_reg & XGBE_XNP_NP_EXCHANGE))
- ? xgbe_an_tx_xnp(pdata, state)
- : xgbe_an_tx_training(pdata, state);
+ ? xgbe_an73_tx_xnp(pdata, state)
+ : xgbe_an73_tx_training(pdata, state);
}
-static enum xgbe_an xgbe_an_rx_xnp(struct xgbe_prv_data *pdata,
- enum xgbe_rx *state)
+static enum xgbe_an xgbe_an73_rx_xnp(struct xgbe_prv_data *pdata,
+ enum xgbe_rx *state)
{
unsigned int ad_reg, lp_reg;
@@ -543,11 +566,11 @@ static enum xgbe_an xgbe_an_rx_xnp(struct xgbe_prv_data *pdata,
return ((ad_reg & XGBE_XNP_NP_EXCHANGE) ||
(lp_reg & XGBE_XNP_NP_EXCHANGE))
- ? xgbe_an_tx_xnp(pdata, state)
- : xgbe_an_tx_training(pdata, state);
+ ? xgbe_an73_tx_xnp(pdata, state)
+ : xgbe_an73_tx_training(pdata, state);
}
-static enum xgbe_an xgbe_an_page_received(struct xgbe_prv_data *pdata)
+static enum xgbe_an xgbe_an73_page_received(struct xgbe_prv_data *pdata)
{
enum xgbe_rx *state;
unsigned long an_timeout;
@@ -566,20 +589,20 @@ static enum xgbe_an xgbe_an_page_received(struct xgbe_prv_data *pdata)
pdata->an_start = jiffies;
netif_dbg(pdata, link, pdata->netdev,
- "AN timed out, resetting state\n");
+ "CL73 AN timed out, resetting state\n");
}
}
state = xgbe_in_kr_mode(pdata) ? &pdata->kr_state
- : &pdata->kx_state;
+ : &pdata->kx_state;
switch (*state) {
case XGBE_RX_BPA:
- ret = xgbe_an_rx_bpa(pdata, state);
+ ret = xgbe_an73_rx_bpa(pdata, state);
break;
case XGBE_RX_XNP:
- ret = xgbe_an_rx_xnp(pdata, state);
+ ret = xgbe_an73_rx_xnp(pdata, state);
break;
default:
@@ -589,7 +612,7 @@ static enum xgbe_an xgbe_an_page_received(struct xgbe_prv_data *pdata)
return ret;
}
-static enum xgbe_an xgbe_an_incompat_link(struct xgbe_prv_data *pdata)
+static enum xgbe_an xgbe_an73_incompat_link(struct xgbe_prv_data *pdata)
{
/* Be sure we aren't looping trying to negotiate */
if (xgbe_in_kr_mode(pdata)) {
@@ -611,23 +634,43 @@ static enum xgbe_an xgbe_an_incompat_link(struct xgbe_prv_data *pdata)
return XGBE_AN_NO_LINK;
}
- xgbe_disable_an(pdata);
+ xgbe_an73_disable(pdata);
xgbe_switch_mode(pdata);
- xgbe_restart_an(pdata);
+ xgbe_an73_restart(pdata);
return XGBE_AN_INCOMPAT_LINK;
}
-static irqreturn_t xgbe_an_isr(int irq, void *data)
+static void xgbe_an37_isr(struct xgbe_prv_data *pdata)
{
- struct xgbe_prv_data *pdata = (struct xgbe_prv_data *)data;
-
- netif_dbg(pdata, intr, pdata->netdev, "AN interrupt received\n");
+ unsigned int reg;
/* Disable AN interrupts */
- XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INTMASK, 0);
+ xgbe_an37_disable_interrupts(pdata);
+
+ /* Save the interrupt(s) that fired */
+ reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_STAT);
+ pdata->an_int = reg & XGBE_AN_CL37_INT_MASK;
+ pdata->an_status = reg & ~XGBE_AN_CL37_INT_MASK;
+
+ if (pdata->an_int) {
+ /* Clear the interrupt(s) that fired and process them */
+ reg &= ~XGBE_AN_CL37_INT_MASK;
+ XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_STAT, reg);
+
+ queue_work(pdata->an_workqueue, &pdata->an_irq_work);
+ } else {
+ /* Enable AN interrupts */
+ xgbe_an37_enable_interrupts(pdata);
+ }
+}
+
+static void xgbe_an73_isr(struct xgbe_prv_data *pdata)
+{
+ /* Disable AN interrupts */
+ xgbe_an73_disable_interrupts(pdata);
/* Save the interrupt(s) that fired */
pdata->an_int = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_INT);
@@ -639,13 +682,37 @@ static irqreturn_t xgbe_an_isr(int irq, void *data)
queue_work(pdata->an_workqueue, &pdata->an_irq_work);
} else {
/* Enable AN interrupts */
- XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INTMASK,
- XGBE_AN_INT_MASK);
+ xgbe_an73_enable_interrupts(pdata);
+ }
+}
+
+static irqreturn_t xgbe_an_isr(int irq, void *data)
+{
+ struct xgbe_prv_data *pdata = (struct xgbe_prv_data *)data;
+
+ netif_dbg(pdata, intr, pdata->netdev, "AN interrupt received\n");
+
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ xgbe_an73_isr(pdata);
+ break;
+ case XGBE_AN_MODE_CL37:
+ case XGBE_AN_MODE_CL37_SGMII:
+ xgbe_an37_isr(pdata);
+ break;
+ default:
+ break;
}
return IRQ_HANDLED;
}
+static irqreturn_t xgbe_an_combined_isr(int irq, struct xgbe_prv_data *pdata)
+{
+ return xgbe_an_isr(irq, pdata);
+}
+
static void xgbe_an_irq_work(struct work_struct *work)
{
struct xgbe_prv_data *pdata = container_of(work,
@@ -679,36 +746,87 @@ static const char *xgbe_state_as_string(enum xgbe_an state)
}
}
-static void xgbe_an_state_machine(struct work_struct *work)
+static void xgbe_an37_state_machine(struct xgbe_prv_data *pdata)
{
- struct xgbe_prv_data *pdata = container_of(work,
- struct xgbe_prv_data,
- an_work);
enum xgbe_an cur_state = pdata->an_state;
- mutex_lock(&pdata->an_mutex);
+ if (!pdata->an_int)
+ return;
+
+ if (pdata->an_int & XGBE_AN_CL37_INT_CMPLT) {
+ pdata->an_state = XGBE_AN_COMPLETE;
+ pdata->an_int &= ~XGBE_AN_CL37_INT_CMPLT;
+
+ /* If SGMII is enabled, check the link status */
+ if ((pdata->an_mode == XGBE_AN_MODE_CL37_SGMII) &&
+ !(pdata->an_status & XGBE_SGMII_AN_LINK_STATUS))
+ pdata->an_state = XGBE_AN_NO_LINK;
+ }
+
+ netif_dbg(pdata, link, pdata->netdev, "CL37 AN %s\n",
+ xgbe_state_as_string(pdata->an_state));
+
+ cur_state = pdata->an_state;
+
+ switch (pdata->an_state) {
+ case XGBE_AN_READY:
+ break;
+
+ case XGBE_AN_COMPLETE:
+ netif_dbg(pdata, link, pdata->netdev,
+ "Auto negotiation successful\n");
+ break;
+
+ case XGBE_AN_NO_LINK:
+ break;
+
+ default:
+ pdata->an_state = XGBE_AN_ERROR;
+ }
+
+ if (pdata->an_state == XGBE_AN_ERROR) {
+ netdev_err(pdata->netdev,
+ "error during auto-negotiation, state=%u\n",
+ cur_state);
+
+ pdata->an_int = 0;
+ xgbe_an37_clear_interrupts(pdata);
+ }
+
+ if (pdata->an_state >= XGBE_AN_COMPLETE) {
+ pdata->an_result = pdata->an_state;
+ pdata->an_state = XGBE_AN_READY;
+
+ netif_dbg(pdata, link, pdata->netdev, "CL37 AN result: %s\n",
+ xgbe_state_as_string(pdata->an_result));
+ }
+
+ xgbe_an37_enable_interrupts(pdata);
+}
+
+static void xgbe_an73_state_machine(struct xgbe_prv_data *pdata)
+{
+ enum xgbe_an cur_state = pdata->an_state;
if (!pdata->an_int)
- goto out;
+ return;
next_int:
- if (pdata->an_int & XGBE_AN_PG_RCV) {
+ if (pdata->an_int & XGBE_AN_CL73_PG_RCV) {
pdata->an_state = XGBE_AN_PAGE_RECEIVED;
- pdata->an_int &= ~XGBE_AN_PG_RCV;
- } else if (pdata->an_int & XGBE_AN_INC_LINK) {
+ pdata->an_int &= ~XGBE_AN_CL73_PG_RCV;
+ } else if (pdata->an_int & XGBE_AN_CL73_INC_LINK) {
pdata->an_state = XGBE_AN_INCOMPAT_LINK;
- pdata->an_int &= ~XGBE_AN_INC_LINK;
- } else if (pdata->an_int & XGBE_AN_INT_CMPLT) {
+ pdata->an_int &= ~XGBE_AN_CL73_INC_LINK;
+ } else if (pdata->an_int & XGBE_AN_CL73_INT_CMPLT) {
pdata->an_state = XGBE_AN_COMPLETE;
- pdata->an_int &= ~XGBE_AN_INT_CMPLT;
+ pdata->an_int &= ~XGBE_AN_CL73_INT_CMPLT;
} else {
pdata->an_state = XGBE_AN_ERROR;
}
- pdata->an_result = pdata->an_state;
-
again:
- netif_dbg(pdata, link, pdata->netdev, "AN %s\n",
+ netif_dbg(pdata, link, pdata->netdev, "CL73 AN %s\n",
xgbe_state_as_string(pdata->an_state));
cur_state = pdata->an_state;
@@ -719,14 +837,14 @@ static void xgbe_an_state_machine(struct work_struct *work)
break;
case XGBE_AN_PAGE_RECEIVED:
- pdata->an_state = xgbe_an_page_received(pdata);
+ pdata->an_state = xgbe_an73_page_received(pdata);
pdata->an_supported++;
break;
case XGBE_AN_INCOMPAT_LINK:
pdata->an_supported = 0;
pdata->parallel_detect = 0;
- pdata->an_state = xgbe_an_incompat_link(pdata);
+ pdata->an_state = xgbe_an73_incompat_link(pdata);
break;
case XGBE_AN_COMPLETE:
@@ -745,14 +863,14 @@ static void xgbe_an_state_machine(struct work_struct *work)
if (pdata->an_state == XGBE_AN_NO_LINK) {
pdata->an_int = 0;
- XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INT, 0);
+ xgbe_an73_clear_interrupts(pdata);
} else if (pdata->an_state == XGBE_AN_ERROR) {
netdev_err(pdata->netdev,
"error during auto-negotiation, state=%u\n",
cur_state);
pdata->an_int = 0;
- XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INT, 0);
+ xgbe_an73_clear_interrupts(pdata);
}
if (pdata->an_state >= XGBE_AN_COMPLETE) {
@@ -762,7 +880,7 @@ static void xgbe_an_state_machine(struct work_struct *work)
pdata->kx_state = XGBE_RX_BPA;
pdata->an_start = 0;
- netif_dbg(pdata, link, pdata->netdev, "AN result: %s\n",
+ netif_dbg(pdata, link, pdata->netdev, "CL73 AN result: %s\n",
xgbe_state_as_string(pdata->an_result));
}
@@ -772,20 +890,88 @@ static void xgbe_an_state_machine(struct work_struct *work)
if (pdata->an_int)
goto next_int;
-out:
- /* Enable AN interrupts on the way out */
- XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INTMASK, XGBE_AN_INT_MASK);
+ xgbe_an73_enable_interrupts(pdata);
+}
+
+static void xgbe_an_state_machine(struct work_struct *work)
+{
+ struct xgbe_prv_data *pdata = container_of(work,
+ struct xgbe_prv_data,
+ an_work);
+
+ mutex_lock(&pdata->an_mutex);
+
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ xgbe_an73_state_machine(pdata);
+ break;
+ case XGBE_AN_MODE_CL37:
+ case XGBE_AN_MODE_CL37_SGMII:
+ xgbe_an37_state_machine(pdata);
+ break;
+ default:
+ break;
+ }
mutex_unlock(&pdata->an_mutex);
}
-static void xgbe_an_init(struct xgbe_prv_data *pdata)
+static void xgbe_an37_init(struct xgbe_prv_data *pdata)
{
- unsigned int reg;
+ unsigned int advertising, reg;
+
+ advertising = pdata->phy_if.phy_impl.an_advertising(pdata);
+
+ /* Set up Advertisement register */
+ reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_ADVERTISE);
+ if (advertising & ADVERTISED_Pause)
+ reg |= 0x100;
+ else
+ reg &= ~0x100;
+
+ if (advertising & ADVERTISED_Asym_Pause)
+ reg |= 0x80;
+ else
+ reg &= ~0x80;
+
+ /* Full duplex, but not half */
+ reg |= XGBE_AN_CL37_FD_MASK;
+ reg &= ~XGBE_AN_CL37_HD_MASK;
+
+ XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_ADVERTISE, reg);
+
+ /* Set up the Control register */
+ reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_CTRL);
+ reg &= ~XGBE_AN_CL37_TX_CONFIG_MASK;
+ reg &= ~XGBE_AN_CL37_PCS_MODE_MASK;
+
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL37:
+ reg |= XGBE_AN_CL37_PCS_MODE_BASEX;
+ break;
+ case XGBE_AN_MODE_CL37_SGMII:
+ reg |= XGBE_AN_CL37_PCS_MODE_SGMII;
+ break;
+ default:
+ break;
+ }
+
+ XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_CTRL, reg);
+
+ netif_dbg(pdata, link, pdata->netdev, "CL37 AN (%s) initialized\n",
+ (pdata->an_mode == XGBE_AN_MODE_CL37) ? "BaseX" : "SGMII");
+}
+
+static void xgbe_an73_init(struct xgbe_prv_data *pdata)
+{
+ unsigned int advertising, reg;
+
+ advertising = pdata->phy_if.phy_impl.an_advertising(pdata);
/* Set up Advertisement register 3 first */
reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2);
- if (pdata->phy.advertising & ADVERTISED_10000baseR_FEC)
+ if (advertising & ADVERTISED_10000baseR_FEC)
reg |= 0xc000;
else
reg &= ~0xc000;
@@ -794,13 +980,13 @@ static void xgbe_an_init(struct xgbe_prv_data *pdata)
/* Set up Advertisement register 2 next */
reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1);
- if (pdata->phy.advertising & ADVERTISED_10000baseKR_Full)
+ if (advertising & ADVERTISED_10000baseKR_Full)
reg |= 0x80;
else
reg &= ~0x80;
- if ((pdata->phy.advertising & ADVERTISED_1000baseKX_Full) ||
- (pdata->phy.advertising & ADVERTISED_2500baseX_Full))
+ if ((advertising & ADVERTISED_1000baseKX_Full) ||
+ (advertising & ADVERTISED_2500baseX_Full))
reg |= 0x20;
else
reg &= ~0x20;
@@ -809,12 +995,12 @@ static void xgbe_an_init(struct xgbe_prv_data *pdata)
/* Set up Advertisement register 1 last */
reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE);
- if (pdata->phy.advertising & ADVERTISED_Pause)
+ if (advertising & ADVERTISED_Pause)
reg |= 0x400;
else
reg &= ~0x400;
- if (pdata->phy.advertising & ADVERTISED_Asym_Pause)
+ if (advertising & ADVERTISED_Asym_Pause)
reg |= 0x800;
else
reg &= ~0x800;
@@ -824,7 +1010,25 @@ static void xgbe_an_init(struct xgbe_prv_data *pdata)
XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE, reg);
- netif_dbg(pdata, link, pdata->netdev, "AN initialized\n");
+ netif_dbg(pdata, link, pdata->netdev, "CL73 AN initialized\n");
+}
+
+static void xgbe_an_init(struct xgbe_prv_data *pdata)
+{
+ /* Set up advertisement registers based on current settings */
+ pdata->an_mode = pdata->phy_if.phy_impl.an_mode(pdata);
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ case XGBE_AN_MODE_CL73_REDRV:
+ xgbe_an73_init(pdata);
+ break;
+ case XGBE_AN_MODE_CL37:
+ case XGBE_AN_MODE_CL37_SGMII:
+ xgbe_an37_init(pdata);
+ break;
+ default:
+ break;
+ }
}
static const char *xgbe_phy_fc_string(struct xgbe_prv_data *pdata)
@@ -842,6 +1046,8 @@ static const char *xgbe_phy_fc_string(struct xgbe_prv_data *pdata)
static const char *xgbe_phy_speed_string(int speed)
{
switch (speed) {
+ case SPEED_100:
+ return "100Mbps";
case SPEED_1000:
return "1Gbps";
case SPEED_2500:
@@ -907,24 +1113,32 @@ static void xgbe_phy_adjust_link(struct xgbe_prv_data *pdata)
xgbe_phy_print_status(pdata);
}
+static bool xgbe_phy_valid_speed(struct xgbe_prv_data *pdata, int speed)
+{
+ return pdata->phy_if.phy_impl.valid_speed(pdata, speed);
+}
+
static int xgbe_phy_config_fixed(struct xgbe_prv_data *pdata)
{
+ enum xgbe_mode mode;
+
netif_dbg(pdata, link, pdata->netdev, "fixed PHY configuration\n");
/* Disable auto-negotiation */
- xgbe_disable_an(pdata);
+ xgbe_an_disable(pdata);
- /* Validate/Set specified speed */
- switch (pdata->phy.speed) {
- case SPEED_10000:
- xgbe_set_mode(pdata, XGBE_MODE_KR);
+ /* Set specified mode for specified speed */
+ mode = pdata->phy_if.phy_impl.get_mode(pdata, pdata->phy.speed);
+ switch (mode) {
+ case XGBE_MODE_KX_1000:
+ case XGBE_MODE_KX_2500:
+ case XGBE_MODE_KR:
+ case XGBE_MODE_SGMII_100:
+ case XGBE_MODE_SGMII_1000:
+ case XGBE_MODE_X:
+ case XGBE_MODE_SFI:
break;
-
- case SPEED_2500:
- case SPEED_1000:
- xgbe_set_mode(pdata, XGBE_MODE_KX);
- break;
-
+ case XGBE_MODE_UNKNOWN:
default:
return -EINVAL;
}
@@ -933,38 +1147,60 @@ static int xgbe_phy_config_fixed(struct xgbe_prv_data *pdata)
if (pdata->phy.duplex != DUPLEX_FULL)
return -EINVAL;
+ xgbe_set_mode(pdata, mode);
+
return 0;
}
static int __xgbe_phy_config_aneg(struct xgbe_prv_data *pdata)
{
+ int ret;
+
set_bit(XGBE_LINK_INIT, &pdata->dev_state);
pdata->link_check = jiffies;
- if (pdata->phy.autoneg != AUTONEG_ENABLE)
- return xgbe_phy_config_fixed(pdata);
+ ret = pdata->phy_if.phy_impl.an_config(pdata);
+ if (ret)
+ return ret;
- netif_dbg(pdata, link, pdata->netdev, "AN PHY configuration\n");
+ if (pdata->phy.autoneg != AUTONEG_ENABLE) {
+ ret = xgbe_phy_config_fixed(pdata);
+ if (ret || !pdata->kr_redrv)
+ return ret;
+
+ netif_dbg(pdata, link, pdata->netdev, "AN redriver support\n");
+ } else {
+ netif_dbg(pdata, link, pdata->netdev, "AN PHY configuration\n");
+ }
/* Disable auto-negotiation interrupt */
disable_irq(pdata->an_irq);
/* Start auto-negotiation in a supported mode */
- if (pdata->phy.advertising & ADVERTISED_10000baseKR_Full) {
+ if (xgbe_use_mode(pdata, XGBE_MODE_KR)) {
xgbe_set_mode(pdata, XGBE_MODE_KR);
- } else if ((pdata->phy.advertising & ADVERTISED_1000baseKX_Full) ||
- (pdata->phy.advertising & ADVERTISED_2500baseX_Full)) {
- xgbe_set_mode(pdata, XGBE_MODE_KX);
+ } else if (xgbe_use_mode(pdata, XGBE_MODE_KX_2500)) {
+ xgbe_set_mode(pdata, XGBE_MODE_KX_2500);
+ } else if (xgbe_use_mode(pdata, XGBE_MODE_KX_1000)) {
+ xgbe_set_mode(pdata, XGBE_MODE_KX_1000);
+ } else if (xgbe_use_mode(pdata, XGBE_MODE_SFI)) {
+ xgbe_set_mode(pdata, XGBE_MODE_SFI);
+ } else if (xgbe_use_mode(pdata, XGBE_MODE_X)) {
+ xgbe_set_mode(pdata, XGBE_MODE_X);
+ } else if (xgbe_use_mode(pdata, XGBE_MODE_SGMII_1000)) {
+ xgbe_set_mode(pdata, XGBE_MODE_SGMII_1000);
+ } else if (xgbe_use_mode(pdata, XGBE_MODE_SGMII_100)) {
+ xgbe_set_mode(pdata, XGBE_MODE_SGMII_100);
} else {
enable_irq(pdata->an_irq);
return -EINVAL;
}
/* Disable and stop any in progress auto-negotiation */
- xgbe_disable_an(pdata);
+ xgbe_an_disable_all(pdata);
/* Clear any auto-negotitation interrupts */
- XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INT, 0);
+ xgbe_an_clear_interrupts_all(pdata);
pdata->an_result = XGBE_AN_READY;
pdata->an_state = XGBE_AN_READY;
@@ -974,11 +1210,8 @@ static int __xgbe_phy_config_aneg(struct xgbe_prv_data *pdata)
/* Re-enable auto-negotiation interrupt */
enable_irq(pdata->an_irq);
- /* Set up advertisement registers based on current settings */
xgbe_an_init(pdata);
-
- /* Enable and start auto-negotiation */
- xgbe_restart_an(pdata);
+ xgbe_an_restart(pdata);
return 0;
}
@@ -1016,108 +1249,52 @@ static void xgbe_check_link_timeout(struct xgbe_prv_data *pdata)
}
}
-static void xgbe_phy_status_force(struct xgbe_prv_data *pdata)
+static enum xgbe_mode xgbe_phy_status_aneg(struct xgbe_prv_data *pdata)
{
- if (xgbe_in_kr_mode(pdata)) {
- pdata->phy.speed = SPEED_10000;
- } else {
- switch (pdata->speed_set) {
- case XGBE_SPEEDSET_1000_10000:
- pdata->phy.speed = SPEED_1000;
- break;
-
- case XGBE_SPEEDSET_2500_10000:
- pdata->phy.speed = SPEED_2500;
- break;
- }
- }
- pdata->phy.duplex = DUPLEX_FULL;
+ return pdata->phy_if.phy_impl.an_outcome(pdata);
}
-static void xgbe_phy_status_aneg(struct xgbe_prv_data *pdata)
+static void xgbe_phy_status_result(struct xgbe_prv_data *pdata)
{
- unsigned int ad_reg, lp_reg;
+ enum xgbe_mode mode;
pdata->phy.lp_advertising = 0;
if ((pdata->phy.autoneg != AUTONEG_ENABLE) || pdata->parallel_detect)
- return xgbe_phy_status_force(pdata);
+ mode = xgbe_cur_mode(pdata);
+ else
+ mode = xgbe_phy_status_aneg(pdata);
- pdata->phy.lp_advertising |= ADVERTISED_Autoneg;
- pdata->phy.lp_advertising |= ADVERTISED_Backplane;
-
- /* Compare Advertisement and Link Partner register 1 */
- ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE);
- lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA);
- if (lp_reg & 0x400)
- pdata->phy.lp_advertising |= ADVERTISED_Pause;
- if (lp_reg & 0x800)
- pdata->phy.lp_advertising |= ADVERTISED_Asym_Pause;
-
- if (pdata->phy.pause_autoneg) {
- /* Set flow control based on auto-negotiation result */
- pdata->phy.tx_pause = 0;
- pdata->phy.rx_pause = 0;
-
- if (ad_reg & lp_reg & 0x400) {
- pdata->phy.tx_pause = 1;
- pdata->phy.rx_pause = 1;
- } else if (ad_reg & lp_reg & 0x800) {
- if (ad_reg & 0x400)
- pdata->phy.rx_pause = 1;
- else if (lp_reg & 0x400)
- pdata->phy.tx_pause = 1;
- }
- }
-
- /* Compare Advertisement and Link Partner register 2 */
- ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1);
- lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 1);
- if (lp_reg & 0x80)
- pdata->phy.lp_advertising |= ADVERTISED_10000baseKR_Full;
- if (lp_reg & 0x20) {
- switch (pdata->speed_set) {
- case XGBE_SPEEDSET_1000_10000:
- pdata->phy.lp_advertising |= ADVERTISED_1000baseKX_Full;
- break;
- case XGBE_SPEEDSET_2500_10000:
- pdata->phy.lp_advertising |= ADVERTISED_2500baseX_Full;
- break;
- }
- }
-
- ad_reg &= lp_reg;
- if (ad_reg & 0x80) {
+ switch (mode) {
+ case XGBE_MODE_SGMII_100:
+ pdata->phy.speed = SPEED_100;
+ break;
+ case XGBE_MODE_X:
+ case XGBE_MODE_KX_1000:
+ case XGBE_MODE_SGMII_1000:
+ pdata->phy.speed = SPEED_1000;
+ break;
+ case XGBE_MODE_KX_2500:
+ pdata->phy.speed = SPEED_2500;
+ break;
+ case XGBE_MODE_KR:
+ case XGBE_MODE_SFI:
pdata->phy.speed = SPEED_10000;
- xgbe_set_mode(pdata, XGBE_MODE_KR);
- } else if (ad_reg & 0x20) {
- switch (pdata->speed_set) {
- case XGBE_SPEEDSET_1000_10000:
- pdata->phy.speed = SPEED_1000;
- break;
-
- case XGBE_SPEEDSET_2500_10000:
- pdata->phy.speed = SPEED_2500;
- break;
- }
-
- xgbe_set_mode(pdata, XGBE_MODE_KX);
- } else {
+ break;
+ case XGBE_MODE_UNKNOWN:
+ default:
pdata->phy.speed = SPEED_UNKNOWN;
}
- /* Compare Advertisement and Link Partner register 3 */
- ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2);
- lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 2);
- if (lp_reg & 0xc000)
- pdata->phy.lp_advertising |= ADVERTISED_10000baseR_FEC;
-
pdata->phy.duplex = DUPLEX_FULL;
+
+ xgbe_set_mode(pdata, mode);
}
static void xgbe_phy_status(struct xgbe_prv_data *pdata)
{
- unsigned int reg, link_aneg;
+ unsigned int link_aneg;
+ int an_restart;
if (test_bit(XGBE_LINK_ERR, &pdata->dev_state)) {
netif_carrier_off(pdata->netdev);
@@ -1128,12 +1305,12 @@ static void xgbe_phy_status(struct xgbe_prv_data *pdata)
link_aneg = (pdata->phy.autoneg == AUTONEG_ENABLE);
- /* Get the link status. Link status is latched low, so read
- * once to clear and then read again to get current state
- */
- reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
- reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
- pdata->phy.link = (reg & MDIO_STAT1_LSTATUS) ? 1 : 0;
+ pdata->phy.link = pdata->phy_if.phy_impl.link_status(pdata,
+ &an_restart);
+ if (an_restart) {
+ xgbe_phy_config_aneg(pdata);
+ return;
+ }
if (pdata->phy.link) {
if (link_aneg && !xgbe_phy_aneg_done(pdata)) {
@@ -1141,7 +1318,7 @@ static void xgbe_phy_status(struct xgbe_prv_data *pdata)
return;
}
- xgbe_phy_status_aneg(pdata);
+ xgbe_phy_status_result(pdata);
if (test_bit(XGBE_LINK_INIT, &pdata->dev_state))
clear_bit(XGBE_LINK_INIT, &pdata->dev_state);
@@ -1155,7 +1332,7 @@ static void xgbe_phy_status(struct xgbe_prv_data *pdata)
return;
}
- xgbe_phy_status_aneg(pdata);
+ xgbe_phy_status_result(pdata);
netif_carrier_off(pdata->netdev);
}
@@ -1168,13 +1345,19 @@ static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
{
netif_dbg(pdata, link, pdata->netdev, "stopping PHY\n");
+ if (!pdata->phy_started)
+ return;
+
+ /* Indicate the PHY is down */
+ pdata->phy_started = 0;
+
/* Disable auto-negotiation */
- xgbe_disable_an(pdata);
+ xgbe_an_disable_all(pdata);
- /* Disable auto-negotiation interrupts */
- XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INTMASK, 0);
+ if (pdata->dev_irq != pdata->an_irq)
+ devm_free_irq(pdata->dev, pdata->an_irq, pdata);
- devm_free_irq(pdata->dev, pdata->an_irq, pdata);
+ pdata->phy_if.phy_impl.stop(pdata);
pdata->phy.link = 0;
netif_carrier_off(pdata->netdev);
@@ -1189,64 +1372,74 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata)
netif_dbg(pdata, link, pdata->netdev, "starting PHY\n");
- ret = devm_request_irq(pdata->dev, pdata->an_irq,
- xgbe_an_isr, 0, pdata->an_name,
- pdata);
- if (ret) {
- netdev_err(netdev, "phy irq request failed\n");
+ ret = pdata->phy_if.phy_impl.start(pdata);
+ if (ret)
return ret;
+
+ /* If we have a separate AN irq, enable it */
+ if (pdata->dev_irq != pdata->an_irq) {
+ ret = devm_request_irq(pdata->dev, pdata->an_irq,
+ xgbe_an_isr, 0, pdata->an_name,
+ pdata);
+ if (ret) {
+ netdev_err(netdev, "phy irq request failed\n");
+ goto err_stop;
+ }
}
/* Set initial mode - call the mode setting routines
* directly to insure we are properly configured
*/
- if (xgbe_use_xgmii_mode(pdata)) {
- xgbe_xgmii_mode(pdata);
- } else if (xgbe_use_gmii_mode(pdata)) {
- xgbe_gmii_mode(pdata);
- } else if (xgbe_use_gmii_2500_mode(pdata)) {
- xgbe_gmii_2500_mode(pdata);
+ if (xgbe_use_mode(pdata, XGBE_MODE_KR)) {
+ xgbe_kr_mode(pdata);
+ } else if (xgbe_use_mode(pdata, XGBE_MODE_KX_2500)) {
+ xgbe_kx_2500_mode(pdata);
+ } else if (xgbe_use_mode(pdata, XGBE_MODE_KX_1000)) {
+ xgbe_kx_1000_mode(pdata);
+ } else if (xgbe_use_mode(pdata, XGBE_MODE_SFI)) {
+ xgbe_sfi_mode(pdata);
+ } else if (xgbe_use_mode(pdata, XGBE_MODE_X)) {
+ xgbe_x_mode(pdata);
+ } else if (xgbe_use_mode(pdata, XGBE_MODE_SGMII_1000)) {
+ xgbe_sgmii_1000_mode(pdata);
+ } else if (xgbe_use_mode(pdata, XGBE_MODE_SGMII_100)) {
+ xgbe_sgmii_100_mode(pdata);
} else {
ret = -EINVAL;
goto err_irq;
}
- /* Set up advertisement registers based on current settings */
- xgbe_an_init(pdata);
+ /* Indicate the PHY is up and running */
+ pdata->phy_started = 1;
- /* Enable auto-negotiation interrupts */
- XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INTMASK, 0x07);
+ xgbe_an_init(pdata);
+ xgbe_an_enable_interrupts(pdata);
return xgbe_phy_config_aneg(pdata);
err_irq:
- devm_free_irq(pdata->dev, pdata->an_irq, pdata);
+ if (pdata->dev_irq != pdata->an_irq)
+ devm_free_irq(pdata->dev, pdata->an_irq, pdata);
+
+err_stop:
+ pdata->phy_if.phy_impl.stop(pdata);
return ret;
}
static int xgbe_phy_reset(struct xgbe_prv_data *pdata)
{
- unsigned int count, reg;
+ int ret;
- reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
- reg |= MDIO_CTRL1_RESET;
- XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
-
- count = 50;
- do {
- msleep(20);
- reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
- } while ((reg & MDIO_CTRL1_RESET) && --count);
-
- if (reg & MDIO_CTRL1_RESET)
- return -ETIMEDOUT;
+ ret = pdata->phy_if.phy_impl.reset(pdata);
+ if (ret)
+ return ret;
/* Disable auto-negotiation for now */
- xgbe_disable_an(pdata);
+ xgbe_an_disable_all(pdata);
/* Clear auto-negotiation interrupts */
- XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INT, 0);
+ xgbe_an_clear_interrupts_all(pdata);
return 0;
}
@@ -1257,74 +1450,96 @@ static void xgbe_dump_phy_registers(struct xgbe_prv_data *pdata)
dev_dbg(dev, "\n************* PHY Reg dump **********************\n");
- dev_dbg(dev, "PCS Control Reg (%#04x) = %#04x\n", MDIO_CTRL1,
+ dev_dbg(dev, "PCS Control Reg (%#06x) = %#06x\n", MDIO_CTRL1,
XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1));
- dev_dbg(dev, "PCS Status Reg (%#04x) = %#04x\n", MDIO_STAT1,
+ dev_dbg(dev, "PCS Status Reg (%#06x) = %#06x\n", MDIO_STAT1,
XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1));
- dev_dbg(dev, "Phy Id (PHYS ID 1 %#04x)= %#04x\n", MDIO_DEVID1,
+ dev_dbg(dev, "Phy Id (PHYS ID 1 %#06x)= %#06x\n", MDIO_DEVID1,
XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVID1));
- dev_dbg(dev, "Phy Id (PHYS ID 2 %#04x)= %#04x\n", MDIO_DEVID2,
+ dev_dbg(dev, "Phy Id (PHYS ID 2 %#06x)= %#06x\n", MDIO_DEVID2,
XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVID2));
- dev_dbg(dev, "Devices in Package (%#04x)= %#04x\n", MDIO_DEVS1,
+ dev_dbg(dev, "Devices in Package (%#06x)= %#06x\n", MDIO_DEVS1,
XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVS1));
- dev_dbg(dev, "Devices in Package (%#04x)= %#04x\n", MDIO_DEVS2,
+ dev_dbg(dev, "Devices in Package (%#06x)= %#06x\n", MDIO_DEVS2,
XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVS2));
- dev_dbg(dev, "Auto-Neg Control Reg (%#04x) = %#04x\n", MDIO_CTRL1,
+ dev_dbg(dev, "Auto-Neg Control Reg (%#06x) = %#06x\n", MDIO_CTRL1,
XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_CTRL1));
- dev_dbg(dev, "Auto-Neg Status Reg (%#04x) = %#04x\n", MDIO_STAT1,
+ dev_dbg(dev, "Auto-Neg Status Reg (%#06x) = %#06x\n", MDIO_STAT1,
XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_STAT1));
- dev_dbg(dev, "Auto-Neg Ad Reg 1 (%#04x) = %#04x\n",
+ dev_dbg(dev, "Auto-Neg Ad Reg 1 (%#06x) = %#06x\n",
MDIO_AN_ADVERTISE,
XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE));
- dev_dbg(dev, "Auto-Neg Ad Reg 2 (%#04x) = %#04x\n",
+ dev_dbg(dev, "Auto-Neg Ad Reg 2 (%#06x) = %#06x\n",
MDIO_AN_ADVERTISE + 1,
XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1));
- dev_dbg(dev, "Auto-Neg Ad Reg 3 (%#04x) = %#04x\n",
+ dev_dbg(dev, "Auto-Neg Ad Reg 3 (%#06x) = %#06x\n",
MDIO_AN_ADVERTISE + 2,
XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2));
- dev_dbg(dev, "Auto-Neg Completion Reg (%#04x) = %#04x\n",
+ dev_dbg(dev, "Auto-Neg Completion Reg (%#06x) = %#06x\n",
MDIO_AN_COMP_STAT,
XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_COMP_STAT));
dev_dbg(dev, "\n*************************************************\n");
}
-static void xgbe_phy_init(struct xgbe_prv_data *pdata)
+static int xgbe_phy_best_advertised_speed(struct xgbe_prv_data *pdata)
{
+ if (pdata->phy.advertising & ADVERTISED_10000baseKR_Full)
+ return SPEED_10000;
+ else if (pdata->phy.advertising & ADVERTISED_10000baseT_Full)
+ return SPEED_10000;
+ else if (pdata->phy.advertising & ADVERTISED_2500baseX_Full)
+ return SPEED_2500;
+ else if (pdata->phy.advertising & ADVERTISED_1000baseKX_Full)
+ return SPEED_1000;
+ else if (pdata->phy.advertising & ADVERTISED_1000baseT_Full)
+ return SPEED_1000;
+ else if (pdata->phy.advertising & ADVERTISED_100baseT_Full)
+ return SPEED_100;
+
+ return SPEED_UNKNOWN;
+}
+
+static void xgbe_phy_exit(struct xgbe_prv_data *pdata)
+{
+ xgbe_phy_stop(pdata);
+
+ pdata->phy_if.phy_impl.exit(pdata);
+}
+
+static int xgbe_phy_init(struct xgbe_prv_data *pdata)
+{
+ int ret;
+
mutex_init(&pdata->an_mutex);
INIT_WORK(&pdata->an_irq_work, xgbe_an_irq_work);
INIT_WORK(&pdata->an_work, xgbe_an_state_machine);
pdata->mdio_mmd = MDIO_MMD_PCS;
- /* Initialize supported features */
- pdata->phy.supported = SUPPORTED_Autoneg;
- pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
- pdata->phy.supported |= SUPPORTED_Backplane;
- pdata->phy.supported |= SUPPORTED_10000baseKR_Full;
- switch (pdata->speed_set) {
- case XGBE_SPEEDSET_1000_10000:
- pdata->phy.supported |= SUPPORTED_1000baseKX_Full;
- break;
- case XGBE_SPEEDSET_2500_10000:
- pdata->phy.supported |= SUPPORTED_2500baseX_Full;
- break;
- }
-
+ /* Check for FEC support */
pdata->fec_ability = XMDIO_READ(pdata, MDIO_MMD_PMAPMD,
MDIO_PMA_10GBR_FECABLE);
pdata->fec_ability &= (MDIO_PMA_10GBR_FECABLE_ABLE |
MDIO_PMA_10GBR_FECABLE_ERRABLE);
- if (pdata->fec_ability & MDIO_PMA_10GBR_FECABLE_ABLE)
- pdata->phy.supported |= SUPPORTED_10000baseR_FEC;
+ /* Setup the phy (including supported features) */
+ ret = pdata->phy_if.phy_impl.init(pdata);
+ if (ret)
+ return ret;
pdata->phy.advertising = pdata->phy.supported;
pdata->phy.address = 0;
- pdata->phy.autoneg = AUTONEG_ENABLE;
- pdata->phy.speed = SPEED_UNKNOWN;
- pdata->phy.duplex = DUPLEX_UNKNOWN;
+ if (pdata->phy.advertising & ADVERTISED_Autoneg) {
+ pdata->phy.autoneg = AUTONEG_ENABLE;
+ pdata->phy.speed = SPEED_UNKNOWN;
+ pdata->phy.duplex = DUPLEX_UNKNOWN;
+ } else {
+ pdata->phy.autoneg = AUTONEG_DISABLE;
+ pdata->phy.speed = xgbe_phy_best_advertised_speed(pdata);
+ pdata->phy.duplex = DUPLEX_FULL;
+ }
pdata->phy.link = 0;
@@ -1346,11 +1561,14 @@ static void xgbe_phy_init(struct xgbe_prv_data *pdata)
if (netif_msg_drv(pdata))
xgbe_dump_phy_registers(pdata);
+
+ return 0;
}
void xgbe_init_function_ptrs_phy(struct xgbe_phy_if *phy_if)
{
phy_if->phy_init = xgbe_phy_init;
+ phy_if->phy_exit = xgbe_phy_exit;
phy_if->phy_reset = xgbe_phy_reset;
phy_if->phy_start = xgbe_phy_start;
@@ -1358,4 +1576,8 @@ void xgbe_init_function_ptrs_phy(struct xgbe_phy_if *phy_if)
phy_if->phy_status = xgbe_phy_status;
phy_if->phy_config_aneg = xgbe_phy_config_aneg;
+
+ phy_if->phy_valid_speed = xgbe_phy_valid_speed;
+
+ phy_if->an_isr = xgbe_an_combined_isr;
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
new file mode 100644
index 0000000..e76b7f6
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -0,0 +1,529 @@
+/*
+ * AMD 10Gb Ethernet driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2016 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ * The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ * (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ * Inc. unless otherwise expressly agreed to in writing between Synopsys
+ * and you.
+ *
+ * The Software IS NOT an item of Licensed Software or Licensed Product
+ * under any End User Software License Agreement or Agreement for Licensed
+ * Product with Synopsys or any supplement thereto. Permission is hereby
+ * granted, free of charge, to any person obtaining a copy of this software
+ * annotated with this license and the Software, to deal in the Software
+ * without restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is furnished
+ * to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ * BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ * PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ * THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2016 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Advanced Micro Devices, Inc. nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ * The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ * (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ * Inc. unless otherwise expressly agreed to in writing between Synopsys
+ * and you.
+ *
+ * The Software IS NOT an item of Licensed Software or Licensed Product
+ * under any End User Software License Agreement or Agreement for Licensed
+ * Product with Synopsys or any supplement thereto. Permission is hereby
+ * granted, free of charge, to any person obtaining a copy of this software
+ * annotated with this license and the Software, to deal in the Software
+ * without restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is furnished
+ * to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ * BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ * PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ * THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/pci.h>
+#include <linux/log2.h>
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+static int xgbe_config_msi(struct xgbe_prv_data *pdata)
+{
+ unsigned int msi_count;
+ unsigned int i, j;
+ int ret;
+
+ msi_count = XGBE_MSIX_BASE_COUNT;
+ msi_count += max(pdata->rx_ring_count,
+ pdata->tx_ring_count);
+ msi_count = roundup_pow_of_two(msi_count);
+
+ ret = pci_enable_msi_exact(pdata->pcidev, msi_count);
+ if (ret < 0) {
+ dev_info(pdata->dev, "MSI request for %u interrupts failed\n",
+ msi_count);
+
+ ret = pci_enable_msi(pdata->pcidev);
+ if (ret < 0) {
+ dev_info(pdata->dev, "MSI enablement failed\n");
+ return ret;
+ }
+
+ msi_count = 1;
+ }
+
+ pdata->irq_count = msi_count;
+
+ pdata->dev_irq = pdata->pcidev->irq;
+
+ if (msi_count > 1) {
+ pdata->ecc_irq = pdata->pcidev->irq + 1;
+ pdata->i2c_irq = pdata->pcidev->irq + 2;
+ pdata->an_irq = pdata->pcidev->irq + 3;
+
+ for (i = XGBE_MSIX_BASE_COUNT, j = 0;
+ (i < msi_count) && (j < XGBE_MAX_DMA_CHANNELS);
+ i++, j++)
+ pdata->channel_irq[j] = pdata->pcidev->irq + i;
+ pdata->channel_irq_count = j;
+
+ pdata->per_channel_irq = 1;
+ pdata->channel_irq_mode = XGBE_IRQ_MODE_LEVEL;
+ } else {
+ pdata->ecc_irq = pdata->pcidev->irq;
+ pdata->i2c_irq = pdata->pcidev->irq;
+ pdata->an_irq = pdata->pcidev->irq;
+ }
+
+ if (netif_msg_probe(pdata))
+ dev_dbg(pdata->dev, "MSI interrupts enabled\n");
+
+ return 0;
+}
+
+static int xgbe_config_msix(struct xgbe_prv_data *pdata)
+{
+ unsigned int msix_count;
+ unsigned int i, j;
+ int ret;
+
+ msix_count = XGBE_MSIX_BASE_COUNT;
+ msix_count += max(pdata->rx_ring_count,
+ pdata->tx_ring_count);
+
+ pdata->msix_entries = devm_kcalloc(pdata->dev, msix_count,
+ sizeof(struct msix_entry),
+ GFP_KERNEL);
+ if (!pdata->msix_entries)
+ return -ENOMEM;
+
+ for (i = 0; i < msix_count; i++)
+ pdata->msix_entries[i].entry = i;
+
+ ret = pci_enable_msix_range(pdata->pcidev, pdata->msix_entries,
+ XGBE_MSIX_MIN_COUNT, msix_count);
+ if (ret < 0) {
+ dev_info(pdata->dev, "MSI-X enablement failed\n");
+ devm_kfree(pdata->dev, pdata->msix_entries);
+ pdata->msix_entries = NULL;
+ return ret;
+ }
+
+ pdata->irq_count = ret;
+
+ pdata->dev_irq = pdata->msix_entries[0].vector;
+ pdata->ecc_irq = pdata->msix_entries[1].vector;
+ pdata->i2c_irq = pdata->msix_entries[2].vector;
+ pdata->an_irq = pdata->msix_entries[3].vector;
+
+ for (i = XGBE_MSIX_BASE_COUNT, j = 0; i < ret; i++, j++)
+ pdata->channel_irq[j] = pdata->msix_entries[i].vector;
+ pdata->channel_irq_count = j;
+
+ pdata->per_channel_irq = 1;
+ pdata->channel_irq_mode = XGBE_IRQ_MODE_LEVEL;
+
+ if (netif_msg_probe(pdata))
+ dev_dbg(pdata->dev, "MSI-X interrupts enabled\n");
+
+ return 0;
+}
+
+static int xgbe_config_irqs(struct xgbe_prv_data *pdata)
+{
+ int ret;
+
+ ret = xgbe_config_msix(pdata);
+ if (!ret)
+ goto out;
+
+ ret = xgbe_config_msi(pdata);
+ if (!ret)
+ goto out;
+
+ pdata->irq_count = 1;
+ pdata->irq_shared = 1;
+
+ pdata->dev_irq = pdata->pcidev->irq;
+ pdata->ecc_irq = pdata->pcidev->irq;
+ pdata->i2c_irq = pdata->pcidev->irq;
+ pdata->an_irq = pdata->pcidev->irq;
+
+out:
+ if (netif_msg_probe(pdata)) {
+ unsigned int i;
+
+ dev_dbg(pdata->dev, " dev irq=%d\n", pdata->dev_irq);
+ dev_dbg(pdata->dev, " ecc irq=%d\n", pdata->ecc_irq);
+ dev_dbg(pdata->dev, " i2c irq=%d\n", pdata->i2c_irq);
+ dev_dbg(pdata->dev, " an irq=%d\n", pdata->an_irq);
+ for (i = 0; i < pdata->channel_irq_count; i++)
+ dev_dbg(pdata->dev, " dma%u irq=%d\n",
+ i, pdata->channel_irq[i]);
+ }
+
+ return 0;
+}
+
+static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+ struct xgbe_prv_data *pdata;
+ struct device *dev = &pdev->dev;
+ void __iomem * const *iomap_table;
+ unsigned int ma_lo, ma_hi;
+ unsigned int reg;
+ int bar_mask;
+ int ret;
+
+ pdata = xgbe_alloc_pdata(dev);
+ if (IS_ERR(pdata)) {
+ ret = PTR_ERR(pdata);
+ goto err_alloc;
+ }
+
+ pdata->pcidev = pdev;
+ pci_set_drvdata(pdev, pdata);
+
+ /* Get the version data */
+ pdata->vdata = (struct xgbe_version_data *)id->driver_data;
+
+ ret = pcim_enable_device(pdev);
+ if (ret) {
+ dev_err(dev, "pcim_enable_device failed\n");
+ goto err_pci_enable;
+ }
+
+ /* Obtain the mmio areas for the device */
+ bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
+ ret = pcim_iomap_regions(pdev, bar_mask, XGBE_DRV_NAME);
+ if (ret) {
+ dev_err(dev, "pcim_iomap_regions failed\n");
+ goto err_pci_enable;
+ }
+
+ iomap_table = pcim_iomap_table(pdev);
+ if (!iomap_table) {
+ dev_err(dev, "pcim_iomap_table failed\n");
+ ret = -ENOMEM;
+ goto err_pci_enable;
+ }
+
+ pdata->xgmac_regs = iomap_table[XGBE_XGMAC_BAR];
+ if (!pdata->xgmac_regs) {
+ dev_err(dev, "xgmac ioremap failed\n");
+ ret = -ENOMEM;
+ goto err_pci_enable;
+ }
+ pdata->xprop_regs = pdata->xgmac_regs + XGBE_MAC_PROP_OFFSET;
+ pdata->xi2c_regs = pdata->xgmac_regs + XGBE_I2C_CTRL_OFFSET;
+ if (netif_msg_probe(pdata)) {
+ dev_dbg(dev, "xgmac_regs = %p\n", pdata->xgmac_regs);
+ dev_dbg(dev, "xprop_regs = %p\n", pdata->xprop_regs);
+ dev_dbg(dev, "xi2c_regs = %p\n", pdata->xi2c_regs);
+ }
+
+ pdata->xpcs_regs = iomap_table[XGBE_XPCS_BAR];
+ if (!pdata->xpcs_regs) {
+ dev_err(dev, "xpcs ioremap failed\n");
+ ret = -ENOMEM;
+ goto err_pci_enable;
+ }
+ if (netif_msg_probe(pdata))
+ dev_dbg(dev, "xpcs_regs = %p\n", pdata->xpcs_regs);
+
+ /* Configure the PCS indirect addressing support */
+ reg = XPCS32_IOREAD(pdata, PCS_V2_WINDOW_DEF);
+ pdata->xpcs_window = XPCS_GET_BITS(reg, PCS_V2_WINDOW_DEF, OFFSET);
+ pdata->xpcs_window <<= 6;
+ pdata->xpcs_window_size = XPCS_GET_BITS(reg, PCS_V2_WINDOW_DEF, SIZE);
+ pdata->xpcs_window_size = 1 << (pdata->xpcs_window_size + 7);
+ pdata->xpcs_window_mask = pdata->xpcs_window_size - 1;
+ if (netif_msg_probe(pdata)) {
+ dev_dbg(dev, "xpcs window = %#010x\n",
+ pdata->xpcs_window);
+ dev_dbg(dev, "xpcs window size = %#010x\n",
+ pdata->xpcs_window_size);
+ dev_dbg(dev, "xpcs window mask = %#010x\n",
+ pdata->xpcs_window_mask);
+ }
+
+ pci_set_master(pdev);
+
+ /* Enable all interrupts in the hardware */
+ XP_IOWRITE(pdata, XP_INT_EN, 0x1fffff);
+
+ /* Retrieve the MAC address */
+ ma_lo = XP_IOREAD(pdata, XP_MAC_ADDR_LO);
+ ma_hi = XP_IOREAD(pdata, XP_MAC_ADDR_HI);
+ pdata->mac_addr[0] = ma_lo & 0xff;
+ pdata->mac_addr[1] = (ma_lo >> 8) & 0xff;
+ pdata->mac_addr[2] = (ma_lo >> 16) & 0xff;
+ pdata->mac_addr[3] = (ma_lo >> 24) & 0xff;
+ pdata->mac_addr[4] = ma_hi & 0xff;
+ pdata->mac_addr[5] = (ma_hi >> 8) & 0xff;
+ if (!XP_GET_BITS(ma_hi, XP_MAC_ADDR_HI, VALID) ||
+ !is_valid_ether_addr(pdata->mac_addr)) {
+ dev_err(dev, "invalid mac address\n");
+ ret = -EINVAL;
+ goto err_pci_enable;
+ }
+
+ /* Clock settings */
+ pdata->sysclk_rate = XGBE_V2_DMA_CLOCK_FREQ;
+ pdata->ptpclk_rate = XGBE_V2_PTP_CLOCK_FREQ;
+
+ /* Set the DMA coherency values */
+ pdata->coherent = 1;
+ pdata->axdomain = XGBE_DMA_OS_AXDOMAIN;
+ pdata->arcache = XGBE_DMA_OS_ARCACHE;
+ pdata->awcache = XGBE_DMA_OS_AWCACHE;
+
+ /* Set the maximum channels and queues */
+ reg = XP_IOREAD(pdata, XP_PROP_1);
+ pdata->tx_max_channel_count = XP_GET_BITS(reg, XP_PROP_1, MAX_TX_DMA);
+ pdata->rx_max_channel_count = XP_GET_BITS(reg, XP_PROP_1, MAX_RX_DMA);
+ pdata->tx_max_q_count = XP_GET_BITS(reg, XP_PROP_1, MAX_TX_QUEUES);
+ pdata->rx_max_q_count = XP_GET_BITS(reg, XP_PROP_1, MAX_RX_QUEUES);
+ if (netif_msg_probe(pdata)) {
+ dev_dbg(dev, "max tx/rx channel count = %u/%u\n",
+ pdata->tx_max_channel_count,
+ pdata->tx_max_channel_count);
+ dev_dbg(dev, "max tx/rx hw queue count = %u/%u\n",
+ pdata->tx_max_q_count, pdata->rx_max_q_count);
+ }
+
+ /* Set the hardware channel and queue counts */
+ xgbe_set_counts(pdata);
+
+ /* Set the maximum fifo amounts */
+ reg = XP_IOREAD(pdata, XP_PROP_2);
+ pdata->tx_max_fifo_size = XP_GET_BITS(reg, XP_PROP_2, TX_FIFO_SIZE);
+ pdata->tx_max_fifo_size *= 16384;
+ pdata->tx_max_fifo_size = min(pdata->tx_max_fifo_size,
+ pdata->vdata->tx_max_fifo_size);
+ pdata->rx_max_fifo_size = XP_GET_BITS(reg, XP_PROP_2, RX_FIFO_SIZE);
+ pdata->rx_max_fifo_size *= 16384;
+ pdata->rx_max_fifo_size = min(pdata->rx_max_fifo_size,
+ pdata->vdata->rx_max_fifo_size);
+ if (netif_msg_probe(pdata))
+ dev_dbg(dev, "max tx/rx max fifo size = %u/%u\n",
+ pdata->tx_max_fifo_size, pdata->rx_max_fifo_size);
+
+ /* Configure interrupt support */
+ ret = xgbe_config_irqs(pdata);
+ if (ret)
+ goto err_pci_enable;
+
+ /* Configure the netdev resource */
+ ret = xgbe_config_netdev(pdata);
+ if (ret)
+ goto err_pci_enable;
+
+ netdev_notice(pdata->netdev, "net device enabled\n");
+
+ return 0;
+
+err_pci_enable:
+ xgbe_free_pdata(pdata);
+
+err_alloc:
+ dev_notice(dev, "net device not enabled\n");
+
+ return ret;
+}
+
+static void xgbe_pci_remove(struct pci_dev *pdev)
+{
+ struct xgbe_prv_data *pdata = pci_get_drvdata(pdev);
+
+ xgbe_deconfig_netdev(pdata);
+
+ xgbe_free_pdata(pdata);
+}
+
+#ifdef CONFIG_PM
+static int xgbe_pci_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ struct xgbe_prv_data *pdata = pci_get_drvdata(pdev);
+ struct net_device *netdev = pdata->netdev;
+ int ret = 0;
+
+ if (netif_running(netdev))
+ ret = xgbe_powerdown(netdev, XGMAC_DRIVER_CONTEXT);
+
+ pdata->lpm_ctrl = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
+ pdata->lpm_ctrl |= MDIO_CTRL1_LPOWER;
+ XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, pdata->lpm_ctrl);
+
+ return ret;
+}
+
+static int xgbe_pci_resume(struct pci_dev *pdev)
+{
+ struct xgbe_prv_data *pdata = pci_get_drvdata(pdev);
+ struct net_device *netdev = pdata->netdev;
+ int ret = 0;
+
+ pdata->lpm_ctrl &= ~MDIO_CTRL1_LPOWER;
+ XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, pdata->lpm_ctrl);
+
+ if (netif_running(netdev)) {
+ ret = xgbe_powerup(netdev, XGMAC_DRIVER_CONTEXT);
+
+ /* Schedule a restart in case the link or phy state changed
+ * while we were powered down.
+ */
+ schedule_work(&pdata->restart_work);
+ }
+
+ return ret;
+}
+#endif /* CONFIG_PM */
+
+static const struct xgbe_version_data xgbe_v2a = {
+ .init_function_ptrs_phy_impl = xgbe_init_function_ptrs_phy_v2,
+ .xpcs_access = XGBE_XPCS_ACCESS_V2,
+ .mmc_64bit = 1,
+ .tx_max_fifo_size = 229376,
+ .rx_max_fifo_size = 229376,
+ .tx_tstamp_workaround = 1,
+ .ecc_support = 1,
+ .i2c_support = 1,
+};
+
+static const struct xgbe_version_data xgbe_v2b = {
+ .init_function_ptrs_phy_impl = xgbe_init_function_ptrs_phy_v2,
+ .xpcs_access = XGBE_XPCS_ACCESS_V2,
+ .mmc_64bit = 1,
+ .tx_max_fifo_size = 65536,
+ .rx_max_fifo_size = 65536,
+ .tx_tstamp_workaround = 1,
+ .ecc_support = 1,
+ .i2c_support = 1,
+};
+
+static const struct pci_device_id xgbe_pci_table[] = {
+ { PCI_VDEVICE(AMD, 0x1458),
+ .driver_data = (kernel_ulong_t)&xgbe_v2a },
+ { PCI_VDEVICE(AMD, 0x1459),
+ .driver_data = (kernel_ulong_t)&xgbe_v2b },
+ /* Last entry must be zero */
+ { 0, }
+};
+MODULE_DEVICE_TABLE(pci, xgbe_pci_table);
+
+static struct pci_driver xgbe_driver = {
+ .name = XGBE_DRV_NAME,
+ .id_table = xgbe_pci_table,
+ .probe = xgbe_pci_probe,
+ .remove = xgbe_pci_remove,
+#ifdef CONFIG_PM
+ .suspend = xgbe_pci_suspend,
+ .resume = xgbe_pci_resume,
+#endif
+};
+
+int xgbe_pci_init(void)
+{
+ return pci_register_driver(&xgbe_driver);
+}
+
+void xgbe_pci_exit(void)
+{
+ pci_unregister_driver(&xgbe_driver);
+}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v1.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v1.c
new file mode 100644
index 0000000..c75edca
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v1.c
@@ -0,0 +1,845 @@
+/*
+ * AMD 10Gb Ethernet driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2016 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ * The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ * (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ * Inc. unless otherwise expressly agreed to in writing between Synopsys
+ * and you.
+ *
+ * The Software IS NOT an item of Licensed Software or Licensed Product
+ * under any End User Software License Agreement or Agreement for Licensed
+ * Product with Synopsys or any supplement thereto. Permission is hereby
+ * granted, free of charge, to any person obtaining a copy of this software
+ * annotated with this license and the Software, to deal in the Software
+ * without restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is furnished
+ * to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ * BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ * PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ * THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2016 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Advanced Micro Devices, Inc. nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ * The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ * (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ * Inc. unless otherwise expressly agreed to in writing between Synopsys
+ * and you.
+ *
+ * The Software IS NOT an item of Licensed Software or Licensed Product
+ * under any End User Software License Agreement or Agreement for Licensed
+ * Product with Synopsys or any supplement thereto. Permission is hereby
+ * granted, free of charge, to any person obtaining a copy of this software
+ * annotated with this license and the Software, to deal in the Software
+ * without restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is furnished
+ * to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ * BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ * PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ * THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <linux/kmod.h>
+#include <linux/device.h>
+#include <linux/property.h>
+#include <linux/mdio.h>
+#include <linux/phy.h>
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+#define XGBE_BLWC_PROPERTY "amd,serdes-blwc"
+#define XGBE_CDR_RATE_PROPERTY "amd,serdes-cdr-rate"
+#define XGBE_PQ_SKEW_PROPERTY "amd,serdes-pq-skew"
+#define XGBE_TX_AMP_PROPERTY "amd,serdes-tx-amp"
+#define XGBE_DFE_CFG_PROPERTY "amd,serdes-dfe-tap-config"
+#define XGBE_DFE_ENA_PROPERTY "amd,serdes-dfe-tap-enable"
+
+/* Default SerDes settings */
+#define XGBE_SPEED_1000_BLWC 1
+#define XGBE_SPEED_1000_CDR 0x2
+#define XGBE_SPEED_1000_PLL 0x0
+#define XGBE_SPEED_1000_PQ 0xa
+#define XGBE_SPEED_1000_RATE 0x3
+#define XGBE_SPEED_1000_TXAMP 0xf
+#define XGBE_SPEED_1000_WORD 0x1
+#define XGBE_SPEED_1000_DFE_TAP_CONFIG 0x3
+#define XGBE_SPEED_1000_DFE_TAP_ENABLE 0x0
+
+#define XGBE_SPEED_2500_BLWC 1
+#define XGBE_SPEED_2500_CDR 0x2
+#define XGBE_SPEED_2500_PLL 0x0
+#define XGBE_SPEED_2500_PQ 0xa
+#define XGBE_SPEED_2500_RATE 0x1
+#define XGBE_SPEED_2500_TXAMP 0xf
+#define XGBE_SPEED_2500_WORD 0x1
+#define XGBE_SPEED_2500_DFE_TAP_CONFIG 0x3
+#define XGBE_SPEED_2500_DFE_TAP_ENABLE 0x0
+
+#define XGBE_SPEED_10000_BLWC 0
+#define XGBE_SPEED_10000_CDR 0x7
+#define XGBE_SPEED_10000_PLL 0x1
+#define XGBE_SPEED_10000_PQ 0x12
+#define XGBE_SPEED_10000_RATE 0x0
+#define XGBE_SPEED_10000_TXAMP 0xa
+#define XGBE_SPEED_10000_WORD 0x7
+#define XGBE_SPEED_10000_DFE_TAP_CONFIG 0x1
+#define XGBE_SPEED_10000_DFE_TAP_ENABLE 0x7f
+
+/* Rate-change complete wait/retry count */
+#define XGBE_RATECHANGE_COUNT 500
+
+static const u32 xgbe_phy_blwc[] = {
+ XGBE_SPEED_1000_BLWC,
+ XGBE_SPEED_2500_BLWC,
+ XGBE_SPEED_10000_BLWC,
+};
+
+static const u32 xgbe_phy_cdr_rate[] = {
+ XGBE_SPEED_1000_CDR,
+ XGBE_SPEED_2500_CDR,
+ XGBE_SPEED_10000_CDR,
+};
+
+static const u32 xgbe_phy_pq_skew[] = {
+ XGBE_SPEED_1000_PQ,
+ XGBE_SPEED_2500_PQ,
+ XGBE_SPEED_10000_PQ,
+};
+
+static const u32 xgbe_phy_tx_amp[] = {
+ XGBE_SPEED_1000_TXAMP,
+ XGBE_SPEED_2500_TXAMP,
+ XGBE_SPEED_10000_TXAMP,
+};
+
+static const u32 xgbe_phy_dfe_tap_cfg[] = {
+ XGBE_SPEED_1000_DFE_TAP_CONFIG,
+ XGBE_SPEED_2500_DFE_TAP_CONFIG,
+ XGBE_SPEED_10000_DFE_TAP_CONFIG,
+};
+
+static const u32 xgbe_phy_dfe_tap_ena[] = {
+ XGBE_SPEED_1000_DFE_TAP_ENABLE,
+ XGBE_SPEED_2500_DFE_TAP_ENABLE,
+ XGBE_SPEED_10000_DFE_TAP_ENABLE,
+};
+
+struct xgbe_phy_data {
+ /* 1000/10000 vs 2500/10000 indicator */
+ unsigned int speed_set;
+
+ /* SerDes UEFI configurable settings.
+ * Switching between modes/speeds requires new values for some
+ * SerDes settings. The values can be supplied as device
+ * properties in array format. The first array entry is for
+ * 1GbE, second for 2.5GbE and third for 10GbE
+ */
+ u32 blwc[XGBE_SPEEDS];
+ u32 cdr_rate[XGBE_SPEEDS];
+ u32 pq_skew[XGBE_SPEEDS];
+ u32 tx_amp[XGBE_SPEEDS];
+ u32 dfe_tap_cfg[XGBE_SPEEDS];
+ u32 dfe_tap_ena[XGBE_SPEEDS];
+};
+
+static void xgbe_phy_kr_training_pre(struct xgbe_prv_data *pdata)
+{
+ XSIR0_IOWRITE_BITS(pdata, SIR0_KR_RT_1, RESET, 1);
+}
+
+static void xgbe_phy_kr_training_post(struct xgbe_prv_data *pdata)
+{
+ XSIR0_IOWRITE_BITS(pdata, SIR0_KR_RT_1, RESET, 0);
+}
+
+static enum xgbe_mode xgbe_phy_an_outcome(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ enum xgbe_mode mode;
+ unsigned int ad_reg, lp_reg;
+
+ pdata->phy.lp_advertising |= ADVERTISED_Autoneg;
+ pdata->phy.lp_advertising |= ADVERTISED_Backplane;
+
+ /* Compare Advertisement and Link Partner register 1 */
+ ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE);
+ lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA);
+ if (lp_reg & 0x400)
+ pdata->phy.lp_advertising |= ADVERTISED_Pause;
+ if (lp_reg & 0x800)
+ pdata->phy.lp_advertising |= ADVERTISED_Asym_Pause;
+
+ if (pdata->phy.pause_autoneg) {
+ /* Set flow control based on auto-negotiation result */
+ pdata->phy.tx_pause = 0;
+ pdata->phy.rx_pause = 0;
+
+ if (ad_reg & lp_reg & 0x400) {
+ pdata->phy.tx_pause = 1;
+ pdata->phy.rx_pause = 1;
+ } else if (ad_reg & lp_reg & 0x800) {
+ if (ad_reg & 0x400)
+ pdata->phy.rx_pause = 1;
+ else if (lp_reg & 0x400)
+ pdata->phy.tx_pause = 1;
+ }
+ }
+
+ /* Compare Advertisement and Link Partner register 2 */
+ ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1);
+ lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 1);
+ if (lp_reg & 0x80)
+ pdata->phy.lp_advertising |= ADVERTISED_10000baseKR_Full;
+ if (lp_reg & 0x20) {
+ if (phy_data->speed_set == XGBE_SPEEDSET_2500_10000)
+ pdata->phy.lp_advertising |= ADVERTISED_2500baseX_Full;
+ else
+ pdata->phy.lp_advertising |= ADVERTISED_1000baseKX_Full;
+ }
+
+ ad_reg &= lp_reg;
+ if (ad_reg & 0x80) {
+ mode = XGBE_MODE_KR;
+ } else if (ad_reg & 0x20) {
+ if (phy_data->speed_set == XGBE_SPEEDSET_2500_10000)
+ mode = XGBE_MODE_KX_2500;
+ else
+ mode = XGBE_MODE_KX_1000;
+ } else {
+ mode = XGBE_MODE_UNKNOWN;
+ }
+
+ /* Compare Advertisement and Link Partner register 3 */
+ ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2);
+ lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 2);
+ if (lp_reg & 0xc000)
+ pdata->phy.lp_advertising |= ADVERTISED_10000baseR_FEC;
+
+ return mode;
+}
+
+static unsigned int xgbe_phy_an_advertising(struct xgbe_prv_data *pdata)
+{
+ return pdata->phy.advertising;
+}
+
+static int xgbe_phy_an_config(struct xgbe_prv_data *pdata)
+{
+ /* Nothing uniquely required for an configuration */
+ return 0;
+}
+
+static enum xgbe_an_mode xgbe_phy_an_mode(struct xgbe_prv_data *pdata)
+{
+ return XGBE_AN_MODE_CL73;
+}
+
+static void xgbe_phy_pcs_power_cycle(struct xgbe_prv_data *pdata)
+{
+ unsigned int reg;
+
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
+
+ reg |= MDIO_CTRL1_LPOWER;
+ XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
+
+ usleep_range(75, 100);
+
+ reg &= ~MDIO_CTRL1_LPOWER;
+ XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
+}
+
+static void xgbe_phy_start_ratechange(struct xgbe_prv_data *pdata)
+{
+ /* Assert Rx and Tx ratechange */
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, RATECHANGE, 1);
+}
+
+static void xgbe_phy_complete_ratechange(struct xgbe_prv_data *pdata)
+{
+ unsigned int wait;
+ u16 status;
+
+ /* Release Rx and Tx ratechange */
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, RATECHANGE, 0);
+
+ /* Wait for Rx and Tx ready */
+ wait = XGBE_RATECHANGE_COUNT;
+ while (wait--) {
+ usleep_range(50, 75);
+
+ status = XSIR0_IOREAD(pdata, SIR0_STATUS);
+ if (XSIR_GET_BITS(status, SIR0_STATUS, RX_READY) &&
+ XSIR_GET_BITS(status, SIR0_STATUS, TX_READY))
+ goto rx_reset;
+ }
+
+ netif_dbg(pdata, link, pdata->netdev, "SerDes rx/tx not ready (%#hx)\n",
+ status);
+
+rx_reset:
+ /* Perform Rx reset for the DFE changes */
+ XRXTX_IOWRITE_BITS(pdata, RXTX_REG6, RESETB_RXD, 0);
+ XRXTX_IOWRITE_BITS(pdata, RXTX_REG6, RESETB_RXD, 1);
+}
+
+static void xgbe_phy_kr_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int reg;
+
+ /* Set PCS to KR/10G speed */
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL2);
+ reg &= ~MDIO_PCS_CTRL2_TYPE;
+ reg |= MDIO_PCS_CTRL2_10GBR;
+ XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL2, reg);
+
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
+ reg &= ~MDIO_CTRL1_SPEEDSEL;
+ reg |= MDIO_CTRL1_SPEED10G;
+ XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
+
+ xgbe_phy_pcs_power_cycle(pdata);
+
+ /* Set SerDes to 10G speed */
+ xgbe_phy_start_ratechange(pdata);
+
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, DATARATE, XGBE_SPEED_10000_RATE);
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, WORDMODE, XGBE_SPEED_10000_WORD);
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, PLLSEL, XGBE_SPEED_10000_PLL);
+
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, CDR_RATE,
+ phy_data->cdr_rate[XGBE_SPEED_10000]);
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, TXAMP,
+ phy_data->tx_amp[XGBE_SPEED_10000]);
+ XRXTX_IOWRITE_BITS(pdata, RXTX_REG20, BLWC_ENA,
+ phy_data->blwc[XGBE_SPEED_10000]);
+ XRXTX_IOWRITE_BITS(pdata, RXTX_REG114, PQ_REG,
+ phy_data->pq_skew[XGBE_SPEED_10000]);
+ XRXTX_IOWRITE_BITS(pdata, RXTX_REG129, RXDFE_CONFIG,
+ phy_data->dfe_tap_cfg[XGBE_SPEED_10000]);
+ XRXTX_IOWRITE(pdata, RXTX_REG22,
+ phy_data->dfe_tap_ena[XGBE_SPEED_10000]);
+
+ xgbe_phy_complete_ratechange(pdata);
+
+ netif_dbg(pdata, link, pdata->netdev, "10GbE KR mode set\n");
+}
+
+static void xgbe_phy_kx_2500_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int reg;
+
+ /* Set PCS to KX/1G speed */
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL2);
+ reg &= ~MDIO_PCS_CTRL2_TYPE;
+ reg |= MDIO_PCS_CTRL2_10GBX;
+ XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL2, reg);
+
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
+ reg &= ~MDIO_CTRL1_SPEEDSEL;
+ reg |= MDIO_CTRL1_SPEED1G;
+ XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
+
+ xgbe_phy_pcs_power_cycle(pdata);
+
+ /* Set SerDes to 2.5G speed */
+ xgbe_phy_start_ratechange(pdata);
+
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, DATARATE, XGBE_SPEED_2500_RATE);
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, WORDMODE, XGBE_SPEED_2500_WORD);
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, PLLSEL, XGBE_SPEED_2500_PLL);
+
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, CDR_RATE,
+ phy_data->cdr_rate[XGBE_SPEED_2500]);
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, TXAMP,
+ phy_data->tx_amp[XGBE_SPEED_2500]);
+ XRXTX_IOWRITE_BITS(pdata, RXTX_REG20, BLWC_ENA,
+ phy_data->blwc[XGBE_SPEED_2500]);
+ XRXTX_IOWRITE_BITS(pdata, RXTX_REG114, PQ_REG,
+ phy_data->pq_skew[XGBE_SPEED_2500]);
+ XRXTX_IOWRITE_BITS(pdata, RXTX_REG129, RXDFE_CONFIG,
+ phy_data->dfe_tap_cfg[XGBE_SPEED_2500]);
+ XRXTX_IOWRITE(pdata, RXTX_REG22,
+ phy_data->dfe_tap_ena[XGBE_SPEED_2500]);
+
+ xgbe_phy_complete_ratechange(pdata);
+
+ netif_dbg(pdata, link, pdata->netdev, "2.5GbE KX mode set\n");
+}
+
+static void xgbe_phy_kx_1000_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int reg;
+
+ /* Set PCS to KX/1G speed */
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL2);
+ reg &= ~MDIO_PCS_CTRL2_TYPE;
+ reg |= MDIO_PCS_CTRL2_10GBX;
+ XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL2, reg);
+
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
+ reg &= ~MDIO_CTRL1_SPEEDSEL;
+ reg |= MDIO_CTRL1_SPEED1G;
+ XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
+
+ xgbe_phy_pcs_power_cycle(pdata);
+
+ /* Set SerDes to 1G speed */
+ xgbe_phy_start_ratechange(pdata);
+
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, DATARATE, XGBE_SPEED_1000_RATE);
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, WORDMODE, XGBE_SPEED_1000_WORD);
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, PLLSEL, XGBE_SPEED_1000_PLL);
+
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, CDR_RATE,
+ phy_data->cdr_rate[XGBE_SPEED_1000]);
+ XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, TXAMP,
+ phy_data->tx_amp[XGBE_SPEED_1000]);
+ XRXTX_IOWRITE_BITS(pdata, RXTX_REG20, BLWC_ENA,
+ phy_data->blwc[XGBE_SPEED_1000]);
+ XRXTX_IOWRITE_BITS(pdata, RXTX_REG114, PQ_REG,
+ phy_data->pq_skew[XGBE_SPEED_1000]);
+ XRXTX_IOWRITE_BITS(pdata, RXTX_REG129, RXDFE_CONFIG,
+ phy_data->dfe_tap_cfg[XGBE_SPEED_1000]);
+ XRXTX_IOWRITE(pdata, RXTX_REG22,
+ phy_data->dfe_tap_ena[XGBE_SPEED_1000]);
+
+ xgbe_phy_complete_ratechange(pdata);
+
+ netif_dbg(pdata, link, pdata->netdev, "1GbE KX mode set\n");
+}
+
+static enum xgbe_mode xgbe_phy_cur_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ enum xgbe_mode mode;
+ unsigned int reg;
+
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL2);
+ reg &= MDIO_PCS_CTRL2_TYPE;
+
+ if (reg == MDIO_PCS_CTRL2_10GBR) {
+ mode = XGBE_MODE_KR;
+ } else {
+ if (phy_data->speed_set == XGBE_SPEEDSET_2500_10000)
+ mode = XGBE_MODE_KX_2500;
+ else
+ mode = XGBE_MODE_KX_1000;
+ }
+
+ return mode;
+}
+
+static enum xgbe_mode xgbe_phy_switch_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ enum xgbe_mode mode;
+
+ /* If we are in KR switch to KX, and vice-versa */
+ if (xgbe_phy_cur_mode(pdata) == XGBE_MODE_KR) {
+ if (phy_data->speed_set == XGBE_SPEEDSET_2500_10000)
+ mode = XGBE_MODE_KX_2500;
+ else
+ mode = XGBE_MODE_KX_1000;
+ } else {
+ mode = XGBE_MODE_KR;
+ }
+
+ return mode;
+}
+
+static enum xgbe_mode xgbe_phy_get_mode(struct xgbe_prv_data *pdata,
+ int speed)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (speed) {
+ case SPEED_1000:
+ return (phy_data->speed_set == XGBE_SPEEDSET_1000_10000)
+ ? XGBE_MODE_KX_1000 : XGBE_MODE_UNKNOWN;
+ case SPEED_2500:
+ return (phy_data->speed_set == XGBE_SPEEDSET_2500_10000)
+ ? XGBE_MODE_KX_2500 : XGBE_MODE_UNKNOWN;
+ case SPEED_10000:
+ return XGBE_MODE_KR;
+ default:
+ return XGBE_MODE_UNKNOWN;
+ }
+}
+
+static void xgbe_phy_set_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode)
+{
+ switch (mode) {
+ case XGBE_MODE_KX_1000:
+ xgbe_phy_kx_1000_mode(pdata);
+ break;
+ case XGBE_MODE_KX_2500:
+ xgbe_phy_kx_2500_mode(pdata);
+ break;
+ case XGBE_MODE_KR:
+ xgbe_phy_kr_mode(pdata);
+ break;
+ default:
+ break;
+ }
+}
+
+static bool xgbe_phy_check_mode(struct xgbe_prv_data *pdata,
+ enum xgbe_mode mode, u32 advert)
+{
+ if (pdata->phy.autoneg == AUTONEG_ENABLE) {
+ if (pdata->phy.advertising & advert)
+ return true;
+ } else {
+ enum xgbe_mode cur_mode;
+
+ cur_mode = xgbe_phy_get_mode(pdata, pdata->phy.speed);
+ if (cur_mode == mode)
+ return true;
+ }
+
+ return false;
+}
+
+static bool xgbe_phy_use_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode)
+{
+ switch (mode) {
+ case XGBE_MODE_KX_1000:
+ return xgbe_phy_check_mode(pdata, mode,
+ ADVERTISED_1000baseKX_Full);
+ case XGBE_MODE_KX_2500:
+ return xgbe_phy_check_mode(pdata, mode,
+ ADVERTISED_2500baseX_Full);
+ case XGBE_MODE_KR:
+ return xgbe_phy_check_mode(pdata, mode,
+ ADVERTISED_10000baseKR_Full);
+ default:
+ return false;
+ }
+}
+
+static bool xgbe_phy_valid_speed(struct xgbe_prv_data *pdata, int speed)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (speed) {
+ case SPEED_1000:
+ if (phy_data->speed_set != XGBE_SPEEDSET_1000_10000)
+ return false;
+ return true;
+ case SPEED_2500:
+ if (phy_data->speed_set != XGBE_SPEEDSET_2500_10000)
+ return false;
+ return true;
+ case SPEED_10000:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
+{
+ unsigned int reg;
+
+ *an_restart = 0;
+
+ /* Link status is latched low, so read once to clear
+ * and then read again to get current state
+ */
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+
+ return (reg & MDIO_STAT1_LSTATUS) ? 1 : 0;
+}
+
+static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
+{
+ /* Nothing uniquely required for stop */
+}
+
+static int xgbe_phy_start(struct xgbe_prv_data *pdata)
+{
+ /* Nothing uniquely required for start */
+ return 0;
+}
+
+static int xgbe_phy_reset(struct xgbe_prv_data *pdata)
+{
+ unsigned int reg, count;
+
+ /* Perform a software reset of the PCS */
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
+ reg |= MDIO_CTRL1_RESET;
+ XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
+
+ count = 50;
+ do {
+ msleep(20);
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
+ } while ((reg & MDIO_CTRL1_RESET) && --count);
+
+ if (reg & MDIO_CTRL1_RESET)
+ return -ETIMEDOUT;
+
+ return 0;
+}
+
+static void xgbe_phy_exit(struct xgbe_prv_data *pdata)
+{
+ /* Nothing uniquely required for exit */
+}
+
+static int xgbe_phy_init(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data;
+ int ret;
+
+ phy_data = devm_kzalloc(pdata->dev, sizeof(*phy_data), GFP_KERNEL);
+ if (!phy_data)
+ return -ENOMEM;
+
+ /* Retrieve the PHY speedset */
+ ret = device_property_read_u32(pdata->phy_dev, XGBE_SPEEDSET_PROPERTY,
+ &phy_data->speed_set);
+ if (ret) {
+ dev_err(pdata->dev, "invalid %s property\n",
+ XGBE_SPEEDSET_PROPERTY);
+ return ret;
+ }
+
+ switch (phy_data->speed_set) {
+ case XGBE_SPEEDSET_1000_10000:
+ case XGBE_SPEEDSET_2500_10000:
+ break;
+ default:
+ dev_err(pdata->dev, "invalid %s property\n",
+ XGBE_SPEEDSET_PROPERTY);
+ return -EINVAL;
+ }
+
+ /* Retrieve the PHY configuration properties */
+ if (device_property_present(pdata->phy_dev, XGBE_BLWC_PROPERTY)) {
+ ret = device_property_read_u32_array(pdata->phy_dev,
+ XGBE_BLWC_PROPERTY,
+ phy_data->blwc,
+ XGBE_SPEEDS);
+ if (ret) {
+ dev_err(pdata->dev, "invalid %s property\n",
+ XGBE_BLWC_PROPERTY);
+ return ret;
+ }
+ } else {
+ memcpy(phy_data->blwc, xgbe_phy_blwc,
+ sizeof(phy_data->blwc));
+ }
+
+ if (device_property_present(pdata->phy_dev, XGBE_CDR_RATE_PROPERTY)) {
+ ret = device_property_read_u32_array(pdata->phy_dev,
+ XGBE_CDR_RATE_PROPERTY,
+ phy_data->cdr_rate,
+ XGBE_SPEEDS);
+ if (ret) {
+ dev_err(pdata->dev, "invalid %s property\n",
+ XGBE_CDR_RATE_PROPERTY);
+ return ret;
+ }
+ } else {
+ memcpy(phy_data->cdr_rate, xgbe_phy_cdr_rate,
+ sizeof(phy_data->cdr_rate));
+ }
+
+ if (device_property_present(pdata->phy_dev, XGBE_PQ_SKEW_PROPERTY)) {
+ ret = device_property_read_u32_array(pdata->phy_dev,
+ XGBE_PQ_SKEW_PROPERTY,
+ phy_data->pq_skew,
+ XGBE_SPEEDS);
+ if (ret) {
+ dev_err(pdata->dev, "invalid %s property\n",
+ XGBE_PQ_SKEW_PROPERTY);
+ return ret;
+ }
+ } else {
+ memcpy(phy_data->pq_skew, xgbe_phy_pq_skew,
+ sizeof(phy_data->pq_skew));
+ }
+
+ if (device_property_present(pdata->phy_dev, XGBE_TX_AMP_PROPERTY)) {
+ ret = device_property_read_u32_array(pdata->phy_dev,
+ XGBE_TX_AMP_PROPERTY,
+ phy_data->tx_amp,
+ XGBE_SPEEDS);
+ if (ret) {
+ dev_err(pdata->dev, "invalid %s property\n",
+ XGBE_TX_AMP_PROPERTY);
+ return ret;
+ }
+ } else {
+ memcpy(phy_data->tx_amp, xgbe_phy_tx_amp,
+ sizeof(phy_data->tx_amp));
+ }
+
+ if (device_property_present(pdata->phy_dev, XGBE_DFE_CFG_PROPERTY)) {
+ ret = device_property_read_u32_array(pdata->phy_dev,
+ XGBE_DFE_CFG_PROPERTY,
+ phy_data->dfe_tap_cfg,
+ XGBE_SPEEDS);
+ if (ret) {
+ dev_err(pdata->dev, "invalid %s property\n",
+ XGBE_DFE_CFG_PROPERTY);
+ return ret;
+ }
+ } else {
+ memcpy(phy_data->dfe_tap_cfg, xgbe_phy_dfe_tap_cfg,
+ sizeof(phy_data->dfe_tap_cfg));
+ }
+
+ if (device_property_present(pdata->phy_dev, XGBE_DFE_ENA_PROPERTY)) {
+ ret = device_property_read_u32_array(pdata->phy_dev,
+ XGBE_DFE_ENA_PROPERTY,
+ phy_data->dfe_tap_ena,
+ XGBE_SPEEDS);
+ if (ret) {
+ dev_err(pdata->dev, "invalid %s property\n",
+ XGBE_DFE_ENA_PROPERTY);
+ return ret;
+ }
+ } else {
+ memcpy(phy_data->dfe_tap_ena, xgbe_phy_dfe_tap_ena,
+ sizeof(phy_data->dfe_tap_ena));
+ }
+
+ /* Initialize supported features */
+ pdata->phy.supported = SUPPORTED_Autoneg;
+ pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+ pdata->phy.supported |= SUPPORTED_Backplane;
+ pdata->phy.supported |= SUPPORTED_10000baseKR_Full;
+ switch (phy_data->speed_set) {
+ case XGBE_SPEEDSET_1000_10000:
+ pdata->phy.supported |= SUPPORTED_1000baseKX_Full;
+ break;
+ case XGBE_SPEEDSET_2500_10000:
+ pdata->phy.supported |= SUPPORTED_2500baseX_Full;
+ break;
+ }
+
+ if (pdata->fec_ability & MDIO_PMA_10GBR_FECABLE_ABLE)
+ pdata->phy.supported |= SUPPORTED_10000baseR_FEC;
+
+ pdata->phy_data = phy_data;
+
+ return 0;
+}
+
+void xgbe_init_function_ptrs_phy_v1(struct xgbe_phy_if *phy_if)
+{
+ struct xgbe_phy_impl_if *phy_impl = &phy_if->phy_impl;
+
+ phy_impl->init = xgbe_phy_init;
+ phy_impl->exit = xgbe_phy_exit;
+
+ phy_impl->reset = xgbe_phy_reset;
+ phy_impl->start = xgbe_phy_start;
+ phy_impl->stop = xgbe_phy_stop;
+
+ phy_impl->link_status = xgbe_phy_link_status;
+
+ phy_impl->valid_speed = xgbe_phy_valid_speed;
+
+ phy_impl->use_mode = xgbe_phy_use_mode;
+ phy_impl->set_mode = xgbe_phy_set_mode;
+ phy_impl->get_mode = xgbe_phy_get_mode;
+ phy_impl->switch_mode = xgbe_phy_switch_mode;
+ phy_impl->cur_mode = xgbe_phy_cur_mode;
+
+ phy_impl->an_mode = xgbe_phy_an_mode;
+
+ phy_impl->an_config = xgbe_phy_an_config;
+
+ phy_impl->an_advertising = xgbe_phy_an_advertising;
+
+ phy_impl->an_outcome = xgbe_phy_an_outcome;
+
+ phy_impl->kr_training_pre = xgbe_phy_kr_training_pre;
+ phy_impl->kr_training_post = xgbe_phy_kr_training_post;
+}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
new file mode 100644
index 0000000..9d8c9530
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -0,0 +1,3084 @@
+/*
+ * AMD 10Gb Ethernet driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2016 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ * The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ * (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ * Inc. unless otherwise expressly agreed to in writing between Synopsys
+ * and you.
+ *
+ * The Software IS NOT an item of Licensed Software or Licensed Product
+ * under any End User Software License Agreement or Agreement for Licensed
+ * Product with Synopsys or any supplement thereto. Permission is hereby
+ * granted, free of charge, to any person obtaining a copy of this software
+ * annotated with this license and the Software, to deal in the Software
+ * without restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is furnished
+ * to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ * BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ * PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ * THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2016 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Advanced Micro Devices, Inc. nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ * The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ * (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ * Inc. unless otherwise expressly agreed to in writing between Synopsys
+ * and you.
+ *
+ * The Software IS NOT an item of Licensed Software or Licensed Product
+ * under any End User Software License Agreement or Agreement for Licensed
+ * Product with Synopsys or any supplement thereto. Permission is hereby
+ * granted, free of charge, to any person obtaining a copy of this software
+ * annotated with this license and the Software, to deal in the Software
+ * without restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is furnished
+ * to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ * BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ * PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ * THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/kmod.h>
+#include <linux/mdio.h>
+#include <linux/phy.h>
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+#define XGBE_PHY_PORT_SPEED_100 BIT(0)
+#define XGBE_PHY_PORT_SPEED_1000 BIT(1)
+#define XGBE_PHY_PORT_SPEED_2500 BIT(2)
+#define XGBE_PHY_PORT_SPEED_10000 BIT(3)
+
+#define XGBE_MUTEX_RELEASE 0x80000000
+
+#define XGBE_SFP_DIRECT 7
+
+/* I2C target addresses */
+#define XGBE_SFP_SERIAL_ID_ADDRESS 0x50
+#define XGBE_SFP_DIAG_INFO_ADDRESS 0x51
+#define XGBE_SFP_PHY_ADDRESS 0x56
+#define XGBE_GPIO_ADDRESS_PCA9555 0x20
+
+/* SFP sideband signal indicators */
+#define XGBE_GPIO_NO_TX_FAULT BIT(0)
+#define XGBE_GPIO_NO_RATE_SELECT BIT(1)
+#define XGBE_GPIO_NO_MOD_ABSENT BIT(2)
+#define XGBE_GPIO_NO_RX_LOS BIT(3)
+
+/* Rate-change complete wait/retry count */
+#define XGBE_RATECHANGE_COUNT 500
+
+enum xgbe_port_mode {
+ XGBE_PORT_MODE_RSVD = 0,
+ XGBE_PORT_MODE_BACKPLANE,
+ XGBE_PORT_MODE_BACKPLANE_2500,
+ XGBE_PORT_MODE_1000BASE_T,
+ XGBE_PORT_MODE_1000BASE_X,
+ XGBE_PORT_MODE_NBASE_T,
+ XGBE_PORT_MODE_10GBASE_T,
+ XGBE_PORT_MODE_10GBASE_R,
+ XGBE_PORT_MODE_SFP,
+ XGBE_PORT_MODE_MAX,
+};
+
+enum xgbe_conn_type {
+ XGBE_CONN_TYPE_NONE = 0,
+ XGBE_CONN_TYPE_SFP,
+ XGBE_CONN_TYPE_MDIO,
+ XGBE_CONN_TYPE_RSVD1,
+ XGBE_CONN_TYPE_BACKPLANE,
+ XGBE_CONN_TYPE_MAX,
+};
+
+/* SFP/SFP+ related definitions */
+enum xgbe_sfp_comm {
+ XGBE_SFP_COMM_DIRECT = 0,
+ XGBE_SFP_COMM_PCA9545,
+};
+
+enum xgbe_sfp_cable {
+ XGBE_SFP_CABLE_UNKNOWN = 0,
+ XGBE_SFP_CABLE_ACTIVE,
+ XGBE_SFP_CABLE_PASSIVE,
+};
+
+enum xgbe_sfp_base {
+ XGBE_SFP_BASE_UNKNOWN = 0,
+ XGBE_SFP_BASE_1000_T,
+ XGBE_SFP_BASE_1000_SX,
+ XGBE_SFP_BASE_1000_LX,
+ XGBE_SFP_BASE_1000_CX,
+ XGBE_SFP_BASE_10000_SR,
+ XGBE_SFP_BASE_10000_LR,
+ XGBE_SFP_BASE_10000_LRM,
+ XGBE_SFP_BASE_10000_ER,
+ XGBE_SFP_BASE_10000_CR,
+};
+
+enum xgbe_sfp_speed {
+ XGBE_SFP_SPEED_UNKNOWN = 0,
+ XGBE_SFP_SPEED_100_1000,
+ XGBE_SFP_SPEED_1000,
+ XGBE_SFP_SPEED_10000,
+};
+
+/* SFP Serial ID Base ID values relative to an offset of 0 */
+#define XGBE_SFP_BASE_ID 0
+#define XGBE_SFP_ID_SFP 0x03
+
+#define XGBE_SFP_BASE_EXT_ID 1
+#define XGBE_SFP_EXT_ID_SFP 0x04
+
+#define XGBE_SFP_BASE_10GBE_CC 3
+#define XGBE_SFP_BASE_10GBE_CC_SR BIT(4)
+#define XGBE_SFP_BASE_10GBE_CC_LR BIT(5)
+#define XGBE_SFP_BASE_10GBE_CC_LRM BIT(6)
+#define XGBE_SFP_BASE_10GBE_CC_ER BIT(7)
+
+#define XGBE_SFP_BASE_1GBE_CC 6
+#define XGBE_SFP_BASE_1GBE_CC_SX BIT(0)
+#define XGBE_SFP_BASE_1GBE_CC_LX BIT(1)
+#define XGBE_SFP_BASE_1GBE_CC_CX BIT(2)
+#define XGBE_SFP_BASE_1GBE_CC_T BIT(3)
+
+#define XGBE_SFP_BASE_CABLE 8
+#define XGBE_SFP_BASE_CABLE_PASSIVE BIT(2)
+#define XGBE_SFP_BASE_CABLE_ACTIVE BIT(3)
+
+#define XGBE_SFP_BASE_BR 12
+#define XGBE_SFP_BASE_BR_1GBE_MIN 0x0a
+#define XGBE_SFP_BASE_BR_1GBE_MAX 0x0d
+#define XGBE_SFP_BASE_BR_10GBE_MIN 0x64
+#define XGBE_SFP_BASE_BR_10GBE_MAX 0x68
+
+#define XGBE_SFP_BASE_CU_CABLE_LEN 18
+
+#define XGBE_SFP_BASE_VENDOR_NAME 20
+#define XGBE_SFP_BASE_VENDOR_NAME_LEN 16
+#define XGBE_SFP_BASE_VENDOR_PN 40
+#define XGBE_SFP_BASE_VENDOR_PN_LEN 16
+#define XGBE_SFP_BASE_VENDOR_REV 56
+#define XGBE_SFP_BASE_VENDOR_REV_LEN 4
+
+#define XGBE_SFP_BASE_CC 63
+
+/* SFP Serial ID Extended ID values relative to an offset of 64 */
+#define XGBE_SFP_BASE_VENDOR_SN 4
+#define XGBE_SFP_BASE_VENDOR_SN_LEN 16
+
+#define XGBE_SFP_EXTD_DIAG 28
+#define XGBE_SFP_EXTD_DIAG_ADDR_CHANGE BIT(2)
+
+#define XGBE_SFP_EXTD_SFF_8472 30
+
+#define XGBE_SFP_EXTD_CC 31
+
+struct xgbe_sfp_eeprom {
+ u8 base[64];
+ u8 extd[32];
+ u8 vendor[32];
+};
+
+#define XGBE_BEL_FUSE_VENDOR "BEL-FUSE "
+#define XGBE_BEL_FUSE_PARTNO "1GBT-SFP06 "
+
+struct xgbe_sfp_ascii {
+ union {
+ char vendor[XGBE_SFP_BASE_VENDOR_NAME_LEN + 1];
+ char partno[XGBE_SFP_BASE_VENDOR_PN_LEN + 1];
+ char rev[XGBE_SFP_BASE_VENDOR_REV_LEN + 1];
+ char serno[XGBE_SFP_BASE_VENDOR_SN_LEN + 1];
+ } u;
+};
+
+/* MDIO PHY reset types */
+enum xgbe_mdio_reset {
+ XGBE_MDIO_RESET_NONE = 0,
+ XGBE_MDIO_RESET_I2C_GPIO,
+ XGBE_MDIO_RESET_INT_GPIO,
+ XGBE_MDIO_RESET_MAX,
+};
+
+/* Re-driver related definitions */
+enum xgbe_phy_redrv_if {
+ XGBE_PHY_REDRV_IF_MDIO = 0,
+ XGBE_PHY_REDRV_IF_I2C,
+ XGBE_PHY_REDRV_IF_MAX,
+};
+
+enum xgbe_phy_redrv_model {
+ XGBE_PHY_REDRV_MODEL_4223 = 0,
+ XGBE_PHY_REDRV_MODEL_4227,
+ XGBE_PHY_REDRV_MODEL_MAX,
+};
+
+enum xgbe_phy_redrv_mode {
+ XGBE_PHY_REDRV_MODE_CX = 5,
+ XGBE_PHY_REDRV_MODE_SR = 9,
+};
+
+#define XGBE_PHY_REDRV_MODE_REG 0x12b0
+
+/* PHY related configuration information */
+struct xgbe_phy_data {
+ enum xgbe_port_mode port_mode;
+
+ unsigned int port_id;
+
+ unsigned int port_speeds;
+
+ enum xgbe_conn_type conn_type;
+
+ enum xgbe_mode cur_mode;
+ enum xgbe_mode start_mode;
+
+ unsigned int rrc_count;
+
+ unsigned int mdio_addr;
+
+ unsigned int comm_owned;
+
+ /* SFP Support */
+ enum xgbe_sfp_comm sfp_comm;
+ unsigned int sfp_mux_address;
+ unsigned int sfp_mux_channel;
+
+ unsigned int sfp_gpio_address;
+ unsigned int sfp_gpio_mask;
+ unsigned int sfp_gpio_rx_los;
+ unsigned int sfp_gpio_tx_fault;
+ unsigned int sfp_gpio_mod_absent;
+ unsigned int sfp_gpio_rate_select;
+
+ unsigned int sfp_rx_los;
+ unsigned int sfp_tx_fault;
+ unsigned int sfp_mod_absent;
+ unsigned int sfp_diags;
+ unsigned int sfp_changed;
+ unsigned int sfp_phy_avail;
+ unsigned int sfp_cable_len;
+ enum xgbe_sfp_base sfp_base;
+ enum xgbe_sfp_cable sfp_cable;
+ enum xgbe_sfp_speed sfp_speed;
+ struct xgbe_sfp_eeprom sfp_eeprom;
+
+ /* External PHY support */
+ enum xgbe_mdio_mode phydev_mode;
+ struct mii_bus *mii;
+ struct phy_device *phydev;
+ enum xgbe_mdio_reset mdio_reset;
+ unsigned int mdio_reset_addr;
+ unsigned int mdio_reset_gpio;
+
+ /* Re-driver support */
+ unsigned int redrv;
+ unsigned int redrv_if;
+ unsigned int redrv_addr;
+ unsigned int redrv_lane;
+ unsigned int redrv_model;
+};
+
+/* I2C, MDIO and GPIO lines are muxed, so only one device at a time */
+static DEFINE_MUTEX(xgbe_phy_comm_lock);
+
+static enum xgbe_an_mode xgbe_phy_an_mode(struct xgbe_prv_data *pdata);
+
+static int xgbe_phy_i2c_xfer(struct xgbe_prv_data *pdata,
+ struct xgbe_i2c_op *i2c_op)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ /* Be sure we own the bus */
+ if (WARN_ON(!phy_data->comm_owned))
+ return -EIO;
+
+ return pdata->i2c_if.i2c_xfer(pdata, i2c_op);
+}
+
+static int xgbe_phy_redrv_write(struct xgbe_prv_data *pdata, unsigned int reg,
+ unsigned int val)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ struct xgbe_i2c_op i2c_op;
+ __be16 *redrv_val;
+ u8 redrv_data[5], csum;
+ unsigned int i, retry;
+ int ret;
+
+ /* High byte of register contains read/write indicator */
+ redrv_data[0] = ((reg >> 8) & 0xff) << 1;
+ redrv_data[1] = reg & 0xff;
+ redrv_val = (__be16 *)&redrv_data[2];
+ *redrv_val = cpu_to_be16(val);
+
+ /* Calculate 1 byte checksum */
+ csum = 0;
+ for (i = 0; i < 4; i++) {
+ csum += redrv_data[i];
+ if (redrv_data[i] > csum)
+ csum++;
+ }
+ redrv_data[4] = ~csum;
+
+ retry = 1;
+again1:
+ i2c_op.cmd = XGBE_I2C_CMD_WRITE;
+ i2c_op.target = phy_data->redrv_addr;
+ i2c_op.len = sizeof(redrv_data);
+ i2c_op.buf = redrv_data;
+ ret = xgbe_phy_i2c_xfer(pdata, &i2c_op);
+ if (ret) {
+ if ((ret == -EAGAIN) && retry--)
+ goto again1;
+
+ return ret;
+ }
+
+ retry = 1;
+again2:
+ i2c_op.cmd = XGBE_I2C_CMD_READ;
+ i2c_op.target = phy_data->redrv_addr;
+ i2c_op.len = 1;
+ i2c_op.buf = redrv_data;
+ ret = xgbe_phy_i2c_xfer(pdata, &i2c_op);
+ if (ret) {
+ if ((ret == -EAGAIN) && retry--)
+ goto again2;
+
+ return ret;
+ }
+
+ if (redrv_data[0] != 0xff) {
+ netif_dbg(pdata, drv, pdata->netdev,
+ "Redriver write checksum error\n");
+ ret = -EIO;
+ }
+
+ return ret;
+}
+
+static int xgbe_phy_i2c_write(struct xgbe_prv_data *pdata, unsigned int target,
+ void *val, unsigned int val_len)
+{
+ struct xgbe_i2c_op i2c_op;
+ int retry, ret;
+
+ retry = 1;
+again:
+ /* Write the specfied register */
+ i2c_op.cmd = XGBE_I2C_CMD_WRITE;
+ i2c_op.target = target;
+ i2c_op.len = val_len;
+ i2c_op.buf = val;
+ ret = xgbe_phy_i2c_xfer(pdata, &i2c_op);
+ if ((ret == -EAGAIN) && retry--)
+ goto again;
+
+ return ret;
+}
+
+static int xgbe_phy_i2c_read(struct xgbe_prv_data *pdata, unsigned int target,
+ void *reg, unsigned int reg_len,
+ void *val, unsigned int val_len)
+{
+ struct xgbe_i2c_op i2c_op;
+ int retry, ret;
+
+ retry = 1;
+again1:
+ /* Set the specified register to read */
+ i2c_op.cmd = XGBE_I2C_CMD_WRITE;
+ i2c_op.target = target;
+ i2c_op.len = reg_len;
+ i2c_op.buf = reg;
+ ret = xgbe_phy_i2c_xfer(pdata, &i2c_op);
+ if (ret) {
+ if ((ret == -EAGAIN) && retry--)
+ goto again1;
+
+ return ret;
+ }
+
+ retry = 1;
+again2:
+ /* Read the specfied register */
+ i2c_op.cmd = XGBE_I2C_CMD_READ;
+ i2c_op.target = target;
+ i2c_op.len = val_len;
+ i2c_op.buf = val;
+ ret = xgbe_phy_i2c_xfer(pdata, &i2c_op);
+ if ((ret == -EAGAIN) && retry--)
+ goto again2;
+
+ return ret;
+}
+
+static int xgbe_phy_sfp_put_mux(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ struct xgbe_i2c_op i2c_op;
+ u8 mux_channel;
+
+ if (phy_data->sfp_comm == XGBE_SFP_COMM_DIRECT)
+ return 0;
+
+ /* Select no mux channels */
+ mux_channel = 0;
+ i2c_op.cmd = XGBE_I2C_CMD_WRITE;
+ i2c_op.target = phy_data->sfp_mux_address;
+ i2c_op.len = sizeof(mux_channel);
+ i2c_op.buf = &mux_channel;
+
+ return xgbe_phy_i2c_xfer(pdata, &i2c_op);
+}
+
+static int xgbe_phy_sfp_get_mux(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ struct xgbe_i2c_op i2c_op;
+ u8 mux_channel;
+
+ if (phy_data->sfp_comm == XGBE_SFP_COMM_DIRECT)
+ return 0;
+
+ /* Select desired mux channel */
+ mux_channel = 1 << phy_data->sfp_mux_channel;
+ i2c_op.cmd = XGBE_I2C_CMD_WRITE;
+ i2c_op.target = phy_data->sfp_mux_address;
+ i2c_op.len = sizeof(mux_channel);
+ i2c_op.buf = &mux_channel;
+
+ return xgbe_phy_i2c_xfer(pdata, &i2c_op);
+}
+
+static void xgbe_phy_put_comm_ownership(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ phy_data->comm_owned = 0;
+
+ mutex_unlock(&xgbe_phy_comm_lock);
+}
+
+static int xgbe_phy_get_comm_ownership(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned long timeout;
+ unsigned int mutex_id;
+
+ if (phy_data->comm_owned)
+ return 0;
+
+ /* The I2C and MDIO/GPIO bus is multiplexed between multiple devices,
+ * the driver needs to take the software mutex and then the hardware
+ * mutexes before being able to use the busses.
+ */
+ mutex_lock(&xgbe_phy_comm_lock);
+
+ /* Clear the mutexes */
+ XP_IOWRITE(pdata, XP_I2C_MUTEX, XGBE_MUTEX_RELEASE);
+ XP_IOWRITE(pdata, XP_MDIO_MUTEX, XGBE_MUTEX_RELEASE);
+
+ /* Mutex formats are the same for I2C and MDIO/GPIO */
+ mutex_id = 0;
+ XP_SET_BITS(mutex_id, XP_I2C_MUTEX, ID, phy_data->port_id);
+ XP_SET_BITS(mutex_id, XP_I2C_MUTEX, ACTIVE, 1);
+
+ timeout = jiffies + (5 * HZ);
+ while (time_before(jiffies, timeout)) {
+ /* Must be all zeroes in order to obtain the mutex */
+ if (XP_IOREAD(pdata, XP_I2C_MUTEX) ||
+ XP_IOREAD(pdata, XP_MDIO_MUTEX)) {
+ usleep_range(100, 200);
+ continue;
+ }
+
+ /* Obtain the mutex */
+ XP_IOWRITE(pdata, XP_I2C_MUTEX, mutex_id);
+ XP_IOWRITE(pdata, XP_MDIO_MUTEX, mutex_id);
+
+ phy_data->comm_owned = 1;
+ return 0;
+ }
+
+ mutex_unlock(&xgbe_phy_comm_lock);
+
+ netdev_err(pdata->netdev, "unable to obtain hardware mutexes\n");
+
+ return -ETIMEDOUT;
+}
+
+static int xgbe_phy_mdio_mii_write(struct xgbe_prv_data *pdata, int addr,
+ int reg, u16 val)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ if (reg & MII_ADDR_C45) {
+ if (phy_data->phydev_mode != XGBE_MDIO_MODE_CL45)
+ return -ENOTSUPP;
+ } else {
+ if (phy_data->phydev_mode != XGBE_MDIO_MODE_CL22)
+ return -ENOTSUPP;
+ }
+
+ return pdata->hw_if.write_ext_mii_regs(pdata, addr, reg, val);
+}
+
+static int xgbe_phy_i2c_mii_write(struct xgbe_prv_data *pdata, int reg, u16 val)
+{
+ __be16 *mii_val;
+ u8 mii_data[3];
+ int ret;
+
+ ret = xgbe_phy_sfp_get_mux(pdata);
+ if (ret)
+ return ret;
+
+ mii_data[0] = reg & 0xff;
+ mii_val = (__be16 *)&mii_data[1];
+ *mii_val = cpu_to_be16(val);
+
+ ret = xgbe_phy_i2c_write(pdata, XGBE_SFP_PHY_ADDRESS,
+ mii_data, sizeof(mii_data));
+
+ xgbe_phy_sfp_put_mux(pdata);
+
+ return ret;
+}
+
+static int xgbe_phy_mii_write(struct mii_bus *mii, int addr, int reg, u16 val)
+{
+ struct xgbe_prv_data *pdata = mii->priv;
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ int ret;
+
+ ret = xgbe_phy_get_comm_ownership(pdata);
+ if (ret)
+ return ret;
+
+ if (phy_data->conn_type == XGBE_CONN_TYPE_SFP)
+ ret = xgbe_phy_i2c_mii_write(pdata, reg, val);
+ else if (phy_data->conn_type & XGBE_CONN_TYPE_MDIO)
+ ret = xgbe_phy_mdio_mii_write(pdata, addr, reg, val);
+ else
+ ret = -ENOTSUPP;
+
+ xgbe_phy_put_comm_ownership(pdata);
+
+ return ret;
+}
+
+static int xgbe_phy_mdio_mii_read(struct xgbe_prv_data *pdata, int addr,
+ int reg)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ if (reg & MII_ADDR_C45) {
+ if (phy_data->phydev_mode != XGBE_MDIO_MODE_CL45)
+ return -ENOTSUPP;
+ } else {
+ if (phy_data->phydev_mode != XGBE_MDIO_MODE_CL22)
+ return -ENOTSUPP;
+ }
+
+ return pdata->hw_if.read_ext_mii_regs(pdata, addr, reg);
+}
+
+static int xgbe_phy_i2c_mii_read(struct xgbe_prv_data *pdata, int reg)
+{
+ __be16 mii_val;
+ u8 mii_reg;
+ int ret;
+
+ ret = xgbe_phy_sfp_get_mux(pdata);
+ if (ret)
+ return ret;
+
+ mii_reg = reg;
+ ret = xgbe_phy_i2c_read(pdata, XGBE_SFP_PHY_ADDRESS,
+ &mii_reg, sizeof(mii_reg),
+ &mii_val, sizeof(mii_val));
+ if (!ret)
+ ret = be16_to_cpu(mii_val);
+
+ xgbe_phy_sfp_put_mux(pdata);
+
+ return ret;
+}
+
+static int xgbe_phy_mii_read(struct mii_bus *mii, int addr, int reg)
+{
+ struct xgbe_prv_data *pdata = mii->priv;
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ int ret;
+
+ ret = xgbe_phy_get_comm_ownership(pdata);
+ if (ret)
+ return ret;
+
+ if (phy_data->conn_type == XGBE_CONN_TYPE_SFP)
+ ret = xgbe_phy_i2c_mii_read(pdata, reg);
+ else if (phy_data->conn_type & XGBE_CONN_TYPE_MDIO)
+ ret = xgbe_phy_mdio_mii_read(pdata, addr, reg);
+ else
+ ret = -ENOTSUPP;
+
+ xgbe_phy_put_comm_ownership(pdata);
+
+ return ret;
+}
+
+static void xgbe_phy_sfp_phy_settings(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ if (phy_data->sfp_mod_absent) {
+ pdata->phy.speed = SPEED_UNKNOWN;
+ pdata->phy.duplex = DUPLEX_UNKNOWN;
+ pdata->phy.autoneg = AUTONEG_ENABLE;
+ pdata->phy.advertising = pdata->phy.supported;
+ }
+
+ pdata->phy.advertising &= ~ADVERTISED_Autoneg;
+ pdata->phy.advertising &= ~ADVERTISED_TP;
+ pdata->phy.advertising &= ~ADVERTISED_FIBRE;
+ pdata->phy.advertising &= ~ADVERTISED_100baseT_Full;
+ pdata->phy.advertising &= ~ADVERTISED_1000baseT_Full;
+ pdata->phy.advertising &= ~ADVERTISED_10000baseT_Full;
+ pdata->phy.advertising &= ~ADVERTISED_10000baseR_FEC;
+
+ switch (phy_data->sfp_base) {
+ case XGBE_SFP_BASE_1000_T:
+ case XGBE_SFP_BASE_1000_SX:
+ case XGBE_SFP_BASE_1000_LX:
+ case XGBE_SFP_BASE_1000_CX:
+ pdata->phy.speed = SPEED_UNKNOWN;
+ pdata->phy.duplex = DUPLEX_UNKNOWN;
+ pdata->phy.autoneg = AUTONEG_ENABLE;
+ pdata->phy.advertising |= ADVERTISED_Autoneg;
+ break;
+ case XGBE_SFP_BASE_10000_SR:
+ case XGBE_SFP_BASE_10000_LR:
+ case XGBE_SFP_BASE_10000_LRM:
+ case XGBE_SFP_BASE_10000_ER:
+ case XGBE_SFP_BASE_10000_CR:
+ default:
+ pdata->phy.speed = SPEED_10000;
+ pdata->phy.duplex = DUPLEX_FULL;
+ pdata->phy.autoneg = AUTONEG_DISABLE;
+ break;
+ }
+
+ switch (phy_data->sfp_base) {
+ case XGBE_SFP_BASE_1000_T:
+ case XGBE_SFP_BASE_1000_CX:
+ case XGBE_SFP_BASE_10000_CR:
+ pdata->phy.advertising |= ADVERTISED_TP;
+ break;
+ default:
+ pdata->phy.advertising |= ADVERTISED_FIBRE;
+ }
+
+ switch (phy_data->sfp_speed) {
+ case XGBE_SFP_SPEED_100_1000:
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100)
+ pdata->phy.advertising |= ADVERTISED_100baseT_Full;
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000)
+ pdata->phy.advertising |= ADVERTISED_1000baseT_Full;
+ break;
+ case XGBE_SFP_SPEED_1000:
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000)
+ pdata->phy.advertising |= ADVERTISED_1000baseT_Full;
+ break;
+ case XGBE_SFP_SPEED_10000:
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000)
+ pdata->phy.advertising |= ADVERTISED_10000baseT_Full;
+ break;
+ default:
+ /* Choose the fastest supported speed */
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000)
+ pdata->phy.advertising |= ADVERTISED_10000baseT_Full;
+ else if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000)
+ pdata->phy.advertising |= ADVERTISED_1000baseT_Full;
+ else if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100)
+ pdata->phy.advertising |= ADVERTISED_100baseT_Full;
+ }
+}
+
+static bool xgbe_phy_sfp_bit_rate(struct xgbe_sfp_eeprom *sfp_eeprom,
+ enum xgbe_sfp_speed sfp_speed)
+{
+ u8 *sfp_base, min, max;
+
+ sfp_base = sfp_eeprom->base;
+
+ switch (sfp_speed) {
+ case XGBE_SFP_SPEED_1000:
+ min = XGBE_SFP_BASE_BR_1GBE_MIN;
+ max = XGBE_SFP_BASE_BR_1GBE_MAX;
+ break;
+ case XGBE_SFP_SPEED_10000:
+ min = XGBE_SFP_BASE_BR_10GBE_MIN;
+ max = XGBE_SFP_BASE_BR_10GBE_MAX;
+ break;
+ default:
+ return false;
+ }
+
+ return ((sfp_base[XGBE_SFP_BASE_BR] >= min) &&
+ (sfp_base[XGBE_SFP_BASE_BR] <= max));
+}
+
+static void xgbe_phy_free_phy_device(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ if (phy_data->phydev) {
+ phy_detach(phy_data->phydev);
+ phy_device_remove(phy_data->phydev);
+ phy_device_free(phy_data->phydev);
+ phy_data->phydev = NULL;
+ }
+}
+
+static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int phy_id = phy_data->phydev->phy_id;
+
+ if ((phy_id & 0xfffffff0) != 0x01ff0cc0)
+ return false;
+
+ /* Enable Base-T AN */
+ phy_write(phy_data->phydev, 0x16, 0x0001);
+ phy_write(phy_data->phydev, 0x00, 0x9140);
+ phy_write(phy_data->phydev, 0x16, 0x0000);
+
+ /* Enable SGMII at 100Base-T/1000Base-T Full Duplex */
+ phy_write(phy_data->phydev, 0x1b, 0x9084);
+ phy_write(phy_data->phydev, 0x09, 0x0e00);
+ phy_write(phy_data->phydev, 0x00, 0x8140);
+ phy_write(phy_data->phydev, 0x04, 0x0d01);
+ phy_write(phy_data->phydev, 0x00, 0x9140);
+
+ phy_data->phydev->supported = PHY_GBIT_FEATURES;
+ phy_data->phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+ phy_data->phydev->advertising = phy_data->phydev->supported;
+
+ netif_dbg(pdata, drv, pdata->netdev,
+ "Finisar PHY quirk in place\n");
+
+ return true;
+}
+
+static void xgbe_phy_external_phy_quirks(struct xgbe_prv_data *pdata)
+{
+ if (xgbe_phy_finisar_phy_quirks(pdata))
+ return;
+}
+
+static int xgbe_phy_find_phy_device(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ struct phy_device *phydev;
+ int ret;
+
+ /* If we already have a PHY, just return */
+ if (phy_data->phydev)
+ return 0;
+
+ /* Check for the use of an external PHY */
+ if (phy_data->phydev_mode == XGBE_MDIO_MODE_NONE)
+ return 0;
+
+ /* For SFP, only use an external PHY if available */
+ if ((phy_data->port_mode == XGBE_PORT_MODE_SFP) &&
+ !phy_data->sfp_phy_avail)
+ return 0;
+
+ /* Create and connect to the PHY device */
+ phydev = get_phy_device(phy_data->mii, phy_data->mdio_addr,
+ (phy_data->phydev_mode == XGBE_MDIO_MODE_CL45));
+ if (IS_ERR(phydev)) {
+ netdev_err(pdata->netdev, "get_phy_device failed\n");
+ return -ENODEV;
+ }
+ netif_dbg(pdata, drv, pdata->netdev, "external PHY id is %#010x\n",
+ phydev->phy_id);
+
+ /*TODO: If c45, add request_module based on one of the MMD ids? */
+
+ ret = phy_device_register(phydev);
+ if (ret) {
+ netdev_err(pdata->netdev, "phy_device_register failed\n");
+ phy_device_free(phydev);
+ return ret;
+ }
+
+ ret = phy_attach_direct(pdata->netdev, phydev, phydev->dev_flags,
+ PHY_INTERFACE_MODE_SGMII);
+ if (ret) {
+ netdev_err(pdata->netdev, "phy_attach_direct failed\n");
+ phy_device_remove(phydev);
+ phy_device_free(phydev);
+ return ret;
+ }
+ phy_data->phydev = phydev;
+
+ xgbe_phy_external_phy_quirks(pdata);
+ phydev->advertising &= pdata->phy.advertising;
+
+ phy_start_aneg(phy_data->phydev);
+
+ return 0;
+}
+
+static void xgbe_phy_sfp_external_phy(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ int ret;
+
+ if (!phy_data->sfp_changed)
+ return;
+
+ phy_data->sfp_phy_avail = 0;
+
+ if (phy_data->sfp_base != XGBE_SFP_BASE_1000_T)
+ return;
+
+ /* Check access to the PHY by reading CTRL1 */
+ ret = xgbe_phy_i2c_mii_read(pdata, MII_BMCR);
+ if (ret < 0)
+ return;
+
+ /* Successfully accessed the PHY */
+ phy_data->sfp_phy_avail = 1;
+}
+
+static bool xgbe_phy_belfuse_parse_quirks(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ struct xgbe_sfp_eeprom *sfp_eeprom = &phy_data->sfp_eeprom;
+
+ if (memcmp(&sfp_eeprom->base[XGBE_SFP_BASE_VENDOR_NAME],
+ XGBE_BEL_FUSE_VENDOR, XGBE_SFP_BASE_VENDOR_NAME_LEN))
+ return false;
+
+ if (!memcmp(&sfp_eeprom->base[XGBE_SFP_BASE_VENDOR_PN],
+ XGBE_BEL_FUSE_PARTNO, XGBE_SFP_BASE_VENDOR_PN_LEN)) {
+ phy_data->sfp_base = XGBE_SFP_BASE_1000_SX;
+ phy_data->sfp_cable = XGBE_SFP_CABLE_ACTIVE;
+ phy_data->sfp_speed = XGBE_SFP_SPEED_1000;
+ if (phy_data->sfp_changed)
+ netif_dbg(pdata, drv, pdata->netdev,
+ "Bel-Fuse SFP quirk in place\n");
+ return true;
+ }
+
+ return false;
+}
+
+static bool xgbe_phy_sfp_parse_quirks(struct xgbe_prv_data *pdata)
+{
+ if (xgbe_phy_belfuse_parse_quirks(pdata))
+ return true;
+
+ return false;
+}
+
+static void xgbe_phy_sfp_parse_eeprom(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ struct xgbe_sfp_eeprom *sfp_eeprom = &phy_data->sfp_eeprom;
+ u8 *sfp_base;
+
+ sfp_base = sfp_eeprom->base;
+
+ if (sfp_base[XGBE_SFP_BASE_ID] != XGBE_SFP_ID_SFP)
+ return;
+
+ if (sfp_base[XGBE_SFP_BASE_EXT_ID] != XGBE_SFP_EXT_ID_SFP)
+ return;
+
+ if (xgbe_phy_sfp_parse_quirks(pdata))
+ return;
+
+ /* Assume ACTIVE cable unless told it is PASSIVE */
+ if (sfp_base[XGBE_SFP_BASE_CABLE] & XGBE_SFP_BASE_CABLE_PASSIVE) {
+ phy_data->sfp_cable = XGBE_SFP_CABLE_PASSIVE;
+ phy_data->sfp_cable_len = sfp_base[XGBE_SFP_BASE_CU_CABLE_LEN];
+ } else {
+ phy_data->sfp_cable = XGBE_SFP_CABLE_ACTIVE;
+ }
+
+ /* Determine the type of SFP */
+ if (sfp_base[XGBE_SFP_BASE_10GBE_CC] & XGBE_SFP_BASE_10GBE_CC_SR)
+ phy_data->sfp_base = XGBE_SFP_BASE_10000_SR;
+ else if (sfp_base[XGBE_SFP_BASE_10GBE_CC] & XGBE_SFP_BASE_10GBE_CC_LR)
+ phy_data->sfp_base = XGBE_SFP_BASE_10000_LR;
+ else if (sfp_base[XGBE_SFP_BASE_10GBE_CC] & XGBE_SFP_BASE_10GBE_CC_LRM)
+ phy_data->sfp_base = XGBE_SFP_BASE_10000_LRM;
+ else if (sfp_base[XGBE_SFP_BASE_10GBE_CC] & XGBE_SFP_BASE_10GBE_CC_ER)
+ phy_data->sfp_base = XGBE_SFP_BASE_10000_ER;
+ else if (sfp_base[XGBE_SFP_BASE_1GBE_CC] & XGBE_SFP_BASE_1GBE_CC_SX)
+ phy_data->sfp_base = XGBE_SFP_BASE_1000_SX;
+ else if (sfp_base[XGBE_SFP_BASE_1GBE_CC] & XGBE_SFP_BASE_1GBE_CC_LX)
+ phy_data->sfp_base = XGBE_SFP_BASE_1000_LX;
+ else if (sfp_base[XGBE_SFP_BASE_1GBE_CC] & XGBE_SFP_BASE_1GBE_CC_CX)
+ phy_data->sfp_base = XGBE_SFP_BASE_1000_CX;
+ else if (sfp_base[XGBE_SFP_BASE_1GBE_CC] & XGBE_SFP_BASE_1GBE_CC_T)
+ phy_data->sfp_base = XGBE_SFP_BASE_1000_T;
+ else if ((phy_data->sfp_cable == XGBE_SFP_CABLE_PASSIVE) &&
+ xgbe_phy_sfp_bit_rate(sfp_eeprom, XGBE_SFP_SPEED_10000))
+ phy_data->sfp_base = XGBE_SFP_BASE_10000_CR;
+
+ switch (phy_data->sfp_base) {
+ case XGBE_SFP_BASE_1000_T:
+ phy_data->sfp_speed = XGBE_SFP_SPEED_100_1000;
+ break;
+ case XGBE_SFP_BASE_1000_SX:
+ case XGBE_SFP_BASE_1000_LX:
+ case XGBE_SFP_BASE_1000_CX:
+ phy_data->sfp_speed = XGBE_SFP_SPEED_1000;
+ break;
+ case XGBE_SFP_BASE_10000_SR:
+ case XGBE_SFP_BASE_10000_LR:
+ case XGBE_SFP_BASE_10000_LRM:
+ case XGBE_SFP_BASE_10000_ER:
+ case XGBE_SFP_BASE_10000_CR:
+ phy_data->sfp_speed = XGBE_SFP_SPEED_10000;
+ break;
+ default:
+ break;
+ }
+}
+
+static void xgbe_phy_sfp_eeprom_info(struct xgbe_prv_data *pdata,
+ struct xgbe_sfp_eeprom *sfp_eeprom)
+{
+ struct xgbe_sfp_ascii sfp_ascii;
+ char *sfp_data = (char *)&sfp_ascii;
+
+ netif_dbg(pdata, drv, pdata->netdev, "SFP detected:\n");
+ memcpy(sfp_data, &sfp_eeprom->base[XGBE_SFP_BASE_VENDOR_NAME],
+ XGBE_SFP_BASE_VENDOR_NAME_LEN);
+ sfp_data[XGBE_SFP_BASE_VENDOR_NAME_LEN] = '\0';
+ netif_dbg(pdata, drv, pdata->netdev, " vendor: %s\n",
+ sfp_data);
+
+ memcpy(sfp_data, &sfp_eeprom->base[XGBE_SFP_BASE_VENDOR_PN],
+ XGBE_SFP_BASE_VENDOR_PN_LEN);
+ sfp_data[XGBE_SFP_BASE_VENDOR_PN_LEN] = '\0';
+ netif_dbg(pdata, drv, pdata->netdev, " part number: %s\n",
+ sfp_data);
+
+ memcpy(sfp_data, &sfp_eeprom->base[XGBE_SFP_BASE_VENDOR_REV],
+ XGBE_SFP_BASE_VENDOR_REV_LEN);
+ sfp_data[XGBE_SFP_BASE_VENDOR_REV_LEN] = '\0';
+ netif_dbg(pdata, drv, pdata->netdev, " revision level: %s\n",
+ sfp_data);
+
+ memcpy(sfp_data, &sfp_eeprom->extd[XGBE_SFP_BASE_VENDOR_SN],
+ XGBE_SFP_BASE_VENDOR_SN_LEN);
+ sfp_data[XGBE_SFP_BASE_VENDOR_SN_LEN] = '\0';
+ netif_dbg(pdata, drv, pdata->netdev, " serial number: %s\n",
+ sfp_data);
+}
+
+static bool xgbe_phy_sfp_verify_eeprom(u8 cc_in, u8 *buf, unsigned int len)
+{
+ u8 cc;
+
+ for (cc = 0; len; buf++, len--)
+ cc += *buf;
+
+ return (cc == cc_in) ? true : false;
+}
+
+static int xgbe_phy_sfp_read_eeprom(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ struct xgbe_sfp_eeprom sfp_eeprom;
+ u8 eeprom_addr;
+ int ret;
+
+ ret = xgbe_phy_sfp_get_mux(pdata);
+ if (ret) {
+ netdev_err(pdata->netdev, "I2C error setting SFP MUX\n");
+ return ret;
+ }
+
+ /* Read the SFP serial ID eeprom */
+ eeprom_addr = 0;
+ ret = xgbe_phy_i2c_read(pdata, XGBE_SFP_SERIAL_ID_ADDRESS,
+ &eeprom_addr, sizeof(eeprom_addr),
+ &sfp_eeprom, sizeof(sfp_eeprom));
+ if (ret) {
+ netdev_err(pdata->netdev, "I2C error reading SFP EEPROM\n");
+ goto put;
+ }
+
+ /* Validate the contents read */
+ if (!xgbe_phy_sfp_verify_eeprom(sfp_eeprom.base[XGBE_SFP_BASE_CC],
+ sfp_eeprom.base,
+ sizeof(sfp_eeprom.base) - 1)) {
+ ret = -EINVAL;
+ goto put;
+ }
+
+ if (!xgbe_phy_sfp_verify_eeprom(sfp_eeprom.extd[XGBE_SFP_EXTD_CC],
+ sfp_eeprom.extd,
+ sizeof(sfp_eeprom.extd) - 1)) {
+ ret = -EINVAL;
+ goto put;
+ }
+
+ /* Check for an added or changed SFP */
+ if (memcmp(&phy_data->sfp_eeprom, &sfp_eeprom, sizeof(sfp_eeprom))) {
+ phy_data->sfp_changed = 1;
+
+ if (netif_msg_drv(pdata))
+ xgbe_phy_sfp_eeprom_info(pdata, &sfp_eeprom);
+
+ memcpy(&phy_data->sfp_eeprom, &sfp_eeprom, sizeof(sfp_eeprom));
+
+ if (sfp_eeprom.extd[XGBE_SFP_EXTD_SFF_8472]) {
+ u8 diag_type = sfp_eeprom.extd[XGBE_SFP_EXTD_DIAG];
+
+ if (!(diag_type & XGBE_SFP_EXTD_DIAG_ADDR_CHANGE))
+ phy_data->sfp_diags = 1;
+ }
+
+ xgbe_phy_free_phy_device(pdata);
+ } else {
+ phy_data->sfp_changed = 0;
+ }
+
+put:
+ xgbe_phy_sfp_put_mux(pdata);
+
+ return ret;
+}
+
+static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int gpio_input;
+ u8 gpio_reg, gpio_ports[2];
+ int ret;
+
+ /* Read the input port registers */
+ gpio_reg = 0;
+ ret = xgbe_phy_i2c_read(pdata, phy_data->sfp_gpio_address,
+ &gpio_reg, sizeof(gpio_reg),
+ gpio_ports, sizeof(gpio_ports));
+ if (ret) {
+ netdev_err(pdata->netdev, "I2C error reading SFP GPIOs\n");
+ return;
+ }
+
+ gpio_input = (gpio_ports[1] << 8) | gpio_ports[0];
+
+ if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT) {
+ /* No GPIO, just assume the module is present for now */
+ phy_data->sfp_mod_absent = 0;
+ } else {
+ if (!(gpio_input & (1 << phy_data->sfp_gpio_mod_absent)))
+ phy_data->sfp_mod_absent = 0;
+ }
+
+ if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS) &&
+ (gpio_input & (1 << phy_data->sfp_gpio_rx_los)))
+ phy_data->sfp_rx_los = 1;
+
+ if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT) &&
+ (gpio_input & (1 << phy_data->sfp_gpio_tx_fault)))
+ phy_data->sfp_tx_fault = 1;
+}
+
+static void xgbe_phy_sfp_mod_absent(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ xgbe_phy_free_phy_device(pdata);
+
+ phy_data->sfp_mod_absent = 1;
+ phy_data->sfp_phy_avail = 0;
+ memset(&phy_data->sfp_eeprom, 0, sizeof(phy_data->sfp_eeprom));
+}
+
+static void xgbe_phy_sfp_reset(struct xgbe_phy_data *phy_data)
+{
+ phy_data->sfp_rx_los = 0;
+ phy_data->sfp_tx_fault = 0;
+ phy_data->sfp_mod_absent = 1;
+ phy_data->sfp_diags = 0;
+ phy_data->sfp_base = XGBE_SFP_BASE_UNKNOWN;
+ phy_data->sfp_cable = XGBE_SFP_CABLE_UNKNOWN;
+ phy_data->sfp_speed = XGBE_SFP_SPEED_UNKNOWN;
+}
+
+static void xgbe_phy_sfp_detect(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ int ret;
+
+ /* Reset the SFP signals and info */
+ xgbe_phy_sfp_reset(phy_data);
+
+ ret = xgbe_phy_get_comm_ownership(pdata);
+ if (ret)
+ return;
+
+ /* Read the SFP signals and check for module presence */
+ xgbe_phy_sfp_signals(pdata);
+ if (phy_data->sfp_mod_absent) {
+ xgbe_phy_sfp_mod_absent(pdata);
+ goto put;
+ }
+
+ ret = xgbe_phy_sfp_read_eeprom(pdata);
+ if (ret) {
+ /* Treat any error as if there isn't an SFP plugged in */
+ xgbe_phy_sfp_reset(phy_data);
+ xgbe_phy_sfp_mod_absent(pdata);
+ goto put;
+ }
+
+ xgbe_phy_sfp_parse_eeprom(pdata);
+
+ xgbe_phy_sfp_external_phy(pdata);
+
+put:
+ xgbe_phy_sfp_phy_settings(pdata);
+
+ xgbe_phy_put_comm_ownership(pdata);
+}
+
+static void xgbe_phy_phydev_flowctrl(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ u16 lcl_adv = 0, rmt_adv = 0;
+ u8 fc;
+
+ pdata->phy.tx_pause = 0;
+ pdata->phy.rx_pause = 0;
+
+ if (!phy_data->phydev)
+ return;
+
+ if (phy_data->phydev->advertising & ADVERTISED_Pause)
+ lcl_adv |= ADVERTISE_PAUSE_CAP;
+ if (phy_data->phydev->advertising & ADVERTISED_Asym_Pause)
+ lcl_adv |= ADVERTISE_PAUSE_ASYM;
+
+ if (phy_data->phydev->pause) {
+ pdata->phy.lp_advertising |= ADVERTISED_Pause;
+ rmt_adv |= LPA_PAUSE_CAP;
+ }
+ if (phy_data->phydev->asym_pause) {
+ pdata->phy.lp_advertising |= ADVERTISED_Asym_Pause;
+ rmt_adv |= LPA_PAUSE_ASYM;
+ }
+
+ fc = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv);
+ if (fc & FLOW_CTRL_TX)
+ pdata->phy.tx_pause = 1;
+ if (fc & FLOW_CTRL_RX)
+ pdata->phy.rx_pause = 1;
+}
+
+static enum xgbe_mode xgbe_phy_an37_sgmii_outcome(struct xgbe_prv_data *pdata)
+{
+ enum xgbe_mode mode;
+
+ pdata->phy.lp_advertising |= ADVERTISED_Autoneg;
+ pdata->phy.lp_advertising |= ADVERTISED_TP;
+
+ /* Use external PHY to determine flow control */
+ if (pdata->phy.pause_autoneg)
+ xgbe_phy_phydev_flowctrl(pdata);
+
+ switch (pdata->an_status & XGBE_SGMII_AN_LINK_SPEED) {
+ case XGBE_SGMII_AN_LINK_SPEED_100:
+ if (pdata->an_status & XGBE_SGMII_AN_LINK_DUPLEX) {
+ pdata->phy.lp_advertising |= ADVERTISED_100baseT_Full;
+ mode = XGBE_MODE_SGMII_100;
+ } else {
+ /* Half-duplex not supported */
+ pdata->phy.lp_advertising |= ADVERTISED_100baseT_Half;
+ mode = XGBE_MODE_UNKNOWN;
+ }
+ break;
+ case XGBE_SGMII_AN_LINK_SPEED_1000:
+ if (pdata->an_status & XGBE_SGMII_AN_LINK_DUPLEX) {
+ pdata->phy.lp_advertising |= ADVERTISED_1000baseT_Full;
+ mode = XGBE_MODE_SGMII_1000;
+ } else {
+ /* Half-duplex not supported */
+ pdata->phy.lp_advertising |= ADVERTISED_1000baseT_Half;
+ mode = XGBE_MODE_UNKNOWN;
+ }
+ break;
+ default:
+ mode = XGBE_MODE_UNKNOWN;
+ }
+
+ return mode;
+}
+
+static enum xgbe_mode xgbe_phy_an37_outcome(struct xgbe_prv_data *pdata)
+{
+ enum xgbe_mode mode;
+ unsigned int ad_reg, lp_reg;
+
+ pdata->phy.lp_advertising |= ADVERTISED_Autoneg;
+ pdata->phy.lp_advertising |= ADVERTISED_FIBRE;
+
+ /* Compare Advertisement and Link Partner register */
+ ad_reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_ADVERTISE);
+ lp_reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_LP_ABILITY);
+ if (lp_reg & 0x100)
+ pdata->phy.lp_advertising |= ADVERTISED_Pause;
+ if (lp_reg & 0x80)
+ pdata->phy.lp_advertising |= ADVERTISED_Asym_Pause;
+
+ if (pdata->phy.pause_autoneg) {
+ /* Set flow control based on auto-negotiation result */
+ pdata->phy.tx_pause = 0;
+ pdata->phy.rx_pause = 0;
+
+ if (ad_reg & lp_reg & 0x100) {
+ pdata->phy.tx_pause = 1;
+ pdata->phy.rx_pause = 1;
+ } else if (ad_reg & lp_reg & 0x80) {
+ if (ad_reg & 0x100)
+ pdata->phy.rx_pause = 1;
+ else if (lp_reg & 0x100)
+ pdata->phy.tx_pause = 1;
+ }
+ }
+
+ if (lp_reg & 0x40)
+ pdata->phy.lp_advertising |= ADVERTISED_1000baseT_Half;
+ if (lp_reg & 0x20)
+ pdata->phy.lp_advertising |= ADVERTISED_1000baseT_Full;
+
+ /* Half duplex is not supported */
+ ad_reg &= lp_reg;
+ mode = (ad_reg & 0x20) ? XGBE_MODE_X : XGBE_MODE_UNKNOWN;
+
+ return mode;
+}
+
+static enum xgbe_mode xgbe_phy_an73_redrv_outcome(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ enum xgbe_mode mode;
+ unsigned int ad_reg, lp_reg;
+
+ pdata->phy.lp_advertising |= ADVERTISED_Autoneg;
+ pdata->phy.lp_advertising |= ADVERTISED_Backplane;
+
+ /* Use external PHY to determine flow control */
+ if (pdata->phy.pause_autoneg)
+ xgbe_phy_phydev_flowctrl(pdata);
+
+ /* Compare Advertisement and Link Partner register 2 */
+ ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1);
+ lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 1);
+ if (lp_reg & 0x80)
+ pdata->phy.lp_advertising |= ADVERTISED_10000baseKR_Full;
+ if (lp_reg & 0x20)
+ pdata->phy.lp_advertising |= ADVERTISED_1000baseKX_Full;
+
+ ad_reg &= lp_reg;
+ if (ad_reg & 0x80) {
+ switch (phy_data->port_mode) {
+ case XGBE_PORT_MODE_BACKPLANE:
+ mode = XGBE_MODE_KR;
+ break;
+ default:
+ mode = XGBE_MODE_SFI;
+ break;
+ }
+ } else if (ad_reg & 0x20) {
+ switch (phy_data->port_mode) {
+ case XGBE_PORT_MODE_BACKPLANE:
+ mode = XGBE_MODE_KX_1000;
+ break;
+ case XGBE_PORT_MODE_1000BASE_X:
+ mode = XGBE_MODE_X;
+ break;
+ case XGBE_PORT_MODE_SFP:
+ switch (phy_data->sfp_base) {
+ case XGBE_SFP_BASE_1000_T:
+ if (phy_data->phydev &&
+ (phy_data->phydev->speed == SPEED_100))
+ mode = XGBE_MODE_SGMII_100;
+ else
+ mode = XGBE_MODE_SGMII_1000;
+ break;
+ case XGBE_SFP_BASE_1000_SX:
+ case XGBE_SFP_BASE_1000_LX:
+ case XGBE_SFP_BASE_1000_CX:
+ default:
+ mode = XGBE_MODE_X;
+ break;
+ }
+ break;
+ default:
+ if (phy_data->phydev &&
+ (phy_data->phydev->speed == SPEED_100))
+ mode = XGBE_MODE_SGMII_100;
+ else
+ mode = XGBE_MODE_SGMII_1000;
+ break;
+ }
+ } else {
+ mode = XGBE_MODE_UNKNOWN;
+ }
+
+ /* Compare Advertisement and Link Partner register 3 */
+ ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2);
+ lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 2);
+ if (lp_reg & 0xc000)
+ pdata->phy.lp_advertising |= ADVERTISED_10000baseR_FEC;
+
+ return mode;
+}
+
+static enum xgbe_mode xgbe_phy_an73_outcome(struct xgbe_prv_data *pdata)
+{
+ enum xgbe_mode mode;
+ unsigned int ad_reg, lp_reg;
+
+ pdata->phy.lp_advertising |= ADVERTISED_Autoneg;
+ pdata->phy.lp_advertising |= ADVERTISED_Backplane;
+
+ /* Compare Advertisement and Link Partner register 1 */
+ ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE);
+ lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA);
+ if (lp_reg & 0x400)
+ pdata->phy.lp_advertising |= ADVERTISED_Pause;
+ if (lp_reg & 0x800)
+ pdata->phy.lp_advertising |= ADVERTISED_Asym_Pause;
+
+ if (pdata->phy.pause_autoneg) {
+ /* Set flow control based on auto-negotiation result */
+ pdata->phy.tx_pause = 0;
+ pdata->phy.rx_pause = 0;
+
+ if (ad_reg & lp_reg & 0x400) {
+ pdata->phy.tx_pause = 1;
+ pdata->phy.rx_pause = 1;
+ } else if (ad_reg & lp_reg & 0x800) {
+ if (ad_reg & 0x400)
+ pdata->phy.rx_pause = 1;
+ else if (lp_reg & 0x400)
+ pdata->phy.tx_pause = 1;
+ }
+ }
+
+ /* Compare Advertisement and Link Partner register 2 */
+ ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1);
+ lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 1);
+ if (lp_reg & 0x80)
+ pdata->phy.lp_advertising |= ADVERTISED_10000baseKR_Full;
+ if (lp_reg & 0x20)
+ pdata->phy.lp_advertising |= ADVERTISED_1000baseKX_Full;
+
+ ad_reg &= lp_reg;
+ if (ad_reg & 0x80)
+ mode = XGBE_MODE_KR;
+ else if (ad_reg & 0x20)
+ mode = XGBE_MODE_KX_1000;
+ else
+ mode = XGBE_MODE_UNKNOWN;
+
+ /* Compare Advertisement and Link Partner register 3 */
+ ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2);
+ lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 2);
+ if (lp_reg & 0xc000)
+ pdata->phy.lp_advertising |= ADVERTISED_10000baseR_FEC;
+
+ return mode;
+}
+
+static enum xgbe_mode xgbe_phy_an_outcome(struct xgbe_prv_data *pdata)
+{
+ switch (pdata->an_mode) {
+ case XGBE_AN_MODE_CL73:
+ return xgbe_phy_an73_outcome(pdata);
+ case XGBE_AN_MODE_CL73_REDRV:
+ return xgbe_phy_an73_redrv_outcome(pdata);
+ case XGBE_AN_MODE_CL37:
+ return xgbe_phy_an37_outcome(pdata);
+ case XGBE_AN_MODE_CL37_SGMII:
+ return xgbe_phy_an37_sgmii_outcome(pdata);
+ default:
+ return XGBE_MODE_UNKNOWN;
+ }
+}
+
+static unsigned int xgbe_phy_an_advertising(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int advertising;
+
+ /* Without a re-driver, just return current advertising */
+ if (!phy_data->redrv)
+ return pdata->phy.advertising;
+
+ /* With the KR re-driver we need to advertise a single speed */
+ advertising = pdata->phy.advertising;
+ advertising &= ~ADVERTISED_1000baseKX_Full;
+ advertising &= ~ADVERTISED_10000baseKR_Full;
+
+ switch (phy_data->port_mode) {
+ case XGBE_PORT_MODE_BACKPLANE:
+ advertising |= ADVERTISED_10000baseKR_Full;
+ break;
+ case XGBE_PORT_MODE_BACKPLANE_2500:
+ advertising |= ADVERTISED_1000baseKX_Full;
+ break;
+ case XGBE_PORT_MODE_1000BASE_T:
+ case XGBE_PORT_MODE_1000BASE_X:
+ case XGBE_PORT_MODE_NBASE_T:
+ advertising |= ADVERTISED_1000baseKX_Full;
+ break;
+ case XGBE_PORT_MODE_10GBASE_T:
+ if (phy_data->phydev &&
+ (phy_data->phydev->speed == SPEED_10000))
+ advertising |= ADVERTISED_10000baseKR_Full;
+ else
+ advertising |= ADVERTISED_1000baseKX_Full;
+ break;
+ case XGBE_PORT_MODE_10GBASE_R:
+ advertising |= ADVERTISED_10000baseKR_Full;
+ break;
+ case XGBE_PORT_MODE_SFP:
+ switch (phy_data->sfp_base) {
+ case XGBE_SFP_BASE_1000_T:
+ case XGBE_SFP_BASE_1000_SX:
+ case XGBE_SFP_BASE_1000_LX:
+ case XGBE_SFP_BASE_1000_CX:
+ advertising |= ADVERTISED_1000baseKX_Full;
+ break;
+ default:
+ advertising |= ADVERTISED_10000baseKR_Full;
+ break;
+ }
+ break;
+ default:
+ advertising |= ADVERTISED_10000baseKR_Full;
+ break;
+ }
+
+ return advertising;
+}
+
+static int xgbe_phy_an_config(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ int ret;
+
+ ret = xgbe_phy_find_phy_device(pdata);
+ if (ret)
+ return ret;
+
+ if (!phy_data->phydev)
+ return 0;
+
+ phy_data->phydev->autoneg = pdata->phy.autoneg;
+ phy_data->phydev->advertising = phy_data->phydev->supported &
+ pdata->phy.advertising;
+
+ if (pdata->phy.autoneg != AUTONEG_ENABLE) {
+ phy_data->phydev->speed = pdata->phy.speed;
+ phy_data->phydev->duplex = pdata->phy.duplex;
+ }
+
+ ret = phy_start_aneg(phy_data->phydev);
+
+ return ret;
+}
+
+static enum xgbe_an_mode xgbe_phy_an_sfp_mode(struct xgbe_phy_data *phy_data)
+{
+ switch (phy_data->sfp_base) {
+ case XGBE_SFP_BASE_1000_T:
+ return XGBE_AN_MODE_CL37_SGMII;
+ case XGBE_SFP_BASE_1000_SX:
+ case XGBE_SFP_BASE_1000_LX:
+ case XGBE_SFP_BASE_1000_CX:
+ return XGBE_AN_MODE_CL37;
+ default:
+ return XGBE_AN_MODE_NONE;
+ }
+}
+
+static enum xgbe_an_mode xgbe_phy_an_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ /* A KR re-driver will always require CL73 AN */
+ if (phy_data->redrv)
+ return XGBE_AN_MODE_CL73_REDRV;
+
+ switch (phy_data->port_mode) {
+ case XGBE_PORT_MODE_BACKPLANE:
+ return XGBE_AN_MODE_CL73;
+ case XGBE_PORT_MODE_BACKPLANE_2500:
+ return XGBE_AN_MODE_NONE;
+ case XGBE_PORT_MODE_1000BASE_T:
+ return XGBE_AN_MODE_CL37_SGMII;
+ case XGBE_PORT_MODE_1000BASE_X:
+ return XGBE_AN_MODE_CL37;
+ case XGBE_PORT_MODE_NBASE_T:
+ return XGBE_AN_MODE_CL37_SGMII;
+ case XGBE_PORT_MODE_10GBASE_T:
+ return XGBE_AN_MODE_CL73;
+ case XGBE_PORT_MODE_10GBASE_R:
+ return XGBE_AN_MODE_NONE;
+ case XGBE_PORT_MODE_SFP:
+ return xgbe_phy_an_sfp_mode(phy_data);
+ default:
+ return XGBE_AN_MODE_NONE;
+ }
+}
+
+static int xgbe_phy_set_redrv_mode_mdio(struct xgbe_prv_data *pdata,
+ enum xgbe_phy_redrv_mode mode)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ u16 redrv_reg, redrv_val;
+
+ redrv_reg = XGBE_PHY_REDRV_MODE_REG + (phy_data->redrv_lane * 0x1000);
+ redrv_val = (u16)mode;
+
+ return pdata->hw_if.write_ext_mii_regs(pdata, phy_data->redrv_addr,
+ redrv_reg, redrv_val);
+}
+
+static int xgbe_phy_set_redrv_mode_i2c(struct xgbe_prv_data *pdata,
+ enum xgbe_phy_redrv_mode mode)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int redrv_reg;
+ int ret;
+
+ /* Calculate the register to write */
+ redrv_reg = XGBE_PHY_REDRV_MODE_REG + (phy_data->redrv_lane * 0x1000);
+
+ ret = xgbe_phy_redrv_write(pdata, redrv_reg, mode);
+
+ return ret;
+}
+
+static void xgbe_phy_set_redrv_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ enum xgbe_phy_redrv_mode mode;
+ int ret;
+
+ if (!phy_data->redrv)
+ return;
+
+ mode = XGBE_PHY_REDRV_MODE_CX;
+ if ((phy_data->port_mode == XGBE_PORT_MODE_SFP) &&
+ (phy_data->sfp_base != XGBE_SFP_BASE_1000_CX) &&
+ (phy_data->sfp_base != XGBE_SFP_BASE_10000_CR))
+ mode = XGBE_PHY_REDRV_MODE_SR;
+
+ ret = xgbe_phy_get_comm_ownership(pdata);
+ if (ret)
+ return;
+
+ if (phy_data->redrv_if)
+ xgbe_phy_set_redrv_mode_i2c(pdata, mode);
+ else
+ xgbe_phy_set_redrv_mode_mdio(pdata, mode);
+
+ xgbe_phy_put_comm_ownership(pdata);
+}
+
+static void xgbe_phy_start_ratechange(struct xgbe_prv_data *pdata)
+{
+ if (!XP_IOREAD_BITS(pdata, XP_DRIVER_INT_RO, STATUS))
+ return;
+
+ /* Log if a previous command did not complete */
+ netif_dbg(pdata, link, pdata->netdev,
+ "firmware mailbox not ready for command\n");
+}
+
+static void xgbe_phy_complete_ratechange(struct xgbe_prv_data *pdata)
+{
+ unsigned int wait;
+
+ /* Wait for command to complete */
+ wait = XGBE_RATECHANGE_COUNT;
+ while (wait--) {
+ if (!XP_IOREAD_BITS(pdata, XP_DRIVER_INT_RO, STATUS))
+ return;
+
+ usleep_range(1000, 2000);
+ }
+
+ netif_dbg(pdata, link, pdata->netdev,
+ "firmware mailbox command did not complete\n");
+}
+
+static void xgbe_phy_rrc(struct xgbe_prv_data *pdata)
+{
+ unsigned int s0;
+
+ xgbe_phy_start_ratechange(pdata);
+
+ /* Receiver Reset Cycle */
+ s0 = 0;
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, COMMAND, 5);
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, SUB_COMMAND, 0);
+
+ /* Call FW to make the change */
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_0, s0);
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_1, 0);
+ XP_IOWRITE_BITS(pdata, XP_DRIVER_INT_REQ, REQUEST, 1);
+
+ xgbe_phy_complete_ratechange(pdata);
+
+ netif_dbg(pdata, link, pdata->netdev, "receiver reset complete\n");
+}
+
+static void xgbe_phy_power_off(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ xgbe_phy_start_ratechange(pdata);
+
+ /* Call FW to make the change */
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_0, 0);
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_1, 0);
+ XP_IOWRITE_BITS(pdata, XP_DRIVER_INT_REQ, REQUEST, 1);
+
+ xgbe_phy_complete_ratechange(pdata);
+
+ phy_data->cur_mode = XGBE_MODE_UNKNOWN;
+
+ netif_dbg(pdata, link, pdata->netdev, "phy powered off\n");
+}
+
+static void xgbe_phy_sfi_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int s0;
+
+ xgbe_phy_set_redrv_mode(pdata);
+
+ xgbe_phy_start_ratechange(pdata);
+
+ /* 10G/SFI */
+ s0 = 0;
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, COMMAND, 3);
+ if (phy_data->sfp_cable != XGBE_SFP_CABLE_PASSIVE) {
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, SUB_COMMAND, 0);
+ } else {
+ if (phy_data->sfp_cable_len <= 1)
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, SUB_COMMAND, 1);
+ else if (phy_data->sfp_cable_len <= 3)
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, SUB_COMMAND, 2);
+ else
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, SUB_COMMAND, 3);
+ }
+
+ /* Call FW to make the change */
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_0, s0);
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_1, 0);
+ XP_IOWRITE_BITS(pdata, XP_DRIVER_INT_REQ, REQUEST, 1);
+
+ xgbe_phy_complete_ratechange(pdata);
+
+ phy_data->cur_mode = XGBE_MODE_SFI;
+
+ netif_dbg(pdata, link, pdata->netdev, "10GbE SFI mode set\n");
+}
+
+static void xgbe_phy_x_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int s0;
+
+ xgbe_phy_set_redrv_mode(pdata);
+
+ xgbe_phy_start_ratechange(pdata);
+
+ /* 1G/X */
+ s0 = 0;
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, COMMAND, 1);
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, SUB_COMMAND, 3);
+
+ /* Call FW to make the change */
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_0, s0);
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_1, 0);
+ XP_IOWRITE_BITS(pdata, XP_DRIVER_INT_REQ, REQUEST, 1);
+
+ xgbe_phy_complete_ratechange(pdata);
+
+ phy_data->cur_mode = XGBE_MODE_X;
+
+ netif_dbg(pdata, link, pdata->netdev, "1GbE X mode set\n");
+}
+
+static void xgbe_phy_sgmii_1000_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int s0;
+
+ xgbe_phy_set_redrv_mode(pdata);
+
+ xgbe_phy_start_ratechange(pdata);
+
+ /* 1G/SGMII */
+ s0 = 0;
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, COMMAND, 1);
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, SUB_COMMAND, 2);
+
+ /* Call FW to make the change */
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_0, s0);
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_1, 0);
+ XP_IOWRITE_BITS(pdata, XP_DRIVER_INT_REQ, REQUEST, 1);
+
+ xgbe_phy_complete_ratechange(pdata);
+
+ phy_data->cur_mode = XGBE_MODE_SGMII_1000;
+
+ netif_dbg(pdata, link, pdata->netdev, "1GbE SGMII mode set\n");
+}
+
+static void xgbe_phy_sgmii_100_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int s0;
+
+ xgbe_phy_set_redrv_mode(pdata);
+
+ xgbe_phy_start_ratechange(pdata);
+
+ /* 1G/SGMII */
+ s0 = 0;
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, COMMAND, 1);
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, SUB_COMMAND, 1);
+
+ /* Call FW to make the change */
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_0, s0);
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_1, 0);
+ XP_IOWRITE_BITS(pdata, XP_DRIVER_INT_REQ, REQUEST, 1);
+
+ xgbe_phy_complete_ratechange(pdata);
+
+ phy_data->cur_mode = XGBE_MODE_SGMII_100;
+
+ netif_dbg(pdata, link, pdata->netdev, "100MbE SGMII mode set\n");
+}
+
+static void xgbe_phy_kr_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int s0;
+
+ xgbe_phy_set_redrv_mode(pdata);
+
+ xgbe_phy_start_ratechange(pdata);
+
+ /* 10G/KR */
+ s0 = 0;
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, COMMAND, 4);
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, SUB_COMMAND, 0);
+
+ /* Call FW to make the change */
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_0, s0);
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_1, 0);
+ XP_IOWRITE_BITS(pdata, XP_DRIVER_INT_REQ, REQUEST, 1);
+
+ xgbe_phy_complete_ratechange(pdata);
+
+ phy_data->cur_mode = XGBE_MODE_KR;
+
+ netif_dbg(pdata, link, pdata->netdev, "10GbE KR mode set\n");
+}
+
+static void xgbe_phy_kx_2500_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int s0;
+
+ xgbe_phy_set_redrv_mode(pdata);
+
+ xgbe_phy_start_ratechange(pdata);
+
+ /* 2.5G/KX */
+ s0 = 0;
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, COMMAND, 2);
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, SUB_COMMAND, 0);
+
+ /* Call FW to make the change */
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_0, s0);
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_1, 0);
+ XP_IOWRITE_BITS(pdata, XP_DRIVER_INT_REQ, REQUEST, 1);
+
+ xgbe_phy_complete_ratechange(pdata);
+
+ phy_data->cur_mode = XGBE_MODE_KX_2500;
+
+ netif_dbg(pdata, link, pdata->netdev, "2.5GbE KX mode set\n");
+}
+
+static void xgbe_phy_kx_1000_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int s0;
+
+ xgbe_phy_set_redrv_mode(pdata);
+
+ xgbe_phy_start_ratechange(pdata);
+
+ /* 1G/KX */
+ s0 = 0;
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, COMMAND, 1);
+ XP_SET_BITS(s0, XP_DRIVER_SCRATCH_0, SUB_COMMAND, 3);
+
+ /* Call FW to make the change */
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_0, s0);
+ XP_IOWRITE(pdata, XP_DRIVER_SCRATCH_1, 0);
+ XP_IOWRITE_BITS(pdata, XP_DRIVER_INT_REQ, REQUEST, 1);
+
+ xgbe_phy_complete_ratechange(pdata);
+
+ phy_data->cur_mode = XGBE_MODE_KX_1000;
+
+ netif_dbg(pdata, link, pdata->netdev, "1GbE KX mode set\n");
+}
+
+static enum xgbe_mode xgbe_phy_cur_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ return phy_data->cur_mode;
+}
+
+static enum xgbe_mode xgbe_phy_switch_baset_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ /* No switching if not 10GBase-T */
+ if (phy_data->port_mode != XGBE_PORT_MODE_10GBASE_T)
+ return xgbe_phy_cur_mode(pdata);
+
+ switch (xgbe_phy_cur_mode(pdata)) {
+ case XGBE_MODE_SGMII_100:
+ case XGBE_MODE_SGMII_1000:
+ return XGBE_MODE_KR;
+ case XGBE_MODE_KR:
+ default:
+ return XGBE_MODE_SGMII_1000;
+ }
+}
+
+static enum xgbe_mode xgbe_phy_switch_bp_2500_mode(struct xgbe_prv_data *pdata)
+{
+ return XGBE_MODE_KX_2500;
+}
+
+static enum xgbe_mode xgbe_phy_switch_bp_mode(struct xgbe_prv_data *pdata)
+{
+ /* If we are in KR switch to KX, and vice-versa */
+ switch (xgbe_phy_cur_mode(pdata)) {
+ case XGBE_MODE_KX_1000:
+ return XGBE_MODE_KR;
+ case XGBE_MODE_KR:
+ default:
+ return XGBE_MODE_KX_1000;
+ }
+}
+
+static enum xgbe_mode xgbe_phy_switch_mode(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (phy_data->port_mode) {
+ case XGBE_PORT_MODE_BACKPLANE:
+ return xgbe_phy_switch_bp_mode(pdata);
+ case XGBE_PORT_MODE_BACKPLANE_2500:
+ return xgbe_phy_switch_bp_2500_mode(pdata);
+ case XGBE_PORT_MODE_1000BASE_T:
+ case XGBE_PORT_MODE_NBASE_T:
+ case XGBE_PORT_MODE_10GBASE_T:
+ return xgbe_phy_switch_baset_mode(pdata);
+ case XGBE_PORT_MODE_1000BASE_X:
+ case XGBE_PORT_MODE_10GBASE_R:
+ case XGBE_PORT_MODE_SFP:
+ /* No switching, so just return current mode */
+ return xgbe_phy_cur_mode(pdata);
+ default:
+ return XGBE_MODE_UNKNOWN;
+ }
+}
+
+static enum xgbe_mode xgbe_phy_get_basex_mode(struct xgbe_phy_data *phy_data,
+ int speed)
+{
+ switch (speed) {
+ case SPEED_1000:
+ return XGBE_MODE_X;
+ case SPEED_10000:
+ return XGBE_MODE_KR;
+ default:
+ return XGBE_MODE_UNKNOWN;
+ }
+}
+
+static enum xgbe_mode xgbe_phy_get_baset_mode(struct xgbe_phy_data *phy_data,
+ int speed)
+{
+ switch (speed) {
+ case SPEED_100:
+ return XGBE_MODE_SGMII_100;
+ case SPEED_1000:
+ return XGBE_MODE_SGMII_1000;
+ case SPEED_10000:
+ return XGBE_MODE_KR;
+ default:
+ return XGBE_MODE_UNKNOWN;
+ }
+}
+
+static enum xgbe_mode xgbe_phy_get_sfp_mode(struct xgbe_phy_data *phy_data,
+ int speed)
+{
+ switch (speed) {
+ case SPEED_100:
+ return XGBE_MODE_SGMII_100;
+ case SPEED_1000:
+ if (phy_data->sfp_base == XGBE_SFP_BASE_1000_T)
+ return XGBE_MODE_SGMII_1000;
+ else
+ return XGBE_MODE_X;
+ case SPEED_10000:
+ case SPEED_UNKNOWN:
+ return XGBE_MODE_SFI;
+ default:
+ return XGBE_MODE_UNKNOWN;
+ }
+}
+
+static enum xgbe_mode xgbe_phy_get_bp_2500_mode(int speed)
+{
+ switch (speed) {
+ case SPEED_2500:
+ return XGBE_MODE_KX_2500;
+ default:
+ return XGBE_MODE_UNKNOWN;
+ }
+}
+
+static enum xgbe_mode xgbe_phy_get_bp_mode(int speed)
+{
+ switch (speed) {
+ case SPEED_1000:
+ return XGBE_MODE_KX_1000;
+ case SPEED_10000:
+ return XGBE_MODE_KR;
+ default:
+ return XGBE_MODE_UNKNOWN;
+ }
+}
+
+static enum xgbe_mode xgbe_phy_get_mode(struct xgbe_prv_data *pdata,
+ int speed)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (phy_data->port_mode) {
+ case XGBE_PORT_MODE_BACKPLANE:
+ return xgbe_phy_get_bp_mode(speed);
+ case XGBE_PORT_MODE_BACKPLANE_2500:
+ return xgbe_phy_get_bp_2500_mode(speed);
+ case XGBE_PORT_MODE_1000BASE_T:
+ case XGBE_PORT_MODE_NBASE_T:
+ case XGBE_PORT_MODE_10GBASE_T:
+ return xgbe_phy_get_baset_mode(phy_data, speed);
+ case XGBE_PORT_MODE_1000BASE_X:
+ case XGBE_PORT_MODE_10GBASE_R:
+ return xgbe_phy_get_basex_mode(phy_data, speed);
+ case XGBE_PORT_MODE_SFP:
+ return xgbe_phy_get_sfp_mode(phy_data, speed);
+ default:
+ return XGBE_MODE_UNKNOWN;
+ }
+}
+
+static void xgbe_phy_set_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode)
+{
+ switch (mode) {
+ case XGBE_MODE_KX_1000:
+ xgbe_phy_kx_1000_mode(pdata);
+ break;
+ case XGBE_MODE_KX_2500:
+ xgbe_phy_kx_2500_mode(pdata);
+ break;
+ case XGBE_MODE_KR:
+ xgbe_phy_kr_mode(pdata);
+ break;
+ case XGBE_MODE_SGMII_100:
+ xgbe_phy_sgmii_100_mode(pdata);
+ break;
+ case XGBE_MODE_SGMII_1000:
+ xgbe_phy_sgmii_1000_mode(pdata);
+ break;
+ case XGBE_MODE_X:
+ xgbe_phy_x_mode(pdata);
+ break;
+ case XGBE_MODE_SFI:
+ xgbe_phy_sfi_mode(pdata);
+ break;
+ default:
+ break;
+ }
+}
+
+static bool xgbe_phy_check_mode(struct xgbe_prv_data *pdata,
+ enum xgbe_mode mode, u32 advert)
+{
+ if (pdata->phy.autoneg == AUTONEG_ENABLE) {
+ if (pdata->phy.advertising & advert)
+ return true;
+ } else {
+ enum xgbe_mode cur_mode;
+
+ cur_mode = xgbe_phy_get_mode(pdata, pdata->phy.speed);
+ if (cur_mode == mode)
+ return true;
+ }
+
+ return false;
+}
+
+static bool xgbe_phy_use_basex_mode(struct xgbe_prv_data *pdata,
+ enum xgbe_mode mode)
+{
+ switch (mode) {
+ case XGBE_MODE_X:
+ return xgbe_phy_check_mode(pdata, mode,
+ ADVERTISED_1000baseT_Full);
+ case XGBE_MODE_KR:
+ return xgbe_phy_check_mode(pdata, mode,
+ ADVERTISED_10000baseT_Full);
+ default:
+ return false;
+ }
+}
+
+static bool xgbe_phy_use_baset_mode(struct xgbe_prv_data *pdata,
+ enum xgbe_mode mode)
+{
+ switch (mode) {
+ case XGBE_MODE_SGMII_100:
+ return xgbe_phy_check_mode(pdata, mode,
+ ADVERTISED_100baseT_Full);
+ case XGBE_MODE_SGMII_1000:
+ return xgbe_phy_check_mode(pdata, mode,
+ ADVERTISED_1000baseT_Full);
+ case XGBE_MODE_KR:
+ return xgbe_phy_check_mode(pdata, mode,
+ ADVERTISED_10000baseT_Full);
+ default:
+ return false;
+ }
+}
+
+static bool xgbe_phy_use_sfp_mode(struct xgbe_prv_data *pdata,
+ enum xgbe_mode mode)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (mode) {
+ case XGBE_MODE_X:
+ if (phy_data->sfp_base == XGBE_SFP_BASE_1000_T)
+ return false;
+ return xgbe_phy_check_mode(pdata, mode,
+ ADVERTISED_1000baseT_Full);
+ case XGBE_MODE_SGMII_100:
+ if (phy_data->sfp_base != XGBE_SFP_BASE_1000_T)
+ return false;
+ return xgbe_phy_check_mode(pdata, mode,
+ ADVERTISED_100baseT_Full);
+ case XGBE_MODE_SGMII_1000:
+ if (phy_data->sfp_base != XGBE_SFP_BASE_1000_T)
+ return false;
+ return xgbe_phy_check_mode(pdata, mode,
+ ADVERTISED_1000baseT_Full);
+ case XGBE_MODE_SFI:
+ return xgbe_phy_check_mode(pdata, mode,
+ ADVERTISED_10000baseT_Full);
+ default:
+ return false;
+ }
+}
+
+static bool xgbe_phy_use_bp_2500_mode(struct xgbe_prv_data *pdata,
+ enum xgbe_mode mode)
+{
+ switch (mode) {
+ case XGBE_MODE_KX_2500:
+ return xgbe_phy_check_mode(pdata, mode,
+ ADVERTISED_2500baseX_Full);
+ default:
+ return false;
+ }
+}
+
+static bool xgbe_phy_use_bp_mode(struct xgbe_prv_data *pdata,
+ enum xgbe_mode mode)
+{
+ switch (mode) {
+ case XGBE_MODE_KX_1000:
+ return xgbe_phy_check_mode(pdata, mode,
+ ADVERTISED_1000baseKX_Full);
+ case XGBE_MODE_KR:
+ return xgbe_phy_check_mode(pdata, mode,
+ ADVERTISED_10000baseKR_Full);
+ default:
+ return false;
+ }
+}
+
+static bool xgbe_phy_use_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (phy_data->port_mode) {
+ case XGBE_PORT_MODE_BACKPLANE:
+ return xgbe_phy_use_bp_mode(pdata, mode);
+ case XGBE_PORT_MODE_BACKPLANE_2500:
+ return xgbe_phy_use_bp_2500_mode(pdata, mode);
+ case XGBE_PORT_MODE_1000BASE_T:
+ case XGBE_PORT_MODE_NBASE_T:
+ case XGBE_PORT_MODE_10GBASE_T:
+ return xgbe_phy_use_baset_mode(pdata, mode);
+ case XGBE_PORT_MODE_1000BASE_X:
+ case XGBE_PORT_MODE_10GBASE_R:
+ return xgbe_phy_use_basex_mode(pdata, mode);
+ case XGBE_PORT_MODE_SFP:
+ return xgbe_phy_use_sfp_mode(pdata, mode);
+ default:
+ return false;
+ }
+}
+
+static bool xgbe_phy_valid_speed_basex_mode(struct xgbe_phy_data *phy_data,
+ int speed)
+{
+ switch (speed) {
+ case SPEED_1000:
+ return (phy_data->port_mode == XGBE_PORT_MODE_1000BASE_X);
+ case SPEED_10000:
+ return (phy_data->port_mode == XGBE_PORT_MODE_10GBASE_R);
+ default:
+ return false;
+ }
+}
+
+static bool xgbe_phy_valid_speed_baset_mode(struct xgbe_phy_data *phy_data,
+ int speed)
+{
+ switch (speed) {
+ case SPEED_100:
+ case SPEED_1000:
+ return true;
+ case SPEED_10000:
+ return (phy_data->port_mode == XGBE_PORT_MODE_10GBASE_T);
+ default:
+ return false;
+ }
+}
+
+static bool xgbe_phy_valid_speed_sfp_mode(struct xgbe_phy_data *phy_data,
+ int speed)
+{
+ switch (speed) {
+ case SPEED_100:
+ return (phy_data->sfp_speed == XGBE_SFP_SPEED_100_1000);
+ case SPEED_1000:
+ return ((phy_data->sfp_speed == XGBE_SFP_SPEED_100_1000) ||
+ (phy_data->sfp_speed == XGBE_SFP_SPEED_1000));
+ case SPEED_10000:
+ return (phy_data->sfp_speed == XGBE_SFP_SPEED_10000);
+ default:
+ return false;
+ }
+}
+
+static bool xgbe_phy_valid_speed_bp_2500_mode(int speed)
+{
+ switch (speed) {
+ case SPEED_2500:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static bool xgbe_phy_valid_speed_bp_mode(int speed)
+{
+ switch (speed) {
+ case SPEED_1000:
+ case SPEED_10000:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static bool xgbe_phy_valid_speed(struct xgbe_prv_data *pdata, int speed)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (phy_data->port_mode) {
+ case XGBE_PORT_MODE_BACKPLANE:
+ return xgbe_phy_valid_speed_bp_mode(speed);
+ case XGBE_PORT_MODE_BACKPLANE_2500:
+ return xgbe_phy_valid_speed_bp_2500_mode(speed);
+ case XGBE_PORT_MODE_1000BASE_T:
+ case XGBE_PORT_MODE_NBASE_T:
+ case XGBE_PORT_MODE_10GBASE_T:
+ return xgbe_phy_valid_speed_baset_mode(phy_data, speed);
+ case XGBE_PORT_MODE_1000BASE_X:
+ case XGBE_PORT_MODE_10GBASE_R:
+ return xgbe_phy_valid_speed_basex_mode(phy_data, speed);
+ case XGBE_PORT_MODE_SFP:
+ return xgbe_phy_valid_speed_sfp_mode(phy_data, speed);
+ default:
+ return false;
+ }
+}
+
+static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int reg;
+ int ret;
+
+ *an_restart = 0;
+
+ if (phy_data->port_mode == XGBE_PORT_MODE_SFP) {
+ /* Check SFP signals */
+ xgbe_phy_sfp_detect(pdata);
+
+ if (phy_data->sfp_changed) {
+ *an_restart = 1;
+ return 0;
+ }
+
+ if (phy_data->sfp_mod_absent || phy_data->sfp_rx_los)
+ return 0;
+ }
+
+ if (phy_data->phydev) {
+ /* Check external PHY */
+ ret = phy_read_status(phy_data->phydev);
+ if (ret < 0)
+ return 0;
+
+ if ((pdata->phy.autoneg == AUTONEG_ENABLE) &&
+ !phy_aneg_done(phy_data->phydev))
+ return 0;
+
+ if (!phy_data->phydev->link)
+ return 0;
+ }
+
+ /* Link status is latched low, so read once to clear
+ * and then read again to get current state
+ */
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+ reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+ if (reg & MDIO_STAT1_LSTATUS)
+ return 1;
+
+ /* No link, attempt a receiver reset cycle */
+ if (phy_data->rrc_count++) {
+ phy_data->rrc_count = 0;
+ xgbe_phy_rrc(pdata);
+ }
+
+ return 0;
+}
+
+static void xgbe_phy_sfp_gpio_setup(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int reg;
+
+ reg = XP_IOREAD(pdata, XP_PROP_3);
+
+ phy_data->sfp_gpio_address = XGBE_GPIO_ADDRESS_PCA9555 +
+ XP_GET_BITS(reg, XP_PROP_3, GPIO_ADDR);
+
+ phy_data->sfp_gpio_mask = XP_GET_BITS(reg, XP_PROP_3, GPIO_MASK);
+
+ phy_data->sfp_gpio_rx_los = XP_GET_BITS(reg, XP_PROP_3,
+ GPIO_RX_LOS);
+ phy_data->sfp_gpio_tx_fault = XP_GET_BITS(reg, XP_PROP_3,
+ GPIO_TX_FAULT);
+ phy_data->sfp_gpio_mod_absent = XP_GET_BITS(reg, XP_PROP_3,
+ GPIO_MOD_ABS);
+ phy_data->sfp_gpio_rate_select = XP_GET_BITS(reg, XP_PROP_3,
+ GPIO_RATE_SELECT);
+
+ if (netif_msg_probe(pdata)) {
+ dev_dbg(pdata->dev, "SFP: gpio_address=%#x\n",
+ phy_data->sfp_gpio_address);
+ dev_dbg(pdata->dev, "SFP: gpio_mask=%#x\n",
+ phy_data->sfp_gpio_mask);
+ dev_dbg(pdata->dev, "SFP: gpio_rx_los=%u\n",
+ phy_data->sfp_gpio_rx_los);
+ dev_dbg(pdata->dev, "SFP: gpio_tx_fault=%u\n",
+ phy_data->sfp_gpio_tx_fault);
+ dev_dbg(pdata->dev, "SFP: gpio_mod_absent=%u\n",
+ phy_data->sfp_gpio_mod_absent);
+ dev_dbg(pdata->dev, "SFP: gpio_rate_select=%u\n",
+ phy_data->sfp_gpio_rate_select);
+ }
+}
+
+static void xgbe_phy_sfp_comm_setup(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int reg, mux_addr_hi, mux_addr_lo;
+
+ reg = XP_IOREAD(pdata, XP_PROP_4);
+
+ mux_addr_hi = XP_GET_BITS(reg, XP_PROP_4, MUX_ADDR_HI);
+ mux_addr_lo = XP_GET_BITS(reg, XP_PROP_4, MUX_ADDR_LO);
+ if (mux_addr_lo == XGBE_SFP_DIRECT)
+ return;
+
+ phy_data->sfp_comm = XGBE_SFP_COMM_PCA9545;
+ phy_data->sfp_mux_address = (mux_addr_hi << 2) + mux_addr_lo;
+ phy_data->sfp_mux_channel = XP_GET_BITS(reg, XP_PROP_4, MUX_CHAN);
+
+ if (netif_msg_probe(pdata)) {
+ dev_dbg(pdata->dev, "SFP: mux_address=%#x\n",
+ phy_data->sfp_mux_address);
+ dev_dbg(pdata->dev, "SFP: mux_channel=%u\n",
+ phy_data->sfp_mux_channel);
+ }
+}
+
+static void xgbe_phy_sfp_setup(struct xgbe_prv_data *pdata)
+{
+ xgbe_phy_sfp_comm_setup(pdata);
+ xgbe_phy_sfp_gpio_setup(pdata);
+}
+
+static int xgbe_phy_int_mdio_reset(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int ret;
+
+ ret = pdata->hw_if.set_gpio(pdata, phy_data->mdio_reset_gpio);
+ if (ret)
+ return ret;
+
+ ret = pdata->hw_if.clr_gpio(pdata, phy_data->mdio_reset_gpio);
+
+ return ret;
+}
+
+static int xgbe_phy_i2c_mdio_reset(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ u8 gpio_reg, gpio_ports[2], gpio_data[3];
+ int ret;
+
+ /* Read the output port registers */
+ gpio_reg = 2;
+ ret = xgbe_phy_i2c_read(pdata, phy_data->mdio_reset_addr,
+ &gpio_reg, sizeof(gpio_reg),
+ gpio_ports, sizeof(gpio_ports));
+ if (ret)
+ return ret;
+
+ /* Prepare to write the GPIO data */
+ gpio_data[0] = 2;
+ gpio_data[1] = gpio_ports[0];
+ gpio_data[2] = gpio_ports[1];
+
+ /* Set the GPIO pin */
+ if (phy_data->mdio_reset_gpio < 8)
+ gpio_data[1] |= (1 << (phy_data->mdio_reset_gpio % 8));
+ else
+ gpio_data[2] |= (1 << (phy_data->mdio_reset_gpio % 8));
+
+ /* Write the output port registers */
+ ret = xgbe_phy_i2c_write(pdata, phy_data->mdio_reset_addr,
+ gpio_data, sizeof(gpio_data));
+ if (ret)
+ return ret;
+
+ /* Clear the GPIO pin */
+ if (phy_data->mdio_reset_gpio < 8)
+ gpio_data[1] &= ~(1 << (phy_data->mdio_reset_gpio % 8));
+ else
+ gpio_data[2] &= ~(1 << (phy_data->mdio_reset_gpio % 8));
+
+ /* Write the output port registers */
+ ret = xgbe_phy_i2c_write(pdata, phy_data->mdio_reset_addr,
+ gpio_data, sizeof(gpio_data));
+
+ return ret;
+}
+
+static int xgbe_phy_mdio_reset(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ int ret;
+
+ if (phy_data->conn_type != XGBE_CONN_TYPE_MDIO)
+ return 0;
+
+ ret = xgbe_phy_get_comm_ownership(pdata);
+ if (ret)
+ return ret;
+
+ if (phy_data->mdio_reset == XGBE_MDIO_RESET_I2C_GPIO)
+ ret = xgbe_phy_i2c_mdio_reset(pdata);
+ else if (phy_data->mdio_reset == XGBE_MDIO_RESET_INT_GPIO)
+ ret = xgbe_phy_int_mdio_reset(pdata);
+
+ xgbe_phy_put_comm_ownership(pdata);
+
+ return ret;
+}
+
+static bool xgbe_phy_redrv_error(struct xgbe_phy_data *phy_data)
+{
+ if (!phy_data->redrv)
+ return false;
+
+ if (phy_data->redrv_if >= XGBE_PHY_REDRV_IF_MAX)
+ return true;
+
+ switch (phy_data->redrv_model) {
+ case XGBE_PHY_REDRV_MODEL_4223:
+ if (phy_data->redrv_lane > 3)
+ return true;
+ break;
+ case XGBE_PHY_REDRV_MODEL_4227:
+ if (phy_data->redrv_lane > 1)
+ return true;
+ break;
+ default:
+ return true;
+ }
+
+ return false;
+}
+
+static int xgbe_phy_mdio_reset_setup(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ unsigned int reg;
+
+ if (phy_data->conn_type != XGBE_CONN_TYPE_MDIO)
+ return 0;
+
+ reg = XP_IOREAD(pdata, XP_PROP_3);
+ phy_data->mdio_reset = XP_GET_BITS(reg, XP_PROP_3, MDIO_RESET);
+ switch (phy_data->mdio_reset) {
+ case XGBE_MDIO_RESET_NONE:
+ case XGBE_MDIO_RESET_I2C_GPIO:
+ case XGBE_MDIO_RESET_INT_GPIO:
+ break;
+ default:
+ dev_err(pdata->dev, "unsupported MDIO reset (%#x)\n",
+ phy_data->mdio_reset);
+ return -EINVAL;
+ }
+
+ if (phy_data->mdio_reset == XGBE_MDIO_RESET_I2C_GPIO) {
+ phy_data->mdio_reset_addr = XGBE_GPIO_ADDRESS_PCA9555 +
+ XP_GET_BITS(reg, XP_PROP_3,
+ MDIO_RESET_I2C_ADDR);
+ phy_data->mdio_reset_gpio = XP_GET_BITS(reg, XP_PROP_3,
+ MDIO_RESET_I2C_GPIO);
+ } else if (phy_data->mdio_reset == XGBE_MDIO_RESET_INT_GPIO) {
+ phy_data->mdio_reset_gpio = XP_GET_BITS(reg, XP_PROP_3,
+ MDIO_RESET_INT_GPIO);
+ }
+
+ return 0;
+}
+
+static bool xgbe_phy_port_mode_mismatch(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (phy_data->port_mode) {
+ case XGBE_PORT_MODE_BACKPLANE:
+ if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) ||
+ (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000))
+ return false;
+ break;
+ case XGBE_PORT_MODE_BACKPLANE_2500:
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_2500)
+ return false;
+ break;
+ case XGBE_PORT_MODE_1000BASE_T:
+ if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) ||
+ (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000))
+ return false;
+ break;
+ case XGBE_PORT_MODE_1000BASE_X:
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000)
+ return false;
+ break;
+ case XGBE_PORT_MODE_NBASE_T:
+ if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) ||
+ (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) ||
+ (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_2500))
+ return false;
+ break;
+ case XGBE_PORT_MODE_10GBASE_T:
+ if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) ||
+ (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) ||
+ (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000))
+ return false;
+ break;
+ case XGBE_PORT_MODE_10GBASE_R:
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000)
+ return false;
+ break;
+ case XGBE_PORT_MODE_SFP:
+ if ((phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) ||
+ (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) ||
+ (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000))
+ return false;
+ break;
+ default:
+ break;
+ }
+
+ return true;
+}
+
+static bool xgbe_phy_conn_type_mismatch(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ switch (phy_data->port_mode) {
+ case XGBE_PORT_MODE_BACKPLANE:
+ case XGBE_PORT_MODE_BACKPLANE_2500:
+ if (phy_data->conn_type == XGBE_CONN_TYPE_BACKPLANE)
+ return false;
+ break;
+ case XGBE_PORT_MODE_1000BASE_T:
+ case XGBE_PORT_MODE_1000BASE_X:
+ case XGBE_PORT_MODE_NBASE_T:
+ case XGBE_PORT_MODE_10GBASE_T:
+ case XGBE_PORT_MODE_10GBASE_R:
+ if (phy_data->conn_type == XGBE_CONN_TYPE_MDIO)
+ return false;
+ break;
+ case XGBE_PORT_MODE_SFP:
+ if (phy_data->conn_type == XGBE_CONN_TYPE_SFP)
+ return false;
+ break;
+ default:
+ break;
+ }
+
+ return true;
+}
+
+static bool xgbe_phy_port_enabled(struct xgbe_prv_data *pdata)
+{
+ unsigned int reg;
+
+ reg = XP_IOREAD(pdata, XP_PROP_0);
+ if (!XP_GET_BITS(reg, XP_PROP_0, PORT_SPEEDS))
+ return false;
+ if (!XP_GET_BITS(reg, XP_PROP_0, CONN_TYPE))
+ return false;
+
+ return true;
+}
+
+static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ /* If we have an external PHY, free it */
+ xgbe_phy_free_phy_device(pdata);
+
+ /* Reset SFP data */
+ xgbe_phy_sfp_reset(phy_data);
+ xgbe_phy_sfp_mod_absent(pdata);
+
+ /* Power off the PHY */
+ xgbe_phy_power_off(pdata);
+
+ /* Stop the I2C controller */
+ pdata->i2c_if.i2c_stop(pdata);
+}
+
+static int xgbe_phy_start(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ int ret;
+
+ /* Start the I2C controller */
+ ret = pdata->i2c_if.i2c_start(pdata);
+ if (ret)
+ return ret;
+
+ /* Start in highest supported mode */
+ xgbe_phy_set_mode(pdata, phy_data->start_mode);
+
+ /* After starting the I2C controller, we can check for an SFP */
+ switch (phy_data->port_mode) {
+ case XGBE_PORT_MODE_SFP:
+ xgbe_phy_sfp_detect(pdata);
+ break;
+ default:
+ break;
+ }
+
+ /* If we have an external PHY, start it */
+ ret = xgbe_phy_find_phy_device(pdata);
+ if (ret)
+ goto err_i2c;
+
+ return 0;
+
+err_i2c:
+ pdata->i2c_if.i2c_stop(pdata);
+
+ return ret;
+}
+
+static int xgbe_phy_reset(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+ enum xgbe_mode cur_mode;
+ int ret;
+
+ /* Reset by power cycling the PHY */
+ cur_mode = phy_data->cur_mode;
+ xgbe_phy_power_off(pdata);
+ xgbe_phy_set_mode(pdata, cur_mode);
+
+ if (!phy_data->phydev)
+ return 0;
+
+ /* Reset the external PHY */
+ ret = xgbe_phy_mdio_reset(pdata);
+ if (ret)
+ return ret;
+
+ return phy_init_hw(phy_data->phydev);
+}
+
+static void xgbe_phy_exit(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data = pdata->phy_data;
+
+ /* Unregister for driving external PHYs */
+ mdiobus_unregister(phy_data->mii);
+}
+
+static int xgbe_phy_init(struct xgbe_prv_data *pdata)
+{
+ struct xgbe_phy_data *phy_data;
+ struct mii_bus *mii;
+ unsigned int reg;
+ int ret;
+
+ /* Check if enabled */
+ if (!xgbe_phy_port_enabled(pdata)) {
+ dev_info(pdata->dev, "device is not enabled\n");
+ return -ENODEV;
+ }
+
+ /* Initialize the I2C controller */
+ ret = pdata->i2c_if.i2c_init(pdata);
+ if (ret)
+ return ret;
+
+ phy_data = devm_kzalloc(pdata->dev, sizeof(*phy_data), GFP_KERNEL);
+ if (!phy_data)
+ return -ENOMEM;
+ pdata->phy_data = phy_data;
+
+ reg = XP_IOREAD(pdata, XP_PROP_0);
+ phy_data->port_mode = XP_GET_BITS(reg, XP_PROP_0, PORT_MODE);
+ phy_data->port_id = XP_GET_BITS(reg, XP_PROP_0, PORT_ID);
+ phy_data->port_speeds = XP_GET_BITS(reg, XP_PROP_0, PORT_SPEEDS);
+ phy_data->conn_type = XP_GET_BITS(reg, XP_PROP_0, CONN_TYPE);
+ phy_data->mdio_addr = XP_GET_BITS(reg, XP_PROP_0, MDIO_ADDR);
+ if (netif_msg_probe(pdata)) {
+ dev_dbg(pdata->dev, "port mode=%u\n", phy_data->port_mode);
+ dev_dbg(pdata->dev, "port id=%u\n", phy_data->port_id);
+ dev_dbg(pdata->dev, "port speeds=%#x\n", phy_data->port_speeds);
+ dev_dbg(pdata->dev, "conn type=%u\n", phy_data->conn_type);
+ dev_dbg(pdata->dev, "mdio addr=%u\n", phy_data->mdio_addr);
+ }
+
+ reg = XP_IOREAD(pdata, XP_PROP_4);
+ phy_data->redrv = XP_GET_BITS(reg, XP_PROP_4, REDRV_PRESENT);
+ phy_data->redrv_if = XP_GET_BITS(reg, XP_PROP_4, REDRV_IF);
+ phy_data->redrv_addr = XP_GET_BITS(reg, XP_PROP_4, REDRV_ADDR);
+ phy_data->redrv_lane = XP_GET_BITS(reg, XP_PROP_4, REDRV_LANE);
+ phy_data->redrv_model = XP_GET_BITS(reg, XP_PROP_4, REDRV_MODEL);
+ if (phy_data->redrv && netif_msg_probe(pdata)) {
+ dev_dbg(pdata->dev, "redrv present\n");
+ dev_dbg(pdata->dev, "redrv i/f=%u\n", phy_data->redrv_if);
+ dev_dbg(pdata->dev, "redrv addr=%#x\n", phy_data->redrv_addr);
+ dev_dbg(pdata->dev, "redrv lane=%u\n", phy_data->redrv_lane);
+ dev_dbg(pdata->dev, "redrv model=%u\n", phy_data->redrv_model);
+ }
+
+ /* Validate the connection requested */
+ if (xgbe_phy_conn_type_mismatch(pdata)) {
+ dev_err(pdata->dev, "phy mode/connection mismatch (%#x/%#x)\n",
+ phy_data->port_mode, phy_data->conn_type);
+ return -EINVAL;
+ }
+
+ /* Validate the mode requested */
+ if (xgbe_phy_port_mode_mismatch(pdata)) {
+ dev_err(pdata->dev, "phy mode/speed mismatch (%#x/%#x)\n",
+ phy_data->port_mode, phy_data->port_speeds);
+ return -EINVAL;
+ }
+
+ /* Check for and validate MDIO reset support */
+ ret = xgbe_phy_mdio_reset_setup(pdata);
+ if (ret)
+ return ret;
+
+ /* Validate the re-driver information */
+ if (xgbe_phy_redrv_error(phy_data)) {
+ dev_err(pdata->dev, "phy re-driver settings error\n");
+ return -EINVAL;
+ }
+ pdata->kr_redrv = phy_data->redrv;
+
+ /* Indicate current mode is unknown */
+ phy_data->cur_mode = XGBE_MODE_UNKNOWN;
+
+ /* Initialize supported features */
+ pdata->phy.supported = 0;
+
+ switch (phy_data->port_mode) {
+ /* Backplane support */
+ case XGBE_PORT_MODE_BACKPLANE:
+ pdata->phy.supported |= SUPPORTED_Autoneg;
+ pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+ pdata->phy.supported |= SUPPORTED_Backplane;
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) {
+ pdata->phy.supported |= SUPPORTED_1000baseKX_Full;
+ phy_data->start_mode = XGBE_MODE_KX_1000;
+ }
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000) {
+ pdata->phy.supported |= SUPPORTED_10000baseKR_Full;
+ if (pdata->fec_ability & MDIO_PMA_10GBR_FECABLE_ABLE)
+ pdata->phy.supported |=
+ SUPPORTED_10000baseR_FEC;
+ phy_data->start_mode = XGBE_MODE_KR;
+ }
+
+ phy_data->phydev_mode = XGBE_MDIO_MODE_NONE;
+ break;
+ case XGBE_PORT_MODE_BACKPLANE_2500:
+ pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+ pdata->phy.supported |= SUPPORTED_Backplane;
+ pdata->phy.supported |= SUPPORTED_2500baseX_Full;
+ phy_data->start_mode = XGBE_MODE_KX_2500;
+
+ phy_data->phydev_mode = XGBE_MDIO_MODE_NONE;
+ break;
+
+ /* MDIO 1GBase-T support */
+ case XGBE_PORT_MODE_1000BASE_T:
+ pdata->phy.supported |= SUPPORTED_Autoneg;
+ pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+ pdata->phy.supported |= SUPPORTED_TP;
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) {
+ pdata->phy.supported |= SUPPORTED_100baseT_Full;
+ phy_data->start_mode = XGBE_MODE_SGMII_100;
+ }
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) {
+ pdata->phy.supported |= SUPPORTED_1000baseT_Full;
+ phy_data->start_mode = XGBE_MODE_SGMII_1000;
+ }
+
+ phy_data->phydev_mode = XGBE_MDIO_MODE_CL22;
+ break;
+
+ /* MDIO Base-X support */
+ case XGBE_PORT_MODE_1000BASE_X:
+ pdata->phy.supported |= SUPPORTED_Autoneg;
+ pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+ pdata->phy.supported |= SUPPORTED_FIBRE;
+ pdata->phy.supported |= SUPPORTED_1000baseT_Full;
+ phy_data->start_mode = XGBE_MODE_X;
+
+ phy_data->phydev_mode = XGBE_MDIO_MODE_CL22;
+ break;
+
+ /* MDIO NBase-T support */
+ case XGBE_PORT_MODE_NBASE_T:
+ pdata->phy.supported |= SUPPORTED_Autoneg;
+ pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+ pdata->phy.supported |= SUPPORTED_TP;
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) {
+ pdata->phy.supported |= SUPPORTED_100baseT_Full;
+ phy_data->start_mode = XGBE_MODE_SGMII_100;
+ }
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) {
+ pdata->phy.supported |= SUPPORTED_1000baseT_Full;
+ phy_data->start_mode = XGBE_MODE_SGMII_1000;
+ }
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_2500) {
+ pdata->phy.supported |= SUPPORTED_2500baseX_Full;
+ phy_data->start_mode = XGBE_MODE_KX_2500;
+ }
+
+ phy_data->phydev_mode = XGBE_MDIO_MODE_CL45;
+ break;
+
+ /* 10GBase-T support */
+ case XGBE_PORT_MODE_10GBASE_T:
+ pdata->phy.supported |= SUPPORTED_Autoneg;
+ pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+ pdata->phy.supported |= SUPPORTED_TP;
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) {
+ pdata->phy.supported |= SUPPORTED_100baseT_Full;
+ phy_data->start_mode = XGBE_MODE_SGMII_100;
+ }
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) {
+ pdata->phy.supported |= SUPPORTED_1000baseT_Full;
+ phy_data->start_mode = XGBE_MODE_SGMII_1000;
+ }
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000) {
+ pdata->phy.supported |= SUPPORTED_10000baseT_Full;
+ phy_data->start_mode = XGBE_MODE_KR;
+ }
+
+ phy_data->phydev_mode = XGBE_MDIO_MODE_NONE;
+ break;
+
+ /* 10GBase-R support */
+ case XGBE_PORT_MODE_10GBASE_R:
+ pdata->phy.supported |= SUPPORTED_Autoneg;
+ pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+ pdata->phy.supported |= SUPPORTED_TP;
+ pdata->phy.supported |= SUPPORTED_10000baseT_Full;
+ if (pdata->fec_ability & MDIO_PMA_10GBR_FECABLE_ABLE)
+ pdata->phy.supported |= SUPPORTED_10000baseR_FEC;
+ phy_data->start_mode = XGBE_MODE_SFI;
+
+ phy_data->phydev_mode = XGBE_MDIO_MODE_NONE;
+ break;
+
+ /* SFP support */
+ case XGBE_PORT_MODE_SFP:
+ pdata->phy.supported |= SUPPORTED_Autoneg;
+ pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+ pdata->phy.supported |= SUPPORTED_TP;
+ pdata->phy.supported |= SUPPORTED_FIBRE;
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) {
+ pdata->phy.supported |= SUPPORTED_100baseT_Full;
+ phy_data->start_mode = XGBE_MODE_SGMII_100;
+ }
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) {
+ pdata->phy.supported |= SUPPORTED_1000baseT_Full;
+ phy_data->start_mode = XGBE_MODE_SGMII_1000;
+ }
+ if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000) {
+ pdata->phy.supported |= SUPPORTED_10000baseT_Full;
+ phy_data->start_mode = XGBE_MODE_SFI;
+ if (pdata->fec_ability & MDIO_PMA_10GBR_FECABLE_ABLE)
+ pdata->phy.supported |=
+ SUPPORTED_10000baseR_FEC;
+ }
+
+ phy_data->phydev_mode = XGBE_MDIO_MODE_CL22;
+
+ xgbe_phy_sfp_setup(pdata);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (netif_msg_probe(pdata))
+ dev_dbg(pdata->dev, "phy supported=%#x\n",
+ pdata->phy.supported);
+
+ if ((phy_data->conn_type & XGBE_CONN_TYPE_MDIO) &&
+ (phy_data->phydev_mode != XGBE_MDIO_MODE_NONE)) {
+ ret = pdata->hw_if.set_ext_mii_mode(pdata, phy_data->mdio_addr,
+ phy_data->phydev_mode);
+ if (ret) {
+ dev_err(pdata->dev,
+ "mdio port/clause not compatible (%d/%u)\n",
+ phy_data->mdio_addr, phy_data->phydev_mode);
+ return -EINVAL;
+ }
+ }
+
+ if (phy_data->redrv && !phy_data->redrv_if) {
+ ret = pdata->hw_if.set_ext_mii_mode(pdata, phy_data->redrv_addr,
+ XGBE_MDIO_MODE_CL22);
+ if (ret) {
+ dev_err(pdata->dev,
+ "redriver mdio port not compatible (%u)\n",
+ phy_data->redrv_addr);
+ return -EINVAL;
+ }
+ }
+
+ /* Register for driving external PHYs */
+ mii = devm_mdiobus_alloc(pdata->dev);
+ if (!mii) {
+ dev_err(pdata->dev, "mdiobus_alloc failed\n");
+ return -ENOMEM;
+ }
+
+ mii->priv = pdata;
+ mii->name = "amd-xgbe-mii";
+ mii->read = xgbe_phy_mii_read;
+ mii->write = xgbe_phy_mii_write;
+ mii->parent = pdata->dev;
+ mii->phy_mask = ~0;
+ snprintf(mii->id, sizeof(mii->id), "%s", dev_name(pdata->dev));
+ ret = mdiobus_register(mii);
+ if (ret) {
+ dev_err(pdata->dev, "mdiobus_register failed\n");
+ return ret;
+ }
+ phy_data->mii = mii;
+
+ return 0;
+}
+
+void xgbe_init_function_ptrs_phy_v2(struct xgbe_phy_if *phy_if)
+{
+ struct xgbe_phy_impl_if *phy_impl = &phy_if->phy_impl;
+
+ phy_impl->init = xgbe_phy_init;
+ phy_impl->exit = xgbe_phy_exit;
+
+ phy_impl->reset = xgbe_phy_reset;
+ phy_impl->start = xgbe_phy_start;
+ phy_impl->stop = xgbe_phy_stop;
+
+ phy_impl->link_status = xgbe_phy_link_status;
+
+ phy_impl->valid_speed = xgbe_phy_valid_speed;
+
+ phy_impl->use_mode = xgbe_phy_use_mode;
+ phy_impl->set_mode = xgbe_phy_set_mode;
+ phy_impl->get_mode = xgbe_phy_get_mode;
+ phy_impl->switch_mode = xgbe_phy_switch_mode;
+ phy_impl->cur_mode = xgbe_phy_cur_mode;
+
+ phy_impl->an_mode = xgbe_phy_an_mode;
+
+ phy_impl->an_config = xgbe_phy_an_config;
+
+ phy_impl->an_advertising = xgbe_phy_an_advertising;
+
+ phy_impl->an_outcome = xgbe_phy_an_outcome;
+}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-platform.c b/drivers/net/ethernet/amd/xgbe/xgbe-platform.c
new file mode 100644
index 0000000..8c530dc
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-platform.c
@@ -0,0 +1,642 @@
+/*
+ * AMD 10Gb Ethernet driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ * The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ * (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ * Inc. unless otherwise expressly agreed to in writing between Synopsys
+ * and you.
+ *
+ * The Software IS NOT an item of Licensed Software or Licensed Product
+ * under any End User Software License Agreement or Agreement for Licensed
+ * Product with Synopsys or any supplement thereto. Permission is hereby
+ * granted, free of charge, to any person obtaining a copy of this software
+ * annotated with this license and the Software, to deal in the Software
+ * without restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is furnished
+ * to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ * BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ * PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ * THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2014-2016 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Advanced Micro Devices, Inc. nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ * The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ * (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ * Inc. unless otherwise expressly agreed to in writing between Synopsys
+ * and you.
+ *
+ * The Software IS NOT an item of Licensed Software or Licensed Product
+ * under any End User Software License Agreement or Agreement for Licensed
+ * Product with Synopsys or any supplement thereto. Permission is hereby
+ * granted, free of charge, to any person obtaining a copy of this software
+ * annotated with this license and the Software, to deal in the Software
+ * without restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is furnished
+ * to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ * BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ * PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ * THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_net.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/of_device.h>
+#include <linux/clk.h>
+#include <linux/property.h>
+#include <linux/acpi.h>
+#include <linux/mdio.h>
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id xgbe_acpi_match[];
+
+static struct xgbe_version_data *xgbe_acpi_vdata(struct xgbe_prv_data *pdata)
+{
+ const struct acpi_device_id *id;
+
+ id = acpi_match_device(xgbe_acpi_match, pdata->dev);
+
+ return id ? (struct xgbe_version_data *)id->driver_data : NULL;
+}
+
+static int xgbe_acpi_support(struct xgbe_prv_data *pdata)
+{
+ struct device *dev = pdata->dev;
+ u32 property;
+ int ret;
+
+ /* Obtain the system clock setting */
+ ret = device_property_read_u32(dev, XGBE_ACPI_DMA_FREQ, &property);
+ if (ret) {
+ dev_err(dev, "unable to obtain %s property\n",
+ XGBE_ACPI_DMA_FREQ);
+ return ret;
+ }
+ pdata->sysclk_rate = property;
+
+ /* Obtain the PTP clock setting */
+ ret = device_property_read_u32(dev, XGBE_ACPI_PTP_FREQ, &property);
+ if (ret) {
+ dev_err(dev, "unable to obtain %s property\n",
+ XGBE_ACPI_PTP_FREQ);
+ return ret;
+ }
+ pdata->ptpclk_rate = property;
+
+ return 0;
+}
+#else /* CONFIG_ACPI */
+static struct xgbe_version_data *xgbe_acpi_vdata(struct xgbe_prv_data *pdata)
+{
+ return NULL;
+}
+
+static int xgbe_acpi_support(struct xgbe_prv_data *pdata)
+{
+ return -EINVAL;
+}
+#endif /* CONFIG_ACPI */
+
+#ifdef CONFIG_OF
+static const struct of_device_id xgbe_of_match[];
+
+static struct xgbe_version_data *xgbe_of_vdata(struct xgbe_prv_data *pdata)
+{
+ const struct of_device_id *id;
+
+ id = of_match_device(xgbe_of_match, pdata->dev);
+
+ return id ? (struct xgbe_version_data *)id->data : NULL;
+}
+
+static int xgbe_of_support(struct xgbe_prv_data *pdata)
+{
+ struct device *dev = pdata->dev;
+
+ /* Obtain the system clock setting */
+ pdata->sysclk = devm_clk_get(dev, XGBE_DMA_CLOCK);
+ if (IS_ERR(pdata->sysclk)) {
+ dev_err(dev, "dma devm_clk_get failed\n");
+ return PTR_ERR(pdata->sysclk);
+ }
+ pdata->sysclk_rate = clk_get_rate(pdata->sysclk);
+
+ /* Obtain the PTP clock setting */
+ pdata->ptpclk = devm_clk_get(dev, XGBE_PTP_CLOCK);
+ if (IS_ERR(pdata->ptpclk)) {
+ dev_err(dev, "ptp devm_clk_get failed\n");
+ return PTR_ERR(pdata->ptpclk);
+ }
+ pdata->ptpclk_rate = clk_get_rate(pdata->ptpclk);
+
+ return 0;
+}
+
+static struct platform_device *xgbe_of_get_phy_pdev(struct xgbe_prv_data *pdata)
+{
+ struct device *dev = pdata->dev;
+ struct device_node *phy_node;
+ struct platform_device *phy_pdev;
+
+ phy_node = of_parse_phandle(dev->of_node, "phy-handle", 0);
+ if (phy_node) {
+ /* Old style device tree:
+ * The XGBE and PHY resources are separate
+ */
+ phy_pdev = of_find_device_by_node(phy_node);
+ of_node_put(phy_node);
+ } else {
+ /* New style device tree:
+ * The XGBE and PHY resources are grouped together with
+ * the PHY resources listed last
+ */
+ get_device(dev);
+ phy_pdev = pdata->platdev;
+ }
+
+ return phy_pdev;
+}
+#else /* CONFIG_OF */
+static struct xgbe_version_data *xgbe_of_vdata(struct xgbe_prv_data *pdata)
+{
+ return NULL;
+}
+
+static int xgbe_of_support(struct xgbe_prv_data *pdata)
+{
+ return -EINVAL;
+}
+
+static struct platform_device *xgbe_of_get_phy_pdev(struct xgbe_prv_data *pdata)
+{
+ return NULL;
+}
+#endif /* CONFIG_OF */
+
+static unsigned int xgbe_resource_count(struct platform_device *pdev,
+ unsigned int type)
+{
+ unsigned int count;
+ int i;
+
+ for (i = 0, count = 0; i < pdev->num_resources; i++) {
+ struct resource *res = &pdev->resource[i];
+
+ if (type == resource_type(res))
+ count++;
+ }
+
+ return count;
+}
+
+static struct platform_device *xgbe_get_phy_pdev(struct xgbe_prv_data *pdata)
+{
+ struct platform_device *phy_pdev;
+
+ if (pdata->use_acpi) {
+ get_device(pdata->dev);
+ phy_pdev = pdata->platdev;
+ } else {
+ phy_pdev = xgbe_of_get_phy_pdev(pdata);
+ }
+
+ return phy_pdev;
+}
+
+static struct xgbe_version_data *xgbe_get_vdata(struct xgbe_prv_data *pdata)
+{
+ return pdata->use_acpi ? xgbe_acpi_vdata(pdata)
+ : xgbe_of_vdata(pdata);
+}
+
+static int xgbe_platform_probe(struct platform_device *pdev)
+{
+ struct xgbe_prv_data *pdata;
+ struct device *dev = &pdev->dev;
+ struct platform_device *phy_pdev;
+ struct resource *res;
+ const char *phy_mode;
+ unsigned int phy_memnum, phy_irqnum;
+ unsigned int dma_irqnum, dma_irqend;
+ enum dev_dma_attr attr;
+ int ret;
+
+ pdata = xgbe_alloc_pdata(dev);
+ if (IS_ERR(pdata)) {
+ ret = PTR_ERR(pdata);
+ goto err_alloc;
+ }
+
+ pdata->platdev = pdev;
+ pdata->adev = ACPI_COMPANION(dev);
+ platform_set_drvdata(pdev, pdata);
+
+ /* Check if we should use ACPI or DT */
+ pdata->use_acpi = dev->of_node ? 0 : 1;
+
+ /* Get the version data */
+ pdata->vdata = xgbe_get_vdata(pdata);
+
+ phy_pdev = xgbe_get_phy_pdev(pdata);
+ if (!phy_pdev) {
+ dev_err(dev, "unable to obtain phy device\n");
+ ret = -EINVAL;
+ goto err_phydev;
+ }
+ pdata->phy_platdev = phy_pdev;
+ pdata->phy_dev = &phy_pdev->dev;
+
+ if (pdev == phy_pdev) {
+ /* New style device tree or ACPI:
+ * The XGBE and PHY resources are grouped together with
+ * the PHY resources listed last
+ */
+ phy_memnum = xgbe_resource_count(pdev, IORESOURCE_MEM) - 3;
+ phy_irqnum = xgbe_resource_count(pdev, IORESOURCE_IRQ) - 1;
+ dma_irqnum = 1;
+ dma_irqend = phy_irqnum;
+ } else {
+ /* Old style device tree:
+ * The XGBE and PHY resources are separate
+ */
+ phy_memnum = 0;
+ phy_irqnum = 0;
+ dma_irqnum = 1;
+ dma_irqend = xgbe_resource_count(pdev, IORESOURCE_IRQ);
+ }
+
+ /* Obtain the mmio areas for the device */
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ pdata->xgmac_regs = devm_ioremap_resource(dev, res);
+ if (IS_ERR(pdata->xgmac_regs)) {
+ dev_err(dev, "xgmac ioremap failed\n");
+ ret = PTR_ERR(pdata->xgmac_regs);
+ goto err_io;
+ }
+ if (netif_msg_probe(pdata))
+ dev_dbg(dev, "xgmac_regs = %p\n", pdata->xgmac_regs);
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+ pdata->xpcs_regs = devm_ioremap_resource(dev, res);
+ if (IS_ERR(pdata->xpcs_regs)) {
+ dev_err(dev, "xpcs ioremap failed\n");
+ ret = PTR_ERR(pdata->xpcs_regs);
+ goto err_io;
+ }
+ if (netif_msg_probe(pdata))
+ dev_dbg(dev, "xpcs_regs = %p\n", pdata->xpcs_regs);
+
+ res = platform_get_resource(phy_pdev, IORESOURCE_MEM, phy_memnum++);
+ pdata->rxtx_regs = devm_ioremap_resource(dev, res);
+ if (IS_ERR(pdata->rxtx_regs)) {
+ dev_err(dev, "rxtx ioremap failed\n");
+ ret = PTR_ERR(pdata->rxtx_regs);
+ goto err_io;
+ }
+ if (netif_msg_probe(pdata))
+ dev_dbg(dev, "rxtx_regs = %p\n", pdata->rxtx_regs);
+
+ res = platform_get_resource(phy_pdev, IORESOURCE_MEM, phy_memnum++);
+ pdata->sir0_regs = devm_ioremap_resource(dev, res);
+ if (IS_ERR(pdata->sir0_regs)) {
+ dev_err(dev, "sir0 ioremap failed\n");
+ ret = PTR_ERR(pdata->sir0_regs);
+ goto err_io;
+ }
+ if (netif_msg_probe(pdata))
+ dev_dbg(dev, "sir0_regs = %p\n", pdata->sir0_regs);
+
+ res = platform_get_resource(phy_pdev, IORESOURCE_MEM, phy_memnum++);
+ pdata->sir1_regs = devm_ioremap_resource(dev, res);
+ if (IS_ERR(pdata->sir1_regs)) {
+ dev_err(dev, "sir1 ioremap failed\n");
+ ret = PTR_ERR(pdata->sir1_regs);
+ goto err_io;
+ }
+ if (netif_msg_probe(pdata))
+ dev_dbg(dev, "sir1_regs = %p\n", pdata->sir1_regs);
+
+ /* Retrieve the MAC address */
+ ret = device_property_read_u8_array(dev, XGBE_MAC_ADDR_PROPERTY,
+ pdata->mac_addr,
+ sizeof(pdata->mac_addr));
+ if (ret || !is_valid_ether_addr(pdata->mac_addr)) {
+ dev_err(dev, "invalid %s property\n", XGBE_MAC_ADDR_PROPERTY);
+ if (!ret)
+ ret = -EINVAL;
+ goto err_io;
+ }
+
+ /* Retrieve the PHY mode - it must be "xgmii" */
+ ret = device_property_read_string(dev, XGBE_PHY_MODE_PROPERTY,
+ &phy_mode);
+ if (ret || strcmp(phy_mode, phy_modes(PHY_INTERFACE_MODE_XGMII))) {
+ dev_err(dev, "invalid %s property\n", XGBE_PHY_MODE_PROPERTY);
+ if (!ret)
+ ret = -EINVAL;
+ goto err_io;
+ }
+ pdata->phy_mode = PHY_INTERFACE_MODE_XGMII;
+
+ /* Check for per channel interrupt support */
+ if (device_property_present(dev, XGBE_DMA_IRQS_PROPERTY)) {
+ pdata->per_channel_irq = 1;
+ pdata->channel_irq_mode = XGBE_IRQ_MODE_EDGE;
+ }
+
+ /* Obtain device settings unique to ACPI/OF */
+ if (pdata->use_acpi)
+ ret = xgbe_acpi_support(pdata);
+ else
+ ret = xgbe_of_support(pdata);
+ if (ret)
+ goto err_io;
+
+ /* Set the DMA coherency values */
+ attr = device_get_dma_attr(dev);
+ if (attr == DEV_DMA_NOT_SUPPORTED) {
+ dev_err(dev, "DMA is not supported");
+ ret = -ENODEV;
+ goto err_io;
+ }
+ pdata->coherent = (attr == DEV_DMA_COHERENT);
+ if (pdata->coherent) {
+ pdata->axdomain = XGBE_DMA_OS_AXDOMAIN;
+ pdata->arcache = XGBE_DMA_OS_ARCACHE;
+ pdata->awcache = XGBE_DMA_OS_AWCACHE;
+ } else {
+ pdata->axdomain = XGBE_DMA_SYS_AXDOMAIN;
+ pdata->arcache = XGBE_DMA_SYS_ARCACHE;
+ pdata->awcache = XGBE_DMA_SYS_AWCACHE;
+ }
+
+ /* Set the maximum fifo amounts */
+ pdata->tx_max_fifo_size = pdata->vdata->tx_max_fifo_size;
+ pdata->rx_max_fifo_size = pdata->vdata->rx_max_fifo_size;
+
+ /* Set the hardware channel and queue counts */
+ xgbe_set_counts(pdata);
+
+ /* Always have XGMAC and XPCS (auto-negotiation) interrupts */
+ pdata->irq_count = 2;
+
+ /* Get the device interrupt */
+ ret = platform_get_irq(pdev, 0);
+ if (ret < 0) {
+ dev_err(dev, "platform_get_irq 0 failed\n");
+ goto err_io;
+ }
+ pdata->dev_irq = ret;
+
+ /* Get the per channel DMA interrupts */
+ if (pdata->per_channel_irq) {
+ unsigned int i, max = ARRAY_SIZE(pdata->channel_irq);
+
+ for (i = 0; (i < max) && (dma_irqnum < dma_irqend); i++) {
+ ret = platform_get_irq(pdata->platdev, dma_irqnum++);
+ if (ret < 0) {
+ netdev_err(pdata->netdev,
+ "platform_get_irq %u failed\n",
+ dma_irqnum - 1);
+ goto err_io;
+ }
+
+ pdata->channel_irq[i] = ret;
+ }
+
+ pdata->channel_irq_count = max;
+
+ pdata->irq_count += max;
+ }
+
+ /* Get the auto-negotiation interrupt */
+ ret = platform_get_irq(phy_pdev, phy_irqnum++);
+ if (ret < 0) {
+ dev_err(dev, "platform_get_irq phy 0 failed\n");
+ goto err_io;
+ }
+ pdata->an_irq = ret;
+
+ /* Configure the netdev resource */
+ ret = xgbe_config_netdev(pdata);
+ if (ret)
+ goto err_io;
+
+ netdev_notice(pdata->netdev, "net device enabled\n");
+
+ return 0;
+
+err_io:
+ platform_device_put(phy_pdev);
+
+err_phydev:
+ xgbe_free_pdata(pdata);
+
+err_alloc:
+ dev_notice(dev, "net device not enabled\n");
+
+ return ret;
+}
+
+static int xgbe_platform_remove(struct platform_device *pdev)
+{
+ struct xgbe_prv_data *pdata = platform_get_drvdata(pdev);
+
+ xgbe_deconfig_netdev(pdata);
+
+ platform_device_put(pdata->phy_platdev);
+
+ xgbe_free_pdata(pdata);
+
+ return 0;
+}
+
+#ifdef CONFIG_PM
+static int xgbe_platform_suspend(struct device *dev)
+{
+ struct xgbe_prv_data *pdata = dev_get_drvdata(dev);
+ struct net_device *netdev = pdata->netdev;
+ int ret = 0;
+
+ DBGPR("-->xgbe_suspend\n");
+
+ if (netif_running(netdev))
+ ret = xgbe_powerdown(netdev, XGMAC_DRIVER_CONTEXT);
+
+ pdata->lpm_ctrl = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
+ pdata->lpm_ctrl |= MDIO_CTRL1_LPOWER;
+ XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, pdata->lpm_ctrl);
+
+ DBGPR("<--xgbe_suspend\n");
+
+ return ret;
+}
+
+static int xgbe_platform_resume(struct device *dev)
+{
+ struct xgbe_prv_data *pdata = dev_get_drvdata(dev);
+ struct net_device *netdev = pdata->netdev;
+ int ret = 0;
+
+ DBGPR("-->xgbe_resume\n");
+
+ pdata->lpm_ctrl &= ~MDIO_CTRL1_LPOWER;
+ XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, pdata->lpm_ctrl);
+
+ if (netif_running(netdev)) {
+ ret = xgbe_powerup(netdev, XGMAC_DRIVER_CONTEXT);
+
+ /* Schedule a restart in case the link or phy state changed
+ * while we were powered down.
+ */
+ schedule_work(&pdata->restart_work);
+ }
+
+ DBGPR("<--xgbe_resume\n");
+
+ return ret;
+}
+#endif /* CONFIG_PM */
+
+static const struct xgbe_version_data xgbe_v1 = {
+ .init_function_ptrs_phy_impl = xgbe_init_function_ptrs_phy_v1,
+ .xpcs_access = XGBE_XPCS_ACCESS_V1,
+ .tx_max_fifo_size = 81920,
+ .rx_max_fifo_size = 81920,
+ .tx_tstamp_workaround = 1,
+};
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id xgbe_acpi_match[] = {
+ { .id = "AMDI8001",
+ .driver_data = (kernel_ulong_t)&xgbe_v1 },
+ {},
+};
+
+MODULE_DEVICE_TABLE(acpi, xgbe_acpi_match);
+#endif
+
+#ifdef CONFIG_OF
+static const struct of_device_id xgbe_of_match[] = {
+ { .compatible = "amd,xgbe-seattle-v1a",
+ .data = &xgbe_v1 },
+ {},
+};
+
+MODULE_DEVICE_TABLE(of, xgbe_of_match);
+#endif
+
+static SIMPLE_DEV_PM_OPS(xgbe_platform_pm_ops,
+ xgbe_platform_suspend, xgbe_platform_resume);
+
+static struct platform_driver xgbe_driver = {
+ .driver = {
+ .name = XGBE_DRV_NAME,
+#ifdef CONFIG_ACPI
+ .acpi_match_table = xgbe_acpi_match,
+#endif
+#ifdef CONFIG_OF
+ .of_match_table = xgbe_of_match,
+#endif
+ .pm = &xgbe_platform_pm_ops,
+ },
+ .probe = xgbe_platform_probe,
+ .remove = xgbe_platform_remove,
+};
+
+int xgbe_platform_init(void)
+{
+ return platform_driver_register(&xgbe_driver);
+}
+
+void xgbe_platform_exit(void)
+{
+ platform_driver_unregister(&xgbe_driver);
+}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index 5dd17dc..f52a9bd 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -127,9 +127,10 @@
#include <linux/timecounter.h>
#include <linux/net_tstamp.h>
#include <net/dcbnl.h>
+#include <linux/completion.h>
#define XGBE_DRV_NAME "amd-xgbe"
-#define XGBE_DRV_VERSION "1.0.2"
+#define XGBE_DRV_VERSION "1.0.3"
#define XGBE_DRV_DESC "AMD 10 Gigabit Ethernet Driver"
/* Descriptor related defines */
@@ -158,7 +159,8 @@
#define XGBE_MAX_DMA_CHANNELS 16
#define XGBE_MAX_QUEUES 16
-#define XGBE_DMA_STOP_TIMEOUT 5
+#define XGBE_PRIORITY_QUEUES 8
+#define XGBE_DMA_STOP_TIMEOUT 1
/* DMA cache settings - Outer sharable, write-back, write-allocate */
#define XGBE_DMA_OS_AXDOMAIN 0x2
@@ -170,6 +172,10 @@
#define XGBE_DMA_SYS_ARCACHE 0x0
#define XGBE_DMA_SYS_AWCACHE 0x0
+/* DMA channel interrupt modes */
+#define XGBE_IRQ_MODE_EDGE 0
+#define XGBE_IRQ_MODE_LEVEL 1
+
#define XGBE_DMA_INTERRUPT_MASK 0x31c7
#define XGMAC_MIN_PACKET 60
@@ -177,18 +183,19 @@
#define XGMAC_MAX_STD_PACKET 1518
#define XGMAC_JUMBO_PACKET_MTU 9000
#define XGMAC_MAX_JUMBO_PACKET 9018
+#define XGMAC_ETH_PREAMBLE (12 + 8) /* Inter-frame gap + preamble */
+
+#define XGMAC_PFC_DATA_LEN 46
+#define XGMAC_PFC_DELAYS 14000
+
+#define XGMAC_PRIO_QUEUES(_cnt) \
+ min_t(unsigned int, IEEE_8021QAZ_MAX_TCS, (_cnt))
/* Common property names */
#define XGBE_MAC_ADDR_PROPERTY "mac-address"
#define XGBE_PHY_MODE_PROPERTY "phy-mode"
#define XGBE_DMA_IRQS_PROPERTY "amd,per-channel-interrupt"
#define XGBE_SPEEDSET_PROPERTY "amd,speed-set"
-#define XGBE_BLWC_PROPERTY "amd,serdes-blwc"
-#define XGBE_CDR_RATE_PROPERTY "amd,serdes-cdr-rate"
-#define XGBE_PQ_SKEW_PROPERTY "amd,serdes-pq-skew"
-#define XGBE_TX_AMP_PROPERTY "amd,serdes-tx-amp"
-#define XGBE_DFE_CFG_PROPERTY "amd,serdes-dfe-tap-config"
-#define XGBE_DFE_ENA_PROPERTY "amd,serdes-dfe-tap-enable"
/* Device-tree clock names */
#define XGBE_DMA_CLOCK "dma_clk"
@@ -198,6 +205,20 @@
#define XGBE_ACPI_DMA_FREQ "amd,dma-freq"
#define XGBE_ACPI_PTP_FREQ "amd,ptp-freq"
+/* PCI BAR mapping */
+#define XGBE_XGMAC_BAR 0
+#define XGBE_XPCS_BAR 1
+#define XGBE_MAC_PROP_OFFSET 0x1d000
+#define XGBE_I2C_CTRL_OFFSET 0x1e000
+
+/* PCI MSIx support */
+#define XGBE_MSIX_BASE_COUNT 4
+#define XGBE_MSIX_MIN_COUNT (XGBE_MSIX_BASE_COUNT + 1)
+
+/* PCI clock frequencies */
+#define XGBE_V2_DMA_CLOCK_FREQ 500000000 /* 500 MHz */
+#define XGBE_V2_PTP_CLOCK_FREQ 125000000 /* 125 MHz */
+
/* Timestamp support - values based on 50MHz PTP clock
* 50MHz => 20 nsec
*/
@@ -208,7 +229,12 @@
#define XGMAC_DRIVER_CONTEXT 1
#define XGMAC_IOCTL_CONTEXT 2
-#define XGBE_FIFO_MAX 81920
+#define XGMAC_FIFO_MIN_ALLOC 2048
+#define XGMAC_FIFO_UNIT 256
+#define XGMAC_FIFO_ALIGN(_x) \
+ (((_x) + XGMAC_FIFO_UNIT - 1) & ~(XGMAC_FIFO_UNIT - 1))
+#define XGMAC_FIFO_FC_OFF 2048
+#define XGMAC_FIFO_FC_MIN 4096
#define XGBE_TC_MIN_QUANTUM 10
@@ -233,6 +259,14 @@
/* Flow control queue count */
#define XGMAC_MAX_FLOW_CONTROL_QUEUES 8
+/* Flow control threshold units */
+#define XGMAC_FLOW_CONTROL_UNIT 512
+#define XGMAC_FLOW_CONTROL_ALIGN(_x) \
+ (((_x) + XGMAC_FLOW_CONTROL_UNIT - 1) & ~(XGMAC_FLOW_CONTROL_UNIT - 1))
+#define XGMAC_FLOW_CONTROL_VALUE(_x) \
+ (((_x) < 1024) ? 0 : ((_x) / XGMAC_FLOW_CONTROL_UNIT) - 2)
+#define XGMAC_FLOW_CONTROL_MAX 33280
+
/* Maximum MAC address hash table size (256 bits = 8 bytes) */
#define XGBE_MAC_HASH_TABLE_SIZE 8
@@ -244,46 +278,19 @@
/* Auto-negotiation */
#define XGBE_AN_MS_TIMEOUT 500
-#define XGBE_LINK_TIMEOUT 10
+#define XGBE_LINK_TIMEOUT 5
-#define XGBE_AN_INT_CMPLT 0x01
-#define XGBE_AN_INC_LINK 0x02
-#define XGBE_AN_PG_RCV 0x04
-#define XGBE_AN_INT_MASK 0x07
+#define XGBE_SGMII_AN_LINK_STATUS BIT(1)
+#define XGBE_SGMII_AN_LINK_SPEED (BIT(2) | BIT(3))
+#define XGBE_SGMII_AN_LINK_SPEED_100 0x04
+#define XGBE_SGMII_AN_LINK_SPEED_1000 0x08
+#define XGBE_SGMII_AN_LINK_DUPLEX BIT(4)
-/* Rate-change complete wait/retry count */
-#define XGBE_RATECHANGE_COUNT 500
+/* ECC correctable error notification window (seconds) */
+#define XGBE_ECC_LIMIT 60
-/* Default SerDes settings */
-#define XGBE_SPEED_10000_BLWC 0
-#define XGBE_SPEED_10000_CDR 0x7
-#define XGBE_SPEED_10000_PLL 0x1
-#define XGBE_SPEED_10000_PQ 0x12
-#define XGBE_SPEED_10000_RATE 0x0
-#define XGBE_SPEED_10000_TXAMP 0xa
-#define XGBE_SPEED_10000_WORD 0x7
-#define XGBE_SPEED_10000_DFE_TAP_CONFIG 0x1
-#define XGBE_SPEED_10000_DFE_TAP_ENABLE 0x7f
-
-#define XGBE_SPEED_2500_BLWC 1
-#define XGBE_SPEED_2500_CDR 0x2
-#define XGBE_SPEED_2500_PLL 0x0
-#define XGBE_SPEED_2500_PQ 0xa
-#define XGBE_SPEED_2500_RATE 0x1
-#define XGBE_SPEED_2500_TXAMP 0xf
-#define XGBE_SPEED_2500_WORD 0x1
-#define XGBE_SPEED_2500_DFE_TAP_CONFIG 0x3
-#define XGBE_SPEED_2500_DFE_TAP_ENABLE 0x0
-
-#define XGBE_SPEED_1000_BLWC 1
-#define XGBE_SPEED_1000_CDR 0x2
-#define XGBE_SPEED_1000_PLL 0x0
-#define XGBE_SPEED_1000_PQ 0xa
-#define XGBE_SPEED_1000_RATE 0x3
-#define XGBE_SPEED_1000_TXAMP 0xf
-#define XGBE_SPEED_1000_WORD 0x1
-#define XGBE_SPEED_1000_DFE_TAP_CONFIG 0x3
-#define XGBE_SPEED_1000_DFE_TAP_ENABLE 0x0
+/* MDIO port types */
+#define XGMAC_MAX_C22_PORT 3
struct xgbe_prv_data;
@@ -461,6 +468,7 @@ enum xgbe_state {
XGBE_DOWN,
XGBE_LINK_INIT,
XGBE_LINK_ERR,
+ XGBE_STOPPED,
};
enum xgbe_int {
@@ -480,6 +488,12 @@ enum xgbe_int_state {
XGMAC_INT_STATE_RESTORE,
};
+enum xgbe_ecc_sec {
+ XGBE_ECC_SEC_TX,
+ XGBE_ECC_SEC_RX,
+ XGBE_ECC_SEC_DESC,
+};
+
enum xgbe_speed {
XGBE_SPEED_1000 = 0,
XGBE_SPEED_2500,
@@ -487,6 +501,19 @@ enum xgbe_speed {
XGBE_SPEEDS,
};
+enum xgbe_xpcs_access {
+ XGBE_XPCS_ACCESS_V1 = 0,
+ XGBE_XPCS_ACCESS_V2,
+};
+
+enum xgbe_an_mode {
+ XGBE_AN_MODE_CL73 = 0,
+ XGBE_AN_MODE_CL73_REDRV,
+ XGBE_AN_MODE_CL37,
+ XGBE_AN_MODE_CL37_SGMII,
+ XGBE_AN_MODE_NONE,
+};
+
enum xgbe_an {
XGBE_AN_READY = 0,
XGBE_AN_PAGE_RECEIVED,
@@ -504,8 +531,14 @@ enum xgbe_rx {
};
enum xgbe_mode {
- XGBE_MODE_KR = 0,
- XGBE_MODE_KX,
+ XGBE_MODE_KX_1000 = 0,
+ XGBE_MODE_KX_2500,
+ XGBE_MODE_KR,
+ XGBE_MODE_X,
+ XGBE_MODE_SGMII_100,
+ XGBE_MODE_SGMII_1000,
+ XGBE_MODE_SFI,
+ XGBE_MODE_UNKNOWN,
};
enum xgbe_speedset {
@@ -513,6 +546,12 @@ enum xgbe_speedset {
XGBE_SPEEDSET_2500_10000,
};
+enum xgbe_mdio_mode {
+ XGBE_MDIO_MODE_NONE = 0,
+ XGBE_MDIO_MODE_CL22,
+ XGBE_MDIO_MODE_CL45,
+};
+
struct xgbe_phy {
u32 supported;
u32 advertising;
@@ -531,6 +570,43 @@ struct xgbe_phy {
int rx_pause;
};
+enum xgbe_i2c_cmd {
+ XGBE_I2C_CMD_READ = 0,
+ XGBE_I2C_CMD_WRITE,
+};
+
+struct xgbe_i2c_op {
+ enum xgbe_i2c_cmd cmd;
+
+ unsigned int target;
+
+ void *buf;
+ unsigned int len;
+};
+
+struct xgbe_i2c_op_state {
+ struct xgbe_i2c_op *op;
+
+ unsigned int tx_len;
+ unsigned char *tx_buf;
+
+ unsigned int rx_len;
+ unsigned char *rx_buf;
+
+ unsigned int tx_abort_source;
+
+ int ret;
+};
+
+struct xgbe_i2c {
+ unsigned int started;
+ unsigned int max_speed_mode;
+ unsigned int rx_fifo_size;
+ unsigned int tx_fifo_size;
+
+ struct xgbe_i2c_op_state op_state;
+};
+
struct xgbe_mmc_stats {
/* Tx Stats */
u64 txoctetcount_gb;
@@ -601,9 +677,15 @@ struct xgbe_hw_if {
int (*read_mmd_regs)(struct xgbe_prv_data *, int, int);
void (*write_mmd_regs)(struct xgbe_prv_data *, int, int, int);
- int (*set_gmii_speed)(struct xgbe_prv_data *);
- int (*set_gmii_2500_speed)(struct xgbe_prv_data *);
- int (*set_xgmii_speed)(struct xgbe_prv_data *);
+ int (*set_speed)(struct xgbe_prv_data *, int);
+
+ int (*set_ext_mii_mode)(struct xgbe_prv_data *, unsigned int,
+ enum xgbe_mdio_mode);
+ int (*read_ext_mii_regs)(struct xgbe_prv_data *, int, int);
+ int (*write_ext_mii_regs)(struct xgbe_prv_data *, int, int, u16);
+
+ int (*set_gpio)(struct xgbe_prv_data *, unsigned int);
+ int (*clr_gpio)(struct xgbe_prv_data *, unsigned int);
void (*enable_tx)(struct xgbe_prv_data *);
void (*disable_tx)(struct xgbe_prv_data *);
@@ -682,11 +764,65 @@ struct xgbe_hw_if {
int (*disable_rss)(struct xgbe_prv_data *);
int (*set_rss_hash_key)(struct xgbe_prv_data *, const u8 *);
int (*set_rss_lookup_table)(struct xgbe_prv_data *, const u32 *);
+
+ /* For ECC */
+ void (*disable_ecc_ded)(struct xgbe_prv_data *);
+ void (*disable_ecc_sec)(struct xgbe_prv_data *, enum xgbe_ecc_sec);
+};
+
+/* This structure represents implementation specific routines for an
+ * implementation of a PHY. All routines are required unless noted below.
+ * Optional routines:
+ * kr_training_pre, kr_training_post
+ */
+struct xgbe_phy_impl_if {
+ /* Perform Setup/teardown actions */
+ int (*init)(struct xgbe_prv_data *);
+ void (*exit)(struct xgbe_prv_data *);
+
+ /* Perform start/stop specific actions */
+ int (*reset)(struct xgbe_prv_data *);
+ int (*start)(struct xgbe_prv_data *);
+ void (*stop)(struct xgbe_prv_data *);
+
+ /* Return the link status */
+ int (*link_status)(struct xgbe_prv_data *, int *);
+
+ /* Indicate if a particular speed is valid */
+ bool (*valid_speed)(struct xgbe_prv_data *, int);
+
+ /* Check if the specified mode can/should be used */
+ bool (*use_mode)(struct xgbe_prv_data *, enum xgbe_mode);
+ /* Switch the PHY into various modes */
+ void (*set_mode)(struct xgbe_prv_data *, enum xgbe_mode);
+ /* Retrieve mode needed for a specific speed */
+ enum xgbe_mode (*get_mode)(struct xgbe_prv_data *, int);
+ /* Retrieve new/next mode when trying to auto-negotiate */
+ enum xgbe_mode (*switch_mode)(struct xgbe_prv_data *);
+ /* Retrieve current mode */
+ enum xgbe_mode (*cur_mode)(struct xgbe_prv_data *);
+
+ /* Retrieve current auto-negotiation mode */
+ enum xgbe_an_mode (*an_mode)(struct xgbe_prv_data *);
+
+ /* Configure auto-negotiation settings */
+ int (*an_config)(struct xgbe_prv_data *);
+
+ /* Set/override auto-negotiation advertisement settings */
+ unsigned int (*an_advertising)(struct xgbe_prv_data *);
+
+ /* Process results of auto-negotiation */
+ enum xgbe_mode (*an_outcome)(struct xgbe_prv_data *);
+
+ /* Pre/Post KR training enablement support */
+ void (*kr_training_pre)(struct xgbe_prv_data *);
+ void (*kr_training_post)(struct xgbe_prv_data *);
};
struct xgbe_phy_if {
- /* For initial PHY setup */
- void (*phy_init)(struct xgbe_prv_data *);
+ /* For PHY setup/teardown */
+ int (*phy_init)(struct xgbe_prv_data *);
+ void (*phy_exit)(struct xgbe_prv_data *);
/* For PHY support when setting device up/down */
int (*phy_reset)(struct xgbe_prv_data *);
@@ -696,6 +832,30 @@ struct xgbe_phy_if {
/* For PHY support while device is up */
void (*phy_status)(struct xgbe_prv_data *);
int (*phy_config_aneg)(struct xgbe_prv_data *);
+
+ /* For PHY settings validation */
+ bool (*phy_valid_speed)(struct xgbe_prv_data *, int);
+
+ /* For single interrupt support */
+ irqreturn_t (*an_isr)(int, struct xgbe_prv_data *);
+
+ /* PHY implementation specific services */
+ struct xgbe_phy_impl_if phy_impl;
+};
+
+struct xgbe_i2c_if {
+ /* For initial I2C setup */
+ int (*i2c_init)(struct xgbe_prv_data *);
+
+ /* For I2C support when setting device up/down */
+ int (*i2c_start)(struct xgbe_prv_data *);
+ void (*i2c_stop)(struct xgbe_prv_data *);
+
+ /* For performing I2C operations */
+ int (*i2c_xfer)(struct xgbe_prv_data *, struct xgbe_i2c_op *);
+
+ /* For single interrupt support */
+ irqreturn_t (*i2c_isr)(int, struct xgbe_prv_data *);
};
struct xgbe_desc_if {
@@ -755,11 +915,28 @@ struct xgbe_hw_features {
unsigned int aux_snap_num; /* Number of Aux snapshot inputs */
};
+struct xgbe_version_data {
+ void (*init_function_ptrs_phy_impl)(struct xgbe_phy_if *);
+ enum xgbe_xpcs_access xpcs_access;
+ unsigned int mmc_64bit;
+ unsigned int tx_max_fifo_size;
+ unsigned int rx_max_fifo_size;
+ unsigned int tx_tstamp_workaround;
+ unsigned int ecc_support;
+ unsigned int i2c_support;
+};
+
struct xgbe_prv_data {
struct net_device *netdev;
- struct platform_device *pdev;
+ struct pci_dev *pcidev;
+ struct platform_device *platdev;
struct acpi_device *adev;
struct device *dev;
+ struct platform_device *phy_platdev;
+ struct device *phy_dev;
+
+ /* Version related data */
+ struct xgbe_version_data *vdata;
/* ACPI or DT flag */
unsigned int use_acpi;
@@ -770,12 +947,17 @@ struct xgbe_prv_data {
void __iomem *rxtx_regs; /* SerDes Rx/Tx CSRs */
void __iomem *sir0_regs; /* SerDes integration registers (1/2) */
void __iomem *sir1_regs; /* SerDes integration registers (2/2) */
+ void __iomem *xprop_regs; /* XGBE property registers */
+ void __iomem *xi2c_regs; /* XGBE I2C CSRs */
/* Overall device lock */
spinlock_t lock;
/* XPCS indirect addressing lock */
spinlock_t xpcs_lock;
+ unsigned int xpcs_window;
+ unsigned int xpcs_window_size;
+ unsigned int xpcs_window_mask;
/* RSS addressing mutex */
struct mutex rss_mutex;
@@ -783,12 +965,39 @@ struct xgbe_prv_data {
/* Flags representing xgbe_state */
unsigned long dev_state;
+ /* ECC support */
+ unsigned long tx_sec_period;
+ unsigned long tx_ded_period;
+ unsigned long rx_sec_period;
+ unsigned long rx_ded_period;
+ unsigned long desc_sec_period;
+ unsigned long desc_ded_period;
+
+ unsigned int tx_sec_count;
+ unsigned int tx_ded_count;
+ unsigned int rx_sec_count;
+ unsigned int rx_ded_count;
+ unsigned int desc_ded_count;
+ unsigned int desc_sec_count;
+
+ struct msix_entry *msix_entries;
int dev_irq;
+ int ecc_irq;
+ int i2c_irq;
+ int channel_irq[XGBE_MAX_DMA_CHANNELS];
+
unsigned int per_channel_irq;
+ unsigned int irq_shared;
+ unsigned int irq_count;
+ unsigned int channel_irq_count;
+ unsigned int channel_irq_mode;
+
+ char ecc_name[IFNAMSIZ + 32];
struct xgbe_hw_if hw_if;
struct xgbe_phy_if phy_if;
struct xgbe_desc_if desc_if;
+ struct xgbe_i2c_if i2c_if;
/* AXI DMA settings */
unsigned int coherent;
@@ -803,12 +1012,16 @@ struct xgbe_prv_data {
/* Rings for Tx/Rx on a DMA channel */
struct xgbe_channel *channel;
+ unsigned int tx_max_channel_count;
+ unsigned int rx_max_channel_count;
unsigned int channel_count;
unsigned int tx_ring_count;
unsigned int tx_desc_count;
unsigned int rx_ring_count;
unsigned int rx_desc_count;
+ unsigned int tx_max_q_count;
+ unsigned int rx_max_q_count;
unsigned int tx_q_count;
unsigned int rx_q_count;
@@ -820,11 +1033,13 @@ struct xgbe_prv_data {
unsigned int tx_threshold;
unsigned int tx_pbl;
unsigned int tx_osp_mode;
+ unsigned int tx_max_fifo_size;
/* Rx settings */
unsigned int rx_sf_mode;
unsigned int rx_threshold;
unsigned int rx_pbl;
+ unsigned int rx_max_fifo_size;
/* Tx coalescing settings */
unsigned int tx_usecs;
@@ -842,6 +1057,8 @@ struct xgbe_prv_data {
unsigned int pause_autoneg;
unsigned int tx_pause;
unsigned int rx_pause;
+ unsigned int rx_rfa[XGBE_MAX_QUEUES];
+ unsigned int rx_rfd[XGBE_MAX_QUEUES];
/* Receive Side Scaling settings */
u8 rss_key[XGBE_RSS_HASH_KEY_SIZE];
@@ -881,13 +1098,16 @@ struct xgbe_prv_data {
struct ieee_pfc *pfc;
unsigned int q2tc_map[XGBE_MAX_QUEUES];
unsigned int prio2q_map[IEEE_8021QAZ_MAX_TCS];
+ unsigned int pfcq[XGBE_MAX_QUEUES];
+ unsigned int pfc_rfa;
u8 num_tcs;
/* Hardware features of the device */
struct xgbe_hw_features hw_feat;
- /* Device restart work structure */
+ /* Device work structures */
struct work_struct restart_work;
+ struct work_struct stopdev_work;
/* Keeps track of power mode */
unsigned int power_down;
@@ -901,9 +1121,14 @@ struct xgbe_prv_data {
int phy_speed;
/* MDIO/PHY related settings */
+ unsigned int phy_started;
+ void *phy_data;
struct xgbe_phy phy;
int mdio_mmd;
unsigned long link_check;
+ struct completion mdio_complete;
+
+ unsigned int kr_redrv;
char an_name[IFNAMSIZ + 32];
struct workqueue_struct *an_workqueue;
@@ -911,23 +1136,9 @@ struct xgbe_prv_data {
int an_irq;
struct work_struct an_irq_work;
- unsigned int speed_set;
-
- /* SerDes UEFI configurable settings.
- * Switching between modes/speeds requires new values for some
- * SerDes settings. The values can be supplied as device
- * properties in array format. The first array entry is for
- * 1GbE, second for 2.5GbE and third for 10GbE
- */
- u32 serdes_blwc[XGBE_SPEEDS];
- u32 serdes_cdr_rate[XGBE_SPEEDS];
- u32 serdes_pq_skew[XGBE_SPEEDS];
- u32 serdes_tx_amp[XGBE_SPEEDS];
- u32 serdes_dfe_tap_cfg[XGBE_SPEEDS];
- u32 serdes_dfe_tap_ena[XGBE_SPEEDS];
-
/* Auto-negotiation state machine support */
unsigned int an_int;
+ unsigned int an_status;
struct mutex an_mutex;
enum xgbe_an an_result;
enum xgbe_an an_state;
@@ -938,6 +1149,13 @@ struct xgbe_prv_data {
unsigned int parallel_detect;
unsigned int fec_ability;
unsigned long an_start;
+ enum xgbe_an_mode an_mode;
+
+ /* I2C support */
+ struct xgbe_i2c i2c;
+ struct mutex i2c_mutex;
+ struct completion i2c_complete;
+ char i2c_name[IFNAMSIZ + 32];
unsigned int lpm_ctrl; /* CTRL1 for resume */
@@ -948,14 +1166,36 @@ struct xgbe_prv_data {
unsigned int debugfs_xpcs_mmd;
unsigned int debugfs_xpcs_reg;
+
+ unsigned int debugfs_xprop_reg;
+
+ unsigned int debugfs_xi2c_reg;
#endif
};
/* Function prototypes*/
+struct xgbe_prv_data *xgbe_alloc_pdata(struct device *);
+void xgbe_free_pdata(struct xgbe_prv_data *);
+void xgbe_set_counts(struct xgbe_prv_data *);
+int xgbe_config_netdev(struct xgbe_prv_data *);
+void xgbe_deconfig_netdev(struct xgbe_prv_data *);
+
+int xgbe_platform_init(void);
+void xgbe_platform_exit(void);
+#ifdef CONFIG_PCI
+int xgbe_pci_init(void);
+void xgbe_pci_exit(void);
+#else
+static inline int xgbe_pci_init(void) { return 0; }
+static inline void xgbe_pci_exit(void) { }
+#endif
void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *);
void xgbe_init_function_ptrs_phy(struct xgbe_phy_if *);
+void xgbe_init_function_ptrs_phy_v1(struct xgbe_phy_if *);
+void xgbe_init_function_ptrs_phy_v2(struct xgbe_phy_if *);
void xgbe_init_function_ptrs_desc(struct xgbe_desc_if *);
+void xgbe_init_function_ptrs_i2c(struct xgbe_i2c_if *);
const struct net_device_ops *xgbe_get_netdev_ops(void);
const struct ethtool_ops *xgbe_get_ethtool_ops(void);
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
index c481f10..5390ae8 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
@@ -204,17 +204,6 @@ static u32 xgene_enet_ring_len(struct xgene_enet_desc_ring *ring)
return num_msgs;
}
-static void xgene_enet_setup_coalescing(struct xgene_enet_desc_ring *ring)
-{
- u32 data = 0x7777;
-
- xgene_enet_ring_wr32(ring, CSR_PBM_COAL, 0x8e);
- xgene_enet_ring_wr32(ring, CSR_PBM_CTICK1, data);
- xgene_enet_ring_wr32(ring, CSR_PBM_CTICK2, data << 16);
- xgene_enet_ring_wr32(ring, CSR_THRESHOLD0_SET1, 0x40);
- xgene_enet_ring_wr32(ring, CSR_THRESHOLD1_SET1, 0x80);
-}
-
void xgene_enet_parse_error(struct xgene_enet_desc_ring *ring,
struct xgene_enet_pdata *pdata,
enum xgene_enet_err_code status)
@@ -929,5 +918,4 @@ struct xgene_ring_ops xgene_ring1_ops = {
.clear = xgene_enet_clear_ring,
.wr_cmd = xgene_enet_wr_cmd,
.len = xgene_enet_ring_len,
- .coalesce = xgene_enet_setup_coalescing,
};
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
index 8456337..06e598c 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
@@ -55,8 +55,10 @@ enum xgene_enet_rm {
#define PREFETCH_BUF_EN BIT(21)
#define CSR_RING_ID_BUF 0x000c
#define CSR_PBM_COAL 0x0014
+#define CSR_PBM_CTICK0 0x0018
#define CSR_PBM_CTICK1 0x001c
#define CSR_PBM_CTICK2 0x0020
+#define CSR_PBM_CTICK3 0x0024
#define CSR_THRESHOLD0_SET1 0x0030
#define CSR_THRESHOLD1_SET1 0x0034
#define CSR_RING_NE_INT_MODE 0x017c
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index 3fc7b0d..1352b52 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -1188,7 +1188,8 @@ static int xgene_enet_create_desc_rings(struct net_device *ndev)
tx_ring->dst_ring_num = xgene_enet_dst_ring_num(cp_ring);
}
- pdata->ring_ops->coalesce(pdata->tx_ring[0]);
+ if (pdata->ring_ops->coalesce)
+ pdata->ring_ops->coalesce(pdata->tx_ring[0]);
pdata->tx_qcnt_hi = pdata->tx_ring[0]->slots - 128;
return 0;
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.c b/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.c
index 2b76732..af51dd5 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.c
@@ -30,7 +30,7 @@ static void xgene_enet_ring_init(struct xgene_enet_desc_ring *ring)
ring_cfg[0] |= SET_VAL(X2_INTLINE, ring->id & RING_BUFNUM_MASK);
ring_cfg[3] |= SET_BIT(X2_DEQINTEN);
}
- ring_cfg[0] |= SET_VAL(X2_CFGCRID, 1);
+ ring_cfg[0] |= SET_VAL(X2_CFGCRID, 2);
addr >>= 8;
ring_cfg[2] |= QCOHERENT | SET_VAL(RINGADDRL, addr);
@@ -192,13 +192,15 @@ static u32 xgene_enet_ring_len(struct xgene_enet_desc_ring *ring)
static void xgene_enet_setup_coalescing(struct xgene_enet_desc_ring *ring)
{
- u32 data = 0x7777;
+ u32 data = 0x77777777;
xgene_enet_ring_wr32(ring, CSR_PBM_COAL, 0x8e);
+ xgene_enet_ring_wr32(ring, CSR_PBM_CTICK0, data);
xgene_enet_ring_wr32(ring, CSR_PBM_CTICK1, data);
- xgene_enet_ring_wr32(ring, CSR_PBM_CTICK2, data << 16);
- xgene_enet_ring_wr32(ring, CSR_THRESHOLD0_SET1, 0x40);
- xgene_enet_ring_wr32(ring, CSR_THRESHOLD1_SET1, 0x80);
+ xgene_enet_ring_wr32(ring, CSR_PBM_CTICK2, data);
+ xgene_enet_ring_wr32(ring, CSR_PBM_CTICK3, data);
+ xgene_enet_ring_wr32(ring, CSR_THRESHOLD0_SET1, 0x08);
+ xgene_enet_ring_wr32(ring, CSR_THRESHOLD1_SET1, 0x10);
}
struct xgene_ring_ops xgene_ring2_ops = {
diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h
index 6cac919..d4a4091 100644
--- a/drivers/net/ethernet/atheros/alx/alx.h
+++ b/drivers/net/ethernet/atheros/alx/alx.h
@@ -50,6 +50,10 @@ struct alx_buffer {
};
struct alx_rx_queue {
+ struct net_device *netdev;
+ struct device *dev;
+ struct alx_napi *np;
+
struct alx_rrd *rrd;
dma_addr_t rrd_dma;
@@ -58,16 +62,26 @@ struct alx_rx_queue {
struct alx_buffer *bufs;
+ u16 count;
u16 write_idx, read_idx;
u16 rrd_read_idx;
+ u16 queue_idx;
};
#define ALX_RX_ALLOC_THRESH 32
struct alx_tx_queue {
+ struct net_device *netdev;
+ struct device *dev;
+
struct alx_txd *tpd;
dma_addr_t tpd_dma;
+
struct alx_buffer *bufs;
+
+ u16 count;
u16 write_idx, read_idx;
+ u16 queue_idx;
+ u16 p_reg, c_reg;
};
#define ALX_DEFAULT_TX_WORK 128
@@ -76,6 +90,18 @@ enum alx_device_quirks {
ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG = BIT(0),
};
+struct alx_napi {
+ struct napi_struct napi;
+ struct alx_priv *alx;
+ struct alx_rx_queue *rxq;
+ struct alx_tx_queue *txq;
+ int vec_idx;
+ u32 vec_mask;
+ char irq_lbl[IFNAMSIZ + 8];
+};
+
+#define ALX_MAX_NAPIS 8
+
#define ALX_FLAG_USING_MSIX BIT(0)
#define ALX_FLAG_USING_MSI BIT(1)
@@ -87,7 +113,6 @@ struct alx_priv {
/* msi-x vectors */
int num_vec;
struct msix_entry *msix_entries;
- char irq_lbl[IFNAMSIZ + 8];
/* all descriptor memory */
struct {
@@ -96,6 +121,11 @@ struct alx_priv {
unsigned int size;
} descmem;
+ struct alx_napi *qnapi[ALX_MAX_NAPIS];
+ int num_txq;
+ int num_rxq;
+ int num_napi;
+
/* protect int_mask updates */
spinlock_t irq_lock;
u32 int_mask;
@@ -104,10 +134,6 @@ struct alx_priv {
unsigned int rx_ringsz;
unsigned int rxbuf_size;
- struct napi_struct napi;
- struct alx_tx_queue txq;
- struct alx_rx_queue rxq;
-
struct work_struct link_check_wk;
struct work_struct reset_wk;
diff --git a/drivers/net/ethernet/atheros/alx/ethtool.c b/drivers/net/ethernet/atheros/alx/ethtool.c
index 08e22df..2f4eabf 100644
--- a/drivers/net/ethernet/atheros/alx/ethtool.c
+++ b/drivers/net/ethernet/atheros/alx/ethtool.c
@@ -125,64 +125,75 @@ static u32 alx_get_supported_speeds(struct alx_hw *hw)
return supported;
}
-static int alx_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+static int alx_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct alx_priv *alx = netdev_priv(netdev);
struct alx_hw *hw = &alx->hw;
+ u32 supported, advertising;
- ecmd->supported = SUPPORTED_Autoneg |
+ supported = SUPPORTED_Autoneg |
SUPPORTED_TP |
SUPPORTED_Pause |
SUPPORTED_Asym_Pause;
if (alx_hw_giga(hw))
- ecmd->supported |= SUPPORTED_1000baseT_Full;
- ecmd->supported |= alx_get_supported_speeds(hw);
+ supported |= SUPPORTED_1000baseT_Full;
+ supported |= alx_get_supported_speeds(hw);
- ecmd->advertising = ADVERTISED_TP;
+ advertising = ADVERTISED_TP;
if (hw->adv_cfg & ADVERTISED_Autoneg)
- ecmd->advertising |= hw->adv_cfg;
+ advertising |= hw->adv_cfg;
- ecmd->port = PORT_TP;
- ecmd->phy_address = 0;
+ cmd->base.port = PORT_TP;
+ cmd->base.phy_address = 0;
if (hw->adv_cfg & ADVERTISED_Autoneg)
- ecmd->autoneg = AUTONEG_ENABLE;
+ cmd->base.autoneg = AUTONEG_ENABLE;
else
- ecmd->autoneg = AUTONEG_DISABLE;
- ecmd->transceiver = XCVR_INTERNAL;
+ cmd->base.autoneg = AUTONEG_DISABLE;
if (hw->flowctrl & ALX_FC_ANEG && hw->adv_cfg & ADVERTISED_Autoneg) {
if (hw->flowctrl & ALX_FC_RX) {
- ecmd->advertising |= ADVERTISED_Pause;
+ advertising |= ADVERTISED_Pause;
if (!(hw->flowctrl & ALX_FC_TX))
- ecmd->advertising |= ADVERTISED_Asym_Pause;
+ advertising |= ADVERTISED_Asym_Pause;
} else if (hw->flowctrl & ALX_FC_TX) {
- ecmd->advertising |= ADVERTISED_Asym_Pause;
+ advertising |= ADVERTISED_Asym_Pause;
}
}
- ethtool_cmd_speed_set(ecmd, hw->link_speed);
- ecmd->duplex = hw->duplex;
+ cmd->base.speed = hw->link_speed;
+ cmd->base.duplex = hw->duplex;
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
return 0;
}
-static int alx_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+static int alx_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
{
struct alx_priv *alx = netdev_priv(netdev);
struct alx_hw *hw = &alx->hw;
u32 adv_cfg;
+ u32 advertising;
ASSERT_RTNL();
- if (ecmd->autoneg == AUTONEG_ENABLE) {
- if (ecmd->advertising & ~alx_get_supported_speeds(hw))
+ ethtool_convert_link_mode_to_legacy_u32(&advertising,
+ cmd->link_modes.advertising);
+
+ if (cmd->base.autoneg == AUTONEG_ENABLE) {
+ if (advertising & ~alx_get_supported_speeds(hw))
return -EINVAL;
- adv_cfg = ecmd->advertising | ADVERTISED_Autoneg;
+ adv_cfg = advertising | ADVERTISED_Autoneg;
} else {
- adv_cfg = alx_speed_to_ethadv(ethtool_cmd_speed(ecmd),
- ecmd->duplex);
+ adv_cfg = alx_speed_to_ethadv(cmd->base.speed,
+ cmd->base.duplex);
if (!adv_cfg || adv_cfg == ADVERTISED_1000baseT_Full)
return -EINVAL;
@@ -300,8 +311,6 @@ static int alx_get_sset_count(struct net_device *netdev, int sset)
}
const struct ethtool_ops alx_ethtool_ops = {
- .get_settings = alx_get_settings,
- .set_settings = alx_set_settings,
.get_pauseparam = alx_get_pauseparam,
.set_pauseparam = alx_set_pauseparam,
.get_msglevel = alx_get_msglevel,
@@ -310,4 +319,6 @@ const struct ethtool_ops alx_ethtool_ops = {
.get_strings = alx_get_strings,
.get_sset_count = alx_get_sset_count,
.get_ethtool_stats = alx_get_ethtool_stats,
+ .get_link_ksettings = alx_get_link_ksettings,
+ .set_link_ksettings = alx_set_link_ksettings,
};
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index eccbacd..c8f5255 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -51,16 +51,12 @@
const char alx_drv_name[] = "alx";
-static bool msix = false;
-module_param(msix, bool, 0);
-MODULE_PARM_DESC(msix, "Enable msi-x interrupt support");
-
-static void alx_free_txbuf(struct alx_priv *alx, int entry)
+static void alx_free_txbuf(struct alx_tx_queue *txq, int entry)
{
- struct alx_buffer *txb = &alx->txq.bufs[entry];
+ struct alx_buffer *txb = &txq->bufs[entry];
if (dma_unmap_len(txb, size)) {
- dma_unmap_single(&alx->hw.pdev->dev,
+ dma_unmap_single(txq->dev,
dma_unmap_addr(txb, dma),
dma_unmap_len(txb, size),
DMA_TO_DEVICE);
@@ -75,7 +71,7 @@ static void alx_free_txbuf(struct alx_priv *alx, int entry)
static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
{
- struct alx_rx_queue *rxq = &alx->rxq;
+ struct alx_rx_queue *rxq = alx->qnapi[0]->rxq;
struct sk_buff *skb;
struct alx_buffer *cur_buf;
dma_addr_t dma;
@@ -143,24 +139,42 @@ static int alx_refill_rx_ring(struct alx_priv *alx, gfp_t gfp)
return count;
}
-static inline int alx_tpd_avail(struct alx_priv *alx)
+static struct alx_tx_queue *alx_tx_queue_mapping(struct alx_priv *alx,
+ struct sk_buff *skb)
{
- struct alx_tx_queue *txq = &alx->txq;
+ unsigned int r_idx = skb->queue_mapping;
+ if (r_idx >= alx->num_txq)
+ r_idx = r_idx % alx->num_txq;
+
+ return alx->qnapi[r_idx]->txq;
+}
+
+static struct netdev_queue *alx_get_tx_queue(const struct alx_tx_queue *txq)
+{
+ return netdev_get_tx_queue(txq->netdev, txq->queue_idx);
+}
+
+static inline int alx_tpd_avail(struct alx_tx_queue *txq)
+{
if (txq->write_idx >= txq->read_idx)
- return alx->tx_ringsz + txq->read_idx - txq->write_idx - 1;
+ return txq->count + txq->read_idx - txq->write_idx - 1;
return txq->read_idx - txq->write_idx - 1;
}
-static bool alx_clean_tx_irq(struct alx_priv *alx)
+static bool alx_clean_tx_irq(struct alx_tx_queue *txq)
{
- struct alx_tx_queue *txq = &alx->txq;
+ struct alx_priv *alx;
+ struct netdev_queue *tx_queue;
u16 hw_read_idx, sw_read_idx;
unsigned int total_bytes = 0, total_packets = 0;
int budget = ALX_DEFAULT_TX_WORK;
+ alx = netdev_priv(txq->netdev);
+ tx_queue = alx_get_tx_queue(txq);
+
sw_read_idx = txq->read_idx;
- hw_read_idx = alx_read_mem16(&alx->hw, ALX_TPD_PRI0_CIDX);
+ hw_read_idx = alx_read_mem16(&alx->hw, txq->c_reg);
if (sw_read_idx != hw_read_idx) {
while (sw_read_idx != hw_read_idx && budget > 0) {
@@ -173,19 +187,19 @@ static bool alx_clean_tx_irq(struct alx_priv *alx)
budget--;
}
- alx_free_txbuf(alx, sw_read_idx);
+ alx_free_txbuf(txq, sw_read_idx);
- if (++sw_read_idx == alx->tx_ringsz)
+ if (++sw_read_idx == txq->count)
sw_read_idx = 0;
}
txq->read_idx = sw_read_idx;
- netdev_completed_queue(alx->dev, total_packets, total_bytes);
+ netdev_tx_completed_queue(tx_queue, total_packets, total_bytes);
}
- if (netif_queue_stopped(alx->dev) && netif_carrier_ok(alx->dev) &&
- alx_tpd_avail(alx) > alx->tx_ringsz/4)
- netif_wake_queue(alx->dev);
+ if (netif_tx_queue_stopped(tx_queue) && netif_carrier_ok(alx->dev) &&
+ alx_tpd_avail(txq) > txq->count / 4)
+ netif_tx_wake_queue(tx_queue);
return sw_read_idx == hw_read_idx;
}
@@ -200,15 +214,17 @@ static void alx_schedule_reset(struct alx_priv *alx)
schedule_work(&alx->reset_wk);
}
-static int alx_clean_rx_irq(struct alx_priv *alx, int budget)
+static int alx_clean_rx_irq(struct alx_rx_queue *rxq, int budget)
{
- struct alx_rx_queue *rxq = &alx->rxq;
+ struct alx_priv *alx;
struct alx_rrd *rrd;
struct alx_buffer *rxb;
struct sk_buff *skb;
u16 length, rfd_cleaned = 0;
int work = 0;
+ alx = netdev_priv(rxq->netdev);
+
while (work < budget) {
rrd = &rxq->rrd[rxq->rrd_read_idx];
if (!(rrd->word3 & cpu_to_le32(1 << RRD_UPDATED_SHIFT)))
@@ -224,7 +240,7 @@ static int alx_clean_rx_irq(struct alx_priv *alx, int budget)
}
rxb = &rxq->bufs[rxq->read_idx];
- dma_unmap_single(&alx->hw.pdev->dev,
+ dma_unmap_single(rxq->dev,
dma_unmap_addr(rxb, dma),
dma_unmap_len(rxb, size),
DMA_FROM_DEVICE);
@@ -242,7 +258,7 @@ static int alx_clean_rx_irq(struct alx_priv *alx, int budget)
length = ALX_GET_FIELD(le32_to_cpu(rrd->word3),
RRD_PKTLEN) - ETH_FCS_LEN;
skb_put(skb, length);
- skb->protocol = eth_type_trans(skb, alx->dev);
+ skb->protocol = eth_type_trans(skb, rxq->netdev);
skb_checksum_none_assert(skb);
if (alx->dev->features & NETIF_F_RXCSUM &&
@@ -259,13 +275,13 @@ static int alx_clean_rx_irq(struct alx_priv *alx, int budget)
}
}
- napi_gro_receive(&alx->napi, skb);
+ napi_gro_receive(&rxq->np->napi, skb);
work++;
next_pkt:
- if (++rxq->read_idx == alx->rx_ringsz)
+ if (++rxq->read_idx == rxq->count)
rxq->read_idx = 0;
- if (++rxq->rrd_read_idx == alx->rx_ringsz)
+ if (++rxq->rrd_read_idx == rxq->count)
rxq->rrd_read_idx = 0;
if (++rfd_cleaned > ALX_RX_ALLOC_THRESH)
@@ -280,23 +296,26 @@ static int alx_clean_rx_irq(struct alx_priv *alx, int budget)
static int alx_poll(struct napi_struct *napi, int budget)
{
- struct alx_priv *alx = container_of(napi, struct alx_priv, napi);
+ struct alx_napi *np = container_of(napi, struct alx_napi, napi);
+ struct alx_priv *alx = np->alx;
struct alx_hw *hw = &alx->hw;
unsigned long flags;
- bool tx_complete;
- int work;
+ bool tx_complete = true;
+ int work = 0;
- tx_complete = alx_clean_tx_irq(alx);
- work = alx_clean_rx_irq(alx, budget);
+ if (np->txq)
+ tx_complete = alx_clean_tx_irq(np->txq);
+ if (np->rxq)
+ work = alx_clean_rx_irq(np->rxq, budget);
if (!tx_complete || work == budget)
return budget;
- napi_complete(&alx->napi);
+ napi_complete(&np->napi);
/* enable interrupt */
if (alx->flags & ALX_FLAG_USING_MSIX) {
- alx_mask_msix(hw, 1, false);
+ alx_mask_msix(hw, np->vec_idx, false);
} else {
spin_lock_irqsave(&alx->irq_lock, flags);
alx->int_mask |= ALX_ISR_TX_Q0 | ALX_ISR_RX_Q0;
@@ -350,7 +369,7 @@ static irqreturn_t alx_intr_handle(struct alx_priv *alx, u32 intr)
goto out;
if (intr & (ALX_ISR_TX_Q0 | ALX_ISR_RX_Q0)) {
- napi_schedule(&alx->napi);
+ napi_schedule(&alx->qnapi[0]->napi);
/* mask rx/tx interrupt, enable them when napi complete */
alx->int_mask &= ~ALX_ISR_ALL_QUEUES;
alx_write_mem32(hw, ALX_IMR, alx->int_mask);
@@ -365,15 +384,15 @@ static irqreturn_t alx_intr_handle(struct alx_priv *alx, u32 intr)
static irqreturn_t alx_intr_msix_ring(int irq, void *data)
{
- struct alx_priv *alx = data;
- struct alx_hw *hw = &alx->hw;
+ struct alx_napi *np = data;
+ struct alx_hw *hw = &np->alx->hw;
/* mask interrupt to ACK chip */
- alx_mask_msix(hw, 1, true);
+ alx_mask_msix(hw, np->vec_idx, true);
/* clear interrupt status */
- alx_write_mem32(hw, ALX_ISR, (ALX_ISR_TX_Q0 | ALX_ISR_RX_Q0));
+ alx_write_mem32(hw, ALX_ISR, np->vec_mask);
- napi_schedule(&alx->napi);
+ napi_schedule(&np->napi);
return IRQ_HANDLED;
}
@@ -424,63 +443,79 @@ static irqreturn_t alx_intr_legacy(int irq, void *data)
return alx_intr_handle(alx, intr);
}
+static const u16 txring_header_reg[] = {ALX_TPD_PRI0_ADDR_LO,
+ ALX_TPD_PRI1_ADDR_LO,
+ ALX_TPD_PRI2_ADDR_LO,
+ ALX_TPD_PRI3_ADDR_LO};
+
static void alx_init_ring_ptrs(struct alx_priv *alx)
{
struct alx_hw *hw = &alx->hw;
u32 addr_hi = ((u64)alx->descmem.dma) >> 32;
+ struct alx_napi *np;
+ int i;
- alx->rxq.read_idx = 0;
- alx->rxq.write_idx = 0;
- alx->rxq.rrd_read_idx = 0;
+ for (i = 0; i < alx->num_napi; i++) {
+ np = alx->qnapi[i];
+ if (np->txq) {
+ np->txq->read_idx = 0;
+ np->txq->write_idx = 0;
+ alx_write_mem32(hw,
+ txring_header_reg[np->txq->queue_idx],
+ np->txq->tpd_dma);
+ }
+
+ if (np->rxq) {
+ np->rxq->read_idx = 0;
+ np->rxq->write_idx = 0;
+ np->rxq->rrd_read_idx = 0;
+ alx_write_mem32(hw, ALX_RRD_ADDR_LO, np->rxq->rrd_dma);
+ alx_write_mem32(hw, ALX_RFD_ADDR_LO, np->rxq->rfd_dma);
+ }
+ }
+
+ alx_write_mem32(hw, ALX_TX_BASE_ADDR_HI, addr_hi);
+ alx_write_mem32(hw, ALX_TPD_RING_SZ, alx->tx_ringsz);
+
alx_write_mem32(hw, ALX_RX_BASE_ADDR_HI, addr_hi);
- alx_write_mem32(hw, ALX_RRD_ADDR_LO, alx->rxq.rrd_dma);
alx_write_mem32(hw, ALX_RRD_RING_SZ, alx->rx_ringsz);
- alx_write_mem32(hw, ALX_RFD_ADDR_LO, alx->rxq.rfd_dma);
alx_write_mem32(hw, ALX_RFD_RING_SZ, alx->rx_ringsz);
alx_write_mem32(hw, ALX_RFD_BUF_SZ, alx->rxbuf_size);
- alx->txq.read_idx = 0;
- alx->txq.write_idx = 0;
- alx_write_mem32(hw, ALX_TX_BASE_ADDR_HI, addr_hi);
- alx_write_mem32(hw, ALX_TPD_PRI0_ADDR_LO, alx->txq.tpd_dma);
- alx_write_mem32(hw, ALX_TPD_RING_SZ, alx->tx_ringsz);
-
/* load these pointers into the chip */
alx_write_mem32(hw, ALX_SRAM9, ALX_SRAM_LOAD_PTR);
}
-static void alx_free_txring_buf(struct alx_priv *alx)
+static void alx_free_txring_buf(struct alx_tx_queue *txq)
{
- struct alx_tx_queue *txq = &alx->txq;
int i;
if (!txq->bufs)
return;
- for (i = 0; i < alx->tx_ringsz; i++)
- alx_free_txbuf(alx, i);
+ for (i = 0; i < txq->count; i++)
+ alx_free_txbuf(txq, i);
- memset(txq->bufs, 0, alx->tx_ringsz * sizeof(struct alx_buffer));
- memset(txq->tpd, 0, alx->tx_ringsz * sizeof(struct alx_txd));
+ memset(txq->bufs, 0, txq->count * sizeof(struct alx_buffer));
+ memset(txq->tpd, 0, txq->count * sizeof(struct alx_txd));
txq->write_idx = 0;
txq->read_idx = 0;
- netdev_reset_queue(alx->dev);
+ netdev_tx_reset_queue(alx_get_tx_queue(txq));
}
-static void alx_free_rxring_buf(struct alx_priv *alx)
+static void alx_free_rxring_buf(struct alx_rx_queue *rxq)
{
- struct alx_rx_queue *rxq = &alx->rxq;
struct alx_buffer *cur_buf;
u16 i;
- if (rxq == NULL)
+ if (!rxq->bufs)
return;
- for (i = 0; i < alx->rx_ringsz; i++) {
+ for (i = 0; i < rxq->count; i++) {
cur_buf = rxq->bufs + i;
if (cur_buf->skb) {
- dma_unmap_single(&alx->hw.pdev->dev,
+ dma_unmap_single(rxq->dev,
dma_unmap_addr(cur_buf, dma),
dma_unmap_len(cur_buf, size),
DMA_FROM_DEVICE);
@@ -498,8 +533,14 @@ static void alx_free_rxring_buf(struct alx_priv *alx)
static void alx_free_buffers(struct alx_priv *alx)
{
- alx_free_txring_buf(alx);
- alx_free_rxring_buf(alx);
+ int i;
+
+ for (i = 0; i < alx->num_txq; i++)
+ if (alx->qnapi[i] && alx->qnapi[i]->txq)
+ alx_free_txring_buf(alx->qnapi[i]->txq);
+
+ if (alx->qnapi[0] && alx->qnapi[0]->rxq)
+ alx_free_rxring_buf(alx->qnapi[0]->rxq);
}
static int alx_reinit_rings(struct alx_priv *alx)
@@ -573,19 +614,41 @@ static int alx_set_mac_address(struct net_device *netdev, void *data)
return 0;
}
-static int alx_alloc_descriptors(struct alx_priv *alx)
+static int alx_alloc_tx_ring(struct alx_priv *alx, struct alx_tx_queue *txq,
+ int offset)
{
- alx->txq.bufs = kcalloc(alx->tx_ringsz,
- sizeof(struct alx_buffer),
- GFP_KERNEL);
- if (!alx->txq.bufs)
+ txq->bufs = kcalloc(txq->count, sizeof(struct alx_buffer), GFP_KERNEL);
+ if (!txq->bufs)
return -ENOMEM;
- alx->rxq.bufs = kcalloc(alx->rx_ringsz,
- sizeof(struct alx_buffer),
- GFP_KERNEL);
- if (!alx->rxq.bufs)
- goto out_free;
+ txq->tpd = alx->descmem.virt + offset;
+ txq->tpd_dma = alx->descmem.dma + offset;
+ offset += sizeof(struct alx_txd) * txq->count;
+
+ return offset;
+}
+
+static int alx_alloc_rx_ring(struct alx_priv *alx, struct alx_rx_queue *rxq,
+ int offset)
+{
+ rxq->bufs = kcalloc(rxq->count, sizeof(struct alx_buffer), GFP_KERNEL);
+ if (!rxq->bufs)
+ return -ENOMEM;
+
+ rxq->rrd = alx->descmem.virt + offset;
+ rxq->rrd_dma = alx->descmem.dma + offset;
+ offset += sizeof(struct alx_rrd) * rxq->count;
+
+ rxq->rfd = alx->descmem.virt + offset;
+ rxq->rfd_dma = alx->descmem.dma + offset;
+ offset += sizeof(struct alx_rfd) * rxq->count;
+
+ return offset;
+}
+
+static int alx_alloc_rings(struct alx_priv *alx)
+{
+ int i, offset = 0;
/* physical tx/rx ring descriptors
*
@@ -593,7 +656,8 @@ static int alx_alloc_descriptors(struct alx_priv *alx)
* 4G boundary (hardware has a single register for high 32 bits
* of addresses only)
*/
- alx->descmem.size = sizeof(struct alx_txd) * alx->tx_ringsz +
+ alx->descmem.size = sizeof(struct alx_txd) * alx->tx_ringsz *
+ alx->num_txq +
sizeof(struct alx_rrd) * alx->rx_ringsz +
sizeof(struct alx_rfd) * alx->rx_ringsz;
alx->descmem.virt = dma_zalloc_coherent(&alx->hw.pdev->dev,
@@ -601,87 +665,178 @@ static int alx_alloc_descriptors(struct alx_priv *alx)
&alx->descmem.dma,
GFP_KERNEL);
if (!alx->descmem.virt)
- goto out_free;
+ return -ENOMEM;
- alx->txq.tpd = alx->descmem.virt;
- alx->txq.tpd_dma = alx->descmem.dma;
-
- /* alignment requirement for next block */
+ /* alignment requirements */
BUILD_BUG_ON(sizeof(struct alx_txd) % 8);
-
- alx->rxq.rrd =
- (void *)((u8 *)alx->descmem.virt +
- sizeof(struct alx_txd) * alx->tx_ringsz);
- alx->rxq.rrd_dma = alx->descmem.dma +
- sizeof(struct alx_txd) * alx->tx_ringsz;
-
- /* alignment requirement for next block */
BUILD_BUG_ON(sizeof(struct alx_rrd) % 8);
- alx->rxq.rfd =
- (void *)((u8 *)alx->descmem.virt +
- sizeof(struct alx_txd) * alx->tx_ringsz +
- sizeof(struct alx_rrd) * alx->rx_ringsz);
- alx->rxq.rfd_dma = alx->descmem.dma +
- sizeof(struct alx_txd) * alx->tx_ringsz +
- sizeof(struct alx_rrd) * alx->rx_ringsz;
+ for (i = 0; i < alx->num_txq; i++) {
+ offset = alx_alloc_tx_ring(alx, alx->qnapi[i]->txq, offset);
+ if (offset < 0) {
+ netdev_err(alx->dev, "Allocation of tx buffer failed!\n");
+ return -ENOMEM;
+ }
+ }
- return 0;
-out_free:
- kfree(alx->txq.bufs);
- kfree(alx->rxq.bufs);
- return -ENOMEM;
-}
-
-static int alx_alloc_rings(struct alx_priv *alx)
-{
- int err;
-
- err = alx_alloc_descriptors(alx);
- if (err)
- return err;
-
- alx->int_mask &= ~ALX_ISR_ALL_QUEUES;
- alx->int_mask |= ALX_ISR_TX_Q0 | ALX_ISR_RX_Q0;
-
- netif_napi_add(alx->dev, &alx->napi, alx_poll, 64);
+ offset = alx_alloc_rx_ring(alx, alx->qnapi[0]->rxq, offset);
+ if (offset < 0) {
+ netdev_err(alx->dev, "Allocation of rx buffer failed!\n");
+ return -ENOMEM;
+ }
alx_reinit_rings(alx);
+
return 0;
}
static void alx_free_rings(struct alx_priv *alx)
{
- netif_napi_del(&alx->napi);
+ int i;
+
alx_free_buffers(alx);
- kfree(alx->txq.bufs);
- kfree(alx->rxq.bufs);
+ for (i = 0; i < alx->num_txq; i++)
+ if (alx->qnapi[i] && alx->qnapi[i]->txq)
+ kfree(alx->qnapi[i]->txq->bufs);
- dma_free_coherent(&alx->hw.pdev->dev,
- alx->descmem.size,
- alx->descmem.virt,
- alx->descmem.dma);
+ if (alx->qnapi[0] && alx->qnapi[0]->rxq)
+ kfree(alx->qnapi[0]->rxq->bufs);
+
+ if (!alx->descmem.virt)
+ dma_free_coherent(&alx->hw.pdev->dev,
+ alx->descmem.size,
+ alx->descmem.virt,
+ alx->descmem.dma);
}
+static void alx_free_napis(struct alx_priv *alx)
+{
+ struct alx_napi *np;
+ int i;
+
+ for (i = 0; i < alx->num_napi; i++) {
+ np = alx->qnapi[i];
+ if (!np)
+ continue;
+
+ netif_napi_del(&np->napi);
+ kfree(np->txq);
+ kfree(np->rxq);
+ kfree(np);
+ alx->qnapi[i] = NULL;
+ }
+}
+
+static const u16 tx_pidx_reg[] = {ALX_TPD_PRI0_PIDX, ALX_TPD_PRI1_PIDX,
+ ALX_TPD_PRI2_PIDX, ALX_TPD_PRI3_PIDX};
+static const u16 tx_cidx_reg[] = {ALX_TPD_PRI0_CIDX, ALX_TPD_PRI1_CIDX,
+ ALX_TPD_PRI2_CIDX, ALX_TPD_PRI3_CIDX};
+static const u32 tx_vect_mask[] = {ALX_ISR_TX_Q0, ALX_ISR_TX_Q1,
+ ALX_ISR_TX_Q2, ALX_ISR_TX_Q3};
+static const u32 rx_vect_mask[] = {ALX_ISR_RX_Q0, ALX_ISR_RX_Q1,
+ ALX_ISR_RX_Q2, ALX_ISR_RX_Q3,
+ ALX_ISR_RX_Q4, ALX_ISR_RX_Q5,
+ ALX_ISR_RX_Q6, ALX_ISR_RX_Q7};
+
+static int alx_alloc_napis(struct alx_priv *alx)
+{
+ struct alx_napi *np;
+ struct alx_rx_queue *rxq;
+ struct alx_tx_queue *txq;
+ int i;
+
+ alx->int_mask &= ~ALX_ISR_ALL_QUEUES;
+
+ /* allocate alx_napi structures */
+ for (i = 0; i < alx->num_napi; i++) {
+ np = kzalloc(sizeof(struct alx_napi), GFP_KERNEL);
+ if (!np)
+ goto err_out;
+
+ np->alx = alx;
+ netif_napi_add(alx->dev, &np->napi, alx_poll, 64);
+ alx->qnapi[i] = np;
+ }
+
+ /* allocate tx queues */
+ for (i = 0; i < alx->num_txq; i++) {
+ np = alx->qnapi[i];
+ txq = kzalloc(sizeof(*txq), GFP_KERNEL);
+ if (!txq)
+ goto err_out;
+
+ np->txq = txq;
+ txq->p_reg = tx_pidx_reg[i];
+ txq->c_reg = tx_cidx_reg[i];
+ txq->queue_idx = i;
+ txq->count = alx->tx_ringsz;
+ txq->netdev = alx->dev;
+ txq->dev = &alx->hw.pdev->dev;
+ np->vec_mask |= tx_vect_mask[i];
+ alx->int_mask |= tx_vect_mask[i];
+ }
+
+ /* allocate rx queues */
+ np = alx->qnapi[0];
+ rxq = kzalloc(sizeof(*rxq), GFP_KERNEL);
+ if (!rxq)
+ goto err_out;
+
+ np->rxq = rxq;
+ rxq->np = alx->qnapi[0];
+ rxq->queue_idx = 0;
+ rxq->count = alx->rx_ringsz;
+ rxq->netdev = alx->dev;
+ rxq->dev = &alx->hw.pdev->dev;
+ np->vec_mask |= rx_vect_mask[0];
+ alx->int_mask |= rx_vect_mask[0];
+
+ return 0;
+
+err_out:
+ netdev_err(alx->dev, "error allocating internal structures\n");
+ alx_free_napis(alx);
+ return -ENOMEM;
+}
+
+static const int txq_vec_mapping_shift[] = {
+ 0, ALX_MSI_MAP_TBL1_TXQ0_SHIFT,
+ 0, ALX_MSI_MAP_TBL1_TXQ1_SHIFT,
+ 1, ALX_MSI_MAP_TBL2_TXQ2_SHIFT,
+ 1, ALX_MSI_MAP_TBL2_TXQ3_SHIFT,
+};
+
static void alx_config_vector_mapping(struct alx_priv *alx)
{
struct alx_hw *hw = &alx->hw;
- u32 tbl = 0;
+ u32 tbl[2] = {0, 0};
+ int i, vector, idx, shift;
if (alx->flags & ALX_FLAG_USING_MSIX) {
- tbl |= 1 << ALX_MSI_MAP_TBL1_TXQ0_SHIFT;
- tbl |= 1 << ALX_MSI_MAP_TBL1_RXQ0_SHIFT;
+ /* tx mappings */
+ for (i = 0, vector = 1; i < alx->num_txq; i++, vector++) {
+ idx = txq_vec_mapping_shift[i * 2];
+ shift = txq_vec_mapping_shift[i * 2 + 1];
+ tbl[idx] |= vector << shift;
+ }
+
+ /* rx mapping */
+ tbl[0] |= 1 << ALX_MSI_MAP_TBL1_RXQ0_SHIFT;
}
- alx_write_mem32(hw, ALX_MSI_MAP_TBL1, tbl);
- alx_write_mem32(hw, ALX_MSI_MAP_TBL2, 0);
+ alx_write_mem32(hw, ALX_MSI_MAP_TBL1, tbl[0]);
+ alx_write_mem32(hw, ALX_MSI_MAP_TBL2, tbl[1]);
alx_write_mem32(hw, ALX_MSI_ID_MAP, 0);
}
static bool alx_enable_msix(struct alx_priv *alx)
{
- int i, err, num_vec = 2;
+ int i, err, num_vec, num_txq, num_rxq;
+
+ num_txq = min_t(int, num_online_cpus(), ALX_MAX_TX_QUEUES);
+ num_rxq = 1;
+ num_vec = max_t(int, num_txq, num_rxq) + 1;
alx->msix_entries = kcalloc(num_vec, sizeof(struct msix_entry),
GFP_KERNEL);
@@ -701,6 +856,10 @@ static bool alx_enable_msix(struct alx_priv *alx)
}
alx->num_vec = num_vec;
+ alx->num_napi = num_vec - 1;
+ alx->num_txq = num_txq;
+ alx->num_rxq = num_rxq;
+
return true;
}
@@ -714,14 +873,29 @@ static int alx_request_msix(struct alx_priv *alx)
if (err)
goto out_err;
- vector++;
- sprintf(alx->irq_lbl, "%s-TxRx-0", netdev->name);
+ for (i = 0; i < alx->num_napi; i++) {
+ struct alx_napi *np = alx->qnapi[i];
- err = request_irq(alx->msix_entries[vector].vector,
- alx_intr_msix_ring, 0, alx->irq_lbl, alx);
+ vector++;
+
+ if (np->txq && np->rxq)
+ sprintf(np->irq_lbl, "%s-TxRx-%u", netdev->name,
+ np->txq->queue_idx);
+ else if (np->txq)
+ sprintf(np->irq_lbl, "%s-tx-%u", netdev->name,
+ np->txq->queue_idx);
+ else if (np->rxq)
+ sprintf(np->irq_lbl, "%s-rx-%u", netdev->name,
+ np->rxq->queue_idx);
+ else
+ sprintf(np->irq_lbl, "%s-unused", netdev->name);
+
+ np->vec_idx = vector;
+ err = request_irq(alx->msix_entries[vector].vector,
+ alx_intr_msix_ring, 0, np->irq_lbl, np);
if (err)
goto out_free;
-
+ }
return 0;
out_free:
@@ -729,7 +903,8 @@ static int alx_request_msix(struct alx_priv *alx)
vector--;
for (i = 0; i < vector; i++)
- free_irq(alx->msix_entries[free_vector++].vector, alx);
+ free_irq(alx->msix_entries[free_vector++].vector,
+ alx->qnapi[i]);
out_err:
return err;
@@ -744,6 +919,9 @@ static void alx_init_intr(struct alx_priv *alx, bool msix)
if (!(alx->flags & ALX_FLAG_USING_MSIX)) {
alx->num_vec = 1;
+ alx->num_napi = 1;
+ alx->num_txq = 1;
+ alx->num_rxq = 1;
if (!pci_enable_msi(alx->hw.pdev))
alx->flags |= ALX_FLAG_USING_MSI;
@@ -799,6 +977,25 @@ static void alx_irq_disable(struct alx_priv *alx)
}
}
+static int alx_realloc_resources(struct alx_priv *alx)
+{
+ int err;
+
+ alx_free_rings(alx);
+ alx_free_napis(alx);
+ alx_disable_advanced_intr(alx);
+
+ err = alx_alloc_napis(alx);
+ if (err)
+ return err;
+
+ err = alx_alloc_rings(alx);
+ if (err)
+ return err;
+
+ return 0;
+}
+
static int alx_request_irq(struct alx_priv *alx)
{
struct pci_dev *pdev = alx->hw.pdev;
@@ -815,8 +1012,9 @@ static int alx_request_irq(struct alx_priv *alx)
goto out;
/* msix request failed, realloc resources */
- alx_disable_advanced_intr(alx);
- alx_init_intr(alx, false);
+ err = alx_realloc_resources(alx);
+ if (err)
+ goto out;
}
if (alx->flags & ALX_FLAG_USING_MSI) {
@@ -845,12 +1043,13 @@ static int alx_request_irq(struct alx_priv *alx)
static void alx_free_irq(struct alx_priv *alx)
{
struct pci_dev *pdev = alx->hw.pdev;
- int i;
+ int i, vector = 0;
if (alx->flags & ALX_FLAG_USING_MSIX) {
- /* we have only 2 vectors without multi queue support */
- for (i = 0; i < 2; i++)
- free_irq(alx->msix_entries[i].vector, alx);
+ free_irq(alx->msix_entries[vector++].vector, alx);
+ for (i = 0; i < alx->num_napi; i++)
+ free_irq(alx->msix_entries[vector++].vector,
+ alx->qnapi[i]);
} else {
free_irq(pdev->irq, alx);
}
@@ -935,11 +1134,14 @@ static netdev_features_t alx_fix_features(struct net_device *netdev,
static void alx_netif_stop(struct alx_priv *alx)
{
+ int i;
+
netif_trans_update(alx->dev);
if (netif_carrier_ok(alx->dev)) {
netif_carrier_off(alx->dev);
netif_tx_disable(alx->dev);
- napi_disable(&alx->napi);
+ for (i = 0; i < alx->num_napi; i++)
+ napi_disable(&alx->qnapi[i]->napi);
}
}
@@ -1008,8 +1210,11 @@ static int alx_change_mtu(struct net_device *netdev, int mtu)
static void alx_netif_start(struct alx_priv *alx)
{
+ int i;
+
netif_tx_wake_all_queues(alx->dev);
- napi_enable(&alx->napi);
+ for (i = 0; i < alx->num_napi; i++)
+ napi_enable(&alx->qnapi[i]->napi);
netif_carrier_on(alx->dev);
}
@@ -1017,21 +1222,28 @@ static int __alx_open(struct alx_priv *alx, bool resume)
{
int err;
- alx_init_intr(alx, msix);
+ alx_init_intr(alx, true);
if (!resume)
netif_carrier_off(alx->dev);
- err = alx_alloc_rings(alx);
+ err = alx_alloc_napis(alx);
if (err)
goto out_disable_adv_intr;
+ err = alx_alloc_rings(alx);
+ if (err)
+ goto out_free_rings;
+
alx_configure(alx);
err = alx_request_irq(alx);
if (err)
goto out_free_rings;
+ netif_set_real_num_tx_queues(alx->dev, alx->num_txq);
+ netif_set_real_num_rx_queues(alx->dev, alx->num_rxq);
+
/* clear old interrupts */
alx_write_mem32(&alx->hw, ALX_ISR, ~(u32)ALX_ISR_DIS);
@@ -1045,6 +1257,7 @@ static int __alx_open(struct alx_priv *alx, bool resume)
out_free_rings:
alx_free_rings(alx);
+ alx_free_napis(alx);
out_disable_adv_intr:
alx_disable_advanced_intr(alx);
return err;
@@ -1055,6 +1268,7 @@ static void __alx_stop(struct alx_priv *alx)
alx_halt(alx);
alx_free_irq(alx);
alx_free_rings(alx);
+ alx_free_napis(alx);
}
static const char *alx_speed_desc(struct alx_hw *hw)
@@ -1237,9 +1451,8 @@ static int alx_tso(struct sk_buff *skb, struct alx_txd *first)
return 1;
}
-static int alx_map_tx_skb(struct alx_priv *alx, struct sk_buff *skb)
+static int alx_map_tx_skb(struct alx_tx_queue *txq, struct sk_buff *skb)
{
- struct alx_tx_queue *txq = &alx->txq;
struct alx_txd *tpd, *first_tpd;
dma_addr_t dma;
int maplen, f, first_idx = txq->write_idx;
@@ -1248,7 +1461,7 @@ static int alx_map_tx_skb(struct alx_priv *alx, struct sk_buff *skb)
tpd = first_tpd;
if (tpd->word1 & (1 << TPD_LSO_V2_SHIFT)) {
- if (++txq->write_idx == alx->tx_ringsz)
+ if (++txq->write_idx == txq->count)
txq->write_idx = 0;
tpd = &txq->tpd[txq->write_idx];
@@ -1258,9 +1471,9 @@ static int alx_map_tx_skb(struct alx_priv *alx, struct sk_buff *skb)
}
maplen = skb_headlen(skb);
- dma = dma_map_single(&alx->hw.pdev->dev, skb->data, maplen,
+ dma = dma_map_single(txq->dev, skb->data, maplen,
DMA_TO_DEVICE);
- if (dma_mapping_error(&alx->hw.pdev->dev, dma))
+ if (dma_mapping_error(txq->dev, dma))
goto err_dma;
dma_unmap_len_set(&txq->bufs[txq->write_idx], size, maplen);
@@ -1274,16 +1487,16 @@ static int alx_map_tx_skb(struct alx_priv *alx, struct sk_buff *skb)
frag = &skb_shinfo(skb)->frags[f];
- if (++txq->write_idx == alx->tx_ringsz)
+ if (++txq->write_idx == txq->count)
txq->write_idx = 0;
tpd = &txq->tpd[txq->write_idx];
tpd->word1 = first_tpd->word1;
maplen = skb_frag_size(frag);
- dma = skb_frag_dma_map(&alx->hw.pdev->dev, frag, 0,
+ dma = skb_frag_dma_map(txq->dev, frag, 0,
maplen, DMA_TO_DEVICE);
- if (dma_mapping_error(&alx->hw.pdev->dev, dma))
+ if (dma_mapping_error(txq->dev, dma))
goto err_dma;
dma_unmap_len_set(&txq->bufs[txq->write_idx], size, maplen);
dma_unmap_addr_set(&txq->bufs[txq->write_idx], dma, dma);
@@ -1296,7 +1509,7 @@ static int alx_map_tx_skb(struct alx_priv *alx, struct sk_buff *skb)
tpd->word1 |= cpu_to_le32(1 << TPD_EOP_SHIFT);
txq->bufs[txq->write_idx].skb = skb;
- if (++txq->write_idx == alx->tx_ringsz)
+ if (++txq->write_idx == txq->count)
txq->write_idx = 0;
return 0;
@@ -1304,23 +1517,24 @@ static int alx_map_tx_skb(struct alx_priv *alx, struct sk_buff *skb)
err_dma:
f = first_idx;
while (f != txq->write_idx) {
- alx_free_txbuf(alx, f);
- if (++f == alx->tx_ringsz)
+ alx_free_txbuf(txq, f);
+ if (++f == txq->count)
f = 0;
}
return -ENOMEM;
}
-static netdev_tx_t alx_start_xmit(struct sk_buff *skb,
- struct net_device *netdev)
+static netdev_tx_t alx_start_xmit_ring(struct sk_buff *skb,
+ struct alx_tx_queue *txq)
{
- struct alx_priv *alx = netdev_priv(netdev);
- struct alx_tx_queue *txq = &alx->txq;
+ struct alx_priv *alx;
struct alx_txd *first;
int tso;
- if (alx_tpd_avail(alx) < alx_tpd_req(skb)) {
- netif_stop_queue(alx->dev);
+ alx = netdev_priv(txq->netdev);
+
+ if (alx_tpd_avail(txq) < alx_tpd_req(skb)) {
+ netif_tx_stop_queue(alx_get_tx_queue(txq));
goto drop;
}
@@ -1333,17 +1547,17 @@ static netdev_tx_t alx_start_xmit(struct sk_buff *skb,
else if (!tso && alx_tx_csum(skb, first))
goto drop;
- if (alx_map_tx_skb(alx, skb) < 0)
+ if (alx_map_tx_skb(txq, skb) < 0)
goto drop;
- netdev_sent_queue(alx->dev, skb->len);
+ netdev_tx_sent_queue(alx_get_tx_queue(txq), skb->len);
/* flush updates before updating hardware */
wmb();
- alx_write_mem16(&alx->hw, ALX_TPD_PRI0_PIDX, txq->write_idx);
+ alx_write_mem16(&alx->hw, txq->p_reg, txq->write_idx);
- if (alx_tpd_avail(alx) < alx->tx_ringsz/8)
- netif_stop_queue(alx->dev);
+ if (alx_tpd_avail(txq) < txq->count / 8)
+ netif_tx_stop_queue(alx_get_tx_queue(txq));
return NETDEV_TX_OK;
@@ -1352,6 +1566,13 @@ static netdev_tx_t alx_start_xmit(struct sk_buff *skb,
return NETDEV_TX_OK;
}
+static netdev_tx_t alx_start_xmit(struct sk_buff *skb,
+ struct net_device *netdev)
+{
+ struct alx_priv *alx = netdev_priv(netdev);
+ return alx_start_xmit_ring(skb, alx_tx_queue_mapping(alx, skb));
+}
+
static void alx_tx_timeout(struct net_device *dev)
{
struct alx_priv *alx = netdev_priv(dev);
@@ -1409,10 +1630,12 @@ static int alx_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
static void alx_poll_controller(struct net_device *netdev)
{
struct alx_priv *alx = netdev_priv(netdev);
+ int i;
if (alx->flags & ALX_FLAG_USING_MSIX) {
alx_intr_msix_misc(0, alx);
- alx_intr_msix_ring(0, alx);
+ for (i = 0; i < alx->num_txq; i++)
+ alx_intr_msix_ring(0, alx->qnapi[i]);
} else if (alx->flags & ALX_FLAG_USING_MSI)
alx_intr_msi(0, alx);
else
@@ -1529,7 +1752,8 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto out_pci_release;
}
- netdev = alloc_etherdev(sizeof(*alx));
+ netdev = alloc_etherdev_mqs(sizeof(*alx),
+ ALX_MAX_TX_QUEUES, 1);
if (!netdev) {
err = -ENOMEM;
goto out_pci_release;
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c
index 872b7ab..cfe86a2 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c
@@ -26,46 +26,52 @@
#include "atl1c.h"
-static int atl1c_get_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int atl1c_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct atl1c_adapter *adapter = netdev_priv(netdev);
struct atl1c_hw *hw = &adapter->hw;
+ u32 supported, advertising;
- ecmd->supported = (SUPPORTED_10baseT_Half |
+ supported = (SUPPORTED_10baseT_Half |
SUPPORTED_10baseT_Full |
SUPPORTED_100baseT_Half |
SUPPORTED_100baseT_Full |
SUPPORTED_Autoneg |
SUPPORTED_TP);
if (hw->link_cap_flags & ATL1C_LINK_CAP_1000M)
- ecmd->supported |= SUPPORTED_1000baseT_Full;
+ supported |= SUPPORTED_1000baseT_Full;
- ecmd->advertising = ADVERTISED_TP;
+ advertising = ADVERTISED_TP;
- ecmd->advertising |= hw->autoneg_advertised;
+ advertising |= hw->autoneg_advertised;
- ecmd->port = PORT_TP;
- ecmd->phy_address = 0;
- ecmd->transceiver = XCVR_INTERNAL;
+ cmd->base.port = PORT_TP;
+ cmd->base.phy_address = 0;
if (adapter->link_speed != SPEED_0) {
- ethtool_cmd_speed_set(ecmd, adapter->link_speed);
+ cmd->base.speed = adapter->link_speed;
if (adapter->link_duplex == FULL_DUPLEX)
- ecmd->duplex = DUPLEX_FULL;
+ cmd->base.duplex = DUPLEX_FULL;
else
- ecmd->duplex = DUPLEX_HALF;
+ cmd->base.duplex = DUPLEX_HALF;
} else {
- ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
- ecmd->duplex = DUPLEX_UNKNOWN;
+ cmd->base.speed = SPEED_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
}
- ecmd->autoneg = AUTONEG_ENABLE;
+ cmd->base.autoneg = AUTONEG_ENABLE;
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
+
return 0;
}
-static int atl1c_set_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int atl1c_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
{
struct atl1c_adapter *adapter = netdev_priv(netdev);
struct atl1c_hw *hw = &adapter->hw;
@@ -74,12 +80,12 @@ static int atl1c_set_settings(struct net_device *netdev,
while (test_and_set_bit(__AT_RESETTING, &adapter->flags))
msleep(1);
- if (ecmd->autoneg == AUTONEG_ENABLE) {
+ if (cmd->base.autoneg == AUTONEG_ENABLE) {
autoneg_advertised = ADVERTISED_Autoneg;
} else {
- u32 speed = ethtool_cmd_speed(ecmd);
+ u32 speed = cmd->base.speed;
if (speed == SPEED_1000) {
- if (ecmd->duplex != DUPLEX_FULL) {
+ if (cmd->base.duplex != DUPLEX_FULL) {
if (netif_msg_link(adapter))
dev_warn(&adapter->pdev->dev,
"1000M half is invalid\n");
@@ -88,12 +94,12 @@ static int atl1c_set_settings(struct net_device *netdev,
}
autoneg_advertised = ADVERTISED_1000baseT_Full;
} else if (speed == SPEED_100) {
- if (ecmd->duplex == DUPLEX_FULL)
+ if (cmd->base.duplex == DUPLEX_FULL)
autoneg_advertised = ADVERTISED_100baseT_Full;
else
autoneg_advertised = ADVERTISED_100baseT_Half;
} else {
- if (ecmd->duplex == DUPLEX_FULL)
+ if (cmd->base.duplex == DUPLEX_FULL)
autoneg_advertised = ADVERTISED_10baseT_Full;
else
autoneg_advertised = ADVERTISED_10baseT_Half;
@@ -284,8 +290,6 @@ static int atl1c_nway_reset(struct net_device *netdev)
}
static const struct ethtool_ops atl1c_ethtool_ops = {
- .get_settings = atl1c_get_settings,
- .set_settings = atl1c_set_settings,
.get_drvinfo = atl1c_get_drvinfo,
.get_regs_len = atl1c_get_regs_len,
.get_regs = atl1c_get_regs,
@@ -297,6 +301,8 @@ static const struct ethtool_ops atl1c_ethtool_ops = {
.get_link = ethtool_op_get_link,
.get_eeprom_len = atl1c_get_eeprom_len,
.get_eeprom = atl1c_get_eeprom,
+ .get_link_ksettings = atl1c_get_link_ksettings,
+ .set_link_ksettings = atl1c_set_link_ksettings,
};
void atl1c_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c b/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c
index 8e3dbd4..cb489e7 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c
@@ -26,73 +26,83 @@
#include "atl1e.h"
-static int atl1e_get_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int atl1e_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct atl1e_adapter *adapter = netdev_priv(netdev);
struct atl1e_hw *hw = &adapter->hw;
+ u32 supported, advertising;
- ecmd->supported = (SUPPORTED_10baseT_Half |
+ supported = (SUPPORTED_10baseT_Half |
SUPPORTED_10baseT_Full |
SUPPORTED_100baseT_Half |
SUPPORTED_100baseT_Full |
SUPPORTED_Autoneg |
SUPPORTED_TP);
if (hw->nic_type == athr_l1e)
- ecmd->supported |= SUPPORTED_1000baseT_Full;
+ supported |= SUPPORTED_1000baseT_Full;
- ecmd->advertising = ADVERTISED_TP;
+ advertising = ADVERTISED_TP;
- ecmd->advertising |= ADVERTISED_Autoneg;
- ecmd->advertising |= hw->autoneg_advertised;
+ advertising |= ADVERTISED_Autoneg;
+ advertising |= hw->autoneg_advertised;
- ecmd->port = PORT_TP;
- ecmd->phy_address = 0;
- ecmd->transceiver = XCVR_INTERNAL;
+ cmd->base.port = PORT_TP;
+ cmd->base.phy_address = 0;
if (adapter->link_speed != SPEED_0) {
- ethtool_cmd_speed_set(ecmd, adapter->link_speed);
+ cmd->base.speed = adapter->link_speed;
if (adapter->link_duplex == FULL_DUPLEX)
- ecmd->duplex = DUPLEX_FULL;
+ cmd->base.duplex = DUPLEX_FULL;
else
- ecmd->duplex = DUPLEX_HALF;
+ cmd->base.duplex = DUPLEX_HALF;
} else {
- ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
- ecmd->duplex = DUPLEX_UNKNOWN;
+ cmd->base.speed = SPEED_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
}
- ecmd->autoneg = AUTONEG_ENABLE;
+ cmd->base.autoneg = AUTONEG_ENABLE;
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
+
return 0;
}
-static int atl1e_set_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int atl1e_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
{
struct atl1e_adapter *adapter = netdev_priv(netdev);
struct atl1e_hw *hw = &adapter->hw;
+ u32 advertising;
+
+ ethtool_convert_link_mode_to_legacy_u32(&advertising,
+ cmd->link_modes.advertising);
while (test_and_set_bit(__AT_RESETTING, &adapter->flags))
msleep(1);
- if (ecmd->autoneg == AUTONEG_ENABLE) {
+ if (cmd->base.autoneg == AUTONEG_ENABLE) {
u16 adv4, adv9;
- if ((ecmd->advertising&ADVERTISE_1000_FULL)) {
+ if (advertising & ADVERTISE_1000_FULL) {
if (hw->nic_type == athr_l1e) {
hw->autoneg_advertised =
- ecmd->advertising & AT_ADV_MASK;
+ advertising & AT_ADV_MASK;
} else {
clear_bit(__AT_RESETTING, &adapter->flags);
return -EINVAL;
}
- } else if (ecmd->advertising&ADVERTISE_1000_HALF) {
+ } else if (advertising & ADVERTISE_1000_HALF) {
clear_bit(__AT_RESETTING, &adapter->flags);
return -EINVAL;
} else {
hw->autoneg_advertised =
- ecmd->advertising & AT_ADV_MASK;
+ advertising & AT_ADV_MASK;
}
- ecmd->advertising = hw->autoneg_advertised |
+ advertising = hw->autoneg_advertised |
ADVERTISED_TP | ADVERTISED_Autoneg;
adv4 = hw->mii_autoneg_adv_reg & ~ADVERTISE_ALL;
@@ -367,8 +377,6 @@ static int atl1e_nway_reset(struct net_device *netdev)
}
static const struct ethtool_ops atl1e_ethtool_ops = {
- .get_settings = atl1e_get_settings,
- .set_settings = atl1e_set_settings,
.get_drvinfo = atl1e_get_drvinfo,
.get_regs_len = atl1e_get_regs_len,
.get_regs = atl1e_get_regs,
@@ -380,6 +388,8 @@ static const struct ethtool_ops atl1e_ethtool_ops = {
.get_eeprom_len = atl1e_get_eeprom_len,
.get_eeprom = atl1e_get_eeprom,
.set_eeprom = atl1e_set_eeprom,
+ .get_link_ksettings = atl1e_get_link_ksettings,
+ .set_link_ksettings = atl1e_set_link_ksettings,
};
void atl1e_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index 9aede18..7dad8e4 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -3214,66 +3214,72 @@ static int atl1_get_sset_count(struct net_device *netdev, int sset)
}
}
-static int atl1_get_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int atl1_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct atl1_adapter *adapter = netdev_priv(netdev);
struct atl1_hw *hw = &adapter->hw;
+ u32 supported, advertising;
- ecmd->supported = (SUPPORTED_10baseT_Half |
+ supported = (SUPPORTED_10baseT_Half |
SUPPORTED_10baseT_Full |
SUPPORTED_100baseT_Half |
SUPPORTED_100baseT_Full |
SUPPORTED_1000baseT_Full |
SUPPORTED_Autoneg | SUPPORTED_TP);
- ecmd->advertising = ADVERTISED_TP;
+ advertising = ADVERTISED_TP;
if (hw->media_type == MEDIA_TYPE_AUTO_SENSOR ||
hw->media_type == MEDIA_TYPE_1000M_FULL) {
- ecmd->advertising |= ADVERTISED_Autoneg;
+ advertising |= ADVERTISED_Autoneg;
if (hw->media_type == MEDIA_TYPE_AUTO_SENSOR) {
- ecmd->advertising |= ADVERTISED_Autoneg;
- ecmd->advertising |=
+ advertising |= ADVERTISED_Autoneg;
+ advertising |=
(ADVERTISED_10baseT_Half |
ADVERTISED_10baseT_Full |
ADVERTISED_100baseT_Half |
ADVERTISED_100baseT_Full |
ADVERTISED_1000baseT_Full);
} else
- ecmd->advertising |= (ADVERTISED_1000baseT_Full);
+ advertising |= (ADVERTISED_1000baseT_Full);
}
- ecmd->port = PORT_TP;
- ecmd->phy_address = 0;
- ecmd->transceiver = XCVR_INTERNAL;
+ cmd->base.port = PORT_TP;
+ cmd->base.phy_address = 0;
if (netif_carrier_ok(adapter->netdev)) {
u16 link_speed, link_duplex;
atl1_get_speed_and_duplex(hw, &link_speed, &link_duplex);
- ethtool_cmd_speed_set(ecmd, link_speed);
+ cmd->base.speed = link_speed;
if (link_duplex == FULL_DUPLEX)
- ecmd->duplex = DUPLEX_FULL;
+ cmd->base.duplex = DUPLEX_FULL;
else
- ecmd->duplex = DUPLEX_HALF;
+ cmd->base.duplex = DUPLEX_HALF;
} else {
- ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
- ecmd->duplex = DUPLEX_UNKNOWN;
+ cmd->base.speed = SPEED_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
}
if (hw->media_type == MEDIA_TYPE_AUTO_SENSOR ||
hw->media_type == MEDIA_TYPE_1000M_FULL)
- ecmd->autoneg = AUTONEG_ENABLE;
+ cmd->base.autoneg = AUTONEG_ENABLE;
else
- ecmd->autoneg = AUTONEG_DISABLE;
+ cmd->base.autoneg = AUTONEG_DISABLE;
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
return 0;
}
-static int atl1_set_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int atl1_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
{
struct atl1_adapter *adapter = netdev_priv(netdev);
struct atl1_hw *hw = &adapter->hw;
u16 phy_data;
int ret_val = 0;
u16 old_media_type = hw->media_type;
+ u32 advertising;
if (netif_running(adapter->netdev)) {
if (netif_msg_link(adapter))
@@ -3282,12 +3288,12 @@ static int atl1_set_settings(struct net_device *netdev,
atl1_down(adapter);
}
- if (ecmd->autoneg == AUTONEG_ENABLE)
+ if (cmd->base.autoneg == AUTONEG_ENABLE)
hw->media_type = MEDIA_TYPE_AUTO_SENSOR;
else {
- u32 speed = ethtool_cmd_speed(ecmd);
+ u32 speed = cmd->base.speed;
if (speed == SPEED_1000) {
- if (ecmd->duplex != DUPLEX_FULL) {
+ if (cmd->base.duplex != DUPLEX_FULL) {
if (netif_msg_link(adapter))
dev_warn(&adapter->pdev->dev,
"1000M half is invalid\n");
@@ -3296,12 +3302,12 @@ static int atl1_set_settings(struct net_device *netdev,
}
hw->media_type = MEDIA_TYPE_1000M_FULL;
} else if (speed == SPEED_100) {
- if (ecmd->duplex == DUPLEX_FULL)
+ if (cmd->base.duplex == DUPLEX_FULL)
hw->media_type = MEDIA_TYPE_100M_FULL;
else
hw->media_type = MEDIA_TYPE_100M_HALF;
} else {
- if (ecmd->duplex == DUPLEX_FULL)
+ if (cmd->base.duplex == DUPLEX_FULL)
hw->media_type = MEDIA_TYPE_10M_FULL;
else
hw->media_type = MEDIA_TYPE_10M_HALF;
@@ -3309,7 +3315,7 @@ static int atl1_set_settings(struct net_device *netdev,
}
switch (hw->media_type) {
case MEDIA_TYPE_AUTO_SENSOR:
- ecmd->advertising =
+ advertising =
ADVERTISED_10baseT_Half |
ADVERTISED_10baseT_Full |
ADVERTISED_100baseT_Half |
@@ -3318,12 +3324,12 @@ static int atl1_set_settings(struct net_device *netdev,
ADVERTISED_Autoneg | ADVERTISED_TP;
break;
case MEDIA_TYPE_1000M_FULL:
- ecmd->advertising =
+ advertising =
ADVERTISED_1000baseT_Full |
ADVERTISED_Autoneg | ADVERTISED_TP;
break;
default:
- ecmd->advertising = 0;
+ advertising = 0;
break;
}
if (atl1_phy_setup_autoneg_adv(hw)) {
@@ -3663,8 +3669,6 @@ static int atl1_nway_reset(struct net_device *netdev)
}
static const struct ethtool_ops atl1_ethtool_ops = {
- .get_settings = atl1_get_settings,
- .set_settings = atl1_set_settings,
.get_drvinfo = atl1_get_drvinfo,
.get_wol = atl1_get_wol,
.set_wol = atl1_set_wol,
@@ -3681,6 +3685,8 @@ static const struct ethtool_ops atl1_ethtool_ops = {
.nway_reset = atl1_nway_reset,
.get_ethtool_stats = atl1_get_ethtool_stats,
.get_sset_count = atl1_get_sset_count,
+ .get_link_ksettings = atl1_get_link_ksettings,
+ .set_link_ksettings = atl1_set_link_ksettings,
};
module_pci_driver(atl1_driver);
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index 6911394..63f2dee 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -1737,81 +1737,87 @@ static void atl2_write_pci_cfg(struct atl2_hw *hw, u32 reg, u16 *value)
pci_write_config_word(adapter->pdev, reg, *value);
}
-static int atl2_get_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int atl2_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *cmd)
{
struct atl2_adapter *adapter = netdev_priv(netdev);
struct atl2_hw *hw = &adapter->hw;
+ u32 supported, advertising;
- ecmd->supported = (SUPPORTED_10baseT_Half |
+ supported = (SUPPORTED_10baseT_Half |
SUPPORTED_10baseT_Full |
SUPPORTED_100baseT_Half |
SUPPORTED_100baseT_Full |
SUPPORTED_Autoneg |
SUPPORTED_TP);
- ecmd->advertising = ADVERTISED_TP;
+ advertising = ADVERTISED_TP;
- ecmd->advertising |= ADVERTISED_Autoneg;
- ecmd->advertising |= hw->autoneg_advertised;
+ advertising |= ADVERTISED_Autoneg;
+ advertising |= hw->autoneg_advertised;
- ecmd->port = PORT_TP;
- ecmd->phy_address = 0;
- ecmd->transceiver = XCVR_INTERNAL;
+ cmd->base.port = PORT_TP;
+ cmd->base.phy_address = 0;
if (adapter->link_speed != SPEED_0) {
- ethtool_cmd_speed_set(ecmd, adapter->link_speed);
+ cmd->base.speed = adapter->link_speed;
if (adapter->link_duplex == FULL_DUPLEX)
- ecmd->duplex = DUPLEX_FULL;
+ cmd->base.duplex = DUPLEX_FULL;
else
- ecmd->duplex = DUPLEX_HALF;
+ cmd->base.duplex = DUPLEX_HALF;
} else {
- ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
- ecmd->duplex = DUPLEX_UNKNOWN;
+ cmd->base.speed = SPEED_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
}
- ecmd->autoneg = AUTONEG_ENABLE;
+ cmd->base.autoneg = AUTONEG_ENABLE;
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
+
return 0;
}
-static int atl2_set_settings(struct net_device *netdev,
- struct ethtool_cmd *ecmd)
+static int atl2_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *cmd)
{
struct atl2_adapter *adapter = netdev_priv(netdev);
struct atl2_hw *hw = &adapter->hw;
+ u32 advertising;
+
+ ethtool_convert_link_mode_to_legacy_u32(&advertising,
+ cmd->link_modes.advertising);
while (test_and_set_bit(__ATL2_RESETTING, &adapter->flags))
msleep(1);
- if (ecmd->autoneg == AUTONEG_ENABLE) {
+ if (cmd->base.autoneg == AUTONEG_ENABLE) {
#define MY_ADV_MASK (ADVERTISE_10_HALF | \
ADVERTISE_10_FULL | \
ADVERTISE_100_HALF| \
ADVERTISE_100_FULL)
- if ((ecmd->advertising & MY_ADV_MASK) == MY_ADV_MASK) {
+ if ((advertising & MY_ADV_MASK) == MY_ADV_MASK) {
hw->MediaType = MEDIA_TYPE_AUTO_SENSOR;
hw->autoneg_advertised = MY_ADV_MASK;
- } else if ((ecmd->advertising & MY_ADV_MASK) ==
- ADVERTISE_100_FULL) {
+ } else if ((advertising & MY_ADV_MASK) == ADVERTISE_100_FULL) {
hw->MediaType = MEDIA_TYPE_100M_FULL;
hw->autoneg_advertised = ADVERTISE_100_FULL;
- } else if ((ecmd->advertising & MY_ADV_MASK) ==
- ADVERTISE_100_HALF) {
+ } else if ((advertising & MY_ADV_MASK) == ADVERTISE_100_HALF) {
hw->MediaType = MEDIA_TYPE_100M_HALF;
hw->autoneg_advertised = ADVERTISE_100_HALF;
- } else if ((ecmd->advertising & MY_ADV_MASK) ==
- ADVERTISE_10_FULL) {
+ } else if ((advertising & MY_ADV_MASK) == ADVERTISE_10_FULL) {
hw->MediaType = MEDIA_TYPE_10M_FULL;
hw->autoneg_advertised = ADVERTISE_10_FULL;
- } else if ((ecmd->advertising & MY_ADV_MASK) ==
- ADVERTISE_10_HALF) {
+ } else if ((advertising & MY_ADV_MASK) == ADVERTISE_10_HALF) {
hw->MediaType = MEDIA_TYPE_10M_HALF;
hw->autoneg_advertised = ADVERTISE_10_HALF;
} else {
clear_bit(__ATL2_RESETTING, &adapter->flags);
return -EINVAL;
}
- ecmd->advertising = hw->autoneg_advertised |
+ advertising = hw->autoneg_advertised |
ADVERTISED_TP | ADVERTISED_Autoneg;
} else {
clear_bit(__ATL2_RESETTING, &adapter->flags);
@@ -2080,8 +2086,6 @@ static int atl2_nway_reset(struct net_device *netdev)
}
static const struct ethtool_ops atl2_ethtool_ops = {
- .get_settings = atl2_get_settings,
- .set_settings = atl2_set_settings,
.get_drvinfo = atl2_get_drvinfo,
.get_regs_len = atl2_get_regs_len,
.get_regs = atl2_get_regs,
@@ -2094,6 +2098,8 @@ static const struct ethtool_ops atl2_ethtool_ops = {
.get_eeprom_len = atl2_get_eeprom_len,
.get_eeprom = atl2_get_eeprom,
.set_eeprom = atl2_set_eeprom,
+ .get_link_ksettings = atl2_get_link_ksettings,
+ .set_link_ksettings = atl2_set_link_ksettings,
};
#define LBYTESWAP(a) ((((a) & 0x00ff00ff) << 8) | \
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index 99c4055..07ff649 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -1037,16 +1037,6 @@ static const struct net_device_ops nb8800_netdev_ops = {
.ndo_validate_addr = eth_validate_addr,
};
-static int nb8800_nway_reset(struct net_device *dev)
-{
- struct phy_device *phydev = dev->phydev;
-
- if (!phydev)
- return -ENODEV;
-
- return genphy_restart_aneg(phydev);
-}
-
static void nb8800_get_pauseparam(struct net_device *dev,
struct ethtool_pauseparam *pp)
{
@@ -1165,7 +1155,7 @@ static void nb8800_get_ethtool_stats(struct net_device *dev,
}
static const struct ethtool_ops nb8800_ethtool_ops = {
- .nway_reset = nb8800_nway_reset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_link = ethtool_op_get_link,
.get_pauseparam = nb8800_get_pauseparam,
.set_pauseparam = nb8800_set_pauseparam,
@@ -1359,6 +1349,7 @@ static const struct of_device_id nb8800_dt_ids[] = {
},
{ }
};
+MODULE_DEVICE_TABLE(of, nb8800_dt_ids);
static int nb8800_probe(struct platform_device *pdev)
{
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 7e513ca..3b14d51 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -1126,7 +1126,8 @@ static int bcm_enet_open(struct net_device *dev)
free_irq(dev->irq, dev);
out_phy_disconnect:
- phy_disconnect(phydev);
+ if (priv->has_phy)
+ phy_disconnect(phydev);
return ret;
}
@@ -1433,11 +1434,8 @@ static int bcm_enet_nway_reset(struct net_device *dev)
struct bcm_enet_priv *priv;
priv = netdev_priv(dev);
- if (priv->has_phy) {
- if (!dev->phydev)
- return -ENODEV;
- return genphy_restart_aneg(dev->phydev);
- }
+ if (priv->has_phy)
+ return phy_ethtool_nway_reset(dev);
return -EOPNOTSUPP;
}
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c
index c16ec3a..4a4ffc0 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c
@@ -80,6 +80,24 @@ static void bcma_bgmac_cmn_maskset32(struct bgmac *bgmac, u16 offset, u32 mask,
bcma_maskset32(bgmac->bcma.cmn, offset, mask, set);
}
+static int bcma_phy_connect(struct bgmac *bgmac)
+{
+ struct phy_device *phy_dev;
+ char bus_id[MII_BUS_ID_SIZE + 3];
+
+ /* Connect to the PHY */
+ snprintf(bus_id, sizeof(bus_id), PHY_ID_FMT, bgmac->mii_bus->id,
+ bgmac->phyaddr);
+ phy_dev = phy_connect(bgmac->net_dev, bus_id, bgmac_adjust_link,
+ PHY_INTERFACE_MODE_MII);
+ if (IS_ERR(phy_dev)) {
+ dev_err(bgmac->dev, "PHY connection failed\n");
+ return PTR_ERR(phy_dev);
+ }
+
+ return 0;
+}
+
static const struct bcma_device_id bgmac_bcma_tbl[] = {
BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_4706_MAC_GBIT,
BCMA_ANY_REV, BCMA_ANY_CLASS),
@@ -275,6 +293,10 @@ static int bgmac_probe(struct bcma_device *core)
bgmac->cco_ctl_maskset = bcma_bgmac_cco_ctl_maskset;
bgmac->get_bus_clock = bcma_bgmac_get_bus_clock;
bgmac->cmn_maskset32 = bcma_bgmac_cmn_maskset32;
+ if (bgmac->mii_bus)
+ bgmac->phy_connect = bcma_phy_connect;
+ else
+ bgmac->phy_connect = bgmac_phy_connect_direct;
err = bgmac_enet_probe(bgmac);
if (err)
diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c
index be52f27..6f736c1 100644
--- a/drivers/net/ethernet/broadcom/bgmac-platform.c
+++ b/drivers/net/ethernet/broadcom/bgmac-platform.c
@@ -14,11 +14,21 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/bcma/bcma.h>
+#include <linux/brcmphy.h>
#include <linux/etherdevice.h>
#include <linux/of_address.h>
+#include <linux/of_mdio.h>
#include <linux/of_net.h>
#include "bgmac.h"
+#define NICPM_IOMUX_CTRL 0x00000008
+
+#define NICPM_IOMUX_CTRL_INIT_VAL 0x3196e000
+#define NICPM_IOMUX_CTRL_SPD_SHIFT 10
+#define NICPM_IOMUX_CTRL_SPD_10M 0
+#define NICPM_IOMUX_CTRL_SPD_100M 1
+#define NICPM_IOMUX_CTRL_SPD_1000M 2
+
static u32 platform_bgmac_read(struct bgmac *bgmac, u16 offset)
{
return readl(bgmac->plat.base + offset);
@@ -86,6 +96,54 @@ static void platform_bgmac_cmn_maskset32(struct bgmac *bgmac, u16 offset,
WARN_ON(1);
}
+static void bgmac_nicpm_speed_set(struct net_device *net_dev)
+{
+ struct bgmac *bgmac = netdev_priv(net_dev);
+ u32 val;
+
+ if (!bgmac->plat.nicpm_base)
+ return;
+
+ val = NICPM_IOMUX_CTRL_INIT_VAL;
+ switch (bgmac->net_dev->phydev->speed) {
+ default:
+ netdev_err(net_dev, "Unsupported speed. Defaulting to 1000Mb\n");
+ case SPEED_1000:
+ val |= NICPM_IOMUX_CTRL_SPD_1000M << NICPM_IOMUX_CTRL_SPD_SHIFT;
+ break;
+ case SPEED_100:
+ val |= NICPM_IOMUX_CTRL_SPD_100M << NICPM_IOMUX_CTRL_SPD_SHIFT;
+ break;
+ case SPEED_10:
+ val |= NICPM_IOMUX_CTRL_SPD_10M << NICPM_IOMUX_CTRL_SPD_SHIFT;
+ break;
+ }
+
+ writel(val, bgmac->plat.nicpm_base + NICPM_IOMUX_CTRL);
+
+ bgmac_adjust_link(bgmac->net_dev);
+}
+
+static int platform_phy_connect(struct bgmac *bgmac)
+{
+ struct phy_device *phy_dev;
+
+ if (bgmac->plat.nicpm_base)
+ phy_dev = of_phy_get_and_connect(bgmac->net_dev,
+ bgmac->dev->of_node,
+ bgmac_nicpm_speed_set);
+ else
+ phy_dev = of_phy_get_and_connect(bgmac->net_dev,
+ bgmac->dev->of_node,
+ bgmac_adjust_link);
+ if (!phy_dev) {
+ dev_err(bgmac->dev, "PHY connection failed\n");
+ return -ENODEV;
+ }
+
+ return 0;
+}
+
static int bgmac_probe(struct platform_device *pdev)
{
struct device_node *np = pdev->dev.of_node;
@@ -102,7 +160,6 @@ static int bgmac_probe(struct platform_device *pdev)
/* Set the features of the 4707 family */
bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
bgmac->feature_flags |= BGMAC_FEAT_NO_RESET;
- bgmac->feature_flags |= BGMAC_FEAT_FORCE_SPEED_2500;
bgmac->feature_flags |= BGMAC_FEAT_CMDCFG_SR_REV4;
bgmac->feature_flags |= BGMAC_FEAT_TX_MASK_SETUP;
bgmac->feature_flags |= BGMAC_FEAT_RX_MASK_SETUP;
@@ -142,6 +199,14 @@ static int bgmac_probe(struct platform_device *pdev)
if (IS_ERR(bgmac->plat.idm_base))
return PTR_ERR(bgmac->plat.idm_base);
+ regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nicpm_base");
+ if (regs) {
+ bgmac->plat.nicpm_base = devm_ioremap_resource(&pdev->dev,
+ regs);
+ if (IS_ERR(bgmac->plat.nicpm_base))
+ return PTR_ERR(bgmac->plat.nicpm_base);
+ }
+
bgmac->read = platform_bgmac_read;
bgmac->write = platform_bgmac_write;
bgmac->idm_read = platform_bgmac_idm_read;
@@ -151,6 +216,12 @@ static int bgmac_probe(struct platform_device *pdev)
bgmac->cco_ctl_maskset = platform_bgmac_cco_ctl_maskset;
bgmac->get_bus_clock = platform_bgmac_get_bus_clock;
bgmac->cmn_maskset32 = platform_bgmac_cmn_maskset32;
+ if (of_parse_phandle(np, "phy-handle", 0)) {
+ bgmac->phy_connect = platform_phy_connect;
+ } else {
+ bgmac->phy_connect = bgmac_phy_connect_direct;
+ bgmac->feature_flags |= BGMAC_FEAT_FORCE_SPEED_2500;
+ }
return bgmac_enet_probe(bgmac);
}
@@ -167,6 +238,7 @@ static int bgmac_remove(struct platform_device *pdev)
static const struct of_device_id bgmac_of_enet_match[] = {
{.compatible = "brcm,amac",},
{.compatible = "brcm,nsp-amac",},
+ {.compatible = "brcm,ns2-amac",},
{},
};
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 856379c..0e066dc6 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -307,6 +307,10 @@ static void bgmac_dma_rx_enable(struct bgmac *bgmac,
u32 ctl;
ctl = bgmac_read(bgmac, ring->mmio_base + BGMAC_DMA_RX_CTL);
+
+ /* preserve ONLY bits 16-17 from current hardware value */
+ ctl &= BGMAC_DMA_RX_ADDREXT_MASK;
+
if (bgmac->feature_flags & BGMAC_FEAT_RX_MASK_SETUP) {
ctl &= ~BGMAC_DMA_RX_BL_MASK;
ctl |= BGMAC_DMA_RX_BL_128 << BGMAC_DMA_RX_BL_SHIFT;
@@ -317,7 +321,6 @@ static void bgmac_dma_rx_enable(struct bgmac *bgmac,
ctl &= ~BGMAC_DMA_RX_PT_MASK;
ctl |= BGMAC_DMA_RX_PT_1 << BGMAC_DMA_RX_PT_SHIFT;
}
- ctl &= BGMAC_DMA_RX_ADDREXT_MASK;
ctl |= BGMAC_DMA_RX_ENABLE;
ctl |= BGMAC_DMA_RX_PARITY_DISABLE;
ctl |= BGMAC_DMA_RX_OVERFLOW_CONT;
@@ -1046,9 +1049,9 @@ static void bgmac_enable(struct bgmac *bgmac)
mode = (bgmac_read(bgmac, BGMAC_DEV_STATUS) & BGMAC_DS_MM_MASK) >>
BGMAC_DS_MM_SHIFT;
- if (!(bgmac->feature_flags & BGMAC_FEAT_CLKCTLST) || mode != 0)
+ if (bgmac->feature_flags & BGMAC_FEAT_CLKCTLST || mode != 0)
bgmac_set(bgmac, BCMA_CLKCTLST, BCMA_CLKCTLST_FORCEHT);
- if (bgmac->feature_flags & BGMAC_FEAT_CLKCTLST && mode == 2)
+ if (!(bgmac->feature_flags & BGMAC_FEAT_CLKCTLST) && mode == 2)
bgmac_cco_ctl_maskset(bgmac, 1, ~0,
BGMAC_CHIPCTL_1_RXC_DLL_BYPASS);
@@ -1082,6 +1085,9 @@ static void bgmac_enable(struct bgmac *bgmac)
/* http://bcm-v4.sipsolutions.net/mac-gbit/gmac/chipinit */
static void bgmac_chip_init(struct bgmac *bgmac)
{
+ /* Clear any erroneously pending interrupts */
+ bgmac_write(bgmac, BGMAC_INT_STATUS, ~0);
+
/* 1 interrupt per received frame */
bgmac_write(bgmac, BGMAC_INT_RECV_LAZY, 1 << BGMAC_IRL_FC_SHIFT);
@@ -1388,7 +1394,7 @@ static const struct ethtool_ops bgmac_ethtool_ops = {
* MII
**************************************************/
-static void bgmac_adjust_link(struct net_device *net_dev)
+void bgmac_adjust_link(struct net_device *net_dev)
{
struct bgmac *bgmac = netdev_priv(net_dev);
struct phy_device *phy_dev = net_dev->phydev;
@@ -1411,8 +1417,9 @@ static void bgmac_adjust_link(struct net_device *net_dev)
phy_print_status(phy_dev);
}
}
+EXPORT_SYMBOL_GPL(bgmac_adjust_link);
-static int bgmac_phy_connect_direct(struct bgmac *bgmac)
+int bgmac_phy_connect_direct(struct bgmac *bgmac)
{
struct fixed_phy_status fphy_status = {
.link = 1,
@@ -1437,24 +1444,7 @@ static int bgmac_phy_connect_direct(struct bgmac *bgmac)
return err;
}
-
-static int bgmac_phy_connect(struct bgmac *bgmac)
-{
- struct phy_device *phy_dev;
- char bus_id[MII_BUS_ID_SIZE + 3];
-
- /* Connect to the PHY */
- snprintf(bus_id, sizeof(bus_id), PHY_ID_FMT, bgmac->mii_bus->id,
- bgmac->phyaddr);
- phy_dev = phy_connect(bgmac->net_dev, bus_id, &bgmac_adjust_link,
- PHY_INTERFACE_MODE_MII);
- if (IS_ERR(phy_dev)) {
- dev_err(bgmac->dev, "PHY connecton failed\n");
- return PTR_ERR(phy_dev);
- }
-
- return 0;
-}
+EXPORT_SYMBOL_GPL(bgmac_phy_connect_direct);
int bgmac_enet_probe(struct bgmac *info)
{
@@ -1507,10 +1497,7 @@ int bgmac_enet_probe(struct bgmac *info)
netif_napi_add(net_dev, &bgmac->napi, bgmac_poll, BGMAC_WEIGHT);
- if (!bgmac->mii_bus)
- err = bgmac_phy_connect_direct(bgmac);
- else
- err = bgmac_phy_connect(bgmac);
+ err = bgmac_phy_connect(bgmac);
if (err) {
dev_err(bgmac->dev, "Cannot connect to phy\n");
goto err_dma_free;
diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h
index 80836b4..71f493f 100644
--- a/drivers/net/ethernet/broadcom/bgmac.h
+++ b/drivers/net/ethernet/broadcom/bgmac.h
@@ -463,6 +463,7 @@ struct bgmac {
struct {
void *base;
void *idm_base;
+ void *nicpm_base;
} plat;
struct {
struct bcma_device *core;
@@ -513,10 +514,13 @@ struct bgmac {
u32 (*get_bus_clock)(struct bgmac *bgmac);
void (*cmn_maskset32)(struct bgmac *bgmac, u16 offset, u32 mask,
u32 set);
+ int (*phy_connect)(struct bgmac *bgmac);
};
int bgmac_enet_probe(struct bgmac *info);
void bgmac_enet_remove(struct bgmac *bgmac);
+void bgmac_adjust_link(struct net_device *net_dev);
+int bgmac_phy_connect_direct(struct bgmac *bgmac);
struct mii_bus *bcma_mdio_mii_register(struct bcma_device *core, u8 phyaddr);
void bcma_mdio_mii_unregister(struct mii_bus *mii_bus);
@@ -583,4 +587,9 @@ static inline void bgmac_set(struct bgmac *bgmac, u16 offset, u32 set)
{
bgmac_maskset(bgmac, offset, ~0, set);
}
+
+static inline int bgmac_phy_connect(struct bgmac *bgmac)
+{
+ return bgmac->phy_connect(bgmac);
+}
#endif /* _BGMAC_H */
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index 2a5df3f..9960a92 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -49,6 +49,7 @@
#include <linux/firmware.h>
#include <linux/log2.h>
#include <linux/aer.h>
+#include <linux/crash_dump.h>
#if IS_ENABLED(CONFIG_CNIC)
#define BCM_CNIC 1
@@ -271,22 +272,25 @@ static inline u32 bnx2_tx_avail(struct bnx2 *bp, struct bnx2_tx_ring_info *txr)
static u32
bnx2_reg_rd_ind(struct bnx2 *bp, u32 offset)
{
+ unsigned long flags;
u32 val;
- spin_lock_bh(&bp->indirect_lock);
+ spin_lock_irqsave(&bp->indirect_lock, flags);
BNX2_WR(bp, BNX2_PCICFG_REG_WINDOW_ADDRESS, offset);
val = BNX2_RD(bp, BNX2_PCICFG_REG_WINDOW);
- spin_unlock_bh(&bp->indirect_lock);
+ spin_unlock_irqrestore(&bp->indirect_lock, flags);
return val;
}
static void
bnx2_reg_wr_ind(struct bnx2 *bp, u32 offset, u32 val)
{
- spin_lock_bh(&bp->indirect_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&bp->indirect_lock, flags);
BNX2_WR(bp, BNX2_PCICFG_REG_WINDOW_ADDRESS, offset);
BNX2_WR(bp, BNX2_PCICFG_REG_WINDOW, val);
- spin_unlock_bh(&bp->indirect_lock);
+ spin_unlock_irqrestore(&bp->indirect_lock, flags);
}
static void
@@ -304,8 +308,10 @@ bnx2_shmem_rd(struct bnx2 *bp, u32 offset)
static void
bnx2_ctx_wr(struct bnx2 *bp, u32 cid_addr, u32 offset, u32 val)
{
+ unsigned long flags;
+
offset += cid_addr;
- spin_lock_bh(&bp->indirect_lock);
+ spin_lock_irqsave(&bp->indirect_lock, flags);
if (BNX2_CHIP(bp) == BNX2_CHIP_5709) {
int i;
@@ -322,7 +328,7 @@ bnx2_ctx_wr(struct bnx2 *bp, u32 cid_addr, u32 offset, u32 val)
BNX2_WR(bp, BNX2_CTX_DATA_ADR, offset);
BNX2_WR(bp, BNX2_CTX_DATA, val);
}
- spin_unlock_bh(&bp->indirect_lock);
+ spin_unlock_irqrestore(&bp->indirect_lock, flags);
}
#ifdef BCM_CNIC
@@ -4759,15 +4765,16 @@ bnx2_setup_msix_tbl(struct bnx2 *bp)
BNX2_WR(bp, BNX2_PCI_GRC_WINDOW3_ADDR, BNX2_MSIX_PBA_ADDR);
}
-static int
-bnx2_reset_chip(struct bnx2 *bp, u32 reset_code)
+static void
+bnx2_wait_dma_complete(struct bnx2 *bp)
{
u32 val;
- int i, rc = 0;
- u8 old_port;
+ int i;
- /* Wait for the current PCI transaction to complete before
- * issuing a reset. */
+ /*
+ * Wait for the current PCI transaction to complete before
+ * issuing a reset.
+ */
if ((BNX2_CHIP(bp) == BNX2_CHIP_5706) ||
(BNX2_CHIP(bp) == BNX2_CHIP_5708)) {
BNX2_WR(bp, BNX2_MISC_ENABLE_CLR_BITS,
@@ -4791,6 +4798,21 @@ bnx2_reset_chip(struct bnx2 *bp, u32 reset_code)
}
}
+ return;
+}
+
+
+static int
+bnx2_reset_chip(struct bnx2 *bp, u32 reset_code)
+{
+ u32 val;
+ int i, rc = 0;
+ u8 old_port;
+
+ /* Wait for the current PCI transaction to complete before
+ * issuing a reset. */
+ bnx2_wait_dma_complete(bp);
+
/* Wait for the firmware to tell us it is ok to issue a reset. */
bnx2_fw_sync(bp, BNX2_DRV_MSG_DATA_WAIT0 | reset_code, 1, 1);
@@ -6356,6 +6378,10 @@ bnx2_open(struct net_device *dev)
struct bnx2 *bp = netdev_priv(dev);
int rc;
+ rc = bnx2_request_firmware(bp);
+ if (rc < 0)
+ goto out;
+
netif_carrier_off(dev);
bnx2_disable_int(bp);
@@ -6424,6 +6450,7 @@ bnx2_open(struct net_device *dev)
bnx2_free_irq(bp);
bnx2_free_mem(bp);
bnx2_del_napi(bp);
+ bnx2_release_firmware(bp);
goto out;
}
@@ -6877,12 +6904,14 @@ bnx2_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *net_stats)
/* All ethtool functions called with rtnl_lock */
static int
-bnx2_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+bnx2_get_link_ksettings(struct net_device *dev,
+ struct ethtool_link_ksettings *cmd)
{
struct bnx2 *bp = netdev_priv(dev);
int support_serdes = 0, support_copper = 0;
+ u32 supported, advertising;
- cmd->supported = SUPPORTED_Autoneg;
+ supported = SUPPORTED_Autoneg;
if (bp->phy_flags & BNX2_PHY_FLAG_REMOTE_PHY_CAP) {
support_serdes = 1;
support_copper = 1;
@@ -6892,56 +6921,59 @@ bnx2_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
support_copper = 1;
if (support_serdes) {
- cmd->supported |= SUPPORTED_1000baseT_Full |
+ supported |= SUPPORTED_1000baseT_Full |
SUPPORTED_FIBRE;
if (bp->phy_flags & BNX2_PHY_FLAG_2_5G_CAPABLE)
- cmd->supported |= SUPPORTED_2500baseX_Full;
-
+ supported |= SUPPORTED_2500baseX_Full;
}
if (support_copper) {
- cmd->supported |= SUPPORTED_10baseT_Half |
+ supported |= SUPPORTED_10baseT_Half |
SUPPORTED_10baseT_Full |
SUPPORTED_100baseT_Half |
SUPPORTED_100baseT_Full |
SUPPORTED_1000baseT_Full |
SUPPORTED_TP;
-
}
spin_lock_bh(&bp->phy_lock);
- cmd->port = bp->phy_port;
- cmd->advertising = bp->advertising;
+ cmd->base.port = bp->phy_port;
+ advertising = bp->advertising;
if (bp->autoneg & AUTONEG_SPEED) {
- cmd->autoneg = AUTONEG_ENABLE;
+ cmd->base.autoneg = AUTONEG_ENABLE;
} else {
- cmd->autoneg = AUTONEG_DISABLE;
+ cmd->base.autoneg = AUTONEG_DISABLE;
}
if (netif_carrier_ok(dev)) {
- ethtool_cmd_speed_set(cmd, bp->line_speed);
- cmd->duplex = bp->duplex;
+ cmd->base.speed = bp->line_speed;
+ cmd->base.duplex = bp->duplex;
if (!(bp->phy_flags & BNX2_PHY_FLAG_SERDES)) {
if (bp->phy_flags & BNX2_PHY_FLAG_MDIX)
- cmd->eth_tp_mdix = ETH_TP_MDI_X;
+ cmd->base.eth_tp_mdix = ETH_TP_MDI_X;
else
- cmd->eth_tp_mdix = ETH_TP_MDI;
+ cmd->base.eth_tp_mdix = ETH_TP_MDI;
}
}
else {
- ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN);
- cmd->duplex = DUPLEX_UNKNOWN;
+ cmd->base.speed = SPEED_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
}
spin_unlock_bh(&bp->phy_lock);
- cmd->transceiver = XCVR_INTERNAL;
- cmd->phy_address = bp->phy_addr;
+ cmd->base.phy_address = bp->phy_addr;
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
return 0;
}
static int
-bnx2_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+bnx2_set_link_ksettings(struct net_device *dev,
+ const struct ethtool_link_ksettings *cmd)
{
struct bnx2 *bp = netdev_priv(dev);
u8 autoneg = bp->autoneg;
@@ -6952,24 +6984,26 @@ bnx2_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
spin_lock_bh(&bp->phy_lock);
- if (cmd->port != PORT_TP && cmd->port != PORT_FIBRE)
+ if (cmd->base.port != PORT_TP && cmd->base.port != PORT_FIBRE)
goto err_out_unlock;
- if (cmd->port != bp->phy_port &&
+ if (cmd->base.port != bp->phy_port &&
!(bp->phy_flags & BNX2_PHY_FLAG_REMOTE_PHY_CAP))
goto err_out_unlock;
/* If device is down, we can store the settings only if the user
* is setting the currently active port.
*/
- if (!netif_running(dev) && cmd->port != bp->phy_port)
+ if (!netif_running(dev) && cmd->base.port != bp->phy_port)
goto err_out_unlock;
- if (cmd->autoneg == AUTONEG_ENABLE) {
+ if (cmd->base.autoneg == AUTONEG_ENABLE) {
autoneg |= AUTONEG_SPEED;
- advertising = cmd->advertising;
- if (cmd->port == PORT_TP) {
+ ethtool_convert_link_mode_to_legacy_u32(
+ &advertising, cmd->link_modes.advertising);
+
+ if (cmd->base.port == PORT_TP) {
advertising &= ETHTOOL_ALL_COPPER_SPEED;
if (!advertising)
advertising = ETHTOOL_ALL_COPPER_SPEED;
@@ -6981,11 +7015,12 @@ bnx2_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
advertising |= ADVERTISED_Autoneg;
}
else {
- u32 speed = ethtool_cmd_speed(cmd);
- if (cmd->port == PORT_FIBRE) {
+ u32 speed = cmd->base.speed;
+
+ if (cmd->base.port == PORT_FIBRE) {
if ((speed != SPEED_1000 &&
speed != SPEED_2500) ||
- (cmd->duplex != DUPLEX_FULL))
+ (cmd->base.duplex != DUPLEX_FULL))
goto err_out_unlock;
if (speed == SPEED_2500 &&
@@ -6996,7 +7031,7 @@ bnx2_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
autoneg &= ~AUTONEG_SPEED;
req_line_speed = speed;
- req_duplex = cmd->duplex;
+ req_duplex = cmd->base.duplex;
advertising = 0;
}
@@ -7010,7 +7045,7 @@ bnx2_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
* brought up.
*/
if (netif_running(dev))
- err = bnx2_setup_phy(bp, cmd->port);
+ err = bnx2_setup_phy(bp, cmd->base.port);
err_out_unlock:
spin_unlock_bh(&bp->phy_lock);
@@ -7795,8 +7830,6 @@ static int bnx2_set_channels(struct net_device *dev,
}
static const struct ethtool_ops bnx2_ethtool_ops = {
- .get_settings = bnx2_get_settings,
- .set_settings = bnx2_set_settings,
.get_drvinfo = bnx2_get_drvinfo,
.get_regs_len = bnx2_get_regs_len,
.get_regs = bnx2_get_regs,
@@ -7820,6 +7853,8 @@ static const struct ethtool_ops bnx2_ethtool_ops = {
.get_sset_count = bnx2_get_sset_count,
.get_channels = bnx2_get_channels,
.set_channels = bnx2_set_channels,
+ .get_link_ksettings = bnx2_get_link_ksettings,
+ .set_link_ksettings = bnx2_set_link_ksettings,
};
/* Called with rtnl_lock */
@@ -8566,12 +8601,15 @@ bnx2_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
pci_set_drvdata(pdev, dev);
- rc = bnx2_request_firmware(bp);
- if (rc < 0)
- goto error;
+ /*
+ * In-flight DMA from 1st kernel could continue going in kdump kernel.
+ * New io-page table has been created before bnx2 does reset at open stage.
+ * We have to wait for the in-flight DMA to complete to avoid it look up
+ * into the newly created io-page table.
+ */
+ if (is_kdump_kernel())
+ bnx2_wait_dma_complete(bp);
-
- bnx2_reset_chip(bp, BNX2_DRV_MSG_CODE_RESET);
memcpy(dev->dev_addr, bp->mac_addr, ETH_ALEN);
dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG |
@@ -8606,7 +8644,6 @@ bnx2_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
return 0;
error:
- bnx2_release_firmware(bp);
pci_iounmap(pdev, bp->regview);
pci_release_regions(pdev);
pci_disable_device(pdev);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index ed42c10..3fd36b4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -3248,13 +3248,14 @@ static int bnx2x_poll(struct napi_struct *napi, int budget)
rmb();
if (!(bnx2x_has_rx_work(fp) || bnx2x_has_tx_work(fp))) {
- napi_complete(napi);
- /* Re-enable interrupts */
- DP(NETIF_MSG_RX_STATUS,
- "Update index to %d\n", fp->fp_hc_idx);
- bnx2x_ack_sb(bp, fp->igu_sb_id, USTORM_ID,
- le16_to_cpu(fp->fp_hc_idx),
- IGU_INT_ENABLE, 1);
+ if (napi_complete_done(napi, rx_work_done)) {
+ /* Re-enable interrupts */
+ DP(NETIF_MSG_RX_STATUS,
+ "Update index to %d\n", fp->fp_hc_idx);
+ bnx2x_ack_sb(bp, fp->igu_sb_id, USTORM_ID,
+ le16_to_cpu(fp->fp_hc_idx),
+ IGU_INT_ENABLE, 1);
+ }
} else {
rx_work_done = budget;
}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 67b6180..ab990da 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -15244,7 +15244,7 @@ static void bnx2x_init_cyclecounter(struct bnx2x *bp)
memset(&bp->cyclecounter, 0, sizeof(bp->cyclecounter));
bp->cyclecounter.read = bnx2x_cyclecounter_read;
bp->cyclecounter.mask = CYCLECOUNTER_MASK(64);
- bp->cyclecounter.shift = 1;
+ bp->cyclecounter.shift = 0;
bp->cyclecounter.mult = 1;
}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index a042da1..7401c90 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1499,6 +1499,7 @@ static int bnxt_async_event_process(struct bnxt *bp,
netdev_warn(bp->dev, "Link speed %d no longer supported\n",
speed);
}
+ set_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT, &bp->sp_event);
/* fall thru */
}
case HWRM_ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE:
@@ -3424,13 +3425,7 @@ static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss)
bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_RSS_CFG, -1, -1);
if (set_rss) {
- vnic->hash_type = VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 |
- VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 |
- VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 |
- VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6;
-
- req.hash_type = cpu_to_le32(vnic->hash_type);
-
+ req.hash_type = cpu_to_le32(bp->rss_hash_cfg);
if (vnic->flags & BNXT_VNIC_RSS_FLAG) {
if (BNXT_CHIP_TYPE_NITRO_A0(bp))
max_rings = bp->rx_nr_rings - 1;
@@ -4954,7 +4949,6 @@ static void bnxt_init_napi(struct bnxt *bp)
bnapi = bp->bnapi[cp_nr_rings];
netif_napi_add(bp->dev, &bnapi->napi,
bnxt_poll_nitroa0, 64);
- napi_hash_add(&bnapi->napi);
}
} else {
bnapi = bp->bnapi[0];
@@ -5096,6 +5090,7 @@ static int bnxt_update_link(struct bnxt *bp, bool chng_link_state)
struct hwrm_port_phy_qcfg_input req = {0};
struct hwrm_port_phy_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
u8 link_up = link_info->link_up;
+ u16 diff;
bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_QCFG, -1, -1);
@@ -5183,6 +5178,23 @@ static int bnxt_update_link(struct bnxt *bp, bool chng_link_state)
link_info->link_up = 0;
}
mutex_unlock(&bp->hwrm_cmd_lock);
+
+ diff = link_info->support_auto_speeds ^ link_info->advertising;
+ if ((link_info->support_auto_speeds | diff) !=
+ link_info->support_auto_speeds) {
+ /* An advertised speed is no longer supported, so we need to
+ * update the advertisement settings. See bnxt_reset() for
+ * comments about the rtnl_lock() sequence below.
+ */
+ clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
+ rtnl_lock();
+ link_info->advertising = link_info->support_auto_speeds;
+ if (test_bit(BNXT_STATE_OPEN, &bp->state) &&
+ (link_info->autoneg & BNXT_AUTONEG_SPEED))
+ bnxt_hwrm_set_link_setting(bp, true, false);
+ set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
+ rtnl_unlock();
+ }
return 0;
}
@@ -5347,7 +5359,7 @@ static int bnxt_hwrm_shutdown_link(struct bnxt *bp)
return 0;
bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_CFG, -1, -1);
- req.flags = cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_FORCE_LINK_DOWN);
+ req.flags = cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_FORCE_LINK_DWN);
return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
}
@@ -5410,6 +5422,12 @@ static int bnxt_update_phy_setting(struct bnxt *bp)
update_link = true;
}
+ /* The last close may have shutdown the link, so need to call
+ * PHY_CFG to bring it back up.
+ */
+ if (!netif_carrier_ok(bp->dev))
+ update_link = true;
+
if (!bnxt_eee_config_ok(bp))
update_eee = true;
@@ -6103,6 +6121,10 @@ static void bnxt_sp_task(struct work_struct *work)
if (test_and_clear_bit(BNXT_RX_NTP_FLTR_SP_EVENT, &bp->sp_event))
bnxt_cfg_ntp_filters(bp);
if (test_and_clear_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event)) {
+ if (test_and_clear_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT,
+ &bp->sp_event))
+ bnxt_hwrm_phy_qcaps(bp);
+
rc = bnxt_update_link(bp, true);
if (rc)
netdev_err(bp->dev, "SP task can't update link (rc: %x)\n",
@@ -6306,6 +6328,7 @@ static int bnxt_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
struct tc_to_netdev *ntc)
{
struct bnxt *bp = netdev_priv(dev);
+ bool sh = false;
u8 tc;
if (ntc->type != TC_SETUP_MQPRIO)
@@ -6322,12 +6345,11 @@ static int bnxt_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
if (netdev_get_num_tc(dev) == tc)
return 0;
+ if (bp->flags & BNXT_FLAG_SHARED_RINGS)
+ sh = true;
+
if (tc) {
int max_rx_rings, max_tx_rings, rc;
- bool sh = false;
-
- if (bp->flags & BNXT_FLAG_SHARED_RINGS)
- sh = true;
rc = bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings, sh);
if (rc || bp->tx_nr_rings_per_tc * tc > max_tx_rings)
@@ -6345,7 +6367,8 @@ static int bnxt_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
bp->tx_nr_rings = bp->tx_nr_rings_per_tc;
netdev_reset_tc(dev);
}
- bp->cp_nr_rings = max_t(int, bp->tx_nr_rings, bp->rx_nr_rings);
+ bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) :
+ bp->tx_nr_rings + bp->rx_nr_rings;
bp->num_stat_ctxs = bp->cp_nr_rings;
if (netif_running(bp->dev))
@@ -6911,6 +6934,19 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
#endif
bnxt_set_dflt_rings(bp);
+ /* Default RSS hash cfg. */
+ bp->rss_hash_cfg = VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 |
+ VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 |
+ VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 |
+ VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6;
+ if (!BNXT_CHIP_NUM_57X0X(bp->chip_num) &&
+ !BNXT_CHIP_TYPE_NITRO_A0(bp) &&
+ bp->hwrm_spec_code >= 0x10501) {
+ bp->flags |= BNXT_FLAG_UDP_RSS_CAP;
+ bp->rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 |
+ VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6;
+ }
+
if (BNXT_PF(bp) && !BNXT_CHIP_TYPE_NITRO_A0(bp)) {
dev->hw_features |= NETIF_F_NTUPLE;
if (bnxt_rfs_capable(bp)) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 51b164a..47be789 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -700,7 +700,6 @@ struct bnxt_vnic_info {
u8 *uc_list;
u16 *fw_grp_ids;
- u16 hash_type;
dma_addr_t rss_table_dma_addr;
__le16 *rss_table;
dma_addr_t rss_hash_key_dma_addr;
@@ -952,6 +951,7 @@ struct bnxt {
#define BNXT_FLAG_RFS 0x100
#define BNXT_FLAG_SHARED_RINGS 0x200
#define BNXT_FLAG_PORT_STATS 0x400
+ #define BNXT_FLAG_UDP_RSS_CAP 0x800
#define BNXT_FLAG_EEE_CAP 0x1000
#define BNXT_FLAG_CHIP_NITRO_A0 0x1000000
@@ -1007,6 +1007,7 @@ struct bnxt {
struct bnxt_ring_grp_info *grp_info;
struct bnxt_vnic_info *vnic_info;
int nr_vnics;
+ u32 rss_hash_cfg;
u8 max_tc;
struct bnxt_queue_info q_info[BNXT_MAX_QUEUE];
@@ -1089,6 +1090,7 @@ struct bnxt {
#define BNXT_RESET_TASK_SILENT_SP_EVENT 11
#define BNXT_GENEVE_ADD_PORT_SP_EVENT 12
#define BNXT_GENEVE_DEL_PORT_SP_EVENT 13
+#define BNXT_LINK_SPEED_CHNG_SP_EVENT 14
struct bnxt_pf_info pf;
#ifdef CONFIG_BNXT_SRIOV
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index a7e04ff..fa6125e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -542,6 +542,146 @@ static int bnxt_grxclsrule(struct bnxt *bp, struct ethtool_rxnfc *cmd)
return rc;
}
+#endif
+
+static u64 get_ethtool_ipv4_rss(struct bnxt *bp)
+{
+ if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4)
+ return RXH_IP_SRC | RXH_IP_DST;
+ return 0;
+}
+
+static u64 get_ethtool_ipv6_rss(struct bnxt *bp)
+{
+ if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6)
+ return RXH_IP_SRC | RXH_IP_DST;
+ return 0;
+}
+
+static int bnxt_grxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd)
+{
+ cmd->data = 0;
+ switch (cmd->flow_type) {
+ case TCP_V4_FLOW:
+ if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4)
+ cmd->data |= RXH_IP_SRC | RXH_IP_DST |
+ RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ cmd->data |= get_ethtool_ipv4_rss(bp);
+ break;
+ case UDP_V4_FLOW:
+ if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4)
+ cmd->data |= RXH_IP_SRC | RXH_IP_DST |
+ RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ /* fall through */
+ case SCTP_V4_FLOW:
+ case AH_ESP_V4_FLOW:
+ case AH_V4_FLOW:
+ case ESP_V4_FLOW:
+ case IPV4_FLOW:
+ cmd->data |= get_ethtool_ipv4_rss(bp);
+ break;
+
+ case TCP_V6_FLOW:
+ if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6)
+ cmd->data |= RXH_IP_SRC | RXH_IP_DST |
+ RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ cmd->data |= get_ethtool_ipv6_rss(bp);
+ break;
+ case UDP_V6_FLOW:
+ if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6)
+ cmd->data |= RXH_IP_SRC | RXH_IP_DST |
+ RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ /* fall through */
+ case SCTP_V6_FLOW:
+ case AH_ESP_V6_FLOW:
+ case AH_V6_FLOW:
+ case ESP_V6_FLOW:
+ case IPV6_FLOW:
+ cmd->data |= get_ethtool_ipv6_rss(bp);
+ break;
+ }
+ return 0;
+}
+
+#define RXH_4TUPLE (RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3)
+#define RXH_2TUPLE (RXH_IP_SRC | RXH_IP_DST)
+
+static int bnxt_srxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd)
+{
+ u32 rss_hash_cfg = bp->rss_hash_cfg;
+ int tuple, rc = 0;
+
+ if (cmd->data == RXH_4TUPLE)
+ tuple = 4;
+ else if (cmd->data == RXH_2TUPLE)
+ tuple = 2;
+ else if (!cmd->data)
+ tuple = 0;
+ else
+ return -EINVAL;
+
+ if (cmd->flow_type == TCP_V4_FLOW) {
+ rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4;
+ if (tuple == 4)
+ rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4;
+ } else if (cmd->flow_type == UDP_V4_FLOW) {
+ if (tuple == 4 && !(bp->flags & BNXT_FLAG_UDP_RSS_CAP))
+ return -EINVAL;
+ rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4;
+ if (tuple == 4)
+ rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4;
+ } else if (cmd->flow_type == TCP_V6_FLOW) {
+ rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6;
+ if (tuple == 4)
+ rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6;
+ } else if (cmd->flow_type == UDP_V6_FLOW) {
+ if (tuple == 4 && !(bp->flags & BNXT_FLAG_UDP_RSS_CAP))
+ return -EINVAL;
+ rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6;
+ if (tuple == 4)
+ rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6;
+ } else if (tuple == 4) {
+ return -EINVAL;
+ }
+
+ switch (cmd->flow_type) {
+ case TCP_V4_FLOW:
+ case UDP_V4_FLOW:
+ case SCTP_V4_FLOW:
+ case AH_ESP_V4_FLOW:
+ case AH_V4_FLOW:
+ case ESP_V4_FLOW:
+ case IPV4_FLOW:
+ if (tuple == 2)
+ rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4;
+ else if (!tuple)
+ rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4;
+ break;
+
+ case TCP_V6_FLOW:
+ case UDP_V6_FLOW:
+ case SCTP_V6_FLOW:
+ case AH_ESP_V6_FLOW:
+ case AH_V6_FLOW:
+ case ESP_V6_FLOW:
+ case IPV6_FLOW:
+ if (tuple == 2)
+ rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6;
+ else if (!tuple)
+ rss_hash_cfg &= ~VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6;
+ break;
+ }
+
+ if (bp->rss_hash_cfg == rss_hash_cfg)
+ return 0;
+
+ bp->rss_hash_cfg = rss_hash_cfg;
+ if (netif_running(bp->dev)) {
+ bnxt_close_nic(bp, false, false);
+ rc = bnxt_open_nic(bp, false, false);
+ }
+ return rc;
+}
static int bnxt_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
u32 *rule_locs)
@@ -550,6 +690,7 @@ static int bnxt_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
int rc = 0;
switch (cmd->cmd) {
+#ifdef CONFIG_RFS_ACCEL
case ETHTOOL_GRXRINGS:
cmd->data = bp->rx_nr_rings;
break;
@@ -566,6 +707,11 @@ static int bnxt_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
case ETHTOOL_GRXCLSRULE:
rc = bnxt_grxclsrule(bp, cmd);
break;
+#endif
+
+ case ETHTOOL_GRXFH:
+ rc = bnxt_grxfh(bp, cmd);
+ break;
default:
rc = -EOPNOTSUPP;
@@ -574,7 +720,23 @@ static int bnxt_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
return rc;
}
-#endif
+
+static int bnxt_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+ struct bnxt *bp = netdev_priv(dev);
+ int rc;
+
+ switch (cmd->cmd) {
+ case ETHTOOL_SRXFH:
+ rc = bnxt_srxfh(bp, cmd);
+ break;
+
+ default:
+ rc = -EOPNOTSUPP;
+ break;
+ }
+ return rc;
+}
static u32 bnxt_get_rxfh_indir_size(struct net_device *dev)
{
@@ -1885,9 +2047,8 @@ const struct ethtool_ops bnxt_ethtool_ops = {
.get_ringparam = bnxt_get_ringparam,
.get_channels = bnxt_get_channels,
.set_channels = bnxt_set_channels,
-#ifdef CONFIG_RFS_ACCEL
.get_rxnfc = bnxt_get_rxnfc,
-#endif
+ .set_rxnfc = bnxt_set_rxnfc,
.get_rxfh_indir_size = bnxt_get_rxfh_indir_size,
.get_rxfh_key_size = bnxt_get_rxfh_key_size,
.get_rxfh = bnxt_get_rxfh,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 04a96cc..0456d5b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -215,6 +215,9 @@ struct hwrm_async_event_cmpl_dcb_config_change {
__le16 event_id;
#define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_ID_DCB_CONFIG_CHANGE 0x3UL
__le32 event_data2;
+ #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA2_ETS 0x1UL
+ #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA2_PFC 0x2UL
+ #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA2_APP 0x4UL
u8 opaque_v;
#define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_V 0x1UL
#define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_OPAQUE_MASK 0xfeUL
@@ -224,6 +227,14 @@ struct hwrm_async_event_cmpl_dcb_config_change {
__le32 event_data1;
#define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA1_PORT_ID_MASK 0xffffUL
#define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA1_PORT_ID_SFT 0
+ #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA1_RECOMMEND_ROCE_PRIORITY_MASK 0xff0000UL
+ #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA1_RECOMMEND_ROCE_PRIORITY_SFT 16
+ #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA1_RECOMMEND_ROCE_PRIORITY_NONE (0xffUL << 16)
+ #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA1_RECOMMEND_ROCE_PRIORITY_LAST HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA1_RECOMMEND_ROCE_PRIORITY_NONE
+ #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA1_RECOMMEND_L2_PRIORITY_MASK 0xff000000UL
+ #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA1_RECOMMEND_L2_PRIORITY_SFT 24
+ #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA1_RECOMMEND_L2_PRIORITY_NONE (0xffUL << 24)
+ #define HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA1_RECOMMEND_L2_PRIORITY_LAST HWRM_ASYNC_EVENT_CMPL_DCB_CONFIG_CHANGE_EVENT_DATA1_RECOMMEND_L2_PRIORITY_NONE
};
/* HWRM Asynchronous Event Completion Record for port connection not allowed (16 bytes) */
@@ -485,12 +496,12 @@ struct hwrm_async_event_cmpl_hwrm_error {
#define HWRM_ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA1_TIMESTAMP 0x1UL
};
-/* HW Resource Manager Specification 1.5.1 */
+/* HW Resource Manager Specification 1.5.4 */
#define HWRM_VERSION_MAJOR 1
#define HWRM_VERSION_MINOR 5
-#define HWRM_VERSION_UPDATE 1
+#define HWRM_VERSION_UPDATE 4
-#define HWRM_VERSION_STR "1.5.1"
+#define HWRM_VERSION_STR "1.5.4"
/*
* Following is the signature for HWRM message field that indicates not
* applicable (All F's). Need to cast it the size of the field if needed.
@@ -612,6 +623,9 @@ struct cmd_nums {
#define HWRM_FW_QSTATUS (0xc1UL)
#define HWRM_FW_SET_TIME (0xc8UL)
#define HWRM_FW_GET_TIME (0xc9UL)
+ #define HWRM_FW_SET_STRUCTURED_DATA (0xcaUL)
+ #define HWRM_FW_GET_STRUCTURED_DATA (0xcbUL)
+ #define HWRM_FW_IPC_MAILBOX (0xccUL)
#define HWRM_EXEC_FWD_RESP (0xd0UL)
#define HWRM_REJECT_FWD_RESP (0xd1UL)
#define HWRM_FWD_RESP (0xd2UL)
@@ -626,6 +640,8 @@ struct cmd_nums {
#define HWRM_DBG_WRITE_DIRECT (0xff12UL)
#define HWRM_DBG_WRITE_INDIRECT (0xff13UL)
#define HWRM_DBG_DUMP (0xff14UL)
+ #define HWRM_NVM_GET_VARIABLE (0xfff1UL)
+ #define HWRM_NVM_SET_VARIABLE (0xfff2UL)
#define HWRM_NVM_INSTALL_UPDATE (0xfff3UL)
#define HWRM_NVM_MODIFY (0xfff4UL)
#define HWRM_NVM_VERIFY_UPDATE (0xfff5UL)
@@ -1399,6 +1415,7 @@ struct hwrm_func_drv_rgtr_input {
#define FUNC_DRV_RGTR_REQ_OS_TYPE_ESXI 0x68UL
#define FUNC_DRV_RGTR_REQ_OS_TYPE_WIN864 0x73UL
#define FUNC_DRV_RGTR_REQ_OS_TYPE_WIN2012R2 0x74UL
+ #define FUNC_DRV_RGTR_REQ_OS_TYPE_UEFI 0x8000UL
u8 ver_maj;
u8 ver_min;
u8 ver_upd;
@@ -1549,7 +1566,7 @@ struct hwrm_port_phy_cfg_input {
__le64 resp_addr;
__le32 flags;
#define PORT_PHY_CFG_REQ_FLAGS_RESET_PHY 0x1UL
- #define PORT_PHY_CFG_REQ_FLAGS_FORCE_LINK_DOWN 0x2UL
+ #define PORT_PHY_CFG_REQ_FLAGS_DEPRECATED 0x2UL
#define PORT_PHY_CFG_REQ_FLAGS_FORCE 0x4UL
#define PORT_PHY_CFG_REQ_FLAGS_RESTART_AUTONEG 0x8UL
#define PORT_PHY_CFG_REQ_FLAGS_EEE_ENABLE 0x10UL
@@ -1562,6 +1579,7 @@ struct hwrm_port_phy_cfg_input {
#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_DISABLE 0x800UL
#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_ENABLE 0x1000UL
#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_DISABLE 0x2000UL
+ #define PORT_PHY_CFG_REQ_FLAGS_FORCE_LINK_DWN 0x4000UL
__le32 enables;
#define PORT_PHY_CFG_REQ_ENABLES_AUTO_MODE 0x1UL
#define PORT_PHY_CFG_REQ_ENABLES_AUTO_DUPLEX 0x2UL
@@ -4023,6 +4041,71 @@ struct hwrm_fw_set_time_output {
u8 valid;
};
+/* hwrm_fw_set_structured_data */
+/* Input (32 bytes) */
+struct hwrm_fw_set_structured_data_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ __le64 src_data_addr;
+ __le16 data_len;
+ u8 hdr_cnt;
+ u8 unused_0[5];
+};
+
+/* Output (16 bytes) */
+struct hwrm_fw_set_structured_data_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ __le32 unused_0;
+ u8 unused_1;
+ u8 unused_2;
+ u8 unused_3;
+ u8 valid;
+};
+
+/* hwrm_fw_get_structured_data */
+/* Input (32 bytes) */
+struct hwrm_fw_get_structured_data_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ __le64 dest_data_addr;
+ __le16 data_len;
+ __le16 structure_id;
+ __le16 subtype;
+ #define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_ALL 0xffffUL
+ #define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NEAR_BRIDGE_ADMIN 0x100UL
+ #define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NEAR_BRIDGE_PEER 0x101UL
+ #define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NEAR_BRIDGE_OPERATIONAL 0x102UL
+ #define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_ADMIN 0x200UL
+ #define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_PEER 0x201UL
+ #define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_OPERATIONAL 0x202UL
+ u8 count;
+ u8 unused_0;
+};
+
+/* Output (16 bytes) */
+struct hwrm_fw_get_structured_data_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ u8 hdr_cnt;
+ u8 unused_0;
+ __le16 unused_1;
+ u8 unused_2;
+ u8 unused_3;
+ u8 unused_4;
+ u8 valid;
+};
+
/* hwrm_exec_fwd_resp */
/* Input (128 bytes) */
struct hwrm_exec_fwd_resp_input {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index ec6cd18..60e2af8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -774,8 +774,8 @@ static int bnxt_vf_set_link(struct bnxt *bp, struct bnxt_vf_info *vf)
if (vf->flags & BNXT_VF_LINK_UP) {
/* if physical link is down, force link up on VF */
- if (phy_qcfg_resp.link ==
- PORT_PHY_QCFG_RESP_LINK_NO_LINK) {
+ if (phy_qcfg_resp.link !=
+ PORT_PHY_QCFG_RESP_LINK_LINK) {
phy_qcfg_resp.link =
PORT_PHY_QCFG_RESP_LINK_LINK;
phy_qcfg_resp.link_speed = cpu_to_le16(
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 4464bc5..33638dc 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -971,13 +971,6 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e)
return phy_ethtool_set_eee(priv->phydev, e);
}
-static int bcmgenet_nway_reset(struct net_device *dev)
-{
- struct bcmgenet_priv *priv = netdev_priv(dev);
-
- return genphy_restart_aneg(priv->phydev);
-}
-
/* standard ethtool support functions. */
static const struct ethtool_ops bcmgenet_ethtool_ops = {
.get_strings = bcmgenet_get_strings,
@@ -991,7 +984,7 @@ static const struct ethtool_ops bcmgenet_ethtool_ops = {
.set_wol = bcmgenet_set_wol,
.get_eee = bcmgenet_get_eee,
.set_eee = bcmgenet_set_eee,
- .nway_reset = bcmgenet_nway_reset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_coalesce = bcmgenet_get_coalesce,
.set_coalesce = bcmgenet_set_coalesce,
.get_link_ksettings = bcmgenet_get_link_ksettings,
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index b200a78..1120308 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -177,6 +177,7 @@ bnad_txcmpl_process(struct bnad *bnad, struct bna_tcb *tcb)
return 0;
hw_cons = *(tcb->hw_consumer_index);
+ rmb();
cons = tcb->consumer_index;
q_depth = tcb->q_depth;
@@ -3094,7 +3095,7 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev)
BNA_QE_INDX_INC(prod, q_depth);
tcb->producer_index = prod;
- smp_mb();
+ wmb();
if (unlikely(!test_bit(BNAD_TXQ_TX_STARTED, &tcb->flags)))
return NETDEV_TX_OK;
@@ -3102,7 +3103,6 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev)
skb_tx_timestamp(skb);
bna_txq_prod_indx_doorbell(tcb);
- smp_mb();
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index e1847ce..654b5bf 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -32,7 +32,9 @@
#include <linux/of_gpio.h>
#include <linux/of_mdio.h>
#include <linux/of_net.h>
-
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
#include "macb.h"
#define MACB_RX_BUFFER_SIZE 128
@@ -60,10 +62,13 @@
| MACB_BIT(TXERR))
#define MACB_TX_INT_FLAGS (MACB_TX_ERR_FLAGS | MACB_BIT(TCOMP))
-#define MACB_MAX_TX_LEN ((unsigned int)((1 << MACB_TX_FRMLEN_SIZE) - 1))
-#define GEM_MAX_TX_LEN ((unsigned int)((1 << GEM_TX_FRMLEN_SIZE) - 1))
+/* Max length of transmit frame must be a multiple of 8 bytes */
+#define MACB_TX_LEN_ALIGN 8
+#define MACB_MAX_TX_LEN ((unsigned int)((1 << MACB_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1)))
+#define GEM_MAX_TX_LEN ((unsigned int)((1 << GEM_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1)))
#define GEM_MTU_MIN_SIZE ETH_MIN_MTU
+#define MACB_NETIF_LSO (NETIF_F_TSO | NETIF_F_UFO)
#define MACB_WOL_HAS_MAGIC_PACKET (0x1 << 0)
#define MACB_WOL_ENABLED (0x1 << 1)
@@ -1223,7 +1228,8 @@ static void macb_poll_controller(struct net_device *dev)
static unsigned int macb_tx_map(struct macb *bp,
struct macb_queue *queue,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ unsigned int hdrlen)
{
dma_addr_t mapping;
unsigned int len, entry, i, tx_head = queue->tx_head;
@@ -1231,14 +1237,27 @@ static unsigned int macb_tx_map(struct macb *bp,
struct macb_dma_desc *desc;
unsigned int offset, size, count = 0;
unsigned int f, nr_frags = skb_shinfo(skb)->nr_frags;
- unsigned int eof = 1;
- u32 ctrl;
+ unsigned int eof = 1, mss_mfs = 0;
+ u32 ctrl, lso_ctrl = 0, seq_ctrl = 0;
+
+ /* LSO */
+ if (skb_shinfo(skb)->gso_size != 0) {
+ if (ip_hdr(skb)->protocol == IPPROTO_UDP)
+ /* UDP - UFO */
+ lso_ctrl = MACB_LSO_UFO_ENABLE;
+ else
+ /* TCP - TSO */
+ lso_ctrl = MACB_LSO_TSO_ENABLE;
+ }
/* First, map non-paged data */
len = skb_headlen(skb);
+
+ /* first buffer length */
+ size = hdrlen;
+
offset = 0;
while (len) {
- size = min(len, bp->max_tx_length);
entry = macb_tx_ring_wrap(bp, tx_head);
tx_skb = &queue->tx_skb[entry];
@@ -1258,6 +1277,8 @@ static unsigned int macb_tx_map(struct macb *bp,
offset += size;
count++;
tx_head++;
+
+ size = min(len, bp->max_tx_length);
}
/* Then, map paged data from fragments */
@@ -1311,6 +1332,21 @@ static unsigned int macb_tx_map(struct macb *bp,
desc = &queue->tx_ring[entry];
desc->ctrl = ctrl;
+ if (lso_ctrl) {
+ if (lso_ctrl == MACB_LSO_UFO_ENABLE)
+ /* include header and FCS in value given to h/w */
+ mss_mfs = skb_shinfo(skb)->gso_size +
+ skb_transport_offset(skb) +
+ ETH_FCS_LEN;
+ else /* TSO */ {
+ mss_mfs = skb_shinfo(skb)->gso_size;
+ /* TCP Sequence Number Source Select
+ * can be set only for TSO
+ */
+ seq_ctrl = 0;
+ }
+ }
+
do {
i--;
entry = macb_tx_ring_wrap(bp, i);
@@ -1325,6 +1361,16 @@ static unsigned int macb_tx_map(struct macb *bp,
if (unlikely(entry == (bp->tx_ring_size - 1)))
ctrl |= MACB_BIT(TX_WRAP);
+ /* First descriptor is header descriptor */
+ if (i == queue->tx_head) {
+ ctrl |= MACB_BF(TX_LSO, lso_ctrl);
+ ctrl |= MACB_BF(TX_TCP_SEQ_SRC, seq_ctrl);
+ } else
+ /* Only set MSS/MFS on payload descriptors
+ * (second or later descriptor)
+ */
+ ctrl |= MACB_BF(MSS_MFS, mss_mfs);
+
/* Set TX buffer descriptor */
macb_set_addr(desc, tx_skb->mapping);
/* desc->addr must be visible to hardware before clearing
@@ -1350,6 +1396,43 @@ static unsigned int macb_tx_map(struct macb *bp,
return 0;
}
+static netdev_features_t macb_features_check(struct sk_buff *skb,
+ struct net_device *dev,
+ netdev_features_t features)
+{
+ unsigned int nr_frags, f;
+ unsigned int hdrlen;
+
+ /* Validate LSO compatibility */
+
+ /* there is only one buffer */
+ if (!skb_is_nonlinear(skb))
+ return features;
+
+ /* length of header */
+ hdrlen = skb_transport_offset(skb);
+ if (ip_hdr(skb)->protocol == IPPROTO_TCP)
+ hdrlen += tcp_hdrlen(skb);
+
+ /* For LSO:
+ * When software supplies two or more payload buffers all payload buffers
+ * apart from the last must be a multiple of 8 bytes in size.
+ */
+ if (!IS_ALIGNED(skb_headlen(skb) - hdrlen, MACB_TX_LEN_ALIGN))
+ return features & ~MACB_NETIF_LSO;
+
+ nr_frags = skb_shinfo(skb)->nr_frags;
+ /* No need to check last fragment */
+ nr_frags--;
+ for (f = 0; f < nr_frags; f++) {
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[f];
+
+ if (!IS_ALIGNED(skb_frag_size(frag), MACB_TX_LEN_ALIGN))
+ return features & ~MACB_NETIF_LSO;
+ }
+ return features;
+}
+
static inline int macb_clear_csum(struct sk_buff *skb)
{
/* no change for packets without checksum offloading */
@@ -1374,7 +1457,28 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
struct macb *bp = netdev_priv(dev);
struct macb_queue *queue = &bp->queues[queue_index];
unsigned long flags;
- unsigned int count, nr_frags, frag_size, f;
+ unsigned int desc_cnt, nr_frags, frag_size, f;
+ unsigned int hdrlen;
+ bool is_lso, is_udp = 0;
+
+ is_lso = (skb_shinfo(skb)->gso_size != 0);
+
+ if (is_lso) {
+ is_udp = !!(ip_hdr(skb)->protocol == IPPROTO_UDP);
+
+ /* length of headers */
+ if (is_udp)
+ /* only queue eth + ip headers separately for UDP */
+ hdrlen = skb_transport_offset(skb);
+ else
+ hdrlen = skb_transport_offset(skb) + tcp_hdrlen(skb);
+ if (skb_headlen(skb) < hdrlen) {
+ netdev_err(bp->dev, "Error - LSO headers fragmented!!!\n");
+ /* if this is required, would need to copy to single buffer */
+ return NETDEV_TX_BUSY;
+ }
+ } else
+ hdrlen = min(skb_headlen(skb), bp->max_tx_length);
#if defined(DEBUG) && defined(VERBOSE_DEBUG)
netdev_vdbg(bp->dev,
@@ -1389,18 +1493,22 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
* socket buffer: skb fragments of jumbo frames may need to be
* split into many buffer descriptors.
*/
- count = DIV_ROUND_UP(skb_headlen(skb), bp->max_tx_length);
+ if (is_lso && (skb_headlen(skb) > hdrlen))
+ /* extra header descriptor if also payload in first buffer */
+ desc_cnt = DIV_ROUND_UP((skb_headlen(skb) - hdrlen), bp->max_tx_length) + 1;
+ else
+ desc_cnt = DIV_ROUND_UP(skb_headlen(skb), bp->max_tx_length);
nr_frags = skb_shinfo(skb)->nr_frags;
for (f = 0; f < nr_frags; f++) {
frag_size = skb_frag_size(&skb_shinfo(skb)->frags[f]);
- count += DIV_ROUND_UP(frag_size, bp->max_tx_length);
+ desc_cnt += DIV_ROUND_UP(frag_size, bp->max_tx_length);
}
spin_lock_irqsave(&bp->lock, flags);
/* This is a hard error, log it. */
if (CIRC_SPACE(queue->tx_head, queue->tx_tail,
- bp->tx_ring_size) < count) {
+ bp->tx_ring_size) < desc_cnt) {
netif_stop_subqueue(dev, queue_index);
spin_unlock_irqrestore(&bp->lock, flags);
netdev_dbg(bp->dev, "tx_head = %u, tx_tail = %u\n",
@@ -1414,7 +1522,7 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
}
/* Map socket buffer for DMA transfer */
- if (!macb_tx_map(bp, queue, skb)) {
+ if (!macb_tx_map(bp, queue, skb, hdrlen)) {
dev_kfree_skb_any(skb);
goto unlock;
}
@@ -2354,6 +2462,7 @@ static const struct net_device_ops macb_netdev_ops = {
.ndo_poll_controller = macb_poll_controller,
#endif
.ndo_set_features = macb_set_features,
+ .ndo_features_check = macb_features_check,
};
/* Configure peripheral capabilities according to device tree
@@ -2560,6 +2669,11 @@ static int macb_init(struct platform_device *pdev)
/* Set features */
dev->hw_features = NETIF_F_SG;
+
+ /* Check LSO capability */
+ if (GEM_BFEXT(PBUF_LSO, gem_readl(bp, DCFG6)))
+ dev->hw_features |= MACB_NETIF_LSO;
+
/* Checksum offload is only available on gem with packet buffer */
if (macb_is_gem(bp) && !(bp->caps & MACB_CAPS_FIFO_MODE))
dev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 1216950..d67adad 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -382,6 +382,10 @@
#define GEM_TX_PKT_BUFF_OFFSET 21
#define GEM_TX_PKT_BUFF_SIZE 1
+/* Bitfields in DCFG6. */
+#define GEM_PBUF_LSO_OFFSET 27
+#define GEM_PBUF_LSO_SIZE 1
+
/* Constants for CLK */
#define MACB_CLK_DIV8 0
#define MACB_CLK_DIV16 1
@@ -414,6 +418,10 @@
#define MACB_CAPS_SG_DISABLED 0x40000000
#define MACB_CAPS_MACB_IS_GEM 0x80000000
+/* LSO settings */
+#define MACB_LSO_UFO_ENABLE 0x01
+#define MACB_LSO_TSO_ENABLE 0x02
+
/* Bit manipulation macros */
#define MACB_BIT(name) \
(1 << MACB_##name##_OFFSET)
@@ -545,6 +553,12 @@ struct macb_dma_desc {
#define MACB_TX_LAST_SIZE 1
#define MACB_TX_NOCRC_OFFSET 16
#define MACB_TX_NOCRC_SIZE 1
+#define MACB_MSS_MFS_OFFSET 16
+#define MACB_MSS_MFS_SIZE 14
+#define MACB_TX_LSO_OFFSET 17
+#define MACB_TX_LSO_SIZE 2
+#define MACB_TX_TCP_SEQ_SRC_OFFSET 19
+#define MACB_TX_TCP_SEQ_SRC_SIZE 1
#define MACB_TX_BUF_EXHAUSTED_OFFSET 27
#define MACB_TX_BUF_EXHAUSTED_SIZE 1
#define MACB_TX_UNDERRUN_OFFSET 28
diff --git a/drivers/net/ethernet/cavium/liquidio/Makefile b/drivers/net/ethernet/cavium/liquidio/Makefile
index 5a27b2a..14958de 100644
--- a/drivers/net/ethernet/cavium/liquidio/Makefile
+++ b/drivers/net/ethernet/cavium/liquidio/Makefile
@@ -11,6 +11,7 @@
cn66xx_device.o \
cn68xx_device.o \
cn23xx_pf_device.o \
+ octeon_mailbox.o \
octeon_mem_ops.o \
octeon_droq.o \
octeon_nic.o
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index 380a641..962dcbc 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -1,28 +1,23 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
-
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
#include <linux/pci.h>
-#include <linux/netdevice.h>
#include <linux/vmalloc.h>
+#include <linux/etherdevice.h>
#include "liquidio_common.h"
#include "octeon_droq.h"
#include "octeon_iq.h"
@@ -30,6 +25,7 @@
#include "octeon_device.h"
#include "cn23xx_pf_device.h"
#include "octeon_main.h"
+#include "octeon_mailbox.h"
#define RESET_NOTDONE 0
#define RESET_DONE 1
@@ -40,11 +36,6 @@
*/
#define CN23XX_INPUT_JABBER 64600
-#define LIOLUT_RING_DISTRIBUTION 9
-const int liolut_num_vfs_to_rings_per_vf[LIOLUT_RING_DISTRIBUTION] = {
- 0, 8, 4, 2, 2, 2, 1, 1, 1
-};
-
void cn23xx_dump_pf_initialized_regs(struct octeon_device *oct)
{
int i = 0;
@@ -309,9 +300,10 @@ u32 cn23xx_pf_get_oq_ticks(struct octeon_device *oct, u32 time_intr_in_us)
static void cn23xx_setup_global_mac_regs(struct octeon_device *oct)
{
- u64 reg_val;
u16 mac_no = oct->pcie_port;
u16 pf_num = oct->pf_num;
+ u64 reg_val;
+ u64 temp;
/* programming SRN and TRS for each MAC(0..3) */
@@ -333,6 +325,14 @@ static void cn23xx_setup_global_mac_regs(struct octeon_device *oct)
/* setting TRS <23:16> */
reg_val = reg_val |
(oct->sriov_info.trs << CN23XX_PKT_MAC_CTL_RINFO_TRS_BIT_POS);
+ /* setting RPVF <39:32> */
+ temp = oct->sriov_info.rings_per_vf & 0xff;
+ reg_val |= (temp << CN23XX_PKT_MAC_CTL_RINFO_RPVF_BIT_POS);
+
+ /* setting NVFS <55:48> */
+ temp = oct->sriov_info.max_vfs & 0xff;
+ reg_val |= (temp << CN23XX_PKT_MAC_CTL_RINFO_NVFS_BIT_POS);
+
/* write these settings to MAC register */
octeon_write_csr64(oct, CN23XX_SLI_PKT_MAC_RINFO64(mac_no, pf_num),
reg_val);
@@ -399,11 +399,12 @@ static int cn23xx_reset_io_queues(struct octeon_device *oct)
static int cn23xx_pf_setup_global_input_regs(struct octeon_device *oct)
{
+ struct octeon_cn23xx_pf *cn23xx = (struct octeon_cn23xx_pf *)oct->chip;
+ struct octeon_instr_queue *iq;
+ u64 intr_threshold, reg_val;
u32 q_no, ern, srn;
u64 pf_num;
- u64 intr_threshold, reg_val;
- struct octeon_instr_queue *iq;
- struct octeon_cn23xx_pf *cn23xx = (struct octeon_cn23xx_pf *)oct->chip;
+ u64 vf_num;
pf_num = oct->pf_num;
@@ -414,12 +415,22 @@ static int cn23xx_pf_setup_global_input_regs(struct octeon_device *oct)
return -1;
/** Set the MAC_NUM and PVF_NUM in IQ_PKT_CONTROL reg
- * for all queues.Only PF can set these bits.
- * bits 29:30 indicate the MAC num.
- * bits 32:47 indicate the PVF num.
- */
+ * for all queues.Only PF can set these bits.
+ * bits 29:30 indicate the MAC num.
+ * bits 32:47 indicate the PVF num.
+ */
for (q_no = 0; q_no < ern; q_no++) {
reg_val = oct->pcie_port << CN23XX_PKT_INPUT_CTL_MAC_NUM_POS;
+
+ /* for VF assigned queues. */
+ if (q_no < oct->sriov_info.pf_srn) {
+ vf_num = q_no / oct->sriov_info.rings_per_vf;
+ vf_num += 1; /* VF1, VF2,........ */
+ } else {
+ vf_num = 0;
+ }
+
+ reg_val |= vf_num << CN23XX_PKT_INPUT_CTL_VF_NUM_POS;
reg_val |= pf_num << CN23XX_PKT_INPUT_CTL_PF_NUM_POS;
octeon_write_csr64(oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no),
@@ -530,8 +541,8 @@ static void cn23xx_pf_setup_global_output_regs(struct octeon_device *oct)
writeq(0x40, (u8 *)oct->mmio[0].hw_addr + CN23XX_SLI_OQ_WMARK);
/** Disabling setting OQs in reset when ring has no dorebells
- * enabling this will cause of head of line blocking
- */
+ * enabling this will cause of head of line blocking
+ */
/* Do it only for pass1.1. and pass1.2 */
if ((oct->rev_id == OCTEON_CN23XX_REV_1_0) ||
(oct->rev_id == OCTEON_CN23XX_REV_1_1))
@@ -662,6 +673,118 @@ static void cn23xx_setup_oq_regs(struct octeon_device *oct, u32 oq_no)
}
}
+static void cn23xx_pf_mbox_thread(struct work_struct *work)
+{
+ struct cavium_wk *wk = (struct cavium_wk *)work;
+ struct octeon_mbox *mbox = (struct octeon_mbox *)wk->ctxptr;
+ struct octeon_device *oct = mbox->oct_dev;
+ u64 mbox_int_val, val64;
+ u32 q_no, i;
+
+ if (oct->rev_id < OCTEON_CN23XX_REV_1_1) {
+ /*read and clear by writing 1*/
+ mbox_int_val = readq(mbox->mbox_int_reg);
+ writeq(mbox_int_val, mbox->mbox_int_reg);
+
+ for (i = 0; i < oct->sriov_info.num_vfs_alloced; i++) {
+ q_no = i * oct->sriov_info.rings_per_vf;
+
+ val64 = readq(oct->mbox[q_no]->mbox_write_reg);
+
+ if (val64 && (val64 != OCTEON_PFVFACK)) {
+ if (octeon_mbox_read(oct->mbox[q_no]))
+ octeon_mbox_process_message(
+ oct->mbox[q_no]);
+ }
+ }
+
+ schedule_delayed_work(&wk->work, msecs_to_jiffies(10));
+ } else {
+ octeon_mbox_process_message(mbox);
+ }
+}
+
+static int cn23xx_setup_pf_mbox(struct octeon_device *oct)
+{
+ struct octeon_mbox *mbox = NULL;
+ u16 mac_no = oct->pcie_port;
+ u16 pf_num = oct->pf_num;
+ u32 q_no, i;
+
+ if (!oct->sriov_info.max_vfs)
+ return 0;
+
+ for (i = 0; i < oct->sriov_info.max_vfs; i++) {
+ q_no = i * oct->sriov_info.rings_per_vf;
+
+ mbox = vmalloc(sizeof(*mbox));
+ if (!mbox)
+ goto free_mbox;
+
+ memset(mbox, 0, sizeof(struct octeon_mbox));
+
+ spin_lock_init(&mbox->lock);
+
+ mbox->oct_dev = oct;
+
+ mbox->q_no = q_no;
+
+ mbox->state = OCTEON_MBOX_STATE_IDLE;
+
+ /* PF mbox interrupt reg */
+ mbox->mbox_int_reg = (u8 *)oct->mmio[0].hw_addr +
+ CN23XX_SLI_MAC_PF_MBOX_INT(mac_no, pf_num);
+
+ /* PF writes into SIG0 reg */
+ mbox->mbox_write_reg = (u8 *)oct->mmio[0].hw_addr +
+ CN23XX_SLI_PKT_PF_VF_MBOX_SIG(q_no, 0);
+
+ /* PF reads from SIG1 reg */
+ mbox->mbox_read_reg = (u8 *)oct->mmio[0].hw_addr +
+ CN23XX_SLI_PKT_PF_VF_MBOX_SIG(q_no, 1);
+
+ /*Mail Box Thread creation*/
+ INIT_DELAYED_WORK(&mbox->mbox_poll_wk.work,
+ cn23xx_pf_mbox_thread);
+ mbox->mbox_poll_wk.ctxptr = (void *)mbox;
+
+ oct->mbox[q_no] = mbox;
+
+ writeq(OCTEON_PFVFSIG, mbox->mbox_read_reg);
+ }
+
+ if (oct->rev_id < OCTEON_CN23XX_REV_1_1)
+ schedule_delayed_work(&oct->mbox[0]->mbox_poll_wk.work,
+ msecs_to_jiffies(0));
+
+ return 0;
+
+free_mbox:
+ while (i) {
+ i--;
+ vfree(oct->mbox[i]);
+ }
+
+ return 1;
+}
+
+static int cn23xx_free_pf_mbox(struct octeon_device *oct)
+{
+ u32 q_no, i;
+
+ if (!oct->sriov_info.max_vfs)
+ return 0;
+
+ for (i = 0; i < oct->sriov_info.max_vfs; i++) {
+ q_no = i * oct->sriov_info.rings_per_vf;
+ cancel_delayed_work_sync(
+ &oct->mbox[q_no]->mbox_poll_wk.work);
+ vfree(oct->mbox[q_no]);
+ }
+
+ return 0;
+}
+
static int cn23xx_enable_io_queues(struct octeon_device *oct)
{
u64 reg_val;
@@ -856,6 +979,29 @@ static u64 cn23xx_pf_msix_interrupt_handler(void *dev)
return ret;
}
+static void cn23xx_handle_pf_mbox_intr(struct octeon_device *oct)
+{
+ struct delayed_work *work;
+ u64 mbox_int_val;
+ u32 i, q_no;
+
+ mbox_int_val = readq(oct->mbox[0]->mbox_int_reg);
+
+ for (i = 0; i < oct->sriov_info.num_vfs_alloced; i++) {
+ q_no = i * oct->sriov_info.rings_per_vf;
+
+ if (mbox_int_val & BIT_ULL(q_no)) {
+ writeq(BIT_ULL(q_no),
+ oct->mbox[0]->mbox_int_reg);
+ if (octeon_mbox_read(oct->mbox[q_no])) {
+ work = &oct->mbox[q_no]->mbox_poll_wk.work;
+ schedule_delayed_work(work,
+ msecs_to_jiffies(0));
+ }
+ }
+ }
+}
+
static irqreturn_t cn23xx_interrupt_handler(void *dev)
{
struct octeon_device *oct = (struct octeon_device *)dev;
@@ -871,6 +1017,10 @@ static irqreturn_t cn23xx_interrupt_handler(void *dev)
dev_err(&oct->pci_dev->dev, "OCTEON[%d]: Error Intr: 0x%016llx\n",
oct->octeon_id, CVM_CAST64(intr64));
+ /* When VFs write into MBOX_SIG2 reg,these intr is set in PF */
+ if (intr64 & CN23XX_INTR_VF_MBOX)
+ cn23xx_handle_pf_mbox_intr(oct);
+
if (oct->msix_on != LIO_FLAG_MSIX_ENABLED) {
if (intr64 & CN23XX_INTR_PKT_DATA)
oct->int_status |= OCT_DEV_INTR_PKT_DATA;
@@ -961,6 +1111,13 @@ static void cn23xx_enable_pf_interrupt(struct octeon_device *oct, u8 intr_flag)
intr_val = readq(cn23xx->intr_enb_reg64);
intr_val |= CN23XX_INTR_PKT_DATA;
writeq(intr_val, cn23xx->intr_enb_reg64);
+ } else if ((intr_flag & OCTEON_MBOX_INTR) &&
+ (oct->sriov_info.max_vfs > 0)) {
+ if (oct->rev_id >= OCTEON_CN23XX_REV_1_1) {
+ intr_val = readq(cn23xx->intr_enb_reg64);
+ intr_val |= CN23XX_INTR_VF_MBOX;
+ writeq(intr_val, cn23xx->intr_enb_reg64);
+ }
}
}
@@ -976,6 +1133,13 @@ static void cn23xx_disable_pf_interrupt(struct octeon_device *oct, u8 intr_flag)
intr_val = readq(cn23xx->intr_enb_reg64);
intr_val &= ~CN23XX_INTR_PKT_DATA;
writeq(intr_val, cn23xx->intr_enb_reg64);
+ } else if ((intr_flag & OCTEON_MBOX_INTR) &&
+ (oct->sriov_info.max_vfs > 0)) {
+ if (oct->rev_id >= OCTEON_CN23XX_REV_1_1) {
+ intr_val = readq(cn23xx->intr_enb_reg64);
+ intr_val &= ~CN23XX_INTR_VF_MBOX;
+ writeq(intr_val, cn23xx->intr_enb_reg64);
+ }
}
}
@@ -1048,50 +1212,59 @@ static void cn23xx_setup_reg_address(struct octeon_device *oct)
static int cn23xx_sriov_config(struct octeon_device *oct)
{
- u32 total_rings;
struct octeon_cn23xx_pf *cn23xx = (struct octeon_cn23xx_pf *)oct->chip;
- /* num_vfs is already filled for us */
+ u32 max_rings, total_rings, max_vfs, rings_per_vf;
u32 pf_srn, num_pf_rings;
+ u32 max_possible_vfs;
cn23xx->conf =
- (struct octeon_config *)oct_get_config_info(oct, LIO_23XX);
+ (struct octeon_config *)oct_get_config_info(oct, LIO_23XX);
switch (oct->rev_id) {
case OCTEON_CN23XX_REV_1_0:
- total_rings = CN23XX_MAX_RINGS_PER_PF_PASS_1_0;
+ max_rings = CN23XX_MAX_RINGS_PER_PF_PASS_1_0;
+ max_possible_vfs = CN23XX_MAX_VFS_PER_PF_PASS_1_0;
break;
case OCTEON_CN23XX_REV_1_1:
- total_rings = CN23XX_MAX_RINGS_PER_PF_PASS_1_1;
+ max_rings = CN23XX_MAX_RINGS_PER_PF_PASS_1_1;
+ max_possible_vfs = CN23XX_MAX_VFS_PER_PF_PASS_1_1;
break;
default:
- total_rings = CN23XX_MAX_RINGS_PER_PF;
+ max_rings = CN23XX_MAX_RINGS_PER_PF;
+ max_possible_vfs = CN23XX_MAX_VFS_PER_PF;
break;
}
- if (!oct->sriov_info.num_pf_rings) {
- if (total_rings > num_present_cpus())
- num_pf_rings = num_present_cpus();
- else
- num_pf_rings = total_rings;
- } else {
- num_pf_rings = oct->sriov_info.num_pf_rings;
- if (num_pf_rings > total_rings) {
- dev_warn(&oct->pci_dev->dev,
- "num_queues_per_pf requested %u is more than available rings. Reducing to %u\n",
- num_pf_rings, total_rings);
- num_pf_rings = total_rings;
- }
- }
+ if (max_rings <= num_present_cpus())
+ num_pf_rings = 1;
+ else
+ num_pf_rings = num_present_cpus();
- total_rings = num_pf_rings;
+#ifdef CONFIG_PCI_IOV
+ max_vfs = min_t(u32,
+ (max_rings - num_pf_rings), max_possible_vfs);
+ rings_per_vf = 1;
+#else
+ max_vfs = 0;
+ rings_per_vf = 0;
+#endif
+
+ total_rings = num_pf_rings + max_vfs;
+
/* the first ring of the pf */
pf_srn = total_rings - num_pf_rings;
oct->sriov_info.trs = total_rings;
+ oct->sriov_info.max_vfs = max_vfs;
+ oct->sriov_info.rings_per_vf = rings_per_vf;
oct->sriov_info.pf_srn = pf_srn;
oct->sriov_info.num_pf_rings = num_pf_rings;
- dev_dbg(&oct->pci_dev->dev, "trs:%d pf_srn:%d num_pf_rings:%d\n",
- oct->sriov_info.trs, oct->sriov_info.pf_srn,
- oct->sriov_info.num_pf_rings);
+ dev_notice(&oct->pci_dev->dev, "trs:%d max_vfs:%d rings_per_vf:%d pf_srn:%d num_pf_rings:%d\n",
+ oct->sriov_info.trs, oct->sriov_info.max_vfs,
+ oct->sriov_info.rings_per_vf, oct->sriov_info.pf_srn,
+ oct->sriov_info.num_pf_rings);
+
+ oct->sriov_info.sriov_enabled = 0;
+
return 0;
}
@@ -1119,6 +1292,9 @@ int setup_cn23xx_octeon_pf_device(struct octeon_device *oct)
oct->fn_list.setup_iq_regs = cn23xx_setup_iq_regs;
oct->fn_list.setup_oq_regs = cn23xx_setup_oq_regs;
+ oct->fn_list.setup_mbox = cn23xx_setup_pf_mbox;
+ oct->fn_list.free_mbox = cn23xx_free_pf_mbox;
+
oct->fn_list.process_interrupt_regs = cn23xx_interrupt_handler;
oct->fn_list.msix_interrupt_handler = cn23xx_pf_msix_interrupt_handler;
@@ -1209,8 +1385,7 @@ void cn23xx_dump_iq_regs(struct octeon_device *oct)
dev_dbg(&oct->pci_dev->dev, "SLI_PKT[%d]_INPUT_CTL [0x%x]: 0x%016llx\n",
q_no, CN23XX_SLI_IQ_PKT_CONTROL64(q_no),
CVM_CAST64(octeon_read_csr64
- (oct,
- CN23XX_SLI_IQ_PKT_CONTROL64(q_no))));
+ (oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no))));
}
pci_read_config_dword(oct->pci_dev, CN23XX_CONFIG_PCIE_DEVCTL, ®val);
@@ -1235,3 +1410,24 @@ int cn23xx_fw_loaded(struct octeon_device *oct)
val = octeon_read_csr64(oct, CN23XX_SLI_SCRATCH1);
return (val >> 1) & 1ULL;
}
+
+void cn23xx_tell_vf_its_macaddr_changed(struct octeon_device *oct, int vfidx,
+ u8 *mac)
+{
+ if (oct->sriov_info.vf_drv_loaded_mask & BIT_ULL(vfidx)) {
+ struct octeon_mbox_cmd mbox_cmd;
+
+ mbox_cmd.msg.u64 = 0;
+ mbox_cmd.msg.s.type = OCTEON_MBOX_REQUEST;
+ mbox_cmd.msg.s.resp_needed = 0;
+ mbox_cmd.msg.s.cmd = OCTEON_PF_CHANGED_VF_MACADDR;
+ mbox_cmd.msg.s.len = 1;
+ mbox_cmd.recv_len = 0;
+ mbox_cmd.recv_status = 0;
+ mbox_cmd.fn = NULL;
+ mbox_cmd.fn_arg = 0;
+ ether_addr_copy(mbox_cmd.msg.s.params, mac);
+ mbox_cmd.q_no = vfidx * oct->sriov_info.rings_per_vf;
+ octeon_mbox_write(oct, &mbox_cmd);
+ }
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h
index 21b5c90..2fedd91 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h
@@ -1,34 +1,31 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
-
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
/*! \file cn23xx_device.h
* \brief Host Driver: Routines that perform CN23XX specific operations.
-*/
+ */
#ifndef __CN23XX_PF_DEVICE_H__
#define __CN23XX_PF_DEVICE_H__
#include "cn23xx_pf_regs.h"
+#define LIO_CMD_WAIT_TM 100
+
/* Register address and configuration for a CN23XX devices.
* If device specific changes need to be made then add a struct to include
* device specific fields as shown in the commented section
@@ -56,4 +53,7 @@ u32 cn23xx_pf_get_oq_ticks(struct octeon_device *oct, u32 time_intr_in_us);
void cn23xx_dump_pf_initialized_regs(struct octeon_device *oct);
int cn23xx_fw_loaded(struct octeon_device *oct);
+
+void cn23xx_tell_vf_its_macaddr_changed(struct octeon_device *oct, int vfidx,
+ u8 *mac);
#endif
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_regs.h b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_regs.h
index 03d79d9..e6d4ad9 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_regs.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_regs.h
@@ -1,29 +1,24 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
-
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
/*! \file cn23xx_regs.h
* \brief Host Driver: Register Address and Register Mask values for
* Octeon CN23XX devices.
-*/
+ */
#ifndef __CN23XX_PF_REGS_H__
#define __CN23XX_PF_REGS_H__
@@ -63,7 +58,7 @@
#define CN23XX_CONFIG_SRIOV_BAR_START 0x19C
#define CN23XX_CONFIG_SRIOV_BARX(i) \
- (CN23XX_CONFIG_SRIOV_BAR_START + (i * 4))
+ (CN23XX_CONFIG_SRIOV_BAR_START + ((i) * 4))
#define CN23XX_CONFIG_SRIOV_BAR_PF 0x08
#define CN23XX_CONFIG_SRIOV_BAR_64BIT 0x04
#define CN23XX_CONFIG_SRIOV_BAR_IO 0x01
@@ -513,7 +508,7 @@
/* 4 Registers (64 - bit) */
#define CN23XX_SLI_S2M_PORT_CTL_START 0x23D80
#define CN23XX_SLI_S2M_PORTX_CTL(port) \
- (CN23XX_SLI_S2M_PORT_CTL_START + (port * 0x10))
+ (CN23XX_SLI_S2M_PORT_CTL_START + ((port) * 0x10))
#define CN23XX_SLI_MAC_NUMBER 0x20050
@@ -554,26 +549,26 @@
* Provides DMA Engine Queue Enable
*/
#define CN23XX_DPI_DMA_ENG0_ENB 0x0001df0000000080ULL
-#define CN23XX_DPI_DMA_ENG_ENB(eng) (CN23XX_DPI_DMA_ENG0_ENB + (eng * 8))
+#define CN23XX_DPI_DMA_ENG_ENB(eng) (CN23XX_DPI_DMA_ENG0_ENB + ((eng) * 8))
/* 8 register (64-bit) - DPI_DMA(0..7)_REQQ_CTL
* Provides control bits for transaction on 8 Queues
*/
#define CN23XX_DPI_DMA_REQQ0_CTL 0x0001df0000000180ULL
#define CN23XX_DPI_DMA_REQQ_CTL(q_no) \
- (CN23XX_DPI_DMA_REQQ0_CTL + (q_no * 8))
+ (CN23XX_DPI_DMA_REQQ0_CTL + ((q_no) * 8))
/* 6 register (64-bit) - DPI_ENG(0..5)_BUF
* Provides DMA Engine FIFO (Queue) Size
*/
#define CN23XX_DPI_DMA_ENG0_BUF 0x0001df0000000880ULL
#define CN23XX_DPI_DMA_ENG_BUF(eng) \
- (CN23XX_DPI_DMA_ENG0_BUF + (eng * 8))
+ (CN23XX_DPI_DMA_ENG0_BUF + ((eng) * 8))
/* 4 Registers (64-bit) */
#define CN23XX_DPI_SLI_PRT_CFG_START 0x0001df0000000900ULL
#define CN23XX_DPI_SLI_PRTX_CFG(port) \
- (CN23XX_DPI_SLI_PRT_CFG_START + (port * 0x8))
+ (CN23XX_DPI_SLI_PRT_CFG_START + ((port) * 0x8))
/* Masks for DPI_DMA_CONTROL Register */
#define CN23XX_DPI_DMA_COMMIT_MODE BIT_ULL(58)
diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
index e779af8..bdec051 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
@@ -1,24 +1,20 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
#include <linux/pci.h>
#include <linux/netdevice.h>
#include "liquidio_common.h"
@@ -275,7 +271,6 @@ void lio_cn6xxx_setup_iq_regs(struct octeon_device *oct, u32 iq_no)
{
struct octeon_instr_queue *iq = oct->instr_queue[iq_no];
- /* Disable Packet-by-Packet mode; No Parse Mode or Skip length */
octeon_write_csr64(oct, CN6XXX_SLI_IQ_PKT_INSTR_HDR64(iq_no), 0);
/* Write the start of the input queue's ring and its size */
@@ -378,7 +373,7 @@ void lio_cn6xxx_disable_io_queues(struct octeon_device *oct)
/* Reset the doorbell register for each Input queue. */
for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
- if (!(oct->io_qmask.iq & (1ULL << i)))
+ if (!(oct->io_qmask.iq & BIT_ULL(i)))
continue;
octeon_write_csr(oct, CN6XXX_SLI_IQ_DOORBELL(i), 0xFFFFFFFF);
d32 = octeon_read_csr(oct, CN6XXX_SLI_IQ_DOORBELL(i));
@@ -400,9 +395,8 @@ void lio_cn6xxx_disable_io_queues(struct octeon_device *oct)
;
/* Reset the doorbell register for each Output queue. */
- /* for (i = 0; i < oct->num_oqs; i++) { */
for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
- if (!(oct->io_qmask.oq & (1ULL << i)))
+ if (!(oct->io_qmask.oq & BIT_ULL(i)))
continue;
octeon_write_csr(oct, CN6XXX_SLI_OQ_PKTS_CREDIT(i), 0xFFFFFFFF);
d32 = octeon_read_csr(oct, CN6XXX_SLI_OQ_PKTS_CREDIT(i));
@@ -537,15 +531,14 @@ static int lio_cn6xxx_process_droq_intr_regs(struct octeon_device *oct)
oct->droq_intr = 0;
- /* for (oq_no = 0; oq_no < oct->num_oqs; oq_no++) { */
for (oq_no = 0; oq_no < MAX_OCTEON_OUTPUT_QUEUES(oct); oq_no++) {
- if (!(droq_mask & (1ULL << oq_no)))
+ if (!(droq_mask & BIT_ULL(oq_no)))
continue;
droq = oct->droq[oq_no];
pkt_count = octeon_droq_check_hw_for_pkts(droq);
if (pkt_count) {
- oct->droq_intr |= (1ULL << oq_no);
+ oct->droq_intr |= BIT_ULL(oq_no);
if (droq->ops.poll_mode) {
u32 value;
u32 reg;
@@ -721,8 +714,6 @@ int lio_setup_cn66xx_octeon_device(struct octeon_device *oct)
int lio_validate_cn6xxx_config_info(struct octeon_device *oct,
struct octeon_config *conf6xxx)
{
- /* int total_instrs = 0; */
-
if (CFG_GET_IQ_MAX_Q(conf6xxx) > CN6XXX_MAX_INPUT_QUEUES) {
dev_err(&oct->pci_dev->dev, "%s: Num IQ (%d) exceeds Max (%d)\n",
__func__, CFG_GET_IQ_MAX_Q(conf6xxx),
diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h
index a40a913..8ed57134 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h
@@ -1,25 +1,20 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
-
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
/*! \file cn66xx_device.h
* \brief Host Driver: Routines that perform CN66XX specific operations.
*/
@@ -96,8 +91,8 @@ void lio_cn6xxx_setup_reg_address(struct octeon_device *oct, void *chip,
struct octeon_reg_list *reg_list);
u32 lio_cn6xxx_coprocessor_clock(struct octeon_device *oct);
u32 lio_cn6xxx_get_oq_ticks(struct octeon_device *oct, u32 time_intr_in_us);
-int lio_setup_cn66xx_octeon_device(struct octeon_device *);
+int lio_setup_cn66xx_octeon_device(struct octeon_device *oct);
int lio_validate_cn6xxx_config_info(struct octeon_device *oct,
- struct octeon_config *);
+ struct octeon_config *conf6xxx);
#endif
diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h b/drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h
index 5e3aff2..b248966 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h
@@ -1,25 +1,20 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
-
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
/*! \file cn66xx_regs.h
* \brief Host Driver: Register Address and Register Mask values for
* Octeon CN66XX devices.
@@ -443,10 +438,10 @@
#define CN6XXX_SLI_S2M_PORT0_CTL 0x3D80
#define CN6XXX_SLI_S2M_PORT1_CTL 0x3D90
#define CN6XXX_SLI_S2M_PORTX_CTL(port) \
- (CN6XXX_SLI_S2M_PORT0_CTL + (port * 0x10))
+ (CN6XXX_SLI_S2M_PORT0_CTL + ((port) * 0x10))
#define CN6XXX_SLI_INT_ENB64(port) \
- (CN6XXX_SLI_INT_ENB64_PORT0 + (port * 0x10))
+ (CN6XXX_SLI_INT_ENB64_PORT0 + ((port) * 0x10))
#define CN6XXX_SLI_MAC_NUMBER 0x3E00
@@ -458,7 +453,7 @@
#define CN6XXX_PCI_BAR1_OFFSET 0x8
#define CN6XXX_BAR1_REG(idx, port) \
- (CN6XXX_BAR1_INDEX_START + (port * CN6XXX_PEM_OFFSET) + \
+ (CN6XXX_BAR1_INDEX_START + ((port) * CN6XXX_PEM_OFFSET) + \
(CN6XXX_PCI_BAR1_OFFSET * (idx)))
/*############################ DPI #########################*/
@@ -476,17 +471,17 @@
#define CN6XXX_DPI_DMA_ENG0_ENB 0x0001df0000000080ULL
#define CN6XXX_DPI_DMA_ENG_ENB(q_no) \
- (CN6XXX_DPI_DMA_ENG0_ENB + (q_no * 8))
+ (CN6XXX_DPI_DMA_ENG0_ENB + ((q_no) * 8))
#define CN6XXX_DPI_DMA_ENG0_BUF 0x0001df0000000880ULL
#define CN6XXX_DPI_DMA_ENG_BUF(q_no) \
- (CN6XXX_DPI_DMA_ENG0_BUF + (q_no * 8))
+ (CN6XXX_DPI_DMA_ENG0_BUF + ((q_no) * 8))
#define CN6XXX_DPI_SLI_PRT0_CFG 0x0001df0000000900ULL
#define CN6XXX_DPI_SLI_PRT1_CFG 0x0001df0000000908ULL
#define CN6XXX_DPI_SLI_PRTX_CFG(port) \
- (CN6XXX_DPI_SLI_PRT0_CFG + (port * 0x10))
+ (CN6XXX_DPI_SLI_PRT0_CFG + ((port) * 0x10))
#define CN6XXX_DPI_DMA_COMMIT_MODE BIT_ULL(58)
#define CN6XXX_DPI_DMA_PKT_HP BIT_ULL(57)
diff --git a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c
index dbf3566..50b533f 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c
@@ -1,24 +1,20 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
#include <linux/pci.h>
#include <linux/netdevice.h>
#include "liquidio_common.h"
@@ -76,7 +72,7 @@ static void lio_cn68xx_setup_pkt_ctl_regs(struct octeon_device *oct)
pktctl = octeon_read_csr64(oct, CN6XXX_SLI_PKT_CTL);
/* 68XX specific */
- max_oqs = CFG_GET_OQ_MAX_Q(CHIP_FIELD(oct, cn6xxx, conf));
+ max_oqs = CFG_GET_OQ_MAX_Q(CHIP_CONF(oct, cn6xxx));
tx_pipe = octeon_read_csr64(oct, CN68XX_SLI_TX_PIPE);
tx_pipe &= 0xffffffffff00ffffULL; /* clear out NUMP field */
tx_pipe |= max_oqs << 16; /* put max_oqs in NUMP field */
diff --git a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.h b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.h
index ea7bdcc..66b8d6b 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.h
@@ -1,25 +1,20 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
-
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
/*! \file cn68xx_device.h
* \brief Host Driver: Routines that perform CN68XX specific operations.
*/
diff --git a/drivers/net/ethernet/cavium/liquidio/cn68xx_regs.h b/drivers/net/ethernet/cavium/liquidio/cn68xx_regs.h
index d45a0f4..0b742f0 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn68xx_regs.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn68xx_regs.h
@@ -1,25 +1,20 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
-
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
/*! \file cn68xx_regs.h
* \brief Host Driver: Register Address and Register Mask values for
* Octeon CN68XX devices. The register map for CN66XX is the same
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index 201eddb..403bcaa 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -1,24 +1,20 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
#include <linux/pci.h>
#include <linux/if_vlan.h>
#include "liquidio_common.h"
@@ -264,3 +260,34 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
nctrl->ncmd.s.cmd);
}
}
+
+void octeon_pf_changed_vf_macaddr(struct octeon_device *oct, u8 *mac)
+{
+ bool macaddr_changed = false;
+ struct net_device *netdev;
+ struct lio *lio;
+
+ rtnl_lock();
+
+ netdev = oct->props[0].netdev;
+ lio = GET_LIO(netdev);
+
+ lio->linfo.macaddr_is_admin_asgnd = true;
+
+ if (!ether_addr_equal(netdev->dev_addr, mac)) {
+ macaddr_changed = true;
+ ether_addr_copy(netdev->dev_addr, mac);
+ ether_addr_copy(((u8 *)&lio->linfo.hw_addr) + 2, mac);
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, netdev);
+ }
+
+ rtnl_unlock();
+
+ if (macaddr_changed)
+ dev_info(&oct->pci_dev->dev,
+ "PF changed VF's MAC address to %pM\n", mac);
+
+ /* no need to notify the firmware of the macaddr change because
+ * the PF did that already
+ */
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
index f163e0a..e233796 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -1,24 +1,20 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
#include <linux/netdevice.h>
#include <linux/net_tstamp.h>
#include <linux/pci.h>
@@ -74,7 +70,6 @@ enum {
INTERFACE_MODE_MIXED,
};
-#define ARRAY_LENGTH(a) (sizeof(a) / sizeof((a)[0]))
#define OCT_ETHTOOL_REGDUMP_LEN 4096
#define OCT_ETHTOOL_REGDUMP_LEN_23XX (4096 * 11)
#define OCT_ETHTOOL_REGSVER 1
@@ -87,9 +82,9 @@ static const char oct_stats_strings[][ETH_GSTRING_LEN] = {
"tx_bytes",
"rx_errors", /*jabber_err+l2_err+frame_err */
"tx_errors", /*fw_err_pko+fw_err_link+fw_err_drop */
- "rx_dropped", /*st->fromwire.total_rcvd - st->fromwire.fw_total_rcvd
- *+st->fromwire.dmac_drop + st->fromwire.fw_err_drop
- */
+ "rx_dropped", /*st->fromwire.total_rcvd - st->fromwire.fw_total_rcvd +
+ *st->fromwire.dmac_drop + st->fromwire.fw_err_drop
+ */
"tx_dropped",
"tx_total_sent",
@@ -259,14 +254,14 @@ lio_ethtool_get_channels(struct net_device *dev,
u32 max_rx = 0, max_tx = 0, tx_count = 0, rx_count = 0;
if (OCTEON_CN6XXX(oct)) {
- struct octeon_config *conf6x = CHIP_FIELD(oct, cn6xxx, conf);
+ struct octeon_config *conf6x = CHIP_CONF(oct, cn6xxx);
max_rx = CFG_GET_OQ_MAX_Q(conf6x);
max_tx = CFG_GET_IQ_MAX_Q(conf6x);
rx_count = CFG_GET_NUM_RXQS_NIC_IF(conf6x, lio->ifidx);
tx_count = CFG_GET_NUM_TXQS_NIC_IF(conf6x, lio->ifidx);
} else if (OCTEON_CN23XX_PF(oct)) {
- struct octeon_config *conf23 = CHIP_FIELD(oct, cn23xx_pf, conf);
+ struct octeon_config *conf23 = CHIP_CONF(oct, cn23xx_pf);
max_rx = CFG_GET_OQ_MAX_Q(conf23);
max_tx = CFG_GET_IQ_MAX_Q(conf23);
@@ -589,14 +584,14 @@ lio_ethtool_get_ringparam(struct net_device *netdev,
rx_pending = 0;
if (OCTEON_CN6XXX(oct)) {
- struct octeon_config *conf6x = CHIP_FIELD(oct, cn6xxx, conf);
+ struct octeon_config *conf6x = CHIP_CONF(oct, cn6xxx);
tx_max_pending = CN6XXX_MAX_IQ_DESCRIPTORS;
rx_max_pending = CN6XXX_MAX_OQ_DESCRIPTORS;
rx_pending = CFG_GET_NUM_RX_DESCS_NIC_IF(conf6x, lio->ifidx);
tx_pending = CFG_GET_NUM_TX_DESCS_NIC_IF(conf6x, lio->ifidx);
} else if (OCTEON_CN23XX_PF(oct)) {
- struct octeon_config *conf23 = CHIP_FIELD(oct, cn23xx_pf, conf);
+ struct octeon_config *conf23 = CHIP_CONF(oct, cn23xx_pf);
tx_max_pending = CN23XX_MAX_IQ_DESCRIPTORS;
rx_max_pending = CN23XX_MAX_OQ_DESCRIPTORS;
@@ -757,9 +752,6 @@ lio_get_ethtool_stats(struct net_device *netdev,
/*sum of oct->instr_queue[iq_no]->stats.tx_dropped */
data[i++] = CVM_CAST64(netstats->tx_dropped);
- /*data[i++] = CVM_CAST64(stats->multicast); */
- /*data[i++] = CVM_CAST64(stats->collisions); */
-
/* firmware tx stats */
/*per_core_stats[cvmx_get_core_num()].link_stats[mdata->from_ifidx].
*fromhost.fw_total_sent
@@ -910,9 +902,8 @@ lio_get_ethtool_stats(struct net_device *netdev,
/*lio->link_changes*/
data[i++] = CVM_CAST64(lio->link_changes);
- /* TX -- lio_update_stats(lio); */
for (j = 0; j < MAX_OCTEON_INSTR_QUEUES(oct_dev); j++) {
- if (!(oct_dev->io_qmask.iq & (1ULL << j)))
+ if (!(oct_dev->io_qmask.iq & BIT_ULL(j)))
continue;
/*packets to network port*/
/*# of packets tx to network */
@@ -954,9 +945,8 @@ lio_get_ethtool_stats(struct net_device *netdev,
}
/* RX */
- /* for (j = 0; j < oct_dev->num_oqs; j++) { */
for (j = 0; j < MAX_OCTEON_OUTPUT_QUEUES(oct_dev); j++) {
- if (!(oct_dev->io_qmask.oq & (1ULL << j)))
+ if (!(oct_dev->io_qmask.oq & BIT_ULL(j)))
continue;
/*packets send to TCP/IP network stack */
@@ -1030,7 +1020,7 @@ static void lio_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
num_iq_stats = ARRAY_SIZE(oct_iq_stats_strings);
for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct_dev); i++) {
- if (!(oct_dev->io_qmask.iq & (1ULL << i)))
+ if (!(oct_dev->io_qmask.iq & BIT_ULL(i)))
continue;
for (j = 0; j < num_iq_stats; j++) {
sprintf(data, "tx-%d-%s", i,
@@ -1040,9 +1030,8 @@ static void lio_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
}
num_oq_stats = ARRAY_SIZE(oct_droq_stats_strings);
- /* for (i = 0; i < oct_dev->num_oqs; i++) { */
for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct_dev); i++) {
- if (!(oct_dev->io_qmask.oq & (1ULL << i)))
+ if (!(oct_dev->io_qmask.oq & BIT_ULL(i)))
continue;
for (j = 0; j < num_oq_stats; j++) {
sprintf(data, "rx-%d-%s", i,
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 71d01a7..3d05b2f 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -1,28 +1,22 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
-#include <linux/version.h>
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
#include <linux/pci.h>
#include <linux/firmware.h>
-#include <linux/ptp_clock_kernel.h>
#include <net/vxlan.h>
#include <linux/kthread.h>
#include "liquidio_common.h"
@@ -54,9 +48,6 @@ MODULE_PARM_DESC(ddr_timeout,
#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
-#define INCR_INSTRQUEUE_PKT_COUNT(octeon_dev_ptr, iq_no, field, count) \
- (octeon_dev_ptr->instr_queue[iq_no]->stats.field += count)
-
static int debug = -1;
module_param(debug, int, 0644);
MODULE_PARM_DESC(debug, "NETIF_MSG debug bits");
@@ -65,10 +56,6 @@ static char fw_type[LIO_MAX_FW_TYPE_LEN];
module_param_string(fw_type, fw_type, sizeof(fw_type), 0000);
MODULE_PARM_DESC(fw_type, "Type of firmware to be loaded. Default \"nic\"");
-static int conf_type;
-module_param(conf_type, int, 0);
-MODULE_PARM_DESC(conf_type, "select octeon configuration 0 default 1 ovs");
-
static int ptp_enable = 1;
/* Bit mask values for lio->ifstate */
@@ -180,6 +167,10 @@ struct octeon_device_priv {
unsigned long napi_mask;
};
+#ifdef CONFIG_PCI_IOV
+static int liquidio_enable_sriov(struct pci_dev *dev, int num_vfs);
+#endif
+
static int octeon_device_init(struct octeon_device *);
static int liquidio_stop(struct net_device *netdev);
static void liquidio_remove(struct pci_dev *pdev);
@@ -197,9 +188,8 @@ static void octeon_droq_bh(unsigned long pdev)
struct octeon_device_priv *oct_priv =
(struct octeon_device_priv *)oct->priv;
- /* for (q_no = 0; q_no < oct->num_oqs; q_no++) { */
for (q_no = 0; q_no < MAX_OCTEON_OUTPUT_QUEUES(oct); q_no++) {
- if (!(oct->io_qmask.oq & (1ULL << q_no)))
+ if (!(oct->io_qmask.oq & BIT_ULL(q_no)))
continue;
reschedule |= octeon_droq_process_packets(oct, oct->droq[q_no],
MAX_PACKET_BUDGET);
@@ -234,7 +224,7 @@ static int lio_wait_for_oq_pkts(struct octeon_device *oct)
pending_pkts = 0;
for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
- if (!(oct->io_qmask.oq & (1ULL << i)))
+ if (!(oct->io_qmask.oq & BIT_ULL(i)))
continue;
pkt_cnt += octeon_droq_check_hw_for_pkts(oct->droq[i]);
}
@@ -316,7 +306,7 @@ static inline void pcierror_quiesce_device(struct octeon_device *oct)
for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
struct octeon_instr_queue *iq;
- if (!(oct->io_qmask.iq & (1ULL << i)))
+ if (!(oct->io_qmask.iq & BIT_ULL(i)))
continue;
iq = oct->instr_queue[i];
@@ -382,7 +372,6 @@ static void stop_pci_io(struct octeon_device *oct)
dev_dbg(&oct->pci_dev->dev, "Device state is now %s\n",
lio_get_state_string(&oct->status));
- /* cn63xx_cleanup_aer_uncorrect_error_status(oct->pci_dev); */
/* making it a common function for all OCTEON models */
cleanup_aer_uncorrect_error_status(oct->pci_dev);
}
@@ -518,6 +507,9 @@ static struct pci_driver liquidio_pci_driver = {
.suspend = liquidio_suspend,
.resume = liquidio_resume,
#endif
+#ifdef CONFIG_PCI_IOV
+ .sriov_configure = liquidio_enable_sriov,
+#endif
};
/**
@@ -763,6 +755,7 @@ static void delete_glists(struct lio *lio)
}
kfree((void *)lio->glist);
+ kfree((void *)lio->glist_lock);
}
/**
@@ -933,7 +926,6 @@ static inline void update_link_status(struct net_device *netdev,
if (lio->linfo.link.s.link_up) {
netif_carrier_on(netdev);
- /* start_txq(netdev); */
txqs_wake(netdev);
} else {
netif_carrier_off(netdev);
@@ -1011,7 +1003,7 @@ static void liquidio_schedule_droq_pkt_handlers(struct octeon_device *oct)
if (oct->int_status & OCT_DEV_INTR_PKT_DATA) {
for (oq_no = 0; oq_no < MAX_OCTEON_OUTPUT_QUEUES(oct);
oq_no++) {
- if (!(oct->droq_intr & (1ULL << oq_no)))
+ if (!(oct->droq_intr & BIT_ULL(oq_no)))
continue;
droq = oct->droq[oq_no];
@@ -1322,6 +1314,7 @@ liquidio_probe(struct pci_dev *pdev,
complete(&first_stage);
if (octeon_device_init(oct_dev)) {
+ complete(&hs->init);
liquidio_remove(pdev);
return -ENOMEM;
}
@@ -1346,7 +1339,15 @@ liquidio_probe(struct pci_dev *pdev,
oct_dev->watchdog_task = kthread_create(
liquidio_watchdog, oct_dev,
"liowd/%02hhx:%02hhx.%hhx", bus, device, function);
- wake_up_process(oct_dev->watchdog_task);
+ if (!IS_ERR(oct_dev->watchdog_task)) {
+ wake_up_process(oct_dev->watchdog_task);
+ } else {
+ oct_dev->watchdog_task = NULL;
+ dev_err(&oct_dev->pci_dev->dev,
+ "failed to create kernel_thread\n");
+ liquidio_remove(pdev);
+ return -1;
+ }
}
}
@@ -1410,6 +1411,8 @@ static void octeon_destroy_resources(struct octeon_device *oct)
if (lio_wait_for_oq_pkts(oct))
dev_err(&oct->pci_dev->dev, "OQ had pending packets\n");
+ /* fallthrough */
+ case OCT_DEV_INTR_SET_DONE:
/* Disable interrupts */
oct->fn_list.disable_interrupt(oct, OCTEON_ALL_INTR);
@@ -1436,12 +1439,20 @@ static void octeon_destroy_resources(struct octeon_device *oct)
pci_disable_msi(oct->pci_dev);
}
+ /* fallthrough */
+ case OCT_DEV_MSIX_ALLOC_VECTOR_DONE:
if (OCTEON_CN23XX_PF(oct))
octeon_free_ioq_vector(oct);
+
+ /* fallthrough */
+ case OCT_DEV_MBOX_SETUP_DONE:
+ if (OCTEON_CN23XX_PF(oct))
+ oct->fn_list.free_mbox(oct);
+
/* fallthrough */
case OCT_DEV_IN_RESET:
case OCT_DEV_DROQ_INIT_DONE:
- /*atomic_set(&oct->status, OCT_DEV_DROQ_INIT_DONE);*/
+ /* Wait for any pending operations */
mdelay(100);
for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
if (!(oct->io_qmask.oq & BIT_ULL(i)))
@@ -1472,6 +1483,10 @@ static void octeon_destroy_resources(struct octeon_device *oct)
continue;
octeon_delete_instr_queue(oct, i);
}
+#ifdef CONFIG_PCI_IOV
+ if (oct->sriov_info.sriov_enabled)
+ pci_disable_sriov(oct->pci_dev);
+#endif
/* fallthrough */
case OCT_DEV_SC_BUFF_POOL_INIT_DONE:
octeon_free_sc_buffer_pool(oct);
@@ -1491,10 +1506,13 @@ static void octeon_destroy_resources(struct octeon_device *oct)
octeon_unmap_pci_barx(oct, 1);
/* fallthrough */
- case OCT_DEV_BEGIN_STATE:
+ case OCT_DEV_PCI_ENABLE_DONE:
+ pci_clear_master(oct->pci_dev);
/* Disable the device, releasing the PCI INT */
pci_disable_device(oct->pci_dev);
+ /* fallthrough */
+ case OCT_DEV_BEGIN_STATE:
/* Nothing to be done here either */
break;
} /* end switch (oct->status) */
@@ -1764,6 +1782,7 @@ static int octeon_pci_os_setup(struct octeon_device *oct)
if (dma_set_mask_and_coherent(&oct->pci_dev->dev, DMA_BIT_MASK(64))) {
dev_err(&oct->pci_dev->dev, "Unexpected DMA device capability\n");
+ pci_disable_device(oct->pci_dev);
return 1;
}
@@ -2426,7 +2445,6 @@ static int liquidio_napi_poll(struct napi_struct *napi, int budget)
* Return back if tx_done is false.
*/
update_txq_status(oct, iq_no);
- /*tx_done = (iq->flush_index == iq->octeon_read_index);*/
} else {
dev_err(&oct->pci_dev->dev, "%s: iq (%d) num invalid\n",
__func__, iq_no);
@@ -3556,7 +3574,152 @@ static void liquidio_del_vxlan_port(struct net_device *netdev,
OCTNET_CMD_VXLAN_PORT_DEL);
}
-static struct net_device_ops lionetdevops = {
+static int __liquidio_set_vf_mac(struct net_device *netdev, int vfidx,
+ u8 *mac, bool is_admin_assigned)
+{
+ struct lio *lio = GET_LIO(netdev);
+ struct octeon_device *oct = lio->oct_dev;
+ struct octnic_ctrl_pkt nctrl;
+
+ if (!is_valid_ether_addr(mac))
+ return -EINVAL;
+
+ if (vfidx < 0 || vfidx >= oct->sriov_info.max_vfs)
+ return -EINVAL;
+
+ memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
+ nctrl.ncmd.u64 = 0;
+ nctrl.ncmd.s.cmd = OCTNET_CMD_CHANGE_MACADDR;
+ /* vfidx is 0 based, but vf_num (param1) is 1 based */
+ nctrl.ncmd.s.param1 = vfidx + 1;
+ nctrl.ncmd.s.param2 = (is_admin_assigned ? 1 : 0);
+ nctrl.ncmd.s.more = 1;
+ nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
+ nctrl.cb_fn = 0;
+ nctrl.wait_time = LIO_CMD_WAIT_TM;
+
+ nctrl.udd[0] = 0;
+ /* The MAC Address is presented in network byte order. */
+ ether_addr_copy((u8 *)&nctrl.udd[0] + 2, mac);
+
+ oct->sriov_info.vf_macaddr[vfidx] = nctrl.udd[0];
+
+ octnet_send_nic_ctrl_pkt(oct, &nctrl);
+
+ return 0;
+}
+
+static int liquidio_set_vf_mac(struct net_device *netdev, int vfidx, u8 *mac)
+{
+ struct lio *lio = GET_LIO(netdev);
+ struct octeon_device *oct = lio->oct_dev;
+ int retval;
+
+ retval = __liquidio_set_vf_mac(netdev, vfidx, mac, true);
+ if (!retval)
+ cn23xx_tell_vf_its_macaddr_changed(oct, vfidx, mac);
+
+ return retval;
+}
+
+static int liquidio_set_vf_vlan(struct net_device *netdev, int vfidx,
+ u16 vlan, u8 qos, __be16 vlan_proto)
+{
+ struct lio *lio = GET_LIO(netdev);
+ struct octeon_device *oct = lio->oct_dev;
+ struct octnic_ctrl_pkt nctrl;
+ u16 vlantci;
+
+ if (vfidx < 0 || vfidx >= oct->sriov_info.num_vfs_alloced)
+ return -EINVAL;
+
+ if (vlan_proto != htons(ETH_P_8021Q))
+ return -EPROTONOSUPPORT;
+
+ if (vlan >= VLAN_N_VID || qos > 7)
+ return -EINVAL;
+
+ if (vlan)
+ vlantci = vlan | (u16)qos << VLAN_PRIO_SHIFT;
+ else
+ vlantci = 0;
+
+ if (oct->sriov_info.vf_vlantci[vfidx] == vlantci)
+ return 0;
+
+ memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
+ if (vlan)
+ nctrl.ncmd.s.cmd = OCTNET_CMD_ADD_VLAN_FILTER;
+ else
+ nctrl.ncmd.s.cmd = OCTNET_CMD_DEL_VLAN_FILTER;
+
+ nctrl.ncmd.s.param1 = vlantci;
+ nctrl.ncmd.s.param2 =
+ vfidx + 1; /* vfidx is 0 based, but vf_num (param2) is 1 based */
+ nctrl.ncmd.s.more = 0;
+ nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
+ nctrl.cb_fn = 0;
+ nctrl.wait_time = LIO_CMD_WAIT_TM;
+
+ octnet_send_nic_ctrl_pkt(oct, &nctrl);
+
+ oct->sriov_info.vf_vlantci[vfidx] = vlantci;
+
+ return 0;
+}
+
+static int liquidio_get_vf_config(struct net_device *netdev, int vfidx,
+ struct ifla_vf_info *ivi)
+{
+ struct lio *lio = GET_LIO(netdev);
+ struct octeon_device *oct = lio->oct_dev;
+ u8 *macaddr;
+
+ if (vfidx < 0 || vfidx >= oct->sriov_info.num_vfs_alloced)
+ return -EINVAL;
+
+ ivi->vf = vfidx;
+ macaddr = 2 + (u8 *)&oct->sriov_info.vf_macaddr[vfidx];
+ ether_addr_copy(&ivi->mac[0], macaddr);
+ ivi->vlan = oct->sriov_info.vf_vlantci[vfidx] & VLAN_VID_MASK;
+ ivi->qos = oct->sriov_info.vf_vlantci[vfidx] >> VLAN_PRIO_SHIFT;
+ ivi->linkstate = oct->sriov_info.vf_linkstate[vfidx];
+ return 0;
+}
+
+static int liquidio_set_vf_link_state(struct net_device *netdev, int vfidx,
+ int linkstate)
+{
+ struct lio *lio = GET_LIO(netdev);
+ struct octeon_device *oct = lio->oct_dev;
+ struct octnic_ctrl_pkt nctrl;
+
+ if (vfidx < 0 || vfidx >= oct->sriov_info.num_vfs_alloced)
+ return -EINVAL;
+
+ if (oct->sriov_info.vf_linkstate[vfidx] == linkstate)
+ return 0;
+
+ memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+ nctrl.ncmd.s.cmd = OCTNET_CMD_SET_VF_LINKSTATE;
+ nctrl.ncmd.s.param1 =
+ vfidx + 1; /* vfidx is 0 based, but vf_num (param1) is 1 based */
+ nctrl.ncmd.s.param2 = linkstate;
+ nctrl.ncmd.s.more = 0;
+ nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
+ nctrl.cb_fn = 0;
+ nctrl.wait_time = LIO_CMD_WAIT_TM;
+
+ octnet_send_nic_ctrl_pkt(oct, &nctrl);
+
+ oct->sriov_info.vf_linkstate[vfidx] = linkstate;
+
+ return 0;
+}
+
+static const struct net_device_ops lionetdevops = {
.ndo_open = liquidio_open,
.ndo_stop = liquidio_stop,
.ndo_start_xmit = liquidio_xmit,
@@ -3573,6 +3736,11 @@ static struct net_device_ops lionetdevops = {
.ndo_set_features = liquidio_set_features,
.ndo_udp_tunnel_add = liquidio_add_vxlan_port,
.ndo_udp_tunnel_del = liquidio_del_vxlan_port,
+ .ndo_set_vf_mac = liquidio_set_vf_mac,
+ .ndo_set_vf_vlan = liquidio_set_vf_vlan,
+ .ndo_get_vf_config = liquidio_get_vf_config,
+ .ndo_set_vf_link_state = liquidio_set_vf_link_state,
+ .ndo_select_queue = select_q
};
/** \brief Entry point for the liquidio module
@@ -3584,7 +3752,7 @@ static int __init liquidio_init(void)
init_completion(&first_stage);
- octeon_init_device_list(conf_type);
+ octeon_init_device_list(OCTEON_CONFIG_TYPE_DEFAULT);
if (liquidio_init_pci())
return -EINVAL;
@@ -3805,9 +3973,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
SET_NETDEV_DEV(netdev, &octeon_dev->pci_dev->dev);
- if (num_iqueues > 1)
- lionetdevops.ndo_select_queue = select_q;
-
/* Associate the routines that will handle different
* netdev tasks.
*/
@@ -3895,6 +4060,19 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
"if%d gmx: %d hw_addr: 0x%llx\n", i,
lio->linfo.gmxport, CVM_CAST64(lio->linfo.hw_addr));
+ for (j = 0; j < octeon_dev->sriov_info.max_vfs; j++) {
+ u8 vfmac[ETH_ALEN];
+
+ random_ether_addr(&vfmac[0]);
+ if (__liquidio_set_vf_mac(netdev, j,
+ &vfmac[0], false)) {
+ dev_err(&octeon_dev->pci_dev->dev,
+ "Error setting VF%d MAC address\n",
+ j);
+ goto setup_nic_dev_fail;
+ }
+ }
+
/* 64-bit swap required on LE machines */
octeon_swap_8B_data(&lio->linfo.hw_addr, 1);
for (j = 0; j < 6; j++)
@@ -3990,6 +4168,101 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
return -ENODEV;
}
+#ifdef CONFIG_PCI_IOV
+static int octeon_enable_sriov(struct octeon_device *oct)
+{
+ unsigned int num_vfs_alloced = oct->sriov_info.num_vfs_alloced;
+ struct pci_dev *vfdev;
+ int err;
+ u32 u;
+
+ if (OCTEON_CN23XX_PF(oct) && num_vfs_alloced) {
+ err = pci_enable_sriov(oct->pci_dev,
+ oct->sriov_info.num_vfs_alloced);
+ if (err) {
+ dev_err(&oct->pci_dev->dev,
+ "OCTEON: Failed to enable PCI sriov: %d\n",
+ err);
+ oct->sriov_info.num_vfs_alloced = 0;
+ return err;
+ }
+ oct->sriov_info.sriov_enabled = 1;
+
+ /* init lookup table that maps DPI ring number to VF pci_dev
+ * struct pointer
+ */
+ u = 0;
+ vfdev = pci_get_device(PCI_VENDOR_ID_CAVIUM,
+ OCTEON_CN23XX_VF_VID, NULL);
+ while (vfdev) {
+ if (vfdev->is_virtfn &&
+ (vfdev->physfn == oct->pci_dev)) {
+ oct->sriov_info.dpiring_to_vfpcidev_lut[u] =
+ vfdev;
+ u += oct->sriov_info.rings_per_vf;
+ }
+ vfdev = pci_get_device(PCI_VENDOR_ID_CAVIUM,
+ OCTEON_CN23XX_VF_VID, vfdev);
+ }
+ }
+
+ return num_vfs_alloced;
+}
+
+static int lio_pci_sriov_disable(struct octeon_device *oct)
+{
+ int u;
+
+ if (pci_vfs_assigned(oct->pci_dev)) {
+ dev_err(&oct->pci_dev->dev, "VFs are still assigned to VMs.\n");
+ return -EPERM;
+ }
+
+ pci_disable_sriov(oct->pci_dev);
+
+ u = 0;
+ while (u < MAX_POSSIBLE_VFS) {
+ oct->sriov_info.dpiring_to_vfpcidev_lut[u] = NULL;
+ u += oct->sriov_info.rings_per_vf;
+ }
+
+ oct->sriov_info.num_vfs_alloced = 0;
+ dev_info(&oct->pci_dev->dev, "oct->pf_num:%d disabled VFs\n",
+ oct->pf_num);
+
+ return 0;
+}
+
+static int liquidio_enable_sriov(struct pci_dev *dev, int num_vfs)
+{
+ struct octeon_device *oct = pci_get_drvdata(dev);
+ int ret = 0;
+
+ if ((num_vfs == oct->sriov_info.num_vfs_alloced) &&
+ (oct->sriov_info.sriov_enabled)) {
+ dev_info(&oct->pci_dev->dev, "oct->pf_num:%d already enabled num_vfs:%d\n",
+ oct->pf_num, num_vfs);
+ return 0;
+ }
+
+ if (!num_vfs) {
+ ret = lio_pci_sriov_disable(oct);
+ } else if (num_vfs > oct->sriov_info.max_vfs) {
+ dev_err(&oct->pci_dev->dev,
+ "OCTEON: Max allowed VFs:%d user requested:%d",
+ oct->sriov_info.max_vfs, num_vfs);
+ ret = -EPERM;
+ } else {
+ oct->sriov_info.num_vfs_alloced = num_vfs;
+ ret = octeon_enable_sriov(oct);
+ dev_info(&oct->pci_dev->dev, "oct->pf_num:%d num_vfs:%d\n",
+ oct->pf_num, num_vfs);
+ }
+
+ return ret;
+}
+#endif
+
/**
* \brief initialize the NIC
* @param oct octeon device
@@ -4095,6 +4368,52 @@ static void nic_starter(struct work_struct *work)
complete(&handshake[oct->octeon_id].started);
}
+static int
+octeon_recv_vf_drv_notice(struct octeon_recv_info *recv_info, void *buf)
+{
+ struct octeon_device *oct = (struct octeon_device *)buf;
+ struct octeon_recv_pkt *recv_pkt = recv_info->recv_pkt;
+ int i, notice, vf_idx;
+ u64 *data, vf_num;
+
+ notice = recv_pkt->rh.r.ossp;
+ data = (u64 *)get_rbd(recv_pkt->buffer_ptr[0]);
+
+ /* the first 64-bit word of data is the vf_num */
+ vf_num = data[0];
+ octeon_swap_8B_data(&vf_num, 1);
+ vf_idx = (int)vf_num - 1;
+
+ if (notice == VF_DRV_LOADED) {
+ if (!(oct->sriov_info.vf_drv_loaded_mask & BIT_ULL(vf_idx))) {
+ oct->sriov_info.vf_drv_loaded_mask |= BIT_ULL(vf_idx);
+ dev_info(&oct->pci_dev->dev,
+ "driver for VF%d was loaded\n", vf_idx);
+ try_module_get(THIS_MODULE);
+ }
+ } else if (notice == VF_DRV_REMOVED) {
+ if (oct->sriov_info.vf_drv_loaded_mask & BIT_ULL(vf_idx)) {
+ oct->sriov_info.vf_drv_loaded_mask &= ~BIT_ULL(vf_idx);
+ dev_info(&oct->pci_dev->dev,
+ "driver for VF%d was removed\n", vf_idx);
+ module_put(THIS_MODULE);
+ }
+ } else if (notice == VF_DRV_MACADDR_CHANGED) {
+ u8 *b = (u8 *)&data[1];
+
+ oct->sriov_info.vf_macaddr[vf_idx] = data[1];
+ dev_info(&oct->pci_dev->dev,
+ "VF driver changed VF%d's MAC address to %pM\n",
+ vf_idx, b + 2);
+ }
+
+ for (i = 0; i < recv_pkt->buffer_count; i++)
+ recv_buffer_free(recv_pkt->buffer_ptr[i]);
+ octeon_free_recv_info(recv_info);
+
+ return 0;
+}
+
/**
* \brief Device initialization for each Octeon device that is probed
* @param octeon_dev octeon device
@@ -4114,6 +4433,8 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
if (octeon_pci_os_setup(octeon_dev))
return 1;
+ atomic_set(&octeon_dev->status, OCT_DEV_PCI_ENABLE_DONE);
+
/* Identify the Octeon type and map the BAR address space. */
if (octeon_chip_specific_setup(octeon_dev)) {
dev_err(&octeon_dev->pci_dev->dev, "Chip specific setup failed\n");
@@ -4153,6 +4474,9 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
octeon_core_drv_init,
octeon_dev);
+ octeon_register_dispatch_fn(octeon_dev, OPCODE_NIC,
+ OPCODE_NIC_VF_DRV_NOTICE,
+ octeon_recv_vf_drv_notice, octeon_dev);
INIT_DELAYED_WORK(&octeon_dev->nic_poll_work.work, nic_starter);
octeon_dev->nic_poll_work.ctxptr = (void *)octeon_dev;
schedule_delayed_work(&octeon_dev->nic_poll_work.work,
@@ -4182,9 +4506,6 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
if (octeon_setup_instr_queues(octeon_dev)) {
dev_err(&octeon_dev->pci_dev->dev,
"instruction queue initialization failed\n");
- /* On error, release any previously allocated queues */
- for (j = 0; j < octeon_dev->num_iqs; j++)
- octeon_delete_instr_queue(octeon_dev, j);
return 1;
}
atomic_set(&octeon_dev->status, OCT_DEV_INSTR_QUEUE_INIT_DONE);
@@ -4200,19 +4521,23 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
if (octeon_setup_output_queues(octeon_dev)) {
dev_err(&octeon_dev->pci_dev->dev, "Output queue initialization failed\n");
- /* Release any previously allocated queues */
- for (j = 0; j < octeon_dev->num_oqs; j++)
- octeon_delete_droq(octeon_dev, j);
return 1;
}
atomic_set(&octeon_dev->status, OCT_DEV_DROQ_INIT_DONE);
if (OCTEON_CN23XX_PF(octeon_dev)) {
+ if (octeon_dev->fn_list.setup_mbox(octeon_dev)) {
+ dev_err(&octeon_dev->pci_dev->dev, "OCTEON: Mailbox setup failed\n");
+ return 1;
+ }
+ atomic_set(&octeon_dev->status, OCT_DEV_MBOX_SETUP_DONE);
+
if (octeon_allocate_ioq_vector(octeon_dev)) {
dev_err(&octeon_dev->pci_dev->dev, "OCTEON: ioq vector allocation failed\n");
return 1;
}
+ atomic_set(&octeon_dev->status, OCT_DEV_MSIX_ALLOC_VECTOR_DONE);
} else {
/* The input and output queue registers were setup earlier (the
@@ -4240,6 +4565,8 @@ static int octeon_device_init(struct octeon_device *octeon_dev)
/* Enable Octeon device interrupts */
octeon_dev->fn_list.enable_interrupt(octeon_dev, OCTEON_ALL_INTR);
+ atomic_set(&octeon_dev->status, OCT_DEV_INTR_SET_DONE);
+
/* Enable the input and output queues for this Octeon device */
ret = octeon_dev->fn_list.enable_io_queues(octeon_dev);
if (ret) {
diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
index 0d990ac..f308ee4 100644
--- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
+++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
@@ -1,25 +1,20 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
-
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
/*! \file liquidio_common.h
* \brief Common: Structures and macros used in PCI-NIC package by core and
* host driver.
@@ -68,12 +63,10 @@ enum octeon_tag_type {
*/
#define OPCODE_CORE 0 /* used for generic core operations */
#define OPCODE_NIC 1 /* used for NIC operations */
-#define OPCODE_LAST OPCODE_NIC
-
/* Subcodes are used by host driver/apps to identify the sub-operation
* for the core. They only need to by unique for a given subsystem.
*/
-#define OPCODE_SUBCODE(op, sub) (((op & 0x0f) << 8) | ((sub) & 0x7f))
+#define OPCODE_SUBCODE(op, sub) ((((op) & 0x0f) << 8) | ((sub) & 0x7f))
/** OPCODE_CORE subcodes. For future use. */
@@ -89,13 +82,13 @@ enum octeon_tag_type {
#define OPCODE_NIC_TIMESTAMP 0x07
#define OPCODE_NIC_INTRMOD_CFG 0x08
#define OPCODE_NIC_IF_CFG 0x09
+#define OPCODE_NIC_VF_DRV_NOTICE 0x0A
+#define VF_DRV_LOADED 1
+#define VF_DRV_REMOVED -1
+#define VF_DRV_MACADDR_CHANGED 2
#define CORE_DRV_TEST_SCATTER_OP 0xFFF5
-#define OPCODE_SLOW_PATH(rh) \
- (OPCODE_SUBCODE(rh->r.opcode, rh->r.subcode) != \
- OPCODE_SUBCODE(OPCODE_NIC, OPCODE_NIC_NW_DATA))
-
/* Application codes advertised by the core driver initialization packet. */
#define CVM_DRV_APP_START 0x0
#define CVM_DRV_NO_APP 0
@@ -105,31 +98,15 @@ enum octeon_tag_type {
#define CVM_DRV_INVALID_APP (CVM_DRV_APP_START + 0x2)
#define CVM_DRV_APP_END (CVM_DRV_INVALID_APP - 1)
-/* Macro to increment index.
- * Index is incremented by count; if the sum exceeds
- * max, index is wrapped-around to the start.
- */
-#define INCR_INDEX(index, count, max) \
-do { \
- if (((index) + (count)) >= (max)) \
- index = ((index) + (count)) - (max); \
- else \
- index += (count); \
-} while (0)
+static inline u32 incr_index(u32 index, u32 count, u32 max)
+{
+ if ((index + count) >= max)
+ index = index + count - max;
+ else
+ index += count;
-#define INCR_INDEX_BY1(index, max) \
-do { \
- if ((++(index)) == (max)) \
- index = 0; \
-} while (0)
-
-#define DECR_INDEX(index, count, max) \
-do { \
- if ((count) > (index)) \
- index = ((max) - ((count - index))); \
- else \
- index -= count; \
-} while (0)
+ return index;
+}
#define OCT_BOARD_NAME 32
#define OCT_SERIAL_LEN 64
@@ -235,6 +212,7 @@ static inline void add_sg_size(struct octeon_sg_entry *sg_entry,
#define OCTNET_CMD_ID_ACTIVE 0x1a
+#define OCTNET_CMD_SET_VF_LINKSTATE 0x1c
#define OCTNET_CMD_VXLAN_PORT_ADD 0x0
#define OCTNET_CMD_VXLAN_PORT_DEL 0x1
#define OCTNET_CMD_RXCSUM_ENABLE 0x0
@@ -731,13 +709,15 @@ struct oct_link_info {
#ifdef __BIG_ENDIAN_BITFIELD
u64 gmxport:16;
- u64 rsvd:32;
+ u64 macaddr_is_admin_asgnd:1;
+ u64 rsvd:31;
u64 num_txpciq:8;
u64 num_rxpciq:8;
#else
u64 num_rxpciq:8;
u64 num_txpciq:8;
- u64 rsvd:32;
+ u64 rsvd:31;
+ u64 macaddr_is_admin_asgnd:1;
u64 gmxport:16;
#endif
@@ -827,6 +807,16 @@ struct oct_link_stats {
};
+static inline int opcode_slow_path(union octeon_rh *rh)
+{
+ u16 subcode1, subcode2;
+
+ subcode1 = OPCODE_SUBCODE((rh)->r.opcode, (rh)->r.subcode);
+ subcode2 = OPCODE_SUBCODE(OPCODE_NIC, OPCODE_NIC_NW_DATA);
+
+ return (subcode2 != subcode1);
+}
+
#define LIO68XX_LED_CTRL_ADDR 0x3501
#define LIO68XX_LED_CTRL_CFGON 0x1f
#define LIO68XX_LED_CTRL_CFGOFF 0x100
diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_image.h b/drivers/net/ethernet/cavium/liquidio/liquidio_image.h
index 93819bd..78a3685 100644
--- a/drivers/net/ethernet/cavium/liquidio/liquidio_image.h
+++ b/drivers/net/ethernet/cavium/liquidio/liquidio_image.h
@@ -1,24 +1,20 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
#ifndef _LIQUIDIO_IMAGE_H_
#define _LIQUIDIO_IMAGE_H_
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_config.h b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
index c765568..1cb3514 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_config.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
@@ -1,25 +1,20 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
-
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
/*! \file octeon_config.h
* \brief Host Driver: Configuration data structures for the host driver.
*/
@@ -65,9 +60,15 @@
#define DEFAULT_NUM_NIC_PORTS_68XX_210NV 2
/* CN23xx IQ configuration macros */
+#define CN23XX_MAX_VFS_PER_PF_PASS_1_0 8
+#define CN23XX_MAX_VFS_PER_PF_PASS_1_1 31
+#define CN23XX_MAX_VFS_PER_PF 63
+#define CN23XX_MAX_RINGS_PER_VF 8
+
#define CN23XX_MAX_RINGS_PER_PF_PASS_1_0 12
#define CN23XX_MAX_RINGS_PER_PF_PASS_1_1 32
#define CN23XX_MAX_RINGS_PER_PF 64
+#define CN23XX_MAX_RINGS_PER_VF 8
#define CN23XX_MAX_INPUT_QUEUES CN23XX_MAX_RINGS_PER_PF
#define CN23XX_MAX_IQ_DESCRIPTORS 2048
@@ -466,4 +467,7 @@ struct octeon_config {
#define MAX_POSSIBLE_OCTEON_INSTR_QUEUES CN23XX_MAX_INPUT_QUEUES
#define MAX_POSSIBLE_OCTEON_OUTPUT_QUEUES CN23XX_MAX_OUTPUT_QUEUES
+
+#define MAX_POSSIBLE_VFS 64
+
#endif /* __OCTEON_CONFIG_H__ */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_console.c b/drivers/net/ethernet/cavium/liquidio/octeon_console.c
index 01a50f3..3265e0b 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_console.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_console.c
@@ -1,25 +1,20 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
-
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
/**
* @file octeon_console.c
*/
@@ -76,9 +71,9 @@ MODULE_PARM_DESC(console_bitmask,
#define OCTEON_CONSOLE_POLL_INTERVAL_MS 100 /* 10 times per second */
/* First three members of cvmx_bootmem_desc are left in original
-** positions for backwards compatibility.
-** Assumes big endian target
-*/
+ * positions for backwards compatibility.
+ * Assumes big endian target
+ */
struct cvmx_bootmem_desc {
/** spinlock to control access to list */
u32 lock;
@@ -143,46 +138,6 @@ struct octeon_pci_console_desc {
};
/**
- * This macro returns the size of a member of a structure.
- * Logically it is the same as "sizeof(s::field)" in C++, but
- * C lacks the "::" operator.
- */
-#define SIZEOF_FIELD(s, field) sizeof(((s *)NULL)->field)
-
-/**
- * This macro returns a member of the cvmx_bootmem_desc
- * structure. These members can't be directly addressed as
- * they might be in memory not directly reachable. In the case
- * where bootmem is compiled with LINUX_HOST, the structure
- * itself might be located on a remote Octeon. The argument
- * "field" is the member name of the cvmx_bootmem_desc to read.
- * Regardless of the type of the field, the return type is always
- * a u64.
- */
-#define CVMX_BOOTMEM_DESC_GET_FIELD(oct, field) \
- __cvmx_bootmem_desc_get(oct, oct->bootmem_desc_addr, \
- offsetof(struct cvmx_bootmem_desc, field), \
- SIZEOF_FIELD(struct cvmx_bootmem_desc, field))
-
-#define __cvmx_bootmem_lock(flags) (flags = flags)
-#define __cvmx_bootmem_unlock(flags) (flags = flags)
-
-/**
- * This macro returns a member of the
- * cvmx_bootmem_named_block_desc structure. These members can't
- * be directly addressed as they might be in memory not directly
- * reachable. In the case where bootmem is compiled with
- * LINUX_HOST, the structure itself might be located on a remote
- * Octeon. The argument "field" is the member name of the
- * cvmx_bootmem_named_block_desc to read. Regardless of the type
- * of the field, the return type is always a u64. The "addr"
- * parameter is the physical address of the structure.
- */
-#define CVMX_BOOTMEM_NAMED_GET_FIELD(oct, addr, field) \
- __cvmx_bootmem_desc_get(oct, addr, \
- offsetof(struct cvmx_bootmem_named_block_desc, field), \
- SIZEOF_FIELD(struct cvmx_bootmem_named_block_desc, field))
-/**
* \brief determines if a given console has debug enabled.
* @param console console to check
* @returns 1 = enabled. 0 otherwise
@@ -263,10 +218,15 @@ static int __cvmx_bootmem_check_version(struct octeon_device *oct,
oct->bootmem_desc_addr =
octeon_read_device_mem64(oct,
BOOTLOADER_PCI_READ_DESC_ADDR);
- major_version =
- (u32)CVMX_BOOTMEM_DESC_GET_FIELD(oct, major_version);
- minor_version =
- (u32)CVMX_BOOTMEM_DESC_GET_FIELD(oct, minor_version);
+ major_version = (u32)__cvmx_bootmem_desc_get(
+ oct, oct->bootmem_desc_addr,
+ offsetof(struct cvmx_bootmem_desc, major_version),
+ FIELD_SIZEOF(struct cvmx_bootmem_desc, major_version));
+ minor_version = (u32)__cvmx_bootmem_desc_get(
+ oct, oct->bootmem_desc_addr,
+ offsetof(struct cvmx_bootmem_desc, minor_version),
+ FIELD_SIZEOF(struct cvmx_bootmem_desc, minor_version));
+
dev_dbg(&oct->pci_dev->dev, "%s: major_version=%d\n", __func__,
major_version);
if ((major_version > 3) ||
@@ -289,10 +249,20 @@ static const struct cvmx_bootmem_named_block_desc
u64 named_addr = cvmx_bootmem_phy_named_block_find(oct, name, flags);
if (named_addr) {
- desc->base_addr = CVMX_BOOTMEM_NAMED_GET_FIELD(oct, named_addr,
- base_addr);
- desc->size =
- CVMX_BOOTMEM_NAMED_GET_FIELD(oct, named_addr, size);
+ desc->base_addr = __cvmx_bootmem_desc_get(
+ oct, named_addr,
+ offsetof(struct cvmx_bootmem_named_block_desc,
+ base_addr),
+ FIELD_SIZEOF(
+ struct cvmx_bootmem_named_block_desc,
+ base_addr));
+ desc->size = __cvmx_bootmem_desc_get(oct, named_addr,
+ offsetof(struct cvmx_bootmem_named_block_desc,
+ size),
+ FIELD_SIZEOF(
+ struct cvmx_bootmem_named_block_desc,
+ size));
+
strncpy(desc->name, name, sizeof(desc->name));
desc->name[sizeof(desc->name) - 1] = 0;
return &oct->bootmem_named_block_desc;
@@ -307,22 +277,41 @@ static u64 cvmx_bootmem_phy_named_block_find(struct octeon_device *oct,
{
u64 result = 0;
- __cvmx_bootmem_lock(flags);
if (!__cvmx_bootmem_check_version(oct, 3)) {
u32 i;
- u64 named_block_array_addr =
- CVMX_BOOTMEM_DESC_GET_FIELD(oct,
- named_block_array_addr);
- u32 num_blocks = (u32)
- CVMX_BOOTMEM_DESC_GET_FIELD(oct, nb_num_blocks);
- u32 name_length = (u32)
- CVMX_BOOTMEM_DESC_GET_FIELD(oct, named_block_name_len);
+
+ u64 named_block_array_addr = __cvmx_bootmem_desc_get(
+ oct, oct->bootmem_desc_addr,
+ offsetof(struct cvmx_bootmem_desc,
+ named_block_array_addr),
+ FIELD_SIZEOF(struct cvmx_bootmem_desc,
+ named_block_array_addr));
+ u32 num_blocks = (u32)__cvmx_bootmem_desc_get(
+ oct, oct->bootmem_desc_addr,
+ offsetof(struct cvmx_bootmem_desc,
+ nb_num_blocks),
+ FIELD_SIZEOF(struct cvmx_bootmem_desc,
+ nb_num_blocks));
+
+ u32 name_length = (u32)__cvmx_bootmem_desc_get(
+ oct, oct->bootmem_desc_addr,
+ offsetof(struct cvmx_bootmem_desc,
+ named_block_name_len),
+ FIELD_SIZEOF(struct cvmx_bootmem_desc,
+ named_block_name_len));
+
u64 named_addr = named_block_array_addr;
for (i = 0; i < num_blocks; i++) {
- u64 named_size =
- CVMX_BOOTMEM_NAMED_GET_FIELD(oct, named_addr,
- size);
+ u64 named_size = __cvmx_bootmem_desc_get(
+ oct, named_addr,
+ offsetof(
+ struct cvmx_bootmem_named_block_desc,
+ size),
+ FIELD_SIZEOF(
+ struct cvmx_bootmem_named_block_desc,
+ size));
+
if (name && named_size) {
char *name_tmp =
kmalloc(name_length + 1, GFP_KERNEL);
@@ -347,7 +336,6 @@ static u64 cvmx_bootmem_phy_named_block_find(struct octeon_device *oct,
sizeof(struct cvmx_bootmem_named_block_desc);
}
}
- __cvmx_bootmem_unlock(flags);
return result;
}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index 586b688..79c8875 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -1,24 +1,20 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
#include <linux/pci.h>
#include <linux/netdevice.h>
#include <linux/vmalloc.h>
@@ -520,11 +516,6 @@ static struct octeon_config default_cn23xx_conf = {
}
};
-enum {
- OCTEON_CONFIG_TYPE_DEFAULT = 0,
- NUM_OCTEON_CONFS,
-};
-
static struct octeon_config_ptr {
u32 conf_type;
} oct_conf_info[MAX_OCTEON_DEVICES] = {
@@ -649,12 +640,12 @@ void octeon_free_device_mem(struct octeon_device *oct)
int i;
for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) {
- if (oct->io_qmask.oq & (1ULL << i))
+ if (oct->io_qmask.oq & BIT_ULL(i))
vfree(oct->droq[i]);
}
for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
- if (oct->io_qmask.iq & (1ULL << i))
+ if (oct->io_qmask.iq & BIT_ULL(i))
vfree(oct->instr_queue[i]);
}
@@ -767,6 +758,7 @@ octeon_allocate_ioq_vector(struct octeon_device *oct)
ioq_vector->oct_dev = oct;
ioq_vector->iq_index = i;
ioq_vector->droq_index = i;
+ ioq_vector->mbox = oct->mbox[i];
cpu_num = i % num_online_cpus();
cpumask_set_cpu(cpu_num, &ioq_vector->affinity_mask);
@@ -795,10 +787,9 @@ int octeon_setup_instr_queues(struct octeon_device *oct)
if (OCTEON_CN6XXX(oct))
num_descs =
- CFG_GET_NUM_DEF_TX_DESCS(CHIP_FIELD(oct, cn6xxx, conf));
+ CFG_GET_NUM_DEF_TX_DESCS(CHIP_CONF(oct, cn6xxx));
else if (OCTEON_CN23XX_PF(oct))
- num_descs = CFG_GET_NUM_DEF_TX_DESCS(CHIP_FIELD(oct, cn23xx_pf,
- conf));
+ num_descs = CFG_GET_NUM_DEF_TX_DESCS(CHIP_CONF(oct, cn23xx_pf));
oct->num_iqs = 0;
@@ -821,6 +812,7 @@ int octeon_setup_instr_queues(struct octeon_device *oct)
if (octeon_init_instr_queue(oct, txpciq, num_descs)) {
/* prevent memory leak */
vfree(oct->instr_queue[0]);
+ oct->instr_queue[0] = NULL;
return 1;
}
@@ -837,14 +829,12 @@ int octeon_setup_output_queues(struct octeon_device *oct)
if (OCTEON_CN6XXX(oct)) {
num_descs =
- CFG_GET_NUM_DEF_RX_DESCS(CHIP_FIELD(oct, cn6xxx, conf));
+ CFG_GET_NUM_DEF_RX_DESCS(CHIP_CONF(oct, cn6xxx));
desc_size =
- CFG_GET_DEF_RX_BUF_SIZE(CHIP_FIELD(oct, cn6xxx, conf));
+ CFG_GET_DEF_RX_BUF_SIZE(CHIP_CONF(oct, cn6xxx));
} else if (OCTEON_CN23XX_PF(oct)) {
- num_descs = CFG_GET_NUM_DEF_RX_DESCS(CHIP_FIELD(oct, cn23xx_pf,
- conf));
- desc_size = CFG_GET_DEF_RX_BUF_SIZE(CHIP_FIELD(oct, cn23xx_pf,
- conf));
+ num_descs = CFG_GET_NUM_DEF_RX_DESCS(CHIP_CONF(oct, cn23xx_pf));
+ desc_size = CFG_GET_DEF_RX_BUF_SIZE(CHIP_CONF(oct, cn23xx_pf));
}
oct->num_oqs = 0;
oct->droq[0] = vmalloc_node(sizeof(*oct->droq[0]), numa_node);
@@ -853,8 +843,11 @@ int octeon_setup_output_queues(struct octeon_device *oct)
if (!oct->droq[0])
return 1;
- if (octeon_init_droq(oct, oq_no, num_descs, desc_size, NULL))
+ if (octeon_init_droq(oct, oq_no, num_descs, desc_size, NULL)) {
+ vfree(oct->droq[oq_no]);
+ oct->droq[oq_no] = NULL;
return 1;
+ }
oct->num_oqs++;
return 0;
@@ -1070,10 +1063,10 @@ int octeon_core_drv_init(struct octeon_recv_info *recv_info, void *buf)
if (OCTEON_CN6XXX(oct))
num_nic_ports =
- CFG_GET_NUM_NIC_PORTS(CHIP_FIELD(oct, cn6xxx, conf));
+ CFG_GET_NUM_NIC_PORTS(CHIP_CONF(oct, cn6xxx));
else if (OCTEON_CN23XX_PF(oct))
num_nic_ports =
- CFG_GET_NUM_NIC_PORTS(CHIP_FIELD(oct, cn23xx_pf, conf));
+ CFG_GET_NUM_NIC_PORTS(CHIP_CONF(oct, cn23xx_pf));
if (atomic_read(&oct->status) >= OCT_DEV_RUNNING) {
dev_err(&oct->pci_dev->dev, "Received CORE OK when device state is 0x%x\n",
@@ -1143,7 +1136,7 @@ int octeon_get_tx_qsize(struct octeon_device *oct, u32 q_no)
{
if (oct && (q_no < MAX_OCTEON_INSTR_QUEUES(oct)) &&
- (oct->io_qmask.iq & (1ULL << q_no)))
+ (oct->io_qmask.iq & BIT_ULL(q_no)))
return oct->instr_queue[q_no]->max_count;
return -1;
@@ -1152,7 +1145,7 @@ int octeon_get_tx_qsize(struct octeon_device *oct, u32 q_no)
int octeon_get_rx_qsize(struct octeon_device *oct, u32 q_no)
{
if (oct && (q_no < MAX_OCTEON_OUTPUT_QUEUES(oct)) &&
- (oct->io_qmask.oq & (1ULL << q_no)))
+ (oct->io_qmask.oq & BIT_ULL(q_no)))
return oct->droq[q_no]->max_count;
return -1;
}
@@ -1168,10 +1161,10 @@ struct octeon_config *octeon_get_conf(struct octeon_device *oct)
if (OCTEON_CN6XXX(oct)) {
default_oct_conf =
- (struct octeon_config *)(CHIP_FIELD(oct, cn6xxx, conf));
+ (struct octeon_config *)(CHIP_CONF(oct, cn6xxx));
} else if (OCTEON_CN23XX_PF(oct)) {
default_oct_conf = (struct octeon_config *)
- (CHIP_FIELD(oct, cn23xx_pf, conf));
+ (CHIP_CONF(oct, cn23xx_pf));
}
return default_oct_conf;
}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index da15c2a..5ce2048 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -1,25 +1,20 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
-
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
/*! \file octeon_device.h
* \brief Host Driver: This file defines the octeon device structure.
*/
@@ -38,6 +33,7 @@
#define OCTEON_CN68XX 0x0091
#define OCTEON_CN66XX 0x0092
#define OCTEON_CN23XX_PF_VID 0x9702
+#define OCTEON_CN23XX_VF_VID 0x9712
/**RevisionId for the chips */
#define OCTEON_CN23XX_REV_1_0 0x00
@@ -52,7 +48,13 @@ enum octeon_pci_swap_mode {
OCTEON_PCI_32BIT_LW_SWAP = 3
};
+enum {
+ OCTEON_CONFIG_TYPE_DEFAULT = 0,
+ NUM_OCTEON_CONFS,
+};
+
#define OCTEON_OUTPUT_INTR (2)
+#define OCTEON_MBOX_INTR (4)
#define OCTEON_ALL_INTR 0xff
/*--------------- PCI BAR1 index registers -------------*/
@@ -70,26 +72,30 @@ enum octeon_pci_swap_mode {
* as it is initialized.
*/
#define OCT_DEV_BEGIN_STATE 0x0
-#define OCT_DEV_PCI_MAP_DONE 0x1
-#define OCT_DEV_DISPATCH_INIT_DONE 0x2
-#define OCT_DEV_INSTR_QUEUE_INIT_DONE 0x3
-#define OCT_DEV_SC_BUFF_POOL_INIT_DONE 0x4
-#define OCT_DEV_RESP_LIST_INIT_DONE 0x5
-#define OCT_DEV_DROQ_INIT_DONE 0x6
-#define OCT_DEV_IO_QUEUES_DONE 0x7
-#define OCT_DEV_CONSOLE_INIT_DONE 0x8
-#define OCT_DEV_HOST_OK 0x9
-#define OCT_DEV_CORE_OK 0xa
-#define OCT_DEV_RUNNING 0xb
-#define OCT_DEV_IN_RESET 0xc
-#define OCT_DEV_STATE_INVALID 0xd
+#define OCT_DEV_PCI_ENABLE_DONE 0x1
+#define OCT_DEV_PCI_MAP_DONE 0x2
+#define OCT_DEV_DISPATCH_INIT_DONE 0x3
+#define OCT_DEV_INSTR_QUEUE_INIT_DONE 0x4
+#define OCT_DEV_SC_BUFF_POOL_INIT_DONE 0x5
+#define OCT_DEV_RESP_LIST_INIT_DONE 0x6
+#define OCT_DEV_DROQ_INIT_DONE 0x7
+#define OCT_DEV_MBOX_SETUP_DONE 0x8
+#define OCT_DEV_MSIX_ALLOC_VECTOR_DONE 0x9
+#define OCT_DEV_INTR_SET_DONE 0xa
+#define OCT_DEV_IO_QUEUES_DONE 0xb
+#define OCT_DEV_CONSOLE_INIT_DONE 0xc
+#define OCT_DEV_HOST_OK 0xd
+#define OCT_DEV_CORE_OK 0xe
+#define OCT_DEV_RUNNING 0xf
+#define OCT_DEV_IN_RESET 0x10
+#define OCT_DEV_STATE_INVALID 0x11
#define OCT_DEV_STATES OCT_DEV_STATE_INVALID
/** Octeon Device interrupts
- * These interrupt bits are set in int_status filed of
- * octeon_device structure
- */
+ * These interrupt bits are set in int_status filed of
+ * octeon_device structure
+ */
#define OCT_DEV_INTR_DMA0_FORCE 0x01
#define OCT_DEV_INTR_DMA1_FORCE 0x02
#define OCT_DEV_INTR_PKT_DATA 0x04
@@ -208,6 +214,10 @@ struct octeon_fn_list {
irqreturn_t (*process_interrupt_regs)(void *);
u64 (*msix_interrupt_handler)(void *);
+
+ int (*setup_mbox)(struct octeon_device *);
+ int (*free_mbox)(struct octeon_device *);
+
int (*soft_reset)(struct octeon_device *);
int (*setup_device_regs)(struct octeon_device *);
void (*bar1_idx_setup)(struct octeon_device *, u64, u32, int);
@@ -322,14 +332,39 @@ struct octeon_pf_vf_hs_word {
};
struct octeon_sriov_info {
+ /* Number of rings assigned to VF */
+ u32 rings_per_vf;
+
+ /** Max Number of VF devices that can be enabled. This variable can
+ * specified during load time or it will be derived after allocating
+ * PF queues. When max_vfs is derived then each VF will get one queue
+ **/
+ u32 max_vfs;
+
+ /** Number of VF devices enabled using sysfs. */
+ u32 num_vfs_alloced;
+
/* Actual rings left for PF device */
u32 num_pf_rings;
- /* SRN of PF usable IO queues */
+ /* SRN of PF usable IO queues */
u32 pf_srn;
+
/* total pf rings */
u32 trs;
+ u32 sriov_enabled;
+
+ /*lookup table that maps DPI ring number to VF pci_dev struct pointer*/
+ struct pci_dev *dpiring_to_vfpcidev_lut[MAX_POSSIBLE_VFS];
+
+ u64 vf_macaddr[MAX_POSSIBLE_VFS];
+
+ u16 vf_vlantci[MAX_POSSIBLE_VFS];
+
+ int vf_linkstate[MAX_POSSIBLE_VFS];
+
+ u64 vf_drv_loaded_mask;
};
struct octeon_ioq_vector {
@@ -337,6 +372,7 @@ struct octeon_ioq_vector {
int iq_index;
int droq_index;
int vector;
+ struct octeon_mbox *mbox;
struct cpumask affinity_mask;
u32 ioq_num;
};
@@ -474,6 +510,9 @@ struct octeon_device {
int msix_on;
+ /** Mail Box details of each octeon queue. */
+ struct octeon_mbox *mbox[MAX_POSSIBLE_VFS];
+
/** IOq information of it's corresponding MSI-X interrupt. */
struct octeon_ioq_vector *ioq_vector;
@@ -490,11 +529,14 @@ struct octeon_device {
#define OCT_DRV_ONLINE 1
#define OCT_DRV_OFFLINE 2
-#define OCTEON_CN6XXX(oct) ((oct->chip_id == OCTEON_CN66XX) || \
- (oct->chip_id == OCTEON_CN68XX))
-#define OCTEON_CN23XX_PF(oct) (oct->chip_id == OCTEON_CN23XX_PF_VID)
-#define CHIP_FIELD(oct, TYPE, field) \
- (((struct octeon_ ## TYPE *)(oct->chip))->field)
+#define OCTEON_CN6XXX(oct) ({ \
+ typeof(oct) _oct = (oct); \
+ ((_oct->chip_id == OCTEON_CN66XX) || \
+ (_oct->chip_id == OCTEON_CN68XX)); })
+#define OCTEON_CN23XX_PF(oct) ((oct)->chip_id == OCTEON_CN23XX_PF_VID)
+#define OCTEON_CN23XX_VF(oct) ((oct)->chip_id == OCTEON_CN23XX_VF_VID)
+#define CHIP_CONF(oct, TYPE) \
+ (((struct octeon_ ## TYPE *)((oct)->chip))->conf)
struct oct_intrmod_cmd {
struct octeon_device *oct_dev;
@@ -508,7 +550,7 @@ struct oct_intrmod_cmd {
void octeon_init_device_list(int conf_type);
/** Free memory for Input and Output queue structures for a octeon device */
-void octeon_free_device_mem(struct octeon_device *);
+void octeon_free_device_mem(struct octeon_device *oct);
/* Look up a free entry in the octeon_device table and allocate resources
* for the octeon_device structure for an octeon device. Called at init
@@ -606,16 +648,16 @@ void lio_pci_writeq(struct octeon_device *oct, u64 val, u64 addr);
/* Routines for reading and writing CSRs */
#define octeon_write_csr(oct_dev, reg_off, value) \
- writel(value, oct_dev->mmio[0].hw_addr + reg_off)
+ writel(value, (oct_dev)->mmio[0].hw_addr + (reg_off))
#define octeon_write_csr64(oct_dev, reg_off, val64) \
- writeq(val64, oct_dev->mmio[0].hw_addr + reg_off)
+ writeq(val64, (oct_dev)->mmio[0].hw_addr + (reg_off))
#define octeon_read_csr(oct_dev, reg_off) \
- readl(oct_dev->mmio[0].hw_addr + reg_off)
+ readl((oct_dev)->mmio[0].hw_addr + (reg_off))
#define octeon_read_csr64(oct_dev, reg_off) \
- readq(oct_dev->mmio[0].hw_addr + reg_off)
+ readq((oct_dev)->mmio[0].hw_addr + (reg_off))
/**
* Checks if memory access is okay
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
index f60e532..8bf1ac76 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -1,24 +1,20 @@
/**********************************************************************
-* Author: Cavium, Inc.
-*
-* Contact: support@cavium.com
-* Please include "LiquidIO" in the subject.
-*
-* Copyright (c) 2003-2015 Cavium, Inc.
-*
-* This file is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License, Version 2, as
-* published by the Free Software Foundation.
-*
-* This file is distributed in the hope that it will be useful, but
-* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
-* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
-* NONINFRINGEMENT. See the GNU General Public License for more
-* details.
-*
-* This file may also be available under a different license from Cavium.
-* Contact Cavium, Inc. for more information
-**********************************************************************/
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
#include <linux/pci.h>
#include <linux/netdevice.h>
#include <linux/vmalloc.h>
@@ -33,9 +29,6 @@
#include "cn66xx_device.h"
#include "cn23xx_pf_device.h"
-#define CVM_MIN(d1, d2) (((d1) < (d2)) ? (d1) : (d2))
-#define CVM_MAX(d1, d2) (((d1) > (d2)) ? (d1) : (d2))
-
struct niclist {
struct list_head list;
void *ptr;
@@ -258,13 +251,13 @@ int octeon_init_droq(struct octeon_device *oct,
c_num_descs = num_descs;
c_buf_size = desc_size;
if (OCTEON_CN6XXX(oct)) {
- struct octeon_config *conf6x = CHIP_FIELD(oct, cn6xxx, conf);
+ struct octeon_config *conf6x = CHIP_CONF(oct, cn6xxx);
c_pkts_per_intr = (u32)CFG_GET_OQ_PKTS_PER_INTR(conf6x);
c_refill_threshold =
(u32)CFG_GET_OQ_REFILL_THRESHOLD(conf6x);
} else if (OCTEON_CN23XX_PF(oct)) {
- struct octeon_config *conf23 = CHIP_FIELD(oct, cn23xx_pf, conf);
+ struct octeon_config *conf23 = CHIP_CONF(oct, cn23xx_pf);
c_pkts_per_intr = (u32)CFG_GET_OQ_PKTS_PER_INTR(conf23);
c_refill_threshold = (u32)CFG_GET_OQ_REFILL_THRESHOLD(conf23);
@@ -337,7 +330,7 @@ int octeon_init_droq(struct octeon_device *oct,
/* For 56xx Pass1, this function won't be called, so no checks. */
oct->fn_list.setup_oq_regs(oct, q_no);
- oct->io_qmask.oq |= (1ULL << q_no);
+ oct->io_qmask.oq |= BIT_ULL(q_no);
return 0;
@@ -409,7 +402,7 @@ static inline struct octeon_recv_info *octeon_create_recv_info(
recv_pkt->buffer_ptr[i] = droq->recv_buf_list[idx].buffer;
droq->recv_buf_list[idx].buffer = NULL;
- INCR_INDEX_BY1(idx, droq->max_count);
+ idx = incr_index(idx, 1, droq->max_count);
bytes_left -= droq->buffer_size;
i++;
buf_cnt--;
@@ -440,14 +433,15 @@ octeon_droq_refill_pullup_descs(struct octeon_droq *droq,
droq->recv_buf_list[refill_index].buffer = NULL;
desc_ring[refill_index].buffer_ptr = 0;
do {
- INCR_INDEX_BY1(droq->refill_idx,
- droq->max_count);
+ droq->refill_idx = incr_index(droq->refill_idx,
+ 1,
+ droq->max_count);
desc_refilled++;
droq->refill_count--;
} while (droq->recv_buf_list[droq->refill_idx].
buffer);
}
- INCR_INDEX_BY1(refill_index, droq->max_count);
+ refill_index = incr_index(refill_index, 1, droq->max_count);
} /* while */
return desc_refilled;
}
@@ -514,7 +508,8 @@ octeon_droq_refill(struct octeon_device *octeon_dev, struct octeon_droq *droq)
/* Reset any previous values in the length field. */
droq->info_list[droq->refill_idx].length = 0;
- INCR_INDEX_BY1(droq->refill_idx, droq->max_count);
+ droq->refill_idx = incr_index(droq->refill_idx, 1,
+ droq->max_count);
desc_refilled++;
droq->refill_count--;
}
@@ -599,7 +594,8 @@ static inline void octeon_droq_drop_packets(struct octeon_device *oct,
buf_cnt = 1;
}
- INCR_INDEX(droq->read_idx, buf_cnt, droq->max_count);
+ droq->read_idx = incr_index(droq->read_idx, buf_cnt,
+ droq->max_count);
droq->refill_count += buf_cnt;
}
}
@@ -639,11 +635,12 @@ octeon_droq_fast_process_packets(struct octeon_device *oct,
rh = &info->rh;
total_len += (u32)info->length;
- if (OPCODE_SLOW_PATH(rh)) {
+ if (opcode_slow_path(rh)) {
u32 buf_cnt;
buf_cnt = octeon_droq_dispatch_pkt(oct, droq, rh, info);
- INCR_INDEX(droq->read_idx, buf_cnt, droq->max_count);
+ droq->read_idx = incr_index(droq->read_idx,
+ buf_cnt, droq->max_count);
droq->refill_count += buf_cnt;
} else {
if (info->length <= droq->buffer_size) {
@@ -657,7 +654,8 @@ octeon_droq_fast_process_packets(struct octeon_device *oct,
droq->recv_buf_list[droq->read_idx].buffer =
NULL;
- INCR_INDEX_BY1(droq->read_idx, droq->max_count);
+ droq->read_idx = incr_index(droq->read_idx, 1,
+ droq->max_count);
droq->refill_count++;
} else {
nicbuf = octeon_fast_packet_alloc((u32)
@@ -689,8 +687,9 @@ octeon_droq_fast_process_packets(struct octeon_device *oct,
}
pkt_len += cpy_len;
- INCR_INDEX_BY1(droq->read_idx,
- droq->max_count);
+ droq->read_idx =
+ incr_index(droq->read_idx, 1,
+ droq->max_count);
droq->refill_count++;
}
}
@@ -804,9 +803,8 @@ octeon_droq_process_poll_pkts(struct octeon_device *oct,
while (total_pkts_processed < budget) {
octeon_droq_check_hw_for_pkts(droq);
- pkts_available =
- CVM_MIN((budget - total_pkts_processed),
- (u32)(atomic_read(&droq->pkts_pending)));
+ pkts_available = min((budget - total_pkts_processed),
+ (u32)(atomic_read(&droq->pkts_pending)));
if (pkts_available == 0)
break;
@@ -988,7 +986,8 @@ int octeon_create_droq(struct octeon_device *oct,
if (!droq)
droq = vmalloc(sizeof(*droq));
if (!droq)
- goto create_droq_fail;
+ return -1;
+
memset(droq, 0, sizeof(struct octeon_droq));
/*Disable the pkt o/p for this Q */
@@ -996,7 +995,11 @@ int octeon_create_droq(struct octeon_device *oct,
oct->droq[q_no] = droq;
/* Initialize the Droq */
- octeon_init_droq(oct, q_no, num_descs, desc_size, app_ctx);
+ if (octeon_init_droq(oct, q_no, num_descs, desc_size, app_ctx)) {
+ vfree(oct->droq[q_no]);
+ oct->droq[q_no] = NULL;
+ return -1;
+ }
oct->num_oqs++;
@@ -1009,8 +1012,4 @@ int octeon_create_droq(struct octeon_device *oct,
* the same time.
*/
return 0;
-
-create_droq_fail:
- octeon_delete_droq(oct, q_no);
- return -ENOMEM;
}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
index 5be002d..e620740 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
@@ -4,7 +4,7 @@
* Contact: support@cavium.com
* Please include "LiquidIO" in the subject.
*
- * Copyright (c) 2003-2015 Cavium, Inc.
+ * Copyright (c) 2003-2016 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
@@ -13,13 +13,8 @@
* This file is distributed in the hope that it will be useful, but
* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
- * NONINFRINGEMENT. See the GNU General Public License for more
- * details.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium, Inc. for more information
- **********************************************************************/
-
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
/*! \file octeon_droq.h
* \brief Implementation of Octeon Output queues. "Output" is with
* respect to the Octeon device on the NIC. From this driver's point of
@@ -81,7 +76,7 @@ struct octeon_skb_page_info {
* the Octeon device. Since the descriptor ring keeps physical (bus)
* addresses, this field is required for the driver to keep track of
* the virtual address pointers.
-*/
+ */
struct octeon_recv_buffer {
/** Packet buffer, including metadata. */
void *buffer;
@@ -121,7 +116,6 @@ struct oct_droq_stats {
/** Num of Packets dropped due to receive path failures. */
u64 rx_dropped;
- /** Num of vxlan packets received; */
u64 rx_vxlan;
/** Num of failures of recv_buffer_alloc() */
@@ -359,7 +353,7 @@ struct octeon_droq {
* @param q_no - droq no. ranges from 0 - 3.
* @param app_ctx - pointer to application context
* @return Success: 0 Failure: 1
-*/
+ */
int octeon_init_droq(struct octeon_device *oct_dev,
u32 q_no,
u32 num_descs,
@@ -372,7 +366,7 @@ int octeon_init_droq(struct octeon_device *oct_dev,
* @param oct_dev - pointer to the octeon device structure
* @param q_no - droq no. ranges from 0 - 3.
* @return: Success: 0 Failure: 1
-*/
+ */
int octeon_delete_droq(struct octeon_device *oct_dev, u32 q_no);
/** Register a change in droq operations. The ops field has a pointer to a
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
index e4d426b..e04ca8f 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
@@ -4,7 +4,7 @@
* Contact: support@cavium.com
* Please include "LiquidIO" in the subject.
*
- * Copyright (c) 2003-2015 Cavium, Inc.
+ * Copyright (c) 2003-2016 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
@@ -13,13 +13,8 @@
* This file is distributed in the hope that it will be useful, but
* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
- * NONINFRINGEMENT. See the GNU General Public License for more
- * details.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium, Inc. for more information
- **********************************************************************/
-
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
/*! \file octeon_iq.h
* \brief Host Driver: Implementation of Octeon input queues. "Input" is
* with respect to the Octeon device on the NIC. From this driver's
@@ -69,7 +64,6 @@ struct oct_iq_stats {
u64 tx_vxlan; /* tunnel */
u64 tx_dmamap_fail;
u64 tx_restart;
- /*u64 tx_timeout_count;*/
};
#define OCT_IQ_STATS_SIZE (sizeof(struct oct_iq_stats))
@@ -78,7 +72,7 @@ struct oct_iq_stats {
* The input queue is used to post raw (instruction) mode data or packet
* data to Octeon device from the host. Each input queue (upto 4) for
* a Octeon device has one such structure to represent it.
-*/
+ */
struct octeon_instr_queue {
struct octeon_device *oct_dev;
@@ -118,8 +112,8 @@ struct octeon_instr_queue {
u32 octeon_read_index;
/** This index aids in finding the window in the queue where Octeon
- * has read the commands.
- */
+ * has read the commands.
+ */
u32 flush_index;
/** This field keeps track of the instructions pending in this queue. */
@@ -150,8 +144,8 @@ struct octeon_instr_queue {
u64 last_db_time;
/** The doorbell timeout. If the doorbell was not rung for this time and
- * fill_cnt is non-zero, ring the doorbell again.
- */
+ * fill_cnt is non-zero, ring the doorbell again.
+ */
u32 db_timeout;
/** Statistics for this input queue. */
@@ -309,6 +303,9 @@ struct octeon_sc_buffer_pool {
atomic_t alloc_buf_count;
};
+#define INCR_INSTRQUEUE_PKT_COUNT(octeon_dev_ptr, iq_no, field, count) \
+ (((octeon_dev_ptr)->instr_queue[iq_no]->stats.field) += count)
+
int octeon_setup_sc_buffer_pool(struct octeon_device *oct);
int octeon_free_sc_buffer_pool(struct octeon_device *oct);
struct octeon_soft_command *
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c
new file mode 100644
index 0000000..73696b42
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c
@@ -0,0 +1,318 @@
+/**********************************************************************
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include "liquidio_common.h"
+#include "octeon_droq.h"
+#include "octeon_iq.h"
+#include "response_manager.h"
+#include "octeon_device.h"
+#include "octeon_main.h"
+#include "octeon_mailbox.h"
+
+/**
+ * octeon_mbox_read:
+ * @oct: Pointer mailbox
+ *
+ * Reads the 8-bytes of data from the mbox register
+ * Writes back the acknowldgement inidcating completion of read
+ */
+int octeon_mbox_read(struct octeon_mbox *mbox)
+{
+ union octeon_mbox_message msg;
+ int ret = 0;
+
+ spin_lock(&mbox->lock);
+
+ msg.u64 = readq(mbox->mbox_read_reg);
+
+ if ((msg.u64 == OCTEON_PFVFACK) || (msg.u64 == OCTEON_PFVFSIG)) {
+ spin_unlock(&mbox->lock);
+ return 0;
+ }
+
+ if (mbox->state & OCTEON_MBOX_STATE_REQUEST_RECEIVING) {
+ mbox->mbox_req.data[mbox->mbox_req.recv_len - 1] = msg.u64;
+ mbox->mbox_req.recv_len++;
+ } else {
+ if (mbox->state & OCTEON_MBOX_STATE_RESPONSE_RECEIVING) {
+ mbox->mbox_resp.data[mbox->mbox_resp.recv_len - 1] =
+ msg.u64;
+ mbox->mbox_resp.recv_len++;
+ } else {
+ if ((mbox->state & OCTEON_MBOX_STATE_IDLE) &&
+ (msg.s.type == OCTEON_MBOX_REQUEST)) {
+ mbox->state &= ~OCTEON_MBOX_STATE_IDLE;
+ mbox->state |=
+ OCTEON_MBOX_STATE_REQUEST_RECEIVING;
+ mbox->mbox_req.msg.u64 = msg.u64;
+ mbox->mbox_req.q_no = mbox->q_no;
+ mbox->mbox_req.recv_len = 1;
+ } else {
+ if ((mbox->state &
+ OCTEON_MBOX_STATE_RESPONSE_PENDING) &&
+ (msg.s.type == OCTEON_MBOX_RESPONSE)) {
+ mbox->state &=
+ ~OCTEON_MBOX_STATE_RESPONSE_PENDING;
+ mbox->state |=
+ OCTEON_MBOX_STATE_RESPONSE_RECEIVING
+ ;
+ mbox->mbox_resp.msg.u64 = msg.u64;
+ mbox->mbox_resp.q_no = mbox->q_no;
+ mbox->mbox_resp.recv_len = 1;
+ } else {
+ writeq(OCTEON_PFVFERR,
+ mbox->mbox_read_reg);
+ mbox->state |= OCTEON_MBOX_STATE_ERROR;
+ spin_unlock(&mbox->lock);
+ return 1;
+ }
+ }
+ }
+ }
+
+ if (mbox->state & OCTEON_MBOX_STATE_REQUEST_RECEIVING) {
+ if (mbox->mbox_req.recv_len < msg.s.len) {
+ ret = 0;
+ } else {
+ mbox->state &= ~OCTEON_MBOX_STATE_REQUEST_RECEIVING;
+ mbox->state |= OCTEON_MBOX_STATE_REQUEST_RECEIVED;
+ ret = 1;
+ }
+ } else {
+ if (mbox->state & OCTEON_MBOX_STATE_RESPONSE_RECEIVING) {
+ if (mbox->mbox_resp.recv_len < msg.s.len) {
+ ret = 0;
+ } else {
+ mbox->state &=
+ ~OCTEON_MBOX_STATE_RESPONSE_RECEIVING;
+ mbox->state |=
+ OCTEON_MBOX_STATE_RESPONSE_RECEIVED;
+ ret = 1;
+ }
+ } else {
+ WARN_ON(1);
+ }
+ }
+
+ writeq(OCTEON_PFVFACK, mbox->mbox_read_reg);
+
+ spin_unlock(&mbox->lock);
+
+ return ret;
+}
+
+/**
+ * octeon_mbox_write:
+ * @oct: Pointer Octeon Device
+ * @mbox_cmd: Cmd to send to mailbox.
+ *
+ * Populates the queue specific mbox structure
+ * with cmd information.
+ * Write the cmd to mbox register
+ */
+int octeon_mbox_write(struct octeon_device *oct,
+ struct octeon_mbox_cmd *mbox_cmd)
+{
+ struct octeon_mbox *mbox = oct->mbox[mbox_cmd->q_no];
+ u32 count, i, ret = OCTEON_MBOX_STATUS_SUCCESS;
+ unsigned long flags;
+
+ spin_lock_irqsave(&mbox->lock, flags);
+
+ if ((mbox_cmd->msg.s.type == OCTEON_MBOX_RESPONSE) &&
+ !(mbox->state & OCTEON_MBOX_STATE_REQUEST_RECEIVED)) {
+ spin_unlock_irqrestore(&mbox->lock, flags);
+ return OCTEON_MBOX_STATUS_FAILED;
+ }
+
+ if ((mbox_cmd->msg.s.type == OCTEON_MBOX_REQUEST) &&
+ !(mbox->state & OCTEON_MBOX_STATE_IDLE)) {
+ spin_unlock_irqrestore(&mbox->lock, flags);
+ return OCTEON_MBOX_STATUS_BUSY;
+ }
+
+ if (mbox_cmd->msg.s.type == OCTEON_MBOX_REQUEST) {
+ memcpy(&mbox->mbox_resp, mbox_cmd,
+ sizeof(struct octeon_mbox_cmd));
+ mbox->state = OCTEON_MBOX_STATE_RESPONSE_PENDING;
+ }
+
+ spin_unlock_irqrestore(&mbox->lock, flags);
+
+ count = 0;
+
+ while (readq(mbox->mbox_write_reg) != OCTEON_PFVFSIG) {
+ schedule_timeout_uninterruptible(LIO_MBOX_WRITE_WAIT_TIME);
+ if (count++ == LIO_MBOX_WRITE_WAIT_CNT) {
+ ret = OCTEON_MBOX_STATUS_FAILED;
+ break;
+ }
+ }
+
+ if (ret == OCTEON_MBOX_STATUS_SUCCESS) {
+ writeq(mbox_cmd->msg.u64, mbox->mbox_write_reg);
+ for (i = 0; i < (u32)(mbox_cmd->msg.s.len - 1); i++) {
+ count = 0;
+ while (readq(mbox->mbox_write_reg) !=
+ OCTEON_PFVFACK) {
+ schedule_timeout_uninterruptible(10);
+ if (count++ == LIO_MBOX_WRITE_WAIT_CNT) {
+ ret = OCTEON_MBOX_STATUS_FAILED;
+ break;
+ }
+ }
+ writeq(mbox_cmd->data[i], mbox->mbox_write_reg);
+ }
+ }
+
+ spin_lock_irqsave(&mbox->lock, flags);
+ if (mbox_cmd->msg.s.type == OCTEON_MBOX_RESPONSE) {
+ mbox->state = OCTEON_MBOX_STATE_IDLE;
+ writeq(OCTEON_PFVFSIG, mbox->mbox_read_reg);
+ } else {
+ if ((!mbox_cmd->msg.s.resp_needed) ||
+ (ret == OCTEON_MBOX_STATUS_FAILED)) {
+ mbox->state &= ~OCTEON_MBOX_STATE_RESPONSE_PENDING;
+ if (!(mbox->state &
+ (OCTEON_MBOX_STATE_REQUEST_RECEIVING |
+ OCTEON_MBOX_STATE_REQUEST_RECEIVED)))
+ mbox->state = OCTEON_MBOX_STATE_IDLE;
+ }
+ }
+ spin_unlock_irqrestore(&mbox->lock, flags);
+
+ return ret;
+}
+
+/**
+ * octeon_mbox_process_cmd:
+ * @mbox: Pointer mailbox
+ * @mbox_cmd: Pointer to command received
+ *
+ * Process the cmd received in mbox
+ */
+static int octeon_mbox_process_cmd(struct octeon_mbox *mbox,
+ struct octeon_mbox_cmd *mbox_cmd)
+{
+ struct octeon_device *oct = mbox->oct_dev;
+
+ switch (mbox_cmd->msg.s.cmd) {
+ case OCTEON_VF_ACTIVE:
+ dev_dbg(&oct->pci_dev->dev, "got vfactive sending data back\n");
+ mbox_cmd->msg.s.type = OCTEON_MBOX_RESPONSE;
+ mbox_cmd->msg.s.resp_needed = 1;
+ mbox_cmd->msg.s.len = 2;
+ mbox_cmd->data[0] = 0; /* VF version is in mbox_cmd->data[0] */
+ ((struct lio_version *)&mbox_cmd->data[0])->major =
+ LIQUIDIO_BASE_MAJOR_VERSION;
+ ((struct lio_version *)&mbox_cmd->data[0])->minor =
+ LIQUIDIO_BASE_MINOR_VERSION;
+ ((struct lio_version *)&mbox_cmd->data[0])->micro =
+ LIQUIDIO_BASE_MICRO_VERSION;
+ memcpy(mbox_cmd->msg.s.params, (uint8_t *)&oct->pfvf_hsword, 6);
+ /* Sending core cofig info to the corresponding active VF.*/
+ octeon_mbox_write(oct, mbox_cmd);
+ break;
+
+ case OCTEON_VF_FLR_REQUEST:
+ dev_info(&oct->pci_dev->dev,
+ "got a request for FLR from VF that owns DPI ring %u\n",
+ mbox->q_no);
+ pcie_capability_set_word(
+ oct->sriov_info.dpiring_to_vfpcidev_lut[mbox->q_no],
+ PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_BCR_FLR);
+ break;
+
+ case OCTEON_PF_CHANGED_VF_MACADDR:
+ if (OCTEON_CN23XX_VF(oct))
+ octeon_pf_changed_vf_macaddr(oct,
+ mbox_cmd->msg.s.params);
+ break;
+
+ default:
+ break;
+ }
+ return 0;
+}
+
+/**
+ *octeon_mbox_process_message:
+ *
+ * Process the received mbox message.
+ */
+int octeon_mbox_process_message(struct octeon_mbox *mbox)
+{
+ struct octeon_mbox_cmd mbox_cmd;
+ unsigned long flags;
+
+ spin_lock_irqsave(&mbox->lock, flags);
+
+ if (mbox->state & OCTEON_MBOX_STATE_ERROR) {
+ if (mbox->state & (OCTEON_MBOX_STATE_RESPONSE_PENDING |
+ OCTEON_MBOX_STATE_RESPONSE_RECEIVING)) {
+ memcpy(&mbox_cmd, &mbox->mbox_resp,
+ sizeof(struct octeon_mbox_cmd));
+ mbox->state = OCTEON_MBOX_STATE_IDLE;
+ writeq(OCTEON_PFVFSIG, mbox->mbox_read_reg);
+ spin_unlock_irqrestore(&mbox->lock, flags);
+ mbox_cmd.recv_status = 1;
+ if (mbox_cmd.fn)
+ mbox_cmd.fn(mbox->oct_dev, &mbox_cmd,
+ mbox_cmd.fn_arg);
+ return 0;
+ }
+
+ mbox->state = OCTEON_MBOX_STATE_IDLE;
+ writeq(OCTEON_PFVFSIG, mbox->mbox_read_reg);
+ spin_unlock_irqrestore(&mbox->lock, flags);
+ return 0;
+ }
+
+ if (mbox->state & OCTEON_MBOX_STATE_RESPONSE_RECEIVED) {
+ memcpy(&mbox_cmd, &mbox->mbox_resp,
+ sizeof(struct octeon_mbox_cmd));
+ mbox->state = OCTEON_MBOX_STATE_IDLE;
+ writeq(OCTEON_PFVFSIG, mbox->mbox_read_reg);
+ spin_unlock_irqrestore(&mbox->lock, flags);
+ mbox_cmd.recv_status = 0;
+ if (mbox_cmd.fn)
+ mbox_cmd.fn(mbox->oct_dev, &mbox_cmd, mbox_cmd.fn_arg);
+ return 0;
+ }
+
+ if (mbox->state & OCTEON_MBOX_STATE_REQUEST_RECEIVED) {
+ memcpy(&mbox_cmd, &mbox->mbox_req,
+ sizeof(struct octeon_mbox_cmd));
+ if (!mbox_cmd.msg.s.resp_needed) {
+ mbox->state &= ~OCTEON_MBOX_STATE_REQUEST_RECEIVED;
+ if (!(mbox->state &
+ OCTEON_MBOX_STATE_RESPONSE_PENDING))
+ mbox->state = OCTEON_MBOX_STATE_IDLE;
+ writeq(OCTEON_PFVFSIG, mbox->mbox_read_reg);
+ }
+
+ spin_unlock_irqrestore(&mbox->lock, flags);
+ octeon_mbox_process_cmd(mbox, &mbox_cmd);
+ return 0;
+ }
+
+ WARN_ON(1);
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h
new file mode 100644
index 0000000..fe60a3e
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h
@@ -0,0 +1,115 @@
+/**********************************************************************
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ * Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2016 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
+#ifndef __MAILBOX_H__
+#define __MAILBOX_H__
+
+/* Macros for Mail Box Communication */
+
+#define OCTEON_MBOX_DATA_MAX 32
+
+#define OCTEON_VF_ACTIVE 0x1
+#define OCTEON_VF_FLR_REQUEST 0x2
+#define OCTEON_PF_CHANGED_VF_MACADDR 0x4
+
+/*Macro for Read acknowldgement*/
+#define OCTEON_PFVFACK 0xffffffffffffffff
+#define OCTEON_PFVFSIG 0x1122334455667788
+#define OCTEON_PFVFERR 0xDEADDEADDEADDEAD
+
+#define LIO_MBOX_WRITE_WAIT_CNT 1000
+#define LIO_MBOX_WRITE_WAIT_TIME 10
+
+enum octeon_mbox_cmd_status {
+ OCTEON_MBOX_STATUS_SUCCESS = 0,
+ OCTEON_MBOX_STATUS_FAILED = 1,
+ OCTEON_MBOX_STATUS_BUSY = 2
+};
+
+enum octeon_mbox_message_type {
+ OCTEON_MBOX_REQUEST = 0,
+ OCTEON_MBOX_RESPONSE = 1
+};
+
+union octeon_mbox_message {
+ u64 u64;
+ struct {
+ u16 type : 1;
+ u16 resp_needed : 1;
+ u16 cmd : 6;
+ u16 len : 8;
+ u8 params[6];
+ } s;
+};
+
+typedef void (*octeon_mbox_callback_t)(void *, void *, void *);
+
+struct octeon_mbox_cmd {
+ union octeon_mbox_message msg;
+ u64 data[OCTEON_MBOX_DATA_MAX];
+ u32 q_no;
+ u32 recv_len;
+ u32 recv_status;
+ octeon_mbox_callback_t fn;
+ void *fn_arg;
+};
+
+enum octeon_mbox_state {
+ OCTEON_MBOX_STATE_IDLE = 1,
+ OCTEON_MBOX_STATE_REQUEST_RECEIVING = 2,
+ OCTEON_MBOX_STATE_REQUEST_RECEIVED = 4,
+ OCTEON_MBOX_STATE_RESPONSE_PENDING = 8,
+ OCTEON_MBOX_STATE_RESPONSE_RECEIVING = 16,
+ OCTEON_MBOX_STATE_RESPONSE_RECEIVED = 16,
+ OCTEON_MBOX_STATE_ERROR = 32
+};
+
+struct octeon_mbox {
+ /** A spinlock to protect access to this q_mbox. */
+ spinlock_t lock;
+
+ struct octeon_device *oct_dev;
+
+ u32 q_no;
+
+ enum octeon_mbox_state state;
+
+ struct cavium_wk mbox_poll_wk;
+
+ /** SLI_MAC_PF_MBOX_INT for PF, SLI_PKT_MBOX_INT for VF. */
+ void *mbox_int_reg;
+
+ /** SLI_PKT_PF_VF_MBOX_SIG(0) for PF, SLI_PKT_PF_VF_MBOX_SIG(1) for VF.
+ */
+ void *mbox_write_reg;
+
+ /** SLI_PKT_PF_VF_MBOX_SIG(1) for PF, SLI_PKT_PF_VF_MBOX_SIG(0) for VF.
+ */
+ void *mbox_read_reg;
+
+ struct octeon_mbox_cmd mbox_req;
+
+ struct octeon_mbox_cmd mbox_resp;
+
+};
+
+int octeon_mbox_read(struct octeon_mbox *mbox);
+int octeon_mbox_write(struct octeon_device *oct,
+ struct octeon_mbox_cmd *mbox_cmd);
+int octeon_mbox_process_message(struct octeon_mbox *mbox);
+
+#endif
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
index 366298f..8cd3891 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_main.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
@@ -4,7 +4,7 @@
* Contact: support@cavium.com
* Please include "LiquidIO" in the subject.
*
- * Copyright (c) 2003-2015 Cavium, Inc.
+ * Copyright (c) 2003-2016 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
@@ -13,13 +13,8 @@
* This file is distributed in the hope that it will be useful, but
* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
- * NONINFRINGEMENT. See the GNU General Public License for more
- * details.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium, Inc. for more information
- **********************************************************************/
-
+ * NONINFRINGEMENT. See the GNU General Public License for more details.
+ ***********************************************************************/
/*! \file octeon_main.h
* \brief Host Driver: This file is included by all host driver source files
* to include common definitions.
@@ -66,7 +61,7 @@ void octeon_update_tx_completion_counters(void *buf, int reqtype,
unsigned int *bytes_compl);
void octeon_report_tx_completion_to_bql(void *txq, unsigned int pkts_compl,
unsigned int bytes_compl);
-
+void octeon_pf_changed_vf_macaddr(struct octeon_device *oct, u8 *mac);
/** Swap 8B blocks */
static inline void octeon_swap_8B_data(u64 *data, u32 blocks)
{
@@ -78,10 +73,10 @@ static inline void octeon_swap_8B_data(u64 *data, u32 blocks)
}
/**
- * \brief unmaps a PCI BAR
- * @param oct Pointer to Octeon device
- * @param baridx bar index
- */
+ * \brief unmaps a PCI BAR
+ * @param oct Pointer to Octeon device
+ * @param baridx bar index
+ */
static inline void octeon_unmap_pci_barx(struct octeon_device *oct, int baridx)
{
dev_dbg(&oct->pci_dev->dev, "Freeing PCI mapped regions for Bar%d\n",
@@ -116,7 +111,7 @@ static inline int octeon_map_pci_barx(struct octeon_device *oct,
mapped_len = oct->mmio[baridx].len;
if (!mapped_len)
- return 1;
+ goto err_release_region;
if (max_map_len && (mapped_len > max_map_len))
mapped_len = max_map_len;
@@ -132,11 +127,15 @@ static inline int octeon_map_pci_barx(struct octeon_device *oct,
if (!oct->mmio[baridx].hw_addr) {
dev_err(&oct->pci_dev->dev, "error ioremap for bar %d\n",
baridx);
- return 1;
+ goto err_release_region;
}
oct->mmio[baridx].done = 1;
return 0;
+
+err_release_region:
+ pci_release_region(oct->pci_dev, baridx * 2);
+ return 1;
}
static inline void *
@@ -203,24 +202,6 @@ sleep_cond(wait_queue_head_t *wait_queue, int *condition)
return errno;
}
-static inline void
-sleep_atomic_cond(wait_queue_head_t *waitq, atomic_t *pcond)
-{
- wait_queue_t we;
-
- init_waitqueue_entry(&we, current);
- add_wait_queue(waitq, &we);
- while (!atomic_read(pcond)) {
- set_current_state(TASK_INTERRUPTIBLE);
- if (signal_pending(current))
- goto out;
- schedule();
- }
-out:
- set_current_state(TASK_RUNNING);
- remove_wait_queue(waitq, &we);
-}
-
/* Gives up the CPU for a timeout period.
* Check that the condition is not true before we go to sleep for a
* timeout period.
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.c b/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.c
index 0dc081a..13a18c9 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.c
@@ -4,7 +4,7 @@
* Contact: support@cavium.com
* Please include "LiquidIO" in the subject.
*
- * Copyright (c) 2003-2015 Cavium, Inc.
+ * Copyright (c) 2003-2016 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
@@ -15,9 +15,6 @@
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
* NONINFRINGEMENT. See the GNU General Public License for more
* details.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium, Inc. for more information
**********************************************************************/
#include <linux/netdevice.h>
#include "liquidio_common.h"
@@ -39,7 +36,7 @@ octeon_toggle_bar1_swapmode(struct octeon_device *oct, u32 idx)
oct->fn_list.bar1_idx_write(oct, idx, mask);
}
#else
-#define octeon_toggle_bar1_swapmode(oct, idx) (oct = oct)
+#define octeon_toggle_bar1_swapmode(oct, idx)
#endif
static void
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.h b/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.h
index 11b1833..bae2fdd 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.h
@@ -4,7 +4,7 @@
* Contact: support@cavium.com
* Please include "LiquidIO" in the subject.
*
- * Copyright (c) 2003-2015 Cavium, Inc.
+ * Copyright (c) 2003-2016 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
@@ -15,9 +15,6 @@
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
* NONINFRINGEMENT. See the GNU General Public License for more
* details.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium, Inc. for more information
**********************************************************************/
/*! \file octeon_mem_ops.h
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
index 54b9665..e94edc8 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
@@ -4,7 +4,7 @@
* Contact: support@cavium.com
* Please include "LiquidIO" in the subject.
*
- * Copyright (c) 2003-2015 Cavium, Inc.
+ * Copyright (c) 2003-2016 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
@@ -15,9 +15,6 @@
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
* NONINFRINGEMENT. See the GNU General Public License for more
* details.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium, Inc. for more information
**********************************************************************/
/*! \file octeon_network.h
@@ -131,7 +128,7 @@ struct lio {
#define LIO_SIZE (sizeof(struct lio))
#define GET_LIO(netdev) ((struct lio *)netdev_priv(netdev))
-#define CIU3_WDOG(c) (0x1010000020000ULL + (c << 3))
+#define CIU3_WDOG(c) (0x1010000020000ULL + ((c) << 3))
#define CIU3_WDOG_MASK 12ULL
#define LIO_MONITOR_WDOG_EXPIRE 1
#define LIO_MONITOR_CORE_STUCK_MSGD 2
@@ -342,9 +339,9 @@ static inline void tx_buffer_free(void *buffer)
}
#define lio_dma_alloc(oct, size, dma_addr) \
- dma_alloc_coherent(&oct->pci_dev->dev, size, dma_addr, GFP_KERNEL)
+ dma_alloc_coherent(&(oct)->pci_dev->dev, size, dma_addr, GFP_KERNEL)
#define lio_dma_free(oct, size, virt_addr, dma_addr) \
- dma_free_coherent(&oct->pci_dev->dev, size, virt_addr, dma_addr)
+ dma_free_coherent(&(oct)->pci_dev->dev, size, virt_addr, dma_addr)
static inline
void *get_rbd(struct sk_buff *skb)
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
index 40ac1fe..c3d6a82 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
@@ -4,7 +4,7 @@
* Contact: support@cavium.com
* Please include "LiquidIO" in the subject.
*
- * Copyright (c) 2003-2015 Cavium, Inc.
+ * Copyright (c) 2003-2016 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
@@ -15,9 +15,6 @@
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
* NONINFRINGEMENT. See the GNU General Public License for more
* details.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium, Inc. for more information
**********************************************************************/
#include <linux/pci.h>
#include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
index 4b8da67b..0c7a5c9 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
@@ -4,7 +4,7 @@
* Contact: support@cavium.com
* Please include "LiquidIO" in the subject.
*
- * Copyright (c) 2003-2015 Cavium, Inc.
+ * Copyright (c) 2003-2016 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
@@ -15,9 +15,6 @@
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
* NONINFRINGEMENT. See the GNU General Public License for more
* details.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium, Inc. for more information
**********************************************************************/
/*! \file octeon_nic.h
@@ -67,7 +64,7 @@ struct octnic_ctrl_pkt {
octnic_ctrl_pkt_cb_fn_t cb_fn;
};
-#define MAX_UDD_SIZE(nctrl) (sizeof(nctrl->udd))
+#define MAX_UDD_SIZE(nctrl) (sizeof((nctrl)->udd))
/** Structure of data information passed by the NIC module to the OSI
* layer when forwarding data to Octeon device software.
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index 90866bb..8531a00 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -4,7 +4,7 @@
* Contact: support@cavium.com
* Please include "LiquidIO" in the subject.
*
- * Copyright (c) 2003-2015 Cavium, Inc.
+ * Copyright (c) 2003-2016 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
@@ -15,9 +15,6 @@
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
* NONINFRINGEMENT. See the GNU General Public License for more
* details.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium, Inc. for more information
**********************************************************************/
#include <linux/pci.h>
#include <linux/netdevice.h>
@@ -32,9 +29,6 @@
#include "cn66xx_device.h"
#include "cn23xx_pf_device.h"
-#define INCR_INSTRQUEUE_PKT_COUNT(octeon_dev_ptr, iq_no, field, count) \
- (octeon_dev_ptr->instr_queue[iq_no]->stats.field += count)
-
struct iq_post_status {
int status;
int index;
@@ -71,9 +65,9 @@ int octeon_init_instr_queue(struct octeon_device *oct,
int numa_node = cpu_to_node(iq_no % num_online_cpus());
if (OCTEON_CN6XXX(oct))
- conf = &(CFG_GET_IQ_CFG(CHIP_FIELD(oct, cn6xxx, conf)));
+ conf = &(CFG_GET_IQ_CFG(CHIP_CONF(oct, cn6xxx)));
else if (OCTEON_CN23XX_PF(oct))
- conf = &(CFG_GET_IQ_CFG(CHIP_FIELD(oct, cn23xx_pf, conf)));
+ conf = &(CFG_GET_IQ_CFG(CHIP_CONF(oct, cn23xx_pf)));
if (!conf) {
dev_err(&oct->pci_dev->dev, "Unsupported Chip %x\n",
oct->chip_id);
@@ -145,7 +139,7 @@ int octeon_init_instr_queue(struct octeon_device *oct,
spin_lock_init(&iq->iq_flush_running_lock);
- oct->io_qmask.iq |= (1ULL << iq_no);
+ oct->io_qmask.iq |= BIT_ULL(iq_no);
/* Set the 32B/64B mode for each input queue */
oct->io_qmask.iq64B |= ((conf->instr_type == 64) << iq_no);
@@ -157,6 +151,8 @@ int octeon_init_instr_queue(struct octeon_device *oct,
WQ_MEM_RECLAIM,
0);
if (!oct->check_db_wq[iq_no].wq) {
+ vfree(iq->request_list);
+ iq->request_list = NULL;
lio_dma_free(oct, q_size, iq->base_addr, iq->base_addr_dma);
dev_err(&oct->pci_dev->dev, "check db wq create failed for iq %d\n",
iq_no);
@@ -183,10 +179,10 @@ int octeon_delete_instr_queue(struct octeon_device *oct, u32 iq_no)
if (OCTEON_CN6XXX(oct))
desc_size =
- CFG_GET_IQ_INSTR_TYPE(CHIP_FIELD(oct, cn6xxx, conf));
+ CFG_GET_IQ_INSTR_TYPE(CHIP_CONF(oct, cn6xxx));
else if (OCTEON_CN23XX_PF(oct))
desc_size =
- CFG_GET_IQ_INSTR_TYPE(CHIP_FIELD(oct, cn23xx_pf, conf));
+ CFG_GET_IQ_INSTR_TYPE(CHIP_CONF(oct, cn23xx_pf));
vfree(iq->request_list);
@@ -250,9 +246,8 @@ int lio_wait_for_instr_fetch(struct octeon_device *oct)
do {
instr_cnt = 0;
- /*for (i = 0; i < oct->num_iqs; i++) {*/
for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
- if (!(oct->io_qmask.iq & (1ULL << i)))
+ if (!(oct->io_qmask.iq & BIT_ULL(i)))
continue;
pending =
atomic_read(&oct->
@@ -319,7 +314,8 @@ __post_command2(struct octeon_instr_queue *iq, u8 *cmd)
/* "index" is returned, host_write_index is modified. */
st.index = iq->host_write_index;
- INCR_INDEX_BY1(iq->host_write_index, iq->max_count);
+ iq->host_write_index = incr_index(iq->host_write_index, 1,
+ iq->max_count);
iq->fill_cnt++;
/* Flush the command into memory. We need to be sure the data is in
@@ -434,7 +430,7 @@ lio_process_iq_request_list(struct octeon_device *oct,
skip_this:
inst_count++;
- INCR_INDEX_BY1(old, iq->max_count);
+ old = incr_index(old, 1, iq->max_count);
if ((napi_budget) && (inst_count >= napi_budget))
break;
@@ -577,8 +573,6 @@ octeon_send_command(struct octeon_device *oct, u32 iq_no,
/* This is only done here to expedite packets being flushed
* for cases where there are no IQ completion interrupts.
*/
- /*if (iq->do_auto_flush)*/
- /* octeon_flush_iq(oct, iq, 2, 0);*/
return st.status;
}
@@ -749,8 +743,10 @@ int octeon_setup_sc_buffer_pool(struct octeon_device *oct)
lio_dma_alloc(oct,
SOFT_COMMAND_BUFFER_SIZE,
(dma_addr_t *)&dma_addr);
- if (!sc)
+ if (!sc) {
+ octeon_free_sc_buffer_pool(oct);
return 1;
+ }
sc->dma_addr = dma_addr;
sc->size = SOFT_COMMAND_BUFFER_SIZE;
diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.c b/drivers/net/ethernet/cavium/liquidio/response_manager.c
index be52178d..fdaf742 100644
--- a/drivers/net/ethernet/cavium/liquidio/response_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/response_manager.c
@@ -4,7 +4,7 @@
* Contact: support@cavium.com
* Please include "LiquidIO" in the subject.
*
- * Copyright (c) 2003-2015 Cavium, Inc.
+ * Copyright (c) 2003-2016 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
@@ -15,9 +15,6 @@
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
* NONINFRINGEMENT. See the GNU General Public License for more
* details.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium, Inc. for more information
**********************************************************************/
#include <linux/pci.h>
#include <linux/netdevice.h>
@@ -81,11 +78,7 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev,
spin_lock_bh(&ordered_sc_list->lock);
if (ordered_sc_list->head.next == &ordered_sc_list->head) {
- /* ordered_sc_list is empty; there is
- * nothing to process
- */
- spin_unlock_bh
- (&ordered_sc_list->lock);
+ spin_unlock_bh(&ordered_sc_list->lock);
return 1;
}
diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.h b/drivers/net/ethernet/cavium/liquidio/response_manager.h
index 7a48752..cbb2d84 100644
--- a/drivers/net/ethernet/cavium/liquidio/response_manager.h
+++ b/drivers/net/ethernet/cavium/liquidio/response_manager.h
@@ -4,7 +4,7 @@
* Contact: support@cavium.com
* Please include "LiquidIO" in the subject.
*
- * Copyright (c) 2003-2015 Cavium, Inc.
+ * Copyright (c) 2003-2016 Cavium, Inc.
*
* This file is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License, Version 2, as
@@ -15,9 +15,6 @@
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
* NONINFRINGEMENT. See the GNU General Public License for more
* details.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium, Inc. for more information
**********************************************************************/
/*! \file response_manager.h
@@ -85,7 +82,6 @@ enum {
/** A value of 0x00000000 indicates no error i.e. success */
#define DRIVER_ERROR_NONE 0x00000000
-/** (Major number: 0x0000; Minor Number: 0x0001) */
#define DRIVER_ERROR_REQ_PENDING 0x00000001
#define DRIVER_ERROR_REQ_TIMEOUT 0x00000003
#define DRIVER_ERROR_REQ_EINTR 0x00000004
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 2125903..0bce1bf 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -635,6 +635,7 @@ struct tx_sw_desc;
struct sge_txq {
unsigned int in_use; /* # of in-use Tx descriptors */
+ unsigned int q_type; /* Q type Eth/Ctrl/Ofld */
unsigned int size; /* # of descriptors */
unsigned int cidx; /* SW consumer index */
unsigned int pidx; /* producer index */
@@ -665,7 +666,7 @@ struct sge_eth_txq { /* state for an SGE Ethernet Tx queue */
unsigned long mapping_err; /* # of I/O MMU packet mapping errors */
} ____cacheline_aligned_in_smp;
-struct sge_ofld_txq { /* state for an SGE offload Tx queue */
+struct sge_uld_txq { /* state for an SGE offload Tx queue */
struct sge_txq q;
struct adapter *adap;
struct sk_buff_head sendq; /* list of backpressured packets */
@@ -693,14 +694,20 @@ struct sge_uld_rxq_info {
u8 uld; /* uld type */
};
+struct sge_uld_txq_info {
+ struct sge_uld_txq *uldtxq; /* Txq's for ULD */
+ atomic_t users; /* num users */
+ u16 ntxq; /* # of egress uld queues */
+};
+
struct sge {
struct sge_eth_txq ethtxq[MAX_ETH_QSETS];
- struct sge_ofld_txq ofldtxq[MAX_OFLD_QSETS];
struct sge_ctrl_txq ctrlq[MAX_CTRL_QUEUES];
struct sge_eth_rxq ethrxq[MAX_ETH_QSETS];
struct sge_rspq fw_evtq ____cacheline_aligned_in_smp;
struct sge_uld_rxq_info **uld_rxq_info;
+ struct sge_uld_txq_info **uld_txq_info;
struct sge_rspq intrq ____cacheline_aligned_in_smp;
spinlock_t intrq_lock;
@@ -1298,8 +1305,9 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
unsigned int cmplqid);
int t4_sge_mod_ctrl_txq(struct adapter *adap, unsigned int eqid,
unsigned int cmplqid);
-int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq,
- struct net_device *dev, unsigned int iqid);
+int t4_sge_alloc_uld_txq(struct adapter *adap, struct sge_uld_txq *txq,
+ struct net_device *dev, unsigned int iqid,
+ unsigned int uld_type);
irqreturn_t t4_sge_intr_msix(int irq, void *cookie);
int t4_sge_init(struct adapter *adap);
void t4_sge_start(struct adapter *adap);
@@ -1661,4 +1669,7 @@ int t4_uld_mem_alloc(struct adapter *adap);
void t4_uld_clean_up(struct adapter *adap);
void t4_register_netevent_notifier(void);
void free_rspq_fl(struct adapter *adap, struct sge_rspq *rq, struct sge_fl *fl);
+void free_tx_desc(struct adapter *adap, struct sge_txq *q,
+ unsigned int n, bool unmap);
+void free_txq(struct adapter *adap, struct sge_txq *q);
#endif /* __CXGB4_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 20455d0..acc2312 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2512,18 +2512,6 @@ do { \
RL("FLLow:", fl.low);
RL("FLStarving:", fl.starving);
- } else if (ofld_idx < ofld_entries) {
- const struct sge_ofld_txq *tx =
- &adap->sge.ofldtxq[ofld_idx * 4];
- int n = min(4, adap->sge.ofldqsets - 4 * ofld_idx);
-
- S("QType:", "OFLD-Txq");
- T("TxQ ID:", q.cntxt_id);
- T("TxQ size:", q.size);
- T("TxQ inuse:", q.in_use);
- T("TxQ CIDX:", q.cidx);
- T("TxQ PIDX:", q.pidx);
-
} else if (ctrl_idx < ctrl_entries) {
const struct sge_ctrl_txq *tx = &adap->sge.ctrlq[ctrl_idx * 4];
int n = min(4, adap->params.nports - 4 * ctrl_idx);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index b0bb23f..449884f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -530,15 +530,15 @@ static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp,
txq = q->adap->sge.egr_map[qid - q->adap->sge.egr_start];
txq->restarts++;
- if ((u8 *)txq < (u8 *)q->adap->sge.ofldtxq) {
+ if (txq->q_type == CXGB4_TXQ_ETH) {
struct sge_eth_txq *eq;
eq = container_of(txq, struct sge_eth_txq, q);
netif_tx_wake_queue(eq->txq);
} else {
- struct sge_ofld_txq *oq;
+ struct sge_uld_txq *oq;
- oq = container_of(txq, struct sge_ofld_txq, q);
+ oq = container_of(txq, struct sge_uld_txq, q);
tasklet_schedule(&oq->qresume_tsk);
}
} else if (opcode == CPL_FW6_MSG || opcode == CPL_FW4_MSG) {
@@ -885,15 +885,6 @@ static int setup_sge_queues(struct adapter *adap)
}
}
- j = s->ofldqsets / adap->params.nports; /* iscsi queues per channel */
- for_each_ofldtxq(s, i) {
- err = t4_sge_alloc_ofld_txq(adap, &s->ofldtxq[i],
- adap->port[i / j],
- s->fw_evtq.cntxt_id);
- if (err)
- goto freeout;
- }
-
for_each_port(adap, i) {
/* Note that cmplqid below is 0 if we don't
* have RDMA queues, and that's the right value.
@@ -1922,8 +1913,18 @@ static void disable_dbs(struct adapter *adap)
for_each_ethrxq(&adap->sge, i)
disable_txq_db(&adap->sge.ethtxq[i].q);
- for_each_ofldtxq(&adap->sge, i)
- disable_txq_db(&adap->sge.ofldtxq[i].q);
+ if (is_offload(adap)) {
+ struct sge_uld_txq_info *txq_info =
+ adap->sge.uld_txq_info[CXGB4_TX_OFLD];
+
+ if (txq_info) {
+ for_each_ofldtxq(&adap->sge, i) {
+ struct sge_uld_txq *txq = &txq_info->uldtxq[i];
+
+ disable_txq_db(&txq->q);
+ }
+ }
+ }
for_each_port(adap, i)
disable_txq_db(&adap->sge.ctrlq[i].q);
}
@@ -1934,8 +1935,18 @@ static void enable_dbs(struct adapter *adap)
for_each_ethrxq(&adap->sge, i)
enable_txq_db(adap, &adap->sge.ethtxq[i].q);
- for_each_ofldtxq(&adap->sge, i)
- enable_txq_db(adap, &adap->sge.ofldtxq[i].q);
+ if (is_offload(adap)) {
+ struct sge_uld_txq_info *txq_info =
+ adap->sge.uld_txq_info[CXGB4_TX_OFLD];
+
+ if (txq_info) {
+ for_each_ofldtxq(&adap->sge, i) {
+ struct sge_uld_txq *txq = &txq_info->uldtxq[i];
+
+ enable_txq_db(adap, &txq->q);
+ }
+ }
+ }
for_each_port(adap, i)
enable_txq_db(adap, &adap->sge.ctrlq[i].q);
}
@@ -2006,8 +2017,17 @@ static void recover_all_queues(struct adapter *adap)
for_each_ethrxq(&adap->sge, i)
sync_txq_pidx(adap, &adap->sge.ethtxq[i].q);
- for_each_ofldtxq(&adap->sge, i)
- sync_txq_pidx(adap, &adap->sge.ofldtxq[i].q);
+ if (is_offload(adap)) {
+ struct sge_uld_txq_info *txq_info =
+ adap->sge.uld_txq_info[CXGB4_TX_OFLD];
+ if (txq_info) {
+ for_each_ofldtxq(&adap->sge, i) {
+ struct sge_uld_txq *txq = &txq_info->uldtxq[i];
+
+ sync_txq_pidx(adap, &txq->q);
+ }
+ }
+ }
for_each_port(adap, i)
sync_txq_pidx(adap, &adap->sge.ctrlq[i].q);
}
@@ -3991,7 +4011,7 @@ static inline bool is_x_10g_port(const struct link_config *lc)
static void cfg_queues(struct adapter *adap)
{
struct sge *s = &adap->sge;
- int i, n10g = 0, qidx = 0;
+ int i = 0, n10g = 0, qidx = 0;
#ifndef CONFIG_CHELSIO_T4_DCB
int q10g = 0;
#endif
@@ -4006,8 +4026,7 @@ static void cfg_queues(struct adapter *adap)
adap->params.crypto = 0;
}
- for_each_port(adap, i)
- n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
+ n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
#ifdef CONFIG_CHELSIO_T4_DCB
/* For Data Center Bridging support we need to be able to support up
* to 8 Traffic Priorities; each of which will be assigned to its
@@ -4055,7 +4074,7 @@ static void cfg_queues(struct adapter *adap)
* capped by the number of available cores.
*/
if (n10g) {
- i = num_online_cpus();
+ i = min_t(int, MAX_OFLD_QSETS, num_online_cpus());
s->ofldqsets = roundup(i, adap->params.nports);
} else {
s->ofldqsets = adap->params.nports;
@@ -4075,9 +4094,6 @@ static void cfg_queues(struct adapter *adap)
for (i = 0; i < ARRAY_SIZE(s->ctrlq); i++)
s->ctrlq[i].q.size = 512;
- for (i = 0; i < ARRAY_SIZE(s->ofldtxq); i++)
- s->ofldtxq[i].q.size = 1024;
-
init_rspq(adap, &s->fw_evtq, 0, 1, 1024, 64);
init_rspq(adap, &s->intrq, 0, 1, 512, 64);
}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index 0945fa4..565a6c6 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -135,15 +135,17 @@ static int uldrx_handler(struct sge_rspq *q, const __be64 *rsp,
}
static int alloc_uld_rxqs(struct adapter *adap,
- struct sge_uld_rxq_info *rxq_info,
- unsigned int nq, unsigned int offset, bool lro)
+ struct sge_uld_rxq_info *rxq_info, bool lro)
{
struct sge *s = &adap->sge;
- struct sge_ofld_rxq *q = rxq_info->uldrxq + offset;
- unsigned short *ids = rxq_info->rspq_id + offset;
- unsigned int per_chan = nq / adap->params.nports;
+ unsigned int nq = rxq_info->nrxq + rxq_info->nciq;
+ struct sge_ofld_rxq *q = rxq_info->uldrxq;
+ unsigned short *ids = rxq_info->rspq_id;
unsigned int bmap_idx = 0;
- int i, err, msi_idx;
+ unsigned int per_chan;
+ int i, err, msi_idx, que_idx = 0;
+
+ per_chan = rxq_info->nrxq / adap->params.nports;
if (adap->flags & USING_MSIX)
msi_idx = 1;
@@ -151,12 +153,18 @@ static int alloc_uld_rxqs(struct adapter *adap,
msi_idx = -((int)s->intrq.abs_id + 1);
for (i = 0; i < nq; i++, q++) {
+ if (i == rxq_info->nrxq) {
+ /* start allocation of concentrator queues */
+ per_chan = rxq_info->nciq / adap->params.nports;
+ que_idx = 0;
+ }
+
if (msi_idx >= 0) {
bmap_idx = get_msix_idx_from_bmap(adap);
msi_idx = adap->msix_info_ulds[bmap_idx].idx;
}
err = t4_sge_alloc_rxq(adap, &q->rspq, false,
- adap->port[i / per_chan],
+ adap->port[que_idx++ / per_chan],
msi_idx,
q->fl.size ? &q->fl : NULL,
uldrx_handler,
@@ -165,29 +173,19 @@ static int alloc_uld_rxqs(struct adapter *adap,
if (err)
goto freeout;
if (msi_idx >= 0)
- rxq_info->msix_tbl[i + offset] = bmap_idx;
+ rxq_info->msix_tbl[i] = bmap_idx;
memset(&q->stats, 0, sizeof(q->stats));
if (ids)
ids[i] = q->rspq.abs_id;
}
return 0;
freeout:
- q = rxq_info->uldrxq + offset;
+ q = rxq_info->uldrxq;
for ( ; i; i--, q++) {
if (q->rspq.desc)
free_rspq_fl(adap, &q->rspq,
q->fl.size ? &q->fl : NULL);
}
-
- /* We need to free rxq also in case of ciq allocation failure */
- if (offset) {
- q = rxq_info->uldrxq + offset;
- for ( ; i; i--, q++) {
- if (q->rspq.desc)
- free_rspq_fl(adap, &q->rspq,
- q->fl.size ? &q->fl : NULL);
- }
- }
return err;
}
@@ -205,9 +203,7 @@ setup_sge_queues_uld(struct adapter *adap, unsigned int uld_type, bool lro)
return -ENOMEM;
}
- ret = !(!alloc_uld_rxqs(adap, rxq_info, rxq_info->nrxq, 0, lro) &&
- !alloc_uld_rxqs(adap, rxq_info, rxq_info->nciq,
- rxq_info->nrxq, lro));
+ ret = !(!alloc_uld_rxqs(adap, rxq_info, lro));
/* Tell uP to route control queue completions to rdma rspq */
if (adap->flags & FULL_INIT_DONE &&
@@ -451,6 +447,106 @@ static void quiesce_rx_uld(struct adapter *adap, unsigned int uld_type)
quiesce_rx(adap, &rxq_info->uldrxq[idx].rspq);
}
+static void
+free_sge_txq_uld(struct adapter *adap, struct sge_uld_txq_info *txq_info)
+{
+ int nq = txq_info->ntxq;
+ int i;
+
+ for (i = 0; i < nq; i++) {
+ struct sge_uld_txq *txq = &txq_info->uldtxq[i];
+
+ if (txq && txq->q.desc) {
+ tasklet_kill(&txq->qresume_tsk);
+ t4_ofld_eq_free(adap, adap->mbox, adap->pf, 0,
+ txq->q.cntxt_id);
+ free_tx_desc(adap, &txq->q, txq->q.in_use, false);
+ kfree(txq->q.sdesc);
+ __skb_queue_purge(&txq->sendq);
+ free_txq(adap, &txq->q);
+ }
+ }
+}
+
+static int
+alloc_sge_txq_uld(struct adapter *adap, struct sge_uld_txq_info *txq_info,
+ unsigned int uld_type)
+{
+ struct sge *s = &adap->sge;
+ int nq = txq_info->ntxq;
+ int i, j, err;
+
+ j = nq / adap->params.nports;
+ for (i = 0; i < nq; i++) {
+ struct sge_uld_txq *txq = &txq_info->uldtxq[i];
+
+ txq->q.size = 1024;
+ err = t4_sge_alloc_uld_txq(adap, txq, adap->port[i / j],
+ s->fw_evtq.cntxt_id, uld_type);
+ if (err)
+ goto freeout;
+ }
+ return 0;
+freeout:
+ free_sge_txq_uld(adap, txq_info);
+ return err;
+}
+
+static void
+release_sge_txq_uld(struct adapter *adap, unsigned int uld_type)
+{
+ struct sge_uld_txq_info *txq_info = NULL;
+ int tx_uld_type = TX_ULD(uld_type);
+
+ txq_info = adap->sge.uld_txq_info[tx_uld_type];
+
+ if (txq_info && atomic_dec_and_test(&txq_info->users)) {
+ free_sge_txq_uld(adap, txq_info);
+ kfree(txq_info->uldtxq);
+ kfree(txq_info);
+ adap->sge.uld_txq_info[tx_uld_type] = NULL;
+ }
+}
+
+static int
+setup_sge_txq_uld(struct adapter *adap, unsigned int uld_type,
+ const struct cxgb4_uld_info *uld_info)
+{
+ struct sge_uld_txq_info *txq_info = NULL;
+ int tx_uld_type, i;
+
+ tx_uld_type = TX_ULD(uld_type);
+ txq_info = adap->sge.uld_txq_info[tx_uld_type];
+
+ if ((tx_uld_type == CXGB4_TX_OFLD) && txq_info &&
+ (atomic_inc_return(&txq_info->users) > 1))
+ return 0;
+
+ txq_info = kzalloc(sizeof(*txq_info), GFP_KERNEL);
+ if (!txq_info)
+ return -ENOMEM;
+
+ i = min_t(int, uld_info->ntxq, num_online_cpus());
+ txq_info->ntxq = roundup(i, adap->params.nports);
+
+ txq_info->uldtxq = kcalloc(txq_info->ntxq, sizeof(struct sge_uld_txq),
+ GFP_KERNEL);
+ if (!txq_info->uldtxq) {
+ kfree(txq_info->uldtxq);
+ return -ENOMEM;
+ }
+
+ if (alloc_sge_txq_uld(adap, txq_info, tx_uld_type)) {
+ kfree(txq_info->uldtxq);
+ kfree(txq_info);
+ return -ENOMEM;
+ }
+
+ atomic_inc(&txq_info->users);
+ adap->sge.uld_txq_info[tx_uld_type] = txq_info;
+ return 0;
+}
+
static void uld_queue_init(struct adapter *adap, unsigned int uld_type,
struct cxgb4_lld_info *lli)
{
@@ -476,7 +572,15 @@ int t4_uld_mem_alloc(struct adapter *adap)
if (!s->uld_rxq_info)
goto err_uld;
+ s->uld_txq_info = kzalloc(CXGB4_TX_MAX *
+ sizeof(struct sge_uld_txq_info *),
+ GFP_KERNEL);
+ if (!s->uld_txq_info)
+ goto err_uld_rx;
return 0;
+
+err_uld_rx:
+ kfree(s->uld_rxq_info);
err_uld:
kfree(adap->uld);
return -ENOMEM;
@@ -486,6 +590,7 @@ void t4_uld_mem_free(struct adapter *adap)
{
struct sge *s = &adap->sge;
+ kfree(s->uld_txq_info);
kfree(s->uld_rxq_info);
kfree(adap->uld);
}
@@ -620,6 +725,9 @@ int cxgb4_register_uld(enum cxgb4_uld type,
ret = -EBUSY;
goto free_irq;
}
+ ret = setup_sge_txq_uld(adap, type, p);
+ if (ret)
+ goto free_irq;
adap->uld[type] = *p;
uld_attach(adap, type);
adap_idx++;
@@ -648,6 +756,7 @@ int cxgb4_register_uld(enum cxgb4_uld type,
break;
adap->uld[type].handle = NULL;
adap->uld[type].add = NULL;
+ release_sge_txq_uld(adap, type);
if (adap->flags & FULL_INIT_DONE)
quiesce_rx_uld(adap, type);
if (adap->flags & USING_MSIX)
@@ -683,6 +792,7 @@ int cxgb4_unregister_uld(enum cxgb4_uld type)
continue;
adap->uld[type].handle = NULL;
adap->uld[type].add = NULL;
+ release_sge_txq_uld(adap, type);
if (adap->flags & FULL_INIT_DONE)
quiesce_rx_uld(adap, type);
if (adap->flags & USING_MSIX)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 2996793..4c85660 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -77,6 +77,8 @@ enum {
/* Special asynchronous notification message */
#define CXGB4_MSG_AN ((void *)1)
+#define TX_ULD(uld)(((uld) != CXGB4_ULD_CRYPTO) ? CXGB4_TX_OFLD :\
+ CXGB4_TX_CRYPTO)
struct serv_entry {
void *data;
@@ -223,6 +225,19 @@ enum cxgb4_uld {
CXGB4_ULD_MAX
};
+enum cxgb4_tx_uld {
+ CXGB4_TX_OFLD,
+ CXGB4_TX_CRYPTO,
+ CXGB4_TX_MAX
+};
+
+enum cxgb4_txq_type {
+ CXGB4_TXQ_ETH,
+ CXGB4_TXQ_ULD,
+ CXGB4_TXQ_CTRL,
+ CXGB4_TXQ_MAX
+};
+
enum cxgb4_state {
CXGB4_STATE_UP,
CXGB4_STATE_START_RECOVERY,
@@ -316,6 +331,7 @@ struct cxgb4_uld_info {
void *handle;
unsigned int nrxq;
unsigned int rxq_size;
+ unsigned int ntxq;
bool ciq;
bool lro;
void *(*add)(const struct cxgb4_lld_info *p);
@@ -333,6 +349,7 @@ struct cxgb4_uld_info {
int cxgb4_register_uld(enum cxgb4_uld type, const struct cxgb4_uld_info *p);
int cxgb4_unregister_uld(enum cxgb4_uld type);
int cxgb4_ofld_send(struct net_device *dev, struct sk_buff *skb);
+int cxgb4_crypto_send(struct net_device *dev, struct sk_buff *skb);
unsigned int cxgb4_dbfifo_count(const struct net_device *dev, int lpfifo);
unsigned int cxgb4_port_chan(const struct net_device *dev);
unsigned int cxgb4_port_viid(const struct net_device *dev);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c
index 539de76..cbd68a8 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sched.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c
@@ -210,8 +210,10 @@ static int t4_sched_queue_bind(struct port_info *pi, struct ch_sched_queue *p)
/* Unbind queue from any existing class */
err = t4_sched_queue_unbind(pi, p);
- if (err)
+ if (err) {
+ t4_free_mem(qe);
goto out;
+ }
/* Bind queue to specified class */
memset(qe, 0, sizeof(*qe));
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 1e74fd6..b7d0753 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -377,8 +377,8 @@ unmap: dma_unmap_page(dev, be64_to_cpu(p->addr[0]),
* Reclaims Tx descriptors from an SGE Tx queue and frees the associated
* Tx buffers. Called with the Tx queue lock held.
*/
-static void free_tx_desc(struct adapter *adap, struct sge_txq *q,
- unsigned int n, bool unmap)
+void free_tx_desc(struct adapter *adap, struct sge_txq *q,
+ unsigned int n, bool unmap)
{
struct tx_sw_desc *d;
unsigned int cidx = q->cidx;
@@ -1543,7 +1543,7 @@ static inline unsigned int calc_tx_flits_ofld(const struct sk_buff *skb)
* inability to map packets. A periodic timer attempts to restart
* queues so marked.
*/
-static void txq_stop_maperr(struct sge_ofld_txq *q)
+static void txq_stop_maperr(struct sge_uld_txq *q)
{
q->mapping_err++;
q->q.stops++;
@@ -1559,7 +1559,7 @@ static void txq_stop_maperr(struct sge_ofld_txq *q)
* Stops an offload Tx queue that has become full and modifies the packet
* being written to request a wakeup.
*/
-static void ofldtxq_stop(struct sge_ofld_txq *q, struct sk_buff *skb)
+static void ofldtxq_stop(struct sge_uld_txq *q, struct sk_buff *skb)
{
struct fw_wr_hdr *wr = (struct fw_wr_hdr *)skb->data;
@@ -1586,7 +1586,7 @@ static void ofldtxq_stop(struct sge_ofld_txq *q, struct sk_buff *skb)
* boolean "service_ofldq_running" to make sure that only one instance
* is ever running at a time ...
*/
-static void service_ofldq(struct sge_ofld_txq *q)
+static void service_ofldq(struct sge_uld_txq *q)
{
u64 *pos, *before, *end;
int credits;
@@ -1706,7 +1706,7 @@ static void service_ofldq(struct sge_ofld_txq *q)
*
* Send an offload packet through an SGE offload queue.
*/
-static int ofld_xmit(struct sge_ofld_txq *q, struct sk_buff *skb)
+static int ofld_xmit(struct sge_uld_txq *q, struct sk_buff *skb)
{
skb->priority = calc_tx_flits_ofld(skb); /* save for restart */
spin_lock(&q->sendq.lock);
@@ -1735,7 +1735,7 @@ static int ofld_xmit(struct sge_ofld_txq *q, struct sk_buff *skb)
*/
static void restart_ofldq(unsigned long data)
{
- struct sge_ofld_txq *q = (struct sge_ofld_txq *)data;
+ struct sge_uld_txq *q = (struct sge_uld_txq *)data;
spin_lock(&q->sendq.lock);
q->full = 0; /* the queue actually is completely empty now */
@@ -1767,17 +1767,23 @@ static inline unsigned int is_ctrl_pkt(const struct sk_buff *skb)
return skb->queue_mapping & 1;
}
-static inline int ofld_send(struct adapter *adap, struct sk_buff *skb)
+static inline int uld_send(struct adapter *adap, struct sk_buff *skb,
+ unsigned int tx_uld_type)
{
+ struct sge_uld_txq_info *txq_info;
+ struct sge_uld_txq *txq;
unsigned int idx = skb_txq(skb);
+ txq_info = adap->sge.uld_txq_info[tx_uld_type];
+ txq = &txq_info->uldtxq[idx];
+
if (unlikely(is_ctrl_pkt(skb))) {
/* Single ctrl queue is a requirement for LE workaround path */
if (adap->tids.nsftids)
idx = 0;
return ctrl_xmit(&adap->sge.ctrlq[idx], skb);
}
- return ofld_xmit(&adap->sge.ofldtxq[idx], skb);
+ return ofld_xmit(txq, skb);
}
/**
@@ -1794,7 +1800,7 @@ int t4_ofld_send(struct adapter *adap, struct sk_buff *skb)
int ret;
local_bh_disable();
- ret = ofld_send(adap, skb);
+ ret = uld_send(adap, skb, CXGB4_TX_OFLD);
local_bh_enable();
return ret;
}
@@ -1813,6 +1819,39 @@ int cxgb4_ofld_send(struct net_device *dev, struct sk_buff *skb)
}
EXPORT_SYMBOL(cxgb4_ofld_send);
+/**
+ * t4_crypto_send - send crypto packet
+ * @adap: the adapter
+ * @skb: the packet
+ *
+ * Sends crypto packet. We use the packet queue_mapping to select the
+ * appropriate Tx queue as follows: bit 0 indicates whether the packet
+ * should be sent as regular or control, bits 1-15 select the queue.
+ */
+static int t4_crypto_send(struct adapter *adap, struct sk_buff *skb)
+{
+ int ret;
+
+ local_bh_disable();
+ ret = uld_send(adap, skb, CXGB4_TX_CRYPTO);
+ local_bh_enable();
+ return ret;
+}
+
+/**
+ * cxgb4_crypto_send - send crypto packet
+ * @dev: the net device
+ * @skb: the packet
+ *
+ * Sends crypto packet. This is an exported version of @t4_crypto_send,
+ * intended for ULDs.
+ */
+int cxgb4_crypto_send(struct net_device *dev, struct sk_buff *skb)
+{
+ return t4_crypto_send(netdev2adap(dev), skb);
+}
+EXPORT_SYMBOL(cxgb4_crypto_send);
+
static inline void copy_frags(struct sk_buff *skb,
const struct pkt_gl *gl, unsigned int offset)
{
@@ -2479,7 +2518,7 @@ static void sge_tx_timer_cb(unsigned long data)
for (i = 0; i < BITS_TO_LONGS(s->egr_sz); i++)
for (m = s->txq_maperr[i]; m; m &= m - 1) {
unsigned long id = __ffs(m) + i * BITS_PER_LONG;
- struct sge_ofld_txq *txq = s->egr_map[id];
+ struct sge_uld_txq *txq = s->egr_map[id];
clear_bit(id, s->txq_maperr);
tasklet_schedule(&txq->qresume_tsk);
@@ -2799,6 +2838,7 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
return ret;
}
+ txq->q.q_type = CXGB4_TXQ_ETH;
init_txq(adap, &txq->q, FW_EQ_ETH_CMD_EQID_G(ntohl(c.eqid_pkd)));
txq->txq = netdevq;
txq->tso = txq->tx_cso = txq->vlan_ins = 0;
@@ -2852,6 +2892,7 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
return ret;
}
+ txq->q.q_type = CXGB4_TXQ_CTRL;
init_txq(adap, &txq->q, FW_EQ_CTRL_CMD_EQID_G(ntohl(c.cmpliqid_eqid)));
txq->adap = adap;
skb_queue_head_init(&txq->sendq);
@@ -2872,13 +2913,15 @@ int t4_sge_mod_ctrl_txq(struct adapter *adap, unsigned int eqid,
return t4_set_params(adap, adap->mbox, adap->pf, 0, 1, ¶m, &val);
}
-int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq,
- struct net_device *dev, unsigned int iqid)
+int t4_sge_alloc_uld_txq(struct adapter *adap, struct sge_uld_txq *txq,
+ struct net_device *dev, unsigned int iqid,
+ unsigned int uld_type)
{
int ret, nentries;
struct fw_eq_ofld_cmd c;
struct sge *s = &adap->sge;
struct port_info *pi = netdev_priv(dev);
+ int cmd = FW_EQ_OFLD_CMD;
/* Add status entries */
nentries = txq->q.size + s->stat_len / sizeof(struct tx_desc);
@@ -2891,7 +2934,9 @@ int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq,
return -ENOMEM;
memset(&c, 0, sizeof(c));
- c.op_to_vfn = htonl(FW_CMD_OP_V(FW_EQ_OFLD_CMD) | FW_CMD_REQUEST_F |
+ if (unlikely(uld_type == CXGB4_TX_CRYPTO))
+ cmd = FW_EQ_CTRL_CMD;
+ c.op_to_vfn = htonl(FW_CMD_OP_V(cmd) | FW_CMD_REQUEST_F |
FW_CMD_WRITE_F | FW_CMD_EXEC_F |
FW_EQ_OFLD_CMD_PFN_V(adap->pf) |
FW_EQ_OFLD_CMD_VFN_V(0));
@@ -2919,6 +2964,7 @@ int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq,
return ret;
}
+ txq->q.q_type = CXGB4_TXQ_ULD;
init_txq(adap, &txq->q, FW_EQ_OFLD_CMD_EQID_G(ntohl(c.eqid_pkd)));
txq->adap = adap;
skb_queue_head_init(&txq->sendq);
@@ -2928,7 +2974,7 @@ int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq,
return 0;
}
-static void free_txq(struct adapter *adap, struct sge_txq *q)
+void free_txq(struct adapter *adap, struct sge_txq *q)
{
struct sge *s = &adap->sge;
@@ -3026,21 +3072,6 @@ void t4_free_sge_resources(struct adapter *adap)
}
}
- /* clean up offload Tx queues */
- for (i = 0; i < ARRAY_SIZE(adap->sge.ofldtxq); i++) {
- struct sge_ofld_txq *q = &adap->sge.ofldtxq[i];
-
- if (q->q.desc) {
- tasklet_kill(&q->qresume_tsk);
- t4_ofld_eq_free(adap, adap->mbox, adap->pf, 0,
- q->q.cntxt_id);
- free_tx_desc(adap, &q->q, q->q.in_use, false);
- kfree(q->q.sdesc);
- __skb_queue_purge(&q->sendq);
- free_txq(adap, &q->q);
- }
- }
-
/* clean up control Tx queues */
for (i = 0; i < ARRAY_SIZE(adap->sge.ctrlq); i++) {
struct sge_ctrl_txq *cq = &adap->sge.ctrlq[i];
@@ -3093,12 +3124,34 @@ void t4_sge_stop(struct adapter *adap)
if (s->tx_timer.function)
del_timer_sync(&s->tx_timer);
- for (i = 0; i < ARRAY_SIZE(s->ofldtxq); i++) {
- struct sge_ofld_txq *q = &s->ofldtxq[i];
+ if (is_offload(adap)) {
+ struct sge_uld_txq_info *txq_info;
- if (q->q.desc)
- tasklet_kill(&q->qresume_tsk);
+ txq_info = adap->sge.uld_txq_info[CXGB4_TX_OFLD];
+ if (txq_info) {
+ struct sge_uld_txq *txq = txq_info->uldtxq;
+
+ for_each_ofldtxq(&adap->sge, i) {
+ if (txq->q.desc)
+ tasklet_kill(&txq->qresume_tsk);
+ }
+ }
}
+
+ if (is_pci_uld(adap)) {
+ struct sge_uld_txq_info *txq_info;
+
+ txq_info = adap->sge.uld_txq_info[CXGB4_TX_CRYPTO];
+ if (txq_info) {
+ struct sge_uld_txq *txq = txq_info->uldtxq;
+
+ for_each_ofldtxq(&adap->sge, i) {
+ if (txq->q.desc)
+ tasklet_kill(&txq->qresume_tsk);
+ }
+ }
+ }
+
for (i = 0; i < ARRAY_SIZE(s->ctrlq); i++) {
struct sge_ctrl_txq *cq = &s->ctrlq[i];
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index 50812a1..df1573c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -178,9 +178,9 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
CH_PCI_ID_TABLE_FENTRY(0x6005),
CH_PCI_ID_TABLE_FENTRY(0x6006),
CH_PCI_ID_TABLE_FENTRY(0x6007),
+ CH_PCI_ID_TABLE_FENTRY(0x6008),
CH_PCI_ID_TABLE_FENTRY(0x6009),
CH_PCI_ID_TABLE_FENTRY(0x600d),
- CH_PCI_ID_TABLE_FENTRY(0x6010),
CH_PCI_ID_TABLE_FENTRY(0x6011),
CH_PCI_ID_TABLE_FENTRY(0x6014),
CH_PCI_ID_TABLE_FENTRY(0x6015),
diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index 130f910..9023c85 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -33,7 +33,7 @@
#define DRV_NAME "enic"
#define DRV_DESCRIPTION "Cisco VIC Ethernet NIC Driver"
-#define DRV_VERSION "2.3.0.20"
+#define DRV_VERSION "2.3.0.31"
#define DRV_COPYRIGHT "Copyright 2008-2013 Cisco Systems, Inc"
#define ENIC_BARS_MAX 6
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index f514faf..cdd7a1a 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1166,12 +1166,18 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
skb->protocol = eth_type_trans(skb, netdev);
skb_record_rx_queue(skb, q_number);
if (netdev->features & NETIF_F_RXHASH) {
- skb_set_hash(skb, rss_hash,
- (rss_type &
- (NIC_CFG_RSS_HASH_TYPE_TCP_IPV6_EX |
- NIC_CFG_RSS_HASH_TYPE_TCP_IPV6 |
- NIC_CFG_RSS_HASH_TYPE_TCP_IPV4)) ?
- PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3);
+ switch (rss_type) {
+ case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv4:
+ case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6:
+ case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6_EX:
+ skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L4);
+ break;
+ case CQ_ENET_RQ_DESC_RSS_TYPE_IPv4:
+ case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6:
+ case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6_EX:
+ skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L3);
+ break;
+ }
}
/* Hardware does not provide whole packet checksum. It only
diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.c b/drivers/net/ethernet/cisco/enic/vnic_rq.c
index e572a52..36bc2c7 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_rq.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_rq.c
@@ -169,19 +169,28 @@ int vnic_rq_disable(struct vnic_rq *rq)
{
unsigned int wait;
struct vnic_dev *vdev = rq->vdev;
+ int i;
- iowrite32(0, &rq->ctrl->enable);
+ /* Due to a race condition with clearing RQ "mini-cache" in hw, we need
+ * to disable the RQ twice to guarantee that stale descriptors are not
+ * used when this RQ is re-enabled.
+ */
+ for (i = 0; i < 2; i++) {
+ iowrite32(0, &rq->ctrl->enable);
- /* Wait for HW to ACK disable request */
- for (wait = 0; wait < 1000; wait++) {
- if (!(ioread32(&rq->ctrl->running)))
- return 0;
- udelay(10);
+ /* Wait for HW to ACK disable request */
+ for (wait = 20000; wait > 0; wait--)
+ if (!ioread32(&rq->ctrl->running))
+ break;
+ if (!wait) {
+ vdev_neterr(vdev, "Failed to disable RQ[%d]\n",
+ rq->index);
+
+ return -ETIMEDOUT;
+ }
}
- vdev_neterr(vdev, "Failed to disable RQ[%d]\n", rq->index);
-
- return -ETIMEDOUT;
+ return 0;
}
void vnic_rq_clean(struct vnic_rq *rq,
@@ -212,6 +221,11 @@ void vnic_rq_clean(struct vnic_rq *rq,
[fetch_index % VNIC_RQ_BUF_BLK_ENTRIES(count)];
iowrite32(fetch_index, &rq->ctrl->posted_index);
+ /* Anytime we write fetch_index, we need to re-write 0 to rq->enable
+ * to re-sync internal VIC state.
+ */
+ iowrite32(0, &rq->ctrl->enable);
+
vnic_dev_clear_desc_ring(&rq->ring);
}
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index c044667..6456c18 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -966,6 +966,7 @@ static int ethoc_set_ringparam(struct net_device *dev,
const struct ethtool_ops ethoc_ethtool_ops = {
.get_regs_len = ethoc_get_regs_len,
.get_regs = ethoc_get_regs,
+ .nway_reset = phy_ethtool_nway_reset,
.get_link = ethtool_op_get_link,
.get_ringparam = ethoc_get_ringparam,
.set_ringparam = ethoc_set_ringparam,
diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c
index f928e6f..223f35c 100644
--- a/drivers/net/ethernet/ezchip/nps_enet.c
+++ b/drivers/net/ethernet/ezchip/nps_enet.c
@@ -669,6 +669,7 @@ static const struct of_device_id nps_enet_dt_ids[] = {
{ .compatible = "ezchip,nps-mgt-enet" },
{ /* Sentinel */ }
};
+MODULE_DEVICE_TABLE(of, nps_enet_dt_ids);
static struct platform_driver nps_enet_driver = {
.probe = nps_enet_probe,
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index d1ca45f..0d41551 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -8,7 +8,7 @@
depends on FSL_SOC || QUICC_ENGINE || CPM1 || CPM2 || PPC_MPC512x || \
M523x || M527x || M5272 || M528x || M520x || M532x || \
ARCH_MXC || ARCH_MXS || (PPC_MPC52xx && PPC_BESTCOMM) || \
- ARCH_LAYERSCAPE
+ ARCH_LAYERSCAPE || COMPILE_TEST
---help---
If you have a network (Ethernet) card belonging to this class, say Y.
@@ -65,6 +65,7 @@
config FSL_XGMAC_MDIO
tristate "Freescale XGMAC MDIO"
select PHYLIB
+ depends on OF
select OF_MDIO
---help---
This driver supports the MDIO bus on the Fman 10G Ethernet MACs, and
@@ -85,6 +86,7 @@
config GIANFAR
tristate "Gianfar Ethernet"
+ depends on HAS_DMA
select FSL_PQ_MDIO
select PHYLIB
select CRC32
@@ -93,4 +95,6 @@
and MPC86xx family of chips, the eTSEC on LS1021A and the FEC
on the 8540.
+source "drivers/net/ethernet/freescale/dpaa/Kconfig"
+
endif # NET_VENDOR_FREESCALE
diff --git a/drivers/net/ethernet/freescale/Makefile b/drivers/net/ethernet/freescale/Makefile
index cbe21dc..4a13115 100644
--- a/drivers/net/ethernet/freescale/Makefile
+++ b/drivers/net/ethernet/freescale/Makefile
@@ -22,3 +22,4 @@
ucc_geth_driver-objs := ucc_geth.o ucc_geth_ethtool.o
obj-$(CONFIG_FSL_FMAN) += fman/
+obj-$(CONFIG_FSL_DPAA_ETH) += dpaa/
diff --git a/drivers/net/ethernet/freescale/dpaa/Kconfig b/drivers/net/ethernet/freescale/dpaa/Kconfig
new file mode 100644
index 0000000..f3a3454
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa/Kconfig
@@ -0,0 +1,10 @@
+menuconfig FSL_DPAA_ETH
+ tristate "DPAA Ethernet"
+ depends on FSL_SOC && FSL_DPAA && FSL_FMAN
+ select PHYLIB
+ select FSL_FMAN_MAC
+ ---help---
+ Data Path Acceleration Architecture Ethernet driver,
+ supporting the Freescale QorIQ chips.
+ Depends on Freescale Buffer Manager and Queue Manager
+ driver and Frame Manager Driver.
diff --git a/drivers/net/ethernet/freescale/dpaa/Makefile b/drivers/net/ethernet/freescale/dpaa/Makefile
new file mode 100644
index 0000000..7db50bc
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa/Makefile
@@ -0,0 +1,12 @@
+#
+# Makefile for the Freescale DPAA Ethernet controllers
+#
+
+# Include FMan headers
+FMAN = $(srctree)/drivers/net/ethernet/freescale/fman
+ccflags-y += -I$(FMAN)
+
+obj-$(CONFIG_FSL_DPAA_ETH) += fsl_dpa.o
+
+fsl_dpa-objs += dpaa_eth.o dpaa_ethtool.o dpaa_eth_sysfs.o
+CFLAGS_dpaa_eth.o := -I$(src)
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
new file mode 100644
index 0000000..3c48a84
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -0,0 +1,2753 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/io.h>
+#include <linux/if_arp.h>
+#include <linux/if_vlan.h>
+#include <linux/icmp.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h>
+#include <linux/highmem.h>
+#include <linux/percpu.h>
+#include <linux/dma-mapping.h>
+#include <linux/sort.h>
+#include <soc/fsl/bman.h>
+#include <soc/fsl/qman.h>
+
+#include "fman.h"
+#include "fman_port.h"
+#include "mac.h"
+#include "dpaa_eth.h"
+
+/* CREATE_TRACE_POINTS only needs to be defined once. Other dpaa files
+ * using trace events only need to #include <trace/events/sched.h>
+ */
+#define CREATE_TRACE_POINTS
+#include "dpaa_eth_trace.h"
+
+static int debug = -1;
+module_param(debug, int, 0444);
+MODULE_PARM_DESC(debug, "Module/Driver verbosity level (0=none,...,16=all)");
+
+static u16 tx_timeout = 1000;
+module_param(tx_timeout, ushort, 0444);
+MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms");
+
+#define FM_FD_STAT_RX_ERRORS \
+ (FM_FD_ERR_DMA | FM_FD_ERR_PHYSICAL | \
+ FM_FD_ERR_SIZE | FM_FD_ERR_CLS_DISCARD | \
+ FM_FD_ERR_EXTRACTION | FM_FD_ERR_NO_SCHEME | \
+ FM_FD_ERR_PRS_TIMEOUT | FM_FD_ERR_PRS_ILL_INSTRUCT | \
+ FM_FD_ERR_PRS_HDR_ERR)
+
+#define FM_FD_STAT_TX_ERRORS \
+ (FM_FD_ERR_UNSUPPORTED_FORMAT | \
+ FM_FD_ERR_LENGTH | FM_FD_ERR_DMA)
+
+#define DPAA_MSG_DEFAULT (NETIF_MSG_DRV | NETIF_MSG_PROBE | \
+ NETIF_MSG_LINK | NETIF_MSG_IFUP | \
+ NETIF_MSG_IFDOWN)
+
+#define DPAA_INGRESS_CS_THRESHOLD 0x10000000
+/* Ingress congestion threshold on FMan ports
+ * The size in bytes of the ingress tail-drop threshold on FMan ports.
+ * Traffic piling up above this value will be rejected by QMan and discarded
+ * by FMan.
+ */
+
+/* Size in bytes of the FQ taildrop threshold */
+#define DPAA_FQ_TD 0x200000
+
+#define DPAA_CS_THRESHOLD_1G 0x06000000
+/* Egress congestion threshold on 1G ports, range 0x1000 .. 0x10000000
+ * The size in bytes of the egress Congestion State notification threshold on
+ * 1G ports. The 1G dTSECs can quite easily be flooded by cores doing Tx in a
+ * tight loop (e.g. by sending UDP datagrams at "while(1) speed"),
+ * and the larger the frame size, the more acute the problem.
+ * So we have to find a balance between these factors:
+ * - avoiding the device staying congested for a prolonged time (risking
+ * the netdev watchdog to fire - see also the tx_timeout module param);
+ * - affecting performance of protocols such as TCP, which otherwise
+ * behave well under the congestion notification mechanism;
+ * - preventing the Tx cores from tightly-looping (as if the congestion
+ * threshold was too low to be effective);
+ * - running out of memory if the CS threshold is set too high.
+ */
+
+#define DPAA_CS_THRESHOLD_10G 0x10000000
+/* The size in bytes of the egress Congestion State notification threshold on
+ * 10G ports, range 0x1000 .. 0x10000000
+ */
+
+/* Largest value that the FQD's OAL field can hold */
+#define FSL_QMAN_MAX_OAL 127
+
+/* Default alignment for start of data in an Rx FD */
+#define DPAA_FD_DATA_ALIGNMENT 16
+
+/* Values for the L3R field of the FM Parse Results
+ */
+/* L3 Type field: First IP Present IPv4 */
+#define FM_L3_PARSE_RESULT_IPV4 0x8000
+/* L3 Type field: First IP Present IPv6 */
+#define FM_L3_PARSE_RESULT_IPV6 0x4000
+/* Values for the L4R field of the FM Parse Results */
+/* L4 Type field: UDP */
+#define FM_L4_PARSE_RESULT_UDP 0x40
+/* L4 Type field: TCP */
+#define FM_L4_PARSE_RESULT_TCP 0x20
+
+#define DPAA_SGT_MAX_ENTRIES 16 /* maximum number of entries in SG Table */
+#define DPAA_BUFF_RELEASE_MAX 8 /* maximum number of buffers released at once */
+
+#define FSL_DPAA_BPID_INV 0xff
+#define FSL_DPAA_ETH_MAX_BUF_COUNT 128
+#define FSL_DPAA_ETH_REFILL_THRESHOLD 80
+
+#define DPAA_TX_PRIV_DATA_SIZE 16
+#define DPAA_PARSE_RESULTS_SIZE sizeof(struct fman_prs_result)
+#define DPAA_TIME_STAMP_SIZE 8
+#define DPAA_HASH_RESULTS_SIZE 8
+#define DPAA_RX_PRIV_DATA_SIZE (u16)(DPAA_TX_PRIV_DATA_SIZE + \
+ dpaa_rx_extra_headroom)
+
+#define DPAA_ETH_RX_QUEUES 128
+
+#define DPAA_ENQUEUE_RETRIES 100000
+
+enum port_type {RX, TX};
+
+struct fm_port_fqs {
+ struct dpaa_fq *tx_defq;
+ struct dpaa_fq *tx_errq;
+ struct dpaa_fq *rx_defq;
+ struct dpaa_fq *rx_errq;
+};
+
+/* All the dpa bps in use at any moment */
+static struct dpaa_bp *dpaa_bp_array[BM_MAX_NUM_OF_POOLS];
+
+/* The raw buffer size must be cacheline aligned */
+#define DPAA_BP_RAW_SIZE 4096
+/* When using more than one buffer pool, the raw sizes are as follows:
+ * 1 bp: 4KB
+ * 2 bp: 2KB, 4KB
+ * 3 bp: 1KB, 2KB, 4KB
+ * 4 bp: 1KB, 2KB, 4KB, 8KB
+ */
+static inline size_t bpool_buffer_raw_size(u8 index, u8 cnt)
+{
+ size_t res = DPAA_BP_RAW_SIZE / 4;
+ u8 i;
+
+ for (i = (cnt < 3) ? cnt : 3; i < 3 + index; i++)
+ res *= 2;
+ return res;
+}
+
+/* FMan-DMA requires 16-byte alignment for Rx buffers, but SKB_DATA_ALIGN is
+ * even stronger (SMP_CACHE_BYTES-aligned), so we just get away with that,
+ * via SKB_WITH_OVERHEAD(). We can't rely on netdev_alloc_frag() giving us
+ * half-page-aligned buffers, so we reserve some more space for start-of-buffer
+ * alignment.
+ */
+#define dpaa_bp_size(raw_size) SKB_WITH_OVERHEAD((raw_size) - SMP_CACHE_BYTES)
+
+static int dpaa_max_frm;
+
+static int dpaa_rx_extra_headroom;
+
+#define dpaa_get_max_mtu() \
+ (dpaa_max_frm - (VLAN_ETH_HLEN + ETH_FCS_LEN))
+
+static int dpaa_netdev_init(struct net_device *net_dev,
+ const struct net_device_ops *dpaa_ops,
+ u16 tx_timeout)
+{
+ struct dpaa_priv *priv = netdev_priv(net_dev);
+ struct device *dev = net_dev->dev.parent;
+ struct dpaa_percpu_priv *percpu_priv;
+ const u8 *mac_addr;
+ int i, err;
+
+ /* Although we access another CPU's private data here
+ * we do it at initialization so it is safe
+ */
+ for_each_possible_cpu(i) {
+ percpu_priv = per_cpu_ptr(priv->percpu_priv, i);
+ percpu_priv->net_dev = net_dev;
+ }
+
+ net_dev->netdev_ops = dpaa_ops;
+ mac_addr = priv->mac_dev->addr;
+
+ net_dev->mem_start = priv->mac_dev->res->start;
+ net_dev->mem_end = priv->mac_dev->res->end;
+
+ net_dev->min_mtu = ETH_MIN_MTU;
+ net_dev->max_mtu = dpaa_get_max_mtu();
+
+ net_dev->hw_features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+ NETIF_F_LLTX);
+
+ net_dev->hw_features |= NETIF_F_SG | NETIF_F_HIGHDMA;
+ /* The kernels enables GSO automatically, if we declare NETIF_F_SG.
+ * For conformity, we'll still declare GSO explicitly.
+ */
+ net_dev->features |= NETIF_F_GSO;
+
+ net_dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+ /* we do not want shared skbs on TX */
+ net_dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+
+ net_dev->features |= net_dev->hw_features;
+ net_dev->vlan_features = net_dev->features;
+
+ memcpy(net_dev->perm_addr, mac_addr, net_dev->addr_len);
+ memcpy(net_dev->dev_addr, mac_addr, net_dev->addr_len);
+
+ net_dev->ethtool_ops = &dpaa_ethtool_ops;
+
+ net_dev->needed_headroom = priv->tx_headroom;
+ net_dev->watchdog_timeo = msecs_to_jiffies(tx_timeout);
+
+ /* start without the RUNNING flag, phylib controls it later */
+ netif_carrier_off(net_dev);
+
+ err = register_netdev(net_dev);
+ if (err < 0) {
+ dev_err(dev, "register_netdev() = %d\n", err);
+ return err;
+ }
+
+ return 0;
+}
+
+static int dpaa_stop(struct net_device *net_dev)
+{
+ struct mac_device *mac_dev;
+ struct dpaa_priv *priv;
+ int i, err, error;
+
+ priv = netdev_priv(net_dev);
+ mac_dev = priv->mac_dev;
+
+ netif_tx_stop_all_queues(net_dev);
+ /* Allow the Fman (Tx) port to process in-flight frames before we
+ * try switching it off.
+ */
+ usleep_range(5000, 10000);
+
+ err = mac_dev->stop(mac_dev);
+ if (err < 0)
+ netif_err(priv, ifdown, net_dev, "mac_dev->stop() = %d\n",
+ err);
+
+ for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) {
+ error = fman_port_disable(mac_dev->port[i]);
+ if (error)
+ err = error;
+ }
+
+ if (net_dev->phydev)
+ phy_disconnect(net_dev->phydev);
+ net_dev->phydev = NULL;
+
+ return err;
+}
+
+static void dpaa_tx_timeout(struct net_device *net_dev)
+{
+ struct dpaa_percpu_priv *percpu_priv;
+ const struct dpaa_priv *priv;
+
+ priv = netdev_priv(net_dev);
+ percpu_priv = this_cpu_ptr(priv->percpu_priv);
+
+ netif_crit(priv, timer, net_dev, "Transmit timeout latency: %u ms\n",
+ jiffies_to_msecs(jiffies - dev_trans_start(net_dev)));
+
+ percpu_priv->stats.tx_errors++;
+}
+
+/* Calculates the statistics for the given device by adding the statistics
+ * collected by each CPU.
+ */
+static struct rtnl_link_stats64 *dpaa_get_stats64(struct net_device *net_dev,
+ struct rtnl_link_stats64 *s)
+{
+ int numstats = sizeof(struct rtnl_link_stats64) / sizeof(u64);
+ struct dpaa_priv *priv = netdev_priv(net_dev);
+ struct dpaa_percpu_priv *percpu_priv;
+ u64 *netstats = (u64 *)s;
+ u64 *cpustats;
+ int i, j;
+
+ for_each_possible_cpu(i) {
+ percpu_priv = per_cpu_ptr(priv->percpu_priv, i);
+
+ cpustats = (u64 *)&percpu_priv->stats;
+
+ /* add stats from all CPUs */
+ for (j = 0; j < numstats; j++)
+ netstats[j] += cpustats[j];
+ }
+
+ return s;
+}
+
+static struct mac_device *dpaa_mac_dev_get(struct platform_device *pdev)
+{
+ struct platform_device *of_dev;
+ struct dpaa_eth_data *eth_data;
+ struct device *dpaa_dev, *dev;
+ struct device_node *mac_node;
+ struct mac_device *mac_dev;
+
+ dpaa_dev = &pdev->dev;
+ eth_data = dpaa_dev->platform_data;
+ if (!eth_data)
+ return ERR_PTR(-ENODEV);
+
+ mac_node = eth_data->mac_node;
+
+ of_dev = of_find_device_by_node(mac_node);
+ if (!of_dev) {
+ dev_err(dpaa_dev, "of_find_device_by_node(%s) failed\n",
+ mac_node->full_name);
+ of_node_put(mac_node);
+ return ERR_PTR(-EINVAL);
+ }
+ of_node_put(mac_node);
+
+ dev = &of_dev->dev;
+
+ mac_dev = dev_get_drvdata(dev);
+ if (!mac_dev) {
+ dev_err(dpaa_dev, "dev_get_drvdata(%s) failed\n",
+ dev_name(dev));
+ return ERR_PTR(-EINVAL);
+ }
+
+ return mac_dev;
+}
+
+static int dpaa_set_mac_address(struct net_device *net_dev, void *addr)
+{
+ const struct dpaa_priv *priv;
+ struct mac_device *mac_dev;
+ struct sockaddr old_addr;
+ int err;
+
+ priv = netdev_priv(net_dev);
+
+ memcpy(old_addr.sa_data, net_dev->dev_addr, ETH_ALEN);
+
+ err = eth_mac_addr(net_dev, addr);
+ if (err < 0) {
+ netif_err(priv, drv, net_dev, "eth_mac_addr() = %d\n", err);
+ return err;
+ }
+
+ mac_dev = priv->mac_dev;
+
+ err = mac_dev->change_addr(mac_dev->fman_mac,
+ (enet_addr_t *)net_dev->dev_addr);
+ if (err < 0) {
+ netif_err(priv, drv, net_dev, "mac_dev->change_addr() = %d\n",
+ err);
+ /* reverting to previous address */
+ eth_mac_addr(net_dev, &old_addr);
+
+ return err;
+ }
+
+ return 0;
+}
+
+static void dpaa_set_rx_mode(struct net_device *net_dev)
+{
+ const struct dpaa_priv *priv;
+ int err;
+
+ priv = netdev_priv(net_dev);
+
+ if (!!(net_dev->flags & IFF_PROMISC) != priv->mac_dev->promisc) {
+ priv->mac_dev->promisc = !priv->mac_dev->promisc;
+ err = priv->mac_dev->set_promisc(priv->mac_dev->fman_mac,
+ priv->mac_dev->promisc);
+ if (err < 0)
+ netif_err(priv, drv, net_dev,
+ "mac_dev->set_promisc() = %d\n",
+ err);
+ }
+
+ err = priv->mac_dev->set_multi(net_dev, priv->mac_dev);
+ if (err < 0)
+ netif_err(priv, drv, net_dev, "mac_dev->set_multi() = %d\n",
+ err);
+}
+
+static struct dpaa_bp *dpaa_bpid2pool(int bpid)
+{
+ if (WARN_ON(bpid < 0 || bpid >= BM_MAX_NUM_OF_POOLS))
+ return NULL;
+
+ return dpaa_bp_array[bpid];
+}
+
+/* checks if this bpool is already allocated */
+static bool dpaa_bpid2pool_use(int bpid)
+{
+ if (dpaa_bpid2pool(bpid)) {
+ atomic_inc(&dpaa_bp_array[bpid]->refs);
+ return true;
+ }
+
+ return false;
+}
+
+/* called only once per bpid by dpaa_bp_alloc_pool() */
+static void dpaa_bpid2pool_map(int bpid, struct dpaa_bp *dpaa_bp)
+{
+ dpaa_bp_array[bpid] = dpaa_bp;
+ atomic_set(&dpaa_bp->refs, 1);
+}
+
+static int dpaa_bp_alloc_pool(struct dpaa_bp *dpaa_bp)
+{
+ int err;
+
+ if (dpaa_bp->size == 0 || dpaa_bp->config_count == 0) {
+ pr_err("%s: Buffer pool is not properly initialized! Missing size or initial number of buffers\n",
+ __func__);
+ return -EINVAL;
+ }
+
+ /* If the pool is already specified, we only create one per bpid */
+ if (dpaa_bp->bpid != FSL_DPAA_BPID_INV &&
+ dpaa_bpid2pool_use(dpaa_bp->bpid))
+ return 0;
+
+ if (dpaa_bp->bpid == FSL_DPAA_BPID_INV) {
+ dpaa_bp->pool = bman_new_pool();
+ if (!dpaa_bp->pool) {
+ pr_err("%s: bman_new_pool() failed\n",
+ __func__);
+ return -ENODEV;
+ }
+
+ dpaa_bp->bpid = (u8)bman_get_bpid(dpaa_bp->pool);
+ }
+
+ if (dpaa_bp->seed_cb) {
+ err = dpaa_bp->seed_cb(dpaa_bp);
+ if (err)
+ goto pool_seed_failed;
+ }
+
+ dpaa_bpid2pool_map(dpaa_bp->bpid, dpaa_bp);
+
+ return 0;
+
+pool_seed_failed:
+ pr_err("%s: pool seeding failed\n", __func__);
+ bman_free_pool(dpaa_bp->pool);
+
+ return err;
+}
+
+/* remove and free all the buffers from the given buffer pool */
+static void dpaa_bp_drain(struct dpaa_bp *bp)
+{
+ u8 num = 8;
+ int ret;
+
+ do {
+ struct bm_buffer bmb[8];
+ int i;
+
+ ret = bman_acquire(bp->pool, bmb, num);
+ if (ret < 0) {
+ if (num == 8) {
+ /* we have less than 8 buffers left;
+ * drain them one by one
+ */
+ num = 1;
+ ret = 1;
+ continue;
+ } else {
+ /* Pool is fully drained */
+ break;
+ }
+ }
+
+ if (bp->free_buf_cb)
+ for (i = 0; i < num; i++)
+ bp->free_buf_cb(bp, &bmb[i]);
+ } while (ret > 0);
+}
+
+static void dpaa_bp_free(struct dpaa_bp *dpaa_bp)
+{
+ struct dpaa_bp *bp = dpaa_bpid2pool(dpaa_bp->bpid);
+
+ /* the mapping between bpid and dpaa_bp is done very late in the
+ * allocation procedure; if something failed before the mapping, the bp
+ * was not configured, therefore we don't need the below instructions
+ */
+ if (!bp)
+ return;
+
+ if (!atomic_dec_and_test(&bp->refs))
+ return;
+
+ if (bp->free_buf_cb)
+ dpaa_bp_drain(bp);
+
+ dpaa_bp_array[bp->bpid] = NULL;
+ bman_free_pool(bp->pool);
+}
+
+static void dpaa_bps_free(struct dpaa_priv *priv)
+{
+ int i;
+
+ for (i = 0; i < DPAA_BPS_NUM; i++)
+ dpaa_bp_free(priv->dpaa_bps[i]);
+}
+
+/* Use multiple WQs for FQ assignment:
+ * - Tx Confirmation queues go to WQ1.
+ * - Rx Error and Tx Error queues go to WQ2 (giving them a better chance
+ * to be scheduled, in case there are many more FQs in WQ3).
+ * - Rx Default and Tx queues go to WQ3 (no differentiation between
+ * Rx and Tx traffic).
+ * This ensures that Tx-confirmed buffers are timely released. In particular,
+ * it avoids congestion on the Tx Confirm FQs, which can pile up PFDRs if they
+ * are greatly outnumbered by other FQs in the system, while
+ * dequeue scheduling is round-robin.
+ */
+static inline void dpaa_assign_wq(struct dpaa_fq *fq)
+{
+ switch (fq->fq_type) {
+ case FQ_TYPE_TX_CONFIRM:
+ case FQ_TYPE_TX_CONF_MQ:
+ fq->wq = 1;
+ break;
+ case FQ_TYPE_RX_ERROR:
+ case FQ_TYPE_TX_ERROR:
+ fq->wq = 2;
+ break;
+ case FQ_TYPE_RX_DEFAULT:
+ case FQ_TYPE_TX:
+ fq->wq = 3;
+ break;
+ default:
+ WARN(1, "Invalid FQ type %d for FQID %d!\n",
+ fq->fq_type, fq->fqid);
+ }
+}
+
+static struct dpaa_fq *dpaa_fq_alloc(struct device *dev,
+ u32 start, u32 count,
+ struct list_head *list,
+ enum dpaa_fq_type fq_type)
+{
+ struct dpaa_fq *dpaa_fq;
+ int i;
+
+ dpaa_fq = devm_kzalloc(dev, sizeof(*dpaa_fq) * count,
+ GFP_KERNEL);
+ if (!dpaa_fq)
+ return NULL;
+
+ for (i = 0; i < count; i++) {
+ dpaa_fq[i].fq_type = fq_type;
+ dpaa_fq[i].fqid = start ? start + i : 0;
+ list_add_tail(&dpaa_fq[i].list, list);
+ }
+
+ for (i = 0; i < count; i++)
+ dpaa_assign_wq(dpaa_fq + i);
+
+ return dpaa_fq;
+}
+
+static int dpaa_alloc_all_fqs(struct device *dev, struct list_head *list,
+ struct fm_port_fqs *port_fqs)
+{
+ struct dpaa_fq *dpaa_fq;
+
+ dpaa_fq = dpaa_fq_alloc(dev, 0, 1, list, FQ_TYPE_RX_ERROR);
+ if (!dpaa_fq)
+ goto fq_alloc_failed;
+
+ port_fqs->rx_errq = &dpaa_fq[0];
+
+ dpaa_fq = dpaa_fq_alloc(dev, 0, 1, list, FQ_TYPE_RX_DEFAULT);
+ if (!dpaa_fq)
+ goto fq_alloc_failed;
+
+ port_fqs->rx_defq = &dpaa_fq[0];
+
+ if (!dpaa_fq_alloc(dev, 0, DPAA_ETH_TXQ_NUM, list, FQ_TYPE_TX_CONF_MQ))
+ goto fq_alloc_failed;
+
+ dpaa_fq = dpaa_fq_alloc(dev, 0, 1, list, FQ_TYPE_TX_ERROR);
+ if (!dpaa_fq)
+ goto fq_alloc_failed;
+
+ port_fqs->tx_errq = &dpaa_fq[0];
+
+ dpaa_fq = dpaa_fq_alloc(dev, 0, 1, list, FQ_TYPE_TX_CONFIRM);
+ if (!dpaa_fq)
+ goto fq_alloc_failed;
+
+ port_fqs->tx_defq = &dpaa_fq[0];
+
+ if (!dpaa_fq_alloc(dev, 0, DPAA_ETH_TXQ_NUM, list, FQ_TYPE_TX))
+ goto fq_alloc_failed;
+
+ return 0;
+
+fq_alloc_failed:
+ dev_err(dev, "dpaa_fq_alloc() failed\n");
+ return -ENOMEM;
+}
+
+static u32 rx_pool_channel;
+static DEFINE_SPINLOCK(rx_pool_channel_init);
+
+static int dpaa_get_channel(void)
+{
+ spin_lock(&rx_pool_channel_init);
+ if (!rx_pool_channel) {
+ u32 pool;
+ int ret;
+
+ ret = qman_alloc_pool(&pool);
+
+ if (!ret)
+ rx_pool_channel = pool;
+ }
+ spin_unlock(&rx_pool_channel_init);
+ if (!rx_pool_channel)
+ return -ENOMEM;
+ return rx_pool_channel;
+}
+
+static void dpaa_release_channel(void)
+{
+ qman_release_pool(rx_pool_channel);
+}
+
+static void dpaa_eth_add_channel(u16 channel)
+{
+ u32 pool = QM_SDQCR_CHANNELS_POOL_CONV(channel);
+ const cpumask_t *cpus = qman_affine_cpus();
+ struct qman_portal *portal;
+ int cpu;
+
+ for_each_cpu(cpu, cpus) {
+ portal = qman_get_affine_portal(cpu);
+ qman_p_static_dequeue_add(portal, pool);
+ }
+}
+
+/* Congestion group state change notification callback.
+ * Stops the device's egress queues while they are congested and
+ * wakes them upon exiting congested state.
+ * Also updates some CGR-related stats.
+ */
+static void dpaa_eth_cgscn(struct qman_portal *qm, struct qman_cgr *cgr,
+ int congested)
+{
+ struct dpaa_priv *priv = (struct dpaa_priv *)container_of(cgr,
+ struct dpaa_priv, cgr_data.cgr);
+
+ if (congested) {
+ priv->cgr_data.congestion_start_jiffies = jiffies;
+ netif_tx_stop_all_queues(priv->net_dev);
+ priv->cgr_data.cgr_congested_count++;
+ } else {
+ priv->cgr_data.congested_jiffies +=
+ (jiffies - priv->cgr_data.congestion_start_jiffies);
+ netif_tx_wake_all_queues(priv->net_dev);
+ }
+}
+
+static int dpaa_eth_cgr_init(struct dpaa_priv *priv)
+{
+ struct qm_mcc_initcgr initcgr;
+ u32 cs_th;
+ int err;
+
+ err = qman_alloc_cgrid(&priv->cgr_data.cgr.cgrid);
+ if (err < 0) {
+ if (netif_msg_drv(priv))
+ pr_err("%s: Error %d allocating CGR ID\n",
+ __func__, err);
+ goto out_error;
+ }
+ priv->cgr_data.cgr.cb = dpaa_eth_cgscn;
+
+ /* Enable Congestion State Change Notifications and CS taildrop */
+ initcgr.we_mask = QM_CGR_WE_CSCN_EN | QM_CGR_WE_CS_THRES;
+ initcgr.cgr.cscn_en = QM_CGR_EN;
+
+ /* Set different thresholds based on the MAC speed.
+ * This may turn suboptimal if the MAC is reconfigured at a speed
+ * lower than its max, e.g. if a dTSEC later negotiates a 100Mbps link.
+ * In such cases, we ought to reconfigure the threshold, too.
+ */
+ if (priv->mac_dev->if_support & SUPPORTED_10000baseT_Full)
+ cs_th = DPAA_CS_THRESHOLD_10G;
+ else
+ cs_th = DPAA_CS_THRESHOLD_1G;
+ qm_cgr_cs_thres_set64(&initcgr.cgr.cs_thres, cs_th, 1);
+
+ initcgr.we_mask |= QM_CGR_WE_CSTD_EN;
+ initcgr.cgr.cstd_en = QM_CGR_EN;
+
+ err = qman_create_cgr(&priv->cgr_data.cgr, QMAN_CGR_FLAG_USE_INIT,
+ &initcgr);
+ if (err < 0) {
+ if (netif_msg_drv(priv))
+ pr_err("%s: Error %d creating CGR with ID %d\n",
+ __func__, err, priv->cgr_data.cgr.cgrid);
+ qman_release_cgrid(priv->cgr_data.cgr.cgrid);
+ goto out_error;
+ }
+ if (netif_msg_drv(priv))
+ pr_debug("Created CGR %d for netdev with hwaddr %pM on QMan channel %d\n",
+ priv->cgr_data.cgr.cgrid, priv->mac_dev->addr,
+ priv->cgr_data.cgr.chan);
+
+out_error:
+ return err;
+}
+
+static inline void dpaa_setup_ingress(const struct dpaa_priv *priv,
+ struct dpaa_fq *fq,
+ const struct qman_fq *template)
+{
+ fq->fq_base = *template;
+ fq->net_dev = priv->net_dev;
+
+ fq->flags = QMAN_FQ_FLAG_NO_ENQUEUE;
+ fq->channel = priv->channel;
+}
+
+static inline void dpaa_setup_egress(const struct dpaa_priv *priv,
+ struct dpaa_fq *fq,
+ struct fman_port *port,
+ const struct qman_fq *template)
+{
+ fq->fq_base = *template;
+ fq->net_dev = priv->net_dev;
+
+ if (port) {
+ fq->flags = QMAN_FQ_FLAG_TO_DCPORTAL;
+ fq->channel = (u16)fman_port_get_qman_channel_id(port);
+ } else {
+ fq->flags = QMAN_FQ_FLAG_NO_MODIFY;
+ }
+}
+
+static void dpaa_fq_setup(struct dpaa_priv *priv,
+ const struct dpaa_fq_cbs *fq_cbs,
+ struct fman_port *tx_port)
+{
+ int egress_cnt = 0, conf_cnt = 0, num_portals = 0, cpu;
+ const cpumask_t *affine_cpus = qman_affine_cpus();
+ u16 portals[NR_CPUS];
+ struct dpaa_fq *fq;
+
+ for_each_cpu(cpu, affine_cpus)
+ portals[num_portals++] = qman_affine_channel(cpu);
+ if (num_portals == 0)
+ dev_err(priv->net_dev->dev.parent,
+ "No Qman software (affine) channels found");
+
+ /* Initialize each FQ in the list */
+ list_for_each_entry(fq, &priv->dpaa_fq_list, list) {
+ switch (fq->fq_type) {
+ case FQ_TYPE_RX_DEFAULT:
+ dpaa_setup_ingress(priv, fq, &fq_cbs->rx_defq);
+ break;
+ case FQ_TYPE_RX_ERROR:
+ dpaa_setup_ingress(priv, fq, &fq_cbs->rx_errq);
+ break;
+ case FQ_TYPE_TX:
+ dpaa_setup_egress(priv, fq, tx_port,
+ &fq_cbs->egress_ern);
+ /* If we have more Tx queues than the number of cores,
+ * just ignore the extra ones.
+ */
+ if (egress_cnt < DPAA_ETH_TXQ_NUM)
+ priv->egress_fqs[egress_cnt++] = &fq->fq_base;
+ break;
+ case FQ_TYPE_TX_CONF_MQ:
+ priv->conf_fqs[conf_cnt++] = &fq->fq_base;
+ /* fall through */
+ case FQ_TYPE_TX_CONFIRM:
+ dpaa_setup_ingress(priv, fq, &fq_cbs->tx_defq);
+ break;
+ case FQ_TYPE_TX_ERROR:
+ dpaa_setup_ingress(priv, fq, &fq_cbs->tx_errq);
+ break;
+ default:
+ dev_warn(priv->net_dev->dev.parent,
+ "Unknown FQ type detected!\n");
+ break;
+ }
+ }
+
+ /* Make sure all CPUs receive a corresponding Tx queue. */
+ while (egress_cnt < DPAA_ETH_TXQ_NUM) {
+ list_for_each_entry(fq, &priv->dpaa_fq_list, list) {
+ if (fq->fq_type != FQ_TYPE_TX)
+ continue;
+ priv->egress_fqs[egress_cnt++] = &fq->fq_base;
+ if (egress_cnt == DPAA_ETH_TXQ_NUM)
+ break;
+ }
+ }
+}
+
+static inline int dpaa_tx_fq_to_id(const struct dpaa_priv *priv,
+ struct qman_fq *tx_fq)
+{
+ int i;
+
+ for (i = 0; i < DPAA_ETH_TXQ_NUM; i++)
+ if (priv->egress_fqs[i] == tx_fq)
+ return i;
+
+ return -EINVAL;
+}
+
+static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable)
+{
+ const struct dpaa_priv *priv;
+ struct qman_fq *confq = NULL;
+ struct qm_mcc_initfq initfq;
+ struct device *dev;
+ struct qman_fq *fq;
+ int queue_id;
+ int err;
+
+ priv = netdev_priv(dpaa_fq->net_dev);
+ dev = dpaa_fq->net_dev->dev.parent;
+
+ if (dpaa_fq->fqid == 0)
+ dpaa_fq->flags |= QMAN_FQ_FLAG_DYNAMIC_FQID;
+
+ dpaa_fq->init = !(dpaa_fq->flags & QMAN_FQ_FLAG_NO_MODIFY);
+
+ err = qman_create_fq(dpaa_fq->fqid, dpaa_fq->flags, &dpaa_fq->fq_base);
+ if (err) {
+ dev_err(dev, "qman_create_fq() failed\n");
+ return err;
+ }
+ fq = &dpaa_fq->fq_base;
+
+ if (dpaa_fq->init) {
+ memset(&initfq, 0, sizeof(initfq));
+
+ initfq.we_mask = QM_INITFQ_WE_FQCTRL;
+ /* Note: we may get to keep an empty FQ in cache */
+ initfq.fqd.fq_ctrl = QM_FQCTRL_PREFERINCACHE;
+
+ /* Try to reduce the number of portal interrupts for
+ * Tx Confirmation FQs.
+ */
+ if (dpaa_fq->fq_type == FQ_TYPE_TX_CONFIRM)
+ initfq.fqd.fq_ctrl |= QM_FQCTRL_HOLDACTIVE;
+
+ /* FQ placement */
+ initfq.we_mask |= QM_INITFQ_WE_DESTWQ;
+
+ qm_fqd_set_destwq(&initfq.fqd, dpaa_fq->channel, dpaa_fq->wq);
+
+ /* Put all egress queues in a congestion group of their own.
+ * Sensu stricto, the Tx confirmation queues are Rx FQs,
+ * rather than Tx - but they nonetheless account for the
+ * memory footprint on behalf of egress traffic. We therefore
+ * place them in the netdev's CGR, along with the Tx FQs.
+ */
+ if (dpaa_fq->fq_type == FQ_TYPE_TX ||
+ dpaa_fq->fq_type == FQ_TYPE_TX_CONFIRM ||
+ dpaa_fq->fq_type == FQ_TYPE_TX_CONF_MQ) {
+ initfq.we_mask |= QM_INITFQ_WE_CGID;
+ initfq.fqd.fq_ctrl |= QM_FQCTRL_CGE;
+ initfq.fqd.cgid = (u8)priv->cgr_data.cgr.cgrid;
+ /* Set a fixed overhead accounting, in an attempt to
+ * reduce the impact of fixed-size skb shells and the
+ * driver's needed headroom on system memory. This is
+ * especially the case when the egress traffic is
+ * composed of small datagrams.
+ * Unfortunately, QMan's OAL value is capped to an
+ * insufficient value, but even that is better than
+ * no overhead accounting at all.
+ */
+ initfq.we_mask |= QM_INITFQ_WE_OAC;
+ qm_fqd_set_oac(&initfq.fqd, QM_OAC_CG);
+ qm_fqd_set_oal(&initfq.fqd,
+ min(sizeof(struct sk_buff) +
+ priv->tx_headroom,
+ (size_t)FSL_QMAN_MAX_OAL));
+ }
+
+ if (td_enable) {
+ initfq.we_mask |= QM_INITFQ_WE_TDTHRESH;
+ qm_fqd_set_taildrop(&initfq.fqd, DPAA_FQ_TD, 1);
+ initfq.fqd.fq_ctrl = QM_FQCTRL_TDE;
+ }
+
+ if (dpaa_fq->fq_type == FQ_TYPE_TX) {
+ queue_id = dpaa_tx_fq_to_id(priv, &dpaa_fq->fq_base);
+ if (queue_id >= 0)
+ confq = priv->conf_fqs[queue_id];
+ if (confq) {
+ initfq.we_mask |= QM_INITFQ_WE_CONTEXTA;
+ /* ContextA: OVOM=1(use contextA2 bits instead of ICAD)
+ * A2V=1 (contextA A2 field is valid)
+ * A0V=1 (contextA A0 field is valid)
+ * B0V=1 (contextB field is valid)
+ * ContextA A2: EBD=1 (deallocate buffers inside FMan)
+ * ContextB B0(ASPID): 0 (absolute Virtual Storage ID)
+ */
+ initfq.fqd.context_a.hi = 0x1e000000;
+ initfq.fqd.context_a.lo = 0x80000000;
+ }
+ }
+
+ /* Put all the ingress queues in our "ingress CGR". */
+ if (priv->use_ingress_cgr &&
+ (dpaa_fq->fq_type == FQ_TYPE_RX_DEFAULT ||
+ dpaa_fq->fq_type == FQ_TYPE_RX_ERROR)) {
+ initfq.we_mask |= QM_INITFQ_WE_CGID;
+ initfq.fqd.fq_ctrl |= QM_FQCTRL_CGE;
+ initfq.fqd.cgid = (u8)priv->ingress_cgr.cgrid;
+ /* Set a fixed overhead accounting, just like for the
+ * egress CGR.
+ */
+ initfq.we_mask |= QM_INITFQ_WE_OAC;
+ qm_fqd_set_oac(&initfq.fqd, QM_OAC_CG);
+ qm_fqd_set_oal(&initfq.fqd,
+ min(sizeof(struct sk_buff) +
+ priv->tx_headroom,
+ (size_t)FSL_QMAN_MAX_OAL));
+ }
+
+ /* Initialization common to all ingress queues */
+ if (dpaa_fq->flags & QMAN_FQ_FLAG_NO_ENQUEUE) {
+ initfq.we_mask |= QM_INITFQ_WE_CONTEXTA;
+ initfq.fqd.fq_ctrl |=
+ QM_FQCTRL_HOLDACTIVE;
+ initfq.fqd.context_a.stashing.exclusive =
+ QM_STASHING_EXCL_DATA | QM_STASHING_EXCL_CTX |
+ QM_STASHING_EXCL_ANNOTATION;
+ qm_fqd_set_stashing(&initfq.fqd, 1, 2,
+ DIV_ROUND_UP(sizeof(struct qman_fq),
+ 64));
+ }
+
+ err = qman_init_fq(fq, QMAN_INITFQ_FLAG_SCHED, &initfq);
+ if (err < 0) {
+ dev_err(dev, "qman_init_fq(%u) = %d\n",
+ qman_fq_fqid(fq), err);
+ qman_destroy_fq(fq);
+ return err;
+ }
+ }
+
+ dpaa_fq->fqid = qman_fq_fqid(fq);
+
+ return 0;
+}
+
+static int dpaa_fq_free_entry(struct device *dev, struct qman_fq *fq)
+{
+ const struct dpaa_priv *priv;
+ struct dpaa_fq *dpaa_fq;
+ int err, error;
+
+ err = 0;
+
+ dpaa_fq = container_of(fq, struct dpaa_fq, fq_base);
+ priv = netdev_priv(dpaa_fq->net_dev);
+
+ if (dpaa_fq->init) {
+ err = qman_retire_fq(fq, NULL);
+ if (err < 0 && netif_msg_drv(priv))
+ dev_err(dev, "qman_retire_fq(%u) = %d\n",
+ qman_fq_fqid(fq), err);
+
+ error = qman_oos_fq(fq);
+ if (error < 0 && netif_msg_drv(priv)) {
+ dev_err(dev, "qman_oos_fq(%u) = %d\n",
+ qman_fq_fqid(fq), error);
+ if (err >= 0)
+ err = error;
+ }
+ }
+
+ qman_destroy_fq(fq);
+ list_del(&dpaa_fq->list);
+
+ return err;
+}
+
+static int dpaa_fq_free(struct device *dev, struct list_head *list)
+{
+ struct dpaa_fq *dpaa_fq, *tmp;
+ int err, error;
+
+ err = 0;
+ list_for_each_entry_safe(dpaa_fq, tmp, list, list) {
+ error = dpaa_fq_free_entry(dev, (struct qman_fq *)dpaa_fq);
+ if (error < 0 && err >= 0)
+ err = error;
+ }
+
+ return err;
+}
+
+static void dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq,
+ struct dpaa_fq *defq,
+ struct dpaa_buffer_layout *buf_layout)
+{
+ struct fman_buffer_prefix_content buf_prefix_content;
+ struct fman_port_params params;
+ int err;
+
+ memset(¶ms, 0, sizeof(params));
+ memset(&buf_prefix_content, 0, sizeof(buf_prefix_content));
+
+ buf_prefix_content.priv_data_size = buf_layout->priv_data_size;
+ buf_prefix_content.pass_prs_result = true;
+ buf_prefix_content.pass_hash_result = true;
+ buf_prefix_content.pass_time_stamp = false;
+ buf_prefix_content.data_align = DPAA_FD_DATA_ALIGNMENT;
+
+ params.specific_params.non_rx_params.err_fqid = errq->fqid;
+ params.specific_params.non_rx_params.dflt_fqid = defq->fqid;
+
+ err = fman_port_config(port, ¶ms);
+ if (err)
+ pr_err("%s: fman_port_config failed\n", __func__);
+
+ err = fman_port_cfg_buf_prefix_content(port, &buf_prefix_content);
+ if (err)
+ pr_err("%s: fman_port_cfg_buf_prefix_content failed\n",
+ __func__);
+
+ err = fman_port_init(port);
+ if (err)
+ pr_err("%s: fm_port_init failed\n", __func__);
+}
+
+static void dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps,
+ size_t count, struct dpaa_fq *errq,
+ struct dpaa_fq *defq,
+ struct dpaa_buffer_layout *buf_layout)
+{
+ struct fman_buffer_prefix_content buf_prefix_content;
+ struct fman_port_rx_params *rx_p;
+ struct fman_port_params params;
+ int i, err;
+
+ memset(¶ms, 0, sizeof(params));
+ memset(&buf_prefix_content, 0, sizeof(buf_prefix_content));
+
+ buf_prefix_content.priv_data_size = buf_layout->priv_data_size;
+ buf_prefix_content.pass_prs_result = true;
+ buf_prefix_content.pass_hash_result = true;
+ buf_prefix_content.pass_time_stamp = false;
+ buf_prefix_content.data_align = DPAA_FD_DATA_ALIGNMENT;
+
+ rx_p = ¶ms.specific_params.rx_params;
+ rx_p->err_fqid = errq->fqid;
+ rx_p->dflt_fqid = defq->fqid;
+
+ count = min(ARRAY_SIZE(rx_p->ext_buf_pools.ext_buf_pool), count);
+ rx_p->ext_buf_pools.num_of_pools_used = (u8)count;
+ for (i = 0; i < count; i++) {
+ rx_p->ext_buf_pools.ext_buf_pool[i].id = bps[i]->bpid;
+ rx_p->ext_buf_pools.ext_buf_pool[i].size = (u16)bps[i]->size;
+ }
+
+ err = fman_port_config(port, ¶ms);
+ if (err)
+ pr_err("%s: fman_port_config failed\n", __func__);
+
+ err = fman_port_cfg_buf_prefix_content(port, &buf_prefix_content);
+ if (err)
+ pr_err("%s: fman_port_cfg_buf_prefix_content failed\n",
+ __func__);
+
+ err = fman_port_init(port);
+ if (err)
+ pr_err("%s: fm_port_init failed\n", __func__);
+}
+
+static void dpaa_eth_init_ports(struct mac_device *mac_dev,
+ struct dpaa_bp **bps, size_t count,
+ struct fm_port_fqs *port_fqs,
+ struct dpaa_buffer_layout *buf_layout,
+ struct device *dev)
+{
+ struct fman_port *rxport = mac_dev->port[RX];
+ struct fman_port *txport = mac_dev->port[TX];
+
+ dpaa_eth_init_tx_port(txport, port_fqs->tx_errq,
+ port_fqs->tx_defq, &buf_layout[TX]);
+ dpaa_eth_init_rx_port(rxport, bps, count, port_fqs->rx_errq,
+ port_fqs->rx_defq, &buf_layout[RX]);
+}
+
+static int dpaa_bman_release(const struct dpaa_bp *dpaa_bp,
+ struct bm_buffer *bmb, int cnt)
+{
+ int err;
+
+ err = bman_release(dpaa_bp->pool, bmb, cnt);
+ /* Should never occur, address anyway to avoid leaking the buffers */
+ if (unlikely(WARN_ON(err)) && dpaa_bp->free_buf_cb)
+ while (cnt-- > 0)
+ dpaa_bp->free_buf_cb(dpaa_bp, &bmb[cnt]);
+
+ return cnt;
+}
+
+static void dpaa_release_sgt_members(struct qm_sg_entry *sgt)
+{
+ struct bm_buffer bmb[DPAA_BUFF_RELEASE_MAX];
+ struct dpaa_bp *dpaa_bp;
+ int i = 0, j;
+
+ memset(bmb, 0, sizeof(bmb));
+
+ do {
+ dpaa_bp = dpaa_bpid2pool(sgt[i].bpid);
+ if (!dpaa_bp)
+ return;
+
+ j = 0;
+ do {
+ WARN_ON(qm_sg_entry_is_ext(&sgt[i]));
+
+ bm_buffer_set64(&bmb[j], qm_sg_entry_get64(&sgt[i]));
+
+ j++; i++;
+ } while (j < ARRAY_SIZE(bmb) &&
+ !qm_sg_entry_is_final(&sgt[i - 1]) &&
+ sgt[i - 1].bpid == sgt[i].bpid);
+
+ dpaa_bman_release(dpaa_bp, bmb, j);
+ } while (!qm_sg_entry_is_final(&sgt[i - 1]));
+}
+
+static void dpaa_fd_release(const struct net_device *net_dev,
+ const struct qm_fd *fd)
+{
+ struct qm_sg_entry *sgt;
+ struct dpaa_bp *dpaa_bp;
+ struct bm_buffer bmb;
+ dma_addr_t addr;
+ void *vaddr;
+
+ bmb.data = 0;
+ bm_buffer_set64(&bmb, qm_fd_addr(fd));
+
+ dpaa_bp = dpaa_bpid2pool(fd->bpid);
+ if (!dpaa_bp)
+ return;
+
+ if (qm_fd_get_format(fd) == qm_fd_sg) {
+ vaddr = phys_to_virt(qm_fd_addr(fd));
+ sgt = vaddr + qm_fd_get_offset(fd);
+
+ dma_unmap_single(dpaa_bp->dev, qm_fd_addr(fd), dpaa_bp->size,
+ DMA_FROM_DEVICE);
+
+ dpaa_release_sgt_members(sgt);
+
+ addr = dma_map_single(dpaa_bp->dev, vaddr, dpaa_bp->size,
+ DMA_FROM_DEVICE);
+ if (dma_mapping_error(dpaa_bp->dev, addr)) {
+ dev_err(dpaa_bp->dev, "DMA mapping failed");
+ return;
+ }
+ bm_buffer_set64(&bmb, addr);
+ }
+
+ dpaa_bman_release(dpaa_bp, &bmb, 1);
+}
+
+static void count_ern(struct dpaa_percpu_priv *percpu_priv,
+ const union qm_mr_entry *msg)
+{
+ switch (msg->ern.rc & QM_MR_RC_MASK) {
+ case QM_MR_RC_CGR_TAILDROP:
+ percpu_priv->ern_cnt.cg_tdrop++;
+ break;
+ case QM_MR_RC_WRED:
+ percpu_priv->ern_cnt.wred++;
+ break;
+ case QM_MR_RC_ERROR:
+ percpu_priv->ern_cnt.err_cond++;
+ break;
+ case QM_MR_RC_ORPWINDOW_EARLY:
+ percpu_priv->ern_cnt.early_window++;
+ break;
+ case QM_MR_RC_ORPWINDOW_LATE:
+ percpu_priv->ern_cnt.late_window++;
+ break;
+ case QM_MR_RC_FQ_TAILDROP:
+ percpu_priv->ern_cnt.fq_tdrop++;
+ break;
+ case QM_MR_RC_ORPWINDOW_RETIRED:
+ percpu_priv->ern_cnt.fq_retired++;
+ break;
+ case QM_MR_RC_ORP_ZERO:
+ percpu_priv->ern_cnt.orp_zero++;
+ break;
+ }
+}
+
+/* Turn on HW checksum computation for this outgoing frame.
+ * If the current protocol is not something we support in this regard
+ * (or if the stack has already computed the SW checksum), we do nothing.
+ *
+ * Returns 0 if all goes well (or HW csum doesn't apply), and a negative value
+ * otherwise.
+ *
+ * Note that this function may modify the fd->cmd field and the skb data buffer
+ * (the Parse Results area).
+ */
+static int dpaa_enable_tx_csum(struct dpaa_priv *priv,
+ struct sk_buff *skb,
+ struct qm_fd *fd,
+ char *parse_results)
+{
+ struct fman_prs_result *parse_result;
+ u16 ethertype = ntohs(skb->protocol);
+ struct ipv6hdr *ipv6h = NULL;
+ struct iphdr *iph;
+ int retval = 0;
+ u8 l4_proto;
+
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ return 0;
+
+ /* Note: L3 csum seems to be already computed in sw, but we can't choose
+ * L4 alone from the FM configuration anyway.
+ */
+
+ /* Fill in some fields of the Parse Results array, so the FMan
+ * can find them as if they came from the FMan Parser.
+ */
+ parse_result = (struct fman_prs_result *)parse_results;
+
+ /* If we're dealing with VLAN, get the real Ethernet type */
+ if (ethertype == ETH_P_8021Q) {
+ /* We can't always assume the MAC header is set correctly
+ * by the stack, so reset to beginning of skb->data
+ */
+ skb_reset_mac_header(skb);
+ ethertype = ntohs(vlan_eth_hdr(skb)->h_vlan_encapsulated_proto);
+ }
+
+ /* Fill in the relevant L3 parse result fields
+ * and read the L4 protocol type
+ */
+ switch (ethertype) {
+ case ETH_P_IP:
+ parse_result->l3r = cpu_to_be16(FM_L3_PARSE_RESULT_IPV4);
+ iph = ip_hdr(skb);
+ WARN_ON(!iph);
+ l4_proto = iph->protocol;
+ break;
+ case ETH_P_IPV6:
+ parse_result->l3r = cpu_to_be16(FM_L3_PARSE_RESULT_IPV6);
+ ipv6h = ipv6_hdr(skb);
+ WARN_ON(!ipv6h);
+ l4_proto = ipv6h->nexthdr;
+ break;
+ default:
+ /* We shouldn't even be here */
+ if (net_ratelimit())
+ netif_alert(priv, tx_err, priv->net_dev,
+ "Can't compute HW csum for L3 proto 0x%x\n",
+ ntohs(skb->protocol));
+ retval = -EIO;
+ goto return_error;
+ }
+
+ /* Fill in the relevant L4 parse result fields */
+ switch (l4_proto) {
+ case IPPROTO_UDP:
+ parse_result->l4r = FM_L4_PARSE_RESULT_UDP;
+ break;
+ case IPPROTO_TCP:
+ parse_result->l4r = FM_L4_PARSE_RESULT_TCP;
+ break;
+ default:
+ if (net_ratelimit())
+ netif_alert(priv, tx_err, priv->net_dev,
+ "Can't compute HW csum for L4 proto 0x%x\n",
+ l4_proto);
+ retval = -EIO;
+ goto return_error;
+ }
+
+ /* At index 0 is IPOffset_1 as defined in the Parse Results */
+ parse_result->ip_off[0] = (u8)skb_network_offset(skb);
+ parse_result->l4_off = (u8)skb_transport_offset(skb);
+
+ /* Enable L3 (and L4, if TCP or UDP) HW checksum. */
+ fd->cmd |= FM_FD_CMD_RPD | FM_FD_CMD_DTC;
+
+ /* On P1023 and similar platforms fd->cmd interpretation could
+ * be disabled by setting CONTEXT_A bit ICMD; currently this bit
+ * is not set so we do not need to check; in the future, if/when
+ * using context_a we need to check this bit
+ */
+
+return_error:
+ return retval;
+}
+
+static int dpaa_bp_add_8_bufs(const struct dpaa_bp *dpaa_bp)
+{
+ struct device *dev = dpaa_bp->dev;
+ struct bm_buffer bmb[8];
+ dma_addr_t addr;
+ void *new_buf;
+ u8 i;
+
+ for (i = 0; i < 8; i++) {
+ new_buf = netdev_alloc_frag(dpaa_bp->raw_size);
+ if (unlikely(!new_buf)) {
+ dev_err(dev, "netdev_alloc_frag() failed, size %zu\n",
+ dpaa_bp->raw_size);
+ goto release_previous_buffs;
+ }
+ new_buf = PTR_ALIGN(new_buf, SMP_CACHE_BYTES);
+
+ addr = dma_map_single(dev, new_buf,
+ dpaa_bp->size, DMA_FROM_DEVICE);
+ if (unlikely(dma_mapping_error(dev, addr))) {
+ dev_err(dpaa_bp->dev, "DMA map failed");
+ goto release_previous_buffs;
+ }
+
+ bmb[i].data = 0;
+ bm_buffer_set64(&bmb[i], addr);
+ }
+
+release_bufs:
+ return dpaa_bman_release(dpaa_bp, bmb, i);
+
+release_previous_buffs:
+ WARN_ONCE(1, "dpaa_eth: failed to add buffers on Rx\n");
+
+ bm_buffer_set64(&bmb[i], 0);
+ /* Avoid releasing a completely null buffer; bman_release() requires
+ * at least one buffer.
+ */
+ if (likely(i))
+ goto release_bufs;
+
+ return 0;
+}
+
+static int dpaa_bp_seed(struct dpaa_bp *dpaa_bp)
+{
+ int i;
+
+ /* Give each CPU an allotment of "config_count" buffers */
+ for_each_possible_cpu(i) {
+ int *count_ptr = per_cpu_ptr(dpaa_bp->percpu_count, i);
+ int j;
+
+ /* Although we access another CPU's counters here
+ * we do it at boot time so it is safe
+ */
+ for (j = 0; j < dpaa_bp->config_count; j += 8)
+ *count_ptr += dpaa_bp_add_8_bufs(dpaa_bp);
+ }
+ return 0;
+}
+
+/* Add buffers/(pages) for Rx processing whenever bpool count falls below
+ * REFILL_THRESHOLD.
+ */
+static int dpaa_eth_refill_bpool(struct dpaa_bp *dpaa_bp, int *countptr)
+{
+ int count = *countptr;
+ int new_bufs;
+
+ if (unlikely(count < FSL_DPAA_ETH_REFILL_THRESHOLD)) {
+ do {
+ new_bufs = dpaa_bp_add_8_bufs(dpaa_bp);
+ if (unlikely(!new_bufs)) {
+ /* Avoid looping forever if we've temporarily
+ * run out of memory. We'll try again at the
+ * next NAPI cycle.
+ */
+ break;
+ }
+ count += new_bufs;
+ } while (count < FSL_DPAA_ETH_MAX_BUF_COUNT);
+
+ *countptr = count;
+ if (unlikely(count < FSL_DPAA_ETH_MAX_BUF_COUNT))
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static int dpaa_eth_refill_bpools(struct dpaa_priv *priv)
+{
+ struct dpaa_bp *dpaa_bp;
+ int *countptr;
+ int res, i;
+
+ for (i = 0; i < DPAA_BPS_NUM; i++) {
+ dpaa_bp = priv->dpaa_bps[i];
+ if (!dpaa_bp)
+ return -EINVAL;
+ countptr = this_cpu_ptr(dpaa_bp->percpu_count);
+ res = dpaa_eth_refill_bpool(dpaa_bp, countptr);
+ if (res)
+ return res;
+ }
+ return 0;
+}
+
+/* Cleanup function for outgoing frame descriptors that were built on Tx path,
+ * either contiguous frames or scatter/gather ones.
+ * Skb freeing is not handled here.
+ *
+ * This function may be called on error paths in the Tx function, so guard
+ * against cases when not all fd relevant fields were filled in.
+ *
+ * Return the skb backpointer, since for S/G frames the buffer containing it
+ * gets freed here.
+ */
+static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
+ const struct qm_fd *fd)
+{
+ const enum dma_data_direction dma_dir = DMA_TO_DEVICE;
+ struct device *dev = priv->net_dev->dev.parent;
+ dma_addr_t addr = qm_fd_addr(fd);
+ const struct qm_sg_entry *sgt;
+ struct sk_buff **skbh, *skb;
+ int nr_frags, i;
+
+ skbh = (struct sk_buff **)phys_to_virt(addr);
+ skb = *skbh;
+
+ if (unlikely(qm_fd_get_format(fd) == qm_fd_sg)) {
+ nr_frags = skb_shinfo(skb)->nr_frags;
+ dma_unmap_single(dev, addr, qm_fd_get_offset(fd) +
+ sizeof(struct qm_sg_entry) * (1 + nr_frags),
+ dma_dir);
+
+ /* The sgt buffer has been allocated with netdev_alloc_frag(),
+ * it's from lowmem.
+ */
+ sgt = phys_to_virt(addr + qm_fd_get_offset(fd));
+
+ /* sgt[0] is from lowmem, was dma_map_single()-ed */
+ dma_unmap_single(dev, qm_sg_addr(&sgt[0]),
+ qm_sg_entry_get_len(&sgt[0]), dma_dir);
+
+ /* remaining pages were mapped with skb_frag_dma_map() */
+ for (i = 1; i < nr_frags; i++) {
+ WARN_ON(qm_sg_entry_is_ext(&sgt[i]));
+
+ dma_unmap_page(dev, qm_sg_addr(&sgt[i]),
+ qm_sg_entry_get_len(&sgt[i]), dma_dir);
+ }
+
+ /* Free the page frag that we allocated on Tx */
+ skb_free_frag(phys_to_virt(addr));
+ } else {
+ dma_unmap_single(dev, addr,
+ skb_tail_pointer(skb) - (u8 *)skbh, dma_dir);
+ }
+
+ return skb;
+}
+
+/* Build a linear skb around the received buffer.
+ * We are guaranteed there is enough room at the end of the data buffer to
+ * accommodate the shared info area of the skb.
+ */
+static struct sk_buff *contig_fd_to_skb(const struct dpaa_priv *priv,
+ const struct qm_fd *fd)
+{
+ ssize_t fd_off = qm_fd_get_offset(fd);
+ dma_addr_t addr = qm_fd_addr(fd);
+ struct dpaa_bp *dpaa_bp;
+ struct sk_buff *skb;
+ void *vaddr;
+
+ vaddr = phys_to_virt(addr);
+ WARN_ON(!IS_ALIGNED((unsigned long)vaddr, SMP_CACHE_BYTES));
+
+ dpaa_bp = dpaa_bpid2pool(fd->bpid);
+ if (!dpaa_bp)
+ goto free_buffer;
+
+ skb = build_skb(vaddr, dpaa_bp->size +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
+ if (unlikely(!skb)) {
+ WARN_ONCE(1, "Build skb failure on Rx\n");
+ goto free_buffer;
+ }
+ WARN_ON(fd_off != priv->rx_headroom);
+ skb_reserve(skb, fd_off);
+ skb_put(skb, qm_fd_get_length(fd));
+
+ skb->ip_summed = CHECKSUM_NONE;
+
+ return skb;
+
+free_buffer:
+ skb_free_frag(vaddr);
+ return NULL;
+}
+
+/* Build an skb with the data of the first S/G entry in the linear portion and
+ * the rest of the frame as skb fragments.
+ *
+ * The page fragment holding the S/G Table is recycled here.
+ */
+static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv,
+ const struct qm_fd *fd)
+{
+ ssize_t fd_off = qm_fd_get_offset(fd);
+ dma_addr_t addr = qm_fd_addr(fd);
+ const struct qm_sg_entry *sgt;
+ struct page *page, *head_page;
+ struct dpaa_bp *dpaa_bp;
+ void *vaddr, *sg_vaddr;
+ int frag_off, frag_len;
+ struct sk_buff *skb;
+ dma_addr_t sg_addr;
+ int page_offset;
+ unsigned int sz;
+ int *count_ptr;
+ int i;
+
+ vaddr = phys_to_virt(addr);
+ WARN_ON(!IS_ALIGNED((unsigned long)vaddr, SMP_CACHE_BYTES));
+
+ /* Iterate through the SGT entries and add data buffers to the skb */
+ sgt = vaddr + fd_off;
+ for (i = 0; i < DPAA_SGT_MAX_ENTRIES; i++) {
+ /* Extension bit is not supported */
+ WARN_ON(qm_sg_entry_is_ext(&sgt[i]));
+
+ sg_addr = qm_sg_addr(&sgt[i]);
+ sg_vaddr = phys_to_virt(sg_addr);
+ WARN_ON(!IS_ALIGNED((unsigned long)sg_vaddr,
+ SMP_CACHE_BYTES));
+
+ /* We may use multiple Rx pools */
+ dpaa_bp = dpaa_bpid2pool(sgt[i].bpid);
+ if (!dpaa_bp)
+ goto free_buffers;
+
+ count_ptr = this_cpu_ptr(dpaa_bp->percpu_count);
+ dma_unmap_single(dpaa_bp->dev, sg_addr, dpaa_bp->size,
+ DMA_FROM_DEVICE);
+ if (i == 0) {
+ sz = dpaa_bp->size +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ skb = build_skb(sg_vaddr, sz);
+ if (WARN_ON(unlikely(!skb)))
+ goto free_buffers;
+
+ skb->ip_summed = CHECKSUM_NONE;
+
+ /* Make sure forwarded skbs will have enough space
+ * on Tx, if extra headers are added.
+ */
+ WARN_ON(fd_off != priv->rx_headroom);
+ skb_reserve(skb, fd_off);
+ skb_put(skb, qm_sg_entry_get_len(&sgt[i]));
+ } else {
+ /* Not the first S/G entry; all data from buffer will
+ * be added in an skb fragment; fragment index is offset
+ * by one since first S/G entry was incorporated in the
+ * linear part of the skb.
+ *
+ * Caution: 'page' may be a tail page.
+ */
+ page = virt_to_page(sg_vaddr);
+ head_page = virt_to_head_page(sg_vaddr);
+
+ /* Compute offset in (possibly tail) page */
+ page_offset = ((unsigned long)sg_vaddr &
+ (PAGE_SIZE - 1)) +
+ (page_address(page) - page_address(head_page));
+ /* page_offset only refers to the beginning of sgt[i];
+ * but the buffer itself may have an internal offset.
+ */
+ frag_off = qm_sg_entry_get_off(&sgt[i]) + page_offset;
+ frag_len = qm_sg_entry_get_len(&sgt[i]);
+ /* skb_add_rx_frag() does no checking on the page; if
+ * we pass it a tail page, we'll end up with
+ * bad page accounting and eventually with segafults.
+ */
+ skb_add_rx_frag(skb, i - 1, head_page, frag_off,
+ frag_len, dpaa_bp->size);
+ }
+ /* Update the pool count for the current {cpu x bpool} */
+ (*count_ptr)--;
+
+ if (qm_sg_entry_is_final(&sgt[i]))
+ break;
+ }
+ WARN_ONCE(i == DPAA_SGT_MAX_ENTRIES, "No final bit on SGT\n");
+
+ /* free the SG table buffer */
+ skb_free_frag(vaddr);
+
+ return skb;
+
+free_buffers:
+ /* compensate sw bpool counter changes */
+ for (i--; i > 0; i--) {
+ dpaa_bp = dpaa_bpid2pool(sgt[i].bpid);
+ if (dpaa_bp) {
+ count_ptr = this_cpu_ptr(dpaa_bp->percpu_count);
+ (*count_ptr)++;
+ }
+ }
+ /* free all the SG entries */
+ for (i = 0; i < DPAA_SGT_MAX_ENTRIES ; i++) {
+ sg_addr = qm_sg_addr(&sgt[i]);
+ sg_vaddr = phys_to_virt(sg_addr);
+ skb_free_frag(sg_vaddr);
+ dpaa_bp = dpaa_bpid2pool(sgt[i].bpid);
+ if (dpaa_bp) {
+ count_ptr = this_cpu_ptr(dpaa_bp->percpu_count);
+ (*count_ptr)--;
+ }
+
+ if (qm_sg_entry_is_final(&sgt[i]))
+ break;
+ }
+ /* free the SGT fragment */
+ skb_free_frag(vaddr);
+
+ return NULL;
+}
+
+static int skb_to_contig_fd(struct dpaa_priv *priv,
+ struct sk_buff *skb, struct qm_fd *fd,
+ int *offset)
+{
+ struct net_device *net_dev = priv->net_dev;
+ struct device *dev = net_dev->dev.parent;
+ enum dma_data_direction dma_dir;
+ unsigned char *buffer_start;
+ struct sk_buff **skbh;
+ dma_addr_t addr;
+ int err;
+
+ /* We are guaranteed to have at least tx_headroom bytes
+ * available, so just use that for offset.
+ */
+ fd->bpid = FSL_DPAA_BPID_INV;
+ buffer_start = skb->data - priv->tx_headroom;
+ dma_dir = DMA_TO_DEVICE;
+
+ skbh = (struct sk_buff **)buffer_start;
+ *skbh = skb;
+
+ /* Enable L3/L4 hardware checksum computation.
+ *
+ * We must do this before dma_map_single(DMA_TO_DEVICE), because we may
+ * need to write into the skb.
+ */
+ err = dpaa_enable_tx_csum(priv, skb, fd,
+ ((char *)skbh) + DPAA_TX_PRIV_DATA_SIZE);
+ if (unlikely(err < 0)) {
+ if (net_ratelimit())
+ netif_err(priv, tx_err, net_dev, "HW csum error: %d\n",
+ err);
+ return err;
+ }
+
+ /* Fill in the rest of the FD fields */
+ qm_fd_set_contig(fd, priv->tx_headroom, skb->len);
+ fd->cmd |= FM_FD_CMD_FCO;
+
+ /* Map the entire buffer size that may be seen by FMan, but no more */
+ addr = dma_map_single(dev, skbh,
+ skb_tail_pointer(skb) - buffer_start, dma_dir);
+ if (unlikely(dma_mapping_error(dev, addr))) {
+ if (net_ratelimit())
+ netif_err(priv, tx_err, net_dev, "dma_map_single() failed\n");
+ return -EINVAL;
+ }
+ qm_fd_addr_set64(fd, addr);
+
+ return 0;
+}
+
+static int skb_to_sg_fd(struct dpaa_priv *priv,
+ struct sk_buff *skb, struct qm_fd *fd)
+{
+ const enum dma_data_direction dma_dir = DMA_TO_DEVICE;
+ const int nr_frags = skb_shinfo(skb)->nr_frags;
+ struct net_device *net_dev = priv->net_dev;
+ struct device *dev = net_dev->dev.parent;
+ struct qm_sg_entry *sgt;
+ struct sk_buff **skbh;
+ int i, j, err, sz;
+ void *buffer_start;
+ skb_frag_t *frag;
+ dma_addr_t addr;
+ size_t frag_len;
+ void *sgt_buf;
+
+ /* get a page frag to store the SGTable */
+ sz = SKB_DATA_ALIGN(priv->tx_headroom +
+ sizeof(struct qm_sg_entry) * (1 + nr_frags));
+ sgt_buf = netdev_alloc_frag(sz);
+ if (unlikely(!sgt_buf)) {
+ netdev_err(net_dev, "netdev_alloc_frag() failed for size %d\n",
+ sz);
+ return -ENOMEM;
+ }
+
+ /* Enable L3/L4 hardware checksum computation.
+ *
+ * We must do this before dma_map_single(DMA_TO_DEVICE), because we may
+ * need to write into the skb.
+ */
+ err = dpaa_enable_tx_csum(priv, skb, fd,
+ sgt_buf + DPAA_TX_PRIV_DATA_SIZE);
+ if (unlikely(err < 0)) {
+ if (net_ratelimit())
+ netif_err(priv, tx_err, net_dev, "HW csum error: %d\n",
+ err);
+ goto csum_failed;
+ }
+
+ sgt = (struct qm_sg_entry *)(sgt_buf + priv->tx_headroom);
+ qm_sg_entry_set_len(&sgt[0], skb_headlen(skb));
+ sgt[0].bpid = FSL_DPAA_BPID_INV;
+ sgt[0].offset = 0;
+ addr = dma_map_single(dev, skb->data,
+ skb_headlen(skb), dma_dir);
+ if (unlikely(dma_mapping_error(dev, addr))) {
+ dev_err(dev, "DMA mapping failed");
+ err = -EINVAL;
+ goto sg0_map_failed;
+ }
+ qm_sg_entry_set64(&sgt[0], addr);
+
+ /* populate the rest of SGT entries */
+ frag = &skb_shinfo(skb)->frags[0];
+ frag_len = frag->size;
+ for (i = 1; i <= nr_frags; i++, frag++) {
+ WARN_ON(!skb_frag_page(frag));
+ addr = skb_frag_dma_map(dev, frag, 0,
+ frag_len, dma_dir);
+ if (unlikely(dma_mapping_error(dev, addr))) {
+ dev_err(dev, "DMA mapping failed");
+ err = -EINVAL;
+ goto sg_map_failed;
+ }
+
+ qm_sg_entry_set_len(&sgt[i], frag_len);
+ sgt[i].bpid = FSL_DPAA_BPID_INV;
+ sgt[i].offset = 0;
+
+ /* keep the offset in the address */
+ qm_sg_entry_set64(&sgt[i], addr);
+ frag_len = frag->size;
+ }
+ qm_sg_entry_set_f(&sgt[i - 1], frag_len);
+
+ qm_fd_set_sg(fd, priv->tx_headroom, skb->len);
+
+ /* DMA map the SGT page */
+ buffer_start = (void *)sgt - priv->tx_headroom;
+ skbh = (struct sk_buff **)buffer_start;
+ *skbh = skb;
+
+ addr = dma_map_single(dev, buffer_start, priv->tx_headroom +
+ sizeof(struct qm_sg_entry) * (1 + nr_frags),
+ dma_dir);
+ if (unlikely(dma_mapping_error(dev, addr))) {
+ dev_err(dev, "DMA mapping failed");
+ err = -EINVAL;
+ goto sgt_map_failed;
+ }
+
+ fd->bpid = FSL_DPAA_BPID_INV;
+ fd->cmd |= FM_FD_CMD_FCO;
+ qm_fd_addr_set64(fd, addr);
+
+ return 0;
+
+sgt_map_failed:
+sg_map_failed:
+ for (j = 0; j < i; j++)
+ dma_unmap_page(dev, qm_sg_addr(&sgt[j]),
+ qm_sg_entry_get_len(&sgt[j]), dma_dir);
+sg0_map_failed:
+csum_failed:
+ skb_free_frag(sgt_buf);
+
+ return err;
+}
+
+static inline int dpaa_xmit(struct dpaa_priv *priv,
+ struct rtnl_link_stats64 *percpu_stats,
+ int queue,
+ struct qm_fd *fd)
+{
+ struct qman_fq *egress_fq;
+ int err, i;
+
+ egress_fq = priv->egress_fqs[queue];
+ if (fd->bpid == FSL_DPAA_BPID_INV)
+ fd->cmd |= qman_fq_fqid(priv->conf_fqs[queue]);
+
+ /* Trace this Tx fd */
+ trace_dpaa_tx_fd(priv->net_dev, egress_fq, fd);
+
+ for (i = 0; i < DPAA_ENQUEUE_RETRIES; i++) {
+ err = qman_enqueue(egress_fq, fd);
+ if (err != -EBUSY)
+ break;
+ }
+
+ if (unlikely(err < 0)) {
+ percpu_stats->tx_errors++;
+ percpu_stats->tx_fifo_errors++;
+ return err;
+ }
+
+ percpu_stats->tx_packets++;
+ percpu_stats->tx_bytes += qm_fd_get_length(fd);
+
+ return 0;
+}
+
+static int dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
+{
+ const int queue_mapping = skb_get_queue_mapping(skb);
+ bool nonlinear = skb_is_nonlinear(skb);
+ struct rtnl_link_stats64 *percpu_stats;
+ struct dpaa_percpu_priv *percpu_priv;
+ struct dpaa_priv *priv;
+ struct qm_fd fd;
+ int offset = 0;
+ int err = 0;
+
+ priv = netdev_priv(net_dev);
+ percpu_priv = this_cpu_ptr(priv->percpu_priv);
+ percpu_stats = &percpu_priv->stats;
+
+ qm_fd_clear_fd(&fd);
+
+ if (!nonlinear) {
+ /* We're going to store the skb backpointer at the beginning
+ * of the data buffer, so we need a privately owned skb
+ *
+ * We've made sure skb is not shared in dev->priv_flags,
+ * we need to verify the skb head is not cloned
+ */
+ if (skb_cow_head(skb, priv->tx_headroom))
+ goto enomem;
+
+ WARN_ON(skb_is_nonlinear(skb));
+ }
+
+ /* MAX_SKB_FRAGS is equal or larger than our dpaa_SGT_MAX_ENTRIES;
+ * make sure we don't feed FMan with more fragments than it supports.
+ */
+ if (nonlinear &&
+ likely(skb_shinfo(skb)->nr_frags < DPAA_SGT_MAX_ENTRIES)) {
+ /* Just create a S/G fd based on the skb */
+ err = skb_to_sg_fd(priv, skb, &fd);
+ percpu_priv->tx_frag_skbuffs++;
+ } else {
+ /* If the egress skb contains more fragments than we support
+ * we have no choice but to linearize it ourselves.
+ */
+ if (unlikely(nonlinear) && __skb_linearize(skb))
+ goto enomem;
+
+ /* Finally, create a contig FD from this skb */
+ err = skb_to_contig_fd(priv, skb, &fd, &offset);
+ }
+ if (unlikely(err < 0))
+ goto skb_to_fd_failed;
+
+ if (likely(dpaa_xmit(priv, percpu_stats, queue_mapping, &fd) == 0))
+ return NETDEV_TX_OK;
+
+ dpaa_cleanup_tx_fd(priv, &fd);
+skb_to_fd_failed:
+enomem:
+ percpu_stats->tx_errors++;
+ dev_kfree_skb(skb);
+ return NETDEV_TX_OK;
+}
+
+static void dpaa_rx_error(struct net_device *net_dev,
+ const struct dpaa_priv *priv,
+ struct dpaa_percpu_priv *percpu_priv,
+ const struct qm_fd *fd,
+ u32 fqid)
+{
+ if (net_ratelimit())
+ netif_err(priv, hw, net_dev, "Err FD status = 0x%08x\n",
+ fd->status & FM_FD_STAT_RX_ERRORS);
+
+ percpu_priv->stats.rx_errors++;
+
+ if (fd->status & FM_FD_ERR_DMA)
+ percpu_priv->rx_errors.dme++;
+ if (fd->status & FM_FD_ERR_PHYSICAL)
+ percpu_priv->rx_errors.fpe++;
+ if (fd->status & FM_FD_ERR_SIZE)
+ percpu_priv->rx_errors.fse++;
+ if (fd->status & FM_FD_ERR_PRS_HDR_ERR)
+ percpu_priv->rx_errors.phe++;
+
+ dpaa_fd_release(net_dev, fd);
+}
+
+static void dpaa_tx_error(struct net_device *net_dev,
+ const struct dpaa_priv *priv,
+ struct dpaa_percpu_priv *percpu_priv,
+ const struct qm_fd *fd,
+ u32 fqid)
+{
+ struct sk_buff *skb;
+
+ if (net_ratelimit())
+ netif_warn(priv, hw, net_dev, "FD status = 0x%08x\n",
+ fd->status & FM_FD_STAT_TX_ERRORS);
+
+ percpu_priv->stats.tx_errors++;
+
+ skb = dpaa_cleanup_tx_fd(priv, fd);
+ dev_kfree_skb(skb);
+}
+
+static int dpaa_eth_poll(struct napi_struct *napi, int budget)
+{
+ struct dpaa_napi_portal *np =
+ container_of(napi, struct dpaa_napi_portal, napi);
+
+ int cleaned = qman_p_poll_dqrr(np->p, budget);
+
+ if (cleaned < budget) {
+ napi_complete(napi);
+ qman_p_irqsource_add(np->p, QM_PIRQ_DQRI);
+
+ } else if (np->down) {
+ qman_p_irqsource_add(np->p, QM_PIRQ_DQRI);
+ }
+
+ return cleaned;
+}
+
+static void dpaa_tx_conf(struct net_device *net_dev,
+ const struct dpaa_priv *priv,
+ struct dpaa_percpu_priv *percpu_priv,
+ const struct qm_fd *fd,
+ u32 fqid)
+{
+ struct sk_buff *skb;
+
+ if (unlikely(fd->status & FM_FD_STAT_TX_ERRORS) != 0) {
+ if (net_ratelimit())
+ netif_warn(priv, hw, net_dev, "FD status = 0x%08x\n",
+ fd->status & FM_FD_STAT_TX_ERRORS);
+
+ percpu_priv->stats.tx_errors++;
+ }
+
+ percpu_priv->tx_confirm++;
+
+ skb = dpaa_cleanup_tx_fd(priv, fd);
+
+ consume_skb(skb);
+}
+
+static inline int dpaa_eth_napi_schedule(struct dpaa_percpu_priv *percpu_priv,
+ struct qman_portal *portal)
+{
+ if (unlikely(in_irq() || !in_serving_softirq())) {
+ /* Disable QMan IRQ and invoke NAPI */
+ qman_p_irqsource_remove(portal, QM_PIRQ_DQRI);
+
+ percpu_priv->np.p = portal;
+ napi_schedule(&percpu_priv->np.napi);
+ percpu_priv->in_interrupt++;
+ return 1;
+ }
+ return 0;
+}
+
+static enum qman_cb_dqrr_result rx_error_dqrr(struct qman_portal *portal,
+ struct qman_fq *fq,
+ const struct qm_dqrr_entry *dq)
+{
+ struct dpaa_fq *dpaa_fq = container_of(fq, struct dpaa_fq, fq_base);
+ struct dpaa_percpu_priv *percpu_priv;
+ struct net_device *net_dev;
+ struct dpaa_bp *dpaa_bp;
+ struct dpaa_priv *priv;
+
+ net_dev = dpaa_fq->net_dev;
+ priv = netdev_priv(net_dev);
+ dpaa_bp = dpaa_bpid2pool(dq->fd.bpid);
+ if (!dpaa_bp)
+ return qman_cb_dqrr_consume;
+
+ percpu_priv = this_cpu_ptr(priv->percpu_priv);
+
+ if (dpaa_eth_napi_schedule(percpu_priv, portal))
+ return qman_cb_dqrr_stop;
+
+ if (dpaa_eth_refill_bpools(priv))
+ /* Unable to refill the buffer pool due to insufficient
+ * system memory. Just release the frame back into the pool,
+ * otherwise we'll soon end up with an empty buffer pool.
+ */
+ dpaa_fd_release(net_dev, &dq->fd);
+ else
+ dpaa_rx_error(net_dev, priv, percpu_priv, &dq->fd, fq->fqid);
+
+ return qman_cb_dqrr_consume;
+}
+
+static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal,
+ struct qman_fq *fq,
+ const struct qm_dqrr_entry *dq)
+{
+ struct rtnl_link_stats64 *percpu_stats;
+ struct dpaa_percpu_priv *percpu_priv;
+ const struct qm_fd *fd = &dq->fd;
+ dma_addr_t addr = qm_fd_addr(fd);
+ enum qm_fd_format fd_format;
+ struct net_device *net_dev;
+ u32 fd_status = fd->status;
+ struct dpaa_bp *dpaa_bp;
+ struct dpaa_priv *priv;
+ unsigned int skb_len;
+ struct sk_buff *skb;
+ int *count_ptr;
+
+ net_dev = ((struct dpaa_fq *)fq)->net_dev;
+ priv = netdev_priv(net_dev);
+ dpaa_bp = dpaa_bpid2pool(dq->fd.bpid);
+ if (!dpaa_bp)
+ return qman_cb_dqrr_consume;
+
+ /* Trace the Rx fd */
+ trace_dpaa_rx_fd(net_dev, fq, &dq->fd);
+
+ percpu_priv = this_cpu_ptr(priv->percpu_priv);
+ percpu_stats = &percpu_priv->stats;
+
+ if (unlikely(dpaa_eth_napi_schedule(percpu_priv, portal)))
+ return qman_cb_dqrr_stop;
+
+ /* Make sure we didn't run out of buffers */
+ if (unlikely(dpaa_eth_refill_bpools(priv))) {
+ /* Unable to refill the buffer pool due to insufficient
+ * system memory. Just release the frame back into the pool,
+ * otherwise we'll soon end up with an empty buffer pool.
+ */
+ dpaa_fd_release(net_dev, &dq->fd);
+ return qman_cb_dqrr_consume;
+ }
+
+ if (unlikely(fd_status & FM_FD_STAT_RX_ERRORS) != 0) {
+ if (net_ratelimit())
+ netif_warn(priv, hw, net_dev, "FD status = 0x%08x\n",
+ fd_status & FM_FD_STAT_RX_ERRORS);
+
+ percpu_stats->rx_errors++;
+ dpaa_fd_release(net_dev, fd);
+ return qman_cb_dqrr_consume;
+ }
+
+ dpaa_bp = dpaa_bpid2pool(fd->bpid);
+ if (!dpaa_bp)
+ return qman_cb_dqrr_consume;
+
+ dma_unmap_single(dpaa_bp->dev, addr, dpaa_bp->size, DMA_FROM_DEVICE);
+
+ /* prefetch the first 64 bytes of the frame or the SGT start */
+ prefetch(phys_to_virt(addr) + qm_fd_get_offset(fd));
+
+ fd_format = qm_fd_get_format(fd);
+ /* The only FD types that we may receive are contig and S/G */
+ WARN_ON((fd_format != qm_fd_contig) && (fd_format != qm_fd_sg));
+
+ /* Account for either the contig buffer or the SGT buffer (depending on
+ * which case we were in) having been removed from the pool.
+ */
+ count_ptr = this_cpu_ptr(dpaa_bp->percpu_count);
+ (*count_ptr)--;
+
+ if (likely(fd_format == qm_fd_contig))
+ skb = contig_fd_to_skb(priv, fd);
+ else
+ skb = sg_fd_to_skb(priv, fd);
+ if (!skb)
+ return qman_cb_dqrr_consume;
+
+ skb->protocol = eth_type_trans(skb, net_dev);
+
+ skb_len = skb->len;
+
+ if (unlikely(netif_receive_skb(skb) == NET_RX_DROP))
+ return qman_cb_dqrr_consume;
+
+ percpu_stats->rx_packets++;
+ percpu_stats->rx_bytes += skb_len;
+
+ return qman_cb_dqrr_consume;
+}
+
+static enum qman_cb_dqrr_result conf_error_dqrr(struct qman_portal *portal,
+ struct qman_fq *fq,
+ const struct qm_dqrr_entry *dq)
+{
+ struct dpaa_percpu_priv *percpu_priv;
+ struct net_device *net_dev;
+ struct dpaa_priv *priv;
+
+ net_dev = ((struct dpaa_fq *)fq)->net_dev;
+ priv = netdev_priv(net_dev);
+
+ percpu_priv = this_cpu_ptr(priv->percpu_priv);
+
+ if (dpaa_eth_napi_schedule(percpu_priv, portal))
+ return qman_cb_dqrr_stop;
+
+ dpaa_tx_error(net_dev, priv, percpu_priv, &dq->fd, fq->fqid);
+
+ return qman_cb_dqrr_consume;
+}
+
+static enum qman_cb_dqrr_result conf_dflt_dqrr(struct qman_portal *portal,
+ struct qman_fq *fq,
+ const struct qm_dqrr_entry *dq)
+{
+ struct dpaa_percpu_priv *percpu_priv;
+ struct net_device *net_dev;
+ struct dpaa_priv *priv;
+
+ net_dev = ((struct dpaa_fq *)fq)->net_dev;
+ priv = netdev_priv(net_dev);
+
+ /* Trace the fd */
+ trace_dpaa_tx_conf_fd(net_dev, fq, &dq->fd);
+
+ percpu_priv = this_cpu_ptr(priv->percpu_priv);
+
+ if (dpaa_eth_napi_schedule(percpu_priv, portal))
+ return qman_cb_dqrr_stop;
+
+ dpaa_tx_conf(net_dev, priv, percpu_priv, &dq->fd, fq->fqid);
+
+ return qman_cb_dqrr_consume;
+}
+
+static void egress_ern(struct qman_portal *portal,
+ struct qman_fq *fq,
+ const union qm_mr_entry *msg)
+{
+ const struct qm_fd *fd = &msg->ern.fd;
+ struct dpaa_percpu_priv *percpu_priv;
+ const struct dpaa_priv *priv;
+ struct net_device *net_dev;
+ struct sk_buff *skb;
+
+ net_dev = ((struct dpaa_fq *)fq)->net_dev;
+ priv = netdev_priv(net_dev);
+ percpu_priv = this_cpu_ptr(priv->percpu_priv);
+
+ percpu_priv->stats.tx_dropped++;
+ percpu_priv->stats.tx_fifo_errors++;
+ count_ern(percpu_priv, msg);
+
+ skb = dpaa_cleanup_tx_fd(priv, fd);
+ dev_kfree_skb_any(skb);
+}
+
+static const struct dpaa_fq_cbs dpaa_fq_cbs = {
+ .rx_defq = { .cb = { .dqrr = rx_default_dqrr } },
+ .tx_defq = { .cb = { .dqrr = conf_dflt_dqrr } },
+ .rx_errq = { .cb = { .dqrr = rx_error_dqrr } },
+ .tx_errq = { .cb = { .dqrr = conf_error_dqrr } },
+ .egress_ern = { .cb = { .ern = egress_ern } }
+};
+
+static void dpaa_eth_napi_enable(struct dpaa_priv *priv)
+{
+ struct dpaa_percpu_priv *percpu_priv;
+ int i;
+
+ for_each_possible_cpu(i) {
+ percpu_priv = per_cpu_ptr(priv->percpu_priv, i);
+
+ percpu_priv->np.down = 0;
+ napi_enable(&percpu_priv->np.napi);
+ }
+}
+
+static void dpaa_eth_napi_disable(struct dpaa_priv *priv)
+{
+ struct dpaa_percpu_priv *percpu_priv;
+ int i;
+
+ for_each_possible_cpu(i) {
+ percpu_priv = per_cpu_ptr(priv->percpu_priv, i);
+
+ percpu_priv->np.down = 1;
+ napi_disable(&percpu_priv->np.napi);
+ }
+}
+
+static int dpaa_open(struct net_device *net_dev)
+{
+ struct mac_device *mac_dev;
+ struct dpaa_priv *priv;
+ int err, i;
+
+ priv = netdev_priv(net_dev);
+ mac_dev = priv->mac_dev;
+ dpaa_eth_napi_enable(priv);
+
+ net_dev->phydev = mac_dev->init_phy(net_dev, priv->mac_dev);
+ if (!net_dev->phydev) {
+ netif_err(priv, ifup, net_dev, "init_phy() failed\n");
+ return -ENODEV;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) {
+ err = fman_port_enable(mac_dev->port[i]);
+ if (err)
+ goto mac_start_failed;
+ }
+
+ err = priv->mac_dev->start(mac_dev);
+ if (err < 0) {
+ netif_err(priv, ifup, net_dev, "mac_dev->start() = %d\n", err);
+ goto mac_start_failed;
+ }
+
+ netif_tx_start_all_queues(net_dev);
+
+ return 0;
+
+mac_start_failed:
+ for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++)
+ fman_port_disable(mac_dev->port[i]);
+
+ dpaa_eth_napi_disable(priv);
+
+ return err;
+}
+
+static int dpaa_eth_stop(struct net_device *net_dev)
+{
+ struct dpaa_priv *priv;
+ int err;
+
+ err = dpaa_stop(net_dev);
+
+ priv = netdev_priv(net_dev);
+ dpaa_eth_napi_disable(priv);
+
+ return err;
+}
+
+static const struct net_device_ops dpaa_ops = {
+ .ndo_open = dpaa_open,
+ .ndo_start_xmit = dpaa_start_xmit,
+ .ndo_stop = dpaa_eth_stop,
+ .ndo_tx_timeout = dpaa_tx_timeout,
+ .ndo_get_stats64 = dpaa_get_stats64,
+ .ndo_set_mac_address = dpaa_set_mac_address,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_set_rx_mode = dpaa_set_rx_mode,
+};
+
+static int dpaa_napi_add(struct net_device *net_dev)
+{
+ struct dpaa_priv *priv = netdev_priv(net_dev);
+ struct dpaa_percpu_priv *percpu_priv;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ percpu_priv = per_cpu_ptr(priv->percpu_priv, cpu);
+
+ netif_napi_add(net_dev, &percpu_priv->np.napi,
+ dpaa_eth_poll, NAPI_POLL_WEIGHT);
+ }
+
+ return 0;
+}
+
+static void dpaa_napi_del(struct net_device *net_dev)
+{
+ struct dpaa_priv *priv = netdev_priv(net_dev);
+ struct dpaa_percpu_priv *percpu_priv;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ percpu_priv = per_cpu_ptr(priv->percpu_priv, cpu);
+
+ netif_napi_del(&percpu_priv->np.napi);
+ }
+}
+
+static inline void dpaa_bp_free_pf(const struct dpaa_bp *bp,
+ struct bm_buffer *bmb)
+{
+ dma_addr_t addr = bm_buf_addr(bmb);
+
+ dma_unmap_single(bp->dev, addr, bp->size, DMA_FROM_DEVICE);
+
+ skb_free_frag(phys_to_virt(addr));
+}
+
+/* Alloc the dpaa_bp struct and configure default values */
+static struct dpaa_bp *dpaa_bp_alloc(struct device *dev)
+{
+ struct dpaa_bp *dpaa_bp;
+
+ dpaa_bp = devm_kzalloc(dev, sizeof(*dpaa_bp), GFP_KERNEL);
+ if (!dpaa_bp)
+ return ERR_PTR(-ENOMEM);
+
+ dpaa_bp->bpid = FSL_DPAA_BPID_INV;
+ dpaa_bp->percpu_count = devm_alloc_percpu(dev, *dpaa_bp->percpu_count);
+ dpaa_bp->config_count = FSL_DPAA_ETH_MAX_BUF_COUNT;
+
+ dpaa_bp->seed_cb = dpaa_bp_seed;
+ dpaa_bp->free_buf_cb = dpaa_bp_free_pf;
+
+ return dpaa_bp;
+}
+
+/* Place all ingress FQs (Rx Default, Rx Error) in a dedicated CGR.
+ * We won't be sending congestion notifications to FMan; for now, we just use
+ * this CGR to generate enqueue rejections to FMan in order to drop the frames
+ * before they reach our ingress queues and eat up memory.
+ */
+static int dpaa_ingress_cgr_init(struct dpaa_priv *priv)
+{
+ struct qm_mcc_initcgr initcgr;
+ u32 cs_th;
+ int err;
+
+ err = qman_alloc_cgrid(&priv->ingress_cgr.cgrid);
+ if (err < 0) {
+ if (netif_msg_drv(priv))
+ pr_err("Error %d allocating CGR ID\n", err);
+ goto out_error;
+ }
+
+ /* Enable CS TD, but disable Congestion State Change Notifications. */
+ initcgr.we_mask = QM_CGR_WE_CS_THRES;
+ initcgr.cgr.cscn_en = QM_CGR_EN;
+ cs_th = DPAA_INGRESS_CS_THRESHOLD;
+ qm_cgr_cs_thres_set64(&initcgr.cgr.cs_thres, cs_th, 1);
+
+ initcgr.we_mask |= QM_CGR_WE_CSTD_EN;
+ initcgr.cgr.cstd_en = QM_CGR_EN;
+
+ /* This CGR will be associated with the SWP affined to the current CPU.
+ * However, we'll place all our ingress FQs in it.
+ */
+ err = qman_create_cgr(&priv->ingress_cgr, QMAN_CGR_FLAG_USE_INIT,
+ &initcgr);
+ if (err < 0) {
+ if (netif_msg_drv(priv))
+ pr_err("Error %d creating ingress CGR with ID %d\n",
+ err, priv->ingress_cgr.cgrid);
+ qman_release_cgrid(priv->ingress_cgr.cgrid);
+ goto out_error;
+ }
+ if (netif_msg_drv(priv))
+ pr_debug("Created ingress CGR %d for netdev with hwaddr %pM\n",
+ priv->ingress_cgr.cgrid, priv->mac_dev->addr);
+
+ priv->use_ingress_cgr = true;
+
+out_error:
+ return err;
+}
+
+static const struct of_device_id dpaa_match[];
+
+static inline u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl)
+{
+ u16 headroom;
+
+ /* The frame headroom must accommodate:
+ * - the driver private data area
+ * - parse results, hash results, timestamp if selected
+ * If either hash results or time stamp are selected, both will
+ * be copied to/from the frame headroom, as TS is located between PR and
+ * HR in the IC and IC copy size has a granularity of 16bytes
+ * (see description of FMBM_RICP and FMBM_TICP registers in DPAARM)
+ *
+ * Also make sure the headroom is a multiple of data_align bytes
+ */
+ headroom = (u16)(bl->priv_data_size + DPAA_PARSE_RESULTS_SIZE +
+ DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE);
+
+ return DPAA_FD_DATA_ALIGNMENT ? ALIGN(headroom,
+ DPAA_FD_DATA_ALIGNMENT) :
+ headroom;
+}
+
+static int dpaa_eth_probe(struct platform_device *pdev)
+{
+ struct dpaa_bp *dpaa_bps[DPAA_BPS_NUM] = {NULL};
+ struct dpaa_percpu_priv *percpu_priv;
+ struct net_device *net_dev = NULL;
+ struct dpaa_fq *dpaa_fq, *tmp;
+ struct dpaa_priv *priv = NULL;
+ struct fm_port_fqs port_fqs;
+ struct mac_device *mac_dev;
+ int err = 0, i, channel;
+ struct device *dev;
+
+ dev = &pdev->dev;
+
+ /* Allocate this early, so we can store relevant information in
+ * the private area
+ */
+ net_dev = alloc_etherdev_mq(sizeof(*priv), DPAA_ETH_TXQ_NUM);
+ if (!net_dev) {
+ dev_err(dev, "alloc_etherdev_mq() failed\n");
+ goto alloc_etherdev_mq_failed;
+ }
+
+ /* Do this here, so we can be verbose early */
+ SET_NETDEV_DEV(net_dev, dev);
+ dev_set_drvdata(dev, net_dev);
+
+ priv = netdev_priv(net_dev);
+ priv->net_dev = net_dev;
+
+ priv->msg_enable = netif_msg_init(debug, DPAA_MSG_DEFAULT);
+
+ mac_dev = dpaa_mac_dev_get(pdev);
+ if (IS_ERR(mac_dev)) {
+ dev_err(dev, "dpaa_mac_dev_get() failed\n");
+ err = PTR_ERR(mac_dev);
+ goto mac_probe_failed;
+ }
+
+ /* If fsl_fm_max_frm is set to a higher value than the all-common 1500,
+ * we choose conservatively and let the user explicitly set a higher
+ * MTU via ifconfig. Otherwise, the user may end up with different MTUs
+ * in the same LAN.
+ * If on the other hand fsl_fm_max_frm has been chosen below 1500,
+ * start with the maximum allowed.
+ */
+ net_dev->mtu = min(dpaa_get_max_mtu(), ETH_DATA_LEN);
+
+ netdev_dbg(net_dev, "Setting initial MTU on net device: %d\n",
+ net_dev->mtu);
+
+ priv->buf_layout[RX].priv_data_size = DPAA_RX_PRIV_DATA_SIZE; /* Rx */
+ priv->buf_layout[TX].priv_data_size = DPAA_TX_PRIV_DATA_SIZE; /* Tx */
+
+ /* device used for DMA mapping */
+ arch_setup_dma_ops(dev, 0, 0, NULL, false);
+ err = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(40));
+ if (err) {
+ dev_err(dev, "dma_coerce_mask_and_coherent() failed\n");
+ goto dev_mask_failed;
+ }
+
+ /* bp init */
+ for (i = 0; i < DPAA_BPS_NUM; i++) {
+ int err;
+
+ dpaa_bps[i] = dpaa_bp_alloc(dev);
+ if (IS_ERR(dpaa_bps[i]))
+ return PTR_ERR(dpaa_bps[i]);
+ /* the raw size of the buffers used for reception */
+ dpaa_bps[i]->raw_size = bpool_buffer_raw_size(i, DPAA_BPS_NUM);
+ /* avoid runtime computations by keeping the usable size here */
+ dpaa_bps[i]->size = dpaa_bp_size(dpaa_bps[i]->raw_size);
+ dpaa_bps[i]->dev = dev;
+
+ err = dpaa_bp_alloc_pool(dpaa_bps[i]);
+ if (err < 0) {
+ dpaa_bps_free(priv);
+ priv->dpaa_bps[i] = NULL;
+ goto bp_create_failed;
+ }
+ priv->dpaa_bps[i] = dpaa_bps[i];
+ }
+
+ INIT_LIST_HEAD(&priv->dpaa_fq_list);
+
+ memset(&port_fqs, 0, sizeof(port_fqs));
+
+ err = dpaa_alloc_all_fqs(dev, &priv->dpaa_fq_list, &port_fqs);
+ if (err < 0) {
+ dev_err(dev, "dpaa_alloc_all_fqs() failed\n");
+ goto fq_probe_failed;
+ }
+
+ priv->mac_dev = mac_dev;
+
+ channel = dpaa_get_channel();
+ if (channel < 0) {
+ dev_err(dev, "dpaa_get_channel() failed\n");
+ err = channel;
+ goto get_channel_failed;
+ }
+
+ priv->channel = (u16)channel;
+
+ /* Start a thread that will walk the CPUs with affine portals
+ * and add this pool channel to each's dequeue mask.
+ */
+ dpaa_eth_add_channel(priv->channel);
+
+ dpaa_fq_setup(priv, &dpaa_fq_cbs, priv->mac_dev->port[TX]);
+
+ /* Create a congestion group for this netdev, with
+ * dynamically-allocated CGR ID.
+ * Must be executed after probing the MAC, but before
+ * assigning the egress FQs to the CGRs.
+ */
+ err = dpaa_eth_cgr_init(priv);
+ if (err < 0) {
+ dev_err(dev, "Error initializing CGR\n");
+ goto tx_cgr_init_failed;
+ }
+
+ err = dpaa_ingress_cgr_init(priv);
+ if (err < 0) {
+ dev_err(dev, "Error initializing ingress CGR\n");
+ goto rx_cgr_init_failed;
+ }
+
+ /* Add the FQs to the interface, and make them active */
+ list_for_each_entry_safe(dpaa_fq, tmp, &priv->dpaa_fq_list, list) {
+ err = dpaa_fq_init(dpaa_fq, false);
+ if (err < 0)
+ goto fq_alloc_failed;
+ }
+
+ priv->tx_headroom = dpaa_get_headroom(&priv->buf_layout[TX]);
+ priv->rx_headroom = dpaa_get_headroom(&priv->buf_layout[RX]);
+
+ /* All real interfaces need their ports initialized */
+ dpaa_eth_init_ports(mac_dev, dpaa_bps, DPAA_BPS_NUM, &port_fqs,
+ &priv->buf_layout[0], dev);
+
+ priv->percpu_priv = devm_alloc_percpu(dev, *priv->percpu_priv);
+ if (!priv->percpu_priv) {
+ dev_err(dev, "devm_alloc_percpu() failed\n");
+ err = -ENOMEM;
+ goto alloc_percpu_failed;
+ }
+ for_each_possible_cpu(i) {
+ percpu_priv = per_cpu_ptr(priv->percpu_priv, i);
+ memset(percpu_priv, 0, sizeof(*percpu_priv));
+ }
+
+ /* Initialize NAPI */
+ err = dpaa_napi_add(net_dev);
+ if (err < 0)
+ goto napi_add_failed;
+
+ err = dpaa_netdev_init(net_dev, &dpaa_ops, tx_timeout);
+ if (err < 0)
+ goto netdev_init_failed;
+
+ dpaa_eth_sysfs_init(&net_dev->dev);
+
+ netif_info(priv, probe, net_dev, "Probed interface %s\n",
+ net_dev->name);
+
+ return 0;
+
+netdev_init_failed:
+napi_add_failed:
+ dpaa_napi_del(net_dev);
+alloc_percpu_failed:
+ dpaa_fq_free(dev, &priv->dpaa_fq_list);
+fq_alloc_failed:
+ qman_delete_cgr_safe(&priv->ingress_cgr);
+ qman_release_cgrid(priv->ingress_cgr.cgrid);
+rx_cgr_init_failed:
+ qman_delete_cgr_safe(&priv->cgr_data.cgr);
+ qman_release_cgrid(priv->cgr_data.cgr.cgrid);
+tx_cgr_init_failed:
+get_channel_failed:
+ dpaa_bps_free(priv);
+bp_create_failed:
+fq_probe_failed:
+dev_mask_failed:
+mac_probe_failed:
+ dev_set_drvdata(dev, NULL);
+ free_netdev(net_dev);
+alloc_etherdev_mq_failed:
+ for (i = 0; i < DPAA_BPS_NUM && dpaa_bps[i]; i++) {
+ if (atomic_read(&dpaa_bps[i]->refs) == 0)
+ devm_kfree(dev, dpaa_bps[i]);
+ }
+ return err;
+}
+
+static int dpaa_remove(struct platform_device *pdev)
+{
+ struct net_device *net_dev;
+ struct dpaa_priv *priv;
+ struct device *dev;
+ int err;
+
+ dev = &pdev->dev;
+ net_dev = dev_get_drvdata(dev);
+
+ priv = netdev_priv(net_dev);
+
+ dpaa_eth_sysfs_remove(dev);
+
+ dev_set_drvdata(dev, NULL);
+ unregister_netdev(net_dev);
+
+ err = dpaa_fq_free(dev, &priv->dpaa_fq_list);
+
+ qman_delete_cgr_safe(&priv->ingress_cgr);
+ qman_release_cgrid(priv->ingress_cgr.cgrid);
+ qman_delete_cgr_safe(&priv->cgr_data.cgr);
+ qman_release_cgrid(priv->cgr_data.cgr.cgrid);
+
+ dpaa_napi_del(net_dev);
+
+ dpaa_bps_free(priv);
+
+ free_netdev(net_dev);
+
+ return err;
+}
+
+static struct platform_device_id dpaa_devtype[] = {
+ {
+ .name = "dpaa-ethernet",
+ .driver_data = 0,
+ }, {
+ }
+};
+MODULE_DEVICE_TABLE(platform, dpaa_devtype);
+
+static struct platform_driver dpaa_driver = {
+ .driver = {
+ .name = KBUILD_MODNAME,
+ },
+ .id_table = dpaa_devtype,
+ .probe = dpaa_eth_probe,
+ .remove = dpaa_remove
+};
+
+static int __init dpaa_load(void)
+{
+ int err;
+
+ pr_debug("FSL DPAA Ethernet driver\n");
+
+ /* initialize dpaa_eth mirror values */
+ dpaa_rx_extra_headroom = fman_get_rx_extra_headroom();
+ dpaa_max_frm = fman_get_max_frm();
+
+ err = platform_driver_register(&dpaa_driver);
+ if (err < 0)
+ pr_err("Error, platform_driver_register() = %d\n", err);
+
+ return err;
+}
+module_init(dpaa_load);
+
+static void __exit dpaa_unload(void)
+{
+ platform_driver_unregister(&dpaa_driver);
+
+ /* Only one channel is used and needs to be released after all
+ * interfaces are removed
+ */
+ dpaa_release_channel();
+}
+module_exit(dpaa_unload);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("FSL DPAA Ethernet driver");
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
new file mode 100644
index 0000000..1f9aebf
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
@@ -0,0 +1,185 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __DPAA_H
+#define __DPAA_H
+
+#include <linux/netdevice.h>
+#include <soc/fsl/qman.h>
+#include <soc/fsl/bman.h>
+
+#include "fman.h"
+#include "mac.h"
+#include "dpaa_eth_trace.h"
+
+#define DPAA_ETH_TXQ_NUM NR_CPUS
+
+#define DPAA_BPS_NUM 3 /* number of bpools per interface */
+
+/* More detailed FQ types - used for fine-grained WQ assignments */
+enum dpaa_fq_type {
+ FQ_TYPE_RX_DEFAULT = 1, /* Rx Default FQs */
+ FQ_TYPE_RX_ERROR, /* Rx Error FQs */
+ FQ_TYPE_TX, /* "Real" Tx FQs */
+ FQ_TYPE_TX_CONFIRM, /* Tx default Conf FQ (actually an Rx FQ) */
+ FQ_TYPE_TX_CONF_MQ, /* Tx conf FQs (one for each Tx FQ) */
+ FQ_TYPE_TX_ERROR, /* Tx Error FQs (these are actually Rx FQs) */
+};
+
+struct dpaa_fq {
+ struct qman_fq fq_base;
+ struct list_head list;
+ struct net_device *net_dev;
+ bool init;
+ u32 fqid;
+ u32 flags;
+ u16 channel;
+ u8 wq;
+ enum dpaa_fq_type fq_type;
+};
+
+struct dpaa_fq_cbs {
+ struct qman_fq rx_defq;
+ struct qman_fq tx_defq;
+ struct qman_fq rx_errq;
+ struct qman_fq tx_errq;
+ struct qman_fq egress_ern;
+};
+
+struct dpaa_bp {
+ /* device used in the DMA mapping operations */
+ struct device *dev;
+ /* current number of buffers in the buffer pool alloted to each CPU */
+ int __percpu *percpu_count;
+ /* all buffers allocated for this pool have this raw size */
+ size_t raw_size;
+ /* all buffers in this pool have this same usable size */
+ size_t size;
+ /* the buffer pools are initialized with config_count buffers for each
+ * CPU; at runtime the number of buffers per CPU is constantly brought
+ * back to this level
+ */
+ u16 config_count;
+ u8 bpid;
+ struct bman_pool *pool;
+ /* bpool can be seeded before use by this cb */
+ int (*seed_cb)(struct dpaa_bp *);
+ /* bpool can be emptied before freeing by this cb */
+ void (*free_buf_cb)(const struct dpaa_bp *, struct bm_buffer *);
+ atomic_t refs;
+};
+
+struct dpaa_rx_errors {
+ u64 dme; /* DMA Error */
+ u64 fpe; /* Frame Physical Error */
+ u64 fse; /* Frame Size Error */
+ u64 phe; /* Header Error */
+};
+
+/* Counters for QMan ERN frames - one counter per rejection code */
+struct dpaa_ern_cnt {
+ u64 cg_tdrop; /* Congestion group taildrop */
+ u64 wred; /* WRED congestion */
+ u64 err_cond; /* Error condition */
+ u64 early_window; /* Order restoration, frame too early */
+ u64 late_window; /* Order restoration, frame too late */
+ u64 fq_tdrop; /* FQ taildrop */
+ u64 fq_retired; /* FQ is retired */
+ u64 orp_zero; /* ORP disabled */
+};
+
+struct dpaa_napi_portal {
+ struct napi_struct napi;
+ struct qman_portal *p;
+ bool down;
+};
+
+struct dpaa_percpu_priv {
+ struct net_device *net_dev;
+ struct dpaa_napi_portal np;
+ u64 in_interrupt;
+ u64 tx_confirm;
+ /* fragmented (non-linear) skbuffs received from the stack */
+ u64 tx_frag_skbuffs;
+ struct rtnl_link_stats64 stats;
+ struct dpaa_rx_errors rx_errors;
+ struct dpaa_ern_cnt ern_cnt;
+};
+
+struct dpaa_buffer_layout {
+ u16 priv_data_size;
+};
+
+struct dpaa_priv {
+ struct dpaa_percpu_priv __percpu *percpu_priv;
+ struct dpaa_bp *dpaa_bps[DPAA_BPS_NUM];
+ /* Store here the needed Tx headroom for convenience and speed
+ * (even though it can be computed based on the fields of buf_layout)
+ */
+ u16 tx_headroom;
+ struct net_device *net_dev;
+ struct mac_device *mac_dev;
+ struct qman_fq *egress_fqs[DPAA_ETH_TXQ_NUM];
+ struct qman_fq *conf_fqs[DPAA_ETH_TXQ_NUM];
+
+ u16 channel;
+ struct list_head dpaa_fq_list;
+
+ u32 msg_enable; /* net_device message level */
+
+ struct {
+ /* All egress queues to a given net device belong to one
+ * (and the same) congestion group.
+ */
+ struct qman_cgr cgr;
+ /* If congested, when it began. Used for performance stats. */
+ u32 congestion_start_jiffies;
+ /* Number of jiffies the Tx port was congested. */
+ u32 congested_jiffies;
+ /* Counter for the number of times the CGR
+ * entered congestion state
+ */
+ u32 cgr_congested_count;
+ } cgr_data;
+ /* Use a per-port CGR for ingress traffic. */
+ bool use_ingress_cgr;
+ struct qman_cgr ingress_cgr;
+
+ struct dpaa_buffer_layout buf_layout[2];
+ u16 rx_headroom;
+};
+
+/* from dpaa_ethtool.c */
+extern const struct ethtool_ops dpaa_ethtool_ops;
+
+/* from dpaa_eth_sysfs.c */
+void dpaa_eth_sysfs_remove(struct device *dev);
+void dpaa_eth_sysfs_init(struct device *dev);
+#endif /* __DPAA_H */
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c
new file mode 100644
index 0000000..ec75d1c
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c
@@ -0,0 +1,165 @@
+/* Copyright 2008-2016 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/of_net.h>
+#include "dpaa_eth.h"
+#include "mac.h"
+
+static ssize_t dpaa_eth_show_addr(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dpaa_priv *priv = netdev_priv(to_net_dev(dev));
+ struct mac_device *mac_dev = priv->mac_dev;
+
+ if (mac_dev)
+ return sprintf(buf, "%llx",
+ (unsigned long long)mac_dev->res->start);
+ else
+ return sprintf(buf, "none");
+}
+
+static ssize_t dpaa_eth_show_fqids(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dpaa_priv *priv = netdev_priv(to_net_dev(dev));
+ struct dpaa_fq *prev = NULL;
+ char *prevstr = NULL;
+ struct dpaa_fq *tmp;
+ struct dpaa_fq *fq;
+ u32 first_fqid = 0;
+ u32 last_fqid = 0;
+ ssize_t bytes = 0;
+ char *str;
+ int i = 0;
+
+ list_for_each_entry_safe(fq, tmp, &priv->dpaa_fq_list, list) {
+ switch (fq->fq_type) {
+ case FQ_TYPE_RX_DEFAULT:
+ str = "Rx default";
+ break;
+ case FQ_TYPE_RX_ERROR:
+ str = "Rx error";
+ break;
+ case FQ_TYPE_TX_CONFIRM:
+ str = "Tx default confirmation";
+ break;
+ case FQ_TYPE_TX_CONF_MQ:
+ str = "Tx confirmation (mq)";
+ break;
+ case FQ_TYPE_TX_ERROR:
+ str = "Tx error";
+ break;
+ case FQ_TYPE_TX:
+ str = "Tx";
+ break;
+ default:
+ str = "Unknown";
+ }
+
+ if (prev && (abs(fq->fqid - prev->fqid) != 1 ||
+ str != prevstr)) {
+ if (last_fqid == first_fqid)
+ bytes += sprintf(buf + bytes,
+ "%s: %d\n", prevstr, prev->fqid);
+ else
+ bytes += sprintf(buf + bytes,
+ "%s: %d - %d\n", prevstr,
+ first_fqid, last_fqid);
+ }
+
+ if (prev && abs(fq->fqid - prev->fqid) == 1 &&
+ str == prevstr) {
+ last_fqid = fq->fqid;
+ } else {
+ first_fqid = fq->fqid;
+ last_fqid = fq->fqid;
+ }
+
+ prev = fq;
+ prevstr = str;
+ i++;
+ }
+
+ if (prev) {
+ if (last_fqid == first_fqid)
+ bytes += sprintf(buf + bytes, "%s: %d\n", prevstr,
+ prev->fqid);
+ else
+ bytes += sprintf(buf + bytes, "%s: %d - %d\n", prevstr,
+ first_fqid, last_fqid);
+ }
+
+ return bytes;
+}
+
+static ssize_t dpaa_eth_show_bpids(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dpaa_priv *priv = netdev_priv(to_net_dev(dev));
+ ssize_t bytes = 0;
+ int i = 0;
+
+ for (i = 0; i < DPAA_BPS_NUM; i++)
+ bytes += snprintf(buf + bytes, PAGE_SIZE - bytes, "%u\n",
+ priv->dpaa_bps[i]->bpid);
+
+ return bytes;
+}
+
+static struct device_attribute dpaa_eth_attrs[] = {
+ __ATTR(device_addr, 0444, dpaa_eth_show_addr, NULL),
+ __ATTR(fqids, 0444, dpaa_eth_show_fqids, NULL),
+ __ATTR(bpids, 0444, dpaa_eth_show_bpids, NULL),
+};
+
+void dpaa_eth_sysfs_init(struct device *dev)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(dpaa_eth_attrs); i++)
+ if (device_create_file(dev, &dpaa_eth_attrs[i])) {
+ dev_err(dev, "Error creating sysfs file\n");
+ while (i > 0)
+ device_remove_file(dev, &dpaa_eth_attrs[--i]);
+ return;
+ }
+}
+
+void dpaa_eth_sysfs_remove(struct device *dev)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(dpaa_eth_attrs); i++)
+ device_remove_file(dev, &dpaa_eth_attrs[i]);
+}
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_trace.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_trace.h
new file mode 100644
index 0000000..409c1dc
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_trace.h
@@ -0,0 +1,141 @@
+/* Copyright 2013-2015 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM dpaa_eth
+
+#if !defined(_DPAA_ETH_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _DPAA_ETH_TRACE_H
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include "dpaa_eth.h"
+#include <linux/tracepoint.h>
+
+#define fd_format_name(format) { qm_fd_##format, #format }
+#define fd_format_list \
+ fd_format_name(contig), \
+ fd_format_name(sg)
+
+/* This is used to declare a class of events.
+ * individual events of this type will be defined below.
+ */
+
+/* Store details about a frame descriptor and the FQ on which it was
+ * transmitted/received.
+ */
+DECLARE_EVENT_CLASS(dpaa_eth_fd,
+ /* Trace function prototype */
+ TP_PROTO(struct net_device *netdev,
+ struct qman_fq *fq,
+ const struct qm_fd *fd),
+
+ /* Repeat argument list here */
+ TP_ARGS(netdev, fq, fd),
+
+ /* A structure containing the relevant information we want to record.
+ * Declare name and type for each normal element, name, type and size
+ * for arrays. Use __string for variable length strings.
+ */
+ TP_STRUCT__entry(
+ __field(u32, fqid)
+ __field(u64, fd_addr)
+ __field(u8, fd_format)
+ __field(u16, fd_offset)
+ __field(u32, fd_length)
+ __field(u32, fd_status)
+ __string(name, netdev->name)
+ ),
+
+ /* The function that assigns values to the above declared fields */
+ TP_fast_assign(
+ __entry->fqid = fq->fqid;
+ __entry->fd_addr = qm_fd_addr_get64(fd);
+ __entry->fd_format = qm_fd_get_format(fd);
+ __entry->fd_offset = qm_fd_get_offset(fd);
+ __entry->fd_length = qm_fd_get_length(fd);
+ __entry->fd_status = fd->status;
+ __assign_str(name, netdev->name);
+ ),
+
+ /* This is what gets printed when the trace event is triggered */
+ TP_printk("[%s] fqid=%d, fd: addr=0x%llx, format=%s, off=%u, len=%u, status=0x%08x",
+ __get_str(name), __entry->fqid, __entry->fd_addr,
+ __print_symbolic(__entry->fd_format, fd_format_list),
+ __entry->fd_offset, __entry->fd_length, __entry->fd_status)
+);
+
+/* Now declare events of the above type. Format is:
+ * DEFINE_EVENT(class, name, proto, args), with proto and args same as for class
+ */
+
+/* Tx (egress) fd */
+DEFINE_EVENT(dpaa_eth_fd, dpaa_tx_fd,
+
+ TP_PROTO(struct net_device *netdev,
+ struct qman_fq *fq,
+ const struct qm_fd *fd),
+
+ TP_ARGS(netdev, fq, fd)
+);
+
+/* Rx fd */
+DEFINE_EVENT(dpaa_eth_fd, dpaa_rx_fd,
+
+ TP_PROTO(struct net_device *netdev,
+ struct qman_fq *fq,
+ const struct qm_fd *fd),
+
+ TP_ARGS(netdev, fq, fd)
+);
+
+/* Tx confirmation fd */
+DEFINE_EVENT(dpaa_eth_fd, dpaa_tx_conf_fd,
+
+ TP_PROTO(struct net_device *netdev,
+ struct qman_fq *fq,
+ const struct qm_fd *fd),
+
+ TP_ARGS(netdev, fq, fd)
+);
+
+/* If only one event of a certain type needs to be declared, use TRACE_EVENT().
+ * The syntax is the same as for DECLARE_EVENT_CLASS().
+ */
+
+#endif /* _DPAA_ETH_TRACE_H */
+
+/* This must be outside ifdef _DPAA_ETH_TRACE_H */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE dpaa_eth_trace
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
new file mode 100644
index 0000000..27e7044
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
@@ -0,0 +1,417 @@
+/* Copyright 2008-2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/string.h>
+
+#include "dpaa_eth.h"
+#include "mac.h"
+
+static const char dpaa_stats_percpu[][ETH_GSTRING_LEN] = {
+ "interrupts",
+ "rx packets",
+ "tx packets",
+ "tx confirm",
+ "tx S/G",
+ "tx error",
+ "rx error",
+};
+
+static char dpaa_stats_global[][ETH_GSTRING_LEN] = {
+ /* dpa rx errors */
+ "rx dma error",
+ "rx frame physical error",
+ "rx frame size error",
+ "rx header error",
+
+ /* demultiplexing errors */
+ "qman cg_tdrop",
+ "qman wred",
+ "qman error cond",
+ "qman early window",
+ "qman late window",
+ "qman fq tdrop",
+ "qman fq retired",
+ "qman orp disabled",
+
+ /* congestion related stats */
+ "congestion time (ms)",
+ "entered congestion",
+ "congested (0/1)"
+};
+
+#define DPAA_STATS_PERCPU_LEN ARRAY_SIZE(dpaa_stats_percpu)
+#define DPAA_STATS_GLOBAL_LEN ARRAY_SIZE(dpaa_stats_global)
+
+static int dpaa_get_settings(struct net_device *net_dev,
+ struct ethtool_cmd *et_cmd)
+{
+ int err;
+
+ if (!net_dev->phydev) {
+ netdev_dbg(net_dev, "phy device not initialized\n");
+ return 0;
+ }
+
+ err = phy_ethtool_gset(net_dev->phydev, et_cmd);
+
+ return err;
+}
+
+static int dpaa_set_settings(struct net_device *net_dev,
+ struct ethtool_cmd *et_cmd)
+{
+ int err;
+
+ if (!net_dev->phydev) {
+ netdev_err(net_dev, "phy device not initialized\n");
+ return -ENODEV;
+ }
+
+ err = phy_ethtool_sset(net_dev->phydev, et_cmd);
+ if (err < 0)
+ netdev_err(net_dev, "phy_ethtool_sset() = %d\n", err);
+
+ return err;
+}
+
+static void dpaa_get_drvinfo(struct net_device *net_dev,
+ struct ethtool_drvinfo *drvinfo)
+{
+ int len;
+
+ strlcpy(drvinfo->driver, KBUILD_MODNAME,
+ sizeof(drvinfo->driver));
+ len = snprintf(drvinfo->version, sizeof(drvinfo->version),
+ "%X", 0);
+ len = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+ "%X", 0);
+
+ if (len >= sizeof(drvinfo->fw_version)) {
+ /* Truncated output */
+ netdev_notice(net_dev, "snprintf() = %d\n", len);
+ }
+ strlcpy(drvinfo->bus_info, dev_name(net_dev->dev.parent->parent),
+ sizeof(drvinfo->bus_info));
+}
+
+static u32 dpaa_get_msglevel(struct net_device *net_dev)
+{
+ return ((struct dpaa_priv *)netdev_priv(net_dev))->msg_enable;
+}
+
+static void dpaa_set_msglevel(struct net_device *net_dev,
+ u32 msg_enable)
+{
+ ((struct dpaa_priv *)netdev_priv(net_dev))->msg_enable = msg_enable;
+}
+
+static int dpaa_nway_reset(struct net_device *net_dev)
+{
+ int err;
+
+ if (!net_dev->phydev) {
+ netdev_err(net_dev, "phy device not initialized\n");
+ return -ENODEV;
+ }
+
+ err = 0;
+ if (net_dev->phydev->autoneg) {
+ err = phy_start_aneg(net_dev->phydev);
+ if (err < 0)
+ netdev_err(net_dev, "phy_start_aneg() = %d\n",
+ err);
+ }
+
+ return err;
+}
+
+static void dpaa_get_pauseparam(struct net_device *net_dev,
+ struct ethtool_pauseparam *epause)
+{
+ struct mac_device *mac_dev;
+ struct dpaa_priv *priv;
+
+ priv = netdev_priv(net_dev);
+ mac_dev = priv->mac_dev;
+
+ if (!net_dev->phydev) {
+ netdev_err(net_dev, "phy device not initialized\n");
+ return;
+ }
+
+ epause->autoneg = mac_dev->autoneg_pause;
+ epause->rx_pause = mac_dev->rx_pause_active;
+ epause->tx_pause = mac_dev->tx_pause_active;
+}
+
+static int dpaa_set_pauseparam(struct net_device *net_dev,
+ struct ethtool_pauseparam *epause)
+{
+ struct mac_device *mac_dev;
+ struct phy_device *phydev;
+ bool rx_pause, tx_pause;
+ struct dpaa_priv *priv;
+ u32 newadv, oldadv;
+ int err;
+
+ priv = netdev_priv(net_dev);
+ mac_dev = priv->mac_dev;
+
+ phydev = net_dev->phydev;
+ if (!phydev) {
+ netdev_err(net_dev, "phy device not initialized\n");
+ return -ENODEV;
+ }
+
+ if (!(phydev->supported & SUPPORTED_Pause) ||
+ (!(phydev->supported & SUPPORTED_Asym_Pause) &&
+ (epause->rx_pause != epause->tx_pause)))
+ return -EINVAL;
+
+ /* The MAC should know how to handle PAUSE frame autonegotiation before
+ * adjust_link is triggered by a forced renegotiation of sym/asym PAUSE
+ * settings.
+ */
+ mac_dev->autoneg_pause = !!epause->autoneg;
+ mac_dev->rx_pause_req = !!epause->rx_pause;
+ mac_dev->tx_pause_req = !!epause->tx_pause;
+
+ /* Determine the sym/asym advertised PAUSE capabilities from the desired
+ * rx/tx pause settings.
+ */
+ newadv = 0;
+ if (epause->rx_pause)
+ newadv = ADVERTISED_Pause | ADVERTISED_Asym_Pause;
+ if (epause->tx_pause)
+ newadv |= ADVERTISED_Asym_Pause;
+
+ oldadv = phydev->advertising &
+ (ADVERTISED_Pause | ADVERTISED_Asym_Pause);
+
+ /* If there are differences between the old and the new advertised
+ * values, restart PHY autonegotiation and advertise the new values.
+ */
+ if (oldadv != newadv) {
+ phydev->advertising &= ~(ADVERTISED_Pause
+ | ADVERTISED_Asym_Pause);
+ phydev->advertising |= newadv;
+ if (phydev->autoneg) {
+ err = phy_start_aneg(phydev);
+ if (err < 0)
+ netdev_err(net_dev, "phy_start_aneg() = %d\n",
+ err);
+ }
+ }
+
+ fman_get_pause_cfg(mac_dev, &rx_pause, &tx_pause);
+ err = fman_set_mac_active_pause(mac_dev, rx_pause, tx_pause);
+ if (err < 0)
+ netdev_err(net_dev, "set_mac_active_pause() = %d\n", err);
+
+ return err;
+}
+
+static int dpaa_get_sset_count(struct net_device *net_dev, int type)
+{
+ unsigned int total_stats, num_stats;
+
+ num_stats = num_online_cpus() + 1;
+ total_stats = num_stats * (DPAA_STATS_PERCPU_LEN + DPAA_BPS_NUM) +
+ DPAA_STATS_GLOBAL_LEN;
+
+ switch (type) {
+ case ETH_SS_STATS:
+ return total_stats;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static void copy_stats(struct dpaa_percpu_priv *percpu_priv, int num_cpus,
+ int crr_cpu, u64 *bp_count, u64 *data)
+{
+ int num_values = num_cpus + 1;
+ int crr = 0, j;
+
+ /* update current CPU's stats and also add them to the total values */
+ data[crr * num_values + crr_cpu] = percpu_priv->in_interrupt;
+ data[crr++ * num_values + num_cpus] += percpu_priv->in_interrupt;
+
+ data[crr * num_values + crr_cpu] = percpu_priv->stats.rx_packets;
+ data[crr++ * num_values + num_cpus] += percpu_priv->stats.rx_packets;
+
+ data[crr * num_values + crr_cpu] = percpu_priv->stats.tx_packets;
+ data[crr++ * num_values + num_cpus] += percpu_priv->stats.tx_packets;
+
+ data[crr * num_values + crr_cpu] = percpu_priv->tx_confirm;
+ data[crr++ * num_values + num_cpus] += percpu_priv->tx_confirm;
+
+ data[crr * num_values + crr_cpu] = percpu_priv->tx_frag_skbuffs;
+ data[crr++ * num_values + num_cpus] += percpu_priv->tx_frag_skbuffs;
+
+ data[crr * num_values + crr_cpu] = percpu_priv->stats.tx_errors;
+ data[crr++ * num_values + num_cpus] += percpu_priv->stats.tx_errors;
+
+ data[crr * num_values + crr_cpu] = percpu_priv->stats.rx_errors;
+ data[crr++ * num_values + num_cpus] += percpu_priv->stats.rx_errors;
+
+ for (j = 0; j < DPAA_BPS_NUM; j++) {
+ data[crr * num_values + crr_cpu] = bp_count[j];
+ data[crr++ * num_values + num_cpus] += bp_count[j];
+ }
+}
+
+static void dpaa_get_ethtool_stats(struct net_device *net_dev,
+ struct ethtool_stats *stats, u64 *data)
+{
+ u64 bp_count[DPAA_BPS_NUM], cg_time, cg_num;
+ struct dpaa_percpu_priv *percpu_priv;
+ struct dpaa_rx_errors rx_errors;
+ unsigned int num_cpus, offset;
+ struct dpaa_ern_cnt ern_cnt;
+ struct dpaa_bp *dpaa_bp;
+ struct dpaa_priv *priv;
+ int total_stats, i, j;
+ bool cg_status;
+
+ total_stats = dpaa_get_sset_count(net_dev, ETH_SS_STATS);
+ priv = netdev_priv(net_dev);
+ num_cpus = num_online_cpus();
+
+ memset(&bp_count, 0, sizeof(bp_count));
+ memset(&rx_errors, 0, sizeof(struct dpaa_rx_errors));
+ memset(&ern_cnt, 0, sizeof(struct dpaa_ern_cnt));
+ memset(data, 0, total_stats * sizeof(u64));
+
+ for_each_online_cpu(i) {
+ percpu_priv = per_cpu_ptr(priv->percpu_priv, i);
+ for (j = 0; j < DPAA_BPS_NUM; j++) {
+ dpaa_bp = priv->dpaa_bps[j];
+ if (!dpaa_bp->percpu_count)
+ continue;
+ bp_count[j] = *(per_cpu_ptr(dpaa_bp->percpu_count, i));
+ }
+ rx_errors.dme += percpu_priv->rx_errors.dme;
+ rx_errors.fpe += percpu_priv->rx_errors.fpe;
+ rx_errors.fse += percpu_priv->rx_errors.fse;
+ rx_errors.phe += percpu_priv->rx_errors.phe;
+
+ ern_cnt.cg_tdrop += percpu_priv->ern_cnt.cg_tdrop;
+ ern_cnt.wred += percpu_priv->ern_cnt.wred;
+ ern_cnt.err_cond += percpu_priv->ern_cnt.err_cond;
+ ern_cnt.early_window += percpu_priv->ern_cnt.early_window;
+ ern_cnt.late_window += percpu_priv->ern_cnt.late_window;
+ ern_cnt.fq_tdrop += percpu_priv->ern_cnt.fq_tdrop;
+ ern_cnt.fq_retired += percpu_priv->ern_cnt.fq_retired;
+ ern_cnt.orp_zero += percpu_priv->ern_cnt.orp_zero;
+
+ copy_stats(percpu_priv, num_cpus, i, bp_count, data);
+ }
+
+ offset = (num_cpus + 1) * (DPAA_STATS_PERCPU_LEN + DPAA_BPS_NUM);
+ memcpy(data + offset, &rx_errors, sizeof(struct dpaa_rx_errors));
+
+ offset += sizeof(struct dpaa_rx_errors) / sizeof(u64);
+ memcpy(data + offset, &ern_cnt, sizeof(struct dpaa_ern_cnt));
+
+ /* gather congestion related counters */
+ cg_num = 0;
+ cg_status = 0;
+ cg_time = jiffies_to_msecs(priv->cgr_data.congested_jiffies);
+ if (qman_query_cgr_congested(&priv->cgr_data.cgr, &cg_status) == 0) {
+ cg_num = priv->cgr_data.cgr_congested_count;
+
+ /* reset congestion stats (like QMan API does */
+ priv->cgr_data.congested_jiffies = 0;
+ priv->cgr_data.cgr_congested_count = 0;
+ }
+
+ offset += sizeof(struct dpaa_ern_cnt) / sizeof(u64);
+ data[offset++] = cg_time;
+ data[offset++] = cg_num;
+ data[offset++] = cg_status;
+}
+
+static void dpaa_get_strings(struct net_device *net_dev, u32 stringset,
+ u8 *data)
+{
+ unsigned int i, j, num_cpus, size;
+ char string_cpu[ETH_GSTRING_LEN];
+ u8 *strings;
+
+ memset(string_cpu, 0, sizeof(string_cpu));
+ strings = data;
+ num_cpus = num_online_cpus();
+ size = DPAA_STATS_GLOBAL_LEN * ETH_GSTRING_LEN;
+
+ for (i = 0; i < DPAA_STATS_PERCPU_LEN; i++) {
+ for (j = 0; j < num_cpus; j++) {
+ snprintf(string_cpu, ETH_GSTRING_LEN, "%s [CPU %d]",
+ dpaa_stats_percpu[i], j);
+ memcpy(strings, string_cpu, ETH_GSTRING_LEN);
+ strings += ETH_GSTRING_LEN;
+ }
+ snprintf(string_cpu, ETH_GSTRING_LEN, "%s [TOTAL]",
+ dpaa_stats_percpu[i]);
+ memcpy(strings, string_cpu, ETH_GSTRING_LEN);
+ strings += ETH_GSTRING_LEN;
+ }
+ for (i = 0; i < DPAA_BPS_NUM; i++) {
+ for (j = 0; j < num_cpus; j++) {
+ snprintf(string_cpu, ETH_GSTRING_LEN,
+ "bpool %c [CPU %d]", 'a' + i, j);
+ memcpy(strings, string_cpu, ETH_GSTRING_LEN);
+ strings += ETH_GSTRING_LEN;
+ }
+ snprintf(string_cpu, ETH_GSTRING_LEN, "bpool %c [TOTAL]",
+ 'a' + i);
+ memcpy(strings, string_cpu, ETH_GSTRING_LEN);
+ strings += ETH_GSTRING_LEN;
+ }
+ memcpy(strings, dpaa_stats_global, size);
+}
+
+const struct ethtool_ops dpaa_ethtool_ops = {
+ .get_settings = dpaa_get_settings,
+ .set_settings = dpaa_set_settings,
+ .get_drvinfo = dpaa_get_drvinfo,
+ .get_msglevel = dpaa_get_msglevel,
+ .set_msglevel = dpaa_set_msglevel,
+ .nway_reset = dpaa_nway_reset,
+ .get_pauseparam = dpaa_get_pauseparam,
+ .set_pauseparam = dpaa_set_pauseparam,
+ .get_link = ethtool_op_get_link,
+ .get_sset_count = dpaa_get_sset_count,
+ .get_ethtool_stats = dpaa_get_ethtool_stats,
+ .get_strings = dpaa_get_strings,
+};
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 43b2839..1aabe4b 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1430,14 +1430,14 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
skb_put(skb, pkt_len - 4);
data = skb->data;
+ if (!is_copybreak && need_swap)
+ swap_buffer(data, pkt_len);
+
#if !defined(CONFIG_M5272)
if (fep->quirks & FEC_QUIRK_HAS_RACC)
data = skb_pull_inline(skb, 2);
#endif
- if (!is_copybreak && need_swap)
- swap_buffer(data, pkt_len);
-
/* Extract the enhanced buffer descriptor */
ebdp = NULL;
if (fep->bufdesc_ex)
@@ -2344,16 +2344,6 @@ static int fec_enet_get_sset_count(struct net_device *dev, int sset)
}
#endif /* !defined(CONFIG_M5272) */
-static int fec_enet_nway_reset(struct net_device *dev)
-{
- struct phy_device *phydev = dev->phydev;
-
- if (!phydev)
- return -ENODEV;
-
- return genphy_restart_aneg(phydev);
-}
-
/* ITR clock source is enet system clock (clk_ahb).
* TCTT unit is cycle_ns * 64 cycle
* So, the ICTT value = X us / (cycle_ns * 64)
@@ -2553,7 +2543,7 @@ static const struct ethtool_ops fec_enet_ethtool_ops = {
.get_drvinfo = fec_enet_get_drvinfo,
.get_regs_len = fec_enet_get_regs_len,
.get_regs = fec_enet_get_regs,
- .nway_reset = fec_enet_nway_reset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_link = ethtool_op_get_link,
.get_coalesce = fec_enet_get_coalesce,
.set_coalesce = fec_enet_set_coalesce,
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index 44f50e1..34843c1 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -807,11 +807,6 @@ static void fs_get_regs(struct net_device *dev, struct ethtool_regs *regs,
regs->version = 0;
}
-static int fs_nway_reset(struct net_device *dev)
-{
- return 0;
-}
-
static u32 fs_get_msglevel(struct net_device *dev)
{
struct fs_enet_private *fep = netdev_priv(dev);
@@ -865,7 +860,7 @@ static int fs_set_tunable(struct net_device *dev,
static const struct ethtool_ops fs_ethtool_ops = {
.get_drvinfo = fs_get_drvinfo,
.get_regs_len = fs_get_regs_len,
- .nway_reset = fs_nway_reset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_link = ethtool_op_get_link,
.get_msglevel = fs_get_msglevel,
.set_msglevel = fs_set_msglevel,
diff --git a/drivers/net/ethernet/freescale/gianfar_ptp.c b/drivers/net/ethernet/freescale/gianfar_ptp.c
index 5779881..3e8d1ff 100644
--- a/drivers/net/ethernet/freescale/gianfar_ptp.c
+++ b/drivers/net/ethernet/freescale/gianfar_ptp.c
@@ -72,7 +72,7 @@ struct gianfar_ptp_registers {
/* Bit definitions for the TMR_CTRL register */
#define ALM1P (1<<31) /* Alarm1 output polarity */
#define ALM2P (1<<30) /* Alarm2 output polarity */
-#define FS (1<<28) /* FIPER start indication */
+#define FIPERST (1<<28) /* FIPER start indication */
#define PP1L (1<<27) /* Fiper1 pulse loopback mode enabled. */
#define PP2L (1<<26) /* Fiper2 pulse loopback mode enabled. */
#define TCLK_PERIOD_SHIFT (16) /* 1588 timer reference clock period. */
@@ -502,7 +502,7 @@ static int gianfar_ptp_probe(struct platform_device *dev)
gfar_write(&etsects->regs->tmr_fiper1, etsects->tmr_fiper1);
gfar_write(&etsects->regs->tmr_fiper2, etsects->tmr_fiper2);
set_alarm(etsects);
- gfar_write(&etsects->regs->tmr_ctrl, tmr_ctrl|FS|RTPE|TE|FRD);
+ gfar_write(&etsects->regs->tmr_ctrl, tmr_ctrl|FIPERST|RTPE|TE|FRD);
spin_unlock_irqrestore(&etsects->lock, flags);
diff --git a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
index 812a968..8ba636f 100644
--- a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
+++ b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
@@ -332,13 +332,6 @@ static void uec_get_ethtool_stats(struct net_device *netdev,
}
}
-static int uec_nway_reset(struct net_device *netdev)
-{
- struct ucc_geth_private *ugeth = netdev_priv(netdev);
-
- return phy_start_aneg(ugeth->phydev);
-}
-
/* Report driver information */
static void
uec_get_drvinfo(struct net_device *netdev,
@@ -394,7 +387,7 @@ static const struct ethtool_ops uec_ethtool_ops = {
.get_regs = uec_get_regs,
.get_msglevel = uec_get_msglevel,
.set_msglevel = uec_set_msglevel,
- .nway_reset = uec_nway_reset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_link = ethtool_op_get_link,
.get_ringparam = uec_get_ringparam,
.set_ringparam = uec_set_ringparam,
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index c54c6fa..b6ed818 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -332,8 +332,10 @@ struct hnae_handle *hnae_get_handle(struct device *owner_dev,
return ERR_PTR(-ENODEV);
handle = dev->ops->get_handle(dev, port_id);
- if (IS_ERR(handle))
+ if (IS_ERR(handle)) {
+ put_device(&dev->cls_dev);
return handle;
+ }
handle->dev = dev;
handle->owner_dev = owner_dev;
@@ -356,6 +358,8 @@ struct hnae_handle *hnae_get_handle(struct device *owner_dev,
for (j = i - 1; j >= 0; j--)
hnae_fini_queue(handle->qs[j]);
+ put_device(&dev->cls_dev);
+
return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL(hnae_get_handle);
@@ -377,6 +381,8 @@ void hnae_put_handle(struct hnae_handle *h)
dev->ops->put_handle(h);
module_put(dev->owner);
+
+ put_device(&dev->cls_dev);
}
EXPORT_SYMBOL(hnae_put_handle);
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index e093cbf..09602f1 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -426,8 +426,14 @@ enum hnae_media_type {
* get mac address
* set_mac_addr()
* set mac address
+ * clr_mc_addr()
+ * clear mcast tcam table
* set_mc_addr()
* set multicast mode
+ * add_uc_addr()
+ * add ucast address
+ * rm_uc_addr()
+ * remove ucast address
* set_mtu()
* set mtu
* update_stats()
@@ -488,6 +494,11 @@ struct hnae_ae_ops {
void (*set_promisc_mode)(struct hnae_handle *handle, u32 en);
int (*get_mac_addr)(struct hnae_handle *handle, void **p);
int (*set_mac_addr)(struct hnae_handle *handle, void *p);
+ int (*add_uc_addr)(struct hnae_handle *handle,
+ const unsigned char *addr);
+ int (*rm_uc_addr)(struct hnae_handle *handle,
+ const unsigned char *addr);
+ int (*clr_mc_addr)(struct hnae_handle *handle);
int (*set_mc_addr)(struct hnae_handle *handle, void *addr);
int (*set_mtu)(struct hnae_handle *handle, int new_mtu);
void (*set_tso_stats)(struct hnae_handle *handle, int enable);
@@ -590,7 +601,7 @@ static inline int hnae_alloc_buffer_attach(struct hnae_ring *ring, int i)
if (ret)
return ret;
- ring->desc[i].addr = (__le64)ring->desc_cb[i].dma;
+ ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma);
return 0;
}
@@ -621,14 +632,14 @@ static inline void hnae_replace_buffer(struct hnae_ring *ring, int i,
bops->unmap_buffer(ring, &ring->desc_cb[i]);
ring->desc_cb[i] = *res_cb;
- ring->desc[i].addr = (__le64)ring->desc_cb[i].dma;
+ ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma);
ring->desc[i].rx.ipoff_bnum_pid_flag = 0;
}
static inline void hnae_reuse_buffer(struct hnae_ring *ring, int i)
{
ring->desc_cb[i].reuse_flag = 0;
- ring->desc[i].addr = (__le64)(ring->desc_cb[i].dma
+ ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma
+ ring->desc_cb[i].page_offset);
ring->desc[i].rx.ipoff_bnum_pid_flag = 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
index e28d960..0a9cdf0 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
@@ -18,9 +18,6 @@
#include "hns_dsaf_rcb.h"
#define AE_NAME_PORT_ID_IDX 6
-#define ETH_STATIC_REG 1
-#define ETH_DUMP_REG 5
-#define ETH_GSTRING_LEN 32
static struct hns_mac_cb *hns_get_mac_cb(struct hnae_handle *handle)
{
@@ -202,11 +199,34 @@ static int hns_ae_set_mac_address(struct hnae_handle *handle, void *p)
return 0;
}
+static int hns_ae_add_uc_address(struct hnae_handle *handle,
+ const unsigned char *addr)
+{
+ struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle);
+
+ if (mac_cb->mac_type != HNAE_PORT_SERVICE)
+ return -ENOSPC;
+
+ return hns_mac_add_uc_addr(mac_cb, handle->vf_id, addr);
+}
+
+static int hns_ae_rm_uc_address(struct hnae_handle *handle,
+ const unsigned char *addr)
+{
+ struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle);
+
+ if (mac_cb->mac_type != HNAE_PORT_SERVICE)
+ return -ENOSPC;
+
+ return hns_mac_rm_uc_addr(mac_cb, handle->vf_id, addr);
+}
+
static int hns_ae_set_multicast_one(struct hnae_handle *handle, void *addr)
{
int ret;
char *mac_addr = (char *)addr;
struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle);
+ u8 port_num;
assert(mac_cb);
@@ -221,8 +241,11 @@ static int hns_ae_set_multicast_one(struct hnae_handle *handle, void *addr)
return ret;
}
- ret = hns_mac_set_multi(mac_cb, DSAF_BASE_INNER_PORT_NUM,
- mac_addr, true);
+ ret = hns_mac_get_inner_port_num(mac_cb, handle->vf_id, &port_num);
+ if (ret)
+ return ret;
+
+ ret = hns_mac_set_multi(mac_cb, port_num, mac_addr, true);
if (ret)
dev_err(handle->owner_dev,
"mac add mul_mac:%pM port%d fail, ret = %#x!\n",
@@ -231,6 +254,16 @@ static int hns_ae_set_multicast_one(struct hnae_handle *handle, void *addr)
return ret;
}
+static int hns_ae_clr_multicast(struct hnae_handle *handle)
+{
+ struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle);
+
+ if (mac_cb->mac_type != HNAE_PORT_SERVICE)
+ return 0;
+
+ return hns_mac_clr_multicast(mac_cb, handle->vf_id);
+}
+
static int hns_ae_set_mtu(struct hnae_handle *handle, int new_mtu)
{
struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle);
@@ -678,9 +711,6 @@ static int hns_ae_config_loopback(struct hnae_handle *handle,
ret = -EINVAL;
}
- if (!ret)
- hns_dsaf_set_inner_lb(mac_cb->dsaf_dev, mac_cb->mac_id, en);
-
return ret;
}
@@ -822,7 +852,10 @@ static struct hnae_ae_ops hns_dsaf_ops = {
.get_coalesce_range = hns_ae_get_coalesce_range,
.set_promisc_mode = hns_ae_set_promisc_mode,
.set_mac_addr = hns_ae_set_mac_address,
+ .add_uc_addr = hns_ae_add_uc_address,
+ .rm_uc_addr = hns_ae_rm_uc_address,
.set_mc_addr = hns_ae_set_multicast_one,
+ .clr_mc_addr = hns_ae_clr_multicast,
.set_mtu = hns_ae_set_mtu,
.update_stats = hns_ae_update_stats,
.set_tso_stats = hns_ae_set_tso_stats,
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
index 1e1eb92..3382441 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
@@ -37,8 +37,8 @@ static const struct mac_stats_string g_gmac_stats_string[] = {
{"gmac_rx_very_long_err", MAC_STATS_FIELD_OFF(rx_long_err)},
{"gmac_rx_runt_err", MAC_STATS_FIELD_OFF(rx_minto64)},
{"gmac_rx_short_err", MAC_STATS_FIELD_OFF(rx_under_min)},
- {"gmac_rx_filt_pkt", MAC_STATS_FIELD_OFF(rx_filter_bytes)},
- {"gmac_rx_octets_total_filt", MAC_STATS_FIELD_OFF(rx_filter_pkts)},
+ {"gmac_rx_filt_pkt", MAC_STATS_FIELD_OFF(rx_filter_pkts)},
+ {"gmac_rx_octets_total_filt", MAC_STATS_FIELD_OFF(rx_filter_bytes)},
{"gmac_rx_overrun_cnt", MAC_STATS_FIELD_OFF(rx_fifo_overrun_err)},
{"gmac_rx_length_err", MAC_STATS_FIELD_OFF(rx_len_err)},
{"gmac_rx_fail_comma", MAC_STATS_FIELD_OFF(rx_comma_err)},
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index d8e9941..3239d27 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -141,9 +141,10 @@ void hns_mac_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex)
*@port_num:port number
*
*/
-static int hns_mac_get_inner_port_num(struct hns_mac_cb *mac_cb,
- u8 vmid, u8 *port_num)
+int hns_mac_get_inner_port_num(struct hns_mac_cb *mac_cb, u8 vmid, u8 *port_num)
{
+ int q_num_per_vf, vf_num_per_port;
+ int vm_queue_id;
u8 tmp_port;
if (mac_cb->dsaf_dev->dsaf_mode <= DSAF_MODE_ENABLE) {
@@ -174,6 +175,12 @@ static int hns_mac_get_inner_port_num(struct hns_mac_cb *mac_cb,
return -EINVAL;
}
+ q_num_per_vf = mac_cb->dsaf_dev->rcb_common[0]->max_q_per_vf;
+ vf_num_per_port = mac_cb->dsaf_dev->rcb_common[0]->max_vfn;
+
+ vm_queue_id = vmid * q_num_per_vf +
+ vf_num_per_port * q_num_per_vf * mac_cb->mac_id;
+
switch (mac_cb->dsaf_dev->dsaf_mode) {
case DSAF_MODE_ENABLE_FIX:
tmp_port = 0;
@@ -193,7 +200,7 @@ static int hns_mac_get_inner_port_num(struct hns_mac_cb *mac_cb,
case DSAF_MODE_DISABLE_6PORT_2VM:
case DSAF_MODE_DISABLE_6PORT_4VM:
case DSAF_MODE_DISABLE_6PORT_16VM:
- tmp_port = vmid;
+ tmp_port = vm_queue_id;
break;
default:
dev_err(mac_cb->dev, "dsaf mode invalid, %s mac%d!\n",
@@ -256,6 +263,46 @@ int hns_mac_change_vf_addr(struct hns_mac_cb *mac_cb,
return 0;
}
+int hns_mac_add_uc_addr(struct hns_mac_cb *mac_cb, u8 vf_id,
+ const unsigned char *addr)
+{
+ struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev;
+ struct dsaf_drv_mac_single_dest_entry mac_entry;
+ int ret;
+
+ if (HNS_DSAF_IS_DEBUG(dsaf_dev))
+ return -ENOSPC;
+
+ memset(&mac_entry, 0, sizeof(mac_entry));
+ memcpy(mac_entry.addr, addr, sizeof(mac_entry.addr));
+ mac_entry.in_port_num = mac_cb->mac_id;
+ ret = hns_mac_get_inner_port_num(mac_cb, vf_id, &mac_entry.port_num);
+ if (ret)
+ return ret;
+
+ return hns_dsaf_set_mac_uc_entry(dsaf_dev, &mac_entry);
+}
+
+int hns_mac_rm_uc_addr(struct hns_mac_cb *mac_cb, u8 vf_id,
+ const unsigned char *addr)
+{
+ struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev;
+ struct dsaf_drv_mac_single_dest_entry mac_entry;
+ int ret;
+
+ if (HNS_DSAF_IS_DEBUG(dsaf_dev))
+ return -ENOSPC;
+
+ memset(&mac_entry, 0, sizeof(mac_entry));
+ memcpy(mac_entry.addr, addr, sizeof(mac_entry.addr));
+ mac_entry.in_port_num = mac_cb->mac_id;
+ ret = hns_mac_get_inner_port_num(mac_cb, vf_id, &mac_entry.port_num);
+ if (ret)
+ return ret;
+
+ return hns_dsaf_rm_mac_addr(dsaf_dev, &mac_entry);
+}
+
int hns_mac_set_multi(struct hns_mac_cb *mac_cb,
u32 port_num, char *addr, bool enable)
{
@@ -323,13 +370,24 @@ int hns_mac_del_mac(struct hns_mac_cb *mac_cb, u32 vfn, char *mac)
return 0;
}
+int hns_mac_clr_multicast(struct hns_mac_cb *mac_cb, int vfn)
+{
+ struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev;
+ u8 port_num;
+ int ret = hns_mac_get_inner_port_num(mac_cb, vfn, &port_num);
+
+ if (ret)
+ return ret;
+
+ return hns_dsaf_clr_mac_mc_port(dsaf_dev, mac_cb->mac_id, port_num);
+}
+
static void hns_mac_param_get(struct mac_params *param,
struct hns_mac_cb *mac_cb)
{
param->vaddr = (void *)mac_cb->vaddr;
param->mac_mode = hns_get_enet_interface(mac_cb);
- memcpy(param->addr, mac_cb->addr_entry_idx[0].addr,
- MAC_NUM_OCTETS_PER_ADDR);
+ ether_addr_copy(param->addr, mac_cb->addr_entry_idx[0].addr);
param->mac_id = mac_cb->mac_id;
param->dev = mac_cb->dev;
}
@@ -346,8 +404,7 @@ static int hns_mac_port_config_bc_en(struct hns_mac_cb *mac_cb,
{
int ret;
struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev;
- u8 addr[MAC_NUM_OCTETS_PER_ADDR]
- = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
+ u8 addr[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
struct dsaf_drv_mac_single_dest_entry mac_entry;
/* directy return ok in debug network mode */
@@ -382,8 +439,7 @@ int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vmid, bool enable)
int ret;
struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev;
u8 port_num;
- u8 addr[MAC_NUM_OCTETS_PER_ADDR]
- = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
+ u8 addr[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
struct mac_entry_idx *uc_mac_entry;
struct dsaf_drv_mac_single_dest_entry mac_entry;
@@ -861,6 +917,13 @@ static int hns_mac_get_info(struct hns_mac_cb *mac_cb)
}
}
+ if (fwnode_property_read_u8_array(mac_cb->fw_port, "mc-mac-mask",
+ mac_cb->mc_mask, ETH_ALEN)) {
+ dev_warn(mac_cb->dev,
+ "no mc-mac-mask property, set to default value.\n");
+ eth_broadcast_addr(mac_cb->mc_mask);
+ }
+
return 0;
}
@@ -1074,6 +1137,8 @@ void hns_mac_set_promisc(struct hns_mac_cb *mac_cb, u8 en)
{
struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb);
+ hns_dsaf_set_promisc_tcam(mac_cb->dsaf_dev, mac_cb->mac_id, !!en);
+
if (mac_ctrl_drv->set_promiscuous)
mac_ctrl_drv->set_promiscuous(mac_ctrl_drv, en);
}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
index 4cbdf14..2bb3d1e 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
@@ -31,7 +31,7 @@ struct dsaf_device;
#define MAC_MIN_MTU 68
#define MAC_MAX_MTU_DBG MAC_DEFAULT_MTU
-#define MAC_DEFAULT_PAUSE_TIME 0xff
+#define MAC_DEFAULT_PAUSE_TIME 0xffff
#define MAC_GMAC_IDX 0
#define MAC_XGMAC_IDX 1
@@ -56,9 +56,6 @@ struct dsaf_device;
/*check mac addr multicast*/
#define MAC_IS_MULTICAST(p) ((*((u8 *)((p) + 0)) & 0x01) ? (1) : (0))
-/**< Number of octets (8-bit bytes) in an ethernet address */
-#define MAC_NUM_OCTETS_PER_ADDR 6
-
struct mac_priv {
void *mac;
};
@@ -189,7 +186,7 @@ struct mac_statistics {
/*mac para struct ,mac get param from nic or dsaf when initialize*/
struct mac_params {
- char addr[MAC_NUM_OCTETS_PER_ADDR];
+ char addr[ETH_ALEN];
void *vaddr; /*virtual address*/
struct device *dev;
u8 mac_id;
@@ -214,7 +211,7 @@ struct mac_info {
};
struct mac_entry_idx {
- u8 addr[MAC_NUM_OCTETS_PER_ADDR];
+ u8 addr[ETH_ALEN];
u16 vlan_id:12;
u16 valid:1;
u16 qos:3;
@@ -317,6 +314,7 @@ struct hns_mac_cb {
u8 __iomem *serdes_vaddr;
struct regmap *serdes_ctrl;
struct regmap *cpld_ctrl;
+ char mc_mask[ETH_ALEN];
u32 cpld_ctrl_reg;
u32 port_rst_off;
u32 port_mode_off;
@@ -409,7 +407,7 @@ struct mac_driver {
};
struct mac_stats_string {
- char desc[64];
+ char desc[ETH_GSTRING_LEN];
unsigned long offset;
};
@@ -461,5 +459,12 @@ void hns_set_led_opt(struct hns_mac_cb *mac_cb);
int hns_cpld_led_set_id(struct hns_mac_cb *mac_cb,
enum hnae_led_state status);
void hns_mac_set_promisc(struct hns_mac_cb *mac_cb, u8 en);
+int hns_mac_get_inner_port_num(struct hns_mac_cb *mac_cb,
+ u8 vmid, u8 *port_num);
+int hns_mac_add_uc_addr(struct hns_mac_cb *mac_cb, u8 vf_id,
+ const unsigned char *addr);
+int hns_mac_rm_uc_addr(struct hns_mac_cb *mac_cb, u8 vf_id,
+ const unsigned char *addr);
+int hns_mac_clr_multicast(struct hns_mac_cb *mac_cb, int vfn);
#endif /* _HNS_DSAF_MAC_H */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 8e5b3f5..90dbda7 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -591,6 +591,16 @@ static void hns_dsaf_voq_bp_all_thrd_cfg(struct dsaf_device *dsaf_dev)
}
}
+static void hns_dsaf_tbl_tcam_match_cfg(
+ struct dsaf_device *dsaf_dev,
+ struct dsaf_tbl_tcam_data *ptbl_tcam_data)
+{
+ dsaf_write_dev(dsaf_dev, DSAF_TBL_TCAM_MATCH_CFG_L_REG,
+ ptbl_tcam_data->tbl_tcam_data_low);
+ dsaf_write_dev(dsaf_dev, DSAF_TBL_TCAM_MATCH_CFG_H_REG,
+ ptbl_tcam_data->tbl_tcam_data_high);
+}
+
/**
* hns_dsaf_tbl_tcam_data_cfg - tbl
* @dsaf_id: dsa fabric id
@@ -755,21 +765,11 @@ static void hns_dsaf_tbl_tcam_data_ucast_pul(
void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en)
{
- if (!HNS_DSAF_IS_DEBUG(dsaf_dev))
+ if (AE_IS_VER1(dsaf_dev->dsaf_ver) && !HNS_DSAF_IS_DEBUG(dsaf_dev))
dsaf_set_dev_bit(dsaf_dev, DSAF_CFG_0_REG,
DSAF_CFG_MIX_MODE_S, !!en);
}
-void hns_dsaf_set_inner_lb(struct dsaf_device *dsaf_dev, u32 mac_id, u32 en)
-{
- if (AE_IS_VER1(dsaf_dev->dsaf_ver) ||
- dsaf_dev->mac_cb[mac_id]->mac_type == HNAE_PORT_DEBUG)
- return;
-
- dsaf_set_dev_bit(dsaf_dev, DSAFV2_SERDES_LBK_0_REG + 4 * mac_id,
- DSAFV2_SERDES_LBK_EN_B, !!en);
-}
-
/**
* hns_dsaf_tbl_stat_en - tbl
* @dsaf_id: dsa fabric id
@@ -904,15 +904,16 @@ static void hns_dsaf_tcam_uc_cfg(
}
/**
- * hns_dsaf_tcam_mc_cfg - INT
- * @dsaf_id: dsa fabric id
- * @address,
- * @ptbl_tcam_data,
- * @ptbl_tcam_mcast,
+ * hns_dsaf_tcam_mc_cfg - cfg the tcam for mc
+ * @dsaf_dev: dsa fabric device struct pointer
+ * @address: tcam index
+ * @ptbl_tcam_data: tcam data struct pointer
+ * @ptbl_tcam_mcast: tcam mask struct pointer, it must be null for HNSv1
*/
static void hns_dsaf_tcam_mc_cfg(
struct dsaf_device *dsaf_dev, u32 address,
struct dsaf_tbl_tcam_data *ptbl_tcam_data,
+ struct dsaf_tbl_tcam_data *ptbl_tcam_mask,
struct dsaf_tbl_tcam_mcast_cfg *ptbl_tcam_mcast)
{
spin_lock_bh(&dsaf_dev->tcam_lock);
@@ -923,7 +924,11 @@ static void hns_dsaf_tcam_mc_cfg(
hns_dsaf_tbl_tcam_data_cfg(dsaf_dev, ptbl_tcam_data);
/*Write Tcam Mcast*/
hns_dsaf_tbl_tcam_mcast_cfg(dsaf_dev, ptbl_tcam_mcast);
- /*Write Plus*/
+ /* Write Match Data */
+ if (ptbl_tcam_mask)
+ hns_dsaf_tbl_tcam_match_cfg(dsaf_dev, ptbl_tcam_mask);
+
+ /* Write Puls */
hns_dsaf_tbl_tcam_data_mcast_pul(dsaf_dev);
spin_unlock_bh(&dsaf_dev->tcam_lock);
@@ -954,6 +959,16 @@ static void hns_dsaf_tcam_mc_invld(struct dsaf_device *dsaf_dev, u32 address)
spin_unlock_bh(&dsaf_dev->tcam_lock);
}
+void hns_dsaf_tcam_addr_get(struct dsaf_drv_tbl_tcam_key *mac_key, u8 *addr)
+{
+ addr[0] = mac_key->high.bits.mac_0;
+ addr[1] = mac_key->high.bits.mac_1;
+ addr[2] = mac_key->high.bits.mac_2;
+ addr[3] = mac_key->high.bits.mac_3;
+ addr[4] = mac_key->low.bits.mac_4;
+ addr[5] = mac_key->low.bits.mac_5;
+}
+
/**
* hns_dsaf_tcam_uc_get - INT
* @dsaf_id: dsa fabric id
@@ -1379,6 +1394,12 @@ static int hns_dsaf_init(struct dsaf_device *dsaf_dev)
if (HNS_DSAF_IS_DEBUG(dsaf_dev))
return 0;
+ if (AE_IS_VER1(dsaf_dev->dsaf_ver))
+ dsaf_dev->tcam_max_num = DSAF_TCAM_SUM;
+ else
+ dsaf_dev->tcam_max_num =
+ DSAF_TCAM_SUM - DSAFV2_MAC_FUZZY_TCAM_NUM;
+
spin_lock_init(&dsaf_dev->tcam_lock);
ret = hns_dsaf_init_hw(dsaf_dev);
if (ret)
@@ -1434,7 +1455,7 @@ static u16 hns_dsaf_find_soft_mac_entry(
u32 i;
soft_mac_entry = priv->soft_mac_tbl;
- for (i = 0; i < DSAF_TCAM_SUM; i++) {
+ for (i = 0; i < dsaf_dev->tcam_max_num; i++) {
/* invall tab entry */
if ((soft_mac_entry->index != DSAF_INVALID_ENTRY_IDX) &&
(soft_mac_entry->tcam_key.high.val == mac_key->high.val) &&
@@ -1459,7 +1480,7 @@ static u16 hns_dsaf_find_empty_mac_entry(struct dsaf_device *dsaf_dev)
u32 i;
soft_mac_entry = priv->soft_mac_tbl;
- for (i = 0; i < DSAF_TCAM_SUM; i++) {
+ for (i = 0; i < dsaf_dev->tcam_max_num; i++) {
/* inv all entry */
if (soft_mac_entry->index == DSAF_INVALID_ENTRY_IDX)
/* return find result --soft index */
@@ -1498,8 +1519,12 @@ static void hns_dsaf_set_mac_key(
mac_key->high.bits.mac_3 = addr[3];
mac_key->low.bits.mac_4 = addr[4];
mac_key->low.bits.mac_5 = addr[5];
- mac_key->low.bits.vlan = vlan_id;
- mac_key->low.bits.port = port;
+ dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_VLAN_M,
+ DSAF_TBL_TCAM_KEY_VLAN_S, vlan_id);
+ dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_PORT_M,
+ DSAF_TBL_TCAM_KEY_PORT_S, port);
+
+ mac_key->low.bits.port_vlan = le16_to_cpu(mac_key->low.bits.port_vlan);
}
/**
@@ -1517,6 +1542,7 @@ int hns_dsaf_set_mac_uc_entry(
struct dsaf_drv_priv *priv =
(struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev);
struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl;
+ struct dsaf_tbl_tcam_data tcam_data;
/* mac addr check */
if (MAC_IS_ALL_ZEROS(mac_entry->addr) ||
@@ -1558,9 +1584,10 @@ int hns_dsaf_set_mac_uc_entry(
/* default config dvc to 0 */
mac_data.tbl_ucast_dvc = 0;
mac_data.tbl_ucast_out_port = mac_entry->port_num;
- hns_dsaf_tcam_uc_cfg(
- dsaf_dev, entry_index,
- (struct dsaf_tbl_tcam_data *)(&mac_key), &mac_data);
+ tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
+ tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+
+ hns_dsaf_tcam_uc_cfg(dsaf_dev, entry_index, &tcam_data, &mac_data);
/* config software entry */
soft_mac_entry += entry_index;
@@ -1571,6 +1598,55 @@ int hns_dsaf_set_mac_uc_entry(
return 0;
}
+int hns_dsaf_rm_mac_addr(
+ struct dsaf_device *dsaf_dev,
+ struct dsaf_drv_mac_single_dest_entry *mac_entry)
+{
+ u16 entry_index = DSAF_INVALID_ENTRY_IDX;
+ struct dsaf_tbl_tcam_ucast_cfg mac_data;
+ struct dsaf_drv_tbl_tcam_key mac_key;
+
+ /* mac addr check */
+ if (!is_valid_ether_addr(mac_entry->addr)) {
+ dev_err(dsaf_dev->dev, "rm_uc_addr %s Mac %pM err!\n",
+ dsaf_dev->ae_dev.name, mac_entry->addr);
+ return -EINVAL;
+ }
+
+ /* config key */
+ hns_dsaf_set_mac_key(dsaf_dev, &mac_key, mac_entry->in_vlan_id,
+ mac_entry->in_port_num, mac_entry->addr);
+
+ entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key);
+ if (entry_index == DSAF_INVALID_ENTRY_IDX) {
+ /* can not find the tcam entry, return 0 */
+ dev_info(dsaf_dev->dev,
+ "rm_uc_addr no tcam, %s Mac key(%#x:%#x)\n",
+ dsaf_dev->ae_dev.name,
+ mac_key.high.val, mac_key.low.val);
+ return 0;
+ }
+
+ dev_dbg(dsaf_dev->dev,
+ "rm_uc_addr, %s Mac key(%#x:%#x) entry_index%d\n",
+ dsaf_dev->ae_dev.name, mac_key.high.val,
+ mac_key.low.val, entry_index);
+
+ hns_dsaf_tcam_uc_get(
+ dsaf_dev, entry_index,
+ (struct dsaf_tbl_tcam_data *)&mac_key,
+ &mac_data);
+
+ /* unicast entry not used locally should not clear */
+ if (mac_entry->port_num != mac_data.tbl_ucast_out_port)
+ return -EFAULT;
+
+ return hns_dsaf_del_mac_entry(dsaf_dev,
+ mac_entry->in_vlan_id,
+ mac_entry->in_port_num,
+ mac_entry->addr);
+}
+
/**
* hns_dsaf_set_mac_mc_entry - set mac mc-entry
* @dsaf_dev: dsa fabric device struct pointer
@@ -1587,6 +1663,7 @@ int hns_dsaf_set_mac_mc_entry(
(struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev);
struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl;
struct dsaf_drv_tbl_tcam_key tmp_mac_key;
+ struct dsaf_tbl_tcam_data tcam_data;
/* mac addr check */
if (MAC_IS_ALL_ZEROS(mac_entry->addr)) {
@@ -1619,9 +1696,12 @@ int hns_dsaf_set_mac_mc_entry(
0, sizeof(mac_data.tbl_mcast_port_msk));
} else {
/* config hardware entry */
- hns_dsaf_tcam_mc_get(
- dsaf_dev, entry_index,
- (struct dsaf_tbl_tcam_data *)(&tmp_mac_key), &mac_data);
+ hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data,
+ &mac_data);
+
+ tmp_mac_key.high.val =
+ le32_to_cpu(tcam_data.tbl_tcam_data_high);
+ tmp_mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
}
mac_data.tbl_mcast_old_en = 0;
mac_data.tbl_mcast_item_vld = 1;
@@ -1633,9 +1713,11 @@ int hns_dsaf_set_mac_mc_entry(
dsaf_dev->ae_dev.name, mac_key.high.val,
mac_key.low.val, entry_index);
- hns_dsaf_tcam_mc_cfg(
- dsaf_dev, entry_index,
- (struct dsaf_tbl_tcam_data *)(&mac_key), &mac_data);
+ tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
+ tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+
+ hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index, &tcam_data, NULL,
+ &mac_data);
/* config software entry */
soft_mac_entry += entry_index;
@@ -1646,6 +1728,16 @@ int hns_dsaf_set_mac_mc_entry(
return 0;
}
+static void hns_dsaf_mc_mask_bit_clear(char *dst, const char *src)
+{
+ u16 *a = (u16 *)dst;
+ const u16 *b = (const u16 *)src;
+
+ a[0] &= b[0];
+ a[1] &= b[1];
+ a[2] &= b[2];
+}
+
/**
* hns_dsaf_add_mac_mc_port - add mac mc-port
* @dsaf_dev: dsa fabric device struct pointer
@@ -1656,11 +1748,15 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
{
u16 entry_index = DSAF_INVALID_ENTRY_IDX;
struct dsaf_drv_tbl_tcam_key mac_key;
+ struct dsaf_drv_tbl_tcam_key mask_key;
+ struct dsaf_tbl_tcam_data *pmask_key = NULL;
struct dsaf_tbl_tcam_mcast_cfg mac_data;
- struct dsaf_drv_priv *priv =
- (struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev);
+ struct dsaf_drv_priv *priv = hns_dsaf_dev_priv(dsaf_dev);
struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl;
struct dsaf_drv_tbl_tcam_key tmp_mac_key;
+ struct dsaf_tbl_tcam_data tcam_data;
+ u8 mc_addr[ETH_ALEN];
+ u8 *mc_mask;
int mskid;
/*chechk mac addr */
@@ -1670,14 +1766,32 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
return -EINVAL;
}
+ ether_addr_copy(mc_addr, mac_entry->addr);
+ mc_mask = dsaf_dev->mac_cb[mac_entry->in_port_num]->mc_mask;
+ if (!AE_IS_VER1(dsaf_dev->dsaf_ver)) {
+ /* prepare for key data setting */
+ hns_dsaf_mc_mask_bit_clear(mc_addr, mc_mask);
+
+ /* config key mask */
+ hns_dsaf_set_mac_key(dsaf_dev, &mask_key,
+ 0x0,
+ 0xff,
+ mc_mask);
+
+ mask_key.high.val = le32_to_cpu(mask_key.high.val);
+ mask_key.low.val = le32_to_cpu(mask_key.low.val);
+
+ pmask_key = (struct dsaf_tbl_tcam_data *)(&mask_key);
+ }
+
/*config key */
hns_dsaf_set_mac_key(
dsaf_dev, &mac_key, mac_entry->in_vlan_id,
- mac_entry->in_port_num, mac_entry->addr);
+ mac_entry->in_port_num, mc_addr);
memset(&mac_data, 0, sizeof(struct dsaf_tbl_tcam_mcast_cfg));
- /*check exist? */
+ /* check if the tcam is exist */
entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key);
if (entry_index == DSAF_INVALID_ENTRY_IDX) {
/*if hasnot , find a empty*/
@@ -1691,11 +1805,15 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
return -EINVAL;
}
} else {
- /*if exist, add in */
- hns_dsaf_tcam_mc_get(
- dsaf_dev, entry_index,
- (struct dsaf_tbl_tcam_data *)(&tmp_mac_key), &mac_data);
+ /* if exist, add in */
+ hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data,
+ &mac_data);
+
+ tmp_mac_key.high.val =
+ le32_to_cpu(tcam_data.tbl_tcam_data_high);
+ tmp_mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
}
+
/* config hardware entry */
if (mac_entry->port_num < DSAF_SERVICE_NW_NUM) {
mskid = mac_entry->port_num;
@@ -1718,9 +1836,12 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
dsaf_dev->ae_dev.name, mac_key.high.val,
mac_key.low.val, entry_index);
- hns_dsaf_tcam_mc_cfg(
- dsaf_dev, entry_index,
- (struct dsaf_tbl_tcam_data *)(&mac_key), &mac_data);
+ tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
+ tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+
+ /* config mc entry with mask */
+ hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index, &tcam_data,
+ pmask_key, &mac_data);
/*config software entry */
soft_mac_entry += entry_index;
@@ -1792,15 +1913,18 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
{
u16 entry_index = DSAF_INVALID_ENTRY_IDX;
struct dsaf_drv_tbl_tcam_key mac_key;
- struct dsaf_drv_priv *priv =
- (struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev);
+ struct dsaf_drv_priv *priv = hns_dsaf_dev_priv(dsaf_dev);
struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl;
u16 vlan_id;
u8 in_port_num;
struct dsaf_tbl_tcam_mcast_cfg mac_data;
- struct dsaf_drv_tbl_tcam_key tmp_mac_key;
+ struct dsaf_tbl_tcam_data tcam_data;
int mskid;
const u8 empty_msk[sizeof(mac_data.tbl_mcast_port_msk)] = {0};
+ struct dsaf_drv_tbl_tcam_key mask_key, tmp_mac_key;
+ struct dsaf_tbl_tcam_data *pmask_key = NULL;
+ u8 mc_addr[ETH_ALEN];
+ u8 *mc_mask;
if (!(void *)mac_entry) {
dev_err(dsaf_dev->dev,
@@ -1808,10 +1932,6 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
return -EINVAL;
}
- /*get key info*/
- vlan_id = mac_entry->in_vlan_id;
- in_port_num = mac_entry->in_port_num;
-
/*check mac addr */
if (MAC_IS_ALL_ZEROS(mac_entry->addr)) {
dev_err(dsaf_dev->dev, "del_port failed, addr %pM!\n",
@@ -1819,11 +1939,31 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
return -EINVAL;
}
- /*config key */
- hns_dsaf_set_mac_key(dsaf_dev, &mac_key, vlan_id, in_port_num,
- mac_entry->addr);
+ /* always mask vlan_id field */
+ ether_addr_copy(mc_addr, mac_entry->addr);
+ mc_mask = dsaf_dev->mac_cb[mac_entry->in_port_num]->mc_mask;
- /*check is exist? */
+ if (!AE_IS_VER1(dsaf_dev->dsaf_ver)) {
+ /* prepare for key data setting */
+ hns_dsaf_mc_mask_bit_clear(mc_addr, mc_mask);
+
+ /* config key mask */
+ hns_dsaf_set_mac_key(dsaf_dev, &mask_key, 0x00, 0xff, mc_addr);
+
+ mask_key.high.val = le32_to_cpu(mask_key.high.val);
+ mask_key.low.val = le32_to_cpu(mask_key.low.val);
+
+ pmask_key = (struct dsaf_tbl_tcam_data *)(&mask_key);
+ }
+
+ /* get key info */
+ vlan_id = mac_entry->in_vlan_id;
+ in_port_num = mac_entry->in_port_num;
+
+ /* config key */
+ hns_dsaf_set_mac_key(dsaf_dev, &mac_key, vlan_id, in_port_num, mc_addr);
+
+ /* check if the tcam entry is exist */
entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key);
if (entry_index == DSAF_INVALID_ENTRY_IDX) {
/*find none */
@@ -1839,10 +1979,11 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
dsaf_dev->ae_dev.name, mac_key.high.val,
mac_key.low.val, entry_index);
- /*read entry*/
- hns_dsaf_tcam_mc_get(
- dsaf_dev, entry_index,
- (struct dsaf_tbl_tcam_data *)(&tmp_mac_key), &mac_data);
+ /* read entry */
+ hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, &mac_data);
+
+ tmp_mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
+ tmp_mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
/*del the port*/
if (mac_entry->port_num < DSAF_SERVICE_NW_NUM) {
@@ -1867,15 +2008,87 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
/* del soft entry */
soft_mac_entry += entry_index;
soft_mac_entry->index = DSAF_INVALID_ENTRY_IDX;
- } else { /* not zer, just del port, updata*/
- hns_dsaf_tcam_mc_cfg(
- dsaf_dev, entry_index,
- (struct dsaf_tbl_tcam_data *)(&mac_key), &mac_data);
+ } else { /* not zero, just del port, update */
+ tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
+ tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+
+ hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index,
+ &tcam_data,
+ pmask_key, &mac_data);
}
return 0;
}
+int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev, u8 mac_id,
+ u8 port_num)
+{
+ struct dsaf_drv_priv *priv = hns_dsaf_dev_priv(dsaf_dev);
+ struct dsaf_drv_soft_mac_tbl *soft_mac_entry;
+ struct dsaf_tbl_tcam_mcast_cfg mac_data;
+ int ret = 0, i;
+
+ if (HNS_DSAF_IS_DEBUG(dsaf_dev))
+ return 0;
+
+ for (i = 0; i < DSAF_TCAM_SUM - DSAFV2_MAC_FUZZY_TCAM_NUM; i++) {
+ u8 addr[ETH_ALEN];
+ u8 port;
+
+ soft_mac_entry = priv->soft_mac_tbl + i;
+
+ hns_dsaf_tcam_addr_get(&soft_mac_entry->tcam_key, addr);
+ port = dsaf_get_field(
+ soft_mac_entry->tcam_key.low.bits.port_vlan,
+ DSAF_TBL_TCAM_KEY_PORT_M,
+ DSAF_TBL_TCAM_KEY_PORT_S);
+ /* check valid tcam mc entry */
+ if (soft_mac_entry->index != DSAF_INVALID_ENTRY_IDX &&
+ port == mac_id &&
+ is_multicast_ether_addr(addr) &&
+ !is_broadcast_ether_addr(addr)) {
+ const u32 empty_msk[DSAF_PORT_MSK_NUM] = {0};
+ struct dsaf_drv_mac_single_dest_entry mac_entry;
+
+ /* disable receiving of this multicast address for
+ * the VF.
+ */
+ ether_addr_copy(mac_entry.addr, addr);
+ mac_entry.in_vlan_id = dsaf_get_field(
+ soft_mac_entry->tcam_key.low.bits.port_vlan,
+ DSAF_TBL_TCAM_KEY_VLAN_M,
+ DSAF_TBL_TCAM_KEY_VLAN_S);
+ mac_entry.in_port_num = mac_id;
+ mac_entry.port_num = port_num;
+ if (hns_dsaf_del_mac_mc_port(dsaf_dev, &mac_entry)) {
+ ret = -EINVAL;
+ continue;
+ }
+
+ /* disable receiving of this multicast address for
+ * the mac port if all VF are disable
+ */
+ hns_dsaf_tcam_mc_get(dsaf_dev, i,
+ (struct dsaf_tbl_tcam_data *)
+ (&soft_mac_entry->tcam_key),
+ &mac_data);
+ dsaf_set_bit(mac_data.tbl_mcast_port_msk[mac_id / 32],
+ mac_id % 32, 0);
+ if (!memcmp(mac_data.tbl_mcast_port_msk, empty_msk,
+ sizeof(u32) * DSAF_PORT_MSK_NUM)) {
+ mac_entry.port_num = mac_id;
+ if (hns_dsaf_del_mac_mc_port(dsaf_dev,
+ &mac_entry)) {
+ ret = -EINVAL;
+ continue;
+ }
+ }
+ }
+ }
+
+ return ret;
+}
+
/**
* hns_dsaf_get_mac_uc_entry - get mac uc entry
* @dsaf_dev: dsa fabric device struct pointer
@@ -1888,6 +2101,7 @@ int hns_dsaf_get_mac_uc_entry(struct dsaf_device *dsaf_dev,
struct dsaf_drv_tbl_tcam_key mac_key;
struct dsaf_tbl_tcam_ucast_cfg mac_data;
+ struct dsaf_tbl_tcam_data tcam_data;
/* check macaddr */
if (MAC_IS_ALL_ZEROS(mac_entry->addr) ||
@@ -1916,9 +2130,12 @@ int hns_dsaf_get_mac_uc_entry(struct dsaf_device *dsaf_dev,
dsaf_dev->ae_dev.name, mac_key.high.val,
mac_key.low.val, entry_index);
- /*read entry*/
- hns_dsaf_tcam_uc_get(dsaf_dev, entry_index,
- (struct dsaf_tbl_tcam_data *)&mac_key, &mac_data);
+ /* read entry */
+ hns_dsaf_tcam_uc_get(dsaf_dev, entry_index, &tcam_data, &mac_data);
+
+ mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
+ mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
+
mac_entry->port_num = mac_data.tbl_ucast_out_port;
return 0;
@@ -1936,6 +2153,7 @@ int hns_dsaf_get_mac_mc_entry(struct dsaf_device *dsaf_dev,
struct dsaf_drv_tbl_tcam_key mac_key;
struct dsaf_tbl_tcam_mcast_cfg mac_data;
+ struct dsaf_tbl_tcam_data tcam_data;
/*check mac addr */
if (MAC_IS_ALL_ZEROS(mac_entry->addr) ||
@@ -1965,8 +2183,10 @@ int hns_dsaf_get_mac_mc_entry(struct dsaf_device *dsaf_dev,
mac_key.low.val, entry_index);
/*read entry */
- hns_dsaf_tcam_mc_get(dsaf_dev, entry_index,
- (struct dsaf_tbl_tcam_data *)&mac_key, &mac_data);
+ hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, &mac_data);
+
+ mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
+ mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
mac_entry->port_mask[0] = mac_data.tbl_mcast_port_msk[0] & 0x3F;
return 0;
@@ -1986,9 +2206,10 @@ int hns_dsaf_get_mac_entry_by_index(
struct dsaf_tbl_tcam_mcast_cfg mac_data;
struct dsaf_tbl_tcam_ucast_cfg mac_uc_data;
- char mac_addr[MAC_NUM_OCTETS_PER_ADDR] = {0};
+ struct dsaf_tbl_tcam_data tcam_data;
+ char mac_addr[ETH_ALEN] = {0};
- if (entry_index >= DSAF_TCAM_SUM) {
+ if (entry_index >= dsaf_dev->tcam_max_num) {
/* find none, del error */
dev_err(dsaf_dev->dev, "get_uc_entry failed, %s\n",
dsaf_dev->ae_dev.name);
@@ -1996,8 +2217,10 @@ int hns_dsaf_get_mac_entry_by_index(
}
/* mc entry, do read opt */
- hns_dsaf_tcam_mc_get(dsaf_dev, entry_index,
- (struct dsaf_tbl_tcam_data *)&mac_key, &mac_data);
+ hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, &mac_data);
+
+ mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
+ mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
mac_entry->port_mask[0] = mac_data.tbl_mcast_port_msk[0] & 0x3F;
@@ -2014,9 +2237,12 @@ int hns_dsaf_get_mac_entry_by_index(
/**mc donot do*/
} else {
/*is not mc, just uc... */
- hns_dsaf_tcam_uc_get(dsaf_dev, entry_index,
- (struct dsaf_tbl_tcam_data *)&mac_key,
+ hns_dsaf_tcam_uc_get(dsaf_dev, entry_index, &tcam_data,
&mac_uc_data);
+
+ mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
+ mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
+
mac_entry->port_mask[0] = (1 << mac_uc_data.tbl_ucast_out_port);
}
@@ -2680,6 +2906,59 @@ int hns_dsaf_get_regs_count(void)
return DSAF_DUMP_REGS_NUM;
}
+/* Reserve the last TCAM entry for promisc support */
+#define dsaf_promisc_tcam_entry(port) \
+ (DSAF_TCAM_SUM - DSAFV2_MAC_FUZZY_TCAM_NUM + (port))
+void hns_dsaf_set_promisc_tcam(struct dsaf_device *dsaf_dev,
+ u32 port, bool enable)
+{
+ struct dsaf_drv_priv *priv = hns_dsaf_dev_priv(dsaf_dev);
+ struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl;
+ u16 entry_index;
+ struct dsaf_drv_tbl_tcam_key tbl_tcam_data, tbl_tcam_mask;
+ struct dsaf_tbl_tcam_mcast_cfg mac_data = {0};
+
+ if ((AE_IS_VER1(dsaf_dev->dsaf_ver)) || HNS_DSAF_IS_DEBUG(dsaf_dev))
+ return;
+
+ /* find the tcam entry index for promisc */
+ entry_index = dsaf_promisc_tcam_entry(port);
+
+ /* config key mask */
+ if (enable) {
+ memset(&tbl_tcam_data, 0, sizeof(tbl_tcam_data));
+ memset(&tbl_tcam_mask, 0, sizeof(tbl_tcam_mask));
+ dsaf_set_field(tbl_tcam_data.low.bits.port_vlan,
+ DSAF_TBL_TCAM_KEY_PORT_M,
+ DSAF_TBL_TCAM_KEY_PORT_S, port);
+ dsaf_set_field(tbl_tcam_mask.low.bits.port_vlan,
+ DSAF_TBL_TCAM_KEY_PORT_M,
+ DSAF_TBL_TCAM_KEY_PORT_S, 0xf);
+
+ /* SUB_QID */
+ dsaf_set_bit(mac_data.tbl_mcast_port_msk[0],
+ DSAF_SERVICE_NW_NUM, true);
+ mac_data.tbl_mcast_item_vld = true; /* item_vld bit */
+ } else {
+ mac_data.tbl_mcast_item_vld = false; /* item_vld bit */
+ }
+
+ dev_dbg(dsaf_dev->dev,
+ "set_promisc_entry, %s Mac key(%#x:%#x) entry_index%d\n",
+ dsaf_dev->ae_dev.name, tbl_tcam_data.high.val,
+ tbl_tcam_data.low.val, entry_index);
+
+ /* config promisc entry with mask */
+ hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index,
+ (struct dsaf_tbl_tcam_data *)&tbl_tcam_data,
+ (struct dsaf_tbl_tcam_data *)&tbl_tcam_mask,
+ &mac_data);
+
+ /* config software entry */
+ soft_mac_entry += entry_index;
+ soft_mac_entry->index = enable ? entry_index : DSAF_INVALID_ENTRY_IDX;
+}
+
/**
* dsaf_probe - probo dsaf dev
* @pdev: dasf platform device
@@ -2761,6 +3040,7 @@ static const struct of_device_id g_dsaf_match[] = {
{.compatible = "hisilicon,hns-dsaf-v2"},
{}
};
+MODULE_DEVICE_TABLE(of, g_dsaf_match);
static struct platform_driver g_dsaf_driver = {
.probe = hns_dsaf_probe,
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
index 35df187..cef6bf4 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
@@ -35,8 +35,6 @@ struct hns_mac_cb;
#define DSAF_CFG_READ_CNT 30
-#define MAC_NUM_OCTETS_PER_ADDR 6
-
#define DSAF_DUMP_REGS_NUM 504
#define DSAF_STATIC_NUM 28
#define DSAF_V2_STATIC_NUM 44
@@ -165,7 +163,7 @@ enum dsaf_mode {
/*mac entry, mc or uc entry*/
struct dsaf_drv_mac_single_dest_entry {
/* mac addr, match the entry*/
- u8 addr[MAC_NUM_OCTETS_PER_ADDR];
+ u8 addr[ETH_ALEN];
u16 in_vlan_id; /* value of VlanId */
/* the vld input port num, dsaf-mode fix 0, */
@@ -179,7 +177,7 @@ struct dsaf_drv_mac_single_dest_entry {
/*only mc entry*/
struct dsaf_drv_mac_multi_dest_entry {
/* mac addr, match the entry*/
- u8 addr[MAC_NUM_OCTETS_PER_ADDR];
+ u8 addr[ETH_ALEN];
u16 in_vlan_id;
/* this mac addr output port,*/
/* bit0-bit5 means Port0-Port5(1bit is vld)**/
@@ -308,8 +306,6 @@ struct dsaf_misc_op {
/* reset series function, it will be reset if the dereset is 0 */
void (*dsaf_reset)(struct dsaf_device *dsaf_dev, bool dereset);
void (*xge_srst)(struct dsaf_device *dsaf_dev, u32 port, bool dereset);
- void (*xge_core_srst)(struct dsaf_device *dsaf_dev, u32 port,
- bool dereset);
void (*ge_srst)(struct dsaf_device *dsaf_dev, u32 port, bool dereset);
void (*ppe_srst)(struct dsaf_device *dsaf_dev, u32 port, bool dereset);
void (*ppe_comm_srst)(struct dsaf_device *dsaf_dev, bool dereset);
@@ -343,6 +339,7 @@ struct dsaf_device {
enum hal_dsaf_mode dsaf_en;
enum hal_dsaf_tc_mode dsaf_tc_mode;
u32 dsaf_ver;
+ u16 tcam_max_num; /* max TCAM entry for user except promisc */
struct ppe_common_cb *ppe_common[DSAF_COMM_DEV_NUM];
struct rcb_common_cb *rcb_common[DSAF_COMM_DEV_NUM];
@@ -360,6 +357,11 @@ static inline void *hns_dsaf_dev_priv(const struct dsaf_device *dsaf_dev)
return (void *)((u8 *)dsaf_dev + sizeof(*dsaf_dev));
}
+#define DSAF_TBL_TCAM_KEY_PORT_S 0
+#define DSAF_TBL_TCAM_KEY_PORT_M (((1ULL << 4) - 1) << 0)
+#define DSAF_TBL_TCAM_KEY_VLAN_S 4
+#define DSAF_TBL_TCAM_KEY_VLAN_M (((1ULL << 12) - 1) << 4)
+
struct dsaf_drv_tbl_tcam_key {
union {
struct {
@@ -373,11 +375,9 @@ struct dsaf_drv_tbl_tcam_key {
} high;
union {
struct {
- u32 port:4; /* port id, */
- /* dsaf-mode fixed 0, non-dsaf-mode port id*/
- u32 vlan:12; /* vlan id */
- u32 mac_5:8;
- u32 mac_4:8;
+ u16 port_vlan;
+ u8 mac_5;
+ u8 mac_4;
} bits;
u32 val;
@@ -461,11 +461,19 @@ void hns_dsaf_get_strings(int stringset, u8 *data, int port,
void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data);
int hns_dsaf_get_regs_count(void);
void hns_dsaf_set_promisc_mode(struct dsaf_device *dsaf_dev, u32 en);
+void hns_dsaf_set_promisc_tcam(struct dsaf_device *dsaf_dev,
+ u32 port, bool enable);
void hns_dsaf_get_rx_mac_pause_en(struct dsaf_device *dsaf_dev, int mac_id,
u32 *en);
int hns_dsaf_set_rx_mac_pause_en(struct dsaf_device *dsaf_dev, int mac_id,
u32 en);
-void hns_dsaf_set_inner_lb(struct dsaf_device *dsaf_dev, u32 mac_id, u32 en);
+int hns_dsaf_rm_mac_addr(
+ struct dsaf_device *dsaf_dev,
+ struct dsaf_drv_mac_single_dest_entry *mac_entry);
+
+int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev,
+ u8 mac_id, u8 port_num);
+
#endif /* __HNS_DSAF_MAIN_H__ */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index 67accce..a2c22d0 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -23,7 +23,6 @@ enum _dsm_op_index {
enum _dsm_rst_type {
HNS_DSAF_RESET_FUNC = 0x1,
HNS_PPE_RESET_FUNC = 0x2,
- HNS_XGE_CORE_RESET_FUNC = 0x3,
HNS_XGE_RESET_FUNC = 0x4,
HNS_GE_RESET_FUNC = 0x5,
HNS_DSAF_CHN_RESET_FUNC = 0x6,
@@ -213,26 +212,6 @@ static void hns_dsaf_xge_srst_by_port_acpi(struct dsaf_device *dsaf_dev,
HNS_XGE_RESET_FUNC, port, dereset);
}
-static void hns_dsaf_xge_core_srst_by_port(struct dsaf_device *dsaf_dev,
- u32 port, bool dereset)
-{
- u32 reg_val = 0;
- u32 reg_addr;
-
- if (port >= DSAF_XGE_NUM)
- return;
-
- reg_val |= XGMAC_TRX_CORE_SRST_M
- << dsaf_dev->mac_cb[port]->port_rst_off;
-
- if (!dereset)
- reg_addr = DSAF_SUB_SC_XGE_RESET_REQ_REG;
- else
- reg_addr = DSAF_SUB_SC_XGE_RESET_DREQ_REG;
-
- dsaf_write_sub(dsaf_dev, reg_addr, reg_val);
-}
-
/**
* hns_dsaf_srst_chns - reset dsaf channels
* @dsaf_dev: dsaf device struct pointer
@@ -293,14 +272,6 @@ void hns_dsaf_roce_srst_acpi(struct dsaf_device *dsaf_dev, bool dereset)
HNS_ROCE_RESET_FUNC, 0, dereset);
}
-static void
-hns_dsaf_xge_core_srst_by_port_acpi(struct dsaf_device *dsaf_dev,
- u32 port, bool dereset)
-{
- hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC,
- HNS_XGE_CORE_RESET_FUNC, port, dereset);
-}
-
static void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port,
bool dereset)
{
@@ -597,7 +568,6 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev)
misc_op->dsaf_reset = hns_dsaf_rst;
misc_op->xge_srst = hns_dsaf_xge_srst_by_port;
- misc_op->xge_core_srst = hns_dsaf_xge_core_srst_by_port;
misc_op->ge_srst = hns_dsaf_ge_srst_by_port;
misc_op->ppe_srst = hns_ppe_srst_by_port;
misc_op->ppe_comm_srst = hns_ppe_com_srst;
@@ -615,7 +585,6 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev)
misc_op->dsaf_reset = hns_dsaf_rst_acpi;
misc_op->xge_srst = hns_dsaf_xge_srst_by_port_acpi;
- misc_op->xge_core_srst = hns_dsaf_xge_core_srst_by_port_acpi;
misc_op->ge_srst = hns_dsaf_ge_srst_by_port_acpi;
misc_op->ppe_srst = hns_ppe_srst_by_port_acpi;
misc_op->ppe_comm_srst = hns_ppe_com_srst;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index ef11077..f0ed80d6 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -543,6 +543,22 @@ int hns_rcb_set_coalesce_usecs(
"error: coalesce_usecs setting supports 0~1023us\n");
return -EINVAL;
}
+
+ if (!AE_IS_VER1(rcb_common->dsaf_dev->dsaf_ver)) {
+ if (timeout == 0)
+ /* set timeout to 0, Disable gap time */
+ dsaf_set_reg_field(rcb_common->io_base,
+ RCB_INT_GAP_TIME_REG + port_idx * 4,
+ PPE_INT_GAPTIME_M, PPE_INT_GAPTIME_B,
+ 0);
+ else
+ /* set timeout non 0, restore gap time to 1 */
+ dsaf_set_reg_field(rcb_common->io_base,
+ RCB_INT_GAP_TIME_REG + port_idx * 4,
+ PPE_INT_GAPTIME_M, PPE_INT_GAPTIME_B,
+ 1);
+ }
+
hns_rcb_set_port_timeout(rcb_common, port_idx, timeout);
return 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index 4b8b803..8722668 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -41,6 +41,9 @@
#define DSAF_SW_PORT_NUM 8
#define DSAF_TOTAL_QUEUE_NUM 129
+/* reserved a tcam entry for each port to support promisc by fuzzy match */
+#define DSAFV2_MAC_FUZZY_TCAM_NUM DSAF_MAX_PORT_NUM
+
#define DSAF_TCAM_SUM 512
#define DSAF_LINE_SUM (2048 * 14)
@@ -297,6 +300,8 @@
#define DSAF_TBL_LKUP_NUM_I_0_REG 0x50C0
#define DSAF_TBL_LKUP_NUM_O_0_REG 0x50E0
#define DSAF_TBL_UCAST_BCAST_MIS_INFO_0_0_REG 0x510C
+#define DSAF_TBL_TCAM_MATCH_CFG_H_REG 0x5130
+#define DSAF_TBL_TCAM_MATCH_CFG_L_REG 0x5134
#define DSAF_INODE_FIFO_WL_0_REG 0x6000
#define DSAF_ONODE_FIFO_WL_0_REG 0x6020
@@ -309,7 +314,6 @@
#define PPE_COM_INTEN_REG 0x110
#define PPE_COM_RINT_REG 0x114
#define PPE_COM_INTSTS_REG 0x118
-#define PPE_COM_COMMON_CNT_CLR_CE_REG 0x1120
#define PPE_COM_HIS_RX_PKT_QID_DROP_CNT_REG 0x300
#define PPE_COM_HIS_RX_PKT_QID_OK_CNT_REG 0x600
#define PPE_COM_HIS_TX_PKT_QID_ERR_CNT_REG 0x900
@@ -417,6 +421,7 @@
#define RCB_CFG_OVERTIME_REG 0x9300
#define RCB_CFG_PKTLINE_INT_NUM_REG 0x9304
#define RCB_CFG_OVERTIME_INT_NUM_REG 0x9308
+#define RCB_INT_GAP_TIME_REG 0x9400
#define RCB_PORT_CFG_OVERTIME_REG 0x9430
#define RCB_RING_RX_RING_BASEADDR_L_REG 0x00000
@@ -697,8 +702,6 @@
#define XGMAC_RX_SYMBOLERRPKTS 0x0210
#define XGMAC_RX_FCSERRPKTS 0x0218
-#define XGMAC_TRX_CORE_SRST_M 0x2080
-
#define DSAF_SRAM_INIT_OVER_M 0xff
#define DSAFV2_SRAM_INIT_OVER_M 0x3ff
#define DSAF_SRAM_INIT_OVER_S 0
@@ -898,6 +901,9 @@
#define PPE_CNT_CLR_CE_B 0
#define PPE_CNT_CLR_SNAP_EN_B 1
+#define PPE_INT_GAPTIME_B 0
+#define PPE_INT_GAPTIME_M 0x3ff
+
#define PPE_COMMON_CNT_CLR_CE_B 0
#define PPE_COMMON_CNT_CLR_SNAP_EN_B 1
#define RCB_COM_TSO_MODE_B 0
@@ -974,6 +980,11 @@
#define XGMAC_ENABLE_TX_B 0
#define XGMAC_ENABLE_RX_B 1
+#define XGMAC_UNIDIR_EN_B 0
+#define XGMAC_RF_TX_EN_B 1
+#define XGMAC_LF_RF_INSERT_S 2
+#define XGMAC_LF_RF_INSERT_M (0x3 << XGMAC_LF_RF_INSERT_S)
+
#define XGMAC_CTL_TX_FCS_B 0
#define XGMAC_CTL_TX_PAD_B 1
#define XGMAC_CTL_TX_PREAMBLE_TRANS_B 3
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
index 8f4f0e8..aae830a 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
@@ -108,6 +108,31 @@ static void hns_xgmac_rx_enable(struct mac_driver *drv, u32 value)
}
/**
+ * hns_xgmac_tx_lf_rf_insert - insert lf rf control about xgmac
+ * @mac_drv: mac driver
+ * @mode: inserf rf or lf
+ */
+static void hns_xgmac_lf_rf_insert(struct mac_driver *mac_drv, u32 mode)
+{
+ dsaf_set_dev_field(mac_drv, XGMAC_MAC_TX_LF_RF_CONTROL_REG,
+ XGMAC_LF_RF_INSERT_M, XGMAC_LF_RF_INSERT_S, mode);
+}
+
+/**
+ * hns_xgmac__lf_rf_control_init - initial the lf rf control register
+ * @mac_drv: mac driver
+ */
+static void hns_xgmac_lf_rf_control_init(struct mac_driver *mac_drv)
+{
+ u32 val = 0;
+
+ dsaf_set_bit(val, XGMAC_UNIDIR_EN_B, 0);
+ dsaf_set_bit(val, XGMAC_RF_TX_EN_B, 1);
+ dsaf_set_field(val, XGMAC_LF_RF_INSERT_M, XGMAC_LF_RF_INSERT_S, 0);
+ dsaf_write_reg(mac_drv, XGMAC_MAC_TX_LF_RF_CONTROL_REG, val);
+}
+
+/**
*hns_xgmac_enable - enable xgmac port
*@drv: mac driver
*@mode: mode of mac port
@@ -115,12 +140,8 @@ static void hns_xgmac_rx_enable(struct mac_driver *drv, u32 value)
static void hns_xgmac_enable(void *mac_drv, enum mac_commom_mode mode)
{
struct mac_driver *drv = (struct mac_driver *)mac_drv;
- struct dsaf_device *dsaf_dev
- = (struct dsaf_device *)dev_get_drvdata(drv->dev);
- u32 port = drv->mac_id;
- dsaf_dev->misc_op->xge_core_srst(dsaf_dev, port, 1);
- mdelay(10);
+ hns_xgmac_lf_rf_insert(drv, HNS_XGMAC_NO_LF_RF_INSERT);
/*enable XGE rX/tX */
if (mode == MAC_COMM_MODE_TX) {
@@ -143,9 +164,6 @@ static void hns_xgmac_enable(void *mac_drv, enum mac_commom_mode mode)
static void hns_xgmac_disable(void *mac_drv, enum mac_commom_mode mode)
{
struct mac_driver *drv = (struct mac_driver *)mac_drv;
- struct dsaf_device *dsaf_dev
- = (struct dsaf_device *)dev_get_drvdata(drv->dev);
- u32 port = drv->mac_id;
if (mode == MAC_COMM_MODE_TX) {
hns_xgmac_tx_enable(drv, 0);
@@ -155,9 +173,7 @@ static void hns_xgmac_disable(void *mac_drv, enum mac_commom_mode mode)
hns_xgmac_tx_enable(drv, 0);
hns_xgmac_rx_enable(drv, 0);
}
-
- mdelay(10);
- dsaf_dev->misc_op->xge_core_srst(dsaf_dev, port, 0);
+ hns_xgmac_lf_rf_insert(drv, HNS_XGMAC_LF_INSERT);
}
/**
@@ -203,6 +219,7 @@ static void hns_xgmac_init(void *mac_drv)
dsaf_dev->misc_op->xge_srst(dsaf_dev, port, 1);
mdelay(100);
+ hns_xgmac_lf_rf_control_init(drv);
hns_xgmac_exc_irq_en(drv, 0);
hns_xgmac_pma_fec_enable(drv, 0x0, 0x0);
@@ -788,7 +805,7 @@ static int hns_xgmac_get_sset_count(int stringset)
*/
static int hns_xgmac_get_regs_count(void)
{
- return ETH_XGMAC_DUMP_NUM;
+ return HNS_XGMAC_DUMP_NUM;
}
void *hns_xgmac_config(struct hns_mac_cb *mac_cb, struct mac_params *mac_param)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.h
index 139f729..da6c534 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.h
@@ -10,6 +10,7 @@
#ifndef _HNS_XGMAC_H
#define _HNS_XGMAC_H
-#define ETH_XGMAC_DUMP_NUM (214)
-
+#define HNS_XGMAC_DUMP_NUM 214
+#define HNS_XGMAC_NO_LF_RF_INSERT 0x0
+#define HNS_XGMAC_LF_INSERT 0x2
#endif
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index a720867..776d81e 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -575,7 +575,6 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
struct sk_buff *skb;
struct hnae_desc *desc;
struct hnae_desc_cb *desc_cb;
- struct ethhdr *eh;
unsigned char *va;
int bnum, length, i;
int pull_len;
@@ -601,7 +600,6 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
ring->stats.sw_err_cnt++;
return -ENOMEM;
}
- skb_reset_mac_header(skb);
prefetchw(skb->data);
length = le16_to_cpu(desc->rx.pkt_len);
@@ -683,14 +681,6 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
return -EFAULT;
}
- /* filter out multicast pkt with the same src mac as this port */
- eh = eth_hdr(skb);
- if (unlikely(is_multicast_ether_addr(eh->h_dest) &&
- ether_addr_equal(ndev->dev_addr, eh->h_source))) {
- dev_kfree_skb_any(skb);
- return -EFAULT;
- }
-
ring->stats.rx_pkts++;
ring->stats.rx_bytes += skb->len;
@@ -748,25 +738,37 @@ static void hns_nic_rx_up_pro(struct hns_nic_ring_data *ring_data,
ndev->last_rx = jiffies;
}
+static int hns_desc_unused(struct hnae_ring *ring)
+{
+ int ntc = ring->next_to_clean;
+ int ntu = ring->next_to_use;
+
+ return ((ntc >= ntu) ? 0 : ring->desc_num) + ntc - ntu;
+}
+
static int hns_nic_rx_poll_one(struct hns_nic_ring_data *ring_data,
int budget, void *v)
{
struct hnae_ring *ring = ring_data->ring;
struct sk_buff *skb;
- int num, bnum, ex_num;
+ int num, bnum;
#define RCB_NOF_ALLOC_RX_BUFF_ONCE 16
int recv_pkts, recv_bds, clean_count, err;
+ int unused_count = hns_desc_unused(ring);
num = readl_relaxed(ring->io_base + RCB_REG_FBDNUM);
rmb(); /* make sure num taken effect before the other data is touched */
recv_pkts = 0, recv_bds = 0, clean_count = 0;
-recv:
+ num -= unused_count;
+
while (recv_pkts < budget && recv_bds < num) {
/* reuse or realloc buffers */
- if (clean_count >= RCB_NOF_ALLOC_RX_BUFF_ONCE) {
- hns_nic_alloc_rx_buffers(ring_data, clean_count);
+ if (clean_count + unused_count >= RCB_NOF_ALLOC_RX_BUFF_ONCE) {
+ hns_nic_alloc_rx_buffers(ring_data,
+ clean_count + unused_count);
clean_count = 0;
+ unused_count = hns_desc_unused(ring);
}
/* poll one pkt */
@@ -787,21 +789,11 @@ static int hns_nic_rx_poll_one(struct hns_nic_ring_data *ring_data,
recv_pkts++;
}
- /* make all data has been write before submit */
- if (recv_pkts < budget) {
- ex_num = readl_relaxed(ring->io_base + RCB_REG_FBDNUM);
-
- if (ex_num > clean_count) {
- num += ex_num - clean_count;
- rmb(); /*complete read rx ring bd number*/
- goto recv;
- }
- }
-
out:
/* make all data has been write before submit */
- if (clean_count > 0)
- hns_nic_alloc_rx_buffers(ring_data, clean_count);
+ if (clean_count + unused_count > 0)
+ hns_nic_alloc_rx_buffers(ring_data,
+ clean_count + unused_count);
return recv_pkts;
}
@@ -811,6 +803,8 @@ static void hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data)
struct hnae_ring *ring = ring_data->ring;
int num = 0;
+ ring_data->ring->q->handle->dev->ops->toggle_ring_irq(ring, 0);
+
/* for hardware bug fixed */
num = readl_relaxed(ring->io_base + RCB_REG_FBDNUM);
@@ -822,6 +816,20 @@ static void hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data)
}
}
+static void hns_nic_rx_fini_pro_v2(struct hns_nic_ring_data *ring_data)
+{
+ struct hnae_ring *ring = ring_data->ring;
+ int num = 0;
+
+ num = readl_relaxed(ring->io_base + RCB_REG_FBDNUM);
+
+ if (num == 0)
+ ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
+ ring, 0);
+ else
+ napi_schedule(&ring_data->napi);
+}
+
static inline void hns_nic_reclaim_one_desc(struct hnae_ring *ring,
int *bytes, int *pkts)
{
@@ -923,7 +931,11 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
static void hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data)
{
struct hnae_ring *ring = ring_data->ring;
- int head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
+ int head;
+
+ ring_data->ring->q->handle->dev->ops->toggle_ring_irq(ring, 0);
+
+ head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
if (head != ring->next_to_clean) {
ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
@@ -933,6 +945,18 @@ static void hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data)
}
}
+static void hns_nic_tx_fini_pro_v2(struct hns_nic_ring_data *ring_data)
+{
+ struct hnae_ring *ring = ring_data->ring;
+ int head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
+
+ if (head == ring->next_to_clean)
+ ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
+ ring, 0);
+ else
+ napi_schedule(&ring_data->napi);
+}
+
static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
{
struct hnae_ring *ring = ring_data->ring;
@@ -964,10 +988,7 @@ static int hns_nic_common_poll(struct napi_struct *napi, int budget)
if (clean_complete >= 0 && clean_complete < budget) {
napi_complete(napi);
- ring_data->ring->q->handle->dev->ops->toggle_ring_irq(
- ring_data->ring, 0);
- if (ring_data->fini_process)
- ring_data->fini_process(ring_data);
+ ring_data->fini_process(ring_data);
return 0;
}
@@ -1472,6 +1493,29 @@ static netdev_features_t hns_nic_fix_features(
return features;
}
+static int hns_nic_uc_sync(struct net_device *netdev, const unsigned char *addr)
+{
+ struct hns_nic_priv *priv = netdev_priv(netdev);
+ struct hnae_handle *h = priv->ae_handle;
+
+ if (h->dev->ops->add_uc_addr)
+ return h->dev->ops->add_uc_addr(h, addr);
+
+ return 0;
+}
+
+static int hns_nic_uc_unsync(struct net_device *netdev,
+ const unsigned char *addr)
+{
+ struct hns_nic_priv *priv = netdev_priv(netdev);
+ struct hnae_handle *h = priv->ae_handle;
+
+ if (h->dev->ops->rm_uc_addr)
+ return h->dev->ops->rm_uc_addr(h, addr);
+
+ return 0;
+}
+
/**
* nic_set_multicast_list - set mutl mac address
* @netdev: net device
@@ -1490,6 +1534,10 @@ void hns_set_multicast_list(struct net_device *ndev)
return;
}
+ if (h->dev->ops->clr_mc_addr)
+ if (h->dev->ops->clr_mc_addr(h))
+ netdev_err(ndev, "clear multicast address fail\n");
+
if (h->dev->ops->set_mc_addr) {
netdev_for_each_mc_addr(ha, ndev)
if (h->dev->ops->set_mc_addr(h, ha->addr))
@@ -1510,6 +1558,9 @@ void hns_nic_set_rx_mode(struct net_device *ndev)
}
hns_set_multicast_list(ndev);
+
+ if (__dev_uc_sync(ndev, hns_nic_uc_sync, hns_nic_uc_unsync))
+ netdev_err(ndev, "sync uc address fail\n");
}
struct rtnl_link_stats64 *hns_nic_get_stats64(struct net_device *ndev,
@@ -1559,6 +1610,21 @@ struct rtnl_link_stats64 *hns_nic_get_stats64(struct net_device *ndev,
return stats;
}
+static u16
+hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb,
+ void *accel_priv, select_queue_fallback_t fallback)
+{
+ struct ethhdr *eth_hdr = (struct ethhdr *)skb->data;
+ struct hns_nic_priv *priv = netdev_priv(ndev);
+
+ /* fix hardware broadcast/multicast packets queue loopback */
+ if (!AE_IS_VER1(priv->enet_ver) &&
+ is_multicast_ether_addr(eth_hdr->h_dest))
+ return 0;
+ else
+ return fallback(ndev, skb);
+}
+
static const struct net_device_ops hns_nic_netdev_ops = {
.ndo_open = hns_nic_net_open,
.ndo_stop = hns_nic_net_stop,
@@ -1574,6 +1640,7 @@ static const struct net_device_ops hns_nic_netdev_ops = {
.ndo_poll_controller = hns_nic_poll_controller,
#endif
.ndo_set_rx_mode = hns_nic_set_rx_mode,
+ .ndo_select_queue = hns_nic_select_queue,
};
static void hns_nic_update_link_status(struct net_device *netdev)
@@ -1735,7 +1802,8 @@ static int hns_nic_init_ring_data(struct hns_nic_priv *priv)
rd->queue_index = i;
rd->ring = &h->qs[i]->tx_ring;
rd->poll_one = hns_nic_tx_poll_one;
- rd->fini_process = is_ver1 ? hns_nic_tx_fini_pro : NULL;
+ rd->fini_process = is_ver1 ? hns_nic_tx_fini_pro :
+ hns_nic_tx_fini_pro_v2;
netif_napi_add(priv->netdev, &rd->napi,
hns_nic_common_poll, NIC_TX_CLEAN_MAX_NUM);
@@ -1747,7 +1815,8 @@ static int hns_nic_init_ring_data(struct hns_nic_priv *priv)
rd->ring = &h->qs[i - h->q_num]->rx_ring;
rd->poll_one = hns_nic_rx_poll_one;
rd->ex_process = hns_nic_rx_up_pro;
- rd->fini_process = is_ver1 ? hns_nic_rx_fini_pro : NULL;
+ rd->fini_process = is_ver1 ? hns_nic_rx_fini_pro :
+ hns_nic_rx_fini_pro_v2;
netif_napi_add(priv->netdev, &rd->napi,
hns_nic_common_poll, NIC_RX_CLEAN_MAX_NUM);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 47e59bb..3ac2183 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -352,6 +352,13 @@ static int __lb_setup(struct net_device *ndev,
break;
}
+ if (!ret) {
+ if (loop == MAC_LOOP_NONE)
+ h->dev->ops->set_promisc_mode(
+ h, ndev->flags & IFF_PROMISC);
+ else
+ h->dev->ops->set_promisc_mode(h, 1);
+ }
return ret;
}
@@ -1171,7 +1178,8 @@ static int hns_nic_nway_reset(struct net_device *netdev)
struct phy_device *phy = netdev->phydev;
if (netif_running(netdev)) {
- if (phy)
+ /* if autoneg is disabled, don't restart auto-negotiation */
+ if (phy && phy->autoneg == AUTONEG_ENABLE)
ret = genphy_restart_aneg(phy);
}
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index 33f4c48..501eb20 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -563,6 +563,7 @@ static const struct of_device_id hns_mdio_match[] = {
{.compatible = "hisilicon,hns-mdio"},
{}
};
+MODULE_DEVICE_TABLE(of, hns_mdio_match);
static const struct acpi_device_id hns_mdio_acpi_match[] = {
{ "HISI0141", 0 },
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index e9719ba..fa66fa6 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -2438,6 +2438,8 @@ static int ehea_open(struct net_device *dev)
netif_info(port, ifup, dev, "enabling port\n");
+ netif_carrier_off(dev);
+
ret = ehea_up(dev);
if (!ret) {
port_napi_enable(port);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 657206b..1e486d1 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1178,7 +1178,7 @@ static struct ibmvnic_sub_crq_queue *init_sub_crq_queue(struct ibmvnic_adapter
if (!scrq)
return NULL;
- scrq->msgs = (union sub_crq *)__get_free_pages(GFP_KERNEL, 2);
+ scrq->msgs = (union sub_crq *)__get_free_pages(GFP_ATOMIC, 2);
memset(scrq->msgs, 0, 4 * PAGE_SIZE);
if (!scrq->msgs) {
dev_warn(dev, "Couldn't allocate crq queue messages page\n");
@@ -1449,14 +1449,16 @@ static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter)
return rc;
req_rx_irq_failed:
- for (j = 0; j < i; j++)
+ for (j = 0; j < i; j++) {
free_irq(adapter->rx_scrq[j]->irq, adapter->rx_scrq[j]);
irq_dispose_mapping(adapter->rx_scrq[j]->irq);
+ }
i = adapter->req_tx_queues;
req_tx_irq_failed:
- for (j = 0; j < i; j++)
+ for (j = 0; j < i; j++) {
free_irq(adapter->tx_scrq[j]->irq, adapter->tx_scrq[j]);
irq_dispose_mapping(adapter->rx_scrq[j]->irq);
+ }
release_sub_crqs_no_irqs(adapter);
return rc;
}
@@ -1491,9 +1493,8 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
adapter->max_rx_add_entries_per_subcrq > entries_page ?
entries_page : adapter->max_rx_add_entries_per_subcrq;
- /* Choosing the maximum number of queues supported by firmware*/
- adapter->req_tx_queues = adapter->max_tx_queues;
- adapter->req_rx_queues = adapter->max_rx_queues;
+ adapter->req_tx_queues = adapter->opt_tx_comp_sub_queues;
+ adapter->req_rx_queues = adapter->opt_rx_comp_queues;
adapter->req_rx_add_queues = adapter->max_rx_add_queues;
adapter->req_mtu = adapter->max_mtu;
@@ -3222,6 +3223,27 @@ static void ibmvnic_free_inflight(struct ibmvnic_adapter *adapter)
spin_unlock_irqrestore(&adapter->inflight_lock, flags);
}
+static void ibmvnic_xport_event(struct work_struct *work)
+{
+ struct ibmvnic_adapter *adapter = container_of(work,
+ struct ibmvnic_adapter,
+ ibmvnic_xport);
+ struct device *dev = &adapter->vdev->dev;
+ long rc;
+
+ ibmvnic_free_inflight(adapter);
+ release_sub_crqs(adapter);
+ if (adapter->migrated) {
+ rc = ibmvnic_reenable_crq_queue(adapter);
+ if (rc)
+ dev_err(dev, "Error after enable rc=%ld\n", rc);
+ adapter->migrated = false;
+ rc = ibmvnic_send_crq_init(adapter);
+ if (rc)
+ dev_err(dev, "Error sending init rc=%ld\n", rc);
+ }
+}
+
static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
struct ibmvnic_adapter *adapter)
{
@@ -3257,15 +3279,7 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
if (gen_crq->cmd == IBMVNIC_PARTITION_MIGRATED) {
dev_info(dev, "Re-enabling adapter\n");
adapter->migrated = true;
- ibmvnic_free_inflight(adapter);
- release_sub_crqs(adapter);
- rc = ibmvnic_reenable_crq_queue(adapter);
- if (rc)
- dev_err(dev, "Error after enable rc=%ld\n", rc);
- adapter->migrated = false;
- rc = ibmvnic_send_crq_init(adapter);
- if (rc)
- dev_err(dev, "Error sending init rc=%ld\n", rc);
+ schedule_work(&adapter->ibmvnic_xport);
} else if (gen_crq->cmd == IBMVNIC_DEVICE_FAILOVER) {
dev_info(dev, "Backing device failover detected\n");
netif_carrier_off(netdev);
@@ -3274,8 +3288,7 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
/* The adapter lost the connection */
dev_err(dev, "Virtual Adapter failed (rc=%d)\n",
gen_crq->cmd);
- ibmvnic_free_inflight(adapter);
- release_sub_crqs(adapter);
+ schedule_work(&adapter->ibmvnic_xport);
}
return;
case IBMVNIC_CRQ_CMD_RSP:
@@ -3644,6 +3657,7 @@ static void handle_crq_init_rsp(struct work_struct *work)
goto task_failed;
netdev->real_num_tx_queues = adapter->req_tx_queues;
+ netdev->mtu = adapter->req_mtu;
netdev->min_mtu = adapter->min_mtu;
netdev->max_mtu = adapter->max_mtu;
@@ -3683,7 +3697,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
struct net_device *netdev;
unsigned char *mac_addr_p;
struct dentry *ent;
- char buf[16]; /* debugfs name buf */
+ char buf[17]; /* debugfs name buf */
int rc;
dev_dbg(&dev->dev, "entering ibmvnic_probe for UA 0x%x\n",
@@ -3717,6 +3731,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
SET_NETDEV_DEV(netdev, &dev->dev);
INIT_WORK(&adapter->vnic_crq_init, handle_crq_init_rsp);
+ INIT_WORK(&adapter->ibmvnic_xport, ibmvnic_xport_event);
spin_lock_init(&adapter->stats_lock);
@@ -3784,6 +3799,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
}
netdev->real_num_tx_queues = adapter->req_tx_queues;
+ netdev->mtu = adapter->req_mtu;
rc = register_netdev(netdev);
if (rc) {
@@ -3820,6 +3836,9 @@ static int ibmvnic_remove(struct vio_dev *dev)
if (adapter->debugfs_dir && !IS_ERR(adapter->debugfs_dir))
debugfs_remove_recursive(adapter->debugfs_dir);
+ dma_unmap_single(&dev->dev, adapter->stats_token,
+ sizeof(struct ibmvnic_statistics), DMA_FROM_DEVICE);
+
if (adapter->ras_comps)
dma_free_coherent(&dev->dev,
adapter->ras_comp_num *
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index bfc84c7..dd775d9 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -27,7 +27,7 @@
/**************************************************************************/
#define IBMVNIC_NAME "ibmvnic"
-#define IBMVNIC_DRIVER_VERSION "1.0"
+#define IBMVNIC_DRIVER_VERSION "1.0.1"
#define IBMVNIC_INVALID_MAP -1
#define IBMVNIC_STATS_TIMEOUT 1
/* basic structures plus 100 2k buffers */
@@ -1048,5 +1048,6 @@ struct ibmvnic_adapter {
u8 map_id;
struct work_struct vnic_crq_init;
+ struct work_struct ibmvnic_xport;
bool failover;
};
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 01cce5b..29c2318 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -39,6 +39,7 @@
#include <linux/iommu.h>
#include <linux/slab.h>
#include <linux/list.h>
+#include <linux/hashtable.h>
#include <linux/string.h>
#include <linux/in.h>
#include <linux/ip.h>
@@ -92,6 +93,7 @@
#define I40E_AQ_LEN 256
#define I40E_AQ_WORK_LIMIT 66 /* max number of VFs + a little */
#define I40E_MAX_USER_PRIORITY 8
+#define I40E_DEFAULT_TRAFFIC_CLASS BIT(0)
#define I40E_DEFAULT_MSG_ENABLE 4
#define I40E_QUEUE_WAIT_RETRY_LIMIT 10
#define I40E_INT_NAME_STR_LEN (IFNAMSIZ + 16)
@@ -427,11 +429,13 @@ struct i40e_pf {
struct ptp_clock_info ptp_caps;
struct sk_buff *ptp_tx_skb;
struct hwtstamp_config tstamp_config;
- unsigned long last_rx_ptp_check;
- spinlock_t tmreg_lock; /* Used to protect the device time registers. */
+ struct mutex tmreg_lock; /* Used to protect the SYSTIME registers. */
u64 ptp_base_adj;
u32 tx_hwtstamp_timeouts;
u32 rx_hwtstamp_cleared;
+ u32 latch_event_flags;
+ spinlock_t ptp_rx_lock; /* Used to protect Rx timestamp registers. */
+ unsigned long latch_events[4];
bool ptp_tx;
bool ptp_rx;
u16 rss_table_size; /* HW RSS table size */
@@ -444,6 +448,20 @@ struct i40e_pf {
u16 phy_led_val;
};
+/**
+ * i40e_mac_to_hkey - Convert a 6-byte MAC Address to a u64 hash key
+ * @macaddr: the MAC Address as the base key
+ *
+ * Simply copies the address and returns it as a u64 for hashing
+ **/
+static inline u64 i40e_addr_to_hkey(const u8 *macaddr)
+{
+ u64 key = 0;
+
+ ether_addr_copy((u8 *)&key, macaddr);
+ return key;
+}
+
enum i40e_filter_state {
I40E_FILTER_INVALID = 0, /* Invalid state */
I40E_FILTER_NEW, /* New, not sent to FW yet */
@@ -453,13 +471,10 @@ enum i40e_filter_state {
/* There is no 'removed' state; the filter struct is freed */
};
struct i40e_mac_filter {
- struct list_head list;
+ struct hlist_node hlist;
u8 macaddr[ETH_ALEN];
#define I40E_VLAN_ANY -1
s16 vlan;
- u8 counter; /* number of instances of this filter */
- bool is_vf; /* filter belongs to a VF */
- bool is_netdev; /* filter belongs to a netdev */
enum i40e_filter_state state;
};
@@ -500,9 +515,11 @@ struct i40e_vsi {
#define I40E_VSI_FLAG_VEB_OWNER BIT(1)
unsigned long flags;
- /* Per VSI lock to protect elements/list (MAC filter) */
- spinlock_t mac_filter_list_lock;
- struct list_head mac_filter_list;
+ /* Per VSI lock to protect elements/hash (MAC filter) */
+ spinlock_t mac_filter_hash_lock;
+ /* Fixed size hash table with 2^8 buckets for MAC filters */
+ DECLARE_HASHTABLE(mac_filter_hash, 8);
+ bool has_vlan_filter;
/* VSI stats */
struct rtnl_link_stats64 net_stats;
@@ -706,6 +723,25 @@ int i40e_get_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
void i40e_fill_rss_lut(struct i40e_pf *pf, u8 *lut,
u16 rss_table_size, u16 rss_size);
struct i40e_vsi *i40e_find_vsi_from_id(struct i40e_pf *pf, u16 id);
+/**
+ * i40e_find_vsi_by_type - Find and return Flow Director VSI
+ * @pf: PF to search for VSI
+ * @type: Value indicating type of VSI we are looking for
+ **/
+static inline struct i40e_vsi *
+i40e_find_vsi_by_type(struct i40e_pf *pf, u16 type)
+{
+ int i;
+
+ for (i = 0; i < pf->num_alloc_vsi; i++) {
+ struct i40e_vsi *vsi = pf->vsi[i];
+
+ if (vsi && vsi->type == type)
+ return vsi;
+ }
+
+ return NULL;
+}
void i40e_update_stats(struct i40e_vsi *vsi);
void i40e_update_eth_stats(struct i40e_vsi *vsi);
struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi);
@@ -722,10 +758,8 @@ u32 i40e_get_global_fd_count(struct i40e_pf *pf);
bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features);
void i40e_set_ethtool_ops(struct net_device *netdev);
struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
- u8 *macaddr, s16 vlan,
- bool is_vf, bool is_netdev);
-void i40e_del_filter(struct i40e_vsi *vsi, u8 *macaddr, s16 vlan,
- bool is_vf, bool is_netdev);
+ const u8 *macaddr, s16 vlan);
+void i40e_del_filter(struct i40e_vsi *vsi, const u8 *macaddr, s16 vlan);
int i40e_sync_vsi_filters(struct i40e_vsi *vsi);
struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
u16 uplink, u32 param1);
@@ -739,7 +773,8 @@ void i40e_service_event_schedule(struct i40e_pf *pf);
void i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id,
u8 *msg, u16 len);
-int i40e_vsi_control_rings(struct i40e_vsi *vsi, bool enable);
+int i40e_vsi_start_rings(struct i40e_vsi *vsi);
+void i40e_vsi_stop_rings(struct i40e_vsi *vsi);
int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count);
struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags, u16 uplink_seid,
u16 downlink_seid, u8 enabled_tc);
@@ -815,14 +850,12 @@ int i40e_close(struct net_device *netdev);
int i40e_vsi_open(struct i40e_vsi *vsi);
void i40e_vlan_stripping_disable(struct i40e_vsi *vsi);
int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid);
-int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid);
-struct i40e_mac_filter *i40e_put_mac_in_vlan(struct i40e_vsi *vsi, u8 *macaddr,
- bool is_vf, bool is_netdev);
-int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, u8 *macaddr,
- bool is_vf, bool is_netdev);
+void i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid);
+struct i40e_mac_filter *i40e_put_mac_in_vlan(struct i40e_vsi *vsi,
+ const u8 *macaddr);
+int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, const u8 *macaddr);
bool i40e_is_vsi_in_vlan(struct i40e_vsi *vsi);
-struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, u8 *macaddr,
- bool is_vf, bool is_netdev);
+struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, const u8 *macaddr);
#ifdef I40E_FCOE
int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
struct tc_to_netdev *tc);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index 738b42a..56fb272 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -964,11 +964,11 @@ i40e_status i40e_clean_arq_element(struct i40e_hw *hw,
desc = I40E_ADMINQ_DESC(hw->aq.arq, ntc);
desc_idx = ntc;
+ hw->aq.arq_last_status =
+ (enum i40e_admin_queue_err)le16_to_cpu(desc->retval);
flags = le16_to_cpu(desc->flags);
if (flags & I40E_AQ_FLAG_ERR) {
ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
- hw->aq.arq_last_status =
- (enum i40e_admin_queue_err)le16_to_cpu(desc->retval);
i40e_debug(hw,
I40E_DEBUG_AQ_MESSAGE,
"AQRX: Event received with error 0x%X.\n",
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index a475946..98791ba 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -3313,8 +3313,10 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff,
/* partition id is 1-based, and functions are evenly spread
* across the ports as partitions
*/
- hw->partition_id = (hw->pf_id / hw->num_ports) + 1;
- hw->num_partitions = num_functions / hw->num_ports;
+ if (hw->num_ports != 0) {
+ hw->partition_id = (hw->pf_id / hw->num_ports) + 1;
+ hw->num_partitions = num_functions / hw->num_ports;
+ }
/* additional HW specific goodies that might
* someday be HW version specific
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 0354632..b8a03a0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -134,7 +134,7 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
struct rtnl_link_stats64 *nstat;
struct i40e_mac_filter *f;
struct i40e_vsi *vsi;
- int i;
+ int i, bkt;
vsi = i40e_dbg_find_vsi(pf, seid);
if (!vsi) {
@@ -166,11 +166,11 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
pf->hw.mac.addr,
pf->hw.mac.san_addr,
pf->hw.mac.port_addr);
- list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) {
dev_info(&pf->pdev->dev,
- " mac_filter_list: %pM vid=%d, is_netdev=%d is_vf=%d counter=%d, state %s\n",
- f->macaddr, f->vlan, f->is_netdev, f->is_vf,
- f->counter, i40e_filter_state_string[f->state]);
+ " mac_filter_hash: %pM vid=%d, state %s\n",
+ f->macaddr, f->vlan,
+ i40e_filter_state_string[f->state]);
}
dev_info(&pf->pdev->dev, " active_filters %d, promisc_threshold %d, overflow promisc %s\n",
vsi->active_filters, vsi->promisc_threshold,
@@ -867,86 +867,6 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
dev_info(&pf->pdev->dev, "deleting relay %d\n", veb_seid);
i40e_veb_release(pf->veb[i]);
-
- } else if (strncmp(cmd_buf, "add macaddr", 11) == 0) {
- struct i40e_mac_filter *f;
- int vlan = 0;
- u8 ma[6];
- int ret;
-
- cnt = sscanf(&cmd_buf[11],
- "%i %hhx:%hhx:%hhx:%hhx:%hhx:%hhx %i",
- &vsi_seid,
- &ma[0], &ma[1], &ma[2], &ma[3], &ma[4], &ma[5],
- &vlan);
- if (cnt == 7) {
- vlan = 0;
- } else if (cnt != 8) {
- dev_info(&pf->pdev->dev,
- "add macaddr: bad command string, cnt=%d\n",
- cnt);
- goto command_write_done;
- }
-
- vsi = i40e_dbg_find_vsi(pf, vsi_seid);
- if (!vsi) {
- dev_info(&pf->pdev->dev,
- "add macaddr: VSI %d not found\n", vsi_seid);
- goto command_write_done;
- }
-
- spin_lock_bh(&vsi->mac_filter_list_lock);
- f = i40e_add_filter(vsi, ma, vlan, false, false);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
- ret = i40e_sync_vsi_filters(vsi);
- if (f && !ret)
- dev_info(&pf->pdev->dev,
- "add macaddr: %pM vlan=%d added to VSI %d\n",
- ma, vlan, vsi_seid);
- else
- dev_info(&pf->pdev->dev,
- "add macaddr: %pM vlan=%d to VSI %d failed, f=%p ret=%d\n",
- ma, vlan, vsi_seid, f, ret);
-
- } else if (strncmp(cmd_buf, "del macaddr", 11) == 0) {
- int vlan = 0;
- u8 ma[6];
- int ret;
-
- cnt = sscanf(&cmd_buf[11],
- "%i %hhx:%hhx:%hhx:%hhx:%hhx:%hhx %i",
- &vsi_seid,
- &ma[0], &ma[1], &ma[2], &ma[3], &ma[4], &ma[5],
- &vlan);
- if (cnt == 7) {
- vlan = 0;
- } else if (cnt != 8) {
- dev_info(&pf->pdev->dev,
- "del macaddr: bad command string, cnt=%d\n",
- cnt);
- goto command_write_done;
- }
-
- vsi = i40e_dbg_find_vsi(pf, vsi_seid);
- if (!vsi) {
- dev_info(&pf->pdev->dev,
- "del macaddr: VSI %d not found\n", vsi_seid);
- goto command_write_done;
- }
-
- spin_lock_bh(&vsi->mac_filter_list_lock);
- i40e_del_filter(vsi, ma, vlan, false, false);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
- ret = i40e_sync_vsi_filters(vsi);
- if (!ret)
- dev_info(&pf->pdev->dev,
- "del macaddr: %pM vlan=%d removed from VSI %d\n",
- ma, vlan, vsi_seid);
- else
- dev_info(&pf->pdev->dev,
- "del macaddr: %pM vlan=%d from VSI %d failed, ret=%d\n",
- ma, vlan, vsi_seid, ret);
-
} else if (strncmp(cmd_buf, "add pvid", 8) == 0) {
i40e_status ret;
u16 vid;
@@ -1615,8 +1535,6 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
dev_info(&pf->pdev->dev, " del vsi [vsi_seid]\n");
dev_info(&pf->pdev->dev, " add relay <uplink_seid> <vsi_seid>\n");
dev_info(&pf->pdev->dev, " del relay <relay_seid>\n");
- dev_info(&pf->pdev->dev, " add macaddr <vsi_seid> <aa:bb:cc:dd:ee:ff> [vlan]\n");
- dev_info(&pf->pdev->dev, " del macaddr <vsi_seid> <aa:bb:cc:dd:ee:ff> [vlan]\n");
dev_info(&pf->pdev->dev, " add pvid <vsi_seid> <vid>\n");
dev_info(&pf->pdev->dev, " del pvid <vsi_seid>\n");
dev_info(&pf->pdev->dev, " dump switch\n");
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index fb4fb52..b9e1162 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -216,7 +216,6 @@ enum i40e_ethtool_test_id {
I40E_ETH_TEST_REG = 0,
I40E_ETH_TEST_EEPROM,
I40E_ETH_TEST_INTR,
- I40E_ETH_TEST_LOOPBACK,
I40E_ETH_TEST_LINK,
};
@@ -224,7 +223,6 @@ static const char i40e_gstrings_test[][ETH_GSTRING_LEN] = {
"Register test (offline)",
"Eeprom test (offline)",
"Interrupt test (offline)",
- "Loopback test (offline)",
"Link test (on/offline)"
};
@@ -1744,17 +1742,6 @@ static int i40e_intr_test(struct net_device *netdev, u64 *data)
return *data;
}
-static int i40e_loopback_test(struct net_device *netdev, u64 *data)
-{
- struct i40e_netdev_priv *np = netdev_priv(netdev);
- struct i40e_pf *pf = np->vsi->back;
-
- netif_info(pf, hw, netdev, "loopback test not implemented\n");
- *data = 0;
-
- return *data;
-}
-
static inline bool i40e_active_vfs(struct i40e_pf *pf)
{
struct i40e_vf *vfs = pf->vf;
@@ -1768,17 +1755,7 @@ static inline bool i40e_active_vfs(struct i40e_pf *pf)
static inline bool i40e_active_vmdqs(struct i40e_pf *pf)
{
- struct i40e_vsi **vsi = pf->vsi;
- int i;
-
- for (i = 0; i < pf->num_alloc_vsi; i++) {
- if (!vsi[i])
- continue;
- if (vsi[i]->type == I40E_VSI_VMDQ2)
- return true;
- }
-
- return false;
+ return !!i40e_find_vsi_by_type(pf, I40E_VSI_VMDQ2);
}
static void i40e_diag_test(struct net_device *netdev,
@@ -1800,7 +1777,6 @@ static void i40e_diag_test(struct net_device *netdev,
data[I40E_ETH_TEST_REG] = 1;
data[I40E_ETH_TEST_EEPROM] = 1;
data[I40E_ETH_TEST_INTR] = 1;
- data[I40E_ETH_TEST_LOOPBACK] = 1;
data[I40E_ETH_TEST_LINK] = 1;
eth_test->flags |= ETH_TEST_FL_FAILED;
clear_bit(__I40E_TESTING, &pf->state);
@@ -1828,9 +1804,6 @@ static void i40e_diag_test(struct net_device *netdev,
if (i40e_intr_test(netdev, &data[I40E_ETH_TEST_INTR]))
eth_test->flags |= ETH_TEST_FL_FAILED;
- if (i40e_loopback_test(netdev, &data[I40E_ETH_TEST_LOOPBACK]))
- eth_test->flags |= ETH_TEST_FL_FAILED;
-
/* run reg test last, a reset is required after it */
if (i40e_reg_test(netdev, &data[I40E_ETH_TEST_REG]))
eth_test->flags |= ETH_TEST_FL_FAILED;
@@ -1851,7 +1824,6 @@ static void i40e_diag_test(struct net_device *netdev,
data[I40E_ETH_TEST_REG] = 0;
data[I40E_ETH_TEST_EEPROM] = 0;
data[I40E_ETH_TEST_INTR] = 0;
- data[I40E_ETH_TEST_LOOPBACK] = 0;
}
skip_ol_tests:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
index 58e6c15..b077ef8b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
@@ -1522,12 +1522,12 @@ void i40e_fcoe_config_netdev(struct net_device *netdev, struct i40e_vsi *vsi)
* same PCI function.
*/
netdev->dev_port = 1;
- spin_lock_bh(&vsi->mac_filter_list_lock);
- i40e_add_filter(vsi, hw->mac.san_addr, 0, false, false);
- i40e_add_filter(vsi, (u8[6]) FC_FCOE_FLOGI_MAC, 0, false, false);
- i40e_add_filter(vsi, FIP_ALL_FCOE_MACS, 0, false, false);
- i40e_add_filter(vsi, FIP_ALL_ENODE_MACS, 0, false, false);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
+ i40e_add_filter(vsi, hw->mac.san_addr, 0);
+ i40e_add_filter(vsi, (u8[6]) FC_FCOE_FLOGI_MAC, 0);
+ i40e_add_filter(vsi, FIP_ALL_FCOE_MACS, 0);
+ i40e_add_filter(vsi, FIP_ALL_ENODE_MACS, 0);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
/* use san mac */
ether_addr_copy(netdev->dev_addr, hw->mac.san_addr);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 7fa535f..5c6a5ce 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1145,25 +1145,22 @@ void i40e_update_stats(struct i40e_vsi *vsi)
* @vsi: the VSI to be searched
* @macaddr: the MAC address
* @vlan: the vlan
- * @is_vf: make sure its a VF filter, else doesn't matter
- * @is_netdev: make sure its a netdev filter, else doesn't matter
*
* Returns ptr to the filter object or NULL
**/
static struct i40e_mac_filter *i40e_find_filter(struct i40e_vsi *vsi,
- u8 *macaddr, s16 vlan,
- bool is_vf, bool is_netdev)
+ const u8 *macaddr, s16 vlan)
{
struct i40e_mac_filter *f;
+ u64 key;
if (!vsi || !macaddr)
return NULL;
- list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ key = i40e_addr_to_hkey(macaddr);
+ hash_for_each_possible(vsi->mac_filter_hash, f, hlist, key) {
if ((ether_addr_equal(macaddr, f->macaddr)) &&
- (vlan == f->vlan) &&
- (!is_vf || f->is_vf) &&
- (!is_netdev || f->is_netdev))
+ (vlan == f->vlan))
return f;
}
return NULL;
@@ -1173,24 +1170,21 @@ static struct i40e_mac_filter *i40e_find_filter(struct i40e_vsi *vsi,
* i40e_find_mac - Find a mac addr in the macvlan filters list
* @vsi: the VSI to be searched
* @macaddr: the MAC address we are searching for
- * @is_vf: make sure its a VF filter, else doesn't matter
- * @is_netdev: make sure its a netdev filter, else doesn't matter
*
* Returns the first filter with the provided MAC address or NULL if
* MAC address was not found
**/
-struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, u8 *macaddr,
- bool is_vf, bool is_netdev)
+struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, const u8 *macaddr)
{
struct i40e_mac_filter *f;
+ u64 key;
if (!vsi || !macaddr)
return NULL;
- list_for_each_entry(f, &vsi->mac_filter_list, list) {
- if ((ether_addr_equal(macaddr, f->macaddr)) &&
- (!is_vf || f->is_vf) &&
- (!is_netdev || f->is_netdev))
+ key = i40e_addr_to_hkey(macaddr);
+ hash_for_each_possible(vsi->mac_filter_hash, f, hlist, key) {
+ if ((ether_addr_equal(macaddr, f->macaddr)))
return f;
}
return NULL;
@@ -1204,86 +1198,31 @@ struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, u8 *macaddr,
**/
bool i40e_is_vsi_in_vlan(struct i40e_vsi *vsi)
{
- struct i40e_mac_filter *f;
+ /* If we have a PVID, always operate in VLAN mode */
+ if (vsi->info.pvid)
+ return true;
- /* Only -1 for all the filters denotes not in vlan mode
- * so we have to go through all the list in order to make sure
+ /* We need to operate in VLAN mode whenever we have any filters with
+ * a VLAN other than I40E_VLAN_ALL. We could check the table each
+ * time, incurring search cost repeatedly. However, we can notice two
+ * things:
+ *
+ * 1) the only place where we can gain a VLAN filter is in
+ * i40e_add_filter.
+ *
+ * 2) the only place where filters are actually removed is in
+ * i40e_vsi_sync_filters_subtask.
+ *
+ * Thus, we can simply use a boolean value, has_vlan_filters which we
+ * will set to true when we add a VLAN filter in i40e_add_filter. Then
+ * we have to perform the full search after deleting filters in
+ * i40e_vsi_sync_filters_subtask, but we already have to search
+ * filters here and can perform the check at the same time. This
+ * results in avoiding embedding a loop for VLAN mode inside another
+ * loop over all the filters, and should maintain correctness as noted
+ * above.
*/
- list_for_each_entry(f, &vsi->mac_filter_list, list) {
- if (f->vlan >= 0 || vsi->info.pvid)
- return true;
- }
-
- return false;
-}
-
-/**
- * i40e_put_mac_in_vlan - Make macvlan filters from macaddrs and vlans
- * @vsi: the VSI to be searched
- * @macaddr: the mac address to be filtered
- * @is_vf: true if it is a VF
- * @is_netdev: true if it is a netdev
- *
- * Goes through all the macvlan filters and adds a
- * macvlan filter for each unique vlan that already exists
- *
- * Returns first filter found on success, else NULL
- **/
-struct i40e_mac_filter *i40e_put_mac_in_vlan(struct i40e_vsi *vsi, u8 *macaddr,
- bool is_vf, bool is_netdev)
-{
- struct i40e_mac_filter *f;
-
- list_for_each_entry(f, &vsi->mac_filter_list, list) {
- if (vsi->info.pvid)
- f->vlan = le16_to_cpu(vsi->info.pvid);
- if (!i40e_find_filter(vsi, macaddr, f->vlan,
- is_vf, is_netdev)) {
- if (!i40e_add_filter(vsi, macaddr, f->vlan,
- is_vf, is_netdev))
- return NULL;
- }
- }
-
- return list_first_entry_or_null(&vsi->mac_filter_list,
- struct i40e_mac_filter, list);
-}
-
-/**
- * i40e_del_mac_all_vlan - Remove a MAC filter from all VLANS
- * @vsi: the VSI to be searched
- * @macaddr: the mac address to be removed
- * @is_vf: true if it is a VF
- * @is_netdev: true if it is a netdev
- *
- * Removes a given MAC address from a VSI, regardless of VLAN
- *
- * Returns 0 for success, or error
- **/
-int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, u8 *macaddr,
- bool is_vf, bool is_netdev)
-{
- struct i40e_mac_filter *f = NULL;
- int changed = 0;
-
- WARN(!spin_is_locked(&vsi->mac_filter_list_lock),
- "Missing mac_filter_list_lock\n");
- list_for_each_entry(f, &vsi->mac_filter_list, list) {
- if ((ether_addr_equal(macaddr, f->macaddr)) &&
- (is_vf == f->is_vf) &&
- (is_netdev == f->is_netdev)) {
- f->counter--;
- changed = 1;
- if (f->counter == 0)
- f->state = I40E_FILTER_REMOVE;
- }
- }
- if (changed) {
- vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
- vsi->back->flags |= I40E_FLAG_FILTER_SYNC;
- return 0;
- }
- return -ENOENT;
+ return vsi->has_vlan_filter;
}
/**
@@ -1291,20 +1230,17 @@ int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, u8 *macaddr,
* @vsi: the VSI to be searched
* @macaddr: the MAC address
* @vlan: the vlan
- * @is_vf: make sure its a VF filter, else doesn't matter
- * @is_netdev: make sure its a netdev filter, else doesn't matter
*
* Returns ptr to the filter object or NULL when no memory available.
*
- * NOTE: This function is expected to be called with mac_filter_list_lock
+ * NOTE: This function is expected to be called with mac_filter_hash_lock
* being held.
**/
struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
- u8 *macaddr, s16 vlan,
- bool is_vf, bool is_netdev)
+ const u8 *macaddr, s16 vlan)
{
struct i40e_mac_filter *f;
- int changed = false;
+ u64 key;
if (!vsi || !macaddr)
return NULL;
@@ -1316,11 +1252,17 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
if (is_broadcast_ether_addr(macaddr))
return NULL;
- f = i40e_find_filter(vsi, macaddr, vlan, is_vf, is_netdev);
+ f = i40e_find_filter(vsi, macaddr, vlan);
if (!f) {
f = kzalloc(sizeof(*f), GFP_ATOMIC);
if (!f)
- goto add_filter_out;
+ return NULL;
+
+ /* Update the boolean indicating if we need to function in
+ * VLAN mode.
+ */
+ if (vlan >= 0)
+ vsi->has_vlan_filter = true;
ether_addr_copy(f->macaddr, macaddr);
f->vlan = vlan;
@@ -1332,100 +1274,148 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
f->state = I40E_FILTER_FAILED;
else
f->state = I40E_FILTER_NEW;
- changed = true;
- INIT_LIST_HEAD(&f->list);
- list_add_tail(&f->list, &vsi->mac_filter_list);
- }
+ INIT_HLIST_NODE(&f->hlist);
- /* increment counter and add a new flag if needed */
- if (is_vf) {
- if (!f->is_vf) {
- f->is_vf = true;
- f->counter++;
- }
- } else if (is_netdev) {
- if (!f->is_netdev) {
- f->is_netdev = true;
- f->counter++;
- }
- } else {
- f->counter++;
- }
+ key = i40e_addr_to_hkey(macaddr);
+ hash_add(vsi->mac_filter_hash, &f->hlist, key);
- if (changed) {
vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
vsi->back->flags |= I40E_FLAG_FILTER_SYNC;
}
-add_filter_out:
+ /* If we're asked to add a filter that has been marked for removal, it
+ * is safe to simply restore it to active state. __i40e_del_filter
+ * will have simply deleted any filters which were previously marked
+ * NEW or FAILED, so if it is currently marked REMOVE it must have
+ * previously been ACTIVE. Since we haven't yet run the sync filters
+ * task, just restore this filter to the ACTIVE state so that the
+ * sync task leaves it in place
+ */
+ if (f->state == I40E_FILTER_REMOVE)
+ f->state = I40E_FILTER_ACTIVE;
+
return f;
}
/**
- * i40e_del_filter - Remove a mac/vlan filter from the VSI
- * @vsi: the VSI to be searched
- * @macaddr: the MAC address
- * @vlan: the vlan
- * @is_vf: make sure it's a VF filter, else doesn't matter
- * @is_netdev: make sure it's a netdev filter, else doesn't matter
+ * __i40e_del_filter - Remove a specific filter from the VSI
+ * @vsi: VSI to remove from
+ * @f: the filter to remove from the list
*
- * NOTE: This function is expected to be called with mac_filter_list_lock
+ * This function should be called instead of i40e_del_filter only if you know
+ * the exact filter you will remove already, such as via i40e_find_filter or
+ * i40e_find_mac.
+ *
+ * NOTE: This function is expected to be called with mac_filter_hash_lock
* being held.
* ANOTHER NOTE: This function MUST be called from within the context of
* the "safe" variants of any list iterators, e.g. list_for_each_entry_safe()
* instead of list_for_each_entry().
**/
-void i40e_del_filter(struct i40e_vsi *vsi,
- u8 *macaddr, s16 vlan,
- bool is_vf, bool is_netdev)
+static void __i40e_del_filter(struct i40e_vsi *vsi, struct i40e_mac_filter *f)
+{
+ if (!f)
+ return;
+
+ if ((f->state == I40E_FILTER_FAILED) ||
+ (f->state == I40E_FILTER_NEW)) {
+ /* this one never got added by the FW. Just remove it,
+ * no need to sync anything.
+ */
+ hash_del(&f->hlist);
+ kfree(f);
+ } else {
+ f->state = I40E_FILTER_REMOVE;
+ vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
+ vsi->back->flags |= I40E_FLAG_FILTER_SYNC;
+ }
+}
+
+/**
+ * i40e_del_filter - Remove a MAC/VLAN filter from the VSI
+ * @vsi: the VSI to be searched
+ * @macaddr: the MAC address
+ * @vlan: the VLAN
+ *
+ * NOTE: This function is expected to be called with mac_filter_hash_lock
+ * being held.
+ * ANOTHER NOTE: This function MUST be called from within the context of
+ * the "safe" variants of any list iterators, e.g. list_for_each_entry_safe()
+ * instead of list_for_each_entry().
+ **/
+void i40e_del_filter(struct i40e_vsi *vsi, const u8 *macaddr, s16 vlan)
{
struct i40e_mac_filter *f;
if (!vsi || !macaddr)
return;
- f = i40e_find_filter(vsi, macaddr, vlan, is_vf, is_netdev);
- if (!f || f->counter == 0)
- return;
+ f = i40e_find_filter(vsi, macaddr, vlan);
+ __i40e_del_filter(vsi, f);
+}
- if (is_vf) {
- if (f->is_vf) {
- f->is_vf = false;
- f->counter--;
- }
- } else if (is_netdev) {
- if (f->is_netdev) {
- f->is_netdev = false;
- f->counter--;
- }
- } else {
- /* make sure we don't remove a filter in use by VF or netdev */
- int min_f = 0;
+/**
+ * i40e_put_mac_in_vlan - Make macvlan filters from macaddrs and vlans
+ * @vsi: the VSI to be searched
+ * @macaddr: the mac address to be filtered
+ *
+ * Goes through all the macvlan filters and adds a macvlan filter for each
+ * unique vlan that already exists. If a PVID has been assigned, instead only
+ * add the macaddr to that VLAN.
+ *
+ * Returns last filter added on success, else NULL
+ **/
+struct i40e_mac_filter *i40e_put_mac_in_vlan(struct i40e_vsi *vsi,
+ const u8 *macaddr)
+{
+ struct i40e_mac_filter *f, *add = NULL;
+ struct hlist_node *h;
+ int bkt;
- min_f += (f->is_vf ? 1 : 0);
- min_f += (f->is_netdev ? 1 : 0);
+ if (vsi->info.pvid)
+ return i40e_add_filter(vsi, macaddr,
+ le16_to_cpu(vsi->info.pvid));
- if (f->counter > min_f)
- f->counter--;
+ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
+ if (f->state == I40E_FILTER_REMOVE)
+ continue;
+ add = i40e_add_filter(vsi, macaddr, f->vlan);
+ if (!add)
+ return NULL;
}
- /* counter == 0 tells sync_filters_subtask to
- * remove the filter from the firmware's list
- */
- if (f->counter == 0) {
- if ((f->state == I40E_FILTER_FAILED) ||
- (f->state == I40E_FILTER_NEW)) {
- /* this one never got added by the FW. Just remove it,
- * no need to sync anything.
- */
- list_del(&f->list);
- kfree(f);
- } else {
- f->state = I40E_FILTER_REMOVE;
- vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
- vsi->back->flags |= I40E_FLAG_FILTER_SYNC;
+ return add;
+}
+
+/**
+ * i40e_del_mac_all_vlan - Remove a MAC filter from all VLANS
+ * @vsi: the VSI to be searched
+ * @macaddr: the mac address to be removed
+ *
+ * Removes a given MAC address from a VSI, regardless of VLAN
+ *
+ * Returns 0 for success, or error
+ **/
+int i40e_del_mac_all_vlan(struct i40e_vsi *vsi, const u8 *macaddr)
+{
+ struct i40e_mac_filter *f;
+ struct hlist_node *h;
+ bool found = false;
+ int bkt;
+
+ WARN(!spin_is_locked(&vsi->mac_filter_hash_lock),
+ "Missing mac_filter_hash_lock\n");
+ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
+ if (ether_addr_equal(macaddr, f->macaddr)) {
+ __i40e_del_filter(vsi, f);
+ found = true;
}
}
+
+ if (found)
+ return 0;
+ else
+ return -ENOENT;
}
/**
@@ -1466,10 +1456,10 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
else
netdev_info(netdev, "set new mac address %pM\n", addr->sa_data);
- spin_lock_bh(&vsi->mac_filter_list_lock);
- i40e_del_mac_all_vlan(vsi, netdev->dev_addr, false, true);
- i40e_put_mac_in_vlan(vsi, addr->sa_data, false, true);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
+ i40e_del_mac_all_vlan(vsi, netdev->dev_addr);
+ i40e_put_mac_in_vlan(vsi, addr->sa_data);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
ether_addr_copy(netdev->dev_addr, addr->sa_data);
if (vsi->type == I40E_VSI_MAIN) {
i40e_status ret;
@@ -1633,6 +1623,52 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
}
/**
+ * i40e_addr_sync - Callback for dev_(mc|uc)_sync to add address
+ * @netdev: the netdevice
+ * @addr: address to add
+ *
+ * Called by __dev_(mc|uc)_sync when an address needs to be added. We call
+ * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock.
+ */
+static int i40e_addr_sync(struct net_device *netdev, const u8 *addr)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_mac_filter *f;
+
+ if (i40e_is_vsi_in_vlan(vsi))
+ f = i40e_put_mac_in_vlan(vsi, addr);
+ else
+ f = i40e_add_filter(vsi, addr, I40E_VLAN_ANY);
+
+ if (f)
+ return 0;
+ else
+ return -ENOMEM;
+}
+
+/**
+ * i40e_addr_unsync - Callback for dev_(mc|uc)_sync to remove address
+ * @netdev: the netdevice
+ * @addr: address to add
+ *
+ * Called by __dev_(mc|uc)_sync when an address needs to be removed. We call
+ * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock.
+ */
+static int i40e_addr_unsync(struct net_device *netdev, const u8 *addr)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+
+ if (i40e_is_vsi_in_vlan(vsi))
+ i40e_del_mac_all_vlan(vsi, addr);
+ else
+ i40e_del_filter(vsi, addr, I40E_VLAN_ANY);
+
+ return 0;
+}
+
+/**
* i40e_set_rx_mode - NDO callback to set the netdev filters
* @netdev: network interface device structure
**/
@@ -1643,62 +1679,14 @@ static void i40e_set_rx_mode(struct net_device *netdev)
#endif
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
- struct i40e_mac_filter *f, *ftmp;
struct i40e_vsi *vsi = np->vsi;
- struct netdev_hw_addr *uca;
- struct netdev_hw_addr *mca;
- struct netdev_hw_addr *ha;
- spin_lock_bh(&vsi->mac_filter_list_lock);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
- /* add addr if not already in the filter list */
- netdev_for_each_uc_addr(uca, netdev) {
- if (!i40e_find_mac(vsi, uca->addr, false, true)) {
- if (i40e_is_vsi_in_vlan(vsi))
- i40e_put_mac_in_vlan(vsi, uca->addr,
- false, true);
- else
- i40e_add_filter(vsi, uca->addr, I40E_VLAN_ANY,
- false, true);
- }
- }
+ __dev_uc_sync(netdev, i40e_addr_sync, i40e_addr_unsync);
+ __dev_mc_sync(netdev, i40e_addr_sync, i40e_addr_unsync);
- netdev_for_each_mc_addr(mca, netdev) {
- if (!i40e_find_mac(vsi, mca->addr, false, true)) {
- if (i40e_is_vsi_in_vlan(vsi))
- i40e_put_mac_in_vlan(vsi, mca->addr,
- false, true);
- else
- i40e_add_filter(vsi, mca->addr, I40E_VLAN_ANY,
- false, true);
- }
- }
-
- /* remove filter if not in netdev list */
- list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
-
- if (!f->is_netdev)
- continue;
-
- netdev_for_each_mc_addr(mca, netdev)
- if (ether_addr_equal(mca->addr, f->macaddr))
- goto bottom_of_search_loop;
-
- netdev_for_each_uc_addr(uca, netdev)
- if (ether_addr_equal(uca->addr, f->macaddr))
- goto bottom_of_search_loop;
-
- for_each_dev_addr(netdev, ha)
- if (ether_addr_equal(ha->addr, f->macaddr))
- goto bottom_of_search_loop;
-
- /* f->macaddr wasn't found in uc, mc, or ha list so delete it */
- i40e_del_filter(vsi, f->macaddr, I40E_VLAN_ANY, false, true);
-
-bottom_of_search_loop:
- continue;
- }
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
/* check for other flag changes */
if (vsi->current_netdev_flags != vsi->netdev->flags) {
@@ -1713,21 +1701,26 @@ static void i40e_set_rx_mode(struct net_device *netdev)
}
/**
- * i40e_undo_del_filter_entries - Undo the changes made to MAC filter entries
- * @vsi: pointer to vsi struct
+ * i40e_undo_filter_entries - Undo the changes made to MAC filter entries
+ * @vsi: Pointer to VSI struct
* @from: Pointer to list which contains MAC filter entries - changes to
* those entries needs to be undone.
*
- * MAC filter entries from list were slated to be removed from device.
+ * MAC filter entries from list were slated to be sent to firmware, either for
+ * addition or deletion.
**/
-static void i40e_undo_del_filter_entries(struct i40e_vsi *vsi,
- struct list_head *from)
+static void i40e_undo_filter_entries(struct i40e_vsi *vsi,
+ struct hlist_head *from)
{
- struct i40e_mac_filter *f, *ftmp;
+ struct i40e_mac_filter *f;
+ struct hlist_node *h;
- list_for_each_entry_safe(f, ftmp, from, list) {
+ hlist_for_each_entry_safe(f, h, from, hlist) {
+ u64 key = i40e_addr_to_hkey(f->macaddr);
+
/* Move the element back into MAC filter list*/
- list_move_tail(&f->list, &vsi->mac_filter_list);
+ hlist_del(&f->hlist);
+ hash_add(vsi->mac_filter_hash, &f->hlist, key);
}
}
@@ -1756,7 +1749,9 @@ i40e_update_filter_state(int count,
/* Everything's good, mark all filters active. */
for (i = 0; i < count ; i++) {
add_head->state = I40E_FILTER_ACTIVE;
- add_head = list_next_entry(add_head, list);
+ add_head = hlist_entry(add_head->hlist.next,
+ typeof(struct i40e_mac_filter),
+ hlist);
}
} else if (aq_err == I40E_AQ_RC_ENOSPC) {
/* Device ran out of filter space. Check the return value
@@ -1770,20 +1765,98 @@ i40e_update_filter_state(int count,
add_head->state = I40E_FILTER_ACTIVE;
retval++;
}
- add_head = list_next_entry(add_head, list);
+ add_head = hlist_entry(add_head->hlist.next,
+ typeof(struct i40e_mac_filter),
+ hlist);
}
} else {
/* Some other horrible thing happened, fail all filters */
retval = 0;
for (i = 0; i < count ; i++) {
add_head->state = I40E_FILTER_FAILED;
- add_head = list_next_entry(add_head, list);
+ add_head = hlist_entry(add_head->hlist.next,
+ typeof(struct i40e_mac_filter),
+ hlist);
}
}
return retval;
}
/**
+ * i40e_aqc_del_filters - Request firmware to delete a set of filters
+ * @vsi: ptr to the VSI
+ * @vsi_name: name to display in messages
+ * @list: the list of filters to send to firmware
+ * @num_del: the number of filters to delete
+ * @retval: Set to -EIO on failure to delete
+ *
+ * Send a request to firmware via AdminQ to delete a set of filters. Uses
+ * *retval instead of a return value so that success does not force ret_val to
+ * be set to 0. This ensures that a sequence of calls to this function
+ * preserve the previous value of *retval on successful delete.
+ */
+static
+void i40e_aqc_del_filters(struct i40e_vsi *vsi, const char *vsi_name,
+ struct i40e_aqc_remove_macvlan_element_data *list,
+ int num_del, int *retval)
+{
+ struct i40e_hw *hw = &vsi->back->hw;
+ i40e_status aq_ret;
+ int aq_err;
+
+ aq_ret = i40e_aq_remove_macvlan(hw, vsi->seid, list, num_del, NULL);
+ aq_err = hw->aq.asq_last_status;
+
+ /* Explicitly ignore and do not report when firmware returns ENOENT */
+ if (aq_ret && !(aq_err == I40E_AQ_RC_ENOENT)) {
+ *retval = -EIO;
+ dev_info(&vsi->back->pdev->dev,
+ "ignoring delete macvlan error on %s, err %s, aq_err %s\n",
+ vsi_name, i40e_stat_str(hw, aq_ret),
+ i40e_aq_str(hw, aq_err));
+ }
+}
+
+/**
+ * i40e_aqc_add_filters - Request firmware to add a set of filters
+ * @vsi: ptr to the VSI
+ * @vsi_name: name to display in messages
+ * @list: the list of filters to send to firmware
+ * @add_head: Position in the add hlist
+ * @num_add: the number of filters to add
+ * @promisc_change: set to true on exit if promiscuous mode was forced on
+ *
+ * Send a request to firmware via AdminQ to add a chunk of filters. Will set
+ * promisc_changed to true if the firmware has run out of space for more
+ * filters.
+ */
+static
+void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name,
+ struct i40e_aqc_add_macvlan_element_data *list,
+ struct i40e_mac_filter *add_head,
+ int num_add, bool *promisc_changed)
+{
+ struct i40e_hw *hw = &vsi->back->hw;
+ i40e_status aq_ret;
+ int aq_err, fcnt;
+
+ aq_ret = i40e_aq_add_macvlan(hw, vsi->seid, list, num_add, NULL);
+ aq_err = hw->aq.asq_last_status;
+ fcnt = i40e_update_filter_state(num_add, list, add_head, aq_ret);
+ vsi->active_filters += fcnt;
+
+ if (fcnt != num_add) {
+ *promisc_changed = true;
+ set_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state);
+ vsi->promisc_threshold = (vsi->active_filters * 3) / 4;
+ dev_warn(&vsi->back->pdev->dev,
+ "Error %s adding RX filters on %s, promiscuous mode forced on\n",
+ i40e_aq_str(hw, aq_err),
+ vsi_name);
+ }
+}
+
+/**
* i40e_sync_vsi_filters - Update the VSI filter list to the HW
* @vsi: ptr to the VSI
*
@@ -1793,22 +1866,25 @@ i40e_update_filter_state(int count,
**/
int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
{
- struct i40e_mac_filter *f, *ftmp, *add_head = NULL;
- struct list_head tmp_add_list, tmp_del_list;
+ struct hlist_head tmp_add_list, tmp_del_list;
+ struct i40e_mac_filter *f, *add_head = NULL;
struct i40e_hw *hw = &vsi->back->hw;
+ unsigned int vlan_any_filters = 0;
+ unsigned int non_vlan_filters = 0;
+ unsigned int vlan_filters = 0;
bool promisc_changed = false;
char vsi_name[16] = "PF";
int filter_list_len = 0;
- u32 changed_flags = 0;
i40e_status aq_ret = 0;
- int retval = 0;
+ u32 changed_flags = 0;
+ struct hlist_node *h;
struct i40e_pf *pf;
int num_add = 0;
int num_del = 0;
- int aq_err = 0;
+ int retval = 0;
u16 cmd_flags;
int list_size;
- int fcnt;
+ int bkt;
/* empty array typed pointers, kcalloc later */
struct i40e_aqc_add_macvlan_element_data *add_list;
@@ -1823,8 +1899,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
vsi->current_netdev_flags = vsi->netdev->flags;
}
- INIT_LIST_HEAD(&tmp_add_list);
- INIT_LIST_HEAD(&tmp_del_list);
+ INIT_HLIST_HEAD(&tmp_add_list);
+ INIT_HLIST_HEAD(&tmp_del_list);
if (vsi->type == I40E_VSI_SRIOV)
snprintf(vsi_name, sizeof(vsi_name) - 1, "VF %d", vsi->vf_id);
@@ -1834,41 +1910,98 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
if (vsi->flags & I40E_VSI_FLAG_FILTER_CHANGED) {
vsi->flags &= ~I40E_VSI_FLAG_FILTER_CHANGED;
- spin_lock_bh(&vsi->mac_filter_list_lock);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
/* Create a list of filters to delete. */
- list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
+ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
if (f->state == I40E_FILTER_REMOVE) {
- WARN_ON(f->counter != 0);
/* Move the element into temporary del_list */
- list_move_tail(&f->list, &tmp_del_list);
+ hash_del(&f->hlist);
+ hlist_add_head(&f->hlist, &tmp_del_list);
vsi->active_filters--;
+
+ /* Avoid counting removed filters */
+ continue;
}
if (f->state == I40E_FILTER_NEW) {
- WARN_ON(f->counter == 0);
- /* Move the element into temporary add_list */
- list_move_tail(&f->list, &tmp_add_list);
+ hash_del(&f->hlist);
+ hlist_add_head(&f->hlist, &tmp_add_list);
}
+
+ /* Count the number of each type of filter we have
+ * remaining, ignoring any filters we're about to
+ * delete.
+ */
+ if (f->vlan > 0)
+ vlan_filters++;
+ else if (!f->vlan)
+ non_vlan_filters++;
+ else
+ vlan_any_filters++;
}
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+
+ /* We should never have VLAN=-1 filters at the same time as we
+ * have either VLAN=0 or VLAN>0 filters, so warn about this
+ * case here to help catch any issues.
+ */
+ WARN_ON(vlan_any_filters && (vlan_filters + non_vlan_filters));
+
+ /* If we only have VLAN=0 filters remaining, and don't have
+ * any other VLAN filters, we need to convert these VLAN=0
+ * filters into VLAN=-1 (I40E_VLAN_ANY) so that we operate
+ * correctly in non-VLAN mode and receive all traffic tagged
+ * or untagged.
+ */
+ if (non_vlan_filters && !vlan_filters) {
+ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f,
+ hlist) {
+ /* Only replace VLAN=0 filters */
+ if (f->vlan)
+ continue;
+
+ /* Allocate a replacement element */
+ add_head = kzalloc(sizeof(*add_head),
+ GFP_KERNEL);
+ if (!add_head)
+ goto err_no_memory_locked;
+
+ /* Copy the filter, with new state and VLAN */
+ *add_head = *f;
+ add_head->state = I40E_FILTER_NEW;
+ add_head->vlan = I40E_VLAN_ANY;
+
+ /* Move the replacement to the add list */
+ INIT_HLIST_NODE(&add_head->hlist);
+ hlist_add_head(&add_head->hlist,
+ &tmp_add_list);
+
+ /* Move the original to the delete list */
+ f->state = I40E_FILTER_REMOVE;
+ hash_del(&f->hlist);
+ hlist_add_head(&f->hlist, &tmp_del_list);
+ vsi->active_filters--;
+ }
+
+ /* Also update any filters on the tmp_add list */
+ hlist_for_each_entry(f, &tmp_add_list, hlist) {
+ if (!f->vlan)
+ f->vlan = I40E_VLAN_ANY;
+ }
+ add_head = NULL;
+ }
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
}
/* Now process 'del_list' outside the lock */
- if (!list_empty(&tmp_del_list)) {
+ if (!hlist_empty(&tmp_del_list)) {
filter_list_len = hw->aq.asq_buf_size /
sizeof(struct i40e_aqc_remove_macvlan_element_data);
list_size = filter_list_len *
sizeof(struct i40e_aqc_remove_macvlan_element_data);
del_list = kzalloc(list_size, GFP_ATOMIC);
- if (!del_list) {
- /* Undo VSI's MAC filter entry element updates */
- spin_lock_bh(&vsi->mac_filter_list_lock);
- i40e_undo_del_filter_entries(vsi, &tmp_del_list);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
- retval = -ENOMEM;
- goto out;
- }
+ if (!del_list)
+ goto err_no_memory;
- list_for_each_entry_safe(f, ftmp, &tmp_del_list, list) {
+ hlist_for_each_entry_safe(f, h, &tmp_del_list, hlist) {
cmd_flags = 0;
/* add to delete list */
@@ -1887,68 +2020,47 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
/* flush a full buffer */
if (num_del == filter_list_len) {
- aq_ret = i40e_aq_remove_macvlan(hw, vsi->seid,
- del_list,
- num_del, NULL);
- aq_err = hw->aq.asq_last_status;
- num_del = 0;
+ i40e_aqc_del_filters(vsi, vsi_name, del_list,
+ num_del, &retval);
memset(del_list, 0, list_size);
-
- /* Explicitly ignore and do not report when
- * firmware returns ENOENT.
- */
- if (aq_ret && !(aq_err == I40E_AQ_RC_ENOENT)) {
- retval = -EIO;
- dev_info(&pf->pdev->dev,
- "ignoring delete macvlan error on %s, err %s, aq_err %s\n",
- vsi_name,
- i40e_stat_str(hw, aq_ret),
- i40e_aq_str(hw, aq_err));
- }
+ num_del = 0;
}
/* Release memory for MAC filter entries which were
* synced up with HW.
*/
- list_del(&f->list);
+ hlist_del(&f->hlist);
kfree(f);
}
if (num_del) {
- aq_ret = i40e_aq_remove_macvlan(hw, vsi->seid, del_list,
- num_del, NULL);
- aq_err = hw->aq.asq_last_status;
- num_del = 0;
-
- /* Explicitly ignore and do not report when firmware
- * returns ENOENT.
- */
- if (aq_ret && !(aq_err == I40E_AQ_RC_ENOENT)) {
- retval = -EIO;
- dev_info(&pf->pdev->dev,
- "ignoring delete macvlan error on %s, err %s aq_err %s\n",
- vsi_name,
- i40e_stat_str(hw, aq_ret),
- i40e_aq_str(hw, aq_err));
- }
+ i40e_aqc_del_filters(vsi, vsi_name, del_list,
+ num_del, &retval);
}
kfree(del_list);
del_list = NULL;
}
- if (!list_empty(&tmp_add_list)) {
+ /* After finishing notifying firmware of the deleted filters, update
+ * the cached value of vsi->has_vlan_filter. Note that we are safe to
+ * use just !!vlan_filters here because if we only have VLAN=0 (that
+ * is, non_vlan_filters) these will all be converted to VLAN=-1 in the
+ * logic above already so this value would still be correct.
+ */
+ vsi->has_vlan_filter = !!vlan_filters;
+
+ if (!hlist_empty(&tmp_add_list)) {
/* Do all the adds now. */
filter_list_len = hw->aq.asq_buf_size /
sizeof(struct i40e_aqc_add_macvlan_element_data);
list_size = filter_list_len *
sizeof(struct i40e_aqc_add_macvlan_element_data);
add_list = kzalloc(list_size, GFP_ATOMIC);
- if (!add_list) {
- retval = -ENOMEM;
- goto out;
- }
+ if (!add_list)
+ goto err_no_memory;
+
num_add = 0;
- list_for_each_entry(f, &tmp_add_list, list) {
+ hlist_for_each_entry(f, &tmp_add_list, hlist) {
if (test_bit(__I40E_FILTER_OVERFLOW_PROMISC,
&vsi->state)) {
f->state = I40E_FILTER_FAILED;
@@ -1973,57 +2085,28 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
/* flush a full buffer */
if (num_add == filter_list_len) {
- aq_ret = i40e_aq_add_macvlan(hw, vsi->seid,
- add_list, num_add,
- NULL);
- aq_err = hw->aq.asq_last_status;
- fcnt = i40e_update_filter_state(num_add,
- add_list,
- add_head,
- aq_ret);
- vsi->active_filters += fcnt;
-
- if (fcnt != num_add) {
- promisc_changed = true;
- set_bit(__I40E_FILTER_OVERFLOW_PROMISC,
- &vsi->state);
- vsi->promisc_threshold =
- (vsi->active_filters * 3) / 4;
- dev_warn(&pf->pdev->dev,
- "Error %s adding RX filters on %s, promiscuous mode forced on\n",
- i40e_aq_str(hw, aq_err),
- vsi_name);
- }
+ i40e_aqc_add_filters(vsi, vsi_name, add_list,
+ add_head, num_add,
+ &promisc_changed);
memset(add_list, 0, list_size);
num_add = 0;
}
}
if (num_add) {
- aq_ret = i40e_aq_add_macvlan(hw, vsi->seid,
- add_list, num_add, NULL);
- aq_err = hw->aq.asq_last_status;
- fcnt = i40e_update_filter_state(num_add, add_list,
- add_head, aq_ret);
- vsi->active_filters += fcnt;
- if (fcnt != num_add) {
- promisc_changed = true;
- set_bit(__I40E_FILTER_OVERFLOW_PROMISC,
- &vsi->state);
- vsi->promisc_threshold =
- (vsi->active_filters * 3) / 4;
- dev_warn(&pf->pdev->dev,
- "Error %s adding RX filters on %s, promiscuous mode forced on\n",
- i40e_aq_str(hw, aq_err), vsi_name);
- }
+ i40e_aqc_add_filters(vsi, vsi_name, add_list, add_head,
+ num_add, &promisc_changed);
}
/* Now move all of the filters from the temp add list back to
* the VSI's list.
*/
- spin_lock_bh(&vsi->mac_filter_list_lock);
- list_for_each_entry_safe(f, ftmp, &tmp_add_list, list) {
- list_move_tail(&f->list, &vsi->mac_filter_list);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
+ hlist_for_each_entry_safe(f, h, &tmp_add_list, hlist) {
+ u64 key = i40e_addr_to_hkey(f->macaddr);
+
+ hlist_del(&f->hlist);
+ hash_add(vsi->mac_filter_hash, &f->hlist, key);
}
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
kfree(add_list);
add_list = NULL;
}
@@ -2035,12 +2118,12 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
/* See if we have any failed filters. We can't drop out of
* promiscuous until these have all been deleted.
*/
- spin_lock_bh(&vsi->mac_filter_list_lock);
- list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
+ hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) {
if (f->state == I40E_FILTER_FAILED)
failed_count++;
}
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
if (!failed_count) {
dev_info(&pf->pdev->dev,
"filter logjam cleared on %s, leaving overflow promiscuous mode\n",
@@ -2168,6 +2251,18 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
clear_bit(__I40E_CONFIG_BUSY, &vsi->state);
return retval;
+
+err_no_memory:
+ /* Restore elements on the temporary add and delete lists */
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
+err_no_memory_locked:
+ i40e_undo_filter_entries(vsi, &tmp_del_list);
+ i40e_undo_filter_entries(vsi, &tmp_add_list);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
+
+ vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
+ clear_bit(__I40E_CONFIG_BUSY, &vsi->state);
+ return -ENOMEM;
}
/**
@@ -2322,34 +2417,33 @@ static void i40e_vlan_rx_register(struct net_device *netdev, u32 features)
**/
int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid)
{
- struct i40e_mac_filter *f, *ftmp, *add_f;
- bool is_netdev, is_vf;
-
- is_vf = (vsi->type == I40E_VSI_SRIOV);
- is_netdev = !!(vsi->netdev);
+ struct i40e_mac_filter *f, *add_f, *del_f;
+ struct hlist_node *h;
+ int bkt;
/* Locked once because all functions invoked below iterates list*/
- spin_lock_bh(&vsi->mac_filter_list_lock);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
- if (is_netdev) {
- add_f = i40e_add_filter(vsi, vsi->netdev->dev_addr, vid,
- is_vf, is_netdev);
+ if (vsi->netdev) {
+ add_f = i40e_add_filter(vsi, vsi->netdev->dev_addr, vid);
if (!add_f) {
dev_info(&vsi->back->pdev->dev,
"Could not add vlan filter %d for %pM\n",
vid, vsi->netdev->dev_addr);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
return -ENOMEM;
}
}
- list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
- add_f = i40e_add_filter(vsi, f->macaddr, vid, is_vf, is_netdev);
+ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
+ if (f->state == I40E_FILTER_REMOVE)
+ continue;
+ add_f = i40e_add_filter(vsi, f->macaddr, vid);
if (!add_f) {
dev_info(&vsi->back->pdev->dev,
"Could not add vlan filter %d for %pM\n",
vid, f->macaddr);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
return -ENOMEM;
}
}
@@ -2359,19 +2453,17 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid)
* with 0, so we now accept untagged and specified tagged traffic
* (and not all tags along with untagged)
*/
- if (vid > 0) {
- if (is_netdev && i40e_find_filter(vsi, vsi->netdev->dev_addr,
- I40E_VLAN_ANY,
- is_vf, is_netdev)) {
- i40e_del_filter(vsi, vsi->netdev->dev_addr,
- I40E_VLAN_ANY, is_vf, is_netdev);
- add_f = i40e_add_filter(vsi, vsi->netdev->dev_addr, 0,
- is_vf, is_netdev);
+ if (vid > 0 && vsi->netdev) {
+ del_f = i40e_find_filter(vsi, vsi->netdev->dev_addr,
+ I40E_VLAN_ANY);
+ if (del_f) {
+ __i40e_del_filter(vsi, del_f);
+ add_f = i40e_add_filter(vsi, vsi->netdev->dev_addr, 0);
if (!add_f) {
dev_info(&vsi->back->pdev->dev,
"Could not add filter 0 for %pM\n",
vsi->netdev->dev_addr);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
return -ENOMEM;
}
}
@@ -2379,25 +2471,26 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid)
/* Do not assume that I40E_VLAN_ANY should be reset to VLAN 0 */
if (vid > 0 && !vsi->info.pvid) {
- list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
- if (!i40e_find_filter(vsi, f->macaddr, I40E_VLAN_ANY,
- is_vf, is_netdev))
+ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
+ if (f->state == I40E_FILTER_REMOVE)
continue;
- i40e_del_filter(vsi, f->macaddr, I40E_VLAN_ANY,
- is_vf, is_netdev);
- add_f = i40e_add_filter(vsi, f->macaddr,
- 0, is_vf, is_netdev);
+ del_f = i40e_find_filter(vsi, f->macaddr,
+ I40E_VLAN_ANY);
+ if (!del_f)
+ continue;
+ __i40e_del_filter(vsi, del_f);
+ add_f = i40e_add_filter(vsi, f->macaddr, 0);
if (!add_f) {
dev_info(&vsi->back->pdev->dev,
"Could not add filter 0 for %pM\n",
f->macaddr);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
return -ENOMEM;
}
}
}
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
/* schedule our worker thread which will take care of
* applying the new filter changes
@@ -2410,79 +2503,31 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid)
* i40e_vsi_kill_vlan - Remove vsi membership for given vlan
* @vsi: the vsi being configured
* @vid: vlan id to be removed (0 = untagged only , -1 = any)
- *
- * Return: 0 on success or negative otherwise
**/
-int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid)
+void i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid)
{
struct net_device *netdev = vsi->netdev;
- struct i40e_mac_filter *f, *ftmp, *add_f;
- bool is_vf, is_netdev;
- int filter_count = 0;
-
- is_vf = (vsi->type == I40E_VSI_SRIOV);
- is_netdev = !!(netdev);
+ struct i40e_mac_filter *f;
+ struct hlist_node *h;
+ int bkt;
/* Locked once because all functions invoked below iterates list */
- spin_lock_bh(&vsi->mac_filter_list_lock);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
- if (is_netdev)
- i40e_del_filter(vsi, netdev->dev_addr, vid, is_vf, is_netdev);
+ if (vsi->netdev)
+ i40e_del_filter(vsi, netdev->dev_addr, vid);
- list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list)
- i40e_del_filter(vsi, f->macaddr, vid, is_vf, is_netdev);
-
- /* go through all the filters for this VSI and if there is only
- * vid == 0 it means there are no other filters, so vid 0 must
- * be replaced with -1. This signifies that we should from now
- * on accept any traffic (with any tag present, or untagged)
- */
- list_for_each_entry(f, &vsi->mac_filter_list, list) {
- if (is_netdev) {
- if (f->vlan &&
- ether_addr_equal(netdev->dev_addr, f->macaddr))
- filter_count++;
- }
-
- if (f->vlan)
- filter_count++;
+ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
+ if (f->vlan == vid)
+ __i40e_del_filter(vsi, f);
}
- if (!filter_count && is_netdev) {
- i40e_del_filter(vsi, netdev->dev_addr, 0, is_vf, is_netdev);
- f = i40e_add_filter(vsi, netdev->dev_addr, I40E_VLAN_ANY,
- is_vf, is_netdev);
- if (!f) {
- dev_info(&vsi->back->pdev->dev,
- "Could not add filter %d for %pM\n",
- I40E_VLAN_ANY, netdev->dev_addr);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
- return -ENOMEM;
- }
- }
-
- if (!filter_count) {
- list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
- i40e_del_filter(vsi, f->macaddr, 0, is_vf, is_netdev);
- add_f = i40e_add_filter(vsi, f->macaddr, I40E_VLAN_ANY,
- is_vf, is_netdev);
- if (!add_f) {
- dev_info(&vsi->back->pdev->dev,
- "Could not add filter %d for %pM\n",
- I40E_VLAN_ANY, f->macaddr);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
- return -ENOMEM;
- }
- }
- }
-
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
/* schedule our worker thread which will take care of
* applying the new filter changes
*/
i40e_service_event_schedule(vsi->back);
- return 0;
}
/**
@@ -3969,30 +4014,36 @@ static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable)
}
/**
- * i40e_vsi_control_rings - Start or stop a VSI's rings
+ * i40e_vsi_start_rings - Start a VSI's rings
* @vsi: the VSI being configured
- * @enable: start or stop the rings
**/
-int i40e_vsi_control_rings(struct i40e_vsi *vsi, bool request)
+int i40e_vsi_start_rings(struct i40e_vsi *vsi)
{
int ret = 0;
/* do rx first for enable and last for disable */
- if (request) {
- ret = i40e_vsi_control_rx(vsi, request);
- if (ret)
- return ret;
- ret = i40e_vsi_control_tx(vsi, request);
- } else {
- /* Ignore return value, we need to shutdown whatever we can */
- i40e_vsi_control_tx(vsi, request);
- i40e_vsi_control_rx(vsi, request);
- }
+ ret = i40e_vsi_control_rx(vsi, true);
+ if (ret)
+ return ret;
+ ret = i40e_vsi_control_tx(vsi, true);
return ret;
}
/**
+ * i40e_vsi_stop_rings - Stop a VSI's rings
+ * @vsi: the VSI being configured
+ **/
+void i40e_vsi_stop_rings(struct i40e_vsi *vsi)
+{
+ /* do rx first for enable and last for disable
+ * Ignore return value, we need to shutdown whatever we can
+ */
+ i40e_vsi_control_tx(vsi, false);
+ i40e_vsi_control_rx(vsi, false);
+}
+
+/**
* i40e_vsi_free_irq - Free the irq association with the OS
* @vsi: the VSI being configured
**/
@@ -4641,29 +4692,6 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf)
}
/**
- * i40e_pf_get_default_tc - Get bitmap for first enabled TC
- * @pf: PF being queried
- *
- * Return a bitmap for first enabled traffic class for this PF.
- **/
-static u8 i40e_pf_get_default_tc(struct i40e_pf *pf)
-{
- u8 enabled_tc = pf->hw.func_caps.enabled_tcmap;
- u8 i = 0;
-
- if (!enabled_tc)
- return 0x1; /* TC0 */
-
- /* Find the first enabled TC */
- for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
- if (enabled_tc & BIT(i))
- break;
- }
-
- return BIT(i);
-}
-
-/**
* i40e_pf_get_pf_tc_map - Get bitmap for enabled traffic classes
* @pf: PF being queried
*
@@ -4673,7 +4701,7 @@ static u8 i40e_pf_get_tc_map(struct i40e_pf *pf)
{
/* If DCB is not enabled for this PF then just return default TC */
if (!(pf->flags & I40E_FLAG_DCB_ENABLED))
- return i40e_pf_get_default_tc(pf);
+ return I40E_DEFAULT_TRAFFIC_CLASS;
/* SFP mode we want PF to be enabled for all TCs */
if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
@@ -4683,7 +4711,7 @@ static u8 i40e_pf_get_tc_map(struct i40e_pf *pf)
if (pf->hw.func_caps.iscsi)
return i40e_get_iscsi_tc_map(pf);
else
- return i40e_pf_get_default_tc(pf);
+ return I40E_DEFAULT_TRAFFIC_CLASS;
}
/**
@@ -5029,7 +5057,7 @@ static void i40e_dcb_reconfigure(struct i40e_pf *pf)
if (v == pf->lan_vsi)
tc_map = i40e_pf_get_tc_map(pf);
else
- tc_map = i40e_pf_get_default_tc(pf);
+ tc_map = I40E_DEFAULT_TRAFFIC_CLASS;
#ifdef I40E_FCOE
if (pf->vsi[v]->type == I40E_VSI_FCOE)
tc_map = i40e_get_fcoe_tc_map(pf);
@@ -5213,7 +5241,7 @@ static int i40e_up_complete(struct i40e_vsi *vsi)
i40e_configure_msi_and_legacy(vsi);
/* start rings */
- err = i40e_vsi_control_rings(vsi, true);
+ err = i40e_vsi_start_rings(vsi);
if (err)
return err;
@@ -5310,7 +5338,7 @@ void i40e_down(struct i40e_vsi *vsi)
netif_tx_disable(vsi->netdev);
}
i40e_vsi_disable_irq(vsi);
- i40e_vsi_control_rings(vsi, false);
+ i40e_vsi_stop_rings(vsi);
i40e_napi_disable_all(vsi);
for (i = 0; i < vsi->num_queue_pairs; i++) {
@@ -5717,7 +5745,7 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
u8 type;
/* Not DCB capable or capability disabled */
- if (!(pf->flags & I40E_FLAG_DCB_ENABLED))
+ if (!(pf->flags & I40E_FLAG_DCB_CAPABLE))
return ret;
/* Ignore if event is not for Nearest Bridge */
@@ -6693,7 +6721,6 @@ static int i40e_vsi_clear(struct i40e_vsi *vsi);
static void i40e_fdir_sb_setup(struct i40e_pf *pf)
{
struct i40e_vsi *vsi;
- int i;
/* quick workaround for an NVM issue that leaves a critical register
* uninitialized
@@ -6704,6 +6731,7 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf)
0xeacb7d61, 0xaa4f05b6, 0x9c5c89ed, 0xfc425ddb,
0xa4654832, 0xfc7461d4, 0x8f827619, 0xf5c63c21,
0x95b3a76d};
+ int i;
for (i = 0; i <= I40E_GLQF_HKEY_MAX_INDEX; i++)
wr32(&pf->hw, I40E_GLQF_HKEY(i), hkey[i]);
@@ -6713,13 +6741,7 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf)
return;
/* find existing VSI and see if it needs configuring */
- vsi = NULL;
- for (i = 0; i < pf->num_alloc_vsi; i++) {
- if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR) {
- vsi = pf->vsi[i];
- break;
- }
- }
+ vsi = i40e_find_vsi_by_type(pf, I40E_VSI_FDIR);
/* create a new VSI if none exists */
if (!vsi) {
@@ -6741,15 +6763,12 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf)
**/
static void i40e_fdir_teardown(struct i40e_pf *pf)
{
- int i;
+ struct i40e_vsi *vsi;
i40e_fdir_filter_exit(pf);
- for (i = 0; i < pf->num_alloc_vsi; i++) {
- if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR) {
- i40e_vsi_release(pf->vsi[i]);
- break;
- }
- }
+ vsi = i40e_find_vsi_by_type(pf, I40E_VSI_FDIR);
+ if (vsi)
+ i40e_vsi_release(vsi);
}
/**
@@ -7377,7 +7396,7 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
pf->rss_table_size : 64;
vsi->netdev_registered = false;
vsi->work_limit = I40E_DEFAULT_IRQ_WORK;
- INIT_LIST_HEAD(&vsi->mac_filter_list);
+ hash_init(vsi->mac_filter_hash);
vsi->irqs_ready = false;
ret = i40e_set_num_rings_in_vsi(vsi);
@@ -7392,7 +7411,7 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
i40e_vsi_setup_irqhandler(vsi, i40e_msix_clean_rings);
/* Initialize VSI lock */
- spin_lock_init(&vsi->mac_filter_list_lock);
+ spin_lock_init(&vsi->mac_filter_hash_lock);
pf->vsi[vsi_idx] = vsi;
ret = vsi_idx;
goto unlock_pf;
@@ -7707,6 +7726,7 @@ static int i40e_init_msix(struct i40e_pf *pf)
pf->flags &= ~I40E_FLAG_MSIX_ENABLED;
kfree(pf->msix_entries);
pf->msix_entries = NULL;
+ pci_disable_msix(pf->pdev);
return -ENODEV;
} else if (v_actual == I40E_MIN_MSIX) {
@@ -9047,7 +9067,7 @@ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
return 0;
return ndo_dflt_bridge_getlink(skb, pid, seq, dev, veb->bridge_mode,
- nlflags, 0, 0, filter_mask, NULL);
+ 0, 0, nlflags, filter_mask, NULL);
}
/* Hardware supports L4 tunnel length of 128B (=2^7) which includes
@@ -9176,18 +9196,18 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
if (vsi->type == I40E_VSI_MAIN) {
SET_NETDEV_DEV(netdev, &pf->pdev->dev);
ether_addr_copy(mac_addr, hw->mac.perm_addr);
- spin_lock_bh(&vsi->mac_filter_list_lock);
- i40e_add_filter(vsi, mac_addr, I40E_VLAN_ANY, false, true);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
+ i40e_add_filter(vsi, mac_addr, I40E_VLAN_ANY);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
} else {
/* relate the VSI_VMDQ name to the VSI_MAIN name */
snprintf(netdev->name, IFNAMSIZ, "%sv%%d",
pf->vsi[pf->lan_vsi]->netdev->name);
random_ether_addr(mac_addr);
- spin_lock_bh(&vsi->mac_filter_list_lock);
- i40e_add_filter(vsi, mac_addr, I40E_VLAN_ANY, false, false);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
+ i40e_add_filter(vsi, mac_addr, I40E_VLAN_ANY);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
}
ether_addr_copy(netdev->dev_addr, mac_addr);
@@ -9276,7 +9296,9 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
struct i40e_pf *pf = vsi->back;
struct i40e_hw *hw = &pf->hw;
struct i40e_vsi_context ctxt;
- struct i40e_mac_filter *f, *ftmp;
+ struct i40e_mac_filter *f;
+ struct hlist_node *h;
+ int bkt;
u8 enabled_tc = 0x1; /* TC0 enabled */
int f_count = 0;
@@ -9475,13 +9497,13 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
vsi->active_filters = 0;
clear_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state);
- spin_lock_bh(&vsi->mac_filter_list_lock);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
/* If macvlan filters already exist, force them to get loaded */
- list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
+ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
f->state = I40E_FILTER_NEW;
f_count++;
}
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
if (f_count) {
vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED;
@@ -9511,11 +9533,12 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
**/
int i40e_vsi_release(struct i40e_vsi *vsi)
{
- struct i40e_mac_filter *f, *ftmp;
+ struct i40e_mac_filter *f;
+ struct hlist_node *h;
struct i40e_veb *veb = NULL;
struct i40e_pf *pf;
u16 uplink_seid;
- int i, n;
+ int i, n, bkt;
pf = vsi->back;
@@ -9545,11 +9568,19 @@ int i40e_vsi_release(struct i40e_vsi *vsi)
i40e_vsi_disable_irq(vsi);
}
- spin_lock_bh(&vsi->mac_filter_list_lock);
- list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list)
- i40e_del_filter(vsi, f->macaddr, f->vlan,
- f->is_vf, f->is_netdev);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
+
+ /* clear the sync flag on all filters */
+ if (vsi->netdev) {
+ __dev_uc_unsync(vsi->netdev, NULL);
+ __dev_mc_unsync(vsi->netdev, NULL);
+ }
+
+ /* make sure any remaining filters are marked for deletion */
+ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist)
+ __i40e_del_filter(vsi, f);
+
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
i40e_sync_vsi_filters(vsi);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 954efe3..38ee18f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -722,9 +722,20 @@ i40e_status i40e_nvmupd_command(struct i40e_hw *hw,
*((u16 *)&bytes[2]) = hw->nvm_wait_opcode;
}
+ /* Clear error status on read */
+ if (hw->nvmupd_state == I40E_NVMUPD_STATE_ERROR)
+ hw->nvmupd_state = I40E_NVMUPD_STATE_INIT;
+
return 0;
}
+ /* Clear status even it is not read and log */
+ if (hw->nvmupd_state == I40E_NVMUPD_STATE_ERROR) {
+ i40e_debug(hw, I40E_DEBUG_NVM,
+ "Clearing I40E_NVMUPD_STATE_ERROR state without reading\n");
+ hw->nvmupd_state = I40E_NVMUPD_STATE_INIT;
+ }
+
switch (hw->nvmupd_state) {
case I40E_NVMUPD_STATE_INIT:
status = i40e_nvmupd_state_init(hw, cmd, bytes, perrno);
@@ -1074,6 +1085,11 @@ void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode)
}
hw->nvm_wait_opcode = 0;
+ if (hw->aq.arq_last_status) {
+ hw->nvmupd_state = I40E_NVMUPD_STATE_ERROR;
+ return;
+ }
+
switch (hw->nvmupd_state) {
case I40E_NVMUPD_STATE_INIT_WAIT:
hw->nvmupd_state = I40E_NVMUPD_STATE_INIT;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index f1fecea..5e2272c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -159,16 +159,15 @@ static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
{
struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps);
struct timespec64 now, then;
- unsigned long flags;
then = ns_to_timespec64(delta);
- spin_lock_irqsave(&pf->tmreg_lock, flags);
+ mutex_lock(&pf->tmreg_lock);
i40e_ptp_read(pf, &now);
now = timespec64_add(now, then);
i40e_ptp_write(pf, (const struct timespec64 *)&now);
- spin_unlock_irqrestore(&pf->tmreg_lock, flags);
+ mutex_unlock(&pf->tmreg_lock);
return 0;
}
@@ -184,11 +183,10 @@ static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
static int i40e_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
{
struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps);
- unsigned long flags;
- spin_lock_irqsave(&pf->tmreg_lock, flags);
+ mutex_lock(&pf->tmreg_lock);
i40e_ptp_read(pf, ts);
- spin_unlock_irqrestore(&pf->tmreg_lock, flags);
+ mutex_unlock(&pf->tmreg_lock);
return 0;
}
@@ -205,11 +203,10 @@ static int i40e_ptp_settime(struct ptp_clock_info *ptp,
const struct timespec64 *ts)
{
struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps);
- unsigned long flags;
- spin_lock_irqsave(&pf->tmreg_lock, flags);
+ mutex_lock(&pf->tmreg_lock);
i40e_ptp_write(pf, ts);
- spin_unlock_irqrestore(&pf->tmreg_lock, flags);
+ mutex_unlock(&pf->tmreg_lock);
return 0;
}
@@ -230,6 +227,47 @@ static int i40e_ptp_feature_enable(struct ptp_clock_info *ptp,
}
/**
+ * i40e_ptp_update_latch_events - Read I40E_PRTTSYN_STAT_1 and latch events
+ * @pf: the PF data structure
+ *
+ * This function reads I40E_PRTTSYN_STAT_1 and updates the corresponding timers
+ * for noticed latch events. This allows the driver to keep track of the first
+ * time a latch event was noticed which will be used to help clear out Rx
+ * timestamps for packets that got dropped or lost.
+ *
+ * This function will return the current value of I40E_PRTTSYN_STAT_1 and is
+ * expected to be called only while under the ptp_rx_lock.
+ **/
+static u32 i40e_ptp_get_rx_events(struct i40e_pf *pf)
+{
+ struct i40e_hw *hw = &pf->hw;
+ u32 prttsyn_stat, new_latch_events;
+ int i;
+
+ prttsyn_stat = rd32(hw, I40E_PRTTSYN_STAT_1);
+ new_latch_events = prttsyn_stat & ~pf->latch_event_flags;
+
+ /* Update the jiffies time for any newly latched timestamp. This
+ * ensures that we store the time that we first discovered a timestamp
+ * was latched by the hardware. The service task will later determine
+ * if we should free the latch and drop that timestamp should too much
+ * time pass. This flow ensures that we only update jiffies for new
+ * events latched since the last time we checked, and not all events
+ * currently latched, so that the service task accounting remains
+ * accurate.
+ */
+ for (i = 0; i < 4; i++) {
+ if (new_latch_events & BIT(i))
+ pf->latch_events[i] = jiffies;
+ }
+
+ /* Finally, we store the current status of the Rx timestamp latches */
+ pf->latch_event_flags = prttsyn_stat;
+
+ return prttsyn_stat;
+}
+
+/**
* i40e_ptp_rx_hang - Detect error case when Rx timestamp registers are hung
* @vsi: The VSI with the rings relevant to 1588
*
@@ -242,10 +280,7 @@ void i40e_ptp_rx_hang(struct i40e_vsi *vsi)
{
struct i40e_pf *pf = vsi->back;
struct i40e_hw *hw = &pf->hw;
- struct i40e_ring *rx_ring;
- unsigned long rx_event;
- u32 prttsyn_stat;
- int n;
+ int i;
/* Since we cannot turn off the Rx timestamp logic if the device is
* configured for Tx timestamping, we check if Rx timestamping is
@@ -255,42 +290,30 @@ void i40e_ptp_rx_hang(struct i40e_vsi *vsi)
if (!(pf->flags & I40E_FLAG_PTP) || !pf->ptp_rx)
return;
- prttsyn_stat = rd32(hw, I40E_PRTTSYN_STAT_1);
+ spin_lock_bh(&pf->ptp_rx_lock);
- /* Unless all four receive timestamp registers are latched, we are not
- * concerned about a possible PTP Rx hang, so just update the timeout
- * counter and exit.
+ /* Update current latch times for Rx events */
+ i40e_ptp_get_rx_events(pf);
+
+ /* Check all the currently latched Rx events and see whether they have
+ * been latched for over a second. It is assumed that any timestamp
+ * should have been cleared within this time, or else it was captured
+ * for a dropped frame that the driver never received. Thus, we will
+ * clear any timestamp that has been latched for over 1 second.
*/
- if (!(prttsyn_stat & ((I40E_PRTTSYN_STAT_1_RXT0_MASK <<
- I40E_PRTTSYN_STAT_1_RXT0_SHIFT) |
- (I40E_PRTTSYN_STAT_1_RXT1_MASK <<
- I40E_PRTTSYN_STAT_1_RXT1_SHIFT) |
- (I40E_PRTTSYN_STAT_1_RXT2_MASK <<
- I40E_PRTTSYN_STAT_1_RXT2_SHIFT) |
- (I40E_PRTTSYN_STAT_1_RXT3_MASK <<
- I40E_PRTTSYN_STAT_1_RXT3_SHIFT)))) {
- pf->last_rx_ptp_check = jiffies;
- return;
+ for (i = 0; i < 4; i++) {
+ if ((pf->latch_event_flags & BIT(i)) &&
+ time_is_before_jiffies(pf->latch_events[i] + HZ)) {
+ rd32(hw, I40E_PRTTSYN_RXTIME_H(i));
+ pf->latch_event_flags &= ~BIT(i);
+ pf->rx_hwtstamp_cleared++;
+ dev_warn(&pf->pdev->dev,
+ "Clearing a missed Rx timestamp event for RXTIME[%d]\n",
+ i);
+ }
}
- /* Determine the most recent watchdog or rx_timestamp event. */
- rx_event = pf->last_rx_ptp_check;
- for (n = 0; n < vsi->num_queue_pairs; n++) {
- rx_ring = vsi->rx_rings[n];
- if (time_after(rx_ring->last_rx_timestamp, rx_event))
- rx_event = rx_ring->last_rx_timestamp;
- }
-
- /* Only need to read the high RXSTMP register to clear the lock */
- if (time_is_before_jiffies(rx_event + 5 * HZ)) {
- rd32(hw, I40E_PRTTSYN_RXTIME_H(0));
- rd32(hw, I40E_PRTTSYN_RXTIME_H(1));
- rd32(hw, I40E_PRTTSYN_RXTIME_H(2));
- rd32(hw, I40E_PRTTSYN_RXTIME_H(3));
- pf->last_rx_ptp_check = jiffies;
- pf->rx_hwtstamp_cleared++;
- WARN_ONCE(1, "Detected Rx timestamp register hang\n");
- }
+ spin_unlock_bh(&pf->ptp_rx_lock);
}
/**
@@ -353,14 +376,25 @@ void i40e_ptp_rx_hwtstamp(struct i40e_pf *pf, struct sk_buff *skb, u8 index)
hw = &pf->hw;
- prttsyn_stat = rd32(hw, I40E_PRTTSYN_STAT_1);
+ spin_lock_bh(&pf->ptp_rx_lock);
- if (!(prttsyn_stat & BIT(index)))
+ /* Get current Rx events and update latch times */
+ prttsyn_stat = i40e_ptp_get_rx_events(pf);
+
+ /* TODO: Should we warn about missing Rx timestamp event? */
+ if (!(prttsyn_stat & BIT(index))) {
+ spin_unlock_bh(&pf->ptp_rx_lock);
return;
+ }
+
+ /* Clear the latched event since we're about to read its register */
+ pf->latch_event_flags &= ~BIT(index);
lo = rd32(hw, I40E_PRTTSYN_RXTIME_L(index));
hi = rd32(hw, I40E_PRTTSYN_RXTIME_H(index));
+ spin_unlock_bh(&pf->ptp_rx_lock);
+
ns = (((u64)hi) << 32) | lo;
i40e_ptp_convert_to_hwtstamp(skb_hwtstamps(skb), ns);
@@ -514,12 +548,15 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf,
}
/* Clear out all 1588-related registers to clear and unlatch them. */
+ spin_lock_bh(&pf->ptp_rx_lock);
rd32(hw, I40E_PRTTSYN_STAT_0);
rd32(hw, I40E_PRTTSYN_TXTIME_H);
rd32(hw, I40E_PRTTSYN_RXTIME_H(0));
rd32(hw, I40E_PRTTSYN_RXTIME_H(1));
rd32(hw, I40E_PRTTSYN_RXTIME_H(2));
rd32(hw, I40E_PRTTSYN_RXTIME_H(3));
+ pf->latch_event_flags = 0;
+ spin_unlock_bh(&pf->ptp_rx_lock);
/* Enable/disable the Tx timestamp interrupt based on user input. */
regval = rd32(hw, I40E_PRTTSYN_CTL0);
@@ -658,10 +695,8 @@ void i40e_ptp_init(struct i40e_pf *pf)
return;
}
- /* we have to initialize the lock first, since we can't control
- * when the user will enter the PHC device entry points
- */
- spin_lock_init(&pf->tmreg_lock);
+ mutex_init(&pf->tmreg_lock);
+ spin_lock_init(&pf->ptp_rx_lock);
/* ensure we have a clock device */
err = i40e_ptp_create_clock(pf);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index daade4fe..5544b50 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -125,10 +125,7 @@ static int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data,
u16 i;
/* find existing FDIR VSI */
- vsi = NULL;
- for (i = 0; i < pf->num_alloc_vsi; i++)
- if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR)
- vsi = pf->vsi[i];
+ vsi = i40e_find_vsi_by_type(pf, I40E_VSI_FDIR);
if (!vsi)
return -ENOENT;
@@ -619,7 +616,7 @@ u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw)
return 0;
}
-#define WB_STRIDE 0x3
+#define WB_STRIDE 4
/**
* i40e_clean_tx_irq - Reclaim resources after transmit completes
@@ -735,7 +732,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
unsigned int j = i40e_get_tx_pending(tx_ring, false);
if (budget &&
- ((j / (WB_STRIDE + 1)) == 0) && (j != 0) &&
+ ((j / WB_STRIDE) == 0) && (j > 0) &&
!test_bit(__I40E_DOWN, &vsi->state) &&
(I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
tx_ring->arm_wb = true;
@@ -1410,13 +1407,12 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring,
u64 qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
u32 rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >>
I40E_RXD_QW1_STATUS_SHIFT;
- u32 rsyn = (rx_status & I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >>
+ u32 tsynvalid = rx_status & I40E_RXD_QW1_STATUS_TSYNVALID_MASK;
+ u32 tsyn = (rx_status & I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >>
I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT;
- if (unlikely(rsyn)) {
- i40e_ptp_rx_hwtstamp(rx_ring->vsi->back, skb, rsyn);
- rx_ring->last_rx_timestamp = jiffies;
- }
+ if (unlikely(tsynvalid))
+ i40e_ptp_rx_hwtstamp(rx_ring->vsi->back, skb, tsyn);
i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
@@ -2704,9 +2700,7 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
u32 td_tag = 0;
dma_addr_t dma;
u16 gso_segs;
- u16 desc_count = 0;
- bool tail_bump = true;
- bool do_rs = false;
+ u16 desc_count = 1;
if (tx_flags & I40E_TX_FLAGS_HW_VLAN) {
td_cmd |= I40E_TX_DESC_CMD_IL2TAG1;
@@ -2789,8 +2783,7 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
tx_bi = &tx_ring->tx_bi[i];
}
- /* set next_to_watch value indicating a packet is present */
- first->next_to_watch = tx_desc;
+ netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount);
i++;
if (i == tx_ring->count)
@@ -2798,66 +2791,72 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
tx_ring->next_to_use = i;
- netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount);
i40e_maybe_stop_tx(tx_ring, DESC_NEEDED);
+ /* write last descriptor with EOP bit */
+ td_cmd |= I40E_TX_DESC_CMD_EOP;
+
+ /* We can OR these values together as they both are checked against
+ * 4 below and at this point desc_count will be used as a boolean value
+ * after this if/else block.
+ */
+ desc_count |= ++tx_ring->packet_stride;
+
/* Algorithm to optimize tail and RS bit setting:
- * if xmit_more is supported
- * if xmit_more is true
- * do not update tail and do not mark RS bit.
- * if xmit_more is false and last xmit_more was false
- * if every packet spanned less than 4 desc
- * then set RS bit on 4th packet and update tail
- * on every packet
- * else
- * update tail and set RS bit on every packet.
- * if xmit_more is false and last_xmit_more was true
- * update tail and set RS bit.
+ * if queue is stopped
+ * mark RS bit
+ * reset packet counter
+ * else if xmit_more is supported and is true
+ * advance packet counter to 4
+ * reset desc_count to 0
*
- * Optimization: wmb to be issued only in case of tail update.
- * Also optimize the Descriptor WB path for RS bit with the same
- * algorithm.
+ * if desc_count >= 4
+ * mark RS bit
+ * reset packet counter
+ * if desc_count > 0
+ * update tail
*
- * Note: If there are less than 4 packets
+ * Note: If there are less than 4 descriptors
* pending and interrupts were disabled the service task will
* trigger a force WB.
*/
- if (skb->xmit_more &&
- !netif_xmit_stopped(txring_txq(tx_ring))) {
- tx_ring->flags |= I40E_TXR_FLAGS_LAST_XMIT_MORE_SET;
- tail_bump = false;
- } else if (!skb->xmit_more &&
- !netif_xmit_stopped(txring_txq(tx_ring)) &&
- (!(tx_ring->flags & I40E_TXR_FLAGS_LAST_XMIT_MORE_SET)) &&
- (tx_ring->packet_stride < WB_STRIDE) &&
- (desc_count < WB_STRIDE)) {
- tx_ring->packet_stride++;
- } else {
+ if (netif_xmit_stopped(txring_txq(tx_ring))) {
+ goto do_rs;
+ } else if (skb->xmit_more) {
+ /* set stride to arm on next packet and reset desc_count */
+ tx_ring->packet_stride = WB_STRIDE;
+ desc_count = 0;
+ } else if (desc_count >= WB_STRIDE) {
+do_rs:
+ /* write last descriptor with RS bit set */
+ td_cmd |= I40E_TX_DESC_CMD_RS;
tx_ring->packet_stride = 0;
- tx_ring->flags &= ~I40E_TXR_FLAGS_LAST_XMIT_MORE_SET;
- do_rs = true;
}
- if (do_rs)
- tx_ring->packet_stride = 0;
tx_desc->cmd_type_offset_bsz =
- build_ctob(td_cmd, td_offset, size, td_tag) |
- cpu_to_le64((u64)(do_rs ? I40E_TXD_CMD :
- I40E_TX_DESC_CMD_EOP) <<
- I40E_TXD_QW1_CMD_SHIFT);
+ build_ctob(td_cmd, td_offset, size, td_tag);
+
+ /* Force memory writes to complete before letting h/w know there
+ * are new descriptors to fetch.
+ *
+ * We also use this memory barrier to make certain all of the
+ * status bits have been updated before next_to_watch is written.
+ */
+ wmb();
+
+ /* set next_to_watch value indicating a packet is present */
+ first->next_to_watch = tx_desc;
/* notify HW of packet */
- if (!tail_bump) {
- prefetchw(tx_desc + 1);
- } else {
- /* Force memory writes to complete before letting h/w
- * know there are new descriptors to fetch. (Only
- * applicable for weak-ordered memory model archs,
- * such as IA-64).
- */
- wmb();
+ if (desc_count) {
writel(i, tx_ring->tail);
+
+ /* we need this if more than one processor can write to our tail
+ * at a time, it synchronizes IO on IA64/Altix systems
+ */
+ mmiowb();
}
+
return;
dma_error:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 5088405..de8550f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -307,15 +307,12 @@ struct i40e_ring {
u8 atr_sample_rate;
u8 atr_count;
- unsigned long last_rx_timestamp;
-
bool ring_active; /* is ring online or not */
bool arm_wb; /* do something to arm write back */
u8 packet_stride;
u16 flags;
#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0)
-#define I40E_TXR_FLAGS_LAST_XMIT_MORE_SET BIT(2)
/* stats structs */
struct i40e_queue_stats stats;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index bd5f13b..d9a2660 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -366,6 +366,7 @@ enum i40e_nvmupd_state {
I40E_NVMUPD_STATE_WRITING,
I40E_NVMUPD_STATE_INIT_WAIT,
I40E_NVMUPD_STATE_WRITE_WAIT,
+ I40E_NVMUPD_STATE_ERROR
};
/* nvm_access definition and its masks/shifts need to be accessible to
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 54b8ee2..53b46553 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -686,17 +686,17 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
if (vf->port_vlan_id)
i40e_vsi_add_pvid(vsi, vf->port_vlan_id);
- spin_lock_bh(&vsi->mac_filter_list_lock);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
if (is_valid_ether_addr(vf->default_lan_addr.addr)) {
f = i40e_add_filter(vsi, vf->default_lan_addr.addr,
- vf->port_vlan_id ? vf->port_vlan_id : -1,
- true, false);
+ vf->port_vlan_id ?
+ vf->port_vlan_id : -1);
if (!f)
dev_info(&pf->pdev->dev,
"Could not add MAC filter %pM for VF %d\n",
vf->default_lan_addr.addr, vf->vf_id);
}
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id),
(u32)hena);
i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id),
@@ -811,6 +811,7 @@ static void i40e_free_vf_res(struct i40e_vf *vf)
i40e_vsi_release(pf->vsi[vf->lan_vsi_idx]);
vf->lan_vsi_idx = 0;
vf->lan_vsi_id = 0;
+ vf->num_mac = 0;
}
msix_vf = pf->hw.func_caps.num_msix_vectors_vf;
@@ -990,7 +991,7 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr)
if (vf->lan_vsi_idx == 0)
goto complete_reset;
- i40e_vsi_control_rings(pf->vsi[vf->lan_vsi_idx], false);
+ i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]);
complete_reset:
/* reallocate VF resources to reset the VSI state */
i40e_free_vf_res(vf);
@@ -1031,8 +1032,7 @@ void i40e_free_vfs(struct i40e_pf *pf)
i40e_notify_client_of_vf_enable(pf, 0);
for (i = 0; i < pf->num_alloc_vfs; i++)
if (test_bit(I40E_VF_STAT_INIT, &pf->vf[i].vf_states))
- i40e_vsi_control_rings(pf->vsi[pf->vf[i].lan_vsi_idx],
- false);
+ i40e_vsi_stop_rings(pf->vsi[pf->vf[i].lan_vsi_idx]);
/* Disable IOV before freeing resources. This lets any VF drivers
* running in the host get themselves cleaned up before we yank
@@ -1449,9 +1449,9 @@ static void i40e_vc_reset_vf_msg(struct i40e_vf *vf)
static inline int i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi)
{
struct i40e_mac_filter *f;
- int num_vlans = 0;
+ int num_vlans = 0, bkt;
- list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) {
if (f->vlan >= 0 && f->vlan <= I40E_MAX_VLANID)
num_vlans++;
}
@@ -1481,6 +1481,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf,
struct i40e_vsi *vsi;
bool alluni = false;
int aq_err = 0;
+ int bkt;
vsi = i40e_find_vsi_from_id(pf, info->vsi_id);
if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) ||
@@ -1507,7 +1508,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf,
vf->port_vlan_id,
NULL);
} else if (i40e_getnum_vf_vsi_vlan_filters(vsi)) {
- list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) {
if (f->vlan < 0 || f->vlan > I40E_MAX_VLANID)
continue;
aq_ret = i40e_aq_set_vsi_mc_promisc_on_vlan(hw,
@@ -1557,7 +1558,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf,
vf->port_vlan_id,
NULL);
} else if (i40e_getnum_vf_vsi_vlan_filters(vsi)) {
- list_for_each_entry(f, &vsi->mac_filter_list, list) {
+ hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) {
aq_ret = 0;
if (f->vlan >= 0 && f->vlan <= I40E_MAX_VLANID) {
aq_ret =
@@ -1757,7 +1758,7 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
goto error_param;
}
- if (i40e_vsi_control_rings(pf->vsi[vf->lan_vsi_idx], true))
+ if (i40e_vsi_start_rings(pf->vsi[vf->lan_vsi_idx]))
aq_ret = I40E_ERR_TIMEOUT;
error_param:
/* send the response to the VF */
@@ -1796,8 +1797,7 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
goto error_param;
}
- if (i40e_vsi_control_rings(pf->vsi[vf->lan_vsi_idx], false))
- aq_ret = I40E_ERR_TIMEOUT;
+ i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]);
error_param:
/* send the response to the VF */
@@ -1927,20 +1927,18 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
/* Lock once, because all function inside for loop accesses VSI's
* MAC filter list which needs to be protected using same lock.
*/
- spin_lock_bh(&vsi->mac_filter_list_lock);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
/* add new addresses to the list */
for (i = 0; i < al->num_elements; i++) {
struct i40e_mac_filter *f;
- f = i40e_find_mac(vsi, al->list[i].addr, true, false);
+ f = i40e_find_mac(vsi, al->list[i].addr);
if (!f) {
if (i40e_is_vsi_in_vlan(vsi))
- f = i40e_put_mac_in_vlan(vsi, al->list[i].addr,
- true, false);
+ f = i40e_put_mac_in_vlan(vsi, al->list[i].addr);
else
- f = i40e_add_filter(vsi, al->list[i].addr, -1,
- true, false);
+ f = i40e_add_filter(vsi, al->list[i].addr, -1);
}
if (!f) {
@@ -1948,13 +1946,13 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
"Unable to add MAC filter %pM for VF %d\n",
al->list[i].addr, vf->vf_id);
ret = I40E_ERR_PARAM;
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
goto error_param;
} else {
vf->num_mac++;
}
}
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
/* program the updated filter list */
ret = i40e_sync_vsi_filters(vsi);
@@ -2003,18 +2001,18 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
}
vsi = pf->vsi[vf->lan_vsi_idx];
- spin_lock_bh(&vsi->mac_filter_list_lock);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
/* delete addresses from the list */
for (i = 0; i < al->num_elements; i++)
- if (i40e_del_mac_all_vlan(vsi, al->list[i].addr, true, false)) {
+ if (i40e_del_mac_all_vlan(vsi, al->list[i].addr)) {
ret = I40E_ERR_INVALID_MAC_ADDR;
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
goto error_param;
} else {
vf->num_mac--;
}
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
/* program the updated filter list */
ret = i40e_sync_vsi_filters(vsi);
@@ -2139,9 +2137,8 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
}
for (i = 0; i < vfl->num_elements; i++) {
- int ret = i40e_vsi_kill_vlan(vsi, vfl->vlan_id[i]);
- if (!ret)
- vf->num_vlan--;
+ i40e_vsi_kill_vlan(vsi, vfl->vlan_id[i]);
+ vf->num_vlan--;
if (test_bit(I40E_VF_STAT_UC_PROMISC, &vf->vf_states))
i40e_aq_set_vsi_uc_promisc_on_vlan(&pf->hw, vsi->seid,
@@ -2153,11 +2150,6 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
false,
vfl->vlan_id[i],
NULL);
-
- if (ret)
- dev_err(&pf->pdev->dev,
- "Unable to delete VLAN filter %d for VF %d, error %d\n",
- vfl->vlan_id[i], vf->vf_id, ret);
}
error_param:
@@ -2689,6 +2681,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
struct i40e_mac_filter *f;
struct i40e_vf *vf;
int ret = 0;
+ int bkt;
/* validate the request */
if (vf_id >= pf->num_alloc_vfs) {
@@ -2715,23 +2708,22 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
}
/* Lock once because below invoked function add/del_filter requires
- * mac_filter_list_lock to be held
+ * mac_filter_hash_lock to be held
*/
- spin_lock_bh(&vsi->mac_filter_list_lock);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
/* delete the temporary mac address */
if (!is_zero_ether_addr(vf->default_lan_addr.addr))
i40e_del_filter(vsi, vf->default_lan_addr.addr,
- vf->port_vlan_id ? vf->port_vlan_id : -1,
- true, false);
+ vf->port_vlan_id ? vf->port_vlan_id : -1);
/* Delete all the filters for this VSI - we're going to kill it
* anyway.
*/
- list_for_each_entry(f, &vsi->mac_filter_list, list)
- i40e_del_filter(vsi, f->macaddr, f->vlan, true, false);
+ hash_for_each(vsi->mac_filter_hash, bkt, f, hlist)
+ i40e_del_filter(vsi, f->macaddr, f->vlan);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
dev_info(&pf->pdev->dev, "Setting MAC %pM on VF %d\n", mac, vf_id);
/* program mac filter */
@@ -2803,9 +2795,9 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
/* duplicate request, so just return success */
goto error_pvid;
- spin_lock_bh(&vsi->mac_filter_list_lock);
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
is_vsi_in_vlan = i40e_is_vsi_in_vlan(vsi);
- spin_unlock_bh(&vsi->mac_filter_list_lock);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
if (le16_to_cpu(vsi->info.pvid) == 0 && is_vsi_in_vlan) {
dev_err(&pf->pdev->dev,
@@ -2835,13 +2827,8 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
if (vsi->info.pvid) {
/* kill old VLAN */
- ret = i40e_vsi_kill_vlan(vsi, (le16_to_cpu(vsi->info.pvid) &
- VLAN_VID_MASK));
- if (ret) {
- dev_info(&vsi->back->pdev->dev,
- "remove VLAN failed, ret=%d, aq_err=%d\n",
- ret, pf->hw.aq.asq_last_status);
- }
+ i40e_vsi_kill_vlan(vsi, (le16_to_cpu(vsi->info.pvid) &
+ VLAN_VID_MASK));
}
if (vlan_id || qos)
ret = i40e_vsi_add_pvid(vsi, vlanprio);
@@ -2940,7 +2927,7 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate,
}
if (max_tx_rate > speed) {
- dev_err(&pf->pdev->dev, "Invalid max tx rate %d specified for VF %d.",
+ dev_err(&pf->pdev->dev, "Invalid max tx rate %d specified for VF %d.\n",
max_tx_rate, vf->vf_id);
ret = -EINVAL;
goto error;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
index 44f7ed7..9638515 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
@@ -912,11 +912,11 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw,
desc = I40E_ADMINQ_DESC(hw->aq.arq, ntc);
desc_idx = ntc;
+ hw->aq.arq_last_status =
+ (enum i40e_admin_queue_err)le16_to_cpu(desc->retval);
flags = le16_to_cpu(desc->flags);
if (flags & I40E_AQ_FLAG_ERR) {
ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
- hw->aq.arq_last_status =
- (enum i40e_admin_queue_err)le16_to_cpu(desc->retval);
i40e_debug(hw,
I40E_DEBUG_AQ_MESSAGE,
"AQRX: Event received with error 0x%X.\n",
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index e2d3622..c4b174af 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -150,7 +150,7 @@ u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw)
return 0;
}
-#define WB_STRIDE 0x3
+#define WB_STRIDE 4
/**
* i40e_clean_tx_irq - Reclaim resources after transmit completes
@@ -266,7 +266,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
unsigned int j = i40evf_get_tx_pending(tx_ring, false);
if (budget &&
- ((j / (WB_STRIDE + 1)) == 0) && (j > 0) &&
+ ((j / WB_STRIDE) == 0) && (j > 0) &&
!test_bit(__I40E_DOWN, &vsi->state) &&
(I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
tx_ring->arm_wb = true;
@@ -1950,9 +1950,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
u32 td_tag = 0;
dma_addr_t dma;
u16 gso_segs;
- u16 desc_count = 0;
- bool tail_bump = true;
- bool do_rs = false;
+ u16 desc_count = 1;
if (tx_flags & I40E_TX_FLAGS_HW_VLAN) {
td_cmd |= I40E_TX_DESC_CMD_IL2TAG1;
@@ -2035,8 +2033,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
tx_bi = &tx_ring->tx_bi[i];
}
- /* set next_to_watch value indicating a packet is present */
- first->next_to_watch = tx_desc;
+ netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount);
i++;
if (i == tx_ring->count)
@@ -2044,66 +2041,72 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
tx_ring->next_to_use = i;
- netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount);
i40e_maybe_stop_tx(tx_ring, DESC_NEEDED);
+ /* write last descriptor with EOP bit */
+ td_cmd |= I40E_TX_DESC_CMD_EOP;
+
+ /* We can OR these values together as they both are checked against
+ * 4 below and at this point desc_count will be used as a boolean value
+ * after this if/else block.
+ */
+ desc_count |= ++tx_ring->packet_stride;
+
/* Algorithm to optimize tail and RS bit setting:
- * if xmit_more is supported
- * if xmit_more is true
- * do not update tail and do not mark RS bit.
- * if xmit_more is false and last xmit_more was false
- * if every packet spanned less than 4 desc
- * then set RS bit on 4th packet and update tail
- * on every packet
- * else
- * update tail and set RS bit on every packet.
- * if xmit_more is false and last_xmit_more was true
- * update tail and set RS bit.
+ * if queue is stopped
+ * mark RS bit
+ * reset packet counter
+ * else if xmit_more is supported and is true
+ * advance packet counter to 4
+ * reset desc_count to 0
*
- * Optimization: wmb to be issued only in case of tail update.
- * Also optimize the Descriptor WB path for RS bit with the same
- * algorithm.
+ * if desc_count >= 4
+ * mark RS bit
+ * reset packet counter
+ * if desc_count > 0
+ * update tail
*
- * Note: If there are less than 4 packets
+ * Note: If there are less than 4 descriptors
* pending and interrupts were disabled the service task will
* trigger a force WB.
*/
- if (skb->xmit_more &&
- !netif_xmit_stopped(txring_txq(tx_ring))) {
- tx_ring->flags |= I40E_TXR_FLAGS_LAST_XMIT_MORE_SET;
- tail_bump = false;
- } else if (!skb->xmit_more &&
- !netif_xmit_stopped(txring_txq(tx_ring)) &&
- (!(tx_ring->flags & I40E_TXR_FLAGS_LAST_XMIT_MORE_SET)) &&
- (tx_ring->packet_stride < WB_STRIDE) &&
- (desc_count < WB_STRIDE)) {
- tx_ring->packet_stride++;
- } else {
+ if (netif_xmit_stopped(txring_txq(tx_ring))) {
+ goto do_rs;
+ } else if (skb->xmit_more) {
+ /* set stride to arm on next packet and reset desc_count */
+ tx_ring->packet_stride = WB_STRIDE;
+ desc_count = 0;
+ } else if (desc_count >= WB_STRIDE) {
+do_rs:
+ /* write last descriptor with RS bit set */
+ td_cmd |= I40E_TX_DESC_CMD_RS;
tx_ring->packet_stride = 0;
- tx_ring->flags &= ~I40E_TXR_FLAGS_LAST_XMIT_MORE_SET;
- do_rs = true;
}
- if (do_rs)
- tx_ring->packet_stride = 0;
tx_desc->cmd_type_offset_bsz =
- build_ctob(td_cmd, td_offset, size, td_tag) |
- cpu_to_le64((u64)(do_rs ? I40E_TXD_CMD :
- I40E_TX_DESC_CMD_EOP) <<
- I40E_TXD_QW1_CMD_SHIFT);
+ build_ctob(td_cmd, td_offset, size, td_tag);
+
+ /* Force memory writes to complete before letting h/w know there
+ * are new descriptors to fetch.
+ *
+ * We also use this memory barrier to make certain all of the
+ * status bits have been updated before next_to_watch is written.
+ */
+ wmb();
+
+ /* set next_to_watch value indicating a packet is present */
+ first->next_to_watch = tx_desc;
/* notify HW of packet */
- if (!tail_bump) {
- prefetchw(tx_desc + 1);
- } else {
- /* Force memory writes to complete before letting h/w
- * know there are new descriptors to fetch. (Only
- * applicable for weak-ordered memory model archs,
- * such as IA-64).
- */
- wmb();
+ if (desc_count) {
writel(i, tx_ring->tail);
+
+ /* we need this if more than one processor can write to our tail
+ * at a time, it synchronizes IO on IA64/Altix systems
+ */
+ mmiowb();
}
+
return;
dma_error:
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index abcdeca..a586e19 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -309,7 +309,6 @@ struct i40e_ring {
bool ring_active; /* is ring online or not */
bool arm_wb; /* do something to arm write back */
u8 packet_stride;
-#define I40E_TXR_FLAGS_LAST_XMIT_MORE_SET BIT(2)
u16 flags;
#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0)
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h
index 97f96e0..ca7afe5 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h
@@ -348,6 +348,7 @@ enum i40e_nvmupd_state {
I40E_NVMUPD_STATE_WRITING,
I40E_NVMUPD_STATE_INIT_WAIT,
I40E_NVMUPD_STATE_WRITE_WAIT,
+ I40E_NVMUPD_STATE_ERROR
};
/* nvm_access definition and its masks/shifts need to be accessible to
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index bcb1caf..db36744 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -1746,15 +1746,17 @@ static void i40evf_reset_task(struct work_struct *work)
/* wait until the reset is complete and the PF is responding to us */
for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) {
+ /* sleep first to make sure a minimum wait time is met */
+ msleep(I40EVF_RESET_WAIT_MS);
+
reg_val = rd32(hw, I40E_VFGEN_RSTAT) &
I40E_VFGEN_RSTAT_VFR_STATE_MASK;
if (reg_val == I40E_VFR_VFACTIVE)
break;
- msleep(I40EVF_RESET_WAIT_MS);
}
+
pci_set_master(adapter->pdev);
- /* extra wait to make sure minimum wait is met */
- msleep(I40EVF_RESET_WAIT_MS);
+
if (i == I40EVF_RESET_WAIT_COUNT) {
struct i40evf_mac_filter *ftmp;
struct i40evf_vlan_filter *fv, *fvtmp;
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index a7895c4..c30eea8 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -226,7 +226,7 @@ static int igb_ptp_adjfreq_82576(struct ptp_clock_info *ptp, s32 ppb)
return 0;
}
-static int igb_ptp_adjfreq_82580(struct ptp_clock_info *ptp, s32 ppb)
+static int igb_ptp_adjfine_82580(struct ptp_clock_info *ptp, long scaled_ppm)
{
struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
ptp_caps);
@@ -235,13 +235,13 @@ static int igb_ptp_adjfreq_82580(struct ptp_clock_info *ptp, s32 ppb)
u64 rate;
u32 inca;
- if (ppb < 0) {
+ if (scaled_ppm < 0) {
neg_adj = 1;
- ppb = -ppb;
+ scaled_ppm = -scaled_ppm;
}
- rate = ppb;
- rate <<= 26;
- rate = div_u64(rate, 1953125);
+ rate = scaled_ppm;
+ rate <<= 13;
+ rate = div_u64(rate, 15625);
inca = rate & INCVALUE_MASK;
if (neg_adj)
@@ -1103,7 +1103,7 @@ void igb_ptp_init(struct igb_adapter *adapter)
adapter->ptp_caps.max_adj = 62499999;
adapter->ptp_caps.n_ext_ts = 0;
adapter->ptp_caps.pps = 0;
- adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82580;
+ adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580;
adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576;
adapter->ptp_caps.gettime64 = igb_ptp_gettime_82576;
adapter->ptp_caps.settime64 = igb_ptp_settime_82576;
@@ -1131,7 +1131,7 @@ void igb_ptp_init(struct igb_adapter *adapter)
adapter->ptp_caps.n_pins = IGB_N_SDP;
adapter->ptp_caps.pps = 1;
adapter->ptp_caps.pin_config = adapter->sdp_config;
- adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82580;
+ adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580;
adapter->ptp_caps.adjtime = igb_ptp_adjtime_i210;
adapter->ptp_caps.gettime64 = igb_ptp_gettime_i210;
adapter->ptp_caps.settime64 = igb_ptp_settime_i210;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index b06e32d..ef81c3d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -1027,4 +1027,6 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
struct ixgbe_ring *tx_ring);
u32 ixgbe_rss_indir_tbl_entries(struct ixgbe_adapter *adapter);
void ixgbe_store_reta(struct ixgbe_adapter *adapter);
+s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg,
+ u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm);
#endif /* _IXGBE_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
index fb51be7..805ab31 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
@@ -367,7 +367,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw)
}
/* Negotiate the fc mode to use */
- ixgbe_fc_autoneg(hw);
+ hw->mac.ops.fc_autoneg(hw);
/* Disable any previous flow control settings */
fctrl_reg = IXGBE_READ_REG(hw, IXGBE_FCTRL);
@@ -1179,6 +1179,7 @@ static const struct ixgbe_mac_operations mac_ops_82598 = {
.get_link_capabilities = &ixgbe_get_link_capabilities_82598,
.led_on = &ixgbe_led_on_generic,
.led_off = &ixgbe_led_off_generic,
+ .init_led_link_act = ixgbe_init_led_link_act_generic,
.blink_led_start = &ixgbe_blink_led_start_generic,
.blink_led_stop = &ixgbe_blink_led_stop_generic,
.set_rar = &ixgbe_set_rar_generic,
@@ -1193,6 +1194,7 @@ static const struct ixgbe_mac_operations mac_ops_82598 = {
.set_vfta = &ixgbe_set_vfta_82598,
.fc_enable = &ixgbe_fc_enable_82598,
.setup_fc = ixgbe_setup_fc_generic,
+ .fc_autoneg = ixgbe_fc_autoneg,
.set_fw_drv_ver = NULL,
.acquire_swfw_sync = &ixgbe_acquire_swfw_sync,
.release_swfw_sync = &ixgbe_release_swfw_sync,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
index 63b2500..e00aaeb 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
@@ -2204,6 +2204,7 @@ static const struct ixgbe_mac_operations mac_ops_82599 = {
.get_link_capabilities = &ixgbe_get_link_capabilities_82599,
.led_on = &ixgbe_led_on_generic,
.led_off = &ixgbe_led_off_generic,
+ .init_led_link_act = ixgbe_init_led_link_act_generic,
.blink_led_start = &ixgbe_blink_led_start_generic,
.blink_led_stop = &ixgbe_blink_led_stop_generic,
.set_rar = &ixgbe_set_rar_generic,
@@ -2219,6 +2220,7 @@ static const struct ixgbe_mac_operations mac_ops_82599 = {
.set_vfta = &ixgbe_set_vfta_generic,
.fc_enable = &ixgbe_fc_enable_generic,
.setup_fc = ixgbe_setup_fc_generic,
+ .fc_autoneg = ixgbe_fc_autoneg,
.set_fw_drv_ver = &ixgbe_set_fw_drv_ver_generic,
.init_uta_tables = &ixgbe_init_uta_tables_generic,
.setup_sfp = &ixgbe_setup_sfp_modules_82599,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 77d3039..8832df3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -298,10 +298,12 @@ s32 ixgbe_start_hw_generic(struct ixgbe_hw *hw)
IXGBE_WRITE_REG(hw, IXGBE_CTRL_EXT, ctrl_ext);
IXGBE_WRITE_FLUSH(hw);
- /* Setup flow control */
- ret_val = hw->mac.ops.setup_fc(hw);
- if (ret_val)
- return ret_val;
+ /* Setup flow control if method for doing so */
+ if (hw->mac.ops.setup_fc) {
+ ret_val = hw->mac.ops.setup_fc(hw);
+ if (ret_val)
+ return ret_val;
+ }
/* Cashe bit indicating need for crosstalk fix */
switch (hw->mac.type) {
@@ -390,6 +392,9 @@ s32 ixgbe_init_hw_generic(struct ixgbe_hw *hw)
status = hw->mac.ops.start_hw(hw);
}
+ /* Initialize the LED link active for LED blink support */
+ hw->mac.ops.init_led_link_act(hw);
+
return status;
}
@@ -773,6 +778,49 @@ s32 ixgbe_stop_adapter_generic(struct ixgbe_hw *hw)
}
/**
+ * ixgbe_init_led_link_act_generic - Store the LED index link/activity.
+ * @hw: pointer to hardware structure
+ *
+ * Store the index for the link active LED. This will be used to support
+ * blinking the LED.
+ **/
+s32 ixgbe_init_led_link_act_generic(struct ixgbe_hw *hw)
+{
+ struct ixgbe_mac_info *mac = &hw->mac;
+ u32 led_reg, led_mode;
+ u16 i;
+
+ led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL);
+
+ /* Get LED link active from the LEDCTL register */
+ for (i = 0; i < 4; i++) {
+ led_mode = led_reg >> IXGBE_LED_MODE_SHIFT(i);
+
+ if ((led_mode & IXGBE_LED_MODE_MASK_BASE) ==
+ IXGBE_LED_LINK_ACTIVE) {
+ mac->led_link_act = i;
+ return 0;
+ }
+ }
+
+ /* If LEDCTL register does not have the LED link active set, then use
+ * known MAC defaults.
+ */
+ switch (hw->mac.type) {
+ case ixgbe_mac_x550em_a:
+ mac->led_link_act = 0;
+ break;
+ case ixgbe_mac_X550EM_x:
+ mac->led_link_act = 1;
+ break;
+ default:
+ mac->led_link_act = 2;
+ }
+
+ return 0;
+}
+
+/**
* ixgbe_led_on_generic - Turns on the software controllable LEDs.
* @hw: pointer to hardware structure
* @index: led number to turn on
@@ -2127,7 +2175,7 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw)
}
/* Negotiate the fc mode to use */
- ixgbe_fc_autoneg(hw);
+ hw->mac.ops.fc_autoneg(hw);
/* Disable any previous flow control settings */
mflcn_reg = IXGBE_READ_REG(hw, IXGBE_MFLCN);
@@ -2231,8 +2279,8 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw)
* Find the intersection between advertised settings and link partner's
* advertised settings
**/
-static s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg,
- u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm)
+s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg,
+ u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm)
{
if ((!(adv_reg)) || (!(lp_reg)))
return IXGBE_ERR_FC_NOT_NEGOTIATED;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
index 6d4c260..5b3e3c6 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
@@ -49,6 +49,7 @@ s32 ixgbe_stop_adapter_generic(struct ixgbe_hw *hw);
s32 ixgbe_led_on_generic(struct ixgbe_hw *hw, u32 index);
s32 ixgbe_led_off_generic(struct ixgbe_hw *hw, u32 index);
+s32 ixgbe_init_led_link_act_generic(struct ixgbe_hw *hw);
s32 ixgbe_init_eeprom_params_generic(struct ixgbe_hw *hw);
s32 ixgbe_write_eeprom_generic(struct ixgbe_hw *hw, u16 offset, u16 data);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index f49f803..fd192bf 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -2225,11 +2225,11 @@ static int ixgbe_set_phys_id(struct net_device *netdev,
return 2;
case ETHTOOL_ID_ON:
- hw->mac.ops.led_on(hw, hw->bus.func);
+ hw->mac.ops.led_on(hw, hw->mac.led_link_act);
break;
case ETHTOOL_ID_OFF:
- hw->mac.ops.led_off(hw, hw->bus.func);
+ hw->mac.ops.led_off(hw, hw->mac.led_link_act);
break;
case ETHTOOL_ID_INACTIVE:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index cbd2cfa..2436984 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -54,6 +54,7 @@
#include <net/pkt_cls.h>
#include <net/tc_act/tc_gact.h>
#include <net/tc_act/tc_mirred.h>
+#include <net/vxlan.h>
#include "ixgbe.h"
#include "ixgbe_common.h"
@@ -3070,6 +3071,9 @@ static void ixgbe_free_irq(struct ixgbe_adapter *adapter)
return;
}
+ if (!adapter->msix_entries)
+ return;
+
for (vector = 0; vector < adapter->num_q_vectors; vector++) {
struct ixgbe_q_vector *q_vector = adapter->q_vector[vector];
struct msix_entry *entry = &adapter->msix_entries[vector];
@@ -5621,7 +5625,8 @@ static void ixgbe_init_dcb(struct ixgbe_adapter *adapter)
* Fields are initialized based on PCI device information and
* OS network device settings (MTU size).
**/
-static int ixgbe_sw_init(struct ixgbe_adapter *adapter)
+static int ixgbe_sw_init(struct ixgbe_adapter *adapter,
+ const struct ixgbe_info *ii)
{
struct ixgbe_hw *hw = &adapter->hw;
struct pci_dev *pdev = adapter->pdev;
@@ -5637,6 +5642,9 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter)
hw->subsystem_vendor_id = pdev->subsystem_vendor;
hw->subsystem_device_id = pdev->subsystem_device;
+ /* get_invariants needs the device IDs */
+ ii->get_invariants(hw);
+
/* Set common capability flags and settings */
rss = min_t(int, ixgbe_max_rss_indices(adapter), num_online_cpus());
adapter->ring_feature[RING_F_RSS].limit = rss;
@@ -7653,11 +7661,17 @@ static void ixgbe_atr(struct ixgbe_ring *ring,
/* snag network header to get L4 type and address */
skb = first->skb;
hdr.network = skb_network_header(skb);
+ if (unlikely(hdr.network <= skb->data))
+ return;
if (skb->encapsulation &&
first->protocol == htons(ETH_P_IP) &&
- hdr.ipv4->protocol != IPPROTO_UDP) {
+ hdr.ipv4->protocol == IPPROTO_UDP) {
struct ixgbe_adapter *adapter = q_vector->adapter;
+ if (unlikely(skb_tail_pointer(skb) < hdr.network +
+ VXLAN_HEADROOM))
+ return;
+
/* verify the port is recognized as VXLAN */
if (adapter->vxlan_port &&
udp_hdr(skb)->dest == adapter->vxlan_port)
@@ -7668,6 +7682,12 @@ static void ixgbe_atr(struct ixgbe_ring *ring,
hdr.network = skb_inner_network_header(skb);
}
+ /* Make sure we have at least [minimum IPv4 header + TCP]
+ * or [IPv6 header] bytes
+ */
+ if (unlikely(skb_tail_pointer(skb) < hdr.network + 40))
+ return;
+
/* Currently only IPv4/IPv6 with TCP is supported */
switch (hdr.ipv4->version) {
case IPVERSION:
@@ -7687,6 +7707,10 @@ static void ixgbe_atr(struct ixgbe_ring *ring,
if (l4_proto != IPPROTO_TCP)
return;
+ if (unlikely(skb_tail_pointer(skb) < hdr.network +
+ hlen + sizeof(struct tcphdr)))
+ return;
+
th = (struct tcphdr *)(hdr.network + hlen);
/* skip this packet since the socket is closing */
@@ -9162,10 +9186,14 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
goto fwd_add_err;
fwd_adapter->pool = pool;
fwd_adapter->real_adapter = adapter;
- err = ixgbe_fwd_ring_up(vdev, fwd_adapter);
- if (err)
- goto fwd_add_err;
- netif_tx_start_all_queues(vdev);
+
+ if (netif_running(pdev)) {
+ err = ixgbe_fwd_ring_up(vdev, fwd_adapter);
+ if (err)
+ goto fwd_add_err;
+ netif_tx_start_all_queues(vdev);
+ }
+
return fwd_adapter;
fwd_add_err:
/* unwind counter and free adapter struct */
@@ -9500,6 +9528,8 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
hw->mac.ops = *ii->mac_ops;
hw->mac.type = ii->mac;
hw->mvals = ii->mvals;
+ if (ii->link_ops)
+ hw->link.ops = *ii->link_ops;
/* EEPROM */
hw->eeprom.ops = *ii->eeprom_ops;
@@ -9523,10 +9553,8 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
hw->phy.mdio.mdio_read = ixgbe_mdio_read;
hw->phy.mdio.mdio_write = ixgbe_mdio_write;
- ii->get_invariants(hw);
-
/* setup the private structure */
- err = ixgbe_sw_init(adapter);
+ err = ixgbe_sw_init(adapter, ii);
if (err)
goto err_sw_init;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index 021ab9b..3b83620 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -109,8 +109,8 @@ static u8 ixgbe_ones_comp_byte_add(u8 add1, u8 add2)
*
* Returns an error code on error.
*/
-static s32 ixgbe_read_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr,
- u16 reg, u16 *val, bool lock)
+s32 ixgbe_read_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr,
+ u16 reg, u16 *val, bool lock)
{
u32 swfw_mask = hw->phy.phy_semaphore_mask;
int max_retry = 10;
@@ -178,36 +178,6 @@ static s32 ixgbe_read_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr,
}
/**
- * ixgbe_read_i2c_combined_generic - Perform I2C read combined operation
- * @hw: pointer to the hardware structure
- * @addr: I2C bus address to read from
- * @reg: I2C device register to read from
- * @val: pointer to location to receive read value
- *
- * Returns an error code on error.
- */
-s32 ixgbe_read_i2c_combined_generic(struct ixgbe_hw *hw, u8 addr,
- u16 reg, u16 *val)
-{
- return ixgbe_read_i2c_combined_generic_int(hw, addr, reg, val, true);
-}
-
-/**
- * ixgbe_read_i2c_combined_generic_unlocked - Unlocked I2C read combined
- * @hw: pointer to the hardware structure
- * @addr: I2C bus address to read from
- * @reg: I2C device register to read from
- * @val: pointer to location to receive read value
- *
- * Returns an error code on error.
- */
-s32 ixgbe_read_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, u8 addr,
- u16 reg, u16 *val)
-{
- return ixgbe_read_i2c_combined_generic_int(hw, addr, reg, val, false);
-}
-
-/**
* ixgbe_write_i2c_combined_generic_int - Perform I2C write combined operation
* @hw: pointer to the hardware structure
* @addr: I2C bus address to write to
@@ -217,8 +187,8 @@ s32 ixgbe_read_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, u8 addr,
*
* Returns an error code on error.
*/
-static s32 ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr,
- u16 reg, u16 val, bool lock)
+s32 ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr,
+ u16 reg, u16 val, bool lock)
{
u32 swfw_mask = hw->phy.phy_semaphore_mask;
int max_retry = 1;
@@ -273,33 +243,39 @@ static s32 ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr,
}
/**
- * ixgbe_write_i2c_combined_generic - Perform I2C write combined operation
- * @hw: pointer to the hardware structure
- * @addr: I2C bus address to write to
- * @reg: I2C device register to write to
- * @val: value to write
+ * ixgbe_probe_phy - Probe a single address for a PHY
+ * @hw: pointer to hardware structure
+ * @phy_addr: PHY address to probe
*
- * Returns an error code on error.
- */
-s32 ixgbe_write_i2c_combined_generic(struct ixgbe_hw *hw,
- u8 addr, u16 reg, u16 val)
+ * Returns true if PHY found
+ **/
+static bool ixgbe_probe_phy(struct ixgbe_hw *hw, u16 phy_addr)
{
- return ixgbe_write_i2c_combined_generic_int(hw, addr, reg, val, true);
-}
+ u16 ext_ability = 0;
-/**
- * ixgbe_write_i2c_combined_generic_unlocked - Unlocked I2C write combined
- * @hw: pointer to the hardware structure
- * @addr: I2C bus address to write to
- * @reg: I2C device register to write to
- * @val: value to write
- *
- * Returns an error code on error.
- */
-s32 ixgbe_write_i2c_combined_generic_unlocked(struct ixgbe_hw *hw,
- u8 addr, u16 reg, u16 val)
-{
- return ixgbe_write_i2c_combined_generic_int(hw, addr, reg, val, false);
+ hw->phy.mdio.prtad = phy_addr;
+ if (mdio45_probe(&hw->phy.mdio, phy_addr) != 0)
+ return false;
+
+ if (ixgbe_get_phy_id(hw))
+ return false;
+
+ hw->phy.type = ixgbe_get_phy_type_from_id(hw->phy.id);
+
+ if (hw->phy.type == ixgbe_phy_unknown) {
+ hw->phy.ops.read_reg(hw,
+ MDIO_PMA_EXTABLE,
+ MDIO_MMD_PMAPMD,
+ &ext_ability);
+ if (ext_ability &
+ (MDIO_PMA_EXTABLE_10GBT |
+ MDIO_PMA_EXTABLE_1000BT))
+ hw->phy.type = ixgbe_phy_cu_unknown;
+ else
+ hw->phy.type = ixgbe_phy_generic;
+ }
+
+ return true;
}
/**
@@ -311,7 +287,7 @@ s32 ixgbe_write_i2c_combined_generic_unlocked(struct ixgbe_hw *hw,
s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw)
{
u32 phy_addr;
- u16 ext_ability = 0;
+ u32 status = IXGBE_ERR_PHY_ADDR_INVALID;
if (!hw->phy.phy_semaphore_mask) {
if (hw->bus.lan_id)
@@ -320,37 +296,34 @@ s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw)
hw->phy.phy_semaphore_mask = IXGBE_GSSR_PHY0_SM;
}
- if (hw->phy.type == ixgbe_phy_unknown) {
- for (phy_addr = 0; phy_addr < IXGBE_MAX_PHY_ADDR; phy_addr++) {
- hw->phy.mdio.prtad = phy_addr;
- if (mdio45_probe(&hw->phy.mdio, phy_addr) == 0) {
- ixgbe_get_phy_id(hw);
- hw->phy.type =
- ixgbe_get_phy_type_from_id(hw->phy.id);
+ if (hw->phy.type != ixgbe_phy_unknown)
+ return 0;
- if (hw->phy.type == ixgbe_phy_unknown) {
- hw->phy.ops.read_reg(hw,
- MDIO_PMA_EXTABLE,
- MDIO_MMD_PMAPMD,
- &ext_ability);
- if (ext_ability &
- (MDIO_PMA_EXTABLE_10GBT |
- MDIO_PMA_EXTABLE_1000BT))
- hw->phy.type =
- ixgbe_phy_cu_unknown;
- else
- hw->phy.type =
- ixgbe_phy_generic;
- }
-
- return 0;
- }
- }
- /* indicate no PHY found */
- hw->phy.mdio.prtad = MDIO_PRTAD_NONE;
- return IXGBE_ERR_PHY_ADDR_INVALID;
+ if (hw->phy.nw_mng_if_sel) {
+ phy_addr = (hw->phy.nw_mng_if_sel &
+ IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD) >>
+ IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD_SHIFT;
+ if (ixgbe_probe_phy(hw, phy_addr))
+ return 0;
+ else
+ return IXGBE_ERR_PHY_ADDR_INVALID;
}
- return 0;
+
+ for (phy_addr = 0; phy_addr < IXGBE_MAX_PHY_ADDR; phy_addr++) {
+ if (ixgbe_probe_phy(hw, phy_addr)) {
+ status = 0;
+ break;
+ }
+ }
+
+ /* Certain media types do not have a phy so an address will not
+ * be found and the code will take this path. Caller has to
+ * decide if it is an error or not.
+ */
+ if (status)
+ hw->phy.mdio.prtad = MDIO_PRTAD_NONE;
+
+ return status;
}
/**
@@ -416,7 +389,8 @@ static enum ixgbe_phy_type ixgbe_get_phy_type_from_id(u32 phy_id)
case TN1010_PHY_ID:
phy_type = ixgbe_phy_tn;
break;
- case X550_PHY_ID:
+ case X550_PHY_ID2:
+ case X550_PHY_ID3:
case X540_PHY_ID:
phy_type = ixgbe_phy_aq;
break;
@@ -427,6 +401,7 @@ static enum ixgbe_phy_type ixgbe_get_phy_type_from_id(u32 phy_id)
phy_type = ixgbe_phy_nl;
break;
case X557_PHY_ID:
+ case X557_PHY_ID2:
phy_type = ixgbe_phy_x550em_ext_t;
break;
default:
@@ -477,8 +452,7 @@ s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw)
*/
for (i = 0; i < 30; i++) {
msleep(100);
- hw->phy.ops.read_reg(hw, MDIO_CTRL1,
- MDIO_MMD_PHYXS, &ctrl);
+ hw->phy.ops.read_reg(hw, MDIO_CTRL1, MDIO_MMD_PHYXS, &ctrl);
if (!(ctrl & MDIO_CTRL1_RESET)) {
udelay(2);
break;
@@ -705,53 +679,52 @@ s32 ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw)
ixgbe_get_copper_link_capabilities_generic(hw, &speed, &autoneg);
- if (speed & IXGBE_LINK_SPEED_10GB_FULL) {
- /* Set or unset auto-negotiation 10G advertisement */
- hw->phy.ops.read_reg(hw, MDIO_AN_10GBT_CTRL,
- MDIO_MMD_AN,
- &autoneg_reg);
+ /* Set or unset auto-negotiation 10G advertisement */
+ hw->phy.ops.read_reg(hw, MDIO_AN_10GBT_CTRL, MDIO_MMD_AN, &autoneg_reg);
- autoneg_reg &= ~MDIO_AN_10GBT_CTRL_ADV10G;
- if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL)
- autoneg_reg |= MDIO_AN_10GBT_CTRL_ADV10G;
+ autoneg_reg &= ~MDIO_AN_10GBT_CTRL_ADV10G;
+ if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) &&
+ (speed & IXGBE_LINK_SPEED_10GB_FULL))
+ autoneg_reg |= MDIO_AN_10GBT_CTRL_ADV10G;
- hw->phy.ops.write_reg(hw, MDIO_AN_10GBT_CTRL,
- MDIO_MMD_AN,
- autoneg_reg);
+ hw->phy.ops.write_reg(hw, MDIO_AN_10GBT_CTRL, MDIO_MMD_AN, autoneg_reg);
+
+ hw->phy.ops.read_reg(hw, IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG,
+ MDIO_MMD_AN, &autoneg_reg);
+
+ if (hw->mac.type == ixgbe_mac_X550) {
+ /* Set or unset auto-negotiation 5G advertisement */
+ autoneg_reg &= ~IXGBE_MII_5GBASE_T_ADVERTISE;
+ if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_5GB_FULL) &&
+ (speed & IXGBE_LINK_SPEED_5GB_FULL))
+ autoneg_reg |= IXGBE_MII_5GBASE_T_ADVERTISE;
+
+ /* Set or unset auto-negotiation 2.5G advertisement */
+ autoneg_reg &= ~IXGBE_MII_2_5GBASE_T_ADVERTISE;
+ if ((hw->phy.autoneg_advertised &
+ IXGBE_LINK_SPEED_2_5GB_FULL) &&
+ (speed & IXGBE_LINK_SPEED_2_5GB_FULL))
+ autoneg_reg |= IXGBE_MII_2_5GBASE_T_ADVERTISE;
}
- if (speed & IXGBE_LINK_SPEED_1GB_FULL) {
- /* Set or unset auto-negotiation 1G advertisement */
- hw->phy.ops.read_reg(hw,
- IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG,
- MDIO_MMD_AN,
- &autoneg_reg);
+ /* Set or unset auto-negotiation 1G advertisement */
+ autoneg_reg &= ~IXGBE_MII_1GBASE_T_ADVERTISE;
+ if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) &&
+ (speed & IXGBE_LINK_SPEED_1GB_FULL))
+ autoneg_reg |= IXGBE_MII_1GBASE_T_ADVERTISE;
- autoneg_reg &= ~IXGBE_MII_1GBASE_T_ADVERTISE;
- if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL)
- autoneg_reg |= IXGBE_MII_1GBASE_T_ADVERTISE;
+ hw->phy.ops.write_reg(hw, IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG,
+ MDIO_MMD_AN, autoneg_reg);
- hw->phy.ops.write_reg(hw,
- IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG,
- MDIO_MMD_AN,
- autoneg_reg);
- }
+ /* Set or unset auto-negotiation 100M advertisement */
+ hw->phy.ops.read_reg(hw, MDIO_AN_ADVERTISE, MDIO_MMD_AN, &autoneg_reg);
- if (speed & IXGBE_LINK_SPEED_100_FULL) {
- /* Set or unset auto-negotiation 100M advertisement */
- hw->phy.ops.read_reg(hw, MDIO_AN_ADVERTISE,
- MDIO_MMD_AN,
- &autoneg_reg);
+ autoneg_reg &= ~(ADVERTISE_100FULL | ADVERTISE_100HALF);
+ if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) &&
+ (speed & IXGBE_LINK_SPEED_100_FULL))
+ autoneg_reg |= ADVERTISE_100FULL;
- autoneg_reg &= ~(ADVERTISE_100FULL |
- ADVERTISE_100HALF);
- if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL)
- autoneg_reg |= ADVERTISE_100FULL;
-
- hw->phy.ops.write_reg(hw, MDIO_AN_ADVERTISE,
- MDIO_MMD_AN,
- autoneg_reg);
- }
+ hw->phy.ops.write_reg(hw, MDIO_AN_ADVERTISE, MDIO_MMD_AN, autoneg_reg);
/* Blocked by MNG FW so don't reset PHY */
if (ixgbe_check_reset_blocked(hw))
@@ -830,6 +803,7 @@ static s32 ixgbe_get_copper_speeds_supported(struct ixgbe_hw *hw)
hw->phy.speeds_supported |= IXGBE_LINK_SPEED_5GB_FULL;
break;
case ixgbe_mac_X550EM_x:
+ case ixgbe_mac_x550em_a:
hw->phy.speeds_supported &= ~IXGBE_LINK_SPEED_100_FULL;
break;
default:
@@ -2396,9 +2370,7 @@ s32 ixgbe_set_copper_phy_power(struct ixgbe_hw *hw, bool on)
if (!on && ixgbe_mng_present(hw))
return 0;
- status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_VENDOR_SPECIFIC_1_CONTROL,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
- ®);
+ status = hw->phy.ops.read_reg(hw, MDIO_CTRL1, MDIO_MMD_VEND1, ®);
if (status)
return status;
@@ -2410,8 +2382,6 @@ s32 ixgbe_set_copper_phy_power(struct ixgbe_hw *hw, bool on)
reg |= IXGBE_MDIO_PHY_SET_LOW_POWER_MODE;
}
- status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_VENDOR_SPECIFIC_1_CONTROL,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
- reg);
+ status = hw->phy.ops.write_reg(hw, MDIO_CTRL1, MDIO_MMD_VEND1, reg);
return status;
}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
index cc735ec..ecf05f8 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
@@ -195,12 +195,8 @@ s32 ixgbe_read_i2c_sff8472_generic(struct ixgbe_hw *hw, u8 byte_offset,
u8 *sff8472_data);
s32 ixgbe_write_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset,
u8 eeprom_data);
-s32 ixgbe_read_i2c_combined_generic(struct ixgbe_hw *hw, u8 addr,
- u16 reg, u16 *val);
-s32 ixgbe_read_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, u8 addr,
- u16 reg, u16 *val);
-s32 ixgbe_write_i2c_combined_generic(struct ixgbe_hw *hw, u8 addr,
- u16 reg, u16 val);
-s32 ixgbe_write_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, u8 addr,
- u16 reg, u16 val);
+s32 ixgbe_read_i2c_combined_generic_int(struct ixgbe_hw *, u8 addr, u16 reg,
+ u16 *val, bool lock);
+s32 ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *, u8 addr, u16 reg,
+ u16 val, bool lock);
#endif /* _IXGBE_PHY_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index 31d82e3..cf21273 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -874,19 +874,13 @@ struct ixgbe_thermal_sensor_data {
#define IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_1GB 0x4 /* 1Gb/s */
#define IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_10GB 0x6 /* 10Gb/s */
-#define IXGBE_MII_10GBASE_T_AUTONEG_CTRL_REG 0x20 /* 10G Control Reg */
#define IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG 0xC400 /* 1G Provisioning 1 */
#define IXGBE_MII_AUTONEG_XNP_TX_REG 0x17 /* 1G XNP Transmit */
-#define IXGBE_MII_AUTONEG_ADVERTISE_REG 0x10 /* 100M Advertisement */
-#define IXGBE_MII_10GBASE_T_ADVERTISE 0x1000 /* full duplex, bit:12*/
#define IXGBE_MII_1GBASE_T_ADVERTISE_XNP_TX 0x4000 /* full duplex, bit:14*/
#define IXGBE_MII_1GBASE_T_ADVERTISE 0x8000 /* full duplex, bit:15*/
#define IXGBE_MII_2_5GBASE_T_ADVERTISE 0x0400
#define IXGBE_MII_5GBASE_T_ADVERTISE 0x0800
-#define IXGBE_MII_100BASE_T_ADVERTISE 0x0100 /* full duplex, bit:8 */
-#define IXGBE_MII_100BASE_T_ADVERTISE_HALF 0x0080 /* half duplex, bit:7 */
#define IXGBE_MII_RESTART 0x200
-#define IXGBE_MII_AUTONEG_COMPLETE 0x20
#define IXGBE_MII_AUTONEG_LINK_UP 0x04
#define IXGBE_MII_AUTONEG_REG 0x0
@@ -1320,30 +1314,20 @@ struct ixgbe_thermal_sensor_data {
/* MDIO definitions */
#define IXGBE_MDIO_ZERO_DEV_TYPE 0x0
-#define IXGBE_MDIO_PMA_PMD_DEV_TYPE 0x1
#define IXGBE_MDIO_PCS_DEV_TYPE 0x3
-#define IXGBE_MDIO_PHY_XS_DEV_TYPE 0x4
-#define IXGBE_MDIO_AUTO_NEG_DEV_TYPE 0x7
-#define IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE 0x1E /* Device 30 */
#define IXGBE_TWINAX_DEV 1
#define IXGBE_MDIO_COMMAND_TIMEOUT 100 /* PHY Timeout for 1 GB mode */
-#define IXGBE_MDIO_VENDOR_SPECIFIC_1_CONTROL 0x0 /* VS1 Control Reg */
-#define IXGBE_MDIO_VENDOR_SPECIFIC_1_STATUS 0x1 /* VS1 Status Reg */
#define IXGBE_MDIO_VENDOR_SPECIFIC_1_LINK_STATUS 0x0008 /* 1 = Link Up */
#define IXGBE_MDIO_VENDOR_SPECIFIC_1_SPEED_STATUS 0x0010 /* 0 - 10G, 1 - 1G */
#define IXGBE_MDIO_VENDOR_SPECIFIC_1_10G_SPEED 0x0018
#define IXGBE_MDIO_VENDOR_SPECIFIC_1_1G_SPEED 0x0010
-#define IXGBE_MDIO_AUTO_NEG_CONTROL 0x0 /* AUTO_NEG Control Reg */
-#define IXGBE_MDIO_AUTO_NEG_STATUS 0x1 /* AUTO_NEG Status Reg */
#define IXGBE_MDIO_AUTO_NEG_VENDOR_STAT 0xC800 /* AUTO_NEG Vendor Status Reg */
#define IXGBE_MDIO_AUTO_NEG_VENDOR_TX_ALARM 0xCC00 /* AUTO_NEG Vendor TX Reg */
#define IXGBE_MDIO_AUTO_NEG_VENDOR_TX_ALARM2 0xCC01 /* AUTO_NEG Vendor Tx Reg */
#define IXGBE_MDIO_AUTO_NEG_VEN_LSC 0x1 /* AUTO_NEG Vendor Tx LSC */
-#define IXGBE_MDIO_AUTO_NEG_ADVT 0x10 /* AUTO_NEG Advt Reg */
-#define IXGBE_MDIO_AUTO_NEG_LP 0x13 /* AUTO_NEG LP Status Reg */
#define IXGBE_MDIO_AUTO_NEG_EEE_ADVT 0x3C /* AUTO_NEG EEE Advt Reg */
#define IXGBE_MDIO_PHY_SET_LOW_POWER_MODE 0x0800 /* Set low power mode */
@@ -1393,8 +1377,10 @@ struct ixgbe_thermal_sensor_data {
#define TN1010_PHY_ID 0x00A19410
#define TNX_FW_REV 0xB
#define X540_PHY_ID 0x01540200
-#define X550_PHY_ID 0x01540220
+#define X550_PHY_ID2 0x01540223
+#define X550_PHY_ID3 0x01540221
#define X557_PHY_ID 0x01540240
+#define X557_PHY_ID2 0x01540250
#define QT2022_PHY_ID 0x0043A400
#define ATH_PHY_ID 0x03429050
#define AQ_FW_REV 0x20
@@ -3352,6 +3338,7 @@ struct ixgbe_mac_operations {
s32 (*led_off)(struct ixgbe_hw *, u32);
s32 (*blink_led_start)(struct ixgbe_hw *, u32);
s32 (*blink_led_stop)(struct ixgbe_hw *, u32);
+ s32 (*init_led_link_act)(struct ixgbe_hw *);
/* RAR, Multicast, VLAN */
s32 (*set_rar)(struct ixgbe_hw *, u32, u8 *, u32, u32);
@@ -3372,6 +3359,7 @@ struct ixgbe_mac_operations {
/* Flow Control */
s32 (*fc_enable)(struct ixgbe_hw *);
s32 (*setup_fc)(struct ixgbe_hw *);
+ void (*fc_autoneg)(struct ixgbe_hw *);
/* Manageability interface */
s32 (*set_fw_drv_ver)(struct ixgbe_hw *, u8, u8, u8, u8);
@@ -3410,16 +3398,28 @@ struct ixgbe_phy_operations {
s32 (*read_i2c_sff8472)(struct ixgbe_hw *, u8 , u8 *);
s32 (*read_i2c_eeprom)(struct ixgbe_hw *, u8 , u8 *);
s32 (*write_i2c_eeprom)(struct ixgbe_hw *, u8, u8);
- s32 (*read_i2c_combined)(struct ixgbe_hw *, u8 addr, u16 reg, u16 *val);
- s32 (*write_i2c_combined)(struct ixgbe_hw *, u8 addr, u16 reg, u16 val);
s32 (*check_overtemp)(struct ixgbe_hw *);
s32 (*set_phy_power)(struct ixgbe_hw *, bool on);
s32 (*enter_lplu)(struct ixgbe_hw *);
s32 (*handle_lasi)(struct ixgbe_hw *hw);
- s32 (*read_i2c_combined_unlocked)(struct ixgbe_hw *, u8 addr, u16 reg,
- u16 *value);
- s32 (*write_i2c_combined_unlocked)(struct ixgbe_hw *, u8 addr, u16 reg,
- u16 value);
+ s32 (*read_i2c_byte_unlocked)(struct ixgbe_hw *, u8 offset, u8 addr,
+ u8 *value);
+ s32 (*write_i2c_byte_unlocked)(struct ixgbe_hw *, u8 offset, u8 addr,
+ u8 value);
+};
+
+struct ixgbe_link_operations {
+ s32 (*read_link)(struct ixgbe_hw *, u8 addr, u16 reg, u16 *val);
+ s32 (*read_link_unlocked)(struct ixgbe_hw *, u8 addr, u16 reg,
+ u16 *val);
+ s32 (*write_link)(struct ixgbe_hw *, u8 addr, u16 reg, u16 val);
+ s32 (*write_link_unlocked)(struct ixgbe_hw *, u8 addr, u16 reg,
+ u16 val);
+};
+
+struct ixgbe_link_info {
+ struct ixgbe_link_operations ops;
+ u8 addr;
};
struct ixgbe_eeprom_info {
@@ -3462,6 +3462,7 @@ struct ixgbe_mac_info {
u8 san_mac_rar_index;
struct ixgbe_thermal_sensor_data thermal_sensor_data;
bool set_lben;
+ u8 led_link_act;
};
struct ixgbe_phy_info {
@@ -3523,6 +3524,7 @@ struct ixgbe_hw {
struct ixgbe_addr_filter_info addr_ctrl;
struct ixgbe_fc_info fc;
struct ixgbe_phy_info phy;
+ struct ixgbe_link_info link;
struct ixgbe_eeprom_info eeprom;
struct ixgbe_bus_info bus;
struct ixgbe_mbx_info mbx;
@@ -3546,6 +3548,7 @@ struct ixgbe_info {
const struct ixgbe_eeprom_operations *eeprom_ops;
const struct ixgbe_phy_operations *phy_ops;
const struct ixgbe_mbx_operations *mbx_ops;
+ const struct ixgbe_link_operations *link_ops;
const u32 *mvals;
};
@@ -3593,17 +3596,35 @@ struct ixgbe_info {
#define IXGBE_FUSES0_REV_MASK (3u << 6)
#define IXGBE_KRM_PORT_CAR_GEN_CTRL(P) ((P) ? 0x8010 : 0x4010)
+#define IXGBE_KRM_LINK_S1(P) ((P) ? 0x8200 : 0x4200)
#define IXGBE_KRM_LINK_CTRL_1(P) ((P) ? 0x820C : 0x420C)
#define IXGBE_KRM_AN_CNTL_1(P) ((P) ? 0x822C : 0x422C)
#define IXGBE_KRM_AN_CNTL_8(P) ((P) ? 0x8248 : 0x4248)
#define IXGBE_KRM_SGMII_CTRL(P) ((P) ? 0x82A0 : 0x42A0)
+#define IXGBE_KRM_LP_BASE_PAGE_HIGH(P) ((P) ? 0x836C : 0x436C)
#define IXGBE_KRM_DSP_TXFFE_STATE_4(P) ((P) ? 0x8634 : 0x4634)
#define IXGBE_KRM_DSP_TXFFE_STATE_5(P) ((P) ? 0x8638 : 0x4638)
#define IXGBE_KRM_RX_TRN_LINKUP_CTRL(P) ((P) ? 0x8B00 : 0x4B00)
#define IXGBE_KRM_PMD_DFX_BURNIN(P) ((P) ? 0x8E00 : 0x4E00)
+#define IXGBE_KRM_PMD_FLX_MASK_ST20(P) ((P) ? 0x9054 : 0x5054)
#define IXGBE_KRM_TX_COEFF_CTRL_1(P) ((P) ? 0x9520 : 0x5520)
#define IXGBE_KRM_RX_ANA_CTL(P) ((P) ? 0x9A00 : 0x5A00)
+#define IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_DA ~(0x3 << 20)
+#define IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_SR BIT(20)
+#define IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_LR (0x2 << 20)
+#define IXGBE_KRM_PMD_FLX_MASK_ST20_SGMII_EN BIT(25)
+#define IXGBE_KRM_PMD_FLX_MASK_ST20_AN37_EN BIT(26)
+#define IXGBE_KRM_PMD_FLX_MASK_ST20_AN_EN BIT(27)
+#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_10M ~(0x7 << 28)
+#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_100M BIT(28)
+#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_1G (0x2 << 28)
+#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_10G (0x3 << 28)
+#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_AN (0x4 << 28)
+#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_2_5G (0x7 << 28)
+#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_MASK (0x7 << 28)
+#define IXGBE_KRM_PMD_FLX_MASK_ST20_FW_AN_RESTART BIT(31)
+
#define IXGBE_KRM_PORT_CAR_GEN_CTRL_NELB_32B BIT(9)
#define IXGBE_KRM_PORT_CAR_GEN_CTRL_NELB_KRPCS BIT(11)
@@ -3618,6 +3639,7 @@ struct ixgbe_info {
#define IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KR BIT(18)
#define IXGBE_KRM_LINK_CTRL_1_TETH_EEE_CAP_KX BIT(24)
#define IXGBE_KRM_LINK_CTRL_1_TETH_EEE_CAP_KR BIT(26)
+#define IXGBE_KRM_LINK_S1_MAC_AN_COMPLETE BIT(28)
#define IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE BIT(29)
#define IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART BIT(31)
@@ -3627,6 +3649,8 @@ struct ixgbe_info {
#define IXGBE_KRM_AN_CNTL_8_LINEAR BIT(0)
#define IXGBE_KRM_AN_CNTL_8_LIMITING BIT(1)
+#define IXGBE_KRM_LP_BASE_PAGE_HIGH_SYM_PAUSE BIT(10)
+#define IXGBE_KRM_LP_BASE_PAGE_HIGH_ASM_PAUSE BIT(11)
#define IXGBE_KRM_SGMII_CTRL_MAC_TAR_FORCE_100_D BIT(12)
#define IXGBE_KRM_SGMII_CTRL_MAC_TAR_FORCE_10_D BIT(19)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
index f2b1d48..e2ff823 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
@@ -851,6 +851,7 @@ static const struct ixgbe_mac_operations mac_ops_X540 = {
.get_link_capabilities = &ixgbe_get_copper_link_capabilities_generic,
.led_on = &ixgbe_led_on_generic,
.led_off = &ixgbe_led_off_generic,
+ .init_led_link_act = ixgbe_init_led_link_act_generic,
.blink_led_start = &ixgbe_blink_led_start_X540,
.blink_led_stop = &ixgbe_blink_led_stop_X540,
.set_rar = &ixgbe_set_rar_generic,
@@ -866,6 +867,7 @@ static const struct ixgbe_mac_operations mac_ops_X540 = {
.set_vfta = &ixgbe_set_vfta_generic,
.fc_enable = &ixgbe_fc_enable_generic,
.setup_fc = ixgbe_setup_fc_generic,
+ .fc_autoneg = ixgbe_fc_autoneg,
.set_fw_drv_ver = &ixgbe_set_fw_drv_ver_generic,
.init_uta_tables = &ixgbe_init_uta_tables_generic,
.setup_sfp = NULL,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index 7e6b926..11fb433 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -28,11 +28,31 @@
static s32 ixgbe_setup_kr_speed_x550em(struct ixgbe_hw *, ixgbe_link_speed);
static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *);
+static void ixgbe_fc_autoneg_fiber_x550em_a(struct ixgbe_hw *);
+static void ixgbe_fc_autoneg_backplane_x550em_a(struct ixgbe_hw *);
+static s32 ixgbe_setup_fc_backplane_x550em_a(struct ixgbe_hw *);
static s32 ixgbe_get_invariants_X550_x(struct ixgbe_hw *hw)
{
struct ixgbe_mac_info *mac = &hw->mac;
struct ixgbe_phy_info *phy = &hw->phy;
+ struct ixgbe_link_info *link = &hw->link;
+
+ /* Start with X540 invariants, since so simular */
+ ixgbe_get_invariants_X540(hw);
+
+ if (mac->ops.get_media_type(hw) != ixgbe_media_type_copper)
+ phy->ops.set_phy_power = NULL;
+
+ link->addr = IXGBE_CS4227;
+
+ return 0;
+}
+
+static s32 ixgbe_get_invariants_X550_a(struct ixgbe_hw *hw)
+{
+ struct ixgbe_mac_info *mac = &hw->mac;
+ struct ixgbe_phy_info *phy = &hw->phy;
/* Start with X540 invariants, since so simular */
ixgbe_get_invariants_X540(hw);
@@ -69,8 +89,7 @@ static void ixgbe_setup_mux_ctl(struct ixgbe_hw *hw)
*/
static s32 ixgbe_read_cs4227(struct ixgbe_hw *hw, u16 reg, u16 *value)
{
- return hw->phy.ops.read_i2c_combined_unlocked(hw, IXGBE_CS4227, reg,
- value);
+ return hw->link.ops.read_link_unlocked(hw, hw->link.addr, reg, value);
}
/**
@@ -83,8 +102,7 @@ static s32 ixgbe_read_cs4227(struct ixgbe_hw *hw, u16 reg, u16 *value)
*/
static s32 ixgbe_write_cs4227(struct ixgbe_hw *hw, u16 reg, u16 value)
{
- return hw->phy.ops.write_i2c_combined_unlocked(hw, IXGBE_CS4227, reg,
- value);
+ return hw->link.ops.write_link_unlocked(hw, hw->link.addr, reg, value);
}
/**
@@ -322,6 +340,68 @@ static s32 ixgbe_write_phy_reg_x550em(struct ixgbe_hw *hw, u32 reg_addr,
return IXGBE_NOT_IMPLEMENTED;
}
+/**
+ * ixgbe_read_i2c_combined_generic - Perform I2C read combined operation
+ * @hw: pointer to the hardware structure
+ * @addr: I2C bus address to read from
+ * @reg: I2C device register to read from
+ * @val: pointer to location to receive read value
+ *
+ * Returns an error code on error.
+ **/
+static s32 ixgbe_read_i2c_combined_generic(struct ixgbe_hw *hw, u8 addr,
+ u16 reg, u16 *val)
+{
+ return ixgbe_read_i2c_combined_generic_int(hw, addr, reg, val, true);
+}
+
+/**
+ * ixgbe_read_i2c_combined_generic_unlocked - Do I2C read combined operation
+ * @hw: pointer to the hardware structure
+ * @addr: I2C bus address to read from
+ * @reg: I2C device register to read from
+ * @val: pointer to location to receive read value
+ *
+ * Returns an error code on error.
+ **/
+static s32
+ixgbe_read_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, u8 addr,
+ u16 reg, u16 *val)
+{
+ return ixgbe_read_i2c_combined_generic_int(hw, addr, reg, val, false);
+}
+
+/**
+ * ixgbe_write_i2c_combined_generic - Perform I2C write combined operation
+ * @hw: pointer to the hardware structure
+ * @addr: I2C bus address to write to
+ * @reg: I2C device register to write to
+ * @val: value to write
+ *
+ * Returns an error code on error.
+ **/
+static s32 ixgbe_write_i2c_combined_generic(struct ixgbe_hw *hw,
+ u8 addr, u16 reg, u16 val)
+{
+ return ixgbe_write_i2c_combined_generic_int(hw, addr, reg, val, true);
+}
+
+/**
+ * ixgbe_write_i2c_combined_generic_unlocked - Do I2C write combined operation
+ * @hw: pointer to the hardware structure
+ * @addr: I2C bus address to write to
+ * @reg: I2C device register to write to
+ * @val: value to write
+ *
+ * Returns an error code on error.
+ **/
+static s32
+ixgbe_write_i2c_combined_generic_unlocked(struct ixgbe_hw *hw,
+ u8 addr, u16 reg, u16 val)
+{
+ return ixgbe_write_i2c_combined_generic_int(hw, addr, reg, val, false);
+}
+
/** ixgbe_init_eeprom_params_X550 - Initialize EEPROM params
* @hw: pointer to hardware structure
*
@@ -1128,47 +1208,17 @@ static s32 ixgbe_write_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr,
return ret;
}
-/** ixgbe_setup_ixfi_x550em - Configure the KR PHY for iXFI mode.
+/**
+ * ixgbe_setup_ixfi_x550em_x - MAC specific iXFI configuration
* @hw: pointer to hardware structure
- * @speed: the link speed to force
*
- * Configures the integrated KR PHY to use iXFI mode. Used to connect an
- * internal and external PHY at a specific speed, without autonegotiation.
+ * iXfI configuration needed for ixgbe_mac_X550EM_x devices.
**/
-static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed)
+static s32 ixgbe_setup_ixfi_x550em_x(struct ixgbe_hw *hw)
{
s32 status;
u32 reg_val;
- /* Disable AN and force speed to 10G Serial. */
- status = ixgbe_read_iosf_sb_reg_x550(hw,
- IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
- IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val);
- if (status)
- return status;
-
- reg_val &= ~IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE;
- reg_val &= ~IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_MASK;
-
- /* Select forced link speed for internal PHY. */
- switch (*speed) {
- case IXGBE_LINK_SPEED_10GB_FULL:
- reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_10G;
- break;
- case IXGBE_LINK_SPEED_1GB_FULL:
- reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_1G;
- break;
- default:
- /* Other link speeds are not supported by internal KR PHY. */
- return IXGBE_ERR_LINK_SETUP;
- }
-
- status = ixgbe_write_iosf_sb_reg_x550(hw,
- IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
- IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
- if (status)
- return status;
-
/* Disable training protocol FSM. */
status = ixgbe_read_iosf_sb_reg_x550(hw,
IXGBE_KRM_RX_TRN_LINKUP_CTRL(hw->bus.lan_id),
@@ -1228,20 +1278,106 @@ static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed)
status = ixgbe_write_iosf_sb_reg_x550(hw,
IXGBE_KRM_TX_COEFF_CTRL_1(hw->bus.lan_id),
IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
- if (status)
- return status;
+ return status;
+}
- /* Toggle port SW reset by AN reset. */
- status = ixgbe_read_iosf_sb_reg_x550(hw,
+/**
+ * ixgbe_restart_an_internal_phy_x550em - restart autonegotiation for the
+ * internal PHY
+ * @hw: pointer to hardware structure
+ **/
+static s32 ixgbe_restart_an_internal_phy_x550em(struct ixgbe_hw *hw)
+{
+ s32 status;
+ u32 link_ctrl;
+
+ /* Restart auto-negotiation. */
+ status = hw->mac.ops.read_iosf_sb_reg(hw,
IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
- IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val);
+ IXGBE_SB_IOSF_TARGET_KR_PHY, &link_ctrl);
+
+ if (status) {
+ hw_dbg(hw, "Auto-negotiation did not complete\n");
+ return status;
+ }
+
+ link_ctrl |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART;
+ status = hw->mac.ops.write_iosf_sb_reg(hw,
+ IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, link_ctrl);
+
+ if (hw->mac.type == ixgbe_mac_x550em_a) {
+ u32 flx_mask_st20;
+
+ /* Indicate to FW that AN restart has been asserted */
+ status = hw->mac.ops.read_iosf_sb_reg(hw,
+ IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, &flx_mask_st20);
+
+ if (status) {
+ hw_dbg(hw, "Auto-negotiation did not complete\n");
+ return status;
+ }
+
+ flx_mask_st20 |= IXGBE_KRM_PMD_FLX_MASK_ST20_FW_AN_RESTART;
+ status = hw->mac.ops.write_iosf_sb_reg(hw,
+ IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, flx_mask_st20);
+ }
+
+ return status;
+}
+
+/** ixgbe_setup_ixfi_x550em - Configure the KR PHY for iXFI mode.
+ * @hw: pointer to hardware structure
+ * @speed: the link speed to force
+ *
+ * Configures the integrated KR PHY to use iXFI mode. Used to connect an
+ * internal and external PHY at a specific speed, without autonegotiation.
+ **/
+static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed)
+{
+ s32 status;
+ u32 reg_val;
+
+ /* Disable AN and force speed to 10G Serial. */
+ status = ixgbe_read_iosf_sb_reg_x550(hw,
+ IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val);
if (status)
return status;
- reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART;
+ reg_val &= ~IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE;
+ reg_val &= ~IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_MASK;
+
+ /* Select forced link speed for internal PHY. */
+ switch (*speed) {
+ case IXGBE_LINK_SPEED_10GB_FULL:
+ reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_10G;
+ break;
+ case IXGBE_LINK_SPEED_1GB_FULL:
+ reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_1G;
+ break;
+ default:
+ /* Other link speeds are not supported by internal KR PHY. */
+ return IXGBE_ERR_LINK_SETUP;
+ }
+
status = ixgbe_write_iosf_sb_reg_x550(hw,
IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
+ if (status)
+ return status;
+
+ /* Additional configuration needed for x550em_x */
+ if (hw->mac.type == ixgbe_mac_X550EM_x) {
+ status = ixgbe_setup_ixfi_x550em_x(hw);
+ if (status)
+ return status;
+ }
+
+ /* Toggle port SW reset by AN reset. */
+ status = ixgbe_restart_an_internal_phy_x550em(hw);
return status;
}
@@ -1292,7 +1428,7 @@ ixgbe_setup_mac_link_sfp_x550em(struct ixgbe_hw *hw,
__always_unused bool autoneg_wait_to_complete)
{
s32 status;
- u16 slice, value;
+ u16 reg_slice, reg_val;
bool setup_linear = false;
/* Check if SFP module is supported and linear */
@@ -1308,71 +1444,68 @@ ixgbe_setup_mac_link_sfp_x550em(struct ixgbe_hw *hw,
if (status)
return status;
- if (!(hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE)) {
- /* Configure CS4227 LINE side to 10G SR. */
- slice = IXGBE_CS4227_LINE_SPARE22_MSB + (hw->bus.lan_id << 12);
- value = IXGBE_CS4227_SPEED_10G;
- status = ixgbe_write_i2c_combined_generic(hw, IXGBE_CS4227,
- slice, value);
- if (status)
- goto i2c_err;
+ /* Configure internal PHY for KR/KX. */
+ ixgbe_setup_kr_speed_x550em(hw, speed);
- slice = IXGBE_CS4227_LINE_SPARE24_LSB + (hw->bus.lan_id << 12);
- value = (IXGBE_CS4227_EDC_MODE_SR << 1) | 1;
- status = ixgbe_write_i2c_combined_generic(hw, IXGBE_CS4227,
- slice, value);
- if (status)
- goto i2c_err;
+ /* Configure CS4227 LINE side to proper mode. */
+ reg_slice = IXGBE_CS4227_LINE_SPARE24_LSB + (hw->bus.lan_id << 12);
+ if (setup_linear)
+ reg_val = (IXGBE_CS4227_EDC_MODE_CX1 << 1) | 0x1;
+ else
+ reg_val = (IXGBE_CS4227_EDC_MODE_SR << 1) | 0x1;
- /* Configure CS4227 for HOST connection rate then type. */
- slice = IXGBE_CS4227_HOST_SPARE22_MSB + (hw->bus.lan_id << 12);
- value = speed & IXGBE_LINK_SPEED_10GB_FULL ?
- IXGBE_CS4227_SPEED_10G : IXGBE_CS4227_SPEED_1G;
- status = ixgbe_write_i2c_combined_generic(hw, IXGBE_CS4227,
- slice, value);
- if (status)
- goto i2c_err;
+ status = hw->link.ops.write_link(hw, hw->link.addr, reg_slice,
+ reg_val);
- slice = IXGBE_CS4227_HOST_SPARE24_LSB + (hw->bus.lan_id << 12);
- if (setup_linear)
- value = (IXGBE_CS4227_EDC_MODE_CX1 << 1) | 1;
- else
- value = (IXGBE_CS4227_EDC_MODE_SR << 1) | 1;
- status = ixgbe_write_i2c_combined_generic(hw, IXGBE_CS4227,
- slice, value);
- if (status)
- goto i2c_err;
+ return status;
+}
- /* Setup XFI internal link. */
- status = ixgbe_setup_ixfi_x550em(hw, &speed);
- if (status) {
- hw_dbg(hw, "setup_ixfi failed with %d\n", status);
- return status;
- }
- } else {
- /* Configure internal PHY for KR/KX. */
- status = ixgbe_setup_kr_speed_x550em(hw, speed);
- if (status) {
- hw_dbg(hw, "setup_kr_speed failed with %d\n", status);
- return status;
- }
+/**
+ * ixgbe_setup_sfi_x550a - Configure the internal PHY for native SFI mode
+ * @hw: pointer to hardware structure
+ * @speed: the link speed to force
+ *
+ * Configures the integrated PHY for native SFI mode. Used to connect the
+ * internal PHY directly to an SFP cage, without autonegotiation.
+ **/
+static s32 ixgbe_setup_sfi_x550a(struct ixgbe_hw *hw, ixgbe_link_speed *speed)
+{
+ struct ixgbe_mac_info *mac = &hw->mac;
+ s32 status;
+ u32 reg_val;
- /* Configure CS4227 LINE side to proper mode. */
- slice = IXGBE_CS4227_LINE_SPARE24_LSB + (hw->bus.lan_id << 12);
- if (setup_linear)
- value = (IXGBE_CS4227_EDC_MODE_CX1 << 1) | 1;
- else
- value = (IXGBE_CS4227_EDC_MODE_SR << 1) | 1;
- status = ixgbe_write_i2c_combined_generic(hw, IXGBE_CS4227,
- slice, value);
- if (status)
- goto i2c_err;
+ /* Disable all AN and force speed to 10G Serial. */
+ status = mac->ops.read_iosf_sb_reg(hw,
+ IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val);
+ if (status)
+ return status;
+
+ reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_AN_EN;
+ reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_AN37_EN;
+ reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SGMII_EN;
+ reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_MASK;
+
+ /* Select forced link speed for internal PHY. */
+ switch (*speed) {
+ case IXGBE_LINK_SPEED_10GB_FULL:
+ reg_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_10G;
+ break;
+ case IXGBE_LINK_SPEED_1GB_FULL:
+ reg_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_1G;
+ break;
+ default:
+ /* Other link speeds are not supported by internal PHY. */
+ return IXGBE_ERR_LINK_SETUP;
}
- return 0;
+ status = mac->ops.write_iosf_sb_reg(hw,
+ IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
-i2c_err:
- hw_dbg(hw, "combined i2c access failed with %d\n", status);
+ /* Toggle port SW reset by AN reset. */
+ status = ixgbe_restart_an_internal_phy_x550em(hw);
+
return status;
}
@@ -1388,45 +1521,39 @@ ixgbe_setup_mac_link_sfp_n(struct ixgbe_hw *hw, ixgbe_link_speed speed,
{
bool setup_linear = false;
u32 reg_phy_int;
- s32 rc;
+ s32 ret_val;
/* Check if SFP module is supported and linear */
- rc = ixgbe_supported_sfp_modules_X550em(hw, &setup_linear);
+ ret_val = ixgbe_supported_sfp_modules_X550em(hw, &setup_linear);
/* If no SFP module present, then return success. Return success since
* SFP not present error is not excepted in the setup MAC link flow.
*/
- if (rc == IXGBE_ERR_SFP_NOT_PRESENT)
+ if (ret_val == IXGBE_ERR_SFP_NOT_PRESENT)
return 0;
- if (!rc)
- return rc;
+ if (!ret_val)
+ return ret_val;
- /* Configure internal PHY for native SFI */
- rc = hw->mac.ops.read_iosf_sb_reg(hw,
- IXGBE_KRM_AN_CNTL_8(hw->bus.lan_id),
- IXGBE_SB_IOSF_TARGET_KR_PHY,
- ®_phy_int);
- if (rc)
- return rc;
+ /* Configure internal PHY for native SFI based on module type */
+ ret_val = hw->mac.ops.read_iosf_sb_reg(hw,
+ IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, ®_phy_int);
+ if (!ret_val)
+ return ret_val;
- if (setup_linear) {
- reg_phy_int &= ~IXGBE_KRM_AN_CNTL_8_LIMITING;
- reg_phy_int |= IXGBE_KRM_AN_CNTL_8_LINEAR;
- } else {
- reg_phy_int |= IXGBE_KRM_AN_CNTL_8_LIMITING;
- reg_phy_int &= ~IXGBE_KRM_AN_CNTL_8_LINEAR;
- }
+ reg_phy_int &= IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_DA;
+ if (!setup_linear)
+ reg_phy_int |= IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_SR;
- rc = hw->mac.ops.write_iosf_sb_reg(hw,
- IXGBE_KRM_AN_CNTL_8(hw->bus.lan_id),
- IXGBE_SB_IOSF_TARGET_KR_PHY,
- reg_phy_int);
- if (rc)
- return rc;
+ ret_val = hw->mac.ops.write_iosf_sb_reg(hw,
+ IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, reg_phy_int);
+ if (!ret_val)
+ return ret_val;
- /* Setup XFI/SFI internal link */
- return ixgbe_setup_ixfi_x550em(hw, &speed);
+ /* Setup SFI internal link. */
+ return ixgbe_setup_sfi_x550a(hw, &speed);
}
/**
@@ -1442,19 +1569,19 @@ ixgbe_setup_mac_link_sfp_x550a(struct ixgbe_hw *hw, ixgbe_link_speed speed,
u32 reg_slice, slice_offset;
bool setup_linear = false;
u16 reg_phy_ext;
- s32 rc;
+ s32 ret_val;
/* Check if SFP module is supported and linear */
- rc = ixgbe_supported_sfp_modules_X550em(hw, &setup_linear);
+ ret_val = ixgbe_supported_sfp_modules_X550em(hw, &setup_linear);
/* If no SFP module present, then return success. Return success since
* SFP not present error is not excepted in the setup MAC link flow.
*/
- if (rc == IXGBE_ERR_SFP_NOT_PRESENT)
+ if (ret_val == IXGBE_ERR_SFP_NOT_PRESENT)
return 0;
- if (!rc)
- return rc;
+ if (!ret_val)
+ return ret_val;
/* Configure internal PHY for KR/KX. */
ixgbe_setup_kr_speed_x550em(hw, speed);
@@ -1463,10 +1590,10 @@ ixgbe_setup_mac_link_sfp_x550a(struct ixgbe_hw *hw, ixgbe_link_speed speed,
return IXGBE_ERR_PHY_ADDR_INVALID;
/* Get external PHY device id */
- rc = hw->phy.ops.read_reg(hw, IXGBE_CS4227_GLOBAL_ID_MSB,
+ ret_val = hw->phy.ops.read_reg(hw, IXGBE_CS4227_GLOBAL_ID_MSB,
IXGBE_MDIO_ZERO_DEV_TYPE, ®_phy_ext);
- if (rc)
- return rc;
+ if (ret_val)
+ return ret_val;
/* When configuring quad port CS4223, the MAC instance is part
* of the slice offset.
@@ -1538,7 +1665,7 @@ static s32 ixgbe_check_link_t_X550em(struct ixgbe_hw *hw,
bool link_up_wait_to_complete)
{
u32 status;
- u16 autoneg_status;
+ u16 i, autoneg_status;
if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper)
return IXGBE_ERR_CONFIG;
@@ -1550,14 +1677,18 @@ static s32 ixgbe_check_link_t_X550em(struct ixgbe_hw *hw,
if (status || !(*link_up))
return status;
- /* MAC link is up, so check external PHY link.
- * Read this twice back to back to indicate current status.
- */
- status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_STATUS,
- IXGBE_MDIO_AUTO_NEG_DEV_TYPE,
- &autoneg_status);
- if (status)
- return status;
+ /* MAC link is up, so check external PHY link.
+ * Link status is latching low, and can only be used to detect link
+ * drop, and not the current status of the link without performing
+ * back-to-back reads.
+ */
+ for (i = 0; i < 2; i++) {
+ status = hw->phy.ops.read_reg(hw, MDIO_STAT1, MDIO_MMD_AN,
+ &autoneg_status);
+
+ if (status)
+ return status;
+ }
/* If external PHY link is not up, then indicate link not up */
if (!(autoneg_status & IXGBE_MDIO_AUTO_NEG_LINK_STATUS))
@@ -1575,7 +1706,7 @@ ixgbe_setup_sgmii(struct ixgbe_hw *hw, __always_unused ixgbe_link_speed speed,
__always_unused bool autoneg_wait_to_complete)
{
struct ixgbe_mac_info *mac = &hw->mac;
- u32 lval, sval;
+ u32 lval, sval, flx_val;
s32 rc;
rc = mac->ops.read_iosf_sb_reg(hw,
@@ -1609,14 +1740,55 @@ ixgbe_setup_sgmii(struct ixgbe_hw *hw, __always_unused ixgbe_link_speed speed,
if (rc)
return rc;
- lval |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART;
- rc = mac->ops.write_iosf_sb_reg(hw,
- IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
- IXGBE_SB_IOSF_TARGET_KR_PHY, lval);
+ rc = mac->ops.read_iosf_sb_reg(hw,
+ IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, &flx_val);
+ if (rc)
+ return rc;
+ rc = mac->ops.read_iosf_sb_reg(hw,
+ IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, &flx_val);
+ if (rc)
+ return rc;
+
+ flx_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_MASK;
+ flx_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_1G;
+ flx_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_AN_EN;
+ flx_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SGMII_EN;
+ flx_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_AN37_EN;
+
+ rc = mac->ops.write_iosf_sb_reg(hw,
+ IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, flx_val);
+ if (rc)
+ return rc;
+
+ rc = ixgbe_restart_an_internal_phy_x550em(hw);
return rc;
}
+/** ixgbe_init_mac_link_ops_X550em_a - Init mac link function pointers
+ * @hw: pointer to hardware structure
+ **/
+static void ixgbe_init_mac_link_ops_X550em_a(struct ixgbe_hw *hw)
+{
+ struct ixgbe_mac_info *mac = &hw->mac;
+
+ switch (mac->ops.get_media_type(hw)) {
+ case ixgbe_media_type_fiber:
+ mac->ops.setup_fc = NULL;
+ mac->ops.fc_autoneg = ixgbe_fc_autoneg_fiber_x550em_a;
+ break;
+ case ixgbe_media_type_backplane:
+ mac->ops.fc_autoneg = ixgbe_fc_autoneg_backplane_x550em_a;
+ mac->ops.setup_fc = ixgbe_setup_fc_backplane_x550em_a;
+ break;
+ default:
+ break;
+ }
+}
+
/** ixgbe_init_mac_link_ops_X550em - init mac link function pointers
* @hw: pointer to hardware structure
**/
@@ -1664,6 +1836,10 @@ static void ixgbe_init_mac_link_ops_X550em(struct ixgbe_hw *hw)
default:
break;
}
+
+ /* Additional modification for X550em_a devices */
+ if (hw->mac.type == ixgbe_mac_x550em_a)
+ ixgbe_init_mac_link_ops_X550em_a(hw);
}
/** ixgbe_setup_sfp_modules_X550em - Setup SFP module
@@ -1740,7 +1916,7 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc)
/* Vendor alarm triggered */
status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_CHIP_STD_INT_FLAG,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+ MDIO_MMD_VEND1,
®);
if (status || !(reg & IXGBE_MDIO_GLOBAL_VEN_ALM_INT_EN))
@@ -1748,7 +1924,7 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc)
/* Vendor Auto-Neg alarm triggered or Global alarm 1 triggered */
status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_FLAG,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+ MDIO_MMD_VEND1,
®);
if (status || !(reg & (IXGBE_MDIO_GLOBAL_AN_VEN_ALM_INT_EN |
@@ -1757,7 +1933,7 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc)
/* Global alarm triggered */
status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_ALARM_1,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+ MDIO_MMD_VEND1,
®);
if (status)
@@ -1772,7 +1948,7 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc)
if (reg & IXGBE_MDIO_GLOBAL_ALM_1_DEV_FAULT) {
/* device fault alarm triggered */
status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_FAULT_MSG,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+ MDIO_MMD_VEND1,
®);
if (status)
return status;
@@ -1787,14 +1963,14 @@ static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc)
/* Vendor alarm 2 triggered */
status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_CHIP_STD_INT_FLAG,
- IXGBE_MDIO_AUTO_NEG_DEV_TYPE, ®);
+ MDIO_MMD_AN, ®);
if (status || !(reg & IXGBE_MDIO_GLOBAL_STD_ALM2_INT))
return status;
/* link connect/disconnect event occurred */
status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_VENDOR_TX_ALARM2,
- IXGBE_MDIO_AUTO_NEG_DEV_TYPE, ®);
+ MDIO_MMD_AN, ®);
if (status)
return status;
@@ -1826,20 +2002,20 @@ static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw)
/* Enable link status change alarm */
status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_PMA_TX_VEN_LASI_INT_MASK,
- IXGBE_MDIO_AUTO_NEG_DEV_TYPE, ®);
+ MDIO_MMD_AN, ®);
if (status)
return status;
reg |= IXGBE_MDIO_PMA_TX_VEN_LASI_INT_EN;
status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_PMA_TX_VEN_LASI_INT_MASK,
- IXGBE_MDIO_AUTO_NEG_DEV_TYPE, reg);
+ MDIO_MMD_AN, reg);
if (status)
return status;
/* Enable high temperature failure and global fault alarms */
status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_MASK,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+ MDIO_MMD_VEND1,
®);
if (status)
return status;
@@ -1848,14 +2024,14 @@ static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw)
IXGBE_MDIO_GLOBAL_INT_DEV_FAULT_EN);
status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_GLOBAL_INT_MASK,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+ MDIO_MMD_VEND1,
reg);
if (status)
return status;
/* Enable vendor Auto-Neg alarm and Global Interrupt Mask 1 alarm */
status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_MASK,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+ MDIO_MMD_VEND1,
®);
if (status)
return status;
@@ -1864,14 +2040,14 @@ static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw)
IXGBE_MDIO_GLOBAL_ALARM_1_INT);
status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_MASK,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+ MDIO_MMD_VEND1,
reg);
if (status)
return status;
/* Enable chip-wide vendor alarm */
status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_STD_MASK,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+ MDIO_MMD_VEND1,
®);
if (status)
return status;
@@ -1879,7 +2055,7 @@ static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw)
reg |= IXGBE_MDIO_GLOBAL_VEN_ALM_INT_EN;
status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_STD_MASK,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+ MDIO_MMD_VEND1,
reg);
return status;
@@ -1945,13 +2121,31 @@ static s32 ixgbe_setup_kr_speed_x550em(struct ixgbe_hw *hw,
if (speed & IXGBE_LINK_SPEED_1GB_FULL)
reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KX;
- /* Restart auto-negotiation. */
- reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART;
status = hw->mac.ops.write_iosf_sb_reg(hw,
IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
- return status;
+ if (hw->mac.type == ixgbe_mac_x550em_a) {
+ /* Set lane mode to KR auto negotiation */
+ status = hw->mac.ops.read_iosf_sb_reg(hw,
+ IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val);
+
+ if (status)
+ return status;
+
+ reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_MASK;
+ reg_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_AN;
+ reg_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_AN_EN;
+ reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_AN37_EN;
+ reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SGMII_EN;
+
+ status = hw->mac.ops.write_iosf_sb_reg(hw,
+ IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
+ }
+
+ return ixgbe_restart_an_internal_phy_x550em(hw);
}
/** ixgbe_setup_kx4_x550em - Configure the KX4 PHY.
@@ -2020,14 +2214,12 @@ static s32 ixgbe_ext_phy_t_x550em_get_link(struct ixgbe_hw *hw, bool *link_up)
*link_up = false;
/* read this twice back to back to indicate current status */
- ret = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_STATUS,
- IXGBE_MDIO_AUTO_NEG_DEV_TYPE,
+ ret = hw->phy.ops.read_reg(hw, MDIO_STAT1, MDIO_MMD_AN,
&autoneg_status);
if (ret)
return ret;
- ret = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_STATUS,
- IXGBE_MDIO_AUTO_NEG_DEV_TYPE,
+ ret = hw->phy.ops.read_reg(hw, MDIO_STAT1, MDIO_MMD_AN,
&autoneg_status);
if (ret)
return ret;
@@ -2073,7 +2265,7 @@ static s32 ixgbe_setup_internal_phy_t_x550em(struct ixgbe_hw *hw)
return 0;
status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_VENDOR_STAT,
- IXGBE_MDIO_AUTO_NEG_DEV_TYPE,
+ MDIO_MMD_AN,
&speed);
if (status)
return status;
@@ -2134,10 +2326,10 @@ static s32 ixgbe_led_on_t_x550em(struct ixgbe_hw *hw, u32 led_idx)
/* To turn on the LED, set mode to ON. */
hw->phy.ops.read_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, &phy_data);
+ MDIO_MMD_VEND1, &phy_data);
phy_data |= IXGBE_X557_LED_MANUAL_SET_MASK;
hw->phy.ops.write_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, phy_data);
+ MDIO_MMD_VEND1, phy_data);
return 0;
}
@@ -2156,10 +2348,10 @@ static s32 ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx)
/* To turn on the LED, set mode to ON. */
hw->phy.ops.read_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, &phy_data);
+ MDIO_MMD_VEND1, &phy_data);
phy_data &= ~IXGBE_X557_LED_MANUAL_SET_MASK;
hw->phy.ops.write_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE, phy_data);
+ MDIO_MMD_VEND1, phy_data);
return 0;
}
@@ -2180,7 +2372,7 @@ static s32 ixgbe_get_lcd_t_x550em(struct ixgbe_hw *hw,
*lcd_speed = IXGBE_LINK_SPEED_UNKNOWN;
status = hw->phy.ops.read_reg(hw, IXGBE_AUTO_NEG_LP_STATUS,
- IXGBE_MDIO_AUTO_NEG_DEV_TYPE,
+ MDIO_MMD_AN,
&an_lp_status);
if (status)
return status;
@@ -2281,6 +2473,90 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw)
return rc;
}
+/**
+ * ixgbe_fc_autoneg_backplane_x550em_a - Enable flow control IEEE clause 37
+ * @hw: pointer to hardware structure
+ **/
+static void ixgbe_fc_autoneg_backplane_x550em_a(struct ixgbe_hw *hw)
+{
+ u32 link_s1, lp_an_page_low, an_cntl_1;
+ s32 status = IXGBE_ERR_FC_NOT_NEGOTIATED;
+ ixgbe_link_speed speed;
+ bool link_up;
+
+ /* AN should have completed when the cable was plugged in.
+ * Look for reasons to bail out. Bail out if:
+ * - FC autoneg is disabled, or if
+ * - link is not up.
+ */
+ if (hw->fc.disable_fc_autoneg) {
+ hw_err(hw, "Flow control autoneg is disabled");
+ goto out;
+ }
+
+ hw->mac.ops.check_link(hw, &speed, &link_up, false);
+ if (!link_up) {
+ hw_err(hw, "The link is down");
+ goto out;
+ }
+
+ /* Check at auto-negotiation has completed */
+ status = hw->mac.ops.read_iosf_sb_reg(hw,
+ IXGBE_KRM_LINK_S1(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, &link_s1);
+
+ if (status || (link_s1 & IXGBE_KRM_LINK_S1_MAC_AN_COMPLETE) == 0) {
+ hw_dbg(hw, "Auto-Negotiation did not complete\n");
+ status = IXGBE_ERR_FC_NOT_NEGOTIATED;
+ goto out;
+ }
+
+ /* Read the 10g AN autoc and LP ability registers and resolve
+ * local flow control settings accordingly
+ */
+ status = hw->mac.ops.read_iosf_sb_reg(hw,
+ IXGBE_KRM_AN_CNTL_1(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, &an_cntl_1);
+
+ if (status) {
+ hw_dbg(hw, "Auto-Negotiation did not complete\n");
+ goto out;
+ }
+
+ status = hw->mac.ops.read_iosf_sb_reg(hw,
+ IXGBE_KRM_LP_BASE_PAGE_HIGH(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, &lp_an_page_low);
+
+ if (status) {
+ hw_dbg(hw, "Auto-Negotiation did not complete\n");
+ goto out;
+ }
+
+ status = ixgbe_negotiate_fc(hw, an_cntl_1, lp_an_page_low,
+ IXGBE_KRM_AN_CNTL_1_SYM_PAUSE,
+ IXGBE_KRM_AN_CNTL_1_ASM_PAUSE,
+ IXGBE_KRM_LP_BASE_PAGE_HIGH_SYM_PAUSE,
+ IXGBE_KRM_LP_BASE_PAGE_HIGH_ASM_PAUSE);
+
+out:
+ if (!status) {
+ hw->fc.fc_was_autonegged = true;
+ } else {
+ hw->fc.fc_was_autonegged = false;
+ hw->fc.current_mode = hw->fc.requested_mode;
+ }
+}
+
+/**
+ * ixgbe_fc_autoneg_fiber_x550em_a - passthrough FC settings
+ * @hw: pointer to hardware structure
+ **/
+static void ixgbe_fc_autoneg_fiber_x550em_a(struct ixgbe_hw *hw)
+{
+ hw->fc.fc_was_autonegged = false;
+ hw->fc.current_mode = hw->fc.requested_mode;
+}
+
/** ixgbe_enter_lplu_x550em - Transition to low power states
* @hw: pointer to hardware structure
*
@@ -2327,7 +2603,7 @@ static s32 ixgbe_enter_lplu_t_x550em(struct ixgbe_hw *hw)
return ixgbe_set_copper_phy_power(hw, false);
status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_VENDOR_STAT,
- IXGBE_MDIO_AUTO_NEG_DEV_TYPE,
+ MDIO_MMD_AN,
&speed);
if (status)
return status;
@@ -2349,20 +2625,20 @@ static s32 ixgbe_enter_lplu_t_x550em(struct ixgbe_hw *hw)
/* Clear AN completed indication */
status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_VENDOR_TX_ALARM,
- IXGBE_MDIO_AUTO_NEG_DEV_TYPE,
+ MDIO_MMD_AN,
&autoneg_reg);
if (status)
return status;
- status = hw->phy.ops.read_reg(hw, IXGBE_MII_10GBASE_T_AUTONEG_CTRL_REG,
- IXGBE_MDIO_AUTO_NEG_DEV_TYPE,
+ status = hw->phy.ops.read_reg(hw, MDIO_AN_10GBT_CTRL,
+ MDIO_MMD_AN,
&an_10g_cntl_reg);
if (status)
return status;
status = hw->phy.ops.read_reg(hw,
IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG,
- IXGBE_MDIO_AUTO_NEG_DEV_TYPE,
+ MDIO_MMD_AN,
&autoneg_reg);
if (status)
return status;
@@ -2520,7 +2796,7 @@ static s32 ixgbe_init_ext_t_x550em(struct ixgbe_hw *hw)
status = hw->phy.ops.read_reg(hw,
IXGBE_MDIO_TX_VENDOR_ALARMS_3,
- IXGBE_MDIO_PMA_PMD_DEV_TYPE,
+ MDIO_MMD_PMAPMD,
®);
if (status)
return status;
@@ -2531,7 +2807,7 @@ static s32 ixgbe_init_ext_t_x550em(struct ixgbe_hw *hw)
if (reg & IXGBE_MDIO_TX_VENDOR_ALARMS_3_RST_MASK) {
status = hw->phy.ops.read_reg(hw,
IXGBE_MDIO_GLOBAL_RES_PR_10,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+ MDIO_MMD_VEND1,
®);
if (status)
return status;
@@ -2540,7 +2816,7 @@ static s32 ixgbe_init_ext_t_x550em(struct ixgbe_hw *hw)
status = hw->phy.ops.write_reg(hw,
IXGBE_MDIO_GLOBAL_RES_PR_10,
- IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+ MDIO_MMD_VEND1,
reg);
if (status)
return status;
@@ -2729,6 +3005,90 @@ static void ixgbe_set_source_address_pruning_X550(struct ixgbe_hw *hw,
}
/**
+ * ixgbe_setup_fc_backplane_x550em_a - Set up flow control
+ * @hw: pointer to hardware structure
+ *
+ * Called at init time to set up flow control.
+ **/
+static s32 ixgbe_setup_fc_backplane_x550em_a(struct ixgbe_hw *hw)
+{
+ s32 status = 0;
+ u32 an_cntl = 0;
+
+ /* Validate the requested mode */
+ if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) {
+ hw_err(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n");
+ return IXGBE_ERR_INVALID_LINK_SETTINGS;
+ }
+
+ if (hw->fc.requested_mode == ixgbe_fc_default)
+ hw->fc.requested_mode = ixgbe_fc_full;
+
+ /* Set up the 1G and 10G flow control advertisement registers so the
+ * HW will be able to do FC autoneg once the cable is plugged in. If
+ * we link at 10G, the 1G advertisement is harmless and vice versa.
+ */
+ status = hw->mac.ops.read_iosf_sb_reg(hw,
+ IXGBE_KRM_AN_CNTL_1(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, &an_cntl);
+
+ if (status) {
+ hw_dbg(hw, "Auto-Negotiation did not complete\n");
+ return status;
+ }
+
+ /* The possible values of fc.requested_mode are:
+ * 0: Flow control is completely disabled
+ * 1: Rx flow control is enabled (we can receive pause frames,
+ * but not send pause frames).
+ * 2: Tx flow control is enabled (we can send pause frames but
+ * we do not support receiving pause frames).
+ * 3: Both Rx and Tx flow control (symmetric) are enabled.
+ * other: Invalid.
+ */
+ switch (hw->fc.requested_mode) {
+ case ixgbe_fc_none:
+ /* Flow control completely disabled by software override. */
+ an_cntl &= ~(IXGBE_KRM_AN_CNTL_1_SYM_PAUSE |
+ IXGBE_KRM_AN_CNTL_1_ASM_PAUSE);
+ break;
+ case ixgbe_fc_tx_pause:
+ /* Tx Flow control is enabled, and Rx Flow control is
+ * disabled by software override.
+ */
+ an_cntl |= IXGBE_KRM_AN_CNTL_1_ASM_PAUSE;
+ an_cntl &= ~IXGBE_KRM_AN_CNTL_1_SYM_PAUSE;
+ break;
+ case ixgbe_fc_rx_pause:
+ /* Rx Flow control is enabled and Tx Flow control is
+ * disabled by software override. Since there really
+ * isn't a way to advertise that we are capable of RX
+ * Pause ONLY, we will advertise that we support both
+ * symmetric and asymmetric Rx PAUSE, as such we fall
+ * through to the fc_full statement. Later, we will
+ * disable the adapter's ability to send PAUSE frames.
+ */
+ case ixgbe_fc_full:
+ /* Flow control (both Rx and Tx) is enabled by SW override. */
+ an_cntl |= IXGBE_KRM_AN_CNTL_1_SYM_PAUSE |
+ IXGBE_KRM_AN_CNTL_1_ASM_PAUSE;
+ break;
+ default:
+ hw_err(hw, "Flow control param set incorrectly\n");
+ return IXGBE_ERR_CONFIG;
+ }
+
+ status = hw->mac.ops.write_iosf_sb_reg(hw,
+ IXGBE_KRM_AN_CNTL_1(hw->bus.lan_id),
+ IXGBE_SB_IOSF_TARGET_KR_PHY, an_cntl);
+
+ /* Restart auto-negotiation. */
+ status = ixgbe_restart_an_internal_phy_x550em(hw);
+
+ return status;
+}
+
+/**
* ixgbe_set_mux - Set mux for port 1 access with CS4227
* @hw: pointer to hardware structure
* @state: set mux if 1, clear if 0
@@ -2934,6 +3294,7 @@ static const struct ixgbe_mac_operations mac_ops_X550 = {
X550_COMMON_MAC
.led_on = ixgbe_led_on_generic,
.led_off = ixgbe_led_off_generic,
+ .init_led_link_act = ixgbe_init_led_link_act_generic,
.reset_hw = &ixgbe_reset_hw_X540,
.get_media_type = &ixgbe_get_media_type_X540,
.get_san_mac_addr = &ixgbe_get_san_mac_addr_generic,
@@ -2948,12 +3309,14 @@ static const struct ixgbe_mac_operations mac_ops_X550 = {
.prot_autoc_read = prot_autoc_read_generic,
.prot_autoc_write = prot_autoc_write_generic,
.setup_fc = ixgbe_setup_fc_generic,
+ .fc_autoneg = ixgbe_fc_autoneg,
};
static const struct ixgbe_mac_operations mac_ops_X550EM_x = {
X550_COMMON_MAC
.led_on = ixgbe_led_on_t_x550em,
.led_off = ixgbe_led_off_t_x550em,
+ .init_led_link_act = ixgbe_init_led_link_act_generic,
.reset_hw = &ixgbe_reset_hw_X550em,
.get_media_type = &ixgbe_get_media_type_X550em,
.get_san_mac_addr = NULL,
@@ -2966,6 +3329,7 @@ static const struct ixgbe_mac_operations mac_ops_X550EM_x = {
.release_swfw_sync = &ixgbe_release_swfw_sync_X550em,
.init_swfw_sync = &ixgbe_init_swfw_sync_X540,
.setup_fc = NULL, /* defined later */
+ .fc_autoneg = ixgbe_fc_autoneg,
.read_iosf_sb_reg = ixgbe_read_iosf_sb_reg_x550,
.write_iosf_sb_reg = ixgbe_write_iosf_sb_reg_x550,
};
@@ -2974,6 +3338,7 @@ static struct ixgbe_mac_operations mac_ops_x550em_a = {
X550_COMMON_MAC
.led_on = ixgbe_led_on_t_x550em,
.led_off = ixgbe_led_off_t_x550em,
+ .init_led_link_act = ixgbe_init_led_link_act_generic,
.reset_hw = ixgbe_reset_hw_X550em,
.get_media_type = ixgbe_get_media_type_X550em,
.get_san_mac_addr = NULL,
@@ -2985,6 +3350,7 @@ static struct ixgbe_mac_operations mac_ops_x550em_a = {
.acquire_swfw_sync = ixgbe_acquire_swfw_sync_x550em_a,
.release_swfw_sync = ixgbe_release_swfw_sync_x550em_a,
.setup_fc = ixgbe_setup_fc_x550em,
+ .fc_autoneg = ixgbe_fc_autoneg,
.read_iosf_sb_reg = ixgbe_read_iosf_sb_reg_x550a,
.write_iosf_sb_reg = ixgbe_write_iosf_sb_reg_x550a,
};
@@ -3036,11 +3402,6 @@ static const struct ixgbe_phy_operations phy_ops_X550EM_x = {
.identify = &ixgbe_identify_phy_x550em,
.read_reg = &ixgbe_read_phy_reg_generic,
.write_reg = &ixgbe_write_phy_reg_generic,
- .read_i2c_combined = &ixgbe_read_i2c_combined_generic,
- .write_i2c_combined = &ixgbe_write_i2c_combined_generic,
- .read_i2c_combined_unlocked = &ixgbe_read_i2c_combined_generic_unlocked,
- .write_i2c_combined_unlocked =
- &ixgbe_write_i2c_combined_generic_unlocked,
};
static const struct ixgbe_phy_operations phy_ops_x550em_a = {
@@ -3053,6 +3414,13 @@ static const struct ixgbe_phy_operations phy_ops_x550em_a = {
.write_reg_mdi = &ixgbe_write_phy_reg_mdi,
};
+static const struct ixgbe_link_operations link_ops_x550em_x = {
+ .read_link = &ixgbe_read_i2c_combined_generic,
+ .read_link_unlocked = &ixgbe_read_i2c_combined_generic_unlocked,
+ .write_link = &ixgbe_write_i2c_combined_generic,
+ .write_link_unlocked = &ixgbe_write_i2c_combined_generic_unlocked,
+};
+
static const u32 ixgbe_mvals_X550[IXGBE_MVALS_IDX_LIMIT] = {
IXGBE_MVALS_INIT(X550)
};
@@ -3083,11 +3451,12 @@ const struct ixgbe_info ixgbe_X550EM_x_info = {
.phy_ops = &phy_ops_X550EM_x,
.mbx_ops = &mbx_ops_generic,
.mvals = ixgbe_mvals_X550EM_x,
+ .link_ops = &link_ops_x550em_x,
};
const struct ixgbe_info ixgbe_x550em_a_info = {
.mac = ixgbe_mac_x550em_a,
- .get_invariants = &ixgbe_get_invariants_X550_x,
+ .get_invariants = &ixgbe_get_invariants_X550_a,
.mac_ops = &mac_ops_x550em_a,
.eeprom_ops = &eeprom_ops_X550EM_x,
.phy_ops = &phy_ops_x550em_a,
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index d2775f0..d316f50 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -1498,6 +1498,9 @@ static void ixgbevf_free_irq(struct ixgbevf_adapter *adapter)
{
int i, q_vectors;
+ if (!adapter->msix_entries)
+ return;
+
q_vectors = adapter->num_msix_vectors;
i = q_vectors - 1;
@@ -2552,6 +2555,9 @@ static void ixgbevf_free_q_vectors(struct ixgbevf_adapter *adapter)
**/
static void ixgbevf_reset_interrupt_capability(struct ixgbevf_adapter *adapter)
{
+ if (!adapter->msix_entries)
+ return;
+
pci_disable_msix(adapter->pdev);
kfree(adapter->msix_entries);
adapter->msix_entries = NULL;
@@ -3794,11 +3800,10 @@ static int ixgbevf_suspend(struct pci_dev *pdev, pm_message_t state)
ixgbevf_free_irq(adapter);
ixgbevf_free_all_tx_resources(adapter);
ixgbevf_free_all_rx_resources(adapter);
+ ixgbevf_clear_interrupt_scheme(adapter);
rtnl_unlock();
}
- ixgbevf_clear_interrupt_scheme(adapter);
-
#ifdef CONFIG_PM
retval = pci_save_state(pdev);
if (retval)
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 1a739d7..9d93137 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -303,15 +303,9 @@ ltq_etop_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
strlcpy(info->version, DRV_VERSION, sizeof(info->version));
}
-static int
-ltq_etop_nway_reset(struct net_device *dev)
-{
- return phy_start_aneg(dev->phydev);
-}
-
static const struct ethtool_ops ltq_etop_ethtool_ops = {
.get_drvinfo = ltq_etop_get_drvinfo,
- .nway_reset = ltq_etop_nway_reset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_link_ksettings = phy_ethtool_get_link_ksettings,
.set_link_ksettings = phy_ethtool_set_link_ksettings,
};
diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index 2664827..d74d4e6 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -5,7 +5,7 @@
config NET_VENDOR_MARVELL
bool "Marvell devices"
default y
- depends on PCI || CPU_PXA168 || MV64X60 || PPC32 || PLAT_ORION || INET
+ depends on PCI || CPU_PXA168 || MV64X60 || PPC32 || PLAT_ORION || INET || COMPILE_TEST
---help---
If you have a network (Ethernet) card belonging to this class, say Y.
@@ -18,7 +18,8 @@
config MV643XX_ETH
tristate "Marvell Discovery (643XX) and Orion ethernet support"
- depends on (MV64X60 || PPC32 || PLAT_ORION) && INET
+ depends on (MV64X60 || PPC32 || PLAT_ORION || COMPILE_TEST) && INET
+ depends on HAS_DMA
select PHYLIB
select MVMDIO
---help---
@@ -55,7 +56,8 @@
config MVNETA
tristate "Marvell Armada 370/38x/XP network interface support"
- depends on PLAT_ORION
+ depends on PLAT_ORION || COMPILE_TEST
+ depends on HAS_DMA
select MVMDIO
select FIXED_PHY
---help---
@@ -77,7 +79,8 @@
config MVPP2
tristate "Marvell Armada 375 network interface support"
- depends on MACH_ARMADA_375
+ depends on MACH_ARMADA_375 || COMPILE_TEST
+ depends on HAS_DMA
select MVMDIO
---help---
This driver supports the network interface units in the
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index 68675d8..5f62c3d 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -1379,6 +1379,7 @@ static unsigned int get_rx_coal(struct mv643xx_eth_private *mp)
temp = (val & 0x003fff00) >> 8;
temp *= 64000000;
+ temp += mp->t_clk / 2;
do_div(temp, mp->t_clk);
return (unsigned int)temp;
@@ -1415,6 +1416,7 @@ static unsigned int get_tx_coal(struct mv643xx_eth_private *mp)
temp = (rdlp(mp, TX_FIFO_URGENT_THRESHOLD) & 0x3fff0) >> 4;
temp *= 64000000;
+ temp += mp->t_clk / 2;
do_div(temp, mp->t_clk);
return (unsigned int)temp;
@@ -1637,14 +1639,6 @@ static void mv643xx_eth_get_drvinfo(struct net_device *dev,
strlcpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info));
}
-static int mv643xx_eth_nway_reset(struct net_device *dev)
-{
- if (!dev->phydev)
- return -EINVAL;
-
- return genphy_restart_aneg(dev->phydev);
-}
-
static int
mv643xx_eth_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
{
@@ -1768,7 +1762,7 @@ static int mv643xx_eth_get_sset_count(struct net_device *dev, int sset)
static const struct ethtool_ops mv643xx_eth_ethtool_ops = {
.get_drvinfo = mv643xx_eth_get_drvinfo,
- .nway_reset = mv643xx_eth_nway_reset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_link = ethtool_op_get_link,
.get_coalesce = mv643xx_eth_get_coalesce,
.set_coalesce = mv643xx_eth_set_coalesce,
@@ -2981,6 +2975,22 @@ static void set_params(struct mv643xx_eth_private *mp,
mp->txq_count = pd->tx_queue_count ? : 1;
}
+static int get_phy_mode(struct mv643xx_eth_private *mp)
+{
+ struct device *dev = mp->dev->dev.parent;
+ int iface = -1;
+
+ if (dev->of_node)
+ iface = of_get_phy_mode(dev->of_node);
+
+ /* Historical default if unspecified. We could also read/write
+ * the interface state in the PSC1
+ */
+ if (iface < 0)
+ iface = PHY_INTERFACE_MODE_GMII;
+ return iface;
+}
+
static struct phy_device *phy_scan(struct mv643xx_eth_private *mp,
int phy_addr)
{
@@ -3007,7 +3017,7 @@ static struct phy_device *phy_scan(struct mv643xx_eth_private *mp,
"orion-mdio-mii", addr);
phydev = phy_connect(mp->dev, phy_id, mv643xx_eth_adjust_link,
- PHY_INTERFACE_MODE_GMII);
+ get_phy_mode(mp));
if (!IS_ERR(phydev)) {
phy_addr_set(mp, addr);
break;
@@ -3106,6 +3116,7 @@ static int mv643xx_eth_probe(struct platform_device *pdev)
if (!dev)
return -ENOMEM;
+ SET_NETDEV_DEV(dev, &pdev->dev);
mp = netdev_priv(dev);
platform_set_drvdata(pdev, mp);
@@ -3145,7 +3156,7 @@ static int mv643xx_eth_probe(struct platform_device *pdev)
if (pd->phy_node) {
phydev = of_phy_connect(mp->dev, pd->phy_node,
mv643xx_eth_adjust_link, 0,
- PHY_INTERFACE_MODE_GMII);
+ get_phy_mode(mp));
if (!phydev)
err = -ENODEV;
else
@@ -3207,8 +3218,6 @@ static int mv643xx_eth_probe(struct platform_device *pdev)
dev->min_mtu = 64;
dev->max_mtu = 9500;
- SET_NETDEV_DEV(dev, &pdev->dev);
-
if (mp->shared->win_protect)
wrl(mp, WINDOW_PROTECT(mp->port_num), mp->shared->win_protect);
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index b85819e..87274d4 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3811,6 +3811,7 @@ static const struct net_device_ops mvneta_netdev_ops = {
};
const struct ethtool_ops mvneta_eth_tool_ops = {
+ .nway_reset = phy_ethtool_nway_reset,
.get_link = ethtool_op_get_link,
.set_coalesce = mvneta_ethtool_set_coalesce,
.get_coalesce = mvneta_ethtool_get_coalesce,
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index c8bf155..ee85786 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -5923,6 +5923,7 @@ static const struct net_device_ops mvpp2_netdev_ops = {
};
static const struct ethtool_ops mvpp2_eth_tool_ops = {
+ .nway_reset = phy_ethtool_nway_reset,
.get_link = ethtool_op_get_link,
.set_coalesce = mvpp2_ethtool_set_coalesce,
.get_coalesce = mvpp2_ethtool_get_coalesce,
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index b78a838..3af2814 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1393,6 +1393,7 @@ static void pxa168_get_drvinfo(struct net_device *dev,
static const struct ethtool_ops pxa168_ethtool_ops = {
.get_drvinfo = pxa168_get_drvinfo,
+ .nway_reset = phy_ethtool_nway_reset,
.get_link = ethtool_op_get_link,
.get_ts_info = ethtool_op_get_ts_info,
.get_link_ksettings = pxa168_get_link_ksettings,
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index b1cef7a..e36bebc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2469,6 +2469,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
kfree(priv->mfunc.master.slave_state);
err_comm:
iounmap(priv->mfunc.comm);
+ priv->mfunc.comm = NULL;
err_vhcr:
dma_free_coherent(&dev->persist->pdev->dev, PAGE_SIZE,
priv->mfunc.vhcr,
@@ -2537,6 +2538,13 @@ void mlx4_report_internal_err_comm_event(struct mlx4_dev *dev)
int slave;
u32 slave_read;
+ /* If the comm channel has not yet been initialized,
+ * skip reporting the internal error event to all
+ * the communication channels.
+ */
+ if (!priv->mfunc.comm)
+ return;
+
/* Report an internal error event to all
* communication channels.
*/
@@ -2571,6 +2579,7 @@ void mlx4_multi_func_cleanup(struct mlx4_dev *dev)
}
iounmap(priv->mfunc.comm);
+ priv->mfunc.comm = NULL;
}
void mlx4_cmd_cleanup(struct mlx4_dev *dev, int cleanup_mask)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index 08fc5fc..a5fc46b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -245,8 +245,11 @@ static u32 freq_to_shift(u16 freq)
{
u32 freq_khz = freq * 1000;
u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC;
+ u64 tmp_rounded =
+ roundup_pow_of_two(max_val_cycles) > max_val_cycles ?
+ roundup_pow_of_two(max_val_cycles) - 1 : UINT_MAX;
u64 max_val_cycles_rounded = is_power_of_2(max_val_cycles + 1) ?
- max_val_cycles : roundup_pow_of_two(max_val_cycles) - 1;
+ max_val_cycles : tmp_rounded;
/* calculate max possible multiplier in order to fit in 64bit */
u64 max_mul = div_u64(0xffffffffffffffffULL, max_val_cycles_rounded);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 132cea6..09dd377 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -65,7 +65,7 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
cq->buf_size = cq->size * mdev->dev->caps.cqe_size;
cq->ring = ring;
- cq->is_tx = mode;
+ cq->type = mode;
cq->vector = mdev->dev->caps.num_comp_vectors;
/* Allocate HW buffers on provided NUMA node.
@@ -104,7 +104,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
*cq->mcq.arm_db = 0;
memset(cq->buf, 0, cq->buf_size);
- if (cq->is_tx == RX) {
+ if (cq->type == RX) {
if (!mlx4_is_eq_vector_valid(mdev->dev, priv->port,
cq->vector)) {
cq->vector = cpumask_first(priv->rx_ring[cq->ring]->affinity_mask);
@@ -133,11 +133,11 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
cq->vector = rx_cq->vector;
}
- if (!cq->is_tx)
+ if (cq->type == RX)
cq->size = priv->rx_ring[cq->ring]->actual_size;
- if ((cq->is_tx && priv->hwtstamp_config.tx_type) ||
- (!cq->is_tx && priv->hwtstamp_config.rx_filter))
+ if ((cq->type != RX && priv->hwtstamp_config.tx_type) ||
+ (cq->type == RX && priv->hwtstamp_config.rx_filter))
timestamp_en = 1;
err = mlx4_cq_alloc(mdev->dev, cq->size, &cq->wqres.mtt,
@@ -146,10 +146,10 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
if (err)
goto free_eq;
- cq->mcq.comp = cq->is_tx ? mlx4_en_tx_irq : mlx4_en_rx_irq;
+ cq->mcq.comp = cq->type != RX ? mlx4_en_tx_irq : mlx4_en_rx_irq;
cq->mcq.event = mlx4_en_cq_event;
- if (cq->is_tx)
+ if (cq->type != RX)
netif_tx_napi_add(cq->dev, &cq->napi, mlx4_en_poll_tx_cq,
NAPI_POLL_WEIGHT);
else
@@ -173,7 +173,7 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq)
mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
if (mlx4_is_eq_vector_valid(mdev->dev, priv->port, cq->vector) &&
- cq->is_tx == RX)
+ cq->type == RX)
mlx4_release_eq(priv->mdev->dev, cq->vector);
cq->vector = 0;
cq->buf_size = 0;
@@ -185,10 +185,6 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq)
void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
{
napi_disable(&cq->napi);
- if (!cq->is_tx) {
- napi_hash_del(&cq->napi);
- synchronize_rcu();
- }
netif_napi_del(&cq->napi);
mlx4_cq_free(priv->mdev->dev, &cq->mcq);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index bdda17d..487a58f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -49,16 +49,19 @@
static int mlx4_en_moderation_update(struct mlx4_en_priv *priv)
{
- int i;
+ int i, t;
int err = 0;
- for (i = 0; i < priv->tx_ring_num; i++) {
- priv->tx_cq[i]->moder_cnt = priv->tx_frames;
- priv->tx_cq[i]->moder_time = priv->tx_usecs;
- if (priv->port_up) {
- err = mlx4_en_set_cq_moder(priv, priv->tx_cq[i]);
- if (err)
- return err;
+ for (t = 0 ; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ for (i = 0; i < priv->tx_ring_num[t]; i++) {
+ priv->tx_cq[t][i]->moder_cnt = priv->tx_frames;
+ priv->tx_cq[t][i]->moder_time = priv->tx_usecs;
+ if (priv->port_up) {
+ err = mlx4_en_set_cq_moder(priv,
+ priv->tx_cq[t][i]);
+ if (err)
+ return err;
+ }
}
}
@@ -192,6 +195,10 @@ static const char main_strings[][ETH_GSTRING_LEN] = {
"tx_prio_7_packets", "tx_prio_7_bytes",
"tx_novlan_packets", "tx_novlan_bytes",
+ /* xdp statistics */
+ "rx_xdp_drop",
+ "rx_xdp_tx",
+ "rx_xdp_tx_full",
};
static const char mlx4_en_test_names[][ETH_GSTRING_LEN]= {
@@ -336,8 +343,8 @@ static int mlx4_en_get_sset_count(struct net_device *dev, int sset)
switch (sset) {
case ETH_SS_STATS:
return bitmap_iterator_count(&it) +
- (priv->tx_ring_num * 2) +
- (priv->rx_ring_num * 3);
+ (priv->tx_ring_num[TX] * 2) +
+ (priv->rx_ring_num * (3 + NUM_XDP_STATS));
case ETH_SS_TEST:
return MLX4_EN_NUM_SELF_TEST - !(priv->mdev->dev->caps.flags
& MLX4_DEV_CAP_FLAG_UC_LOOPBACK) * 2;
@@ -397,14 +404,21 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev,
if (bitmap_iterator_test(&it))
data[index++] = ((unsigned long *)&priv->pkstats)[i];
- for (i = 0; i < priv->tx_ring_num; i++) {
- data[index++] = priv->tx_ring[i]->packets;
- data[index++] = priv->tx_ring[i]->bytes;
+ for (i = 0; i < NUM_XDP_STATS; i++, bitmap_iterator_inc(&it))
+ if (bitmap_iterator_test(&it))
+ data[index++] = ((unsigned long *)&priv->xdp_stats)[i];
+
+ for (i = 0; i < priv->tx_ring_num[TX]; i++) {
+ data[index++] = priv->tx_ring[TX][i]->packets;
+ data[index++] = priv->tx_ring[TX][i]->bytes;
}
for (i = 0; i < priv->rx_ring_num; i++) {
data[index++] = priv->rx_ring[i]->packets;
data[index++] = priv->rx_ring[i]->bytes;
data[index++] = priv->rx_ring[i]->dropped;
+ data[index++] = priv->rx_ring[i]->xdp_drop;
+ data[index++] = priv->rx_ring[i]->xdp_tx;
+ data[index++] = priv->rx_ring[i]->xdp_tx_full;
}
spin_unlock_bh(&priv->stats_lock);
@@ -467,7 +481,13 @@ static void mlx4_en_get_strings(struct net_device *dev,
strcpy(data + (index++) * ETH_GSTRING_LEN,
main_strings[strings]);
- for (i = 0; i < priv->tx_ring_num; i++) {
+ for (i = 0; i < NUM_XDP_STATS; i++, strings++,
+ bitmap_iterator_inc(&it))
+ if (bitmap_iterator_test(&it))
+ strcpy(data + (index++) * ETH_GSTRING_LEN,
+ main_strings[strings]);
+
+ for (i = 0; i < priv->tx_ring_num[TX]; i++) {
sprintf(data + (index++) * ETH_GSTRING_LEN,
"tx%d_packets", i);
sprintf(data + (index++) * ETH_GSTRING_LEN,
@@ -480,6 +500,12 @@ static void mlx4_en_get_strings(struct net_device *dev,
"rx%d_bytes", i);
sprintf(data + (index++) * ETH_GSTRING_LEN,
"rx%d_dropped", i);
+ sprintf(data + (index++) * ETH_GSTRING_LEN,
+ "rx%d_xdp_drop", i);
+ sprintf(data + (index++) * ETH_GSTRING_LEN,
+ "rx%d_xdp_tx", i);
+ sprintf(data + (index++) * ETH_GSTRING_LEN,
+ "rx%d_xdp_tx_full", i);
}
break;
case ETH_SS_PRIV_FLAGS:
@@ -1060,7 +1086,7 @@ static int mlx4_en_set_ringparam(struct net_device *dev,
if (rx_size == (priv->port_up ? priv->rx_ring[0]->actual_size :
priv->rx_ring[0]->size) &&
- tx_size == priv->tx_ring[0]->size)
+ tx_size == priv->tx_ring[TX][0]->size)
return 0;
tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
@@ -1105,7 +1131,7 @@ static void mlx4_en_get_ringparam(struct net_device *dev,
param->tx_max_pending = MLX4_EN_MAX_TX_SIZE;
param->rx_pending = priv->port_up ?
priv->rx_ring[0]->actual_size : priv->rx_ring[0]->size;
- param->tx_pending = priv->tx_ring[0]->size;
+ param->tx_pending = priv->tx_ring[TX][0]->size;
}
static u32 mlx4_en_get_rxfh_indir_size(struct net_device *dev)
@@ -1710,7 +1736,7 @@ static void mlx4_en_get_channels(struct net_device *dev,
channel->max_tx = MLX4_EN_MAX_TX_RING_P_UP;
channel->rx_count = priv->rx_ring_num;
- channel->tx_count = priv->tx_ring_num / MLX4_EN_NUM_UP;
+ channel->tx_count = priv->tx_ring_num[TX] / MLX4_EN_NUM_UP;
}
static int mlx4_en_set_channels(struct net_device *dev,
@@ -1721,6 +1747,7 @@ static int mlx4_en_set_channels(struct net_device *dev,
struct mlx4_en_port_profile new_prof;
struct mlx4_en_priv *tmp;
int port_up = 0;
+ int xdp_count;
int err = 0;
if (channel->other_count || channel->combined_count ||
@@ -1729,20 +1756,25 @@ static int mlx4_en_set_channels(struct net_device *dev,
!channel->tx_count || !channel->rx_count)
return -EINVAL;
- if (channel->tx_count * MLX4_EN_NUM_UP <= priv->xdp_ring_num) {
- en_err(priv, "Minimum %d tx channels required with XDP on\n",
- priv->xdp_ring_num / MLX4_EN_NUM_UP + 1);
- return -EINVAL;
- }
-
tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
if (!tmp)
return -ENOMEM;
mutex_lock(&mdev->state_lock);
+ xdp_count = priv->tx_ring_num[TX_XDP] ? channel->rx_count : 0;
+ if (channel->tx_count * MLX4_EN_NUM_UP + xdp_count > MAX_TX_RINGS) {
+ err = -EINVAL;
+ en_err(priv,
+ "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n",
+ channel->tx_count * MLX4_EN_NUM_UP + xdp_count,
+ MAX_TX_RINGS);
+ goto out;
+ }
+
memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
new_prof.num_tx_rings_p_up = channel->tx_count;
- new_prof.tx_ring_num = channel->tx_count * MLX4_EN_NUM_UP;
+ new_prof.tx_ring_num[TX] = channel->tx_count * MLX4_EN_NUM_UP;
+ new_prof.tx_ring_num[TX_XDP] = xdp_count;
new_prof.rx_ring_num = channel->rx_count;
err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
@@ -1756,14 +1788,13 @@ static int mlx4_en_set_channels(struct net_device *dev,
mlx4_en_safe_replace_resources(priv, tmp);
- netif_set_real_num_tx_queues(dev, priv->tx_ring_num -
- priv->xdp_ring_num);
+ netif_set_real_num_tx_queues(dev, priv->tx_ring_num[TX]);
netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
if (dev->num_tc)
mlx4_en_setup_tc(dev, MLX4_EN_NUM_UP);
- en_warn(priv, "Using %d TX rings\n", priv->tx_ring_num);
+ en_warn(priv, "Using %d TX rings\n", priv->tx_ring_num[TX]);
en_warn(priv, "Using %d RX rings\n", priv->rx_ring_num);
if (port_up) {
@@ -1774,8 +1805,8 @@ static int mlx4_en_set_channels(struct net_device *dev,
err = mlx4_en_moderation_update(priv);
out:
- kfree(tmp);
mutex_unlock(&mdev->state_lock);
+ kfree(tmp);
return err;
}
@@ -1823,11 +1854,15 @@ static int mlx4_en_set_priv_flags(struct net_device *dev, u32 flags)
int ret = 0;
if (bf_enabled_new != bf_enabled_old) {
+ int t;
+
if (bf_enabled_new) {
bool bf_supported = true;
- for (i = 0; i < priv->tx_ring_num; i++)
- bf_supported &= priv->tx_ring[i]->bf_alloced;
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++)
+ for (i = 0; i < priv->tx_ring_num[t]; i++)
+ bf_supported &=
+ priv->tx_ring[t][i]->bf_alloced;
if (!bf_supported) {
en_err(priv, "BlueFlame is not supported\n");
@@ -1839,8 +1874,10 @@ static int mlx4_en_set_priv_flags(struct net_device *dev, u32 flags)
priv->pflags &= ~MLX4_EN_PRIV_FLAGS_BLUEFLAME;
}
- for (i = 0; i < priv->tx_ring_num; i++)
- priv->tx_ring[i]->bf_enabled = bf_enabled_new;
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++)
+ for (i = 0; i < priv->tx_ring_num[t]; i++)
+ priv->tx_ring[t][i]->bf_enabled =
+ bf_enabled_new;
en_info(priv, "BlueFlame %s\n",
bf_enabled_new ? "Enabled" : "Disabled");
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index bf7628d..36a7a54 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -169,7 +169,7 @@ static int mlx4_en_get_profile(struct mlx4_en_dev *mdev)
params->prof[i].tx_ppp = pfctx;
params->prof[i].tx_ring_size = MLX4_EN_DEF_TX_RING_SIZE;
params->prof[i].rx_ring_size = MLX4_EN_DEF_RX_RING_SIZE;
- params->prof[i].tx_ring_num = params->num_tx_rings_p_up *
+ params->prof[i].tx_ring_num[TX] = params->num_tx_rings_p_up *
MLX4_EN_NUM_UP;
params->prof[i].rss_rings = 0;
params->prof[i].inline_thold = inline_thold;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index bf35ac4..9a807e9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1214,8 +1214,8 @@ static void mlx4_en_netpoll(struct net_device *dev)
struct mlx4_en_cq *cq;
int i;
- for (i = 0; i < priv->tx_ring_num; i++) {
- cq = priv->tx_cq[i];
+ for (i = 0; i < priv->tx_ring_num[TX]; i++) {
+ cq = priv->tx_cq[TX][i];
napi_schedule(&cq->napi);
}
}
@@ -1299,12 +1299,14 @@ static void mlx4_en_tx_timeout(struct net_device *dev)
if (netif_msg_timer(priv))
en_warn(priv, "Tx timeout called on port:%d\n", priv->port);
- for (i = 0; i < priv->tx_ring_num; i++) {
+ for (i = 0; i < priv->tx_ring_num[TX]; i++) {
+ struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[TX][i];
+
if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, i)))
continue;
en_warn(priv, "TX timeout on queue: %d, QP: 0x%x, CQ: 0x%x, Cons: 0x%x, Prod: 0x%x\n",
- i, priv->tx_ring[i]->qpn, priv->tx_ring[i]->cqn,
- priv->tx_ring[i]->cons, priv->tx_ring[i]->prod);
+ i, tx_ring->qpn, tx_ring->cqn,
+ tx_ring->cons, tx_ring->prod);
}
priv->port_stats.tx_timeout++;
@@ -1328,7 +1330,7 @@ mlx4_en_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv)
{
struct mlx4_en_cq *cq;
- int i;
+ int i, t;
/* If we haven't received a specific coalescing setting
* (module param), we set the moderation parameters as follows:
@@ -1353,10 +1355,12 @@ static void mlx4_en_set_default_moderation(struct mlx4_en_priv *priv)
priv->last_moder_bytes[i] = 0;
}
- for (i = 0; i < priv->tx_ring_num; i++) {
- cq = priv->tx_cq[i];
- cq->moder_cnt = priv->tx_frames;
- cq->moder_time = priv->tx_usecs;
+ for (t = 0 ; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ for (i = 0; i < priv->tx_ring_num[t]; i++) {
+ cq = priv->tx_cq[t][i];
+ cq->moder_cnt = priv->tx_frames;
+ cq->moder_time = priv->tx_usecs;
+ }
}
/* Reset auto-moderation params */
@@ -1526,19 +1530,13 @@ static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
static void mlx4_en_init_recycle_ring(struct mlx4_en_priv *priv,
int tx_ring_idx)
{
- struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[tx_ring_idx];
- int rr_index;
+ struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[TX_XDP][tx_ring_idx];
+ int rr_index = tx_ring_idx;
- rr_index = (priv->xdp_ring_num - priv->tx_ring_num) + tx_ring_idx;
- if (rr_index >= 0) {
- tx_ring->free_tx_desc = mlx4_en_recycle_tx_desc;
- tx_ring->recycle_ring = priv->rx_ring[rr_index];
- en_dbg(DRV, priv,
- "Set tx_ring[%d]->recycle_ring = rx_ring[%d]\n",
- tx_ring_idx, rr_index);
- } else {
- tx_ring->recycle_ring = NULL;
- }
+ tx_ring->free_tx_desc = mlx4_en_recycle_tx_desc;
+ tx_ring->recycle_ring = priv->rx_ring[rr_index];
+ en_dbg(DRV, priv, "Set tx_ring[%d][%d]->recycle_ring = rx_ring[%d]\n",
+ TX_XDP, tx_ring_idx, rr_index);
}
int mlx4_en_start_port(struct net_device *dev)
@@ -1548,9 +1546,8 @@ int mlx4_en_start_port(struct net_device *dev)
struct mlx4_en_cq *cq;
struct mlx4_en_tx_ring *tx_ring;
int rx_index = 0;
- int tx_index = 0;
int err = 0;
- int i;
+ int i, t;
int j;
u8 mc_list[16] = {0};
@@ -1635,43 +1632,51 @@ int mlx4_en_start_port(struct net_device *dev)
goto rss_err;
/* Configure tx cq's and rings */
- for (i = 0; i < priv->tx_ring_num; i++) {
- /* Configure cq */
- cq = priv->tx_cq[i];
- err = mlx4_en_activate_cq(priv, cq, i);
- if (err) {
- en_err(priv, "Failed allocating Tx CQ\n");
- goto tx_err;
+ for (t = 0 ; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ u8 num_tx_rings_p_up = t == TX ? priv->num_tx_rings_p_up : 1;
+
+ for (i = 0; i < priv->tx_ring_num[t]; i++) {
+ /* Configure cq */
+ cq = priv->tx_cq[t][i];
+ err = mlx4_en_activate_cq(priv, cq, i);
+ if (err) {
+ en_err(priv, "Failed allocating Tx CQ\n");
+ goto tx_err;
+ }
+ err = mlx4_en_set_cq_moder(priv, cq);
+ if (err) {
+ en_err(priv, "Failed setting cq moderation parameters\n");
+ mlx4_en_deactivate_cq(priv, cq);
+ goto tx_err;
+ }
+ en_dbg(DRV, priv,
+ "Resetting index of collapsed CQ:%d to -1\n", i);
+ cq->buf->wqe_index = cpu_to_be16(0xffff);
+
+ /* Configure ring */
+ tx_ring = priv->tx_ring[t][i];
+ err = mlx4_en_activate_tx_ring(priv, tx_ring,
+ cq->mcq.cqn,
+ i / num_tx_rings_p_up);
+ if (err) {
+ en_err(priv, "Failed allocating Tx ring\n");
+ mlx4_en_deactivate_cq(priv, cq);
+ goto tx_err;
+ }
+ if (t != TX_XDP) {
+ tx_ring->tx_queue = netdev_get_tx_queue(dev, i);
+ tx_ring->recycle_ring = NULL;
+ } else {
+ mlx4_en_init_recycle_ring(priv, i);
+ }
+
+ /* Arm CQ for TX completions */
+ mlx4_en_arm_cq(priv, cq);
+
+ /* Set initial ownership of all Tx TXBBs to SW (1) */
+ for (j = 0; j < tx_ring->buf_size; j += STAMP_STRIDE)
+ *((u32 *)(tx_ring->buf + j)) = 0xffffffff;
}
- err = mlx4_en_set_cq_moder(priv, cq);
- if (err) {
- en_err(priv, "Failed setting cq moderation parameters\n");
- mlx4_en_deactivate_cq(priv, cq);
- goto tx_err;
- }
- en_dbg(DRV, priv, "Resetting index of collapsed CQ:%d to -1\n", i);
- cq->buf->wqe_index = cpu_to_be16(0xffff);
-
- /* Configure ring */
- tx_ring = priv->tx_ring[i];
- err = mlx4_en_activate_tx_ring(priv, tx_ring, cq->mcq.cqn,
- i / priv->num_tx_rings_p_up);
- if (err) {
- en_err(priv, "Failed allocating Tx ring\n");
- mlx4_en_deactivate_cq(priv, cq);
- goto tx_err;
- }
- tx_ring->tx_queue = netdev_get_tx_queue(dev, i);
-
- mlx4_en_init_recycle_ring(priv, i);
-
- /* Arm CQ for TX completions */
- mlx4_en_arm_cq(priv, cq);
-
- /* Set initial ownership of all Tx TXBBs to SW (1) */
- for (j = 0; j < tx_ring->buf_size; j += STAMP_STRIDE)
- *((u32 *) (tx_ring->buf + j)) = 0xffffffff;
- ++tx_index;
}
/* Configure port */
@@ -1733,15 +1738,31 @@ int mlx4_en_start_port(struct net_device *dev)
udp_tunnel_get_rx_info(dev);
priv->port_up = true;
+
+ /* Process all completions if exist to prevent
+ * the queues freezing if they are full
+ */
+ for (i = 0; i < priv->rx_ring_num; i++)
+ napi_schedule(&priv->rx_cq[i]->napi);
+
netif_tx_start_all_queues(dev);
netif_device_attach(dev);
return 0;
tx_err:
- while (tx_index--) {
- mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[tx_index]);
- mlx4_en_deactivate_cq(priv, priv->tx_cq[tx_index]);
+ if (t == MLX4_EN_NUM_TX_TYPES) {
+ t--;
+ i = priv->tx_ring_num[t];
+ }
+ while (t >= 0) {
+ while (i--) {
+ mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[t][i]);
+ mlx4_en_deactivate_cq(priv, priv->tx_cq[t][i]);
+ }
+ if (!t--)
+ break;
+ i = priv->tx_ring_num[t];
}
mlx4_en_destroy_drop_qp(priv);
rss_err:
@@ -1766,7 +1787,7 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
struct mlx4_en_dev *mdev = priv->mdev;
struct mlx4_en_mc_list *mclist, *tmp;
struct ethtool_flow_id *flow, *tmp_flow;
- int i;
+ int i, t;
u8 mc_list[16] = {0};
if (!priv->port_up) {
@@ -1852,14 +1873,17 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
mlx4_en_destroy_drop_qp(priv);
/* Free TX Rings */
- for (i = 0; i < priv->tx_ring_num; i++) {
- mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[i]);
- mlx4_en_deactivate_cq(priv, priv->tx_cq[i]);
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ for (i = 0; i < priv->tx_ring_num[t]; i++) {
+ mlx4_en_deactivate_tx_ring(priv, priv->tx_ring[t][i]);
+ mlx4_en_deactivate_cq(priv, priv->tx_cq[t][i]);
+ }
}
msleep(10);
- for (i = 0; i < priv->tx_ring_num; i++)
- mlx4_en_free_tx_buf(dev, priv->tx_ring[i]);
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++)
+ for (i = 0; i < priv->tx_ring_num[t]; i++)
+ mlx4_en_free_tx_buf(dev, priv->tx_ring[t][i]);
if (mdev->dev->caps.steering_mode != MLX4_STEERING_MODE_A0)
mlx4_en_delete_rss_steer_rules(priv);
@@ -1908,10 +1932,12 @@ static void mlx4_en_clear_stats(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
+ struct mlx4_en_tx_ring **tx_ring;
int i;
- if (mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 1))
- en_dbg(HW, priv, "Failed dumping statistics\n");
+ if (!mlx4_is_slave(mdev->dev))
+ if (mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 1))
+ en_dbg(HW, priv, "Failed dumping statistics\n");
memset(&priv->pstats, 0, sizeof(priv->pstats));
memset(&priv->pkstats, 0, sizeof(priv->pkstats));
@@ -1924,15 +1950,16 @@ static void mlx4_en_clear_stats(struct net_device *dev)
sizeof(priv->tx_priority_flowstats));
memset(&priv->pf_stats, 0, sizeof(priv->pf_stats));
- for (i = 0; i < priv->tx_ring_num; i++) {
- priv->tx_ring[i]->bytes = 0;
- priv->tx_ring[i]->packets = 0;
- priv->tx_ring[i]->tx_csum = 0;
- priv->tx_ring[i]->tx_dropped = 0;
- priv->tx_ring[i]->queue_stopped = 0;
- priv->tx_ring[i]->wake_queue = 0;
- priv->tx_ring[i]->tso_packets = 0;
- priv->tx_ring[i]->xmit_more = 0;
+ tx_ring = priv->tx_ring[TX];
+ for (i = 0; i < priv->tx_ring_num[TX]; i++) {
+ tx_ring[i]->bytes = 0;
+ tx_ring[i]->packets = 0;
+ tx_ring[i]->tx_csum = 0;
+ tx_ring[i]->tx_dropped = 0;
+ tx_ring[i]->queue_stopped = 0;
+ tx_ring[i]->wake_queue = 0;
+ tx_ring[i]->tso_packets = 0;
+ tx_ring[i]->xmit_more = 0;
}
for (i = 0; i < priv->rx_ring_num; i++) {
priv->rx_ring[i]->bytes = 0;
@@ -1988,17 +2015,20 @@ static int mlx4_en_close(struct net_device *dev)
static void mlx4_en_free_resources(struct mlx4_en_priv *priv)
{
- int i;
+ int i, t;
#ifdef CONFIG_RFS_ACCEL
priv->dev->rx_cpu_rmap = NULL;
#endif
- for (i = 0; i < priv->tx_ring_num; i++) {
- if (priv->tx_ring && priv->tx_ring[i])
- mlx4_en_destroy_tx_ring(priv, &priv->tx_ring[i]);
- if (priv->tx_cq && priv->tx_cq[i])
- mlx4_en_destroy_cq(priv, &priv->tx_cq[i]);
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ for (i = 0; i < priv->tx_ring_num[t]; i++) {
+ if (priv->tx_ring[t] && priv->tx_ring[t][i])
+ mlx4_en_destroy_tx_ring(priv,
+ &priv->tx_ring[t][i]);
+ if (priv->tx_cq[t] && priv->tx_cq[t][i])
+ mlx4_en_destroy_cq(priv, &priv->tx_cq[t][i]);
+ }
}
for (i = 0; i < priv->rx_ring_num; i++) {
@@ -2014,20 +2044,22 @@ static void mlx4_en_free_resources(struct mlx4_en_priv *priv)
static int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
{
struct mlx4_en_port_profile *prof = priv->prof;
- int i;
+ int i, t;
int node;
/* Create tx Rings */
- for (i = 0; i < priv->tx_ring_num; i++) {
- node = cpu_to_node(i % num_online_cpus());
- if (mlx4_en_create_cq(priv, &priv->tx_cq[i],
- prof->tx_ring_size, i, TX, node))
- goto err;
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ for (i = 0; i < priv->tx_ring_num[t]; i++) {
+ node = cpu_to_node(i % num_online_cpus());
+ if (mlx4_en_create_cq(priv, &priv->tx_cq[t][i],
+ prof->tx_ring_size, i, t, node))
+ goto err;
- if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i],
- prof->tx_ring_size, TXBB_SIZE,
- node, i))
- goto err;
+ if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[t][i],
+ prof->tx_ring_size,
+ TXBB_SIZE, node, i))
+ goto err;
+ }
}
/* Create rx Rings */
@@ -2059,11 +2091,14 @@ static int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
if (priv->rx_cq[i])
mlx4_en_destroy_cq(priv, &priv->rx_cq[i]);
}
- for (i = 0; i < priv->tx_ring_num; i++) {
- if (priv->tx_ring[i])
- mlx4_en_destroy_tx_ring(priv, &priv->tx_ring[i]);
- if (priv->tx_cq[i])
- mlx4_en_destroy_cq(priv, &priv->tx_cq[i]);
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ for (i = 0; i < priv->tx_ring_num[t]; i++) {
+ if (priv->tx_ring[t][i])
+ mlx4_en_destroy_tx_ring(priv,
+ &priv->tx_ring[t][i]);
+ if (priv->tx_cq[t][i])
+ mlx4_en_destroy_cq(priv, &priv->tx_cq[t][i]);
+ }
}
return -ENOMEM;
}
@@ -2080,10 +2115,11 @@ static int mlx4_en_copy_priv(struct mlx4_en_priv *dst,
struct mlx4_en_priv *src,
struct mlx4_en_port_profile *prof)
{
+ int t;
+
memcpy(&dst->hwtstamp_config, &prof->hwtstamp_config,
sizeof(dst->hwtstamp_config));
dst->num_tx_rings_p_up = src->mdev->profile.num_tx_rings_p_up;
- dst->tx_ring_num = prof->tx_ring_num;
dst->rx_ring_num = prof->rx_ring_num;
dst->flags = prof->flags;
dst->mdev = src->mdev;
@@ -2093,33 +2129,50 @@ static int mlx4_en_copy_priv(struct mlx4_en_priv *dst,
dst->stride = roundup_pow_of_two(sizeof(struct mlx4_en_rx_desc) +
DS_SIZE * MLX4_EN_MAX_RX_FRAGS);
- dst->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring *) * MAX_TX_RINGS,
- GFP_KERNEL);
- if (!dst->tx_ring)
- return -ENOMEM;
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ dst->tx_ring_num[t] = prof->tx_ring_num[t];
+ if (!dst->tx_ring_num[t])
+ continue;
- dst->tx_cq = kzalloc(sizeof(struct mlx4_en_cq *) * MAX_TX_RINGS,
- GFP_KERNEL);
- if (!dst->tx_cq) {
- kfree(dst->tx_ring);
- return -ENOMEM;
+ dst->tx_ring[t] = kzalloc(sizeof(struct mlx4_en_tx_ring *) *
+ MAX_TX_RINGS, GFP_KERNEL);
+ if (!dst->tx_ring[t])
+ goto err_free_tx;
+
+ dst->tx_cq[t] = kzalloc(sizeof(struct mlx4_en_cq *) *
+ MAX_TX_RINGS, GFP_KERNEL);
+ if (!dst->tx_cq[t]) {
+ kfree(dst->tx_ring[t]);
+ goto err_free_tx;
+ }
}
+
return 0;
+
+err_free_tx:
+ while (t--) {
+ kfree(dst->tx_ring[t]);
+ kfree(dst->tx_cq[t]);
+ }
+ return -ENOMEM;
}
static void mlx4_en_update_priv(struct mlx4_en_priv *dst,
struct mlx4_en_priv *src)
{
+ int t;
memcpy(dst->rx_ring, src->rx_ring,
sizeof(struct mlx4_en_rx_ring *) * src->rx_ring_num);
memcpy(dst->rx_cq, src->rx_cq,
sizeof(struct mlx4_en_cq *) * src->rx_ring_num);
memcpy(&dst->hwtstamp_config, &src->hwtstamp_config,
sizeof(dst->hwtstamp_config));
- dst->tx_ring_num = src->tx_ring_num;
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ dst->tx_ring_num[t] = src->tx_ring_num[t];
+ dst->tx_ring[t] = src->tx_ring[t];
+ dst->tx_cq[t] = src->tx_cq[t];
+ }
dst->rx_ring_num = src->rx_ring_num;
- dst->tx_ring = src->tx_ring;
- dst->tx_cq = src->tx_cq;
memcpy(dst->prof, src->prof, sizeof(struct mlx4_en_port_profile));
}
@@ -2127,14 +2180,18 @@ int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
struct mlx4_en_priv *tmp,
struct mlx4_en_port_profile *prof)
{
+ int t;
+
mlx4_en_copy_priv(tmp, priv, prof);
if (mlx4_en_alloc_resources(tmp)) {
en_warn(priv,
"%s: Resource allocation failed, using previous configuration\n",
__func__);
- kfree(tmp->tx_ring);
- kfree(tmp->tx_cq);
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ kfree(tmp->tx_ring[t]);
+ kfree(tmp->tx_cq[t]);
+ }
return -ENOMEM;
}
return 0;
@@ -2153,6 +2210,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
struct mlx4_en_dev *mdev = priv->mdev;
bool shutdown = mdev->dev->persist->interface_state &
MLX4_INTERFACE_STATE_SHUTDOWN;
+ int t;
en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port);
@@ -2189,8 +2247,10 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
mlx4_en_free_resources(priv);
- kfree(priv->tx_ring);
- kfree(priv->tx_cq);
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ kfree(priv->tx_ring[t]);
+ kfree(priv->tx_cq[t]);
+ }
if (!shutdown)
free_netdev(dev);
@@ -2205,7 +2265,7 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
en_dbg(DRV, priv, "Change MTU called - current:%d new:%d\n",
dev->mtu, new_mtu);
- if (priv->xdp_ring_num && MLX4_EN_EFF_MTU(new_mtu) > FRAG_SZ0) {
+ if (priv->tx_ring_num[TX_XDP] && MLX4_EN_EFF_MTU(new_mtu) > FRAG_SZ0) {
en_err(priv, "MTU size:%d requires frags but XDP running\n",
new_mtu);
return -EOPNOTSUPP;
@@ -2596,7 +2656,7 @@ static netdev_features_t mlx4_en_features_check(struct sk_buff *skb,
static int mlx4_en_set_tx_maxrate(struct net_device *dev, int queue_index, u32 maxrate)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
- struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[queue_index];
+ struct mlx4_en_tx_ring *tx_ring = priv->tx_ring[TX][queue_index];
struct mlx4_update_qp_params params;
int err;
@@ -2624,18 +2684,21 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
+ struct mlx4_en_port_profile new_prof;
struct bpf_prog *old_prog;
+ struct mlx4_en_priv *tmp;
+ int tx_changed = 0;
int xdp_ring_num;
int port_up = 0;
int err;
int i;
- xdp_ring_num = prog ? ALIGN(priv->rx_ring_num, MLX4_EN_NUM_UP) : 0;
+ xdp_ring_num = prog ? priv->rx_ring_num : 0;
/* No need to reconfigure buffers when simply swapping the
* program for a new one.
*/
- if (priv->xdp_ring_num == xdp_ring_num) {
+ if (priv->tx_ring_num[TX_XDP] == xdp_ring_num) {
if (prog) {
prog = bpf_prog_add(prog, priv->rx_ring_num - 1);
if (IS_ERR(prog))
@@ -2659,28 +2722,44 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
return -EOPNOTSUPP;
}
- if (priv->tx_ring_num < xdp_ring_num + MLX4_EN_NUM_UP) {
- en_err(priv,
- "Minimum %d tx channels required to run XDP\n",
- (xdp_ring_num + MLX4_EN_NUM_UP) / MLX4_EN_NUM_UP);
- return -EINVAL;
- }
+ tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+ if (!tmp)
+ return -ENOMEM;
if (prog) {
prog = bpf_prog_add(prog, priv->rx_ring_num - 1);
- if (IS_ERR(prog))
- return PTR_ERR(prog);
+ if (IS_ERR(prog)) {
+ err = PTR_ERR(prog);
+ goto out;
+ }
}
mutex_lock(&mdev->state_lock);
+ memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
+ new_prof.tx_ring_num[TX_XDP] = xdp_ring_num;
+
+ if (priv->tx_ring_num[TX] + xdp_ring_num > MAX_TX_RINGS) {
+ tx_changed = 1;
+ new_prof.tx_ring_num[TX] =
+ MAX_TX_RINGS - ALIGN(xdp_ring_num, MLX4_EN_NUM_UP);
+ en_warn(priv, "Reducing the number of TX rings, to not exceed the max total rings number.\n");
+ }
+
+ err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+ if (err) {
+ if (prog)
+ bpf_prog_sub(prog, priv->rx_ring_num - 1);
+ goto unlock_out;
+ }
+
if (priv->port_up) {
port_up = 1;
mlx4_en_stop_port(dev, 1);
}
- priv->xdp_ring_num = xdp_ring_num;
- netif_set_real_num_tx_queues(dev, priv->tx_ring_num -
- priv->xdp_ring_num);
+ mlx4_en_safe_replace_resources(priv, tmp);
+ if (tx_changed)
+ netif_set_real_num_tx_queues(dev, priv->tx_ring_num[TX]);
for (i = 0; i < priv->rx_ring_num; i++) {
old_prog = rcu_dereference_protected(
@@ -2700,15 +2779,18 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
}
}
+unlock_out:
mutex_unlock(&mdev->state_lock);
- return 0;
+out:
+ kfree(tmp);
+ return err;
}
static bool mlx4_xdp_attached(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
- return !!priv->xdp_ring_num;
+ return !!priv->tx_ring_num[TX_XDP];
}
static int mlx4_xdp(struct net_device *dev, struct netdev_xdp *xdp)
@@ -3045,6 +3127,10 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev,
if (!mlx4_is_slave(dev))
bitmap_set(stats_bitmap->bitmap, last_i, NUM_PKT_STATS);
+ last_i += NUM_PKT_STATS;
+
+ bitmap_set(stats_bitmap->bitmap, last_i, NUM_XDP_STATS);
+ last_i += NUM_XDP_STATS;
}
int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
@@ -3052,7 +3138,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
{
struct net_device *dev;
struct mlx4_en_priv *priv;
- int i;
+ int i, t;
int err;
dev = alloc_etherdev_mqs(sizeof(struct mlx4_en_priv),
@@ -3060,7 +3146,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
if (dev == NULL)
return -ENOMEM;
- netif_set_real_num_tx_queues(dev, prof->tx_ring_num);
+ netif_set_real_num_tx_queues(dev, prof->tx_ring_num[TX]);
netif_set_real_num_rx_queues(dev, prof->rx_ring_num);
SET_NETDEV_DEV(dev, &mdev->dev->persist->pdev->dev);
@@ -3097,21 +3183,27 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
priv->ctrl_flags = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE |
MLX4_WQE_CTRL_SOLICITED);
priv->num_tx_rings_p_up = mdev->profile.num_tx_rings_p_up;
- priv->tx_ring_num = prof->tx_ring_num;
priv->tx_work_limit = MLX4_EN_DEFAULT_TX_WORK;
netdev_rss_key_fill(priv->rss_key, sizeof(priv->rss_key));
- priv->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring *) * MAX_TX_RINGS,
- GFP_KERNEL);
- if (!priv->tx_ring) {
- err = -ENOMEM;
- goto out;
- }
- priv->tx_cq = kzalloc(sizeof(struct mlx4_en_cq *) * MAX_TX_RINGS,
- GFP_KERNEL);
- if (!priv->tx_cq) {
- err = -ENOMEM;
- goto out;
+ for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
+ priv->tx_ring_num[t] = prof->tx_ring_num[t];
+ if (!priv->tx_ring_num[t])
+ continue;
+
+ priv->tx_ring[t] = kzalloc(sizeof(struct mlx4_en_tx_ring *) *
+ MAX_TX_RINGS, GFP_KERNEL);
+ if (!priv->tx_ring[t]) {
+ err = -ENOMEM;
+ goto err_free_tx;
+ }
+ priv->tx_cq[t] = kzalloc(sizeof(struct mlx4_en_cq *) *
+ MAX_TX_RINGS, GFP_KERNEL);
+ if (!priv->tx_cq[t]) {
+ kfree(priv->tx_ring[t]);
+ err = -ENOMEM;
+ goto out;
+ }
}
priv->rx_ring_num = prof->rx_ring_num;
priv->cqe_factor = (mdev->dev->caps.cqe_size == 64) ? 1 : 0;
@@ -3194,7 +3286,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
else
dev->netdev_ops = &mlx4_netdev_ops;
dev->watchdog_timeo = MLX4_EN_WATCHDOG_TIMEOUT;
- netif_set_real_num_tx_queues(dev, priv->tx_ring_num);
+ netif_set_real_num_tx_queues(dev, priv->tx_ring_num[TX]);
netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
dev->ethtool_ops = &mlx4_en_ethtool_ops;
@@ -3294,7 +3386,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
netif_carrier_off(dev);
mlx4_en_set_default_moderation(priv);
- en_warn(priv, "Using %d TX rings\n", prof->tx_ring_num);
+ en_warn(priv, "Using %d TX rings\n", prof->tx_ring_num[TX]);
en_warn(priv, "Using %d RX rings\n", prof->rx_ring_num);
mlx4_en_update_loopback_state(priv->dev, priv->dev->features);
@@ -3354,6 +3446,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
return 0;
+err_free_tx:
+ while (t--) {
+ kfree(priv->tx_ring[t]);
+ kfree(priv->tx_cq[t]);
+ }
out:
mlx4_en_destroy_netdev(dev);
return err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 5aa8b75..1eb4c1e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -166,7 +166,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
return PTR_ERR(mailbox);
err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, in_mod, 0,
MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B,
- MLX4_CMD_WRAPPED);
+ MLX4_CMD_NATIVE);
if (err)
goto out;
@@ -179,6 +179,9 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
priv->port_stats.rx_chksum_good = 0;
priv->port_stats.rx_chksum_none = 0;
priv->port_stats.rx_chksum_complete = 0;
+ priv->xdp_stats.rx_xdp_drop = 0;
+ priv->xdp_stats.rx_xdp_tx = 0;
+ priv->xdp_stats.rx_xdp_tx_full = 0;
for (i = 0; i < priv->rx_ring_num; i++) {
stats->rx_packets += priv->rx_ring[i]->packets;
stats->rx_bytes += priv->rx_ring[i]->bytes;
@@ -186,6 +189,9 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
priv->port_stats.rx_chksum_good += priv->rx_ring[i]->csum_ok;
priv->port_stats.rx_chksum_none += priv->rx_ring[i]->csum_none;
priv->port_stats.rx_chksum_complete += priv->rx_ring[i]->csum_complete;
+ priv->xdp_stats.rx_xdp_drop += priv->rx_ring[i]->xdp_drop;
+ priv->xdp_stats.rx_xdp_tx += priv->rx_ring[i]->xdp_tx;
+ priv->xdp_stats.rx_xdp_tx_full += priv->rx_ring[i]->xdp_tx_full;
}
stats->tx_packets = 0;
stats->tx_bytes = 0;
@@ -196,8 +202,8 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
priv->port_stats.tso_packets = 0;
priv->port_stats.xmit_more = 0;
- for (i = 0; i < priv->tx_ring_num; i++) {
- const struct mlx4_en_tx_ring *ring = priv->tx_ring[i];
+ for (i = 0; i < priv->tx_ring_num[TX]; i++) {
+ const struct mlx4_en_tx_ring *ring = priv->tx_ring[TX][i];
stats->tx_packets += ring->packets;
stats->tx_bytes += ring->bytes;
@@ -322,7 +328,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma,
in_mod | MLX4_DUMP_ETH_STATS_FLOW_CONTROL,
0, MLX4_CMD_DUMP_ETH_STATS,
- MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
if (err)
goto out;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index f2e8bed..22f08f9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -788,7 +788,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
struct bpf_prog *xdp_prog;
int doorbell_pending;
struct sk_buff *skb;
- int tx_index;
int index;
int nr;
unsigned int length;
@@ -808,7 +807,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
rcu_read_lock();
xdp_prog = rcu_dereference(ring->xdp_prog);
doorbell_pending = 0;
- tx_index = (priv->tx_ring_num - priv->xdp_ring_num) + cq->ring;
/* We assume a 1:1 mapping between CQEs and Rx descriptors, so Rx
* descriptor offset can be deduced from the CQE index instead of
@@ -877,8 +875,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
*/
length = be32_to_cpu(cqe->byte_cnt);
length -= ring->fcs_del;
- ring->bytes += length;
- ring->packets++;
l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
(cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
@@ -904,22 +900,26 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
case XDP_PASS:
break;
case XDP_TX:
- if (likely(!mlx4_en_xmit_frame(frags, dev,
- length, tx_index,
+ if (likely(!mlx4_en_xmit_frame(ring, frags, dev,
+ length, cq->ring,
&doorbell_pending)))
goto consumed;
- goto xdp_drop; /* Drop on xmit failure */
+ goto xdp_drop_no_cnt; /* Drop on xmit failure */
default:
bpf_warn_invalid_xdp_action(act);
case XDP_ABORTED:
case XDP_DROP:
-xdp_drop:
+ ring->xdp_drop++;
+xdp_drop_no_cnt:
if (likely(mlx4_en_rx_recycle(ring, frags)))
goto consumed;
goto next;
}
}
+ ring->bytes += length;
+ ring->packets++;
+
if (likely(dev->features & NETIF_F_RXCSUM)) {
if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
MLX4_CQE_STATUS_UDP)) {
@@ -1082,7 +1082,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
out:
rcu_read_unlock();
if (doorbell_pending)
- mlx4_en_xmit_doorbell(priv->tx_ring[tx_index]);
+ mlx4_en_xmit_doorbell(priv->tx_ring[TX_XDP][cq->ring]);
AVG_PERF_COUNTER(priv->pstats.rx_coal_avg, polled);
mlx4_cq_set_ci(&cq->mcq);
@@ -1137,8 +1137,8 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
done = 0;
}
/* Done for now */
- napi_complete_done(napi, done);
- mlx4_en_arm_cq(priv, cq);
+ if (napi_complete_done(napi, done))
+ mlx4_en_arm_cq(priv, cq);
return done;
}
@@ -1162,7 +1162,7 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
/* bpf requires buffers to be set up as 1 packet per page.
* This only works when num_frags == 1.
*/
- if (priv->xdp_ring_num) {
+ if (priv->tx_ring_num[TX_XDP]) {
dma_dir = PCI_DMA_BIDIRECTIONAL;
/* This will gain efficient xdp frame recycling at the expense
* of more costly truesize accounting
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
index b66e03d..c06346a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
@@ -118,6 +118,29 @@ static int mlx4_en_test_loopback(struct mlx4_en_priv *priv)
return !loopback_ok;
}
+static int mlx4_en_test_interrupts(struct mlx4_en_priv *priv)
+{
+ struct mlx4_en_dev *mdev = priv->mdev;
+ int err = 0;
+ int i = 0;
+
+ err = mlx4_test_async(mdev->dev);
+ /* When not in MSI_X or slave, test only async */
+ if (!(mdev->dev->flags & MLX4_FLAG_MSI_X) || mlx4_is_slave(mdev->dev))
+ return err;
+
+ /* A loop over all completion vectors of current port,
+ * for each vector check whether it works by mapping command
+ * completions to that vector and performing a NOP command
+ */
+ for (i = 0; i < priv->rx_ring_num; i++) {
+ err = mlx4_test_interrupt(mdev->dev, priv->rx_cq[i]->vector);
+ if (err)
+ break;
+ }
+
+ return err;
+}
static int mlx4_en_test_link(struct mlx4_en_priv *priv)
{
@@ -151,7 +174,6 @@ static int mlx4_en_test_speed(struct mlx4_en_priv *priv)
void mlx4_en_ex_selftest(struct net_device *dev, u32 *flags, u64 *buf)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
- struct mlx4_en_dev *mdev = priv->mdev;
int i, carrier_ok;
memset(buf, 0, sizeof(u64) * MLX4_EN_NUM_SELF_TEST);
@@ -177,7 +199,7 @@ void mlx4_en_ex_selftest(struct net_device *dev, u32 *flags, u64 *buf)
netif_carrier_on(dev);
}
- buf[0] = mlx4_test_interrupts(mdev->dev);
+ buf[0] = mlx4_en_test_interrupts(priv);
buf[1] = mlx4_en_test_link(priv);
buf[2] = mlx4_en_test_speed(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index e2509bb..5de3cbe 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -392,7 +392,8 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring)
cnt++;
}
- netdev_tx_reset_queue(ring->tx_queue);
+ if (ring->tx_queue)
+ netdev_tx_reset_queue(ring->tx_queue);
if (cnt)
en_dbg(DRV, priv, "Freed %d uncompleted tx descriptors\n", cnt);
@@ -405,7 +406,7 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_cq *mcq = &cq->mcq;
- struct mlx4_en_tx_ring *ring = priv->tx_ring[cq->ring];
+ struct mlx4_en_tx_ring *ring = priv->tx_ring[cq->type][cq->ring];
struct mlx4_cqe *cqe;
u16 index;
u16 new_index, ring_index, stamp_index;
@@ -807,7 +808,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
bool bf_ok;
tx_ind = skb_get_queue_mapping(skb);
- ring = priv->tx_ring[tx_ind];
+ ring = priv->tx_ring[TX][tx_ind];
if (!priv->port_up)
goto tx_drop;
@@ -1078,7 +1079,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
-netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
+netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
+ struct mlx4_en_rx_alloc *frame,
struct net_device *dev, unsigned int length,
int tx_ind, int *doorbell_pending)
{
@@ -1101,7 +1103,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
BUILD_BUG_ON_MSG(ALIGN(CTRL_SIZE + DS_SIZE, TXBB_SIZE) != TXBB_SIZE,
"mlx4_en_xmit_frame requires minimum size tx desc");
- ring = priv->tx_ring[tx_ind];
+ ring = priv->tx_ring[TX_XDP][tx_ind];
if (!priv->port_up)
goto tx_drop;
@@ -1153,8 +1155,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
((ring->prod & ring->size) ?
cpu_to_be32(MLX4_EN_BIT_DESC_OWN) : 0);
- ring->packets++;
- ring->bytes += tx_info->nr_bytes;
+ rx_ring->xdp_tx++;
AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, length);
ring->prod += nr_txbb;
@@ -1178,7 +1179,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
return NETDEV_TX_OK;
tx_drop_count:
- ring->tx_dropped++;
+ rx_ring->xdp_tx_full++;
tx_drop:
return NETDEV_TX_BUSY;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index cf8f8a7..cd3638e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -1361,53 +1361,49 @@ void mlx4_cleanup_eq_table(struct mlx4_dev *dev)
kfree(priv->eq_table.uar_map);
}
-/* A test that verifies that we can accept interrupts on all
- * the irq vectors of the device.
+/* A test that verifies that we can accept interrupts
+ * on the vector allocated for asynchronous events
+ */
+int mlx4_test_async(struct mlx4_dev *dev)
+{
+ return mlx4_NOP(dev);
+}
+EXPORT_SYMBOL(mlx4_test_async);
+
+/* A test that verifies that we can accept interrupts
+ * on the given irq vector of the tested port.
* Interrupts are checked using the NOP command.
*/
-int mlx4_test_interrupts(struct mlx4_dev *dev)
+int mlx4_test_interrupt(struct mlx4_dev *dev, int vector)
{
struct mlx4_priv *priv = mlx4_priv(dev);
- int i;
int err;
- err = mlx4_NOP(dev);
- /* When not in MSI_X, there is only one irq to check */
- if (!(dev->flags & MLX4_FLAG_MSI_X) || mlx4_is_slave(dev))
- return err;
+ /* Temporary use polling for command completions */
+ mlx4_cmd_use_polling(dev);
- /* A loop over all completion vectors, for each vector we will check
- * whether it works by mapping command completions to that vector
- * and performing a NOP command
- */
- for(i = 0; !err && (i < dev->caps.num_comp_vectors); ++i) {
- /* Make sure request_irq was called */
- if (!priv->eq_table.eq[i].have_irq)
- continue;
-
- /* Temporary use polling for command completions */
- mlx4_cmd_use_polling(dev);
-
- /* Map the new eq to handle all asynchronous events */
- err = mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0,
- priv->eq_table.eq[i].eqn);
- if (err) {
- mlx4_warn(dev, "Failed mapping eq for interrupt test\n");
- mlx4_cmd_use_events(dev);
- break;
- }
-
- /* Go back to using events */
- mlx4_cmd_use_events(dev);
- err = mlx4_NOP(dev);
+ /* Map the new eq to handle all asynchronous events */
+ err = mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0,
+ priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].eqn);
+ if (err) {
+ mlx4_warn(dev, "Failed mapping eq for interrupt test\n");
+ goto out;
}
+ /* Go back to using events */
+ mlx4_cmd_use_events(dev);
+ err = mlx4_NOP(dev);
+
/* Return to default */
+ mlx4_cmd_use_polling(dev);
+out:
mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0,
priv->eq_table.eq[MLX4_EQ_ASYNC].eqn);
+ mlx4_cmd_use_events(dev);
+
return err;
}
-EXPORT_SYMBOL(mlx4_test_interrupts);
+EXPORT_SYMBOL(mlx4_test_interrupt);
bool mlx4_is_eq_vector_valid(struct mlx4_dev *dev, u8 port, int vector)
{
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index c41ab31..84bab9f0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -49,9 +49,9 @@ enum {
extern void __buggy_use_of_MLX4_GET(void);
extern void __buggy_use_of_MLX4_PUT(void);
-static bool enable_qos = true;
+static bool enable_qos;
module_param(enable_qos, bool, 0444);
-MODULE_PARM_DESC(enable_qos, "Enable Enhanced QoS support (default: on)");
+MODULE_PARM_DESC(enable_qos, "Enable Enhanced QoS support (default: off)");
#define MLX4_GET(dest, source, offset) \
do { \
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 7183ac4..6f4e67b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1102,6 +1102,14 @@ static int __set_port_type(struct mlx4_port_info *info,
int i;
int err = 0;
+ if ((port_type & mdev->caps.supported_type[info->port]) != port_type) {
+ mlx4_err(mdev,
+ "Requested port type for port %d is not supported on this HCA\n",
+ info->port);
+ err = -EINVAL;
+ goto err_sup;
+ }
+
mlx4_stop_sense(mdev);
mutex_lock(&priv->port_mutex);
info->tmp_type = port_type;
@@ -1147,7 +1155,7 @@ static int __set_port_type(struct mlx4_port_info *info,
out:
mlx4_start_sense(mdev);
mutex_unlock(&priv->port_mutex);
-
+err_sup:
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index e4878f3..88ee7d8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -145,9 +145,10 @@ enum mlx4_resource {
RES_MTT,
RES_MAC,
RES_VLAN,
- RES_EQ,
+ RES_NPORT_ID,
RES_COUNTER,
RES_FS_RULE,
+ RES_EQ,
MLX4_NUM_OF_RESOURCE_TYPE
};
@@ -1329,8 +1330,6 @@ int mlx4_SET_VLAN_FLTR_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_cmd_info *cmd);
int mlx4_common_set_vlan_fltr(struct mlx4_dev *dev, int function,
int port, void *buf);
-int mlx4_common_dump_eth_stats(struct mlx4_dev *dev, int slave, u32 in_mod,
- struct mlx4_cmd_mailbox *outbox);
int mlx4_DUMP_ETH_STATS_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index a3528dd..eff2165 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -207,8 +207,11 @@ enum {
*/
enum cq_type {
- RX = 0,
- TX = 1,
+ /* keep tx types first */
+ TX,
+ TX_XDP,
+#define MLX4_EN_NUM_TX_TYPES (TX_XDP + 1)
+ RX,
};
@@ -347,6 +350,9 @@ struct mlx4_en_rx_ring {
unsigned long csum_ok;
unsigned long csum_none;
unsigned long csum_complete;
+ unsigned long xdp_drop;
+ unsigned long xdp_tx;
+ unsigned long xdp_tx_full;
unsigned long dropped;
int hwtstamp_rx_filter;
cpumask_var_t affinity_mask;
@@ -361,7 +367,7 @@ struct mlx4_en_cq {
int size;
int buf_size;
int vector;
- enum cq_type is_tx;
+ enum cq_type type;
u16 moder_time;
u16 moder_cnt;
struct mlx4_cqe *buf;
@@ -372,7 +378,7 @@ struct mlx4_en_cq {
struct mlx4_en_port_profile {
u32 flags;
- u32 tx_ring_num;
+ u32 tx_ring_num[MLX4_EN_NUM_TX_TYPES];
u32 rx_ring_num;
u32 tx_ring_size;
u32 rx_ring_size;
@@ -569,17 +575,16 @@ struct mlx4_en_priv {
u32 flags;
u8 num_tx_rings_p_up;
u32 tx_work_limit;
- u32 tx_ring_num;
+ u32 tx_ring_num[MLX4_EN_NUM_TX_TYPES];
u32 rx_ring_num;
u32 rx_skb_size;
struct mlx4_en_frag_info frag_info[MLX4_EN_MAX_RX_FRAGS];
u16 num_frags;
u16 log_rx_info;
- int xdp_ring_num;
- struct mlx4_en_tx_ring **tx_ring;
+ struct mlx4_en_tx_ring **tx_ring[MLX4_EN_NUM_TX_TYPES];
struct mlx4_en_rx_ring *rx_ring[MAX_RX_RINGS];
- struct mlx4_en_cq **tx_cq;
+ struct mlx4_en_cq **tx_cq[MLX4_EN_NUM_TX_TYPES];
struct mlx4_en_cq *rx_cq[MAX_RX_RINGS];
struct mlx4_qp drop_qp;
struct work_struct rx_mode_task;
@@ -597,6 +602,7 @@ struct mlx4_en_priv {
struct mlx4_en_flow_stats_rx rx_flowstats;
struct mlx4_en_flow_stats_tx tx_flowstats;
struct mlx4_en_port_stats port_stats;
+ struct mlx4_en_xdp_stats xdp_stats;
struct mlx4_en_stats_bitmap stats_bitmap;
struct list_head mc_list;
struct list_head curr_list;
@@ -685,7 +691,8 @@ void mlx4_en_tx_irq(struct mlx4_cq *mcq);
u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
void *accel_priv, select_queue_fallback_t fallback);
netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
-netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_alloc *frame,
+netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
+ struct mlx4_en_rx_alloc *frame,
struct net_device *dev, unsigned int length,
int tx_ind, int *doorbell_pending);
void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
index 7fd466c..48641cb 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
@@ -55,6 +55,13 @@ struct mlx4_en_perf_stats {
#define NUM_PERF_COUNTERS 6
};
+struct mlx4_en_xdp_stats {
+ unsigned long rx_xdp_drop;
+ unsigned long rx_xdp_tx;
+ unsigned long rx_xdp_tx_full;
+#define NUM_XDP_STATS 3
+};
+
#define NUM_MAIN_STATS 21
#define MLX4_NUM_PRIORITIES 8
@@ -107,7 +114,8 @@ enum {
};
#define NUM_ALL_STATS (NUM_MAIN_STATS + NUM_PORT_STATS + NUM_PKT_STATS + \
- NUM_FLOW_STATS + NUM_PERF_STATS + NUM_PF_STATS)
+ NUM_FLOW_STATS + NUM_PERF_STATS + NUM_PF_STATS + \
+ NUM_XDP_STATS)
#define MLX4_FIND_NETDEV_STAT(n) (offsetof(struct net_device_stats, n) / \
sizeof(((struct net_device_stats *)0)->n))
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index c5b2064..b656dd5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -1728,24 +1728,13 @@ int mlx4_SET_VLAN_FLTR_wrapper(struct mlx4_dev *dev, int slave,
return err;
}
-int mlx4_common_dump_eth_stats(struct mlx4_dev *dev, int slave,
- u32 in_mod, struct mlx4_cmd_mailbox *outbox)
-{
- return mlx4_cmd_box(dev, 0, outbox->dma, in_mod, 0,
- MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B,
- MLX4_CMD_NATIVE);
-}
-
int mlx4_DUMP_ETH_STATS_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_vhcr *vhcr,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd)
{
- if (slave != dev->caps.function)
- return 0;
- return mlx4_common_dump_eth_stats(dev, slave,
- vhcr->in_modifier, outbox);
+ return 0;
}
int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid,
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 84d7857..c548bea 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -1605,13 +1605,14 @@ static int eq_res_start_move_to(struct mlx4_dev *dev, int slave, int index,
r->com.from_state = r->com.state;
r->com.to_state = state;
r->com.state = RES_EQ_BUSY;
- if (eq)
- *eq = r;
}
}
spin_unlock_irq(mlx4_tlock(dev));
+ if (!err && eq)
+ *eq = r;
+
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
index 6cb3830..2c6e3c7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
@@ -41,6 +41,13 @@
#include "mlx5_core.h"
+struct mlx5_db_pgdir {
+ struct list_head list;
+ unsigned long *bitmap;
+ __be32 *db_page;
+ dma_addr_t db_dma;
+};
+
/* Handling for queue buffers -- we allocate a bunch of memory and
* register it in a memory region at HCA virtual address 0.
*/
@@ -102,17 +109,28 @@ EXPORT_SYMBOL_GPL(mlx5_buf_free);
static struct mlx5_db_pgdir *mlx5_alloc_db_pgdir(struct mlx5_core_dev *dev,
int node)
{
+ u32 db_per_page = PAGE_SIZE / cache_line_size();
struct mlx5_db_pgdir *pgdir;
pgdir = kzalloc(sizeof(*pgdir), GFP_KERNEL);
if (!pgdir)
return NULL;
- bitmap_fill(pgdir->bitmap, MLX5_DB_PER_PAGE);
+ pgdir->bitmap = kcalloc(BITS_TO_LONGS(db_per_page),
+ sizeof(unsigned long),
+ GFP_KERNEL);
+
+ if (!pgdir->bitmap) {
+ kfree(pgdir);
+ return NULL;
+ }
+
+ bitmap_fill(pgdir->bitmap, db_per_page);
pgdir->db_page = mlx5_dma_zalloc_coherent_node(dev, PAGE_SIZE,
&pgdir->db_dma, node);
if (!pgdir->db_page) {
+ kfree(pgdir->bitmap);
kfree(pgdir);
return NULL;
}
@@ -123,18 +141,19 @@ static struct mlx5_db_pgdir *mlx5_alloc_db_pgdir(struct mlx5_core_dev *dev,
static int mlx5_alloc_db_from_pgdir(struct mlx5_db_pgdir *pgdir,
struct mlx5_db *db)
{
+ u32 db_per_page = PAGE_SIZE / cache_line_size();
int offset;
int i;
- i = find_first_bit(pgdir->bitmap, MLX5_DB_PER_PAGE);
- if (i >= MLX5_DB_PER_PAGE)
+ i = find_first_bit(pgdir->bitmap, db_per_page);
+ if (i >= db_per_page)
return -ENOMEM;
__clear_bit(i, pgdir->bitmap);
db->u.pgdir = pgdir;
db->index = i;
- offset = db->index * L1_CACHE_BYTES;
+ offset = db->index * cache_line_size();
db->db = pgdir->db_page + offset / sizeof(*pgdir->db_page);
db->dma = pgdir->db_dma + offset;
@@ -181,14 +200,16 @@ EXPORT_SYMBOL_GPL(mlx5_db_alloc);
void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db)
{
+ u32 db_per_page = PAGE_SIZE / cache_line_size();
mutex_lock(&dev->priv.pgdir_mutex);
__set_bit(db->index, db->u.pgdir->bitmap);
- if (bitmap_full(db->u.pgdir->bitmap, MLX5_DB_PER_PAGE)) {
+ if (bitmap_full(db->u.pgdir->bitmap, db_per_page)) {
dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE,
db->u.pgdir->db_page, db->u.pgdir->db_dma);
list_del(&db->u.pgdir->list);
+ kfree(db->u.pgdir->bitmap);
kfree(db->u.pgdir);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 1e639f8..0fe7a60 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -54,14 +54,6 @@ enum {
};
enum {
- NUM_LONG_LISTS = 2,
- NUM_MED_LISTS = 64,
- LONG_LIST_SIZE = (2ULL * 1024 * 1024 * 1024 / PAGE_SIZE) * 8 + 16 +
- MLX5_CMD_DATA_BLOCK_SIZE,
- MED_LIST_SIZE = 16 + MLX5_CMD_DATA_BLOCK_SIZE,
-};
-
-enum {
MLX5_CMD_DELIVERY_STAT_OK = 0x0,
MLX5_CMD_DELIVERY_STAT_SIGNAT_ERR = 0x1,
MLX5_CMD_DELIVERY_STAT_TOK_ERR = 0x2,
@@ -318,6 +310,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY:
case MLX5_CMD_OP_SET_FLOW_TABLE_ROOT:
case MLX5_CMD_OP_DEALLOC_ENCAP_HEADER:
+ case MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT:
+ case MLX5_CMD_OP_DESTROY_QOS_PARA_VPORT:
return MLX5_CMD_STAT_OK;
case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -419,11 +413,14 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_QUERY_FLOW_TABLE:
case MLX5_CMD_OP_CREATE_FLOW_GROUP:
case MLX5_CMD_OP_QUERY_FLOW_GROUP:
-
case MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY:
case MLX5_CMD_OP_ALLOC_FLOW_COUNTER:
case MLX5_CMD_OP_QUERY_FLOW_COUNTER:
case MLX5_CMD_OP_ALLOC_ENCAP_HEADER:
+ case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT:
+ case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT:
+ case MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT:
+ case MLX5_CMD_OP_CREATE_QOS_PARA_VPORT:
*status = MLX5_DRIVER_STATUS_ABORTED;
*synd = MLX5_DRIVER_SYND;
return -EIO;
@@ -580,6 +577,12 @@ const char *mlx5_command_str(int command)
MLX5_COMMAND_STR_CASE(MODIFY_FLOW_TABLE);
MLX5_COMMAND_STR_CASE(ALLOC_ENCAP_HEADER);
MLX5_COMMAND_STR_CASE(DEALLOC_ENCAP_HEADER);
+ MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT);
+ MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT);
+ MLX5_COMMAND_STR_CASE(QUERY_SCHEDULING_ELEMENT);
+ MLX5_COMMAND_STR_CASE(MODIFY_SCHEDULING_ELEMENT);
+ MLX5_COMMAND_STR_CASE(CREATE_QOS_PARA_VPORT);
+ MLX5_COMMAND_STR_CASE(DESTROY_QOS_PARA_VPORT);
default: return "unknown command opcode";
}
}
@@ -1361,10 +1364,10 @@ static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
{
unsigned long flags;
- if (msg->cache) {
- spin_lock_irqsave(&msg->cache->lock, flags);
- list_add_tail(&msg->list, &msg->cache->head);
- spin_unlock_irqrestore(&msg->cache->lock, flags);
+ if (msg->parent) {
+ spin_lock_irqsave(&msg->parent->lock, flags);
+ list_add_tail(&msg->list, &msg->parent->head);
+ spin_unlock_irqrestore(&msg->parent->lock, flags);
} else {
mlx5_free_cmd_msg(dev, msg);
}
@@ -1461,30 +1464,37 @@ static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size,
gfp_t gfp)
{
struct mlx5_cmd_msg *msg = ERR_PTR(-ENOMEM);
+ struct cmd_msg_cache *ch = NULL;
struct mlx5_cmd *cmd = &dev->cmd;
- struct cache_ent *ent = NULL;
+ int i;
- if (in_size > MED_LIST_SIZE && in_size <= LONG_LIST_SIZE)
- ent = &cmd->cache.large;
- else if (in_size > 16 && in_size <= MED_LIST_SIZE)
- ent = &cmd->cache.med;
+ if (in_size <= 16)
+ goto cache_miss;
- if (ent) {
- spin_lock_irq(&ent->lock);
- if (!list_empty(&ent->head)) {
- msg = list_entry(ent->head.next, typeof(*msg), list);
- /* For cached lists, we must explicitly state what is
- * the real size
- */
- msg->len = in_size;
- list_del(&msg->list);
+ for (i = 0; i < MLX5_NUM_COMMAND_CACHES; i++) {
+ ch = &cmd->cache[i];
+ if (in_size > ch->max_inbox_size)
+ continue;
+ spin_lock_irq(&ch->lock);
+ if (list_empty(&ch->head)) {
+ spin_unlock_irq(&ch->lock);
+ continue;
}
- spin_unlock_irq(&ent->lock);
+ msg = list_entry(ch->head.next, typeof(*msg), list);
+ /* For cached lists, we must explicitly state what is
+ * the real size
+ */
+ msg->len = in_size;
+ list_del(&msg->list);
+ spin_unlock_irq(&ch->lock);
+ break;
}
- if (IS_ERR(msg))
- msg = mlx5_alloc_cmd_msg(dev, gfp, in_size, 0);
+ if (!IS_ERR(msg))
+ return msg;
+cache_miss:
+ msg = mlx5_alloc_cmd_msg(dev, gfp, in_size, 0);
return msg;
}
@@ -1582,58 +1592,56 @@ EXPORT_SYMBOL(mlx5_cmd_exec_cb);
static void destroy_msg_cache(struct mlx5_core_dev *dev)
{
- struct mlx5_cmd *cmd = &dev->cmd;
+ struct cmd_msg_cache *ch;
struct mlx5_cmd_msg *msg;
struct mlx5_cmd_msg *n;
+ int i;
- list_for_each_entry_safe(msg, n, &cmd->cache.large.head, list) {
- list_del(&msg->list);
- mlx5_free_cmd_msg(dev, msg);
- }
-
- list_for_each_entry_safe(msg, n, &cmd->cache.med.head, list) {
- list_del(&msg->list);
- mlx5_free_cmd_msg(dev, msg);
+ for (i = 0; i < MLX5_NUM_COMMAND_CACHES; i++) {
+ ch = &dev->cmd.cache[i];
+ list_for_each_entry_safe(msg, n, &ch->head, list) {
+ list_del(&msg->list);
+ mlx5_free_cmd_msg(dev, msg);
+ }
}
}
-static int create_msg_cache(struct mlx5_core_dev *dev)
+static unsigned cmd_cache_num_ent[MLX5_NUM_COMMAND_CACHES] = {
+ 512, 32, 16, 8, 2
+};
+
+static unsigned cmd_cache_ent_size[MLX5_NUM_COMMAND_CACHES] = {
+ 16 + MLX5_CMD_DATA_BLOCK_SIZE,
+ 16 + MLX5_CMD_DATA_BLOCK_SIZE * 2,
+ 16 + MLX5_CMD_DATA_BLOCK_SIZE * 16,
+ 16 + MLX5_CMD_DATA_BLOCK_SIZE * 256,
+ 16 + MLX5_CMD_DATA_BLOCK_SIZE * 512,
+};
+
+static void create_msg_cache(struct mlx5_core_dev *dev)
{
struct mlx5_cmd *cmd = &dev->cmd;
+ struct cmd_msg_cache *ch;
struct mlx5_cmd_msg *msg;
- int err;
int i;
+ int k;
- spin_lock_init(&cmd->cache.large.lock);
- INIT_LIST_HEAD(&cmd->cache.large.head);
- spin_lock_init(&cmd->cache.med.lock);
- INIT_LIST_HEAD(&cmd->cache.med.head);
-
- for (i = 0; i < NUM_LONG_LISTS; i++) {
- msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, LONG_LIST_SIZE, 0);
- if (IS_ERR(msg)) {
- err = PTR_ERR(msg);
- goto ex_err;
+ /* Initialize and fill the caches with initial entries */
+ for (k = 0; k < MLX5_NUM_COMMAND_CACHES; k++) {
+ ch = &cmd->cache[k];
+ spin_lock_init(&ch->lock);
+ INIT_LIST_HEAD(&ch->head);
+ ch->num_ent = cmd_cache_num_ent[k];
+ ch->max_inbox_size = cmd_cache_ent_size[k];
+ for (i = 0; i < ch->num_ent; i++) {
+ msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL | __GFP_NOWARN,
+ ch->max_inbox_size, 0);
+ if (IS_ERR(msg))
+ break;
+ msg->parent = ch;
+ list_add_tail(&msg->list, &ch->head);
}
- msg->cache = &cmd->cache.large;
- list_add_tail(&msg->list, &cmd->cache.large.head);
}
-
- for (i = 0; i < NUM_MED_LISTS; i++) {
- msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, MED_LIST_SIZE, 0);
- if (IS_ERR(msg)) {
- err = PTR_ERR(msg);
- goto ex_err;
- }
- msg->cache = &cmd->cache.med;
- list_add_tail(&msg->list, &cmd->cache.med.head);
- }
-
- return 0;
-
-ex_err:
- destroy_msg_cache(dev);
- return err;
}
static int alloc_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd)
@@ -1756,11 +1764,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
cmd->mode = CMD_MODE_POLLING;
- err = create_msg_cache(dev);
- if (err) {
- dev_err(&dev->pdev->dev, "failed to create command cache\n");
- goto err_free_page;
- }
+ create_msg_cache(dev);
set_wqname(dev);
cmd->wq = create_singlethread_workqueue(cmd->wq_name);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 460363b..ac09767 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -85,6 +85,9 @@
#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD (128)
#define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ (64 * 1024)
+#define MLX5E_DEFAULT_LRO_TIMEOUT 32
+#define MLX5E_LRO_TIMEOUT_ARR_SIZE 4
+
#define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC 0x10
#define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE 0x3
#define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS 0x20
@@ -221,6 +224,7 @@ struct mlx5e_params {
struct ieee_ets ets;
#endif
bool rx_am_enabled;
+ u32 lro_timeout;
};
struct mlx5e_tstamp {
@@ -520,7 +524,7 @@ struct mlx5e_vxlan_db {
struct mlx5e_l2_rule {
u8 addr[ETH_ALEN + 2];
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
};
struct mlx5e_flow_table {
@@ -541,10 +545,10 @@ struct mlx5e_tc_table {
struct mlx5e_vlan_table {
struct mlx5e_flow_table ft;
unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
- struct mlx5_flow_rule *active_vlans_rule[VLAN_N_VID];
- struct mlx5_flow_rule *untagged_rule;
- struct mlx5_flow_rule *any_vlan_rule;
- bool filter_disabled;
+ struct mlx5_flow_handle *active_vlans_rule[VLAN_N_VID];
+ struct mlx5_flow_handle *untagged_rule;
+ struct mlx5_flow_handle *any_vlan_rule;
+ bool filter_disabled;
};
struct mlx5e_l2_table {
@@ -562,14 +566,14 @@ struct mlx5e_l2_table {
/* L3/L4 traffic type classifier */
struct mlx5e_ttc_table {
struct mlx5e_flow_table ft;
- struct mlx5_flow_rule *rules[MLX5E_NUM_TT];
+ struct mlx5_flow_handle *rules[MLX5E_NUM_TT];
};
#define ARFS_HASH_SHIFT BITS_PER_BYTE
#define ARFS_HASH_SIZE BIT(BITS_PER_BYTE)
struct arfs_table {
struct mlx5e_flow_table ft;
- struct mlx5_flow_rule *default_rule;
+ struct mlx5_flow_handle *default_rule;
struct hlist_head rules_hash[ARFS_HASH_SIZE];
};
@@ -888,5 +892,10 @@ int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev);
void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev);
struct rtnl_link_stats64 *
mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
+u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout);
+void mlx5e_add_vxlan_port(struct net_device *netdev,
+ struct udp_tunnel_info *ti);
+void mlx5e_del_vxlan_port(struct net_device *netdev,
+ struct udp_tunnel_info *ti);
#endif /* __MLX5_EN_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index a8cb387..68419a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -56,7 +56,7 @@ struct arfs_tuple {
struct arfs_rule {
struct mlx5e_priv *priv;
struct work_struct arfs_work;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
struct hlist_node hlist;
int rxq;
/* Flow ID passed to ndo_rx_flow_steer */
@@ -104,7 +104,7 @@ static int arfs_disable(struct mlx5e_priv *priv)
tt = arfs_get_tt(i);
/* Modify ttc rules destination to bypass the aRFS tables*/
err = mlx5_modify_rule_destination(priv->fs.ttc.rules[tt],
- &dest);
+ &dest, NULL);
if (err) {
netdev_err(priv->netdev,
"%s: modify ttc destination failed\n",
@@ -137,7 +137,7 @@ int mlx5e_arfs_enable(struct mlx5e_priv *priv)
tt = arfs_get_tt(i);
/* Modify ttc rules destination to point on the aRFS FTs */
err = mlx5_modify_rule_destination(priv->fs.ttc.rules[tt],
- &dest);
+ &dest, NULL);
if (err) {
netdev_err(priv->netdev,
"%s: modify ttc destination failed err=%d\n",
@@ -151,7 +151,7 @@ int mlx5e_arfs_enable(struct mlx5e_priv *priv)
static void arfs_destroy_table(struct arfs_table *arfs_t)
{
- mlx5_del_flow_rule(arfs_t->default_rule);
+ mlx5_del_flow_rules(arfs_t->default_rule);
mlx5e_destroy_flow_table(&arfs_t->ft);
}
@@ -174,6 +174,11 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv,
enum arfs_type type)
{
struct arfs_table *arfs_t = &priv->fs.arfs.arfs_tables[type];
+ struct mlx5_flow_act flow_act = {
+ .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+ .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
+ .encap_id = 0,
+ };
struct mlx5_flow_destination dest;
struct mlx5e_tir *tir = priv->indir_tir;
struct mlx5_flow_spec *spec;
@@ -205,10 +210,9 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv,
goto out;
}
- arfs_t->default_rule = mlx5_add_flow_rule(arfs_t->ft.t, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- MLX5_FS_DEFAULT_FLOW_TAG,
- &dest);
+ arfs_t->default_rule = mlx5_add_flow_rules(arfs_t->ft.t, spec,
+ &flow_act,
+ &dest, 1);
if (IS_ERR(arfs_t->default_rule)) {
err = PTR_ERR(arfs_t->default_rule);
arfs_t->default_rule = NULL;
@@ -324,7 +328,7 @@ static int arfs_create_table(struct mlx5e_priv *priv,
int err;
ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO,
- MLX5E_ARFS_TABLE_SIZE, MLX5E_ARFS_FT_LEVEL);
+ MLX5E_ARFS_TABLE_SIZE, MLX5E_ARFS_FT_LEVEL, 0);
if (IS_ERR(ft->t)) {
err = PTR_ERR(ft->t);
ft->t = NULL;
@@ -396,7 +400,7 @@ static void arfs_may_expire_flow(struct mlx5e_priv *priv)
spin_unlock_bh(&priv->fs.arfs.arfs_lock);
hlist_for_each_entry_safe(arfs_rule, htmp, &del_list, hlist) {
if (arfs_rule->rule)
- mlx5_del_flow_rule(arfs_rule->rule);
+ mlx5_del_flow_rules(arfs_rule->rule);
hlist_del(&arfs_rule->hlist);
kfree(arfs_rule);
}
@@ -420,7 +424,7 @@ static void arfs_del_rules(struct mlx5e_priv *priv)
hlist_for_each_entry_safe(rule, htmp, &del_list, hlist) {
cancel_work_sync(&rule->arfs_work);
if (rule->rule)
- mlx5_del_flow_rule(rule->rule);
+ mlx5_del_flow_rules(rule->rule);
hlist_del(&rule->hlist);
kfree(rule);
}
@@ -462,12 +466,17 @@ static struct arfs_table *arfs_get_table(struct mlx5e_arfs_tables *arfs,
return NULL;
}
-static struct mlx5_flow_rule *arfs_add_rule(struct mlx5e_priv *priv,
- struct arfs_rule *arfs_rule)
+static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv,
+ struct arfs_rule *arfs_rule)
{
+ struct mlx5_flow_act flow_act = {
+ .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+ .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
+ .encap_id = 0,
+ };
struct mlx5e_arfs_tables *arfs = &priv->fs.arfs;
struct arfs_tuple *tuple = &arfs_rule->tuple;
- struct mlx5_flow_rule *rule = NULL;
+ struct mlx5_flow_handle *rule = NULL;
struct mlx5_flow_destination dest;
struct arfs_table *arfs_table;
struct mlx5_flow_spec *spec;
@@ -544,9 +553,7 @@ static struct mlx5_flow_rule *arfs_add_rule(struct mlx5e_priv *priv,
}
dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
dest.tir_num = priv->direct_tir[arfs_rule->rxq].tirn;
- rule = mlx5_add_flow_rule(ft, spec, MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- MLX5_FS_DEFAULT_FLOW_TAG,
- &dest);
+ rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
if (IS_ERR(rule)) {
err = PTR_ERR(rule);
netdev_err(priv->netdev, "%s: add rule(filter id=%d, rq idx=%d) failed, err=%d\n",
@@ -559,14 +566,14 @@ static struct mlx5_flow_rule *arfs_add_rule(struct mlx5e_priv *priv,
}
static void arfs_modify_rule_rq(struct mlx5e_priv *priv,
- struct mlx5_flow_rule *rule, u16 rxq)
+ struct mlx5_flow_handle *rule, u16 rxq)
{
struct mlx5_flow_destination dst;
int err = 0;
dst.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
dst.tir_num = priv->direct_tir[rxq].tirn;
- err = mlx5_modify_rule_destination(rule, &dst);
+ err = mlx5_modify_rule_destination(rule, &dst, NULL);
if (err)
netdev_warn(priv->netdev,
"Failed to modfiy aRFS rule destination to rq=%d\n", rxq);
@@ -578,7 +585,7 @@ static void arfs_handle_work(struct work_struct *work)
struct arfs_rule,
arfs_work);
struct mlx5e_priv *priv = arfs_rule->priv;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
mutex_lock(&priv->state_lock);
if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 27ff401..9ea7b37 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -171,9 +171,13 @@ static int mlx5e_get_sset_count(struct net_device *dev, int sset)
return NUM_SW_COUNTERS +
MLX5E_NUM_Q_CNTRS(priv) +
NUM_VPORT_COUNTERS + NUM_PPORT_COUNTERS +
+ NUM_PCIE_COUNTERS +
MLX5E_NUM_RQ_STATS(priv) +
MLX5E_NUM_SQ_STATS(priv) +
- MLX5E_NUM_PFC_COUNTERS(priv);
+ MLX5E_NUM_PFC_COUNTERS(priv) +
+ ARRAY_SIZE(mlx5e_pme_status_desc) +
+ ARRAY_SIZE(mlx5e_pme_error_desc);
+
case ETH_SS_PRIV_FLAGS:
return ARRAY_SIZE(mlx5e_priv_flags);
/* fallthrough */
@@ -213,6 +217,14 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data)
strcpy(data + (idx++) * ETH_GSTRING_LEN,
pport_2819_stats_desc[i].format);
+ for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++)
+ strcpy(data + (idx++) * ETH_GSTRING_LEN,
+ pcie_perf_stats_desc[i].format);
+
+ for (i = 0; i < NUM_PCIE_TAS_COUNTERS; i++)
+ strcpy(data + (idx++) * ETH_GSTRING_LEN,
+ pcie_tas_stats_desc[i].format);
+
for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
sprintf(data + (idx++) * ETH_GSTRING_LEN,
@@ -237,6 +249,13 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data)
}
}
+ /* port module event counters */
+ for (i = 0; i < ARRAY_SIZE(mlx5e_pme_status_desc); i++)
+ strcpy(data + (idx++) * ETH_GSTRING_LEN, mlx5e_pme_status_desc[i].format);
+
+ for (i = 0; i < ARRAY_SIZE(mlx5e_pme_error_desc); i++)
+ strcpy(data + (idx++) * ETH_GSTRING_LEN, mlx5e_pme_error_desc[i].format);
+
if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
return;
@@ -279,6 +298,7 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
struct mlx5e_priv *priv = netdev_priv(dev);
+ struct mlx5_priv *mlx5_priv;
int i, j, tc, prio, idx = 0;
unsigned long pfc_combined;
@@ -314,6 +334,14 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.RFC_2819_counters,
pport_2819_stats_desc, i);
+ for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++)
+ data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_perf_counters,
+ pcie_perf_stats_desc, i);
+
+ for (i = 0; i < NUM_PCIE_TAS_COUNTERS; i++)
+ data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_tas_counters,
+ pcie_tas_stats_desc, i);
+
for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[prio],
@@ -335,6 +363,16 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
}
}
+ /* port module event counters */
+ mlx5_priv = &priv->mdev->priv;
+ for (i = 0; i < ARRAY_SIZE(mlx5e_pme_status_desc); i++)
+ data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.status_counters,
+ mlx5e_pme_status_desc, i);
+
+ for (i = 0; i < ARRAY_SIZE(mlx5e_pme_error_desc); i++)
+ data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.error_counters,
+ mlx5e_pme_error_desc, i);
+
if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
return;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 36fbc6b..1fe80de 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -158,9 +158,14 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv,
enum mlx5e_vlan_rule_type rule_type,
u16 vid, struct mlx5_flow_spec *spec)
{
+ struct mlx5_flow_act flow_act = {
+ .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+ .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
+ .encap_id = 0,
+ };
struct mlx5_flow_table *ft = priv->fs.vlan.ft.t;
struct mlx5_flow_destination dest;
- struct mlx5_flow_rule **rule_p;
+ struct mlx5_flow_handle **rule_p;
int err = 0;
dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
@@ -187,10 +192,7 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv,
break;
}
- *rule_p = mlx5_add_flow_rule(ft, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- MLX5_FS_DEFAULT_FLOW_TAG,
- &dest);
+ *rule_p = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
if (IS_ERR(*rule_p)) {
err = PTR_ERR(*rule_p);
@@ -229,20 +231,20 @@ static void mlx5e_del_vlan_rule(struct mlx5e_priv *priv,
switch (rule_type) {
case MLX5E_VLAN_RULE_TYPE_UNTAGGED:
if (priv->fs.vlan.untagged_rule) {
- mlx5_del_flow_rule(priv->fs.vlan.untagged_rule);
+ mlx5_del_flow_rules(priv->fs.vlan.untagged_rule);
priv->fs.vlan.untagged_rule = NULL;
}
break;
case MLX5E_VLAN_RULE_TYPE_ANY_VID:
if (priv->fs.vlan.any_vlan_rule) {
- mlx5_del_flow_rule(priv->fs.vlan.any_vlan_rule);
+ mlx5_del_flow_rules(priv->fs.vlan.any_vlan_rule);
priv->fs.vlan.any_vlan_rule = NULL;
}
break;
case MLX5E_VLAN_RULE_TYPE_MATCH_VID:
mlx5e_vport_context_update_vlans(priv);
if (priv->fs.vlan.active_vlans_rule[vid]) {
- mlx5_del_flow_rule(priv->fs.vlan.active_vlans_rule[vid]);
+ mlx5_del_flow_rules(priv->fs.vlan.active_vlans_rule[vid]);
priv->fs.vlan.active_vlans_rule[vid] = NULL;
}
mlx5e_vport_context_update_vlans(priv);
@@ -560,7 +562,7 @@ static void mlx5e_cleanup_ttc_rules(struct mlx5e_ttc_table *ttc)
for (i = 0; i < MLX5E_NUM_TT; i++) {
if (!IS_ERR_OR_NULL(ttc->rules[i])) {
- mlx5_del_flow_rule(ttc->rules[i]);
+ mlx5_del_flow_rules(ttc->rules[i]);
ttc->rules[i] = NULL;
}
}
@@ -616,13 +618,19 @@ static struct {
},
};
-static struct mlx5_flow_rule *mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
- struct mlx5_flow_table *ft,
- struct mlx5_flow_destination *dest,
- u16 etype,
- u8 proto)
+static struct mlx5_flow_handle *
+mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
+ struct mlx5_flow_table *ft,
+ struct mlx5_flow_destination *dest,
+ u16 etype,
+ u8 proto)
{
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_act flow_act = {
+ .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+ .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
+ .encap_id = 0,
+ };
+ struct mlx5_flow_handle *rule;
struct mlx5_flow_spec *spec;
int err = 0;
@@ -643,10 +651,7 @@ static struct mlx5_flow_rule *mlx5e_generate_ttc_rule(struct mlx5e_priv *priv,
MLX5_SET(fte_match_param, spec->match_value, outer_headers.ethertype, etype);
}
- rule = mlx5_add_flow_rule(ft, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- MLX5_FS_DEFAULT_FLOW_TAG,
- dest);
+ rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1);
if (IS_ERR(rule)) {
err = PTR_ERR(rule);
netdev_err(priv->netdev, "%s: add rule failed\n", __func__);
@@ -660,7 +665,7 @@ static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv)
{
struct mlx5_flow_destination dest;
struct mlx5e_ttc_table *ttc;
- struct mlx5_flow_rule **rules;
+ struct mlx5_flow_handle **rules;
struct mlx5_flow_table *ft;
int tt;
int err;
@@ -776,7 +781,7 @@ static int mlx5e_create_ttc_table(struct mlx5e_priv *priv)
int err;
ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO,
- MLX5E_TTC_TABLE_SIZE, MLX5E_TTC_FT_LEVEL);
+ MLX5E_TTC_TABLE_SIZE, MLX5E_TTC_FT_LEVEL, 0);
if (IS_ERR(ft->t)) {
err = PTR_ERR(ft->t);
ft->t = NULL;
@@ -801,7 +806,7 @@ static void mlx5e_del_l2_flow_rule(struct mlx5e_priv *priv,
struct mlx5e_l2_rule *ai)
{
if (!IS_ERR_OR_NULL(ai->rule)) {
- mlx5_del_flow_rule(ai->rule);
+ mlx5_del_flow_rules(ai->rule);
ai->rule = NULL;
}
}
@@ -809,6 +814,11 @@ static void mlx5e_del_l2_flow_rule(struct mlx5e_priv *priv,
static int mlx5e_add_l2_flow_rule(struct mlx5e_priv *priv,
struct mlx5e_l2_rule *ai, int type)
{
+ struct mlx5_flow_act flow_act = {
+ .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+ .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG,
+ .encap_id = 0,
+ };
struct mlx5_flow_table *ft = priv->fs.l2.ft.t;
struct mlx5_flow_destination dest;
struct mlx5_flow_spec *spec;
@@ -847,9 +857,7 @@ static int mlx5e_add_l2_flow_rule(struct mlx5e_priv *priv,
break;
}
- ai->rule = mlx5_add_flow_rule(ft, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- MLX5_FS_DEFAULT_FLOW_TAG, &dest);
+ ai->rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
if (IS_ERR(ai->rule)) {
netdev_err(priv->netdev, "%s: add l2 rule(mac:%pM) failed\n",
__func__, mv_dmac);
@@ -947,7 +955,7 @@ static int mlx5e_create_l2_table(struct mlx5e_priv *priv)
ft->num_groups = 0;
ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO,
- MLX5E_L2_TABLE_SIZE, MLX5E_L2_FT_LEVEL);
+ MLX5E_L2_TABLE_SIZE, MLX5E_L2_FT_LEVEL, 0);
if (IS_ERR(ft->t)) {
err = PTR_ERR(ft->t);
@@ -1037,7 +1045,7 @@ static int mlx5e_create_vlan_table(struct mlx5e_priv *priv)
ft->num_groups = 0;
ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO,
- MLX5E_VLAN_TABLE_SIZE, MLX5E_VLAN_FT_LEVEL);
+ MLX5E_VLAN_TABLE_SIZE, MLX5E_VLAN_FT_LEVEL, 0);
if (IS_ERR(ft->t)) {
err = PTR_ERR(ft->t);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index d17c242..3691451 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -36,7 +36,7 @@
struct mlx5e_ethtool_rule {
struct list_head list;
struct ethtool_rx_flow_spec flow_spec;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
struct mlx5e_ethtool_table *eth_ft;
};
@@ -99,7 +99,7 @@ static struct mlx5e_ethtool_table *get_flow_table(struct mlx5e_priv *priv,
MLX5E_ETHTOOL_NUM_ENTRIES);
ft = mlx5_create_auto_grouped_flow_table(ns, prio,
table_size,
- MLX5E_ETHTOOL_NUM_GROUPS, 0);
+ MLX5E_ETHTOOL_NUM_GROUPS, 0, 0);
if (IS_ERR(ft))
return (void *)ft;
@@ -284,15 +284,16 @@ static bool outer_header_zero(u32 *match_criteria)
size - 1);
}
-static struct mlx5_flow_rule *add_ethtool_flow_rule(struct mlx5e_priv *priv,
- struct mlx5_flow_table *ft,
- struct ethtool_rx_flow_spec *fs)
+static struct mlx5_flow_handle *
+add_ethtool_flow_rule(struct mlx5e_priv *priv,
+ struct mlx5_flow_table *ft,
+ struct ethtool_rx_flow_spec *fs)
{
struct mlx5_flow_destination *dst = NULL;
+ struct mlx5_flow_act flow_act = {0};
struct mlx5_flow_spec *spec;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
int err = 0;
- u32 action;
spec = mlx5_vzalloc(sizeof(*spec));
if (!spec)
@@ -303,7 +304,7 @@ static struct mlx5_flow_rule *add_ethtool_flow_rule(struct mlx5e_priv *priv,
goto free;
if (fs->ring_cookie == RX_CLS_FLOW_DISC) {
- action = MLX5_FLOW_CONTEXT_ACTION_DROP;
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
} else {
dst = kzalloc(sizeof(*dst), GFP_KERNEL);
if (!dst) {
@@ -313,12 +314,12 @@ static struct mlx5_flow_rule *add_ethtool_flow_rule(struct mlx5e_priv *priv,
dst->type = MLX5_FLOW_DESTINATION_TYPE_TIR;
dst->tir_num = priv->direct_tir[fs->ring_cookie].tirn;
- action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
}
spec->match_criteria_enable = (!outer_header_zero(spec->match_criteria));
- rule = mlx5_add_flow_rule(ft, spec, action,
- MLX5_FS_DEFAULT_FLOW_TAG, dst);
+ flow_act.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
+ rule = mlx5_add_flow_rules(ft, spec, &flow_act, dst, 1);
if (IS_ERR(rule)) {
err = PTR_ERR(rule);
netdev_err(priv->netdev, "%s: failed to add ethtool steering rule: %d\n",
@@ -335,7 +336,7 @@ static void del_ethtool_rule(struct mlx5e_priv *priv,
struct mlx5e_ethtool_rule *eth_rule)
{
if (eth_rule->rule)
- mlx5_del_flow_rule(eth_rule->rule);
+ mlx5_del_flow_rules(eth_rule->rule);
list_del(ð_rule->list);
priv->fs.ethtool.tot_num_rules--;
put_flow_table(eth_rule->eth_ft);
@@ -475,7 +476,7 @@ int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
{
struct mlx5e_ethtool_table *eth_ft;
struct mlx5e_ethtool_rule *eth_rule;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
int num_tuples;
int err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 03183eb..bd0732d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -290,12 +290,36 @@ static void mlx5e_update_q_counter(struct mlx5e_priv *priv)
&qcnt->rx_out_of_buffer);
}
+static void mlx5e_update_pcie_counters(struct mlx5e_priv *priv)
+{
+ struct mlx5e_pcie_stats *pcie_stats = &priv->stats.pcie;
+ struct mlx5_core_dev *mdev = priv->mdev;
+ int sz = MLX5_ST_SZ_BYTES(mpcnt_reg);
+ void *out;
+ u32 *in;
+
+ in = mlx5_vzalloc(sz);
+ if (!in)
+ return;
+
+ out = pcie_stats->pcie_perf_counters;
+ MLX5_SET(mpcnt_reg, in, grp, MLX5_PCIE_PERFORMANCE_COUNTERS_GROUP);
+ mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_MPCNT, 0, 0);
+
+ out = pcie_stats->pcie_tas_counters;
+ MLX5_SET(mpcnt_reg, in, grp, MLX5_PCIE_TIMERS_AND_STATES_COUNTERS_GROUP);
+ mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_MPCNT, 0, 0);
+
+ kvfree(in);
+}
+
void mlx5e_update_stats(struct mlx5e_priv *priv)
{
mlx5e_update_q_counter(priv);
mlx5e_update_vport_counters(priv);
mlx5e_update_pport_counters(priv);
mlx5e_update_sw_counters(priv);
+ mlx5e_update_pcie_counters(priv);
}
void mlx5e_update_stats_work(struct work_struct *work)
@@ -1445,6 +1469,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
c->netdev = priv->netdev;
c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
c->num_tc = priv->params.num_tc;
+ c->xdp = !!priv->xdp_prog;
if (priv->params.rx_am_enabled)
rx_cq_profile = mlx5e_am_get_def_profile(priv->params.rx_cq_period_mode);
@@ -1468,6 +1493,12 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
if (err)
goto err_close_tx_cqs;
+ /* XDP SQ CQ params are same as normal TXQ sq CQ params */
+ err = c->xdp ? mlx5e_open_cq(c, &cparam->tx_cq, &c->xdp_sq.cq,
+ priv->params.tx_cq_moderation) : 0;
+ if (err)
+ goto err_close_rx_cq;
+
napi_enable(&c->napi);
err = mlx5e_open_sq(c, 0, &cparam->icosq, &c->icosq);
@@ -1488,21 +1519,10 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
}
}
- if (priv->xdp_prog) {
- /* XDP SQ CQ params are same as normal TXQ sq CQ params */
- err = mlx5e_open_cq(c, &cparam->tx_cq, &c->xdp_sq.cq,
- priv->params.tx_cq_moderation);
- if (err)
- goto err_close_sqs;
+ err = c->xdp ? mlx5e_open_sq(c, 0, &cparam->xdp_sq, &c->xdp_sq) : 0;
+ if (err)
+ goto err_close_sqs;
- err = mlx5e_open_sq(c, 0, &cparam->xdp_sq, &c->xdp_sq);
- if (err) {
- mlx5e_close_cq(&c->xdp_sq.cq);
- goto err_close_sqs;
- }
- }
-
- c->xdp = !!priv->xdp_prog;
err = mlx5e_open_rq(c, &cparam->rq, &c->rq);
if (err)
goto err_close_xdp_sq;
@@ -1512,7 +1532,8 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
return 0;
err_close_xdp_sq:
- mlx5e_close_sq(&c->xdp_sq);
+ if (c->xdp)
+ mlx5e_close_sq(&c->xdp_sq);
err_close_sqs:
mlx5e_close_sqs(c);
@@ -1522,6 +1543,10 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
err_disable_napi:
napi_disable(&c->napi);
+ if (c->xdp)
+ mlx5e_close_cq(&c->xdp_sq.cq);
+
+err_close_rx_cq:
mlx5e_close_cq(&c->rq.cq);
err_close_tx_cqs:
@@ -1532,7 +1557,6 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
err_napi_del:
netif_napi_del(&c->napi);
- napi_hash_del(&c->napi);
kfree(c);
return err;
@@ -1553,9 +1577,6 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
mlx5e_close_cq(&c->icosq.cq);
netif_napi_del(&c->napi);
- napi_hash_del(&c->napi);
- synchronize_rcu();
-
kfree(c);
}
@@ -1971,9 +1992,7 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv)
MLX5_SET(tirc, tirc, lro_max_ip_payload_size,
(priv->params.lro_wqe_sz -
ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
- MLX5_SET(tirc, tirc, lro_timeout_period_usecs,
- MLX5_CAP_ETH(priv->mdev,
- lro_timer_supported_periods[2]));
+ MLX5_SET(tirc, tirc, lro_timeout_period_usecs, priv->params.lro_timeout);
}
void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv)
@@ -2927,6 +2946,20 @@ static int mlx5e_set_vf_trust(struct net_device *dev, int vf, bool setting)
return mlx5_eswitch_set_vport_trust(mdev->priv.eswitch, vf + 1, setting);
}
+
+static int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate,
+ int max_tx_rate)
+{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+ struct mlx5_core_dev *mdev = priv->mdev;
+
+ if (min_tx_rate)
+ return -EOPNOTSUPP;
+
+ return mlx5_eswitch_set_vport_rate(mdev->priv.eswitch, vf + 1,
+ max_tx_rate);
+}
+
static int mlx5_vport_link2ifla(u8 esw_link)
{
switch (esw_link) {
@@ -2983,8 +3016,8 @@ static int mlx5e_get_vf_stats(struct net_device *dev,
vf_stats);
}
-static void mlx5e_add_vxlan_port(struct net_device *netdev,
- struct udp_tunnel_info *ti)
+void mlx5e_add_vxlan_port(struct net_device *netdev,
+ struct udp_tunnel_info *ti)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -2997,8 +3030,8 @@ static void mlx5e_add_vxlan_port(struct net_device *netdev,
mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 1);
}
-static void mlx5e_del_vxlan_port(struct net_device *netdev,
- struct udp_tunnel_info *ti)
+void mlx5e_del_vxlan_port(struct net_device *netdev,
+ struct udp_tunnel_info *ti)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -3234,6 +3267,7 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = {
.ndo_set_vf_vlan = mlx5e_set_vf_vlan,
.ndo_set_vf_spoofchk = mlx5e_set_vf_spoofchk,
.ndo_set_vf_trust = mlx5e_set_vf_trust,
+ .ndo_set_vf_rate = mlx5e_set_vf_rate,
.ndo_get_vf_config = mlx5e_get_vf_config,
.ndo_set_vf_link_state = mlx5e_set_vf_link_state,
.ndo_get_vf_stats = mlx5e_get_vf_stats,
@@ -3383,6 +3417,18 @@ static void mlx5e_query_min_inline(struct mlx5_core_dev *mdev,
}
}
+u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout)
+{
+ int i;
+
+ /* The supported periods are organized in ascending order */
+ for (i = 0; i < MLX5E_LRO_TIMEOUT_ARR_SIZE - 1; i++)
+ if (MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]) >= wanted_timeout)
+ break;
+
+ return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]);
+}
+
static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
struct net_device *netdev,
const struct mlx5e_profile *profile,
@@ -3401,6 +3447,9 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev,
priv->profile = profile;
priv->ppriv = ppriv;
+ priv->params.lro_timeout =
+ mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
+
priv->params.log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
/* set CQE compression */
@@ -4023,7 +4072,6 @@ void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv)
const struct mlx5e_profile *profile = priv->profile;
struct net_device *netdev = priv->netdev;
- unregister_netdev(netdev);
destroy_workqueue(priv->wq);
if (profile->cleanup)
profile->cleanup(priv);
@@ -4040,6 +4088,7 @@ static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv)
for (vport = 1; vport < total_vfs; vport++)
mlx5_eswitch_unregister_vport_rep(esw, vport);
+ unregister_netdev(priv->netdev);
mlx5e_detach(mdev, vpriv);
mlx5e_destroy_netdev(mdev, priv);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 3c97da1..a84825d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -256,6 +256,8 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = {
.ndo_get_phys_port_name = mlx5e_rep_get_phys_port_name,
.ndo_setup_tc = mlx5e_rep_ndo_setup_tc,
.ndo_get_stats64 = mlx5e_get_stats,
+ .ndo_udp_tunnel_add = mlx5e_add_vxlan_port,
+ .ndo_udp_tunnel_del = mlx5e_del_vxlan_port,
};
static void mlx5e_build_rep_netdev_priv(struct mlx5_core_dev *mdev,
@@ -308,7 +310,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
netdev->switchdev_ops = &mlx5e_rep_switchdev_ops;
#endif
- netdev->features |= NETIF_F_VLAN_CHALLENGED | NETIF_F_HW_TC;
+ netdev->features |= NETIF_F_VLAN_CHALLENGED | NETIF_F_HW_TC | NETIF_F_NETNS_LOCAL;
netdev->hw_features |= NETIF_F_HW_TC;
eth_hw_addr_random(netdev);
@@ -328,7 +330,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
struct mlx5_eswitch_rep *rep = priv->ppriv;
struct mlx5_core_dev *mdev = priv->mdev;
- struct mlx5_flow_rule *flow_rule;
+ struct mlx5_flow_handle *flow_rule;
int err;
int i;
@@ -360,7 +362,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
return 0;
err_del_flow_rule:
- mlx5_del_flow_rule(rep->vport_rx_rule);
+ mlx5_del_flow_rules(rep->vport_rx_rule);
err_destroy_direct_tirs:
mlx5e_destroy_direct_tirs(priv);
err_destroy_direct_rqts:
@@ -375,7 +377,7 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
int i;
mlx5e_tc_cleanup(priv);
- mlx5_del_flow_rule(rep->vport_rx_rule);
+ mlx5_del_flow_rules(rep->vport_rx_rule);
mlx5e_destroy_direct_tirs(priv);
for (i = 0; i < priv->params.num_channels; i++)
mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
@@ -457,6 +459,7 @@ void mlx5e_vport_rep_unload(struct mlx5_eswitch *esw,
struct mlx5e_priv *priv = rep->priv_data;
struct net_device *netdev = priv->netdev;
+ unregister_netdev(netdev);
mlx5e_detach_netdev(esw->dev, netdev);
mlx5e_destroy_netdev(esw->dev, priv);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 57452fd..5da6a1c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -39,7 +39,7 @@
#define MLX5E_READ_CTR32_CPU(ptr, dsc, i) \
(*(u32 *)((char *)ptr + dsc[i].offset))
#define MLX5E_READ_CTR32_BE(ptr, dsc, i) \
- be64_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset))
+ be32_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset))
#define MLX5E_DECLARE_STAT(type, fld) #fld, offsetof(type, fld)
#define MLX5E_DECLARE_RX_STAT(type, fld) "rx%d_"#fld, offsetof(type, fld)
@@ -276,6 +276,32 @@ static const struct counter_desc pport_per_prio_pfc_stats_desc[] = {
{ "rx_%s_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) },
};
+#define PCIE_PERF_OFF(c) \
+ MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_perf_cntrs_grp_data_layout.c)
+#define PCIE_PERF_GET(pcie_stats, c) \
+ MLX5_GET(mpcnt_reg, pcie_stats->pcie_perf_counters, \
+ counter_set.pcie_perf_cntrs_grp_data_layout.c)
+#define PCIE_TAS_OFF(c) \
+ MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_tas_cntrs_grp_data_layout.c)
+#define PCIE_TAS_GET(pcie_stats, c) \
+ MLX5_GET(mpcnt_reg, pcie_stats->pcie_tas_counters, \
+ counter_set.pcie_tas_cntrs_grp_data_layout.c)
+
+struct mlx5e_pcie_stats {
+ __be64 pcie_perf_counters[MLX5_ST_SZ_QW(mpcnt_reg)];
+ __be64 pcie_tas_counters[MLX5_ST_SZ_QW(mpcnt_reg)];
+};
+
+static const struct counter_desc pcie_perf_stats_desc[] = {
+ { "rx_pci_signal_integrity", PCIE_PERF_OFF(rx_errors) },
+ { "tx_pci_signal_integrity", PCIE_PERF_OFF(tx_errors) },
+};
+
+static const struct counter_desc pcie_tas_stats_desc[] = {
+ { "tx_pci_transport_nonfatal_msg", PCIE_TAS_OFF(non_fatal_err_msg_sent) },
+ { "tx_pci_transport_fatal_msg", PCIE_TAS_OFF(fatal_err_msg_sent) },
+};
+
struct mlx5e_rq_stats {
u64 packets;
u64 bytes;
@@ -360,6 +386,8 @@ static const struct counter_desc sq_stats_desc[] = {
#define NUM_PPORT_802_3_COUNTERS ARRAY_SIZE(pport_802_3_stats_desc)
#define NUM_PPORT_2863_COUNTERS ARRAY_SIZE(pport_2863_stats_desc)
#define NUM_PPORT_2819_COUNTERS ARRAY_SIZE(pport_2819_stats_desc)
+#define NUM_PCIE_PERF_COUNTERS ARRAY_SIZE(pcie_perf_stats_desc)
+#define NUM_PCIE_TAS_COUNTERS ARRAY_SIZE(pcie_tas_stats_desc)
#define NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS \
ARRAY_SIZE(pport_per_prio_traffic_stats_desc)
#define NUM_PPORT_PER_PRIO_PFC_COUNTERS \
@@ -369,6 +397,7 @@ static const struct counter_desc sq_stats_desc[] = {
NUM_PPORT_2819_COUNTERS + \
NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS * \
NUM_PPORT_PRIO)
+#define NUM_PCIE_COUNTERS (NUM_PCIE_PERF_COUNTERS + NUM_PCIE_TAS_COUNTERS)
#define NUM_RQ_STATS ARRAY_SIZE(rq_stats_desc)
#define NUM_SQ_STATS ARRAY_SIZE(sq_stats_desc)
@@ -377,6 +406,24 @@ struct mlx5e_stats {
struct mlx5e_qcounter_stats qcnt;
struct mlx5e_vport_stats vport;
struct mlx5e_pport_stats pport;
+ struct mlx5e_pcie_stats pcie;
+};
+
+static const struct counter_desc mlx5e_pme_status_desc[] = {
+ { "module_plug", 0 },
+ { "module_unplug", 8 },
+};
+
+static const struct counter_desc mlx5e_pme_error_desc[] = {
+ { "module_pwr_budget_exd", 0 }, /* power budget exceed */
+ { "module_long_range", 8 }, /* long range for non MLNX cable */
+ { "module_bus_stuck", 16 }, /* bus stuck (I2C or data shorted) */
+ { "module_no_eeprom", 24 }, /* no eeprom/retry time out */
+ { "module_enforce_part", 32 }, /* enforce part number list */
+ { "module_unknown_id", 40 }, /* unknown identifier */
+ { "module_high_temp", 48 }, /* high temperature */
+ { "module_bad_shorted", 56 }, /* bad or shorted cable/module */
+ { "module_unknown_status", 64 },
};
#endif /* __MLX5_EN_STATS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 135a95b..4b99112 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -40,28 +40,43 @@
#include <net/switchdev.h>
#include <net/tc_act/tc_mirred.h>
#include <net/tc_act/tc_vlan.h>
+#include <net/tc_act/tc_tunnel_key.h>
+#include <net/vxlan.h>
#include "en.h"
#include "en_tc.h"
#include "eswitch.h"
+#include "vxlan.h"
struct mlx5e_tc_flow {
struct rhash_head node;
u64 cookie;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
+ struct list_head encap; /* flows sharing the same encap */
struct mlx5_esw_flow_attr *attr;
};
+enum {
+ MLX5_HEADER_TYPE_VXLAN = 0x0,
+ MLX5_HEADER_TYPE_NVGRE = 0x1,
+};
+
#define MLX5E_TC_TABLE_NUM_ENTRIES 1024
#define MLX5E_TC_TABLE_NUM_GROUPS 4
-static struct mlx5_flow_rule *mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
- struct mlx5_flow_spec *spec,
- u32 action, u32 flow_tag)
+static struct mlx5_flow_handle *
+mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
+ struct mlx5_flow_spec *spec,
+ u32 action, u32 flow_tag)
{
struct mlx5_core_dev *dev = priv->mdev;
struct mlx5_flow_destination dest = { 0 };
+ struct mlx5_flow_act flow_act = {
+ .action = action,
+ .flow_tag = flow_tag,
+ .encap_id = 0,
+ };
struct mlx5_fc *counter = NULL;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
bool table_created = false;
if (action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
@@ -82,7 +97,7 @@ static struct mlx5_flow_rule *mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
MLX5E_TC_PRIO,
MLX5E_TC_TABLE_NUM_ENTRIES,
MLX5E_TC_TABLE_NUM_GROUPS,
- 0);
+ 0, 0);
if (IS_ERR(priv->fs.tc.t)) {
netdev_err(priv->netdev,
"Failed to create tc offload table\n");
@@ -94,9 +109,7 @@ static struct mlx5_flow_rule *mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
}
spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
- rule = mlx5_add_flow_rule(priv->fs.tc.t, spec,
- action, flow_tag,
- &dest);
+ rule = mlx5_add_flow_rules(priv->fs.tc.t, spec, &flow_act, &dest, 1);
if (IS_ERR(rule))
goto err_add_rule;
@@ -114,9 +127,10 @@ static struct mlx5_flow_rule *mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
return rule;
}
-static struct mlx5_flow_rule *mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
- struct mlx5_flow_spec *spec,
- struct mlx5_esw_flow_attr *attr)
+static struct mlx5_flow_handle *
+mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
+ struct mlx5_flow_spec *spec,
+ struct mlx5_esw_flow_attr *attr)
{
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
int err;
@@ -129,7 +143,7 @@ static struct mlx5_flow_rule *mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
}
static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
- struct mlx5_flow_rule *rule,
+ struct mlx5_flow_handle *rule,
struct mlx5_esw_flow_attr *attr)
{
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
@@ -140,7 +154,7 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
if (esw && esw->mode == SRIOV_OFFLOADS)
mlx5_eswitch_del_vlan_action(esw, attr);
- mlx5_del_flow_rule(rule);
+ mlx5_del_flow_rules(rule);
mlx5_fc_destroy(priv->mdev, counter);
@@ -150,6 +164,121 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
}
}
+static void parse_vxlan_attr(struct mlx5_flow_spec *spec,
+ struct tc_cls_flower_offload *f)
+{
+ void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ outer_headers);
+ void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ outer_headers);
+ void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ misc_parameters);
+ void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ misc_parameters);
+
+ MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_UDP);
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+ struct flow_dissector_key_keyid *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_ENC_KEYID,
+ f->key);
+ struct flow_dissector_key_keyid *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_ENC_KEYID,
+ f->mask);
+ MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni,
+ be32_to_cpu(mask->keyid));
+ MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni,
+ be32_to_cpu(key->keyid));
+ }
+}
+
+static int parse_tunnel_attr(struct mlx5e_priv *priv,
+ struct mlx5_flow_spec *spec,
+ struct tc_cls_flower_offload *f)
+{
+ void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ outer_headers);
+ void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ outer_headers);
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
+ struct flow_dissector_key_ports *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_ENC_PORTS,
+ f->key);
+ struct flow_dissector_key_ports *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_ENC_PORTS,
+ f->mask);
+
+ /* Full udp dst port must be given */
+ if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst)))
+ return -EOPNOTSUPP;
+
+ /* udp src port isn't supported */
+ if (memchr_inv(&mask->src, 0, sizeof(mask->src)))
+ return -EOPNOTSUPP;
+
+ if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->dst)) &&
+ MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
+ parse_vxlan_attr(spec, f);
+ else
+ return -EOPNOTSUPP;
+
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c,
+ udp_dport, ntohs(mask->dst));
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v,
+ udp_dport, ntohs(key->dst));
+
+ } else { /* udp dst port must be given */
+ return -EOPNOTSUPP;
+ }
+
+ if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+ struct flow_dissector_key_ipv4_addrs *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
+ f->key);
+ struct flow_dissector_key_ipv4_addrs *mask =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
+ f->mask);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c,
+ src_ipv4_src_ipv6.ipv4_layout.ipv4,
+ ntohl(mask->src));
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v,
+ src_ipv4_src_ipv6.ipv4_layout.ipv4,
+ ntohl(key->src));
+
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c,
+ dst_ipv4_dst_ipv6.ipv4_layout.ipv4,
+ ntohl(mask->dst));
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v,
+ dst_ipv4_dst_ipv6.ipv4_layout.ipv4,
+ ntohl(key->dst));
+ }
+
+ MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IP);
+
+ /* Enforce DMAC when offloading incoming tunneled flows.
+ * Flow counters require a match on the DMAC.
+ */
+ MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, dmac_47_16);
+ MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, dmac_15_0);
+ ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
+ dmac_47_16), priv->netdev->dev_addr);
+
+ /* let software handle IP fragments */
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag, 0);
+
+ return 0;
+}
+
static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec,
struct tc_cls_flower_offload *f)
{
@@ -167,12 +296,44 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec
BIT(FLOW_DISSECTOR_KEY_VLAN) |
BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
- BIT(FLOW_DISSECTOR_KEY_PORTS))) {
+ BIT(FLOW_DISSECTOR_KEY_PORTS) |
+ BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) |
+ BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) |
+ BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) |
+ BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) |
+ BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL))) {
netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n",
f->dissector->used_keys);
return -EOPNOTSUPP;
}
+ if ((dissector_uses_key(f->dissector,
+ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) ||
+ dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID) ||
+ dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) &&
+ dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
+ struct flow_dissector_key_control *key =
+ skb_flow_dissector_target(f->dissector,
+ FLOW_DISSECTOR_KEY_ENC_CONTROL,
+ f->key);
+ switch (key->addr_type) {
+ case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+ if (parse_tunnel_attr(priv, spec, f))
+ return -EOPNOTSUPP;
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ /* In decap flow, header pointers should point to the inner
+ * headers, outer header were already set by parse_tunnel_attr
+ */
+ headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+ inner_headers);
+ headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+ inner_headers);
+ }
+
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
struct flow_dissector_key_control *key =
skb_flow_dissector_target(f->dissector,
@@ -237,12 +398,15 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec
skb_flow_dissector_target(f->dissector,
FLOW_DISSECTOR_KEY_VLAN,
f->mask);
- if (mask->vlan_id) {
+ if (mask->vlan_id || mask->vlan_priority) {
MLX5_SET(fte_match_set_lyr_2_4, headers_c, vlan_tag, 1);
MLX5_SET(fte_match_set_lyr_2_4, headers_v, vlan_tag, 1);
MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, mask->vlan_id);
MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, key->vlan_id);
+
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio, mask->vlan_priority);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio, key->vlan_priority);
}
}
@@ -384,11 +548,243 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
return 0;
}
-static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
- struct mlx5_esw_flow_attr *attr)
+static inline int cmp_encap_info(struct mlx5_encap_info *a,
+ struct mlx5_encap_info *b)
{
+ return memcmp(a, b, sizeof(*a));
+}
+
+static inline int hash_encap_info(struct mlx5_encap_info *info)
+{
+ return jhash(info, sizeof(*info), 0);
+}
+
+static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
+ struct net_device *mirred_dev,
+ struct net_device **out_dev,
+ struct flowi4 *fl4,
+ struct neighbour **out_n,
+ __be32 *saddr,
+ int *out_ttl)
+{
+ struct rtable *rt;
+ struct neighbour *n = NULL;
+ int ttl;
+
+#if IS_ENABLED(CONFIG_INET)
+ rt = ip_route_output_key(dev_net(mirred_dev), fl4);
+ if (IS_ERR(rt)) {
+ pr_warn("%s: no route to %pI4\n", __func__, &fl4->daddr);
+ return -EOPNOTSUPP;
+ }
+#else
+ return -EOPNOTSUPP;
+#endif
+
+ if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev)) {
+ pr_warn("%s: Can't offload the flow, netdevices aren't on the same HW e-switch\n",
+ __func__);
+ ip_rt_put(rt);
+ return -EOPNOTSUPP;
+ }
+
+ ttl = ip4_dst_hoplimit(&rt->dst);
+ n = dst_neigh_lookup(&rt->dst, &fl4->daddr);
+ ip_rt_put(rt);
+ if (!n)
+ return -ENOMEM;
+
+ *out_n = n;
+ *saddr = fl4->saddr;
+ *out_ttl = ttl;
+ *out_dev = rt->dst.dev;
+
+ return 0;
+}
+
+static int gen_vxlan_header_ipv4(struct net_device *out_dev,
+ char buf[],
+ unsigned char h_dest[ETH_ALEN],
+ int ttl,
+ __be32 daddr,
+ __be32 saddr,
+ __be16 udp_dst_port,
+ __be32 vx_vni)
+{
+ int encap_size = VXLAN_HLEN + sizeof(struct iphdr) + ETH_HLEN;
+ struct ethhdr *eth = (struct ethhdr *)buf;
+ struct iphdr *ip = (struct iphdr *)((char *)eth + sizeof(struct ethhdr));
+ struct udphdr *udp = (struct udphdr *)((char *)ip + sizeof(struct iphdr));
+ struct vxlanhdr *vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr));
+
+ memset(buf, 0, encap_size);
+
+ ether_addr_copy(eth->h_dest, h_dest);
+ ether_addr_copy(eth->h_source, out_dev->dev_addr);
+ eth->h_proto = htons(ETH_P_IP);
+
+ ip->daddr = daddr;
+ ip->saddr = saddr;
+
+ ip->ttl = ttl;
+ ip->protocol = IPPROTO_UDP;
+ ip->version = 0x4;
+ ip->ihl = 0x5;
+
+ udp->dest = udp_dst_port;
+ vxh->vx_flags = VXLAN_HF_VNI;
+ vxh->vx_vni = vxlan_vni_field(vx_vni);
+
+ return encap_size;
+}
+
+static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
+ struct net_device *mirred_dev,
+ struct mlx5_encap_entry *e,
+ struct net_device **out_dev)
+{
+ int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
+ struct flowi4 fl4 = {};
+ struct neighbour *n;
+ char *encap_header;
+ int encap_size;
+ __be32 saddr;
+ int ttl;
+ int err;
+
+ encap_header = kzalloc(max_encap_size, GFP_KERNEL);
+ if (!encap_header)
+ return -ENOMEM;
+
+ switch (e->tunnel_type) {
+ case MLX5_HEADER_TYPE_VXLAN:
+ fl4.flowi4_proto = IPPROTO_UDP;
+ fl4.fl4_dport = e->tun_info.tp_dst;
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+ fl4.daddr = e->tun_info.daddr;
+
+ err = mlx5e_route_lookup_ipv4(priv, mirred_dev, out_dev,
+ &fl4, &n, &saddr, &ttl);
+ if (err)
+ goto out;
+
+ e->n = n;
+ e->out_dev = *out_dev;
+
+ if (!(n->nud_state & NUD_VALID)) {
+ err = -ENOTSUPP;
+ goto out;
+ }
+
+ neigh_ha_snapshot(e->h_dest, n, *out_dev);
+
+ switch (e->tunnel_type) {
+ case MLX5_HEADER_TYPE_VXLAN:
+ encap_size = gen_vxlan_header_ipv4(*out_dev, encap_header,
+ e->h_dest, ttl,
+ e->tun_info.daddr,
+ saddr, e->tun_info.tp_dst,
+ e->tun_info.tun_id);
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+
+ err = mlx5_encap_alloc(priv->mdev, e->tunnel_type,
+ encap_size, encap_header, &e->encap_id);
+out:
+ kfree(encap_header);
+ return err;
+}
+
+static int mlx5e_attach_encap(struct mlx5e_priv *priv,
+ struct ip_tunnel_info *tun_info,
+ struct net_device *mirred_dev,
+ struct mlx5_esw_flow_attr *attr)
+{
+ struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+ unsigned short family = ip_tunnel_info_af(tun_info);
+ struct ip_tunnel_key *key = &tun_info->key;
+ struct mlx5_encap_info info;
+ struct mlx5_encap_entry *e;
+ struct net_device *out_dev;
+ uintptr_t hash_key;
+ bool found = false;
+ int tunnel_type;
+ int err;
+
+ /* udp dst port must be given */
+ if (!memchr_inv(&key->tp_dst, 0, sizeof(key->tp_dst)))
+ return -EOPNOTSUPP;
+
+ if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->tp_dst)) &&
+ MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) {
+ info.tp_dst = key->tp_dst;
+ info.tun_id = tunnel_id_to_key32(key->tun_id);
+ tunnel_type = MLX5_HEADER_TYPE_VXLAN;
+ } else {
+ return -EOPNOTSUPP;
+ }
+
+ switch (family) {
+ case AF_INET:
+ info.daddr = key->u.ipv4.dst;
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ hash_key = hash_encap_info(&info);
+
+ hash_for_each_possible_rcu(esw->offloads.encap_tbl, e,
+ encap_hlist, hash_key) {
+ if (!cmp_encap_info(&e->tun_info, &info)) {
+ found = true;
+ break;
+ }
+ }
+
+ if (found) {
+ attr->encap = e;
+ return 0;
+ }
+
+ e = kzalloc(sizeof(*e), GFP_KERNEL);
+ if (!e)
+ return -ENOMEM;
+
+ e->tun_info = info;
+ e->tunnel_type = tunnel_type;
+ INIT_LIST_HEAD(&e->flows);
+
+ err = mlx5e_create_encap_header_ipv4(priv, mirred_dev, e, &out_dev);
+ if (err)
+ goto out_err;
+
+ attr->encap = e;
+ hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key);
+
+ return err;
+
+out_err:
+ kfree(e);
+ return err;
+}
+
+static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
+ struct mlx5e_tc_flow *flow)
+{
+ struct mlx5_esw_flow_attr *attr = flow->attr;
+ struct ip_tunnel_info *info = NULL;
const struct tc_action *a;
LIST_HEAD(actions);
+ bool encap = false;
+ int err;
if (tc_no_actions(exts))
return -EINVAL;
@@ -411,15 +807,37 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
out_dev = __dev_get_by_index(dev_net(priv->netdev), ifindex);
- if (!switchdev_port_same_parent_id(priv->netdev, out_dev)) {
+ if (switchdev_port_same_parent_id(priv->netdev,
+ out_dev)) {
+ attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+ MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ out_priv = netdev_priv(out_dev);
+ attr->out_rep = out_priv->ppriv;
+ } else if (encap) {
+ err = mlx5e_attach_encap(priv, info,
+ out_dev, attr);
+ if (err)
+ return err;
+ list_add(&flow->encap, &attr->encap->flows);
+ attr->action |= MLX5_FLOW_CONTEXT_ACTION_ENCAP |
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+ MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ out_priv = netdev_priv(attr->encap->out_dev);
+ attr->out_rep = out_priv->ppriv;
+ } else {
pr_err("devices %s %s not on same switch HW, can't offload forwarding\n",
priv->netdev->name, out_dev->name);
return -EINVAL;
}
+ continue;
+ }
- attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
- out_priv = netdev_priv(out_dev);
- attr->out_rep = out_priv->ppriv;
+ if (is_tcf_tunnel_set(a)) {
+ info = tcf_tunnel_info(a);
+ if (info)
+ encap = true;
+ else
+ return -EOPNOTSUPP;
continue;
}
@@ -436,6 +854,11 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
continue;
}
+ if (is_tcf_tunnel_release(a)) {
+ attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
+ continue;
+ }
+
return -EINVAL;
}
return 0;
@@ -450,7 +873,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
u32 flow_tag, action;
struct mlx5e_tc_flow *flow;
struct mlx5_flow_spec *spec;
- struct mlx5_flow_rule *old = NULL;
+ struct mlx5_flow_handle *old = NULL;
struct mlx5_esw_flow_attr *old_attr = NULL;
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
@@ -484,7 +907,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
if (fdb_flow) {
flow->attr = (struct mlx5_esw_flow_attr *)(flow + 1);
- err = parse_tc_fdb_actions(priv, f->exts, flow->attr);
+ err = parse_tc_fdb_actions(priv, f->exts, flow);
if (err < 0)
goto err_free;
flow->rule = mlx5e_tc_add_fdb_flow(priv, spec, flow->attr);
@@ -511,7 +934,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
goto out;
err_del_rule:
- mlx5_del_flow_rule(flow->rule);
+ mlx5_del_flow_rules(flow->rule);
err_free:
if (!old)
@@ -521,6 +944,24 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol,
return err;
}
+static void mlx5e_detach_encap(struct mlx5e_priv *priv,
+ struct mlx5e_tc_flow *flow) {
+ struct list_head *next = flow->encap.next;
+
+ list_del(&flow->encap);
+ if (list_empty(next)) {
+ struct mlx5_encap_entry *e;
+
+ e = list_entry(next, struct mlx5_encap_entry, flows);
+ if (e->n) {
+ mlx5_encap_dealloc(priv->mdev, e->encap_id);
+ neigh_release(e->n);
+ }
+ hlist_del_rcu(&e->encap_hlist);
+ kfree(e);
+ }
+}
+
int mlx5e_delete_flower(struct mlx5e_priv *priv,
struct tc_cls_flower_offload *f)
{
@@ -536,6 +977,9 @@ int mlx5e_delete_flower(struct mlx5e_priv *priv,
mlx5e_tc_del_flow(priv, flow->rule, flow->attr);
+ if (flow->attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)
+ mlx5e_detach_encap(priv, flow);
+
kfree(flow);
return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index aaca090..8ffcc88 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -139,6 +139,8 @@ static const char *eqe_type_str(u8 type)
return "MLX5_EVENT_TYPE_PORT_CHANGE";
case MLX5_EVENT_TYPE_GPIO_EVENT:
return "MLX5_EVENT_TYPE_GPIO_EVENT";
+ case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
+ return "MLX5_EVENT_TYPE_PORT_MODULE_EVENT";
case MLX5_EVENT_TYPE_REMOTE_CONFIG:
return "MLX5_EVENT_TYPE_REMOTE_CONFIG";
case MLX5_EVENT_TYPE_DB_BF_CONGESTION:
@@ -285,6 +287,11 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
mlx5_eswitch_vport_event(dev->priv.eswitch, eqe);
break;
#endif
+
+ case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
+ mlx5_port_module_event(dev, eqe);
+ break;
+
default:
mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n",
eqe->type, eq->eqn);
@@ -469,7 +476,7 @@ void mlx5_eq_cleanup(struct mlx5_core_dev *dev)
int mlx5_start_eqs(struct mlx5_core_dev *dev)
{
struct mlx5_eq_table *table = &dev->priv.eq_table;
- u32 async_event_mask = MLX5_ASYNC_EVENT_MASK;
+ u64 async_event_mask = MLX5_ASYNC_EVENT_MASK;
int err;
if (MLX5_CAP_GEN(dev, pg))
@@ -480,6 +487,11 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
mlx5_core_is_pf(dev))
async_event_mask |= (1ull << MLX5_EVENT_TYPE_NIC_VPORT_CHANGE);
+ if (MLX5_CAP_GEN(dev, port_module_event))
+ async_event_mask |= (1ull << MLX5_EVENT_TYPE_PORT_MODULE_EVENT);
+ else
+ mlx5_core_dbg(dev, "port_module_event is not set\n");
+
err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD,
MLX5_NUM_CMD_EQE, 1ull << MLX5_EVENT_TYPE_CMD,
"mlx5_cmd_eq", &dev->priv.uuari.uars[0]);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index abbf2c3..9734ac8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -56,7 +56,7 @@ struct esw_uc_addr {
/* E-Switch MC FDB table hash node */
struct esw_mc_addr { /* SRIOV only */
struct l2addr_node node;
- struct mlx5_flow_rule *uplink_rule; /* Forward to uplink rule */
+ struct mlx5_flow_handle *uplink_rule; /* Forward to uplink rule */
u32 refcnt;
};
@@ -65,7 +65,7 @@ struct vport_addr {
struct l2addr_node node;
u8 action;
u32 vport;
- struct mlx5_flow_rule *flow_rule; /* SRIOV only */
+ struct mlx5_flow_handle *flow_rule; /* SRIOV only */
/* A flag indicating that mac was added due to mc promiscuous vport */
bool mc_promisc;
};
@@ -237,13 +237,14 @@ static void del_l2_table_entry(struct mlx5_core_dev *dev, u32 index)
}
/* E-Switch FDB */
-static struct mlx5_flow_rule *
+static struct mlx5_flow_handle *
__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
u8 mac_c[ETH_ALEN], u8 mac_v[ETH_ALEN])
{
int match_header = (is_zero_ether_addr(mac_c) ? 0 :
MLX5_MATCH_OUTER_HEADERS);
- struct mlx5_flow_rule *flow_rule = NULL;
+ struct mlx5_flow_handle *flow_rule = NULL;
+ struct mlx5_flow_act flow_act = {0};
struct mlx5_flow_destination dest;
struct mlx5_flow_spec *spec;
void *mv_misc = NULL;
@@ -285,10 +286,10 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
"\tFDB add rule dmac_v(%pM) dmac_c(%pM) -> vport(%d)\n",
dmac_v, dmac_c, vport);
spec->match_criteria_enable = match_header;
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
flow_rule =
- mlx5_add_flow_rule(esw->fdb_table.fdb, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- 0, &dest);
+ mlx5_add_flow_rules(esw->fdb_table.fdb, spec,
+ &flow_act, &dest, 1);
if (IS_ERR(flow_rule)) {
esw_warn(esw->dev,
"FDB: Failed to add flow rule: dmac_v(%pM) dmac_c(%pM) -> vport(%d), err(%ld)\n",
@@ -300,7 +301,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
return flow_rule;
}
-static struct mlx5_flow_rule *
+static struct mlx5_flow_handle *
esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport)
{
u8 mac_c[ETH_ALEN];
@@ -309,7 +310,7 @@ esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport)
return __esw_fdb_set_vport_rule(esw, vport, false, mac_c, mac);
}
-static struct mlx5_flow_rule *
+static struct mlx5_flow_handle *
esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport)
{
u8 mac_c[ETH_ALEN];
@@ -322,7 +323,7 @@ esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport)
return __esw_fdb_set_vport_rule(esw, vport, false, mac_c, mac_v);
}
-static struct mlx5_flow_rule *
+static struct mlx5_flow_handle *
esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport)
{
u8 mac_c[ETH_ALEN];
@@ -361,7 +362,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw, int nvports)
memset(flow_group_in, 0, inlen);
table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
- fdb = mlx5_create_flow_table(root_ns, 0, table_size, 0);
+ fdb = mlx5_create_flow_table(root_ns, 0, table_size, 0, 0);
if (IS_ERR(fdb)) {
err = PTR_ERR(fdb);
esw_warn(dev, "Failed to create FDB Table err %d\n", err);
@@ -515,7 +516,7 @@ static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
del_l2_table_entry(esw->dev, esw_uc->table_index);
if (vaddr->flow_rule)
- mlx5_del_flow_rule(vaddr->flow_rule);
+ mlx5_del_flow_rules(vaddr->flow_rule);
vaddr->flow_rule = NULL;
l2addr_hash_del(esw_uc);
@@ -562,7 +563,7 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw,
case MLX5_ACTION_DEL:
if (!iter_vaddr)
continue;
- mlx5_del_flow_rule(iter_vaddr->flow_rule);
+ mlx5_del_flow_rules(iter_vaddr->flow_rule);
l2addr_hash_del(iter_vaddr);
break;
}
@@ -632,7 +633,7 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
esw_mc->uplink_rule);
if (vaddr->flow_rule)
- mlx5_del_flow_rule(vaddr->flow_rule);
+ mlx5_del_flow_rules(vaddr->flow_rule);
vaddr->flow_rule = NULL;
/* If the multicast mac is added as a result of mc promiscuous vport,
@@ -645,7 +646,7 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
update_allmulti_vports(esw, vaddr, esw_mc);
if (esw_mc->uplink_rule)
- mlx5_del_flow_rule(esw_mc->uplink_rule);
+ mlx5_del_flow_rules(esw_mc->uplink_rule);
l2addr_hash_del(esw_mc);
return 0;
@@ -828,14 +829,14 @@ static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num,
UPLINK_VPORT);
allmulti_addr->refcnt++;
} else if (vport->allmulti_rule) {
- mlx5_del_flow_rule(vport->allmulti_rule);
+ mlx5_del_flow_rules(vport->allmulti_rule);
vport->allmulti_rule = NULL;
if (--allmulti_addr->refcnt > 0)
goto promisc;
if (allmulti_addr->uplink_rule)
- mlx5_del_flow_rule(allmulti_addr->uplink_rule);
+ mlx5_del_flow_rules(allmulti_addr->uplink_rule);
allmulti_addr->uplink_rule = NULL;
}
@@ -847,7 +848,7 @@ static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num,
vport->promisc_rule = esw_fdb_set_vport_promisc_rule(esw,
vport_num);
} else if (vport->promisc_rule) {
- mlx5_del_flow_rule(vport->promisc_rule);
+ mlx5_del_flow_rules(vport->promisc_rule);
vport->promisc_rule = NULL;
}
}
@@ -931,8 +932,8 @@ static void esw_vport_change_handler(struct work_struct *work)
mutex_unlock(&esw->state_lock);
}
-static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
- struct mlx5_vport *vport)
+static int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport)
{
int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
struct mlx5_flow_group *vlan_grp = NULL;
@@ -949,9 +950,11 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
int table_size = 2;
int err = 0;
- if (!MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support) ||
- !IS_ERR_OR_NULL(vport->egress.acl))
- return;
+ if (!MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support))
+ return -EOPNOTSUPP;
+
+ if (!IS_ERR_OR_NULL(vport->egress.acl))
+ return 0;
esw_debug(dev, "Create vport[%d] egress ACL log_max_size(%d)\n",
vport->vport, MLX5_CAP_ESW_EGRESS_ACL(dev, log_max_ft_size));
@@ -959,12 +962,12 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS);
if (!root_ns) {
esw_warn(dev, "Failed to get E-Switch egress flow namespace\n");
- return;
+ return -EIO;
}
flow_group_in = mlx5_vzalloc(inlen);
if (!flow_group_in)
- return;
+ return -ENOMEM;
acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
if (IS_ERR(acl)) {
@@ -1009,16 +1012,17 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
mlx5_destroy_flow_group(vlan_grp);
if (err && !IS_ERR_OR_NULL(acl))
mlx5_destroy_flow_table(acl);
+ return err;
}
static void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
if (!IS_ERR_OR_NULL(vport->egress.allowed_vlan))
- mlx5_del_flow_rule(vport->egress.allowed_vlan);
+ mlx5_del_flow_rules(vport->egress.allowed_vlan);
if (!IS_ERR_OR_NULL(vport->egress.drop_rule))
- mlx5_del_flow_rule(vport->egress.drop_rule);
+ mlx5_del_flow_rules(vport->egress.drop_rule);
vport->egress.allowed_vlan = NULL;
vport->egress.drop_rule = NULL;
@@ -1041,8 +1045,8 @@ static void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw,
vport->egress.acl = NULL;
}
-static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
- struct mlx5_vport *vport)
+static int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport)
{
int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
struct mlx5_core_dev *dev = esw->dev;
@@ -1063,9 +1067,11 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
int table_size = 4;
int err = 0;
- if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support) ||
- !IS_ERR_OR_NULL(vport->ingress.acl))
- return;
+ if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support))
+ return -EOPNOTSUPP;
+
+ if (!IS_ERR_OR_NULL(vport->ingress.acl))
+ return 0;
esw_debug(dev, "Create vport[%d] ingress ACL log_max_size(%d)\n",
vport->vport, MLX5_CAP_ESW_INGRESS_ACL(dev, log_max_ft_size));
@@ -1073,12 +1079,12 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS);
if (!root_ns) {
esw_warn(dev, "Failed to get E-Switch ingress flow namespace\n");
- return;
+ return -EIO;
}
flow_group_in = mlx5_vzalloc(inlen);
if (!flow_group_in)
- return;
+ return -ENOMEM;
acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
if (IS_ERR(acl)) {
@@ -1167,16 +1173,17 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
}
kvfree(flow_group_in);
+ return err;
}
static void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
if (!IS_ERR_OR_NULL(vport->ingress.drop_rule))
- mlx5_del_flow_rule(vport->ingress.drop_rule);
+ mlx5_del_flow_rules(vport->ingress.drop_rule);
if (!IS_ERR_OR_NULL(vport->ingress.allow_rule))
- mlx5_del_flow_rule(vport->ingress.allow_rule);
+ mlx5_del_flow_rules(vport->ingress.allow_rule);
vport->ingress.drop_rule = NULL;
vport->ingress.allow_rule = NULL;
@@ -1206,6 +1213,7 @@ static void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw,
static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
+ struct mlx5_flow_act flow_act = {0};
struct mlx5_flow_spec *spec;
int err = 0;
u8 *smac_v;
@@ -1225,7 +1233,13 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
return 0;
}
- esw_vport_enable_ingress_acl(esw, vport);
+ err = esw_vport_enable_ingress_acl(esw, vport);
+ if (err) {
+ mlx5_core_warn(esw->dev,
+ "failed to enable ingress acl (%d) on vport[%d]\n",
+ err, vport->vport);
+ return err;
+ }
esw_debug(esw->dev,
"vport[%d] configure ingress rules, vlan(%d) qos(%d)\n",
@@ -1252,10 +1266,10 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
}
spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
vport->ingress.allow_rule =
- mlx5_add_flow_rule(vport->ingress.acl, spec,
- MLX5_FLOW_CONTEXT_ACTION_ALLOW,
- 0, NULL);
+ mlx5_add_flow_rules(vport->ingress.acl, spec,
+ &flow_act, NULL, 0);
if (IS_ERR(vport->ingress.allow_rule)) {
err = PTR_ERR(vport->ingress.allow_rule);
esw_warn(esw->dev,
@@ -1266,10 +1280,10 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
}
memset(spec, 0, sizeof(*spec));
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
vport->ingress.drop_rule =
- mlx5_add_flow_rule(vport->ingress.acl, spec,
- MLX5_FLOW_CONTEXT_ACTION_DROP,
- 0, NULL);
+ mlx5_add_flow_rules(vport->ingress.acl, spec,
+ &flow_act, NULL, 0);
if (IS_ERR(vport->ingress.drop_rule)) {
err = PTR_ERR(vport->ingress.drop_rule);
esw_warn(esw->dev,
@@ -1289,6 +1303,7 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
static int esw_vport_egress_config(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
+ struct mlx5_flow_act flow_act = {0};
struct mlx5_flow_spec *spec;
int err = 0;
@@ -1299,7 +1314,13 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
return 0;
}
- esw_vport_enable_egress_acl(esw, vport);
+ err = esw_vport_enable_egress_acl(esw, vport);
+ if (err) {
+ mlx5_core_warn(esw->dev,
+ "failed to enable egress acl (%d) on vport[%d]\n",
+ err, vport->vport);
+ return err;
+ }
esw_debug(esw->dev,
"vport[%d] configure egress rules, vlan(%d) qos(%d)\n",
@@ -1320,10 +1341,10 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
MLX5_SET(fte_match_param, spec->match_value, outer_headers.first_vid, vport->info.vlan);
spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
vport->egress.allowed_vlan =
- mlx5_add_flow_rule(vport->egress.acl, spec,
- MLX5_FLOW_CONTEXT_ACTION_ALLOW,
- 0, NULL);
+ mlx5_add_flow_rules(vport->egress.acl, spec,
+ &flow_act, NULL, 0);
if (IS_ERR(vport->egress.allowed_vlan)) {
err = PTR_ERR(vport->egress.allowed_vlan);
esw_warn(esw->dev,
@@ -1335,10 +1356,10 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
/* Drop others rule (star rule) */
memset(spec, 0, sizeof(*spec));
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
vport->egress.drop_rule =
- mlx5_add_flow_rule(vport->egress.acl, spec,
- MLX5_FLOW_CONTEXT_ACTION_DROP,
- 0, NULL);
+ mlx5_add_flow_rules(vport->egress.acl, spec,
+ &flow_act, NULL, 0);
if (IS_ERR(vport->egress.drop_rule)) {
err = PTR_ERR(vport->egress.drop_rule);
esw_warn(esw->dev,
@@ -1351,6 +1372,147 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
return err;
}
+/* Vport QoS management */
+static int esw_create_tsar(struct mlx5_eswitch *esw)
+{
+ u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
+ struct mlx5_core_dev *dev = esw->dev;
+ int err;
+
+ if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
+ return 0;
+
+ if (esw->qos.enabled)
+ return -EEXIST;
+
+ err = mlx5_create_scheduling_element_cmd(dev,
+ SCHEDULING_HIERARCHY_E_SWITCH,
+ &tsar_ctx,
+ &esw->qos.root_tsar_id);
+ if (err) {
+ esw_warn(esw->dev, "E-Switch create TSAR failed (%d)\n", err);
+ return err;
+ }
+
+ esw->qos.enabled = true;
+ return 0;
+}
+
+static void esw_destroy_tsar(struct mlx5_eswitch *esw)
+{
+ int err;
+
+ if (!esw->qos.enabled)
+ return;
+
+ err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+ SCHEDULING_HIERARCHY_E_SWITCH,
+ esw->qos.root_tsar_id);
+ if (err)
+ esw_warn(esw->dev, "E-Switch destroy TSAR failed (%d)\n", err);
+
+ esw->qos.enabled = false;
+}
+
+static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num,
+ u32 initial_max_rate)
+{
+ u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
+ struct mlx5_vport *vport = &esw->vports[vport_num];
+ struct mlx5_core_dev *dev = esw->dev;
+ void *vport_elem;
+ int err = 0;
+
+ if (!esw->qos.enabled || !MLX5_CAP_GEN(dev, qos) ||
+ !MLX5_CAP_QOS(dev, esw_scheduling))
+ return 0;
+
+ if (vport->qos.enabled)
+ return -EEXIST;
+
+ MLX5_SET(scheduling_context, &sched_ctx, element_type,
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
+ vport_elem = MLX5_ADDR_OF(scheduling_context, &sched_ctx,
+ element_attributes);
+ MLX5_SET(vport_element, vport_elem, vport_number, vport_num);
+ MLX5_SET(scheduling_context, &sched_ctx, parent_element_id,
+ esw->qos.root_tsar_id);
+ MLX5_SET(scheduling_context, &sched_ctx, max_average_bw,
+ initial_max_rate);
+
+ err = mlx5_create_scheduling_element_cmd(dev,
+ SCHEDULING_HIERARCHY_E_SWITCH,
+ &sched_ctx,
+ &vport->qos.esw_tsar_ix);
+ if (err) {
+ esw_warn(esw->dev, "E-Switch create TSAR vport element failed (vport=%d,err=%d)\n",
+ vport_num, err);
+ return err;
+ }
+
+ vport->qos.enabled = true;
+ return 0;
+}
+
+static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num)
+{
+ struct mlx5_vport *vport = &esw->vports[vport_num];
+ int err = 0;
+
+ if (!vport->qos.enabled)
+ return;
+
+ err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+ SCHEDULING_HIERARCHY_E_SWITCH,
+ vport->qos.esw_tsar_ix);
+ if (err)
+ esw_warn(esw->dev, "E-Switch destroy TSAR vport element failed (vport=%d,err=%d)\n",
+ vport_num, err);
+
+ vport->qos.enabled = false;
+}
+
+static int esw_vport_qos_config(struct mlx5_eswitch *esw, int vport_num,
+ u32 max_rate)
+{
+ u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
+ struct mlx5_vport *vport = &esw->vports[vport_num];
+ struct mlx5_core_dev *dev = esw->dev;
+ void *vport_elem;
+ u32 bitmask = 0;
+ int err = 0;
+
+ if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
+ return -EOPNOTSUPP;
+
+ if (!vport->qos.enabled)
+ return -EIO;
+
+ MLX5_SET(scheduling_context, &sched_ctx, element_type,
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
+ vport_elem = MLX5_ADDR_OF(scheduling_context, &sched_ctx,
+ element_attributes);
+ MLX5_SET(vport_element, vport_elem, vport_number, vport_num);
+ MLX5_SET(scheduling_context, &sched_ctx, parent_element_id,
+ esw->qos.root_tsar_id);
+ MLX5_SET(scheduling_context, &sched_ctx, max_average_bw,
+ max_rate);
+ bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW;
+
+ err = mlx5_modify_scheduling_element_cmd(dev,
+ SCHEDULING_HIERARCHY_E_SWITCH,
+ &sched_ctx,
+ vport->qos.esw_tsar_ix,
+ bitmask);
+ if (err) {
+ esw_warn(esw->dev, "E-Switch modify TSAR vport element failed (vport=%d,err=%d)\n",
+ vport_num, err);
+ return err;
+ }
+
+ return 0;
+}
+
static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN])
{
((u8 *)node_guid)[7] = mac[0];
@@ -1386,6 +1548,7 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw,
esw_vport_egress_config(esw, vport);
}
}
+
static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
int enable_events)
{
@@ -1399,6 +1562,10 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
/* Restore old vport configuration */
esw_apply_vport_conf(esw, vport);
+ /* Attach vport to the eswitch rate limiter */
+ if (esw_vport_enable_qos(esw, vport_num, vport->info.max_rate))
+ esw_warn(esw->dev, "Failed to attach vport %d to eswitch rate limiter", vport_num);
+
/* Sync with current vport context */
vport->enabled_events = enable_events;
vport->enabled = true;
@@ -1437,7 +1604,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
*/
esw_vport_change_handle_locked(vport);
vport->enabled_events = 0;
-
+ esw_vport_disable_qos(esw, vport_num);
if (vport_num && esw->mode == SRIOV_LEGACY) {
mlx5_modify_vport_admin_state(esw->dev,
MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
@@ -1483,6 +1650,10 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
if (err)
goto abort;
+ err = esw_create_tsar(esw);
+ if (err)
+ esw_warn(esw->dev, "Failed to create eswitch TSAR");
+
enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : UC_ADDR_CHANGE;
for (i = 0; i <= nvfs; i++)
esw_enable_vport(esw, i, enabled_events);
@@ -1517,7 +1688,9 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
esw_disable_vport(esw, i);
if (mc_promisc && mc_promisc->uplink_rule)
- mlx5_del_flow_rule(mc_promisc->uplink_rule);
+ mlx5_del_flow_rules(mc_promisc->uplink_rule);
+
+ esw_destroy_tsar(esw);
if (esw->mode == SRIOV_LEGACY)
esw_destroy_legacy_fdb_table(esw);
@@ -1609,6 +1782,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
goto abort;
}
+ hash_init(esw->offloads.encap_tbl);
mutex_init(&esw->state_lock);
for (vport_num = 0; vport_num < total_vports; vport_num++) {
@@ -1777,6 +1951,7 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
ivi->qos = evport->info.qos;
ivi->spoofchk = evport->info.spoofchk;
ivi->trusted = evport->info.trusted;
+ ivi->max_tx_rate = evport->info.max_rate;
mutex_unlock(&esw->state_lock);
return 0;
@@ -1870,6 +2045,27 @@ int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
return 0;
}
+int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw,
+ int vport, u32 max_rate)
+{
+ struct mlx5_vport *evport;
+ int err = 0;
+
+ if (!ESW_ALLOWED(esw))
+ return -EPERM;
+ if (!LEGAL_VPORT(esw, vport))
+ return -EINVAL;
+
+ mutex_lock(&esw->state_lock);
+ evport = &esw->vports[vport];
+ err = esw_vport_qos_config(esw, vport, max_rate);
+ if (!err)
+ evport->info.max_rate = max_rate;
+
+ mutex_unlock(&esw->state_lock);
+ return err;
+}
+
int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
int vport,
struct ifla_vf_stats *vf_stats)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 2e2938e..40482e8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -97,16 +97,16 @@ struct vport_ingress {
struct mlx5_flow_group *allow_spoofchk_only_grp;
struct mlx5_flow_group *allow_untagged_only_grp;
struct mlx5_flow_group *drop_grp;
- struct mlx5_flow_rule *allow_rule;
- struct mlx5_flow_rule *drop_rule;
+ struct mlx5_flow_handle *allow_rule;
+ struct mlx5_flow_handle *drop_rule;
};
struct vport_egress {
struct mlx5_flow_table *acl;
struct mlx5_flow_group *allowed_vlans_grp;
struct mlx5_flow_group *drop_grp;
- struct mlx5_flow_rule *allowed_vlan;
- struct mlx5_flow_rule *drop_rule;
+ struct mlx5_flow_handle *allowed_vlan;
+ struct mlx5_flow_handle *drop_rule;
};
struct mlx5_vport_info {
@@ -115,6 +115,7 @@ struct mlx5_vport_info {
u8 qos;
u64 node_guid;
int link_state;
+ u32 max_rate;
bool spoofchk;
bool trusted;
};
@@ -124,8 +125,8 @@ struct mlx5_vport {
int vport;
struct hlist_head uc_list[MLX5_L2_ADDR_HASH_SIZE];
struct hlist_head mc_list[MLX5_L2_ADDR_HASH_SIZE];
- struct mlx5_flow_rule *promisc_rule;
- struct mlx5_flow_rule *allmulti_rule;
+ struct mlx5_flow_handle *promisc_rule;
+ struct mlx5_flow_handle *allmulti_rule;
struct work_struct vport_change_handler;
struct vport_ingress ingress;
@@ -133,6 +134,11 @@ struct mlx5_vport {
struct mlx5_vport_info info;
+ struct {
+ bool enabled;
+ u32 esw_tsar_ix;
+ } qos;
+
bool enabled;
u16 enabled_events;
};
@@ -156,7 +162,7 @@ struct mlx5_eswitch_fdb {
struct mlx5_flow_table *fdb;
struct mlx5_flow_group *send_to_vport_grp;
struct mlx5_flow_group *miss_grp;
- struct mlx5_flow_rule *miss_rule;
+ struct mlx5_flow_handle *miss_rule;
int vlan_push_pop_refcount;
} offloads;
};
@@ -169,7 +175,7 @@ enum {
};
struct mlx5_esw_sq {
- struct mlx5_flow_rule *send_to_vport_rule;
+ struct mlx5_flow_handle *send_to_vport_rule;
struct list_head list;
};
@@ -182,7 +188,7 @@ struct mlx5_eswitch_rep {
u8 hw_id[ETH_ALEN];
void *priv_data;
- struct mlx5_flow_rule *vport_rx_rule;
+ struct mlx5_flow_handle *vport_rx_rule;
struct list_head vport_sqs_list;
u16 vlan;
u32 vlan_refcount;
@@ -193,6 +199,7 @@ struct mlx5_esw_offload {
struct mlx5_flow_table *ft_offloads;
struct mlx5_flow_group *vport_rx_group;
struct mlx5_eswitch_rep *vport_reps;
+ DECLARE_HASHTABLE(encap_tbl, 8);
};
struct mlx5_eswitch {
@@ -209,6 +216,12 @@ struct mlx5_eswitch {
*/
struct mutex state_lock;
struct esw_mc_addr *mc_promisc;
+
+ struct {
+ bool enabled;
+ u32 root_tsar_id;
+ } qos;
+
struct mlx5_esw_offload offloads;
int mode;
};
@@ -234,6 +247,8 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
int vport, bool spoofchk);
int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
int vport_num, bool setting);
+int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw,
+ int vport, u32 max_rate);
int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
int vport, struct ifla_vf_info *ivi);
int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
@@ -243,11 +258,11 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
struct mlx5_flow_spec;
struct mlx5_esw_flow_attr;
-struct mlx5_flow_rule *
+struct mlx5_flow_handle *
mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_spec *spec,
struct mlx5_esw_flow_attr *attr);
-struct mlx5_flow_rule *
+struct mlx5_flow_handle *
mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn);
enum {
@@ -258,6 +273,24 @@ enum {
#define MLX5_FLOW_CONTEXT_ACTION_VLAN_POP 0x40
#define MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH 0x80
+struct mlx5_encap_info {
+ __be32 daddr;
+ __be32 tun_id;
+ __be16 tp_dst;
+};
+
+struct mlx5_encap_entry {
+ struct hlist_node encap_hlist;
+ struct list_head flows;
+ u32 encap_id;
+ struct neighbour *n;
+ struct mlx5_encap_info tun_info;
+ unsigned char h_dest[ETH_ALEN]; /* destination eth addr */
+
+ struct net_device *out_dev;
+ int tunnel_type;
+};
+
struct mlx5_esw_flow_attr {
struct mlx5_eswitch_rep *in_rep;
struct mlx5_eswitch_rep *out_rep;
@@ -265,6 +298,7 @@ struct mlx5_esw_flow_attr {
int action;
u16 vlan;
bool vlan_handled;
+ struct mlx5_encap_entry *encap;
};
int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index c55ad8d..731f286 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -43,32 +43,36 @@ enum {
FDB_SLOW_PATH
};
-struct mlx5_flow_rule *
+struct mlx5_flow_handle *
mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_spec *spec,
struct mlx5_esw_flow_attr *attr)
{
- struct mlx5_flow_destination dest = { 0 };
+ struct mlx5_flow_destination dest[2] = {};
+ struct mlx5_flow_act flow_act = {0};
struct mlx5_fc *counter = NULL;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
void *misc;
- int action;
+ int i = 0;
if (esw->mode != SRIOV_OFFLOADS)
return ERR_PTR(-EOPNOTSUPP);
- action = attr->action;
+ /* per flow vlan pop/push is emulated, don't set that into the firmware */
+ flow_act.action = attr->action & ~(MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH | MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
- if (action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
- dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
- dest.vport_num = attr->out_rep->vport;
- action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
- } else if (action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+ if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
+ dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+ dest[i].vport_num = attr->out_rep->vport;
+ i++;
+ }
+ if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
counter = mlx5_fc_create(esw->dev, true);
if (IS_ERR(counter))
return ERR_CAST(counter);
- dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
- dest.counter = counter;
+ dest[i].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+ dest[i].counter = counter;
+ i++;
}
misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
@@ -79,10 +83,14 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS |
MLX5_MATCH_MISC_PARAMETERS;
+ if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP)
+ spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;
- rule = mlx5_add_flow_rule((struct mlx5_flow_table *)esw->fdb_table.fdb,
- spec, action, 0, &dest);
+ if (attr->encap)
+ flow_act.encap_id = attr->encap->encap_id;
+ rule = mlx5_add_flow_rules((struct mlx5_flow_table *)esw->fdb_table.fdb,
+ spec, &flow_act, dest, i);
if (IS_ERR(rule))
mlx5_fc_destroy(esw->dev, counter);
@@ -269,11 +277,12 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
return err;
}
-static struct mlx5_flow_rule *
+static struct mlx5_flow_handle *
mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn)
{
+ struct mlx5_flow_act flow_act = {0};
struct mlx5_flow_destination dest;
- struct mlx5_flow_rule *flow_rule;
+ struct mlx5_flow_handle *flow_rule;
struct mlx5_flow_spec *spec;
void *misc;
@@ -295,10 +304,10 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn
spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest.vport_num = vport;
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
- flow_rule = mlx5_add_flow_rule(esw->fdb_table.offloads.fdb, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- 0, &dest);
+ flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.fdb, spec,
+ &flow_act, &dest, 1);
if (IS_ERR(flow_rule))
esw_warn(esw->dev, "FDB: Failed to add send to vport rule err %ld\n", PTR_ERR(flow_rule));
out:
@@ -315,7 +324,7 @@ void mlx5_eswitch_sqs2vport_stop(struct mlx5_eswitch *esw,
return;
list_for_each_entry_safe(esw_sq, tmp, &rep->vport_sqs_list, list) {
- mlx5_del_flow_rule(esw_sq->send_to_vport_rule);
+ mlx5_del_flow_rules(esw_sq->send_to_vport_rule);
list_del(&esw_sq->list);
kfree(esw_sq);
}
@@ -325,7 +334,7 @@ int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
struct mlx5_eswitch_rep *rep,
u16 *sqns_array, int sqns_num)
{
- struct mlx5_flow_rule *flow_rule;
+ struct mlx5_flow_handle *flow_rule;
struct mlx5_esw_sq *esw_sq;
int err;
int i;
@@ -361,8 +370,9 @@ int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw,
static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
{
+ struct mlx5_flow_act flow_act = {0};
struct mlx5_flow_destination dest;
- struct mlx5_flow_rule *flow_rule = NULL;
+ struct mlx5_flow_handle *flow_rule = NULL;
struct mlx5_flow_spec *spec;
int err = 0;
@@ -375,10 +385,10 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest.vport_num = 0;
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
- flow_rule = mlx5_add_flow_rule(esw->fdb_table.offloads.fdb, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- 0, &dest);
+ flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.fdb, spec,
+ &flow_act, &dest, 1);
if (IS_ERR(flow_rule)) {
err = PTR_ERR(flow_rule);
esw_warn(esw->dev, "FDB: Failed to add miss flow rule err %d\n", err);
@@ -405,6 +415,7 @@ static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports)
u32 *flow_group_in;
void *match_criteria;
int table_size, ix, err = 0;
+ u32 flags = 0;
flow_group_in = mlx5_vzalloc(inlen);
if (!flow_group_in)
@@ -419,9 +430,14 @@ static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports)
esw_debug(dev, "Create offloads FDB table, log_max_size(%d)\n",
MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
+ if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, encap) &&
+ MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap))
+ flags |= MLX5_FLOW_TABLE_TUNNEL_EN;
+
fdb = mlx5_create_auto_grouped_flow_table(root_ns, FDB_FAST_PATH,
ESW_OFFLOADS_NUM_ENTRIES,
- ESW_OFFLOADS_NUM_GROUPS, 0);
+ ESW_OFFLOADS_NUM_GROUPS, 0,
+ flags);
if (IS_ERR(fdb)) {
err = PTR_ERR(fdb);
esw_warn(dev, "Failed to create Fast path FDB Table err %d\n", err);
@@ -430,7 +446,7 @@ static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports)
esw->fdb_table.fdb = fdb;
table_size = nvports + MAX_PF_SQ + 1;
- fdb = mlx5_create_flow_table(root_ns, FDB_SLOW_PATH, table_size, 0);
+ fdb = mlx5_create_flow_table(root_ns, FDB_SLOW_PATH, table_size, 0, 0);
if (IS_ERR(fdb)) {
err = PTR_ERR(fdb);
esw_warn(dev, "Failed to create slow path FDB Table err %d\n", err);
@@ -501,7 +517,7 @@ static void esw_destroy_offloads_fdb_table(struct mlx5_eswitch *esw)
return;
esw_debug(esw->dev, "Destroy offloads FDB Table\n");
- mlx5_del_flow_rule(esw->fdb_table.offloads.miss_rule);
+ mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule);
mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
@@ -522,7 +538,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw)
return -ENOMEM;
}
- ft_offloads = mlx5_create_flow_table(ns, 0, dev->priv.sriov.num_vfs + 2, 0);
+ ft_offloads = mlx5_create_flow_table(ns, 0, dev->priv.sriov.num_vfs + 2, 0, 0);
if (IS_ERR(ft_offloads)) {
err = PTR_ERR(ft_offloads);
esw_warn(esw->dev, "Failed to create offloads table, err %d\n", err);
@@ -585,11 +601,12 @@ static void esw_destroy_vport_rx_group(struct mlx5_eswitch *esw)
mlx5_destroy_flow_group(esw->offloads.vport_rx_group);
}
-struct mlx5_flow_rule *
+struct mlx5_flow_handle *
mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn)
{
+ struct mlx5_flow_act flow_act = {0};
struct mlx5_flow_destination dest;
- struct mlx5_flow_rule *flow_rule;
+ struct mlx5_flow_handle *flow_rule;
struct mlx5_flow_spec *spec;
void *misc;
@@ -610,9 +627,9 @@ mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn)
dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
dest.tir_num = tirn;
- flow_rule = mlx5_add_flow_rule(esw->offloads.ft_offloads, spec,
- MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
- 0, &dest);
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ flow_rule = mlx5_add_flow_rules(esw->offloads.ft_offloads, spec,
+ &flow_act, &dest, 1);
if (IS_ERR(flow_rule)) {
esw_warn(esw->dev, "fs offloads: Failed to add vport rx rule err %ld\n", PTR_ERR(flow_rule));
goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 113c323..c4478ec 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -37,6 +37,7 @@
#include "fs_core.h"
#include "fs_cmd.h"
#include "mlx5_core.h"
+#include "eswitch.h"
int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev,
struct mlx5_flow_table *ft)
@@ -61,8 +62,9 @@ int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev,
enum fs_flow_table_op_mod op_mod,
enum fs_flow_table_type type, unsigned int level,
unsigned int log_size, struct mlx5_flow_table
- *next_ft, unsigned int *table_id)
+ *next_ft, unsigned int *table_id, u32 flags)
{
+ int en_encap_decap = !!(flags & MLX5_FLOW_TABLE_TUNNEL_EN);
u32 out[MLX5_ST_SZ_DW(create_flow_table_out)] = {0};
u32 in[MLX5_ST_SZ_DW(create_flow_table_in)] = {0};
int err;
@@ -78,6 +80,9 @@ int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev,
MLX5_SET(create_flow_table_in, in, other_vport, 1);
}
+ MLX5_SET(create_flow_table_in, in, decap_en, en_encap_decap);
+ MLX5_SET(create_flow_table_in, in, encap_en, en_encap_decap);
+
switch (op_mod) {
case FS_FT_OP_MOD_NORMAL:
if (next_ft) {
@@ -243,6 +248,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
MLX5_SET(flow_context, in_flow_context, group_id, group_id);
MLX5_SET(flow_context, in_flow_context, flow_tag, fte->flow_tag);
MLX5_SET(flow_context, in_flow_context, action, fte->action);
+ MLX5_SET(flow_context, in_flow_context, encap_id, fte->encap_id);
in_match_value = MLX5_ADDR_OF(flow_context, in_flow_context,
match_value);
memcpy(in_match_value, &fte->val, MLX5_ST_SZ_BYTES(fte_match_param));
@@ -453,27 +459,32 @@ void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev,
*bytes = MLX5_GET64(traffic_counter, stats, octets);
}
-#define MAX_ENCAP_SIZE (128)
-
-int mlx5_cmd_alloc_encap(struct mlx5_core_dev *dev,
- int header_type,
- size_t size,
- void *encap_header,
- u32 *encap_id)
+int mlx5_encap_alloc(struct mlx5_core_dev *dev,
+ int header_type,
+ size_t size,
+ void *encap_header,
+ u32 *encap_id)
{
+ int max_encap_size = MLX5_CAP_ESW(dev, max_encap_header_size);
u32 out[MLX5_ST_SZ_DW(alloc_encap_header_out)];
- u32 in[MLX5_ST_SZ_DW(alloc_encap_header_in) +
- (MAX_ENCAP_SIZE / sizeof(u32))];
- void *encap_header_in = MLX5_ADDR_OF(alloc_encap_header_in, in,
- encap_header);
- void *header = MLX5_ADDR_OF(encap_header_in, encap_header_in,
- encap_header);
- int inlen = header - (void *)in + size;
+ void *encap_header_in;
+ void *header;
+ int inlen;
int err;
+ u32 *in;
- if (size > MAX_ENCAP_SIZE)
+ if (size > MLX5_CAP_ESW(dev, max_encap_header_size))
return -EINVAL;
+ in = kzalloc(MLX5_ST_SZ_BYTES(alloc_encap_header_in) + max_encap_size,
+ GFP_KERNEL);
+ if (!in)
+ return -ENOMEM;
+
+ encap_header_in = MLX5_ADDR_OF(alloc_encap_header_in, in, encap_header);
+ header = MLX5_ADDR_OF(encap_header_in, encap_header_in, encap_header);
+ inlen = header - (void *)in + size;
+
memset(in, 0, inlen);
MLX5_SET(alloc_encap_header_in, in, opcode,
MLX5_CMD_OP_ALLOC_ENCAP_HEADER);
@@ -485,10 +496,11 @@ int mlx5_cmd_alloc_encap(struct mlx5_core_dev *dev,
err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
*encap_id = MLX5_GET(alloc_encap_header_out, out, encap_id);
+ kfree(in);
return err;
}
-void mlx5_cmd_dealloc_encap(struct mlx5_core_dev *dev, u32 encap_id)
+void mlx5_encap_dealloc(struct mlx5_core_dev *dev, u32 encap_id)
{
u32 in[MLX5_ST_SZ_DW(dealloc_encap_header_in)];
u32 out[MLX5_ST_SZ_DW(dealloc_encap_header_out)];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
index c5bc468..8fad806 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
@@ -38,7 +38,7 @@ int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev,
enum fs_flow_table_op_mod op_mod,
enum fs_flow_table_type type, unsigned int level,
unsigned int log_size, struct mlx5_flow_table
- *next_ft, unsigned int *table_id);
+ *next_ft, unsigned int *table_id, u32 flags);
int mlx5_cmd_destroy_flow_table(struct mlx5_core_dev *dev,
struct mlx5_flow_table *ft);
@@ -89,11 +89,4 @@ void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev,
struct mlx5_cmd_fc_bulk *b, u16 id,
u64 *packets, u64 *bytes);
-int mlx5_cmd_alloc_encap(struct mlx5_core_dev *dev,
- int header_type,
- size_t size,
- void *encap_header,
- u32 *encap_id);
-void mlx5_cmd_dealloc_encap(struct mlx5_core_dev *dev, u32 encap_id);
-
#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 5da2cc8..68ec4ea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -153,6 +153,11 @@ static void del_rule(struct fs_node *node);
static void del_flow_table(struct fs_node *node);
static void del_flow_group(struct fs_node *node);
static void del_fte(struct fs_node *node);
+static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
+ struct mlx5_flow_destination *d2);
+static struct mlx5_flow_rule *
+find_flow_rule(struct fs_fte *fte,
+ struct mlx5_flow_destination *dest);
static void tree_init_node(struct fs_node *node,
unsigned int refcount,
@@ -369,6 +374,7 @@ static void del_rule(struct fs_node *node)
struct mlx5_core_dev *dev = get_dev(node);
int match_len = MLX5_ST_SZ_BYTES(fte_match_param);
int err;
+ bool update_fte = false;
match_value = mlx5_vzalloc(match_len);
if (!match_value) {
@@ -387,13 +393,23 @@ static void del_rule(struct fs_node *node)
list_del(&rule->next_ft);
mutex_unlock(&rule->dest_attr.ft->lock);
}
+
+ if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER &&
+ --fte->dests_size) {
+ modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION);
+ fte->action &= ~MLX5_FLOW_CONTEXT_ACTION_COUNT;
+ update_fte = true;
+ goto out;
+ }
+
if ((fte->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) &&
--fte->dests_size) {
modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST),
- err = mlx5_cmd_update_fte(dev, ft,
- fg->id,
- modify_mask,
- fte);
+ update_fte = true;
+ }
+out:
+ if (update_fte && fte->dests_size) {
+ err = mlx5_cmd_update_fte(dev, ft, fg->id, modify_mask, fte);
if (err)
mlx5_core_warn(dev,
"%s can't del rule fg id=%d fte_index=%d\n",
@@ -436,13 +452,15 @@ static void del_flow_group(struct fs_node *node)
fs_get_obj(ft, fg->node.parent);
dev = get_dev(&ft->node);
+ if (ft->autogroup.active)
+ ft->autogroup.num_groups--;
+
if (mlx5_cmd_destroy_flow_group(dev, ft, fg->id))
mlx5_core_warn(dev, "flow steering can't destroy fg %d of ft %d\n",
fg->id, ft->id);
}
-static struct fs_fte *alloc_fte(u8 action,
- u32 flow_tag,
+static struct fs_fte *alloc_fte(struct mlx5_flow_act *flow_act,
u32 *match_value,
unsigned int index)
{
@@ -454,9 +472,10 @@ static struct fs_fte *alloc_fte(u8 action,
memcpy(fte->val, match_value, sizeof(fte->val));
fte->node.type = FS_TYPE_FLOW_ENTRY;
- fte->flow_tag = flow_tag;
+ fte->flow_tag = flow_act->flow_tag;
fte->index = index;
- fte->action = action;
+ fte->action = flow_act->action;
+ fte->encap_id = flow_act->encap_id;
return fte;
}
@@ -486,7 +505,8 @@ static struct mlx5_flow_group *alloc_flow_group(u32 *create_fg_in)
static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, int max_fte,
enum fs_flow_table_type table_type,
- enum fs_flow_table_op_mod op_mod)
+ enum fs_flow_table_op_mod op_mod,
+ u32 flags)
{
struct mlx5_flow_table *ft;
@@ -500,6 +520,7 @@ static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, int max_ft
ft->type = table_type;
ft->vport = vport;
ft->max_fte = max_fte;
+ ft->flags = flags;
INIT_LIST_HEAD(&ft->fwd_rules);
mutex_init(&ft->lock);
@@ -638,8 +659,8 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio
return err;
}
-int mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
- struct mlx5_flow_destination *dest)
+static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
+ struct mlx5_flow_destination *dest)
{
struct mlx5_flow_table *ft;
struct mlx5_flow_group *fg;
@@ -664,6 +685,28 @@ int mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
return err;
}
+int mlx5_modify_rule_destination(struct mlx5_flow_handle *handle,
+ struct mlx5_flow_destination *new_dest,
+ struct mlx5_flow_destination *old_dest)
+{
+ int i;
+
+ if (!old_dest) {
+ if (handle->num_rules != 1)
+ return -EINVAL;
+ return _mlx5_modify_rule_destination(handle->rule[0],
+ new_dest);
+ }
+
+ for (i = 0; i < handle->num_rules; i++) {
+ if (mlx5_flow_dests_cmp(new_dest, &handle->rule[i]->dest_attr))
+ return _mlx5_modify_rule_destination(handle->rule[i],
+ new_dest);
+ }
+
+ return -EINVAL;
+}
+
/* Modify/set FWD rules that point on old_next_ft to point on new_next_ft */
static int connect_fwd_rules(struct mlx5_core_dev *dev,
struct mlx5_flow_table *new_next_ft,
@@ -686,7 +729,7 @@ static int connect_fwd_rules(struct mlx5_core_dev *dev,
list_splice_init(&old_next_ft->fwd_rules, &new_next_ft->fwd_rules);
mutex_unlock(&old_next_ft->lock);
list_for_each_entry(iter, &new_next_ft->fwd_rules, next_ft) {
- err = mlx5_modify_rule_destination(iter, &dest);
+ err = _mlx5_modify_rule_destination(iter, &dest);
if (err)
pr_err("mlx5_core: failed to modify rule to point on flow table %d\n",
new_next_ft->id);
@@ -736,7 +779,8 @@ static void list_add_flow_table(struct mlx5_flow_table *ft,
static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
enum fs_flow_table_op_mod op_mod,
u16 vport, int prio,
- int max_fte, u32 level)
+ int max_fte, u32 level,
+ u32 flags)
{
struct mlx5_flow_table *next_ft = NULL;
struct mlx5_flow_table *ft;
@@ -769,7 +813,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
vport,
max_fte ? roundup_pow_of_two(max_fte) : 0,
root->table_type,
- op_mod);
+ op_mod, flags);
if (!ft) {
err = -ENOMEM;
goto unlock_root;
@@ -779,7 +823,8 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0;
next_ft = find_next_chained_ft(fs_prio);
err = mlx5_cmd_create_flow_table(root->dev, ft->vport, ft->op_mod, ft->type,
- ft->level, log_table_sz, next_ft, &ft->id);
+ ft->level, log_table_sz, next_ft, &ft->id,
+ ft->flags);
if (err)
goto free_ft;
@@ -804,10 +849,11 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
struct mlx5_flow_table *mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
int prio, int max_fte,
- u32 level)
+ u32 level,
+ u32 flags)
{
return __mlx5_create_flow_table(ns, FS_FT_OP_MOD_NORMAL, 0, prio,
- max_fte, level);
+ max_fte, level, flags);
}
struct mlx5_flow_table *mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns,
@@ -815,7 +861,7 @@ struct mlx5_flow_table *mlx5_create_vport_flow_table(struct mlx5_flow_namespace
u32 level, u16 vport)
{
return __mlx5_create_flow_table(ns, FS_FT_OP_MOD_NORMAL, vport, prio,
- max_fte, level);
+ max_fte, level, 0);
}
struct mlx5_flow_table *mlx5_create_lag_demux_flow_table(
@@ -823,7 +869,7 @@ struct mlx5_flow_table *mlx5_create_lag_demux_flow_table(
int prio, u32 level)
{
return __mlx5_create_flow_table(ns, FS_FT_OP_MOD_LAG_DEMUX, 0, prio, 0,
- level);
+ level, 0);
}
EXPORT_SYMBOL(mlx5_create_lag_demux_flow_table);
@@ -831,14 +877,15 @@ struct mlx5_flow_table *mlx5_create_auto_grouped_flow_table(struct mlx5_flow_nam
int prio,
int num_flow_table_entries,
int max_num_groups,
- u32 level)
+ u32 level,
+ u32 flags)
{
struct mlx5_flow_table *ft;
if (max_num_groups > num_flow_table_entries)
return ERR_PTR(-EINVAL);
- ft = mlx5_create_flow_table(ns, prio, num_flow_table_entries, level);
+ ft = mlx5_create_flow_table(ns, prio, num_flow_table_entries, level, flags);
if (IS_ERR(ft))
return ft;
@@ -879,7 +926,7 @@ static struct mlx5_flow_group *create_flow_group_common(struct mlx5_flow_table *
tree_init_node(&fg->node, !is_auto_fg, del_flow_group);
tree_add_node(&fg->node, &ft->node);
/* Add node to group list */
- list_add(&fg->node.list, ft->node.children.prev);
+ list_add(&fg->node.list, prev_fg);
return fg;
}
@@ -893,7 +940,7 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft,
return ERR_PTR(-EPERM);
lock_ref_node(&ft->node);
- fg = create_flow_group_common(ft, fg_in, &ft->node.children, false);
+ fg = create_flow_group_common(ft, fg_in, ft->node.children.prev, false);
unlock_ref_node(&ft->node);
return fg;
@@ -915,55 +962,133 @@ static struct mlx5_flow_rule *alloc_rule(struct mlx5_flow_destination *dest)
return rule;
}
-/* fte should not be deleted while calling this function */
-static struct mlx5_flow_rule *add_rule_fte(struct fs_fte *fte,
- struct mlx5_flow_group *fg,
- struct mlx5_flow_destination *dest)
+static struct mlx5_flow_handle *alloc_handle(int num_rules)
{
- struct mlx5_flow_table *ft;
- struct mlx5_flow_rule *rule;
- int modify_mask = 0;
- int err;
+ struct mlx5_flow_handle *handle;
- rule = alloc_rule(dest);
- if (!rule)
+ handle = kzalloc(sizeof(*handle) + sizeof(handle->rule[0]) *
+ num_rules, GFP_KERNEL);
+ if (!handle)
+ return NULL;
+
+ handle->num_rules = num_rules;
+
+ return handle;
+}
+
+static void destroy_flow_handle(struct fs_fte *fte,
+ struct mlx5_flow_handle *handle,
+ struct mlx5_flow_destination *dest,
+ int i)
+{
+ for (; --i >= 0;) {
+ if (atomic_dec_and_test(&handle->rule[i]->node.refcount)) {
+ fte->dests_size--;
+ list_del(&handle->rule[i]->node.list);
+ kfree(handle->rule[i]);
+ }
+ }
+ kfree(handle);
+}
+
+static struct mlx5_flow_handle *
+create_flow_handle(struct fs_fte *fte,
+ struct mlx5_flow_destination *dest,
+ int dest_num,
+ int *modify_mask,
+ bool *new_rule)
+{
+ struct mlx5_flow_handle *handle;
+ struct mlx5_flow_rule *rule = NULL;
+ static int count = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS);
+ static int dst = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST);
+ int type;
+ int i = 0;
+
+ handle = alloc_handle((dest_num) ? dest_num : 1);
+ if (!handle)
return ERR_PTR(-ENOMEM);
+ do {
+ if (dest) {
+ rule = find_flow_rule(fte, dest + i);
+ if (rule) {
+ atomic_inc(&rule->node.refcount);
+ goto rule_found;
+ }
+ }
+
+ *new_rule = true;
+ rule = alloc_rule(dest + i);
+ if (!rule)
+ goto free_rules;
+
+ /* Add dest to dests list- we need flow tables to be in the
+ * end of the list for forward to next prio rules.
+ */
+ tree_init_node(&rule->node, 1, del_rule);
+ if (dest &&
+ dest[i].type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE)
+ list_add(&rule->node.list, &fte->node.children);
+ else
+ list_add_tail(&rule->node.list, &fte->node.children);
+ if (dest) {
+ fte->dests_size++;
+
+ type = dest[i].type ==
+ MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+ *modify_mask |= type ? count : dst;
+ }
+rule_found:
+ handle->rule[i] = rule;
+ } while (++i < dest_num);
+
+ return handle;
+
+free_rules:
+ destroy_flow_handle(fte, handle, dest, i);
+ return ERR_PTR(-ENOMEM);
+}
+
+/* fte should not be deleted while calling this function */
+static struct mlx5_flow_handle *
+add_rule_fte(struct fs_fte *fte,
+ struct mlx5_flow_group *fg,
+ struct mlx5_flow_destination *dest,
+ int dest_num,
+ bool update_action)
+{
+ struct mlx5_flow_handle *handle;
+ struct mlx5_flow_table *ft;
+ int modify_mask = 0;
+ int err;
+ bool new_rule = false;
+
+ handle = create_flow_handle(fte, dest, dest_num, &modify_mask,
+ &new_rule);
+ if (IS_ERR(handle) || !new_rule)
+ goto out;
+
+ if (update_action)
+ modify_mask |= BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION);
+
fs_get_obj(ft, fg->node.parent);
- /* Add dest to dests list- we need flow tables to be in the
- * end of the list for forward to next prio rules.
- */
- tree_init_node(&rule->node, 1, del_rule);
- if (dest && dest->type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE)
- list_add(&rule->node.list, &fte->node.children);
- else
- list_add_tail(&rule->node.list, &fte->node.children);
- if (dest) {
- fte->dests_size++;
-
- modify_mask |= dest->type == MLX5_FLOW_DESTINATION_TYPE_COUNTER ?
- BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS) :
- BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST);
- }
-
- if (fte->dests_size == 1 || !dest)
+ if (!(fte->status & FS_FTE_STATUS_EXISTING))
err = mlx5_cmd_create_fte(get_dev(&ft->node),
ft, fg->id, fte);
else
err = mlx5_cmd_update_fte(get_dev(&ft->node),
ft, fg->id, modify_mask, fte);
if (err)
- goto free_rule;
+ goto free_handle;
fte->status |= FS_FTE_STATUS_EXISTING;
- return rule;
+out:
+ return handle;
-free_rule:
- list_del(&rule->node.list);
- kfree(rule);
- if (dest)
- fte->dests_size--;
+free_handle:
+ destroy_flow_handle(fte, handle, dest, handle->num_rules);
return ERR_PTR(err);
}
@@ -992,15 +1117,14 @@ static unsigned int get_free_fte_index(struct mlx5_flow_group *fg,
/* prev is output, prev->next = new_fte */
static struct fs_fte *create_fte(struct mlx5_flow_group *fg,
u32 *match_value,
- u8 action,
- u32 flow_tag,
+ struct mlx5_flow_act *flow_act,
struct list_head **prev)
{
struct fs_fte *fte;
int index;
index = get_free_fte_index(fg, prev);
- fte = alloc_fte(action, flow_tag, match_value, index);
+ fte = alloc_fte(flow_act, match_value, index);
if (IS_ERR(fte))
return fte;
@@ -1012,7 +1136,7 @@ static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft,
u32 *match_criteria)
{
int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
- struct list_head *prev = &ft->node.children;
+ struct list_head *prev = ft->node.children.prev;
unsigned int candidate_index = 0;
struct mlx5_flow_group *fg;
void *match_criteria_addr;
@@ -1064,71 +1188,81 @@ static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft,
return fg;
}
+static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
+ struct mlx5_flow_destination *d2)
+{
+ if (d1->type == d2->type) {
+ if ((d1->type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
+ d1->vport_num == d2->vport_num) ||
+ (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
+ d1->ft == d2->ft) ||
+ (d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR &&
+ d1->tir_num == d2->tir_num))
+ return true;
+ }
+
+ return false;
+}
+
static struct mlx5_flow_rule *find_flow_rule(struct fs_fte *fte,
struct mlx5_flow_destination *dest)
{
struct mlx5_flow_rule *rule;
list_for_each_entry(rule, &fte->node.children, node.list) {
- if (rule->dest_attr.type == dest->type) {
- if ((dest->type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
- dest->vport_num == rule->dest_attr.vport_num) ||
- (dest->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
- dest->ft == rule->dest_attr.ft) ||
- (dest->type == MLX5_FLOW_DESTINATION_TYPE_TIR &&
- dest->tir_num == rule->dest_attr.tir_num))
- return rule;
- }
+ if (mlx5_flow_dests_cmp(&rule->dest_attr, dest))
+ return rule;
}
return NULL;
}
-static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
- u32 *match_value,
- u8 action,
- u32 flow_tag,
- struct mlx5_flow_destination *dest)
+static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg,
+ u32 *match_value,
+ struct mlx5_flow_act *flow_act,
+ struct mlx5_flow_destination *dest,
+ int dest_num)
{
- struct fs_fte *fte;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *handle;
struct mlx5_flow_table *ft;
struct list_head *prev;
+ struct fs_fte *fte;
+ int i;
nested_lock_ref_node(&fg->node, FS_MUTEX_PARENT);
fs_for_each_fte(fte, fg) {
nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD);
if (compare_match_value(&fg->mask, match_value, &fte->val) &&
- action == fte->action && flow_tag == fte->flow_tag) {
- rule = find_flow_rule(fte, dest);
- if (rule) {
- atomic_inc(&rule->node.refcount);
- unlock_ref_node(&fte->node);
- unlock_ref_node(&fg->node);
- return rule;
+ (flow_act->action & fte->action) &&
+ flow_act->flow_tag == fte->flow_tag) {
+ int old_action = fte->action;
+
+ fte->action |= flow_act->action;
+ handle = add_rule_fte(fte, fg, dest, dest_num,
+ old_action != flow_act->action);
+ if (IS_ERR(handle)) {
+ fte->action = old_action;
+ goto unlock_fte;
+ } else {
+ goto add_rules;
}
- rule = add_rule_fte(fte, fg, dest);
- unlock_ref_node(&fte->node);
- if (IS_ERR(rule))
- goto unlock_fg;
- else
- goto add_rule;
}
unlock_ref_node(&fte->node);
}
fs_get_obj(ft, fg->node.parent);
if (fg->num_ftes >= fg->max_ftes) {
- rule = ERR_PTR(-ENOSPC);
+ handle = ERR_PTR(-ENOSPC);
goto unlock_fg;
}
- fte = create_fte(fg, match_value, action, flow_tag, &prev);
+ fte = create_fte(fg, match_value, flow_act, &prev);
if (IS_ERR(fte)) {
- rule = (void *)fte;
+ handle = (void *)fte;
goto unlock_fg;
}
tree_init_node(&fte->node, 0, del_fte);
- rule = add_rule_fte(fte, fg, dest);
- if (IS_ERR(rule)) {
+ nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD);
+ handle = add_rule_fte(fte, fg, dest, dest_num, false);
+ if (IS_ERR(handle)) {
kfree(fte);
goto unlock_fg;
}
@@ -1137,19 +1271,24 @@ static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg,
tree_add_node(&fte->node, &fg->node);
list_add(&fte->node.list, prev);
-add_rule:
- tree_add_node(&rule->node, &fte->node);
+add_rules:
+ for (i = 0; i < handle->num_rules; i++) {
+ if (atomic_read(&handle->rule[i]->node.refcount) == 1)
+ tree_add_node(&handle->rule[i]->node, &fte->node);
+ }
+unlock_fte:
+ unlock_ref_node(&fte->node);
unlock_fg:
unlock_ref_node(&fg->node);
- return rule;
+ return handle;
}
-struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_rule *rule)
+struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_handle *handle)
{
struct mlx5_flow_rule *dst;
struct fs_fte *fte;
- fs_get_obj(fte, rule->node.parent);
+ fs_get_obj(fte, handle->rule[0]->node.parent);
fs_for_each_dst(dst, fte) {
if (dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
@@ -1167,8 +1306,9 @@ static bool counter_is_valid(struct mlx5_fc *counter, u32 action)
if (!counter)
return false;
- /* Hardware support counter for a drop action only */
- return action == (MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT);
+ return (action & (MLX5_FLOW_CONTEXT_ACTION_DROP |
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST)) &&
+ (action & MLX5_FLOW_CONTEXT_ACTION_COUNT);
}
static bool dest_is_valid(struct mlx5_flow_destination *dest,
@@ -1188,18 +1328,22 @@ static bool dest_is_valid(struct mlx5_flow_destination *dest,
return true;
}
-static struct mlx5_flow_rule *
-_mlx5_add_flow_rule(struct mlx5_flow_table *ft,
- struct mlx5_flow_spec *spec,
- u32 action,
- u32 flow_tag,
- struct mlx5_flow_destination *dest)
+static struct mlx5_flow_handle *
+_mlx5_add_flow_rules(struct mlx5_flow_table *ft,
+ struct mlx5_flow_spec *spec,
+ struct mlx5_flow_act *flow_act,
+ struct mlx5_flow_destination *dest,
+ int dest_num)
+
{
struct mlx5_flow_group *g;
- struct mlx5_flow_rule *rule;
+ struct mlx5_flow_handle *rule;
+ int i;
- if (!dest_is_valid(dest, action, ft))
- return ERR_PTR(-EINVAL);
+ for (i = 0; i < dest_num; i++) {
+ if (!dest_is_valid(&dest[i], flow_act->action, ft))
+ return ERR_PTR(-EINVAL);
+ }
nested_lock_ref_node(&ft->node, FS_MUTEX_GRANDPARENT);
fs_for_each_fg(g, ft)
@@ -1208,7 +1352,7 @@ _mlx5_add_flow_rule(struct mlx5_flow_table *ft,
g->mask.match_criteria,
spec->match_criteria)) {
rule = add_rule_fg(g, spec->match_value,
- action, flow_tag, dest);
+ flow_act, dest, dest_num);
if (!IS_ERR(rule) || PTR_ERR(rule) != -ENOSPC)
goto unlock;
}
@@ -1220,8 +1364,7 @@ _mlx5_add_flow_rule(struct mlx5_flow_table *ft,
goto unlock;
}
- rule = add_rule_fg(g, spec->match_value,
- action, flow_tag, dest);
+ rule = add_rule_fg(g, spec->match_value, flow_act, dest, dest_num);
if (IS_ERR(rule)) {
/* Remove assumes refcount > 0 and autogroup creates a group
* with a refcount = 0.
@@ -1242,22 +1385,22 @@ static bool fwd_next_prio_supported(struct mlx5_flow_table *ft)
(MLX5_CAP_FLOWTABLE(get_dev(&ft->node), nic_rx_multi_path_tirs)));
}
-struct mlx5_flow_rule *
-mlx5_add_flow_rule(struct mlx5_flow_table *ft,
- struct mlx5_flow_spec *spec,
- u32 action,
- u32 flow_tag,
- struct mlx5_flow_destination *dest)
+struct mlx5_flow_handle *
+mlx5_add_flow_rules(struct mlx5_flow_table *ft,
+ struct mlx5_flow_spec *spec,
+ struct mlx5_flow_act *flow_act,
+ struct mlx5_flow_destination *dest,
+ int dest_num)
{
struct mlx5_flow_root_namespace *root = find_root(&ft->node);
struct mlx5_flow_destination gen_dest;
struct mlx5_flow_table *next_ft = NULL;
- struct mlx5_flow_rule *rule = NULL;
- u32 sw_action = action;
+ struct mlx5_flow_handle *handle = NULL;
+ u32 sw_action = flow_act->action;
struct fs_prio *prio;
fs_get_obj(prio, ft->node.parent);
- if (action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
+ if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
if (!fwd_next_prio_supported(ft))
return ERR_PTR(-EOPNOTSUPP);
if (dest)
@@ -1268,34 +1411,40 @@ mlx5_add_flow_rule(struct mlx5_flow_table *ft,
gen_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
gen_dest.ft = next_ft;
dest = &gen_dest;
- action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+ dest_num = 1;
+ flow_act->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
} else {
mutex_unlock(&root->chain_lock);
return ERR_PTR(-EOPNOTSUPP);
}
}
- rule = _mlx5_add_flow_rule(ft, spec, action, flow_tag, dest);
+ handle = _mlx5_add_flow_rules(ft, spec, flow_act, dest, dest_num);
if (sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
- if (!IS_ERR_OR_NULL(rule) &&
- (list_empty(&rule->next_ft))) {
+ if (!IS_ERR_OR_NULL(handle) &&
+ (list_empty(&handle->rule[0]->next_ft))) {
mutex_lock(&next_ft->lock);
- list_add(&rule->next_ft, &next_ft->fwd_rules);
+ list_add(&handle->rule[0]->next_ft,
+ &next_ft->fwd_rules);
mutex_unlock(&next_ft->lock);
- rule->sw_action = MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
+ handle->rule[0]->sw_action = MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
}
mutex_unlock(&root->chain_lock);
}
- return rule;
+ return handle;
}
-EXPORT_SYMBOL(mlx5_add_flow_rule);
+EXPORT_SYMBOL(mlx5_add_flow_rules);
-void mlx5_del_flow_rule(struct mlx5_flow_rule *rule)
+void mlx5_del_flow_rules(struct mlx5_flow_handle *handle)
{
- tree_remove_node(&rule->node);
+ int i;
+
+ for (i = handle->num_rules - 1; i >= 0; i--)
+ tree_remove_node(&handle->rule[i]->node);
+ kfree(handle);
}
-EXPORT_SYMBOL(mlx5_del_flow_rule);
+EXPORT_SYMBOL(mlx5_del_flow_rules);
/* Assuming prio->node.children(flow tables) is sorted by level */
static struct mlx5_flow_table *find_next_ft(struct mlx5_flow_table *ft)
@@ -1675,7 +1824,7 @@ static int create_anchor_flow_table(struct mlx5_flow_steering *steering)
ns = mlx5_get_flow_namespace(steering->dev, MLX5_FLOW_NAMESPACE_ANCHOR);
if (!ns)
return -EINVAL;
- ft = mlx5_create_flow_table(ns, ANCHOR_PRIO, ANCHOR_SIZE, ANCHOR_LEVEL);
+ ft = mlx5_create_flow_table(ns, ANCHOR_PRIO, ANCHOR_SIZE, ANCHOR_LEVEL, 0);
if (IS_ERR(ft)) {
mlx5_core_err(steering->dev, "Failed to create last anchor flow table");
return PTR_ERR(ft);
@@ -1687,7 +1836,7 @@ static int init_root_ns(struct mlx5_flow_steering *steering)
{
steering->root_ns = create_root_ns(steering, FS_FT_NIC_RX);
- if (IS_ERR_OR_NULL(steering->root_ns))
+ if (!steering->root_ns)
goto cleanup;
if (init_root_tree(steering, &root_fs, &steering->root_ns->ns.node))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 71ff03b..8e668c6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -94,6 +94,11 @@ struct mlx5_flow_rule {
u32 sw_action;
};
+struct mlx5_flow_handle {
+ int num_rules;
+ struct mlx5_flow_rule *rule[];
+};
+
/* Type of children is mlx5_flow_group */
struct mlx5_flow_table {
struct fs_node node;
@@ -112,6 +117,7 @@ struct mlx5_flow_table {
struct mutex lock;
/* FWD rules that point on this flow table */
struct list_head fwd_rules;
+ u32 flags;
};
struct mlx5_fc_cache {
@@ -145,6 +151,7 @@ struct fs_fte {
u32 flow_tag;
u32 index;
u32 action;
+ u32 encap_id;
enum fs_fte_status status;
struct mlx5_fc *counter;
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 3a9195b..3b026c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -218,6 +218,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging)
goto err_out;
if (aging) {
+ counter->cache.lastuse = jiffies;
counter->aging = true;
spin_lock(&fc_stats->addlist_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 1a05fb9..5bcf934 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -61,10 +61,15 @@ enum {
enum {
MLX5_NIC_IFC_FULL = 0,
MLX5_NIC_IFC_DISABLED = 1,
- MLX5_NIC_IFC_NO_DRAM_NIC = 2
+ MLX5_NIC_IFC_NO_DRAM_NIC = 2,
+ MLX5_NIC_IFC_INVALID = 3
};
-static u8 get_nic_interface(struct mlx5_core_dev *dev)
+enum {
+ MLX5_DROP_NEW_HEALTH_WORK,
+};
+
+static u8 get_nic_state(struct mlx5_core_dev *dev)
{
return (ioread32be(&dev->iseg->cmdq_addr_l_sz) >> 8) & 3;
}
@@ -97,7 +102,7 @@ static int in_fatal(struct mlx5_core_dev *dev)
struct mlx5_core_health *health = &dev->priv.health;
struct health_buffer __iomem *h = health->health;
- if (get_nic_interface(dev) == MLX5_NIC_IFC_DISABLED)
+ if (get_nic_state(dev) == MLX5_NIC_IFC_DISABLED)
return 1;
if (ioread32be(&h->fw_ver) == 0xffffffff)
@@ -127,7 +132,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev)
static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
{
- u8 nic_interface = get_nic_interface(dev);
+ u8 nic_interface = get_nic_state(dev);
switch (nic_interface) {
case MLX5_NIC_IFC_FULL:
@@ -149,8 +154,34 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
mlx5_disable_device(dev);
}
+static void health_recover(struct work_struct *work)
+{
+ struct mlx5_core_health *health;
+ struct delayed_work *dwork;
+ struct mlx5_core_dev *dev;
+ struct mlx5_priv *priv;
+ u8 nic_state;
+
+ dwork = container_of(work, struct delayed_work, work);
+ health = container_of(dwork, struct mlx5_core_health, recover_work);
+ priv = container_of(health, struct mlx5_priv, health);
+ dev = container_of(priv, struct mlx5_core_dev, priv);
+
+ nic_state = get_nic_state(dev);
+ if (nic_state == MLX5_NIC_IFC_INVALID) {
+ dev_err(&dev->pdev->dev, "health recovery flow aborted since the nic state is invalid\n");
+ return;
+ }
+
+ dev_err(&dev->pdev->dev, "starting health recovery flow\n");
+ mlx5_recover_device(dev);
+}
+
+/* How much time to wait until health resetting the driver (in msecs) */
+#define MLX5_RECOVERY_DELAY_MSECS 60000
static void health_care(struct work_struct *work)
{
+ unsigned long recover_delay = msecs_to_jiffies(MLX5_RECOVERY_DELAY_MSECS);
struct mlx5_core_health *health;
struct mlx5_core_dev *dev;
struct mlx5_priv *priv;
@@ -160,6 +191,14 @@ static void health_care(struct work_struct *work)
dev = container_of(priv, struct mlx5_core_dev, priv);
mlx5_core_warn(dev, "handling bad device here\n");
mlx5_handle_bad_state(dev);
+
+ spin_lock(&health->wq_lock);
+ if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags))
+ schedule_delayed_work(&health->recover_work, recover_delay);
+ else
+ dev_err(&dev->pdev->dev,
+ "new health works are not permitted at this stage\n");
+ spin_unlock(&health->wq_lock);
}
static const char *hsynd_str(u8 synd)
@@ -272,7 +311,13 @@ static void poll_health(unsigned long data)
if (in_fatal(dev) && !health->sick) {
health->sick = true;
print_health_info(dev);
- schedule_work(&health->work);
+ spin_lock(&health->wq_lock);
+ if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags))
+ queue_work(health->wq, &health->work);
+ else
+ dev_err(&dev->pdev->dev,
+ "new health works are not permitted at this stage\n");
+ spin_unlock(&health->wq_lock);
}
}
@@ -281,6 +326,8 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev)
struct mlx5_core_health *health = &dev->priv.health;
init_timer(&health->timer);
+ health->sick = 0;
+ clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
health->health = &dev->iseg->health;
health->health_counter = &dev->iseg->health_counter;
@@ -297,11 +344,22 @@ void mlx5_stop_health_poll(struct mlx5_core_dev *dev)
del_timer_sync(&health->timer);
}
+void mlx5_drain_health_wq(struct mlx5_core_dev *dev)
+{
+ struct mlx5_core_health *health = &dev->priv.health;
+
+ spin_lock(&health->wq_lock);
+ set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
+ spin_unlock(&health->wq_lock);
+ cancel_delayed_work_sync(&health->recover_work);
+ cancel_work_sync(&health->work);
+}
+
void mlx5_health_cleanup(struct mlx5_core_dev *dev)
{
struct mlx5_core_health *health = &dev->priv.health;
- flush_work(&health->work);
+ destroy_workqueue(health->wq);
}
int mlx5_health_init(struct mlx5_core_dev *dev)
@@ -316,9 +374,13 @@ int mlx5_health_init(struct mlx5_core_dev *dev)
strcpy(name, "mlx5_health");
strcat(name, dev_name(&dev->pdev->dev));
+ health->wq = create_singlethread_workqueue(name);
kfree(name);
-
+ if (!health->wq)
+ return -ENOMEM;
+ spin_lock_init(&health->wq_lock);
INIT_WORK(&health->work, health_care);
+ INIT_DELAYED_WORK(&health->recover_work, health_recover);
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index d9c3c70..f28df33 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -175,6 +175,41 @@ static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili)
return err;
}
+static void mlx5_set_driver_version(struct mlx5_core_dev *dev)
+{
+ int driver_ver_sz = MLX5_FLD_SZ_BYTES(set_driver_version_in,
+ driver_version);
+ u8 in[MLX5_ST_SZ_BYTES(set_driver_version_in)] = {0};
+ u8 out[MLX5_ST_SZ_BYTES(set_driver_version_out)] = {0};
+ int remaining_size = driver_ver_sz;
+ char *string;
+
+ if (!MLX5_CAP_GEN(dev, driver_version))
+ return;
+
+ string = MLX5_ADDR_OF(set_driver_version_in, in, driver_version);
+
+ strncpy(string, "Linux", remaining_size);
+
+ remaining_size = max_t(int, 0, driver_ver_sz - strlen(string));
+ strncat(string, ",", remaining_size);
+
+ remaining_size = max_t(int, 0, driver_ver_sz - strlen(string));
+ strncat(string, DRIVER_NAME, remaining_size);
+
+ remaining_size = max_t(int, 0, driver_ver_sz - strlen(string));
+ strncat(string, ",", remaining_size);
+
+ remaining_size = max_t(int, 0, driver_ver_sz - strlen(string));
+ strncat(string, DRIVER_VERSION, remaining_size);
+
+ /*Send the command*/
+ MLX5_SET(set_driver_version_in, in, opcode,
+ MLX5_CMD_OP_SET_DRIVER_VERSION);
+
+ mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
static int set_dma_caps(struct pci_dev *pdev)
{
int err;
@@ -844,12 +879,6 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
struct pci_dev *pdev = dev->pdev;
int err;
- err = mlx5_query_hca_caps(dev);
- if (err) {
- dev_err(&pdev->dev, "query hca failed\n");
- goto out;
- }
-
err = mlx5_query_board_id(dev);
if (err) {
dev_err(&pdev->dev, "query board id failed\n");
@@ -1021,8 +1050,16 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
goto err_pagealloc_stop;
}
+ mlx5_set_driver_version(dev);
+
mlx5_start_health_poll(dev);
+ err = mlx5_query_hca_caps(dev);
+ if (err) {
+ dev_err(&pdev->dev, "query hca failed\n");
+ goto err_stop_poll;
+ }
+
if (boot && mlx5_init_once(dev, priv)) {
dev_err(&pdev->dev, "sw objs init failed\n");
goto err_stop_poll;
@@ -1226,6 +1263,9 @@ static int init_one(struct pci_dev *pdev,
pci_set_drvdata(pdev, dev);
+ dev->pdev = pdev;
+ dev->event = mlx5_core_event;
+
if (prof_sel < 0 || prof_sel >= ARRAY_SIZE(profile)) {
mlx5_core_warn(dev,
"selected profile out of range, selecting default (%d)\n",
@@ -1233,8 +1273,6 @@ static int init_one(struct pci_dev *pdev,
prof_sel = MLX5_DEFAULT_PROF;
}
dev->profile = &profile[prof_sel];
- dev->pdev = pdev;
- dev->event = mlx5_core_event;
INIT_LIST_HEAD(&priv->ctx_list);
spin_lock_init(&priv->ctx_lock);
@@ -1313,10 +1351,16 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
struct mlx5_priv *priv = &dev->priv;
dev_info(&pdev->dev, "%s was called\n", __func__);
+
mlx5_enter_error_state(dev);
mlx5_unload_one(dev, priv, false);
- pci_save_state(pdev);
- mlx5_pci_disable_device(dev);
+ /* In case of kernel call save the pci state and drain health wq */
+ if (state) {
+ pci_save_state(pdev);
+ mlx5_drain_health_wq(dev);
+ mlx5_pci_disable_device(dev);
+ }
+
return state == pci_channel_io_perm_failure ?
PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
}
@@ -1373,11 +1417,6 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
return PCI_ERS_RESULT_RECOVERED;
}
-void mlx5_disable_device(struct mlx5_core_dev *dev)
-{
- mlx5_pci_err_detected(dev->pdev, 0);
-}
-
static void mlx5_pci_resume(struct pci_dev *pdev)
{
struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
@@ -1422,11 +1461,24 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
{ PCI_VDEVICE(MELLANOX, 0x1017) }, /* ConnectX-5, PCIe 3.0 */
{ PCI_VDEVICE(MELLANOX, 0x1018), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5 VF */
{ PCI_VDEVICE(MELLANOX, 0x1019) }, /* ConnectX-5, PCIe 4.0 */
+ { PCI_VDEVICE(MELLANOX, 0x101a), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5, PCIe 4.0 VF */
{ 0, }
};
MODULE_DEVICE_TABLE(pci, mlx5_core_pci_table);
+void mlx5_disable_device(struct mlx5_core_dev *dev)
+{
+ mlx5_pci_err_detected(dev->pdev, 0);
+}
+
+void mlx5_recover_device(struct mlx5_core_dev *dev)
+{
+ mlx5_pci_disable_device(dev);
+ if (mlx5_pci_slot_reset(dev->pdev) == PCI_ERS_RESULT_RECOVERED)
+ mlx5_pci_resume(dev->pdev);
+}
+
static struct pci_driver mlx5_core_driver = {
.name = DRIVER_NAME,
.id_table = mlx5_core_pci_table,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 3d0cfb9..7e635eb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -81,8 +81,10 @@ int mlx5_cmd_init_hca(struct mlx5_core_dev *dev);
int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev);
void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
unsigned long param);
+void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
void mlx5_enter_error_state(struct mlx5_core_dev *dev);
void mlx5_disable_device(struct mlx5_core_dev *dev);
+void mlx5_recover_device(struct mlx5_core_dev *dev);
int mlx5_sriov_init(struct mlx5_core_dev *dev);
void mlx5_sriov_cleanup(struct mlx5_core_dev *dev);
int mlx5_sriov_attach(struct mlx5_core_dev *dev);
@@ -91,6 +93,13 @@ int mlx5_core_sriov_configure(struct pci_dev *dev, int num_vfs);
bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev);
int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id);
int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id);
+int mlx5_create_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
+ void *context, u32 *element_id);
+int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
+ void *context, u32 element_id,
+ u32 modify_bitmask);
+int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
+ u32 element_id);
int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
cycle_t mlx5_read_internal_timer(struct mlx5_core_dev *dev);
u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx);
@@ -113,6 +122,12 @@ struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev);
void mlx5_dev_list_lock(void);
void mlx5_dev_list_unlock(void);
int mlx5_dev_list_trylock(void);
+int mlx5_encap_alloc(struct mlx5_core_dev *dev,
+ int header_type,
+ size_t size,
+ void *encap_header,
+ u32 *encap_id);
+void mlx5_encap_dealloc(struct mlx5_core_dev *dev, u32 encap_id);
bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index cc4fd61..a57d5a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -209,6 +209,7 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr)
static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id)
{
struct page *page;
+ u64 zero_addr = 1;
u64 addr;
int err;
int nid = dev_to_node(&dev->pdev->dev);
@@ -218,26 +219,35 @@ static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id)
mlx5_core_warn(dev, "failed to allocate page\n");
return -ENOMEM;
}
+map:
addr = dma_map_page(&dev->pdev->dev, page, 0,
PAGE_SIZE, DMA_BIDIRECTIONAL);
if (dma_mapping_error(&dev->pdev->dev, addr)) {
mlx5_core_warn(dev, "failed dma mapping page\n");
err = -ENOMEM;
- goto out_alloc;
+ goto err_mapping;
}
+
+ /* Firmware doesn't support page with physical address 0 */
+ if (addr == 0) {
+ zero_addr = addr;
+ goto map;
+ }
+
err = insert_page(dev, addr, page, func_id);
if (err) {
mlx5_core_err(dev, "failed to track allocated page\n");
- goto out_mapping;
+ dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE,
+ DMA_BIDIRECTIONAL);
}
- return 0;
+err_mapping:
+ if (err)
+ __free_page(page);
-out_mapping:
- dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
-
-out_alloc:
- __free_page(page);
+ if (zero_addr == 0)
+ dma_unmap_page(&dev->pdev->dev, zero_addr, PAGE_SIZE,
+ DMA_BIDIRECTIONAL);
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 34e7184..b77928f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -746,3 +746,60 @@ void mlx5_query_port_fcs(struct mlx5_core_dev *mdev, bool *supported,
*supported = !!(MLX5_GET(pcmr_reg, out, fcs_cap));
*enabled = !!(MLX5_GET(pcmr_reg, out, fcs_chk));
}
+
+static const char *mlx5_pme_status[MLX5_MODULE_STATUS_NUM] = {
+ "Cable plugged", /* MLX5_MODULE_STATUS_PLUGGED = 0x1 */
+ "Cable unplugged", /* MLX5_MODULE_STATUS_UNPLUGGED = 0x2 */
+ "Cable error", /* MLX5_MODULE_STATUS_ERROR = 0x3 */
+};
+
+static const char *mlx5_pme_error[MLX5_MODULE_EVENT_ERROR_NUM] = {
+ "Power budget exceeded",
+ "Long Range for non MLNX cable",
+ "Bus stuck(I2C or data shorted)",
+ "No EEPROM/retry timeout",
+ "Enforce part number list",
+ "Unknown identifier",
+ "High Temperature",
+ "Bad or shorted cable/module",
+ "Unknown status",
+};
+
+void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
+{
+ enum port_module_event_status_type module_status;
+ enum port_module_event_error_type error_type;
+ struct mlx5_eqe_port_module *module_event_eqe;
+ struct mlx5_priv *priv = &dev->priv;
+ u8 module_num;
+
+ module_event_eqe = &eqe->data.port_module;
+ module_num = module_event_eqe->module;
+ module_status = module_event_eqe->module_status &
+ PORT_MODULE_EVENT_MODULE_STATUS_MASK;
+ error_type = module_event_eqe->error_type &
+ PORT_MODULE_EVENT_ERROR_TYPE_MASK;
+
+ if (module_status < MLX5_MODULE_STATUS_ERROR) {
+ priv->pme_stats.status_counters[module_status - 1]++;
+ } else if (module_status == MLX5_MODULE_STATUS_ERROR) {
+ if (error_type >= MLX5_MODULE_EVENT_ERROR_UNKNOWN)
+ /* Unknown error type */
+ error_type = MLX5_MODULE_EVENT_ERROR_UNKNOWN;
+ priv->pme_stats.error_counters[error_type]++;
+ }
+
+ if (!printk_ratelimit())
+ return;
+
+ if (module_status < MLX5_MODULE_STATUS_ERROR)
+ mlx5_core_info(dev,
+ "Port module event: module %u, %s\n",
+ module_num, mlx5_pme_status[module_status - 1]);
+
+ else if (module_status == MLX5_MODULE_STATUS_ERROR)
+ mlx5_core_info(dev,
+ "Port module event[error]: module %u, %s, %s\n",
+ module_num, mlx5_pme_status[module_status - 1],
+ mlx5_pme_error[error_type]);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
index 104902a..e651e4c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
@@ -36,6 +36,71 @@
#include <linux/mlx5/cmd.h>
#include "mlx5_core.h"
+/* Scheduling element fw management */
+int mlx5_create_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
+ void *ctx, u32 *element_id)
+{
+ u32 in[MLX5_ST_SZ_DW(create_scheduling_element_in)] = {0};
+ u32 out[MLX5_ST_SZ_DW(create_scheduling_element_in)] = {0};
+ void *schedc;
+ int err;
+
+ schedc = MLX5_ADDR_OF(create_scheduling_element_in, in,
+ scheduling_context);
+ MLX5_SET(create_scheduling_element_in, in, opcode,
+ MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT);
+ MLX5_SET(create_scheduling_element_in, in, scheduling_hierarchy,
+ hierarchy);
+ memcpy(schedc, ctx, MLX5_ST_SZ_BYTES(scheduling_context));
+
+ err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+ if (err)
+ return err;
+
+ *element_id = MLX5_GET(create_scheduling_element_out, out,
+ scheduling_element_id);
+ return 0;
+}
+
+int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
+ void *ctx, u32 element_id,
+ u32 modify_bitmask)
+{
+ u32 in[MLX5_ST_SZ_DW(modify_scheduling_element_in)] = {0};
+ u32 out[MLX5_ST_SZ_DW(modify_scheduling_element_in)] = {0};
+ void *schedc;
+
+ schedc = MLX5_ADDR_OF(modify_scheduling_element_in, in,
+ scheduling_context);
+ MLX5_SET(modify_scheduling_element_in, in, opcode,
+ MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT);
+ MLX5_SET(modify_scheduling_element_in, in, scheduling_element_id,
+ element_id);
+ MLX5_SET(modify_scheduling_element_in, in, modify_bitmask,
+ modify_bitmask);
+ MLX5_SET(modify_scheduling_element_in, in, scheduling_hierarchy,
+ hierarchy);
+ memcpy(schedc, ctx, MLX5_ST_SZ_BYTES(scheduling_context));
+
+ return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
+ u32 element_id)
+{
+ u32 in[MLX5_ST_SZ_DW(destroy_scheduling_element_in)] = {0};
+ u32 out[MLX5_ST_SZ_DW(destroy_scheduling_element_in)] = {0};
+
+ MLX5_SET(destroy_scheduling_element_in, in, opcode,
+ MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT);
+ MLX5_SET(destroy_scheduling_element_in, in, scheduling_element_id,
+ element_id);
+ MLX5_SET(destroy_scheduling_element_in, in, scheduling_hierarchy,
+ hierarchy);
+
+ return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
/* Finds an entry where we can register the given rate
* If the rate already exists, return the entry where it is registered,
* otherwise return the first available entry.
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
index d0bcf59..c9822e6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
@@ -29,6 +29,27 @@
To compile this driver as a module, choose M here: the
module will be called mlxsw_pci.
+config MLXSW_I2C
+ tristate "I2C bus implementation for Mellanox Technologies Switch ASICs"
+ depends on I2C && MLXSW_CORE
+ default m
+ ---help---
+ This is I2C bus implementation for Mellanox Technologies Switch ASICs.
+
+ To compile this driver as a module, choose M here: the
+ module will be called mlxsw_i2c.
+
+config MLXSW_SWITCHIB
+ tristate "Mellanox Technologies SwitchIB and SwitchIB-2 support"
+ depends on MLXSW_CORE && NET_SWITCHDEV
+ default m
+ ---help---
+ This driver supports Mellanox Technologies SwitchIB and SwitchIB-2
+ Infiniband Switch ASICs.
+
+ To compile this driver as a module, choose M here: the
+ module will be called mlxsw_switchib.
+
config MLXSW_SWITCHX2
tristate "Mellanox Technologies SwitchX-2 support"
depends on MLXSW_CORE && MLXSW_PCI && NET_SWITCHDEV
@@ -58,3 +79,14 @@
---help---
Say Y here if you want to use Data Center Bridging (DCB) in the
driver.
+
+config MLXSW_MINIMAL
+ tristate "Mellanox Technologies minimal I2C support"
+ depends on MLXSW_CORE && MLXSW_I2C
+ default m
+ ---help---
+ This driver supports I2C access for Mellanox Technologies Switch
+ ASICs.
+
+ To compile this driver as a module, choose M here: the
+ module will be called mlxsw_minimal.
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index d20ae18..2722942 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -3,6 +3,10 @@
mlxsw_core-$(CONFIG_MLXSW_CORE_HWMON) += core_hwmon.o
obj-$(CONFIG_MLXSW_PCI) += mlxsw_pci.o
mlxsw_pci-objs := pci.o
+obj-$(CONFIG_MLXSW_I2C) += mlxsw_i2c.o
+mlxsw_i2c-objs := i2c.o
+obj-$(CONFIG_MLXSW_SWITCHIB) += mlxsw_switchib.o
+mlxsw_switchib-objs := switchib.o
obj-$(CONFIG_MLXSW_SWITCHX2) += mlxsw_switchx2.o
mlxsw_switchx2-objs := switchx2.o
obj-$(CONFIG_MLXSW_SPECTRUM) += mlxsw_spectrum.o
@@ -10,3 +14,5 @@
spectrum_switchdev.o spectrum_router.o \
spectrum_kvdl.o
mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB) += spectrum_dcb.o
+obj-$(CONFIG_MLXSW_MINIMAL) += mlxsw_minimal.o
+mlxsw_minimal-objs := minimal.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 02183f6..763752f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -90,6 +90,23 @@ struct mlxsw_core_pcpu_stats {
u32 port_rx_invalid;
};
+struct mlxsw_core_port {
+ struct devlink_port devlink_port;
+ void *port_driver_priv;
+ u8 local_port;
+};
+
+void *mlxsw_core_port_driver_priv(struct mlxsw_core_port *mlxsw_core_port)
+{
+ return mlxsw_core_port->port_driver_priv;
+}
+EXPORT_SYMBOL(mlxsw_core_port_driver_priv);
+
+static bool mlxsw_core_port_check(struct mlxsw_core_port *mlxsw_core_port)
+{
+ return mlxsw_core_port->port_driver_priv != NULL;
+}
+
struct mlxsw_core {
struct mlxsw_driver *driver;
const struct mlxsw_bus *bus;
@@ -114,6 +131,7 @@ struct mlxsw_core {
} lag;
struct mlxsw_res res;
struct mlxsw_hwmon *hwmon;
+ struct mlxsw_core_port ports[MLXSW_PORT_MAX_PORTS];
unsigned long driver_priv[0];
/* driver_priv has to be always the last item */
};
@@ -580,6 +598,9 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
u64 tid;
int err;
+ if (!(mlxsw_core->bus->features & MLXSW_BUS_F_TXRX))
+ return 0;
+
/* Set the upper 32 bits of the transaction ID field to a random
* number. This allows us to discard EMADs addressed to other
* devices.
@@ -616,6 +637,9 @@ static void mlxsw_emad_fini(struct mlxsw_core *mlxsw_core)
{
char hpkt_pl[MLXSW_REG_HPKT_LEN];
+ if (!(mlxsw_core->bus->features & MLXSW_BUS_F_TXRX))
+ return;
+
mlxsw_core->emad.use_emad = false;
mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_DISCARD,
MLXSW_TRAP_ID_ETHEMAD);
@@ -920,6 +944,21 @@ static void *__dl_port(struct devlink_port *devlink_port)
return container_of(devlink_port, struct mlxsw_core_port, devlink_port);
}
+static int mlxsw_devlink_port_type_set(struct devlink_port *devlink_port,
+ enum devlink_port_type port_type)
+{
+ struct mlxsw_core *mlxsw_core = devlink_priv(devlink_port->devlink);
+ struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+ struct mlxsw_core_port *mlxsw_core_port = __dl_port(devlink_port);
+
+ if (!mlxsw_driver->port_type_set)
+ return -EOPNOTSUPP;
+
+ return mlxsw_driver->port_type_set(mlxsw_core,
+ mlxsw_core_port->local_port,
+ port_type);
+}
+
static int mlxsw_devlink_sb_port_pool_get(struct devlink_port *devlink_port,
unsigned int sb_index, u16 pool_index,
u32 *p_threshold)
@@ -928,7 +967,8 @@ static int mlxsw_devlink_sb_port_pool_get(struct devlink_port *devlink_port,
struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
struct mlxsw_core_port *mlxsw_core_port = __dl_port(devlink_port);
- if (!mlxsw_driver->sb_port_pool_get)
+ if (!mlxsw_driver->sb_port_pool_get ||
+ !mlxsw_core_port_check(mlxsw_core_port))
return -EOPNOTSUPP;
return mlxsw_driver->sb_port_pool_get(mlxsw_core_port, sb_index,
pool_index, p_threshold);
@@ -942,7 +982,8 @@ static int mlxsw_devlink_sb_port_pool_set(struct devlink_port *devlink_port,
struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
struct mlxsw_core_port *mlxsw_core_port = __dl_port(devlink_port);
- if (!mlxsw_driver->sb_port_pool_set)
+ if (!mlxsw_driver->sb_port_pool_set ||
+ !mlxsw_core_port_check(mlxsw_core_port))
return -EOPNOTSUPP;
return mlxsw_driver->sb_port_pool_set(mlxsw_core_port, sb_index,
pool_index, threshold);
@@ -958,7 +999,8 @@ mlxsw_devlink_sb_tc_pool_bind_get(struct devlink_port *devlink_port,
struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
struct mlxsw_core_port *mlxsw_core_port = __dl_port(devlink_port);
- if (!mlxsw_driver->sb_tc_pool_bind_get)
+ if (!mlxsw_driver->sb_tc_pool_bind_get ||
+ !mlxsw_core_port_check(mlxsw_core_port))
return -EOPNOTSUPP;
return mlxsw_driver->sb_tc_pool_bind_get(mlxsw_core_port, sb_index,
tc_index, pool_type,
@@ -975,7 +1017,8 @@ mlxsw_devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port,
struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
struct mlxsw_core_port *mlxsw_core_port = __dl_port(devlink_port);
- if (!mlxsw_driver->sb_tc_pool_bind_set)
+ if (!mlxsw_driver->sb_tc_pool_bind_set ||
+ !mlxsw_core_port_check(mlxsw_core_port))
return -EOPNOTSUPP;
return mlxsw_driver->sb_tc_pool_bind_set(mlxsw_core_port, sb_index,
tc_index, pool_type,
@@ -1013,7 +1056,8 @@ mlxsw_devlink_sb_occ_port_pool_get(struct devlink_port *devlink_port,
struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
struct mlxsw_core_port *mlxsw_core_port = __dl_port(devlink_port);
- if (!mlxsw_driver->sb_occ_port_pool_get)
+ if (!mlxsw_driver->sb_occ_port_pool_get ||
+ !mlxsw_core_port_check(mlxsw_core_port))
return -EOPNOTSUPP;
return mlxsw_driver->sb_occ_port_pool_get(mlxsw_core_port, sb_index,
pool_index, p_cur, p_max);
@@ -1029,7 +1073,8 @@ mlxsw_devlink_sb_occ_tc_port_bind_get(struct devlink_port *devlink_port,
struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
struct mlxsw_core_port *mlxsw_core_port = __dl_port(devlink_port);
- if (!mlxsw_driver->sb_occ_tc_port_bind_get)
+ if (!mlxsw_driver->sb_occ_tc_port_bind_get ||
+ !mlxsw_core_port_check(mlxsw_core_port))
return -EOPNOTSUPP;
return mlxsw_driver->sb_occ_tc_port_bind_get(mlxsw_core_port,
sb_index, tc_index,
@@ -1037,6 +1082,7 @@ mlxsw_devlink_sb_occ_tc_port_bind_get(struct devlink_port *devlink_port,
}
static const struct devlink_ops mlxsw_devlink_ops = {
+ .port_type_set = mlxsw_devlink_port_type_set,
.port_split = mlxsw_devlink_port_split,
.port_unsplit = mlxsw_devlink_port_unsplit,
.sb_pool_get = mlxsw_devlink_sb_pool_get,
@@ -1116,9 +1162,11 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
if (err)
goto err_hwmon_init;
- err = mlxsw_driver->init(mlxsw_core, mlxsw_bus_info);
- if (err)
- goto err_driver_init;
+ if (mlxsw_driver->init) {
+ err = mlxsw_driver->init(mlxsw_core, mlxsw_bus_info);
+ if (err)
+ goto err_driver_init;
+ }
err = mlxsw_core_debugfs_init(mlxsw_core);
if (err)
@@ -1127,7 +1175,8 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
return 0;
err_debugfs_init:
- mlxsw_core->driver->fini(mlxsw_core);
+ if (mlxsw_core->driver->fini)
+ mlxsw_core->driver->fini(mlxsw_core);
err_driver_init:
err_hwmon_init:
devlink_unregister(devlink);
@@ -1153,7 +1202,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core)
struct devlink *devlink = priv_to_devlink(mlxsw_core);
mlxsw_core_debugfs_fini(mlxsw_core);
- mlxsw_core->driver->fini(mlxsw_core);
+ if (mlxsw_core->driver->fini)
+ mlxsw_core->driver->fini(mlxsw_core);
devlink_unregister(devlink);
mlxsw_emad_fini(mlxsw_core);
mlxsw_core->bus->fini(mlxsw_core->bus_priv);
@@ -1656,28 +1706,83 @@ u64 mlxsw_core_res_get(struct mlxsw_core *mlxsw_core,
}
EXPORT_SYMBOL(mlxsw_core_res_get);
-int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core,
- struct mlxsw_core_port *mlxsw_core_port, u8 local_port,
- struct net_device *dev, bool split, u32 split_group)
+int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port)
{
struct devlink *devlink = priv_to_devlink(mlxsw_core);
+ struct mlxsw_core_port *mlxsw_core_port =
+ &mlxsw_core->ports[local_port];
struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port;
+ int err;
- if (split)
- devlink_port_split_set(devlink_port, split_group);
- devlink_port_type_eth_set(devlink_port, dev);
- return devlink_port_register(devlink, devlink_port, local_port);
+ mlxsw_core_port->local_port = local_port;
+ err = devlink_port_register(devlink, devlink_port, local_port);
+ if (err)
+ memset(mlxsw_core_port, 0, sizeof(*mlxsw_core_port));
+ return err;
}
EXPORT_SYMBOL(mlxsw_core_port_init);
-void mlxsw_core_port_fini(struct mlxsw_core_port *mlxsw_core_port)
+void mlxsw_core_port_fini(struct mlxsw_core *mlxsw_core, u8 local_port)
{
+ struct mlxsw_core_port *mlxsw_core_port =
+ &mlxsw_core->ports[local_port];
struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port;
devlink_port_unregister(devlink_port);
+ memset(mlxsw_core_port, 0, sizeof(*mlxsw_core_port));
}
EXPORT_SYMBOL(mlxsw_core_port_fini);
+void mlxsw_core_port_eth_set(struct mlxsw_core *mlxsw_core, u8 local_port,
+ void *port_driver_priv, struct net_device *dev,
+ bool split, u32 split_group)
+{
+ struct mlxsw_core_port *mlxsw_core_port =
+ &mlxsw_core->ports[local_port];
+ struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port;
+
+ mlxsw_core_port->port_driver_priv = port_driver_priv;
+ if (split)
+ devlink_port_split_set(devlink_port, split_group);
+ devlink_port_type_eth_set(devlink_port, dev);
+}
+EXPORT_SYMBOL(mlxsw_core_port_eth_set);
+
+void mlxsw_core_port_ib_set(struct mlxsw_core *mlxsw_core, u8 local_port,
+ void *port_driver_priv)
+{
+ struct mlxsw_core_port *mlxsw_core_port =
+ &mlxsw_core->ports[local_port];
+ struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port;
+
+ mlxsw_core_port->port_driver_priv = port_driver_priv;
+ devlink_port_type_ib_set(devlink_port, NULL);
+}
+EXPORT_SYMBOL(mlxsw_core_port_ib_set);
+
+void mlxsw_core_port_clear(struct mlxsw_core *mlxsw_core, u8 local_port,
+ void *port_driver_priv)
+{
+ struct mlxsw_core_port *mlxsw_core_port =
+ &mlxsw_core->ports[local_port];
+ struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port;
+
+ mlxsw_core_port->port_driver_priv = port_driver_priv;
+ devlink_port_type_clear(devlink_port);
+}
+EXPORT_SYMBOL(mlxsw_core_port_clear);
+
+enum devlink_port_type mlxsw_core_port_type_get(struct mlxsw_core *mlxsw_core,
+ u8 local_port)
+{
+ struct mlxsw_core_port *mlxsw_core_port =
+ &mlxsw_core->ports[local_port];
+ struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port;
+
+ return devlink_port->type;
+}
+EXPORT_SYMBOL(mlxsw_core_port_type_get);
+
static void mlxsw_core_buf_dump_dbg(struct mlxsw_core *mlxsw_core,
const char *buf, size_t size)
{
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index 0cf721c..f7a4d838 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -52,6 +52,7 @@
#include "resources.h"
struct mlxsw_core;
+struct mlxsw_core_port;
struct mlxsw_driver;
struct mlxsw_bus;
struct mlxsw_bus_info;
@@ -141,23 +142,18 @@ u8 mlxsw_core_lag_mapping_get(struct mlxsw_core *mlxsw_core,
void mlxsw_core_lag_mapping_clear(struct mlxsw_core *mlxsw_core,
u16 lag_id, u8 local_port);
-struct mlxsw_core_port {
- struct devlink_port devlink_port;
-};
-
-static inline void *
-mlxsw_core_port_driver_priv(struct mlxsw_core_port *mlxsw_core_port)
-{
- /* mlxsw_core_port is ensured to always be the first field in driver
- * port structure.
- */
- return mlxsw_core_port;
-}
-
-int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core,
- struct mlxsw_core_port *mlxsw_core_port, u8 local_port,
- struct net_device *dev, bool split, u32 split_group);
-void mlxsw_core_port_fini(struct mlxsw_core_port *mlxsw_core_port);
+void *mlxsw_core_port_driver_priv(struct mlxsw_core_port *mlxsw_core_port);
+int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port);
+void mlxsw_core_port_fini(struct mlxsw_core *mlxsw_core, u8 local_port);
+void mlxsw_core_port_eth_set(struct mlxsw_core *mlxsw_core, u8 local_port,
+ void *port_driver_priv, struct net_device *dev,
+ bool split, u32 split_group);
+void mlxsw_core_port_ib_set(struct mlxsw_core *mlxsw_core, u8 local_port,
+ void *port_driver_priv);
+void mlxsw_core_port_clear(struct mlxsw_core *mlxsw_core, u8 local_port,
+ void *port_driver_priv);
+enum devlink_port_type mlxsw_core_port_type_get(struct mlxsw_core *mlxsw_core,
+ u8 local_port);
int mlxsw_core_schedule_dw(struct delayed_work *dwork, unsigned long delay);
@@ -218,6 +214,8 @@ struct mlxsw_driver {
int (*init)(struct mlxsw_core *mlxsw_core,
const struct mlxsw_bus_info *mlxsw_bus_info);
void (*fini)(struct mlxsw_core *mlxsw_core);
+ int (*port_type_set)(struct mlxsw_core *mlxsw_core, u8 local_port,
+ enum devlink_port_type new_type);
int (*port_split)(struct mlxsw_core *mlxsw_core, u8 local_port,
unsigned int count);
int (*port_unsplit)(struct mlxsw_core *mlxsw_core, u8 local_port);
@@ -270,6 +268,8 @@ u64 mlxsw_core_res_get(struct mlxsw_core *mlxsw_core,
#define MLXSW_CORE_RES_GET(res, short_res_id) \
mlxsw_core_res_get(res, MLXSW_RES_ID_##short_res_id)
+#define MLXSW_BUS_F_TXRX BIT(0)
+
struct mlxsw_bus {
const char *kind;
int (*init)(void *bus_priv, struct mlxsw_core *mlxsw_core,
@@ -285,6 +285,7 @@ struct mlxsw_bus {
char *in_mbox, size_t in_mbox_size,
char *out_mbox, size_t out_mbox_size,
u8 *p_status);
+ u8 features;
};
struct mlxsw_bus_info {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
index 1ac8bf1..ab710e3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
@@ -262,7 +262,7 @@ static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon,
static int mlxsw_hwmon_temp_init(struct mlxsw_hwmon *mlxsw_hwmon)
{
- char mtcap_pl[MLXSW_REG_MTCAP_LEN];
+ char mtcap_pl[MLXSW_REG_MTCAP_LEN] = {0};
char mtmp_pl[MLXSW_REG_MTMP_LEN];
u8 sensor_count;
int i;
@@ -295,7 +295,7 @@ static int mlxsw_hwmon_temp_init(struct mlxsw_hwmon *mlxsw_hwmon)
static int mlxsw_hwmon_fans_init(struct mlxsw_hwmon *mlxsw_hwmon)
{
- char mfcr_pl[MLXSW_REG_MFCR_LEN];
+ char mfcr_pl[MLXSW_REG_MFCR_LEN] = {0};
enum mlxsw_reg_mfcr_pwm_frequency freq;
unsigned int type_index;
unsigned int num;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
new file mode 100644
index 0000000..e50c8db
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
@@ -0,0 +1,582 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/i2c.c
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Vadim Pasternak <vadimp@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/slab.h>
+
+#include "cmd.h"
+#include "core.h"
+#include "i2c.h"
+
+static const char mlxsw_i2c_driver_name[] = "mlxsw_i2c";
+
+#define MLXSW_I2C_CIR2_BASE 0x72000
+#define MLXSW_I2C_CIR_STATUS_OFF 0x18
+#define MLXSW_I2C_CIR2_OFF_STATUS (MLXSW_I2C_CIR2_BASE + \
+ MLXSW_I2C_CIR_STATUS_OFF)
+#define MLXSW_I2C_OPMOD_SHIFT 12
+#define MLXSW_I2C_GO_BIT_SHIFT 23
+#define MLXSW_I2C_CIR_CTRL_STATUS_SHIFT 24
+#define MLXSW_I2C_GO_BIT BIT(MLXSW_I2C_GO_BIT_SHIFT)
+#define MLXSW_I2C_GO_OPMODE BIT(MLXSW_I2C_OPMOD_SHIFT)
+#define MLXSW_I2C_SET_IMM_CMD (MLXSW_I2C_GO_OPMODE | \
+ MLXSW_CMD_OPCODE_QUERY_FW)
+#define MLXSW_I2C_PUSH_IMM_CMD (MLXSW_I2C_GO_BIT | \
+ MLXSW_I2C_SET_IMM_CMD)
+#define MLXSW_I2C_SET_CMD (MLXSW_CMD_OPCODE_ACCESS_REG)
+#define MLXSW_I2C_PUSH_CMD (MLXSW_I2C_GO_BIT | MLXSW_I2C_SET_CMD)
+#define MLXSW_I2C_TLV_HDR_SIZE 0x10
+#define MLXSW_I2C_ADDR_WIDTH 4
+#define MLXSW_I2C_PUSH_CMD_SIZE (MLXSW_I2C_ADDR_WIDTH + 4)
+#define MLXSW_I2C_READ_SEMA_SIZE 4
+#define MLXSW_I2C_PREP_SIZE (MLXSW_I2C_ADDR_WIDTH + 28)
+#define MLXSW_I2C_MBOX_SIZE 20
+#define MLXSW_I2C_MBOX_OUT_PARAM_OFF 12
+#define MLXSW_I2C_MAX_BUFF_SIZE 32
+#define MLXSW_I2C_MBOX_OFFSET_BITS 20
+#define MLXSW_I2C_MBOX_SIZE_BITS 12
+#define MLXSW_I2C_ADDR_BUF_SIZE 4
+#define MLXSW_I2C_BLK_MAX 32
+#define MLXSW_I2C_RETRY 5
+#define MLXSW_I2C_TIMEOUT_MSECS 5000
+
+/**
+ * struct mlxsw_i2c - device private data:
+ * @cmd.mb_size_in: input mailbox size;
+ * @cmd.mb_off_in: input mailbox offset in register space;
+ * @cmd.mb_size_out: output mailbox size;
+ * @cmd.mb_off_out: output mailbox offset in register space;
+ * @cmd.lock: command execution lock;
+ * @dev: I2C device;
+ * @core: switch core pointer;
+ * @bus_info: bus info block;
+ */
+struct mlxsw_i2c {
+ struct {
+ u32 mb_size_in;
+ u32 mb_off_in;
+ u32 mb_size_out;
+ u32 mb_off_out;
+ struct mutex lock;
+ } cmd;
+ struct device *dev;
+ struct mlxsw_core *core;
+ struct mlxsw_bus_info bus_info;
+};
+
+#define MLXSW_I2C_READ_MSG(_client, _addr_buf, _buf, _len) { \
+ { .addr = (_client)->addr, \
+ .buf = (_addr_buf), \
+ .len = MLXSW_I2C_ADDR_BUF_SIZE, \
+ .flags = 0 }, \
+ { .addr = (_client)->addr, \
+ .buf = (_buf), \
+ .len = (_len), \
+ .flags = I2C_M_RD } }
+
+#define MLXSW_I2C_WRITE_MSG(_client, _buf, _len) \
+ { .addr = (_client)->addr, \
+ .buf = (u8 *)(_buf), \
+ .len = (_len), \
+ .flags = 0 }
+
+/* Routine converts in and out mail boxes offset and size. */
+static inline void
+mlxsw_i2c_convert_mbox(struct mlxsw_i2c *mlxsw_i2c, u8 *buf)
+{
+ u32 tmp;
+
+ /* Local in/out mailboxes: 20 bits for offset, 12 for size */
+ tmp = be32_to_cpup((__be32 *) buf);
+ mlxsw_i2c->cmd.mb_off_in = tmp &
+ GENMASK(MLXSW_I2C_MBOX_OFFSET_BITS - 1, 0);
+ mlxsw_i2c->cmd.mb_size_in = (tmp & GENMASK(31,
+ MLXSW_I2C_MBOX_OFFSET_BITS)) >>
+ MLXSW_I2C_MBOX_OFFSET_BITS;
+
+ tmp = be32_to_cpup((__be32 *) (buf + MLXSW_I2C_ADDR_WIDTH));
+ mlxsw_i2c->cmd.mb_off_out = tmp &
+ GENMASK(MLXSW_I2C_MBOX_OFFSET_BITS - 1, 0);
+ mlxsw_i2c->cmd.mb_size_out = (tmp & GENMASK(31,
+ MLXSW_I2C_MBOX_OFFSET_BITS)) >>
+ MLXSW_I2C_MBOX_OFFSET_BITS;
+}
+
+/* Routine obtains register size from mail box buffer. */
+static inline int mlxsw_i2c_get_reg_size(u8 *in_mbox)
+{
+ u16 tmp = be16_to_cpup((__be16 *) (in_mbox + MLXSW_I2C_TLV_HDR_SIZE));
+
+ return (tmp & 0x7ff) * 4 + MLXSW_I2C_TLV_HDR_SIZE;
+}
+
+/* Routine sets I2C device internal offset in the transaction buffer. */
+static inline void mlxsw_i2c_set_slave_addr(u8 *buf, u32 off)
+{
+ __be32 *val = (__be32 *) buf;
+
+ *val = htonl(off);
+}
+
+/* Routine waits until go bit is cleared. */
+static int mlxsw_i2c_wait_go_bit(struct i2c_client *client,
+ struct mlxsw_i2c *mlxsw_i2c, u8 *p_status)
+{
+ u8 addr_buf[MLXSW_I2C_ADDR_BUF_SIZE];
+ u8 buf[MLXSW_I2C_READ_SEMA_SIZE];
+ int len = MLXSW_I2C_READ_SEMA_SIZE;
+ struct i2c_msg read_sema[] =
+ MLXSW_I2C_READ_MSG(client, addr_buf, buf, len);
+ bool wait_done = false;
+ unsigned long end;
+ int i = 0, err;
+
+ mlxsw_i2c_set_slave_addr(addr_buf, MLXSW_I2C_CIR2_OFF_STATUS);
+
+ end = jiffies + msecs_to_jiffies(MLXSW_I2C_TIMEOUT_MSECS);
+ do {
+ u32 ctrl;
+
+ err = i2c_transfer(client->adapter, read_sema,
+ ARRAY_SIZE(read_sema));
+
+ ctrl = be32_to_cpu(*(__be32 *) buf);
+ if (err == ARRAY_SIZE(read_sema)) {
+ if (!(ctrl & MLXSW_I2C_GO_BIT)) {
+ wait_done = true;
+ *p_status = ctrl >>
+ MLXSW_I2C_CIR_CTRL_STATUS_SHIFT;
+ break;
+ }
+ }
+ cond_resched();
+ } while ((time_before(jiffies, end)) || (i++ < MLXSW_I2C_RETRY));
+
+ if (wait_done) {
+ if (*p_status)
+ err = -EIO;
+ } else {
+ return -ETIMEDOUT;
+ }
+
+ return err > 0 ? 0 : err;
+}
+
+/* Routine posts a command to ASIC though mail box. */
+static int mlxsw_i2c_write_cmd(struct i2c_client *client,
+ struct mlxsw_i2c *mlxsw_i2c,
+ int immediate)
+{
+ __be32 push_cmd_buf[MLXSW_I2C_PUSH_CMD_SIZE / 4] = {
+ 0, cpu_to_be32(MLXSW_I2C_PUSH_IMM_CMD)
+ };
+ __be32 prep_cmd_buf[MLXSW_I2C_PREP_SIZE / 4] = {
+ 0, 0, 0, 0, 0, 0,
+ cpu_to_be32(client->adapter->nr & 0xffff),
+ cpu_to_be32(MLXSW_I2C_SET_IMM_CMD)
+ };
+ struct i2c_msg push_cmd =
+ MLXSW_I2C_WRITE_MSG(client, push_cmd_buf,
+ MLXSW_I2C_PUSH_CMD_SIZE);
+ struct i2c_msg prep_cmd =
+ MLXSW_I2C_WRITE_MSG(client, prep_cmd_buf, MLXSW_I2C_PREP_SIZE);
+ int err;
+
+ if (!immediate) {
+ push_cmd_buf[1] = cpu_to_be32(MLXSW_I2C_PUSH_CMD);
+ prep_cmd_buf[7] = cpu_to_be32(MLXSW_I2C_SET_CMD);
+ }
+ mlxsw_i2c_set_slave_addr((u8 *)prep_cmd_buf,
+ MLXSW_I2C_CIR2_BASE);
+ mlxsw_i2c_set_slave_addr((u8 *)push_cmd_buf,
+ MLXSW_I2C_CIR2_OFF_STATUS);
+
+ /* Prepare Command Interface Register for transaction */
+ err = i2c_transfer(client->adapter, &prep_cmd, 1);
+ if (err < 0)
+ return err;
+ else if (err != 1)
+ return -EIO;
+
+ /* Write out Command Interface Register GO bit to push transaction */
+ err = i2c_transfer(client->adapter, &push_cmd, 1);
+ if (err < 0)
+ return err;
+ else if (err != 1)
+ return -EIO;
+
+ return 0;
+}
+
+/* Routine obtains mail box offsets from ASIC register space. */
+static int mlxsw_i2c_get_mbox(struct i2c_client *client,
+ struct mlxsw_i2c *mlxsw_i2c)
+{
+ u8 addr_buf[MLXSW_I2C_ADDR_BUF_SIZE];
+ u8 buf[MLXSW_I2C_MBOX_SIZE];
+ struct i2c_msg mbox_cmd[] =
+ MLXSW_I2C_READ_MSG(client, addr_buf, buf, MLXSW_I2C_MBOX_SIZE);
+ int err;
+
+ /* Read mail boxes offsets. */
+ mlxsw_i2c_set_slave_addr(addr_buf, MLXSW_I2C_CIR2_BASE);
+ err = i2c_transfer(client->adapter, mbox_cmd, 2);
+ if (err != 2) {
+ dev_err(&client->dev, "Could not obtain mail boxes\n");
+ if (!err)
+ return -EIO;
+ else
+ return err;
+ }
+
+ /* Convert mail boxes. */
+ mlxsw_i2c_convert_mbox(mlxsw_i2c, &buf[MLXSW_I2C_MBOX_OUT_PARAM_OFF]);
+
+ return err;
+}
+
+/* Routine sends I2C write transaction to ASIC device. */
+static int
+mlxsw_i2c_write(struct device *dev, size_t in_mbox_size, u8 *in_mbox, int num,
+ u8 *p_status)
+{
+ struct i2c_client *client = to_i2c_client(dev);
+ struct mlxsw_i2c *mlxsw_i2c = i2c_get_clientdata(client);
+ unsigned long timeout = msecs_to_jiffies(MLXSW_I2C_TIMEOUT_MSECS);
+ u8 tran_buf[MLXSW_I2C_MAX_BUFF_SIZE + MLXSW_I2C_ADDR_BUF_SIZE];
+ int off = mlxsw_i2c->cmd.mb_off_in, chunk_size, i, j;
+ unsigned long end;
+ struct i2c_msg write_tran =
+ MLXSW_I2C_WRITE_MSG(client, tran_buf, MLXSW_I2C_PUSH_CMD_SIZE);
+ int err;
+
+ for (i = 0; i < num; i++) {
+ chunk_size = (in_mbox_size > MLXSW_I2C_BLK_MAX) ?
+ MLXSW_I2C_BLK_MAX : in_mbox_size;
+ write_tran.len = MLXSW_I2C_ADDR_WIDTH + chunk_size;
+ mlxsw_i2c_set_slave_addr(tran_buf, off);
+ memcpy(&tran_buf[MLXSW_I2C_ADDR_BUF_SIZE], in_mbox +
+ chunk_size * i, chunk_size);
+
+ j = 0;
+ end = jiffies + timeout;
+ do {
+ err = i2c_transfer(client->adapter, &write_tran, 1);
+ if (err == 1)
+ break;
+
+ cond_resched();
+ } while ((time_before(jiffies, end)) ||
+ (j++ < MLXSW_I2C_RETRY));
+
+ if (err != 1) {
+ if (!err)
+ err = -EIO;
+ return err;
+ }
+
+ off += chunk_size;
+ in_mbox_size -= chunk_size;
+ }
+
+ /* Prepare and write out Command Interface Register for transaction. */
+ err = mlxsw_i2c_write_cmd(client, mlxsw_i2c, 0);
+ if (err) {
+ dev_err(&client->dev, "Could not start transaction");
+ return -EIO;
+ }
+
+ /* Wait until go bit is cleared. */
+ err = mlxsw_i2c_wait_go_bit(client, mlxsw_i2c, p_status);
+ if (err) {
+ dev_err(&client->dev, "HW semaphore is not released");
+ return err;
+ }
+
+ /* Validate transaction completion status. */
+ if (*p_status) {
+ dev_err(&client->dev, "Bad transaction completion status %x\n",
+ *p_status);
+ return -EIO;
+ }
+
+ return err > 0 ? 0 : err;
+}
+
+/* Routine executes I2C command. */
+static int
+mlxsw_i2c_cmd(struct device *dev, size_t in_mbox_size, u8 *in_mbox,
+ size_t out_mbox_size, u8 *out_mbox, u8 *status)
+{
+ struct i2c_client *client = to_i2c_client(dev);
+ struct mlxsw_i2c *mlxsw_i2c = i2c_get_clientdata(client);
+ unsigned long timeout = msecs_to_jiffies(MLXSW_I2C_TIMEOUT_MSECS);
+ u8 tran_buf[MLXSW_I2C_ADDR_BUF_SIZE];
+ int num, chunk_size, reg_size, i, j;
+ int off = mlxsw_i2c->cmd.mb_off_out;
+ unsigned long end;
+ struct i2c_msg read_tran[] =
+ MLXSW_I2C_READ_MSG(client, tran_buf, NULL, 0);
+ int err;
+
+ WARN_ON(in_mbox_size % sizeof(u32) || out_mbox_size % sizeof(u32));
+
+ reg_size = mlxsw_i2c_get_reg_size(in_mbox);
+ num = reg_size / MLXSW_I2C_BLK_MAX;
+ if (reg_size % MLXSW_I2C_BLK_MAX)
+ num++;
+
+ if (mutex_lock_interruptible(&mlxsw_i2c->cmd.lock) < 0) {
+ dev_err(&client->dev, "Could not acquire lock");
+ return -EINVAL;
+ }
+
+ err = mlxsw_i2c_write(dev, reg_size, in_mbox, num, status);
+ if (err)
+ goto cmd_fail;
+
+ /* No out mailbox is case of write transaction. */
+ if (!out_mbox) {
+ mutex_unlock(&mlxsw_i2c->cmd.lock);
+ return 0;
+ }
+
+ /* Send read transaction to get output mailbox content. */
+ read_tran[1].buf = out_mbox;
+ for (i = 0; i < num; i++) {
+ chunk_size = (reg_size > MLXSW_I2C_BLK_MAX) ?
+ MLXSW_I2C_BLK_MAX : reg_size;
+ read_tran[1].len = chunk_size;
+ mlxsw_i2c_set_slave_addr(tran_buf, off);
+
+ j = 0;
+ end = jiffies + timeout;
+ do {
+ err = i2c_transfer(client->adapter, read_tran,
+ ARRAY_SIZE(read_tran));
+ if (err == ARRAY_SIZE(read_tran))
+ break;
+
+ cond_resched();
+ } while ((time_before(jiffies, end)) ||
+ (j++ < MLXSW_I2C_RETRY));
+
+ if (err != ARRAY_SIZE(read_tran)) {
+ if (!err)
+ err = -EIO;
+
+ goto cmd_fail;
+ }
+
+ off += chunk_size;
+ reg_size -= chunk_size;
+ read_tran[1].buf += chunk_size;
+ }
+
+ mutex_unlock(&mlxsw_i2c->cmd.lock);
+
+ return 0;
+
+cmd_fail:
+ mutex_unlock(&mlxsw_i2c->cmd.lock);
+ return err;
+}
+
+static int mlxsw_i2c_cmd_exec(void *bus_priv, u16 opcode, u8 opcode_mod,
+ u32 in_mod, bool out_mbox_direct,
+ char *in_mbox, size_t in_mbox_size,
+ char *out_mbox, size_t out_mbox_size,
+ u8 *status)
+{
+ struct mlxsw_i2c *mlxsw_i2c = bus_priv;
+
+ return mlxsw_i2c_cmd(mlxsw_i2c->dev, in_mbox_size, in_mbox,
+ out_mbox_size, out_mbox, status);
+}
+
+static bool mlxsw_i2c_skb_transmit_busy(void *bus_priv,
+ const struct mlxsw_tx_info *tx_info)
+{
+ return false;
+}
+
+static int mlxsw_i2c_skb_transmit(void *bus_priv, struct sk_buff *skb,
+ const struct mlxsw_tx_info *tx_info)
+{
+ return 0;
+}
+
+static int
+mlxsw_i2c_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
+ const struct mlxsw_config_profile *profile,
+ struct mlxsw_res *resources)
+{
+ struct mlxsw_i2c *mlxsw_i2c = bus_priv;
+
+ mlxsw_i2c->core = mlxsw_core;
+
+ return 0;
+}
+
+static void mlxsw_i2c_fini(void *bus_priv)
+{
+ struct mlxsw_i2c *mlxsw_i2c = bus_priv;
+
+ mlxsw_i2c->core = NULL;
+}
+
+static const struct mlxsw_bus mlxsw_i2c_bus = {
+ .kind = "i2c",
+ .init = mlxsw_i2c_init,
+ .fini = mlxsw_i2c_fini,
+ .skb_transmit_busy = mlxsw_i2c_skb_transmit_busy,
+ .skb_transmit = mlxsw_i2c_skb_transmit,
+ .cmd_exec = mlxsw_i2c_cmd_exec,
+};
+
+static int mlxsw_i2c_probe(struct i2c_client *client,
+ const struct i2c_device_id *id)
+{
+ struct mlxsw_i2c *mlxsw_i2c;
+ u8 status;
+ int err;
+
+ mlxsw_i2c = devm_kzalloc(&client->dev, sizeof(*mlxsw_i2c), GFP_KERNEL);
+ if (!mlxsw_i2c)
+ return -ENOMEM;
+
+ i2c_set_clientdata(client, mlxsw_i2c);
+ mutex_init(&mlxsw_i2c->cmd.lock);
+
+ /* In order to use mailboxes through the i2c, special area is reserved
+ * on the i2c address space that can be used for input and output
+ * mailboxes. Such mailboxes are called local mailboxes. When using a
+ * local mailbox, software should specify 0 as the Input/Output
+ * parameters. The location of the Local Mailbox addresses on the i2c
+ * space can be retrieved through the QUERY_FW command.
+ * For this purpose QUERY_FW is to be issued with opcode modifier equal
+ * 0x01. For such command the output parameter is an immediate value.
+ * Here QUERY_FW command is invoked for ASIC probing and for getting
+ * local mailboxes addresses from immedate output parameters.
+ */
+
+ /* Prepare and write out Command Interface Register for transaction */
+ err = mlxsw_i2c_write_cmd(client, mlxsw_i2c, 1);
+ if (err) {
+ dev_err(&client->dev, "Could not start transaction");
+ goto errout;
+ }
+
+ /* Wait until go bit is cleared. */
+ err = mlxsw_i2c_wait_go_bit(client, mlxsw_i2c, &status);
+ if (err) {
+ dev_err(&client->dev, "HW semaphore is not released");
+ goto errout;
+ }
+
+ /* Validate transaction completion status. */
+ if (status) {
+ dev_err(&client->dev, "Bad transaction completion status %x\n",
+ status);
+ err = -EIO;
+ goto errout;
+ }
+
+ /* Get mailbox offsets. */
+ err = mlxsw_i2c_get_mbox(client, mlxsw_i2c);
+ if (err < 0) {
+ dev_err(&client->dev, "Fail to get mailboxes\n");
+ goto errout;
+ }
+
+ dev_info(&client->dev, "%s mb size=%x off=0x%08x out mb size=%x off=0x%08x\n",
+ id->name, mlxsw_i2c->cmd.mb_size_in,
+ mlxsw_i2c->cmd.mb_off_in, mlxsw_i2c->cmd.mb_size_out,
+ mlxsw_i2c->cmd.mb_off_out);
+
+ /* Register device bus. */
+ mlxsw_i2c->bus_info.device_kind = id->name;
+ mlxsw_i2c->bus_info.device_name = client->name;
+ mlxsw_i2c->bus_info.dev = &client->dev;
+ mlxsw_i2c->dev = &client->dev;
+
+ err = mlxsw_core_bus_device_register(&mlxsw_i2c->bus_info,
+ &mlxsw_i2c_bus, mlxsw_i2c);
+ if (err) {
+ dev_err(&client->dev, "Fail to register core bus\n");
+ return err;
+ }
+
+ return 0;
+
+errout:
+ i2c_set_clientdata(client, NULL);
+
+ return err;
+}
+
+static int mlxsw_i2c_remove(struct i2c_client *client)
+{
+ struct mlxsw_i2c *mlxsw_i2c = i2c_get_clientdata(client);
+
+ mlxsw_core_bus_device_unregister(mlxsw_i2c->core);
+ mutex_destroy(&mlxsw_i2c->cmd.lock);
+
+ return 0;
+}
+
+int mlxsw_i2c_driver_register(struct i2c_driver *i2c_driver)
+{
+ i2c_driver->probe = mlxsw_i2c_probe;
+ i2c_driver->remove = mlxsw_i2c_remove;
+ return i2c_add_driver(i2c_driver);
+}
+EXPORT_SYMBOL(mlxsw_i2c_driver_register);
+
+void mlxsw_i2c_driver_unregister(struct i2c_driver *i2c_driver)
+{
+ i2c_del_driver(i2c_driver);
+}
+EXPORT_SYMBOL(mlxsw_i2c_driver_unregister);
+
+MODULE_AUTHOR("Vadim Pasternak <vadimp@mellanox.com>");
+MODULE_DESCRIPTION("Mellanox switch I2C interface driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.h b/drivers/net/ethernet/mellanox/mlxsw/i2c.h
new file mode 100644
index 0000000..daa24b2
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.h
@@ -0,0 +1,60 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/i2c.h
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Vadim Pasternak <vadimp@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_I2C_H
+#define _MLXSW_I2C_H
+
+#include <linux/i2c.h>
+
+#if IS_ENABLED(CONFIG_MLXSW_I2C)
+
+int mlxsw_i2c_driver_register(struct i2c_driver *i2c_driver);
+void mlxsw_i2c_driver_unregister(struct i2c_driver *i2c_driver);
+
+#else
+
+static inline int
+mlxsw_i2c_driver_register(struct i2c_driver *i2c_driver)
+{
+ return -ENODEV;
+}
+
+static inline void
+mlxsw_i2c_driver_unregister(struct i2c_driver *i2c_driver)
+{
+}
+
+#endif
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/ib.h b/drivers/net/ethernet/mellanox/mlxsw/ib.h
new file mode 100644
index 0000000..ce313aa
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/ib.h
@@ -0,0 +1,39 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/ib.h
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Elad Raz <eladr@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef _MLXSW_IB_H
+#define _MLXSW_IB_H
+
+#define MLXSW_IB_DEFAULT_MTU 4096
+
+#endif /* _MLXSW_IB_H */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
new file mode 100644
index 0000000..3dd1626
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
@@ -0,0 +1,97 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/minimal.c
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Vadim Pasternak <vadimp@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/i2c.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/types.h>
+
+#include "core.h"
+#include "i2c.h"
+
+static const char mlxsw_minimal_driver_name[] = "mlxsw_minimal";
+
+static const struct mlxsw_config_profile mlxsw_minimal_config_profile;
+
+static struct mlxsw_driver mlxsw_minimal_driver = {
+ .kind = mlxsw_minimal_driver_name,
+ .priv_size = 1,
+ .profile = &mlxsw_minimal_config_profile,
+};
+
+static const struct i2c_device_id mlxsw_minimal_i2c_id[] = {
+ { "mlxsw_minimal", 0},
+ { },
+};
+
+static struct i2c_driver mlxsw_minimal_i2c_driver = {
+ .driver.name = "mlxsw_minimal",
+ .class = I2C_CLASS_HWMON,
+ .id_table = mlxsw_minimal_i2c_id,
+};
+
+static int __init mlxsw_minimal_module_init(void)
+{
+ int err;
+
+ err = mlxsw_core_driver_register(&mlxsw_minimal_driver);
+ if (err)
+ return err;
+
+ err = mlxsw_i2c_driver_register(&mlxsw_minimal_i2c_driver);
+ if (err)
+ goto err_i2c_driver_register;
+
+ return 0;
+
+err_i2c_driver_register:
+ mlxsw_core_driver_unregister(&mlxsw_minimal_driver);
+
+ return err;
+}
+
+static void __exit mlxsw_minimal_module_exit(void)
+{
+ mlxsw_i2c_driver_unregister(&mlxsw_minimal_i2c_driver);
+ mlxsw_core_driver_unregister(&mlxsw_minimal_driver);
+}
+
+module_init(mlxsw_minimal_module_init);
+module_exit(mlxsw_minimal_module_exit);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Vadim Pasternak <vadimp@mellanox.com>");
+MODULE_DESCRIPTION("Mellanox minimal driver");
+MODULE_DEVICE_TABLE(i2c, mlxsw_minimal_i2c_id);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 63d89f7..a223c85 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1755,13 +1755,20 @@ static const struct mlxsw_bus mlxsw_pci_bus = {
.skb_transmit_busy = mlxsw_pci_skb_transmit_busy,
.skb_transmit = mlxsw_pci_skb_transmit,
.cmd_exec = mlxsw_pci_cmd_exec,
+ .features = MLXSW_BUS_F_TXRX,
};
-static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci)
+static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci,
+ const struct pci_device_id *id)
{
unsigned long end;
mlxsw_pci_write32(mlxsw_pci, SW_RESET, MLXSW_PCI_SW_RESET_RST_BIT);
+ if (id->device == PCI_DEVICE_ID_MELLANOX_SWITCHX2) {
+ msleep(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS);
+ return 0;
+ }
+
wmb(); /* reset needs to be written before we read control register */
end = jiffies + msecs_to_jiffies(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS);
do {
@@ -1829,7 +1836,7 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
mlxsw_pci->pdev = pdev;
pci_set_drvdata(pdev, mlxsw_pci);
- err = mlxsw_pci_sw_reset(mlxsw_pci);
+ err = mlxsw_pci_sw_reset(mlxsw_pci, id);
if (err) {
dev_err(&pdev->dev, "Software reset failed\n");
goto err_sw_reset;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h
index 35a0011..d655823 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h
@@ -39,6 +39,8 @@
#define PCI_DEVICE_ID_MELLANOX_SWITCHX2 0xc738
#define PCI_DEVICE_ID_MELLANOX_SPECTRUM 0xcb84
+#define PCI_DEVICE_ID_MELLANOX_SWITCHIB 0xcb20
+#define PCI_DEVICE_ID_MELLANOX_SWITCHIB2 0xcf08
#if IS_ENABLED(CONFIG_MLXSW_PCI)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index 708736f..d147ddd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -60,7 +60,7 @@
#define MLXSW_PCI_SW_RESET_RST_BIT BIT(0)
#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 5000
#define MLXSW_PCI_FW_READY 0xA1844
-#define MLXSW_PCI_FW_READY_MASK 0xFF
+#define MLXSW_PCI_FW_READY_MASK 0xFFFF
#define MLXSW_PCI_FW_READY_MAGIC 0x5E
#define MLXSW_PCI_DOORBELL_SDQ_OFFSET 0x000
diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h
index af371a8..3d42146 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/port.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/port.h
@@ -44,6 +44,7 @@
#define MLXSW_PORT_SWID_DISABLED_PORT 255
#define MLXSW_PORT_SWID_ALL_SWIDS 254
+#define MLXSW_PORT_SWID_TYPE_IB 1
#define MLXSW_PORT_SWID_TYPE_ETH 2
#define MLXSW_PORT_MID 0xd000
@@ -51,6 +52,9 @@
#define MLXSW_PORT_MAX_PHY_PORTS 0x40
#define MLXSW_PORT_MAX_PORTS (MLXSW_PORT_MAX_PHY_PORTS + 1)
+#define MLXSW_PORT_MAX_IB_PHY_PORTS 36
+#define MLXSW_PORT_MAX_IB_PORTS (MLXSW_PORT_MAX_IB_PHY_PORTS + 1)
+
#define MLXSW_PORT_DEVID_BITS_OFFSET 10
#define MLXSW_PORT_PHY_BITS_OFFSET 4
#define MLXSW_PORT_PHY_BITS_MASK (MLXSW_PORT_MAX_PHY_PORTS - 1)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index debcf26..edad7cb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2054,6 +2054,7 @@ MLXSW_REG_DEFINE(ptys, MLXSW_REG_PTYS_ID, MLXSW_REG_PTYS_LEN);
*/
MLXSW_ITEM32(reg, ptys, local_port, 0x00, 16, 8);
+#define MLXSW_REG_PTYS_PROTO_MASK_IB BIT(0)
#define MLXSW_REG_PTYS_PROTO_MASK_ETH BIT(2)
/* reg_ptys_proto_mask
@@ -2112,18 +2113,61 @@ MLXSW_ITEM32(reg, ptys, an_status, 0x04, 28, 4);
*/
MLXSW_ITEM32(reg, ptys, eth_proto_cap, 0x0C, 0, 32);
+/* reg_ptys_ib_link_width_cap
+ * IB port supported widths.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, ptys, ib_link_width_cap, 0x10, 16, 16);
+
+#define MLXSW_REG_PTYS_IB_SPEED_SDR BIT(0)
+#define MLXSW_REG_PTYS_IB_SPEED_DDR BIT(1)
+#define MLXSW_REG_PTYS_IB_SPEED_QDR BIT(2)
+#define MLXSW_REG_PTYS_IB_SPEED_FDR10 BIT(3)
+#define MLXSW_REG_PTYS_IB_SPEED_FDR BIT(4)
+#define MLXSW_REG_PTYS_IB_SPEED_EDR BIT(5)
+
+/* reg_ptys_ib_proto_cap
+ * IB port supported speeds and protocols.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, ptys, ib_proto_cap, 0x10, 0, 16);
+
/* reg_ptys_eth_proto_admin
* Speed and protocol to set port to.
* Access: RW
*/
MLXSW_ITEM32(reg, ptys, eth_proto_admin, 0x18, 0, 32);
+/* reg_ptys_ib_link_width_admin
+ * IB width to set port to.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptys, ib_link_width_admin, 0x1C, 16, 16);
+
+/* reg_ptys_ib_proto_admin
+ * IB speeds and protocols to set port to.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptys, ib_proto_admin, 0x1C, 0, 16);
+
/* reg_ptys_eth_proto_oper
* The current speed and protocol configured for the port.
* Access: RO
*/
MLXSW_ITEM32(reg, ptys, eth_proto_oper, 0x24, 0, 32);
+/* reg_ptys_ib_link_width_oper
+ * The current IB width to set port to.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, ptys, ib_link_width_oper, 0x28, 16, 16);
+
+/* reg_ptys_ib_proto_oper
+ * The current IB speed and protocol.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, ptys, ib_proto_oper, 0x28, 0, 16);
+
/* reg_ptys_eth_proto_lp_advertise
* The protocols that were advertised by the link partner during
* autonegotiation.
@@ -2131,8 +2175,8 @@ MLXSW_ITEM32(reg, ptys, eth_proto_oper, 0x24, 0, 32);
*/
MLXSW_ITEM32(reg, ptys, eth_proto_lp_advertise, 0x30, 0, 32);
-static inline void mlxsw_reg_ptys_pack(char *payload, u8 local_port,
- u32 proto_admin)
+static inline void mlxsw_reg_ptys_eth_pack(char *payload, u8 local_port,
+ u32 proto_admin)
{
MLXSW_REG_ZERO(ptys, payload);
mlxsw_reg_ptys_local_port_set(payload, local_port);
@@ -2140,9 +2184,10 @@ static inline void mlxsw_reg_ptys_pack(char *payload, u8 local_port,
mlxsw_reg_ptys_eth_proto_admin_set(payload, proto_admin);
}
-static inline void mlxsw_reg_ptys_unpack(char *payload, u32 *p_eth_proto_cap,
- u32 *p_eth_proto_adm,
- u32 *p_eth_proto_oper)
+static inline void mlxsw_reg_ptys_eth_unpack(char *payload,
+ u32 *p_eth_proto_cap,
+ u32 *p_eth_proto_adm,
+ u32 *p_eth_proto_oper)
{
if (p_eth_proto_cap)
*p_eth_proto_cap = mlxsw_reg_ptys_eth_proto_cap_get(payload);
@@ -2152,6 +2197,33 @@ static inline void mlxsw_reg_ptys_unpack(char *payload, u32 *p_eth_proto_cap,
*p_eth_proto_oper = mlxsw_reg_ptys_eth_proto_oper_get(payload);
}
+static inline void mlxsw_reg_ptys_ib_pack(char *payload, u8 local_port,
+ u16 proto_admin, u16 link_width)
+{
+ MLXSW_REG_ZERO(ptys, payload);
+ mlxsw_reg_ptys_local_port_set(payload, local_port);
+ mlxsw_reg_ptys_proto_mask_set(payload, MLXSW_REG_PTYS_PROTO_MASK_IB);
+ mlxsw_reg_ptys_ib_proto_admin_set(payload, proto_admin);
+ mlxsw_reg_ptys_ib_link_width_admin_set(payload, link_width);
+}
+
+static inline void mlxsw_reg_ptys_ib_unpack(char *payload, u16 *p_ib_proto_cap,
+ u16 *p_ib_link_width_cap,
+ u16 *p_ib_proto_oper,
+ u16 *p_ib_link_width_oper)
+{
+ if (p_ib_proto_cap)
+ *p_ib_proto_cap = mlxsw_reg_ptys_ib_proto_cap_get(payload);
+ if (p_ib_link_width_cap)
+ *p_ib_link_width_cap =
+ mlxsw_reg_ptys_ib_link_width_cap_get(payload);
+ if (p_ib_proto_oper)
+ *p_ib_proto_oper = mlxsw_reg_ptys_ib_proto_oper_get(payload);
+ if (p_ib_link_width_oper)
+ *p_ib_link_width_oper =
+ mlxsw_reg_ptys_ib_link_width_oper_get(payload);
+}
+
/* PPAD - Port Physical Address Register
* -------------------------------------
* The PPAD register configures the per port physical MAC address.
@@ -2676,6 +2748,27 @@ static inline void mlxsw_reg_ppcnt_pack(char *payload, u8 local_port,
mlxsw_reg_ppcnt_prio_tc_set(payload, prio_tc);
}
+/* PLIB - Port Local to InfiniBand Port
+ * ------------------------------------
+ * The PLIB register performs mapping from Local Port into InfiniBand Port.
+ */
+#define MLXSW_REG_PLIB_ID 0x500A
+#define MLXSW_REG_PLIB_LEN 0x10
+
+MLXSW_REG_DEFINE(plib, MLXSW_REG_PLIB_ID, MLXSW_REG_PLIB_LEN);
+
+/* reg_plib_local_port
+ * Local port number.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, plib, local_port, 0x00, 16, 8);
+
+/* reg_plib_ib_port
+ * InfiniBand port remapping for local_port.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, plib, ib_port, 0x00, 0, 8);
+
/* PPTB - Port Prio To Buffer Register
* -----------------------------------
* Configures the switch priority to buffer table.
@@ -4331,7 +4424,7 @@ enum mlxsw_reg_mfcr_pwm_frequency {
* Controls the frequency of the PWM signal.
* Access: RW
*/
-MLXSW_ITEM32(reg, mfcr, pwm_frequency, 0x00, 0, 6);
+MLXSW_ITEM32(reg, mfcr, pwm_frequency, 0x00, 0, 7);
#define MLXSW_MFCR_TACHOS_MAX 10
@@ -5116,6 +5209,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
MLXSW_REG(paos),
MLXSW_REG(pfcc),
MLXSW_REG(ppcnt),
+ MLXSW_REG(plib),
MLXSW_REG(pptb),
MLXSW_REG(pbmc),
MLXSW_REG(pspa),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index d652f7f..4a1f9d5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -54,7 +54,6 @@
#include <linux/dcbnl.h>
#include <linux/inetdevice.h>
#include <net/switchdev.h>
-#include <generated/utsrelease.h>
#include <net/pkt_cls.h>
#include <net/tc_act/tc_mirred.h>
#include <net/netevent.h>
@@ -158,7 +157,7 @@ static void mlxsw_sp_txhdr_construct(struct sk_buff *skb,
static int mlxsw_sp_base_mac_get(struct mlxsw_sp *mlxsw_sp)
{
- char spad_pl[MLXSW_REG_SPAD_LEN];
+ char spad_pl[MLXSW_REG_SPAD_LEN] = {0};
int err;
err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(spad), spad_pl);
@@ -232,7 +231,7 @@ mlxsw_sp_span_entry_create(struct mlxsw_sp_port *port)
span_entry->used = true;
span_entry->id = index;
- span_entry->ref_count = 0;
+ span_entry->ref_count = 1;
span_entry->local_port = local_port;
return span_entry;
}
@@ -271,6 +270,7 @@ static struct mlxsw_sp_span_entry
span_entry = mlxsw_sp_span_entry_find(port);
if (span_entry) {
+ /* Already exists, just take a reference */
span_entry->ref_count++;
return span_entry;
}
@@ -281,6 +281,7 @@ static struct mlxsw_sp_span_entry
static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_span_entry *span_entry)
{
+ WARN_ON(!span_entry->ref_count);
if (--span_entry->ref_count == 0)
mlxsw_sp_span_entry_destroy(mlxsw_sp, span_entry);
return 0;
@@ -2003,12 +2004,12 @@ static int mlxsw_sp_port_get_link_ksettings(struct net_device *dev,
int err;
autoneg = mlxsw_sp_port->link.autoneg;
- mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sp_port->local_port, 0);
+ mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sp_port->local_port, 0);
err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
if (err)
return err;
- mlxsw_reg_ptys_unpack(ptys_pl, ð_proto_cap, ð_proto_admin,
- ð_proto_oper);
+ mlxsw_reg_ptys_eth_unpack(ptys_pl, ð_proto_cap, ð_proto_admin,
+ ð_proto_oper);
mlxsw_sp_port_get_link_supported(eth_proto_cap, cmd);
@@ -2037,11 +2038,11 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev,
bool autoneg;
int err;
- mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sp_port->local_port, 0);
+ mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sp_port->local_port, 0);
err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
if (err)
return err;
- mlxsw_reg_ptys_unpack(ptys_pl, ð_proto_cap, NULL, NULL);
+ mlxsw_reg_ptys_eth_unpack(ptys_pl, ð_proto_cap, NULL, NULL);
autoneg = cmd->base.autoneg == AUTONEG_ENABLE;
eth_proto_new = autoneg ?
@@ -2054,7 +2055,8 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev,
return -EINVAL;
}
- mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sp_port->local_port, eth_proto_new);
+ mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sp_port->local_port,
+ eth_proto_new);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
if (err)
return err;
@@ -2092,8 +2094,8 @@ mlxsw_sp_port_speed_by_width_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 width)
u32 eth_proto_admin;
eth_proto_admin = mlxsw_sp_to_ptys_upper_speed(upper_speed);
- mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sp_port->local_port,
- eth_proto_admin);
+ mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sp_port->local_port,
+ eth_proto_admin);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
}
@@ -2211,8 +2213,8 @@ static int mlxsw_sp_port_pvid_vport_destroy(struct mlxsw_sp_port *mlxsw_sp_port)
return mlxsw_sp_port_kill_vid(mlxsw_sp_port->dev, 0, 1);
}
-static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
- bool split, u8 module, u8 width, u8 lane)
+static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+ bool split, u8 module, u8 width, u8 lane)
{
struct mlxsw_sp_port *mlxsw_sp_port;
struct net_device *dev;
@@ -2357,20 +2359,12 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
goto err_register_netdev;
}
- err = mlxsw_core_port_init(mlxsw_sp->core, &mlxsw_sp_port->core_port,
- mlxsw_sp_port->local_port, dev,
- mlxsw_sp_port->split, module);
- if (err) {
- dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to init core port\n",
- mlxsw_sp_port->local_port);
- goto err_core_port_init;
- }
-
+ mlxsw_core_port_eth_set(mlxsw_sp->core, mlxsw_sp_port->local_port,
+ mlxsw_sp_port, dev, mlxsw_sp_port->split,
+ module);
mlxsw_core_schedule_dw(&mlxsw_sp_port->hw_stats.update_dw, 0);
return 0;
-err_core_port_init:
- unregister_netdev(dev);
err_register_netdev:
mlxsw_sp->ports[local_port] = NULL;
mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
@@ -2399,14 +2393,34 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
return err;
}
-static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
+static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+ bool split, u8 module, u8 width, u8 lane)
+{
+ int err;
+
+ err = mlxsw_core_port_init(mlxsw_sp->core, local_port);
+ if (err) {
+ dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to init core port\n",
+ local_port);
+ return err;
+ }
+ err = __mlxsw_sp_port_create(mlxsw_sp, local_port, false,
+ module, width, lane);
+ if (err)
+ goto err_port_create;
+ return 0;
+
+err_port_create:
+ mlxsw_core_port_fini(mlxsw_sp->core, local_port);
+ return err;
+}
+
+static void __mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
{
struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port];
- if (!mlxsw_sp_port)
- return;
cancel_delayed_work_sync(&mlxsw_sp_port->hw_stats.update_dw);
- mlxsw_core_port_fini(&mlxsw_sp_port->core_port);
+ mlxsw_core_port_clear(mlxsw_sp->core, local_port, mlxsw_sp);
unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
mlxsw_sp->ports[local_port] = NULL;
mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
@@ -2422,12 +2436,24 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
free_netdev(mlxsw_sp_port->dev);
}
+static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
+{
+ __mlxsw_sp_port_remove(mlxsw_sp, local_port);
+ mlxsw_core_port_fini(mlxsw_sp->core, local_port);
+}
+
+static bool mlxsw_sp_port_created(struct mlxsw_sp *mlxsw_sp, u8 local_port)
+{
+ return mlxsw_sp->ports[local_port] != NULL;
+}
+
static void mlxsw_sp_ports_remove(struct mlxsw_sp *mlxsw_sp)
{
int i;
for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++)
- mlxsw_sp_port_remove(mlxsw_sp, i);
+ if (mlxsw_sp_port_created(mlxsw_sp, i))
+ mlxsw_sp_port_remove(mlxsw_sp, i);
kfree(mlxsw_sp->ports);
}
@@ -2451,8 +2477,8 @@ static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
if (!width)
continue;
mlxsw_sp->port_to_module[i] = module;
- err = mlxsw_sp_port_create(mlxsw_sp, i, false, module, width,
- lane);
+ err = mlxsw_sp_port_create(mlxsw_sp, i, false,
+ module, width, lane);
if (err)
goto err_port_create;
}
@@ -2461,7 +2487,8 @@ static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp)
err_port_create:
err_port_module_info_get:
for (i--; i >= 1; i--)
- mlxsw_sp_port_remove(mlxsw_sp, i);
+ if (mlxsw_sp_port_created(mlxsw_sp, i))
+ mlxsw_sp_port_remove(mlxsw_sp, i);
kfree(mlxsw_sp->ports);
return err;
}
@@ -2503,7 +2530,8 @@ static int mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port,
err_port_create:
for (i--; i >= 0; i--)
- mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
+ if (mlxsw_sp_port_created(mlxsw_sp, base_port + i))
+ mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
i = count;
err_port_swid_set:
for (i--; i >= 0; i--)
@@ -2593,7 +2621,8 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
}
for (i = 0; i < count; i++)
- mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
+ if (mlxsw_sp_port_created(mlxsw_sp, base_port + i))
+ mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
err = mlxsw_sp_port_split_create(mlxsw_sp, base_port, module, count);
if (err) {
@@ -2638,7 +2667,8 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port)
base_port = base_port + 2;
for (i = 0; i < count; i++)
- mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
+ if (mlxsw_sp_port_created(mlxsw_sp, base_port + i))
+ mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index cc54625..cc1af19 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -115,7 +115,7 @@ struct mlxsw_sp_rif {
struct mlxsw_sp_mid {
struct list_head list;
unsigned char addr[ETH_ALEN];
- u16 vid;
+ u16 fid;
u16 mid;
unsigned int ref_count;
};
@@ -316,7 +316,6 @@ struct mlxsw_sp_port_pcpu_stats {
};
struct mlxsw_sp_port {
- struct mlxsw_core_port core_port; /* must be first */
struct net_device *dev;
struct mlxsw_sp_port_pcpu_stats __percpu *pcpu_stats;
struct mlxsw_sp *mlxsw_sp;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 107934f..683f045 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -320,6 +320,8 @@ mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp,
lpm_tree);
if (err)
goto err_left_struct_set;
+ memcpy(&lpm_tree->prefix_usage, prefix_usage,
+ sizeof(lpm_tree->prefix_usage));
return lpm_tree;
err_left_struct_set:
@@ -343,7 +345,8 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp,
for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
lpm_tree = &mlxsw_sp->router.lpm_trees[i];
- if (lpm_tree->proto == proto &&
+ if (lpm_tree->ref_count != 0 &&
+ lpm_tree->proto == proto &&
mlxsw_sp_prefix_usage_eq(&lpm_tree->prefix_usage,
prefix_usage))
goto inc_ref_count;
@@ -586,21 +589,22 @@ static int mlxsw_sp_vrs_init(struct mlxsw_sp *mlxsw_sp)
return 0;
}
+static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp);
+
static void mlxsw_sp_vrs_fini(struct mlxsw_sp *mlxsw_sp)
{
+ mlxsw_sp_router_fib_flush(mlxsw_sp);
kfree(mlxsw_sp->router.vrs);
}
struct mlxsw_sp_neigh_key {
- unsigned char addr[sizeof(struct in6_addr)];
- struct net_device *dev;
+ struct neighbour *n;
};
struct mlxsw_sp_neigh_entry {
struct rhash_head ht_node;
struct mlxsw_sp_neigh_key key;
u16 rif;
- struct neighbour *n;
bool offloaded;
struct delayed_work dw;
struct mlxsw_sp_port *mlxsw_sp_port;
@@ -638,19 +642,15 @@ mlxsw_sp_neigh_entry_remove(struct mlxsw_sp *mlxsw_sp,
static void mlxsw_sp_router_neigh_update_hw(struct work_struct *work);
static struct mlxsw_sp_neigh_entry *
-mlxsw_sp_neigh_entry_create(const void *addr, size_t addr_len,
- struct net_device *dev, u16 rif,
- struct neighbour *n)
+mlxsw_sp_neigh_entry_create(struct neighbour *n, u16 rif)
{
struct mlxsw_sp_neigh_entry *neigh_entry;
neigh_entry = kzalloc(sizeof(*neigh_entry), GFP_ATOMIC);
if (!neigh_entry)
return NULL;
- memcpy(neigh_entry->key.addr, addr, addr_len);
- neigh_entry->key.dev = dev;
+ neigh_entry->key.n = n;
neigh_entry->rif = rif;
- neigh_entry->n = n;
INIT_DELAYED_WORK(&neigh_entry->dw, mlxsw_sp_router_neigh_update_hw);
INIT_LIST_HEAD(&neigh_entry->nexthop_list);
return neigh_entry;
@@ -663,13 +663,11 @@ mlxsw_sp_neigh_entry_destroy(struct mlxsw_sp_neigh_entry *neigh_entry)
}
static struct mlxsw_sp_neigh_entry *
-mlxsw_sp_neigh_entry_lookup(struct mlxsw_sp *mlxsw_sp, const void *addr,
- size_t addr_len, struct net_device *dev)
+mlxsw_sp_neigh_entry_lookup(struct mlxsw_sp *mlxsw_sp, struct neighbour *n)
{
- struct mlxsw_sp_neigh_key key = {{ 0 } };
+ struct mlxsw_sp_neigh_key key;
- memcpy(key.addr, addr, addr_len);
- key.dev = dev;
+ key.n = n;
return rhashtable_lookup_fast(&mlxsw_sp->router.neigh_ht,
&key, mlxsw_sp_neigh_ht_params);
}
@@ -681,26 +679,20 @@ int mlxsw_sp_router_neigh_construct(struct net_device *dev,
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
struct mlxsw_sp_neigh_entry *neigh_entry;
struct mlxsw_sp_rif *r;
- u32 dip;
int err;
if (n->tbl != &arp_tbl)
return 0;
- dip = ntohl(*((__be32 *) n->primary_key));
- neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &dip, sizeof(dip),
- n->dev);
- if (neigh_entry) {
- WARN_ON(neigh_entry->n != n);
+ neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n);
+ if (neigh_entry)
return 0;
- }
r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev);
if (WARN_ON(!r))
return -EINVAL;
- neigh_entry = mlxsw_sp_neigh_entry_create(&dip, sizeof(dip), n->dev,
- r->rif, n);
+ neigh_entry = mlxsw_sp_neigh_entry_create(n, r->rif);
if (!neigh_entry)
return -ENOMEM;
err = mlxsw_sp_neigh_entry_insert(mlxsw_sp, neigh_entry);
@@ -719,14 +711,11 @@ void mlxsw_sp_router_neigh_destroy(struct net_device *dev,
struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
struct mlxsw_sp_neigh_entry *neigh_entry;
- u32 dip;
if (n->tbl != &arp_tbl)
return;
- dip = ntohl(*((__be32 *) n->primary_key));
- neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &dip, sizeof(dip),
- n->dev);
+ neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n);
if (!neigh_entry)
return;
mlxsw_sp_neigh_entry_remove(mlxsw_sp, neigh_entry);
@@ -809,6 +798,26 @@ static void mlxsw_sp_router_neigh_rec_process(struct mlxsw_sp *mlxsw_sp,
}
}
+static bool mlxsw_sp_router_rauhtd_is_full(char *rauhtd_pl)
+{
+ u8 num_rec, last_rec_index, num_entries;
+
+ num_rec = mlxsw_reg_rauhtd_num_rec_get(rauhtd_pl);
+ last_rec_index = num_rec - 1;
+
+ if (num_rec < MLXSW_REG_RAUHTD_REC_MAX_NUM)
+ return false;
+ if (mlxsw_reg_rauhtd_rec_type_get(rauhtd_pl, last_rec_index) ==
+ MLXSW_REG_RAUHTD_TYPE_IPV6)
+ return true;
+
+ num_entries = mlxsw_reg_rauhtd_ipv4_rec_num_entries_get(rauhtd_pl,
+ last_rec_index);
+ if (++num_entries == MLXSW_REG_RAUHTD_IPV4_ENT_PER_REC)
+ return true;
+ return false;
+}
+
static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp)
{
char *rauhtd_pl;
@@ -835,7 +844,7 @@ static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp)
for (i = 0; i < num_rec; i++)
mlxsw_sp_router_neigh_rec_process(mlxsw_sp, rauhtd_pl,
i);
- } while (num_rec);
+ } while (mlxsw_sp_router_rauhtd_is_full(rauhtd_pl));
rtnl_unlock();
kfree(rauhtd_pl);
@@ -854,7 +863,7 @@ static void mlxsw_sp_router_neighs_update_nh(struct mlxsw_sp *mlxsw_sp)
* is active regardless of the traffic.
*/
if (!list_empty(&neigh_entry->nexthop_list))
- neigh_event_send(neigh_entry->n, NULL);
+ neigh_event_send(neigh_entry->key.n, NULL);
}
rtnl_unlock();
}
@@ -900,9 +909,9 @@ static void mlxsw_sp_router_probe_unresolved_nexthops(struct work_struct *work)
rtnl_lock();
list_for_each_entry(neigh_entry, &mlxsw_sp->router.nexthop_neighs_list,
nexthop_neighs_list_node) {
- if (!(neigh_entry->n->nud_state & NUD_VALID) &&
+ if (!(neigh_entry->key.n->nud_state & NUD_VALID) &&
!list_empty(&neigh_entry->nexthop_list))
- neigh_event_send(neigh_entry->n, NULL);
+ neigh_event_send(neigh_entry->key.n, NULL);
}
rtnl_unlock();
@@ -919,7 +928,7 @@ static void mlxsw_sp_router_neigh_update_hw(struct work_struct *work)
{
struct mlxsw_sp_neigh_entry *neigh_entry =
container_of(work, struct mlxsw_sp_neigh_entry, dw.work);
- struct neighbour *n = neigh_entry->n;
+ struct neighbour *n = neigh_entry->key.n;
struct mlxsw_sp_port *mlxsw_sp_port = neigh_entry->mlxsw_sp_port;
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
char rauht_pl[MLXSW_REG_RAUHT_LEN];
@@ -1022,11 +1031,8 @@ int mlxsw_sp_router_netevent_event(struct notifier_block *unused,
mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
dip = ntohl(*((__be32 *) n->primary_key));
- neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp,
- &dip,
- sizeof(__be32),
- dev);
- if (WARN_ON(!neigh_entry) || WARN_ON(neigh_entry->n != n)) {
+ neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n);
+ if (WARN_ON(!neigh_entry)) {
mlxsw_sp_port_dev_put(mlxsw_sp_port);
return NOTIFY_DONE;
}
@@ -1335,33 +1341,26 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp,
struct fib_nh *fib_nh)
{
struct mlxsw_sp_neigh_entry *neigh_entry;
- u32 gwip = ntohl(fib_nh->nh_gw);
struct net_device *dev = fib_nh->nh_dev;
struct neighbour *n;
u8 nud_state;
- neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &gwip,
- sizeof(gwip), dev);
- if (!neigh_entry) {
- __be32 gwipn = htonl(gwip);
-
- n = neigh_create(&arp_tbl, &gwipn, dev);
+ /* Take a reference of neigh here ensuring that neigh would
+ * not be detructed before the nexthop entry is finished.
+ * The reference is taken either in neigh_lookup() or
+ * in neith_create() in case n is not found.
+ */
+ n = neigh_lookup(&arp_tbl, &fib_nh->nh_gw, dev);
+ if (!n) {
+ n = neigh_create(&arp_tbl, &fib_nh->nh_gw, dev);
if (IS_ERR(n))
return PTR_ERR(n);
neigh_event_send(n, NULL);
- neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &gwip,
- sizeof(gwip), dev);
- if (!neigh_entry) {
- neigh_release(n);
- return -EINVAL;
- }
- } else {
- /* Take a reference of neigh here ensuring that neigh would
- * not be detructed before the nexthop entry is finished.
- * The second branch takes the reference in neith_create()
- */
- n = neigh_entry->n;
- neigh_clone(n);
+ }
+ neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n);
+ if (!neigh_entry) {
+ neigh_release(n);
+ return -EINVAL;
}
/* If that is the first nexthop connected to that neigh, add to
@@ -1395,7 +1394,7 @@ static void mlxsw_sp_nexthop_fini(struct mlxsw_sp *mlxsw_sp,
if (list_empty(&nh->neigh_entry->nexthop_list))
list_del(&nh->neigh_entry->nexthop_neighs_list_node);
- neigh_release(neigh_entry->n);
+ neigh_release(neigh_entry->key.n);
}
static struct mlxsw_sp_nexthop_group *
@@ -1455,11 +1454,11 @@ static bool mlxsw_sp_nexthop_match(struct mlxsw_sp_nexthop *nh,
for (i = 0; i < fi->fib_nhs; i++) {
struct fib_nh *fib_nh = &fi->fib_nh[i];
- u32 gwip = ntohl(fib_nh->nh_gw);
+ struct neighbour *n = nh->neigh_entry->key.n;
- if (memcmp(nh->neigh_entry->key.addr,
- &gwip, sizeof(u32)) == 0 &&
- nh->neigh_entry->key.dev == fib_nh->nh_dev)
+ if (memcmp(n->primary_key, &fib_nh->nh_gw,
+ sizeof(fib_nh->nh_gw)) == 0 &&
+ n->dev == fib_nh->nh_dev)
return true;
}
return false;
@@ -1815,19 +1814,17 @@ static int mlxsw_sp_router_fib4_add(struct mlxsw_sp *mlxsw_sp,
return err;
}
-static int mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp,
- struct fib_entry_notifier_info *fen_info)
+static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp,
+ struct fib_entry_notifier_info *fen_info)
{
struct mlxsw_sp_fib_entry *fib_entry;
if (mlxsw_sp->router.aborted)
- return 0;
+ return;
fib_entry = mlxsw_sp_fib_entry_find(mlxsw_sp, fen_info);
- if (!fib_entry) {
- dev_warn(mlxsw_sp->bus_info->dev, "Failed to find FIB4 entry being removed.\n");
- return -ENOENT;
- }
+ if (!fib_entry)
+ return;
if (fib_entry->ref_count == 1) {
mlxsw_sp_fib_entry_del(mlxsw_sp, fib_entry);
@@ -1835,7 +1832,6 @@ static int mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp,
}
mlxsw_sp_fib_entry_put(mlxsw_sp, fib_entry);
- return 0;
}
static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
@@ -1857,7 +1853,8 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
if (err)
return err;
- mlxsw_reg_raltb_pack(raltb_pl, 0, MLXSW_REG_RALXX_PROTOCOL_IPV4, 0);
+ mlxsw_reg_raltb_pack(raltb_pl, 0, MLXSW_REG_RALXX_PROTOCOL_IPV4,
+ MLXSW_SP_LPM_TREE_MIN);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
if (err)
return err;
@@ -1868,16 +1865,16 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
}
-static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp)
+static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp)
{
struct mlxsw_sp_fib_entry *fib_entry;
struct mlxsw_sp_fib_entry *tmp;
struct mlxsw_sp_vr *vr;
int i;
- int err;
for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
vr = &mlxsw_sp->router.vrs[i];
+
if (!vr->used)
continue;
@@ -1893,6 +1890,16 @@ static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp)
break;
}
}
+}
+
+static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp)
+{
+ int err;
+
+ if (mlxsw_sp->router.aborted)
+ return;
+ dev_warn(mlxsw_sp->bus_info->dev, "FIB abort triggered. Note that FIB entries are no longer being offloaded to this device.\n");
+ mlxsw_sp_router_fib_flush(mlxsw_sp);
mlxsw_sp->router.aborted = true;
err = mlxsw_sp_router_set_abort_trap(mlxsw_sp);
if (err)
@@ -1948,6 +1955,9 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
struct fib_entry_notifier_info *fen_info = ptr;
int err;
+ if (!net_eq(fen_info->info.net, &init_net))
+ return NOTIFY_DONE;
+
switch (event) {
case FIB_EVENT_ENTRY_ADD:
err = mlxsw_sp_router_fib4_add(mlxsw_sp, fen_info);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index b19552a7..b87ba7d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -929,12 +929,12 @@ static int mlxsw_sp_port_smid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mid,
static struct mlxsw_sp_mid *__mlxsw_sp_mc_get(struct mlxsw_sp *mlxsw_sp,
const unsigned char *addr,
- u16 vid)
+ u16 fid)
{
struct mlxsw_sp_mid *mid;
list_for_each_entry(mid, &mlxsw_sp->br_mids.list, list) {
- if (ether_addr_equal(mid->addr, addr) && mid->vid == vid)
+ if (ether_addr_equal(mid->addr, addr) && mid->fid == fid)
return mid;
}
return NULL;
@@ -942,7 +942,7 @@ static struct mlxsw_sp_mid *__mlxsw_sp_mc_get(struct mlxsw_sp *mlxsw_sp,
static struct mlxsw_sp_mid *__mlxsw_sp_mc_alloc(struct mlxsw_sp *mlxsw_sp,
const unsigned char *addr,
- u16 vid)
+ u16 fid)
{
struct mlxsw_sp_mid *mid;
u16 mid_idx;
@@ -958,7 +958,7 @@ static struct mlxsw_sp_mid *__mlxsw_sp_mc_alloc(struct mlxsw_sp *mlxsw_sp,
set_bit(mid_idx, mlxsw_sp->br_mids.mapped);
ether_addr_copy(mid->addr, addr);
- mid->vid = vid;
+ mid->fid = fid;
mid->mid = mid_idx;
mid->ref_count = 0;
list_add_tail(&mid->list, &mlxsw_sp->br_mids.list);
@@ -991,9 +991,9 @@ static int mlxsw_sp_port_mdb_add(struct mlxsw_sp_port *mlxsw_sp_port,
if (switchdev_trans_ph_prepare(trans))
return 0;
- mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, mdb->vid);
+ mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, fid);
if (!mid) {
- mid = __mlxsw_sp_mc_alloc(mlxsw_sp, mdb->addr, mdb->vid);
+ mid = __mlxsw_sp_mc_alloc(mlxsw_sp, mdb->addr, fid);
if (!mid) {
netdev_err(dev, "Unable to allocate MC group\n");
return -ENOMEM;
@@ -1137,7 +1137,7 @@ static int mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port,
u16 mid_idx;
int err = 0;
- mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, mdb->vid);
+ mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, fid);
if (!mid) {
netdev_err(dev, "Unable to remove port from MC DB\n");
return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchib.c b/drivers/net/ethernet/mellanox/mlxsw/switchib.c
new file mode 100644
index 0000000..1552594
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchib.c
@@ -0,0 +1,597 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/switchib.c
+ * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016 Elad Raz <eladr@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ * contributors may be used to endorse or promote products derived from
+ * this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/slab.h>
+#include <linux/device.h>
+#include <linux/skbuff.h>
+#include <linux/if_vlan.h>
+#include <net/switchdev.h>
+
+#include "pci.h"
+#include "core.h"
+#include "reg.h"
+#include "port.h"
+#include "trap.h"
+#include "txheader.h"
+#include "ib.h"
+
+static const char mlxsw_sib_driver_name[] = "mlxsw_switchib";
+static const char mlxsw_sib2_driver_name[] = "mlxsw_switchib2";
+
+struct mlxsw_sib_port;
+
+struct mlxsw_sib {
+ struct mlxsw_sib_port **ports;
+ struct mlxsw_core *core;
+ const struct mlxsw_bus_info *bus_info;
+};
+
+struct mlxsw_sib_port {
+ struct mlxsw_sib *mlxsw_sib;
+ u8 local_port;
+ struct {
+ u8 module;
+ } mapping;
+};
+
+/* tx_v1_hdr_version
+ * Tx header version.
+ * Must be set to 1.
+ */
+MLXSW_ITEM32(tx_v1, hdr, version, 0x00, 28, 4);
+
+/* tx_v1_hdr_ctl
+ * Packet control type.
+ * 0 - Ethernet control (e.g. EMADs, LACP)
+ * 1 - Ethernet data
+ */
+MLXSW_ITEM32(tx_v1, hdr, ctl, 0x00, 26, 2);
+
+/* tx_v1_hdr_proto
+ * Packet protocol type. Must be set to 1 (Ethernet).
+ */
+MLXSW_ITEM32(tx_v1, hdr, proto, 0x00, 21, 3);
+
+/* tx_v1_hdr_swid
+ * Switch partition ID. Must be set to 0.
+ */
+MLXSW_ITEM32(tx_v1, hdr, swid, 0x00, 12, 3);
+
+/* tx_v1_hdr_control_tclass
+ * Indicates if the packet should use the control TClass and not one
+ * of the data TClasses.
+ */
+MLXSW_ITEM32(tx_v1, hdr, control_tclass, 0x00, 6, 1);
+
+/* tx_v1_hdr_port_mid
+ * Destination local port for unicast packets.
+ * Destination multicast ID for multicast packets.
+ *
+ * Control packets are directed to a specific egress port, while data
+ * packets are transmitted through the CPU port (0) into the switch partition,
+ * where forwarding rules are applied.
+ */
+MLXSW_ITEM32(tx_v1, hdr, port_mid, 0x04, 16, 16);
+
+/* tx_v1_hdr_type
+ * 0 - Data packets
+ * 6 - Control packets
+ */
+MLXSW_ITEM32(tx_v1, hdr, type, 0x0C, 0, 4);
+
+static void
+mlxsw_sib_tx_v1_hdr_construct(struct sk_buff *skb,
+ const struct mlxsw_tx_info *tx_info)
+{
+ char *txhdr = skb_push(skb, MLXSW_TXHDR_LEN);
+
+ memset(txhdr, 0, MLXSW_TXHDR_LEN);
+
+ mlxsw_tx_v1_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1);
+ mlxsw_tx_v1_hdr_ctl_set(txhdr, MLXSW_TXHDR_ETH_CTL);
+ mlxsw_tx_v1_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH);
+ mlxsw_tx_v1_hdr_swid_set(txhdr, 0);
+ mlxsw_tx_v1_hdr_control_tclass_set(txhdr, 1);
+ mlxsw_tx_v1_hdr_port_mid_set(txhdr, tx_info->local_port);
+ mlxsw_tx_v1_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL);
+}
+
+static int
+mlxsw_sib_port_admin_status_set(struct mlxsw_sib_port *mlxsw_sib_port,
+ bool is_up)
+{
+ struct mlxsw_sib *mlxsw_sib = mlxsw_sib_port->mlxsw_sib;
+ char paos_pl[MLXSW_REG_PAOS_LEN];
+
+ mlxsw_reg_paos_pack(paos_pl, mlxsw_sib_port->local_port,
+ is_up ? MLXSW_PORT_ADMIN_STATUS_UP :
+ MLXSW_PORT_ADMIN_STATUS_DOWN);
+ return mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(paos), paos_pl);
+}
+
+static int mlxsw_sib_port_mtu_set(struct mlxsw_sib_port *mlxsw_sib_port,
+ u16 mtu)
+{
+ struct mlxsw_sib *mlxsw_sib = mlxsw_sib_port->mlxsw_sib;
+ char pmtu_pl[MLXSW_REG_PMTU_LEN];
+ int max_mtu;
+ int err;
+
+ mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sib_port->local_port, 0);
+ err = mlxsw_reg_query(mlxsw_sib->core, MLXSW_REG(pmtu), pmtu_pl);
+ if (err)
+ return err;
+ max_mtu = mlxsw_reg_pmtu_max_mtu_get(pmtu_pl);
+
+ if (mtu > max_mtu)
+ return -EINVAL;
+
+ mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sib_port->local_port, mtu);
+ return mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(pmtu), pmtu_pl);
+}
+
+static int mlxsw_sib_port_set(struct mlxsw_sib_port *mlxsw_sib_port, u8 port)
+{
+ struct mlxsw_sib *mlxsw_sib = mlxsw_sib_port->mlxsw_sib;
+ char plib_pl[MLXSW_REG_PLIB_LEN] = {0};
+ int err;
+
+ mlxsw_reg_plib_local_port_set(plib_pl, mlxsw_sib_port->local_port);
+ mlxsw_reg_plib_ib_port_set(plib_pl, port);
+ err = mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(plib), plib_pl);
+ return err;
+}
+
+static int mlxsw_sib_port_swid_set(struct mlxsw_sib_port *mlxsw_sib_port,
+ u8 swid)
+{
+ struct mlxsw_sib *mlxsw_sib = mlxsw_sib_port->mlxsw_sib;
+ char pspa_pl[MLXSW_REG_PSPA_LEN];
+
+ mlxsw_reg_pspa_pack(pspa_pl, swid, mlxsw_sib_port->local_port);
+ return mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(pspa), pspa_pl);
+}
+
+static int mlxsw_sib_port_module_info_get(struct mlxsw_sib *mlxsw_sib,
+ u8 local_port, u8 *p_module,
+ u8 *p_width)
+{
+ char pmlp_pl[MLXSW_REG_PMLP_LEN];
+ int err;
+
+ mlxsw_reg_pmlp_pack(pmlp_pl, local_port);
+ err = mlxsw_reg_query(mlxsw_sib->core, MLXSW_REG(pmlp), pmlp_pl);
+ if (err)
+ return err;
+ *p_module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0);
+ *p_width = mlxsw_reg_pmlp_width_get(pmlp_pl);
+ return 0;
+}
+
+static int mlxsw_sib_port_speed_set(struct mlxsw_sib_port *mlxsw_sib_port,
+ u16 speed, u16 width)
+{
+ struct mlxsw_sib *mlxsw_sib = mlxsw_sib_port->mlxsw_sib;
+ char ptys_pl[MLXSW_REG_PTYS_LEN];
+
+ mlxsw_reg_ptys_ib_pack(ptys_pl, mlxsw_sib_port->local_port, speed,
+ width);
+ return mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(ptys), ptys_pl);
+}
+
+static bool mlxsw_sib_port_created(struct mlxsw_sib *mlxsw_sib, u8 local_port)
+{
+ return mlxsw_sib->ports[local_port] != NULL;
+}
+
+static int __mlxsw_sib_port_create(struct mlxsw_sib *mlxsw_sib, u8 local_port,
+ u8 module, u8 width)
+{
+ struct mlxsw_sib_port *mlxsw_sib_port;
+ int err;
+
+ mlxsw_sib_port = kzalloc(sizeof(*mlxsw_sib_port), GFP_KERNEL);
+ if (!mlxsw_sib_port)
+ return -ENOMEM;
+ mlxsw_sib_port->mlxsw_sib = mlxsw_sib;
+ mlxsw_sib_port->local_port = local_port;
+ mlxsw_sib_port->mapping.module = module;
+
+ err = mlxsw_sib_port_swid_set(mlxsw_sib_port, 0);
+ if (err) {
+ dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to set SWID\n",
+ mlxsw_sib_port->local_port);
+ goto err_port_swid_set;
+ }
+
+ /* Expose the IB port number as it's front panel name */
+ err = mlxsw_sib_port_set(mlxsw_sib_port, module + 1);
+ if (err) {
+ dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to set IB port\n",
+ mlxsw_sib_port->local_port);
+ goto err_port_ib_set;
+ }
+
+ /* Supports all speeds from SDR to FDR (bitmask) and support bus width
+ * of 1x, 2x and 4x (3 bits bitmask)
+ */
+ err = mlxsw_sib_port_speed_set(mlxsw_sib_port,
+ MLXSW_REG_PTYS_IB_SPEED_EDR - 1,
+ BIT(3) - 1);
+ if (err) {
+ dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to set speed\n",
+ mlxsw_sib_port->local_port);
+ goto err_port_speed_set;
+ }
+
+ /* Change to the maximum MTU the device supports, the SMA will take
+ * care of the active MTU
+ */
+ err = mlxsw_sib_port_mtu_set(mlxsw_sib_port, MLXSW_IB_DEFAULT_MTU);
+ if (err) {
+ dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to set MTU\n",
+ mlxsw_sib_port->local_port);
+ goto err_port_mtu_set;
+ }
+
+ err = mlxsw_sib_port_admin_status_set(mlxsw_sib_port, true);
+ if (err) {
+ dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to change admin state to UP\n",
+ mlxsw_sib_port->local_port);
+ goto err_port_admin_set;
+ }
+
+ mlxsw_core_port_ib_set(mlxsw_sib->core, mlxsw_sib_port->local_port,
+ mlxsw_sib_port);
+ mlxsw_sib->ports[local_port] = mlxsw_sib_port;
+ return 0;
+
+err_port_admin_set:
+err_port_mtu_set:
+err_port_speed_set:
+err_port_ib_set:
+ mlxsw_sib_port_swid_set(mlxsw_sib_port, MLXSW_PORT_SWID_DISABLED_PORT);
+err_port_swid_set:
+ kfree(mlxsw_sib_port);
+ return err;
+}
+
+static int mlxsw_sib_port_create(struct mlxsw_sib *mlxsw_sib, u8 local_port,
+ u8 module, u8 width)
+{
+ int err;
+
+ err = mlxsw_core_port_init(mlxsw_sib->core, local_port);
+ if (err) {
+ dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to init core port\n",
+ local_port);
+ return err;
+ }
+ err = __mlxsw_sib_port_create(mlxsw_sib, local_port, module, width);
+ if (err)
+ goto err_port_create;
+
+ return 0;
+
+err_port_create:
+ mlxsw_core_port_fini(mlxsw_sib->core, local_port);
+ return err;
+}
+
+static void __mlxsw_sib_port_remove(struct mlxsw_sib *mlxsw_sib, u8 local_port)
+{
+ struct mlxsw_sib_port *mlxsw_sib_port = mlxsw_sib->ports[local_port];
+
+ mlxsw_core_port_clear(mlxsw_sib->core, local_port, mlxsw_sib);
+ mlxsw_sib->ports[local_port] = NULL;
+ mlxsw_sib_port_admin_status_set(mlxsw_sib_port, false);
+ mlxsw_sib_port_swid_set(mlxsw_sib_port, MLXSW_PORT_SWID_DISABLED_PORT);
+ kfree(mlxsw_sib_port);
+}
+
+static void mlxsw_sib_port_remove(struct mlxsw_sib *mlxsw_sib, u8 local_port)
+{
+ __mlxsw_sib_port_remove(mlxsw_sib, local_port);
+ mlxsw_core_port_fini(mlxsw_sib->core, local_port);
+}
+
+static void mlxsw_sib_ports_remove(struct mlxsw_sib *mlxsw_sib)
+{
+ int i;
+
+ for (i = 1; i < MLXSW_PORT_MAX_IB_PORTS; i++)
+ if (mlxsw_sib_port_created(mlxsw_sib, i))
+ mlxsw_sib_port_remove(mlxsw_sib, i);
+ kfree(mlxsw_sib->ports);
+}
+
+static int mlxsw_sib_ports_create(struct mlxsw_sib *mlxsw_sib)
+{
+ size_t alloc_size;
+ u8 module, width;
+ int i;
+ int err;
+
+ alloc_size = sizeof(struct mlxsw_sib_port *) * MLXSW_PORT_MAX_IB_PORTS;
+ mlxsw_sib->ports = kzalloc(alloc_size, GFP_KERNEL);
+ if (!mlxsw_sib->ports)
+ return -ENOMEM;
+
+ for (i = 1; i < MLXSW_PORT_MAX_IB_PORTS; i++) {
+ err = mlxsw_sib_port_module_info_get(mlxsw_sib, i, &module,
+ &width);
+ if (err)
+ goto err_port_module_info_get;
+ if (!width)
+ continue;
+ err = mlxsw_sib_port_create(mlxsw_sib, i, module, width);
+ if (err)
+ goto err_port_create;
+ }
+ return 0;
+
+err_port_create:
+err_port_module_info_get:
+ for (i--; i >= 1; i--)
+ if (mlxsw_sib_port_created(mlxsw_sib, i))
+ mlxsw_sib_port_remove(mlxsw_sib, i);
+ kfree(mlxsw_sib->ports);
+ return err;
+}
+
+static void
+mlxsw_sib_pude_ib_event_func(struct mlxsw_sib_port *mlxsw_sib_port,
+ enum mlxsw_reg_pude_oper_status status)
+{
+ if (status == MLXSW_PORT_OPER_STATUS_UP)
+ pr_info("ib link for port %d - up\n",
+ mlxsw_sib_port->mapping.module + 1);
+ else
+ pr_info("ib link for port %d - down\n",
+ mlxsw_sib_port->mapping.module + 1);
+}
+
+static void mlxsw_sib_pude_event_func(const struct mlxsw_reg_info *reg,
+ char *pude_pl, void *priv)
+{
+ struct mlxsw_sib *mlxsw_sib = priv;
+ struct mlxsw_sib_port *mlxsw_sib_port;
+ enum mlxsw_reg_pude_oper_status status;
+ u8 local_port;
+
+ local_port = mlxsw_reg_pude_local_port_get(pude_pl);
+ mlxsw_sib_port = mlxsw_sib->ports[local_port];
+ if (!mlxsw_sib_port) {
+ dev_warn(mlxsw_sib->bus_info->dev, "Port %d: Link event received for non-existent port\n",
+ local_port);
+ return;
+ }
+
+ status = mlxsw_reg_pude_oper_status_get(pude_pl);
+ mlxsw_sib_pude_ib_event_func(mlxsw_sib_port, status);
+}
+
+static struct mlxsw_event_listener mlxsw_sib_pude_event = {
+ .func = mlxsw_sib_pude_event_func,
+ .trap_id = MLXSW_TRAP_ID_PUDE,
+};
+
+static int mlxsw_sib_event_register(struct mlxsw_sib *mlxsw_sib,
+ enum mlxsw_event_trap_id trap_id)
+{
+ struct mlxsw_event_listener *el;
+ char hpkt_pl[MLXSW_REG_HPKT_LEN];
+ int err;
+
+ switch (trap_id) {
+ case MLXSW_TRAP_ID_PUDE:
+ el = &mlxsw_sib_pude_event;
+ break;
+ }
+ err = mlxsw_core_event_listener_register(mlxsw_sib->core, el,
+ mlxsw_sib);
+ if (err)
+ return err;
+
+ mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_FORWARD, trap_id);
+ err = mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(hpkt), hpkt_pl);
+ if (err)
+ goto err_event_trap_set;
+
+ return 0;
+
+err_event_trap_set:
+ mlxsw_core_event_listener_unregister(mlxsw_sib->core, el, mlxsw_sib);
+ return err;
+}
+
+static void mlxsw_sib_event_unregister(struct mlxsw_sib *mlxsw_sib,
+ enum mlxsw_event_trap_id trap_id)
+{
+ struct mlxsw_event_listener *el;
+
+ switch (trap_id) {
+ case MLXSW_TRAP_ID_PUDE:
+ el = &mlxsw_sib_pude_event;
+ break;
+ }
+ mlxsw_core_event_listener_unregister(mlxsw_sib->core, el, mlxsw_sib);
+}
+
+static int mlxsw_sib_init(struct mlxsw_core *mlxsw_core,
+ const struct mlxsw_bus_info *mlxsw_bus_info)
+{
+ struct mlxsw_sib *mlxsw_sib = mlxsw_core_driver_priv(mlxsw_core);
+ int err;
+
+ mlxsw_sib->core = mlxsw_core;
+ mlxsw_sib->bus_info = mlxsw_bus_info;
+
+ err = mlxsw_sib_ports_create(mlxsw_sib);
+ if (err) {
+ dev_err(mlxsw_sib->bus_info->dev, "Failed to create ports\n");
+ return err;
+ }
+
+ err = mlxsw_sib_event_register(mlxsw_sib, MLXSW_TRAP_ID_PUDE);
+ if (err) {
+ dev_err(mlxsw_sib->bus_info->dev, "Failed to register for PUDE events\n");
+ goto err_event_register;
+ }
+
+ return 0;
+
+err_event_register:
+ mlxsw_sib_ports_remove(mlxsw_sib);
+ return err;
+}
+
+static void mlxsw_sib_fini(struct mlxsw_core *mlxsw_core)
+{
+ struct mlxsw_sib *mlxsw_sib = mlxsw_core_driver_priv(mlxsw_core);
+
+ mlxsw_sib_event_unregister(mlxsw_sib, MLXSW_TRAP_ID_PUDE);
+ mlxsw_sib_ports_remove(mlxsw_sib);
+}
+
+static struct mlxsw_config_profile mlxsw_sib_config_profile = {
+ .used_max_system_port = 1,
+ .max_system_port = 48000,
+ .used_max_ib_mc = 1,
+ .max_ib_mc = 27,
+ .used_max_pkey = 1,
+ .max_pkey = 32,
+ .swid_config = {
+ {
+ .used_type = 1,
+ .type = MLXSW_PORT_SWID_TYPE_IB,
+ }
+ },
+ .resource_query_enable = 0,
+};
+
+static struct mlxsw_driver mlxsw_sib_driver = {
+ .kind = mlxsw_sib_driver_name,
+ .priv_size = sizeof(struct mlxsw_sib),
+ .init = mlxsw_sib_init,
+ .fini = mlxsw_sib_fini,
+ .txhdr_construct = mlxsw_sib_tx_v1_hdr_construct,
+ .txhdr_len = MLXSW_TXHDR_LEN,
+ .profile = &mlxsw_sib_config_profile,
+};
+
+static struct mlxsw_driver mlxsw_sib2_driver = {
+ .kind = mlxsw_sib2_driver_name,
+ .priv_size = sizeof(struct mlxsw_sib),
+ .init = mlxsw_sib_init,
+ .fini = mlxsw_sib_fini,
+ .txhdr_construct = mlxsw_sib_tx_v1_hdr_construct,
+ .txhdr_len = MLXSW_TXHDR_LEN,
+ .profile = &mlxsw_sib_config_profile,
+};
+
+static const struct pci_device_id mlxsw_sib_pci_id_table[] = {
+ {PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SWITCHIB), 0},
+ {0, },
+};
+
+static struct pci_driver mlxsw_sib_pci_driver = {
+ .name = mlxsw_sib_driver_name,
+ .id_table = mlxsw_sib_pci_id_table,
+};
+
+static const struct pci_device_id mlxsw_sib2_pci_id_table[] = {
+ {PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SWITCHIB2), 0},
+ {0, },
+};
+
+static struct pci_driver mlxsw_sib2_pci_driver = {
+ .name = mlxsw_sib2_driver_name,
+ .id_table = mlxsw_sib2_pci_id_table,
+};
+
+static int __init mlxsw_sib_module_init(void)
+{
+ int err;
+
+ err = mlxsw_core_driver_register(&mlxsw_sib_driver);
+ if (err)
+ return err;
+
+ err = mlxsw_core_driver_register(&mlxsw_sib2_driver);
+ if (err)
+ goto err_sib2_driver_register;
+
+ err = mlxsw_pci_driver_register(&mlxsw_sib_pci_driver);
+ if (err)
+ goto err_sib_pci_driver_register;
+
+ err = mlxsw_pci_driver_register(&mlxsw_sib2_pci_driver);
+ if (err)
+ goto err_sib2_pci_driver_register;
+
+ return 0;
+
+err_sib2_pci_driver_register:
+ mlxsw_pci_driver_unregister(&mlxsw_sib_pci_driver);
+err_sib_pci_driver_register:
+ mlxsw_core_driver_unregister(&mlxsw_sib2_driver);
+err_sib2_driver_register:
+ mlxsw_core_driver_unregister(&mlxsw_sib_driver);
+ return err;
+}
+
+static void __exit mlxsw_sib_module_exit(void)
+{
+ mlxsw_pci_driver_unregister(&mlxsw_sib2_pci_driver);
+ mlxsw_pci_driver_unregister(&mlxsw_sib_pci_driver);
+ mlxsw_core_driver_unregister(&mlxsw_sib2_driver);
+ mlxsw_core_driver_unregister(&mlxsw_sib_driver);
+}
+
+module_init(mlxsw_sib_module_init);
+module_exit(mlxsw_sib_module_exit);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Elad Raz <eladr@@mellanox.com>");
+MODULE_DESCRIPTION("Mellanox SwitchIB and SwitchIB-2 driver");
+MODULE_ALIAS("mlxsw_switchib2");
+MODULE_DEVICE_TABLE(pci, mlxsw_sib_pci_id_table);
+MODULE_DEVICE_TABLE(pci, mlxsw_sib2_pci_id_table);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index dc3c5ed..60f19fb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -3,7 +3,7 @@
* Copyright (c) 2015 Mellanox Technologies. All rights reserved.
* Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
* Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
+ * Copyright (c) 2015-2016 Elad Raz <eladr@mellanox.com>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
@@ -45,7 +45,6 @@
#include <linux/skbuff.h>
#include <linux/if_vlan.h>
#include <net/switchdev.h>
-#include <generated/utsrelease.h>
#include "pci.h"
#include "core.h"
@@ -53,6 +52,7 @@
#include "port.h"
#include "trap.h"
#include "txheader.h"
+#include "ib.h"
static const char mlxsw_sx_driver_name[] = "mlxsw_switchx2";
static const char mlxsw_sx_driver_version[] = "1.0";
@@ -76,11 +76,13 @@ struct mlxsw_sx_port_pcpu_stats {
};
struct mlxsw_sx_port {
- struct mlxsw_core_port core_port; /* must be first */
struct net_device *dev;
struct mlxsw_sx_port_pcpu_stats __percpu *pcpu_stats;
struct mlxsw_sx *mlxsw_sx;
u8 local_port;
+ struct {
+ u8 module;
+ } mapping;
};
/* tx_hdr_version
@@ -216,14 +218,14 @@ static int mlxsw_sx_port_oper_status_get(struct mlxsw_sx_port *mlxsw_sx_port,
return 0;
}
-static int mlxsw_sx_port_mtu_set(struct mlxsw_sx_port *mlxsw_sx_port, u16 mtu)
+static int __mlxsw_sx_port_mtu_set(struct mlxsw_sx_port *mlxsw_sx_port,
+ u16 mtu)
{
struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
char pmtu_pl[MLXSW_REG_PMTU_LEN];
int max_mtu;
int err;
- mtu += MLXSW_TXHDR_LEN + ETH_HLEN;
mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sx_port->local_port, 0);
err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(pmtu), pmtu_pl);
if (err)
@@ -237,6 +239,32 @@ static int mlxsw_sx_port_mtu_set(struct mlxsw_sx_port *mlxsw_sx_port, u16 mtu)
return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(pmtu), pmtu_pl);
}
+static int mlxsw_sx_port_mtu_eth_set(struct mlxsw_sx_port *mlxsw_sx_port,
+ u16 mtu)
+{
+ mtu += MLXSW_TXHDR_LEN + ETH_HLEN;
+ return __mlxsw_sx_port_mtu_set(mlxsw_sx_port, mtu);
+}
+
+static int mlxsw_sx_port_mtu_ib_set(struct mlxsw_sx_port *mlxsw_sx_port,
+ u16 mtu)
+{
+ return __mlxsw_sx_port_mtu_set(mlxsw_sx_port, mtu);
+}
+
+static int mlxsw_sx_port_ib_port_set(struct mlxsw_sx_port *mlxsw_sx_port,
+ u8 ib_port)
+{
+ struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
+ char plib_pl[MLXSW_REG_PLIB_LEN] = {0};
+ int err;
+
+ mlxsw_reg_plib_local_port_set(plib_pl, mlxsw_sx_port->local_port);
+ mlxsw_reg_plib_ib_port_set(plib_pl, ib_port);
+ err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(plib), plib_pl);
+ return err;
+}
+
static int mlxsw_sx_port_swid_set(struct mlxsw_sx_port *mlxsw_sx_port, u8 swid)
{
struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
@@ -256,18 +284,19 @@ mlxsw_sx_port_system_port_mapping_set(struct mlxsw_sx_port *mlxsw_sx_port)
return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sspr), sspr_pl);
}
-static int mlxsw_sx_port_module_check(struct mlxsw_sx_port *mlxsw_sx_port,
- bool *p_usable)
+static int mlxsw_sx_port_module_info_get(struct mlxsw_sx *mlxsw_sx,
+ u8 local_port, u8 *p_module,
+ u8 *p_width)
{
- struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
char pmlp_pl[MLXSW_REG_PMLP_LEN];
int err;
- mlxsw_reg_pmlp_pack(pmlp_pl, mlxsw_sx_port->local_port);
+ mlxsw_reg_pmlp_pack(pmlp_pl, local_port);
err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(pmlp), pmlp_pl);
if (err)
return err;
- *p_usable = mlxsw_reg_pmlp_width_get(pmlp_pl) ? true : false;
+ *p_module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0);
+ *p_width = mlxsw_reg_pmlp_width_get(pmlp_pl);
return 0;
}
@@ -345,7 +374,7 @@ static int mlxsw_sx_port_change_mtu(struct net_device *dev, int mtu)
struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
int err;
- err = mlxsw_sx_port_mtu_set(mlxsw_sx_port, mtu);
+ err = mlxsw_sx_port_mtu_eth_set(mlxsw_sx_port, mtu);
if (err)
return err;
dev->mtu = mtu;
@@ -384,12 +413,26 @@ mlxsw_sx_port_get_stats64(struct net_device *dev,
return stats;
}
+static int mlxsw_sx_port_get_phys_port_name(struct net_device *dev, char *name,
+ size_t len)
+{
+ struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
+ int err;
+
+ err = snprintf(name, len, "p%d", mlxsw_sx_port->mapping.module + 1);
+ if (err >= len)
+ return -EINVAL;
+
+ return 0;
+}
+
static const struct net_device_ops mlxsw_sx_port_netdev_ops = {
.ndo_open = mlxsw_sx_port_open,
.ndo_stop = mlxsw_sx_port_stop,
.ndo_start_xmit = mlxsw_sx_port_xmit,
.ndo_change_mtu = mlxsw_sx_port_change_mtu,
.ndo_get_stats64 = mlxsw_sx_port_get_stats64,
+ .ndo_get_phys_port_name = mlxsw_sx_port_get_phys_port_name,
};
static void mlxsw_sx_port_get_drvinfo(struct net_device *dev,
@@ -644,6 +687,7 @@ static const struct mlxsw_sx_port_link_mode mlxsw_sx_port_link_mode[] = {
};
#define MLXSW_SX_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sx_port_link_mode)
+#define MLXSW_SX_PORT_BASE_SPEED 10000 /* Mb/s */
static u32 mlxsw_sx_from_ptys_supported_port(u32 ptys_eth_proto)
{
@@ -743,14 +787,14 @@ static int mlxsw_sx_port_get_settings(struct net_device *dev,
u32 eth_proto_oper;
int err;
- mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sx_port->local_port, 0);
+ mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sx_port->local_port, 0);
err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(ptys), ptys_pl);
if (err) {
netdev_err(dev, "Failed to get proto");
return err;
}
- mlxsw_reg_ptys_unpack(ptys_pl, ð_proto_cap,
- ð_proto_admin, ð_proto_oper);
+ mlxsw_reg_ptys_eth_unpack(ptys_pl, ð_proto_cap,
+ ð_proto_admin, ð_proto_oper);
cmd->supported = mlxsw_sx_from_ptys_supported_port(eth_proto_cap) |
mlxsw_sx_from_ptys_supported_link(eth_proto_cap) |
@@ -791,6 +835,18 @@ static u32 mlxsw_sx_to_ptys_speed(u32 speed)
return ptys_proto;
}
+static u32 mlxsw_sx_to_ptys_upper_speed(u32 upper_speed)
+{
+ u32 ptys_proto = 0;
+ int i;
+
+ for (i = 0; i < MLXSW_SX_PORT_LINK_MODE_LEN; i++) {
+ if (mlxsw_sx_port_link_mode[i].speed <= upper_speed)
+ ptys_proto |= mlxsw_sx_port_link_mode[i].mask;
+ }
+ return ptys_proto;
+}
+
static int mlxsw_sx_port_set_settings(struct net_device *dev,
struct ethtool_cmd *cmd)
{
@@ -810,13 +866,14 @@ static int mlxsw_sx_port_set_settings(struct net_device *dev,
mlxsw_sx_to_ptys_advert_link(cmd->advertising) :
mlxsw_sx_to_ptys_speed(speed);
- mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sx_port->local_port, 0);
+ mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sx_port->local_port, 0);
err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(ptys), ptys_pl);
if (err) {
netdev_err(dev, "Failed to get proto");
return err;
}
- mlxsw_reg_ptys_unpack(ptys_pl, ð_proto_cap, ð_proto_admin, NULL);
+ mlxsw_reg_ptys_eth_unpack(ptys_pl, ð_proto_cap, ð_proto_admin,
+ NULL);
eth_proto_new = eth_proto_new & eth_proto_cap;
if (!eth_proto_new) {
@@ -826,7 +883,8 @@ static int mlxsw_sx_port_set_settings(struct net_device *dev,
if (eth_proto_new == eth_proto_admin)
return 0;
- mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sx_port->local_port, eth_proto_new);
+ mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sx_port->local_port,
+ eth_proto_new);
err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(ptys), ptys_pl);
if (err) {
netdev_err(dev, "Failed to set proto admin");
@@ -890,7 +948,7 @@ static const struct switchdev_ops mlxsw_sx_port_switchdev_ops = {
static int mlxsw_sx_hw_id_get(struct mlxsw_sx *mlxsw_sx)
{
- char spad_pl[MLXSW_REG_SPAD_LEN];
+ char spad_pl[MLXSW_REG_SPAD_LEN] = {0};
int err;
err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(spad), spad_pl);
@@ -937,13 +995,28 @@ static int mlxsw_sx_port_stp_state_set(struct mlxsw_sx_port *mlxsw_sx_port,
return err;
}
-static int mlxsw_sx_port_speed_set(struct mlxsw_sx_port *mlxsw_sx_port,
- u32 speed)
+static int mlxsw_sx_port_ib_speed_set(struct mlxsw_sx_port *mlxsw_sx_port,
+ u16 speed, u16 width)
{
struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
char ptys_pl[MLXSW_REG_PTYS_LEN];
- mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sx_port->local_port, speed);
+ mlxsw_reg_ptys_ib_pack(ptys_pl, mlxsw_sx_port->local_port, speed,
+ width);
+ return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(ptys), ptys_pl);
+}
+
+static int
+mlxsw_sx_port_speed_by_width_set(struct mlxsw_sx_port *mlxsw_sx_port, u8 width)
+{
+ struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
+ u32 upper_speed = MLXSW_SX_PORT_BASE_SPEED * width;
+ char ptys_pl[MLXSW_REG_PTYS_LEN];
+ u32 eth_proto_admin;
+
+ eth_proto_admin = mlxsw_sx_to_ptys_upper_speed(upper_speed);
+ mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sx_port->local_port,
+ eth_proto_admin);
return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(ptys), ptys_pl);
}
@@ -958,11 +1031,11 @@ mlxsw_sx_port_mac_learning_mode_set(struct mlxsw_sx_port *mlxsw_sx_port,
return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(spmlr), spmlr_pl);
}
-static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
+static int __mlxsw_sx_port_eth_create(struct mlxsw_sx *mlxsw_sx, u8 local_port,
+ u8 module, u8 width)
{
struct mlxsw_sx_port *mlxsw_sx_port;
struct net_device *dev;
- bool usable;
int err;
dev = alloc_etherdev(sizeof(struct mlxsw_sx_port));
@@ -973,6 +1046,7 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
mlxsw_sx_port->dev = dev;
mlxsw_sx_port->mlxsw_sx = mlxsw_sx;
mlxsw_sx_port->local_port = local_port;
+ mlxsw_sx_port->mapping.module = module;
mlxsw_sx_port->pcpu_stats =
netdev_alloc_pcpu_stats(struct mlxsw_sx_port_pcpu_stats);
@@ -1005,19 +1079,6 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
*/
dev->needed_headroom = MLXSW_TXHDR_LEN;
- err = mlxsw_sx_port_module_check(mlxsw_sx_port, &usable);
- if (err) {
- dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to check module\n",
- mlxsw_sx_port->local_port);
- goto err_port_module_check;
- }
-
- if (!usable) {
- dev_dbg(mlxsw_sx->bus_info->dev, "Port %d: Not usable, skipping initialization\n",
- mlxsw_sx_port->local_port);
- goto port_not_usable;
- }
-
err = mlxsw_sx_port_system_port_mapping_set(mlxsw_sx_port);
if (err) {
dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set system port mapping\n",
@@ -1032,15 +1093,14 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
goto err_port_swid_set;
}
- err = mlxsw_sx_port_speed_set(mlxsw_sx_port,
- MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4);
+ err = mlxsw_sx_port_speed_by_width_set(mlxsw_sx_port, width);
if (err) {
dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set speed\n",
mlxsw_sx_port->local_port);
goto err_port_speed_set;
}
- err = mlxsw_sx_port_mtu_set(mlxsw_sx_port, ETH_DATA_LEN);
+ err = mlxsw_sx_port_mtu_eth_set(mlxsw_sx_port, ETH_DATA_LEN);
if (err) {
dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set MTU\n",
mlxsw_sx_port->local_port);
@@ -1075,29 +1135,20 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
goto err_register_netdev;
}
- err = mlxsw_core_port_init(mlxsw_sx->core, &mlxsw_sx_port->core_port,
- mlxsw_sx_port->local_port, dev, false, 0);
- if (err) {
- dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to init core port\n",
- mlxsw_sx_port->local_port);
- goto err_core_port_init;
- }
-
+ mlxsw_core_port_eth_set(mlxsw_sx->core, mlxsw_sx_port->local_port,
+ mlxsw_sx_port, dev, false, 0);
mlxsw_sx->ports[local_port] = mlxsw_sx_port;
return 0;
-err_core_port_init:
- unregister_netdev(dev);
err_register_netdev:
err_port_mac_learning_mode_set:
err_port_stp_state_set:
err_port_admin_status_set:
err_port_mtu_set:
err_port_speed_set:
+ mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT);
err_port_swid_set:
err_port_system_port_mapping_set:
-port_not_usable:
-err_port_module_check:
err_dev_addr_get:
free_percpu(mlxsw_sx_port->pcpu_stats);
err_alloc_stats:
@@ -1105,31 +1156,168 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port)
return err;
}
-static void mlxsw_sx_port_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port)
+static int mlxsw_sx_port_eth_create(struct mlxsw_sx *mlxsw_sx, u8 local_port,
+ u8 module, u8 width)
+{
+ int err;
+
+ err = mlxsw_core_port_init(mlxsw_sx->core, local_port);
+ if (err) {
+ dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to init core port\n",
+ local_port);
+ return err;
+ }
+ err = __mlxsw_sx_port_eth_create(mlxsw_sx, local_port, module, width);
+ if (err)
+ goto err_port_create;
+
+ return 0;
+
+err_port_create:
+ mlxsw_core_port_fini(mlxsw_sx->core, local_port);
+ return err;
+}
+
+static void __mlxsw_sx_port_eth_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port)
{
struct mlxsw_sx_port *mlxsw_sx_port = mlxsw_sx->ports[local_port];
- if (!mlxsw_sx_port)
- return;
- mlxsw_core_port_fini(&mlxsw_sx_port->core_port);
+ mlxsw_core_port_clear(mlxsw_sx->core, local_port, mlxsw_sx);
unregister_netdev(mlxsw_sx_port->dev); /* This calls ndo_stop */
+ mlxsw_sx->ports[local_port] = NULL;
mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT);
free_percpu(mlxsw_sx_port->pcpu_stats);
free_netdev(mlxsw_sx_port->dev);
}
+static bool mlxsw_sx_port_created(struct mlxsw_sx *mlxsw_sx, u8 local_port)
+{
+ return mlxsw_sx->ports[local_port] != NULL;
+}
+
+static int __mlxsw_sx_port_ib_create(struct mlxsw_sx *mlxsw_sx, u8 local_port,
+ u8 module, u8 width)
+{
+ struct mlxsw_sx_port *mlxsw_sx_port;
+ int err;
+
+ mlxsw_sx_port = kzalloc(sizeof(*mlxsw_sx_port), GFP_KERNEL);
+ if (!mlxsw_sx_port)
+ return -ENOMEM;
+ mlxsw_sx_port->mlxsw_sx = mlxsw_sx;
+ mlxsw_sx_port->local_port = local_port;
+ mlxsw_sx_port->mapping.module = module;
+
+ err = mlxsw_sx_port_system_port_mapping_set(mlxsw_sx_port);
+ if (err) {
+ dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set system port mapping\n",
+ mlxsw_sx_port->local_port);
+ goto err_port_system_port_mapping_set;
+ }
+
+ /* Adding port to Infiniband swid (1) */
+ err = mlxsw_sx_port_swid_set(mlxsw_sx_port, 1);
+ if (err) {
+ dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set SWID\n",
+ mlxsw_sx_port->local_port);
+ goto err_port_swid_set;
+ }
+
+ /* Expose the IB port number as it's front panel name */
+ err = mlxsw_sx_port_ib_port_set(mlxsw_sx_port, module + 1);
+ if (err) {
+ dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set IB port\n",
+ mlxsw_sx_port->local_port);
+ goto err_port_ib_set;
+ }
+
+ /* Supports all speeds from SDR to FDR (bitmask) and support bus width
+ * of 1x, 2x and 4x (3 bits bitmask)
+ */
+ err = mlxsw_sx_port_ib_speed_set(mlxsw_sx_port,
+ MLXSW_REG_PTYS_IB_SPEED_EDR - 1,
+ BIT(3) - 1);
+ if (err) {
+ dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set speed\n",
+ mlxsw_sx_port->local_port);
+ goto err_port_speed_set;
+ }
+
+ /* Change to the maximum MTU the device supports, the SMA will take
+ * care of the active MTU
+ */
+ err = mlxsw_sx_port_mtu_ib_set(mlxsw_sx_port, MLXSW_IB_DEFAULT_MTU);
+ if (err) {
+ dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set MTU\n",
+ mlxsw_sx_port->local_port);
+ goto err_port_mtu_set;
+ }
+
+ err = mlxsw_sx_port_admin_status_set(mlxsw_sx_port, true);
+ if (err) {
+ dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to change admin state to UP\n",
+ mlxsw_sx_port->local_port);
+ goto err_port_admin_set;
+ }
+
+ mlxsw_core_port_ib_set(mlxsw_sx->core, mlxsw_sx_port->local_port,
+ mlxsw_sx_port);
+ mlxsw_sx->ports[local_port] = mlxsw_sx_port;
+ return 0;
+
+err_port_admin_set:
+err_port_mtu_set:
+err_port_speed_set:
+err_port_ib_set:
+ mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT);
+err_port_swid_set:
+err_port_system_port_mapping_set:
+ kfree(mlxsw_sx_port);
+ return err;
+}
+
+static void __mlxsw_sx_port_ib_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port)
+{
+ struct mlxsw_sx_port *mlxsw_sx_port = mlxsw_sx->ports[local_port];
+
+ mlxsw_core_port_clear(mlxsw_sx->core, local_port, mlxsw_sx);
+ mlxsw_sx->ports[local_port] = NULL;
+ mlxsw_sx_port_admin_status_set(mlxsw_sx_port, false);
+ mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT);
+ kfree(mlxsw_sx_port);
+}
+
+static void __mlxsw_sx_port_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port)
+{
+ enum devlink_port_type port_type =
+ mlxsw_core_port_type_get(mlxsw_sx->core, local_port);
+
+ if (port_type == DEVLINK_PORT_TYPE_ETH)
+ __mlxsw_sx_port_eth_remove(mlxsw_sx, local_port);
+ else if (port_type == DEVLINK_PORT_TYPE_IB)
+ __mlxsw_sx_port_ib_remove(mlxsw_sx, local_port);
+}
+
+static void mlxsw_sx_port_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port)
+{
+ __mlxsw_sx_port_remove(mlxsw_sx, local_port);
+ mlxsw_core_port_fini(mlxsw_sx->core, local_port);
+}
+
static void mlxsw_sx_ports_remove(struct mlxsw_sx *mlxsw_sx)
{
int i;
for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++)
- mlxsw_sx_port_remove(mlxsw_sx, i);
+ if (mlxsw_sx_port_created(mlxsw_sx, i))
+ mlxsw_sx_port_remove(mlxsw_sx, i);
kfree(mlxsw_sx->ports);
}
static int mlxsw_sx_ports_create(struct mlxsw_sx *mlxsw_sx)
{
size_t alloc_size;
+ u8 module, width;
int i;
int err;
@@ -1139,25 +1327,57 @@ static int mlxsw_sx_ports_create(struct mlxsw_sx *mlxsw_sx)
return -ENOMEM;
for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++) {
- err = mlxsw_sx_port_create(mlxsw_sx, i);
+ err = mlxsw_sx_port_module_info_get(mlxsw_sx, i, &module,
+ &width);
+ if (err)
+ goto err_port_module_info_get;
+ if (!width)
+ continue;
+ err = mlxsw_sx_port_eth_create(mlxsw_sx, i, module, width);
if (err)
goto err_port_create;
}
return 0;
err_port_create:
+err_port_module_info_get:
for (i--; i >= 1; i--)
- mlxsw_sx_port_remove(mlxsw_sx, i);
+ if (mlxsw_sx_port_created(mlxsw_sx, i))
+ mlxsw_sx_port_remove(mlxsw_sx, i);
kfree(mlxsw_sx->ports);
return err;
}
+static void mlxsw_sx_pude_eth_event_func(struct mlxsw_sx_port *mlxsw_sx_port,
+ enum mlxsw_reg_pude_oper_status status)
+{
+ if (status == MLXSW_PORT_OPER_STATUS_UP) {
+ netdev_info(mlxsw_sx_port->dev, "link up\n");
+ netif_carrier_on(mlxsw_sx_port->dev);
+ } else {
+ netdev_info(mlxsw_sx_port->dev, "link down\n");
+ netif_carrier_off(mlxsw_sx_port->dev);
+ }
+}
+
+static void mlxsw_sx_pude_ib_event_func(struct mlxsw_sx_port *mlxsw_sx_port,
+ enum mlxsw_reg_pude_oper_status status)
+{
+ if (status == MLXSW_PORT_OPER_STATUS_UP)
+ pr_info("ib link for port %d - up\n",
+ mlxsw_sx_port->mapping.module + 1);
+ else
+ pr_info("ib link for port %d - down\n",
+ mlxsw_sx_port->mapping.module + 1);
+}
+
static void mlxsw_sx_pude_event_func(const struct mlxsw_reg_info *reg,
char *pude_pl, void *priv)
{
struct mlxsw_sx *mlxsw_sx = priv;
struct mlxsw_sx_port *mlxsw_sx_port;
enum mlxsw_reg_pude_oper_status status;
+ enum devlink_port_type port_type;
u8 local_port;
local_port = mlxsw_reg_pude_local_port_get(pude_pl);
@@ -1169,13 +1389,11 @@ static void mlxsw_sx_pude_event_func(const struct mlxsw_reg_info *reg,
}
status = mlxsw_reg_pude_oper_status_get(pude_pl);
- if (status == MLXSW_PORT_OPER_STATUS_UP) {
- netdev_info(mlxsw_sx_port->dev, "link up\n");
- netif_carrier_on(mlxsw_sx_port->dev);
- } else {
- netdev_info(mlxsw_sx_port->dev, "link down\n");
- netif_carrier_off(mlxsw_sx_port->dev);
- }
+ port_type = mlxsw_core_port_type_get(mlxsw_sx->core, local_port);
+ if (port_type == DEVLINK_PORT_TYPE_ETH)
+ mlxsw_sx_pude_eth_event_func(mlxsw_sx_port, status);
+ else if (port_type == DEVLINK_PORT_TYPE_IB)
+ mlxsw_sx_pude_ib_event_func(mlxsw_sx_port, status);
}
static struct mlxsw_event_listener mlxsw_sx_pude_event = {
@@ -1249,6 +1467,33 @@ static void mlxsw_sx_rx_listener_func(struct sk_buff *skb, u8 local_port,
netif_receive_skb(skb);
}
+static int mlxsw_sx_port_type_set(struct mlxsw_core *mlxsw_core, u8 local_port,
+ enum devlink_port_type new_type)
+{
+ struct mlxsw_sx *mlxsw_sx = mlxsw_core_driver_priv(mlxsw_core);
+ u8 module, width;
+ int err;
+
+ if (new_type == DEVLINK_PORT_TYPE_AUTO)
+ return -EOPNOTSUPP;
+
+ __mlxsw_sx_port_remove(mlxsw_sx, local_port);
+ err = mlxsw_sx_port_module_info_get(mlxsw_sx, local_port, &module,
+ &width);
+ if (err)
+ goto err_port_module_info_get;
+
+ if (new_type == DEVLINK_PORT_TYPE_ETH)
+ err = __mlxsw_sx_port_eth_create(mlxsw_sx, local_port, module,
+ width);
+ else if (new_type == DEVLINK_PORT_TYPE_IB)
+ err = __mlxsw_sx_port_ib_create(mlxsw_sx, local_port, module,
+ width);
+
+err_port_module_info_get:
+ return err;
+}
+
static const struct mlxsw_rx_listener mlxsw_sx_rx_listener[] = {
{
.func = mlxsw_sx_rx_listener_func,
@@ -1534,13 +1779,17 @@ static struct mlxsw_config_profile mlxsw_sx_config_profile = {
.used_flood_mode = 1,
.flood_mode = 3,
.used_max_ib_mc = 1,
- .max_ib_mc = 0,
+ .max_ib_mc = 6,
.used_max_pkey = 1,
.max_pkey = 0,
.swid_config = {
{
.used_type = 1,
.type = MLXSW_PORT_SWID_TYPE_ETH,
+ },
+ {
+ .used_type = 1,
+ .type = MLXSW_PORT_SWID_TYPE_IB,
}
},
.resource_query_enable = 0,
@@ -1554,6 +1803,7 @@ static struct mlxsw_driver mlxsw_sx_driver = {
.txhdr_construct = mlxsw_sx_txhdr_construct,
.txhdr_len = MLXSW_TXHDR_LEN,
.profile = &mlxsw_sx_config_profile,
+ .port_type_set = mlxsw_sx_port_type_set,
};
static const struct pci_device_id mlxsw_sx_pci_id_table[] = {
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_bpf.h b/drivers/net/ethernet/netronome/nfp/nfp_bpf.h
index 87aa8a3..76a19f1 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_bpf.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_bpf.h
@@ -62,6 +62,7 @@ enum nfp_bpf_action_type {
NN_ACT_TC_DROP,
NN_ACT_TC_REDIR,
NN_ACT_DIRECT,
+ NN_ACT_XDP,
};
/* Software register representation, hardware encoding in asm.h */
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_bpf_jit.c b/drivers/net/ethernet/netronome/nfp/nfp_bpf_jit.c
index f8df530..335beb8 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_bpf_jit.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_bpf_jit.c
@@ -1126,7 +1126,7 @@ static int data_ind_ld4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
meta->insn.src_reg * 2, true, 4);
}
-static int mem_ldx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+static int mem_ldx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
if (meta->insn.off == offsetof(struct sk_buff, len))
emit_alu(nfp_prog, reg_both(meta->insn.dst_reg * 2),
@@ -1134,12 +1134,42 @@ static int mem_ldx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
else
return -ENOTSUPP;
- wrp_immed(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1), 0);
+ return 0;
+}
+
+static int mem_ldx4_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+ u32 dst = reg_both(meta->insn.dst_reg * 2);
+
+ if (meta->insn.off != offsetof(struct xdp_md, data) &&
+ meta->insn.off != offsetof(struct xdp_md, data_end))
+ return -ENOTSUPP;
+
+ emit_alu(nfp_prog, dst, reg_none(), ALU_OP_NONE, NFP_BPF_ABI_PKT);
+
+ if (meta->insn.off == offsetof(struct xdp_md, data))
+ return 0;
+
+ emit_alu(nfp_prog, dst, dst, ALU_OP_ADD, NFP_BPF_ABI_LEN);
return 0;
}
-static int mem_stx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+static int mem_ldx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+ int ret;
+
+ if (nfp_prog->act == NN_ACT_XDP)
+ ret = mem_ldx4_xdp(nfp_prog, meta);
+ else
+ ret = mem_ldx4_skb(nfp_prog, meta);
+
+ wrp_immed(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1), 0);
+
+ return ret;
+}
+
+static int mem_stx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
if (meta->insn.off == offsetof(struct sk_buff, mark))
return wrp_set_mark(nfp_prog, meta->insn.src_reg * 2);
@@ -1147,6 +1177,18 @@ static int mem_stx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
return -ENOTSUPP;
}
+static int mem_stx4_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+ return -ENOTSUPP;
+}
+
+static int mem_stx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+ if (nfp_prog->act == NN_ACT_XDP)
+ return mem_stx4_xdp(nfp_prog, meta);
+ return mem_stx4_skb(nfp_prog, meta);
+}
+
static int jump(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
{
if (meta->insn.off < 0) /* TODO */
@@ -1530,6 +1572,47 @@ static void nfp_outro_tc_da(struct nfp_prog *nfp_prog)
emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_b(2), SHF_SC_L_SHF, 16);
}
+static void nfp_outro_xdp(struct nfp_prog *nfp_prog)
+{
+ /* XDP return codes:
+ * 0 aborted 0x82 -> drop, count as stat3
+ * 1 drop 0x22 -> drop, count as stat1
+ * 2 pass 0x11 -> pass, count as stat0
+ * 3 tx 0x44 -> redir, count as stat2
+ * * unknown 0x82 -> drop, count as stat3
+ */
+ /* Target for aborts */
+ nfp_prog->tgt_abort = nfp_prog_current_offset(nfp_prog);
+
+ emit_br_def(nfp_prog, nfp_prog->tgt_done, 2);
+
+ emit_alu(nfp_prog, reg_a(0),
+ reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS);
+ emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_imm(0x82), SHF_SC_L_SHF, 16);
+
+ /* Target for normal exits */
+ nfp_prog->tgt_out = nfp_prog_current_offset(nfp_prog);
+
+ /* if R0 > 3 jump to abort */
+ emit_alu(nfp_prog, reg_none(), reg_imm(3), ALU_OP_SUB, reg_b(0));
+ emit_br(nfp_prog, BR_BLO, nfp_prog->tgt_abort, 0);
+
+ wrp_immed(nfp_prog, reg_b(2), 0x44112282);
+
+ emit_shf(nfp_prog, reg_a(1),
+ reg_none(), SHF_OP_NONE, reg_b(0), SHF_SC_L_SHF, 3);
+
+ emit_alu(nfp_prog, reg_none(), reg_a(1), ALU_OP_OR, reg_imm(0));
+ emit_shf(nfp_prog, reg_b(2),
+ reg_imm(0xff), SHF_OP_AND, reg_b(2), SHF_SC_R_SHF, 0);
+
+ emit_br_def(nfp_prog, nfp_prog->tgt_done, 2);
+
+ emit_alu(nfp_prog, reg_a(0),
+ reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS);
+ emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_b(2), SHF_SC_L_SHF, 16);
+}
+
static void nfp_outro(struct nfp_prog *nfp_prog)
{
switch (nfp_prog->act) {
@@ -1540,6 +1623,9 @@ static void nfp_outro(struct nfp_prog *nfp_prog)
case NN_ACT_TC_REDIR:
nfp_outro_tc_legacy(nfp_prog);
break;
+ case NN_ACT_XDP:
+ nfp_outro_xdp(nfp_prog);
+ break;
}
}
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_bpf_verifier.c b/drivers/net/ethernet/netronome/nfp/nfp_bpf_verifier.c
index 144cae8..b3361f9 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_bpf_verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_bpf_verifier.c
@@ -80,6 +80,9 @@ nfp_bpf_check_exit(struct nfp_prog *nfp_prog,
{
const struct bpf_reg_state *reg0 = &env->cur_state.regs[0];
+ if (nfp_prog->act == NN_ACT_XDP)
+ return 0;
+
if (reg0->type != CONST_IMM) {
pr_info("unsupported exit state: %d, imm: %llx\n",
reg0->type, reg0->imm);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index ed824e1..2115f44 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -75,7 +75,6 @@
/* Default size for MTU and freelist buffer sizes */
#define NFP_NET_DEFAULT_MTU 1500
-#define NFP_NET_DEFAULT_RX_BUFSZ 2048
/* Maximum number of bytes prepended to a packet */
#define NFP_NET_MAX_PREPEND 64
@@ -88,6 +87,9 @@
/* Queue/Ring definitions */
#define NFP_NET_MAX_TX_RINGS 64 /* Max. # of Tx rings per device */
#define NFP_NET_MAX_RX_RINGS 64 /* Max. # of Rx rings per device */
+#define NFP_NET_MAX_R_VECS (NFP_NET_MAX_TX_RINGS > NFP_NET_MAX_RX_RINGS ? \
+ NFP_NET_MAX_TX_RINGS : NFP_NET_MAX_RX_RINGS)
+#define NFP_NET_MAX_IRQS (NFP_NET_NON_Q_VECTORS + NFP_NET_MAX_R_VECS)
#define NFP_NET_MIN_TX_DESCS 256 /* Min. # of Tx descs per ring */
#define NFP_NET_MIN_RX_DESCS 256 /* Min. # of Rx descs per ring */
@@ -102,6 +104,10 @@
/* Offload definitions */
#define NFP_NET_N_VXLAN_PORTS (NFP_NET_CFG_VXLAN_SZ / sizeof(__be16))
+#define NFP_NET_RX_BUF_HEADROOM (NET_SKB_PAD + NET_IP_ALIGN)
+#define NFP_NET_RX_BUF_NON_DATA (NFP_NET_RX_BUF_HEADROOM + \
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+
/* Forward declarations */
struct nfp_net;
struct nfp_net_r_vector;
@@ -165,7 +171,10 @@ struct nfp_net_tx_desc {
* on the head's buffer). Equal to skb->len for non-TSO packets.
*/
struct nfp_net_tx_buf {
- struct sk_buff *skb;
+ union {
+ struct sk_buff *skb;
+ void *frag;
+ };
dma_addr_t dma_addr;
short int fidx;
u16 pkt_cnt;
@@ -278,11 +287,11 @@ struct nfp_net_rx_hash {
/**
* struct nfp_net_rx_buf - software RX buffer descriptor
- * @skb: sk_buff associated with this buffer
+ * @frag: page fragment buffer
* @dma_addr: DMA mapping address of the buffer
*/
struct nfp_net_rx_buf {
- struct sk_buff *skb;
+ void *frag;
dma_addr_t dma_addr;
};
@@ -335,6 +344,7 @@ struct nfp_net_rx_ring {
* @napi: NAPI structure for this ring vec
* @tx_ring: Pointer to TX ring
* @rx_ring: Pointer to RX ring
+ * @xdp_ring: Pointer to an extra TX ring for XDP
* @irq_idx: Index into MSI-X table
* @rx_sync: Seqlock for atomic updates of RX stats
* @rx_pkts: Number of received packets
@@ -378,6 +388,8 @@ struct nfp_net_r_vector {
u64 hw_csum_rx_inner_ok;
u64 hw_csum_rx_error;
+ struct nfp_net_tx_ring *xdp_ring;
+
struct u64_stats_sync tx_sync;
u64 tx_pkts;
u64 tx_bytes;
@@ -421,12 +433,13 @@ struct nfp_stat_pair {
* @netdev: Backpointer to net_device structure
* @nfp_fallback: Is the driver used in fallback mode?
* @is_vf: Is the driver attached to a VF?
- * @is_nfp3200: Is the driver for a NFP-3200 card?
* @fw_loaded: Is the firmware loaded?
* @bpf_offload_skip_sw: Offloaded BPF program will not be rerun by cls_bpf
+ * @bpf_offload_xdp: Offloaded BPF program is XDP
* @ctrl: Local copy of the control register/word.
* @fl_bufsz: Currently configured size of the freelist buffers
* @rx_offset: Offset in the RX buffers where packet data starts
+ * @xdp_prog: Installed XDP program
* @cpp: Pointer to the CPP handle
* @nfp_dev_cpp: Pointer to the NFP Device handle
* @ctrl_area: Pointer to the CPP area for the control BAR
@@ -446,12 +459,13 @@ struct nfp_stat_pair {
* @max_tx_rings: Maximum number of TX rings supported by the Firmware
* @max_rx_rings: Maximum number of RX rings supported by the Firmware
* @num_tx_rings: Currently configured number of TX rings
+ * @num_stack_tx_rings: Number of TX rings used by the stack (not XDP)
* @num_rx_rings: Currently configured number of RX rings
* @txd_cnt: Size of the TX ring in number of descriptors
* @rxd_cnt: Size of the RX ring in number of descriptors
* @tx_rings: Array of pre-allocated TX ring structures
* @rx_rings: Array of pre-allocated RX ring structures
- * @num_irqs: Number of allocated interrupt vectors
+ * @max_r_vecs: Number of allocated interrupt vectors for RX/TX
* @num_r_vecs: Number of used ring vectors
* @r_vecs: Pre-allocated array of ring vectors
* @irq_entries: Pre-allocated array of MSI-X entries
@@ -487,15 +501,17 @@ struct nfp_net {
unsigned nfp_fallback:1;
unsigned is_vf:1;
- unsigned is_nfp3200:1;
unsigned fw_loaded:1;
unsigned bpf_offload_skip_sw:1;
+ unsigned bpf_offload_xdp:1;
u32 ctrl;
u32 fl_bufsz;
u32 rx_offset;
+ struct bpf_prog *xdp_prog;
+
struct nfp_net_tx_ring *tx_rings;
struct nfp_net_rx_ring *rx_rings;
@@ -524,11 +540,12 @@ struct nfp_net {
struct timer_list rx_filter_stats_timer;
spinlock_t rx_filter_lock;
- int max_tx_rings;
- int max_rx_rings;
+ unsigned int max_tx_rings;
+ unsigned int max_rx_rings;
- int num_tx_rings;
- int num_rx_rings;
+ unsigned int num_tx_rings;
+ unsigned int num_stack_tx_rings;
+ unsigned int num_rx_rings;
int stride_tx;
int stride_rx;
@@ -536,11 +553,10 @@ struct nfp_net {
int txd_cnt;
int rxd_cnt;
- u8 num_irqs;
- u8 num_r_vecs;
- struct nfp_net_r_vector r_vecs[NFP_NET_MAX_TX_RINGS];
- struct msix_entry irq_entries[NFP_NET_NON_Q_VECTORS +
- NFP_NET_MAX_TX_RINGS];
+ unsigned int max_r_vecs;
+ unsigned int num_r_vecs;
+ struct nfp_net_r_vector r_vecs[NFP_NET_MAX_R_VECS];
+ struct msix_entry irq_entries[NFP_NET_MAX_IRQS];
irq_handler_t lsc_handler;
char lsc_name[IFNAMSIZ + 8];
@@ -580,6 +596,13 @@ struct nfp_net {
struct dentry *debugfs_dir;
};
+struct nfp_net_ring_set {
+ unsigned int n_rings;
+ unsigned int mtu;
+ unsigned int dcnt;
+ void *rings;
+};
+
/* Functions to read/write from/to a BAR
* Performs any endian conversion necessary.
*/
@@ -593,16 +616,13 @@ static inline void nn_writeb(struct nfp_net *nn, int off, u8 val)
writeb(val, nn->ctrl_bar + off);
}
-/* NFP-3200 can't handle 16-bit accesses too well */
static inline u16 nn_readw(struct nfp_net *nn, int off)
{
- WARN_ON_ONCE(nn->is_nfp3200);
return readw(nn->ctrl_bar + off);
}
static inline void nn_writew(struct nfp_net *nn, int off, u16 val)
{
- WARN_ON_ONCE(nn->is_nfp3200);
writew(val, nn->ctrl_bar + off);
}
@@ -650,7 +670,7 @@ static inline void nn_pci_flush(struct nfp_net *nn)
#define NFP_QCP_QUEUE_STS_HI 0x000c
#define NFP_QCP_QUEUE_STS_HI_WRITEPTR_mask 0x3ffff
-/* The offset of a QCP queues in the PCIe Target (same on NFP3200 and NFP6000 */
+/* The offset of a QCP queues in the PCIe Target */
#define NFP_PCIE_QUEUE(_q) (0x80000 + (NFP_QCP_QUEUE_ADDR_SZ * ((_q) & 0xff)))
/* nfp_qcp_ptr - Read or Write Pointer of a queue */
@@ -757,8 +777,9 @@ extern const char nfp_net_driver_version[];
void nfp_net_get_fw_version(struct nfp_net_fw_version *fw_ver,
void __iomem *ctrl_bar);
-struct nfp_net *nfp_net_netdev_alloc(struct pci_dev *pdev,
- int max_tx_rings, int max_rx_rings);
+struct nfp_net *
+nfp_net_netdev_alloc(struct pci_dev *pdev,
+ unsigned int max_tx_rings, unsigned int max_rx_rings);
void nfp_net_netdev_free(struct nfp_net *nn);
int nfp_net_netdev_init(struct net_device *netdev);
void nfp_net_netdev_clean(struct net_device *netdev);
@@ -770,7 +791,9 @@ void nfp_net_rss_write_key(struct nfp_net *nn);
void nfp_net_coalesce_write_cfg(struct nfp_net *nn);
int nfp_net_irqs_alloc(struct nfp_net *nn);
void nfp_net_irqs_disable(struct nfp_net *nn);
-int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt);
+int
+nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog,
+ struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx);
#ifdef CONFIG_NFP_NET_DEBUG
void nfp_net_debugfs_create(void);
@@ -796,8 +819,6 @@ static inline void nfp_net_debugfs_adapter_del(struct nfp_net *nn)
#endif /* CONFIG_NFP_NET_DEBUG */
void nfp_net_filter_stats_timer(unsigned long data);
-int
-nfp_net_bpf_offload(struct nfp_net *nn, u32 handle, __be16 proto,
- struct tc_cls_bpf_offload *cls_bpf);
+int nfp_net_bpf_offload(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf);
#endif /* _NFP_NET_H_ */
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index d365760..eb37157 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -41,6 +41,7 @@
* Chris Telfer <chris.telfer@netronome.com>
*/
+#include <linux/bpf.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>
@@ -50,6 +51,7 @@
#include <linux/interrupt.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
+#include <linux/page_ref.h>
#include <linux/pci.h>
#include <linux/pci_regs.h>
#include <linux/msi.h>
@@ -80,6 +82,22 @@ void nfp_net_get_fw_version(struct nfp_net_fw_version *fw_ver,
put_unaligned_le32(reg, fw_ver);
}
+static dma_addr_t
+nfp_net_dma_map_rx(struct nfp_net *nn, void *frag, unsigned int bufsz,
+ int direction)
+{
+ return dma_map_single(&nn->pdev->dev, frag + NFP_NET_RX_BUF_HEADROOM,
+ bufsz - NFP_NET_RX_BUF_NON_DATA, direction);
+}
+
+static void
+nfp_net_dma_unmap_rx(struct nfp_net *nn, dma_addr_t dma_addr,
+ unsigned int bufsz, int direction)
+{
+ dma_unmap_single(&nn->pdev->dev, dma_addr,
+ bufsz - NFP_NET_RX_BUF_NON_DATA, direction);
+}
+
/* Firmware reconfig
*
* Firmware reconfig may take a while so we have two versions of it -
@@ -249,43 +267,14 @@ int nfp_net_reconfig(struct nfp_net *nn, u32 update)
*/
/**
- * nfp_net_irq_unmask_msix() - Unmask MSI-X after automasking
- * @nn: NFP Network structure
- * @entry_nr: MSI-X table entry
- *
- * Clear the MSI-X table mask bit for the given entry bypassing Linux irq
- * handling subsystem. Use *only* to reenable automasked vectors.
- */
-static void nfp_net_irq_unmask_msix(struct nfp_net *nn, unsigned int entry_nr)
-{
- struct list_head *msi_head = &nn->pdev->dev.msi_list;
- struct msi_desc *entry;
- u32 off;
-
- /* All MSI-Xs have the same mask_base */
- entry = list_first_entry(msi_head, struct msi_desc, list);
-
- off = (PCI_MSIX_ENTRY_SIZE * entry_nr) +
- PCI_MSIX_ENTRY_VECTOR_CTRL;
- writel(0, entry->mask_base + off);
- readl(entry->mask_base);
-}
-
-/**
* nfp_net_irq_unmask() - Unmask automasked interrupt
* @nn: NFP Network structure
* @entry_nr: MSI-X table entry
*
- * If MSI-X auto-masking is enabled clear the mask bit, otherwise
- * clear the ICR for the entry.
+ * Clear the ICR for the IRQ entry.
*/
static void nfp_net_irq_unmask(struct nfp_net *nn, unsigned int entry_nr)
{
- if (nn->ctrl & NFP_NET_CFG_CTRL_MSIXAUTO) {
- nfp_net_irq_unmask_msix(nn, entry_nr);
- return;
- }
-
nn_writeb(nn, NFP_NET_CFG_ICR(entry_nr), NFP_NET_CFG_ICR_UNMASKED);
nn_pci_flush(nn);
}
@@ -320,28 +309,6 @@ static int nfp_net_msix_alloc(struct nfp_net *nn, int nr_vecs)
}
/**
- * nfp_net_irqs_wanted() - Work out how many interrupt vectors we want
- * @nn: NFP Network structure
- *
- * We want a vector per CPU (or ring), whatever is smaller plus
- * NFP_NET_NON_Q_VECTORS for LSC etc.
- *
- * Return: Number of interrupts wanted
- */
-static int nfp_net_irqs_wanted(struct nfp_net *nn)
-{
- int ncpus;
- int vecs;
-
- ncpus = num_online_cpus();
-
- vecs = max_t(int, nn->num_tx_rings, nn->num_rx_rings);
- vecs = min_t(int, vecs, ncpus);
-
- return vecs + NFP_NET_NON_Q_VECTORS;
-}
-
-/**
* nfp_net_irqs_alloc() - allocates MSI-X irqs
* @nn: NFP Network structure
*
@@ -350,22 +317,24 @@ static int nfp_net_irqs_wanted(struct nfp_net *nn)
int nfp_net_irqs_alloc(struct nfp_net *nn)
{
int wanted_irqs;
+ unsigned int n;
- wanted_irqs = nfp_net_irqs_wanted(nn);
+ wanted_irqs = nn->num_r_vecs + NFP_NET_NON_Q_VECTORS;
- nn->num_irqs = nfp_net_msix_alloc(nn, wanted_irqs);
- if (nn->num_irqs == 0) {
+ n = nfp_net_msix_alloc(nn, wanted_irqs);
+ if (n == 0) {
nn_err(nn, "Failed to allocate MSI-X IRQs\n");
return 0;
}
- nn->num_r_vecs = nn->num_irqs - NFP_NET_NON_Q_VECTORS;
+ nn->max_r_vecs = n - NFP_NET_NON_Q_VECTORS;
+ nn->num_r_vecs = nn->max_r_vecs;
- if (nn->num_irqs < wanted_irqs)
+ if (n < wanted_irqs)
nn_warn(nn, "Unable to allocate %d vectors. Got %d instead\n",
- wanted_irqs, nn->num_irqs);
+ wanted_irqs, n);
- return nn->num_irqs;
+ return n;
}
/**
@@ -515,18 +484,19 @@ static void nfp_net_irqs_assign(struct net_device *netdev)
struct nfp_net_r_vector *r_vec;
int r;
- /* Assumes nn->num_tx_rings == nn->num_rx_rings */
- if (nn->num_tx_rings > nn->num_r_vecs) {
- nn_warn(nn, "More rings (%d) than vectors (%d).\n",
- nn->num_tx_rings, nn->num_r_vecs);
- nn->num_tx_rings = nn->num_r_vecs;
- nn->num_rx_rings = nn->num_r_vecs;
- }
+ if (nn->num_rx_rings > nn->num_r_vecs ||
+ nn->num_tx_rings > nn->num_r_vecs)
+ nn_warn(nn, "More rings (%d,%d) than vectors (%d).\n",
+ nn->num_rx_rings, nn->num_tx_rings, nn->num_r_vecs);
+
+ nn->num_rx_rings = min(nn->num_r_vecs, nn->num_rx_rings);
+ nn->num_tx_rings = min(nn->num_r_vecs, nn->num_tx_rings);
+ nn->num_stack_tx_rings = nn->num_tx_rings;
nn->lsc_handler = nfp_net_irq_lsc;
nn->exn_handler = nfp_net_irq_exn;
- for (r = 0; r < nn->num_r_vecs; r++) {
+ for (r = 0; r < nn->max_r_vecs; r++) {
r_vec = &nn->r_vecs[r];
r_vec->nfp_net = nn;
r_vec->handler = nfp_net_irq_rxtx;
@@ -605,7 +575,7 @@ static void nfp_net_aux_irq_free(struct nfp_net *nn, u32 ctrl_offset,
*
* Return: True if the ring is full.
*/
-static inline int nfp_net_tx_full(struct nfp_net_tx_ring *tx_ring, int dcnt)
+static int nfp_net_tx_full(struct nfp_net_tx_ring *tx_ring, int dcnt)
{
return (tx_ring->wr_p - tx_ring->rd_p) >= (tx_ring->cnt - dcnt);
}
@@ -745,6 +715,13 @@ static void nfp_net_tx_csum(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
u64_stats_update_end(&r_vec->tx_sync);
}
+static void nfp_net_tx_xmit_more_flush(struct nfp_net_tx_ring *tx_ring)
+{
+ wmb();
+ nfp_qcp_wr_ptr_add(tx_ring->qcp_q, tx_ring->wr_ptr_add);
+ tx_ring->wr_ptr_add = 0;
+}
+
/**
* nfp_net_tx() - Main transmit entry point
* @skb: SKB to transmit
@@ -790,7 +767,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
if (dma_mapping_error(&nn->pdev->dev, dma_addr))
goto err_free;
- wr_idx = tx_ring->wr_p % tx_ring->cnt;
+ wr_idx = tx_ring->wr_p & (tx_ring->cnt - 1);
/* Stash the soft descriptor of the head then initialize it */
txbuf = &tx_ring->txbufs[wr_idx];
@@ -834,7 +811,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
if (dma_mapping_error(&nn->pdev->dev, dma_addr))
goto err_unmap;
- wr_idx = (wr_idx + 1) % tx_ring->cnt;
+ wr_idx = (wr_idx + 1) & (tx_ring->cnt - 1);
tx_ring->txbufs[wr_idx].skb = skb;
tx_ring->txbufs[wr_idx].dma_addr = dma_addr;
tx_ring->txbufs[wr_idx].fidx = f;
@@ -859,12 +836,8 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
nfp_net_tx_ring_stop(nd_q, tx_ring);
tx_ring->wr_ptr_add += nr_frags + 1;
- if (!skb->xmit_more || netif_xmit_stopped(nd_q)) {
- /* force memory write before we let HW know */
- wmb();
- nfp_qcp_wr_ptr_add(tx_ring->qcp_q, tx_ring->wr_ptr_add);
- tx_ring->wr_ptr_add = 0;
- }
+ if (!skb->xmit_more || netif_xmit_stopped(nd_q))
+ nfp_net_tx_xmit_more_flush(tx_ring);
skb_tx_timestamp(skb);
@@ -929,7 +902,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
todo = qcp_rd_p + tx_ring->cnt - tx_ring->qcp_rd_p;
while (todo--) {
- idx = tx_ring->rd_p % tx_ring->cnt;
+ idx = tx_ring->rd_p & (tx_ring->cnt - 1);
tx_ring->rd_p++;
skb = tx_ring->txbufs[idx].skb;
@@ -986,6 +959,56 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
tx_ring->rd_p, tx_ring->wr_p, tx_ring->cnt);
}
+static void nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring)
+{
+ struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
+ struct nfp_net *nn = r_vec->nfp_net;
+ u32 done_pkts = 0, done_bytes = 0;
+ int idx, todo;
+ u32 qcp_rd_p;
+
+ /* Work out how many descriptors have been transmitted */
+ qcp_rd_p = nfp_qcp_rd_ptr_read(tx_ring->qcp_q);
+
+ if (qcp_rd_p == tx_ring->qcp_rd_p)
+ return;
+
+ if (qcp_rd_p > tx_ring->qcp_rd_p)
+ todo = qcp_rd_p - tx_ring->qcp_rd_p;
+ else
+ todo = qcp_rd_p + tx_ring->cnt - tx_ring->qcp_rd_p;
+
+ while (todo--) {
+ idx = tx_ring->rd_p & (tx_ring->cnt - 1);
+ tx_ring->rd_p++;
+
+ if (!tx_ring->txbufs[idx].frag)
+ continue;
+
+ nfp_net_dma_unmap_rx(nn, tx_ring->txbufs[idx].dma_addr,
+ nn->fl_bufsz, DMA_BIDIRECTIONAL);
+ __free_page(virt_to_page(tx_ring->txbufs[idx].frag));
+
+ done_pkts++;
+ done_bytes += tx_ring->txbufs[idx].real_len;
+
+ tx_ring->txbufs[idx].dma_addr = 0;
+ tx_ring->txbufs[idx].frag = NULL;
+ tx_ring->txbufs[idx].fidx = -2;
+ }
+
+ tx_ring->qcp_rd_p = qcp_rd_p;
+
+ u64_stats_update_begin(&r_vec->tx_sync);
+ r_vec->tx_bytes += done_bytes;
+ r_vec->tx_pkts += done_pkts;
+ u64_stats_update_end(&r_vec->tx_sync);
+
+ WARN_ONCE(tx_ring->wr_p - tx_ring->rd_p > tx_ring->cnt,
+ "TX ring corruption rd_p=%u wr_p=%u cnt=%u\n",
+ tx_ring->rd_p, tx_ring->wr_p, tx_ring->cnt);
+}
+
/**
* nfp_net_tx_ring_reset() - Free any untransmitted buffers and reset pointers
* @nn: NFP Net device
@@ -996,39 +1019,47 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
static void
nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
{
+ struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
const struct skb_frag_struct *frag;
- struct netdev_queue *nd_q;
struct pci_dev *pdev = nn->pdev;
+ struct netdev_queue *nd_q;
while (tx_ring->rd_p != tx_ring->wr_p) {
- int nr_frags, fidx, idx;
- struct sk_buff *skb;
+ struct nfp_net_tx_buf *tx_buf;
+ int idx;
- idx = tx_ring->rd_p % tx_ring->cnt;
- skb = tx_ring->txbufs[idx].skb;
- nr_frags = skb_shinfo(skb)->nr_frags;
- fidx = tx_ring->txbufs[idx].fidx;
+ idx = tx_ring->rd_p & (tx_ring->cnt - 1);
+ tx_buf = &tx_ring->txbufs[idx];
- if (fidx == -1) {
- /* unmap head */
- dma_unmap_single(&pdev->dev,
- tx_ring->txbufs[idx].dma_addr,
- skb_headlen(skb), DMA_TO_DEVICE);
+ if (tx_ring == r_vec->xdp_ring) {
+ nfp_net_dma_unmap_rx(nn, tx_buf->dma_addr,
+ nn->fl_bufsz, DMA_BIDIRECTIONAL);
+ __free_page(virt_to_page(tx_ring->txbufs[idx].frag));
} else {
- /* unmap fragment */
- frag = &skb_shinfo(skb)->frags[fidx];
- dma_unmap_page(&pdev->dev,
- tx_ring->txbufs[idx].dma_addr,
- skb_frag_size(frag), DMA_TO_DEVICE);
+ struct sk_buff *skb = tx_ring->txbufs[idx].skb;
+ int nr_frags = skb_shinfo(skb)->nr_frags;
+
+ if (tx_buf->fidx == -1) {
+ /* unmap head */
+ dma_unmap_single(&pdev->dev, tx_buf->dma_addr,
+ skb_headlen(skb),
+ DMA_TO_DEVICE);
+ } else {
+ /* unmap fragment */
+ frag = &skb_shinfo(skb)->frags[tx_buf->fidx];
+ dma_unmap_page(&pdev->dev, tx_buf->dma_addr,
+ skb_frag_size(frag),
+ DMA_TO_DEVICE);
+ }
+
+ /* check for last gather fragment */
+ if (tx_buf->fidx == nr_frags - 1)
+ dev_kfree_skb_any(skb);
}
- /* check for last gather fragment */
- if (fidx == nr_frags - 1)
- dev_kfree_skb_any(skb);
-
- tx_ring->txbufs[idx].dma_addr = 0;
- tx_ring->txbufs[idx].skb = NULL;
- tx_ring->txbufs[idx].fidx = -2;
+ tx_buf->dma_addr = 0;
+ tx_buf->skb = NULL;
+ tx_buf->fidx = -2;
tx_ring->qcp_rd_p++;
tx_ring->rd_p++;
@@ -1040,6 +1071,9 @@ nfp_net_tx_ring_reset(struct nfp_net *nn, struct nfp_net_tx_ring *tx_ring)
tx_ring->qcp_rd_p = 0;
tx_ring->wr_ptr_add = 0;
+ if (tx_ring == r_vec->xdp_ring)
+ return;
+
nd_q = netdev_get_tx_queue(nn->netdev, tx_ring->idx);
netdev_tx_reset_queue(nd_q);
}
@@ -1049,7 +1083,7 @@ static void nfp_net_tx_timeout(struct net_device *netdev)
struct nfp_net *nn = netdev_priv(netdev);
int i;
- for (i = 0; i < nn->num_tx_rings; i++) {
+ for (i = 0; i < nn->netdev->real_num_tx_queues; i++) {
if (!netif_tx_queue_stopped(netdev_get_tx_queue(netdev, i)))
continue;
nn_warn(nn, "TX timeout on ring: %d\n", i);
@@ -1059,69 +1093,112 @@ static void nfp_net_tx_timeout(struct net_device *netdev)
/* Receive processing
*/
-
-/**
- * nfp_net_rx_space() - return the number of free slots on the RX ring
- * @rx_ring: RX ring structure
- *
- * Make sure we leave at least one slot free.
- *
- * Return: True if there is space on the RX ring
- */
-static inline int nfp_net_rx_space(struct nfp_net_rx_ring *rx_ring)
+static unsigned int
+nfp_net_calc_fl_bufsz(struct nfp_net *nn, unsigned int mtu)
{
- return (rx_ring->cnt - 1) - (rx_ring->wr_p - rx_ring->rd_p);
+ unsigned int fl_bufsz;
+
+ fl_bufsz = NFP_NET_RX_BUF_HEADROOM;
+ if (nn->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
+ fl_bufsz += NFP_NET_MAX_PREPEND;
+ else
+ fl_bufsz += nn->rx_offset;
+ fl_bufsz += ETH_HLEN + VLAN_HLEN * 2 + mtu;
+
+ fl_bufsz = SKB_DATA_ALIGN(fl_bufsz);
+ fl_bufsz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+ return fl_bufsz;
+}
+
+static void
+nfp_net_free_frag(void *frag, bool xdp)
+{
+ if (!xdp)
+ skb_free_frag(frag);
+ else
+ __free_page(virt_to_page(frag));
}
/**
- * nfp_net_rx_alloc_one() - Allocate and map skb for RX
+ * nfp_net_rx_alloc_one() - Allocate and map page frag for RX
* @rx_ring: RX ring structure of the skb
* @dma_addr: Pointer to storage for DMA address (output param)
* @fl_bufsz: size of freelist buffers
+ * @xdp: Whether XDP is enabled
*
- * This function will allcate a new skb, map it for DMA.
+ * This function will allcate a new page frag, map it for DMA.
*
- * Return: allocated skb or NULL on failure.
+ * Return: allocated page frag or NULL on failure.
*/
-static struct sk_buff *
+static void *
nfp_net_rx_alloc_one(struct nfp_net_rx_ring *rx_ring, dma_addr_t *dma_addr,
- unsigned int fl_bufsz)
+ unsigned int fl_bufsz, bool xdp)
{
struct nfp_net *nn = rx_ring->r_vec->nfp_net;
- struct sk_buff *skb;
+ int direction;
+ void *frag;
- skb = netdev_alloc_skb(nn->netdev, fl_bufsz);
- if (!skb) {
- nn_warn_ratelimit(nn, "Failed to alloc receive SKB\n");
+ if (!xdp)
+ frag = netdev_alloc_frag(fl_bufsz);
+ else
+ frag = page_address(alloc_page(GFP_KERNEL | __GFP_COLD));
+ if (!frag) {
+ nn_warn_ratelimit(nn, "Failed to alloc receive page frag\n");
return NULL;
}
- *dma_addr = dma_map_single(&nn->pdev->dev, skb->data,
- fl_bufsz, DMA_FROM_DEVICE);
+ direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
+
+ *dma_addr = nfp_net_dma_map_rx(nn, frag, fl_bufsz, direction);
if (dma_mapping_error(&nn->pdev->dev, *dma_addr)) {
- dev_kfree_skb_any(skb);
+ nfp_net_free_frag(frag, xdp);
nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n");
return NULL;
}
- return skb;
+ return frag;
+}
+
+static void *
+nfp_net_napi_alloc_one(struct nfp_net *nn, int direction, dma_addr_t *dma_addr)
+{
+ void *frag;
+
+ if (!nn->xdp_prog)
+ frag = napi_alloc_frag(nn->fl_bufsz);
+ else
+ frag = page_address(alloc_page(GFP_ATOMIC | __GFP_COLD));
+ if (!frag) {
+ nn_warn_ratelimit(nn, "Failed to alloc receive page frag\n");
+ return NULL;
+ }
+
+ *dma_addr = nfp_net_dma_map_rx(nn, frag, nn->fl_bufsz, direction);
+ if (dma_mapping_error(&nn->pdev->dev, *dma_addr)) {
+ nfp_net_free_frag(frag, nn->xdp_prog);
+ nn_warn_ratelimit(nn, "Failed to map DMA RX buffer\n");
+ return NULL;
+ }
+
+ return frag;
}
/**
* nfp_net_rx_give_one() - Put mapped skb on the software and hardware rings
* @rx_ring: RX ring structure
- * @skb: Skb to put on rings
+ * @frag: page fragment buffer
* @dma_addr: DMA address of skb mapping
*/
static void nfp_net_rx_give_one(struct nfp_net_rx_ring *rx_ring,
- struct sk_buff *skb, dma_addr_t dma_addr)
+ void *frag, dma_addr_t dma_addr)
{
unsigned int wr_idx;
- wr_idx = rx_ring->wr_p % rx_ring->cnt;
+ wr_idx = rx_ring->wr_p & (rx_ring->cnt - 1);
/* Stash SKB and DMA address away */
- rx_ring->rxbufs[wr_idx].skb = skb;
+ rx_ring->rxbufs[wr_idx].frag = frag;
rx_ring->rxbufs[wr_idx].dma_addr = dma_addr;
/* Fill freelist descriptor */
@@ -1153,12 +1230,12 @@ static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring)
unsigned int wr_idx, last_idx;
/* Move the empty entry to the end of the list */
- wr_idx = rx_ring->wr_p % rx_ring->cnt;
+ wr_idx = rx_ring->wr_p & (rx_ring->cnt - 1);
last_idx = rx_ring->cnt - 1;
rx_ring->rxbufs[wr_idx].dma_addr = rx_ring->rxbufs[last_idx].dma_addr;
- rx_ring->rxbufs[wr_idx].skb = rx_ring->rxbufs[last_idx].skb;
+ rx_ring->rxbufs[wr_idx].frag = rx_ring->rxbufs[last_idx].frag;
rx_ring->rxbufs[last_idx].dma_addr = 0;
- rx_ring->rxbufs[last_idx].skb = NULL;
+ rx_ring->rxbufs[last_idx].frag = NULL;
memset(rx_ring->rxds, 0, sizeof(*rx_ring->rxds) * rx_ring->cnt);
rx_ring->wr_p = 0;
@@ -1170,15 +1247,17 @@ static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring)
* nfp_net_rx_ring_bufs_free() - Free any buffers currently on the RX ring
* @nn: NFP Net device
* @rx_ring: RX ring to remove buffers from
+ * @xdp: Whether XDP is enabled
*
* Assumes that the device is stopped and buffers are in [0, ring->cnt - 1)
* entries. After device is disabled nfp_net_rx_ring_reset() must be called
* to restore required ring geometry.
*/
static void
-nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring)
+nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
+ bool xdp)
{
- struct pci_dev *pdev = nn->pdev;
+ int direction = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
unsigned int i;
for (i = 0; i < rx_ring->cnt - 1; i++) {
@@ -1186,14 +1265,14 @@ nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring)
* fails to allocate enough buffers and calls here to free
* already allocated ones.
*/
- if (!rx_ring->rxbufs[i].skb)
+ if (!rx_ring->rxbufs[i].frag)
continue;
- dma_unmap_single(&pdev->dev, rx_ring->rxbufs[i].dma_addr,
- rx_ring->bufsz, DMA_FROM_DEVICE);
- dev_kfree_skb_any(rx_ring->rxbufs[i].skb);
+ nfp_net_dma_unmap_rx(nn, rx_ring->rxbufs[i].dma_addr,
+ rx_ring->bufsz, direction);
+ nfp_net_free_frag(rx_ring->rxbufs[i].frag, xdp);
rx_ring->rxbufs[i].dma_addr = 0;
- rx_ring->rxbufs[i].skb = NULL;
+ rx_ring->rxbufs[i].frag = NULL;
}
}
@@ -1201,9 +1280,11 @@ nfp_net_rx_ring_bufs_free(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring)
* nfp_net_rx_ring_bufs_alloc() - Fill RX ring with buffers (don't give to FW)
* @nn: NFP Net device
* @rx_ring: RX ring to remove buffers from
+ * @xdp: Whether XDP is enabled
*/
static int
-nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring)
+nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
+ bool xdp)
{
struct nfp_net_rx_buf *rxbufs;
unsigned int i;
@@ -1211,11 +1292,11 @@ nfp_net_rx_ring_bufs_alloc(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring)
rxbufs = rx_ring->rxbufs;
for (i = 0; i < rx_ring->cnt - 1; i++) {
- rxbufs[i].skb =
+ rxbufs[i].frag =
nfp_net_rx_alloc_one(rx_ring, &rxbufs[i].dma_addr,
- rx_ring->bufsz);
- if (!rxbufs[i].skb) {
- nfp_net_rx_ring_bufs_free(nn, rx_ring);
+ rx_ring->bufsz, xdp);
+ if (!rxbufs[i].frag) {
+ nfp_net_rx_ring_bufs_free(nn, rx_ring, xdp);
return -ENOMEM;
}
}
@@ -1232,7 +1313,7 @@ static void nfp_net_rx_ring_fill_freelist(struct nfp_net_rx_ring *rx_ring)
unsigned int i;
for (i = 0; i < rx_ring->cnt - 1; i++)
- nfp_net_rx_give_one(rx_ring, rx_ring->rxbufs[i].skb,
+ nfp_net_rx_give_one(rx_ring, rx_ring->rxbufs[i].frag,
rx_ring->rxbufs[i].dma_addr);
}
@@ -1359,6 +1440,87 @@ nfp_net_parse_meta(struct net_device *netdev, struct sk_buff *skb,
return data;
}
+static void
+nfp_net_rx_drop(struct nfp_net_r_vector *r_vec, struct nfp_net_rx_ring *rx_ring,
+ struct nfp_net_rx_buf *rxbuf, struct sk_buff *skb)
+{
+ u64_stats_update_begin(&r_vec->rx_sync);
+ r_vec->rx_drops++;
+ u64_stats_update_end(&r_vec->rx_sync);
+
+ /* skb is build based on the frag, free_skb() would free the frag
+ * so to be able to reuse it we need an extra ref.
+ */
+ if (skb && rxbuf && skb->head == rxbuf->frag)
+ page_ref_inc(virt_to_head_page(rxbuf->frag));
+ if (rxbuf)
+ nfp_net_rx_give_one(rx_ring, rxbuf->frag, rxbuf->dma_addr);
+ if (skb)
+ dev_kfree_skb_any(skb);
+}
+
+static void
+nfp_net_tx_xdp_buf(struct nfp_net *nn, struct nfp_net_rx_ring *rx_ring,
+ struct nfp_net_tx_ring *tx_ring,
+ struct nfp_net_rx_buf *rxbuf, unsigned int pkt_off,
+ unsigned int pkt_len)
+{
+ struct nfp_net_tx_buf *txbuf;
+ struct nfp_net_tx_desc *txd;
+ dma_addr_t new_dma_addr;
+ void *new_frag;
+ int wr_idx;
+
+ if (unlikely(nfp_net_tx_full(tx_ring, 1))) {
+ nfp_net_rx_drop(rx_ring->r_vec, rx_ring, rxbuf, NULL);
+ return;
+ }
+
+ new_frag = nfp_net_napi_alloc_one(nn, DMA_BIDIRECTIONAL, &new_dma_addr);
+ if (unlikely(!new_frag)) {
+ nfp_net_rx_drop(rx_ring->r_vec, rx_ring, rxbuf, NULL);
+ return;
+ }
+ nfp_net_rx_give_one(rx_ring, new_frag, new_dma_addr);
+
+ wr_idx = tx_ring->wr_p & (tx_ring->cnt - 1);
+
+ /* Stash the soft descriptor of the head then initialize it */
+ txbuf = &tx_ring->txbufs[wr_idx];
+ txbuf->frag = rxbuf->frag;
+ txbuf->dma_addr = rxbuf->dma_addr;
+ txbuf->fidx = -1;
+ txbuf->pkt_cnt = 1;
+ txbuf->real_len = pkt_len;
+
+ dma_sync_single_for_device(&nn->pdev->dev, rxbuf->dma_addr + pkt_off,
+ pkt_len, DMA_TO_DEVICE);
+
+ /* Build TX descriptor */
+ txd = &tx_ring->txds[wr_idx];
+ txd->offset_eop = PCIE_DESC_TX_EOP;
+ txd->dma_len = cpu_to_le16(pkt_len);
+ nfp_desc_set_dma_addr(txd, rxbuf->dma_addr + pkt_off);
+ txd->data_len = cpu_to_le16(pkt_len);
+
+ txd->flags = 0;
+ txd->mss = 0;
+ txd->l4_offset = 0;
+
+ tx_ring->wr_p++;
+ tx_ring->wr_ptr_add++;
+}
+
+static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, unsigned int len)
+{
+ struct xdp_buff xdp;
+
+ xdp.data = data;
+ xdp.data_end = data + len;
+
+ return BPF_PROG_RUN(prog, (void *)&xdp);
+}
+
/**
* nfp_net_rx() - receive up to @budget packets on @rx_ring
* @rx_ring: RX ring to receive from
@@ -1368,62 +1530,39 @@ nfp_net_parse_meta(struct net_device *netdev, struct sk_buff *skb,
* more cleanly separate packet receive code from other bookkeeping
* functions performed in the napi poll function.
*
- * There are differences between the NFP-3200 firmware and the
- * NFP-6000 firmware. The NFP-3200 firmware uses a dedicated RX queue
- * to indicate that new packets have arrived. The NFP-6000 does not
- * have this queue and uses the DD bit in the RX descriptor. This
- * method cannot be used on the NFP-3200 as it causes a race
- * condition: The RX ring write pointer on the NFP-3200 is updated
- * after packets (and descriptors) have been DMAed. If the DD bit is
- * used and subsequently the read pointer is updated this may lead to
- * the RX queue to underflow (if the firmware has not yet update the
- * write pointer). Therefore we use slightly ugly conditional code
- * below to handle the differences. We may, in the future update the
- * NFP-3200 firmware to behave the same as the firmware on the
- * NFP-6000.
- *
* Return: Number of packets received.
*/
static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
{
struct nfp_net_r_vector *r_vec = rx_ring->r_vec;
struct nfp_net *nn = r_vec->nfp_net;
- unsigned int data_len, meta_len;
- int avail = 0, pkts_polled = 0;
- struct sk_buff *skb, *new_skb;
- struct nfp_net_rx_desc *rxd;
- dma_addr_t new_dma_addr;
- u32 qcp_wr_p;
+ struct nfp_net_tx_ring *tx_ring;
+ struct bpf_prog *xdp_prog;
+ unsigned int true_bufsz;
+ struct sk_buff *skb;
+ int pkts_polled = 0;
+ int rx_dma_map_dir;
int idx;
- if (nn->is_nfp3200) {
- /* Work out how many packets arrived */
- qcp_wr_p = nfp_qcp_wr_ptr_read(rx_ring->qcp_rx);
- idx = rx_ring->rd_p % rx_ring->cnt;
+ rcu_read_lock();
+ xdp_prog = READ_ONCE(nn->xdp_prog);
+ rx_dma_map_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
+ true_bufsz = xdp_prog ? PAGE_SIZE : nn->fl_bufsz;
+ tx_ring = r_vec->xdp_ring;
- if (qcp_wr_p == idx)
- /* No new packets */
- return 0;
+ while (pkts_polled < budget) {
+ unsigned int meta_len, data_len, data_off, pkt_len, pkt_off;
+ struct nfp_net_rx_buf *rxbuf;
+ struct nfp_net_rx_desc *rxd;
+ dma_addr_t new_dma_addr;
+ void *new_frag;
- if (qcp_wr_p > idx)
- avail = qcp_wr_p - idx;
- else
- avail = qcp_wr_p + rx_ring->cnt - idx;
- } else {
- avail = budget + 1;
- }
-
- while (avail > 0 && pkts_polled < budget) {
- idx = rx_ring->rd_p % rx_ring->cnt;
+ idx = rx_ring->rd_p & (rx_ring->cnt - 1);
rxd = &rx_ring->rxds[idx];
- if (!(rxd->rxd.meta_len_dd & PCIE_DESC_RX_DD)) {
- if (nn->is_nfp3200)
- nn_dbg(nn, "RX descriptor not valid (DD)%d:%u rxd[0]=%#x rxd[1]=%#x\n",
- rx_ring->idx, idx,
- rxd->vals[0], rxd->vals[1]);
+ if (!(rxd->rxd.meta_len_dd & PCIE_DESC_RX_DD))
break;
- }
+
/* Memory barrier to ensure that we won't do other reads
* before the DD bit.
*/
@@ -1431,27 +1570,8 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
rx_ring->rd_p++;
pkts_polled++;
- avail--;
- skb = rx_ring->rxbufs[idx].skb;
-
- new_skb = nfp_net_rx_alloc_one(rx_ring, &new_dma_addr,
- nn->fl_bufsz);
- if (!new_skb) {
- nfp_net_rx_give_one(rx_ring, rx_ring->rxbufs[idx].skb,
- rx_ring->rxbufs[idx].dma_addr);
- u64_stats_update_begin(&r_vec->rx_sync);
- r_vec->rx_drops++;
- u64_stats_update_end(&r_vec->rx_sync);
- continue;
- }
-
- dma_unmap_single(&nn->pdev->dev,
- rx_ring->rxbufs[idx].dma_addr,
- nn->fl_bufsz, DMA_FROM_DEVICE);
-
- nfp_net_rx_give_one(rx_ring, new_skb, new_dma_addr);
-
+ rxbuf = &rx_ring->rxbufs[idx];
/* < meta_len >
* <-- [rx_offset] -->
* ---------------------------------------------------------
@@ -1466,19 +1586,66 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
*/
meta_len = rxd->rxd.meta_len_dd & PCIE_DESC_RX_META_LEN_MASK;
data_len = le16_to_cpu(rxd->rxd.data_len);
+ pkt_len = data_len - meta_len;
if (nn->rx_offset == NFP_NET_CFG_RX_OFFSET_DYNAMIC)
- skb_reserve(skb, meta_len);
+ pkt_off = meta_len;
else
- skb_reserve(skb, nn->rx_offset);
- skb_put(skb, data_len - meta_len);
+ pkt_off = nn->rx_offset;
+ data_off = NFP_NET_RX_BUF_HEADROOM + pkt_off;
/* Stats update */
u64_stats_update_begin(&r_vec->rx_sync);
r_vec->rx_pkts++;
- r_vec->rx_bytes += skb->len;
+ r_vec->rx_bytes += pkt_len;
u64_stats_update_end(&r_vec->rx_sync);
+ if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF &&
+ nn->bpf_offload_xdp)) {
+ int act;
+
+ dma_sync_single_for_cpu(&nn->pdev->dev,
+ rxbuf->dma_addr + pkt_off,
+ pkt_len, DMA_FROM_DEVICE);
+ act = nfp_net_run_xdp(xdp_prog, rxbuf->frag + data_off,
+ pkt_len);
+ switch (act) {
+ case XDP_PASS:
+ break;
+ case XDP_TX:
+ nfp_net_tx_xdp_buf(nn, rx_ring, tx_ring, rxbuf,
+ pkt_off, pkt_len);
+ continue;
+ default:
+ bpf_warn_invalid_xdp_action(act);
+ case XDP_ABORTED:
+ case XDP_DROP:
+ nfp_net_rx_give_one(rx_ring, rxbuf->frag,
+ rxbuf->dma_addr);
+ continue;
+ }
+ }
+
+ skb = build_skb(rxbuf->frag, true_bufsz);
+ if (unlikely(!skb)) {
+ nfp_net_rx_drop(r_vec, rx_ring, rxbuf, NULL);
+ continue;
+ }
+ new_frag = nfp_net_napi_alloc_one(nn, rx_dma_map_dir,
+ &new_dma_addr);
+ if (unlikely(!new_frag)) {
+ nfp_net_rx_drop(r_vec, rx_ring, rxbuf, skb);
+ continue;
+ }
+
+ nfp_net_dma_unmap_rx(nn, rxbuf->dma_addr, nn->fl_bufsz,
+ rx_dma_map_dir);
+
+ nfp_net_rx_give_one(rx_ring, new_frag, new_dma_addr);
+
+ skb_reserve(skb, data_off);
+ skb_put(skb, pkt_len);
+
if (nn->fw_ver.major <= 3) {
nfp_net_set_hash_desc(nn->netdev, skb, rxd);
} else if (meta_len) {
@@ -1486,12 +1653,8 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
end = nfp_net_parse_meta(nn->netdev, skb, meta_len);
if (unlikely(end != skb->data)) {
- u64_stats_update_begin(&r_vec->rx_sync);
- r_vec->rx_drops++;
- u64_stats_update_end(&r_vec->rx_sync);
-
- dev_kfree_skb_any(skb);
nn_warn_ratelimit(nn, "invalid RX packet metadata\n");
+ nfp_net_rx_drop(r_vec, rx_ring, NULL, skb);
continue;
}
}
@@ -1508,8 +1671,9 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
napi_gro_receive(&rx_ring->r_vec->napi, skb);
}
- if (nn->is_nfp3200)
- nfp_qcp_rd_ptr_add(rx_ring->qcp_rx, pkts_polled);
+ if (xdp_prog && tx_ring->wr_ptr_add)
+ nfp_net_tx_xmit_more_flush(tx_ring);
+ rcu_read_unlock();
return pkts_polled;
}
@@ -1525,21 +1689,19 @@ static int nfp_net_poll(struct napi_struct *napi, int budget)
{
struct nfp_net_r_vector *r_vec =
container_of(napi, struct nfp_net_r_vector, napi);
- struct nfp_net_rx_ring *rx_ring = r_vec->rx_ring;
- struct nfp_net_tx_ring *tx_ring = r_vec->tx_ring;
- struct nfp_net *nn = r_vec->nfp_net;
- struct netdev_queue *txq;
- unsigned int pkts_polled;
+ unsigned int pkts_polled = 0;
- tx_ring = &nn->tx_rings[rx_ring->idx];
- txq = netdev_get_tx_queue(nn->netdev, tx_ring->idx);
- nfp_net_tx_complete(tx_ring);
-
- pkts_polled = nfp_net_rx(rx_ring, budget);
+ if (r_vec->tx_ring)
+ nfp_net_tx_complete(r_vec->tx_ring);
+ if (r_vec->rx_ring) {
+ pkts_polled = nfp_net_rx(r_vec->rx_ring, budget);
+ if (r_vec->xdp_ring)
+ nfp_net_xdp_complete(r_vec->xdp_ring);
+ }
if (pkts_polled < budget) {
napi_complete_done(napi, pkts_polled);
- nfp_net_irq_unmask(nn, r_vec->irq_idx);
+ nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_idx);
}
return pkts_polled;
@@ -1575,10 +1737,12 @@ static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring)
* nfp_net_tx_ring_alloc() - Allocate resource for a TX ring
* @tx_ring: TX Ring structure to allocate
* @cnt: Ring buffer count
+ * @is_xdp: True if ring will be used for XDP
*
* Return: 0 on success, negative errno otherwise.
*/
-static int nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt)
+static int
+nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt, bool is_xdp)
{
struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
struct nfp_net *nn = r_vec->nfp_net;
@@ -1598,11 +1762,14 @@ static int nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt)
if (!tx_ring->txbufs)
goto err_alloc;
- netif_set_xps_queue(nn->netdev, &r_vec->affinity_mask, tx_ring->idx);
+ if (!is_xdp)
+ netif_set_xps_queue(nn->netdev, &r_vec->affinity_mask,
+ tx_ring->idx);
- nn_dbg(nn, "TxQ%02d: QCidx=%02d cnt=%d dma=%#llx host=%p\n",
+ nn_dbg(nn, "TxQ%02d: QCidx=%02d cnt=%d dma=%#llx host=%p %s\n",
tx_ring->idx, tx_ring->qcidx,
- tx_ring->cnt, (unsigned long long)tx_ring->dma, tx_ring->txds);
+ tx_ring->cnt, (unsigned long long)tx_ring->dma, tx_ring->txds,
+ is_xdp ? "XDP" : "");
return 0;
@@ -1612,23 +1779,29 @@ static int nfp_net_tx_ring_alloc(struct nfp_net_tx_ring *tx_ring, u32 cnt)
}
static struct nfp_net_tx_ring *
-nfp_net_shadow_tx_rings_prepare(struct nfp_net *nn, u32 buf_cnt)
+nfp_net_tx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s,
+ unsigned int num_stack_tx_rings)
{
struct nfp_net_tx_ring *rings;
unsigned int r;
- rings = kcalloc(nn->num_tx_rings, sizeof(*rings), GFP_KERNEL);
+ rings = kcalloc(s->n_rings, sizeof(*rings), GFP_KERNEL);
if (!rings)
return NULL;
- for (r = 0; r < nn->num_tx_rings; r++) {
- nfp_net_tx_ring_init(&rings[r], nn->tx_rings[r].r_vec, r);
+ for (r = 0; r < s->n_rings; r++) {
+ int bias = 0;
- if (nfp_net_tx_ring_alloc(&rings[r], buf_cnt))
+ if (r >= num_stack_tx_rings)
+ bias = num_stack_tx_rings;
+
+ nfp_net_tx_ring_init(&rings[r], &nn->r_vecs[r - bias], r);
+
+ if (nfp_net_tx_ring_alloc(&rings[r], s->dcnt, bias))
goto err_free_prev;
}
- return rings;
+ return s->rings = rings;
err_free_prev:
while (r--)
@@ -1637,28 +1810,27 @@ nfp_net_shadow_tx_rings_prepare(struct nfp_net *nn, u32 buf_cnt)
return NULL;
}
-static struct nfp_net_tx_ring *
-nfp_net_shadow_tx_rings_swap(struct nfp_net *nn, struct nfp_net_tx_ring *rings)
+static void
+nfp_net_tx_ring_set_swap(struct nfp_net *nn, struct nfp_net_ring_set *s)
{
- struct nfp_net_tx_ring *old = nn->tx_rings;
- unsigned int r;
+ struct nfp_net_ring_set new = *s;
- for (r = 0; r < nn->num_tx_rings; r++)
- old[r].r_vec->tx_ring = &rings[r];
+ s->dcnt = nn->txd_cnt;
+ s->rings = nn->tx_rings;
+ s->n_rings = nn->num_tx_rings;
- nn->tx_rings = rings;
- return old;
+ nn->txd_cnt = new.dcnt;
+ nn->tx_rings = new.rings;
+ nn->num_tx_rings = new.n_rings;
}
static void
-nfp_net_shadow_tx_rings_free(struct nfp_net *nn, struct nfp_net_tx_ring *rings)
+nfp_net_tx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s)
{
+ struct nfp_net_tx_ring *rings = s->rings;
unsigned int r;
- if (!rings)
- return;
-
- for (r = 0; r < nn->num_tx_rings; r++)
+ for (r = 0; r < s->n_rings; r++)
nfp_net_tx_ring_free(&rings[r]);
kfree(rings);
@@ -1730,31 +1902,32 @@ nfp_net_rx_ring_alloc(struct nfp_net_rx_ring *rx_ring, unsigned int fl_bufsz,
}
static struct nfp_net_rx_ring *
-nfp_net_shadow_rx_rings_prepare(struct nfp_net *nn, unsigned int fl_bufsz,
- u32 buf_cnt)
+nfp_net_rx_ring_set_prepare(struct nfp_net *nn, struct nfp_net_ring_set *s,
+ bool xdp)
{
+ unsigned int fl_bufsz = nfp_net_calc_fl_bufsz(nn, s->mtu);
struct nfp_net_rx_ring *rings;
unsigned int r;
- rings = kcalloc(nn->num_rx_rings, sizeof(*rings), GFP_KERNEL);
+ rings = kcalloc(s->n_rings, sizeof(*rings), GFP_KERNEL);
if (!rings)
return NULL;
- for (r = 0; r < nn->num_rx_rings; r++) {
- nfp_net_rx_ring_init(&rings[r], nn->rx_rings[r].r_vec, r);
+ for (r = 0; r < s->n_rings; r++) {
+ nfp_net_rx_ring_init(&rings[r], &nn->r_vecs[r], r);
- if (nfp_net_rx_ring_alloc(&rings[r], fl_bufsz, buf_cnt))
+ if (nfp_net_rx_ring_alloc(&rings[r], fl_bufsz, s->dcnt))
goto err_free_prev;
- if (nfp_net_rx_ring_bufs_alloc(nn, &rings[r]))
+ if (nfp_net_rx_ring_bufs_alloc(nn, &rings[r], xdp))
goto err_free_ring;
}
- return rings;
+ return s->rings = rings;
err_free_prev:
while (r--) {
- nfp_net_rx_ring_bufs_free(nn, &rings[r]);
+ nfp_net_rx_ring_bufs_free(nn, &rings[r], xdp);
err_free_ring:
nfp_net_rx_ring_free(&rings[r]);
}
@@ -1762,35 +1935,50 @@ nfp_net_shadow_rx_rings_prepare(struct nfp_net *nn, unsigned int fl_bufsz,
return NULL;
}
-static struct nfp_net_rx_ring *
-nfp_net_shadow_rx_rings_swap(struct nfp_net *nn, struct nfp_net_rx_ring *rings)
+static void
+nfp_net_rx_ring_set_swap(struct nfp_net *nn, struct nfp_net_ring_set *s)
{
- struct nfp_net_rx_ring *old = nn->rx_rings;
- unsigned int r;
+ struct nfp_net_ring_set new = *s;
- for (r = 0; r < nn->num_rx_rings; r++)
- old[r].r_vec->rx_ring = &rings[r];
+ s->mtu = nn->netdev->mtu;
+ s->dcnt = nn->rxd_cnt;
+ s->rings = nn->rx_rings;
+ s->n_rings = nn->num_rx_rings;
- nn->rx_rings = rings;
- return old;
+ nn->netdev->mtu = new.mtu;
+ nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, new.mtu);
+ nn->rxd_cnt = new.dcnt;
+ nn->rx_rings = new.rings;
+ nn->num_rx_rings = new.n_rings;
}
static void
-nfp_net_shadow_rx_rings_free(struct nfp_net *nn, struct nfp_net_rx_ring *rings)
+nfp_net_rx_ring_set_free(struct nfp_net *nn, struct nfp_net_ring_set *s,
+ bool xdp)
{
+ struct nfp_net_rx_ring *rings = s->rings;
unsigned int r;
- if (!rings)
- return;
-
- for (r = 0; r < nn->num_r_vecs; r++) {
- nfp_net_rx_ring_bufs_free(nn, &rings[r]);
+ for (r = 0; r < s->n_rings; r++) {
+ nfp_net_rx_ring_bufs_free(nn, &rings[r], xdp);
nfp_net_rx_ring_free(&rings[r]);
}
kfree(rings);
}
+static void
+nfp_net_vector_assign_rings(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
+ int idx)
+{
+ r_vec->rx_ring = idx < nn->num_rx_rings ? &nn->rx_rings[idx] : NULL;
+ r_vec->tx_ring =
+ idx < nn->num_stack_tx_rings ? &nn->tx_rings[idx] : NULL;
+
+ r_vec->xdp_ring = idx < nn->num_tx_rings - nn->num_stack_tx_rings ?
+ &nn->tx_rings[nn->num_stack_tx_rings + idx] : NULL;
+}
+
static int
nfp_net_prepare_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
int idx)
@@ -1798,25 +1986,20 @@ nfp_net_prepare_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
struct msix_entry *entry = &nn->irq_entries[r_vec->irq_idx];
int err;
- r_vec->tx_ring = &nn->tx_rings[idx];
- nfp_net_tx_ring_init(r_vec->tx_ring, r_vec, idx);
-
- r_vec->rx_ring = &nn->rx_rings[idx];
- nfp_net_rx_ring_init(r_vec->rx_ring, r_vec, idx);
+ /* Setup NAPI */
+ netif_napi_add(nn->netdev, &r_vec->napi,
+ nfp_net_poll, NAPI_POLL_WEIGHT);
snprintf(r_vec->name, sizeof(r_vec->name),
"%s-rxtx-%d", nn->netdev->name, idx);
err = request_irq(entry->vector, r_vec->handler, 0, r_vec->name, r_vec);
if (err) {
+ netif_napi_del(&r_vec->napi);
nn_err(nn, "Error requesting IRQ %d\n", entry->vector);
return err;
}
disable_irq(entry->vector);
- /* Setup NAPI */
- netif_napi_add(nn->netdev, &r_vec->napi,
- nfp_net_poll, NAPI_POLL_WEIGHT);
-
irq_set_affinity_hint(entry->vector, &r_vec->affinity_mask);
nn_dbg(nn, "RV%02d: irq=%03d/%03d\n", idx, entry->vector, entry->entry);
@@ -1879,13 +2062,13 @@ void nfp_net_coalesce_write_cfg(struct nfp_net *nn)
/* copy RX interrupt coalesce parameters */
value = (nn->rx_coalesce_max_frames << 16) |
(factor * nn->rx_coalesce_usecs);
- for (i = 0; i < nn->num_r_vecs; i++)
+ for (i = 0; i < nn->num_rx_rings; i++)
nn_writel(nn, NFP_NET_CFG_RXR_IRQ_MOD(i), value);
/* copy TX interrupt coalesce parameters */
value = (nn->tx_coalesce_max_frames << 16) |
(factor * nn->tx_coalesce_usecs);
- for (i = 0; i < nn->num_r_vecs; i++)
+ for (i = 0; i < nn->num_tx_rings; i++)
nn_writel(nn, NFP_NET_CFG_TXR_IRQ_MOD(i), value);
}
@@ -1901,9 +2084,8 @@ static void nfp_net_write_mac_addr(struct nfp_net *nn)
{
nn_writel(nn, NFP_NET_CFG_MACADDR + 0,
get_unaligned_be32(nn->netdev->dev_addr));
- /* We can't do writew for NFP-3200 compatibility */
- nn_writel(nn, NFP_NET_CFG_MACADDR + 4,
- get_unaligned_be16(nn->netdev->dev_addr + 4) << 16);
+ nn_writew(nn, NFP_NET_CFG_MACADDR + 6,
+ get_unaligned_be16(nn->netdev->dev_addr + 4));
}
static void nfp_net_vec_clear_ring_data(struct nfp_net *nn, unsigned int idx)
@@ -1944,27 +2126,33 @@ static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
if (err)
nn_err(nn, "Could not disable device: %d\n", err);
- for (r = 0; r < nn->num_r_vecs; r++) {
- nfp_net_rx_ring_reset(nn->r_vecs[r].rx_ring);
- nfp_net_tx_ring_reset(nn, nn->r_vecs[r].tx_ring);
+ for (r = 0; r < nn->num_rx_rings; r++)
+ nfp_net_rx_ring_reset(&nn->rx_rings[r]);
+ for (r = 0; r < nn->num_tx_rings; r++)
+ nfp_net_tx_ring_reset(nn, &nn->tx_rings[r]);
+ for (r = 0; r < nn->num_r_vecs; r++)
nfp_net_vec_clear_ring_data(nn, r);
- }
nn->ctrl = new_ctrl;
}
static void
-nfp_net_vec_write_ring_data(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
- unsigned int idx)
+nfp_net_rx_ring_hw_cfg_write(struct nfp_net *nn,
+ struct nfp_net_rx_ring *rx_ring, unsigned int idx)
{
/* Write the DMA address, size and MSI-X info to the device */
- nn_writeq(nn, NFP_NET_CFG_RXR_ADDR(idx), r_vec->rx_ring->dma);
- nn_writeb(nn, NFP_NET_CFG_RXR_SZ(idx), ilog2(r_vec->rx_ring->cnt));
- nn_writeb(nn, NFP_NET_CFG_RXR_VEC(idx), r_vec->irq_idx);
+ nn_writeq(nn, NFP_NET_CFG_RXR_ADDR(idx), rx_ring->dma);
+ nn_writeb(nn, NFP_NET_CFG_RXR_SZ(idx), ilog2(rx_ring->cnt));
+ nn_writeb(nn, NFP_NET_CFG_RXR_VEC(idx), rx_ring->r_vec->irq_idx);
+}
- nn_writeq(nn, NFP_NET_CFG_TXR_ADDR(idx), r_vec->tx_ring->dma);
- nn_writeb(nn, NFP_NET_CFG_TXR_SZ(idx), ilog2(r_vec->tx_ring->cnt));
- nn_writeb(nn, NFP_NET_CFG_TXR_VEC(idx), r_vec->irq_idx);
+static void
+nfp_net_tx_ring_hw_cfg_write(struct nfp_net *nn,
+ struct nfp_net_tx_ring *tx_ring, unsigned int idx)
+{
+ nn_writeq(nn, NFP_NET_CFG_TXR_ADDR(idx), tx_ring->dma);
+ nn_writeb(nn, NFP_NET_CFG_TXR_SZ(idx), ilog2(tx_ring->cnt));
+ nn_writeb(nn, NFP_NET_CFG_TXR_VEC(idx), tx_ring->r_vec->irq_idx);
}
static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
@@ -1989,8 +2177,10 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
update |= NFP_NET_CFG_UPDATE_IRQMOD;
}
- for (r = 0; r < nn->num_r_vecs; r++)
- nfp_net_vec_write_ring_data(nn, &nn->r_vecs[r], r);
+ for (r = 0; r < nn->num_tx_rings; r++)
+ nfp_net_tx_ring_hw_cfg_write(nn, &nn->tx_rings[r], r);
+ for (r = 0; r < nn->num_rx_rings; r++)
+ nfp_net_rx_ring_hw_cfg_write(nn, &nn->rx_rings[r], r);
nn_writeq(nn, NFP_NET_CFG_TXRS_ENABLE, nn->num_tx_rings == 64 ?
0xffffffffffffffffULL : ((u64)1 << nn->num_tx_rings) - 1);
@@ -2016,8 +2206,8 @@ static int __nfp_net_set_config_and_enable(struct nfp_net *nn)
nn->ctrl = new_ctrl;
- for (r = 0; r < nn->num_r_vecs; r++)
- nfp_net_rx_ring_fill_freelist(nn->r_vecs[r].rx_ring);
+ for (r = 0; r < nn->num_rx_rings; r++)
+ nfp_net_rx_ring_fill_freelist(&nn->rx_rings[r]);
/* Since reconfiguration requests while NFP is down are ignored we
* have to wipe the entire VXLAN configuration and reinitialize it.
@@ -2068,6 +2258,15 @@ static void nfp_net_open_stack(struct nfp_net *nn)
static int nfp_net_netdev_open(struct net_device *netdev)
{
struct nfp_net *nn = netdev_priv(netdev);
+ struct nfp_net_ring_set rx = {
+ .n_rings = nn->num_rx_rings,
+ .mtu = nn->netdev->mtu,
+ .dcnt = nn->rxd_cnt,
+ };
+ struct nfp_net_ring_set tx = {
+ .n_rings = nn->num_tx_rings,
+ .dcnt = nn->txd_cnt,
+ };
int err, r;
if (nn->ctrl & NFP_NET_CFG_CTRL_ENABLE) {
@@ -2092,39 +2291,29 @@ static int nfp_net_netdev_open(struct net_device *netdev)
goto err_free_exn;
disable_irq(nn->irq_entries[NFP_NET_IRQ_LSC_IDX].vector);
- nn->rx_rings = kcalloc(nn->num_rx_rings, sizeof(*nn->rx_rings),
- GFP_KERNEL);
+ for (r = 0; r < nn->num_r_vecs; r++) {
+ err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r);
+ if (err)
+ goto err_cleanup_vec_p;
+ }
+
+ nn->rx_rings = nfp_net_rx_ring_set_prepare(nn, &rx, nn->xdp_prog);
if (!nn->rx_rings) {
err = -ENOMEM;
- goto err_free_lsc;
+ goto err_cleanup_vec;
}
- nn->tx_rings = kcalloc(nn->num_tx_rings, sizeof(*nn->tx_rings),
- GFP_KERNEL);
+
+ nn->tx_rings = nfp_net_tx_ring_set_prepare(nn, &tx,
+ nn->num_stack_tx_rings);
if (!nn->tx_rings) {
err = -ENOMEM;
goto err_free_rx_rings;
}
- for (r = 0; r < nn->num_r_vecs; r++) {
- err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r);
- if (err)
- goto err_free_prev_vecs;
+ for (r = 0; r < nn->max_r_vecs; r++)
+ nfp_net_vector_assign_rings(nn, &nn->r_vecs[r], r);
- err = nfp_net_tx_ring_alloc(nn->r_vecs[r].tx_ring, nn->txd_cnt);
- if (err)
- goto err_cleanup_vec_p;
-
- err = nfp_net_rx_ring_alloc(nn->r_vecs[r].rx_ring,
- nn->fl_bufsz, nn->rxd_cnt);
- if (err)
- goto err_free_tx_ring_p;
-
- err = nfp_net_rx_ring_bufs_alloc(nn, nn->r_vecs[r].rx_ring);
- if (err)
- goto err_flush_rx_ring_p;
- }
-
- err = netif_set_real_num_tx_queues(netdev, nn->num_tx_rings);
+ err = netif_set_real_num_tx_queues(netdev, nn->num_stack_tx_rings);
if (err)
goto err_free_rings;
@@ -2154,21 +2343,14 @@ static int nfp_net_netdev_open(struct net_device *netdev)
return 0;
err_free_rings:
- r = nn->num_r_vecs;
-err_free_prev_vecs:
- while (r--) {
- nfp_net_rx_ring_bufs_free(nn, nn->r_vecs[r].rx_ring);
-err_flush_rx_ring_p:
- nfp_net_rx_ring_free(nn->r_vecs[r].rx_ring);
-err_free_tx_ring_p:
- nfp_net_tx_ring_free(nn->r_vecs[r].tx_ring);
-err_cleanup_vec_p:
- nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
- }
- kfree(nn->tx_rings);
+ nfp_net_tx_ring_set_free(nn, &tx);
err_free_rx_rings:
- kfree(nn->rx_rings);
-err_free_lsc:
+ nfp_net_rx_ring_set_free(nn, &rx, nn->xdp_prog);
+err_cleanup_vec:
+ r = nn->num_r_vecs;
+err_cleanup_vec_p:
+ while (r--)
+ nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
nfp_net_aux_irq_free(nn, NFP_NET_CFG_LSC, NFP_NET_IRQ_LSC_IDX);
err_free_exn:
nfp_net_aux_irq_free(nn, NFP_NET_CFG_EXN, NFP_NET_IRQ_EXN_IDX);
@@ -2203,12 +2385,14 @@ static void nfp_net_close_free_all(struct nfp_net *nn)
{
unsigned int r;
- for (r = 0; r < nn->num_r_vecs; r++) {
- nfp_net_rx_ring_bufs_free(nn, nn->r_vecs[r].rx_ring);
- nfp_net_rx_ring_free(nn->r_vecs[r].rx_ring);
- nfp_net_tx_ring_free(nn->r_vecs[r].tx_ring);
- nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
+ for (r = 0; r < nn->num_rx_rings; r++) {
+ nfp_net_rx_ring_bufs_free(nn, &nn->rx_rings[r], nn->xdp_prog);
+ nfp_net_rx_ring_free(&nn->rx_rings[r]);
}
+ for (r = 0; r < nn->num_tx_rings; r++)
+ nfp_net_tx_ring_free(&nn->tx_rings[r]);
+ for (r = 0; r < nn->num_r_vecs; r++)
+ nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
kfree(nn->rx_rings);
kfree(nn->tx_rings);
@@ -2271,89 +2455,135 @@ static void nfp_net_set_rx_mode(struct net_device *netdev)
nn->ctrl = new_ctrl;
}
-static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu)
+static void nfp_net_rss_init_itbl(struct nfp_net *nn)
{
- unsigned int old_mtu, old_fl_bufsz, new_fl_bufsz;
- struct nfp_net *nn = netdev_priv(netdev);
- struct nfp_net_rx_ring *tmp_rings;
- int err;
+ int i;
- old_mtu = netdev->mtu;
- old_fl_bufsz = nn->fl_bufsz;
- new_fl_bufsz = NFP_NET_MAX_PREPEND + ETH_HLEN + VLAN_HLEN * 2 + new_mtu;
-
- if (!netif_running(netdev)) {
- netdev->mtu = new_mtu;
- nn->fl_bufsz = new_fl_bufsz;
- return 0;
- }
-
- /* Prepare new rings */
- tmp_rings = nfp_net_shadow_rx_rings_prepare(nn, new_fl_bufsz,
- nn->rxd_cnt);
- if (!tmp_rings)
- return -ENOMEM;
-
- /* Stop device, swap in new rings, try to start the firmware */
- nfp_net_close_stack(nn);
- nfp_net_clear_config_and_disable(nn);
-
- tmp_rings = nfp_net_shadow_rx_rings_swap(nn, tmp_rings);
-
- netdev->mtu = new_mtu;
- nn->fl_bufsz = new_fl_bufsz;
-
- err = nfp_net_set_config_and_enable(nn);
- if (err) {
- const int err_new = err;
-
- /* Try with old configuration and old rings */
- tmp_rings = nfp_net_shadow_rx_rings_swap(nn, tmp_rings);
-
- netdev->mtu = old_mtu;
- nn->fl_bufsz = old_fl_bufsz;
-
- err = __nfp_net_set_config_and_enable(nn);
- if (err)
- nn_err(nn, "Can't restore MTU - FW communication failed (%d,%d)\n",
- err_new, err);
- }
-
- nfp_net_shadow_rx_rings_free(nn, tmp_rings);
-
- nfp_net_open_stack(nn);
-
- return err;
+ for (i = 0; i < sizeof(nn->rss_itbl); i++)
+ nn->rss_itbl[i] =
+ ethtool_rxfh_indir_default(i, nn->num_rx_rings);
}
-int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt)
+static int
+nfp_net_ring_swap_enable(struct nfp_net *nn, unsigned int *num_vecs,
+ unsigned int *stack_tx_rings,
+ struct bpf_prog **xdp_prog,
+ struct nfp_net_ring_set *rx,
+ struct nfp_net_ring_set *tx)
{
- struct nfp_net_tx_ring *tx_rings = NULL;
- struct nfp_net_rx_ring *rx_rings = NULL;
- u32 old_rxd_cnt, old_txd_cnt;
+ unsigned int r;
int err;
+ if (rx)
+ nfp_net_rx_ring_set_swap(nn, rx);
+ if (tx)
+ nfp_net_tx_ring_set_swap(nn, tx);
+
+ swap(*num_vecs, nn->num_r_vecs);
+ swap(*stack_tx_rings, nn->num_stack_tx_rings);
+ *xdp_prog = xchg(&nn->xdp_prog, *xdp_prog);
+
+ for (r = 0; r < nn->max_r_vecs; r++)
+ nfp_net_vector_assign_rings(nn, &nn->r_vecs[r], r);
+
+ if (!netif_is_rxfh_configured(nn->netdev))
+ nfp_net_rss_init_itbl(nn);
+
+ err = netif_set_real_num_rx_queues(nn->netdev,
+ nn->num_rx_rings);
+ if (err)
+ return err;
+
+ if (nn->netdev->real_num_tx_queues != nn->num_stack_tx_rings) {
+ err = netif_set_real_num_tx_queues(nn->netdev,
+ nn->num_stack_tx_rings);
+ if (err)
+ return err;
+ }
+
+ return __nfp_net_set_config_and_enable(nn);
+}
+
+static int
+nfp_net_check_config(struct nfp_net *nn, struct bpf_prog *xdp_prog,
+ struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx)
+{
+ /* XDP-enabled tests */
+ if (!xdp_prog)
+ return 0;
+ if (rx && nfp_net_calc_fl_bufsz(nn, rx->mtu) > PAGE_SIZE) {
+ nn_warn(nn, "MTU too large w/ XDP enabled\n");
+ return -EINVAL;
+ }
+ if (tx && tx->n_rings > nn->max_tx_rings) {
+ nn_warn(nn, "Insufficient number of TX rings w/ XDP enabled\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void
+nfp_net_ring_reconfig_down(struct nfp_net *nn, struct bpf_prog **xdp_prog,
+ struct nfp_net_ring_set *rx,
+ struct nfp_net_ring_set *tx,
+ unsigned int stack_tx_rings, unsigned int num_vecs)
+{
+ nn->netdev->mtu = rx ? rx->mtu : nn->netdev->mtu;
+ nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, nn->netdev->mtu);
+ nn->rxd_cnt = rx ? rx->dcnt : nn->rxd_cnt;
+ nn->txd_cnt = tx ? tx->dcnt : nn->txd_cnt;
+ nn->num_rx_rings = rx ? rx->n_rings : nn->num_rx_rings;
+ nn->num_tx_rings = tx ? tx->n_rings : nn->num_tx_rings;
+ nn->num_stack_tx_rings = stack_tx_rings;
+ nn->num_r_vecs = num_vecs;
+ *xdp_prog = xchg(&nn->xdp_prog, *xdp_prog);
+
+ if (!netif_is_rxfh_configured(nn->netdev))
+ nfp_net_rss_init_itbl(nn);
+}
+
+int
+nfp_net_ring_reconfig(struct nfp_net *nn, struct bpf_prog **xdp_prog,
+ struct nfp_net_ring_set *rx, struct nfp_net_ring_set *tx)
+{
+ unsigned int stack_tx_rings, num_vecs, r;
+ int err;
+
+ stack_tx_rings = tx ? tx->n_rings : nn->num_tx_rings;
+ if (*xdp_prog)
+ stack_tx_rings -= rx ? rx->n_rings : nn->num_rx_rings;
+
+ num_vecs = max(rx ? rx->n_rings : nn->num_rx_rings, stack_tx_rings);
+
+ err = nfp_net_check_config(nn, *xdp_prog, rx, tx);
+ if (err)
+ return err;
+
if (!netif_running(nn->netdev)) {
- nn->rxd_cnt = rxd_cnt;
- nn->txd_cnt = txd_cnt;
+ nfp_net_ring_reconfig_down(nn, xdp_prog, rx, tx,
+ stack_tx_rings, num_vecs);
return 0;
}
- old_rxd_cnt = nn->rxd_cnt;
- old_txd_cnt = nn->txd_cnt;
-
/* Prepare new rings */
- if (nn->rxd_cnt != rxd_cnt) {
- rx_rings = nfp_net_shadow_rx_rings_prepare(nn, nn->fl_bufsz,
- rxd_cnt);
- if (!rx_rings)
- return -ENOMEM;
+ for (r = nn->num_r_vecs; r < num_vecs; r++) {
+ err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r);
+ if (err) {
+ num_vecs = r;
+ goto err_cleanup_vecs;
+ }
}
- if (nn->txd_cnt != txd_cnt) {
- tx_rings = nfp_net_shadow_tx_rings_prepare(nn, txd_cnt);
- if (!tx_rings) {
- nfp_net_shadow_rx_rings_free(nn, rx_rings);
- return -ENOMEM;
+ if (rx) {
+ if (!nfp_net_rx_ring_set_prepare(nn, rx, *xdp_prog)) {
+ err = -ENOMEM;
+ goto err_cleanup_vecs;
+ }
+ }
+ if (tx) {
+ if (!nfp_net_tx_ring_set_prepare(nn, tx, stack_tx_rings)) {
+ err = -ENOMEM;
+ goto err_free_rx;
}
}
@@ -2361,39 +2591,51 @@ int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt)
nfp_net_close_stack(nn);
nfp_net_clear_config_and_disable(nn);
- if (rx_rings)
- rx_rings = nfp_net_shadow_rx_rings_swap(nn, rx_rings);
- if (tx_rings)
- tx_rings = nfp_net_shadow_tx_rings_swap(nn, tx_rings);
-
- nn->rxd_cnt = rxd_cnt;
- nn->txd_cnt = txd_cnt;
-
- err = nfp_net_set_config_and_enable(nn);
+ err = nfp_net_ring_swap_enable(nn, &num_vecs, &stack_tx_rings,
+ xdp_prog, rx, tx);
if (err) {
- const int err_new = err;
+ int err2;
+
+ nfp_net_clear_config_and_disable(nn);
/* Try with old configuration and old rings */
- if (rx_rings)
- rx_rings = nfp_net_shadow_rx_rings_swap(nn, rx_rings);
- if (tx_rings)
- tx_rings = nfp_net_shadow_tx_rings_swap(nn, tx_rings);
-
- nn->rxd_cnt = old_rxd_cnt;
- nn->txd_cnt = old_txd_cnt;
-
- err = __nfp_net_set_config_and_enable(nn);
- if (err)
+ err2 = nfp_net_ring_swap_enable(nn, &num_vecs, &stack_tx_rings,
+ xdp_prog, rx, tx);
+ if (err2)
nn_err(nn, "Can't restore ring config - FW communication failed (%d,%d)\n",
- err_new, err);
+ err, err2);
}
+ for (r = num_vecs - 1; r >= nn->num_r_vecs; r--)
+ nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
- nfp_net_shadow_rx_rings_free(nn, rx_rings);
- nfp_net_shadow_tx_rings_free(nn, tx_rings);
+ if (rx)
+ nfp_net_rx_ring_set_free(nn, rx, *xdp_prog);
+ if (tx)
+ nfp_net_tx_ring_set_free(nn, tx);
nfp_net_open_stack(nn);
return err;
+
+err_free_rx:
+ if (rx)
+ nfp_net_rx_ring_set_free(nn, rx, *xdp_prog);
+err_cleanup_vecs:
+ for (r = num_vecs - 1; r >= nn->num_r_vecs; r--)
+ nfp_net_cleanup_vector(nn, &nn->r_vecs[r]);
+ return err;
+}
+
+static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu)
+{
+ struct nfp_net *nn = netdev_priv(netdev);
+ struct nfp_net_ring_set rx = {
+ .n_rings = nn->num_rx_rings,
+ .mtu = new_mtu,
+ .dcnt = nn->rxd_cnt,
+ };
+
+ return nfp_net_ring_reconfig(nn, &nn->xdp_prog, &rx, NULL);
}
static struct rtnl_link_stats64 *nfp_net_stat64(struct net_device *netdev,
@@ -2450,8 +2692,12 @@ nfp_net_setup_tc(struct net_device *netdev, u32 handle, __be16 proto,
if (proto != htons(ETH_P_ALL))
return -ENOTSUPP;
- if (tc->type == TC_SETUP_CLSBPF && nfp_net_ebpf_capable(nn))
- return nfp_net_bpf_offload(nn, handle, proto, tc->cls_bpf);
+ if (tc->type == TC_SETUP_CLSBPF && nfp_net_ebpf_capable(nn)) {
+ if (!nn->bpf_offload_xdp)
+ return nfp_net_bpf_offload(nn, tc->cls_bpf);
+ else
+ return -EBUSY;
+ }
return -EINVAL;
}
@@ -2659,6 +2905,87 @@ static void nfp_net_del_vxlan_port(struct net_device *netdev,
nfp_net_set_vxlan_port(nn, idx, 0);
}
+static int nfp_net_xdp_offload(struct nfp_net *nn, struct bpf_prog *prog)
+{
+ struct tc_cls_bpf_offload cmd = {
+ .prog = prog,
+ };
+ int ret;
+
+ if (!nfp_net_ebpf_capable(nn))
+ return -EINVAL;
+
+ if (nn->ctrl & NFP_NET_CFG_CTRL_BPF) {
+ if (!nn->bpf_offload_xdp)
+ return prog ? -EBUSY : 0;
+ cmd.command = prog ? TC_CLSBPF_REPLACE : TC_CLSBPF_DESTROY;
+ } else {
+ if (!prog)
+ return 0;
+ cmd.command = TC_CLSBPF_ADD;
+ }
+
+ ret = nfp_net_bpf_offload(nn, &cmd);
+ /* Stop offload if replace not possible */
+ if (ret && cmd.command == TC_CLSBPF_REPLACE)
+ nfp_net_xdp_offload(nn, NULL);
+ nn->bpf_offload_xdp = prog && !ret;
+ return ret;
+}
+
+static int nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog)
+{
+ struct nfp_net_ring_set rx = {
+ .n_rings = nn->num_rx_rings,
+ .mtu = nn->netdev->mtu,
+ .dcnt = nn->rxd_cnt,
+ };
+ struct nfp_net_ring_set tx = {
+ .n_rings = nn->num_tx_rings,
+ .dcnt = nn->txd_cnt,
+ };
+ int err;
+
+ if (!prog && !nn->xdp_prog)
+ return 0;
+ if (prog && nn->xdp_prog) {
+ prog = xchg(&nn->xdp_prog, prog);
+ bpf_prog_put(prog);
+ nfp_net_xdp_offload(nn, nn->xdp_prog);
+ return 0;
+ }
+
+ tx.n_rings += prog ? nn->num_rx_rings : -nn->num_rx_rings;
+
+ /* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */
+ err = nfp_net_ring_reconfig(nn, &prog, &rx, &tx);
+ if (err)
+ return err;
+
+ /* @prog got swapped and is now the old one */
+ if (prog)
+ bpf_prog_put(prog);
+
+ nfp_net_xdp_offload(nn, nn->xdp_prog);
+
+ return 0;
+}
+
+static int nfp_net_xdp(struct net_device *netdev, struct netdev_xdp *xdp)
+{
+ struct nfp_net *nn = netdev_priv(netdev);
+
+ switch (xdp->command) {
+ case XDP_SETUP_PROG:
+ return nfp_net_xdp_setup(nn, xdp->prog);
+ case XDP_QUERY_PROG:
+ xdp->prog_attached = !!nn->xdp_prog;
+ return 0;
+ default:
+ return -EINVAL;
+ }
+}
+
static const struct net_device_ops nfp_net_netdev_ops = {
.ndo_open = nfp_net_netdev_open,
.ndo_stop = nfp_net_netdev_close,
@@ -2673,6 +3000,7 @@ static const struct net_device_ops nfp_net_netdev_ops = {
.ndo_features_check = nfp_net_features_check,
.ndo_udp_tunnel_add = nfp_net_add_vxlan_port,
.ndo_udp_tunnel_del = nfp_net_del_vxlan_port,
+ .ndo_xdp = nfp_net_xdp,
};
/**
@@ -2681,8 +3009,7 @@ static const struct net_device_ops nfp_net_netdev_ops = {
*/
void nfp_net_info(struct nfp_net *nn)
{
- nn_info(nn, "Netronome %s %sNetdev: TxQs=%d/%d RxQs=%d/%d\n",
- nn->is_nfp3200 ? "NFP-32xx" : "NFP-6xxx",
+ nn_info(nn, "Netronome NFP-6xxx %sNetdev: TxQs=%d/%d RxQs=%d/%d\n",
nn->is_vf ? "VF " : "",
nn->num_tx_rings, nn->max_tx_rings,
nn->num_rx_rings, nn->max_rx_rings);
@@ -2723,11 +3050,11 @@ void nfp_net_info(struct nfp_net *nn)
* Return: NFP Net device structure, or ERR_PTR on error.
*/
struct nfp_net *nfp_net_netdev_alloc(struct pci_dev *pdev,
- int max_tx_rings, int max_rx_rings)
+ unsigned int max_tx_rings,
+ unsigned int max_rx_rings)
{
struct net_device *netdev;
struct nfp_net *nn;
- int nqs;
netdev = alloc_etherdev_mqs(sizeof(struct nfp_net),
max_tx_rings, max_rx_rings);
@@ -2743,9 +3070,12 @@ struct nfp_net *nfp_net_netdev_alloc(struct pci_dev *pdev,
nn->max_tx_rings = max_tx_rings;
nn->max_rx_rings = max_rx_rings;
- nqs = netif_get_num_default_rss_queues();
- nn->num_tx_rings = min_t(int, nqs, max_tx_rings);
- nn->num_rx_rings = min_t(int, nqs, max_rx_rings);
+ nn->num_tx_rings = min_t(unsigned int, max_tx_rings, num_online_cpus());
+ nn->num_rx_rings = min_t(unsigned int, max_rx_rings,
+ netif_get_num_default_rss_queues());
+
+ nn->num_r_vecs = max(nn->num_tx_rings, nn->num_rx_rings);
+ nn->num_r_vecs = min_t(unsigned int, nn->num_r_vecs, num_online_cpus());
nn->txd_cnt = NFP_NET_TX_DESCS_DEFAULT;
nn->rxd_cnt = NFP_NET_RX_DESCS_DEFAULT;
@@ -2777,13 +3107,9 @@ void nfp_net_netdev_free(struct nfp_net *nn)
*/
static void nfp_net_rss_init(struct nfp_net *nn)
{
- int i;
-
netdev_rss_key_fill(nn->rss_key, NFP_NET_CFG_RSS_KEY_SZ);
- for (i = 0; i < sizeof(nn->rss_itbl); i++)
- nn->rss_itbl[i] =
- ethtool_rxfh_indir_default(i, nn->num_rx_rings);
+ nfp_net_rss_init_itbl(nn);
/* Enable IPv4/IPv6 TCP by default */
nn->rss_cfg = NFP_NET_CFG_RSS_IPV4_TCP |
@@ -2821,12 +3147,18 @@ int nfp_net_netdev_init(struct net_device *netdev)
nfp_net_write_mac_addr(nn);
+ /* Determine RX packet/metadata boundary offset */
+ if (nn->fw_ver.major >= 2)
+ nn->rx_offset = nn_readl(nn, NFP_NET_CFG_RX_OFFSET);
+ else
+ nn->rx_offset = NFP_NET_RX_OFFSET;
+
/* Set default MTU and Freelist buffer size */
if (nn->max_mtu < NFP_NET_DEFAULT_MTU)
netdev->mtu = nn->max_mtu;
else
netdev->mtu = NFP_NET_DEFAULT_MTU;
- nn->fl_bufsz = NFP_NET_DEFAULT_RX_BUFSZ;
+ nn->fl_bufsz = nfp_net_calc_fl_bufsz(nn, netdev->mtu);
/* Advertise/enable offloads based on capabilities
*
@@ -2897,18 +3229,6 @@ int nfp_net_netdev_init(struct net_device *netdev)
nn->ctrl |= NFP_NET_CFG_CTRL_IRQMOD;
}
- /* On NFP-3200 enable MSI-X auto-masking, if supported and the
- * interrupts are not shared.
- */
- if (nn->is_nfp3200 && nn->cap & NFP_NET_CFG_CTRL_MSIXAUTO)
- nn->ctrl |= NFP_NET_CFG_CTRL_MSIXAUTO;
-
- /* On NFP4000/NFP6000, determine RX packet/metadata boundary offset */
- if (nn->fw_ver.major >= 2)
- nn->rx_offset = nn_readl(nn, NFP_NET_CFG_RX_OFFSET);
- else
- nn->rx_offset = NFP_NET_RX_OFFSET;
-
/* Stash the re-configuration queue away. First odd queue in TX Bar */
nn->qcp_cfg = nn->tx_bar + NFP_QCP_QUEUE_ADDR_SZ;
@@ -2922,7 +3242,6 @@ int nfp_net_netdev_init(struct net_device *netdev)
return err;
/* Finalise the netdev setup */
- ether_setup(netdev);
netdev->netdev_ops = &nfp_net_netdev_ops;
netdev->watchdog_timeo = msecs_to_jiffies(5 * 1000);
@@ -2944,5 +3263,11 @@ int nfp_net_netdev_init(struct net_device *netdev)
*/
void nfp_net_netdev_clean(struct net_device *netdev)
{
- unregister_netdev(netdev);
+ struct nfp_net *nn = netdev_priv(netdev);
+
+ if (nn->xdp_prog)
+ bpf_prog_put(nn->xdp_prog);
+ if (nn->bpf_offload_xdp)
+ nfp_net_xdp_offload(nn, NULL);
+ unregister_netdev(nn->netdev);
}
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
index 93b10b4..385ba35 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
@@ -50,7 +50,7 @@
/**
* Configuration BAR size.
*
- * The configuration BAR is 8K in size, but on the NFP6000, due to
+ * The configuration BAR is 8K in size, but due to
* THB-350, 32k needs to be reserved.
*/
#define NFP_NET_CFG_BAR_SZ (32 * 1024)
@@ -186,18 +186,13 @@
#define NFP_NET_CFG_START_RXQ 0x004c
/**
- * NFP-3200 workaround (0x0050 - 0x0058)
- * @NFP_NET_CFG_SPARE_ADDR: DMA address for ME code to use (e.g. YDS-155 fix)
- */
-#define NFP_NET_CFG_SPARE_ADDR 0x0050
-/**
- * NFP6000/NFP4000 - Prepend configuration
+ * Prepend configuration
*/
#define NFP_NET_CFG_RX_OFFSET 0x0050
#define NFP_NET_CFG_RX_OFFSET_DYNAMIC 0 /* Prepend mode */
/**
- * NFP6000/NFP4000 - VXLAN/UDP encap configuration
+ * VXLAN/UDP encap configuration
* @NFP_NET_CFG_VXLAN_PORT: Base address of table of tunnels' UDP dst ports
* @NFP_NET_CFG_VXLAN_SZ: Size of the UDP port table in bytes
*/
@@ -205,7 +200,7 @@
#define NFP_NET_CFG_VXLAN_SZ 0x0008
/**
- * NFP6000 - BPF section
+ * BPF section
* @NFP_NET_CFG_BPF_ABI: BPF ABI version
* @NFP_NET_CFG_BPF_CAP: BPF capabilities
* @NFP_NET_CFG_BPF_MAX_LEN: Maximum size of JITed BPF code in bytes
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
index f7c9a5b..c66f3f9 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
@@ -44,8 +44,8 @@ static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
struct nfp_net_r_vector *r_vec = file->private;
struct nfp_net_rx_ring *rx_ring;
struct nfp_net_rx_desc *rxd;
- struct sk_buff *skb;
struct nfp_net *nn;
+ void *frag;
int i;
rtnl_lock();
@@ -73,10 +73,9 @@ static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
seq_printf(file, "%04d: 0x%08x 0x%08x", i,
rxd->vals[0], rxd->vals[1]);
- skb = READ_ONCE(rx_ring->rxbufs[i].skb);
- if (skb)
- seq_printf(file, " skb->head=%p skb->data=%p",
- skb->head, skb->data);
+ frag = READ_ONCE(rx_ring->rxbufs[i].frag);
+ if (frag)
+ seq_printf(file, " frag=%p", frag);
if (rx_ring->rxbufs[i].dma_addr)
seq_printf(file, " dma_addr=%pad",
@@ -115,6 +114,16 @@ static const struct file_operations nfp_rx_q_fops = {
.llseek = seq_lseek
};
+static int nfp_net_debugfs_tx_q_open(struct inode *inode, struct file *f);
+
+static const struct file_operations nfp_tx_q_fops = {
+ .owner = THIS_MODULE,
+ .open = nfp_net_debugfs_tx_q_open,
+ .release = single_release,
+ .read = seq_read,
+ .llseek = seq_lseek
+};
+
static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data)
{
struct nfp_net_r_vector *r_vec = file->private;
@@ -127,10 +136,13 @@ static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data)
rtnl_lock();
- if (!r_vec->nfp_net || !r_vec->tx_ring)
+ if (debugfs_real_fops(file->file) == &nfp_tx_q_fops)
+ tx_ring = r_vec->tx_ring;
+ else
+ tx_ring = r_vec->xdp_ring;
+ if (!r_vec->nfp_net || !tx_ring)
goto out;
nn = r_vec->nfp_net;
- tx_ring = r_vec->tx_ring;
if (!netif_running(nn->netdev))
goto out;
@@ -149,9 +161,14 @@ static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data)
txd->vals[2], txd->vals[3]);
skb = READ_ONCE(tx_ring->txbufs[i].skb);
- if (skb)
- seq_printf(file, " skb->head=%p skb->data=%p",
- skb->head, skb->data);
+ if (skb) {
+ if (tx_ring == r_vec->tx_ring)
+ seq_printf(file, " skb->head=%p skb->data=%p",
+ skb->head, skb->data);
+ else
+ seq_printf(file, " frag=%p", skb);
+ }
+
if (tx_ring->txbufs[i].dma_addr)
seq_printf(file, " dma_addr=%pad",
&tx_ring->txbufs[i].dma_addr);
@@ -177,7 +194,7 @@ static int nfp_net_debugfs_tx_q_open(struct inode *inode, struct file *f)
return single_open(f, nfp_net_debugfs_tx_q_read, inode->i_private);
}
-static const struct file_operations nfp_tx_q_fops = {
+static const struct file_operations nfp_xdp_q_fops = {
.owner = THIS_MODULE,
.open = nfp_net_debugfs_tx_q_open,
.release = single_release,
@@ -187,7 +204,7 @@ static const struct file_operations nfp_tx_q_fops = {
void nfp_net_debugfs_adapter_add(struct nfp_net *nn)
{
- struct dentry *queues, *tx, *rx;
+ struct dentry *queues, *tx, *rx, *xdp;
char int_name[16];
int i;
@@ -205,16 +222,19 @@ void nfp_net_debugfs_adapter_add(struct nfp_net *nn)
rx = debugfs_create_dir("rx", queues);
tx = debugfs_create_dir("tx", queues);
- if (IS_ERR_OR_NULL(rx) || IS_ERR_OR_NULL(tx))
+ xdp = debugfs_create_dir("xdp", queues);
+ if (IS_ERR_OR_NULL(rx) || IS_ERR_OR_NULL(tx) || IS_ERR_OR_NULL(xdp))
return;
- for (i = 0; i < nn->num_rx_rings; i++) {
+ for (i = 0; i < min(nn->max_rx_rings, nn->max_r_vecs); i++) {
sprintf(int_name, "%d", i);
debugfs_create_file(int_name, S_IRUSR, rx,
&nn->r_vecs[i], &nfp_rx_q_fops);
+ debugfs_create_file(int_name, S_IRUSR, xdp,
+ &nn->r_vecs[i], &nfp_xdp_q_fops);
}
- for (i = 0; i < nn->num_tx_rings; i++) {
+ for (i = 0; i < min(nn->max_tx_rings, nn->max_r_vecs); i++) {
sprintf(int_name, "%d", i);
debugfs_create_file(int_name, S_IRUSR, tx,
&nn->r_vecs[i], &nfp_tx_q_fops);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 3418f22..1b26e96 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -158,6 +158,28 @@ static void nfp_net_get_ringparam(struct net_device *netdev,
ring->tx_pending = nn->txd_cnt;
}
+static int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt)
+{
+ struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL;
+ struct nfp_net_ring_set rx = {
+ .n_rings = nn->num_rx_rings,
+ .mtu = nn->netdev->mtu,
+ .dcnt = rxd_cnt,
+ };
+ struct nfp_net_ring_set tx = {
+ .n_rings = nn->num_tx_rings,
+ .dcnt = txd_cnt,
+ };
+
+ if (nn->rxd_cnt != rxd_cnt)
+ reconfig_rx = ℞
+ if (nn->txd_cnt != txd_cnt)
+ reconfig_tx = &tx;
+
+ return nfp_net_ring_reconfig(nn, &nn->xdp_prog,
+ reconfig_rx, reconfig_tx);
+}
+
static int nfp_net_set_ringparam(struct net_device *netdev,
struct ethtool_ringparam *ring)
{
@@ -614,6 +636,76 @@ static int nfp_net_set_coalesce(struct net_device *netdev,
return nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_IRQMOD);
}
+static void nfp_net_get_channels(struct net_device *netdev,
+ struct ethtool_channels *channel)
+{
+ struct nfp_net *nn = netdev_priv(netdev);
+ unsigned int num_tx_rings;
+
+ num_tx_rings = nn->num_tx_rings;
+ if (nn->xdp_prog)
+ num_tx_rings -= nn->num_rx_rings;
+
+ channel->max_rx = min(nn->max_rx_rings, nn->max_r_vecs);
+ channel->max_tx = min(nn->max_tx_rings, nn->max_r_vecs);
+ channel->max_combined = min(channel->max_rx, channel->max_tx);
+ channel->max_other = NFP_NET_NON_Q_VECTORS;
+ channel->combined_count = min(nn->num_rx_rings, num_tx_rings);
+ channel->rx_count = nn->num_rx_rings - channel->combined_count;
+ channel->tx_count = num_tx_rings - channel->combined_count;
+ channel->other_count = NFP_NET_NON_Q_VECTORS;
+}
+
+static int nfp_net_set_num_rings(struct nfp_net *nn, unsigned int total_rx,
+ unsigned int total_tx)
+{
+ struct nfp_net_ring_set *reconfig_rx = NULL, *reconfig_tx = NULL;
+ struct nfp_net_ring_set rx = {
+ .n_rings = total_rx,
+ .mtu = nn->netdev->mtu,
+ .dcnt = nn->rxd_cnt,
+ };
+ struct nfp_net_ring_set tx = {
+ .n_rings = total_tx,
+ .dcnt = nn->txd_cnt,
+ };
+
+ if (nn->num_rx_rings != total_rx)
+ reconfig_rx = ℞
+ if (nn->num_stack_tx_rings != total_tx ||
+ (nn->xdp_prog && reconfig_rx))
+ reconfig_tx = &tx;
+
+ /* nfp_net_check_config() will catch tx.n_rings > nn->max_tx_rings */
+ if (nn->xdp_prog)
+ tx.n_rings += total_rx;
+
+ return nfp_net_ring_reconfig(nn, &nn->xdp_prog,
+ reconfig_rx, reconfig_tx);
+}
+
+static int nfp_net_set_channels(struct net_device *netdev,
+ struct ethtool_channels *channel)
+{
+ struct nfp_net *nn = netdev_priv(netdev);
+ unsigned int total_rx, total_tx;
+
+ /* Reject unsupported */
+ if (!channel->combined_count ||
+ channel->other_count != NFP_NET_NON_Q_VECTORS ||
+ (channel->rx_count && channel->tx_count))
+ return -EINVAL;
+
+ total_rx = channel->combined_count + channel->rx_count;
+ total_tx = channel->combined_count + channel->tx_count;
+
+ if (total_rx > min(nn->max_rx_rings, nn->max_r_vecs) ||
+ total_tx > min(nn->max_tx_rings, nn->max_r_vecs))
+ return -EINVAL;
+
+ return nfp_net_set_num_rings(nn, total_rx, total_tx);
+}
+
static const struct ethtool_ops nfp_net_ethtool_ops = {
.get_drvinfo = nfp_net_get_drvinfo,
.get_link = ethtool_op_get_link,
@@ -632,6 +724,8 @@ static const struct ethtool_ops nfp_net_ethtool_ops = {
.get_regs = nfp_net_get_regs,
.get_coalesce = nfp_net_get_coalesce,
.set_coalesce = nfp_net_set_coalesce,
+ .get_channels = nfp_net_get_channels,
+ .set_channels = nfp_net_set_channels,
};
void nfp_net_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c
index cfed40c..18a851e 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c
@@ -111,6 +111,9 @@ nfp_net_bpf_get_act(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf)
const struct tc_action *a;
LIST_HEAD(actions);
+ if (!cls_bpf->exts)
+ return NN_ACT_XDP;
+
/* TC direct action */
if (cls_bpf->exts_integrated) {
if (tc_no_actions(cls_bpf->exts))
@@ -233,9 +236,7 @@ static int nfp_net_bpf_stop(struct nfp_net *nn)
return nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN);
}
-int
-nfp_net_bpf_offload(struct nfp_net *nn, u32 handle, __be16 proto,
- struct tc_cls_bpf_offload *cls_bpf)
+int nfp_net_bpf_offload(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf)
{
struct nfp_bpf_result res;
dma_addr_t dma_addr;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
index 2800bbf..d065235 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
@@ -63,9 +63,7 @@ static void nfp_netvf_get_mac_addr(struct nfp_net *nn)
u8 mac_addr[ETH_ALEN];
put_unaligned_be32(nn_readl(nn, NFP_NET_CFG_MACADDR + 0), &mac_addr[0]);
- /* We can't do readw for NFP-3200 compatibility */
- put_unaligned_be16(nn_readl(nn, NFP_NET_CFG_MACADDR + 4) >> 16,
- &mac_addr[4]);
+ put_unaligned_be16(nn_readw(nn, NFP_NET_CFG_MACADDR + 6), &mac_addr[4]);
if (!is_valid_ether_addr(mac_addr)) {
eth_hw_addr_random(nn->netdev);
@@ -86,7 +84,6 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
int tx_bar_no, rx_bar_no;
u8 __iomem *ctrl_bar;
struct nfp_net *nn;
- int is_nfp3200;
u32 startq;
int stride;
int err;
@@ -101,15 +98,6 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
goto err_pci_disable;
}
- switch (pdev->device) {
- case PCI_DEVICE_NFP6000VF:
- is_nfp3200 = 0;
- break;
- default:
- err = -ENODEV;
- goto err_pci_regions;
- }
-
pci_set_master(pdev);
err = dma_set_mask_and_coherent(&pdev->dev,
@@ -149,15 +137,9 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
} else {
switch (fw_ver.major) {
case 1 ... 4:
- if (is_nfp3200) {
- stride = 2;
- tx_bar_no = NFP_NET_Q0_BAR;
- rx_bar_no = NFP_NET_Q1_BAR;
- } else {
- stride = 4;
- tx_bar_no = NFP_NET_Q0_BAR;
- rx_bar_no = tx_bar_no;
- }
+ stride = 4;
+ tx_bar_no = NFP_NET_Q0_BAR;
+ rx_bar_no = tx_bar_no;
break;
default:
dev_err(&pdev->dev, "Unsupported Firmware ABI %d.%d.%d.%d\n",
@@ -189,20 +171,10 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
max_rx_rings = (rx_bar_sz / NFP_QCP_QUEUE_ADDR_SZ) / 2;
}
- /* XXX Implement a workaround for THB-350 here. Ideally, we
- * have a different PCI ID for A rev VFs.
- */
- switch (pdev->device) {
- case PCI_DEVICE_NFP6000VF:
- startq = readl(ctrl_bar + NFP_NET_CFG_START_TXQ);
- tx_bar_off = NFP_PCIE_QUEUE(startq);
- startq = readl(ctrl_bar + NFP_NET_CFG_START_RXQ);
- rx_bar_off = NFP_PCIE_QUEUE(startq);
- break;
- default:
- err = -ENODEV;
- goto err_ctrl_unmap;
- }
+ startq = readl(ctrl_bar + NFP_NET_CFG_START_TXQ);
+ tx_bar_off = NFP_PCIE_QUEUE(startq);
+ startq = readl(ctrl_bar + NFP_NET_CFG_START_RXQ);
+ rx_bar_off = NFP_PCIE_QUEUE(startq);
/* Allocate and initialise the netdev */
nn = nfp_net_netdev_alloc(pdev, max_tx_rings, max_rx_rings);
@@ -214,7 +186,6 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
nn->fw_ver = fw_ver;
nn->ctrl_bar = ctrl_bar;
nn->is_vf = 1;
- nn->is_nfp3200 = is_nfp3200;
nn->stride_tx = stride;
nn->stride_rx = stride;
diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig
index 0df1391f9..32f2a45 100644
--- a/drivers/net/ethernet/qlogic/Kconfig
+++ b/drivers/net/ethernet/qlogic/Kconfig
@@ -107,15 +107,7 @@
---help---
This enables the support for ...
-config INFINIBAND_QEDR
- tristate "QLogic qede RoCE sources [debug]"
- depends on QEDE && 64BIT
- select QED_LL2
- default n
- ---help---
- This provides a temporary node that allows the compilation
- and logical testing of the InfiniBand over Ethernet support
- for QLogic QED. This would be replaced by the 'real' option
- once the QEDR driver is added [+relocated].
+config QED_RDMA
+ bool
endif # NET_VENDOR_QLOGIC
diff --git a/drivers/net/ethernet/qlogic/qed/Makefile b/drivers/net/ethernet/qlogic/qed/Makefile
index cda0af7..967acf3 100644
--- a/drivers/net/ethernet/qlogic/qed/Makefile
+++ b/drivers/net/ethernet/qlogic/qed/Makefile
@@ -5,4 +5,4 @@
qed_selftest.o qed_dcbx.o qed_debug.o
qed-$(CONFIG_QED_SRIOV) += qed_sriov.o qed_vf.o
qed-$(CONFIG_QED_LL2) += qed_ll2.o
-qed-$(CONFIG_INFINIBAND_QEDR) += qed_roce.o
+qed-$(CONFIG_QED_RDMA) += qed_roce.o
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 653bb57..50b8a01 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -154,7 +154,10 @@ struct qed_qm_iids {
u32 tids;
};
-enum QED_RESOURCES {
+/* HW / FW resources, output of features supported below, most information
+ * is received from MFW.
+ */
+enum qed_resources {
QED_SB,
QED_L2_QUEUE,
QED_VPORT,
@@ -166,6 +169,7 @@ enum QED_RESOURCES {
QED_RDMA_CNQ_RAM,
QED_ILT,
QED_LL2_QUEUE,
+ QED_CMDQS_CQS,
QED_RDMA_STATS_QUEUE,
QED_MAX_RESC,
};
@@ -174,6 +178,7 @@ enum QED_FEATURE {
QED_PF_L2_QUE,
QED_VF,
QED_RDMA_CNQ,
+ QED_VF_L2_QUE,
QED_MAX_FEATURES,
};
@@ -195,6 +200,11 @@ enum qed_dev_cap {
QED_DEV_CAP_ROCE,
};
+enum qed_wol_support {
+ QED_WOL_SUPPORT_NONE,
+ QED_WOL_SUPPORT_PME,
+};
+
struct qed_hw_info {
/* PCI personality */
enum qed_pci_personality personality;
@@ -226,6 +236,9 @@ struct qed_hw_info {
u32 port_mode;
u32 hw_mode;
unsigned long device_capabilities;
+ u16 mtu;
+
+ enum qed_wol_support b_wol_support;
};
struct qed_hw_cid_data {
@@ -538,7 +551,9 @@ struct qed_dev {
u8 mcp_rev;
u8 boot_mode;
- u8 wol;
+ /* WoL related configurations */
+ u8 wol_config;
+ u8 wol_mac[ETH_ALEN];
u32 int_mode;
enum qed_coalescing_mode int_coalescing_mode;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 82370a1..0c42c24 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -47,13 +47,8 @@
#define TM_ALIGN BIT(TM_SHIFT)
#define TM_ELEM_SIZE 4
-/* ILT constants */
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
/* For RoCE we configure to 64K to cover for RoCE max tasks 256K purpose. */
-#define ILT_DEFAULT_HW_P_SIZE 4
-#else
-#define ILT_DEFAULT_HW_P_SIZE 3
-#endif
+#define ILT_DEFAULT_HW_P_SIZE (IS_ENABLED(CONFIG_QED_RDMA) ? 4 : 3)
#define ILT_PAGE_IN_BYTES(hw_p_size) (1U << ((hw_p_size) + 12))
#define ILT_CFG_REG(cli, reg) PSWRQ2_REG_ ## cli ## _ ## reg ## _RT_OFFSET
@@ -349,14 +344,14 @@ static struct qed_tid_seg *qed_cxt_tid_seg_info(struct qed_hwfn *p_hwfn,
return NULL;
}
-void qed_cxt_set_srq_count(struct qed_hwfn *p_hwfn, u32 num_srqs)
+static void qed_cxt_set_srq_count(struct qed_hwfn *p_hwfn, u32 num_srqs)
{
struct qed_cxt_mngr *p_mgr = p_hwfn->p_cxt_mngr;
p_mgr->srq_count = num_srqs;
}
-u32 qed_cxt_get_srq_count(struct qed_hwfn *p_hwfn)
+static u32 qed_cxt_get_srq_count(struct qed_hwfn *p_hwfn)
{
struct qed_cxt_mngr *p_mgr = p_hwfn->p_cxt_mngr;
@@ -1804,8 +1799,8 @@ int qed_cxt_get_cid_info(struct qed_hwfn *p_hwfn, struct qed_cxt_info *p_info)
return 0;
}
-void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
- struct qed_rdma_pf_params *p_params)
+static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
+ struct qed_rdma_pf_params *p_params)
{
u32 num_cons, num_tasks, num_qps, num_mrs, num_srqs;
enum protocol_type proto;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 130da1c..a4789a9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -1190,6 +1190,7 @@ int qed_dcbx_get_config_params(struct qed_hwfn *p_hwfn,
if (!dcbx_info)
return -ENOMEM;
+ memset(dcbx_info, 0, sizeof(*dcbx_info));
rc = qed_dcbx_query_params(p_hwfn, dcbx_info, QED_DCBX_OPERATIONAL_MIB);
if (rc) {
kfree(dcbx_info);
@@ -1225,6 +1226,7 @@ static struct qed_dcbx_get *qed_dcbnl_get_dcbx(struct qed_hwfn *hwfn,
if (!dcbx_info)
return NULL;
+ memset(dcbx_info, 0, sizeof(*dcbx_info));
if (qed_dcbx_query_params(hwfn, dcbx_info, type)) {
kfree(dcbx_info);
return NULL;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 88e7d5b..68f19ca 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -405,7 +405,7 @@ struct phy_defs {
/***************************** Constant Arrays *******************************/
/* Debug arrays */
-static struct dbg_array s_dbg_arrays[MAX_BIN_DBG_BUFFER_TYPE] = { {0} };
+static struct dbg_array s_dbg_arrays[MAX_BIN_DBG_BUFFER_TYPE] = { {NULL} };
/* Chip constant definitions array */
static struct chip_defs s_chip_defs[MAX_CHIP_IDS] = {
@@ -4028,10 +4028,10 @@ static enum dbg_status qed_mcp_trace_read_meta(struct qed_hwfn *p_hwfn,
}
/* Dump MCP Trace */
-enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
- struct qed_ptt *p_ptt,
- u32 *dump_buf,
- bool dump, u32 *num_dumped_dwords)
+static enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ u32 *dump_buf,
+ bool dump, u32 *num_dumped_dwords)
{
u32 trace_data_grc_addr, trace_data_size_bytes, trace_data_size_dwords;
u32 trace_meta_size_dwords, running_bundle_id, offset = 0;
@@ -4130,10 +4130,10 @@ enum dbg_status qed_mcp_trace_dump(struct qed_hwfn *p_hwfn,
}
/* Dump GRC FIFO */
-enum dbg_status qed_reg_fifo_dump(struct qed_hwfn *p_hwfn,
- struct qed_ptt *p_ptt,
- u32 *dump_buf,
- bool dump, u32 *num_dumped_dwords)
+static enum dbg_status qed_reg_fifo_dump(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ u32 *dump_buf,
+ bool dump, u32 *num_dumped_dwords)
{
u32 offset = 0, dwords_read, size_param_offset;
bool fifo_has_data;
@@ -4192,10 +4192,10 @@ enum dbg_status qed_reg_fifo_dump(struct qed_hwfn *p_hwfn,
}
/* Dump IGU FIFO */
-enum dbg_status qed_igu_fifo_dump(struct qed_hwfn *p_hwfn,
- struct qed_ptt *p_ptt,
- u32 *dump_buf,
- bool dump, u32 *num_dumped_dwords)
+static enum dbg_status qed_igu_fifo_dump(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ u32 *dump_buf,
+ bool dump, u32 *num_dumped_dwords)
{
u32 offset = 0, dwords_read, size_param_offset;
bool fifo_has_data;
@@ -4255,10 +4255,11 @@ enum dbg_status qed_igu_fifo_dump(struct qed_hwfn *p_hwfn,
}
/* Protection Override dump */
-enum dbg_status qed_protection_override_dump(struct qed_hwfn *p_hwfn,
- struct qed_ptt *p_ptt,
- u32 *dump_buf,
- bool dump, u32 *num_dumped_dwords)
+static enum dbg_status qed_protection_override_dump(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ u32 *dump_buf,
+ bool dump,
+ u32 *num_dumped_dwords)
{
u32 offset = 0, size_param_offset, override_window_dwords;
@@ -6339,10 +6340,11 @@ enum dbg_status qed_print_fw_asserts_results(struct qed_hwfn *p_hwfn,
}
/* Wrapper for unifying the idle_chk and mcp_trace api */
-enum dbg_status qed_print_idle_chk_results_wrapper(struct qed_hwfn *p_hwfn,
- u32 *dump_buf,
- u32 num_dumped_dwords,
- char *results_buf)
+static enum dbg_status
+qed_print_idle_chk_results_wrapper(struct qed_hwfn *p_hwfn,
+ u32 *dump_buf,
+ u32 num_dumped_dwords,
+ char *results_buf)
{
u32 num_errors, num_warnnings;
@@ -6413,8 +6415,8 @@ static void qed_dbg_print_feature(u8 *p_text_buf, u32 text_size)
#define QED_RESULTS_BUF_MIN_SIZE 16
/* Generic function for decoding debug feature info */
-enum dbg_status format_feature(struct qed_hwfn *p_hwfn,
- enum qed_dbg_features feature_idx)
+static enum dbg_status format_feature(struct qed_hwfn *p_hwfn,
+ enum qed_dbg_features feature_idx)
{
struct qed_dbg_feature *feature =
&p_hwfn->cdev->dbg_params.features[feature_idx];
@@ -6480,8 +6482,9 @@ enum dbg_status format_feature(struct qed_hwfn *p_hwfn,
}
/* Generic function for performing the dump of a debug feature. */
-enum dbg_status qed_dbg_dump(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
- enum qed_dbg_features feature_idx)
+static enum dbg_status qed_dbg_dump(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ enum qed_dbg_features feature_idx)
{
struct qed_dbg_feature *feature =
&p_hwfn->cdev->dbg_params.features[feature_idx];
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 754f6a9..5be7b8a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -497,12 +497,13 @@ int qed_resc_alloc(struct qed_dev *cdev)
if (p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE) {
num_cons = qed_cxt_get_proto_cid_count(p_hwfn,
PROTOCOLID_ROCE,
- 0) * 2;
+ NULL) * 2;
n_eqes += num_cons + 2 * MAX_NUM_VFS_BB;
} else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) {
num_cons =
qed_cxt_get_proto_cid_count(p_hwfn,
- PROTOCOLID_ISCSI, 0);
+ PROTOCOLID_ISCSI,
+ NULL);
n_eqes += 2 * num_cons;
}
@@ -1056,8 +1057,10 @@ int qed_hw_init(struct qed_dev *cdev,
bool allow_npar_tx_switch,
const u8 *bin_fw_data)
{
- u32 load_code, param;
- int rc, mfw_rc, i;
+ u32 load_code, param, drv_mb_param;
+ bool b_default_mtu = true;
+ struct qed_hwfn *p_hwfn;
+ int rc = 0, mfw_rc, i;
if ((int_mode == QED_INT_MODE_MSI) && (cdev->num_hwfns > 1)) {
DP_NOTICE(cdev, "MSI mode is not supported for CMT devices\n");
@@ -1073,6 +1076,12 @@ int qed_hw_init(struct qed_dev *cdev,
for_each_hwfn(cdev, i) {
struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
+ /* If management didn't provide a default, set one of our own */
+ if (!p_hwfn->hw_info.mtu) {
+ p_hwfn->hw_info.mtu = 1500;
+ b_default_mtu = false;
+ }
+
if (IS_VF(cdev)) {
p_hwfn->b_int_enabled = 1;
continue;
@@ -1156,6 +1165,38 @@ int qed_hw_init(struct qed_dev *cdev,
p_hwfn->hw_init_done = true;
}
+ if (IS_PF(cdev)) {
+ p_hwfn = QED_LEADING_HWFN(cdev);
+ drv_mb_param = (FW_MAJOR_VERSION << 24) |
+ (FW_MINOR_VERSION << 16) |
+ (FW_REVISION_VERSION << 8) |
+ (FW_ENGINEERING_VERSION);
+ rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
+ DRV_MSG_CODE_OV_UPDATE_STORM_FW_VER,
+ drv_mb_param, &load_code, ¶m);
+ if (rc)
+ DP_INFO(p_hwfn, "Failed to update firmware version\n");
+
+ if (!b_default_mtu) {
+ rc = qed_mcp_ov_update_mtu(p_hwfn, p_hwfn->p_main_ptt,
+ p_hwfn->hw_info.mtu);
+ if (rc)
+ DP_INFO(p_hwfn,
+ "Failed to update default mtu\n");
+ }
+
+ rc = qed_mcp_ov_update_driver_state(p_hwfn,
+ p_hwfn->p_main_ptt,
+ QED_OV_DRIVER_STATE_DISABLED);
+ if (rc)
+ DP_INFO(p_hwfn, "Failed to update driver state\n");
+
+ rc = qed_mcp_ov_update_eswitch(p_hwfn, p_hwfn->p_main_ptt,
+ QED_OV_ESWITCH_VEB);
+ if (rc)
+ DP_INFO(p_hwfn, "Failed to update eswitch mode\n");
+ }
+
return 0;
}
@@ -1323,8 +1364,24 @@ int qed_hw_reset(struct qed_dev *cdev)
{
int rc = 0;
u32 unload_resp, unload_param;
+ u32 wol_param;
int i;
+ switch (cdev->wol_config) {
+ case QED_OV_WOL_DISABLED:
+ wol_param = DRV_MB_PARAM_UNLOAD_WOL_DISABLED;
+ break;
+ case QED_OV_WOL_ENABLED:
+ wol_param = DRV_MB_PARAM_UNLOAD_WOL_ENABLED;
+ break;
+ default:
+ DP_NOTICE(cdev,
+ "Unknown WoL configuration %02x\n", cdev->wol_config);
+ /* Fallthrough */
+ case QED_OV_WOL_DEFAULT:
+ wol_param = DRV_MB_PARAM_UNLOAD_WOL_MCP;
+ }
+
for_each_hwfn(cdev, i) {
struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
@@ -1353,8 +1410,7 @@ int qed_hw_reset(struct qed_dev *cdev)
/* Send unload command to MCP */
rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
- DRV_MSG_CODE_UNLOAD_REQ,
- DRV_MB_PARAM_UNLOAD_WOL_MCP,
+ DRV_MSG_CODE_UNLOAD_REQ, wol_param,
&unload_resp, &unload_param);
if (rc) {
DP_NOTICE(p_hwfn, "qed_hw_reset: UNLOAD_REQ failed\n");
@@ -1420,71 +1476,276 @@ static void get_function_id(struct qed_hwfn *p_hwfn)
static void qed_hw_set_feat(struct qed_hwfn *p_hwfn)
{
u32 *feat_num = p_hwfn->hw_info.feat_num;
+ struct qed_sb_cnt_info sb_cnt_info;
int num_features = 1;
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
- /* Roce CNQ each requires: 1 status block + 1 CNQ. We divide the
- * status blocks equally between L2 / RoCE but with consideration as
- * to how many l2 queues / cnqs we have
- */
- if (p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE) {
+ if (IS_ENABLED(CONFIG_QED_RDMA) &&
+ p_hwfn->hw_info.personality == QED_PCI_ETH_ROCE) {
+ /* Roce CNQ each requires: 1 status block + 1 CNQ. We divide
+ * the status blocks equally between L2 / RoCE but with
+ * consideration as to how many l2 queues / cnqs we have.
+ */
num_features++;
feat_num[QED_RDMA_CNQ] =
min_t(u32, RESC_NUM(p_hwfn, QED_SB) / num_features,
RESC_NUM(p_hwfn, QED_RDMA_CNQ_RAM));
}
-#endif
+
feat_num[QED_PF_L2_QUE] = min_t(u32, RESC_NUM(p_hwfn, QED_SB) /
num_features,
RESC_NUM(p_hwfn, QED_L2_QUEUE));
- DP_VERBOSE(p_hwfn, NETIF_MSG_PROBE,
- "#PF_L2_QUEUES=%d #SBS=%d num_features=%d\n",
- feat_num[QED_PF_L2_QUE], RESC_NUM(p_hwfn, QED_SB),
- num_features);
+
+ memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
+ qed_int_get_num_sbs(p_hwfn, &sb_cnt_info);
+ feat_num[QED_VF_L2_QUE] =
+ min_t(u32,
+ RESC_NUM(p_hwfn, QED_L2_QUEUE) -
+ FEAT_NUM(p_hwfn, QED_PF_L2_QUE), sb_cnt_info.sb_iov_cnt);
+
+ DP_VERBOSE(p_hwfn,
+ NETIF_MSG_PROBE,
+ "#PF_L2_QUEUES=%d VF_L2_QUEUES=%d #ROCE_CNQ=%d #SBS=%d num_features=%d\n",
+ (int)FEAT_NUM(p_hwfn, QED_PF_L2_QUE),
+ (int)FEAT_NUM(p_hwfn, QED_VF_L2_QUE),
+ (int)FEAT_NUM(p_hwfn, QED_RDMA_CNQ),
+ RESC_NUM(p_hwfn, QED_SB), num_features);
+}
+
+static enum resource_id_enum qed_hw_get_mfw_res_id(enum qed_resources res_id)
+{
+ enum resource_id_enum mfw_res_id = RESOURCE_NUM_INVALID;
+
+ switch (res_id) {
+ case QED_SB:
+ mfw_res_id = RESOURCE_NUM_SB_E;
+ break;
+ case QED_L2_QUEUE:
+ mfw_res_id = RESOURCE_NUM_L2_QUEUE_E;
+ break;
+ case QED_VPORT:
+ mfw_res_id = RESOURCE_NUM_VPORT_E;
+ break;
+ case QED_RSS_ENG:
+ mfw_res_id = RESOURCE_NUM_RSS_ENGINES_E;
+ break;
+ case QED_PQ:
+ mfw_res_id = RESOURCE_NUM_PQ_E;
+ break;
+ case QED_RL:
+ mfw_res_id = RESOURCE_NUM_RL_E;
+ break;
+ case QED_MAC:
+ case QED_VLAN:
+ /* Each VFC resource can accommodate both a MAC and a VLAN */
+ mfw_res_id = RESOURCE_VFC_FILTER_E;
+ break;
+ case QED_ILT:
+ mfw_res_id = RESOURCE_ILT_E;
+ break;
+ case QED_LL2_QUEUE:
+ mfw_res_id = RESOURCE_LL2_QUEUE_E;
+ break;
+ case QED_RDMA_CNQ_RAM:
+ case QED_CMDQS_CQS:
+ /* CNQ/CMDQS are the same resource */
+ mfw_res_id = RESOURCE_CQS_E;
+ break;
+ case QED_RDMA_STATS_QUEUE:
+ mfw_res_id = RESOURCE_RDMA_STATS_QUEUE_E;
+ break;
+ default:
+ break;
+ }
+
+ return mfw_res_id;
+}
+
+static u32 qed_hw_get_dflt_resc_num(struct qed_hwfn *p_hwfn,
+ enum qed_resources res_id)
+{
+ u8 num_funcs = p_hwfn->num_funcs_on_engine;
+ struct qed_sb_cnt_info sb_cnt_info;
+ u32 dflt_resc_num = 0;
+
+ switch (res_id) {
+ case QED_SB:
+ memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
+ qed_int_get_num_sbs(p_hwfn, &sb_cnt_info);
+ dflt_resc_num = sb_cnt_info.sb_cnt;
+ break;
+ case QED_L2_QUEUE:
+ dflt_resc_num = MAX_NUM_L2_QUEUES_BB / num_funcs;
+ break;
+ case QED_VPORT:
+ dflt_resc_num = MAX_NUM_VPORTS_BB / num_funcs;
+ break;
+ case QED_RSS_ENG:
+ dflt_resc_num = ETH_RSS_ENGINE_NUM_BB / num_funcs;
+ break;
+ case QED_PQ:
+ /* The granularity of the PQs is 8 */
+ dflt_resc_num = MAX_QM_TX_QUEUES_BB / num_funcs;
+ dflt_resc_num &= ~0x7;
+ break;
+ case QED_RL:
+ dflt_resc_num = MAX_QM_GLOBAL_RLS / num_funcs;
+ break;
+ case QED_MAC:
+ case QED_VLAN:
+ /* Each VFC resource can accommodate both a MAC and a VLAN */
+ dflt_resc_num = ETH_NUM_MAC_FILTERS / num_funcs;
+ break;
+ case QED_ILT:
+ dflt_resc_num = PXP_NUM_ILT_RECORDS_BB / num_funcs;
+ break;
+ case QED_LL2_QUEUE:
+ dflt_resc_num = MAX_NUM_LL2_RX_QUEUES / num_funcs;
+ break;
+ case QED_RDMA_CNQ_RAM:
+ case QED_CMDQS_CQS:
+ /* CNQ/CMDQS are the same resource */
+ dflt_resc_num = NUM_OF_CMDQS_CQS / num_funcs;
+ break;
+ case QED_RDMA_STATS_QUEUE:
+ dflt_resc_num = RDMA_NUM_STATISTIC_COUNTERS_BB / num_funcs;
+ break;
+ default:
+ break;
+ }
+
+ return dflt_resc_num;
+}
+
+static const char *qed_hw_get_resc_name(enum qed_resources res_id)
+{
+ switch (res_id) {
+ case QED_SB:
+ return "SB";
+ case QED_L2_QUEUE:
+ return "L2_QUEUE";
+ case QED_VPORT:
+ return "VPORT";
+ case QED_RSS_ENG:
+ return "RSS_ENG";
+ case QED_PQ:
+ return "PQ";
+ case QED_RL:
+ return "RL";
+ case QED_MAC:
+ return "MAC";
+ case QED_VLAN:
+ return "VLAN";
+ case QED_RDMA_CNQ_RAM:
+ return "RDMA_CNQ_RAM";
+ case QED_ILT:
+ return "ILT";
+ case QED_LL2_QUEUE:
+ return "LL2_QUEUE";
+ case QED_CMDQS_CQS:
+ return "CMDQS_CQS";
+ case QED_RDMA_STATS_QUEUE:
+ return "RDMA_STATS_QUEUE";
+ default:
+ return "UNKNOWN_RESOURCE";
+ }
+}
+
+static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn,
+ enum qed_resources res_id)
+{
+ u32 dflt_resc_num = 0, dflt_resc_start = 0, mcp_resp, mcp_param;
+ u32 *p_resc_num, *p_resc_start;
+ struct resource_info resc_info;
+ int rc;
+
+ p_resc_num = &RESC_NUM(p_hwfn, res_id);
+ p_resc_start = &RESC_START(p_hwfn, res_id);
+
+ /* Default values assumes that each function received equal share */
+ dflt_resc_num = qed_hw_get_dflt_resc_num(p_hwfn, res_id);
+ if (!dflt_resc_num) {
+ DP_ERR(p_hwfn,
+ "Failed to get default amount for resource %d [%s]\n",
+ res_id, qed_hw_get_resc_name(res_id));
+ return -EINVAL;
+ }
+ dflt_resc_start = dflt_resc_num * p_hwfn->enabled_func_idx;
+
+ memset(&resc_info, 0, sizeof(resc_info));
+ resc_info.res_id = qed_hw_get_mfw_res_id(res_id);
+ if (resc_info.res_id == RESOURCE_NUM_INVALID) {
+ DP_ERR(p_hwfn,
+ "Failed to match resource %d [%s] with the MFW resources\n",
+ res_id, qed_hw_get_resc_name(res_id));
+ return -EINVAL;
+ }
+
+ rc = qed_mcp_get_resc_info(p_hwfn, p_hwfn->p_main_ptt, &resc_info,
+ &mcp_resp, &mcp_param);
+ if (rc) {
+ DP_NOTICE(p_hwfn,
+ "MFW response failure for an allocation request for resource %d [%s]\n",
+ res_id, qed_hw_get_resc_name(res_id));
+ return rc;
+ }
+
+ /* Default driver values are applied in the following cases:
+ * - The resource allocation MB command is not supported by the MFW
+ * - There is an internal error in the MFW while processing the request
+ * - The resource ID is unknown to the MFW
+ */
+ if (mcp_resp != FW_MSG_CODE_RESOURCE_ALLOC_OK &&
+ mcp_resp != FW_MSG_CODE_RESOURCE_ALLOC_DEPRECATED) {
+ DP_NOTICE(p_hwfn,
+ "Resource %d [%s]: No allocation info was received [mcp_resp 0x%x]. Applying default values [num %d, start %d].\n",
+ res_id,
+ qed_hw_get_resc_name(res_id),
+ mcp_resp, dflt_resc_num, dflt_resc_start);
+ *p_resc_num = dflt_resc_num;
+ *p_resc_start = dflt_resc_start;
+ goto out;
+ }
+
+ /* Special handling for status blocks; Would be revised in future */
+ if (res_id == QED_SB) {
+ resc_info.size -= 1;
+ resc_info.offset -= p_hwfn->enabled_func_idx;
+ }
+
+ *p_resc_num = resc_info.size;
+ *p_resc_start = resc_info.offset;
+
+out:
+ /* PQs have to divide by 8 [that's the HW granularity].
+ * Reduce number so it would fit.
+ */
+ if ((res_id == QED_PQ) && ((*p_resc_num % 8) || (*p_resc_start % 8))) {
+ DP_INFO(p_hwfn,
+ "PQs need to align by 8; Number %08x --> %08x, Start %08x --> %08x\n",
+ *p_resc_num,
+ (*p_resc_num) & ~0x7,
+ *p_resc_start, (*p_resc_start) & ~0x7);
+ *p_resc_num &= ~0x7;
+ *p_resc_start &= ~0x7;
+ }
+
+ return 0;
}
static int qed_hw_get_resc(struct qed_hwfn *p_hwfn)
{
- u8 enabled_func_idx = p_hwfn->enabled_func_idx;
- u32 *resc_start = p_hwfn->hw_info.resc_start;
- u8 num_funcs = p_hwfn->num_funcs_on_engine;
- u32 *resc_num = p_hwfn->hw_info.resc_num;
- struct qed_sb_cnt_info sb_cnt_info;
- int i, max_vf_vlan_filters;
+ u8 res_id;
+ int rc;
- memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
-
-#ifdef CONFIG_QED_SRIOV
- max_vf_vlan_filters = QED_ETH_MAX_VF_NUM_VLAN_FILTERS;
-#else
- max_vf_vlan_filters = 0;
-#endif
-
- qed_int_get_num_sbs(p_hwfn, &sb_cnt_info);
-
- resc_num[QED_SB] = min_t(u32,
- (MAX_SB_PER_PATH_BB / num_funcs),
- sb_cnt_info.sb_cnt);
- resc_num[QED_L2_QUEUE] = MAX_NUM_L2_QUEUES_BB / num_funcs;
- resc_num[QED_VPORT] = MAX_NUM_VPORTS_BB / num_funcs;
- resc_num[QED_RSS_ENG] = ETH_RSS_ENGINE_NUM_BB / num_funcs;
- resc_num[QED_PQ] = MAX_QM_TX_QUEUES_BB / num_funcs;
- resc_num[QED_RL] = min_t(u32, 64, resc_num[QED_VPORT]);
- resc_num[QED_MAC] = ETH_NUM_MAC_FILTERS / num_funcs;
- resc_num[QED_VLAN] = (ETH_NUM_VLAN_FILTERS - 1 /*For vlan0*/) /
- num_funcs;
- resc_num[QED_ILT] = PXP_NUM_ILT_RECORDS_BB / num_funcs;
- resc_num[QED_LL2_QUEUE] = MAX_NUM_LL2_RX_QUEUES / num_funcs;
- resc_num[QED_RDMA_CNQ_RAM] = NUM_OF_CMDQS_CQS / num_funcs;
- resc_num[QED_RDMA_STATS_QUEUE] = RDMA_NUM_STATISTIC_COUNTERS_BB /
- num_funcs;
-
- for (i = 0; i < QED_MAX_RESC; i++)
- resc_start[i] = resc_num[i] * enabled_func_idx;
+ for (res_id = 0; res_id < QED_MAX_RESC; res_id++) {
+ rc = qed_hw_set_resc_info(p_hwfn, res_id);
+ if (rc)
+ return rc;
+ }
/* Sanity for ILT */
- if (RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_BB) {
+ if ((RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_BB)) {
DP_NOTICE(p_hwfn, "Can't assign ILT pages [%08x,...,%08x]\n",
RESC_START(p_hwfn, QED_ILT),
RESC_END(p_hwfn, QED_ILT) - 1);
@@ -1494,34 +1755,12 @@ static int qed_hw_get_resc(struct qed_hwfn *p_hwfn)
qed_hw_set_feat(p_hwfn);
DP_VERBOSE(p_hwfn, NETIF_MSG_PROBE,
- "The numbers for each resource are:\n"
- "SB = %d start = %d\n"
- "L2_QUEUE = %d start = %d\n"
- "VPORT = %d start = %d\n"
- "PQ = %d start = %d\n"
- "RL = %d start = %d\n"
- "MAC = %d start = %d\n"
- "VLAN = %d start = %d\n"
- "ILT = %d start = %d\n"
- "LL2_QUEUE = %d start = %d\n",
- p_hwfn->hw_info.resc_num[QED_SB],
- p_hwfn->hw_info.resc_start[QED_SB],
- p_hwfn->hw_info.resc_num[QED_L2_QUEUE],
- p_hwfn->hw_info.resc_start[QED_L2_QUEUE],
- p_hwfn->hw_info.resc_num[QED_VPORT],
- p_hwfn->hw_info.resc_start[QED_VPORT],
- p_hwfn->hw_info.resc_num[QED_PQ],
- p_hwfn->hw_info.resc_start[QED_PQ],
- p_hwfn->hw_info.resc_num[QED_RL],
- p_hwfn->hw_info.resc_start[QED_RL],
- p_hwfn->hw_info.resc_num[QED_MAC],
- p_hwfn->hw_info.resc_start[QED_MAC],
- p_hwfn->hw_info.resc_num[QED_VLAN],
- p_hwfn->hw_info.resc_start[QED_VLAN],
- p_hwfn->hw_info.resc_num[QED_ILT],
- p_hwfn->hw_info.resc_start[QED_ILT],
- RESC_NUM(p_hwfn, QED_LL2_QUEUE),
- RESC_START(p_hwfn, QED_LL2_QUEUE));
+ "The numbers for each resource are:\n");
+ for (res_id = 0; res_id < QED_MAX_RESC; res_id++)
+ DP_VERBOSE(p_hwfn, NETIF_MSG_PROBE, "%s = %d start = %d\n",
+ qed_hw_get_resc_name(res_id),
+ RESC_NUM(p_hwfn, res_id),
+ RESC_START(p_hwfn, res_id));
return 0;
}
@@ -1800,6 +2039,9 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn,
qed_get_num_funcs(p_hwfn, p_ptt);
+ if (qed_mcp_is_init(p_hwfn))
+ p_hwfn->hw_info.mtu = p_hwfn->mcp_info->func_info.mtu;
+
return qed_hw_get_resc(p_hwfn);
}
@@ -1974,8 +2216,13 @@ int qed_hw_prepare(struct qed_dev *cdev,
void qed_hw_remove(struct qed_dev *cdev)
{
+ struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
int i;
+ if (IS_PF(cdev))
+ qed_mcp_ov_update_driver_state(p_hwfn, p_hwfn->p_main_ptt,
+ QED_OV_DRIVER_STATE_NOT_LOADED);
+
for_each_hwfn(cdev, i) {
struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 72eee29..785ab03 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -727,9 +727,6 @@ struct core_tx_bd_flags {
#define CORE_TX_BD_FLAGS_L4_PROTOCOL_SHIFT 6
#define CORE_TX_BD_FLAGS_L4_PSEUDO_CSUM_MODE_MASK 0x1
#define CORE_TX_BD_FLAGS_L4_PSEUDO_CSUM_MODE_SHIFT 7
-#define CORE_TX_BD_FLAGS_ROCE_FLAV_MASK 0x1
-#define CORE_TX_BD_FLAGS_ROCE_FLAV_SHIFT 12
-
};
struct core_tx_bd {
@@ -8529,6 +8526,41 @@ struct mdump_config_stc {
u32 valid_logs;
};
+enum resource_id_enum {
+ RESOURCE_NUM_SB_E = 0,
+ RESOURCE_NUM_L2_QUEUE_E = 1,
+ RESOURCE_NUM_VPORT_E = 2,
+ RESOURCE_NUM_VMQ_E = 3,
+ RESOURCE_FACTOR_NUM_RSS_PF_E = 4,
+ RESOURCE_FACTOR_RSS_PER_VF_E = 5,
+ RESOURCE_NUM_RL_E = 6,
+ RESOURCE_NUM_PQ_E = 7,
+ RESOURCE_NUM_VF_E = 8,
+ RESOURCE_VFC_FILTER_E = 9,
+ RESOURCE_ILT_E = 10,
+ RESOURCE_CQS_E = 11,
+ RESOURCE_GFT_PROFILES_E = 12,
+ RESOURCE_NUM_TC_E = 13,
+ RESOURCE_NUM_RSS_ENGINES_E = 14,
+ RESOURCE_LL2_QUEUE_E = 15,
+ RESOURCE_RDMA_STATS_QUEUE_E = 16,
+ RESOURCE_MAX_NUM,
+ RESOURCE_NUM_INVALID = 0xFFFFFFFF
+};
+
+/* Resource ID is to be filled by the driver in the MB request
+ * Size, offset & flags to be filled by the MFW in the MB response
+ */
+struct resource_info {
+ enum resource_id_enum res_id;
+ u32 size; /* number of allocated resources */
+ u32 offset; /* Offset of the 1st resource */
+ u32 vf_size;
+ u32 vf_offset;
+ u32 flags;
+#define RESOURCE_ELEMENT_STRICT (1 << 0)
+};
+
union drv_union_data {
u32 ver_str[MCP_DRV_VER_STR_SIZE_DWORD];
struct mcp_mac wol_mac;
@@ -8546,9 +8578,9 @@ union drv_union_data {
struct drv_version_stc drv_version;
struct lan_stats_stc lan_stats;
- u64 reserved_stats[11];
struct ocbb_data_stc ocbb_info;
struct temperature_status_stc temp_info;
+ struct resource_info resource;
struct bist_nvm_image_att nvm_image_att;
struct mdump_config_stc mdump_config;
};
@@ -8564,9 +8596,19 @@ struct public_drv_mb {
#define DRV_MSG_CODE_INIT_PHY 0x22000000
#define DRV_MSG_CODE_LINK_RESET 0x23000000
#define DRV_MSG_CODE_SET_DCBX 0x25000000
+#define DRV_MSG_CODE_OV_UPDATE_CURR_CFG 0x26000000
+#define DRV_MSG_CODE_OV_UPDATE_BUS_NUM 0x27000000
+#define DRV_MSG_CODE_OV_UPDATE_BOOT_PROGRESS 0x28000000
+#define DRV_MSG_CODE_OV_UPDATE_STORM_FW_VER 0x29000000
+#define DRV_MSG_CODE_OV_UPDATE_DRIVER_STATE 0x31000000
+#define DRV_MSG_CODE_BW_UPDATE_ACK 0x32000000
+#define DRV_MSG_CODE_OV_UPDATE_MTU 0x33000000
+#define DRV_MSG_CODE_OV_UPDATE_WOL 0x38000000
+#define DRV_MSG_CODE_OV_UPDATE_ESWITCH_MODE 0x39000000
#define DRV_MSG_CODE_BW_UPDATE_ACK 0x32000000
#define DRV_MSG_CODE_NIG_DRAIN 0x30000000
+#define DRV_MSG_GET_RESOURCE_ALLOC_MSG 0x34000000
#define DRV_MSG_CODE_VF_DISABLED_DONE 0xc0000000
#define DRV_MSG_CODE_CFG_VF_MSIX 0xc0010000
#define DRV_MSG_CODE_NVM_GET_FILE_ATT 0x00030000
@@ -8574,6 +8616,13 @@ struct public_drv_mb {
#define DRV_MSG_CODE_MCP_RESET 0x00090000
#define DRV_MSG_CODE_SET_VERSION 0x000f0000
#define DRV_MSG_CODE_MCP_HALT 0x00100000
+#define DRV_MSG_CODE_SET_VMAC 0x00110000
+#define DRV_MSG_CODE_GET_VMAC 0x00120000
+#define DRV_MSG_CODE_VMAC_TYPE_SHIFT 4
+#define DRV_MSG_CODE_VMAC_TYPE_MASK 0x30
+#define DRV_MSG_CODE_VMAC_TYPE_MAC 1
+#define DRV_MSG_CODE_VMAC_TYPE_WWNN 2
+#define DRV_MSG_CODE_VMAC_TYPE_WWPN 3
#define DRV_MSG_CODE_GET_STATS 0x00130000
#define DRV_MSG_CODE_STATS_TYPE_LAN 1
@@ -8585,11 +8634,16 @@ struct public_drv_mb {
#define DRV_MSG_CODE_BIST_TEST 0x001e0000
#define DRV_MSG_CODE_SET_LED_MODE 0x00200000
+#define DRV_MSG_CODE_GET_PF_RDMA_PROTOCOL 0x002b0000
+#define DRV_MSG_CODE_OS_WOL 0x002e0000
#define DRV_MSG_SEQ_NUMBER_MASK 0x0000ffff
u32 drv_mb_param;
-#define DRV_MB_PARAM_UNLOAD_WOL_MCP 0x00000001
+#define DRV_MB_PARAM_UNLOAD_WOL_UNKNOWN 0x00000000
+#define DRV_MB_PARAM_UNLOAD_WOL_MCP 0x00000001
+#define DRV_MB_PARAM_UNLOAD_WOL_DISABLED 0x00000002
+#define DRV_MB_PARAM_UNLOAD_WOL_ENABLED 0x00000003
#define DRV_MB_PARAM_DCBX_NOTIFY_MASK 0x000000FF
#define DRV_MB_PARAM_DCBX_NOTIFY_SHIFT 3
@@ -8602,13 +8656,59 @@ struct public_drv_mb {
#define DRV_MB_PARAM_LLDP_SEND_MASK 0x00000001
#define DRV_MB_PARAM_LLDP_SEND_SHIFT 0
+#define DRV_MB_PARAM_OV_CURR_CFG_SHIFT 0
+#define DRV_MB_PARAM_OV_CURR_CFG_MASK 0x0000000F
+#define DRV_MB_PARAM_OV_CURR_CFG_NONE 0
+#define DRV_MB_PARAM_OV_CURR_CFG_OS 1
+#define DRV_MB_PARAM_OV_CURR_CFG_VENDOR_SPEC 2
+#define DRV_MB_PARAM_OV_CURR_CFG_OTHER 3
+
+#define DRV_MB_PARAM_OV_STORM_FW_VER_SHIFT 0
+#define DRV_MB_PARAM_OV_STORM_FW_VER_MASK 0xFFFFFFFF
+#define DRV_MB_PARAM_OV_STORM_FW_VER_MAJOR_MASK 0xFF000000
+#define DRV_MB_PARAM_OV_STORM_FW_VER_MINOR_MASK 0x00FF0000
+#define DRV_MB_PARAM_OV_STORM_FW_VER_BUILD_MASK 0x0000FF00
+#define DRV_MB_PARAM_OV_STORM_FW_VER_DROP_MASK 0x000000FF
+
+#define DRV_MSG_CODE_OV_UPDATE_DRIVER_STATE_SHIFT 0
+#define DRV_MSG_CODE_OV_UPDATE_DRIVER_STATE_MASK 0xF
+#define DRV_MSG_CODE_OV_UPDATE_DRIVER_STATE_UNKNOWN 0x1
+#define DRV_MSG_CODE_OV_UPDATE_DRIVER_STATE_NOT_LOADED 0x2
+#define DRV_MSG_CODE_OV_UPDATE_DRIVER_STATE_LOADING 0x3
+#define DRV_MSG_CODE_OV_UPDATE_DRIVER_STATE_DISABLED 0x4
+#define DRV_MSG_CODE_OV_UPDATE_DRIVER_STATE_ACTIVE 0x5
+
+#define DRV_MB_PARAM_OV_MTU_SIZE_SHIFT 0
+#define DRV_MB_PARAM_OV_MTU_SIZE_MASK 0xFFFFFFFF
+
+#define DRV_MB_PARAM_WOL_MASK (DRV_MB_PARAM_WOL_DEFAULT | \
+ DRV_MB_PARAM_WOL_DISABLED | \
+ DRV_MB_PARAM_WOL_ENABLED)
+#define DRV_MB_PARAM_WOL_DEFAULT DRV_MB_PARAM_UNLOAD_WOL_MCP
+#define DRV_MB_PARAM_WOL_DISABLED DRV_MB_PARAM_UNLOAD_WOL_DISABLED
+#define DRV_MB_PARAM_WOL_ENABLED DRV_MB_PARAM_UNLOAD_WOL_ENABLED
+
+#define DRV_MB_PARAM_ESWITCH_MODE_MASK (DRV_MB_PARAM_ESWITCH_MODE_NONE | \
+ DRV_MB_PARAM_ESWITCH_MODE_VEB | \
+ DRV_MB_PARAM_ESWITCH_MODE_VEPA)
+#define DRV_MB_PARAM_ESWITCH_MODE_NONE 0x0
+#define DRV_MB_PARAM_ESWITCH_MODE_VEB 0x1
+#define DRV_MB_PARAM_ESWITCH_MODE_VEPA 0x2
#define DRV_MB_PARAM_SET_LED_MODE_OPER 0x0
#define DRV_MB_PARAM_SET_LED_MODE_ON 0x1
#define DRV_MB_PARAM_SET_LED_MODE_OFF 0x2
+ /* Resource Allocation params - Driver version support */
+#define DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_MASK 0xFFFF0000
+#define DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT 16
+#define DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR_MASK 0x0000FFFF
+#define DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR_SHIFT 0
+
#define DRV_MB_PARAM_BIST_REGISTER_TEST 1
#define DRV_MB_PARAM_BIST_CLOCK_TEST 2
+#define DRV_MB_PARAM_BIST_NVM_TEST_NUM_IMAGES 3
+#define DRV_MB_PARAM_BIST_NVM_TEST_IMAGE_BY_INDEX 4
#define DRV_MB_PARAM_BIST_RC_UNKNOWN 0
#define DRV_MB_PARAM_BIST_RC_PASSED 1
@@ -8617,6 +8717,8 @@ struct public_drv_mb {
#define DRV_MB_PARAM_BIST_TEST_INDEX_SHIFT 0
#define DRV_MB_PARAM_BIST_TEST_INDEX_MASK 0x000000FF
+#define DRV_MB_PARAM_BIST_TEST_IMAGE_INDEX_SHIFT 8
+#define DRV_MB_PARAM_BIST_TEST_IMAGE_INDEX_MASK 0x0000FF00
u32 fw_mb_header;
#define FW_MSG_CODE_MASK 0xffff0000
@@ -8631,15 +8733,27 @@ struct public_drv_mb {
#define FW_MSG_CODE_DRV_UNLOAD_PORT 0x20120000
#define FW_MSG_CODE_DRV_UNLOAD_FUNCTION 0x20130000
#define FW_MSG_CODE_DRV_UNLOAD_DONE 0x21100000
+#define FW_MSG_CODE_RESOURCE_ALLOC_OK 0x34000000
+#define FW_MSG_CODE_RESOURCE_ALLOC_UNKNOWN 0x35000000
+#define FW_MSG_CODE_RESOURCE_ALLOC_DEPRECATED 0x36000000
#define FW_MSG_CODE_DRV_CFG_VF_MSIX_DONE 0xb0010000
#define FW_MSG_CODE_NVM_OK 0x00010000
#define FW_MSG_CODE_OK 0x00160000
+#define FW_MSG_CODE_OS_WOL_SUPPORTED 0x00800000
+#define FW_MSG_CODE_OS_WOL_NOT_SUPPORTED 0x00810000
+
#define FW_MSG_SEQ_NUMBER_MASK 0x0000ffff
u32 fw_mb_param;
+ /* get pf rdma protocol command responce */
+#define FW_MB_PARAM_GET_PF_RDMA_NONE 0x0
+#define FW_MB_PARAM_GET_PF_RDMA_ROCE 0x1
+#define FW_MB_PARAM_GET_PF_RDMA_IWARP 0x2
+#define FW_MB_PARAM_GET_PF_RDMA_BOTH 0x3
+
u32 drv_pulse_mb;
#define DRV_PULSE_SEQ_MASK 0x00007fff
#define DRV_PULSE_SYSTEM_TIME_MASK 0xffff0000
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index 2adedc6..bb74e1c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -3030,6 +3030,31 @@ int qed_int_igu_read_cam(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
}
}
}
+
+ /* There's a possibility the igu_sb_cnt_iov doesn't properly reflect
+ * the number of VF SBs [especially for first VF on engine, as we can't
+ * diffrentiate between empty entries and its entries].
+ * Since we don't really support more SBs than VFs today, prevent any
+ * such configuration by sanitizing the number of SBs to equal the
+ * number of VFs.
+ */
+ if (IS_PF_SRIOV(p_hwfn)) {
+ u16 total_vfs = p_hwfn->cdev->p_iov_info->total_vfs;
+
+ if (total_vfs < p_igu_info->free_blks) {
+ DP_VERBOSE(p_hwfn,
+ (NETIF_MSG_INTR | QED_MSG_IOV),
+ "Limiting number of SBs for IOV - %04x --> %04x\n",
+ p_igu_info->free_blks,
+ p_hwfn->cdev->p_iov_info->total_vfs);
+ p_igu_info->free_blks = total_vfs;
+ } else if (total_vfs > p_igu_info->free_blks) {
+ DP_NOTICE(p_hwfn,
+ "IGU has only %04x SBs for VFs while the device has %04x VFs\n",
+ p_igu_info->free_blks, total_vfs);
+ return -EINVAL;
+ }
+ }
p_igu_info->igu_sb_cnt_iov = p_igu_info->free_blks;
DP_VERBOSE(
@@ -3163,7 +3188,12 @@ u16 qed_int_queue_id_from_sb_id(struct qed_hwfn *p_hwfn, u16 sb_id)
return sb_id - p_info->igu_base_sb;
} else if ((sb_id >= p_info->igu_base_sb_iov) &&
(sb_id < p_info->igu_base_sb_iov + p_info->igu_sb_cnt_iov)) {
- return sb_id - p_info->igu_base_sb_iov + p_info->igu_sb_cnt;
+ /* We want the first VF queue to be adjacent to the
+ * last PF queue. Since L2 queues can be partial to
+ * SBs, we'll use the feature instead.
+ */
+ return sb_id - p_info->igu_base_sb_iov +
+ FEAT_NUM(p_hwfn, QED_PF_L2_QUE);
} else {
DP_NOTICE(p_hwfn, "SB %d not in range for function\n", sb_id);
return 0;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 6b0e22d..900b253 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -1691,7 +1691,9 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev,
}
qed_vf_get_num_vlan_filters(&cdev->hwfns[0],
- &info->num_vlan_filters);
+ (u8 *)&info->num_vlan_filters);
+ qed_vf_get_num_mac_filters(&cdev->hwfns[0],
+ (u8 *)&info->num_mac_filters);
qed_vf_get_port_mac(&cdev->hwfns[0], info->port_mac);
info->is_legacy = !!cdev->hwfns[0].vf_iov_info->b_pre_fp_hsi;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 02a8be2..f95385c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -38,6 +38,7 @@
#include "qed_mcp.h"
#include "qed_reg_addr.h"
#include "qed_sp.h"
+#include "qed_roce.h"
#define QED_LL2_RX_REGISTERED(ll2) ((ll2)->rx_queue.b_cb_registred)
#define QED_LL2_TX_REGISTERED(ll2) ((ll2)->tx_queue.b_cb_registred)
@@ -140,11 +141,11 @@ static void qed_ll2_kill_buffers(struct qed_dev *cdev)
qed_ll2_dealloc_buffer(cdev, buffer);
}
-void qed_ll2b_complete_rx_packet(struct qed_hwfn *p_hwfn,
- u8 connection_handle,
- struct qed_ll2_rx_packet *p_pkt,
- struct core_rx_fast_path_cqe *p_cqe,
- bool b_last_packet)
+static void qed_ll2b_complete_rx_packet(struct qed_hwfn *p_hwfn,
+ u8 connection_handle,
+ struct qed_ll2_rx_packet *p_pkt,
+ struct core_rx_fast_path_cqe *p_cqe,
+ bool b_last_packet)
{
u16 packet_length = le16_to_cpu(p_cqe->packet_length);
struct qed_ll2_buffer *buffer = p_pkt->cookie;
@@ -515,7 +516,7 @@ static int qed_ll2_rxq_completion(struct qed_hwfn *p_hwfn, void *cookie)
return rc;
}
-void qed_ll2_rxq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
+static void qed_ll2_rxq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
{
struct qed_ll2_info *p_ll2_conn = NULL;
struct qed_ll2_rx_packet *p_pkt = NULL;
@@ -537,8 +538,7 @@ void qed_ll2_rxq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
if (!p_pkt)
break;
- list_del(&p_pkt->list_entry);
- list_add_tail(&p_pkt->list_entry, &p_rx->free_descq);
+ list_move_tail(&p_pkt->list_entry, &p_rx->free_descq);
rx_buf_addr = p_pkt->rx_buf_addr;
cookie = p_pkt->cookie;
@@ -992,9 +992,8 @@ static void qed_ll2_post_rx_buffer_notify_fw(struct qed_hwfn *p_hwfn,
p_posting_packet = list_first_entry(&p_rx->posting_descq,
struct qed_ll2_rx_packet,
list_entry);
- list_del(&p_posting_packet->list_entry);
- list_add_tail(&p_posting_packet->list_entry,
- &p_rx->active_descq);
+ list_move_tail(&p_posting_packet->list_entry,
+ &p_rx->active_descq);
b_notify_fw = true;
}
@@ -1120,12 +1119,10 @@ static void qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
start_bd->bd_flags.as_bitfield |= CORE_TX_BD_FLAGS_START_BD_MASK <<
CORE_TX_BD_FLAGS_START_BD_SHIFT;
SET_FIELD(start_bd->bitfield0, CORE_TX_BD_NBDS, num_of_bds);
+ SET_FIELD(start_bd->bitfield0, CORE_TX_BD_ROCE_FLAV, type);
DMA_REGPAIR_LE(start_bd->addr, first_frag);
start_bd->nbytes = cpu_to_le16(first_frag_len);
- SET_FIELD(start_bd->bd_flags.as_bitfield, CORE_TX_BD_FLAGS_ROCE_FLAV,
- type);
-
DP_VERBOSE(p_hwfn,
(NETIF_MSG_TX_QUEUED | QED_MSG_LL2),
"LL2 [q 0x%02x cid 0x%08x type 0x%08x] Tx Producer at [0x%04x] - set with a %04x bytes %02x BDs buffer at %08x:%08x\n",
@@ -1188,8 +1185,7 @@ static void qed_ll2_tx_packet_notify(struct qed_hwfn *p_hwfn,
if (!p_pkt)
break;
- list_del(&p_pkt->list_entry);
- list_add_tail(&p_pkt->list_entry, &p_tx->active_descq);
+ list_move_tail(&p_pkt->list_entry, &p_tx->active_descq);
}
SET_FIELD(db_msg.params, CORE_DB_DATA_DEST, DB_DEST_XCM);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
index 80a5dc2..4e3d62a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
@@ -293,24 +293,4 @@ void qed_ll2_setup(struct qed_hwfn *p_hwfn,
*/
void qed_ll2_free(struct qed_hwfn *p_hwfn,
struct qed_ll2_info *p_ll2_connections);
-void qed_ll2b_complete_rx_gsi_packet(struct qed_hwfn *p_hwfn,
- u8 connection_handle,
- void *cookie,
- dma_addr_t rx_buf_addr,
- u16 data_length,
- u8 data_length_error,
- u16 parse_flags,
- u16 vlan,
- u32 src_mac_addr_hi,
- u16 src_mac_addr_lo, bool b_last_packet);
-void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn,
- u8 connection_handle,
- void *cookie,
- dma_addr_t first_frag_addr,
- bool b_last_fragment, bool b_last_packet);
-void qed_ll2b_release_tx_gsi_packet(struct qed_hwfn *p_hwfn,
- u8 connection_handle,
- void *cookie,
- dma_addr_t first_frag_addr,
- bool b_last_fragment, bool b_last_packet);
#endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 4ee3151..aeb98d8 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -33,10 +33,8 @@
#include "qed_hw.h"
#include "qed_selftest.h"
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
#define QED_ROCE_QPS (8192)
#define QED_ROCE_DPIS (8)
-#endif
static char version[] =
"QLogic FastLinQ 4xxxx Core Module qed " DRV_MODULE_VERSION "\n";
@@ -223,6 +221,10 @@ int qed_fill_dev_info(struct qed_dev *cdev,
dev_info->fw_eng = FW_ENGINEERING_VERSION;
dev_info->mf_mode = cdev->mf_mode;
dev_info->tx_switching = true;
+
+ if (QED_LEADING_HWFN(cdev)->hw_info.b_wol_support ==
+ QED_WOL_SUPPORT_PME)
+ dev_info->wol_support = true;
} else {
qed_vf_get_fw_version(&cdev->hwfns[0], &dev_info->fw_major,
&dev_info->fw_minor, &dev_info->fw_rev,
@@ -245,6 +247,8 @@ int qed_fill_dev_info(struct qed_dev *cdev,
&dev_info->mfw_rev, NULL);
}
+ dev_info->mtu = QED_LEADING_HWFN(cdev)->hw_info.mtu;
+
return 0;
}
@@ -682,9 +686,7 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev,
enum qed_int_mode int_mode)
{
struct qed_sb_cnt_info sb_cnt_info;
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
- int num_l2_queues;
-#endif
+ int num_l2_queues = 0;
int rc;
int i;
@@ -715,8 +717,9 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev,
cdev->int_params.fp_msix_cnt = cdev->int_params.out.num_vectors -
cdev->num_hwfns;
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
- num_l2_queues = 0;
+ if (!IS_ENABLED(CONFIG_QED_RDMA))
+ return 0;
+
for_each_hwfn(cdev, i)
num_l2_queues += FEAT_NUM(&cdev->hwfns[i], QED_PF_L2_QUE);
@@ -738,7 +741,6 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev,
DP_VERBOSE(cdev, QED_MSG_RDMA, "roce_msix_cnt=%d roce_msix_base=%d\n",
cdev->int_params.rdma_msix_cnt,
cdev->int_params.rdma_msix_base);
-#endif
return 0;
}
@@ -843,13 +845,14 @@ static void qed_update_pf_params(struct qed_dev *cdev,
{
int i;
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
- params->rdma_pf_params.num_qps = QED_ROCE_QPS;
- params->rdma_pf_params.min_dpis = QED_ROCE_DPIS;
- /* divide by 3 the MRs to avoid MF ILT overflow */
- params->rdma_pf_params.num_mrs = RDMA_MAX_TIDS;
- params->rdma_pf_params.gl_pi = QED_ROCE_PROTOCOL_INDEX;
-#endif
+ if (IS_ENABLED(CONFIG_QED_RDMA)) {
+ params->rdma_pf_params.num_qps = QED_ROCE_QPS;
+ params->rdma_pf_params.min_dpis = QED_ROCE_DPIS;
+ /* divide by 3 the MRs to avoid MF ILT overflow */
+ params->rdma_pf_params.num_mrs = RDMA_MAX_TIDS;
+ params->rdma_pf_params.gl_pi = QED_ROCE_PROTOCOL_INDEX;
+ }
+
for (i = 0; i < cdev->num_hwfns; i++) {
struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
@@ -880,6 +883,7 @@ static int qed_slowpath_start(struct qed_dev *cdev,
}
}
+ cdev->rx_coalesce_usecs = QED_DEFAULT_RX_USECS;
rc = qed_nic_setup(cdev);
if (rc)
goto err;
@@ -1432,11 +1436,106 @@ static int qed_set_led(struct qed_dev *cdev, enum qed_led_mode mode)
return status;
}
-struct qed_selftest_ops qed_selftest_ops_pass = {
+static int qed_update_wol(struct qed_dev *cdev, bool enabled)
+{
+ struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+ struct qed_ptt *ptt;
+ int rc = 0;
+
+ if (IS_VF(cdev))
+ return 0;
+
+ ptt = qed_ptt_acquire(hwfn);
+ if (!ptt)
+ return -EAGAIN;
+
+ rc = qed_mcp_ov_update_wol(hwfn, ptt, enabled ? QED_OV_WOL_ENABLED
+ : QED_OV_WOL_DISABLED);
+ if (rc)
+ goto out;
+ rc = qed_mcp_ov_update_current_config(hwfn, ptt, QED_OV_CLIENT_DRV);
+
+out:
+ qed_ptt_release(hwfn, ptt);
+ return rc;
+}
+
+static int qed_update_drv_state(struct qed_dev *cdev, bool active)
+{
+ struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+ struct qed_ptt *ptt;
+ int status = 0;
+
+ if (IS_VF(cdev))
+ return 0;
+
+ ptt = qed_ptt_acquire(hwfn);
+ if (!ptt)
+ return -EAGAIN;
+
+ status = qed_mcp_ov_update_driver_state(hwfn, ptt, active ?
+ QED_OV_DRIVER_STATE_ACTIVE :
+ QED_OV_DRIVER_STATE_DISABLED);
+
+ qed_ptt_release(hwfn, ptt);
+
+ return status;
+}
+
+static int qed_update_mac(struct qed_dev *cdev, u8 *mac)
+{
+ struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+ struct qed_ptt *ptt;
+ int status = 0;
+
+ if (IS_VF(cdev))
+ return 0;
+
+ ptt = qed_ptt_acquire(hwfn);
+ if (!ptt)
+ return -EAGAIN;
+
+ status = qed_mcp_ov_update_mac(hwfn, ptt, mac);
+ if (status)
+ goto out;
+
+ status = qed_mcp_ov_update_current_config(hwfn, ptt, QED_OV_CLIENT_DRV);
+
+out:
+ qed_ptt_release(hwfn, ptt);
+ return status;
+}
+
+static int qed_update_mtu(struct qed_dev *cdev, u16 mtu)
+{
+ struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+ struct qed_ptt *ptt;
+ int status = 0;
+
+ if (IS_VF(cdev))
+ return 0;
+
+ ptt = qed_ptt_acquire(hwfn);
+ if (!ptt)
+ return -EAGAIN;
+
+ status = qed_mcp_ov_update_mtu(hwfn, ptt, mtu);
+ if (status)
+ goto out;
+
+ status = qed_mcp_ov_update_current_config(hwfn, ptt, QED_OV_CLIENT_DRV);
+
+out:
+ qed_ptt_release(hwfn, ptt);
+ return status;
+}
+
+static struct qed_selftest_ops qed_selftest_ops_pass = {
.selftest_memory = &qed_selftest_memory,
.selftest_interrupt = &qed_selftest_interrupt,
.selftest_register = &qed_selftest_register,
.selftest_clock = &qed_selftest_clock,
+ .selftest_nvram = &qed_selftest_nvram,
};
const struct qed_common_ops qed_common_ops_pass = {
@@ -1466,6 +1565,10 @@ const struct qed_common_ops qed_common_ops_pass = {
.get_coalesce = &qed_get_coalesce,
.set_coalesce = &qed_set_coalesce,
.set_led = &qed_set_led,
+ .update_drv_state = &qed_update_drv_state,
+ .update_mac = &qed_update_mac,
+ .update_mtu = &qed_update_mtu,
+ .update_wol = &qed_update_wol,
};
void qed_get_protocol_stats(struct qed_dev *cdev,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index bdc9ba9..6dd3ce4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -14,6 +14,7 @@
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/string.h>
+#include <linux/etherdevice.h>
#include "qed.h"
#include "qed_dcbx.h"
#include "qed_hsi.h"
@@ -329,6 +330,7 @@ static int qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn,
struct qed_mcp_mb_params *p_mb_params)
{
u32 union_data_addr;
+
int rc;
/* MCP not initialized */
@@ -374,11 +376,32 @@ int qed_mcp_cmd(struct qed_hwfn *p_hwfn,
u32 *o_mcp_param)
{
struct qed_mcp_mb_params mb_params;
+ union drv_union_data data_src;
int rc;
memset(&mb_params, 0, sizeof(mb_params));
+ memset(&data_src, 0, sizeof(data_src));
mb_params.cmd = cmd;
mb_params.param = param;
+
+ /* In case of UNLOAD_DONE, set the primary MAC */
+ if ((cmd == DRV_MSG_CODE_UNLOAD_DONE) &&
+ (p_hwfn->cdev->wol_config == QED_OV_WOL_ENABLED)) {
+ u8 *p_mac = p_hwfn->cdev->wol_mac;
+
+ data_src.wol_mac.mac_upper = p_mac[0] << 8 | p_mac[1];
+ data_src.wol_mac.mac_lower = p_mac[2] << 24 | p_mac[3] << 16 |
+ p_mac[4] << 8 | p_mac[5];
+
+ DP_VERBOSE(p_hwfn,
+ (QED_MSG_SP | NETIF_MSG_IFDOWN),
+ "Setting WoL MAC: %pM --> [%08x,%08x]\n",
+ p_mac, data_src.wol_mac.mac_upper,
+ data_src.wol_mac.mac_lower);
+
+ mb_params.p_data_src = &data_src;
+ }
+
rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
if (rc)
return rc;
@@ -1001,28 +1024,89 @@ int qed_mcp_get_media_type(struct qed_dev *cdev, u32 *p_media_type)
return 0;
}
+/* Old MFW has a global configuration for all PFs regarding RDMA support */
+static void
+qed_mcp_get_shmem_proto_legacy(struct qed_hwfn *p_hwfn,
+ enum qed_pci_personality *p_proto)
+{
+ /* There wasn't ever a legacy MFW that published iwarp.
+ * So at this point, this is either plain l2 or RoCE.
+ */
+ if (test_bit(QED_DEV_CAP_ROCE, &p_hwfn->hw_info.device_capabilities))
+ *p_proto = QED_PCI_ETH_ROCE;
+ else
+ *p_proto = QED_PCI_ETH;
+
+ DP_VERBOSE(p_hwfn, NETIF_MSG_IFUP,
+ "According to Legacy capabilities, L2 personality is %08x\n",
+ (u32) *p_proto);
+}
+
+static int
+qed_mcp_get_shmem_proto_mfw(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ enum qed_pci_personality *p_proto)
+{
+ u32 resp = 0, param = 0;
+ int rc;
+
+ rc = qed_mcp_cmd(p_hwfn, p_ptt,
+ DRV_MSG_CODE_GET_PF_RDMA_PROTOCOL, 0, &resp, ¶m);
+ if (rc)
+ return rc;
+ if (resp != FW_MSG_CODE_OK) {
+ DP_VERBOSE(p_hwfn, NETIF_MSG_IFUP,
+ "MFW lacks support for command; Returns %08x\n",
+ resp);
+ return -EINVAL;
+ }
+
+ switch (param) {
+ case FW_MB_PARAM_GET_PF_RDMA_NONE:
+ *p_proto = QED_PCI_ETH;
+ break;
+ case FW_MB_PARAM_GET_PF_RDMA_ROCE:
+ *p_proto = QED_PCI_ETH_ROCE;
+ break;
+ case FW_MB_PARAM_GET_PF_RDMA_BOTH:
+ DP_NOTICE(p_hwfn,
+ "Current day drivers don't support RoCE & iWARP. Default to RoCE-only\n");
+ *p_proto = QED_PCI_ETH_ROCE;
+ break;
+ case FW_MB_PARAM_GET_PF_RDMA_IWARP:
+ default:
+ DP_NOTICE(p_hwfn,
+ "MFW answers GET_PF_RDMA_PROTOCOL but param is %08x\n",
+ param);
+ return -EINVAL;
+ }
+
+ DP_VERBOSE(p_hwfn,
+ NETIF_MSG_IFUP,
+ "According to capabilities, L2 personality is %08x [resp %08x param %08x]\n",
+ (u32) *p_proto, resp, param);
+ return 0;
+}
+
static int
qed_mcp_get_shmem_proto(struct qed_hwfn *p_hwfn,
struct public_func *p_info,
+ struct qed_ptt *p_ptt,
enum qed_pci_personality *p_proto)
{
int rc = 0;
switch (p_info->config & FUNC_MF_CFG_PROTOCOL_MASK) {
case FUNC_MF_CFG_PROTOCOL_ETHERNET:
- if (test_bit(QED_DEV_CAP_ROCE,
- &p_hwfn->hw_info.device_capabilities))
- *p_proto = QED_PCI_ETH_ROCE;
- else
- *p_proto = QED_PCI_ETH;
+ if (qed_mcp_get_shmem_proto_mfw(p_hwfn, p_ptt, p_proto))
+ qed_mcp_get_shmem_proto_legacy(p_hwfn, p_proto);
break;
case FUNC_MF_CFG_PROTOCOL_ISCSI:
*p_proto = QED_PCI_ISCSI;
break;
case FUNC_MF_CFG_PROTOCOL_ROCE:
DP_NOTICE(p_hwfn, "RoCE personality is not a valid value!\n");
- rc = -EINVAL;
- break;
+ /* Fallthrough */
default:
rc = -EINVAL;
}
@@ -1042,7 +1126,8 @@ int qed_mcp_fill_shmem_func_info(struct qed_hwfn *p_hwfn,
info->pause_on_host = (shmem_info.config &
FUNC_MF_CFG_PAUSE_ON_HOST_RING) ? 1 : 0;
- if (qed_mcp_get_shmem_proto(p_hwfn, &shmem_info, &info->protocol)) {
+ if (qed_mcp_get_shmem_proto(p_hwfn, &shmem_info, p_ptt,
+ &info->protocol)) {
DP_ERR(p_hwfn, "Unknown personality %08x\n",
(u32)(shmem_info.config & FUNC_MF_CFG_PROTOCOL_MASK));
return -EINVAL;
@@ -1057,6 +1142,9 @@ int qed_mcp_fill_shmem_func_info(struct qed_hwfn *p_hwfn,
info->mac[3] = (u8)(shmem_info.mac_lower >> 16);
info->mac[4] = (u8)(shmem_info.mac_lower >> 8);
info->mac[5] = (u8)(shmem_info.mac_lower);
+
+ /* Store primary MAC for later possible WoL */
+ memcpy(&p_hwfn->cdev->wol_mac, info->mac, ETH_ALEN);
} else {
DP_NOTICE(p_hwfn, "MAC is 0 in shmem\n");
}
@@ -1068,13 +1156,30 @@ int qed_mcp_fill_shmem_func_info(struct qed_hwfn *p_hwfn,
info->ovlan = (u16)(shmem_info.ovlan_stag & FUNC_MF_CFG_OV_STAG_MASK);
+ info->mtu = (u16)shmem_info.mtu_size;
+
+ p_hwfn->hw_info.b_wol_support = QED_WOL_SUPPORT_NONE;
+ p_hwfn->cdev->wol_config = (u8)QED_OV_WOL_DEFAULT;
+ if (qed_mcp_is_init(p_hwfn)) {
+ u32 resp = 0, param = 0;
+ int rc;
+
+ rc = qed_mcp_cmd(p_hwfn, p_ptt,
+ DRV_MSG_CODE_OS_WOL, 0, &resp, ¶m);
+ if (rc)
+ return rc;
+ if (resp == FW_MSG_CODE_OS_WOL_SUPPORTED)
+ p_hwfn->hw_info.b_wol_support = QED_WOL_SUPPORT_PME;
+ }
+
DP_VERBOSE(p_hwfn, (QED_MSG_SP | NETIF_MSG_IFUP),
- "Read configuration from shmem: pause_on_host %02x protocol %02x BW [%02x - %02x] MAC %02x:%02x:%02x:%02x:%02x:%02x wwn port %llx node %llx ovlan %04x\n",
+ "Read configuration from shmem: pause_on_host %02x protocol %02x BW [%02x - %02x] MAC %02x:%02x:%02x:%02x:%02x:%02x wwn port %llx node %llx ovlan %04x wol %02x\n",
info->pause_on_host, info->protocol,
info->bandwidth_min, info->bandwidth_max,
info->mac[0], info->mac[1], info->mac[2],
info->mac[3], info->mac[4], info->mac[5],
- info->wwn_port, info->wwn_node, info->ovlan);
+ info->wwn_port, info->wwn_node,
+ info->ovlan, (u8)p_hwfn->hw_info.b_wol_support);
return 0;
}
@@ -1223,6 +1328,178 @@ int qed_mcp_resume(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
return (cpu_mode & MCP_REG_CPU_MODE_SOFT_HALT) ? -EAGAIN : 0;
}
+int qed_mcp_ov_update_current_config(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ enum qed_ov_client client)
+{
+ u32 resp = 0, param = 0;
+ u32 drv_mb_param;
+ int rc;
+
+ switch (client) {
+ case QED_OV_CLIENT_DRV:
+ drv_mb_param = DRV_MB_PARAM_OV_CURR_CFG_OS;
+ break;
+ case QED_OV_CLIENT_USER:
+ drv_mb_param = DRV_MB_PARAM_OV_CURR_CFG_OTHER;
+ break;
+ case QED_OV_CLIENT_VENDOR_SPEC:
+ drv_mb_param = DRV_MB_PARAM_OV_CURR_CFG_VENDOR_SPEC;
+ break;
+ default:
+ DP_NOTICE(p_hwfn, "Invalid client type %d\n", client);
+ return -EINVAL;
+ }
+
+ rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_OV_UPDATE_CURR_CFG,
+ drv_mb_param, &resp, ¶m);
+ if (rc)
+ DP_ERR(p_hwfn, "MCP response failure, aborting\n");
+
+ return rc;
+}
+
+int qed_mcp_ov_update_driver_state(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ enum qed_ov_driver_state drv_state)
+{
+ u32 resp = 0, param = 0;
+ u32 drv_mb_param;
+ int rc;
+
+ switch (drv_state) {
+ case QED_OV_DRIVER_STATE_NOT_LOADED:
+ drv_mb_param = DRV_MSG_CODE_OV_UPDATE_DRIVER_STATE_NOT_LOADED;
+ break;
+ case QED_OV_DRIVER_STATE_DISABLED:
+ drv_mb_param = DRV_MSG_CODE_OV_UPDATE_DRIVER_STATE_DISABLED;
+ break;
+ case QED_OV_DRIVER_STATE_ACTIVE:
+ drv_mb_param = DRV_MSG_CODE_OV_UPDATE_DRIVER_STATE_ACTIVE;
+ break;
+ default:
+ DP_NOTICE(p_hwfn, "Invalid driver state %d\n", drv_state);
+ return -EINVAL;
+ }
+
+ rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_OV_UPDATE_DRIVER_STATE,
+ drv_mb_param, &resp, ¶m);
+ if (rc)
+ DP_ERR(p_hwfn, "Failed to send driver state\n");
+
+ return rc;
+}
+
+int qed_mcp_ov_update_mtu(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt, u16 mtu)
+{
+ u32 resp = 0, param = 0;
+ u32 drv_mb_param;
+ int rc;
+
+ drv_mb_param = (u32)mtu << DRV_MB_PARAM_OV_MTU_SIZE_SHIFT;
+ rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_OV_UPDATE_MTU,
+ drv_mb_param, &resp, ¶m);
+ if (rc)
+ DP_ERR(p_hwfn, "Failed to send mtu value, rc = %d\n", rc);
+
+ return rc;
+}
+
+int qed_mcp_ov_update_mac(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt, u8 *mac)
+{
+ struct qed_mcp_mb_params mb_params;
+ union drv_union_data union_data;
+ int rc;
+
+ memset(&mb_params, 0, sizeof(mb_params));
+ mb_params.cmd = DRV_MSG_CODE_SET_VMAC;
+ mb_params.param = DRV_MSG_CODE_VMAC_TYPE_MAC <<
+ DRV_MSG_CODE_VMAC_TYPE_SHIFT;
+ mb_params.param |= MCP_PF_ID(p_hwfn);
+ ether_addr_copy(&union_data.raw_data[0], mac);
+ mb_params.p_data_src = &union_data;
+ rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
+ if (rc)
+ DP_ERR(p_hwfn, "Failed to send mac address, rc = %d\n", rc);
+
+ /* Store primary MAC for later possible WoL */
+ memcpy(p_hwfn->cdev->wol_mac, mac, ETH_ALEN);
+
+ return rc;
+}
+
+int qed_mcp_ov_update_wol(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt, enum qed_ov_wol wol)
+{
+ u32 resp = 0, param = 0;
+ u32 drv_mb_param;
+ int rc;
+
+ if (p_hwfn->hw_info.b_wol_support == QED_WOL_SUPPORT_NONE) {
+ DP_VERBOSE(p_hwfn, QED_MSG_SP,
+ "Can't change WoL configuration when WoL isn't supported\n");
+ return -EINVAL;
+ }
+
+ switch (wol) {
+ case QED_OV_WOL_DEFAULT:
+ drv_mb_param = DRV_MB_PARAM_WOL_DEFAULT;
+ break;
+ case QED_OV_WOL_DISABLED:
+ drv_mb_param = DRV_MB_PARAM_WOL_DISABLED;
+ break;
+ case QED_OV_WOL_ENABLED:
+ drv_mb_param = DRV_MB_PARAM_WOL_ENABLED;
+ break;
+ default:
+ DP_ERR(p_hwfn, "Invalid wol state %d\n", wol);
+ return -EINVAL;
+ }
+
+ rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_OV_UPDATE_WOL,
+ drv_mb_param, &resp, ¶m);
+ if (rc)
+ DP_ERR(p_hwfn, "Failed to send wol mode, rc = %d\n", rc);
+
+ /* Store the WoL update for a future unload */
+ p_hwfn->cdev->wol_config = (u8)wol;
+
+ return rc;
+}
+
+int qed_mcp_ov_update_eswitch(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ enum qed_ov_eswitch eswitch)
+{
+ u32 resp = 0, param = 0;
+ u32 drv_mb_param;
+ int rc;
+
+ switch (eswitch) {
+ case QED_OV_ESWITCH_NONE:
+ drv_mb_param = DRV_MB_PARAM_ESWITCH_MODE_NONE;
+ break;
+ case QED_OV_ESWITCH_VEB:
+ drv_mb_param = DRV_MB_PARAM_ESWITCH_MODE_VEB;
+ break;
+ case QED_OV_ESWITCH_VEPA:
+ drv_mb_param = DRV_MB_PARAM_ESWITCH_MODE_VEPA;
+ break;
+ default:
+ DP_ERR(p_hwfn, "Invalid eswitch mode %d\n", eswitch);
+ return -EINVAL;
+ }
+
+ rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_OV_UPDATE_ESWITCH_MODE,
+ drv_mb_param, &resp, ¶m);
+ if (rc)
+ DP_ERR(p_hwfn, "Failed to send eswitch mode, rc = %d\n", rc);
+
+ return rc;
+}
+
int qed_mcp_set_led(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt, enum qed_led_mode mode)
{
@@ -1271,6 +1548,52 @@ int qed_mcp_mask_parities(struct qed_hwfn *p_hwfn,
return rc;
}
+int qed_mcp_nvm_read(struct qed_dev *cdev, u32 addr, u8 *p_buf, u32 len)
+{
+ u32 bytes_left = len, offset = 0, bytes_to_copy, read_len = 0;
+ struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+ u32 resp = 0, resp_param = 0;
+ struct qed_ptt *p_ptt;
+ int rc = 0;
+
+ p_ptt = qed_ptt_acquire(p_hwfn);
+ if (!p_ptt)
+ return -EBUSY;
+
+ while (bytes_left > 0) {
+ bytes_to_copy = min_t(u32, bytes_left, MCP_DRV_NVM_BUF_LEN);
+
+ rc = qed_mcp_nvm_rd_cmd(p_hwfn, p_ptt,
+ DRV_MSG_CODE_NVM_READ_NVRAM,
+ addr + offset +
+ (bytes_to_copy <<
+ DRV_MB_PARAM_NVM_LEN_SHIFT),
+ &resp, &resp_param,
+ &read_len,
+ (u32 *)(p_buf + offset));
+
+ if (rc || (resp != FW_MSG_CODE_NVM_OK)) {
+ DP_NOTICE(cdev, "MCP command rc = %d\n", rc);
+ break;
+ }
+
+ /* This can be a lengthy process, and it's possible scheduler
+ * isn't preemptable. Sleep a bit to prevent CPU hogging.
+ */
+ if (bytes_left % 0x1000 <
+ (bytes_left - read_len) % 0x1000)
+ usleep_range(1000, 2000);
+
+ offset += read_len;
+ bytes_left -= read_len;
+ }
+
+ cdev->mcp_nvm_resp = resp;
+ qed_ptt_release(p_hwfn, p_ptt);
+
+ return rc;
+}
+
int qed_mcp_bist_register_test(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
{
u32 drv_mb_param = 0, rsp, param;
@@ -1312,3 +1635,101 @@ int qed_mcp_bist_clock_test(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
return rc;
}
+
+int qed_mcp_bist_nvm_test_get_num_images(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ u32 *num_images)
+{
+ u32 drv_mb_param = 0, rsp;
+ int rc = 0;
+
+ drv_mb_param = (DRV_MB_PARAM_BIST_NVM_TEST_NUM_IMAGES <<
+ DRV_MB_PARAM_BIST_TEST_INDEX_SHIFT);
+
+ rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_BIST_TEST,
+ drv_mb_param, &rsp, num_images);
+ if (rc)
+ return rc;
+
+ if (((rsp & FW_MSG_CODE_MASK) != FW_MSG_CODE_OK))
+ rc = -EINVAL;
+
+ return rc;
+}
+
+int qed_mcp_bist_nvm_test_get_image_att(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ struct bist_nvm_image_att *p_image_att,
+ u32 image_index)
+{
+ u32 buf_size = 0, param, resp = 0, resp_param = 0;
+ int rc;
+
+ param = DRV_MB_PARAM_BIST_NVM_TEST_IMAGE_BY_INDEX <<
+ DRV_MB_PARAM_BIST_TEST_INDEX_SHIFT;
+ param |= image_index << DRV_MB_PARAM_BIST_TEST_IMAGE_INDEX_SHIFT;
+
+ rc = qed_mcp_nvm_rd_cmd(p_hwfn, p_ptt,
+ DRV_MSG_CODE_BIST_TEST, param,
+ &resp, &resp_param,
+ &buf_size,
+ (u32 *)p_image_att);
+ if (rc)
+ return rc;
+
+ if (((resp & FW_MSG_CODE_MASK) != FW_MSG_CODE_OK) ||
+ (p_image_att->return_code != 1))
+ rc = -EINVAL;
+
+ return rc;
+}
+
+#define QED_RESC_ALLOC_VERSION_MAJOR 1
+#define QED_RESC_ALLOC_VERSION_MINOR 0
+#define QED_RESC_ALLOC_VERSION \
+ ((QED_RESC_ALLOC_VERSION_MAJOR << \
+ DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT) | \
+ (QED_RESC_ALLOC_VERSION_MINOR << \
+ DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MINOR_SHIFT))
+int qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ struct resource_info *p_resc_info,
+ u32 *p_mcp_resp, u32 *p_mcp_param)
+{
+ struct qed_mcp_mb_params mb_params;
+ union drv_union_data union_data;
+ int rc;
+
+ memset(&mb_params, 0, sizeof(mb_params));
+ memset(&union_data, 0, sizeof(union_data));
+ mb_params.cmd = DRV_MSG_GET_RESOURCE_ALLOC_MSG;
+ mb_params.param = QED_RESC_ALLOC_VERSION;
+
+ /* Need to have a sufficient large struct, as the cmd_and_union
+ * is going to do memcpy from and to it.
+ */
+ memcpy(&union_data.resource, p_resc_info, sizeof(*p_resc_info));
+
+ mb_params.p_data_src = &union_data;
+ mb_params.p_data_dst = &union_data;
+ rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
+ if (rc)
+ return rc;
+
+ /* Copy the data back */
+ memcpy(p_resc_info, &union_data.resource, sizeof(*p_resc_info));
+ *p_mcp_resp = mb_params.mcp_resp;
+ *p_mcp_param = mb_params.mcp_param;
+
+ DP_VERBOSE(p_hwfn,
+ QED_MSG_SP,
+ "MFW resource_info: version 0x%x, res_id 0x%x, size 0x%x, offset 0x%x, vf_size 0x%x, vf_offset 0x%x, flags 0x%x\n",
+ *p_mcp_param,
+ p_resc_info->res_id,
+ p_resc_info->size,
+ p_resc_info->offset,
+ p_resc_info->vf_size,
+ p_resc_info->vf_offset, p_resc_info->flags);
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index dff520e..407a2c1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -92,6 +92,8 @@ struct qed_mcp_function_info {
#define QED_MCP_VLAN_UNSET (0xffff)
u16 ovlan;
+
+ u16 mtu;
};
struct qed_mcp_nvm_common {
@@ -147,6 +149,30 @@ union qed_mcp_protocol_stats {
struct qed_mcp_rdma_stats rdma_stats;
};
+enum qed_ov_eswitch {
+ QED_OV_ESWITCH_NONE,
+ QED_OV_ESWITCH_VEB,
+ QED_OV_ESWITCH_VEPA
+};
+
+enum qed_ov_client {
+ QED_OV_CLIENT_DRV,
+ QED_OV_CLIENT_USER,
+ QED_OV_CLIENT_VENDOR_SPEC
+};
+
+enum qed_ov_driver_state {
+ QED_OV_DRIVER_STATE_NOT_LOADED,
+ QED_OV_DRIVER_STATE_DISABLED,
+ QED_OV_DRIVER_STATE_ACTIVE
+};
+
+enum qed_ov_wol {
+ QED_OV_WOL_DEFAULT,
+ QED_OV_WOL_DISABLED,
+ QED_OV_WOL_ENABLED
+};
+
/**
* @brief - returns the link params of the hw function
*
@@ -278,6 +304,69 @@ qed_mcp_send_drv_version(struct qed_hwfn *p_hwfn,
struct qed_mcp_drv_version *p_ver);
/**
+ * @brief Notify MFW about the change in base device properties
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param client - qed client type
+ *
+ * @return int - 0 - operation was successful.
+ */
+int qed_mcp_ov_update_current_config(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ enum qed_ov_client client);
+
+/**
+ * @brief Notify MFW about the driver state
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param drv_state - Driver state
+ *
+ * @return int - 0 - operation was successful.
+ */
+int qed_mcp_ov_update_driver_state(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ enum qed_ov_driver_state drv_state);
+
+/**
+ * @brief Send MTU size to MFW
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param mtu - MTU size
+ *
+ * @return int - 0 - operation was successful.
+ */
+int qed_mcp_ov_update_mtu(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt, u16 mtu);
+
+/**
+ * @brief Send MAC address to MFW
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param mac - MAC address
+ *
+ * @return int - 0 - operation was successful.
+ */
+int qed_mcp_ov_update_mac(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt, u8 *mac);
+
+/**
+ * @brief Send WOL mode to MFW
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param wol - WOL mode
+ *
+ * @return int - 0 - operation was successful.
+ */
+int qed_mcp_ov_update_wol(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ enum qed_ov_wol wol);
+
+/**
* @brief Set LED status
*
* @param p_hwfn
@@ -291,6 +380,18 @@ int qed_mcp_set_led(struct qed_hwfn *p_hwfn,
enum qed_led_mode mode);
/**
+ * @brief Read from nvm
+ *
+ * @param cdev
+ * @param addr - nvm offset
+ * @param p_buf - nvm read buffer
+ * @param len - buffer len
+ *
+ * @return int - 0 - operation was successful.
+ */
+int qed_mcp_nvm_read(struct qed_dev *cdev, u32 addr, u8 *p_buf, u32 len);
+
+/**
* @brief Bist register test
*
* @param p_hwfn - hw function
@@ -312,6 +413,35 @@ int qed_mcp_bist_register_test(struct qed_hwfn *p_hwfn,
int qed_mcp_bist_clock_test(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt);
+/**
+ * @brief Bist nvm test - get number of images
+ *
+ * @param p_hwfn - hw function
+ * @param p_ptt - PTT required for register access
+ * @param num_images - number of images if operation was
+ * successful. 0 if not.
+ *
+ * @return int - 0 - operation was successful.
+ */
+int qed_mcp_bist_nvm_test_get_num_images(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ u32 *num_images);
+
+/**
+ * @brief Bist nvm test - get image attributes by index
+ *
+ * @param p_hwfn - hw function
+ * @param p_ptt - PTT required for register access
+ * @param p_image_att - Attributes of image
+ * @param image_index - Index of image to get information for
+ *
+ * @return int - 0 - operation was successful.
+ */
+int qed_mcp_bist_nvm_test_get_image_att(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ struct bist_nvm_image_att *p_image_att,
+ u32 image_index);
+
/* Using hwfn number (and not pf_num) is required since in CMT mode,
* same pf_num may be used by two different hwfn
* TODO - this shouldn't really be in .h file, but until all fields
@@ -546,4 +676,32 @@ int __qed_configure_pf_min_bandwidth(struct qed_hwfn *p_hwfn,
int qed_mcp_mask_parities(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt, u32 mask_parities);
+/**
+ * @brief Send eswitch mode to MFW
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param eswitch - eswitch mode
+ *
+ * @return int - 0 - operation was successful.
+ */
+int qed_mcp_ov_update_eswitch(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ enum qed_ov_eswitch eswitch);
+
+/**
+ * @brief - Gets the MFW allocation info for the given resource
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param p_resc_info - descriptor of requested resource
+ * @param p_mcp_resp
+ * @param p_mcp_param
+ *
+ * @return int - 0 - operation was successful.
+ */
+int qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ struct resource_info *p_resc_info,
+ u32 *p_mcp_resp, u32 *p_mcp_param);
#endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index b11beb5..6a353ff 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -129,17 +129,12 @@ static void qed_bmap_release_id(struct qed_hwfn *p_hwfn,
}
}
-u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id)
+static u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id)
{
/* First sb id for RoCE is after all the l2 sb */
return FEAT_NUM((struct qed_hwfn *)p_hwfn, QED_PF_L2_QUE) + rel_sb_id;
}
-u32 qed_rdma_query_cau_timer_res(void *rdma_cxt)
-{
- return QED_CAU_DEF_RX_TIMER_RES;
-}
-
static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
struct qed_rdma_start_in_params *params)
@@ -162,7 +157,8 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
p_hwfn->p_rdma_info = p_rdma_info;
p_rdma_info->proto = PROTOCOLID_ROCE;
- num_cons = qed_cxt_get_proto_cid_count(p_hwfn, p_rdma_info->proto, 0);
+ num_cons = qed_cxt_get_proto_cid_count(p_hwfn, p_rdma_info->proto,
+ NULL);
p_rdma_info->num_qps = num_cons / 2;
@@ -275,7 +271,7 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
return rc;
}
-void qed_rdma_resc_free(struct qed_hwfn *p_hwfn)
+static void qed_rdma_resc_free(struct qed_hwfn *p_hwfn)
{
struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
@@ -527,6 +523,26 @@ static int qed_rdma_start_fw(struct qed_hwfn *p_hwfn,
return qed_spq_post(p_hwfn, p_ent, NULL);
}
+static int qed_rdma_alloc_tid(void *rdma_cxt, u32 *itid)
+{
+ struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
+ int rc;
+
+ DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Allocate TID\n");
+
+ spin_lock_bh(&p_hwfn->p_rdma_info->lock);
+ rc = qed_rdma_bmap_alloc_id(p_hwfn,
+ &p_hwfn->p_rdma_info->tid_map, itid);
+ spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
+ if (rc)
+ goto out;
+
+ rc = qed_cxt_dynamic_ilt_alloc(p_hwfn, QED_ELEM_TASK, *itid);
+out:
+ DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Allocate TID - done, rc = %d\n", rc);
+ return rc;
+}
+
static int qed_rdma_reserve_lkey(struct qed_hwfn *p_hwfn)
{
struct qed_rdma_device *dev = p_hwfn->p_rdma_info->dev;
@@ -573,7 +589,7 @@ static int qed_rdma_setup(struct qed_hwfn *p_hwfn,
return qed_rdma_start_fw(p_hwfn, params, p_ptt);
}
-int qed_rdma_stop(void *rdma_cxt)
+static int qed_rdma_stop(void *rdma_cxt)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
struct rdma_close_func_ramrod_data *p_ramrod;
@@ -629,8 +645,8 @@ int qed_rdma_stop(void *rdma_cxt)
return rc;
}
-int qed_rdma_add_user(void *rdma_cxt,
- struct qed_rdma_add_user_out_params *out_params)
+static int qed_rdma_add_user(void *rdma_cxt,
+ struct qed_rdma_add_user_out_params *out_params)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
u32 dpi_start_offset;
@@ -664,7 +680,7 @@ int qed_rdma_add_user(void *rdma_cxt,
return rc;
}
-struct qed_rdma_port *qed_rdma_query_port(void *rdma_cxt)
+static struct qed_rdma_port *qed_rdma_query_port(void *rdma_cxt)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
struct qed_rdma_port *p_port = p_hwfn->p_rdma_info->port;
@@ -680,7 +696,7 @@ struct qed_rdma_port *qed_rdma_query_port(void *rdma_cxt)
return p_port;
}
-struct qed_rdma_device *qed_rdma_query_device(void *rdma_cxt)
+static struct qed_rdma_device *qed_rdma_query_device(void *rdma_cxt)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
@@ -690,7 +706,7 @@ struct qed_rdma_device *qed_rdma_query_device(void *rdma_cxt)
return p_hwfn->p_rdma_info->dev;
}
-void qed_rdma_free_tid(void *rdma_cxt, u32 itid)
+static void qed_rdma_free_tid(void *rdma_cxt, u32 itid)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
@@ -701,27 +717,7 @@ void qed_rdma_free_tid(void *rdma_cxt, u32 itid)
spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
}
-int qed_rdma_alloc_tid(void *rdma_cxt, u32 *itid)
-{
- struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
- int rc;
-
- DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Allocate TID\n");
-
- spin_lock_bh(&p_hwfn->p_rdma_info->lock);
- rc = qed_rdma_bmap_alloc_id(p_hwfn,
- &p_hwfn->p_rdma_info->tid_map, itid);
- spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
- if (rc)
- goto out;
-
- rc = qed_cxt_dynamic_ilt_alloc(p_hwfn, QED_ELEM_TASK, *itid);
-out:
- DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Allocate TID - done, rc = %d\n", rc);
- return rc;
-}
-
-void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 qz_offset, u16 prod)
+static void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 qz_offset, u16 prod)
{
struct qed_hwfn *p_hwfn;
u16 qz_num;
@@ -816,7 +812,7 @@ static int qed_rdma_get_int(struct qed_dev *cdev, struct qed_int_info *info)
return 0;
}
-int qed_rdma_alloc_pd(void *rdma_cxt, u16 *pd)
+static int qed_rdma_alloc_pd(void *rdma_cxt, u16 *pd)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
u32 returned_id;
@@ -836,7 +832,7 @@ int qed_rdma_alloc_pd(void *rdma_cxt, u16 *pd)
return rc;
}
-void qed_rdma_free_pd(void *rdma_cxt, u16 pd)
+static void qed_rdma_free_pd(void *rdma_cxt, u16 pd)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
@@ -873,8 +869,9 @@ qed_rdma_toggle_bit_create_resize_cq(struct qed_hwfn *p_hwfn, u16 icid)
return toggle_bit;
}
-int qed_rdma_create_cq(void *rdma_cxt,
- struct qed_rdma_create_cq_in_params *params, u16 *icid)
+static int qed_rdma_create_cq(void *rdma_cxt,
+ struct qed_rdma_create_cq_in_params *params,
+ u16 *icid)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
struct qed_rdma_info *p_info = p_hwfn->p_rdma_info;
@@ -957,98 +954,10 @@ int qed_rdma_create_cq(void *rdma_cxt,
return rc;
}
-int qed_rdma_resize_cq(void *rdma_cxt,
- struct qed_rdma_resize_cq_in_params *in_params,
- struct qed_rdma_resize_cq_out_params *out_params)
-{
- struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
- struct rdma_resize_cq_output_params *p_ramrod_res;
- struct rdma_resize_cq_ramrod_data *p_ramrod;
- enum qed_rdma_toggle_bit toggle_bit;
- struct qed_sp_init_data init_data;
- struct qed_spq_entry *p_ent;
- dma_addr_t ramrod_res_phys;
- u8 fw_return_code;
- int rc = -ENOMEM;
-
- DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", in_params->icid);
-
- p_ramrod_res =
- (struct rdma_resize_cq_output_params *)
- dma_alloc_coherent(&p_hwfn->cdev->pdev->dev,
- sizeof(struct rdma_resize_cq_output_params),
- &ramrod_res_phys, GFP_KERNEL);
- if (!p_ramrod_res) {
- DP_NOTICE(p_hwfn,
- "qed resize cq failed: cannot allocate memory (ramrod)\n");
- return rc;
- }
-
- /* Get SPQ entry */
- memset(&init_data, 0, sizeof(init_data));
- init_data.cid = in_params->icid;
- init_data.opaque_fid = p_hwfn->hw_info.opaque_fid;
- init_data.comp_mode = QED_SPQ_MODE_EBLOCK;
-
- rc = qed_sp_init_request(p_hwfn, &p_ent,
- RDMA_RAMROD_RESIZE_CQ,
- p_hwfn->p_rdma_info->proto, &init_data);
- if (rc)
- goto err;
-
- p_ramrod = &p_ent->ramrod.rdma_resize_cq;
-
- p_ramrod->flags = 0;
-
- /* toggle the bit for every resize or create cq for a given icid */
- toggle_bit = qed_rdma_toggle_bit_create_resize_cq(p_hwfn,
- in_params->icid);
-
- SET_FIELD(p_ramrod->flags,
- RDMA_RESIZE_CQ_RAMROD_DATA_TOGGLE_BIT, toggle_bit);
-
- SET_FIELD(p_ramrod->flags,
- RDMA_RESIZE_CQ_RAMROD_DATA_IS_TWO_LEVEL_PBL,
- in_params->pbl_two_level);
-
- p_ramrod->pbl_log_page_size = in_params->pbl_page_size_log - 12;
- p_ramrod->pbl_num_pages = cpu_to_le16(in_params->pbl_num_pages);
- p_ramrod->max_cqes = cpu_to_le32(in_params->cq_size);
- DMA_REGPAIR_LE(p_ramrod->pbl_addr, in_params->pbl_ptr);
- DMA_REGPAIR_LE(p_ramrod->output_params_addr, ramrod_res_phys);
-
- rc = qed_spq_post(p_hwfn, p_ent, &fw_return_code);
- if (rc)
- goto err;
-
- if (fw_return_code != RDMA_RETURN_OK) {
- DP_NOTICE(p_hwfn, "fw_return_code = %d\n", fw_return_code);
- rc = -EINVAL;
- goto err;
- }
-
- out_params->prod = le32_to_cpu(p_ramrod_res->old_cq_prod);
- out_params->cons = le32_to_cpu(p_ramrod_res->old_cq_cons);
-
- dma_free_coherent(&p_hwfn->cdev->pdev->dev,
- sizeof(struct rdma_resize_cq_output_params),
- p_ramrod_res, ramrod_res_phys);
-
- DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Resized CQ, rc = %d\n", rc);
-
- return rc;
-
-err: dma_free_coherent(&p_hwfn->cdev->pdev->dev,
- sizeof(struct rdma_resize_cq_output_params),
- p_ramrod_res, ramrod_res_phys);
- DP_NOTICE(p_hwfn, "Resized CQ, Failed - rc = %d\n", rc);
-
- return rc;
-}
-
-int qed_rdma_destroy_cq(void *rdma_cxt,
- struct qed_rdma_destroy_cq_in_params *in_params,
- struct qed_rdma_destroy_cq_out_params *out_params)
+static int
+qed_rdma_destroy_cq(void *rdma_cxt,
+ struct qed_rdma_destroy_cq_in_params *in_params,
+ struct qed_rdma_destroy_cq_out_params *out_params)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
struct rdma_destroy_cq_output_params *p_ramrod_res;
@@ -1169,7 +1078,7 @@ static enum roce_flavor qed_roce_mode_to_flavor(enum roce_mode roce_mode)
return flavor;
}
-int qed_roce_alloc_cid(struct qed_hwfn *p_hwfn, u16 *cid)
+static int qed_roce_alloc_cid(struct qed_hwfn *p_hwfn, u16 *cid)
{
struct qed_rdma_info *p_rdma_info = p_hwfn->p_rdma_info;
u32 responder_icid;
@@ -1793,9 +1702,9 @@ static int qed_roce_sp_destroy_qp_requester(struct qed_hwfn *p_hwfn,
return rc;
}
-int qed_roce_query_qp(struct qed_hwfn *p_hwfn,
- struct qed_rdma_qp *qp,
- struct qed_rdma_query_qp_out_params *out_params)
+static int qed_roce_query_qp(struct qed_hwfn *p_hwfn,
+ struct qed_rdma_qp *qp,
+ struct qed_rdma_query_qp_out_params *out_params)
{
struct roce_query_qp_resp_output_params *p_resp_ramrod_res;
struct roce_query_qp_req_output_params *p_req_ramrod_res;
@@ -1936,7 +1845,7 @@ int qed_roce_query_qp(struct qed_hwfn *p_hwfn,
return rc;
}
-int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
+static int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
{
u32 num_invalidated_mw = 0;
u32 num_bound_mw = 0;
@@ -1985,9 +1894,9 @@ int qed_roce_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
return 0;
}
-int qed_rdma_query_qp(void *rdma_cxt,
- struct qed_rdma_qp *qp,
- struct qed_rdma_query_qp_out_params *out_params)
+static int qed_rdma_query_qp(void *rdma_cxt,
+ struct qed_rdma_qp *qp,
+ struct qed_rdma_query_qp_out_params *out_params)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
int rc;
@@ -2022,7 +1931,7 @@ int qed_rdma_query_qp(void *rdma_cxt,
return rc;
}
-int qed_rdma_destroy_qp(void *rdma_cxt, struct qed_rdma_qp *qp)
+static int qed_rdma_destroy_qp(void *rdma_cxt, struct qed_rdma_qp *qp)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
int rc = 0;
@@ -2038,7 +1947,7 @@ int qed_rdma_destroy_qp(void *rdma_cxt, struct qed_rdma_qp *qp)
return rc;
}
-struct qed_rdma_qp *
+static struct qed_rdma_qp *
qed_rdma_create_qp(void *rdma_cxt,
struct qed_rdma_create_qp_in_params *in_params,
struct qed_rdma_create_qp_out_params *out_params)
@@ -2215,9 +2124,9 @@ static int qed_roce_modify_qp(struct qed_hwfn *p_hwfn,
return rc;
}
-int qed_rdma_modify_qp(void *rdma_cxt,
- struct qed_rdma_qp *qp,
- struct qed_rdma_modify_qp_in_params *params)
+static int qed_rdma_modify_qp(void *rdma_cxt,
+ struct qed_rdma_qp *qp,
+ struct qed_rdma_modify_qp_in_params *params)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
enum qed_roce_qp_state prev_state;
@@ -2312,8 +2221,9 @@ int qed_rdma_modify_qp(void *rdma_cxt,
return rc;
}
-int qed_rdma_register_tid(void *rdma_cxt,
- struct qed_rdma_register_tid_in_params *params)
+static int
+qed_rdma_register_tid(void *rdma_cxt,
+ struct qed_rdma_register_tid_in_params *params)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
struct rdma_register_tid_ramrod_data *p_ramrod;
@@ -2450,7 +2360,7 @@ int qed_rdma_register_tid(void *rdma_cxt,
return rc;
}
-int qed_rdma_deregister_tid(void *rdma_cxt, u32 itid)
+static int qed_rdma_deregister_tid(void *rdma_cxt, u32 itid)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
struct rdma_deregister_tid_ramrod_data *p_ramrod;
@@ -2561,7 +2471,8 @@ void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
qed_rdma_dpm_conf(p_hwfn, p_ptt);
}
-int qed_rdma_start(void *rdma_cxt, struct qed_rdma_start_in_params *params)
+static int qed_rdma_start(void *rdma_cxt,
+ struct qed_rdma_start_in_params *params)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
struct qed_ptt *p_ptt;
@@ -2601,7 +2512,7 @@ static int qed_rdma_init(struct qed_dev *cdev,
return qed_rdma_start(QED_LEADING_HWFN(cdev), params);
}
-void qed_rdma_remove_user(void *rdma_cxt, u16 dpi)
+static void qed_rdma_remove_user(void *rdma_cxt, u16 dpi)
{
struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
@@ -2808,11 +2719,6 @@ static int qed_roce_ll2_stop(struct qed_dev *cdev)
struct qed_roce_ll2_info *roce_ll2 = hwfn->ll2;
int rc;
- if (!cdev) {
- DP_ERR(cdev, "qed roce ll2 stop: invalid cdev\n");
- return -EINVAL;
- }
-
if (roce_ll2->handle == QED_LL2_UNUSED_HANDLE) {
DP_ERR(cdev, "qed roce ll2 stop: cannot stop an unused LL2\n");
return -EINVAL;
@@ -2849,7 +2755,7 @@ static int qed_roce_ll2_tx(struct qed_dev *cdev,
int rc;
int i;
- if (!cdev || !pkt || !params) {
+ if (!pkt || !params) {
DP_ERR(cdev,
"roce ll2 tx: failed tx because one of the following is NULL - drv=%p, pkt=%p, params=%p\n",
cdev, pkt, params);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.h b/drivers/net/ethernet/qlogic/qed/qed_roce.h
index 2f091e8..279f342 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.h
@@ -95,26 +95,6 @@ struct qed_rdma_info {
enum protocol_type proto;
};
-struct qed_rdma_resize_cq_in_params {
- u16 icid;
- u32 cq_size;
- bool pbl_two_level;
- u64 pbl_ptr;
- u16 pbl_num_pages;
- u8 pbl_page_size_log;
-};
-
-struct qed_rdma_resize_cq_out_params {
- u32 prod;
- u32 cons;
-};
-
-struct qed_rdma_resize_cnq_in_params {
- u32 cnq_id;
- u32 pbl_page_size_log;
- u64 pbl_ptr;
-};
-
struct qed_rdma_qp {
struct regpair qp_handle;
struct regpair qp_handle_async;
@@ -181,36 +161,55 @@ struct qed_rdma_qp {
dma_addr_t shared_queue_phys_addr;
};
-int
-qed_rdma_add_user(void *rdma_cxt,
- struct qed_rdma_add_user_out_params *out_params);
-int qed_rdma_alloc_pd(void *rdma_cxt, u16 *pd);
-int qed_rdma_alloc_tid(void *rdma_cxt, u32 *tid);
-int qed_rdma_deregister_tid(void *rdma_cxt, u32 tid);
-void qed_rdma_free_tid(void *rdma_cxt, u32 tid);
-struct qed_rdma_device *qed_rdma_query_device(void *rdma_cxt);
-struct qed_rdma_port *qed_rdma_query_port(void *rdma_cxt);
-int
-qed_rdma_register_tid(void *rdma_cxt,
- struct qed_rdma_register_tid_in_params *params);
-void qed_rdma_remove_user(void *rdma_cxt, u16 dpi);
-int qed_rdma_start(void *p_hwfn, struct qed_rdma_start_in_params *params);
-int qed_rdma_stop(void *rdma_cxt);
-u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id);
-u32 qed_rdma_query_cau_timer_res(void *p_hwfn);
-void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 cnq_index, u16 prod);
-void qed_rdma_resc_free(struct qed_hwfn *p_hwfn);
+#if IS_ENABLED(CONFIG_QED_RDMA)
+void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
void qed_async_roce_event(struct qed_hwfn *p_hwfn,
struct event_ring_entry *p_eqe);
-int qed_rdma_destroy_qp(void *rdma_cxt, struct qed_rdma_qp *qp);
-int qed_rdma_modify_qp(void *rdma_cxt, struct qed_rdma_qp *qp,
- struct qed_rdma_modify_qp_in_params *params);
-int qed_rdma_query_qp(void *rdma_cxt, struct qed_rdma_qp *qp,
- struct qed_rdma_query_qp_out_params *out_params);
-
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
-void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn,
+ u8 connection_handle,
+ void *cookie,
+ dma_addr_t first_frag_addr,
+ bool b_last_fragment, bool b_last_packet);
+void qed_ll2b_release_tx_gsi_packet(struct qed_hwfn *p_hwfn,
+ u8 connection_handle,
+ void *cookie,
+ dma_addr_t first_frag_addr,
+ bool b_last_fragment, bool b_last_packet);
+void qed_ll2b_complete_rx_gsi_packet(struct qed_hwfn *p_hwfn,
+ u8 connection_handle,
+ void *cookie,
+ dma_addr_t rx_buf_addr,
+ u16 data_length,
+ u8 data_length_error,
+ u16 parse_flags,
+ u16 vlan,
+ u32 src_mac_addr_hi,
+ u16 src_mac_addr_lo, bool b_last_packet);
#else
-void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) {}
+static inline void qed_rdma_dpm_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) {}
+static inline void qed_async_roce_event(struct qed_hwfn *p_hwfn, struct event_ring_entry *p_eqe) {}
+static inline void qed_ll2b_complete_tx_gsi_packet(struct qed_hwfn *p_hwfn,
+ u8 connection_handle,
+ void *cookie,
+ dma_addr_t first_frag_addr,
+ bool b_last_fragment,
+ bool b_last_packet) {}
+static inline void qed_ll2b_release_tx_gsi_packet(struct qed_hwfn *p_hwfn,
+ u8 connection_handle,
+ void *cookie,
+ dma_addr_t first_frag_addr,
+ bool b_last_fragment,
+ bool b_last_packet) {}
+static inline void qed_ll2b_complete_rx_gsi_packet(struct qed_hwfn *p_hwfn,
+ u8 connection_handle,
+ void *cookie,
+ dma_addr_t rx_buf_addr,
+ u16 data_length,
+ u8 data_length_error,
+ u16 parse_flags,
+ u16 vlan,
+ u32 src_mac_addr_hi,
+ u16 src_mac_addr_lo,
+ bool b_last_packet) {}
#endif
#endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_selftest.c b/drivers/net/ethernet/qlogic/qed/qed_selftest.c
index 9b7678f..48bfaec 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_selftest.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_selftest.c
@@ -1,3 +1,4 @@
+#include <linux/crc32.h>
#include "qed.h"
#include "qed_dev_api.h"
#include "qed_mcp.h"
@@ -75,3 +76,103 @@ int qed_selftest_clock(struct qed_dev *cdev)
return rc;
}
+
+int qed_selftest_nvram(struct qed_dev *cdev)
+{
+ struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+ struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn);
+ u32 num_images, i, j, nvm_crc, calc_crc;
+ struct bist_nvm_image_att image_att;
+ u8 *buf = NULL;
+ __be32 val;
+ int rc;
+
+ if (!p_ptt) {
+ DP_ERR(p_hwfn, "failed to acquire ptt\n");
+ return -EBUSY;
+ }
+
+ /* Acquire from MFW the amount of available images */
+ rc = qed_mcp_bist_nvm_test_get_num_images(p_hwfn, p_ptt, &num_images);
+ if (rc || !num_images) {
+ DP_ERR(p_hwfn, "Failed getting number of images\n");
+ return -EINVAL;
+ }
+
+ /* Iterate over images and validate CRC */
+ for (i = 0; i < num_images; i++) {
+ /* This mailbox returns information about the image required for
+ * reading it.
+ */
+ rc = qed_mcp_bist_nvm_test_get_image_att(p_hwfn, p_ptt,
+ &image_att, i);
+ if (rc) {
+ DP_ERR(p_hwfn,
+ "Failed getting image index %d attributes\n",
+ i);
+ goto err0;
+ }
+
+ /* After MFW crash dump is collected - the image's CRC stops
+ * being valid.
+ */
+ if (image_att.image_type == NVM_TYPE_MDUMP)
+ continue;
+
+ DP_VERBOSE(p_hwfn, QED_MSG_SP, "image index %d, size %x\n",
+ i, image_att.len);
+
+ /* Allocate a buffer for holding the nvram image */
+ buf = kzalloc(image_att.len, GFP_KERNEL);
+ if (!buf) {
+ rc = -ENOMEM;
+ goto err0;
+ }
+
+ /* Read image into buffer */
+ rc = qed_mcp_nvm_read(p_hwfn->cdev, image_att.nvm_start_addr,
+ buf, image_att.len);
+ if (rc) {
+ DP_ERR(p_hwfn,
+ "Failed reading image index %d from nvm.\n", i);
+ goto err1;
+ }
+
+ /* Convert the buffer into big-endian format (excluding the
+ * closing 4 bytes of CRC).
+ */
+ for (j = 0; j < image_att.len - 4; j += 4) {
+ val = cpu_to_be32(*(u32 *)&buf[j]);
+ *(u32 *)&buf[j] = (__force u32)val;
+ }
+
+ /* Calc CRC for the "actual" image buffer, i.e. not including
+ * the last 4 CRC bytes.
+ */
+ nvm_crc = *(u32 *)(buf + image_att.len - 4);
+ calc_crc = crc32(0xffffffff, buf, image_att.len - 4);
+ calc_crc = (__force u32)~cpu_to_be32(calc_crc);
+ DP_VERBOSE(p_hwfn, QED_MSG_SP,
+ "nvm crc 0x%x, calc_crc 0x%x\n", nvm_crc, calc_crc);
+
+ if (calc_crc != nvm_crc) {
+ rc = -EINVAL;
+ goto err1;
+ }
+
+ /* Done with this image; Free to prevent double release
+ * on subsequent failure.
+ */
+ kfree(buf);
+ buf = NULL;
+ }
+
+ qed_ptt_release(p_hwfn, p_ptt);
+ return 0;
+
+err1:
+ kfree(buf);
+err0:
+ qed_ptt_release(p_hwfn, p_ptt);
+ return rc;
+}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_selftest.h b/drivers/net/ethernet/qlogic/qed/qed_selftest.h
index 50eb0b49..739ddb7 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_selftest.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_selftest.h
@@ -37,4 +37,14 @@ int qed_selftest_register(struct qed_dev *cdev);
* @return int
*/
int qed_selftest_clock(struct qed_dev *cdev);
+
+/**
+ * @brief qed_selftest_nvram - Perform nvram test
+ *
+ * @param cdev
+ *
+ * @return int
+ */
+int qed_selftest_nvram(struct qed_dev *cdev);
+
#endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h
index 27c450f..9c897bc 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h
@@ -80,7 +80,6 @@ union ramrod_data {
struct roce_destroy_qp_resp_ramrod_data roce_destroy_qp_resp;
struct roce_destroy_qp_req_ramrod_data roce_destroy_qp_req;
struct rdma_create_cq_ramrod_data rdma_create_cq;
- struct rdma_resize_cq_ramrod_data rdma_resize_cq;
struct rdma_destroy_cq_ramrod_data rdma_destroy_cq;
struct rdma_srq_create_ramrod_data rdma_create_srq;
struct rdma_srq_destroy_ramrod_data rdma_destroy_srq;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 6c05402..019960b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -28,9 +28,7 @@
#include "qed_reg_addr.h"
#include "qed_sp.h"
#include "qed_sriov.h"
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
#include "qed_roce.h"
-#endif
/***************************************************************************
* Structures & Definitions
@@ -272,11 +270,9 @@ qed_async_event_completion(struct qed_hwfn *p_hwfn,
struct event_ring_entry *p_eqe)
{
switch (p_eqe->protocol_id) {
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
case PROTOCOLID_ROCE:
qed_async_roce_event(p_hwfn, p_eqe);
return 0;
-#endif
case PROTOCOLID_COMMON:
return qed_sriov_eqe_event(p_hwfn,
p_eqe->opcode,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index 6f029f9..f3f742a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -3470,7 +3470,6 @@ int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled)
static int qed_sriov_enable(struct qed_dev *cdev, int num)
{
- struct qed_sb_cnt_info sb_cnt_info;
int i, j, rc;
if (num >= RESC_NUM(&cdev->hwfns[0], QED_VPORT)) {
@@ -3483,7 +3482,11 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num)
for_each_hwfn(cdev, j) {
struct qed_hwfn *hwfn = &cdev->hwfns[j];
struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
- int num_sbs = 0, limit = 16;
+ int num_queues;
+
+ /* Make sure not to use more than 16 queues per VF */
+ num_queues = min_t(int,
+ FEAT_NUM(hwfn, QED_VF_L2_QUE) / num, 16);
if (!ptt) {
DP_ERR(hwfn, "Failed to acquire ptt\n");
@@ -3491,19 +3494,11 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num)
goto err;
}
- if (IS_MF_DEFAULT(hwfn))
- limit = MAX_NUM_VFS_BB / hwfn->num_funcs_on_engine;
-
- memset(&sb_cnt_info, 0, sizeof(sb_cnt_info));
- qed_int_get_num_sbs(hwfn, &sb_cnt_info);
- num_sbs = min_t(int, sb_cnt_info.sb_free_blk, limit);
-
for (i = 0; i < num; i++) {
if (!qed_iov_is_valid_vfid(hwfn, i, false, true))
continue;
- rc = qed_iov_init_hw_for_vf(hwfn,
- ptt, i, num_sbs / num);
+ rc = qed_iov_init_hw_for_vf(hwfn, ptt, i, num_queues);
if (rc) {
DP_ERR(cdev, "Failed to enable VF[%d]\n", i);
qed_ptt_release(hwfn, ptt);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index f580bf4..3c06336 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -1171,6 +1171,13 @@ void qed_vf_get_num_vlan_filters(struct qed_hwfn *p_hwfn, u8 *num_vlan_filters)
*num_vlan_filters = p_vf->acquire_resp.resc.num_vlan_filters;
}
+void qed_vf_get_num_mac_filters(struct qed_hwfn *p_hwfn, u8 *num_mac_filters)
+{
+ struct qed_vf_iov *p_vf = p_hwfn->vf_iov_info;
+
+ *num_mac_filters = p_vf->acquire_resp.resc.num_mac_filters;
+}
+
bool qed_vf_check_mac(struct qed_hwfn *p_hwfn, u8 *mac)
{
struct qed_bulletin_content *bulletin;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h
index 944745b..325c250 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h
@@ -623,6 +623,14 @@ void qed_vf_get_num_vlan_filters(struct qed_hwfn *p_hwfn,
u8 *num_vlan_filters);
/**
+ * @brief Get number of MAC filters allocated for VF by qed
+ *
+ * @param p_hwfn
+ * @param num_rxqs - allocated MAC filters
+ */
+void qed_vf_get_num_mac_filters(struct qed_hwfn *p_hwfn, u8 *num_mac_filters);
+
+/**
* @brief Check if VF can set a MAC address
*
* @param p_hwfn
@@ -872,6 +880,11 @@ static inline void qed_vf_get_num_vlan_filters(struct qed_hwfn *p_hwfn,
{
}
+static inline void qed_vf_get_num_mac_filters(struct qed_hwfn *p_hwfn,
+ u8 *num_mac_filters)
+{
+}
+
static inline bool qed_vf_check_mac(struct qed_hwfn *p_hwfn, u8 *mac)
{
return false;
diff --git a/drivers/net/ethernet/qlogic/qede/Makefile b/drivers/net/ethernet/qlogic/qede/Makefile
index 28dc589..048a230 100644
--- a/drivers/net/ethernet/qlogic/qede/Makefile
+++ b/drivers/net/ethernet/qlogic/qede/Makefile
@@ -2,4 +2,4 @@
qede-y := qede_main.o qede_ethtool.o
qede-$(CONFIG_DCB) += qede_dcbnl.o
-qede-$(CONFIG_INFINIBAND_QEDR) += qede_roce.o
+qede-$(CONFIG_QED_RDMA) += qede_roce.o
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 9135b9d..0cba21b 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -193,6 +193,8 @@ struct qede_dev {
u16 vxlan_dst_port;
u16 geneve_dst_port;
+ bool wol_enabled;
+
struct qede_rdma_dev rdma_info;
};
@@ -349,12 +351,13 @@ bool qede_has_rx_work(struct qede_rx_queue *rxq);
int qede_txq_has_work(struct qede_tx_queue *txq);
void qede_recycle_rx_bd_ring(struct qede_rx_queue *rxq, struct qede_dev *edev,
u8 count);
+void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq);
#define RX_RING_SIZE_POW 13
#define RX_RING_SIZE ((u16)BIT(RX_RING_SIZE_POW))
#define NUM_RX_BDS_MAX (RX_RING_SIZE - 1)
#define NUM_RX_BDS_MIN 128
-#define NUM_RX_BDS_DEF NUM_RX_BDS_MAX
+#define NUM_RX_BDS_DEF ((u16)BIT(10) - 1)
#define TX_RING_SIZE_POW 13
#define TX_RING_SIZE ((u16)BIT(TX_RING_SIZE_POW))
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index b7dbb44..8a3debe 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -157,6 +157,7 @@ enum qede_ethtool_tests {
QEDE_ETHTOOL_MEMORY_TEST,
QEDE_ETHTOOL_REGISTER_TEST,
QEDE_ETHTOOL_CLOCK_TEST,
+ QEDE_ETHTOOL_NVRAM_TEST,
QEDE_ETHTOOL_TEST_MAX
};
@@ -166,6 +167,7 @@ static const char qede_tests_str_arr[QEDE_ETHTOOL_TEST_MAX][ETH_GSTRING_LEN] = {
"Memory (online)\t\t",
"Register (online)\t",
"Clock (online)\t\t",
+ "Nvram (online)\t\t",
};
static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf)
@@ -175,16 +177,23 @@ static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf)
for (i = 0, k = 0; i < QEDE_QUEUE_CNT(edev); i++) {
int tc;
- for (j = 0; j < QEDE_NUM_RQSTATS; j++)
- sprintf(buf + (k + j) * ETH_GSTRING_LEN,
- "%d: %s", i, qede_rqstats_arr[j].string);
- k += QEDE_NUM_RQSTATS;
- for (tc = 0; tc < edev->num_tc; tc++) {
- for (j = 0; j < QEDE_NUM_TQSTATS; j++)
+ if (edev->fp_array[i].type & QEDE_FASTPATH_RX) {
+ for (j = 0; j < QEDE_NUM_RQSTATS; j++)
sprintf(buf + (k + j) * ETH_GSTRING_LEN,
- "%d.%d: %s", i, tc,
- qede_tqstats_arr[j].string);
- k += QEDE_NUM_TQSTATS;
+ "%d: %s", i,
+ qede_rqstats_arr[j].string);
+ k += QEDE_NUM_RQSTATS;
+ }
+
+ if (edev->fp_array[i].type & QEDE_FASTPATH_TX) {
+ for (tc = 0; tc < edev->num_tc; tc++) {
+ for (j = 0; j < QEDE_NUM_TQSTATS; j++)
+ sprintf(buf + (k + j) *
+ ETH_GSTRING_LEN,
+ "%d.%d: %s", i, tc,
+ qede_tqstats_arr[j].string);
+ k += QEDE_NUM_TQSTATS;
+ }
}
}
@@ -318,7 +327,7 @@ static const struct qede_link_mode_mapping qed_lm_map[] = {
{ \
int i; \
\
- for (i = 0; i < QED_LM_COUNT; i++) { \
+ for (i = 0; i < ARRAY_SIZE(qed_lm_map); i++) { \
if ((caps) & (qed_lm_map[i].qed_link_mode)) \
__set_bit(qed_lm_map[i].ethtool_link_mode,\
lk_ksettings->link_modes.name); \
@@ -329,7 +338,7 @@ static const struct qede_link_mode_mapping qed_lm_map[] = {
{ \
int i; \
\
- for (i = 0; i < QED_LM_COUNT; i++) { \
+ for (i = 0; i < ARRAY_SIZE(qed_lm_map); i++) { \
if (test_bit(qed_lm_map[i].ethtool_link_mode, \
lk_ksettings->link_modes.name)) \
caps |= qed_lm_map[i].qed_link_mode; \
@@ -481,6 +490,45 @@ static void qede_get_drvinfo(struct net_device *ndev,
strlcpy(info->bus_info, pci_name(edev->pdev), sizeof(info->bus_info));
}
+static void qede_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
+{
+ struct qede_dev *edev = netdev_priv(ndev);
+
+ if (edev->dev_info.common.wol_support) {
+ wol->supported = WAKE_MAGIC;
+ wol->wolopts = edev->wol_enabled ? WAKE_MAGIC : 0;
+ }
+}
+
+static int qede_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
+{
+ struct qede_dev *edev = netdev_priv(ndev);
+ bool wol_requested;
+ int rc;
+
+ if (wol->wolopts & ~WAKE_MAGIC) {
+ DP_INFO(edev,
+ "Can't support WoL options other than magic-packet\n");
+ return -EINVAL;
+ }
+
+ wol_requested = !!(wol->wolopts & WAKE_MAGIC);
+ if (wol_requested == edev->wol_enabled)
+ return 0;
+
+ /* Need to actually change configuration */
+ if (!edev->dev_info.common.wol_support) {
+ DP_INFO(edev, "Device doesn't support WoL\n");
+ return -EINVAL;
+ }
+
+ rc = edev->ops->common->update_wol(edev->cdev, wol_requested);
+ if (!rc)
+ edev->wol_enabled = wol_requested;
+
+ return rc;
+}
+
static u32 qede_get_msglevel(struct net_device *ndev)
{
struct qede_dev *edev = netdev_priv(ndev);
@@ -739,6 +787,8 @@ int qede_change_mtu(struct net_device *ndev, int new_mtu)
qede_update_mtu(edev, &args);
+ edev->ops->common->update_mtu(edev->cdev, args.mtu);
+
return 0;
}
@@ -748,6 +798,8 @@ static void qede_get_channels(struct net_device *dev,
struct qede_dev *edev = netdev_priv(dev);
channels->max_combined = QEDE_MAX_RSS_CNT(edev);
+ channels->max_rx = QEDE_MAX_RSS_CNT(edev);
+ channels->max_tx = QEDE_MAX_RSS_CNT(edev);
channels->combined_count = QEDE_QUEUE_CNT(edev) - edev->fp_num_tx -
edev->fp_num_rx;
channels->tx_count = edev->fp_num_tx;
@@ -812,6 +864,13 @@ static int qede_set_channels(struct net_device *dev,
edev->req_queues = count;
edev->req_num_tx = channels->tx_count;
edev->req_num_rx = channels->rx_count;
+ /* Reset the indirection table if rx queue count is updated */
+ if ((edev->req_queues - edev->req_num_tx) != QEDE_RSS_COUNT(edev)) {
+ edev->rss_params_inited &= ~QEDE_RSS_INDIR_INITED;
+ memset(&edev->rss_params.rss_ind_table, 0,
+ sizeof(edev->rss_params.rss_ind_table));
+ }
+
if (netif_running(dev))
qede_reload(edev, NULL, NULL);
@@ -1045,6 +1104,12 @@ static int qede_set_rxfh(struct net_device *dev, const u32 *indir,
struct qede_dev *edev = netdev_priv(dev);
int i;
+ if (edev->dev_info.common.num_hwfns > 1) {
+ DP_INFO(edev,
+ "RSS configuration is not supported for 100G devices\n");
+ return -EOPNOTSUPP;
+ }
+
if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
return -EOPNOTSUPP;
@@ -1176,8 +1241,8 @@ static int qede_selftest_transmit_traffic(struct qede_dev *edev,
}
first_bd = (struct eth_tx_1st_bd *)qed_chain_consume(&txq->tx_pbl);
- dma_unmap_page(&edev->pdev->dev, BD_UNMAP_ADDR(first_bd),
- BD_UNMAP_LEN(first_bd), DMA_TO_DEVICE);
+ dma_unmap_single(&edev->pdev->dev, BD_UNMAP_ADDR(first_bd),
+ BD_UNMAP_LEN(first_bd), DMA_TO_DEVICE);
txq->sw_tx_cons++;
txq->sw_tx_ring[idx].skb = NULL;
@@ -1191,8 +1256,8 @@ static int qede_selftest_receive_traffic(struct qede_dev *edev)
struct qede_rx_queue *rxq = NULL;
struct sw_rx_data *sw_rx_data;
union eth_rx_cqe *cqe;
+ int i, rc = 0;
u8 *data_ptr;
- int i;
for_each_queue(i) {
if (edev->fp_array[i].type & QEDE_FASTPATH_RX) {
@@ -1211,46 +1276,60 @@ static int qede_selftest_receive_traffic(struct qede_dev *edev)
* queue and that the loopback traffic is not IP.
*/
for (i = 0; i < QEDE_SELFTEST_POLL_COUNT; i++) {
- if (qede_has_rx_work(rxq))
+ if (!qede_has_rx_work(rxq)) {
+ usleep_range(100, 200);
+ continue;
+ }
+
+ hw_comp_cons = le16_to_cpu(*rxq->hw_cons_ptr);
+ sw_comp_cons = qed_chain_get_cons_idx(&rxq->rx_comp_ring);
+
+ /* Memory barrier to prevent the CPU from doing speculative
+ * reads of CQE/BD before reading hw_comp_cons. If the CQE is
+ * read before it is written by FW, then FW writes CQE and SB,
+ * and then the CPU reads the hw_comp_cons, it will use an old
+ * CQE.
+ */
+ rmb();
+
+ /* Get the CQE from the completion ring */
+ cqe = (union eth_rx_cqe *)qed_chain_consume(&rxq->rx_comp_ring);
+
+ /* Get the data from the SW ring */
+ sw_rx_index = rxq->sw_rx_cons & NUM_RX_BDS_MAX;
+ sw_rx_data = &rxq->sw_rx_ring[sw_rx_index];
+ fp_cqe = &cqe->fast_path_regular;
+ len = le16_to_cpu(fp_cqe->len_on_first_bd);
+ data_ptr = (u8 *)(page_address(sw_rx_data->data) +
+ fp_cqe->placement_offset +
+ sw_rx_data->page_offset);
+ if (ether_addr_equal(data_ptr, edev->ndev->dev_addr) &&
+ ether_addr_equal(data_ptr + ETH_ALEN,
+ edev->ndev->dev_addr)) {
+ for (i = ETH_HLEN; i < len; i++)
+ if (data_ptr[i] != (unsigned char)(i & 0xff)) {
+ rc = -1;
+ break;
+ }
+
+ qede_recycle_rx_bd_ring(rxq, edev, 1);
+ qed_chain_recycle_consumed(&rxq->rx_comp_ring);
break;
- usleep_range(100, 200);
+ }
+
+ DP_INFO(edev, "Not the transmitted packet\n");
+ qede_recycle_rx_bd_ring(rxq, edev, 1);
+ qed_chain_recycle_consumed(&rxq->rx_comp_ring);
}
- if (!qede_has_rx_work(rxq)) {
+ if (i == QEDE_SELFTEST_POLL_COUNT) {
DP_NOTICE(edev, "Failed to receive the traffic\n");
return -1;
}
- hw_comp_cons = le16_to_cpu(*rxq->hw_cons_ptr);
- sw_comp_cons = qed_chain_get_cons_idx(&rxq->rx_comp_ring);
+ qede_update_rx_prod(edev, rxq);
- /* Memory barrier to prevent the CPU from doing speculative reads of CQE
- * / BD before reading hw_comp_cons. If the CQE is read before it is
- * written by FW, then FW writes CQE and SB, and then the CPU reads the
- * hw_comp_cons, it will use an old CQE.
- */
- rmb();
-
- /* Get the CQE from the completion ring */
- cqe = (union eth_rx_cqe *)qed_chain_consume(&rxq->rx_comp_ring);
-
- /* Get the data from the SW ring */
- sw_rx_index = rxq->sw_rx_cons & NUM_RX_BDS_MAX;
- sw_rx_data = &rxq->sw_rx_ring[sw_rx_index];
- fp_cqe = &cqe->fast_path_regular;
- len = le16_to_cpu(fp_cqe->len_on_first_bd);
- data_ptr = (u8 *)(page_address(sw_rx_data->data) +
- fp_cqe->placement_offset + sw_rx_data->page_offset);
- for (i = ETH_HLEN; i < len; i++)
- if (data_ptr[i] != (unsigned char)(i & 0xff)) {
- DP_NOTICE(edev, "Loopback test failed\n");
- qede_recycle_rx_bd_ring(rxq, edev, 1);
- return -1;
- }
-
- qede_recycle_rx_bd_ring(rxq, edev, 1);
-
- return 0;
+ return rc;
}
static int qede_selftest_run_loopback(struct qede_dev *edev, u32 loopback_mode)
@@ -1361,6 +1440,11 @@ static void qede_self_test(struct net_device *dev,
buf[QEDE_ETHTOOL_CLOCK_TEST] = 1;
etest->flags |= ETH_TEST_FL_FAILED;
}
+
+ if (edev->ops->common->selftest->selftest_nvram(edev->cdev)) {
+ buf[QEDE_ETHTOOL_NVRAM_TEST] = 1;
+ etest->flags |= ETH_TEST_FL_FAILED;
+ }
}
static int qede_set_tunable(struct net_device *dev,
@@ -1411,6 +1495,8 @@ static const struct ethtool_ops qede_ethtool_ops = {
.get_drvinfo = qede_get_drvinfo,
.get_regs_len = qede_get_regs_len,
.get_regs = qede_get_regs,
+ .get_wol = qede_get_wol,
+ .set_wol = qede_set_wol,
.get_msglevel = qede_get_msglevel,
.set_msglevel = qede_set_msglevel,
.nway_reset = qede_nway_reset,
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 4f29865..b84a2c4 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -95,6 +95,7 @@ static int qede_probe(struct pci_dev *pdev, const struct pci_device_id *id);
#define TX_TIMEOUT (5 * HZ)
static void qede_remove(struct pci_dev *pdev);
+static void qede_shutdown(struct pci_dev *pdev);
static int qede_alloc_rx_buffer(struct qede_dev *edev,
struct qede_rx_queue *rxq);
static void qede_link_update(void *dev, struct qed_link_output *link);
@@ -166,6 +167,7 @@ static struct pci_driver qede_pci_driver = {
.id_table = qede_pci_tbl,
.probe = qede_probe,
.remove = qede_remove,
+ .shutdown = qede_shutdown,
#ifdef CONFIG_QED_SRIOV
.sriov_configure = qede_sriov_configure,
#endif
@@ -317,8 +319,8 @@ static int qede_free_tx_pkt(struct qede_dev *edev,
split_bd_len = BD_UNMAP_LEN(split);
bds_consumed++;
}
- dma_unmap_page(&edev->pdev->dev, BD_UNMAP_ADDR(first_bd),
- BD_UNMAP_LEN(first_bd) + split_bd_len, DMA_TO_DEVICE);
+ dma_unmap_single(&edev->pdev->dev, BD_UNMAP_ADDR(first_bd),
+ BD_UNMAP_LEN(first_bd) + split_bd_len, DMA_TO_DEVICE);
/* Unmap the data of the skb frags */
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++, bds_consumed++) {
@@ -363,8 +365,8 @@ static void qede_free_failed_tx_pkt(struct qede_dev *edev,
nbd--;
}
- dma_unmap_page(&edev->pdev->dev, BD_UNMAP_ADDR(first_bd),
- BD_UNMAP_LEN(first_bd) + split_bd_len, DMA_TO_DEVICE);
+ dma_unmap_single(&edev->pdev->dev, BD_UNMAP_ADDR(first_bd),
+ BD_UNMAP_LEN(first_bd) + split_bd_len, DMA_TO_DEVICE);
/* Unmap the data of the skb frags */
for (i = 0; i < nbd; i++) {
@@ -964,8 +966,7 @@ static inline int qede_realloc_rx_buffer(struct qede_dev *edev,
return 0;
}
-static inline void qede_update_rx_prod(struct qede_dev *edev,
- struct qede_rx_queue *rxq)
+void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq)
{
u16 bd_prod = qed_chain_get_prod_idx(&rxq->rx_bd_ring);
u16 cqe_prod = qed_chain_get_prod_idx(&rxq->rx_comp_ring);
@@ -2365,7 +2366,7 @@ static void qede_init_ndev(struct qede_dev *edev)
qede_set_ethtool_ops(ndev);
- ndev->priv_flags = IFF_UNICAST_FLT;
+ ndev->priv_flags |= IFF_UNICAST_FLT;
/* user-changeble features */
hw_features = NETIF_F_GRO | NETIF_F_SG |
@@ -2397,6 +2398,8 @@ static void qede_init_ndev(struct qede_dev *edev)
/* Set network device HW mac */
ether_addr_copy(edev->ndev->dev_addr, edev->dev_info.common.hw_mac);
+
+ ndev->mtu = edev->dev_info.common.mtu;
}
/* This function converts from 32b param to two params of level and module
@@ -2704,6 +2707,8 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
/* Use global ops since we've freed edev */
qed_ops->common->slowpath_stop(cdev);
+ if (system_state == SYSTEM_POWER_OFF)
+ return;
qed_ops->common->remove(cdev);
dev_info(&pdev->dev, "Ending qede_remove successfully\n");
@@ -2714,6 +2719,11 @@ static void qede_remove(struct pci_dev *pdev)
__qede_remove(pdev, QEDE_REMOVE_NORMAL);
}
+static void qede_shutdown(struct pci_dev *pdev)
+{
+ __qede_remove(pdev, QEDE_REMOVE_NORMAL);
+}
+
/* -------------------------------------------------------------------------
* START OF LOAD / UNLOAD
* -------------------------------------------------------------------------
@@ -2905,7 +2915,7 @@ static int qede_alloc_sge_mem(struct qede_dev *edev, struct qede_rx_queue *rxq)
}
mapping = dma_map_page(&edev->pdev->dev, replace_buf->data, 0,
- rxq->rx_buf_size, DMA_FROM_DEVICE);
+ PAGE_SIZE, DMA_FROM_DEVICE);
if (unlikely(dma_mapping_error(&edev->pdev->dev, mapping))) {
DP_NOTICE(edev,
"Failed to map TPA replacement buffer\n");
@@ -3006,7 +3016,7 @@ static int qede_alloc_mem_txq(struct qede_dev *edev, struct qede_tx_queue *txq)
txq->num_tx_buffers = edev->q_num_tx_buffers;
/* Allocate the parallel driver ring for Tx buffers */
- size = sizeof(*txq->sw_tx_ring) * NUM_TX_BDS_MAX;
+ size = sizeof(*txq->sw_tx_ring) * TX_RING_SIZE;
txq->sw_tx_ring = kzalloc(size, GFP_KERNEL);
if (!txq->sw_tx_ring) {
DP_NOTICE(edev, "Tx buffers ring allocation failed\n");
@@ -3017,7 +3027,7 @@ static int qede_alloc_mem_txq(struct qede_dev *edev, struct qede_tx_queue *txq)
QED_CHAIN_USE_TO_CONSUME_PRODUCE,
QED_CHAIN_MODE_PBL,
QED_CHAIN_CNT_TYPE_U16,
- NUM_TX_BDS_MAX,
+ TX_RING_SIZE,
sizeof(*p_virt), &txq->tx_pbl);
if (rc)
goto err;
@@ -3752,6 +3762,8 @@ static int qede_open(struct net_device *ndev)
udp_tunnel_get_rx_info(ndev);
+ edev->ops->common->update_drv_state(edev->cdev, true);
+
return 0;
}
@@ -3761,6 +3773,8 @@ static int qede_close(struct net_device *ndev)
qede_unload(edev, QEDE_UNLOAD_NORMAL);
+ edev->ops->common->update_drv_state(edev->cdev, false);
+
return 0;
}
@@ -3821,6 +3835,8 @@ static int qede_set_mac_addr(struct net_device *ndev, void *p)
if (rc)
return rc;
+ edev->ops->common->update_mac(edev->cdev, addr->sa_data);
+
/* Add MAC filter according to the new unicast HW MAC address */
ether_addr_copy(edev->primary_mac, ndev->dev_addr);
return qede_set_ucast_rx_mac(edev, QED_FILTER_XCAST_TYPE_ADD,
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
index e97968e..0b4deb3 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
@@ -575,10 +575,11 @@ void emac_mac_start(struct emac_adapter *adpt)
mac |= TXEN | RXEN; /* enable RX/TX */
- /* We don't have ethtool support yet, so force flow-control mode
- * to 'full' always.
- */
- mac |= TXFC | RXFC;
+ /* Configure MAC flow control to match the PHY's settings. */
+ if (phydev->pause)
+ mac |= RXFC;
+ if (phydev->pause != phydev->asym_pause)
+ mac |= TXFC;
/* setup link speed */
mac &= ~SPEED_MASK;
@@ -1003,6 +1004,12 @@ int emac_mac_up(struct emac_adapter *adpt)
writel((u32)~DIS_INT, adpt->base + EMAC_INT_STATUS);
writel(adpt->irq.mask, adpt->base + EMAC_INT_MASK);
+ /* Enable pause frames. Without this feature, the EMAC has been shown
+ * to receive (and drop) frames with FCS errors at gigabit connections.
+ */
+ adpt->phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+ adpt->phydev->advertising |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+
adpt->phydev->irq = PHY_IGNORE_INTERRUPT;
phy_start(adpt->phydev);
@@ -1021,14 +1028,18 @@ void emac_mac_down(struct emac_adapter *adpt)
napi_disable(&adpt->rx_q.napi);
phy_stop(adpt->phydev);
- phy_disconnect(adpt->phydev);
- /* disable mac irq */
+ /* Interrupts must be disabled before the PHY is disconnected, to
+ * avoid a race condition where adjust_link is null when we get
+ * an interrupt.
+ */
writel(DIS_INT, adpt->base + EMAC_INT_STATUS);
writel(0, adpt->base + EMAC_INT_MASK);
synchronize_irq(adpt->irq.irq);
free_irq(adpt->irq.irq, &adpt->irq);
+ phy_disconnect(adpt->phydev);
+
emac_mac_reset(adpt);
emac_tx_q_descs_free(adpt);
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
index 75c1b53..72fe343 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
@@ -421,7 +421,7 @@ static const struct emac_reg_write sgmii_v2_laned[] = {
/* CDR Settings */
{EMAC_SGMII_LN_UCDR_FO_GAIN_MODE0,
UCDR_STEP_BY_TWO_MODE0 | UCDR_xO_GAIN_MODE(10)},
- {EMAC_SGMII_LN_UCDR_SO_GAIN_MODE0, UCDR_xO_GAIN_MODE(6)},
+ {EMAC_SGMII_LN_UCDR_SO_GAIN_MODE0, UCDR_xO_GAIN_MODE(0)},
{EMAC_SGMII_LN_UCDR_SO_CONFIG, UCDR_ENABLE | UCDR_SO_SATURATION(12)},
/* TX/RX Settings */
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
index e4e1925..8be526a 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -568,6 +568,7 @@ static const struct of_device_id emac_dt_match[] = {
},
{}
};
+MODULE_DEVICE_TABLE(of, emac_dt_match);
#if IS_ENABLED(CONFIG_ACPI)
static const struct acpi_device_id emac_acpi_match[] = {
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index b698ea5..2830190 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -8269,7 +8269,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
if ((sizeof(dma_addr_t) > 4) &&
(use_dac == 1 || (use_dac == -1 && pci_is_pcie(pdev) &&
tp->mac_version >= RTL_GIGA_MAC_VER_18)) &&
- !pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+ !pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) &&
+ !pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64))) {
/* CPlusCmd Dual Access Cycle is only needed for non-PCIe */
if (!pci_is_pcie(pdev))
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 2e81b70..67df4cf 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -1471,7 +1471,7 @@ static int rocker_world_check_init(struct rocker_port *rocker_port)
if (rocker->wops) {
if (rocker->wops->mode != mode) {
dev_err(&rocker->pdev->dev, "hardware has ports in different worlds, which is not supported\n");
- return err;
+ return -EINVAL;
}
return 0;
}
@@ -2534,7 +2534,7 @@ static void rocker_port_dev_addr_init(struct rocker_port *rocker_port)
#define ROCKER_PORT_MAX_MTU 9000
static int rocker_probe_port(struct rocker *rocker, unsigned int port_number)
{
- const struct pci_dev *pdev = rocker->pdev;
+ struct pci_dev *pdev = rocker->pdev;
struct rocker_port *rocker_port;
struct net_device *dev;
int err;
@@ -2542,6 +2542,7 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number)
dev = alloc_etherdev(sizeof(struct rocker_port));
if (!dev)
return -ENOMEM;
+ SET_NETDEV_DEV(dev, &pdev->dev);
rocker_port = netdev_priv(dev);
rocker_port->dev = dev;
rocker_port->rocker = rocker;
diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c
index 431a608..4ca4613 100644
--- a/drivers/net/ethernet/rocker/rocker_ofdpa.c
+++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c
@@ -1493,8 +1493,6 @@ static int ofdpa_port_ipv4_nh(struct ofdpa_port *ofdpa_port,
spin_lock_irqsave(&ofdpa->neigh_tbl_lock, lock_flags);
found = ofdpa_neigh_tbl_find(ofdpa, ip_addr);
- if (found)
- *index = found->index;
updating = found && adding;
removing = found && !adding;
@@ -1508,9 +1506,11 @@ static int ofdpa_port_ipv4_nh(struct ofdpa_port *ofdpa_port,
resolved = false;
} else if (removing) {
ofdpa_neigh_del(trans, found);
+ *index = found->index;
} else if (updating) {
ofdpa_neigh_update(found, trans, NULL, false);
resolved = !is_zero_ether_addr(found->eth_dst);
+ *index = found->index;
} else {
err = -ENOENT;
}
diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile
index ce8470fe7..b3b620f 100644
--- a/drivers/net/ethernet/sfc/Makefile
+++ b/drivers/net/ethernet/sfc/Makefile
@@ -1,7 +1,7 @@
sfc-y += efx.o nic.o farch.o falcon.o siena.o ef10.o tx.o \
rx.o selftest.o ethtool.o qt202x_phy.o mdio_10g.o \
tenxpress.o txc43128_phy.o falcon_boards.o \
- mcdi.o mcdi_port.o mcdi_mon.o ptp.o
+ mcdi.o mcdi_port.o mcdi_mon.o ptp.o tx_tso.o
sfc-$(CONFIG_SFC_MTD) += mtd.o
sfc-$(CONFIG_SFC_SRIOV) += sriov.o siena_sriov.o ef10_sriov.o
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 00279da..0f58ea8 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -2086,6 +2086,92 @@ static inline void efx_ef10_push_tx_desc(struct efx_tx_queue *tx_queue,
ER_DZ_TX_DESC_UPD, tx_queue->queue);
}
+/* Add Firmware-Assisted TSO v2 option descriptors to a queue.
+ */
+static int efx_ef10_tx_tso_desc(struct efx_tx_queue *tx_queue,
+ struct sk_buff *skb,
+ bool *data_mapped)
+{
+ struct efx_tx_buffer *buffer;
+ struct tcphdr *tcp;
+ struct iphdr *ip;
+
+ u16 ipv4_id;
+ u32 seqnum;
+ u32 mss;
+
+ EFX_BUG_ON_PARANOID(tx_queue->tso_version != 2);
+
+ mss = skb_shinfo(skb)->gso_size;
+
+ if (unlikely(mss < 4)) {
+ WARN_ONCE(1, "MSS of %u is too small for TSO v2\n", mss);
+ return -EINVAL;
+ }
+
+ ip = ip_hdr(skb);
+ if (ip->version == 4) {
+ /* Modify IPv4 header if needed. */
+ ip->tot_len = 0;
+ ip->check = 0;
+ ipv4_id = ip->id;
+ } else {
+ /* Modify IPv6 header if needed. */
+ struct ipv6hdr *ipv6 = ipv6_hdr(skb);
+
+ ipv6->payload_len = 0;
+ ipv4_id = 0;
+ }
+
+ tcp = tcp_hdr(skb);
+ seqnum = ntohl(tcp->seq);
+
+ buffer = efx_tx_queue_get_insert_buffer(tx_queue);
+
+ buffer->flags = EFX_TX_BUF_OPTION;
+ buffer->len = 0;
+ buffer->unmap_len = 0;
+ EFX_POPULATE_QWORD_5(buffer->option,
+ ESF_DZ_TX_DESC_IS_OPT, 1,
+ ESF_DZ_TX_OPTION_TYPE, ESE_DZ_TX_OPTION_DESC_TSO,
+ ESF_DZ_TX_TSO_OPTION_TYPE,
+ ESE_DZ_TX_TSO_OPTION_DESC_FATSO2A,
+ ESF_DZ_TX_TSO_IP_ID, ipv4_id,
+ ESF_DZ_TX_TSO_TCP_SEQNO, seqnum
+ );
+ ++tx_queue->insert_count;
+
+ buffer = efx_tx_queue_get_insert_buffer(tx_queue);
+
+ buffer->flags = EFX_TX_BUF_OPTION;
+ buffer->len = 0;
+ buffer->unmap_len = 0;
+ EFX_POPULATE_QWORD_4(buffer->option,
+ ESF_DZ_TX_DESC_IS_OPT, 1,
+ ESF_DZ_TX_OPTION_TYPE, ESE_DZ_TX_OPTION_DESC_TSO,
+ ESF_DZ_TX_TSO_OPTION_TYPE,
+ ESE_DZ_TX_TSO_OPTION_DESC_FATSO2B,
+ ESF_DZ_TX_TSO_TCP_MSS, mss
+ );
+ ++tx_queue->insert_count;
+
+ return 0;
+}
+
+static u32 efx_ef10_tso_versions(struct efx_nic *efx)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ u32 tso_versions = 0;
+
+ if (nic_data->datapath_caps &
+ (1 << MC_CMD_GET_CAPABILITIES_OUT_TX_TSO_LBN))
+ tso_versions |= BIT(1);
+ if (nic_data->datapath_caps2 &
+ (1 << MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_LBN))
+ tso_versions |= BIT(2);
+ return tso_versions;
+}
+
static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
{
MCDI_DECLARE_BUF(inbuf, MC_CMD_INIT_TXQ_IN_LEN(EFX_MAX_DMAQ_SIZE * 8 /
@@ -2095,6 +2181,7 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
struct efx_channel *channel = tx_queue->channel;
struct efx_nic *efx = tx_queue->efx;
struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ bool tso_v2 = false;
size_t inlen;
dma_addr_t dma_addr;
efx_qword_t *txd;
@@ -2102,13 +2189,21 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
int i;
BUILD_BUG_ON(MC_CMD_INIT_TXQ_OUT_LEN != 0);
+ /* TSOv2 is a limited resource that can only be configured on a limited
+ * number of queues. TSO without checksum offload is not really a thing,
+ * so we only enable it for those queues.
+ */
+ if (csum_offload && (nic_data->datapath_caps2 &
+ (1 << MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_LBN))) {
+ tso_v2 = true;
+ netif_dbg(efx, hw, efx->net_dev, "Using TSOv2 for channel %u\n",
+ channel->channel);
+ }
+
MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_SIZE, tx_queue->ptr_mask + 1);
MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_TARGET_EVQ, channel->channel);
MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_LABEL, tx_queue->queue);
MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_INSTANCE, tx_queue->queue);
- MCDI_POPULATE_DWORD_2(inbuf, INIT_TXQ_IN_FLAGS,
- INIT_TXQ_IN_FLAG_IP_CSUM_DIS, !csum_offload,
- INIT_TXQ_IN_FLAG_TCP_CSUM_DIS, !csum_offload);
MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_OWNER_ID, 0);
MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_PORT_ID, nic_data->vport_id);
@@ -2124,10 +2219,30 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
inlen = MC_CMD_INIT_TXQ_IN_LEN(entries);
- rc = efx_mcdi_rpc(efx, MC_CMD_INIT_TXQ, inbuf, inlen,
- NULL, 0, NULL);
- if (rc)
- goto fail;
+ do {
+ MCDI_POPULATE_DWORD_3(inbuf, INIT_TXQ_IN_FLAGS,
+ /* This flag was removed from mcdi_pcol.h for
+ * the non-_EXT version of INIT_TXQ. However,
+ * firmware still honours it.
+ */
+ INIT_TXQ_EXT_IN_FLAG_TSOV2_EN, tso_v2,
+ INIT_TXQ_IN_FLAG_IP_CSUM_DIS, !csum_offload,
+ INIT_TXQ_IN_FLAG_TCP_CSUM_DIS, !csum_offload);
+
+ rc = efx_mcdi_rpc_quiet(efx, MC_CMD_INIT_TXQ, inbuf, inlen,
+ NULL, 0, NULL);
+ if (rc == -ENOSPC && tso_v2) {
+ /* Retry without TSOv2 if we're short on contexts. */
+ tso_v2 = false;
+ netif_warn(efx, probe, efx->net_dev,
+ "TSOv2 context not available to segment in hardware. TCP performance may be reduced.\n");
+ } else if (rc) {
+ efx_mcdi_display_error(efx, MC_CMD_INIT_TXQ,
+ MC_CMD_INIT_TXQ_EXT_IN_LEN,
+ NULL, 0, rc);
+ goto fail;
+ }
+ } while (rc);
/* A previous user of this TX queue might have set us up the
* bomb by writing a descriptor to the TX push collector but
@@ -2146,8 +2261,11 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
ESF_DZ_TX_OPTION_IP_CSUM, csum_offload);
tx_queue->write_count = 1;
- if (nic_data->datapath_caps &
- (1 << MC_CMD_GET_CAPABILITIES_OUT_TX_TSO_LBN)) {
+ if (tso_v2) {
+ tx_queue->handle_tso = efx_ef10_tx_tso_desc;
+ tx_queue->tso_version = 2;
+ } else if (nic_data->datapath_caps &
+ (1 << MC_CMD_GET_CAPABILITIES_OUT_TX_TSO_LBN)) {
tx_queue->tso_version = 1;
}
@@ -2202,6 +2320,25 @@ static inline void efx_ef10_notify_tx_desc(struct efx_tx_queue *tx_queue)
ER_DZ_TX_DESC_UPD_DWORD, tx_queue->queue);
}
+#define EFX_EF10_MAX_TX_DESCRIPTOR_LEN 0x3fff
+
+static unsigned int efx_ef10_tx_limit_len(struct efx_tx_queue *tx_queue,
+ dma_addr_t dma_addr, unsigned int len)
+{
+ if (len > EFX_EF10_MAX_TX_DESCRIPTOR_LEN) {
+ /* If we need to break across multiple descriptors we should
+ * stop at a page boundary. This assumes the length limit is
+ * greater than the page size.
+ */
+ dma_addr_t end = dma_addr + EFX_EF10_MAX_TX_DESCRIPTOR_LEN;
+
+ BUILD_BUG_ON(EFX_EF10_MAX_TX_DESCRIPTOR_LEN < EFX_PAGE_SIZE);
+ len = (end & (~(EFX_PAGE_SIZE - 1))) - dma_addr;
+ }
+
+ return len;
+}
+
static void efx_ef10_tx_write(struct efx_tx_queue *tx_queue)
{
unsigned int old_write_count = tx_queue->write_count;
@@ -2245,6 +2382,86 @@ static void efx_ef10_tx_write(struct efx_tx_queue *tx_queue)
}
}
+#define RSS_MODE_HASH_ADDRS (1 << RSS_MODE_HASH_SRC_ADDR_LBN |\
+ 1 << RSS_MODE_HASH_DST_ADDR_LBN)
+#define RSS_MODE_HASH_PORTS (1 << RSS_MODE_HASH_SRC_PORT_LBN |\
+ 1 << RSS_MODE_HASH_DST_PORT_LBN)
+#define RSS_CONTEXT_FLAGS_DEFAULT (1 << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_IPV4_EN_LBN |\
+ 1 << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_TCPV4_EN_LBN |\
+ 1 << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_IPV6_EN_LBN |\
+ 1 << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_TCPV6_EN_LBN |\
+ (RSS_MODE_HASH_ADDRS | RSS_MODE_HASH_PORTS) << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TCP_IPV4_RSS_MODE_LBN |\
+ RSS_MODE_HASH_ADDRS << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_UDP_IPV4_RSS_MODE_LBN |\
+ RSS_MODE_HASH_ADDRS << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_OTHER_IPV4_RSS_MODE_LBN |\
+ (RSS_MODE_HASH_ADDRS | RSS_MODE_HASH_PORTS) << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TCP_IPV6_RSS_MODE_LBN |\
+ RSS_MODE_HASH_ADDRS << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_UDP_IPV6_RSS_MODE_LBN |\
+ RSS_MODE_HASH_ADDRS << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_OTHER_IPV6_RSS_MODE_LBN)
+
+static int efx_ef10_get_rss_flags(struct efx_nic *efx, u32 context, u32 *flags)
+{
+ /* Firmware had a bug (sfc bug 61952) where it would not actually
+ * fill in the flags field in the response to MC_CMD_RSS_CONTEXT_GET_FLAGS.
+ * This meant that it would always contain whatever was previously
+ * in the MCDI buffer. Fortunately, all firmware versions with
+ * this bug have the same default flags value for a newly-allocated
+ * RSS context, and the only time we want to get the flags is just
+ * after allocating. Moreover, the response has a 32-bit hole
+ * where the context ID would be in the request, so we can use an
+ * overlength buffer in the request and pre-fill the flags field
+ * with what we believe the default to be. Thus if the firmware
+ * has the bug, it will leave our pre-filled value in the flags
+ * field of the response, and we will get the right answer.
+ *
+ * However, this does mean that this function should NOT be used if
+ * the RSS context flags might not be their defaults - it is ONLY
+ * reliably correct for a newly-allocated RSS context.
+ */
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_LEN);
+ size_t outlen;
+ int rc;
+
+ /* Check we have a hole for the context ID */
+ BUILD_BUG_ON(MC_CMD_RSS_CONTEXT_GET_FLAGS_IN_LEN != MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_FLAGS_OFST);
+ MCDI_SET_DWORD(inbuf, RSS_CONTEXT_GET_FLAGS_IN_RSS_CONTEXT_ID, context);
+ MCDI_SET_DWORD(inbuf, RSS_CONTEXT_GET_FLAGS_OUT_FLAGS,
+ RSS_CONTEXT_FLAGS_DEFAULT);
+ rc = efx_mcdi_rpc(efx, MC_CMD_RSS_CONTEXT_GET_FLAGS, inbuf,
+ sizeof(inbuf), outbuf, sizeof(outbuf), &outlen);
+ if (rc == 0) {
+ if (outlen < MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_LEN)
+ rc = -EIO;
+ else
+ *flags = MCDI_DWORD(outbuf, RSS_CONTEXT_GET_FLAGS_OUT_FLAGS);
+ }
+ return rc;
+}
+
+/* Attempt to enable 4-tuple UDP hashing on the specified RSS context.
+ * If we fail, we just leave the RSS context at its default hash settings,
+ * which is safe but may slightly reduce performance.
+ * Defaults are 4-tuple for TCP and 2-tuple for UDP and other-IP, so we
+ * just need to set the UDP ports flags (for both IP versions).
+ */
+static void efx_ef10_set_rss_flags(struct efx_nic *efx, u32 context)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_LEN);
+ u32 flags;
+
+ BUILD_BUG_ON(MC_CMD_RSS_CONTEXT_SET_FLAGS_OUT_LEN != 0);
+
+ if (efx_ef10_get_rss_flags(efx, context, &flags) != 0)
+ return;
+ MCDI_SET_DWORD(inbuf, RSS_CONTEXT_SET_FLAGS_IN_RSS_CONTEXT_ID, context);
+ flags |= RSS_MODE_HASH_PORTS << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_UDP_IPV4_RSS_MODE_LBN;
+ flags |= RSS_MODE_HASH_PORTS << MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_UDP_IPV6_RSS_MODE_LBN;
+ MCDI_SET_DWORD(inbuf, RSS_CONTEXT_SET_FLAGS_IN_FLAGS, flags);
+ if (!efx_mcdi_rpc(efx, MC_CMD_RSS_CONTEXT_SET_FLAGS, inbuf, sizeof(inbuf),
+ NULL, 0, NULL))
+ /* Succeeded, so UDP 4-tuple is now enabled */
+ efx->rx_hash_udp_4tuple = true;
+}
+
static int efx_ef10_alloc_rss_context(struct efx_nic *efx, u32 *context,
bool exclusive, unsigned *context_size)
{
@@ -2290,6 +2507,10 @@ static int efx_ef10_alloc_rss_context(struct efx_nic *efx, u32 *context,
if (context_size)
*context_size = rss_spread;
+ if (nic_data->datapath_caps &
+ 1 << MC_CMD_GET_CAPABILITIES_OUT_ADDITIONAL_RSS_MODES_LBN)
+ efx_ef10_set_rss_flags(efx, *context);
+
return 0;
}
@@ -5385,6 +5606,7 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = {
.tx_init = efx_ef10_tx_init,
.tx_remove = efx_ef10_tx_remove,
.tx_write = efx_ef10_tx_write,
+ .tx_limit_len = efx_ef10_tx_limit_len,
.rx_push_rss_config = efx_ef10_vf_rx_push_rss_config,
.rx_probe = efx_ef10_rx_probe,
.rx_init = efx_ef10_rx_init,
@@ -5491,6 +5713,7 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
.tx_init = efx_ef10_tx_init,
.tx_remove = efx_ef10_tx_remove,
.tx_write = efx_ef10_tx_write,
+ .tx_limit_len = efx_ef10_tx_limit_len,
.rx_push_rss_config = efx_ef10_pf_rx_push_rss_config,
.rx_probe = efx_ef10_rx_probe,
.rx_init = efx_ef10_rx_init,
@@ -5550,6 +5773,7 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
#endif
.get_mac_address = efx_ef10_get_mac_address_pf,
.set_mac_address = efx_ef10_set_mac_address,
+ .tso_versions = efx_ef10_tso_versions,
.revision = EFX_REV_HUNT_A0,
.max_dma_mask = DMA_BIT_MASK(ESF_DZ_TX_KER_BUF_ADDR_WIDTH),
diff --git a/drivers/net/ethernet/sfc/ef10_regs.h b/drivers/net/ethernet/sfc/ef10_regs.h
index 62a55dd..2c4bf94 100644
--- a/drivers/net/ethernet/sfc/ef10_regs.h
+++ b/drivers/net/ethernet/sfc/ef10_regs.h
@@ -1,6 +1,6 @@
/****************************************************************************
* Driver for Solarflare network controllers and boards
- * Copyright 2012-2013 Solarflare Communications Inc.
+ * Copyright 2012-2015 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -147,8 +147,14 @@
#define ESF_DZ_RX_OVERRIDE_HOLDOFF_WIDTH 1
#define ESF_DZ_RX_DROP_EVENT_LBN 58
#define ESF_DZ_RX_DROP_EVENT_WIDTH 1
-#define ESF_DZ_RX_EV_RSVD2_LBN 54
-#define ESF_DZ_RX_EV_RSVD2_WIDTH 4
+#define ESF_DD_RX_EV_RSVD2_LBN 54
+#define ESF_DD_RX_EV_RSVD2_WIDTH 4
+#define ESF_EZ_RX_TCP_UDP_INNER_CHKSUM_ERR_LBN 57
+#define ESF_EZ_RX_TCP_UDP_INNER_CHKSUM_ERR_WIDTH 1
+#define ESF_EZ_RX_IP_INNER_CHKSUM_ERR_LBN 56
+#define ESF_EZ_RX_IP_INNER_CHKSUM_ERR_WIDTH 1
+#define ESF_EZ_RX_EV_RSVD2_LBN 54
+#define ESF_EZ_RX_EV_RSVD2_WIDTH 2
#define ESF_DZ_RX_EV_SOFT2_LBN 52
#define ESF_DZ_RX_EV_SOFT2_WIDTH 2
#define ESF_DZ_RX_DSC_PTR_LBITS_LBN 48
@@ -192,12 +198,21 @@
#define ESF_DZ_RX_MAC_CLASS_WIDTH 1
#define ESE_DZ_MAC_CLASS_MCAST 1
#define ESE_DZ_MAC_CLASS_UCAST 0
-#define ESF_DZ_RX_EV_SOFT1_LBN 32
-#define ESF_DZ_RX_EV_SOFT1_WIDTH 3
-#define ESF_DZ_RX_EV_RSVD1_LBN 31
-#define ESF_DZ_RX_EV_RSVD1_WIDTH 1
-#define ESF_DZ_RX_ABORT_LBN 30
-#define ESF_DZ_RX_ABORT_WIDTH 1
+#define ESF_DD_RX_EV_SOFT1_LBN 32
+#define ESF_DD_RX_EV_SOFT1_WIDTH 3
+#define ESF_EZ_RX_EV_SOFT1_LBN 34
+#define ESF_EZ_RX_EV_SOFT1_WIDTH 1
+#define ESF_EZ_RX_ENCAP_HDR_LBN 32
+#define ESF_EZ_RX_ENCAP_HDR_WIDTH 2
+#define ESE_EZ_ENCAP_HDR_GRE 2
+#define ESE_EZ_ENCAP_HDR_VXLAN 1
+#define ESE_EZ_ENCAP_HDR_NONE 0
+#define ESF_DD_RX_EV_RSVD1_LBN 30
+#define ESF_DD_RX_EV_RSVD1_WIDTH 2
+#define ESF_EZ_RX_EV_RSVD1_LBN 31
+#define ESF_EZ_RX_EV_RSVD1_WIDTH 1
+#define ESF_EZ_RX_ABORT_LBN 30
+#define ESF_EZ_RX_ABORT_WIDTH 1
#define ESF_DZ_RX_ECC_ERR_LBN 29
#define ESF_DZ_RX_ECC_ERR_WIDTH 1
#define ESF_DZ_RX_CRC1_ERR_LBN 28
@@ -235,6 +250,12 @@
#define ESE_DZ_TX_OPTION_DESC_TSO 7
#define ESE_DZ_TX_OPTION_DESC_VLAN 6
#define ESE_DZ_TX_OPTION_DESC_CRC_CSUM 0
+#define ESF_DZ_TX_OPTION_TS_AT_TXDP_LBN 8
+#define ESF_DZ_TX_OPTION_TS_AT_TXDP_WIDTH 1
+#define ESF_DZ_TX_OPTION_INNER_UDP_TCP_CSUM_LBN 7
+#define ESF_DZ_TX_OPTION_INNER_UDP_TCP_CSUM_WIDTH 1
+#define ESF_DZ_TX_OPTION_INNER_IP_CSUM_LBN 6
+#define ESF_DZ_TX_OPTION_INNER_IP_CSUM_WIDTH 1
#define ESF_DZ_TX_TIMESTAMP_LBN 5
#define ESF_DZ_TX_TIMESTAMP_WIDTH 1
#define ESF_DZ_TX_OPTION_CRC_MODE_LBN 2
@@ -257,14 +278,22 @@
#define ESF_DZ_TX_OVERRIDE_HOLDOFF_WIDTH 1
#define ESF_DZ_TX_DROP_EVENT_LBN 58
#define ESF_DZ_TX_DROP_EVENT_WIDTH 1
-#define ESF_DZ_TX_EV_RSVD_LBN 48
-#define ESF_DZ_TX_EV_RSVD_WIDTH 10
+#define ESF_DD_TX_EV_RSVD_LBN 48
+#define ESF_DD_TX_EV_RSVD_WIDTH 10
+#define ESF_EZ_TCP_UDP_INNER_CHKSUM_ERR_LBN 57
+#define ESF_EZ_TCP_UDP_INNER_CHKSUM_ERR_WIDTH 1
+#define ESF_EZ_IP_INNER_CHKSUM_ERR_LBN 56
+#define ESF_EZ_IP_INNER_CHKSUM_ERR_WIDTH 1
+#define ESF_EZ_TX_EV_RSVD_LBN 48
+#define ESF_EZ_TX_EV_RSVD_WIDTH 8
#define ESF_DZ_TX_SOFT2_LBN 32
#define ESF_DZ_TX_SOFT2_WIDTH 16
-#define ESF_DZ_TX_CAN_MERGE_LBN 31
-#define ESF_DZ_TX_CAN_MERGE_WIDTH 1
-#define ESF_DZ_TX_SOFT1_LBN 24
-#define ESF_DZ_TX_SOFT1_WIDTH 7
+#define ESF_DD_TX_SOFT1_LBN 24
+#define ESF_DD_TX_SOFT1_WIDTH 8
+#define ESF_EZ_TX_CAN_MERGE_LBN 31
+#define ESF_EZ_TX_CAN_MERGE_WIDTH 1
+#define ESF_EZ_TX_SOFT1_LBN 24
+#define ESF_EZ_TX_SOFT1_WIDTH 7
#define ESF_DZ_TX_QLABEL_LBN 16
#define ESF_DZ_TX_QLABEL_WIDTH 5
#define ESF_DZ_TX_DESCR_INDX_LBN 0
@@ -301,6 +330,10 @@
#define ESE_DZ_TX_OPTION_DESC_TSO 7
#define ESE_DZ_TX_OPTION_DESC_VLAN 6
#define ESE_DZ_TX_OPTION_DESC_CRC_CSUM 0
+#define ESF_DZ_TX_TSO_OPTION_TYPE_LBN 56
+#define ESF_DZ_TX_TSO_OPTION_TYPE_WIDTH 4
+#define ESE_DZ_TX_TSO_OPTION_DESC_ENCAP 1
+#define ESE_DZ_TX_TSO_OPTION_DESC_NORMAL 0
#define ESF_DZ_TX_TSO_TCP_FLAGS_LBN 48
#define ESF_DZ_TX_TSO_TCP_FLAGS_WIDTH 8
#define ESF_DZ_TX_TSO_IP_ID_LBN 32
@@ -308,6 +341,46 @@
#define ESF_DZ_TX_TSO_TCP_SEQNO_LBN 0
#define ESF_DZ_TX_TSO_TCP_SEQNO_WIDTH 32
+/* TX_TSO_FATSO2A_DESC */
+#define ESF_DZ_TX_DESC_IS_OPT_LBN 63
+#define ESF_DZ_TX_DESC_IS_OPT_WIDTH 1
+#define ESF_DZ_TX_OPTION_TYPE_LBN 60
+#define ESF_DZ_TX_OPTION_TYPE_WIDTH 3
+#define ESE_DZ_TX_OPTION_DESC_TSO 7
+#define ESE_DZ_TX_OPTION_DESC_VLAN 6
+#define ESE_DZ_TX_OPTION_DESC_CRC_CSUM 0
+#define ESF_DZ_TX_TSO_OPTION_TYPE_LBN 56
+#define ESF_DZ_TX_TSO_OPTION_TYPE_WIDTH 4
+#define ESE_DZ_TX_TSO_OPTION_DESC_FATSO2B 3
+#define ESE_DZ_TX_TSO_OPTION_DESC_FATSO2A 2
+#define ESE_DZ_TX_TSO_OPTION_DESC_ENCAP 1
+#define ESE_DZ_TX_TSO_OPTION_DESC_NORMAL 0
+#define ESF_DZ_TX_TSO_IP_ID_LBN 32
+#define ESF_DZ_TX_TSO_IP_ID_WIDTH 16
+#define ESF_DZ_TX_TSO_TCP_SEQNO_LBN 0
+#define ESF_DZ_TX_TSO_TCP_SEQNO_WIDTH 32
+
+
+/* TX_TSO_FATSO2B_DESC */
+#define ESF_DZ_TX_DESC_IS_OPT_LBN 63
+#define ESF_DZ_TX_DESC_IS_OPT_WIDTH 1
+#define ESF_DZ_TX_OPTION_TYPE_LBN 60
+#define ESF_DZ_TX_OPTION_TYPE_WIDTH 3
+#define ESE_DZ_TX_OPTION_DESC_TSO 7
+#define ESE_DZ_TX_OPTION_DESC_VLAN 6
+#define ESE_DZ_TX_OPTION_DESC_CRC_CSUM 0
+#define ESF_DZ_TX_TSO_OPTION_TYPE_LBN 56
+#define ESF_DZ_TX_TSO_OPTION_TYPE_WIDTH 4
+#define ESE_DZ_TX_TSO_OPTION_DESC_FATSO2B 3
+#define ESE_DZ_TX_TSO_OPTION_DESC_FATSO2A 2
+#define ESE_DZ_TX_TSO_OPTION_DESC_ENCAP 1
+#define ESE_DZ_TX_TSO_OPTION_DESC_NORMAL 0
+#define ESF_DZ_TX_TSO_OUTER_IP_ID_LBN 0
+#define ESF_DZ_TX_TSO_OUTER_IP_ID_WIDTH 16
+#define ESF_DZ_TX_TSO_TCP_MSS_LBN 32
+#define ESF_DZ_TX_TSO_TCP_MSS_WIDTH 16
+
+
/*************************************************************************/
/* TX_DESC_UPD_REG: Transmit descriptor update register.
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index b626da6..756a0964 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -485,6 +485,9 @@ efx_copy_channel(const struct efx_channel *old_channel)
*channel = *old_channel;
channel->napi_dev = NULL;
+ INIT_HLIST_NODE(&channel->napi_str.napi_hash_node);
+ channel->napi_str.napi_id = 0;
+ channel->napi_str.state = 0;
memset(&channel->eventq, 0, sizeof(channel->eventq));
for (j = 0; j < EFX_TXQ_TYPES; j++) {
@@ -2110,10 +2113,9 @@ static void efx_init_napi(struct efx_nic *efx)
static void efx_fini_napi_channel(struct efx_channel *channel)
{
- if (channel->napi_dev) {
+ if (channel->napi_dev)
netif_napi_del(&channel->napi_str);
- napi_hash_del(&channel->napi_str);
- }
+
channel->napi_dev = NULL;
}
@@ -3198,23 +3200,6 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
efx = netdev_priv(net_dev);
efx->type = (const struct efx_nic_type *) entry->driver_data;
efx->fixed_features |= NETIF_F_HIGHDMA;
- net_dev->features |= (efx->type->offload_features | NETIF_F_SG |
- NETIF_F_TSO | NETIF_F_RXCSUM);
- if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
- net_dev->features |= NETIF_F_TSO6;
- /* Mask for features that also apply to VLAN devices */
- net_dev->vlan_features |= (NETIF_F_HW_CSUM | NETIF_F_SG |
- NETIF_F_HIGHDMA | NETIF_F_ALL_TSO |
- NETIF_F_RXCSUM);
-
- net_dev->hw_features = net_dev->features & ~efx->fixed_features;
-
- /* Disable VLAN filtering by default. It may be enforced if
- * the feature is fixed (i.e. VLAN filters are required to
- * receive VLAN tagged packets due to vPort restrictions).
- */
- net_dev->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
- net_dev->features |= efx->fixed_features;
pci_set_drvdata(pci_dev, efx);
SET_NETDEV_DEV(net_dev, &pci_dev->dev);
@@ -3237,6 +3222,27 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
if (rc)
goto fail3;
+ net_dev->features |= (efx->type->offload_features | NETIF_F_SG |
+ NETIF_F_TSO | NETIF_F_RXCSUM);
+ if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
+ net_dev->features |= NETIF_F_TSO6;
+ /* Check whether device supports TSO */
+ if (!efx->type->tso_versions || !efx->type->tso_versions(efx))
+ net_dev->features &= ~NETIF_F_ALL_TSO;
+ /* Mask for features that also apply to VLAN devices */
+ net_dev->vlan_features |= (NETIF_F_HW_CSUM | NETIF_F_SG |
+ NETIF_F_HIGHDMA | NETIF_F_ALL_TSO |
+ NETIF_F_RXCSUM);
+
+ net_dev->hw_features = net_dev->features & ~efx->fixed_features;
+
+ /* Disable VLAN filtering by default. It may be enforced if
+ * the feature is fixed (i.e. VLAN filters are required to
+ * receive VLAN tagged packets due to vPort restrictions).
+ */
+ net_dev->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+ net_dev->features |= efx->fixed_features;
+
rc = efx_register_netdev(efx);
if (rc)
goto fail4;
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 445ccdb..740cdf0 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -69,8 +69,10 @@ static const struct efx_sw_stat_desc efx_sw_stat_desc[] = {
EFX_ETHTOOL_UINT_TXQ_STAT(tso_bursts),
EFX_ETHTOOL_UINT_TXQ_STAT(tso_long_headers),
EFX_ETHTOOL_UINT_TXQ_STAT(tso_packets),
+ EFX_ETHTOOL_UINT_TXQ_STAT(tso_fallbacks),
EFX_ETHTOOL_UINT_TXQ_STAT(pushes),
EFX_ETHTOOL_UINT_TXQ_STAT(pio_packets),
+ EFX_ETHTOOL_UINT_TXQ_STAT(cb_packets),
EFX_ETHTOOL_ATOMIC_NIC_ERROR_STAT(rx_reset),
EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_tobe_disc),
EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_ip_hdr_chksum_err),
@@ -968,20 +970,24 @@ efx_ethtool_get_rxnfc(struct net_device *net_dev,
info->data = 0;
switch (info->flow_type) {
- case TCP_V4_FLOW:
- info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
- /* fall through */
case UDP_V4_FLOW:
+ if (efx->rx_hash_udp_4tuple)
+ /* fall through */
+ case TCP_V4_FLOW:
+ info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ /* fall through */
case SCTP_V4_FLOW:
case AH_ESP_V4_FLOW:
case IPV4_FLOW:
info->data |= RXH_IP_SRC | RXH_IP_DST;
min_revision = EFX_REV_FALCON_B0;
break;
- case TCP_V6_FLOW:
- info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
- /* fall through */
case UDP_V6_FLOW:
+ if (efx->rx_hash_udp_4tuple)
+ /* fall through */
+ case TCP_V6_FLOW:
+ info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ /* fall through */
case SCTP_V6_FLOW:
case AH_ESP_V6_FLOW:
case IPV6_FLOW:
diff --git a/drivers/net/ethernet/sfc/falcon.c b/drivers/net/ethernet/sfc/falcon.c
index 1a70926..6a1e74b 100644
--- a/drivers/net/ethernet/sfc/falcon.c
+++ b/drivers/net/ethernet/sfc/falcon.c
@@ -2750,6 +2750,7 @@ const struct efx_nic_type falcon_a1_nic_type = {
.tx_init = efx_farch_tx_init,
.tx_remove = efx_farch_tx_remove,
.tx_write = efx_farch_tx_write,
+ .tx_limit_len = efx_farch_tx_limit_len,
.rx_push_rss_config = dummy_rx_push_rss_config,
.rx_probe = efx_farch_rx_probe,
.rx_init = efx_farch_rx_init,
@@ -2849,6 +2850,7 @@ const struct efx_nic_type falcon_b0_nic_type = {
.tx_init = efx_farch_tx_init,
.tx_remove = efx_farch_tx_remove,
.tx_write = efx_farch_tx_write,
+ .tx_limit_len = efx_farch_tx_limit_len,
.rx_push_rss_config = falcon_b0_rx_push_rss_config,
.rx_probe = efx_farch_rx_probe,
.rx_init = efx_farch_rx_init,
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index 4762ec4..3d5b91b 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -356,6 +356,21 @@ void efx_farch_tx_write(struct efx_tx_queue *tx_queue)
}
}
+unsigned int efx_farch_tx_limit_len(struct efx_tx_queue *tx_queue,
+ dma_addr_t dma_addr, unsigned int len)
+{
+ /* Don't cross 4K boundaries with descriptors. */
+ unsigned int limit = (~dma_addr & (EFX_PAGE_SIZE - 1)) + 1;
+
+ len = min(limit, len);
+
+ if (EFX_WORKAROUND_5391(tx_queue->efx) && (dma_addr & 0xf))
+ len = min_t(unsigned int, len, 512 - (dma_addr & 0xf));
+
+ return len;
+}
+
+
/* Allocate hardware resources for a TX queue */
int efx_farch_tx_probe(struct efx_tx_queue *tx_queue)
{
diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h
index ccceafc..35cc3d4 100644
--- a/drivers/net/ethernet/sfc/mcdi_pcol.h
+++ b/drivers/net/ethernet/sfc/mcdi_pcol.h
@@ -276,6 +276,9 @@
/* The clock whose frequency you've attempted to set set
* doesn't exist on this NIC */
#define MC_CMD_ERR_NO_CLOCK 0x1015
+/* Returned by MC_CMD_TESTASSERT if the action that should
+ * have caused an assertion failed to do so. */
+#define MC_CMD_ERR_UNREACHABLE 0x1016
#define MC_CMD_ERR_CODE_OFST 0
@@ -933,6 +936,8 @@
#define MC_CMD_COPYCODE_IN_BOOT_MAGIC_SKIP_BOOT_ICORE_SYNC_WIDTH 1
#define MC_CMD_COPYCODE_IN_BOOT_MAGIC_FORCE_STANDALONE_LBN 5
#define MC_CMD_COPYCODE_IN_BOOT_MAGIC_FORCE_STANDALONE_WIDTH 1
+#define MC_CMD_COPYCODE_IN_BOOT_MAGIC_DISABLE_XIP_LBN 6
+#define MC_CMD_COPYCODE_IN_BOOT_MAGIC_DISABLE_XIP_WIDTH 1
/* Destination address */
#define MC_CMD_COPYCODE_IN_DEST_ADDR_OFST 4
#define MC_CMD_COPYCODE_IN_NUMWORDS_OFST 8
@@ -1659,6 +1664,8 @@
#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_CAPABILITIES_OFST 8
#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_REPORT_SYNC_STATUS_LBN 0
#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_REPORT_SYNC_STATUS_WIDTH 1
+#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_RX_TSTAMP_OOB_LBN 1
+#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_RX_TSTAMP_OOB_WIDTH 1
#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_RESERVED0_OFST 12
#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_RESERVED1_OFST 16
#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_RESERVED2_OFST 20
@@ -2211,6 +2218,10 @@
#define MC_CMD_FW_HIGH_TX_RATE 0x3
/* enum: Reserved value */
#define MC_CMD_FW_PACKED_STREAM_HASH_MODE_1 0x4
+/* enum: Prefer to use firmware with additional "rules engine" filtering
+ * support
+ */
+#define MC_CMD_FW_RULES_ENGINE 0x5
/* enum: Only this option is allowed for non-admin functions */
#define MC_CMD_FW_DONT_CARE 0xffffffff
@@ -3654,12 +3665,27 @@
#define MC_CMD_0x38_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-/* MC_CMD_NVRAM_UPDATE_START_IN msgrequest */
+/* MC_CMD_NVRAM_UPDATE_START_IN msgrequest: Legacy NVRAM_UPDATE_START request.
+ * Use NVRAM_UPDATE_START_V2_IN in new code
+ */
#define MC_CMD_NVRAM_UPDATE_START_IN_LEN 4
#define MC_CMD_NVRAM_UPDATE_START_IN_TYPE_OFST 0
/* Enum values, see field(s): */
/* MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
+/* MC_CMD_NVRAM_UPDATE_START_V2_IN msgrequest: Extended NVRAM_UPDATE_START
+ * request with additional flags indicating version of command in use. See
+ * MC_CMD_NVRAM_UPDATE_FINISH_V2_OUT for details of extended functionality. Use
+ * paired up with NVRAM_UPDATE_FINISH_V2_IN.
+ */
+#define MC_CMD_NVRAM_UPDATE_START_V2_IN_LEN 8
+#define MC_CMD_NVRAM_UPDATE_START_V2_IN_TYPE_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
+#define MC_CMD_NVRAM_UPDATE_START_V2_IN_FLAGS_OFST 4
+#define MC_CMD_NVRAM_UPDATE_START_V2_IN_FLAG_REPORT_VERIFY_RESULT_LBN 0
+#define MC_CMD_NVRAM_UPDATE_START_V2_IN_FLAG_REPORT_VERIFY_RESULT_WIDTH 1
+
/* MC_CMD_NVRAM_UPDATE_START_OUT msgresponse */
#define MC_CMD_NVRAM_UPDATE_START_OUT_LEN 0
@@ -3784,16 +3810,81 @@
#define MC_CMD_0x3c_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-/* MC_CMD_NVRAM_UPDATE_FINISH_IN msgrequest */
+/* MC_CMD_NVRAM_UPDATE_FINISH_IN msgrequest: Legacy NVRAM_UPDATE_FINISH
+ * request. Use NVRAM_UPDATE_FINISH_V2_IN in new code
+ */
#define MC_CMD_NVRAM_UPDATE_FINISH_IN_LEN 8
#define MC_CMD_NVRAM_UPDATE_FINISH_IN_TYPE_OFST 0
/* Enum values, see field(s): */
/* MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
#define MC_CMD_NVRAM_UPDATE_FINISH_IN_REBOOT_OFST 4
-/* MC_CMD_NVRAM_UPDATE_FINISH_OUT msgresponse */
+/* MC_CMD_NVRAM_UPDATE_FINISH_V2_IN msgrequest: Extended NVRAM_UPDATE_FINISH
+ * request with additional flags indicating version of NVRAM_UPDATE commands in
+ * use. See MC_CMD_NVRAM_UPDATE_FINISH_V2_OUT for details of extended
+ * functionality. Use paired up with NVRAM_UPDATE_START_V2_IN.
+ */
+#define MC_CMD_NVRAM_UPDATE_FINISH_V2_IN_LEN 12
+#define MC_CMD_NVRAM_UPDATE_FINISH_V2_IN_TYPE_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
+#define MC_CMD_NVRAM_UPDATE_FINISH_V2_IN_REBOOT_OFST 4
+#define MC_CMD_NVRAM_UPDATE_FINISH_V2_IN_FLAGS_OFST 8
+#define MC_CMD_NVRAM_UPDATE_FINISH_V2_IN_FLAG_REPORT_VERIFY_RESULT_LBN 0
+#define MC_CMD_NVRAM_UPDATE_FINISH_V2_IN_FLAG_REPORT_VERIFY_RESULT_WIDTH 1
+
+/* MC_CMD_NVRAM_UPDATE_FINISH_OUT msgresponse: Legacy NVRAM_UPDATE_FINISH
+ * response. Use NVRAM_UPDATE_FINISH_V2_OUT in new code
+ */
#define MC_CMD_NVRAM_UPDATE_FINISH_OUT_LEN 0
+/* MC_CMD_NVRAM_UPDATE_FINISH_V2_OUT msgresponse:
+ *
+ * Extended NVRAM_UPDATE_FINISH response that communicates the result of secure
+ * firmware validation where applicable back to the host.
+ *
+ * Medford only: For signed firmware images, such as those for medford, the MC
+ * firmware verifies the signature before marking the firmware image as valid.
+ * This process takes a few seconds to complete. So is likely to take more than
+ * the MCDI timeout. Hence signature verification is initiated when
+ * MC_CMD_NVRAM_UPDATE_FINISH_V2_IN is received by the firmware, however, the
+ * MCDI command returns immediately with error code EAGAIN. Subsequent
+ * NVRAM_UPDATE_FINISH_V2_IN requests also return EAGAIN if the verification is
+ * in progress. Once the verification has completed, this response payload
+ * includes the results of the signature verification. Note that the nvram lock
+ * in firmware is only released after the verification has completed and the
+ * host has read back the result code from firmware.
+ */
+#define MC_CMD_NVRAM_UPDATE_FINISH_V2_OUT_LEN 4
+/* Result of nvram update completion processing */
+#define MC_CMD_NVRAM_UPDATE_FINISH_V2_OUT_RESULT_CODE_OFST 0
+/* enum: Verify succeeded without any errors. */
+#define MC_CMD_NVRAM_VERIFY_RC_SUCCESS 0x1
+/* enum: CMS format verification failed due to an internal error. */
+#define MC_CMD_NVRAM_VERIFY_RC_CMS_CHECK_FAILED 0x2
+/* enum: Invalid CMS format in image metadata. */
+#define MC_CMD_NVRAM_VERIFY_RC_INVALID_CMS_FORMAT 0x3
+/* enum: Message digest verification failed due to an internal error. */
+#define MC_CMD_NVRAM_VERIFY_RC_MESSAGE_DIGEST_CHECK_FAILED 0x4
+/* enum: Error in message digest calculated over the reflash-header, payload
+ * and reflash-trailer.
+ */
+#define MC_CMD_NVRAM_VERIFY_RC_BAD_MESSAGE_DIGEST 0x5
+/* enum: Signature verification failed due to an internal error. */
+#define MC_CMD_NVRAM_VERIFY_RC_SIGNATURE_CHECK_FAILED 0x6
+/* enum: There are no valid signatures in the image. */
+#define MC_CMD_NVRAM_VERIFY_RC_NO_VALID_SIGNATURES 0x7
+/* enum: Trusted approvers verification failed due to an internal error. */
+#define MC_CMD_NVRAM_VERIFY_RC_TRUSTED_APPROVERS_CHECK_FAILED 0x8
+/* enum: The Trusted approver's list is empty. */
+#define MC_CMD_NVRAM_VERIFY_RC_NO_TRUSTED_APPROVERS 0x9
+/* enum: Signature chain verification failed due to an internal error. */
+#define MC_CMD_NVRAM_VERIFY_RC_SIGNATURE_CHAIN_CHECK_FAILED 0xa
+/* enum: The signers of the signatures in the image are not listed in the
+ * Trusted approver's list.
+ */
+#define MC_CMD_NVRAM_VERIFY_RC_NO_SIGNATURE_MATCH 0xb
+
/***********************************/
/* MC_CMD_REBOOT
@@ -4356,6 +4447,28 @@
/* MC_CMD_TESTASSERT_OUT msgresponse */
#define MC_CMD_TESTASSERT_OUT_LEN 0
+/* MC_CMD_TESTASSERT_V2_IN msgrequest */
+#define MC_CMD_TESTASSERT_V2_IN_LEN 4
+/* How to provoke the assertion */
+#define MC_CMD_TESTASSERT_V2_IN_TYPE_OFST 0
+/* enum: Assert using the FAIL_ASSERTION_WITH_USEFUL_VALUES macro. Unless
+ * you're testing firmware, this is what you want.
+ */
+#define MC_CMD_TESTASSERT_V2_IN_FAIL_ASSERTION_WITH_USEFUL_VALUES 0x0
+/* enum: Assert using assert(0); */
+#define MC_CMD_TESTASSERT_V2_IN_ASSERT_FALSE 0x1
+/* enum: Deliberately trigger a watchdog */
+#define MC_CMD_TESTASSERT_V2_IN_WATCHDOG 0x2
+/* enum: Deliberately trigger a trap by loading from an invalid address */
+#define MC_CMD_TESTASSERT_V2_IN_LOAD_TRAP 0x3
+/* enum: Deliberately trigger a trap by storing to an invalid address */
+#define MC_CMD_TESTASSERT_V2_IN_STORE_TRAP 0x4
+/* enum: Jump to an invalid address */
+#define MC_CMD_TESTASSERT_V2_IN_JUMP_TRAP 0x5
+
+/* MC_CMD_TESTASSERT_V2_OUT msgresponse */
+#define MC_CMD_TESTASSERT_V2_OUT_LEN 0
+
/***********************************/
/* MC_CMD_WORKAROUND
@@ -4421,6 +4534,7 @@
* (GET_PHY_CFG_OUT_MEDIA_TYPE); the valid 'page number' input values, and the
* output data, are interpreted on a per-type basis. For SFP+: PAGE=0 or 1
* returns a 128-byte block read from module I2C address 0xA0 offset 0 or 0x80.
+ * Anything else: currently undefined. Locks required: None. Return code: 0.
*/
#define MC_CMD_GET_PHY_MEDIA_INFO 0x4b
@@ -5362,12 +5476,14 @@
#define NVRAM_PARTITION_TYPE_EXPANSION_UEFI 0xd00
/* enum: Spare partition 0 */
#define NVRAM_PARTITION_TYPE_SPARE_0 0x1000
-/* enum: Spare partition 1 */
-#define NVRAM_PARTITION_TYPE_SPARE_1 0x1100
+/* enum: Used for XIP code of shmbooted images */
+#define NVRAM_PARTITION_TYPE_XIP_SCRATCH 0x1100
/* enum: Spare partition 2 */
#define NVRAM_PARTITION_TYPE_SPARE_2 0x1200
-/* enum: Spare partition 3 */
-#define NVRAM_PARTITION_TYPE_SPARE_3 0x1300
+/* enum: Manufacturing partition. Used during manufacture to pass information
+ * between XJTAG and Manftest.
+ */
+#define NVRAM_PARTITION_TYPE_MANUFACTURING 0x1300
/* enum: Spare partition 4 */
#define NVRAM_PARTITION_TYPE_SPARE_4 0x1400
/* enum: Spare partition 5 */
@@ -5402,6 +5518,14 @@
#define LICENSED_APP_ID_CAPTURE_SOLARSYSTEM 0x40
/* enum: Network Access Control */
#define LICENSED_APP_ID_NETWORK_ACCESS_CONTROL 0x80
+/* enum: TCP Direct */
+#define LICENSED_APP_ID_TCP_DIRECT 0x100
+/* enum: Low Latency */
+#define LICENSED_APP_ID_LOW_LATENCY 0x200
+/* enum: SolarCapture Tap */
+#define LICENSED_APP_ID_SOLARCAPTURE_TAP 0x400
+/* enum: Capture SolarSystem 40G */
+#define LICENSED_APP_ID_CAPTURE_SOLARSYSTEM_40G 0x800
#define LICENSED_APP_ID_ID_LBN 0
#define LICENSED_APP_ID_ID_WIDTH 32
@@ -5458,6 +5582,14 @@
#define LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_WIDTH 1
#define LICENSED_V3_APPS_NETWORK_ACCESS_CONTROL_LBN 7
#define LICENSED_V3_APPS_NETWORK_ACCESS_CONTROL_WIDTH 1
+#define LICENSED_V3_APPS_TCP_DIRECT_LBN 8
+#define LICENSED_V3_APPS_TCP_DIRECT_WIDTH 1
+#define LICENSED_V3_APPS_LOW_LATENCY_LBN 9
+#define LICENSED_V3_APPS_LOW_LATENCY_WIDTH 1
+#define LICENSED_V3_APPS_SOLARCAPTURE_TAP_LBN 10
+#define LICENSED_V3_APPS_SOLARCAPTURE_TAP_WIDTH 1
+#define LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_40G_LBN 11
+#define LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_40G_WIDTH 1
#define LICENSED_V3_APPS_MASK_LBN 0
#define LICENSED_V3_APPS_MASK_WIDTH 64
@@ -5988,6 +6120,8 @@
#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_INNER_TCP_CSUM_EN_WIDTH 1
#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_TSOV2_EN_LBN 12
#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_TSOV2_EN_WIDTH 1
+#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_CTPIO_LBN 13
+#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_CTPIO_WIDTH 1
/* Owner ID to use if in buffer mode (zero if physical) */
#define MC_CMD_INIT_TXQ_EXT_IN_OWNER_ID_OFST 20
/* The port ID associated with the v-adaptor which should contain this DMAQ. */
@@ -7728,6 +7862,8 @@
* tests (Medford development only)
*/
#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
+/* enum: Rules engine RX PD production firmware */
+#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
/* enum: RX PD firmware parsing but not filtering network overlay tunnel
@@ -7763,6 +7899,8 @@
* tests (Medford development only)
*/
#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
+/* enum: Rules engine TX PD production firmware */
+#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
/* Hardware capabilities of NIC */
@@ -7913,6 +8051,8 @@
* tests (Medford development only)
*/
#define MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
+/* enum: Rules engine RX PD production firmware */
+#define MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
#define MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
/* enum: RX PD firmware parsing but not filtering network overlay tunnel
@@ -7948,6 +8088,8 @@
* tests (Medford development only)
*/
#define MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
+/* enum: Rules engine TX PD production firmware */
+#define MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
#define MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
/* Hardware capabilities of NIC */
@@ -7980,6 +8122,8 @@
#define MC_CMD_GET_CAPABILITIES_V2_OUT_RX_SNIFF_WIDTH 1
#define MC_CMD_GET_CAPABILITIES_V2_OUT_TX_SNIFF_LBN 11
#define MC_CMD_GET_CAPABILITIES_V2_OUT_TX_SNIFF_WIDTH 1
+#define MC_CMD_GET_CAPABILITIES_V2_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
+#define MC_CMD_GET_CAPABILITIES_V2_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
/* Number of FATSOv2 contexts per datapath supported by this NIC. Not present
* on older firmware (check the length).
*/
@@ -8247,6 +8391,8 @@
#define MC_CMD_GET_CAPABILITIES_V3_OUT_RX_SNIFF_WIDTH 1
#define MC_CMD_GET_CAPABILITIES_V3_OUT_TX_SNIFF_LBN 11
#define MC_CMD_GET_CAPABILITIES_V3_OUT_TX_SNIFF_WIDTH 1
+#define MC_CMD_GET_CAPABILITIES_V3_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
+#define MC_CMD_GET_CAPABILITIES_V3_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
/* Number of FATSOv2 contexts per datapath supported by this NIC. Not present
* on older firmware (check the length).
*/
@@ -8304,7 +8450,7 @@
#define MC_CMD_GET_CAPABILITIES_V3_OUT_SIZE_PIO_BUFF_LEN 2
/* On chips later than Medford the amount of address space assigned to each VI
* is configurable. This is a global setting that the driver must query to
- * discover the VI to address mapping. Cut-through PIO (CTPIO) in not available
+ * discover the VI to address mapping. Cut-through PIO (CTPIO) is not available
* with 8k VI windows.
*/
#define MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_OFST 72
@@ -10283,6 +10429,8 @@
* more data is returned.
*/
#define MC_CMD_PCIE_TUNE_IN_POLL_EYE_PLOT 0x6
+/* enum: Enable the SERDES BIST and set it to generate a 200MHz square wave */
+#define MC_CMD_PCIE_TUNE_IN_BIST_SQUARE_WAVE 0x7
/* Align the arguments to 32 bits */
#define MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_RSVD_OFST 1
#define MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_RSVD_LEN 3
@@ -10468,6 +10616,12 @@
#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MINNUM 0
#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MAXNUM 126
+/* MC_CMD_PCIE_TUNE_BIST_SQUARE_WAVE_IN msgrequest */
+#define MC_CMD_PCIE_TUNE_BIST_SQUARE_WAVE_IN_LEN 0
+
+/* MC_CMD_PCIE_TUNE_BIST_SQUARE_WAVE_OUT msgrequest */
+#define MC_CMD_PCIE_TUNE_BIST_SQUARE_WAVE_OUT_LEN 0
+
/***********************************/
/* MC_CMD_LICENSING
@@ -10783,29 +10937,45 @@
#define MC_CMD_0xd4_PRIVILEGE_CTG SRIOV_CTG_GENERAL
/* MC_CMD_LICENSED_V3_VALIDATE_APP_IN msgrequest */
-#define MC_CMD_LICENSED_V3_VALIDATE_APP_IN_LEN 72
+#define MC_CMD_LICENSED_V3_VALIDATE_APP_IN_LEN 56
+/* challenge for validation (384 bits) */
+#define MC_CMD_LICENSED_V3_VALIDATE_APP_IN_CHALLENGE_OFST 0
+#define MC_CMD_LICENSED_V3_VALIDATE_APP_IN_CHALLENGE_LEN 48
/* application ID expressed as a single bit mask */
-#define MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_OFST 0
+#define MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_OFST 48
#define MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LEN 8
-#define MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LO_OFST 0
-#define MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_HI_OFST 4
-/* challenge for validation */
-#define MC_CMD_LICENSED_V3_VALIDATE_APP_IN_CHALLENGE_OFST 8
-#define MC_CMD_LICENSED_V3_VALIDATE_APP_IN_CHALLENGE_LEN 64
+#define MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LO_OFST 48
+#define MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_HI_OFST 52
/* MC_CMD_LICENSED_V3_VALIDATE_APP_OUT msgresponse */
-#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_LEN 72
+#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_LEN 116
+/* validation response to challenge in the form of ECDSA signature consisting
+ * of two 384-bit integers, r and s, in big-endian order. The signature signs a
+ * SHA-384 digest of a message constructed from the concatenation of the input
+ * message and the remaining fields of this output message, e.g. challenge[48
+ * bytes] ... expiry_time[4 bytes] ...
+ */
+#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_RESPONSE_OFST 0
+#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_RESPONSE_LEN 96
/* application expiry time */
-#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_TIME_OFST 0
+#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_TIME_OFST 96
/* application expiry units */
-#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNITS_OFST 4
+#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNITS_OFST 100
/* enum: expiry units are accounting units */
#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNIT_ACC 0x0
/* enum: expiry units are calendar days */
#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNIT_DAYS 0x1
-/* validation response to challenge */
-#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_RESPONSE_OFST 8
-#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_RESPONSE_LEN 64
+/* base MAC address of the NIC stored in NVRAM (note that this is a constant
+ * value for a given NIC regardless which function is calling, effectively this
+ * is PF0 base MAC address)
+ */
+#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_BASE_MACADDR_OFST 104
+#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_BASE_MACADDR_LEN 6
+/* MAC address of v-adaptor associated with the client. If no such v-adapator
+ * exists, then the field is filled with 0xFF.
+ */
+#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_VADAPTOR_MACADDR_OFST 110
+#define MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_VADAPTOR_MACADDR_LEN 6
/***********************************/
@@ -10835,6 +11005,70 @@
/***********************************/
+/* MC_CMD_LICENSING_V3_TEMPORARY
+ * Perform operations to support installation of a single temporary license in
+ * the adapter, in addition to those found in the licensing partition. See
+ * SF-116124-SW for an overview of how this could be used. The license is
+ * stored in MC persistent data and so will survive a MC reboot, but will be
+ * erased when the adapter is power cycled
+ */
+#define MC_CMD_LICENSING_V3_TEMPORARY 0xd6
+
+#define MC_CMD_0xd6_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_LICENSING_V3_TEMPORARY_IN msgrequest */
+#define MC_CMD_LICENSING_V3_TEMPORARY_IN_LEN 4
+/* operation code */
+#define MC_CMD_LICENSING_V3_TEMPORARY_IN_OP_OFST 0
+/* enum: install a new license, overwriting any existing temporary license.
+ * This is an asynchronous operation owing to the time taken to validate an
+ * ECDSA license
+ */
+#define MC_CMD_LICENSING_V3_TEMPORARY_SET 0x0
+/* enum: clear the license immediately rather than waiting for the next power
+ * cycle
+ */
+#define MC_CMD_LICENSING_V3_TEMPORARY_CLEAR 0x1
+/* enum: get the status of the asynchronous MC_CMD_LICENSING_V3_TEMPORARY_SET
+ * operation
+ */
+#define MC_CMD_LICENSING_V3_TEMPORARY_STATUS 0x2
+
+/* MC_CMD_LICENSING_V3_TEMPORARY_IN_SET msgrequest */
+#define MC_CMD_LICENSING_V3_TEMPORARY_IN_SET_LEN 164
+#define MC_CMD_LICENSING_V3_TEMPORARY_IN_SET_OP_OFST 0
+/* ECDSA license and signature */
+#define MC_CMD_LICENSING_V3_TEMPORARY_IN_SET_LICENSE_OFST 4
+#define MC_CMD_LICENSING_V3_TEMPORARY_IN_SET_LICENSE_LEN 160
+
+/* MC_CMD_LICENSING_V3_TEMPORARY_IN_CLEAR msgrequest */
+#define MC_CMD_LICENSING_V3_TEMPORARY_IN_CLEAR_LEN 4
+#define MC_CMD_LICENSING_V3_TEMPORARY_IN_CLEAR_OP_OFST 0
+
+/* MC_CMD_LICENSING_V3_TEMPORARY_IN_STATUS msgrequest */
+#define MC_CMD_LICENSING_V3_TEMPORARY_IN_STATUS_LEN 4
+#define MC_CMD_LICENSING_V3_TEMPORARY_IN_STATUS_OP_OFST 0
+
+/* MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS msgresponse */
+#define MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LEN 12
+/* status code */
+#define MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_STATUS_OFST 0
+/* enum: finished validating and installing license */
+#define MC_CMD_LICENSING_V3_TEMPORARY_STATUS_OK 0x0
+/* enum: license validation and installation in progress */
+#define MC_CMD_LICENSING_V3_TEMPORARY_STATUS_IN_PROGRESS 0x1
+/* enum: licensing error. More specific error messages are not provided to
+ * avoid exposing details of the licensing system to the client
+ */
+#define MC_CMD_LICENSING_V3_TEMPORARY_STATUS_ERROR 0x2
+/* bitmask of licensed features */
+#define MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_OFST 4
+#define MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_LEN 8
+#define MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_LO_OFST 4
+#define MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_HI_OFST 8
+
+
+/***********************************/
/* MC_CMD_SET_PORT_SNIFF_CONFIG
* Configure RX port sniffing for the physical port associated with the calling
* function. Only a privileged function may change the port sniffing
@@ -11705,6 +11939,66 @@
/* MC_CMD_RX_BALANCING_OUT msgresponse */
#define MC_CMD_RX_BALANCING_OUT_LEN 0
+
+/***********************************/
+/* MC_CMD_NVRAM_PRIVATE_APPEND
+ * Append a single TLV to the MC_USAGE_TLV partition. Returns MC_CMD_ERR_EEXIST
+ * if the tag is already present.
+ */
+#define MC_CMD_NVRAM_PRIVATE_APPEND 0x11c
+
+#define MC_CMD_0x11c_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
+/* MC_CMD_NVRAM_PRIVATE_APPEND_IN msgrequest */
+#define MC_CMD_NVRAM_PRIVATE_APPEND_IN_LENMIN 9
+#define MC_CMD_NVRAM_PRIVATE_APPEND_IN_LENMAX 252
+#define MC_CMD_NVRAM_PRIVATE_APPEND_IN_LEN(num) (8+1*(num))
+/* The tag to be appended */
+#define MC_CMD_NVRAM_PRIVATE_APPEND_IN_TAG_OFST 0
+/* The length of the data */
+#define MC_CMD_NVRAM_PRIVATE_APPEND_IN_LENGTH_OFST 4
+/* The data to be contained in the TLV structure */
+#define MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_OFST 8
+#define MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_LEN 1
+#define MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_MINNUM 1
+#define MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_MAXNUM 244
+
+/* MC_CMD_NVRAM_PRIVATE_APPEND_OUT msgresponse */
+#define MC_CMD_NVRAM_PRIVATE_APPEND_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_XPM_VERIFY_CONTENTS
+ * Verify that the contents of the XPM memory is correct (Medford only). This
+ * is used during manufacture to check that the XPM memory has been programmed
+ * correctly at ATE.
+ */
+#define MC_CMD_XPM_VERIFY_CONTENTS 0x11b
+
+#define MC_CMD_0x11b_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
+/* MC_CMD_XPM_VERIFY_CONTENTS_IN msgrequest */
+#define MC_CMD_XPM_VERIFY_CONTENTS_IN_LEN 4
+/* Data type to be checked */
+#define MC_CMD_XPM_VERIFY_CONTENTS_IN_DATA_TYPE_OFST 0
+
+/* MC_CMD_XPM_VERIFY_CONTENTS_OUT msgresponse */
+#define MC_CMD_XPM_VERIFY_CONTENTS_OUT_LENMIN 12
+#define MC_CMD_XPM_VERIFY_CONTENTS_OUT_LENMAX 252
+#define MC_CMD_XPM_VERIFY_CONTENTS_OUT_LEN(num) (12+1*(num))
+/* Number of sectors found (test builds only) */
+#define MC_CMD_XPM_VERIFY_CONTENTS_OUT_NUM_SECTORS_OFST 0
+/* Number of bytes found (test builds only) */
+#define MC_CMD_XPM_VERIFY_CONTENTS_OUT_NUM_BYTES_OFST 4
+/* Length of signature */
+#define MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIG_LENGTH_OFST 8
+/* Signature */
+#define MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_OFST 12
+#define MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_LEN 1
+#define MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_MINNUM 0
+#define MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_MAXNUM 240
+
+
/***********************************/
/* MC_CMD_SET_EVQ_TMR
* Update the timer load, timer reload and timer mode values for a given EVQ.
@@ -11798,4 +12092,151 @@
*/
#define MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_STEP_OFST 32
+
+/***********************************/
+/* MC_CMD_ALLOCATE_TX_VFIFO_CP
+ * When we use the TX_vFIFO_ULL mode, we can allocate common pools using the
+ * non used switch buffers.
+ */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP 0x11d
+
+#define MC_CMD_0x11d_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
+/* MC_CMD_ALLOCATE_TX_VFIFO_CP_IN msgrequest */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_LEN 20
+/* Desired instance. Must be set to a specific instance, which is a function
+ * local queue index.
+ */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_INSTANCE_OFST 0
+/* Will the common pool be used as TX_vFIFO_ULL (1) */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_MODE_OFST 4
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_ENABLED 0x1 /* enum */
+/* enum: Using this interface without TX_vFIFO_ULL is not supported for now */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_DISABLED 0x0
+/* Number of buffers to reserve for the common pool */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_SIZE_OFST 8
+/* TX datapath to which the Common Pool is connected to. */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_INGRESS_OFST 12
+/* enum: Extracts information from function */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_USE_FUNCTION_VALUE -0x1
+/* Network port or RX Engine to which the common pool connects. */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_EGRESS_OFST 16
+/* enum: Extracts information from function */
+/* MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_USE_FUNCTION_VALUE -0x1 */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_PORT0 0x0 /* enum */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_PORT1 0x1 /* enum */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_PORT2 0x2 /* enum */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_PORT3 0x3 /* enum */
+/* enum: To enable Switch loopback with Rx engine 0 */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_RX_ENGINE0 0x4
+/* enum: To enable Switch loopback with Rx engine 1 */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_RX_ENGINE1 0x5
+
+/* MC_CMD_ALLOCATE_TX_VFIFO_CP_OUT msgresponse */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_OUT_LEN 4
+/* ID of the common pool allocated */
+#define MC_CMD_ALLOCATE_TX_VFIFO_CP_OUT_CP_ID_OFST 0
+
+
+/***********************************/
+/* MC_CMD_ALLOCATE_TX_VFIFO_VFIFO
+ * When we use the TX_vFIFO_ULL mode, we can allocate vFIFOs using the
+ * previously allocated common pools.
+ */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO 0x11e
+
+#define MC_CMD_0x11e_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
+/* MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN msgrequest */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_LEN 20
+/* Common pool previously allocated to which the new vFIFO will be associated
+ */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_CP_OFST 0
+/* Port or RX engine to associate the vFIFO egress */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_EGRESS_OFST 4
+/* enum: Extracts information from common pool */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_USE_CP_VALUE -0x1
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PORT0 0x0 /* enum */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PORT1 0x1 /* enum */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PORT2 0x2 /* enum */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PORT3 0x3 /* enum */
+/* enum: To enable Switch loopback with Rx engine 0 */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_RX_ENGINE0 0x4
+/* enum: To enable Switch loopback with Rx engine 1 */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_RX_ENGINE1 0x5
+/* Minimum number of buffers that the pool must have */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_SIZE_OFST 8
+/* enum: Do not check the space available */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_NO_MINIMUM 0x0
+/* Will the vFIFO be used as TX_vFIFO_ULL */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_MODE_OFST 12
+/* Network priority of the vFIFO,if applicable */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PRIORITY_OFST 16
+/* enum: Search for the lowest unused priority */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_LOWEST_AVAILABLE -0x1
+
+/* MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT msgresponse */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT_LEN 8
+/* Short vFIFO ID */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT_VID_OFST 0
+/* Network priority of the vFIFO */
+#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT_PRIORITY_OFST 4
+
+
+/***********************************/
+/* MC_CMD_TEARDOWN_TX_VFIFO_VF
+ * This interface clears the configuration of the given vFIFO and leaves it
+ * ready to be re-used.
+ */
+#define MC_CMD_TEARDOWN_TX_VFIFO_VF 0x11f
+
+#define MC_CMD_0x11f_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
+/* MC_CMD_TEARDOWN_TX_VFIFO_VF_IN msgrequest */
+#define MC_CMD_TEARDOWN_TX_VFIFO_VF_IN_LEN 4
+/* Short vFIFO ID */
+#define MC_CMD_TEARDOWN_TX_VFIFO_VF_IN_VFIFO_OFST 0
+
+/* MC_CMD_TEARDOWN_TX_VFIFO_VF_OUT msgresponse */
+#define MC_CMD_TEARDOWN_TX_VFIFO_VF_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_DEALLOCATE_TX_VFIFO_CP
+ * This interface clears the configuration of the given common pool and leaves
+ * it ready to be re-used.
+ */
+#define MC_CMD_DEALLOCATE_TX_VFIFO_CP 0x121
+
+#define MC_CMD_0x121_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
+/* MC_CMD_DEALLOCATE_TX_VFIFO_CP_IN msgrequest */
+#define MC_CMD_DEALLOCATE_TX_VFIFO_CP_IN_LEN 4
+/* Common pool ID given when pool allocated */
+#define MC_CMD_DEALLOCATE_TX_VFIFO_CP_IN_POOL_ID_OFST 0
+
+/* MC_CMD_DEALLOCATE_TX_VFIFO_CP_OUT msgresponse */
+#define MC_CMD_DEALLOCATE_TX_VFIFO_CP_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS
+ * This interface allows the host to find out how many common pool buffers are
+ * not yet assigned.
+ */
+#define MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS 0x124
+
+#define MC_CMD_0x124_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
+/* MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_IN msgrequest */
+#define MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_IN_LEN 0
+
+/* MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT msgresponse */
+#define MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT_LEN 8
+/* Available buffers for the ENG to NET vFIFOs. */
+#define MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT_NET_OFST 0
+/* Available buffers for the ENG to ENG and NET to ENG vFIFOs. */
+#define MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT_ENG_OFST 4
+
+
#endif /* MCDI_PCOL_H */
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 99d8c82..f97f828 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -189,13 +189,17 @@ struct efx_tx_buffer {
* @channel: The associated channel
* @core_txq: The networking core TX queue structure
* @buffer: The software buffer ring
- * @tsoh_page: Array of pages of TSO header buffers
+ * @cb_page: Array of pages of copy buffers. Carved up according to
+ * %EFX_TX_CB_ORDER into %EFX_TX_CB_SIZE-sized chunks.
* @txd: The hardware descriptor ring
* @ptr_mask: The size of the ring minus 1.
* @piobuf: PIO buffer region for this TX queue (shared with its partner).
* Size of the region is efx_piobuf_size.
* @piobuf_offset: Buffer offset to be specified in PIO descriptors
* @initialised: Has hardware queue been initialised?
+ * @tx_min_size: Minimum transmit size for this queue. Depends on HW.
+ * @handle_tso: TSO xmit preparation handler. Sets up the TSO metadata and
+ * may also map tx data, depending on the nature of the TSO implementation.
* @read_count: Current read pointer.
* This is the number of buffers that have been removed from both rings.
* @old_write_count: The value of @write_count when last checked.
@@ -221,9 +225,11 @@ struct efx_tx_buffer {
* @tso_long_headers: Number of packets with headers too long for standard
* blocks
* @tso_packets: Number of packets via the TSO xmit path
+ * @tso_fallbacks: Number of times TSO fallback used
* @pushes: Number of times the TX push feature has been used
* @pio_packets: Number of times the TX PIO feature has been used
* @xmit_more_available: Are any packets waiting to be pushed to the NIC
+ * @cb_packets: Number of times the TX copybreak feature has been used
* @empty_read_count: If the completion path has seen the queue as empty
* and the transmission path has not yet checked this, the value of
* @read_count bitwise-added to %EFX_EMPTY_COUNT_VALID; otherwise 0.
@@ -236,12 +242,16 @@ struct efx_tx_queue {
struct efx_channel *channel;
struct netdev_queue *core_txq;
struct efx_tx_buffer *buffer;
- struct efx_buffer *tsoh_page;
+ struct efx_buffer *cb_page;
struct efx_special_buffer txd;
unsigned int ptr_mask;
void __iomem *piobuf;
unsigned int piobuf_offset;
bool initialised;
+ unsigned int tx_min_size;
+
+ /* Function pointers used in the fast path. */
+ int (*handle_tso)(struct efx_tx_queue*, struct sk_buff*, bool *);
/* Members used mainly on the completion path */
unsigned int read_count ____cacheline_aligned_in_smp;
@@ -257,9 +267,11 @@ struct efx_tx_queue {
unsigned int tso_bursts;
unsigned int tso_long_headers;
unsigned int tso_packets;
+ unsigned int tso_fallbacks;
unsigned int pushes;
unsigned int pio_packets;
bool xmit_more_available;
+ unsigned int cb_packets;
/* Statistics to supplement MAC stats */
unsigned long tx_packets;
@@ -269,6 +281,9 @@ struct efx_tx_queue {
atomic_t flush_outstanding;
};
+#define EFX_TX_CB_ORDER 7
+#define EFX_TX_CB_SIZE (1 << EFX_TX_CB_ORDER) - NET_IP_ALIGN
+
/**
* struct efx_rx_buffer - An Efx RX data buffer
* @dma_addr: DMA base address of the buffer
@@ -853,6 +868,7 @@ struct vfdi_status;
* @rx_hash_key: Toeplitz hash key for RSS
* @rx_indir_table: Indirection table for RSS
* @rx_scatter: Scatter mode enabled for receives
+ * @rx_hash_udp_4tuple: UDP 4-tuple hashing enabled
* @int_error_count: Number of internal errors seen recently
* @int_error_expire: Time at which error count will be expired
* @irq_soft_enabled: Are IRQs soft-enabled? If not, IRQ handler will
@@ -990,6 +1006,7 @@ struct efx_nic {
u8 rx_hash_key[40];
u32 rx_indir_table[128];
bool rx_scatter;
+ bool rx_hash_udp_4tuple;
unsigned int_error_count;
unsigned long int_error_expire;
@@ -1210,6 +1227,8 @@ struct efx_mtd_partition {
* and tx_type will already have been validated but this operation
* must validate and update rx_filter.
* @set_mac_address: Set the MAC address of the device
+ * @tso_versions: Returns mask of firmware-assisted TSO versions supported.
+ * If %NULL, then device does not support any TSO version.
* @revision: Hardware architecture revision
* @txd_ptr_tbl_base: TX descriptor ring base address
* @rxd_ptr_tbl_base: RX descriptor ring base address
@@ -1286,6 +1305,8 @@ struct efx_nic_type {
void (*tx_init)(struct efx_tx_queue *tx_queue);
void (*tx_remove)(struct efx_tx_queue *tx_queue);
void (*tx_write)(struct efx_tx_queue *tx_queue);
+ unsigned int (*tx_limit_len)(struct efx_tx_queue *tx_queue,
+ dma_addr_t dma_addr, unsigned int len);
int (*rx_push_rss_config)(struct efx_nic *efx, bool user,
const u32 *rx_indir_table);
int (*rx_probe)(struct efx_rx_queue *rx_queue);
@@ -1364,6 +1385,7 @@ struct efx_nic_type {
void (*vswitching_remove)(struct efx_nic *efx);
int (*get_mac_address)(struct efx_nic *efx, unsigned char *perm_addr);
int (*set_mac_address)(struct efx_nic *efx);
+ u32 (*tso_versions)(struct efx_nic *efx);
int revision;
unsigned int txd_ptr_tbl_base;
@@ -1543,4 +1565,32 @@ static inline netdev_features_t efx_supported_features(const struct efx_nic *efx
return net_dev->features | net_dev->hw_features;
}
+/* Get the current TX queue insert index. */
+static inline unsigned int
+efx_tx_queue_get_insert_index(const struct efx_tx_queue *tx_queue)
+{
+ return tx_queue->insert_count & tx_queue->ptr_mask;
+}
+
+/* Get a TX buffer. */
+static inline struct efx_tx_buffer *
+__efx_tx_queue_get_insert_buffer(const struct efx_tx_queue *tx_queue)
+{
+ return &tx_queue->buffer[efx_tx_queue_get_insert_index(tx_queue)];
+}
+
+/* Get a TX buffer, checking it's not currently in use. */
+static inline struct efx_tx_buffer *
+efx_tx_queue_get_insert_buffer(const struct efx_tx_queue *tx_queue)
+{
+ struct efx_tx_buffer *buffer =
+ __efx_tx_queue_get_insert_buffer(tx_queue);
+
+ EFX_BUG_ON_PARANOID(buffer->len);
+ EFX_BUG_ON_PARANOID(buffer->flags);
+ EFX_BUG_ON_PARANOID(buffer->unmap_len);
+
+ return buffer;
+}
+
#endif /* EFX_NET_DRIVER_H */
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 73bee7e..06dd96e 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -681,6 +681,8 @@ void efx_farch_tx_init(struct efx_tx_queue *tx_queue);
void efx_farch_tx_fini(struct efx_tx_queue *tx_queue);
void efx_farch_tx_remove(struct efx_tx_queue *tx_queue);
void efx_farch_tx_write(struct efx_tx_queue *tx_queue);
+unsigned int efx_farch_tx_limit_len(struct efx_tx_queue *tx_queue,
+ dma_addr_t dma_addr, unsigned int len);
int efx_farch_rx_probe(struct efx_rx_queue *rx_queue);
void efx_farch_rx_init(struct efx_rx_queue *rx_queue);
void efx_farch_rx_fini(struct efx_rx_queue *rx_queue);
diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c
index 04ed1b4..3975cad 100644
--- a/drivers/net/ethernet/sfc/siena.c
+++ b/drivers/net/ethernet/sfc/siena.c
@@ -977,6 +977,7 @@ const struct efx_nic_type siena_a0_nic_type = {
.tx_init = efx_farch_tx_init,
.tx_remove = efx_farch_tx_remove,
.tx_write = efx_farch_tx_write,
+ .tx_limit_len = efx_farch_tx_limit_len,
.rx_push_rss_config = siena_rx_push_rss_config,
.rx_probe = efx_farch_rx_probe,
.rx_init = efx_farch_rx_init,
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 2337789..1aa728c 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -22,6 +22,7 @@
#include "efx.h"
#include "io.h"
#include "nic.h"
+#include "tx.h"
#include "workarounds.h"
#include "ef10_regs.h"
@@ -33,29 +34,30 @@ unsigned int efx_piobuf_size __read_mostly = EFX_PIOBUF_SIZE_DEF;
#endif /* EFX_USE_PIO */
-static inline unsigned int
-efx_tx_queue_get_insert_index(const struct efx_tx_queue *tx_queue)
+static inline u8 *efx_tx_get_copy_buffer(struct efx_tx_queue *tx_queue,
+ struct efx_tx_buffer *buffer)
{
- return tx_queue->insert_count & tx_queue->ptr_mask;
+ unsigned int index = efx_tx_queue_get_insert_index(tx_queue);
+ struct efx_buffer *page_buf =
+ &tx_queue->cb_page[index >> (PAGE_SHIFT - EFX_TX_CB_ORDER)];
+ unsigned int offset =
+ ((index << EFX_TX_CB_ORDER) + NET_IP_ALIGN) & (PAGE_SIZE - 1);
+
+ if (unlikely(!page_buf->addr) &&
+ efx_nic_alloc_buffer(tx_queue->efx, page_buf, PAGE_SIZE,
+ GFP_ATOMIC))
+ return NULL;
+ buffer->dma_addr = page_buf->dma_addr + offset;
+ buffer->unmap_len = 0;
+ return (u8 *)page_buf->addr + offset;
}
-static inline struct efx_tx_buffer *
-__efx_tx_queue_get_insert_buffer(const struct efx_tx_queue *tx_queue)
+u8 *efx_tx_get_copy_buffer_limited(struct efx_tx_queue *tx_queue,
+ struct efx_tx_buffer *buffer, size_t len)
{
- return &tx_queue->buffer[efx_tx_queue_get_insert_index(tx_queue)];
-}
-
-static inline struct efx_tx_buffer *
-efx_tx_queue_get_insert_buffer(const struct efx_tx_queue *tx_queue)
-{
- struct efx_tx_buffer *buffer =
- __efx_tx_queue_get_insert_buffer(tx_queue);
-
- EFX_BUG_ON_PARANOID(buffer->len);
- EFX_BUG_ON_PARANOID(buffer->flags);
- EFX_BUG_ON_PARANOID(buffer->unmap_len);
-
- return buffer;
+ if (len > EFX_TX_CB_SIZE)
+ return NULL;
+ return efx_tx_get_copy_buffer(tx_queue, buffer);
}
static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
@@ -90,27 +92,6 @@ static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
buffer->flags = 0;
}
-static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
- struct sk_buff *skb);
-
-static inline unsigned
-efx_max_tx_len(struct efx_nic *efx, dma_addr_t dma_addr)
-{
- /* Depending on the NIC revision, we can use descriptor
- * lengths up to 8K or 8K-1. However, since PCI Express
- * devices must split read requests at 4K boundaries, there is
- * little benefit from using descriptors that cross those
- * boundaries and we keep things simple by not doing so.
- */
- unsigned len = (~dma_addr & (EFX_PAGE_SIZE - 1)) + 1;
-
- /* Work around hardware bug for unaligned buffers. */
- if (EFX_WORKAROUND_5391(efx) && (dma_addr & 0xf))
- len = min_t(unsigned, len, 512 - (dma_addr & 0xf));
-
- return len;
-}
-
unsigned int efx_tx_max_skb_descs(struct efx_nic *efx)
{
/* Header and payload descriptor for each output segment, plus
@@ -173,6 +154,39 @@ static void efx_tx_maybe_stop_queue(struct efx_tx_queue *txq1)
}
}
+static int efx_enqueue_skb_copy(struct efx_tx_queue *tx_queue,
+ struct sk_buff *skb)
+{
+ unsigned int min_len = tx_queue->tx_min_size;
+ unsigned int copy_len = skb->len;
+ struct efx_tx_buffer *buffer;
+ u8 *copy_buffer;
+ int rc;
+
+ EFX_BUG_ON_PARANOID(copy_len > EFX_TX_CB_SIZE);
+
+ buffer = efx_tx_queue_get_insert_buffer(tx_queue);
+
+ copy_buffer = efx_tx_get_copy_buffer(tx_queue, buffer);
+ if (unlikely(!copy_buffer))
+ return -ENOMEM;
+
+ rc = skb_copy_bits(skb, 0, copy_buffer, copy_len);
+ EFX_WARN_ON_PARANOID(rc);
+ if (unlikely(copy_len < min_len)) {
+ memset(copy_buffer + copy_len, 0, min_len - copy_len);
+ buffer->len = min_len;
+ } else {
+ buffer->len = copy_len;
+ }
+
+ buffer->skb = skb;
+ buffer->flags = EFX_TX_BUF_SKB;
+
+ ++tx_queue->insert_count;
+ return rc;
+}
+
#ifdef EFX_USE_PIO
struct efx_short_copy_buffer {
@@ -267,8 +281,8 @@ static void efx_skb_copy_bits_to_pio(struct efx_nic *efx, struct sk_buff *skb,
EFX_BUG_ON_PARANOID(skb_shinfo(skb)->frag_list);
}
-static struct efx_tx_buffer *
-efx_enqueue_skb_pio(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
+static int efx_enqueue_skb_pio(struct efx_tx_queue *tx_queue,
+ struct sk_buff *skb)
{
struct efx_tx_buffer *buffer =
efx_tx_queue_get_insert_buffer(tx_queue);
@@ -292,7 +306,7 @@ efx_enqueue_skb_pio(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
efx_flush_copy_buffer(tx_queue->efx, piobuf, ©_buf);
} else {
/* Pad the write to the size of a cache line.
- * We can do this because we know the skb_shared_info sruct is
+ * We can do this because we know the skb_shared_info struct is
* after the source, and the destination buffer is big enough.
*/
BUILD_BUG_ON(L1_CACHE_BYTES >
@@ -301,6 +315,9 @@ efx_enqueue_skb_pio(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
ALIGN(skb->len, L1_CACHE_BYTES) >> 3);
}
+ buffer->skb = skb;
+ buffer->flags = EFX_TX_BUF_SKB | EFX_TX_BUF_OPTION;
+
EFX_POPULATE_QWORD_5(buffer->option,
ESF_DZ_TX_DESC_IS_OPT, 1,
ESF_DZ_TX_OPTION_TYPE, ESE_DZ_TX_OPTION_DESC_PIO,
@@ -308,12 +325,161 @@ efx_enqueue_skb_pio(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
ESF_DZ_TX_PIO_BYTE_CNT, skb->len,
ESF_DZ_TX_PIO_BUF_ADDR,
tx_queue->piobuf_offset);
- ++tx_queue->pio_packets;
++tx_queue->insert_count;
- return buffer;
+ return 0;
}
#endif /* EFX_USE_PIO */
+static struct efx_tx_buffer *efx_tx_map_chunk(struct efx_tx_queue *tx_queue,
+ dma_addr_t dma_addr,
+ size_t len)
+{
+ const struct efx_nic_type *nic_type = tx_queue->efx->type;
+ struct efx_tx_buffer *buffer;
+ unsigned int dma_len;
+
+ /* Map the fragment taking account of NIC-dependent DMA limits. */
+ do {
+ buffer = efx_tx_queue_get_insert_buffer(tx_queue);
+ dma_len = nic_type->tx_limit_len(tx_queue, dma_addr, len);
+
+ buffer->len = dma_len;
+ buffer->dma_addr = dma_addr;
+ buffer->flags = EFX_TX_BUF_CONT;
+ len -= dma_len;
+ dma_addr += dma_len;
+ ++tx_queue->insert_count;
+ } while (len);
+
+ return buffer;
+}
+
+/* Map all data from an SKB for DMA and create descriptors on the queue.
+ */
+static int efx_tx_map_data(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
+ unsigned int segment_count)
+{
+ struct efx_nic *efx = tx_queue->efx;
+ struct device *dma_dev = &efx->pci_dev->dev;
+ unsigned int frag_index, nr_frags;
+ dma_addr_t dma_addr, unmap_addr;
+ unsigned short dma_flags;
+ size_t len, unmap_len;
+
+ nr_frags = skb_shinfo(skb)->nr_frags;
+ frag_index = 0;
+
+ /* Map header data. */
+ len = skb_headlen(skb);
+ dma_addr = dma_map_single(dma_dev, skb->data, len, DMA_TO_DEVICE);
+ dma_flags = EFX_TX_BUF_MAP_SINGLE;
+ unmap_len = len;
+ unmap_addr = dma_addr;
+
+ if (unlikely(dma_mapping_error(dma_dev, dma_addr)))
+ return -EIO;
+
+ if (segment_count) {
+ /* For TSO we need to put the header in to a separate
+ * descriptor. Map this separately if necessary.
+ */
+ size_t header_len = skb_transport_header(skb) - skb->data +
+ (tcp_hdr(skb)->doff << 2u);
+
+ if (header_len != len) {
+ tx_queue->tso_long_headers++;
+ efx_tx_map_chunk(tx_queue, dma_addr, header_len);
+ len -= header_len;
+ dma_addr += header_len;
+ }
+ }
+
+ /* Add descriptors for each fragment. */
+ do {
+ struct efx_tx_buffer *buffer;
+ skb_frag_t *fragment;
+
+ buffer = efx_tx_map_chunk(tx_queue, dma_addr, len);
+
+ /* The final descriptor for a fragment is responsible for
+ * unmapping the whole fragment.
+ */
+ buffer->flags = EFX_TX_BUF_CONT | dma_flags;
+ buffer->unmap_len = unmap_len;
+ buffer->dma_offset = buffer->dma_addr - unmap_addr;
+
+ if (frag_index >= nr_frags) {
+ /* Store SKB details with the final buffer for
+ * the completion.
+ */
+ buffer->skb = skb;
+ buffer->flags = EFX_TX_BUF_SKB | dma_flags;
+ return 0;
+ }
+
+ /* Move on to the next fragment. */
+ fragment = &skb_shinfo(skb)->frags[frag_index++];
+ len = skb_frag_size(fragment);
+ dma_addr = skb_frag_dma_map(dma_dev, fragment,
+ 0, len, DMA_TO_DEVICE);
+ dma_flags = 0;
+ unmap_len = len;
+ unmap_addr = dma_addr;
+
+ if (unlikely(dma_mapping_error(dma_dev, dma_addr)))
+ return -EIO;
+ } while (1);
+}
+
+/* Remove buffers put into a tx_queue. None of the buffers must have
+ * an skb attached.
+ */
+static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue)
+{
+ struct efx_tx_buffer *buffer;
+
+ /* Work backwards until we hit the original insert pointer value */
+ while (tx_queue->insert_count != tx_queue->write_count) {
+ --tx_queue->insert_count;
+ buffer = __efx_tx_queue_get_insert_buffer(tx_queue);
+ efx_dequeue_buffer(tx_queue, buffer, NULL, NULL);
+ }
+}
+
+/*
+ * Fallback to software TSO.
+ *
+ * This is used if we are unable to send a GSO packet through hardware TSO.
+ * This should only ever happen due to per-queue restrictions - unsupported
+ * packets should first be filtered by the feature flags.
+ *
+ * Returns 0 on success, error code otherwise.
+ */
+static int efx_tx_tso_fallback(struct efx_tx_queue *tx_queue,
+ struct sk_buff *skb)
+{
+ struct sk_buff *segments, *next;
+
+ segments = skb_gso_segment(skb, 0);
+ if (IS_ERR(segments))
+ return PTR_ERR(segments);
+
+ dev_kfree_skb_any(skb);
+ skb = segments;
+
+ while (skb) {
+ next = skb->next;
+ skb->next = NULL;
+
+ if (next)
+ skb->xmit_more = true;
+ efx_enqueue_skb(tx_queue, skb);
+ skb = next;
+ }
+
+ return 0;
+}
+
/*
* Add a socket buffer to a TX queue
*
@@ -332,103 +498,55 @@ efx_enqueue_skb_pio(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
*/
netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
{
- struct efx_nic *efx = tx_queue->efx;
- struct device *dma_dev = &efx->pci_dev->dev;
- struct efx_tx_buffer *buffer;
- unsigned int old_insert_count = tx_queue->insert_count;
- skb_frag_t *fragment;
- unsigned int len, unmap_len = 0;
- dma_addr_t dma_addr, unmap_addr = 0;
- unsigned int dma_len;
- unsigned short dma_flags;
- int i = 0;
+ bool data_mapped = false;
+ unsigned int segments;
+ unsigned int skb_len;
+ int rc;
- if (skb_shinfo(skb)->gso_size)
- return efx_enqueue_skb_tso(tx_queue, skb);
+ skb_len = skb->len;
+ segments = skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 0;
+ if (segments == 1)
+ segments = 0; /* Don't use TSO for a single segment. */
- /* Get size of the initial fragment */
- len = skb_headlen(skb);
-
- /* Pad if necessary */
- if (EFX_WORKAROUND_15592(efx) && skb->len <= 32) {
- EFX_BUG_ON_PARANOID(skb->data_len);
- len = 32 + 1;
- if (skb_pad(skb, len - skb->len))
- return NETDEV_TX_OK;
- }
-
- /* Consider using PIO for short packets */
-#ifdef EFX_USE_PIO
- if (skb->len <= efx_piobuf_size && !skb->xmit_more &&
- efx_nic_may_tx_pio(tx_queue)) {
- buffer = efx_enqueue_skb_pio(tx_queue, skb);
- dma_flags = EFX_TX_BUF_OPTION;
- goto finish_packet;
- }
-#endif
-
- /* Map for DMA. Use dma_map_single rather than dma_map_page
- * since this is more efficient on machines with sparse
- * memory.
+ /* Handle TSO first - it's *possible* (although unlikely) that we might
+ * be passed a packet to segment that's smaller than the copybreak/PIO
+ * size limit.
*/
- dma_flags = EFX_TX_BUF_MAP_SINGLE;
- dma_addr = dma_map_single(dma_dev, skb->data, len, PCI_DMA_TODEVICE);
-
- /* Process all fragments */
- while (1) {
- if (unlikely(dma_mapping_error(dma_dev, dma_addr)))
- goto dma_err;
-
- /* Store fields for marking in the per-fragment final
- * descriptor */
- unmap_len = len;
- unmap_addr = dma_addr;
-
- /* Add to TX queue, splitting across DMA boundaries */
- do {
- buffer = efx_tx_queue_get_insert_buffer(tx_queue);
-
- dma_len = efx_max_tx_len(efx, dma_addr);
- if (likely(dma_len >= len))
- dma_len = len;
-
- /* Fill out per descriptor fields */
- buffer->len = dma_len;
- buffer->dma_addr = dma_addr;
- buffer->flags = EFX_TX_BUF_CONT;
- len -= dma_len;
- dma_addr += dma_len;
- ++tx_queue->insert_count;
- } while (len);
-
- /* Transfer ownership of the unmapping to the final buffer */
- buffer->flags = EFX_TX_BUF_CONT | dma_flags;
- buffer->unmap_len = unmap_len;
- buffer->dma_offset = buffer->dma_addr - unmap_addr;
- unmap_len = 0;
-
- /* Get address and size of next fragment */
- if (i >= skb_shinfo(skb)->nr_frags)
- break;
- fragment = &skb_shinfo(skb)->frags[i];
- len = skb_frag_size(fragment);
- i++;
- /* Map for DMA */
- dma_flags = 0;
- dma_addr = skb_frag_dma_map(dma_dev, fragment, 0, len,
- DMA_TO_DEVICE);
+ if (segments) {
+ EFX_BUG_ON_PARANOID(!tx_queue->handle_tso);
+ rc = tx_queue->handle_tso(tx_queue, skb, &data_mapped);
+ if (rc == -EINVAL) {
+ rc = efx_tx_tso_fallback(tx_queue, skb);
+ tx_queue->tso_fallbacks++;
+ if (rc == 0)
+ return 0;
+ }
+ if (rc)
+ goto err;
+#ifdef EFX_USE_PIO
+ } else if (skb_len <= efx_piobuf_size && !skb->xmit_more &&
+ efx_nic_may_tx_pio(tx_queue)) {
+ /* Use PIO for short packets with an empty queue. */
+ if (efx_enqueue_skb_pio(tx_queue, skb))
+ goto err;
+ tx_queue->pio_packets++;
+ data_mapped = true;
+#endif
+ } else if (skb_len < tx_queue->tx_min_size ||
+ (skb->data_len && skb_len <= EFX_TX_CB_SIZE)) {
+ /* Pad short packets or coalesce short fragmented packets. */
+ if (efx_enqueue_skb_copy(tx_queue, skb))
+ goto err;
+ tx_queue->cb_packets++;
+ data_mapped = true;
}
- /* Transfer ownership of the skb to the final buffer */
-#ifdef EFX_USE_PIO
-finish_packet:
-#endif
- buffer->skb = skb;
- buffer->flags = EFX_TX_BUF_SKB | dma_flags;
+ /* Map for DMA and create descriptors if we haven't done so already. */
+ if (!data_mapped && (efx_tx_map_data(tx_queue, skb, segments)))
+ goto err;
- netdev_tx_sent_queue(tx_queue->core_txq, skb->len);
-
- efx_tx_maybe_stop_queue(tx_queue);
+ /* Update BQL */
+ netdev_tx_sent_queue(tx_queue->core_txq, skb_len);
/* Pass off to hardware */
if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
@@ -446,37 +564,22 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
tx_queue->xmit_more_available = skb->xmit_more;
}
- tx_queue->tx_packets++;
+ if (segments) {
+ tx_queue->tso_bursts++;
+ tx_queue->tso_packets += segments;
+ tx_queue->tx_packets += segments;
+ } else {
+ tx_queue->tx_packets++;
+ }
+
+ efx_tx_maybe_stop_queue(tx_queue);
return NETDEV_TX_OK;
- dma_err:
- netif_err(efx, tx_err, efx->net_dev,
- " TX queue %d could not map skb with %d bytes %d "
- "fragments for DMA\n", tx_queue->queue, skb->len,
- skb_shinfo(skb)->nr_frags + 1);
- /* Mark the packet as transmitted, and free the SKB ourselves */
+err:
+ efx_enqueue_unwind(tx_queue);
dev_kfree_skb_any(skb);
-
- /* Work backwards until we hit the original insert pointer value */
- while (tx_queue->insert_count != old_insert_count) {
- unsigned int pkts_compl = 0, bytes_compl = 0;
- --tx_queue->insert_count;
- buffer = __efx_tx_queue_get_insert_buffer(tx_queue);
- efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
- }
-
- /* Free the fragment we were mid-way through pushing */
- if (unmap_len) {
- if (dma_flags & EFX_TX_BUF_MAP_SINGLE)
- dma_unmap_single(dma_dev, unmap_addr, unmap_len,
- DMA_TO_DEVICE);
- else
- dma_unmap_page(dma_dev, unmap_addr, unmap_len,
- DMA_TO_DEVICE);
- }
-
return NETDEV_TX_OK;
}
@@ -667,19 +770,9 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index)
}
}
-/* Size of page-based TSO header buffers. Larger blocks must be
- * allocated from the heap.
- */
-#define TSOH_STD_SIZE 128
-#define TSOH_PER_PAGE (PAGE_SIZE / TSOH_STD_SIZE)
-
-/* At most half the descriptors in the queue at any time will refer to
- * a TSO header buffer, since they must always be followed by a
- * payload descriptor referring to an skb.
- */
-static unsigned int efx_tsoh_page_count(struct efx_tx_queue *tx_queue)
+static unsigned int efx_tx_cb_page_count(struct efx_tx_queue *tx_queue)
{
- return DIV_ROUND_UP(tx_queue->ptr_mask + 1, 2 * TSOH_PER_PAGE);
+ return DIV_ROUND_UP(tx_queue->ptr_mask + 1, PAGE_SIZE >> EFX_TX_CB_ORDER);
}
int efx_probe_tx_queue(struct efx_tx_queue *tx_queue)
@@ -703,14 +796,11 @@ int efx_probe_tx_queue(struct efx_tx_queue *tx_queue)
if (!tx_queue->buffer)
return -ENOMEM;
- if (tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD) {
- tx_queue->tsoh_page =
- kcalloc(efx_tsoh_page_count(tx_queue),
- sizeof(tx_queue->tsoh_page[0]), GFP_KERNEL);
- if (!tx_queue->tsoh_page) {
- rc = -ENOMEM;
- goto fail1;
- }
+ tx_queue->cb_page = kcalloc(efx_tx_cb_page_count(tx_queue),
+ sizeof(tx_queue->cb_page[0]), GFP_KERNEL);
+ if (!tx_queue->cb_page) {
+ rc = -ENOMEM;
+ goto fail1;
}
/* Allocate hardware ring */
@@ -721,8 +811,8 @@ int efx_probe_tx_queue(struct efx_tx_queue *tx_queue)
return 0;
fail2:
- kfree(tx_queue->tsoh_page);
- tx_queue->tsoh_page = NULL;
+ kfree(tx_queue->cb_page);
+ tx_queue->cb_page = NULL;
fail1:
kfree(tx_queue->buffer);
tx_queue->buffer = NULL;
@@ -731,7 +821,9 @@ int efx_probe_tx_queue(struct efx_tx_queue *tx_queue)
void efx_init_tx_queue(struct efx_tx_queue *tx_queue)
{
- netif_dbg(tx_queue->efx, drv, tx_queue->efx->net_dev,
+ struct efx_nic *efx = tx_queue->efx;
+
+ netif_dbg(efx, drv, efx->net_dev,
"initialising TX queue %d\n", tx_queue->queue);
tx_queue->insert_count = 0;
@@ -742,6 +834,14 @@ void efx_init_tx_queue(struct efx_tx_queue *tx_queue)
tx_queue->empty_read_count = 0 | EFX_EMPTY_COUNT_VALID;
tx_queue->xmit_more_available = false;
+ /* Set up default function pointers. These may get replaced by
+ * efx_nic_init_tx() based off NIC/queue capabilities.
+ */
+ tx_queue->handle_tso = efx_enqueue_skb_tso;
+
+ /* Some older hardware requires Tx writes larger than 32. */
+ tx_queue->tx_min_size = EFX_WORKAROUND_15592(efx) ? 33 : 0;
+
/* Set up TX descriptor ring */
efx_nic_init_tx(tx_queue);
@@ -781,589 +881,14 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue)
"destroying TX queue %d\n", tx_queue->queue);
efx_nic_remove_tx(tx_queue);
- if (tx_queue->tsoh_page) {
- for (i = 0; i < efx_tsoh_page_count(tx_queue); i++)
+ if (tx_queue->cb_page) {
+ for (i = 0; i < efx_tx_cb_page_count(tx_queue); i++)
efx_nic_free_buffer(tx_queue->efx,
- &tx_queue->tsoh_page[i]);
- kfree(tx_queue->tsoh_page);
- tx_queue->tsoh_page = NULL;
+ &tx_queue->cb_page[i]);
+ kfree(tx_queue->cb_page);
+ tx_queue->cb_page = NULL;
}
kfree(tx_queue->buffer);
tx_queue->buffer = NULL;
}
-
-
-/* Efx TCP segmentation acceleration.
- *
- * Why? Because by doing it here in the driver we can go significantly
- * faster than the GSO.
- *
- * Requires TX checksum offload support.
- */
-
-#define PTR_DIFF(p1, p2) ((u8 *)(p1) - (u8 *)(p2))
-
-/**
- * struct tso_state - TSO state for an SKB
- * @out_len: Remaining length in current segment
- * @seqnum: Current sequence number
- * @ipv4_id: Current IPv4 ID, host endian
- * @packet_space: Remaining space in current packet
- * @dma_addr: DMA address of current position
- * @in_len: Remaining length in current SKB fragment
- * @unmap_len: Length of SKB fragment
- * @unmap_addr: DMA address of SKB fragment
- * @dma_flags: TX buffer flags for DMA mapping - %EFX_TX_BUF_MAP_SINGLE or 0
- * @protocol: Network protocol (after any VLAN header)
- * @ip_off: Offset of IP header
- * @tcp_off: Offset of TCP header
- * @header_len: Number of bytes of header
- * @ip_base_len: IPv4 tot_len or IPv6 payload_len, before TCP payload
- * @header_dma_addr: Header DMA address, when using option descriptors
- * @header_unmap_len: Header DMA mapped length, or 0 if not using option
- * descriptors
- *
- * The state used during segmentation. It is put into this data structure
- * just to make it easy to pass into inline functions.
- */
-struct tso_state {
- /* Output position */
- unsigned out_len;
- unsigned seqnum;
- u16 ipv4_id;
- unsigned packet_space;
-
- /* Input position */
- dma_addr_t dma_addr;
- unsigned in_len;
- unsigned unmap_len;
- dma_addr_t unmap_addr;
- unsigned short dma_flags;
-
- __be16 protocol;
- unsigned int ip_off;
- unsigned int tcp_off;
- unsigned header_len;
- unsigned int ip_base_len;
- dma_addr_t header_dma_addr;
- unsigned int header_unmap_len;
-};
-
-
-/*
- * Verify that our various assumptions about sk_buffs and the conditions
- * under which TSO will be attempted hold true. Return the protocol number.
- */
-static __be16 efx_tso_check_protocol(struct sk_buff *skb)
-{
- __be16 protocol = skb->protocol;
-
- EFX_BUG_ON_PARANOID(((struct ethhdr *)skb->data)->h_proto !=
- protocol);
- if (protocol == htons(ETH_P_8021Q)) {
- struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
- protocol = veh->h_vlan_encapsulated_proto;
- }
-
- if (protocol == htons(ETH_P_IP)) {
- EFX_BUG_ON_PARANOID(ip_hdr(skb)->protocol != IPPROTO_TCP);
- } else {
- EFX_BUG_ON_PARANOID(protocol != htons(ETH_P_IPV6));
- EFX_BUG_ON_PARANOID(ipv6_hdr(skb)->nexthdr != NEXTHDR_TCP);
- }
- EFX_BUG_ON_PARANOID((PTR_DIFF(tcp_hdr(skb), skb->data)
- + (tcp_hdr(skb)->doff << 2u)) >
- skb_headlen(skb));
-
- return protocol;
-}
-
-static u8 *efx_tsoh_get_buffer(struct efx_tx_queue *tx_queue,
- struct efx_tx_buffer *buffer, unsigned int len)
-{
- u8 *result;
-
- EFX_BUG_ON_PARANOID(buffer->len);
- EFX_BUG_ON_PARANOID(buffer->flags);
- EFX_BUG_ON_PARANOID(buffer->unmap_len);
-
- if (likely(len <= TSOH_STD_SIZE - NET_IP_ALIGN)) {
- unsigned index =
- (tx_queue->insert_count & tx_queue->ptr_mask) / 2;
- struct efx_buffer *page_buf =
- &tx_queue->tsoh_page[index / TSOH_PER_PAGE];
- unsigned offset =
- TSOH_STD_SIZE * (index % TSOH_PER_PAGE) + NET_IP_ALIGN;
-
- if (unlikely(!page_buf->addr) &&
- efx_nic_alloc_buffer(tx_queue->efx, page_buf, PAGE_SIZE,
- GFP_ATOMIC))
- return NULL;
-
- result = (u8 *)page_buf->addr + offset;
- buffer->dma_addr = page_buf->dma_addr + offset;
- buffer->flags = EFX_TX_BUF_CONT;
- } else {
- tx_queue->tso_long_headers++;
-
- buffer->heap_buf = kmalloc(NET_IP_ALIGN + len, GFP_ATOMIC);
- if (unlikely(!buffer->heap_buf))
- return NULL;
- result = (u8 *)buffer->heap_buf + NET_IP_ALIGN;
- buffer->flags = EFX_TX_BUF_CONT | EFX_TX_BUF_HEAP;
- }
-
- buffer->len = len;
-
- return result;
-}
-
-/**
- * efx_tx_queue_insert - push descriptors onto the TX queue
- * @tx_queue: Efx TX queue
- * @dma_addr: DMA address of fragment
- * @len: Length of fragment
- * @final_buffer: The final buffer inserted into the queue
- *
- * Push descriptors onto the TX queue.
- */
-static void efx_tx_queue_insert(struct efx_tx_queue *tx_queue,
- dma_addr_t dma_addr, unsigned len,
- struct efx_tx_buffer **final_buffer)
-{
- struct efx_tx_buffer *buffer;
- struct efx_nic *efx = tx_queue->efx;
- unsigned dma_len;
-
- EFX_BUG_ON_PARANOID(len <= 0);
-
- while (1) {
- buffer = efx_tx_queue_get_insert_buffer(tx_queue);
- ++tx_queue->insert_count;
-
- EFX_BUG_ON_PARANOID(tx_queue->insert_count -
- tx_queue->read_count >=
- efx->txq_entries);
-
- buffer->dma_addr = dma_addr;
-
- dma_len = efx_max_tx_len(efx, dma_addr);
-
- /* If there is enough space to send then do so */
- if (dma_len >= len)
- break;
-
- buffer->len = dma_len;
- buffer->flags = EFX_TX_BUF_CONT;
- dma_addr += dma_len;
- len -= dma_len;
- }
-
- EFX_BUG_ON_PARANOID(!len);
- buffer->len = len;
- *final_buffer = buffer;
-}
-
-
-/*
- * Put a TSO header into the TX queue.
- *
- * This is special-cased because we know that it is small enough to fit in
- * a single fragment, and we know it doesn't cross a page boundary. It
- * also allows us to not worry about end-of-packet etc.
- */
-static int efx_tso_put_header(struct efx_tx_queue *tx_queue,
- struct efx_tx_buffer *buffer, u8 *header)
-{
- if (unlikely(buffer->flags & EFX_TX_BUF_HEAP)) {
- buffer->dma_addr = dma_map_single(&tx_queue->efx->pci_dev->dev,
- header, buffer->len,
- DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(&tx_queue->efx->pci_dev->dev,
- buffer->dma_addr))) {
- kfree(buffer->heap_buf);
- buffer->len = 0;
- buffer->flags = 0;
- return -ENOMEM;
- }
- buffer->unmap_len = buffer->len;
- buffer->dma_offset = 0;
- buffer->flags |= EFX_TX_BUF_MAP_SINGLE;
- }
-
- ++tx_queue->insert_count;
- return 0;
-}
-
-
-/* Remove buffers put into a tx_queue. None of the buffers must have
- * an skb attached.
- */
-static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue,
- unsigned int insert_count)
-{
- struct efx_tx_buffer *buffer;
-
- /* Work backwards until we hit the original insert pointer value */
- while (tx_queue->insert_count != insert_count) {
- --tx_queue->insert_count;
- buffer = __efx_tx_queue_get_insert_buffer(tx_queue);
- efx_dequeue_buffer(tx_queue, buffer, NULL, NULL);
- }
-}
-
-
-/* Parse the SKB header and initialise state. */
-static int tso_start(struct tso_state *st, struct efx_nic *efx,
- struct efx_tx_queue *tx_queue,
- const struct sk_buff *skb)
-{
- struct device *dma_dev = &efx->pci_dev->dev;
- unsigned int header_len, in_len;
- bool use_opt_desc = false;
- dma_addr_t dma_addr;
-
- if (tx_queue->tso_version == 1)
- use_opt_desc = true;
-
- st->ip_off = skb_network_header(skb) - skb->data;
- st->tcp_off = skb_transport_header(skb) - skb->data;
- header_len = st->tcp_off + (tcp_hdr(skb)->doff << 2u);
- in_len = skb_headlen(skb) - header_len;
- st->header_len = header_len;
- st->in_len = in_len;
- if (st->protocol == htons(ETH_P_IP)) {
- st->ip_base_len = st->header_len - st->ip_off;
- st->ipv4_id = ntohs(ip_hdr(skb)->id);
- } else {
- st->ip_base_len = st->header_len - st->tcp_off;
- st->ipv4_id = 0;
- }
- st->seqnum = ntohl(tcp_hdr(skb)->seq);
-
- EFX_BUG_ON_PARANOID(tcp_hdr(skb)->urg);
- EFX_BUG_ON_PARANOID(tcp_hdr(skb)->syn);
- EFX_BUG_ON_PARANOID(tcp_hdr(skb)->rst);
-
- st->out_len = skb->len - header_len;
-
- if (!use_opt_desc) {
- st->header_unmap_len = 0;
-
- if (likely(in_len == 0)) {
- st->dma_flags = 0;
- st->unmap_len = 0;
- return 0;
- }
-
- dma_addr = dma_map_single(dma_dev, skb->data + header_len,
- in_len, DMA_TO_DEVICE);
- st->dma_flags = EFX_TX_BUF_MAP_SINGLE;
- st->dma_addr = dma_addr;
- st->unmap_addr = dma_addr;
- st->unmap_len = in_len;
- } else {
- dma_addr = dma_map_single(dma_dev, skb->data,
- skb_headlen(skb), DMA_TO_DEVICE);
- st->header_dma_addr = dma_addr;
- st->header_unmap_len = skb_headlen(skb);
- st->dma_flags = 0;
- st->dma_addr = dma_addr + header_len;
- st->unmap_len = 0;
- }
-
- return unlikely(dma_mapping_error(dma_dev, dma_addr)) ? -ENOMEM : 0;
-}
-
-static int tso_get_fragment(struct tso_state *st, struct efx_nic *efx,
- skb_frag_t *frag)
-{
- st->unmap_addr = skb_frag_dma_map(&efx->pci_dev->dev, frag, 0,
- skb_frag_size(frag), DMA_TO_DEVICE);
- if (likely(!dma_mapping_error(&efx->pci_dev->dev, st->unmap_addr))) {
- st->dma_flags = 0;
- st->unmap_len = skb_frag_size(frag);
- st->in_len = skb_frag_size(frag);
- st->dma_addr = st->unmap_addr;
- return 0;
- }
- return -ENOMEM;
-}
-
-
-/**
- * tso_fill_packet_with_fragment - form descriptors for the current fragment
- * @tx_queue: Efx TX queue
- * @skb: Socket buffer
- * @st: TSO state
- *
- * Form descriptors for the current fragment, until we reach the end
- * of fragment or end-of-packet.
- */
-static void tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue,
- const struct sk_buff *skb,
- struct tso_state *st)
-{
- struct efx_tx_buffer *buffer;
- int n;
-
- if (st->in_len == 0)
- return;
- if (st->packet_space == 0)
- return;
-
- EFX_BUG_ON_PARANOID(st->in_len <= 0);
- EFX_BUG_ON_PARANOID(st->packet_space <= 0);
-
- n = min(st->in_len, st->packet_space);
-
- st->packet_space -= n;
- st->out_len -= n;
- st->in_len -= n;
-
- efx_tx_queue_insert(tx_queue, st->dma_addr, n, &buffer);
-
- if (st->out_len == 0) {
- /* Transfer ownership of the skb */
- buffer->skb = skb;
- buffer->flags = EFX_TX_BUF_SKB;
- } else if (st->packet_space != 0) {
- buffer->flags = EFX_TX_BUF_CONT;
- }
-
- if (st->in_len == 0) {
- /* Transfer ownership of the DMA mapping */
- buffer->unmap_len = st->unmap_len;
- buffer->dma_offset = buffer->unmap_len - buffer->len;
- buffer->flags |= st->dma_flags;
- st->unmap_len = 0;
- }
-
- st->dma_addr += n;
-}
-
-
-/**
- * tso_start_new_packet - generate a new header and prepare for the new packet
- * @tx_queue: Efx TX queue
- * @skb: Socket buffer
- * @st: TSO state
- *
- * Generate a new header and prepare for the new packet. Return 0 on
- * success, or -%ENOMEM if failed to alloc header.
- */
-static int tso_start_new_packet(struct efx_tx_queue *tx_queue,
- const struct sk_buff *skb,
- struct tso_state *st)
-{
- struct efx_tx_buffer *buffer =
- efx_tx_queue_get_insert_buffer(tx_queue);
- bool is_last = st->out_len <= skb_shinfo(skb)->gso_size;
- u8 tcp_flags_clear;
-
- if (!is_last) {
- st->packet_space = skb_shinfo(skb)->gso_size;
- tcp_flags_clear = 0x09; /* mask out FIN and PSH */
- } else {
- st->packet_space = st->out_len;
- tcp_flags_clear = 0x00;
- }
-
- if (!st->header_unmap_len) {
- /* Allocate and insert a DMA-mapped header buffer. */
- struct tcphdr *tsoh_th;
- unsigned ip_length;
- u8 *header;
- int rc;
-
- header = efx_tsoh_get_buffer(tx_queue, buffer, st->header_len);
- if (!header)
- return -ENOMEM;
-
- tsoh_th = (struct tcphdr *)(header + st->tcp_off);
-
- /* Copy and update the headers. */
- memcpy(header, skb->data, st->header_len);
-
- tsoh_th->seq = htonl(st->seqnum);
- ((u8 *)tsoh_th)[13] &= ~tcp_flags_clear;
-
- ip_length = st->ip_base_len + st->packet_space;
-
- if (st->protocol == htons(ETH_P_IP)) {
- struct iphdr *tsoh_iph =
- (struct iphdr *)(header + st->ip_off);
-
- tsoh_iph->tot_len = htons(ip_length);
- tsoh_iph->id = htons(st->ipv4_id);
- } else {
- struct ipv6hdr *tsoh_iph =
- (struct ipv6hdr *)(header + st->ip_off);
-
- tsoh_iph->payload_len = htons(ip_length);
- }
-
- rc = efx_tso_put_header(tx_queue, buffer, header);
- if (unlikely(rc))
- return rc;
- } else {
- /* Send the original headers with a TSO option descriptor
- * in front
- */
- u8 tcp_flags = ((u8 *)tcp_hdr(skb))[13] & ~tcp_flags_clear;
-
- buffer->flags = EFX_TX_BUF_OPTION;
- buffer->len = 0;
- buffer->unmap_len = 0;
- EFX_POPULATE_QWORD_5(buffer->option,
- ESF_DZ_TX_DESC_IS_OPT, 1,
- ESF_DZ_TX_OPTION_TYPE,
- ESE_DZ_TX_OPTION_DESC_TSO,
- ESF_DZ_TX_TSO_TCP_FLAGS, tcp_flags,
- ESF_DZ_TX_TSO_IP_ID, st->ipv4_id,
- ESF_DZ_TX_TSO_TCP_SEQNO, st->seqnum);
- ++tx_queue->insert_count;
-
- /* We mapped the headers in tso_start(). Unmap them
- * when the last segment is completed.
- */
- buffer = efx_tx_queue_get_insert_buffer(tx_queue);
- buffer->dma_addr = st->header_dma_addr;
- buffer->len = st->header_len;
- if (is_last) {
- buffer->flags = EFX_TX_BUF_CONT | EFX_TX_BUF_MAP_SINGLE;
- buffer->unmap_len = st->header_unmap_len;
- buffer->dma_offset = 0;
- /* Ensure we only unmap them once in case of a
- * later DMA mapping error and rollback
- */
- st->header_unmap_len = 0;
- } else {
- buffer->flags = EFX_TX_BUF_CONT;
- buffer->unmap_len = 0;
- }
- ++tx_queue->insert_count;
- }
-
- st->seqnum += skb_shinfo(skb)->gso_size;
-
- /* Linux leaves suitable gaps in the IP ID space for us to fill. */
- ++st->ipv4_id;
-
- ++tx_queue->tso_packets;
-
- ++tx_queue->tx_packets;
-
- return 0;
-}
-
-
-/**
- * efx_enqueue_skb_tso - segment and transmit a TSO socket buffer
- * @tx_queue: Efx TX queue
- * @skb: Socket buffer
- *
- * Context: You must hold netif_tx_lock() to call this function.
- *
- * Add socket buffer @skb to @tx_queue, doing TSO or return != 0 if
- * @skb was not enqueued. In all cases @skb is consumed. Return
- * %NETDEV_TX_OK.
- */
-static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
- struct sk_buff *skb)
-{
- struct efx_nic *efx = tx_queue->efx;
- unsigned int old_insert_count = tx_queue->insert_count;
- int frag_i, rc;
- struct tso_state state;
-
- /* Find the packet protocol and sanity-check it */
- state.protocol = efx_tso_check_protocol(skb);
-
- rc = tso_start(&state, efx, tx_queue, skb);
- if (rc)
- goto mem_err;
-
- if (likely(state.in_len == 0)) {
- /* Grab the first payload fragment. */
- EFX_BUG_ON_PARANOID(skb_shinfo(skb)->nr_frags < 1);
- frag_i = 0;
- rc = tso_get_fragment(&state, efx,
- skb_shinfo(skb)->frags + frag_i);
- if (rc)
- goto mem_err;
- } else {
- /* Payload starts in the header area. */
- frag_i = -1;
- }
-
- if (tso_start_new_packet(tx_queue, skb, &state) < 0)
- goto mem_err;
-
- while (1) {
- tso_fill_packet_with_fragment(tx_queue, skb, &state);
-
- /* Move onto the next fragment? */
- if (state.in_len == 0) {
- if (++frag_i >= skb_shinfo(skb)->nr_frags)
- /* End of payload reached. */
- break;
- rc = tso_get_fragment(&state, efx,
- skb_shinfo(skb)->frags + frag_i);
- if (rc)
- goto mem_err;
- }
-
- /* Start at new packet? */
- if (state.packet_space == 0 &&
- tso_start_new_packet(tx_queue, skb, &state) < 0)
- goto mem_err;
- }
-
- netdev_tx_sent_queue(tx_queue->core_txq, skb->len);
-
- efx_tx_maybe_stop_queue(tx_queue);
-
- /* Pass off to hardware */
- if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
- struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
-
- /* There could be packets left on the partner queue if those
- * SKBs had skb->xmit_more set. If we do not push those they
- * could be left for a long time and cause a netdev watchdog.
- */
- if (txq2->xmit_more_available)
- efx_nic_push_buffers(txq2);
-
- efx_nic_push_buffers(tx_queue);
- } else {
- tx_queue->xmit_more_available = skb->xmit_more;
- }
-
- tx_queue->tso_bursts++;
- return NETDEV_TX_OK;
-
- mem_err:
- netif_err(efx, tx_err, efx->net_dev,
- "Out of memory for TSO headers, or DMA mapping error\n");
- dev_kfree_skb_any(skb);
-
- /* Free the DMA mapping we were in the process of writing out */
- if (state.unmap_len) {
- if (state.dma_flags & EFX_TX_BUF_MAP_SINGLE)
- dma_unmap_single(&efx->pci_dev->dev, state.unmap_addr,
- state.unmap_len, DMA_TO_DEVICE);
- else
- dma_unmap_page(&efx->pci_dev->dev, state.unmap_addr,
- state.unmap_len, DMA_TO_DEVICE);
- }
-
- /* Free the header DMA mapping, if using option descriptors */
- if (state.header_unmap_len)
- dma_unmap_single(&efx->pci_dev->dev, state.header_dma_addr,
- state.header_unmap_len, DMA_TO_DEVICE);
-
- efx_enqueue_unwind(tx_queue, old_insert_count);
- return NETDEV_TX_OK;
-}
diff --git a/drivers/net/ethernet/sfc/tx.h b/drivers/net/ethernet/sfc/tx.h
new file mode 100644
index 0000000..1cccc97
--- /dev/null
+++ b/drivers/net/ethernet/sfc/tx.h
@@ -0,0 +1,27 @@
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2005-2006 Fen Systems Ltd.
+ * Copyright 2006-2015 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef EFX_TX_H
+#define EFX_TX_H
+
+#include <linux/types.h>
+
+/* Driver internal tx-path related declarations. */
+
+unsigned int efx_tx_limit_len(struct efx_tx_queue *tx_queue,
+ dma_addr_t dma_addr, unsigned int len);
+
+u8 *efx_tx_get_copy_buffer_limited(struct efx_tx_queue *tx_queue,
+ struct efx_tx_buffer *buffer, size_t len);
+
+int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
+ bool *data_mapped);
+
+#endif /* EFX_TX_H */
diff --git a/drivers/net/ethernet/sfc/tx_tso.c b/drivers/net/ethernet/sfc/tx_tso.c
new file mode 100644
index 0000000..6032887
--- /dev/null
+++ b/drivers/net/ethernet/sfc/tx_tso.c
@@ -0,0 +1,452 @@
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2005-2006 Fen Systems Ltd.
+ * Copyright 2005-2015 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#include <linux/pci.h>
+#include <linux/tcp.h>
+#include <linux/ip.h>
+#include <linux/in.h>
+#include <linux/ipv6.h>
+#include <linux/slab.h>
+#include <net/ipv6.h>
+#include <linux/if_ether.h>
+#include <linux/highmem.h>
+#include <linux/moduleparam.h>
+#include <linux/cache.h>
+#include "net_driver.h"
+#include "efx.h"
+#include "io.h"
+#include "nic.h"
+#include "tx.h"
+#include "workarounds.h"
+#include "ef10_regs.h"
+
+/* Efx legacy TCP segmentation acceleration.
+ *
+ * Utilises firmware support to go faster than GSO (but not as fast as TSOv2).
+ *
+ * Requires TX checksum offload support.
+ */
+
+#define PTR_DIFF(p1, p2) ((u8 *)(p1) - (u8 *)(p2))
+
+/**
+ * struct tso_state - TSO state for an SKB
+ * @out_len: Remaining length in current segment
+ * @seqnum: Current sequence number
+ * @ipv4_id: Current IPv4 ID, host endian
+ * @packet_space: Remaining space in current packet
+ * @dma_addr: DMA address of current position
+ * @in_len: Remaining length in current SKB fragment
+ * @unmap_len: Length of SKB fragment
+ * @unmap_addr: DMA address of SKB fragment
+ * @protocol: Network protocol (after any VLAN header)
+ * @ip_off: Offset of IP header
+ * @tcp_off: Offset of TCP header
+ * @header_len: Number of bytes of header
+ * @ip_base_len: IPv4 tot_len or IPv6 payload_len, before TCP payload
+ * @header_dma_addr: Header DMA address
+ * @header_unmap_len: Header DMA mapped length
+ *
+ * The state used during segmentation. It is put into this data structure
+ * just to make it easy to pass into inline functions.
+ */
+struct tso_state {
+ /* Output position */
+ unsigned int out_len;
+ unsigned int seqnum;
+ u16 ipv4_id;
+ unsigned int packet_space;
+
+ /* Input position */
+ dma_addr_t dma_addr;
+ unsigned int in_len;
+ unsigned int unmap_len;
+ dma_addr_t unmap_addr;
+
+ __be16 protocol;
+ unsigned int ip_off;
+ unsigned int tcp_off;
+ unsigned int header_len;
+ unsigned int ip_base_len;
+ dma_addr_t header_dma_addr;
+ unsigned int header_unmap_len;
+};
+
+static inline void prefetch_ptr(struct efx_tx_queue *tx_queue)
+{
+ unsigned int insert_ptr = efx_tx_queue_get_insert_index(tx_queue);
+ char *ptr;
+
+ ptr = (char *) (tx_queue->buffer + insert_ptr);
+ prefetch(ptr);
+ prefetch(ptr + 0x80);
+
+ ptr = (char *) (((efx_qword_t *)tx_queue->txd.buf.addr) + insert_ptr);
+ prefetch(ptr);
+ prefetch(ptr + 0x80);
+}
+
+/**
+ * efx_tx_queue_insert - push descriptors onto the TX queue
+ * @tx_queue: Efx TX queue
+ * @dma_addr: DMA address of fragment
+ * @len: Length of fragment
+ * @final_buffer: The final buffer inserted into the queue
+ *
+ * Push descriptors onto the TX queue.
+ */
+static void efx_tx_queue_insert(struct efx_tx_queue *tx_queue,
+ dma_addr_t dma_addr, unsigned int len,
+ struct efx_tx_buffer **final_buffer)
+{
+ struct efx_tx_buffer *buffer;
+ unsigned int dma_len;
+
+ EFX_BUG_ON_PARANOID(len <= 0);
+
+ while (1) {
+ buffer = efx_tx_queue_get_insert_buffer(tx_queue);
+ ++tx_queue->insert_count;
+
+ EFX_BUG_ON_PARANOID(tx_queue->insert_count -
+ tx_queue->read_count >=
+ tx_queue->efx->txq_entries);
+
+ buffer->dma_addr = dma_addr;
+
+ dma_len = tx_queue->efx->type->tx_limit_len(tx_queue,
+ dma_addr, len);
+
+ /* If there's space for everything this is our last buffer. */
+ if (dma_len >= len)
+ break;
+
+ buffer->len = dma_len;
+ buffer->flags = EFX_TX_BUF_CONT;
+ dma_addr += dma_len;
+ len -= dma_len;
+ }
+
+ EFX_BUG_ON_PARANOID(!len);
+ buffer->len = len;
+ *final_buffer = buffer;
+}
+
+/*
+ * Verify that our various assumptions about sk_buffs and the conditions
+ * under which TSO will be attempted hold true. Return the protocol number.
+ */
+static __be16 efx_tso_check_protocol(struct sk_buff *skb)
+{
+ __be16 protocol = skb->protocol;
+
+ EFX_BUG_ON_PARANOID(((struct ethhdr *)skb->data)->h_proto !=
+ protocol);
+ if (protocol == htons(ETH_P_8021Q)) {
+ struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
+
+ protocol = veh->h_vlan_encapsulated_proto;
+ }
+
+ if (protocol == htons(ETH_P_IP)) {
+ EFX_BUG_ON_PARANOID(ip_hdr(skb)->protocol != IPPROTO_TCP);
+ } else {
+ EFX_BUG_ON_PARANOID(protocol != htons(ETH_P_IPV6));
+ EFX_BUG_ON_PARANOID(ipv6_hdr(skb)->nexthdr != NEXTHDR_TCP);
+ }
+ EFX_BUG_ON_PARANOID((PTR_DIFF(tcp_hdr(skb), skb->data)
+ + (tcp_hdr(skb)->doff << 2u)) >
+ skb_headlen(skb));
+
+ return protocol;
+}
+
+
+/* Parse the SKB header and initialise state. */
+static int tso_start(struct tso_state *st, struct efx_nic *efx,
+ struct efx_tx_queue *tx_queue,
+ const struct sk_buff *skb)
+{
+ struct device *dma_dev = &efx->pci_dev->dev;
+ unsigned int header_len, in_len;
+ dma_addr_t dma_addr;
+
+ st->ip_off = skb_network_header(skb) - skb->data;
+ st->tcp_off = skb_transport_header(skb) - skb->data;
+ header_len = st->tcp_off + (tcp_hdr(skb)->doff << 2u);
+ in_len = skb_headlen(skb) - header_len;
+ st->header_len = header_len;
+ st->in_len = in_len;
+ if (st->protocol == htons(ETH_P_IP)) {
+ st->ip_base_len = st->header_len - st->ip_off;
+ st->ipv4_id = ntohs(ip_hdr(skb)->id);
+ } else {
+ st->ip_base_len = st->header_len - st->tcp_off;
+ st->ipv4_id = 0;
+ }
+ st->seqnum = ntohl(tcp_hdr(skb)->seq);
+
+ EFX_BUG_ON_PARANOID(tcp_hdr(skb)->urg);
+ EFX_BUG_ON_PARANOID(tcp_hdr(skb)->syn);
+ EFX_BUG_ON_PARANOID(tcp_hdr(skb)->rst);
+
+ st->out_len = skb->len - header_len;
+
+ dma_addr = dma_map_single(dma_dev, skb->data,
+ skb_headlen(skb), DMA_TO_DEVICE);
+ st->header_dma_addr = dma_addr;
+ st->header_unmap_len = skb_headlen(skb);
+ st->dma_addr = dma_addr + header_len;
+ st->unmap_len = 0;
+
+ return unlikely(dma_mapping_error(dma_dev, dma_addr)) ? -ENOMEM : 0;
+}
+
+static int tso_get_fragment(struct tso_state *st, struct efx_nic *efx,
+ skb_frag_t *frag)
+{
+ st->unmap_addr = skb_frag_dma_map(&efx->pci_dev->dev, frag, 0,
+ skb_frag_size(frag), DMA_TO_DEVICE);
+ if (likely(!dma_mapping_error(&efx->pci_dev->dev, st->unmap_addr))) {
+ st->unmap_len = skb_frag_size(frag);
+ st->in_len = skb_frag_size(frag);
+ st->dma_addr = st->unmap_addr;
+ return 0;
+ }
+ return -ENOMEM;
+}
+
+
+/**
+ * tso_fill_packet_with_fragment - form descriptors for the current fragment
+ * @tx_queue: Efx TX queue
+ * @skb: Socket buffer
+ * @st: TSO state
+ *
+ * Form descriptors for the current fragment, until we reach the end
+ * of fragment or end-of-packet.
+ */
+static void tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue,
+ const struct sk_buff *skb,
+ struct tso_state *st)
+{
+ struct efx_tx_buffer *buffer;
+ int n;
+
+ if (st->in_len == 0)
+ return;
+ if (st->packet_space == 0)
+ return;
+
+ EFX_BUG_ON_PARANOID(st->in_len <= 0);
+ EFX_BUG_ON_PARANOID(st->packet_space <= 0);
+
+ n = min(st->in_len, st->packet_space);
+
+ st->packet_space -= n;
+ st->out_len -= n;
+ st->in_len -= n;
+
+ efx_tx_queue_insert(tx_queue, st->dma_addr, n, &buffer);
+
+ if (st->out_len == 0) {
+ /* Transfer ownership of the skb */
+ buffer->skb = skb;
+ buffer->flags = EFX_TX_BUF_SKB;
+ } else if (st->packet_space != 0) {
+ buffer->flags = EFX_TX_BUF_CONT;
+ }
+
+ if (st->in_len == 0) {
+ /* Transfer ownership of the DMA mapping */
+ buffer->unmap_len = st->unmap_len;
+ buffer->dma_offset = buffer->unmap_len - buffer->len;
+ st->unmap_len = 0;
+ }
+
+ st->dma_addr += n;
+}
+
+
+#define TCP_FLAGS_OFFSET 13
+
+/**
+ * tso_start_new_packet - generate a new header and prepare for the new packet
+ * @tx_queue: Efx TX queue
+ * @skb: Socket buffer
+ * @st: TSO state
+ *
+ * Generate a new header and prepare for the new packet. Return 0 on
+ * success, or -%ENOMEM if failed to alloc header, or other negative error.
+ */
+static int tso_start_new_packet(struct efx_tx_queue *tx_queue,
+ const struct sk_buff *skb,
+ struct tso_state *st)
+{
+ struct efx_tx_buffer *buffer =
+ efx_tx_queue_get_insert_buffer(tx_queue);
+ bool is_last = st->out_len <= skb_shinfo(skb)->gso_size;
+ u8 tcp_flags_mask, tcp_flags;
+
+ if (!is_last) {
+ st->packet_space = skb_shinfo(skb)->gso_size;
+ tcp_flags_mask = 0x09; /* mask out FIN and PSH */
+ } else {
+ st->packet_space = st->out_len;
+ tcp_flags_mask = 0x00;
+ }
+
+ if (WARN_ON(!st->header_unmap_len))
+ return -EINVAL;
+ /* Send the original headers with a TSO option descriptor
+ * in front
+ */
+ tcp_flags = ((u8 *)tcp_hdr(skb))[TCP_FLAGS_OFFSET] & ~tcp_flags_mask;
+
+ buffer->flags = EFX_TX_BUF_OPTION;
+ buffer->len = 0;
+ buffer->unmap_len = 0;
+ EFX_POPULATE_QWORD_5(buffer->option,
+ ESF_DZ_TX_DESC_IS_OPT, 1,
+ ESF_DZ_TX_OPTION_TYPE,
+ ESE_DZ_TX_OPTION_DESC_TSO,
+ ESF_DZ_TX_TSO_TCP_FLAGS, tcp_flags,
+ ESF_DZ_TX_TSO_IP_ID, st->ipv4_id,
+ ESF_DZ_TX_TSO_TCP_SEQNO, st->seqnum);
+ ++tx_queue->insert_count;
+
+ /* We mapped the headers in tso_start(). Unmap them
+ * when the last segment is completed.
+ */
+ buffer = efx_tx_queue_get_insert_buffer(tx_queue);
+ buffer->dma_addr = st->header_dma_addr;
+ buffer->len = st->header_len;
+ if (is_last) {
+ buffer->flags = EFX_TX_BUF_CONT | EFX_TX_BUF_MAP_SINGLE;
+ buffer->unmap_len = st->header_unmap_len;
+ buffer->dma_offset = 0;
+ /* Ensure we only unmap them once in case of a
+ * later DMA mapping error and rollback
+ */
+ st->header_unmap_len = 0;
+ } else {
+ buffer->flags = EFX_TX_BUF_CONT;
+ buffer->unmap_len = 0;
+ }
+ ++tx_queue->insert_count;
+
+ st->seqnum += skb_shinfo(skb)->gso_size;
+
+ /* Linux leaves suitable gaps in the IP ID space for us to fill. */
+ ++st->ipv4_id;
+
+ return 0;
+}
+
+/**
+ * efx_enqueue_skb_tso - segment and transmit a TSO socket buffer
+ * @tx_queue: Efx TX queue
+ * @skb: Socket buffer
+ * @data_mapped: Did we map the data? Always set to true
+ * by this on success.
+ *
+ * Context: You must hold netif_tx_lock() to call this function.
+ *
+ * Add socket buffer @skb to @tx_queue, doing TSO or return != 0 if
+ * @skb was not enqueued. @skb is consumed unless return value is
+ * %EINVAL.
+ */
+int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
+ struct sk_buff *skb,
+ bool *data_mapped)
+{
+ struct efx_nic *efx = tx_queue->efx;
+ int frag_i, rc;
+ struct tso_state state;
+
+ if (tx_queue->tso_version != 1)
+ return -EINVAL;
+
+ prefetch(skb->data);
+
+ /* Find the packet protocol and sanity-check it */
+ state.protocol = efx_tso_check_protocol(skb);
+
+ EFX_BUG_ON_PARANOID(tx_queue->write_count != tx_queue->insert_count);
+
+ rc = tso_start(&state, efx, tx_queue, skb);
+ if (rc)
+ goto fail;
+
+ if (likely(state.in_len == 0)) {
+ /* Grab the first payload fragment. */
+ EFX_BUG_ON_PARANOID(skb_shinfo(skb)->nr_frags < 1);
+ frag_i = 0;
+ rc = tso_get_fragment(&state, efx,
+ skb_shinfo(skb)->frags + frag_i);
+ if (rc)
+ goto fail;
+ } else {
+ /* Payload starts in the header area. */
+ frag_i = -1;
+ }
+
+ rc = tso_start_new_packet(tx_queue, skb, &state);
+ if (rc)
+ goto fail;
+
+ prefetch_ptr(tx_queue);
+
+ while (1) {
+ tso_fill_packet_with_fragment(tx_queue, skb, &state);
+
+ /* Move onto the next fragment? */
+ if (state.in_len == 0) {
+ if (++frag_i >= skb_shinfo(skb)->nr_frags)
+ /* End of payload reached. */
+ break;
+ rc = tso_get_fragment(&state, efx,
+ skb_shinfo(skb)->frags + frag_i);
+ if (rc)
+ goto fail;
+ }
+
+ /* Start at new packet? */
+ if (state.packet_space == 0) {
+ rc = tso_start_new_packet(tx_queue, skb, &state);
+ if (rc)
+ goto fail;
+ }
+ }
+
+ *data_mapped = true;
+
+ return 0;
+
+fail:
+ if (rc == -ENOMEM)
+ netif_err(efx, tx_err, efx->net_dev,
+ "Out of memory for TSO headers, or DMA mapping error\n");
+ else
+ netif_err(efx, tx_err, efx->net_dev, "TSO failed, rc = %d\n", rc);
+
+ /* Free the DMA mapping we were in the process of writing out */
+ if (state.unmap_len) {
+ dma_unmap_page(&efx->pci_dev->dev, state.unmap_addr,
+ state.unmap_len, DMA_TO_DEVICE);
+ }
+
+ /* Free the header DMA mapping */
+ if (state.header_unmap_len)
+ dma_unmap_single(&efx->pci_dev->dev, state.header_dma_addr,
+ state.header_unmap_len, DMA_TO_DEVICE);
+
+ return rc;
+}
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index cdb343f..be09573 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -1956,11 +1956,6 @@ static void smsc911x_ethtool_getdrvinfo(struct net_device *dev,
sizeof(info->bus_info));
}
-static int smsc911x_ethtool_nwayreset(struct net_device *dev)
-{
- return phy_start_aneg(dev->phydev);
-}
-
static u32 smsc911x_ethtool_getmsglevel(struct net_device *dev)
{
struct smsc911x_data *pdata = netdev_priv(dev);
@@ -2132,7 +2127,7 @@ static int smsc911x_ethtool_set_eeprom(struct net_device *dev,
static const struct ethtool_ops smsc911x_ethtool_ops = {
.get_link = ethtool_op_get_link,
.get_drvinfo = smsc911x_ethtool_getdrvinfo,
- .nway_reset = smsc911x_ethtool_nwayreset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_msglevel = smsc911x_ethtool_getmsglevel,
.set_msglevel = smsc911x_ethtool_setmsglevel,
.get_regs_len = smsc911x_ethtool_getregslen,
diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c
index b7bfed4b..3174aeb 100644
--- a/drivers/net/ethernet/smsc/smsc9420.c
+++ b/drivers/net/ethernet/smsc/smsc9420.c
@@ -254,14 +254,6 @@ static void smsc9420_ethtool_set_msglevel(struct net_device *netdev, u32 data)
pd->msg_enable = data;
}
-static int smsc9420_ethtool_nway_reset(struct net_device *netdev)
-{
- if (!netdev->phydev)
- return -ENODEV;
-
- return phy_start_aneg(netdev->phydev);
-}
-
static int smsc9420_ethtool_getregslen(struct net_device *dev)
{
/* all smsc9420 registers plus all phy registers */
@@ -417,7 +409,7 @@ static const struct ethtool_ops smsc9420_ethtool_ops = {
.get_drvinfo = smsc9420_ethtool_get_drvinfo,
.get_msglevel = smsc9420_ethtool_get_msglevel,
.set_msglevel = smsc9420_ethtool_set_msglevel,
- .nway_reset = smsc9420_ethtool_nway_reset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_link = ethtool_op_get_link,
.get_eeprom_len = smsc9420_ethtool_get_eeprom_len,
.get_eeprom = smsc9420_ethtool_get_eeprom,
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 3818c5e..6e9fcc3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -69,6 +69,17 @@
the stmmac device driver. This driver is used for Meson6,
Meson8, Meson8b and GXBB SoCs.
+config DWMAC_OXNAS
+ tristate "Oxford Semiconductor OXNAS dwmac support"
+ default ARCH_OXNAS
+ depends on OF && COMMON_CLK && (ARCH_OXNAS || COMPILE_TEST)
+ select MFD_SYSCON
+ help
+ Support for Ethernet controller on Oxford Semiconductor OXNAS SoCs.
+
+ This selects the Oxford Semiconductor OXNASSoC glue layer support for
+ the stmmac device driver. This driver is used for OX820.
+
config DWMAC_ROCKCHIP
tristate "Rockchip dwmac support"
default ARCH_ROCKCHIP
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index 5d6ece5..8f83a86 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -10,6 +10,7 @@
obj-$(CONFIG_DWMAC_IPQ806X) += dwmac-ipq806x.o
obj-$(CONFIG_DWMAC_LPC18XX) += dwmac-lpc18xx.o
obj-$(CONFIG_DWMAC_MESON) += dwmac-meson.o dwmac-meson8b.o
+obj-$(CONFIG_DWMAC_OXNAS) += dwmac-oxnas.o
obj-$(CONFIG_DWMAC_ROCKCHIP) += dwmac-rk.o
obj-$(CONFIG_DWMAC_SOCFPGA) += dwmac-altr-socfpga.o
obj-$(CONFIG_DWMAC_STI) += dwmac-sti.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
index b3e669a..026e8e9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
@@ -34,7 +34,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
unsigned int entry = priv->cur_tx;
struct dma_desc *desc = priv->dma_tx + entry;
unsigned int nopaged_len = skb_headlen(skb);
- unsigned int bmax;
+ unsigned int bmax, des2;
unsigned int i = 1, len;
if (priv->plat->enh_desc)
@@ -44,11 +44,12 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
len = nopaged_len - bmax;
- desc->des2 = dma_map_single(priv->device, skb->data,
- bmax, DMA_TO_DEVICE);
- if (dma_mapping_error(priv->device, desc->des2))
+ des2 = dma_map_single(priv->device, skb->data,
+ bmax, DMA_TO_DEVICE);
+ desc->des2 = cpu_to_le32(des2);
+ if (dma_mapping_error(priv->device, des2))
return -1;
- priv->tx_skbuff_dma[entry].buf = desc->des2;
+ priv->tx_skbuff_dma[entry].buf = des2;
priv->tx_skbuff_dma[entry].len = bmax;
/* do not close the descriptor and do not set own bit */
priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_CHAIN_MODE,
@@ -60,12 +61,13 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
desc = priv->dma_tx + entry;
if (len > bmax) {
- desc->des2 = dma_map_single(priv->device,
- (skb->data + bmax * i),
- bmax, DMA_TO_DEVICE);
- if (dma_mapping_error(priv->device, desc->des2))
+ des2 = dma_map_single(priv->device,
+ (skb->data + bmax * i),
+ bmax, DMA_TO_DEVICE);
+ desc->des2 = cpu_to_le32(des2);
+ if (dma_mapping_error(priv->device, des2))
return -1;
- priv->tx_skbuff_dma[entry].buf = desc->des2;
+ priv->tx_skbuff_dma[entry].buf = des2;
priv->tx_skbuff_dma[entry].len = bmax;
priv->hw->desc->prepare_tx_desc(desc, 0, bmax, csum,
STMMAC_CHAIN_MODE, 1,
@@ -73,12 +75,13 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
len -= bmax;
i++;
} else {
- desc->des2 = dma_map_single(priv->device,
- (skb->data + bmax * i), len,
- DMA_TO_DEVICE);
- if (dma_mapping_error(priv->device, desc->des2))
+ des2 = dma_map_single(priv->device,
+ (skb->data + bmax * i), len,
+ DMA_TO_DEVICE);
+ desc->des2 = cpu_to_le32(des2);
+ if (dma_mapping_error(priv->device, des2))
return -1;
- priv->tx_skbuff_dma[entry].buf = desc->des2;
+ priv->tx_skbuff_dma[entry].buf = des2;
priv->tx_skbuff_dma[entry].len = len;
/* last descriptor can be set now */
priv->hw->desc->prepare_tx_desc(desc, 0, len, csum,
@@ -119,19 +122,19 @@ static void stmmac_init_dma_chain(void *des, dma_addr_t phy_addr,
struct dma_extended_desc *p = (struct dma_extended_desc *)des;
for (i = 0; i < (size - 1); i++) {
dma_phy += sizeof(struct dma_extended_desc);
- p->basic.des3 = (unsigned int)dma_phy;
+ p->basic.des3 = cpu_to_le32((unsigned int)dma_phy);
p++;
}
- p->basic.des3 = (unsigned int)phy_addr;
+ p->basic.des3 = cpu_to_le32((unsigned int)phy_addr);
} else {
struct dma_desc *p = (struct dma_desc *)des;
for (i = 0; i < (size - 1); i++) {
dma_phy += sizeof(struct dma_desc);
- p->des3 = (unsigned int)dma_phy;
+ p->des3 = cpu_to_le32((unsigned int)dma_phy);
p++;
}
- p->des3 = (unsigned int)phy_addr;
+ p->des3 = cpu_to_le32((unsigned int)phy_addr);
}
}
@@ -144,10 +147,10 @@ static void stmmac_refill_desc3(void *priv_ptr, struct dma_desc *p)
* 1588-2002 time stamping is enabled, hence reinitialize it
* to keep explicit chaining in the descriptor.
*/
- p->des3 = (unsigned int)(priv->dma_rx_phy +
- (((priv->dirty_rx) + 1) %
- DMA_RX_SIZE) *
- sizeof(struct dma_desc));
+ p->des3 = cpu_to_le32((unsigned int)(priv->dma_rx_phy +
+ (((priv->dirty_rx) + 1) %
+ DMA_RX_SIZE) *
+ sizeof(struct dma_desc)));
}
static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p)
@@ -161,9 +164,9 @@ static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p)
* 1588-2002 time stamping is enabled, hence reinitialize it
* to keep explicit chaining in the descriptor.
*/
- p->des3 = (unsigned int)((priv->dma_tx_phy +
- ((priv->dirty_tx + 1) % DMA_TX_SIZE))
- * sizeof(struct dma_desc));
+ p->des3 = cpu_to_le32((unsigned int)((priv->dma_tx_phy +
+ ((priv->dirty_tx + 1) % DMA_TX_SIZE))
+ * sizeof(struct dma_desc)));
}
const struct stmmac_mode_ops chain_mode_ops = {
diff --git a/drivers/net/ethernet/stmicro/stmmac/descs.h b/drivers/net/ethernet/stmicro/stmmac/descs.h
index 2e4c171..4000af4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/descs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/descs.h
@@ -87,7 +87,7 @@
#define TDES0_ERROR_SUMMARY BIT(15)
#define TDES0_IP_HEADER_ERROR BIT(16)
#define TDES0_TIME_STAMP_STATUS BIT(17)
-#define TDES0_OWN BIT(31)
+#define TDES0_OWN ((u32)BIT(31)) /* silence sparse */
/* TDES1 */
#define TDES1_BUFFER1_SIZE_MASK GENMASK(10, 0)
#define TDES1_BUFFER2_SIZE_MASK GENMASK(21, 11)
@@ -130,7 +130,7 @@
#define ETDES0_FIRST_SEGMENT BIT(28)
#define ETDES0_LAST_SEGMENT BIT(29)
#define ETDES0_INTERRUPT BIT(30)
-#define ETDES0_OWN BIT(31)
+#define ETDES0_OWN ((u32)BIT(31)) /* silence sparse */
/* TDES1 */
#define ETDES1_BUFFER1_SIZE_MASK GENMASK(12, 0)
#define ETDES1_BUFFER2_SIZE_MASK GENMASK(28, 16)
@@ -166,19 +166,19 @@
/* Basic descriptor structure for normal and alternate descriptors */
struct dma_desc {
- unsigned int des0;
- unsigned int des1;
- unsigned int des2;
- unsigned int des3;
+ __le32 des0;
+ __le32 des1;
+ __le32 des2;
+ __le32 des3;
};
/* Extended descriptor structure (e.g. >= databook 3.50a) */
struct dma_extended_desc {
struct dma_desc basic; /* Basic descriptors */
- unsigned int des4; /* Extended Status */
- unsigned int des5; /* Reserved */
- unsigned int des6; /* Tx/Rx Timestamp Low */
- unsigned int des7; /* Tx/Rx Timestamp High */
+ __le32 des4; /* Extended Status */
+ __le32 des5; /* Reserved */
+ __le32 des6; /* Tx/Rx Timestamp Low */
+ __le32 des7; /* Tx/Rx Timestamp High */
};
/* Transmit checksum insertion control */
diff --git a/drivers/net/ethernet/stmicro/stmmac/descs_com.h b/drivers/net/ethernet/stmicro/stmmac/descs_com.h
index 7635a46..1d181e2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/descs_com.h
+++ b/drivers/net/ethernet/stmicro/stmmac/descs_com.h
@@ -35,47 +35,50 @@
/* Enhanced descriptors */
static inline void ehn_desc_rx_set_on_ring(struct dma_desc *p, int end)
{
- p->des1 |= ((BUF_SIZE_8KiB - 1) << ERDES1_BUFFER2_SIZE_SHIFT)
- & ERDES1_BUFFER2_SIZE_MASK;
+ p->des1 |= cpu_to_le32(((BUF_SIZE_8KiB - 1)
+ << ERDES1_BUFFER2_SIZE_SHIFT)
+ & ERDES1_BUFFER2_SIZE_MASK);
if (end)
- p->des1 |= ERDES1_END_RING;
+ p->des1 |= cpu_to_le32(ERDES1_END_RING);
}
static inline void enh_desc_end_tx_desc_on_ring(struct dma_desc *p, int end)
{
if (end)
- p->des0 |= ETDES0_END_RING;
+ p->des0 |= cpu_to_le32(ETDES0_END_RING);
else
- p->des0 &= ~ETDES0_END_RING;
+ p->des0 &= cpu_to_le32(~ETDES0_END_RING);
}
static inline void enh_set_tx_desc_len_on_ring(struct dma_desc *p, int len)
{
if (unlikely(len > BUF_SIZE_4KiB)) {
- p->des1 |= (((len - BUF_SIZE_4KiB) << ETDES1_BUFFER2_SIZE_SHIFT)
+ p->des1 |= cpu_to_le32((((len - BUF_SIZE_4KiB)
+ << ETDES1_BUFFER2_SIZE_SHIFT)
& ETDES1_BUFFER2_SIZE_MASK) | (BUF_SIZE_4KiB
- & ETDES1_BUFFER1_SIZE_MASK);
+ & ETDES1_BUFFER1_SIZE_MASK));
} else
- p->des1 |= (len & ETDES1_BUFFER1_SIZE_MASK);
+ p->des1 |= cpu_to_le32((len & ETDES1_BUFFER1_SIZE_MASK));
}
/* Normal descriptors */
static inline void ndesc_rx_set_on_ring(struct dma_desc *p, int end)
{
- p->des1 |= ((BUF_SIZE_2KiB - 1) << RDES1_BUFFER2_SIZE_SHIFT)
- & RDES1_BUFFER2_SIZE_MASK;
+ p->des1 |= cpu_to_le32(((BUF_SIZE_2KiB - 1)
+ << RDES1_BUFFER2_SIZE_SHIFT)
+ & RDES1_BUFFER2_SIZE_MASK);
if (end)
- p->des1 |= RDES1_END_RING;
+ p->des1 |= cpu_to_le32(RDES1_END_RING);
}
static inline void ndesc_end_tx_desc_on_ring(struct dma_desc *p, int end)
{
if (end)
- p->des1 |= TDES1_END_RING;
+ p->des1 |= cpu_to_le32(TDES1_END_RING);
else
- p->des1 &= ~TDES1_END_RING;
+ p->des1 &= cpu_to_le32(~TDES1_END_RING);
}
static inline void norm_set_tx_desc_len_on_ring(struct dma_desc *p, int len)
@@ -83,10 +86,11 @@ static inline void norm_set_tx_desc_len_on_ring(struct dma_desc *p, int len)
if (unlikely(len > BUF_SIZE_2KiB)) {
unsigned int buffer1 = (BUF_SIZE_2KiB - 1)
& TDES1_BUFFER1_SIZE_MASK;
- p->des1 |= ((((len - buffer1) << TDES1_BUFFER2_SIZE_SHIFT)
- & TDES1_BUFFER2_SIZE_MASK) | buffer1);
+ p->des1 |= cpu_to_le32((((len - buffer1)
+ << TDES1_BUFFER2_SIZE_SHIFT)
+ & TDES1_BUFFER2_SIZE_MASK) | buffer1);
} else
- p->des1 |= (len & TDES1_BUFFER1_SIZE_MASK);
+ p->des1 |= cpu_to_le32((len & TDES1_BUFFER1_SIZE_MASK));
}
/* Specific functions used for Chain mode */
@@ -94,32 +98,32 @@ static inline void norm_set_tx_desc_len_on_ring(struct dma_desc *p, int len)
/* Enhanced descriptors */
static inline void ehn_desc_rx_set_on_chain(struct dma_desc *p)
{
- p->des1 |= ERDES1_SECOND_ADDRESS_CHAINED;
+ p->des1 |= cpu_to_le32(ERDES1_SECOND_ADDRESS_CHAINED);
}
static inline void enh_desc_end_tx_desc_on_chain(struct dma_desc *p)
{
- p->des0 |= ETDES0_SECOND_ADDRESS_CHAINED;
+ p->des0 |= cpu_to_le32(ETDES0_SECOND_ADDRESS_CHAINED);
}
static inline void enh_set_tx_desc_len_on_chain(struct dma_desc *p, int len)
{
- p->des1 |= (len & ETDES1_BUFFER1_SIZE_MASK);
+ p->des1 |= cpu_to_le32(len & ETDES1_BUFFER1_SIZE_MASK);
}
/* Normal descriptors */
static inline void ndesc_rx_set_on_chain(struct dma_desc *p, int end)
{
- p->des1 |= RDES1_SECOND_ADDRESS_CHAINED;
+ p->des1 |= cpu_to_le32(RDES1_SECOND_ADDRESS_CHAINED);
}
static inline void ndesc_tx_set_on_chain(struct dma_desc *p)
{
- p->des1 |= TDES1_SECOND_ADDRESS_CHAINED;
+ p->des1 |= cpu_to_le32(TDES1_SECOND_ADDRESS_CHAINED);
}
static inline void norm_set_tx_desc_len_on_chain(struct dma_desc *p, int len)
{
- p->des1 |= len & TDES1_BUFFER1_SIZE_MASK;
+ p->des1 |= cpu_to_le32(len & TDES1_BUFFER1_SIZE_MASK);
}
#endif /* __DESC_COM_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
new file mode 100644
index 0000000..c355975
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
@@ -0,0 +1,217 @@
+/*
+ * Oxford Semiconductor OXNAS DWMAC glue layer
+ *
+ * Copyright (C) 2016 Neil Armstrong <narmstrong@baylibre.com>
+ * Copyright (C) 2014 Daniel Golle <daniel@makrotopia.org>
+ * Copyright (C) 2013 Ma Haijun <mahaijuns@gmail.com>
+ * Copyright (C) 2012 John Crispin <blogic@openwrt.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/mfd/syscon.h>
+#include <linux/stmmac.h>
+
+#include "stmmac_platform.h"
+
+/* System Control regmap offsets */
+#define OXNAS_DWMAC_CTRL_REGOFFSET 0x78
+#define OXNAS_DWMAC_DELAY_REGOFFSET 0x100
+
+/* Control Register */
+#define DWMAC_CKEN_RX_IN 14
+#define DWMAC_CKEN_RXN_OUT 13
+#define DWMAC_CKEN_RX_OUT 12
+#define DWMAC_CKEN_TX_IN 10
+#define DWMAC_CKEN_TXN_OUT 9
+#define DWMAC_CKEN_TX_OUT 8
+#define DWMAC_RX_SOURCE 7
+#define DWMAC_TX_SOURCE 6
+#define DWMAC_LOW_TX_SOURCE 4
+#define DWMAC_AUTO_TX_SOURCE 3
+#define DWMAC_RGMII 2
+#define DWMAC_SIMPLE_MUX 1
+#define DWMAC_CKEN_GTX 0
+
+/* Delay register */
+#define DWMAC_TX_VARDELAY_SHIFT 0
+#define DWMAC_TXN_VARDELAY_SHIFT 8
+#define DWMAC_RX_VARDELAY_SHIFT 16
+#define DWMAC_RXN_VARDELAY_SHIFT 24
+#define DWMAC_TX_VARDELAY(d) ((d) << DWMAC_TX_VARDELAY_SHIFT)
+#define DWMAC_TXN_VARDELAY(d) ((d) << DWMAC_TXN_VARDELAY_SHIFT)
+#define DWMAC_RX_VARDELAY(d) ((d) << DWMAC_RX_VARDELAY_SHIFT)
+#define DWMAC_RXN_VARDELAY(d) ((d) << DWMAC_RXN_VARDELAY_SHIFT)
+
+struct oxnas_dwmac {
+ struct device *dev;
+ struct clk *clk;
+ struct regmap *regmap;
+};
+
+static int oxnas_dwmac_init(struct oxnas_dwmac *dwmac)
+{
+ unsigned int value;
+ int ret;
+
+ /* Reset HW here before changing the glue configuration */
+ ret = device_reset(dwmac->dev);
+ if (ret)
+ return ret;
+
+ ret = clk_prepare_enable(dwmac->clk);
+ if (ret)
+ return ret;
+
+ ret = regmap_read(dwmac->regmap, OXNAS_DWMAC_CTRL_REGOFFSET, &value);
+ if (ret < 0) {
+ clk_disable_unprepare(dwmac->clk);
+ return ret;
+ }
+
+ /* Enable GMII_GTXCLK to follow GMII_REFCLK, required for gigabit PHY */
+ value |= BIT(DWMAC_CKEN_GTX) |
+ /* Use simple mux for 25/125 Mhz clock switching */
+ BIT(DWMAC_SIMPLE_MUX) |
+ /* set auto switch tx clock source */
+ BIT(DWMAC_AUTO_TX_SOURCE) |
+ /* enable tx & rx vardelay */
+ BIT(DWMAC_CKEN_TX_OUT) |
+ BIT(DWMAC_CKEN_TXN_OUT) |
+ BIT(DWMAC_CKEN_TX_IN) |
+ BIT(DWMAC_CKEN_RX_OUT) |
+ BIT(DWMAC_CKEN_RXN_OUT) |
+ BIT(DWMAC_CKEN_RX_IN);
+ regmap_write(dwmac->regmap, OXNAS_DWMAC_CTRL_REGOFFSET, value);
+
+ /* set tx & rx vardelay */
+ value = DWMAC_TX_VARDELAY(4) |
+ DWMAC_TXN_VARDELAY(2) |
+ DWMAC_RX_VARDELAY(10) |
+ DWMAC_RXN_VARDELAY(8);
+ regmap_write(dwmac->regmap, OXNAS_DWMAC_DELAY_REGOFFSET, value);
+
+ return 0;
+}
+
+static int oxnas_dwmac_probe(struct platform_device *pdev)
+{
+ struct plat_stmmacenet_data *plat_dat;
+ struct stmmac_resources stmmac_res;
+ struct device_node *sysctrl;
+ struct oxnas_dwmac *dwmac;
+ int ret;
+
+ sysctrl = of_parse_phandle(pdev->dev.of_node, "oxsemi,sys-ctrl", 0);
+ if (!sysctrl) {
+ dev_err(&pdev->dev, "failed to get sys-ctrl node\n");
+ return -EINVAL;
+ }
+
+ ret = stmmac_get_platform_resources(pdev, &stmmac_res);
+ if (ret)
+ return ret;
+
+ plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac);
+ if (IS_ERR(plat_dat))
+ return PTR_ERR(plat_dat);
+
+ dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL);
+ if (!dwmac)
+ return -ENOMEM;
+
+ dwmac->dev = &pdev->dev;
+ plat_dat->bsp_priv = dwmac;
+
+ dwmac->regmap = syscon_node_to_regmap(sysctrl);
+ if (IS_ERR(dwmac->regmap)) {
+ dev_err(&pdev->dev, "failed to have sysctrl regmap\n");
+ return PTR_ERR(dwmac->regmap);
+ }
+
+ dwmac->clk = devm_clk_get(&pdev->dev, "gmac");
+ if (IS_ERR(dwmac->clk))
+ return PTR_ERR(dwmac->clk);
+
+ ret = oxnas_dwmac_init(dwmac);
+ if (ret)
+ return ret;
+
+ ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
+ if (ret)
+ clk_disable_unprepare(dwmac->clk);
+
+ return ret;
+}
+
+static int oxnas_dwmac_remove(struct platform_device *pdev)
+{
+ struct oxnas_dwmac *dwmac = get_stmmac_bsp_priv(&pdev->dev);
+ int ret = stmmac_dvr_remove(&pdev->dev);
+
+ clk_disable_unprepare(dwmac->clk);
+
+ return ret;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int oxnas_dwmac_suspend(struct device *dev)
+{
+ struct oxnas_dwmac *dwmac = get_stmmac_bsp_priv(dev);
+ int ret;
+
+ ret = stmmac_suspend(dev);
+ clk_disable_unprepare(dwmac->clk);
+
+ return ret;
+}
+
+static int oxnas_dwmac_resume(struct device *dev)
+{
+ struct oxnas_dwmac *dwmac = get_stmmac_bsp_priv(dev);
+ int ret;
+
+ ret = oxnas_dwmac_init(dwmac);
+ if (ret)
+ return ret;
+
+ ret = stmmac_resume(dev);
+
+ return ret;
+}
+#endif /* CONFIG_PM_SLEEP */
+
+static SIMPLE_DEV_PM_OPS(oxnas_dwmac_pm_ops,
+ oxnas_dwmac_suspend, oxnas_dwmac_resume);
+
+static const struct of_device_id oxnas_dwmac_match[] = {
+ { .compatible = "oxsemi,ox820-dwmac" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, oxnas_dwmac_match);
+
+static struct platform_driver oxnas_dwmac_driver = {
+ .probe = oxnas_dwmac_probe,
+ .remove = oxnas_dwmac_remove,
+ .driver = {
+ .name = "oxnas-dwmac",
+ .pm = &oxnas_dwmac_pm_ops,
+ .of_match_table = oxnas_dwmac_match,
+ },
+};
+module_platform_driver(oxnas_dwmac_driver);
+
+MODULE_AUTHOR("Neil Armstrong <narmstrong@baylibre.com>");
+MODULE_DESCRIPTION("Oxford Semiconductor OXNAS DWMAC glue layer");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 3740a44..6b787d7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -901,44 +901,6 @@ static void rk_gmac_powerdown(struct rk_priv_data *gmac)
gmac_clk_enable(gmac, false);
}
-static int rk_gmac_init(struct platform_device *pdev, void *priv)
-{
- struct rk_priv_data *bsp_priv = priv;
-
- return rk_gmac_powerup(bsp_priv);
-}
-
-static void rk_gmac_exit(struct platform_device *pdev, void *priv)
-{
- struct rk_priv_data *bsp_priv = priv;
-
- rk_gmac_powerdown(bsp_priv);
-}
-
-static void rk_gmac_suspend(struct platform_device *pdev, void *priv)
-{
- struct rk_priv_data *bsp_priv = priv;
-
- /* Keep the PHY up if we use Wake-on-Lan. */
- if (device_may_wakeup(&pdev->dev))
- return;
-
- rk_gmac_powerdown(bsp_priv);
- bsp_priv->suspended = true;
-}
-
-static void rk_gmac_resume(struct platform_device *pdev, void *priv)
-{
- struct rk_priv_data *bsp_priv = priv;
-
- /* The PHY was up for Wake-on-Lan. */
- if (!bsp_priv->suspended)
- return;
-
- rk_gmac_powerup(bsp_priv);
- bsp_priv->suspended = false;
-}
-
static void rk_fix_speed(void *priv, unsigned int speed)
{
struct rk_priv_data *bsp_priv = priv;
@@ -974,23 +936,60 @@ static int rk_gmac_probe(struct platform_device *pdev)
return PTR_ERR(plat_dat);
plat_dat->has_gmac = true;
- plat_dat->init = rk_gmac_init;
- plat_dat->exit = rk_gmac_exit;
plat_dat->fix_mac_speed = rk_fix_speed;
- plat_dat->suspend = rk_gmac_suspend;
- plat_dat->resume = rk_gmac_resume;
plat_dat->bsp_priv = rk_gmac_setup(pdev, data);
if (IS_ERR(plat_dat->bsp_priv))
return PTR_ERR(plat_dat->bsp_priv);
- ret = rk_gmac_init(pdev, plat_dat->bsp_priv);
+ ret = rk_gmac_powerup(plat_dat->bsp_priv);
if (ret)
return ret;
return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
}
+static int rk_gmac_remove(struct platform_device *pdev)
+{
+ struct rk_priv_data *bsp_priv = get_stmmac_bsp_priv(&pdev->dev);
+ int ret = stmmac_dvr_remove(&pdev->dev);
+
+ rk_gmac_powerdown(bsp_priv);
+
+ return ret;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int rk_gmac_suspend(struct device *dev)
+{
+ struct rk_priv_data *bsp_priv = get_stmmac_bsp_priv(dev);
+ int ret = stmmac_suspend(dev);
+
+ /* Keep the PHY up if we use Wake-on-Lan. */
+ if (!device_may_wakeup(dev)) {
+ rk_gmac_powerdown(bsp_priv);
+ bsp_priv->suspended = true;
+ }
+
+ return ret;
+}
+
+static int rk_gmac_resume(struct device *dev)
+{
+ struct rk_priv_data *bsp_priv = get_stmmac_bsp_priv(dev);
+
+ /* The PHY was up for Wake-on-Lan. */
+ if (bsp_priv->suspended) {
+ rk_gmac_powerup(bsp_priv);
+ bsp_priv->suspended = false;
+ }
+
+ return stmmac_resume(dev);
+}
+#endif /* CONFIG_PM_SLEEP */
+
+static SIMPLE_DEV_PM_OPS(rk_gmac_pm_ops, rk_gmac_suspend, rk_gmac_resume);
+
static const struct of_device_id rk_gmac_dwmac_match[] = {
{ .compatible = "rockchip,rk3228-gmac", .data = &rk3228_ops },
{ .compatible = "rockchip,rk3288-gmac", .data = &rk3288_ops },
@@ -1003,10 +1002,10 @@ MODULE_DEVICE_TABLE(of, rk_gmac_dwmac_match);
static struct platform_driver rk_gmac_dwmac_driver = {
.probe = rk_gmac_probe,
- .remove = stmmac_pltfr_remove,
+ .remove = rk_gmac_remove,
.driver = {
.name = "rk_gmac-dwmac",
- .pm = &stmmac_pltfr_pm_ops,
+ .pm = &rk_gmac_pm_ops,
.of_match_table = rk_gmac_dwmac_match,
},
};
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
index 58c05ac..c9006ab 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
@@ -126,8 +126,8 @@ struct sti_dwmac {
struct clk *clk; /* PHY clock */
u32 ctrl_reg; /* GMAC glue-logic control register */
int clk_sel_reg; /* GMAC ext clk selection register */
- struct device *dev;
struct regmap *regmap;
+ bool gmac_en;
u32 speed;
void (*fix_retime_src)(void *priv, unsigned int speed);
};
@@ -191,7 +191,7 @@ static void stih4xx_fix_retime_src(void *priv, u32 spd)
}
}
- if (src == TX_RETIME_SRC_CLKGEN && dwmac->clk && freq)
+ if (src == TX_RETIME_SRC_CLKGEN && freq)
clk_set_rate(dwmac->clk, freq);
regmap_update_bits(dwmac->regmap, reg, STIH4XX_RETIME_SRC_MASK,
@@ -222,26 +222,20 @@ static void stid127_fix_retime_src(void *priv, u32 spd)
freq = DWMAC_2_5MHZ;
}
- if (dwmac->clk && freq)
+ if (freq)
clk_set_rate(dwmac->clk, freq);
regmap_update_bits(dwmac->regmap, reg, STID127_RETIME_SRC_MASK, val);
}
-static int sti_dwmac_init(struct platform_device *pdev, void *priv)
+static int sti_dwmac_set_mode(struct sti_dwmac *dwmac)
{
- struct sti_dwmac *dwmac = priv;
struct regmap *regmap = dwmac->regmap;
int iface = dwmac->interface;
- struct device *dev = dwmac->dev;
- struct device_node *np = dev->of_node;
u32 reg = dwmac->ctrl_reg;
u32 val;
- if (dwmac->clk)
- clk_prepare_enable(dwmac->clk);
-
- if (of_property_read_bool(np, "st,gmac_en"))
+ if (dwmac->gmac_en)
regmap_update_bits(regmap, reg, EN_MASK, EN);
regmap_update_bits(regmap, reg, MII_PHY_SEL_MASK, phy_intf_sels[iface]);
@@ -249,18 +243,11 @@ static int sti_dwmac_init(struct platform_device *pdev, void *priv)
val = (iface == PHY_INTERFACE_MODE_REVMII) ? 0 : ENMII;
regmap_update_bits(regmap, reg, ENMII_MASK, val);
- dwmac->fix_retime_src(priv, dwmac->speed);
+ dwmac->fix_retime_src(dwmac, dwmac->speed);
return 0;
}
-static void sti_dwmac_exit(struct platform_device *pdev, void *priv)
-{
- struct sti_dwmac *dwmac = priv;
-
- if (dwmac->clk)
- clk_disable_unprepare(dwmac->clk);
-}
static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
struct platform_device *pdev)
{
@@ -270,9 +257,6 @@ static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
struct regmap *regmap;
int err;
- if (!np)
- return -EINVAL;
-
/* clk selection from extra syscfg register */
dwmac->clk_sel_reg = -ENXIO;
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "sti-clkconf");
@@ -289,9 +273,9 @@ static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
return err;
}
- dwmac->dev = dev;
dwmac->interface = of_get_phy_mode(np);
dwmac->regmap = regmap;
+ dwmac->gmac_en = of_property_read_bool(np, "st,gmac_en");
dwmac->ext_phyclk = of_property_read_bool(np, "st,ext-phyclk");
dwmac->tx_retime_src = TX_RETIME_SRC_NA;
dwmac->speed = SPEED_100;
@@ -357,17 +341,62 @@ static int sti_dwmac_probe(struct platform_device *pdev)
dwmac->fix_retime_src = data->fix_retime_src;
plat_dat->bsp_priv = dwmac;
- plat_dat->init = sti_dwmac_init;
- plat_dat->exit = sti_dwmac_exit;
plat_dat->fix_mac_speed = data->fix_retime_src;
- ret = sti_dwmac_init(pdev, plat_dat->bsp_priv);
+ ret = clk_prepare_enable(dwmac->clk);
if (ret)
return ret;
- return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
+ ret = sti_dwmac_set_mode(dwmac);
+ if (ret)
+ goto disable_clk;
+
+ ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
+ if (ret)
+ goto disable_clk;
+
+ return 0;
+
+disable_clk:
+ clk_disable_unprepare(dwmac->clk);
+ return ret;
}
+static int sti_dwmac_remove(struct platform_device *pdev)
+{
+ struct sti_dwmac *dwmac = get_stmmac_bsp_priv(&pdev->dev);
+ int ret = stmmac_dvr_remove(&pdev->dev);
+
+ clk_disable_unprepare(dwmac->clk);
+
+ return ret;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int sti_dwmac_suspend(struct device *dev)
+{
+ struct sti_dwmac *dwmac = get_stmmac_bsp_priv(dev);
+ int ret = stmmac_suspend(dev);
+
+ clk_disable_unprepare(dwmac->clk);
+
+ return ret;
+}
+
+static int sti_dwmac_resume(struct device *dev)
+{
+ struct sti_dwmac *dwmac = get_stmmac_bsp_priv(dev);
+
+ clk_prepare_enable(dwmac->clk);
+ sti_dwmac_set_mode(dwmac);
+
+ return stmmac_resume(dev);
+}
+#endif /* CONFIG_PM_SLEEP */
+
+static SIMPLE_DEV_PM_OPS(sti_dwmac_pm_ops, sti_dwmac_suspend,
+ sti_dwmac_resume);
+
static const struct sti_dwmac_of_data stih4xx_dwmac_data = {
.fix_retime_src = stih4xx_fix_retime_src,
};
@@ -387,10 +416,10 @@ MODULE_DEVICE_TABLE(of, sti_dwmac_match);
static struct platform_driver sti_dwmac_driver = {
.probe = sti_dwmac_probe,
- .remove = stmmac_pltfr_remove,
+ .remove = sti_dwmac_remove,
.driver = {
.name = "sti-dwmac",
- .pm = &stmmac_pltfr_pm_ops,
+ .pm = &sti_dwmac_pm_ops,
.of_match_table = sti_dwmac_match,
},
};
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 4ec7397..bec72d3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -23,7 +23,7 @@ static int dwmac4_wrback_get_tx_status(void *data, struct stmmac_extra_stats *x,
unsigned int tdes3;
int ret = tx_done;
- tdes3 = p->des3;
+ tdes3 = le32_to_cpu(p->des3);
/* Get tx owner first */
if (unlikely(tdes3 & TDES3_OWN))
@@ -77,9 +77,9 @@ static int dwmac4_wrback_get_rx_status(void *data, struct stmmac_extra_stats *x,
struct dma_desc *p)
{
struct net_device_stats *stats = (struct net_device_stats *)data;
- unsigned int rdes1 = p->des1;
- unsigned int rdes2 = p->des2;
- unsigned int rdes3 = p->des3;
+ unsigned int rdes1 = le32_to_cpu(p->des1);
+ unsigned int rdes2 = le32_to_cpu(p->des2);
+ unsigned int rdes3 = le32_to_cpu(p->des3);
int message_type;
int ret = good_frame;
@@ -169,42 +169,43 @@ static int dwmac4_wrback_get_rx_status(void *data, struct stmmac_extra_stats *x,
static int dwmac4_rd_get_tx_len(struct dma_desc *p)
{
- return (p->des2 & TDES2_BUFFER1_SIZE_MASK);
+ return (le32_to_cpu(p->des2) & TDES2_BUFFER1_SIZE_MASK);
}
static int dwmac4_get_tx_owner(struct dma_desc *p)
{
- return (p->des3 & TDES3_OWN) >> TDES3_OWN_SHIFT;
+ return (le32_to_cpu(p->des3) & TDES3_OWN) >> TDES3_OWN_SHIFT;
}
static void dwmac4_set_tx_owner(struct dma_desc *p)
{
- p->des3 |= TDES3_OWN;
+ p->des3 |= cpu_to_le32(TDES3_OWN);
}
static void dwmac4_set_rx_owner(struct dma_desc *p)
{
- p->des3 |= RDES3_OWN;
+ p->des3 |= cpu_to_le32(RDES3_OWN);
}
static int dwmac4_get_tx_ls(struct dma_desc *p)
{
- return (p->des3 & TDES3_LAST_DESCRIPTOR) >> TDES3_LAST_DESCRIPTOR_SHIFT;
+ return (le32_to_cpu(p->des3) & TDES3_LAST_DESCRIPTOR)
+ >> TDES3_LAST_DESCRIPTOR_SHIFT;
}
static int dwmac4_wrback_get_rx_frame_len(struct dma_desc *p, int rx_coe)
{
- return (p->des3 & RDES3_PACKET_SIZE_MASK);
+ return (le32_to_cpu(p->des3) & RDES3_PACKET_SIZE_MASK);
}
static void dwmac4_rd_enable_tx_timestamp(struct dma_desc *p)
{
- p->des2 |= TDES2_TIMESTAMP_ENABLE;
+ p->des2 |= cpu_to_le32(TDES2_TIMESTAMP_ENABLE);
}
static int dwmac4_wrback_get_tx_timestamp_status(struct dma_desc *p)
{
- return (p->des3 & TDES3_TIMESTAMP_STATUS)
+ return (le32_to_cpu(p->des3) & TDES3_TIMESTAMP_STATUS)
>> TDES3_TIMESTAMP_STATUS_SHIFT;
}
@@ -216,9 +217,9 @@ static u64 dwmac4_wrback_get_timestamp(void *desc, u32 ats)
struct dma_desc *p = (struct dma_desc *)desc;
u64 ns;
- ns = p->des0;
+ ns = le32_to_cpu(p->des0);
/* convert high/sec time stamp value to nanosecond */
- ns += p->des1 * 1000000000ULL;
+ ns += le32_to_cpu(p->des1) * 1000000000ULL;
return ns;
}
@@ -227,17 +228,17 @@ static int dwmac4_context_get_rx_timestamp_status(void *desc, u32 ats)
{
struct dma_desc *p = (struct dma_desc *)desc;
- return (p->des1 & RDES1_TIMESTAMP_AVAILABLE)
+ return (le32_to_cpu(p->des1) & RDES1_TIMESTAMP_AVAILABLE)
>> RDES1_TIMESTAMP_AVAILABLE_SHIFT;
}
static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
int mode, int end)
{
- p->des3 = RDES3_OWN | RDES3_BUFFER1_VALID_ADDR;
+ p->des3 = cpu_to_le32(RDES3_OWN | RDES3_BUFFER1_VALID_ADDR);
if (!disable_rx_ic)
- p->des3 |= RDES3_INT_ON_COMPLETION_EN;
+ p->des3 |= cpu_to_le32(RDES3_INT_ON_COMPLETION_EN);
}
static void dwmac4_rd_init_tx_desc(struct dma_desc *p, int mode, int end)
@@ -252,9 +253,9 @@ static void dwmac4_rd_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
bool csum_flag, int mode, bool tx_own,
bool ls)
{
- unsigned int tdes3 = p->des3;
+ unsigned int tdes3 = le32_to_cpu(p->des3);
- p->des2 |= (len & TDES2_BUFFER1_SIZE_MASK);
+ p->des2 |= cpu_to_le32(len & TDES2_BUFFER1_SIZE_MASK);
if (is_fs)
tdes3 |= TDES3_FIRST_DESCRIPTOR;
@@ -282,7 +283,7 @@ static void dwmac4_rd_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
*/
wmb();
- p->des3 = tdes3;
+ p->des3 = cpu_to_le32(tdes3);
}
static void dwmac4_rd_prepare_tso_tx_desc(struct dma_desc *p, int is_fs,
@@ -290,14 +291,14 @@ static void dwmac4_rd_prepare_tso_tx_desc(struct dma_desc *p, int is_fs,
bool ls, unsigned int tcphdrlen,
unsigned int tcppayloadlen)
{
- unsigned int tdes3 = p->des3;
+ unsigned int tdes3 = le32_to_cpu(p->des3);
if (len1)
- p->des2 |= (len1 & TDES2_BUFFER1_SIZE_MASK);
+ p->des2 |= cpu_to_le32((len1 & TDES2_BUFFER1_SIZE_MASK));
if (len2)
- p->des2 |= (len2 << TDES2_BUFFER2_SIZE_MASK_SHIFT)
- & TDES2_BUFFER2_SIZE_MASK;
+ p->des2 |= cpu_to_le32((len2 << TDES2_BUFFER2_SIZE_MASK_SHIFT)
+ & TDES2_BUFFER2_SIZE_MASK);
if (is_fs) {
tdes3 |= TDES3_FIRST_DESCRIPTOR |
@@ -325,7 +326,7 @@ static void dwmac4_rd_prepare_tso_tx_desc(struct dma_desc *p, int is_fs,
*/
wmb();
- p->des3 = tdes3;
+ p->des3 = cpu_to_le32(tdes3);
}
static void dwmac4_release_tx_desc(struct dma_desc *p, int mode)
@@ -336,7 +337,7 @@ static void dwmac4_release_tx_desc(struct dma_desc *p, int mode)
static void dwmac4_rd_set_tx_ic(struct dma_desc *p)
{
- p->des2 |= TDES2_INTERRUPT_ON_COMPLETION;
+ p->des2 |= cpu_to_le32(TDES2_INTERRUPT_ON_COMPLETION);
}
static void dwmac4_display_ring(void *head, unsigned int size, bool rx)
@@ -347,10 +348,10 @@ static void dwmac4_display_ring(void *head, unsigned int size, bool rx)
pr_info("%s descriptor ring:\n", rx ? "RX" : "TX");
for (i = 0; i < size; i++) {
- if (p->des0)
- pr_info("%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
- i, (unsigned int)virt_to_phys(p),
- p->des0, p->des1, p->des2, p->des3);
+ pr_info("%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
+ i, (unsigned int)virt_to_phys(p),
+ le32_to_cpu(p->des0), le32_to_cpu(p->des1),
+ le32_to_cpu(p->des2), le32_to_cpu(p->des3));
p++;
}
}
@@ -359,8 +360,8 @@ static void dwmac4_set_mss_ctxt(struct dma_desc *p, unsigned int mss)
{
p->des0 = 0;
p->des1 = 0;
- p->des2 = mss;
- p->des3 = TDES3_CONTEXT_TYPE | TDES3_CTXT_TCMSSV;
+ p->des2 = cpu_to_le32(mss);
+ p->des3 = cpu_to_le32(TDES3_CONTEXT_TYPE | TDES3_CTXT_TCMSSV);
}
const struct stmmac_desc_ops dwmac4_desc_ops = {
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 38f19c9..8295aa9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -30,7 +30,7 @@ static int enh_desc_get_tx_status(void *data, struct stmmac_extra_stats *x,
struct dma_desc *p, void __iomem *ioaddr)
{
struct net_device_stats *stats = (struct net_device_stats *)data;
- unsigned int tdes0 = p->des0;
+ unsigned int tdes0 = le32_to_cpu(p->des0);
int ret = tx_done;
/* Get tx owner first */
@@ -95,7 +95,7 @@ static int enh_desc_get_tx_status(void *data, struct stmmac_extra_stats *x,
static int enh_desc_get_tx_len(struct dma_desc *p)
{
- return (p->des1 & ETDES1_BUFFER1_SIZE_MASK);
+ return (le32_to_cpu(p->des1) & ETDES1_BUFFER1_SIZE_MASK);
}
static int enh_desc_coe_rdes0(int ipc_err, int type, int payload_err)
@@ -134,8 +134,8 @@ static int enh_desc_coe_rdes0(int ipc_err, int type, int payload_err)
static void enh_desc_get_ext_status(void *data, struct stmmac_extra_stats *x,
struct dma_extended_desc *p)
{
- unsigned int rdes0 = p->basic.des0;
- unsigned int rdes4 = p->des4;
+ unsigned int rdes0 = le32_to_cpu(p->basic.des0);
+ unsigned int rdes4 = le32_to_cpu(p->des4);
if (unlikely(rdes0 & ERDES0_RX_MAC_ADDR)) {
int message_type = (rdes4 & ERDES4_MSG_TYPE_MASK) >> 8;
@@ -191,7 +191,7 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x,
struct dma_desc *p)
{
struct net_device_stats *stats = (struct net_device_stats *)data;
- unsigned int rdes0 = p->des0;
+ unsigned int rdes0 = le32_to_cpu(p->des0);
int ret = good_frame;
if (unlikely(rdes0 & RDES0_OWN))
@@ -257,8 +257,8 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x,
static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
int mode, int end)
{
- p->des0 |= RDES0_OWN;
- p->des1 |= ((BUF_SIZE_8KiB - 1) & ERDES1_BUFFER1_SIZE_MASK);
+ p->des0 |= cpu_to_le32(RDES0_OWN);
+ p->des1 |= cpu_to_le32((BUF_SIZE_8KiB - 1) & ERDES1_BUFFER1_SIZE_MASK);
if (mode == STMMAC_CHAIN_MODE)
ehn_desc_rx_set_on_chain(p);
@@ -266,12 +266,12 @@ static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
ehn_desc_rx_set_on_ring(p, end);
if (disable_rx_ic)
- p->des1 |= ERDES1_DISABLE_IC;
+ p->des1 |= cpu_to_le32(ERDES1_DISABLE_IC);
}
static void enh_desc_init_tx_desc(struct dma_desc *p, int mode, int end)
{
- p->des0 &= ~ETDES0_OWN;
+ p->des0 &= cpu_to_le32(~ETDES0_OWN);
if (mode == STMMAC_CHAIN_MODE)
enh_desc_end_tx_desc_on_chain(p);
else
@@ -280,27 +280,27 @@ static void enh_desc_init_tx_desc(struct dma_desc *p, int mode, int end)
static int enh_desc_get_tx_owner(struct dma_desc *p)
{
- return (p->des0 & ETDES0_OWN) >> 31;
+ return (le32_to_cpu(p->des0) & ETDES0_OWN) >> 31;
}
static void enh_desc_set_tx_owner(struct dma_desc *p)
{
- p->des0 |= ETDES0_OWN;
+ p->des0 |= cpu_to_le32(ETDES0_OWN);
}
static void enh_desc_set_rx_owner(struct dma_desc *p)
{
- p->des0 |= RDES0_OWN;
+ p->des0 |= cpu_to_le32(RDES0_OWN);
}
static int enh_desc_get_tx_ls(struct dma_desc *p)
{
- return (p->des0 & ETDES0_LAST_SEGMENT) >> 29;
+ return (le32_to_cpu(p->des0) & ETDES0_LAST_SEGMENT) >> 29;
}
static void enh_desc_release_tx_desc(struct dma_desc *p, int mode)
{
- int ter = (p->des0 & ETDES0_END_RING) >> 21;
+ int ter = (le32_to_cpu(p->des0) & ETDES0_END_RING) >> 21;
memset(p, 0, offsetof(struct dma_desc, des2));
if (mode == STMMAC_CHAIN_MODE)
@@ -313,7 +313,7 @@ static void enh_desc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
bool csum_flag, int mode, bool tx_own,
bool ls)
{
- unsigned int tdes0 = p->des0;
+ unsigned int tdes0 = le32_to_cpu(p->des0);
if (mode == STMMAC_CHAIN_MODE)
enh_set_tx_desc_len_on_chain(p, len);
@@ -344,12 +344,12 @@ static void enh_desc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
*/
wmb();
- p->des0 = tdes0;
+ p->des0 = cpu_to_le32(tdes0);
}
static void enh_desc_set_tx_ic(struct dma_desc *p)
{
- p->des0 |= ETDES0_INTERRUPT;
+ p->des0 |= cpu_to_le32(ETDES0_INTERRUPT);
}
static int enh_desc_get_rx_frame_len(struct dma_desc *p, int rx_coe_type)
@@ -364,18 +364,18 @@ static int enh_desc_get_rx_frame_len(struct dma_desc *p, int rx_coe_type)
if (rx_coe_type == STMMAC_RX_COE_TYPE1)
csum = 2;
- return (((p->des0 & RDES0_FRAME_LEN_MASK) >> RDES0_FRAME_LEN_SHIFT) -
- csum);
+ return (((le32_to_cpu(p->des0) & RDES0_FRAME_LEN_MASK)
+ >> RDES0_FRAME_LEN_SHIFT) - csum);
}
static void enh_desc_enable_tx_timestamp(struct dma_desc *p)
{
- p->des0 |= ETDES0_TIME_STAMP_ENABLE;
+ p->des0 |= cpu_to_le32(ETDES0_TIME_STAMP_ENABLE);
}
static int enh_desc_get_tx_timestamp_status(struct dma_desc *p)
{
- return (p->des0 & ETDES0_TIME_STAMP_STATUS) >> 17;
+ return (le32_to_cpu(p->des0) & ETDES0_TIME_STAMP_STATUS) >> 17;
}
static u64 enh_desc_get_timestamp(void *desc, u32 ats)
@@ -384,13 +384,13 @@ static u64 enh_desc_get_timestamp(void *desc, u32 ats)
if (ats) {
struct dma_extended_desc *p = (struct dma_extended_desc *)desc;
- ns = p->des6;
+ ns = le32_to_cpu(p->des6);
/* convert high/sec time stamp value to nanosecond */
- ns += p->des7 * 1000000000ULL;
+ ns += le32_to_cpu(p->des7) * 1000000000ULL;
} else {
struct dma_desc *p = (struct dma_desc *)desc;
- ns = p->des2;
- ns += p->des3 * 1000000000ULL;
+ ns = le32_to_cpu(p->des2);
+ ns += le32_to_cpu(p->des3) * 1000000000ULL;
}
return ns;
@@ -400,10 +400,11 @@ static int enh_desc_get_rx_timestamp_status(void *desc, u32 ats)
{
if (ats) {
struct dma_extended_desc *p = (struct dma_extended_desc *)desc;
- return (p->basic.des0 & RDES0_IPC_CSUM_ERROR) >> 7;
+ return (le32_to_cpu(p->basic.des0) & RDES0_IPC_CSUM_ERROR) >> 7;
} else {
struct dma_desc *p = (struct dma_desc *)desc;
- if ((p->des2 == 0xffffffff) && (p->des3 == 0xffffffff))
+ if ((le32_to_cpu(p->des2) == 0xffffffff) &&
+ (le32_to_cpu(p->des3) == 0xffffffff))
/* timestamp is corrupted, hence don't store it */
return 0;
else
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index 2beacd0..fd78406 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -30,8 +30,8 @@ static int ndesc_get_tx_status(void *data, struct stmmac_extra_stats *x,
struct dma_desc *p, void __iomem *ioaddr)
{
struct net_device_stats *stats = (struct net_device_stats *)data;
- unsigned int tdes0 = p->des0;
- unsigned int tdes1 = p->des1;
+ unsigned int tdes0 = le32_to_cpu(p->des0);
+ unsigned int tdes1 = le32_to_cpu(p->des1);
int ret = tx_done;
/* Get tx owner first */
@@ -77,7 +77,7 @@ static int ndesc_get_tx_status(void *data, struct stmmac_extra_stats *x,
static int ndesc_get_tx_len(struct dma_desc *p)
{
- return (p->des1 & RDES1_BUFFER1_SIZE_MASK);
+ return (le32_to_cpu(p->des1) & RDES1_BUFFER1_SIZE_MASK);
}
/* This function verifies if each incoming frame has some errors
@@ -88,7 +88,7 @@ static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x,
struct dma_desc *p)
{
int ret = good_frame;
- unsigned int rdes0 = p->des0;
+ unsigned int rdes0 = le32_to_cpu(p->des0);
struct net_device_stats *stats = (struct net_device_stats *)data;
if (unlikely(rdes0 & RDES0_OWN))
@@ -141,8 +141,8 @@ static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x,
static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode,
int end)
{
- p->des0 |= RDES0_OWN;
- p->des1 |= (BUF_SIZE_2KiB - 1) & RDES1_BUFFER1_SIZE_MASK;
+ p->des0 |= cpu_to_le32(RDES0_OWN);
+ p->des1 |= cpu_to_le32((BUF_SIZE_2KiB - 1) & RDES1_BUFFER1_SIZE_MASK);
if (mode == STMMAC_CHAIN_MODE)
ndesc_rx_set_on_chain(p, end);
@@ -150,12 +150,12 @@ static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode,
ndesc_rx_set_on_ring(p, end);
if (disable_rx_ic)
- p->des1 |= RDES1_DISABLE_IC;
+ p->des1 |= cpu_to_le32(RDES1_DISABLE_IC);
}
static void ndesc_init_tx_desc(struct dma_desc *p, int mode, int end)
{
- p->des0 &= ~TDES0_OWN;
+ p->des0 &= cpu_to_le32(~TDES0_OWN);
if (mode == STMMAC_CHAIN_MODE)
ndesc_tx_set_on_chain(p);
else
@@ -164,27 +164,27 @@ static void ndesc_init_tx_desc(struct dma_desc *p, int mode, int end)
static int ndesc_get_tx_owner(struct dma_desc *p)
{
- return (p->des0 & TDES0_OWN) >> 31;
+ return (le32_to_cpu(p->des0) & TDES0_OWN) >> 31;
}
static void ndesc_set_tx_owner(struct dma_desc *p)
{
- p->des0 |= TDES0_OWN;
+ p->des0 |= cpu_to_le32(TDES0_OWN);
}
static void ndesc_set_rx_owner(struct dma_desc *p)
{
- p->des0 |= RDES0_OWN;
+ p->des0 |= cpu_to_le32(RDES0_OWN);
}
static int ndesc_get_tx_ls(struct dma_desc *p)
{
- return (p->des1 & TDES1_LAST_SEGMENT) >> 30;
+ return (le32_to_cpu(p->des1) & TDES1_LAST_SEGMENT) >> 30;
}
static void ndesc_release_tx_desc(struct dma_desc *p, int mode)
{
- int ter = (p->des1 & TDES1_END_RING) >> 25;
+ int ter = (le32_to_cpu(p->des1) & TDES1_END_RING) >> 25;
memset(p, 0, offsetof(struct dma_desc, des2));
if (mode == STMMAC_CHAIN_MODE)
@@ -197,7 +197,7 @@ static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
bool csum_flag, int mode, bool tx_own,
bool ls)
{
- unsigned int tdes1 = p->des1;
+ unsigned int tdes1 = le32_to_cpu(p->des1);
if (is_fs)
tdes1 |= TDES1_FIRST_SEGMENT;
@@ -212,7 +212,7 @@ static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
if (ls)
tdes1 |= TDES1_LAST_SEGMENT;
- p->des1 = tdes1;
+ p->des1 = cpu_to_le32(tdes1);
if (mode == STMMAC_CHAIN_MODE)
norm_set_tx_desc_len_on_chain(p, len);
@@ -220,12 +220,12 @@ static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
norm_set_tx_desc_len_on_ring(p, len);
if (tx_own)
- p->des0 |= TDES0_OWN;
+ p->des0 |= cpu_to_le32(TDES0_OWN);
}
static void ndesc_set_tx_ic(struct dma_desc *p)
{
- p->des1 |= TDES1_INTERRUPT;
+ p->des1 |= cpu_to_le32(TDES1_INTERRUPT);
}
static int ndesc_get_rx_frame_len(struct dma_desc *p, int rx_coe_type)
@@ -241,19 +241,20 @@ static int ndesc_get_rx_frame_len(struct dma_desc *p, int rx_coe_type)
if (rx_coe_type == STMMAC_RX_COE_TYPE1)
csum = 2;
- return (((p->des0 & RDES0_FRAME_LEN_MASK) >> RDES0_FRAME_LEN_SHIFT) -
+ return (((le32_to_cpu(p->des0) & RDES0_FRAME_LEN_MASK)
+ >> RDES0_FRAME_LEN_SHIFT) -
csum);
}
static void ndesc_enable_tx_timestamp(struct dma_desc *p)
{
- p->des1 |= TDES1_TIME_STAMP_ENABLE;
+ p->des1 |= cpu_to_le32(TDES1_TIME_STAMP_ENABLE);
}
static int ndesc_get_tx_timestamp_status(struct dma_desc *p)
{
- return (p->des0 & TDES0_TIME_STAMP_STATUS) >> 17;
+ return (le32_to_cpu(p->des0) & TDES0_TIME_STAMP_STATUS) >> 17;
}
static u64 ndesc_get_timestamp(void *desc, u32 ats)
@@ -261,9 +262,9 @@ static u64 ndesc_get_timestamp(void *desc, u32 ats)
struct dma_desc *p = (struct dma_desc *)desc;
u64 ns;
- ns = p->des2;
+ ns = le32_to_cpu(p->des2);
/* convert high/sec time stamp value to nanosecond */
- ns += p->des3 * 1000000000ULL;
+ ns += le32_to_cpu(p->des3) * 1000000000ULL;
return ns;
}
@@ -272,7 +273,8 @@ static int ndesc_get_rx_timestamp_status(void *desc, u32 ats)
{
struct dma_desc *p = (struct dma_desc *)desc;
- if ((p->des2 == 0xffffffff) && (p->des3 == 0xffffffff))
+ if ((le32_to_cpu(p->des2) == 0xffffffff) &&
+ (le32_to_cpu(p->des3) == 0xffffffff))
/* timestamp is corrupted, hence don't store it */
return 0;
else
diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
index 7723b5d..9983ce9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
@@ -34,7 +34,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
unsigned int entry = priv->cur_tx;
struct dma_desc *desc;
unsigned int nopaged_len = skb_headlen(skb);
- unsigned int bmax, len;
+ unsigned int bmax, len, des2;
if (priv->extend_desc)
desc = (struct dma_desc *)(priv->dma_etx + entry);
@@ -50,16 +50,17 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
if (nopaged_len > BUF_SIZE_8KiB) {
- desc->des2 = dma_map_single(priv->device, skb->data,
- bmax, DMA_TO_DEVICE);
- if (dma_mapping_error(priv->device, desc->des2))
+ des2 = dma_map_single(priv->device, skb->data, bmax,
+ DMA_TO_DEVICE);
+ desc->des2 = cpu_to_le32(des2);
+ if (dma_mapping_error(priv->device, des2))
return -1;
- priv->tx_skbuff_dma[entry].buf = desc->des2;
+ priv->tx_skbuff_dma[entry].buf = des2;
priv->tx_skbuff_dma[entry].len = bmax;
priv->tx_skbuff_dma[entry].is_jumbo = true;
- desc->des3 = desc->des2 + BUF_SIZE_4KiB;
+ desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum,
STMMAC_RING_MODE, 0, false);
priv->tx_skbuff[entry] = NULL;
@@ -70,26 +71,28 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
else
desc = priv->dma_tx + entry;
- desc->des2 = dma_map_single(priv->device, skb->data + bmax,
- len, DMA_TO_DEVICE);
- if (dma_mapping_error(priv->device, desc->des2))
+ des2 = dma_map_single(priv->device, skb->data + bmax, len,
+ DMA_TO_DEVICE);
+ desc->des2 = cpu_to_le32(des2);
+ if (dma_mapping_error(priv->device, des2))
return -1;
- priv->tx_skbuff_dma[entry].buf = desc->des2;
+ priv->tx_skbuff_dma[entry].buf = des2;
priv->tx_skbuff_dma[entry].len = len;
priv->tx_skbuff_dma[entry].is_jumbo = true;
- desc->des3 = desc->des2 + BUF_SIZE_4KiB;
+ desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
priv->hw->desc->prepare_tx_desc(desc, 0, len, csum,
STMMAC_RING_MODE, 1, true);
} else {
- desc->des2 = dma_map_single(priv->device, skb->data,
- nopaged_len, DMA_TO_DEVICE);
- if (dma_mapping_error(priv->device, desc->des2))
+ des2 = dma_map_single(priv->device, skb->data,
+ nopaged_len, DMA_TO_DEVICE);
+ desc->des2 = cpu_to_le32(des2);
+ if (dma_mapping_error(priv->device, des2))
return -1;
- priv->tx_skbuff_dma[entry].buf = desc->des2;
+ priv->tx_skbuff_dma[entry].buf = des2;
priv->tx_skbuff_dma[entry].len = nopaged_len;
priv->tx_skbuff_dma[entry].is_jumbo = true;
- desc->des3 = desc->des2 + BUF_SIZE_4KiB;
+ desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum,
STMMAC_RING_MODE, 0, true);
}
@@ -115,13 +118,13 @@ static void stmmac_refill_desc3(void *priv_ptr, struct dma_desc *p)
/* Fill DES3 in case of RING mode */
if (priv->dma_buf_sz >= BUF_SIZE_8KiB)
- p->des3 = p->des2 + BUF_SIZE_8KiB;
+ p->des3 = cpu_to_le32(le32_to_cpu(p->des2) + BUF_SIZE_8KiB);
}
/* In ring mode we need to fill the desc3 because it is used as buffer */
static void stmmac_init_desc3(struct dma_desc *p)
{
- p->des3 = p->des2 + BUF_SIZE_8KiB;
+ p->des3 = cpu_to_le32(le32_to_cpu(p->des2) + BUF_SIZE_8KiB);
}
static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index f94e028..758b4e2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -144,7 +144,7 @@ int stmmac_mdio_register(struct net_device *ndev);
int stmmac_mdio_reset(struct mii_bus *mii);
void stmmac_set_ethtool_ops(struct net_device *netdev);
-int stmmac_ptp_register(struct stmmac_priv *priv);
+void stmmac_ptp_register(struct stmmac_priv *priv);
void stmmac_ptp_unregister(struct stmmac_priv *priv);
int stmmac_resume(struct device *dev);
int stmmac_suspend(struct device *dev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 3fe9340..0290d52 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -870,6 +870,7 @@ static const struct ethtool_ops stmmac_ethtool_ops = {
.get_regs = stmmac_ethtool_gregs,
.get_regs_len = stmmac_ethtool_get_regs_len,
.get_link = ethtool_op_get_link,
+ .nway_reset = phy_ethtool_nway_reset,
.get_pauseparam = stmmac_get_pauseparam,
.set_pauseparam = stmmac_set_pauseparam,
.get_ethtool_stats = stmmac_get_ethtool_stats,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index fa4a82f..fbd1cd7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -305,7 +305,7 @@ bool stmmac_eee_init(struct stmmac_priv *priv)
*/
spin_lock_irqsave(&priv->lock, flags);
if (priv->eee_active) {
- pr_debug("stmmac: disable EEE\n");
+ netdev_dbg(priv->dev, "disable EEE\n");
del_timer_sync(&priv->eee_ctrl_timer);
priv->hw->mac->set_eee_timer(priv->hw, 0,
tx_lpi_timer);
@@ -334,7 +334,7 @@ bool stmmac_eee_init(struct stmmac_priv *priv)
ret = true;
spin_unlock_irqrestore(&priv->lock, flags);
- pr_debug("stmmac: Energy-Efficient Ethernet initialized\n");
+ netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n");
}
out:
return ret;
@@ -456,8 +456,8 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
sizeof(struct hwtstamp_config)))
return -EFAULT;
- pr_debug("%s config flags:0x%x, tx_type:0x%x, rx_filter:0x%x\n",
- __func__, config.flags, config.tx_type, config.rx_filter);
+ netdev_dbg(priv->dev, "%s config flags:0x%x, tx_type:0x%x, rx_filter:0x%x\n",
+ __func__, config.flags, config.tx_type, config.rx_filter);
/* reserved for future extensions */
if (config.flags)
@@ -678,7 +678,9 @@ static int stmmac_init_ptp(struct stmmac_priv *priv)
priv->hwts_tx_en = 0;
priv->hwts_rx_en = 0;
- return stmmac_ptp_register(priv);
+ stmmac_ptp_register(priv);
+
+ return 0;
}
static void stmmac_release_ptp(struct stmmac_priv *priv)
@@ -753,9 +755,9 @@ static void stmmac_adjust_link(struct net_device *dev)
stmmac_hw_fix_mac_speed(priv);
break;
default:
- if (netif_msg_link(priv))
- pr_warn("%s: Speed (%d) not 10/100\n",
- dev->name, phydev->speed);
+ netif_warn(priv, link, priv->dev,
+ "Speed (%d) not 10/100\n",
+ phydev->speed);
break;
}
@@ -808,10 +810,10 @@ static void stmmac_check_pcs_mode(struct stmmac_priv *priv)
(interface == PHY_INTERFACE_MODE_RGMII_ID) ||
(interface == PHY_INTERFACE_MODE_RGMII_RXID) ||
(interface == PHY_INTERFACE_MODE_RGMII_TXID)) {
- pr_debug("STMMAC: PCS RGMII support enable\n");
+ netdev_dbg(priv->dev, "PCS RGMII support enabled\n");
priv->hw->pcs = STMMAC_PCS_RGMII;
} else if (interface == PHY_INTERFACE_MODE_SGMII) {
- pr_debug("STMMAC: PCS SGMII support enable\n");
+ netdev_dbg(priv->dev, "PCS SGMII support enabled\n");
priv->hw->pcs = STMMAC_PCS_SGMII;
}
}
@@ -846,15 +848,15 @@ static int stmmac_init_phy(struct net_device *dev)
snprintf(phy_id_fmt, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id,
priv->plat->phy_addr);
- pr_debug("stmmac_init_phy: trying to attach to %s\n",
- phy_id_fmt);
+ netdev_dbg(priv->dev, "%s: trying to attach to %s\n", __func__,
+ phy_id_fmt);
phydev = phy_connect(dev, phy_id_fmt, &stmmac_adjust_link,
interface);
}
if (IS_ERR_OR_NULL(phydev)) {
- pr_err("%s: Could not attach to PHY\n", dev->name);
+ netdev_err(priv->dev, "Could not attach to PHY\n");
if (!phydev)
return -ENODEV;
@@ -880,8 +882,15 @@ static int stmmac_init_phy(struct net_device *dev)
return -ENODEV;
}
- pr_debug("stmmac_init_phy: %s: attached to PHY (UID 0x%x)"
- " Link = %d\n", dev->name, phydev->phy_id, phydev->link);
+ /* stmmac_adjust_link will change this to PHY_IGNORE_INTERRUPT to avoid
+ * subsequent PHY polling, make sure we force a link transition if
+ * we have a UP/DOWN/UP transition
+ */
+ if (phydev->is_pseudo_fixed_link)
+ phydev->irq = PHY_POLL;
+
+ netdev_dbg(priv->dev, "%s: attached to PHY (UID 0x%x) Link = %d\n",
+ __func__, phydev->phy_id, phydev->link);
return 0;
}
@@ -967,7 +976,8 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
skb = __netdev_alloc_skb_ip_align(priv->dev, priv->dma_buf_sz, flags);
if (!skb) {
- pr_err("%s: Rx init fails; skb is NULL\n", __func__);
+ netdev_err(priv->dev,
+ "%s: Rx init fails; skb is NULL\n", __func__);
return -ENOMEM;
}
priv->rx_skbuff[i] = skb;
@@ -975,15 +985,15 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
priv->dma_buf_sz,
DMA_FROM_DEVICE);
if (dma_mapping_error(priv->device, priv->rx_skbuff_dma[i])) {
- pr_err("%s: DMA mapping error\n", __func__);
+ netdev_err(priv->dev, "%s: DMA mapping error\n", __func__);
dev_kfree_skb_any(skb);
return -EINVAL;
}
if (priv->synopsys_id >= DWMAC_CORE_4_00)
- p->des0 = priv->rx_skbuff_dma[i];
+ p->des0 = cpu_to_le32(priv->rx_skbuff_dma[i]);
else
- p->des2 = priv->rx_skbuff_dma[i];
+ p->des2 = cpu_to_le32(priv->rx_skbuff_dma[i]);
if ((priv->hw->mode->init_desc3) &&
(priv->dma_buf_sz == BUF_SIZE_16KiB))
@@ -1025,13 +1035,14 @@ static int init_dma_desc_rings(struct net_device *dev, gfp_t flags)
priv->dma_buf_sz = bfsize;
- if (netif_msg_probe(priv)) {
- pr_debug("(%s) dma_rx_phy=0x%08x dma_tx_phy=0x%08x\n", __func__,
- (u32) priv->dma_rx_phy, (u32) priv->dma_tx_phy);
+ netif_dbg(priv, probe, priv->dev,
+ "(%s) dma_rx_phy=0x%08x dma_tx_phy=0x%08x\n",
+ __func__, (u32)priv->dma_rx_phy, (u32)priv->dma_tx_phy);
- /* RX INITIALIZATION */
- pr_debug("\tSKB addresses:\nskb\t\tskb data\tdma data\n");
- }
+ /* RX INITIALIZATION */
+ netif_dbg(priv, probe, priv->dev,
+ "SKB addresses:\nskb\t\tskb data\tdma data\n");
+
for (i = 0; i < DMA_RX_SIZE; i++) {
struct dma_desc *p;
if (priv->extend_desc)
@@ -1043,10 +1054,9 @@ static int init_dma_desc_rings(struct net_device *dev, gfp_t flags)
if (ret)
goto err_init_rx_buffers;
- if (netif_msg_probe(priv))
- pr_debug("[%p]\t[%p]\t[%x]\n", priv->rx_skbuff[i],
- priv->rx_skbuff[i]->data,
- (unsigned int)priv->rx_skbuff_dma[i]);
+ netif_dbg(priv, probe, priv->dev, "[%p]\t[%p]\t[%x]\n",
+ priv->rx_skbuff[i], priv->rx_skbuff[i]->data,
+ (unsigned int)priv->rx_skbuff_dma[i]);
}
priv->cur_rx = 0;
priv->dirty_rx = (unsigned int)(i - DMA_RX_SIZE);
@@ -1376,8 +1386,8 @@ static void stmmac_tx_clean(struct stmmac_priv *priv)
netif_tx_lock(priv->dev);
if (netif_queue_stopped(priv->dev) &&
stmmac_tx_avail(priv) > STMMAC_TX_THRESH) {
- if (netif_msg_tx_done(priv))
- pr_debug("%s: restart transmit\n", __func__);
+ netif_dbg(priv, tx_done, priv->dev,
+ "%s: restart transmit\n", __func__);
netif_wake_queue(priv->dev);
}
netif_tx_unlock(priv->dev);
@@ -1488,7 +1498,7 @@ static void stmmac_mmc_setup(struct stmmac_priv *priv)
dwmac_mmc_ctrl(priv->mmcaddr, mode);
memset(&priv->mmc, 0, sizeof(struct stmmac_counters));
} else
- pr_info(" No MAC Management Counters available\n");
+ netdev_info(priv->dev, "No MAC Management Counters available\n");
}
/**
@@ -1501,18 +1511,18 @@ static void stmmac_mmc_setup(struct stmmac_priv *priv)
static void stmmac_selec_desc_mode(struct stmmac_priv *priv)
{
if (priv->plat->enh_desc) {
- pr_info(" Enhanced/Alternate descriptors\n");
+ dev_info(priv->device, "Enhanced/Alternate descriptors\n");
/* GMAC older than 3.50 has no extended descriptors */
if (priv->synopsys_id >= DWMAC_CORE_3_50) {
- pr_info("\tEnabled extended descriptors\n");
+ dev_info(priv->device, "Enabled extended descriptors\n");
priv->extend_desc = 1;
} else
- pr_warn("Extended descriptors not supported\n");
+ dev_warn(priv->device, "Extended descriptors not supported\n");
priv->hw->desc = &enh_desc_ops;
} else {
- pr_info(" Normal descriptors\n");
+ dev_info(priv->device, "Normal descriptors\n");
priv->hw->desc = &ndesc_ops;
}
}
@@ -1553,8 +1563,8 @@ static void stmmac_check_ether_addr(struct stmmac_priv *priv)
priv->dev->dev_addr, 0);
if (!is_valid_ether_addr(priv->dev->dev_addr))
eth_hw_addr_random(priv->dev);
- pr_info("%s: device MAC address %pM\n", priv->dev->name,
- priv->dev->dev_addr);
+ netdev_info(priv->dev, "device MAC address %pM\n",
+ priv->dev->dev_addr);
}
}
@@ -1662,7 +1672,8 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
/* DMA initialization and SW reset */
ret = stmmac_init_dma_engine(priv);
if (ret < 0) {
- pr_err("%s: DMA engine initialization failed\n", __func__);
+ netdev_err(priv->dev, "%s: DMA engine initialization failed\n",
+ __func__);
return ret;
}
@@ -1691,7 +1702,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
ret = priv->hw->mac->rx_ipc(priv->hw);
if (!ret) {
- pr_warn(" RX IPC Checksum Offload disabled\n");
+ netdev_warn(priv->dev, "RX IPC Checksum Offload disabled\n");
priv->plat->rx_coe = STMMAC_RX_COE_NONE;
priv->hw->rx_csum = 0;
}
@@ -1710,16 +1721,17 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
if (init_ptp) {
ret = stmmac_init_ptp(priv);
if (ret)
- netdev_warn(priv->dev, "PTP support cannot init.\n");
+ netdev_warn(priv->dev, "fail to init PTP.\n");
}
#ifdef CONFIG_DEBUG_FS
ret = stmmac_init_fs(dev);
if (ret < 0)
- pr_warn("%s: failed debugFS registration\n", __func__);
+ netdev_warn(priv->dev, "%s: failed debugFS registration\n",
+ __func__);
#endif
/* Start the ball rolling... */
- pr_debug("%s: DMA RX/TX processes started...\n", dev->name);
+ netdev_dbg(priv->dev, "DMA RX/TX processes started...\n");
priv->hw->dma->start_tx(priv->ioaddr);
priv->hw->dma->start_rx(priv->ioaddr);
@@ -1774,8 +1786,9 @@ static int stmmac_open(struct net_device *dev)
priv->hw->pcs != STMMAC_PCS_RTBI) {
ret = stmmac_init_phy(dev);
if (ret) {
- pr_err("%s: Cannot attach to PHY (error: %d)\n",
- __func__, ret);
+ netdev_err(priv->dev,
+ "%s: Cannot attach to PHY (error: %d)\n",
+ __func__, ret);
return ret;
}
}
@@ -1789,19 +1802,21 @@ static int stmmac_open(struct net_device *dev)
ret = alloc_dma_desc_resources(priv);
if (ret < 0) {
- pr_err("%s: DMA descriptors allocation failed\n", __func__);
+ netdev_err(priv->dev, "%s: DMA descriptors allocation failed\n",
+ __func__);
goto dma_desc_error;
}
ret = init_dma_desc_rings(dev, GFP_KERNEL);
if (ret < 0) {
- pr_err("%s: DMA descriptors initialization failed\n", __func__);
+ netdev_err(priv->dev, "%s: DMA descriptors initialization failed\n",
+ __func__);
goto init_error;
}
ret = stmmac_hw_setup(dev, true);
if (ret < 0) {
- pr_err("%s: Hw setup failed\n", __func__);
+ netdev_err(priv->dev, "%s: Hw setup failed\n", __func__);
goto init_error;
}
@@ -1814,8 +1829,9 @@ static int stmmac_open(struct net_device *dev)
ret = request_irq(dev->irq, stmmac_interrupt,
IRQF_SHARED, dev->name, dev);
if (unlikely(ret < 0)) {
- pr_err("%s: ERROR: allocating the IRQ %d (error: %d)\n",
- __func__, dev->irq, ret);
+ netdev_err(priv->dev,
+ "%s: ERROR: allocating the IRQ %d (error: %d)\n",
+ __func__, dev->irq, ret);
goto init_error;
}
@@ -1824,8 +1840,9 @@ static int stmmac_open(struct net_device *dev)
ret = request_irq(priv->wol_irq, stmmac_interrupt,
IRQF_SHARED, dev->name, dev);
if (unlikely(ret < 0)) {
- pr_err("%s: ERROR: allocating the WoL IRQ %d (%d)\n",
- __func__, priv->wol_irq, ret);
+ netdev_err(priv->dev,
+ "%s: ERROR: allocating the WoL IRQ %d (%d)\n",
+ __func__, priv->wol_irq, ret);
goto wolirq_error;
}
}
@@ -1835,8 +1852,9 @@ static int stmmac_open(struct net_device *dev)
ret = request_irq(priv->lpi_irq, stmmac_interrupt, IRQF_SHARED,
dev->name, dev);
if (unlikely(ret < 0)) {
- pr_err("%s: ERROR: allocating the LPI IRQ %d (%d)\n",
- __func__, priv->lpi_irq, ret);
+ netdev_err(priv->dev,
+ "%s: ERROR: allocating the LPI IRQ %d (%d)\n",
+ __func__, priv->lpi_irq, ret);
goto lpiirq_error;
}
}
@@ -1937,7 +1955,7 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des,
priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE);
desc = priv->dma_tx + priv->cur_tx;
- desc->des0 = des + (total_len - tmp_len);
+ desc->des0 = cpu_to_le32(des + (total_len - tmp_len));
buff_size = tmp_len >= TSO_MAX_BUFF_SIZE ?
TSO_MAX_BUFF_SIZE : tmp_len;
@@ -1999,7 +2017,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
if (!netif_queue_stopped(dev)) {
netif_stop_queue(dev);
/* This is a hard error, log it. */
- pr_err("%s: Tx Ring full when queue awake\n", __func__);
+ netdev_err(priv->dev,
+ "%s: Tx Ring full when queue awake\n",
+ __func__);
}
spin_unlock(&priv->tx_lock);
return NETDEV_TX_BUSY;
@@ -2039,11 +2059,11 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
priv->tx_skbuff_dma[first_entry].len = skb_headlen(skb);
priv->tx_skbuff[first_entry] = skb;
- first->des0 = des;
+ first->des0 = cpu_to_le32(des);
/* Fill start of payload in buff2 of first descriptor */
if (pay_len)
- first->des1 = des + proto_hdr_len;
+ first->des1 = cpu_to_le32(des + proto_hdr_len);
/* If needed take extra descriptors to fill the remaining payload */
tmp_pay_len = pay_len - TSO_MAX_BUFF_SIZE;
@@ -2072,8 +2092,8 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE);
if (unlikely(stmmac_tx_avail(priv) <= (MAX_SKB_FRAGS + 1))) {
- if (netif_msg_hw(priv))
- pr_debug("%s: stop transmitted packets\n", __func__);
+ netif_dbg(priv, hw, priv->dev, "%s: stop transmitted packets\n",
+ __func__);
netif_stop_queue(dev);
}
@@ -2179,7 +2199,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
if (!netif_queue_stopped(dev)) {
netif_stop_queue(dev);
/* This is a hard error, log it. */
- pr_err("%s: Tx Ring full when queue awake\n", __func__);
+ netdev_err(priv->dev,
+ "%s: Tx Ring full when queue awake\n",
+ __func__);
}
return NETDEV_TX_BUSY;
}
@@ -2232,13 +2254,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
priv->tx_skbuff[entry] = NULL;
- if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) {
- desc->des0 = des;
- priv->tx_skbuff_dma[entry].buf = desc->des0;
- } else {
- desc->des2 = des;
- priv->tx_skbuff_dma[entry].buf = desc->des2;
- }
+ priv->tx_skbuff_dma[entry].buf = des;
+ if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
+ desc->des0 = cpu_to_le32(des);
+ else
+ desc->des2 = cpu_to_le32(des);
priv->tx_skbuff_dma[entry].map_as_page = true;
priv->tx_skbuff_dma[entry].len = len;
@@ -2256,9 +2276,10 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
if (netif_msg_pktdata(priv)) {
void *tx_head;
- pr_debug("%s: curr=%d dirty=%d f=%d, e=%d, first=%p, nfrags=%d",
- __func__, priv->cur_tx, priv->dirty_tx, first_entry,
- entry, first, nfrags);
+ netdev_dbg(priv->dev,
+ "%s: curr=%d dirty=%d f=%d, e=%d, first=%p, nfrags=%d",
+ __func__, priv->cur_tx, priv->dirty_tx, first_entry,
+ entry, first, nfrags);
if (priv->extend_desc)
tx_head = (void *)priv->dma_etx;
@@ -2267,13 +2288,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
priv->hw->desc->display_ring(tx_head, DMA_TX_SIZE, false);
- pr_debug(">>> frame to be transmitted: ");
+ netdev_dbg(priv->dev, ">>> frame to be transmitted: ");
print_pkt(skb->data, skb->len);
}
if (unlikely(stmmac_tx_avail(priv) <= (MAX_SKB_FRAGS + 1))) {
- if (netif_msg_hw(priv))
- pr_debug("%s: stop transmitted packets\n", __func__);
+ netif_dbg(priv, hw, priv->dev, "%s: stop transmitted packets\n",
+ __func__);
netif_stop_queue(dev);
}
@@ -2309,13 +2330,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
if (dma_mapping_error(priv->device, des))
goto dma_map_err;
- if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) {
- first->des0 = des;
- priv->tx_skbuff_dma[first_entry].buf = first->des0;
- } else {
- first->des2 = des;
- priv->tx_skbuff_dma[first_entry].buf = first->des2;
- }
+ priv->tx_skbuff_dma[first_entry].buf = des;
+ if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
+ first->des0 = cpu_to_le32(des);
+ else
+ first->des2 = cpu_to_le32(des);
priv->tx_skbuff_dma[first_entry].len = nopaged_len;
priv->tx_skbuff_dma[first_entry].last_segment = last_segment;
@@ -2352,7 +2371,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
dma_map_err:
spin_unlock(&priv->tx_lock);
- dev_err(priv->device, "Tx dma map failed\n");
+ netdev_err(priv->dev, "Tx DMA map failed\n");
dev_kfree_skb(skb);
priv->dev->stats.tx_dropped++;
return NETDEV_TX_OK;
@@ -2423,16 +2442,16 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv)
DMA_FROM_DEVICE);
if (dma_mapping_error(priv->device,
priv->rx_skbuff_dma[entry])) {
- dev_err(priv->device, "Rx dma map failed\n");
+ netdev_err(priv->dev, "Rx DMA map failed\n");
dev_kfree_skb(skb);
break;
}
if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) {
- p->des0 = priv->rx_skbuff_dma[entry];
+ p->des0 = cpu_to_le32(priv->rx_skbuff_dma[entry]);
p->des1 = 0;
} else {
- p->des2 = priv->rx_skbuff_dma[entry];
+ p->des2 = cpu_to_le32(priv->rx_skbuff_dma[entry]);
}
if (priv->hw->mode->refill_desc3)
priv->hw->mode->refill_desc3(priv, p);
@@ -2440,8 +2459,8 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv)
if (priv->rx_zeroc_thresh > 0)
priv->rx_zeroc_thresh--;
- if (netif_msg_rx_status(priv))
- pr_debug("\trefill entry #%d\n", entry);
+ netif_dbg(priv, rx_status, priv->dev,
+ "refill entry #%d\n", entry);
}
wmb();
@@ -2474,7 +2493,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
if (netif_msg_rx_status(priv)) {
void *rx_head;
- pr_debug("%s: descriptor ring:\n", __func__);
+ netdev_dbg(priv->dev, "%s: descriptor ring:\n", __func__);
if (priv->extend_desc)
rx_head = (void *)priv->dma_erx;
else
@@ -2533,9 +2552,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
unsigned int des;
if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
- des = p->des0;
+ des = le32_to_cpu(p->des0);
else
- des = p->des2;
+ des = le32_to_cpu(p->des2);
frame_len = priv->hw->desc->get_rx_frame_len(p, coe);
@@ -2544,9 +2563,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
* ignored
*/
if (frame_len > priv->dma_buf_sz) {
- pr_err("%s: len %d larger than size (%d)\n",
- priv->dev->name, frame_len,
- priv->dma_buf_sz);
+ netdev_err(priv->dev,
+ "len %d larger than size (%d)\n",
+ frame_len, priv->dma_buf_sz);
priv->dev->stats.rx_length_errors++;
break;
}
@@ -2558,11 +2577,11 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
frame_len -= ETH_FCS_LEN;
if (netif_msg_rx_status(priv)) {
- pr_debug("\tdesc: %p [entry %d] buff=0x%x\n",
- p, entry, des);
+ netdev_dbg(priv->dev, "\tdesc: %p [entry %d] buff=0x%x\n",
+ p, entry, des);
if (frame_len > ETH_FRAME_LEN)
- pr_debug("\tframe size %d, COE: %d\n",
- frame_len, status);
+ netdev_dbg(priv->dev, "frame size %d, COE: %d\n",
+ frame_len, status);
}
/* The zero-copy is always used for all the sizes
@@ -2599,8 +2618,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
} else {
skb = priv->rx_skbuff[entry];
if (unlikely(!skb)) {
- pr_err("%s: Inconsistent Rx chain\n",
- priv->dev->name);
+ netdev_err(priv->dev,
+ "%s: Inconsistent Rx chain\n",
+ priv->dev->name);
priv->dev->stats.rx_dropped++;
break;
}
@@ -2618,7 +2638,8 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
stmmac_get_rx_hwtstamp(priv, entry, skb);
if (netif_msg_pktdata(priv)) {
- pr_debug("frame received (%dbytes)", frame_len);
+ netdev_dbg(priv->dev, "frame received (%dbytes)",
+ frame_len);
print_pkt(skb->data, frame_len);
}
@@ -2715,8 +2736,10 @@ static void stmmac_set_rx_mode(struct net_device *dev)
*/
static int stmmac_change_mtu(struct net_device *dev, int new_mtu)
{
+ struct stmmac_priv *priv = netdev_priv(dev);
+
if (netif_running(dev)) {
- pr_err("%s: must be stopped to change its MTU\n", dev->name);
+ netdev_err(priv->dev, "must be stopped to change its MTU\n");
return -EBUSY;
}
@@ -2795,7 +2818,7 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
pm_wakeup_event(priv->device, 0);
if (unlikely(!dev)) {
- pr_err("%s: invalid dev pointer\n", __func__);
+ netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__);
return IRQ_NONE;
}
@@ -2892,14 +2915,17 @@ static void sysfs_display_ring(void *head, int size, int extend_desc,
x = *(u64 *) ep;
seq_printf(seq, "%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
i, (unsigned int)virt_to_phys(ep),
- ep->basic.des0, ep->basic.des1,
- ep->basic.des2, ep->basic.des3);
+ le32_to_cpu(ep->basic.des0),
+ le32_to_cpu(ep->basic.des1),
+ le32_to_cpu(ep->basic.des2),
+ le32_to_cpu(ep->basic.des3));
ep++;
} else {
x = *(u64 *) p;
seq_printf(seq, "%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
i, (unsigned int)virt_to_phys(ep),
- p->des0, p->des1, p->des2, p->des3);
+ le32_to_cpu(p->des0), le32_to_cpu(p->des1),
+ le32_to_cpu(p->des2), le32_to_cpu(p->des3));
p++;
}
seq_printf(seq, "\n");
@@ -3024,8 +3050,7 @@ static int stmmac_init_fs(struct net_device *dev)
priv->dbgfs_dir = debugfs_create_dir(dev->name, stmmac_fs_dir);
if (!priv->dbgfs_dir || IS_ERR(priv->dbgfs_dir)) {
- pr_err("ERROR %s/%s, debugfs create directory failed\n",
- STMMAC_RESOURCE_NAME, dev->name);
+ netdev_err(priv->dev, "ERROR failed to create debugfs directory\n");
return -ENOMEM;
}
@@ -3037,7 +3062,7 @@ static int stmmac_init_fs(struct net_device *dev)
&stmmac_rings_status_fops);
if (!priv->dbgfs_rings_status || IS_ERR(priv->dbgfs_rings_status)) {
- pr_info("ERROR creating stmmac ring debugfs file\n");
+ netdev_err(priv->dev, "ERROR creating stmmac ring debugfs file\n");
debugfs_remove_recursive(priv->dbgfs_dir);
return -ENOMEM;
@@ -3049,7 +3074,7 @@ static int stmmac_init_fs(struct net_device *dev)
dev, &stmmac_dma_cap_fops);
if (!priv->dbgfs_dma_cap || IS_ERR(priv->dbgfs_dma_cap)) {
- pr_info("ERROR creating stmmac MMC debugfs file\n");
+ netdev_err(priv->dev, "ERROR creating stmmac MMC debugfs file\n");
debugfs_remove_recursive(priv->dbgfs_dir);
return -ENOMEM;
@@ -3121,11 +3146,11 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
} else {
if (chain_mode) {
priv->hw->mode = &chain_mode_ops;
- pr_info(" Chain mode enabled\n");
+ dev_info(priv->device, "Chain mode enabled\n");
priv->mode = STMMAC_CHAIN_MODE;
} else {
priv->hw->mode = &ring_mode_ops;
- pr_info(" Ring mode enabled\n");
+ dev_info(priv->device, "Ring mode enabled\n");
priv->mode = STMMAC_RING_MODE;
}
}
@@ -3133,7 +3158,7 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
/* Get the HW capability (new GMAC newer than 3.50a) */
priv->hw_cap_support = stmmac_get_hw_features(priv);
if (priv->hw_cap_support) {
- pr_info(" DMA HW capability register supported");
+ dev_info(priv->device, "DMA HW capability register supported\n");
/* We can override some gmac/dma configuration fields: e.g.
* enh_desc, tx_coe (e.g. that are passed through the
@@ -3158,8 +3183,9 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
else if (priv->dma_cap.rx_coe_type1)
priv->plat->rx_coe = STMMAC_RX_COE_TYPE1;
- } else
- pr_info(" No HW DMA feature register supported");
+ } else {
+ dev_info(priv->device, "No HW DMA feature register supported\n");
+ }
/* To use alternate (extended), normal or GMAC4 descriptor structures */
if (priv->synopsys_id >= DWMAC_CORE_4_00)
@@ -3169,20 +3195,20 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
if (priv->plat->rx_coe) {
priv->hw->rx_csum = priv->plat->rx_coe;
- pr_info(" RX Checksum Offload Engine supported\n");
+ dev_info(priv->device, "RX Checksum Offload Engine supported\n");
if (priv->synopsys_id < DWMAC_CORE_4_00)
- pr_info("\tCOE Type %d\n", priv->hw->rx_csum);
+ dev_info(priv->device, "COE Type %d\n", priv->hw->rx_csum);
}
if (priv->plat->tx_coe)
- pr_info(" TX Checksum insertion supported\n");
+ dev_info(priv->device, "TX Checksum insertion supported\n");
if (priv->plat->pmt) {
- pr_info(" Wake-Up On Lan supported\n");
+ dev_info(priv->device, "Wake-Up On Lan supported\n");
device_set_wakeup_capable(priv->device, 1);
}
if (priv->dma_cap.tsoen)
- pr_info(" TSO supported\n");
+ dev_info(priv->device, "TSO supported\n");
return 0;
}
@@ -3241,8 +3267,8 @@ int stmmac_dvr_probe(struct device *device,
priv->stmmac_clk = devm_clk_get(priv->device, STMMAC_RESOURCE_NAME);
if (IS_ERR(priv->stmmac_clk)) {
- dev_warn(priv->device, "%s: warning: cannot get CSR clock\n",
- __func__);
+ netdev_warn(priv->dev, "%s: warning: cannot get CSR clock\n",
+ __func__);
/* If failed to obtain stmmac_clk and specific clk_csr value
* is NOT passed from the platform, probe fail.
*/
@@ -3291,7 +3317,7 @@ int stmmac_dvr_probe(struct device *device,
if ((priv->plat->tso_en) && (priv->dma_cap.tsoen)) {
ndev->hw_features |= NETIF_F_TSO;
priv->tso = true;
- pr_info(" TSO feature enabled\n");
+ dev_info(priv->device, "TSO feature enabled\n");
}
ndev->features |= ndev->hw_features | NETIF_F_HIGHDMA;
ndev->watchdog_timeo = msecs_to_jiffies(watchdog);
@@ -3320,7 +3346,7 @@ int stmmac_dvr_probe(struct device *device,
*/
if ((priv->synopsys_id >= DWMAC_CORE_3_50) && (!priv->plat->riwt_off)) {
priv->use_riwt = 1;
- pr_info(" Enable RX Mitigation via HW Watchdog Timer\n");
+ netdev_info(priv->dev, "Enable RX Mitigation via HW Watchdog Timer\n");
}
netif_napi_add(ndev, &priv->napi, stmmac_poll, 64);
@@ -3330,7 +3356,8 @@ int stmmac_dvr_probe(struct device *device,
ret = register_netdev(ndev);
if (ret) {
- pr_err("%s: ERROR %i registering the device\n", __func__, ret);
+ netdev_err(priv->dev, "%s: ERROR %i registering the device\n",
+ __func__, ret);
goto error_netdev_register;
}
@@ -3353,8 +3380,9 @@ int stmmac_dvr_probe(struct device *device,
/* MDIO bus Registration */
ret = stmmac_mdio_register(ndev);
if (ret < 0) {
- pr_debug("%s: MDIO bus (id: %d) registration failed",
- __func__, priv->plat->bus_id);
+ netdev_err(priv->dev,
+ "%s: MDIO bus (id: %d) registration failed",
+ __func__, priv->plat->bus_id);
goto error_mdio_register;
}
}
@@ -3387,7 +3415,7 @@ int stmmac_dvr_remove(struct device *dev)
struct net_device *ndev = dev_get_drvdata(dev);
struct stmmac_priv *priv = netdev_priv(ndev);
- pr_info("%s:\n\tremoving driver", __func__);
+ netdev_info(priv->dev, "%s: removing driver", __func__);
priv->hw->dma->stop_rx(priv->ioaddr);
priv->hw->dma->stop_tx(priv->ioaddr);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index ec29585..e3216e5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -260,7 +260,7 @@ int stmmac_mdio_reset(struct mii_bus *bus)
#endif
if (data->phy_reset) {
- pr_debug("stmmac_mdio_reset: calling phy_reset\n");
+ netdev_dbg(ndev, "stmmac_mdio_reset: calling phy_reset\n");
data->phy_reset(priv->plat->bsp_priv);
}
@@ -325,7 +325,7 @@ int stmmac_mdio_register(struct net_device *ndev)
else
err = mdiobus_register(new_bus);
if (err != 0) {
- pr_err("%s: Cannot register as MDIO bus\n", new_bus->name);
+ netdev_err(ndev, "Cannot register the MDIO bus\n");
goto bus_register_fail;
}
@@ -372,16 +372,16 @@ int stmmac_mdio_register(struct net_device *ndev)
irq_str = irq_num;
break;
}
- pr_info("%s: PHY ID %08x at %d IRQ %s (%s)%s\n",
- ndev->name, phydev->phy_id, addr,
- irq_str, phydev_name(phydev),
- act ? " active" : "");
+ netdev_info(ndev, "PHY ID %08x at %d IRQ %s (%s)%s\n",
+ phydev->phy_id, addr,
+ irq_str, phydev_name(phydev),
+ act ? " active" : "");
found = 1;
}
}
if (!found && !mdio_node) {
- pr_warn("%s: No PHY found\n", ndev->name);
+ netdev_warn(ndev, "No PHY found\n");
mdiobus_unregister(new_bus);
mdiobus_free(new_bus);
return -ENODEV;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 0a0d6a8..4d544c3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -417,9 +417,7 @@ static int stmmac_pltfr_suspend(struct device *dev)
struct platform_device *pdev = to_platform_device(dev);
ret = stmmac_suspend(dev);
- if (priv->plat->suspend)
- priv->plat->suspend(pdev, priv->plat->bsp_priv);
- else if (priv->plat->exit)
+ if (priv->plat->exit)
priv->plat->exit(pdev, priv->plat->bsp_priv);
return ret;
@@ -438,9 +436,7 @@ static int stmmac_pltfr_resume(struct device *dev)
struct stmmac_priv *priv = netdev_priv(ndev);
struct platform_device *pdev = to_platform_device(dev);
- if (priv->plat->resume)
- priv->plat->resume(pdev, priv->plat->bsp_priv);
- else if (priv->plat->init)
+ if (priv->plat->init)
priv->plat->init(pdev, priv->plat->bsp_priv);
return stmmac_resume(dev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index 289d527..1477471 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -177,7 +177,7 @@ static struct ptp_clock_info stmmac_ptp_clock_ops = {
* Description: this function will register the ptp clock driver
* to kernel. It also does some house keeping work.
*/
-int stmmac_ptp_register(struct stmmac_priv *priv)
+void stmmac_ptp_register(struct stmmac_priv *priv)
{
spin_lock_init(&priv->ptp_lock);
priv->ptp_clock_ops = stmmac_ptp_clock_ops;
@@ -185,15 +185,10 @@ int stmmac_ptp_register(struct stmmac_priv *priv)
priv->ptp_clock = ptp_clock_register(&priv->ptp_clock_ops,
priv->device);
if (IS_ERR(priv->ptp_clock)) {
+ netdev_err(priv->dev, "ptp_clock_register failed\n");
priv->ptp_clock = NULL;
- return PTR_ERR(priv->ptp_clock);
- }
-
- spin_lock_init(&priv->ptp_lock);
-
- netdev_dbg(priv->dev, "Added PTP HW clock successfully\n");
-
- return 0;
+ } else if (priv->ptp_clock)
+ netdev_info(priv->dev, "registered PTP clock\n");
}
/**
diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c
index 58efe69..8878b75 100644
--- a/drivers/net/ethernet/sun/sunvnet_common.c
+++ b/drivers/net/ethernet/sun/sunvnet_common.c
@@ -704,9 +704,8 @@ static int handle_mcast(struct vnet_port *port, void *msgbuf)
return 0;
}
-/* Got back a STOPPED LDC message on port. If the queue is stopped,
- * wake it up so that we'll send out another START message at the
- * next TX.
+/* If the queue is stopped, wake it up so that we'll
+ * send out another START message at the next TX.
*/
static void maybe_tx_wakeup(struct vnet_port *port)
{
@@ -734,6 +733,7 @@ EXPORT_SYMBOL_GPL(sunvnet_port_is_up_common);
static int vnet_event_napi(struct vnet_port *port, int budget)
{
+ struct net_device *dev = VNET_PORT_TO_NET_DEVICE(port);
struct vio_driver_state *vio = &port->vio;
int tx_wakeup, err;
int npkts = 0;
@@ -747,6 +747,16 @@ static int vnet_event_napi(struct vnet_port *port, int budget)
if (event == LDC_EVENT_RESET) {
vnet_port_reset(port);
vio_port_up(vio);
+
+ /* If the device is running but its tx queue was
+ * stopped (due to flow control), restart it.
+ * This is necessary since vnet_port_reset()
+ * clears the tx drings and thus we may never get
+ * back a VIO_TYPE_DATA ACK packet - which is
+ * the normal mechanism to restart the tx queue.
+ */
+ if (netif_running(dev))
+ maybe_tx_wakeup(port);
}
port->rx_event = 0;
return 0;
diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
index eaa51ce..7053301 100644
--- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c
+++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c
@@ -982,11 +982,13 @@ static int dwceqos_mii_probe(struct net_device *ndev)
if (netif_msg_probe(lp))
phy_attached_info(phydev);
- phydev->supported &= PHY_GBIT_FEATURES;
+ phydev->supported &= PHY_GBIT_FEATURES | SUPPORTED_Pause |
+ SUPPORTED_Asym_Pause;
lp->link = 0;
lp->speed = 0;
lp->duplex = DUPLEX_UNKNOWN;
+ lp->flowcontrol.autoneg = AUTONEG_ENABLE;
return 0;
}
diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c
index 054a8dd..ba1e45f 100644
--- a/drivers/net/ethernet/ti/cpsw-phy-sel.c
+++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c
@@ -176,9 +176,12 @@ void cpsw_phy_sel(struct device *dev, phy_interface_t phy_mode, int slave)
}
dev = bus_find_device(&platform_bus_type, NULL, node, match);
+ of_node_put(node);
priv = dev_get_drvdata(dev);
priv->cpsw_phy_sel(priv, phy_mode, slave);
+
+ put_device(dev);
}
EXPORT_SYMBOL_GPL(cpsw_phy_sel);
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index b1ddf89..39d06e8 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1376,10 +1376,6 @@ static int cpsw_ndo_open(struct net_device *ndev)
ALE_ALL_PORTS, ALE_ALL_PORTS, 0, 0);
if (!cpsw_common_res_usage_state(cpsw)) {
- /* setup tx dma to fixed prio and zero offset */
- cpdma_control_set(cpsw->dma, CPDMA_TX_PRIO_FIXED, 1);
- cpdma_control_set(cpsw->dma, CPDMA_RX_BUFFER_OFFSET, 0);
-
/* disable priority elevation */
__raw_writel(0, &cpsw->regs->ptype);
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index c3f35f1..56708a7 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -124,6 +124,29 @@ struct cpdma_chan {
int int_set, int_clear, td;
};
+struct cpdma_control_info {
+ u32 reg;
+ u32 shift, mask;
+ int access;
+#define ACCESS_RO BIT(0)
+#define ACCESS_WO BIT(1)
+#define ACCESS_RW (ACCESS_RO | ACCESS_WO)
+};
+
+static struct cpdma_control_info controls[] = {
+ [CPDMA_CMD_IDLE] = {CPDMA_DMACONTROL, 3, 1, ACCESS_WO},
+ [CPDMA_COPY_ERROR_FRAMES] = {CPDMA_DMACONTROL, 4, 1, ACCESS_RW},
+ [CPDMA_RX_OFF_LEN_UPDATE] = {CPDMA_DMACONTROL, 2, 1, ACCESS_RW},
+ [CPDMA_RX_OWNERSHIP_FLIP] = {CPDMA_DMACONTROL, 1, 1, ACCESS_RW},
+ [CPDMA_TX_PRIO_FIXED] = {CPDMA_DMACONTROL, 0, 1, ACCESS_RW},
+ [CPDMA_STAT_IDLE] = {CPDMA_DMASTATUS, 31, 1, ACCESS_RO},
+ [CPDMA_STAT_TX_ERR_CODE] = {CPDMA_DMASTATUS, 20, 0xf, ACCESS_RW},
+ [CPDMA_STAT_TX_ERR_CHAN] = {CPDMA_DMASTATUS, 16, 0x7, ACCESS_RW},
+ [CPDMA_STAT_RX_ERR_CODE] = {CPDMA_DMASTATUS, 12, 0xf, ACCESS_RW},
+ [CPDMA_STAT_RX_ERR_CHAN] = {CPDMA_DMASTATUS, 8, 0x7, ACCESS_RW},
+ [CPDMA_RX_BUFFER_OFFSET] = {CPDMA_RXBUFFOFS, 0, 0xffff, ACCESS_RW},
+};
+
#define tx_chan_num(chan) (chan)
#define rx_chan_num(chan) ((chan) + CPDMA_MAX_CHANNELS)
#define is_rx_chan(chan) ((chan)->chan_num >= CPDMA_MAX_CHANNELS)
@@ -253,6 +276,31 @@ static void cpdma_desc_free(struct cpdma_desc_pool *pool,
gen_pool_free(pool->gen_pool, (unsigned long)desc, pool->desc_size);
}
+static int _cpdma_control_set(struct cpdma_ctlr *ctlr, int control, int value)
+{
+ struct cpdma_control_info *info = &controls[control];
+ u32 val;
+
+ if (!ctlr->params.has_ext_regs)
+ return -ENOTSUPP;
+
+ if (ctlr->state != CPDMA_STATE_ACTIVE)
+ return -EINVAL;
+
+ if (control < 0 || control >= ARRAY_SIZE(controls))
+ return -ENOENT;
+
+ if ((info->access & ACCESS_WO) != ACCESS_WO)
+ return -EPERM;
+
+ val = dma_reg_read(ctlr, info->reg);
+ val &= ~(info->mask << info->shift);
+ val |= (value & info->mask) << info->shift;
+ dma_reg_write(ctlr, info->reg, val);
+
+ return 0;
+}
+
struct cpdma_ctlr *cpdma_ctlr_create(struct cpdma_params *params)
{
struct cpdma_ctlr *ctlr;
@@ -324,6 +372,10 @@ int cpdma_ctlr_start(struct cpdma_ctlr *ctlr)
if (ctlr->channels[i])
cpdma_chan_start(ctlr->channels[i]);
}
+
+ _cpdma_control_set(ctlr, CPDMA_TX_PRIO_FIXED, 1);
+ _cpdma_control_set(ctlr, CPDMA_RX_BUFFER_OFFSET, 0);
+
spin_unlock_irqrestore(&ctlr->lock, flags);
return 0;
}
@@ -335,7 +387,7 @@ int cpdma_ctlr_stop(struct cpdma_ctlr *ctlr)
int i;
spin_lock_irqsave(&ctlr->lock, flags);
- if (ctlr->state == CPDMA_STATE_TEARDOWN) {
+ if (ctlr->state != CPDMA_STATE_ACTIVE) {
spin_unlock_irqrestore(&ctlr->lock, flags);
return -EINVAL;
}
@@ -533,7 +585,7 @@ int cpdma_chan_destroy(struct cpdma_chan *chan)
cpdma_chan_stop(chan);
ctlr->channels[chan->chan_num] = NULL;
ctlr->chan_num--;
-
+ devm_kfree(ctlr->dev, chan);
cpdma_chan_split_pool(ctlr);
spin_unlock_irqrestore(&ctlr->lock, flags);
@@ -874,29 +926,6 @@ int cpdma_chan_int_ctrl(struct cpdma_chan *chan, bool enable)
return 0;
}
-struct cpdma_control_info {
- u32 reg;
- u32 shift, mask;
- int access;
-#define ACCESS_RO BIT(0)
-#define ACCESS_WO BIT(1)
-#define ACCESS_RW (ACCESS_RO | ACCESS_WO)
-};
-
-static struct cpdma_control_info controls[] = {
- [CPDMA_CMD_IDLE] = {CPDMA_DMACONTROL, 3, 1, ACCESS_WO},
- [CPDMA_COPY_ERROR_FRAMES] = {CPDMA_DMACONTROL, 4, 1, ACCESS_RW},
- [CPDMA_RX_OFF_LEN_UPDATE] = {CPDMA_DMACONTROL, 2, 1, ACCESS_RW},
- [CPDMA_RX_OWNERSHIP_FLIP] = {CPDMA_DMACONTROL, 1, 1, ACCESS_RW},
- [CPDMA_TX_PRIO_FIXED] = {CPDMA_DMACONTROL, 0, 1, ACCESS_RW},
- [CPDMA_STAT_IDLE] = {CPDMA_DMASTATUS, 31, 1, ACCESS_RO},
- [CPDMA_STAT_TX_ERR_CODE] = {CPDMA_DMASTATUS, 20, 0xf, ACCESS_RW},
- [CPDMA_STAT_TX_ERR_CHAN] = {CPDMA_DMASTATUS, 16, 0x7, ACCESS_RW},
- [CPDMA_STAT_RX_ERR_CODE] = {CPDMA_DMASTATUS, 12, 0xf, ACCESS_RW},
- [CPDMA_STAT_RX_ERR_CHAN] = {CPDMA_DMASTATUS, 8, 0x7, ACCESS_RW},
- [CPDMA_RX_BUFFER_OFFSET] = {CPDMA_RXBUFFOFS, 0, 0xffff, ACCESS_RW},
-};
-
int cpdma_control_get(struct cpdma_ctlr *ctlr, int control)
{
unsigned long flags;
@@ -931,35 +960,10 @@ int cpdma_control_get(struct cpdma_ctlr *ctlr, int control)
int cpdma_control_set(struct cpdma_ctlr *ctlr, int control, int value)
{
unsigned long flags;
- struct cpdma_control_info *info = &controls[control];
int ret;
- u32 val;
spin_lock_irqsave(&ctlr->lock, flags);
-
- ret = -ENOTSUPP;
- if (!ctlr->params.has_ext_regs)
- goto unlock_ret;
-
- ret = -EINVAL;
- if (ctlr->state != CPDMA_STATE_ACTIVE)
- goto unlock_ret;
-
- ret = -ENOENT;
- if (control < 0 || control >= ARRAY_SIZE(controls))
- goto unlock_ret;
-
- ret = -EPERM;
- if ((info->access & ACCESS_WO) != ACCESS_WO)
- goto unlock_ret;
-
- val = dma_reg_read(ctlr, info->reg);
- val &= ~(info->mask << info->shift);
- val |= (value & info->mask) << info->shift;
- dma_reg_write(ctlr, info->reg, val);
- ret = 0;
-
-unlock_ret:
+ ret = _cpdma_control_set(ctlr, control, value);
spin_unlock_irqrestore(&ctlr->lock, flags);
return ret;
}
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index 2fd94a5..84fbe57 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -1410,6 +1410,7 @@ static int emac_dev_open(struct net_device *ndev)
int i = 0;
struct emac_priv *priv = netdev_priv(ndev);
struct phy_device *phydev = NULL;
+ struct device *phy = NULL;
ret = pm_runtime_get_sync(&priv->pdev->dev);
if (ret < 0) {
@@ -1488,19 +1489,20 @@ static int emac_dev_open(struct net_device *ndev)
/* use the first phy on the bus if pdata did not give us a phy id */
if (!phydev && !priv->phy_id) {
- struct device *phy;
-
phy = bus_find_device(&mdio_bus_type, NULL, NULL,
match_first_device);
- if (phy)
+ if (phy) {
priv->phy_id = dev_name(phy);
+ if (!priv->phy_id || !*priv->phy_id)
+ put_device(phy);
+ }
}
if (!phydev && priv->phy_id && *priv->phy_id) {
phydev = phy_connect(ndev, priv->phy_id,
&emac_adjust_link,
PHY_INTERFACE_MODE_MII);
-
+ put_device(phy); /* reference taken by bus_find_device */
if (IS_ERR(phydev)) {
dev_err(emac_dev, "could not connect to phy %s\n",
priv->phy_id);
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 78b4c83..7981b99 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -1568,7 +1568,7 @@ static int netcp_setup_navigator_resources(struct net_device *ndev)
/* open Tx completion queue */
snprintf(name, sizeof(name), "tx-compl-%s", ndev->name);
netcp->tx_compl_q = knav_queue_open(name, netcp->tx_compl_qid, 0);
- if (IS_ERR_OR_NULL(netcp->tx_compl_q)) {
+ if (IS_ERR(netcp->tx_compl_q)) {
ret = PTR_ERR(netcp->tx_compl_q);
goto fail;
}
@@ -1588,7 +1588,7 @@ static int netcp_setup_navigator_resources(struct net_device *ndev)
/* open Rx completion queue */
snprintf(name, sizeof(name), "rx-compl-%s", ndev->name);
netcp->rx_queue = knav_queue_open(name, netcp->rx_queue_id, 0);
- if (IS_ERR_OR_NULL(netcp->rx_queue)) {
+ if (IS_ERR(netcp->rx_queue)) {
ret = PTR_ERR(netcp->rx_queue);
goto fail;
}
@@ -1610,7 +1610,7 @@ static int netcp_setup_navigator_resources(struct net_device *ndev)
++i) {
snprintf(name, sizeof(name), "rx-fdq-%s-%d", ndev->name, i);
netcp->rx_fdq[i] = knav_queue_open(name, KNAV_QUEUE_GP, 0);
- if (IS_ERR_OR_NULL(netcp->rx_fdq[i])) {
+ if (IS_ERR(netcp->rx_fdq[i])) {
ret = PTR_ERR(netcp->rx_fdq[i]);
goto fail;
}
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c
index b3abd02..eed18f8 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c
@@ -1694,7 +1694,7 @@ struct gelic_wl_scan_info *gelic_wl_find_best_bss(struct gelic_wl_info *wl)
pr_debug("%s: bssid matched\n", __func__);
break;
} else {
- pr_debug("%s: bssid unmached\n", __func__);
+ pr_debug("%s: bssid unmatched\n", __func__);
continue;
}
}
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index a9bd665..bcd7b76 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -967,13 +967,8 @@ static const struct attribute_group temac_attr_group = {
};
/* ethtool support */
-static int temac_nway_reset(struct net_device *ndev)
-{
- return phy_start_aneg(ndev->phydev);
-}
-
static const struct ethtool_ops temac_ethtool_ops = {
- .nway_reset = temac_nway_reset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_link = ethtool_op_get_link,
.get_ts_info = ethtool_op_get_ts_info,
.get_link_ksettings = phy_ethtool_get_link_ksettings,
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index 46cc33b..aee55c0 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -708,8 +708,7 @@ static int eth_poll(struct napi_struct *napi, int budget)
if (!qmgr_stat_below_low_watermark(rxq) &&
napi_reschedule(napi)) { /* not empty again */
#if DEBUG_RX
- printk(KERN_DEBUG "%s: eth_poll"
- " napi_reschedule successed\n",
+ printk(KERN_DEBUG "%s: eth_poll napi_reschedule succeeded\n",
dev->name);
#endif
qmgr_disable_irq(rxq);
@@ -1002,11 +1001,6 @@ static void ixp4xx_get_drvinfo(struct net_device *dev,
strlcpy(info->bus_info, "internal", sizeof(info->bus_info));
}
-static int ixp4xx_nway_reset(struct net_device *dev)
-{
- return phy_start_aneg(dev->phydev);
-}
-
int ixp46x_phc_index = -1;
EXPORT_SYMBOL_GPL(ixp46x_phc_index);
@@ -1038,7 +1032,7 @@ static int ixp4xx_get_ts_info(struct net_device *dev,
static const struct ethtool_ops ixp4xx_ethtool_ops = {
.get_drvinfo = ixp4xx_get_drvinfo,
- .nway_reset = ixp4xx_nway_reset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_link = ethtool_op_get_link,
.get_ts_info = ixp4xx_get_ts_info,
.get_link_ksettings = phy_ethtool_get_link_ksettings,
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 752bcaa..90dc6b1 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -43,7 +43,7 @@ struct geneve_net {
struct list_head sock_list;
};
-static int geneve_net_id;
+static unsigned int geneve_net_id;
union geneve_addr {
struct sockaddr_in sin;
@@ -58,9 +58,9 @@ struct geneve_dev {
struct hlist_node hlist; /* vni hash table */
struct net *net; /* netns for packet i/o */
struct net_device *dev; /* netdev for geneve tunnel */
- struct geneve_sock *sock4; /* IPv4 socket used for geneve tunnel */
+ struct geneve_sock __rcu *sock4; /* IPv4 socket used for geneve tunnel */
#if IS_ENABLED(CONFIG_IPV6)
- struct geneve_sock *sock6; /* IPv6 socket used for geneve tunnel */
+ struct geneve_sock __rcu *sock6; /* IPv6 socket used for geneve tunnel */
#endif
u8 vni[3]; /* virtual network ID for tunnel */
u8 ttl; /* TTL override */
@@ -453,7 +453,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk,
skb_gro_pull(skb, gh_len);
skb_gro_postpull_rcsum(skb, gh, gh_len);
- pp = ptype->callbacks.gro_receive(head, skb);
+ pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
flush = 0;
out_unlock:
@@ -543,9 +543,19 @@ static void __geneve_sock_release(struct geneve_sock *gs)
static void geneve_sock_release(struct geneve_dev *geneve)
{
- __geneve_sock_release(geneve->sock4);
+ struct geneve_sock *gs4 = rtnl_dereference(geneve->sock4);
#if IS_ENABLED(CONFIG_IPV6)
- __geneve_sock_release(geneve->sock6);
+ struct geneve_sock *gs6 = rtnl_dereference(geneve->sock6);
+
+ rcu_assign_pointer(geneve->sock6, NULL);
+#endif
+
+ rcu_assign_pointer(geneve->sock4, NULL);
+ synchronize_net();
+
+ __geneve_sock_release(gs4);
+#if IS_ENABLED(CONFIG_IPV6)
+ __geneve_sock_release(gs6);
#endif
}
@@ -586,10 +596,10 @@ static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6)
gs->flags = geneve->flags;
#if IS_ENABLED(CONFIG_IPV6)
if (ipv6)
- geneve->sock6 = gs;
+ rcu_assign_pointer(geneve->sock6, gs);
else
#endif
- geneve->sock4 = gs;
+ rcu_assign_pointer(geneve->sock4, gs);
hash = geneve_net_vni_hash(geneve->vni);
hlist_add_head_rcu(&geneve->hlist, &gs->vni_list[hash]);
@@ -603,9 +613,7 @@ static int geneve_open(struct net_device *dev)
bool metadata = geneve->collect_md;
int ret = 0;
- geneve->sock4 = NULL;
#if IS_ENABLED(CONFIG_IPV6)
- geneve->sock6 = NULL;
if (ipv6 || metadata)
ret = geneve_sock_add(geneve, true);
#endif
@@ -720,6 +728,9 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
struct rtable *rt = NULL;
__u8 tos;
+ if (!rcu_dereference(geneve->sock4))
+ return ERR_PTR(-EIO);
+
memset(fl4, 0, sizeof(*fl4));
fl4->flowi4_mark = skb->mark;
fl4->flowi4_proto = IPPROTO_UDP;
@@ -772,11 +783,15 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
{
bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct geneve_dev *geneve = netdev_priv(dev);
- struct geneve_sock *gs6 = geneve->sock6;
struct dst_entry *dst = NULL;
struct dst_cache *dst_cache;
+ struct geneve_sock *gs6;
__u8 prio;
+ gs6 = rcu_dereference(geneve->sock6);
+ if (!gs6)
+ return ERR_PTR(-EIO);
+
memset(fl6, 0, sizeof(*fl6));
fl6->flowi6_mark = skb->mark;
fl6->flowi6_proto = IPPROTO_UDP;
@@ -842,7 +857,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
struct ip_tunnel_info *info)
{
struct geneve_dev *geneve = netdev_priv(dev);
- struct geneve_sock *gs4 = geneve->sock4;
+ struct geneve_sock *gs4;
struct rtable *rt = NULL;
const struct iphdr *iip; /* interior IP header */
int err = -EINVAL;
@@ -853,6 +868,10 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
bool xnet = !net_eq(geneve->net, dev_net(geneve->dev));
u32 flags = geneve->flags;
+ gs4 = rcu_dereference(geneve->sock4);
+ if (!gs4)
+ goto tx_error;
+
if (geneve->collect_md) {
if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) {
netdev_dbg(dev, "no tunnel metadata\n");
@@ -932,9 +951,9 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
struct ip_tunnel_info *info)
{
struct geneve_dev *geneve = netdev_priv(dev);
- struct geneve_sock *gs6 = geneve->sock6;
struct dst_entry *dst = NULL;
const struct iphdr *iip; /* interior IP header */
+ struct geneve_sock *gs6;
int err = -EINVAL;
struct flowi6 fl6;
__u8 prio, ttl;
@@ -943,6 +962,10 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
bool xnet = !net_eq(geneve->net, dev_net(geneve->dev));
u32 flags = geneve->flags;
+ gs6 = rcu_dereference(geneve->sock6);
+ if (!gs6)
+ goto tx_error;
+
if (geneve->collect_md) {
if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) {
netdev_dbg(dev, "no tunnel metadata\n");
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 719d19f..98f10c2 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -77,7 +77,7 @@ struct gtp_dev {
struct hlist_head *addr_hash;
};
-static int gtp_net_id __read_mostly;
+static unsigned int gtp_net_id __read_mostly;
struct gtp_net {
struct list_head gtp_dev_list;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 3b28cf1..9522763 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -447,7 +447,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
* Setup the sendside checksum offload only if this is not a
* GSO packet.
*/
- if (skb_is_gso(skb)) {
+ if ((net_trans_info & (INFO_TCP | INFO_UDP)) && skb_is_gso(skb)) {
struct ndis_tcp_lso_info *lso_info;
rndis_msg_size += NDIS_LSO_PPI_SIZE;
@@ -607,15 +607,18 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net,
packet->total_data_buflen);
skb->protocol = eth_type_trans(skb, net);
- if (csum_info) {
- /* We only look at the IP checksum here.
- * Should we be dropping the packet if checksum
- * failed? How do we deal with other checksums - TCP/UDP?
- */
- if (csum_info->receive.ip_checksum_succeeded)
+
+ /* skb is already created with CHECKSUM_NONE */
+ skb_checksum_none_assert(skb);
+
+ /*
+ * In Linux, the IP checksum is always checked.
+ * Do L4 checksum offload if enabled and present.
+ */
+ if (csum_info && (net->features & NETIF_F_RXCSUM)) {
+ if (csum_info->receive.tcp_checksum_succeeded ||
+ csum_info->receive.udp_checksum_succeeded)
skb->ip_summed = CHECKSUM_UNNECESSARY;
- else
- skb->ip_summed = CHECKSUM_NONE;
}
if (vlan_tci & VLAN_TAG_PRESENT)
@@ -696,12 +699,8 @@ int netvsc_recv_callback(struct hv_device *device_obj,
static void netvsc_get_drvinfo(struct net_device *net,
struct ethtool_drvinfo *info)
{
- struct net_device_context *net_device_ctx = netdev_priv(net);
- struct hv_device *dev = net_device_ctx->device_ctx;
-
strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
- strlcpy(info->bus_info, vmbus_dev_name(dev), sizeof(info->bus_info));
}
static void netvsc_get_channels(struct net_device *net,
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 0a715ab..cc00eb0 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -397,6 +397,14 @@ static struct macsec_cb *macsec_skb_cb(struct sk_buff *skb)
#define DEFAULT_ENCRYPT false
#define DEFAULT_ENCODING_SA 0
+static bool send_sci(const struct macsec_secy *secy)
+{
+ const struct macsec_tx_sc *tx_sc = &secy->tx_sc;
+
+ return tx_sc->send_sci ||
+ (secy->n_rx_sc > 1 && !tx_sc->end_station && !tx_sc->scb);
+}
+
static sci_t make_sci(u8 *addr, __be16 port)
{
sci_t sci;
@@ -437,15 +445,15 @@ static unsigned int macsec_extra_len(bool sci_present)
/* Fill SecTAG according to IEEE 802.1AE-2006 10.5.3 */
static void macsec_fill_sectag(struct macsec_eth_header *h,
- const struct macsec_secy *secy, u32 pn)
+ const struct macsec_secy *secy, u32 pn,
+ bool sci_present)
{
const struct macsec_tx_sc *tx_sc = &secy->tx_sc;
- memset(&h->tci_an, 0, macsec_sectag_len(tx_sc->send_sci));
+ memset(&h->tci_an, 0, macsec_sectag_len(sci_present));
h->eth.h_proto = htons(ETH_P_MACSEC);
- if (tx_sc->send_sci ||
- (secy->n_rx_sc > 1 && !tx_sc->end_station && !tx_sc->scb)) {
+ if (sci_present) {
h->tci_an |= MACSEC_TCI_SC;
memcpy(&h->secure_channel_id, &secy->sci,
sizeof(h->secure_channel_id));
@@ -650,6 +658,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
struct macsec_tx_sc *tx_sc;
struct macsec_tx_sa *tx_sa;
struct macsec_dev *macsec = macsec_priv(dev);
+ bool sci_present;
u32 pn;
secy = &macsec->secy;
@@ -687,7 +696,8 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
unprotected_len = skb->len;
eth = eth_hdr(skb);
- hh = (struct macsec_eth_header *)skb_push(skb, macsec_extra_len(tx_sc->send_sci));
+ sci_present = send_sci(secy);
+ hh = (struct macsec_eth_header *)skb_push(skb, macsec_extra_len(sci_present));
memmove(hh, eth, 2 * ETH_ALEN);
pn = tx_sa_update_pn(tx_sa, secy);
@@ -696,7 +706,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
kfree_skb(skb);
return ERR_PTR(-ENOLINK);
}
- macsec_fill_sectag(hh, secy, pn);
+ macsec_fill_sectag(hh, secy, pn, sci_present);
macsec_set_shortlen(hh, unprotected_len - 2 * ETH_ALEN);
skb_put(skb, secy->icv_len);
@@ -726,10 +736,10 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb,
skb_to_sgvec(skb, sg, 0, skb->len);
if (tx_sc->encrypt) {
- int len = skb->len - macsec_hdr_len(tx_sc->send_sci) -
+ int len = skb->len - macsec_hdr_len(sci_present) -
secy->icv_len;
aead_request_set_crypt(req, sg, sg, len, iv);
- aead_request_set_ad(req, macsec_hdr_len(tx_sc->send_sci));
+ aead_request_set_ad(req, macsec_hdr_len(sci_present));
} else {
aead_request_set_crypt(req, sg, sg, 0, iv);
aead_request_set_ad(req, skb->len - secy->icv_len);
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index a064415..13b7e0b 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -179,20 +179,20 @@ static void macvlan_hash_change_addr(struct macvlan_dev *vlan,
macvlan_hash_add(vlan);
}
-static int macvlan_addr_busy(const struct macvlan_port *port,
- const unsigned char *addr)
+static bool macvlan_addr_busy(const struct macvlan_port *port,
+ const unsigned char *addr)
{
/* Test to see if the specified multicast address is
* currently in use by the underlying device or
* another macvlan.
*/
if (ether_addr_equal_64bits(port->dev->dev_addr, addr))
- return 1;
+ return true;
if (macvlan_hash_lookup(port, addr))
- return 1;
+ return true;
- return 0;
+ return false;
}
@@ -1280,6 +1280,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
struct net_device *lowerdev;
int err;
int macmode;
+ bool create = false;
if (!tb[IFLA_LINK])
return -EINVAL;
@@ -1310,12 +1311,18 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
err = macvlan_port_create(lowerdev);
if (err < 0)
return err;
+ create = true;
}
port = macvlan_port_get_rtnl(lowerdev);
/* Only 1 macvlan device can be created in passthru mode */
- if (port->passthru)
- return -EINVAL;
+ if (port->passthru) {
+ /* The macvlan port must be not created this time,
+ * still goto destroy_macvlan_port for readability.
+ */
+ err = -EINVAL;
+ goto destroy_macvlan_port;
+ }
vlan->lowerdev = lowerdev;
vlan->dev = dev;
@@ -1331,24 +1338,28 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
vlan->flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]);
if (vlan->mode == MACVLAN_MODE_PASSTHRU) {
- if (port->count)
- return -EINVAL;
+ if (port->count) {
+ err = -EINVAL;
+ goto destroy_macvlan_port;
+ }
port->passthru = true;
eth_hw_addr_inherit(dev, lowerdev);
}
if (data && data[IFLA_MACVLAN_MACADDR_MODE]) {
- if (vlan->mode != MACVLAN_MODE_SOURCE)
- return -EINVAL;
+ if (vlan->mode != MACVLAN_MODE_SOURCE) {
+ err = -EINVAL;
+ goto destroy_macvlan_port;
+ }
macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]);
err = macvlan_changelink_sources(vlan, macmode, data);
if (err)
- return err;
+ goto destroy_macvlan_port;
}
err = register_netdevice(dev);
if (err < 0)
- return err;
+ goto destroy_macvlan_port;
dev->priv_flags |= IFF_MACVLAN;
err = netdev_upper_dev_link(lowerdev, dev);
@@ -1363,7 +1374,9 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
unregister_netdev:
unregister_netdevice(dev);
-
+destroy_macvlan_port:
+ if (create)
+ macvlan_port_destroy(port->dev);
return err;
}
EXPORT_SYMBOL_GPL(macvlan_common_newlink);
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 070e329..5da9861 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -821,9 +821,8 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
if (iov_iter_count(iter) < vnet_hdr_len)
return -EINVAL;
- ret = virtio_net_hdr_from_skb(skb, &vnet_hdr,
- macvtap_is_little_endian(q));
- if (ret)
+ if (virtio_net_hdr_from_skb(skb, &vnet_hdr,
+ macvtap_is_little_endian(q)))
BUG();
if (copy_to_iter(&vnet_hdr, sizeof(vnet_hdr), iter) !=
diff --git a/drivers/net/mii.c b/drivers/net/mii.c
index 993570b..6d953c5 100644
--- a/drivers/net/mii.c
+++ b/drivers/net/mii.c
@@ -135,6 +135,103 @@ int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd)
}
/**
+ * mii_ethtool_get_link_ksettings - get settings that are specified in @cmd
+ * @mii: MII interface
+ * @cmd: requested ethtool_link_ksettings
+ *
+ * The @cmd parameter is expected to have been cleared before calling
+ * mii_ethtool_get_link_ksettings().
+ *
+ * Returns 0 for success, negative on error.
+ */
+int mii_ethtool_get_link_ksettings(struct mii_if_info *mii,
+ struct ethtool_link_ksettings *cmd)
+{
+ struct net_device *dev = mii->dev;
+ u16 bmcr, bmsr, ctrl1000 = 0, stat1000 = 0;
+ u32 nego, supported, advertising, lp_advertising;
+
+ supported = (SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full |
+ SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full |
+ SUPPORTED_Autoneg | SUPPORTED_TP | SUPPORTED_MII);
+ if (mii->supports_gmii)
+ supported |= SUPPORTED_1000baseT_Half |
+ SUPPORTED_1000baseT_Full;
+
+ /* only supports twisted-pair */
+ cmd->base.port = PORT_MII;
+
+ /* this isn't fully supported at higher layers */
+ cmd->base.phy_address = mii->phy_id;
+ cmd->base.mdio_support = ETH_MDIO_SUPPORTS_C22;
+
+ advertising = ADVERTISED_TP | ADVERTISED_MII;
+
+ bmcr = mii->mdio_read(dev, mii->phy_id, MII_BMCR);
+ bmsr = mii->mdio_read(dev, mii->phy_id, MII_BMSR);
+ if (mii->supports_gmii) {
+ ctrl1000 = mii->mdio_read(dev, mii->phy_id, MII_CTRL1000);
+ stat1000 = mii->mdio_read(dev, mii->phy_id, MII_STAT1000);
+ }
+ if (bmcr & BMCR_ANENABLE) {
+ advertising |= ADVERTISED_Autoneg;
+ cmd->base.autoneg = AUTONEG_ENABLE;
+
+ advertising |= mii_get_an(mii, MII_ADVERTISE);
+ if (mii->supports_gmii)
+ advertising |= mii_ctrl1000_to_ethtool_adv_t(ctrl1000);
+
+ if (bmsr & BMSR_ANEGCOMPLETE) {
+ lp_advertising = mii_get_an(mii, MII_LPA);
+ lp_advertising |=
+ mii_stat1000_to_ethtool_lpa_t(stat1000);
+ } else {
+ lp_advertising = 0;
+ }
+
+ nego = advertising & lp_advertising;
+
+ if (nego & (ADVERTISED_1000baseT_Full |
+ ADVERTISED_1000baseT_Half)) {
+ cmd->base.speed = SPEED_1000;
+ cmd->base.duplex = !!(nego & ADVERTISED_1000baseT_Full);
+ } else if (nego & (ADVERTISED_100baseT_Full |
+ ADVERTISED_100baseT_Half)) {
+ cmd->base.speed = SPEED_100;
+ cmd->base.duplex = !!(nego & ADVERTISED_100baseT_Full);
+ } else {
+ cmd->base.speed = SPEED_10;
+ cmd->base.duplex = !!(nego & ADVERTISED_10baseT_Full);
+ }
+ } else {
+ cmd->base.autoneg = AUTONEG_DISABLE;
+
+ cmd->base.speed = ((bmcr & BMCR_SPEED1000 &&
+ (bmcr & BMCR_SPEED100) == 0) ?
+ SPEED_1000 :
+ ((bmcr & BMCR_SPEED100) ?
+ SPEED_100 : SPEED_10));
+ cmd->base.duplex = (bmcr & BMCR_FULLDPLX) ?
+ DUPLEX_FULL : DUPLEX_HALF;
+
+ lp_advertising = 0;
+ }
+
+ mii->full_duplex = cmd->base.duplex;
+
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+ supported);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
+ advertising);
+ ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.lp_advertising,
+ lp_advertising);
+
+ /* ignore maxtxpkt, maxrxpkt for now */
+
+ return 0;
+}
+
+/**
* mii_ethtool_sset - set settings that are specified in @ecmd
* @mii: MII interface
* @ecmd: requested ethtool_cmd
@@ -227,6 +324,104 @@ int mii_ethtool_sset(struct mii_if_info *mii, struct ethtool_cmd *ecmd)
}
/**
+ * mii_ethtool_set_link_ksettings - set settings that are specified in @cmd
+ * @mii: MII interfaces
+ * @cmd: requested ethtool_link_ksettings
+ *
+ * Returns 0 for success, negative on error.
+ */
+int mii_ethtool_set_link_ksettings(struct mii_if_info *mii,
+ const struct ethtool_link_ksettings *cmd)
+{
+ struct net_device *dev = mii->dev;
+ u32 speed = cmd->base.speed;
+
+ if (speed != SPEED_10 &&
+ speed != SPEED_100 &&
+ speed != SPEED_1000)
+ return -EINVAL;
+ if (cmd->base.duplex != DUPLEX_HALF && cmd->base.duplex != DUPLEX_FULL)
+ return -EINVAL;
+ if (cmd->base.port != PORT_MII)
+ return -EINVAL;
+ if (cmd->base.phy_address != mii->phy_id)
+ return -EINVAL;
+ if (cmd->base.autoneg != AUTONEG_DISABLE &&
+ cmd->base.autoneg != AUTONEG_ENABLE)
+ return -EINVAL;
+ if ((speed == SPEED_1000) && (!mii->supports_gmii))
+ return -EINVAL;
+
+ /* ignore supported, maxtxpkt, maxrxpkt */
+
+ if (cmd->base.autoneg == AUTONEG_ENABLE) {
+ u32 bmcr, advert, tmp;
+ u32 advert2 = 0, tmp2 = 0;
+ u32 advertising;
+
+ ethtool_convert_link_mode_to_legacy_u32(
+ &advertising, cmd->link_modes.advertising);
+
+ if ((advertising & (ADVERTISED_10baseT_Half |
+ ADVERTISED_10baseT_Full |
+ ADVERTISED_100baseT_Half |
+ ADVERTISED_100baseT_Full |
+ ADVERTISED_1000baseT_Half |
+ ADVERTISED_1000baseT_Full)) == 0)
+ return -EINVAL;
+
+ /* advertise only what has been requested */
+ advert = mii->mdio_read(dev, mii->phy_id, MII_ADVERTISE);
+ tmp = advert & ~(ADVERTISE_ALL | ADVERTISE_100BASE4);
+ if (mii->supports_gmii) {
+ advert2 = mii->mdio_read(dev, mii->phy_id,
+ MII_CTRL1000);
+ tmp2 = advert2 &
+ ~(ADVERTISE_1000HALF | ADVERTISE_1000FULL);
+ }
+ tmp |= ethtool_adv_to_mii_adv_t(advertising);
+
+ if (mii->supports_gmii)
+ tmp2 |= ethtool_adv_to_mii_ctrl1000_t(advertising);
+ if (advert != tmp) {
+ mii->mdio_write(dev, mii->phy_id, MII_ADVERTISE, tmp);
+ mii->advertising = tmp;
+ }
+ if ((mii->supports_gmii) && (advert2 != tmp2))
+ mii->mdio_write(dev, mii->phy_id, MII_CTRL1000, tmp2);
+
+ /* turn on autonegotiation, and force a renegotiate */
+ bmcr = mii->mdio_read(dev, mii->phy_id, MII_BMCR);
+ bmcr |= (BMCR_ANENABLE | BMCR_ANRESTART);
+ mii->mdio_write(dev, mii->phy_id, MII_BMCR, bmcr);
+
+ mii->force_media = 0;
+ } else {
+ u32 bmcr, tmp;
+
+ /* turn off auto negotiation, set speed and duplexity */
+ bmcr = mii->mdio_read(dev, mii->phy_id, MII_BMCR);
+ tmp = bmcr & ~(BMCR_ANENABLE | BMCR_SPEED100 |
+ BMCR_SPEED1000 | BMCR_FULLDPLX);
+ if (speed == SPEED_1000)
+ tmp |= BMCR_SPEED1000;
+ else if (speed == SPEED_100)
+ tmp |= BMCR_SPEED100;
+ if (cmd->base.duplex == DUPLEX_FULL) {
+ tmp |= BMCR_FULLDPLX;
+ mii->full_duplex = 1;
+ } else {
+ mii->full_duplex = 0;
+ }
+ if (bmcr != tmp)
+ mii->mdio_write(dev, mii->phy_id, MII_BMCR, tmp);
+
+ mii->force_media = 1;
+ }
+ return 0;
+}
+
+/**
* mii_check_gmii_support - check if the MII supports Gb interfaces
* @mii: the MII interface
*/
@@ -466,7 +661,9 @@ MODULE_LICENSE("GPL");
EXPORT_SYMBOL(mii_link_ok);
EXPORT_SYMBOL(mii_nway_restart);
EXPORT_SYMBOL(mii_ethtool_gset);
+EXPORT_SYMBOL(mii_ethtool_get_link_ksettings);
EXPORT_SYMBOL(mii_ethtool_sset);
+EXPORT_SYMBOL(mii_ethtool_set_link_ksettings);
EXPORT_SYMBOL(mii_check_link);
EXPORT_SYMBOL(mii_check_media);
EXPORT_SYMBOL(mii_check_gmii_support);
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 45f68ea..d361835 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -217,7 +217,7 @@
select BCM_NET_PHYLIB
---help---
Currently supports the BCM5411, BCM5421, BCM5461, BCM54616S, BCM5464,
- BCM5481 and BCM5482 PHYs.
+ BCM5481, BCM54810 and BCM5482 PHYs.
config CICADA_PHY
tristate "Cicada PHYs"
@@ -277,6 +277,11 @@
---help---
Currently has a driver for the 88E1011S
+config MESON_GXL_PHY
+ tristate "Amlogic Meson GXL Internal PHY"
+ ---help---
+ Currently has a driver for the Amlogic Meson GXL Internal PHY
+
config MICREL_PHY
tristate "Micrel PHYs"
---help---
@@ -290,7 +295,7 @@
config MICROSEMI_PHY
tristate "Microsemi PHYs"
---help---
- Currently supports the VSC8531 and VSC8541 PHYs
+ Currently supports VSC8530, VSC8531, VSC8540 and VSC8541 PHYs
config NATIONAL_PHY
tristate "National Semiconductor PHYs"
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 86d12cd..356859a 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -42,6 +42,7 @@
obj-$(CONFIG_LSI_ET1011C_PHY) += et1011c.o
obj-$(CONFIG_LXT_PHY) += lxt.o
obj-$(CONFIG_MARVELL_PHY) += marvell.o
+obj-$(CONFIG_MESON_GXL_PHY) += meson-gxl.o
obj-$(CONFIG_MICREL_KS8995MA) += spi_ks8995.o
obj-$(CONFIG_MICREL_PHY) += micrel.o
obj-$(CONFIG_MICROCHIP_PHY) += microchip.o
diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index dd47b69..c1e52b9 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -42,19 +42,24 @@
#define AT803X_MMD_ACCESS_CONTROL 0x0D
#define AT803X_MMD_ACCESS_CONTROL_DATA 0x0E
#define AT803X_FUNC_DATA 0x4003
+#define AT803X_REG_CHIP_CONFIG 0x1f
+#define AT803X_BT_BX_REG_SEL 0x8000
#define AT803X_DEBUG_ADDR 0x1D
#define AT803X_DEBUG_DATA 0x1E
+#define AT803X_MODE_CFG_MASK 0x0F
+#define AT803X_MODE_CFG_SGMII 0x01
+
+#define AT803X_PSSR 0x11 /*PHY-Specific Status Register*/
+#define AT803X_PSSR_MR_AN_COMPLETE 0x0200
+
#define AT803X_DEBUG_REG_0 0x00
#define AT803X_DEBUG_RX_CLK_DLY_EN BIT(15)
#define AT803X_DEBUG_REG_5 0x05
#define AT803X_DEBUG_TX_CLK_DLY_EN BIT(8)
-#define AT803X_REG_CHIP_CONFIG 0x1f
-#define AT803X_BT_BX_REG_SEL 0x8000
-
#define ATH8030_PHY_ID 0x004dd076
#define ATH8031_PHY_ID 0x004dd074
#define ATH8035_PHY_ID 0x004dd072
@@ -210,7 +215,6 @@ static int at803x_suspend(struct phy_device *phydev)
{
int value;
int wol_enabled;
- int ccr;
mutex_lock(&phydev->lock);
@@ -226,16 +230,6 @@ static int at803x_suspend(struct phy_device *phydev)
phy_write(phydev, MII_BMCR, value);
- if (phydev->interface != PHY_INTERFACE_MODE_SGMII)
- goto done;
-
- /* also power-down SGMII interface */
- ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG);
- phy_write(phydev, AT803X_REG_CHIP_CONFIG, ccr & ~AT803X_BT_BX_REG_SEL);
- phy_write(phydev, MII_BMCR, phy_read(phydev, MII_BMCR) | BMCR_PDOWN);
- phy_write(phydev, AT803X_REG_CHIP_CONFIG, ccr | AT803X_BT_BX_REG_SEL);
-
-done:
mutex_unlock(&phydev->lock);
return 0;
@@ -244,7 +238,6 @@ static int at803x_suspend(struct phy_device *phydev)
static int at803x_resume(struct phy_device *phydev)
{
int value;
- int ccr;
mutex_lock(&phydev->lock);
@@ -252,17 +245,6 @@ static int at803x_resume(struct phy_device *phydev)
value &= ~(BMCR_PDOWN | BMCR_ISOLATE);
phy_write(phydev, MII_BMCR, value);
- if (phydev->interface != PHY_INTERFACE_MODE_SGMII)
- goto done;
-
- /* also power-up SGMII interface */
- ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG);
- phy_write(phydev, AT803X_REG_CHIP_CONFIG, ccr & ~AT803X_BT_BX_REG_SEL);
- value = phy_read(phydev, MII_BMCR) & ~(BMCR_PDOWN | BMCR_ISOLATE);
- phy_write(phydev, MII_BMCR, value);
- phy_write(phydev, AT803X_REG_CHIP_CONFIG, ccr | AT803X_BT_BX_REG_SEL);
-
-done:
mutex_unlock(&phydev->lock);
return 0;
@@ -382,6 +364,36 @@ static void at803x_link_change_notify(struct phy_device *phydev)
}
}
+static int at803x_aneg_done(struct phy_device *phydev)
+{
+ int ccr;
+
+ int aneg_done = genphy_aneg_done(phydev);
+ if (aneg_done != BMSR_ANEGCOMPLETE)
+ return aneg_done;
+
+ /*
+ * in SGMII mode, if copper side autoneg is successful,
+ * also check SGMII side autoneg result
+ */
+ ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG);
+ if ((ccr & AT803X_MODE_CFG_MASK) != AT803X_MODE_CFG_SGMII)
+ return aneg_done;
+
+ /* switch to SGMII/fiber page */
+ phy_write(phydev, AT803X_REG_CHIP_CONFIG, ccr & ~AT803X_BT_BX_REG_SEL);
+
+ /* check if the SGMII link is OK. */
+ if (!(phy_read(phydev, AT803X_PSSR) & AT803X_PSSR_MR_AN_COMPLETE)) {
+ pr_warn("803x_aneg_done: SGMII link is not ok\n");
+ aneg_done = 0;
+ }
+ /* switch back to copper page */
+ phy_write(phydev, AT803X_REG_CHIP_CONFIG, ccr | AT803X_BT_BX_REG_SEL);
+
+ return aneg_done;
+}
+
static struct phy_driver at803x_driver[] = {
{
/* ATHEROS 8035 */
@@ -433,6 +445,7 @@ static struct phy_driver at803x_driver[] = {
.flags = PHY_HAS_INTERRUPT,
.config_aneg = genphy_config_aneg,
.read_status = genphy_read_status,
+ .aneg_done = at803x_aneg_done,
.ack_interrupt = &at803x_ack_interrupt,
.config_intr = &at803x_config_intr,
} };
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 583ef8a..b1e32e9 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -18,7 +18,7 @@
#include <linux/module.h>
#include <linux/phy.h>
#include <linux/brcmphy.h>
-
+#include <linux/of.h>
#define BRCM_PHY_MODEL(phydev) \
((phydev)->drv->phy_id & (phydev)->drv->phy_id_mask)
@@ -30,11 +30,49 @@ MODULE_DESCRIPTION("Broadcom PHY driver");
MODULE_AUTHOR("Maciej W. Rozycki");
MODULE_LICENSE("GPL");
+static int bcm54xx_auxctl_read(struct phy_device *phydev, u16 regnum)
+{
+ /* The register must be written to both the Shadow Register Select and
+ * the Shadow Read Register Selector
+ */
+ phy_write(phydev, MII_BCM54XX_AUX_CTL, regnum |
+ regnum << MII_BCM54XX_AUXCTL_SHDWSEL_READ_SHIFT);
+ return phy_read(phydev, MII_BCM54XX_AUX_CTL);
+}
+
static int bcm54xx_auxctl_write(struct phy_device *phydev, u16 regnum, u16 val)
{
return phy_write(phydev, MII_BCM54XX_AUX_CTL, regnum | val);
}
+static int bcm54810_config(struct phy_device *phydev)
+{
+ int rc, val;
+
+ val = bcm_phy_read_exp(phydev, BCM54810_EXP_BROADREACH_LRE_MISC_CTL);
+ val &= ~BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN;
+ rc = bcm_phy_write_exp(phydev, BCM54810_EXP_BROADREACH_LRE_MISC_CTL,
+ val);
+ if (rc < 0)
+ return rc;
+
+ val = bcm54xx_auxctl_read(phydev, MII_BCM54XX_AUXCTL_SHDWSEL_MISC);
+ val &= ~MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN;
+ val |= MII_BCM54XX_AUXCTL_MISC_WREN;
+ rc = bcm54xx_auxctl_write(phydev, MII_BCM54XX_AUXCTL_SHDWSEL_MISC,
+ val);
+ if (rc < 0)
+ return rc;
+
+ val = bcm_phy_read_shadow(phydev, BCM54810_SHD_CLK_CTL);
+ val &= ~BCM54810_SHD_CLK_CTL_GTXCLK_EN;
+ rc = bcm_phy_write_shadow(phydev, BCM54810_SHD_CLK_CTL, val);
+ if (rc < 0)
+ return rc;
+
+ return 0;
+}
+
/* Needs SMDSP clock enabled via bcm54xx_phydsp_config() */
static int bcm50610_a0_workaround(struct phy_device *phydev)
{
@@ -207,6 +245,12 @@ static int bcm54xx_config_init(struct phy_device *phydev)
(phydev->dev_flags & PHY_BRCM_AUTO_PWRDWN_ENABLE))
bcm54xx_adjust_rxrefclk(phydev);
+ if (BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54810) {
+ err = bcm54810_config(phydev);
+ if (err)
+ return err;
+ }
+
bcm54xx_phydsp_config(phydev);
return 0;
@@ -304,6 +348,7 @@ static int bcm5482_read_status(struct phy_device *phydev)
static int bcm5481_config_aneg(struct phy_device *phydev)
{
+ struct device_node *np = phydev->mdio.dev.of_node;
int ret;
/* Aneg firsly. */
@@ -334,6 +379,14 @@ static int bcm5481_config_aneg(struct phy_device *phydev)
phy_write(phydev, 0x18, reg);
}
+ if (of_property_read_bool(np, "enet-phy-lane-swap")) {
+ /* Lane Swap - Undocumented register...magic! */
+ ret = bcm_phy_write_exp(phydev, MII_BCM54XX_EXP_SEL_ER + 0x9,
+ 0x11B);
+ if (ret < 0)
+ return ret;
+ }
+
return ret;
}
@@ -568,6 +621,18 @@ static struct phy_driver broadcom_drivers[] = {
.ack_interrupt = bcm_phy_ack_intr,
.config_intr = bcm_phy_config_intr,
}, {
+ .phy_id = PHY_ID_BCM54810,
+ .phy_id_mask = 0xfffffff0,
+ .name = "Broadcom BCM54810",
+ .features = PHY_GBIT_FEATURES |
+ SUPPORTED_Pause | SUPPORTED_Asym_Pause,
+ .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
+ .config_init = bcm54xx_config_init,
+ .config_aneg = bcm5481_config_aneg,
+ .read_status = genphy_read_status,
+ .ack_interrupt = bcm_phy_ack_intr,
+ .config_intr = bcm_phy_config_intr,
+}, {
.phy_id = PHY_ID_BCM5482,
.phy_id_mask = 0xfffffff0,
.name = "Broadcom BCM5482",
@@ -651,6 +716,7 @@ static struct mdio_device_id __maybe_unused broadcom_tbl[] = {
{ PHY_ID_BCM54616S, 0xfffffff0 },
{ PHY_ID_BCM5464, 0xfffffff0 },
{ PHY_ID_BCM5481, 0xfffffff0 },
+ { PHY_ID_BCM54810, 0xfffffff0 },
{ PHY_ID_BCM5482, 0xfffffff0 },
{ PHY_ID_BCM50610, 0xfffffff0 },
{ PHY_ID_BCM50610M, 0xfffffff0 },
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 7a240fc..e2460a5 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -375,7 +375,7 @@ static int periodic_output(struct dp83640_clock *clock,
/* ptp clock methods */
-static int ptp_dp83640_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+static int ptp_dp83640_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
{
struct dp83640_clock *clock =
container_of(ptp, struct dp83640_clock, caps);
@@ -384,13 +384,13 @@ static int ptp_dp83640_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
int neg_adj = 0;
u16 hi, lo;
- if (ppb < 0) {
+ if (scaled_ppm < 0) {
neg_adj = 1;
- ppb = -ppb;
+ scaled_ppm = -scaled_ppm;
}
- rate = ppb;
- rate <<= 26;
- rate = div_u64(rate, 1953125);
+ rate = scaled_ppm;
+ rate <<= 13;
+ rate = div_u64(rate, 15625);
hi = (rate >> 16) & PTP_RATE_HI_MASK;
if (neg_adj)
@@ -1035,7 +1035,7 @@ static void dp83640_clock_init(struct dp83640_clock *clock, struct mii_bus *bus)
clock->caps.n_per_out = N_PER_OUT;
clock->caps.n_pins = DP83640_N_PINS;
clock->caps.pps = 0;
- clock->caps.adjfreq = ptp_dp83640_adjfreq;
+ clock->caps.adjfine = ptp_dp83640_adjfine;
clock->caps.adjtime = ptp_dp83640_adjtime;
clock->caps.gettime64 = ptp_dp83640_gettime;
clock->caps.settime64 = ptp_dp83640_settime;
diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c
index 03d54c4..800b39f 100644
--- a/drivers/net/phy/dp83848.c
+++ b/drivers/net/phy/dp83848.c
@@ -19,6 +19,7 @@
#define TI_DP83848C_PHY_ID 0x20005ca0
#define NS_DP83848C_PHY_ID 0x20005c90
#define TLK10X_PHY_ID 0x2000a210
+#define TI_DP83822_PHY_ID 0x2000a240
/* Registers */
#define DP83848_MICR 0x11 /* MII Interrupt Control Register */
@@ -77,6 +78,7 @@ static struct mdio_device_id __maybe_unused dp83848_tbl[] = {
{ TI_DP83848C_PHY_ID, 0xfffffff0 },
{ NS_DP83848C_PHY_ID, 0xfffffff0 },
{ TLK10X_PHY_ID, 0xfffffff0 },
+ { TI_DP83822_PHY_ID, 0xfffffff0 },
{ }
};
MODULE_DEVICE_TABLE(mdio, dp83848_tbl);
@@ -105,6 +107,7 @@ static struct phy_driver dp83848_driver[] = {
DP83848_PHY_DRIVER(TI_DP83848C_PHY_ID, "TI DP83848C 10/100 Mbps PHY"),
DP83848_PHY_DRIVER(NS_DP83848C_PHY_ID, "NS DP83848C 10/100 Mbps PHY"),
DP83848_PHY_DRIVER(TLK10X_PHY_ID, "TI TLK10X 10/100 Mbps PHY"),
+ DP83848_PHY_DRIVER(TI_DP83822_PHY_ID, "TI DP83822 10/100 Mbps PHY"),
};
module_phy_driver(dp83848_driver);
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index c2dcf02..fa31f50 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -361,7 +361,7 @@ static int m88e1111_config_aneg(struct phy_device *phydev)
static int marvell_of_reg_init(struct phy_device *phydev)
{
const __be32 *paddr;
- int len, i, saved_page, current_page, page_changed, ret;
+ int len, i, saved_page, current_page, ret;
if (!phydev->mdio.dev.of_node)
return 0;
@@ -374,7 +374,6 @@ static int marvell_of_reg_init(struct phy_device *phydev)
saved_page = phy_read(phydev, MII_MARVELL_PHY_PAGE);
if (saved_page < 0)
return saved_page;
- page_changed = 0;
current_page = saved_page;
ret = 0;
@@ -388,7 +387,6 @@ static int marvell_of_reg_init(struct phy_device *phydev)
if (reg_page != current_page) {
current_page = reg_page;
- page_changed = 1;
ret = phy_write(phydev, MII_MARVELL_PHY_PAGE, reg_page);
if (ret < 0)
goto err;
@@ -411,7 +409,7 @@ static int marvell_of_reg_init(struct phy_device *phydev)
}
err:
- if (page_changed) {
+ if (current_page != saved_page) {
i = phy_write(phydev, MII_MARVELL_PHY_PAGE, saved_page);
if (ret == 0)
ret = i;
diff --git a/drivers/net/phy/mdio-mux-mmioreg.c b/drivers/net/phy/mdio-mux-mmioreg.c
index d0bed52..6a33646 100644
--- a/drivers/net/phy/mdio-mux-mmioreg.c
+++ b/drivers/net/phy/mdio-mux-mmioreg.c
@@ -21,7 +21,8 @@
struct mdio_mux_mmioreg_state {
void *mux_handle;
phys_addr_t phys;
- uint8_t mask;
+ unsigned int iosize;
+ unsigned int mask;
};
/*
@@ -47,17 +48,47 @@ static int mdio_mux_mmioreg_switch_fn(int current_child, int desired_child,
struct mdio_mux_mmioreg_state *s = data;
if (current_child ^ desired_child) {
- void __iomem *p = ioremap(s->phys, 1);
- uint8_t x, y;
-
+ void __iomem *p = ioremap(s->phys, s->iosize);
if (!p)
return -ENOMEM;
- x = ioread8(p);
- y = (x & ~s->mask) | desired_child;
- if (x != y) {
- iowrite8((x & ~s->mask) | desired_child, p);
- pr_debug("%s: %02x -> %02x\n", __func__, x, y);
+ switch (s->iosize) {
+ case sizeof(uint8_t): {
+ uint8_t x, y;
+
+ x = ioread8(p);
+ y = (x & ~s->mask) | desired_child;
+ if (x != y) {
+ iowrite8((x & ~s->mask) | desired_child, p);
+ pr_debug("%s: %02x -> %02x\n", __func__, x, y);
+ }
+
+ break;
+ }
+ case sizeof(uint16_t): {
+ uint16_t x, y;
+
+ x = ioread16(p);
+ y = (x & ~s->mask) | desired_child;
+ if (x != y) {
+ iowrite16((x & ~s->mask) | desired_child, p);
+ pr_debug("%s: %04x -> %04x\n", __func__, x, y);
+ }
+
+ break;
+ }
+ case sizeof(uint32_t): {
+ uint32_t x, y;
+
+ x = ioread32(p);
+ y = (x & ~s->mask) | desired_child;
+ if (x != y) {
+ iowrite32((x & ~s->mask) | desired_child, p);
+ pr_debug("%s: %08x -> %08x\n", __func__, x, y);
+ }
+
+ break;
+ }
}
iounmap(p);
@@ -88,8 +119,11 @@ static int mdio_mux_mmioreg_probe(struct platform_device *pdev)
}
s->phys = res.start;
- if (resource_size(&res) != sizeof(uint8_t)) {
- dev_err(&pdev->dev, "only 8-bit registers are supported\n");
+ s->iosize = resource_size(&res);
+ if (s->iosize != sizeof(uint8_t) &&
+ s->iosize != sizeof(uint16_t) &&
+ s->iosize != sizeof(uint32_t)) {
+ dev_err(&pdev->dev, "only 8/16/32-bit registers are supported\n");
return -EINVAL;
}
@@ -98,8 +132,8 @@ static int mdio_mux_mmioreg_probe(struct platform_device *pdev)
dev_err(&pdev->dev, "missing or invalid mux-mask property\n");
return -ENODEV;
}
- if (be32_to_cpup(iprop) > 255) {
- dev_err(&pdev->dev, "only 8-bit registers are supported\n");
+ if (be32_to_cpup(iprop) >= BIT(s->iosize * 8)) {
+ dev_err(&pdev->dev, "only 8/16/32-bit registers are supported\n");
return -EINVAL;
}
s->mask = be32_to_cpup(iprop);
diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c
index 9c88e67..43c8fd4 100644
--- a/drivers/net/phy/mdio_device.c
+++ b/drivers/net/phy/mdio_device.c
@@ -144,7 +144,7 @@ int mdio_driver_register(struct mdio_driver *drv)
struct mdio_driver_common *mdiodrv = &drv->mdiodrv;
int retval;
- pr_info("mdio_driver_register: %s\n", mdiodrv->driver.name);
+ pr_debug("mdio_driver_register: %s\n", mdiodrv->driver.name);
mdiodrv->driver.bus = &mdio_bus_type;
mdiodrv->driver.probe = mdio_probe;
diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c
new file mode 100644
index 0000000..1ea69b7
--- /dev/null
+++ b/drivers/net/phy/meson-gxl.c
@@ -0,0 +1,81 @@
+/*
+ * Amlogic Meson GXL Internal PHY Driver
+ *
+ * Copyright (C) 2015 Amlogic, Inc. All rights reserved.
+ * Copyright (C) 2016 BayLibre, SAS. All rights reserved.
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mii.h>
+#include <linux/ethtool.h>
+#include <linux/phy.h>
+#include <linux/netdevice.h>
+
+static int meson_gxl_config_init(struct phy_device *phydev)
+{
+ /* Enable Analog and DSP register Bank access by */
+ phy_write(phydev, 0x14, 0x0000);
+ phy_write(phydev, 0x14, 0x0400);
+ phy_write(phydev, 0x14, 0x0000);
+ phy_write(phydev, 0x14, 0x0400);
+
+ /* Write Analog register 23 */
+ phy_write(phydev, 0x17, 0x8E0D);
+ phy_write(phydev, 0x14, 0x4417);
+
+ /* Enable fractional PLL */
+ phy_write(phydev, 0x17, 0x0005);
+ phy_write(phydev, 0x14, 0x5C1B);
+
+ /* Program fraction FR_PLL_DIV1 */
+ phy_write(phydev, 0x17, 0x029A);
+ phy_write(phydev, 0x14, 0x5C1D);
+
+ /* Program fraction FR_PLL_DIV1 */
+ phy_write(phydev, 0x17, 0xAAAA);
+ phy_write(phydev, 0x14, 0x5C1C);
+
+ return 0;
+}
+
+static struct phy_driver meson_gxl_phy[] = {
+ {
+ .phy_id = 0x01814400,
+ .phy_id_mask = 0xfffffff0,
+ .name = "Meson GXL Internal PHY",
+ .features = PHY_BASIC_FEATURES,
+ .flags = PHY_IS_INTERNAL,
+ .config_init = meson_gxl_config_init,
+ .config_aneg = genphy_config_aneg,
+ .aneg_done = genphy_aneg_done,
+ .read_status = genphy_read_status,
+ .suspend = genphy_suspend,
+ .resume = genphy_resume,
+ },
+};
+
+static struct mdio_device_id __maybe_unused meson_gxl_tbl[] = {
+ { 0x01814400, 0xfffffff0 },
+ { }
+};
+
+module_phy_driver(meson_gxl_phy);
+
+MODULE_DEVICE_TABLE(mdio, meson_gxl_tbl);
+
+MODULE_DESCRIPTION("Amlogic Meson GXL Internal PHY driver");
+MODULE_AUTHOR("Baoqi wang");
+MODULE_AUTHOR("Neil Armstrong <narmstrong@baylibre.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c
index 7c00e50..eb4db22 100644
--- a/drivers/net/phy/microchip.c
+++ b/drivers/net/phy/microchip.c
@@ -106,6 +106,40 @@ static int lan88xx_set_wol(struct phy_device *phydev,
return 0;
}
+static void lan88xx_set_mdix(struct phy_device *phydev)
+{
+ int buf;
+ int val;
+
+ switch (phydev->mdix) {
+ case ETH_TP_MDI:
+ val = LAN88XX_EXT_MODE_CTRL_MDI_;
+ break;
+ case ETH_TP_MDI_X:
+ val = LAN88XX_EXT_MODE_CTRL_MDI_X_;
+ break;
+ case ETH_TP_MDI_AUTO:
+ val = LAN88XX_EXT_MODE_CTRL_AUTO_MDIX_;
+ break;
+ default:
+ return;
+ }
+
+ phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, LAN88XX_EXT_PAGE_SPACE_1);
+ buf = phy_read(phydev, LAN88XX_EXT_MODE_CTRL);
+ buf &= ~LAN88XX_EXT_MODE_CTRL_MDIX_MASK_;
+ buf |= val;
+ phy_write(phydev, LAN88XX_EXT_MODE_CTRL, buf);
+ phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, LAN88XX_EXT_PAGE_SPACE_0);
+}
+
+static int lan88xx_config_aneg(struct phy_device *phydev)
+{
+ lan88xx_set_mdix(phydev);
+
+ return genphy_config_aneg(phydev);
+}
+
static struct phy_driver microchip_phy_driver[] = {
{
.phy_id = 0x0007c130,
@@ -120,7 +154,7 @@ static struct phy_driver microchip_phy_driver[] = {
.remove = lan88xx_remove,
.config_init = genphy_config_init,
- .config_aneg = genphy_config_aneg,
+ .config_aneg = lan88xx_config_aneg,
.read_status = genphy_read_status,
.ack_interrupt = lan88xx_phy_ack_interrupt,
diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c
index 113616b..92018ba 100644
--- a/drivers/net/phy/mscc.c
+++ b/drivers/net/phy/mscc.c
@@ -46,8 +46,15 @@ enum rgmii_rx_clock_delay {
#define MSCC_EXT_PAGE_ACCESS 31
#define MSCC_PHY_PAGE_STANDARD 0x0000 /* Standard registers */
+#define MSCC_PHY_PAGE_EXTENDED 0x0001 /* Extended registers */
#define MSCC_PHY_PAGE_EXTENDED_2 0x0002 /* Extended reg - page 2 */
+/* Extended Page 1 Registers */
+#define MSCC_PHY_ACTIPHY_CNTL 20
+#define DOWNSHIFT_CNTL_MASK 0x001C
+#define DOWNSHIFT_EN 0x0010
+#define DOWNSHIFT_CNTL_POS 2
+
/* Extended Page 2 Registers */
#define MSCC_PHY_RGMII_CNTL 20
#define RGMII_RX_CLK_DELAY_MASK 0x0070
@@ -65,7 +72,9 @@ enum rgmii_rx_clock_delay {
#define SECURE_ON_PASSWD_LEN_4 0x4000
/* Microsemi PHY ID's */
+#define PHY_ID_VSC8530 0x00070560
#define PHY_ID_VSC8531 0x00070570
+#define PHY_ID_VSC8540 0x00070760
#define PHY_ID_VSC8541 0x00070770
#define MSCC_VDDMAC_1500 1500
@@ -73,6 +82,8 @@ enum rgmii_rx_clock_delay {
#define MSCC_VDDMAC_2500 2500
#define MSCC_VDDMAC_3300 3300
+#define DOWNSHIFT_COUNT_MAX 5
+
struct vsc8531_private {
int rate_magic;
};
@@ -99,6 +110,66 @@ static int vsc85xx_phy_page_set(struct phy_device *phydev, u8 page)
return rc;
}
+static int vsc85xx_downshift_get(struct phy_device *phydev, u8 *count)
+{
+ int rc;
+ u16 reg_val;
+
+ mutex_lock(&phydev->lock);
+ rc = vsc85xx_phy_page_set(phydev, MSCC_PHY_PAGE_EXTENDED);
+ if (rc != 0)
+ goto out_unlock;
+
+ reg_val = phy_read(phydev, MSCC_PHY_ACTIPHY_CNTL);
+ reg_val &= DOWNSHIFT_CNTL_MASK;
+ if (!(reg_val & DOWNSHIFT_EN))
+ *count = DOWNSHIFT_DEV_DISABLE;
+ else
+ *count = ((reg_val & ~DOWNSHIFT_EN) >> DOWNSHIFT_CNTL_POS) + 2;
+ rc = vsc85xx_phy_page_set(phydev, MSCC_PHY_PAGE_STANDARD);
+
+out_unlock:
+ mutex_unlock(&phydev->lock);
+
+ return rc;
+}
+
+static int vsc85xx_downshift_set(struct phy_device *phydev, u8 count)
+{
+ int rc;
+ u16 reg_val;
+
+ if (count == DOWNSHIFT_DEV_DEFAULT_COUNT) {
+ /* Default downshift count 3 (i.e. Bit3:2 = 0b01) */
+ count = ((1 << DOWNSHIFT_CNTL_POS) | DOWNSHIFT_EN);
+ } else if (count > DOWNSHIFT_COUNT_MAX || count == 1) {
+ phydev_err(phydev, "Downshift count should be 2,3,4 or 5\n");
+ return -ERANGE;
+ } else if (count) {
+ /* Downshift count is either 2,3,4 or 5 */
+ count = (((count - 2) << DOWNSHIFT_CNTL_POS) | DOWNSHIFT_EN);
+ }
+
+ mutex_lock(&phydev->lock);
+ rc = vsc85xx_phy_page_set(phydev, MSCC_PHY_PAGE_EXTENDED);
+ if (rc != 0)
+ goto out_unlock;
+
+ reg_val = phy_read(phydev, MSCC_PHY_ACTIPHY_CNTL);
+ reg_val &= ~(DOWNSHIFT_CNTL_MASK);
+ reg_val |= count;
+ rc = phy_write(phydev, MSCC_PHY_ACTIPHY_CNTL, reg_val);
+ if (rc != 0)
+ goto out_unlock;
+
+ rc = vsc85xx_phy_page_set(phydev, MSCC_PHY_PAGE_STANDARD);
+
+out_unlock:
+ mutex_unlock(&phydev->lock);
+
+ return rc;
+}
+
static int vsc85xx_wol_set(struct phy_device *phydev,
struct ethtool_wolinfo *wol)
{
@@ -327,6 +398,29 @@ static int vsc85xx_default_config(struct phy_device *phydev)
return rc;
}
+static int vsc85xx_get_tunable(struct phy_device *phydev,
+ struct ethtool_tunable *tuna, void *data)
+{
+ switch (tuna->id) {
+ case ETHTOOL_PHY_DOWNSHIFT:
+ return vsc85xx_downshift_get(phydev, (u8 *)data);
+ default:
+ return -EINVAL;
+ }
+}
+
+static int vsc85xx_set_tunable(struct phy_device *phydev,
+ struct ethtool_tunable *tuna,
+ const void *data)
+{
+ switch (tuna->id) {
+ case ETHTOOL_PHY_DOWNSHIFT:
+ return vsc85xx_downshift_set(phydev, *(u8 *)data);
+ default:
+ return -EINVAL;
+ }
+}
+
static int vsc85xx_config_init(struct phy_device *phydev)
{
int rc;
@@ -399,6 +493,27 @@ static int vsc85xx_probe(struct phy_device *phydev)
/* Microsemi VSC85xx PHYs */
static struct phy_driver vsc85xx_driver[] = {
{
+ .phy_id = PHY_ID_VSC8530,
+ .name = "Microsemi FE VSC8530",
+ .phy_id_mask = 0xfffffff0,
+ .features = PHY_BASIC_FEATURES,
+ .flags = PHY_HAS_INTERRUPT,
+ .soft_reset = &genphy_soft_reset,
+ .config_init = &vsc85xx_config_init,
+ .config_aneg = &genphy_config_aneg,
+ .aneg_done = &genphy_aneg_done,
+ .read_status = &genphy_read_status,
+ .ack_interrupt = &vsc85xx_ack_interrupt,
+ .config_intr = &vsc85xx_config_intr,
+ .suspend = &genphy_suspend,
+ .resume = &genphy_resume,
+ .probe = &vsc85xx_probe,
+ .set_wol = &vsc85xx_wol_set,
+ .get_wol = &vsc85xx_wol_get,
+ .get_tunable = &vsc85xx_get_tunable,
+ .set_tunable = &vsc85xx_set_tunable,
+},
+{
.phy_id = PHY_ID_VSC8531,
.name = "Microsemi VSC8531",
.phy_id_mask = 0xfffffff0,
@@ -416,6 +531,29 @@ static struct phy_driver vsc85xx_driver[] = {
.probe = &vsc85xx_probe,
.set_wol = &vsc85xx_wol_set,
.get_wol = &vsc85xx_wol_get,
+ .get_tunable = &vsc85xx_get_tunable,
+ .set_tunable = &vsc85xx_set_tunable,
+},
+{
+ .phy_id = PHY_ID_VSC8540,
+ .name = "Microsemi FE VSC8540 SyncE",
+ .phy_id_mask = 0xfffffff0,
+ .features = PHY_BASIC_FEATURES,
+ .flags = PHY_HAS_INTERRUPT,
+ .soft_reset = &genphy_soft_reset,
+ .config_init = &vsc85xx_config_init,
+ .config_aneg = &genphy_config_aneg,
+ .aneg_done = &genphy_aneg_done,
+ .read_status = &genphy_read_status,
+ .ack_interrupt = &vsc85xx_ack_interrupt,
+ .config_intr = &vsc85xx_config_intr,
+ .suspend = &genphy_suspend,
+ .resume = &genphy_resume,
+ .probe = &vsc85xx_probe,
+ .set_wol = &vsc85xx_wol_set,
+ .get_wol = &vsc85xx_wol_get,
+ .get_tunable = &vsc85xx_get_tunable,
+ .set_tunable = &vsc85xx_set_tunable,
},
{
.phy_id = PHY_ID_VSC8541,
@@ -435,6 +573,8 @@ static struct phy_driver vsc85xx_driver[] = {
.probe = &vsc85xx_probe,
.set_wol = &vsc85xx_wol_set,
.get_wol = &vsc85xx_wol_get,
+ .get_tunable = &vsc85xx_get_tunable,
+ .set_tunable = &vsc85xx_set_tunable,
}
};
@@ -442,7 +582,9 @@ static struct phy_driver vsc85xx_driver[] = {
module_phy_driver(vsc85xx_driver);
static struct mdio_device_id __maybe_unused vsc85xx_tbl[] = {
+ { PHY_ID_VSC8530, 0xfffffff0, },
{ PHY_ID_VSC8531, 0xfffffff0, },
+ { PHY_ID_VSC8540, 0xfffffff0, },
{ PHY_ID_VSC8541, 0xfffffff0, },
{ }
};
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 2f94c60..73adbaa 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -143,13 +143,14 @@ static int phy_config_interrupt(struct phy_device *phydev, u32 interrupts)
* Returns > 0 on success or < 0 on error. 0 means that auto-negotiation
* is still pending.
*/
-static inline int phy_aneg_done(struct phy_device *phydev)
+int phy_aneg_done(struct phy_device *phydev)
{
if (phydev->drv->aneg_done)
return phydev->drv->aneg_done(phydev);
return genphy_aneg_done(phydev);
}
+EXPORT_SYMBOL(phy_aneg_done);
/* A structure for mapping a particular speed and duplex
* combination to a particular SUPPORTED and ADVERTISED value
@@ -1440,3 +1441,14 @@ int phy_ethtool_set_link_ksettings(struct net_device *ndev,
return phy_ethtool_ksettings_set(phydev, cmd);
}
EXPORT_SYMBOL(phy_ethtool_set_link_ksettings);
+
+int phy_ethtool_nway_reset(struct net_device *ndev)
+{
+ struct phy_device *phydev = ndev->phydev;
+
+ if (!phydev)
+ return -ENODEV;
+
+ return genphy_restart_aneg(phydev);
+}
+EXPORT_SYMBOL(phy_ethtool_nway_reset);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 49a1c98..9e8f048 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -724,6 +724,7 @@ struct phy_device *phy_connect(struct net_device *dev, const char *bus_id,
phydev = to_phy_device(d);
rc = phy_connect_direct(dev, phydev, handler, interface);
+ put_device(d);
if (rc)
return ERR_PTR(rc);
@@ -956,6 +957,7 @@ struct phy_device *phy_attach(struct net_device *dev, const char *bus_id,
phydev = to_phy_device(d);
rc = phy_attach_direct(dev, phydev, phydev->dev_flags, interface);
+ put_device(d);
if (rc)
return ERR_PTR(rc);
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 5489c0e..3d3b1f4 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -204,7 +204,7 @@ static atomic_t ppp_unit_count = ATOMIC_INIT(0);
static atomic_t channel_count = ATOMIC_INIT(0);
/* per-net private data for this module */
-static int ppp_net_id __read_mostly;
+static unsigned int ppp_net_id __read_mostly;
struct ppp_net {
/* units to ppp mapping */
struct idr units_idr;
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 4ddae81..f017c72 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -95,7 +95,7 @@ static const struct proto_ops pppoe_ops;
static const struct ppp_channel_ops pppoe_chan_ops;
/* per-net private data for this module */
-static int pppoe_net_id __read_mostly;
+static unsigned int pppoe_net_id __read_mostly;
struct pppoe_net {
/*
* we could use _single_ hash table for all
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9142db8..64e694c 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1252,8 +1252,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
return -EFAULT;
}
- err = virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun));
- if (err) {
+ if (virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun))) {
this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
kfree_skb(skb);
return -EINVAL;
@@ -1361,15 +1360,13 @@ static ssize_t tun_put_user(struct tun_struct *tun,
}
if (vnet_hdr_sz) {
- struct virtio_net_hdr gso = { 0 }; /* no info leak */
- int ret;
+ struct virtio_net_hdr gso;
if (iov_iter_count(iter) < vnet_hdr_sz)
return -EINVAL;
- ret = virtio_net_hdr_from_skb(skb, &gso,
- tun_is_little_endian(tun));
- if (ret) {
+ if (virtio_net_hdr_from_skb(skb, &gso,
+ tun_is_little_endian(tun))) {
struct skb_shared_info *sinfo = skb_shinfo(skb);
pr_err("unexpected GSO type: "
"0x%x, gso_size %d, hdr_len %d\n",
@@ -1985,7 +1982,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
int le;
int ret;
- if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == 0x89) {
+ if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == SOCK_IOC_TYPE) {
if (copy_from_user(&ifr, argp, ifreq_len))
return -EFAULT;
} else {
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c
index f79eb12..125cff5 100644
--- a/drivers/net/usb/asix_common.c
+++ b/drivers/net/usb/asix_common.c
@@ -433,13 +433,13 @@ int asix_mdio_read(struct net_device *netdev, int phy_id, int loc)
mutex_lock(&dev->phy_mutex);
do {
ret = asix_set_sw_mii(dev, 0);
- if (ret == -ENODEV)
+ if (ret == -ENODEV || ret == -ETIMEDOUT)
break;
usleep_range(1000, 1100);
ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG,
0, 0, 1, &smsr, 0);
} while (!(smsr & AX_HOST_EN) && (i++ < 30) && (ret != -ENODEV));
- if (ret == -ENODEV) {
+ if (ret == -ENODEV || ret == -ETIMEDOUT) {
mutex_unlock(&dev->phy_mutex);
return ret;
}
@@ -497,13 +497,13 @@ int asix_mdio_read_nopm(struct net_device *netdev, int phy_id, int loc)
mutex_lock(&dev->phy_mutex);
do {
ret = asix_set_sw_mii(dev, 1);
- if (ret == -ENODEV)
+ if (ret == -ENODEV || ret == -ETIMEDOUT)
break;
usleep_range(1000, 1100);
ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG,
0, 0, 1, &smsr, 1);
} while (!(smsr & AX_HOST_EN) && (i++ < 30) && (ret != -ENODEV));
- if (ret == -ENODEV) {
+ if (ret == -ENODEV || ret == -ETIMEDOUT) {
mutex_unlock(&dev->phy_mutex);
return ret;
}
diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index 49a3bc1..6308386 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -149,14 +149,6 @@ static const struct net_device_ops ax88172a_netdev_ops = {
.ndo_set_rx_mode = asix_set_multicast,
};
-static int ax88172a_nway_reset(struct net_device *net)
-{
- if (!net->phydev)
- return -ENODEV;
-
- return phy_start_aneg(net->phydev);
-}
-
static const struct ethtool_ops ax88172a_ethtool_ops = {
.get_drvinfo = asix_get_drvinfo,
.get_link = usbnet_get_link,
@@ -167,7 +159,7 @@ static const struct ethtool_ops ax88172a_ethtool_ops = {
.get_eeprom_len = asix_get_eeprom_len,
.get_eeprom = asix_get_eeprom,
.set_eeprom = asix_set_eeprom,
- .nway_reset = ax88172a_nway_reset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_link_ksettings = phy_ethtool_get_link_ksettings,
.set_link_ksettings = phy_ethtool_set_link_ksettings,
};
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index 36c70d6..a3a7db0 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1654,6 +1654,19 @@ static const struct driver_info ax88178a_info = {
.tx_fixup = ax88179_tx_fixup,
};
+static const struct driver_info cypress_GX3_info = {
+ .description = "Cypress GX3 SuperSpeed to Gigabit Ethernet Controller",
+ .bind = ax88179_bind,
+ .unbind = ax88179_unbind,
+ .status = ax88179_status,
+ .link_reset = ax88179_link_reset,
+ .reset = ax88179_reset,
+ .stop = ax88179_stop,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
+ .rx_fixup = ax88179_rx_fixup,
+ .tx_fixup = ax88179_tx_fixup,
+};
+
static const struct driver_info dlink_dub1312_info = {
.description = "D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter",
.bind = ax88179_bind,
@@ -1716,6 +1729,10 @@ static const struct usb_device_id products[] = {
USB_DEVICE(0x0b95, 0x178a),
.driver_info = (unsigned long)&ax88178a_info,
}, {
+ /* Cypress GX3 SuperSpeed to Gigabit Ethernet Bridge Controller */
+ USB_DEVICE(0x04b4, 0x3610),
+ .driver_info = (unsigned long)&cypress_GX3_info,
+}, {
/* D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter */
USB_DEVICE(0x2001, 0x4a00),
.driver_info = (unsigned long)&dlink_dub1312_info,
diff --git a/drivers/net/usb/kalmia.c b/drivers/net/usb/kalmia.c
index 5662bab..3e37724 100644
--- a/drivers/net/usb/kalmia.c
+++ b/drivers/net/usb/kalmia.c
@@ -151,7 +151,7 @@ kalmia_bind(struct usbnet *dev, struct usb_interface *intf)
status = kalmia_init_and_get_ethernet_addr(dev, ethernet_addr);
- if (status < 0) {
+ if (status) {
usb_set_intfdata(intf, NULL);
usb_driver_release_interface(driver_of(intf), intf);
return status;
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index c4e748e..0c459e9 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -30,13 +30,17 @@
#include <linux/ipv6.h>
#include <linux/mdio.h>
#include <net/ip6_checksum.h>
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <linux/irq.h>
+#include <linux/irqchip/chained_irq.h>
#include <linux/microchipphy.h>
#include "lan78xx.h"
#define DRIVER_AUTHOR "WOOJUNG HUH <woojung.huh@microchip.com>"
#define DRIVER_DESC "LAN78XX USB 3.0 Gigabit Ethernet Devices"
#define DRIVER_NAME "lan78xx"
-#define DRIVER_VERSION "1.0.4"
+#define DRIVER_VERSION "1.0.5"
#define TX_TIMEOUT_JIFFIES (5 * HZ)
#define THROTTLE_JIFFIES (HZ / 8)
@@ -89,6 +93,38 @@
/* statistic update interval (mSec) */
#define STAT_UPDATE_TIMER (1 * 1000)
+/* defines interrupts from interrupt EP */
+#define MAX_INT_EP (32)
+#define INT_EP_INTEP (31)
+#define INT_EP_OTP_WR_DONE (28)
+#define INT_EP_EEE_TX_LPI_START (26)
+#define INT_EP_EEE_TX_LPI_STOP (25)
+#define INT_EP_EEE_RX_LPI (24)
+#define INT_EP_MAC_RESET_TIMEOUT (23)
+#define INT_EP_RDFO (22)
+#define INT_EP_TXE (21)
+#define INT_EP_USB_STATUS (20)
+#define INT_EP_TX_DIS (19)
+#define INT_EP_RX_DIS (18)
+#define INT_EP_PHY (17)
+#define INT_EP_DP (16)
+#define INT_EP_MAC_ERR (15)
+#define INT_EP_TDFU (14)
+#define INT_EP_TDFO (13)
+#define INT_EP_UTX (12)
+#define INT_EP_GPIO_11 (11)
+#define INT_EP_GPIO_10 (10)
+#define INT_EP_GPIO_9 (9)
+#define INT_EP_GPIO_8 (8)
+#define INT_EP_GPIO_7 (7)
+#define INT_EP_GPIO_6 (6)
+#define INT_EP_GPIO_5 (5)
+#define INT_EP_GPIO_4 (4)
+#define INT_EP_GPIO_3 (3)
+#define INT_EP_GPIO_2 (2)
+#define INT_EP_GPIO_1 (1)
+#define INT_EP_GPIO_0 (0)
+
static const char lan78xx_gstrings[][ETH_GSTRING_LEN] = {
"RX FCS Errors",
"RX Alignment Errors",
@@ -296,6 +332,15 @@ struct statstage {
struct lan78xx_statstage64 curr_stat;
};
+struct irq_domain_data {
+ struct irq_domain *irqdomain;
+ unsigned int phyirq;
+ struct irq_chip *irqchip;
+ irq_flow_handler_t irq_handler;
+ u32 irqenable;
+ struct mutex irq_lock; /* for irq bus access */
+};
+
struct lan78xx_net {
struct net_device *net;
struct usb_device *udev;
@@ -351,6 +396,8 @@ struct lan78xx_net {
int delta;
struct statstage stats;
+
+ struct irq_domain_data domain_data;
};
/* use ethtool to change the level for any given device */
@@ -1096,11 +1143,6 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)
int ladv, radv, ret;
u32 buf;
- /* clear PHY interrupt status */
- ret = phy_read(phydev, LAN88XX_INT_STS);
- if (unlikely(ret < 0))
- return -EIO;
-
/* clear LAN78xx interrupt status */
ret = lan78xx_write_reg(dev, INT_STS, INT_STS_PHY_INT_);
if (unlikely(ret < 0))
@@ -1120,16 +1162,12 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)
if (unlikely(ret < 0))
return -EIO;
- phy_mac_interrupt(phydev, 0);
-
del_timer(&dev->stat_monitor);
} else if (phydev->link && !dev->link_on) {
dev->link_on = true;
phy_ethtool_ksettings_get(phydev, &ecmd);
- ret = phy_read(phydev, LAN88XX_INT_STS);
-
if (dev->udev->speed == USB_SPEED_SUPER) {
if (ecmd.base.speed == 1000) {
/* disable U2 */
@@ -1163,7 +1201,6 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)
ret = lan78xx_update_flowcontrol(dev, ecmd.base.duplex, ladv,
radv);
- phy_mac_interrupt(phydev, 1);
if (!timer_pending(&dev->stat_monitor)) {
dev->delta = 1;
@@ -1202,7 +1239,10 @@ static void lan78xx_status(struct lan78xx_net *dev, struct urb *urb)
if (intdata & INT_ENP_PHY_INT) {
netif_dbg(dev, link, dev->net, "PHY INTR: 0x%08x\n", intdata);
- lan78xx_defer_kevent(dev, EVENT_LINK_RESET);
+ lan78xx_defer_kevent(dev, EVENT_LINK_RESET);
+
+ if (dev->domain_data.phyirq > 0)
+ generic_handle_irq(dev->domain_data.phyirq);
} else
netdev_warn(dev->net,
"unexpected interrupt: 0x%08x\n", intdata);
@@ -1407,11 +1447,6 @@ static u32 lan78xx_get_link(struct net_device *net)
return net->phydev->link;
}
-static int lan78xx_nway_reset(struct net_device *net)
-{
- return phy_start_aneg(net->phydev);
-}
-
static void lan78xx_get_drvinfo(struct net_device *net,
struct ethtool_drvinfo *info)
{
@@ -1436,62 +1471,12 @@ static void lan78xx_set_msglevel(struct net_device *net, u32 level)
dev->msg_enable = level;
}
-static int lan78xx_get_mdix_status(struct net_device *net)
-{
- struct phy_device *phydev = net->phydev;
- int buf;
-
- phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, LAN88XX_EXT_PAGE_SPACE_1);
- buf = phy_read(phydev, LAN88XX_EXT_MODE_CTRL);
- phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, LAN88XX_EXT_PAGE_SPACE_0);
-
- return buf;
-}
-
-static void lan78xx_set_mdix_status(struct net_device *net, __u8 mdix_ctrl)
-{
- struct lan78xx_net *dev = netdev_priv(net);
- struct phy_device *phydev = net->phydev;
- int buf;
-
- if (mdix_ctrl == ETH_TP_MDI) {
- phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS,
- LAN88XX_EXT_PAGE_SPACE_1);
- buf = phy_read(phydev, LAN88XX_EXT_MODE_CTRL);
- buf &= ~LAN88XX_EXT_MODE_CTRL_MDIX_MASK_;
- phy_write(phydev, LAN88XX_EXT_MODE_CTRL,
- buf | LAN88XX_EXT_MODE_CTRL_MDI_);
- phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS,
- LAN88XX_EXT_PAGE_SPACE_0);
- } else if (mdix_ctrl == ETH_TP_MDI_X) {
- phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS,
- LAN88XX_EXT_PAGE_SPACE_1);
- buf = phy_read(phydev, LAN88XX_EXT_MODE_CTRL);
- buf &= ~LAN88XX_EXT_MODE_CTRL_MDIX_MASK_;
- phy_write(phydev, LAN88XX_EXT_MODE_CTRL,
- buf | LAN88XX_EXT_MODE_CTRL_MDI_X_);
- phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS,
- LAN88XX_EXT_PAGE_SPACE_0);
- } else if (mdix_ctrl == ETH_TP_MDI_AUTO) {
- phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS,
- LAN88XX_EXT_PAGE_SPACE_1);
- buf = phy_read(phydev, LAN88XX_EXT_MODE_CTRL);
- buf &= ~LAN88XX_EXT_MODE_CTRL_MDIX_MASK_;
- phy_write(phydev, LAN88XX_EXT_MODE_CTRL,
- buf | LAN88XX_EXT_MODE_CTRL_AUTO_MDIX_);
- phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS,
- LAN88XX_EXT_PAGE_SPACE_0);
- }
- dev->mdix_ctrl = mdix_ctrl;
-}
-
static int lan78xx_get_link_ksettings(struct net_device *net,
struct ethtool_link_ksettings *cmd)
{
struct lan78xx_net *dev = netdev_priv(net);
struct phy_device *phydev = net->phydev;
int ret;
- int buf;
ret = usb_autopm_get_interface(dev->intf);
if (ret < 0)
@@ -1499,20 +1484,6 @@ static int lan78xx_get_link_ksettings(struct net_device *net,
ret = phy_ethtool_ksettings_get(phydev, cmd);
- buf = lan78xx_get_mdix_status(net);
-
- buf &= LAN88XX_EXT_MODE_CTRL_MDIX_MASK_;
- if (buf == LAN88XX_EXT_MODE_CTRL_AUTO_MDIX_) {
- cmd->base.eth_tp_mdix = ETH_TP_MDI_AUTO;
- cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
- } else if (buf == LAN88XX_EXT_MODE_CTRL_MDI_) {
- cmd->base.eth_tp_mdix = ETH_TP_MDI;
- cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI;
- } else if (buf == LAN88XX_EXT_MODE_CTRL_MDI_X_) {
- cmd->base.eth_tp_mdix = ETH_TP_MDI_X;
- cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_X;
- }
-
usb_autopm_put_interface(dev->intf);
return ret;
@@ -1530,9 +1501,6 @@ static int lan78xx_set_link_ksettings(struct net_device *net,
if (ret < 0)
return ret;
- if (dev->mdix_ctrl != cmd->base.eth_tp_mdix_ctrl)
- lan78xx_set_mdix_status(net, cmd->base.eth_tp_mdix_ctrl);
-
/* change speed & duplex */
ret = phy_ethtool_ksettings_set(phydev, cmd);
@@ -1615,7 +1583,7 @@ static int lan78xx_set_pause(struct net_device *net,
static const struct ethtool_ops lan78xx_ethtool_ops = {
.get_link = lan78xx_get_link,
- .nway_reset = lan78xx_nway_reset,
+ .nway_reset = phy_ethtool_nway_reset,
.get_drvinfo = lan78xx_get_drvinfo,
.get_msglevel = lan78xx_get_msglevel,
.set_msglevel = lan78xx_set_msglevel,
@@ -1844,6 +1812,127 @@ static void lan78xx_link_status_change(struct net_device *net)
}
}
+static int irq_map(struct irq_domain *d, unsigned int irq,
+ irq_hw_number_t hwirq)
+{
+ struct irq_domain_data *data = d->host_data;
+
+ irq_set_chip_data(irq, data);
+ irq_set_chip_and_handler(irq, data->irqchip, data->irq_handler);
+ irq_set_noprobe(irq);
+
+ return 0;
+}
+
+static void irq_unmap(struct irq_domain *d, unsigned int irq)
+{
+ irq_set_chip_and_handler(irq, NULL, NULL);
+ irq_set_chip_data(irq, NULL);
+}
+
+static const struct irq_domain_ops chip_domain_ops = {
+ .map = irq_map,
+ .unmap = irq_unmap,
+};
+
+static void lan78xx_irq_mask(struct irq_data *irqd)
+{
+ struct irq_domain_data *data = irq_data_get_irq_chip_data(irqd);
+
+ data->irqenable &= ~BIT(irqd_to_hwirq(irqd));
+}
+
+static void lan78xx_irq_unmask(struct irq_data *irqd)
+{
+ struct irq_domain_data *data = irq_data_get_irq_chip_data(irqd);
+
+ data->irqenable |= BIT(irqd_to_hwirq(irqd));
+}
+
+static void lan78xx_irq_bus_lock(struct irq_data *irqd)
+{
+ struct irq_domain_data *data = irq_data_get_irq_chip_data(irqd);
+
+ mutex_lock(&data->irq_lock);
+}
+
+static void lan78xx_irq_bus_sync_unlock(struct irq_data *irqd)
+{
+ struct irq_domain_data *data = irq_data_get_irq_chip_data(irqd);
+ struct lan78xx_net *dev =
+ container_of(data, struct lan78xx_net, domain_data);
+ u32 buf;
+ int ret;
+
+ /* call register access here because irq_bus_lock & irq_bus_sync_unlock
+ * are only two callbacks executed in non-atomic contex.
+ */
+ ret = lan78xx_read_reg(dev, INT_EP_CTL, &buf);
+ if (buf != data->irqenable)
+ ret = lan78xx_write_reg(dev, INT_EP_CTL, data->irqenable);
+
+ mutex_unlock(&data->irq_lock);
+}
+
+static struct irq_chip lan78xx_irqchip = {
+ .name = "lan78xx-irqs",
+ .irq_mask = lan78xx_irq_mask,
+ .irq_unmask = lan78xx_irq_unmask,
+ .irq_bus_lock = lan78xx_irq_bus_lock,
+ .irq_bus_sync_unlock = lan78xx_irq_bus_sync_unlock,
+};
+
+static int lan78xx_setup_irq_domain(struct lan78xx_net *dev)
+{
+ struct device_node *of_node;
+ struct irq_domain *irqdomain;
+ unsigned int irqmap = 0;
+ u32 buf;
+ int ret = 0;
+
+ of_node = dev->udev->dev.parent->of_node;
+
+ mutex_init(&dev->domain_data.irq_lock);
+
+ lan78xx_read_reg(dev, INT_EP_CTL, &buf);
+ dev->domain_data.irqenable = buf;
+
+ dev->domain_data.irqchip = &lan78xx_irqchip;
+ dev->domain_data.irq_handler = handle_simple_irq;
+
+ irqdomain = irq_domain_add_simple(of_node, MAX_INT_EP, 0,
+ &chip_domain_ops, &dev->domain_data);
+ if (irqdomain) {
+ /* create mapping for PHY interrupt */
+ irqmap = irq_create_mapping(irqdomain, INT_EP_PHY);
+ if (!irqmap) {
+ irq_domain_remove(irqdomain);
+
+ irqdomain = NULL;
+ ret = -EINVAL;
+ }
+ } else {
+ ret = -EINVAL;
+ }
+
+ dev->domain_data.irqdomain = irqdomain;
+ dev->domain_data.phyirq = irqmap;
+
+ return ret;
+}
+
+static void lan78xx_remove_irq_domain(struct lan78xx_net *dev)
+{
+ if (dev->domain_data.phyirq > 0) {
+ irq_dispose_mapping(dev->domain_data.phyirq);
+
+ if (dev->domain_data.irqdomain)
+ irq_domain_remove(dev->domain_data.irqdomain);
+ }
+ dev->domain_data.phyirq = 0;
+ dev->domain_data.irqdomain = NULL;
+}
+
static int lan78xx_phy_init(struct lan78xx_net *dev)
{
int ret;
@@ -1856,15 +1945,15 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
return -EIO;
}
- /* Enable PHY interrupts.
- * We handle our own interrupt
- */
- ret = phy_read(phydev, LAN88XX_INT_STS);
- ret = phy_write(phydev, LAN88XX_INT_MASK,
- LAN88XX_INT_MASK_MDINTPIN_EN_ |
- LAN88XX_INT_MASK_LINK_CHANGE_);
+ /* if phyirq is not set, use polling mode in phylib */
+ if (dev->domain_data.phyirq > 0)
+ phydev->irq = dev->domain_data.phyirq;
+ else
+ phydev->irq = 0;
+ netdev_dbg(dev->net, "phydev->irq = %d\n", phydev->irq);
- phydev->irq = PHY_IGNORE_INTERRUPT;
+ /* set to AUTOMDIX */
+ phydev->mdix = ETH_TP_MDI_AUTO;
ret = phy_connect_direct(dev->net, phydev,
lan78xx_link_status_change,
@@ -1875,9 +1964,6 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
return -EIO;
}
- /* set to AUTOMDIX */
- lan78xx_set_mdix_status(dev->net, ETH_TP_MDI_AUTO);
-
/* MAC doesn't support 1000T Half */
phydev->supported &= ~SUPPORTED_1000baseT_Half;
@@ -2255,11 +2341,6 @@ static int lan78xx_reset(struct lan78xx_net *dev)
buf |= MAC_CR_AUTO_DUPLEX_ | MAC_CR_AUTO_SPEED_;
ret = lan78xx_write_reg(dev, MAC_CR, buf);
- /* enable PHY interrupts */
- ret = lan78xx_read_reg(dev, INT_EP_CTL, &buf);
- buf |= INT_ENP_PHY_INT;
- ret = lan78xx_write_reg(dev, INT_EP_CTL, buf);
-
ret = lan78xx_read_reg(dev, MAC_TX, &buf);
buf |= MAC_TX_TXEN_;
ret = lan78xx_write_reg(dev, MAC_TX, buf);
@@ -2668,6 +2749,14 @@ static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf)
dev->net->hw_features = dev->net->features;
+ ret = lan78xx_setup_irq_domain(dev);
+ if (ret < 0) {
+ netdev_warn(dev->net,
+ "lan78xx_setup_irq_domain() failed : %d", ret);
+ kfree(pdata);
+ return ret;
+ }
+
/* Init all registers */
ret = lan78xx_reset(dev);
@@ -2684,6 +2773,8 @@ static void lan78xx_unbind(struct lan78xx_net *dev, struct usb_interface *intf)
{
struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]);
+ lan78xx_remove_irq_domain(dev);
+
lan78xx_remove_mdio(dev);
if (pdata) {
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 4213c28..7dc6122 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1730,7 +1730,7 @@ static u8 r8152_rx_csum(struct r8152 *tp, struct rx_desc *rx_desc)
u8 checksum = CHECKSUM_NONE;
u32 opts2, opts3;
- if (tp->version == RTL_VER_01)
+ if (tp->version == RTL_VER_01 || tp->version == RTL_VER_02)
goto return_result;
opts2 = le32_to_cpu(rx_desc->opts2);
@@ -1745,7 +1745,7 @@ static u8 r8152_rx_csum(struct r8152 *tp, struct rx_desc *rx_desc)
checksum = CHECKSUM_NONE;
else
checksum = CHECKSUM_UNNECESSARY;
- } else if (RD_IPV6_CS) {
+ } else if (opts2 & RD_IPV6_CS) {
if ((opts2 & RD_UDP_CS) && !(opts3 & UDPF))
checksum = CHECKSUM_UNNECESSARY;
else if ((opts2 & RD_TCP_CS) && !(opts3 & TCPF))
@@ -3266,10 +3266,8 @@ static int rtl8152_open(struct net_device *netdev)
goto out;
res = usb_autopm_get_interface(tp->intf);
- if (res < 0) {
- free_all_mem(tp);
- goto out;
- }
+ if (res < 0)
+ goto out_free;
mutex_lock(&tp->control);
@@ -3285,10 +3283,9 @@ static int rtl8152_open(struct net_device *netdev)
netif_device_detach(tp->netdev);
netif_warn(tp, ifup, netdev, "intr_urb submit failed: %d\n",
res);
- free_all_mem(tp);
- } else {
- napi_enable(&tp->napi);
+ goto out_unlock;
}
+ napi_enable(&tp->napi);
mutex_unlock(&tp->control);
@@ -3297,7 +3294,13 @@ static int rtl8152_open(struct net_device *netdev)
tp->pm_notifier.notifier_call = rtl_notifier;
register_pm_notifier(&tp->pm_notifier);
#endif
+ return 0;
+out_unlock:
+ mutex_unlock(&tp->control);
+ usb_autopm_put_interface(tp->intf);
+out_free:
+ free_all_mem(tp);
out:
return res;
}
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 2cafd12..ca5239a 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2037,23 +2037,33 @@ static struct virtio_device_id id_table[] = {
{ 0 },
};
+#define VIRTNET_FEATURES \
+ VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM, \
+ VIRTIO_NET_F_MAC, \
+ VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6, \
+ VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, \
+ VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO, \
+ VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ, \
+ VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, \
+ VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \
+ VIRTIO_NET_F_CTRL_MAC_ADDR, \
+ VIRTIO_NET_F_MTU
+
static unsigned int features[] = {
- VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM,
- VIRTIO_NET_F_GSO, VIRTIO_NET_F_MAC,
- VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6,
- VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6,
- VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO,
- VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ,
- VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN,
- VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ,
- VIRTIO_NET_F_CTRL_MAC_ADDR,
+ VIRTNET_FEATURES,
+};
+
+static unsigned int features_legacy[] = {
+ VIRTNET_FEATURES,
+ VIRTIO_NET_F_GSO,
VIRTIO_F_ANY_LAYOUT,
- VIRTIO_NET_F_MTU,
};
static struct virtio_driver virtio_net_driver = {
.feature_table = features,
.feature_table_size = ARRAY_SIZE(features),
+ .feature_table_legacy = features_legacy,
+ .feature_table_size_legacy = ARRAY_SIZE(features_legacy),
.driver.name = KBUILD_MODNAME,
.driver.owner = THIS_MODULE,
.id_table = id_table,
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 0c36de1..e34b129 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -2279,6 +2279,7 @@ vmxnet3_set_mc(struct net_device *netdev)
&adapter->shared->devRead.rxFilterConf;
u8 *new_table = NULL;
dma_addr_t new_table_pa = 0;
+ bool new_table_pa_valid = false;
u32 new_mode = VMXNET3_RXM_UCAST;
if (netdev->flags & IFF_PROMISC) {
@@ -2307,13 +2308,15 @@ vmxnet3_set_mc(struct net_device *netdev)
new_table,
sz,
PCI_DMA_TODEVICE);
+ if (!dma_mapping_error(&adapter->pdev->dev,
+ new_table_pa)) {
+ new_mode |= VMXNET3_RXM_MCAST;
+ new_table_pa_valid = true;
+ rxConf->mfTablePA = cpu_to_le64(
+ new_table_pa);
+ }
}
-
- if (!dma_mapping_error(&adapter->pdev->dev,
- new_table_pa)) {
- new_mode |= VMXNET3_RXM_MCAST;
- rxConf->mfTablePA = cpu_to_le64(new_table_pa);
- } else {
+ if (!new_table_pa_valid) {
netdev_info(netdev,
"failed to copy mcast list, setting ALL_MULTI\n");
new_mode |= VMXNET3_RXM_ALL_MULTI;
@@ -2338,7 +2341,7 @@ vmxnet3_set_mc(struct net_device *netdev)
VMXNET3_CMD_UPDATE_MAC_FILTERS);
spin_unlock_irqrestore(&adapter->cmd_lock, flags);
- if (new_table_pa)
+ if (new_table_pa_valid)
dma_unmap_single(&adapter->pdev->dev, new_table_pa,
rxConf->mfTableLen, PCI_DMA_TODEVICE);
kfree(new_table);
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 85c271c..3bca246 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -272,11 +272,6 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
if (IS_ERR(rt))
goto err;
- if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
- ip_rt_put(rt);
- goto err;
- }
-
skb_dst_drop(skb);
/* if dst.dev is loopback or the VRF device again this is locally
@@ -611,6 +606,10 @@ static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
struct dst_entry *dst = NULL;
struct rtable *rth;
+ /* don't divert multicast */
+ if (ipv4_is_multicast(ip_hdr(skb)->daddr))
+ return skb;
+
rcu_read_lock();
rth = rcu_dereference(vrf->rth);
@@ -956,6 +955,7 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
if (skb->pkt_type == PACKET_LOOPBACK) {
skb->dev = vrf_dev;
skb->skb_iif = vrf_dev->ifindex;
+ IP6CB(skb)->flags |= IP6SKB_L3SLAVE;
skb->pkt_type = PACKET_HOST;
goto out;
}
@@ -996,6 +996,10 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
{
skb->dev = vrf_dev;
skb->skb_iif = vrf_dev->ifindex;
+ IPCB(skb)->flags |= IPSKB_L3SLAVE;
+
+ if (ipv4_is_multicast(ip_hdr(skb)->daddr))
+ goto out;
/* loopback traffic; do not push through packet taps again.
* Reset pkt_type for upper layers to process skb
@@ -1160,8 +1164,19 @@ static int vrf_add_fib_rules(const struct net_device *dev)
if (err < 0)
goto ipv6_err;
+#if IS_ENABLED(CONFIG_IP_MROUTE_MULTIPLE_TABLES)
+ err = vrf_fib_rule(dev, RTNL_FAMILY_IPMR, true);
+ if (err < 0)
+ goto ipmr_err;
+#endif
+
return 0;
+#if IS_ENABLED(CONFIG_IP_MROUTE_MULTIPLE_TABLES)
+ipmr_err:
+ vrf_fib_rule(dev, AF_INET6, false);
+#endif
+
ipv6_err:
vrf_fib_rule(dev, AF_INET, false);
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index c0170b6..21e92be 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -52,7 +52,7 @@ static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
-static int vxlan_net_id;
+static unsigned int vxlan_net_id;
static struct rtnl_link_ops vxlan_link_ops;
static const u8 all_zeros_mac[ETH_ALEN + 2];
@@ -583,7 +583,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk,
}
}
- pp = eth_gro_receive(head, skb);
+ pp = call_gro_receive(eth_gro_receive, head, skb);
flush = 0;
out:
@@ -943,17 +943,22 @@ static bool vxlan_snoop(struct net_device *dev,
static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev)
{
struct vxlan_dev *vxlan;
+ struct vxlan_sock *sock4;
+#if IS_ENABLED(CONFIG_IPV6)
+ struct vxlan_sock *sock6;
+#endif
unsigned short family = dev->default_dst.remote_ip.sa.sa_family;
+ sock4 = rtnl_dereference(dev->vn4_sock);
+
/* The vxlan_sock is only used by dev, leaving group has
* no effect on other vxlan devices.
*/
- if (family == AF_INET && dev->vn4_sock &&
- atomic_read(&dev->vn4_sock->refcnt) == 1)
+ if (family == AF_INET && sock4 && atomic_read(&sock4->refcnt) == 1)
return false;
#if IS_ENABLED(CONFIG_IPV6)
- if (family == AF_INET6 && dev->vn6_sock &&
- atomic_read(&dev->vn6_sock->refcnt) == 1)
+ sock6 = rtnl_dereference(dev->vn6_sock);
+ if (family == AF_INET6 && sock6 && atomic_read(&sock6->refcnt) == 1)
return false;
#endif
@@ -961,10 +966,12 @@ static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev)
if (!netif_running(vxlan->dev) || vxlan == dev)
continue;
- if (family == AF_INET && vxlan->vn4_sock != dev->vn4_sock)
+ if (family == AF_INET &&
+ rtnl_dereference(vxlan->vn4_sock) != sock4)
continue;
#if IS_ENABLED(CONFIG_IPV6)
- if (family == AF_INET6 && vxlan->vn6_sock != dev->vn6_sock)
+ if (family == AF_INET6 &&
+ rtnl_dereference(vxlan->vn6_sock) != sock6)
continue;
#endif
@@ -1005,22 +1012,25 @@ static bool __vxlan_sock_release_prep(struct vxlan_sock *vs)
static void vxlan_sock_release(struct vxlan_dev *vxlan)
{
- bool ipv4 = __vxlan_sock_release_prep(vxlan->vn4_sock);
+ struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock);
#if IS_ENABLED(CONFIG_IPV6)
- bool ipv6 = __vxlan_sock_release_prep(vxlan->vn6_sock);
+ struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock);
+
+ rcu_assign_pointer(vxlan->vn6_sock, NULL);
#endif
+ rcu_assign_pointer(vxlan->vn4_sock, NULL);
synchronize_net();
- if (ipv4) {
- udp_tunnel_sock_release(vxlan->vn4_sock->sock);
- kfree(vxlan->vn4_sock);
+ if (__vxlan_sock_release_prep(sock4)) {
+ udp_tunnel_sock_release(sock4->sock);
+ kfree(sock4);
}
#if IS_ENABLED(CONFIG_IPV6)
- if (ipv6) {
- udp_tunnel_sock_release(vxlan->vn6_sock->sock);
- kfree(vxlan->vn6_sock);
+ if (__vxlan_sock_release_prep(sock6)) {
+ udp_tunnel_sock_release(sock6->sock);
+ kfree(sock6);
}
#endif
}
@@ -1036,18 +1046,21 @@ static int vxlan_igmp_join(struct vxlan_dev *vxlan)
int ret = -EINVAL;
if (ip->sa.sa_family == AF_INET) {
+ struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock);
struct ip_mreqn mreq = {
.imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr,
.imr_ifindex = ifindex,
};
- sk = vxlan->vn4_sock->sock->sk;
+ sk = sock4->sock->sk;
lock_sock(sk);
ret = ip_mc_join_group(sk, &mreq);
release_sock(sk);
#if IS_ENABLED(CONFIG_IPV6)
} else {
- sk = vxlan->vn6_sock->sock->sk;
+ struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock);
+
+ sk = sock6->sock->sk;
lock_sock(sk);
ret = ipv6_stub->ipv6_sock_mc_join(sk, ifindex,
&ip->sin6.sin6_addr);
@@ -1067,18 +1080,21 @@ static int vxlan_igmp_leave(struct vxlan_dev *vxlan)
int ret = -EINVAL;
if (ip->sa.sa_family == AF_INET) {
+ struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock);
struct ip_mreqn mreq = {
.imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr,
.imr_ifindex = ifindex,
};
- sk = vxlan->vn4_sock->sock->sk;
+ sk = sock4->sock->sk;
lock_sock(sk);
ret = ip_mc_leave_group(sk, &mreq);
release_sock(sk);
#if IS_ENABLED(CONFIG_IPV6)
} else {
- sk = vxlan->vn6_sock->sock->sk;
+ struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock);
+
+ sk = sock6->sock->sk;
lock_sock(sk);
ret = ipv6_stub->ipv6_sock_mc_drop(sk, ifindex,
&ip->sin6.sin6_addr);
@@ -1734,21 +1750,16 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst,
}
min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len
- + VXLAN_HLEN + iphdr_len
- + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
+ + VXLAN_HLEN + iphdr_len;
/* Need space for new headers (invalidates iph ptr) */
err = skb_cow_head(skb, min_headroom);
if (unlikely(err))
- goto out_free;
-
- skb = vlan_hwaccel_push_inside(skb);
- if (WARN_ON(!skb))
- return -ENOMEM;
+ return err;
err = iptunnel_handle_offloads(skb, type);
if (err)
- goto out_free;
+ return err;
vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
vxh->vx_flags = VXLAN_HF_VNI;
@@ -1772,19 +1783,16 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst,
if (vxflags & VXLAN_F_GPE) {
err = vxlan_build_gpe_hdr(vxh, vxflags, skb->protocol);
if (err < 0)
- goto out_free;
+ return err;
inner_protocol = skb->protocol;
}
skb_set_inner_protocol(skb, inner_protocol);
return 0;
-
-out_free:
- kfree_skb(skb);
- return err;
}
-static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan,
+static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, struct net_device *dev,
+ struct vxlan_sock *sock4,
struct sk_buff *skb, int oif, u8 tos,
__be32 daddr, __be32 *saddr,
struct dst_cache *dst_cache,
@@ -1794,6 +1802,9 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan,
struct rtable *rt = NULL;
struct flowi4 fl4;
+ if (!sock4)
+ return ERR_PTR(-EIO);
+
if (tos && !info)
use_cache = false;
if (use_cache) {
@@ -1811,16 +1822,27 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan,
fl4.saddr = *saddr;
rt = ip_route_output_key(vxlan->net, &fl4);
- if (!IS_ERR(rt)) {
+ if (likely(!IS_ERR(rt))) {
+ if (rt->dst.dev == dev) {
+ netdev_dbg(dev, "circular route to %pI4\n", &daddr);
+ ip_rt_put(rt);
+ return ERR_PTR(-ELOOP);
+ }
+
*saddr = fl4.saddr;
if (use_cache)
dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr);
+ } else {
+ netdev_dbg(dev, "no route to %pI4\n", &daddr);
+ return ERR_PTR(-ENETUNREACH);
}
return rt;
}
#if IS_ENABLED(CONFIG_IPV6)
static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
+ struct net_device *dev,
+ struct vxlan_sock *sock6,
struct sk_buff *skb, int oif, u8 tos,
__be32 label,
const struct in6_addr *daddr,
@@ -1833,6 +1855,9 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
struct flowi6 fl6;
int err;
+ if (!sock6)
+ return ERR_PTR(-EIO);
+
if (tos && !info)
use_cache = false;
if (use_cache) {
@@ -1850,10 +1875,18 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
fl6.flowi6_proto = IPPROTO_UDP;
err = ipv6_stub->ipv6_dst_lookup(vxlan->net,
- vxlan->vn6_sock->sock->sk,
+ sock6->sock->sk,
&ndst, &fl6);
- if (err < 0)
- return ERR_PTR(err);
+ if (unlikely(err < 0)) {
+ netdev_dbg(dev, "no route to %pI6\n", daddr);
+ return ERR_PTR(-ENETUNREACH);
+ }
+
+ if (unlikely(ndst->dev == dev)) {
+ netdev_dbg(dev, "circular route to %pI6\n", daddr);
+ dst_release(ndst);
+ return ERR_PTR(-ELOOP);
+ }
*saddr = fl6.saddr;
if (use_cache)
@@ -1907,23 +1940,55 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
}
}
+static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev,
+ struct vxlan_dev *vxlan, union vxlan_addr *daddr,
+ __be32 dst_port, __be32 vni, struct dst_entry *dst,
+ u32 rt_flags)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+ /* IPv6 rt-flags are checked against RTF_LOCAL, but the value of
+ * RTF_LOCAL is equal to RTCF_LOCAL. So to keep code simple
+ * we can use RTCF_LOCAL which works for ipv4 and ipv6 route entry.
+ */
+ BUILD_BUG_ON(RTCF_LOCAL != RTF_LOCAL);
+#endif
+ /* Bypass encapsulation if the destination is local */
+ if (rt_flags & RTCF_LOCAL &&
+ !(rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
+ struct vxlan_dev *dst_vxlan;
+
+ dst_release(dst);
+ dst_vxlan = vxlan_find_vni(vxlan->net, vni,
+ daddr->sa.sa_family, dst_port,
+ vxlan->flags);
+ if (!dst_vxlan) {
+ dev->stats.tx_errors++;
+ kfree_skb(skb);
+
+ return -ENOENT;
+ }
+ vxlan_encap_bypass(skb, vxlan, dst_vxlan);
+ return 1;
+ }
+
+ return 0;
+}
+
static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
struct vxlan_rdst *rdst, bool did_rsc)
{
struct dst_cache *dst_cache;
struct ip_tunnel_info *info;
struct vxlan_dev *vxlan = netdev_priv(dev);
- struct sock *sk;
- struct rtable *rt = NULL;
- const struct iphdr *old_iph;
+ const struct iphdr *old_iph = ip_hdr(skb);
union vxlan_addr *dst;
union vxlan_addr remote_ip, local_ip;
union vxlan_addr *src;
struct vxlan_metadata _md;
struct vxlan_metadata *md = &_md;
__be16 src_port = 0, dst_port;
+ struct dst_entry *ndst = NULL;
__be32 vni, label;
- __be16 df = 0;
__u8 tos, ttl;
int err;
u32 flags = vxlan->flags;
@@ -1933,19 +1998,40 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
info = skb_tunnel_info(skb);
if (rdst) {
+ dst = &rdst->remote_ip;
+ if (vxlan_addr_any(dst)) {
+ if (did_rsc) {
+ /* short-circuited back to local bridge */
+ vxlan_encap_bypass(skb, vxlan, vxlan);
+ return;
+ }
+ goto drop;
+ }
+
dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port;
vni = rdst->remote_vni;
- dst = &rdst->remote_ip;
src = &vxlan->cfg.saddr;
dst_cache = &rdst->dst_cache;
+ md->gbp = skb->mark;
+ ttl = vxlan->cfg.ttl;
+ if (!ttl && vxlan_addr_multicast(dst))
+ ttl = 1;
+
+ tos = vxlan->cfg.tos;
+ if (tos == 1)
+ tos = ip_tunnel_get_dsfield(old_iph, skb);
+
+ if (dst->sa.sa_family == AF_INET)
+ udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX);
+ else
+ udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
+ label = vxlan->cfg.label;
} else {
if (!info) {
WARN_ONCE(1, "%s: Missing encapsulation instructions\n",
dev->name);
goto drop;
}
- dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port;
- vni = tunnel_id_to_key32(info->key.tun_id);
remote_ip.sa.sa_family = ip_tunnel_info_af(info);
if (remote_ip.sa.sa_family == AF_INET) {
remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst;
@@ -1955,179 +2041,111 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
local_ip.sin6.sin6_addr = info->key.u.ipv6.src;
}
dst = &remote_ip;
+ dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port;
+ vni = tunnel_id_to_key32(info->key.tun_id);
src = &local_ip;
dst_cache = &info->dst_cache;
- }
-
- if (vxlan_addr_any(dst)) {
- if (did_rsc) {
- /* short-circuited back to local bridge */
- vxlan_encap_bypass(skb, vxlan, vxlan);
- return;
- }
- goto drop;
- }
-
- old_iph = ip_hdr(skb);
-
- ttl = vxlan->cfg.ttl;
- if (!ttl && vxlan_addr_multicast(dst))
- ttl = 1;
-
- tos = vxlan->cfg.tos;
- if (tos == 1)
- tos = ip_tunnel_get_dsfield(old_iph, skb);
-
- label = vxlan->cfg.label;
- src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min,
- vxlan->cfg.port_max, true);
-
- if (info) {
+ if (info->options_len)
+ md = ip_tunnel_info_opts(info);
ttl = info->key.ttl;
tos = info->key.tos;
label = info->key.label;
udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM);
-
- if (info->options_len)
- md = ip_tunnel_info_opts(info);
- } else {
- md->gbp = skb->mark;
}
+ src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min,
+ vxlan->cfg.port_max, true);
if (dst->sa.sa_family == AF_INET) {
- if (!vxlan->vn4_sock)
- goto drop;
- sk = vxlan->vn4_sock->sock->sk;
+ struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
+ struct rtable *rt;
+ __be16 df = 0;
- rt = vxlan_get_route(vxlan, skb,
+ rt = vxlan_get_route(vxlan, dev, sock4, skb,
rdst ? rdst->remote_ifindex : 0, tos,
dst->sin.sin_addr.s_addr,
&src->sin.sin_addr.s_addr,
dst_cache, info);
if (IS_ERR(rt)) {
- netdev_dbg(dev, "no route to %pI4\n",
- &dst->sin.sin_addr.s_addr);
- dev->stats.tx_carrier_errors++;
+ err = PTR_ERR(rt);
goto tx_error;
}
- if (rt->dst.dev == dev) {
- netdev_dbg(dev, "circular route to %pI4\n",
- &dst->sin.sin_addr.s_addr);
- dev->stats.collisions++;
- goto rt_tx_error;
- }
-
/* Bypass encapsulation if the destination is local */
- if (!info && rt->rt_flags & RTCF_LOCAL &&
- !(rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
- struct vxlan_dev *dst_vxlan;
-
- ip_rt_put(rt);
- dst_vxlan = vxlan_find_vni(vxlan->net, vni,
- dst->sa.sa_family, dst_port,
- vxlan->flags);
- if (!dst_vxlan)
- goto tx_error;
- vxlan_encap_bypass(skb, vxlan, dst_vxlan);
- return;
+ if (!info) {
+ err = encap_bypass_if_local(skb, dev, vxlan, dst,
+ dst_port, vni, &rt->dst,
+ rt->rt_flags);
+ if (err)
+ return;
+ } else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) {
+ df = htons(IP_DF);
}
- if (!info)
- udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX);
- else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)
- df = htons(IP_DF);
-
+ ndst = &rt->dst;
tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
- err = vxlan_build_skb(skb, &rt->dst, sizeof(struct iphdr),
+ err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr),
vni, md, flags, udp_sum);
if (err < 0)
- goto xmit_tx_error;
+ goto tx_error;
- udp_tunnel_xmit_skb(rt, sk, skb, src->sin.sin_addr.s_addr,
+ udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, src->sin.sin_addr.s_addr,
dst->sin.sin_addr.s_addr, tos, ttl, df,
src_port, dst_port, xnet, !udp_sum);
#if IS_ENABLED(CONFIG_IPV6)
} else {
- struct dst_entry *ndst;
- u32 rt6i_flags;
+ struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);
- if (!vxlan->vn6_sock)
- goto drop;
- sk = vxlan->vn6_sock->sock->sk;
-
- ndst = vxlan6_get_route(vxlan, skb,
+ ndst = vxlan6_get_route(vxlan, dev, sock6, skb,
rdst ? rdst->remote_ifindex : 0, tos,
label, &dst->sin6.sin6_addr,
&src->sin6.sin6_addr,
dst_cache, info);
if (IS_ERR(ndst)) {
- netdev_dbg(dev, "no route to %pI6\n",
- &dst->sin6.sin6_addr);
- dev->stats.tx_carrier_errors++;
+ err = PTR_ERR(ndst);
+ ndst = NULL;
goto tx_error;
}
- if (ndst->dev == dev) {
- netdev_dbg(dev, "circular route to %pI6\n",
- &dst->sin6.sin6_addr);
- dst_release(ndst);
- dev->stats.collisions++;
- goto tx_error;
+ if (!info) {
+ u32 rt6i_flags = ((struct rt6_info *)ndst)->rt6i_flags;
+
+ err = encap_bypass_if_local(skb, dev, vxlan, dst,
+ dst_port, vni, ndst,
+ rt6i_flags);
+ if (err)
+ return;
}
- /* Bypass encapsulation if the destination is local */
- rt6i_flags = ((struct rt6_info *)ndst)->rt6i_flags;
- if (!info && rt6i_flags & RTF_LOCAL &&
- !(rt6i_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
- struct vxlan_dev *dst_vxlan;
-
- dst_release(ndst);
- dst_vxlan = vxlan_find_vni(vxlan->net, vni,
- dst->sa.sa_family, dst_port,
- vxlan->flags);
- if (!dst_vxlan)
- goto tx_error;
- vxlan_encap_bypass(skb, vxlan, dst_vxlan);
- return;
- }
-
- if (!info)
- udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
-
tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
ttl = ttl ? : ip6_dst_hoplimit(ndst);
skb_scrub_packet(skb, xnet);
err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr),
vni, md, flags, udp_sum);
- if (err < 0) {
- dst_release(ndst);
- dev->stats.tx_errors++;
- return;
- }
- udp_tunnel6_xmit_skb(ndst, sk, skb, dev,
+ if (err < 0)
+ goto tx_error;
+
+ udp_tunnel6_xmit_skb(ndst, sock6->sock->sk, skb, dev,
&src->sin6.sin6_addr,
&dst->sin6.sin6_addr, tos, ttl,
label, src_port, dst_port, !udp_sum);
#endif
}
-
return;
drop:
dev->stats.tx_dropped++;
- goto tx_free;
-
-xmit_tx_error:
- /* skb is already freed. */
- skb = NULL;
-rt_tx_error:
- ip_rt_put(rt);
-tx_error:
- dev->stats.tx_errors++;
-tx_free:
dev_kfree_skb(skb);
+ return;
+
+tx_error:
+ if (err == -ELOOP)
+ dev->stats.collisions++;
+ else if (err == -ENETUNREACH)
+ dev->stats.tx_carrier_errors++;
+ dst_release(ndst);
+ dev->stats.tx_errors++;
+ kfree_skb(skb);
}
/* Transmit local packets over Vxlan
@@ -2403,11 +2421,10 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
dport = info->key.tp_dst ? : vxlan->cfg.dst_port;
if (ip_tunnel_info_af(info) == AF_INET) {
+ struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
struct rtable *rt;
- if (!vxlan->vn4_sock)
- return -EINVAL;
- rt = vxlan_get_route(vxlan, skb, 0, info->key.tos,
+ rt = vxlan_get_route(vxlan, dev, sock4, skb, 0, info->key.tos,
info->key.u.ipv4.dst,
&info->key.u.ipv4.src, NULL, info);
if (IS_ERR(rt))
@@ -2415,11 +2432,10 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
ip_rt_put(rt);
} else {
#if IS_ENABLED(CONFIG_IPV6)
+ struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);
struct dst_entry *ndst;
- if (!vxlan->vn6_sock)
- return -EINVAL;
- ndst = vxlan6_get_route(vxlan, skb, 0, info->key.tos,
+ ndst = vxlan6_get_route(vxlan, dev, sock6, skb, 0, info->key.tos,
info->key.label, &info->key.u.ipv6.dst,
&info->key.u.ipv6.src, NULL, info);
if (IS_ERR(ndst))
@@ -2507,10 +2523,8 @@ static void vxlan_setup(struct net_device *dev)
dev->features |= NETIF_F_GSO_SOFTWARE;
dev->vlan_features = dev->features;
- dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
dev->hw_features |= NETIF_F_GSO_SOFTWARE;
- dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
netif_keep_dst(dev);
dev->priv_flags |= IFF_NO_QUEUE;
@@ -2728,10 +2742,10 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6)
return PTR_ERR(vs);
#if IS_ENABLED(CONFIG_IPV6)
if (ipv6)
- vxlan->vn6_sock = vs;
+ rcu_assign_pointer(vxlan->vn6_sock, vs);
else
#endif
- vxlan->vn4_sock = vs;
+ rcu_assign_pointer(vxlan->vn4_sock, vs);
vxlan_vs_add_dev(vs, vxlan);
return 0;
}
@@ -2742,9 +2756,9 @@ static int vxlan_sock_add(struct vxlan_dev *vxlan)
bool metadata = vxlan->flags & VXLAN_F_COLLECT_METADATA;
int ret = 0;
- vxlan->vn4_sock = NULL;
+ RCU_INIT_POINTER(vxlan->vn4_sock, NULL);
#if IS_ENABLED(CONFIG_IPV6)
- vxlan->vn6_sock = NULL;
+ RCU_INIT_POINTER(vxlan->vn6_sock, NULL);
if (ipv6 || metadata)
ret = __vxlan_sock_add(vxlan, true);
#endif
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index 33ab334..4e9fe75 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -294,7 +294,7 @@
config SLIC_DS26522
tristate "Slic Maxim ds26522 card support"
depends on SPI
- depends on FSL_SOC || ARCH_MXC || ARCH_LAYERSCAPE
+ depends on FSL_SOC || ARCH_MXC || ARCH_LAYERSCAPE || COMPILE_TEST
help
This module initializes and configures the slic maxim card
in T1 or E1 mode.
diff --git a/drivers/net/wan/slic_ds26522.c b/drivers/net/wan/slic_ds26522.c
index d06a887..b776a0a 100644
--- a/drivers/net/wan/slic_ds26522.c
+++ b/drivers/net/wan/slic_ds26522.c
@@ -223,12 +223,19 @@ static int slic_ds26522_probe(struct spi_device *spi)
return ret;
}
+static const struct spi_device_id slic_ds26522_id[] = {
+ { .name = "ds26522" },
+ { /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(spi, slic_ds26522_id);
+
static const struct of_device_id slic_ds26522_match[] = {
{
.compatible = "maxim,ds26522",
},
{},
};
+MODULE_DEVICE_TABLE(of, slic_ds26522_match);
static struct spi_driver slic_ds26522_driver = {
.driver = {
@@ -239,6 +246,7 @@ static struct spi_driver slic_ds26522_driver = {
},
.probe = slic_ds26522_probe,
.remove = slic_ds26522_remove,
+ .id_table = slic_ds26522_id,
};
static int __init slic_ds26522_init(void)
diff --git a/drivers/net/wireless/Kconfig b/drivers/net/wireless/Kconfig
index 8c8edaf..8f5a3f4 100644
--- a/drivers/net/wireless/Kconfig
+++ b/drivers/net/wireless/Kconfig
@@ -17,6 +17,19 @@
if WLAN
+config WIRELESS_WDS
+ bool "mac80211-based legacy WDS support" if EXPERT
+ help
+ This option enables the deprecated WDS support, the newer
+ mac80211-based 4-addr AP/client support supersedes it with
+ a much better feature set (HT, VHT, ...)
+
+ We plan to remove this option and code, so if you find
+ that you have to enable it, please let us know on the
+ linux-wireless@vger.kernel.org mailing list, so we can
+ help you migrate to 4-addr AP/client (or, if it's really
+ necessary, give up on our plan of removing it).
+
source "drivers/net/wireless/admtek/Kconfig"
source "drivers/net/wireless/ath/Kconfig"
source "drivers/net/wireless/atmel/Kconfig"
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index dda49af..521f1c5 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -450,6 +450,7 @@ struct ath10k_debug {
u32 pktlog_filter;
u32 reg_addr;
u32 nf_cal_period;
+ void *cal_data;
struct ath10k_fw_crash_data *fw_crash_data;
};
diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index 832da6e..82a4c67 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -30,6 +30,8 @@
/* ms */
#define ATH10K_DEBUG_HTT_STATS_INTERVAL 1000
+#define ATH10K_DEBUG_CAL_DATA_LEN 12064
+
#define ATH10K_FW_CRASH_DUMP_VERSION 1
/**
@@ -1451,56 +1453,51 @@ static const struct file_operations fops_fw_dbglog = {
.llseek = default_llseek,
};
-static int ath10k_debug_cal_data_open(struct inode *inode, struct file *file)
+static int ath10k_debug_cal_data_fetch(struct ath10k *ar)
{
- struct ath10k *ar = inode->i_private;
- void *buf;
u32 hi_addr;
__le32 addr;
int ret;
- mutex_lock(&ar->conf_mutex);
+ lockdep_assert_held(&ar->conf_mutex);
- if (ar->state != ATH10K_STATE_ON &&
- ar->state != ATH10K_STATE_UTF) {
- ret = -ENETDOWN;
- goto err;
- }
-
- buf = vmalloc(ar->hw_params.cal_data_len);
- if (!buf) {
- ret = -ENOMEM;
- goto err;
- }
+ if (WARN_ON(ar->hw_params.cal_data_len > ATH10K_DEBUG_CAL_DATA_LEN))
+ return -EINVAL;
hi_addr = host_interest_item_address(HI_ITEM(hi_board_data));
ret = ath10k_hif_diag_read(ar, hi_addr, &addr, sizeof(addr));
if (ret) {
- ath10k_warn(ar, "failed to read hi_board_data address: %d\n", ret);
- goto err_vfree;
+ ath10k_warn(ar, "failed to read hi_board_data address: %d\n",
+ ret);
+ return ret;
}
- ret = ath10k_hif_diag_read(ar, le32_to_cpu(addr), buf,
+ ret = ath10k_hif_diag_read(ar, le32_to_cpu(addr), ar->debug.cal_data,
ar->hw_params.cal_data_len);
if (ret) {
ath10k_warn(ar, "failed to read calibration data: %d\n", ret);
- goto err_vfree;
+ return ret;
}
- file->private_data = buf;
+ return 0;
+}
+static int ath10k_debug_cal_data_open(struct inode *inode, struct file *file)
+{
+ struct ath10k *ar = inode->i_private;
+
+ mutex_lock(&ar->conf_mutex);
+
+ if (ar->state == ATH10K_STATE_ON ||
+ ar->state == ATH10K_STATE_UTF) {
+ ath10k_debug_cal_data_fetch(ar);
+ }
+
+ file->private_data = ar;
mutex_unlock(&ar->conf_mutex);
return 0;
-
-err_vfree:
- vfree(buf);
-
-err:
- mutex_unlock(&ar->conf_mutex);
-
- return ret;
}
static ssize_t ath10k_debug_cal_data_read(struct file *file,
@@ -1508,18 +1505,16 @@ static ssize_t ath10k_debug_cal_data_read(struct file *file,
size_t count, loff_t *ppos)
{
struct ath10k *ar = file->private_data;
- void *buf = file->private_data;
- return simple_read_from_buffer(user_buf, count, ppos,
- buf, ar->hw_params.cal_data_len);
-}
+ mutex_lock(&ar->conf_mutex);
-static int ath10k_debug_cal_data_release(struct inode *inode,
- struct file *file)
-{
- vfree(file->private_data);
+ count = simple_read_from_buffer(user_buf, count, ppos,
+ ar->debug.cal_data,
+ ar->hw_params.cal_data_len);
- return 0;
+ mutex_unlock(&ar->conf_mutex);
+
+ return count;
}
static ssize_t ath10k_write_ani_enable(struct file *file,
@@ -1580,7 +1575,6 @@ static const struct file_operations fops_ani_enable = {
static const struct file_operations fops_cal_data = {
.open = ath10k_debug_cal_data_open,
.read = ath10k_debug_cal_data_read,
- .release = ath10k_debug_cal_data_release,
.owner = THIS_MODULE,
.llseek = default_llseek,
};
@@ -1932,6 +1926,8 @@ void ath10k_debug_stop(struct ath10k *ar)
{
lockdep_assert_held(&ar->conf_mutex);
+ ath10k_debug_cal_data_fetch(ar);
+
/* Must not use _sync to avoid deadlock, we do that in
* ath10k_debug_destroy(). The check for htt_stats_mask is to avoid
* warning from del_timer(). */
@@ -2344,6 +2340,10 @@ int ath10k_debug_create(struct ath10k *ar)
if (!ar->debug.fw_crash_data)
return -ENOMEM;
+ ar->debug.cal_data = vzalloc(ATH10K_DEBUG_CAL_DATA_LEN);
+ if (!ar->debug.cal_data)
+ return -ENOMEM;
+
INIT_LIST_HEAD(&ar->debug.fw_stats.pdevs);
INIT_LIST_HEAD(&ar->debug.fw_stats.vdevs);
INIT_LIST_HEAD(&ar->debug.fw_stats.peers);
@@ -2357,6 +2357,9 @@ void ath10k_debug_destroy(struct ath10k *ar)
vfree(ar->debug.fw_crash_data);
ar->debug.fw_crash_data = NULL;
+ vfree(ar->debug.cal_data);
+ ar->debug.cal_data = NULL;
+
ath10k_debug_fw_stats_reset(ar);
kfree(ar->debug.tpc_stats);
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 76297d6..e322b6d 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -7881,6 +7881,7 @@ int ath10k_mac_register(struct ath10k *ar)
ieee80211_hw_set(ar->hw, WANT_MONITOR_VIF);
ieee80211_hw_set(ar->hw, CHANCTX_STA_CSA);
ieee80211_hw_set(ar->hw, QUEUE_CONTROL);
+ ieee80211_hw_set(ar->hw, SUPPORTS_TX_FRAG);
if (!test_bit(ATH10K_FLAG_RAW_MODE, &ar->dev_flags))
ieee80211_hw_set(ar->hw, SW_CRYPTO_CONTROL);
diff --git a/drivers/net/wireless/ath/ath6kl/sdio.c b/drivers/net/wireless/ath/ath6kl/sdio.c
index eab0ab9..76eb336 100644
--- a/drivers/net/wireless/ath/ath6kl/sdio.c
+++ b/drivers/net/wireless/ath/ath6kl/sdio.c
@@ -1401,6 +1401,7 @@ static const struct sdio_device_id ath6kl_sdio_devices[] = {
{SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x0))},
{SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x1))},
{SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x2))},
+ {SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x18))},
{},
};
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_calib.c b/drivers/net/wireless/ath/ath9k/ar9003_calib.c
index b6f064a..7e27a06 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_calib.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_calib.c
@@ -33,7 +33,6 @@ struct coeff {
enum ar9003_cal_types {
IQ_MISMATCH_CAL = BIT(0),
- TEMP_COMP_CAL = BIT(1),
};
static void ar9003_hw_setup_calibration(struct ath_hw *ah,
@@ -59,12 +58,6 @@ static void ar9003_hw_setup_calibration(struct ath_hw *ah,
/* Kick-off cal */
REG_SET_BIT(ah, AR_PHY_TIMING4, AR_PHY_TIMING4_DO_CAL);
break;
- case TEMP_COMP_CAL:
- ath_dbg(common, CALIBRATE,
- "starting Temperature Compensation Calibration\n");
- REG_SET_BIT(ah, AR_CH0_THERM, AR_CH0_THERM_LOCAL);
- REG_SET_BIT(ah, AR_CH0_THERM, AR_CH0_THERM_START);
- break;
default:
ath_err(common, "Invalid calibration type\n");
break;
@@ -93,8 +86,7 @@ static bool ar9003_hw_per_calibration(struct ath_hw *ah,
/*
* Accumulate cal measures for active chains
*/
- if (cur_caldata->calCollect)
- cur_caldata->calCollect(ah);
+ cur_caldata->calCollect(ah);
ah->cal_samples++;
if (ah->cal_samples >= cur_caldata->calNumSamples) {
@@ -107,8 +99,7 @@ static bool ar9003_hw_per_calibration(struct ath_hw *ah,
/*
* Process accumulated data
*/
- if (cur_caldata->calPostProc)
- cur_caldata->calPostProc(ah, numChains);
+ cur_caldata->calPostProc(ah, numChains);
/* Calibration has finished. */
caldata->CalValid |= cur_caldata->calType;
@@ -323,16 +314,9 @@ static const struct ath9k_percal_data iq_cal_single_sample = {
ar9003_hw_iqcalibrate
};
-static const struct ath9k_percal_data temp_cal_single_sample = {
- TEMP_COMP_CAL,
- MIN_CAL_SAMPLES,
- PER_MAX_LOG_COUNT,
-};
-
static void ar9003_hw_init_cal_settings(struct ath_hw *ah)
{
ah->iq_caldata.calData = &iq_cal_single_sample;
- ah->temp_caldata.calData = &temp_cal_single_sample;
if (AR_SREV_9300_20_OR_LATER(ah)) {
ah->enabled_cals |= TX_IQ_CAL;
@@ -340,7 +324,7 @@ static void ar9003_hw_init_cal_settings(struct ath_hw *ah)
ah->enabled_cals |= TX_IQ_ON_AGC_CAL;
}
- ah->supp_cals = IQ_MISMATCH_CAL | TEMP_COMP_CAL;
+ ah->supp_cals = IQ_MISMATCH_CAL;
}
#define OFF_UPPER_LT 24
@@ -1399,9 +1383,6 @@ static void ar9003_hw_init_cal_common(struct ath_hw *ah)
INIT_CAL(&ah->iq_caldata);
INSERT_CAL(ah, &ah->iq_caldata);
- INIT_CAL(&ah->temp_caldata);
- INSERT_CAL(ah, &ah->temp_caldata);
-
/* Initialize current pointer to first element in list */
ah->cal_list_curr = ah->cal_list;
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index 2a5d3ad..9cbca12 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -830,7 +830,6 @@ struct ath_hw {
/* Calibration */
u32 supp_cals;
struct ath9k_cal_list iq_caldata;
- struct ath9k_cal_list temp_caldata;
struct ath9k_cal_list adcgain_caldata;
struct ath9k_cal_list adcdc_caldata;
struct ath9k_cal_list *cal_list;
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index cfa3fe8..368d9b3 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -734,9 +734,11 @@ static const struct ieee80211_iface_limit if_limits[] = {
BIT(NL80211_IFTYPE_P2P_GO) },
};
+#ifdef CONFIG_WIRELESS_WDS
static const struct ieee80211_iface_limit wds_limits[] = {
{ .max = 2048, .types = BIT(NL80211_IFTYPE_WDS) },
};
+#endif
#ifdef CONFIG_ATH9K_CHANNEL_CONTEXT
@@ -774,6 +776,7 @@ static const struct ieee80211_iface_combination if_comb[] = {
BIT(NL80211_CHAN_WIDTH_40),
#endif
},
+#ifdef CONFIG_WIRELESS_WDS
{
.limits = wds_limits,
.n_limits = ARRAY_SIZE(wds_limits),
@@ -781,6 +784,7 @@ static const struct ieee80211_iface_combination if_comb[] = {
.num_different_channels = 1,
.beacon_int_infra_match = true,
},
+#endif
};
#ifdef CONFIG_ATH9K_CHANNEL_CONTEXT
@@ -851,7 +855,9 @@ static void ath9k_set_hw_capab(struct ath_softc *sc, struct ieee80211_hw *hw)
BIT(NL80211_IFTYPE_STATION) |
BIT(NL80211_IFTYPE_ADHOC) |
BIT(NL80211_IFTYPE_MESH_POINT) |
+#ifdef CONFIG_WIRELESS_WDS
BIT(NL80211_IFTYPE_WDS) |
+#endif
BIT(NL80211_IFTYPE_OCB);
if (ath9k_is_chanctx_enabled())
diff --git a/drivers/net/wireless/broadcom/b43/main.c b/drivers/net/wireless/broadcom/b43/main.c
index 6e5d909..52f3541 100644
--- a/drivers/net/wireless/broadcom/b43/main.c
+++ b/drivers/net/wireless/broadcom/b43/main.c
@@ -5591,7 +5591,9 @@ static struct b43_wl *b43_wireless_init(struct b43_bus_dev *dev)
BIT(NL80211_IFTYPE_AP) |
BIT(NL80211_IFTYPE_MESH_POINT) |
BIT(NL80211_IFTYPE_STATION) |
+#ifdef CONFIG_WIRELESS_WDS
BIT(NL80211_IFTYPE_WDS) |
+#endif
BIT(NL80211_IFTYPE_ADHOC);
hw->wiphy->flags |= WIPHY_FLAG_IBSS_RSN;
diff --git a/drivers/net/wireless/broadcom/b43legacy/main.c b/drivers/net/wireless/broadcom/b43legacy/main.c
index 83770d2..e97ab2b 100644
--- a/drivers/net/wireless/broadcom/b43legacy/main.c
+++ b/drivers/net/wireless/broadcom/b43legacy/main.c
@@ -3838,7 +3838,9 @@ static int b43legacy_wireless_init(struct ssb_device *dev)
hw->wiphy->interface_modes =
BIT(NL80211_IFTYPE_AP) |
BIT(NL80211_IFTYPE_STATION) |
+#ifdef CONFIG_WIRELESS_WDS
BIT(NL80211_IFTYPE_WDS) |
+#endif
BIT(NL80211_IFTYPE_ADHOC);
hw->queues = 1; /* FIXME: hardware has more queues */
hw->max_rates = 2;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index b777e1b..cf267f9 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -414,23 +414,24 @@ static int brcmf_vif_change_validate(struct brcmf_cfg80211_info *cfg,
struct brcmf_cfg80211_vif *vif,
enum nl80211_iftype new_type)
{
- int iftype_num[NUM_NL80211_IFTYPES];
struct brcmf_cfg80211_vif *pos;
bool check_combos = false;
int ret = 0;
+ struct iface_combination_params params = {
+ .num_different_channels = 1,
+ };
- memset(&iftype_num[0], 0, sizeof(iftype_num));
list_for_each_entry(pos, &cfg->vif_list, list)
if (pos == vif) {
- iftype_num[new_type]++;
+ params.iftype_num[new_type]++;
} else {
/* concurrent interfaces so need check combinations */
check_combos = true;
- iftype_num[pos->wdev.iftype]++;
+ params.iftype_num[pos->wdev.iftype]++;
}
if (check_combos)
- ret = cfg80211_check_combinations(cfg->wiphy, 1, 0, iftype_num);
+ ret = cfg80211_check_combinations(cfg->wiphy, ¶ms);
return ret;
}
@@ -438,15 +439,16 @@ static int brcmf_vif_change_validate(struct brcmf_cfg80211_info *cfg,
static int brcmf_vif_add_validate(struct brcmf_cfg80211_info *cfg,
enum nl80211_iftype new_type)
{
- int iftype_num[NUM_NL80211_IFTYPES];
struct brcmf_cfg80211_vif *pos;
+ struct iface_combination_params params = {
+ .num_different_channels = 1,
+ };
- memset(&iftype_num[0], 0, sizeof(iftype_num));
list_for_each_entry(pos, &cfg->vif_list, list)
- iftype_num[pos->wdev.iftype]++;
+ params.iftype_num[pos->wdev.iftype]++;
- iftype_num[new_type]++;
- return cfg80211_check_combinations(cfg->wiphy, 1, 0, iftype_num);
+ params.iftype_num[new_type]++;
+ return cfg80211_check_combinations(cfg->wiphy, ¶ms);
}
static void convert_key_from_CPU(struct brcmf_wsec_key *key,
@@ -4516,7 +4518,7 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev,
/* store current 11d setting */
if (brcmf_fil_cmd_int_get(ifp, BRCMF_C_GET_REGULATORY,
&ifp->vif->is_11d)) {
- supports_11d = false;
+ is_11d = supports_11d = false;
} else {
country_ie = brcmf_parse_tlvs((u8 *)settings->beacon.tail,
settings->beacon.tail_len,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 4fdc3da..b88e204 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -1087,6 +1087,15 @@ iwl_mvm_netdetect_config(struct iwl_mvm *mvm,
ret = iwl_mvm_switch_to_d3(mvm);
if (ret)
return ret;
+ } else {
+ /* In theory, we wouldn't have to stop a running sched
+ * scan in order to start another one (for
+ * net-detect). But in practice this doesn't seem to
+ * work properly, so stop any running sched_scan now.
+ */
+ ret = iwl_mvm_scan_stop(mvm, IWL_MVM_SCAN_SCHED, true);
+ if (ret)
+ return ret;
}
/* rfkill release can be either for wowlan or netdetect */
@@ -1254,7 +1263,10 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
out:
if (ret < 0) {
iwl_mvm_ref(mvm, IWL_MVM_REF_UCODE_DOWN);
- ieee80211_restart_hw(mvm->hw);
+ if (mvm->restart_fw > 0) {
+ mvm->restart_fw--;
+ ieee80211_restart_hw(mvm->hw);
+ }
iwl_mvm_free_nd(mvm);
}
out_noreset:
@@ -2088,6 +2100,16 @@ static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test)
iwl_mvm_update_changed_regdom(mvm);
if (mvm->net_detect) {
+ /* If this is a non-unified image, we restart the FW,
+ * so no need to stop the netdetect scan. If that
+ * fails, continue and try to get the wake-up reasons,
+ * but trigger a HW restart by keeping a failure code
+ * in ret.
+ */
+ if (unified_image)
+ ret = iwl_mvm_scan_stop(mvm, IWL_MVM_SCAN_NETDETECT,
+ false);
+
iwl_mvm_query_netdetect_reasons(mvm, vif);
/* has unlocked the mutex, so skip that */
goto out;
@@ -2271,7 +2293,8 @@ static void iwl_mvm_d3_test_disconn_work_iter(void *_data, u8 *mac,
static int iwl_mvm_d3_test_release(struct inode *inode, struct file *file)
{
struct iwl_mvm *mvm = inode->i_private;
- int remaining_time = 10;
+ bool unified_image = fw_has_capa(&mvm->fw->ucode_capa,
+ IWL_UCODE_TLV_CAPA_CNSLDTD_D3_D0_IMG);
mvm->d3_test_active = false;
@@ -2282,18 +2305,22 @@ static int iwl_mvm_d3_test_release(struct inode *inode, struct file *file)
mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED;
iwl_abort_notification_waits(&mvm->notif_wait);
- ieee80211_restart_hw(mvm->hw);
+ if (!unified_image) {
+ int remaining_time = 10;
- /* wait for restart and disconnect all interfaces */
- while (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) &&
- remaining_time > 0) {
- remaining_time--;
- msleep(1000);
+ ieee80211_restart_hw(mvm->hw);
+
+ /* wait for restart and disconnect all interfaces */
+ while (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) &&
+ remaining_time > 0) {
+ remaining_time--;
+ msleep(1000);
+ }
+
+ if (remaining_time == 0)
+ IWL_ERR(mvm, "Timed out waiting for HW restart!\n");
}
- if (remaining_time == 0)
- IWL_ERR(mvm, "Timed out waiting for HW restart to finish!\n");
-
ieee80211_iterate_active_interfaces_atomic(
mvm->hw, IEEE80211_IFACE_ITER_NORMAL,
iwl_mvm_d3_test_disconn_work_iter, mvm->keep_vif);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 07da4ef..7b7d2a1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -1529,8 +1529,8 @@ static ssize_t iwl_dbgfs_mem_read(struct file *file, char __user *user_buf,
.data = { &cmd, },
.len = { sizeof(cmd) },
};
- size_t delta, len;
- ssize_t ret;
+ size_t delta;
+ ssize_t ret, len;
hcmd.id = iwl_cmd_id(*ppos >> 24 ? UMAC_RD_WR : LMAC_RD_WR,
DEBUG_GROUP, 0);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 318efd8..1db1dc1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -4121,7 +4121,6 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm,
struct iwl_mvm_internal_rxq_notif *notif,
u32 size)
{
- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(notif_waitq);
u32 qmask = BIT(mvm->trans->num_rx_queues) - 1;
int ret;
@@ -4143,7 +4142,7 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm,
}
if (notif->sync)
- ret = wait_event_timeout(notif_waitq,
+ ret = wait_event_timeout(mvm->rx_sync_waitq,
atomic_read(&mvm->queue_sync_counter) == 0,
HZ);
WARN_ON_ONCE(!ret);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index d17cbf6..c60703e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -937,6 +937,7 @@ struct iwl_mvm {
/* sync d0i3_tx queue and IWL_MVM_STATUS_IN_D0I3 status flag */
spinlock_t d0i3_tx_lock;
wait_queue_head_t d0i3_exit_waitq;
+ wait_queue_head_t rx_sync_waitq;
/* BT-Coex */
struct iwl_bt_coex_profile_notif last_bt_notif;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 05fe6dd..4d35deb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -619,6 +619,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
spin_lock_init(&mvm->refs_lock);
skb_queue_head_init(&mvm->d0i3_tx);
init_waitqueue_head(&mvm->d0i3_exit_waitq);
+ init_waitqueue_head(&mvm->rx_sync_waitq);
atomic_set(&mvm->queue_sync_counter, 0);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index a57c6ef..6c802ce 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -547,7 +547,8 @@ void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb,
"Received expired RX queue sync message\n");
return;
}
- atomic_dec(&mvm->queue_sync_counter);
+ if (!atomic_dec_return(&mvm->queue_sync_counter))
+ wake_up(&mvm->rx_sync_waitq);
}
switch (internal_notif->type) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index f279fdd..fa97432 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1199,6 +1199,9 @@ static int iwl_mvm_num_scans(struct iwl_mvm *mvm)
static int iwl_mvm_check_running_scans(struct iwl_mvm *mvm, int type)
{
+ bool unified_image = fw_has_capa(&mvm->fw->ucode_capa,
+ IWL_UCODE_TLV_CAPA_CNSLDTD_D3_D0_IMG);
+
/* This looks a bit arbitrary, but the idea is that if we run
* out of possible simultaneous scans and the userspace is
* trying to run a scan type that is already running, we
@@ -1225,12 +1228,30 @@ static int iwl_mvm_check_running_scans(struct iwl_mvm *mvm, int type)
return -EBUSY;
return iwl_mvm_scan_stop(mvm, IWL_MVM_SCAN_REGULAR, true);
case IWL_MVM_SCAN_NETDETECT:
- /* No need to stop anything for net-detect since the
- * firmware is restarted anyway. This way, any sched
- * scans that were running will be restarted when we
- * resume.
- */
- return 0;
+ /* For non-unified images, there's no need to stop
+ * anything for net-detect since the firmware is
+ * restarted anyway. This way, any sched scans that
+ * were running will be restarted when we resume.
+ */
+ if (!unified_image)
+ return 0;
+
+ /* If this is a unified image and we ran out of scans,
+ * we need to stop something. Prefer stopping regular
+ * scans, because the results are useless at this
+ * point, and we should be able to keep running
+ * another scheduled scan while suspended.
+ */
+ if (mvm->scan_status & IWL_MVM_SCAN_REGULAR_MASK)
+ return iwl_mvm_scan_stop(mvm, IWL_MVM_SCAN_REGULAR,
+ true);
+ if (mvm->scan_status & IWL_MVM_SCAN_SCHED_MASK)
+ return iwl_mvm_scan_stop(mvm, IWL_MVM_SCAN_SCHED,
+ true);
+
+ /* fall through, something is wrong if no scan was
+ * running but we ran out of scans.
+ */
default:
WARN_ON(1);
break;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 001be40..2f8134b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -541,48 +541,64 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
MODULE_DEVICE_TABLE(pci, iwl_hw_card_ids);
#ifdef CONFIG_ACPI
-#define SPL_METHOD "SPLC"
-#define SPL_DOMAINTYPE_MODULE BIT(0)
-#define SPL_DOMAINTYPE_WIFI BIT(1)
-#define SPL_DOMAINTYPE_WIGIG BIT(2)
-#define SPL_DOMAINTYPE_RFEM BIT(3)
+#define ACPI_SPLC_METHOD "SPLC"
+#define ACPI_SPLC_DOMAIN_WIFI (0x07)
-static u64 splx_get_pwr_limit(struct iwl_trans *trans, union acpi_object *splx)
+static u64 splc_get_pwr_limit(struct iwl_trans *trans, union acpi_object *splc)
{
- union acpi_object *limits, *domain_type, *power_limit;
+ union acpi_object *data_pkg, *dflt_pwr_limit;
+ int i;
- if (splx->type != ACPI_TYPE_PACKAGE ||
- splx->package.count != 2 ||
- splx->package.elements[0].type != ACPI_TYPE_INTEGER ||
- splx->package.elements[0].integer.value != 0) {
- IWL_ERR(trans, "Unsupported splx structure\n");
+ /* We need at least two elements, one for the revision and one
+ * for the data itself. Also check that the revision is
+ * supported (currently only revision 0).
+ */
+ if (splc->type != ACPI_TYPE_PACKAGE ||
+ splc->package.count < 2 ||
+ splc->package.elements[0].type != ACPI_TYPE_INTEGER ||
+ splc->package.elements[0].integer.value != 0) {
+ IWL_DEBUG_INFO(trans,
+ "Unsupported structure returned by the SPLC method. Ignoring.\n");
return 0;
}
- limits = &splx->package.elements[1];
- if (limits->type != ACPI_TYPE_PACKAGE ||
- limits->package.count < 2 ||
- limits->package.elements[0].type != ACPI_TYPE_INTEGER ||
- limits->package.elements[1].type != ACPI_TYPE_INTEGER) {
- IWL_ERR(trans, "Invalid limits element\n");
+ /* loop through all the packages to find the one for WiFi */
+ for (i = 1; i < splc->package.count; i++) {
+ union acpi_object *domain;
+
+ data_pkg = &splc->package.elements[i];
+
+ /* Skip anything that is not a package with the right
+ * amount of elements (i.e. at least 2 integers).
+ */
+ if (data_pkg->type != ACPI_TYPE_PACKAGE ||
+ data_pkg->package.count < 2 ||
+ data_pkg->package.elements[0].type != ACPI_TYPE_INTEGER ||
+ data_pkg->package.elements[1].type != ACPI_TYPE_INTEGER)
+ continue;
+
+ domain = &data_pkg->package.elements[0];
+ if (domain->integer.value == ACPI_SPLC_DOMAIN_WIFI)
+ break;
+
+ data_pkg = NULL;
+ }
+
+ if (!data_pkg) {
+ IWL_DEBUG_INFO(trans,
+ "No element for the WiFi domain returned by the SPLC method.\n");
return 0;
}
- domain_type = &limits->package.elements[0];
- power_limit = &limits->package.elements[1];
- if (!(domain_type->integer.value & SPL_DOMAINTYPE_WIFI)) {
- IWL_DEBUG_INFO(trans, "WiFi power is not limited\n");
- return 0;
- }
-
- return power_limit->integer.value;
+ dflt_pwr_limit = &data_pkg->package.elements[1];
+ return dflt_pwr_limit->integer.value;
}
static void set_dflt_pwr_limit(struct iwl_trans *trans, struct pci_dev *pdev)
{
acpi_handle pxsx_handle;
acpi_handle handle;
- struct acpi_buffer splx = {ACPI_ALLOCATE_BUFFER, NULL};
+ struct acpi_buffer splc = {ACPI_ALLOCATE_BUFFER, NULL};
acpi_status status;
pxsx_handle = ACPI_HANDLE(&pdev->dev);
@@ -593,23 +609,24 @@ static void set_dflt_pwr_limit(struct iwl_trans *trans, struct pci_dev *pdev)
}
/* Get the method's handle */
- status = acpi_get_handle(pxsx_handle, (acpi_string)SPL_METHOD, &handle);
+ status = acpi_get_handle(pxsx_handle, (acpi_string)ACPI_SPLC_METHOD,
+ &handle);
if (ACPI_FAILURE(status)) {
- IWL_DEBUG_INFO(trans, "SPL method not found\n");
+ IWL_DEBUG_INFO(trans, "SPLC method not found\n");
return;
}
/* Call SPLC with no arguments */
- status = acpi_evaluate_object(handle, NULL, NULL, &splx);
+ status = acpi_evaluate_object(handle, NULL, NULL, &splc);
if (ACPI_FAILURE(status)) {
IWL_ERR(trans, "SPLC invocation failed (0x%x)\n", status);
return;
}
- trans->dflt_pwr_limit = splx_get_pwr_limit(trans, splx.pointer);
+ trans->dflt_pwr_limit = splc_get_pwr_limit(trans, splc.pointer);
IWL_DEBUG_INFO(trans, "Default power limit set to %lld\n",
trans->dflt_pwr_limit);
- kfree(splx.pointer);
+ kfree(splc.pointer);
}
#else /* CONFIG_ACPI */
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index e9a278b..5f840f1 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -592,6 +592,7 @@ static int iwl_pcie_txq_alloc(struct iwl_trans *trans,
static int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq,
int slots_num, u32 txq_id)
{
+ struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
int ret;
txq->need_update = false;
@@ -606,6 +607,13 @@ static int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq,
return ret;
spin_lock_init(&txq->lock);
+
+ if (txq_id == trans_pcie->cmd_queue) {
+ static struct lock_class_key iwl_pcie_cmd_queue_lock_class;
+
+ lockdep_set_class(&txq->lock, &iwl_pcie_cmd_queue_lock_class);
+ }
+
__skb_queue_head_init(&txq->overflow_q);
/*
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 220e9dc..1293f84 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -250,7 +250,7 @@ static inline void hwsim_clear_chanctx_magic(struct ieee80211_chanctx_conf *c)
cp->magic = 0;
}
-static int hwsim_net_id;
+static unsigned int hwsim_net_id;
static int hwsim_netgroup;
@@ -2249,35 +2249,51 @@ static void mac80211_hwsim_get_et_stats(struct ieee80211_hw *hw,
WARN_ON(i != MAC80211_HWSIM_SSTATS_LEN);
}
+#define HWSIM_COMMON_OPS \
+ .tx = mac80211_hwsim_tx, \
+ .start = mac80211_hwsim_start, \
+ .stop = mac80211_hwsim_stop, \
+ .add_interface = mac80211_hwsim_add_interface, \
+ .change_interface = mac80211_hwsim_change_interface, \
+ .remove_interface = mac80211_hwsim_remove_interface, \
+ .config = mac80211_hwsim_config, \
+ .configure_filter = mac80211_hwsim_configure_filter, \
+ .bss_info_changed = mac80211_hwsim_bss_info_changed, \
+ .sta_add = mac80211_hwsim_sta_add, \
+ .sta_remove = mac80211_hwsim_sta_remove, \
+ .sta_notify = mac80211_hwsim_sta_notify, \
+ .set_tim = mac80211_hwsim_set_tim, \
+ .conf_tx = mac80211_hwsim_conf_tx, \
+ .get_survey = mac80211_hwsim_get_survey, \
+ CFG80211_TESTMODE_CMD(mac80211_hwsim_testmode_cmd) \
+ .ampdu_action = mac80211_hwsim_ampdu_action, \
+ .flush = mac80211_hwsim_flush, \
+ .get_tsf = mac80211_hwsim_get_tsf, \
+ .set_tsf = mac80211_hwsim_set_tsf, \
+ .get_et_sset_count = mac80211_hwsim_get_et_sset_count, \
+ .get_et_stats = mac80211_hwsim_get_et_stats, \
+ .get_et_strings = mac80211_hwsim_get_et_strings,
+
static const struct ieee80211_ops mac80211_hwsim_ops = {
- .tx = mac80211_hwsim_tx,
- .start = mac80211_hwsim_start,
- .stop = mac80211_hwsim_stop,
- .add_interface = mac80211_hwsim_add_interface,
- .change_interface = mac80211_hwsim_change_interface,
- .remove_interface = mac80211_hwsim_remove_interface,
- .config = mac80211_hwsim_config,
- .configure_filter = mac80211_hwsim_configure_filter,
- .bss_info_changed = mac80211_hwsim_bss_info_changed,
- .sta_add = mac80211_hwsim_sta_add,
- .sta_remove = mac80211_hwsim_sta_remove,
- .sta_notify = mac80211_hwsim_sta_notify,
- .set_tim = mac80211_hwsim_set_tim,
- .conf_tx = mac80211_hwsim_conf_tx,
- .get_survey = mac80211_hwsim_get_survey,
- CFG80211_TESTMODE_CMD(mac80211_hwsim_testmode_cmd)
- .ampdu_action = mac80211_hwsim_ampdu_action,
+ HWSIM_COMMON_OPS
.sw_scan_start = mac80211_hwsim_sw_scan,
.sw_scan_complete = mac80211_hwsim_sw_scan_complete,
- .flush = mac80211_hwsim_flush,
- .get_tsf = mac80211_hwsim_get_tsf,
- .set_tsf = mac80211_hwsim_set_tsf,
- .get_et_sset_count = mac80211_hwsim_get_et_sset_count,
- .get_et_stats = mac80211_hwsim_get_et_stats,
- .get_et_strings = mac80211_hwsim_get_et_strings,
};
-static struct ieee80211_ops mac80211_hwsim_mchan_ops;
+static const struct ieee80211_ops mac80211_hwsim_mchan_ops = {
+ HWSIM_COMMON_OPS
+ .hw_scan = mac80211_hwsim_hw_scan,
+ .cancel_hw_scan = mac80211_hwsim_cancel_hw_scan,
+ .sw_scan_start = NULL,
+ .sw_scan_complete = NULL,
+ .remain_on_channel = mac80211_hwsim_roc,
+ .cancel_remain_on_channel = mac80211_hwsim_croc,
+ .add_chanctx = mac80211_hwsim_add_chanctx,
+ .remove_chanctx = mac80211_hwsim_remove_chanctx,
+ .change_chanctx = mac80211_hwsim_change_chanctx,
+ .assign_vif_chanctx = mac80211_hwsim_assign_vif_chanctx,
+ .unassign_vif_chanctx = mac80211_hwsim_unassign_vif_chanctx,
+};
struct hwsim_new_radio_params {
unsigned int channels;
@@ -3362,21 +3378,6 @@ static int __init init_mac80211_hwsim(void)
if (channels < 1)
return -EINVAL;
- mac80211_hwsim_mchan_ops = mac80211_hwsim_ops;
- mac80211_hwsim_mchan_ops.hw_scan = mac80211_hwsim_hw_scan;
- mac80211_hwsim_mchan_ops.cancel_hw_scan = mac80211_hwsim_cancel_hw_scan;
- mac80211_hwsim_mchan_ops.sw_scan_start = NULL;
- mac80211_hwsim_mchan_ops.sw_scan_complete = NULL;
- mac80211_hwsim_mchan_ops.remain_on_channel = mac80211_hwsim_roc;
- mac80211_hwsim_mchan_ops.cancel_remain_on_channel = mac80211_hwsim_croc;
- mac80211_hwsim_mchan_ops.add_chanctx = mac80211_hwsim_add_chanctx;
- mac80211_hwsim_mchan_ops.remove_chanctx = mac80211_hwsim_remove_chanctx;
- mac80211_hwsim_mchan_ops.change_chanctx = mac80211_hwsim_change_chanctx;
- mac80211_hwsim_mchan_ops.assign_vif_chanctx =
- mac80211_hwsim_assign_vif_chanctx;
- mac80211_hwsim_mchan_ops.unassign_vif_chanctx =
- mac80211_hwsim_unassign_vif_chanctx;
-
spin_lock_init(&hwsim_radio_lock);
err = register_pernet_device(&hwsim_net_ops);
diff --git a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
index 9448012..274dd5a 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
@@ -45,7 +45,7 @@ static int mwifiex_11n_dispatch_amsdu_pkt(struct mwifiex_private *priv,
skb_trim(skb, le16_to_cpu(local_rx_pd->rx_pkt_length));
ieee80211_amsdu_to_8023s(skb, &list, priv->curr_addr,
- priv->wdev.iftype, 0, false);
+ priv->wdev.iftype, 0, NULL, NULL);
while (!skb_queue_empty(&list)) {
struct rx_packet_hdr *rx_hdr;
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c
index 4e0c565..236f790 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c
@@ -1362,11 +1362,13 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev)
if (rt2x00dev->bcn->limit > 0)
rt2x00dev->hw->wiphy->interface_modes |=
BIT(NL80211_IFTYPE_ADHOC) |
- BIT(NL80211_IFTYPE_AP) |
#ifdef CONFIG_MAC80211_MESH
BIT(NL80211_IFTYPE_MESH_POINT) |
#endif
- BIT(NL80211_IFTYPE_WDS);
+#ifdef CONFIG_WIRELESS_WDS
+ BIT(NL80211_IFTYPE_WDS) |
+#endif
+ BIT(NL80211_IFTYPE_AP);
rt2x00dev->hw->wiphy->flags |= WIPHY_FLAG_IBSS_RSN;
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
index 10166289..08d587a 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h
@@ -238,7 +238,7 @@ struct rtl8xxxu_rxdesc16 {
u32 pattern1match:1;
u32 pattern0match:1;
#endif
- __le32 tsfl;
+ u32 tsfl;
#if 0
u32 bassn:12;
u32 bavld:1;
@@ -368,7 +368,7 @@ struct rtl8xxxu_rxdesc24 {
u32 ldcp:1;
u32 splcp:1;
#endif
- __le32 tsfl;
+ u32 tsfl;
};
struct rtl8xxxu_txdesc32 {
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
index df54d27..a793fed 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
@@ -1461,7 +1461,9 @@ static int rtl8192eu_active_to_emu(struct rtl8xxxu_priv *priv)
int count, ret = 0;
/* Turn off RF */
- rtl8xxxu_write8(priv, REG_RF_CTRL, 0);
+ val8 = rtl8xxxu_read8(priv, REG_RF_CTRL);
+ val8 &= ~RF_ENABLE;
+ rtl8xxxu_write8(priv, REG_RF_CTRL, val8);
/* Switch DPDT_SEL_P output from register 0x65[2] */
val8 = rtl8xxxu_read8(priv, REG_LEDCFG2);
@@ -1593,6 +1595,10 @@ static void rtl8192e_enable_rf(struct rtl8xxxu_priv *priv)
u32 val32;
u8 val8;
+ val32 = rtl8xxxu_read32(priv, REG_RX_WAIT_CCA);
+ val32 |= (BIT(22) | BIT(23));
+ rtl8xxxu_write32(priv, REG_RX_WAIT_CCA, val32);
+
val8 = rtl8xxxu_read8(priv, REG_GPIO_MUXCFG);
val8 |= BIT(5);
rtl8xxxu_write8(priv, REG_GPIO_MUXCFG, val8);
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c
index 6c086b5..02b8ddd 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8723b.c
@@ -1498,6 +1498,10 @@ static void rtl8723b_enable_rf(struct rtl8xxxu_priv *priv)
u32 val32;
u8 val8;
+ val32 = rtl8xxxu_read32(priv, REG_RX_WAIT_CCA);
+ val32 |= (BIT(22) | BIT(23));
+ rtl8xxxu_write32(priv, REG_RX_WAIT_CCA, val32);
+
/*
* No indication anywhere as to what 0x0790 does. The 2 antenna
* vendor code preserves bits 6-7 here.
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
index b2d7f6e..a5e6ec2 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c
@@ -5197,7 +5197,12 @@ int rtl8xxxu_parse_rxdesc16(struct rtl8xxxu_priv *priv, struct sk_buff *skb)
pkt_offset = roundup(pkt_len + drvinfo_sz + desc_shift +
sizeof(struct rtl8xxxu_rxdesc16), 128);
- if (pkt_cnt > 1)
+ /*
+ * Only clone the skb if there's enough data at the end to
+ * at least cover the rx descriptor
+ */
+ if (pkt_cnt > 1 &&
+ urb_len > (pkt_offset + sizeof(struct rtl8xxxu_rxdesc16)))
next_skb = skb_clone(skb, GFP_ATOMIC);
rx_status = IEEE80211_SKB_RXCB(skb);
@@ -5215,7 +5220,7 @@ int rtl8xxxu_parse_rxdesc16(struct rtl8xxxu_priv *priv, struct sk_buff *skb)
rtl8xxxu_rx_parse_phystats(priv, rx_status, phy_stats,
rx_desc->rxmcs);
- rx_status->mactime = le32_to_cpu(rx_desc->tsfl);
+ rx_status->mactime = rx_desc->tsfl;
rx_status->flag |= RX_FLAG_MACTIME_START;
if (!rx_desc->swdec)
@@ -5285,7 +5290,7 @@ int rtl8xxxu_parse_rxdesc24(struct rtl8xxxu_priv *priv, struct sk_buff *skb)
rtl8xxxu_rx_parse_phystats(priv, rx_status, phy_stats,
rx_desc->rxmcs);
- rx_status->mactime = le32_to_cpu(rx_desc->tsfl);
+ rx_status->mactime = rx_desc->tsfl;
rx_status->flag |= RX_FLAG_MACTIME_START;
if (!rx_desc->swdec)
diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c
index f95760c..8e7f23c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.c
+++ b/drivers/net/wireless/realtek/rtlwifi/core.c
@@ -111,7 +111,7 @@ static void rtl_fw_do_work(const struct firmware *firmware, void *context,
if (!err)
goto found_alt;
}
- pr_err("Firmware %s not available\n", rtlpriv->cfg->fw_name);
+ pr_err("Selected firmware is not available\n");
rtlpriv->max_fw_size = 0;
return;
}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c
index e7b11b4..f361808 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c
@@ -86,6 +86,7 @@ int rtl88e_init_sw_vars(struct ieee80211_hw *hw)
struct rtl_priv *rtlpriv = rtl_priv(hw);
struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
u8 tid;
+ char *fw_name;
rtl8188ee_bt_reg_init(hw);
rtlpriv->dm.dm_initialgain_enable = 1;
@@ -169,10 +170,10 @@ int rtl88e_init_sw_vars(struct ieee80211_hw *hw)
return 1;
}
- rtlpriv->cfg->fw_name = "rtlwifi/rtl8188efw.bin";
+ fw_name = "rtlwifi/rtl8188efw.bin";
rtlpriv->max_fw_size = 0x8000;
- pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name);
- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+ pr_info("Using firmware %s\n", fw_name);
+ err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
rtlpriv->io.dev, GFP_KERNEL, hw,
rtl_fw_cb);
if (err) {
@@ -284,7 +285,6 @@ static const struct rtl_hal_cfg rtl88ee_hal_cfg = {
.bar_id = 2,
.write_readback = true,
.name = "rtl88e_pci",
- .fw_name = "rtlwifi/rtl8188efw.bin",
.ops = &rtl8188ee_hal_ops,
.mod_params = &rtl88ee_mod_params,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
index 87aa209..8b6e37c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
@@ -96,6 +96,7 @@ int rtl92c_init_sw_vars(struct ieee80211_hw *hw)
struct rtl_priv *rtlpriv = rtl_priv(hw);
struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+ char *fw_name = "rtlwifi/rtl8192cfwU.bin";
rtl8192ce_bt_reg_init(hw);
@@ -167,15 +168,12 @@ int rtl92c_init_sw_vars(struct ieee80211_hw *hw)
}
/* request fw */
- if (IS_VENDOR_UMC_A_CUT(rtlhal->version) &&
- !IS_92C_SERIAL(rtlhal->version))
- rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cfwU.bin";
- else if (IS_81XXC_VENDOR_UMC_B_CUT(rtlhal->version))
- rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cfwU_B.bin";
+ if (IS_81XXC_VENDOR_UMC_B_CUT(rtlhal->version))
+ fw_name = "rtlwifi/rtl8192cfwU_B.bin";
rtlpriv->max_fw_size = 0x4000;
- pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name);
- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+ pr_info("Using firmware %s\n", fw_name);
+ err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
rtlpriv->io.dev, GFP_KERNEL, hw,
rtl_fw_cb);
if (err) {
@@ -262,7 +260,6 @@ static const struct rtl_hal_cfg rtl92ce_hal_cfg = {
.bar_id = 2,
.write_readback = true,
.name = "rtl92c_pci",
- .fw_name = "rtlwifi/rtl8192cfw.bin",
.ops = &rtl8192ce_hal_ops,
.mod_params = &rtl92ce_mod_params,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c
index 7c6f7f0..f953320 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c
@@ -59,6 +59,7 @@ static int rtl92cu_init_sw_vars(struct ieee80211_hw *hw)
{
struct rtl_priv *rtlpriv = rtl_priv(hw);
int err;
+ char *fw_name;
rtlpriv->dm.dm_initialgain_enable = true;
rtlpriv->dm.dm_flag = 0;
@@ -77,18 +78,18 @@ static int rtl92cu_init_sw_vars(struct ieee80211_hw *hw)
}
if (IS_VENDOR_UMC_A_CUT(rtlpriv->rtlhal.version) &&
!IS_92C_SERIAL(rtlpriv->rtlhal.version)) {
- rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cufw_A.bin";
+ fw_name = "rtlwifi/rtl8192cufw_A.bin";
} else if (IS_81XXC_VENDOR_UMC_B_CUT(rtlpriv->rtlhal.version)) {
- rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cufw_B.bin";
+ fw_name = "rtlwifi/rtl8192cufw_B.bin";
} else {
- rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cufw_TMSC.bin";
+ fw_name = "rtlwifi/rtl8192cufw_TMSC.bin";
}
/* provide name of alternative file */
rtlpriv->cfg->alt_fw_name = "rtlwifi/rtl8192cufw.bin";
- pr_info("Loading firmware %s\n", rtlpriv->cfg->fw_name);
+ pr_info("Loading firmware %s\n", fw_name);
rtlpriv->max_fw_size = 0x4000;
err = request_firmware_nowait(THIS_MODULE, 1,
- rtlpriv->cfg->fw_name, rtlpriv->io.dev,
+ fw_name, rtlpriv->io.dev,
GFP_KERNEL, hw, rtl_fw_cb);
return err;
}
@@ -187,7 +188,6 @@ static struct rtl_hal_usbint_cfg rtl92cu_interface_cfg = {
static struct rtl_hal_cfg rtl92cu_hal_cfg = {
.name = "rtl92c_usb",
- .fw_name = "rtlwifi/rtl8192cufw.bin",
.ops = &rtl8192cu_hal_ops,
.mod_params = &rtl92cu_mod_params,
.usb_interface_cfg = &rtl92cu_interface_cfg,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c
index 0538a4d..1ebfee1 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c
@@ -92,6 +92,7 @@ static int rtl92d_init_sw_vars(struct ieee80211_hw *hw)
u8 tid;
struct rtl_priv *rtlpriv = rtl_priv(hw);
struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
+ char *fw_name = "rtlwifi/rtl8192defw.bin";
rtlpriv->dm.dm_initialgain_enable = true;
rtlpriv->dm.dm_flag = 0;
@@ -181,10 +182,10 @@ static int rtl92d_init_sw_vars(struct ieee80211_hw *hw)
rtlpriv->max_fw_size = 0x8000;
pr_info("Driver for Realtek RTL8192DE WLAN interface\n");
- pr_info("Loading firmware file %s\n", rtlpriv->cfg->fw_name);
+ pr_info("Loading firmware file %s\n", fw_name);
/* request fw */
- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+ err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
rtlpriv->io.dev, GFP_KERNEL, hw,
rtl_fw_cb);
if (err) {
@@ -266,7 +267,6 @@ static const struct rtl_hal_cfg rtl92de_hal_cfg = {
.bar_id = 2,
.write_readback = true,
.name = "rtl8192de",
- .fw_name = "rtlwifi/rtl8192defw.bin",
.ops = &rtl8192de_hal_ops,
.mod_params = &rtl92de_mod_params,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c
index ac299cb..46b605de3 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c
@@ -91,6 +91,7 @@ int rtl92ee_init_sw_vars(struct ieee80211_hw *hw)
struct rtl_priv *rtlpriv = rtl_priv(hw);
struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
int err = 0;
+ char *fw_name;
rtl92ee_bt_reg_init(hw);
rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support;
@@ -170,11 +171,11 @@ int rtl92ee_init_sw_vars(struct ieee80211_hw *hw)
}
/* request fw */
- rtlpriv->cfg->fw_name = "rtlwifi/rtl8192eefw.bin";
+ fw_name = "rtlwifi/rtl8192eefw.bin";
rtlpriv->max_fw_size = 0x8000;
- pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name);
- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+ pr_info("Using firmware %s\n", fw_name);
+ err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
rtlpriv->io.dev, GFP_KERNEL, hw,
rtl_fw_cb);
if (err) {
@@ -266,7 +267,6 @@ static const struct rtl_hal_cfg rtl92ee_hal_cfg = {
.bar_id = 2,
.write_readback = true,
.name = "rtl92ee_pci",
- .fw_name = "rtlwifi/rtl8192eefw.bin",
.ops = &rtl8192ee_hal_ops,
.mod_params = &rtl92ee_mod_params,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c
index 5e8e02d..3e1eaea 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c
@@ -89,12 +89,13 @@ static void rtl92se_fw_cb(const struct firmware *firmware, void *context)
struct ieee80211_hw *hw = context;
struct rtl_priv *rtlpriv = rtl_priv(hw);
struct rt_firmware *pfirmware = NULL;
+ char *fw_name = "rtlwifi/rtl8192sefw.bin";
RT_TRACE(rtlpriv, COMP_ERR, DBG_LOUD,
"Firmware callback routine entered!\n");
complete(&rtlpriv->firmware_loading_complete);
if (!firmware) {
- pr_err("Firmware %s not available\n", rtlpriv->cfg->fw_name);
+ pr_err("Firmware %s not available\n", fw_name);
rtlpriv->max_fw_size = 0;
return;
}
@@ -117,6 +118,7 @@ static int rtl92s_init_sw_vars(struct ieee80211_hw *hw)
struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
int err = 0;
u16 earlyrxthreshold = 7;
+ char *fw_name = "rtlwifi/rtl8192sefw.bin";
rtlpriv->dm.dm_initialgain_enable = true;
rtlpriv->dm.dm_flag = 0;
@@ -214,9 +216,9 @@ static int rtl92s_init_sw_vars(struct ieee80211_hw *hw)
rtlpriv->max_fw_size = RTL8190_MAX_FIRMWARE_CODE_SIZE*2 +
sizeof(struct fw_hdr);
pr_info("Driver for Realtek RTL8192SE/RTL8191SE\n"
- "Loading firmware %s\n", rtlpriv->cfg->fw_name);
+ "Loading firmware %s\n", fw_name);
/* request fw */
- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+ err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
rtlpriv->io.dev, GFP_KERNEL, hw,
rtl92se_fw_cb);
if (err) {
@@ -310,7 +312,6 @@ static const struct rtl_hal_cfg rtl92se_hal_cfg = {
.bar_id = 1,
.write_readback = false,
.name = "rtl92s_pci",
- .fw_name = "rtlwifi/rtl8192sefw.bin",
.ops = &rtl8192se_hal_ops,
.mod_params = &rtl92se_mod_params,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c
index 89c828a..c51a9e8 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c
@@ -94,6 +94,7 @@ int rtl8723e_init_sw_vars(struct ieee80211_hw *hw)
struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
int err = 0;
+ char *fw_name = "rtlwifi/rtl8723fw.bin";
rtl8723e_bt_reg_init(hw);
@@ -176,14 +177,12 @@ int rtl8723e_init_sw_vars(struct ieee80211_hw *hw)
return 1;
}
- if (IS_VENDOR_8723_A_CUT(rtlhal->version))
- rtlpriv->cfg->fw_name = "rtlwifi/rtl8723fw.bin";
- else if (IS_81xxC_VENDOR_UMC_B_CUT(rtlhal->version))
- rtlpriv->cfg->fw_name = "rtlwifi/rtl8723fw_B.bin";
+ if (IS_81xxC_VENDOR_UMC_B_CUT(rtlhal->version))
+ fw_name = "rtlwifi/rtl8723fw_B.bin";
rtlpriv->max_fw_size = 0x6000;
- pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name);
- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+ pr_info("Using firmware %s\n", fw_name);
+ err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
rtlpriv->io.dev, GFP_KERNEL, hw,
rtl_fw_cb);
if (err) {
@@ -280,7 +279,6 @@ static const struct rtl_hal_cfg rtl8723e_hal_cfg = {
.bar_id = 2,
.write_readback = true,
.name = "rtl8723e_pci",
- .fw_name = "rtlwifi/rtl8723efw.bin",
.ops = &rtl8723e_hal_ops,
.mod_params = &rtl8723e_mod_params,
.maps[SYS_ISO_CTRL] = REG_SYS_ISO_CTRL,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
index 20b53f0..847644d 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c
@@ -91,6 +91,7 @@ int rtl8723be_init_sw_vars(struct ieee80211_hw *hw)
struct rtl_priv *rtlpriv = rtl_priv(hw);
struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
+ char *fw_name = "rtlwifi/rtl8723befw.bin";
rtl8723be_bt_reg_init(hw);
rtlpriv->btcoexist.btc_ops = rtl_btc_get_ops_pointer();
@@ -184,8 +185,8 @@ int rtl8723be_init_sw_vars(struct ieee80211_hw *hw)
}
rtlpriv->max_fw_size = 0x8000;
- pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name);
- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+ pr_info("Using firmware %s\n", fw_name);
+ err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
rtlpriv->io.dev, GFP_KERNEL, hw,
rtl_fw_cb);
if (err) {
@@ -280,7 +281,6 @@ static const struct rtl_hal_cfg rtl8723be_hal_cfg = {
.bar_id = 2,
.write_readback = true,
.name = "rtl8723be_pci",
- .fw_name = "rtlwifi/rtl8723befw.bin",
.ops = &rtl8723be_hal_ops,
.mod_params = &rtl8723be_mod_params,
.maps[SYS_ISO_CTRL] = REG_SYS_ISO_CTRL,
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
index 22f687b1..297938e 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
@@ -93,6 +93,7 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw)
struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
+ char *fw_name, *wowlan_fw_name;
rtl8821ae_bt_reg_init(hw);
rtlpriv->btcoexist.btc_ops = rtl_btc_get_ops_pointer();
@@ -203,17 +204,17 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw)
}
if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE) {
- rtlpriv->cfg->fw_name = "rtlwifi/rtl8812aefw.bin";
- rtlpriv->cfg->wowlan_fw_name = "rtlwifi/rtl8812aefw_wowlan.bin";
+ fw_name = "rtlwifi/rtl8812aefw.bin";
+ wowlan_fw_name = "rtlwifi/rtl8812aefw_wowlan.bin";
} else {
- rtlpriv->cfg->fw_name = "rtlwifi/rtl8821aefw.bin";
- rtlpriv->cfg->wowlan_fw_name = "rtlwifi/rtl8821aefw_wowlan.bin";
+ fw_name = "rtlwifi/rtl8821aefw.bin";
+ wowlan_fw_name = "rtlwifi/rtl8821aefw_wowlan.bin";
}
rtlpriv->max_fw_size = 0x8000;
/*load normal firmware*/
- pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name);
- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name,
+ pr_info("Using firmware %s\n", fw_name);
+ err = request_firmware_nowait(THIS_MODULE, 1, fw_name,
rtlpriv->io.dev, GFP_KERNEL, hw,
rtl_fw_cb);
if (err) {
@@ -222,9 +223,9 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw)
return 1;
}
/*load wowlan firmware*/
- pr_info("Using firmware %s\n", rtlpriv->cfg->wowlan_fw_name);
+ pr_info("Using firmware %s\n", wowlan_fw_name);
err = request_firmware_nowait(THIS_MODULE, 1,
- rtlpriv->cfg->wowlan_fw_name,
+ wowlan_fw_name,
rtlpriv->io.dev, GFP_KERNEL, hw,
rtl_wowlan_fw_cb);
if (err) {
@@ -320,7 +321,6 @@ static const struct rtl_hal_cfg rtl8821ae_hal_cfg = {
.bar_id = 2,
.write_readback = true,
.name = "rtl8821ae_pci",
- .fw_name = "rtlwifi/rtl8821aefw.bin",
.ops = &rtl8821ae_hal_ops,
.mod_params = &rtl8821ae_mod_params,
.maps[SYS_ISO_CTRL] = REG_SYS_ISO_CTRL,
diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h
index 595f7d5..dafe486 100644
--- a/drivers/net/wireless/realtek/rtlwifi/wifi.h
+++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h
@@ -2278,9 +2278,7 @@ struct rtl_hal_cfg {
u8 bar_id;
bool write_readback;
char *name;
- char *fw_name;
char *alt_fw_name;
- char *wowlan_fw_name;
struct rtl_hal_ops *ops;
struct rtl_mod_params *mod_params;
struct rtl_hal_usbint_cfg *usb_interface_cfg;
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 471521a..9f39c6c 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -6086,6 +6086,7 @@ static int wl1271_init_ieee80211(struct wl1271 *wl)
ieee80211_hw_set(wl->hw, SUPPORTS_DYNAMIC_PS);
ieee80211_hw_set(wl->hw, SIGNAL_DBM);
ieee80211_hw_set(wl->hw, SUPPORTS_PS);
+ ieee80211_hw_set(wl->hw, SUPPORTS_TX_FRAG);
wl->hw->wiphy->cipher_suites = cipher_suites;
wl->hw->wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites);
diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c
index a6e94b1..47fe7f9 100644
--- a/drivers/net/wireless/ti/wlcore/sdio.c
+++ b/drivers/net/wireless/ti/wlcore/sdio.c
@@ -391,7 +391,6 @@ static void wl1271_remove(struct sdio_func *func)
pm_runtime_get_noresume(&func->dev);
platform_device_unregister(glue->core);
- kfree(glue);
}
#ifdef CONFIG_PM
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 8674e18..55a4488 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -889,16 +889,16 @@ static int connect_ctrl_ring(struct backend_info *be)
unsigned int evtchn;
int err;
- err = xenbus_gather(XBT_NIL, dev->otherend,
- "ctrl-ring-ref", "%u", &val, NULL);
- if (err)
+ err = xenbus_scanf(XBT_NIL, dev->otherend,
+ "ctrl-ring-ref", "%u", &val);
+ if (err < 0)
goto done; /* The frontend does not have a control ring */
ring_ref = val;
- err = xenbus_gather(XBT_NIL, dev->otherend,
- "event-channel-ctrl", "%u", &val, NULL);
- if (err) {
+ err = xenbus_scanf(XBT_NIL, dev->otherend,
+ "event-channel-ctrl", "%u", &val);
+ if (err < 0) {
xenbus_dev_fatal(dev, err,
"reading %s/event-channel-ctrl",
dev->otherend);
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 7d616b0..e085c8c 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -304,7 +304,7 @@ static void xennet_alloc_rx_buffers(struct netfront_queue *queue)
queue->rx_skbs[id] = skb;
ref = gnttab_claim_grant_reference(&queue->gref_rx_head);
- BUG_ON((signed short)ref < 0);
+ WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref));
queue->grant_rx_ref[id] = ref;
page = skb_frag_page(&skb_shinfo(skb)->frags[0]);
@@ -428,7 +428,7 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset,
id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs);
tx = RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++);
ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
- BUG_ON((signed short)ref < 0);
+ WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref));
gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id,
gfn, GNTMAP_readonly);
diff --git a/drivers/nfc/mei_phy.c b/drivers/nfc/mei_phy.c
index 83deda4..6f9563a 100644
--- a/drivers/nfc/mei_phy.c
+++ b/drivers/nfc/mei_phy.c
@@ -133,7 +133,7 @@ static int mei_nfc_if_version(struct nfc_mei_phy *phy)
return -ENOMEM;
bytes_recv = mei_cldev_recv(phy->cldev, (u8 *)reply, if_version_length);
- if (bytes_recv < 0 || bytes_recv < sizeof(struct mei_nfc_reply)) {
+ if (bytes_recv < 0 || bytes_recv < if_version_length) {
pr_err("Could not read IF version\n");
r = -EIO;
goto err;
diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c
index 0d5c29a..7310a26 100644
--- a/drivers/ntb/hw/intel/ntb_hw_intel.c
+++ b/drivers/ntb/hw/intel/ntb_hw_intel.c
@@ -112,17 +112,17 @@ MODULE_PARM_DESC(xeon_b2b_usd_bar2_addr64,
module_param_named(xeon_b2b_usd_bar4_addr64,
xeon_b2b_usd_addr.bar4_addr64, ullong, 0644);
-MODULE_PARM_DESC(xeon_b2b_usd_bar2_addr64,
+MODULE_PARM_DESC(xeon_b2b_usd_bar4_addr64,
"XEON B2B USD BAR 4 64-bit address");
module_param_named(xeon_b2b_usd_bar4_addr32,
xeon_b2b_usd_addr.bar4_addr32, ullong, 0644);
-MODULE_PARM_DESC(xeon_b2b_usd_bar2_addr64,
+MODULE_PARM_DESC(xeon_b2b_usd_bar4_addr32,
"XEON B2B USD split-BAR 4 32-bit address");
module_param_named(xeon_b2b_usd_bar5_addr32,
xeon_b2b_usd_addr.bar5_addr32, ullong, 0644);
-MODULE_PARM_DESC(xeon_b2b_usd_bar2_addr64,
+MODULE_PARM_DESC(xeon_b2b_usd_bar5_addr32,
"XEON B2B USD split-BAR 5 32-bit address");
module_param_named(xeon_b2b_dsd_bar2_addr64,
@@ -132,17 +132,17 @@ MODULE_PARM_DESC(xeon_b2b_dsd_bar2_addr64,
module_param_named(xeon_b2b_dsd_bar4_addr64,
xeon_b2b_dsd_addr.bar4_addr64, ullong, 0644);
-MODULE_PARM_DESC(xeon_b2b_dsd_bar2_addr64,
+MODULE_PARM_DESC(xeon_b2b_dsd_bar4_addr64,
"XEON B2B DSD BAR 4 64-bit address");
module_param_named(xeon_b2b_dsd_bar4_addr32,
xeon_b2b_dsd_addr.bar4_addr32, ullong, 0644);
-MODULE_PARM_DESC(xeon_b2b_dsd_bar2_addr64,
+MODULE_PARM_DESC(xeon_b2b_dsd_bar4_addr32,
"XEON B2B DSD split-BAR 4 32-bit address");
module_param_named(xeon_b2b_dsd_bar5_addr32,
xeon_b2b_dsd_addr.bar5_addr32, ullong, 0644);
-MODULE_PARM_DESC(xeon_b2b_dsd_bar2_addr64,
+MODULE_PARM_DESC(xeon_b2b_dsd_bar5_addr32,
"XEON B2B DSD split-BAR 5 32-bit address");
#ifndef ioread64
@@ -1755,6 +1755,8 @@ static int xeon_setup_b2b_mw(struct intel_ntb_dev *ndev,
XEON_B2B_MIN_SIZE);
if (!ndev->peer_mmio)
return -EIO;
+
+ ndev->peer_addr = pci_resource_start(pdev, b2b_bar);
}
return 0;
@@ -2019,6 +2021,7 @@ static int intel_ntb_init_pci(struct intel_ntb_dev *ndev, struct pci_dev *pdev)
goto err_mmio;
}
ndev->peer_mmio = ndev->self_mmio;
+ ndev->peer_addr = pci_resource_start(pdev, 0);
return 0;
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 8601c10..4eb8adb 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -257,7 +257,7 @@ enum {
#define NTB_QP_DEF_NUM_ENTRIES 100
#define NTB_LINK_DOWN_TIMEOUT 10
#define DMA_RETRIES 20
-#define DMA_OUT_RESOURCE_TO 50
+#define DMA_OUT_RESOURCE_TO msecs_to_jiffies(50)
static void ntb_transport_rxc_db(unsigned long data);
static const struct ntb_ctx_ops ntb_transport_ops;
diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
index 6a50f20..e75d4fd 100644
--- a/drivers/ntb/test/ntb_perf.c
+++ b/drivers/ntb/test/ntb_perf.c
@@ -72,7 +72,7 @@
#define MAX_THREADS 32
#define MAX_TEST_SIZE SZ_1M
#define MAX_SRCS 32
-#define DMA_OUT_RESOURCE_TO 50
+#define DMA_OUT_RESOURCE_TO msecs_to_jiffies(50)
#define DMA_RETRIES 20
#define SZ_4G (1ULL << 32)
#define MAX_SEG_ORDER 20 /* no larger than 1M for kmalloc buffer */
@@ -589,7 +589,7 @@ static ssize_t debugfs_run_read(struct file *filp, char __user *ubuf,
return -ENOMEM;
if (mutex_is_locked(&perf->run_mutex)) {
- out_off = snprintf(buf, 64, "running\n");
+ out_off = scnprintf(buf, 64, "running\n");
goto read_from_buf;
}
@@ -600,14 +600,14 @@ static ssize_t debugfs_run_read(struct file *filp, char __user *ubuf,
break;
if (pctx->status) {
- out_off += snprintf(buf + out_off, 1024 - out_off,
+ out_off += scnprintf(buf + out_off, 1024 - out_off,
"%d: error %d\n", i,
pctx->status);
continue;
}
rate = div64_u64(pctx->copied, pctx->diff_us);
- out_off += snprintf(buf + out_off, 1024 - out_off,
+ out_off += scnprintf(buf + out_off, 1024 - out_off,
"%d: copied %llu bytes in %llu usecs, %llu MBytes/s\n",
i, pctx->copied, pctx->diff_us, rate);
}
diff --git a/drivers/ntb/test/ntb_pingpong.c b/drivers/ntb/test/ntb_pingpong.c
index 7d31179..4358611 100644
--- a/drivers/ntb/test/ntb_pingpong.c
+++ b/drivers/ntb/test/ntb_pingpong.c
@@ -88,7 +88,7 @@ MODULE_PARM_DESC(delay_ms, "Milliseconds to delay the response to peer");
static unsigned long db_init = 0x7;
module_param(db_init, ulong, 0644);
-MODULE_PARM_DESC(delay_ms, "Initial doorbell bits to ring on the peer");
+MODULE_PARM_DESC(db_init, "Initial doorbell bits to ring on the peer");
struct pp_ctx {
struct ntb_dev *ntb;
diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig
index 8b2b740..124c243 100644
--- a/drivers/nvdimm/Kconfig
+++ b/drivers/nvdimm/Kconfig
@@ -89,7 +89,7 @@
Select Y if unsure
config NVDIMM_DAX
- tristate "NVDIMM DAX: Raw access to persistent memory"
+ bool "NVDIMM DAX: Raw access to persistent memory"
default LIBNVDIMM
depends on NVDIMM_PFN
help
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 3509cff..abe5c6b 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -2176,12 +2176,14 @@ static struct device **scan_labels(struct nd_region *nd_region)
return devs;
err:
- for (i = 0; devs[i]; i++)
- if (is_nd_blk(&nd_region->dev))
- namespace_blk_release(devs[i]);
- else
- namespace_pmem_release(devs[i]);
- kfree(devs);
+ if (devs) {
+ for (i = 0; devs[i]; i++)
+ if (is_nd_blk(&nd_region->dev))
+ namespace_blk_release(devs[i]);
+ else
+ namespace_pmem_release(devs[i]);
+ kfree(devs);
+ }
return NULL;
}
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 42b3a82..2461843 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -47,7 +47,7 @@ static struct nd_region *to_region(struct pmem_device *pmem)
return to_nd_region(to_dev(pmem)->parent);
}
-static void pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset,
+static int pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset,
unsigned int len)
{
struct device *dev = to_dev(pmem);
@@ -62,8 +62,12 @@ static void pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset,
__func__, (unsigned long long) sector,
cleared / 512, cleared / 512 > 1 ? "s" : "");
badblocks_clear(&pmem->bb, sector, cleared / 512);
+ } else {
+ return -EIO;
}
+
invalidate_pmem(pmem->virt_addr + offset, len);
+ return 0;
}
static void write_pmem(void *pmem_addr, struct page *page,
@@ -123,7 +127,7 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
flush_dcache_page(page);
write_pmem(pmem_addr, page, off, len);
if (unlikely(bad_pmem)) {
- pmem_clear_poison(pmem, pmem_off, len);
+ rc = pmem_clear_poison(pmem, pmem_off, len);
write_pmem(pmem_addr, page, off, len);
}
}
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 329381a..79e679d 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -554,7 +554,7 @@ int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
/* gcc-4.4.4 (at least) has issues with initializers and anon unions */
c.identify.opcode = nvme_admin_identify;
- c.identify.cns = cpu_to_le32(1);
+ c.identify.cns = cpu_to_le32(NVME_ID_CNS_CTRL);
*id = kmalloc(sizeof(struct nvme_id_ctrl), GFP_KERNEL);
if (!*id)
@@ -572,7 +572,7 @@ static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *n
struct nvme_command c = { };
c.identify.opcode = nvme_admin_identify;
- c.identify.cns = cpu_to_le32(2);
+ c.identify.cns = cpu_to_le32(NVME_ID_CNS_NS_ACTIVE_LIST);
c.identify.nsid = cpu_to_le32(nsid);
return nvme_submit_sync_cmd(dev->admin_q, &c, ns_list, 0x1000);
}
@@ -900,9 +900,9 @@ static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id)
return -ENODEV;
}
- if (ns->ctrl->vs >= NVME_VS(1, 1))
+ if (ns->ctrl->vs >= NVME_VS(1, 1, 0))
memcpy(ns->eui, (*id)->eui64, sizeof(ns->eui));
- if (ns->ctrl->vs >= NVME_VS(1, 2))
+ if (ns->ctrl->vs >= NVME_VS(1, 2, 0))
memcpy(ns->uuid, (*id)->nguid, sizeof(ns->uuid));
return 0;
@@ -1086,6 +1086,8 @@ static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled)
int ret;
while ((ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &csts)) == 0) {
+ if (csts == ~0)
+ return -ENODEV;
if ((csts & NVME_CSTS_RDY) == bit)
break;
@@ -1240,7 +1242,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
}
page_shift = NVME_CAP_MPSMIN(cap) + 12;
- if (ctrl->vs >= NVME_VS(1, 1))
+ if (ctrl->vs >= NVME_VS(1, 1, 0))
ctrl->subsystem = NVME_CAP_NSSRC(cap);
ret = nvme_identify_ctrl(ctrl, &id);
@@ -1840,7 +1842,7 @@ static void nvme_scan_work(struct work_struct *work)
return;
nn = le32_to_cpu(id->nn);
- if (ctrl->vs >= NVME_VS(1, 1) &&
+ if (ctrl->vs >= NVME_VS(1, 1, 0) &&
!(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) {
if (!nvme_scan_ns_list(ctrl, nn))
goto done;
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index f5e3011..5daf2f4 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -612,7 +612,7 @@ int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node,
ret = nvm_register(dev);
- ns->lba_shift = ilog2(dev->sec_size) - 9;
+ ns->lba_shift = ilog2(dev->sec_size);
if (sysfs_create_group(&dev->dev.kobj, attrs))
pr_warn("%s: failed to create sysfs group for identification\n",
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 0fc99f0..0248d0e 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -99,6 +99,7 @@ struct nvme_dev {
dma_addr_t cmb_dma_addr;
u64 cmb_size;
u32 cmbsz;
+ u32 cmbloc;
struct nvme_ctrl ctrl;
struct completion ioq_wait;
};
@@ -893,7 +894,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
"I/O %d QID %d timeout, reset controller\n",
req->tag, nvmeq->qid);
nvme_dev_disable(dev, false);
- queue_work(nvme_workq, &dev->reset_work);
+ nvme_reset(dev);
/*
* Mark the request as handled, since the inline shutdown
@@ -1214,7 +1215,7 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
u64 cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
struct nvme_queue *nvmeq;
- dev->subsystem = readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 1) ?
+ dev->subsystem = readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 1, 0) ?
NVME_CAP_NSSRC(cap) : 0;
if (dev->subsystem &&
@@ -1291,7 +1292,7 @@ static void nvme_watchdog_timer(unsigned long data)
/* Skip controllers under certain specific conditions. */
if (nvme_should_reset(dev, csts)) {
- if (queue_work(nvme_workq, &dev->reset_work))
+ if (!nvme_reset(dev))
dev_warn(dev->dev,
"Failed status: 0x%x, reset controller.\n",
csts);
@@ -1331,28 +1332,37 @@ static int nvme_create_io_queues(struct nvme_dev *dev)
return ret >= 0 ? 0 : ret;
}
+static ssize_t nvme_cmb_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
+
+ return snprintf(buf, PAGE_SIZE, "cmbloc : x%08x\ncmbsz : x%08x\n",
+ ndev->cmbloc, ndev->cmbsz);
+}
+static DEVICE_ATTR(cmb, S_IRUGO, nvme_cmb_show, NULL);
+
static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
{
u64 szu, size, offset;
- u32 cmbloc;
resource_size_t bar_size;
struct pci_dev *pdev = to_pci_dev(dev->dev);
void __iomem *cmb;
dma_addr_t dma_addr;
- if (!use_cmb_sqes)
- return NULL;
-
dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ);
if (!(NVME_CMB_SZ(dev->cmbsz)))
return NULL;
+ dev->cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
- cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
+ if (!use_cmb_sqes)
+ return NULL;
szu = (u64)1 << (12 + 4 * NVME_CMB_SZU(dev->cmbsz));
size = szu * NVME_CMB_SZ(dev->cmbsz);
- offset = szu * NVME_CMB_OFST(cmbloc);
- bar_size = pci_resource_len(pdev, NVME_CMB_BIR(cmbloc));
+ offset = szu * NVME_CMB_OFST(dev->cmbloc);
+ bar_size = pci_resource_len(pdev, NVME_CMB_BIR(dev->cmbloc));
if (offset > bar_size)
return NULL;
@@ -1365,7 +1375,7 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
if (size > bar_size - offset)
size = bar_size - offset;
- dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(cmbloc)) + offset;
+ dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(dev->cmbloc)) + offset;
cmb = ioremap_wc(dma_addr, size);
if (!cmb)
return NULL;
@@ -1511,9 +1521,9 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
return 0;
}
-static void nvme_disable_io_queues(struct nvme_dev *dev)
+static void nvme_disable_io_queues(struct nvme_dev *dev, int queues)
{
- int pass, queues = dev->online_queues - 1;
+ int pass;
unsigned long timeout;
u8 opcode = nvme_admin_delete_sq;
@@ -1616,9 +1626,25 @@ static int nvme_pci_enable(struct nvme_dev *dev)
dev->q_depth);
}
- if (readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 2))
+ /*
+ * CMBs can currently only exist on >=1.2 PCIe devices. We only
+ * populate sysfs if a CMB is implemented. Note that we add the
+ * CMB attribute to the nvme_ctrl kobj which removes the need to remove
+ * it on exit. Since nvme_dev_attrs_group has no name we can pass
+ * NULL as final argument to sysfs_add_file_to_group.
+ */
+
+ if (readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 2, 0)) {
dev->cmb = nvme_map_cmb(dev);
+ if (dev->cmbsz) {
+ if (sysfs_add_file_to_group(&dev->ctrl.device->kobj,
+ &dev_attr_cmb.attr, NULL))
+ dev_warn(dev->dev,
+ "failed to add sysfs attribute for CMB\n");
+ }
+ }
+
pci_enable_pcie_error_reporting(pdev);
pci_save_state(pdev);
return 0;
@@ -1649,7 +1675,7 @@ static void nvme_pci_disable(struct nvme_dev *dev)
static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
{
- int i;
+ int i, queues;
u32 csts = -1;
del_timer_sync(&dev->watchdog_timer);
@@ -1660,6 +1686,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
csts = readl(dev->bar + NVME_REG_CSTS);
}
+ queues = dev->online_queues - 1;
for (i = dev->queue_count - 1; i > 0; i--)
nvme_suspend_queue(dev->queues[i]);
@@ -1671,7 +1698,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
if (dev->queue_count)
nvme_suspend_queue(dev->queues[0]);
} else {
- nvme_disable_io_queues(dev);
+ nvme_disable_io_queues(dev, queues);
nvme_disable_admin_queue(dev, shutdown);
}
nvme_pci_disable(dev);
@@ -1818,11 +1845,10 @@ static int nvme_reset(struct nvme_dev *dev)
{
if (!dev->ctrl.admin_q || blk_queue_dying(dev->ctrl.admin_q))
return -ENODEV;
-
+ if (work_busy(&dev->reset_work))
+ return -ENODEV;
if (!queue_work(nvme_workq, &dev->reset_work))
return -EBUSY;
-
- flush_work(&dev->reset_work);
return 0;
}
@@ -1846,7 +1872,12 @@ static int nvme_pci_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
static int nvme_pci_reset_ctrl(struct nvme_ctrl *ctrl)
{
- return nvme_reset(to_nvme_dev(ctrl));
+ struct nvme_dev *dev = to_nvme_dev(ctrl);
+ int ret = nvme_reset(dev);
+
+ if (!ret)
+ flush_work(&dev->reset_work);
+ return ret;
}
static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
@@ -1940,7 +1971,7 @@ static void nvme_reset_notify(struct pci_dev *pdev, bool prepare)
if (prepare)
nvme_dev_disable(dev, false);
else
- queue_work(nvme_workq, &dev->reset_work);
+ nvme_reset(dev);
}
static void nvme_shutdown(struct pci_dev *pdev)
@@ -2009,7 +2040,7 @@ static int nvme_resume(struct device *dev)
struct pci_dev *pdev = to_pci_dev(dev);
struct nvme_dev *ndev = pci_get_drvdata(pdev);
- queue_work(nvme_workq, &ndev->reset_work);
+ nvme_reset(ndev);
return 0;
}
#endif
@@ -2048,7 +2079,7 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
dev_info(dev->ctrl.device, "restart after slot reset\n");
pci_restore_state(pdev);
- queue_work(nvme_workq, &dev->reset_work);
+ nvme_reset(dev);
return PCI_ERS_RESULT_RECOVERED;
}
diff --git a/drivers/nvme/host/scsi.c b/drivers/nvme/host/scsi.c
index c2a0a1c7..3eaa4d2 100644
--- a/drivers/nvme/host/scsi.c
+++ b/drivers/nvme/host/scsi.c
@@ -606,7 +606,7 @@ static int nvme_fill_device_id_eui64(struct nvme_ns *ns, struct sg_io_hdr *hdr,
eui = id_ns->eui64;
len = sizeof(id_ns->eui64);
- if (ns->ctrl->vs >= NVME_VS(1, 2)) {
+ if (ns->ctrl->vs >= NVME_VS(1, 2, 0)) {
if (bitmap_empty(eui, len * 8)) {
eui = id_ns->nguid;
len = sizeof(id_ns->nguid);
@@ -679,7 +679,7 @@ static int nvme_trans_device_id_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
{
int res;
- if (ns->ctrl->vs >= NVME_VS(1, 1)) {
+ if (ns->ctrl->vs >= NVME_VS(1, 1, 0)) {
res = nvme_fill_device_id_eui64(ns, hdr, resp, alloc_len);
if (res != -EOPNOTSUPP)
return res;
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 7ab9c93..6fe4c48 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -199,7 +199,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
*/
/* we support multiple ports and multiples hosts: */
- id->mic = (1 << 0) | (1 << 1);
+ id->cmic = (1 << 0) | (1 << 1);
/* no limit on data transfer sizes for now */
id->mdts = 0;
@@ -511,13 +511,13 @@ int nvmet_parse_admin_cmd(struct nvmet_req *req)
case nvme_admin_identify:
req->data_len = 4096;
switch (le32_to_cpu(cmd->identify.cns)) {
- case 0x00:
+ case NVME_ID_CNS_NS:
req->execute = nvmet_execute_identify_ns;
return 0;
- case 0x01:
+ case NVME_ID_CNS_CTRL:
req->execute = nvmet_execute_identify_ctrl;
return 0;
- case 0x02:
+ case NVME_ID_CNS_NS_ACTIVE_LIST:
req->execute = nvmet_execute_identify_nslist;
return 0;
}
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 6559d5a..b4cacb6 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -882,7 +882,7 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
if (!subsys)
return NULL;
- subsys->ver = (1 << 16) | (2 << 8) | 1; /* NVMe 1.2.1 */
+ subsys->ver = NVME_VS(1, 2, 1); /* NVMe 1.2.1 */
switch (type) {
case NVME_NQN_NVME:
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 6f65646..12f39ee 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -54,7 +54,7 @@ static void nvmet_format_discovery_entry(struct nvmf_disc_rsp_page_hdr *hdr,
/* we support only dynamic controllers */
e->cntlid = cpu_to_le16(NVME_CNTLID_DYNAMIC);
e->asqsz = cpu_to_le16(NVMF_AQ_DEPTH);
- e->nqntype = type;
+ e->subtype = type;
memcpy(e->trsvcid, port->disc_addr.trsvcid, NVMF_TRSVCID_SIZE);
memcpy(e->traddr, port->disc_addr.traddr, NVMF_TRADDR_SIZE);
memcpy(e->tsas.common, port->disc_addr.tsas.common, NVMF_TSAS_SIZE);
@@ -187,7 +187,7 @@ int nvmet_parse_discovery_cmd(struct nvmet_req *req)
case nvme_admin_identify:
req->data_len = 4096;
switch (le32_to_cpu(cmd->identify.cns)) {
- case 0x01:
+ case NVME_ID_CNS_CTRL:
req->execute =
nvmet_execute_identify_disc_ctrl;
return 0;
diff --git a/drivers/of/base.c b/drivers/of/base.c
index d687e6d..a0bccb5 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -2077,8 +2077,6 @@ void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align))
name = of_get_property(of_aliases, "stdout", NULL);
if (name)
of_stdout = of_find_node_opts_by_path(name, &of_stdout_options);
- if (of_stdout)
- console_set_by_of();
}
if (!of_aliases)
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index f811d27..e4bf07d 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -29,6 +29,7 @@
const struct of_device_id of_default_bus_match_table[] = {
{ .compatible = "simple-bus", },
{ .compatible = "simple-mfd", },
+ { .compatible = "isa", },
#ifdef CONFIG_ARM_AMBA
{ .compatible = "arm,amba-bus", },
#endif /* CONFIG_ARM_AMBA */
diff --git a/drivers/pci/host/pci-layerscape.c b/drivers/pci/host/pci-layerscape.c
index 2cb7315..6537079 100644
--- a/drivers/pci/host/pci-layerscape.c
+++ b/drivers/pci/host/pci-layerscape.c
@@ -247,6 +247,7 @@ static int __init ls_pcie_probe(struct platform_device *pdev)
pp = &pcie->pp;
pp->dev = dev;
+ pcie->drvdata = match->data;
pp->ops = pcie->drvdata->ops;
dbi_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs");
@@ -256,7 +257,6 @@ static int __init ls_pcie_probe(struct platform_device *pdev)
return PTR_ERR(pcie->pp.dbi_base);
}
- pcie->drvdata = match->data;
pcie->lut = pcie->pp.dbi_base + pcie->drvdata->lut_offset;
if (!ls_pcie_is_bridge(pcie))
diff --git a/drivers/pci/host/pcie-designware-plat.c b/drivers/pci/host/pcie-designware-plat.c
index 537f58a..8df6312 100644
--- a/drivers/pci/host/pcie-designware-plat.c
+++ b/drivers/pci/host/pcie-designware-plat.c
@@ -3,7 +3,7 @@
*
* Copyright (C) 2015-2016 Synopsys, Inc. (www.synopsys.com)
*
- * Authors: Joao Pinto <jpinto@synopsys.com>
+ * Authors: Joao Pinto <jpmpinto@gmail.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index 035f50c..bed1999 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -637,8 +637,6 @@ int dw_pcie_host_init(struct pcie_port *pp)
}
}
- pp->iatu_unroll_enabled = dw_pcie_iatu_unroll_enabled(pp);
-
if (pp->ops->host_init)
pp->ops->host_init(pp);
@@ -809,6 +807,11 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
{
u32 val;
+ /* get iATU unroll support */
+ pp->iatu_unroll_enabled = dw_pcie_iatu_unroll_enabled(pp);
+ dev_dbg(pp->dev, "iATU unroll: %s\n",
+ pp->iatu_unroll_enabled ? "enabled" : "disabled");
+
/* set the number of lanes */
val = dw_pcie_readl_rc(pp, PCIE_PORT_LINK_CONTROL);
val &= ~PORT_LINK_MODE_MASK;
diff --git a/drivers/pci/host/pcie-qcom.c b/drivers/pci/host/pcie-qcom.c
index ef0a84c..3593640 100644
--- a/drivers/pci/host/pcie-qcom.c
+++ b/drivers/pci/host/pcie-qcom.c
@@ -533,11 +533,11 @@ static int qcom_pcie_probe(struct platform_device *pdev)
if (IS_ERR(pcie->phy))
return PTR_ERR(pcie->phy);
+ pp->dev = dev;
ret = pcie->ops->get_resources(pcie);
if (ret)
return ret;
- pp->dev = dev;
pp->root_bus_nr = -1;
pp->ops = &qcom_pcie_dw_ops;
diff --git a/drivers/pci/host/pcie-rockchip.c b/drivers/pci/host/pcie-rockchip.c
index e0b22da..e04f69b 100644
--- a/drivers/pci/host/pcie-rockchip.c
+++ b/drivers/pci/host/pcie-rockchip.c
@@ -190,6 +190,9 @@ struct rockchip_pcie {
struct reset_control *mgmt_rst;
struct reset_control *mgmt_sticky_rst;
struct reset_control *pipe_rst;
+ struct reset_control *pm_rst;
+ struct reset_control *aclk_rst;
+ struct reset_control *pclk_rst;
struct clk *aclk_pcie;
struct clk *aclk_perf_pcie;
struct clk *hclk_pcie;
@@ -408,6 +411,44 @@ static int rockchip_pcie_init_port(struct rockchip_pcie *rockchip)
gpiod_set_value(rockchip->ep_gpio, 0);
+ err = reset_control_assert(rockchip->aclk_rst);
+ if (err) {
+ dev_err(dev, "assert aclk_rst err %d\n", err);
+ return err;
+ }
+
+ err = reset_control_assert(rockchip->pclk_rst);
+ if (err) {
+ dev_err(dev, "assert pclk_rst err %d\n", err);
+ return err;
+ }
+
+ err = reset_control_assert(rockchip->pm_rst);
+ if (err) {
+ dev_err(dev, "assert pm_rst err %d\n", err);
+ return err;
+ }
+
+ udelay(10);
+
+ err = reset_control_deassert(rockchip->pm_rst);
+ if (err) {
+ dev_err(dev, "deassert pm_rst err %d\n", err);
+ return err;
+ }
+
+ err = reset_control_deassert(rockchip->aclk_rst);
+ if (err) {
+ dev_err(dev, "deassert mgmt_sticky_rst err %d\n", err);
+ return err;
+ }
+
+ err = reset_control_deassert(rockchip->pclk_rst);
+ if (err) {
+ dev_err(dev, "deassert mgmt_sticky_rst err %d\n", err);
+ return err;
+ }
+
err = phy_init(rockchip->phy);
if (err < 0) {
dev_err(dev, "fail to init phy, err %d\n", err);
@@ -781,6 +822,27 @@ static int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip)
return PTR_ERR(rockchip->pipe_rst);
}
+ rockchip->pm_rst = devm_reset_control_get(dev, "pm");
+ if (IS_ERR(rockchip->pm_rst)) {
+ if (PTR_ERR(rockchip->pm_rst) != -EPROBE_DEFER)
+ dev_err(dev, "missing pm reset property in node\n");
+ return PTR_ERR(rockchip->pm_rst);
+ }
+
+ rockchip->pclk_rst = devm_reset_control_get(dev, "pclk");
+ if (IS_ERR(rockchip->pclk_rst)) {
+ if (PTR_ERR(rockchip->pclk_rst) != -EPROBE_DEFER)
+ dev_err(dev, "missing pclk reset property in node\n");
+ return PTR_ERR(rockchip->pclk_rst);
+ }
+
+ rockchip->aclk_rst = devm_reset_control_get(dev, "aclk");
+ if (IS_ERR(rockchip->aclk_rst)) {
+ if (PTR_ERR(rockchip->aclk_rst) != -EPROBE_DEFER)
+ dev_err(dev, "missing aclk reset property in node\n");
+ return PTR_ERR(rockchip->aclk_rst);
+ }
+
rockchip->ep_gpio = devm_gpiod_get(dev, "ep", GPIOD_OUT_HIGH);
if (IS_ERR(rockchip->ep_gpio)) {
dev_err(dev, "missing ep-gpios property in node\n");
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index bfdd074..ad70507 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -610,6 +610,7 @@ static int msi_verify_entries(struct pci_dev *dev)
* msi_capability_init - configure device's MSI capability structure
* @dev: pointer to the pci_dev data structure of MSI device function
* @nvec: number of interrupts to allocate
+ * @affinity: flag to indicate cpu irq affinity mask should be set
*
* Setup the MSI capability structure of the device with the requested
* number of interrupts. A return value of zero indicates the successful
@@ -752,6 +753,7 @@ static void msix_program_entries(struct pci_dev *dev,
* @dev: pointer to the pci_dev data structure of MSI-X device function
* @entries: pointer to an array of struct msix_entry entries
* @nvec: number of @entries
+ * @affinity: flag to indicate cpu irq affinity mask should be set
*
* Setup the MSI-X capability structure of device function with a
* single MSI-X irq. A return of zero indicates the successful setup of
diff --git a/drivers/pci/pci-mid.c b/drivers/pci/pci-mid.c
index 55f453d..c7f3408 100644
--- a/drivers/pci/pci-mid.c
+++ b/drivers/pci/pci-mid.c
@@ -29,6 +29,11 @@ static int mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state)
return intel_mid_pci_set_power_state(pdev, state);
}
+static pci_power_t mid_pci_get_power_state(struct pci_dev *pdev)
+{
+ return intel_mid_pci_get_power_state(pdev);
+}
+
static pci_power_t mid_pci_choose_state(struct pci_dev *pdev)
{
return PCI_D3hot;
@@ -52,6 +57,7 @@ static bool mid_pci_need_resume(struct pci_dev *dev)
static struct pci_platform_pm_ops mid_pci_platform_pm = {
.is_manageable = mid_pci_power_manageable,
.set_state = mid_pci_set_power_state,
+ .get_state = mid_pci_get_power_state,
.choose_state = mid_pci_choose_state,
.sleep_wake = mid_pci_sleep_wake,
.run_wake = mid_pci_run_wake,
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index 66c4d8f..9526e34 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -121,6 +121,14 @@ int pci_claim_resource(struct pci_dev *dev, int resource)
return -EINVAL;
}
+ /*
+ * If we have a shadow copy in RAM, the PCI device doesn't respond
+ * to the shadow range, so we don't need to claim it, and upstream
+ * bridges don't need to route the range to the device.
+ */
+ if (res->flags & IORESOURCE_ROM_SHADOW)
+ return 0;
+
root = pci_find_parent_resource(dev, res);
if (!root) {
dev_info(&dev->dev, "can't claim BAR %d %pR: no compatible bridge window\n",
diff --git a/drivers/pcmcia/soc_common.c b/drivers/pcmcia/soc_common.c
index 153f312..b6b316d 100644
--- a/drivers/pcmcia/soc_common.c
+++ b/drivers/pcmcia/soc_common.c
@@ -107,7 +107,7 @@ int soc_pcmcia_regulator_set(struct soc_pcmcia_socket *skt,
ret = regulator_enable(r->reg);
} else {
- regulator_disable(r->reg);
+ ret = regulator_disable(r->reg);
}
if (ret == 0)
r->on = on;
diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index c2ac764..a8ac4bc 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -1011,7 +1011,7 @@ xgene_pmu_dev_ctx *acpi_get_pmu_hw_inf(struct xgene_pmu *xgene_pmu,
rc = acpi_dev_get_resources(adev, &resource_list,
acpi_pmu_dev_add_resource, &res);
acpi_dev_free_resource_list(&resource_list);
- if (rc < 0 || IS_ERR(&res)) {
+ if (rc < 0) {
dev_err(dev, "PMU type %d: No resource address found\n", type);
goto err;
}
diff --git a/drivers/phy/phy-da8xx-usb.c b/drivers/phy/phy-da8xx-usb.c
index 32ae78c..c85fb0b 100644
--- a/drivers/phy/phy-da8xx-usb.c
+++ b/drivers/phy/phy-da8xx-usb.c
@@ -198,7 +198,8 @@ static int da8xx_usb_phy_probe(struct platform_device *pdev)
} else {
int ret;
- ret = phy_create_lookup(d_phy->usb11_phy, "usb-phy", "ohci.0");
+ ret = phy_create_lookup(d_phy->usb11_phy, "usb-phy",
+ "ohci-da8xx");
if (ret)
dev_warn(dev, "Failed to create usb11 phy lookup\n");
ret = phy_create_lookup(d_phy->usb20_phy, "usb-phy",
@@ -216,7 +217,7 @@ static int da8xx_usb_phy_remove(struct platform_device *pdev)
if (!pdev->dev.of_node) {
phy_remove_lookup(d_phy->usb20_phy, "usb-phy", "musb-da8xx");
- phy_remove_lookup(d_phy->usb11_phy, "usb-phy", "ohci.0");
+ phy_remove_lookup(d_phy->usb11_phy, "usb-phy", "ohci-da8xx");
}
return 0;
diff --git a/drivers/phy/phy-rockchip-pcie.c b/drivers/phy/phy-rockchip-pcie.c
index a2b4c6b..6904633 100644
--- a/drivers/phy/phy-rockchip-pcie.c
+++ b/drivers/phy/phy-rockchip-pcie.c
@@ -249,21 +249,10 @@ static int rockchip_pcie_phy_init(struct phy *phy)
static int rockchip_pcie_phy_exit(struct phy *phy)
{
struct rockchip_pcie_phy *rk_phy = phy_get_drvdata(phy);
- int err = 0;
clk_disable_unprepare(rk_phy->clk_pciephy_ref);
- err = reset_control_deassert(rk_phy->phy_rst);
- if (err) {
- dev_err(&phy->dev, "deassert phy_rst err %d\n", err);
- goto err_reset;
- }
-
- return err;
-
-err_reset:
- clk_prepare_enable(rk_phy->clk_pciephy_ref);
- return err;
+ return 0;
}
static const struct phy_ops ops = {
diff --git a/drivers/phy/phy-sun4i-usb.c b/drivers/phy/phy-sun4i-usb.c
index b9342a2..fec34f5 100644
--- a/drivers/phy/phy-sun4i-usb.c
+++ b/drivers/phy/phy-sun4i-usb.c
@@ -264,7 +264,7 @@ static int sun4i_usb_phy_init(struct phy *_phy)
return ret;
}
- if (data->cfg->enable_pmu_unk1) {
+ if (phy->pmu && data->cfg->enable_pmu_unk1) {
val = readl(phy->pmu + REG_PMU_UNK1);
writel(val & ~2, phy->pmu + REG_PMU_UNK1);
}
diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g5.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g5.c
index e1ab864..87b4639 100644
--- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g5.c
+++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g5.c
@@ -26,7 +26,7 @@
#define ASPEED_G5_NR_PINS 228
-#define COND1 SIG_DESC_BIT(SCU90, 6, 0)
+#define COND1 { SCU90, BIT(6), 0, 0 }
#define COND2 { SCU94, GENMASK(1, 0), 0, 0 }
#define B14 0
@@ -151,21 +151,21 @@ FUNC_GROUP_DECL(GPID0, F19, E21);
#define GPID2_DESC SIG_DESC_SET(SCU8C, 9)
-#define D20 26
+#define F20 26
SIG_EXPR_LIST_DECL_SINGLE(SD2DAT0, SD2, SD2_DESC);
SIG_EXPR_DECL(GPID2IN, GPID2, GPID2_DESC);
SIG_EXPR_DECL(GPID2IN, GPID, GPID_DESC);
SIG_EXPR_LIST_DECL_DUAL(GPID2IN, GPID2, GPID);
-MS_PIN_DECL(D20, GPIOD2, SD2DAT0, GPID2IN);
+MS_PIN_DECL(F20, GPIOD2, SD2DAT0, GPID2IN);
-#define D21 27
+#define D20 27
SIG_EXPR_LIST_DECL_SINGLE(SD2DAT1, SD2, SD2_DESC);
SIG_EXPR_DECL(GPID2OUT, GPID2, GPID2_DESC);
SIG_EXPR_DECL(GPID2OUT, GPID, GPID_DESC);
SIG_EXPR_LIST_DECL_DUAL(GPID2OUT, GPID2, GPID);
-MS_PIN_DECL(D21, GPIOD3, SD2DAT1, GPID2OUT);
+MS_PIN_DECL(D20, GPIOD3, SD2DAT1, GPID2OUT);
-FUNC_GROUP_DECL(GPID2, D20, D21);
+FUNC_GROUP_DECL(GPID2, F20, D20);
#define GPIE_DESC SIG_DESC_SET(HW_STRAP1, 21)
#define GPIE0_DESC SIG_DESC_SET(SCU8C, 12)
@@ -182,28 +182,88 @@ SIG_EXPR_LIST_DECL_SINGLE(NDCD3, NDCD3, SIG_DESC_SET(SCU80, 17));
SIG_EXPR_DECL(GPIE0OUT, GPIE0, GPIE0_DESC);
SIG_EXPR_DECL(GPIE0OUT, GPIE, GPIE_DESC);
SIG_EXPR_LIST_DECL_DUAL(GPIE0OUT, GPIE0, GPIE);
-MS_PIN_DECL(C20, GPIE0, NDCD3, GPIE0OUT);
+MS_PIN_DECL(C20, GPIOE1, NDCD3, GPIE0OUT);
FUNC_GROUP_DECL(GPIE0, B20, C20);
-#define SPI1_DESC SIG_DESC_SET(HW_STRAP1, 13)
+#define SPI1_DESC { HW_STRAP1, GENMASK(13, 12), 1, 0 }
+#define SPI1DEBUG_DESC { HW_STRAP1, GENMASK(13, 12), 2, 0 }
+#define SPI1PASSTHRU_DESC { HW_STRAP1, GENMASK(13, 12), 3, 0 }
+
#define C18 64
-SIG_EXPR_LIST_DECL_SINGLE(SYSCS, SPI1, COND1, SPI1_DESC);
+SIG_EXPR_DECL(SYSCS, SPI1DEBUG, COND1, SPI1DEBUG_DESC);
+SIG_EXPR_DECL(SYSCS, SPI1PASSTHRU, COND1, SPI1PASSTHRU_DESC);
+SIG_EXPR_LIST_DECL_DUAL(SYSCS, SPI1DEBUG, SPI1PASSTHRU);
SS_PIN_DECL(C18, GPIOI0, SYSCS);
#define E15 65
-SIG_EXPR_LIST_DECL_SINGLE(SYSCK, SPI1, COND1, SPI1_DESC);
+SIG_EXPR_DECL(SYSCK, SPI1DEBUG, COND1, SPI1DEBUG_DESC);
+SIG_EXPR_DECL(SYSCK, SPI1PASSTHRU, COND1, SPI1PASSTHRU_DESC);
+SIG_EXPR_LIST_DECL_DUAL(SYSCK, SPI1DEBUG, SPI1PASSTHRU);
SS_PIN_DECL(E15, GPIOI1, SYSCK);
-#define A14 66
-SIG_EXPR_LIST_DECL_SINGLE(SYSMOSI, SPI1, COND1, SPI1_DESC);
-SS_PIN_DECL(A14, GPIOI2, SYSMOSI);
+#define B16 66
+SIG_EXPR_DECL(SYSMOSI, SPI1DEBUG, COND1, SPI1DEBUG_DESC);
+SIG_EXPR_DECL(SYSMOSI, SPI1PASSTHRU, COND1, SPI1PASSTHRU_DESC);
+SIG_EXPR_LIST_DECL_DUAL(SYSMOSI, SPI1DEBUG, SPI1PASSTHRU);
+SS_PIN_DECL(B16, GPIOI2, SYSMOSI);
#define C16 67
-SIG_EXPR_LIST_DECL_SINGLE(SYSMISO, SPI1, COND1, SPI1_DESC);
+SIG_EXPR_DECL(SYSMISO, SPI1DEBUG, COND1, SPI1DEBUG_DESC);
+SIG_EXPR_DECL(SYSMISO, SPI1PASSTHRU, COND1, SPI1PASSTHRU_DESC);
+SIG_EXPR_LIST_DECL_DUAL(SYSMISO, SPI1DEBUG, SPI1PASSTHRU);
SS_PIN_DECL(C16, GPIOI3, SYSMISO);
-FUNC_GROUP_DECL(SPI1, C18, E15, A14, C16);
+#define VB_DESC SIG_DESC_SET(HW_STRAP1, 5)
+
+#define B15 68
+SIG_EXPR_DECL(SPI1CS0, SPI1, COND1, SPI1_DESC);
+SIG_EXPR_DECL(SPI1CS0, SPI1DEBUG, COND1, SPI1DEBUG_DESC);
+SIG_EXPR_DECL(SPI1CS0, SPI1PASSTHRU, COND1, SPI1PASSTHRU_DESC);
+SIG_EXPR_LIST_DECL(SPI1CS0, SIG_EXPR_PTR(SPI1CS0, SPI1),
+ SIG_EXPR_PTR(SPI1CS0, SPI1DEBUG),
+ SIG_EXPR_PTR(SPI1CS0, SPI1PASSTHRU));
+SIG_EXPR_LIST_DECL_SINGLE(VBCS, VGABIOSROM, COND1, VB_DESC);
+MS_PIN_DECL(B15, GPIOI4, SPI1CS0, VBCS);
+
+#define C15 69
+SIG_EXPR_DECL(SPI1CK, SPI1, COND1, SPI1_DESC);
+SIG_EXPR_DECL(SPI1CK, SPI1DEBUG, COND1, SPI1DEBUG_DESC);
+SIG_EXPR_DECL(SPI1CK, SPI1PASSTHRU, COND1, SPI1PASSTHRU_DESC);
+SIG_EXPR_LIST_DECL(SPI1CK, SIG_EXPR_PTR(SPI1CK, SPI1),
+ SIG_EXPR_PTR(SPI1CK, SPI1DEBUG),
+ SIG_EXPR_PTR(SPI1CK, SPI1PASSTHRU));
+SIG_EXPR_LIST_DECL_SINGLE(VBCK, VGABIOSROM, COND1, VB_DESC);
+MS_PIN_DECL(C15, GPIOI5, SPI1CK, VBCK);
+
+#define A14 70
+SIG_EXPR_DECL(SPI1MOSI, SPI1, COND1, SPI1_DESC);
+SIG_EXPR_DECL(SPI1MOSI, SPI1DEBUG, COND1, SPI1DEBUG_DESC);
+SIG_EXPR_DECL(SPI1MOSI, SPI1PASSTHRU, COND1, SPI1PASSTHRU_DESC);
+SIG_EXPR_LIST_DECL(SPI1MOSI, SIG_EXPR_PTR(SPI1MOSI, SPI1),
+ SIG_EXPR_PTR(SPI1MOSI, SPI1DEBUG),
+ SIG_EXPR_PTR(SPI1MOSI, SPI1PASSTHRU));
+SIG_EXPR_LIST_DECL_SINGLE(VBMOSI, VGABIOSROM, COND1, VB_DESC);
+MS_PIN_DECL(A14, GPIOI6, SPI1MOSI, VBMOSI);
+
+#define A15 71
+SIG_EXPR_DECL(SPI1MISO, SPI1, COND1, SPI1_DESC);
+SIG_EXPR_DECL(SPI1MISO, SPI1DEBUG, COND1, SPI1DEBUG_DESC);
+SIG_EXPR_DECL(SPI1MISO, SPI1PASSTHRU, COND1, SPI1PASSTHRU_DESC);
+SIG_EXPR_LIST_DECL(SPI1MISO, SIG_EXPR_PTR(SPI1MISO, SPI1),
+ SIG_EXPR_PTR(SPI1MISO, SPI1DEBUG),
+ SIG_EXPR_PTR(SPI1MISO, SPI1PASSTHRU));
+SIG_EXPR_LIST_DECL_SINGLE(VBMISO, VGABIOSROM, COND1, VB_DESC);
+MS_PIN_DECL(A15, GPIOI7, SPI1MISO, VBMISO);
+
+FUNC_GROUP_DECL(SPI1, B15, C15, A14, A15);
+FUNC_GROUP_DECL(SPI1DEBUG, C18, E15, B16, C16, B15, C15, A14, A15);
+FUNC_GROUP_DECL(SPI1PASSTHRU, C18, E15, B16, C16, B15, C15, A14, A15);
+FUNC_GROUP_DECL(VGABIOSROM, B15, C15, A14, A15);
+
+#define R2 72
+SIG_EXPR_LIST_DECL_SINGLE(SGPMCK, SGPM, SIG_DESC_SET(SCU84, 8));
+SS_PIN_DECL(R2, GPIOJ0, SGPMCK);
#define L2 73
SIG_EXPR_LIST_DECL_SINGLE(SGPMLD, SGPM, SIG_DESC_SET(SCU84, 9));
@@ -580,6 +640,7 @@ static struct pinctrl_pin_desc aspeed_g5_pins[ASPEED_G5_NR_PINS] = {
ASPEED_PINCTRL_PIN(A12),
ASPEED_PINCTRL_PIN(A13),
ASPEED_PINCTRL_PIN(A14),
+ ASPEED_PINCTRL_PIN(A15),
ASPEED_PINCTRL_PIN(A2),
ASPEED_PINCTRL_PIN(A3),
ASPEED_PINCTRL_PIN(A4),
@@ -592,6 +653,8 @@ static struct pinctrl_pin_desc aspeed_g5_pins[ASPEED_G5_NR_PINS] = {
ASPEED_PINCTRL_PIN(B12),
ASPEED_PINCTRL_PIN(B13),
ASPEED_PINCTRL_PIN(B14),
+ ASPEED_PINCTRL_PIN(B15),
+ ASPEED_PINCTRL_PIN(B16),
ASPEED_PINCTRL_PIN(B2),
ASPEED_PINCTRL_PIN(B20),
ASPEED_PINCTRL_PIN(B3),
@@ -603,6 +666,7 @@ static struct pinctrl_pin_desc aspeed_g5_pins[ASPEED_G5_NR_PINS] = {
ASPEED_PINCTRL_PIN(C12),
ASPEED_PINCTRL_PIN(C13),
ASPEED_PINCTRL_PIN(C14),
+ ASPEED_PINCTRL_PIN(C15),
ASPEED_PINCTRL_PIN(C16),
ASPEED_PINCTRL_PIN(C18),
ASPEED_PINCTRL_PIN(C2),
@@ -614,7 +678,6 @@ static struct pinctrl_pin_desc aspeed_g5_pins[ASPEED_G5_NR_PINS] = {
ASPEED_PINCTRL_PIN(D10),
ASPEED_PINCTRL_PIN(D2),
ASPEED_PINCTRL_PIN(D20),
- ASPEED_PINCTRL_PIN(D21),
ASPEED_PINCTRL_PIN(D4),
ASPEED_PINCTRL_PIN(D5),
ASPEED_PINCTRL_PIN(D6),
@@ -630,6 +693,7 @@ static struct pinctrl_pin_desc aspeed_g5_pins[ASPEED_G5_NR_PINS] = {
ASPEED_PINCTRL_PIN(E7),
ASPEED_PINCTRL_PIN(E9),
ASPEED_PINCTRL_PIN(F19),
+ ASPEED_PINCTRL_PIN(F20),
ASPEED_PINCTRL_PIN(F9),
ASPEED_PINCTRL_PIN(H20),
ASPEED_PINCTRL_PIN(L1),
@@ -691,11 +755,14 @@ static const struct aspeed_pin_group aspeed_g5_groups[] = {
ASPEED_PINCTRL_GROUP(RMII2),
ASPEED_PINCTRL_GROUP(SD1),
ASPEED_PINCTRL_GROUP(SPI1),
+ ASPEED_PINCTRL_GROUP(SPI1DEBUG),
+ ASPEED_PINCTRL_GROUP(SPI1PASSTHRU),
ASPEED_PINCTRL_GROUP(TIMER4),
ASPEED_PINCTRL_GROUP(TIMER5),
ASPEED_PINCTRL_GROUP(TIMER6),
ASPEED_PINCTRL_GROUP(TIMER7),
ASPEED_PINCTRL_GROUP(TIMER8),
+ ASPEED_PINCTRL_GROUP(VGABIOSROM),
};
static const struct aspeed_pin_function aspeed_g5_functions[] = {
@@ -733,11 +800,14 @@ static const struct aspeed_pin_function aspeed_g5_functions[] = {
ASPEED_PINCTRL_FUNC(RMII2),
ASPEED_PINCTRL_FUNC(SD1),
ASPEED_PINCTRL_FUNC(SPI1),
+ ASPEED_PINCTRL_FUNC(SPI1DEBUG),
+ ASPEED_PINCTRL_FUNC(SPI1PASSTHRU),
ASPEED_PINCTRL_FUNC(TIMER4),
ASPEED_PINCTRL_FUNC(TIMER5),
ASPEED_PINCTRL_FUNC(TIMER6),
ASPEED_PINCTRL_FUNC(TIMER7),
ASPEED_PINCTRL_FUNC(TIMER8),
+ ASPEED_PINCTRL_FUNC(VGABIOSROM),
};
static struct aspeed_pinctrl_data aspeed_g5_pinctrl_data = {
diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
index 0391f9f..49aeba9 100644
--- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c
+++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
@@ -166,13 +166,9 @@ static bool aspeed_sig_expr_set(const struct aspeed_sig_expr *expr,
bool enable, struct regmap *map)
{
int i;
- bool ret;
-
- ret = aspeed_sig_expr_eval(expr, enable, map);
- if (ret)
- return ret;
for (i = 0; i < expr->ndescs; i++) {
+ bool ret;
const struct aspeed_sig_desc *desc = &expr->descs[i];
u32 pattern = enable ? desc->enable : desc->disable;
@@ -199,12 +195,18 @@ static bool aspeed_sig_expr_set(const struct aspeed_sig_expr *expr,
static bool aspeed_sig_expr_enable(const struct aspeed_sig_expr *expr,
struct regmap *map)
{
+ if (aspeed_sig_expr_eval(expr, true, map))
+ return true;
+
return aspeed_sig_expr_set(expr, true, map);
}
static bool aspeed_sig_expr_disable(const struct aspeed_sig_expr *expr,
struct regmap *map)
{
+ if (!aspeed_sig_expr_eval(expr, true, map))
+ return true;
+
return aspeed_sig_expr_set(expr, false, map);
}
diff --git a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c
index 7f77007..5d1e505c3 100644
--- a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c
+++ b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c
@@ -844,6 +844,6 @@ static struct platform_driver iproc_gpio_driver = {
static int __init iproc_gpio_init(void)
{
- return platform_driver_probe(&iproc_gpio_driver, iproc_gpio_probe);
+ return platform_driver_register(&iproc_gpio_driver);
}
arch_initcall_sync(iproc_gpio_init);
diff --git a/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c
index 35783db..c8deb8b 100644
--- a/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c
+++ b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c
@@ -741,6 +741,6 @@ static struct platform_driver nsp_gpio_driver = {
static int __init nsp_gpio_init(void)
{
- return platform_driver_probe(&nsp_gpio_driver, nsp_gpio_probe);
+ return platform_driver_register(&nsp_gpio_driver);
}
arch_initcall_sync(nsp_gpio_init);
diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index 4761320..79c4e14 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -687,6 +687,7 @@ static int imx_pinctrl_probe_dt(struct platform_device *pdev,
if (!info->functions)
return -ENOMEM;
+ info->group_index = 0;
if (flat_funcs) {
info->ngroups = of_get_child_count(np);
} else {
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index d22a9fe..71bbeb9 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -1808,6 +1808,8 @@ static int byt_pinctrl_probe(struct platform_device *pdev)
return PTR_ERR(vg->pctl_dev);
}
+ raw_spin_lock_init(&vg->lock);
+
ret = byt_gpio_probe(vg);
if (ret) {
pinctrl_unregister(vg->pctl_dev);
@@ -1815,7 +1817,6 @@ static int byt_pinctrl_probe(struct platform_device *pdev)
}
platform_set_drvdata(pdev, vg);
- raw_spin_lock_init(&vg->lock);
pm_runtime_enable(&pdev->dev);
return 0;
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index 30389f4..c43b1e9 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1652,12 +1652,15 @@ static int chv_pinctrl_probe(struct platform_device *pdev)
}
#ifdef CONFIG_PM_SLEEP
-static int chv_pinctrl_suspend(struct device *dev)
+static int chv_pinctrl_suspend_noirq(struct device *dev)
{
struct platform_device *pdev = to_platform_device(dev);
struct chv_pinctrl *pctrl = platform_get_drvdata(pdev);
+ unsigned long flags;
int i;
+ raw_spin_lock_irqsave(&chv_lock, flags);
+
pctrl->saved_intmask = readl(pctrl->regs + CHV_INTMASK);
for (i = 0; i < pctrl->community->npins; i++) {
@@ -1678,15 +1681,20 @@ static int chv_pinctrl_suspend(struct device *dev)
ctx->padctrl1 = readl(reg);
}
+ raw_spin_unlock_irqrestore(&chv_lock, flags);
+
return 0;
}
-static int chv_pinctrl_resume(struct device *dev)
+static int chv_pinctrl_resume_noirq(struct device *dev)
{
struct platform_device *pdev = to_platform_device(dev);
struct chv_pinctrl *pctrl = platform_get_drvdata(pdev);
+ unsigned long flags;
int i;
+ raw_spin_lock_irqsave(&chv_lock, flags);
+
/*
* Mask all interrupts before restoring per-pin configuration
* registers because we don't know in which state BIOS left them
@@ -1731,12 +1739,15 @@ static int chv_pinctrl_resume(struct device *dev)
chv_writel(0xffff, pctrl->regs + CHV_INTSTAT);
chv_writel(pctrl->saved_intmask, pctrl->regs + CHV_INTMASK);
+ raw_spin_unlock_irqrestore(&chv_lock, flags);
+
return 0;
}
#endif
static const struct dev_pm_ops chv_pinctrl_pm_ops = {
- SET_LATE_SYSTEM_SLEEP_PM_OPS(chv_pinctrl_suspend, chv_pinctrl_resume)
+ SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(chv_pinctrl_suspend_noirq,
+ chv_pinctrl_resume_noirq)
};
static const struct acpi_device_id chv_pinctrl_acpi_match[] = {
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 63387a4..0144376 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -19,6 +19,7 @@
#include <linux/pinctrl/pinconf.h>
#include <linux/pinctrl/pinconf-generic.h>
+#include "../core.h"
#include "pinctrl-intel.h"
/* Offset from regs */
@@ -1056,6 +1057,26 @@ int intel_pinctrl_remove(struct platform_device *pdev)
EXPORT_SYMBOL_GPL(intel_pinctrl_remove);
#ifdef CONFIG_PM_SLEEP
+static bool intel_pinctrl_should_save(struct intel_pinctrl *pctrl, unsigned pin)
+{
+ const struct pin_desc *pd = pin_desc_get(pctrl->pctldev, pin);
+
+ if (!pd || !intel_pad_usable(pctrl, pin))
+ return false;
+
+ /*
+ * Only restore the pin if it is actually in use by the kernel (or
+ * by userspace). It is possible that some pins are used by the
+ * BIOS during resume and those are not always locked down so leave
+ * them alone.
+ */
+ if (pd->mux_owner || pd->gpio_owner ||
+ gpiochip_line_is_irq(&pctrl->chip, pin))
+ return true;
+
+ return false;
+}
+
int intel_pinctrl_suspend(struct device *dev)
{
struct platform_device *pdev = to_platform_device(dev);
@@ -1069,7 +1090,7 @@ int intel_pinctrl_suspend(struct device *dev)
const struct pinctrl_pin_desc *desc = &pctrl->soc->pins[i];
u32 val;
- if (!intel_pad_usable(pctrl, desc->number))
+ if (!intel_pinctrl_should_save(pctrl, desc->number))
continue;
val = readl(intel_get_padcfg(pctrl, desc->number, PADCFG0));
@@ -1130,7 +1151,7 @@ int intel_pinctrl_resume(struct device *dev)
void __iomem *padcfg;
u32 val;
- if (!intel_pad_usable(pctrl, desc->number))
+ if (!intel_pinctrl_should_save(pctrl, desc->number))
continue;
padcfg = intel_get_padcfg(pctrl, desc->number, PADCFG0);
diff --git a/drivers/pinctrl/pinctrl-st.c b/drivers/pinctrl/pinctrl-st.c
index 99da4cf..b7bb371 100644
--- a/drivers/pinctrl/pinctrl-st.c
+++ b/drivers/pinctrl/pinctrl-st.c
@@ -1512,7 +1512,7 @@ static int st_gpiolib_register_bank(struct st_pinctrl *info,
if (info->irqmux_base || gpio_irq > 0) {
err = gpiochip_irqchip_add(&bank->gpio_chip, &st_gpio_irqchip,
0, handle_simple_irq,
- IRQ_TYPE_LEVEL_LOW);
+ IRQ_TYPE_NONE);
if (err) {
gpiochip_remove(&bank->gpio_chip);
dev_info(dev, "could not add irqchip\n");
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index 200667f..efc4371 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -1092,9 +1092,11 @@ int stm32_pctl_probe(struct platform_device *pdev)
return -EINVAL;
}
- ret = stm32_pctrl_dt_setup_irq(pdev, pctl);
- if (ret)
- return ret;
+ if (of_find_property(np, "interrupt-parent", NULL)) {
+ ret = stm32_pctrl_dt_setup_irq(pdev, pctl);
+ if (ret)
+ return ret;
+ }
for_each_child_of_node(np, child)
if (of_property_read_bool(child, "gpio-controller"))
diff --git a/drivers/platform/goldfish/goldfish_pipe.c b/drivers/platform/goldfish/goldfish_pipe.c
index 07462d7..1aba2c7 100644
--- a/drivers/platform/goldfish/goldfish_pipe.c
+++ b/drivers/platform/goldfish/goldfish_pipe.c
@@ -309,7 +309,8 @@ static ssize_t goldfish_pipe_read_write(struct file *filp, char __user *buffer,
* much memory to the process.
*/
down_read(¤t->mm->mmap_sem);
- ret = get_user_pages(address, 1, !is_write, 0, &page, NULL);
+ ret = get_user_pages(address, 1, is_write ? 0 : FOLL_WRITE,
+ &page, NULL);
up_read(¤t->mm->mmap_sem);
if (ret < 0)
break;
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 81b8dcc..b8a21d7 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -576,6 +576,7 @@
config ASUS_NB_WMI
tristate "Asus Notebook WMI Driver"
depends on ASUS_WMI
+ depends on SERIO_I8042 || SERIO_I8042 = n
---help---
This is a driver for newer Asus notebooks. It adds extra features
like wireless radio and bluetooth control, leds, hotkeys, backlight...
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index d1a091b..a7614fc 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -933,6 +933,20 @@ static const struct dmi_system_id no_hw_rfkill_list[] = {
DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo YOGA 900"),
},
},
+ {
+ .ident = "Lenovo Yoga 900",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_BOARD_NAME, "VIUU4"),
+ },
+ },
+ {
+ .ident = "Lenovo YOGA 910-13IKB",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo YOGA 910-13IKB"),
+ },
+ },
{}
};
diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c
index ed58742..12dbb50 100644
--- a/drivers/platform/x86/intel-hid.c
+++ b/drivers/platform/x86/intel-hid.c
@@ -264,7 +264,7 @@ check_acpi_dev(acpi_handle handle, u32 lvl, void *context, void **rv)
return AE_OK;
if (acpi_match_device_ids(dev, ids) == 0)
- if (acpi_create_platform_device(dev))
+ if (acpi_create_platform_device(dev, NULL))
dev_info(&dev->dev,
"intel-hid: created platform device\n");
diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c
index 146d02f..7808076 100644
--- a/drivers/platform/x86/intel-vbtn.c
+++ b/drivers/platform/x86/intel-vbtn.c
@@ -164,7 +164,7 @@ check_acpi_dev(acpi_handle handle, u32 lvl, void *context, void **rv)
return AE_OK;
if (acpi_match_device_ids(dev, ids) == 0)
- if (acpi_create_platform_device(dev))
+ if (acpi_create_platform_device(dev, NULL))
dev_info(&dev->dev,
"intel-vbtn: created platform device\n");
diff --git a/drivers/platform/x86/toshiba-wmi.c b/drivers/platform/x86/toshiba-wmi.c
index feac457..2df07ee 100644
--- a/drivers/platform/x86/toshiba-wmi.c
+++ b/drivers/platform/x86/toshiba-wmi.c
@@ -24,14 +24,15 @@
#include <linux/acpi.h>
#include <linux/input.h>
#include <linux/input/sparse-keymap.h>
+#include <linux/dmi.h>
MODULE_AUTHOR("Azael Avalos");
MODULE_DESCRIPTION("Toshiba WMI Hotkey Driver");
MODULE_LICENSE("GPL");
-#define TOSHIBA_WMI_EVENT_GUID "59142400-C6A3-40FA-BADB-8A2652834100"
+#define WMI_EVENT_GUID "59142400-C6A3-40FA-BADB-8A2652834100"
-MODULE_ALIAS("wmi:"TOSHIBA_WMI_EVENT_GUID);
+MODULE_ALIAS("wmi:"WMI_EVENT_GUID);
static struct input_dev *toshiba_wmi_input_dev;
@@ -63,6 +64,16 @@ static void toshiba_wmi_notify(u32 value, void *context)
kfree(response.pointer);
}
+static struct dmi_system_id toshiba_wmi_dmi_table[] __initdata = {
+ {
+ .ident = "Toshiba laptop",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+ },
+ },
+ {}
+};
+
static int __init toshiba_wmi_input_setup(void)
{
acpi_status status;
@@ -81,7 +92,7 @@ static int __init toshiba_wmi_input_setup(void)
if (err)
goto err_free_dev;
- status = wmi_install_notify_handler(TOSHIBA_WMI_EVENT_GUID,
+ status = wmi_install_notify_handler(WMI_EVENT_GUID,
toshiba_wmi_notify, NULL);
if (ACPI_FAILURE(status)) {
err = -EIO;
@@ -95,7 +106,7 @@ static int __init toshiba_wmi_input_setup(void)
return 0;
err_remove_notifier:
- wmi_remove_notify_handler(TOSHIBA_WMI_EVENT_GUID);
+ wmi_remove_notify_handler(WMI_EVENT_GUID);
err_free_keymap:
sparse_keymap_free(toshiba_wmi_input_dev);
err_free_dev:
@@ -105,7 +116,7 @@ static int __init toshiba_wmi_input_setup(void)
static void toshiba_wmi_input_destroy(void)
{
- wmi_remove_notify_handler(TOSHIBA_WMI_EVENT_GUID);
+ wmi_remove_notify_handler(WMI_EVENT_GUID);
sparse_keymap_free(toshiba_wmi_input_dev);
input_unregister_device(toshiba_wmi_input_dev);
}
@@ -114,7 +125,8 @@ static int __init toshiba_wmi_init(void)
{
int ret;
- if (!wmi_has_guid(TOSHIBA_WMI_EVENT_GUID))
+ if (!wmi_has_guid(WMI_EVENT_GUID) ||
+ !dmi_check_system(toshiba_wmi_dmi_table))
return -ENODEV;
ret = toshiba_wmi_input_setup();
@@ -130,7 +142,7 @@ static int __init toshiba_wmi_init(void)
static void __exit toshiba_wmi_exit(void)
{
- if (wmi_has_guid(TOSHIBA_WMI_EVENT_GUID))
+ if (wmi_has_guid(WMI_EVENT_GUID))
toshiba_wmi_input_destroy();
}
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index 86280b7..9c13381 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -153,7 +153,10 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct timex *tx)
s32 ppb = scaled_ppm_to_ppb(tx->freq);
if (ppb > ops->max_adj || ppb < -ops->max_adj)
return -ERANGE;
- err = ops->adjfreq(ops, ppb);
+ if (ops->adjfine)
+ err = ops->adjfine(ops, tx->freq);
+ else
+ err = ops->adjfreq(ops, ppb);
ptp->dialed_frequency = tx->freq;
} else if (tx->modes == 0) {
tx->freq = ptp->dialed_frequency;
diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c
index 302e626..53d4395 100644
--- a/drivers/ptp/ptp_sysfs.c
+++ b/drivers/ptp/ptp_sysfs.c
@@ -28,7 +28,7 @@ static ssize_t clock_name_show(struct device *dev,
struct ptp_clock *ptp = dev_get_drvdata(dev);
return snprintf(page, PAGE_SIZE-1, "%s\n", ptp->info->name);
}
-static DEVICE_ATTR(clock_name, 0444, clock_name_show, NULL);
+static DEVICE_ATTR_RO(clock_name);
#define PTP_SHOW_INT(name, var) \
static ssize_t var##_show(struct device *dev, \
diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index 436dfe8..9013a58 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -892,7 +892,8 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode,
down_read(¤t->mm->mmap_sem);
pinned = get_user_pages(
(unsigned long)xfer->loc_addr & PAGE_MASK,
- nr_pages, dir == DMA_FROM_DEVICE, 0,
+ nr_pages,
+ dir == DMA_FROM_DEVICE ? FOLL_WRITE : 0,
page_list, NULL);
up_read(¤t->mm->mmap_sem);
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 67426c0..5c1519b 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -2754,7 +2754,7 @@ static int _regulator_set_voltage_time(struct regulator_dev *rdev,
ramp_delay = rdev->desc->ramp_delay;
if (ramp_delay == 0) {
- rdev_warn(rdev, "ramp_delay not set\n");
+ rdev_dbg(rdev, "ramp_delay not set\n");
return 0;
}
diff --git a/drivers/reset/reset-uniphier.c b/drivers/reset/reset-uniphier.c
index 8b2558e..968c3ae 100644
--- a/drivers/reset/reset-uniphier.c
+++ b/drivers/reset/reset-uniphier.c
@@ -154,7 +154,7 @@ const struct uniphier_reset_data uniphier_sld3_mio_reset_data[] = {
UNIPHIER_RESET_END,
};
-const struct uniphier_reset_data uniphier_pro5_mio_reset_data[] = {
+const struct uniphier_reset_data uniphier_pro5_sd_reset_data[] = {
UNIPHIER_MIO_RESET_SD(0, 0),
UNIPHIER_MIO_RESET_SD(1, 1),
UNIPHIER_MIO_RESET_EMMC_HW_RESET(6, 1),
@@ -360,7 +360,7 @@ static const struct of_device_id uniphier_reset_match[] = {
.compatible = "socionext,uniphier-ld20-reset",
.data = uniphier_ld20_sys_reset_data,
},
- /* Media I/O reset */
+ /* Media I/O reset, SD reset */
{
.compatible = "socionext,uniphier-sld3-mio-reset",
.data = uniphier_sld3_mio_reset_data,
@@ -378,20 +378,20 @@ static const struct of_device_id uniphier_reset_match[] = {
.data = uniphier_sld3_mio_reset_data,
},
{
- .compatible = "socionext,uniphier-pro5-mio-reset",
- .data = uniphier_pro5_mio_reset_data,
+ .compatible = "socionext,uniphier-pro5-sd-reset",
+ .data = uniphier_pro5_sd_reset_data,
},
{
- .compatible = "socionext,uniphier-pxs2-mio-reset",
- .data = uniphier_pro5_mio_reset_data,
+ .compatible = "socionext,uniphier-pxs2-sd-reset",
+ .data = uniphier_pro5_sd_reset_data,
},
{
.compatible = "socionext,uniphier-ld11-mio-reset",
.data = uniphier_sld3_mio_reset_data,
},
{
- .compatible = "socionext,uniphier-ld20-mio-reset",
- .data = uniphier_pro5_mio_reset_data,
+ .compatible = "socionext,uniphier-ld20-sd-reset",
+ .data = uniphier_pro5_sd_reset_data,
},
/* Peripheral reset */
{
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index d1e0807..e859d14 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -208,14 +208,14 @@
will be called rtc-as3722.
config RTC_DRV_DS1307
- tristate "Dallas/Maxim DS1307/37/38/39/40, ST M41T00, EPSON RX-8025"
+ tristate "Dallas/Maxim DS1307/37/38/39/40, ST M41T00, EPSON RX-8025, ISL12057"
help
If you say yes here you get support for various compatible RTC
chips (often with battery backup) connected with I2C. This driver
should handle DS1307, DS1337, DS1338, DS1339, DS1340, ST M41T00,
- EPSON RX-8025 and probably other chips. In some cases the RTC
- must already have been initialized (by manufacturing or a
- bootloader).
+ EPSON RX-8025, Intersil ISL12057 and probably other chips. In some
+ cases the RTC must already have been initialized (by manufacturing or
+ a bootloader).
The first seven registers on these chips hold an RTC, and other
registers may add features such as NVRAM, a trickle charger for
@@ -234,6 +234,20 @@
Say Y here if you want to expose temperature sensor data on
rtc-ds1307 (only DS3231)
+config RTC_DRV_DS1307_CENTURY
+ bool "Century bit support for rtc-ds1307"
+ depends on RTC_DRV_DS1307
+ default n
+ help
+ The DS1307 driver suffered from a bug where it was enabling the
+ century bit inconditionnally but never used it when reading the time.
+ It made the driver unable to support dates beyond 2099.
+ Setting this option will add proper support for the century bit but if
+ the time was previously set using a kernel predating this option,
+ reading the date will return a date in the next century.
+ To solve that, you could boot a kernel without this option set, set
+ the RTC date and then boot a kernel with this option set.
+
config RTC_DRV_DS1374
tristate "Dallas/Maxim DS1374"
help
@@ -374,16 +388,6 @@
This driver can also be built as a module. If so, the module
will be called rtc-isl12022.
-config RTC_DRV_ISL12057
- select REGMAP_I2C
- tristate "Intersil ISL12057"
- help
- If you say yes here you get support for the Intersil ISL12057
- I2C RTC chip.
-
- This driver can also be built as a module. If so, the module
- will be called rtc-isl12057.
-
config RTC_DRV_X1205
tristate "Xicor/Intersil X1205"
help
@@ -661,6 +665,7 @@
will be called rtc-ds1343.
config RTC_DRV_DS1347
+ select REGMAP_SPI
tristate "Dallas/Maxim DS1347"
help
If you say yes here you get support for the
@@ -1201,7 +1206,7 @@
config RTC_DRV_ASM9260
tristate "Alphascale asm9260 RTC"
- depends on MACH_ASM9260
+ depends on MACH_ASM9260 || COMPILE_TEST
help
If you say yes here you get support for the RTC on the
Alphascale asm9260 SoC.
@@ -1241,6 +1246,9 @@
config RTC_DRV_OMAP
tristate "TI OMAP Real Time Clock"
depends on ARCH_OMAP || ARCH_DAVINCI || COMPILE_TEST
+ depends on OF
+ depends on PINCTRL
+ select GENERIC_PINCONF
help
Say "yes" here to support the on chip real time clock
present on TI OMAP1, AM33xx, DA8xx/OMAP-L13x, AM43xx and DRA7xx.
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 8fb994b..1ac694a 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -72,7 +72,6 @@
obj-$(CONFIG_RTC_DRV_HYM8563) += rtc-hym8563.o
obj-$(CONFIG_RTC_DRV_IMXDI) += rtc-imxdi.o
obj-$(CONFIG_RTC_DRV_ISL12022) += rtc-isl12022.o
-obj-$(CONFIG_RTC_DRV_ISL12057) += rtc-isl12057.o
obj-$(CONFIG_RTC_DRV_ISL1208) += rtc-isl1208.o
obj-$(CONFIG_RTC_DRV_JZ4740) += rtc-jz4740.o
obj-$(CONFIG_RTC_DRV_LP8788) += rtc-lp8788.o
diff --git a/drivers/rtc/rtc-ac100.c b/drivers/rtc/rtc-ac100.c
index 70b4fd0..9e33618 100644
--- a/drivers/rtc/rtc-ac100.c
+++ b/drivers/rtc/rtc-ac100.c
@@ -327,6 +327,8 @@ static int ac100_rtc_register_clks(struct ac100_rtc_dev *chip)
.flags = 0,
};
+ of_property_read_string_index(np, "clock-output-names",
+ i, &init.name);
clk->regmap = chip->regmap;
clk->offset = AC100_CLKOUT_CTRL1 + i;
clk->hw.init = &init;
@@ -552,6 +554,9 @@ static int ac100_rtc_probe(struct platform_device *pdev)
int ret;
chip = devm_kzalloc(&pdev->dev, sizeof(*chip), GFP_KERNEL);
+ if (!chip)
+ return -ENOMEM;
+
platform_set_drvdata(pdev, chip);
chip->dev = &pdev->dev;
chip->regmap = ac100->regmap;
diff --git a/drivers/rtc/rtc-asm9260.c b/drivers/rtc/rtc-asm9260.c
index 5219916..d365349 100644
--- a/drivers/rtc/rtc-asm9260.c
+++ b/drivers/rtc/rtc-asm9260.c
@@ -112,8 +112,6 @@ struct asm9260_rtc_priv {
void __iomem *iobase;
struct rtc_device *rtc;
struct clk *clk;
- /* io lock */
- spinlock_t lock;
};
static irqreturn_t asm9260_rtc_irq(int irq, void *dev_id)
@@ -122,11 +120,15 @@ static irqreturn_t asm9260_rtc_irq(int irq, void *dev_id)
u32 isr;
unsigned long events = 0;
+ mutex_lock(&priv->rtc->ops_lock);
isr = ioread32(priv->iobase + HW_CIIR);
- if (!isr)
+ if (!isr) {
+ mutex_unlock(&priv->rtc->ops_lock);
return IRQ_NONE;
+ }
iowrite32(0, priv->iobase + HW_CIIR);
+ mutex_unlock(&priv->rtc->ops_lock);
events |= RTC_AF | RTC_IRQF;
@@ -139,9 +141,7 @@ static int asm9260_rtc_read_time(struct device *dev, struct rtc_time *tm)
{
struct asm9260_rtc_priv *priv = dev_get_drvdata(dev);
u32 ctime0, ctime1, ctime2;
- unsigned long irq_flags;
- spin_lock_irqsave(&priv->lock, irq_flags);
ctime0 = ioread32(priv->iobase + HW_CTIME0);
ctime1 = ioread32(priv->iobase + HW_CTIME1);
ctime2 = ioread32(priv->iobase + HW_CTIME2);
@@ -155,7 +155,6 @@ static int asm9260_rtc_read_time(struct device *dev, struct rtc_time *tm)
ctime1 = ioread32(priv->iobase + HW_CTIME1);
ctime2 = ioread32(priv->iobase + HW_CTIME2);
}
- spin_unlock_irqrestore(&priv->lock, irq_flags);
tm->tm_sec = (ctime0 >> BM_CTIME0_SEC_S) & BM_CTIME0_SEC_M;
tm->tm_min = (ctime0 >> BM_CTIME0_MIN_S) & BM_CTIME0_MIN_M;
@@ -174,9 +173,7 @@ static int asm9260_rtc_read_time(struct device *dev, struct rtc_time *tm)
static int asm9260_rtc_set_time(struct device *dev, struct rtc_time *tm)
{
struct asm9260_rtc_priv *priv = dev_get_drvdata(dev);
- unsigned long irq_flags;
- spin_lock_irqsave(&priv->lock, irq_flags);
/*
* make sure SEC counter will not flip other counter on write time,
* real value will be written at the enf of sequence.
@@ -191,7 +188,6 @@ static int asm9260_rtc_set_time(struct device *dev, struct rtc_time *tm)
iowrite32(tm->tm_hour, priv->iobase + HW_HOUR);
iowrite32(tm->tm_min, priv->iobase + HW_MIN);
iowrite32(tm->tm_sec, priv->iobase + HW_SEC);
- spin_unlock_irqrestore(&priv->lock, irq_flags);
return 0;
}
@@ -199,9 +195,7 @@ static int asm9260_rtc_set_time(struct device *dev, struct rtc_time *tm)
static int asm9260_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
{
struct asm9260_rtc_priv *priv = dev_get_drvdata(dev);
- unsigned long irq_flags;
- spin_lock_irqsave(&priv->lock, irq_flags);
alrm->time.tm_year = ioread32(priv->iobase + HW_ALYEAR);
alrm->time.tm_mon = ioread32(priv->iobase + HW_ALMON);
alrm->time.tm_mday = ioread32(priv->iobase + HW_ALDOM);
@@ -213,7 +207,6 @@ static int asm9260_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
alrm->enabled = ioread32(priv->iobase + HW_AMR) ? 1 : 0;
alrm->pending = ioread32(priv->iobase + HW_CIIR) ? 1 : 0;
- spin_unlock_irqrestore(&priv->lock, irq_flags);
return rtc_valid_tm(&alrm->time);
}
@@ -221,9 +214,7 @@ static int asm9260_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
static int asm9260_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
{
struct asm9260_rtc_priv *priv = dev_get_drvdata(dev);
- unsigned long irq_flags;
- spin_lock_irqsave(&priv->lock, irq_flags);
iowrite32(alrm->time.tm_year, priv->iobase + HW_ALYEAR);
iowrite32(alrm->time.tm_mon, priv->iobase + HW_ALMON);
iowrite32(alrm->time.tm_mday, priv->iobase + HW_ALDOM);
@@ -234,7 +225,6 @@ static int asm9260_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
iowrite32(alrm->time.tm_sec, priv->iobase + HW_ALSEC);
iowrite32(alrm->enabled ? 0 : BM_AMR_OFF, priv->iobase + HW_AMR);
- spin_unlock_irqrestore(&priv->lock, irq_flags);
return 0;
}
@@ -337,6 +327,7 @@ static const struct of_device_id asm9260_dt_ids[] = {
{ .compatible = "alphascale,asm9260-rtc", },
{}
};
+MODULE_DEVICE_TABLE(of, asm9260_dt_ids);
static struct platform_driver asm9260_rtc_driver = {
.probe = asm9260_rtc_probe,
diff --git a/drivers/rtc/rtc-at32ap700x.c b/drivers/rtc/rtc-at32ap700x.c
index 83ac233..de8bf56 100644
--- a/drivers/rtc/rtc-at32ap700x.c
+++ b/drivers/rtc/rtc-at32ap700x.c
@@ -187,7 +187,7 @@ static irqreturn_t at32_rtc_interrupt(int irq, void *dev_id)
return ret;
}
-static struct rtc_class_ops at32_rtc_ops = {
+static const struct rtc_class_ops at32_rtc_ops = {
.read_time = at32_rtc_readtime,
.set_time = at32_rtc_settime,
.read_alarm = at32_rtc_readalarm,
diff --git a/drivers/rtc/rtc-bq32k.c b/drivers/rtc/rtc-bq32k.c
index 0299988..3977424 100644
--- a/drivers/rtc/rtc-bq32k.c
+++ b/drivers/rtc/rtc-bq32k.c
@@ -93,8 +93,15 @@ static int bq32k_rtc_read_time(struct device *dev, struct rtc_time *tm)
if (error)
return error;
+ /*
+ * In case of oscillator failure, the register contents should be
+ * considered invalid. The flag is cleared the next time the RTC is set.
+ */
+ if (regs.minutes & BQ32K_OF)
+ return -EINVAL;
+
tm->tm_sec = bcd2bin(regs.seconds & BQ32K_SECONDS_MASK);
- tm->tm_min = bcd2bin(regs.minutes & BQ32K_SECONDS_MASK);
+ tm->tm_min = bcd2bin(regs.minutes & BQ32K_MINUTES_MASK);
tm->tm_hour = bcd2bin(regs.cent_hours & BQ32K_HOURS_MASK);
tm->tm_mday = bcd2bin(regs.date);
tm->tm_wday = bcd2bin(regs.day) - 1;
@@ -204,13 +211,10 @@ static int bq32k_probe(struct i2c_client *client,
/* Check Oscillator Failure flag */
error = bq32k_read(dev, ®, BQ32K_MINUTES, 1);
- if (!error && (reg & BQ32K_OF)) {
- dev_warn(dev, "Oscillator Failure. Check RTC battery.\n");
- reg &= ~BQ32K_OF;
- error = bq32k_write(dev, ®, BQ32K_MINUTES, 1);
- }
if (error)
return error;
+ if (reg & BQ32K_OF)
+ dev_warn(dev, "Oscillator Failure. Check RTC battery.\n");
if (client->dev.of_node)
trickle_charger_of_init(dev, client->dev.of_node);
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 43745ca..7030d7c 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -62,6 +62,8 @@ struct cmos_rtc {
u8 day_alrm;
u8 mon_alrm;
u8 century;
+
+ struct rtc_wkalrm saved_wkalrm;
};
/* both platform and pnp busses use negative numbers for invalid irqs */
@@ -707,6 +709,8 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
goto cleanup1;
}
+ hpet_rtc_timer_init();
+
if (is_valid_irq(rtc_irq)) {
irq_handler_t rtc_cmos_int_handler;
@@ -714,6 +718,7 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
rtc_cmos_int_handler = hpet_rtc_interrupt;
retval = hpet_register_irq_handler(cmos_interrupt);
if (retval) {
+ hpet_mask_rtc_irq_bit(RTC_IRQMASK);
dev_warn(dev, "hpet_register_irq_handler "
" failed in rtc_init().");
goto cleanup1;
@@ -729,7 +734,6 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
goto cleanup1;
}
}
- hpet_rtc_timer_init();
/* export at least the first block of NVRAM */
nvram.size = address_space - NVRAM_OFFSET;
@@ -772,7 +776,7 @@ static void cmos_do_shutdown(int rtc_irq)
spin_unlock_irq(&rtc_lock);
}
-static void __exit cmos_do_remove(struct device *dev)
+static void cmos_do_remove(struct device *dev)
{
struct cmos_rtc *cmos = dev_get_drvdata(dev);
struct resource *ports;
@@ -844,8 +848,6 @@ static int cmos_aie_poweroff(struct device *dev)
return retval;
}
-#ifdef CONFIG_PM
-
static int cmos_suspend(struct device *dev)
{
struct cmos_rtc *cmos = dev_get_drvdata(dev);
@@ -877,6 +879,8 @@ static int cmos_suspend(struct device *dev)
enable_irq_wake(cmos->irq);
}
+ cmos_read_alarm(dev, &cmos->saved_wkalrm);
+
dev_dbg(dev, "suspend%s, ctrl %02x\n",
(tmp & RTC_AIE) ? ", alarm may wake" : "",
tmp);
@@ -892,12 +896,32 @@ static int cmos_suspend(struct device *dev)
*/
static inline int cmos_poweroff(struct device *dev)
{
+ if (!IS_ENABLED(CONFIG_PM))
+ return -ENOSYS;
+
return cmos_suspend(dev);
}
-#ifdef CONFIG_PM_SLEEP
+static void cmos_check_wkalrm(struct device *dev)
+{
+ struct cmos_rtc *cmos = dev_get_drvdata(dev);
+ struct rtc_wkalrm current_alarm;
+ time64_t t_current_expires;
+ time64_t t_saved_expires;
-static int cmos_resume(struct device *dev)
+ cmos_read_alarm(dev, ¤t_alarm);
+ t_current_expires = rtc_tm_to_time64(¤t_alarm.time);
+ t_saved_expires = rtc_tm_to_time64(&cmos->saved_wkalrm.time);
+ if (t_current_expires != t_saved_expires ||
+ cmos->saved_wkalrm.enabled != current_alarm.enabled) {
+ cmos_set_alarm(dev, &cmos->saved_wkalrm);
+ }
+}
+
+static void cmos_check_acpi_rtc_status(struct device *dev,
+ unsigned char *rtc_control);
+
+static int __maybe_unused cmos_resume(struct device *dev)
{
struct cmos_rtc *cmos = dev_get_drvdata(dev);
unsigned char tmp;
@@ -910,6 +934,9 @@ static int cmos_resume(struct device *dev)
cmos->enabled_wake = 0;
}
+ /* The BIOS might have changed the alarm, restore it */
+ cmos_check_wkalrm(dev);
+
spin_lock_irq(&rtc_lock);
tmp = cmos->suspend_ctrl;
cmos->suspend_ctrl = 0;
@@ -936,6 +963,9 @@ static int cmos_resume(struct device *dev)
tmp &= ~RTC_AIE;
hpet_mask_rtc_irq_bit(RTC_AIE);
} while (mask & RTC_AIE);
+
+ if (tmp & RTC_AIE)
+ cmos_check_acpi_rtc_status(dev, &tmp);
}
spin_unlock_irq(&rtc_lock);
@@ -944,16 +974,6 @@ static int cmos_resume(struct device *dev)
return 0;
}
-#endif
-#else
-
-static inline int cmos_poweroff(struct device *dev)
-{
- return -ENOSYS;
-}
-
-#endif
-
static SIMPLE_DEV_PM_OPS(cmos_pm_ops, cmos_suspend, cmos_resume);
/*----------------------------------------------------------------*/
@@ -973,6 +993,21 @@ static SIMPLE_DEV_PM_OPS(cmos_pm_ops, cmos_suspend, cmos_resume);
static u32 rtc_handler(void *context)
{
struct device *dev = context;
+ struct cmos_rtc *cmos = dev_get_drvdata(dev);
+ unsigned char rtc_control = 0;
+ unsigned char rtc_intr;
+ unsigned long flags;
+
+ spin_lock_irqsave(&rtc_lock, flags);
+ if (cmos_rtc.suspend_ctrl)
+ rtc_control = CMOS_READ(RTC_CONTROL);
+ if (rtc_control & RTC_AIE) {
+ cmos_rtc.suspend_ctrl &= ~RTC_AIE;
+ CMOS_WRITE(rtc_control, RTC_CONTROL);
+ rtc_intr = CMOS_READ(RTC_INTR_FLAGS);
+ rtc_update_irq(cmos->rtc, 1, rtc_intr);
+ }
+ spin_unlock_irqrestore(&rtc_lock, flags);
pm_wakeup_event(dev, 0);
acpi_clear_event(ACPI_EVENT_RTC);
@@ -1039,12 +1074,39 @@ static void cmos_wake_setup(struct device *dev)
device_init_wakeup(dev, 1);
}
+static void cmos_check_acpi_rtc_status(struct device *dev,
+ unsigned char *rtc_control)
+{
+ struct cmos_rtc *cmos = dev_get_drvdata(dev);
+ acpi_event_status rtc_status;
+ acpi_status status;
+
+ if (acpi_gbl_FADT.flags & ACPI_FADT_FIXED_RTC)
+ return;
+
+ status = acpi_get_event_status(ACPI_EVENT_RTC, &rtc_status);
+ if (ACPI_FAILURE(status)) {
+ dev_err(dev, "Could not get RTC status\n");
+ } else if (rtc_status & ACPI_EVENT_FLAG_SET) {
+ unsigned char mask;
+ *rtc_control &= ~RTC_AIE;
+ CMOS_WRITE(*rtc_control, RTC_CONTROL);
+ mask = CMOS_READ(RTC_INTR_FLAGS);
+ rtc_update_irq(cmos->rtc, 1, mask);
+ }
+}
+
#else
static void cmos_wake_setup(struct device *dev)
{
}
+static void cmos_check_acpi_rtc_status(struct device *dev,
+ unsigned char *rtc_control)
+{
+}
+
#endif
#ifdef CONFIG_PNP
@@ -1068,7 +1130,7 @@ static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id)
pnp_irq(pnp, 0));
}
-static void __exit cmos_pnp_remove(struct pnp_dev *pnp)
+static void cmos_pnp_remove(struct pnp_dev *pnp)
{
cmos_do_remove(&pnp->dev);
}
@@ -1100,7 +1162,7 @@ static struct pnp_driver cmos_pnp_driver = {
.name = (char *) driver_name,
.id_table = rtc_ids,
.probe = cmos_pnp_probe,
- .remove = __exit_p(cmos_pnp_remove),
+ .remove = cmos_pnp_remove,
.shutdown = cmos_pnp_shutdown,
/* flag ensures resume() gets called, and stops syslog spam */
@@ -1177,7 +1239,7 @@ static int __init cmos_platform_probe(struct platform_device *pdev)
return cmos_do_probe(&pdev->dev, resource, irq);
}
-static int __exit cmos_platform_remove(struct platform_device *pdev)
+static int cmos_platform_remove(struct platform_device *pdev)
{
cmos_do_remove(&pdev->dev);
return 0;
@@ -1202,13 +1264,11 @@ static void cmos_platform_shutdown(struct platform_device *pdev)
MODULE_ALIAS("platform:rtc_cmos");
static struct platform_driver cmos_platform_driver = {
- .remove = __exit_p(cmos_platform_remove),
+ .remove = cmos_platform_remove,
.shutdown = cmos_platform_shutdown,
.driver = {
.name = driver_name,
-#ifdef CONFIG_PM
.pm = &cmos_pm_ops,
-#endif
.of_match_table = of_match_ptr(of_cmos_match),
}
};
diff --git a/drivers/rtc/rtc-coh901331.c b/drivers/rtc/rtc-coh901331.c
index 101b7a2..cfc4141 100644
--- a/drivers/rtc/rtc-coh901331.c
+++ b/drivers/rtc/rtc-coh901331.c
@@ -140,7 +140,7 @@ static int coh901331_alarm_irq_enable(struct device *dev, unsigned int enabled)
return 0;
}
-static struct rtc_class_ops coh901331_ops = {
+static const struct rtc_class_ops coh901331_ops = {
.read_time = coh901331_read_time,
.set_mmss = coh901331_set_mmss,
.read_alarm = coh901331_read_alarm,
diff --git a/drivers/rtc/rtc-davinci.c b/drivers/rtc/rtc-davinci.c
index dba60c1..caf3556 100644
--- a/drivers/rtc/rtc-davinci.c
+++ b/drivers/rtc/rtc-davinci.c
@@ -469,7 +469,7 @@ static int davinci_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
return 0;
}
-static struct rtc_class_ops davinci_rtc_ops = {
+static const struct rtc_class_ops davinci_rtc_ops = {
.ioctl = davinci_rtc_ioctl,
.read_time = davinci_rtc_read_time,
.set_time = davinci_rtc_set_time,
diff --git a/drivers/rtc/rtc-digicolor.c b/drivers/rtc/rtc-digicolor.c
index 8d05596..b253bf1 100644
--- a/drivers/rtc/rtc-digicolor.c
+++ b/drivers/rtc/rtc-digicolor.c
@@ -159,7 +159,7 @@ static int dc_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
return 0;
}
-static struct rtc_class_ops dc_rtc_ops = {
+static const struct rtc_class_ops dc_rtc_ops = {
.read_time = dc_rtc_read_time,
.set_mmss = dc_rtc_set_mmss,
.read_alarm = dc_rtc_read_alarm,
diff --git a/drivers/rtc/rtc-ds1302.c b/drivers/rtc/rtc-ds1302.c
index f5dd09f..0ec4be6 100644
--- a/drivers/rtc/rtc-ds1302.c
+++ b/drivers/rtc/rtc-ds1302.c
@@ -102,7 +102,7 @@ static int ds1302_rtc_get_time(struct device *dev, struct rtc_time *time)
return rtc_valid_tm(time);
}
-static struct rtc_class_ops ds1302_rtc_ops = {
+static const struct rtc_class_ops ds1302_rtc_ops = {
.read_time = ds1302_rtc_get_time,
.set_time = ds1302_rtc_set_time,
};
diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index 8e1c5cb..4e31036 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -186,6 +186,7 @@ static const struct i2c_device_id ds1307_id[] = {
{ "mcp7941x", mcp794xx },
{ "pt7c4338", ds_1307 },
{ "rx8025", rx_8025 },
+ { "isl12057", ds_1337 },
{ }
};
MODULE_DEVICE_TABLE(i2c, ds1307_id);
@@ -382,10 +383,25 @@ static int ds1307_get_time(struct device *dev, struct rtc_time *t)
t->tm_mday = bcd2bin(ds1307->regs[DS1307_REG_MDAY] & 0x3f);
tmp = ds1307->regs[DS1307_REG_MONTH] & 0x1f;
t->tm_mon = bcd2bin(tmp) - 1;
-
- /* assume 20YY not 19YY, and ignore DS1337_BIT_CENTURY */
t->tm_year = bcd2bin(ds1307->regs[DS1307_REG_YEAR]) + 100;
+#ifdef CONFIG_RTC_DRV_DS1307_CENTURY
+ switch (ds1307->type) {
+ case ds_1337:
+ case ds_1339:
+ case ds_3231:
+ if (ds1307->regs[DS1307_REG_MONTH] & DS1337_BIT_CENTURY)
+ t->tm_year += 100;
+ break;
+ case ds_1340:
+ if (ds1307->regs[DS1307_REG_HOUR] & DS1340_BIT_CENTURY)
+ t->tm_year += 100;
+ break;
+ default:
+ break;
+ }
+#endif
+
dev_dbg(dev, "%s secs=%d, mins=%d, "
"hours=%d, mday=%d, mon=%d, year=%d, wday=%d\n",
"read", t->tm_sec, t->tm_min,
@@ -409,6 +425,27 @@ static int ds1307_set_time(struct device *dev, struct rtc_time *t)
t->tm_hour, t->tm_mday,
t->tm_mon, t->tm_year, t->tm_wday);
+#ifdef CONFIG_RTC_DRV_DS1307_CENTURY
+ if (t->tm_year < 100)
+ return -EINVAL;
+
+ switch (ds1307->type) {
+ case ds_1337:
+ case ds_1339:
+ case ds_3231:
+ case ds_1340:
+ if (t->tm_year > 299)
+ return -EINVAL;
+ default:
+ if (t->tm_year > 199)
+ return -EINVAL;
+ break;
+ }
+#else
+ if (t->tm_year < 100 || t->tm_year > 199)
+ return -EINVAL;
+#endif
+
buf[DS1307_REG_SECS] = bin2bcd(t->tm_sec);
buf[DS1307_REG_MIN] = bin2bcd(t->tm_min);
buf[DS1307_REG_HOUR] = bin2bcd(t->tm_hour);
@@ -424,11 +461,13 @@ static int ds1307_set_time(struct device *dev, struct rtc_time *t)
case ds_1337:
case ds_1339:
case ds_3231:
- buf[DS1307_REG_MONTH] |= DS1337_BIT_CENTURY;
+ if (t->tm_year > 199)
+ buf[DS1307_REG_MONTH] |= DS1337_BIT_CENTURY;
break;
case ds_1340:
- buf[DS1307_REG_HOUR] |= DS1340_BIT_CENTURY_EN
- | DS1340_BIT_CENTURY;
+ buf[DS1307_REG_HOUR] |= DS1340_BIT_CENTURY_EN;
+ if (t->tm_year > 199)
+ buf[DS1307_REG_HOUR] |= DS1340_BIT_CENTURY;
break;
case mcp794xx:
/*
@@ -1295,6 +1334,11 @@ static int ds1307_probe(struct i2c_client *client,
if (of_property_read_bool(client->dev.of_node, "wakeup-source")) {
ds1307_can_wakeup_device = true;
}
+ /* Intersil ISL12057 DT backward compatibility */
+ if (of_property_read_bool(client->dev.of_node,
+ "isil,irq2-can-wakeup-machine")) {
+ ds1307_can_wakeup_device = true;
+ }
#endif
switch (ds1307->type) {
diff --git a/drivers/rtc/rtc-ds1347.c b/drivers/rtc/rtc-ds1347.c
index 641e8e8..ccfc9d4 100644
--- a/drivers/rtc/rtc-ds1347.c
+++ b/drivers/rtc/rtc-ds1347.c
@@ -18,6 +18,7 @@
#include <linux/rtc.h>
#include <linux/spi/spi.h>
#include <linux/bcd.h>
+#include <linux/regmap.h>
/* Registers in ds1347 rtc */
@@ -32,37 +33,28 @@
#define DS1347_STATUS_REG 0x17
#define DS1347_CLOCK_BURST 0x3F
-static int ds1347_read_reg(struct device *dev, unsigned char address,
- unsigned char *data)
-{
- struct spi_device *spi = to_spi_device(dev);
+static const struct regmap_range ds1347_ranges[] = {
+ {
+ .range_min = DS1347_SECONDS_REG,
+ .range_max = DS1347_STATUS_REG,
+ },
+};
- *data = address | 0x80;
-
- return spi_write_then_read(spi, data, 1, data, 1);
-}
-
-static int ds1347_write_reg(struct device *dev, unsigned char address,
- unsigned char data)
-{
- struct spi_device *spi = to_spi_device(dev);
- unsigned char buf[2];
-
- buf[0] = address & 0x7F;
- buf[1] = data;
-
- return spi_write_then_read(spi, buf, 2, NULL, 0);
-}
+static const struct regmap_access_table ds1347_access_table = {
+ .yes_ranges = ds1347_ranges,
+ .n_yes_ranges = ARRAY_SIZE(ds1347_ranges),
+};
static int ds1347_read_time(struct device *dev, struct rtc_time *dt)
{
struct spi_device *spi = to_spi_device(dev);
+ struct regmap *map;
int err;
unsigned char buf[8];
- buf[0] = DS1347_CLOCK_BURST | 0x80;
+ map = spi_get_drvdata(spi);
- err = spi_write_then_read(spi, buf, 1, buf, 8);
+ err = regmap_bulk_read(map, DS1347_CLOCK_BURST, buf, 8);
if (err)
return err;
@@ -80,25 +72,27 @@ static int ds1347_read_time(struct device *dev, struct rtc_time *dt)
static int ds1347_set_time(struct device *dev, struct rtc_time *dt)
{
struct spi_device *spi = to_spi_device(dev);
- unsigned char buf[9];
+ struct regmap *map;
+ unsigned char buf[8];
- buf[0] = DS1347_CLOCK_BURST & 0x7F;
- buf[1] = bin2bcd(dt->tm_sec);
- buf[2] = bin2bcd(dt->tm_min);
- buf[3] = (bin2bcd(dt->tm_hour) & 0x3F);
- buf[4] = bin2bcd(dt->tm_mday);
- buf[5] = bin2bcd(dt->tm_mon + 1);
- buf[6] = bin2bcd(dt->tm_wday + 1);
+ map = spi_get_drvdata(spi);
+
+ buf[0] = bin2bcd(dt->tm_sec);
+ buf[1] = bin2bcd(dt->tm_min);
+ buf[2] = (bin2bcd(dt->tm_hour) & 0x3F);
+ buf[3] = bin2bcd(dt->tm_mday);
+ buf[4] = bin2bcd(dt->tm_mon + 1);
+ buf[5] = bin2bcd(dt->tm_wday + 1);
/* year in linux is from 1900 i.e in range of 100
in rtc it is from 00 to 99 */
dt->tm_year = dt->tm_year % 100;
- buf[7] = bin2bcd(dt->tm_year);
- buf[8] = bin2bcd(0x00);
+ buf[6] = bin2bcd(dt->tm_year);
+ buf[7] = bin2bcd(0x00);
/* write the rtc settings */
- return spi_write_then_read(spi, buf, 9, NULL, 0);
+ return regmap_bulk_write(map, DS1347_CLOCK_BURST, buf, 8);
}
static const struct rtc_class_ops ds1347_rtc_ops = {
@@ -109,35 +103,53 @@ static const struct rtc_class_ops ds1347_rtc_ops = {
static int ds1347_probe(struct spi_device *spi)
{
struct rtc_device *rtc;
- unsigned char data;
+ struct regmap_config config;
+ struct regmap *map;
+ unsigned int data;
int res;
+ memset(&config, 0, sizeof(config));
+ config.reg_bits = 8;
+ config.val_bits = 8;
+ config.read_flag_mask = 0x80;
+ config.max_register = 0x3F;
+ config.wr_table = &ds1347_access_table;
+
/* spi setup with ds1347 in mode 3 and bits per word as 8 */
spi->mode = SPI_MODE_3;
spi->bits_per_word = 8;
spi_setup(spi);
+ map = devm_regmap_init_spi(spi, &config);
+
+ if (IS_ERR(map)) {
+ dev_err(&spi->dev, "ds1347 regmap init spi failed\n");
+ return PTR_ERR(map);
+ }
+
+ spi_set_drvdata(spi, map);
+
/* RTC Settings */
- res = ds1347_read_reg(&spi->dev, DS1347_SECONDS_REG, &data);
+ res = regmap_read(map, DS1347_SECONDS_REG, &data);
if (res)
return res;
/* Disable the write protect of rtc */
- ds1347_read_reg(&spi->dev, DS1347_CONTROL_REG, &data);
+ regmap_read(map, DS1347_CONTROL_REG, &data);
data = data & ~(1<<7);
- ds1347_write_reg(&spi->dev, DS1347_CONTROL_REG, data);
+ regmap_write(map, DS1347_CONTROL_REG, data);
/* Enable the oscillator , disable the oscillator stop flag,
and glitch filter to reduce current consumption */
- ds1347_read_reg(&spi->dev, DS1347_STATUS_REG, &data);
+ regmap_read(map, DS1347_STATUS_REG, &data);
data = data & 0x1B;
- ds1347_write_reg(&spi->dev, DS1347_STATUS_REG, data);
+ regmap_write(map, DS1347_STATUS_REG, data);
/* display the settings */
- ds1347_read_reg(&spi->dev, DS1347_CONTROL_REG, &data);
+ regmap_read(map, DS1347_CONTROL_REG, &data);
dev_info(&spi->dev, "DS1347 RTC CTRL Reg = 0x%02x\n", data);
- ds1347_read_reg(&spi->dev, DS1347_STATUS_REG, &data);
+ regmap_read(map, DS1347_STATUS_REG, &data);
dev_info(&spi->dev, "DS1347 RTC Status Reg = 0x%02x\n", data);
rtc = devm_rtc_device_register(&spi->dev, "ds1347",
@@ -146,8 +158,6 @@ static int ds1347_probe(struct spi_device *spi)
if (IS_ERR(rtc))
return PTR_ERR(rtc);
- spi_set_drvdata(spi, rtc);
-
return 0;
}
diff --git a/drivers/rtc/rtc-gemini.c b/drivers/rtc/rtc-gemini.c
index b57505e..688debc 100644
--- a/drivers/rtc/rtc-gemini.c
+++ b/drivers/rtc/rtc-gemini.c
@@ -110,7 +110,7 @@ static int gemini_rtc_set_time(struct device *dev, struct rtc_time *tm)
return 0;
}
-static struct rtc_class_ops gemini_rtc_ops = {
+static const struct rtc_class_ops gemini_rtc_ops = {
.read_time = gemini_rtc_read_time,
.set_time = gemini_rtc_set_time,
};
diff --git a/drivers/rtc/rtc-isl12057.c b/drivers/rtc/rtc-isl12057.c
deleted file mode 100644
index 0e7f0f5..0000000
--- a/drivers/rtc/rtc-isl12057.c
+++ /dev/null
@@ -1,643 +0,0 @@
-/*
- * rtc-isl12057 - Driver for Intersil ISL12057 I2C Real Time Clock
- *
- * Copyright (C) 2013, Arnaud EBALARD <arno@natisbad.org>
- *
- * This work is largely based on Intersil ISL1208 driver developed by
- * Hebert Valerio Riedel <hvr@gnu.org>.
- *
- * Detailed datasheet on which this development is based is available here:
- *
- * http://natisbad.org/NAS2/refs/ISL12057.pdf
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
-
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/rtc.h>
-#include <linux/i2c.h>
-#include <linux/bcd.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/regmap.h>
-
-#define DRV_NAME "rtc-isl12057"
-
-/* RTC section */
-#define ISL12057_REG_RTC_SC 0x00 /* Seconds */
-#define ISL12057_REG_RTC_MN 0x01 /* Minutes */
-#define ISL12057_REG_RTC_HR 0x02 /* Hours */
-#define ISL12057_REG_RTC_HR_PM BIT(5) /* AM/PM bit in 12h format */
-#define ISL12057_REG_RTC_HR_MIL BIT(6) /* 24h/12h format */
-#define ISL12057_REG_RTC_DW 0x03 /* Day of the Week */
-#define ISL12057_REG_RTC_DT 0x04 /* Date */
-#define ISL12057_REG_RTC_MO 0x05 /* Month */
-#define ISL12057_REG_RTC_MO_CEN BIT(7) /* Century bit */
-#define ISL12057_REG_RTC_YR 0x06 /* Year */
-#define ISL12057_RTC_SEC_LEN 7
-
-/* Alarm 1 section */
-#define ISL12057_REG_A1_SC 0x07 /* Alarm 1 Seconds */
-#define ISL12057_REG_A1_MN 0x08 /* Alarm 1 Minutes */
-#define ISL12057_REG_A1_HR 0x09 /* Alarm 1 Hours */
-#define ISL12057_REG_A1_HR_PM BIT(5) /* AM/PM bit in 12h format */
-#define ISL12057_REG_A1_HR_MIL BIT(6) /* 24h/12h format */
-#define ISL12057_REG_A1_DWDT 0x0A /* Alarm 1 Date / Day of the week */
-#define ISL12057_REG_A1_DWDT_B BIT(6) /* DW / DT selection bit */
-#define ISL12057_A1_SEC_LEN 4
-
-/* Alarm 2 section */
-#define ISL12057_REG_A2_MN 0x0B /* Alarm 2 Minutes */
-#define ISL12057_REG_A2_HR 0x0C /* Alarm 2 Hours */
-#define ISL12057_REG_A2_DWDT 0x0D /* Alarm 2 Date / Day of the week */
-#define ISL12057_A2_SEC_LEN 3
-
-/* Control/Status registers */
-#define ISL12057_REG_INT 0x0E
-#define ISL12057_REG_INT_A1IE BIT(0) /* Alarm 1 interrupt enable bit */
-#define ISL12057_REG_INT_A2IE BIT(1) /* Alarm 2 interrupt enable bit */
-#define ISL12057_REG_INT_INTCN BIT(2) /* Interrupt control enable bit */
-#define ISL12057_REG_INT_RS1 BIT(3) /* Freq out control bit 1 */
-#define ISL12057_REG_INT_RS2 BIT(4) /* Freq out control bit 2 */
-#define ISL12057_REG_INT_EOSC BIT(7) /* Oscillator enable bit */
-
-#define ISL12057_REG_SR 0x0F
-#define ISL12057_REG_SR_A1F BIT(0) /* Alarm 1 interrupt bit */
-#define ISL12057_REG_SR_A2F BIT(1) /* Alarm 2 interrupt bit */
-#define ISL12057_REG_SR_OSF BIT(7) /* Oscillator failure bit */
-
-/* Register memory map length */
-#define ISL12057_MEM_MAP_LEN 0x10
-
-struct isl12057_rtc_data {
- struct rtc_device *rtc;
- struct regmap *regmap;
- struct mutex lock;
- int irq;
-};
-
-static void isl12057_rtc_regs_to_tm(struct rtc_time *tm, u8 *regs)
-{
- tm->tm_sec = bcd2bin(regs[ISL12057_REG_RTC_SC]);
- tm->tm_min = bcd2bin(regs[ISL12057_REG_RTC_MN]);
-
- if (regs[ISL12057_REG_RTC_HR] & ISL12057_REG_RTC_HR_MIL) { /* AM/PM */
- tm->tm_hour = bcd2bin(regs[ISL12057_REG_RTC_HR] & 0x1f);
- if (regs[ISL12057_REG_RTC_HR] & ISL12057_REG_RTC_HR_PM)
- tm->tm_hour += 12;
- } else { /* 24 hour mode */
- tm->tm_hour = bcd2bin(regs[ISL12057_REG_RTC_HR] & 0x3f);
- }
-
- tm->tm_mday = bcd2bin(regs[ISL12057_REG_RTC_DT]);
- tm->tm_wday = bcd2bin(regs[ISL12057_REG_RTC_DW]) - 1; /* starts at 1 */
- tm->tm_mon = bcd2bin(regs[ISL12057_REG_RTC_MO] & 0x1f) - 1; /* ditto */
- tm->tm_year = bcd2bin(regs[ISL12057_REG_RTC_YR]) + 100;
-
- /* Check if years register has overflown from 99 to 00 */
- if (regs[ISL12057_REG_RTC_MO] & ISL12057_REG_RTC_MO_CEN)
- tm->tm_year += 100;
-}
-
-static int isl12057_rtc_tm_to_regs(u8 *regs, struct rtc_time *tm)
-{
- u8 century_bit;
-
- /*
- * The clock has an 8 bit wide bcd-coded register for the year.
- * It also has a century bit encoded in MO flag which provides
- * information about overflow of year register from 99 to 00.
- * tm_year is an offset from 1900 and we are interested in the
- * 2000-2199 range, so any value less than 100 or larger than
- * 299 is invalid.
- */
- if (tm->tm_year < 100 || tm->tm_year > 299)
- return -EINVAL;
-
- century_bit = (tm->tm_year > 199) ? ISL12057_REG_RTC_MO_CEN : 0;
-
- regs[ISL12057_REG_RTC_SC] = bin2bcd(tm->tm_sec);
- regs[ISL12057_REG_RTC_MN] = bin2bcd(tm->tm_min);
- regs[ISL12057_REG_RTC_HR] = bin2bcd(tm->tm_hour); /* 24-hour format */
- regs[ISL12057_REG_RTC_DT] = bin2bcd(tm->tm_mday);
- regs[ISL12057_REG_RTC_MO] = bin2bcd(tm->tm_mon + 1) | century_bit;
- regs[ISL12057_REG_RTC_YR] = bin2bcd(tm->tm_year % 100);
- regs[ISL12057_REG_RTC_DW] = bin2bcd(tm->tm_wday + 1);
-
- return 0;
-}
-
-/*
- * Try and match register bits w/ fixed null values to see whether we
- * are dealing with an ISL12057. Note: this function is called early
- * during init and hence does need mutex protection.
- */
-static int isl12057_i2c_validate_chip(struct regmap *regmap)
-{
- u8 regs[ISL12057_MEM_MAP_LEN];
- static const u8 mask[ISL12057_MEM_MAP_LEN] = { 0x80, 0x80, 0x80, 0xf8,
- 0xc0, 0x60, 0x00, 0x00,
- 0x00, 0x00, 0x00, 0x00,
- 0x00, 0x00, 0x60, 0x7c };
- int ret, i;
-
- ret = regmap_bulk_read(regmap, 0, regs, ISL12057_MEM_MAP_LEN);
- if (ret)
- return ret;
-
- for (i = 0; i < ISL12057_MEM_MAP_LEN; ++i) {
- if (regs[i] & mask[i]) /* check if bits are cleared */
- return -ENODEV;
- }
-
- return 0;
-}
-
-static int _isl12057_rtc_clear_alarm(struct device *dev)
-{
- struct isl12057_rtc_data *data = dev_get_drvdata(dev);
- int ret;
-
- ret = regmap_update_bits(data->regmap, ISL12057_REG_SR,
- ISL12057_REG_SR_A1F, 0);
- if (ret)
- dev_err(dev, "%s: clearing alarm failed (%d)\n", __func__, ret);
-
- return ret;
-}
-
-static int _isl12057_rtc_update_alarm(struct device *dev, int enable)
-{
- struct isl12057_rtc_data *data = dev_get_drvdata(dev);
- int ret;
-
- ret = regmap_update_bits(data->regmap, ISL12057_REG_INT,
- ISL12057_REG_INT_A1IE,
- enable ? ISL12057_REG_INT_A1IE : 0);
- if (ret)
- dev_err(dev, "%s: changing alarm interrupt flag failed (%d)\n",
- __func__, ret);
-
- return ret;
-}
-
-/*
- * Note: as we only read from device and do not perform any update, there is
- * no need for an equivalent function which would try and get driver's main
- * lock. Here, it is safe for everyone if we just use regmap internal lock
- * on the device when reading.
- */
-static int _isl12057_rtc_read_time(struct device *dev, struct rtc_time *tm)
-{
- struct isl12057_rtc_data *data = dev_get_drvdata(dev);
- u8 regs[ISL12057_RTC_SEC_LEN];
- unsigned int sr;
- int ret;
-
- ret = regmap_read(data->regmap, ISL12057_REG_SR, &sr);
- if (ret) {
- dev_err(dev, "%s: unable to read oscillator status flag (%d)\n",
- __func__, ret);
- goto out;
- } else {
- if (sr & ISL12057_REG_SR_OSF) {
- ret = -ENODATA;
- goto out;
- }
- }
-
- ret = regmap_bulk_read(data->regmap, ISL12057_REG_RTC_SC, regs,
- ISL12057_RTC_SEC_LEN);
- if (ret)
- dev_err(dev, "%s: unable to read RTC time section (%d)\n",
- __func__, ret);
-
-out:
- if (ret)
- return ret;
-
- isl12057_rtc_regs_to_tm(tm, regs);
-
- return rtc_valid_tm(tm);
-}
-
-static int isl12057_rtc_update_alarm(struct device *dev, int enable)
-{
- struct isl12057_rtc_data *data = dev_get_drvdata(dev);
- int ret;
-
- mutex_lock(&data->lock);
- ret = _isl12057_rtc_update_alarm(dev, enable);
- mutex_unlock(&data->lock);
-
- return ret;
-}
-
-static int isl12057_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
-{
- struct isl12057_rtc_data *data = dev_get_drvdata(dev);
- struct rtc_time *alarm_tm = &alarm->time;
- u8 regs[ISL12057_A1_SEC_LEN];
- unsigned int ir;
- int ret;
-
- mutex_lock(&data->lock);
- ret = regmap_bulk_read(data->regmap, ISL12057_REG_A1_SC, regs,
- ISL12057_A1_SEC_LEN);
- if (ret) {
- dev_err(dev, "%s: reading alarm section failed (%d)\n",
- __func__, ret);
- goto err_unlock;
- }
-
- alarm_tm->tm_sec = bcd2bin(regs[0] & 0x7f);
- alarm_tm->tm_min = bcd2bin(regs[1] & 0x7f);
- alarm_tm->tm_hour = bcd2bin(regs[2] & 0x3f);
- alarm_tm->tm_mday = bcd2bin(regs[3] & 0x3f);
-
- ret = regmap_read(data->regmap, ISL12057_REG_INT, &ir);
- if (ret) {
- dev_err(dev, "%s: reading alarm interrupt flag failed (%d)\n",
- __func__, ret);
- goto err_unlock;
- }
-
- alarm->enabled = !!(ir & ISL12057_REG_INT_A1IE);
-
-err_unlock:
- mutex_unlock(&data->lock);
-
- return ret;
-}
-
-static int isl12057_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
-{
- struct isl12057_rtc_data *data = dev_get_drvdata(dev);
- struct rtc_time *alarm_tm = &alarm->time;
- unsigned long rtc_secs, alarm_secs;
- u8 regs[ISL12057_A1_SEC_LEN];
- struct rtc_time rtc_tm;
- int ret, enable = 1;
-
- mutex_lock(&data->lock);
- ret = _isl12057_rtc_read_time(dev, &rtc_tm);
- if (ret)
- goto err_unlock;
-
- ret = rtc_tm_to_time(&rtc_tm, &rtc_secs);
- if (ret)
- goto err_unlock;
-
- ret = rtc_tm_to_time(alarm_tm, &alarm_secs);
- if (ret)
- goto err_unlock;
-
- /* If alarm time is before current time, disable the alarm */
- if (!alarm->enabled || alarm_secs <= rtc_secs) {
- enable = 0;
- } else {
- /*
- * Chip only support alarms up to one month in the future. Let's
- * return an error if we get something after that limit.
- * Comparison is done by incrementing rtc_tm month field by one
- * and checking alarm value is still below.
- */
- if (rtc_tm.tm_mon == 11) { /* handle year wrapping */
- rtc_tm.tm_mon = 0;
- rtc_tm.tm_year += 1;
- } else {
- rtc_tm.tm_mon += 1;
- }
-
- ret = rtc_tm_to_time(&rtc_tm, &rtc_secs);
- if (ret)
- goto err_unlock;
-
- if (alarm_secs > rtc_secs) {
- dev_err(dev, "%s: max for alarm is one month (%d)\n",
- __func__, ret);
- ret = -EINVAL;
- goto err_unlock;
- }
- }
-
- /* Disable the alarm before modifying it */
- ret = _isl12057_rtc_update_alarm(dev, 0);
- if (ret < 0) {
- dev_err(dev, "%s: unable to disable the alarm (%d)\n",
- __func__, ret);
- goto err_unlock;
- }
-
- /* Program alarm registers */
- regs[0] = bin2bcd(alarm_tm->tm_sec) & 0x7f;
- regs[1] = bin2bcd(alarm_tm->tm_min) & 0x7f;
- regs[2] = bin2bcd(alarm_tm->tm_hour) & 0x3f;
- regs[3] = bin2bcd(alarm_tm->tm_mday) & 0x3f;
-
- ret = regmap_bulk_write(data->regmap, ISL12057_REG_A1_SC, regs,
- ISL12057_A1_SEC_LEN);
- if (ret < 0) {
- dev_err(dev, "%s: writing alarm section failed (%d)\n",
- __func__, ret);
- goto err_unlock;
- }
-
- /* Enable or disable alarm */
- ret = _isl12057_rtc_update_alarm(dev, enable);
-
-err_unlock:
- mutex_unlock(&data->lock);
-
- return ret;
-}
-
-static int isl12057_rtc_set_time(struct device *dev, struct rtc_time *tm)
-{
- struct isl12057_rtc_data *data = dev_get_drvdata(dev);
- u8 regs[ISL12057_RTC_SEC_LEN];
- int ret;
-
- ret = isl12057_rtc_tm_to_regs(regs, tm);
- if (ret)
- return ret;
-
- mutex_lock(&data->lock);
- ret = regmap_bulk_write(data->regmap, ISL12057_REG_RTC_SC, regs,
- ISL12057_RTC_SEC_LEN);
- if (ret) {
- dev_err(dev, "%s: unable to write RTC time section (%d)\n",
- __func__, ret);
- goto out;
- }
-
- /*
- * Now that RTC time has been updated, let's clear oscillator
- * failure flag, if needed.
- */
- ret = regmap_update_bits(data->regmap, ISL12057_REG_SR,
- ISL12057_REG_SR_OSF, 0);
- if (ret < 0)
- dev_err(dev, "%s: unable to clear osc. failure bit (%d)\n",
- __func__, ret);
-
-out:
- mutex_unlock(&data->lock);
-
- return ret;
-}
-
-/*
- * Check current RTC status and enable/disable what needs to be. Return 0 if
- * everything went ok and a negative value upon error. Note: this function
- * is called early during init and hence does need mutex protection.
- */
-static int isl12057_check_rtc_status(struct device *dev, struct regmap *regmap)
-{
- int ret;
-
- /* Enable oscillator if not already running */
- ret = regmap_update_bits(regmap, ISL12057_REG_INT,
- ISL12057_REG_INT_EOSC, 0);
- if (ret < 0) {
- dev_err(dev, "%s: unable to enable oscillator (%d)\n",
- __func__, ret);
- return ret;
- }
-
- /* Clear alarm bit if needed */
- ret = regmap_update_bits(regmap, ISL12057_REG_SR,
- ISL12057_REG_SR_A1F, 0);
- if (ret < 0) {
- dev_err(dev, "%s: unable to clear alarm bit (%d)\n",
- __func__, ret);
- return ret;
- }
-
- return 0;
-}
-
-#ifdef CONFIG_OF
-/*
- * One would expect the device to be marked as a wakeup source only
- * when an IRQ pin of the RTC is routed to an interrupt line of the
- * CPU. In practice, such an IRQ pin can be connected to a PMIC and
- * this allows the device to be powered up when RTC alarm rings. This
- * is for instance the case on ReadyNAS 102, 104 and 2120. On those
- * devices with no IRQ driectly connected to the SoC, the RTC chip
- * can be forced as a wakeup source by stating that explicitly in
- * the device's .dts file using the "wakeup-source" boolean property.
- * This will guarantee 'wakealarm' sysfs entry is available on the device.
- *
- * The function below returns 1, i.e. the capability of the chip to
- * wakeup the device, based on IRQ availability or if the boolean
- * property has been set in the .dts file. Otherwise, it returns 0.
- */
-
-static bool isl12057_can_wakeup_machine(struct device *dev)
-{
- struct isl12057_rtc_data *data = dev_get_drvdata(dev);
-
- return data->irq || of_property_read_bool(dev->of_node, "wakeup-source")
- || of_property_read_bool(dev->of_node, /* legacy */
- "isil,irq2-can-wakeup-machine");
-}
-#else
-static bool isl12057_can_wakeup_machine(struct device *dev)
-{
- struct isl12057_rtc_data *data = dev_get_drvdata(dev);
-
- return !!data->irq;
-}
-#endif
-
-static int isl12057_rtc_alarm_irq_enable(struct device *dev,
- unsigned int enable)
-{
- struct isl12057_rtc_data *rtc_data = dev_get_drvdata(dev);
- int ret = -ENOTTY;
-
- if (rtc_data->irq)
- ret = isl12057_rtc_update_alarm(dev, enable);
-
- return ret;
-}
-
-static irqreturn_t isl12057_rtc_interrupt(int irq, void *data)
-{
- struct i2c_client *client = data;
- struct isl12057_rtc_data *rtc_data = dev_get_drvdata(&client->dev);
- struct rtc_device *rtc = rtc_data->rtc;
- int ret, handled = IRQ_NONE;
- unsigned int sr;
-
- ret = regmap_read(rtc_data->regmap, ISL12057_REG_SR, &sr);
- if (!ret && (sr & ISL12057_REG_SR_A1F)) {
- dev_dbg(&client->dev, "RTC alarm!\n");
-
- rtc_update_irq(rtc, 1, RTC_IRQF | RTC_AF);
-
- /* Acknowledge and disable the alarm */
- _isl12057_rtc_clear_alarm(&client->dev);
- _isl12057_rtc_update_alarm(&client->dev, 0);
-
- handled = IRQ_HANDLED;
- }
-
- return handled;
-}
-
-static const struct rtc_class_ops rtc_ops = {
- .read_time = _isl12057_rtc_read_time,
- .set_time = isl12057_rtc_set_time,
- .read_alarm = isl12057_rtc_read_alarm,
- .set_alarm = isl12057_rtc_set_alarm,
- .alarm_irq_enable = isl12057_rtc_alarm_irq_enable,
-};
-
-static const struct regmap_config isl12057_rtc_regmap_config = {
- .reg_bits = 8,
- .val_bits = 8,
-};
-
-static int isl12057_probe(struct i2c_client *client,
- const struct i2c_device_id *id)
-{
- struct device *dev = &client->dev;
- struct isl12057_rtc_data *data;
- struct regmap *regmap;
- int ret;
-
- if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C |
- I2C_FUNC_SMBUS_BYTE_DATA |
- I2C_FUNC_SMBUS_I2C_BLOCK))
- return -ENODEV;
-
- regmap = devm_regmap_init_i2c(client, &isl12057_rtc_regmap_config);
- if (IS_ERR(regmap)) {
- ret = PTR_ERR(regmap);
- dev_err(dev, "%s: regmap allocation failed (%d)\n",
- __func__, ret);
- return ret;
- }
-
- ret = isl12057_i2c_validate_chip(regmap);
- if (ret)
- return ret;
-
- ret = isl12057_check_rtc_status(dev, regmap);
- if (ret)
- return ret;
-
- data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
- if (!data)
- return -ENOMEM;
-
- mutex_init(&data->lock);
- data->regmap = regmap;
- dev_set_drvdata(dev, data);
-
- if (client->irq > 0) {
- ret = devm_request_threaded_irq(dev, client->irq, NULL,
- isl12057_rtc_interrupt,
- IRQF_SHARED|IRQF_ONESHOT,
- DRV_NAME, client);
- if (!ret)
- data->irq = client->irq;
- else
- dev_err(dev, "%s: irq %d unavailable (%d)\n", __func__,
- client->irq, ret);
- }
-
- if (isl12057_can_wakeup_machine(dev))
- device_init_wakeup(dev, true);
-
- data->rtc = devm_rtc_device_register(dev, DRV_NAME, &rtc_ops,
- THIS_MODULE);
- ret = PTR_ERR_OR_ZERO(data->rtc);
- if (ret) {
- dev_err(dev, "%s: unable to register RTC device (%d)\n",
- __func__, ret);
- goto err;
- }
-
- /* We cannot support UIE mode if we do not have an IRQ line */
- if (!data->irq)
- data->rtc->uie_unsupported = 1;
-
-err:
- return ret;
-}
-
-static int isl12057_remove(struct i2c_client *client)
-{
- if (isl12057_can_wakeup_machine(&client->dev))
- device_init_wakeup(&client->dev, false);
-
- return 0;
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int isl12057_rtc_suspend(struct device *dev)
-{
- struct isl12057_rtc_data *rtc_data = dev_get_drvdata(dev);
-
- if (rtc_data->irq && device_may_wakeup(dev))
- return enable_irq_wake(rtc_data->irq);
-
- return 0;
-}
-
-static int isl12057_rtc_resume(struct device *dev)
-{
- struct isl12057_rtc_data *rtc_data = dev_get_drvdata(dev);
-
- if (rtc_data->irq && device_may_wakeup(dev))
- return disable_irq_wake(rtc_data->irq);
-
- return 0;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(isl12057_rtc_pm_ops, isl12057_rtc_suspend,
- isl12057_rtc_resume);
-
-#ifdef CONFIG_OF
-static const struct of_device_id isl12057_dt_match[] = {
- { .compatible = "isl,isl12057" }, /* for backward compat., don't use */
- { .compatible = "isil,isl12057" },
- { },
-};
-MODULE_DEVICE_TABLE(of, isl12057_dt_match);
-#endif
-
-static const struct i2c_device_id isl12057_id[] = {
- { "isl12057", 0 },
- { }
-};
-MODULE_DEVICE_TABLE(i2c, isl12057_id);
-
-static struct i2c_driver isl12057_driver = {
- .driver = {
- .name = DRV_NAME,
- .pm = &isl12057_rtc_pm_ops,
- .of_match_table = of_match_ptr(isl12057_dt_match),
- },
- .probe = isl12057_probe,
- .remove = isl12057_remove,
- .id_table = isl12057_id,
-};
-module_i2c_driver(isl12057_driver);
-
-MODULE_AUTHOR("Arnaud EBALARD <arno@natisbad.org>");
-MODULE_DESCRIPTION("Intersil ISL12057 RTC driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c
index b2bcfc0..5e14651 100644
--- a/drivers/rtc/rtc-jz4740.c
+++ b/drivers/rtc/rtc-jz4740.c
@@ -174,7 +174,7 @@ static int jz4740_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
return jz4740_rtc_ctrl_set_bits(rtc, JZ_RTC_CTRL_AF_IRQ, enable);
}
-static struct rtc_class_ops jz4740_rtc_ops = {
+static const struct rtc_class_ops jz4740_rtc_ops = {
.read_time = jz4740_rtc_read_time,
.set_mmss = jz4740_rtc_set_mmss,
.read_alarm = jz4740_rtc_read_alarm,
diff --git a/drivers/rtc/rtc-mcp795.c b/drivers/rtc/rtc-mcp795.c
index 025bb33..4021fd0 100644
--- a/drivers/rtc/rtc-mcp795.c
+++ b/drivers/rtc/rtc-mcp795.c
@@ -151,7 +151,7 @@ static int mcp795_read_time(struct device *dev, struct rtc_time *tim)
return rtc_valid_tm(tim);
}
-static struct rtc_class_ops mcp795_rtc_ops = {
+static const struct rtc_class_ops mcp795_rtc_ops = {
.read_time = mcp795_read_time,
.set_time = mcp795_set_time
};
diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c
index 44f622c..1a61fa5 100644
--- a/drivers/rtc/rtc-mt6397.c
+++ b/drivers/rtc/rtc-mt6397.c
@@ -301,7 +301,7 @@ static int mtk_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
return ret;
}
-static struct rtc_class_ops mtk_rtc_ops = {
+static const struct rtc_class_ops mtk_rtc_ops = {
.read_time = mtk_rtc_read_time,
.set_time = mtk_rtc_set_time,
.read_alarm = mtk_rtc_read_alarm,
diff --git a/drivers/rtc/rtc-nuc900.c b/drivers/rtc/rtc-nuc900.c
index 09fc1c1..b1b6b30 100644
--- a/drivers/rtc/rtc-nuc900.c
+++ b/drivers/rtc/rtc-nuc900.c
@@ -214,7 +214,7 @@ static int nuc900_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
return 0;
}
-static struct rtc_class_ops nuc900_rtc_ops = {
+static const struct rtc_class_ops nuc900_rtc_ops = {
.read_time = nuc900_rtc_read_time,
.set_time = nuc900_rtc_set_time,
.read_alarm = nuc900_rtc_read_alarm,
diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c
index ec2e9c5..51e5244 100644
--- a/drivers/rtc/rtc-omap.c
+++ b/drivers/rtc/rtc-omap.c
@@ -13,19 +13,23 @@
* 2 of the License, or (at your option) any later version.
*/
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/ioport.h>
-#include <linux/delay.h>
-#include <linux/rtc.h>
+#include <dt-bindings/gpio/gpio.h>
#include <linux/bcd.h>
-#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
#include <linux/of.h>
#include <linux/of_device.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
-#include <linux/io.h>
-#include <linux/clk.h>
+#include <linux/rtc.h>
/*
* The OMAP RTC is a year/month/day/hours/minutes/seconds BCD clock
@@ -109,12 +113,15 @@
/* OMAP_RTC_OSC_REG bit fields: */
#define OMAP_RTC_OSC_32KCLK_EN BIT(6)
#define OMAP_RTC_OSC_SEL_32KCLK_SRC BIT(3)
+#define OMAP_RTC_OSC_OSC32K_GZ_DISABLE BIT(4)
/* OMAP_RTC_IRQWAKEEN bit fields: */
#define OMAP_RTC_IRQWAKEEN_ALARM_WAKEEN BIT(1)
/* OMAP_RTC_PMIC bit fields: */
#define OMAP_RTC_PMIC_POWER_EN_EN BIT(16)
+#define OMAP_RTC_PMIC_EXT_WKUP_EN(x) BIT(x)
+#define OMAP_RTC_PMIC_EXT_WKUP_POL(x) BIT(4 + x)
/* OMAP_RTC_KICKER values */
#define KICK0_VALUE 0x83e70b13
@@ -140,7 +147,9 @@ struct omap_rtc {
u8 interrupts_reg;
bool is_pmic_controller;
bool has_ext_clk;
+ bool is_suspending;
const struct omap_rtc_device_type *type;
+ struct pinctrl_dev *pctldev;
};
static inline u8 rtc_read(struct omap_rtc *rtc, unsigned int reg)
@@ -469,7 +478,7 @@ static void omap_rtc_power_off(void)
mdelay(2500);
}
-static struct rtc_class_ops omap_rtc_ops = {
+static const struct rtc_class_ops omap_rtc_ops = {
.read_time = omap_rtc_read_time,
.set_time = omap_rtc_set_time,
.read_alarm = omap_rtc_read_alarm,
@@ -525,6 +534,139 @@ static const struct of_device_id omap_rtc_of_match[] = {
};
MODULE_DEVICE_TABLE(of, omap_rtc_of_match);
+static const struct pinctrl_pin_desc rtc_pins_desc[] = {
+ PINCTRL_PIN(0, "ext_wakeup0"),
+ PINCTRL_PIN(1, "ext_wakeup1"),
+ PINCTRL_PIN(2, "ext_wakeup2"),
+ PINCTRL_PIN(3, "ext_wakeup3"),
+};
+
+static int rtc_pinctrl_get_groups_count(struct pinctrl_dev *pctldev)
+{
+ return 0;
+}
+
+static const char *rtc_pinctrl_get_group_name(struct pinctrl_dev *pctldev,
+ unsigned int group)
+{
+ return NULL;
+}
+
+static const struct pinctrl_ops rtc_pinctrl_ops = {
+ .get_groups_count = rtc_pinctrl_get_groups_count,
+ .get_group_name = rtc_pinctrl_get_group_name,
+ .dt_node_to_map = pinconf_generic_dt_node_to_map_pin,
+ .dt_free_map = pinconf_generic_dt_free_map,
+};
+
+enum rtc_pin_config_param {
+ PIN_CONFIG_ACTIVE_HIGH = PIN_CONFIG_END + 1,
+};
+
+static const struct pinconf_generic_params rtc_params[] = {
+ {"ti,active-high", PIN_CONFIG_ACTIVE_HIGH, 0},
+};
+
+#ifdef CONFIG_DEBUG_FS
+static const struct pin_config_item rtc_conf_items[ARRAY_SIZE(rtc_params)] = {
+ PCONFDUMP(PIN_CONFIG_ACTIVE_HIGH, "input active high", NULL, false),
+};
+#endif
+
+static int rtc_pinconf_get(struct pinctrl_dev *pctldev,
+ unsigned int pin, unsigned long *config)
+{
+ struct omap_rtc *rtc = pinctrl_dev_get_drvdata(pctldev);
+ unsigned int param = pinconf_to_config_param(*config);
+ u32 val;
+ u16 arg = 0;
+
+ rtc->type->unlock(rtc);
+ val = rtc_readl(rtc, OMAP_RTC_PMIC_REG);
+ rtc->type->lock(rtc);
+
+ switch (param) {
+ case PIN_CONFIG_INPUT_ENABLE:
+ if (!(val & OMAP_RTC_PMIC_EXT_WKUP_EN(pin)))
+ return -EINVAL;
+ break;
+ case PIN_CONFIG_ACTIVE_HIGH:
+ if (val & OMAP_RTC_PMIC_EXT_WKUP_POL(pin))
+ return -EINVAL;
+ break;
+ default:
+ return -ENOTSUPP;
+ };
+
+ *config = pinconf_to_config_packed(param, arg);
+
+ return 0;
+}
+
+static int rtc_pinconf_set(struct pinctrl_dev *pctldev,
+ unsigned int pin, unsigned long *configs,
+ unsigned int num_configs)
+{
+ struct omap_rtc *rtc = pinctrl_dev_get_drvdata(pctldev);
+ u32 val;
+ unsigned int param;
+ u16 param_val;
+ int i;
+
+ rtc->type->unlock(rtc);
+ val = rtc_readl(rtc, OMAP_RTC_PMIC_REG);
+ rtc->type->lock(rtc);
+
+ /* active low by default */
+ val |= OMAP_RTC_PMIC_EXT_WKUP_POL(pin);
+
+ for (i = 0; i < num_configs; i++) {
+ param = pinconf_to_config_param(configs[i]);
+ param_val = pinconf_to_config_argument(configs[i]);
+
+ switch (param) {
+ case PIN_CONFIG_INPUT_ENABLE:
+ if (param_val)
+ val |= OMAP_RTC_PMIC_EXT_WKUP_EN(pin);
+ else
+ val &= ~OMAP_RTC_PMIC_EXT_WKUP_EN(pin);
+ break;
+ case PIN_CONFIG_ACTIVE_HIGH:
+ val &= ~OMAP_RTC_PMIC_EXT_WKUP_POL(pin);
+ break;
+ default:
+ dev_err(&rtc->rtc->dev, "Property %u not supported\n",
+ param);
+ return -ENOTSUPP;
+ }
+ }
+
+ rtc->type->unlock(rtc);
+ rtc_writel(rtc, OMAP_RTC_PMIC_REG, val);
+ rtc->type->lock(rtc);
+
+ return 0;
+}
+
+static const struct pinconf_ops rtc_pinconf_ops = {
+ .is_generic = true,
+ .pin_config_get = rtc_pinconf_get,
+ .pin_config_set = rtc_pinconf_set,
+};
+
+static struct pinctrl_desc rtc_pinctrl_desc = {
+ .pins = rtc_pins_desc,
+ .npins = ARRAY_SIZE(rtc_pins_desc),
+ .pctlops = &rtc_pinctrl_ops,
+ .confops = &rtc_pinconf_ops,
+ .custom_params = rtc_params,
+ .num_custom_params = ARRAY_SIZE(rtc_params),
+#ifdef CONFIG_DEBUG_FS
+ .custom_conf_items = rtc_conf_items,
+#endif
+ .owner = THIS_MODULE,
+};
+
static int omap_rtc_probe(struct platform_device *pdev)
{
struct omap_rtc *rtc;
@@ -646,8 +788,9 @@ static int omap_rtc_probe(struct platform_device *pdev)
*/
if (rtc->has_ext_clk) {
reg = rtc_read(rtc, OMAP_RTC_OSC_REG);
- rtc_write(rtc, OMAP_RTC_OSC_REG,
- reg | OMAP_RTC_OSC_SEL_32KCLK_SRC);
+ reg &= ~OMAP_RTC_OSC_OSC32K_GZ_DISABLE;
+ reg |= OMAP_RTC_OSC_32KCLK_EN | OMAP_RTC_OSC_SEL_32KCLK_SRC;
+ rtc_writel(rtc, OMAP_RTC_OSC_REG, reg);
}
rtc->type->lock(rtc);
@@ -681,6 +824,15 @@ static int omap_rtc_probe(struct platform_device *pdev)
}
}
+ /* Support ext_wakeup pinconf */
+ rtc_pinctrl_desc.name = dev_name(&pdev->dev);
+
+ rtc->pctldev = pinctrl_register(&rtc_pinctrl_desc, &pdev->dev, rtc);
+ if (IS_ERR(rtc->pctldev)) {
+ dev_err(&pdev->dev, "Couldn't register pinctrl driver\n");
+ return PTR_ERR(rtc->pctldev);
+ }
+
return 0;
err:
@@ -724,6 +876,9 @@ static int __exit omap_rtc_remove(struct platform_device *pdev)
pm_runtime_put_sync(&pdev->dev);
pm_runtime_disable(&pdev->dev);
+ /* Remove ext_wakeup pinconf */
+ pinctrl_unregister(rtc->pctldev);
+
return 0;
}
@@ -746,8 +901,7 @@ static int omap_rtc_suspend(struct device *dev)
rtc_write(rtc, OMAP_RTC_INTERRUPTS_REG, 0);
rtc->type->lock(rtc);
- /* Disable the clock/module */
- pm_runtime_put_sync(dev);
+ rtc->is_suspending = true;
return 0;
}
@@ -756,9 +910,6 @@ static int omap_rtc_resume(struct device *dev)
{
struct omap_rtc *rtc = dev_get_drvdata(dev);
- /* Enable the clock/module so that we can access the registers */
- pm_runtime_get_sync(dev);
-
rtc->type->unlock(rtc);
if (device_may_wakeup(dev))
disable_irq_wake(rtc->irq_alarm);
@@ -766,11 +917,34 @@ static int omap_rtc_resume(struct device *dev)
rtc_write(rtc, OMAP_RTC_INTERRUPTS_REG, rtc->interrupts_reg);
rtc->type->lock(rtc);
+ rtc->is_suspending = false;
+
return 0;
}
#endif
-static SIMPLE_DEV_PM_OPS(omap_rtc_pm_ops, omap_rtc_suspend, omap_rtc_resume);
+#ifdef CONFIG_PM
+static int omap_rtc_runtime_suspend(struct device *dev)
+{
+ struct omap_rtc *rtc = dev_get_drvdata(dev);
+
+ if (rtc->is_suspending && !rtc->has_ext_clk)
+ return -EBUSY;
+
+ return 0;
+}
+
+static int omap_rtc_runtime_resume(struct device *dev)
+{
+ return 0;
+}
+#endif
+
+static const struct dev_pm_ops omap_rtc_pm_ops = {
+ SET_SYSTEM_SLEEP_PM_OPS(omap_rtc_suspend, omap_rtc_resume)
+ SET_RUNTIME_PM_OPS(omap_rtc_runtime_suspend,
+ omap_rtc_runtime_resume, NULL)
+};
static void omap_rtc_shutdown(struct platform_device *pdev)
{
diff --git a/drivers/rtc/rtc-palmas.c b/drivers/rtc/rtc-palmas.c
index 6080e0e..4bcfb88 100644
--- a/drivers/rtc/rtc-palmas.c
+++ b/drivers/rtc/rtc-palmas.c
@@ -225,7 +225,7 @@ static irqreturn_t palmas_rtc_interrupt(int irq, void *context)
return IRQ_HANDLED;
}
-static struct rtc_class_ops palmas_rtc_ops = {
+static const struct rtc_class_ops palmas_rtc_ops = {
.read_time = palmas_rtc_read_time,
.set_time = palmas_rtc_set_time,
.read_alarm = palmas_rtc_read_alarm,
diff --git a/drivers/rtc/rtc-pcf2123.c b/drivers/rtc/rtc-pcf2123.c
index b4478cc..8895f77 100644
--- a/drivers/rtc/rtc-pcf2123.c
+++ b/drivers/rtc/rtc-pcf2123.c
@@ -182,7 +182,8 @@ static ssize_t pcf2123_show(struct device *dev, struct device_attribute *attr,
}
static ssize_t pcf2123_store(struct device *dev, struct device_attribute *attr,
- const char *buffer, size_t count) {
+ const char *buffer, size_t count)
+{
struct pcf2123_sysfs_reg *r;
unsigned long reg;
unsigned long val;
@@ -199,7 +200,7 @@ static ssize_t pcf2123_store(struct device *dev, struct device_attribute *attr,
if (ret)
return ret;
- pcf2123_write_reg(dev, reg, val);
+ ret = pcf2123_write_reg(dev, reg, val);
if (ret < 0)
return -EIO;
return count;
diff --git a/drivers/rtc/rtc-pcf50633.c b/drivers/rtc/rtc-pcf50633.c
index e6b6911..00c31c9 100644
--- a/drivers/rtc/rtc-pcf50633.c
+++ b/drivers/rtc/rtc-pcf50633.c
@@ -232,7 +232,7 @@ static int pcf50633_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
return ret;
}
-static struct rtc_class_ops pcf50633_rtc_ops = {
+static const struct rtc_class_ops pcf50633_rtc_ops = {
.read_time = pcf50633_rtc_read_time,
.set_time = pcf50633_rtc_set_time,
.read_alarm = pcf50633_rtc_read_alarm,
diff --git a/drivers/rtc/rtc-pic32.c b/drivers/rtc/rtc-pic32.c
index 64e1e45..5cfb6df 100644
--- a/drivers/rtc/rtc-pic32.c
+++ b/drivers/rtc/rtc-pic32.c
@@ -400,7 +400,6 @@ static struct platform_driver pic32_rtc_driver = {
.remove = pic32_rtc_remove,
.driver = {
.name = "pic32-rtc",
- .owner = THIS_MODULE,
.of_match_table = of_match_ptr(pic32_rtc_dt_ids),
},
};
diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c
index 9a2f6a9..f9277e5 100644
--- a/drivers/rtc/rtc-rv8803.c
+++ b/drivers/rtc/rtc-rv8803.c
@@ -52,11 +52,21 @@
#define RV8803_CTRL_TIE BIT(4)
#define RV8803_CTRL_UIE BIT(5)
+#define RX8900_BACKUP_CTRL 0x18
+#define RX8900_FLAG_SWOFF BIT(2)
+#define RX8900_FLAG_VDETOFF BIT(3)
+
+enum rv8803_type {
+ rv_8803,
+ rx_8900
+};
+
struct rv8803_data {
struct i2c_client *client;
struct rtc_device *rtc;
struct mutex flags_lock;
u8 ctrl;
+ enum rv8803_type type;
};
static int rv8803_read_reg(const struct i2c_client *client, u8 reg)
@@ -497,6 +507,35 @@ static struct rtc_class_ops rv8803_rtc_ops = {
.ioctl = rv8803_ioctl,
};
+static int rx8900_trickle_charger_init(struct rv8803_data *rv8803)
+{
+ struct i2c_client *client = rv8803->client;
+ struct device_node *node = client->dev.of_node;
+ int err;
+ u8 flags;
+
+ if (!node)
+ return 0;
+
+ if (rv8803->type != rx_8900)
+ return 0;
+
+ err = i2c_smbus_read_byte_data(rv8803->client, RX8900_BACKUP_CTRL);
+ if (err < 0)
+ return err;
+
+ flags = ~(RX8900_FLAG_VDETOFF | RX8900_FLAG_SWOFF) & (u8)err;
+
+ if (of_property_read_bool(node, "epson,vdet-disable"))
+ flags |= RX8900_FLAG_VDETOFF;
+
+ if (of_property_read_bool(node, "trickle-diode-disable"))
+ flags |= RX8900_FLAG_SWOFF;
+
+ return i2c_smbus_write_byte_data(rv8803->client, RX8900_BACKUP_CTRL,
+ flags);
+}
+
static int rv8803_probe(struct i2c_client *client,
const struct i2c_device_id *id)
{
@@ -517,6 +556,7 @@ static int rv8803_probe(struct i2c_client *client,
mutex_init(&rv8803->flags_lock);
rv8803->client = client;
+ rv8803->type = id->driver_data;
i2c_set_clientdata(client, rv8803);
flags = rv8803_read_reg(client, RV8803_FLAG);
@@ -558,6 +598,12 @@ static int rv8803_probe(struct i2c_client *client,
if (err)
return err;
+ err = rx8900_trickle_charger_init(rv8803);
+ if (err) {
+ dev_err(&client->dev, "failed to init charger\n");
+ return err;
+ }
+
err = device_create_bin_file(&client->dev, &rv8803_nvram_attr);
if (err)
return err;
@@ -575,8 +621,8 @@ static int rv8803_remove(struct i2c_client *client)
}
static const struct i2c_device_id rv8803_id[] = {
- { "rv8803", 0 },
- { "rx8900", 0 },
+ { "rv8803", rv_8803 },
+ { "rx8900", rx_8900 },
{ }
};
MODULE_DEVICE_TABLE(i2c, rv8803_id);
diff --git a/drivers/rtc/rtc-rx6110.c b/drivers/rtc/rtc-rx6110.c
index bbad00b..7c9c08e 100644
--- a/drivers/rtc/rtc-rx6110.c
+++ b/drivers/rtc/rtc-rx6110.c
@@ -317,7 +317,7 @@ static int rx6110_init(struct rx6110_data *rx6110)
return ret;
}
-static struct rtc_class_ops rx6110_rtc_ops = {
+static const struct rtc_class_ops rx6110_rtc_ops = {
.read_time = rx6110_get_time,
.set_time = rx6110_set_time,
};
@@ -388,7 +388,6 @@ MODULE_DEVICE_TABLE(spi, rx6110_id);
static struct spi_driver rx6110_driver = {
.driver = {
.name = RX6110_DRIVER_NAME,
- .owner = THIS_MODULE,
},
.probe = rx6110_probe,
.remove = rx6110_remove,
diff --git a/drivers/rtc/rtc-rx8025.c b/drivers/rtc/rtc-rx8025.c
index 2b85cc7..91857d8 100644
--- a/drivers/rtc/rtc-rx8025.c
+++ b/drivers/rtc/rtc-rx8025.c
@@ -403,7 +403,7 @@ static int rx8025_alarm_irq_enable(struct device *dev, unsigned int enabled)
return 0;
}
-static struct rtc_class_ops rx8025_rtc_ops = {
+static const struct rtc_class_ops rx8025_rtc_ops = {
.read_time = rx8025_get_time,
.set_time = rx8025_set_time,
.read_alarm = rx8025_read_alarm,
diff --git a/drivers/rtc/rtc-spear.c b/drivers/rtc/rtc-spear.c
index f05ef85..e377f42 100644
--- a/drivers/rtc/rtc-spear.c
+++ b/drivers/rtc/rtc-spear.c
@@ -343,7 +343,7 @@ static int spear_alarm_irq_enable(struct device *dev, unsigned int enabled)
return ret;
}
-static struct rtc_class_ops spear_rtc_ops = {
+static const struct rtc_class_ops spear_rtc_ops = {
.read_time = spear_rtc_read_time,
.set_time = spear_rtc_set_time,
.read_alarm = spear_rtc_read_alarm,
diff --git a/drivers/rtc/rtc-stmp3xxx.c b/drivers/rtc/rtc-stmp3xxx.c
index e6aaaa5..d578e40 100644
--- a/drivers/rtc/rtc-stmp3xxx.c
+++ b/drivers/rtc/rtc-stmp3xxx.c
@@ -231,7 +231,7 @@ static int stmp3xxx_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
return 0;
}
-static struct rtc_class_ops stmp3xxx_rtc_ops = {
+static const struct rtc_class_ops stmp3xxx_rtc_ops = {
.alarm_irq_enable =
stmp3xxx_alarm_irq_enable,
.read_time = stmp3xxx_rtc_gettime,
diff --git a/drivers/rtc/rtc-sysfs.c b/drivers/rtc/rtc-sysfs.c
index 63b9fb1..1218d5d 100644
--- a/drivers/rtc/rtc-sysfs.c
+++ b/drivers/rtc/rtc-sysfs.c
@@ -160,7 +160,7 @@ wakealarm_store(struct device *dev, struct device_attribute *attr,
unsigned long push = 0;
struct rtc_wkalrm alm;
struct rtc_device *rtc = to_rtc_device(dev);
- char *buf_ptr;
+ const char *buf_ptr;
int adjust = 0;
/* Only request alarms that trigger in the future. Disable them
@@ -171,7 +171,7 @@ wakealarm_store(struct device *dev, struct device_attribute *attr,
return retval;
rtc_tm_to_time(&alm.time, &now);
- buf_ptr = (char *)buf;
+ buf_ptr = buf;
if (*buf_ptr == '+') {
buf_ptr++;
if (*buf_ptr == '=') {
diff --git a/drivers/rtc/rtc-tegra.c b/drivers/rtc/rtc-tegra.c
index 15ac597..3853ba9 100644
--- a/drivers/rtc/rtc-tegra.c
+++ b/drivers/rtc/rtc-tegra.c
@@ -291,7 +291,7 @@ static irqreturn_t tegra_rtc_irq_handler(int irq, void *data)
return IRQ_HANDLED;
}
-static struct rtc_class_ops tegra_rtc_ops = {
+static const struct rtc_class_ops tegra_rtc_ops = {
.read_time = tegra_rtc_read_time,
.set_time = tegra_rtc_set_time,
.read_alarm = tegra_rtc_read_alarm,
diff --git a/drivers/rtc/rtc-twl.c b/drivers/rtc/rtc-twl.c
index 2dc787d..176720b 100644
--- a/drivers/rtc/rtc-twl.c
+++ b/drivers/rtc/rtc-twl.c
@@ -462,7 +462,7 @@ static irqreturn_t twl_rtc_interrupt(int irq, void *rtc)
return ret;
}
-static struct rtc_class_ops twl_rtc_ops = {
+static const struct rtc_class_ops twl_rtc_ops = {
.read_time = twl_rtc_read_time,
.set_time = twl_rtc_set_time,
.read_alarm = twl_rtc_read_alarm,
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 831935a..a7a8847 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -1205,7 +1205,7 @@ static int verify_fcx_max_data(struct dasd_device *device, __u8 lpm)
mdc, lpm);
return mdc;
}
- fcx_max_data = mdc * FCX_MAX_DATA_FACTOR;
+ fcx_max_data = (u32)mdc * FCX_MAX_DATA_FACTOR;
if (fcx_max_data < private->fcx_max_data) {
dev_warn(&device->cdev->dev,
"The maximum data size for zHPF requests %u "
@@ -1675,7 +1675,7 @@ static u32 get_fcx_max_data(struct dasd_device *device)
" data size for zHPF requests failed\n");
return 0;
} else
- return mdc * FCX_MAX_DATA_FACTOR;
+ return (u32)mdc * FCX_MAX_DATA_FACTOR;
}
/*
diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c
index 46be25c..876c7e6 100644
--- a/drivers/s390/cio/chp.c
+++ b/drivers/s390/cio/chp.c
@@ -780,7 +780,7 @@ static int cfg_wait_idle(void)
static int __init chp_init(void)
{
struct chp_id chpid;
- int ret;
+ int state, ret;
ret = crw_register_handler(CRW_RSC_CPATH, chp_process_crw);
if (ret)
@@ -791,7 +791,9 @@ static int __init chp_init(void)
return 0;
/* Register available channel-paths. */
chp_id_for_each(&chpid) {
- if (chp_info_get_status(chpid) != CHP_STATUS_NOT_RECOGNIZED)
+ state = chp_info_get_status(chpid);
+ if (state == CHP_STATUS_CONFIGURED ||
+ state == CHP_STATUS_STANDBY)
chp_new(chpid);
}
diff --git a/drivers/s390/scsi/zfcp_dbf.c b/drivers/s390/scsi/zfcp_dbf.c
index 637cf89..5810019 100644
--- a/drivers/s390/scsi/zfcp_dbf.c
+++ b/drivers/s390/scsi/zfcp_dbf.c
@@ -384,7 +384,7 @@ void zfcp_dbf_san(char *tag, struct zfcp_dbf *dbf,
/* if (len > rec_len):
* dump data up to cap_len ignoring small duplicate in rec->payload
*/
- spin_lock_irqsave(&dbf->pay_lock, flags);
+ spin_lock(&dbf->pay_lock);
memset(payload, 0, sizeof(*payload));
memcpy(payload->area, paytag, ZFCP_DBF_TAG_LEN);
payload->fsf_req_id = req_id;
diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
index db27390..790babc 100644
--- a/drivers/scsi/NCR5380.c
+++ b/drivers/scsi/NCR5380.c
@@ -353,7 +353,7 @@ static void NCR5380_print_phase(struct Scsi_Host *instance)
#endif
-static int probe_irq __initdata;
+static int probe_irq;
/**
* probe_intr - helper for IRQ autoprobe
@@ -365,7 +365,7 @@ static int probe_irq __initdata;
* used by the IRQ probe code.
*/
-static irqreturn_t __init probe_intr(int irq, void *dev_id)
+static irqreturn_t probe_intr(int irq, void *dev_id)
{
probe_irq = irq;
return IRQ_HANDLED;
@@ -380,7 +380,7 @@ static irqreturn_t __init probe_intr(int irq, void *dev_id)
* and then looking to see what interrupt actually turned up.
*/
-static int __init __maybe_unused NCR5380_probe_irq(struct Scsi_Host *instance,
+static int __maybe_unused NCR5380_probe_irq(struct Scsi_Host *instance,
int possible)
{
struct NCR5380_hostdata *hostdata = shost_priv(instance);
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 3d53d63..f0cfb04 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -2636,18 +2636,9 @@ static int arcmsr_queue_command_lck(struct scsi_cmnd *cmd,
struct AdapterControlBlock *acb = (struct AdapterControlBlock *) host->hostdata;
struct CommandControlBlock *ccb;
int target = cmd->device->id;
- int lun = cmd->device->lun;
- uint8_t scsicmd = cmd->cmnd[0];
cmd->scsi_done = done;
cmd->host_scribble = NULL;
cmd->result = 0;
- if ((scsicmd == SYNCHRONIZE_CACHE) ||(scsicmd == SEND_DIAGNOSTIC)){
- if(acb->devstate[target][lun] == ARECA_RAID_GONE) {
- cmd->result = (DID_NO_CONNECT << 16);
- }
- cmd->scsi_done(cmd);
- return 0;
- }
if (target == 16) {
/* virtual device for iop message transfer */
arcmsr_handle_virtual_command(acb, cmd);
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index 6a6906f..d9239c2 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -61,7 +61,7 @@ MODULE_PARM_DESC(be_max_phys_size,
"memory that can be allocated. Range is 16 - 128");
#define beiscsi_disp_param(_name)\
-ssize_t \
+static ssize_t \
beiscsi_##_name##_disp(struct device *dev,\
struct device_attribute *attrib, char *buf) \
{ \
@@ -74,7 +74,7 @@ beiscsi_##_name##_disp(struct device *dev,\
}
#define beiscsi_change_param(_name, _minval, _maxval, _defaval)\
-int \
+static int \
beiscsi_##_name##_change(struct beiscsi_hba *phba, uint32_t val)\
{\
if (val >= _minval && val <= _maxval) {\
@@ -93,7 +93,7 @@ beiscsi_##_name##_change(struct beiscsi_hba *phba, uint32_t val)\
}
#define beiscsi_store_param(_name) \
-ssize_t \
+static ssize_t \
beiscsi_##_name##_store(struct device *dev,\
struct device_attribute *attr, const char *buf,\
size_t count) \
@@ -112,7 +112,7 @@ beiscsi_##_name##_store(struct device *dev,\
}
#define beiscsi_init_param(_name, _minval, _maxval, _defval) \
-int \
+static int \
beiscsi_##_name##_init(struct beiscsi_hba *phba, uint32_t val) \
{ \
if (val >= _minval && val <= _maxval) {\
@@ -900,8 +900,9 @@ void hwi_ring_cq_db(struct beiscsi_hba *phba,
static struct sgl_handle *alloc_io_sgl_handle(struct beiscsi_hba *phba)
{
struct sgl_handle *psgl_handle;
+ unsigned long flags;
- spin_lock_bh(&phba->io_sgl_lock);
+ spin_lock_irqsave(&phba->io_sgl_lock, flags);
if (phba->io_sgl_hndl_avbl) {
beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_IO,
"BM_%d : In alloc_io_sgl_handle,"
@@ -919,14 +920,16 @@ static struct sgl_handle *alloc_io_sgl_handle(struct beiscsi_hba *phba)
phba->io_sgl_alloc_index++;
} else
psgl_handle = NULL;
- spin_unlock_bh(&phba->io_sgl_lock);
+ spin_unlock_irqrestore(&phba->io_sgl_lock, flags);
return psgl_handle;
}
static void
free_io_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
{
- spin_lock_bh(&phba->io_sgl_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&phba->io_sgl_lock, flags);
beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_IO,
"BM_%d : In free_,io_sgl_free_index=%d\n",
phba->io_sgl_free_index);
@@ -941,7 +944,7 @@ free_io_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
"value there=%p\n", phba->io_sgl_free_index,
phba->io_sgl_hndl_base
[phba->io_sgl_free_index]);
- spin_unlock_bh(&phba->io_sgl_lock);
+ spin_unlock_irqrestore(&phba->io_sgl_lock, flags);
return;
}
phba->io_sgl_hndl_base[phba->io_sgl_free_index] = psgl_handle;
@@ -950,7 +953,7 @@ free_io_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
phba->io_sgl_free_index = 0;
else
phba->io_sgl_free_index++;
- spin_unlock_bh(&phba->io_sgl_lock);
+ spin_unlock_irqrestore(&phba->io_sgl_lock, flags);
}
static inline struct wrb_handle *
@@ -958,15 +961,16 @@ beiscsi_get_wrb_handle(struct hwi_wrb_context *pwrb_context,
unsigned int wrbs_per_cxn)
{
struct wrb_handle *pwrb_handle;
+ unsigned long flags;
- spin_lock_bh(&pwrb_context->wrb_lock);
+ spin_lock_irqsave(&pwrb_context->wrb_lock, flags);
pwrb_handle = pwrb_context->pwrb_handle_base[pwrb_context->alloc_index];
pwrb_context->wrb_handles_available--;
if (pwrb_context->alloc_index == (wrbs_per_cxn - 1))
pwrb_context->alloc_index = 0;
else
pwrb_context->alloc_index++;
- spin_unlock_bh(&pwrb_context->wrb_lock);
+ spin_unlock_irqrestore(&pwrb_context->wrb_lock, flags);
if (pwrb_handle)
memset(pwrb_handle->pwrb, 0, sizeof(*pwrb_handle->pwrb));
@@ -1001,14 +1005,16 @@ beiscsi_put_wrb_handle(struct hwi_wrb_context *pwrb_context,
struct wrb_handle *pwrb_handle,
unsigned int wrbs_per_cxn)
{
- spin_lock_bh(&pwrb_context->wrb_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&pwrb_context->wrb_lock, flags);
pwrb_context->pwrb_handle_base[pwrb_context->free_index] = pwrb_handle;
pwrb_context->wrb_handles_available++;
if (pwrb_context->free_index == (wrbs_per_cxn - 1))
pwrb_context->free_index = 0;
else
pwrb_context->free_index++;
- spin_unlock_bh(&pwrb_context->wrb_lock);
+ spin_unlock_irqrestore(&pwrb_context->wrb_lock, flags);
}
/**
@@ -1037,8 +1043,9 @@ free_wrb_handle(struct beiscsi_hba *phba, struct hwi_wrb_context *pwrb_context,
static struct sgl_handle *alloc_mgmt_sgl_handle(struct beiscsi_hba *phba)
{
struct sgl_handle *psgl_handle;
+ unsigned long flags;
- spin_lock_bh(&phba->mgmt_sgl_lock);
+ spin_lock_irqsave(&phba->mgmt_sgl_lock, flags);
if (phba->eh_sgl_hndl_avbl) {
psgl_handle = phba->eh_sgl_hndl_base[phba->eh_sgl_alloc_index];
phba->eh_sgl_hndl_base[phba->eh_sgl_alloc_index] = NULL;
@@ -1056,14 +1063,16 @@ static struct sgl_handle *alloc_mgmt_sgl_handle(struct beiscsi_hba *phba)
phba->eh_sgl_alloc_index++;
} else
psgl_handle = NULL;
- spin_unlock_bh(&phba->mgmt_sgl_lock);
+ spin_unlock_irqrestore(&phba->mgmt_sgl_lock, flags);
return psgl_handle;
}
void
free_mgmt_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
{
- spin_lock_bh(&phba->mgmt_sgl_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&phba->mgmt_sgl_lock, flags);
beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_CONFIG,
"BM_%d : In free_mgmt_sgl_handle,"
"eh_sgl_free_index=%d\n",
@@ -1078,7 +1087,7 @@ free_mgmt_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
"BM_%d : Double Free in eh SGL ,"
"eh_sgl_free_index=%d\n",
phba->eh_sgl_free_index);
- spin_unlock_bh(&phba->mgmt_sgl_lock);
+ spin_unlock_irqrestore(&phba->mgmt_sgl_lock, flags);
return;
}
phba->eh_sgl_hndl_base[phba->eh_sgl_free_index] = psgl_handle;
@@ -1088,7 +1097,7 @@ free_mgmt_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle)
phba->eh_sgl_free_index = 0;
else
phba->eh_sgl_free_index++;
- spin_unlock_bh(&phba->mgmt_sgl_lock);
+ spin_unlock_irqrestore(&phba->mgmt_sgl_lock, flags);
}
static void
@@ -4584,7 +4593,7 @@ static int beiscsi_alloc_pdu(struct iscsi_task *task, uint8_t opcode)
io_task->cmd_bhs = NULL;
return -ENOMEM;
}
-int beiscsi_iotask_v2(struct iscsi_task *task, struct scatterlist *sg,
+static int beiscsi_iotask_v2(struct iscsi_task *task, struct scatterlist *sg,
unsigned int num_sg, unsigned int xferlen,
unsigned int writedir)
{
@@ -4973,7 +4982,7 @@ static int beiscsi_bsg_request(struct bsg_job *job)
return rc;
}
-void beiscsi_hba_attrs_init(struct beiscsi_hba *phba)
+static void beiscsi_hba_attrs_init(struct beiscsi_hba *phba)
{
/* Set the logging parameter */
beiscsi_log_enable_init(phba, beiscsi_log_enable);
diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
index 7c0d7af..4655a9f 100644
--- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
+++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
@@ -85,6 +85,7 @@ static inline int send_tx_flowc_wr(struct cxgbi_sock *);
static const struct cxgb4_uld_info cxgb4i_uld_info = {
.name = DRV_MODULE_NAME,
.nrxq = MAX_ULD_QSETS,
+ .ntxq = MAX_ULD_QSETS,
.rxq_size = 1024,
.lro = false,
.add = t4_uld_add,
@@ -685,6 +686,11 @@ static int push_tx_frames(struct cxgbi_sock *csk, int req_completion)
req_completion);
csk->snd_nxt += len;
cxgbi_skcb_clear_flag(skb, SKCBF_TX_NEED_HDR);
+ } else if (cxgbi_skcb_test_flag(skb, SKCBF_TX_FLAG_COMPL) &&
+ (csk->wr_una_cred >= (csk->wr_max_cred / 2))) {
+ struct cpl_close_con_req *req =
+ (struct cpl_close_con_req *)skb->data;
+ req->wr.wr_hi |= htonl(FW_WR_COMPL_F);
}
total_size += skb->truesize;
t4_set_arp_err_handler(skb, csk, arp_failure_skb_discard);
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index d142113..2ffe029 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -2081,9 +2081,10 @@ void cxgbi_cleanup_task(struct iscsi_task *task)
/* never reached the xmit task callout */
if (tdata->skb)
__kfree_skb(tdata->skb);
- memset(tdata, 0, sizeof(*tdata));
task_release_itt(task, task->hdr_itt);
+ memset(tdata, 0, sizeof(*tdata));
+
iscsi_tcp_cleanup_task(task);
}
EXPORT_SYMBOL_GPL(cxgbi_cleanup_task);
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index 241829e..7bb2068 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -793,6 +793,7 @@ static void alua_rtpg_work(struct work_struct *work)
WARN_ON(pg->flags & ALUA_PG_RUN_RTPG);
WARN_ON(pg->flags & ALUA_PG_RUN_STPG);
spin_unlock_irqrestore(&pg->lock, flags);
+ kref_put(&pg->kref, release_port_group);
return;
}
if (pg->flags & ALUA_SYNC_STPG)
@@ -890,6 +891,7 @@ static void alua_rtpg_queue(struct alua_port_group *pg,
/* Do not queue if the worker is already running */
if (!(pg->flags & ALUA_PG_RUNNING)) {
kref_get(&pg->kref);
+ sdev = NULL;
start_queue = 1;
}
}
@@ -901,7 +903,8 @@ static void alua_rtpg_queue(struct alua_port_group *pg,
if (start_queue &&
!queue_delayed_work(alua_wq, &pg->rtpg_work,
msecs_to_jiffies(ALUA_RTPG_DELAY_MSECS))) {
- scsi_device_put(sdev);
+ if (sdev)
+ scsi_device_put(sdev);
kref_put(&pg->kref, release_port_group);
}
}
diff --git a/drivers/scsi/g_NCR5380.c b/drivers/scsi/g_NCR5380.c
index 516bd6c..cbf0103 100644
--- a/drivers/scsi/g_NCR5380.c
+++ b/drivers/scsi/g_NCR5380.c
@@ -30,161 +30,41 @@
#include "NCR5380.h"
#include <linux/init.h>
#include <linux/ioport.h>
-#include <linux/isapnp.h>
+#include <linux/isa.h>
+#include <linux/pnp.h>
#include <linux/interrupt.h>
+#define MAX_CARDS 8
+
+/* old-style parameters for compatibility */
static int ncr_irq;
-static int ncr_dma;
static int ncr_addr;
static int ncr_5380;
static int ncr_53c400;
static int ncr_53c400a;
static int dtc_3181e;
static int hp_c2502;
+module_param(ncr_irq, int, 0);
+module_param(ncr_addr, int, 0);
+module_param(ncr_5380, int, 0);
+module_param(ncr_53c400, int, 0);
+module_param(ncr_53c400a, int, 0);
+module_param(dtc_3181e, int, 0);
+module_param(hp_c2502, int, 0);
-static struct override {
- NCR5380_map_type NCR5380_map_name;
- int irq;
- int dma;
- int board; /* Use NCR53c400, Ricoh, etc. extensions ? */
-} overrides
-#ifdef GENERIC_NCR5380_OVERRIDE
-[] __initdata = GENERIC_NCR5380_OVERRIDE;
-#else
-[1] __initdata = { { 0,},};
-#endif
+static int irq[] = { 0, 0, 0, 0, 0, 0, 0, 0 };
+module_param_array(irq, int, NULL, 0);
+MODULE_PARM_DESC(irq, "IRQ number(s)");
-#define NO_OVERRIDES ARRAY_SIZE(overrides)
+static int base[] = { 0, 0, 0, 0, 0, 0, 0, 0 };
+module_param_array(base, int, NULL, 0);
+MODULE_PARM_DESC(base, "base address(es)");
-#ifndef MODULE
+static int card[] = { -1, -1, -1, -1, -1, -1, -1, -1 };
+module_param_array(card, int, NULL, 0);
+MODULE_PARM_DESC(card, "card type (0=NCR5380, 1=NCR53C400, 2=NCR53C400A, 3=DTC3181E, 4=HP C2502)");
-/**
- * internal_setup - handle lilo command string override
- * @board: BOARD_* identifier for the board
- * @str: unused
- * @ints: numeric parameters
- *
- * Do LILO command line initialization of the overrides array. Display
- * errors when needed
- *
- * Locks: none
- */
-
-static void __init internal_setup(int board, char *str, int *ints)
-{
- static int commandline_current;
- switch (board) {
- case BOARD_NCR5380:
- if (ints[0] != 2 && ints[0] != 3) {
- printk(KERN_ERR "generic_NCR5380_setup : usage ncr5380=" STRVAL(NCR5380_map_name) ",irq,dma\n");
- return;
- }
- break;
- case BOARD_NCR53C400:
- if (ints[0] != 2) {
- printk(KERN_ERR "generic_NCR53C400_setup : usage ncr53c400=" STRVAL(NCR5380_map_name) ",irq\n");
- return;
- }
- break;
- case BOARD_NCR53C400A:
- if (ints[0] != 2) {
- printk(KERN_ERR "generic_NCR53C400A_setup : usage ncr53c400a=" STRVAL(NCR5380_map_name) ",irq\n");
- return;
- }
- break;
- case BOARD_DTC3181E:
- if (ints[0] != 2) {
- printk("generic_DTC3181E_setup : usage dtc3181e=" STRVAL(NCR5380_map_name) ",irq\n");
- return;
- }
- break;
- }
-
- if (commandline_current < NO_OVERRIDES) {
- overrides[commandline_current].NCR5380_map_name = (NCR5380_map_type) ints[1];
- overrides[commandline_current].irq = ints[2];
- if (ints[0] == 3)
- overrides[commandline_current].dma = ints[3];
- else
- overrides[commandline_current].dma = DMA_NONE;
- overrides[commandline_current].board = board;
- ++commandline_current;
- }
-}
-
-
-/**
- * do_NCR53C80_setup - set up entry point
- * @str: unused
- *
- * Setup function invoked at boot to parse the ncr5380= command
- * line.
- */
-
-static int __init do_NCR5380_setup(char *str)
-{
- int ints[10];
-
- get_options(str, ARRAY_SIZE(ints), ints);
- internal_setup(BOARD_NCR5380, str, ints);
- return 1;
-}
-
-/**
- * do_NCR53C400_setup - set up entry point
- * @str: unused
- * @ints: integer parameters from kernel setup code
- *
- * Setup function invoked at boot to parse the ncr53c400= command
- * line.
- */
-
-static int __init do_NCR53C400_setup(char *str)
-{
- int ints[10];
-
- get_options(str, ARRAY_SIZE(ints), ints);
- internal_setup(BOARD_NCR53C400, str, ints);
- return 1;
-}
-
-/**
- * do_NCR53C400A_setup - set up entry point
- * @str: unused
- * @ints: integer parameters from kernel setup code
- *
- * Setup function invoked at boot to parse the ncr53c400a= command
- * line.
- */
-
-static int __init do_NCR53C400A_setup(char *str)
-{
- int ints[10];
-
- get_options(str, ARRAY_SIZE(ints), ints);
- internal_setup(BOARD_NCR53C400A, str, ints);
- return 1;
-}
-
-/**
- * do_DTC3181E_setup - set up entry point
- * @str: unused
- * @ints: integer parameters from kernel setup code
- *
- * Setup function invoked at boot to parse the dtc3181e= command
- * line.
- */
-
-static int __init do_DTC3181E_setup(char *str)
-{
- int ints[10];
-
- get_options(str, ARRAY_SIZE(ints), ints);
- internal_setup(BOARD_DTC3181E, str, ints);
- return 1;
-}
-
-#endif
+MODULE_LICENSE("GPL");
#ifndef SCSI_G_NCR5380_MEM
/*
@@ -210,21 +90,9 @@ static void magic_configure(int idx, u8 irq, u8 magic[])
}
#endif
-/**
- * generic_NCR5380_detect - look for NCR5380 controllers
- * @tpnt: the scsi template
- *
- * Scan for the present of NCR5380, NCR53C400, NCR53C400A, DTC3181E
- * and DTC436(ISAPnP) controllers. If overrides have been set we use
- * them.
- *
- * Locks: none
- */
-
-static int __init generic_NCR5380_detect(struct scsi_host_template *tpnt)
+static int generic_NCR5380_init_one(struct scsi_host_template *tpnt,
+ struct device *pdev, int base, int irq, int board)
{
- static int current_override;
- int count;
unsigned int *ports;
u8 *magic = NULL;
#ifndef SCSI_G_NCR5380_MEM
@@ -232,272 +100,222 @@ static int __init generic_NCR5380_detect(struct scsi_host_template *tpnt)
int port_idx = -1;
unsigned long region_size;
#endif
- static unsigned int __initdata ncr_53c400a_ports[] = {
+ static unsigned int ncr_53c400a_ports[] = {
0x280, 0x290, 0x300, 0x310, 0x330, 0x340, 0x348, 0x350, 0
};
- static unsigned int __initdata dtc_3181e_ports[] = {
+ static unsigned int dtc_3181e_ports[] = {
0x220, 0x240, 0x280, 0x2a0, 0x2c0, 0x300, 0x320, 0x340, 0
};
- static u8 ncr_53c400a_magic[] __initdata = { /* 53C400A & DTC436 */
+ static u8 ncr_53c400a_magic[] = { /* 53C400A & DTC436 */
0x59, 0xb9, 0xc5, 0xae, 0xa6
};
- static u8 hp_c2502_magic[] __initdata = { /* HP C2502 */
+ static u8 hp_c2502_magic[] = { /* HP C2502 */
0x0f, 0x22, 0xf0, 0x20, 0x80
};
- int flags;
+ int flags, ret;
struct Scsi_Host *instance;
struct NCR5380_hostdata *hostdata;
#ifdef SCSI_G_NCR5380_MEM
- unsigned long base;
void __iomem *iomem;
resource_size_t iomem_size;
#endif
- if (ncr_irq)
- overrides[0].irq = ncr_irq;
- if (ncr_dma)
- overrides[0].dma = ncr_dma;
- if (ncr_addr)
- overrides[0].NCR5380_map_name = (NCR5380_map_type) ncr_addr;
- if (ncr_5380)
- overrides[0].board = BOARD_NCR5380;
- else if (ncr_53c400)
- overrides[0].board = BOARD_NCR53C400;
- else if (ncr_53c400a)
- overrides[0].board = BOARD_NCR53C400A;
- else if (dtc_3181e)
- overrides[0].board = BOARD_DTC3181E;
- else if (hp_c2502)
- overrides[0].board = BOARD_HP_C2502;
-#ifndef SCSI_G_NCR5380_MEM
- if (!current_override && isapnp_present()) {
- struct pnp_dev *dev = NULL;
- count = 0;
- while ((dev = pnp_find_dev(NULL, ISAPNP_VENDOR('D', 'T', 'C'), ISAPNP_FUNCTION(0x436e), dev))) {
- if (count >= NO_OVERRIDES)
- break;
- if (pnp_device_attach(dev) < 0)
- continue;
- if (pnp_activate_dev(dev) < 0) {
- printk(KERN_ERR "dtc436e probe: activate failed\n");
- pnp_device_detach(dev);
- continue;
- }
- if (!pnp_port_valid(dev, 0)) {
- printk(KERN_ERR "dtc436e probe: no valid port\n");
- pnp_device_detach(dev);
- continue;
- }
- if (pnp_irq_valid(dev, 0))
- overrides[count].irq = pnp_irq(dev, 0);
- else
- overrides[count].irq = NO_IRQ;
- if (pnp_dma_valid(dev, 0))
- overrides[count].dma = pnp_dma(dev, 0);
- else
- overrides[count].dma = DMA_NONE;
- overrides[count].NCR5380_map_name = (NCR5380_map_type) pnp_port_start(dev, 0);
- overrides[count].board = BOARD_DTC3181E;
- count++;
- }
+ ports = NULL;
+ flags = 0;
+ switch (board) {
+ case BOARD_NCR5380:
+ flags = FLAG_NO_PSEUDO_DMA | FLAG_DMA_FIXUP;
+ break;
+ case BOARD_NCR53C400A:
+ ports = ncr_53c400a_ports;
+ magic = ncr_53c400a_magic;
+ break;
+ case BOARD_HP_C2502:
+ ports = ncr_53c400a_ports;
+ magic = hp_c2502_magic;
+ break;
+ case BOARD_DTC3181E:
+ ports = dtc_3181e_ports;
+ magic = ncr_53c400a_magic;
+ break;
}
-#endif
-
- for (count = 0; current_override < NO_OVERRIDES; ++current_override) {
- if (!(overrides[current_override].NCR5380_map_name))
- continue;
-
- ports = NULL;
- flags = 0;
- switch (overrides[current_override].board) {
- case BOARD_NCR5380:
- flags = FLAG_NO_PSEUDO_DMA | FLAG_DMA_FIXUP;
- break;
- case BOARD_NCR53C400A:
- ports = ncr_53c400a_ports;
- magic = ncr_53c400a_magic;
- break;
- case BOARD_HP_C2502:
- ports = ncr_53c400a_ports;
- magic = hp_c2502_magic;
- break;
- case BOARD_DTC3181E:
- ports = dtc_3181e_ports;
- magic = ncr_53c400a_magic;
- break;
- }
#ifndef SCSI_G_NCR5380_MEM
- if (ports && magic) {
- /* wakeup sequence for the NCR53C400A and DTC3181E */
+ if (ports && magic) {
+ /* wakeup sequence for the NCR53C400A and DTC3181E */
- /* Disable the adapter and look for a free io port */
- magic_configure(-1, 0, magic);
+ /* Disable the adapter and look for a free io port */
+ magic_configure(-1, 0, magic);
- region_size = 16;
-
- if (overrides[current_override].NCR5380_map_name != PORT_AUTO)
- for (i = 0; ports[i]; i++) {
- if (!request_region(ports[i], region_size, "ncr53c80"))
- continue;
- if (overrides[current_override].NCR5380_map_name == ports[i])
- break;
- release_region(ports[i], region_size);
- } else
- for (i = 0; ports[i]; i++) {
- if (!request_region(ports[i], region_size, "ncr53c80"))
- continue;
- if (inb(ports[i]) == 0xff)
- break;
- release_region(ports[i], region_size);
+ region_size = 16;
+ if (base)
+ for (i = 0; ports[i]; i++) {
+ if (base == ports[i]) { /* index found */
+ if (!request_region(ports[i],
+ region_size,
+ "ncr53c80"))
+ return -EBUSY;
+ break;
}
- if (ports[i]) {
- /* At this point we have our region reserved */
- magic_configure(i, 0, magic); /* no IRQ yet */
- outb(0xc0, ports[i] + 9);
- if (inb(ports[i] + 9) != 0x80)
- continue;
- overrides[current_override].NCR5380_map_name = ports[i];
- port_idx = i;
- } else
- continue;
- }
- else
- {
- /* Not a 53C400A style setup - just grab */
- region_size = 8;
- if (!request_region(overrides[current_override].NCR5380_map_name,
- region_size, "ncr5380"))
- continue;
- }
-#else
- base = overrides[current_override].NCR5380_map_name;
- iomem_size = NCR53C400_region_size;
- if (!request_mem_region(base, iomem_size, "ncr5380"))
- continue;
- iomem = ioremap(base, iomem_size);
- if (!iomem) {
- release_mem_region(base, iomem_size);
- continue;
- }
-#endif
- instance = scsi_register(tpnt, sizeof(struct NCR5380_hostdata));
- if (instance == NULL)
- goto out_release;
- hostdata = shost_priv(instance);
-
-#ifndef SCSI_G_NCR5380_MEM
- instance->io_port = overrides[current_override].NCR5380_map_name;
- instance->n_io_port = region_size;
- hostdata->io_width = 1; /* 8-bit PDMA by default */
-
- /*
- * On NCR53C400 boards, NCR5380 registers are mapped 8 past
- * the base address.
- */
- switch (overrides[current_override].board) {
- case BOARD_NCR53C400:
- instance->io_port += 8;
- hostdata->c400_ctl_status = 0;
- hostdata->c400_blk_cnt = 1;
- hostdata->c400_host_buf = 4;
- break;
- case BOARD_DTC3181E:
- hostdata->io_width = 2; /* 16-bit PDMA */
- /* fall through */
- case BOARD_NCR53C400A:
- case BOARD_HP_C2502:
- hostdata->c400_ctl_status = 9;
- hostdata->c400_blk_cnt = 10;
- hostdata->c400_host_buf = 8;
- break;
- }
-#else
- instance->base = overrides[current_override].NCR5380_map_name;
- hostdata->iomem = iomem;
- hostdata->iomem_size = iomem_size;
- switch (overrides[current_override].board) {
- case BOARD_NCR53C400:
- hostdata->c400_ctl_status = 0x100;
- hostdata->c400_blk_cnt = 0x101;
- hostdata->c400_host_buf = 0x104;
- break;
- case BOARD_DTC3181E:
- case BOARD_NCR53C400A:
- case BOARD_HP_C2502:
- pr_err(DRV_MODULE_NAME ": unknown register offsets\n");
- goto out_unregister;
- }
-#endif
-
- if (NCR5380_init(instance, flags | FLAG_LATE_DMA_SETUP))
- goto out_unregister;
-
- switch (overrides[current_override].board) {
- case BOARD_NCR53C400:
- case BOARD_DTC3181E:
- case BOARD_NCR53C400A:
- case BOARD_HP_C2502:
- NCR5380_write(hostdata->c400_ctl_status, CSR_BASE);
- }
-
- NCR5380_maybe_reset_bus(instance);
-
- if (overrides[current_override].irq != IRQ_AUTO)
- instance->irq = overrides[current_override].irq;
- else
- instance->irq = NCR5380_probe_irq(instance, 0xffff);
-
- /* Compatibility with documented NCR5380 kernel parameters */
- if (instance->irq == 255)
- instance->irq = NO_IRQ;
-
- if (instance->irq != NO_IRQ) {
-#ifndef SCSI_G_NCR5380_MEM
- /* set IRQ for HP C2502 */
- if (overrides[current_override].board == BOARD_HP_C2502)
- magic_configure(port_idx, instance->irq, magic);
-#endif
- if (request_irq(instance->irq, generic_NCR5380_intr,
- 0, "NCR5380", instance)) {
- printk(KERN_WARNING "scsi%d : IRQ%d not free, interrupts disabled\n", instance->host_no, instance->irq);
- instance->irq = NO_IRQ;
}
- }
-
- if (instance->irq == NO_IRQ) {
- printk(KERN_INFO "scsi%d : interrupts not enabled. for better interactive performance,\n", instance->host_no);
- printk(KERN_INFO "scsi%d : please jumper the board for a free IRQ.\n", instance->host_no);
- }
-
- ++current_override;
- ++count;
+ else
+ for (i = 0; ports[i]; i++) {
+ if (!request_region(ports[i], region_size,
+ "ncr53c80"))
+ continue;
+ if (inb(ports[i]) == 0xff)
+ break;
+ release_region(ports[i], region_size);
+ }
+ if (ports[i]) {
+ /* At this point we have our region reserved */
+ magic_configure(i, 0, magic); /* no IRQ yet */
+ outb(0xc0, ports[i] + 9);
+ if (inb(ports[i] + 9) != 0x80) {
+ ret = -ENODEV;
+ goto out_release;
+ }
+ base = ports[i];
+ port_idx = i;
+ } else
+ return -EINVAL;
}
- return count;
+ else
+ {
+ /* NCR5380 - no configuration, just grab */
+ region_size = 8;
+ if (!base || !request_region(base, region_size, "ncr5380"))
+ return -EBUSY;
+ }
+#else
+ iomem_size = NCR53C400_region_size;
+ if (!request_mem_region(base, iomem_size, "ncr5380"))
+ return -EBUSY;
+ iomem = ioremap(base, iomem_size);
+ if (!iomem) {
+ release_mem_region(base, iomem_size);
+ return -ENOMEM;
+ }
+#endif
+ instance = scsi_host_alloc(tpnt, sizeof(struct NCR5380_hostdata));
+ if (instance == NULL) {
+ ret = -ENOMEM;
+ goto out_release;
+ }
+ hostdata = shost_priv(instance);
+#ifndef SCSI_G_NCR5380_MEM
+ instance->io_port = base;
+ instance->n_io_port = region_size;
+ hostdata->io_width = 1; /* 8-bit PDMA by default */
+
+ /*
+ * On NCR53C400 boards, NCR5380 registers are mapped 8 past
+ * the base address.
+ */
+ switch (board) {
+ case BOARD_NCR53C400:
+ instance->io_port += 8;
+ hostdata->c400_ctl_status = 0;
+ hostdata->c400_blk_cnt = 1;
+ hostdata->c400_host_buf = 4;
+ break;
+ case BOARD_DTC3181E:
+ hostdata->io_width = 2; /* 16-bit PDMA */
+ /* fall through */
+ case BOARD_NCR53C400A:
+ case BOARD_HP_C2502:
+ hostdata->c400_ctl_status = 9;
+ hostdata->c400_blk_cnt = 10;
+ hostdata->c400_host_buf = 8;
+ break;
+ }
+#else
+ instance->base = base;
+ hostdata->iomem = iomem;
+ hostdata->iomem_size = iomem_size;
+ switch (board) {
+ case BOARD_NCR53C400:
+ hostdata->c400_ctl_status = 0x100;
+ hostdata->c400_blk_cnt = 0x101;
+ hostdata->c400_host_buf = 0x104;
+ break;
+ case BOARD_DTC3181E:
+ case BOARD_NCR53C400A:
+ case BOARD_HP_C2502:
+ pr_err(DRV_MODULE_NAME ": unknown register offsets\n");
+ ret = -EINVAL;
+ goto out_unregister;
+ }
+#endif
+
+ ret = NCR5380_init(instance, flags | FLAG_LATE_DMA_SETUP);
+ if (ret)
+ goto out_unregister;
+
+ switch (board) {
+ case BOARD_NCR53C400:
+ case BOARD_DTC3181E:
+ case BOARD_NCR53C400A:
+ case BOARD_HP_C2502:
+ NCR5380_write(hostdata->c400_ctl_status, CSR_BASE);
+ }
+
+ NCR5380_maybe_reset_bus(instance);
+
+ if (irq != IRQ_AUTO)
+ instance->irq = irq;
+ else
+ instance->irq = NCR5380_probe_irq(instance, 0xffff);
+
+ /* Compatibility with documented NCR5380 kernel parameters */
+ if (instance->irq == 255)
+ instance->irq = NO_IRQ;
+
+ if (instance->irq != NO_IRQ) {
+#ifndef SCSI_G_NCR5380_MEM
+ /* set IRQ for HP C2502 */
+ if (board == BOARD_HP_C2502)
+ magic_configure(port_idx, instance->irq, magic);
+#endif
+ if (request_irq(instance->irq, generic_NCR5380_intr,
+ 0, "NCR5380", instance)) {
+ printk(KERN_WARNING "scsi%d : IRQ%d not free, interrupts disabled\n", instance->host_no, instance->irq);
+ instance->irq = NO_IRQ;
+ }
+ }
+
+ if (instance->irq == NO_IRQ) {
+ printk(KERN_INFO "scsi%d : interrupts not enabled. for better interactive performance,\n", instance->host_no);
+ printk(KERN_INFO "scsi%d : please jumper the board for a free IRQ.\n", instance->host_no);
+ }
+
+ ret = scsi_add_host(instance, pdev);
+ if (ret)
+ goto out_free_irq;
+ scsi_scan_host(instance);
+ dev_set_drvdata(pdev, instance);
+ return 0;
+
+out_free_irq:
+ if (instance->irq != NO_IRQ)
+ free_irq(instance->irq, instance);
+ NCR5380_exit(instance);
out_unregister:
- scsi_unregister(instance);
+ scsi_host_put(instance);
out_release:
#ifndef SCSI_G_NCR5380_MEM
- release_region(overrides[current_override].NCR5380_map_name, region_size);
+ release_region(base, region_size);
#else
iounmap(iomem);
release_mem_region(base, iomem_size);
#endif
- return count;
+ return ret;
}
-/**
- * generic_NCR5380_release_resources - free resources
- * @instance: host adapter to clean up
- *
- * Free the generic interface resources from this adapter.
- *
- * Locks: none
- */
-
-static int generic_NCR5380_release_resources(struct Scsi_Host *instance)
+static void generic_NCR5380_release_resources(struct Scsi_Host *instance)
{
+ scsi_remove_host(instance);
if (instance->irq != NO_IRQ)
free_irq(instance->irq, instance);
NCR5380_exit(instance);
@@ -511,7 +329,7 @@ static int generic_NCR5380_release_resources(struct Scsi_Host *instance)
release_mem_region(instance->base, hostdata->iomem_size);
}
#endif
- return 0;
+ scsi_host_put(instance);
}
/**
@@ -701,10 +519,9 @@ static int generic_NCR5380_dma_xfer_len(struct Scsi_Host *instance,
#include "NCR5380.c"
static struct scsi_host_template driver_template = {
+ .module = THIS_MODULE,
.proc_name = DRV_MODULE_NAME,
.name = "Generic NCR5380/NCR53C400 SCSI",
- .detect = generic_NCR5380_detect,
- .release = generic_NCR5380_release_resources,
.info = generic_NCR5380_info,
.queuecommand = generic_NCR5380_queue_command,
.eh_abort_handler = generic_NCR5380_abort,
@@ -718,31 +535,115 @@ static struct scsi_host_template driver_template = {
.max_sectors = 128,
};
-#include "scsi_module.c"
-module_param(ncr_irq, int, 0);
-module_param(ncr_dma, int, 0);
-module_param(ncr_addr, int, 0);
-module_param(ncr_5380, int, 0);
-module_param(ncr_53c400, int, 0);
-module_param(ncr_53c400a, int, 0);
-module_param(dtc_3181e, int, 0);
-module_param(hp_c2502, int, 0);
-MODULE_LICENSE("GPL");
+static int generic_NCR5380_isa_match(struct device *pdev, unsigned int ndev)
+{
+ int ret = generic_NCR5380_init_one(&driver_template, pdev, base[ndev],
+ irq[ndev], card[ndev]);
+ if (ret) {
+ if (base[ndev])
+ printk(KERN_WARNING "Card not found at address 0x%03x\n",
+ base[ndev]);
+ return 0;
+ }
-#if !defined(SCSI_G_NCR5380_MEM) && defined(MODULE)
-static struct isapnp_device_id id_table[] = {
- {
- ISAPNP_ANY_ID, ISAPNP_ANY_ID,
- ISAPNP_VENDOR('D', 'T', 'C'), ISAPNP_FUNCTION(0x436e),
- 0},
- {0}
+ return 1;
+}
+
+static int generic_NCR5380_isa_remove(struct device *pdev,
+ unsigned int ndev)
+{
+ generic_NCR5380_release_resources(dev_get_drvdata(pdev));
+ dev_set_drvdata(pdev, NULL);
+ return 0;
+}
+
+static struct isa_driver generic_NCR5380_isa_driver = {
+ .match = generic_NCR5380_isa_match,
+ .remove = generic_NCR5380_isa_remove,
+ .driver = {
+ .name = DRV_MODULE_NAME
+ },
};
-MODULE_DEVICE_TABLE(isapnp, id_table);
-#endif
+#if !defined(SCSI_G_NCR5380_MEM) && defined(CONFIG_PNP)
+static struct pnp_device_id generic_NCR5380_pnp_ids[] = {
+ { .id = "DTC436e", .driver_data = BOARD_DTC3181E },
+ { .id = "" }
+};
+MODULE_DEVICE_TABLE(pnp, generic_NCR5380_pnp_ids);
-__setup("ncr5380=", do_NCR5380_setup);
-__setup("ncr53c400=", do_NCR53C400_setup);
-__setup("ncr53c400a=", do_NCR53C400A_setup);
-__setup("dtc3181e=", do_DTC3181E_setup);
+static int generic_NCR5380_pnp_probe(struct pnp_dev *pdev,
+ const struct pnp_device_id *id)
+{
+ int base, irq;
+
+ if (pnp_activate_dev(pdev) < 0)
+ return -EBUSY;
+
+ base = pnp_port_start(pdev, 0);
+ irq = pnp_irq(pdev, 0);
+
+ return generic_NCR5380_init_one(&driver_template, &pdev->dev, base, irq,
+ id->driver_data);
+}
+
+static void generic_NCR5380_pnp_remove(struct pnp_dev *pdev)
+{
+ generic_NCR5380_release_resources(pnp_get_drvdata(pdev));
+ pnp_set_drvdata(pdev, NULL);
+}
+
+static struct pnp_driver generic_NCR5380_pnp_driver = {
+ .name = DRV_MODULE_NAME,
+ .id_table = generic_NCR5380_pnp_ids,
+ .probe = generic_NCR5380_pnp_probe,
+ .remove = generic_NCR5380_pnp_remove,
+};
+#endif /* !defined(SCSI_G_NCR5380_MEM) && defined(CONFIG_PNP) */
+
+static int pnp_registered, isa_registered;
+
+static int __init generic_NCR5380_init(void)
+{
+ int ret = 0;
+
+ /* compatibility with old-style parameters */
+ if (irq[0] == 0 && base[0] == 0 && card[0] == -1) {
+ irq[0] = ncr_irq;
+ base[0] = ncr_addr;
+ if (ncr_5380)
+ card[0] = BOARD_NCR5380;
+ if (ncr_53c400)
+ card[0] = BOARD_NCR53C400;
+ if (ncr_53c400a)
+ card[0] = BOARD_NCR53C400A;
+ if (dtc_3181e)
+ card[0] = BOARD_DTC3181E;
+ if (hp_c2502)
+ card[0] = BOARD_HP_C2502;
+ }
+
+#if !defined(SCSI_G_NCR5380_MEM) && defined(CONFIG_PNP)
+ if (!pnp_register_driver(&generic_NCR5380_pnp_driver))
+ pnp_registered = 1;
+#endif
+ ret = isa_register_driver(&generic_NCR5380_isa_driver, MAX_CARDS);
+ if (!ret)
+ isa_registered = 1;
+
+ return (pnp_registered || isa_registered) ? 0 : ret;
+}
+
+static void __exit generic_NCR5380_exit(void)
+{
+#if !defined(SCSI_G_NCR5380_MEM) && defined(CONFIG_PNP)
+ if (pnp_registered)
+ pnp_unregister_driver(&generic_NCR5380_pnp_driver);
+#endif
+ if (isa_registered)
+ isa_unregister_driver(&generic_NCR5380_isa_driver);
+}
+
+module_init(generic_NCR5380_init);
+module_exit(generic_NCR5380_exit);
diff --git a/drivers/scsi/g_NCR5380.h b/drivers/scsi/g_NCR5380.h
index 5951774..b175b92 100644
--- a/drivers/scsi/g_NCR5380.h
+++ b/drivers/scsi/g_NCR5380.h
@@ -14,15 +14,9 @@
#ifndef GENERIC_NCR5380_H
#define GENERIC_NCR5380_H
-#define __STRVAL(x) #x
-#define STRVAL(x) __STRVAL(x)
-
#ifndef SCSI_G_NCR5380_MEM
#define DRV_MODULE_NAME "g_NCR5380"
-#define NCR5380_map_type int
-#define NCR5380_map_name port
-
#define NCR5380_read(reg) \
inb(instance->io_port + (reg))
#define NCR5380_write(reg, value) \
@@ -38,8 +32,6 @@
/* therefore SCSI_G_NCR5380_MEM */
#define DRV_MODULE_NAME "g_NCR5380_mmio"
-#define NCR5380_map_type unsigned long
-#define NCR5380_map_name base
#define NCR53C400_mem_base 0x3880
#define NCR53C400_host_buffer 0x3900
#define NCR53C400_region_size 0x3a00
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index a8762a3..5324741 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -2586,7 +2586,6 @@ static void ipr_process_error(struct ipr_cmnd *ipr_cmd)
struct ipr_hostrcb *hostrcb = ipr_cmd->u.hostrcb;
u32 ioasc = be32_to_cpu(ipr_cmd->s.ioasa.hdr.ioasc);
u32 fd_ioasc;
- char *envp[] = { "ASYNC_ERR_LOG=1", NULL };
if (ioa_cfg->sis64)
fd_ioasc = be32_to_cpu(hostrcb->hcam.u.error64.fd_ioasc);
@@ -2607,8 +2606,8 @@ static void ipr_process_error(struct ipr_cmnd *ipr_cmd)
}
list_add_tail(&hostrcb->queue, &ioa_cfg->hostrcb_report_q);
+ schedule_work(&ioa_cfg->work_q);
hostrcb = ipr_get_free_hostrcb(ioa_cfg);
- kobject_uevent_env(&ioa_cfg->host->shost_dev.kobj, KOBJ_CHANGE, envp);
ipr_send_hcam(ioa_cfg, IPR_HCAM_CDB_OP_CODE_LOG_DATA, hostrcb);
}
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index c051694..f9b6fba 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -791,9 +791,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
free_task:
/* regular RX path uses back_lock */
- spin_lock_bh(&session->back_lock);
+ spin_lock(&session->back_lock);
__iscsi_put_task(task);
- spin_unlock_bh(&session->back_lock);
+ spin_unlock(&session->back_lock);
return NULL;
}
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index ca86c88..3aaea71 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -2233,7 +2233,7 @@ struct megasas_instance_template {
};
#define MEGASAS_IS_LOGICAL(scp) \
- (scp->device->channel < MEGASAS_MAX_PD_CHANNELS) ? 0 : 1
+ ((scp->device->channel < MEGASAS_MAX_PD_CHANNELS) ? 0 : 1)
#define MEGASAS_DEV_INDEX(scp) \
(((scp->device->channel % 2) * MEGASAS_MAX_DEV_PER_CHANNEL) + \
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 9ff57de..d8b1fbd 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -1700,16 +1700,13 @@ megasas_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
goto out_done;
}
- switch (scmd->cmnd[0]) {
- case SYNCHRONIZE_CACHE:
- /*
- * FW takes care of flush cache on its own
- * No need to send it down
- */
+ /*
+ * FW takes care of flush cache on its own for Virtual Disk.
+ * No need to send it down for VD. For JBOD send SYNCHRONIZE_CACHE to FW.
+ */
+ if ((scmd->cmnd[0] == SYNCHRONIZE_CACHE) && MEGASAS_IS_LOGICAL(scmd)) {
scmd->result = DID_OK << 16;
goto out_done;
- default:
- break;
}
return instance->instancet->build_and_issue_cmd(instance, scmd);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 209a969..8aa769a 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -1273,9 +1273,9 @@ scsih_target_alloc(struct scsi_target *starget)
sas_target_priv_data->handle = raid_device->handle;
sas_target_priv_data->sas_address = raid_device->wwid;
sas_target_priv_data->flags |= MPT_TARGET_FLAGS_VOLUME;
- sas_target_priv_data->raid_device = raid_device;
if (ioc->is_warpdrive)
- raid_device->starget = starget;
+ sas_target_priv_data->raid_device = raid_device;
+ raid_device->starget = starget;
}
spin_unlock_irqrestore(&ioc->raid_device_lock, flags);
return 0;
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index ace65db..567fa08 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -707,6 +707,11 @@ qla2xxx_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
srb_t *sp;
int rval;
+ if (unlikely(test_bit(UNLOADING, &base_vha->dpc_flags))) {
+ cmd->result = DID_NO_CONNECT << 16;
+ goto qc24_fail_command;
+ }
+
if (ha->flags.eeh_busy) {
if (ha->flags.pci_channel_io_perm_failure) {
ql_dbg(ql_dbg_aer, vha, 0x9010,
@@ -1451,6 +1456,15 @@ qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res)
for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) {
sp = req->outstanding_cmds[cnt];
if (sp) {
+ /* Get a reference to the sp and drop the lock.
+ * The reference ensures this sp->done() call
+ * - and not the call in qla2xxx_eh_abort() -
+ * ends the SCSI command (with result 'res').
+ */
+ sp_get(sp);
+ spin_unlock_irqrestore(&ha->hardware_lock, flags);
+ qla2xxx_eh_abort(GET_CMD_SP(sp));
+ spin_lock_irqsave(&ha->hardware_lock, flags);
req->outstanding_cmds[cnt] = NULL;
sp->done(vha, sp, res);
}
@@ -2341,6 +2355,8 @@ qla2xxx_scan_finished(struct Scsi_Host *shost, unsigned long time)
{
scsi_qla_host_t *vha = shost_priv(shost);
+ if (test_bit(UNLOADING, &vha->dpc_flags))
+ return 1;
if (!vha->host)
return 1;
if (time > vha->hw->loop_reset_delay * HZ)
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index c905709..cf04a36 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -5134,6 +5134,7 @@ static void __exit scsi_debug_exit(void)
bus_unregister(&pseudo_lld_bus);
root_device_unregister(pseudo_primary);
+ vfree(map_storep);
vfree(dif_storep);
vfree(fake_storep);
kfree(sdebug_q_arr);
diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c
index 54d446c..b8d3b97 100644
--- a/drivers/scsi/scsi_dh.c
+++ b/drivers/scsi/scsi_dh.c
@@ -36,9 +36,9 @@ struct scsi_dh_blist {
};
static const struct scsi_dh_blist scsi_dh_blist[] = {
- {"DGC", "RAID", "clariion" },
- {"DGC", "DISK", "clariion" },
- {"DGC", "VRAID", "clariion" },
+ {"DGC", "RAID", "emc" },
+ {"DGC", "DISK", "emc" },
+ {"DGC", "VRAID", "emc" },
{"COMPAQ", "MSA1000 VOLUME", "hp_sw" },
{"COMPAQ", "HSV110", "hp_sw" },
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 212e98d..6f7128f 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -1307,7 +1307,6 @@ static void scsi_sequential_lun_scan(struct scsi_target *starget,
static int scsi_report_lun_scan(struct scsi_target *starget, int bflags,
enum scsi_scan_mode rescan)
{
- char devname[64];
unsigned char scsi_cmd[MAX_COMMAND_SIZE];
unsigned int length;
u64 lun;
@@ -1349,9 +1348,6 @@ static int scsi_report_lun_scan(struct scsi_target *starget, int bflags,
}
}
- sprintf(devname, "host %d channel %d id %d",
- shost->host_no, sdev->channel, sdev->id);
-
/*
* Allocate enough to hold the header (the same size as one scsi_lun)
* plus the number of luns we are requesting. 511 was the default
@@ -1470,12 +1466,12 @@ static int scsi_report_lun_scan(struct scsi_target *starget, int bflags,
out_err:
kfree(lun_data);
out:
- scsi_device_put(sdev);
if (scsi_device_created(sdev))
/*
* the sdev we used didn't appear in the report luns scan
*/
__scsi_remove_device(sdev);
+ scsi_device_put(sdev);
return ret;
}
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 7af5226..618422e 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -4922,9 +4922,8 @@ static int sgl_map_user_pages(struct st_buffer *STbp,
res = get_user_pages_unlocked(
uaddr,
nr_pages,
- rw == READ,
- 0, /* don't force */
- pages);
+ pages,
+ rw == READ ? FOLL_WRITE : 0); /* don't force */
/* Errors and no page mapped should return here */
if (res < nr_pages)
diff --git a/drivers/scsi/ufs/Kconfig b/drivers/scsi/ufs/Kconfig
index 4796690..e27b4d4e 100644
--- a/drivers/scsi/ufs/Kconfig
+++ b/drivers/scsi/ufs/Kconfig
@@ -63,7 +63,7 @@
config SCSI_UFS_DWC_TC_PCI
tristate "DesignWare pci support using a G210 Test Chip"
- depends on SCSI_UFSHCD && PCI
+ depends on SCSI_UFSHCD_PCI
---help---
Synopsys Test Chip is a PHY for prototyping purposes.
diff --git a/drivers/scsi/ufs/ufs_quirks.h b/drivers/scsi/ufs/ufs_quirks.h
index ee4ab85..22f881e 100644
--- a/drivers/scsi/ufs/ufs_quirks.h
+++ b/drivers/scsi/ufs/ufs_quirks.h
@@ -25,6 +25,7 @@
#define UFS_VENDOR_TOSHIBA 0x198
#define UFS_VENDOR_SAMSUNG 0x1CE
+#define UFS_VENDOR_SKHYNIX 0x1AD
/**
* ufs_device_info - ufs device details
@@ -145,6 +146,7 @@ static struct ufs_dev_fix ufs_fixups[] = {
UFS_DEVICE_QUIRK_PA_TACTIVATE),
UFS_FIX(UFS_VENDOR_TOSHIBA, "THGLF2G9D8KBADG",
UFS_DEVICE_QUIRK_PA_TACTIVATE),
+ UFS_FIX(UFS_VENDOR_SKHYNIX, UFS_ANY_MODEL, UFS_DEVICE_NO_VCCQ),
END_FIX
};
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 37f3c51..05c7456 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -1266,9 +1266,12 @@ static void ufshcd_prepare_utp_query_req_upiu(struct ufs_hba *hba,
ucd_req_ptr->header.dword_1 = UPIU_HEADER_DWORD(
0, query->request.query_func, 0, 0);
- /* Data segment length */
- ucd_req_ptr->header.dword_2 = UPIU_HEADER_DWORD(
- 0, 0, len >> 8, (u8)len);
+ /* Data segment length only need for WRITE_DESC */
+ if (query->request.upiu_req.opcode == UPIU_QUERY_OPCODE_WRITE_DESC)
+ ucd_req_ptr->header.dword_2 =
+ UPIU_HEADER_DWORD(0, 0, (len >> 8), (u8)len);
+ else
+ ucd_req_ptr->header.dword_2 = 0;
/* Copy the Query Request buffer as is */
memcpy(&ucd_req_ptr->qr, &query->request.upiu_req,
@@ -6500,6 +6503,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
if (IS_ERR(hba->devfreq)) {
dev_err(hba->dev, "Unable to register with devfreq %ld\n",
PTR_ERR(hba->devfreq));
+ err = PTR_ERR(hba->devfreq);
goto out_remove_scsi_host;
}
/* Suspend devfreq until the UFS device is detected */
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index 4a0d3cd..15ca09c 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -793,6 +793,7 @@ static int pvscsi_abort(struct scsi_cmnd *cmd)
unsigned long flags;
int result = SUCCESS;
DECLARE_COMPLETION_ONSTACK(abort_cmp);
+ int done;
scmd_printk(KERN_DEBUG, cmd, "task abort on host %u, %p\n",
adapter->host->host_no, cmd);
@@ -824,10 +825,10 @@ static int pvscsi_abort(struct scsi_cmnd *cmd)
pvscsi_abort_cmd(adapter, ctx);
spin_unlock_irqrestore(&adapter->hw_lock, flags);
/* Wait for 2 secs for the completion. */
- wait_for_completion_timeout(&abort_cmp, msecs_to_jiffies(2000));
+ done = wait_for_completion_timeout(&abort_cmp, msecs_to_jiffies(2000));
spin_lock_irqsave(&adapter->hw_lock, flags);
- if (!completion_done(&abort_cmp)) {
+ if (!done) {
/*
* Failed to abort the command, unmark the fact that it
* was requested to be aborted.
diff --git a/drivers/scsi/vmw_pvscsi.h b/drivers/scsi/vmw_pvscsi.h
index c097d2c..d41292e 100644
--- a/drivers/scsi/vmw_pvscsi.h
+++ b/drivers/scsi/vmw_pvscsi.h
@@ -26,7 +26,7 @@
#include <linux/types.h>
-#define PVSCSI_DRIVER_VERSION_STRING "1.0.6.0-k"
+#define PVSCSI_DRIVER_VERSION_STRING "1.0.7.0-k"
#define PVSCSI_MAX_NUM_SG_ENTRIES_PER_SEGMENT 128
diff --git a/drivers/soc/Kconfig b/drivers/soc/Kconfig
index fe42a2f..e6e90e8 100644
--- a/drivers/soc/Kconfig
+++ b/drivers/soc/Kconfig
@@ -1,6 +1,7 @@
menu "SOC (System On Chip) specific Drivers"
source "drivers/soc/bcm/Kconfig"
+source "drivers/soc/fsl/qbman/Kconfig"
source "drivers/soc/fsl/qe/Kconfig"
source "drivers/soc/mediatek/Kconfig"
source "drivers/soc/qcom/Kconfig"
diff --git a/drivers/soc/fsl/Makefile b/drivers/soc/fsl/Makefile
index 203307f..75e1f53 100644
--- a/drivers/soc/fsl/Makefile
+++ b/drivers/soc/fsl/Makefile
@@ -2,5 +2,6 @@
# Makefile for the Linux Kernel SOC fsl specific device drivers
#
+obj-$(CONFIG_FSL_DPAA) += qbman/
obj-$(CONFIG_QUICC_ENGINE) += qe/
obj-$(CONFIG_CPM) += qe/
diff --git a/drivers/soc/fsl/qbman/Kconfig b/drivers/soc/fsl/qbman/Kconfig
new file mode 100644
index 0000000..757033c
--- /dev/null
+++ b/drivers/soc/fsl/qbman/Kconfig
@@ -0,0 +1,67 @@
+menuconfig FSL_DPAA
+ bool "Freescale DPAA 1.x support"
+ depends on FSL_SOC_BOOKE
+ select GENERIC_ALLOCATOR
+ help
+ The Freescale Data Path Acceleration Architecture (DPAA) is a set of
+ hardware components on specific QorIQ multicore processors.
+ This architecture provides the infrastructure to support simplified
+ sharing of networking interfaces and accelerators by multiple CPUs.
+ The major h/w blocks composing DPAA are BMan and QMan.
+
+ The Buffer Manager (BMan) is a hardware buffer pool management block
+ that allows software and accelerators on the datapath to acquire and
+ release buffers in order to build frames.
+
+ The Queue Manager (QMan) is a hardware queue management block
+ that allows software and accelerators on the datapath to enqueue and
+ dequeue frames in order to communicate.
+
+if FSL_DPAA
+
+config FSL_DPAA_CHECKING
+ bool "Additional driver checking"
+ help
+ Compiles in additional checks, to sanity-check the drivers and
+ any use of the exported API. Not recommended for performance.
+
+config FSL_BMAN_TEST
+ tristate "BMan self-tests"
+ help
+ Compile the BMan self-test code. These tests will
+ exercise the BMan APIs to confirm functionality
+ of both the software drivers and hardware device.
+
+config FSL_BMAN_TEST_API
+ bool "High-level API self-test"
+ depends on FSL_BMAN_TEST
+ default y
+ help
+ This requires the presence of cpu-affine portals, and performs
+ high-level API testing with them (whichever portal(s) are affine
+ to the cpu(s) the test executes on).
+
+config FSL_QMAN_TEST
+ tristate "QMan self-tests"
+ help
+ Compile self-test code for QMan.
+
+config FSL_QMAN_TEST_API
+ bool "QMan high-level self-test"
+ depends on FSL_QMAN_TEST
+ default y
+ help
+ This requires the presence of cpu-affine portals, and performs
+ high-level API testing with them (whichever portal(s) are affine to
+ the cpu(s) the test executes on).
+
+config FSL_QMAN_TEST_STASH
+ bool "QMan 'hot potato' data-stashing self-test"
+ depends on FSL_QMAN_TEST
+ default y
+ help
+ This performs a "hot potato" style test enqueuing/dequeuing a frame
+ across a series of FQs scheduled to different portals (and cpus), with
+ DQRR, data and context stashing always on.
+
+endif # FSL_DPAA
diff --git a/drivers/soc/fsl/qbman/Makefile b/drivers/soc/fsl/qbman/Makefile
new file mode 100644
index 0000000..7ae199f
--- /dev/null
+++ b/drivers/soc/fsl/qbman/Makefile
@@ -0,0 +1,12 @@
+obj-$(CONFIG_FSL_DPAA) += bman_ccsr.o qman_ccsr.o \
+ bman_portal.o qman_portal.o \
+ bman.o qman.o
+
+obj-$(CONFIG_FSL_BMAN_TEST) += bman-test.o
+bman-test-y = bman_test.o
+bman-test-$(CONFIG_FSL_BMAN_TEST_API) += bman_test_api.o
+
+obj-$(CONFIG_FSL_QMAN_TEST) += qman-test.o
+qman-test-y = qman_test.o
+qman-test-$(CONFIG_FSL_QMAN_TEST_API) += qman_test_api.o
+qman-test-$(CONFIG_FSL_QMAN_TEST_STASH) += qman_test_stash.o
diff --git a/drivers/soc/fsl/qbman/bman.c b/drivers/soc/fsl/qbman/bman.c
new file mode 100644
index 0000000..ffa48fd
--- /dev/null
+++ b/drivers/soc/fsl/qbman/bman.c
@@ -0,0 +1,797 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "bman_priv.h"
+
+#define IRQNAME "BMan portal %d"
+#define MAX_IRQNAME 16 /* big enough for "BMan portal %d" */
+
+/* Portal register assists */
+
+/* Cache-inhibited register offsets */
+#define BM_REG_RCR_PI_CINH 0x0000
+#define BM_REG_RCR_CI_CINH 0x0004
+#define BM_REG_RCR_ITR 0x0008
+#define BM_REG_CFG 0x0100
+#define BM_REG_SCN(n) (0x0200 + ((n) << 2))
+#define BM_REG_ISR 0x0e00
+#define BM_REG_IER 0x0e04
+#define BM_REG_ISDR 0x0e08
+#define BM_REG_IIR 0x0e0c
+
+/* Cache-enabled register offsets */
+#define BM_CL_CR 0x0000
+#define BM_CL_RR0 0x0100
+#define BM_CL_RR1 0x0140
+#define BM_CL_RCR 0x1000
+#define BM_CL_RCR_PI_CENA 0x3000
+#define BM_CL_RCR_CI_CENA 0x3100
+
+/*
+ * Portal modes.
+ * Enum types;
+ * pmode == production mode
+ * cmode == consumption mode,
+ * Enum values use 3 letter codes. First letter matches the portal mode,
+ * remaining two letters indicate;
+ * ci == cache-inhibited portal register
+ * ce == cache-enabled portal register
+ * vb == in-band valid-bit (cache-enabled)
+ */
+enum bm_rcr_pmode { /* matches BCSP_CFG::RPM */
+ bm_rcr_pci = 0, /* PI index, cache-inhibited */
+ bm_rcr_pce = 1, /* PI index, cache-enabled */
+ bm_rcr_pvb = 2 /* valid-bit */
+};
+enum bm_rcr_cmode { /* s/w-only */
+ bm_rcr_cci, /* CI index, cache-inhibited */
+ bm_rcr_cce /* CI index, cache-enabled */
+};
+
+
+/* --- Portal structures --- */
+
+#define BM_RCR_SIZE 8
+
+/* Release Command */
+struct bm_rcr_entry {
+ union {
+ struct {
+ u8 _ncw_verb; /* writes to this are non-coherent */
+ u8 bpid; /* used with BM_RCR_VERB_CMD_BPID_SINGLE */
+ u8 __reserved1[62];
+ };
+ struct bm_buffer bufs[8];
+ };
+};
+#define BM_RCR_VERB_VBIT 0x80
+#define BM_RCR_VERB_CMD_MASK 0x70 /* one of two values; */
+#define BM_RCR_VERB_CMD_BPID_SINGLE 0x20
+#define BM_RCR_VERB_CMD_BPID_MULTI 0x30
+#define BM_RCR_VERB_BUFCOUNT_MASK 0x0f /* values 1..8 */
+
+struct bm_rcr {
+ struct bm_rcr_entry *ring, *cursor;
+ u8 ci, available, ithresh, vbit;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ u32 busy;
+ enum bm_rcr_pmode pmode;
+ enum bm_rcr_cmode cmode;
+#endif
+};
+
+/* MC (Management Command) command */
+struct bm_mc_command {
+ u8 _ncw_verb; /* writes to this are non-coherent */
+ u8 bpid; /* used by acquire command */
+ u8 __reserved[62];
+};
+#define BM_MCC_VERB_VBIT 0x80
+#define BM_MCC_VERB_CMD_MASK 0x70 /* where the verb contains; */
+#define BM_MCC_VERB_CMD_ACQUIRE 0x10
+#define BM_MCC_VERB_CMD_QUERY 0x40
+#define BM_MCC_VERB_ACQUIRE_BUFCOUNT 0x0f /* values 1..8 go here */
+
+/* MC result, Acquire and Query Response */
+union bm_mc_result {
+ struct {
+ u8 verb;
+ u8 bpid;
+ u8 __reserved[62];
+ };
+ struct bm_buffer bufs[8];
+};
+#define BM_MCR_VERB_VBIT 0x80
+#define BM_MCR_VERB_CMD_MASK BM_MCC_VERB_CMD_MASK
+#define BM_MCR_VERB_CMD_ACQUIRE BM_MCC_VERB_CMD_ACQUIRE
+#define BM_MCR_VERB_CMD_QUERY BM_MCC_VERB_CMD_QUERY
+#define BM_MCR_VERB_CMD_ERR_INVALID 0x60
+#define BM_MCR_VERB_CMD_ERR_ECC 0x70
+#define BM_MCR_VERB_ACQUIRE_BUFCOUNT BM_MCC_VERB_ACQUIRE_BUFCOUNT /* 0..8 */
+#define BM_MCR_TIMEOUT 10000 /* us */
+
+struct bm_mc {
+ struct bm_mc_command *cr;
+ union bm_mc_result *rr;
+ u8 rridx, vbit;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ enum {
+ /* Can only be _mc_start()ed */
+ mc_idle,
+ /* Can only be _mc_commit()ed or _mc_abort()ed */
+ mc_user,
+ /* Can only be _mc_retry()ed */
+ mc_hw
+ } state;
+#endif
+};
+
+struct bm_addr {
+ void __iomem *ce; /* cache-enabled */
+ void __iomem *ci; /* cache-inhibited */
+};
+
+struct bm_portal {
+ struct bm_addr addr;
+ struct bm_rcr rcr;
+ struct bm_mc mc;
+} ____cacheline_aligned;
+
+/* Cache-inhibited register access. */
+static inline u32 bm_in(struct bm_portal *p, u32 offset)
+{
+ return __raw_readl(p->addr.ci + offset);
+}
+
+static inline void bm_out(struct bm_portal *p, u32 offset, u32 val)
+{
+ __raw_writel(val, p->addr.ci + offset);
+}
+
+/* Cache Enabled Portal Access */
+static inline void bm_cl_invalidate(struct bm_portal *p, u32 offset)
+{
+ dpaa_invalidate(p->addr.ce + offset);
+}
+
+static inline void bm_cl_touch_ro(struct bm_portal *p, u32 offset)
+{
+ dpaa_touch_ro(p->addr.ce + offset);
+}
+
+static inline u32 bm_ce_in(struct bm_portal *p, u32 offset)
+{
+ return __raw_readl(p->addr.ce + offset);
+}
+
+struct bman_portal {
+ struct bm_portal p;
+ /* interrupt sources processed by portal_isr(), configurable */
+ unsigned long irq_sources;
+ /* probing time config params for cpu-affine portals */
+ const struct bm_portal_config *config;
+ char irqname[MAX_IRQNAME];
+};
+
+static cpumask_t affine_mask;
+static DEFINE_SPINLOCK(affine_mask_lock);
+static DEFINE_PER_CPU(struct bman_portal, bman_affine_portal);
+
+static inline struct bman_portal *get_affine_portal(void)
+{
+ return &get_cpu_var(bman_affine_portal);
+}
+
+static inline void put_affine_portal(void)
+{
+ put_cpu_var(bman_affine_portal);
+}
+
+/*
+ * This object type refers to a pool, it isn't *the* pool. There may be
+ * more than one such object per BMan buffer pool, eg. if different users of the
+ * pool are operating via different portals.
+ */
+struct bman_pool {
+ /* index of the buffer pool to encapsulate (0-63) */
+ u32 bpid;
+ /* Used for hash-table admin when using depletion notifications. */
+ struct bman_portal *portal;
+ struct bman_pool *next;
+};
+
+static u32 poll_portal_slow(struct bman_portal *p, u32 is);
+
+static irqreturn_t portal_isr(int irq, void *ptr)
+{
+ struct bman_portal *p = ptr;
+ struct bm_portal *portal = &p->p;
+ u32 clear = p->irq_sources;
+ u32 is = bm_in(portal, BM_REG_ISR) & p->irq_sources;
+
+ if (unlikely(!is))
+ return IRQ_NONE;
+
+ clear |= poll_portal_slow(p, is);
+ bm_out(portal, BM_REG_ISR, clear);
+ return IRQ_HANDLED;
+}
+
+/* --- RCR API --- */
+
+#define RCR_SHIFT ilog2(sizeof(struct bm_rcr_entry))
+#define RCR_CARRY (uintptr_t)(BM_RCR_SIZE << RCR_SHIFT)
+
+/* Bit-wise logic to wrap a ring pointer by clearing the "carry bit" */
+static struct bm_rcr_entry *rcr_carryclear(struct bm_rcr_entry *p)
+{
+ uintptr_t addr = (uintptr_t)p;
+
+ addr &= ~RCR_CARRY;
+
+ return (struct bm_rcr_entry *)addr;
+}
+
+#ifdef CONFIG_FSL_DPAA_CHECKING
+/* Bit-wise logic to convert a ring pointer to a ring index */
+static int rcr_ptr2idx(struct bm_rcr_entry *e)
+{
+ return ((uintptr_t)e >> RCR_SHIFT) & (BM_RCR_SIZE - 1);
+}
+#endif
+
+/* Increment the 'cursor' ring pointer, taking 'vbit' into account */
+static inline void rcr_inc(struct bm_rcr *rcr)
+{
+ /* increment to the next RCR pointer and handle overflow and 'vbit' */
+ struct bm_rcr_entry *partial = rcr->cursor + 1;
+
+ rcr->cursor = rcr_carryclear(partial);
+ if (partial != rcr->cursor)
+ rcr->vbit ^= BM_RCR_VERB_VBIT;
+}
+
+static int bm_rcr_get_avail(struct bm_portal *portal)
+{
+ struct bm_rcr *rcr = &portal->rcr;
+
+ return rcr->available;
+}
+
+static int bm_rcr_get_fill(struct bm_portal *portal)
+{
+ struct bm_rcr *rcr = &portal->rcr;
+
+ return BM_RCR_SIZE - 1 - rcr->available;
+}
+
+static void bm_rcr_set_ithresh(struct bm_portal *portal, u8 ithresh)
+{
+ struct bm_rcr *rcr = &portal->rcr;
+
+ rcr->ithresh = ithresh;
+ bm_out(portal, BM_REG_RCR_ITR, ithresh);
+}
+
+static void bm_rcr_cce_prefetch(struct bm_portal *portal)
+{
+ __maybe_unused struct bm_rcr *rcr = &portal->rcr;
+
+ DPAA_ASSERT(rcr->cmode == bm_rcr_cce);
+ bm_cl_touch_ro(portal, BM_CL_RCR_CI_CENA);
+}
+
+static u8 bm_rcr_cce_update(struct bm_portal *portal)
+{
+ struct bm_rcr *rcr = &portal->rcr;
+ u8 diff, old_ci = rcr->ci;
+
+ DPAA_ASSERT(rcr->cmode == bm_rcr_cce);
+ rcr->ci = bm_ce_in(portal, BM_CL_RCR_CI_CENA) & (BM_RCR_SIZE - 1);
+ bm_cl_invalidate(portal, BM_CL_RCR_CI_CENA);
+ diff = dpaa_cyc_diff(BM_RCR_SIZE, old_ci, rcr->ci);
+ rcr->available += diff;
+ return diff;
+}
+
+static inline struct bm_rcr_entry *bm_rcr_start(struct bm_portal *portal)
+{
+ struct bm_rcr *rcr = &portal->rcr;
+
+ DPAA_ASSERT(!rcr->busy);
+ if (!rcr->available)
+ return NULL;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ rcr->busy = 1;
+#endif
+ dpaa_zero(rcr->cursor);
+ return rcr->cursor;
+}
+
+static inline void bm_rcr_pvb_commit(struct bm_portal *portal, u8 myverb)
+{
+ struct bm_rcr *rcr = &portal->rcr;
+ struct bm_rcr_entry *rcursor;
+
+ DPAA_ASSERT(rcr->busy);
+ DPAA_ASSERT(rcr->pmode == bm_rcr_pvb);
+ DPAA_ASSERT(rcr->available >= 1);
+ dma_wmb();
+ rcursor = rcr->cursor;
+ rcursor->_ncw_verb = myverb | rcr->vbit;
+ dpaa_flush(rcursor);
+ rcr_inc(rcr);
+ rcr->available--;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ rcr->busy = 0;
+#endif
+}
+
+static int bm_rcr_init(struct bm_portal *portal, enum bm_rcr_pmode pmode,
+ enum bm_rcr_cmode cmode)
+{
+ struct bm_rcr *rcr = &portal->rcr;
+ u32 cfg;
+ u8 pi;
+
+ rcr->ring = portal->addr.ce + BM_CL_RCR;
+ rcr->ci = bm_in(portal, BM_REG_RCR_CI_CINH) & (BM_RCR_SIZE - 1);
+ pi = bm_in(portal, BM_REG_RCR_PI_CINH) & (BM_RCR_SIZE - 1);
+ rcr->cursor = rcr->ring + pi;
+ rcr->vbit = (bm_in(portal, BM_REG_RCR_PI_CINH) & BM_RCR_SIZE) ?
+ BM_RCR_VERB_VBIT : 0;
+ rcr->available = BM_RCR_SIZE - 1
+ - dpaa_cyc_diff(BM_RCR_SIZE, rcr->ci, pi);
+ rcr->ithresh = bm_in(portal, BM_REG_RCR_ITR);
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ rcr->busy = 0;
+ rcr->pmode = pmode;
+ rcr->cmode = cmode;
+#endif
+ cfg = (bm_in(portal, BM_REG_CFG) & 0xffffffe0)
+ | (pmode & 0x3); /* BCSP_CFG::RPM */
+ bm_out(portal, BM_REG_CFG, cfg);
+ return 0;
+}
+
+static void bm_rcr_finish(struct bm_portal *portal)
+{
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ struct bm_rcr *rcr = &portal->rcr;
+ int i;
+
+ DPAA_ASSERT(!rcr->busy);
+
+ i = bm_in(portal, BM_REG_RCR_PI_CINH) & (BM_RCR_SIZE - 1);
+ if (i != rcr_ptr2idx(rcr->cursor))
+ pr_crit("losing uncommited RCR entries\n");
+
+ i = bm_in(portal, BM_REG_RCR_CI_CINH) & (BM_RCR_SIZE - 1);
+ if (i != rcr->ci)
+ pr_crit("missing existing RCR completions\n");
+ if (rcr->ci != rcr_ptr2idx(rcr->cursor))
+ pr_crit("RCR destroyed unquiesced\n");
+#endif
+}
+
+/* --- Management command API --- */
+static int bm_mc_init(struct bm_portal *portal)
+{
+ struct bm_mc *mc = &portal->mc;
+
+ mc->cr = portal->addr.ce + BM_CL_CR;
+ mc->rr = portal->addr.ce + BM_CL_RR0;
+ mc->rridx = (__raw_readb(&mc->cr->_ncw_verb) & BM_MCC_VERB_VBIT) ?
+ 0 : 1;
+ mc->vbit = mc->rridx ? BM_MCC_VERB_VBIT : 0;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ mc->state = mc_idle;
+#endif
+ return 0;
+}
+
+static void bm_mc_finish(struct bm_portal *portal)
+{
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ struct bm_mc *mc = &portal->mc;
+
+ DPAA_ASSERT(mc->state == mc_idle);
+ if (mc->state != mc_idle)
+ pr_crit("Losing incomplete MC command\n");
+#endif
+}
+
+static inline struct bm_mc_command *bm_mc_start(struct bm_portal *portal)
+{
+ struct bm_mc *mc = &portal->mc;
+
+ DPAA_ASSERT(mc->state == mc_idle);
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ mc->state = mc_user;
+#endif
+ dpaa_zero(mc->cr);
+ return mc->cr;
+}
+
+static inline void bm_mc_commit(struct bm_portal *portal, u8 myverb)
+{
+ struct bm_mc *mc = &portal->mc;
+ union bm_mc_result *rr = mc->rr + mc->rridx;
+
+ DPAA_ASSERT(mc->state == mc_user);
+ dma_wmb();
+ mc->cr->_ncw_verb = myverb | mc->vbit;
+ dpaa_flush(mc->cr);
+ dpaa_invalidate_touch_ro(rr);
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ mc->state = mc_hw;
+#endif
+}
+
+static inline union bm_mc_result *bm_mc_result(struct bm_portal *portal)
+{
+ struct bm_mc *mc = &portal->mc;
+ union bm_mc_result *rr = mc->rr + mc->rridx;
+
+ DPAA_ASSERT(mc->state == mc_hw);
+ /*
+ * The inactive response register's verb byte always returns zero until
+ * its command is submitted and completed. This includes the valid-bit,
+ * in case you were wondering...
+ */
+ if (!__raw_readb(&rr->verb)) {
+ dpaa_invalidate_touch_ro(rr);
+ return NULL;
+ }
+ mc->rridx ^= 1;
+ mc->vbit ^= BM_MCC_VERB_VBIT;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ mc->state = mc_idle;
+#endif
+ return rr;
+}
+
+static inline int bm_mc_result_timeout(struct bm_portal *portal,
+ union bm_mc_result **mcr)
+{
+ int timeout = BM_MCR_TIMEOUT;
+
+ do {
+ *mcr = bm_mc_result(portal);
+ if (*mcr)
+ break;
+ udelay(1);
+ } while (--timeout);
+
+ return timeout;
+}
+
+/* Disable all BSCN interrupts for the portal */
+static void bm_isr_bscn_disable(struct bm_portal *portal)
+{
+ bm_out(portal, BM_REG_SCN(0), 0);
+ bm_out(portal, BM_REG_SCN(1), 0);
+}
+
+static int bman_create_portal(struct bman_portal *portal,
+ const struct bm_portal_config *c)
+{
+ struct bm_portal *p;
+ int ret;
+
+ p = &portal->p;
+ /*
+ * prep the low-level portal struct with the mapped addresses from the
+ * config, everything that follows depends on it and "config" is more
+ * for (de)reference...
+ */
+ p->addr.ce = c->addr_virt[DPAA_PORTAL_CE];
+ p->addr.ci = c->addr_virt[DPAA_PORTAL_CI];
+ if (bm_rcr_init(p, bm_rcr_pvb, bm_rcr_cce)) {
+ dev_err(c->dev, "RCR initialisation failed\n");
+ goto fail_rcr;
+ }
+ if (bm_mc_init(p)) {
+ dev_err(c->dev, "MC initialisation failed\n");
+ goto fail_mc;
+ }
+ /*
+ * Default to all BPIDs disabled, we enable as required at
+ * run-time.
+ */
+ bm_isr_bscn_disable(p);
+
+ /* Write-to-clear any stale interrupt status bits */
+ bm_out(p, BM_REG_ISDR, 0xffffffff);
+ portal->irq_sources = 0;
+ bm_out(p, BM_REG_IER, 0);
+ bm_out(p, BM_REG_ISR, 0xffffffff);
+ snprintf(portal->irqname, MAX_IRQNAME, IRQNAME, c->cpu);
+ if (request_irq(c->irq, portal_isr, 0, portal->irqname, portal)) {
+ dev_err(c->dev, "request_irq() failed\n");
+ goto fail_irq;
+ }
+ if (c->cpu != -1 && irq_can_set_affinity(c->irq) &&
+ irq_set_affinity(c->irq, cpumask_of(c->cpu))) {
+ dev_err(c->dev, "irq_set_affinity() failed\n");
+ goto fail_affinity;
+ }
+
+ /* Need RCR to be empty before continuing */
+ ret = bm_rcr_get_fill(p);
+ if (ret) {
+ dev_err(c->dev, "RCR unclean\n");
+ goto fail_rcr_empty;
+ }
+ /* Success */
+ portal->config = c;
+
+ bm_out(p, BM_REG_ISDR, 0);
+ bm_out(p, BM_REG_IIR, 0);
+
+ return 0;
+
+fail_rcr_empty:
+fail_affinity:
+ free_irq(c->irq, portal);
+fail_irq:
+ bm_mc_finish(p);
+fail_mc:
+ bm_rcr_finish(p);
+fail_rcr:
+ return -EIO;
+}
+
+struct bman_portal *bman_create_affine_portal(const struct bm_portal_config *c)
+{
+ struct bman_portal *portal;
+ int err;
+
+ portal = &per_cpu(bman_affine_portal, c->cpu);
+ err = bman_create_portal(portal, c);
+ if (err)
+ return NULL;
+
+ spin_lock(&affine_mask_lock);
+ cpumask_set_cpu(c->cpu, &affine_mask);
+ spin_unlock(&affine_mask_lock);
+
+ return portal;
+}
+
+static u32 poll_portal_slow(struct bman_portal *p, u32 is)
+{
+ u32 ret = is;
+
+ if (is & BM_PIRQ_RCRI) {
+ bm_rcr_cce_update(&p->p);
+ bm_rcr_set_ithresh(&p->p, 0);
+ bm_out(&p->p, BM_REG_ISR, BM_PIRQ_RCRI);
+ is &= ~BM_PIRQ_RCRI;
+ }
+
+ /* There should be no status register bits left undefined */
+ DPAA_ASSERT(!is);
+ return ret;
+}
+
+int bman_p_irqsource_add(struct bman_portal *p, u32 bits)
+{
+ unsigned long irqflags;
+
+ local_irq_save(irqflags);
+ set_bits(bits & BM_PIRQ_VISIBLE, &p->irq_sources);
+ bm_out(&p->p, BM_REG_IER, p->irq_sources);
+ local_irq_restore(irqflags);
+ return 0;
+}
+
+static int bm_shutdown_pool(u32 bpid)
+{
+ struct bm_mc_command *bm_cmd;
+ union bm_mc_result *bm_res;
+
+ while (1) {
+ struct bman_portal *p = get_affine_portal();
+ /* Acquire buffers until empty */
+ bm_cmd = bm_mc_start(&p->p);
+ bm_cmd->bpid = bpid;
+ bm_mc_commit(&p->p, BM_MCC_VERB_CMD_ACQUIRE | 1);
+ if (!bm_mc_result_timeout(&p->p, &bm_res)) {
+ put_affine_portal();
+ pr_crit("BMan Acquire Command timedout\n");
+ return -ETIMEDOUT;
+ }
+ if (!(bm_res->verb & BM_MCR_VERB_ACQUIRE_BUFCOUNT)) {
+ put_affine_portal();
+ /* Pool is empty */
+ return 0;
+ }
+ put_affine_portal();
+ }
+
+ return 0;
+}
+
+struct gen_pool *bm_bpalloc;
+
+static int bm_alloc_bpid_range(u32 *result, u32 count)
+{
+ unsigned long addr;
+
+ addr = gen_pool_alloc(bm_bpalloc, count);
+ if (!addr)
+ return -ENOMEM;
+
+ *result = addr & ~DPAA_GENALLOC_OFF;
+
+ return 0;
+}
+
+static int bm_release_bpid(u32 bpid)
+{
+ int ret;
+
+ ret = bm_shutdown_pool(bpid);
+ if (ret) {
+ pr_debug("BPID %d leaked\n", bpid);
+ return ret;
+ }
+
+ gen_pool_free(bm_bpalloc, bpid | DPAA_GENALLOC_OFF, 1);
+ return 0;
+}
+
+struct bman_pool *bman_new_pool(void)
+{
+ struct bman_pool *pool = NULL;
+ u32 bpid;
+
+ if (bm_alloc_bpid_range(&bpid, 1))
+ return NULL;
+
+ pool = kmalloc(sizeof(*pool), GFP_KERNEL);
+ if (!pool)
+ goto err;
+
+ pool->bpid = bpid;
+
+ return pool;
+err:
+ bm_release_bpid(bpid);
+ kfree(pool);
+ return NULL;
+}
+EXPORT_SYMBOL(bman_new_pool);
+
+void bman_free_pool(struct bman_pool *pool)
+{
+ bm_release_bpid(pool->bpid);
+
+ kfree(pool);
+}
+EXPORT_SYMBOL(bman_free_pool);
+
+int bman_get_bpid(const struct bman_pool *pool)
+{
+ return pool->bpid;
+}
+EXPORT_SYMBOL(bman_get_bpid);
+
+static void update_rcr_ci(struct bman_portal *p, int avail)
+{
+ if (avail)
+ bm_rcr_cce_prefetch(&p->p);
+ else
+ bm_rcr_cce_update(&p->p);
+}
+
+int bman_release(struct bman_pool *pool, const struct bm_buffer *bufs, u8 num)
+{
+ struct bman_portal *p;
+ struct bm_rcr_entry *r;
+ unsigned long irqflags;
+ int avail, timeout = 1000; /* 1ms */
+ int i = num - 1;
+
+ DPAA_ASSERT(num > 0 && num <= 8);
+
+ do {
+ p = get_affine_portal();
+ local_irq_save(irqflags);
+ avail = bm_rcr_get_avail(&p->p);
+ if (avail < 2)
+ update_rcr_ci(p, avail);
+ r = bm_rcr_start(&p->p);
+ local_irq_restore(irqflags);
+ put_affine_portal();
+ if (likely(r))
+ break;
+
+ udelay(1);
+ } while (--timeout);
+
+ if (unlikely(!timeout))
+ return -ETIMEDOUT;
+
+ p = get_affine_portal();
+ local_irq_save(irqflags);
+ /*
+ * we can copy all but the first entry, as this can trigger badness
+ * with the valid-bit
+ */
+ bm_buffer_set64(r->bufs, bm_buffer_get64(bufs));
+ bm_buffer_set_bpid(r->bufs, pool->bpid);
+ if (i)
+ memcpy(&r->bufs[1], &bufs[1], i * sizeof(bufs[0]));
+
+ bm_rcr_pvb_commit(&p->p, BM_RCR_VERB_CMD_BPID_SINGLE |
+ (num & BM_RCR_VERB_BUFCOUNT_MASK));
+
+ local_irq_restore(irqflags);
+ put_affine_portal();
+ return 0;
+}
+EXPORT_SYMBOL(bman_release);
+
+int bman_acquire(struct bman_pool *pool, struct bm_buffer *bufs, u8 num)
+{
+ struct bman_portal *p = get_affine_portal();
+ struct bm_mc_command *mcc;
+ union bm_mc_result *mcr;
+ int ret;
+
+ DPAA_ASSERT(num > 0 && num <= 8);
+
+ mcc = bm_mc_start(&p->p);
+ mcc->bpid = pool->bpid;
+ bm_mc_commit(&p->p, BM_MCC_VERB_CMD_ACQUIRE |
+ (num & BM_MCC_VERB_ACQUIRE_BUFCOUNT));
+ if (!bm_mc_result_timeout(&p->p, &mcr)) {
+ put_affine_portal();
+ pr_crit("BMan Acquire Timeout\n");
+ return -ETIMEDOUT;
+ }
+ ret = mcr->verb & BM_MCR_VERB_ACQUIRE_BUFCOUNT;
+ if (bufs)
+ memcpy(&bufs[0], &mcr->bufs[0], num * sizeof(bufs[0]));
+
+ put_affine_portal();
+ if (ret != num)
+ ret = -ENOMEM;
+ return ret;
+}
+EXPORT_SYMBOL(bman_acquire);
+
+const struct bm_portal_config *
+bman_get_bm_portal_config(const struct bman_portal *portal)
+{
+ return portal->config;
+}
diff --git a/drivers/soc/fsl/qbman/bman_ccsr.c b/drivers/soc/fsl/qbman/bman_ccsr.c
new file mode 100644
index 0000000..9deb052
--- /dev/null
+++ b/drivers/soc/fsl/qbman/bman_ccsr.c
@@ -0,0 +1,263 @@
+/* Copyright (c) 2009 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "bman_priv.h"
+
+u16 bman_ip_rev;
+EXPORT_SYMBOL(bman_ip_rev);
+
+/* Register offsets */
+#define REG_FBPR_FPC 0x0800
+#define REG_ECSR 0x0a00
+#define REG_ECIR 0x0a04
+#define REG_EADR 0x0a08
+#define REG_EDATA(n) (0x0a10 + ((n) * 0x04))
+#define REG_SBEC(n) (0x0a80 + ((n) * 0x04))
+#define REG_IP_REV_1 0x0bf8
+#define REG_IP_REV_2 0x0bfc
+#define REG_FBPR_BARE 0x0c00
+#define REG_FBPR_BAR 0x0c04
+#define REG_FBPR_AR 0x0c10
+#define REG_SRCIDR 0x0d04
+#define REG_LIODNR 0x0d08
+#define REG_ERR_ISR 0x0e00
+#define REG_ERR_IER 0x0e04
+#define REG_ERR_ISDR 0x0e08
+
+/* Used by all error interrupt registers except 'inhibit' */
+#define BM_EIRQ_IVCI 0x00000010 /* Invalid Command Verb */
+#define BM_EIRQ_FLWI 0x00000008 /* FBPR Low Watermark */
+#define BM_EIRQ_MBEI 0x00000004 /* Multi-bit ECC Error */
+#define BM_EIRQ_SBEI 0x00000002 /* Single-bit ECC Error */
+#define BM_EIRQ_BSCN 0x00000001 /* pool State Change Notification */
+
+struct bman_hwerr_txt {
+ u32 mask;
+ const char *txt;
+};
+
+static const struct bman_hwerr_txt bman_hwerr_txts[] = {
+ { BM_EIRQ_IVCI, "Invalid Command Verb" },
+ { BM_EIRQ_FLWI, "FBPR Low Watermark" },
+ { BM_EIRQ_MBEI, "Multi-bit ECC Error" },
+ { BM_EIRQ_SBEI, "Single-bit ECC Error" },
+ { BM_EIRQ_BSCN, "Pool State Change Notification" },
+};
+
+/* Only trigger low water mark interrupt once only */
+#define BMAN_ERRS_TO_DISABLE BM_EIRQ_FLWI
+
+/* Pointer to the start of the BMan's CCSR space */
+static u32 __iomem *bm_ccsr_start;
+
+static inline u32 bm_ccsr_in(u32 offset)
+{
+ return ioread32be(bm_ccsr_start + offset/4);
+}
+static inline void bm_ccsr_out(u32 offset, u32 val)
+{
+ iowrite32be(val, bm_ccsr_start + offset/4);
+}
+
+static void bm_get_version(u16 *id, u8 *major, u8 *minor)
+{
+ u32 v = bm_ccsr_in(REG_IP_REV_1);
+ *id = (v >> 16);
+ *major = (v >> 8) & 0xff;
+ *minor = v & 0xff;
+}
+
+/* signal transactions for FBPRs with higher priority */
+#define FBPR_AR_RPRIO_HI BIT(30)
+
+static void bm_set_memory(u64 ba, u32 size)
+{
+ u32 exp = ilog2(size);
+ /* choke if size isn't within range */
+ DPAA_ASSERT(size >= 4096 && size <= 1024*1024*1024 &&
+ is_power_of_2(size));
+ /* choke if '[e]ba' has lower-alignment than 'size' */
+ DPAA_ASSERT(!(ba & (size - 1)));
+ bm_ccsr_out(REG_FBPR_BARE, upper_32_bits(ba));
+ bm_ccsr_out(REG_FBPR_BAR, lower_32_bits(ba));
+ bm_ccsr_out(REG_FBPR_AR, exp - 1);
+}
+
+/*
+ * Location and size of BMan private memory
+ *
+ * Ideally we would use the DMA API to turn rmem->base into a DMA address
+ * (especially if iommu translations ever get involved). Unfortunately, the
+ * DMA API currently does not allow mapping anything that is not backed with
+ * a struct page.
+ */
+static dma_addr_t fbpr_a;
+static size_t fbpr_sz;
+
+static int bman_fbpr(struct reserved_mem *rmem)
+{
+ fbpr_a = rmem->base;
+ fbpr_sz = rmem->size;
+
+ WARN_ON(!(fbpr_a && fbpr_sz));
+
+ return 0;
+}
+RESERVEDMEM_OF_DECLARE(bman_fbpr, "fsl,bman-fbpr", bman_fbpr);
+
+static irqreturn_t bman_isr(int irq, void *ptr)
+{
+ u32 isr_val, ier_val, ecsr_val, isr_mask, i;
+ struct device *dev = ptr;
+
+ ier_val = bm_ccsr_in(REG_ERR_IER);
+ isr_val = bm_ccsr_in(REG_ERR_ISR);
+ ecsr_val = bm_ccsr_in(REG_ECSR);
+ isr_mask = isr_val & ier_val;
+
+ if (!isr_mask)
+ return IRQ_NONE;
+
+ for (i = 0; i < ARRAY_SIZE(bman_hwerr_txts); i++) {
+ if (bman_hwerr_txts[i].mask & isr_mask) {
+ dev_err_ratelimited(dev, "ErrInt: %s\n",
+ bman_hwerr_txts[i].txt);
+ if (bman_hwerr_txts[i].mask & ecsr_val) {
+ /* Re-arm error capture registers */
+ bm_ccsr_out(REG_ECSR, ecsr_val);
+ }
+ if (bman_hwerr_txts[i].mask & BMAN_ERRS_TO_DISABLE) {
+ dev_dbg(dev, "Disabling error 0x%x\n",
+ bman_hwerr_txts[i].mask);
+ ier_val &= ~bman_hwerr_txts[i].mask;
+ bm_ccsr_out(REG_ERR_IER, ier_val);
+ }
+ }
+ }
+ bm_ccsr_out(REG_ERR_ISR, isr_val);
+
+ return IRQ_HANDLED;
+}
+
+static int fsl_bman_probe(struct platform_device *pdev)
+{
+ int ret, err_irq;
+ struct device *dev = &pdev->dev;
+ struct device_node *node = dev->of_node;
+ struct resource *res;
+ u16 id, bm_pool_cnt;
+ u8 major, minor;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res) {
+ dev_err(dev, "Can't get %s property 'IORESOURCE_MEM'\n",
+ node->full_name);
+ return -ENXIO;
+ }
+ bm_ccsr_start = devm_ioremap(dev, res->start,
+ res->end - res->start + 1);
+ if (!bm_ccsr_start)
+ return -ENXIO;
+
+ bm_get_version(&id, &major, &minor);
+ if (major == 1 && minor == 0) {
+ bman_ip_rev = BMAN_REV10;
+ bm_pool_cnt = BM_POOL_MAX;
+ } else if (major == 2 && minor == 0) {
+ bman_ip_rev = BMAN_REV20;
+ bm_pool_cnt = 8;
+ } else if (major == 2 && minor == 1) {
+ bman_ip_rev = BMAN_REV21;
+ bm_pool_cnt = BM_POOL_MAX;
+ } else {
+ dev_err(dev, "Unknown Bman version:%04x,%02x,%02x\n",
+ id, major, minor);
+ return -ENODEV;
+ }
+
+ bm_set_memory(fbpr_a, fbpr_sz);
+
+ err_irq = platform_get_irq(pdev, 0);
+ if (err_irq <= 0) {
+ dev_info(dev, "Can't get %s IRQ\n", node->full_name);
+ return -ENODEV;
+ }
+ ret = devm_request_irq(dev, err_irq, bman_isr, IRQF_SHARED, "bman-err",
+ dev);
+ if (ret) {
+ dev_err(dev, "devm_request_irq() failed %d for '%s'\n",
+ ret, node->full_name);
+ return ret;
+ }
+ /* Disable Buffer Pool State Change */
+ bm_ccsr_out(REG_ERR_ISDR, BM_EIRQ_BSCN);
+ /*
+ * Write-to-clear any stale bits, (eg. starvation being asserted prior
+ * to resource allocation during driver init).
+ */
+ bm_ccsr_out(REG_ERR_ISR, 0xffffffff);
+ /* Enable Error Interrupts */
+ bm_ccsr_out(REG_ERR_IER, 0xffffffff);
+
+ bm_bpalloc = devm_gen_pool_create(dev, 0, -1, "bman-bpalloc");
+ if (IS_ERR(bm_bpalloc)) {
+ ret = PTR_ERR(bm_bpalloc);
+ dev_err(dev, "bman-bpalloc pool init failed (%d)\n", ret);
+ return ret;
+ }
+
+ /* seed BMan resource pool */
+ ret = gen_pool_add(bm_bpalloc, DPAA_GENALLOC_OFF, bm_pool_cnt, -1);
+ if (ret) {
+ dev_err(dev, "Failed to seed BPID range [%d..%d] (%d)\n",
+ 0, bm_pool_cnt - 1, ret);
+ return ret;
+ }
+
+ return 0;
+};
+
+static const struct of_device_id fsl_bman_ids[] = {
+ {
+ .compatible = "fsl,bman",
+ },
+ {}
+};
+
+static struct platform_driver fsl_bman_driver = {
+ .driver = {
+ .name = KBUILD_MODNAME,
+ .of_match_table = fsl_bman_ids,
+ .suppress_bind_attrs = true,
+ },
+ .probe = fsl_bman_probe,
+};
+
+builtin_platform_driver(fsl_bman_driver);
diff --git a/drivers/soc/fsl/qbman/bman_portal.c b/drivers/soc/fsl/qbman/bman_portal.c
new file mode 100644
index 0000000..6579cc1
--- /dev/null
+++ b/drivers/soc/fsl/qbman/bman_portal.c
@@ -0,0 +1,219 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "bman_priv.h"
+
+static struct bman_portal *affine_bportals[NR_CPUS];
+static struct cpumask portal_cpus;
+/* protect bman global registers and global data shared among portals */
+static DEFINE_SPINLOCK(bman_lock);
+
+static struct bman_portal *init_pcfg(struct bm_portal_config *pcfg)
+{
+ struct bman_portal *p = bman_create_affine_portal(pcfg);
+
+ if (!p) {
+ dev_crit(pcfg->dev, "%s: Portal failure on cpu %d\n",
+ __func__, pcfg->cpu);
+ return NULL;
+ }
+
+ bman_p_irqsource_add(p, BM_PIRQ_RCRI);
+ affine_bportals[pcfg->cpu] = p;
+
+ dev_info(pcfg->dev, "Portal initialised, cpu %d\n", pcfg->cpu);
+
+ return p;
+}
+
+static void bman_offline_cpu(unsigned int cpu)
+{
+ struct bman_portal *p = affine_bportals[cpu];
+ const struct bm_portal_config *pcfg;
+
+ if (!p)
+ return;
+
+ pcfg = bman_get_bm_portal_config(p);
+ if (!pcfg)
+ return;
+
+ irq_set_affinity(pcfg->irq, cpumask_of(0));
+}
+
+static void bman_online_cpu(unsigned int cpu)
+{
+ struct bman_portal *p = affine_bportals[cpu];
+ const struct bm_portal_config *pcfg;
+
+ if (!p)
+ return;
+
+ pcfg = bman_get_bm_portal_config(p);
+ if (!pcfg)
+ return;
+
+ irq_set_affinity(pcfg->irq, cpumask_of(cpu));
+}
+
+static int bman_hotplug_cpu_callback(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
+{
+ unsigned int cpu = (unsigned long)hcpu;
+
+ switch (action) {
+ case CPU_ONLINE:
+ case CPU_ONLINE_FROZEN:
+ bman_online_cpu(cpu);
+ break;
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ bman_offline_cpu(cpu);
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block bman_hotplug_cpu_notifier = {
+ .notifier_call = bman_hotplug_cpu_callback,
+};
+
+static int bman_portal_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct device_node *node = dev->of_node;
+ struct bm_portal_config *pcfg;
+ struct resource *addr_phys[2];
+ void __iomem *va;
+ int irq, cpu;
+
+ pcfg = devm_kmalloc(dev, sizeof(*pcfg), GFP_KERNEL);
+ if (!pcfg)
+ return -ENOMEM;
+
+ pcfg->dev = dev;
+
+ addr_phys[0] = platform_get_resource(pdev, IORESOURCE_MEM,
+ DPAA_PORTAL_CE);
+ if (!addr_phys[0]) {
+ dev_err(dev, "Can't get %s property 'reg::CE'\n",
+ node->full_name);
+ return -ENXIO;
+ }
+
+ addr_phys[1] = platform_get_resource(pdev, IORESOURCE_MEM,
+ DPAA_PORTAL_CI);
+ if (!addr_phys[1]) {
+ dev_err(dev, "Can't get %s property 'reg::CI'\n",
+ node->full_name);
+ return -ENXIO;
+ }
+
+ pcfg->cpu = -1;
+
+ irq = platform_get_irq(pdev, 0);
+ if (irq <= 0) {
+ dev_err(dev, "Can't get %s IRQ'\n", node->full_name);
+ return -ENXIO;
+ }
+ pcfg->irq = irq;
+
+ va = ioremap_prot(addr_phys[0]->start, resource_size(addr_phys[0]), 0);
+ if (!va)
+ goto err_ioremap1;
+
+ pcfg->addr_virt[DPAA_PORTAL_CE] = va;
+
+ va = ioremap_prot(addr_phys[1]->start, resource_size(addr_phys[1]),
+ _PAGE_GUARDED | _PAGE_NO_CACHE);
+ if (!va)
+ goto err_ioremap2;
+
+ pcfg->addr_virt[DPAA_PORTAL_CI] = va;
+
+ spin_lock(&bman_lock);
+ cpu = cpumask_next_zero(-1, &portal_cpus);
+ if (cpu >= nr_cpu_ids) {
+ /* unassigned portal, skip init */
+ spin_unlock(&bman_lock);
+ return 0;
+ }
+
+ cpumask_set_cpu(cpu, &portal_cpus);
+ spin_unlock(&bman_lock);
+ pcfg->cpu = cpu;
+
+ if (!init_pcfg(pcfg))
+ goto err_ioremap2;
+
+ /* clear irq affinity if assigned cpu is offline */
+ if (!cpu_online(cpu))
+ bman_offline_cpu(cpu);
+
+ return 0;
+
+err_ioremap2:
+ iounmap(pcfg->addr_virt[DPAA_PORTAL_CE]);
+err_ioremap1:
+ dev_err(dev, "ioremap failed\n");
+ return -ENXIO;
+}
+
+static const struct of_device_id bman_portal_ids[] = {
+ {
+ .compatible = "fsl,bman-portal",
+ },
+ {}
+};
+MODULE_DEVICE_TABLE(of, bman_portal_ids);
+
+static struct platform_driver bman_portal_driver = {
+ .driver = {
+ .name = KBUILD_MODNAME,
+ .of_match_table = bman_portal_ids,
+ },
+ .probe = bman_portal_probe,
+};
+
+static int __init bman_portal_driver_register(struct platform_driver *drv)
+{
+ int ret;
+
+ ret = platform_driver_register(drv);
+ if (ret < 0)
+ return ret;
+
+ register_hotcpu_notifier(&bman_hotplug_cpu_notifier);
+
+ return 0;
+}
+
+module_driver(bman_portal_driver,
+ bman_portal_driver_register, platform_driver_unregister);
diff --git a/drivers/soc/fsl/qbman/bman_priv.h b/drivers/soc/fsl/qbman/bman_priv.h
new file mode 100644
index 0000000..f6896a2
--- /dev/null
+++ b/drivers/soc/fsl/qbman/bman_priv.h
@@ -0,0 +1,80 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include "dpaa_sys.h"
+
+#include <soc/fsl/bman.h>
+
+/* Portal processing (interrupt) sources */
+#define BM_PIRQ_RCRI 0x00000002 /* RCR Ring (below threshold) */
+
+/* Revision info (for errata and feature handling) */
+#define BMAN_REV10 0x0100
+#define BMAN_REV20 0x0200
+#define BMAN_REV21 0x0201
+extern u16 bman_ip_rev; /* 0 if uninitialised, otherwise BMAN_REVx */
+
+extern struct gen_pool *bm_bpalloc;
+
+struct bm_portal_config {
+ /*
+ * Corenet portal addresses;
+ * [0]==cache-enabled, [1]==cache-inhibited.
+ */
+ void __iomem *addr_virt[2];
+ /* Allow these to be joined in lists */
+ struct list_head list;
+ struct device *dev;
+ /* User-visible portal configuration settings */
+ /* portal is affined to this cpu */
+ int cpu;
+ /* portal interrupt line */
+ int irq;
+};
+
+struct bman_portal *bman_create_affine_portal(
+ const struct bm_portal_config *config);
+/*
+ * The below bman_p_***() variant might be called in a situation that the cpu
+ * which the portal affine to is not online yet.
+ * @bman_portal specifies which portal the API will use.
+ */
+int bman_p_irqsource_add(struct bman_portal *p, u32 bits);
+
+/*
+ * Used by all portal interrupt registers except 'inhibit'
+ * This mask contains all the "irqsource" bits visible to API users
+ */
+#define BM_PIRQ_VISIBLE BM_PIRQ_RCRI
+
+const struct bm_portal_config *
+bman_get_bm_portal_config(const struct bman_portal *portal);
diff --git a/drivers/soc/fsl/qbman/bman_test.c b/drivers/soc/fsl/qbman/bman_test.c
new file mode 100644
index 0000000..09b1c96
--- /dev/null
+++ b/drivers/soc/fsl/qbman/bman_test.c
@@ -0,0 +1,53 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "bman_test.h"
+
+MODULE_AUTHOR("Geoff Thorpe");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("BMan testing");
+
+static int test_init(void)
+{
+#ifdef CONFIG_FSL_BMAN_TEST_API
+ int loop = 1;
+
+ while (loop--)
+ bman_test_api();
+#endif
+ return 0;
+}
+
+static void test_exit(void)
+{
+}
+
+module_init(test_init);
+module_exit(test_exit);
diff --git a/drivers/soc/fsl/qbman/bman_test.h b/drivers/soc/fsl/qbman/bman_test.h
new file mode 100644
index 0000000..037ed34
--- /dev/null
+++ b/drivers/soc/fsl/qbman/bman_test.h
@@ -0,0 +1,35 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "bman_priv.h"
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+void bman_test_api(void);
diff --git a/drivers/soc/fsl/qbman/bman_test_api.c b/drivers/soc/fsl/qbman/bman_test_api.c
new file mode 100644
index 0000000..6f6bdd1
--- /dev/null
+++ b/drivers/soc/fsl/qbman/bman_test_api.c
@@ -0,0 +1,151 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "bman_test.h"
+
+#define NUM_BUFS 93
+#define LOOPS 3
+#define BMAN_TOKEN_MASK 0x00FFFFFFFFFFLLU
+
+static struct bman_pool *pool;
+static struct bm_buffer bufs_in[NUM_BUFS] ____cacheline_aligned;
+static struct bm_buffer bufs_out[NUM_BUFS] ____cacheline_aligned;
+static int bufs_received;
+
+static void bufs_init(void)
+{
+ int i;
+
+ for (i = 0; i < NUM_BUFS; i++)
+ bm_buffer_set64(&bufs_in[i], 0xfedc01234567LLU * i);
+ bufs_received = 0;
+}
+
+static inline int bufs_cmp(const struct bm_buffer *a, const struct bm_buffer *b)
+{
+ if (bman_ip_rev == BMAN_REV20 || bman_ip_rev == BMAN_REV21) {
+
+ /*
+ * On SoCs with BMan revison 2.0, BMan only respects the 40
+ * LS-bits of buffer addresses, masking off the upper 8-bits on
+ * release commands. The API provides for 48-bit addresses
+ * because some SoCs support all 48-bits. When generating
+ * garbage addresses for testing, we either need to zero the
+ * upper 8-bits when releasing to BMan (otherwise we'll be
+ * disappointed when the buffers we acquire back from BMan
+ * don't match), or we need to mask the upper 8-bits off when
+ * comparing. We do the latter.
+ */
+ if ((bm_buffer_get64(a) & BMAN_TOKEN_MASK) <
+ (bm_buffer_get64(b) & BMAN_TOKEN_MASK))
+ return -1;
+ if ((bm_buffer_get64(a) & BMAN_TOKEN_MASK) >
+ (bm_buffer_get64(b) & BMAN_TOKEN_MASK))
+ return 1;
+ } else {
+ if (bm_buffer_get64(a) < bm_buffer_get64(b))
+ return -1;
+ if (bm_buffer_get64(a) > bm_buffer_get64(b))
+ return 1;
+ }
+
+ return 0;
+}
+
+static void bufs_confirm(void)
+{
+ int i, j;
+
+ for (i = 0; i < NUM_BUFS; i++) {
+ int matches = 0;
+
+ for (j = 0; j < NUM_BUFS; j++)
+ if (!bufs_cmp(&bufs_in[i], &bufs_out[j]))
+ matches++;
+ WARN_ON(matches != 1);
+ }
+}
+
+/* test */
+void bman_test_api(void)
+{
+ int i, loops = LOOPS;
+
+ bufs_init();
+
+ pr_info("%s(): Starting\n", __func__);
+
+ pool = bman_new_pool();
+ if (!pool) {
+ pr_crit("bman_new_pool() failed\n");
+ goto failed;
+ }
+
+ /* Release buffers */
+do_loop:
+ i = 0;
+ while (i < NUM_BUFS) {
+ int num = 8;
+
+ if (i + num > NUM_BUFS)
+ num = NUM_BUFS - i;
+ if (bman_release(pool, bufs_in + i, num)) {
+ pr_crit("bman_release() failed\n");
+ goto failed;
+ }
+ i += num;
+ }
+
+ /* Acquire buffers */
+ while (i > 0) {
+ int tmp, num = 8;
+
+ if (num > i)
+ num = i;
+ tmp = bman_acquire(pool, bufs_out + i - num, num);
+ WARN_ON(tmp != num);
+ i -= num;
+ }
+ i = bman_acquire(pool, NULL, 1);
+ WARN_ON(i > 0);
+
+ bufs_confirm();
+
+ if (--loops)
+ goto do_loop;
+
+ /* Clean up */
+ bman_free_pool(pool);
+ pr_info("%s(): Finished\n", __func__);
+ return;
+
+failed:
+ WARN_ON(1);
+}
diff --git a/drivers/soc/fsl/qbman/dpaa_sys.h b/drivers/soc/fsl/qbman/dpaa_sys.h
new file mode 100644
index 0000000..b63fd72
--- /dev/null
+++ b/drivers/soc/fsl/qbman/dpaa_sys.h
@@ -0,0 +1,103 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __DPAA_SYS_H
+#define __DPAA_SYS_H
+
+#include <linux/cpu.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/kthread.h>
+#include <linux/vmalloc.h>
+#include <linux/platform_device.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/prefetch.h>
+#include <linux/genalloc.h>
+#include <asm/cacheflush.h>
+
+/* For 2-element tables related to cache-inhibited and cache-enabled mappings */
+#define DPAA_PORTAL_CE 0
+#define DPAA_PORTAL_CI 1
+
+#if (L1_CACHE_BYTES != 32) && (L1_CACHE_BYTES != 64)
+#error "Unsupported Cacheline Size"
+#endif
+
+static inline void dpaa_flush(void *p)
+{
+#ifdef CONFIG_PPC
+ flush_dcache_range((unsigned long)p, (unsigned long)p+64);
+#elif defined(CONFIG_ARM32)
+ __cpuc_flush_dcache_area(p, 64);
+#elif defined(CONFIG_ARM64)
+ __flush_dcache_area(p, 64);
+#endif
+}
+
+#define dpaa_invalidate(p) dpaa_flush(p)
+
+#define dpaa_zero(p) memset(p, 0, 64)
+
+static inline void dpaa_touch_ro(void *p)
+{
+#if (L1_CACHE_BYTES == 32)
+ prefetch(p+32);
+#endif
+ prefetch(p);
+}
+
+/* Commonly used combo */
+static inline void dpaa_invalidate_touch_ro(void *p)
+{
+ dpaa_invalidate(p);
+ dpaa_touch_ro(p);
+}
+
+
+#ifdef CONFIG_FSL_DPAA_CHECKING
+#define DPAA_ASSERT(x) WARN_ON(!(x))
+#else
+#define DPAA_ASSERT(x)
+#endif
+
+/* cyclic helper for rings */
+static inline u8 dpaa_cyc_diff(u8 ringsize, u8 first, u8 last)
+{
+ /* 'first' is included, 'last' is excluded */
+ if (first <= last)
+ return last - first;
+ return ringsize + last - first;
+}
+
+/* Offset applied to genalloc pools due to zero being an error return */
+#define DPAA_GENALLOC_OFF 0x80000000
+
+#endif /* __DPAA_SYS_H */
diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c
new file mode 100644
index 0000000..119054b
--- /dev/null
+++ b/drivers/soc/fsl/qbman/qman.c
@@ -0,0 +1,2881 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "qman_priv.h"
+
+#define DQRR_MAXFILL 15
+#define EQCR_ITHRESH 4 /* if EQCR congests, interrupt threshold */
+#define IRQNAME "QMan portal %d"
+#define MAX_IRQNAME 16 /* big enough for "QMan portal %d" */
+#define QMAN_POLL_LIMIT 32
+#define QMAN_PIRQ_DQRR_ITHRESH 12
+#define QMAN_PIRQ_MR_ITHRESH 4
+#define QMAN_PIRQ_IPERIOD 100
+
+/* Portal register assists */
+
+/* Cache-inhibited register offsets */
+#define QM_REG_EQCR_PI_CINH 0x0000
+#define QM_REG_EQCR_CI_CINH 0x0004
+#define QM_REG_EQCR_ITR 0x0008
+#define QM_REG_DQRR_PI_CINH 0x0040
+#define QM_REG_DQRR_CI_CINH 0x0044
+#define QM_REG_DQRR_ITR 0x0048
+#define QM_REG_DQRR_DCAP 0x0050
+#define QM_REG_DQRR_SDQCR 0x0054
+#define QM_REG_DQRR_VDQCR 0x0058
+#define QM_REG_DQRR_PDQCR 0x005c
+#define QM_REG_MR_PI_CINH 0x0080
+#define QM_REG_MR_CI_CINH 0x0084
+#define QM_REG_MR_ITR 0x0088
+#define QM_REG_CFG 0x0100
+#define QM_REG_ISR 0x0e00
+#define QM_REG_IER 0x0e04
+#define QM_REG_ISDR 0x0e08
+#define QM_REG_IIR 0x0e0c
+#define QM_REG_ITPR 0x0e14
+
+/* Cache-enabled register offsets */
+#define QM_CL_EQCR 0x0000
+#define QM_CL_DQRR 0x1000
+#define QM_CL_MR 0x2000
+#define QM_CL_EQCR_PI_CENA 0x3000
+#define QM_CL_EQCR_CI_CENA 0x3100
+#define QM_CL_DQRR_PI_CENA 0x3200
+#define QM_CL_DQRR_CI_CENA 0x3300
+#define QM_CL_MR_PI_CENA 0x3400
+#define QM_CL_MR_CI_CENA 0x3500
+#define QM_CL_CR 0x3800
+#define QM_CL_RR0 0x3900
+#define QM_CL_RR1 0x3940
+
+/*
+ * BTW, the drivers (and h/w programming model) already obtain the required
+ * synchronisation for portal accesses and data-dependencies. Use of barrier()s
+ * or other order-preserving primitives simply degrade performance. Hence the
+ * use of the __raw_*() interfaces, which simply ensure that the compiler treats
+ * the portal registers as volatile
+ */
+
+/* Cache-enabled ring access */
+#define qm_cl(base, idx) ((void *)base + ((idx) << 6))
+
+/*
+ * Portal modes.
+ * Enum types;
+ * pmode == production mode
+ * cmode == consumption mode,
+ * dmode == h/w dequeue mode.
+ * Enum values use 3 letter codes. First letter matches the portal mode,
+ * remaining two letters indicate;
+ * ci == cache-inhibited portal register
+ * ce == cache-enabled portal register
+ * vb == in-band valid-bit (cache-enabled)
+ * dc == DCA (Discrete Consumption Acknowledgment), DQRR-only
+ * As for "enum qm_dqrr_dmode", it should be self-explanatory.
+ */
+enum qm_eqcr_pmode { /* matches QCSP_CFG::EPM */
+ qm_eqcr_pci = 0, /* PI index, cache-inhibited */
+ qm_eqcr_pce = 1, /* PI index, cache-enabled */
+ qm_eqcr_pvb = 2 /* valid-bit */
+};
+enum qm_dqrr_dmode { /* matches QCSP_CFG::DP */
+ qm_dqrr_dpush = 0, /* SDQCR + VDQCR */
+ qm_dqrr_dpull = 1 /* PDQCR */
+};
+enum qm_dqrr_pmode { /* s/w-only */
+ qm_dqrr_pci, /* reads DQRR_PI_CINH */
+ qm_dqrr_pce, /* reads DQRR_PI_CENA */
+ qm_dqrr_pvb /* reads valid-bit */
+};
+enum qm_dqrr_cmode { /* matches QCSP_CFG::DCM */
+ qm_dqrr_cci = 0, /* CI index, cache-inhibited */
+ qm_dqrr_cce = 1, /* CI index, cache-enabled */
+ qm_dqrr_cdc = 2 /* Discrete Consumption Acknowledgment */
+};
+enum qm_mr_pmode { /* s/w-only */
+ qm_mr_pci, /* reads MR_PI_CINH */
+ qm_mr_pce, /* reads MR_PI_CENA */
+ qm_mr_pvb /* reads valid-bit */
+};
+enum qm_mr_cmode { /* matches QCSP_CFG::MM */
+ qm_mr_cci = 0, /* CI index, cache-inhibited */
+ qm_mr_cce = 1 /* CI index, cache-enabled */
+};
+
+/* --- Portal structures --- */
+
+#define QM_EQCR_SIZE 8
+#define QM_DQRR_SIZE 16
+#define QM_MR_SIZE 8
+
+/* "Enqueue Command" */
+struct qm_eqcr_entry {
+ u8 _ncw_verb; /* writes to this are non-coherent */
+ u8 dca;
+ u16 seqnum;
+ u32 orp; /* 24-bit */
+ u32 fqid; /* 24-bit */
+ u32 tag;
+ struct qm_fd fd;
+ u8 __reserved3[32];
+} __packed;
+#define QM_EQCR_VERB_VBIT 0x80
+#define QM_EQCR_VERB_CMD_MASK 0x61 /* but only one value; */
+#define QM_EQCR_VERB_CMD_ENQUEUE 0x01
+#define QM_EQCR_SEQNUM_NESN 0x8000 /* Advance NESN */
+#define QM_EQCR_SEQNUM_NLIS 0x4000 /* More fragments to come */
+#define QM_EQCR_SEQNUM_SEQMASK 0x3fff /* sequence number goes here */
+
+struct qm_eqcr {
+ struct qm_eqcr_entry *ring, *cursor;
+ u8 ci, available, ithresh, vbit;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ u32 busy;
+ enum qm_eqcr_pmode pmode;
+#endif
+};
+
+struct qm_dqrr {
+ const struct qm_dqrr_entry *ring, *cursor;
+ u8 pi, ci, fill, ithresh, vbit;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ enum qm_dqrr_dmode dmode;
+ enum qm_dqrr_pmode pmode;
+ enum qm_dqrr_cmode cmode;
+#endif
+};
+
+struct qm_mr {
+ union qm_mr_entry *ring, *cursor;
+ u8 pi, ci, fill, ithresh, vbit;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ enum qm_mr_pmode pmode;
+ enum qm_mr_cmode cmode;
+#endif
+};
+
+/* MC (Management Command) command */
+/* "Query FQ" */
+struct qm_mcc_queryfq {
+ u8 _ncw_verb;
+ u8 __reserved1[3];
+ u32 fqid; /* 24-bit */
+ u8 __reserved2[56];
+} __packed;
+/* "Alter FQ State Commands " */
+struct qm_mcc_alterfq {
+ u8 _ncw_verb;
+ u8 __reserved1[3];
+ u32 fqid; /* 24-bit */
+ u8 __reserved2;
+ u8 count; /* number of consecutive FQID */
+ u8 __reserved3[10];
+ u32 context_b; /* frame queue context b */
+ u8 __reserved4[40];
+} __packed;
+
+/* "Query CGR" */
+struct qm_mcc_querycgr {
+ u8 _ncw_verb;
+ u8 __reserved1[30];
+ u8 cgid;
+ u8 __reserved2[32];
+};
+
+struct qm_mcc_querywq {
+ u8 _ncw_verb;
+ u8 __reserved;
+ /* select channel if verb != QUERYWQ_DEDICATED */
+ u16 channel_wq; /* ignores wq (3 lsbits): _res[0-2] */
+ u8 __reserved2[60];
+} __packed;
+
+#define QM_MCC_VERB_VBIT 0x80
+#define QM_MCC_VERB_MASK 0x7f /* where the verb contains; */
+#define QM_MCC_VERB_INITFQ_PARKED 0x40
+#define QM_MCC_VERB_INITFQ_SCHED 0x41
+#define QM_MCC_VERB_QUERYFQ 0x44
+#define QM_MCC_VERB_QUERYFQ_NP 0x45 /* "non-programmable" fields */
+#define QM_MCC_VERB_QUERYWQ 0x46
+#define QM_MCC_VERB_QUERYWQ_DEDICATED 0x47
+#define QM_MCC_VERB_ALTER_SCHED 0x48 /* Schedule FQ */
+#define QM_MCC_VERB_ALTER_FE 0x49 /* Force Eligible FQ */
+#define QM_MCC_VERB_ALTER_RETIRE 0x4a /* Retire FQ */
+#define QM_MCC_VERB_ALTER_OOS 0x4b /* Take FQ out of service */
+#define QM_MCC_VERB_ALTER_FQXON 0x4d /* FQ XON */
+#define QM_MCC_VERB_ALTER_FQXOFF 0x4e /* FQ XOFF */
+#define QM_MCC_VERB_INITCGR 0x50
+#define QM_MCC_VERB_MODIFYCGR 0x51
+#define QM_MCC_VERB_CGRTESTWRITE 0x52
+#define QM_MCC_VERB_QUERYCGR 0x58
+#define QM_MCC_VERB_QUERYCONGESTION 0x59
+union qm_mc_command {
+ struct {
+ u8 _ncw_verb; /* writes to this are non-coherent */
+ u8 __reserved[63];
+ };
+ struct qm_mcc_initfq initfq;
+ struct qm_mcc_queryfq queryfq;
+ struct qm_mcc_alterfq alterfq;
+ struct qm_mcc_initcgr initcgr;
+ struct qm_mcc_querycgr querycgr;
+ struct qm_mcc_querywq querywq;
+ struct qm_mcc_queryfq_np queryfq_np;
+};
+
+/* MC (Management Command) result */
+/* "Query FQ" */
+struct qm_mcr_queryfq {
+ u8 verb;
+ u8 result;
+ u8 __reserved1[8];
+ struct qm_fqd fqd; /* the FQD fields are here */
+ u8 __reserved2[30];
+} __packed;
+
+/* "Alter FQ State Commands" */
+struct qm_mcr_alterfq {
+ u8 verb;
+ u8 result;
+ u8 fqs; /* Frame Queue Status */
+ u8 __reserved1[61];
+};
+#define QM_MCR_VERB_RRID 0x80
+#define QM_MCR_VERB_MASK QM_MCC_VERB_MASK
+#define QM_MCR_VERB_INITFQ_PARKED QM_MCC_VERB_INITFQ_PARKED
+#define QM_MCR_VERB_INITFQ_SCHED QM_MCC_VERB_INITFQ_SCHED
+#define QM_MCR_VERB_QUERYFQ QM_MCC_VERB_QUERYFQ
+#define QM_MCR_VERB_QUERYFQ_NP QM_MCC_VERB_QUERYFQ_NP
+#define QM_MCR_VERB_QUERYWQ QM_MCC_VERB_QUERYWQ
+#define QM_MCR_VERB_QUERYWQ_DEDICATED QM_MCC_VERB_QUERYWQ_DEDICATED
+#define QM_MCR_VERB_ALTER_SCHED QM_MCC_VERB_ALTER_SCHED
+#define QM_MCR_VERB_ALTER_FE QM_MCC_VERB_ALTER_FE
+#define QM_MCR_VERB_ALTER_RETIRE QM_MCC_VERB_ALTER_RETIRE
+#define QM_MCR_VERB_ALTER_OOS QM_MCC_VERB_ALTER_OOS
+#define QM_MCR_RESULT_NULL 0x00
+#define QM_MCR_RESULT_OK 0xf0
+#define QM_MCR_RESULT_ERR_FQID 0xf1
+#define QM_MCR_RESULT_ERR_FQSTATE 0xf2
+#define QM_MCR_RESULT_ERR_NOTEMPTY 0xf3 /* OOS fails if FQ is !empty */
+#define QM_MCR_RESULT_ERR_BADCHANNEL 0xf4
+#define QM_MCR_RESULT_PENDING 0xf8
+#define QM_MCR_RESULT_ERR_BADCOMMAND 0xff
+#define QM_MCR_FQS_ORLPRESENT 0x02 /* ORL fragments to come */
+#define QM_MCR_FQS_NOTEMPTY 0x01 /* FQ has enqueued frames */
+#define QM_MCR_TIMEOUT 10000 /* us */
+union qm_mc_result {
+ struct {
+ u8 verb;
+ u8 result;
+ u8 __reserved1[62];
+ };
+ struct qm_mcr_queryfq queryfq;
+ struct qm_mcr_alterfq alterfq;
+ struct qm_mcr_querycgr querycgr;
+ struct qm_mcr_querycongestion querycongestion;
+ struct qm_mcr_querywq querywq;
+ struct qm_mcr_queryfq_np queryfq_np;
+};
+
+struct qm_mc {
+ union qm_mc_command *cr;
+ union qm_mc_result *rr;
+ u8 rridx, vbit;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ enum {
+ /* Can be _mc_start()ed */
+ qman_mc_idle,
+ /* Can be _mc_commit()ed or _mc_abort()ed */
+ qman_mc_user,
+ /* Can only be _mc_retry()ed */
+ qman_mc_hw
+ } state;
+#endif
+};
+
+struct qm_addr {
+ void __iomem *ce; /* cache-enabled */
+ void __iomem *ci; /* cache-inhibited */
+};
+
+struct qm_portal {
+ /*
+ * In the non-CONFIG_FSL_DPAA_CHECKING case, the following stuff up to
+ * and including 'mc' fits within a cacheline (yay!). The 'config' part
+ * is setup-only, so isn't a cause for a concern. In other words, don't
+ * rearrange this structure on a whim, there be dragons ...
+ */
+ struct qm_addr addr;
+ struct qm_eqcr eqcr;
+ struct qm_dqrr dqrr;
+ struct qm_mr mr;
+ struct qm_mc mc;
+} ____cacheline_aligned;
+
+/* Cache-inhibited register access. */
+static inline u32 qm_in(struct qm_portal *p, u32 offset)
+{
+ return __raw_readl(p->addr.ci + offset);
+}
+
+static inline void qm_out(struct qm_portal *p, u32 offset, u32 val)
+{
+ __raw_writel(val, p->addr.ci + offset);
+}
+
+/* Cache Enabled Portal Access */
+static inline void qm_cl_invalidate(struct qm_portal *p, u32 offset)
+{
+ dpaa_invalidate(p->addr.ce + offset);
+}
+
+static inline void qm_cl_touch_ro(struct qm_portal *p, u32 offset)
+{
+ dpaa_touch_ro(p->addr.ce + offset);
+}
+
+static inline u32 qm_ce_in(struct qm_portal *p, u32 offset)
+{
+ return __raw_readl(p->addr.ce + offset);
+}
+
+/* --- EQCR API --- */
+
+#define EQCR_SHIFT ilog2(sizeof(struct qm_eqcr_entry))
+#define EQCR_CARRY (uintptr_t)(QM_EQCR_SIZE << EQCR_SHIFT)
+
+/* Bit-wise logic to wrap a ring pointer by clearing the "carry bit" */
+static struct qm_eqcr_entry *eqcr_carryclear(struct qm_eqcr_entry *p)
+{
+ uintptr_t addr = (uintptr_t)p;
+
+ addr &= ~EQCR_CARRY;
+
+ return (struct qm_eqcr_entry *)addr;
+}
+
+/* Bit-wise logic to convert a ring pointer to a ring index */
+static int eqcr_ptr2idx(struct qm_eqcr_entry *e)
+{
+ return ((uintptr_t)e >> EQCR_SHIFT) & (QM_EQCR_SIZE - 1);
+}
+
+/* Increment the 'cursor' ring pointer, taking 'vbit' into account */
+static inline void eqcr_inc(struct qm_eqcr *eqcr)
+{
+ /* increment to the next EQCR pointer and handle overflow and 'vbit' */
+ struct qm_eqcr_entry *partial = eqcr->cursor + 1;
+
+ eqcr->cursor = eqcr_carryclear(partial);
+ if (partial != eqcr->cursor)
+ eqcr->vbit ^= QM_EQCR_VERB_VBIT;
+}
+
+static inline int qm_eqcr_init(struct qm_portal *portal,
+ enum qm_eqcr_pmode pmode,
+ unsigned int eq_stash_thresh,
+ int eq_stash_prio)
+{
+ struct qm_eqcr *eqcr = &portal->eqcr;
+ u32 cfg;
+ u8 pi;
+
+ eqcr->ring = portal->addr.ce + QM_CL_EQCR;
+ eqcr->ci = qm_in(portal, QM_REG_EQCR_CI_CINH) & (QM_EQCR_SIZE - 1);
+ qm_cl_invalidate(portal, QM_CL_EQCR_CI_CENA);
+ pi = qm_in(portal, QM_REG_EQCR_PI_CINH) & (QM_EQCR_SIZE - 1);
+ eqcr->cursor = eqcr->ring + pi;
+ eqcr->vbit = (qm_in(portal, QM_REG_EQCR_PI_CINH) & QM_EQCR_SIZE) ?
+ QM_EQCR_VERB_VBIT : 0;
+ eqcr->available = QM_EQCR_SIZE - 1 -
+ dpaa_cyc_diff(QM_EQCR_SIZE, eqcr->ci, pi);
+ eqcr->ithresh = qm_in(portal, QM_REG_EQCR_ITR);
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ eqcr->busy = 0;
+ eqcr->pmode = pmode;
+#endif
+ cfg = (qm_in(portal, QM_REG_CFG) & 0x00ffffff) |
+ (eq_stash_thresh << 28) | /* QCSP_CFG: EST */
+ (eq_stash_prio << 26) | /* QCSP_CFG: EP */
+ ((pmode & 0x3) << 24); /* QCSP_CFG::EPM */
+ qm_out(portal, QM_REG_CFG, cfg);
+ return 0;
+}
+
+static inline unsigned int qm_eqcr_get_ci_stashing(struct qm_portal *portal)
+{
+ return (qm_in(portal, QM_REG_CFG) >> 28) & 0x7;
+}
+
+static inline void qm_eqcr_finish(struct qm_portal *portal)
+{
+ struct qm_eqcr *eqcr = &portal->eqcr;
+ u8 pi = qm_in(portal, QM_REG_EQCR_PI_CINH) & (QM_EQCR_SIZE - 1);
+ u8 ci = qm_in(portal, QM_REG_EQCR_CI_CINH) & (QM_EQCR_SIZE - 1);
+
+ DPAA_ASSERT(!eqcr->busy);
+ if (pi != eqcr_ptr2idx(eqcr->cursor))
+ pr_crit("losing uncommited EQCR entries\n");
+ if (ci != eqcr->ci)
+ pr_crit("missing existing EQCR completions\n");
+ if (eqcr->ci != eqcr_ptr2idx(eqcr->cursor))
+ pr_crit("EQCR destroyed unquiesced\n");
+}
+
+static inline struct qm_eqcr_entry *qm_eqcr_start_no_stash(struct qm_portal
+ *portal)
+{
+ struct qm_eqcr *eqcr = &portal->eqcr;
+
+ DPAA_ASSERT(!eqcr->busy);
+ if (!eqcr->available)
+ return NULL;
+
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ eqcr->busy = 1;
+#endif
+ dpaa_zero(eqcr->cursor);
+ return eqcr->cursor;
+}
+
+static inline struct qm_eqcr_entry *qm_eqcr_start_stash(struct qm_portal
+ *portal)
+{
+ struct qm_eqcr *eqcr = &portal->eqcr;
+ u8 diff, old_ci;
+
+ DPAA_ASSERT(!eqcr->busy);
+ if (!eqcr->available) {
+ old_ci = eqcr->ci;
+ eqcr->ci = qm_ce_in(portal, QM_CL_EQCR_CI_CENA) &
+ (QM_EQCR_SIZE - 1);
+ diff = dpaa_cyc_diff(QM_EQCR_SIZE, old_ci, eqcr->ci);
+ eqcr->available += diff;
+ if (!diff)
+ return NULL;
+ }
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ eqcr->busy = 1;
+#endif
+ dpaa_zero(eqcr->cursor);
+ return eqcr->cursor;
+}
+
+static inline void eqcr_commit_checks(struct qm_eqcr *eqcr)
+{
+ DPAA_ASSERT(eqcr->busy);
+ DPAA_ASSERT(eqcr->cursor->orp == (eqcr->cursor->orp & 0x00ffffff));
+ DPAA_ASSERT(eqcr->cursor->fqid == (eqcr->cursor->fqid & 0x00ffffff));
+ DPAA_ASSERT(eqcr->available >= 1);
+}
+
+static inline void qm_eqcr_pvb_commit(struct qm_portal *portal, u8 myverb)
+{
+ struct qm_eqcr *eqcr = &portal->eqcr;
+ struct qm_eqcr_entry *eqcursor;
+
+ eqcr_commit_checks(eqcr);
+ DPAA_ASSERT(eqcr->pmode == qm_eqcr_pvb);
+ dma_wmb();
+ eqcursor = eqcr->cursor;
+ eqcursor->_ncw_verb = myverb | eqcr->vbit;
+ dpaa_flush(eqcursor);
+ eqcr_inc(eqcr);
+ eqcr->available--;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ eqcr->busy = 0;
+#endif
+}
+
+static inline void qm_eqcr_cce_prefetch(struct qm_portal *portal)
+{
+ qm_cl_touch_ro(portal, QM_CL_EQCR_CI_CENA);
+}
+
+static inline u8 qm_eqcr_cce_update(struct qm_portal *portal)
+{
+ struct qm_eqcr *eqcr = &portal->eqcr;
+ u8 diff, old_ci = eqcr->ci;
+
+ eqcr->ci = qm_ce_in(portal, QM_CL_EQCR_CI_CENA) & (QM_EQCR_SIZE - 1);
+ qm_cl_invalidate(portal, QM_CL_EQCR_CI_CENA);
+ diff = dpaa_cyc_diff(QM_EQCR_SIZE, old_ci, eqcr->ci);
+ eqcr->available += diff;
+ return diff;
+}
+
+static inline void qm_eqcr_set_ithresh(struct qm_portal *portal, u8 ithresh)
+{
+ struct qm_eqcr *eqcr = &portal->eqcr;
+
+ eqcr->ithresh = ithresh;
+ qm_out(portal, QM_REG_EQCR_ITR, ithresh);
+}
+
+static inline u8 qm_eqcr_get_avail(struct qm_portal *portal)
+{
+ struct qm_eqcr *eqcr = &portal->eqcr;
+
+ return eqcr->available;
+}
+
+static inline u8 qm_eqcr_get_fill(struct qm_portal *portal)
+{
+ struct qm_eqcr *eqcr = &portal->eqcr;
+
+ return QM_EQCR_SIZE - 1 - eqcr->available;
+}
+
+/* --- DQRR API --- */
+
+#define DQRR_SHIFT ilog2(sizeof(struct qm_dqrr_entry))
+#define DQRR_CARRY (uintptr_t)(QM_DQRR_SIZE << DQRR_SHIFT)
+
+static const struct qm_dqrr_entry *dqrr_carryclear(
+ const struct qm_dqrr_entry *p)
+{
+ uintptr_t addr = (uintptr_t)p;
+
+ addr &= ~DQRR_CARRY;
+
+ return (const struct qm_dqrr_entry *)addr;
+}
+
+static inline int dqrr_ptr2idx(const struct qm_dqrr_entry *e)
+{
+ return ((uintptr_t)e >> DQRR_SHIFT) & (QM_DQRR_SIZE - 1);
+}
+
+static const struct qm_dqrr_entry *dqrr_inc(const struct qm_dqrr_entry *e)
+{
+ return dqrr_carryclear(e + 1);
+}
+
+static inline void qm_dqrr_set_maxfill(struct qm_portal *portal, u8 mf)
+{
+ qm_out(portal, QM_REG_CFG, (qm_in(portal, QM_REG_CFG) & 0xff0fffff) |
+ ((mf & (QM_DQRR_SIZE - 1)) << 20));
+}
+
+static inline int qm_dqrr_init(struct qm_portal *portal,
+ const struct qm_portal_config *config,
+ enum qm_dqrr_dmode dmode,
+ enum qm_dqrr_pmode pmode,
+ enum qm_dqrr_cmode cmode, u8 max_fill)
+{
+ struct qm_dqrr *dqrr = &portal->dqrr;
+ u32 cfg;
+
+ /* Make sure the DQRR will be idle when we enable */
+ qm_out(portal, QM_REG_DQRR_SDQCR, 0);
+ qm_out(portal, QM_REG_DQRR_VDQCR, 0);
+ qm_out(portal, QM_REG_DQRR_PDQCR, 0);
+ dqrr->ring = portal->addr.ce + QM_CL_DQRR;
+ dqrr->pi = qm_in(portal, QM_REG_DQRR_PI_CINH) & (QM_DQRR_SIZE - 1);
+ dqrr->ci = qm_in(portal, QM_REG_DQRR_CI_CINH) & (QM_DQRR_SIZE - 1);
+ dqrr->cursor = dqrr->ring + dqrr->ci;
+ dqrr->fill = dpaa_cyc_diff(QM_DQRR_SIZE, dqrr->ci, dqrr->pi);
+ dqrr->vbit = (qm_in(portal, QM_REG_DQRR_PI_CINH) & QM_DQRR_SIZE) ?
+ QM_DQRR_VERB_VBIT : 0;
+ dqrr->ithresh = qm_in(portal, QM_REG_DQRR_ITR);
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ dqrr->dmode = dmode;
+ dqrr->pmode = pmode;
+ dqrr->cmode = cmode;
+#endif
+ /* Invalidate every ring entry before beginning */
+ for (cfg = 0; cfg < QM_DQRR_SIZE; cfg++)
+ dpaa_invalidate(qm_cl(dqrr->ring, cfg));
+ cfg = (qm_in(portal, QM_REG_CFG) & 0xff000f00) |
+ ((max_fill & (QM_DQRR_SIZE - 1)) << 20) | /* DQRR_MF */
+ ((dmode & 1) << 18) | /* DP */
+ ((cmode & 3) << 16) | /* DCM */
+ 0xa0 | /* RE+SE */
+ (0 ? 0x40 : 0) | /* Ignore RP */
+ (0 ? 0x10 : 0); /* Ignore SP */
+ qm_out(portal, QM_REG_CFG, cfg);
+ qm_dqrr_set_maxfill(portal, max_fill);
+ return 0;
+}
+
+static inline void qm_dqrr_finish(struct qm_portal *portal)
+{
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ struct qm_dqrr *dqrr = &portal->dqrr;
+
+ if (dqrr->cmode != qm_dqrr_cdc &&
+ dqrr->ci != dqrr_ptr2idx(dqrr->cursor))
+ pr_crit("Ignoring completed DQRR entries\n");
+#endif
+}
+
+static inline const struct qm_dqrr_entry *qm_dqrr_current(
+ struct qm_portal *portal)
+{
+ struct qm_dqrr *dqrr = &portal->dqrr;
+
+ if (!dqrr->fill)
+ return NULL;
+ return dqrr->cursor;
+}
+
+static inline u8 qm_dqrr_next(struct qm_portal *portal)
+{
+ struct qm_dqrr *dqrr = &portal->dqrr;
+
+ DPAA_ASSERT(dqrr->fill);
+ dqrr->cursor = dqrr_inc(dqrr->cursor);
+ return --dqrr->fill;
+}
+
+static inline void qm_dqrr_pvb_update(struct qm_portal *portal)
+{
+ struct qm_dqrr *dqrr = &portal->dqrr;
+ struct qm_dqrr_entry *res = qm_cl(dqrr->ring, dqrr->pi);
+
+ DPAA_ASSERT(dqrr->pmode == qm_dqrr_pvb);
+#ifndef CONFIG_FSL_PAMU
+ /*
+ * If PAMU is not available we need to invalidate the cache.
+ * When PAMU is available the cache is updated by stash
+ */
+ dpaa_invalidate_touch_ro(res);
+#endif
+ /*
+ * when accessing 'verb', use __raw_readb() to ensure that compiler
+ * inlining doesn't try to optimise out "excess reads".
+ */
+ if ((__raw_readb(&res->verb) & QM_DQRR_VERB_VBIT) == dqrr->vbit) {
+ dqrr->pi = (dqrr->pi + 1) & (QM_DQRR_SIZE - 1);
+ if (!dqrr->pi)
+ dqrr->vbit ^= QM_DQRR_VERB_VBIT;
+ dqrr->fill++;
+ }
+}
+
+static inline void qm_dqrr_cdc_consume_1ptr(struct qm_portal *portal,
+ const struct qm_dqrr_entry *dq,
+ int park)
+{
+ __maybe_unused struct qm_dqrr *dqrr = &portal->dqrr;
+ int idx = dqrr_ptr2idx(dq);
+
+ DPAA_ASSERT(dqrr->cmode == qm_dqrr_cdc);
+ DPAA_ASSERT((dqrr->ring + idx) == dq);
+ DPAA_ASSERT(idx < QM_DQRR_SIZE);
+ qm_out(portal, QM_REG_DQRR_DCAP, (0 << 8) | /* DQRR_DCAP::S */
+ ((park ? 1 : 0) << 6) | /* DQRR_DCAP::PK */
+ idx); /* DQRR_DCAP::DCAP_CI */
+}
+
+static inline void qm_dqrr_cdc_consume_n(struct qm_portal *portal, u32 bitmask)
+{
+ __maybe_unused struct qm_dqrr *dqrr = &portal->dqrr;
+
+ DPAA_ASSERT(dqrr->cmode == qm_dqrr_cdc);
+ qm_out(portal, QM_REG_DQRR_DCAP, (1 << 8) | /* DQRR_DCAP::S */
+ (bitmask << 16)); /* DQRR_DCAP::DCAP_CI */
+}
+
+static inline void qm_dqrr_sdqcr_set(struct qm_portal *portal, u32 sdqcr)
+{
+ qm_out(portal, QM_REG_DQRR_SDQCR, sdqcr);
+}
+
+static inline void qm_dqrr_vdqcr_set(struct qm_portal *portal, u32 vdqcr)
+{
+ qm_out(portal, QM_REG_DQRR_VDQCR, vdqcr);
+}
+
+static inline void qm_dqrr_set_ithresh(struct qm_portal *portal, u8 ithresh)
+{
+ qm_out(portal, QM_REG_DQRR_ITR, ithresh);
+}
+
+/* --- MR API --- */
+
+#define MR_SHIFT ilog2(sizeof(union qm_mr_entry))
+#define MR_CARRY (uintptr_t)(QM_MR_SIZE << MR_SHIFT)
+
+static union qm_mr_entry *mr_carryclear(union qm_mr_entry *p)
+{
+ uintptr_t addr = (uintptr_t)p;
+
+ addr &= ~MR_CARRY;
+
+ return (union qm_mr_entry *)addr;
+}
+
+static inline int mr_ptr2idx(const union qm_mr_entry *e)
+{
+ return ((uintptr_t)e >> MR_SHIFT) & (QM_MR_SIZE - 1);
+}
+
+static inline union qm_mr_entry *mr_inc(union qm_mr_entry *e)
+{
+ return mr_carryclear(e + 1);
+}
+
+static inline int qm_mr_init(struct qm_portal *portal, enum qm_mr_pmode pmode,
+ enum qm_mr_cmode cmode)
+{
+ struct qm_mr *mr = &portal->mr;
+ u32 cfg;
+
+ mr->ring = portal->addr.ce + QM_CL_MR;
+ mr->pi = qm_in(portal, QM_REG_MR_PI_CINH) & (QM_MR_SIZE - 1);
+ mr->ci = qm_in(portal, QM_REG_MR_CI_CINH) & (QM_MR_SIZE - 1);
+ mr->cursor = mr->ring + mr->ci;
+ mr->fill = dpaa_cyc_diff(QM_MR_SIZE, mr->ci, mr->pi);
+ mr->vbit = (qm_in(portal, QM_REG_MR_PI_CINH) & QM_MR_SIZE)
+ ? QM_MR_VERB_VBIT : 0;
+ mr->ithresh = qm_in(portal, QM_REG_MR_ITR);
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ mr->pmode = pmode;
+ mr->cmode = cmode;
+#endif
+ cfg = (qm_in(portal, QM_REG_CFG) & 0xfffff0ff) |
+ ((cmode & 1) << 8); /* QCSP_CFG:MM */
+ qm_out(portal, QM_REG_CFG, cfg);
+ return 0;
+}
+
+static inline void qm_mr_finish(struct qm_portal *portal)
+{
+ struct qm_mr *mr = &portal->mr;
+
+ if (mr->ci != mr_ptr2idx(mr->cursor))
+ pr_crit("Ignoring completed MR entries\n");
+}
+
+static inline const union qm_mr_entry *qm_mr_current(struct qm_portal *portal)
+{
+ struct qm_mr *mr = &portal->mr;
+
+ if (!mr->fill)
+ return NULL;
+ return mr->cursor;
+}
+
+static inline int qm_mr_next(struct qm_portal *portal)
+{
+ struct qm_mr *mr = &portal->mr;
+
+ DPAA_ASSERT(mr->fill);
+ mr->cursor = mr_inc(mr->cursor);
+ return --mr->fill;
+}
+
+static inline void qm_mr_pvb_update(struct qm_portal *portal)
+{
+ struct qm_mr *mr = &portal->mr;
+ union qm_mr_entry *res = qm_cl(mr->ring, mr->pi);
+
+ DPAA_ASSERT(mr->pmode == qm_mr_pvb);
+ /*
+ * when accessing 'verb', use __raw_readb() to ensure that compiler
+ * inlining doesn't try to optimise out "excess reads".
+ */
+ if ((__raw_readb(&res->verb) & QM_MR_VERB_VBIT) == mr->vbit) {
+ mr->pi = (mr->pi + 1) & (QM_MR_SIZE - 1);
+ if (!mr->pi)
+ mr->vbit ^= QM_MR_VERB_VBIT;
+ mr->fill++;
+ res = mr_inc(res);
+ }
+ dpaa_invalidate_touch_ro(res);
+}
+
+static inline void qm_mr_cci_consume(struct qm_portal *portal, u8 num)
+{
+ struct qm_mr *mr = &portal->mr;
+
+ DPAA_ASSERT(mr->cmode == qm_mr_cci);
+ mr->ci = (mr->ci + num) & (QM_MR_SIZE - 1);
+ qm_out(portal, QM_REG_MR_CI_CINH, mr->ci);
+}
+
+static inline void qm_mr_cci_consume_to_current(struct qm_portal *portal)
+{
+ struct qm_mr *mr = &portal->mr;
+
+ DPAA_ASSERT(mr->cmode == qm_mr_cci);
+ mr->ci = mr_ptr2idx(mr->cursor);
+ qm_out(portal, QM_REG_MR_CI_CINH, mr->ci);
+}
+
+static inline void qm_mr_set_ithresh(struct qm_portal *portal, u8 ithresh)
+{
+ qm_out(portal, QM_REG_MR_ITR, ithresh);
+}
+
+/* --- Management command API --- */
+
+static inline int qm_mc_init(struct qm_portal *portal)
+{
+ struct qm_mc *mc = &portal->mc;
+
+ mc->cr = portal->addr.ce + QM_CL_CR;
+ mc->rr = portal->addr.ce + QM_CL_RR0;
+ mc->rridx = (__raw_readb(&mc->cr->_ncw_verb) & QM_MCC_VERB_VBIT)
+ ? 0 : 1;
+ mc->vbit = mc->rridx ? QM_MCC_VERB_VBIT : 0;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ mc->state = qman_mc_idle;
+#endif
+ return 0;
+}
+
+static inline void qm_mc_finish(struct qm_portal *portal)
+{
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ struct qm_mc *mc = &portal->mc;
+
+ DPAA_ASSERT(mc->state == qman_mc_idle);
+ if (mc->state != qman_mc_idle)
+ pr_crit("Losing incomplete MC command\n");
+#endif
+}
+
+static inline union qm_mc_command *qm_mc_start(struct qm_portal *portal)
+{
+ struct qm_mc *mc = &portal->mc;
+
+ DPAA_ASSERT(mc->state == qman_mc_idle);
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ mc->state = qman_mc_user;
+#endif
+ dpaa_zero(mc->cr);
+ return mc->cr;
+}
+
+static inline void qm_mc_commit(struct qm_portal *portal, u8 myverb)
+{
+ struct qm_mc *mc = &portal->mc;
+ union qm_mc_result *rr = mc->rr + mc->rridx;
+
+ DPAA_ASSERT(mc->state == qman_mc_user);
+ dma_wmb();
+ mc->cr->_ncw_verb = myverb | mc->vbit;
+ dpaa_flush(mc->cr);
+ dpaa_invalidate_touch_ro(rr);
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ mc->state = qman_mc_hw;
+#endif
+}
+
+static inline union qm_mc_result *qm_mc_result(struct qm_portal *portal)
+{
+ struct qm_mc *mc = &portal->mc;
+ union qm_mc_result *rr = mc->rr + mc->rridx;
+
+ DPAA_ASSERT(mc->state == qman_mc_hw);
+ /*
+ * The inactive response register's verb byte always returns zero until
+ * its command is submitted and completed. This includes the valid-bit,
+ * in case you were wondering...
+ */
+ if (!__raw_readb(&rr->verb)) {
+ dpaa_invalidate_touch_ro(rr);
+ return NULL;
+ }
+ mc->rridx ^= 1;
+ mc->vbit ^= QM_MCC_VERB_VBIT;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ mc->state = qman_mc_idle;
+#endif
+ return rr;
+}
+
+static inline int qm_mc_result_timeout(struct qm_portal *portal,
+ union qm_mc_result **mcr)
+{
+ int timeout = QM_MCR_TIMEOUT;
+
+ do {
+ *mcr = qm_mc_result(portal);
+ if (*mcr)
+ break;
+ udelay(1);
+ } while (--timeout);
+
+ return timeout;
+}
+
+static inline void fq_set(struct qman_fq *fq, u32 mask)
+{
+ set_bits(mask, &fq->flags);
+}
+
+static inline void fq_clear(struct qman_fq *fq, u32 mask)
+{
+ clear_bits(mask, &fq->flags);
+}
+
+static inline int fq_isset(struct qman_fq *fq, u32 mask)
+{
+ return fq->flags & mask;
+}
+
+static inline int fq_isclear(struct qman_fq *fq, u32 mask)
+{
+ return !(fq->flags & mask);
+}
+
+struct qman_portal {
+ struct qm_portal p;
+ /* PORTAL_BITS_*** - dynamic, strictly internal */
+ unsigned long bits;
+ /* interrupt sources processed by portal_isr(), configurable */
+ unsigned long irq_sources;
+ u32 use_eqcr_ci_stashing;
+ /* only 1 volatile dequeue at a time */
+ struct qman_fq *vdqcr_owned;
+ u32 sdqcr;
+ /* probing time config params for cpu-affine portals */
+ const struct qm_portal_config *config;
+ /* needed for providing a non-NULL device to dma_map_***() */
+ struct platform_device *pdev;
+ /* 2-element array. cgrs[0] is mask, cgrs[1] is snapshot. */
+ struct qman_cgrs *cgrs;
+ /* linked-list of CSCN handlers. */
+ struct list_head cgr_cbs;
+ /* list lock */
+ spinlock_t cgr_lock;
+ struct work_struct congestion_work;
+ struct work_struct mr_work;
+ char irqname[MAX_IRQNAME];
+};
+
+static cpumask_t affine_mask;
+static DEFINE_SPINLOCK(affine_mask_lock);
+static u16 affine_channels[NR_CPUS];
+static DEFINE_PER_CPU(struct qman_portal, qman_affine_portal);
+struct qman_portal *affine_portals[NR_CPUS];
+
+static inline struct qman_portal *get_affine_portal(void)
+{
+ return &get_cpu_var(qman_affine_portal);
+}
+
+static inline void put_affine_portal(void)
+{
+ put_cpu_var(qman_affine_portal);
+}
+
+static struct workqueue_struct *qm_portal_wq;
+
+int qman_wq_alloc(void)
+{
+ qm_portal_wq = alloc_workqueue("qman_portal_wq", 0, 1);
+ if (!qm_portal_wq)
+ return -ENOMEM;
+ return 0;
+}
+
+/*
+ * This is what everything can wait on, even if it migrates to a different cpu
+ * to the one whose affine portal it is waiting on.
+ */
+static DECLARE_WAIT_QUEUE_HEAD(affine_queue);
+
+static struct qman_fq **fq_table;
+static u32 num_fqids;
+
+int qman_alloc_fq_table(u32 _num_fqids)
+{
+ num_fqids = _num_fqids;
+
+ fq_table = vzalloc(num_fqids * 2 * sizeof(struct qman_fq *));
+ if (!fq_table)
+ return -ENOMEM;
+
+ pr_debug("Allocated fq lookup table at %p, entry count %u\n",
+ fq_table, num_fqids * 2);
+ return 0;
+}
+
+static struct qman_fq *idx_to_fq(u32 idx)
+{
+ struct qman_fq *fq;
+
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ if (WARN_ON(idx >= num_fqids * 2))
+ return NULL;
+#endif
+ fq = fq_table[idx];
+ DPAA_ASSERT(!fq || idx == fq->idx);
+
+ return fq;
+}
+
+/*
+ * Only returns full-service fq objects, not enqueue-only
+ * references (QMAN_FQ_FLAG_NO_MODIFY).
+ */
+static struct qman_fq *fqid_to_fq(u32 fqid)
+{
+ return idx_to_fq(fqid * 2);
+}
+
+static struct qman_fq *tag_to_fq(u32 tag)
+{
+#if BITS_PER_LONG == 64
+ return idx_to_fq(tag);
+#else
+ return (struct qman_fq *)tag;
+#endif
+}
+
+static u32 fq_to_tag(struct qman_fq *fq)
+{
+#if BITS_PER_LONG == 64
+ return fq->idx;
+#else
+ return (u32)fq;
+#endif
+}
+
+static u32 __poll_portal_slow(struct qman_portal *p, u32 is);
+static inline unsigned int __poll_portal_fast(struct qman_portal *p,
+ unsigned int poll_limit);
+static void qm_congestion_task(struct work_struct *work);
+static void qm_mr_process_task(struct work_struct *work);
+
+static irqreturn_t portal_isr(int irq, void *ptr)
+{
+ struct qman_portal *p = ptr;
+
+ u32 clear = QM_DQAVAIL_MASK | p->irq_sources;
+ u32 is = qm_in(&p->p, QM_REG_ISR) & p->irq_sources;
+
+ if (unlikely(!is))
+ return IRQ_NONE;
+
+ /* DQRR-handling if it's interrupt-driven */
+ if (is & QM_PIRQ_DQRI)
+ __poll_portal_fast(p, QMAN_POLL_LIMIT);
+ /* Handling of anything else that's interrupt-driven */
+ clear |= __poll_portal_slow(p, is);
+ qm_out(&p->p, QM_REG_ISR, clear);
+ return IRQ_HANDLED;
+}
+
+static int drain_mr_fqrni(struct qm_portal *p)
+{
+ const union qm_mr_entry *msg;
+loop:
+ msg = qm_mr_current(p);
+ if (!msg) {
+ /*
+ * if MR was full and h/w had other FQRNI entries to produce, we
+ * need to allow it time to produce those entries once the
+ * existing entries are consumed. A worst-case situation
+ * (fully-loaded system) means h/w sequencers may have to do 3-4
+ * other things before servicing the portal's MR pump, each of
+ * which (if slow) may take ~50 qman cycles (which is ~200
+ * processor cycles). So rounding up and then multiplying this
+ * worst-case estimate by a factor of 10, just to be
+ * ultra-paranoid, goes as high as 10,000 cycles. NB, we consume
+ * one entry at a time, so h/w has an opportunity to produce new
+ * entries well before the ring has been fully consumed, so
+ * we're being *really* paranoid here.
+ */
+ u64 now, then = jiffies;
+
+ do {
+ now = jiffies;
+ } while ((then + 10000) > now);
+ msg = qm_mr_current(p);
+ if (!msg)
+ return 0;
+ }
+ if ((msg->verb & QM_MR_VERB_TYPE_MASK) != QM_MR_VERB_FQRNI) {
+ /* We aren't draining anything but FQRNIs */
+ pr_err("Found verb 0x%x in MR\n", msg->verb);
+ return -1;
+ }
+ qm_mr_next(p);
+ qm_mr_cci_consume(p, 1);
+ goto loop;
+}
+
+static int qman_create_portal(struct qman_portal *portal,
+ const struct qm_portal_config *c,
+ const struct qman_cgrs *cgrs)
+{
+ struct qm_portal *p;
+ char buf[16];
+ int ret;
+ u32 isdr;
+
+ p = &portal->p;
+
+#ifdef CONFIG_FSL_PAMU
+ /* PAMU is required for stashing */
+ portal->use_eqcr_ci_stashing = ((qman_ip_rev >= QMAN_REV30) ? 1 : 0);
+#else
+ portal->use_eqcr_ci_stashing = 0;
+#endif
+ /*
+ * prep the low-level portal struct with the mapped addresses from the
+ * config, everything that follows depends on it and "config" is more
+ * for (de)reference
+ */
+ p->addr.ce = c->addr_virt[DPAA_PORTAL_CE];
+ p->addr.ci = c->addr_virt[DPAA_PORTAL_CI];
+ /*
+ * If CI-stashing is used, the current defaults use a threshold of 3,
+ * and stash with high-than-DQRR priority.
+ */
+ if (qm_eqcr_init(p, qm_eqcr_pvb,
+ portal->use_eqcr_ci_stashing ? 3 : 0, 1)) {
+ dev_err(c->dev, "EQCR initialisation failed\n");
+ goto fail_eqcr;
+ }
+ if (qm_dqrr_init(p, c, qm_dqrr_dpush, qm_dqrr_pvb,
+ qm_dqrr_cdc, DQRR_MAXFILL)) {
+ dev_err(c->dev, "DQRR initialisation failed\n");
+ goto fail_dqrr;
+ }
+ if (qm_mr_init(p, qm_mr_pvb, qm_mr_cci)) {
+ dev_err(c->dev, "MR initialisation failed\n");
+ goto fail_mr;
+ }
+ if (qm_mc_init(p)) {
+ dev_err(c->dev, "MC initialisation failed\n");
+ goto fail_mc;
+ }
+ /* static interrupt-gating controls */
+ qm_dqrr_set_ithresh(p, QMAN_PIRQ_DQRR_ITHRESH);
+ qm_mr_set_ithresh(p, QMAN_PIRQ_MR_ITHRESH);
+ qm_out(p, QM_REG_ITPR, QMAN_PIRQ_IPERIOD);
+ portal->cgrs = kmalloc(2 * sizeof(*cgrs), GFP_KERNEL);
+ if (!portal->cgrs)
+ goto fail_cgrs;
+ /* initial snapshot is no-depletion */
+ qman_cgrs_init(&portal->cgrs[1]);
+ if (cgrs)
+ portal->cgrs[0] = *cgrs;
+ else
+ /* if the given mask is NULL, assume all CGRs can be seen */
+ qman_cgrs_fill(&portal->cgrs[0]);
+ INIT_LIST_HEAD(&portal->cgr_cbs);
+ spin_lock_init(&portal->cgr_lock);
+ INIT_WORK(&portal->congestion_work, qm_congestion_task);
+ INIT_WORK(&portal->mr_work, qm_mr_process_task);
+ portal->bits = 0;
+ portal->sdqcr = QM_SDQCR_SOURCE_CHANNELS | QM_SDQCR_COUNT_UPTO3 |
+ QM_SDQCR_DEDICATED_PRECEDENCE | QM_SDQCR_TYPE_PRIO_QOS |
+ QM_SDQCR_TOKEN_SET(0xab) | QM_SDQCR_CHANNELS_DEDICATED;
+ sprintf(buf, "qportal-%d", c->channel);
+ portal->pdev = platform_device_alloc(buf, -1);
+ if (!portal->pdev)
+ goto fail_devalloc;
+ if (dma_set_mask(&portal->pdev->dev, DMA_BIT_MASK(40)))
+ goto fail_devadd;
+ ret = platform_device_add(portal->pdev);
+ if (ret)
+ goto fail_devadd;
+ isdr = 0xffffffff;
+ qm_out(p, QM_REG_ISDR, isdr);
+ portal->irq_sources = 0;
+ qm_out(p, QM_REG_IER, 0);
+ qm_out(p, QM_REG_ISR, 0xffffffff);
+ snprintf(portal->irqname, MAX_IRQNAME, IRQNAME, c->cpu);
+ if (request_irq(c->irq, portal_isr, 0, portal->irqname, portal)) {
+ dev_err(c->dev, "request_irq() failed\n");
+ goto fail_irq;
+ }
+ if (c->cpu != -1 && irq_can_set_affinity(c->irq) &&
+ irq_set_affinity(c->irq, cpumask_of(c->cpu))) {
+ dev_err(c->dev, "irq_set_affinity() failed\n");
+ goto fail_affinity;
+ }
+
+ /* Need EQCR to be empty before continuing */
+ isdr &= ~QM_PIRQ_EQCI;
+ qm_out(p, QM_REG_ISDR, isdr);
+ ret = qm_eqcr_get_fill(p);
+ if (ret) {
+ dev_err(c->dev, "EQCR unclean\n");
+ goto fail_eqcr_empty;
+ }
+ isdr &= ~(QM_PIRQ_DQRI | QM_PIRQ_MRI);
+ qm_out(p, QM_REG_ISDR, isdr);
+ if (qm_dqrr_current(p)) {
+ dev_err(c->dev, "DQRR unclean\n");
+ qm_dqrr_cdc_consume_n(p, 0xffff);
+ }
+ if (qm_mr_current(p) && drain_mr_fqrni(p)) {
+ /* special handling, drain just in case it's a few FQRNIs */
+ const union qm_mr_entry *e = qm_mr_current(p);
+
+ dev_err(c->dev, "MR dirty, VB 0x%x, rc 0x%x\n, addr 0x%x",
+ e->verb, e->ern.rc, e->ern.fd.addr_lo);
+ goto fail_dqrr_mr_empty;
+ }
+ /* Success */
+ portal->config = c;
+ qm_out(p, QM_REG_ISDR, 0);
+ qm_out(p, QM_REG_IIR, 0);
+ /* Write a sane SDQCR */
+ qm_dqrr_sdqcr_set(p, portal->sdqcr);
+ return 0;
+
+fail_dqrr_mr_empty:
+fail_eqcr_empty:
+fail_affinity:
+ free_irq(c->irq, portal);
+fail_irq:
+ platform_device_del(portal->pdev);
+fail_devadd:
+ platform_device_put(portal->pdev);
+fail_devalloc:
+ kfree(portal->cgrs);
+fail_cgrs:
+ qm_mc_finish(p);
+fail_mc:
+ qm_mr_finish(p);
+fail_mr:
+ qm_dqrr_finish(p);
+fail_dqrr:
+ qm_eqcr_finish(p);
+fail_eqcr:
+ return -EIO;
+}
+
+struct qman_portal *qman_create_affine_portal(const struct qm_portal_config *c,
+ const struct qman_cgrs *cgrs)
+{
+ struct qman_portal *portal;
+ int err;
+
+ portal = &per_cpu(qman_affine_portal, c->cpu);
+ err = qman_create_portal(portal, c, cgrs);
+ if (err)
+ return NULL;
+
+ spin_lock(&affine_mask_lock);
+ cpumask_set_cpu(c->cpu, &affine_mask);
+ affine_channels[c->cpu] = c->channel;
+ affine_portals[c->cpu] = portal;
+ spin_unlock(&affine_mask_lock);
+
+ return portal;
+}
+
+static void qman_destroy_portal(struct qman_portal *qm)
+{
+ const struct qm_portal_config *pcfg;
+
+ /* Stop dequeues on the portal */
+ qm_dqrr_sdqcr_set(&qm->p, 0);
+
+ /*
+ * NB we do this to "quiesce" EQCR. If we add enqueue-completions or
+ * something related to QM_PIRQ_EQCI, this may need fixing.
+ * Also, due to the prefetching model used for CI updates in the enqueue
+ * path, this update will only invalidate the CI cacheline *after*
+ * working on it, so we need to call this twice to ensure a full update
+ * irrespective of where the enqueue processing was at when the teardown
+ * began.
+ */
+ qm_eqcr_cce_update(&qm->p);
+ qm_eqcr_cce_update(&qm->p);
+ pcfg = qm->config;
+
+ free_irq(pcfg->irq, qm);
+
+ kfree(qm->cgrs);
+ qm_mc_finish(&qm->p);
+ qm_mr_finish(&qm->p);
+ qm_dqrr_finish(&qm->p);
+ qm_eqcr_finish(&qm->p);
+
+ platform_device_del(qm->pdev);
+ platform_device_put(qm->pdev);
+
+ qm->config = NULL;
+}
+
+const struct qm_portal_config *qman_destroy_affine_portal(void)
+{
+ struct qman_portal *qm = get_affine_portal();
+ const struct qm_portal_config *pcfg;
+ int cpu;
+
+ pcfg = qm->config;
+ cpu = pcfg->cpu;
+
+ qman_destroy_portal(qm);
+
+ spin_lock(&affine_mask_lock);
+ cpumask_clear_cpu(cpu, &affine_mask);
+ spin_unlock(&affine_mask_lock);
+ put_affine_portal();
+ return pcfg;
+}
+
+/* Inline helper to reduce nesting in __poll_portal_slow() */
+static inline void fq_state_change(struct qman_portal *p, struct qman_fq *fq,
+ const union qm_mr_entry *msg, u8 verb)
+{
+ switch (verb) {
+ case QM_MR_VERB_FQRL:
+ DPAA_ASSERT(fq_isset(fq, QMAN_FQ_STATE_ORL));
+ fq_clear(fq, QMAN_FQ_STATE_ORL);
+ break;
+ case QM_MR_VERB_FQRN:
+ DPAA_ASSERT(fq->state == qman_fq_state_parked ||
+ fq->state == qman_fq_state_sched);
+ DPAA_ASSERT(fq_isset(fq, QMAN_FQ_STATE_CHANGING));
+ fq_clear(fq, QMAN_FQ_STATE_CHANGING);
+ if (msg->fq.fqs & QM_MR_FQS_NOTEMPTY)
+ fq_set(fq, QMAN_FQ_STATE_NE);
+ if (msg->fq.fqs & QM_MR_FQS_ORLPRESENT)
+ fq_set(fq, QMAN_FQ_STATE_ORL);
+ fq->state = qman_fq_state_retired;
+ break;
+ case QM_MR_VERB_FQPN:
+ DPAA_ASSERT(fq->state == qman_fq_state_sched);
+ DPAA_ASSERT(fq_isclear(fq, QMAN_FQ_STATE_CHANGING));
+ fq->state = qman_fq_state_parked;
+ }
+}
+
+static void qm_congestion_task(struct work_struct *work)
+{
+ struct qman_portal *p = container_of(work, struct qman_portal,
+ congestion_work);
+ struct qman_cgrs rr, c;
+ union qm_mc_result *mcr;
+ struct qman_cgr *cgr;
+
+ spin_lock(&p->cgr_lock);
+ qm_mc_start(&p->p);
+ qm_mc_commit(&p->p, QM_MCC_VERB_QUERYCONGESTION);
+ if (!qm_mc_result_timeout(&p->p, &mcr)) {
+ spin_unlock(&p->cgr_lock);
+ dev_crit(p->config->dev, "QUERYCONGESTION timeout\n");
+ return;
+ }
+ /* mask out the ones I'm not interested in */
+ qman_cgrs_and(&rr, (struct qman_cgrs *)&mcr->querycongestion.state,
+ &p->cgrs[0]);
+ /* check previous snapshot for delta, enter/exit congestion */
+ qman_cgrs_xor(&c, &rr, &p->cgrs[1]);
+ /* update snapshot */
+ qman_cgrs_cp(&p->cgrs[1], &rr);
+ /* Invoke callback */
+ list_for_each_entry(cgr, &p->cgr_cbs, node)
+ if (cgr->cb && qman_cgrs_get(&c, cgr->cgrid))
+ cgr->cb(p, cgr, qman_cgrs_get(&rr, cgr->cgrid));
+ spin_unlock(&p->cgr_lock);
+}
+
+static void qm_mr_process_task(struct work_struct *work)
+{
+ struct qman_portal *p = container_of(work, struct qman_portal,
+ mr_work);
+ const union qm_mr_entry *msg;
+ struct qman_fq *fq;
+ u8 verb, num = 0;
+
+ preempt_disable();
+
+ while (1) {
+ qm_mr_pvb_update(&p->p);
+ msg = qm_mr_current(&p->p);
+ if (!msg)
+ break;
+
+ verb = msg->verb & QM_MR_VERB_TYPE_MASK;
+ /* The message is a software ERN iff the 0x20 bit is clear */
+ if (verb & 0x20) {
+ switch (verb) {
+ case QM_MR_VERB_FQRNI:
+ /* nada, we drop FQRNIs on the floor */
+ break;
+ case QM_MR_VERB_FQRN:
+ case QM_MR_VERB_FQRL:
+ /* Lookup in the retirement table */
+ fq = fqid_to_fq(msg->fq.fqid);
+ if (WARN_ON(!fq))
+ break;
+ fq_state_change(p, fq, msg, verb);
+ if (fq->cb.fqs)
+ fq->cb.fqs(p, fq, msg);
+ break;
+ case QM_MR_VERB_FQPN:
+ /* Parked */
+ fq = tag_to_fq(msg->fq.contextB);
+ fq_state_change(p, fq, msg, verb);
+ if (fq->cb.fqs)
+ fq->cb.fqs(p, fq, msg);
+ break;
+ case QM_MR_VERB_DC_ERN:
+ /* DCP ERN */
+ pr_crit_once("Leaking DCP ERNs!\n");
+ break;
+ default:
+ pr_crit("Invalid MR verb 0x%02x\n", verb);
+ }
+ } else {
+ /* Its a software ERN */
+ fq = tag_to_fq(msg->ern.tag);
+ fq->cb.ern(p, fq, msg);
+ }
+ num++;
+ qm_mr_next(&p->p);
+ }
+
+ qm_mr_cci_consume(&p->p, num);
+ preempt_enable();
+}
+
+static u32 __poll_portal_slow(struct qman_portal *p, u32 is)
+{
+ if (is & QM_PIRQ_CSCI) {
+ queue_work_on(smp_processor_id(), qm_portal_wq,
+ &p->congestion_work);
+ }
+
+ if (is & QM_PIRQ_EQRI) {
+ qm_eqcr_cce_update(&p->p);
+ qm_eqcr_set_ithresh(&p->p, 0);
+ wake_up(&affine_queue);
+ }
+
+ if (is & QM_PIRQ_MRI) {
+ queue_work_on(smp_processor_id(), qm_portal_wq,
+ &p->mr_work);
+ }
+
+ return is;
+}
+
+/*
+ * remove some slowish-path stuff from the "fast path" and make sure it isn't
+ * inlined.
+ */
+static noinline void clear_vdqcr(struct qman_portal *p, struct qman_fq *fq)
+{
+ p->vdqcr_owned = NULL;
+ fq_clear(fq, QMAN_FQ_STATE_VDQCR);
+ wake_up(&affine_queue);
+}
+
+/*
+ * The only states that would conflict with other things if they ran at the
+ * same time on the same cpu are:
+ *
+ * (i) setting/clearing vdqcr_owned, and
+ * (ii) clearing the NE (Not Empty) flag.
+ *
+ * Both are safe. Because;
+ *
+ * (i) this clearing can only occur after qman_volatile_dequeue() has set the
+ * vdqcr_owned field (which it does before setting VDQCR), and
+ * qman_volatile_dequeue() blocks interrupts and preemption while this is
+ * done so that we can't interfere.
+ * (ii) the NE flag is only cleared after qman_retire_fq() has set it, and as
+ * with (i) that API prevents us from interfering until it's safe.
+ *
+ * The good thing is that qman_volatile_dequeue() and qman_retire_fq() run far
+ * less frequently (ie. per-FQ) than __poll_portal_fast() does, so the nett
+ * advantage comes from this function not having to "lock" anything at all.
+ *
+ * Note also that the callbacks are invoked at points which are safe against the
+ * above potential conflicts, but that this function itself is not re-entrant
+ * (this is because the function tracks one end of each FIFO in the portal and
+ * we do *not* want to lock that). So the consequence is that it is safe for
+ * user callbacks to call into any QMan API.
+ */
+static inline unsigned int __poll_portal_fast(struct qman_portal *p,
+ unsigned int poll_limit)
+{
+ const struct qm_dqrr_entry *dq;
+ struct qman_fq *fq;
+ enum qman_cb_dqrr_result res;
+ unsigned int limit = 0;
+
+ do {
+ qm_dqrr_pvb_update(&p->p);
+ dq = qm_dqrr_current(&p->p);
+ if (!dq)
+ break;
+
+ if (dq->stat & QM_DQRR_STAT_UNSCHEDULED) {
+ /*
+ * VDQCR: don't trust contextB as the FQ may have
+ * been configured for h/w consumption and we're
+ * draining it post-retirement.
+ */
+ fq = p->vdqcr_owned;
+ /*
+ * We only set QMAN_FQ_STATE_NE when retiring, so we
+ * only need to check for clearing it when doing
+ * volatile dequeues. It's one less thing to check
+ * in the critical path (SDQCR).
+ */
+ if (dq->stat & QM_DQRR_STAT_FQ_EMPTY)
+ fq_clear(fq, QMAN_FQ_STATE_NE);
+ /*
+ * This is duplicated from the SDQCR code, but we
+ * have stuff to do before *and* after this callback,
+ * and we don't want multiple if()s in the critical
+ * path (SDQCR).
+ */
+ res = fq->cb.dqrr(p, fq, dq);
+ if (res == qman_cb_dqrr_stop)
+ break;
+ /* Check for VDQCR completion */
+ if (dq->stat & QM_DQRR_STAT_DQCR_EXPIRED)
+ clear_vdqcr(p, fq);
+ } else {
+ /* SDQCR: contextB points to the FQ */
+ fq = tag_to_fq(dq->contextB);
+ /* Now let the callback do its stuff */
+ res = fq->cb.dqrr(p, fq, dq);
+ /*
+ * The callback can request that we exit without
+ * consuming this entry nor advancing;
+ */
+ if (res == qman_cb_dqrr_stop)
+ break;
+ }
+ /* Interpret 'dq' from a driver perspective. */
+ /*
+ * Parking isn't possible unless HELDACTIVE was set. NB,
+ * FORCEELIGIBLE implies HELDACTIVE, so we only need to
+ * check for HELDACTIVE to cover both.
+ */
+ DPAA_ASSERT((dq->stat & QM_DQRR_STAT_FQ_HELDACTIVE) ||
+ (res != qman_cb_dqrr_park));
+ /* just means "skip it, I'll consume it myself later on" */
+ if (res != qman_cb_dqrr_defer)
+ qm_dqrr_cdc_consume_1ptr(&p->p, dq,
+ res == qman_cb_dqrr_park);
+ /* Move forward */
+ qm_dqrr_next(&p->p);
+ /*
+ * Entry processed and consumed, increment our counter. The
+ * callback can request that we exit after consuming the
+ * entry, and we also exit if we reach our processing limit,
+ * so loop back only if neither of these conditions is met.
+ */
+ } while (++limit < poll_limit && res != qman_cb_dqrr_consume_stop);
+
+ return limit;
+}
+
+void qman_p_irqsource_add(struct qman_portal *p, u32 bits)
+{
+ unsigned long irqflags;
+
+ local_irq_save(irqflags);
+ set_bits(bits & QM_PIRQ_VISIBLE, &p->irq_sources);
+ qm_out(&p->p, QM_REG_IER, p->irq_sources);
+ local_irq_restore(irqflags);
+}
+EXPORT_SYMBOL(qman_p_irqsource_add);
+
+void qman_p_irqsource_remove(struct qman_portal *p, u32 bits)
+{
+ unsigned long irqflags;
+ u32 ier;
+
+ /*
+ * Our interrupt handler only processes+clears status register bits that
+ * are in p->irq_sources. As we're trimming that mask, if one of them
+ * were to assert in the status register just before we remove it from
+ * the enable register, there would be an interrupt-storm when we
+ * release the IRQ lock. So we wait for the enable register update to
+ * take effect in h/w (by reading it back) and then clear all other bits
+ * in the status register. Ie. we clear them from ISR once it's certain
+ * IER won't allow them to reassert.
+ */
+ local_irq_save(irqflags);
+ bits &= QM_PIRQ_VISIBLE;
+ clear_bits(bits, &p->irq_sources);
+ qm_out(&p->p, QM_REG_IER, p->irq_sources);
+ ier = qm_in(&p->p, QM_REG_IER);
+ /*
+ * Using "~ier" (rather than "bits" or "~p->irq_sources") creates a
+ * data-dependency, ie. to protect against re-ordering.
+ */
+ qm_out(&p->p, QM_REG_ISR, ~ier);
+ local_irq_restore(irqflags);
+}
+EXPORT_SYMBOL(qman_p_irqsource_remove);
+
+const cpumask_t *qman_affine_cpus(void)
+{
+ return &affine_mask;
+}
+EXPORT_SYMBOL(qman_affine_cpus);
+
+u16 qman_affine_channel(int cpu)
+{
+ if (cpu < 0) {
+ struct qman_portal *portal = get_affine_portal();
+
+ cpu = portal->config->cpu;
+ put_affine_portal();
+ }
+ WARN_ON(!cpumask_test_cpu(cpu, &affine_mask));
+ return affine_channels[cpu];
+}
+EXPORT_SYMBOL(qman_affine_channel);
+
+struct qman_portal *qman_get_affine_portal(int cpu)
+{
+ return affine_portals[cpu];
+}
+EXPORT_SYMBOL(qman_get_affine_portal);
+
+int qman_p_poll_dqrr(struct qman_portal *p, unsigned int limit)
+{
+ return __poll_portal_fast(p, limit);
+}
+EXPORT_SYMBOL(qman_p_poll_dqrr);
+
+void qman_p_static_dequeue_add(struct qman_portal *p, u32 pools)
+{
+ unsigned long irqflags;
+
+ local_irq_save(irqflags);
+ pools &= p->config->pools;
+ p->sdqcr |= pools;
+ qm_dqrr_sdqcr_set(&p->p, p->sdqcr);
+ local_irq_restore(irqflags);
+}
+EXPORT_SYMBOL(qman_p_static_dequeue_add);
+
+/* Frame queue API */
+
+static const char *mcr_result_str(u8 result)
+{
+ switch (result) {
+ case QM_MCR_RESULT_NULL:
+ return "QM_MCR_RESULT_NULL";
+ case QM_MCR_RESULT_OK:
+ return "QM_MCR_RESULT_OK";
+ case QM_MCR_RESULT_ERR_FQID:
+ return "QM_MCR_RESULT_ERR_FQID";
+ case QM_MCR_RESULT_ERR_FQSTATE:
+ return "QM_MCR_RESULT_ERR_FQSTATE";
+ case QM_MCR_RESULT_ERR_NOTEMPTY:
+ return "QM_MCR_RESULT_ERR_NOTEMPTY";
+ case QM_MCR_RESULT_PENDING:
+ return "QM_MCR_RESULT_PENDING";
+ case QM_MCR_RESULT_ERR_BADCOMMAND:
+ return "QM_MCR_RESULT_ERR_BADCOMMAND";
+ }
+ return "<unknown MCR result>";
+}
+
+int qman_create_fq(u32 fqid, u32 flags, struct qman_fq *fq)
+{
+ if (flags & QMAN_FQ_FLAG_DYNAMIC_FQID) {
+ int ret = qman_alloc_fqid(&fqid);
+
+ if (ret)
+ return ret;
+ }
+ fq->fqid = fqid;
+ fq->flags = flags;
+ fq->state = qman_fq_state_oos;
+ fq->cgr_groupid = 0;
+
+ /* A context_b of 0 is allegedly special, so don't use that fqid */
+ if (fqid == 0 || fqid >= num_fqids) {
+ WARN(1, "bad fqid %d\n", fqid);
+ return -EINVAL;
+ }
+
+ fq->idx = fqid * 2;
+ if (flags & QMAN_FQ_FLAG_NO_MODIFY)
+ fq->idx++;
+
+ WARN_ON(fq_table[fq->idx]);
+ fq_table[fq->idx] = fq;
+
+ return 0;
+}
+EXPORT_SYMBOL(qman_create_fq);
+
+void qman_destroy_fq(struct qman_fq *fq)
+{
+ /*
+ * We don't need to lock the FQ as it is a pre-condition that the FQ be
+ * quiesced. Instead, run some checks.
+ */
+ switch (fq->state) {
+ case qman_fq_state_parked:
+ case qman_fq_state_oos:
+ if (fq_isset(fq, QMAN_FQ_FLAG_DYNAMIC_FQID))
+ qman_release_fqid(fq->fqid);
+
+ DPAA_ASSERT(fq_table[fq->idx]);
+ fq_table[fq->idx] = NULL;
+ return;
+ default:
+ break;
+ }
+ DPAA_ASSERT(NULL == "qman_free_fq() on unquiesced FQ!");
+}
+EXPORT_SYMBOL(qman_destroy_fq);
+
+u32 qman_fq_fqid(struct qman_fq *fq)
+{
+ return fq->fqid;
+}
+EXPORT_SYMBOL(qman_fq_fqid);
+
+int qman_init_fq(struct qman_fq *fq, u32 flags, struct qm_mcc_initfq *opts)
+{
+ union qm_mc_command *mcc;
+ union qm_mc_result *mcr;
+ struct qman_portal *p;
+ u8 res, myverb;
+ int ret = 0;
+
+ myverb = (flags & QMAN_INITFQ_FLAG_SCHED)
+ ? QM_MCC_VERB_INITFQ_SCHED : QM_MCC_VERB_INITFQ_PARKED;
+
+ if (fq->state != qman_fq_state_oos &&
+ fq->state != qman_fq_state_parked)
+ return -EINVAL;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ if (fq_isset(fq, QMAN_FQ_FLAG_NO_MODIFY))
+ return -EINVAL;
+#endif
+ if (opts && (opts->we_mask & QM_INITFQ_WE_OAC)) {
+ /* And can't be set at the same time as TDTHRESH */
+ if (opts->we_mask & QM_INITFQ_WE_TDTHRESH)
+ return -EINVAL;
+ }
+ /* Issue an INITFQ_[PARKED|SCHED] management command */
+ p = get_affine_portal();
+ if (fq_isset(fq, QMAN_FQ_STATE_CHANGING) ||
+ (fq->state != qman_fq_state_oos &&
+ fq->state != qman_fq_state_parked)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ mcc = qm_mc_start(&p->p);
+ if (opts)
+ mcc->initfq = *opts;
+ mcc->initfq.fqid = fq->fqid;
+ mcc->initfq.count = 0;
+ /*
+ * If the FQ does *not* have the TO_DCPORTAL flag, contextB is set as a
+ * demux pointer. Otherwise, the caller-provided value is allowed to
+ * stand, don't overwrite it.
+ */
+ if (fq_isclear(fq, QMAN_FQ_FLAG_TO_DCPORTAL)) {
+ dma_addr_t phys_fq;
+
+ mcc->initfq.we_mask |= QM_INITFQ_WE_CONTEXTB;
+ mcc->initfq.fqd.context_b = fq_to_tag(fq);
+ /*
+ * and the physical address - NB, if the user wasn't trying to
+ * set CONTEXTA, clear the stashing settings.
+ */
+ if (!(mcc->initfq.we_mask & QM_INITFQ_WE_CONTEXTA)) {
+ mcc->initfq.we_mask |= QM_INITFQ_WE_CONTEXTA;
+ memset(&mcc->initfq.fqd.context_a, 0,
+ sizeof(mcc->initfq.fqd.context_a));
+ } else {
+ phys_fq = dma_map_single(&p->pdev->dev, fq, sizeof(*fq),
+ DMA_TO_DEVICE);
+ qm_fqd_stashing_set64(&mcc->initfq.fqd, phys_fq);
+ }
+ }
+ if (flags & QMAN_INITFQ_FLAG_LOCAL) {
+ int wq = 0;
+
+ if (!(mcc->initfq.we_mask & QM_INITFQ_WE_DESTWQ)) {
+ mcc->initfq.we_mask |= QM_INITFQ_WE_DESTWQ;
+ wq = 4;
+ }
+ qm_fqd_set_destwq(&mcc->initfq.fqd, p->config->channel, wq);
+ }
+ qm_mc_commit(&p->p, myverb);
+ if (!qm_mc_result_timeout(&p->p, &mcr)) {
+ dev_err(p->config->dev, "MCR timeout\n");
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+
+ DPAA_ASSERT((mcr->verb & QM_MCR_VERB_MASK) == myverb);
+ res = mcr->result;
+ if (res != QM_MCR_RESULT_OK) {
+ ret = -EIO;
+ goto out;
+ }
+ if (opts) {
+ if (opts->we_mask & QM_INITFQ_WE_FQCTRL) {
+ if (opts->fqd.fq_ctrl & QM_FQCTRL_CGE)
+ fq_set(fq, QMAN_FQ_STATE_CGR_EN);
+ else
+ fq_clear(fq, QMAN_FQ_STATE_CGR_EN);
+ }
+ if (opts->we_mask & QM_INITFQ_WE_CGID)
+ fq->cgr_groupid = opts->fqd.cgid;
+ }
+ fq->state = (flags & QMAN_INITFQ_FLAG_SCHED) ?
+ qman_fq_state_sched : qman_fq_state_parked;
+
+out:
+ put_affine_portal();
+ return ret;
+}
+EXPORT_SYMBOL(qman_init_fq);
+
+int qman_schedule_fq(struct qman_fq *fq)
+{
+ union qm_mc_command *mcc;
+ union qm_mc_result *mcr;
+ struct qman_portal *p;
+ int ret = 0;
+
+ if (fq->state != qman_fq_state_parked)
+ return -EINVAL;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ if (fq_isset(fq, QMAN_FQ_FLAG_NO_MODIFY))
+ return -EINVAL;
+#endif
+ /* Issue a ALTERFQ_SCHED management command */
+ p = get_affine_portal();
+ if (fq_isset(fq, QMAN_FQ_STATE_CHANGING) ||
+ fq->state != qman_fq_state_parked) {
+ ret = -EBUSY;
+ goto out;
+ }
+ mcc = qm_mc_start(&p->p);
+ mcc->alterfq.fqid = fq->fqid;
+ qm_mc_commit(&p->p, QM_MCC_VERB_ALTER_SCHED);
+ if (!qm_mc_result_timeout(&p->p, &mcr)) {
+ dev_err(p->config->dev, "ALTER_SCHED timeout\n");
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+
+ DPAA_ASSERT((mcr->verb & QM_MCR_VERB_MASK) == QM_MCR_VERB_ALTER_SCHED);
+ if (mcr->result != QM_MCR_RESULT_OK) {
+ ret = -EIO;
+ goto out;
+ }
+ fq->state = qman_fq_state_sched;
+out:
+ put_affine_portal();
+ return ret;
+}
+EXPORT_SYMBOL(qman_schedule_fq);
+
+int qman_retire_fq(struct qman_fq *fq, u32 *flags)
+{
+ union qm_mc_command *mcc;
+ union qm_mc_result *mcr;
+ struct qman_portal *p;
+ int ret;
+ u8 res;
+
+ if (fq->state != qman_fq_state_parked &&
+ fq->state != qman_fq_state_sched)
+ return -EINVAL;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ if (fq_isset(fq, QMAN_FQ_FLAG_NO_MODIFY))
+ return -EINVAL;
+#endif
+ p = get_affine_portal();
+ if (fq_isset(fq, QMAN_FQ_STATE_CHANGING) ||
+ fq->state == qman_fq_state_retired ||
+ fq->state == qman_fq_state_oos) {
+ ret = -EBUSY;
+ goto out;
+ }
+ mcc = qm_mc_start(&p->p);
+ mcc->alterfq.fqid = fq->fqid;
+ qm_mc_commit(&p->p, QM_MCC_VERB_ALTER_RETIRE);
+ if (!qm_mc_result_timeout(&p->p, &mcr)) {
+ dev_crit(p->config->dev, "ALTER_RETIRE timeout\n");
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+
+ DPAA_ASSERT((mcr->verb & QM_MCR_VERB_MASK) == QM_MCR_VERB_ALTER_RETIRE);
+ res = mcr->result;
+ /*
+ * "Elegant" would be to treat OK/PENDING the same way; set CHANGING,
+ * and defer the flags until FQRNI or FQRN (respectively) show up. But
+ * "Friendly" is to process OK immediately, and not set CHANGING. We do
+ * friendly, otherwise the caller doesn't necessarily have a fully
+ * "retired" FQ on return even if the retirement was immediate. However
+ * this does mean some code duplication between here and
+ * fq_state_change().
+ */
+ if (res == QM_MCR_RESULT_OK) {
+ ret = 0;
+ /* Process 'fq' right away, we'll ignore FQRNI */
+ if (mcr->alterfq.fqs & QM_MCR_FQS_NOTEMPTY)
+ fq_set(fq, QMAN_FQ_STATE_NE);
+ if (mcr->alterfq.fqs & QM_MCR_FQS_ORLPRESENT)
+ fq_set(fq, QMAN_FQ_STATE_ORL);
+ if (flags)
+ *flags = fq->flags;
+ fq->state = qman_fq_state_retired;
+ if (fq->cb.fqs) {
+ /*
+ * Another issue with supporting "immediate" retirement
+ * is that we're forced to drop FQRNIs, because by the
+ * time they're seen it may already be "too late" (the
+ * fq may have been OOS'd and free()'d already). But if
+ * the upper layer wants a callback whether it's
+ * immediate or not, we have to fake a "MR" entry to
+ * look like an FQRNI...
+ */
+ union qm_mr_entry msg;
+
+ msg.verb = QM_MR_VERB_FQRNI;
+ msg.fq.fqs = mcr->alterfq.fqs;
+ msg.fq.fqid = fq->fqid;
+ msg.fq.contextB = fq_to_tag(fq);
+ fq->cb.fqs(p, fq, &msg);
+ }
+ } else if (res == QM_MCR_RESULT_PENDING) {
+ ret = 1;
+ fq_set(fq, QMAN_FQ_STATE_CHANGING);
+ } else {
+ ret = -EIO;
+ }
+out:
+ put_affine_portal();
+ return ret;
+}
+EXPORT_SYMBOL(qman_retire_fq);
+
+int qman_oos_fq(struct qman_fq *fq)
+{
+ union qm_mc_command *mcc;
+ union qm_mc_result *mcr;
+ struct qman_portal *p;
+ int ret = 0;
+
+ if (fq->state != qman_fq_state_retired)
+ return -EINVAL;
+#ifdef CONFIG_FSL_DPAA_CHECKING
+ if (fq_isset(fq, QMAN_FQ_FLAG_NO_MODIFY))
+ return -EINVAL;
+#endif
+ p = get_affine_portal();
+ if (fq_isset(fq, QMAN_FQ_STATE_BLOCKOOS) ||
+ fq->state != qman_fq_state_retired) {
+ ret = -EBUSY;
+ goto out;
+ }
+ mcc = qm_mc_start(&p->p);
+ mcc->alterfq.fqid = fq->fqid;
+ qm_mc_commit(&p->p, QM_MCC_VERB_ALTER_OOS);
+ if (!qm_mc_result_timeout(&p->p, &mcr)) {
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+ DPAA_ASSERT((mcr->verb & QM_MCR_VERB_MASK) == QM_MCR_VERB_ALTER_OOS);
+ if (mcr->result != QM_MCR_RESULT_OK) {
+ ret = -EIO;
+ goto out;
+ }
+ fq->state = qman_fq_state_oos;
+out:
+ put_affine_portal();
+ return ret;
+}
+EXPORT_SYMBOL(qman_oos_fq);
+
+int qman_query_fq(struct qman_fq *fq, struct qm_fqd *fqd)
+{
+ union qm_mc_command *mcc;
+ union qm_mc_result *mcr;
+ struct qman_portal *p = get_affine_portal();
+ int ret = 0;
+
+ mcc = qm_mc_start(&p->p);
+ mcc->queryfq.fqid = fq->fqid;
+ qm_mc_commit(&p->p, QM_MCC_VERB_QUERYFQ);
+ if (!qm_mc_result_timeout(&p->p, &mcr)) {
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+
+ DPAA_ASSERT((mcr->verb & QM_MCR_VERB_MASK) == QM_MCR_VERB_QUERYFQ);
+ if (mcr->result == QM_MCR_RESULT_OK)
+ *fqd = mcr->queryfq.fqd;
+ else
+ ret = -EIO;
+out:
+ put_affine_portal();
+ return ret;
+}
+
+static int qman_query_fq_np(struct qman_fq *fq,
+ struct qm_mcr_queryfq_np *np)
+{
+ union qm_mc_command *mcc;
+ union qm_mc_result *mcr;
+ struct qman_portal *p = get_affine_portal();
+ int ret = 0;
+
+ mcc = qm_mc_start(&p->p);
+ mcc->queryfq.fqid = fq->fqid;
+ qm_mc_commit(&p->p, QM_MCC_VERB_QUERYFQ_NP);
+ if (!qm_mc_result_timeout(&p->p, &mcr)) {
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+
+ DPAA_ASSERT((mcr->verb & QM_MCR_VERB_MASK) == QM_MCR_VERB_QUERYFQ_NP);
+ if (mcr->result == QM_MCR_RESULT_OK)
+ *np = mcr->queryfq_np;
+ else if (mcr->result == QM_MCR_RESULT_ERR_FQID)
+ ret = -ERANGE;
+ else
+ ret = -EIO;
+out:
+ put_affine_portal();
+ return ret;
+}
+
+static int qman_query_cgr(struct qman_cgr *cgr,
+ struct qm_mcr_querycgr *cgrd)
+{
+ union qm_mc_command *mcc;
+ union qm_mc_result *mcr;
+ struct qman_portal *p = get_affine_portal();
+ int ret = 0;
+
+ mcc = qm_mc_start(&p->p);
+ mcc->querycgr.cgid = cgr->cgrid;
+ qm_mc_commit(&p->p, QM_MCC_VERB_QUERYCGR);
+ if (!qm_mc_result_timeout(&p->p, &mcr)) {
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+ DPAA_ASSERT((mcr->verb & QM_MCR_VERB_MASK) == QM_MCC_VERB_QUERYCGR);
+ if (mcr->result == QM_MCR_RESULT_OK)
+ *cgrd = mcr->querycgr;
+ else {
+ dev_err(p->config->dev, "QUERY_CGR failed: %s\n",
+ mcr_result_str(mcr->result));
+ ret = -EIO;
+ }
+out:
+ put_affine_portal();
+ return ret;
+}
+
+int qman_query_cgr_congested(struct qman_cgr *cgr, bool *result)
+{
+ struct qm_mcr_querycgr query_cgr;
+ int err;
+
+ err = qman_query_cgr(cgr, &query_cgr);
+ if (err)
+ return err;
+
+ *result = !!query_cgr.cgr.cs;
+ return 0;
+}
+EXPORT_SYMBOL(qman_query_cgr_congested);
+
+/* internal function used as a wait_event() expression */
+static int set_p_vdqcr(struct qman_portal *p, struct qman_fq *fq, u32 vdqcr)
+{
+ unsigned long irqflags;
+ int ret = -EBUSY;
+
+ local_irq_save(irqflags);
+ if (p->vdqcr_owned)
+ goto out;
+ if (fq_isset(fq, QMAN_FQ_STATE_VDQCR))
+ goto out;
+
+ fq_set(fq, QMAN_FQ_STATE_VDQCR);
+ p->vdqcr_owned = fq;
+ qm_dqrr_vdqcr_set(&p->p, vdqcr);
+ ret = 0;
+out:
+ local_irq_restore(irqflags);
+ return ret;
+}
+
+static int set_vdqcr(struct qman_portal **p, struct qman_fq *fq, u32 vdqcr)
+{
+ int ret;
+
+ *p = get_affine_portal();
+ ret = set_p_vdqcr(*p, fq, vdqcr);
+ put_affine_portal();
+ return ret;
+}
+
+static int wait_vdqcr_start(struct qman_portal **p, struct qman_fq *fq,
+ u32 vdqcr, u32 flags)
+{
+ int ret = 0;
+
+ if (flags & QMAN_VOLATILE_FLAG_WAIT_INT)
+ ret = wait_event_interruptible(affine_queue,
+ !set_vdqcr(p, fq, vdqcr));
+ else
+ wait_event(affine_queue, !set_vdqcr(p, fq, vdqcr));
+ return ret;
+}
+
+int qman_volatile_dequeue(struct qman_fq *fq, u32 flags, u32 vdqcr)
+{
+ struct qman_portal *p;
+ int ret;
+
+ if (fq->state != qman_fq_state_parked &&
+ fq->state != qman_fq_state_retired)
+ return -EINVAL;
+ if (vdqcr & QM_VDQCR_FQID_MASK)
+ return -EINVAL;
+ if (fq_isset(fq, QMAN_FQ_STATE_VDQCR))
+ return -EBUSY;
+ vdqcr = (vdqcr & ~QM_VDQCR_FQID_MASK) | fq->fqid;
+ if (flags & QMAN_VOLATILE_FLAG_WAIT)
+ ret = wait_vdqcr_start(&p, fq, vdqcr, flags);
+ else
+ ret = set_vdqcr(&p, fq, vdqcr);
+ if (ret)
+ return ret;
+ /* VDQCR is set */
+ if (flags & QMAN_VOLATILE_FLAG_FINISH) {
+ if (flags & QMAN_VOLATILE_FLAG_WAIT_INT)
+ /*
+ * NB: don't propagate any error - the caller wouldn't
+ * know whether the VDQCR was issued or not. A signal
+ * could arrive after returning anyway, so the caller
+ * can check signal_pending() if that's an issue.
+ */
+ wait_event_interruptible(affine_queue,
+ !fq_isset(fq, QMAN_FQ_STATE_VDQCR));
+ else
+ wait_event(affine_queue,
+ !fq_isset(fq, QMAN_FQ_STATE_VDQCR));
+ }
+ return 0;
+}
+EXPORT_SYMBOL(qman_volatile_dequeue);
+
+static void update_eqcr_ci(struct qman_portal *p, u8 avail)
+{
+ if (avail)
+ qm_eqcr_cce_prefetch(&p->p);
+ else
+ qm_eqcr_cce_update(&p->p);
+}
+
+int qman_enqueue(struct qman_fq *fq, const struct qm_fd *fd)
+{
+ struct qman_portal *p;
+ struct qm_eqcr_entry *eq;
+ unsigned long irqflags;
+ u8 avail;
+
+ p = get_affine_portal();
+ local_irq_save(irqflags);
+
+ if (p->use_eqcr_ci_stashing) {
+ /*
+ * The stashing case is easy, only update if we need to in
+ * order to try and liberate ring entries.
+ */
+ eq = qm_eqcr_start_stash(&p->p);
+ } else {
+ /*
+ * The non-stashing case is harder, need to prefetch ahead of
+ * time.
+ */
+ avail = qm_eqcr_get_avail(&p->p);
+ if (avail < 2)
+ update_eqcr_ci(p, avail);
+ eq = qm_eqcr_start_no_stash(&p->p);
+ }
+
+ if (unlikely(!eq))
+ goto out;
+
+ eq->fqid = fq->fqid;
+ eq->tag = fq_to_tag(fq);
+ eq->fd = *fd;
+
+ qm_eqcr_pvb_commit(&p->p, QM_EQCR_VERB_CMD_ENQUEUE);
+out:
+ local_irq_restore(irqflags);
+ put_affine_portal();
+ return 0;
+}
+EXPORT_SYMBOL(qman_enqueue);
+
+static int qm_modify_cgr(struct qman_cgr *cgr, u32 flags,
+ struct qm_mcc_initcgr *opts)
+{
+ union qm_mc_command *mcc;
+ union qm_mc_result *mcr;
+ struct qman_portal *p = get_affine_portal();
+ u8 verb = QM_MCC_VERB_MODIFYCGR;
+ int ret = 0;
+
+ mcc = qm_mc_start(&p->p);
+ if (opts)
+ mcc->initcgr = *opts;
+ mcc->initcgr.cgid = cgr->cgrid;
+ if (flags & QMAN_CGR_FLAG_USE_INIT)
+ verb = QM_MCC_VERB_INITCGR;
+ qm_mc_commit(&p->p, verb);
+ if (!qm_mc_result_timeout(&p->p, &mcr)) {
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+
+ DPAA_ASSERT((mcr->verb & QM_MCR_VERB_MASK) == verb);
+ if (mcr->result != QM_MCR_RESULT_OK)
+ ret = -EIO;
+
+out:
+ put_affine_portal();
+ return ret;
+}
+
+#define PORTAL_IDX(n) (n->config->channel - QM_CHANNEL_SWPORTAL0)
+#define TARG_MASK(n) (BIT(31) >> PORTAL_IDX(n))
+
+static u8 qman_cgr_cpus[CGR_NUM];
+
+void qman_init_cgr_all(void)
+{
+ struct qman_cgr cgr;
+ int err_cnt = 0;
+
+ for (cgr.cgrid = 0; cgr.cgrid < CGR_NUM; cgr.cgrid++) {
+ if (qm_modify_cgr(&cgr, QMAN_CGR_FLAG_USE_INIT, NULL))
+ err_cnt++;
+ }
+
+ if (err_cnt)
+ pr_err("Warning: %d error%s while initialising CGR h/w\n",
+ err_cnt, (err_cnt > 1) ? "s" : "");
+}
+
+int qman_create_cgr(struct qman_cgr *cgr, u32 flags,
+ struct qm_mcc_initcgr *opts)
+{
+ struct qm_mcr_querycgr cgr_state;
+ struct qm_mcc_initcgr local_opts = {};
+ int ret;
+ struct qman_portal *p;
+
+ /*
+ * We have to check that the provided CGRID is within the limits of the
+ * data-structures, for obvious reasons. However we'll let h/w take
+ * care of determining whether it's within the limits of what exists on
+ * the SoC.
+ */
+ if (cgr->cgrid >= CGR_NUM)
+ return -EINVAL;
+
+ preempt_disable();
+ p = get_affine_portal();
+ qman_cgr_cpus[cgr->cgrid] = smp_processor_id();
+ preempt_enable();
+
+ cgr->chan = p->config->channel;
+ spin_lock(&p->cgr_lock);
+
+ if (opts) {
+ ret = qman_query_cgr(cgr, &cgr_state);
+ if (ret)
+ goto out;
+ if (opts)
+ local_opts = *opts;
+ if ((qman_ip_rev & 0xFF00) >= QMAN_REV30)
+ local_opts.cgr.cscn_targ_upd_ctrl =
+ QM_CGR_TARG_UDP_CTRL_WRITE_BIT | PORTAL_IDX(p);
+ else
+ /* Overwrite TARG */
+ local_opts.cgr.cscn_targ = cgr_state.cgr.cscn_targ |
+ TARG_MASK(p);
+ local_opts.we_mask |= QM_CGR_WE_CSCN_TARG;
+
+ /* send init if flags indicate so */
+ if (opts && (flags & QMAN_CGR_FLAG_USE_INIT))
+ ret = qm_modify_cgr(cgr, QMAN_CGR_FLAG_USE_INIT,
+ &local_opts);
+ else
+ ret = qm_modify_cgr(cgr, 0, &local_opts);
+ if (ret)
+ goto out;
+ }
+
+ list_add(&cgr->node, &p->cgr_cbs);
+
+ /* Determine if newly added object requires its callback to be called */
+ ret = qman_query_cgr(cgr, &cgr_state);
+ if (ret) {
+ /* we can't go back, so proceed and return success */
+ dev_err(p->config->dev, "CGR HW state partially modified\n");
+ ret = 0;
+ goto out;
+ }
+ if (cgr->cb && cgr_state.cgr.cscn_en &&
+ qman_cgrs_get(&p->cgrs[1], cgr->cgrid))
+ cgr->cb(p, cgr, 1);
+out:
+ spin_unlock(&p->cgr_lock);
+ put_affine_portal();
+ return ret;
+}
+EXPORT_SYMBOL(qman_create_cgr);
+
+int qman_delete_cgr(struct qman_cgr *cgr)
+{
+ unsigned long irqflags;
+ struct qm_mcr_querycgr cgr_state;
+ struct qm_mcc_initcgr local_opts;
+ int ret = 0;
+ struct qman_cgr *i;
+ struct qman_portal *p = get_affine_portal();
+
+ if (cgr->chan != p->config->channel) {
+ /* attempt to delete from other portal than creator */
+ dev_err(p->config->dev, "CGR not owned by current portal");
+ dev_dbg(p->config->dev, " create 0x%x, delete 0x%x\n",
+ cgr->chan, p->config->channel);
+
+ ret = -EINVAL;
+ goto put_portal;
+ }
+ memset(&local_opts, 0, sizeof(struct qm_mcc_initcgr));
+ spin_lock_irqsave(&p->cgr_lock, irqflags);
+ list_del(&cgr->node);
+ /*
+ * If there are no other CGR objects for this CGRID in the list,
+ * update CSCN_TARG accordingly
+ */
+ list_for_each_entry(i, &p->cgr_cbs, node)
+ if (i->cgrid == cgr->cgrid && i->cb)
+ goto release_lock;
+ ret = qman_query_cgr(cgr, &cgr_state);
+ if (ret) {
+ /* add back to the list */
+ list_add(&cgr->node, &p->cgr_cbs);
+ goto release_lock;
+ }
+ /* Overwrite TARG */
+ local_opts.we_mask = QM_CGR_WE_CSCN_TARG;
+ if ((qman_ip_rev & 0xFF00) >= QMAN_REV30)
+ local_opts.cgr.cscn_targ_upd_ctrl = PORTAL_IDX(p);
+ else
+ local_opts.cgr.cscn_targ = cgr_state.cgr.cscn_targ &
+ ~(TARG_MASK(p));
+ ret = qm_modify_cgr(cgr, 0, &local_opts);
+ if (ret)
+ /* add back to the list */
+ list_add(&cgr->node, &p->cgr_cbs);
+release_lock:
+ spin_unlock_irqrestore(&p->cgr_lock, irqflags);
+put_portal:
+ put_affine_portal();
+ return ret;
+}
+EXPORT_SYMBOL(qman_delete_cgr);
+
+struct cgr_comp {
+ struct qman_cgr *cgr;
+ struct completion completion;
+};
+
+static int qman_delete_cgr_thread(void *p)
+{
+ struct cgr_comp *cgr_comp = (struct cgr_comp *)p;
+ int ret;
+
+ ret = qman_delete_cgr(cgr_comp->cgr);
+ complete(&cgr_comp->completion);
+
+ return ret;
+}
+
+void qman_delete_cgr_safe(struct qman_cgr *cgr)
+{
+ struct task_struct *thread;
+ struct cgr_comp cgr_comp;
+
+ preempt_disable();
+ if (qman_cgr_cpus[cgr->cgrid] != smp_processor_id()) {
+ init_completion(&cgr_comp.completion);
+ cgr_comp.cgr = cgr;
+ thread = kthread_create(qman_delete_cgr_thread, &cgr_comp,
+ "cgr_del");
+
+ if (IS_ERR(thread))
+ goto out;
+
+ kthread_bind(thread, qman_cgr_cpus[cgr->cgrid]);
+ wake_up_process(thread);
+ wait_for_completion(&cgr_comp.completion);
+ preempt_enable();
+ return;
+ }
+out:
+ qman_delete_cgr(cgr);
+ preempt_enable();
+}
+EXPORT_SYMBOL(qman_delete_cgr_safe);
+
+/* Cleanup FQs */
+
+static int _qm_mr_consume_and_match_verb(struct qm_portal *p, int v)
+{
+ const union qm_mr_entry *msg;
+ int found = 0;
+
+ qm_mr_pvb_update(p);
+ msg = qm_mr_current(p);
+ while (msg) {
+ if ((msg->verb & QM_MR_VERB_TYPE_MASK) == v)
+ found = 1;
+ qm_mr_next(p);
+ qm_mr_cci_consume_to_current(p);
+ qm_mr_pvb_update(p);
+ msg = qm_mr_current(p);
+ }
+ return found;
+}
+
+static int _qm_dqrr_consume_and_match(struct qm_portal *p, u32 fqid, int s,
+ bool wait)
+{
+ const struct qm_dqrr_entry *dqrr;
+ int found = 0;
+
+ do {
+ qm_dqrr_pvb_update(p);
+ dqrr = qm_dqrr_current(p);
+ if (!dqrr)
+ cpu_relax();
+ } while (wait && !dqrr);
+
+ while (dqrr) {
+ if (dqrr->fqid == fqid && (dqrr->stat & s))
+ found = 1;
+ qm_dqrr_cdc_consume_1ptr(p, dqrr, 0);
+ qm_dqrr_pvb_update(p);
+ qm_dqrr_next(p);
+ dqrr = qm_dqrr_current(p);
+ }
+ return found;
+}
+
+#define qm_mr_drain(p, V) \
+ _qm_mr_consume_and_match_verb(p, QM_MR_VERB_##V)
+
+#define qm_dqrr_drain(p, f, S) \
+ _qm_dqrr_consume_and_match(p, f, QM_DQRR_STAT_##S, false)
+
+#define qm_dqrr_drain_wait(p, f, S) \
+ _qm_dqrr_consume_and_match(p, f, QM_DQRR_STAT_##S, true)
+
+#define qm_dqrr_drain_nomatch(p) \
+ _qm_dqrr_consume_and_match(p, 0, 0, false)
+
+static int qman_shutdown_fq(u32 fqid)
+{
+ struct qman_portal *p;
+ struct device *dev;
+ union qm_mc_command *mcc;
+ union qm_mc_result *mcr;
+ int orl_empty, drain = 0, ret = 0;
+ u32 channel, wq, res;
+ u8 state;
+
+ p = get_affine_portal();
+ dev = p->config->dev;
+ /* Determine the state of the FQID */
+ mcc = qm_mc_start(&p->p);
+ mcc->queryfq_np.fqid = fqid;
+ qm_mc_commit(&p->p, QM_MCC_VERB_QUERYFQ_NP);
+ if (!qm_mc_result_timeout(&p->p, &mcr)) {
+ dev_err(dev, "QUERYFQ_NP timeout\n");
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+
+ DPAA_ASSERT((mcr->verb & QM_MCR_VERB_MASK) == QM_MCR_VERB_QUERYFQ_NP);
+ state = mcr->queryfq_np.state & QM_MCR_NP_STATE_MASK;
+ if (state == QM_MCR_NP_STATE_OOS)
+ goto out; /* Already OOS, no need to do anymore checks */
+
+ /* Query which channel the FQ is using */
+ mcc = qm_mc_start(&p->p);
+ mcc->queryfq.fqid = fqid;
+ qm_mc_commit(&p->p, QM_MCC_VERB_QUERYFQ);
+ if (!qm_mc_result_timeout(&p->p, &mcr)) {
+ dev_err(dev, "QUERYFQ timeout\n");
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+
+ DPAA_ASSERT((mcr->verb & QM_MCR_VERB_MASK) == QM_MCR_VERB_QUERYFQ);
+ /* Need to store these since the MCR gets reused */
+ channel = qm_fqd_get_chan(&mcr->queryfq.fqd);
+ wq = qm_fqd_get_wq(&mcr->queryfq.fqd);
+
+ switch (state) {
+ case QM_MCR_NP_STATE_TEN_SCHED:
+ case QM_MCR_NP_STATE_TRU_SCHED:
+ case QM_MCR_NP_STATE_ACTIVE:
+ case QM_MCR_NP_STATE_PARKED:
+ orl_empty = 0;
+ mcc = qm_mc_start(&p->p);
+ mcc->alterfq.fqid = fqid;
+ qm_mc_commit(&p->p, QM_MCC_VERB_ALTER_RETIRE);
+ if (!qm_mc_result_timeout(&p->p, &mcr)) {
+ dev_err(dev, "QUERYFQ_NP timeout\n");
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+ DPAA_ASSERT((mcr->verb & QM_MCR_VERB_MASK) ==
+ QM_MCR_VERB_ALTER_RETIRE);
+ res = mcr->result; /* Make a copy as we reuse MCR below */
+
+ if (res == QM_MCR_RESULT_PENDING) {
+ /*
+ * Need to wait for the FQRN in the message ring, which
+ * will only occur once the FQ has been drained. In
+ * order for the FQ to drain the portal needs to be set
+ * to dequeue from the channel the FQ is scheduled on
+ */
+ int found_fqrn = 0;
+ u16 dequeue_wq = 0;
+
+ /* Flag that we need to drain FQ */
+ drain = 1;
+
+ if (channel >= qm_channel_pool1 &&
+ channel < qm_channel_pool1 + 15) {
+ /* Pool channel, enable the bit in the portal */
+ dequeue_wq = (channel -
+ qm_channel_pool1 + 1)<<4 | wq;
+ } else if (channel < qm_channel_pool1) {
+ /* Dedicated channel */
+ dequeue_wq = wq;
+ } else {
+ dev_err(dev, "Can't recover FQ 0x%x, ch: 0x%x",
+ fqid, channel);
+ ret = -EBUSY;
+ goto out;
+ }
+ /* Set the sdqcr to drain this channel */
+ if (channel < qm_channel_pool1)
+ qm_dqrr_sdqcr_set(&p->p,
+ QM_SDQCR_TYPE_ACTIVE |
+ QM_SDQCR_CHANNELS_DEDICATED);
+ else
+ qm_dqrr_sdqcr_set(&p->p,
+ QM_SDQCR_TYPE_ACTIVE |
+ QM_SDQCR_CHANNELS_POOL_CONV
+ (channel));
+ do {
+ /* Keep draining DQRR while checking the MR*/
+ qm_dqrr_drain_nomatch(&p->p);
+ /* Process message ring too */
+ found_fqrn = qm_mr_drain(&p->p, FQRN);
+ cpu_relax();
+ } while (!found_fqrn);
+
+ }
+ if (res != QM_MCR_RESULT_OK &&
+ res != QM_MCR_RESULT_PENDING) {
+ dev_err(dev, "retire_fq failed: FQ 0x%x, res=0x%x\n",
+ fqid, res);
+ ret = -EIO;
+ goto out;
+ }
+ if (!(mcr->alterfq.fqs & QM_MCR_FQS_ORLPRESENT)) {
+ /*
+ * ORL had no entries, no need to wait until the
+ * ERNs come in
+ */
+ orl_empty = 1;
+ }
+ /*
+ * Retirement succeeded, check to see if FQ needs
+ * to be drained
+ */
+ if (drain || mcr->alterfq.fqs & QM_MCR_FQS_NOTEMPTY) {
+ /* FQ is Not Empty, drain using volatile DQ commands */
+ do {
+ u32 vdqcr = fqid | QM_VDQCR_NUMFRAMES_SET(3);
+
+ qm_dqrr_vdqcr_set(&p->p, vdqcr);
+ /*
+ * Wait for a dequeue and process the dequeues,
+ * making sure to empty the ring completely
+ */
+ } while (qm_dqrr_drain_wait(&p->p, fqid, FQ_EMPTY));
+ }
+ qm_dqrr_sdqcr_set(&p->p, 0);
+
+ while (!orl_empty) {
+ /* Wait for the ORL to have been completely drained */
+ orl_empty = qm_mr_drain(&p->p, FQRL);
+ cpu_relax();
+ }
+ mcc = qm_mc_start(&p->p);
+ mcc->alterfq.fqid = fqid;
+ qm_mc_commit(&p->p, QM_MCC_VERB_ALTER_OOS);
+ if (!qm_mc_result_timeout(&p->p, &mcr)) {
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+
+ DPAA_ASSERT((mcr->verb & QM_MCR_VERB_MASK) ==
+ QM_MCR_VERB_ALTER_OOS);
+ if (mcr->result != QM_MCR_RESULT_OK) {
+ dev_err(dev, "OOS after drain fail: FQ 0x%x (0x%x)\n",
+ fqid, mcr->result);
+ ret = -EIO;
+ goto out;
+ }
+ break;
+
+ case QM_MCR_NP_STATE_RETIRED:
+ /* Send OOS Command */
+ mcc = qm_mc_start(&p->p);
+ mcc->alterfq.fqid = fqid;
+ qm_mc_commit(&p->p, QM_MCC_VERB_ALTER_OOS);
+ if (!qm_mc_result_timeout(&p->p, &mcr)) {
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+
+ DPAA_ASSERT((mcr->verb & QM_MCR_VERB_MASK) ==
+ QM_MCR_VERB_ALTER_OOS);
+ if (mcr->result) {
+ dev_err(dev, "OOS fail: FQ 0x%x (0x%x)\n",
+ fqid, mcr->result);
+ ret = -EIO;
+ goto out;
+ }
+ break;
+
+ case QM_MCR_NP_STATE_OOS:
+ /* Done */
+ break;
+
+ default:
+ ret = -EIO;
+ }
+
+out:
+ put_affine_portal();
+ return ret;
+}
+
+const struct qm_portal_config *qman_get_qm_portal_config(
+ struct qman_portal *portal)
+{
+ return portal->config;
+}
+
+struct gen_pool *qm_fqalloc; /* FQID allocator */
+struct gen_pool *qm_qpalloc; /* pool-channel allocator */
+struct gen_pool *qm_cgralloc; /* CGR ID allocator */
+
+static int qman_alloc_range(struct gen_pool *p, u32 *result, u32 cnt)
+{
+ unsigned long addr;
+
+ addr = gen_pool_alloc(p, cnt);
+ if (!addr)
+ return -ENOMEM;
+
+ *result = addr & ~DPAA_GENALLOC_OFF;
+
+ return 0;
+}
+
+int qman_alloc_fqid_range(u32 *result, u32 count)
+{
+ return qman_alloc_range(qm_fqalloc, result, count);
+}
+EXPORT_SYMBOL(qman_alloc_fqid_range);
+
+int qman_alloc_pool_range(u32 *result, u32 count)
+{
+ return qman_alloc_range(qm_qpalloc, result, count);
+}
+EXPORT_SYMBOL(qman_alloc_pool_range);
+
+int qman_alloc_cgrid_range(u32 *result, u32 count)
+{
+ return qman_alloc_range(qm_cgralloc, result, count);
+}
+EXPORT_SYMBOL(qman_alloc_cgrid_range);
+
+int qman_release_fqid(u32 fqid)
+{
+ int ret = qman_shutdown_fq(fqid);
+
+ if (ret) {
+ pr_debug("FQID %d leaked\n", fqid);
+ return ret;
+ }
+
+ gen_pool_free(qm_fqalloc, fqid | DPAA_GENALLOC_OFF, 1);
+ return 0;
+}
+EXPORT_SYMBOL(qman_release_fqid);
+
+static int qpool_cleanup(u32 qp)
+{
+ /*
+ * We query all FQDs starting from
+ * FQID 1 until we get an "invalid FQID" error, looking for non-OOS FQDs
+ * whose destination channel is the pool-channel being released.
+ * When a non-OOS FQD is found we attempt to clean it up
+ */
+ struct qman_fq fq = {
+ .fqid = QM_FQID_RANGE_START
+ };
+ int err;
+
+ do {
+ struct qm_mcr_queryfq_np np;
+
+ err = qman_query_fq_np(&fq, &np);
+ if (err)
+ /* FQID range exceeded, found no problems */
+ return 0;
+ if ((np.state & QM_MCR_NP_STATE_MASK) != QM_MCR_NP_STATE_OOS) {
+ struct qm_fqd fqd;
+
+ err = qman_query_fq(&fq, &fqd);
+ if (WARN_ON(err))
+ return 0;
+ if (qm_fqd_get_chan(&fqd) == qp) {
+ /* The channel is the FQ's target, clean it */
+ err = qman_shutdown_fq(fq.fqid);
+ if (err)
+ /*
+ * Couldn't shut down the FQ
+ * so the pool must be leaked
+ */
+ return err;
+ }
+ }
+ /* Move to the next FQID */
+ fq.fqid++;
+ } while (1);
+}
+
+int qman_release_pool(u32 qp)
+{
+ int ret;
+
+ ret = qpool_cleanup(qp);
+ if (ret) {
+ pr_debug("CHID %d leaked\n", qp);
+ return ret;
+ }
+
+ gen_pool_free(qm_qpalloc, qp | DPAA_GENALLOC_OFF, 1);
+ return 0;
+}
+EXPORT_SYMBOL(qman_release_pool);
+
+static int cgr_cleanup(u32 cgrid)
+{
+ /*
+ * query all FQDs starting from FQID 1 until we get an "invalid FQID"
+ * error, looking for non-OOS FQDs whose CGR is the CGR being released
+ */
+ struct qman_fq fq = {
+ .fqid = 1
+ };
+ int err;
+
+ do {
+ struct qm_mcr_queryfq_np np;
+
+ err = qman_query_fq_np(&fq, &np);
+ if (err)
+ /* FQID range exceeded, found no problems */
+ return 0;
+ if ((np.state & QM_MCR_NP_STATE_MASK) != QM_MCR_NP_STATE_OOS) {
+ struct qm_fqd fqd;
+
+ err = qman_query_fq(&fq, &fqd);
+ if (WARN_ON(err))
+ return 0;
+ if ((fqd.fq_ctrl & QM_FQCTRL_CGE) &&
+ fqd.cgid == cgrid) {
+ pr_err("CRGID 0x%x is being used by FQID 0x%x, CGR will be leaked\n",
+ cgrid, fq.fqid);
+ return -EIO;
+ }
+ }
+ /* Move to the next FQID */
+ fq.fqid++;
+ } while (1);
+}
+
+int qman_release_cgrid(u32 cgrid)
+{
+ int ret;
+
+ ret = cgr_cleanup(cgrid);
+ if (ret) {
+ pr_debug("CGRID %d leaked\n", cgrid);
+ return ret;
+ }
+
+ gen_pool_free(qm_cgralloc, cgrid | DPAA_GENALLOC_OFF, 1);
+ return 0;
+}
+EXPORT_SYMBOL(qman_release_cgrid);
diff --git a/drivers/soc/fsl/qbman/qman_ccsr.c b/drivers/soc/fsl/qbman/qman_ccsr.c
new file mode 100644
index 0000000..0cace9e
--- /dev/null
+++ b/drivers/soc/fsl/qbman/qman_ccsr.c
@@ -0,0 +1,808 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "qman_priv.h"
+
+u16 qman_ip_rev;
+EXPORT_SYMBOL(qman_ip_rev);
+u16 qm_channel_pool1 = QMAN_CHANNEL_POOL1;
+EXPORT_SYMBOL(qm_channel_pool1);
+
+/* Register offsets */
+#define REG_QCSP_LIO_CFG(n) (0x0000 + ((n) * 0x10))
+#define REG_QCSP_IO_CFG(n) (0x0004 + ((n) * 0x10))
+#define REG_QCSP_DD_CFG(n) (0x000c + ((n) * 0x10))
+#define REG_DD_CFG 0x0200
+#define REG_DCP_CFG(n) (0x0300 + ((n) * 0x10))
+#define REG_DCP_DD_CFG(n) (0x0304 + ((n) * 0x10))
+#define REG_DCP_DLM_AVG(n) (0x030c + ((n) * 0x10))
+#define REG_PFDR_FPC 0x0400
+#define REG_PFDR_FP_HEAD 0x0404
+#define REG_PFDR_FP_TAIL 0x0408
+#define REG_PFDR_FP_LWIT 0x0410
+#define REG_PFDR_CFG 0x0414
+#define REG_SFDR_CFG 0x0500
+#define REG_SFDR_IN_USE 0x0504
+#define REG_WQ_CS_CFG(n) (0x0600 + ((n) * 0x04))
+#define REG_WQ_DEF_ENC_WQID 0x0630
+#define REG_WQ_SC_DD_CFG(n) (0x640 + ((n) * 0x04))
+#define REG_WQ_PC_DD_CFG(n) (0x680 + ((n) * 0x04))
+#define REG_WQ_DC0_DD_CFG(n) (0x6c0 + ((n) * 0x04))
+#define REG_WQ_DC1_DD_CFG(n) (0x700 + ((n) * 0x04))
+#define REG_WQ_DCn_DD_CFG(n) (0x6c0 + ((n) * 0x40)) /* n=2,3 */
+#define REG_CM_CFG 0x0800
+#define REG_ECSR 0x0a00
+#define REG_ECIR 0x0a04
+#define REG_EADR 0x0a08
+#define REG_ECIR2 0x0a0c
+#define REG_EDATA(n) (0x0a10 + ((n) * 0x04))
+#define REG_SBEC(n) (0x0a80 + ((n) * 0x04))
+#define REG_MCR 0x0b00
+#define REG_MCP(n) (0x0b04 + ((n) * 0x04))
+#define REG_MISC_CFG 0x0be0
+#define REG_HID_CFG 0x0bf0
+#define REG_IDLE_STAT 0x0bf4
+#define REG_IP_REV_1 0x0bf8
+#define REG_IP_REV_2 0x0bfc
+#define REG_FQD_BARE 0x0c00
+#define REG_PFDR_BARE 0x0c20
+#define REG_offset_BAR 0x0004 /* relative to REG_[FQD|PFDR]_BARE */
+#define REG_offset_AR 0x0010 /* relative to REG_[FQD|PFDR]_BARE */
+#define REG_QCSP_BARE 0x0c80
+#define REG_QCSP_BAR 0x0c84
+#define REG_CI_SCHED_CFG 0x0d00
+#define REG_SRCIDR 0x0d04
+#define REG_LIODNR 0x0d08
+#define REG_CI_RLM_AVG 0x0d14
+#define REG_ERR_ISR 0x0e00
+#define REG_ERR_IER 0x0e04
+#define REG_REV3_QCSP_LIO_CFG(n) (0x1000 + ((n) * 0x10))
+#define REG_REV3_QCSP_IO_CFG(n) (0x1004 + ((n) * 0x10))
+#define REG_REV3_QCSP_DD_CFG(n) (0x100c + ((n) * 0x10))
+
+/* Assists for QMAN_MCR */
+#define MCR_INIT_PFDR 0x01000000
+#define MCR_get_rslt(v) (u8)((v) >> 24)
+#define MCR_rslt_idle(r) (!(r) || ((r) >= 0xf0))
+#define MCR_rslt_ok(r) ((r) == 0xf0)
+#define MCR_rslt_eaccess(r) ((r) == 0xf8)
+#define MCR_rslt_inval(r) ((r) == 0xff)
+
+/*
+ * Corenet initiator settings. Stash request queues are 4-deep to match cores
+ * ability to snarf. Stash priority is 3, other priorities are 2.
+ */
+#define QM_CI_SCHED_CFG_SRCCIV 4
+#define QM_CI_SCHED_CFG_SRQ_W 3
+#define QM_CI_SCHED_CFG_RW_W 2
+#define QM_CI_SCHED_CFG_BMAN_W 2
+/* write SRCCIV enable */
+#define QM_CI_SCHED_CFG_SRCCIV_EN BIT(31)
+
+/* Follows WQ_CS_CFG0-5 */
+enum qm_wq_class {
+ qm_wq_portal = 0,
+ qm_wq_pool = 1,
+ qm_wq_fman0 = 2,
+ qm_wq_fman1 = 3,
+ qm_wq_caam = 4,
+ qm_wq_pme = 5,
+ qm_wq_first = qm_wq_portal,
+ qm_wq_last = qm_wq_pme
+};
+
+/* Follows FQD_[BARE|BAR|AR] and PFDR_[BARE|BAR|AR] */
+enum qm_memory {
+ qm_memory_fqd,
+ qm_memory_pfdr
+};
+
+/* Used by all error interrupt registers except 'inhibit' */
+#define QM_EIRQ_CIDE 0x20000000 /* Corenet Initiator Data Error */
+#define QM_EIRQ_CTDE 0x10000000 /* Corenet Target Data Error */
+#define QM_EIRQ_CITT 0x08000000 /* Corenet Invalid Target Transaction */
+#define QM_EIRQ_PLWI 0x04000000 /* PFDR Low Watermark */
+#define QM_EIRQ_MBEI 0x02000000 /* Multi-bit ECC Error */
+#define QM_EIRQ_SBEI 0x01000000 /* Single-bit ECC Error */
+#define QM_EIRQ_PEBI 0x00800000 /* PFDR Enqueues Blocked Interrupt */
+#define QM_EIRQ_IFSI 0x00020000 /* Invalid FQ Flow Control State */
+#define QM_EIRQ_ICVI 0x00010000 /* Invalid Command Verb */
+#define QM_EIRQ_IDDI 0x00000800 /* Invalid Dequeue (Direct-connect) */
+#define QM_EIRQ_IDFI 0x00000400 /* Invalid Dequeue FQ */
+#define QM_EIRQ_IDSI 0x00000200 /* Invalid Dequeue Source */
+#define QM_EIRQ_IDQI 0x00000100 /* Invalid Dequeue Queue */
+#define QM_EIRQ_IECE 0x00000010 /* Invalid Enqueue Configuration */
+#define QM_EIRQ_IEOI 0x00000008 /* Invalid Enqueue Overflow */
+#define QM_EIRQ_IESI 0x00000004 /* Invalid Enqueue State */
+#define QM_EIRQ_IECI 0x00000002 /* Invalid Enqueue Channel */
+#define QM_EIRQ_IEQI 0x00000001 /* Invalid Enqueue Queue */
+
+/* QMAN_ECIR valid error bit */
+#define PORTAL_ECSR_ERR (QM_EIRQ_IEQI | QM_EIRQ_IESI | QM_EIRQ_IEOI | \
+ QM_EIRQ_IDQI | QM_EIRQ_IDSI | QM_EIRQ_IDFI | \
+ QM_EIRQ_IDDI | QM_EIRQ_ICVI | QM_EIRQ_IFSI)
+#define FQID_ECSR_ERR (QM_EIRQ_IEQI | QM_EIRQ_IECI | QM_EIRQ_IESI | \
+ QM_EIRQ_IEOI | QM_EIRQ_IDQI | QM_EIRQ_IDFI | \
+ QM_EIRQ_IFSI)
+
+struct qm_ecir {
+ u32 info; /* res[30-31], ptyp[29], pnum[24-28], fqid[0-23] */
+};
+
+static bool qm_ecir_is_dcp(const struct qm_ecir *p)
+{
+ return p->info & BIT(29);
+}
+
+static int qm_ecir_get_pnum(const struct qm_ecir *p)
+{
+ return (p->info >> 24) & 0x1f;
+}
+
+static int qm_ecir_get_fqid(const struct qm_ecir *p)
+{
+ return p->info & (BIT(24) - 1);
+}
+
+struct qm_ecir2 {
+ u32 info; /* ptyp[31], res[10-30], pnum[0-9] */
+};
+
+static bool qm_ecir2_is_dcp(const struct qm_ecir2 *p)
+{
+ return p->info & BIT(31);
+}
+
+static int qm_ecir2_get_pnum(const struct qm_ecir2 *p)
+{
+ return p->info & (BIT(10) - 1);
+}
+
+struct qm_eadr {
+ u32 info; /* memid[24-27], eadr[0-11] */
+ /* v3: memid[24-28], eadr[0-15] */
+};
+
+static int qm_eadr_get_memid(const struct qm_eadr *p)
+{
+ return (p->info >> 24) & 0xf;
+}
+
+static int qm_eadr_get_eadr(const struct qm_eadr *p)
+{
+ return p->info & (BIT(12) - 1);
+}
+
+static int qm_eadr_v3_get_memid(const struct qm_eadr *p)
+{
+ return (p->info >> 24) & 0x1f;
+}
+
+static int qm_eadr_v3_get_eadr(const struct qm_eadr *p)
+{
+ return p->info & (BIT(16) - 1);
+}
+
+struct qman_hwerr_txt {
+ u32 mask;
+ const char *txt;
+};
+
+
+static const struct qman_hwerr_txt qman_hwerr_txts[] = {
+ { QM_EIRQ_CIDE, "Corenet Initiator Data Error" },
+ { QM_EIRQ_CTDE, "Corenet Target Data Error" },
+ { QM_EIRQ_CITT, "Corenet Invalid Target Transaction" },
+ { QM_EIRQ_PLWI, "PFDR Low Watermark" },
+ { QM_EIRQ_MBEI, "Multi-bit ECC Error" },
+ { QM_EIRQ_SBEI, "Single-bit ECC Error" },
+ { QM_EIRQ_PEBI, "PFDR Enqueues Blocked Interrupt" },
+ { QM_EIRQ_ICVI, "Invalid Command Verb" },
+ { QM_EIRQ_IFSI, "Invalid Flow Control State" },
+ { QM_EIRQ_IDDI, "Invalid Dequeue (Direct-connect)" },
+ { QM_EIRQ_IDFI, "Invalid Dequeue FQ" },
+ { QM_EIRQ_IDSI, "Invalid Dequeue Source" },
+ { QM_EIRQ_IDQI, "Invalid Dequeue Queue" },
+ { QM_EIRQ_IECE, "Invalid Enqueue Configuration" },
+ { QM_EIRQ_IEOI, "Invalid Enqueue Overflow" },
+ { QM_EIRQ_IESI, "Invalid Enqueue State" },
+ { QM_EIRQ_IECI, "Invalid Enqueue Channel" },
+ { QM_EIRQ_IEQI, "Invalid Enqueue Queue" },
+};
+
+struct qman_error_info_mdata {
+ u16 addr_mask;
+ u16 bits;
+ const char *txt;
+};
+
+static const struct qman_error_info_mdata error_mdata[] = {
+ { 0x01FF, 24, "FQD cache tag memory 0" },
+ { 0x01FF, 24, "FQD cache tag memory 1" },
+ { 0x01FF, 24, "FQD cache tag memory 2" },
+ { 0x01FF, 24, "FQD cache tag memory 3" },
+ { 0x0FFF, 512, "FQD cache memory" },
+ { 0x07FF, 128, "SFDR memory" },
+ { 0x01FF, 72, "WQ context memory" },
+ { 0x00FF, 240, "CGR memory" },
+ { 0x00FF, 302, "Internal Order Restoration List memory" },
+ { 0x01FF, 256, "SW portal ring memory" },
+};
+
+#define QMAN_ERRS_TO_DISABLE (QM_EIRQ_PLWI | QM_EIRQ_PEBI)
+
+/*
+ * TODO: unimplemented registers
+ *
+ * Keeping a list here of QMan registers I have not yet covered;
+ * QCSP_DD_IHRSR, QCSP_DD_IHRFR, QCSP_DD_HASR,
+ * DCP_DD_IHRSR, DCP_DD_IHRFR, DCP_DD_HASR, CM_CFG,
+ * QMAN_EECC, QMAN_SBET, QMAN_EINJ, QMAN_SBEC0-12
+ */
+
+/* Pointer to the start of the QMan's CCSR space */
+static u32 __iomem *qm_ccsr_start;
+/* A SDQCR mask comprising all the available/visible pool channels */
+static u32 qm_pools_sdqcr;
+
+static inline u32 qm_ccsr_in(u32 offset)
+{
+ return ioread32be(qm_ccsr_start + offset/4);
+}
+
+static inline void qm_ccsr_out(u32 offset, u32 val)
+{
+ iowrite32be(val, qm_ccsr_start + offset/4);
+}
+
+u32 qm_get_pools_sdqcr(void)
+{
+ return qm_pools_sdqcr;
+}
+
+enum qm_dc_portal {
+ qm_dc_portal_fman0 = 0,
+ qm_dc_portal_fman1 = 1
+};
+
+static void qm_set_dc(enum qm_dc_portal portal, int ed, u8 sernd)
+{
+ DPAA_ASSERT(!ed || portal == qm_dc_portal_fman0 ||
+ portal == qm_dc_portal_fman1);
+ if ((qman_ip_rev & 0xFF00) >= QMAN_REV30)
+ qm_ccsr_out(REG_DCP_CFG(portal),
+ (ed ? 0x1000 : 0) | (sernd & 0x3ff));
+ else
+ qm_ccsr_out(REG_DCP_CFG(portal),
+ (ed ? 0x100 : 0) | (sernd & 0x1f));
+}
+
+static void qm_set_wq_scheduling(enum qm_wq_class wq_class,
+ u8 cs_elev, u8 csw2, u8 csw3, u8 csw4,
+ u8 csw5, u8 csw6, u8 csw7)
+{
+ qm_ccsr_out(REG_WQ_CS_CFG(wq_class), ((cs_elev & 0xff) << 24) |
+ ((csw2 & 0x7) << 20) | ((csw3 & 0x7) << 16) |
+ ((csw4 & 0x7) << 12) | ((csw5 & 0x7) << 8) |
+ ((csw6 & 0x7) << 4) | (csw7 & 0x7));
+}
+
+static void qm_set_hid(void)
+{
+ qm_ccsr_out(REG_HID_CFG, 0);
+}
+
+static void qm_set_corenet_initiator(void)
+{
+ qm_ccsr_out(REG_CI_SCHED_CFG, QM_CI_SCHED_CFG_SRCCIV_EN |
+ (QM_CI_SCHED_CFG_SRCCIV << 24) |
+ (QM_CI_SCHED_CFG_SRQ_W << 8) |
+ (QM_CI_SCHED_CFG_RW_W << 4) |
+ QM_CI_SCHED_CFG_BMAN_W);
+}
+
+static void qm_get_version(u16 *id, u8 *major, u8 *minor)
+{
+ u32 v = qm_ccsr_in(REG_IP_REV_1);
+ *id = (v >> 16);
+ *major = (v >> 8) & 0xff;
+ *minor = v & 0xff;
+}
+
+#define PFDR_AR_EN BIT(31)
+static void qm_set_memory(enum qm_memory memory, u64 ba, u32 size)
+{
+ u32 offset = (memory == qm_memory_fqd) ? REG_FQD_BARE : REG_PFDR_BARE;
+ u32 exp = ilog2(size);
+
+ /* choke if size isn't within range */
+ DPAA_ASSERT((size >= 4096) && (size <= 1024*1024*1024) &&
+ is_power_of_2(size));
+ /* choke if 'ba' has lower-alignment than 'size' */
+ DPAA_ASSERT(!(ba & (size - 1)));
+ qm_ccsr_out(offset, upper_32_bits(ba));
+ qm_ccsr_out(offset + REG_offset_BAR, lower_32_bits(ba));
+ qm_ccsr_out(offset + REG_offset_AR, PFDR_AR_EN | (exp - 1));
+}
+
+static void qm_set_pfdr_threshold(u32 th, u8 k)
+{
+ qm_ccsr_out(REG_PFDR_FP_LWIT, th & 0xffffff);
+ qm_ccsr_out(REG_PFDR_CFG, k);
+}
+
+static void qm_set_sfdr_threshold(u16 th)
+{
+ qm_ccsr_out(REG_SFDR_CFG, th & 0x3ff);
+}
+
+static int qm_init_pfdr(struct device *dev, u32 pfdr_start, u32 num)
+{
+ u8 rslt = MCR_get_rslt(qm_ccsr_in(REG_MCR));
+
+ DPAA_ASSERT(pfdr_start && !(pfdr_start & 7) && !(num & 7) && num);
+ /* Make sure the command interface is 'idle' */
+ if (!MCR_rslt_idle(rslt)) {
+ dev_crit(dev, "QMAN_MCR isn't idle");
+ WARN_ON(1);
+ }
+
+ /* Write the MCR command params then the verb */
+ qm_ccsr_out(REG_MCP(0), pfdr_start);
+ /*
+ * TODO: remove this - it's a workaround for a model bug that is
+ * corrected in more recent versions. We use the workaround until
+ * everyone has upgraded.
+ */
+ qm_ccsr_out(REG_MCP(1), pfdr_start + num - 16);
+ dma_wmb();
+ qm_ccsr_out(REG_MCR, MCR_INIT_PFDR);
+ /* Poll for the result */
+ do {
+ rslt = MCR_get_rslt(qm_ccsr_in(REG_MCR));
+ } while (!MCR_rslt_idle(rslt));
+ if (MCR_rslt_ok(rslt))
+ return 0;
+ if (MCR_rslt_eaccess(rslt))
+ return -EACCES;
+ if (MCR_rslt_inval(rslt))
+ return -EINVAL;
+ dev_crit(dev, "Unexpected result from MCR_INIT_PFDR: %02x\n", rslt);
+ return -ENODEV;
+}
+
+/*
+ * Ideally we would use the DMA API to turn rmem->base into a DMA address
+ * (especially if iommu translations ever get involved). Unfortunately, the
+ * DMA API currently does not allow mapping anything that is not backed with
+ * a struct page.
+ */
+static dma_addr_t fqd_a, pfdr_a;
+static size_t fqd_sz, pfdr_sz;
+
+static int qman_fqd(struct reserved_mem *rmem)
+{
+ fqd_a = rmem->base;
+ fqd_sz = rmem->size;
+
+ WARN_ON(!(fqd_a && fqd_sz));
+
+ return 0;
+}
+RESERVEDMEM_OF_DECLARE(qman_fqd, "fsl,qman-fqd", qman_fqd);
+
+static int qman_pfdr(struct reserved_mem *rmem)
+{
+ pfdr_a = rmem->base;
+ pfdr_sz = rmem->size;
+
+ WARN_ON(!(pfdr_a && pfdr_sz));
+
+ return 0;
+}
+RESERVEDMEM_OF_DECLARE(qman_pfdr, "fsl,qman-pfdr", qman_pfdr);
+
+static unsigned int qm_get_fqid_maxcnt(void)
+{
+ return fqd_sz / 64;
+}
+
+/*
+ * Flush this memory range from data cache so that QMAN originated
+ * transactions for this memory region could be marked non-coherent.
+ */
+static int zero_priv_mem(struct device *dev, struct device_node *node,
+ phys_addr_t addr, size_t sz)
+{
+ /* map as cacheable, non-guarded */
+ void __iomem *tmpp = ioremap_prot(addr, sz, 0);
+
+ memset_io(tmpp, 0, sz);
+ flush_dcache_range((unsigned long)tmpp,
+ (unsigned long)tmpp + sz);
+ iounmap(tmpp);
+
+ return 0;
+}
+
+static void log_edata_bits(struct device *dev, u32 bit_count)
+{
+ u32 i, j, mask = 0xffffffff;
+
+ dev_warn(dev, "ErrInt, EDATA:\n");
+ i = bit_count / 32;
+ if (bit_count % 32) {
+ i++;
+ mask = ~(mask << bit_count % 32);
+ }
+ j = 16 - i;
+ dev_warn(dev, " 0x%08x\n", qm_ccsr_in(REG_EDATA(j)) & mask);
+ j++;
+ for (; j < 16; j++)
+ dev_warn(dev, " 0x%08x\n", qm_ccsr_in(REG_EDATA(j)));
+}
+
+static void log_additional_error_info(struct device *dev, u32 isr_val,
+ u32 ecsr_val)
+{
+ struct qm_ecir ecir_val;
+ struct qm_eadr eadr_val;
+ int memid;
+
+ ecir_val.info = qm_ccsr_in(REG_ECIR);
+ /* Is portal info valid */
+ if ((qman_ip_rev & 0xFF00) >= QMAN_REV30) {
+ struct qm_ecir2 ecir2_val;
+
+ ecir2_val.info = qm_ccsr_in(REG_ECIR2);
+ if (ecsr_val & PORTAL_ECSR_ERR) {
+ dev_warn(dev, "ErrInt: %s id %d\n",
+ qm_ecir2_is_dcp(&ecir2_val) ? "DCP" : "SWP",
+ qm_ecir2_get_pnum(&ecir2_val));
+ }
+ if (ecsr_val & (FQID_ECSR_ERR | QM_EIRQ_IECE))
+ dev_warn(dev, "ErrInt: ecir.fqid 0x%x\n",
+ qm_ecir_get_fqid(&ecir_val));
+
+ if (ecsr_val & (QM_EIRQ_SBEI|QM_EIRQ_MBEI)) {
+ eadr_val.info = qm_ccsr_in(REG_EADR);
+ memid = qm_eadr_v3_get_memid(&eadr_val);
+ dev_warn(dev, "ErrInt: EADR Memory: %s, 0x%x\n",
+ error_mdata[memid].txt,
+ error_mdata[memid].addr_mask
+ & qm_eadr_v3_get_eadr(&eadr_val));
+ log_edata_bits(dev, error_mdata[memid].bits);
+ }
+ } else {
+ if (ecsr_val & PORTAL_ECSR_ERR) {
+ dev_warn(dev, "ErrInt: %s id %d\n",
+ qm_ecir_is_dcp(&ecir_val) ? "DCP" : "SWP",
+ qm_ecir_get_pnum(&ecir_val));
+ }
+ if (ecsr_val & FQID_ECSR_ERR)
+ dev_warn(dev, "ErrInt: ecir.fqid 0x%x\n",
+ qm_ecir_get_fqid(&ecir_val));
+
+ if (ecsr_val & (QM_EIRQ_SBEI|QM_EIRQ_MBEI)) {
+ eadr_val.info = qm_ccsr_in(REG_EADR);
+ memid = qm_eadr_get_memid(&eadr_val);
+ dev_warn(dev, "ErrInt: EADR Memory: %s, 0x%x\n",
+ error_mdata[memid].txt,
+ error_mdata[memid].addr_mask
+ & qm_eadr_get_eadr(&eadr_val));
+ log_edata_bits(dev, error_mdata[memid].bits);
+ }
+ }
+}
+
+static irqreturn_t qman_isr(int irq, void *ptr)
+{
+ u32 isr_val, ier_val, ecsr_val, isr_mask, i;
+ struct device *dev = ptr;
+
+ ier_val = qm_ccsr_in(REG_ERR_IER);
+ isr_val = qm_ccsr_in(REG_ERR_ISR);
+ ecsr_val = qm_ccsr_in(REG_ECSR);
+ isr_mask = isr_val & ier_val;
+
+ if (!isr_mask)
+ return IRQ_NONE;
+
+ for (i = 0; i < ARRAY_SIZE(qman_hwerr_txts); i++) {
+ if (qman_hwerr_txts[i].mask & isr_mask) {
+ dev_err_ratelimited(dev, "ErrInt: %s\n",
+ qman_hwerr_txts[i].txt);
+ if (qman_hwerr_txts[i].mask & ecsr_val) {
+ log_additional_error_info(dev, isr_mask,
+ ecsr_val);
+ /* Re-arm error capture registers */
+ qm_ccsr_out(REG_ECSR, ecsr_val);
+ }
+ if (qman_hwerr_txts[i].mask & QMAN_ERRS_TO_DISABLE) {
+ dev_dbg(dev, "Disabling error 0x%x\n",
+ qman_hwerr_txts[i].mask);
+ ier_val &= ~qman_hwerr_txts[i].mask;
+ qm_ccsr_out(REG_ERR_IER, ier_val);
+ }
+ }
+ }
+ qm_ccsr_out(REG_ERR_ISR, isr_val);
+
+ return IRQ_HANDLED;
+}
+
+static int qman_init_ccsr(struct device *dev)
+{
+ int i, err;
+
+ /* FQD memory */
+ qm_set_memory(qm_memory_fqd, fqd_a, fqd_sz);
+ /* PFDR memory */
+ qm_set_memory(qm_memory_pfdr, pfdr_a, pfdr_sz);
+ err = qm_init_pfdr(dev, 8, pfdr_sz / 64 - 8);
+ if (err)
+ return err;
+ /* thresholds */
+ qm_set_pfdr_threshold(512, 64);
+ qm_set_sfdr_threshold(128);
+ /* clear stale PEBI bit from interrupt status register */
+ qm_ccsr_out(REG_ERR_ISR, QM_EIRQ_PEBI);
+ /* corenet initiator settings */
+ qm_set_corenet_initiator();
+ /* HID settings */
+ qm_set_hid();
+ /* Set scheduling weights to defaults */
+ for (i = qm_wq_first; i <= qm_wq_last; i++)
+ qm_set_wq_scheduling(i, 0, 0, 0, 0, 0, 0, 0);
+ /* We are not prepared to accept ERNs for hardware enqueues */
+ qm_set_dc(qm_dc_portal_fman0, 1, 0);
+ qm_set_dc(qm_dc_portal_fman1, 1, 0);
+ return 0;
+}
+
+#define LIO_CFG_LIODN_MASK 0x0fff0000
+void qman_liodn_fixup(u16 channel)
+{
+ static int done;
+ static u32 liodn_offset;
+ u32 before, after;
+ int idx = channel - QM_CHANNEL_SWPORTAL0;
+
+ if ((qman_ip_rev & 0xFF00) >= QMAN_REV30)
+ before = qm_ccsr_in(REG_REV3_QCSP_LIO_CFG(idx));
+ else
+ before = qm_ccsr_in(REG_QCSP_LIO_CFG(idx));
+ if (!done) {
+ liodn_offset = before & LIO_CFG_LIODN_MASK;
+ done = 1;
+ return;
+ }
+ after = (before & (~LIO_CFG_LIODN_MASK)) | liodn_offset;
+ if ((qman_ip_rev & 0xFF00) >= QMAN_REV30)
+ qm_ccsr_out(REG_REV3_QCSP_LIO_CFG(idx), after);
+ else
+ qm_ccsr_out(REG_QCSP_LIO_CFG(idx), after);
+}
+
+#define IO_CFG_SDEST_MASK 0x00ff0000
+void qman_set_sdest(u16 channel, unsigned int cpu_idx)
+{
+ int idx = channel - QM_CHANNEL_SWPORTAL0;
+ u32 before, after;
+
+ if ((qman_ip_rev & 0xFF00) >= QMAN_REV30) {
+ before = qm_ccsr_in(REG_REV3_QCSP_IO_CFG(idx));
+ /* Each pair of vcpu share the same SRQ(SDEST) */
+ cpu_idx /= 2;
+ after = (before & (~IO_CFG_SDEST_MASK)) | (cpu_idx << 16);
+ qm_ccsr_out(REG_REV3_QCSP_IO_CFG(idx), after);
+ } else {
+ before = qm_ccsr_in(REG_QCSP_IO_CFG(idx));
+ after = (before & (~IO_CFG_SDEST_MASK)) | (cpu_idx << 16);
+ qm_ccsr_out(REG_QCSP_IO_CFG(idx), after);
+ }
+}
+
+static int qman_resource_init(struct device *dev)
+{
+ int pool_chan_num, cgrid_num;
+ int ret, i;
+
+ switch (qman_ip_rev >> 8) {
+ case 1:
+ pool_chan_num = 15;
+ cgrid_num = 256;
+ break;
+ case 2:
+ pool_chan_num = 3;
+ cgrid_num = 64;
+ break;
+ case 3:
+ pool_chan_num = 15;
+ cgrid_num = 256;
+ break;
+ default:
+ return -ENODEV;
+ }
+
+ ret = gen_pool_add(qm_qpalloc, qm_channel_pool1 | DPAA_GENALLOC_OFF,
+ pool_chan_num, -1);
+ if (ret) {
+ dev_err(dev, "Failed to seed pool channels (%d)\n", ret);
+ return ret;
+ }
+
+ ret = gen_pool_add(qm_cgralloc, DPAA_GENALLOC_OFF, cgrid_num, -1);
+ if (ret) {
+ dev_err(dev, "Failed to seed CGRID range (%d)\n", ret);
+ return ret;
+ }
+
+ /* parse pool channels into the SDQCR mask */
+ for (i = 0; i < cgrid_num; i++)
+ qm_pools_sdqcr |= QM_SDQCR_CHANNELS_POOL_CONV(i);
+
+ ret = gen_pool_add(qm_fqalloc, QM_FQID_RANGE_START | DPAA_GENALLOC_OFF,
+ qm_get_fqid_maxcnt() - QM_FQID_RANGE_START, -1);
+ if (ret) {
+ dev_err(dev, "Failed to seed FQID range (%d)\n", ret);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int fsl_qman_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct device_node *node = dev->of_node;
+ struct resource *res;
+ int ret, err_irq;
+ u16 id;
+ u8 major, minor;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res) {
+ dev_err(dev, "Can't get %s property 'IORESOURCE_MEM'\n",
+ node->full_name);
+ return -ENXIO;
+ }
+ qm_ccsr_start = devm_ioremap(dev, res->start, resource_size(res));
+ if (!qm_ccsr_start)
+ return -ENXIO;
+
+ qm_get_version(&id, &major, &minor);
+ if (major == 1 && minor == 0) {
+ dev_err(dev, "Rev1.0 on P4080 rev1 is not supported!\n");
+ return -ENODEV;
+ } else if (major == 1 && minor == 1)
+ qman_ip_rev = QMAN_REV11;
+ else if (major == 1 && minor == 2)
+ qman_ip_rev = QMAN_REV12;
+ else if (major == 2 && minor == 0)
+ qman_ip_rev = QMAN_REV20;
+ else if (major == 3 && minor == 0)
+ qman_ip_rev = QMAN_REV30;
+ else if (major == 3 && minor == 1)
+ qman_ip_rev = QMAN_REV31;
+ else {
+ dev_err(dev, "Unknown QMan version\n");
+ return -ENODEV;
+ }
+
+ if ((qman_ip_rev & 0xff00) >= QMAN_REV30)
+ qm_channel_pool1 = QMAN_CHANNEL_POOL1_REV3;
+
+ ret = zero_priv_mem(dev, node, fqd_a, fqd_sz);
+ WARN_ON(ret);
+ if (ret)
+ return -ENODEV;
+
+ ret = qman_init_ccsr(dev);
+ if (ret) {
+ dev_err(dev, "CCSR setup failed\n");
+ return ret;
+ }
+
+ err_irq = platform_get_irq(pdev, 0);
+ if (err_irq <= 0) {
+ dev_info(dev, "Can't get %s property 'interrupts'\n",
+ node->full_name);
+ return -ENODEV;
+ }
+ ret = devm_request_irq(dev, err_irq, qman_isr, IRQF_SHARED, "qman-err",
+ dev);
+ if (ret) {
+ dev_err(dev, "devm_request_irq() failed %d for '%s'\n",
+ ret, node->full_name);
+ return ret;
+ }
+
+ /*
+ * Write-to-clear any stale bits, (eg. starvation being asserted prior
+ * to resource allocation during driver init).
+ */
+ qm_ccsr_out(REG_ERR_ISR, 0xffffffff);
+ /* Enable Error Interrupts */
+ qm_ccsr_out(REG_ERR_IER, 0xffffffff);
+
+ qm_fqalloc = devm_gen_pool_create(dev, 0, -1, "qman-fqalloc");
+ if (IS_ERR(qm_fqalloc)) {
+ ret = PTR_ERR(qm_fqalloc);
+ dev_err(dev, "qman-fqalloc pool init failed (%d)\n", ret);
+ return ret;
+ }
+
+ qm_qpalloc = devm_gen_pool_create(dev, 0, -1, "qman-qpalloc");
+ if (IS_ERR(qm_qpalloc)) {
+ ret = PTR_ERR(qm_qpalloc);
+ dev_err(dev, "qman-qpalloc pool init failed (%d)\n", ret);
+ return ret;
+ }
+
+ qm_cgralloc = devm_gen_pool_create(dev, 0, -1, "qman-cgralloc");
+ if (IS_ERR(qm_cgralloc)) {
+ ret = PTR_ERR(qm_cgralloc);
+ dev_err(dev, "qman-cgralloc pool init failed (%d)\n", ret);
+ return ret;
+ }
+
+ ret = qman_resource_init(dev);
+ if (ret)
+ return ret;
+
+ ret = qman_alloc_fq_table(qm_get_fqid_maxcnt());
+ if (ret)
+ return ret;
+
+ ret = qman_wq_alloc();
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+static const struct of_device_id fsl_qman_ids[] = {
+ {
+ .compatible = "fsl,qman",
+ },
+ {}
+};
+
+static struct platform_driver fsl_qman_driver = {
+ .driver = {
+ .name = KBUILD_MODNAME,
+ .of_match_table = fsl_qman_ids,
+ .suppress_bind_attrs = true,
+ },
+ .probe = fsl_qman_probe,
+};
+
+builtin_platform_driver(fsl_qman_driver);
diff --git a/drivers/soc/fsl/qbman/qman_portal.c b/drivers/soc/fsl/qbman/qman_portal.c
new file mode 100644
index 0000000..1486143
--- /dev/null
+++ b/drivers/soc/fsl/qbman/qman_portal.c
@@ -0,0 +1,355 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "qman_priv.h"
+
+/* Enable portal interupts (as opposed to polling mode) */
+#define CONFIG_FSL_DPA_PIRQ_SLOW 1
+#define CONFIG_FSL_DPA_PIRQ_FAST 1
+
+static struct cpumask portal_cpus;
+/* protect qman global registers and global data shared among portals */
+static DEFINE_SPINLOCK(qman_lock);
+
+static void portal_set_cpu(struct qm_portal_config *pcfg, int cpu)
+{
+#ifdef CONFIG_FSL_PAMU
+ struct device *dev = pcfg->dev;
+ int window_count = 1;
+ struct iommu_domain_geometry geom_attr;
+ struct pamu_stash_attribute stash_attr;
+ int ret;
+
+ pcfg->iommu_domain = iommu_domain_alloc(&platform_bus_type);
+ if (!pcfg->iommu_domain) {
+ dev_err(dev, "%s(): iommu_domain_alloc() failed", __func__);
+ goto no_iommu;
+ }
+ geom_attr.aperture_start = 0;
+ geom_attr.aperture_end =
+ ((dma_addr_t)1 << min(8 * sizeof(dma_addr_t), (size_t)36)) - 1;
+ geom_attr.force_aperture = true;
+ ret = iommu_domain_set_attr(pcfg->iommu_domain, DOMAIN_ATTR_GEOMETRY,
+ &geom_attr);
+ if (ret < 0) {
+ dev_err(dev, "%s(): iommu_domain_set_attr() = %d", __func__,
+ ret);
+ goto out_domain_free;
+ }
+ ret = iommu_domain_set_attr(pcfg->iommu_domain, DOMAIN_ATTR_WINDOWS,
+ &window_count);
+ if (ret < 0) {
+ dev_err(dev, "%s(): iommu_domain_set_attr() = %d", __func__,
+ ret);
+ goto out_domain_free;
+ }
+ stash_attr.cpu = cpu;
+ stash_attr.cache = PAMU_ATTR_CACHE_L1;
+ ret = iommu_domain_set_attr(pcfg->iommu_domain,
+ DOMAIN_ATTR_FSL_PAMU_STASH,
+ &stash_attr);
+ if (ret < 0) {
+ dev_err(dev, "%s(): iommu_domain_set_attr() = %d",
+ __func__, ret);
+ goto out_domain_free;
+ }
+ ret = iommu_domain_window_enable(pcfg->iommu_domain, 0, 0, 1ULL << 36,
+ IOMMU_READ | IOMMU_WRITE);
+ if (ret < 0) {
+ dev_err(dev, "%s(): iommu_domain_window_enable() = %d",
+ __func__, ret);
+ goto out_domain_free;
+ }
+ ret = iommu_attach_device(pcfg->iommu_domain, dev);
+ if (ret < 0) {
+ dev_err(dev, "%s(): iommu_device_attach() = %d", __func__,
+ ret);
+ goto out_domain_free;
+ }
+ ret = iommu_domain_set_attr(pcfg->iommu_domain,
+ DOMAIN_ATTR_FSL_PAMU_ENABLE,
+ &window_count);
+ if (ret < 0) {
+ dev_err(dev, "%s(): iommu_domain_set_attr() = %d", __func__,
+ ret);
+ goto out_detach_device;
+ }
+
+no_iommu:
+#endif
+ qman_set_sdest(pcfg->channel, cpu);
+
+ return;
+
+#ifdef CONFIG_FSL_PAMU
+out_detach_device:
+ iommu_detach_device(pcfg->iommu_domain, NULL);
+out_domain_free:
+ iommu_domain_free(pcfg->iommu_domain);
+ pcfg->iommu_domain = NULL;
+#endif
+}
+
+static struct qman_portal *init_pcfg(struct qm_portal_config *pcfg)
+{
+ struct qman_portal *p;
+ u32 irq_sources = 0;
+
+ /* We need the same LIODN offset for all portals */
+ qman_liodn_fixup(pcfg->channel);
+
+ pcfg->iommu_domain = NULL;
+ portal_set_cpu(pcfg, pcfg->cpu);
+
+ p = qman_create_affine_portal(pcfg, NULL);
+ if (!p) {
+ dev_crit(pcfg->dev, "%s: Portal failure on cpu %d\n",
+ __func__, pcfg->cpu);
+ return NULL;
+ }
+
+ /* Determine what should be interrupt-vs-poll driven */
+#ifdef CONFIG_FSL_DPA_PIRQ_SLOW
+ irq_sources |= QM_PIRQ_EQCI | QM_PIRQ_EQRI | QM_PIRQ_MRI |
+ QM_PIRQ_CSCI;
+#endif
+#ifdef CONFIG_FSL_DPA_PIRQ_FAST
+ irq_sources |= QM_PIRQ_DQRI;
+#endif
+ qman_p_irqsource_add(p, irq_sources);
+
+ spin_lock(&qman_lock);
+ if (cpumask_equal(&portal_cpus, cpu_possible_mask)) {
+ /* all assigned portals are initialized now */
+ qman_init_cgr_all();
+ }
+ spin_unlock(&qman_lock);
+
+ dev_info(pcfg->dev, "Portal initialised, cpu %d\n", pcfg->cpu);
+
+ return p;
+}
+
+static void qman_portal_update_sdest(const struct qm_portal_config *pcfg,
+ unsigned int cpu)
+{
+#ifdef CONFIG_FSL_PAMU /* TODO */
+ struct pamu_stash_attribute stash_attr;
+ int ret;
+
+ if (pcfg->iommu_domain) {
+ stash_attr.cpu = cpu;
+ stash_attr.cache = PAMU_ATTR_CACHE_L1;
+ ret = iommu_domain_set_attr(pcfg->iommu_domain,
+ DOMAIN_ATTR_FSL_PAMU_STASH, &stash_attr);
+ if (ret < 0) {
+ dev_err(pcfg->dev,
+ "Failed to update pamu stash setting\n");
+ return;
+ }
+ }
+#endif
+ qman_set_sdest(pcfg->channel, cpu);
+}
+
+static void qman_offline_cpu(unsigned int cpu)
+{
+ struct qman_portal *p;
+ const struct qm_portal_config *pcfg;
+
+ p = affine_portals[cpu];
+ if (p) {
+ pcfg = qman_get_qm_portal_config(p);
+ if (pcfg) {
+ irq_set_affinity(pcfg->irq, cpumask_of(0));
+ qman_portal_update_sdest(pcfg, 0);
+ }
+ }
+}
+
+static void qman_online_cpu(unsigned int cpu)
+{
+ struct qman_portal *p;
+ const struct qm_portal_config *pcfg;
+
+ p = affine_portals[cpu];
+ if (p) {
+ pcfg = qman_get_qm_portal_config(p);
+ if (pcfg) {
+ irq_set_affinity(pcfg->irq, cpumask_of(cpu));
+ qman_portal_update_sdest(pcfg, cpu);
+ }
+ }
+}
+
+static int qman_hotplug_cpu_callback(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
+{
+ unsigned int cpu = (unsigned long)hcpu;
+
+ switch (action) {
+ case CPU_ONLINE:
+ case CPU_ONLINE_FROZEN:
+ qman_online_cpu(cpu);
+ break;
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ qman_offline_cpu(cpu);
+ default:
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block qman_hotplug_cpu_notifier = {
+ .notifier_call = qman_hotplug_cpu_callback,
+};
+
+static int qman_portal_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct device_node *node = dev->of_node;
+ struct qm_portal_config *pcfg;
+ struct resource *addr_phys[2];
+ const u32 *channel;
+ void __iomem *va;
+ int irq, len, cpu;
+
+ pcfg = devm_kmalloc(dev, sizeof(*pcfg), GFP_KERNEL);
+ if (!pcfg)
+ return -ENOMEM;
+
+ pcfg->dev = dev;
+
+ addr_phys[0] = platform_get_resource(pdev, IORESOURCE_MEM,
+ DPAA_PORTAL_CE);
+ if (!addr_phys[0]) {
+ dev_err(dev, "Can't get %s property 'reg::CE'\n",
+ node->full_name);
+ return -ENXIO;
+ }
+
+ addr_phys[1] = platform_get_resource(pdev, IORESOURCE_MEM,
+ DPAA_PORTAL_CI);
+ if (!addr_phys[1]) {
+ dev_err(dev, "Can't get %s property 'reg::CI'\n",
+ node->full_name);
+ return -ENXIO;
+ }
+
+ channel = of_get_property(node, "cell-index", &len);
+ if (!channel || (len != 4)) {
+ dev_err(dev, "Can't get %s property 'cell-index'\n",
+ node->full_name);
+ return -ENXIO;
+ }
+ pcfg->channel = *channel;
+ pcfg->cpu = -1;
+ irq = platform_get_irq(pdev, 0);
+ if (irq <= 0) {
+ dev_err(dev, "Can't get %s IRQ\n", node->full_name);
+ return -ENXIO;
+ }
+ pcfg->irq = irq;
+
+ va = ioremap_prot(addr_phys[0]->start, resource_size(addr_phys[0]), 0);
+ if (!va)
+ goto err_ioremap1;
+
+ pcfg->addr_virt[DPAA_PORTAL_CE] = va;
+
+ va = ioremap_prot(addr_phys[1]->start, resource_size(addr_phys[1]),
+ _PAGE_GUARDED | _PAGE_NO_CACHE);
+ if (!va)
+ goto err_ioremap2;
+
+ pcfg->addr_virt[DPAA_PORTAL_CI] = va;
+
+ pcfg->pools = qm_get_pools_sdqcr();
+
+ spin_lock(&qman_lock);
+ cpu = cpumask_next_zero(-1, &portal_cpus);
+ if (cpu >= nr_cpu_ids) {
+ /* unassigned portal, skip init */
+ spin_unlock(&qman_lock);
+ return 0;
+ }
+
+ cpumask_set_cpu(cpu, &portal_cpus);
+ spin_unlock(&qman_lock);
+ pcfg->cpu = cpu;
+
+ if (!init_pcfg(pcfg))
+ goto err_ioremap2;
+
+ /* clear irq affinity if assigned cpu is offline */
+ if (!cpu_online(cpu))
+ qman_offline_cpu(cpu);
+
+ return 0;
+
+err_ioremap2:
+ iounmap(pcfg->addr_virt[DPAA_PORTAL_CE]);
+err_ioremap1:
+ dev_err(dev, "ioremap failed\n");
+ return -ENXIO;
+}
+
+static const struct of_device_id qman_portal_ids[] = {
+ {
+ .compatible = "fsl,qman-portal",
+ },
+ {}
+};
+MODULE_DEVICE_TABLE(of, qman_portal_ids);
+
+static struct platform_driver qman_portal_driver = {
+ .driver = {
+ .name = KBUILD_MODNAME,
+ .of_match_table = qman_portal_ids,
+ },
+ .probe = qman_portal_probe,
+};
+
+static int __init qman_portal_driver_register(struct platform_driver *drv)
+{
+ int ret;
+
+ ret = platform_driver_register(drv);
+ if (ret < 0)
+ return ret;
+
+ register_hotcpu_notifier(&qman_hotplug_cpu_notifier);
+
+ return 0;
+}
+
+module_driver(qman_portal_driver,
+ qman_portal_driver_register, platform_driver_unregister);
diff --git a/drivers/soc/fsl/qbman/qman_priv.h b/drivers/soc/fsl/qbman/qman_priv.h
new file mode 100644
index 0000000..5cf821e
--- /dev/null
+++ b/drivers/soc/fsl/qbman/qman_priv.h
@@ -0,0 +1,371 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include "dpaa_sys.h"
+
+#include <soc/fsl/qman.h>
+#include <linux/iommu.h>
+
+#if defined(CONFIG_FSL_PAMU)
+#include <asm/fsl_pamu_stash.h>
+#endif
+
+struct qm_mcr_querywq {
+ u8 verb;
+ u8 result;
+ u16 channel_wq; /* ignores wq (3 lsbits): _res[0-2] */
+ u8 __reserved[28];
+ u32 wq_len[8];
+} __packed;
+
+static inline u16 qm_mcr_querywq_get_chan(const struct qm_mcr_querywq *wq)
+{
+ return wq->channel_wq >> 3;
+}
+
+struct __qm_mcr_querycongestion {
+ u32 state[8];
+};
+
+/* "Query Congestion Group State" */
+struct qm_mcr_querycongestion {
+ u8 verb;
+ u8 result;
+ u8 __reserved[30];
+ /* Access this struct using qman_cgrs_get() */
+ struct __qm_mcr_querycongestion state;
+} __packed;
+
+/* "Query CGR" */
+struct qm_mcr_querycgr {
+ u8 verb;
+ u8 result;
+ u16 __reserved1;
+ struct __qm_mc_cgr cgr; /* CGR fields */
+ u8 __reserved2[6];
+ u8 i_bcnt_hi; /* high 8-bits of 40-bit "Instant" */
+ u32 i_bcnt_lo; /* low 32-bits of 40-bit */
+ u8 __reserved3[3];
+ u8 a_bcnt_hi; /* high 8-bits of 40-bit "Average" */
+ u32 a_bcnt_lo; /* low 32-bits of 40-bit */
+ u32 cscn_targ_swp[4];
+} __packed;
+
+static inline u64 qm_mcr_querycgr_i_get64(const struct qm_mcr_querycgr *q)
+{
+ return ((u64)q->i_bcnt_hi << 32) | (u64)q->i_bcnt_lo;
+}
+static inline u64 qm_mcr_querycgr_a_get64(const struct qm_mcr_querycgr *q)
+{
+ return ((u64)q->a_bcnt_hi << 32) | (u64)q->a_bcnt_lo;
+}
+
+/* "Query FQ Non-Programmable Fields" */
+struct qm_mcc_queryfq_np {
+ u8 _ncw_verb;
+ u8 __reserved1[3];
+ u32 fqid; /* 24-bit */
+ u8 __reserved2[56];
+} __packed;
+
+struct qm_mcr_queryfq_np {
+ u8 verb;
+ u8 result;
+ u8 __reserved1;
+ u8 state; /* QM_MCR_NP_STATE_*** */
+ u32 fqd_link; /* 24-bit, _res2[24-31] */
+ u16 odp_seq; /* 14-bit, _res3[14-15] */
+ u16 orp_nesn; /* 14-bit, _res4[14-15] */
+ u16 orp_ea_hseq; /* 15-bit, _res5[15] */
+ u16 orp_ea_tseq; /* 15-bit, _res6[15] */
+ u32 orp_ea_hptr; /* 24-bit, _res7[24-31] */
+ u32 orp_ea_tptr; /* 24-bit, _res8[24-31] */
+ u32 pfdr_hptr; /* 24-bit, _res9[24-31] */
+ u32 pfdr_tptr; /* 24-bit, _res10[24-31] */
+ u8 __reserved2[5];
+ u8 is; /* 1-bit, _res12[1-7] */
+ u16 ics_surp;
+ u32 byte_cnt;
+ u32 frm_cnt; /* 24-bit, _res13[24-31] */
+ u32 __reserved3;
+ u16 ra1_sfdr; /* QM_MCR_NP_RA1_*** */
+ u16 ra2_sfdr; /* QM_MCR_NP_RA2_*** */
+ u16 __reserved4;
+ u16 od1_sfdr; /* QM_MCR_NP_OD1_*** */
+ u16 od2_sfdr; /* QM_MCR_NP_OD2_*** */
+ u16 od3_sfdr; /* QM_MCR_NP_OD3_*** */
+} __packed;
+
+#define QM_MCR_NP_STATE_FE 0x10
+#define QM_MCR_NP_STATE_R 0x08
+#define QM_MCR_NP_STATE_MASK 0x07 /* Reads FQD::STATE; */
+#define QM_MCR_NP_STATE_OOS 0x00
+#define QM_MCR_NP_STATE_RETIRED 0x01
+#define QM_MCR_NP_STATE_TEN_SCHED 0x02
+#define QM_MCR_NP_STATE_TRU_SCHED 0x03
+#define QM_MCR_NP_STATE_PARKED 0x04
+#define QM_MCR_NP_STATE_ACTIVE 0x05
+#define QM_MCR_NP_PTR_MASK 0x07ff /* for RA[12] & OD[123] */
+#define QM_MCR_NP_RA1_NRA(v) (((v) >> 14) & 0x3) /* FQD::NRA */
+#define QM_MCR_NP_RA2_IT(v) (((v) >> 14) & 0x1) /* FQD::IT */
+#define QM_MCR_NP_OD1_NOD(v) (((v) >> 14) & 0x3) /* FQD::NOD */
+#define QM_MCR_NP_OD3_NPC(v) (((v) >> 14) & 0x3) /* FQD::NPC */
+
+enum qm_mcr_queryfq_np_masks {
+ qm_mcr_fqd_link_mask = BIT(24)-1,
+ qm_mcr_odp_seq_mask = BIT(14)-1,
+ qm_mcr_orp_nesn_mask = BIT(14)-1,
+ qm_mcr_orp_ea_hseq_mask = BIT(15)-1,
+ qm_mcr_orp_ea_tseq_mask = BIT(15)-1,
+ qm_mcr_orp_ea_hptr_mask = BIT(24)-1,
+ qm_mcr_orp_ea_tptr_mask = BIT(24)-1,
+ qm_mcr_pfdr_hptr_mask = BIT(24)-1,
+ qm_mcr_pfdr_tptr_mask = BIT(24)-1,
+ qm_mcr_is_mask = BIT(1)-1,
+ qm_mcr_frm_cnt_mask = BIT(24)-1,
+};
+#define qm_mcr_np_get(np, field) \
+ ((np)->field & (qm_mcr_##field##_mask))
+
+/* Congestion Groups */
+
+/*
+ * This wrapper represents a bit-array for the state of the 256 QMan congestion
+ * groups. Is also used as a *mask* for congestion groups, eg. so we ignore
+ * those that don't concern us. We harness the structure and accessor details
+ * already used in the management command to query congestion groups.
+ */
+#define CGR_BITS_PER_WORD 5
+#define CGR_WORD(x) ((x) >> CGR_BITS_PER_WORD)
+#define CGR_BIT(x) (BIT(31) >> ((x) & 0x1f))
+#define CGR_NUM (sizeof(struct __qm_mcr_querycongestion) << 3)
+
+struct qman_cgrs {
+ struct __qm_mcr_querycongestion q;
+};
+
+static inline void qman_cgrs_init(struct qman_cgrs *c)
+{
+ memset(c, 0, sizeof(*c));
+}
+
+static inline void qman_cgrs_fill(struct qman_cgrs *c)
+{
+ memset(c, 0xff, sizeof(*c));
+}
+
+static inline int qman_cgrs_get(struct qman_cgrs *c, u8 cgr)
+{
+ return c->q.state[CGR_WORD(cgr)] & CGR_BIT(cgr);
+}
+
+static inline void qman_cgrs_cp(struct qman_cgrs *dest,
+ const struct qman_cgrs *src)
+{
+ *dest = *src;
+}
+
+static inline void qman_cgrs_and(struct qman_cgrs *dest,
+ const struct qman_cgrs *a, const struct qman_cgrs *b)
+{
+ int ret;
+ u32 *_d = dest->q.state;
+ const u32 *_a = a->q.state;
+ const u32 *_b = b->q.state;
+
+ for (ret = 0; ret < 8; ret++)
+ *_d++ = *_a++ & *_b++;
+}
+
+static inline void qman_cgrs_xor(struct qman_cgrs *dest,
+ const struct qman_cgrs *a, const struct qman_cgrs *b)
+{
+ int ret;
+ u32 *_d = dest->q.state;
+ const u32 *_a = a->q.state;
+ const u32 *_b = b->q.state;
+
+ for (ret = 0; ret < 8; ret++)
+ *_d++ = *_a++ ^ *_b++;
+}
+
+void qman_init_cgr_all(void);
+
+struct qm_portal_config {
+ /*
+ * Corenet portal addresses;
+ * [0]==cache-enabled, [1]==cache-inhibited.
+ */
+ void __iomem *addr_virt[2];
+ struct device *dev;
+ struct iommu_domain *iommu_domain;
+ /* Allow these to be joined in lists */
+ struct list_head list;
+ /* User-visible portal configuration settings */
+ /* portal is affined to this cpu */
+ int cpu;
+ /* portal interrupt line */
+ int irq;
+ /*
+ * the portal's dedicated channel id, used initialising
+ * frame queues to target this portal when scheduled
+ */
+ u16 channel;
+ /*
+ * mask of pool channels this portal has dequeue access to
+ * (using QM_SDQCR_CHANNELS_POOL(n) for the bitmask)
+ */
+ u32 pools;
+};
+
+/* Revision info (for errata and feature handling) */
+#define QMAN_REV11 0x0101
+#define QMAN_REV12 0x0102
+#define QMAN_REV20 0x0200
+#define QMAN_REV30 0x0300
+#define QMAN_REV31 0x0301
+extern u16 qman_ip_rev; /* 0 if uninitialised, otherwise QMAN_REVx */
+
+#define QM_FQID_RANGE_START 1 /* FQID 0 reserved for internal use */
+extern struct gen_pool *qm_fqalloc; /* FQID allocator */
+extern struct gen_pool *qm_qpalloc; /* pool-channel allocator */
+extern struct gen_pool *qm_cgralloc; /* CGR ID allocator */
+u32 qm_get_pools_sdqcr(void);
+
+int qman_wq_alloc(void);
+void qman_liodn_fixup(u16 channel);
+void qman_set_sdest(u16 channel, unsigned int cpu_idx);
+
+struct qman_portal *qman_create_affine_portal(
+ const struct qm_portal_config *config,
+ const struct qman_cgrs *cgrs);
+const struct qm_portal_config *qman_destroy_affine_portal(void);
+
+/*
+ * qman_query_fq - Queries FQD fields (via h/w query command)
+ * @fq: the frame queue object to be queried
+ * @fqd: storage for the queried FQD fields
+ */
+int qman_query_fq(struct qman_fq *fq, struct qm_fqd *fqd);
+
+/*
+ * For qman_volatile_dequeue(); Choose one PRECEDENCE. EXACT is optional. Use
+ * NUMFRAMES(n) (6-bit) or NUMFRAMES_TILLEMPTY to fill in the frame-count. Use
+ * FQID(n) to fill in the frame queue ID.
+ */
+#define QM_VDQCR_PRECEDENCE_VDQCR 0x0
+#define QM_VDQCR_PRECEDENCE_SDQCR 0x80000000
+#define QM_VDQCR_EXACT 0x40000000
+#define QM_VDQCR_NUMFRAMES_MASK 0x3f000000
+#define QM_VDQCR_NUMFRAMES_SET(n) (((n) & 0x3f) << 24)
+#define QM_VDQCR_NUMFRAMES_GET(n) (((n) >> 24) & 0x3f)
+#define QM_VDQCR_NUMFRAMES_TILLEMPTY QM_VDQCR_NUMFRAMES_SET(0)
+
+#define QMAN_VOLATILE_FLAG_WAIT 0x00000001 /* wait if VDQCR is in use */
+#define QMAN_VOLATILE_FLAG_WAIT_INT 0x00000002 /* if wait, interruptible? */
+#define QMAN_VOLATILE_FLAG_FINISH 0x00000004 /* wait till VDQCR completes */
+
+/*
+ * qman_volatile_dequeue - Issue a volatile dequeue command
+ * @fq: the frame queue object to dequeue from
+ * @flags: a bit-mask of QMAN_VOLATILE_FLAG_*** options
+ * @vdqcr: bit mask of QM_VDQCR_*** options, as per qm_dqrr_vdqcr_set()
+ *
+ * Attempts to lock access to the portal's VDQCR volatile dequeue functionality.
+ * The function will block and sleep if QMAN_VOLATILE_FLAG_WAIT is specified and
+ * the VDQCR is already in use, otherwise returns non-zero for failure. If
+ * QMAN_VOLATILE_FLAG_FINISH is specified, the function will only return once
+ * the VDQCR command has finished executing (ie. once the callback for the last
+ * DQRR entry resulting from the VDQCR command has been called). If not using
+ * the FINISH flag, completion can be determined either by detecting the
+ * presence of the QM_DQRR_STAT_UNSCHEDULED and QM_DQRR_STAT_DQCR_EXPIRED bits
+ * in the "stat" parameter passed to the FQ's dequeue callback, or by waiting
+ * for the QMAN_FQ_STATE_VDQCR bit to disappear.
+ */
+int qman_volatile_dequeue(struct qman_fq *fq, u32 flags, u32 vdqcr);
+
+int qman_alloc_fq_table(u32 num_fqids);
+
+/* QMan s/w corenet portal, low-level i/face */
+
+/*
+ * For qm_dqrr_sdqcr_set(); Choose one SOURCE. Choose one COUNT. Choose one
+ * dequeue TYPE. Choose TOKEN (8-bit).
+ * If SOURCE == CHANNELS,
+ * Choose CHANNELS_DEDICATED and/or CHANNELS_POOL(n).
+ * You can choose DEDICATED_PRECEDENCE if the portal channel should have
+ * priority.
+ * If SOURCE == SPECIFICWQ,
+ * Either select the work-queue ID with SPECIFICWQ_WQ(), or select the
+ * channel (SPECIFICWQ_DEDICATED or SPECIFICWQ_POOL()) and specify the
+ * work-queue priority (0-7) with SPECIFICWQ_WQ() - either way, you get the
+ * same value.
+ */
+#define QM_SDQCR_SOURCE_CHANNELS 0x0
+#define QM_SDQCR_SOURCE_SPECIFICWQ 0x40000000
+#define QM_SDQCR_COUNT_EXACT1 0x0
+#define QM_SDQCR_COUNT_UPTO3 0x20000000
+#define QM_SDQCR_DEDICATED_PRECEDENCE 0x10000000
+#define QM_SDQCR_TYPE_MASK 0x03000000
+#define QM_SDQCR_TYPE_NULL 0x0
+#define QM_SDQCR_TYPE_PRIO_QOS 0x01000000
+#define QM_SDQCR_TYPE_ACTIVE_QOS 0x02000000
+#define QM_SDQCR_TYPE_ACTIVE 0x03000000
+#define QM_SDQCR_TOKEN_MASK 0x00ff0000
+#define QM_SDQCR_TOKEN_SET(v) (((v) & 0xff) << 16)
+#define QM_SDQCR_TOKEN_GET(v) (((v) >> 16) & 0xff)
+#define QM_SDQCR_CHANNELS_DEDICATED 0x00008000
+#define QM_SDQCR_SPECIFICWQ_MASK 0x000000f7
+#define QM_SDQCR_SPECIFICWQ_DEDICATED 0x00000000
+#define QM_SDQCR_SPECIFICWQ_POOL(n) ((n) << 4)
+#define QM_SDQCR_SPECIFICWQ_WQ(n) (n)
+
+/* For qm_dqrr_vdqcr_set(): use FQID(n) to fill in the frame queue ID */
+#define QM_VDQCR_FQID_MASK 0x00ffffff
+#define QM_VDQCR_FQID(n) ((n) & QM_VDQCR_FQID_MASK)
+
+/*
+ * Used by all portal interrupt registers except 'inhibit'
+ * Channels with frame availability
+ */
+#define QM_PIRQ_DQAVAIL 0x0000ffff
+
+/* The DQAVAIL interrupt fields break down into these bits; */
+#define QM_DQAVAIL_PORTAL 0x8000 /* Portal channel */
+#define QM_DQAVAIL_POOL(n) (0x8000 >> (n)) /* Pool channel, n==[1..15] */
+#define QM_DQAVAIL_MASK 0xffff
+/* This mask contains all the "irqsource" bits visible to API users */
+#define QM_PIRQ_VISIBLE (QM_PIRQ_SLOW | QM_PIRQ_DQRI)
+
+extern struct qman_portal *affine_portals[NR_CPUS];
+const struct qm_portal_config *qman_get_qm_portal_config(
+ struct qman_portal *portal);
diff --git a/drivers/soc/fsl/qbman/qman_test.c b/drivers/soc/fsl/qbman/qman_test.c
new file mode 100644
index 0000000..18f7f02
--- /dev/null
+++ b/drivers/soc/fsl/qbman/qman_test.c
@@ -0,0 +1,62 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "qman_test.h"
+
+MODULE_AUTHOR("Geoff Thorpe");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("QMan testing");
+
+static int test_init(void)
+{
+ int loop = 1;
+ int err = 0;
+
+ while (loop--) {
+#ifdef CONFIG_FSL_QMAN_TEST_STASH
+ err = qman_test_stash();
+ if (err)
+ break;
+#endif
+#ifdef CONFIG_FSL_QMAN_TEST_API
+ err = qman_test_api();
+ if (err)
+ break;
+#endif
+ }
+ return err;
+}
+
+static void test_exit(void)
+{
+}
+
+module_init(test_init);
+module_exit(test_exit);
diff --git a/drivers/soc/fsl/qbman/qman_test.h b/drivers/soc/fsl/qbman/qman_test.h
new file mode 100644
index 0000000..d5f8cb2
--- /dev/null
+++ b/drivers/soc/fsl/qbman/qman_test.h
@@ -0,0 +1,36 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "qman_priv.h"
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+int qman_test_stash(void);
+int qman_test_api(void);
diff --git a/drivers/soc/fsl/qbman/qman_test_api.c b/drivers/soc/fsl/qbman/qman_test_api.c
new file mode 100644
index 0000000..6880ff1
--- /dev/null
+++ b/drivers/soc/fsl/qbman/qman_test_api.c
@@ -0,0 +1,252 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "qman_test.h"
+
+#define CGR_ID 27
+#define POOL_ID 2
+#define FQ_FLAGS QMAN_FQ_FLAG_DYNAMIC_FQID
+#define NUM_ENQUEUES 10
+#define NUM_PARTIAL 4
+#define PORTAL_SDQCR (QM_SDQCR_SOURCE_CHANNELS | \
+ QM_SDQCR_TYPE_PRIO_QOS | \
+ QM_SDQCR_TOKEN_SET(0x98) | \
+ QM_SDQCR_CHANNELS_DEDICATED | \
+ QM_SDQCR_CHANNELS_POOL(POOL_ID))
+#define PORTAL_OPAQUE ((void *)0xf00dbeef)
+#define VDQCR_FLAGS (QMAN_VOLATILE_FLAG_WAIT | QMAN_VOLATILE_FLAG_FINISH)
+
+static enum qman_cb_dqrr_result cb_dqrr(struct qman_portal *,
+ struct qman_fq *,
+ const struct qm_dqrr_entry *);
+static void cb_ern(struct qman_portal *, struct qman_fq *,
+ const union qm_mr_entry *);
+static void cb_fqs(struct qman_portal *, struct qman_fq *,
+ const union qm_mr_entry *);
+
+static struct qm_fd fd, fd_dq;
+static struct qman_fq fq_base = {
+ .cb.dqrr = cb_dqrr,
+ .cb.ern = cb_ern,
+ .cb.fqs = cb_fqs
+};
+static DECLARE_WAIT_QUEUE_HEAD(waitqueue);
+static int retire_complete, sdqcr_complete;
+
+/* Helpers for initialising and "incrementing" a frame descriptor */
+static void fd_init(struct qm_fd *fd)
+{
+ qm_fd_addr_set64(fd, 0xabdeadbeefLLU);
+ qm_fd_set_contig_big(fd, 0x0000ffff);
+ fd->cmd = 0xfeedf00d;
+}
+
+static void fd_inc(struct qm_fd *fd)
+{
+ u64 t = qm_fd_addr_get64(fd);
+ int z = t >> 40;
+ unsigned int len, off;
+ enum qm_fd_format fmt;
+
+ t <<= 1;
+ if (z)
+ t |= 1;
+ qm_fd_addr_set64(fd, t);
+
+ fmt = qm_fd_get_format(fd);
+ off = qm_fd_get_offset(fd);
+ len = qm_fd_get_length(fd);
+ len--;
+ qm_fd_set_param(fd, fmt, off, len);
+
+ fd->cmd++;
+}
+
+/* The only part of the 'fd' we can't memcmp() is the ppid */
+static int fd_cmp(const struct qm_fd *a, const struct qm_fd *b)
+{
+ int r = (qm_fd_addr_get64(a) == qm_fd_addr_get64(b)) ? 0 : -1;
+
+ if (!r) {
+ enum qm_fd_format fmt_a, fmt_b;
+
+ fmt_a = qm_fd_get_format(a);
+ fmt_b = qm_fd_get_format(b);
+ r = fmt_a - fmt_b;
+ }
+ if (!r)
+ r = a->cfg - b->cfg;
+ if (!r)
+ r = a->cmd - b->cmd;
+ return r;
+}
+
+/* test */
+static int do_enqueues(struct qman_fq *fq)
+{
+ unsigned int loop;
+ int err = 0;
+
+ for (loop = 0; loop < NUM_ENQUEUES; loop++) {
+ if (qman_enqueue(fq, &fd)) {
+ pr_crit("qman_enqueue() failed\n");
+ err = -EIO;
+ }
+ fd_inc(&fd);
+ }
+
+ return err;
+}
+
+int qman_test_api(void)
+{
+ unsigned int flags, frmcnt;
+ int err;
+ struct qman_fq *fq = &fq_base;
+
+ pr_info("%s(): Starting\n", __func__);
+ fd_init(&fd);
+ fd_init(&fd_dq);
+
+ /* Initialise (parked) FQ */
+ err = qman_create_fq(0, FQ_FLAGS, fq);
+ if (err) {
+ pr_crit("qman_create_fq() failed\n");
+ goto failed;
+ }
+ err = qman_init_fq(fq, QMAN_INITFQ_FLAG_LOCAL, NULL);
+ if (err) {
+ pr_crit("qman_init_fq() failed\n");
+ goto failed;
+ }
+ /* Do enqueues + VDQCR, twice. (Parked FQ) */
+ err = do_enqueues(fq);
+ if (err)
+ goto failed;
+ pr_info("VDQCR (till-empty);\n");
+ frmcnt = QM_VDQCR_NUMFRAMES_TILLEMPTY;
+ err = qman_volatile_dequeue(fq, VDQCR_FLAGS, frmcnt);
+ if (err) {
+ pr_crit("qman_volatile_dequeue() failed\n");
+ goto failed;
+ }
+ err = do_enqueues(fq);
+ if (err)
+ goto failed;
+ pr_info("VDQCR (%d of %d);\n", NUM_PARTIAL, NUM_ENQUEUES);
+ frmcnt = QM_VDQCR_NUMFRAMES_SET(NUM_PARTIAL);
+ err = qman_volatile_dequeue(fq, VDQCR_FLAGS, frmcnt);
+ if (err) {
+ pr_crit("qman_volatile_dequeue() failed\n");
+ goto failed;
+ }
+ pr_info("VDQCR (%d of %d);\n", NUM_ENQUEUES - NUM_PARTIAL,
+ NUM_ENQUEUES);
+ frmcnt = QM_VDQCR_NUMFRAMES_SET(NUM_ENQUEUES - NUM_PARTIAL);
+ err = qman_volatile_dequeue(fq, VDQCR_FLAGS, frmcnt);
+ if (err) {
+ pr_err("qman_volatile_dequeue() failed\n");
+ goto failed;
+ }
+
+ err = do_enqueues(fq);
+ if (err)
+ goto failed;
+ pr_info("scheduled dequeue (till-empty)\n");
+ err = qman_schedule_fq(fq);
+ if (err) {
+ pr_crit("qman_schedule_fq() failed\n");
+ goto failed;
+ }
+ wait_event(waitqueue, sdqcr_complete);
+
+ /* Retire and OOS the FQ */
+ err = qman_retire_fq(fq, &flags);
+ if (err < 0) {
+ pr_crit("qman_retire_fq() failed\n");
+ goto failed;
+ }
+ wait_event(waitqueue, retire_complete);
+ if (flags & QMAN_FQ_STATE_BLOCKOOS) {
+ err = -EIO;
+ pr_crit("leaking frames\n");
+ goto failed;
+ }
+ err = qman_oos_fq(fq);
+ if (err) {
+ pr_crit("qman_oos_fq() failed\n");
+ goto failed;
+ }
+ qman_destroy_fq(fq);
+ pr_info("%s(): Finished\n", __func__);
+ return 0;
+
+failed:
+ WARN_ON(1);
+ return err;
+}
+
+static enum qman_cb_dqrr_result cb_dqrr(struct qman_portal *p,
+ struct qman_fq *fq,
+ const struct qm_dqrr_entry *dq)
+{
+ if (WARN_ON(fd_cmp(&fd_dq, &dq->fd))) {
+ pr_err("BADNESS: dequeued frame doesn't match;\n");
+ return qman_cb_dqrr_consume;
+ }
+ fd_inc(&fd_dq);
+ if (!(dq->stat & QM_DQRR_STAT_UNSCHEDULED) && !fd_cmp(&fd_dq, &fd)) {
+ sdqcr_complete = 1;
+ wake_up(&waitqueue);
+ }
+ return qman_cb_dqrr_consume;
+}
+
+static void cb_ern(struct qman_portal *p, struct qman_fq *fq,
+ const union qm_mr_entry *msg)
+{
+ pr_crit("cb_ern() unimplemented");
+ WARN_ON(1);
+}
+
+static void cb_fqs(struct qman_portal *p, struct qman_fq *fq,
+ const union qm_mr_entry *msg)
+{
+ u8 verb = (msg->verb & QM_MR_VERB_TYPE_MASK);
+
+ if ((verb != QM_MR_VERB_FQRN) && (verb != QM_MR_VERB_FQRNI)) {
+ pr_crit("unexpected FQS message");
+ WARN_ON(1);
+ return;
+ }
+ pr_info("Retirement message received\n");
+ retire_complete = 1;
+ wake_up(&waitqueue);
+}
diff --git a/drivers/soc/fsl/qbman/qman_test_stash.c b/drivers/soc/fsl/qbman/qman_test_stash.c
new file mode 100644
index 0000000..43cf66b
--- /dev/null
+++ b/drivers/soc/fsl/qbman/qman_test_stash.c
@@ -0,0 +1,617 @@
+/* Copyright 2009 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "qman_test.h"
+
+#include <linux/dma-mapping.h>
+#include <linux/delay.h>
+
+/*
+ * Algorithm:
+ *
+ * Each cpu will have HP_PER_CPU "handlers" set up, each of which incorporates
+ * an rx/tx pair of FQ objects (both of which are stashed on dequeue). The
+ * organisation of FQIDs is such that the HP_PER_CPU*NUM_CPUS handlers will
+ * shuttle a "hot potato" frame around them such that every forwarding action
+ * moves it from one cpu to another. (The use of more than one handler per cpu
+ * is to allow enough handlers/FQs to truly test the significance of caching -
+ * ie. when cache-expiries are occurring.)
+ *
+ * The "hot potato" frame content will be HP_NUM_WORDS*4 bytes in size, and the
+ * first and last words of the frame data will undergo a transformation step on
+ * each forwarding action. To achieve this, each handler will be assigned a
+ * 32-bit "mixer", that is produced using a 32-bit LFSR. When a frame is
+ * received by a handler, the mixer of the expected sender is XOR'd into all
+ * words of the entire frame, which is then validated against the original
+ * values. Then, before forwarding, the entire frame is XOR'd with the mixer of
+ * the current handler. Apart from validating that the frame is taking the
+ * expected path, this also provides some quasi-realistic overheads to each
+ * forwarding action - dereferencing *all* the frame data, computation, and
+ * conditional branching. There is a "special" handler designated to act as the
+ * instigator of the test by creating an enqueuing the "hot potato" frame, and
+ * to determine when the test has completed by counting HP_LOOPS iterations.
+ *
+ * Init phases:
+ *
+ * 1. prepare each cpu's 'hp_cpu' struct using on_each_cpu(,,1) and link them
+ * into 'hp_cpu_list'. Specifically, set processor_id, allocate HP_PER_CPU
+ * handlers and link-list them (but do no other handler setup).
+ *
+ * 2. scan over 'hp_cpu_list' HP_PER_CPU times, the first time sets each
+ * hp_cpu's 'iterator' to point to its first handler. With each loop,
+ * allocate rx/tx FQIDs and mixer values to the hp_cpu's iterator handler
+ * and advance the iterator for the next loop. This includes a final fixup,
+ * which connects the last handler to the first (and which is why phase 2
+ * and 3 are separate).
+ *
+ * 3. scan over 'hp_cpu_list' HP_PER_CPU times, the first time sets each
+ * hp_cpu's 'iterator' to point to its first handler. With each loop,
+ * initialise FQ objects and advance the iterator for the next loop.
+ * Moreover, do this initialisation on the cpu it applies to so that Rx FQ
+ * initialisation targets the correct cpu.
+ */
+
+/*
+ * helper to run something on all cpus (can't use on_each_cpu(), as that invokes
+ * the fn from irq context, which is too restrictive).
+ */
+struct bstrap {
+ int (*fn)(void);
+ atomic_t started;
+};
+static int bstrap_fn(void *bs)
+{
+ struct bstrap *bstrap = bs;
+ int err;
+
+ atomic_inc(&bstrap->started);
+ err = bstrap->fn();
+ if (err)
+ return err;
+ while (!kthread_should_stop())
+ msleep(20);
+ return 0;
+}
+static int on_all_cpus(int (*fn)(void))
+{
+ int cpu;
+
+ for_each_cpu(cpu, cpu_online_mask) {
+ struct bstrap bstrap = {
+ .fn = fn,
+ .started = ATOMIC_INIT(0)
+ };
+ struct task_struct *k = kthread_create(bstrap_fn, &bstrap,
+ "hotpotato%d", cpu);
+ int ret;
+
+ if (IS_ERR(k))
+ return -ENOMEM;
+ kthread_bind(k, cpu);
+ wake_up_process(k);
+ /*
+ * If we call kthread_stop() before the "wake up" has had an
+ * effect, then the thread may exit with -EINTR without ever
+ * running the function. So poll until it's started before
+ * requesting it to stop.
+ */
+ while (!atomic_read(&bstrap.started))
+ msleep(20);
+ ret = kthread_stop(k);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+struct hp_handler {
+
+ /* The following data is stashed when 'rx' is dequeued; */
+ /* -------------- */
+ /* The Rx FQ, dequeues of which will stash the entire hp_handler */
+ struct qman_fq rx;
+ /* The Tx FQ we should forward to */
+ struct qman_fq tx;
+ /* The value we XOR post-dequeue, prior to validating */
+ u32 rx_mixer;
+ /* The value we XOR pre-enqueue, after validating */
+ u32 tx_mixer;
+ /* what the hotpotato address should be on dequeue */
+ dma_addr_t addr;
+ u32 *frame_ptr;
+
+ /* The following data isn't (necessarily) stashed on dequeue; */
+ /* -------------- */
+ u32 fqid_rx, fqid_tx;
+ /* list node for linking us into 'hp_cpu' */
+ struct list_head node;
+ /* Just to check ... */
+ unsigned int processor_id;
+} ____cacheline_aligned;
+
+struct hp_cpu {
+ /* identify the cpu we run on; */
+ unsigned int processor_id;
+ /* root node for the per-cpu list of handlers */
+ struct list_head handlers;
+ /* list node for linking us into 'hp_cpu_list' */
+ struct list_head node;
+ /*
+ * when repeatedly scanning 'hp_list', each time linking the n'th
+ * handlers together, this is used as per-cpu iterator state
+ */
+ struct hp_handler *iterator;
+};
+
+/* Each cpu has one of these */
+static DEFINE_PER_CPU(struct hp_cpu, hp_cpus);
+
+/* links together the hp_cpu structs, in first-come first-serve order. */
+static LIST_HEAD(hp_cpu_list);
+static spinlock_t hp_lock = __SPIN_LOCK_UNLOCKED(hp_lock);
+
+static unsigned int hp_cpu_list_length;
+
+/* the "special" handler, that starts and terminates the test. */
+static struct hp_handler *special_handler;
+static int loop_counter;
+
+/* handlers are allocated out of this, so they're properly aligned. */
+static struct kmem_cache *hp_handler_slab;
+
+/* this is the frame data */
+static void *__frame_ptr;
+static u32 *frame_ptr;
+static dma_addr_t frame_dma;
+
+/* the main function waits on this */
+static DECLARE_WAIT_QUEUE_HEAD(queue);
+
+#define HP_PER_CPU 2
+#define HP_LOOPS 8
+/* 80 bytes, like a small ethernet frame, and bleeds into a second cacheline */
+#define HP_NUM_WORDS 80
+/* First word of the LFSR-based frame data */
+#define HP_FIRST_WORD 0xabbaf00d
+
+static inline u32 do_lfsr(u32 prev)
+{
+ return (prev >> 1) ^ (-(prev & 1u) & 0xd0000001u);
+}
+
+static int allocate_frame_data(void)
+{
+ u32 lfsr = HP_FIRST_WORD;
+ int loop;
+ struct platform_device *pdev = platform_device_alloc("foobar", -1);
+
+ if (!pdev) {
+ pr_crit("platform_device_alloc() failed");
+ return -EIO;
+ }
+ if (platform_device_add(pdev)) {
+ pr_crit("platform_device_add() failed");
+ return -EIO;
+ }
+ __frame_ptr = kmalloc(4 * HP_NUM_WORDS, GFP_KERNEL);
+ if (!__frame_ptr)
+ return -ENOMEM;
+
+ frame_ptr = PTR_ALIGN(__frame_ptr, 64);
+ for (loop = 0; loop < HP_NUM_WORDS; loop++) {
+ frame_ptr[loop] = lfsr;
+ lfsr = do_lfsr(lfsr);
+ }
+ frame_dma = dma_map_single(&pdev->dev, frame_ptr, 4 * HP_NUM_WORDS,
+ DMA_BIDIRECTIONAL);
+ platform_device_del(pdev);
+ platform_device_put(pdev);
+ return 0;
+}
+
+static void deallocate_frame_data(void)
+{
+ kfree(__frame_ptr);
+}
+
+static inline int process_frame_data(struct hp_handler *handler,
+ const struct qm_fd *fd)
+{
+ u32 *p = handler->frame_ptr;
+ u32 lfsr = HP_FIRST_WORD;
+ int loop;
+
+ if (qm_fd_addr_get64(fd) != handler->addr) {
+ pr_crit("bad frame address");
+ return -EIO;
+ }
+ for (loop = 0; loop < HP_NUM_WORDS; loop++, p++) {
+ *p ^= handler->rx_mixer;
+ if (*p != lfsr) {
+ pr_crit("corrupt frame data");
+ return -EIO;
+ }
+ *p ^= handler->tx_mixer;
+ lfsr = do_lfsr(lfsr);
+ }
+ return 0;
+}
+
+static enum qman_cb_dqrr_result normal_dqrr(struct qman_portal *portal,
+ struct qman_fq *fq,
+ const struct qm_dqrr_entry *dqrr)
+{
+ struct hp_handler *handler = (struct hp_handler *)fq;
+
+ if (process_frame_data(handler, &dqrr->fd)) {
+ WARN_ON(1);
+ goto skip;
+ }
+ if (qman_enqueue(&handler->tx, &dqrr->fd)) {
+ pr_crit("qman_enqueue() failed");
+ WARN_ON(1);
+ }
+skip:
+ return qman_cb_dqrr_consume;
+}
+
+static enum qman_cb_dqrr_result special_dqrr(struct qman_portal *portal,
+ struct qman_fq *fq,
+ const struct qm_dqrr_entry *dqrr)
+{
+ struct hp_handler *handler = (struct hp_handler *)fq;
+
+ process_frame_data(handler, &dqrr->fd);
+ if (++loop_counter < HP_LOOPS) {
+ if (qman_enqueue(&handler->tx, &dqrr->fd)) {
+ pr_crit("qman_enqueue() failed");
+ WARN_ON(1);
+ goto skip;
+ }
+ } else {
+ pr_info("Received final (%dth) frame\n", loop_counter);
+ wake_up(&queue);
+ }
+skip:
+ return qman_cb_dqrr_consume;
+}
+
+static int create_per_cpu_handlers(void)
+{
+ struct hp_handler *handler;
+ int loop;
+ struct hp_cpu *hp_cpu = this_cpu_ptr(&hp_cpus);
+
+ hp_cpu->processor_id = smp_processor_id();
+ spin_lock(&hp_lock);
+ list_add_tail(&hp_cpu->node, &hp_cpu_list);
+ hp_cpu_list_length++;
+ spin_unlock(&hp_lock);
+ INIT_LIST_HEAD(&hp_cpu->handlers);
+ for (loop = 0; loop < HP_PER_CPU; loop++) {
+ handler = kmem_cache_alloc(hp_handler_slab, GFP_KERNEL);
+ if (!handler) {
+ pr_crit("kmem_cache_alloc() failed");
+ WARN_ON(1);
+ return -EIO;
+ }
+ handler->processor_id = hp_cpu->processor_id;
+ handler->addr = frame_dma;
+ handler->frame_ptr = frame_ptr;
+ list_add_tail(&handler->node, &hp_cpu->handlers);
+ }
+ return 0;
+}
+
+static int destroy_per_cpu_handlers(void)
+{
+ struct list_head *loop, *tmp;
+ struct hp_cpu *hp_cpu = this_cpu_ptr(&hp_cpus);
+
+ spin_lock(&hp_lock);
+ list_del(&hp_cpu->node);
+ spin_unlock(&hp_lock);
+ list_for_each_safe(loop, tmp, &hp_cpu->handlers) {
+ u32 flags = 0;
+ struct hp_handler *handler = list_entry(loop, struct hp_handler,
+ node);
+ if (qman_retire_fq(&handler->rx, &flags) ||
+ (flags & QMAN_FQ_STATE_BLOCKOOS)) {
+ pr_crit("qman_retire_fq(rx) failed, flags: %x", flags);
+ WARN_ON(1);
+ return -EIO;
+ }
+ if (qman_oos_fq(&handler->rx)) {
+ pr_crit("qman_oos_fq(rx) failed");
+ WARN_ON(1);
+ return -EIO;
+ }
+ qman_destroy_fq(&handler->rx);
+ qman_destroy_fq(&handler->tx);
+ qman_release_fqid(handler->fqid_rx);
+ list_del(&handler->node);
+ kmem_cache_free(hp_handler_slab, handler);
+ }
+ return 0;
+}
+
+static inline u8 num_cachelines(u32 offset)
+{
+ u8 res = (offset + (L1_CACHE_BYTES - 1))
+ / (L1_CACHE_BYTES);
+ if (res > 3)
+ return 3;
+ return res;
+}
+#define STASH_DATA_CL \
+ num_cachelines(HP_NUM_WORDS * 4)
+#define STASH_CTX_CL \
+ num_cachelines(offsetof(struct hp_handler, fqid_rx))
+
+static int init_handler(void *h)
+{
+ struct qm_mcc_initfq opts;
+ struct hp_handler *handler = h;
+ int err;
+
+ if (handler->processor_id != smp_processor_id()) {
+ err = -EIO;
+ goto failed;
+ }
+ /* Set up rx */
+ memset(&handler->rx, 0, sizeof(handler->rx));
+ if (handler == special_handler)
+ handler->rx.cb.dqrr = special_dqrr;
+ else
+ handler->rx.cb.dqrr = normal_dqrr;
+ err = qman_create_fq(handler->fqid_rx, 0, &handler->rx);
+ if (err) {
+ pr_crit("qman_create_fq(rx) failed");
+ goto failed;
+ }
+ memset(&opts, 0, sizeof(opts));
+ opts.we_mask = QM_INITFQ_WE_FQCTRL | QM_INITFQ_WE_CONTEXTA;
+ opts.fqd.fq_ctrl = QM_FQCTRL_CTXASTASHING;
+ qm_fqd_set_stashing(&opts.fqd, 0, STASH_DATA_CL, STASH_CTX_CL);
+ err = qman_init_fq(&handler->rx, QMAN_INITFQ_FLAG_SCHED |
+ QMAN_INITFQ_FLAG_LOCAL, &opts);
+ if (err) {
+ pr_crit("qman_init_fq(rx) failed");
+ goto failed;
+ }
+ /* Set up tx */
+ memset(&handler->tx, 0, sizeof(handler->tx));
+ err = qman_create_fq(handler->fqid_tx, QMAN_FQ_FLAG_NO_MODIFY,
+ &handler->tx);
+ if (err) {
+ pr_crit("qman_create_fq(tx) failed");
+ goto failed;
+ }
+
+ return 0;
+failed:
+ return err;
+}
+
+static void init_handler_cb(void *h)
+{
+ if (init_handler(h))
+ WARN_ON(1);
+}
+
+static int init_phase2(void)
+{
+ int loop;
+ u32 fqid = 0;
+ u32 lfsr = 0xdeadbeef;
+ struct hp_cpu *hp_cpu;
+ struct hp_handler *handler;
+
+ for (loop = 0; loop < HP_PER_CPU; loop++) {
+ list_for_each_entry(hp_cpu, &hp_cpu_list, node) {
+ int err;
+
+ if (!loop)
+ hp_cpu->iterator = list_first_entry(
+ &hp_cpu->handlers,
+ struct hp_handler, node);
+ else
+ hp_cpu->iterator = list_entry(
+ hp_cpu->iterator->node.next,
+ struct hp_handler, node);
+ /* Rx FQID is the previous handler's Tx FQID */
+ hp_cpu->iterator->fqid_rx = fqid;
+ /* Allocate new FQID for Tx */
+ err = qman_alloc_fqid(&fqid);
+ if (err) {
+ pr_crit("qman_alloc_fqid() failed");
+ return err;
+ }
+ hp_cpu->iterator->fqid_tx = fqid;
+ /* Rx mixer is the previous handler's Tx mixer */
+ hp_cpu->iterator->rx_mixer = lfsr;
+ /* Get new mixer for Tx */
+ lfsr = do_lfsr(lfsr);
+ hp_cpu->iterator->tx_mixer = lfsr;
+ }
+ }
+ /* Fix up the first handler (fqid_rx==0, rx_mixer=0xdeadbeef) */
+ hp_cpu = list_first_entry(&hp_cpu_list, struct hp_cpu, node);
+ handler = list_first_entry(&hp_cpu->handlers, struct hp_handler, node);
+ if (handler->fqid_rx != 0 || handler->rx_mixer != 0xdeadbeef)
+ return 1;
+ handler->fqid_rx = fqid;
+ handler->rx_mixer = lfsr;
+ /* and tag it as our "special" handler */
+ special_handler = handler;
+ return 0;
+}
+
+static int init_phase3(void)
+{
+ int loop, err;
+ struct hp_cpu *hp_cpu;
+
+ for (loop = 0; loop < HP_PER_CPU; loop++) {
+ list_for_each_entry(hp_cpu, &hp_cpu_list, node) {
+ if (!loop)
+ hp_cpu->iterator = list_first_entry(
+ &hp_cpu->handlers,
+ struct hp_handler, node);
+ else
+ hp_cpu->iterator = list_entry(
+ hp_cpu->iterator->node.next,
+ struct hp_handler, node);
+ preempt_disable();
+ if (hp_cpu->processor_id == smp_processor_id()) {
+ err = init_handler(hp_cpu->iterator);
+ if (err)
+ return err;
+ } else {
+ smp_call_function_single(hp_cpu->processor_id,
+ init_handler_cb, hp_cpu->iterator, 1);
+ }
+ preempt_enable();
+ }
+ }
+ return 0;
+}
+
+static int send_first_frame(void *ignore)
+{
+ u32 *p = special_handler->frame_ptr;
+ u32 lfsr = HP_FIRST_WORD;
+ int loop, err;
+ struct qm_fd fd;
+
+ if (special_handler->processor_id != smp_processor_id()) {
+ err = -EIO;
+ goto failed;
+ }
+ memset(&fd, 0, sizeof(fd));
+ qm_fd_addr_set64(&fd, special_handler->addr);
+ qm_fd_set_contig_big(&fd, HP_NUM_WORDS * 4);
+ for (loop = 0; loop < HP_NUM_WORDS; loop++, p++) {
+ if (*p != lfsr) {
+ err = -EIO;
+ pr_crit("corrupt frame data");
+ goto failed;
+ }
+ *p ^= special_handler->tx_mixer;
+ lfsr = do_lfsr(lfsr);
+ }
+ pr_info("Sending first frame\n");
+ err = qman_enqueue(&special_handler->tx, &fd);
+ if (err) {
+ pr_crit("qman_enqueue() failed");
+ goto failed;
+ }
+
+ return 0;
+failed:
+ return err;
+}
+
+static void send_first_frame_cb(void *ignore)
+{
+ if (send_first_frame(NULL))
+ WARN_ON(1);
+}
+
+int qman_test_stash(void)
+{
+ int err;
+
+ if (cpumask_weight(cpu_online_mask) < 2) {
+ pr_info("%s(): skip - only 1 CPU\n", __func__);
+ return 0;
+ }
+
+ pr_info("%s(): Starting\n", __func__);
+
+ hp_cpu_list_length = 0;
+ loop_counter = 0;
+ hp_handler_slab = kmem_cache_create("hp_handler_slab",
+ sizeof(struct hp_handler), L1_CACHE_BYTES,
+ SLAB_HWCACHE_ALIGN, NULL);
+ if (!hp_handler_slab) {
+ err = -EIO;
+ pr_crit("kmem_cache_create() failed");
+ goto failed;
+ }
+
+ err = allocate_frame_data();
+ if (err)
+ goto failed;
+
+ /* Init phase 1 */
+ pr_info("Creating %d handlers per cpu...\n", HP_PER_CPU);
+ if (on_all_cpus(create_per_cpu_handlers)) {
+ err = -EIO;
+ pr_crit("on_each_cpu() failed");
+ goto failed;
+ }
+ pr_info("Number of cpus: %d, total of %d handlers\n",
+ hp_cpu_list_length, hp_cpu_list_length * HP_PER_CPU);
+
+ err = init_phase2();
+ if (err)
+ goto failed;
+
+ err = init_phase3();
+ if (err)
+ goto failed;
+
+ preempt_disable();
+ if (special_handler->processor_id == smp_processor_id()) {
+ err = send_first_frame(NULL);
+ if (err)
+ goto failed;
+ } else {
+ smp_call_function_single(special_handler->processor_id,
+ send_first_frame_cb, NULL, 1);
+ }
+ preempt_enable();
+
+ wait_event(queue, loop_counter == HP_LOOPS);
+ deallocate_frame_data();
+ if (on_all_cpus(destroy_per_cpu_handlers)) {
+ err = -EIO;
+ pr_crit("on_each_cpu() failed");
+ goto failed;
+ }
+ kmem_cache_destroy(hp_handler_slab);
+ pr_info("%s(): Finished\n", __func__);
+
+ return 0;
+failed:
+ WARN_ON(1);
+ return err;
+}
diff --git a/drivers/soc/fsl/qe/gpio.c b/drivers/soc/fsl/qe/gpio.c
index 333eb22..0aaf429 100644
--- a/drivers/soc/fsl/qe/gpio.c
+++ b/drivers/soc/fsl/qe/gpio.c
@@ -41,7 +41,8 @@ struct qe_gpio_chip {
static void qe_gpio_save_regs(struct of_mm_gpio_chip *mm_gc)
{
- struct qe_gpio_chip *qe_gc = gpiochip_get_data(&mm_gc->gc);
+ struct qe_gpio_chip *qe_gc =
+ container_of(mm_gc, struct qe_gpio_chip, mm_gc);
struct qe_pio_regs __iomem *regs = mm_gc->regs;
qe_gc->cpdata = in_be32(®s->cpdata);
diff --git a/drivers/soc/fsl/qe/qe.c b/drivers/soc/fsl/qe/qe.c
index 7026507..2707a82 100644
--- a/drivers/soc/fsl/qe/qe.c
+++ b/drivers/soc/fsl/qe/qe.c
@@ -69,8 +69,8 @@ static phys_addr_t qebase = -1;
phys_addr_t get_qe_base(void)
{
struct device_node *qe;
- int size;
- const u32 *prop;
+ int ret;
+ struct resource res;
if (qebase != -1)
return qebase;
@@ -82,9 +82,9 @@ phys_addr_t get_qe_base(void)
return qebase;
}
- prop = of_get_property(qe, "reg", &size);
- if (prop && size >= sizeof(*prop))
- qebase = of_translate_address(qe, prop);
+ ret = of_address_to_resource(qe, 0, &res);
+ if (!ret)
+ qebase = res.start;
of_node_put(qe);
return qebase;
diff --git a/drivers/soc/fsl/qe/qe_common.c b/drivers/soc/fsl/qe/qe_common.c
index 41eff80..104e68d 100644
--- a/drivers/soc/fsl/qe/qe_common.c
+++ b/drivers/soc/fsl/qe/qe_common.c
@@ -70,6 +70,11 @@ int cpm_muram_init(void)
}
muram_pool = gen_pool_create(0, -1);
+ if (!muram_pool) {
+ pr_err("Cannot allocate memory pool for CPM/QE muram");
+ ret = -ENOMEM;
+ goto out_muram;
+ }
muram_pbase = of_translate_address(np, zero);
if (muram_pbase == (phys_addr_t)OF_BAD_ADDR) {
pr_err("Cannot translate zero through CPM muram node");
@@ -116,6 +121,9 @@ static unsigned long cpm_muram_alloc_common(unsigned long size,
struct muram_block *entry;
unsigned long start;
+ if (!muram_pool && cpm_muram_init())
+ goto out2;
+
start = gen_pool_alloc_algo(muram_pool, size, algo, data);
if (!start)
goto out2;
diff --git a/drivers/soc/fsl/qe/qe_tdm.c b/drivers/soc/fsl/qe/qe_tdm.c
index 5e48b14..a1048b4 100644
--- a/drivers/soc/fsl/qe/qe_tdm.c
+++ b/drivers/soc/fsl/qe/qe_tdm.c
@@ -99,7 +99,7 @@ int ucc_of_parse_tdm(struct device_node *np, struct ucc_tdm *utdm,
utdm->tdm_port = val;
ut_info->uf_info.tdm_num = utdm->tdm_port;
- if (of_get_property(np, "fsl,tdm-internal-loopback", NULL))
+ if (of_property_read_bool(np, "fsl,tdm-internal-loopback"))
utdm->tdm_mode = TDM_INTERNAL_LOOPBACK;
else
utdm->tdm_mode = TDM_NORMAL;
@@ -167,7 +167,7 @@ int ucc_of_parse_tdm(struct device_node *np, struct ucc_tdm *utdm,
}
if (siram_init_flag == 0) {
- memset_io(utdm->siram, 0, res->end - res->start + 1);
+ memset_io(utdm->siram, 0, resource_size(res));
siram_init_flag = 1;
}
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 35c0dd9..a67b0ff 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -70,6 +70,7 @@
#define SPI_SR 0x2c
#define SPI_SR_EOQF 0x10000000
#define SPI_SR_TCFQF 0x80000000
+#define SPI_SR_CLEAR 0xdaad0000
#define SPI_RSER 0x30
#define SPI_RSER_EOQFE 0x10000000
@@ -646,6 +647,11 @@ static const struct regmap_config dspi_regmap_config = {
.max_register = 0x88,
};
+static void dspi_init(struct fsl_dspi *dspi)
+{
+ regmap_write(dspi->regmap, SPI_SR, SPI_SR_CLEAR);
+}
+
static int dspi_probe(struct platform_device *pdev)
{
struct device_node *np = pdev->dev.of_node;
@@ -709,6 +715,7 @@ static int dspi_probe(struct platform_device *pdev)
return PTR_ERR(dspi->regmap);
}
+ dspi_init(dspi);
dspi->irq = platform_get_irq(pdev, 0);
if (dspi->irq < 0) {
dev_err(&pdev->dev, "can't get platform irq\n");
diff --git a/drivers/spi/spi-fsl-espi.c b/drivers/spi/spi-fsl-espi.c
index 7451585..2c175b9 100644
--- a/drivers/spi/spi-fsl-espi.c
+++ b/drivers/spi/spi-fsl-espi.c
@@ -458,7 +458,7 @@ static void fsl_espi_cpu_irq(struct mpc8xxx_spi *mspi, u32 events)
mspi->len -= rx_nr_bytes;
- if (mspi->rx)
+ if (rx_nr_bytes && mspi->rx)
mspi->get_rx(rx_data, mspi);
}
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 5787b72..838783c 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1618,9 +1618,11 @@ static void of_register_spi_devices(struct spi_master *master)
if (of_node_test_and_set_flag(nc, OF_POPULATED))
continue;
spi = of_register_spi_device(master, nc);
- if (IS_ERR(spi))
+ if (IS_ERR(spi)) {
dev_warn(&master->dev, "Failed to create SPI device for %s\n",
nc->full_name);
+ of_node_clear_flag(nc, OF_POPULATED);
+ }
}
}
#else
@@ -3131,6 +3133,7 @@ static int of_spi_notify(struct notifier_block *nb, unsigned long action,
if (IS_ERR(spi)) {
pr_err("%s: failed to create for '%s'\n",
__func__, rd->dn->full_name);
+ of_node_clear_flag(rd->dn, OF_POPULATED);
return notifier_from_errno(PTR_ERR(spi));
}
break;
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index 396ded5..209a8f7 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -1187,8 +1187,10 @@ int ion_query_heaps(struct ion_client *client, struct ion_heap_query *query)
hdata.type = heap->type;
hdata.heap_id = heap->id;
- ret = copy_to_user(&buffer[cnt],
- &hdata, sizeof(hdata));
+ if (copy_to_user(&buffer[cnt], &hdata, sizeof(hdata))) {
+ ret = -EFAULT;
+ goto out;
+ }
cnt++;
if (cnt >= max_cnt)
diff --git a/drivers/staging/android/ion/ion_of.c b/drivers/staging/android/ion/ion_of.c
index 15bac92..46b2bb9 100644
--- a/drivers/staging/android/ion/ion_of.c
+++ b/drivers/staging/android/ion/ion_of.c
@@ -107,7 +107,7 @@ struct ion_platform_data *ion_parse_dt(struct platform_device *pdev,
heap_pdev = of_platform_device_create(node, heaps[i].name,
&pdev->dev);
- if (!pdev)
+ if (!heap_pdev)
return ERR_PTR(-ENOMEM);
heap_pdev->dev.platform_data = &heaps[i];
diff --git a/drivers/staging/comedi/drivers/ni_tio.c b/drivers/staging/comedi/drivers/ni_tio.c
index 7043eb0..5ab49a7 100644
--- a/drivers/staging/comedi/drivers/ni_tio.c
+++ b/drivers/staging/comedi/drivers/ni_tio.c
@@ -207,7 +207,8 @@ static int ni_tio_clock_period_ps(const struct ni_gpct *counter,
* clock period is specified by user with prescaling
* already taken into account.
*/
- return counter->clock_period_ps;
+ *period_ps = counter->clock_period_ps;
+ return 0;
}
switch (generic_clock_source & NI_GPCT_PRESCALE_MODE_CLOCK_SRC_MASK) {
diff --git a/drivers/staging/greybus/arche-platform.c b/drivers/staging/greybus/arche-platform.c
index e36ee98..d33d6fe 100644
--- a/drivers/staging/greybus/arche-platform.c
+++ b/drivers/staging/greybus/arche-platform.c
@@ -128,6 +128,7 @@ int arche_platform_change_state(enum arche_platform_state state,
pdev = of_find_device_by_node(np);
if (!pdev) {
pr_err("arche-platform device not found\n");
+ of_node_put(np);
return -ENODEV;
}
@@ -185,6 +186,7 @@ int arche_platform_change_state(enum arche_platform_state state,
exit:
spin_unlock_irqrestore(&arche_pdata->wake_lock, flags);
mutex_unlock(&arche_pdata->platform_state_mutex);
+ put_device(&pdev->dev);
of_node_put(np);
return ret;
}
diff --git a/drivers/staging/greybus/es2.c b/drivers/staging/greybus/es2.c
index 071bb1c..baab460 100644
--- a/drivers/staging/greybus/es2.c
+++ b/drivers/staging/greybus/es2.c
@@ -1548,7 +1548,8 @@ static int ap_probe(struct usb_interface *interface,
INIT_LIST_HEAD(&es2->arpcs);
spin_lock_init(&es2->arpc_lock);
- if (es2_arpc_in_enable(es2))
+ retval = es2_arpc_in_enable(es2);
+ if (retval)
goto error;
retval = gb_hd_add(hd);
diff --git a/drivers/staging/greybus/gpio.c b/drivers/staging/greybus/gpio.c
index 5e06e42..250caa0 100644
--- a/drivers/staging/greybus/gpio.c
+++ b/drivers/staging/greybus/gpio.c
@@ -702,15 +702,13 @@ static int gb_gpio_probe(struct gbphy_device *gbphy_dev,
ret = gb_gpio_irqchip_add(gpio, irqc, 0,
handle_level_irq, IRQ_TYPE_NONE);
if (ret) {
- dev_err(&connection->bundle->dev,
- "failed to add irq chip: %d\n", ret);
+ dev_err(&gbphy_dev->dev, "failed to add irq chip: %d\n", ret);
goto exit_line_free;
}
ret = gpiochip_add(gpio);
if (ret) {
- dev_err(&connection->bundle->dev,
- "failed to add gpio chip: %d\n", ret);
+ dev_err(&gbphy_dev->dev, "failed to add gpio chip: %d\n", ret);
goto exit_gpio_irqchip_remove;
}
diff --git a/drivers/staging/greybus/module.c b/drivers/staging/greybus/module.c
index 69f67dd..660b467 100644
--- a/drivers/staging/greybus/module.c
+++ b/drivers/staging/greybus/module.c
@@ -127,7 +127,7 @@ struct gb_module *gb_module_create(struct gb_host_device *hd, u8 module_id,
return module;
err_put_interfaces:
- for (--i; i > 0; --i)
+ for (--i; i >= 0; --i)
gb_interface_put(module->interfaces[i]);
put_device(&module->dev);
diff --git a/drivers/staging/greybus/uart.c b/drivers/staging/greybus/uart.c
index 5ee7954..2633d2b 100644
--- a/drivers/staging/greybus/uart.c
+++ b/drivers/staging/greybus/uart.c
@@ -888,7 +888,7 @@ static int gb_uart_probe(struct gbphy_device *gbphy_dev,
minor = alloc_minor(gb_tty);
if (minor < 0) {
if (minor == -ENOSPC) {
- dev_err(&connection->bundle->dev,
+ dev_err(&gbphy_dev->dev,
"no more free minor numbers\n");
retval = -ENODEV;
} else {
diff --git a/drivers/staging/iio/accel/sca3000_core.c b/drivers/staging/iio/accel/sca3000_core.c
index d626125..564b36d 100644
--- a/drivers/staging/iio/accel/sca3000_core.c
+++ b/drivers/staging/iio/accel/sca3000_core.c
@@ -468,6 +468,8 @@ static inline int __sca3000_get_base_freq(struct sca3000_state *st,
case SCA3000_MEAS_MODE_OP_2:
*base_freq = info->option_mode_2_freq;
break;
+ default:
+ ret = -EINVAL;
}
error_ret:
return ret;
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index 5eecf1c..3892a74 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -655,6 +655,7 @@ static void ad5933_work(struct work_struct *work)
__be16 buf[2];
int val[2];
unsigned char status;
+ int ret;
mutex_lock(&indio_dev->mlock);
if (st->state == AD5933_CTRL_INIT_START_FREQ) {
@@ -662,19 +663,22 @@ static void ad5933_work(struct work_struct *work)
ad5933_cmd(st, AD5933_CTRL_START_SWEEP);
st->state = AD5933_CTRL_START_SWEEP;
schedule_delayed_work(&st->work, st->poll_time_jiffies);
- mutex_unlock(&indio_dev->mlock);
- return;
+ goto out;
}
- ad5933_i2c_read(st->client, AD5933_REG_STATUS, 1, &status);
+ ret = ad5933_i2c_read(st->client, AD5933_REG_STATUS, 1, &status);
+ if (ret)
+ goto out;
if (status & AD5933_STAT_DATA_VALID) {
int scan_count = bitmap_weight(indio_dev->active_scan_mask,
indio_dev->masklength);
- ad5933_i2c_read(st->client,
+ ret = ad5933_i2c_read(st->client,
test_bit(1, indio_dev->active_scan_mask) ?
AD5933_REG_REAL_DATA : AD5933_REG_IMAG_DATA,
scan_count * 2, (u8 *)buf);
+ if (ret)
+ goto out;
if (scan_count == 2) {
val[0] = be16_to_cpu(buf[0]);
@@ -686,8 +690,7 @@ static void ad5933_work(struct work_struct *work)
} else {
/* no data available - try again later */
schedule_delayed_work(&st->work, st->poll_time_jiffies);
- mutex_unlock(&indio_dev->mlock);
- return;
+ goto out;
}
if (status & AD5933_STAT_SWEEP_DONE) {
@@ -700,7 +703,7 @@ static void ad5933_work(struct work_struct *work)
ad5933_cmd(st, AD5933_CTRL_INC_FREQ);
schedule_delayed_work(&st->work, st->poll_time_jiffies);
}
-
+out:
mutex_unlock(&indio_dev->mlock);
}
diff --git a/drivers/staging/lustre/lustre/llite/lproc_llite.c b/drivers/staging/lustre/lustre/llite/lproc_llite.c
index 6eae605..23fda9d 100644
--- a/drivers/staging/lustre/lustre/llite/lproc_llite.c
+++ b/drivers/staging/lustre/lustre/llite/lproc_llite.c
@@ -871,12 +871,10 @@ static ssize_t xattr_cache_store(struct kobject *kobj,
}
LUSTRE_RW_ATTR(xattr_cache);
-static ssize_t unstable_stats_show(struct kobject *kobj,
- struct attribute *attr,
- char *buf)
+static int ll_unstable_stats_seq_show(struct seq_file *m, void *v)
{
- struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
- ll_kobj);
+ struct super_block *sb = m->private;
+ struct ll_sb_info *sbi = ll_s2sbi(sb);
struct cl_client_cache *cache = sbi->ll_cache;
long pages;
int mb;
@@ -884,19 +882,21 @@ static ssize_t unstable_stats_show(struct kobject *kobj,
pages = atomic_long_read(&cache->ccc_unstable_nr);
mb = (pages * PAGE_SIZE) >> 20;
- return sprintf(buf, "unstable_check: %8d\n"
- "unstable_pages: %12ld\n"
- "unstable_mb: %8d\n",
- cache->ccc_unstable_check, pages, mb);
+ seq_printf(m,
+ "unstable_check: %8d\n"
+ "unstable_pages: %12ld\n"
+ "unstable_mb: %8d\n",
+ cache->ccc_unstable_check, pages, mb);
+
+ return 0;
}
-static ssize_t unstable_stats_store(struct kobject *kobj,
- struct attribute *attr,
- const char *buffer,
- size_t count)
+static ssize_t ll_unstable_stats_seq_write(struct file *file,
+ const char __user *buffer,
+ size_t count, loff_t *off)
{
- struct ll_sb_info *sbi = container_of(kobj, struct ll_sb_info,
- ll_kobj);
+ struct super_block *sb = ((struct seq_file *)file->private_data)->private;
+ struct ll_sb_info *sbi = ll_s2sbi(sb);
char kernbuf[128];
int val, rc;
@@ -922,7 +922,7 @@ static ssize_t unstable_stats_store(struct kobject *kobj,
return count;
}
-LUSTRE_RW_ATTR(unstable_stats);
+LPROC_SEQ_FOPS(ll_unstable_stats);
static ssize_t root_squash_show(struct kobject *kobj, struct attribute *attr,
char *buf)
@@ -995,6 +995,7 @@ static struct lprocfs_vars lprocfs_llite_obd_vars[] = {
/* { "filegroups", lprocfs_rd_filegroups, 0, 0 }, */
{ "max_cached_mb", &ll_max_cached_mb_fops, NULL },
{ "statahead_stats", &ll_statahead_stats_fops, NULL, 0 },
+ { "unstable_stats", &ll_unstable_stats_fops, NULL },
{ "sbi_flags", &ll_sbi_flags_fops, NULL, 0 },
{ .name = "nosquash_nids",
.fops = &ll_nosquash_nids_fops },
@@ -1026,7 +1027,6 @@ static struct attribute *llite_attrs[] = {
&lustre_attr_max_easize.attr,
&lustre_attr_default_easize.attr,
&lustre_attr_xattr_cache.attr,
- &lustre_attr_unstable_stats.attr,
&lustre_attr_root_squash.attr,
NULL,
};
diff --git a/drivers/staging/media/bcm2048/radio-bcm2048.c b/drivers/staging/media/bcm2048/radio-bcm2048.c
index ea15cc6..4d9bd02e 100644
--- a/drivers/staging/media/bcm2048/radio-bcm2048.c
+++ b/drivers/staging/media/bcm2048/radio-bcm2048.c
@@ -482,6 +482,8 @@ static int bcm2048_set_rds_no_lock(struct bcm2048_device *bdev, u8 rds_on)
flags);
memset(&bdev->rds_info, 0, sizeof(bdev->rds_info));
}
+ if (err)
+ return err;
return bcm2048_send_command(bdev, BCM2048_I2C_FM_RDS_SYSTEM,
bdev->cache_fm_rds_system);
diff --git a/drivers/staging/nvec/nvec_ps2.c b/drivers/staging/nvec/nvec_ps2.c
index a324322..499952c 100644
--- a/drivers/staging/nvec/nvec_ps2.c
+++ b/drivers/staging/nvec/nvec_ps2.c
@@ -106,13 +106,12 @@ static int nvec_mouse_probe(struct platform_device *pdev)
{
struct nvec_chip *nvec = dev_get_drvdata(pdev->dev.parent);
struct serio *ser_dev;
- char mouse_reset[] = { NVEC_PS2, SEND_COMMAND, PSMOUSE_RST, 3 };
- ser_dev = devm_kzalloc(&pdev->dev, sizeof(struct serio), GFP_KERNEL);
+ ser_dev = kzalloc(sizeof(struct serio), GFP_KERNEL);
if (!ser_dev)
return -ENOMEM;
- ser_dev->id.type = SERIO_PS_PSTHRU;
+ ser_dev->id.type = SERIO_8042;
ser_dev->write = ps2_sendcommand;
ser_dev->start = ps2_startstreaming;
ser_dev->stop = ps2_stopstreaming;
@@ -127,9 +126,6 @@ static int nvec_mouse_probe(struct platform_device *pdev)
serio_register_port(ser_dev);
- /* mouse reset */
- nvec_write_async(nvec, mouse_reset, sizeof(mouse_reset));
-
return 0;
}
diff --git a/drivers/staging/sm750fb/ddk750_reg.h b/drivers/staging/sm750fb/ddk750_reg.h
index 9552479..4ed6d8d 100644
--- a/drivers/staging/sm750fb/ddk750_reg.h
+++ b/drivers/staging/sm750fb/ddk750_reg.h
@@ -601,13 +601,13 @@
#define PANEL_PLANE_TL 0x08001C
#define PANEL_PLANE_TL_TOP_SHIFT 16
-#define PANEL_PLANE_TL_TOP_MASK (0xeff << 16)
-#define PANEL_PLANE_TL_LEFT_MASK 0xeff
+#define PANEL_PLANE_TL_TOP_MASK (0x7ff << 16)
+#define PANEL_PLANE_TL_LEFT_MASK 0x7ff
#define PANEL_PLANE_BR 0x080020
#define PANEL_PLANE_BR_BOTTOM_SHIFT 16
-#define PANEL_PLANE_BR_BOTTOM_MASK (0xeff << 16)
-#define PANEL_PLANE_BR_RIGHT_MASK 0xeff
+#define PANEL_PLANE_BR_BOTTOM_MASK (0x7ff << 16)
+#define PANEL_PLANE_BR_RIGHT_MASK 0x7ff
#define PANEL_HORIZONTAL_TOTAL 0x080024
#define PANEL_HORIZONTAL_TOTAL_TOTAL_SHIFT 16
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c
index c29040f..1091b9f 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c
@@ -423,8 +423,7 @@ create_pagelist(char __user *buf, size_t count, unsigned short type,
actual_pages = get_user_pages(task, task->mm,
(unsigned long)buf & ~(PAGE_SIZE - 1),
num_pages,
- (type == PAGELIST_READ) /*Write */ ,
- 0 /*Force */ ,
+ (type == PAGELIST_READ) ? FOLL_WRITE : 0,
pages,
NULL /*vmas */);
up_read(&task->mm->mmap_sem);
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
index e11c0e0..7b6cd4d 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
@@ -1477,8 +1477,7 @@ dump_phys_mem(void *virt_addr, uint32_t num_bytes)
current->mm, /* mm */
(unsigned long)virt_addr, /* start */
num_pages, /* len */
- 0, /* write */
- 0, /* force */
+ 0, /* gup_flags */
pages, /* pages (array of page pointers) */
NULL); /* vmas */
up_read(¤t->mm->mmap_sem);
diff --git a/drivers/staging/wilc1000/host_interface.c b/drivers/staging/wilc1000/host_interface.c
index 78f5613..6ab7443 100644
--- a/drivers/staging/wilc1000/host_interface.c
+++ b/drivers/staging/wilc1000/host_interface.c
@@ -3388,7 +3388,6 @@ int wilc_init(struct net_device *dev, struct host_if_drv **hif_drv_handler)
clients_count++;
- destroy_workqueue(hif_workqueue);
_fail_:
return result;
}
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_main.c b/drivers/target/iscsi/cxgbit/cxgbit_main.c
index ad26b93..96eedfc 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_main.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_main.c
@@ -653,6 +653,7 @@ static struct iscsit_transport cxgbit_transport = {
static struct cxgb4_uld_info cxgbit_uld_info = {
.name = DRV_NAME,
.nrxq = MAX_ULD_QSETS,
+ .ntxq = MAX_ULD_QSETS,
.rxq_size = 1024,
.lro = true,
.add = cxgbit_uld_add,
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 39b928c..b7d747e 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -1804,6 +1804,10 @@ int iscsit_process_nop_out(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
* Otherwise, initiator is not expecting a NOPIN is response.
* Just ignore for now.
*/
+
+ if (cmd)
+ iscsit_free_cmd(cmd, false);
+
return 0;
}
EXPORT_SYMBOL(iscsit_process_nop_out);
@@ -2982,7 +2986,7 @@ iscsit_build_nopin_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn,
pr_debug("Built NOPIN %s Response ITT: 0x%08x, TTT: 0x%08x,"
" StatSN: 0x%08x, Length %u\n", (nopout_response) ?
- "Solicitied" : "Unsolicitied", cmd->init_task_tag,
+ "Solicited" : "Unsolicited", cmd->init_task_tag,
cmd->targ_xfer_tag, cmd->stat_sn, cmd->buf_ptr_size);
}
EXPORT_SYMBOL(iscsit_build_nopin_rsp);
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index adf419f..15f79a2 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -434,7 +434,7 @@ static int iscsi_login_zero_tsih_s2(
/*
* Make MaxRecvDataSegmentLength PAGE_SIZE aligned for
- * Immediate Data + Unsolicitied Data-OUT if necessary..
+ * Immediate Data + Unsolicited Data-OUT if necessary..
*/
param = iscsi_find_param_from_key("MaxRecvDataSegmentLength",
conn->param_list);
@@ -646,7 +646,7 @@ static void iscsi_post_login_start_timers(struct iscsi_conn *conn)
{
struct iscsi_session *sess = conn->sess;
/*
- * FIXME: Unsolicitied NopIN support for ISER
+ * FIXME: Unsolicited NopIN support for ISER
*/
if (conn->conn_transport->transport_type == ISCSI_INFINIBAND)
return;
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 6094a6b..7dfefd6 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -754,15 +754,7 @@ EXPORT_SYMBOL(target_complete_cmd);
void target_complete_cmd_with_length(struct se_cmd *cmd, u8 scsi_status, int length)
{
- if (scsi_status != SAM_STAT_GOOD) {
- return;
- }
-
- /*
- * Calculate new residual count based upon length of SCSI data
- * transferred.
- */
- if (length < cmd->data_length) {
+ if (scsi_status == SAM_STAT_GOOD && length < cmd->data_length) {
if (cmd->se_cmd_flags & SCF_UNDERFLOW_BIT) {
cmd->residual_count += cmd->data_length - length;
} else {
@@ -771,12 +763,6 @@ void target_complete_cmd_with_length(struct se_cmd *cmd, u8 scsi_status, int len
}
cmd->data_length = length;
- } else if (length > cmd->data_length) {
- cmd->se_cmd_flags |= SCF_OVERFLOW_BIT;
- cmd->residual_count = length - cmd->data_length;
- } else {
- cmd->se_cmd_flags &= ~(SCF_OVERFLOW_BIT | SCF_UNDERFLOW_BIT);
- cmd->residual_count = 0;
}
target_complete_cmd(cmd, scsi_status);
@@ -1706,6 +1692,7 @@ void transport_generic_request_failure(struct se_cmd *cmd,
case TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED:
case TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED:
case TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED:
+ case TCM_COPY_TARGET_DEVICE_NOT_REACHABLE:
break;
case TCM_OUT_OF_RESOURCES:
sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
@@ -2547,8 +2534,12 @@ int target_get_sess_cmd(struct se_cmd *se_cmd, bool ack_kref)
* fabric acknowledgement that requires two target_put_sess_cmd()
* invocations before se_cmd descriptor release.
*/
- if (ack_kref)
- kref_get(&se_cmd->cmd_kref);
+ if (ack_kref) {
+ if (!kref_get_unless_zero(&se_cmd->cmd_kref))
+ return -EINVAL;
+
+ se_cmd->se_cmd_flags |= SCF_ACK_KREF;
+ }
spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
if (se_sess->sess_tearing_down) {
@@ -2627,7 +2618,7 @@ EXPORT_SYMBOL(target_put_sess_cmd);
*/
void target_sess_cmd_list_set_waiting(struct se_session *se_sess)
{
- struct se_cmd *se_cmd;
+ struct se_cmd *se_cmd, *tmp_cmd;
unsigned long flags;
int rc;
@@ -2639,14 +2630,16 @@ void target_sess_cmd_list_set_waiting(struct se_session *se_sess)
se_sess->sess_tearing_down = 1;
list_splice_init(&se_sess->sess_cmd_list, &se_sess->sess_wait_list);
- list_for_each_entry(se_cmd, &se_sess->sess_wait_list, se_cmd_list) {
+ list_for_each_entry_safe(se_cmd, tmp_cmd,
+ &se_sess->sess_wait_list, se_cmd_list) {
rc = kref_get_unless_zero(&se_cmd->cmd_kref);
if (rc) {
se_cmd->cmd_wait_set = 1;
spin_lock(&se_cmd->t_state_lock);
se_cmd->transport_state |= CMD_T_FABRIC_STOP;
spin_unlock(&se_cmd->t_state_lock);
- }
+ } else
+ list_del_init(&se_cmd->se_cmd_list);
}
spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
@@ -2871,6 +2864,12 @@ static const struct sense_info sense_info_table[] = {
.ascq = 0x03, /* LOGICAL BLOCK REFERENCE TAG CHECK FAILED */
.add_sector_info = true,
},
+ [TCM_COPY_TARGET_DEVICE_NOT_REACHABLE] = {
+ .key = COPY_ABORTED,
+ .asc = 0x0d,
+ .ascq = 0x02, /* COPY TARGET DEVICE NOT REACHABLE */
+
+ },
[TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE] = {
/*
* Returning ILLEGAL REQUEST would cause immediate IO errors on
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 0f173bf..2b3c856 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -96,7 +96,7 @@ struct tcmu_dev {
size_t dev_size;
u32 cmdr_size;
u32 cmdr_last_cleaned;
- /* Offset of data ring from start of mb */
+ /* Offset of data area from start of mb */
/* Must add data_off and mb_addr to get the address */
size_t data_off;
size_t data_size;
@@ -349,7 +349,7 @@ static inline size_t spc_bitmap_free(unsigned long *bitmap)
/*
* We can't queue a command until we have space available on the cmd ring *and*
- * space available on the data ring.
+ * space available on the data area.
*
* Called with ring lock held.
*/
@@ -389,7 +389,8 @@ static bool is_ring_space_avail(struct tcmu_dev *udev, size_t cmd_size, size_t d
return true;
}
-static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
+static sense_reason_t
+tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
{
struct tcmu_dev *udev = tcmu_cmd->tcmu_dev;
struct se_cmd *se_cmd = tcmu_cmd->se_cmd;
@@ -405,7 +406,7 @@ static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
DECLARE_BITMAP(old_bitmap, DATA_BLOCK_BITS);
if (test_bit(TCMU_DEV_BIT_BROKEN, &udev->flags))
- return -EINVAL;
+ return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
/*
* Must be a certain minimum size for response sense info, but
@@ -432,11 +433,14 @@ static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
BUG_ON(!(se_cmd->t_bidi_data_sg && se_cmd->t_bidi_data_nents));
data_length += se_cmd->t_bidi_data_sg->length;
}
- if ((command_size > (udev->cmdr_size / 2))
- || data_length > udev->data_size)
- pr_warn("TCMU: Request of size %zu/%zu may be too big for %u/%zu "
- "cmd/data ring buffers\n", command_size, data_length,
+ if ((command_size > (udev->cmdr_size / 2)) ||
+ data_length > udev->data_size) {
+ pr_warn("TCMU: Request of size %zu/%zu is too big for %u/%zu "
+ "cmd ring/data area\n", command_size, data_length,
udev->cmdr_size, udev->data_size);
+ spin_unlock_irq(&udev->cmdr_lock);
+ return TCM_INVALID_CDB_FIELD;
+ }
while (!is_ring_space_avail(udev, command_size, data_length)) {
int ret;
@@ -450,7 +454,7 @@ static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
finish_wait(&udev->wait_cmdr, &__wait);
if (!ret) {
pr_warn("tcmu: command timed out\n");
- return -ETIMEDOUT;
+ return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
}
spin_lock_irq(&udev->cmdr_lock);
@@ -487,9 +491,7 @@ static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
bitmap_copy(old_bitmap, udev->data_bitmap, DATA_BLOCK_BITS);
- /*
- * Fix up iovecs, and handle if allocation in data ring wrapped.
- */
+ /* Handle allocating space from the data area */
iov = &entry->req.iov[0];
iov_cnt = 0;
copy_to_data_area = (se_cmd->data_direction == DMA_TO_DEVICE
@@ -526,10 +528,11 @@ static int tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
mod_timer(&udev->timeout,
round_jiffies_up(jiffies + msecs_to_jiffies(TCMU_TIME_OUT)));
- return 0;
+ return TCM_NO_SENSE;
}
-static int tcmu_queue_cmd(struct se_cmd *se_cmd)
+static sense_reason_t
+tcmu_queue_cmd(struct se_cmd *se_cmd)
{
struct se_device *se_dev = se_cmd->se_dev;
struct tcmu_dev *udev = TCMU_DEV(se_dev);
@@ -538,10 +541,10 @@ static int tcmu_queue_cmd(struct se_cmd *se_cmd)
tcmu_cmd = tcmu_alloc_cmd(se_cmd);
if (!tcmu_cmd)
- return -ENOMEM;
+ return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
ret = tcmu_queue_cmd_ring(tcmu_cmd);
- if (ret < 0) {
+ if (ret != TCM_NO_SENSE) {
pr_err("TCMU: Could not queue command\n");
spin_lock_irq(&udev->commands_lock);
idr_remove(&udev->commands, tcmu_cmd->cmd_id);
@@ -561,7 +564,7 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry *
if (test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags)) {
/*
* cmd has been completed already from timeout, just reclaim
- * data ring space and free cmd
+ * data area space and free cmd
*/
free_data_area(udev, cmd);
@@ -1129,20 +1132,9 @@ static sector_t tcmu_get_blocks(struct se_device *dev)
}
static sense_reason_t
-tcmu_pass_op(struct se_cmd *se_cmd)
-{
- int ret = tcmu_queue_cmd(se_cmd);
-
- if (ret != 0)
- return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
- else
- return TCM_NO_SENSE;
-}
-
-static sense_reason_t
tcmu_parse_cdb(struct se_cmd *cmd)
{
- return passthrough_parse_cdb(cmd, tcmu_pass_op);
+ return passthrough_parse_cdb(cmd, tcmu_queue_cmd);
}
static const struct target_backend_ops tcmu_ops = {
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 75cd854..094a144 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -104,7 +104,7 @@ static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op
}
mutex_unlock(&g_device_mutex);
- pr_err("Unable to locate 0xe4 descriptor for EXTENDED_COPY\n");
+ pr_debug_ratelimited("Unable to locate 0xe4 descriptor for EXTENDED_COPY\n");
return -EINVAL;
}
@@ -185,7 +185,7 @@ static int target_xcopy_parse_tiddesc_e4(struct se_cmd *se_cmd, struct xcopy_op
static int target_xcopy_parse_target_descriptors(struct se_cmd *se_cmd,
struct xcopy_op *xop, unsigned char *p,
- unsigned short tdll)
+ unsigned short tdll, sense_reason_t *sense_ret)
{
struct se_device *local_dev = se_cmd->se_dev;
unsigned char *desc = p;
@@ -193,6 +193,8 @@ static int target_xcopy_parse_target_descriptors(struct se_cmd *se_cmd,
unsigned short start = 0;
bool src = true;
+ *sense_ret = TCM_INVALID_PARAMETER_LIST;
+
if (offset != 0) {
pr_err("XCOPY target descriptor list length is not"
" multiple of %d\n", XCOPY_TARGET_DESC_LEN);
@@ -243,9 +245,16 @@ static int target_xcopy_parse_target_descriptors(struct se_cmd *se_cmd,
rc = target_xcopy_locate_se_dev_e4(se_cmd, xop, true);
else
rc = target_xcopy_locate_se_dev_e4(se_cmd, xop, false);
-
- if (rc < 0)
+ /*
+ * If a matching IEEE NAA 0x83 descriptor for the requested device
+ * is not located on this node, return COPY_ABORTED with ASQ/ASQC
+ * 0x0d/0x02 - COPY_TARGET_DEVICE_NOT_REACHABLE to request the
+ * initiator to fall back to normal copy method.
+ */
+ if (rc < 0) {
+ *sense_ret = TCM_COPY_TARGET_DEVICE_NOT_REACHABLE;
goto out;
+ }
pr_debug("XCOPY TGT desc: Source dev: %p NAA IEEE WWN: 0x%16phN\n",
xop->src_dev, &xop->src_tid_wwn[0]);
@@ -653,6 +662,7 @@ static int target_xcopy_read_source(
rc = target_xcopy_setup_pt_cmd(xpt_cmd, xop, src_dev, &cdb[0],
remote_port, true);
if (rc < 0) {
+ ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status;
transport_generic_free_cmd(se_cmd, 0);
return rc;
}
@@ -664,6 +674,7 @@ static int target_xcopy_read_source(
rc = target_xcopy_issue_pt_cmd(xpt_cmd);
if (rc < 0) {
+ ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status;
transport_generic_free_cmd(se_cmd, 0);
return rc;
}
@@ -714,6 +725,7 @@ static int target_xcopy_write_destination(
remote_port, false);
if (rc < 0) {
struct se_cmd *src_cmd = &xop->src_pt_cmd->se_cmd;
+ ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status;
/*
* If the failure happened before the t_mem_list hand-off in
* target_xcopy_setup_pt_cmd(), Reset memory + clear flag so that
@@ -729,6 +741,7 @@ static int target_xcopy_write_destination(
rc = target_xcopy_issue_pt_cmd(xpt_cmd);
if (rc < 0) {
+ ec_cmd->scsi_status = xpt_cmd->se_cmd.scsi_status;
se_cmd->se_cmd_flags &= ~SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC;
transport_generic_free_cmd(se_cmd, 0);
return rc;
@@ -815,9 +828,14 @@ static void target_xcopy_do_work(struct work_struct *work)
out:
xcopy_pt_undepend_remotedev(xop);
kfree(xop);
-
- pr_warn("target_xcopy_do_work: Setting X-COPY CHECK_CONDITION -> sending response\n");
- ec_cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
+ /*
+ * Don't override an error scsi status if it has already been set
+ */
+ if (ec_cmd->scsi_status == SAM_STAT_GOOD) {
+ pr_warn_ratelimited("target_xcopy_do_work: rc: %d, Setting X-COPY"
+ " CHECK_CONDITION -> sending response\n", rc);
+ ec_cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
+ }
target_complete_cmd(ec_cmd, SAM_STAT_CHECK_CONDITION);
}
@@ -875,7 +893,7 @@ sense_reason_t target_do_xcopy(struct se_cmd *se_cmd)
" tdll: %hu sdll: %u inline_dl: %u\n", list_id, list_id_usage,
tdll, sdll, inline_dl);
- rc = target_xcopy_parse_target_descriptors(se_cmd, xop, &p[16], tdll);
+ rc = target_xcopy_parse_target_descriptors(se_cmd, xop, &p[16], tdll, &ret);
if (rc <= 0)
goto out;
diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c
index 216e18c..ff5de9a 100644
--- a/drivers/target/tcm_fc/tfc_cmd.c
+++ b/drivers/target/tcm_fc/tfc_cmd.c
@@ -572,10 +572,10 @@ static void ft_send_work(struct work_struct *work)
if (target_submit_cmd(&cmd->se_cmd, cmd->sess->se_sess, fcp->fc_cdb,
&cmd->ft_sense_buffer[0], scsilun_to_int(&fcp->fc_lun),
ntohl(fcp->fc_dl), task_attr, data_dir,
- TARGET_SCF_ACK_KREF))
+ TARGET_SCF_ACK_KREF | TARGET_SCF_USE_CPUID))
goto err;
- pr_debug("r_ctl %x alloc target_submit_cmd\n", fh->fh_r_ctl);
+ pr_debug("r_ctl %x target_submit_cmd %p\n", fh->fh_r_ctl, cmd);
return;
err:
diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c
index 6ffbb60..fd5c3de 100644
--- a/drivers/target/tcm_fc/tfc_sess.c
+++ b/drivers/target/tcm_fc/tfc_sess.c
@@ -39,6 +39,11 @@
#include "tcm_fc.h"
+#define TFC_SESS_DBG(lport, fmt, args...) \
+ pr_debug("host%u: rport %6.6x: " fmt, \
+ (lport)->host->host_no, \
+ (lport)->port_id, ##args )
+
static void ft_sess_delete_all(struct ft_tport *);
/*
@@ -167,24 +172,29 @@ static struct ft_sess *ft_sess_get(struct fc_lport *lport, u32 port_id)
struct ft_tport *tport;
struct hlist_head *head;
struct ft_sess *sess;
+ char *reason = "no session created";
rcu_read_lock();
tport = rcu_dereference(lport->prov[FC_TYPE_FCP]);
- if (!tport)
+ if (!tport) {
+ reason = "not an FCP port";
goto out;
+ }
head = &tport->hash[ft_sess_hash(port_id)];
hlist_for_each_entry_rcu(sess, head, hash) {
if (sess->port_id == port_id) {
kref_get(&sess->kref);
rcu_read_unlock();
- pr_debug("port_id %x found %p\n", port_id, sess);
+ TFC_SESS_DBG(lport, "port_id %x found %p\n",
+ port_id, sess);
return sess;
}
}
out:
rcu_read_unlock();
- pr_debug("port_id %x not found\n", port_id);
+ TFC_SESS_DBG(lport, "port_id %x not found, %s\n",
+ port_id, reason);
return NULL;
}
@@ -195,7 +205,7 @@ static int ft_sess_alloc_cb(struct se_portal_group *se_tpg,
struct ft_tport *tport = sess->tport;
struct hlist_head *head = &tport->hash[ft_sess_hash(sess->port_id)];
- pr_debug("port_id %x sess %p\n", sess->port_id, sess);
+ TFC_SESS_DBG(tport->lport, "port_id %x sess %p\n", sess->port_id, sess);
hlist_add_head_rcu(&sess->hash, head);
tport->sess_count++;
@@ -223,7 +233,7 @@ static struct ft_sess *ft_sess_create(struct ft_tport *tport, u32 port_id,
sess = kzalloc(sizeof(*sess), GFP_KERNEL);
if (!sess)
- return NULL;
+ return ERR_PTR(-ENOMEM);
kref_init(&sess->kref); /* ref for table entry */
sess->tport = tport;
@@ -234,8 +244,9 @@ static struct ft_sess *ft_sess_create(struct ft_tport *tport, u32 port_id,
TARGET_PROT_NORMAL, &initiatorname[0],
sess, ft_sess_alloc_cb);
if (IS_ERR(sess->se_sess)) {
+ int rc = PTR_ERR(sess->se_sess);
kfree(sess);
- return NULL;
+ sess = ERR_PTR(rc);
}
return sess;
}
@@ -319,7 +330,7 @@ void ft_sess_close(struct se_session *se_sess)
mutex_unlock(&ft_lport_lock);
return;
}
- pr_debug("port_id %x\n", port_id);
+ TFC_SESS_DBG(sess->tport->lport, "port_id %x close session\n", port_id);
ft_sess_unhash(sess);
mutex_unlock(&ft_lport_lock);
ft_close_sess(sess);
@@ -379,8 +390,13 @@ static int ft_prli_locked(struct fc_rport_priv *rdata, u32 spp_len,
if (!(fcp_parm & FCP_SPPF_INIT_FCN))
return FC_SPP_RESP_CONF;
sess = ft_sess_create(tport, rdata->ids.port_id, rdata);
- if (!sess)
- return FC_SPP_RESP_RES;
+ if (IS_ERR(sess)) {
+ if (PTR_ERR(sess) == -EACCES) {
+ spp->spp_flags &= ~FC_SPP_EST_IMG_PAIR;
+ return FC_SPP_RESP_CONF;
+ } else
+ return FC_SPP_RESP_RES;
+ }
if (!sess->params)
rdata->prli_count++;
sess->params = fcp_parm;
@@ -423,8 +439,8 @@ static int ft_prli(struct fc_rport_priv *rdata, u32 spp_len,
mutex_lock(&ft_lport_lock);
ret = ft_prli_locked(rdata, spp_len, rspp, spp);
mutex_unlock(&ft_lport_lock);
- pr_debug("port_id %x flags %x ret %x\n",
- rdata->ids.port_id, rspp ? rspp->spp_flags : 0, ret);
+ TFC_SESS_DBG(rdata->local_port, "port_id %x flags %x ret %x\n",
+ rdata->ids.port_id, rspp ? rspp->spp_flags : 0, ret);
return ret;
}
@@ -477,11 +493,11 @@ static void ft_recv(struct fc_lport *lport, struct fc_frame *fp)
struct ft_sess *sess;
u32 sid = fc_frame_sid(fp);
- pr_debug("sid %x\n", sid);
+ TFC_SESS_DBG(lport, "recv sid %x\n", sid);
sess = ft_sess_get(lport, sid);
if (!sess) {
- pr_debug("sid %x sess lookup failed\n", sid);
+ TFC_SESS_DBG(lport, "sid %x sess lookup failed\n", sid);
/* TBD XXX - if FCP_CMND, send PRLO */
fc_frame_free(fp);
return;
diff --git a/drivers/thermal/intel_pch_thermal.c b/drivers/thermal/intel_pch_thermal.c
index 9b4815e..19bf202 100644
--- a/drivers/thermal/intel_pch_thermal.c
+++ b/drivers/thermal/intel_pch_thermal.c
@@ -20,10 +20,13 @@
#include <linux/types.h>
#include <linux/init.h>
#include <linux/pci.h>
+#include <linux/acpi.h>
#include <linux/thermal.h>
#include <linux/pm.h>
/* Intel PCH thermal Device IDs */
+#define PCH_THERMAL_DID_HSW_1 0x9C24 /* Haswell PCH */
+#define PCH_THERMAL_DID_HSW_2 0x8C24 /* Haswell PCH */
#define PCH_THERMAL_DID_WPT 0x9CA4 /* Wildcat Point */
#define PCH_THERMAL_DID_SKL 0x9D31 /* Skylake PCH */
@@ -66,9 +69,53 @@ struct pch_thermal_device {
unsigned long crt_temp;
int hot_trip_id;
unsigned long hot_temp;
+ int psv_trip_id;
+ unsigned long psv_temp;
bool bios_enabled;
};
+#ifdef CONFIG_ACPI
+
+/*
+ * On some platforms, there is a companion ACPI device, which adds
+ * passive trip temperature using _PSV method. There is no specific
+ * passive temperature setting in MMIO interface of this PCI device.
+ */
+static void pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd,
+ int *nr_trips)
+{
+ struct acpi_device *adev;
+
+ ptd->psv_trip_id = -1;
+
+ adev = ACPI_COMPANION(&ptd->pdev->dev);
+ if (adev) {
+ unsigned long long r;
+ acpi_status status;
+
+ status = acpi_evaluate_integer(adev->handle, "_PSV", NULL,
+ &r);
+ if (ACPI_SUCCESS(status)) {
+ unsigned long trip_temp;
+
+ trip_temp = DECI_KELVIN_TO_MILLICELSIUS(r);
+ if (trip_temp) {
+ ptd->psv_temp = trip_temp;
+ ptd->psv_trip_id = *nr_trips;
+ ++(*nr_trips);
+ }
+ }
+ }
+}
+#else
+static void pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd,
+ int *nr_trips)
+{
+ ptd->psv_trip_id = -1;
+
+}
+#endif
+
static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips)
{
u8 tsel;
@@ -119,6 +166,8 @@ static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips)
++(*nr_trips);
}
+ pch_wpt_add_acpi_psv_trip(ptd, nr_trips);
+
return 0;
}
@@ -194,6 +243,8 @@ static int pch_get_trip_type(struct thermal_zone_device *tzd, int trip,
*type = THERMAL_TRIP_CRITICAL;
else if (ptd->hot_trip_id == trip)
*type = THERMAL_TRIP_HOT;
+ else if (ptd->psv_trip_id == trip)
+ *type = THERMAL_TRIP_PASSIVE;
else
return -EINVAL;
@@ -208,6 +259,8 @@ static int pch_get_trip_temp(struct thermal_zone_device *tzd, int trip, int *tem
*temp = ptd->crt_temp;
else if (ptd->hot_trip_id == trip)
*temp = ptd->hot_temp;
+ else if (ptd->psv_trip_id == trip)
+ *temp = ptd->psv_temp;
else
return -EINVAL;
@@ -242,6 +295,11 @@ static int intel_pch_thermal_probe(struct pci_dev *pdev,
ptd->ops = &pch_dev_ops_wpt;
dev_name = "pch_skylake";
break;
+ case PCH_THERMAL_DID_HSW_1:
+ case PCH_THERMAL_DID_HSW_2:
+ ptd->ops = &pch_dev_ops_wpt;
+ dev_name = "pch_haswell";
+ break;
default:
dev_err(&pdev->dev, "unknown pch thermal device\n");
return -ENODEV;
@@ -324,6 +382,8 @@ static int intel_pch_thermal_resume(struct device *device)
static struct pci_device_id intel_pch_thermal_id[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_WPT) },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_SKL) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_HSW_1) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_HSW_2) },
{ 0, },
};
MODULE_DEVICE_TABLE(pci, intel_pch_thermal_id);
diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c
index 0e4dc0a..7a22307 100644
--- a/drivers/thermal/intel_powerclamp.c
+++ b/drivers/thermal/intel_powerclamp.c
@@ -669,20 +669,10 @@ static struct thermal_cooling_device_ops powerclamp_cooling_ops = {
.set_cur_state = powerclamp_set_cur_state,
};
-static const struct x86_cpu_id intel_powerclamp_ids[] __initconst = {
- { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_MWAIT },
- { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_ARAT },
- { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_NONSTOP_TSC },
- { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_CONSTANT_TSC},
- {}
-};
-MODULE_DEVICE_TABLE(x86cpu, intel_powerclamp_ids);
-
static int __init powerclamp_probe(void)
{
- if (!x86_match_cpu(intel_powerclamp_ids)) {
- pr_err("Intel powerclamp does not run on family %d model %d\n",
- boot_cpu_data.x86, boot_cpu_data.x86_model);
+ if (!boot_cpu_has(X86_FEATURE_MWAIT)) {
+ pr_err("CPU does not support MWAIT");
return -ENODEV;
}
diff --git a/drivers/tty/serial/8250/8250_lpss.c b/drivers/tty/serial/8250/8250_lpss.c
index 886fcf3..b992346 100644
--- a/drivers/tty/serial/8250/8250_lpss.c
+++ b/drivers/tty/serial/8250/8250_lpss.c
@@ -213,7 +213,7 @@ static int qrk_serial_setup(struct lpss8250 *lpss, struct uart_port *port)
struct pci_dev *pdev = to_pci_dev(port->dev);
int ret;
- ret = pci_alloc_irq_vectors(pdev, 1, 1, 0);
+ ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
if (ret < 0)
return ret;
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 1bfb6fd..1731b98 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -83,7 +83,8 @@ static const struct serial8250_config uart_config[] = {
.name = "16550A",
.fifo_size = 16,
.tx_loadsz = 16,
- .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10,
+ .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10 |
+ UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT,
.rxtrig_bytes = {1, 4, 8, 14},
.flags = UART_CAP_FIFO,
},
diff --git a/drivers/tty/serial/8250/8250_uniphier.c b/drivers/tty/serial/8250/8250_uniphier.c
index b8d9c8c..417d9e7 100644
--- a/drivers/tty/serial/8250/8250_uniphier.c
+++ b/drivers/tty/serial/8250/8250_uniphier.c
@@ -99,7 +99,7 @@ static void uniphier_serial_out(struct uart_port *p, int offset, int value)
case UART_LCR:
valshift = UNIPHIER_UART_LCR_SHIFT;
/* Divisor latch access bit does not exist. */
- value &= ~(UART_LCR_DLAB << valshift);
+ value &= ~UART_LCR_DLAB;
/* fall through */
case UART_MCR:
offset = UNIPHIER_UART_LCR_MCR;
@@ -199,7 +199,7 @@ static int uniphier_uart_probe(struct platform_device *pdev)
regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!regs) {
- dev_err(dev, "failed to get memory resource");
+ dev_err(dev, "failed to get memory resource\n");
return -EINVAL;
}
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index c783140..25c1d7b 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -1625,6 +1625,7 @@
config SERIAL_STM32
tristate "STMicroelectronics STM32 serial port support"
select SERIAL_CORE
+ depends on HAS_DMA
depends on ARM || COMPILE_TEST
help
This driver is for the on-chip Serial Controller on
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index fd8aa1f..168b10c 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -2132,11 +2132,29 @@ static void atmel_set_termios(struct uart_port *port, struct ktermios *termios,
mode |= ATMEL_US_USMODE_RS485;
} else if (termios->c_cflag & CRTSCTS) {
/* RS232 with hardware handshake (RTS/CTS) */
- if (atmel_use_dma_rx(port) && !atmel_use_fifo(port)) {
- dev_info(port->dev, "not enabling hardware flow control because DMA is used");
- termios->c_cflag &= ~CRTSCTS;
- } else {
+ if (atmel_use_fifo(port) &&
+ !mctrl_gpio_to_gpiod(atmel_port->gpios, UART_GPIO_CTS)) {
+ /*
+ * with ATMEL_US_USMODE_HWHS set, the controller will
+ * be able to drive the RTS pin high/low when the RX
+ * FIFO is above RXFTHRES/below RXFTHRES2.
+ * It will also disable the transmitter when the CTS
+ * pin is high.
+ * This mode is not activated if CTS pin is a GPIO
+ * because in this case, the transmitter is always
+ * disabled (there must be an internal pull-up
+ * responsible for this behaviour).
+ * If the RTS pin is a GPIO, the controller won't be
+ * able to drive it according to the FIFO thresholds,
+ * but it will be handled by the driver.
+ */
mode |= ATMEL_US_USMODE_HWHS;
+ } else {
+ /*
+ * For platforms without FIFO, the flow control is
+ * handled by the driver.
+ */
+ mode |= ATMEL_US_USMODE_NORMAL;
}
} else {
/* RS232 without hadware handshake */
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index de9d510..76103f2 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -328,7 +328,7 @@ static void lpuart_dma_tx(struct lpuart_port *sport)
sport->dma_tx_bytes = uart_circ_chars_pending(xmit);
- if (xmit->tail < xmit->head) {
+ if (xmit->tail < xmit->head || xmit->head == 0) {
sport->dma_tx_nents = 1;
sg_init_one(sgl, xmit->buf + xmit->tail, sport->dma_tx_bytes);
} else {
@@ -359,7 +359,6 @@ static void lpuart_dma_tx(struct lpuart_port *sport)
sport->dma_tx_in_progress = true;
sport->dma_tx_cookie = dmaengine_submit(sport->dma_tx_desc);
dma_async_issue_pending(sport->dma_tx_chan);
-
}
static void lpuart_dma_tx_complete(void *arg)
diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c
index d391650..42caccb 100644
--- a/drivers/tty/serial/pch_uart.c
+++ b/drivers/tty/serial/pch_uart.c
@@ -419,6 +419,7 @@ static struct dmi_system_id pch_uart_dmi_table[] = {
},
(void *)MINNOW_UARTCLK,
},
+ { }
};
/* Return UART clock, checking for board specific clocks. */
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 2675792..fb06725 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1130,9 +1130,13 @@ static int sc16is7xx_gpio_direction_output(struct gpio_chip *chip,
{
struct sc16is7xx_port *s = gpiochip_get_data(chip);
struct uart_port *port = &s->p[0].port;
+ u8 state = sc16is7xx_port_read(port, SC16IS7XX_IOSTATE_REG);
- sc16is7xx_port_update(port, SC16IS7XX_IOSTATE_REG, BIT(offset),
- val ? BIT(offset) : 0);
+ if (val)
+ state |= BIT(offset);
+ else
+ state &= ~BIT(offset);
+ sc16is7xx_port_write(port, SC16IS7XX_IOSTATE_REG, state);
sc16is7xx_port_update(port, SC16IS7XX_IODIR_REG, BIT(offset),
BIT(offset));
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 6e4f636..f2303f3 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -111,7 +111,7 @@ void uart_write_wakeup(struct uart_port *port)
* closed. No cookie for you.
*/
BUG_ON(!state);
- tty_wakeup(state->port.tty);
+ tty_port_tty_wakeup(&state->port);
}
static void uart_stop(struct tty_struct *tty)
@@ -632,7 +632,7 @@ static void uart_flush_buffer(struct tty_struct *tty)
if (port->ops->flush_buffer)
port->ops->flush_buffer(port);
uart_port_unlock(port, flags);
- tty_wakeup(tty);
+ tty_port_tty_wakeup(&state->port);
}
/*
@@ -2746,8 +2746,6 @@ int uart_add_one_port(struct uart_driver *drv, struct uart_port *uport)
uport->cons = drv->cons;
uport->minor = drv->tty_driver->minor_start + uport->line;
- port->console = uart_console(uport);
-
/*
* If this port is a console, then the spinlock is already
* initialised.
@@ -2761,6 +2759,8 @@ int uart_add_one_port(struct uart_driver *drv, struct uart_port *uport)
uart_configure_port(drv, state, uport);
+ port->console = uart_console(uport);
+
num_groups = 2;
if (uport->attr_group)
num_groups++;
diff --git a/drivers/tty/serial/stm32-usart.h b/drivers/tty/serial/stm32-usart.h
index 41d9749..cd97ceb 100644
--- a/drivers/tty/serial/stm32-usart.h
+++ b/drivers/tty/serial/stm32-usart.h
@@ -31,7 +31,7 @@ struct stm32_usart_info {
struct stm32_usart_config cfg;
};
-#define UNDEF_REG ~0
+#define UNDEF_REG 0xff
/* Register offsets */
struct stm32_usart_info stm32f4_info = {
diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index f37edaa..dd4c02f 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -1200,6 +1200,7 @@ static int __init cdns_early_console_setup(struct earlycon_device *device,
OF_EARLYCON_DECLARE(cdns, "xlnx,xuartps", cdns_early_console_setup);
OF_EARLYCON_DECLARE(cdns, "cdns,uart-r1p8", cdns_early_console_setup);
OF_EARLYCON_DECLARE(cdns, "cdns,uart-r1p12", cdns_early_console_setup);
+OF_EARLYCON_DECLARE(cdns, "xlnx,zynqmp-uart", cdns_early_console_setup);
/**
* cdns_uart_console_write - perform write operation
@@ -1438,6 +1439,7 @@ static const struct of_device_id cdns_uart_of_match[] = {
{ .compatible = "xlnx,xuartps", },
{ .compatible = "cdns,uart-r1p8", },
{ .compatible = "cdns,uart-r1p12", .data = &zynqmp_uart_def },
+ { .compatible = "xlnx,zynqmp-uart", .data = &zynqmp_uart_def },
{}
};
MODULE_DEVICE_TABLE(of, cdns_uart_of_match);
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 06fb39c..8c3bf3d 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -870,10 +870,15 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc,
if (new_cols == vc->vc_cols && new_rows == vc->vc_rows)
return 0;
+ if (new_screen_size > (4 << 20))
+ return -EINVAL;
newscreen = kmalloc(new_screen_size, GFP_USER);
if (!newscreen)
return -ENOMEM;
+ if (vc == sel_cons)
+ clear_selection();
+
old_rows = vc->vc_rows;
old_row_size = vc->vc_size_row;
@@ -1176,7 +1181,7 @@ static void csi_J(struct vc_data *vc, int vpar)
break;
case 3: /* erase scroll-back buffer (and whole display) */
scr_memsetw(vc->vc_screenbuf, vc->vc_video_erase_char,
- vc->vc_screenbuf_size >> 1);
+ vc->vc_screenbuf_size);
set_origin(vc);
if (con_is_visible(vc))
update_screen(vc);
diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c
index 96ae695..111b0e0b 100644
--- a/drivers/usb/chipidea/host.c
+++ b/drivers/usb/chipidea/host.c
@@ -188,6 +188,8 @@ static void host_stop(struct ci_hdrc *ci)
if (hcd) {
usb_remove_hcd(hcd);
+ ci->role = CI_ROLE_END;
+ synchronize_irq(ci->irq);
usb_put_hcd(hcd);
if (ci->platdata->reg_vbus && !ci_otg_is_fsm_mode(ci) &&
(ci->platdata->flags & CI_HDRC_TURN_VBUS_EARLY_ON))
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 78f0f85..fada988 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -932,8 +932,6 @@ static int wait_serial_change(struct acm *acm, unsigned long arg)
DECLARE_WAITQUEUE(wait, current);
struct async_icount old, new;
- if (arg & (TIOCM_DSR | TIOCM_RI | TIOCM_CD))
- return -EINVAL;
do {
spin_lock_irq(&acm->read_lock);
old = acm->oldcount;
@@ -1161,6 +1159,8 @@ static int acm_probe(struct usb_interface *intf,
if (quirks == IGNORE_DEVICE)
return -ENODEV;
+ memset(&h, 0x00, sizeof(struct usb_cdc_parsed_header));
+
num_rx_buf = (quirks == SINGLE_RX_URB) ? 1 : ACM_NR;
/* handle quirks deadly to normal probing*/
diff --git a/drivers/usb/dwc2/core.c b/drivers/usb/dwc2/core.c
index fa9b26b..4c0fa0b 100644
--- a/drivers/usb/dwc2/core.c
+++ b/drivers/usb/dwc2/core.c
@@ -463,9 +463,18 @@ static void dwc2_clear_force_mode(struct dwc2_hsotg *hsotg)
*/
void dwc2_force_dr_mode(struct dwc2_hsotg *hsotg)
{
+ bool ret;
+
switch (hsotg->dr_mode) {
case USB_DR_MODE_HOST:
- dwc2_force_mode(hsotg, true);
+ ret = dwc2_force_mode(hsotg, true);
+ /*
+ * NOTE: This is required for some rockchip soc based
+ * platforms on their host-only dwc2.
+ */
+ if (!ret)
+ msleep(50);
+
break;
case USB_DR_MODE_PERIPHERAL:
dwc2_force_mode(hsotg, false);
diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h
index aad4107..2a21a04 100644
--- a/drivers/usb/dwc2/core.h
+++ b/drivers/usb/dwc2/core.h
@@ -259,6 +259,13 @@ enum dwc2_lx_state {
DWC2_L3, /* Off state */
};
+/*
+ * Gadget periodic tx fifo sizes as used by legacy driver
+ * EP0 is not included
+ */
+#define DWC2_G_P_LEGACY_TX_FIFO_SIZE {256, 256, 256, 256, 768, 768, 768, \
+ 768, 0, 0, 0, 0, 0, 0, 0}
+
/* Gadget ep0 states */
enum dwc2_ep0_state {
DWC2_EP0_SETUP,
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index 4cd6403..24fbebc 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -186,10 +186,9 @@ static void dwc2_hsotg_ctrl_epint(struct dwc2_hsotg *hsotg,
*/
static void dwc2_hsotg_init_fifo(struct dwc2_hsotg *hsotg)
{
- unsigned int fifo;
+ unsigned int ep;
unsigned int addr;
int timeout;
- u32 dptxfsizn;
u32 val;
/* Reset fifo map if not correctly cleared during previous session */
@@ -217,16 +216,16 @@ static void dwc2_hsotg_init_fifo(struct dwc2_hsotg *hsotg)
* them to endpoints dynamically according to maxpacket size value of
* given endpoint.
*/
- for (fifo = 1; fifo < MAX_EPS_CHANNELS; fifo++) {
- dptxfsizn = dwc2_readl(hsotg->regs + DPTXFSIZN(fifo));
+ for (ep = 1; ep < MAX_EPS_CHANNELS; ep++) {
+ if (!hsotg->g_tx_fifo_sz[ep])
+ continue;
+ val = addr;
+ val |= hsotg->g_tx_fifo_sz[ep] << FIFOSIZE_DEPTH_SHIFT;
+ WARN_ONCE(addr + hsotg->g_tx_fifo_sz[ep] > hsotg->fifo_mem,
+ "insufficient fifo memory");
+ addr += hsotg->g_tx_fifo_sz[ep];
- val = (dptxfsizn & FIFOSIZE_DEPTH_MASK) | addr;
- addr += dptxfsizn >> FIFOSIZE_DEPTH_SHIFT;
-
- if (addr > hsotg->fifo_mem)
- break;
-
- dwc2_writel(val, hsotg->regs + DPTXFSIZN(fifo));
+ dwc2_writel(val, hsotg->regs + DPTXFSIZN(ep));
}
/*
@@ -3807,10 +3806,36 @@ static void dwc2_hsotg_dump(struct dwc2_hsotg *hsotg)
static void dwc2_hsotg_of_probe(struct dwc2_hsotg *hsotg)
{
struct device_node *np = hsotg->dev->of_node;
+ u32 len = 0;
+ u32 i = 0;
/* Enable dma if requested in device tree */
hsotg->g_using_dma = of_property_read_bool(np, "g-use-dma");
+ /*
+ * Register TX periodic fifo size per endpoint.
+ * EP0 is excluded since it has no fifo configuration.
+ */
+ if (!of_find_property(np, "g-tx-fifo-size", &len))
+ goto rx_fifo;
+
+ len /= sizeof(u32);
+
+ /* Read tx fifo sizes other than ep0 */
+ if (of_property_read_u32_array(np, "g-tx-fifo-size",
+ &hsotg->g_tx_fifo_sz[1], len))
+ goto rx_fifo;
+
+ /* Add ep0 */
+ len++;
+
+ /* Make remaining TX fifos unavailable */
+ if (len < MAX_EPS_CHANNELS) {
+ for (i = len; i < MAX_EPS_CHANNELS; i++)
+ hsotg->g_tx_fifo_sz[i] = 0;
+ }
+
+rx_fifo:
/* Register RX fifo size */
of_property_read_u32(np, "g-rx-fifo-size", &hsotg->g_rx_fifo_sz);
@@ -3832,10 +3857,13 @@ int dwc2_gadget_init(struct dwc2_hsotg *hsotg, int irq)
struct device *dev = hsotg->dev;
int epnum;
int ret;
+ int i;
+ u32 p_tx_fifo[] = DWC2_G_P_LEGACY_TX_FIFO_SIZE;
/* Initialize to legacy fifo configuration values */
hsotg->g_rx_fifo_sz = 2048;
hsotg->g_np_g_tx_fifo_sz = 1024;
+ memcpy(&hsotg->g_tx_fifo_sz[1], p_tx_fifo, sizeof(p_tx_fifo));
/* Device tree specific probe */
dwc2_hsotg_of_probe(hsotg);
@@ -3853,6 +3881,9 @@ int dwc2_gadget_init(struct dwc2_hsotg *hsotg, int irq)
dev_dbg(dev, "NonPeriodic TXFIFO size: %d\n",
hsotg->g_np_g_tx_fifo_sz);
dev_dbg(dev, "RXFIFO size: %d\n", hsotg->g_rx_fifo_sz);
+ for (i = 0; i < MAX_EPS_CHANNELS; i++)
+ dev_dbg(dev, "Periodic TXFIFO%2d size: %d\n", i,
+ hsotg->g_tx_fifo_sz[i]);
hsotg->gadget.max_speed = USB_SPEED_HIGH;
hsotg->gadget.ops = &dwc2_hsotg_gadget_ops;
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 7287a76..fea4469 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -769,15 +769,14 @@ static int dwc3_core_init(struct dwc3 *dwc)
return 0;
err4:
- phy_power_off(dwc->usb2_generic_phy);
+ phy_power_off(dwc->usb3_generic_phy);
err3:
- phy_power_off(dwc->usb3_generic_phy);
+ phy_power_off(dwc->usb2_generic_phy);
err2:
usb_phy_set_suspend(dwc->usb2_phy, 1);
usb_phy_set_suspend(dwc->usb3_phy, 1);
- dwc3_core_exit(dwc);
err1:
usb_phy_shutdown(dwc->usb2_phy);
diff --git a/drivers/usb/dwc3/dwc3-st.c b/drivers/usb/dwc3/dwc3-st.c
index 89a2f71..aaaf256 100644
--- a/drivers/usb/dwc3/dwc3-st.c
+++ b/drivers/usb/dwc3/dwc3-st.c
@@ -31,6 +31,7 @@
#include <linux/slab.h>
#include <linux/regmap.h>
#include <linux/reset.h>
+#include <linux/pinctrl/consumer.h>
#include <linux/usb/of.h>
#include "core.h"
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 07cc892..1dfa56a5f 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -783,6 +783,7 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep,
req->trb = trb;
req->trb_dma = dwc3_trb_dma_offset(dep, trb);
req->first_trb_index = dep->trb_enqueue;
+ dep->queued_requests++;
}
dwc3_ep_inc_enq(dep);
@@ -833,8 +834,6 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep,
trb->ctrl |= DWC3_TRB_CTRL_HWO;
- dep->queued_requests++;
-
trace_dwc3_prepare_trb(dep, trb);
}
@@ -1074,9 +1073,17 @@ static int __dwc3_gadget_ep_queue(struct dwc3_ep *dep, struct dwc3_request *req)
list_add_tail(&req->list, &dep->pending_list);
- if (usb_endpoint_xfer_isoc(dep->endpoint.desc) &&
- dep->flags & DWC3_EP_PENDING_REQUEST) {
- if (list_empty(&dep->started_list)) {
+ /*
+ * NOTICE: Isochronous endpoints should NEVER be prestarted. We must
+ * wait for a XferNotReady event so we will know what's the current
+ * (micro-)frame number.
+ *
+ * Without this trick, we are very, very likely gonna get Bus Expiry
+ * errors which will force us issue EndTransfer command.
+ */
+ if (usb_endpoint_xfer_isoc(dep->endpoint.desc)) {
+ if ((dep->flags & DWC3_EP_PENDING_REQUEST) &&
+ list_empty(&dep->started_list)) {
dwc3_stop_active_transfer(dwc, dep->number, true);
dep->flags = DWC3_EP_ENABLED;
}
@@ -1861,8 +1868,11 @@ static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep,
unsigned int s_pkt = 0;
unsigned int trb_status;
- dep->queued_requests--;
dwc3_ep_inc_deq(dep);
+
+ if (req->trb == trb)
+ dep->queued_requests--;
+
trace_dwc3_complete_trb(dep, trb);
/*
@@ -2980,7 +2990,7 @@ int dwc3_gadget_init(struct dwc3 *dwc)
kfree(dwc->setup_buf);
err2:
- dma_free_coherent(dwc->dev, sizeof(*dwc->ep0_trb),
+ dma_free_coherent(dwc->dev, sizeof(*dwc->ep0_trb) * 2,
dwc->ep0_trb, dwc->ep0_trb_addr);
err1:
@@ -3005,7 +3015,7 @@ void dwc3_gadget_exit(struct dwc3 *dwc)
kfree(dwc->setup_buf);
kfree(dwc->zlp_buf);
- dma_free_coherent(dwc->dev, sizeof(*dwc->ep0_trb),
+ dma_free_coherent(dwc->dev, sizeof(*dwc->ep0_trb) * 2,
dwc->ep0_trb, dwc->ep0_trb_addr);
dma_free_coherent(dwc->dev, sizeof(*dwc->ctrl_req),
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 54ad100..e40d47d 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -136,8 +136,60 @@ struct ffs_epfile {
/*
* Buffer for holding data from partial reads which may happen since
* we’re rounding user read requests to a multiple of a max packet size.
+ *
+ * The pointer is initialised with NULL value and may be set by
+ * __ffs_epfile_read_data function to point to a temporary buffer.
+ *
+ * In normal operation, calls to __ffs_epfile_read_buffered will consume
+ * data from said buffer and eventually free it. Importantly, while the
+ * function is using the buffer, it sets the pointer to NULL. This is
+ * all right since __ffs_epfile_read_data and __ffs_epfile_read_buffered
+ * can never run concurrently (they are synchronised by epfile->mutex)
+ * so the latter will not assign a new value to the pointer.
+ *
+ * Meanwhile ffs_func_eps_disable frees the buffer (if the pointer is
+ * valid) and sets the pointer to READ_BUFFER_DROP value. This special
+ * value is crux of the synchronisation between ffs_func_eps_disable and
+ * __ffs_epfile_read_data.
+ *
+ * Once __ffs_epfile_read_data is about to finish it will try to set the
+ * pointer back to its old value (as described above), but seeing as the
+ * pointer is not-NULL (namely READ_BUFFER_DROP) it will instead free
+ * the buffer.
+ *
+ * == State transitions ==
+ *
+ * • ptr == NULL: (initial state)
+ * â—¦ __ffs_epfile_read_buffer_free: go to ptr == DROP
+ * â—¦ __ffs_epfile_read_buffered: nop
+ * â—¦ __ffs_epfile_read_data allocates temp buffer: go to ptr == buf
+ * â—¦ reading finishes: n/a, not in ‘and reading’ state
+ * • ptr == DROP:
+ * â—¦ __ffs_epfile_read_buffer_free: nop
+ * â—¦ __ffs_epfile_read_buffered: go to ptr == NULL
+ * â—¦ __ffs_epfile_read_data allocates temp buffer: free buf, nop
+ * â—¦ reading finishes: n/a, not in ‘and reading’ state
+ * • ptr == buf:
+ * â—¦ __ffs_epfile_read_buffer_free: free buf, go to ptr == DROP
+ * â—¦ __ffs_epfile_read_buffered: go to ptr == NULL and reading
+ * â—¦ __ffs_epfile_read_data: n/a, __ffs_epfile_read_buffered
+ * is always called first
+ * â—¦ reading finishes: n/a, not in ‘and reading’ state
+ * • ptr == NULL and reading:
+ * â—¦ __ffs_epfile_read_buffer_free: go to ptr == DROP and reading
+ * â—¦ __ffs_epfile_read_buffered: n/a, mutex is held
+ * â—¦ __ffs_epfile_read_data: n/a, mutex is held
+ * â—¦ reading finishes and …
+ * … all data read: free buf, go to ptr == NULL
+ * … otherwise: go to ptr == buf and reading
+ * • ptr == DROP and reading:
+ * â—¦ __ffs_epfile_read_buffer_free: nop
+ * â—¦ __ffs_epfile_read_buffered: n/a, mutex is held
+ * â—¦ __ffs_epfile_read_data: n/a, mutex is held
+ * â—¦ reading finishes: free buf, go to ptr == DROP
*/
- struct ffs_buffer *read_buffer; /* P: epfile->mutex */
+ struct ffs_buffer *read_buffer;
+#define READ_BUFFER_DROP ((struct ffs_buffer *)ERR_PTR(-ESHUTDOWN))
char name[5];
@@ -736,25 +788,47 @@ static void ffs_epfile_async_io_complete(struct usb_ep *_ep,
schedule_work(&io_data->work);
}
+static void __ffs_epfile_read_buffer_free(struct ffs_epfile *epfile)
+{
+ /*
+ * See comment in struct ffs_epfile for full read_buffer pointer
+ * synchronisation story.
+ */
+ struct ffs_buffer *buf = xchg(&epfile->read_buffer, READ_BUFFER_DROP);
+ if (buf && buf != READ_BUFFER_DROP)
+ kfree(buf);
+}
+
/* Assumes epfile->mutex is held. */
static ssize_t __ffs_epfile_read_buffered(struct ffs_epfile *epfile,
struct iov_iter *iter)
{
- struct ffs_buffer *buf = epfile->read_buffer;
+ /*
+ * Null out epfile->read_buffer so ffs_func_eps_disable does not free
+ * the buffer while we are using it. See comment in struct ffs_epfile
+ * for full read_buffer pointer synchronisation story.
+ */
+ struct ffs_buffer *buf = xchg(&epfile->read_buffer, NULL);
ssize_t ret;
- if (!buf)
+ if (!buf || buf == READ_BUFFER_DROP)
return 0;
ret = copy_to_iter(buf->data, buf->length, iter);
if (buf->length == ret) {
kfree(buf);
- epfile->read_buffer = NULL;
- } else if (unlikely(iov_iter_count(iter))) {
+ return ret;
+ }
+
+ if (unlikely(iov_iter_count(iter))) {
ret = -EFAULT;
} else {
buf->length -= ret;
buf->data += ret;
}
+
+ if (cmpxchg(&epfile->read_buffer, NULL, buf))
+ kfree(buf);
+
return ret;
}
@@ -783,7 +857,15 @@ static ssize_t __ffs_epfile_read_data(struct ffs_epfile *epfile,
buf->length = data_len;
buf->data = buf->storage;
memcpy(buf->storage, data + ret, data_len);
- epfile->read_buffer = buf;
+
+ /*
+ * At this point read_buffer is NULL or READ_BUFFER_DROP (if
+ * ffs_func_eps_disable has been called in the meanwhile). See comment
+ * in struct ffs_epfile for full read_buffer pointer synchronisation
+ * story.
+ */
+ if (unlikely(cmpxchg(&epfile->read_buffer, NULL, buf)))
+ kfree(buf);
return ret;
}
@@ -1097,8 +1179,7 @@ ffs_epfile_release(struct inode *inode, struct file *file)
ENTER();
- kfree(epfile->read_buffer);
- epfile->read_buffer = NULL;
+ __ffs_epfile_read_buffer_free(epfile);
ffs_data_closed(epfile->ffs);
return 0;
@@ -1724,24 +1805,20 @@ static void ffs_func_eps_disable(struct ffs_function *func)
unsigned count = func->ffs->eps_count;
unsigned long flags;
+ spin_lock_irqsave(&func->ffs->eps_lock, flags);
do {
- if (epfile)
- mutex_lock(&epfile->mutex);
- spin_lock_irqsave(&func->ffs->eps_lock, flags);
/* pending requests get nuked */
if (likely(ep->ep))
usb_ep_disable(ep->ep);
++ep;
- spin_unlock_irqrestore(&func->ffs->eps_lock, flags);
if (epfile) {
epfile->ep = NULL;
- kfree(epfile->read_buffer);
- epfile->read_buffer = NULL;
- mutex_unlock(&epfile->mutex);
+ __ffs_epfile_read_buffer_free(epfile);
++epfile;
}
} while (--count);
+ spin_unlock_irqrestore(&func->ffs->eps_lock, flags);
}
static int ffs_func_eps_enable(struct ffs_function *func)
diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 39a6df1..84a1709 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -579,13 +579,6 @@ static netdev_tx_t eth_start_xmit(struct sk_buff *skb,
req->length = length;
- /* throttle high/super speed IRQ rate back slightly */
- if (gadget_is_dualspeed(dev->gadget))
- req->no_interrupt = (dev->gadget->speed == USB_SPEED_HIGH ||
- dev->gadget->speed == USB_SPEED_SUPER)
- ? ((atomic_read(&dev->tx_qlen) % dev->qmult) != 0)
- : 0;
-
retval = usb_ep_queue(in, req, GFP_ATOMIC);
switch (retval) {
default:
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index bb1f6c8..45bc997 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -1978,7 +1978,7 @@ static struct usba_ep * atmel_udc_of_init(struct platform_device *pdev,
dev_err(&pdev->dev, "of_probe: name error(%d)\n", ret);
goto err;
}
- ep->ep.name = name;
+ ep->ep.name = kasprintf(GFP_KERNEL, "ep%d", ep->index);
ep->ep_regs = udc->regs + USBA_EPT_BASE(i);
ep->dma_regs = udc->regs + USBA_DMA_BASE(i);
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 1e5f529..0630648 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -1308,11 +1308,6 @@ MODULE_LICENSE ("GPL");
#define PLATFORM_DRIVER ehci_mv_driver
#endif
-#ifdef CONFIG_MIPS_SEAD3
-#include "ehci-sead3.c"
-#define PLATFORM_DRIVER ehci_hcd_sead3_driver
-#endif
-
static int __init ehci_hcd_init(void)
{
int retval = 0;
diff --git a/drivers/usb/host/ehci-platform.c b/drivers/usb/host/ehci-platform.c
index 876dca4..a268d9e 100644
--- a/drivers/usb/host/ehci-platform.c
+++ b/drivers/usb/host/ehci-platform.c
@@ -39,7 +39,7 @@
#define DRIVER_DESC "EHCI generic platform driver"
#define EHCI_MAX_CLKS 4
-#define EHCI_MAX_RSTS 3
+#define EHCI_MAX_RSTS 4
#define hcd_to_ehci_priv(h) ((struct ehci_platform_priv *)hcd_to_ehci(h)->priv)
struct ehci_platform_priv {
diff --git a/drivers/usb/host/ehci-sead3.c b/drivers/usb/host/ehci-sead3.c
deleted file mode 100644
index 3d86cc2..0000000
--- a/drivers/usb/host/ehci-sead3.c
+++ /dev/null
@@ -1,185 +0,0 @@
-/*
- * MIPS CI13320A EHCI Host Controller driver
- * Based on "ehci-au1xxx.c" by K.Boge <karsten.boge@amd.com>
- *
- * Copyright (C) 2012 MIPS Technologies, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
- * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
- * for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software Foundation,
- * Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/err.h>
-#include <linux/platform_device.h>
-
-static int ehci_sead3_setup(struct usb_hcd *hcd)
-{
- int ret;
- struct ehci_hcd *ehci = hcd_to_ehci(hcd);
-
- ehci->caps = hcd->regs + 0x100;
-
-#ifdef __BIG_ENDIAN
- ehci->big_endian_mmio = 1;
- ehci->big_endian_desc = 1;
-#endif
-
- ret = ehci_setup(hcd);
- if (ret)
- return ret;
-
- ehci->need_io_watchdog = 0;
-
- /* Set burst length to 16 words. */
- ehci_writel(ehci, 0x1010, &ehci->regs->reserved1[1]);
-
- return ret;
-}
-
-const struct hc_driver ehci_sead3_hc_driver = {
- .description = hcd_name,
- .product_desc = "SEAD-3 EHCI",
- .hcd_priv_size = sizeof(struct ehci_hcd),
-
- /*
- * generic hardware linkage
- */
- .irq = ehci_irq,
- .flags = HCD_MEMORY | HCD_USB2 | HCD_BH,
-
- /*
- * basic lifecycle operations
- *
- */
- .reset = ehci_sead3_setup,
- .start = ehci_run,
- .stop = ehci_stop,
- .shutdown = ehci_shutdown,
-
- /*
- * managing i/o requests and associated device resources
- */
- .urb_enqueue = ehci_urb_enqueue,
- .urb_dequeue = ehci_urb_dequeue,
- .endpoint_disable = ehci_endpoint_disable,
- .endpoint_reset = ehci_endpoint_reset,
-
- /*
- * scheduling support
- */
- .get_frame_number = ehci_get_frame,
-
- /*
- * root hub support
- */
- .hub_status_data = ehci_hub_status_data,
- .hub_control = ehci_hub_control,
- .bus_suspend = ehci_bus_suspend,
- .bus_resume = ehci_bus_resume,
- .relinquish_port = ehci_relinquish_port,
- .port_handed_over = ehci_port_handed_over,
-
- .clear_tt_buffer_complete = ehci_clear_tt_buffer_complete,
-};
-
-static int ehci_hcd_sead3_drv_probe(struct platform_device *pdev)
-{
- struct usb_hcd *hcd;
- struct resource *res;
- int ret;
-
- if (usb_disabled())
- return -ENODEV;
-
- if (pdev->resource[1].flags != IORESOURCE_IRQ) {
- pr_debug("resource[1] is not IORESOURCE_IRQ");
- return -ENOMEM;
- }
- hcd = usb_create_hcd(&ehci_sead3_hc_driver, &pdev->dev, "SEAD-3");
- if (!hcd)
- return -ENOMEM;
-
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- hcd->regs = devm_ioremap_resource(&pdev->dev, res);
- if (IS_ERR(hcd->regs)) {
- ret = PTR_ERR(hcd->regs);
- goto err1;
- }
- hcd->rsrc_start = res->start;
- hcd->rsrc_len = resource_size(res);
-
- /* Root hub has integrated TT. */
- hcd->has_tt = 1;
-
- ret = usb_add_hcd(hcd, pdev->resource[1].start,
- IRQF_SHARED);
- if (ret == 0) {
- platform_set_drvdata(pdev, hcd);
- device_wakeup_enable(hcd->self.controller);
- return ret;
- }
-
-err1:
- usb_put_hcd(hcd);
- return ret;
-}
-
-static int ehci_hcd_sead3_drv_remove(struct platform_device *pdev)
-{
- struct usb_hcd *hcd = platform_get_drvdata(pdev);
-
- usb_remove_hcd(hcd);
- usb_put_hcd(hcd);
-
- return 0;
-}
-
-#ifdef CONFIG_PM
-static int ehci_hcd_sead3_drv_suspend(struct device *dev)
-{
- struct usb_hcd *hcd = dev_get_drvdata(dev);
- bool do_wakeup = device_may_wakeup(dev);
-
- return ehci_suspend(hcd, do_wakeup);
-}
-
-static int ehci_hcd_sead3_drv_resume(struct device *dev)
-{
- struct usb_hcd *hcd = dev_get_drvdata(dev);
-
- ehci_resume(hcd, false);
- return 0;
-}
-
-static const struct dev_pm_ops sead3_ehci_pmops = {
- .suspend = ehci_hcd_sead3_drv_suspend,
- .resume = ehci_hcd_sead3_drv_resume,
-};
-
-#define SEAD3_EHCI_PMOPS (&sead3_ehci_pmops)
-
-#else
-#define SEAD3_EHCI_PMOPS NULL
-#endif
-
-static struct platform_driver ehci_hcd_sead3_driver = {
- .probe = ehci_hcd_sead3_drv_probe,
- .remove = ehci_hcd_sead3_drv_remove,
- .shutdown = usb_hcd_platform_shutdown,
- .driver = {
- .name = "sead3-ehci",
- .pm = SEAD3_EHCI_PMOPS,
- }
-};
-
-MODULE_ALIAS("platform:sead3-ehci");
diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c
index 5b5880c..b38a228 100644
--- a/drivers/usb/host/ohci-at91.c
+++ b/drivers/usb/host/ohci-at91.c
@@ -221,6 +221,12 @@ static int usb_hcd_at91_probe(const struct hc_driver *driver,
ohci->num_ports = board->ports;
at91_start_hc(pdev);
+ /*
+ * The RemoteWakeupConnected bit has to be set explicitly
+ * before calling ohci_run. The reset value of this bit is 0.
+ */
+ ohci->hc_control = OHCI_CTRL_RWC;
+
retval = usb_add_hcd(hcd, irq, IRQF_SHARED);
if (retval == 0) {
device_wakeup_enable(hcd->self.controller);
@@ -677,9 +683,6 @@ ohci_hcd_at91_drv_suspend(struct device *dev)
* REVISIT: some boards will be able to turn VBUS off...
*/
if (!ohci_at91->wakeup) {
- ohci->hc_control = ohci_readl(ohci, &ohci->regs->control);
- ohci->hc_control &= OHCI_CTRL_RWC;
- ohci_writel(ohci, ohci->hc_control, &ohci->regs->control);
ohci->rh_state = OHCI_RH_HALTED;
/* flush the writes */
diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index 1700908..86612ac 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -72,7 +72,7 @@
static const char hcd_name [] = "ohci_hcd";
#define STATECHANGE_DELAY msecs_to_jiffies(300)
-#define IO_WATCHDOG_DELAY msecs_to_jiffies(250)
+#define IO_WATCHDOG_DELAY msecs_to_jiffies(275)
#include "ohci.h"
#include "pci-quirks.h"
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index d793f54..a9a1e4c 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -995,6 +995,14 @@ static void quirk_usb_handoff_xhci(struct pci_dev *pdev)
}
val = readl(base + ext_cap_offset);
+ /* Auto handoff never worked for these devices. Force it and continue */
+ if ((pdev->vendor == PCI_VENDOR_ID_TI && pdev->device == 0x8241) ||
+ (pdev->vendor == PCI_VENDOR_ID_RENESAS
+ && pdev->device == 0x0014)) {
+ val = (val | XHCI_HC_OS_OWNED) & ~XHCI_HC_BIOS_OWNED;
+ writel(val, base + ext_cap_offset);
+ }
+
/* If the BIOS owns the HC, signal that the OS wants it, and wait */
if (val & XHCI_HC_BIOS_OWNED) {
writel(val | XHCI_HC_OS_OWNED, base + ext_cap_offset);
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 730b9fd..0ef1690 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -1166,7 +1166,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
xhci_set_link_state(xhci, port_array, wIndex,
XDEV_RESUME);
spin_unlock_irqrestore(&xhci->lock, flags);
- msleep(20);
+ msleep(USB_RESUME_TIMEOUT);
spin_lock_irqsave(&xhci->lock, flags);
xhci_set_link_state(xhci, port_array, wIndex,
XDEV_U0);
@@ -1355,6 +1355,35 @@ int xhci_bus_suspend(struct usb_hcd *hcd)
return 0;
}
+/*
+ * Workaround for missing Cold Attach Status (CAS) if device re-plugged in S3.
+ * warm reset a USB3 device stuck in polling or compliance mode after resume.
+ * See Intel 100/c230 series PCH specification update Doc #332692-006 Errata #8
+ */
+static bool xhci_port_missing_cas_quirk(int port_index,
+ __le32 __iomem **port_array)
+{
+ u32 portsc;
+
+ portsc = readl(port_array[port_index]);
+
+ /* if any of these are set we are not stuck */
+ if (portsc & (PORT_CONNECT | PORT_CAS))
+ return false;
+
+ if (((portsc & PORT_PLS_MASK) != XDEV_POLLING) &&
+ ((portsc & PORT_PLS_MASK) != XDEV_COMP_MODE))
+ return false;
+
+ /* clear wakeup/change bits, and do a warm port reset */
+ portsc &= ~(PORT_RWC_BITS | PORT_CEC | PORT_WAKE_BITS);
+ portsc |= PORT_WR;
+ writel(portsc, port_array[port_index]);
+ /* flush write */
+ readl(port_array[port_index]);
+ return true;
+}
+
int xhci_bus_resume(struct usb_hcd *hcd)
{
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
@@ -1392,6 +1421,14 @@ int xhci_bus_resume(struct usb_hcd *hcd)
u32 temp;
temp = readl(port_array[port_index]);
+
+ /* warm reset CAS limited ports stuck in polling/compliance */
+ if ((xhci->quirks & XHCI_MISSING_CAS) &&
+ (hcd->speed >= HCD_USB3) &&
+ xhci_port_missing_cas_quirk(port_index, port_array)) {
+ xhci_dbg(xhci, "reset stuck port %d\n", port_index);
+ continue;
+ }
if (DEV_SUPERSPEED_ANY(temp))
temp &= ~(PORT_RWC_BITS | PORT_CEC | PORT_WAKE_BITS);
else
@@ -1410,7 +1447,7 @@ int xhci_bus_resume(struct usb_hcd *hcd)
if (need_usb2_u3_exit) {
spin_unlock_irqrestore(&xhci->lock, flags);
- msleep(20);
+ msleep(USB_RESUME_TIMEOUT);
spin_lock_irqsave(&xhci->lock, flags);
}
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index d7b0f97..e96ae80 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -45,11 +45,13 @@
#define PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI 0x8c31
#define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI 0x9c31
+#define PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_XHCI 0x9cb1
#define PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI 0x22b5
#define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI 0xa12f
#define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI 0x9d2f
#define PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI 0x0aa8
#define PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI 0x1aa8
+#define PCI_DEVICE_ID_INTEL_APL_XHCI 0x5aa8
static const char hcd_name[] = "xhci_hcd";
@@ -153,7 +155,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
xhci->quirks |= XHCI_SPURIOUS_REBOOT;
}
if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
- pdev->device == PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI) {
+ (pdev->device == PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI ||
+ pdev->device == PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_XHCI)) {
xhci->quirks |= XHCI_SPURIOUS_REBOOT;
xhci->quirks |= XHCI_SPURIOUS_WAKEUP;
}
@@ -169,6 +172,11 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI) {
xhci->quirks |= XHCI_SSIC_PORT_UNUSED;
}
+ if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+ (pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI ||
+ pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI))
+ xhci->quirks |= XHCI_MISSING_CAS;
+
if (pdev->vendor == PCI_VENDOR_ID_ETRON &&
pdev->device == PCI_DEVICE_ID_EJ168) {
xhci->quirks |= XHCI_RESET_ON_RESUME;
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index b2c1dc5..f945380 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -314,6 +314,8 @@ struct xhci_op_regs {
#define XDEV_U2 (0x2 << 5)
#define XDEV_U3 (0x3 << 5)
#define XDEV_INACTIVE (0x6 << 5)
+#define XDEV_POLLING (0x7 << 5)
+#define XDEV_COMP_MODE (0xa << 5)
#define XDEV_RESUME (0xf << 5)
/* true: port has power (see HCC_PPC) */
#define PORT_POWER (1 << 9)
@@ -1653,6 +1655,7 @@ struct xhci_hcd {
#define XHCI_MTK_HOST (1 << 21)
#define XHCI_SSIC_PORT_UNUSED (1 << 22)
#define XHCI_NO_64BIT_SUPPORT (1 << 23)
+#define XHCI_MISSING_CAS (1 << 24)
unsigned int num_active_eps;
unsigned int limit_active_eps;
/* There are two roothubs to keep track of bus suspend info for */
diff --git a/drivers/usb/musb/da8xx.c b/drivers/usb/musb/da8xx.c
index 210b7e4..2440f88 100644
--- a/drivers/usb/musb/da8xx.c
+++ b/drivers/usb/musb/da8xx.c
@@ -479,7 +479,8 @@ static int da8xx_probe(struct platform_device *pdev)
glue->phy = devm_phy_get(&pdev->dev, "usb-phy");
if (IS_ERR(glue->phy)) {
- dev_err(&pdev->dev, "failed to get phy\n");
+ if (PTR_ERR(glue->phy) != -EPROBE_DEFER)
+ dev_err(&pdev->dev, "failed to get phy\n");
return PTR_ERR(glue->phy);
}
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 27dadc0..e01116e 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -2114,11 +2114,6 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
musb->io.ep_offset = musb_flat_ep_offset;
musb->io.ep_select = musb_flat_ep_select;
}
- /* And override them with platform specific ops if specified. */
- if (musb->ops->ep_offset)
- musb->io.ep_offset = musb->ops->ep_offset;
- if (musb->ops->ep_select)
- musb->io.ep_select = musb->ops->ep_select;
/* At least tusb6010 has its own offsets */
if (musb->ops->ep_offset)
diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c
index bff4869..4042ea0 100644
--- a/drivers/usb/musb/musb_gadget.c
+++ b/drivers/usb/musb/musb_gadget.c
@@ -1255,6 +1255,7 @@ static int musb_gadget_queue(struct usb_ep *ep, struct usb_request *req,
map_dma_buffer(request, musb, musb_ep);
+ pm_runtime_get_sync(musb->controller);
spin_lock_irqsave(&musb->lock, lockflags);
/* don't queue if the ep is down */
@@ -1275,6 +1276,9 @@ static int musb_gadget_queue(struct usb_ep *ep, struct usb_request *req,
unlock:
spin_unlock_irqrestore(&musb->lock, lockflags);
+ pm_runtime_mark_last_busy(musb->controller);
+ pm_runtime_put_autosuspend(musb->controller);
+
return status;
}
diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index 1ab6973..cc12254 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -287,6 +287,7 @@ static int omap2430_musb_init(struct musb *musb)
}
musb->isr = omap2430_musb_interrupt;
phy_init(musb->phy);
+ phy_power_on(musb->phy);
l = musb_readl(musb->mregs, OTG_INTERFSEL);
@@ -323,8 +324,6 @@ static void omap2430_musb_enable(struct musb *musb)
struct musb_hdrc_platform_data *pdata = dev_get_platdata(dev);
struct omap_musb_board_data *data = pdata->board_data;
- if (!WARN_ON(!musb->phy))
- phy_power_on(musb->phy);
switch (glue->status) {
@@ -361,9 +360,6 @@ static void omap2430_musb_disable(struct musb *musb)
struct device *dev = musb->controller;
struct omap2430_glue *glue = dev_get_drvdata(dev->parent);
- if (!WARN_ON(!musb->phy))
- phy_power_off(musb->phy);
-
if (glue->status != MUSB_UNKNOWN)
omap_control_usb_set_mode(glue->control_otghs,
USB_MODE_DISCONNECT);
@@ -375,6 +371,7 @@ static int omap2430_musb_exit(struct musb *musb)
struct omap2430_glue *glue = dev_get_drvdata(dev->parent);
omap2430_low_level_exit(musb);
+ phy_power_off(musb->phy);
phy_exit(musb->phy);
musb->phy = NULL;
cancel_work_sync(&glue->omap_musb_mailbox_work);
diff --git a/drivers/usb/renesas_usbhs/rcar3.c b/drivers/usb/renesas_usbhs/rcar3.c
index 1d70add..d544b33 100644
--- a/drivers/usb/renesas_usbhs/rcar3.c
+++ b/drivers/usb/renesas_usbhs/rcar3.c
@@ -9,6 +9,7 @@
*
*/
+#include <linux/delay.h>
#include <linux/io.h>
#include "common.h"
#include "rcar3.h"
@@ -35,10 +36,13 @@ static int usbhs_rcar3_power_ctrl(struct platform_device *pdev,
usbhs_write32(priv, UGCTRL2, UGCTRL2_RESERVED_3 | UGCTRL2_USB0SEL_OTG);
- if (enable)
+ if (enable) {
usbhs_bset(priv, LPSTS, LPSTS_SUSPM, LPSTS_SUSPM);
- else
+ /* The controller on R-Car Gen3 needs to wait up to 45 usec */
+ udelay(45);
+ } else {
usbhs_bset(priv, LPSTS, LPSTS_SUSPM, 0);
+ }
return 0;
}
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 54a4de0..f61477b 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -1077,7 +1077,9 @@ static int cp210x_tiocmget(struct tty_struct *tty)
u8 control;
int result;
- cp210x_read_u8_reg(port, CP210X_GET_MDMSTS, &control);
+ result = cp210x_read_u8_reg(port, CP210X_GET_MDMSTS, &control);
+ if (result)
+ return result;
result = ((control & CONTROL_DTR) ? TIOCM_DTR : 0)
|((control & CONTROL_RTS) ? TIOCM_RTS : 0)
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index b2d767e..0ff7f38 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -986,7 +986,8 @@ static const struct usb_device_id id_table_combined[] = {
/* ekey Devices */
{ USB_DEVICE(FTDI_VID, FTDI_EKEY_CONV_USB_PID) },
/* Infineon Devices */
- { USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_PID, 1) },
+ { USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_TC1798_PID, 1) },
+ { USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_TC2X7_PID, 1) },
/* GE Healthcare devices */
{ USB_DEVICE(GE_HEALTHCARE_VID, GE_HEALTHCARE_NEMO_TRACKER_PID) },
/* Active Research (Actisense) devices */
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index f87a938..21011c0 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -626,8 +626,9 @@
/*
* Infineon Technologies
*/
-#define INFINEON_VID 0x058b
-#define INFINEON_TRIBOARD_PID 0x0028 /* DAS JTAG TriBoard TC1798 V1.0 */
+#define INFINEON_VID 0x058b
+#define INFINEON_TRIBOARD_TC1798_PID 0x0028 /* DAS JTAG TriBoard TC1798 V1.0 */
+#define INFINEON_TRIBOARD_TC2X7_PID 0x0043 /* DAS JTAG TriBoard TC2X7 V1.0 */
/*
* Acton Research Corp.
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index d213cf4..4a037b4 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -1078,7 +1078,8 @@ static int usb_serial_probe(struct usb_interface *interface,
serial->disconnected = 0;
- usb_serial_console_init(serial->port[0]->minor);
+ if (num_ports > 0)
+ usb_serial_console_init(serial->port[0]->minor);
exit:
module_put(type->driver.owner);
return 0;
diff --git a/drivers/usb/wusbcore/crypto.c b/drivers/usb/wusbcore/crypto.c
index 79b2b62..79451f7 100644
--- a/drivers/usb/wusbcore/crypto.c
+++ b/drivers/usb/wusbcore/crypto.c
@@ -133,6 +133,13 @@ static void bytewise_xor(void *_bo, const void *_bi1, const void *_bi2,
bo[itr] = bi1[itr] ^ bi2[itr];
}
+/* Scratch space for MAC calculations. */
+struct wusb_mac_scratch {
+ struct aes_ccm_b0 b0;
+ struct aes_ccm_b1 b1;
+ struct aes_ccm_a ax;
+};
+
/*
* CC-MAC function WUSB1.0[6.5]
*
@@ -197,16 +204,15 @@ static void bytewise_xor(void *_bo, const void *_bi1, const void *_bi2,
* what sg[4] is for. Maybe there is a smarter way to do this.
*/
static int wusb_ccm_mac(struct crypto_skcipher *tfm_cbc,
- struct crypto_cipher *tfm_aes, void *mic,
+ struct crypto_cipher *tfm_aes,
+ struct wusb_mac_scratch *scratch,
+ void *mic,
const struct aes_ccm_nonce *n,
const struct aes_ccm_label *a, const void *b,
size_t blen)
{
int result = 0;
SKCIPHER_REQUEST_ON_STACK(req, tfm_cbc);
- struct aes_ccm_b0 b0;
- struct aes_ccm_b1 b1;
- struct aes_ccm_a ax;
struct scatterlist sg[4], sg_dst;
void *dst_buf;
size_t dst_size;
@@ -218,16 +224,17 @@ static int wusb_ccm_mac(struct crypto_skcipher *tfm_cbc,
* These checks should be compile time optimized out
* ensure @a fills b1's mac_header and following fields
*/
- WARN_ON(sizeof(*a) != sizeof(b1) - sizeof(b1.la));
- WARN_ON(sizeof(b0) != sizeof(struct aes_ccm_block));
- WARN_ON(sizeof(b1) != sizeof(struct aes_ccm_block));
- WARN_ON(sizeof(ax) != sizeof(struct aes_ccm_block));
+ WARN_ON(sizeof(*a) != sizeof(scratch->b1) - sizeof(scratch->b1.la));
+ WARN_ON(sizeof(scratch->b0) != sizeof(struct aes_ccm_block));
+ WARN_ON(sizeof(scratch->b1) != sizeof(struct aes_ccm_block));
+ WARN_ON(sizeof(scratch->ax) != sizeof(struct aes_ccm_block));
result = -ENOMEM;
zero_padding = blen % sizeof(struct aes_ccm_block);
if (zero_padding)
zero_padding = sizeof(struct aes_ccm_block) - zero_padding;
- dst_size = blen + sizeof(b0) + sizeof(b1) + zero_padding;
+ dst_size = blen + sizeof(scratch->b0) + sizeof(scratch->b1) +
+ zero_padding;
dst_buf = kzalloc(dst_size, GFP_KERNEL);
if (!dst_buf)
goto error_dst_buf;
@@ -235,9 +242,9 @@ static int wusb_ccm_mac(struct crypto_skcipher *tfm_cbc,
memset(iv, 0, sizeof(iv));
/* Setup B0 */
- b0.flags = 0x59; /* Format B0 */
- b0.ccm_nonce = *n;
- b0.lm = cpu_to_be16(0); /* WUSB1.0[6.5] sez l(m) is 0 */
+ scratch->b0.flags = 0x59; /* Format B0 */
+ scratch->b0.ccm_nonce = *n;
+ scratch->b0.lm = cpu_to_be16(0); /* WUSB1.0[6.5] sez l(m) is 0 */
/* Setup B1
*
@@ -246,12 +253,12 @@ static int wusb_ccm_mac(struct crypto_skcipher *tfm_cbc,
* 14'--after clarification, it means to use A's contents
* for MAC Header, EO, sec reserved and padding.
*/
- b1.la = cpu_to_be16(blen + 14);
- memcpy(&b1.mac_header, a, sizeof(*a));
+ scratch->b1.la = cpu_to_be16(blen + 14);
+ memcpy(&scratch->b1.mac_header, a, sizeof(*a));
sg_init_table(sg, ARRAY_SIZE(sg));
- sg_set_buf(&sg[0], &b0, sizeof(b0));
- sg_set_buf(&sg[1], &b1, sizeof(b1));
+ sg_set_buf(&sg[0], &scratch->b0, sizeof(scratch->b0));
+ sg_set_buf(&sg[1], &scratch->b1, sizeof(scratch->b1));
sg_set_buf(&sg[2], b, blen);
/* 0 if well behaved :) */
sg_set_buf(&sg[3], bzero, zero_padding);
@@ -276,11 +283,12 @@ static int wusb_ccm_mac(struct crypto_skcipher *tfm_cbc,
* POS Crypto API: size is assumed to be AES's block size.
* Thanks for documenting it -- tip taken from airo.c
*/
- ax.flags = 0x01; /* as per WUSB 1.0 spec */
- ax.ccm_nonce = *n;
- ax.counter = 0;
- crypto_cipher_encrypt_one(tfm_aes, (void *)&ax, (void *)&ax);
- bytewise_xor(mic, &ax, iv, 8);
+ scratch->ax.flags = 0x01; /* as per WUSB 1.0 spec */
+ scratch->ax.ccm_nonce = *n;
+ scratch->ax.counter = 0;
+ crypto_cipher_encrypt_one(tfm_aes, (void *)&scratch->ax,
+ (void *)&scratch->ax);
+ bytewise_xor(mic, &scratch->ax, iv, 8);
result = 8;
error_cbc_crypt:
kfree(dst_buf);
@@ -303,6 +311,7 @@ ssize_t wusb_prf(void *out, size_t out_size,
struct aes_ccm_nonce n = *_n;
struct crypto_skcipher *tfm_cbc;
struct crypto_cipher *tfm_aes;
+ struct wusb_mac_scratch *scratch;
u64 sfn = 0;
__le64 sfn_le;
@@ -329,17 +338,25 @@ ssize_t wusb_prf(void *out, size_t out_size,
printk(KERN_ERR "E: can't set AES key: %d\n", (int)result);
goto error_setkey_aes;
}
+ scratch = kmalloc(sizeof(*scratch), GFP_KERNEL);
+ if (!scratch) {
+ result = -ENOMEM;
+ goto error_alloc_scratch;
+ }
for (bitr = 0; bitr < (len + 63) / 64; bitr++) {
sfn_le = cpu_to_le64(sfn++);
memcpy(&n.sfn, &sfn_le, sizeof(n.sfn)); /* n.sfn++... */
- result = wusb_ccm_mac(tfm_cbc, tfm_aes, out + bytes,
+ result = wusb_ccm_mac(tfm_cbc, tfm_aes, scratch, out + bytes,
&n, a, b, blen);
if (result < 0)
goto error_ccm_mac;
bytes += result;
}
result = bytes;
+
+ kfree(scratch);
+error_alloc_scratch:
error_ccm_mac:
error_setkey_aes:
crypto_free_cipher(tfm_aes);
diff --git a/drivers/uwb/lc-rc.c b/drivers/uwb/lc-rc.c
index d059ad4..97ee1b4 100644
--- a/drivers/uwb/lc-rc.c
+++ b/drivers/uwb/lc-rc.c
@@ -56,8 +56,11 @@ static struct uwb_rc *uwb_rc_find_by_index(int index)
struct uwb_rc *rc = NULL;
dev = class_find_device(&uwb_rc_class, NULL, &index, uwb_rc_index_match);
- if (dev)
+ if (dev) {
rc = dev_get_drvdata(dev);
+ put_device(dev);
+ }
+
return rc;
}
@@ -467,7 +470,9 @@ struct uwb_rc *__uwb_rc_try_get(struct uwb_rc *target_rc)
if (dev) {
rc = dev_get_drvdata(dev);
__uwb_rc_get(rc);
+ put_device(dev);
}
+
return rc;
}
EXPORT_SYMBOL_GPL(__uwb_rc_try_get);
@@ -520,8 +525,11 @@ struct uwb_rc *uwb_rc_get_by_grandpa(const struct device *grandpa_dev)
dev = class_find_device(&uwb_rc_class, NULL, grandpa_dev,
find_rc_grandpa);
- if (dev)
+ if (dev) {
rc = dev_get_drvdata(dev);
+ put_device(dev);
+ }
+
return rc;
}
EXPORT_SYMBOL_GPL(uwb_rc_get_by_grandpa);
@@ -553,8 +561,10 @@ struct uwb_rc *uwb_rc_get_by_dev(const struct uwb_dev_addr *addr)
struct uwb_rc *rc = NULL;
dev = class_find_device(&uwb_rc_class, NULL, addr, find_rc_dev);
- if (dev)
+ if (dev) {
rc = dev_get_drvdata(dev);
+ put_device(dev);
+ }
return rc;
}
diff --git a/drivers/uwb/pal.c b/drivers/uwb/pal.c
index c1304b8..678e937 100644
--- a/drivers/uwb/pal.c
+++ b/drivers/uwb/pal.c
@@ -97,6 +97,8 @@ static bool uwb_rc_class_device_exists(struct uwb_rc *target_rc)
dev = class_find_device(&uwb_rc_class, NULL, target_rc, find_rc);
+ put_device(dev);
+
return (dev != NULL);
}
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index d624a52..031bc08 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -829,8 +829,9 @@ static long vfio_pci_ioctl(void *device_data,
} else if (cmd == VFIO_DEVICE_SET_IRQS) {
struct vfio_irq_set hdr;
+ size_t size;
u8 *data = NULL;
- int ret = 0;
+ int max, ret = 0;
minsz = offsetofend(struct vfio_irq_set, count);
@@ -838,23 +839,31 @@ static long vfio_pci_ioctl(void *device_data,
return -EFAULT;
if (hdr.argsz < minsz || hdr.index >= VFIO_PCI_NUM_IRQS ||
+ hdr.count >= (U32_MAX - hdr.start) ||
hdr.flags & ~(VFIO_IRQ_SET_DATA_TYPE_MASK |
VFIO_IRQ_SET_ACTION_TYPE_MASK))
return -EINVAL;
- if (!(hdr.flags & VFIO_IRQ_SET_DATA_NONE)) {
- size_t size;
- int max = vfio_pci_get_irq_count(vdev, hdr.index);
+ max = vfio_pci_get_irq_count(vdev, hdr.index);
+ if (hdr.start >= max || hdr.start + hdr.count > max)
+ return -EINVAL;
- if (hdr.flags & VFIO_IRQ_SET_DATA_BOOL)
- size = sizeof(uint8_t);
- else if (hdr.flags & VFIO_IRQ_SET_DATA_EVENTFD)
- size = sizeof(int32_t);
- else
- return -EINVAL;
+ switch (hdr.flags & VFIO_IRQ_SET_DATA_TYPE_MASK) {
+ case VFIO_IRQ_SET_DATA_NONE:
+ size = 0;
+ break;
+ case VFIO_IRQ_SET_DATA_BOOL:
+ size = sizeof(uint8_t);
+ break;
+ case VFIO_IRQ_SET_DATA_EVENTFD:
+ size = sizeof(int32_t);
+ break;
+ default:
+ return -EINVAL;
+ }
- if (hdr.argsz - minsz < hdr.count * size ||
- hdr.start >= max || hdr.start + hdr.count > max)
+ if (size) {
+ if (hdr.argsz - minsz < hdr.count * size)
return -EINVAL;
data = memdup_user((void __user *)(arg + minsz),
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index c2e6089..1c46045 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -256,7 +256,7 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix)
if (!is_irq_none(vdev))
return -EINVAL;
- vdev->ctx = kzalloc(nvec * sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL);
+ vdev->ctx = kcalloc(nvec, sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL);
if (!vdev->ctx)
return -ENOMEM;
diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index af2f117..5d3b0db 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -2187,7 +2187,7 @@
config FB_COBALT
tristate "Cobalt server LCD frame buffer support"
- depends on FB && (MIPS_COBALT || MIPS_SEAD3)
+ depends on FB && MIPS_COBALT
config FB_SH7760
bool "SH7760/SH7763/SH7720/SH7721 LCDC support"
diff --git a/drivers/video/fbdev/cobalt_lcdfb.c b/drivers/video/fbdev/cobalt_lcdfb.c
index 07675d6..2d3b691 100644
--- a/drivers/video/fbdev/cobalt_lcdfb.c
+++ b/drivers/video/fbdev/cobalt_lcdfb.c
@@ -63,7 +63,6 @@
#define LCD_CUR_POS(x) ((x) & LCD_CUR_POS_MASK)
#define LCD_TEXT_POS(x) ((x) | LCD_TEXT_MODE)
-#ifdef CONFIG_MIPS_COBALT
static inline void lcd_write_control(struct fb_info *info, u8 control)
{
writel((u32)control << 24, info->screen_base);
@@ -83,47 +82,6 @@ static inline u8 lcd_read_data(struct fb_info *info)
{
return readl(info->screen_base + LCD_DATA_REG_OFFSET) >> 24;
}
-#else
-
-#define LCD_CTL 0x00
-#define LCD_DATA 0x08
-#define CPLD_STATUS 0x10
-#define CPLD_DATA 0x18
-
-static inline void cpld_wait(struct fb_info *info)
-{
- do {
- } while (readl(info->screen_base + CPLD_STATUS) & 1);
-}
-
-static inline void lcd_write_control(struct fb_info *info, u8 control)
-{
- cpld_wait(info);
- writel(control, info->screen_base + LCD_CTL);
-}
-
-static inline u8 lcd_read_control(struct fb_info *info)
-{
- cpld_wait(info);
- readl(info->screen_base + LCD_CTL);
- cpld_wait(info);
- return readl(info->screen_base + CPLD_DATA) & 0xff;
-}
-
-static inline void lcd_write_data(struct fb_info *info, u8 data)
-{
- cpld_wait(info);
- writel(data, info->screen_base + LCD_DATA);
-}
-
-static inline u8 lcd_read_data(struct fb_info *info)
-{
- cpld_wait(info);
- readl(info->screen_base + LCD_DATA);
- cpld_wait(info);
- return readl(info->screen_base + CPLD_DATA) & 0xff;
-}
-#endif
static int lcd_busy_wait(struct fb_info *info)
{
diff --git a/drivers/video/fbdev/pvr2fb.c b/drivers/video/fbdev/pvr2fb.c
index 3b1ca44..a2564ab 100644
--- a/drivers/video/fbdev/pvr2fb.c
+++ b/drivers/video/fbdev/pvr2fb.c
@@ -686,8 +686,8 @@ static ssize_t pvr2fb_write(struct fb_info *info, const char *buf,
if (!pages)
return -ENOMEM;
- ret = get_user_pages_unlocked((unsigned long)buf, nr_pages, WRITE,
- 0, pages);
+ ret = get_user_pages_unlocked((unsigned long)buf, nr_pages, pages,
+ FOLL_WRITE);
if (ret < nr_pages) {
nr_pages = ret;
diff --git a/drivers/virt/fsl_hypervisor.c b/drivers/virt/fsl_hypervisor.c
index 60bdad3..150ce2a 100644
--- a/drivers/virt/fsl_hypervisor.c
+++ b/drivers/virt/fsl_hypervisor.c
@@ -245,8 +245,8 @@ static long ioctl_memcpy(struct fsl_hv_ioctl_memcpy __user *p)
/* Get the physical addresses of the source buffer */
down_read(¤t->mm->mmap_sem);
num_pinned = get_user_pages(param.local_vaddr - lb_offset,
- num_pages, (param.source == -1) ? READ : WRITE,
- 0, pages, NULL);
+ num_pages, (param.source == -1) ? 0 : FOLL_WRITE,
+ pages, NULL);
up_read(¤t->mm->mmap_sem);
if (num_pinned != num_pages) {
diff --git a/drivers/virtio/config.c b/drivers/virtio/config.c
deleted file mode 100644
index f70bcd2..0000000
--- a/drivers/virtio/config.c
+++ /dev/null
@@ -1,12 +0,0 @@
-/* Configuration space parsing helpers for virtio.
- *
- * The configuration is [type][len][... len bytes ...] fields.
- *
- * Copyright 2007 Rusty Russell, IBM Corporation.
- * GPL v2 or later.
- */
-#include <linux/err.h>
-#include <linux/virtio.h>
-#include <linux/virtio_config.h>
-#include <linux/bug.h>
-
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 4e7003d..181793f 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -577,6 +577,8 @@ static int virtballoon_probe(struct virtio_device *vdev)
virtio_device_ready(vdev);
+ if (towards_target(vb))
+ virtballoon_changed(vdev);
return 0;
out_del_vqs:
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index 8c4e617..6d9e517 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -212,10 +212,18 @@ int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev)
return -ENODEV;
}
- rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64));
- if (rc)
- rc = dma_set_mask_and_coherent(&pci_dev->dev,
- DMA_BIT_MASK(32));
+ rc = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(64));
+ if (rc) {
+ rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32));
+ } else {
+ /*
+ * The virtio ring base address is expressed as a 32-bit PFN,
+ * with a page size of 1 << VIRTIO_PCI_QUEUE_ADDR_SHIFT.
+ */
+ dma_set_coherent_mask(&pci_dev->dev,
+ DMA_BIT_MASK(32 + VIRTIO_PCI_QUEUE_ADDR_SHIFT));
+ }
+
if (rc)
dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA. Trying to continue, but this might not work.\n");
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index ed9c9ee..489bfc6 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -167,7 +167,7 @@ static bool vring_use_dma_api(struct virtio_device *vdev)
* making all of the arch DMA ops work on the vring device itself
* is a mess. For now, we use the parent device for DMA ops.
*/
-static struct device *vring_dma_dev(const struct vring_virtqueue *vq)
+static inline struct device *vring_dma_dev(const struct vring_virtqueue *vq)
{
return vq->vq.vdev->dev.parent;
}
@@ -732,7 +732,8 @@ void virtqueue_disable_cb(struct virtqueue *_vq)
if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
- vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
}
}
@@ -764,7 +765,8 @@ unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
* entry. Always do both to keep code simple. */
if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
- vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
}
vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
END_USE(vq);
@@ -832,10 +834,11 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
* more to do. */
/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
* either clear the flags bit or point the event index at the next
- * entry. Always do both to keep code simple. */
+ * entry. Always update the event index to keep code simple. */
if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
- vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
}
/* TODO: tune this threshold */
bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
@@ -953,7 +956,8 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
/* No callback? Tell other side not to bother us. */
if (!callback) {
vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
- vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
+ if (!vq->event)
+ vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
}
/* Put everything in free lists. */
diff --git a/drivers/vme/vme.c b/drivers/vme/vme.c
index 15b6407..bdbadaa 100644
--- a/drivers/vme/vme.c
+++ b/drivers/vme/vme.c
@@ -156,12 +156,16 @@ size_t vme_get_size(struct vme_resource *resource)
case VME_MASTER:
retval = vme_master_get(resource, &enabled, &base, &size,
&aspace, &cycle, &dwidth);
+ if (retval)
+ return 0;
return size;
break;
case VME_SLAVE:
retval = vme_slave_get(resource, &enabled, &base, &size,
&buf_base, &aspace, &cycle);
+ if (retval)
+ return 0;
return size;
break;
diff --git a/drivers/watchdog/wdat_wdt.c b/drivers/watchdog/wdat_wdt.c
index e473e3b..6d1fbda 100644
--- a/drivers/watchdog/wdat_wdt.c
+++ b/drivers/watchdog/wdat_wdt.c
@@ -499,6 +499,10 @@ static int wdat_wdt_resume_noirq(struct device *dev)
ret = wdat_wdt_enable_reboot(wdat);
if (ret)
return ret;
+
+ ret = wdat_wdt_ping(&wdat->wdd);
+ if (ret)
+ return ret;
}
return wdat_wdt_start(&wdat->wdd);
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index e12bd36..26e5e85 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -168,7 +168,9 @@ static void do_suspend(void)
#endif /* CONFIG_HIBERNATE_CALLBACKS */
struct shutdown_handler {
- const char *command;
+#define SHUTDOWN_CMD_SIZE 11
+ const char command[SHUTDOWN_CMD_SIZE];
+ bool flag;
void (*cb)(void);
};
@@ -206,22 +208,22 @@ static void do_reboot(void)
ctrl_alt_del();
}
+static struct shutdown_handler shutdown_handlers[] = {
+ { "poweroff", true, do_poweroff },
+ { "halt", false, do_poweroff },
+ { "reboot", true, do_reboot },
+#ifdef CONFIG_HIBERNATE_CALLBACKS
+ { "suspend", true, do_suspend },
+#endif
+};
+
static void shutdown_handler(struct xenbus_watch *watch,
const char **vec, unsigned int len)
{
char *str;
struct xenbus_transaction xbt;
int err;
- static struct shutdown_handler handlers[] = {
- { "poweroff", do_poweroff },
- { "halt", do_poweroff },
- { "reboot", do_reboot },
-#ifdef CONFIG_HIBERNATE_CALLBACKS
- { "suspend", do_suspend },
-#endif
- {NULL, NULL},
- };
- static struct shutdown_handler *handler;
+ int idx;
if (shutting_down != SHUTDOWN_INVALID)
return;
@@ -238,13 +240,13 @@ static void shutdown_handler(struct xenbus_watch *watch,
return;
}
- for (handler = &handlers[0]; handler->command; handler++) {
- if (strcmp(str, handler->command) == 0)
+ for (idx = 0; idx < ARRAY_SIZE(shutdown_handlers); idx++) {
+ if (strcmp(str, shutdown_handlers[idx].command) == 0)
break;
}
/* Only acknowledge commands which we are prepared to handle. */
- if (handler->cb)
+ if (idx < ARRAY_SIZE(shutdown_handlers))
xenbus_write(xbt, "control", "shutdown", "");
err = xenbus_transaction_end(xbt, 0);
@@ -253,8 +255,8 @@ static void shutdown_handler(struct xenbus_watch *watch,
goto again;
}
- if (handler->cb) {
- handler->cb();
+ if (idx < ARRAY_SIZE(shutdown_handlers)) {
+ shutdown_handlers[idx].cb();
} else {
pr_info("Ignoring shutdown request: %s\n", str);
shutting_down = SHUTDOWN_INVALID;
@@ -310,6 +312,9 @@ static struct notifier_block xen_reboot_nb = {
static int setup_shutdown_watcher(void)
{
int err;
+ int idx;
+#define FEATURE_PATH_SIZE (SHUTDOWN_CMD_SIZE + sizeof("feature-"))
+ char node[FEATURE_PATH_SIZE];
err = register_xenbus_watch(&shutdown_watch);
if (err) {
@@ -326,6 +331,14 @@ static int setup_shutdown_watcher(void)
}
#endif
+ for (idx = 0; idx < ARRAY_SIZE(shutdown_handlers); idx++) {
+ if (!shutdown_handlers[idx].flag)
+ continue;
+ snprintf(node, FEATURE_PATH_SIZE, "feature-%s",
+ shutdown_handlers[idx].command);
+ xenbus_printf(XBT_NIL, "control", node, "%u", 1);
+ }
+
return 0;
}
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index c1010f01..1e8be12 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -364,7 +364,7 @@ static int xenbus_write_transaction(unsigned msg_type,
static int xenbus_write_watch(unsigned msg_type, struct xenbus_file_priv *u)
{
- struct watch_adapter *watch, *tmp_watch;
+ struct watch_adapter *watch;
char *path, *token;
int err, rc;
LIST_HEAD(staging_q);
@@ -399,7 +399,7 @@ static int xenbus_write_watch(unsigned msg_type, struct xenbus_file_priv *u)
}
list_add(&watch->list, &u->watches);
} else {
- list_for_each_entry_safe(watch, tmp_watch, &u->watches, list) {
+ list_for_each_entry(watch, &u->watches, list) {
if (!strcmp(watch->token, token) &&
!strcmp(watch->watch.node, path)) {
unregister_xenbus_watch(&watch->watch);
diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c
index 611a231..6d40a97 100644
--- a/drivers/xen/xenbus/xenbus_probe_frontend.c
+++ b/drivers/xen/xenbus/xenbus_probe_frontend.c
@@ -335,7 +335,9 @@ static int backend_state;
static void xenbus_reset_backend_state_changed(struct xenbus_watch *w,
const char **v, unsigned int l)
{
- xenbus_scanf(XBT_NIL, v[XS_WATCH_PATH], "", "%i", &backend_state);
+ if (xenbus_scanf(XBT_NIL, v[XS_WATCH_PATH], "", "%i",
+ &backend_state) != 1)
+ backend_state = XenbusStateUnknown;
printk(KERN_DEBUG "XENBUS: backend %s %s\n",
v[XS_WATCH_PATH], xenbus_strstate(backend_state));
wake_up(&backend_state_wq);
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 2037e7a..d764236 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -91,11 +91,9 @@ static const struct afs_call_type afs_SRXCBTellMeAboutYourself = {
*/
bool afs_cm_incoming_call(struct afs_call *call)
{
- u32 operation_id = ntohl(call->operation_ID);
+ _enter("{CB.OP %u}", call->operation_ID);
- _enter("{CB.OP %u}", operation_id);
-
- switch (operation_id) {
+ switch (call->operation_ID) {
case CBCallBack:
call->type = &afs_SRXCBCallBack;
return true;
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 96f4d76..31c616a 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -364,7 +364,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
buffer = kmap(page);
ret = afs_extract_data(call, buffer,
call->count, true);
- kunmap(buffer);
+ kunmap(page);
if (ret < 0)
return ret;
}
@@ -397,7 +397,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
page = call->reply3;
buffer = kmap(page);
memset(buffer + call->count, 0, PAGE_SIZE - call->count);
- kunmap(buffer);
+ kunmap(page);
}
_leave(" = 0 [done]");
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 5497c84..535a38d 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -112,7 +112,7 @@ struct afs_call {
bool need_attention; /* T if RxRPC poked us */
u16 service_id; /* RxRPC service ID to call */
__be16 port; /* target UDP port */
- __be32 operation_ID; /* operation ID for an incoming call */
+ u32 operation_ID; /* operation ID for an incoming call */
u32 count; /* count for use in unmarshalling */
__be32 tmp; /* place to extract temporary data */
afs_dataversion_t store_version; /* updated version expected from store */
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 477928b..25f05a8 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -676,10 +676,11 @@ static int afs_deliver_cm_op_id(struct afs_call *call)
ASSERTCMP(call->offset, <, 4);
/* the operation ID forms the first four bytes of the request data */
- ret = afs_extract_data(call, &call->operation_ID, 4, true);
+ ret = afs_extract_data(call, &call->tmp, 4, true);
if (ret < 0)
return ret;
+ call->operation_ID = ntohl(call->tmp);
call->state = AFS_CALL_AWAIT_REQUEST;
call->offset = 0;
diff --git a/fs/aio.c b/fs/aio.c
index 1157e13..428484f 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1078,6 +1078,17 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
unsigned tail, pos, head;
unsigned long flags;
+ if (kiocb->ki_flags & IOCB_WRITE) {
+ struct file *file = kiocb->ki_filp;
+
+ /*
+ * Tell lockdep we inherited freeze protection from submission
+ * thread.
+ */
+ __sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+ file_end_write(file);
+ }
+
/*
* Special case handling for sync iocbs:
* - events go directly into the iocb for fast handling
@@ -1392,122 +1403,106 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
return -EINVAL;
}
-typedef ssize_t (rw_iter_op)(struct kiocb *, struct iov_iter *);
-
-static int aio_setup_vectored_rw(int rw, char __user *buf, size_t len,
- struct iovec **iovec,
- bool compat,
- struct iov_iter *iter)
+static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec,
+ bool vectored, bool compat, struct iov_iter *iter)
{
+ void __user *buf = (void __user *)(uintptr_t)iocb->aio_buf;
+ size_t len = iocb->aio_nbytes;
+
+ if (!vectored) {
+ ssize_t ret = import_single_range(rw, buf, len, *iovec, iter);
+ *iovec = NULL;
+ return ret;
+ }
#ifdef CONFIG_COMPAT
if (compat)
- return compat_import_iovec(rw,
- (struct compat_iovec __user *)buf,
- len, UIO_FASTIOV, iovec, iter);
+ return compat_import_iovec(rw, buf, len, UIO_FASTIOV, iovec,
+ iter);
#endif
- return import_iovec(rw, (struct iovec __user *)buf,
- len, UIO_FASTIOV, iovec, iter);
+ return import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter);
}
-/*
- * aio_run_iocb:
- * Performs the initial checks and io submission.
- */
-static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
- char __user *buf, size_t len, bool compat)
+static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
{
- struct file *file = req->ki_filp;
- ssize_t ret;
- int rw;
- fmode_t mode;
- rw_iter_op *iter_op;
- struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
- struct iov_iter iter;
-
- switch (opcode) {
- case IOCB_CMD_PREAD:
- case IOCB_CMD_PREADV:
- mode = FMODE_READ;
- rw = READ;
- iter_op = file->f_op->read_iter;
- goto rw_common;
-
- case IOCB_CMD_PWRITE:
- case IOCB_CMD_PWRITEV:
- mode = FMODE_WRITE;
- rw = WRITE;
- iter_op = file->f_op->write_iter;
- goto rw_common;
-rw_common:
- if (unlikely(!(file->f_mode & mode)))
- return -EBADF;
-
- if (!iter_op)
- return -EINVAL;
-
- if (opcode == IOCB_CMD_PREADV || opcode == IOCB_CMD_PWRITEV)
- ret = aio_setup_vectored_rw(rw, buf, len,
- &iovec, compat, &iter);
- else {
- ret = import_single_range(rw, buf, len, iovec, &iter);
- iovec = NULL;
- }
- if (!ret)
- ret = rw_verify_area(rw, file, &req->ki_pos,
- iov_iter_count(&iter));
- if (ret < 0) {
- kfree(iovec);
- return ret;
- }
-
- if (rw == WRITE)
- file_start_write(file);
-
- ret = iter_op(req, &iter);
-
- if (rw == WRITE)
- file_end_write(file);
- kfree(iovec);
- break;
-
- case IOCB_CMD_FDSYNC:
- if (!file->f_op->aio_fsync)
- return -EINVAL;
-
- ret = file->f_op->aio_fsync(req, 1);
- break;
-
- case IOCB_CMD_FSYNC:
- if (!file->f_op->aio_fsync)
- return -EINVAL;
-
- ret = file->f_op->aio_fsync(req, 0);
- break;
-
- default:
- pr_debug("EINVAL: no operation provided\n");
- return -EINVAL;
- }
-
- if (ret != -EIOCBQUEUED) {
+ switch (ret) {
+ case -EIOCBQUEUED:
+ return ret;
+ case -ERESTARTSYS:
+ case -ERESTARTNOINTR:
+ case -ERESTARTNOHAND:
+ case -ERESTART_RESTARTBLOCK:
/*
* There's no easy way to restart the syscall since other AIO's
* may be already running. Just fail this IO with EINTR.
*/
- if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR ||
- ret == -ERESTARTNOHAND ||
- ret == -ERESTART_RESTARTBLOCK))
- ret = -EINTR;
+ ret = -EINTR;
+ /*FALLTHRU*/
+ default:
aio_complete(req, ret, 0);
+ return 0;
}
+}
- return 0;
+static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored,
+ bool compat)
+{
+ struct file *file = req->ki_filp;
+ struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
+ struct iov_iter iter;
+ ssize_t ret;
+
+ if (unlikely(!(file->f_mode & FMODE_READ)))
+ return -EBADF;
+ if (unlikely(!file->f_op->read_iter))
+ return -EINVAL;
+
+ ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter);
+ if (ret)
+ return ret;
+ ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter));
+ if (!ret)
+ ret = aio_ret(req, file->f_op->read_iter(req, &iter));
+ kfree(iovec);
+ return ret;
+}
+
+static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
+ bool compat)
+{
+ struct file *file = req->ki_filp;
+ struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
+ struct iov_iter iter;
+ ssize_t ret;
+
+ if (unlikely(!(file->f_mode & FMODE_WRITE)))
+ return -EBADF;
+ if (unlikely(!file->f_op->write_iter))
+ return -EINVAL;
+
+ ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter);
+ if (ret)
+ return ret;
+ ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter));
+ if (!ret) {
+ req->ki_flags |= IOCB_WRITE;
+ file_start_write(file);
+ ret = aio_ret(req, file->f_op->write_iter(req, &iter));
+ /*
+ * We release freeze protection in aio_complete(). Fool lockdep
+ * by telling it the lock got released so that it doesn't
+ * complain about held lock when we return to userspace.
+ */
+ __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+ }
+ kfree(iovec);
+ return ret;
}
static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
struct iocb *iocb, bool compat)
{
struct aio_kiocb *req;
+ struct file *file;
ssize_t ret;
/* enforce forwards compatibility on users */
@@ -1530,7 +1525,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
if (unlikely(!req))
return -EAGAIN;
- req->common.ki_filp = fget(iocb->aio_fildes);
+ req->common.ki_filp = file = fget(iocb->aio_fildes);
if (unlikely(!req->common.ki_filp)) {
ret = -EBADF;
goto out_put_req;
@@ -1565,13 +1560,29 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
req->ki_user_iocb = user_iocb;
req->ki_user_data = iocb->aio_data;
- ret = aio_run_iocb(&req->common, iocb->aio_lio_opcode,
- (char __user *)(unsigned long)iocb->aio_buf,
- iocb->aio_nbytes,
- compat);
- if (ret)
- goto out_put_req;
+ get_file(file);
+ switch (iocb->aio_lio_opcode) {
+ case IOCB_CMD_PREAD:
+ ret = aio_read(&req->common, iocb, false, compat);
+ break;
+ case IOCB_CMD_PWRITE:
+ ret = aio_write(&req->common, iocb, false, compat);
+ break;
+ case IOCB_CMD_PREADV:
+ ret = aio_read(&req->common, iocb, true, compat);
+ break;
+ case IOCB_CMD_PWRITEV:
+ ret = aio_write(&req->common, iocb, true, compat);
+ break;
+ default:
+ pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
+ ret = -EINVAL;
+ break;
+ }
+ fput(file);
+ if (ret && ret != -EIOCBQUEUED)
+ goto out_put_req;
return 0;
out_put_req:
put_reqs_available(ctx, 1);
diff --git a/fs/befs/befs.h b/fs/befs/befs.h
index e0f59263a..c6bad51 100644
--- a/fs/befs/befs.h
+++ b/fs/befs/befs.h
@@ -43,7 +43,10 @@ struct befs_sb_info {
u32 ag_shift;
u32 num_ags;
- /* jornal log entry */
+ /* State of the superblock */
+ u32 flags;
+
+ /* Journal log entry */
befs_block_run log_blocks;
befs_off_t log_start;
befs_off_t log_end;
@@ -79,7 +82,7 @@ enum befs_err {
BEFS_BT_END,
BEFS_BT_EMPTY,
BEFS_BT_MATCH,
- BEFS_BT_PARMATCH,
+ BEFS_BT_OVERFLOW,
BEFS_BT_NOT_FOUND
};
@@ -140,18 +143,6 @@ befs_iaddrs_per_block(struct super_block *sb)
return BEFS_SB(sb)->block_size / sizeof (befs_disk_inode_addr);
}
-static inline int
-befs_iaddr_is_empty(const befs_inode_addr *iaddr)
-{
- return (!iaddr->allocation_group) && (!iaddr->start) && (!iaddr->len);
-}
-
-static inline size_t
-befs_brun_size(struct super_block *sb, befs_block_run run)
-{
- return BEFS_SB(sb)->block_size * run.len;
-}
-
#include "endian.h"
#endif /* _LINUX_BEFS_H */
diff --git a/fs/befs/btree.c b/fs/befs/btree.c
index 307645f9..7e135ea 100644
--- a/fs/befs/btree.c
+++ b/fs/befs/btree.c
@@ -85,7 +85,7 @@ struct befs_btree_node {
};
/* local constants */
-static const befs_off_t befs_bt_inval = 0xffffffffffffffffULL;
+static const befs_off_t BEFS_BT_INVAL = 0xffffffffffffffffULL;
/* local functions */
static int befs_btree_seekleaf(struct super_block *sb, const befs_data_stream *ds,
@@ -156,8 +156,6 @@ befs_bt_read_super(struct super_block *sb, const befs_data_stream *ds,
sup->max_depth = fs32_to_cpu(sb, od_sup->max_depth);
sup->data_type = fs32_to_cpu(sb, od_sup->data_type);
sup->root_node_ptr = fs64_to_cpu(sb, od_sup->root_node_ptr);
- sup->free_node_ptr = fs64_to_cpu(sb, od_sup->free_node_ptr);
- sup->max_size = fs64_to_cpu(sb, od_sup->max_size);
brelse(bh);
if (sup->magic != BEFS_BTREE_MAGIC) {
@@ -183,8 +181,8 @@ befs_bt_read_super(struct super_block *sb, const befs_data_stream *ds,
* Calls befs_read_datastream to read in the indicated btree node and
* makes sure its header fields are in cpu byteorder, byteswapping if
* necessary.
- * Note: node->bh must be NULL when this function called first
- * time. Don't forget brelse(node->bh) after last call.
+ * Note: node->bh must be NULL when this function is called the first time.
+ * Don't forget brelse(node->bh) after last call.
*
* On success, returns BEFS_OK and *@node contains the btree node that
* starts at @node_off, with the node->head fields in cpu byte order.
@@ -244,7 +242,7 @@ befs_bt_read_node(struct super_block *sb, const befs_data_stream *ds,
* Read the superblock and rootnode of the b+tree.
* Drill down through the interior nodes using befs_find_key().
* Once at the correct leaf node, use befs_find_key() again to get the
- * actuall value stored with the key.
+ * actual value stored with the key.
*/
int
befs_btree_find(struct super_block *sb, const befs_data_stream *ds,
@@ -283,9 +281,9 @@ befs_btree_find(struct super_block *sb, const befs_data_stream *ds,
while (!befs_leafnode(this_node)) {
res = befs_find_key(sb, this_node, key, &node_off);
- if (res == BEFS_BT_NOT_FOUND)
+ /* if no key set, try the overflow node */
+ if (res == BEFS_BT_OVERFLOW)
node_off = this_node->head.overflow;
- /* if no match, go to overflow node */
if (befs_bt_read_node(sb, ds, this_node, node_off) != BEFS_OK) {
befs_error(sb, "befs_btree_find() failed to read "
"node at %llu", node_off);
@@ -293,15 +291,15 @@ befs_btree_find(struct super_block *sb, const befs_data_stream *ds,
}
}
- /* at the correct leaf node now */
-
+ /* at a leaf node now, check if it is correct */
res = befs_find_key(sb, this_node, key, value);
brelse(this_node->bh);
kfree(this_node);
if (res != BEFS_BT_MATCH) {
- befs_debug(sb, "<--- %s Key %s not found", __func__, key);
+ befs_error(sb, "<--- %s Key %s not found", __func__, key);
+ befs_debug(sb, "<--- %s ERROR", __func__);
*value = 0;
return BEFS_BT_NOT_FOUND;
}
@@ -324,16 +322,12 @@ befs_btree_find(struct super_block *sb, const befs_data_stream *ds,
* @findkey: Keystring to search for
* @value: If key is found, the value stored with the key is put here
*
- * finds exact match if one exists, and returns BEFS_BT_MATCH
- * If no exact match, finds first key in node that is greater
- * (alphabetically) than the search key and returns BEFS_BT_PARMATCH
- * (for partial match, I guess). Can you think of something better to
- * call it?
+ * Finds exact match if one exists, and returns BEFS_BT_MATCH.
+ * If there is no match and node's value array is too small for key, return
+ * BEFS_BT_OVERFLOW.
+ * If no match and node should countain this key, return BEFS_BT_NOT_FOUND.
*
- * If no key was a match or greater than the search key, return
- * BEFS_BT_NOT_FOUND.
- *
- * Use binary search instead of a linear.
+ * Uses binary search instead of a linear.
*/
static int
befs_find_key(struct super_block *sb, struct befs_btree_node *node,
@@ -348,18 +342,16 @@ befs_find_key(struct super_block *sb, struct befs_btree_node *node,
befs_debug(sb, "---> %s %s", __func__, findkey);
- *value = 0;
-
findkey_len = strlen(findkey);
- /* if node can not contain key, just skeep this node */
+ /* if node can not contain key, just skip this node */
last = node->head.all_key_count - 1;
thiskey = befs_bt_get_key(sb, node, last, &keylen);
eq = befs_compare_strings(thiskey, keylen, findkey, findkey_len);
if (eq < 0) {
- befs_debug(sb, "<--- %s %s not found", __func__, findkey);
- return BEFS_BT_NOT_FOUND;
+ befs_debug(sb, "<--- node can't contain %s", findkey);
+ return BEFS_BT_OVERFLOW;
}
valarray = befs_bt_valarray(node);
@@ -387,12 +379,15 @@ befs_find_key(struct super_block *sb, struct befs_btree_node *node,
else
first = mid + 1;
}
+
+ /* return an existing value so caller can arrive to a leaf node */
if (eq < 0)
*value = fs64_to_cpu(sb, valarray[mid + 1]);
else
*value = fs64_to_cpu(sb, valarray[mid]);
- befs_debug(sb, "<--- %s found %s at %d", __func__, thiskey, mid);
- return BEFS_BT_PARMATCH;
+ befs_error(sb, "<--- %s %s not found", __func__, findkey);
+ befs_debug(sb, "<--- %s ERROR", __func__);
+ return BEFS_BT_NOT_FOUND;
}
/**
@@ -405,7 +400,7 @@ befs_find_key(struct super_block *sb, struct befs_btree_node *node,
* @keysize: Length of the returned key
* @value: Value stored with the returned key
*
- * Heres how it works: Key_no is the index of the key/value pair to
+ * Here's how it works: Key_no is the index of the key/value pair to
* return in keybuf/value.
* Bufsize is the size of keybuf (BEFS_NAME_LEN+1 is a good size). Keysize is
* the number of characters in the key (just a convenience).
@@ -422,7 +417,7 @@ befs_btree_read(struct super_block *sb, const befs_data_stream *ds,
{
struct befs_btree_node *this_node;
befs_btree_super bt_super;
- befs_off_t node_off = 0;
+ befs_off_t node_off;
int cur_key;
fs64 *valarray;
char *keystart;
@@ -467,7 +462,7 @@ befs_btree_read(struct super_block *sb, const befs_data_stream *ds,
while (key_sum + this_node->head.all_key_count <= key_no) {
/* no more nodes to look in: key_no is too large */
- if (this_node->head.right == befs_bt_inval) {
+ if (this_node->head.right == BEFS_BT_INVAL) {
*keysize = 0;
*value = 0;
befs_debug(sb,
@@ -541,7 +536,6 @@ befs_btree_read(struct super_block *sb, const befs_data_stream *ds,
* @node_off: Pointer to offset of current node within datastream. Modified
* by the function.
*
- *
* Helper function for btree traverse. Moves the current position to the
* start of the first leaf node.
*
@@ -608,7 +602,7 @@ static int
befs_leafnode(struct befs_btree_node *node)
{
/* all interior nodes (and only interior nodes) have an overflow node */
- if (node->head.overflow == befs_bt_inval)
+ if (node->head.overflow == BEFS_BT_INVAL)
return 1;
else
return 0;
@@ -715,7 +709,7 @@ befs_bt_get_key(struct super_block *sb, struct befs_btree_node *node,
*
* Returns 0 if @key1 and @key2 are equal.
* Returns >0 if @key1 is greater.
- * Returns <0 if @key2 is greater..
+ * Returns <0 if @key2 is greater.
*/
static int
befs_compare_strings(const void *key1, int keylen1,
diff --git a/fs/befs/datastream.c b/fs/befs/datastream.c
index af1bc19..b4c7ba0 100644
--- a/fs/befs/datastream.c
+++ b/fs/befs/datastream.c
@@ -22,22 +22,22 @@ const befs_inode_addr BAD_IADDR = { 0, 0, 0 };
static int befs_find_brun_direct(struct super_block *sb,
const befs_data_stream *data,
- befs_blocknr_t blockno, befs_block_run * run);
+ befs_blocknr_t blockno, befs_block_run *run);
static int befs_find_brun_indirect(struct super_block *sb,
const befs_data_stream *data,
befs_blocknr_t blockno,
- befs_block_run * run);
+ befs_block_run *run);
static int befs_find_brun_dblindirect(struct super_block *sb,
const befs_data_stream *data,
befs_blocknr_t blockno,
- befs_block_run * run);
+ befs_block_run *run);
/**
* befs_read_datastream - get buffer_head containing data, starting from pos.
* @sb: Filesystem superblock
- * @ds: datastrem to find data with
+ * @ds: datastream to find data with
* @pos: start of data
* @off: offset of data in buffer_head->b_data
*
@@ -46,7 +46,7 @@ static int befs_find_brun_dblindirect(struct super_block *sb,
*/
struct buffer_head *
befs_read_datastream(struct super_block *sb, const befs_data_stream *ds,
- befs_off_t pos, uint * off)
+ befs_off_t pos, uint *off)
{
struct buffer_head *bh;
befs_block_run run;
@@ -75,7 +75,13 @@ befs_read_datastream(struct super_block *sb, const befs_data_stream *ds,
return bh;
}
-/*
+/**
+ * befs_fblock2brun - give back block run for fblock
+ * @sb: the superblock
+ * @data: datastream to read from
+ * @fblock: the blocknumber with the file position to find
+ * @run: The found run is passed back through this pointer
+ *
* Takes a file position and gives back a brun who's starting block
* is block number fblock of the file.
*
@@ -88,7 +94,7 @@ befs_read_datastream(struct super_block *sb, const befs_data_stream *ds,
*/
int
befs_fblock2brun(struct super_block *sb, const befs_data_stream *data,
- befs_blocknr_t fblock, befs_block_run * run)
+ befs_blocknr_t fblock, befs_block_run *run)
{
int err;
befs_off_t pos = fblock << BEFS_SB(sb)->block_shift;
@@ -115,7 +121,7 @@ befs_fblock2brun(struct super_block *sb, const befs_data_stream *data,
/**
* befs_read_lsmylink - read long symlink from datastream.
* @sb: Filesystem superblock
- * @ds: Datastrem to read from
+ * @ds: Datastream to read from
* @buff: Buffer in which to place long symlink data
* @len: Length of the long symlink in bytes
*
@@ -128,6 +134,7 @@ befs_read_lsymlink(struct super_block *sb, const befs_data_stream *ds,
befs_off_t bytes_read = 0; /* bytes readed */
u16 plen;
struct buffer_head *bh;
+
befs_debug(sb, "---> %s length: %llu", __func__, len);
while (bytes_read < len) {
@@ -183,13 +190,13 @@ befs_count_blocks(struct super_block *sb, const befs_data_stream *ds)
metablocks += ds->indirect.len;
/*
- Double indir block, plus all the indirect blocks it mapps
- In the double-indirect range, all block runs of data are
- BEFS_DBLINDIR_BRUN_LEN blocks long. Therefore, we know
- how many data block runs are in the double-indirect region,
- and from that we know how many indirect blocks it takes to
- map them. We assume that the indirect blocks are also
- BEFS_DBLINDIR_BRUN_LEN blocks long.
+ * Double indir block, plus all the indirect blocks it maps.
+ * In the double-indirect range, all block runs of data are
+ * BEFS_DBLINDIR_BRUN_LEN blocks long. Therefore, we know
+ * how many data block runs are in the double-indirect region,
+ * and from that we know how many indirect blocks it takes to
+ * map them. We assume that the indirect blocks are also
+ * BEFS_DBLINDIR_BRUN_LEN blocks long.
*/
if (ds->size > ds->max_indirect_range && ds->max_indirect_range != 0) {
uint dbl_bytes;
@@ -212,58 +219,50 @@ befs_count_blocks(struct super_block *sb, const befs_data_stream *ds)
return blocks;
}
-/*
- Finds the block run that starts at file block number blockno
- in the file represented by the datastream data, if that
- blockno is in the direct region of the datastream.
-
- sb: the superblock
- data: the datastream
- blockno: the blocknumber to find
- run: The found run is passed back through this pointer
-
- Return value is BEFS_OK if the blockrun is found, BEFS_ERR
- otherwise.
-
- Algorithm:
- Linear search. Checks each element of array[] to see if it
- contains the blockno-th filesystem block. This is necessary
- because the block runs map variable amounts of data. Simply
- keeps a count of the number of blocks searched so far (sum),
- incrementing this by the length of each block run as we come
- across it. Adds sum to *count before returning (this is so
- you can search multiple arrays that are logicaly one array,
- as in the indirect region code).
-
- When/if blockno is found, if blockno is inside of a block
- run as stored on disk, we offset the start and length members
- of the block run, so that blockno is the start and len is
- still valid (the run ends in the same place).
-
- 2001-11-15 Will Dyson
-*/
+/**
+ * befs_find_brun_direct - find a direct block run in the datastream
+ * @sb: the superblock
+ * @data: the datastream
+ * @blockno: the blocknumber to find
+ * @run: The found run is passed back through this pointer
+ *
+ * Finds the block run that starts at file block number blockno
+ * in the file represented by the datastream data, if that
+ * blockno is in the direct region of the datastream.
+ *
+ * Return value is BEFS_OK if the blockrun is found, BEFS_ERR
+ * otherwise.
+ *
+ * Algorithm:
+ * Linear search. Checks each element of array[] to see if it
+ * contains the blockno-th filesystem block. This is necessary
+ * because the block runs map variable amounts of data. Simply
+ * keeps a count of the number of blocks searched so far (sum),
+ * incrementing this by the length of each block run as we come
+ * across it. Adds sum to *count before returning (this is so
+ * you can search multiple arrays that are logicaly one array,
+ * as in the indirect region code).
+ *
+ * When/if blockno is found, if blockno is inside of a block
+ * run as stored on disk, we offset the start and length members
+ * of the block run, so that blockno is the start and len is
+ * still valid (the run ends in the same place).
+ */
static int
befs_find_brun_direct(struct super_block *sb, const befs_data_stream *data,
- befs_blocknr_t blockno, befs_block_run * run)
+ befs_blocknr_t blockno, befs_block_run *run)
{
int i;
const befs_block_run *array = data->direct;
befs_blocknr_t sum;
- befs_blocknr_t max_block =
- data->max_direct_range >> BEFS_SB(sb)->block_shift;
befs_debug(sb, "---> %s, find %lu", __func__, (unsigned long)blockno);
- if (blockno > max_block) {
- befs_error(sb, "%s passed block outside of direct region",
- __func__);
- return BEFS_ERR;
- }
-
for (i = 0, sum = 0; i < BEFS_NUM_DIRECT_BLOCKS;
sum += array[i].len, i++) {
if (blockno >= sum && blockno < sum + (array[i].len)) {
int offset = blockno - sum;
+
run->allocation_group = array[i].allocation_group;
run->start = array[i].start + offset;
run->len = array[i].len - offset;
@@ -275,38 +274,39 @@ befs_find_brun_direct(struct super_block *sb, const befs_data_stream *data,
}
}
+ befs_error(sb, "%s failed to find file block %lu", __func__,
+ (unsigned long)blockno);
befs_debug(sb, "---> %s ERROR", __func__);
return BEFS_ERR;
}
-/*
- Finds the block run that starts at file block number blockno
- in the file represented by the datastream data, if that
- blockno is in the indirect region of the datastream.
-
- sb: the superblock
- data: the datastream
- blockno: the blocknumber to find
- run: The found run is passed back through this pointer
-
- Return value is BEFS_OK if the blockrun is found, BEFS_ERR
- otherwise.
-
- Algorithm:
- For each block in the indirect run of the datastream, read
- it in and search through it for search_blk.
-
- XXX:
- Really should check to make sure blockno is inside indirect
- region.
-
- 2001-11-15 Will Dyson
-*/
+/**
+ * befs_find_brun_indirect - find a block run in the datastream
+ * @sb: the superblock
+ * @data: the datastream
+ * @blockno: the blocknumber to find
+ * @run: The found run is passed back through this pointer
+ *
+ * Finds the block run that starts at file block number blockno
+ * in the file represented by the datastream data, if that
+ * blockno is in the indirect region of the datastream.
+ *
+ * Return value is BEFS_OK if the blockrun is found, BEFS_ERR
+ * otherwise.
+ *
+ * Algorithm:
+ * For each block in the indirect run of the datastream, read
+ * it in and search through it for search_blk.
+ *
+ * XXX:
+ * Really should check to make sure blockno is inside indirect
+ * region.
+ */
static int
befs_find_brun_indirect(struct super_block *sb,
const befs_data_stream *data,
befs_blocknr_t blockno,
- befs_block_run * run)
+ befs_block_run *run)
{
int i, j;
befs_blocknr_t sum = 0;
@@ -326,11 +326,12 @@ befs_find_brun_indirect(struct super_block *sb,
/* Examine blocks of the indirect run one at a time */
for (i = 0; i < indirect.len; i++) {
- indirblock = befs_bread(sb, indirblockno + i);
+ indirblock = sb_bread(sb, indirblockno + i);
if (indirblock == NULL) {
- befs_debug(sb, "---> %s failed to read "
+ befs_error(sb, "---> %s failed to read "
"disk block %lu from the indirect brun",
__func__, (unsigned long)indirblockno + i);
+ befs_debug(sb, "<--- %s ERROR", __func__);
return BEFS_ERR;
}
@@ -370,52 +371,51 @@ befs_find_brun_indirect(struct super_block *sb,
return BEFS_ERR;
}
-/*
- Finds the block run that starts at file block number blockno
- in the file represented by the datastream data, if that
- blockno is in the double-indirect region of the datastream.
-
- sb: the superblock
- data: the datastream
- blockno: the blocknumber to find
- run: The found run is passed back through this pointer
-
- Return value is BEFS_OK if the blockrun is found, BEFS_ERR
- otherwise.
-
- Algorithm:
- The block runs in the double-indirect region are different.
- They are always allocated 4 fs blocks at a time, so each
- block run maps a constant amount of file data. This means
- that we can directly calculate how many block runs into the
- double-indirect region we need to go to get to the one that
- maps a particular filesystem block.
-
- We do this in two stages. First we calculate which of the
- inode addresses in the double-indirect block will point us
- to the indirect block that contains the mapping for the data,
- then we calculate which of the inode addresses in that
- indirect block maps the data block we are after.
-
- Oh, and once we've done that, we actually read in the blocks
- that contain the inode addresses we calculated above. Even
- though the double-indirect run may be several blocks long,
- we can calculate which of those blocks will contain the index
- we are after and only read that one. We then follow it to
- the indirect block and perform a similar process to find
- the actual block run that maps the data block we are interested
- in.
-
- Then we offset the run as in befs_find_brun_array() and we are
- done.
-
- 2001-11-15 Will Dyson
-*/
+/**
+ * befs_find_brun_dblindirect - find a block run in the datastream
+ * @sb: the superblock
+ * @data: the datastream
+ * @blockno: the blocknumber to find
+ * @run: The found run is passed back through this pointer
+ *
+ * Finds the block run that starts at file block number blockno
+ * in the file represented by the datastream data, if that
+ * blockno is in the double-indirect region of the datastream.
+ *
+ * Return value is BEFS_OK if the blockrun is found, BEFS_ERR
+ * otherwise.
+ *
+ * Algorithm:
+ * The block runs in the double-indirect region are different.
+ * They are always allocated 4 fs blocks at a time, so each
+ * block run maps a constant amount of file data. This means
+ * that we can directly calculate how many block runs into the
+ * double-indirect region we need to go to get to the one that
+ * maps a particular filesystem block.
+ *
+ * We do this in two stages. First we calculate which of the
+ * inode addresses in the double-indirect block will point us
+ * to the indirect block that contains the mapping for the data,
+ * then we calculate which of the inode addresses in that
+ * indirect block maps the data block we are after.
+ *
+ * Oh, and once we've done that, we actually read in the blocks
+ * that contain the inode addresses we calculated above. Even
+ * though the double-indirect run may be several blocks long,
+ * we can calculate which of those blocks will contain the index
+ * we are after and only read that one. We then follow it to
+ * the indirect block and perform a similar process to find
+ * the actual block run that maps the data block we are interested
+ * in.
+ *
+ * Then we offset the run as in befs_find_brun_array() and we are
+ * done.
+ */
static int
befs_find_brun_dblindirect(struct super_block *sb,
const befs_data_stream *data,
befs_blocknr_t blockno,
- befs_block_run * run)
+ befs_block_run *run)
{
int dblindir_indx;
int indir_indx;
@@ -430,10 +430,9 @@ befs_find_brun_dblindirect(struct super_block *sb,
struct buffer_head *indir_block;
befs_block_run indir_run;
befs_disk_inode_addr *iaddr_array;
- struct befs_sb_info *befs_sb = BEFS_SB(sb);
befs_blocknr_t indir_start_blk =
- data->max_indirect_range >> befs_sb->block_shift;
+ data->max_indirect_range >> BEFS_SB(sb)->block_shift;
off_t dbl_indir_off = blockno - indir_start_blk;
@@ -471,7 +470,7 @@ befs_find_brun_dblindirect(struct super_block *sb,
}
dbl_indir_block =
- befs_bread(sb, iaddr2blockno(sb, &data->double_indirect) +
+ sb_bread(sb, iaddr2blockno(sb, &data->double_indirect) +
dbl_which_block);
if (dbl_indir_block == NULL) {
befs_error(sb, "%s couldn't read the "
@@ -479,7 +478,6 @@ befs_find_brun_dblindirect(struct super_block *sb,
(unsigned long)
iaddr2blockno(sb, &data->double_indirect) +
dbl_which_block);
- brelse(dbl_indir_block);
return BEFS_ERR;
}
@@ -499,12 +497,11 @@ befs_find_brun_dblindirect(struct super_block *sb,
}
indir_block =
- befs_bread(sb, iaddr2blockno(sb, &indir_run) + which_block);
+ sb_bread(sb, iaddr2blockno(sb, &indir_run) + which_block);
if (indir_block == NULL) {
befs_error(sb, "%s couldn't read the indirect block "
"at blockno %lu", __func__, (unsigned long)
iaddr2blockno(sb, &indir_run) + which_block);
- brelse(indir_block);
return BEFS_ERR;
}
diff --git a/fs/befs/debug.c b/fs/befs/debug.c
index 4de7cff..85c1339 100644
--- a/fs/befs/debug.c
+++ b/fs/befs/debug.c
@@ -169,6 +169,7 @@ befs_dump_super_block(const struct super_block *sb, befs_super_block * sup)
befs_debug(sb, " num_blocks %llu", fs64_to_cpu(sb, sup->num_blocks));
befs_debug(sb, " used_blocks %llu", fs64_to_cpu(sb, sup->used_blocks));
+ befs_debug(sb, " inode_size %u", fs32_to_cpu(sb, sup->inode_size));
befs_debug(sb, " magic2 %08x", fs32_to_cpu(sb, sup->magic2));
befs_debug(sb, " blocks_per_ag %u",
diff --git a/fs/befs/io.c b/fs/befs/io.c
index 523c8af..b4a5581 100644
--- a/fs/befs/io.c
+++ b/fs/befs/io.c
@@ -27,7 +27,7 @@ struct buffer_head *
befs_bread_iaddr(struct super_block *sb, befs_inode_addr iaddr)
{
struct buffer_head *bh;
- befs_blocknr_t block = 0;
+ befs_blocknr_t block;
struct befs_sb_info *befs_sb = BEFS_SB(sb);
befs_debug(sb, "---> Enter %s "
@@ -59,27 +59,3 @@ befs_bread_iaddr(struct super_block *sb, befs_inode_addr iaddr)
befs_debug(sb, "<--- %s ERROR", __func__);
return NULL;
}
-
-struct buffer_head *
-befs_bread(struct super_block *sb, befs_blocknr_t block)
-{
- struct buffer_head *bh;
-
- befs_debug(sb, "---> Enter %s %lu", __func__, (unsigned long)block);
-
- bh = sb_bread(sb, block);
-
- if (bh == NULL) {
- befs_error(sb, "Failed to read block %lu",
- (unsigned long)block);
- goto error;
- }
-
- befs_debug(sb, "<--- %s", __func__);
-
- return bh;
-
- error:
- befs_debug(sb, "<--- %s ERROR", __func__);
- return NULL;
-}
diff --git a/fs/befs/io.h b/fs/befs/io.h
index 9b78266..78d7bc6 100644
--- a/fs/befs/io.h
+++ b/fs/befs/io.h
@@ -5,5 +5,3 @@
struct buffer_head *befs_bread_iaddr(struct super_block *sb,
befs_inode_addr iaddr);
-struct buffer_head *befs_bread(struct super_block *sb, befs_blocknr_t block);
-
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index bfe9f99..647a276 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -120,7 +120,7 @@ befs_get_block(struct inode *inode, sector_t block,
struct super_block *sb = inode->i_sb;
befs_data_stream *ds = &BEFS_I(inode)->i_data.ds;
befs_block_run run = BAD_IADDR;
- int res = 0;
+ int res;
ulong disk_off;
befs_debug(sb, "---> befs_get_block() for inode %lu, block %ld",
@@ -179,15 +179,16 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
kfree(utfname);
} else {
- ret = befs_btree_find(sb, ds, dentry->d_name.name, &offset);
+ ret = befs_btree_find(sb, ds, name, &offset);
}
if (ret == BEFS_BT_NOT_FOUND) {
befs_debug(sb, "<--- %s %pd not found", __func__, dentry);
+ d_add(dentry, NULL);
return ERR_PTR(-ENOENT);
} else if (ret != BEFS_OK || offset == 0) {
- befs_warning(sb, "<--- %s Error", __func__);
+ befs_error(sb, "<--- %s Error", __func__);
return ERR_PTR(-ENODATA);
}
@@ -211,56 +212,55 @@ befs_readdir(struct file *file, struct dir_context *ctx)
befs_off_t value;
int result;
size_t keysize;
- unsigned char d_type;
char keybuf[BEFS_NAME_LEN + 1];
befs_debug(sb, "---> %s name %pD, inode %ld, ctx->pos %lld",
__func__, file, inode->i_ino, ctx->pos);
-more:
- result = befs_btree_read(sb, ds, ctx->pos, BEFS_NAME_LEN + 1,
- keybuf, &keysize, &value);
+ while (1) {
+ result = befs_btree_read(sb, ds, ctx->pos, BEFS_NAME_LEN + 1,
+ keybuf, &keysize, &value);
- if (result == BEFS_ERR) {
- befs_debug(sb, "<--- %s ERROR", __func__);
- befs_error(sb, "IO error reading %pD (inode %lu)",
- file, inode->i_ino);
- return -EIO;
-
- } else if (result == BEFS_BT_END) {
- befs_debug(sb, "<--- %s END", __func__);
- return 0;
-
- } else if (result == BEFS_BT_EMPTY) {
- befs_debug(sb, "<--- %s Empty directory", __func__);
- return 0;
- }
-
- d_type = DT_UNKNOWN;
-
- /* Convert to NLS */
- if (BEFS_SB(sb)->nls) {
- char *nlsname;
- int nlsnamelen;
- result =
- befs_utf2nls(sb, keybuf, keysize, &nlsname, &nlsnamelen);
- if (result < 0) {
+ if (result == BEFS_ERR) {
befs_debug(sb, "<--- %s ERROR", __func__);
- return result;
+ befs_error(sb, "IO error reading %pD (inode %lu)",
+ file, inode->i_ino);
+ return -EIO;
+
+ } else if (result == BEFS_BT_END) {
+ befs_debug(sb, "<--- %s END", __func__);
+ return 0;
+
+ } else if (result == BEFS_BT_EMPTY) {
+ befs_debug(sb, "<--- %s Empty directory", __func__);
+ return 0;
}
- if (!dir_emit(ctx, nlsname, nlsnamelen,
- (ino_t) value, d_type)) {
+
+ /* Convert to NLS */
+ if (BEFS_SB(sb)->nls) {
+ char *nlsname;
+ int nlsnamelen;
+
+ result =
+ befs_utf2nls(sb, keybuf, keysize, &nlsname,
+ &nlsnamelen);
+ if (result < 0) {
+ befs_debug(sb, "<--- %s ERROR", __func__);
+ return result;
+ }
+ if (!dir_emit(ctx, nlsname, nlsnamelen,
+ (ino_t) value, DT_UNKNOWN)) {
+ kfree(nlsname);
+ return 0;
+ }
kfree(nlsname);
- return 0;
+ } else {
+ if (!dir_emit(ctx, keybuf, keysize,
+ (ino_t) value, DT_UNKNOWN))
+ return 0;
}
- kfree(nlsname);
- } else {
- if (!dir_emit(ctx, keybuf, keysize,
- (ino_t) value, d_type))
- return 0;
+ ctx->pos++;
}
- ctx->pos++;
- goto more;
}
static struct inode *
@@ -299,7 +299,6 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
struct befs_sb_info *befs_sb = BEFS_SB(sb);
struct befs_inode_info *befs_ino;
struct inode *inode;
- long ret = -EIO;
befs_debug(sb, "---> %s inode = %lu", __func__, ino);
@@ -318,7 +317,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
befs_ino->i_inode_num.allocation_group,
befs_ino->i_inode_num.start, befs_ino->i_inode_num.len);
- bh = befs_bread(sb, inode->i_ino);
+ bh = sb_bread(sb, inode->i_ino);
if (!bh) {
befs_error(sb, "unable to read inode block - "
"inode = %lu", inode->i_ino);
@@ -421,7 +420,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
unacquire_none:
iget_failed(inode);
befs_debug(sb, "<--- %s - Bad inode", __func__);
- return ERR_PTR(ret);
+ return ERR_PTR(-EIO);
}
/* Initialize the inode cache. Called at fs setup.
@@ -436,10 +435,9 @@ befs_init_inodecache(void)
0, (SLAB_RECLAIM_ACCOUNT|
SLAB_MEM_SPREAD|SLAB_ACCOUNT),
init_once);
- if (befs_inode_cachep == NULL) {
- pr_err("%s: Couldn't initialize inode slabcache\n", __func__);
+ if (befs_inode_cachep == NULL)
return -ENOMEM;
- }
+
return 0;
}
@@ -524,8 +522,6 @@ befs_utf2nls(struct super_block *sb, const char *in,
*out = result = kmalloc(maxlen, GFP_NOFS);
if (!*out) {
- befs_error(sb, "%s cannot allocate memory", __func__);
- *out_len = 0;
return -ENOMEM;
}
@@ -604,7 +600,6 @@ befs_nls2utf(struct super_block *sb, const char *in,
*out = result = kmalloc(maxlen, GFP_NOFS);
if (!*out) {
- befs_error(sb, "%s cannot allocate memory", __func__);
*out_len = 0;
return -ENOMEM;
}
@@ -637,10 +632,6 @@ befs_nls2utf(struct super_block *sb, const char *in,
return -EILSEQ;
}
-/**
- * Use the
- *
- */
enum {
Opt_uid, Opt_gid, Opt_charset, Opt_debug, Opt_err,
};
@@ -760,19 +751,19 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
long ret = -EINVAL;
const unsigned long sb_block = 0;
const off_t x86_sb_off = 512;
+ int blocksize;
save_mount_options(sb, data);
sb->s_fs_info = kzalloc(sizeof(*befs_sb), GFP_KERNEL);
- if (sb->s_fs_info == NULL) {
- pr_err("(%s): Unable to allocate memory for private "
- "portion of superblock. Bailing.\n", sb->s_id);
+ if (sb->s_fs_info == NULL)
goto unacquire_none;
- }
+
befs_sb = BEFS_SB(sb);
if (!parse_options((char *) data, &befs_sb->mount_opts)) {
- befs_error(sb, "cannot parse mount options");
+ if (!silent)
+ befs_error(sb, "cannot parse mount options");
goto unacquire_priv_sbp;
}
@@ -793,10 +784,16 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
* least 1k to get the second 512 bytes of the volume.
* -WD 10-26-01
*/
- sb_min_blocksize(sb, 1024);
+ blocksize = sb_min_blocksize(sb, 1024);
+ if (!blocksize) {
+ if (!silent)
+ befs_error(sb, "unable to set blocksize");
+ goto unacquire_priv_sbp;
+ }
if (!(bh = sb_bread(sb, sb_block))) {
- befs_error(sb, "unable to read superblock");
+ if (!silent)
+ befs_error(sb, "unable to read superblock");
goto unacquire_priv_sbp;
}
@@ -820,9 +817,9 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
brelse(bh);
if( befs_sb->num_blocks > ~((sector_t)0) ) {
- befs_error(sb, "blocks count: %llu "
- "is larger than the host can use",
- befs_sb->num_blocks);
+ if (!silent)
+ befs_error(sb, "blocks count: %llu is larger than the host can use",
+ befs_sb->num_blocks);
goto unacquire_priv_sbp;
}
@@ -841,7 +838,8 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
}
sb->s_root = d_make_root(root);
if (!sb->s_root) {
- befs_error(sb, "get root inode failed");
+ if (!silent)
+ befs_error(sb, "get root inode failed");
goto unacquire_priv_sbp;
}
@@ -870,9 +868,9 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
unacquire_priv_sbp:
kfree(befs_sb->mount_opts.iocharset);
kfree(sb->s_fs_info);
+ sb->s_fs_info = NULL;
unacquire_none:
- sb->s_fs_info = NULL;
return ret;
}
diff --git a/fs/befs/super.c b/fs/befs/super.c
index aeafc4d..7c50025 100644
--- a/fs/befs/super.c
+++ b/fs/befs/super.c
@@ -13,24 +13,20 @@
#include "befs.h"
#include "super.h"
-/**
- * load_befs_sb -- Read from disk and properly byteswap all the fields
+/*
+ * befs_load_sb -- Read from disk and properly byteswap all the fields
* of the befs superblock
- *
- *
- *
- *
*/
int
-befs_load_sb(struct super_block *sb, befs_super_block * disk_sb)
+befs_load_sb(struct super_block *sb, befs_super_block *disk_sb)
{
struct befs_sb_info *befs_sb = BEFS_SB(sb);
/* Check the byte order of the filesystem */
if (disk_sb->fs_byte_order == BEFS_BYTEORDER_NATIVE_LE)
- befs_sb->byte_order = BEFS_BYTESEX_LE;
+ befs_sb->byte_order = BEFS_BYTESEX_LE;
else if (disk_sb->fs_byte_order == BEFS_BYTEORDER_NATIVE_BE)
- befs_sb->byte_order = BEFS_BYTESEX_BE;
+ befs_sb->byte_order = BEFS_BYTESEX_BE;
befs_sb->magic1 = fs32_to_cpu(sb, disk_sb->magic1);
befs_sb->magic2 = fs32_to_cpu(sb, disk_sb->magic2);
@@ -45,6 +41,8 @@ befs_load_sb(struct super_block *sb, befs_super_block * disk_sb)
befs_sb->ag_shift = fs32_to_cpu(sb, disk_sb->ag_shift);
befs_sb->num_ags = fs32_to_cpu(sb, disk_sb->num_ags);
+ befs_sb->flags = fs32_to_cpu(sb, disk_sb->flags);
+
befs_sb->log_blocks = fsrun_to_cpu(sb, disk_sb->log_blocks);
befs_sb->log_start = fs64_to_cpu(sb, disk_sb->log_start);
befs_sb->log_end = fs64_to_cpu(sb, disk_sb->log_end);
@@ -84,15 +82,15 @@ befs_check_sb(struct super_block *sb)
}
if (befs_sb->block_size > PAGE_SIZE) {
- befs_error(sb, "blocksize(%u) cannot be larger"
+ befs_error(sb, "blocksize(%u) cannot be larger "
"than system pagesize(%lu)", befs_sb->block_size,
PAGE_SIZE);
return BEFS_ERR;
}
/*
- * block_shift and block_size encode the same information
- * in different ways as a consistency check.
+ * block_shift and block_size encode the same information
+ * in different ways as a consistency check.
*/
if ((1 << befs_sb->block_shift) != befs_sb->block_size) {
@@ -101,10 +99,18 @@ befs_check_sb(struct super_block *sb)
return BEFS_ERR;
}
- if (befs_sb->log_start != befs_sb->log_end) {
+
+ /* ag_shift also encodes the same information as blocks_per_ag in a
+ * different way, non-fatal consistency check
+ */
+ if ((1 << befs_sb->ag_shift) != befs_sb->blocks_per_ag)
+ befs_error(sb, "ag_shift disagrees with blocks_per_ag.");
+
+ if (befs_sb->log_start != befs_sb->log_end ||
+ befs_sb->flags == BEFS_DIRTY) {
befs_error(sb, "Filesystem not clean! There are blocks in the "
- "journal. You must boot into BeOS and mount this volume "
- "to make it clean.");
+ "journal. You must boot into BeOS and mount this "
+ "volume to make it clean.");
return BEFS_ERR;
}
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index ccc70d9..d4d8b7e 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -698,7 +698,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
ret = btrfs_map_bio(root, comp_bio, mirror_num, 0);
if (ret) {
- bio->bi_error = ret;
+ comp_bio->bi_error = ret;
bio_endio(comp_bio);
}
@@ -728,7 +728,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
ret = btrfs_map_bio(root, comp_bio, mirror_num, 0);
if (ret) {
- bio->bi_error = ret;
+ comp_bio->bi_error = ret;
bio_endio(comp_bio);
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 6c21bad..0b8ce2b 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -252,7 +252,8 @@ struct btrfs_super_block {
#define BTRFS_FEATURE_COMPAT_SAFE_CLEAR 0ULL
#define BTRFS_FEATURE_COMPAT_RO_SUPP \
- (BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE)
+ (BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE | \
+ BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID)
#define BTRFS_FEATURE_COMPAT_RO_SAFE_SET 0ULL
#define BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR 0ULL
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index e720d3e..3a57f99 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2586,6 +2586,7 @@ int open_ctree(struct super_block *sb,
int num_backups_tried = 0;
int backup_index = 0;
int max_active;
+ int clear_free_space_tree = 0;
tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
@@ -3148,6 +3149,26 @@ int open_ctree(struct super_block *sb,
if (sb->s_flags & MS_RDONLY)
return 0;
+ if (btrfs_test_opt(fs_info, CLEAR_CACHE) &&
+ btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
+ clear_free_space_tree = 1;
+ } else if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
+ !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID)) {
+ btrfs_warn(fs_info, "free space tree is invalid");
+ clear_free_space_tree = 1;
+ }
+
+ if (clear_free_space_tree) {
+ btrfs_info(fs_info, "clearing free space tree");
+ ret = btrfs_clear_free_space_tree(fs_info);
+ if (ret) {
+ btrfs_warn(fs_info,
+ "failed to clear free space tree: %d", ret);
+ close_ctree(tree_root);
+ return ret;
+ }
+ }
+
if (btrfs_test_opt(tree_root->fs_info, FREE_SPACE_TREE) &&
!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
btrfs_info(fs_info, "creating free space tree");
@@ -3185,18 +3206,6 @@ int open_ctree(struct super_block *sb,
btrfs_qgroup_rescan_resume(fs_info);
- if (btrfs_test_opt(tree_root->fs_info, CLEAR_CACHE) &&
- btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
- btrfs_info(fs_info, "clearing free space tree");
- ret = btrfs_clear_free_space_tree(fs_info);
- if (ret) {
- btrfs_warn(fs_info,
- "failed to clear free space tree: %d", ret);
- close_ctree(tree_root);
- return ret;
- }
- }
-
if (!fs_info->uuid_root) {
btrfs_info(fs_info, "creating UUID tree");
ret = btrfs_create_uuid_tree(fs_info);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 210c94a..4607af3 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2647,7 +2647,10 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
btrfs_free_delayed_extent_op(extent_op);
if (ret) {
+ spin_lock(&delayed_refs->lock);
locked_ref->processing = 0;
+ delayed_refs->num_heads_ready++;
+ spin_unlock(&delayed_refs->lock);
btrfs_delayed_ref_unlock(locked_ref);
btrfs_put_delayed_ref(ref);
btrfs_debug(fs_info, "run_one_delayed_ref returned %d",
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index ee40384..8ed05d9 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -5558,17 +5558,45 @@ void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
}
}
-/*
- * The extent buffer bitmap operations are done with byte granularity because
- * bitmap items are not guaranteed to be aligned to a word and therefore a
- * single word in a bitmap may straddle two pages in the extent buffer.
- */
-#define BIT_BYTE(nr) ((nr) / BITS_PER_BYTE)
-#define BYTE_MASK ((1 << BITS_PER_BYTE) - 1)
-#define BITMAP_FIRST_BYTE_MASK(start) \
- ((BYTE_MASK << ((start) & (BITS_PER_BYTE - 1))) & BYTE_MASK)
-#define BITMAP_LAST_BYTE_MASK(nbits) \
- (BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
+void le_bitmap_set(u8 *map, unsigned int start, int len)
+{
+ u8 *p = map + BIT_BYTE(start);
+ const unsigned int size = start + len;
+ int bits_to_set = BITS_PER_BYTE - (start % BITS_PER_BYTE);
+ u8 mask_to_set = BITMAP_FIRST_BYTE_MASK(start);
+
+ while (len - bits_to_set >= 0) {
+ *p |= mask_to_set;
+ len -= bits_to_set;
+ bits_to_set = BITS_PER_BYTE;
+ mask_to_set = ~0;
+ p++;
+ }
+ if (len) {
+ mask_to_set &= BITMAP_LAST_BYTE_MASK(size);
+ *p |= mask_to_set;
+ }
+}
+
+void le_bitmap_clear(u8 *map, unsigned int start, int len)
+{
+ u8 *p = map + BIT_BYTE(start);
+ const unsigned int size = start + len;
+ int bits_to_clear = BITS_PER_BYTE - (start % BITS_PER_BYTE);
+ u8 mask_to_clear = BITMAP_FIRST_BYTE_MASK(start);
+
+ while (len - bits_to_clear >= 0) {
+ *p &= ~mask_to_clear;
+ len -= bits_to_clear;
+ bits_to_clear = BITS_PER_BYTE;
+ mask_to_clear = ~0;
+ p++;
+ }
+ if (len) {
+ mask_to_clear &= BITMAP_LAST_BYTE_MASK(size);
+ *p &= ~mask_to_clear;
+ }
+}
/*
* eb_bitmap_offset() - calculate the page and offset of the byte containing the
@@ -5612,7 +5640,7 @@ static inline void eb_bitmap_offset(struct extent_buffer *eb,
int extent_buffer_test_bit(struct extent_buffer *eb, unsigned long start,
unsigned long nr)
{
- char *kaddr;
+ u8 *kaddr;
struct page *page;
unsigned long i;
size_t offset;
@@ -5634,13 +5662,13 @@ int extent_buffer_test_bit(struct extent_buffer *eb, unsigned long start,
void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
unsigned long pos, unsigned long len)
{
- char *kaddr;
+ u8 *kaddr;
struct page *page;
unsigned long i;
size_t offset;
const unsigned int size = pos + len;
int bits_to_set = BITS_PER_BYTE - (pos % BITS_PER_BYTE);
- unsigned int mask_to_set = BITMAP_FIRST_BYTE_MASK(pos);
+ u8 mask_to_set = BITMAP_FIRST_BYTE_MASK(pos);
eb_bitmap_offset(eb, start, pos, &i, &offset);
page = eb->pages[i];
@@ -5651,7 +5679,7 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
kaddr[offset] |= mask_to_set;
len -= bits_to_set;
bits_to_set = BITS_PER_BYTE;
- mask_to_set = ~0U;
+ mask_to_set = ~0;
if (++offset >= PAGE_SIZE && len > 0) {
offset = 0;
page = eb->pages[++i];
@@ -5676,13 +5704,13 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start,
unsigned long pos, unsigned long len)
{
- char *kaddr;
+ u8 *kaddr;
struct page *page;
unsigned long i;
size_t offset;
const unsigned int size = pos + len;
int bits_to_clear = BITS_PER_BYTE - (pos % BITS_PER_BYTE);
- unsigned int mask_to_clear = BITMAP_FIRST_BYTE_MASK(pos);
+ u8 mask_to_clear = BITMAP_FIRST_BYTE_MASK(pos);
eb_bitmap_offset(eb, start, pos, &i, &offset);
page = eb->pages[i];
@@ -5693,7 +5721,7 @@ void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start,
kaddr[offset] &= ~mask_to_clear;
len -= bits_to_clear;
bits_to_clear = BITS_PER_BYTE;
- mask_to_clear = ~0U;
+ mask_to_clear = ~0;
if (++offset >= PAGE_SIZE && len > 0) {
offset = 0;
page = eb->pages[++i];
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 4a094f1..ab31d14 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -59,6 +59,28 @@
*/
#define EXTENT_PAGE_PRIVATE 1
+/*
+ * The extent buffer bitmap operations are done with byte granularity instead of
+ * word granularity for two reasons:
+ * 1. The bitmaps must be little-endian on disk.
+ * 2. Bitmap items are not guaranteed to be aligned to a word and therefore a
+ * single word in a bitmap may straddle two pages in the extent buffer.
+ */
+#define BIT_BYTE(nr) ((nr) / BITS_PER_BYTE)
+#define BYTE_MASK ((1 << BITS_PER_BYTE) - 1)
+#define BITMAP_FIRST_BYTE_MASK(start) \
+ ((BYTE_MASK << ((start) & (BITS_PER_BYTE - 1))) & BYTE_MASK)
+#define BITMAP_LAST_BYTE_MASK(nbits) \
+ (BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
+
+static inline int le_test_bit(int nr, const u8 *addr)
+{
+ return 1U & (addr[BIT_BYTE(nr)] >> (nr & (BITS_PER_BYTE-1)));
+}
+
+extern void le_bitmap_set(u8 *map, unsigned int start, int len);
+extern void le_bitmap_clear(u8 *map, unsigned int start, int len);
+
struct extent_state;
struct btrfs_root;
struct btrfs_io_bio;
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index e4a42a8..57401b4 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -151,7 +151,7 @@ static inline u32 free_space_bitmap_size(u64 size, u32 sectorsize)
return DIV_ROUND_UP((u32)div_u64(size, sectorsize), BITS_PER_BYTE);
}
-static unsigned long *alloc_bitmap(u32 bitmap_size)
+static u8 *alloc_bitmap(u32 bitmap_size)
{
void *mem;
@@ -180,8 +180,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
struct btrfs_free_space_info *info;
struct btrfs_key key, found_key;
struct extent_buffer *leaf;
- unsigned long *bitmap;
- char *bitmap_cursor;
+ u8 *bitmap, *bitmap_cursor;
u64 start, end;
u64 bitmap_range, i;
u32 bitmap_size, flags, expected_extent_count;
@@ -231,7 +230,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
block_group->sectorsize);
last = div_u64(found_key.objectid + found_key.offset - start,
block_group->sectorsize);
- bitmap_set(bitmap, first, last - first);
+ le_bitmap_set(bitmap, first, last - first);
extent_count++;
nr++;
@@ -270,7 +269,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
goto out;
}
- bitmap_cursor = (char *)bitmap;
+ bitmap_cursor = bitmap;
bitmap_range = block_group->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS;
i = start;
while (i < end) {
@@ -319,7 +318,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
struct btrfs_free_space_info *info;
struct btrfs_key key, found_key;
struct extent_buffer *leaf;
- unsigned long *bitmap;
+ u8 *bitmap;
u64 start, end;
/* Initialize to silence GCC. */
u64 extent_start = 0;
@@ -363,7 +362,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
break;
} else if (found_key.type == BTRFS_FREE_SPACE_BITMAP_KEY) {
unsigned long ptr;
- char *bitmap_cursor;
+ u8 *bitmap_cursor;
u32 bitmap_pos, data_size;
ASSERT(found_key.objectid >= start);
@@ -373,7 +372,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
bitmap_pos = div_u64(found_key.objectid - start,
block_group->sectorsize *
BITS_PER_BYTE);
- bitmap_cursor = ((char *)bitmap) + bitmap_pos;
+ bitmap_cursor = bitmap + bitmap_pos;
data_size = free_space_bitmap_size(found_key.offset,
block_group->sectorsize);
@@ -410,7 +409,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
offset = start;
bitnr = 0;
while (offset < end) {
- bit = !!test_bit(bitnr, bitmap);
+ bit = !!le_test_bit(bitnr, bitmap);
if (prev_bit == 0 && bit == 1) {
extent_start = offset;
} else if (prev_bit == 1 && bit == 0) {
@@ -1185,6 +1184,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
}
btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE);
+ btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID);
clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
ret = btrfs_commit_transaction(trans, tree_root);
@@ -1253,6 +1253,7 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info)
return PTR_ERR(trans);
btrfs_clear_fs_compat_ro(fs_info, FREE_SPACE_TREE);
+ btrfs_clear_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID);
fs_info->free_space_root = NULL;
ret = clear_free_space_tree(trans, free_space_root);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2b790bd..8e3a5a2 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4605,8 +4605,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
BUG_ON(ret);
if (btrfs_should_throttle_delayed_refs(trans, root))
btrfs_async_run_delayed_refs(root,
- trans->transid,
- trans->delayed_ref_updates * 2, 0);
+ trans->delayed_ref_updates * 2,
+ trans->transid, 0);
if (be_nice) {
if (truncate_space_check(trans, root,
extent_num_bytes)) {
@@ -8931,9 +8931,14 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
* So even we call qgroup_free_data(), it won't decrease reserved
* space.
* 2) Not written to disk
- * This means the reserved space should be freed here.
+ * This means the reserved space should be freed here. However,
+ * if a truncate invalidates the page (by clearing PageDirty)
+ * and the page is accounted for while allocating extent
+ * in btrfs_check_data_free_space() we let delayed_ref to
+ * free the entire extent.
*/
- btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
+ if (PageDirty(page))
+ btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
if (!inode_evicting) {
clear_extent_bit(tree, page_start, page_end,
EXTENT_LOCKED | EXTENT_DIRTY |
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 18e1aa0f..7acbd2c 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3814,6 +3814,11 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
}
btrfs_release_path(path);
key.offset = next_key_min_offset;
+
+ if (fatal_signal_pending(current)) {
+ ret = -EINTR;
+ goto out;
+ }
}
ret = 0;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 0ec8ffa..c4af0cd 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2728,7 +2728,14 @@ static int do_relocation(struct btrfs_trans_handle *trans,
bytenr = btrfs_node_blockptr(upper->eb, slot);
if (lowest) {
- BUG_ON(bytenr != node->bytenr);
+ if (bytenr != node->bytenr) {
+ btrfs_err(root->fs_info,
+ "lowest leaf/node mismatch: bytenr %llu node->bytenr %llu slot %d upper %llu",
+ bytenr, node->bytenr, slot,
+ upper->eb->start);
+ err = -EIO;
+ goto next;
+ }
} else {
if (node->eb->start == bytenr)
goto next;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 01bc36c..71261b4 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -5805,6 +5805,64 @@ static int changed_extent(struct send_ctx *sctx,
int ret = 0;
if (sctx->cur_ino != sctx->cmp_key->objectid) {
+
+ if (result == BTRFS_COMPARE_TREE_CHANGED) {
+ struct extent_buffer *leaf_l;
+ struct extent_buffer *leaf_r;
+ struct btrfs_file_extent_item *ei_l;
+ struct btrfs_file_extent_item *ei_r;
+
+ leaf_l = sctx->left_path->nodes[0];
+ leaf_r = sctx->right_path->nodes[0];
+ ei_l = btrfs_item_ptr(leaf_l,
+ sctx->left_path->slots[0],
+ struct btrfs_file_extent_item);
+ ei_r = btrfs_item_ptr(leaf_r,
+ sctx->right_path->slots[0],
+ struct btrfs_file_extent_item);
+
+ /*
+ * We may have found an extent item that has changed
+ * only its disk_bytenr field and the corresponding
+ * inode item was not updated. This case happens due to
+ * very specific timings during relocation when a leaf
+ * that contains file extent items is COWed while
+ * relocation is ongoing and its in the stage where it
+ * updates data pointers. So when this happens we can
+ * safely ignore it since we know it's the same extent,
+ * but just at different logical and physical locations
+ * (when an extent is fully replaced with a new one, we
+ * know the generation number must have changed too,
+ * since snapshot creation implies committing the current
+ * transaction, and the inode item must have been updated
+ * as well).
+ * This replacement of the disk_bytenr happens at
+ * relocation.c:replace_file_extents() through
+ * relocation.c:btrfs_reloc_cow_block().
+ */
+ if (btrfs_file_extent_generation(leaf_l, ei_l) ==
+ btrfs_file_extent_generation(leaf_r, ei_r) &&
+ btrfs_file_extent_ram_bytes(leaf_l, ei_l) ==
+ btrfs_file_extent_ram_bytes(leaf_r, ei_r) &&
+ btrfs_file_extent_compression(leaf_l, ei_l) ==
+ btrfs_file_extent_compression(leaf_r, ei_r) &&
+ btrfs_file_extent_encryption(leaf_l, ei_l) ==
+ btrfs_file_extent_encryption(leaf_r, ei_r) &&
+ btrfs_file_extent_other_encoding(leaf_l, ei_l) ==
+ btrfs_file_extent_other_encoding(leaf_r, ei_r) &&
+ btrfs_file_extent_type(leaf_l, ei_l) ==
+ btrfs_file_extent_type(leaf_r, ei_r) &&
+ btrfs_file_extent_disk_bytenr(leaf_l, ei_l) !=
+ btrfs_file_extent_disk_bytenr(leaf_r, ei_r) &&
+ btrfs_file_extent_disk_num_bytes(leaf_l, ei_l) ==
+ btrfs_file_extent_disk_num_bytes(leaf_r, ei_r) &&
+ btrfs_file_extent_offset(leaf_l, ei_l) ==
+ btrfs_file_extent_offset(leaf_r, ei_r) &&
+ btrfs_file_extent_num_bytes(leaf_l, ei_l) ==
+ btrfs_file_extent_num_bytes(leaf_r, ei_r))
+ return 0;
+ }
+
inconsistent_snapshot_error(sctx, result, "extent");
return -EIO;
}
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index d19ab03..caad80b 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -273,20 +273,37 @@ static int test_find_delalloc(u32 sectorsize)
return ret;
}
-/**
- * test_bit_in_byte - Determine whether a bit is set in a byte
- * @nr: bit number to test
- * @addr: Address to start counting from
- */
-static inline int test_bit_in_byte(int nr, const u8 *addr)
+static int check_eb_bitmap(unsigned long *bitmap, struct extent_buffer *eb,
+ unsigned long len)
{
- return 1UL & (addr[nr / BITS_PER_BYTE] >> (nr & (BITS_PER_BYTE - 1)));
+ unsigned long i;
+
+ for (i = 0; i < len * BITS_PER_BYTE; i++) {
+ int bit, bit1;
+
+ bit = !!test_bit(i, bitmap);
+ bit1 = !!extent_buffer_test_bit(eb, 0, i);
+ if (bit1 != bit) {
+ test_msg("Bits do not match\n");
+ return -EINVAL;
+ }
+
+ bit1 = !!extent_buffer_test_bit(eb, i / BITS_PER_BYTE,
+ i % BITS_PER_BYTE);
+ if (bit1 != bit) {
+ test_msg("Offset bits do not match\n");
+ return -EINVAL;
+ }
+ }
+ return 0;
}
static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
unsigned long len)
{
- unsigned long i, x;
+ unsigned long i, j;
+ u32 x;
+ int ret;
memset(bitmap, 0, len);
memset_extent_buffer(eb, 0, 0, len);
@@ -297,16 +314,18 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
bitmap_set(bitmap, 0, len * BITS_PER_BYTE);
extent_buffer_bitmap_set(eb, 0, 0, len * BITS_PER_BYTE);
- if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
+ ret = check_eb_bitmap(bitmap, eb, len);
+ if (ret) {
test_msg("Setting all bits failed\n");
- return -EINVAL;
+ return ret;
}
bitmap_clear(bitmap, 0, len * BITS_PER_BYTE);
extent_buffer_bitmap_clear(eb, 0, 0, len * BITS_PER_BYTE);
- if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
+ ret = check_eb_bitmap(bitmap, eb, len);
+ if (ret) {
test_msg("Clearing all bits failed\n");
- return -EINVAL;
+ return ret;
}
/* Straddling pages test */
@@ -316,9 +335,10 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
sizeof(long) * BITS_PER_BYTE);
extent_buffer_bitmap_set(eb, PAGE_SIZE - sizeof(long) / 2, 0,
sizeof(long) * BITS_PER_BYTE);
- if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
+ ret = check_eb_bitmap(bitmap, eb, len);
+ if (ret) {
test_msg("Setting straddling pages failed\n");
- return -EINVAL;
+ return ret;
}
bitmap_set(bitmap, 0, len * BITS_PER_BYTE);
@@ -328,9 +348,10 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
extent_buffer_bitmap_set(eb, 0, 0, len * BITS_PER_BYTE);
extent_buffer_bitmap_clear(eb, PAGE_SIZE - sizeof(long) / 2, 0,
sizeof(long) * BITS_PER_BYTE);
- if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
+ ret = check_eb_bitmap(bitmap, eb, len);
+ if (ret) {
test_msg("Clearing straddling pages failed\n");
- return -EINVAL;
+ return ret;
}
}
@@ -339,28 +360,22 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
* something repetitive that could miss some hypothetical off-by-n bug.
*/
x = 0;
- for (i = 0; i < len / sizeof(long); i++) {
- x = (0x19660dULL * (u64)x + 0x3c6ef35fULL) & 0xffffffffUL;
- bitmap[i] = x;
+ bitmap_clear(bitmap, 0, len * BITS_PER_BYTE);
+ extent_buffer_bitmap_clear(eb, 0, 0, len * BITS_PER_BYTE);
+ for (i = 0; i < len * BITS_PER_BYTE / 32; i++) {
+ x = (0x19660dULL * (u64)x + 0x3c6ef35fULL) & 0xffffffffU;
+ for (j = 0; j < 32; j++) {
+ if (x & (1U << j)) {
+ bitmap_set(bitmap, i * 32 + j, 1);
+ extent_buffer_bitmap_set(eb, 0, i * 32 + j, 1);
+ }
+ }
}
- write_extent_buffer(eb, bitmap, 0, len);
- for (i = 0; i < len * BITS_PER_BYTE; i++) {
- int bit, bit1;
-
- bit = !!test_bit_in_byte(i, (u8 *)bitmap);
- bit1 = !!extent_buffer_test_bit(eb, 0, i);
- if (bit1 != bit) {
- test_msg("Testing bit pattern failed\n");
- return -EINVAL;
- }
-
- bit1 = !!extent_buffer_test_bit(eb, i / BITS_PER_BYTE,
- i % BITS_PER_BYTE);
- if (bit1 != bit) {
- test_msg("Testing bit pattern with offset failed\n");
- return -EINVAL;
- }
+ ret = check_eb_bitmap(bitmap, eb, len);
+ if (ret) {
+ test_msg("Random bit pattern failed\n");
+ return ret;
}
return 0;
diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c
index 7508d3b..6e14404 100644
--- a/fs/btrfs/tests/free-space-tree-tests.c
+++ b/fs/btrfs/tests/free-space-tree-tests.c
@@ -24,20 +24,15 @@
#include "../transaction.h"
struct free_space_extent {
- u64 start, length;
+ u64 start;
+ u64 length;
};
-/*
- * The test cases align their operations to this in order to hit some of the
- * edge cases in the bitmap code.
- */
-#define BITMAP_RANGE (BTRFS_FREE_SPACE_BITMAP_BITS * PAGE_SIZE)
-
static int __check_free_space_extents(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *cache,
struct btrfs_path *path,
- struct free_space_extent *extents,
+ const struct free_space_extent * const extents,
unsigned int num_extents)
{
struct btrfs_free_space_info *info;
@@ -126,7 +121,7 @@ static int check_free_space_extents(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *cache,
struct btrfs_path *path,
- struct free_space_extent *extents,
+ const struct free_space_extent * const extents,
unsigned int num_extents)
{
struct btrfs_free_space_info *info;
@@ -168,9 +163,10 @@ static int check_free_space_extents(struct btrfs_trans_handle *trans,
static int test_empty_block_group(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *cache,
- struct btrfs_path *path)
+ struct btrfs_path *path,
+ u32 alignment)
{
- struct free_space_extent extents[] = {
+ const struct free_space_extent extents[] = {
{cache->key.objectid, cache->key.offset},
};
@@ -181,9 +177,10 @@ static int test_empty_block_group(struct btrfs_trans_handle *trans,
static int test_remove_all(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *cache,
- struct btrfs_path *path)
+ struct btrfs_path *path,
+ u32 alignment)
{
- struct free_space_extent extents[] = {};
+ const struct free_space_extent extents[] = {};
int ret;
ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
@@ -201,16 +198,17 @@ static int test_remove_all(struct btrfs_trans_handle *trans,
static int test_remove_beginning(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *cache,
- struct btrfs_path *path)
+ struct btrfs_path *path,
+ u32 alignment)
{
- struct free_space_extent extents[] = {
- {cache->key.objectid + BITMAP_RANGE,
- cache->key.offset - BITMAP_RANGE},
+ const struct free_space_extent extents[] = {
+ {cache->key.objectid + alignment,
+ cache->key.offset - alignment},
};
int ret;
ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
- cache->key.objectid, BITMAP_RANGE);
+ cache->key.objectid, alignment);
if (ret) {
test_msg("Could not remove free space\n");
return ret;
@@ -224,17 +222,18 @@ static int test_remove_beginning(struct btrfs_trans_handle *trans,
static int test_remove_end(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *cache,
- struct btrfs_path *path)
+ struct btrfs_path *path,
+ u32 alignment)
{
- struct free_space_extent extents[] = {
- {cache->key.objectid, cache->key.offset - BITMAP_RANGE},
+ const struct free_space_extent extents[] = {
+ {cache->key.objectid, cache->key.offset - alignment},
};
int ret;
ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
cache->key.objectid +
- cache->key.offset - BITMAP_RANGE,
- BITMAP_RANGE);
+ cache->key.offset - alignment,
+ alignment);
if (ret) {
test_msg("Could not remove free space\n");
return ret;
@@ -247,18 +246,19 @@ static int test_remove_end(struct btrfs_trans_handle *trans,
static int test_remove_middle(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *cache,
- struct btrfs_path *path)
+ struct btrfs_path *path,
+ u32 alignment)
{
- struct free_space_extent extents[] = {
- {cache->key.objectid, BITMAP_RANGE},
- {cache->key.objectid + 2 * BITMAP_RANGE,
- cache->key.offset - 2 * BITMAP_RANGE},
+ const struct free_space_extent extents[] = {
+ {cache->key.objectid, alignment},
+ {cache->key.objectid + 2 * alignment,
+ cache->key.offset - 2 * alignment},
};
int ret;
ret = __remove_from_free_space_tree(trans, fs_info, cache, path,
- cache->key.objectid + BITMAP_RANGE,
- BITMAP_RANGE);
+ cache->key.objectid + alignment,
+ alignment);
if (ret) {
test_msg("Could not remove free space\n");
return ret;
@@ -271,10 +271,11 @@ static int test_remove_middle(struct btrfs_trans_handle *trans,
static int test_merge_left(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *cache,
- struct btrfs_path *path)
+ struct btrfs_path *path,
+ u32 alignment)
{
- struct free_space_extent extents[] = {
- {cache->key.objectid, 2 * BITMAP_RANGE},
+ const struct free_space_extent extents[] = {
+ {cache->key.objectid, 2 * alignment},
};
int ret;
@@ -287,15 +288,15 @@ static int test_merge_left(struct btrfs_trans_handle *trans,
}
ret = __add_to_free_space_tree(trans, fs_info, cache, path,
- cache->key.objectid, BITMAP_RANGE);
+ cache->key.objectid, alignment);
if (ret) {
test_msg("Could not add free space\n");
return ret;
}
ret = __add_to_free_space_tree(trans, fs_info, cache, path,
- cache->key.objectid + BITMAP_RANGE,
- BITMAP_RANGE);
+ cache->key.objectid + alignment,
+ alignment);
if (ret) {
test_msg("Could not add free space\n");
return ret;
@@ -308,10 +309,11 @@ static int test_merge_left(struct btrfs_trans_handle *trans,
static int test_merge_right(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *cache,
- struct btrfs_path *path)
+ struct btrfs_path *path,
+ u32 alignment)
{
- struct free_space_extent extents[] = {
- {cache->key.objectid + BITMAP_RANGE, 2 * BITMAP_RANGE},
+ const struct free_space_extent extents[] = {
+ {cache->key.objectid + alignment, 2 * alignment},
};
int ret;
@@ -324,16 +326,16 @@ static int test_merge_right(struct btrfs_trans_handle *trans,
}
ret = __add_to_free_space_tree(trans, fs_info, cache, path,
- cache->key.objectid + 2 * BITMAP_RANGE,
- BITMAP_RANGE);
+ cache->key.objectid + 2 * alignment,
+ alignment);
if (ret) {
test_msg("Could not add free space\n");
return ret;
}
ret = __add_to_free_space_tree(trans, fs_info, cache, path,
- cache->key.objectid + BITMAP_RANGE,
- BITMAP_RANGE);
+ cache->key.objectid + alignment,
+ alignment);
if (ret) {
test_msg("Could not add free space\n");
return ret;
@@ -346,10 +348,11 @@ static int test_merge_right(struct btrfs_trans_handle *trans,
static int test_merge_both(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *cache,
- struct btrfs_path *path)
+ struct btrfs_path *path,
+ u32 alignment)
{
- struct free_space_extent extents[] = {
- {cache->key.objectid, 3 * BITMAP_RANGE},
+ const struct free_space_extent extents[] = {
+ {cache->key.objectid, 3 * alignment},
};
int ret;
@@ -362,23 +365,23 @@ static int test_merge_both(struct btrfs_trans_handle *trans,
}
ret = __add_to_free_space_tree(trans, fs_info, cache, path,
- cache->key.objectid, BITMAP_RANGE);
+ cache->key.objectid, alignment);
if (ret) {
test_msg("Could not add free space\n");
return ret;
}
ret = __add_to_free_space_tree(trans, fs_info, cache, path,
- cache->key.objectid + 2 * BITMAP_RANGE,
- BITMAP_RANGE);
+ cache->key.objectid + 2 * alignment,
+ alignment);
if (ret) {
test_msg("Could not add free space\n");
return ret;
}
ret = __add_to_free_space_tree(trans, fs_info, cache, path,
- cache->key.objectid + BITMAP_RANGE,
- BITMAP_RANGE);
+ cache->key.objectid + alignment,
+ alignment);
if (ret) {
test_msg("Could not add free space\n");
return ret;
@@ -391,12 +394,13 @@ static int test_merge_both(struct btrfs_trans_handle *trans,
static int test_merge_none(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
struct btrfs_block_group_cache *cache,
- struct btrfs_path *path)
+ struct btrfs_path *path,
+ u32 alignment)
{
- struct free_space_extent extents[] = {
- {cache->key.objectid, BITMAP_RANGE},
- {cache->key.objectid + 2 * BITMAP_RANGE, BITMAP_RANGE},
- {cache->key.objectid + 4 * BITMAP_RANGE, BITMAP_RANGE},
+ const struct free_space_extent extents[] = {
+ {cache->key.objectid, alignment},
+ {cache->key.objectid + 2 * alignment, alignment},
+ {cache->key.objectid + 4 * alignment, alignment},
};
int ret;
@@ -409,23 +413,23 @@ static int test_merge_none(struct btrfs_trans_handle *trans,
}
ret = __add_to_free_space_tree(trans, fs_info, cache, path,
- cache->key.objectid, BITMAP_RANGE);
+ cache->key.objectid, alignment);
if (ret) {
test_msg("Could not add free space\n");
return ret;
}
ret = __add_to_free_space_tree(trans, fs_info, cache, path,
- cache->key.objectid + 4 * BITMAP_RANGE,
- BITMAP_RANGE);
+ cache->key.objectid + 4 * alignment,
+ alignment);
if (ret) {
test_msg("Could not add free space\n");
return ret;
}
ret = __add_to_free_space_tree(trans, fs_info, cache, path,
- cache->key.objectid + 2 * BITMAP_RANGE,
- BITMAP_RANGE);
+ cache->key.objectid + 2 * alignment,
+ alignment);
if (ret) {
test_msg("Could not add free space\n");
return ret;
@@ -438,10 +442,11 @@ static int test_merge_none(struct btrfs_trans_handle *trans,
typedef int (*test_func_t)(struct btrfs_trans_handle *,
struct btrfs_fs_info *,
struct btrfs_block_group_cache *,
- struct btrfs_path *);
+ struct btrfs_path *,
+ u32 alignment);
-static int run_test(test_func_t test_func, int bitmaps,
- u32 sectorsize, u32 nodesize)
+static int run_test(test_func_t test_func, int bitmaps, u32 sectorsize,
+ u32 nodesize, u32 alignment)
{
struct btrfs_fs_info *fs_info;
struct btrfs_root *root = NULL;
@@ -480,7 +485,7 @@ static int run_test(test_func_t test_func, int bitmaps,
btrfs_set_header_nritems(root->node, 0);
root->alloc_bytenr += 2 * nodesize;
- cache = btrfs_alloc_dummy_block_group(8 * BITMAP_RANGE, sectorsize);
+ cache = btrfs_alloc_dummy_block_group(8 * alignment, sectorsize);
if (!cache) {
test_msg("Couldn't allocate dummy block group cache\n");
ret = -ENOMEM;
@@ -514,7 +519,7 @@ static int run_test(test_func_t test_func, int bitmaps,
}
}
- ret = test_func(&trans, root->fs_info, cache, path);
+ ret = test_func(&trans, root->fs_info, cache, path, alignment);
if (ret)
goto out;
@@ -539,15 +544,27 @@ static int run_test(test_func_t test_func, int bitmaps,
return ret;
}
-static int run_test_both_formats(test_func_t test_func,
- u32 sectorsize, u32 nodesize)
+static int run_test_both_formats(test_func_t test_func, u32 sectorsize,
+ u32 nodesize, u32 alignment)
{
+ int test_ret = 0;
int ret;
- ret = run_test(test_func, 0, sectorsize, nodesize);
- if (ret)
- return ret;
- return run_test(test_func, 1, sectorsize, nodesize);
+ ret = run_test(test_func, 0, sectorsize, nodesize, alignment);
+ if (ret) {
+ test_msg("%pf failed with extents, sectorsize=%u, nodesize=%u, alignment=%u\n",
+ test_func, sectorsize, nodesize, alignment);
+ test_ret = ret;
+ }
+
+ ret = run_test(test_func, 1, sectorsize, nodesize, alignment);
+ if (ret) {
+ test_msg("%pf failed with bitmaps, sectorsize=%u, nodesize=%u, alignment=%u\n",
+ test_func, sectorsize, nodesize, alignment);
+ test_ret = ret;
+ }
+
+ return test_ret;
}
int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize)
@@ -563,18 +580,30 @@ int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize)
test_merge_both,
test_merge_none,
};
+ u32 bitmap_alignment;
+ int test_ret = 0;
int i;
+ /*
+ * Align some operations to a page to flush out bugs in the extent
+ * buffer bitmap handling of highmem.
+ */
+ bitmap_alignment = BTRFS_FREE_SPACE_BITMAP_BITS * PAGE_SIZE;
+
test_msg("Running free space tree tests\n");
for (i = 0; i < ARRAY_SIZE(tests); i++) {
- int ret = run_test_both_formats(tests[i], sectorsize,
- nodesize);
- if (ret) {
- test_msg("%pf : sectorsize %u failed\n",
- tests[i], sectorsize);
- return ret;
- }
+ int ret;
+
+ ret = run_test_both_formats(tests[i], sectorsize, nodesize,
+ sectorsize);
+ if (ret)
+ test_ret = ret;
+
+ ret = run_test_both_formats(tests[i], sectorsize, nodesize,
+ bitmap_alignment);
+ if (ret)
+ test_ret = ret;
}
- return 0;
+ return test_ret;
}
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 528cae1..3d33c4e 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2713,14 +2713,12 @@ static inline void btrfs_remove_all_log_ctxs(struct btrfs_root *root,
int index, int error)
{
struct btrfs_log_ctx *ctx;
+ struct btrfs_log_ctx *safe;
- if (!error) {
- INIT_LIST_HEAD(&root->log_ctxs[index]);
- return;
- }
-
- list_for_each_entry(ctx, &root->log_ctxs[index], list)
+ list_for_each_entry_safe(ctx, safe, &root->log_ctxs[index], list) {
+ list_del_init(&ctx->list);
ctx->log_ret = error;
+ }
INIT_LIST_HEAD(&root->log_ctxs[index]);
}
@@ -2961,13 +2959,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
mutex_unlock(&root->log_mutex);
out_wake_log_root:
- /*
- * We needn't get log_mutex here because we are sure all
- * the other tasks are blocked.
- */
+ mutex_lock(&log_root_tree->log_mutex);
btrfs_remove_all_log_ctxs(log_root_tree, index2, ret);
- mutex_lock(&log_root_tree->log_mutex);
log_root_tree->log_transid_committed++;
atomic_set(&log_root_tree->log_commit[index2], 0);
mutex_unlock(&log_root_tree->log_mutex);
@@ -2978,10 +2972,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
if (waitqueue_active(&log_root_tree->log_commit_wait[index2]))
wake_up(&log_root_tree->log_commit_wait[index2]);
out:
- /* See above. */
- btrfs_remove_all_log_ctxs(root, index1, ret);
-
mutex_lock(&root->log_mutex);
+ btrfs_remove_all_log_ctxs(root, index1, ret);
root->log_transid_committed++;
atomic_set(&root->log_commit[index1], 0);
mutex_unlock(&root->log_mutex);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 7bf0882..f995e35 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1272,7 +1272,8 @@ static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
statret = __ceph_do_getattr(inode, page,
CEPH_STAT_CAP_INLINE_DATA, !!page);
if (statret < 0) {
- __free_page(page);
+ if (page)
+ __free_page(page);
if (statret == -ENODATA) {
BUG_ON(retry_op != READ_INLINE);
goto again;
@@ -1769,7 +1770,6 @@ const struct file_operations ceph_file_fops = {
.fsync = ceph_fsync,
.lock = ceph_lock,
.flock = ceph_flock,
- .splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.unlocked_ioctl = ceph_ioctl,
.compat_ioctl = ceph_ioctl,
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index bca1b49..ef4d046 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1511,7 +1511,8 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
ceph_fill_dirfrag(d_inode(parent), rinfo->dir_dir);
}
- if (ceph_frag_is_leftmost(frag) && req->r_readdir_offset == 2) {
+ if (ceph_frag_is_leftmost(frag) && req->r_readdir_offset == 2 &&
+ !(rinfo->hash_order && req->r_path2)) {
/* note dir version at start of readdir so we can tell
* if any dentries get dropped */
req->r_dir_release_cnt = atomic64_read(&ci->i_release_count);
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index a29ffce..b382e59 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -845,6 +845,8 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc)
err = ceph_fs_debugfs_init(fsc);
if (err < 0)
goto fail;
+ } else {
+ root = dget(fsc->sb->s_root);
}
fsc->mount_state = CEPH_MOUNT_MOUNTED;
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 40b7032..febc28f 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -16,7 +16,7 @@
static int __remove_xattr(struct ceph_inode_info *ci,
struct ceph_inode_xattr *xattr);
-const struct xattr_handler ceph_other_xattr_handler;
+static const struct xattr_handler ceph_other_xattr_handler;
/*
* List of handlers for synthetic system.* attributes. Other
@@ -1086,7 +1086,7 @@ static int ceph_set_xattr_handler(const struct xattr_handler *handler,
return __ceph_setxattr(inode, name, value, size, flags);
}
-const struct xattr_handler ceph_other_xattr_handler = {
+static const struct xattr_handler ceph_other_xattr_handler = {
.prefix = "", /* match any name => handlers called with full name */
.get = ceph_get_xattr_handler,
.set = ceph_set_xattr_handler,
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 6c58e13..3d03e48 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -152,6 +152,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
list_for_each(tmp1, &cifs_tcp_ses_list) {
server = list_entry(tmp1, struct TCP_Server_Info,
tcp_ses_list);
+ seq_printf(m, "\nNumber of credits: %d", server->credits);
i++;
list_for_each(tmp2, &server->smb_ses_list) {
ses = list_entry(tmp2, struct cifs_ses,
diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h
index 1418daa..07ed81c 100644
--- a/fs/cifs/cifs_fs_sb.h
+++ b/fs/cifs/cifs_fs_sb.h
@@ -49,6 +49,7 @@
#define CIFS_MOUNT_USE_PREFIX_PATH 0x1000000 /* make subpath with unaccessible
* root mountable
*/
+#define CIFS_MOUNT_UID_FROM_ACL 0x2000000 /* try to get UID via special SID */
struct cifs_sb_info {
struct rb_root tlink_tree;
diff --git a/fs/cifs/cifs_ioctl.h b/fs/cifs/cifs_ioctl.h
index 0065256..57ff075 100644
--- a/fs/cifs/cifs_ioctl.h
+++ b/fs/cifs/cifs_ioctl.h
@@ -36,7 +36,15 @@ struct smb_mnt_fs_info {
__u64 cifs_posix_caps;
} __packed;
+struct smb_snapshot_array {
+ __u32 number_of_snapshots;
+ __u32 number_of_snapshots_returned;
+ __u32 snapshot_array_size;
+ /* snapshots[]; */
+} __packed;
+
#define CIFS_IOCTL_MAGIC 0xCF
#define CIFS_IOC_COPYCHUNK_FILE _IOW(CIFS_IOCTL_MAGIC, 3, int)
#define CIFS_IOC_SET_INTEGRITY _IO(CIFS_IOCTL_MAGIC, 4)
#define CIFS_IOC_GET_MNT_INFO _IOR(CIFS_IOCTL_MAGIC, 5, struct smb_mnt_fs_info)
+#define CIFS_ENUMERATE_SNAPSHOTS _IOR(CIFS_IOCTL_MAGIC, 6, struct smb_snapshot_array)
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 71e8a56..15bac39 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -42,6 +42,35 @@ static const struct cifs_sid sid_authusers = {
/* group users */
static const struct cifs_sid sid_user = {1, 2 , {0, 0, 0, 0, 0, 5}, {} };
+/* S-1-22-1 Unmapped Unix users */
+static const struct cifs_sid sid_unix_users = {1, 1, {0, 0, 0, 0, 0, 22},
+ {cpu_to_le32(1), 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} };
+
+/* S-1-22-2 Unmapped Unix groups */
+static const struct cifs_sid sid_unix_groups = { 1, 1, {0, 0, 0, 0, 0, 22},
+ {cpu_to_le32(2), 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} };
+
+/*
+ * See http://technet.microsoft.com/en-us/library/hh509017(v=ws.10).aspx
+ */
+
+/* S-1-5-88 MS NFS and Apple style UID/GID/mode */
+
+/* S-1-5-88-1 Unix uid */
+static const struct cifs_sid sid_unix_NFS_users = { 1, 2, {0, 0, 0, 0, 0, 5},
+ {cpu_to_le32(88),
+ cpu_to_le32(1), 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} };
+
+/* S-1-5-88-2 Unix gid */
+static const struct cifs_sid sid_unix_NFS_groups = { 1, 2, {0, 0, 0, 0, 0, 5},
+ {cpu_to_le32(88),
+ cpu_to_le32(2), 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} };
+
+/* S-1-5-88-3 Unix mode */
+static const struct cifs_sid sid_unix_NFS_mode = { 1, 2, {0, 0, 0, 0, 0, 5},
+ {cpu_to_le32(88),
+ cpu_to_le32(3), 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} };
+
static const struct cred *root_cred;
static int
@@ -183,6 +212,62 @@ compare_sids(const struct cifs_sid *ctsid, const struct cifs_sid *cwsid)
return 0; /* sids compare/match */
}
+static bool
+is_well_known_sid(const struct cifs_sid *psid, uint32_t *puid, bool is_group)
+{
+ int i;
+ int num_subauth;
+ const struct cifs_sid *pwell_known_sid;
+
+ if (!psid || (puid == NULL))
+ return false;
+
+ num_subauth = psid->num_subauth;
+
+ /* check if Mac (or Windows NFS) vs. Samba format for Unix owner SID */
+ if (num_subauth == 2) {
+ if (is_group)
+ pwell_known_sid = &sid_unix_groups;
+ else
+ pwell_known_sid = &sid_unix_users;
+ } else if (num_subauth == 3) {
+ if (is_group)
+ pwell_known_sid = &sid_unix_NFS_groups;
+ else
+ pwell_known_sid = &sid_unix_NFS_users;
+ } else
+ return false;
+
+ /* compare the revision */
+ if (psid->revision != pwell_known_sid->revision)
+ return false;
+
+ /* compare all of the six auth values */
+ for (i = 0; i < NUM_AUTHS; ++i) {
+ if (psid->authority[i] != pwell_known_sid->authority[i]) {
+ cifs_dbg(FYI, "auth %d did not match\n", i);
+ return false;
+ }
+ }
+
+ if (num_subauth == 2) {
+ if (psid->sub_auth[0] != pwell_known_sid->sub_auth[0])
+ return false;
+
+ *puid = le32_to_cpu(psid->sub_auth[1]);
+ } else /* 3 subauths, ie Windows/Mac style */ {
+ *puid = le32_to_cpu(psid->sub_auth[0]);
+ if ((psid->sub_auth[0] != pwell_known_sid->sub_auth[0]) ||
+ (psid->sub_auth[1] != pwell_known_sid->sub_auth[1]))
+ return false;
+
+ *puid = le32_to_cpu(psid->sub_auth[2]);
+ }
+
+ cifs_dbg(FYI, "Unix UID %d returned from SID\n", *puid);
+ return true; /* well known sid found, uid returned */
+}
+
static void
cifs_copy_sid(struct cifs_sid *dst, const struct cifs_sid *src)
{
@@ -276,6 +361,43 @@ sid_to_id(struct cifs_sb_info *cifs_sb, struct cifs_sid *psid,
return -EIO;
}
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL) {
+ uint32_t unix_id;
+ bool is_group;
+
+ if (sidtype != SIDOWNER)
+ is_group = true;
+ else
+ is_group = false;
+
+ if (is_well_known_sid(psid, &unix_id, is_group) == false)
+ goto try_upcall_to_get_id;
+
+ if (is_group) {
+ kgid_t gid;
+ gid_t id;
+
+ id = (gid_t)unix_id;
+ gid = make_kgid(&init_user_ns, id);
+ if (gid_valid(gid)) {
+ fgid = gid;
+ goto got_valid_id;
+ }
+ } else {
+ kuid_t uid;
+ uid_t id;
+
+ id = (uid_t)unix_id;
+ uid = make_kuid(&init_user_ns, id);
+ if (uid_valid(uid)) {
+ fuid = uid;
+ goto got_valid_id;
+ }
+ }
+ /* If unable to find uid/gid easily from SID try via upcall */
+ }
+
+try_upcall_to_get_id:
sidstr = sid_to_key_str(psid, sidtype);
if (!sidstr)
return -ENOMEM;
@@ -329,6 +451,7 @@ sid_to_id(struct cifs_sb_info *cifs_sb, struct cifs_sid *psid,
* Note that we return 0 here unconditionally. If the mapping
* fails then we just fall back to using the mnt_uid/mnt_gid.
*/
+got_valid_id:
if (sidtype == SIDOWNER)
fattr->cf_uid = fuid;
else
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index cca04e7..15261ba 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -64,15 +64,15 @@ unsigned int global_secflags = CIFSSEC_DEF;
unsigned int sign_CIFS_PDUs = 1;
static const struct super_operations cifs_super_ops;
unsigned int CIFSMaxBufSize = CIFS_MAX_MSGSIZE;
-module_param(CIFSMaxBufSize, uint, 0);
+module_param(CIFSMaxBufSize, uint, 0444);
MODULE_PARM_DESC(CIFSMaxBufSize, "Network buffer size (not including header). "
"Default: 16384 Range: 8192 to 130048");
unsigned int cifs_min_rcv = CIFS_MIN_RCV_POOL;
-module_param(cifs_min_rcv, uint, 0);
+module_param(cifs_min_rcv, uint, 0444);
MODULE_PARM_DESC(cifs_min_rcv, "Network buffers in pool. Default: 4 Range: "
"1 to 64");
unsigned int cifs_min_small = 30;
-module_param(cifs_min_small, uint, 0);
+module_param(cifs_min_small, uint, 0444);
MODULE_PARM_DESC(cifs_min_small, "Small network buffers in pool. Default: 30 "
"Range: 2 to 256");
unsigned int cifs_max_pending = CIFS_MAX_REQ;
@@ -271,7 +271,7 @@ cifs_alloc_inode(struct super_block *sb)
cifs_inode->createtime = 0;
cifs_inode->epoch = 0;
#ifdef CONFIG_CIFS_SMB2
- get_random_bytes(cifs_inode->lease_key, SMB2_LEASE_KEY_SIZE);
+ generate_random_uuid(cifs_inode->lease_key);
#endif
/*
* Can not set i_flags here - they get immediately overwritten to zero
@@ -469,6 +469,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
seq_puts(s, ",posixpaths");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)
seq_puts(s, ",setuids");
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL)
+ seq_puts(s, ",idsfromsid");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
seq_puts(s, ",serverino");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
@@ -1262,7 +1264,6 @@ init_cifs(void)
GlobalTotalActiveXid = 0;
GlobalMaxActiveXid = 0;
spin_lock_init(&cifs_tcp_ses_lock);
- spin_lock_init(&cifs_file_list_lock);
spin_lock_init(&GlobalMid_Lock);
get_random_bytes(&cifs_lock_secret, sizeof(cifs_lock_secret));
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 8f1d8c1..1f17f6b 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -75,6 +75,18 @@
#define SMB_ECHO_INTERVAL_MAX 600
#define SMB_ECHO_INTERVAL_DEFAULT 60
+/*
+ * Default number of credits to keep available for SMB3.
+ * This value is chosen somewhat arbitrarily. The Windows client
+ * defaults to 128 credits, the Windows server allows clients up to
+ * 512 credits (or 8K for later versions), and the NetApp server
+ * does not limit clients at all. Choose a high enough default value
+ * such that the client shouldn't limit performance, but allow mount
+ * to override (until you approach 64K, where we limit credits to 65000
+ * to reduce possibility of seeing more server credit overflow bugs.
+ */
+#define SMB2_MAX_CREDITS_AVAILABLE 32000
+
#include "cifspdu.h"
#ifndef XATTR_DOS_ATTRIB
@@ -376,6 +388,8 @@ struct smb_version_operations {
int (*calc_signature)(struct smb_rqst *, struct TCP_Server_Info *);
int (*set_integrity)(const unsigned int, struct cifs_tcon *tcon,
struct cifsFileInfo *src_file);
+ int (*enum_snapshots)(const unsigned int xid, struct cifs_tcon *tcon,
+ struct cifsFileInfo *src_file, void __user *);
int (*query_mf_symlink)(unsigned int, struct cifs_tcon *,
struct cifs_sb_info *, const unsigned char *,
char *, unsigned int *);
@@ -464,6 +478,7 @@ struct smb_vol {
bool retry:1;
bool intr:1;
bool setuids:1;
+ bool setuidfromacl:1;
bool override_uid:1;
bool override_gid:1;
bool dynperm:1;
@@ -510,6 +525,7 @@ struct smb_vol {
struct sockaddr_storage srcaddr; /* allow binding to a local IP */
struct nls_table *local_nls;
unsigned int echo_interval; /* echo interval in secs */
+ unsigned int max_credits; /* smb3 max_credits 10 < credits < 60000 */
};
#define CIFS_MOUNT_MASK (CIFS_MOUNT_NO_PERM | CIFS_MOUNT_SET_UID | \
@@ -567,7 +583,8 @@ struct TCP_Server_Info {
bool noblocksnd; /* use blocking sendmsg */
bool noautotune; /* do not autotune send buf sizes */
bool tcp_nodelay;
- int credits; /* send no more requests at once */
+ unsigned int credits; /* send no more requests at once */
+ unsigned int max_credits; /* can override large 32000 default at mnt */
unsigned int in_flight; /* number of requests on the wire to server */
spinlock_t req_lock; /* protect the two values above */
struct mutex srv_mutex;
@@ -833,6 +850,7 @@ struct cifs_tcon {
struct list_head tcon_list;
int tc_count;
struct list_head openFileList;
+ spinlock_t open_file_lock; /* protects list above */
struct cifs_ses *ses; /* pointer to session associated with */
char treeName[MAX_TREE_SIZE + 1]; /* UNC name of resource in ASCII */
char *nativeFileSystem;
@@ -889,7 +907,7 @@ struct cifs_tcon {
#endif /* CONFIG_CIFS_STATS2 */
__u64 bytes_read;
__u64 bytes_written;
- spinlock_t stat_lock;
+ spinlock_t stat_lock; /* protects the two fields above */
#endif /* CONFIG_CIFS_STATS */
FILE_SYSTEM_DEVICE_INFO fsDevInfo;
FILE_SYSTEM_ATTRIBUTE_INFO fsAttrInfo; /* ok if fs name truncated */
@@ -1040,20 +1058,24 @@ struct cifs_fid_locks {
};
struct cifsFileInfo {
+ /* following two lists are protected by tcon->open_file_lock */
struct list_head tlist; /* pointer to next fid owned by tcon */
struct list_head flist; /* next fid (file instance) for this inode */
+ /* lock list below protected by cifsi->lock_sem */
struct cifs_fid_locks *llist; /* brlocks held by this fid */
kuid_t uid; /* allows finding which FileInfo structure */
__u32 pid; /* process id who opened file */
struct cifs_fid fid; /* file id from remote */
+ struct list_head rlist; /* reconnect list */
/* BB add lock scope info here if needed */ ;
/* lock scope id (0 if none) */
struct dentry *dentry;
- unsigned int f_flags;
struct tcon_link *tlink;
+ unsigned int f_flags;
bool invalidHandle:1; /* file closed via session abend */
bool oplock_break_cancelled:1;
- int count; /* refcount protected by cifs_file_list_lock */
+ int count;
+ spinlock_t file_info_lock; /* protects four flag/count fields above */
struct mutex fh_mutex; /* prevents reopen race after dead ses*/
struct cifs_search_info srch_inf;
struct work_struct oplock_break; /* work for oplock breaks */
@@ -1120,7 +1142,7 @@ struct cifs_writedata {
/*
* Take a reference on the file private data. Must be called with
- * cifs_file_list_lock held.
+ * cfile->file_info_lock held.
*/
static inline void
cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file)
@@ -1514,8 +1536,10 @@ require use of the stronger protocol */
* GlobalMid_Lock protects:
* list operations on pending_mid_q and oplockQ
* updates to XID counters, multiplex id and SMB sequence numbers
- * cifs_file_list_lock protects:
- * list operations on tcp and SMB session lists and tCon lists
+ * tcp_ses_lock protects:
+ * list operations on tcp and SMB session lists
+ * tcon->open_file_lock protects the list of open files hanging off the tcon
+ * cfile->file_info_lock protects counters and fields in cifs file struct
* f_owner.lock protects certain per file struct operations
* mapping->page_lock protects certain per page operations
*
@@ -1547,18 +1571,12 @@ GLOBAL_EXTERN struct list_head cifs_tcp_ses_list;
* tcp session, and the list of tcon's per smb session. It also protects
* the reference counters for the server, smb session, and tcon. Finally,
* changes to the tcon->tidStatus should be done while holding this lock.
+ * generally the locks should be taken in order tcp_ses_lock before
+ * tcon->open_file_lock and that before file->file_info_lock since the
+ * structure order is cifs_socket-->cifs_ses-->cifs_tcon-->cifs_file
*/
GLOBAL_EXTERN spinlock_t cifs_tcp_ses_lock;
-/*
- * This lock protects the cifs_file->llist and cifs_file->flist
- * list operations, and updates to some flags (cifs_file->invalidHandle)
- * It will be moved to either use the tcon->stat_lock or equivalent later.
- * If cifs_tcp_ses_lock and the lock below are both needed to be held, then
- * the cifs_tcp_ses_lock must be grabbed first and released last.
- */
-GLOBAL_EXTERN spinlock_t cifs_file_list_lock;
-
#ifdef CONFIG_CIFS_DNOTIFY_EXPERIMENTAL /* unused temporarily */
/* Outstanding dir notify requests */
GLOBAL_EXTERN struct list_head GlobalDnotifyReqList;
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 4ead72a..ced0e42 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -193,6 +193,8 @@ extern struct smb_vol *cifs_get_volume_info(char *mount_data,
extern int cifs_mount(struct cifs_sb_info *, struct smb_vol *);
extern void cifs_umount(struct cifs_sb_info *);
extern void cifs_mark_open_files_invalid(struct cifs_tcon *tcon);
+extern void cifs_reopen_persistent_handles(struct cifs_tcon *tcon);
+
extern bool cifs_find_lock_conflict(struct cifsFileInfo *cfile, __u64 offset,
__u64 length, __u8 type,
struct cifsLockInfo **conf_lock,
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index f82d282..3f3185f 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -98,13 +98,13 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon)
struct list_head *tmp1;
/* list all files open on tree connection and mark them invalid */
- spin_lock(&cifs_file_list_lock);
+ spin_lock(&tcon->open_file_lock);
list_for_each_safe(tmp, tmp1, &tcon->openFileList) {
open_file = list_entry(tmp, struct cifsFileInfo, tlist);
open_file->invalidHandle = true;
open_file->oplock_break_cancelled = true;
}
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&tcon->open_file_lock);
/*
* BB Add call to invalidate_inodes(sb) for all superblocks mounted
* to this tcon.
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 2e4f4ba..aab5227 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -63,7 +63,6 @@ extern mempool_t *cifs_req_poolp;
#define TLINK_IDLE_EXPIRE (600 * HZ)
enum {
-
/* Mount options that take no arguments */
Opt_user_xattr, Opt_nouser_xattr,
Opt_forceuid, Opt_noforceuid,
@@ -76,7 +75,7 @@ enum {
Opt_noposixpaths, Opt_nounix,
Opt_nocase,
Opt_brl, Opt_nobrl,
- Opt_forcemandatorylock, Opt_setuids,
+ Opt_forcemandatorylock, Opt_setuidfromacl, Opt_setuids,
Opt_nosetuids, Opt_dynperm, Opt_nodynperm,
Opt_nohard, Opt_nosoft,
Opt_nointr, Opt_intr,
@@ -95,7 +94,7 @@ enum {
Opt_cruid, Opt_gid, Opt_file_mode,
Opt_dirmode, Opt_port,
Opt_rsize, Opt_wsize, Opt_actimeo,
- Opt_echo_interval,
+ Opt_echo_interval, Opt_max_credits,
/* Mount options which take string value */
Opt_user, Opt_pass, Opt_ip,
@@ -148,6 +147,7 @@ static const match_table_t cifs_mount_option_tokens = {
{ Opt_forcemandatorylock, "forcemand" },
{ Opt_setuids, "setuids" },
{ Opt_nosetuids, "nosetuids" },
+ { Opt_setuidfromacl, "idsfromsid" },
{ Opt_dynperm, "dynperm" },
{ Opt_nodynperm, "nodynperm" },
{ Opt_nohard, "nohard" },
@@ -190,6 +190,7 @@ static const match_table_t cifs_mount_option_tokens = {
{ Opt_wsize, "wsize=%s" },
{ Opt_actimeo, "actimeo=%s" },
{ Opt_echo_interval, "echo_interval=%s" },
+ { Opt_max_credits, "max_credits=%s" },
{ Opt_blank_user, "user=" },
{ Opt_blank_user, "username=" },
@@ -1376,6 +1377,9 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
case Opt_nosetuids:
vol->setuids = 0;
break;
+ case Opt_setuidfromacl:
+ vol->setuidfromacl = 1;
+ break;
case Opt_dynperm:
vol->dynperm = true;
break;
@@ -1586,6 +1590,15 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
}
vol->echo_interval = option;
break;
+ case Opt_max_credits:
+ if (get_option_ul(args, &option) || (option < 20) ||
+ (option > 60000)) {
+ cifs_dbg(VFS, "%s: Invalid max_credits value\n",
+ __func__);
+ goto cifs_parse_mount_err;
+ }
+ vol->max_credits = option;
+ break;
/* String Arguments */
@@ -2163,7 +2176,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
memcpy(&tcp_ses->dstaddr, &volume_info->dstaddr,
sizeof(tcp_ses->dstaddr));
#ifdef CONFIG_CIFS_SMB2
- get_random_bytes(tcp_ses->client_guid, SMB2_CLIENT_GUID_SIZE);
+ generate_random_uuid(tcp_ses->client_guid);
#endif
/*
* at this point we are the only ones with the pointer
@@ -3270,6 +3283,8 @@ int cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_PERM;
if (pvolume_info->setuids)
cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_SET_UID;
+ if (pvolume_info->setuidfromacl)
+ cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_UID_FROM_ACL;
if (pvolume_info->server_ino)
cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_SERVER_INUM;
if (pvolume_info->remap)
@@ -3598,7 +3613,11 @@ cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
bdi_destroy(&cifs_sb->bdi);
goto out;
}
-
+ if ((volume_info->max_credits < 20) ||
+ (volume_info->max_credits > 60000))
+ server->max_credits = SMB2_MAX_CREDITS_AVAILABLE;
+ else
+ server->max_credits = volume_info->max_credits;
/* get a reference to a SMB session */
ses = cifs_get_smb_ses(server, volume_info);
if (IS_ERR(ses)) {
@@ -3688,14 +3707,16 @@ cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
goto mount_fail_check;
}
- rc = cifs_are_all_path_components_accessible(server,
+ if (rc != -EREMOTE) {
+ rc = cifs_are_all_path_components_accessible(server,
xid, tcon, cifs_sb,
full_path);
- if (rc != 0) {
- cifs_dbg(VFS, "cannot query dirs between root and final path, "
- "enabling CIFS_MOUNT_USE_PREFIX_PATH\n");
- cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
- rc = 0;
+ if (rc != 0) {
+ cifs_dbg(VFS, "cannot query dirs between root and final path, "
+ "enabling CIFS_MOUNT_USE_PREFIX_PATH\n");
+ cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
+ rc = 0;
+ }
}
kfree(full_path);
}
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index a95fe8b..7f5f617 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -305,6 +305,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
cfile->tlink = cifs_get_tlink(tlink);
INIT_WORK(&cfile->oplock_break, cifs_oplock_break);
mutex_init(&cfile->fh_mutex);
+ spin_lock_init(&cfile->file_info_lock);
cifs_sb_active(inode->i_sb);
@@ -317,7 +318,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
oplock = 0;
}
- spin_lock(&cifs_file_list_lock);
+ spin_lock(&tcon->open_file_lock);
if (fid->pending_open->oplock != CIFS_OPLOCK_NO_CHANGE && oplock)
oplock = fid->pending_open->oplock;
list_del(&fid->pending_open->olist);
@@ -326,12 +327,13 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
server->ops->set_fid(cfile, fid, oplock);
list_add(&cfile->tlist, &tcon->openFileList);
+
/* if readable file instance put first in list*/
if (file->f_mode & FMODE_READ)
list_add(&cfile->flist, &cinode->openFileList);
else
list_add_tail(&cfile->flist, &cinode->openFileList);
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&tcon->open_file_lock);
if (fid->purge_cache)
cifs_zap_mapping(inode);
@@ -343,16 +345,16 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
struct cifsFileInfo *
cifsFileInfo_get(struct cifsFileInfo *cifs_file)
{
- spin_lock(&cifs_file_list_lock);
+ spin_lock(&cifs_file->file_info_lock);
cifsFileInfo_get_locked(cifs_file);
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&cifs_file->file_info_lock);
return cifs_file;
}
/*
* Release a reference on the file private data. This may involve closing
* the filehandle out on the server. Must be called without holding
- * cifs_file_list_lock.
+ * tcon->open_file_lock and cifs_file->file_info_lock.
*/
void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
{
@@ -367,11 +369,15 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
struct cifs_pending_open open;
bool oplock_break_cancelled;
- spin_lock(&cifs_file_list_lock);
+ spin_lock(&tcon->open_file_lock);
+
+ spin_lock(&cifs_file->file_info_lock);
if (--cifs_file->count > 0) {
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&cifs_file->file_info_lock);
+ spin_unlock(&tcon->open_file_lock);
return;
}
+ spin_unlock(&cifs_file->file_info_lock);
if (server->ops->get_lease_key)
server->ops->get_lease_key(inode, &fid);
@@ -395,7 +401,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
set_bit(CIFS_INO_INVALID_MAPPING, &cifsi->flags);
cifs_set_oplock_level(cifsi, 0);
}
- spin_unlock(&cifs_file_list_lock);
+
+ spin_unlock(&tcon->open_file_lock);
oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break);
@@ -732,6 +739,15 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
* to the server to get the new inode info.
*/
+ /*
+ * If the server returned a read oplock and we have mandatory brlocks,
+ * set oplock level to None.
+ */
+ if (server->ops->is_read_op(oplock) && cifs_has_mand_locks(cinode)) {
+ cifs_dbg(FYI, "Reset oplock val from read to None due to mand locks\n");
+ oplock = 0;
+ }
+
server->ops->set_fid(cfile, &cfile->fid, oplock);
if (oparms.reconnect)
cifs_relock_file(cfile);
@@ -753,6 +769,36 @@ int cifs_close(struct inode *inode, struct file *file)
return 0;
}
+void
+cifs_reopen_persistent_handles(struct cifs_tcon *tcon)
+{
+ struct cifsFileInfo *open_file;
+ struct list_head *tmp;
+ struct list_head *tmp1;
+ struct list_head tmp_list;
+
+ cifs_dbg(FYI, "Reopen persistent handles");
+ INIT_LIST_HEAD(&tmp_list);
+
+ /* list all files open on tree connection, reopen resilient handles */
+ spin_lock(&tcon->open_file_lock);
+ list_for_each(tmp, &tcon->openFileList) {
+ open_file = list_entry(tmp, struct cifsFileInfo, tlist);
+ if (!open_file->invalidHandle)
+ continue;
+ cifsFileInfo_get(open_file);
+ list_add_tail(&open_file->rlist, &tmp_list);
+ }
+ spin_unlock(&tcon->open_file_lock);
+
+ list_for_each_safe(tmp, tmp1, &tmp_list) {
+ open_file = list_entry(tmp, struct cifsFileInfo, rlist);
+ cifs_reopen_file(open_file, false /* do not flush */);
+ list_del_init(&open_file->rlist);
+ cifsFileInfo_put(open_file);
+ }
+}
+
int cifs_closedir(struct inode *inode, struct file *file)
{
int rc = 0;
@@ -772,10 +818,10 @@ int cifs_closedir(struct inode *inode, struct file *file)
server = tcon->ses->server;
cifs_dbg(FYI, "Freeing private data in close dir\n");
- spin_lock(&cifs_file_list_lock);
+ spin_lock(&cfile->file_info_lock);
if (server->ops->dir_needs_close(cfile)) {
cfile->invalidHandle = true;
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&cfile->file_info_lock);
if (server->ops->close_dir)
rc = server->ops->close_dir(xid, tcon, &cfile->fid);
else
@@ -784,7 +830,7 @@ int cifs_closedir(struct inode *inode, struct file *file)
/* not much we can do if it fails anyway, ignore rc */
rc = 0;
} else
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&cfile->file_info_lock);
buf = cfile->srch_inf.ntwrk_buf_start;
if (buf) {
@@ -1728,12 +1774,13 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
{
struct cifsFileInfo *open_file = NULL;
struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb);
+ struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
/* only filter by fsuid on multiuser mounts */
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
fsuid_only = false;
- spin_lock(&cifs_file_list_lock);
+ spin_lock(&tcon->open_file_lock);
/* we could simply get the first_list_entry since write-only entries
are always at the end of the list but since the first entry might
have a close pending, we go through the whole list */
@@ -1744,8 +1791,8 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
if (!open_file->invalidHandle) {
/* found a good file */
/* lock it so it will not be closed on us */
- cifsFileInfo_get_locked(open_file);
- spin_unlock(&cifs_file_list_lock);
+ cifsFileInfo_get(open_file);
+ spin_unlock(&tcon->open_file_lock);
return open_file;
} /* else might as well continue, and look for
another, or simply have the caller reopen it
@@ -1753,7 +1800,7 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
} else /* write only file */
break; /* write only files are last so must be done */
}
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&tcon->open_file_lock);
return NULL;
}
@@ -1762,6 +1809,7 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode,
{
struct cifsFileInfo *open_file, *inv_file = NULL;
struct cifs_sb_info *cifs_sb;
+ struct cifs_tcon *tcon;
bool any_available = false;
int rc;
unsigned int refind = 0;
@@ -1777,15 +1825,16 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode,
}
cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb);
+ tcon = cifs_sb_master_tcon(cifs_sb);
/* only filter by fsuid on multiuser mounts */
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
fsuid_only = false;
- spin_lock(&cifs_file_list_lock);
+ spin_lock(&tcon->open_file_lock);
refind_writable:
if (refind > MAX_REOPEN_ATT) {
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&tcon->open_file_lock);
return NULL;
}
list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
@@ -1796,8 +1845,8 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode,
if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
if (!open_file->invalidHandle) {
/* found a good writable file */
- cifsFileInfo_get_locked(open_file);
- spin_unlock(&cifs_file_list_lock);
+ cifsFileInfo_get(open_file);
+ spin_unlock(&tcon->open_file_lock);
return open_file;
} else {
if (!inv_file)
@@ -1813,24 +1862,24 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode,
if (inv_file) {
any_available = false;
- cifsFileInfo_get_locked(inv_file);
+ cifsFileInfo_get(inv_file);
}
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&tcon->open_file_lock);
if (inv_file) {
rc = cifs_reopen_file(inv_file, false);
if (!rc)
return inv_file;
else {
- spin_lock(&cifs_file_list_lock);
+ spin_lock(&tcon->open_file_lock);
list_move_tail(&inv_file->flist,
&cifs_inode->openFileList);
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&tcon->open_file_lock);
cifsFileInfo_put(inv_file);
- spin_lock(&cifs_file_list_lock);
++refind;
inv_file = NULL;
+ spin_lock(&tcon->open_file_lock);
goto refind_writable;
}
}
@@ -3612,15 +3661,17 @@ static int cifs_readpage(struct file *file, struct page *page)
static int is_inode_writable(struct cifsInodeInfo *cifs_inode)
{
struct cifsFileInfo *open_file;
+ struct cifs_tcon *tcon =
+ cifs_sb_master_tcon(CIFS_SB(cifs_inode->vfs_inode.i_sb));
- spin_lock(&cifs_file_list_lock);
+ spin_lock(&tcon->open_file_lock);
list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&tcon->open_file_lock);
return 1;
}
}
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&tcon->open_file_lock);
return 0;
}
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 7a3b84e..9f51b81 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -189,7 +189,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
xid = get_xid();
cifs_sb = CIFS_SB(inode->i_sb);
-
+ cifs_dbg(VFS, "cifs ioctl 0x%x\n", command);
switch (command) {
case FS_IOC_GETFLAGS:
if (pSMBFile == NULL)
@@ -267,11 +267,23 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
tcon = tlink_tcon(pSMBFile->tlink);
rc = smb_mnt_get_fsinfo(xid, tcon, (void __user *)arg);
break;
+ case CIFS_ENUMERATE_SNAPSHOTS:
+ if (arg == 0) {
+ rc = -EINVAL;
+ goto cifs_ioc_exit;
+ }
+ tcon = tlink_tcon(pSMBFile->tlink);
+ if (tcon->ses->server->ops->enum_snapshots)
+ rc = tcon->ses->server->ops->enum_snapshots(xid, tcon,
+ pSMBFile, (void __user *)arg);
+ else
+ rc = -EOPNOTSUPP;
+ break;
default:
cifs_dbg(FYI, "unsupported ioctl\n");
break;
}
-
+cifs_ioc_exit:
free_xid(xid);
return rc;
}
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 813fe13..c672915 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -120,6 +120,7 @@ tconInfoAlloc(void)
++ret_buf->tc_count;
INIT_LIST_HEAD(&ret_buf->openFileList);
INIT_LIST_HEAD(&ret_buf->tcon_list);
+ spin_lock_init(&ret_buf->open_file_lock);
#ifdef CONFIG_CIFS_STATS
spin_lock_init(&ret_buf->stat_lock);
#endif
@@ -465,7 +466,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
continue;
cifs_stats_inc(&tcon->stats.cifs_stats.num_oplock_brks);
- spin_lock(&cifs_file_list_lock);
+ spin_lock(&tcon->open_file_lock);
list_for_each(tmp2, &tcon->openFileList) {
netfile = list_entry(tmp2, struct cifsFileInfo,
tlist);
@@ -495,11 +496,11 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
&netfile->oplock_break);
netfile->oplock_break_cancelled = false;
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&tcon->open_file_lock);
spin_unlock(&cifs_tcp_ses_lock);
return true;
}
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&tcon->open_file_lock);
spin_unlock(&cifs_tcp_ses_lock);
cifs_dbg(FYI, "No matching file for oplock break\n");
return true;
@@ -613,9 +614,9 @@ backup_cred(struct cifs_sb_info *cifs_sb)
void
cifs_del_pending_open(struct cifs_pending_open *open)
{
- spin_lock(&cifs_file_list_lock);
+ spin_lock(&tlink_tcon(open->tlink)->open_file_lock);
list_del(&open->olist);
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&tlink_tcon(open->tlink)->open_file_lock);
}
void
@@ -635,7 +636,7 @@ void
cifs_add_pending_open(struct cifs_fid *fid, struct tcon_link *tlink,
struct cifs_pending_open *open)
{
- spin_lock(&cifs_file_list_lock);
+ spin_lock(&tlink_tcon(tlink)->open_file_lock);
cifs_add_pending_open_locked(fid, tlink, open);
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&tlink_tcon(open->tlink)->open_file_lock);
}
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 65cf85d..8f6a2a5 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -597,14 +597,14 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos,
is_dir_changed(file)) || (index_to_find < first_entry_in_buffer)) {
/* close and restart search */
cifs_dbg(FYI, "search backing up - close and restart search\n");
- spin_lock(&cifs_file_list_lock);
+ spin_lock(&cfile->file_info_lock);
if (server->ops->dir_needs_close(cfile)) {
cfile->invalidHandle = true;
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&cfile->file_info_lock);
if (server->ops->close_dir)
server->ops->close_dir(xid, tcon, &cfile->fid);
} else
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&cfile->file_info_lock);
if (cfile->srch_inf.ntwrk_buf_start) {
cifs_dbg(FYI, "freeing SMB ff cache buf on search rewind\n");
if (cfile->srch_inf.smallBuf)
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index 4f0231e..1238cd3 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -266,9 +266,15 @@ smb2_set_file_info(struct inode *inode, const char *full_path,
struct tcon_link *tlink;
int rc;
+ if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) &&
+ (buf->LastWriteTime == 0) && (buf->ChangeTime) &&
+ (buf->Attributes == 0))
+ return 0; /* would be a no op, no sense sending this */
+
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
+
rc = smb2_open_op_close(xid, tlink_tcon(tlink), cifs_sb, full_path,
FILE_WRITE_ATTRIBUTES, FILE_OPEN, 0, buf,
SMB2_OP_SET_INFO);
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 389fb9f..3d38348 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -549,19 +549,19 @@ smb2_is_valid_lease_break(char *buffer)
list_for_each(tmp1, &server->smb_ses_list) {
ses = list_entry(tmp1, struct cifs_ses, smb_ses_list);
- spin_lock(&cifs_file_list_lock);
list_for_each(tmp2, &ses->tcon_list) {
tcon = list_entry(tmp2, struct cifs_tcon,
tcon_list);
+ spin_lock(&tcon->open_file_lock);
cifs_stats_inc(
&tcon->stats.cifs_stats.num_oplock_brks);
if (smb2_tcon_has_lease(tcon, rsp, lw)) {
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&tcon->open_file_lock);
spin_unlock(&cifs_tcp_ses_lock);
return true;
}
+ spin_unlock(&tcon->open_file_lock);
}
- spin_unlock(&cifs_file_list_lock);
}
}
spin_unlock(&cifs_tcp_ses_lock);
@@ -603,7 +603,7 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
tcon = list_entry(tmp1, struct cifs_tcon, tcon_list);
cifs_stats_inc(&tcon->stats.cifs_stats.num_oplock_brks);
- spin_lock(&cifs_file_list_lock);
+ spin_lock(&tcon->open_file_lock);
list_for_each(tmp2, &tcon->openFileList) {
cfile = list_entry(tmp2, struct cifsFileInfo,
tlist);
@@ -615,7 +615,7 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
cifs_dbg(FYI, "file id match, oplock break\n");
cinode = CIFS_I(d_inode(cfile->dentry));
-
+ spin_lock(&cfile->file_info_lock);
if (!CIFS_CACHE_WRITE(cinode) &&
rsp->OplockLevel == SMB2_OPLOCK_LEVEL_NONE)
cfile->oplock_break_cancelled = true;
@@ -637,14 +637,14 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
clear_bit(
CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
&cinode->flags);
-
+ spin_unlock(&cfile->file_info_lock);
queue_work(cifsiod_wq, &cfile->oplock_break);
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&tcon->open_file_lock);
spin_unlock(&cifs_tcp_ses_lock);
return true;
}
- spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&tcon->open_file_lock);
spin_unlock(&cifs_tcp_ses_lock);
cifs_dbg(FYI, "No matching file for oplock break\n");
return true;
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index d203c03..5d456eb 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -28,6 +28,7 @@
#include "cifs_unicode.h"
#include "smb2status.h"
#include "smb2glob.h"
+#include "cifs_ioctl.h"
static int
change_conf(struct TCP_Server_Info *server)
@@ -70,6 +71,10 @@ smb2_add_credits(struct TCP_Server_Info *server, const unsigned int add,
spin_lock(&server->req_lock);
val = server->ops->get_credits_field(server, optype);
*val += add;
+ if (*val > 65000) {
+ *val = 65000; /* Don't get near 64K credits, avoid srv bugs */
+ printk_once(KERN_WARNING "server overflowed SMB3 credits\n");
+ }
server->in_flight--;
if (server->in_flight == 0 && (optype & CIFS_OP_MASK) != CIFS_NEG_OP)
rc = change_conf(server);
@@ -287,7 +292,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
cifs_dbg(FYI, "Link Speed %lld\n",
le64_to_cpu(out_buf->LinkSpeed));
}
-
+ kfree(out_buf);
return rc;
}
#endif /* STATS2 */
@@ -541,6 +546,7 @@ smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock)
server->ops->set_oplock_level(cinode, oplock, fid->epoch,
&fid->purge_cache);
cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode);
+ memcpy(cfile->fid.create_guid, fid->create_guid, 16);
}
static void
@@ -699,6 +705,7 @@ smb2_clone_range(const unsigned int xid,
cchunk_out:
kfree(pcchunk);
+ kfree(retbuf);
return rc;
}
@@ -823,7 +830,6 @@ smb2_duplicate_extents(const unsigned int xid,
{
int rc;
unsigned int ret_data_len;
- char *retbuf = NULL;
struct duplicate_extents_to_file dup_ext_buf;
struct cifs_tcon *tcon = tlink_tcon(trgtfile->tlink);
@@ -849,7 +855,7 @@ smb2_duplicate_extents(const unsigned int xid,
FSCTL_DUPLICATE_EXTENTS_TO_FILE,
true /* is_fsctl */, (char *)&dup_ext_buf,
sizeof(struct duplicate_extents_to_file),
- (char **)&retbuf,
+ NULL,
&ret_data_len);
if (ret_data_len > 0)
@@ -872,7 +878,6 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon,
struct cifsFileInfo *cfile)
{
struct fsctl_set_integrity_information_req integr_info;
- char *retbuf = NULL;
unsigned int ret_data_len;
integr_info.ChecksumAlgorithm = cpu_to_le16(CHECKSUM_TYPE_UNCHANGED);
@@ -884,12 +889,56 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon,
FSCTL_SET_INTEGRITY_INFORMATION,
true /* is_fsctl */, (char *)&integr_info,
sizeof(struct fsctl_set_integrity_information_req),
- (char **)&retbuf,
+ NULL,
&ret_data_len);
}
static int
+smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon,
+ struct cifsFileInfo *cfile, void __user *ioc_buf)
+{
+ char *retbuf = NULL;
+ unsigned int ret_data_len = 0;
+ int rc;
+ struct smb_snapshot_array snapshot_in;
+
+ rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
+ cfile->fid.volatile_fid,
+ FSCTL_SRV_ENUMERATE_SNAPSHOTS,
+ true /* is_fsctl */, NULL, 0 /* no input data */,
+ (char **)&retbuf,
+ &ret_data_len);
+ cifs_dbg(FYI, "enum snaphots ioctl returned %d and ret buflen is %d\n",
+ rc, ret_data_len);
+ if (rc)
+ return rc;
+
+ if (ret_data_len && (ioc_buf != NULL) && (retbuf != NULL)) {
+ /* Fixup buffer */
+ if (copy_from_user(&snapshot_in, ioc_buf,
+ sizeof(struct smb_snapshot_array))) {
+ rc = -EFAULT;
+ kfree(retbuf);
+ return rc;
+ }
+ if (snapshot_in.snapshot_array_size < sizeof(struct smb_snapshot_array)) {
+ rc = -ERANGE;
+ return rc;
+ }
+
+ if (ret_data_len > snapshot_in.snapshot_array_size)
+ ret_data_len = snapshot_in.snapshot_array_size;
+
+ if (copy_to_user(ioc_buf, retbuf, ret_data_len))
+ rc = -EFAULT;
+ }
+
+ kfree(retbuf);
+ return rc;
+}
+
+static int
smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
const char *path, struct cifs_sb_info *cifs_sb,
struct cifs_fid *fid, __u16 search_flags,
@@ -1041,7 +1090,7 @@ smb2_set_lease_key(struct inode *inode, struct cifs_fid *fid)
static void
smb2_new_lease_key(struct cifs_fid *fid)
{
- get_random_bytes(fid->lease_key, SMB2_LEASE_KEY_SIZE);
+ generate_random_uuid(fid->lease_key);
}
#define SMB2_SYMLINK_STRUCT_SIZE \
@@ -1654,6 +1703,7 @@ struct smb_version_operations smb21_operations = {
.clone_range = smb2_clone_range,
.wp_retry_size = smb2_wp_retry_size,
.dir_needs_close = smb2_dir_needs_close,
+ .enum_snapshots = smb3_enum_snapshots,
};
struct smb_version_operations smb30_operations = {
@@ -1740,6 +1790,7 @@ struct smb_version_operations smb30_operations = {
.wp_retry_size = smb2_wp_retry_size,
.dir_needs_close = smb2_dir_needs_close,
.fallocate = smb3_fallocate,
+ .enum_snapshots = smb3_enum_snapshots,
};
#ifdef CONFIG_CIFS_SMB311
@@ -1827,6 +1878,7 @@ struct smb_version_operations smb311_operations = {
.wp_retry_size = smb2_wp_retry_size,
.dir_needs_close = smb2_dir_needs_close,
.fallocate = smb3_fallocate,
+ .enum_snapshots = smb3_enum_snapshots,
};
#endif /* CIFS_SMB311 */
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 29e06db..5ca5ea46 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -100,7 +100,21 @@ smb2_hdr_assemble(struct smb2_hdr *hdr, __le16 smb2_cmd /* command */ ,
hdr->ProtocolId = SMB2_PROTO_NUMBER;
hdr->StructureSize = cpu_to_le16(64);
hdr->Command = smb2_cmd;
- hdr->CreditRequest = cpu_to_le16(2); /* BB make this dynamic */
+ if (tcon && tcon->ses && tcon->ses->server) {
+ struct TCP_Server_Info *server = tcon->ses->server;
+
+ spin_lock(&server->req_lock);
+ /* Request up to 2 credits but don't go over the limit. */
+ if (server->credits >= server->max_credits)
+ hdr->CreditRequest = cpu_to_le16(0);
+ else
+ hdr->CreditRequest = cpu_to_le16(
+ min_t(int, server->max_credits -
+ server->credits, 2));
+ spin_unlock(&server->req_lock);
+ } else {
+ hdr->CreditRequest = cpu_to_le16(2);
+ }
hdr->ProcessId = cpu_to_le32((__u16)current->tgid);
if (!tcon)
@@ -236,8 +250,13 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
}
cifs_mark_open_files_invalid(tcon);
+
rc = SMB2_tcon(0, tcon->ses, tcon->treeName, tcon, nls_codepage);
mutex_unlock(&tcon->ses->session_mutex);
+
+ if (tcon->use_persistent)
+ cifs_reopen_persistent_handles(tcon);
+
cifs_dbg(FYI, "reconnect tcon rc = %d\n", rc);
if (rc)
goto out;
@@ -574,59 +593,42 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
return -EIO;
}
-int
-SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
- const struct nls_table *nls_cp)
-{
- struct smb2_sess_setup_req *req;
- struct smb2_sess_setup_rsp *rsp = NULL;
+struct SMB2_sess_data {
+ unsigned int xid;
+ struct cifs_ses *ses;
+ struct nls_table *nls_cp;
+ void (*func)(struct SMB2_sess_data *);
+ int result;
+ u64 previous_session;
+
+ /* we will send the SMB in three pieces:
+ * a fixed length beginning part, an optional
+ * SPNEGO blob (which can be zero length), and a
+ * last part which will include the strings
+ * and rest of bcc area. This allows us to avoid
+ * a large buffer 17K allocation
+ */
+ int buf0_type;
struct kvec iov[2];
- int rc = 0;
- int resp_buftype = CIFS_NO_BUFFER;
- __le32 phase = NtLmNegotiate; /* NTLMSSP, if needed, is multistage */
+};
+
+static int
+SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data)
+{
+ int rc;
+ struct cifs_ses *ses = sess_data->ses;
+ struct smb2_sess_setup_req *req;
struct TCP_Server_Info *server = ses->server;
- u16 blob_length = 0;
- struct key *spnego_key = NULL;
- char *security_blob = NULL;
- unsigned char *ntlmssp_blob = NULL;
- bool use_spnego = false; /* else use raw ntlmssp */
-
- cifs_dbg(FYI, "Session Setup\n");
-
- if (!server) {
- WARN(1, "%s: server is NULL!\n", __func__);
- return -EIO;
- }
-
- /*
- * If we are here due to reconnect, free per-smb session key
- * in case signing was required.
- */
- kfree(ses->auth_key.response);
- ses->auth_key.response = NULL;
-
- /*
- * If memory allocation is successful, caller of this function
- * frees it.
- */
- ses->ntlmssp = kmalloc(sizeof(struct ntlmssp_auth), GFP_KERNEL);
- if (!ses->ntlmssp)
- return -ENOMEM;
- ses->ntlmssp->sesskey_per_smbsess = true;
-
- /* FIXME: allow for other auth types besides NTLMSSP (e.g. krb5) */
- if (ses->sectype != Kerberos && ses->sectype != RawNTLMSSP)
- ses->sectype = RawNTLMSSP;
-
-ssetup_ntlmssp_authenticate:
- if (phase == NtLmChallenge)
- phase = NtLmAuthenticate; /* if ntlmssp, now final phase */
rc = small_smb2_init(SMB2_SESSION_SETUP, NULL, (void **) &req);
if (rc)
return rc;
req->hdr.SessionId = 0; /* First session, not a reauthenticate */
+
+ /* if reconnect, we need to send previous sess id, otherwise it is 0 */
+ req->PreviousSessionId = sess_data->previous_session;
+
req->Flags = 0; /* MBZ */
/* to enable echos and oplocks */
req->hdr.CreditRequest = cpu_to_le16(3);
@@ -642,199 +644,368 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
req->Capabilities = 0;
req->Channel = 0; /* MBZ */
- iov[0].iov_base = (char *)req;
+ sess_data->iov[0].iov_base = (char *)req;
/* 4 for rfc1002 length field and 1 for pad */
- iov[0].iov_len = get_rfc1002_length(req) + 4 - 1;
+ sess_data->iov[0].iov_len = get_rfc1002_length(req) + 4 - 1;
+ /*
+ * This variable will be used to clear the buffer
+ * allocated above in case of any error in the calling function.
+ */
+ sess_data->buf0_type = CIFS_SMALL_BUFFER;
- if (ses->sectype == Kerberos) {
-#ifdef CONFIG_CIFS_UPCALL
- struct cifs_spnego_msg *msg;
+ return 0;
+}
- spnego_key = cifs_get_spnego_key(ses);
- if (IS_ERR(spnego_key)) {
- rc = PTR_ERR(spnego_key);
- spnego_key = NULL;
- goto ssetup_exit;
- }
+static void
+SMB2_sess_free_buffer(struct SMB2_sess_data *sess_data)
+{
+ free_rsp_buf(sess_data->buf0_type, sess_data->iov[0].iov_base);
+ sess_data->buf0_type = CIFS_NO_BUFFER;
+}
- msg = spnego_key->payload.data[0];
- /*
- * check version field to make sure that cifs.upcall is
- * sending us a response in an expected form
- */
- if (msg->version != CIFS_SPNEGO_UPCALL_VERSION) {
- cifs_dbg(VFS,
- "bad cifs.upcall version. Expected %d got %d",
- CIFS_SPNEGO_UPCALL_VERSION, msg->version);
- rc = -EKEYREJECTED;
- goto ssetup_exit;
- }
- ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
- GFP_KERNEL);
- if (!ses->auth_key.response) {
- cifs_dbg(VFS,
- "Kerberos can't allocate (%u bytes) memory",
- msg->sesskey_len);
- rc = -ENOMEM;
- goto ssetup_exit;
- }
- ses->auth_key.len = msg->sesskey_len;
- blob_length = msg->secblob_len;
- iov[1].iov_base = msg->data + msg->sesskey_len;
- iov[1].iov_len = blob_length;
-#else
- rc = -EOPNOTSUPP;
- goto ssetup_exit;
-#endif /* CONFIG_CIFS_UPCALL */
- } else if (phase == NtLmNegotiate) { /* if not krb5 must be ntlmssp */
- ntlmssp_blob = kmalloc(sizeof(struct _NEGOTIATE_MESSAGE),
- GFP_KERNEL);
- if (ntlmssp_blob == NULL) {
- rc = -ENOMEM;
- goto ssetup_exit;
- }
- build_ntlmssp_negotiate_blob(ntlmssp_blob, ses);
- if (use_spnego) {
- /* blob_length = build_spnego_ntlmssp_blob(
- &security_blob,
- sizeof(struct _NEGOTIATE_MESSAGE),
- ntlmssp_blob); */
- /* BB eventually need to add this */
- cifs_dbg(VFS, "spnego not supported for SMB2 yet\n");
- rc = -EOPNOTSUPP;
- kfree(ntlmssp_blob);
- goto ssetup_exit;
- } else {
- blob_length = sizeof(struct _NEGOTIATE_MESSAGE);
- /* with raw NTLMSSP we don't encapsulate in SPNEGO */
- security_blob = ntlmssp_blob;
- }
- iov[1].iov_base = security_blob;
- iov[1].iov_len = blob_length;
- } else if (phase == NtLmAuthenticate) {
- req->hdr.SessionId = ses->Suid;
- rc = build_ntlmssp_auth_blob(&ntlmssp_blob, &blob_length, ses,
- nls_cp);
- if (rc) {
- cifs_dbg(FYI, "build_ntlmssp_auth_blob failed %d\n",
- rc);
- goto ssetup_exit; /* BB double check error handling */
- }
- if (use_spnego) {
- /* blob_length = build_spnego_ntlmssp_blob(
- &security_blob,
- blob_length,
- ntlmssp_blob); */
- cifs_dbg(VFS, "spnego not supported for SMB2 yet\n");
- rc = -EOPNOTSUPP;
- kfree(ntlmssp_blob);
- goto ssetup_exit;
- } else {
- security_blob = ntlmssp_blob;
- }
- iov[1].iov_base = security_blob;
- iov[1].iov_len = blob_length;
- } else {
- cifs_dbg(VFS, "illegal ntlmssp phase\n");
- rc = -EIO;
- goto ssetup_exit;
- }
+static int
+SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data)
+{
+ int rc;
+ struct smb2_sess_setup_req *req = sess_data->iov[0].iov_base;
/* Testing shows that buffer offset must be at location of Buffer[0] */
req->SecurityBufferOffset =
- cpu_to_le16(sizeof(struct smb2_sess_setup_req) -
- 1 /* pad */ - 4 /* rfc1001 len */);
- req->SecurityBufferLength = cpu_to_le16(blob_length);
+ cpu_to_le16(sizeof(struct smb2_sess_setup_req) -
+ 1 /* pad */ - 4 /* rfc1001 len */);
+ req->SecurityBufferLength = cpu_to_le16(sess_data->iov[1].iov_len);
- inc_rfc1001_len(req, blob_length - 1 /* pad */);
+ inc_rfc1001_len(req, sess_data->iov[1].iov_len - 1 /* pad */);
/* BB add code to build os and lm fields */
- rc = SendReceive2(xid, ses, iov, 2, &resp_buftype,
- CIFS_LOG_ERROR | CIFS_NEG_OP);
+ rc = SendReceive2(sess_data->xid, sess_data->ses,
+ sess_data->iov, 2,
+ &sess_data->buf0_type,
+ CIFS_LOG_ERROR | CIFS_NEG_OP);
- kfree(security_blob);
- rsp = (struct smb2_sess_setup_rsp *)iov[0].iov_base;
- ses->Suid = rsp->hdr.SessionId;
- if (resp_buftype != CIFS_NO_BUFFER &&
- rsp->hdr.Status == STATUS_MORE_PROCESSING_REQUIRED) {
- if (phase != NtLmNegotiate) {
- cifs_dbg(VFS, "Unexpected more processing error\n");
- goto ssetup_exit;
- }
- if (offsetof(struct smb2_sess_setup_rsp, Buffer) - 4 !=
- le16_to_cpu(rsp->SecurityBufferOffset)) {
- cifs_dbg(VFS, "Invalid security buffer offset %d\n",
- le16_to_cpu(rsp->SecurityBufferOffset));
- rc = -EIO;
- goto ssetup_exit;
- }
+ return rc;
+}
- /* NTLMSSP Negotiate sent now processing challenge (response) */
- phase = NtLmChallenge; /* process ntlmssp challenge */
- rc = 0; /* MORE_PROCESSING is not an error here but expected */
- rc = decode_ntlmssp_challenge(rsp->Buffer,
- le16_to_cpu(rsp->SecurityBufferLength), ses);
+static int
+SMB2_sess_establish_session(struct SMB2_sess_data *sess_data)
+{
+ int rc = 0;
+ struct cifs_ses *ses = sess_data->ses;
+
+ mutex_lock(&ses->server->srv_mutex);
+ if (ses->server->sign && ses->server->ops->generate_signingkey) {
+ rc = ses->server->ops->generate_signingkey(ses);
+ kfree(ses->auth_key.response);
+ ses->auth_key.response = NULL;
+ if (rc) {
+ cifs_dbg(FYI,
+ "SMB3 session key generation failed\n");
+ mutex_unlock(&ses->server->srv_mutex);
+ goto keygen_exit;
+ }
+ }
+ if (!ses->server->session_estab) {
+ ses->server->sequence_number = 0x2;
+ ses->server->session_estab = true;
+ }
+ mutex_unlock(&ses->server->srv_mutex);
+
+ cifs_dbg(FYI, "SMB2/3 session established successfully\n");
+ spin_lock(&GlobalMid_Lock);
+ ses->status = CifsGood;
+ ses->need_reconnect = false;
+ spin_unlock(&GlobalMid_Lock);
+
+keygen_exit:
+ if (!ses->server->sign) {
+ kfree(ses->auth_key.response);
+ ses->auth_key.response = NULL;
+ }
+ return rc;
+}
+
+#ifdef CONFIG_CIFS_UPCALL
+static void
+SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
+{
+ int rc;
+ struct cifs_ses *ses = sess_data->ses;
+ struct cifs_spnego_msg *msg;
+ struct key *spnego_key = NULL;
+ struct smb2_sess_setup_rsp *rsp = NULL;
+
+ rc = SMB2_sess_alloc_buffer(sess_data);
+ if (rc)
+ goto out;
+
+ spnego_key = cifs_get_spnego_key(ses);
+ if (IS_ERR(spnego_key)) {
+ rc = PTR_ERR(spnego_key);
+ spnego_key = NULL;
+ goto out;
}
+ msg = spnego_key->payload.data[0];
/*
- * BB eventually add code for SPNEGO decoding of NtlmChallenge blob,
- * but at least the raw NTLMSSP case works.
+ * check version field to make sure that cifs.upcall is
+ * sending us a response in an expected form
*/
- /*
- * No tcon so can't do
- * cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_fail[SMB2...]);
- */
- if (rc != 0)
- goto ssetup_exit;
+ if (msg->version != CIFS_SPNEGO_UPCALL_VERSION) {
+ cifs_dbg(VFS,
+ "bad cifs.upcall version. Expected %d got %d",
+ CIFS_SPNEGO_UPCALL_VERSION, msg->version);
+ rc = -EKEYREJECTED;
+ goto out_put_spnego_key;
+ }
+
+ ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
+ GFP_KERNEL);
+ if (!ses->auth_key.response) {
+ cifs_dbg(VFS,
+ "Kerberos can't allocate (%u bytes) memory",
+ msg->sesskey_len);
+ rc = -ENOMEM;
+ goto out_put_spnego_key;
+ }
+ ses->auth_key.len = msg->sesskey_len;
+
+ sess_data->iov[1].iov_base = msg->data + msg->sesskey_len;
+ sess_data->iov[1].iov_len = msg->secblob_len;
+
+ rc = SMB2_sess_sendreceive(sess_data);
+ if (rc)
+ goto out_put_spnego_key;
+
+ rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base;
+ ses->Suid = rsp->hdr.SessionId;
ses->session_flags = le16_to_cpu(rsp->SessionFlags);
if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA)
cifs_dbg(VFS, "SMB3 encryption not supported yet\n");
-ssetup_exit:
- free_rsp_buf(resp_buftype, rsp);
- /* if ntlmssp, and negotiate succeeded, proceed to authenticate phase */
- if ((phase == NtLmChallenge) && (rc == 0))
- goto ssetup_ntlmssp_authenticate;
+ rc = SMB2_sess_establish_session(sess_data);
+out_put_spnego_key:
+ key_invalidate(spnego_key);
+ key_put(spnego_key);
+out:
+ sess_data->result = rc;
+ sess_data->func = NULL;
+ SMB2_sess_free_buffer(sess_data);
+}
+#else
+static void
+SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
+{
+ cifs_dbg(VFS, "Kerberos negotiated but upcall support disabled!\n");
+ sess_data->result = -EOPNOTSUPP;
+ sess_data->func = NULL;
+}
+#endif
+static void
+SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data);
+
+static void
+SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data)
+{
+ int rc;
+ struct cifs_ses *ses = sess_data->ses;
+ struct smb2_sess_setup_rsp *rsp = NULL;
+ char *ntlmssp_blob = NULL;
+ bool use_spnego = false; /* else use raw ntlmssp */
+ u16 blob_length = 0;
+
+ /*
+ * If memory allocation is successful, caller of this function
+ * frees it.
+ */
+ ses->ntlmssp = kmalloc(sizeof(struct ntlmssp_auth), GFP_KERNEL);
+ if (!ses->ntlmssp) {
+ rc = -ENOMEM;
+ goto out_err;
+ }
+ ses->ntlmssp->sesskey_per_smbsess = true;
+
+ rc = SMB2_sess_alloc_buffer(sess_data);
+ if (rc)
+ goto out_err;
+
+ ntlmssp_blob = kmalloc(sizeof(struct _NEGOTIATE_MESSAGE),
+ GFP_KERNEL);
+ if (ntlmssp_blob == NULL) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ build_ntlmssp_negotiate_blob(ntlmssp_blob, ses);
+ if (use_spnego) {
+ /* BB eventually need to add this */
+ cifs_dbg(VFS, "spnego not supported for SMB2 yet\n");
+ rc = -EOPNOTSUPP;
+ goto out;
+ } else {
+ blob_length = sizeof(struct _NEGOTIATE_MESSAGE);
+ /* with raw NTLMSSP we don't encapsulate in SPNEGO */
+ }
+ sess_data->iov[1].iov_base = ntlmssp_blob;
+ sess_data->iov[1].iov_len = blob_length;
+
+ rc = SMB2_sess_sendreceive(sess_data);
+ rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base;
+
+ /* If true, rc here is expected and not an error */
+ if (sess_data->buf0_type != CIFS_NO_BUFFER &&
+ rsp->hdr.Status == STATUS_MORE_PROCESSING_REQUIRED)
+ rc = 0;
+
+ if (rc)
+ goto out;
+
+ if (offsetof(struct smb2_sess_setup_rsp, Buffer) - 4 !=
+ le16_to_cpu(rsp->SecurityBufferOffset)) {
+ cifs_dbg(VFS, "Invalid security buffer offset %d\n",
+ le16_to_cpu(rsp->SecurityBufferOffset));
+ rc = -EIO;
+ goto out;
+ }
+ rc = decode_ntlmssp_challenge(rsp->Buffer,
+ le16_to_cpu(rsp->SecurityBufferLength), ses);
+ if (rc)
+ goto out;
+
+ cifs_dbg(FYI, "rawntlmssp session setup challenge phase\n");
+
+
+ ses->Suid = rsp->hdr.SessionId;
+ ses->session_flags = le16_to_cpu(rsp->SessionFlags);
+ if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA)
+ cifs_dbg(VFS, "SMB3 encryption not supported yet\n");
+
+out:
+ kfree(ntlmssp_blob);
+ SMB2_sess_free_buffer(sess_data);
if (!rc) {
- mutex_lock(&server->srv_mutex);
- if (server->sign && server->ops->generate_signingkey) {
- rc = server->ops->generate_signingkey(ses);
- kfree(ses->auth_key.response);
- ses->auth_key.response = NULL;
- if (rc) {
- cifs_dbg(FYI,
- "SMB3 session key generation failed\n");
- mutex_unlock(&server->srv_mutex);
- goto keygen_exit;
- }
- }
- if (!server->session_estab) {
- server->sequence_number = 0x2;
- server->session_estab = true;
- }
- mutex_unlock(&server->srv_mutex);
-
- cifs_dbg(FYI, "SMB2/3 session established successfully\n");
- spin_lock(&GlobalMid_Lock);
- ses->status = CifsGood;
- ses->need_reconnect = false;
- spin_unlock(&GlobalMid_Lock);
+ sess_data->result = 0;
+ sess_data->func = SMB2_sess_auth_rawntlmssp_authenticate;
+ return;
}
-
-keygen_exit:
- if (!server->sign) {
- kfree(ses->auth_key.response);
- ses->auth_key.response = NULL;
- }
- if (spnego_key) {
- key_invalidate(spnego_key);
- key_put(spnego_key);
- }
+out_err:
kfree(ses->ntlmssp);
+ ses->ntlmssp = NULL;
+ sess_data->result = rc;
+ sess_data->func = NULL;
+}
+static void
+SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data)
+{
+ int rc;
+ struct cifs_ses *ses = sess_data->ses;
+ struct smb2_sess_setup_req *req;
+ struct smb2_sess_setup_rsp *rsp = NULL;
+ unsigned char *ntlmssp_blob = NULL;
+ bool use_spnego = false; /* else use raw ntlmssp */
+ u16 blob_length = 0;
+
+ rc = SMB2_sess_alloc_buffer(sess_data);
+ if (rc)
+ goto out;
+
+ req = (struct smb2_sess_setup_req *) sess_data->iov[0].iov_base;
+ req->hdr.SessionId = ses->Suid;
+
+ rc = build_ntlmssp_auth_blob(&ntlmssp_blob, &blob_length, ses,
+ sess_data->nls_cp);
+ if (rc) {
+ cifs_dbg(FYI, "build_ntlmssp_auth_blob failed %d\n", rc);
+ goto out;
+ }
+
+ if (use_spnego) {
+ /* BB eventually need to add this */
+ cifs_dbg(VFS, "spnego not supported for SMB2 yet\n");
+ rc = -EOPNOTSUPP;
+ goto out;
+ }
+ sess_data->iov[1].iov_base = ntlmssp_blob;
+ sess_data->iov[1].iov_len = blob_length;
+
+ rc = SMB2_sess_sendreceive(sess_data);
+ if (rc)
+ goto out;
+
+ rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base;
+
+ ses->Suid = rsp->hdr.SessionId;
+ ses->session_flags = le16_to_cpu(rsp->SessionFlags);
+ if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA)
+ cifs_dbg(VFS, "SMB3 encryption not supported yet\n");
+
+ rc = SMB2_sess_establish_session(sess_data);
+out:
+ kfree(ntlmssp_blob);
+ SMB2_sess_free_buffer(sess_data);
+ kfree(ses->ntlmssp);
+ ses->ntlmssp = NULL;
+ sess_data->result = rc;
+ sess_data->func = NULL;
+}
+
+static int
+SMB2_select_sec(struct cifs_ses *ses, struct SMB2_sess_data *sess_data)
+{
+ if (ses->sectype != Kerberos && ses->sectype != RawNTLMSSP)
+ ses->sectype = RawNTLMSSP;
+
+ switch (ses->sectype) {
+ case Kerberos:
+ sess_data->func = SMB2_auth_kerberos;
+ break;
+ case RawNTLMSSP:
+ sess_data->func = SMB2_sess_auth_rawntlmssp_negotiate;
+ break;
+ default:
+ cifs_dbg(VFS, "secType %d not supported!\n", ses->sectype);
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+int
+SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
+ const struct nls_table *nls_cp)
+{
+ int rc = 0;
+ struct TCP_Server_Info *server = ses->server;
+ struct SMB2_sess_data *sess_data;
+
+ cifs_dbg(FYI, "Session Setup\n");
+
+ if (!server) {
+ WARN(1, "%s: server is NULL!\n", __func__);
+ return -EIO;
+ }
+
+ sess_data = kzalloc(sizeof(struct SMB2_sess_data), GFP_KERNEL);
+ if (!sess_data)
+ return -ENOMEM;
+
+ rc = SMB2_select_sec(ses, sess_data);
+ if (rc)
+ goto out;
+ sess_data->xid = xid;
+ sess_data->ses = ses;
+ sess_data->buf0_type = CIFS_NO_BUFFER;
+ sess_data->nls_cp = (struct nls_table *) nls_cp;
+
+ while (sess_data->func)
+ sess_data->func(sess_data);
+
+ rc = sess_data->result;
+out:
+ kfree(sess_data);
return rc;
}
@@ -1164,7 +1335,7 @@ create_durable_v2_buf(struct cifs_fid *pfid)
buf->dcontext.Timeout = 0; /* Should this be configurable by workload */
buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT);
- get_random_bytes(buf->dcontext.CreateGuid, 16);
+ generate_random_uuid(buf->dcontext.CreateGuid);
memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16);
/* SMB2_CREATE_DURABLE_HANDLE_REQUEST is "DH2Q" */
@@ -2057,6 +2228,7 @@ smb2_async_readv(struct cifs_readdata *rdata)
if (rdata->credits) {
buf->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes,
SMB2_MAX_BUFFER_SIZE));
+ buf->CreditRequest = buf->CreditCharge;
spin_lock(&server->req_lock);
server->credits += rdata->credits -
le16_to_cpu(buf->CreditCharge);
@@ -2243,6 +2415,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
if (wdata->credits) {
req->hdr.CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes,
SMB2_MAX_BUFFER_SIZE));
+ req->hdr.CreditRequest = req->hdr.CreditCharge;
spin_lock(&server->req_lock);
server->credits += wdata->credits -
le16_to_cpu(req->hdr.CreditCharge);
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index ff88d9f..fd3709e 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -276,7 +276,7 @@ struct smb2_sess_setup_req {
__le32 Channel;
__le16 SecurityBufferOffset;
__le16 SecurityBufferLength;
- __le64 PreviousSessionId;
+ __u64 PreviousSessionId;
__u8 Buffer[1]; /* variable length GSS security buffer */
} __packed;
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 5e23f64..20af518 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -33,7 +33,8 @@
#define MAX_EA_VALUE_SIZE 65535
#define CIFS_XATTR_CIFS_ACL "system.cifs_acl"
-
+#define CIFS_XATTR_ATTRIB "cifs.dosattrib" /* full name: user.cifs.dosattrib */
+#define CIFS_XATTR_CREATETIME "cifs.creationtime" /* user.cifs.creationtime */
/* BB need to add server (Samba e.g) support for security and trusted prefix */
enum { XATTR_USER, XATTR_CIFS_ACL, XATTR_ACL_ACCESS, XATTR_ACL_DEFAULT };
@@ -144,6 +145,54 @@ static int cifs_xattr_set(const struct xattr_handler *handler,
return rc;
}
+static int cifs_attrib_get(struct dentry *dentry,
+ struct inode *inode, void *value,
+ size_t size)
+{
+ ssize_t rc;
+ __u32 *pattribute;
+
+ rc = cifs_revalidate_dentry_attr(dentry);
+
+ if (rc)
+ return rc;
+
+ if ((value == NULL) || (size == 0))
+ return sizeof(__u32);
+ else if (size < sizeof(__u32))
+ return -ERANGE;
+
+ /* return dos attributes as pseudo xattr */
+ pattribute = (__u32 *)value;
+ *pattribute = CIFS_I(inode)->cifsAttrs;
+
+ return sizeof(__u32);
+}
+
+static int cifs_creation_time_get(struct dentry *dentry, struct inode *inode,
+ void *value, size_t size)
+{
+ ssize_t rc;
+ __u64 * pcreatetime;
+
+ rc = cifs_revalidate_dentry_attr(dentry);
+ if (rc)
+ return rc;
+
+ if ((value == NULL) || (size == 0))
+ return sizeof(__u64);
+ else if (size < sizeof(__u64))
+ return -ERANGE;
+
+ /* return dos attributes as pseudo xattr */
+ pcreatetime = (__u64 *)value;
+ *pcreatetime = CIFS_I(inode)->createtime;
+ return sizeof(__u64);
+
+ return rc;
+}
+
+
static int cifs_xattr_get(const struct xattr_handler *handler,
struct dentry *dentry, struct inode *inode,
const char *name, void *value, size_t size)
@@ -168,10 +217,19 @@ static int cifs_xattr_get(const struct xattr_handler *handler,
rc = -ENOMEM;
goto out;
}
- /* return dos attributes as pseudo xattr */
+
/* return alt name if available as pseudo attr */
switch (handler->flags) {
case XATTR_USER:
+ cifs_dbg(FYI, "%s:querying user xattr %s\n", __func__, name);
+ if (strcmp(name, CIFS_XATTR_ATTRIB) == 0) {
+ rc = cifs_attrib_get(dentry, inode, value, size);
+ break;
+ } else if (strcmp(name, CIFS_XATTR_CREATETIME) == 0) {
+ rc = cifs_creation_time_get(dentry, inode, value, size);
+ break;
+ }
+
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
goto out;
diff --git a/fs/coredump.c b/fs/coredump.c
index 281b768..eb9c92c 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -1,6 +1,7 @@
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/fdtable.h>
+#include <linux/freezer.h>
#include <linux/mm.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
@@ -423,7 +424,9 @@ static int coredump_wait(int exit_code, struct core_state *core_state)
if (core_waiters > 0) {
struct core_thread *ptr;
+ freezer_do_not_count();
wait_for_completion(&core_state->startup);
+ freezer_count();
/*
* Wait for all the threads to become inactive, so that
* all the thread context (extended register state, like
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index 61057b7d..98f87fe 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -151,7 +151,10 @@ static int do_page_crypto(struct inode *inode,
struct page *src_page, struct page *dest_page,
gfp_t gfp_flags)
{
- u8 xts_tweak[FS_XTS_TWEAK_SIZE];
+ struct {
+ __le64 index;
+ u8 padding[FS_XTS_TWEAK_SIZE - sizeof(__le64)];
+ } xts_tweak;
struct skcipher_request *req = NULL;
DECLARE_FS_COMPLETION_RESULT(ecr);
struct scatterlist dst, src;
@@ -171,17 +174,15 @@ static int do_page_crypto(struct inode *inode,
req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
page_crypt_complete, &ecr);
- BUILD_BUG_ON(FS_XTS_TWEAK_SIZE < sizeof(index));
- memcpy(xts_tweak, &index, sizeof(index));
- memset(&xts_tweak[sizeof(index)], 0,
- FS_XTS_TWEAK_SIZE - sizeof(index));
+ BUILD_BUG_ON(sizeof(xts_tweak) != FS_XTS_TWEAK_SIZE);
+ xts_tweak.index = cpu_to_le64(index);
+ memset(xts_tweak.padding, 0, sizeof(xts_tweak.padding));
sg_init_table(&dst, 1);
sg_set_page(&dst, dest_page, PAGE_SIZE, 0);
sg_init_table(&src, 1);
sg_set_page(&src, src_page, PAGE_SIZE, 0);
- skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE,
- xts_tweak);
+ skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE, &xts_tweak);
if (rw == FS_DECRYPT)
res = crypto_skcipher_decrypt(req);
else
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index ed115ac..6865663 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -109,6 +109,8 @@ int fscrypt_process_policy(struct file *filp,
if (ret)
return ret;
+ inode_lock(inode);
+
if (!inode_has_encryption_context(inode)) {
if (!S_ISDIR(inode->i_mode))
ret = -EINVAL;
@@ -127,6 +129,8 @@ int fscrypt_process_policy(struct file *filp,
ret = -EINVAL;
}
+ inode_unlock(inode);
+
mnt_drop_write_file(filp);
return ret;
}
diff --git a/fs/exec.c b/fs/exec.c
index 6fcfb3f..4e497b9 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -191,6 +191,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
{
struct page *page;
int ret;
+ unsigned int gup_flags = FOLL_FORCE;
#ifdef CONFIG_STACK_GROWSUP
if (write) {
@@ -199,12 +200,16 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
return NULL;
}
#endif
+
+ if (write)
+ gup_flags |= FOLL_WRITE;
+
/*
* We are doing an exec(). 'current' is the process
* doing the exec and bprm->mm is the new process's mm.
*/
- ret = get_user_pages_remote(current, bprm->mm, pos, 1, write,
- 1, &page, NULL);
+ ret = get_user_pages_remote(current, bprm->mm, pos, 1, gup_flags,
+ &page, NULL);
if (ret <= 0)
return NULL;
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
index 79101651..42f9a0a 100644
--- a/fs/exofs/dir.c
+++ b/fs/exofs/dir.c
@@ -137,7 +137,7 @@ static bool exofs_check_page(struct page *page)
bad_entry:
EXOFS_ERR(
"ERROR [exofs_check_page]: bad entry in directory(0x%lx): %s - "
- "offset=%lu, inode=0x%llu, rec_len=%d, name_len=%d\n",
+ "offset=%lu, inode=0x%llx, rec_len=%d, name_len=%d\n",
dir->i_ino, error, (page->index<<PAGE_SHIFT)+offs,
_LLU(le64_to_cpu(p->inode_no)),
rec_len, p->name_len);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index d831e24..41b8b44 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -622,7 +622,7 @@ static int ext2_get_blocks(struct inode *inode,
u32 *bno, bool *new, bool *boundary,
int create)
{
- int err = -EIO;
+ int err;
int offsets[4];
Indirect chain[4];
Indirect *partial;
@@ -639,7 +639,7 @@ static int ext2_get_blocks(struct inode *inode,
depth = ext2_block_to_path(inode,iblock,offsets,&blocks_to_boundary);
if (depth == 0)
- return (err);
+ return -EIO;
partial = ext2_get_branch(inode, depth, offsets, chain, &err);
/* Simplest case - block found, no allocation needed */
@@ -761,7 +761,6 @@ static int ext2_get_blocks(struct inode *inode,
ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
mutex_unlock(&ei->truncate_mutex);
got_it:
- *bno = le32_to_cpu(chain[depth-1].key);
if (count > blocks_to_boundary)
*boundary = true;
err = count;
@@ -772,6 +771,8 @@ static int ext2_get_blocks(struct inode *inode,
brelse(partial->bh);
partial--;
}
+ if (err > 0)
+ *bno = le32_to_cpu(chain[depth-1].key);
return err;
}
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 02ddec6..fdb1954 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -128,12 +128,12 @@ static void debug_print_tree(struct ext4_sb_info *sbi)
node = rb_first(&sbi->system_blks);
while (node) {
entry = rb_entry(node, struct ext4_system_zone, node);
- printk("%s%llu-%llu", first ? "" : ", ",
+ printk(KERN_CONT "%s%llu-%llu", first ? "" : ", ",
entry->start_blk, entry->start_blk + entry->count - 1);
first = 0;
node = rb_next(node);
}
- printk("\n");
+ printk(KERN_CONT "\n");
}
int ext4_setup_system_zone(struct super_block *sb)
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 3ef1df6..1aba469 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -27,16 +27,15 @@
#ifdef CONFIG_EXT4_DEBUG
extern ushort ext4_mballoc_debug;
-#define mb_debug(n, fmt, a...) \
- do { \
- if ((n) <= ext4_mballoc_debug) { \
- printk(KERN_DEBUG "(%s, %d): %s: ", \
- __FILE__, __LINE__, __func__); \
- printk(fmt, ## a); \
- } \
- } while (0)
+#define mb_debug(n, fmt, ...) \
+do { \
+ if ((n) <= ext4_mballoc_debug) { \
+ printk(KERN_DEBUG "(%s, %d): %s: " fmt, \
+ __FILE__, __LINE__, __func__, ##__VA_ARGS__); \
+ } \
+} while (0)
#else
-#define mb_debug(n, fmt, a...) no_printk(fmt, ## a)
+#define mb_debug(n, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
#define EXT4_MB_HISTORY_ALLOC 1 /* allocation */
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index f92f10d..104f8bf 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -577,12 +577,13 @@ static inline unsigned dx_node_limit(struct inode *dir)
static void dx_show_index(char * label, struct dx_entry *entries)
{
int i, n = dx_get_count (entries);
- printk(KERN_DEBUG "%s index ", label);
+ printk(KERN_DEBUG "%s index", label);
for (i = 0; i < n; i++) {
- printk("%x->%lu ", i ? dx_get_hash(entries + i) :
- 0, (unsigned long)dx_get_block(entries + i));
+ printk(KERN_CONT " %x->%lu",
+ i ? dx_get_hash(entries + i) : 0,
+ (unsigned long)dx_get_block(entries + i));
}
- printk("\n");
+ printk(KERN_CONT "\n");
}
struct stats
@@ -679,7 +680,7 @@ static struct stats dx_show_leaf(struct inode *dir,
}
de = ext4_next_entry(de, size);
}
- printk("(%i)\n", names);
+ printk(KERN_CONT "(%i)\n", names);
return (struct stats) { names, space, 1 };
}
@@ -798,7 +799,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
q = entries + count - 1;
while (p <= q) {
m = p + (q - p) / 2;
- dxtrace(printk("."));
+ dxtrace(printk(KERN_CONT "."));
if (dx_get_hash(m) > hash)
q = m - 1;
else
@@ -810,7 +811,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
at = entries;
while (n--)
{
- dxtrace(printk(","));
+ dxtrace(printk(KERN_CONT ","));
if (dx_get_hash(++at) > hash)
{
at--;
@@ -821,7 +822,8 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
}
at = p - 1;
- dxtrace(printk(" %x->%u\n", at == entries ? 0 : dx_get_hash(at),
+ dxtrace(printk(KERN_CONT " %x->%u\n",
+ at == entries ? 0 : dx_get_hash(at),
dx_get_block(at)));
frame->entries = entries;
frame->at = at;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6db81fb..20da99d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -597,14 +597,15 @@ void __ext4_std_error(struct super_block *sb, const char *function,
void __ext4_abort(struct super_block *sb, const char *function,
unsigned int line, const char *fmt, ...)
{
+ struct va_format vaf;
va_list args;
save_error_info(sb, function, line);
va_start(args, fmt);
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: ", sb->s_id,
- function, line);
- vprintk(fmt, args);
- printk("\n");
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: %pV\n",
+ sb->s_id, function, line, &vaf);
va_end(args);
if ((sb->s_flags & MS_RDONLY) == 0) {
@@ -2715,12 +2716,12 @@ static void print_daily_error_info(unsigned long arg)
es->s_first_error_func,
le32_to_cpu(es->s_first_error_line));
if (es->s_first_error_ino)
- printk(": inode %u",
+ printk(KERN_CONT ": inode %u",
le32_to_cpu(es->s_first_error_ino));
if (es->s_first_error_block)
- printk(": block %llu", (unsigned long long)
+ printk(KERN_CONT ": block %llu", (unsigned long long)
le64_to_cpu(es->s_first_error_block));
- printk("\n");
+ printk(KERN_CONT "\n");
}
if (es->s_last_error_time) {
printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
@@ -2729,12 +2730,12 @@ static void print_daily_error_info(unsigned long arg)
es->s_last_error_func,
le32_to_cpu(es->s_last_error_line));
if (es->s_last_error_ino)
- printk(": inode %u",
+ printk(KERN_CONT ": inode %u",
le32_to_cpu(es->s_last_error_ino));
if (es->s_last_error_block)
- printk(": block %llu", (unsigned long long)
+ printk(KERN_CONT ": block %llu", (unsigned long long)
le64_to_cpu(es->s_last_error_block));
- printk("\n");
+ printk(KERN_CONT "\n");
}
mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); /* Once a day */
}
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 73bcfd4..42145be 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -223,14 +223,18 @@ static struct attribute *ext4_attrs[] = {
EXT4_ATTR_FEATURE(lazy_itable_init);
EXT4_ATTR_FEATURE(batched_discard);
EXT4_ATTR_FEATURE(meta_bg_resize);
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
EXT4_ATTR_FEATURE(encryption);
+#endif
EXT4_ATTR_FEATURE(metadata_csum_seed);
static struct attribute *ext4_feat_attrs[] = {
ATTR_LIST(lazy_itable_init),
ATTR_LIST(batched_discard),
ATTR_LIST(meta_bg_resize),
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
ATTR_LIST(encryption),
+#endif
ATTR_LIST(metadata_csum_seed),
NULL,
};
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index c15d633..d77be9e 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -61,18 +61,12 @@
#include "acl.h"
#ifdef EXT4_XATTR_DEBUG
-# define ea_idebug(inode, f...) do { \
- printk(KERN_DEBUG "inode %s:%lu: ", \
- inode->i_sb->s_id, inode->i_ino); \
- printk(f); \
- printk("\n"); \
- } while (0)
-# define ea_bdebug(bh, f...) do { \
- printk(KERN_DEBUG "block %pg:%lu: ", \
- bh->b_bdev, (unsigned long) bh->b_blocknr); \
- printk(f); \
- printk("\n"); \
- } while (0)
+# define ea_idebug(inode, fmt, ...) \
+ printk(KERN_DEBUG "inode %s:%lu: " fmt "\n", \
+ inode->i_sb->s_id, inode->i_ino, ##__VA_ARGS__)
+# define ea_bdebug(bh, fmt, ...) \
+ printk(KERN_DEBUG "block %pg:%lu: " fmt "\n", \
+ bh->b_bdev, (unsigned long)bh->b_blocknr, ##__VA_ARGS__)
#else
# define ea_idebug(inode, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
# define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
@@ -241,7 +235,7 @@ __xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header,
int error = -EFSCORRUPTED;
if (((void *) header >= end) ||
- (header->h_magic != le32_to_cpu(EXT4_XATTR_MAGIC)))
+ (header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)))
goto errout;
error = ext4_xattr_check_names(entry, end, entry);
errout:
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 93985c6..6f14ee9 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -852,16 +852,16 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
for (segno = start_segno; segno < end_segno; segno++) {
- if (get_valid_blocks(sbi, segno, 1) == 0 ||
- unlikely(f2fs_cp_error(sbi)))
- goto next;
-
/* find segment summary of victim */
sum_page = find_get_page(META_MAPPING(sbi),
GET_SUM_BLOCK(sbi, segno));
- f2fs_bug_on(sbi, !PageUptodate(sum_page));
f2fs_put_page(sum_page, 0);
+ if (get_valid_blocks(sbi, segno, 1) == 0 ||
+ !PageUptodate(sum_page) ||
+ unlikely(f2fs_cp_error(sbi)))
+ goto next;
+
sum = page_address(sum_page);
f2fs_bug_on(sbi, type != GET_SUM_TYPE((&sum->footer)));
diff --git a/fs/iomap.c b/fs/iomap.c
index 013d1d3..a8ee8c3 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -433,8 +433,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
struct page *page = data;
int ret;
- ret = __block_write_begin_int(page, pos & ~PAGE_MASK, length,
- NULL, iomap);
+ ret = __block_write_begin_int(page, pos, length, NULL, iomap);
if (ret)
return ret;
@@ -561,7 +560,7 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
}
while (len > 0) {
- ret = iomap_apply(inode, start, len, 0, ops, &ctx,
+ ret = iomap_apply(inode, start, len, IOMAP_REPORT, ops, &ctx,
iomap_fiemap_actor);
/* inode with no (attribute) mapping will give ENOENT */
if (ret == -ENOENT)
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index ad0c745..871c8b3 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -687,6 +687,11 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent)
pri_bh = NULL;
root_found:
+ /* We don't support read-write mounts */
+ if (!(s->s_flags & MS_RDONLY)) {
+ error = -EACCES;
+ goto out_freebh;
+ }
if (joliet_level && (pri == NULL || !opt.rock)) {
/* This is the case of Joliet with the norock mount flag.
@@ -1501,9 +1506,6 @@ struct inode *__isofs_iget(struct super_block *sb,
static struct dentry *isofs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
- /* We don't support read-write mounts */
- if (!(flags & MS_RDONLY))
- return ERR_PTR(-EACCES);
return mount_bdev(fs_type, flags, dev_name, data, isofs_fill_super);
}
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 3d8246a..e165266 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1149,6 +1149,7 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
JBUFFER_TRACE(jh, "file as BJ_Reserved");
spin_lock(&journal->j_list_lock);
__jbd2_journal_file_buffer(jh, transaction, BJ_Reserved);
+ spin_unlock(&journal->j_list_lock);
} else if (jh->b_transaction == journal->j_committing_transaction) {
/* first access by this transaction */
jh->b_modified = 0;
@@ -1156,8 +1157,8 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
JBUFFER_TRACE(jh, "set next transaction");
spin_lock(&journal->j_list_lock);
jh->b_next_transaction = transaction;
+ spin_unlock(&journal->j_list_lock);
}
- spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
/*
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index dcd96aa..cf4c636 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -110,8 +110,9 @@ static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a,
* kn_to: /n1/n2/n3 [depth=3]
* result: /../..
*
- * return value: length of the string. If greater than buflen,
- * then contents of buf are undefined. On error, -1 is returned.
+ * Returns the length of the full path. If the full length is equal to or
+ * greater than @buflen, @buf contains the truncated path with the trailing
+ * '\0'. On error, -errno is returned.
*/
static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
struct kernfs_node *kn_from,
@@ -119,9 +120,8 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
{
struct kernfs_node *kn, *common;
const char parent_str[] = "/..";
- size_t depth_from, depth_to, len = 0, nlen = 0;
- char *p;
- int i;
+ size_t depth_from, depth_to, len = 0;
+ int i, j;
if (!kn_from)
kn_from = kernfs_root(kn_to)->kn;
@@ -131,7 +131,7 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
common = kernfs_common_ancestor(kn_from, kn_to);
if (WARN_ON(!common))
- return -1;
+ return -EINVAL;
depth_to = kernfs_depth(common, kn_to);
depth_from = kernfs_depth(common, kn_from);
@@ -144,22 +144,16 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
len < buflen ? buflen - len : 0);
/* Calculate how many bytes we need for the rest */
- for (kn = kn_to; kn != common; kn = kn->parent)
- nlen += strlen(kn->name) + 1;
-
- if (len + nlen >= buflen)
- return len + nlen;
-
- p = buf + len + nlen;
- *p = '\0';
- for (kn = kn_to; kn != common; kn = kn->parent) {
- size_t tmp = strlen(kn->name);
- p -= tmp;
- memcpy(p, kn->name, tmp);
- *(--p) = '/';
+ for (i = depth_to - 1; i >= 0; i--) {
+ for (kn = kn_to, j = 0; j < i; j++)
+ kn = kn->parent;
+ len += strlcpy(buf + len, "/",
+ len < buflen ? buflen - len : 0);
+ len += strlcpy(buf + len, kn->name,
+ len < buflen ? buflen - len : 0);
}
- return len + nlen;
+ return len;
}
/**
@@ -186,29 +180,6 @@ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
}
/**
- * kernfs_path_len - determine the length of the full path of a given node
- * @kn: kernfs_node of interest
- *
- * The returned length doesn't include the space for the terminating '\0'.
- */
-size_t kernfs_path_len(struct kernfs_node *kn)
-{
- size_t len = 0;
- unsigned long flags;
-
- spin_lock_irqsave(&kernfs_rename_lock, flags);
-
- do {
- len += strlen(kn->name) + 1;
- kn = kn->parent;
- } while (kn && kn->parent);
-
- spin_unlock_irqrestore(&kernfs_rename_lock, flags);
-
- return len;
-}
-
-/**
* kernfs_path_from_node - build path of node @to relative to @from.
* @from: parent kernfs_node relative to which we need to build the path
* @to: kernfs_node of interest
@@ -220,8 +191,9 @@ size_t kernfs_path_len(struct kernfs_node *kn)
* path (which includes '..'s) as needed to reach from @from to @to is
* returned.
*
- * If @buf isn't long enough, the return value will be greater than @buflen
- * and @buf contents are undefined.
+ * Returns the length of the full path. If the full length is equal to or
+ * greater than @buflen, @buf contains the truncated path with the trailing
+ * '\0'. On error, -errno is returned.
*/
int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from,
char *buf, size_t buflen)
@@ -237,28 +209,6 @@ int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from,
EXPORT_SYMBOL_GPL(kernfs_path_from_node);
/**
- * kernfs_path - build full path of a given node
- * @kn: kernfs_node of interest
- * @buf: buffer to copy @kn's name into
- * @buflen: size of @buf
- *
- * Builds and returns the full path of @kn in @buf of @buflen bytes. The
- * path is built from the end of @buf so the returned pointer usually
- * doesn't match @buf. If @buf isn't long enough, @buf is nul terminated
- * and %NULL is returned.
- */
-char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen)
-{
- int ret;
-
- ret = kernfs_path_from_node(kn, NULL, buf, buflen);
- if (ret < 0 || ret >= buflen)
- return NULL;
- return buf;
-}
-EXPORT_SYMBOL_GPL(kernfs_path);
-
-/**
* pr_cont_kernfs_name - pr_cont name of a kernfs_node
* @kn: kernfs_node of interest
*
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 2bcb86e..78219d5 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -911,6 +911,7 @@ const struct file_operations kernfs_file_fops = {
.open = kernfs_fop_open,
.release = kernfs_fop_release,
.poll = kernfs_fop_poll,
+ .fsync = noop_fsync,
};
/**
diff --git a/fs/lockd/netns.h b/fs/lockd/netns.h
index 5426189..fb8cac8 100644
--- a/fs/lockd/netns.h
+++ b/fs/lockd/netns.h
@@ -15,6 +15,6 @@ struct lockd_net {
struct list_head nsm_handles;
};
-extern int lockd_net_id;
+extern unsigned int lockd_net_id;
#endif
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index fc4084e..1c13dd8 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -57,7 +57,7 @@ static struct task_struct *nlmsvc_task;
static struct svc_rqst *nlmsvc_rqst;
unsigned long nlmsvc_timeout;
-int lockd_net_id;
+unsigned int lockd_net_id;
/*
* These can be set at insmod time (useful for NFS as root filesystem),
diff --git a/fs/locks.c b/fs/locks.c
index ce93b41..22c5b4a 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1609,6 +1609,7 @@ int fcntl_getlease(struct file *filp)
ctx = smp_load_acquire(&inode->i_flctx);
if (ctx && !list_empty_careful(&ctx->flc_lease)) {
+ percpu_down_read_preempt_disable(&file_rwsem);
spin_lock(&ctx->flc_lock);
time_out_leases(inode, &dispose);
list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
@@ -1618,6 +1619,8 @@ int fcntl_getlease(struct file *filp)
break;
}
spin_unlock(&ctx->flc_lock);
+ percpu_up_read_preempt_enable(&file_rwsem);
+
locks_dispose_list(&dispose);
}
return type;
@@ -2529,11 +2532,14 @@ locks_remove_lease(struct file *filp, struct file_lock_context *ctx)
if (list_empty(&ctx->flc_lease))
return;
+ percpu_down_read_preempt_disable(&file_rwsem);
spin_lock(&ctx->flc_lock);
list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list)
if (filp == fl->fl_file)
lease_modify(fl, F_UNLCK, &dispose);
spin_unlock(&ctx->flc_lock);
+ percpu_up_read_preempt_enable(&file_rwsem);
+
locks_dispose_list(&dispose);
}
diff --git a/fs/namei.c b/fs/namei.c
index a7f601c..5b4eed2 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4668,6 +4668,31 @@ int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen)
}
EXPORT_SYMBOL(generic_readlink);
+/**
+ * vfs_get_link - get symlink body
+ * @dentry: dentry on which to get symbolic link
+ * @done: caller needs to free returned data with this
+ *
+ * Calls security hook and i_op->get_link() on the supplied inode.
+ *
+ * It does not touch atime. That's up to the caller if necessary.
+ *
+ * Does not work on "special" symlinks like /proc/$$/fd/N
+ */
+const char *vfs_get_link(struct dentry *dentry, struct delayed_call *done)
+{
+ const char *res = ERR_PTR(-EINVAL);
+ struct inode *inode = d_inode(dentry);
+
+ if (d_is_symlink(dentry)) {
+ res = ERR_PTR(security_inode_readlink(dentry));
+ if (!res)
+ res = inode->i_op->get_link(dentry, inode, done);
+ }
+ return res;
+}
+EXPORT_SYMBOL(vfs_get_link);
+
/* get the link contents into pagecache */
const char *page_get_link(struct dentry *dentry, struct inode *inode,
struct delayed_call *callback)
diff --git a/fs/namespace.c b/fs/namespace.c
index 58aca9c..e6c234b 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2824,6 +2824,7 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns)
return new_ns;
}
+__latent_entropy
struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
struct user_namespace *user_ns, struct fs_struct *new_fs)
{
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 2178476..2905479 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -344,9 +344,10 @@ static void bl_write_cleanup(struct work_struct *work)
u64 start = hdr->args.offset & (loff_t)PAGE_MASK;
u64 end = (hdr->args.offset + hdr->args.count +
PAGE_SIZE - 1) & (loff_t)PAGE_MASK;
+ u64 lwb = hdr->args.offset + hdr->args.count;
ext_tree_mark_written(bl, start >> SECTOR_SHIFT,
- (end - start) >> SECTOR_SHIFT, end);
+ (end - start) >> SECTOR_SHIFT, lwb);
}
pnfs_ld_write_done(hdr);
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 7555ba8..ebecfb8 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -314,7 +314,8 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
/* Match the full socket address */
if (!rpc_cmp_addr_port(sap, clap))
/* Match all xprt_switch full socket addresses */
- if (!rpc_clnt_xprt_switch_has_addr(clp->cl_rpcclient,
+ if (IS_ERR(clp->cl_rpcclient) ||
+ !rpc_clnt_xprt_switch_has_addr(clp->cl_rpcclient,
sap))
continue;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index bf4ec5e..ce42dd0 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -2015,7 +2015,7 @@ static void nfsiod_stop(void)
destroy_workqueue(wq);
}
-int nfs_net_id;
+unsigned int nfs_net_id;
EXPORT_SYMBOL_GPL(nfs_net_id);
static int nfs_net_init(struct net *net)
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index c8162c6..5551e8e 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -98,7 +98,7 @@ char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen,
return end;
}
namelen = strlen(base);
- if (flags & NFS_PATH_CANONICAL) {
+ if (*end == '/') {
/* Strip off excess slashes in base string */
while (namelen > 0 && base[namelen - 1] == '/')
namelen--;
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
index fbce0d8..5fbd2bd 100644
--- a/fs/nfs/netns.h
+++ b/fs/nfs/netns.h
@@ -35,6 +35,6 @@ struct nfs_net {
#endif
};
-extern int nfs_net_id;
+extern unsigned int nfs_net_id;
#endif
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ad917bd7..7897826 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1545,7 +1545,7 @@ static int update_open_stateid(struct nfs4_state *state,
struct nfs_client *clp = server->nfs_client;
struct nfs_inode *nfsi = NFS_I(state->inode);
struct nfs_delegation *deleg_cur;
- nfs4_stateid freeme = {0};
+ nfs4_stateid freeme = { };
int ret = 0;
fmode &= (FMODE_READ|FMODE_WRITE);
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index b629730..a61350f 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -178,12 +178,14 @@ static int nfs4_slot_get_seqid(struct nfs4_slot_table *tbl, u32 slotid,
__must_hold(&tbl->slot_tbl_lock)
{
struct nfs4_slot *slot;
+ int ret;
slot = nfs4_lookup_slot(tbl, slotid);
- if (IS_ERR(slot))
- return PTR_ERR(slot);
- *seq_nr = slot->seq_nr;
- return 0;
+ ret = PTR_ERR_OR_ZERO(slot);
+ if (!ret)
+ *seq_nr = slot->seq_nr;
+
+ return ret;
}
/*
@@ -196,7 +198,7 @@ static int nfs4_slot_get_seqid(struct nfs4_slot_table *tbl, u32 slotid,
static bool nfs4_slot_seqid_in_use(struct nfs4_slot_table *tbl,
u32 slotid, u32 seq_nr)
{
- u32 cur_seq;
+ u32 cur_seq = 0;
bool ret = false;
spin_lock(&tbl->slot_tbl_lock);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 56b2d96..259ef85 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -146,6 +146,8 @@ set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh,
u32 id;
int i;
+ if (fsinfo->nlayouttypes == 0)
+ goto out_no_driver;
if (!(server->nfs_client->cl_exchange_flags &
(EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_USE_PNFS_MDS))) {
printk(KERN_ERR "NFS: %s: cl_exchange_flags 0x%x\n",
diff --git a/fs/nfs_common/grace.c b/fs/nfs_common/grace.c
index fd8c9a5..420d3a0 100644
--- a/fs/nfs_common/grace.c
+++ b/fs/nfs_common/grace.c
@@ -9,7 +9,7 @@
#include <net/netns/generic.h>
#include <linux/fs.h>
-static int grace_net_id;
+static unsigned int grace_net_id;
static DEFINE_SPINLOCK(grace_lock);
/**
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index b10d557..3714231 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -84,6 +84,8 @@ struct nfsd_net {
struct list_head client_lru;
struct list_head close_lru;
struct list_head del_recall_lru;
+
+ /* protected by blocked_locks_lock */
struct list_head blocked_locks_lru;
struct delayed_work laundromat_work;
@@ -91,6 +93,9 @@ struct nfsd_net {
/* client_lock protects the client lru list and session hash table */
spinlock_t client_lock;
+ /* protects blocked_locks_lru */
+ spinlock_t blocked_locks_lock;
+
struct file *rec_file;
bool in_grace;
const struct nfsd4_client_tracking_ops *client_tracking_ops;
@@ -119,5 +124,5 @@ struct nfsd_net {
/* Simple check to find out if a given net was properly initialized */
#define nfsd_netns_ready(nn) ((nn)->sessionid_hashtbl)
-extern int nfsd_net_id;
+extern unsigned int nfsd_net_id;
#endif /* __NFSD_NETNS_H__ */
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9752beb..4b4beaa 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -217,7 +217,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
{
struct nfsd4_blocked_lock *cur, *found = NULL;
- spin_lock(&nn->client_lock);
+ spin_lock(&nn->blocked_locks_lock);
list_for_each_entry(cur, &lo->lo_blocked, nbl_list) {
if (fh_match(fh, &cur->nbl_fh)) {
list_del_init(&cur->nbl_list);
@@ -226,7 +226,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
break;
}
}
- spin_unlock(&nn->client_lock);
+ spin_unlock(&nn->blocked_locks_lock);
if (found)
posix_unblock_lock(&found->nbl_lock);
return found;
@@ -1227,9 +1227,7 @@ static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp,
static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp)
{
- struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner);
-
- lockdep_assert_held(&oo->oo_owner.so_client->cl_lock);
+ lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);
list_del_init(&stp->st_locks);
nfs4_unhash_stid(&stp->st_stid);
@@ -1238,12 +1236,12 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp)
static void release_lock_stateid(struct nfs4_ol_stateid *stp)
{
- struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner);
+ struct nfs4_client *clp = stp->st_stid.sc_client;
bool unhashed;
- spin_lock(&oo->oo_owner.so_client->cl_lock);
+ spin_lock(&clp->cl_lock);
unhashed = unhash_lock_stateid(stp);
- spin_unlock(&oo->oo_owner.so_client->cl_lock);
+ spin_unlock(&clp->cl_lock);
if (unhashed)
nfs4_put_stid(&stp->st_stid);
}
@@ -4665,7 +4663,7 @@ nfs4_laundromat(struct nfsd_net *nn)
* indefinitely once the lock does become free.
*/
BUG_ON(!list_empty(&reaplist));
- spin_lock(&nn->client_lock);
+ spin_lock(&nn->blocked_locks_lock);
while (!list_empty(&nn->blocked_locks_lru)) {
nbl = list_first_entry(&nn->blocked_locks_lru,
struct nfsd4_blocked_lock, nbl_lru);
@@ -4678,7 +4676,7 @@ nfs4_laundromat(struct nfsd_net *nn)
list_move(&nbl->nbl_lru, &reaplist);
list_del_init(&nbl->nbl_list);
}
- spin_unlock(&nn->client_lock);
+ spin_unlock(&nn->blocked_locks_lock);
while (!list_empty(&reaplist)) {
nbl = list_first_entry(&nn->blocked_locks_lru,
@@ -5439,13 +5437,13 @@ nfsd4_lm_notify(struct file_lock *fl)
bool queue = false;
/* An empty list means that something else is going to be using it */
- spin_lock(&nn->client_lock);
+ spin_lock(&nn->blocked_locks_lock);
if (!list_empty(&nbl->nbl_list)) {
list_del_init(&nbl->nbl_list);
list_del_init(&nbl->nbl_lru);
queue = true;
}
- spin_unlock(&nn->client_lock);
+ spin_unlock(&nn->blocked_locks_lock);
if (queue)
nfsd4_run_cb(&nbl->nbl_cb);
@@ -5868,10 +5866,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (fl_flags & FL_SLEEP) {
nbl->nbl_time = jiffies;
- spin_lock(&nn->client_lock);
+ spin_lock(&nn->blocked_locks_lock);
list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked);
list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru);
- spin_unlock(&nn->client_lock);
+ spin_unlock(&nn->blocked_locks_lock);
}
err = vfs_lock_file(filp, F_SETLK, file_lock, conflock);
@@ -5900,10 +5898,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (nbl) {
/* dequeue it if we queued it before */
if (fl_flags & FL_SLEEP) {
- spin_lock(&nn->client_lock);
+ spin_lock(&nn->blocked_locks_lock);
list_del_init(&nbl->nbl_list);
list_del_init(&nbl->nbl_lru);
- spin_unlock(&nn->client_lock);
+ spin_unlock(&nn->blocked_locks_lock);
}
free_blocked_lock(nbl);
}
@@ -6943,9 +6941,11 @@ static int nfs4_state_create_net(struct net *net)
INIT_LIST_HEAD(&nn->client_lru);
INIT_LIST_HEAD(&nn->close_lru);
INIT_LIST_HEAD(&nn->del_recall_lru);
- INIT_LIST_HEAD(&nn->blocked_locks_lru);
spin_lock_init(&nn->client_lock);
+ spin_lock_init(&nn->blocked_locks_lock);
+ INIT_LIST_HEAD(&nn->blocked_locks_lru);
+
INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main);
get_net(net);
@@ -7063,14 +7063,14 @@ nfs4_state_shutdown_net(struct net *net)
}
BUG_ON(!list_empty(&reaplist));
- spin_lock(&nn->client_lock);
+ spin_lock(&nn->blocked_locks_lock);
while (!list_empty(&nn->blocked_locks_lru)) {
nbl = list_first_entry(&nn->blocked_locks_lru,
struct nfsd4_blocked_lock, nbl_lru);
list_move(&nbl->nbl_lru, &reaplist);
list_del_init(&nbl->nbl_list);
}
- spin_unlock(&nn->client_lock);
+ spin_unlock(&nn->blocked_locks_lock);
while (!list_empty(&reaplist)) {
nbl = list_first_entry(&nn->blocked_locks_lru,
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 36b2af9..2857e46 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1201,7 +1201,7 @@ static int create_proc_exports_entry(void)
}
#endif
-int nfsd_net_id;
+unsigned int nfsd_net_id;
static __net_init int nfsd_init_net(struct net *net)
{
diff --git a/fs/nsfs.c b/fs/nsfs.c
index 8718af8..8c9fb29 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -118,7 +118,7 @@ void *ns_get_path(struct path *path, struct task_struct *task,
return ret;
}
-static int open_related_ns(struct ns_common *ns,
+int open_related_ns(struct ns_common *ns,
struct ns_common *(*get_ns)(struct ns_common *ns))
{
struct path path = {};
diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c
index a186135..0ee19ec 100644
--- a/fs/ntfs/dir.c
+++ b/fs/ntfs/dir.c
@@ -1544,8 +1544,6 @@ const struct file_operations ntfs_dir_ops = {
.iterate = ntfs_readdir, /* Read directory contents. */
#ifdef NTFS_RW
.fsync = ntfs_dir_fsync, /* Sync a directory to disk. */
- /*.aio_fsync = ,*/ /* Sync all outstanding async
- i/o operations on a kiocb. */
#endif /* NTFS_RW */
/*.ioctl = ,*/ /* Perform function on the
mounted filesystem. */
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index e7054e2..3ecb9f3 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -3699,7 +3699,7 @@ static void ocfs2_dx_dir_transfer_leaf(struct inode *dir, u32 split_hash,
static int ocfs2_dx_dir_rebalance_credits(struct ocfs2_super *osb,
struct ocfs2_dx_root_block *dx_root)
{
- int credits = ocfs2_clusters_to_blocks(osb->sb, 2);
+ int credits = ocfs2_clusters_to_blocks(osb->sb, 3);
credits += ocfs2_calc_extend_credits(osb->sb, &dx_root->dr_list);
credits += ocfs2_quota_trans_credits(osb->sb);
diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c
index 1e8fe84..5355efb 100644
--- a/fs/orangefs/dcache.c
+++ b/fs/orangefs/dcache.c
@@ -73,7 +73,7 @@ static int orangefs_revalidate_lookup(struct dentry *dentry)
}
}
- dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+ orangefs_set_timeout(dentry);
ret = 1;
out_release_op:
op_release(new_op);
@@ -94,8 +94,9 @@ static int orangefs_revalidate_lookup(struct dentry *dentry)
static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags)
{
int ret;
+ unsigned long time = (unsigned long) dentry->d_fsdata;
- if (time_before(jiffies, dentry->d_time))
+ if (time_before(jiffies, time))
return 1;
if (flags & LOOKUP_RCU)
diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index 66ea0cc..02cc613 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -621,9 +621,9 @@ static int orangefs_file_release(struct inode *inode, struct file *file)
* readahead cache (if any); this forces an expensive refresh of
* data for the next caller of mmap (or 'get_block' accesses)
*/
- if (file->f_path.dentry->d_inode &&
- file->f_path.dentry->d_inode->i_mapping &&
- mapping_nrpages(&file->f_path.dentry->d_inode->i_data)) {
+ if (file_inode(file) &&
+ file_inode(file)->i_mapping &&
+ mapping_nrpages(&file_inode(file)->i_data)) {
if (orangefs_features & ORANGEFS_FEATURE_READAHEAD) {
gossip_debug(GOSSIP_INODE_DEBUG,
"calling flush_racache on %pU\n",
@@ -632,7 +632,7 @@ static int orangefs_file_release(struct inode *inode, struct file *file)
gossip_debug(GOSSIP_INODE_DEBUG,
"flush_racache finished\n");
}
- truncate_inode_pages(file->f_path.dentry->d_inode->i_mapping,
+ truncate_inode_pages(file_inode(file)->i_mapping,
0);
}
return 0;
@@ -648,7 +648,7 @@ static int orangefs_fsync(struct file *file,
{
int ret = -EINVAL;
struct orangefs_inode_s *orangefs_inode =
- ORANGEFS_I(file->f_path.dentry->d_inode);
+ ORANGEFS_I(file_inode(file));
struct orangefs_kernel_op_s *new_op = NULL;
/* required call */
@@ -661,7 +661,7 @@ static int orangefs_fsync(struct file *file,
ret = service_operation(new_op,
"orangefs_fsync",
- get_interruptible_flag(file->f_path.dentry->d_inode));
+ get_interruptible_flag(file_inode(file)));
gossip_debug(GOSSIP_FILE_DEBUG,
"orangefs_fsync got return value of %d\n",
@@ -669,7 +669,7 @@ static int orangefs_fsync(struct file *file,
op_release(new_op);
- orangefs_flush_inode(file->f_path.dentry->d_inode);
+ orangefs_flush_inode(file_inode(file));
return ret;
}
diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c
index d15d3d2..a290ff6 100644
--- a/fs/orangefs/namei.c
+++ b/fs/orangefs/namei.c
@@ -72,7 +72,7 @@ static int orangefs_create(struct inode *dir,
d_instantiate(dentry, inode);
unlock_new_inode(inode);
- dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+ orangefs_set_timeout(dentry);
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
@@ -183,7 +183,7 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry,
goto out;
}
- dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+ orangefs_set_timeout(dentry);
inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn);
if (IS_ERR(inode)) {
@@ -322,7 +322,7 @@ static int orangefs_symlink(struct inode *dir,
d_instantiate(dentry, inode);
unlock_new_inode(inode);
- dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+ orangefs_set_timeout(dentry);
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
@@ -386,7 +386,7 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
d_instantiate(dentry, inode);
unlock_new_inode(inode);
- dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+ orangefs_set_timeout(dentry);
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c
index eb09aa0..d484068 100644
--- a/fs/orangefs/orangefs-debugfs.c
+++ b/fs/orangefs/orangefs-debugfs.c
@@ -141,6 +141,9 @@ static struct client_debug_mask client_debug_mask;
*/
static DEFINE_MUTEX(orangefs_debug_lock);
+/* Used to protect data in ORANGEFS_KMOD_DEBUG_HELP_FILE */
+static DEFINE_MUTEX(orangefs_help_file_lock);
+
/*
* initialize kmod debug operations, create orangefs debugfs dir and
* ORANGEFS_KMOD_DEBUG_HELP_FILE.
@@ -289,6 +292,8 @@ static void *help_start(struct seq_file *m, loff_t *pos)
gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_start: start\n");
+ mutex_lock(&orangefs_help_file_lock);
+
if (*pos == 0)
payload = m->private;
@@ -305,6 +310,7 @@ static void *help_next(struct seq_file *m, void *v, loff_t *pos)
static void help_stop(struct seq_file *m, void *p)
{
gossip_debug(GOSSIP_DEBUGFS_DEBUG, "help_stop: start\n");
+ mutex_unlock(&orangefs_help_file_lock);
}
static int help_show(struct seq_file *m, void *v)
@@ -610,32 +616,54 @@ static int orangefs_prepare_cdm_array(char *debug_array_string)
* /sys/kernel/debug/orangefs/debug-help can be catted to
* see all the available kernel and client debug keywords.
*
- * When the kernel boots, we have no idea what keywords the
+ * When orangefs.ko initializes, we have no idea what keywords the
* client supports, nor their associated masks.
*
- * We pass through this function once at boot and stamp a
+ * We pass through this function once at module-load and stamp a
* boilerplate "we don't know" message for the client in the
* debug-help file. We pass through here again when the client
* starts and then we can fill out the debug-help file fully.
*
* The client might be restarted any number of times between
- * reboots, we only build the debug-help file the first time.
+ * module reloads, we only build the debug-help file the first time.
*/
int orangefs_prepare_debugfs_help_string(int at_boot)
{
- int rc = -EINVAL;
- int i;
- int byte_count = 0;
char *client_title = "Client Debug Keywords:\n";
char *kernel_title = "Kernel Debug Keywords:\n";
+ size_t string_size = DEBUG_HELP_STRING_SIZE;
+ size_t result_size;
+ size_t i;
+ char *new;
+ int rc = -EINVAL;
gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__);
- if (at_boot) {
- byte_count += strlen(HELP_STRING_UNINITIALIZED);
+ if (at_boot)
client_title = HELP_STRING_UNINITIALIZED;
- } else {
- /*
+
+ /* build a new debug_help_string. */
+ new = kzalloc(DEBUG_HELP_STRING_SIZE, GFP_KERNEL);
+ if (!new) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ /*
+ * strlcat(dst, src, size) will append at most
+ * "size - strlen(dst) - 1" bytes of src onto dst,
+ * null terminating the result, and return the total
+ * length of the string it tried to create.
+ *
+ * We'll just plow through here building our new debug
+ * help string and let strlcat take care of assuring that
+ * dst doesn't overflow.
+ */
+ strlcat(new, client_title, string_size);
+
+ if (!at_boot) {
+
+ /*
* fill the client keyword/mask array and remember
* how many elements there were.
*/
@@ -644,64 +672,40 @@ int orangefs_prepare_debugfs_help_string(int at_boot)
if (cdm_element_count <= 0)
goto out;
- /* Count the bytes destined for debug_help_string. */
- byte_count += strlen(client_title);
-
for (i = 0; i < cdm_element_count; i++) {
- byte_count += strlen(cdm_array[i].keyword + 2);
- if (byte_count >= DEBUG_HELP_STRING_SIZE) {
- pr_info("%s: overflow 1!\n", __func__);
- goto out;
- }
+ strlcat(new, "\t", string_size);
+ strlcat(new, cdm_array[i].keyword, string_size);
+ strlcat(new, "\n", string_size);
}
-
- gossip_debug(GOSSIP_UTILS_DEBUG,
- "%s: cdm_element_count:%d:\n",
- __func__,
- cdm_element_count);
}
- byte_count += strlen(kernel_title);
+ strlcat(new, "\n", string_size);
+ strlcat(new, kernel_title, string_size);
+
for (i = 0; i < num_kmod_keyword_mask_map; i++) {
- byte_count +=
- strlen(s_kmod_keyword_mask_map[i].keyword + 2);
- if (byte_count >= DEBUG_HELP_STRING_SIZE) {
- pr_info("%s: overflow 2!\n", __func__);
- goto out;
- }
+ strlcat(new, "\t", string_size);
+ strlcat(new, s_kmod_keyword_mask_map[i].keyword, string_size);
+ result_size = strlcat(new, "\n", string_size);
}
- /* build debug_help_string. */
- debug_help_string = kzalloc(DEBUG_HELP_STRING_SIZE, GFP_KERNEL);
- if (!debug_help_string) {
- rc = -ENOMEM;
+ /* See if we tried to put too many bytes into "new"... */
+ if (result_size >= string_size) {
+ kfree(new);
goto out;
}
- strcat(debug_help_string, client_title);
-
- if (!at_boot) {
- for (i = 0; i < cdm_element_count; i++) {
- strcat(debug_help_string, "\t");
- strcat(debug_help_string, cdm_array[i].keyword);
- strcat(debug_help_string, "\n");
- }
- }
-
- strcat(debug_help_string, "\n");
- strcat(debug_help_string, kernel_title);
-
- for (i = 0; i < num_kmod_keyword_mask_map; i++) {
- strcat(debug_help_string, "\t");
- strcat(debug_help_string, s_kmod_keyword_mask_map[i].keyword);
- strcat(debug_help_string, "\n");
+ if (at_boot) {
+ debug_help_string = new;
+ } else {
+ mutex_lock(&orangefs_help_file_lock);
+ memset(debug_help_string, 0, DEBUG_HELP_STRING_SIZE);
+ strlcat(debug_help_string, new, string_size);
+ mutex_unlock(&orangefs_help_file_lock);
}
rc = 0;
-out:
-
- return rc;
+out: return rc;
}
@@ -959,8 +963,12 @@ int orangefs_debugfs_new_client_string(void __user *arg)
ret = copy_from_user(&client_debug_array_string,
(void __user *)arg,
ORANGEFS_MAX_DEBUG_STRING_LEN);
- if (ret != 0)
+
+ if (ret != 0) {
+ pr_info("%s: CLIENT_STRING: copy_from_user failed\n",
+ __func__);
return -EIO;
+ }
/*
* The real client-core makes an effort to ensure
@@ -975,45 +983,18 @@ int orangefs_debugfs_new_client_string(void __user *arg)
client_debug_array_string[ORANGEFS_MAX_DEBUG_STRING_LEN - 1] =
'\0';
- if (ret != 0) {
- pr_info("%s: CLIENT_STRING: copy_from_user failed\n",
- __func__);
- return -EIO;
- }
-
pr_info("%s: client debug array string has been received.\n",
__func__);
if (!help_string_initialized) {
- /* Free the "we don't know yet" default string... */
- kfree(debug_help_string);
-
- /* build a proper debug help string */
+ /* Build a proper debug help string. */
if (orangefs_prepare_debugfs_help_string(0)) {
gossip_err("%s: no debug help string \n",
__func__);
return -EIO;
}
- /* Replace the boilerplate boot-time debug-help file. */
- debugfs_remove(help_file_dentry);
-
- help_file_dentry =
- debugfs_create_file(
- ORANGEFS_KMOD_DEBUG_HELP_FILE,
- 0444,
- debug_dir,
- debug_help_string,
- &debug_help_fops);
-
- if (!help_file_dentry) {
- gossip_err("%s: debugfs_create_file failed for"
- " :%s:!\n",
- __func__,
- ORANGEFS_KMOD_DEBUG_HELP_FILE);
- return -EIO;
- }
}
debug_mask_to_string(&client_debug_mask, 1);
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index 0a82048..3bf803d 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -580,4 +580,11 @@ static inline void orangefs_i_size_write(struct inode *inode, loff_t i_size)
#endif
}
+static inline void orangefs_set_timeout(struct dentry *dentry)
+{
+ unsigned long time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
+
+ dentry->d_fsdata = (void *) time;
+}
+
#endif /* __ORANGEFSKERNEL_H */
diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c
index 2e5b030..4113eb0 100644
--- a/fs/orangefs/orangefs-mod.c
+++ b/fs/orangefs/orangefs-mod.c
@@ -124,7 +124,7 @@ static int __init orangefs_init(void)
* unknown at boot time.
*
* orangefs_prepare_debugfs_help_string will be used again
- * later to rebuild the debug-help file after the client starts
+ * later to rebuild the debug-help-string after the client starts
* and passes along the needed info. The argument signifies
* which time orangefs_prepare_debugfs_help_string is being
* called.
@@ -152,7 +152,9 @@ static int __init orangefs_init(void)
ret = register_filesystem(&orangefs_fs_type);
if (ret == 0) {
- pr_info("orangefs: module version %s loaded\n", ORANGEFS_VERSION);
+ pr_info("%s: module version %s loaded\n",
+ __func__,
+ ORANGEFS_VERSION);
ret = 0;
goto out;
}
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 3f803b3..36795ee 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -57,6 +57,7 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new)
ssize_t list_size, size, value_size = 0;
char *buf, *name, *value = NULL;
int uninitialized_var(error);
+ size_t slen;
if (!(old->d_inode->i_opflags & IOP_XATTR) ||
!(new->d_inode->i_opflags & IOP_XATTR))
@@ -79,7 +80,16 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new)
goto out;
}
- for (name = buf; name < (buf + list_size); name += strlen(name) + 1) {
+ for (name = buf; list_size; name += slen) {
+ slen = strnlen(name, list_size) + 1;
+
+ /* underlying fs providing us with an broken xattr list? */
+ if (WARN_ON(slen > list_size)) {
+ error = -EIO;
+ break;
+ }
+ list_size -= slen;
+
if (ovl_is_private_xattr(name))
continue;
retry:
@@ -168,46 +178,14 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
len -= bytes;
}
+ if (!error)
+ error = vfs_fsync(new_file, 0);
fput(new_file);
out_fput:
fput(old_file);
return error;
}
-static char *ovl_read_symlink(struct dentry *realdentry)
-{
- int res;
- char *buf;
- struct inode *inode = realdentry->d_inode;
- mm_segment_t old_fs;
-
- res = -EINVAL;
- if (!inode->i_op->readlink)
- goto err;
-
- res = -ENOMEM;
- buf = (char *) __get_free_page(GFP_KERNEL);
- if (!buf)
- goto err;
-
- old_fs = get_fs();
- set_fs(get_ds());
- /* The cast to a user pointer is valid due to the set_fs() */
- res = inode->i_op->readlink(realdentry,
- (char __user *)buf, PAGE_SIZE - 1);
- set_fs(old_fs);
- if (res < 0) {
- free_page((unsigned long) buf);
- goto err;
- }
- buf[res] = '\0';
-
- return buf;
-
-err:
- return ERR_PTR(res);
-}
-
static int ovl_set_timestamps(struct dentry *upperdentry, struct kstat *stat)
{
struct iattr attr = {
@@ -354,19 +332,20 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
struct path *lowerpath, struct kstat *stat)
{
+ DEFINE_DELAYED_CALL(done);
struct dentry *workdir = ovl_workdir(dentry);
int err;
struct kstat pstat;
struct path parentpath;
+ struct dentry *lowerdentry = lowerpath->dentry;
struct dentry *upperdir;
struct dentry *upperdentry;
- const struct cred *old_cred;
- char *link = NULL;
+ const char *link = NULL;
if (WARN_ON(!workdir))
return -EROFS;
- ovl_do_check_copy_up(lowerpath->dentry);
+ ovl_do_check_copy_up(lowerdentry);
ovl_path_upper(parent, &parentpath);
upperdir = parentpath.dentry;
@@ -376,13 +355,11 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
return err;
if (S_ISLNK(stat->mode)) {
- link = ovl_read_symlink(lowerpath->dentry);
+ link = vfs_get_link(lowerdentry, &done);
if (IS_ERR(link))
return PTR_ERR(link);
}
- old_cred = ovl_override_creds(dentry->d_sb);
-
err = -EIO;
if (lock_rename(workdir, upperdir) != NULL) {
pr_err("overlayfs: failed to lock workdir+upperdir\n");
@@ -403,19 +380,16 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
}
out_unlock:
unlock_rename(workdir, upperdir);
- revert_creds(old_cred);
-
- if (link)
- free_page((unsigned long) link);
+ do_delayed_call(&done);
return err;
}
int ovl_copy_up(struct dentry *dentry)
{
- int err;
+ int err = 0;
+ const struct cred *old_cred = ovl_override_creds(dentry->d_sb);
- err = 0;
while (!err) {
struct dentry *next;
struct dentry *parent;
@@ -447,6 +421,7 @@ int ovl_copy_up(struct dentry *dentry)
dput(parent);
dput(next);
}
+ revert_creds(old_cred);
return err;
}
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 5f90ddf..306b6c1 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -14,6 +14,7 @@
#include <linux/cred.h>
#include <linux/posix_acl.h>
#include <linux/posix_acl_xattr.h>
+#include <linux/atomic.h>
#include "overlayfs.h"
void ovl_cleanup(struct inode *wdir, struct dentry *wdentry)
@@ -37,8 +38,10 @@ struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry)
{
struct dentry *temp;
char name[20];
+ static atomic_t temp_id = ATOMIC_INIT(0);
- snprintf(name, sizeof(name), "#%lx", (unsigned long) dentry);
+ /* counter is allowed to wrap, since temp dentries are ephemeral */
+ snprintf(name, sizeof(name), "#%x", atomic_inc_return(&temp_id));
temp = lookup_one_len(name, workdir, strlen(name));
if (!IS_ERR(temp) && temp->d_inode) {
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index c18d6a4..7fb53d0 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -19,6 +19,7 @@ static int ovl_copy_up_truncate(struct dentry *dentry)
struct dentry *parent;
struct kstat stat;
struct path lowerpath;
+ const struct cred *old_cred;
parent = dget_parent(dentry);
err = ovl_copy_up(parent);
@@ -26,12 +27,14 @@ static int ovl_copy_up_truncate(struct dentry *dentry)
goto out_dput_parent;
ovl_path_lower(dentry, &lowerpath);
- err = vfs_getattr(&lowerpath, &stat);
- if (err)
- goto out_dput_parent;
- stat.size = 0;
- err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat);
+ old_cred = ovl_override_creds(dentry->d_sb);
+ err = vfs_getattr(&lowerpath, &stat);
+ if (!err) {
+ stat.size = 0;
+ err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat);
+ }
+ revert_creds(old_cred);
out_dput_parent:
dput(parent);
@@ -153,45 +156,18 @@ static const char *ovl_get_link(struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
- struct dentry *realdentry;
- struct inode *realinode;
const struct cred *old_cred;
const char *p;
if (!dentry)
return ERR_PTR(-ECHILD);
- realdentry = ovl_dentry_real(dentry);
- realinode = realdentry->d_inode;
-
- if (WARN_ON(!realinode->i_op->get_link))
- return ERR_PTR(-EPERM);
-
old_cred = ovl_override_creds(dentry->d_sb);
- p = realinode->i_op->get_link(realdentry, realinode, done);
+ p = vfs_get_link(ovl_dentry_real(dentry), done);
revert_creds(old_cred);
return p;
}
-static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
-{
- struct path realpath;
- struct inode *realinode;
- const struct cred *old_cred;
- int err;
-
- ovl_path_real(dentry, &realpath);
- realinode = realpath.dentry->d_inode;
-
- if (!realinode->i_op->readlink)
- return -EINVAL;
-
- old_cred = ovl_override_creds(dentry->d_sb);
- err = realinode->i_op->readlink(realpath.dentry, buf, bufsiz);
- revert_creds(old_cred);
- return err;
-}
-
bool ovl_is_private_xattr(const char *name)
{
return strncmp(name, OVL_XATTR_PREFIX,
@@ -294,9 +270,6 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type)
if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode))
return NULL;
- if (!realinode->i_op->get_acl)
- return NULL;
-
old_cred = ovl_override_creds(inode->i_sb);
acl = get_acl(realinode, type);
revert_creds(old_cred);
@@ -375,7 +348,7 @@ static const struct inode_operations ovl_file_inode_operations = {
static const struct inode_operations ovl_symlink_inode_operations = {
.setattr = ovl_setattr,
.get_link = ovl_get_link,
- .readlink = ovl_readlink,
+ .readlink = generic_readlink,
.getattr = ovl_getattr,
.listxattr = ovl_listxattr,
.update_time = ovl_update_time,
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 7e3f012..edd46a0 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -273,12 +273,11 @@ static bool ovl_is_opaquedir(struct dentry *dentry)
{
int res;
char val;
- struct inode *inode = dentry->d_inode;
- if (!S_ISDIR(inode->i_mode) || !(inode->i_opflags & IOP_XATTR))
+ if (!d_is_dir(dentry))
return false;
- res = __vfs_getxattr(dentry, inode, OVL_XATTR_OPAQUE, &val, 1);
+ res = vfs_getxattr(dentry, OVL_XATTR_OPAQUE, &val, 1);
if (res == 1 && val == 'y')
return true;
@@ -419,16 +418,12 @@ static bool ovl_dentry_weird(struct dentry *dentry)
DCACHE_OP_COMPARE);
}
-static inline struct dentry *ovl_lookup_real(struct super_block *ovl_sb,
- struct dentry *dir,
+static inline struct dentry *ovl_lookup_real(struct dentry *dir,
const struct qstr *name)
{
- const struct cred *old_cred;
struct dentry *dentry;
- old_cred = ovl_override_creds(ovl_sb);
dentry = lookup_one_len_unlocked(name->name, dir, name->len);
- revert_creds(old_cred);
if (IS_ERR(dentry)) {
if (PTR_ERR(dentry) == -ENOENT)
@@ -469,6 +464,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
struct ovl_entry *oe;
+ const struct cred *old_cred;
struct ovl_entry *poe = dentry->d_parent->d_fsdata;
struct path *stack = NULL;
struct dentry *upperdir, *upperdentry = NULL;
@@ -479,9 +475,10 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
unsigned int i;
int err;
+ old_cred = ovl_override_creds(dentry->d_sb);
upperdir = ovl_upperdentry_dereference(poe);
if (upperdir) {
- this = ovl_lookup_real(dentry->d_sb, upperdir, &dentry->d_name);
+ this = ovl_lookup_real(upperdir, &dentry->d_name);
err = PTR_ERR(this);
if (IS_ERR(this))
goto out;
@@ -514,8 +511,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
bool opaque = false;
struct path lowerpath = poe->lowerstack[i];
- this = ovl_lookup_real(dentry->d_sb,
- lowerpath.dentry, &dentry->d_name);
+ this = ovl_lookup_real(lowerpath.dentry, &dentry->d_name);
err = PTR_ERR(this);
if (IS_ERR(this)) {
/*
@@ -588,6 +584,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
ovl_copyattr(realdentry->d_inode, inode);
}
+ revert_creds(old_cred);
oe->opaque = upperopaque;
oe->__upperdentry = upperdentry;
memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr);
@@ -606,6 +603,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
out_put_upper:
dput(upperdentry);
out:
+ revert_creds(old_cred);
return ERR_PTR(err);
}
@@ -834,6 +832,19 @@ static struct dentry *ovl_workdir_create(struct vfsmount *mnt,
if (err)
goto out_dput;
+ /*
+ * Try to remove POSIX ACL xattrs from workdir. We are good if:
+ *
+ * a) success (there was a POSIX ACL xattr and was removed)
+ * b) -ENODATA (there was no POSIX ACL xattr)
+ * c) -EOPNOTSUPP (POSIX ACL xattrs are not supported)
+ *
+ * There are various other error values that could effectively
+ * mean that the xattr doesn't exist (e.g. -ERANGE is returned
+ * if the xattr name is too long), but the set of filesystems
+ * allowed as upper are limited to "normal" ones, where checking
+ * for the above two errors is sufficient.
+ */
err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_DEFAULT);
if (err && err != -ENODATA && err != -EOPNOTSUPP)
goto out_dput;
@@ -1026,6 +1037,21 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
posix_acl_release(acl);
+ /*
+ * Check if sgid bit needs to be cleared (actual setacl operation will
+ * be done with mounter's capabilities and so that won't do it for us).
+ */
+ if (unlikely(inode->i_mode & S_ISGID) &&
+ handler->flags == ACL_TYPE_ACCESS &&
+ !in_group_p(inode->i_gid) &&
+ !capable_wrt_inode_uidgid(inode, CAP_FSETID)) {
+ struct iattr iattr = { .ia_valid = ATTR_KILL_SGID };
+
+ err = ovl_setattr(dentry, &iattr);
+ if (err)
+ return err;
+ }
+
err = ovl_xattr_set(dentry, handler->name, value, size, flags);
if (!err)
ovl_copyattr(ovl_inode_real(inode, NULL), inode);
@@ -1292,6 +1318,12 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
if (!oe)
goto out_put_cred;
+ sb->s_magic = OVERLAYFS_SUPER_MAGIC;
+ sb->s_op = &ovl_super_operations;
+ sb->s_xattr = ovl_xattr_handlers;
+ sb->s_fs_info = ufs;
+ sb->s_flags |= MS_POSIXACL | MS_NOREMOTELOCK;
+
root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR));
if (!root_dentry)
goto out_free_oe;
@@ -1315,12 +1347,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
ovl_inode_init(d_inode(root_dentry), realinode, !!upperpath.dentry);
ovl_copyattr(realinode, d_inode(root_dentry));
- sb->s_magic = OVERLAYFS_SUPER_MAGIC;
- sb->s_op = &ovl_super_operations;
- sb->s_xattr = ovl_xattr_handlers;
sb->s_root = root_dentry;
- sb->s_fs_info = ufs;
- sb->s_flags |= MS_POSIXACL | MS_NOREMOTELOCK;
return 0;
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 89600fd..81818ad 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -412,10 +412,11 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
mm = get_task_mm(task);
if (mm) {
vsize = task_vsize(mm);
- if (permitted) {
- eip = KSTK_EIP(task);
- esp = KSTK_ESP(task);
- }
+ /*
+ * esp and eip are intentionally zeroed out. There is no
+ * non-racy way to read them without freezing the task.
+ * Programs that need reliable values can use ptrace(2).
+ */
}
get_task_comm(tcomm, task);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index c2964d8..ca651ac 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -832,6 +832,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
unsigned long addr = *ppos;
ssize_t copied;
char *page;
+ unsigned int flags;
if (!mm)
return 0;
@@ -844,6 +845,11 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
if (!atomic_inc_not_zero(&mm->mm_users))
goto free;
+ /* Maybe we should limit FOLL_FORCE to actual ptrace users? */
+ flags = FOLL_FORCE;
+ if (write)
+ flags |= FOLL_WRITE;
+
while (count > 0) {
int this_len = min_t(int, count, PAGE_SIZE);
@@ -852,7 +858,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
break;
}
- this_len = access_remote_vm(mm, addr, page, this_len, write);
+ this_len = access_remote_vm(mm, addr, page, this_len, flags);
if (!this_len) {
if (!copied)
copied = -EIO;
@@ -964,8 +970,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
max_len = min_t(size_t, PAGE_SIZE, count);
this_len = min(max_len, this_len);
- retval = access_remote_vm(mm, (env_start + src),
- page, this_len, 0);
+ retval = access_remote_vm(mm, (env_start + src), page, this_len, 0);
if (retval <= 0) {
ret = retval;
@@ -1007,6 +1012,9 @@ static ssize_t auxv_read(struct file *file, char __user *buf,
{
struct mm_struct *mm = file->private_data;
unsigned int nwords = 0;
+
+ if (!mm)
+ return 0;
do {
nwords += 2;
} while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 6909582..35b92d8 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -266,24 +266,15 @@ static int do_maps_open(struct inode *inode, struct file *file,
* /proc/PID/maps that is the stack of the main task.
*/
static int is_stack(struct proc_maps_private *priv,
- struct vm_area_struct *vma, int is_pid)
+ struct vm_area_struct *vma)
{
- int stack = 0;
-
- if (is_pid) {
- stack = vma->vm_start <= vma->vm_mm->start_stack &&
- vma->vm_end >= vma->vm_mm->start_stack;
- } else {
- struct inode *inode = priv->inode;
- struct task_struct *task;
-
- rcu_read_lock();
- task = pid_task(proc_pid(inode), PIDTYPE_PID);
- if (task)
- stack = vma_is_stack_for_task(vma, task);
- rcu_read_unlock();
- }
- return stack;
+ /*
+ * We make no effort to guess what a given thread considers to be
+ * its "stack". It's not even well-defined for programs written
+ * languages like Go.
+ */
+ return vma->vm_start <= vma->vm_mm->start_stack &&
+ vma->vm_end >= vma->vm_mm->start_stack;
}
static void
@@ -354,7 +345,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
goto done;
}
- if (is_stack(priv, vma, is_pid))
+ if (is_stack(priv, vma))
name = "[stack]";
}
@@ -1669,7 +1660,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
seq_file_path(m, file, "\n\t= ");
} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
seq_puts(m, " heap");
- } else if (is_stack(proc_priv, vma, is_pid)) {
+ } else if (is_stack(proc_priv, vma)) {
seq_puts(m, " stack");
}
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index faacb0c..3717562 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -124,25 +124,17 @@ unsigned long task_statm(struct mm_struct *mm,
}
static int is_stack(struct proc_maps_private *priv,
- struct vm_area_struct *vma, int is_pid)
+ struct vm_area_struct *vma)
{
struct mm_struct *mm = vma->vm_mm;
- int stack = 0;
- if (is_pid) {
- stack = vma->vm_start <= mm->start_stack &&
- vma->vm_end >= mm->start_stack;
- } else {
- struct inode *inode = priv->inode;
- struct task_struct *task;
-
- rcu_read_lock();
- task = pid_task(proc_pid(inode), PIDTYPE_PID);
- if (task)
- stack = vma_is_stack_for_task(vma, task);
- rcu_read_unlock();
- }
- return stack;
+ /*
+ * We make no effort to guess what a given thread considers to be
+ * its "stack". It's not even well-defined for programs written
+ * languages like Go.
+ */
+ return vma->vm_start <= mm->start_stack &&
+ vma->vm_end >= mm->start_stack;
}
/*
@@ -184,7 +176,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
if (file) {
seq_pad(m, ' ');
seq_file_path(m, file, "");
- } else if (mm && is_stack(priv, vma, is_pid)) {
+ } else if (mm && is_stack(priv, vma)) {
seq_pad(m, ' ');
seq_printf(m, "[stack]");
}
diff --git a/fs/read_write.c b/fs/read_write.c
index 66215a7..190e0d36 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -730,6 +730,35 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
/* A write operation does a read from user space and vice versa */
#define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ)
+/**
+ * rw_copy_check_uvector() - Copy an array of &struct iovec from userspace
+ * into the kernel and check that it is valid.
+ *
+ * @type: One of %CHECK_IOVEC_ONLY, %READ, or %WRITE.
+ * @uvector: Pointer to the userspace array.
+ * @nr_segs: Number of elements in userspace array.
+ * @fast_segs: Number of elements in @fast_pointer.
+ * @fast_pointer: Pointer to (usually small on-stack) kernel array.
+ * @ret_pointer: (output parameter) Pointer to a variable that will point to
+ * either @fast_pointer, a newly allocated kernel array, or NULL,
+ * depending on which array was used.
+ *
+ * This function copies an array of &struct iovec of @nr_segs from
+ * userspace into the kernel and checks that each element is valid (e.g.
+ * it does not point to a kernel address or cause overflow by being too
+ * large, etc.).
+ *
+ * As an optimization, the caller may provide a pointer to a small
+ * on-stack array in @fast_pointer, typically %UIO_FASTIOV elements long
+ * (the size of this array, or 0 if unused, should be given in @fast_segs).
+ *
+ * @ret_pointer will always point to the array that was used, so the
+ * caller must take care not to call kfree() on it e.g. in case the
+ * @fast_pointer array was used and it was allocated on the stack.
+ *
+ * Return: The total number of bytes covered by the iovec array on success
+ * or a negative error code on error.
+ */
ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
unsigned long nr_segs, unsigned long fast_segs,
struct iovec *fast_pointer,
diff --git a/fs/splice.c b/fs/splice.c
index 153d4f3..dcaf185 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -299,13 +299,8 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
{
struct iov_iter to;
struct kiocb kiocb;
- loff_t isize;
int idx, ret;
- isize = i_size_read(in->f_mapping->host);
- if (unlikely(*ppos >= isize))
- return 0;
-
iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len);
idx = to.idx;
init_sync_kiocb(&kiocb, in);
diff --git a/fs/super.c b/fs/super.c
index c2ff475..c183835 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1269,25 +1269,34 @@ EXPORT_SYMBOL(__sb_start_write);
static void sb_wait_write(struct super_block *sb, int level)
{
percpu_down_write(sb->s_writers.rw_sem + level-1);
- /*
- * We are going to return to userspace and forget about this lock, the
- * ownership goes to the caller of thaw_super() which does unlock.
- *
- * FIXME: we should do this before return from freeze_super() after we
- * called sync_filesystem(sb) and s_op->freeze_fs(sb), and thaw_super()
- * should re-acquire these locks before s_op->unfreeze_fs(sb). However
- * this leads to lockdep false-positives, so currently we do the early
- * release right after acquire.
- */
- percpu_rwsem_release(sb->s_writers.rw_sem + level-1, 0, _THIS_IP_);
}
-static void sb_freeze_unlock(struct super_block *sb)
+/*
+ * We are going to return to userspace and forget about these locks, the
+ * ownership goes to the caller of thaw_super() which does unlock().
+ */
+static void lockdep_sb_freeze_release(struct super_block *sb)
+{
+ int level;
+
+ for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--)
+ percpu_rwsem_release(sb->s_writers.rw_sem + level, 0, _THIS_IP_);
+}
+
+/*
+ * Tell lockdep we are holding these locks before we call ->unfreeze_fs(sb).
+ */
+static void lockdep_sb_freeze_acquire(struct super_block *sb)
{
int level;
for (level = 0; level < SB_FREEZE_LEVELS; ++level)
percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_);
+}
+
+static void sb_freeze_unlock(struct super_block *sb)
+{
+ int level;
for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--)
percpu_up_write(sb->s_writers.rw_sem + level);
@@ -1379,10 +1388,11 @@ int freeze_super(struct super_block *sb)
}
}
/*
- * This is just for debugging purposes so that fs can warn if it
- * sees write activity when frozen is set to SB_FREEZE_COMPLETE.
+ * For debugging purposes so that fs can warn if it sees write activity
+ * when frozen is set to SB_FREEZE_COMPLETE, and for thaw_super().
*/
sb->s_writers.frozen = SB_FREEZE_COMPLETE;
+ lockdep_sb_freeze_release(sb);
up_write(&sb->s_umount);
return 0;
}
@@ -1399,7 +1409,7 @@ int thaw_super(struct super_block *sb)
int error;
down_write(&sb->s_umount);
- if (sb->s_writers.frozen == SB_UNFROZEN) {
+ if (sb->s_writers.frozen != SB_FREEZE_COMPLETE) {
up_write(&sb->s_umount);
return -EINVAL;
}
@@ -1409,11 +1419,14 @@ int thaw_super(struct super_block *sb)
goto out;
}
+ lockdep_sb_freeze_acquire(sb);
+
if (sb->s_op->unfreeze_fs) {
error = sb->s_op->unfreeze_fs(sb);
if (error) {
printk(KERN_ERR
"VFS:Filesystem thaw failed\n");
+ lockdep_sb_freeze_release(sb);
up_write(&sb->s_umount);
return error;
}
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 94374e4..2b67bda 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -21,14 +21,14 @@ DEFINE_SPINLOCK(sysfs_symlink_target_lock);
void sysfs_warn_dup(struct kernfs_node *parent, const char *name)
{
- char *buf, *path = NULL;
+ char *buf;
buf = kzalloc(PATH_MAX, GFP_KERNEL);
if (buf)
- path = kernfs_path(parent, buf, PATH_MAX);
+ kernfs_path(parent, buf, PATH_MAX);
WARN(1, KERN_WARNING "sysfs: cannot create duplicate filename '%s/%s'\n",
- path, name);
+ buf, name);
kfree(buf);
}
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index c8f60df..ca16c5d 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -439,7 +439,7 @@ static unsigned int vfs_dent_type(uint8_t type)
*/
static int ubifs_readdir(struct file *file, struct dir_context *ctx)
{
- int err;
+ int err = 0;
struct qstr nm;
union ubifs_key key;
struct ubifs_dent_node *dent;
@@ -541,14 +541,20 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx)
kfree(file->private_data);
file->private_data = NULL;
- if (err != -ENOENT) {
+ if (err != -ENOENT)
ubifs_err(c, "cannot find next direntry, error %d", err);
- return err;
- }
+ else
+ /*
+ * -ENOENT is a non-fatal error in this context, the TNC uses
+ * it to indicate that the cursor moved past the current directory
+ * and readdir() has to stop.
+ */
+ err = 0;
+
/* 2 is a special value indicating that there are no more direntries */
ctx->pos = 2;
- return 0;
+ return err;
}
/* Free saved readdir() state when the directory is closed */
@@ -1060,9 +1066,9 @@ static void unlock_4_inodes(struct inode *inode1, struct inode *inode2,
mutex_unlock(&ubifs_inode(inode1)->ui_mutex);
}
-static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry,
- unsigned int flags)
+static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags)
{
struct ubifs_info *c = old_dir->i_sb->s_fs_info;
struct inode *old_inode = d_inode(old_dentry);
@@ -1323,7 +1329,7 @@ static int ubifs_xrename(struct inode *old_dir, struct dentry *old_dentry,
return err;
}
-static int ubifs_rename2(struct inode *old_dir, struct dentry *old_dentry,
+static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
@@ -1336,7 +1342,7 @@ static int ubifs_rename2(struct inode *old_dir, struct dentry *old_dentry,
if (flags & RENAME_EXCHANGE)
return ubifs_xrename(old_dir, old_dentry, new_dir, new_dentry);
- return ubifs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
+ return do_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
}
int ubifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
@@ -1387,7 +1393,7 @@ const struct inode_operations ubifs_dir_inode_operations = {
.mkdir = ubifs_mkdir,
.rmdir = ubifs_rmdir,
.mknod = ubifs_mknod,
- .rename = ubifs_rename2,
+ .rename = ubifs_rename,
.setattr = ubifs_setattr,
.getattr = ubifs_getattr,
.listxattr = ubifs_listxattr,
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index 6c2f4d4..d9f9615 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -172,6 +172,7 @@ static int create_xattr(struct ubifs_info *c, struct inode *host,
host_ui->xattr_cnt -= 1;
host_ui->xattr_size -= CALC_DENT_SIZE(nm->len);
host_ui->xattr_size -= CALC_XATTR_BYTES(size);
+ host_ui->xattr_names -= nm->len;
mutex_unlock(&host_ui->ui_mutex);
out_free:
make_bad_inode(inode);
@@ -478,6 +479,7 @@ static int remove_xattr(struct ubifs_info *c, struct inode *host,
host_ui->xattr_cnt += 1;
host_ui->xattr_size += CALC_DENT_SIZE(nm->len);
host_ui->xattr_size += CALC_XATTR_BYTES(ui->data_len);
+ host_ui->xattr_names += nm->len;
mutex_unlock(&host_ui->ui_mutex);
ubifs_release_budget(c, &req);
make_bad_inode(inode);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index c27344c..c6eb219 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3974,9 +3974,6 @@ xfs_bmap_remap_alloc(
* allocating, so skip that check by pretending to be freeing.
*/
error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING);
- if (error)
- goto error0;
-error0:
xfs_perag_put(args.pag);
if (error)
trace_xfs_bmap_remap_alloc_error(ap->ip, error, _RET_IP_);
@@ -3999,6 +3996,39 @@ xfs_bmap_alloc(
return xfs_bmap_btalloc(ap);
}
+/* Trim extent to fit a logical block range. */
+void
+xfs_trim_extent(
+ struct xfs_bmbt_irec *irec,
+ xfs_fileoff_t bno,
+ xfs_filblks_t len)
+{
+ xfs_fileoff_t distance;
+ xfs_fileoff_t end = bno + len;
+
+ if (irec->br_startoff + irec->br_blockcount <= bno ||
+ irec->br_startoff >= end) {
+ irec->br_blockcount = 0;
+ return;
+ }
+
+ if (irec->br_startoff < bno) {
+ distance = bno - irec->br_startoff;
+ if (isnullstartblock(irec->br_startblock))
+ irec->br_startblock = DELAYSTARTBLOCK;
+ if (irec->br_startblock != DELAYSTARTBLOCK &&
+ irec->br_startblock != HOLESTARTBLOCK)
+ irec->br_startblock += distance;
+ irec->br_startoff += distance;
+ irec->br_blockcount -= distance;
+ }
+
+ if (end < irec->br_startoff + irec->br_blockcount) {
+ distance = irec->br_startoff + irec->br_blockcount - end;
+ irec->br_blockcount -= distance;
+ }
+}
+
/*
* Trim the returned map to the required bounds
*/
@@ -4829,6 +4859,219 @@ xfs_bmap_split_indlen(
return stolen;
}
+int
+xfs_bmap_del_extent_delay(
+ struct xfs_inode *ip,
+ int whichfork,
+ xfs_extnum_t *idx,
+ struct xfs_bmbt_irec *got,
+ struct xfs_bmbt_irec *del)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_bmbt_irec new;
+ int64_t da_old, da_new, da_diff = 0;
+ xfs_fileoff_t del_endoff, got_endoff;
+ xfs_filblks_t got_indlen, new_indlen, stolen;
+ int error = 0, state = 0;
+ bool isrt;
+
+ XFS_STATS_INC(mp, xs_del_exlist);
+
+ isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip);
+ del_endoff = del->br_startoff + del->br_blockcount;
+ got_endoff = got->br_startoff + got->br_blockcount;
+ da_old = startblockval(got->br_startblock);
+ da_new = 0;
+
+ ASSERT(*idx >= 0);
+ ASSERT(*idx < ifp->if_bytes / sizeof(struct xfs_bmbt_rec));
+ ASSERT(del->br_blockcount > 0);
+ ASSERT(got->br_startoff <= del->br_startoff);
+ ASSERT(got_endoff >= del_endoff);
+
+ if (isrt) {
+ int64_t rtexts = XFS_FSB_TO_B(mp, del->br_blockcount);
+
+ do_div(rtexts, mp->m_sb.sb_rextsize);
+ xfs_mod_frextents(mp, rtexts);
+ }
+
+ /*
+ * Update the inode delalloc counter now and wait to update the
+ * sb counters as we might have to borrow some blocks for the
+ * indirect block accounting.
+ */
+ xfs_trans_reserve_quota_nblks(NULL, ip, -((long)del->br_blockcount), 0,
+ isrt ? XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS);
+ ip->i_delayed_blks -= del->br_blockcount;
+
+ if (whichfork == XFS_COW_FORK)
+ state |= BMAP_COWFORK;
+
+ if (got->br_startoff == del->br_startoff)
+ state |= BMAP_LEFT_CONTIG;
+ if (got_endoff == del_endoff)
+ state |= BMAP_RIGHT_CONTIG;
+
+ switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) {
+ case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:
+ /*
+ * Matches the whole extent. Delete the entry.
+ */
+ xfs_iext_remove(ip, *idx, 1, state);
+ --*idx;
+ break;
+ case BMAP_LEFT_CONTIG:
+ /*
+ * Deleting the first part of the extent.
+ */
+ trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+ got->br_startoff = del_endoff;
+ got->br_blockcount -= del->br_blockcount;
+ da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip,
+ got->br_blockcount), da_old);
+ got->br_startblock = nullstartblock((int)da_new);
+ xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+ trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+ break;
+ case BMAP_RIGHT_CONTIG:
+ /*
+ * Deleting the last part of the extent.
+ */
+ trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+ got->br_blockcount = got->br_blockcount - del->br_blockcount;
+ da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip,
+ got->br_blockcount), da_old);
+ got->br_startblock = nullstartblock((int)da_new);
+ xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+ trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+ break;
+ case 0:
+ /*
+ * Deleting the middle of the extent.
+ *
+ * Distribute the original indlen reservation across the two new
+ * extents. Steal blocks from the deleted extent if necessary.
+ * Stealing blocks simply fudges the fdblocks accounting below.
+ * Warn if either of the new indlen reservations is zero as this
+ * can lead to delalloc problems.
+ */
+ trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+
+ got->br_blockcount = del->br_startoff - got->br_startoff;
+ got_indlen = xfs_bmap_worst_indlen(ip, got->br_blockcount);
+
+ new.br_blockcount = got_endoff - del_endoff;
+ new_indlen = xfs_bmap_worst_indlen(ip, new.br_blockcount);
+
+ WARN_ON_ONCE(!got_indlen || !new_indlen);
+ stolen = xfs_bmap_split_indlen(da_old, &got_indlen, &new_indlen,
+ del->br_blockcount);
+
+ got->br_startblock = nullstartblock((int)got_indlen);
+ xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+ trace_xfs_bmap_post_update(ip, *idx, 0, _THIS_IP_);
+
+ new.br_startoff = del_endoff;
+ new.br_state = got->br_state;
+ new.br_startblock = nullstartblock((int)new_indlen);
+
+ ++*idx;
+ xfs_iext_insert(ip, *idx, 1, &new, state);
+
+ da_new = got_indlen + new_indlen - stolen;
+ del->br_blockcount -= stolen;
+ break;
+ }
+
+ ASSERT(da_old >= da_new);
+ da_diff = da_old - da_new;
+ if (!isrt)
+ da_diff += del->br_blockcount;
+ if (da_diff)
+ xfs_mod_fdblocks(mp, da_diff, false);
+ return error;
+}
+
+void
+xfs_bmap_del_extent_cow(
+ struct xfs_inode *ip,
+ xfs_extnum_t *idx,
+ struct xfs_bmbt_irec *got,
+ struct xfs_bmbt_irec *del)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+ struct xfs_bmbt_irec new;
+ xfs_fileoff_t del_endoff, got_endoff;
+ int state = BMAP_COWFORK;
+
+ XFS_STATS_INC(mp, xs_del_exlist);
+
+ del_endoff = del->br_startoff + del->br_blockcount;
+ got_endoff = got->br_startoff + got->br_blockcount;
+
+ ASSERT(*idx >= 0);
+ ASSERT(*idx < ifp->if_bytes / sizeof(struct xfs_bmbt_rec));
+ ASSERT(del->br_blockcount > 0);
+ ASSERT(got->br_startoff <= del->br_startoff);
+ ASSERT(got_endoff >= del_endoff);
+ ASSERT(!isnullstartblock(got->br_startblock));
+
+ if (got->br_startoff == del->br_startoff)
+ state |= BMAP_LEFT_CONTIG;
+ if (got_endoff == del_endoff)
+ state |= BMAP_RIGHT_CONTIG;
+
+ switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) {
+ case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:
+ /*
+ * Matches the whole extent. Delete the entry.
+ */
+ xfs_iext_remove(ip, *idx, 1, state);
+ --*idx;
+ break;
+ case BMAP_LEFT_CONTIG:
+ /*
+ * Deleting the first part of the extent.
+ */
+ trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+ got->br_startoff = del_endoff;
+ got->br_blockcount -= del->br_blockcount;
+ got->br_startblock = del->br_startblock + del->br_blockcount;
+ xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+ trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+ break;
+ case BMAP_RIGHT_CONTIG:
+ /*
+ * Deleting the last part of the extent.
+ */
+ trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+ got->br_blockcount -= del->br_blockcount;
+ xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+ trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+ break;
+ case 0:
+ /*
+ * Deleting the middle of the extent.
+ */
+ trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+ got->br_blockcount = del->br_startoff - got->br_startoff;
+ xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+ trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+
+ new.br_startoff = del_endoff;
+ new.br_blockcount = got_endoff - del_endoff;
+ new.br_state = got->br_state;
+ new.br_startblock = del->br_startblock + del->br_blockcount;
+
+ ++*idx;
+ xfs_iext_insert(ip, *idx, 1, &new, state);
+ break;
+ }
+}
+
/*
* Called by xfs_bmapi to update file extent records and the btree
* after removing space (or undoing a delayed allocation).
@@ -5171,175 +5414,6 @@ xfs_bmap_del_extent(
return error;
}
-/* Remove an extent from the CoW fork. Similar to xfs_bmap_del_extent. */
-int
-xfs_bunmapi_cow(
- struct xfs_inode *ip,
- struct xfs_bmbt_irec *del)
-{
- xfs_filblks_t da_new;
- xfs_filblks_t da_old;
- xfs_fsblock_t del_endblock = 0;
- xfs_fileoff_t del_endoff;
- int delay;
- struct xfs_bmbt_rec_host *ep;
- int error;
- struct xfs_bmbt_irec got;
- xfs_fileoff_t got_endoff;
- struct xfs_ifork *ifp;
- struct xfs_mount *mp;
- xfs_filblks_t nblks;
- struct xfs_bmbt_irec new;
- /* REFERENCED */
- uint qfield;
- xfs_filblks_t temp;
- xfs_filblks_t temp2;
- int state = BMAP_COWFORK;
- int eof;
- xfs_extnum_t eidx;
-
- mp = ip->i_mount;
- XFS_STATS_INC(mp, xs_del_exlist);
-
- ep = xfs_bmap_search_extents(ip, del->br_startoff, XFS_COW_FORK, &eof,
- &eidx, &got, &new);
-
- ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); ifp = ifp;
- ASSERT((eidx >= 0) && (eidx < ifp->if_bytes /
- (uint)sizeof(xfs_bmbt_rec_t)));
- ASSERT(del->br_blockcount > 0);
- ASSERT(got.br_startoff <= del->br_startoff);
- del_endoff = del->br_startoff + del->br_blockcount;
- got_endoff = got.br_startoff + got.br_blockcount;
- ASSERT(got_endoff >= del_endoff);
- delay = isnullstartblock(got.br_startblock);
- ASSERT(isnullstartblock(del->br_startblock) == delay);
- qfield = 0;
- error = 0;
- /*
- * If deleting a real allocation, must free up the disk space.
- */
- if (!delay) {
- nblks = del->br_blockcount;
- qfield = XFS_TRANS_DQ_BCOUNT;
- /*
- * Set up del_endblock and cur for later.
- */
- del_endblock = del->br_startblock + del->br_blockcount;
- da_old = da_new = 0;
- } else {
- da_old = startblockval(got.br_startblock);
- da_new = 0;
- nblks = 0;
- }
- qfield = qfield;
- nblks = nblks;
-
- /*
- * Set flag value to use in switch statement.
- * Left-contig is 2, right-contig is 1.
- */
- switch (((got.br_startoff == del->br_startoff) << 1) |
- (got_endoff == del_endoff)) {
- case 3:
- /*
- * Matches the whole extent. Delete the entry.
- */
- xfs_iext_remove(ip, eidx, 1, BMAP_COWFORK);
- --eidx;
- break;
-
- case 2:
- /*
- * Deleting the first part of the extent.
- */
- trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
- xfs_bmbt_set_startoff(ep, del_endoff);
- temp = got.br_blockcount - del->br_blockcount;
- xfs_bmbt_set_blockcount(ep, temp);
- if (delay) {
- temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
- da_old);
- xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
- trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
- da_new = temp;
- break;
- }
- xfs_bmbt_set_startblock(ep, del_endblock);
- trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
- break;
-
- case 1:
- /*
- * Deleting the last part of the extent.
- */
- temp = got.br_blockcount - del->br_blockcount;
- trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
- xfs_bmbt_set_blockcount(ep, temp);
- if (delay) {
- temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
- da_old);
- xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
- trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
- da_new = temp;
- break;
- }
- trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
- break;
-
- case 0:
- /*
- * Deleting the middle of the extent.
- */
- temp = del->br_startoff - got.br_startoff;
- trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
- xfs_bmbt_set_blockcount(ep, temp);
- new.br_startoff = del_endoff;
- temp2 = got_endoff - del_endoff;
- new.br_blockcount = temp2;
- new.br_state = got.br_state;
- if (!delay) {
- new.br_startblock = del_endblock;
- } else {
- temp = xfs_bmap_worst_indlen(ip, temp);
- xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
- temp2 = xfs_bmap_worst_indlen(ip, temp2);
- new.br_startblock = nullstartblock((int)temp2);
- da_new = temp + temp2;
- while (da_new > da_old) {
- if (temp) {
- temp--;
- da_new--;
- xfs_bmbt_set_startblock(ep,
- nullstartblock((int)temp));
- }
- if (da_new == da_old)
- break;
- if (temp2) {
- temp2--;
- da_new--;
- new.br_startblock =
- nullstartblock((int)temp2);
- }
- }
- }
- trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
- xfs_iext_insert(ip, eidx + 1, 1, &new, state);
- ++eidx;
- break;
- }
-
- /*
- * Account for change in delayed indirect blocks.
- * Nothing to do for disk quota accounting here.
- */
- ASSERT(da_old >= da_new);
- if (da_old > da_new)
- xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new), false);
-
- return error;
-}
-
/*
* Unmap (remove) blocks from a file.
* If nexts is nonzero then the number of extents to remove is limited to
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index f97db71..7cae6ec 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -190,6 +190,8 @@ void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt,
#define XFS_BMAP_TRACE_EXLIST(ip,c,w)
#endif
+void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
+ xfs_filblks_t len);
int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
void xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
@@ -221,7 +223,11 @@ int xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t bno, xfs_filblks_t len, int flags,
xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
struct xfs_defer_ops *dfops, int *done);
-int xfs_bunmapi_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *del);
+int xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
+ xfs_extnum_t *idx, struct xfs_bmbt_irec *got,
+ struct xfs_bmbt_irec *del);
+void xfs_bmap_del_extent_cow(struct xfs_inode *ip, xfs_extnum_t *idx,
+ struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *del);
int xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx,
xfs_extnum_t num);
uint xfs_default_attroffset(struct xfs_inode *ip);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 5c8e6f2..0e80993 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -4826,7 +4826,7 @@ xfs_btree_calc_size(
return rval;
}
-int
+static int
xfs_btree_count_blocks_helper(
struct xfs_btree_cur *cur,
int level,
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 613c5cf1..5c2929f 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -199,9 +199,9 @@ xfs_defer_intake_work(
struct xfs_defer_pending *dfp;
list_for_each_entry(dfp, &dop->dop_intake, dfp_list) {
- trace_xfs_defer_intake_work(tp->t_mountp, dfp);
dfp->dfp_intent = dfp->dfp_type->create_intent(tp,
dfp->dfp_count);
+ trace_xfs_defer_intake_work(tp->t_mountp, dfp);
list_sort(tp->t_mountp, &dfp->dfp_work,
dfp->dfp_type->diff_items);
list_for_each(li, &dfp->dfp_work)
@@ -221,21 +221,14 @@ xfs_defer_trans_abort(
struct xfs_defer_pending *dfp;
trace_xfs_defer_trans_abort(tp->t_mountp, dop);
- /*
- * If the transaction was committed, drop the intent reference
- * since we're bailing out of here. The other reference is
- * dropped when the intent hits the AIL. If the transaction
- * was not committed, the intent is freed by the intent item
- * unlock handler on abort.
- */
- if (!dop->dop_committed)
- return;
- /* Abort intent items. */
+ /* Abort intent items that don't have a done item. */
list_for_each_entry(dfp, &dop->dop_pending, dfp_list) {
trace_xfs_defer_pending_abort(tp->t_mountp, dfp);
- if (!dfp->dfp_done)
+ if (dfp->dfp_intent && !dfp->dfp_done) {
dfp->dfp_type->abort_intent(dfp->dfp_intent);
+ dfp->dfp_intent = NULL;
+ }
}
/* Shut down FS. */
diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index 3cc3cf7..ac9a003 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -191,8 +191,7 @@ xfs_dquot_buf_verify_crc(
if (mp->m_quotainfo)
ndquots = mp->m_quotainfo->qi_dqperchunk;
else
- ndquots = xfs_calc_dquots_per_chunk(
- XFS_BB_TO_FSB(mp, bp->b_length));
+ ndquots = xfs_calc_dquots_per_chunk(bp->b_length);
for (i = 0; i < ndquots; i++, d++) {
if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk),
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index f6547fc..6b7579e 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -865,7 +865,6 @@ typedef struct xfs_timestamp {
* padding field for v3 inodes.
*/
#define XFS_DINODE_MAGIC 0x494e /* 'IN' */
-#define XFS_DINODE_GOOD_VERSION(v) ((v) >= 1 && (v) <= 3)
typedef struct xfs_dinode {
__be16 di_magic; /* inode magic # = XFS_DINODE_MAGIC */
__be16 di_mode; /* mode and type of file */
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 8de9a3a..134424f 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -57,6 +57,17 @@ xfs_inobp_check(
}
#endif
+bool
+xfs_dinode_good_version(
+ struct xfs_mount *mp,
+ __u8 version)
+{
+ if (xfs_sb_version_hascrc(&mp->m_sb))
+ return version == 3;
+
+ return version == 1 || version == 2;
+}
+
/*
* If we are doing readahead on an inode buffer, we might be in log recovery
* reading an inode allocation buffer that hasn't yet been replayed, and hence
@@ -91,7 +102,7 @@ xfs_inode_buf_verify(
dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog));
di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
- XFS_DINODE_GOOD_VERSION(dip->di_version);
+ xfs_dinode_good_version(mp, dip->di_version);
if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
XFS_ERRTAG_ITOBP_INOTOBP,
XFS_RANDOM_ITOBP_INOTOBP))) {
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index 62d9d46..3cfe12a 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -74,6 +74,8 @@ void xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from);
void xfs_log_dinode_to_disk(struct xfs_log_dinode *from,
struct xfs_dinode *to);
+bool xfs_dinode_good_version(struct xfs_mount *mp, __u8 version);
+
#if defined(DEBUG)
void xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
#else
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a314fc7..6e4f7f9 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -249,6 +249,7 @@ xfs_file_dio_aio_read(
struct xfs_inode *ip = XFS_I(inode);
loff_t isize = i_size_read(inode);
size_t count = iov_iter_count(to);
+ loff_t end = iocb->ki_pos + count - 1;
struct iov_iter data;
struct xfs_buftarg *target;
ssize_t ret = 0;
@@ -272,49 +273,21 @@ xfs_file_dio_aio_read(
file_accessed(iocb->ki_filp);
- /*
- * Locking is a bit tricky here. If we take an exclusive lock for direct
- * IO, we effectively serialise all new concurrent read IO to this file
- * and block it behind IO that is currently in progress because IO in
- * progress holds the IO lock shared. We only need to hold the lock
- * exclusive to blow away the page cache, so only take lock exclusively
- * if the page cache needs invalidation. This allows the normal direct
- * IO case of no page cache pages to proceeed concurrently without
- * serialisation.
- */
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
if (mapping->nrpages) {
- xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
- xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
+ ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
+ if (ret)
+ goto out_unlock;
/*
- * The generic dio code only flushes the range of the particular
- * I/O. Because we take an exclusive lock here, this whole
- * sequence is considerably more expensive for us. This has a
- * noticeable performance impact for any file with cached pages,
- * even when outside of the range of the particular I/O.
- *
- * Hence, amortize the cost of the lock against a full file
- * flush and reduce the chances of repeated iolock cycles going
- * forward.
+ * Invalidate whole pages. This can return an error if we fail
+ * to invalidate a page, but this should never happen on XFS.
+ * Warn if it does fail.
*/
- if (mapping->nrpages) {
- ret = filemap_write_and_wait(mapping);
- if (ret) {
- xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
- return ret;
- }
-
- /*
- * Invalidate whole pages. This can return an error if
- * we fail to invalidate a page, but this should never
- * happen on XFS. Warn if it does fail.
- */
- ret = invalidate_inode_pages2(mapping);
- WARN_ON_ONCE(ret);
- ret = 0;
- }
- xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
+ ret = invalidate_inode_pages2_range(mapping,
+ iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
+ WARN_ON_ONCE(ret);
+ ret = 0;
}
data = *to;
@@ -324,8 +297,9 @@ xfs_file_dio_aio_read(
iocb->ki_pos += ret;
iov_iter_advance(to, ret);
}
- xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
+out_unlock:
+ xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
@@ -570,61 +544,49 @@ xfs_file_dio_aio_write(
if ((iocb->ki_pos | count) & target->bt_logical_sectormask)
return -EINVAL;
- /* "unaligned" here means not aligned to a filesystem block */
+ /*
+ * Don't take the exclusive iolock here unless the I/O is unaligned to
+ * the file system block size. We don't need to consider the EOF
+ * extension case here because xfs_file_aio_write_checks() will relock
+ * the inode as necessary for EOF zeroing cases and fill out the new
+ * inode size as appropriate.
+ */
if ((iocb->ki_pos & mp->m_blockmask) ||
- ((iocb->ki_pos + count) & mp->m_blockmask))
+ ((iocb->ki_pos + count) & mp->m_blockmask)) {
unaligned_io = 1;
-
- /*
- * We don't need to take an exclusive lock unless there page cache needs
- * to be invalidated or unaligned IO is being executed. We don't need to
- * consider the EOF extension case here because
- * xfs_file_aio_write_checks() will relock the inode as necessary for
- * EOF zeroing cases and fill out the new inode size as appropriate.
- */
- if (unaligned_io || mapping->nrpages)
iolock = XFS_IOLOCK_EXCL;
- else
+ } else {
iolock = XFS_IOLOCK_SHARED;
- xfs_rw_ilock(ip, iolock);
-
- /*
- * Recheck if there are cached pages that need invalidate after we got
- * the iolock to protect against other threads adding new pages while
- * we were waiting for the iolock.
- */
- if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
- xfs_rw_iunlock(ip, iolock);
- iolock = XFS_IOLOCK_EXCL;
- xfs_rw_ilock(ip, iolock);
}
+ xfs_rw_ilock(ip, iolock);
+
ret = xfs_file_aio_write_checks(iocb, from, &iolock);
if (ret)
goto out;
count = iov_iter_count(from);
end = iocb->ki_pos + count - 1;
- /*
- * See xfs_file_dio_aio_read() for why we do a full-file flush here.
- */
if (mapping->nrpages) {
- ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
+ ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
if (ret)
goto out;
+
/*
* Invalidate whole pages. This can return an error if we fail
* to invalidate a page, but this should never happen on XFS.
* Warn if it does fail.
*/
- ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping);
+ ret = invalidate_inode_pages2_range(mapping,
+ iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
WARN_ON_ONCE(ret);
ret = 0;
}
/*
* If we are doing unaligned IO, wait for all other IO to drain,
- * otherwise demote the lock if we had to flush cached pages
+ * otherwise demote the lock if we had to take the exclusive lock
+ * for other reasons in xfs_file_aio_write_checks.
*/
if (unaligned_io)
inode_dio_wait(inode);
@@ -947,134 +909,6 @@ xfs_file_fallocate(
return error;
}
-/*
- * Flush all file writes out to disk.
- */
-static int
-xfs_file_wait_for_io(
- struct inode *inode,
- loff_t offset,
- size_t len)
-{
- loff_t rounding;
- loff_t ioffset;
- loff_t iendoffset;
- loff_t bs;
- int ret;
-
- bs = inode->i_sb->s_blocksize;
- inode_dio_wait(inode);
-
- rounding = max_t(xfs_off_t, bs, PAGE_SIZE);
- ioffset = round_down(offset, rounding);
- iendoffset = round_up(offset + len, rounding) - 1;
- ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
- iendoffset);
- return ret;
-}
-
-/* Hook up to the VFS reflink function */
-STATIC int
-xfs_file_share_range(
- struct file *file_in,
- loff_t pos_in,
- struct file *file_out,
- loff_t pos_out,
- u64 len,
- bool is_dedupe)
-{
- struct inode *inode_in;
- struct inode *inode_out;
- ssize_t ret;
- loff_t bs;
- loff_t isize;
- int same_inode;
- loff_t blen;
- unsigned int flags = 0;
-
- inode_in = file_inode(file_in);
- inode_out = file_inode(file_out);
- bs = inode_out->i_sb->s_blocksize;
-
- /* Don't touch certain kinds of inodes */
- if (IS_IMMUTABLE(inode_out))
- return -EPERM;
- if (IS_SWAPFILE(inode_in) ||
- IS_SWAPFILE(inode_out))
- return -ETXTBSY;
-
- /* Reflink only works within this filesystem. */
- if (inode_in->i_sb != inode_out->i_sb)
- return -EXDEV;
- same_inode = (inode_in->i_ino == inode_out->i_ino);
-
- /* Don't reflink dirs, pipes, sockets... */
- if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
- return -EISDIR;
- if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode))
- return -EINVAL;
- if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
- return -EINVAL;
-
- /* Don't share DAX file data for now. */
- if (IS_DAX(inode_in) || IS_DAX(inode_out))
- return -EINVAL;
-
- /* Are we going all the way to the end? */
- isize = i_size_read(inode_in);
- if (isize == 0)
- return 0;
- if (len == 0)
- len = isize - pos_in;
-
- /* Ensure offsets don't wrap and the input is inside i_size */
- if (pos_in + len < pos_in || pos_out + len < pos_out ||
- pos_in + len > isize)
- return -EINVAL;
-
- /* Don't allow dedupe past EOF in the dest file */
- if (is_dedupe) {
- loff_t disize;
-
- disize = i_size_read(inode_out);
- if (pos_out >= disize || pos_out + len > disize)
- return -EINVAL;
- }
-
- /* If we're linking to EOF, continue to the block boundary. */
- if (pos_in + len == isize)
- blen = ALIGN(isize, bs) - pos_in;
- else
- blen = len;
-
- /* Only reflink if we're aligned to block boundaries */
- if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
- !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
- return -EINVAL;
-
- /* Don't allow overlapped reflink within the same file */
- if (same_inode && pos_out + blen > pos_in && pos_out < pos_in + blen)
- return -EINVAL;
-
- /* Wait for the completion of any pending IOs on srcfile */
- ret = xfs_file_wait_for_io(inode_in, pos_in, len);
- if (ret)
- goto out;
- ret = xfs_file_wait_for_io(inode_out, pos_out, len);
- if (ret)
- goto out;
-
- if (is_dedupe)
- flags |= XFS_REFLINK_DEDUPE;
- ret = xfs_reflink_remap_range(XFS_I(inode_in), pos_in, XFS_I(inode_out),
- pos_out, len, flags);
- if (ret < 0)
- goto out;
-
-out:
- return ret;
-}
-
STATIC ssize_t
xfs_file_copy_range(
struct file *file_in,
@@ -1086,7 +920,7 @@ xfs_file_copy_range(
{
int error;
- error = xfs_file_share_range(file_in, pos_in, file_out, pos_out,
+ error = xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
len, false);
if (error)
return error;
@@ -1101,7 +935,7 @@ xfs_file_clone_range(
loff_t pos_out,
u64 len)
{
- return xfs_file_share_range(file_in, pos_in, file_out, pos_out,
+ return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
len, false);
}
@@ -1124,7 +958,7 @@ xfs_file_dedupe_range(
if (len > XFS_MAX_DEDUPE_LEN)
len = XFS_MAX_DEDUPE_LEN;
- error = xfs_file_share_range(src_file, loff, dst_file, dst_loff,
+ error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff,
len, true);
if (error)
return error;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 14796b7..f295049 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1656,9 +1656,9 @@ void
xfs_inode_set_cowblocks_tag(
xfs_inode_t *ip)
{
- trace_xfs_inode_set_eofblocks_tag(ip);
+ trace_xfs_inode_set_cowblocks_tag(ip);
return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_cowblocks,
- trace_xfs_perag_set_eofblocks,
+ trace_xfs_perag_set_cowblocks,
XFS_ICI_COWBLOCKS_TAG);
}
@@ -1666,7 +1666,7 @@ void
xfs_inode_clear_cowblocks_tag(
xfs_inode_t *ip)
{
- trace_xfs_inode_clear_eofblocks_tag(ip);
+ trace_xfs_inode_clear_cowblocks_tag(ip);
return __xfs_inode_clear_eofblocks_tag(ip,
- trace_xfs_perag_clear_eofblocks, XFS_ICI_COWBLOCKS_TAG);
+ trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG);
}
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index d907eb9..436e109 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -566,6 +566,17 @@ xfs_file_iomap_begin_delay(
xfs_bmap_search_extents(ip, offset_fsb, XFS_DATA_FORK, &eof, &idx,
&got, &prev);
if (!eof && got.br_startoff <= offset_fsb) {
+ if (xfs_is_reflink_inode(ip)) {
+ bool shared;
+
+ end_fsb = min(XFS_B_TO_FSB(mp, offset + count),
+ maxbytes_fsb);
+ xfs_trim_extent(&got, offset_fsb, end_fsb - offset_fsb);
+ error = xfs_reflink_reserve_cow(ip, &got, &shared);
+ if (error)
+ goto out_unlock;
+ }
+
trace_xfs_iomap_found(ip, offset, count, 0, &got);
goto done;
}
@@ -961,19 +972,13 @@ xfs_file_iomap_begin(
struct xfs_mount *mp = ip->i_mount;
struct xfs_bmbt_irec imap;
xfs_fileoff_t offset_fsb, end_fsb;
- bool shared, trimmed;
int nimaps = 1, error = 0;
+ bool shared = false, trimmed = false;
unsigned lockmode;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
- if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
- error = xfs_reflink_reserve_cow_range(ip, offset, length);
- if (error < 0)
- return error;
- }
-
if ((flags & IOMAP_WRITE) && !IS_DAX(inode) &&
!xfs_get_extsz_hint(ip)) {
/* Reserve delalloc blocks for regular writeback. */
@@ -981,7 +986,16 @@ xfs_file_iomap_begin(
iomap);
}
- lockmode = xfs_ilock_data_map_shared(ip);
+ /*
+ * COW writes will allocate delalloc space, so we need to make sure
+ * to take the lock exclusively here.
+ */
+ if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
+ lockmode = XFS_ILOCK_EXCL;
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ } else {
+ lockmode = xfs_ilock_data_map_shared(ip);
+ }
ASSERT(offset <= mp->m_super->s_maxbytes);
if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes)
@@ -991,16 +1005,24 @@ xfs_file_iomap_begin(
error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
&nimaps, 0);
- if (error) {
- xfs_iunlock(ip, lockmode);
- return error;
+ if (error)
+ goto out_unlock;
+
+ if (flags & IOMAP_REPORT) {
+ /* Trim the mapping to the nearest shared extent boundary. */
+ error = xfs_reflink_trim_around_shared(ip, &imap, &shared,
+ &trimmed);
+ if (error)
+ goto out_unlock;
}
- /* Trim the mapping to the nearest shared extent boundary. */
- error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed);
- if (error) {
- xfs_iunlock(ip, lockmode);
- return error;
+ if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
+ error = xfs_reflink_reserve_cow(ip, &imap, &shared);
+ if (error)
+ goto out_unlock;
+
+ end_fsb = imap.br_startoff + imap.br_blockcount;
+ length = XFS_FSB_TO_B(mp, end_fsb) - offset;
}
if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) {
@@ -1039,6 +1061,9 @@ xfs_file_iomap_begin(
if (shared)
iomap->flags |= IOMAP_F_SHARED;
return 0;
+out_unlock:
+ xfs_iunlock(ip, lockmode);
+ return error;
}
static int
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index fc78739..b341f10 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1009,6 +1009,7 @@ xfs_mountfs(
out_quota:
xfs_qm_unmount_quotas(mp);
out_rtunmount:
+ mp->m_super->s_flags &= ~MS_ACTIVE;
xfs_rtunmount_inodes(mp);
out_rele_rip:
IRELE(rip);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 5965e94..a279b4e 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -182,7 +182,8 @@ xfs_reflink_trim_around_shared(
if (!xfs_is_reflink_inode(ip) ||
ISUNWRITTEN(irec) ||
irec->br_startblock == HOLESTARTBLOCK ||
- irec->br_startblock == DELAYSTARTBLOCK) {
+ irec->br_startblock == DELAYSTARTBLOCK ||
+ isnullstartblock(irec->br_startblock)) {
*shared = false;
return 0;
}
@@ -227,50 +228,54 @@ xfs_reflink_trim_around_shared(
}
}
-/* Create a CoW reservation for a range of blocks within a file. */
-static int
-__xfs_reflink_reserve_cow(
+/*
+ * Trim the passed in imap to the next shared/unshared extent boundary, and
+ * if imap->br_startoff points to a shared extent reserve space for it in the
+ * COW fork. In this case *shared is set to true, else to false.
+ *
+ * Note that imap will always contain the block numbers for the existing blocks
+ * in the data fork, as the upper layers need them for read-modify-write
+ * operations.
+ */
+int
+xfs_reflink_reserve_cow(
struct xfs_inode *ip,
- xfs_fileoff_t *offset_fsb,
- xfs_fileoff_t end_fsb,
- bool *skipped)
+ struct xfs_bmbt_irec *imap,
+ bool *shared)
{
- struct xfs_bmbt_irec got, prev, imap;
- xfs_fileoff_t orig_end_fsb;
- int nimaps, eof = 0, error = 0;
- bool shared = false, trimmed = false;
+ struct xfs_bmbt_irec got, prev;
+ xfs_fileoff_t end_fsb, orig_end_fsb;
+ int eof = 0, error = 0;
+ bool trimmed;
xfs_extnum_t idx;
xfs_extlen_t align;
- /* Already reserved? Skip the refcount btree access. */
- xfs_bmap_search_extents(ip, *offset_fsb, XFS_COW_FORK, &eof, &idx,
+ /*
+ * Search the COW fork extent list first. This serves two purposes:
+ * first this implement the speculative preallocation using cowextisze,
+ * so that we also unshared block adjacent to shared blocks instead
+ * of just the shared blocks themselves. Second the lookup in the
+ * extent list is generally faster than going out to the shared extent
+ * tree.
+ */
+ xfs_bmap_search_extents(ip, imap->br_startoff, XFS_COW_FORK, &eof, &idx,
&got, &prev);
- if (!eof && got.br_startoff <= *offset_fsb) {
- end_fsb = orig_end_fsb = got.br_startoff + got.br_blockcount;
- trace_xfs_reflink_cow_found(ip, &got);
- goto done;
- }
+ if (!eof && got.br_startoff <= imap->br_startoff) {
+ trace_xfs_reflink_cow_found(ip, imap);
+ xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
- /* Read extent from the source file. */
- nimaps = 1;
- error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb,
- &imap, &nimaps, 0);
- if (error)
- goto out_unlock;
- ASSERT(nimaps == 1);
+ *shared = true;
+ return 0;
+ }
/* Trim the mapping to the nearest shared extent boundary. */
- error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed);
+ error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
if (error)
- goto out_unlock;
-
- end_fsb = orig_end_fsb = imap.br_startoff + imap.br_blockcount;
+ return error;
/* Not shared? Just report the (potentially capped) extent. */
- if (!shared) {
- *skipped = true;
- goto done;
- }
+ if (!*shared)
+ return 0;
/*
* Fork all the shared blocks from our write offset until the end of
@@ -278,72 +283,38 @@ __xfs_reflink_reserve_cow(
*/
error = xfs_qm_dqattach_locked(ip, 0);
if (error)
- goto out_unlock;
+ return error;
+
+ end_fsb = orig_end_fsb = imap->br_startoff + imap->br_blockcount;
align = xfs_eof_alignment(ip, xfs_get_cowextsz_hint(ip));
if (align)
end_fsb = roundup_64(end_fsb, align);
retry:
- error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, *offset_fsb,
- end_fsb - *offset_fsb, &got,
- &prev, &idx, eof);
+ error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, imap->br_startoff,
+ end_fsb - imap->br_startoff, &got, &prev, &idx, eof);
switch (error) {
case 0:
break;
case -ENOSPC:
case -EDQUOT:
/* retry without any preallocation */
- trace_xfs_reflink_cow_enospc(ip, &imap);
+ trace_xfs_reflink_cow_enospc(ip, imap);
if (end_fsb != orig_end_fsb) {
end_fsb = orig_end_fsb;
goto retry;
}
/*FALLTHRU*/
default:
- goto out_unlock;
+ return error;
}
if (end_fsb != orig_end_fsb)
xfs_inode_set_cowblocks_tag(ip);
trace_xfs_reflink_cow_alloc(ip, &got);
-done:
- *offset_fsb = end_fsb;
-out_unlock:
- return error;
-}
-
-/* Create a CoW reservation for part of a file. */
-int
-xfs_reflink_reserve_cow_range(
- struct xfs_inode *ip,
- xfs_off_t offset,
- xfs_off_t count)
-{
- struct xfs_mount *mp = ip->i_mount;
- xfs_fileoff_t offset_fsb, end_fsb;
- bool skipped = false;
- int error;
-
- trace_xfs_reflink_reserve_cow_range(ip, offset, count);
-
- offset_fsb = XFS_B_TO_FSBT(mp, offset);
- end_fsb = XFS_B_TO_FSB(mp, offset + count);
-
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- while (offset_fsb < end_fsb) {
- error = __xfs_reflink_reserve_cow(ip, &offset_fsb, end_fsb,
- &skipped);
- if (error) {
- trace_xfs_reflink_reserve_cow_range_error(ip, error,
- _RET_IP_);
- break;
- }
- }
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
- return error;
+ return 0;
}
/* Allocate all CoW reservations covering a range of blocks in a file. */
@@ -358,9 +329,8 @@ __xfs_reflink_allocate_cow(
struct xfs_defer_ops dfops;
struct xfs_trans *tp;
xfs_fsblock_t first_block;
- xfs_fileoff_t next_fsb;
int nimaps = 1, error;
- bool skipped = false;
+ bool shared;
xfs_defer_init(&dfops, &first_block);
@@ -371,33 +341,38 @@ __xfs_reflink_allocate_cow(
xfs_ilock(ip, XFS_ILOCK_EXCL);
- next_fsb = *offset_fsb;
- error = __xfs_reflink_reserve_cow(ip, &next_fsb, end_fsb, &skipped);
+ /* Read extent from the source file. */
+ nimaps = 1;
+ error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb,
+ &imap, &nimaps, 0);
+ if (error)
+ goto out_unlock;
+ ASSERT(nimaps == 1);
+
+ error = xfs_reflink_reserve_cow(ip, &imap, &shared);
if (error)
goto out_trans_cancel;
- if (skipped) {
- *offset_fsb = next_fsb;
+ if (!shared) {
+ *offset_fsb = imap.br_startoff + imap.br_blockcount;
goto out_trans_cancel;
}
xfs_trans_ijoin(tp, ip, 0);
- error = xfs_bmapi_write(tp, ip, *offset_fsb, next_fsb - *offset_fsb,
+ error = xfs_bmapi_write(tp, ip, imap.br_startoff, imap.br_blockcount,
XFS_BMAPI_COWFORK, &first_block,
XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK),
&imap, &nimaps, &dfops);
if (error)
goto out_trans_cancel;
- /* We might not have been able to map the whole delalloc extent */
- *offset_fsb = min(*offset_fsb + imap.br_blockcount, next_fsb);
-
error = xfs_defer_finish(&tp, &dfops, NULL);
if (error)
goto out_trans_cancel;
error = xfs_trans_commit(tp);
+ *offset_fsb = imap.br_startoff + imap.br_blockcount;
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
@@ -536,58 +511,49 @@ xfs_reflink_cancel_cow_blocks(
xfs_fileoff_t offset_fsb,
xfs_fileoff_t end_fsb)
{
- struct xfs_bmbt_irec irec;
- xfs_filblks_t count_fsb;
+ struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+ struct xfs_bmbt_irec got, prev, del;
+ xfs_extnum_t idx;
xfs_fsblock_t firstfsb;
struct xfs_defer_ops dfops;
- int error = 0;
- int nimaps;
+ int error = 0, eof = 0;
if (!xfs_is_reflink_inode(ip))
return 0;
- /* Go find the old extent in the CoW fork. */
- while (offset_fsb < end_fsb) {
- nimaps = 1;
- count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
- error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec,
- &nimaps, XFS_BMAPI_COWFORK);
- if (error)
- break;
- ASSERT(nimaps == 1);
+ xfs_bmap_search_extents(ip, offset_fsb, XFS_COW_FORK, &eof, &idx,
+ &got, &prev);
+ if (eof)
+ return 0;
- trace_xfs_reflink_cancel_cow(ip, &irec);
+ while (got.br_startoff < end_fsb) {
+ del = got;
+ xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
+ trace_xfs_reflink_cancel_cow(ip, &del);
- if (irec.br_startblock == DELAYSTARTBLOCK) {
- /* Free a delayed allocation. */
- xfs_mod_fdblocks(ip->i_mount, irec.br_blockcount,
- false);
- ip->i_delayed_blks -= irec.br_blockcount;
-
- /* Remove the mapping from the CoW fork. */
- error = xfs_bunmapi_cow(ip, &irec);
+ if (isnullstartblock(del.br_startblock)) {
+ error = xfs_bmap_del_extent_delay(ip, XFS_COW_FORK,
+ &idx, &got, &del);
if (error)
break;
- } else if (irec.br_startblock == HOLESTARTBLOCK) {
- /* empty */
} else {
xfs_trans_ijoin(*tpp, ip, 0);
xfs_defer_init(&dfops, &firstfsb);
/* Free the CoW orphan record. */
error = xfs_refcount_free_cow_extent(ip->i_mount,
- &dfops, irec.br_startblock,
- irec.br_blockcount);
+ &dfops, del.br_startblock,
+ del.br_blockcount);
if (error)
break;
xfs_bmap_add_free(ip->i_mount, &dfops,
- irec.br_startblock, irec.br_blockcount,
+ del.br_startblock, del.br_blockcount,
NULL);
/* Update quota accounting */
xfs_trans_mod_dquot_byino(*tpp, ip, XFS_TRANS_DQ_BCOUNT,
- -(long)irec.br_blockcount);
+ -(long)del.br_blockcount);
/* Roll the transaction */
error = xfs_defer_finish(tpp, &dfops, ip);
@@ -597,15 +563,18 @@ xfs_reflink_cancel_cow_blocks(
}
/* Remove the mapping from the CoW fork. */
- error = xfs_bunmapi_cow(ip, &irec);
- if (error)
- break;
+ xfs_bmap_del_extent_cow(ip, &idx, &got, &del);
}
- /* Roll on... */
- offset_fsb = irec.br_startoff + irec.br_blockcount;
+ if (++idx >= ifp->if_bytes / sizeof(struct xfs_bmbt_rec))
+ break;
+ xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got);
}
+ /* clear tag if cow fork is emptied */
+ if (!ifp->if_bytes)
+ xfs_inode_clear_cowblocks_tag(ip);
+
return error;
}
@@ -668,25 +637,26 @@ xfs_reflink_end_cow(
xfs_off_t offset,
xfs_off_t count)
{
- struct xfs_bmbt_irec irec;
- struct xfs_bmbt_irec uirec;
+ struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+ struct xfs_bmbt_irec got, prev, del;
struct xfs_trans *tp;
xfs_fileoff_t offset_fsb;
xfs_fileoff_t end_fsb;
- xfs_filblks_t count_fsb;
xfs_fsblock_t firstfsb;
struct xfs_defer_ops dfops;
- int error;
+ int error, eof = 0;
unsigned int resblks;
- xfs_filblks_t ilen;
xfs_filblks_t rlen;
- int nimaps;
+ xfs_extnum_t idx;
trace_xfs_reflink_end_cow(ip, offset, count);
+ /* No COW extents? That's easy! */
+ if (ifp->if_bytes == 0)
+ return 0;
+
offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
- count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
/* Start a rolling transaction to switch the mappings */
resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
@@ -698,72 +668,65 @@ xfs_reflink_end_cow(
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
- /* Go find the old extent in the CoW fork. */
- while (offset_fsb < end_fsb) {
- /* Read extent from the source file */
- nimaps = 1;
- count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
- error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec,
- &nimaps, XFS_BMAPI_COWFORK);
- if (error)
- goto out_cancel;
- ASSERT(nimaps == 1);
+ xfs_bmap_search_extents(ip, end_fsb - 1, XFS_COW_FORK, &eof, &idx,
+ &got, &prev);
- ASSERT(irec.br_startblock != DELAYSTARTBLOCK);
- trace_xfs_reflink_cow_remap(ip, &irec);
+ /* If there is a hole at end_fsb - 1 go to the previous extent */
+ if (eof || got.br_startoff > end_fsb) {
+ ASSERT(idx > 0);
+ xfs_bmbt_get_all(xfs_iext_get_ext(ifp, --idx), &got);
+ }
- /*
- * We can have a hole in the CoW fork if part of a directio
- * write is CoW but part of it isn't.
- */
- rlen = ilen = irec.br_blockcount;
- if (irec.br_startblock == HOLESTARTBLOCK)
+ /* Walk backwards until we're out of the I/O range... */
+ while (got.br_startoff + got.br_blockcount > offset_fsb) {
+ del = got;
+ xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
+
+ /* Extent delete may have bumped idx forward */
+ if (!del.br_blockcount) {
+ idx--;
goto next_extent;
-
- /* Unmap the old blocks in the data fork. */
- while (rlen) {
- xfs_defer_init(&dfops, &firstfsb);
- error = __xfs_bunmapi(tp, ip, irec.br_startoff,
- &rlen, 0, 1, &firstfsb, &dfops);
- if (error)
- goto out_defer;
-
- /*
- * Trim the extent to whatever got unmapped.
- * Remember, bunmapi works backwards.
- */
- uirec.br_startblock = irec.br_startblock + rlen;
- uirec.br_startoff = irec.br_startoff + rlen;
- uirec.br_blockcount = irec.br_blockcount - rlen;
- irec.br_blockcount = rlen;
- trace_xfs_reflink_cow_remap_piece(ip, &uirec);
-
- /* Free the CoW orphan record. */
- error = xfs_refcount_free_cow_extent(tp->t_mountp,
- &dfops, uirec.br_startblock,
- uirec.br_blockcount);
- if (error)
- goto out_defer;
-
- /* Map the new blocks into the data fork. */
- error = xfs_bmap_map_extent(tp->t_mountp, &dfops,
- ip, &uirec);
- if (error)
- goto out_defer;
-
- /* Remove the mapping from the CoW fork. */
- error = xfs_bunmapi_cow(ip, &uirec);
- if (error)
- goto out_defer;
-
- error = xfs_defer_finish(&tp, &dfops, ip);
- if (error)
- goto out_defer;
}
+ ASSERT(!isnullstartblock(got.br_startblock));
+
+ /* Unmap the old blocks in the data fork. */
+ xfs_defer_init(&dfops, &firstfsb);
+ rlen = del.br_blockcount;
+ error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1,
+ &firstfsb, &dfops);
+ if (error)
+ goto out_defer;
+
+ /* Trim the extent to whatever got unmapped. */
+ if (rlen) {
+ xfs_trim_extent(&del, del.br_startoff + rlen,
+ del.br_blockcount - rlen);
+ }
+ trace_xfs_reflink_cow_remap(ip, &del);
+
+ /* Free the CoW orphan record. */
+ error = xfs_refcount_free_cow_extent(tp->t_mountp, &dfops,
+ del.br_startblock, del.br_blockcount);
+ if (error)
+ goto out_defer;
+
+ /* Map the new blocks into the data fork. */
+ error = xfs_bmap_map_extent(tp->t_mountp, &dfops, ip, &del);
+ if (error)
+ goto out_defer;
+
+ /* Remove the mapping from the CoW fork. */
+ xfs_bmap_del_extent_cow(ip, &idx, &got, &del);
+
+ error = xfs_defer_finish(&tp, &dfops, ip);
+ if (error)
+ goto out_defer;
+
next_extent:
- /* Roll on... */
- offset_fsb = irec.br_startoff + ilen;
+ if (idx < 0)
+ break;
+ xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got);
}
error = xfs_trans_commit(tp);
@@ -774,7 +737,6 @@ xfs_reflink_end_cow(
out_defer:
xfs_defer_cancel(&dfops);
-out_cancel:
xfs_trans_cancel(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
@@ -1312,19 +1274,26 @@ xfs_compare_extents(
*/
int
xfs_reflink_remap_range(
- struct xfs_inode *src,
- xfs_off_t srcoff,
- struct xfs_inode *dest,
- xfs_off_t destoff,
- xfs_off_t len,
- unsigned int flags)
+ struct file *file_in,
+ loff_t pos_in,
+ struct file *file_out,
+ loff_t pos_out,
+ u64 len,
+ bool is_dedupe)
{
+ struct inode *inode_in = file_inode(file_in);
+ struct xfs_inode *src = XFS_I(inode_in);
+ struct inode *inode_out = file_inode(file_out);
+ struct xfs_inode *dest = XFS_I(inode_out);
struct xfs_mount *mp = src->i_mount;
+ loff_t bs = inode_out->i_sb->s_blocksize;
+ bool same_inode = (inode_in == inode_out);
xfs_fileoff_t sfsbno, dfsbno;
xfs_filblks_t fsblen;
- int error;
xfs_extlen_t cowextsize;
- bool is_same;
+ loff_t isize;
+ ssize_t ret;
+ loff_t blen;
if (!xfs_sb_version_hasreflink(&mp->m_sb))
return -EOPNOTSUPP;
@@ -1332,17 +1301,8 @@ xfs_reflink_remap_range(
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
- /* Don't reflink realtime inodes */
- if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
- return -EINVAL;
-
- if (flags & ~XFS_REFLINK_ALL)
- return -EINVAL;
-
- trace_xfs_reflink_remap_range(src, srcoff, len, dest, destoff);
-
/* Lock both files against IO */
- if (src->i_ino == dest->i_ino) {
+ if (same_inode) {
xfs_ilock(src, XFS_IOLOCK_EXCL);
xfs_ilock(src, XFS_MMAPLOCK_EXCL);
} else {
@@ -1350,39 +1310,126 @@ xfs_reflink_remap_range(
xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL);
}
+ /* Don't touch certain kinds of inodes */
+ ret = -EPERM;
+ if (IS_IMMUTABLE(inode_out))
+ goto out_unlock;
+
+ ret = -ETXTBSY;
+ if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
+ goto out_unlock;
+
+
+ /* Don't reflink dirs, pipes, sockets... */
+ ret = -EISDIR;
+ if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+ goto out_unlock;
+ ret = -EINVAL;
+ if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode))
+ goto out_unlock;
+ if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+ goto out_unlock;
+
+ /* Don't reflink realtime inodes */
+ if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
+ goto out_unlock;
+
+ /* Don't share DAX file data for now. */
+ if (IS_DAX(inode_in) || IS_DAX(inode_out))
+ goto out_unlock;
+
+ /* Are we going all the way to the end? */
+ isize = i_size_read(inode_in);
+ if (isize == 0) {
+ ret = 0;
+ goto out_unlock;
+ }
+
+ if (len == 0)
+ len = isize - pos_in;
+
+ /* Ensure offsets don't wrap and the input is inside i_size */
+ if (pos_in + len < pos_in || pos_out + len < pos_out ||
+ pos_in + len > isize)
+ goto out_unlock;
+
+ /* Don't allow dedupe past EOF in the dest file */
+ if (is_dedupe) {
+ loff_t disize;
+
+ disize = i_size_read(inode_out);
+ if (pos_out >= disize || pos_out + len > disize)
+ goto out_unlock;
+ }
+
+ /* If we're linking to EOF, continue to the block boundary. */
+ if (pos_in + len == isize)
+ blen = ALIGN(isize, bs) - pos_in;
+ else
+ blen = len;
+
+ /* Only reflink if we're aligned to block boundaries */
+ if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
+ !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
+ goto out_unlock;
+
+ /* Don't allow overlapped reflink within the same file */
+ if (same_inode) {
+ if (pos_out + blen > pos_in && pos_out < pos_in + blen)
+ goto out_unlock;
+ }
+
+ /* Wait for the completion of any pending IOs on both files */
+ inode_dio_wait(inode_in);
+ if (!same_inode)
+ inode_dio_wait(inode_out);
+
+ ret = filemap_write_and_wait_range(inode_in->i_mapping,
+ pos_in, pos_in + len - 1);
+ if (ret)
+ goto out_unlock;
+
+ ret = filemap_write_and_wait_range(inode_out->i_mapping,
+ pos_out, pos_out + len - 1);
+ if (ret)
+ goto out_unlock;
+
+ trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
+
/*
* Check that the extents are the same.
*/
- if (flags & XFS_REFLINK_DEDUPE) {
- is_same = false;
- error = xfs_compare_extents(VFS_I(src), srcoff, VFS_I(dest),
- destoff, len, &is_same);
- if (error)
- goto out_error;
+ if (is_dedupe) {
+ bool is_same = false;
+
+ ret = xfs_compare_extents(inode_in, pos_in, inode_out, pos_out,
+ len, &is_same);
+ if (ret)
+ goto out_unlock;
if (!is_same) {
- error = -EBADE;
- goto out_error;
+ ret = -EBADE;
+ goto out_unlock;
}
}
- error = xfs_reflink_set_inode_flag(src, dest);
- if (error)
- goto out_error;
+ ret = xfs_reflink_set_inode_flag(src, dest);
+ if (ret)
+ goto out_unlock;
/*
* Invalidate the page cache so that we can clear any CoW mappings
* in the destination file.
*/
- truncate_inode_pages_range(&VFS_I(dest)->i_data, destoff,
- PAGE_ALIGN(destoff + len) - 1);
+ truncate_inode_pages_range(&inode_out->i_data, pos_out,
+ PAGE_ALIGN(pos_out + len) - 1);
- dfsbno = XFS_B_TO_FSBT(mp, destoff);
- sfsbno = XFS_B_TO_FSBT(mp, srcoff);
+ dfsbno = XFS_B_TO_FSBT(mp, pos_out);
+ sfsbno = XFS_B_TO_FSBT(mp, pos_in);
fsblen = XFS_B_TO_FSB(mp, len);
- error = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
- destoff + len);
- if (error)
- goto out_error;
+ ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
+ pos_out + len);
+ if (ret)
+ goto out_unlock;
/*
* Carry the cowextsize hint from src to dest if we're sharing the
@@ -1390,26 +1437,24 @@ xfs_reflink_remap_range(
* has a cowextsize hint, and the destination file does not.
*/
cowextsize = 0;
- if (srcoff == 0 && len == i_size_read(VFS_I(src)) &&
+ if (pos_in == 0 && len == i_size_read(inode_in) &&
(src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) &&
- destoff == 0 && len >= i_size_read(VFS_I(dest)) &&
+ pos_out == 0 && len >= i_size_read(inode_out) &&
!(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
cowextsize = src->i_d.di_cowextsize;
- error = xfs_reflink_update_dest(dest, destoff + len, cowextsize);
- if (error)
- goto out_error;
+ ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize);
-out_error:
+out_unlock:
xfs_iunlock(src, XFS_MMAPLOCK_EXCL);
xfs_iunlock(src, XFS_IOLOCK_EXCL);
if (src->i_ino != dest->i_ino) {
xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
xfs_iunlock(dest, XFS_IOLOCK_EXCL);
}
- if (error)
- trace_xfs_reflink_remap_range_error(dest, error, _RET_IP_);
- return error;
+ if (ret)
+ trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
+ return ret;
}
/*
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index 5dc3c8a..fad1160 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -26,8 +26,8 @@ extern int xfs_reflink_find_shared(struct xfs_mount *mp, xfs_agnumber_t agno,
extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed);
-extern int xfs_reflink_reserve_cow_range(struct xfs_inode *ip,
- xfs_off_t offset, xfs_off_t count);
+extern int xfs_reflink_reserve_cow(struct xfs_inode *ip,
+ struct xfs_bmbt_irec *imap, bool *shared);
extern int xfs_reflink_allocate_cow_range(struct xfs_inode *ip,
xfs_off_t offset, xfs_off_t count);
extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset,
@@ -43,11 +43,8 @@ extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset,
extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
xfs_off_t count);
extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
-#define XFS_REFLINK_DEDUPE 1 /* only reflink if contents match */
-#define XFS_REFLINK_ALL (XFS_REFLINK_DEDUPE)
-extern int xfs_reflink_remap_range(struct xfs_inode *src, xfs_off_t srcoff,
- struct xfs_inode *dest, xfs_off_t destoff, xfs_off_t len,
- unsigned int flags);
+extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe);
extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip,
struct xfs_trans **tpp);
extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset,
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 5f8d55d..276d302 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -512,13 +512,13 @@ static struct attribute *xfs_error_attrs[] = {
};
-struct kobj_type xfs_error_cfg_ktype = {
+static struct kobj_type xfs_error_cfg_ktype = {
.release = xfs_sysfs_release,
.sysfs_ops = &xfs_sysfs_ops,
.default_attrs = xfs_error_attrs,
};
-struct kobj_type xfs_error_ktype = {
+static struct kobj_type xfs_error_ktype = {
.release = xfs_sysfs_release,
.sysfs_ops = &xfs_sysfs_ops,
};
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index ad188d3..0907752 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3346,7 +3346,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_alloc);
DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found);
DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_enospc);
-DEFINE_RW_EVENT(xfs_reflink_reserve_cow_range);
+DEFINE_RW_EVENT(xfs_reflink_reserve_cow);
DEFINE_RW_EVENT(xfs_reflink_allocate_cow_range);
DEFINE_INODE_IREC_EVENT(xfs_reflink_bounce_dio_write);
@@ -3356,9 +3356,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec);
DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range);
DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow);
DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap);
-DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_piece);
-DEFINE_INODE_ERROR_EVENT(xfs_reflink_reserve_cow_range_error);
DEFINE_INODE_ERROR_EVENT(xfs_reflink_allocate_cow_range_error);
DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error);
DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error);
diff --git a/include/acpi/pcc.h b/include/acpi/pcc.h
index 17a940a..8caa79c 100644
--- a/include/acpi/pcc.h
+++ b/include/acpi/pcc.h
@@ -21,7 +21,7 @@ extern void pcc_mbox_free_channel(struct mbox_chan *chan);
static inline struct mbox_chan *pcc_mbox_request_channel(struct mbox_client *cl,
int subspace_id)
{
- return NULL;
+ return ERR_PTR(-ENODEV);
}
static inline void pcc_mbox_free_channel(struct mbox_chan *chan) { }
#endif
diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h
new file mode 100644
index 0000000..63554e9
--- /dev/null
+++ b/include/asm-generic/export.h
@@ -0,0 +1,94 @@
+#ifndef __ASM_GENERIC_EXPORT_H
+#define __ASM_GENERIC_EXPORT_H
+
+#ifndef KSYM_FUNC
+#define KSYM_FUNC(x) x
+#endif
+#ifdef CONFIG_64BIT
+#define __put .quad
+#ifndef KSYM_ALIGN
+#define KSYM_ALIGN 8
+#endif
+#ifndef KCRC_ALIGN
+#define KCRC_ALIGN 8
+#endif
+#else
+#define __put .long
+#ifndef KSYM_ALIGN
+#define KSYM_ALIGN 4
+#endif
+#ifndef KCRC_ALIGN
+#define KCRC_ALIGN 4
+#endif
+#endif
+
+#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
+#define KSYM(name) _##name
+#else
+#define KSYM(name) name
+#endif
+
+/*
+ * note on .section use: @progbits vs %progbits nastiness doesn't matter,
+ * since we immediately emit into those sections anyway.
+ */
+.macro ___EXPORT_SYMBOL name,val,sec
+#ifdef CONFIG_MODULES
+ .globl KSYM(__ksymtab_\name)
+ .section ___ksymtab\sec+\name,"a"
+ .balign KSYM_ALIGN
+KSYM(__ksymtab_\name):
+ __put \val, KSYM(__kstrtab_\name)
+ .previous
+ .section __ksymtab_strings,"a"
+KSYM(__kstrtab_\name):
+#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
+ .asciz "_\name"
+#else
+ .asciz "\name"
+#endif
+ .previous
+#ifdef CONFIG_MODVERSIONS
+ .section ___kcrctab\sec+\name,"a"
+ .balign KCRC_ALIGN
+KSYM(__kcrctab_\name):
+ __put KSYM(__crc_\name)
+ .weak KSYM(__crc_\name)
+ .previous
+#endif
+#endif
+.endm
+#undef __put
+
+#if defined(__KSYM_DEPS__)
+
+#define __EXPORT_SYMBOL(sym, val, sec) === __KSYM_##sym ===
+
+#elif defined(CONFIG_TRIM_UNUSED_KSYMS)
+
+#include <linux/kconfig.h>
+#include <generated/autoksyms.h>
+
+#define __EXPORT_SYMBOL(sym, val, sec) \
+ __cond_export_sym(sym, val, sec, __is_defined(__KSYM_##sym))
+#define __cond_export_sym(sym, val, sec, conf) \
+ ___cond_export_sym(sym, val, sec, conf)
+#define ___cond_export_sym(sym, val, sec, enabled) \
+ __cond_export_sym_##enabled(sym, val, sec)
+#define __cond_export_sym_1(sym, val, sec) ___EXPORT_SYMBOL sym, val, sec
+#define __cond_export_sym_0(sym, val, sec) /* nothing */
+
+#else
+#define __EXPORT_SYMBOL(sym, val, sec) ___EXPORT_SYMBOL sym, val, sec
+#endif
+
+#define EXPORT_SYMBOL(name) \
+ __EXPORT_SYMBOL(name, KSYM_FUNC(KSYM(name)),)
+#define EXPORT_SYMBOL_GPL(name) \
+ __EXPORT_SYMBOL(name, KSYM_FUNC(KSYM(name)), _gpl)
+#define EXPORT_DATA_SYMBOL(name) \
+ __EXPORT_SYMBOL(name, KSYM(name),)
+#define EXPORT_DATA_SYMBOL_GPL(name) \
+ __EXPORT_SYMBOL(name, KSYM(name),_gpl)
+
+#endif
diff --git a/include/asm-generic/libata-portmap.h b/include/asm-generic/libata-portmap.h
deleted file mode 100644
index cf14f2f..0000000
--- a/include/asm-generic/libata-portmap.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __ASM_GENERIC_LIBATA_PORTMAP_H
-#define __ASM_GENERIC_LIBATA_PORTMAP_H
-
-#define ATA_PRIMARY_IRQ(dev) 14
-#define ATA_SECONDARY_IRQ(dev) 15
-
-#endif
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 4d9f233..0504ef8 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -65,6 +65,11 @@ extern void setup_per_cpu_areas(void);
#define PER_CPU_DEF_ATTRIBUTES
#endif
+#define raw_cpu_generic_read(pcp) \
+({ \
+ *raw_cpu_ptr(&(pcp)); \
+})
+
#define raw_cpu_generic_to_op(pcp, val, op) \
do { \
*raw_cpu_ptr(&(pcp)) op val; \
@@ -72,34 +77,39 @@ do { \
#define raw_cpu_generic_add_return(pcp, val) \
({ \
- raw_cpu_add(pcp, val); \
- raw_cpu_read(pcp); \
+ typeof(&(pcp)) __p = raw_cpu_ptr(&(pcp)); \
+ \
+ *__p += val; \
+ *__p; \
})
#define raw_cpu_generic_xchg(pcp, nval) \
({ \
+ typeof(&(pcp)) __p = raw_cpu_ptr(&(pcp)); \
typeof(pcp) __ret; \
- __ret = raw_cpu_read(pcp); \
- raw_cpu_write(pcp, nval); \
+ __ret = *__p; \
+ *__p = nval; \
__ret; \
})
#define raw_cpu_generic_cmpxchg(pcp, oval, nval) \
({ \
+ typeof(&(pcp)) __p = raw_cpu_ptr(&(pcp)); \
typeof(pcp) __ret; \
- __ret = raw_cpu_read(pcp); \
+ __ret = *__p; \
if (__ret == (oval)) \
- raw_cpu_write(pcp, nval); \
+ *__p = nval; \
__ret; \
})
#define raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
({ \
+ typeof(&(pcp1)) __p1 = raw_cpu_ptr(&(pcp1)); \
+ typeof(&(pcp2)) __p2 = raw_cpu_ptr(&(pcp2)); \
int __ret = 0; \
- if (raw_cpu_read(pcp1) == (oval1) && \
- raw_cpu_read(pcp2) == (oval2)) { \
- raw_cpu_write(pcp1, nval1); \
- raw_cpu_write(pcp2, nval2); \
+ if (*__p1 == (oval1) && *__p2 == (oval2)) { \
+ *__p1 = nval1; \
+ *__p2 = nval2; \
__ret = 1; \
} \
(__ret); \
@@ -108,9 +118,9 @@ do { \
#define this_cpu_generic_read(pcp) \
({ \
typeof(pcp) __ret; \
- preempt_disable(); \
- __ret = *this_cpu_ptr(&(pcp)); \
- preempt_enable(); \
+ preempt_disable_notrace(); \
+ __ret = raw_cpu_generic_read(pcp); \
+ preempt_enable_notrace(); \
__ret; \
})
@@ -118,17 +128,17 @@ do { \
do { \
unsigned long __flags; \
raw_local_irq_save(__flags); \
- *raw_cpu_ptr(&(pcp)) op val; \
+ raw_cpu_generic_to_op(pcp, val, op); \
raw_local_irq_restore(__flags); \
} while (0)
+
#define this_cpu_generic_add_return(pcp, val) \
({ \
typeof(pcp) __ret; \
unsigned long __flags; \
raw_local_irq_save(__flags); \
- raw_cpu_add(pcp, val); \
- __ret = raw_cpu_read(pcp); \
+ __ret = raw_cpu_generic_add_return(pcp, val); \
raw_local_irq_restore(__flags); \
__ret; \
})
@@ -138,8 +148,7 @@ do { \
typeof(pcp) __ret; \
unsigned long __flags; \
raw_local_irq_save(__flags); \
- __ret = raw_cpu_read(pcp); \
- raw_cpu_write(pcp, nval); \
+ __ret = raw_cpu_generic_xchg(pcp, nval); \
raw_local_irq_restore(__flags); \
__ret; \
})
@@ -149,9 +158,7 @@ do { \
typeof(pcp) __ret; \
unsigned long __flags; \
raw_local_irq_save(__flags); \
- __ret = raw_cpu_read(pcp); \
- if (__ret == (oval)) \
- raw_cpu_write(pcp, nval); \
+ __ret = raw_cpu_generic_cmpxchg(pcp, oval, nval); \
raw_local_irq_restore(__flags); \
__ret; \
})
@@ -168,16 +175,16 @@ do { \
})
#ifndef raw_cpu_read_1
-#define raw_cpu_read_1(pcp) (*raw_cpu_ptr(&(pcp)))
+#define raw_cpu_read_1(pcp) raw_cpu_generic_read(pcp)
#endif
#ifndef raw_cpu_read_2
-#define raw_cpu_read_2(pcp) (*raw_cpu_ptr(&(pcp)))
+#define raw_cpu_read_2(pcp) raw_cpu_generic_read(pcp)
#endif
#ifndef raw_cpu_read_4
-#define raw_cpu_read_4(pcp) (*raw_cpu_ptr(&(pcp)))
+#define raw_cpu_read_4(pcp) raw_cpu_generic_read(pcp)
#endif
#ifndef raw_cpu_read_8
-#define raw_cpu_read_8(pcp) (*raw_cpu_ptr(&(pcp)))
+#define raw_cpu_read_8(pcp) raw_cpu_generic_read(pcp)
#endif
#ifndef raw_cpu_write_1
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index af0254c..4df64a1 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -14,6 +14,8 @@
* [_sdata, _edata]: contains .data.* sections, may also contain .rodata.*
* and/or .init.* sections.
* [__start_rodata, __end_rodata]: contains .rodata.* sections
+ * [__start_data_ro_after_init, __end_data_ro_after_init]:
+ * contains data.ro_after_init section
* [__init_begin, __init_end]: contains .init.* sections, but .init.text.*
* may be out of this range on some architectures.
* [_sinittext, _einittext]: contains .init.text.* sections
@@ -31,6 +33,7 @@ extern char _data[], _sdata[], _edata[];
extern char __bss_start[], __bss_stop[];
extern char __init_begin[], __init_end[];
extern char _sinittext[], _einittext[];
+extern char __start_data_ro_after_init[], __end_data_ro_after_init[];
extern char _end[];
extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
extern char __kprobes_text_start[], __kprobes_text_end[];
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 3e42bcd..31e1d63 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -196,9 +196,14 @@
*(.dtb.init.rodata) \
VMLINUX_SYMBOL(__dtb_end) = .;
-/* .data section */
+/*
+ * .data section
+ * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections generates
+ * .data.identifier which needs to be pulled in with .data, but don't want to
+ * pull in .data..stuff which has its own requirements. Same for bss.
+ */
#define DATA_DATA \
- *(.data) \
+ *(.data .data.[0-9a-zA-Z_]*) \
*(.ref.data) \
*(.data..shared_aligned) /* percpu related */ \
MEM_KEEP(init.data) \
@@ -254,7 +259,10 @@
* own by defining an empty RO_AFTER_INIT_DATA.
*/
#ifndef RO_AFTER_INIT_DATA
-#define RO_AFTER_INIT_DATA *(.data..ro_after_init)
+#define RO_AFTER_INIT_DATA \
+ __start_data_ro_after_init = .; \
+ *(.data..ro_after_init) \
+ __end_data_ro_after_init = .;
#endif
/*
@@ -320,76 +328,76 @@
/* Kernel symbol table: Normal symbols */ \
__ksymtab : AT(ADDR(__ksymtab) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___ksymtab) = .; \
- *(SORT(___ksymtab+*)) \
+ KEEP(*(SORT(___ksymtab+*))) \
VMLINUX_SYMBOL(__stop___ksymtab) = .; \
} \
\
/* Kernel symbol table: GPL-only symbols */ \
__ksymtab_gpl : AT(ADDR(__ksymtab_gpl) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___ksymtab_gpl) = .; \
- *(SORT(___ksymtab_gpl+*)) \
+ KEEP(*(SORT(___ksymtab_gpl+*))) \
VMLINUX_SYMBOL(__stop___ksymtab_gpl) = .; \
} \
\
/* Kernel symbol table: Normal unused symbols */ \
__ksymtab_unused : AT(ADDR(__ksymtab_unused) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___ksymtab_unused) = .; \
- *(SORT(___ksymtab_unused+*)) \
+ KEEP(*(SORT(___ksymtab_unused+*))) \
VMLINUX_SYMBOL(__stop___ksymtab_unused) = .; \
} \
\
/* Kernel symbol table: GPL-only unused symbols */ \
__ksymtab_unused_gpl : AT(ADDR(__ksymtab_unused_gpl) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___ksymtab_unused_gpl) = .; \
- *(SORT(___ksymtab_unused_gpl+*)) \
+ KEEP(*(SORT(___ksymtab_unused_gpl+*))) \
VMLINUX_SYMBOL(__stop___ksymtab_unused_gpl) = .; \
} \
\
/* Kernel symbol table: GPL-future-only symbols */ \
__ksymtab_gpl_future : AT(ADDR(__ksymtab_gpl_future) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___ksymtab_gpl_future) = .; \
- *(SORT(___ksymtab_gpl_future+*)) \
+ KEEP(*(SORT(___ksymtab_gpl_future+*))) \
VMLINUX_SYMBOL(__stop___ksymtab_gpl_future) = .; \
} \
\
/* Kernel symbol table: Normal symbols */ \
__kcrctab : AT(ADDR(__kcrctab) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___kcrctab) = .; \
- *(SORT(___kcrctab+*)) \
+ KEEP(*(SORT(___kcrctab+*))) \
VMLINUX_SYMBOL(__stop___kcrctab) = .; \
} \
\
/* Kernel symbol table: GPL-only symbols */ \
__kcrctab_gpl : AT(ADDR(__kcrctab_gpl) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___kcrctab_gpl) = .; \
- *(SORT(___kcrctab_gpl+*)) \
+ KEEP(*(SORT(___kcrctab_gpl+*))) \
VMLINUX_SYMBOL(__stop___kcrctab_gpl) = .; \
} \
\
/* Kernel symbol table: Normal unused symbols */ \
__kcrctab_unused : AT(ADDR(__kcrctab_unused) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___kcrctab_unused) = .; \
- *(SORT(___kcrctab_unused+*)) \
+ KEEP(*(SORT(___kcrctab_unused+*))) \
VMLINUX_SYMBOL(__stop___kcrctab_unused) = .; \
} \
\
/* Kernel symbol table: GPL-only unused symbols */ \
__kcrctab_unused_gpl : AT(ADDR(__kcrctab_unused_gpl) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___kcrctab_unused_gpl) = .; \
- *(SORT(___kcrctab_unused_gpl+*)) \
+ KEEP(*(SORT(___kcrctab_unused_gpl+*))) \
VMLINUX_SYMBOL(__stop___kcrctab_unused_gpl) = .; \
} \
\
/* Kernel symbol table: GPL-future-only symbols */ \
__kcrctab_gpl_future : AT(ADDR(__kcrctab_gpl_future) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___kcrctab_gpl_future) = .; \
- *(SORT(___kcrctab_gpl_future+*)) \
+ KEEP(*(SORT(___kcrctab_gpl_future+*))) \
VMLINUX_SYMBOL(__stop___kcrctab_gpl_future) = .; \
} \
\
/* Kernel symbol table: strings */ \
__ksymtab_strings : AT(ADDR(__ksymtab_strings) - LOAD_OFFSET) { \
- *(__ksymtab_strings) \
+ KEEP(*(__ksymtab_strings)) \
} \
\
/* __*init sections */ \
@@ -424,12 +432,17 @@
#define SECURITY_INIT \
.security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__security_initcall_start) = .; \
- *(.security_initcall.init) \
+ KEEP(*(.security_initcall.init)) \
VMLINUX_SYMBOL(__security_initcall_end) = .; \
}
/* .text section. Map to function alignment to avoid address changes
- * during second ld run in second ld pass when generating System.map */
+ * during second ld run in second ld pass when generating System.map
+ * LD_DEAD_CODE_DATA_ELIMINATION option enables -ffunction-sections generates
+ * .text.identifier which needs to be pulled in with .text , but some
+ * architectures define .text.foo which is not intended to be pulled in here.
+ * Those enabling LD_DEAD_CODE_DATA_ELIMINATION must ensure they don't have
+ * conflicting section names, and must pull in .text.[0-9a-zA-Z_]* */
#define TEXT_TEXT \
ALIGN_FUNCTION(); \
*(.text.hot .text .text.fixup .text.unlikely) \
@@ -533,6 +546,7 @@
/* init and exit section handling */
#define INIT_DATA \
+ KEEP(*(SORT(___kentry+*))) \
*(.init.data) \
MEM_DISCARD(init.data) \
KERNEL_CTORS() \
@@ -599,7 +613,7 @@
BSS_FIRST_SECTIONS \
*(.bss..page_aligned) \
*(.dynbss) \
- *(.bss) \
+ *(.bss .bss.[0-9a-zA-Z_]*) \
*(COMMON) \
}
@@ -682,12 +696,12 @@
#define INIT_CALLS_LEVEL(level) \
VMLINUX_SYMBOL(__initcall##level##_start) = .; \
- *(.initcall##level##.init) \
- *(.initcall##level##s.init) \
+ KEEP(*(.initcall##level##.init)) \
+ KEEP(*(.initcall##level##s.init)) \
#define INIT_CALLS \
VMLINUX_SYMBOL(__initcall_start) = .; \
- *(.initcallearly.init) \
+ KEEP(*(.initcallearly.init)) \
INIT_CALLS_LEVEL(0) \
INIT_CALLS_LEVEL(1) \
INIT_CALLS_LEVEL(2) \
@@ -701,21 +715,21 @@
#define CON_INITCALL \
VMLINUX_SYMBOL(__con_initcall_start) = .; \
- *(.con_initcall.init) \
+ KEEP(*(.con_initcall.init)) \
VMLINUX_SYMBOL(__con_initcall_end) = .;
#define SECURITY_INITCALL \
VMLINUX_SYMBOL(__security_initcall_start) = .; \
- *(.security_initcall.init) \
+ KEEP(*(.security_initcall.init)) \
VMLINUX_SYMBOL(__security_initcall_end) = .;
#ifdef CONFIG_BLK_DEV_INITRD
#define INIT_RAM_FS \
. = ALIGN(4); \
VMLINUX_SYMBOL(__initramfs_start) = .; \
- *(.init.ramfs) \
+ KEEP(*(.init.ramfs)) \
. = ALIGN(8); \
- *(.init.ramfs.info)
+ KEEP(*(.init.ramfs.info))
#else
#define INIT_RAM_FS
#endif
diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h
index 43cf193..8b4dc62 100644
--- a/include/drm/drm_plane.h
+++ b/include/drm/drm_plane.h
@@ -47,8 +47,14 @@ struct drm_crtc;
* @src_h: height of visible portion of plane (in 16.16)
* @rotation: rotation of the plane
* @zpos: priority of the given plane on crtc (optional)
+ * Note that multiple active planes on the same crtc can have an identical
+ * zpos value. The rule to solving the conflict is to compare the plane
+ * object IDs; the plane with a higher ID must be stacked on top of a
+ * plane with a lower ID.
* @normalized_zpos: normalized value of zpos: unique, range from 0 to N-1
- * where N is the number of active planes for given crtc
+ * where N is the number of active planes for given crtc. Note that
+ * the driver must call drm_atomic_normalize_zpos() to update this before
+ * it can be trusted.
* @src: clipped source coordinates of the plane (in 16.16)
* @dst: clipped destination coordinates of the plane
* @visible: visibility of the plane
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 94afcb2c..61a3d90 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -326,6 +326,7 @@ struct pci_dev;
int acpi_pci_irq_enable (struct pci_dev *dev);
void acpi_penalize_isa_irq(int irq, int active);
bool acpi_isa_irq_available(int irq);
+void acpi_penalize_sci_irq(int irq, int trigger, int polarity);
void acpi_pci_irq_disable (struct pci_dev *dev);
extern int ec_read(u8 addr, u8 *val);
@@ -554,7 +555,8 @@ int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *);
int acpi_device_modalias(struct device *, char *, int);
void acpi_walk_dep_device_list(acpi_handle handle);
-struct platform_device *acpi_create_platform_device(struct acpi_device *);
+struct platform_device *acpi_create_platform_device(struct acpi_device *,
+ struct property_entry *);
#define ACPI_PTR(_ptr) (_ptr)
static inline void acpi_device_set_enumerated(struct acpi_device *adev)
@@ -946,9 +948,17 @@ struct acpi_reference_args {
#ifdef CONFIG_ACPI
int acpi_dev_get_property(struct acpi_device *adev, const char *name,
acpi_object_type type, const union acpi_object **obj);
-int acpi_node_get_property_reference(struct fwnode_handle *fwnode,
- const char *name, size_t index,
- struct acpi_reference_args *args);
+int __acpi_node_get_property_reference(struct fwnode_handle *fwnode,
+ const char *name, size_t index, size_t num_args,
+ struct acpi_reference_args *args);
+
+static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode,
+ const char *name, size_t index,
+ struct acpi_reference_args *args)
+{
+ return __acpi_node_get_property_reference(fwnode, name, index,
+ MAX_ACPI_REFERENCE_ARGS, args);
+}
int acpi_node_prop_get(struct fwnode_handle *fwnode, const char *propname,
void **valptr);
@@ -1024,6 +1034,14 @@ static inline int acpi_dev_get_property(struct acpi_device *adev,
return -ENXIO;
}
+static inline int
+__acpi_node_get_property_reference(struct fwnode_handle *fwnode,
+ const char *name, size_t index, size_t num_args,
+ struct acpi_reference_args *args)
+{
+ return -ENXIO;
+}
+
static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode,
const char *name, size_t index,
struct acpi_reference_args *args)
diff --git a/include/linux/ata.h b/include/linux/ata.h
index adbc812..fdb18036 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -105,6 +105,7 @@ enum {
ATA_ID_CFA_KEY_MGMT = 162,
ATA_ID_CFA_MODES = 163,
ATA_ID_DATA_SET_MGMT = 169,
+ ATA_ID_SCT_CMD_XPORT = 206,
ATA_ID_ROT_SPEED = 217,
ATA_ID_PIO4 = (1 << 1),
@@ -789,6 +790,48 @@ static inline bool ata_id_sense_reporting_enabled(const u16 *id)
}
/**
+ *
+ * Word: 206 - SCT Command Transport
+ * 15:12 - Vendor Specific
+ * 11:6 - Reserved
+ * 5 - SCT Command Transport Data Tables supported
+ * 4 - SCT Command Transport Features Control supported
+ * 3 - SCT Command Transport Error Recovery Control supported
+ * 2 - SCT Command Transport Write Same supported
+ * 1 - SCT Command Transport Long Sector Access supported
+ * 0 - SCT Command Transport supported
+ */
+static inline bool ata_id_sct_data_tables(const u16 *id)
+{
+ return id[ATA_ID_SCT_CMD_XPORT] & (1 << 5) ? true : false;
+}
+
+static inline bool ata_id_sct_features_ctrl(const u16 *id)
+{
+ return id[ATA_ID_SCT_CMD_XPORT] & (1 << 4) ? true : false;
+}
+
+static inline bool ata_id_sct_error_recovery_ctrl(const u16 *id)
+{
+ return id[ATA_ID_SCT_CMD_XPORT] & (1 << 3) ? true : false;
+}
+
+static inline bool ata_id_sct_write_same(const u16 *id)
+{
+ return id[ATA_ID_SCT_CMD_XPORT] & (1 << 2) ? true : false;
+}
+
+static inline bool ata_id_sct_long_sector_access(const u16 *id)
+{
+ return id[ATA_ID_SCT_CMD_XPORT] & (1 << 1) ? true : false;
+}
+
+static inline bool ata_id_sct_supported(const u16 *id)
+{
+ return id[ATA_ID_SCT_CMD_XPORT] & (1 << 0) ? true : false;
+}
+
+/**
* ata_id_major_version - get ATA level of drive
* @id: Identify data
*
@@ -1071,32 +1114,6 @@ static inline void ata_id_to_hd_driveid(u16 *id)
#endif
}
-/*
- * Write LBA Range Entries to the buffer that will cover the extent from
- * sector to sector + count. This is used for TRIM and for ADD LBA(S)
- * TO NV CACHE PINNED SET.
- */
-static inline unsigned ata_set_lba_range_entries(void *_buffer,
- unsigned num, u64 sector, unsigned long count)
-{
- __le64 *buffer = _buffer;
- unsigned i = 0, used_bytes;
-
- while (i < num) {
- u64 entry = sector |
- ((u64)(count > 0xffff ? 0xffff : count) << 48);
- buffer[i++] = __cpu_to_le64(entry);
- if (count <= 0xffff)
- break;
- count -= 0xffff;
- sector += 0xffff;
- }
-
- used_bytes = ALIGN(i * 8, 512);
- memset(buffer + i, 0, used_bytes - i * 8);
- return used_bytes;
-}
-
static inline bool ata_ok(u8 status)
{
return ((status & (ATA_BUSY | ATA_DRDY | ATA_DF | ATA_DRQ | ATA_ERR))
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index cbdbf34..3bf5d33 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -343,16 +343,7 @@ static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd)
*/
static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
{
- char *p;
-
- p = cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
- if (!p) {
- strncpy(buf, "<unavailable>", buflen);
- return -ENAMETOOLONG;
- }
-
- memmove(buf, p, buf + buflen - p);
- return 0;
+ return cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
}
/**
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index edcd96d..01c1487 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -234,6 +234,7 @@ void bpf_register_map_type(struct bpf_map_type_list *tl);
struct bpf_prog *bpf_prog_get(u32 ufd);
struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type);
struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i);
+void bpf_prog_sub(struct bpf_prog *prog, int i);
struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog);
void bpf_prog_put(struct bpf_prog *prog);
@@ -303,6 +304,10 @@ static inline struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i)
return ERR_PTR(-EOPNOTSUPP);
}
+static inline void bpf_prog_sub(struct bpf_prog *prog, int i)
+{
+}
+
static inline void bpf_prog_put(struct bpf_prog *prog)
{
}
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 60def78..848dc50 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -13,6 +13,7 @@
#define PHY_ID_BCM5241 0x0143bc30
#define PHY_ID_BCMAC131 0x0143bc70
#define PHY_ID_BCM5481 0x0143bca0
+#define PHY_ID_BCM54810 0x03625d00
#define PHY_ID_BCM5482 0x0143bcb0
#define PHY_ID_BCM5411 0x00206070
#define PHY_ID_BCM5421 0x002060e0
@@ -56,6 +57,7 @@
#define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00002000
#define PHY_BRCM_CLEAR_RGMII_MODE 0x00004000
#define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00008000
+
/* Broadcom BCM7xxx specific workarounds */
#define PHY_BRCM_7XXX_REV(x) (((x) >> 8) & 0xff)
#define PHY_BRCM_7XXX_PATCH(x) ((x) & 0xff)
@@ -110,6 +112,8 @@
#define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX 0x0200
#define MII_BCM54XX_AUXCTL_MISC_RDSEL_MISC 0x7000
#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x0007
+#define MII_BCM54XX_AUXCTL_SHDWSEL_READ_SHIFT 12
+#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN (1 << 8)
#define MII_BCM54XX_AUXCTL_SHDWSEL_MASK 0x0007
@@ -191,6 +195,12 @@
#define BCM5482_SSD_SGMII_SLAVE_EN 0x0002 /* Slave mode enable */
#define BCM5482_SSD_SGMII_SLAVE_AD 0x0001 /* Slave auto-detection */
+/* BCM54810 Registers */
+#define BCM54810_EXP_BROADREACH_LRE_MISC_CTL (MII_BCM54XX_EXP_SEL_ER + 0x90)
+#define BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN (1 << 0)
+#define BCM54810_SHD_CLK_CTL 0x3
+#define BCM54810_SHD_CLK_CTL_GTXCLK_EN (1 << 9)
+
/*****************************************************************************/
/* Fast Ethernet Transceiver definitions. */
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 96337b1..a8e6634 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -258,6 +258,8 @@ struct ceph_watch_item {
struct ceph_entity_addr addr;
};
+#define CEPH_LINGER_ID_START 0xffff000000000000ULL
+
struct ceph_osd_client {
struct ceph_client *client;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 440a721..c83c23f 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -97,7 +97,7 @@ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
int cgroup_rm_cftypes(struct cftype *cfts);
void cgroup_file_notify(struct cgroup_file *cfile);
-char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
+int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry);
int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *tsk);
@@ -555,8 +555,7 @@ static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen)
return kernfs_name(cgrp->kn, buf, buflen);
}
-static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf,
- size_t buflen)
+static inline int cgroup_path(struct cgroup *cgrp, char *buf, size_t buflen)
{
return kernfs_path(cgrp->kn, buf, buflen);
}
@@ -658,8 +657,8 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
struct user_namespace *user_ns,
struct cgroup_namespace *old_ns);
-char *cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
- struct cgroup_namespace *ns);
+int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
+ struct cgroup_namespace *ns);
#else /* !CONFIG_CGROUPS */
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index af59638..a428aec 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -785,7 +785,7 @@ extern struct of_device_id __clk_of_table;
* routines, one at of_clk_init(), and one at platform device probe
*/
#define CLK_OF_DECLARE_DRIVER(name, compat, fn) \
- static void name##_of_clk_init_driver(struct device_node *np) \
+ static void __init name##_of_clk_init_driver(struct device_node *np) \
{ \
of_node_clear_flag(np, OF_POPULATED); \
fn(np); \
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 573c5a1..432f5c9 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -188,6 +188,13 @@
#endif /* GCC_VERSION >= 40300 */
#if GCC_VERSION >= 40500
+
+#ifndef __CHECKER__
+#ifdef LATENT_ENTROPY_PLUGIN
+#define __latent_entropy __attribute__((latent_entropy))
+#endif
+#endif
+
/*
* Mark a position in code as unreachable. This can be used to
* suppress control flow warnings after asm blocks that transfer
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 6685698..cf0fa5d 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -182,6 +182,29 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
# define unreachable() do { } while (1)
#endif
+/*
+ * KENTRY - kernel entry point
+ * This can be used to annotate symbols (functions or data) that are used
+ * without their linker symbol being referenced explicitly. For example,
+ * interrupt vector handlers, or functions in the kernel image that are found
+ * programatically.
+ *
+ * Not required for symbols exported with EXPORT_SYMBOL, or initcalls. Those
+ * are handled in their own way (with KEEP() in linker scripts).
+ *
+ * KENTRY can be avoided if the symbols in question are marked as KEEP() in the
+ * linker script. For example an architecture could KEEP() its entire
+ * boot/exception vector code rather than annotate each function and data.
+ */
+#ifndef KENTRY
+# define KENTRY(sym) \
+ extern typeof(sym) sym; \
+ static const unsigned long __kentry_##sym \
+ __used \
+ __attribute__((section("___kentry" "+" #sym ), used)) \
+ = (unsigned long)&sym;
+#endif
+
#ifndef RELOC_HIDE
# define RELOC_HIDE(ptr, off) \
({ unsigned long __ptr; \
@@ -406,6 +429,10 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
# define __attribute_const__ /* unimplemented */
#endif
+#ifndef __latent_entropy
+# define __latent_entropy
+#endif
+
/*
* Tell gcc if a function is cold. The compiler will assume any path
* directly leading to the call is unlikely.
diff --git a/include/linux/console.h b/include/linux/console.h
index 3672809..d530c46 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -173,12 +173,6 @@ static inline void console_sysfs_notify(void)
#endif
extern bool console_suspend_enabled;
-#ifdef CONFIG_OF
-extern void console_set_by_of(void);
-#else
-static inline void console_set_by_of(void) {}
-#endif
-
/* Suspend and resume console messages over PM events */
extern void suspend_console(void);
extern void resume_console(void);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 631ba33b..32dc0cbd 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -639,19 +639,19 @@ static inline int cpufreq_table_find_index_al(struct cpufreq_policy *policy,
unsigned int target_freq)
{
struct cpufreq_frequency_table *table = policy->freq_table;
+ struct cpufreq_frequency_table *pos, *best = table - 1;
unsigned int freq;
- int i, best = -1;
- for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
- freq = table[i].frequency;
+ cpufreq_for_each_valid_entry(pos, table) {
+ freq = pos->frequency;
if (freq >= target_freq)
- return i;
+ return pos - table;
- best = i;
+ best = pos;
}
- return best;
+ return best - table;
}
/* Find lowest freq at or above target in a table in descending order */
@@ -659,28 +659,28 @@ static inline int cpufreq_table_find_index_dl(struct cpufreq_policy *policy,
unsigned int target_freq)
{
struct cpufreq_frequency_table *table = policy->freq_table;
+ struct cpufreq_frequency_table *pos, *best = table - 1;
unsigned int freq;
- int i, best = -1;
- for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
- freq = table[i].frequency;
+ cpufreq_for_each_valid_entry(pos, table) {
+ freq = pos->frequency;
if (freq == target_freq)
- return i;
+ return pos - table;
if (freq > target_freq) {
- best = i;
+ best = pos;
continue;
}
/* No freq found above target_freq */
- if (best == -1)
- return i;
+ if (best == table - 1)
+ return pos - table;
- return best;
+ return best - table;
}
- return best;
+ return best - table;
}
/* Works only on sorted freq-tables */
@@ -700,28 +700,28 @@ static inline int cpufreq_table_find_index_ah(struct cpufreq_policy *policy,
unsigned int target_freq)
{
struct cpufreq_frequency_table *table = policy->freq_table;
+ struct cpufreq_frequency_table *pos, *best = table - 1;
unsigned int freq;
- int i, best = -1;
- for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
- freq = table[i].frequency;
+ cpufreq_for_each_valid_entry(pos, table) {
+ freq = pos->frequency;
if (freq == target_freq)
- return i;
+ return pos - table;
if (freq < target_freq) {
- best = i;
+ best = pos;
continue;
}
/* No freq found below target_freq */
- if (best == -1)
- return i;
+ if (best == table - 1)
+ return pos - table;
- return best;
+ return best - table;
}
- return best;
+ return best - table;
}
/* Find highest freq at or below target in a table in descending order */
@@ -729,19 +729,19 @@ static inline int cpufreq_table_find_index_dh(struct cpufreq_policy *policy,
unsigned int target_freq)
{
struct cpufreq_frequency_table *table = policy->freq_table;
+ struct cpufreq_frequency_table *pos, *best = table - 1;
unsigned int freq;
- int i, best = -1;
- for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
- freq = table[i].frequency;
+ cpufreq_for_each_valid_entry(pos, table) {
+ freq = pos->frequency;
if (freq <= target_freq)
- return i;
+ return pos - table;
- best = i;
+ best = pos;
}
- return best;
+ return best - table;
}
/* Works only on sorted freq-tables */
@@ -761,32 +761,32 @@ static inline int cpufreq_table_find_index_ac(struct cpufreq_policy *policy,
unsigned int target_freq)
{
struct cpufreq_frequency_table *table = policy->freq_table;
+ struct cpufreq_frequency_table *pos, *best = table - 1;
unsigned int freq;
- int i, best = -1;
- for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
- freq = table[i].frequency;
+ cpufreq_for_each_valid_entry(pos, table) {
+ freq = pos->frequency;
if (freq == target_freq)
- return i;
+ return pos - table;
if (freq < target_freq) {
- best = i;
+ best = pos;
continue;
}
/* No freq found below target_freq */
- if (best == -1)
- return i;
+ if (best == table - 1)
+ return pos - table;
/* Choose the closest freq */
- if (target_freq - table[best].frequency > freq - target_freq)
- return i;
+ if (target_freq - best->frequency > freq - target_freq)
+ return pos - table;
- return best;
+ return best - table;
}
- return best;
+ return best - table;
}
/* Find closest freq to target in a table in descending order */
@@ -794,32 +794,32 @@ static inline int cpufreq_table_find_index_dc(struct cpufreq_policy *policy,
unsigned int target_freq)
{
struct cpufreq_frequency_table *table = policy->freq_table;
+ struct cpufreq_frequency_table *pos, *best = table - 1;
unsigned int freq;
- int i, best = -1;
- for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
- freq = table[i].frequency;
+ cpufreq_for_each_valid_entry(pos, table) {
+ freq = pos->frequency;
if (freq == target_freq)
- return i;
+ return pos - table;
if (freq > target_freq) {
- best = i;
+ best = pos;
continue;
}
/* No freq found above target_freq */
- if (best == -1)
- return i;
+ if (best == table - 1)
+ return pos - table;
/* Choose the closest freq */
- if (table[best].frequency - target_freq > target_freq - freq)
- return i;
+ if (best->frequency - target_freq > target_freq - freq)
+ return pos - table;
- return best;
+ return best - table;
}
- return best;
+ return best - table;
}
/* Works only on sorted freq-tables */
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 9b207a8..afe641c 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -81,6 +81,7 @@ enum cpuhp_state {
CPUHP_AP_ARM_ARCH_TIMER_STARTING,
CPUHP_AP_ARM_GLOBAL_TIMER_STARTING,
CPUHP_AP_DUMMY_TIMER_STARTING,
+ CPUHP_AP_JCORE_TIMER_STARTING,
CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING,
CPUHP_AP_ARM_TWD_STARTING,
CPUHP_AP_METAG_TIMER_STARTING,
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index 4d3f0d1..bf1907d 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -52,7 +52,8 @@ extern struct srcu_struct debugfs_srcu;
* Must only be called under the protection established by
* debugfs_use_file_start().
*/
-static inline const struct file_operations *debugfs_real_fops(struct file *filp)
+static inline const struct file_operations *
+debugfs_real_fops(const struct file *filp)
__must_hold(&debugfs_srcu)
{
/*
diff --git a/include/linux/device.h b/include/linux/device.h
index bc41e87..a00105c 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -698,6 +698,25 @@ static inline int devm_add_action_or_reset(struct device *dev,
return ret;
}
+/**
+ * devm_alloc_percpu - Resource-managed alloc_percpu
+ * @dev: Device to allocate per-cpu memory for
+ * @type: Type to allocate per-cpu memory for
+ *
+ * Managed alloc_percpu. Per-cpu memory allocated with this function is
+ * automatically freed on driver detach.
+ *
+ * RETURNS:
+ * Pointer to allocated memory on success, NULL on failure.
+ */
+#define devm_alloc_percpu(dev, type) \
+ ((typeof(type) __percpu *)__devm_alloc_percpu((dev), sizeof(type), \
+ __alignof__(type)))
+
+void __percpu *__devm_alloc_percpu(struct device *dev, size_t size,
+ size_t align);
+void devm_free_percpu(struct device *dev, void __percpu *pdata);
+
struct device_dma_parameters {
/*
* a low level driver may set these to teach IOMMU code about
diff --git a/include/linux/export.h b/include/linux/export.h
index d7df492..2a0f61f 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -1,5 +1,6 @@
#ifndef _LINUX_EXPORT_H
#define _LINUX_EXPORT_H
+
/*
* Export symbols from the kernel to modules. Forked from module.h
* to reduce the amount of pointless cruft we feed to gcc when only
@@ -42,27 +43,26 @@ extern struct module __this_module;
#ifdef CONFIG_MODVERSIONS
/* Mark the CRC weak since genksyms apparently decides not to
* generate a checksums for some symbols */
-#define __CRC_SYMBOL(sym, sec) \
- extern __visible void *__crc_##sym __attribute__((weak)); \
- static const unsigned long __kcrctab_##sym \
- __used \
- __attribute__((section("___kcrctab" sec "+" #sym), unused)) \
+#define __CRC_SYMBOL(sym, sec) \
+ extern __visible void *__crc_##sym __attribute__((weak)); \
+ static const unsigned long __kcrctab_##sym \
+ __used \
+ __attribute__((section("___kcrctab" sec "+" #sym), used)) \
= (unsigned long) &__crc_##sym;
#else
#define __CRC_SYMBOL(sym, sec)
#endif
/* For every exported symbol, place a struct in the __ksymtab section */
-#define ___EXPORT_SYMBOL(sym, sec) \
- extern typeof(sym) sym; \
- __CRC_SYMBOL(sym, sec) \
- static const char __kstrtab_##sym[] \
- __attribute__((section("__ksymtab_strings"), aligned(1))) \
- = VMLINUX_SYMBOL_STR(sym); \
- extern const struct kernel_symbol __ksymtab_##sym; \
- __visible const struct kernel_symbol __ksymtab_##sym \
- __used \
- __attribute__((section("___ksymtab" sec "+" #sym), unused)) \
+#define ___EXPORT_SYMBOL(sym, sec) \
+ extern typeof(sym) sym; \
+ __CRC_SYMBOL(sym, sec) \
+ static const char __kstrtab_##sym[] \
+ __attribute__((section("__ksymtab_strings"), aligned(1))) \
+ = VMLINUX_SYMBOL_STR(sym); \
+ static const struct kernel_symbol __ksymtab_##sym \
+ __used \
+ __attribute__((section("___ksymtab" sec "+" #sym), used)) \
= { (unsigned long)&sym, __kstrtab_##sym }
#if defined(__KSYM_DEPS__)
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index aca2a6a..6e84b2cae 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -105,7 +105,7 @@ struct files_struct *get_files_struct(struct task_struct *);
void put_files_struct(struct files_struct *fs);
void reset_files_struct(struct files_struct *);
int unshare_files(struct files_struct **);
-struct files_struct *dup_fd(struct files_struct *, int *);
+struct files_struct *dup_fd(struct files_struct *, int *) __latent_entropy;
void do_close_on_exec(struct files_struct *);
int iterate_fd(struct files_struct *, unsigned,
int (*)(const void *, struct file *, unsigned),
diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h
index c46d2aa..1d18af0 100644
--- a/include/linux/frontswap.h
+++ b/include/linux/frontswap.h
@@ -106,8 +106,9 @@ static inline void frontswap_invalidate_area(unsigned type)
static inline void frontswap_init(unsigned type, unsigned long *map)
{
- if (frontswap_enabled())
- __frontswap_init(type, map);
+#ifdef CONFIG_FRONTSWAP
+ __frontswap_init(type, map);
+#endif
}
#endif /* _LINUX_FRONTSWAP_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bc65d59..dc0478c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -321,6 +321,7 @@ struct writeback_control;
#define IOCB_HIPRI (1 << 3)
#define IOCB_DSYNC (1 << 4)
#define IOCB_SYNC (1 << 5)
+#define IOCB_WRITE (1 << 6)
struct kiocb {
struct file *ki_filp;
@@ -1709,7 +1710,6 @@ struct file_operations {
int (*flush) (struct file *, fl_owner_t id);
int (*release) (struct inode *, struct file *);
int (*fsync) (struct file *, loff_t, loff_t, int datasync);
- int (*aio_fsync) (struct kiocb *, int datasync);
int (*fasync) (int, struct file *, int);
int (*lock) (struct file *, int, struct file_lock *);
ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
@@ -2934,6 +2934,7 @@ extern int vfs_stat(const char __user *, struct kstat *);
extern int vfs_lstat(const char __user *, struct kstat *);
extern int vfs_fstat(unsigned int, struct kstat *);
extern int vfs_fstatat(int , const char __user *, struct kstat *, int);
+extern const char *vfs_get_link(struct dentry *, struct delayed_call *);
extern int __generic_block_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo,
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 1dbf52f..e0341af 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -437,7 +437,7 @@ extern void disk_flush_events(struct gendisk *disk, unsigned int mask);
extern unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask);
/* drivers/char/random.c */
-extern void add_disk_randomness(struct gendisk *disk);
+extern void add_disk_randomness(struct gendisk *disk) __latent_entropy;
extern void rand_initialize_disk(struct gendisk *disk);
static inline sector_t get_start_sect(struct block_device *bdev)
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 6824556..cd184bd 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1169,13 +1169,6 @@ int __must_check __vmbus_driver_register(struct hv_driver *hv_driver,
const char *mod_name);
void vmbus_driver_unregister(struct hv_driver *hv_driver);
-static inline const char *vmbus_dev_name(const struct hv_device *device_obj)
-{
- const struct kobject *kobj = &device_obj->device.kobj;
-
- return kobj->name;
-}
-
void vmbus_hvsock_device_unregister(struct vmbus_channel *channel);
int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj,
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index a80516f..fe84932 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1576,6 +1576,9 @@ struct ieee80211_vht_operation {
#define WLAN_AUTH_SHARED_KEY 1
#define WLAN_AUTH_FT 2
#define WLAN_AUTH_SAE 3
+#define WLAN_AUTH_FILS_SK 4
+#define WLAN_AUTH_FILS_SK_PFS 5
+#define WLAN_AUTH_FILS_PK 6
#define WLAN_AUTH_LEAP 128
#define WLAN_AUTH_CHALLENGE_LEN 128
@@ -1960,6 +1963,26 @@ enum ieee80211_eid {
WLAN_EID_VENDOR_SPECIFIC = 221,
WLAN_EID_QOS_PARAMETER = 222,
+ WLAN_EID_CAG_NUMBER = 237,
+ WLAN_EID_AP_CSN = 239,
+ WLAN_EID_FILS_INDICATION = 240,
+ WLAN_EID_DILS = 241,
+ WLAN_EID_FRAGMENT = 242,
+ WLAN_EID_EXTENSION = 255
+};
+
+/* Element ID Extensions for Element ID 255 */
+enum ieee80211_eid_ext {
+ WLAN_EID_EXT_ASSOC_DELAY_INFO = 1,
+ WLAN_EID_EXT_FILS_REQ_PARAMS = 2,
+ WLAN_EID_EXT_FILS_KEY_CONFIRM = 3,
+ WLAN_EID_EXT_FILS_SESSION = 4,
+ WLAN_EID_EXT_FILS_HLP_CONTAINER = 5,
+ WLAN_EID_EXT_FILS_IP_ADDR_ASSIGN = 6,
+ WLAN_EID_EXT_KEY_DELIVERY = 7,
+ WLAN_EID_EXT_FILS_WRAPPED_DATA = 8,
+ WLAN_EID_EXT_FILS_PUBLIC_KEY = 12,
+ WLAN_EID_EXT_FILS_NONCE = 13,
};
/* Action category code */
@@ -2073,6 +2096,9 @@ enum ieee80211_key_len {
#define IEEE80211_GCMP_MIC_LEN 16
#define IEEE80211_GCMP_PN_LEN 6
+#define FILS_NONCE_LEN 16
+#define FILS_MAX_KEK_LEN 64
+
/* Public action codes */
enum ieee80211_pub_actioncode {
WLAN_PUB_ACTION_EXT_CHANSW_ANN = 4,
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 3319d97..8d5fcd6 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -399,22 +399,6 @@ static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb)
skb->vlan_tci = 0;
return skb;
}
-/*
- * vlan_hwaccel_push_inside - pushes vlan tag to the payload
- * @skb: skbuff to tag
- *
- * Checks is tag is present in @skb->vlan_tci and if it is, it pushes the
- * VLAN tag from @skb->vlan_tci inside to the payload.
- *
- * Following the skb_unshare() example, in case of error, the calling function
- * doesn't have to worry about freeing the original skb.
- */
-static inline struct sk_buff *vlan_hwaccel_push_inside(struct sk_buff *skb)
-{
- if (skb_vlan_tag_present(skb))
- skb = __vlan_hwaccel_push_inside(skb);
- return skb;
-}
/**
* __vlan_hwaccel_put_tag - hardware accelerated VLAN inserting
diff --git a/include/linux/init.h b/include/linux/init.h
index 5a3321a..e30104c 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -39,7 +39,7 @@
/* These are for everybody (although not all archs will actually
discard it in modules) */
-#define __init __section(.init.text) __cold notrace
+#define __init __section(.init.text) __cold notrace __latent_entropy
#define __initdata __section(.init.data)
#define __initconst __section(.init.rodata)
#define __exitdata __section(.exit.data)
@@ -75,7 +75,8 @@
#define __exit __section(.exit.text) __exitused __cold notrace
/* Used for MEMORY_HOTPLUG */
-#define __meminit __section(.meminit.text) __cold notrace
+#define __meminit __section(.meminit.text) __cold notrace \
+ __latent_entropy
#define __meminitdata __section(.meminit.data)
#define __meminitconst __section(.meminit.rodata)
#define __memexit __section(.memexit.text) __exitused __cold notrace
@@ -139,24 +140,8 @@ extern bool initcall_debug;
#ifndef __ASSEMBLY__
-#ifdef CONFIG_LTO
-/* Work around a LTO gcc problem: when there is no reference to a variable
- * in a module it will be moved to the end of the program. This causes
- * reordering of initcalls which the kernel does not like.
- * Add a dummy reference function to avoid this. The function is
- * deleted by the linker.
- */
-#define LTO_REFERENCE_INITCALL(x) \
- ; /* yes this is needed */ \
- static __used __exit void *reference_##x(void) \
- { \
- return &x; \
- }
-#else
-#define LTO_REFERENCE_INITCALL(x)
-#endif
-
-/* initcalls are now grouped by functionality into separate
+/*
+ * initcalls are now grouped by functionality into separate
* subsections. Ordering inside the subsections is determined
* by link order.
* For backwards compatibility, initcall() puts the call in
@@ -164,12 +149,16 @@ extern bool initcall_debug;
*
* The `id' arg to __define_initcall() is needed so that multiple initcalls
* can point at the same handler without causing duplicate-symbol build errors.
+ *
+ * Initcalls are run by placing pointers in initcall sections that the
+ * kernel iterates at runtime. The linker can do dead code / data elimination
+ * and remove that completely, so the initcall sections have to be marked
+ * as KEEP() in the linker script.
*/
#define __define_initcall(fn, id) \
static initcall_t __initcall_##fn##id __used \
- __attribute__((__section__(".initcall" #id ".init"))) = fn; \
- LTO_REFERENCE_INITCALL(__initcall_##fn##id)
+ __attribute__((__section__(".initcall" #id ".init"))) = fn;
/*
* Early initcalls run before initializing SMP.
@@ -205,15 +194,15 @@ extern bool initcall_debug;
#define __initcall(fn) device_initcall(fn)
-#define __exitcall(fn) \
+#define __exitcall(fn) \
static exitcall_t __exitcall_##fn __exit_call = fn
-#define console_initcall(fn) \
- static initcall_t __initcall_##fn \
+#define console_initcall(fn) \
+ static initcall_t __initcall_##fn \
__used __section(.con_initcall.init) = fn
-#define security_initcall(fn) \
- static initcall_t __initcall_##fn \
+#define security_initcall(fn) \
+ static initcall_t __initcall_##fn \
__used __section(.security_initcall.init) = fn
struct obs_kernel_param {
diff --git a/include/linux/io.h b/include/linux/io.h
index e2c8419..82ef36e 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -141,4 +141,26 @@ enum {
void *memremap(resource_size_t offset, size_t size, unsigned long flags);
void memunmap(void *addr);
+/*
+ * On x86 PAT systems we have memory tracking that keeps track of
+ * the allowed mappings on memory ranges. This tracking works for
+ * all the in-kernel mapping APIs (ioremap*), but where the user
+ * wishes to map a range from a physical device into user memory
+ * the tracking won't be updated. This API is to be used by
+ * drivers which remap physical device pages into userspace,
+ * and wants to make sure they are mapped WC and not UC.
+ */
+#ifndef arch_io_reserve_memtype_wc
+static inline int arch_io_reserve_memtype_wc(resource_size_t base,
+ resource_size_t size)
+{
+ return 0;
+}
+
+static inline void arch_io_free_memtype_wc(resource_size_t base,
+ resource_size_t size)
+{
+}
+#endif
+
#endif /* _LINUX_IO_H */
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index e63e288..7892f55 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -19,11 +19,15 @@ struct vm_fault;
#define IOMAP_UNWRITTEN 0x04 /* blocks allocated @blkno in unwritten state */
/*
- * Flags for iomap mappings:
+ * Flags for all iomap mappings:
*/
-#define IOMAP_F_MERGED 0x01 /* contains multiple blocks/extents */
-#define IOMAP_F_SHARED 0x02 /* block shared with another file */
-#define IOMAP_F_NEW 0x04 /* blocks have been newly allocated */
+#define IOMAP_F_NEW 0x01 /* blocks have been newly allocated */
+
+/*
+ * Flags that only need to be reported for IOMAP_REPORT requests:
+ */
+#define IOMAP_F_MERGED 0x10 /* contains multiple blocks/extents */
+#define IOMAP_F_SHARED 0x20 /* block shared with another file */
/*
* Magic value for blkno:
@@ -42,8 +46,9 @@ struct iomap {
/*
* Flags for iomap_begin / iomap_end. No flag implies a read.
*/
-#define IOMAP_WRITE (1 << 0)
-#define IOMAP_ZERO (1 << 1)
+#define IOMAP_WRITE (1 << 0) /* writing, must allocate blocks */
+#define IOMAP_ZERO (1 << 1) /* zeroing operation, may skip holes */
+#define IOMAP_REPORT (1 << 2) /* report extent status, e.g. FIEMAP */
struct iomap_ops {
/*
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 7e9a789..3f95233 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -64,6 +64,10 @@ struct ipv6_devconf {
} stable_secret;
__s32 use_oif_addrs_only;
__s32 keep_addr_on_down;
+ __s32 seg6_enabled;
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ __s32 seg6_require_hmac;
+#endif
struct ctl_table_header *sysctl_header;
};
@@ -123,12 +127,12 @@ struct inet6_skb_parm {
};
#if defined(CONFIG_NET_L3_MASTER_DEV)
-static inline bool skb_l3mdev_slave(__u16 flags)
+static inline bool ipv6_l3mdev_skb(__u16 flags)
{
return flags & IP6SKB_L3SLAVE;
}
#else
-static inline bool skb_l3mdev_slave(__u16 flags)
+static inline bool ipv6_l3mdev_skb(__u16 flags)
{
return false;
}
@@ -139,11 +143,22 @@ static inline bool skb_l3mdev_slave(__u16 flags)
static inline int inet6_iif(const struct sk_buff *skb)
{
- bool l3_slave = skb_l3mdev_slave(IP6CB(skb)->flags);
+ bool l3_slave = ipv6_l3mdev_skb(IP6CB(skb)->flags);
return l3_slave ? skb->skb_iif : IP6CB(skb)->iif;
}
+/* can not be used in TCP layer after tcp_v6_fill_cb */
+static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb)
+{
+#if defined(CONFIG_NET_L3_MASTER_DEV)
+ if (!net->ipv4.sysctl_tcp_l3mdev_accept &&
+ skb && ipv6_l3mdev_skb(IP6CB(skb)->flags))
+ return true;
+#endif
+ return false;
+}
+
struct tcp6_request_sock {
struct tcp_request_sock tcp6rsk_tcp;
};
@@ -218,8 +233,9 @@ struct ipv6_pinfo {
rxflow:1,
rxtclass:1,
rxpmtu:1,
- rxorigdstaddr:1;
- /* 2 bits hole */
+ rxorigdstaddr:1,
+ recvfragsize:1;
+ /* 1 bits hole */
} bits;
__u16 all;
} rxopt;
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 8361c8d..b7e3431 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -290,7 +290,7 @@
#define GITS_BASER_TYPE_SHIFT (56)
#define GITS_BASER_TYPE(r) (((r) >> GITS_BASER_TYPE_SHIFT) & 7)
#define GITS_BASER_ENTRY_SIZE_SHIFT (48)
-#define GITS_BASER_ENTRY_SIZE(r) ((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0xff) + 1)
+#define GITS_BASER_ENTRY_SIZE(r) ((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0x1f) + 1)
#define GITS_BASER_SHAREABILITY_SHIFT (10)
#define GITS_BASER_InnerShareable \
GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index d600303..820c0ad 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -44,6 +44,7 @@ static inline void kasan_disable_current(void)
void kasan_unpoison_shadow(const void *address, size_t size);
void kasan_unpoison_task_stack(struct task_struct *task);
+void kasan_unpoison_stack_above_sp_to(const void *watermark);
void kasan_alloc_pages(struct page *page, unsigned int order);
void kasan_free_pages(struct page *page, unsigned int order);
@@ -85,6 +86,7 @@ size_t kasan_metadata_size(struct kmem_cache *cache);
static inline void kasan_unpoison_shadow(const void *address, size_t size) {}
static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
+static inline void kasan_unpoison_stack_above_sp_to(const void *watermark) {}
static inline void kasan_enable_current(void) {}
static inline void kasan_disable_current(void) {}
diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h
index 15ec117..8f2e059 100644
--- a/include/linux/kconfig.h
+++ b/include/linux/kconfig.h
@@ -31,7 +31,6 @@
* When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when
* the last step cherry picks the 2nd arg, we get a zero.
*/
-#define config_enabled(cfg) ___is_defined(cfg)
#define __is_defined(x) ___is_defined(x)
#define ___is_defined(val) ____is_defined(__ARG_PLACEHOLDER_##val)
#define ____is_defined(arg1_or_junk) __take_second_arg(arg1_or_junk 1, 0)
@@ -41,13 +40,13 @@
* otherwise. For boolean options, this is equivalent to
* IS_ENABLED(CONFIG_FOO).
*/
-#define IS_BUILTIN(option) config_enabled(option)
+#define IS_BUILTIN(option) __is_defined(option)
/*
* IS_MODULE(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'm', 0
* otherwise.
*/
-#define IS_MODULE(option) config_enabled(option##_MODULE)
+#define IS_MODULE(option) __is_defined(option##_MODULE)
/*
* IS_REACHABLE(CONFIG_FOO) evaluates to 1 if the currently compiled
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 96356ef..7056238 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -269,10 +269,8 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn)
}
int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen);
-size_t kernfs_path_len(struct kernfs_node *kn);
int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn,
char *buf, size_t buflen);
-char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen);
void pr_cont_kernfs_name(struct kernfs_node *kn);
void pr_cont_kernfs_path(struct kernfs_node *kn);
struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn);
@@ -341,12 +339,10 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn)
static inline int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
{ return -ENOSYS; }
-static inline size_t kernfs_path_len(struct kernfs_node *kn)
-{ return 0; }
-
-static inline char *kernfs_path(struct kernfs_node *kn, char *buf,
- size_t buflen)
-{ return NULL; }
+static inline int kernfs_path_from_node(struct kernfs_node *root_kn,
+ struct kernfs_node *kn,
+ char *buf, size_t buflen)
+{ return -ENOSYS; }
static inline void pr_cont_kernfs_name(struct kernfs_node *kn) { }
static inline void pr_cont_kernfs_path(struct kernfs_node *kn) { }
@@ -436,6 +432,22 @@ static inline void kernfs_init(void) { }
#endif /* CONFIG_KERNFS */
+/**
+ * kernfs_path - build full path of a given node
+ * @kn: kernfs_node of interest
+ * @buf: buffer to copy @kn's name into
+ * @buflen: size of @buf
+ *
+ * Builds and returns the full path of @kn in @buf of @buflen bytes. The
+ * path is built from the end of @buf so the returned pointer usually
+ * doesn't match @buf. If @buf isn't long enough, @buf is nul terminated
+ * and %NULL is returned.
+ */
+static inline int kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen)
+{
+ return kernfs_path_from_node(kn, NULL, buf, buflen);
+}
+
static inline struct kernfs_node *
kernfs_find_and_get(struct kernfs_node *kn, const char *name)
{
diff --git a/include/linux/libata.h b/include/linux/libata.h
index e37d4f9..616eef4 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -46,7 +46,8 @@
#ifdef CONFIG_ATA_NONSTANDARD
#include <asm/libata-portmap.h>
#else
-#include <asm-generic/libata-portmap.h>
+#define ATA_PRIMARY_IRQ(dev) 14
+#define ATA_SECONDARY_IRQ(dev) 15
#endif
/*
diff --git a/include/linux/mbus.h b/include/linux/mbus.h
index 2931aa4..0d3f14f 100644
--- a/include/linux/mbus.h
+++ b/include/linux/mbus.h
@@ -82,6 +82,7 @@ static inline int mvebu_mbus_get_io_win_info(phys_addr_t phyaddr, u32 *size,
}
#endif
+#ifdef CONFIG_MVEBU_MBUS
int mvebu_mbus_save_cpu_target(u32 __iomem *store_addr);
void mvebu_mbus_get_pcie_mem_aperture(struct resource *res);
void mvebu_mbus_get_pcie_io_aperture(struct resource *res);
@@ -97,5 +98,12 @@ int mvebu_mbus_init(const char *soc, phys_addr_t mbus_phys_base,
size_t mbus_size, phys_addr_t sdram_phys_base,
size_t sdram_size);
int mvebu_mbus_dt_init(bool is_coherent);
+#else
+static inline int mvebu_mbus_get_dram_win_info(phys_addr_t phyaddr, u8 *target,
+ u8 *attr)
+{
+ return -EINVAL;
+}
+#endif /* CONFIG_MVEBU_MBUS */
#endif /* __LINUX_MBUS_H */
diff --git a/include/linux/mii.h b/include/linux/mii.h
index 47492c96..1629a0c 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -31,7 +31,11 @@ struct mii_if_info {
extern int mii_link_ok (struct mii_if_info *mii);
extern int mii_nway_restart (struct mii_if_info *mii);
extern int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd);
+extern int mii_ethtool_get_link_ksettings(
+ struct mii_if_info *mii, struct ethtool_link_ksettings *cmd);
extern int mii_ethtool_sset(struct mii_if_info *mii, struct ethtool_cmd *ecmd);
+extern int mii_ethtool_set_link_ksettings(
+ struct mii_if_info *mii, const struct ethtool_link_ksettings *cmd);
extern int mii_check_gmii_support(struct mii_if_info *mii);
extern void mii_check_link (struct mii_if_info *mii);
extern unsigned int mii_check_media (struct mii_if_info *mii,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index f6a16429..3be7abd 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1399,7 +1399,8 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
u32 *lkey, u32 *rkey);
int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
int mlx4_SYNC_TPT(struct mlx4_dev *dev);
-int mlx4_test_interrupts(struct mlx4_dev *dev);
+int mlx4_test_interrupt(struct mlx4_dev *dev, int vector);
+int mlx4_test_async(struct mlx4_dev *dev);
int mlx4_query_diag_counters(struct mlx4_dev *dev, u8 op_modifier,
const u32 offset[], u32 value[],
size_t array_len, u8 port);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 5827614..9f48936 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -277,6 +277,7 @@ enum mlx5_event {
MLX5_EVENT_TYPE_INTERNAL_ERROR = 0x08,
MLX5_EVENT_TYPE_PORT_CHANGE = 0x09,
MLX5_EVENT_TYPE_GPIO_EVENT = 0x15,
+ MLX5_EVENT_TYPE_PORT_MODULE_EVENT = 0x16,
MLX5_EVENT_TYPE_REMOTE_CONFIG = 0x19,
MLX5_EVENT_TYPE_DB_BF_CONGESTION = 0x1a,
@@ -552,6 +553,15 @@ struct mlx5_eqe_vport_change {
__be32 rsvd1[6];
} __packed;
+struct mlx5_eqe_port_module {
+ u8 reserved_at_0[1];
+ u8 module;
+ u8 reserved_at_2[1];
+ u8 module_status;
+ u8 reserved_at_4[2];
+ u8 error_type;
+} __packed;
+
union ev_data {
__be32 raw[7];
struct mlx5_eqe_cmd cmd;
@@ -565,6 +575,7 @@ union ev_data {
struct mlx5_eqe_page_req req_pages;
struct mlx5_eqe_page_fault page_fault;
struct mlx5_eqe_vport_change vport_change;
+ struct mlx5_eqe_port_module port_module;
} __packed;
struct mlx5_eqe {
@@ -1060,6 +1071,11 @@ enum {
MLX5_INFINIBAND_PORT_COUNTERS_GROUP = 0x20,
};
+enum {
+ MLX5_PCIE_PERFORMANCE_COUNTERS_GROUP = 0x0,
+ MLX5_PCIE_TIMERS_AND_STATES_COUNTERS_GROUP = 0x2,
+};
+
static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz)
{
if (pkey_sz > MLX5_MAX_LOG_PKEY_TABLE)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 85c4786..ae1f451 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -121,6 +121,7 @@ enum {
MLX5_REG_HOST_ENDIANNESS = 0x7004,
MLX5_REG_MCIA = 0x9014,
MLX5_REG_MLCR = 0x902b,
+ MLX5_REG_MPCNT = 0x9051,
};
enum {
@@ -208,7 +209,7 @@ struct mlx5_cmd_first {
struct mlx5_cmd_msg {
struct list_head list;
- struct cache_ent *cache;
+ struct cmd_msg_cache *parent;
u32 len;
struct mlx5_cmd_first first;
struct mlx5_cmd_mailbox *next;
@@ -228,17 +229,17 @@ struct mlx5_cmd_debug {
u16 outlen;
};
-struct cache_ent {
+struct cmd_msg_cache {
/* protect block chain allocations
*/
spinlock_t lock;
struct list_head head;
+ unsigned int max_inbox_size;
+ unsigned int num_ent;
};
-struct cmd_msg_cache {
- struct cache_ent large;
- struct cache_ent med;
-
+enum {
+ MLX5_NUM_COMMAND_CACHES = 5,
};
struct mlx5_cmd_stats {
@@ -281,7 +282,7 @@ struct mlx5_cmd {
struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS];
struct pci_pool *pool;
struct mlx5_cmd_debug dbg;
- struct cmd_msg_cache cache;
+ struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES];
int checksum_disabled;
struct mlx5_cmd_stats stats[MLX5_CMD_OP_MAX];
};
@@ -418,8 +419,12 @@ struct mlx5_core_health {
u32 prev;
int miss_counter;
bool sick;
+ /* wq spinlock to synchronize draining */
+ spinlock_t wq_lock;
struct workqueue_struct *wq;
+ unsigned long flags;
struct work_struct work;
+ struct delayed_work recover_work;
};
struct mlx5_cq_table {
@@ -494,6 +499,31 @@ struct mlx5_rl_table {
struct mlx5_rl_entry *rl_entry;
};
+enum port_module_event_status_type {
+ MLX5_MODULE_STATUS_PLUGGED = 0x1,
+ MLX5_MODULE_STATUS_UNPLUGGED = 0x2,
+ MLX5_MODULE_STATUS_ERROR = 0x3,
+ MLX5_MODULE_STATUS_NUM = 0x3,
+};
+
+enum port_module_event_error_type {
+ MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED,
+ MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX_CABLE_MODULE,
+ MLX5_MODULE_EVENT_ERROR_BUS_STUCK,
+ MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT,
+ MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST,
+ MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER,
+ MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE,
+ MLX5_MODULE_EVENT_ERROR_BAD_CABLE,
+ MLX5_MODULE_EVENT_ERROR_UNKNOWN,
+ MLX5_MODULE_EVENT_ERROR_NUM,
+};
+
+struct mlx5_port_module_event_stats {
+ u64 status_counters[MLX5_MODULE_STATUS_NUM];
+ u64 error_counters[MLX5_MODULE_EVENT_ERROR_NUM];
+};
+
struct mlx5_priv {
char name[MLX5_MAX_NAME_LEN];
struct mlx5_eq_table eq_table;
@@ -555,6 +585,8 @@ struct mlx5_priv {
unsigned long pci_dev_data;
struct mlx5_fc_stats fc_stats;
struct mlx5_rl_table rl_table;
+
+ struct mlx5_port_module_event_stats pme_stats;
};
enum mlx5_device_state {
@@ -626,10 +658,6 @@ struct mlx5_db {
};
enum {
- MLX5_DB_PER_PAGE = PAGE_SIZE / L1_CACHE_BYTES,
-};
-
-enum {
MLX5_COMP_EQ_SIZE = 1024,
};
@@ -638,13 +666,6 @@ enum {
MLX5_PTYS_EN = 1 << 2,
};
-struct mlx5_db_pgdir {
- struct list_head list;
- DECLARE_BITMAP(bitmap, MLX5_DB_PER_PAGE);
- __be32 *db_page;
- dma_addr_t db_dma;
-};
-
typedef void (*mlx5_cmd_cbk_t)(int status, void *context);
struct mlx5_cmd_work_ent {
@@ -789,6 +810,7 @@ void mlx5_health_cleanup(struct mlx5_core_dev *dev);
int mlx5_health_init(struct mlx5_core_dev *dev);
void mlx5_start_health_poll(struct mlx5_core_dev *dev);
void mlx5_stop_health_poll(struct mlx5_core_dev *dev);
+void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
struct mlx5_buf *buf, int node);
int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf);
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 93ebc5e..949b24b 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -42,6 +42,10 @@ enum {
MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO = 1 << 16,
};
+enum {
+ MLX5_FLOW_TABLE_TUNNEL_EN = BIT(0),
+};
+
#define LEFTOVERS_RULE_NUM 2
static inline void build_leftovers_ft_param(int *priority,
int *n_ent,
@@ -69,8 +73,8 @@ enum mlx5_flow_namespace_type {
struct mlx5_flow_table;
struct mlx5_flow_group;
-struct mlx5_flow_rule;
struct mlx5_flow_namespace;
+struct mlx5_flow_handle;
struct mlx5_flow_spec {
u8 match_criteria_enable;
@@ -97,13 +101,15 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
int prio,
int num_flow_table_entries,
int max_num_groups,
- u32 level);
+ u32 level,
+ u32 flags);
struct mlx5_flow_table *
mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
int prio,
int num_flow_table_entries,
- u32 level);
+ u32 level,
+ u32 flags);
struct mlx5_flow_table *
mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns,
int prio,
@@ -124,21 +130,28 @@ struct mlx5_flow_group *
mlx5_create_flow_group(struct mlx5_flow_table *ft, u32 *in);
void mlx5_destroy_flow_group(struct mlx5_flow_group *fg);
+struct mlx5_flow_act {
+ u32 action;
+ u32 flow_tag;
+ u32 encap_id;
+};
+
/* Single destination per rule.
* Group ID is implied by the match criteria.
*/
-struct mlx5_flow_rule *
-mlx5_add_flow_rule(struct mlx5_flow_table *ft,
- struct mlx5_flow_spec *spec,
- u32 action,
- u32 flow_tag,
- struct mlx5_flow_destination *dest);
-void mlx5_del_flow_rule(struct mlx5_flow_rule *fr);
+struct mlx5_flow_handle *
+mlx5_add_flow_rules(struct mlx5_flow_table *ft,
+ struct mlx5_flow_spec *spec,
+ struct mlx5_flow_act *flow_act,
+ struct mlx5_flow_destination *dest,
+ int dest_num);
+void mlx5_del_flow_rules(struct mlx5_flow_handle *fr);
-int mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
- struct mlx5_flow_destination *dest);
+int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler,
+ struct mlx5_flow_destination *new_dest,
+ struct mlx5_flow_destination *old_dest);
-struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_rule *rule);
+struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_handle *handler);
struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging);
void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter);
void mlx5_fc_query_cached(struct mlx5_fc *counter,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6045d4d..a5f0fbe 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -83,6 +83,7 @@ enum {
MLX5_CMD_OP_SET_HCA_CAP = 0x109,
MLX5_CMD_OP_QUERY_ISSI = 0x10a,
MLX5_CMD_OP_SET_ISSI = 0x10b,
+ MLX5_CMD_OP_SET_DRIVER_VERSION = 0x10d,
MLX5_CMD_OP_CREATE_MKEY = 0x200,
MLX5_CMD_OP_QUERY_MKEY = 0x201,
MLX5_CMD_OP_DESTROY_MKEY = 0x202,
@@ -145,6 +146,12 @@ enum {
MLX5_CMD_OP_QUERY_Q_COUNTER = 0x773,
MLX5_CMD_OP_SET_RATE_LIMIT = 0x780,
MLX5_CMD_OP_QUERY_RATE_LIMIT = 0x781,
+ MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT = 0x782,
+ MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT = 0x783,
+ MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT = 0x784,
+ MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT = 0x785,
+ MLX5_CMD_OP_CREATE_QOS_PARA_VPORT = 0x786,
+ MLX5_CMD_OP_DESTROY_QOS_PARA_VPORT = 0x787,
MLX5_CMD_OP_ALLOC_PD = 0x800,
MLX5_CMD_OP_DEALLOC_PD = 0x801,
MLX5_CMD_OP_ALLOC_UAR = 0x802,
@@ -537,13 +544,27 @@ struct mlx5_ifc_e_switch_cap_bits {
struct mlx5_ifc_qos_cap_bits {
u8 packet_pacing[0x1];
- u8 reserved_0[0x1f];
- u8 reserved_1[0x20];
+ u8 esw_scheduling[0x1];
+ u8 reserved_at_2[0x1e];
+
+ u8 reserved_at_20[0x20];
+
u8 packet_pacing_max_rate[0x20];
+
u8 packet_pacing_min_rate[0x20];
- u8 reserved_2[0x10];
+
+ u8 reserved_at_80[0x10];
u8 packet_pacing_rate_table_size[0x10];
- u8 reserved_3[0x760];
+
+ u8 esw_element_type[0x10];
+ u8 esw_tsar_type[0x10];
+
+ u8 reserved_at_c0[0x10];
+ u8 max_qos_para_vport[0x10];
+
+ u8 max_tsar_bw_share[0x20];
+
+ u8 reserved_at_100[0x700];
};
struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
@@ -804,7 +825,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 early_vf_enable[0x1];
u8 reserved_at_1a9[0x2];
u8 local_ca_ack_delay[0x5];
- u8 reserved_at_1af[0x2];
+ u8 port_module_event[0x1];
+ u8 reserved_at_1b0[0x1];
u8 ports_check[0x1];
u8 reserved_at_1b2[0x1];
u8 disable_link_up[0x1];
@@ -888,7 +910,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 log_pg_sz[0x8];
u8 bf[0x1];
- u8 reserved_at_261[0x1];
+ u8 driver_version[0x1];
u8 pad_tx_eth_packet[0x1];
u8 reserved_at_263[0x8];
u8 log_bf_reg_size[0x5];
@@ -1735,6 +1757,80 @@ struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits {
u8 reserved_at_4c0[0x300];
};
+struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits {
+ u8 life_time_counter_high[0x20];
+
+ u8 life_time_counter_low[0x20];
+
+ u8 rx_errors[0x20];
+
+ u8 tx_errors[0x20];
+
+ u8 l0_to_recovery_eieos[0x20];
+
+ u8 l0_to_recovery_ts[0x20];
+
+ u8 l0_to_recovery_framing[0x20];
+
+ u8 l0_to_recovery_retrain[0x20];
+
+ u8 crc_error_dllp[0x20];
+
+ u8 crc_error_tlp[0x20];
+
+ u8 reserved_at_140[0x680];
+};
+
+struct mlx5_ifc_pcie_tas_cntrs_grp_data_layout_bits {
+ u8 life_time_counter_high[0x20];
+
+ u8 life_time_counter_low[0x20];
+
+ u8 time_to_boot_image_start[0x20];
+
+ u8 time_to_link_image[0x20];
+
+ u8 calibration_time[0x20];
+
+ u8 time_to_first_perst[0x20];
+
+ u8 time_to_detect_state[0x20];
+
+ u8 time_to_l0[0x20];
+
+ u8 time_to_crs_en[0x20];
+
+ u8 time_to_plastic_image_start[0x20];
+
+ u8 time_to_iron_image_start[0x20];
+
+ u8 perst_handler[0x20];
+
+ u8 times_in_l1[0x20];
+
+ u8 times_in_l23[0x20];
+
+ u8 dl_down[0x20];
+
+ u8 config_cycle1usec[0x20];
+
+ u8 config_cycle2to7usec[0x20];
+
+ u8 config_cycle_8to15usec[0x20];
+
+ u8 config_cycle_16_to_63usec[0x20];
+
+ u8 config_cycle_64usec[0x20];
+
+ u8 correctable_err_msg_sent[0x20];
+
+ u8 non_fatal_err_msg_sent[0x20];
+
+ u8 fatal_err_msg_sent[0x20];
+
+ u8 reserved_at_2e0[0x4e0];
+};
+
struct mlx5_ifc_cmd_inter_comp_event_bits {
u8 command_completion_vector[0x20];
@@ -2333,6 +2429,30 @@ struct mlx5_ifc_sqc_bits {
struct mlx5_ifc_wq_bits wq;
};
+enum {
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR = 0x0,
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT = 0x1,
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC = 0x2,
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC = 0x3,
+};
+
+struct mlx5_ifc_scheduling_context_bits {
+ u8 element_type[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 element_attributes[0x20];
+
+ u8 parent_element_id[0x20];
+
+ u8 reserved_at_60[0x40];
+
+ u8 bw_share[0x20];
+
+ u8 max_average_bw[0x20];
+
+ u8 reserved_at_e0[0x120];
+};
+
struct mlx5_ifc_rqtc_bits {
u8 reserved_at_0[0xa0];
@@ -2844,7 +2964,7 @@ struct mlx5_ifc_xrqc_bits {
struct mlx5_ifc_tag_matching_topology_context_bits tag_matching_topology_context;
- u8 reserved_at_180[0x200];
+ u8 reserved_at_180[0x880];
struct mlx5_ifc_wq_bits wq;
};
@@ -2875,6 +2995,12 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits {
u8 reserved_at_0[0x7c0];
};
+union mlx5_ifc_pcie_cntrs_grp_data_layout_auto_bits {
+ struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits pcie_perf_cntrs_grp_data_layout;
+ struct mlx5_ifc_pcie_tas_cntrs_grp_data_layout_bits pcie_tas_cntrs_grp_data_layout;
+ u8 reserved_at_0[0x7c0];
+};
+
union mlx5_ifc_event_auto_bits {
struct mlx5_ifc_comp_event_bits comp_event;
struct mlx5_ifc_dct_events_bits dct_events;
@@ -2920,6 +3046,29 @@ struct mlx5_ifc_register_loopback_control_bits {
u8 reserved_at_20[0x60];
};
+struct mlx5_ifc_vport_tc_element_bits {
+ u8 traffic_class[0x4];
+ u8 reserved_at_4[0xc];
+ u8 vport_number[0x10];
+};
+
+struct mlx5_ifc_vport_element_bits {
+ u8 reserved_at_0[0x10];
+ u8 vport_number[0x10];
+};
+
+enum {
+ TSAR_ELEMENT_TSAR_TYPE_DWRR = 0x0,
+ TSAR_ELEMENT_TSAR_TYPE_ROUND_ROBIN = 0x1,
+ TSAR_ELEMENT_TSAR_TYPE_ETS = 0x2,
+};
+
+struct mlx5_ifc_tsar_element_bits {
+ u8 reserved_at_0[0x8];
+ u8 tsar_type[0x8];
+ u8 reserved_at_10[0x10];
+};
+
struct mlx5_ifc_teardown_hca_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
@@ -3540,6 +3689,39 @@ struct mlx5_ifc_query_special_contexts_in_bits {
u8 reserved_at_40[0x40];
};
+struct mlx5_ifc_query_scheduling_element_out_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 reserved_at_40[0xc0];
+
+ struct mlx5_ifc_scheduling_context_bits scheduling_context;
+
+ u8 reserved_at_300[0x100];
+};
+
+enum {
+ SCHEDULING_HIERARCHY_E_SWITCH = 0x2,
+};
+
+struct mlx5_ifc_query_scheduling_element_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 scheduling_hierarchy[0x8];
+ u8 reserved_at_48[0x18];
+
+ u8 scheduling_element_id[0x20];
+
+ u8 reserved_at_80[0x180];
+};
+
struct mlx5_ifc_query_rqt_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
@@ -3904,6 +4086,25 @@ struct mlx5_ifc_query_issi_in_bits {
u8 reserved_at_40[0x40];
};
+struct mlx5_ifc_set_driver_version_out_bits {
+ u8 status[0x8];
+ u8 reserved_0[0x18];
+
+ u8 syndrome[0x20];
+ u8 reserved_1[0x40];
+};
+
+struct mlx5_ifc_set_driver_version_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_0[0x10];
+
+ u8 reserved_1[0x10];
+ u8 op_mod[0x10];
+
+ u8 reserved_2[0x40];
+ u8 driver_version[64][0x8];
+};
+
struct mlx5_ifc_query_hca_vport_pkey_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
@@ -4725,6 +4926,43 @@ struct mlx5_ifc_modify_sq_in_bits {
struct mlx5_ifc_sqc_bits ctx;
};
+struct mlx5_ifc_modify_scheduling_element_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x1c0];
+};
+
+enum {
+ MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_BW_SHARE = 0x1,
+ MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW = 0x2,
+};
+
+struct mlx5_ifc_modify_scheduling_element_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 scheduling_hierarchy[0x8];
+ u8 reserved_at_48[0x18];
+
+ u8 scheduling_element_id[0x20];
+
+ u8 reserved_at_80[0x20];
+
+ u8 modify_bitmask[0x20];
+
+ u8 reserved_at_c0[0x40];
+
+ struct mlx5_ifc_scheduling_context_bits scheduling_context;
+
+ u8 reserved_at_300[0x100];
+};
+
struct mlx5_ifc_modify_rqt_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
@@ -5390,6 +5628,30 @@ struct mlx5_ifc_destroy_sq_in_bits {
u8 reserved_at_60[0x20];
};
+struct mlx5_ifc_destroy_scheduling_element_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x1c0];
+};
+
+struct mlx5_ifc_destroy_scheduling_element_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 scheduling_hierarchy[0x8];
+ u8 reserved_at_48[0x18];
+
+ u8 scheduling_element_id[0x20];
+
+ u8 reserved_at_80[0x180];
+};
+
struct mlx5_ifc_destroy_rqt_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
@@ -6017,6 +6279,36 @@ struct mlx5_ifc_create_sq_in_bits {
struct mlx5_ifc_sqc_bits ctx;
};
+struct mlx5_ifc_create_scheduling_element_out_bits {
+ u8 status[0x8];
+ u8 reserved_at_8[0x18];
+
+ u8 syndrome[0x20];
+
+ u8 reserved_at_40[0x40];
+
+ u8 scheduling_element_id[0x20];
+
+ u8 reserved_at_a0[0x160];
+};
+
+struct mlx5_ifc_create_scheduling_element_in_bits {
+ u8 opcode[0x10];
+ u8 reserved_at_10[0x10];
+
+ u8 reserved_at_20[0x10];
+ u8 op_mod[0x10];
+
+ u8 scheduling_hierarchy[0x8];
+ u8 reserved_at_48[0x18];
+
+ u8 reserved_at_60[0xa0];
+
+ struct mlx5_ifc_scheduling_context_bits scheduling_context;
+
+ u8 reserved_at_300[0x100];
+};
+
struct mlx5_ifc_create_rqt_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
@@ -7028,6 +7320,18 @@ struct mlx5_ifc_ppcnt_reg_bits {
union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set;
};
+struct mlx5_ifc_mpcnt_reg_bits {
+ u8 reserved_at_0[0x8];
+ u8 pcie_index[0x8];
+ u8 reserved_at_10[0xa];
+ u8 grp[0x6];
+
+ u8 clr[0x1];
+ u8 reserved_at_21[0x1f];
+
+ union mlx5_ifc_pcie_cntrs_grp_data_layout_auto_bits counter_set;
+};
+
struct mlx5_ifc_ppad_reg_bits {
u8 reserved_at_0[0x3];
u8 single_mac[0x1];
@@ -7633,6 +7937,7 @@ union mlx5_ifc_ports_control_registers_document_bits {
struct mlx5_ifc_pmtu_reg_bits pmtu_reg;
struct mlx5_ifc_ppad_reg_bits ppad_reg;
struct mlx5_ifc_ppcnt_reg_bits ppcnt_reg;
+ struct mlx5_ifc_mpcnt_reg_bits mpcnt_reg;
struct mlx5_ifc_pplm_reg_bits pplm_reg;
struct mlx5_ifc_pplr_reg_bits pplr_reg;
struct mlx5_ifc_ppsc_reg_bits ppsc_reg;
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index b3065ac..dde8c7e 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -94,6 +94,9 @@ enum mlx5e_link_mode {
#define MLX5E_PROT_MASK(link_mode) (1 << link_mode)
+#define PORT_MODULE_EVENT_MODULE_STATUS_MASK 0xF
+#define PORT_MODULE_EVENT_ERROR_TYPE_MASK 0xF
+
int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps);
int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys,
int ptys_size, int proto_mask, u8 local_port);
diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h
index 33c97dc..1cde0fd 100644
--- a/include/linux/mlx5/srq.h
+++ b/include/linux/mlx5/srq.h
@@ -55,7 +55,7 @@ struct mlx5_srq_attr {
u32 lwm;
u32 user_index;
u64 db_record;
- u64 *pas;
+ __be64 *pas;
};
struct mlx5_core_dev;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e9caec6..a92c8d7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1266,29 +1266,25 @@ static inline int fixup_user_fault(struct task_struct *tsk,
}
#endif
-extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);
+extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len,
+ unsigned int gup_flags);
extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
- void *buf, int len, int write);
+ void *buf, int len, unsigned int gup_flags);
-long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long start, unsigned long nr_pages,
- unsigned int foll_flags, struct page **pages,
- struct vm_area_struct **vmas, int *nonblocking);
long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages,
+ unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas);
long get_user_pages(unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages,
+ unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas);
long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages, int *locked);
+ unsigned int gup_flags, struct page **pages, int *locked);
long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages,
- unsigned int gup_flags);
+ struct page **pages, unsigned int gup_flags);
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages);
+ struct page **pages, unsigned int gup_flags);
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages);
@@ -1306,7 +1302,7 @@ struct frame_vector {
struct frame_vector *frame_vector_create(unsigned int nr_frames);
void frame_vector_destroy(struct frame_vector *vec);
int get_vaddr_frames(unsigned long start, unsigned int nr_pfns,
- bool write, bool force, struct frame_vector *vec);
+ unsigned int gup_flags, struct frame_vector *vec);
void put_vaddr_frames(struct frame_vector *vec);
int frame_vector_to_pages(struct frame_vector *vec);
void frame_vector_to_pfns(struct frame_vector *vec);
@@ -1391,7 +1387,7 @@ static inline int stack_guard_page_end(struct vm_area_struct *vma,
!vma_growsup(vma->vm_next, addr);
}
-int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t);
+int vma_is_stack_for_current(struct vm_area_struct *vma);
extern unsigned long move_page_tables(struct vm_area_struct *vma,
unsigned long old_addr, struct vm_area_struct *new_vma,
@@ -2232,6 +2228,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
#define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */
#define FOLL_MLOCK 0x1000 /* lock present pages */
#define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */
+#define FOLL_COW 0x4000 /* internal GUP flag */
typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
void *data);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 7f2ae99..0f088f3 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -440,33 +440,7 @@ struct zone {
seqlock_t span_seqlock;
#endif
- /*
- * wait_table -- the array holding the hash table
- * wait_table_hash_nr_entries -- the size of the hash table array
- * wait_table_bits -- wait_table_size == (1 << wait_table_bits)
- *
- * The purpose of all these is to keep track of the people
- * waiting for a page to become available and make them
- * runnable again when possible. The trouble is that this
- * consumes a lot of space, especially when so few things
- * wait on pages at a given time. So instead of using
- * per-page waitqueues, we use a waitqueue hash table.
- *
- * The bucket discipline is to sleep on the same queue when
- * colliding and wake all in that wait queue when removing.
- * When something wakes, it must check to be sure its page is
- * truly available, a la thundering herd. The cost of a
- * collision is great, but given the expected load of the
- * table, they should be so rare as to be outweighed by the
- * benefits from the saved space.
- *
- * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the
- * primary users of these fields, and in mm/page_alloc.c
- * free_area_init_core() performs the initialization of them.
- */
- wait_queue_head_t *wait_table;
- unsigned long wait_table_hash_nr_entries;
- unsigned long wait_table_bits;
+ int initialized;
/* Write-intensive fields used from the page allocator */
ZONE_PADDING(_pad1_)
@@ -546,7 +520,7 @@ static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn)
static inline bool zone_is_initialized(struct zone *zone)
{
- return !!zone->wait_table;
+ return zone->initialized;
}
static inline bool zone_is_empty(struct zone *zone)
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index c5d3d502..d8905a2 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -1184,7 +1184,7 @@ int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip,
int page);
/* Reset and initialize a NAND device */
-int nand_reset(struct nand_chip *chip);
+int nand_reset(struct nand_chip *chip, int chipnr);
/* Free resources held by the NAND device */
void nand_cleanup(struct nand_chip *chip);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 458c876..e84800e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -316,7 +316,6 @@ struct napi_struct {
unsigned int gro_count;
int (*poll)(struct napi_struct *, int);
#ifdef CONFIG_NETPOLL
- spinlock_t poll_lock;
int poll_owner;
#endif
struct net_device *dev;
@@ -334,6 +333,16 @@ enum {
NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */
NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */
NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */
+ NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */
+};
+
+enum {
+ NAPIF_STATE_SCHED = (1UL << NAPI_STATE_SCHED),
+ NAPIF_STATE_DISABLE = (1UL << NAPI_STATE_DISABLE),
+ NAPIF_STATE_NPSVC = (1UL << NAPI_STATE_NPSVC),
+ NAPIF_STATE_HASHED = (1UL << NAPI_STATE_HASHED),
+ NAPIF_STATE_NO_BUSY_POLL = (1UL << NAPI_STATE_NO_BUSY_POLL),
+ NAPIF_STATE_IN_BUSY_POLL = (1UL << NAPI_STATE_IN_BUSY_POLL),
};
enum gro_result {
@@ -453,32 +462,22 @@ static inline bool napi_reschedule(struct napi_struct *napi)
return false;
}
-void __napi_complete(struct napi_struct *n);
-void napi_complete_done(struct napi_struct *n, int work_done);
+bool __napi_complete(struct napi_struct *n);
+bool napi_complete_done(struct napi_struct *n, int work_done);
/**
* napi_complete - NAPI processing complete
* @n: NAPI context
*
* Mark NAPI processing as complete.
* Consider using napi_complete_done() instead.
+ * Return false if device should avoid rearming interrupts.
*/
-static inline void napi_complete(struct napi_struct *n)
+static inline bool napi_complete(struct napi_struct *n)
{
return napi_complete_done(n, 0);
}
/**
- * napi_hash_add - add a NAPI to global hashtable
- * @napi: NAPI context
- *
- * Generate a new napi_id and store a @napi under it in napi_hash.
- * Used for busy polling (CONFIG_NET_RX_BUSY_POLL).
- * Note: This is normally automatically done from netif_napi_add(),
- * so might disappear in a future Linux version.
- */
-void napi_hash_add(struct napi_struct *napi);
-
-/**
* napi_hash_del - remove a NAPI from global table
* @napi: NAPI context
*
@@ -732,8 +731,8 @@ struct xps_dev_maps {
struct rcu_head rcu;
struct xps_map __rcu *cpu_map[0];
};
-#define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) + \
- (nr_cpu_ids * sizeof(struct xps_map *)))
+#define XPS_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \
+ (nr_cpu_ids * (_tcs) * sizeof(struct xps_map *)))
#endif /* CONFIG_XPS */
#define TC_MAX_QUEUE 16
@@ -1920,34 +1919,10 @@ int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc)
return 0;
}
-static inline
-void netdev_reset_tc(struct net_device *dev)
-{
- dev->num_tc = 0;
- memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq));
- memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map));
-}
-
-static inline
-int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset)
-{
- if (tc >= dev->num_tc)
- return -EINVAL;
-
- dev->tc_to_txq[tc].count = count;
- dev->tc_to_txq[tc].offset = offset;
- return 0;
-}
-
-static inline
-int netdev_set_num_tc(struct net_device *dev, u8 num_tc)
-{
- if (num_tc > TC_MAX_QUEUE)
- return -EINVAL;
-
- dev->num_tc = num_tc;
- return 0;
-}
+int netdev_txq_to_tc(struct net_device *dev, unsigned int txq);
+void netdev_reset_tc(struct net_device *dev);
+int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset);
+int netdev_set_num_tc(struct net_device *dev, u8 num_tc);
static inline
int netdev_get_num_tc(struct net_device *dev)
@@ -2167,7 +2142,10 @@ struct napi_gro_cb {
/* Used to determine if flush_id can be ignored */
u8 is_atomic:1;
- /* 5 bit hole */
+ /* Number of gro_receive callbacks this packet already went through */
+ u8 recursion_counter:4;
+
+ /* 1 bit hole */
/* used to support CHECKSUM_COMPLETE for tunneling protocols */
__wsum csum;
@@ -2178,6 +2156,40 @@ struct napi_gro_cb {
#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
+#define GRO_RECURSION_LIMIT 15
+static inline int gro_recursion_inc_test(struct sk_buff *skb)
+{
+ return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT;
+}
+
+typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *);
+static inline struct sk_buff **call_gro_receive(gro_receive_t cb,
+ struct sk_buff **head,
+ struct sk_buff *skb)
+{
+ if (unlikely(gro_recursion_inc_test(skb))) {
+ NAPI_GRO_CB(skb)->flush |= 1;
+ return NULL;
+ }
+
+ return cb(head, skb);
+}
+
+typedef struct sk_buff **(*gro_receive_sk_t)(struct sock *, struct sk_buff **,
+ struct sk_buff *);
+static inline struct sk_buff **call_gro_receive_sk(gro_receive_sk_t cb,
+ struct sock *sk,
+ struct sk_buff **head,
+ struct sk_buff *skb)
+{
+ if (unlikely(gro_recursion_inc_test(skb))) {
+ NAPI_GRO_CB(skb)->flush |= 1;
+ return NULL;
+ }
+
+ return cb(sk, head, skb);
+}
+
struct packet_type {
__be16 type; /* This is really htons(ether_type). */
struct net_device *dev; /* NULL is wildcarded here */
@@ -3250,6 +3262,21 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
bool is_skb_forwardable(const struct net_device *dev,
const struct sk_buff *skb);
+static __always_inline int ____dev_forward_skb(struct net_device *dev,
+ struct sk_buff *skb)
+{
+ if (skb_orphan_frags(skb, GFP_ATOMIC) ||
+ unlikely(!is_skb_forwardable(dev, skb))) {
+ atomic_long_inc(&dev->rx_dropped);
+ kfree_skb(skb);
+ return NET_RX_DROP;
+ }
+
+ skb_scrub_packet(skb, true);
+ skb->priority = 0;
+ return 0;
+}
+
void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev);
extern int netdev_budget;
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index abc7fdc..6923014 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -49,13 +49,11 @@ struct sock;
struct nf_hook_state {
unsigned int hook;
- int thresh;
u_int8_t pf;
struct net_device *in;
struct net_device *out;
struct sock *sk;
struct net *net;
- struct nf_hook_entry __rcu *hook_entries;
int (*okfn)(struct net *, struct sock *, struct sk_buff *);
};
@@ -82,9 +80,8 @@ struct nf_hook_entry {
};
static inline void nf_hook_state_init(struct nf_hook_state *p,
- struct nf_hook_entry *hook_entry,
unsigned int hook,
- int thresh, u_int8_t pf,
+ u_int8_t pf,
struct net_device *indev,
struct net_device *outdev,
struct sock *sk,
@@ -92,13 +89,11 @@ static inline void nf_hook_state_init(struct nf_hook_state *p,
int (*okfn)(struct net *, struct sock *, struct sk_buff *))
{
p->hook = hook;
- p->thresh = thresh;
p->pf = pf;
p->in = indev;
p->out = outdev;
p->sk = sk;
p->net = net;
- RCU_INIT_POINTER(p->hook_entries, hook_entry);
p->okfn = okfn;
}
@@ -152,23 +147,20 @@ void nf_unregister_sockopt(struct nf_sockopt_ops *reg);
extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
#endif
-int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state);
+int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state,
+ struct nf_hook_entry *entry);
/**
- * nf_hook_thresh - call a netfilter hook
+ * nf_hook - call a netfilter hook
*
* Returns 1 if the hook has allowed the packet to pass. The function
* okfn must be invoked by the caller in this case. Any other return
* value indicates the packet has been consumed by the hook.
*/
-static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook,
- struct net *net,
- struct sock *sk,
- struct sk_buff *skb,
- struct net_device *indev,
- struct net_device *outdev,
- int (*okfn)(struct net *, struct sock *, struct sk_buff *),
- int thresh)
+static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net,
+ struct sock *sk, struct sk_buff *skb,
+ struct net_device *indev, struct net_device *outdev,
+ int (*okfn)(struct net *, struct sock *, struct sk_buff *))
{
struct nf_hook_entry *hook_head;
int ret = 1;
@@ -185,24 +177,16 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook,
if (hook_head) {
struct nf_hook_state state;
- nf_hook_state_init(&state, hook_head, hook, thresh,
- pf, indev, outdev, sk, net, okfn);
+ nf_hook_state_init(&state, hook, pf, indev, outdev,
+ sk, net, okfn);
- ret = nf_hook_slow(skb, &state);
+ ret = nf_hook_slow(skb, &state, hook_head);
}
rcu_read_unlock();
return ret;
}
-static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net,
- struct sock *sk, struct sk_buff *skb,
- struct net_device *indev, struct net_device *outdev,
- int (*okfn)(struct net *, struct sock *, struct sk_buff *))
-{
- return nf_hook_thresh(pf, hook, net, sk, skb, indev, outdev, okfn, INT_MIN);
-}
-
/* Activate hook; either okfn or kfree_skb called, unless a hook
returns NF_STOLEN (in which case, it's up to the hook to deal with
the consequences).
@@ -221,19 +205,6 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net,
*/
static inline int
-NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk,
- struct sk_buff *skb, struct net_device *in,
- struct net_device *out,
- int (*okfn)(struct net *, struct sock *, struct sk_buff *),
- int thresh)
-{
- int ret = nf_hook_thresh(pf, hook, net, sk, skb, in, out, okfn, thresh);
- if (ret == 1)
- ret = okfn(net, sk, skb);
- return ret;
-}
-
-static inline int
NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk,
struct sk_buff *skb, struct net_device *in, struct net_device *out,
int (*okfn)(struct net *, struct sock *, struct sk_buff *),
@@ -242,7 +213,7 @@ NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk,
int ret;
if (!cond ||
- ((ret = nf_hook_thresh(pf, hook, net, sk, skb, in, out, okfn, INT_MIN)) == 1))
+ ((ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn)) == 1))
ret = okfn(net, sk, skb);
return ret;
}
@@ -252,7 +223,10 @@ NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct
struct net_device *in, struct net_device *out,
int (*okfn)(struct net *, struct sock *, struct sk_buff *))
{
- return NF_HOOK_THRESH(pf, hook, net, sk, skb, in, out, okfn, INT_MIN);
+ int ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn);
+ if (ret == 1)
+ ret = okfn(net, sk, skb);
+ return ret;
}
/* Call setsockopt() */
diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 83b9a2e..8e42253 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -79,10 +79,12 @@ enum ip_set_ext_id {
IPSET_EXT_ID_MAX,
};
+struct ip_set;
+
/* Extension type */
struct ip_set_ext_type {
/* Destroy extension private data (can be NULL) */
- void (*destroy)(void *ext);
+ void (*destroy)(struct ip_set *set, void *ext);
enum ip_set_extension type;
enum ipset_cadt_flags flag;
/* Size and minimal alignment */
@@ -92,17 +94,6 @@ struct ip_set_ext_type {
extern const struct ip_set_ext_type ip_set_extensions[];
-struct ip_set_ext {
- u64 packets;
- u64 bytes;
- u32 timeout;
- u32 skbmark;
- u32 skbmarkmask;
- u32 skbprio;
- u16 skbqueue;
- char *comment;
-};
-
struct ip_set_counter {
atomic64_t bytes;
atomic64_t packets;
@@ -122,6 +113,15 @@ struct ip_set_skbinfo {
u32 skbmarkmask;
u32 skbprio;
u16 skbqueue;
+ u16 __pad;
+};
+
+struct ip_set_ext {
+ struct ip_set_skbinfo skbinfo;
+ u64 packets;
+ u64 bytes;
+ char *comment;
+ u32 timeout;
};
struct ip_set;
@@ -252,6 +252,10 @@ struct ip_set {
u8 flags;
/* Default timeout value, if enabled */
u32 timeout;
+ /* Number of elements (vs timeout) */
+ u32 elements;
+ /* Size of the dynamic extensions (vs timeout) */
+ size_t ext_size;
/* Element data size */
size_t dsize;
/* Offsets to extensions in elements */
@@ -268,7 +272,7 @@ ip_set_ext_destroy(struct ip_set *set, void *data)
*/
if (SET_WITH_COMMENT(set))
ip_set_extensions[IPSET_EXT_ID_COMMENT].destroy(
- ext_comment(data, set));
+ set, ext_comment(data, set));
}
static inline int
@@ -294,104 +298,6 @@ ip_set_put_flags(struct sk_buff *skb, struct ip_set *set)
return nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(cadt_flags));
}
-static inline void
-ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter)
-{
- atomic64_add((long long)bytes, &(counter)->bytes);
-}
-
-static inline void
-ip_set_add_packets(u64 packets, struct ip_set_counter *counter)
-{
- atomic64_add((long long)packets, &(counter)->packets);
-}
-
-static inline u64
-ip_set_get_bytes(const struct ip_set_counter *counter)
-{
- return (u64)atomic64_read(&(counter)->bytes);
-}
-
-static inline u64
-ip_set_get_packets(const struct ip_set_counter *counter)
-{
- return (u64)atomic64_read(&(counter)->packets);
-}
-
-static inline void
-ip_set_update_counter(struct ip_set_counter *counter,
- const struct ip_set_ext *ext,
- struct ip_set_ext *mext, u32 flags)
-{
- if (ext->packets != ULLONG_MAX &&
- !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) {
- ip_set_add_bytes(ext->bytes, counter);
- ip_set_add_packets(ext->packets, counter);
- }
- if (flags & IPSET_FLAG_MATCH_COUNTERS) {
- mext->packets = ip_set_get_packets(counter);
- mext->bytes = ip_set_get_bytes(counter);
- }
-}
-
-static inline void
-ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo,
- const struct ip_set_ext *ext,
- struct ip_set_ext *mext, u32 flags)
-{
- mext->skbmark = skbinfo->skbmark;
- mext->skbmarkmask = skbinfo->skbmarkmask;
- mext->skbprio = skbinfo->skbprio;
- mext->skbqueue = skbinfo->skbqueue;
-}
-static inline bool
-ip_set_put_skbinfo(struct sk_buff *skb, struct ip_set_skbinfo *skbinfo)
-{
- /* Send nonzero parameters only */
- return ((skbinfo->skbmark || skbinfo->skbmarkmask) &&
- nla_put_net64(skb, IPSET_ATTR_SKBMARK,
- cpu_to_be64((u64)skbinfo->skbmark << 32 |
- skbinfo->skbmarkmask),
- IPSET_ATTR_PAD)) ||
- (skbinfo->skbprio &&
- nla_put_net32(skb, IPSET_ATTR_SKBPRIO,
- cpu_to_be32(skbinfo->skbprio))) ||
- (skbinfo->skbqueue &&
- nla_put_net16(skb, IPSET_ATTR_SKBQUEUE,
- cpu_to_be16(skbinfo->skbqueue)));
-}
-
-static inline void
-ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo,
- const struct ip_set_ext *ext)
-{
- skbinfo->skbmark = ext->skbmark;
- skbinfo->skbmarkmask = ext->skbmarkmask;
- skbinfo->skbprio = ext->skbprio;
- skbinfo->skbqueue = ext->skbqueue;
-}
-
-static inline bool
-ip_set_put_counter(struct sk_buff *skb, struct ip_set_counter *counter)
-{
- return nla_put_net64(skb, IPSET_ATTR_BYTES,
- cpu_to_be64(ip_set_get_bytes(counter)),
- IPSET_ATTR_PAD) ||
- nla_put_net64(skb, IPSET_ATTR_PACKETS,
- cpu_to_be64(ip_set_get_packets(counter)),
- IPSET_ATTR_PAD);
-}
-
-static inline void
-ip_set_init_counter(struct ip_set_counter *counter,
- const struct ip_set_ext *ext)
-{
- if (ext->bytes != ULLONG_MAX)
- atomic64_set(&(counter)->bytes, (long long)(ext->bytes));
- if (ext->packets != ULLONG_MAX)
- atomic64_set(&(counter)->packets, (long long)(ext->packets));
-}
-
/* Netlink CB args */
enum {
IPSET_CB_NET = 0, /* net namespace */
@@ -431,6 +337,8 @@ extern size_t ip_set_elem_len(struct ip_set *set, struct nlattr *tb[],
size_t len, size_t align);
extern int ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[],
struct ip_set_ext *ext);
+extern int ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set,
+ const void *e, bool active);
static inline int
ip_set_get_hostipaddr4(struct nlattr *nla, u32 *ipaddr)
@@ -546,10 +454,8 @@ bitmap_bytes(u32 a, u32 b)
#include <linux/netfilter/ipset/ip_set_timeout.h>
#include <linux/netfilter/ipset/ip_set_comment.h>
-
-int
-ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set,
- const void *e, bool active);
+#include <linux/netfilter/ipset/ip_set_counter.h>
+#include <linux/netfilter/ipset/ip_set_skbinfo.h>
#define IP_SET_INIT_KEXT(skb, opt, set) \
{ .bytes = (skb)->len, .packets = 1, \
diff --git a/include/linux/netfilter/ipset/ip_set_bitmap.h b/include/linux/netfilter/ipset/ip_set_bitmap.h
index 5e4662a..366d6c0 100644
--- a/include/linux/netfilter/ipset/ip_set_bitmap.h
+++ b/include/linux/netfilter/ipset/ip_set_bitmap.h
@@ -6,8 +6,8 @@
#define IPSET_BITMAP_MAX_RANGE 0x0000FFFF
enum {
+ IPSET_ADD_STORE_PLAIN_TIMEOUT = -1,
IPSET_ADD_FAILED = 1,
- IPSET_ADD_STORE_PLAIN_TIMEOUT,
IPSET_ADD_START_STORED_TIMEOUT,
};
diff --git a/include/linux/netfilter/ipset/ip_set_comment.h b/include/linux/netfilter/ipset/ip_set_comment.h
index 8d02485..8e2bab1 100644
--- a/include/linux/netfilter/ipset/ip_set_comment.h
+++ b/include/linux/netfilter/ipset/ip_set_comment.h
@@ -20,13 +20,14 @@ ip_set_comment_uget(struct nlattr *tb)
* The kadt functions don't use the comment extensions in any way.
*/
static inline void
-ip_set_init_comment(struct ip_set_comment *comment,
+ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment,
const struct ip_set_ext *ext)
{
struct ip_set_comment_rcu *c = rcu_dereference_protected(comment->c, 1);
size_t len = ext->comment ? strlen(ext->comment) : 0;
if (unlikely(c)) {
+ set->ext_size -= sizeof(*c) + strlen(c->str) + 1;
kfree_rcu(c, rcu);
rcu_assign_pointer(comment->c, NULL);
}
@@ -34,16 +35,17 @@ ip_set_init_comment(struct ip_set_comment *comment,
return;
if (unlikely(len > IPSET_MAX_COMMENT_SIZE))
len = IPSET_MAX_COMMENT_SIZE;
- c = kzalloc(sizeof(*c) + len + 1, GFP_ATOMIC);
+ c = kmalloc(sizeof(*c) + len + 1, GFP_ATOMIC);
if (unlikely(!c))
return;
strlcpy(c->str, ext->comment, len + 1);
+ set->ext_size += sizeof(*c) + strlen(c->str) + 1;
rcu_assign_pointer(comment->c, c);
}
/* Used only when dumping a set, protected by rcu_read_lock_bh() */
static inline int
-ip_set_put_comment(struct sk_buff *skb, struct ip_set_comment *comment)
+ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment)
{
struct ip_set_comment_rcu *c = rcu_dereference_bh(comment->c);
@@ -58,13 +60,14 @@ ip_set_put_comment(struct sk_buff *skb, struct ip_set_comment *comment)
* of the set data anymore.
*/
static inline void
-ip_set_comment_free(struct ip_set_comment *comment)
+ip_set_comment_free(struct ip_set *set, struct ip_set_comment *comment)
{
struct ip_set_comment_rcu *c;
c = rcu_dereference_protected(comment->c, 1);
if (unlikely(!c))
return;
+ set->ext_size -= sizeof(*c) + strlen(c->str) + 1;
kfree_rcu(c, rcu);
rcu_assign_pointer(comment->c, NULL);
}
diff --git a/include/linux/netfilter/ipset/ip_set_counter.h b/include/linux/netfilter/ipset/ip_set_counter.h
new file mode 100644
index 0000000..bb6fba4
--- /dev/null
+++ b/include/linux/netfilter/ipset/ip_set_counter.h
@@ -0,0 +1,75 @@
+#ifndef _IP_SET_COUNTER_H
+#define _IP_SET_COUNTER_H
+
+/* Copyright (C) 2015 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifdef __KERNEL__
+
+static inline void
+ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter)
+{
+ atomic64_add((long long)bytes, &(counter)->bytes);
+}
+
+static inline void
+ip_set_add_packets(u64 packets, struct ip_set_counter *counter)
+{
+ atomic64_add((long long)packets, &(counter)->packets);
+}
+
+static inline u64
+ip_set_get_bytes(const struct ip_set_counter *counter)
+{
+ return (u64)atomic64_read(&(counter)->bytes);
+}
+
+static inline u64
+ip_set_get_packets(const struct ip_set_counter *counter)
+{
+ return (u64)atomic64_read(&(counter)->packets);
+}
+
+static inline void
+ip_set_update_counter(struct ip_set_counter *counter,
+ const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags)
+{
+ if (ext->packets != ULLONG_MAX &&
+ !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) {
+ ip_set_add_bytes(ext->bytes, counter);
+ ip_set_add_packets(ext->packets, counter);
+ }
+ if (flags & IPSET_FLAG_MATCH_COUNTERS) {
+ mext->packets = ip_set_get_packets(counter);
+ mext->bytes = ip_set_get_bytes(counter);
+ }
+}
+
+static inline bool
+ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter)
+{
+ return nla_put_net64(skb, IPSET_ATTR_BYTES,
+ cpu_to_be64(ip_set_get_bytes(counter)),
+ IPSET_ATTR_PAD) ||
+ nla_put_net64(skb, IPSET_ATTR_PACKETS,
+ cpu_to_be64(ip_set_get_packets(counter)),
+ IPSET_ATTR_PAD);
+}
+
+static inline void
+ip_set_init_counter(struct ip_set_counter *counter,
+ const struct ip_set_ext *ext)
+{
+ if (ext->bytes != ULLONG_MAX)
+ atomic64_set(&(counter)->bytes, (long long)(ext->bytes));
+ if (ext->packets != ULLONG_MAX)
+ atomic64_set(&(counter)->packets, (long long)(ext->packets));
+}
+
+#endif /* __KERNEL__ */
+#endif /* _IP_SET_COUNTER_H */
diff --git a/include/linux/netfilter/ipset/ip_set_skbinfo.h b/include/linux/netfilter/ipset/ip_set_skbinfo.h
new file mode 100644
index 0000000..29d7ef2
--- /dev/null
+++ b/include/linux/netfilter/ipset/ip_set_skbinfo.h
@@ -0,0 +1,46 @@
+#ifndef _IP_SET_SKBINFO_H
+#define _IP_SET_SKBINFO_H
+
+/* Copyright (C) 2015 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifdef __KERNEL__
+
+static inline void
+ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo,
+ const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags)
+{
+ mext->skbinfo = *skbinfo;
+}
+
+static inline bool
+ip_set_put_skbinfo(struct sk_buff *skb, const struct ip_set_skbinfo *skbinfo)
+{
+ /* Send nonzero parameters only */
+ return ((skbinfo->skbmark || skbinfo->skbmarkmask) &&
+ nla_put_net64(skb, IPSET_ATTR_SKBMARK,
+ cpu_to_be64((u64)skbinfo->skbmark << 32 |
+ skbinfo->skbmarkmask),
+ IPSET_ATTR_PAD)) ||
+ (skbinfo->skbprio &&
+ nla_put_net32(skb, IPSET_ATTR_SKBPRIO,
+ cpu_to_be32(skbinfo->skbprio))) ||
+ (skbinfo->skbqueue &&
+ nla_put_net16(skb, IPSET_ATTR_SKBQUEUE,
+ cpu_to_be16(skbinfo->skbqueue)));
+}
+
+static inline void
+ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo,
+ const struct ip_set_ext *ext)
+{
+ *skbinfo = ext->skbinfo;
+}
+
+#endif /* __KERNEL__ */
+#endif /* _IP_SET_SKBINFO_H */
diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h
index 1d6a935..bfb3531 100644
--- a/include/linux/netfilter/ipset/ip_set_timeout.h
+++ b/include/linux/netfilter/ipset/ip_set_timeout.h
@@ -40,7 +40,7 @@ ip_set_timeout_uget(struct nlattr *tb)
}
static inline bool
-ip_set_timeout_expired(unsigned long *t)
+ip_set_timeout_expired(const unsigned long *t)
{
return *t != IPSET_ELEM_PERMANENT && time_is_before_jiffies(*t);
}
@@ -63,7 +63,7 @@ ip_set_timeout_set(unsigned long *timeout, u32 value)
}
static inline u32
-ip_set_timeout_get(unsigned long *timeout)
+ip_set_timeout_get(const unsigned long *timeout)
{
return *timeout == IPSET_ELEM_PERMANENT ? 0 :
jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC;
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 2ad1a2b..cd4eaf8 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -4,6 +4,7 @@
#include <linux/netdevice.h>
#include <linux/static_key.h>
+#include <linux/netfilter.h>
#include <uapi/linux/netfilter/x_tables.h>
/* Test a struct->invflags and a boolean for inequality */
@@ -17,14 +18,9 @@
* @target: the target extension
* @matchinfo: per-match data
* @targetinfo: per-target data
- * @net network namespace through which the action was invoked
- * @in: input netdevice
- * @out: output netdevice
+ * @state: pointer to hook state this packet came from
* @fragoff: packet is a fragment, this is the data offset
* @thoff: position of transport header relative to skb->data
- * @hook: hook number given packet came from
- * @family: Actual NFPROTO_* through which the function is invoked
- * (helpful when match->family == NFPROTO_UNSPEC)
*
* Fields written to by extensions:
*
@@ -38,15 +34,47 @@ struct xt_action_param {
union {
const void *matchinfo, *targinfo;
};
- struct net *net;
- const struct net_device *in, *out;
+ const struct nf_hook_state *state;
int fragoff;
unsigned int thoff;
- unsigned int hooknum;
- u_int8_t family;
bool hotdrop;
};
+static inline struct net *xt_net(const struct xt_action_param *par)
+{
+ return par->state->net;
+}
+
+static inline struct net_device *xt_in(const struct xt_action_param *par)
+{
+ return par->state->in;
+}
+
+static inline const char *xt_inname(const struct xt_action_param *par)
+{
+ return par->state->in->name;
+}
+
+static inline struct net_device *xt_out(const struct xt_action_param *par)
+{
+ return par->state->out;
+}
+
+static inline const char *xt_outname(const struct xt_action_param *par)
+{
+ return par->state->out->name;
+}
+
+static inline unsigned int xt_hooknum(const struct xt_action_param *par)
+{
+ return par->state->hook;
+}
+
+static inline u_int8_t xt_family(const struct xt_action_param *par)
+{
+ return par->state->pf;
+}
+
/**
* struct xt_mtchk_param - parameters for match extensions'
* checkentry functions
diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h
index 33e37fb..2dc3b49 100644
--- a/include/linux/netfilter_ingress.h
+++ b/include/linux/netfilter_ingress.h
@@ -26,10 +26,10 @@ static inline int nf_hook_ingress(struct sk_buff *skb)
if (unlikely(!e))
return 0;
- nf_hook_state_init(&state, e, NF_NETDEV_INGRESS, INT_MIN,
+ nf_hook_state_init(&state, NF_NETDEV_INGRESS,
NFPROTO_NETDEV, skb->dev, NULL, NULL,
dev_net(skb->dev), NULL);
- return nf_hook_slow(skb, &state);
+ return nf_hook_slow(skb, &state, e);
}
static inline void nf_hook_ingress_init(struct net_device *dev)
diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index b25ee9f..1828900 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -78,8 +78,11 @@ static inline void *netpoll_poll_lock(struct napi_struct *napi)
struct net_device *dev = napi->dev;
if (dev && dev->npinfo) {
- spin_lock(&napi->poll_lock);
- napi->poll_owner = smp_processor_id();
+ int owner = smp_processor_id();
+
+ while (cmpxchg(&napi->poll_owner, -1, owner) != -1)
+ cpu_relax();
+
return napi;
}
return NULL;
@@ -89,10 +92,8 @@ static inline void netpoll_poll_unlock(void *have)
{
struct napi_struct *napi = have;
- if (napi) {
- napi->poll_owner = -1;
- spin_unlock(&napi->poll_lock);
- }
+ if (napi)
+ smp_store_release(&napi->poll_owner, -1);
}
static inline bool netpoll_tx_running(struct net_device *dev)
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 7676557..fc3c242 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -16,7 +16,6 @@
#define _LINUX_NVME_H
#include <linux/types.h>
-#include <linux/uuid.h>
/* NQN names in commands fields specified one size */
#define NVMF_NQN_FIELD_LEN 256
@@ -182,7 +181,7 @@ struct nvme_id_ctrl {
char fr[8];
__u8 rab;
__u8 ieee[3];
- __u8 mic;
+ __u8 cmic;
__u8 mdts;
__le16 cntlid;
__le32 ver;
@@ -202,7 +201,13 @@ struct nvme_id_ctrl {
__u8 apsta;
__le16 wctemp;
__le16 cctemp;
- __u8 rsvd270[50];
+ __le16 mtfa;
+ __le32 hmpre;
+ __le32 hmmin;
+ __u8 tnvmcap[16];
+ __u8 unvmcap[16];
+ __le32 rpmbs;
+ __u8 rsvd316[4];
__le16 kas;
__u8 rsvd322[190];
__u8 sqes;
@@ -267,7 +272,7 @@ struct nvme_id_ns {
__le16 nabo;
__le16 nabspf;
__u16 rsvd46;
- __le64 nvmcap[2];
+ __u8 nvmcap[16];
__u8 rsvd64[40];
__u8 nguid[16];
__u8 eui64[8];
@@ -277,6 +282,16 @@ struct nvme_id_ns {
};
enum {
+ NVME_ID_CNS_NS = 0x00,
+ NVME_ID_CNS_CTRL = 0x01,
+ NVME_ID_CNS_NS_ACTIVE_LIST = 0x02,
+ NVME_ID_CNS_NS_PRESENT_LIST = 0x10,
+ NVME_ID_CNS_NS_PRESENT = 0x11,
+ NVME_ID_CNS_CTRL_NS_LIST = 0x12,
+ NVME_ID_CNS_CTRL_LIST = 0x13,
+};
+
+enum {
NVME_NS_FEAT_THIN = 1 << 0,
NVME_NS_FLBAS_LBA_MASK = 0xf,
NVME_NS_FLBAS_META_EXT = 0x10,
@@ -556,8 +571,10 @@ enum nvme_admin_opcode {
nvme_admin_set_features = 0x09,
nvme_admin_get_features = 0x0a,
nvme_admin_async_event = 0x0c,
+ nvme_admin_ns_mgmt = 0x0d,
nvme_admin_activate_fw = 0x10,
nvme_admin_download_fw = 0x11,
+ nvme_admin_ns_attach = 0x15,
nvme_admin_keep_alive = 0x18,
nvme_admin_format_nvm = 0x80,
nvme_admin_security_send = 0x81,
@@ -583,6 +600,7 @@ enum {
NVME_FEAT_WRITE_ATOMIC = 0x0a,
NVME_FEAT_ASYNC_EVENT = 0x0b,
NVME_FEAT_AUTO_PST = 0x0c,
+ NVME_FEAT_HOST_MEM_BUF = 0x0d,
NVME_FEAT_KATO = 0x0f,
NVME_FEAT_SW_PROGRESS = 0x80,
NVME_FEAT_HOST_ID = 0x81,
@@ -745,7 +763,7 @@ struct nvmf_common_command {
struct nvmf_disc_rsp_page_entry {
__u8 trtype;
__u8 adrfam;
- __u8 nqntype;
+ __u8 subtype;
__u8 treq;
__le16 portid;
__le16 cntlid;
@@ -794,7 +812,7 @@ struct nvmf_connect_command {
};
struct nvmf_connect_data {
- uuid_be hostid;
+ __u8 hostid[16];
__le16 cntlid;
char resv4[238];
char subsysnqn[NVMF_NQN_FIELD_LEN];
@@ -905,12 +923,23 @@ enum {
NVME_SC_INVALID_VECTOR = 0x108,
NVME_SC_INVALID_LOG_PAGE = 0x109,
NVME_SC_INVALID_FORMAT = 0x10a,
- NVME_SC_FIRMWARE_NEEDS_RESET = 0x10b,
+ NVME_SC_FW_NEEDS_CONV_RESET = 0x10b,
NVME_SC_INVALID_QUEUE = 0x10c,
NVME_SC_FEATURE_NOT_SAVEABLE = 0x10d,
NVME_SC_FEATURE_NOT_CHANGEABLE = 0x10e,
NVME_SC_FEATURE_NOT_PER_NS = 0x10f,
- NVME_SC_FW_NEEDS_RESET_SUBSYS = 0x110,
+ NVME_SC_FW_NEEDS_SUBSYS_RESET = 0x110,
+ NVME_SC_FW_NEEDS_RESET = 0x111,
+ NVME_SC_FW_NEEDS_MAX_TIME = 0x112,
+ NVME_SC_FW_ACIVATE_PROHIBITED = 0x113,
+ NVME_SC_OVERLAPPING_RANGE = 0x114,
+ NVME_SC_NS_INSUFFICENT_CAP = 0x115,
+ NVME_SC_NS_ID_UNAVAILABLE = 0x116,
+ NVME_SC_NS_ALREADY_ATTACHED = 0x118,
+ NVME_SC_NS_IS_PRIVATE = 0x119,
+ NVME_SC_NS_NOT_ATTACHED = 0x11a,
+ NVME_SC_THIN_PROV_NOT_SUPP = 0x11b,
+ NVME_SC_CTRL_LIST_INVALID = 0x11c,
/*
* I/O Command Set Specific - NVM commands:
@@ -941,6 +970,7 @@ enum {
NVME_SC_REFTAG_CHECK = 0x284,
NVME_SC_COMPARE_FAILED = 0x285,
NVME_SC_ACCESS_DENIED = 0x286,
+ NVME_SC_UNWRITTEN_BLOCK = 0x287,
NVME_SC_DNR = 0x4000,
};
@@ -960,6 +990,7 @@ struct nvme_completion {
__le16 status; /* did the command fail, and if so, why? */
};
-#define NVME_VS(major, minor) (((major) << 16) | ((minor) << 8))
+#define NVME_VS(major, minor, tertiary) \
+ (((major) << 16) | ((minor) << 8) | (tertiary))
#endif /* _LINUX_NVME_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 060d0ed..4741ecd 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1257,6 +1257,7 @@ extern u64 perf_swevent_set_period(struct perf_event *event);
extern void perf_event_enable(struct perf_event *event);
extern void perf_event_disable(struct perf_event *event);
extern void perf_event_disable_local(struct perf_event *event);
+extern void perf_event_disable_inatomic(struct perf_event *event);
extern void perf_event_task_tick(void);
#else /* !CONFIG_PERF_EVENTS: */
static inline void *
diff --git a/include/linux/phy.h b/include/linux/phy.h
index e7e1fd3..edde28c 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -611,6 +611,13 @@ struct phy_driver {
void (*get_strings)(struct phy_device *dev, u8 *data);
void (*get_stats)(struct phy_device *dev,
struct ethtool_stats *stats, u64 *data);
+
+ /* Get and Set PHY tunables */
+ int (*get_tunable)(struct phy_device *dev,
+ struct ethtool_tunable *tuna, void *data);
+ int (*set_tunable)(struct phy_device *dev,
+ struct ethtool_tunable *tuna,
+ const void *data);
};
#define to_phy_driver(d) container_of(to_mdio_common_driver(d), \
struct phy_driver, mdiodrv)
@@ -786,6 +793,7 @@ void phy_detach(struct phy_device *phydev);
void phy_start(struct phy_device *phydev);
void phy_stop(struct phy_device *phydev);
int phy_start_aneg(struct phy_device *phydev);
+int phy_aneg_done(struct phy_device *phydev);
int phy_stop_interrupts(struct phy_device *phydev);
@@ -859,6 +867,7 @@ int phy_ethtool_get_link_ksettings(struct net_device *ndev,
struct ethtool_link_ksettings *cmd);
int phy_ethtool_set_link_ksettings(struct net_device *ndev,
const struct ethtool_link_ksettings *cmd);
+int phy_ethtool_nway_reset(struct net_device *ndev);
int __init mdio_bus_init(void);
void mdio_bus_exit(void);
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index ee1bed7..78bb0d7 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -253,6 +253,13 @@ static inline int phy_set_mode(struct phy *phy, enum phy_mode mode)
return -ENOSYS;
}
+static inline int phy_reset(struct phy *phy)
+{
+ if (!phy)
+ return 0;
+ return -ENOSYS;
+}
+
static inline int phy_get_bus_width(struct phy *phy)
{
return -ENOSYS;
diff --git a/include/linux/pim.h b/include/linux/pim.h
index e1d756f..0e81b27 100644
--- a/include/linux/pim.h
+++ b/include/linux/pim.h
@@ -1,6 +1,7 @@
#ifndef __LINUX_PIM_H
#define __LINUX_PIM_H
+#include <linux/skbuff.h>
#include <asm/byteorder.h>
/* Message types - V1 */
@@ -9,24 +10,86 @@
/* Message types - V2 */
#define PIM_VERSION 2
-#define PIM_REGISTER 1
+
+/* RFC7761, sec 4.9:
+ * Type
+ * Types for specific PIM messages. PIM Types are:
+ *
+ * Message Type Destination
+ * ---------------------------------------------------------------------
+ * 0 = Hello Multicast to ALL-PIM-ROUTERS
+ * 1 = Register Unicast to RP
+ * 2 = Register-Stop Unicast to source of Register
+ * packet
+ * 3 = Join/Prune Multicast to ALL-PIM-ROUTERS
+ * 4 = Bootstrap Multicast to ALL-PIM-ROUTERS
+ * 5 = Assert Multicast to ALL-PIM-ROUTERS
+ * 6 = Graft (used in PIM-DM only) Unicast to RPF'(S)
+ * 7 = Graft-Ack (used in PIM-DM only) Unicast to source of Graft
+ * packet
+ * 8 = Candidate-RP-Advertisement Unicast to Domain's BSR
+ */
+enum {
+ PIM_TYPE_HELLO,
+ PIM_TYPE_REGISTER,
+ PIM_TYPE_REGISTER_STOP,
+ PIM_TYPE_JOIN_PRUNE,
+ PIM_TYPE_BOOTSTRAP,
+ PIM_TYPE_ASSERT,
+ PIM_TYPE_GRAFT,
+ PIM_TYPE_GRAFT_ACK,
+ PIM_TYPE_CANDIDATE_RP_ADV
+};
#define PIM_NULL_REGISTER cpu_to_be32(0x40000000)
-static inline bool ipmr_pimsm_enabled(void)
-{
- return IS_BUILTIN(CONFIG_IP_PIMSM_V1) || IS_BUILTIN(CONFIG_IP_PIMSM_V2);
-}
+/* RFC7761, sec 4.9:
+ * The PIM header common to all PIM messages is:
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |PIM Ver| Type | Reserved | Checksum |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ */
+struct pimhdr {
+ __u8 type;
+ __u8 reserved;
+ __be16 csum;
+};
/* PIMv2 register message header layout (ietf-draft-idmr-pimvsm-v2-00.ps */
-struct pimreghdr
-{
+struct pimreghdr {
__u8 type;
__u8 reserved;
__be16 csum;
__be32 flags;
};
-struct sk_buff;
-extern int pim_rcv_v1(struct sk_buff *);
+int pim_rcv_v1(struct sk_buff *skb);
+
+static inline bool ipmr_pimsm_enabled(void)
+{
+ return IS_BUILTIN(CONFIG_IP_PIMSM_V1) || IS_BUILTIN(CONFIG_IP_PIMSM_V2);
+}
+
+static inline struct pimhdr *pim_hdr(const struct sk_buff *skb)
+{
+ return (struct pimhdr *)skb_transport_header(skb);
+}
+
+static inline u8 pim_hdr_version(const struct pimhdr *pimhdr)
+{
+ return pimhdr->type >> 4;
+}
+
+static inline u8 pim_hdr_type(const struct pimhdr *pimhdr)
+{
+ return pimhdr->type & 0xf;
+}
+
+/* check if the address is 224.0.0.13, RFC7761 sec 4.3.1 */
+static inline bool pim_ipv4_all_pim_routers(__be32 addr)
+{
+ return addr == htonl(0xE000000D);
+}
#endif
diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h
index e4c08c1..a1bacf1 100644
--- a/include/linux/pkeys.h
+++ b/include/linux/pkeys.h
@@ -25,7 +25,6 @@ static inline int mm_pkey_alloc(struct mm_struct *mm)
static inline int mm_pkey_free(struct mm_struct *mm, int pkey)
{
- WARN_ONCE(1, "free of protection key when disabled");
return -EINVAL;
}
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index b97bf2e..368c7ad 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -82,4 +82,8 @@ static inline struct proc_dir_entry *proc_net_mkdir(
return proc_mkdir_data(name, 0, parent, net);
}
+struct ns_common;
+int open_related_ns(struct ns_common *ns,
+ struct ns_common *(*get_ns)(struct ns_common *ns));
+
#endif /* _LINUX_PROC_FS_H */
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index 5ad54fc..b76d47a 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -58,7 +58,14 @@ struct system_device_crosststamp;
*
* clock operations
*
+ * @adjfine: Adjusts the frequency of the hardware clock.
+ * parameter scaled_ppm: Desired frequency offset from
+ * nominal frequency in parts per million, but with a
+ * 16 bit binary fractional field.
+ *
* @adjfreq: Adjusts the frequency of the hardware clock.
+ * This method is deprecated. New drivers should implement
+ * the @adjfine method instead.
* parameter delta: Desired frequency offset from nominal frequency
* in parts per billion
*
@@ -108,6 +115,7 @@ struct ptp_clock_info {
int n_pins;
int pps;
struct ptp_pin_desc *pin_config;
+ int (*adjfine)(struct ptp_clock_info *ptp, long scaled_ppm);
int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta);
int (*adjtime)(struct ptp_clock_info *ptp, s64 delta);
int (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts);
diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h
index 1513080..9755a3f 100644
--- a/include/linux/qed/qed_eth_if.h
+++ b/include/linux/qed/qed_eth_if.h
@@ -22,7 +22,7 @@ struct qed_dev_eth_info {
u8 num_tc;
u8 port_mac[ETH_ALEN];
- u8 num_vlan_filters;
+ u16 num_vlan_filters;
u16 num_mac_filters;
/* Legacy VF - this affects the datapath, so qede has to know */
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index f9ae903..ea095b4 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -146,6 +146,7 @@ enum qed_led_mode {
#define DIRECT_REG_RD(reg_addr) readl((void __iomem *)(reg_addr))
#define QED_COALESCE_MAX 0xFF
+#define QED_DEFAULT_RX_USECS 12
/* forward */
struct qed_dev;
@@ -266,6 +267,9 @@ struct qed_dev_info {
u8 mf_mode;
bool tx_switching;
bool rdma_supported;
+ u16 mtu;
+
+ bool wol_support;
};
enum qed_sb_type {
@@ -400,6 +404,15 @@ struct qed_selftest_ops {
* @return 0 on success, error otherwise.
*/
int (*selftest_clock)(struct qed_dev *cdev);
+
+/**
+ * @brief selftest_nvram - Perform nvram test
+ *
+ * @param cdev
+ *
+ * @return 0 on success, error otherwise.
+ */
+ int (*selftest_nvram) (struct qed_dev *cdev);
};
struct qed_common_ops {
@@ -553,6 +566,41 @@ struct qed_common_ops {
*/
int (*set_led)(struct qed_dev *cdev,
enum qed_led_mode mode);
+
+/**
+ * @brief update_drv_state - API to inform the change in the driver state.
+ *
+ * @param cdev
+ * @param active
+ *
+ */
+ int (*update_drv_state)(struct qed_dev *cdev, bool active);
+
+/**
+ * @brief update_mac - API to inform the change in the mac address
+ *
+ * @param cdev
+ * @param mac
+ *
+ */
+ int (*update_mac)(struct qed_dev *cdev, u8 *mac);
+
+/**
+ * @brief update_mtu - API to inform the change in the mtu
+ *
+ * @param cdev
+ * @param mtu
+ *
+ */
+ int (*update_mtu)(struct qed_dev *cdev, u16 mtu);
+
+/**
+ * @brief update_wol - update of changes in the WoL configuration
+ *
+ * @param cdev
+ * @param enabled - true iff WoL should be enabled.
+ */
+ int (*update_wol) (struct qed_dev *cdev, bool enabled);
};
#define MASK_FIELD(_name, _value) \
diff --git a/include/linux/qed/qede_roce.h b/include/linux/qed/qede_roce.h
index 99fbe6d..f48d64b 100644
--- a/include/linux/qed/qede_roce.h
+++ b/include/linux/qed/qede_roce.h
@@ -68,7 +68,7 @@ void qede_roce_unregister_driver(struct qedr_driver *drv);
bool qede_roce_supported(struct qede_dev *dev);
-#if IS_ENABLED(CONFIG_INFINIBAND_QEDR)
+#if IS_ENABLED(CONFIG_QED_RDMA)
int qede_roce_dev_add(struct qede_dev *dev);
void qede_roce_dev_event_open(struct qede_dev *dev);
void qede_roce_dev_event_close(struct qede_dev *dev);
diff --git a/include/linux/random.h b/include/linux/random.h
index f7bb7a3..7bd2403 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -18,9 +18,20 @@ struct random_ready_callback {
};
extern void add_device_randomness(const void *, unsigned int);
+
+#if defined(CONFIG_GCC_PLUGIN_LATENT_ENTROPY) && !defined(__CHECKER__)
+static inline void add_latent_entropy(void)
+{
+ add_device_randomness((const void *)&latent_entropy,
+ sizeof(latent_entropy));
+}
+#else
+static inline void add_latent_entropy(void) {}
+#endif
+
extern void add_input_randomness(unsigned int type, unsigned int code,
- unsigned int value);
-extern void add_interrupt_randomness(int irq, int irq_flags);
+ unsigned int value) __latent_entropy;
+extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy;
extern void get_random_bytes(void *buf, int nbytes);
extern int add_random_ready_callback(struct random_ready_callback *rdy);
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 9adc7b2..f667313 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -15,6 +15,7 @@
#include <linux/list.h>
#include <linux/rbtree.h>
+#include <linux/delay.h>
#include <linux/err.h>
#include <linux/bug.h>
#include <linux/lockdep.h>
@@ -116,22 +117,22 @@ struct reg_sequence {
#define regmap_read_poll_timeout(map, addr, val, cond, sleep_us, timeout_us) \
({ \
ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \
- int ret; \
+ int pollret; \
might_sleep_if(sleep_us); \
for (;;) { \
- ret = regmap_read((map), (addr), &(val)); \
- if (ret) \
+ pollret = regmap_read((map), (addr), &(val)); \
+ if (pollret) \
break; \
if (cond) \
break; \
if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \
- ret = regmap_read((map), (addr), &(val)); \
+ pollret = regmap_read((map), (addr), &(val)); \
break; \
} \
if (sleep_us) \
usleep_range((sleep_us >> 2) + 1, sleep_us); \
} \
- ret ?: ((cond) ? 0 : -ETIMEDOUT); \
+ pollret ?: ((cond) ? 0 : -ETIMEDOUT); \
})
#ifdef CONFIG_REGMAP
diff --git a/include/linux/seg6.h b/include/linux/seg6.h
new file mode 100644
index 0000000..7a66d2b
--- /dev/null
+++ b/include/linux/seg6.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SEG6_H
+#define _LINUX_SEG6_H
+
+#include <uapi/linux/seg6.h>
+
+#endif
diff --git a/include/linux/seg6_genl.h b/include/linux/seg6_genl.h
new file mode 100644
index 0000000..d6c3fb4f
--- /dev/null
+++ b/include/linux/seg6_genl.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SEG6_GENL_H
+#define _LINUX_SEG6_GENL_H
+
+#include <uapi/linux/seg6_genl.h>
+
+#endif
diff --git a/include/linux/seg6_hmac.h b/include/linux/seg6_hmac.h
new file mode 100644
index 0000000..da437eb
--- /dev/null
+++ b/include/linux/seg6_hmac.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SEG6_HMAC_H
+#define _LINUX_SEG6_HMAC_H
+
+#include <uapi/linux/seg6_hmac.h>
+
+#endif
diff --git a/include/linux/seg6_iptunnel.h b/include/linux/seg6_iptunnel.h
new file mode 100644
index 0000000..5377cf6
--- /dev/null
+++ b/include/linux/seg6_iptunnel.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_SEG6_IPTUNNEL_H
+#define _LINUX_SEG6_IPTUNNEL_H
+
+#include <uapi/linux/seg6_iptunnel.h>
+
+#endif
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 663fda2..a4aeeca 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -936,6 +936,7 @@ struct sk_buff_fclones {
/**
* skb_fclone_busy - check if fclone is busy
+ * @sk: socket
* @skb: buffer
*
* Returns true if skb is a fast clone, and its clone is not freed.
@@ -3032,9 +3033,13 @@ static inline void skb_frag_list_init(struct sk_buff *skb)
int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
const struct sk_buff *skb);
struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned flags,
+ void (*destructor)(struct sock *sk,
+ struct sk_buff *skb),
int *peeked, int *off, int *err,
struct sk_buff **last);
struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
+ void (*destructor)(struct sock *sk,
+ struct sk_buff *skb),
int *peeked, int *off, int *err);
struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock,
int *err);
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 705840e..3537fb3 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -135,8 +135,6 @@ struct plat_stmmacenet_data {
void (*bus_setup)(void __iomem *ioaddr);
int (*init)(struct platform_device *pdev, void *priv);
void (*exit)(struct platform_device *pdev, void *priv);
- void (*suspend)(struct platform_device *pdev, void *priv);
- void (*resume)(struct platform_device *pdev, void *priv);
void *bsp_priv;
struct stmmac_axi *axi;
int has_gmac4;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 0d7abb8..91a740f 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -902,8 +902,5 @@ asmlinkage long sys_pkey_mprotect(unsigned long start, size_t len,
unsigned long prot, int pkey);
asmlinkage long sys_pkey_alloc(unsigned long flags, unsigned long init_val);
asmlinkage long sys_pkey_free(int pkey);
-//asmlinkage long sys_pkey_get(int pkey, unsigned long flags);
-//asmlinkage long sys_pkey_set(int pkey, unsigned long access_rights,
-// unsigned long flags);
#endif
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index a17ae7b..32a7c7e 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -176,8 +176,6 @@ struct tcp_sock {
* sum(delta(snd_una)), or how many bytes
* were acked.
*/
- struct u64_stats_sync syncp; /* protects 64bit vars (cf tcp_get_info()) */
-
u32 snd_una; /* First byte we want an ack for */
u32 snd_sml; /* Last byte of the most recently transmitted small packet */
u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 45f004e..2873baf 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -14,17 +14,6 @@ struct timespec;
struct compat_timespec;
#ifdef CONFIG_THREAD_INFO_IN_TASK
-struct thread_info {
- unsigned long flags; /* low level flags */
-};
-
-#define INIT_THREAD_INFO(tsk) \
-{ \
- .flags = 0, \
-}
-#endif
-
-#ifdef CONFIG_THREAD_INFO_IN_TASK
#define current_thread_info() ((struct thread_info *)current)
#endif
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 1c912f8..6620400 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -58,7 +58,7 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
struct virtio_net_hdr *hdr,
bool little_endian)
{
- memset(hdr, 0, sizeof(*hdr));
+ memset(hdr, 0, sizeof(*hdr)); /* no info leak */
if (skb_is_gso(skb)) {
struct skb_shared_info *sinfo = skb_shinfo(skb);
@@ -98,4 +98,4 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
return 0;
}
-#endif /* _LINUX_VIRTIO_BYTEORDER */
+#endif /* _LINUX_VIRTIO_NET_H */
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 82f3c91..d8eae87 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -42,7 +42,6 @@ struct tc_action {
struct gnet_stats_basic_cpu __percpu *cpu_bstats;
struct gnet_stats_queue __percpu *cpu_qstats;
};
-#define tcf_act common.tcfa_act
#define tcf_head common.tcfa_head
#define tcf_index common.tcfa_index
#define tcf_refcnt common.tcfa_refcnt
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index f2d0727..8f998af 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -174,6 +174,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex,
const struct in6_addr *addr);
int ipv6_sock_mc_drop(struct sock *sk, int ifindex,
const struct in6_addr *addr);
+void __ipv6_sock_mc_close(struct sock *sk);
void ipv6_sock_mc_close(struct sock *sk);
bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr,
const struct in6_addr *src_addr);
diff --git a/include/net/bonding.h b/include/net/bonding.h
index f32f7ef..3c85777 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -681,7 +681,7 @@ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip)
}
/* exported from bond_main.c */
-extern int bond_net_id;
+extern unsigned int bond_net_id;
extern const struct bond_parm_tbl bond_lacp_tbl[];
extern const struct bond_parm_tbl xmit_hashtype_tbl[];
extern const struct bond_parm_tbl arp_validate_tbl[];
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 2fbeb13..d73b849 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -58,10 +58,9 @@ static inline unsigned long busy_loop_end_time(void)
return busy_loop_us_clock() + ACCESS_ONCE(sysctl_net_busy_poll);
}
-static inline bool sk_can_busy_loop(struct sock *sk)
+static inline bool sk_can_busy_loop(const struct sock *sk)
{
- return sk->sk_ll_usec && sk->sk_napi_id &&
- !need_resched() && !signal_pending(current);
+ return sk->sk_ll_usec && sk->sk_napi_id && !signal_pending(current);
}
@@ -81,11 +80,6 @@ static inline void skb_mark_napi_id(struct sk_buff *skb,
skb->napi_id = napi->napi_id;
}
-/* used in the protocol hanlder to propagate the napi_id to the socket */
-static inline void sk_mark_napi_id(struct sock *sk, struct sk_buff *skb)
-{
- sk->sk_napi_id = skb->napi_id;
-}
#else /* CONFIG_NET_RX_BUSY_POLL */
static inline unsigned long net_busy_loop_on(void)
@@ -108,10 +102,6 @@ static inline void skb_mark_napi_id(struct sk_buff *skb,
{
}
-static inline void sk_mark_napi_id(struct sock *sk, struct sk_buff *skb)
-{
-}
-
static inline bool busy_loop_timeout(unsigned long end_time)
{
return true;
@@ -123,4 +113,23 @@ static inline bool sk_busy_loop(struct sock *sk, int nonblock)
}
#endif /* CONFIG_NET_RX_BUSY_POLL */
+
+/* used in the protocol hanlder to propagate the napi_id to the socket */
+static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ sk->sk_napi_id = skb->napi_id;
+#endif
+}
+
+/* variant used for unconnected sockets */
+static inline void sk_mark_napi_id_once(struct sock *sk,
+ const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ if (!sk->sk_napi_id)
+ sk->sk_napi_id = skb->napi_id;
+#endif
+}
+
#endif /* _LINUX_NET_BUSY_POLL_H */
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index fe78f02..2019310 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -772,6 +772,30 @@ struct cfg80211_csa_settings {
};
/**
+ * struct iface_combination_params - input parameters for interface combinations
+ *
+ * Used to pass interface combination parameters
+ *
+ * @num_different_channels: the number of different channels we want
+ * to use for verification
+ * @radar_detect: a bitmap where each bit corresponds to a channel
+ * width where radar detection is needed, as in the definition of
+ * &struct ieee80211_iface_combination.@radar_detect_widths
+ * @iftype_num: array with the number of interfaces of each interface
+ * type. The index is the interface type as specified in &enum
+ * nl80211_iftype.
+ * @new_beacon_int: set this to the beacon interval of a new interface
+ * that's not operating yet, if such is to be checked as part of
+ * the verification
+ */
+struct iface_combination_params {
+ int num_different_channels;
+ u8 radar_detect;
+ int iftype_num[NUM_NL80211_IFTYPES];
+ u32 new_beacon_int;
+};
+
+/**
* enum station_parameters_apply_mask - station parameter values to apply
* @STATION_PARAM_APPLY_UAPSD: apply new uAPSD parameters (uapsd_queues, max_sp)
* @STATION_PARAM_APPLY_CAPABILITY: apply new capability
@@ -796,9 +820,9 @@ enum station_parameters_apply_mask {
* (or NULL for no change)
* @supported_rates_len: number of supported rates
* @sta_flags_mask: station flags that changed
- * (bitmask of BIT(NL80211_STA_FLAG_...))
+ * (bitmask of BIT(%NL80211_STA_FLAG_...))
* @sta_flags_set: station flags values
- * (bitmask of BIT(NL80211_STA_FLAG_...))
+ * (bitmask of BIT(%NL80211_STA_FLAG_...))
* @listen_interval: listen interval or -1 for no change
* @aid: AID or zero for no change
* @peer_aid: mesh peer AID or zero for no change
@@ -1761,9 +1785,11 @@ const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 ie);
* @key_len: length of WEP key for shared key authentication
* @key_idx: index of WEP key for shared key authentication
* @key: WEP key for shared key authentication
- * @sae_data: Non-IE data to use with SAE or %NULL. This starts with
- * Authentication transaction sequence number field.
- * @sae_data_len: Length of sae_data buffer in octets
+ * @auth_data: Fields and elements in Authentication frames. This contains
+ * the authentication frame body (non-IE and IE data), excluding the
+ * Authentication algorithm number, i.e., starting at the Authentication
+ * transaction sequence number field.
+ * @auth_data_len: Length of auth_data buffer in octets
*/
struct cfg80211_auth_request {
struct cfg80211_bss *bss;
@@ -1772,8 +1798,8 @@ struct cfg80211_auth_request {
enum nl80211_auth_type auth_type;
const u8 *key;
u8 key_len, key_idx;
- const u8 *sae_data;
- size_t sae_data_len;
+ const u8 *auth_data;
+ size_t auth_data_len;
};
/**
@@ -1814,6 +1840,12 @@ enum cfg80211_assoc_req_flags {
* @ht_capa_mask: The bits of ht_capa which are to be used.
* @vht_capa: VHT capability override
* @vht_capa_mask: VHT capability mask indicating which fields to use
+ * @fils_kek: FILS KEK for protecting (Re)Association Request/Response frame or
+ * %NULL if FILS is not used.
+ * @fils_kek_len: Length of fils_kek in octets
+ * @fils_nonces: FILS nonces (part of AAD) for protecting (Re)Association
+ * Request/Response frame or %NULL if FILS is not used. This field starts
+ * with 16 octets of STA Nonce followed by 16 octets of AP Nonce.
*/
struct cfg80211_assoc_request {
struct cfg80211_bss *bss;
@@ -1825,6 +1857,9 @@ struct cfg80211_assoc_request {
struct ieee80211_ht_cap ht_capa;
struct ieee80211_ht_cap ht_capa_mask;
struct ieee80211_vht_cap vht_capa, vht_capa_mask;
+ const u8 *fils_kek;
+ size_t fils_kek_len;
+ const u8 *fils_nonces;
};
/**
@@ -2016,6 +2051,18 @@ struct cfg80211_connect_params {
};
/**
+ * enum cfg80211_connect_params_changed - Connection parameters being updated
+ *
+ * This enum provides information of all connect parameters that
+ * have to be updated as part of update_connect_params() call.
+ *
+ * @UPDATE_ASSOC_IES: Indicates whether association request IEs are updated
+ */
+enum cfg80211_connect_params_changed {
+ UPDATE_ASSOC_IES = BIT(0),
+};
+
+/**
* enum wiphy_params_flags - set_wiphy_params bitfield values
* @WIPHY_PARAM_RETRY_SHORT: wiphy->retry_short has changed
* @WIPHY_PARAM_RETRY_LONG: wiphy->retry_long has changed
@@ -2536,9 +2583,18 @@ struct cfg80211_nan_func {
* cases, the result of roaming is indicated with a call to
* cfg80211_roamed() or cfg80211_roamed_bss().
* (invoked with the wireless_dev mutex held)
- * @disconnect: Disconnect from the BSS/ESS. Once done, call
- * cfg80211_disconnected().
+ * @update_connect_params: Update the connect parameters while connected to a
+ * BSS. The updated parameters can be used by driver/firmware for
+ * subsequent BSS selection (roaming) decisions and to form the
+ * Authentication/(Re)Association Request frames. This call does not
+ * request an immediate disassociation or reassociation with the current
+ * BSS, i.e., this impacts only subsequent (re)associations. The bits in
+ * changed are defined in &enum cfg80211_connect_params_changed.
* (invoked with the wireless_dev mutex held)
+ * @disconnect: Disconnect from the BSS/ESS or stop connection attempts if
+ * connection is in progress. Once done, call cfg80211_disconnected() in
+ * case connection was already established (invoked with the
+ * wireless_dev mutex held), otherwise call cfg80211_connect_timeout().
*
* @join_ibss: Join the specified IBSS (or create if necessary). Once done, call
* cfg80211_ibss_joined(), also call that function when changing BSSID due
@@ -2706,6 +2762,8 @@ struct cfg80211_nan_func {
* @nan_change_conf: changes NAN configuration. The changed parameters must
* be specified in @changes (using &enum cfg80211_nan_conf_changes);
* All other parameters must be ignored.
+ *
+ * @set_multicast_to_unicast: configure multicast to unicast conversion for BSS
*/
struct cfg80211_ops {
int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
@@ -2820,6 +2878,10 @@ struct cfg80211_ops {
int (*connect)(struct wiphy *wiphy, struct net_device *dev,
struct cfg80211_connect_params *sme);
+ int (*update_connect_params)(struct wiphy *wiphy,
+ struct net_device *dev,
+ struct cfg80211_connect_params *sme,
+ u32 changed);
int (*disconnect)(struct wiphy *wiphy, struct net_device *dev,
u16 reason_code);
@@ -2982,6 +3044,10 @@ struct cfg80211_ops {
struct wireless_dev *wdev,
struct cfg80211_nan_conf *conf,
u32 changes);
+
+ int (*set_multicast_to_unicast)(struct wiphy *wiphy,
+ struct net_device *dev,
+ const bool enabled);
};
/*
@@ -3080,6 +3146,12 @@ struct ieee80211_iface_limit {
* only in special cases.
* @radar_detect_widths: bitmap of channel widths supported for radar detection
* @radar_detect_regions: bitmap of regions supported for radar detection
+ * @beacon_int_min_gcd: This interface combination supports different
+ * beacon intervals.
+ * = 0 - all beacon intervals for different interface must be same.
+ * > 0 - any beacon interval for the interface part of this combination AND
+ * *GCD* of all beacon intervals from beaconing interfaces of this
+ * combination must be greater or equal to this value.
*
* With this structure the driver can describe which interface
* combinations it supports concurrently.
@@ -3088,47 +3160,54 @@ struct ieee80211_iface_limit {
*
* 1. Allow #STA <= 1, #AP <= 1, matching BI, channels = 1, 2 total:
*
- * struct ieee80211_iface_limit limits1[] = {
- * { .max = 1, .types = BIT(NL80211_IFTYPE_STATION), },
- * { .max = 1, .types = BIT(NL80211_IFTYPE_AP}, },
- * };
- * struct ieee80211_iface_combination combination1 = {
- * .limits = limits1,
- * .n_limits = ARRAY_SIZE(limits1),
- * .max_interfaces = 2,
- * .beacon_int_infra_match = true,
- * };
+ * .. code-block:: c
+ *
+ * struct ieee80211_iface_limit limits1[] = {
+ * { .max = 1, .types = BIT(NL80211_IFTYPE_STATION), },
+ * { .max = 1, .types = BIT(NL80211_IFTYPE_AP}, },
+ * };
+ * struct ieee80211_iface_combination combination1 = {
+ * .limits = limits1,
+ * .n_limits = ARRAY_SIZE(limits1),
+ * .max_interfaces = 2,
+ * .beacon_int_infra_match = true,
+ * };
*
*
* 2. Allow #{AP, P2P-GO} <= 8, channels = 1, 8 total:
*
- * struct ieee80211_iface_limit limits2[] = {
- * { .max = 8, .types = BIT(NL80211_IFTYPE_AP) |
- * BIT(NL80211_IFTYPE_P2P_GO), },
- * };
- * struct ieee80211_iface_combination combination2 = {
- * .limits = limits2,
- * .n_limits = ARRAY_SIZE(limits2),
- * .max_interfaces = 8,
- * .num_different_channels = 1,
- * };
+ * .. code-block:: c
+ *
+ * struct ieee80211_iface_limit limits2[] = {
+ * { .max = 8, .types = BIT(NL80211_IFTYPE_AP) |
+ * BIT(NL80211_IFTYPE_P2P_GO), },
+ * };
+ * struct ieee80211_iface_combination combination2 = {
+ * .limits = limits2,
+ * .n_limits = ARRAY_SIZE(limits2),
+ * .max_interfaces = 8,
+ * .num_different_channels = 1,
+ * };
*
*
* 3. Allow #STA <= 1, #{P2P-client,P2P-GO} <= 3 on two channels, 4 total.
*
- * This allows for an infrastructure connection and three P2P connections.
+ * This allows for an infrastructure connection and three P2P connections.
*
- * struct ieee80211_iface_limit limits3[] = {
- * { .max = 1, .types = BIT(NL80211_IFTYPE_STATION), },
- * { .max = 3, .types = BIT(NL80211_IFTYPE_P2P_GO) |
- * BIT(NL80211_IFTYPE_P2P_CLIENT), },
- * };
- * struct ieee80211_iface_combination combination3 = {
- * .limits = limits3,
- * .n_limits = ARRAY_SIZE(limits3),
- * .max_interfaces = 4,
- * .num_different_channels = 2,
- * };
+ * .. code-block:: c
+ *
+ * struct ieee80211_iface_limit limits3[] = {
+ * { .max = 1, .types = BIT(NL80211_IFTYPE_STATION), },
+ * { .max = 3, .types = BIT(NL80211_IFTYPE_P2P_GO) |
+ * BIT(NL80211_IFTYPE_P2P_CLIENT), },
+ * };
+ * struct ieee80211_iface_combination combination3 = {
+ * .limits = limits3,
+ * .n_limits = ARRAY_SIZE(limits3),
+ * .max_interfaces = 4,
+ * .num_different_channels = 2,
+ * };
+ *
*/
struct ieee80211_iface_combination {
const struct ieee80211_iface_limit *limits;
@@ -3138,6 +3217,7 @@ struct ieee80211_iface_combination {
bool beacon_int_infra_match;
u8 radar_detect_widths;
u8 radar_detect_regions;
+ u32 beacon_int_min_gcd;
};
struct ieee80211_txrx_stypes {
@@ -3745,8 +3825,8 @@ struct cfg80211_cached_keys;
* @beacon_interval: beacon interval used on this device for transmitting
* beacons, 0 when not valid
* @address: The address for this device, valid only if @netdev is %NULL
- * @p2p_started: true if this is a P2P Device that has been started
- * @nan_started: true if this is a NAN interface that has been started
+ * @is_running: true if this is a non-netdev device that has been started, e.g.
+ * the P2P Device.
* @cac_started: true if DFS channel availability check has been started
* @cac_start_time: timestamp (jiffies) when the dfs state was entered.
* @cac_time_ms: CAC time in ms
@@ -3778,7 +3858,7 @@ struct wireless_dev {
struct mutex mtx;
- bool use_4addr, p2p_started, nan_started;
+ bool use_4addr, is_running;
u8 address[ETH_ALEN] __aligned(sizeof(u16));
@@ -3835,6 +3915,13 @@ static inline u8 *wdev_address(struct wireless_dev *wdev)
return wdev->address;
}
+static inline bool wdev_running(struct wireless_dev *wdev)
+{
+ if (wdev->netdev)
+ return netif_running(wdev->netdev);
+ return wdev->is_running;
+}
+
/**
* wdev_priv - return wiphy priv from wireless_dev
*
@@ -4040,14 +4127,29 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr);
*/
/**
+ * ieee80211_data_to_8023_exthdr - convert an 802.11 data frame to 802.3
+ * @skb: the 802.11 data frame
+ * @ehdr: pointer to a &struct ethhdr that will get the header, instead
+ * of it being pushed into the SKB
+ * @addr: the device MAC address
+ * @iftype: the virtual interface type
+ * Return: 0 on success. Non-zero on error.
+ */
+int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
+ const u8 *addr, enum nl80211_iftype iftype);
+
+/**
* ieee80211_data_to_8023 - convert an 802.11 data frame to 802.3
* @skb: the 802.11 data frame
* @addr: the device MAC address
* @iftype: the virtual interface type
* Return: 0 on success. Non-zero on error.
*/
-int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
- enum nl80211_iftype iftype);
+static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
+ enum nl80211_iftype iftype)
+{
+ return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype);
+}
/**
* ieee80211_data_from_8023 - convert an 802.3 frame to 802.11
@@ -4065,22 +4167,23 @@ int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr,
/**
* ieee80211_amsdu_to_8023s - decode an IEEE 802.11n A-MSDU frame
*
- * Decode an IEEE 802.11n A-MSDU frame and convert it to a list of
- * 802.3 frames. The @list will be empty if the decode fails. The
- * @skb is consumed after the function returns.
+ * Decode an IEEE 802.11 A-MSDU and convert it to a list of 802.3 frames.
+ * The @list will be empty if the decode fails. The @skb must be fully
+ * header-less before being passed in here; it is freed in this function.
*
- * @skb: The input IEEE 802.11n A-MSDU frame.
+ * @skb: The input A-MSDU frame without any headers.
* @list: The output list of 802.3 frames. It must be allocated and
* initialized by by the caller.
* @addr: The device MAC address.
* @iftype: The device interface type.
* @extra_headroom: The hardware extra headroom for SKBs in the @list.
- * @has_80211_header: Set it true if SKB is with IEEE 802.11 header.
+ * @check_da: DA to check in the inner ethernet header, or NULL
+ * @check_sa: SA to check in the inner ethernet header, or NULL
*/
void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
const u8 *addr, enum nl80211_iftype iftype,
const unsigned int extra_headroom,
- bool has_80211_header);
+ const u8 *check_da, const u8 *check_sa);
/**
* cfg80211_classify8021d - determine the 802.1p/1d tag for a data frame
@@ -4140,6 +4243,27 @@ static inline const u8 *cfg80211_find_ie(u8 eid, const u8 *ies, int len)
}
/**
+ * cfg80211_find_ext_ie - find information element with EID Extension in data
+ *
+ * @ext_eid: element ID Extension
+ * @ies: data consisting of IEs
+ * @len: length of data
+ *
+ * Return: %NULL if the extended element ID could not be found or if
+ * the element is invalid (claims to be longer than the given
+ * data), or a pointer to the first byte of the requested
+ * element, that is the byte containing the element ID.
+ *
+ * Note: There are no checks on the element length other than
+ * having to fit into the given data.
+ */
+static inline const u8 *cfg80211_find_ext_ie(u8 ext_eid, const u8 *ies, int len)
+{
+ return cfg80211_find_ie_match(WLAN_EID_EXTENSION, ies, len,
+ &ext_eid, 1, 2);
+}
+
+/**
* cfg80211_find_vendor_ie - find vendor specific information element in data
*
* @oui: vendor OUI
@@ -4539,7 +4663,8 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr);
* moves to cfg80211 in this call
* @buf: authentication frame (header + body)
* @len: length of the frame data
- * @uapsd_queues: bitmap of ACs configured to uapsd. -1 if n/a.
+ * @uapsd_queues: bitmap of queues configured for uapsd. Same format
+ * as the AC bitmap in the QoS info field
*
* After being asked to associate via cfg80211_ops::assoc() the driver must
* call either this function or cfg80211_auth_timeout().
@@ -5575,36 +5700,20 @@ unsigned int ieee80211_get_num_supported_channels(struct wiphy *wiphy);
* cfg80211_check_combinations - check interface combinations
*
* @wiphy: the wiphy
- * @num_different_channels: the number of different channels we want
- * to use for verification
- * @radar_detect: a bitmap where each bit corresponds to a channel
- * width where radar detection is needed, as in the definition of
- * &struct ieee80211_iface_combination.@radar_detect_widths
- * @iftype_num: array with the numbers of interfaces of each interface
- * type. The index is the interface type as specified in &enum
- * nl80211_iftype.
+ * @params: the interface combinations parameter
*
* This function can be called by the driver to check whether a
* combination of interfaces and their types are allowed according to
* the interface combinations.
*/
int cfg80211_check_combinations(struct wiphy *wiphy,
- const int num_different_channels,
- const u8 radar_detect,
- const int iftype_num[NUM_NL80211_IFTYPES]);
+ struct iface_combination_params *params);
/**
* cfg80211_iter_combinations - iterate over matching combinations
*
* @wiphy: the wiphy
- * @num_different_channels: the number of different channels we want
- * to use for verification
- * @radar_detect: a bitmap where each bit corresponds to a channel
- * width where radar detection is needed, as in the definition of
- * &struct ieee80211_iface_combination.@radar_detect_widths
- * @iftype_num: array with the numbers of interfaces of each interface
- * type. The index is the interface type as specified in &enum
- * nl80211_iftype.
+ * @params: the interface combinations parameter
* @iter: function to call for each matching combination
* @data: pointer to pass to iter function
*
@@ -5613,9 +5722,7 @@ int cfg80211_check_combinations(struct wiphy *wiphy,
* purposes.
*/
int cfg80211_iter_combinations(struct wiphy *wiphy,
- const int num_different_channels,
- const u8 radar_detect,
- const int iftype_num[NUM_NL80211_IFTYPES],
+ struct iface_combination_params *params,
void (*iter)(const struct ieee80211_iface_combination *c,
void *data),
void *data);
diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index 6965c8f..701fc81 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -115,6 +115,7 @@ static inline struct ip_tunnel_info *skb_tunnel_info_unclone(struct sk_buff *skb
static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr,
__be32 daddr,
__u8 tos, __u8 ttl,
+ __be16 tp_dst,
__be16 flags,
__be64 tunnel_id,
int md_size)
@@ -127,7 +128,7 @@ static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr,
ip_tunnel_key_init(&tun_dst->u.tun_info.key,
saddr, daddr, tos, ttl,
- 0, 0, 0, tunnel_id, flags);
+ 0, 0, tp_dst, tunnel_id, flags);
return tun_dst;
}
@@ -139,12 +140,13 @@ static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb,
const struct iphdr *iph = ip_hdr(skb);
return __ip_tun_set_dst(iph->saddr, iph->daddr, iph->tos, iph->ttl,
- flags, tunnel_id, md_size);
+ 0, flags, tunnel_id, md_size);
}
static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *saddr,
const struct in6_addr *daddr,
__u8 tos, __u8 ttl,
+ __be16 tp_dst,
__be32 label,
__be16 flags,
__be64 tunnel_id,
@@ -162,7 +164,7 @@ static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *sad
info->key.tun_flags = flags;
info->key.tun_id = tunnel_id;
info->key.tp_src = 0;
- info->key.tp_dst = 0;
+ info->key.tp_dst = tp_dst;
info->key.u.ipv6.src = *saddr;
info->key.u.ipv6.dst = *daddr;
@@ -183,7 +185,7 @@ static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb,
return __ipv6_tun_set_dst(&ip6h->saddr, &ip6h->daddr,
ipv6_get_dsfield(ip6h), ip6h->hop_limit,
- ip6_flowlabel(ip6h), flags, tunnel_id,
+ 0, ip6_flowlabel(ip6h), flags, tunnel_id,
md_size);
}
#endif /* __NET_DST_METADATA_H */
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 456e4a6..8dbfdf7 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -8,6 +8,11 @@
#include <net/flow.h>
#include <net/rtnetlink.h>
+struct fib_kuid_range {
+ kuid_t start;
+ kuid_t end;
+};
+
struct fib_rule {
struct list_head list;
int iifindex;
@@ -30,6 +35,7 @@ struct fib_rule {
int suppress_prefixlen;
char iifname[IFNAMSIZ];
char oifname[IFNAMSIZ];
+ struct fib_kuid_range uid_range;
struct rcu_head rcu;
};
@@ -92,7 +98,8 @@ struct fib_rules_ops {
[FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \
[FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \
[FRA_GOTO] = { .type = NLA_U32 }, \
- [FRA_L3MDEV] = { .type = NLA_U8 }
+ [FRA_L3MDEV] = { .type = NLA_U8 }, \
+ [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) }
static inline void fib_rule_get(struct fib_rule *rule)
{
diff --git a/include/net/flow.h b/include/net/flow.h
index 035aa77..6bbbca8 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -11,6 +11,7 @@
#include <linux/in6.h>
#include <linux/atomic.h>
#include <net/flow_dissector.h>
+#include <linux/uidgid.h>
/*
* ifindex generation is per-net namespace, and loopback is
@@ -37,6 +38,7 @@ struct flowi_common {
#define FLOWI_FLAG_SKIP_NH_OIF 0x04
__u32 flowic_secid;
struct flowi_tunnel flowic_tun_key;
+ kuid_t flowic_uid;
};
union flowi_uli {
@@ -74,6 +76,7 @@ struct flowi4 {
#define flowi4_flags __fl_common.flowic_flags
#define flowi4_secid __fl_common.flowic_secid
#define flowi4_tun_key __fl_common.flowic_tun_key
+#define flowi4_uid __fl_common.flowic_uid
/* (saddr,daddr) must be grouped, same order as in IP header */
__be32 saddr;
@@ -93,7 +96,8 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
__u32 mark, __u8 tos, __u8 scope,
__u8 proto, __u8 flags,
__be32 daddr, __be32 saddr,
- __be16 dport, __be16 sport)
+ __be16 dport, __be16 sport,
+ kuid_t uid)
{
fl4->flowi4_oif = oif;
fl4->flowi4_iif = LOOPBACK_IFINDEX;
@@ -104,6 +108,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
fl4->flowi4_flags = flags;
fl4->flowi4_secid = 0;
fl4->flowi4_tun_key.tun_id = 0;
+ fl4->flowi4_uid = uid;
fl4->daddr = daddr;
fl4->saddr = saddr;
fl4->fl4_dport = dport;
@@ -131,6 +136,7 @@ struct flowi6 {
#define flowi6_flags __fl_common.flowic_flags
#define flowi6_secid __fl_common.flowic_secid
#define flowi6_tun_key __fl_common.flowic_tun_key
+#define flowi6_uid __fl_common.flowic_uid
struct in6_addr daddr;
struct in6_addr saddr;
/* Note: flowi6_tos is encoded in flowlabel, too. */
@@ -176,6 +182,7 @@ struct flowi {
#define flowi_flags u.__fl_common.flowic_flags
#define flowi_secid u.__fl_common.flowic_secid
#define flowi_tun_key u.__fl_common.flowic_tun_key
+#define flowi_uid u.__fl_common.flowic_uid
} __attribute__((__aligned__(BITS_PER_LONG/8)));
static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index d953492..c4f3166 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -128,6 +128,11 @@ enum flow_dissector_key_id {
FLOW_DISSECTOR_KEY_FLOW_LABEL, /* struct flow_dissector_key_flow_tags */
FLOW_DISSECTOR_KEY_GRE_KEYID, /* struct flow_dissector_key_keyid */
FLOW_DISSECTOR_KEY_MPLS_ENTROPY, /* struct flow_dissector_key_keyid */
+ FLOW_DISSECTOR_KEY_ENC_KEYID, /* struct flow_dissector_key_keyid */
+ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */
+ FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */
+ FLOW_DISSECTOR_KEY_ENC_CONTROL, /* struct flow_dissector_key_control */
+ FLOW_DISSECTOR_KEY_ENC_PORTS, /* struct flow_dissector_key_ports */
FLOW_DISSECTOR_KEY_MAX,
};
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 3ec87ba..a34275b 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -48,7 +48,7 @@ struct genl_info;
* @n_ops: number of operations supported by this family
*/
struct genl_family {
- unsigned int id; /* private */
+ int id; /* private */
unsigned int hdrsize;
char name[GENL_NAMSIZ];
unsigned int version;
diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h
index ba07b9d..d0e7e3f 100644
--- a/include/net/ieee80211_radiotap.h
+++ b/include/net/ieee80211_radiotap.h
@@ -333,9 +333,9 @@ enum ieee80211_radiotap_type {
#define IEEE80211_RADIOTAP_TIMESTAMP_UNIT_NS 0x0003
#define IEEE80211_RADIOTAP_TIMESTAMP_SPOS_MASK 0x00F0
#define IEEE80211_RADIOTAP_TIMESTAMP_SPOS_BEGIN_MDPU 0x0000
-#define IEEE80211_RADIOTAP_TIMESTAMP_SPOS_EO_MPDU 0x0010
+#define IEEE80211_RADIOTAP_TIMESTAMP_SPOS_PLCP_SIG_ACQ 0x0010
#define IEEE80211_RADIOTAP_TIMESTAMP_SPOS_EO_PPDU 0x0020
-#define IEEE80211_RADIOTAP_TIMESTAMP_SPOS_PLCP_SIG_ACQ 0x0030
+#define IEEE80211_RADIOTAP_TIMESTAMP_SPOS_EO_MPDU 0x0030
#define IEEE80211_RADIOTAP_TIMESTAMP_SPOS_UNKNOWN 0x00F0
#define IEEE80211_RADIOTAP_TIMESTAMP_FLAG_64BIT 0x00
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 515352c..b0576cb 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -190,8 +190,8 @@ struct inet6_dev {
__u32 if_flags;
int dead;
+ u32 desync_factor;
u8 rndid[8];
- struct timer_list regen_timer;
struct list_head tempaddr_list;
struct in6_addr token;
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 236a810..c9cff97 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -228,6 +228,7 @@ struct inet_sock {
#define IP_CMSG_PASSSEC BIT(5)
#define IP_CMSG_ORIGDSTADDR BIT(6)
#define IP_CMSG_CHECKSUM BIT(7)
+#define IP_CMSG_RECVFRAGSIZE BIT(8)
/**
* sk_to_full_sk - Access to a full socket
diff --git a/include/net/ip.h b/include/net/ip.h
index bc43c0f..ab6761a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -38,7 +38,7 @@ struct sock;
struct inet_skb_parm {
int iif;
struct ip_options opt; /* Compiled IP options */
- unsigned char flags;
+ u16 flags;
#define IPSKB_FORWARDED BIT(0)
#define IPSKB_XFRM_TUNNEL_SIZE BIT(1)
@@ -47,11 +47,16 @@ struct inet_skb_parm {
#define IPSKB_REROUTED BIT(4)
#define IPSKB_DOREDIRECT BIT(5)
#define IPSKB_FRAG_PMTU BIT(6)
-#define IPSKB_FRAG_SEGS BIT(7)
+#define IPSKB_L3SLAVE BIT(7)
u16 frag_max_size;
};
+static inline bool ipv4_l3mdev_skb(u16 flags)
+{
+ return !!(flags & IPSKB_L3SLAVE);
+}
+
static inline unsigned int ip_hdrlen(const struct sk_buff *skb)
{
return ip_hdr(skb)->ihl * 4;
@@ -173,6 +178,7 @@ struct ip_reply_arg {
/* -1 if not needed */
int bound_dev_if;
u8 tos;
+ kuid_t uid;
};
#define IP_REPLY_ARG_NOSRCCHECK 1
@@ -572,7 +578,8 @@ int ip_options_rcv_srr(struct sk_buff *skb);
*/
void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
-void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int offset);
+void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
+ struct sk_buff *skb, int tlen, int offset);
int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
struct ipcm_cookie *ipc, bool allow_ipv6);
int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
@@ -594,7 +601,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
{
- ip_cmsg_recv_offset(msg, skb, 0);
+ ip_cmsg_recv_offset(msg, skb->sk, skb, 0, 0);
}
bool icmp_global_allow(void);
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index fb961a5..a74e2aa 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -230,6 +230,8 @@ struct fib6_table {
rwlock_t tb6_lock;
struct fib6_node tb6_root;
struct inet_peer_base tb6_peers;
+ unsigned int flags;
+#define RT6_TABLE_HAS_DFLT_ROUTER BIT(0)
};
#define RT6_TABLE_UNSPEC RT_TABLE_UNSPEC
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index e0cd318..9dc2c18 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -32,6 +32,7 @@ struct route_info {
#define RT6_LOOKUP_F_SRCPREF_TMP 0x00000008
#define RT6_LOOKUP_F_SRCPREF_PUBLIC 0x00000010
#define RT6_LOOKUP_F_SRCPREF_COA 0x00000020
+#define RT6_LOOKUP_F_IGNORE_LINKSTATE 0x00000040
/* We do not (yet ?) support IPv6 jumbograms (RFC 2675)
* Unlike IPv4, hdr->seg_len doesn't include the IPv6 header
@@ -139,9 +140,10 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
const struct in6_addr *gwaddr);
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif,
- u32 mark);
+ u32 mark, kuid_t uid);
void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu);
-void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark);
+void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
+ kuid_t uid);
void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
u32 mark);
void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk);
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 20ed969..1b1cf33 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -146,6 +146,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
{
int pkt_len, err;
+ memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
pkt_len = skb->len - skb_inner_network_offset(skb);
err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb);
if (unlikely(net_xmit_eval(err)))
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 59557c0..e893fe4 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -129,7 +129,7 @@ struct ip_tunnel {
#endif
struct ip_tunnel_prl_entry __rcu *prl; /* potential router list */
unsigned int prl_count; /* # of entries in PRL */
- int ip_tnl_net_id;
+ unsigned int ip_tnl_net_id;
struct gro_cells gro_cells;
bool collect_md;
bool ignore_df;
@@ -248,7 +248,7 @@ void ip_tunnel_uninit(struct net_device *dev);
void ip_tunnel_dellink(struct net_device *dev, struct list_head *head);
struct net *ip_tunnel_get_link_net(const struct net_device *dev);
int ip_tunnel_get_iflink(const struct net_device *dev);
-int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
+int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
struct rtnl_link_ops *ops, char *devname);
void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops);
@@ -275,7 +275,7 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p);
int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p);
-void ip_tunnel_setup(struct net_device *dev, int net_id);
+void ip_tunnel_setup(struct net_device *dev, unsigned int net_id);
struct ip_tunnel_encap_ops {
size_t (*encap_hlen)(struct ip_tunnel_encap *e);
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 8fed1cd..0a3622b 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -932,7 +932,8 @@ int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
*/
void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
- u8 *proto, struct in6_addr **daddr_p);
+ u8 *proto, struct in6_addr **daddr_p,
+ struct in6_addr *saddr);
void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
u8 *proto);
diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index 82e76fe..d4c1c75 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -94,7 +94,8 @@ static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate)
static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate,
unsigned int mtu)
{
- if (lwtunnel_xmit_redirect(lwtstate) && lwtstate->headroom < mtu)
+ if ((lwtunnel_xmit_redirect(lwtstate) ||
+ lwtunnel_output_redirect(lwtstate)) && lwtstate->headroom < mtu)
return lwtstate->headroom;
return 0;
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index a810dfc..5345d35 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -811,14 +811,18 @@ enum mac80211_rate_control_flags {
* in the control information, and it will be filled by the rate
* control algorithm according to what should be sent. For example,
* if this array contains, in the format { <idx>, <count> } the
- * information
+ * information::
+ *
* { 3, 2 }, { 2, 2 }, { 1, 4 }, { -1, 0 }, { -1, 0 }
+ *
* then this means that the frame should be transmitted
* up to twice at rate 3, up to twice at rate 2, and up to four
* times at rate 1 if it doesn't get acknowledged. Say it gets
* acknowledged by the peer after the fifth attempt, the status
- * information should then contain
+ * information should then contain::
+ *
* { 3, 2 }, { 2, 2 }, { 1, 1 }, { -1, 0 } ...
+ *
* since it was transmitted twice at rate 3, twice at rate 2
* and once at rate 1 after which we received an acknowledgement.
*/
@@ -1168,8 +1172,8 @@ enum mac80211_rx_vht_flags {
* @rate_idx: index of data rate into band's supported rates or MCS index if
* HT or VHT is used (%RX_FLAG_HT/%RX_FLAG_VHT)
* @vht_nss: number of streams (VHT only)
- * @flag: %RX_FLAG_*
- * @vht_flag: %RX_VHT_FLAG_*
+ * @flag: %RX_FLAG_\*
+ * @vht_flag: %RX_VHT_FLAG_\*
* @rx_flags: internal RX flags for mac80211
* @ampdu_reference: A-MPDU reference number, must be a different value for
* each A-MPDU but the same for each subframe within one A-MPDU
@@ -1432,13 +1436,13 @@ enum ieee80211_vif_flags {
* @probe_req_reg: probe requests should be reported to mac80211 for this
* interface.
* @drv_priv: data area for driver use, will always be aligned to
- * sizeof(void *).
+ * sizeof(void \*).
* @txq: the multicast data TX queue (if driver uses the TXQ abstraction)
*/
struct ieee80211_vif {
enum nl80211_iftype type;
struct ieee80211_bss_conf bss_conf;
- u8 addr[ETH_ALEN];
+ u8 addr[ETH_ALEN] __aligned(2);
bool p2p;
bool csa_active;
bool mu_mimo_owner;
@@ -1743,9 +1747,10 @@ struct ieee80211_sta_rates {
* @wme: indicates whether the STA supports QoS/WME (if local devices does,
* otherwise always false)
* @drv_priv: data area for driver use, will always be aligned to
- * sizeof(void *), size is determined in hw information.
+ * sizeof(void \*), size is determined in hw information.
* @uapsd_queues: bitmap of queues configured for uapsd. Only valid
- * if wme is supported.
+ * if wme is supported. The bits order is like in
+ * IEEE80211_WMM_IE_STA_QOSINFO_AC_*.
* @max_sp: max Service Period. Only valid if wme is supported.
* @bandwidth: current bandwidth the station can receive with
* @rx_nss: in HT/VHT, the maximum number of spatial streams the
@@ -2025,6 +2030,10 @@ struct ieee80211_txq {
* drivers, mac80211 packet loss mechanism will not be triggered and driver
* is completely depending on firmware event for station kickout.
*
+ * @IEEE80211_HW_SUPPORTS_TX_FRAG: Hardware does fragmentation by itself.
+ * The stack will not do fragmentation.
+ * The callback for @set_frag_threshold should be set as well.
+ *
* @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays
*/
enum ieee80211_hw_flags {
@@ -2066,6 +2075,7 @@ enum ieee80211_hw_flags {
IEEE80211_HW_TX_AMSDU,
IEEE80211_HW_TX_FRAG_LIST,
IEEE80211_HW_REPORTS_LOW_ACK,
+ IEEE80211_HW_SUPPORTS_TX_FRAG,
/* keep last, obviously */
NUM_IEEE80211_HW_FLAGS
@@ -2146,12 +2156,12 @@ enum ieee80211_hw_flags {
*
* @radiotap_mcs_details: lists which MCS information can the HW
* reports, by default it is set to _MCS, _GI and _BW but doesn't
- * include _FMT. Use %IEEE80211_RADIOTAP_MCS_HAVE_* values, only
+ * include _FMT. Use %IEEE80211_RADIOTAP_MCS_HAVE_\* values, only
* adding _BW is supported today.
*
* @radiotap_vht_details: lists which VHT MCS information the HW reports,
* the default is _GI | _BANDWIDTH.
- * Use the %IEEE80211_RADIOTAP_VHT_KNOWN_* values.
+ * Use the %IEEE80211_RADIOTAP_VHT_KNOWN_\* values.
*
* @radiotap_timestamp: Information for the radiotap timestamp field; if the
* 'units_pos' member is set to a non-negative value it must be set to
@@ -2486,6 +2496,7 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb);
* in the software stack cares about, we will, in the future, have mac80211
* tell the driver which information elements are interesting in the sense
* that we want to see changes in them. This will include
+ *
* - a list of information element IDs
* - a list of OUIs for the vendor information element
*
@@ -3093,8 +3104,9 @@ enum ieee80211_reconfig_type {
* The callback must be atomic.
*
* @set_frag_threshold: Configuration of fragmentation threshold. Assign this
- * if the device does fragmentation by itself; if this callback is
- * implemented then the stack will not do fragmentation.
+ * if the device does fragmentation by itself. Note that to prevent the
+ * stack from doing fragmentation IEEE80211_HW_SUPPORTS_TX_FRAG
+ * should be set as well.
* The callback can sleep.
*
* @set_rts_threshold: Configuration of RTS threshold (if device needs it)
@@ -4087,6 +4099,10 @@ void ieee80211_sta_pspoll(struct ieee80211_sta *sta);
* This must be used in conjunction with ieee80211_sta_ps_transition()
* and possibly ieee80211_sta_pspoll(); calls to all three must be
* serialized.
+ * %IEEE80211_NUM_TIDS can be passed as the tid if the tid is unknown.
+ * In this case, mac80211 will not check that this tid maps to an AC
+ * that is trigger enabled and assume that the caller did the proper
+ * checks.
*/
void ieee80211_sta_uapsd_trigger(struct ieee80211_sta *sta, u8 tid);
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index fc4f757..d7149e9 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -291,7 +291,7 @@ struct pernet_operations {
int (*init)(struct net *net);
void (*exit)(struct net *net);
void (*exit_batch)(struct list_head *net_exit_list);
- int *id;
+ unsigned int *id;
size_t size;
};
diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h
index de629f1..e7b8365 100644
--- a/include/net/netfilter/nf_conntrack_l4proto.h
+++ b/include/net/netfilter/nf_conntrack_l4proto.h
@@ -98,7 +98,7 @@ struct nf_conntrack_l4proto {
const struct nla_policy *nla_policy;
} ctnl_timeout;
#endif
- int *net_id;
+ unsigned int *net_id;
/* Init l4proto pernet data */
int (*init_net)(struct net *net, u_int16_t proto);
@@ -125,14 +125,24 @@ struct nf_conntrack_l4proto *nf_ct_l4proto_find_get(u_int16_t l3proto,
void nf_ct_l4proto_put(struct nf_conntrack_l4proto *p);
/* Protocol pernet registration. */
+int nf_ct_l4proto_pernet_register_one(struct net *net,
+ struct nf_conntrack_l4proto *proto);
+void nf_ct_l4proto_pernet_unregister_one(struct net *net,
+ struct nf_conntrack_l4proto *proto);
int nf_ct_l4proto_pernet_register(struct net *net,
- struct nf_conntrack_l4proto *proto);
+ struct nf_conntrack_l4proto *proto[],
+ unsigned int num_proto);
void nf_ct_l4proto_pernet_unregister(struct net *net,
- struct nf_conntrack_l4proto *proto);
+ struct nf_conntrack_l4proto *proto[],
+ unsigned int num_proto);
/* Protocol global registration. */
-int nf_ct_l4proto_register(struct nf_conntrack_l4proto *proto);
-void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *proto);
+int nf_ct_l4proto_register_one(struct nf_conntrack_l4proto *proto);
+void nf_ct_l4proto_unregister_one(struct nf_conntrack_l4proto *proto);
+int nf_ct_l4proto_register(struct nf_conntrack_l4proto *proto[],
+ unsigned int num_proto);
+void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *proto[],
+ unsigned int num_proto);
/* Generic netlink helpers */
int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb,
diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h
index 4988146..1723a67 100644
--- a/include/net/netfilter/nf_conntrack_labels.h
+++ b/include/net/netfilter/nf_conntrack_labels.h
@@ -30,8 +30,7 @@ static inline struct nf_conn_labels *nf_ct_labels_ext_add(struct nf_conn *ct)
if (net->ct.labels_used == 0)
return NULL;
- return nf_ct_ext_add_length(ct, NF_CT_EXT_LABELS,
- sizeof(struct nf_conn_labels), GFP_ATOMIC);
+ return nf_ct_ext_add(ct, NF_CT_EXT_LABELS, GFP_ATOMIC);
#else
return NULL;
#endif
diff --git a/include/net/netfilter/nf_conntrack_synproxy.h b/include/net/netfilter/nf_conntrack_synproxy.h
index e693731..b0ca402 100644
--- a/include/net/netfilter/nf_conntrack_synproxy.h
+++ b/include/net/netfilter/nf_conntrack_synproxy.h
@@ -54,7 +54,7 @@ struct synproxy_net {
struct synproxy_stats __percpu *stats;
};
-extern int synproxy_net_id;
+extern unsigned int synproxy_net_id;
static inline struct synproxy_net *synproxy_pernet(struct net *net)
{
return net_generic(net, synproxy_net_id);
diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h
index 309cd26..a559aa4 100644
--- a/include/net/netfilter/nf_log.h
+++ b/include/net/netfilter/nf_log.h
@@ -109,5 +109,10 @@ void nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf,
const struct net_device *out,
const struct nf_loginfo *loginfo,
const char *prefix);
+void nf_log_l2packet(struct net *net, u_int8_t pf, unsigned int hooknum,
+ const struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ const struct nf_loginfo *loginfo, const char *prefix);
#endif /* _NF_LOG_H */
diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h
index 2280cfe..09948d1 100644
--- a/include/net/netfilter/nf_queue.h
+++ b/include/net/netfilter/nf_queue.h
@@ -12,6 +12,7 @@ struct nf_queue_entry {
unsigned int id;
struct nf_hook_state state;
+ struct nf_hook_entry *hook;
u16 size; /* sizeof(entry) + saved route keys */
/* extra space to store route keys */
diff --git a/include/net/netfilter/nf_socket.h b/include/net/netfilter/nf_socket.h
new file mode 100644
index 0000000..f2fc39c
--- /dev/null
+++ b/include/net/netfilter/nf_socket.h
@@ -0,0 +1,27 @@
+#ifndef _NF_SOCK_H_
+#define _NF_SOCK_H_
+
+struct net_device;
+struct sk_buff;
+struct sock;
+struct net;
+
+static inline bool nf_sk_is_transparent(struct sock *sk)
+{
+ switch (sk->sk_state) {
+ case TCP_TIME_WAIT:
+ return inet_twsk(sk)->tw_transparent;
+ case TCP_NEW_SYN_RECV:
+ return inet_rsk(inet_reqsk(sk))->no_srccheck;
+ default:
+ return inet_sk(sk)->transparent;
+ }
+}
+
+struct sock *nf_sk_lookup_slow_v4(struct net *net, const struct sk_buff *skb,
+ const struct net_device *indev);
+
+struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
+ const struct net_device *indev);
+
+#endif
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 5031e07..311f027 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -14,27 +14,43 @@
struct nft_pktinfo {
struct sk_buff *skb;
- struct net *net;
- const struct net_device *in;
- const struct net_device *out;
- u8 pf;
- u8 hook;
bool tprot_set;
u8 tprot;
/* for x_tables compatibility */
struct xt_action_param xt;
};
+static inline struct net *nft_net(const struct nft_pktinfo *pkt)
+{
+ return pkt->xt.state->net;
+}
+
+static inline unsigned int nft_hook(const struct nft_pktinfo *pkt)
+{
+ return pkt->xt.state->hook;
+}
+
+static inline u8 nft_pf(const struct nft_pktinfo *pkt)
+{
+ return pkt->xt.state->pf;
+}
+
+static inline const struct net_device *nft_in(const struct nft_pktinfo *pkt)
+{
+ return pkt->xt.state->in;
+}
+
+static inline const struct net_device *nft_out(const struct nft_pktinfo *pkt)
+{
+ return pkt->xt.state->out;
+}
+
static inline void nft_set_pktinfo(struct nft_pktinfo *pkt,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
pkt->skb = skb;
- pkt->net = pkt->xt.net = state->net;
- pkt->in = pkt->xt.in = state->in;
- pkt->out = pkt->xt.out = state->out;
- pkt->hook = pkt->xt.hooknum = state->hook;
- pkt->pf = pkt->xt.family = state->pf;
+ pkt->xt.state = state;
}
static inline void nft_set_pktinfo_proto_unspec(struct nft_pktinfo *pkt,
@@ -145,7 +161,7 @@ static inline enum nft_registers nft_type_to_reg(enum nft_data_types type)
return type == NFT_DATA_VERDICT ? NFT_REG_VERDICT : NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE;
}
-unsigned int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest);
+int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest);
unsigned int nft_parse_register(const struct nlattr *attr);
int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg);
@@ -542,7 +558,8 @@ void *nft_set_elem_init(const struct nft_set *set,
const struct nft_set_ext_tmpl *tmpl,
const u32 *key, const u32 *data,
u64 timeout, gfp_t gfp);
-void nft_set_elem_destroy(const struct nft_set *set, void *elem);
+void nft_set_elem_destroy(const struct nft_set *set, void *elem,
+ bool destroy_expr);
/**
* struct nft_set_gc_batch_head - nf_tables set garbage collection batch
@@ -693,7 +710,6 @@ static inline int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src)
{
int err;
- __module_get(src->ops->type->owner);
if (src->ops->clone) {
dst->ops = src->ops;
err = src->ops->clone(dst, src);
@@ -702,6 +718,8 @@ static inline int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src)
} else {
memcpy(dst, src, src->ops->size);
}
+
+ __module_get(src->ops->type->owner);
return 0;
}
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index 00f4f6b..862373d 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -1,12 +1,18 @@
#ifndef _NET_NF_TABLES_CORE_H
#define _NET_NF_TABLES_CORE_H
+extern struct nft_expr_type nft_imm_type;
+extern struct nft_expr_type nft_cmp_type;
+extern struct nft_expr_type nft_lookup_type;
+extern struct nft_expr_type nft_bitwise_type;
+extern struct nft_expr_type nft_byteorder_type;
+extern struct nft_expr_type nft_payload_type;
+extern struct nft_expr_type nft_dynset_type;
+extern struct nft_expr_type nft_range_type;
+
int nf_tables_core_module_init(void);
void nf_tables_core_module_exit(void);
-int nft_immediate_module_init(void);
-void nft_immediate_module_exit(void);
-
struct nft_cmp_fast_expr {
u32 data;
enum nft_registers sreg:8;
@@ -25,24 +31,6 @@ static inline u32 nft_cmp_fast_mask(unsigned int len)
extern const struct nft_expr_ops nft_cmp_fast_ops;
-int nft_cmp_module_init(void);
-void nft_cmp_module_exit(void);
-
-int nft_range_module_init(void);
-void nft_range_module_exit(void);
-
-int nft_lookup_module_init(void);
-void nft_lookup_module_exit(void);
-
-int nft_dynset_module_init(void);
-void nft_dynset_module_exit(void);
-
-int nft_bitwise_module_init(void);
-void nft_bitwise_module_exit(void);
-
-int nft_byteorder_module_init(void);
-void nft_byteorder_module_exit(void);
-
struct nft_payload {
enum nft_payload_bases base:8;
u8 offset;
@@ -62,7 +50,4 @@ struct nft_payload_set {
extern const struct nft_expr_ops nft_payload_fast_ops;
extern struct static_key_false nft_trace_enabled;
-int nft_payload_module_init(void);
-void nft_payload_module_exit(void);
-
#endif /* _NET_NF_TABLES_CORE_H */
diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h
new file mode 100644
index 0000000..cbedda0
--- /dev/null
+++ b/include/net/netfilter/nft_fib.h
@@ -0,0 +1,31 @@
+#ifndef _NFT_FIB_H_
+#define _NFT_FIB_H_
+
+struct nft_fib {
+ enum nft_registers dreg:8;
+ u8 result;
+ u32 flags;
+};
+
+extern const struct nla_policy nft_fib_policy[];
+
+int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr);
+int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ const struct nlattr * const tb[]);
+int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ const struct nft_data **data);
+
+
+void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
+ const struct nft_pktinfo *pkt);
+void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
+ const struct nft_pktinfo *pkt);
+
+void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
+ const struct nft_pktinfo *pkt);
+void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
+ const struct nft_pktinfo *pkt);
+
+void nft_fib_store_result(void *reg, enum nft_fib_result r,
+ const struct nft_pktinfo *pkt, int index);
+#endif
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index e469e85..3d06d94 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -91,7 +91,6 @@ struct netns_ct {
struct nf_ip_net nf_ct_proto;
#if defined(CONFIG_NF_CONNTRACK_LABELS)
unsigned int labels_used;
- u8 label_words;
#endif
};
#endif
diff --git a/include/net/netns/generic.h b/include/net/netns/generic.h
index 70e1585..d315786 100644
--- a/include/net/netns/generic.h
+++ b/include/net/netns/generic.h
@@ -31,7 +31,7 @@ struct net_generic {
void *ptr[0];
};
-static inline void *net_generic(const struct net *net, int id)
+static inline void *net_generic(const struct net *net, unsigned int id)
{
struct net_generic *ng;
void *ptr;
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 10d0848..de7745e 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -85,6 +85,7 @@ struct netns_ipv6 {
#endif
atomic_t dev_addr_genid;
atomic_t fib6_sernum;
+ struct seg6_pernet_data *seg6_data;
};
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index cd334c9..f1b76b8 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -6,6 +6,8 @@
#include <linux/if_vlan.h>
#include <net/sch_generic.h>
+#define DEFAULT_TX_QUEUE_LEN 1000
+
struct qdisc_walker {
int stop;
int skip;
diff --git a/include/net/route.h b/include/net/route.h
index 0429d47..c0874c8 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -153,7 +153,7 @@ static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi
flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos,
RT_SCOPE_UNIVERSE, proto,
sk ? inet_sk_flowi_flags(sk) : 0,
- daddr, saddr, dport, sport);
+ daddr, saddr, dport, sport, sock_net_uid(net, sk));
if (sk)
security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
return ip_route_output_flow(net, fl4, sk);
@@ -269,7 +269,8 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32
flow_flags |= FLOWI_FLAG_ANYSRC;
flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
- protocol, flow_flags, dst, src, dport, sport);
+ protocol, flow_flags, dst, src, dport, sport,
+ sk->sk_uid);
}
static inline struct rtable *ip_route_connect(struct flowi4 *fl4,
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 87a7f42..f0dcaeb 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -152,7 +152,7 @@ void sctp_unhash_endpoint(struct sctp_endpoint *);
struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *,
struct sctphdr *, struct sctp_association **,
struct sctp_transport **);
-void sctp_err_finish(struct sock *, struct sctp_association *);
+void sctp_err_finish(struct sock *, struct sctp_transport *);
void sctp_icmp_frag_needed(struct sock *, struct sctp_association *,
struct sctp_transport *t, __u32 pmtu);
void sctp_icmp_redirect(struct sock *, struct sctp_transport *,
@@ -164,7 +164,7 @@ void sctp_backlog_migrate(struct sctp_association *assoc,
struct sock *oldsk, struct sock *newsk);
int sctp_transport_hashtable_init(void);
void sctp_transport_hashtable_destroy(void);
-void sctp_hash_transport(struct sctp_transport *t);
+int sctp_hash_transport(struct sctp_transport *t);
void sctp_unhash_transport(struct sctp_transport *t);
struct sctp_transport *sctp_addrs_lookup_transport(
struct net *net,
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index bd4a3de..92daabd 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -124,7 +124,7 @@ extern struct sctp_globals {
/* This is the sctp port control hash. */
struct sctp_bind_hashbucket *port_hashtable;
/* This is the hash of all transports. */
- struct rhashtable transport_hashtable;
+ struct rhltable transport_hashtable;
/* Sizes of above hashtables. */
int ep_hashsize;
@@ -761,7 +761,7 @@ static inline int sctp_packet_empty(struct sctp_packet *packet)
struct sctp_transport {
/* A list of transports. */
struct list_head transports;
- struct rhash_head node;
+ struct rhlist_head node;
/* Reference counting. */
atomic_t refcnt;
diff --git a/include/net/seg6.h b/include/net/seg6.h
new file mode 100644
index 0000000..4e03575
--- /dev/null
+++ b/include/net/seg6.h
@@ -0,0 +1,62 @@
+/*
+ * SR-IPv6 implementation
+ *
+ * Author:
+ * David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _NET_SEG6_H
+#define _NET_SEG6_H
+
+#include <linux/net.h>
+#include <linux/ipv6.h>
+#include <net/lwtunnel.h>
+#include <linux/seg6.h>
+#include <linux/rhashtable.h>
+
+static inline void update_csum_diff4(struct sk_buff *skb, __be32 from,
+ __be32 to)
+{
+ __be32 diff[] = { ~from, to };
+
+ skb->csum = ~csum_partial((char *)diff, sizeof(diff), ~skb->csum);
+}
+
+static inline void update_csum_diff16(struct sk_buff *skb, __be32 *from,
+ __be32 *to)
+{
+ __be32 diff[] = {
+ ~from[0], ~from[1], ~from[2], ~from[3],
+ to[0], to[1], to[2], to[3],
+ };
+
+ skb->csum = ~csum_partial((char *)diff, sizeof(diff), ~skb->csum);
+}
+
+struct seg6_pernet_data {
+ struct mutex lock;
+ struct in6_addr __rcu *tun_src;
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ struct rhashtable hmac_infos;
+#endif
+};
+
+static inline struct seg6_pernet_data *seg6_pernet(struct net *net)
+{
+ return net->ipv6.seg6_data;
+}
+
+extern int seg6_init(void);
+extern void seg6_exit(void);
+extern int seg6_iptunnel_init(void);
+extern void seg6_iptunnel_exit(void);
+
+extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len);
+
+#endif
diff --git a/include/net/seg6_hmac.h b/include/net/seg6_hmac.h
new file mode 100644
index 0000000..69c3a10
--- /dev/null
+++ b/include/net/seg6_hmac.h
@@ -0,0 +1,62 @@
+/*
+ * SR-IPv6 implementation
+ *
+ * Author:
+ * David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _NET_SEG6_HMAC_H
+#define _NET_SEG6_HMAC_H
+
+#include <net/flow.h>
+#include <net/ip6_fib.h>
+#include <net/sock.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/route.h>
+#include <net/seg6.h>
+#include <linux/seg6_hmac.h>
+#include <linux/rhashtable.h>
+
+#define SEG6_HMAC_MAX_DIGESTSIZE 160
+#define SEG6_HMAC_RING_SIZE 256
+
+struct seg6_hmac_info {
+ struct rhash_head node;
+ struct rcu_head rcu;
+
+ u32 hmackeyid;
+ char secret[SEG6_HMAC_SECRET_LEN];
+ u8 slen;
+ u8 alg_id;
+};
+
+struct seg6_hmac_algo {
+ u8 alg_id;
+ char name[64];
+ struct crypto_shash * __percpu *tfms;
+ struct shash_desc * __percpu *shashs;
+};
+
+extern int seg6_hmac_compute(struct seg6_hmac_info *hinfo,
+ struct ipv6_sr_hdr *hdr, struct in6_addr *saddr,
+ u8 *output);
+extern struct seg6_hmac_info *seg6_hmac_info_lookup(struct net *net, u32 key);
+extern int seg6_hmac_info_add(struct net *net, u32 key,
+ struct seg6_hmac_info *hinfo);
+extern int seg6_hmac_info_del(struct net *net, u32 key);
+extern int seg6_push_hmac(struct net *net, struct in6_addr *saddr,
+ struct ipv6_sr_hdr *srh);
+extern bool seg6_hmac_validate_skb(struct sk_buff *skb);
+extern int seg6_hmac_init(void);
+extern void seg6_hmac_exit(void);
+extern int seg6_hmac_net_init(struct net *net);
+extern void seg6_hmac_net_exit(struct net *net);
+
+#endif
diff --git a/include/net/sock.h b/include/net/sock.h
index 2764895..442cbb1 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -252,6 +252,7 @@ struct sock_common {
* @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
* @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
* @sk_sndbuf: size of send buffer in bytes
+ * @sk_padding: unused element for alignment
* @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
* @sk_no_check_rx: allow zero checksum in RX packets
* @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
@@ -302,7 +303,8 @@ struct sock_common {
* @sk_backlog_rcv: callback to process the backlog
* @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
* @sk_reuseport_cb: reuseport group container
- */
+ * @sk_rcu: used during RCU grace period
+ */
struct sock {
/*
* Now struct inet_timewait_sock also uses sock_common, so please just
@@ -417,6 +419,7 @@ struct sock {
u32 sk_max_ack_backlog;
__u32 sk_priority;
__u32 sk_mark;
+ kuid_t sk_uid;
struct pid *sk_peer_pid;
const struct cred *sk_peer_cred;
long sk_rcvtimeo;
@@ -912,14 +915,16 @@ static inline void sock_rps_reset_rxhash(struct sock *sk)
#endif
}
-#define sk_wait_event(__sk, __timeo, __condition) \
+#define sk_wait_event(__sk, __timeo, __condition, __wait) \
({ int __rc; \
release_sock(__sk); \
__rc = __condition; \
if (!__rc) { \
- *(__timeo) = schedule_timeout(*(__timeo)); \
+ *(__timeo) = wait_woken(__wait, \
+ TASK_INTERRUPTIBLE, \
+ *(__timeo)); \
} \
- sched_annotate_sleep(); \
+ sched_annotate_sleep(); \
lock_sock(__sk); \
__rc = __condition; \
__rc; \
@@ -1160,11 +1165,6 @@ static inline void sk_enter_memory_pressure(struct sock *sk)
sk->sk_prot->enter_memory_pressure(sk);
}
-static inline long sk_prot_mem_limits(const struct sock *sk, int index)
-{
- return sk->sk_prot->sysctl_mem[index];
-}
-
static inline long
sk_memory_allocated(const struct sock *sk)
{
@@ -1279,11 +1279,27 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind);
void __sk_mem_reduce_allocated(struct sock *sk, int amount);
void __sk_mem_reclaim(struct sock *sk, int amount);
-#define SK_MEM_QUANTUM ((int)PAGE_SIZE)
+/* We used to have PAGE_SIZE here, but systems with 64KB pages
+ * do not necessarily have 16x time more memory than 4KB ones.
+ */
+#define SK_MEM_QUANTUM 4096
#define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM)
#define SK_MEM_SEND 0
#define SK_MEM_RECV 1
+/* sysctl_mem values are in pages, we convert them in SK_MEM_QUANTUM units */
+static inline long sk_prot_mem_limits(const struct sock *sk, int index)
+{
+ long val = sk->sk_prot->sysctl_mem[index];
+
+#if PAGE_SIZE > SK_MEM_QUANTUM
+ val <<= PAGE_SHIFT - SK_MEM_QUANTUM_SHIFT;
+#elif PAGE_SIZE < SK_MEM_QUANTUM
+ val >>= SK_MEM_QUANTUM_SHIFT - PAGE_SHIFT;
+#endif
+ return val;
+}
+
static inline int sk_mem_pages(int amt)
{
return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT;
@@ -1596,11 +1612,11 @@ static inline void sock_put(struct sock *sk)
void sock_gen_put(struct sock *sk);
int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested,
- unsigned int trim_cap);
+ unsigned int trim_cap, bool refcounted);
static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
const int nested)
{
- return __sk_receive_skb(sk, skb, nested, 1);
+ return __sk_receive_skb(sk, skb, nested, 1, true);
}
static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
@@ -1651,6 +1667,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
sk->sk_wq = parent->wq;
parent->sk = sk;
sk_set_socket(sk, parent);
+ sk->sk_uid = SOCK_INODE(parent)->i_uid;
security_sock_graft(sk, parent);
write_unlock_bh(&sk->sk_callback_lock);
}
@@ -1658,6 +1675,11 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
kuid_t sock_i_uid(struct sock *sk);
unsigned long sock_i_ino(struct sock *sk);
+static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk)
+{
+ return sk ? sk->sk_uid : make_kuid(net->user_ns, 0);
+}
+
static inline u32 net_tx_rndhash(void)
{
u32 v = prandom_u32();
diff --git a/include/net/tc_act/tc_tunnel_key.h b/include/net/tc_act/tc_tunnel_key.h
index 253f8da..efef0b4 100644
--- a/include/net/tc_act/tc_tunnel_key.h
+++ b/include/net/tc_act/tc_tunnel_key.h
@@ -12,6 +12,8 @@
#define __NET_TC_TUNNEL_KEY_H
#include <net/act_api.h>
+#include <linux/tc_act/tc_tunnel_key.h>
+#include <net/dst_metadata.h>
struct tcf_tunnel_key_params {
struct rcu_head rcu;
@@ -27,4 +29,39 @@ struct tcf_tunnel_key {
#define to_tunnel_key(a) ((struct tcf_tunnel_key *)a)
+static inline bool is_tcf_tunnel_set(const struct tc_action *a)
+{
+#ifdef CONFIG_NET_CLS_ACT
+ struct tcf_tunnel_key *t = to_tunnel_key(a);
+ struct tcf_tunnel_key_params *params = rtnl_dereference(t->params);
+
+ if (a->ops && a->ops->type == TCA_ACT_TUNNEL_KEY)
+ return params->tcft_action == TCA_TUNNEL_KEY_ACT_SET;
+#endif
+ return false;
+}
+
+static inline bool is_tcf_tunnel_release(const struct tc_action *a)
+{
+#ifdef CONFIG_NET_CLS_ACT
+ struct tcf_tunnel_key *t = to_tunnel_key(a);
+ struct tcf_tunnel_key_params *params = rtnl_dereference(t->params);
+
+ if (a->ops && a->ops->type == TCA_ACT_TUNNEL_KEY)
+ return params->tcft_action == TCA_TUNNEL_KEY_ACT_RELEASE;
+#endif
+ return false;
+}
+
+static inline struct ip_tunnel_info *tcf_tunnel_info(const struct tc_action *a)
+{
+#ifdef CONFIG_NET_CLS_ACT
+ struct tcf_tunnel_key *t = to_tunnel_key(a);
+ struct tcf_tunnel_key_params *params = rtnl_dereference(t->params);
+
+ return ¶ms->tcft_enc_metadata->u.tun_info;
+#else
+ return NULL;
+#endif
+}
#endif /* __NET_TC_TUNNEL_KEY_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f83b7f2..123979f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -794,12 +794,23 @@ struct tcp_skb_cb {
*/
static inline int tcp_v6_iif(const struct sk_buff *skb)
{
- bool l3_slave = skb_l3mdev_slave(TCP_SKB_CB(skb)->header.h6.flags);
+ bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif;
}
#endif
+/* TCP_SKB_CB reference means this can not be used from early demux */
+static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+ if (!net->ipv4.sysctl_tcp_l3mdev_accept &&
+ skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags))
+ return true;
+#endif
+ return false;
+}
+
/* Due to TSO, an SKB can be composed of multiple actual
* packets. To keep these tracked properly, we use this.
*/
@@ -1209,6 +1220,7 @@ static inline void tcp_prequeue_init(struct tcp_sock *tp)
bool tcp_prequeue(struct sock *sk, struct sk_buff *skb);
bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb);
+int tcp_filter(struct sock *sk, struct sk_buff *skb);
#undef STATE_TRACE
diff --git a/include/net/udp.h b/include/net/udp.h
index 18f1e6b..1661791 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -246,8 +246,24 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb,
}
/* net/ipv4/udp.c */
+void udp_destruct_sock(struct sock *sk);
void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len);
int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb);
+void udp_skb_destructor(struct sock *sk, struct sk_buff *skb);
+static inline struct sk_buff *
+__skb_recv_udp(struct sock *sk, unsigned int flags, int noblock, int *peeked,
+ int *off, int *err)
+{
+ return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
+ udp_skb_destructor, peeked, off, err);
+}
+static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags,
+ int noblock, int *err)
+{
+ int peeked, off = 0;
+
+ return __skb_recv_udp(sk, flags, noblock, &peeked, &off, err);
+}
void udp_v4_early_demux(struct sk_buff *skb);
int udp_get_port(struct sock *sk, unsigned short snum,
@@ -262,6 +278,7 @@ void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst);
int udp_rcv(struct sk_buff *skb);
int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
int udp_init_sock(struct sock *sk);
+int __udp_disconnect(struct sock *sk, int flags);
int udp_disconnect(struct sock *sk, int flags);
unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait);
struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
diff --git a/include/net/udplite.h b/include/net/udplite.h
index 8076193..36097d3 100644
--- a/include/net/udplite.h
+++ b/include/net/udplite.h
@@ -27,6 +27,7 @@ static __inline__ int udplite_getfrag(void *from, char *to, int offset,
static inline int udplite_sk_init(struct sock *sk)
{
udp_sk(sk)->pcflag = UDPLITE_BIT;
+ sk->sk_destruct = udp_destruct_sock;
return 0;
}
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 0255613..49a5920 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -225,9 +225,9 @@ struct vxlan_config {
struct vxlan_dev {
struct hlist_node hlist; /* vni hash table */
struct list_head next; /* vxlan's per namespace list */
- struct vxlan_sock *vn4_sock; /* listening socket for IPv4 */
+ struct vxlan_sock __rcu *vn4_sock; /* listening socket for IPv4 */
#if IS_ENABLED(CONFIG_IPV6)
- struct vxlan_sock *vn6_sock; /* listening socket for IPv6 */
+ struct vxlan_sock __rcu *vn6_sock; /* listening socket for IPv6 */
#endif
struct net_device *dev;
struct net *net; /* netns for packet i/o */
@@ -281,16 +281,6 @@ struct vxlan_dev {
struct net_device *vxlan_dev_create(struct net *net, const char *name,
u8 name_assign_type, struct vxlan_config *conf);
-static inline __be16 vxlan_dev_dst_port(struct vxlan_dev *vxlan,
- unsigned short family)
-{
-#if IS_ENABLED(CONFIG_IPV6)
- if (family == AF_INET6)
- return inet_sk(vxlan->vn6_sock->sock->sk)->inet_sport;
-#endif
- return inet_sk(vxlan->vn4_sock->sock->sk)->inet_sport;
-}
-
static inline netdev_features_t vxlan_features_check(struct sk_buff *skb,
netdev_features_t features)
{
diff --git a/include/soc/fsl/bman.h b/include/soc/fsl/bman.h
new file mode 100644
index 0000000..eaaf56d
--- /dev/null
+++ b/include/soc/fsl/bman.h
@@ -0,0 +1,129 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __FSL_BMAN_H
+#define __FSL_BMAN_H
+
+/* wrapper for 48-bit buffers */
+struct bm_buffer {
+ union {
+ struct {
+ __be16 bpid; /* hi 8-bits reserved */
+ __be16 hi; /* High 16-bits of 48-bit address */
+ __be32 lo; /* Low 32-bits of 48-bit address */
+ };
+ __be64 data;
+ };
+} __aligned(8);
+/*
+ * Restore the 48 bit address previously stored in BMan
+ * hardware pools as a dma_addr_t
+ */
+static inline dma_addr_t bm_buf_addr(const struct bm_buffer *buf)
+{
+ return be64_to_cpu(buf->data) & 0xffffffffffffLLU;
+}
+
+static inline u64 bm_buffer_get64(const struct bm_buffer *buf)
+{
+ return be64_to_cpu(buf->data) & 0xffffffffffffLLU;
+}
+
+static inline void bm_buffer_set64(struct bm_buffer *buf, u64 addr)
+{
+ buf->hi = cpu_to_be16(upper_32_bits(addr));
+ buf->lo = cpu_to_be32(lower_32_bits(addr));
+}
+
+static inline u8 bm_buffer_get_bpid(const struct bm_buffer *buf)
+{
+ return be16_to_cpu(buf->bpid) & 0xff;
+}
+
+static inline void bm_buffer_set_bpid(struct bm_buffer *buf, int bpid)
+{
+ buf->bpid = cpu_to_be16(bpid & 0xff);
+}
+
+/* Managed portal, high-level i/face */
+
+/* Portal and Buffer Pools */
+struct bman_portal;
+struct bman_pool;
+
+#define BM_POOL_MAX 64 /* max # of buffer pools */
+
+/**
+ * bman_new_pool - Allocates a Buffer Pool object
+ *
+ * Creates a pool object, and returns a reference to it or NULL on error.
+ */
+struct bman_pool *bman_new_pool(void);
+
+/**
+ * bman_free_pool - Deallocates a Buffer Pool object
+ * @pool: the pool object to release
+ */
+void bman_free_pool(struct bman_pool *pool);
+
+/**
+ * bman_get_bpid - Returns a pool object's BPID.
+ * @pool: the pool object
+ *
+ * The returned value is the index of the encapsulated buffer pool,
+ * in the range of [0, @BM_POOL_MAX-1].
+ */
+int bman_get_bpid(const struct bman_pool *pool);
+
+/**
+ * bman_release - Release buffer(s) to the buffer pool
+ * @pool: the buffer pool object to release to
+ * @bufs: an array of buffers to release
+ * @num: the number of buffers in @bufs (1-8)
+ *
+ * Adds the given buffers to RCR entries. If the RCR ring is unresponsive,
+ * the function will return -ETIMEDOUT. Otherwise, it returns zero.
+ */
+int bman_release(struct bman_pool *pool, const struct bm_buffer *bufs, u8 num);
+
+/**
+ * bman_acquire - Acquire buffer(s) from a buffer pool
+ * @pool: the buffer pool object to acquire from
+ * @bufs: array for storing the acquired buffers
+ * @num: the number of buffers desired (@bufs is at least this big)
+ *
+ * Issues an "Acquire" command via the portal's management command interface.
+ * The return value will be the number of buffers obtained from the pool, or a
+ * negative error code if a h/w error or pool starvation was encountered. In
+ * the latter case, the content of @bufs is undefined.
+ */
+int bman_acquire(struct bman_pool *pool, struct bm_buffer *bufs, u8 num);
+
+#endif /* __FSL_BMAN_H */
diff --git a/include/soc/fsl/qman.h b/include/soc/fsl/qman.h
new file mode 100644
index 0000000..37f3eb0
--- /dev/null
+++ b/include/soc/fsl/qman.h
@@ -0,0 +1,1074 @@
+/* Copyright 2008 - 2016 Freescale Semiconductor, Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __FSL_QMAN_H
+#define __FSL_QMAN_H
+
+#include <linux/bitops.h>
+
+/* Hardware constants */
+#define QM_CHANNEL_SWPORTAL0 0
+#define QMAN_CHANNEL_POOL1 0x21
+#define QMAN_CHANNEL_POOL1_REV3 0x401
+extern u16 qm_channel_pool1;
+
+/* Portal processing (interrupt) sources */
+#define QM_PIRQ_CSCI 0x00100000 /* Congestion State Change */
+#define QM_PIRQ_EQCI 0x00080000 /* Enqueue Command Committed */
+#define QM_PIRQ_EQRI 0x00040000 /* EQCR Ring (below threshold) */
+#define QM_PIRQ_DQRI 0x00020000 /* DQRR Ring (non-empty) */
+#define QM_PIRQ_MRI 0x00010000 /* MR Ring (non-empty) */
+/*
+ * This mask contains all the interrupt sources that need handling except DQRI,
+ * ie. that if present should trigger slow-path processing.
+ */
+#define QM_PIRQ_SLOW (QM_PIRQ_CSCI | QM_PIRQ_EQCI | QM_PIRQ_EQRI | \
+ QM_PIRQ_MRI)
+
+/* For qman_static_dequeue_*** APIs */
+#define QM_SDQCR_CHANNELS_POOL_MASK 0x00007fff
+/* for n in [1,15] */
+#define QM_SDQCR_CHANNELS_POOL(n) (0x00008000 >> (n))
+/* for conversion from n of qm_channel */
+static inline u32 QM_SDQCR_CHANNELS_POOL_CONV(u16 channel)
+{
+ return QM_SDQCR_CHANNELS_POOL(channel + 1 - qm_channel_pool1);
+}
+
+/* --- QMan data structures (and associated constants) --- */
+
+/* "Frame Descriptor (FD)" */
+struct qm_fd {
+ union {
+ struct {
+ u8 cfg8b_w1;
+ u8 bpid; /* Buffer Pool ID */
+ u8 cfg8b_w3;
+ u8 addr_hi; /* high 8-bits of 40-bit address */
+ __be32 addr_lo; /* low 32-bits of 40-bit address */
+ } __packed;
+ __be64 data;
+ };
+ __be32 cfg; /* format, offset, length / congestion */
+ union {
+ __be32 cmd;
+ __be32 status;
+ };
+} __aligned(8);
+
+#define QM_FD_FORMAT_SG BIT(31)
+#define QM_FD_FORMAT_LONG BIT(30)
+#define QM_FD_FORMAT_COMPOUND BIT(29)
+#define QM_FD_FORMAT_MASK GENMASK(31, 29)
+#define QM_FD_OFF_SHIFT 20
+#define QM_FD_OFF_MASK GENMASK(28, 20)
+#define QM_FD_LEN_MASK GENMASK(19, 0)
+#define QM_FD_LEN_BIG_MASK GENMASK(28, 0)
+
+enum qm_fd_format {
+ /*
+ * 'contig' implies a contiguous buffer, whereas 'sg' implies a
+ * scatter-gather table. 'big' implies a 29-bit length with no offset
+ * field, otherwise length is 20-bit and offset is 9-bit. 'compound'
+ * implies a s/g-like table, where each entry itself represents a frame
+ * (contiguous or scatter-gather) and the 29-bit "length" is
+ * interpreted purely for congestion calculations, ie. a "congestion
+ * weight".
+ */
+ qm_fd_contig = 0,
+ qm_fd_contig_big = QM_FD_FORMAT_LONG,
+ qm_fd_sg = QM_FD_FORMAT_SG,
+ qm_fd_sg_big = QM_FD_FORMAT_SG | QM_FD_FORMAT_LONG,
+ qm_fd_compound = QM_FD_FORMAT_COMPOUND
+};
+
+static inline dma_addr_t qm_fd_addr(const struct qm_fd *fd)
+{
+ return be64_to_cpu(fd->data) & 0xffffffffffLLU;
+}
+
+static inline u64 qm_fd_addr_get64(const struct qm_fd *fd)
+{
+ return be64_to_cpu(fd->data) & 0xffffffffffLLU;
+}
+
+static inline void qm_fd_addr_set64(struct qm_fd *fd, u64 addr)
+{
+ fd->addr_hi = upper_32_bits(addr);
+ fd->addr_lo = cpu_to_be32(lower_32_bits(addr));
+}
+
+/*
+ * The 'format' field indicates the interpretation of the remaining
+ * 29 bits of the 32-bit word.
+ * If 'format' is _contig or _sg, 20b length and 9b offset.
+ * If 'format' is _contig_big or _sg_big, 29b length.
+ * If 'format' is _compound, 29b "congestion weight".
+ */
+static inline enum qm_fd_format qm_fd_get_format(const struct qm_fd *fd)
+{
+ return be32_to_cpu(fd->cfg) & QM_FD_FORMAT_MASK;
+}
+
+static inline int qm_fd_get_offset(const struct qm_fd *fd)
+{
+ return (be32_to_cpu(fd->cfg) & QM_FD_OFF_MASK) >> QM_FD_OFF_SHIFT;
+}
+
+static inline int qm_fd_get_length(const struct qm_fd *fd)
+{
+ return be32_to_cpu(fd->cfg) & QM_FD_LEN_MASK;
+}
+
+static inline int qm_fd_get_len_big(const struct qm_fd *fd)
+{
+ return be32_to_cpu(fd->cfg) & QM_FD_LEN_BIG_MASK;
+}
+
+static inline void qm_fd_set_param(struct qm_fd *fd, enum qm_fd_format fmt,
+ int off, int len)
+{
+ fd->cfg = cpu_to_be32(fmt | (len & QM_FD_LEN_BIG_MASK) |
+ ((off << QM_FD_OFF_SHIFT) & QM_FD_OFF_MASK));
+}
+
+#define qm_fd_set_contig(fd, off, len) \
+ qm_fd_set_param(fd, qm_fd_contig, off, len)
+#define qm_fd_set_sg(fd, off, len) qm_fd_set_param(fd, qm_fd_sg, off, len)
+#define qm_fd_set_contig_big(fd, len) \
+ qm_fd_set_param(fd, qm_fd_contig_big, 0, len)
+#define qm_fd_set_sg_big(fd, len) qm_fd_set_param(fd, qm_fd_sg_big, 0, len)
+
+static inline void qm_fd_clear_fd(struct qm_fd *fd)
+{
+ fd->data = 0;
+ fd->cfg = 0;
+ fd->cmd = 0;
+}
+
+/* Scatter/Gather table entry */
+struct qm_sg_entry {
+ union {
+ struct {
+ u8 __reserved1[3];
+ u8 addr_hi; /* high 8-bits of 40-bit address */
+ __be32 addr_lo; /* low 32-bits of 40-bit address */
+ };
+ __be64 data;
+ };
+ __be32 cfg; /* E bit, F bit, length */
+ u8 __reserved2;
+ u8 bpid;
+ __be16 offset; /* 13-bit, _res[13-15]*/
+} __packed;
+
+#define QM_SG_LEN_MASK GENMASK(29, 0)
+#define QM_SG_OFF_MASK GENMASK(12, 0)
+#define QM_SG_FIN BIT(30)
+#define QM_SG_EXT BIT(31)
+
+static inline dma_addr_t qm_sg_addr(const struct qm_sg_entry *sg)
+{
+ return be64_to_cpu(sg->data) & 0xffffffffffLLU;
+}
+
+static inline u64 qm_sg_entry_get64(const struct qm_sg_entry *sg)
+{
+ return be64_to_cpu(sg->data) & 0xffffffffffLLU;
+}
+
+static inline void qm_sg_entry_set64(struct qm_sg_entry *sg, u64 addr)
+{
+ sg->addr_hi = upper_32_bits(addr);
+ sg->addr_lo = cpu_to_be32(lower_32_bits(addr));
+}
+
+static inline bool qm_sg_entry_is_final(const struct qm_sg_entry *sg)
+{
+ return be32_to_cpu(sg->cfg) & QM_SG_FIN;
+}
+
+static inline bool qm_sg_entry_is_ext(const struct qm_sg_entry *sg)
+{
+ return be32_to_cpu(sg->cfg) & QM_SG_EXT;
+}
+
+static inline int qm_sg_entry_get_len(const struct qm_sg_entry *sg)
+{
+ return be32_to_cpu(sg->cfg) & QM_SG_LEN_MASK;
+}
+
+static inline void qm_sg_entry_set_len(struct qm_sg_entry *sg, int len)
+{
+ sg->cfg = cpu_to_be32(len & QM_SG_LEN_MASK);
+}
+
+static inline void qm_sg_entry_set_f(struct qm_sg_entry *sg, int len)
+{
+ sg->cfg = cpu_to_be32(QM_SG_FIN | (len & QM_SG_LEN_MASK));
+}
+
+static inline int qm_sg_entry_get_off(const struct qm_sg_entry *sg)
+{
+ return be32_to_cpu(sg->offset) & QM_SG_OFF_MASK;
+}
+
+/* "Frame Dequeue Response" */
+struct qm_dqrr_entry {
+ u8 verb;
+ u8 stat;
+ u16 seqnum; /* 15-bit */
+ u8 tok;
+ u8 __reserved2[3];
+ u32 fqid; /* 24-bit */
+ u32 contextB;
+ struct qm_fd fd;
+ u8 __reserved4[32];
+} __packed;
+#define QM_DQRR_VERB_VBIT 0x80
+#define QM_DQRR_VERB_MASK 0x7f /* where the verb contains; */
+#define QM_DQRR_VERB_FRAME_DEQUEUE 0x60 /* "this format" */
+#define QM_DQRR_STAT_FQ_EMPTY 0x80 /* FQ empty */
+#define QM_DQRR_STAT_FQ_HELDACTIVE 0x40 /* FQ held active */
+#define QM_DQRR_STAT_FQ_FORCEELIGIBLE 0x20 /* FQ was force-eligible'd */
+#define QM_DQRR_STAT_FD_VALID 0x10 /* has a non-NULL FD */
+#define QM_DQRR_STAT_UNSCHEDULED 0x02 /* Unscheduled dequeue */
+#define QM_DQRR_STAT_DQCR_EXPIRED 0x01 /* VDQCR or PDQCR expired*/
+
+/* "ERN Message Response" */
+/* "FQ State Change Notification" */
+union qm_mr_entry {
+ struct {
+ u8 verb;
+ u8 __reserved[63];
+ };
+ struct {
+ u8 verb;
+ u8 dca;
+ u16 seqnum;
+ u8 rc; /* Rej Code: 8-bit */
+ u8 orp_hi; /* ORP: 24-bit */
+ u16 orp_lo;
+ u32 fqid; /* 24-bit */
+ u32 tag;
+ struct qm_fd fd;
+ u8 __reserved1[32];
+ } __packed ern;
+ struct {
+ u8 verb;
+ u8 fqs; /* Frame Queue Status */
+ u8 __reserved1[6];
+ u32 fqid; /* 24-bit */
+ u32 contextB;
+ u8 __reserved2[48];
+ } __packed fq; /* FQRN/FQRNI/FQRL/FQPN */
+};
+#define QM_MR_VERB_VBIT 0x80
+/*
+ * ERNs originating from direct-connect portals ("dcern") use 0x20 as a verb
+ * which would be invalid as a s/w enqueue verb. A s/w ERN can be distinguished
+ * from the other MR types by noting if the 0x20 bit is unset.
+ */
+#define QM_MR_VERB_TYPE_MASK 0x27
+#define QM_MR_VERB_DC_ERN 0x20
+#define QM_MR_VERB_FQRN 0x21
+#define QM_MR_VERB_FQRNI 0x22
+#define QM_MR_VERB_FQRL 0x23
+#define QM_MR_VERB_FQPN 0x24
+#define QM_MR_RC_MASK 0xf0 /* contains one of; */
+#define QM_MR_RC_CGR_TAILDROP 0x00
+#define QM_MR_RC_WRED 0x10
+#define QM_MR_RC_ERROR 0x20
+#define QM_MR_RC_ORPWINDOW_EARLY 0x30
+#define QM_MR_RC_ORPWINDOW_LATE 0x40
+#define QM_MR_RC_FQ_TAILDROP 0x50
+#define QM_MR_RC_ORPWINDOW_RETIRED 0x60
+#define QM_MR_RC_ORP_ZERO 0x70
+#define QM_MR_FQS_ORLPRESENT 0x02 /* ORL fragments to come */
+#define QM_MR_FQS_NOTEMPTY 0x01 /* FQ has enqueued frames */
+
+/*
+ * An identical structure of FQD fields is present in the "Init FQ" command and
+ * the "Query FQ" result, it's suctioned out into the "struct qm_fqd" type.
+ * Within that, the 'stashing' and 'taildrop' pieces are also factored out, the
+ * latter has two inlines to assist with converting to/from the mant+exp
+ * representation.
+ */
+struct qm_fqd_stashing {
+ /* See QM_STASHING_EXCL_<...> */
+ u8 exclusive;
+ /* Numbers of cachelines */
+ u8 cl; /* _res[6-7], as[4-5], ds[2-3], cs[0-1] */
+};
+
+struct qm_fqd_oac {
+ /* "Overhead Accounting Control", see QM_OAC_<...> */
+ u8 oac; /* oac[6-7], _res[0-5] */
+ /* Two's-complement value (-128 to +127) */
+ s8 oal; /* "Overhead Accounting Length" */
+};
+
+struct qm_fqd {
+ /* _res[6-7], orprws[3-5], oa[2], olws[0-1] */
+ u8 orpc;
+ u8 cgid;
+ __be16 fq_ctrl; /* See QM_FQCTRL_<...> */
+ __be16 dest_wq; /* channel[3-15], wq[0-2] */
+ __be16 ics_cred; /* 15-bit */
+ /*
+ * For "Initialize Frame Queue" commands, the write-enable mask
+ * determines whether 'td' or 'oac_init' is observed. For query
+ * commands, this field is always 'td', and 'oac_query' (below) reflects
+ * the Overhead ACcounting values.
+ */
+ union {
+ __be16 td; /* "Taildrop": _res[13-15], mant[5-12], exp[0-4] */
+ struct qm_fqd_oac oac_init;
+ };
+ __be32 context_b;
+ union {
+ /* Treat it as 64-bit opaque */
+ __be64 opaque;
+ struct {
+ __be32 hi;
+ __be32 lo;
+ };
+ /* Treat it as s/w portal stashing config */
+ /* see "FQD Context_A field used for [...]" */
+ struct {
+ struct qm_fqd_stashing stashing;
+ /*
+ * 48-bit address of FQ context to
+ * stash, must be cacheline-aligned
+ */
+ __be16 context_hi;
+ __be32 context_lo;
+ } __packed;
+ } context_a;
+ struct qm_fqd_oac oac_query;
+} __packed;
+
+#define QM_FQD_CHAN_OFF 3
+#define QM_FQD_WQ_MASK GENMASK(2, 0)
+#define QM_FQD_TD_EXP_MASK GENMASK(4, 0)
+#define QM_FQD_TD_MANT_OFF 5
+#define QM_FQD_TD_MANT_MASK GENMASK(12, 5)
+#define QM_FQD_TD_MAX 0xe0000000
+#define QM_FQD_TD_MANT_MAX 0xff
+#define QM_FQD_OAC_OFF 6
+#define QM_FQD_AS_OFF 4
+#define QM_FQD_DS_OFF 2
+#define QM_FQD_XS_MASK 0x3
+
+/* 64-bit converters for context_hi/lo */
+static inline u64 qm_fqd_stashing_get64(const struct qm_fqd *fqd)
+{
+ return be64_to_cpu(fqd->context_a.opaque) & 0xffffffffffffULL;
+}
+
+static inline dma_addr_t qm_fqd_stashing_addr(const struct qm_fqd *fqd)
+{
+ return be64_to_cpu(fqd->context_a.opaque) & 0xffffffffffffULL;
+}
+
+static inline u64 qm_fqd_context_a_get64(const struct qm_fqd *fqd)
+{
+ return qm_fqd_stashing_get64(fqd);
+}
+
+static inline void qm_fqd_stashing_set64(struct qm_fqd *fqd, u64 addr)
+{
+ fqd->context_a.context_hi = upper_32_bits(addr);
+ fqd->context_a.context_lo = lower_32_bits(addr);
+}
+
+static inline void qm_fqd_context_a_set64(struct qm_fqd *fqd, u64 addr)
+{
+ fqd->context_a.hi = cpu_to_be16(upper_32_bits(addr));
+ fqd->context_a.lo = cpu_to_be32(lower_32_bits(addr));
+}
+
+/* convert a threshold value into mant+exp representation */
+static inline int qm_fqd_set_taildrop(struct qm_fqd *fqd, u32 val,
+ int roundup)
+{
+ u32 e = 0;
+ int td, oddbit = 0;
+
+ if (val > QM_FQD_TD_MAX)
+ return -ERANGE;
+
+ while (val > QM_FQD_TD_MANT_MAX) {
+ oddbit = val & 1;
+ val >>= 1;
+ e++;
+ if (roundup && oddbit)
+ val++;
+ }
+
+ td = (val << QM_FQD_TD_MANT_OFF) & QM_FQD_TD_MANT_MASK;
+ td |= (e & QM_FQD_TD_EXP_MASK);
+ fqd->td = cpu_to_be16(td);
+ return 0;
+}
+/* and the other direction */
+static inline int qm_fqd_get_taildrop(const struct qm_fqd *fqd)
+{
+ int td = be16_to_cpu(fqd->td);
+
+ return ((td & QM_FQD_TD_MANT_MASK) >> QM_FQD_TD_MANT_OFF)
+ << (td & QM_FQD_TD_EXP_MASK);
+}
+
+static inline void qm_fqd_set_stashing(struct qm_fqd *fqd, u8 as, u8 ds, u8 cs)
+{
+ struct qm_fqd_stashing *st = &fqd->context_a.stashing;
+
+ st->cl = ((as & QM_FQD_XS_MASK) << QM_FQD_AS_OFF) |
+ ((ds & QM_FQD_XS_MASK) << QM_FQD_DS_OFF) |
+ (cs & QM_FQD_XS_MASK);
+}
+
+static inline u8 qm_fqd_get_stashing(const struct qm_fqd *fqd)
+{
+ return fqd->context_a.stashing.cl;
+}
+
+static inline void qm_fqd_set_oac(struct qm_fqd *fqd, u8 val)
+{
+ fqd->oac_init.oac = val << QM_FQD_OAC_OFF;
+}
+
+static inline void qm_fqd_set_oal(struct qm_fqd *fqd, s8 val)
+{
+ fqd->oac_init.oal = val;
+}
+
+static inline void qm_fqd_set_destwq(struct qm_fqd *fqd, int ch, int wq)
+{
+ fqd->dest_wq = cpu_to_be16((ch << QM_FQD_CHAN_OFF) |
+ (wq & QM_FQD_WQ_MASK));
+}
+
+static inline int qm_fqd_get_chan(const struct qm_fqd *fqd)
+{
+ return be16_to_cpu(fqd->dest_wq) >> QM_FQD_CHAN_OFF;
+}
+
+static inline int qm_fqd_get_wq(const struct qm_fqd *fqd)
+{
+ return be16_to_cpu(fqd->dest_wq) & QM_FQD_WQ_MASK;
+}
+
+/* See "Frame Queue Descriptor (FQD)" */
+/* Frame Queue Descriptor (FQD) field 'fq_ctrl' uses these constants */
+#define QM_FQCTRL_MASK 0x07ff /* 'fq_ctrl' flags; */
+#define QM_FQCTRL_CGE 0x0400 /* Congestion Group Enable */
+#define QM_FQCTRL_TDE 0x0200 /* Tail-Drop Enable */
+#define QM_FQCTRL_CTXASTASHING 0x0080 /* Context-A stashing */
+#define QM_FQCTRL_CPCSTASH 0x0040 /* CPC Stash Enable */
+#define QM_FQCTRL_FORCESFDR 0x0008 /* High-priority SFDRs */
+#define QM_FQCTRL_AVOIDBLOCK 0x0004 /* Don't block active */
+#define QM_FQCTRL_HOLDACTIVE 0x0002 /* Hold active in portal */
+#define QM_FQCTRL_PREFERINCACHE 0x0001 /* Aggressively cache FQD */
+#define QM_FQCTRL_LOCKINCACHE QM_FQCTRL_PREFERINCACHE /* older naming */
+
+/* See "FQD Context_A field used for [...] */
+/* Frame Queue Descriptor (FQD) field 'CONTEXT_A' uses these constants */
+#define QM_STASHING_EXCL_ANNOTATION 0x04
+#define QM_STASHING_EXCL_DATA 0x02
+#define QM_STASHING_EXCL_CTX 0x01
+
+/* See "Intra Class Scheduling" */
+/* FQD field 'OAC' (Overhead ACcounting) uses these constants */
+#define QM_OAC_ICS 0x2 /* Accounting for Intra-Class Scheduling */
+#define QM_OAC_CG 0x1 /* Accounting for Congestion Groups */
+
+/*
+ * This struct represents the 32-bit "WR_PARM_[GYR]" parameters in CGR fields
+ * and associated commands/responses. The WRED parameters are calculated from
+ * these fields as follows;
+ * MaxTH = MA * (2 ^ Mn)
+ * Slope = SA / (2 ^ Sn)
+ * MaxP = 4 * (Pn + 1)
+ */
+struct qm_cgr_wr_parm {
+ /* MA[24-31], Mn[19-23], SA[12-18], Sn[6-11], Pn[0-5] */
+ u32 word;
+};
+/*
+ * This struct represents the 13-bit "CS_THRES" CGR field. In the corresponding
+ * management commands, this is padded to a 16-bit structure field, so that's
+ * how we represent it here. The congestion state threshold is calculated from
+ * these fields as follows;
+ * CS threshold = TA * (2 ^ Tn)
+ */
+struct qm_cgr_cs_thres {
+ /* _res[13-15], TA[5-12], Tn[0-4] */
+ u16 word;
+};
+/*
+ * This identical structure of CGR fields is present in the "Init/Modify CGR"
+ * commands and the "Query CGR" result. It's suctioned out here into its own
+ * struct.
+ */
+struct __qm_mc_cgr {
+ struct qm_cgr_wr_parm wr_parm_g;
+ struct qm_cgr_wr_parm wr_parm_y;
+ struct qm_cgr_wr_parm wr_parm_r;
+ u8 wr_en_g; /* boolean, use QM_CGR_EN */
+ u8 wr_en_y; /* boolean, use QM_CGR_EN */
+ u8 wr_en_r; /* boolean, use QM_CGR_EN */
+ u8 cscn_en; /* boolean, use QM_CGR_EN */
+ union {
+ struct {
+ u16 cscn_targ_upd_ctrl; /* use QM_CSCN_TARG_UDP_ */
+ u16 cscn_targ_dcp_low; /* CSCN_TARG_DCP low-16bits */
+ };
+ u32 cscn_targ; /* use QM_CGR_TARG_* */
+ };
+ u8 cstd_en; /* boolean, use QM_CGR_EN */
+ u8 cs; /* boolean, only used in query response */
+ struct qm_cgr_cs_thres cs_thres; /* use qm_cgr_cs_thres_set64() */
+ u8 mode; /* QMAN_CGR_MODE_FRAME not supported in rev1.0 */
+} __packed;
+#define QM_CGR_EN 0x01 /* For wr_en_*, cscn_en, cstd_en */
+#define QM_CGR_TARG_UDP_CTRL_WRITE_BIT 0x8000 /* value written to portal bit*/
+#define QM_CGR_TARG_UDP_CTRL_DCP 0x4000 /* 0: SWP, 1: DCP */
+#define QM_CGR_TARG_PORTAL(n) (0x80000000 >> (n)) /* s/w portal, 0-9 */
+#define QM_CGR_TARG_FMAN0 0x00200000 /* direct-connect portal: fman0 */
+#define QM_CGR_TARG_FMAN1 0x00100000 /* : fman1 */
+/* Convert CGR thresholds to/from "cs_thres" format */
+static inline u64 qm_cgr_cs_thres_get64(const struct qm_cgr_cs_thres *th)
+{
+ return ((th->word >> 5) & 0xff) << (th->word & 0x1f);
+}
+
+static inline int qm_cgr_cs_thres_set64(struct qm_cgr_cs_thres *th, u64 val,
+ int roundup)
+{
+ u32 e = 0;
+ int oddbit = 0;
+
+ while (val > 0xff) {
+ oddbit = val & 1;
+ val >>= 1;
+ e++;
+ if (roundup && oddbit)
+ val++;
+ }
+ th->word = ((val & 0xff) << 5) | (e & 0x1f);
+ return 0;
+}
+
+/* "Initialize FQ" */
+struct qm_mcc_initfq {
+ u8 __reserved1[2];
+ u16 we_mask; /* Write Enable Mask */
+ u32 fqid; /* 24-bit */
+ u16 count; /* Initialises 'count+1' FQDs */
+ struct qm_fqd fqd; /* the FQD fields go here */
+ u8 __reserved2[30];
+} __packed;
+/* "Initialize/Modify CGR" */
+struct qm_mcc_initcgr {
+ u8 __reserve1[2];
+ u16 we_mask; /* Write Enable Mask */
+ struct __qm_mc_cgr cgr; /* CGR fields */
+ u8 __reserved2[2];
+ u8 cgid;
+ u8 __reserved3[32];
+} __packed;
+
+/* INITFQ-specific flags */
+#define QM_INITFQ_WE_MASK 0x01ff /* 'Write Enable' flags; */
+#define QM_INITFQ_WE_OAC 0x0100
+#define QM_INITFQ_WE_ORPC 0x0080
+#define QM_INITFQ_WE_CGID 0x0040
+#define QM_INITFQ_WE_FQCTRL 0x0020
+#define QM_INITFQ_WE_DESTWQ 0x0010
+#define QM_INITFQ_WE_ICSCRED 0x0008
+#define QM_INITFQ_WE_TDTHRESH 0x0004
+#define QM_INITFQ_WE_CONTEXTB 0x0002
+#define QM_INITFQ_WE_CONTEXTA 0x0001
+/* INITCGR/MODIFYCGR-specific flags */
+#define QM_CGR_WE_MASK 0x07ff /* 'Write Enable Mask'; */
+#define QM_CGR_WE_WR_PARM_G 0x0400
+#define QM_CGR_WE_WR_PARM_Y 0x0200
+#define QM_CGR_WE_WR_PARM_R 0x0100
+#define QM_CGR_WE_WR_EN_G 0x0080
+#define QM_CGR_WE_WR_EN_Y 0x0040
+#define QM_CGR_WE_WR_EN_R 0x0020
+#define QM_CGR_WE_CSCN_EN 0x0010
+#define QM_CGR_WE_CSCN_TARG 0x0008
+#define QM_CGR_WE_CSTD_EN 0x0004
+#define QM_CGR_WE_CS_THRES 0x0002
+#define QM_CGR_WE_MODE 0x0001
+
+#define QMAN_CGR_FLAG_USE_INIT 0x00000001
+
+ /* Portal and Frame Queues */
+/* Represents a managed portal */
+struct qman_portal;
+
+/*
+ * This object type represents QMan frame queue descriptors (FQD), it is
+ * cacheline-aligned, and initialised by qman_create_fq(). The structure is
+ * defined further down.
+ */
+struct qman_fq;
+
+/*
+ * This object type represents a QMan congestion group, it is defined further
+ * down.
+ */
+struct qman_cgr;
+
+/*
+ * This enum, and the callback type that returns it, are used when handling
+ * dequeued frames via DQRR. Note that for "null" callbacks registered with the
+ * portal object (for handling dequeues that do not demux because contextB is
+ * NULL), the return value *MUST* be qman_cb_dqrr_consume.
+ */
+enum qman_cb_dqrr_result {
+ /* DQRR entry can be consumed */
+ qman_cb_dqrr_consume,
+ /* Like _consume, but requests parking - FQ must be held-active */
+ qman_cb_dqrr_park,
+ /* Does not consume, for DCA mode only. */
+ qman_cb_dqrr_defer,
+ /*
+ * Stop processing without consuming this ring entry. Exits the current
+ * qman_p_poll_dqrr() or interrupt-handling, as appropriate. If within
+ * an interrupt handler, the callback would typically call
+ * qman_irqsource_remove(QM_PIRQ_DQRI) before returning this value,
+ * otherwise the interrupt will reassert immediately.
+ */
+ qman_cb_dqrr_stop,
+ /* Like qman_cb_dqrr_stop, but consumes the current entry. */
+ qman_cb_dqrr_consume_stop
+};
+typedef enum qman_cb_dqrr_result (*qman_cb_dqrr)(struct qman_portal *qm,
+ struct qman_fq *fq,
+ const struct qm_dqrr_entry *dqrr);
+
+/*
+ * This callback type is used when handling ERNs, FQRNs and FQRLs via MR. They
+ * are always consumed after the callback returns.
+ */
+typedef void (*qman_cb_mr)(struct qman_portal *qm, struct qman_fq *fq,
+ const union qm_mr_entry *msg);
+
+/*
+ * s/w-visible states. Ie. tentatively scheduled + truly scheduled + active +
+ * held-active + held-suspended are just "sched". Things like "retired" will not
+ * be assumed until it is complete (ie. QMAN_FQ_STATE_CHANGING is set until
+ * then, to indicate it's completing and to gate attempts to retry the retire
+ * command). Note, park commands do not set QMAN_FQ_STATE_CHANGING because it's
+ * technically impossible in the case of enqueue DCAs (which refer to DQRR ring
+ * index rather than the FQ that ring entry corresponds to), so repeated park
+ * commands are allowed (if you're silly enough to try) but won't change FQ
+ * state, and the resulting park notifications move FQs from "sched" to
+ * "parked".
+ */
+enum qman_fq_state {
+ qman_fq_state_oos,
+ qman_fq_state_parked,
+ qman_fq_state_sched,
+ qman_fq_state_retired
+};
+
+#define QMAN_FQ_STATE_CHANGING 0x80000000 /* 'state' is changing */
+#define QMAN_FQ_STATE_NE 0x40000000 /* retired FQ isn't empty */
+#define QMAN_FQ_STATE_ORL 0x20000000 /* retired FQ has ORL */
+#define QMAN_FQ_STATE_BLOCKOOS 0xe0000000 /* if any are set, no OOS */
+#define QMAN_FQ_STATE_CGR_EN 0x10000000 /* CGR enabled */
+#define QMAN_FQ_STATE_VDQCR 0x08000000 /* being volatile dequeued */
+
+/*
+ * Frame queue objects (struct qman_fq) are stored within memory passed to
+ * qman_create_fq(), as this allows stashing of caller-provided demux callback
+ * pointers at no extra cost to stashing of (driver-internal) FQ state. If the
+ * caller wishes to add per-FQ state and have it benefit from dequeue-stashing,
+ * they should;
+ *
+ * (a) extend the qman_fq structure with their state; eg.
+ *
+ * // myfq is allocated and driver_fq callbacks filled in;
+ * struct my_fq {
+ * struct qman_fq base;
+ * int an_extra_field;
+ * [ ... add other fields to be associated with each FQ ...]
+ * } *myfq = some_my_fq_allocator();
+ * struct qman_fq *fq = qman_create_fq(fqid, flags, &myfq->base);
+ *
+ * // in a dequeue callback, access extra fields from 'fq' via a cast;
+ * struct my_fq *myfq = (struct my_fq *)fq;
+ * do_something_with(myfq->an_extra_field);
+ * [...]
+ *
+ * (b) when and if configuring the FQ for context stashing, specify how ever
+ * many cachelines are required to stash 'struct my_fq', to accelerate not
+ * only the QMan driver but the callback as well.
+ */
+
+struct qman_fq_cb {
+ qman_cb_dqrr dqrr; /* for dequeued frames */
+ qman_cb_mr ern; /* for s/w ERNs */
+ qman_cb_mr fqs; /* frame-queue state changes*/
+};
+
+struct qman_fq {
+ /* Caller of qman_create_fq() provides these demux callbacks */
+ struct qman_fq_cb cb;
+ /*
+ * These are internal to the driver, don't touch. In particular, they
+ * may change, be removed, or extended (so you shouldn't rely on
+ * sizeof(qman_fq) being a constant).
+ */
+ u32 fqid, idx;
+ unsigned long flags;
+ enum qman_fq_state state;
+ int cgr_groupid;
+};
+
+/*
+ * This callback type is used when handling congestion group entry/exit.
+ * 'congested' is non-zero on congestion-entry, and zero on congestion-exit.
+ */
+typedef void (*qman_cb_cgr)(struct qman_portal *qm,
+ struct qman_cgr *cgr, int congested);
+
+struct qman_cgr {
+ /* Set these prior to qman_create_cgr() */
+ u32 cgrid; /* 0..255, but u32 to allow specials like -1, 256, etc.*/
+ qman_cb_cgr cb;
+ /* These are private to the driver */
+ u16 chan; /* portal channel this object is created on */
+ struct list_head node;
+};
+
+/* Flags to qman_create_fq() */
+#define QMAN_FQ_FLAG_NO_ENQUEUE 0x00000001 /* can't enqueue */
+#define QMAN_FQ_FLAG_NO_MODIFY 0x00000002 /* can only enqueue */
+#define QMAN_FQ_FLAG_TO_DCPORTAL 0x00000004 /* consumed by CAAM/PME/Fman */
+#define QMAN_FQ_FLAG_DYNAMIC_FQID 0x00000020 /* (de)allocate fqid */
+
+/* Flags to qman_init_fq() */
+#define QMAN_INITFQ_FLAG_SCHED 0x00000001 /* schedule rather than park */
+#define QMAN_INITFQ_FLAG_LOCAL 0x00000004 /* set dest portal */
+
+ /* Portal Management */
+/**
+ * qman_p_irqsource_add - add processing sources to be interrupt-driven
+ * @bits: bitmask of QM_PIRQ_**I processing sources
+ *
+ * Adds processing sources that should be interrupt-driven (rather than
+ * processed via qman_poll_***() functions).
+ */
+void qman_p_irqsource_add(struct qman_portal *p, u32 bits);
+
+/**
+ * qman_p_irqsource_remove - remove processing sources from being int-driven
+ * @bits: bitmask of QM_PIRQ_**I processing sources
+ *
+ * Removes processing sources from being interrupt-driven, so that they will
+ * instead be processed via qman_poll_***() functions.
+ */
+void qman_p_irqsource_remove(struct qman_portal *p, u32 bits);
+
+/**
+ * qman_affine_cpus - return a mask of cpus that have affine portals
+ */
+const cpumask_t *qman_affine_cpus(void);
+
+/**
+ * qman_affine_channel - return the channel ID of an portal
+ * @cpu: the cpu whose affine portal is the subject of the query
+ *
+ * If @cpu is -1, the affine portal for the current CPU will be used. It is a
+ * bug to call this function for any value of @cpu (other than -1) that is not a
+ * member of the mask returned from qman_affine_cpus().
+ */
+u16 qman_affine_channel(int cpu);
+
+/**
+ * qman_get_affine_portal - return the portal pointer affine to cpu
+ * @cpu: the cpu whose affine portal is the subject of the query
+ */
+struct qman_portal *qman_get_affine_portal(int cpu);
+
+/**
+ * qman_p_poll_dqrr - process DQRR (fast-path) entries
+ * @limit: the maximum number of DQRR entries to process
+ *
+ * Use of this function requires that DQRR processing not be interrupt-driven.
+ * The return value represents the number of DQRR entries processed.
+ */
+int qman_p_poll_dqrr(struct qman_portal *p, unsigned int limit);
+
+/**
+ * qman_p_static_dequeue_add - Add pool channels to the portal SDQCR
+ * @pools: bit-mask of pool channels, using QM_SDQCR_CHANNELS_POOL(n)
+ *
+ * Adds a set of pool channels to the portal's static dequeue command register
+ * (SDQCR). The requested pools are limited to those the portal has dequeue
+ * access to.
+ */
+void qman_p_static_dequeue_add(struct qman_portal *p, u32 pools);
+
+ /* FQ management */
+/**
+ * qman_create_fq - Allocates a FQ
+ * @fqid: the index of the FQD to encapsulate, must be "Out of Service"
+ * @flags: bit-mask of QMAN_FQ_FLAG_*** options
+ * @fq: memory for storing the 'fq', with callbacks filled in
+ *
+ * Creates a frame queue object for the given @fqid, unless the
+ * QMAN_FQ_FLAG_DYNAMIC_FQID flag is set in @flags, in which case a FQID is
+ * dynamically allocated (or the function fails if none are available). Once
+ * created, the caller should not touch the memory at 'fq' except as extended to
+ * adjacent memory for user-defined fields (see the definition of "struct
+ * qman_fq" for more info). NO_MODIFY is only intended for enqueuing to
+ * pre-existing frame-queues that aren't to be otherwise interfered with, it
+ * prevents all other modifications to the frame queue. The TO_DCPORTAL flag
+ * causes the driver to honour any contextB modifications requested in the
+ * qm_init_fq() API, as this indicates the frame queue will be consumed by a
+ * direct-connect portal (PME, CAAM, or Fman). When frame queues are consumed by
+ * software portals, the contextB field is controlled by the driver and can't be
+ * modified by the caller.
+ */
+int qman_create_fq(u32 fqid, u32 flags, struct qman_fq *fq);
+
+/**
+ * qman_destroy_fq - Deallocates a FQ
+ * @fq: the frame queue object to release
+ *
+ * The memory for this frame queue object ('fq' provided in qman_create_fq()) is
+ * not deallocated but the caller regains ownership, to do with as desired. The
+ * FQ must be in the 'out-of-service' or in the 'parked' state.
+ */
+void qman_destroy_fq(struct qman_fq *fq);
+
+/**
+ * qman_fq_fqid - Queries the frame queue ID of a FQ object
+ * @fq: the frame queue object to query
+ */
+u32 qman_fq_fqid(struct qman_fq *fq);
+
+/**
+ * qman_init_fq - Initialises FQ fields, leaves the FQ "parked" or "scheduled"
+ * @fq: the frame queue object to modify, must be 'parked' or new.
+ * @flags: bit-mask of QMAN_INITFQ_FLAG_*** options
+ * @opts: the FQ-modification settings, as defined in the low-level API
+ *
+ * The @opts parameter comes from the low-level portal API. Select
+ * QMAN_INITFQ_FLAG_SCHED in @flags to cause the frame queue to be scheduled
+ * rather than parked. NB, @opts can be NULL.
+ *
+ * Note that some fields and options within @opts may be ignored or overwritten
+ * by the driver;
+ * 1. the 'count' and 'fqid' fields are always ignored (this operation only
+ * affects one frame queue: @fq).
+ * 2. the QM_INITFQ_WE_CONTEXTB option of the 'we_mask' field and the associated
+ * 'fqd' structure's 'context_b' field are sometimes overwritten;
+ * - if @fq was not created with QMAN_FQ_FLAG_TO_DCPORTAL, then context_b is
+ * initialised to a value used by the driver for demux.
+ * - if context_b is initialised for demux, so is context_a in case stashing
+ * is requested (see item 4).
+ * (So caller control of context_b is only possible for TO_DCPORTAL frame queue
+ * objects.)
+ * 3. if @flags contains QMAN_INITFQ_FLAG_LOCAL, the 'fqd' structure's
+ * 'dest::channel' field will be overwritten to match the portal used to issue
+ * the command. If the WE_DESTWQ write-enable bit had already been set by the
+ * caller, the channel workqueue will be left as-is, otherwise the write-enable
+ * bit is set and the workqueue is set to a default of 4. If the "LOCAL" flag
+ * isn't set, the destination channel/workqueue fields and the write-enable bit
+ * are left as-is.
+ * 4. if the driver overwrites context_a/b for demux, then if
+ * QM_INITFQ_WE_CONTEXTA is set, the driver will only overwrite
+ * context_a.address fields and will leave the stashing fields provided by the
+ * user alone, otherwise it will zero out the context_a.stashing fields.
+ */
+int qman_init_fq(struct qman_fq *fq, u32 flags, struct qm_mcc_initfq *opts);
+
+/**
+ * qman_schedule_fq - Schedules a FQ
+ * @fq: the frame queue object to schedule, must be 'parked'
+ *
+ * Schedules the frame queue, which must be Parked, which takes it to
+ * Tentatively-Scheduled or Truly-Scheduled depending on its fill-level.
+ */
+int qman_schedule_fq(struct qman_fq *fq);
+
+/**
+ * qman_retire_fq - Retires a FQ
+ * @fq: the frame queue object to retire
+ * @flags: FQ flags (QMAN_FQ_STATE*) if retirement completes immediately
+ *
+ * Retires the frame queue. This returns zero if it succeeds immediately, +1 if
+ * the retirement was started asynchronously, otherwise it returns negative for
+ * failure. When this function returns zero, @flags is set to indicate whether
+ * the retired FQ is empty and/or whether it has any ORL fragments (to show up
+ * as ERNs). Otherwise the corresponding flags will be known when a subsequent
+ * FQRN message shows up on the portal's message ring.
+ *
+ * NB, if the retirement is asynchronous (the FQ was in the Truly Scheduled or
+ * Active state), the completion will be via the message ring as a FQRN - but
+ * the corresponding callback may occur before this function returns!! Ie. the
+ * caller should be prepared to accept the callback as the function is called,
+ * not only once it has returned.
+ */
+int qman_retire_fq(struct qman_fq *fq, u32 *flags);
+
+/**
+ * qman_oos_fq - Puts a FQ "out of service"
+ * @fq: the frame queue object to be put out-of-service, must be 'retired'
+ *
+ * The frame queue must be retired and empty, and if any order restoration list
+ * was released as ERNs at the time of retirement, they must all be consumed.
+ */
+int qman_oos_fq(struct qman_fq *fq);
+
+/**
+ * qman_enqueue - Enqueue a frame to a frame queue
+ * @fq: the frame queue object to enqueue to
+ * @fd: a descriptor of the frame to be enqueued
+ *
+ * Fills an entry in the EQCR of portal @qm to enqueue the frame described by
+ * @fd. The descriptor details are copied from @fd to the EQCR entry, the 'pid'
+ * field is ignored. The return value is non-zero on error, such as ring full.
+ */
+int qman_enqueue(struct qman_fq *fq, const struct qm_fd *fd);
+
+/**
+ * qman_alloc_fqid_range - Allocate a contiguous range of FQIDs
+ * @result: is set by the API to the base FQID of the allocated range
+ * @count: the number of FQIDs required
+ *
+ * Returns 0 on success, or a negative error code.
+ */
+int qman_alloc_fqid_range(u32 *result, u32 count);
+#define qman_alloc_fqid(result) qman_alloc_fqid_range(result, 1)
+
+/**
+ * qman_release_fqid - Release the specified frame queue ID
+ * @fqid: the FQID to be released back to the resource pool
+ *
+ * This function can also be used to seed the allocator with
+ * FQID ranges that it can subsequently allocate from.
+ * Returns 0 on success, or a negative error code.
+ */
+int qman_release_fqid(u32 fqid);
+
+ /* Pool-channel management */
+/**
+ * qman_alloc_pool_range - Allocate a contiguous range of pool-channel IDs
+ * @result: is set by the API to the base pool-channel ID of the allocated range
+ * @count: the number of pool-channel IDs required
+ *
+ * Returns 0 on success, or a negative error code.
+ */
+int qman_alloc_pool_range(u32 *result, u32 count);
+#define qman_alloc_pool(result) qman_alloc_pool_range(result, 1)
+
+/**
+ * qman_release_pool - Release the specified pool-channel ID
+ * @id: the pool-chan ID to be released back to the resource pool
+ *
+ * This function can also be used to seed the allocator with
+ * pool-channel ID ranges that it can subsequently allocate from.
+ * Returns 0 on success, or a negative error code.
+ */
+int qman_release_pool(u32 id);
+
+ /* CGR management */
+/**
+ * qman_create_cgr - Register a congestion group object
+ * @cgr: the 'cgr' object, with fields filled in
+ * @flags: QMAN_CGR_FLAG_* values
+ * @opts: optional state of CGR settings
+ *
+ * Registers this object to receiving congestion entry/exit callbacks on the
+ * portal affine to the cpu portal on which this API is executed. If opts is
+ * NULL then only the callback (cgr->cb) function is registered. If @flags
+ * contains QMAN_CGR_FLAG_USE_INIT, then an init hw command (which will reset
+ * any unspecified parameters) will be used rather than a modify hw hardware
+ * (which only modifies the specified parameters).
+ */
+int qman_create_cgr(struct qman_cgr *cgr, u32 flags,
+ struct qm_mcc_initcgr *opts);
+
+/**
+ * qman_delete_cgr - Deregisters a congestion group object
+ * @cgr: the 'cgr' object to deregister
+ *
+ * "Unplugs" this CGR object from the portal affine to the cpu on which this API
+ * is executed. This must be excuted on the same affine portal on which it was
+ * created.
+ */
+int qman_delete_cgr(struct qman_cgr *cgr);
+
+/**
+ * qman_delete_cgr_safe - Deregisters a congestion group object from any CPU
+ * @cgr: the 'cgr' object to deregister
+ *
+ * This will select the proper CPU and run there qman_delete_cgr().
+ */
+void qman_delete_cgr_safe(struct qman_cgr *cgr);
+
+/**
+ * qman_query_cgr_congested - Queries CGR's congestion status
+ * @cgr: the 'cgr' object to query
+ * @result: returns 'cgr's congestion status, 1 (true) if congested
+ */
+int qman_query_cgr_congested(struct qman_cgr *cgr, bool *result);
+
+/**
+ * qman_alloc_cgrid_range - Allocate a contiguous range of CGR IDs
+ * @result: is set by the API to the base CGR ID of the allocated range
+ * @count: the number of CGR IDs required
+ *
+ * Returns 0 on success, or a negative error code.
+ */
+int qman_alloc_cgrid_range(u32 *result, u32 count);
+#define qman_alloc_cgrid(result) qman_alloc_cgrid_range(result, 1)
+
+/**
+ * qman_release_cgrid - Release the specified CGR ID
+ * @id: the CGR ID to be released back to the resource pool
+ *
+ * This function can also be used to seed the allocator with
+ * CGR ID ranges that it can subsequently allocate from.
+ * Returns 0 on success, or a negative error code.
+ */
+int qman_release_cgrid(u32 id);
+
+#endif /* __FSL_QMAN_H */
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index fb8e3b6..c211900 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -177,6 +177,7 @@ enum tcm_sense_reason_table {
TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED = R(0x15),
TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED = R(0x16),
TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED = R(0x17),
+ TCM_COPY_TARGET_DEVICE_NOT_REACHABLE = R(0x18),
#undef R
};
diff --git a/include/trace/events/cgroup.h b/include/trace/events/cgroup.h
new file mode 100644
index 0000000..ab68640
--- /dev/null
+++ b/include/trace/events/cgroup.h
@@ -0,0 +1,163 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM cgroup
+
+#if !defined(_TRACE_CGROUP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_CGROUP_H
+
+#include <linux/cgroup.h>
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(cgroup_root,
+
+ TP_PROTO(struct cgroup_root *root),
+
+ TP_ARGS(root),
+
+ TP_STRUCT__entry(
+ __field( int, root )
+ __field( u16, ss_mask )
+ __string( name, root->name )
+ ),
+
+ TP_fast_assign(
+ __entry->root = root->hierarchy_id;
+ __entry->ss_mask = root->subsys_mask;
+ __assign_str(name, root->name);
+ ),
+
+ TP_printk("root=%d ss_mask=%#x name=%s",
+ __entry->root, __entry->ss_mask, __get_str(name))
+);
+
+DEFINE_EVENT(cgroup_root, cgroup_setup_root,
+
+ TP_PROTO(struct cgroup_root *root),
+
+ TP_ARGS(root)
+);
+
+DEFINE_EVENT(cgroup_root, cgroup_destroy_root,
+
+ TP_PROTO(struct cgroup_root *root),
+
+ TP_ARGS(root)
+);
+
+DEFINE_EVENT(cgroup_root, cgroup_remount,
+
+ TP_PROTO(struct cgroup_root *root),
+
+ TP_ARGS(root)
+);
+
+DECLARE_EVENT_CLASS(cgroup,
+
+ TP_PROTO(struct cgroup *cgrp),
+
+ TP_ARGS(cgrp),
+
+ TP_STRUCT__entry(
+ __field( int, root )
+ __field( int, id )
+ __field( int, level )
+ __dynamic_array(char, path,
+ cgrp->kn ? cgroup_path(cgrp, NULL, 0) + 1
+ : strlen("(null)"))
+ ),
+
+ TP_fast_assign(
+ __entry->root = cgrp->root->hierarchy_id;
+ __entry->id = cgrp->id;
+ __entry->level = cgrp->level;
+ if (cgrp->kn)
+ cgroup_path(cgrp, __get_dynamic_array(path),
+ __get_dynamic_array_len(path));
+ else
+ __assign_str(path, "(null)");
+ ),
+
+ TP_printk("root=%d id=%d level=%d path=%s",
+ __entry->root, __entry->id, __entry->level, __get_str(path))
+);
+
+DEFINE_EVENT(cgroup, cgroup_mkdir,
+
+ TP_PROTO(struct cgroup *cgroup),
+
+ TP_ARGS(cgroup)
+);
+
+DEFINE_EVENT(cgroup, cgroup_rmdir,
+
+ TP_PROTO(struct cgroup *cgroup),
+
+ TP_ARGS(cgroup)
+);
+
+DEFINE_EVENT(cgroup, cgroup_release,
+
+ TP_PROTO(struct cgroup *cgroup),
+
+ TP_ARGS(cgroup)
+);
+
+DEFINE_EVENT(cgroup, cgroup_rename,
+
+ TP_PROTO(struct cgroup *cgroup),
+
+ TP_ARGS(cgroup)
+);
+
+DECLARE_EVENT_CLASS(cgroup_migrate,
+
+ TP_PROTO(struct cgroup *dst_cgrp, struct task_struct *task, bool threadgroup),
+
+ TP_ARGS(dst_cgrp, task, threadgroup),
+
+ TP_STRUCT__entry(
+ __field( int, dst_root )
+ __field( int, dst_id )
+ __field( int, dst_level )
+ __dynamic_array(char, dst_path,
+ dst_cgrp->kn ? cgroup_path(dst_cgrp, NULL, 0) + 1
+ : strlen("(null)"))
+ __field( int, pid )
+ __string( comm, task->comm )
+ ),
+
+ TP_fast_assign(
+ __entry->dst_root = dst_cgrp->root->hierarchy_id;
+ __entry->dst_id = dst_cgrp->id;
+ __entry->dst_level = dst_cgrp->level;
+ if (dst_cgrp->kn)
+ cgroup_path(dst_cgrp, __get_dynamic_array(dst_path),
+ __get_dynamic_array_len(dst_path));
+ else
+ __assign_str(dst_path, "(null)");
+ __entry->pid = task->pid;
+ __assign_str(comm, task->comm);
+ ),
+
+ TP_printk("dst_root=%d dst_id=%d dst_level=%d dst_path=%s pid=%d comm=%s",
+ __entry->dst_root, __entry->dst_id, __entry->dst_level,
+ __get_str(dst_path), __entry->pid, __get_str(comm))
+);
+
+DEFINE_EVENT(cgroup_migrate, cgroup_attach_task,
+
+ TP_PROTO(struct cgroup *dst_cgrp, struct task_struct *task, bool threadgroup),
+
+ TP_ARGS(dst_cgrp, task, threadgroup)
+);
+
+DEFINE_EVENT(cgroup_migrate, cgroup_transfer_tasks,
+
+ TP_PROTO(struct cgroup *dst_cgrp, struct task_struct *task, bool threadgroup),
+
+ TP_ARGS(dst_cgrp, task, threadgroup)
+);
+
+#endif /* _TRACE_CGROUP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index dbfee7e..9b1462e 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -730,10 +730,6 @@ __SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
__SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
#define __NR_pkey_free 290
__SYSCALL(__NR_pkey_free, sys_pkey_free)
-#define __NR_pkey_get 291
-//__SYSCALL(__NR_pkey_get, sys_pkey_get)
-#define __NR_pkey_set 292
-//__SYSCALL(__NR_pkey_set, sys_pkey_set)
#undef __NR_syscalls
#define __NR_syscalls 291
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 6965d09..cd2be1c 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -75,6 +75,7 @@
header-y += bpf.h
header-y += bpqether.h
header-y += bsg.h
+header-y += bt-bmc.h
header-y += btrfs.h
header-y += can.h
header-y += capability.h
diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h
index 5cd4d4d..9c9c6ad 100644
--- a/include/uapi/linux/atm_zatm.h
+++ b/include/uapi/linux/atm_zatm.h
@@ -14,7 +14,6 @@
#include <linux/atmapi.h>
#include <linux/atmioc.h>
-#include <linux/time.h>
#define ZATM_GETPOOL _IOW('a',ATMIOC_SARPRV+1,struct atmif_sioc)
/* get pool statistics */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e2f38e0..7d9b283 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -85,6 +85,8 @@ enum bpf_map_type {
BPF_MAP_TYPE_PERCPU_ARRAY,
BPF_MAP_TYPE_STACK_TRACE,
BPF_MAP_TYPE_CGROUP_ARRAY,
+ BPF_MAP_TYPE_LRU_HASH,
+ BPF_MAP_TYPE_LRU_PERCPU_HASH,
};
enum bpf_prog_type {
@@ -106,6 +108,13 @@ enum bpf_prog_type {
#define BPF_EXIST 2 /* update existing element */
#define BPF_F_NO_PREALLOC (1U << 0)
+/* Instead of having one common LRU list in the
+ * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list
+ * which can scale and perform better.
+ * Note, the LRU nodes (including free nodes) cannot be moved
+ * across different LRU lists.
+ */
+#define BPF_F_NO_COMMON_LRU (1U << 1)
union bpf_attr {
struct { /* anonymous struct used by BPF_MAP_CREATE command */
diff --git a/include/uapi/linux/bpqether.h b/include/uapi/linux/bpqether.h
index a6c35e1..05865ed 100644
--- a/include/uapi/linux/bpqether.h
+++ b/include/uapi/linux/bpqether.h
@@ -5,9 +5,7 @@
* Defines for the BPQETHER pseudo device driver
*/
-#ifndef __LINUX_IF_ETHER_H
#include <linux/if_ether.h>
-#endif
#define SIOCSBPQETHOPT (SIOCDEVPRIVATE+0) /* reserved */
#define SIOCSBPQETHADDR (SIOCDEVPRIVATE+1)
diff --git a/include/uapi/linux/bt-bmc.h b/include/uapi/linux/bt-bmc.h
new file mode 100644
index 0000000..d9ec766
--- /dev/null
+++ b/include/uapi/linux/bt-bmc.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (c) 2015-2016, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _UAPI_LINUX_BT_BMC_H
+#define _UAPI_LINUX_BT_BMC_H
+
+#include <linux/ioctl.h>
+
+#define __BT_BMC_IOCTL_MAGIC 0xb1
+#define BT_BMC_IOCTL_SMS_ATN _IO(__BT_BMC_IOCTL_MAGIC, 0x00)
+
+#endif /* _UAPI_LINUX_BT_BMC_H */
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index ac5eacd..db4c253 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -239,7 +239,17 @@ struct btrfs_ioctl_fs_info_args {
* Used by:
* struct btrfs_ioctl_feature_flags
*/
-#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE (1ULL << 0)
+#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE (1ULL << 0)
+/*
+ * Older kernels (< 4.9) on big-endian systems produced broken free space tree
+ * bitmaps, and btrfs-progs also used to corrupt the free space tree (versions
+ * < 4.7.3). If this bit is clear, then the free space tree cannot be trusted.
+ * btrfs-progs can also intentionally clear this bit to ask the kernel to
+ * rebuild the free space tree, however this might not work on older kernels
+ * that do not know about this bit. If not sure, clear the cache manually on
+ * first mount when booting older kernel versions.
+ */
+#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID (1ULL << 1)
#define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF (1ULL << 0)
#define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL (1ULL << 1)
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 099a420..f0db778 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -119,8 +119,7 @@ struct ethtool_cmd {
static inline void ethtool_cmd_speed_set(struct ethtool_cmd *ep,
__u32 speed)
{
-
- ep->speed = (__u16)speed;
+ ep->speed = (__u16)(speed & 0xFFFF);
ep->speed_hi = (__u16)(speed >> 16);
}
@@ -249,6 +248,19 @@ struct ethtool_tunable {
void *data[0];
};
+#define DOWNSHIFT_DEV_DEFAULT_COUNT 0xff
+#define DOWNSHIFT_DEV_DISABLE 0
+
+enum phy_tunable_id {
+ ETHTOOL_PHY_ID_UNSPEC,
+ ETHTOOL_PHY_DOWNSHIFT,
+ /*
+ * Add your fresh new phy tunable attribute above and remember to update
+ * phy_tunable_strings[] in net/core/ethtool.c
+ */
+ __ETHTOOL_PHY_TUNABLE_COUNT,
+};
+
/**
* struct ethtool_regs - hardware register dump
* @cmd: Command number = %ETHTOOL_GREGS
@@ -549,6 +561,7 @@ struct ethtool_pauseparam {
* @ETH_SS_FEATURES: Device feature names
* @ETH_SS_RSS_HASH_FUNCS: RSS hush function names
* @ETH_SS_PHY_STATS: Statistic names, for use with %ETHTOOL_GPHYSTATS
+ * @ETH_SS_PHY_TUNABLES: PHY tunable names
*/
enum ethtool_stringset {
ETH_SS_TEST = 0,
@@ -559,6 +572,7 @@ enum ethtool_stringset {
ETH_SS_RSS_HASH_FUNCS,
ETH_SS_TUNABLES,
ETH_SS_PHY_STATS,
+ ETH_SS_PHY_TUNABLES,
};
/**
@@ -1314,7 +1328,8 @@ struct ethtool_per_queue_op {
#define ETHTOOL_GLINKSETTINGS 0x0000004c /* Get ethtool_link_settings */
#define ETHTOOL_SLINKSETTINGS 0x0000004d /* Set ethtool_link_settings */
-
+#define ETHTOOL_PHY_GTUNABLE 0x0000004e /* Get PHY tunable configuration */
+#define ETHTOOL_PHY_STUNABLE 0x0000004f /* Set PHY tunable configuration */
/* compatibility with older code */
#define SPARC_ETH_GSET ETHTOOL_GSET
diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 14404b3..bbf02a6 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -29,6 +29,11 @@ struct fib_rule_hdr {
__u32 flags;
};
+struct fib_rule_uid_range {
+ __u32 start;
+ __u32 end;
+};
+
enum {
FRA_UNSPEC,
FRA_DST, /* destination address */
@@ -51,6 +56,7 @@ enum {
FRA_OIFNAME,
FRA_PAD,
FRA_L3MDEV, /* iif or oif is l3mdev goto its table */
+ FRA_UID_RANGE, /* UID range */
__FRA_MAX
};
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index eaf9491..4e557f4 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -117,6 +117,7 @@ struct in_addr {
#define IP_NODEFRAG 22
#define IP_CHECKSUM 23
#define IP_BIND_ADDRESS_NO_PORT 24
+#define IP_RECVFRAGSIZE 25
/* IP_MTU_DISCOVER values */
#define IP_PMTUDISC_DONT 0 /* Never send DF frames */
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index b39ea4f..46444f8 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -283,6 +283,7 @@ struct in6_flowlabel_req {
#define IPV6_RECVORIGDSTADDR IPV6_ORIGDSTADDR
#define IPV6_TRANSPARENT 75
#define IPV6_UNICAST_IF 76
+#define IPV6_RECVFRAGSIZE 77
/*
* Multicast Routing:
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 8c27723..53561be 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -39,6 +39,7 @@ struct in6_ifreq {
#define IPV6_SRCRT_STRICT 0x01 /* Deprecated; will be removed */
#define IPV6_SRCRT_TYPE_0 0 /* Deprecated; will be removed */
#define IPV6_SRCRT_TYPE_2 2 /* IPv6 type 2 Routing Header */
+#define IPV6_SRCRT_TYPE_4 4 /* Segment Routing with IPv6 */
/*
* routing header
@@ -178,6 +179,8 @@ enum {
DEVCONF_DROP_UNSOLICITED_NA,
DEVCONF_KEEP_ADDR_ON_DOWN,
DEVCONF_RTR_SOLICIT_MAX_INTERVAL,
+ DEVCONF_SEG6_ENABLED,
+ DEVCONF_SEG6_REQUIRE_HMAC,
DEVCONF_MAX
};
diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 4bd27d0..5daa48e 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -124,8 +124,8 @@ enum {
L2TP_ATTR_STATS, /* nested */
L2TP_ATTR_IP6_SADDR, /* struct in6_addr */
L2TP_ATTR_IP6_DADDR, /* struct in6_addr */
- L2TP_ATTR_UDP_ZERO_CSUM6_TX, /* u8 */
- L2TP_ATTR_UDP_ZERO_CSUM6_RX, /* u8 */
+ L2TP_ATTR_UDP_ZERO_CSUM6_TX, /* flag */
+ L2TP_ATTR_UDP_ZERO_CSUM6_RX, /* flag */
L2TP_ATTR_PAD,
__L2TP_ATTR_MAX,
};
diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h
index a478fe8..453cc62 100644
--- a/include/uapi/linux/lwtunnel.h
+++ b/include/uapi/linux/lwtunnel.h
@@ -9,6 +9,7 @@ enum lwtunnel_encap_types {
LWTUNNEL_ENCAP_IP,
LWTUNNEL_ENCAP_ILA,
LWTUNNEL_ENCAP_IP6,
+ LWTUNNEL_ENCAP_SEG6,
__LWTUNNEL_ENCAP_MAX,
};
diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h
index d93f949..7550e91 100644
--- a/include/uapi/linux/netfilter.h
+++ b/include/uapi/linux/netfilter.h
@@ -13,7 +13,7 @@
#define NF_STOLEN 2
#define NF_QUEUE 3
#define NF_REPEAT 4
-#define NF_STOP 5
+#define NF_STOP 5 /* Deprecated, for userspace nf_queue compatibility. */
#define NF_MAX_VERDICT NF_STOP
/* we overload the higher bits for encoding auxiliary data such as the queue
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index c6c4477..14e5f61 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -759,6 +759,19 @@ enum nft_meta_keys {
};
/**
+ * enum nft_rt_keys - nf_tables routing expression keys
+ *
+ * @NFT_RT_CLASSID: realm value of packet's route (skb->dst->tclassid)
+ * @NFT_RT_NEXTHOP4: routing nexthop for IPv4
+ * @NFT_RT_NEXTHOP6: routing nexthop for IPv6
+ */
+enum nft_rt_keys {
+ NFT_RT_CLASSID,
+ NFT_RT_NEXTHOP4,
+ NFT_RT_NEXTHOP6,
+};
+
+/**
* enum nft_hash_attributes - nf_tables hash expression netlink attributes
*
* @NFTA_HASH_SREG: source register (NLA_U32)
@@ -797,6 +810,20 @@ enum nft_meta_attributes {
#define NFTA_META_MAX (__NFTA_META_MAX - 1)
/**
+ * enum nft_rt_attributes - nf_tables routing expression netlink attributes
+ *
+ * @NFTA_RT_DREG: destination register (NLA_U32)
+ * @NFTA_RT_KEY: routing data item to load (NLA_U32: nft_rt_keys)
+ */
+enum nft_rt_attributes {
+ NFTA_RT_UNSPEC,
+ NFTA_RT_DREG,
+ NFTA_RT_KEY,
+ __NFTA_RT_MAX
+};
+#define NFTA_RT_MAX (__NFTA_RT_MAX - 1)
+
+/**
* enum nft_ct_keys - nf_tables ct expression keys
*
* @NFT_CT_STATE: conntrack state (bitmask of enum ip_conntrack_info)
@@ -1109,6 +1136,42 @@ enum nft_gen_attributes {
};
#define NFTA_GEN_MAX (__NFTA_GEN_MAX - 1)
+/*
+ * enum nft_fib_attributes - nf_tables fib expression netlink attributes
+ *
+ * @NFTA_FIB_DREG: destination register (NLA_U32)
+ * @NFTA_FIB_RESULT: desired result (NLA_U32)
+ * @NFTA_FIB_FLAGS: flowi fields to initialize when querying the FIB (NLA_U32)
+ *
+ * The FIB expression performs a route lookup according
+ * to the packet data.
+ */
+enum nft_fib_attributes {
+ NFTA_FIB_UNSPEC,
+ NFTA_FIB_DREG,
+ NFTA_FIB_RESULT,
+ NFTA_FIB_FLAGS,
+ __NFTA_FIB_MAX
+};
+#define NFTA_FIB_MAX (__NFTA_FIB_MAX - 1)
+
+enum nft_fib_result {
+ NFT_FIB_RESULT_UNSPEC,
+ NFT_FIB_RESULT_OIF,
+ NFT_FIB_RESULT_OIFNAME,
+ NFT_FIB_RESULT_ADDRTYPE,
+ __NFT_FIB_RESULT_MAX
+};
+#define NFT_FIB_RESULT_MAX (__NFT_FIB_RESULT_MAX - 1)
+
+enum nft_fib_flags {
+ NFTA_FIB_F_SADDR = 1 << 0, /* look up src */
+ NFTA_FIB_F_DADDR = 1 << 1, /* look up dst */
+ NFTA_FIB_F_MARK = 1 << 2, /* use skb->mark */
+ NFTA_FIB_F_IIF = 1 << 3, /* restrict to iif */
+ NFTA_FIB_F_OIF = 1 << 4, /* restrict to oif */
+};
+
/**
* enum nft_trace_attributes - nf_tables trace netlink attributes
*
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 56368e9..259c9c7 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -600,6 +600,20 @@
*
* @NL80211_CMD_SET_WDS_PEER: Set the MAC address of the peer on a WDS interface.
*
+ * @NL80211_CMD_SET_MULTICAST_TO_UNICAST: Configure if this AP should perform
+ * multicast to unicast conversion. When enabled, all multicast packets
+ * with ethertype ARP, IPv4 or IPv6 (possibly within an 802.1Q header)
+ * will be sent out to each station once with the destination (multicast)
+ * MAC address replaced by the station's MAC address. Note that this may
+ * break certain expectations of the receiver, e.g. the ability to drop
+ * unicast IP packets encapsulated in multicast L2 frames, or the ability
+ * to not send destination unreachable messages in such cases.
+ * This can only be toggled per BSS. Configure this on an interface of
+ * type %NL80211_IFTYPE_AP. It applies to all its VLAN interfaces
+ * (%NL80211_IFTYPE_AP_VLAN), except for those in 4addr (WDS) mode.
+ * If %NL80211_ATTR_MULTICAST_TO_UNICAST_ENABLED is not present with this
+ * command, the feature is disabled.
+ *
* @NL80211_CMD_JOIN_MESH: Join a mesh. The mesh ID must be given, and initial
* mesh config parameters may be given.
* @NL80211_CMD_LEAVE_MESH: Leave the mesh network -- no special arguments, the
@@ -874,6 +888,12 @@
* This will contain a %NL80211_ATTR_NAN_MATCH nested attribute and
* %NL80211_ATTR_COOKIE.
*
+ * @NL80211_CMD_UPDATE_CONNECT_PARAMS: Update one or more connect parameters
+ * for subsequent roaming cases if the driver or firmware uses internal
+ * BSS selection. This command can be issued only while connected and it
+ * does not result in a change for the current association. Currently,
+ * only the %NL80211_ATTR_IE data is used and updated with this command.
+ *
* @NL80211_CMD_MAX: highest used command number
* @__NL80211_CMD_AFTER_LAST: internal use
*/
@@ -1069,6 +1089,10 @@ enum nl80211_commands {
NL80211_CMD_CHANGE_NAN_CONFIG,
NL80211_CMD_NAN_MATCH,
+ NL80211_CMD_SET_MULTICAST_TO_UNICAST,
+
+ NL80211_CMD_UPDATE_CONNECT_PARAMS,
+
/* add new commands above here */
/* used to define NL80211_CMD_MAX below */
@@ -1638,8 +1662,16 @@ enum nl80211_commands {
* the connection request from a station. nl80211_connect_failed_reason
* enum has different reasons of connection failure.
*
- * @NL80211_ATTR_SAE_DATA: SAE elements in Authentication frames. This starts
- * with the Authentication transaction sequence number field.
+ * @NL80211_ATTR_AUTH_DATA: Fields and elements in Authentication frames.
+ * This contains the authentication frame body (non-IE and IE data),
+ * excluding the Authentication algorithm number, i.e., starting at the
+ * Authentication transaction sequence number field. It is used with
+ * authentication algorithms that need special fields to be added into
+ * the frames (SAE and FILS). Currently, only the SAE cases use the
+ * initial two fields (Authentication transaction sequence number and
+ * Status code). However, those fields are included in the attribute data
+ * for all authentication algorithms to keep the attribute definition
+ * consistent.
*
* @NL80211_ATTR_VHT_CAPABILITY: VHT Capability information element (from
* association request when used with NL80211_CMD_NEW_STATION)
@@ -1936,6 +1968,14 @@ enum nl80211_commands {
* attribute.
* @NL80211_ATTR_NAN_MATCH: used to report a match. This is a nested attribute.
* See &enum nl80211_nan_match_attributes.
+ * @NL80211_ATTR_FILS_KEK: KEK for FILS (Re)Association Request/Response frame
+ * protection.
+ * @NL80211_ATTR_FILS_NONCES: Nonces (part of AAD) for FILS (Re)Association
+ * Request/Response frame protection. This attribute contains the 16 octet
+ * STA Nonce followed by 16 octets of AP Nonce.
+ *
+ * @NL80211_ATTR_MULTICAST_TO_UNICAST_ENABLED: Indicates whether or not multicast
+ * packets should be send out as unicast to all stations (flag attribute).
*
* @NUM_NL80211_ATTR: total number of nl80211_attrs available
* @NL80211_ATTR_MAX: highest attribute number currently defined
@@ -2195,7 +2235,7 @@ enum nl80211_attrs {
NL80211_ATTR_CONN_FAILED_REASON,
- NL80211_ATTR_SAE_DATA,
+ NL80211_ATTR_AUTH_DATA,
NL80211_ATTR_VHT_CAPABILITY,
@@ -2336,6 +2376,11 @@ enum nl80211_attrs {
NL80211_ATTR_NAN_FUNC,
NL80211_ATTR_NAN_MATCH,
+ NL80211_ATTR_FILS_KEK,
+ NL80211_ATTR_FILS_NONCES,
+
+ NL80211_ATTR_MULTICAST_TO_UNICAST_ENABLED,
+
/* add attributes here, update the policy in nl80211.c */
__NL80211_ATTR_AFTER_LAST,
@@ -2347,6 +2392,7 @@ enum nl80211_attrs {
#define NL80211_ATTR_SCAN_GENERATION NL80211_ATTR_GENERATION
#define NL80211_ATTR_MESH_PARAMS NL80211_ATTR_MESH_CONFIG
#define NL80211_ATTR_IFACE_SOCKET_OWNER NL80211_ATTR_SOCKET_OWNER
+#define NL80211_ATTR_SAE_DATA NL80211_ATTR_AUTH_DATA
/*
* Allow user space programs to use #ifdef on new attributes by defining them
@@ -3660,6 +3706,9 @@ enum nl80211_bss_status {
* @NL80211_AUTHTYPE_FT: Fast BSS Transition (IEEE 802.11r)
* @NL80211_AUTHTYPE_NETWORK_EAP: Network EAP (some Cisco APs and mainly LEAP)
* @NL80211_AUTHTYPE_SAE: Simultaneous authentication of equals
+ * @NL80211_AUTHTYPE_FILS_SK: Fast Initial Link Setup shared key
+ * @NL80211_AUTHTYPE_FILS_SK_PFS: Fast Initial Link Setup shared key with PFS
+ * @NL80211_AUTHTYPE_FILS_PK: Fast Initial Link Setup public key
* @__NL80211_AUTHTYPE_NUM: internal
* @NL80211_AUTHTYPE_MAX: maximum valid auth algorithm
* @NL80211_AUTHTYPE_AUTOMATIC: determine automatically (if necessary by
@@ -3672,6 +3721,9 @@ enum nl80211_auth_type {
NL80211_AUTHTYPE_FT,
NL80211_AUTHTYPE_NETWORK_EAP,
NL80211_AUTHTYPE_SAE,
+ NL80211_AUTHTYPE_FILS_SK,
+ NL80211_AUTHTYPE_FILS_SK_PFS,
+ NL80211_AUTHTYPE_FILS_PK,
/* keep last */
__NL80211_AUTHTYPE_NUM,
@@ -4280,6 +4332,9 @@ enum nl80211_iface_limit_attrs {
* of supported channel widths for radar detection.
* @NL80211_IFACE_COMB_RADAR_DETECT_REGIONS: u32 attribute containing the bitmap
* of supported regulatory regions for radar detection.
+ * @NL80211_IFACE_COMB_BI_MIN_GCD: u32 attribute specifying the minimum GCD of
+ * different beacon intervals supported by all the interface combinations
+ * in this group (if not present, all beacon intervals be identical).
* @NUM_NL80211_IFACE_COMB: number of attributes
* @MAX_NL80211_IFACE_COMB: highest attribute number
*
@@ -4287,8 +4342,8 @@ enum nl80211_iface_limit_attrs {
* limits = [ #{STA} <= 1, #{AP} <= 1 ], matching BI, channels = 1, max = 2
* => allows an AP and a STA that must match BIs
*
- * numbers = [ #{AP, P2P-GO} <= 8 ], channels = 1, max = 8
- * => allows 8 of AP/GO
+ * numbers = [ #{AP, P2P-GO} <= 8 ], BI min gcd, channels = 1, max = 8,
+ * => allows 8 of AP/GO that can have BI gcd >= min gcd
*
* numbers = [ #{STA} <= 2 ], channels = 2, max = 2
* => allows two STAs on different channels
@@ -4314,6 +4369,7 @@ enum nl80211_if_combination_attrs {
NL80211_IFACE_COMB_NUM_CHANNELS,
NL80211_IFACE_COMB_RADAR_DETECT_WIDTHS,
NL80211_IFACE_COMB_RADAR_DETECT_REGIONS,
+ NL80211_IFACE_COMB_BI_MIN_GCD,
/* keep last */
NUM_NL80211_IFACE_COMB,
@@ -4634,6 +4690,8 @@ enum nl80211_feature_flags {
* configuration (AP/mesh) with HT rates.
* @NL80211_EXT_FEATURE_BEACON_RATE_VHT: Driver supports beacon rate
* configuration (AP/mesh) with VHT rates.
+ * @NL80211_EXT_FEATURE_FILS_STA: This driver supports Fast Initial Link Setup
+ * with user space SME (NL80211_CMD_AUTHENTICATE) in station mode.
*
* @NUM_NL80211_EXT_FEATURES: number of extended features.
* @MAX_NL80211_EXT_FEATURES: highest extended feature index.
@@ -4648,6 +4706,7 @@ enum nl80211_ext_feature_index {
NL80211_EXT_FEATURE_BEACON_RATE_LEGACY,
NL80211_EXT_FEATURE_BEACON_RATE_HT,
NL80211_EXT_FEATURE_BEACON_RATE_VHT,
+ NL80211_EXT_FEATURE_FILS_STA,
/* add new features before the definition below */
NUM_NL80211_EXT_FEATURES,
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 59ed399..375d812 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -705,6 +705,15 @@ enum ovs_nat_attr {
#define OVS_NAT_ATTR_MAX (__OVS_NAT_ATTR_MAX - 1)
+/*
+ * struct ovs_action_push_eth - %OVS_ACTION_ATTR_PUSH_ETH action argument.
+ * @addresses: Source and destination MAC addresses.
+ * @eth_type: Ethernet type
+ */
+struct ovs_action_push_eth {
+ struct ovs_key_ethernet addresses;
+};
+
/**
* enum ovs_action_attr - Action types.
*
@@ -738,6 +747,10 @@ enum ovs_nat_attr {
* is no MPLS label stack, as determined by ethertype, no action is taken.
* @OVS_ACTION_ATTR_CT: Track the connection. Populate the conntrack-related
* entries in the flow key.
+ * @OVS_ACTION_ATTR_PUSH_ETH: Push a new outermost Ethernet header onto the
+ * packet.
+ * @OVS_ACTION_ATTR_POP_ETH: Pop the outermost Ethernet header off the
+ * packet.
*
* Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all
* fields within a header are modifiable, e.g. the IPv4 protocol and fragment
@@ -765,6 +778,8 @@ enum ovs_action_attr {
* bits. */
OVS_ACTION_ATTR_CT, /* Nested OVS_CT_ATTR_* . */
OVS_ACTION_ATTR_TRUNC, /* u32 struct ovs_action_trunc. */
+ OVS_ACTION_ATTR_PUSH_ETH, /* struct ovs_action_push_eth. */
+ OVS_ACTION_ATTR_POP_ETH, /* No argument. */
__OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted
* from userspace. */
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index d812172..e5a2e68 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -612,6 +612,8 @@
*/
#define PCI_EXP_DEVCAP2 36 /* Device Capabilities 2 */
#define PCI_EXP_DEVCAP2_ARI 0x00000020 /* Alternative Routing-ID */
+#define PCI_EXP_DEVCAP2_ATOMIC_ROUTE 0x00000040 /* Atomic Op routing */
+#define PCI_EXP_DEVCAP2_ATOMIC_COMP64 0x00000100 /* Atomic 64-bit compare */
#define PCI_EXP_DEVCAP2_LTR 0x00000800 /* Latency tolerance reporting */
#define PCI_EXP_DEVCAP2_OBFF_MASK 0x000c0000 /* OBFF support mechanism */
#define PCI_EXP_DEVCAP2_OBFF_MSG 0x00040000 /* New message signaling */
@@ -619,6 +621,7 @@
#define PCI_EXP_DEVCTL2 40 /* Device Control 2 */
#define PCI_EXP_DEVCTL2_COMP_TIMEOUT 0x000f /* Completion Timeout Value */
#define PCI_EXP_DEVCTL2_ARI 0x0020 /* Alternative Routing-ID */
+#define PCI_EXP_DEVCTL2_ATOMIC_REQ 0x0040 /* Set Atomic requests */
#define PCI_EXP_DEVCTL2_IDO_REQ_EN 0x0100 /* Allow IDO for requests */
#define PCI_EXP_DEVCTL2_IDO_CMP_EN 0x0200 /* Allow IDO for completions */
#define PCI_EXP_DEVCTL2_LTR_EN 0x0400 /* Enable LTR mechanism */
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 8fd715f..86786d4 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -447,6 +447,16 @@ enum {
TCA_FLOWER_KEY_TCP_DST_MASK, /* be16 */
TCA_FLOWER_KEY_UDP_SRC_MASK, /* be16 */
TCA_FLOWER_KEY_UDP_DST_MASK, /* be16 */
+ TCA_FLOWER_KEY_SCTP_SRC_MASK, /* be16 */
+ TCA_FLOWER_KEY_SCTP_DST_MASK, /* be16 */
+
+ TCA_FLOWER_KEY_SCTP_SRC, /* be16 */
+ TCA_FLOWER_KEY_SCTP_DST, /* be16 */
+
+ TCA_FLOWER_KEY_ENC_UDP_SRC_PORT, /* be16 */
+ TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK, /* be16 */
+ TCA_FLOWER_KEY_ENC_UDP_DST_PORT, /* be16 */
+ TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, /* be16 */
__TCA_FLOWER_MAX,
};
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 262f037..e14377f 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -318,6 +318,7 @@ enum rtattr_type_t {
RTA_ENCAP,
RTA_EXPIRES,
RTA_PAD,
+ RTA_UID,
__RTA_MAX
};
@@ -350,7 +351,7 @@ struct rtnexthop {
#define RTNH_F_OFFLOAD 8 /* offloaded route */
#define RTNH_F_LINKDOWN 16 /* carrier-down on nexthop */
-#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN)
+#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN | RTNH_F_OFFLOAD)
/* Macros to handle hexthops */
diff --git a/include/uapi/linux/seg6.h b/include/uapi/linux/seg6.h
new file mode 100644
index 0000000..c396a80
--- /dev/null
+++ b/include/uapi/linux/seg6.h
@@ -0,0 +1,54 @@
+/*
+ * SR-IPv6 implementation
+ *
+ * Author:
+ * David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _UAPI_LINUX_SEG6_H
+#define _UAPI_LINUX_SEG6_H
+
+/*
+ * SRH
+ */
+struct ipv6_sr_hdr {
+ __u8 nexthdr;
+ __u8 hdrlen;
+ __u8 type;
+ __u8 segments_left;
+ __u8 first_segment;
+ __u8 flag_1;
+ __u8 flag_2;
+ __u8 reserved;
+
+ struct in6_addr segments[0];
+};
+
+#define SR6_FLAG1_CLEANUP (1 << 7)
+#define SR6_FLAG1_PROTECTED (1 << 6)
+#define SR6_FLAG1_OAM (1 << 5)
+#define SR6_FLAG1_ALERT (1 << 4)
+#define SR6_FLAG1_HMAC (1 << 3)
+
+#define SR6_TLV_INGRESS 1
+#define SR6_TLV_EGRESS 2
+#define SR6_TLV_OPAQUE 3
+#define SR6_TLV_PADDING 4
+#define SR6_TLV_HMAC 5
+
+#define sr_has_cleanup(srh) ((srh)->flag_1 & SR6_FLAG1_CLEANUP)
+#define sr_has_hmac(srh) ((srh)->flag_1 & SR6_FLAG1_HMAC)
+
+struct sr6_tlv {
+ __u8 type;
+ __u8 len;
+ __u8 data[0];
+};
+
+#endif
diff --git a/include/uapi/linux/seg6_genl.h b/include/uapi/linux/seg6_genl.h
new file mode 100644
index 0000000..fcf1c60
--- /dev/null
+++ b/include/uapi/linux/seg6_genl.h
@@ -0,0 +1,32 @@
+#ifndef _UAPI_LINUX_SEG6_GENL_H
+#define _UAPI_LINUX_SEG6_GENL_H
+
+#define SEG6_GENL_NAME "SEG6"
+#define SEG6_GENL_VERSION 0x1
+
+enum {
+ SEG6_ATTR_UNSPEC,
+ SEG6_ATTR_DST,
+ SEG6_ATTR_DSTLEN,
+ SEG6_ATTR_HMACKEYID,
+ SEG6_ATTR_SECRET,
+ SEG6_ATTR_SECRETLEN,
+ SEG6_ATTR_ALGID,
+ SEG6_ATTR_HMACINFO,
+ __SEG6_ATTR_MAX,
+};
+
+#define SEG6_ATTR_MAX (__SEG6_ATTR_MAX - 1)
+
+enum {
+ SEG6_CMD_UNSPEC,
+ SEG6_CMD_SETHMAC,
+ SEG6_CMD_DUMPHMAC,
+ SEG6_CMD_SET_TUNSRC,
+ SEG6_CMD_GET_TUNSRC,
+ __SEG6_CMD_MAX,
+};
+
+#define SEG6_CMD_MAX (__SEG6_CMD_MAX - 1)
+
+#endif
diff --git a/include/uapi/linux/seg6_hmac.h b/include/uapi/linux/seg6_hmac.h
new file mode 100644
index 0000000..b652dfd
--- /dev/null
+++ b/include/uapi/linux/seg6_hmac.h
@@ -0,0 +1,21 @@
+#ifndef _UAPI_LINUX_SEG6_HMAC_H
+#define _UAPI_LINUX_SEG6_HMAC_H
+
+#include <linux/seg6.h>
+
+#define SEG6_HMAC_SECRET_LEN 64
+#define SEG6_HMAC_FIELD_LEN 32
+
+struct sr6_tlv_hmac {
+ struct sr6_tlv tlvhdr;
+ __u16 reserved;
+ __be32 hmackeyid;
+ __u8 hmac[SEG6_HMAC_FIELD_LEN];
+};
+
+enum {
+ SEG6_HMAC_ALGO_SHA1 = 1,
+ SEG6_HMAC_ALGO_SHA256 = 2,
+};
+
+#endif
diff --git a/include/uapi/linux/seg6_iptunnel.h b/include/uapi/linux/seg6_iptunnel.h
new file mode 100644
index 0000000..0f7dbd2
--- /dev/null
+++ b/include/uapi/linux/seg6_iptunnel.h
@@ -0,0 +1,44 @@
+/*
+ * SR-IPv6 implementation
+ *
+ * Author:
+ * David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _UAPI_LINUX_SEG6_IPTUNNEL_H
+#define _UAPI_LINUX_SEG6_IPTUNNEL_H
+
+enum {
+ SEG6_IPTUNNEL_UNSPEC,
+ SEG6_IPTUNNEL_SRH,
+ __SEG6_IPTUNNEL_MAX,
+};
+#define SEG6_IPTUNNEL_MAX (__SEG6_IPTUNNEL_MAX - 1)
+
+struct seg6_iptunnel_encap {
+ int mode;
+ struct ipv6_sr_hdr srh[0];
+};
+
+#define SEG6_IPTUN_ENCAP_SIZE(x) ((sizeof(*x)) + (((x)->srh->hdrlen + 1) << 3))
+
+enum {
+ SEG6_IPTUN_MODE_INLINE,
+ SEG6_IPTUN_MODE_ENCAP,
+};
+
+static inline size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo)
+{
+ int encap = (tuninfo->mode == SEG6_IPTUN_MODE_ENCAP);
+
+ return ((tuninfo->srh->hdrlen + 1) << 3) +
+ (encap * sizeof(struct ipv6hdr));
+}
+
+#endif
diff --git a/include/uapi/linux/sockios.h b/include/uapi/linux/sockios.h
index 8e7890b..79d029d 100644
--- a/include/uapi/linux/sockios.h
+++ b/include/uapi/linux/sockios.h
@@ -24,6 +24,8 @@
#define SIOCINQ FIONREAD
#define SIOCOUTQ TIOCOUTQ /* output queue size (not sent + not acked) */
+#define SOCK_IOC_TYPE 0x89
+
/* Routing table calls. */
#define SIOCADDRT 0x890B /* add routing table entry */
#define SIOCDELRT 0x890C /* delete routing table entry */
@@ -84,6 +86,7 @@
#define SIOCWANDEV 0x894A /* get/set netdev parameters */
#define SIOCOUTQNSD 0x894B /* output queue size (not sent only) */
+#define SIOCGSKNS 0x894C /* get socket network namespace */
/* ARP cache control calls. */
/* 0x8950 - 0x8952 * obsolete calls, don't re-use */
diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h
index 890106f..84ea55e 100644
--- a/include/uapi/linux/tc_act/tc_tunnel_key.h
+++ b/include/uapi/linux/tc_act/tc_tunnel_key.h
@@ -33,6 +33,7 @@ enum {
TCA_TUNNEL_KEY_ENC_IPV6_DST, /* struct in6_addr */
TCA_TUNNEL_KEY_ENC_KEY_ID, /* be64 */
TCA_TUNNEL_KEY_PAD,
+ TCA_TUNNEL_KEY_ENC_DST_PORT, /* be16 */
__TCA_TUNNEL_KEY_MAX,
};
diff --git a/include/uapi/rdma/qedr-abi.h b/include/uapi/rdma/qedr-abi.h
new file mode 100644
index 0000000..75c270d
--- /dev/null
+++ b/include/uapi/rdma/qedr-abi.h
@@ -0,0 +1,106 @@
+/* QLogic qedr NIC Driver
+ * Copyright (c) 2015-2016 QLogic Corporation
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and /or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef __QEDR_USER_H__
+#define __QEDR_USER_H__
+
+#include <linux/types.h>
+
+#define QEDR_ABI_VERSION (8)
+
+/* user kernel communication data structures. */
+
+struct qedr_alloc_ucontext_resp {
+ __u64 db_pa;
+ __u32 db_size;
+
+ __u32 max_send_wr;
+ __u32 max_recv_wr;
+ __u32 max_srq_wr;
+ __u32 sges_per_send_wr;
+ __u32 sges_per_recv_wr;
+ __u32 sges_per_srq_wr;
+ __u32 max_cqes;
+};
+
+struct qedr_alloc_pd_ureq {
+ __u64 rsvd1;
+};
+
+struct qedr_alloc_pd_uresp {
+ __u32 pd_id;
+};
+
+struct qedr_create_cq_ureq {
+ __u64 addr;
+ __u64 len;
+};
+
+struct qedr_create_cq_uresp {
+ __u32 db_offset;
+ __u16 icid;
+};
+
+struct qedr_create_qp_ureq {
+ __u32 qp_handle_hi;
+ __u32 qp_handle_lo;
+
+ /* SQ */
+ /* user space virtual address of SQ buffer */
+ __u64 sq_addr;
+
+ /* length of SQ buffer */
+ __u64 sq_len;
+
+ /* RQ */
+ /* user space virtual address of RQ buffer */
+ __u64 rq_addr;
+
+ /* length of RQ buffer */
+ __u64 rq_len;
+};
+
+struct qedr_create_qp_uresp {
+ __u32 qp_id;
+ __u32 atomic_supported;
+
+ /* SQ */
+ __u32 sq_db_offset;
+ __u16 sq_icid;
+
+ /* RQ */
+ __u32 rq_db_offset;
+ __u16 rq_icid;
+
+ __u32 rq_db2_offset;
+};
+
+#endif /* __QEDR_USER_H__ */
diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h
index 33d00a4..819d895 100644
--- a/include/uapi/sound/asoc.h
+++ b/include/uapi/sound/asoc.h
@@ -18,12 +18,6 @@
#include <linux/types.h>
#include <sound/asound.h>
-#ifndef __KERNEL__
-#error This API is an early revision and not enabled in the current
-#error kernel release, it will be enabled in a future kernel version
-#error with incompatible changes to what is here.
-#endif
-
/*
* Maximum number of channels topology kcontrol can represent.
*/
diff --git a/init/Makefile b/init/Makefile
index 7bc47ee..c4fb455 100644
--- a/init/Makefile
+++ b/init/Makefile
@@ -2,6 +2,8 @@
# Makefile for the linux kernel.
#
+ccflags-y := -fno-function-sections -fno-data-sections
+
obj-y := main.o version.o mounts.o
ifneq ($(CONFIG_BLK_DEV_INITRD),y)
obj-y += noinitramfs.o
diff --git a/init/main.c b/init/main.c
index a8a58e2..2858be7 100644
--- a/init/main.c
+++ b/init/main.c
@@ -789,6 +789,7 @@ int __init_or_module do_one_initcall(initcall_t fn)
}
WARN(msgbuf[0], "initcall %pF returned with %s\n", fn, msgbuf);
+ add_latent_entropy();
return ret;
}
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index a521999..bf74eaa 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -53,7 +53,7 @@ static struct msg_msg *alloc_msg(size_t len)
size_t alen;
alen = min(len, DATALEN_MSG);
- msg = kmalloc(sizeof(*msg) + alen, GFP_KERNEL);
+ msg = kmalloc(sizeof(*msg) + alen, GFP_KERNEL_ACCOUNT);
if (msg == NULL)
return NULL;
@@ -65,7 +65,7 @@ static struct msg_msg *alloc_msg(size_t len)
while (len > 0) {
struct msg_msgseg *seg;
alen = min(len, DATALEN_SEG);
- seg = kmalloc(sizeof(*seg) + alen, GFP_KERNEL);
+ seg = kmalloc(sizeof(*seg) + alen, GFP_KERNEL_ACCOUNT);
if (seg == NULL)
goto out_err;
*pseg = seg;
diff --git a/kernel/audit.c b/kernel/audit.c
index f1ca116..92c463d 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -126,7 +126,7 @@ static atomic_t audit_lost = ATOMIC_INIT(0);
/* The netlink socket. */
static struct sock *audit_sock;
-static int audit_net_id;
+static unsigned int audit_net_id;
/* Hash for inode-based rules */
struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS];
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index eed911d..c4d89d6 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,7 +1,7 @@
obj-y := core.o
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o
-obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o
+obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o
ifeq ($(CONFIG_PERF_EVENTS),y)
obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
endif
diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c
new file mode 100644
index 0000000..89b7ef4
--- /dev/null
+++ b/kernel/bpf/bpf_lru_list.c
@@ -0,0 +1,695 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/cpumask.h>
+#include <linux/spinlock.h>
+#include <linux/percpu.h>
+
+#include "bpf_lru_list.h"
+
+#define LOCAL_FREE_TARGET (128)
+#define LOCAL_NR_SCANS LOCAL_FREE_TARGET
+
+#define PERCPU_FREE_TARGET (16)
+#define PERCPU_NR_SCANS PERCPU_FREE_TARGET
+
+/* Helpers to get the local list index */
+#define LOCAL_LIST_IDX(t) ((t) - BPF_LOCAL_LIST_T_OFFSET)
+#define LOCAL_FREE_LIST_IDX LOCAL_LIST_IDX(BPF_LRU_LOCAL_LIST_T_FREE)
+#define LOCAL_PENDING_LIST_IDX LOCAL_LIST_IDX(BPF_LRU_LOCAL_LIST_T_PENDING)
+#define IS_LOCAL_LIST_TYPE(t) ((t) >= BPF_LOCAL_LIST_T_OFFSET)
+
+static int get_next_cpu(int cpu)
+{
+ cpu = cpumask_next(cpu, cpu_possible_mask);
+ if (cpu >= nr_cpu_ids)
+ cpu = cpumask_first(cpu_possible_mask);
+ return cpu;
+}
+
+/* Local list helpers */
+static struct list_head *local_free_list(struct bpf_lru_locallist *loc_l)
+{
+ return &loc_l->lists[LOCAL_FREE_LIST_IDX];
+}
+
+static struct list_head *local_pending_list(struct bpf_lru_locallist *loc_l)
+{
+ return &loc_l->lists[LOCAL_PENDING_LIST_IDX];
+}
+
+/* bpf_lru_node helpers */
+static bool bpf_lru_node_is_ref(const struct bpf_lru_node *node)
+{
+ return node->ref;
+}
+
+static void bpf_lru_list_count_inc(struct bpf_lru_list *l,
+ enum bpf_lru_list_type type)
+{
+ if (type < NR_BPF_LRU_LIST_COUNT)
+ l->counts[type]++;
+}
+
+static void bpf_lru_list_count_dec(struct bpf_lru_list *l,
+ enum bpf_lru_list_type type)
+{
+ if (type < NR_BPF_LRU_LIST_COUNT)
+ l->counts[type]--;
+}
+
+static void __bpf_lru_node_move_to_free(struct bpf_lru_list *l,
+ struct bpf_lru_node *node,
+ struct list_head *free_list,
+ enum bpf_lru_list_type tgt_free_type)
+{
+ if (WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(node->type)))
+ return;
+
+ /* If the removing node is the next_inactive_rotation candidate,
+ * move the next_inactive_rotation pointer also.
+ */
+ if (&node->list == l->next_inactive_rotation)
+ l->next_inactive_rotation = l->next_inactive_rotation->prev;
+
+ bpf_lru_list_count_dec(l, node->type);
+
+ node->type = tgt_free_type;
+ list_move(&node->list, free_list);
+}
+
+/* Move nodes from local list to the LRU list */
+static void __bpf_lru_node_move_in(struct bpf_lru_list *l,
+ struct bpf_lru_node *node,
+ enum bpf_lru_list_type tgt_type)
+{
+ if (WARN_ON_ONCE(!IS_LOCAL_LIST_TYPE(node->type)) ||
+ WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(tgt_type)))
+ return;
+
+ bpf_lru_list_count_inc(l, tgt_type);
+ node->type = tgt_type;
+ node->ref = 0;
+ list_move(&node->list, &l->lists[tgt_type]);
+}
+
+/* Move nodes between or within active and inactive list (like
+ * active to inactive, inactive to active or tail of active back to
+ * the head of active).
+ */
+static void __bpf_lru_node_move(struct bpf_lru_list *l,
+ struct bpf_lru_node *node,
+ enum bpf_lru_list_type tgt_type)
+{
+ if (WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(node->type)) ||
+ WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(tgt_type)))
+ return;
+
+ if (node->type != tgt_type) {
+ bpf_lru_list_count_dec(l, node->type);
+ bpf_lru_list_count_inc(l, tgt_type);
+ node->type = tgt_type;
+ }
+ node->ref = 0;
+
+ /* If the moving node is the next_inactive_rotation candidate,
+ * move the next_inactive_rotation pointer also.
+ */
+ if (&node->list == l->next_inactive_rotation)
+ l->next_inactive_rotation = l->next_inactive_rotation->prev;
+
+ list_move(&node->list, &l->lists[tgt_type]);
+}
+
+static bool bpf_lru_list_inactive_low(const struct bpf_lru_list *l)
+{
+ return l->counts[BPF_LRU_LIST_T_INACTIVE] <
+ l->counts[BPF_LRU_LIST_T_ACTIVE];
+}
+
+/* Rotate the active list:
+ * 1. Start from tail
+ * 2. If the node has the ref bit set, it will be rotated
+ * back to the head of active list with the ref bit cleared.
+ * Give this node one more chance to survive in the active list.
+ * 3. If the ref bit is not set, move it to the head of the
+ * inactive list.
+ * 4. It will at most scan nr_scans nodes
+ */
+static void __bpf_lru_list_rotate_active(struct bpf_lru *lru,
+ struct bpf_lru_list *l)
+{
+ struct list_head *active = &l->lists[BPF_LRU_LIST_T_ACTIVE];
+ struct bpf_lru_node *node, *tmp_node, *first_node;
+ unsigned int i = 0;
+
+ first_node = list_first_entry(active, struct bpf_lru_node, list);
+ list_for_each_entry_safe_reverse(node, tmp_node, active, list) {
+ if (bpf_lru_node_is_ref(node))
+ __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_ACTIVE);
+ else
+ __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE);
+
+ if (++i == lru->nr_scans || node == first_node)
+ break;
+ }
+}
+
+/* Rotate the inactive list. It starts from the next_inactive_rotation
+ * 1. If the node has ref bit set, it will be moved to the head
+ * of active list with the ref bit cleared.
+ * 2. If the node does not have ref bit set, it will leave it
+ * at its current location (i.e. do nothing) so that it can
+ * be considered during the next inactive_shrink.
+ * 3. It will at most scan nr_scans nodes
+ */
+static void __bpf_lru_list_rotate_inactive(struct bpf_lru *lru,
+ struct bpf_lru_list *l)
+{
+ struct list_head *inactive = &l->lists[BPF_LRU_LIST_T_INACTIVE];
+ struct list_head *cur, *last, *next = inactive;
+ struct bpf_lru_node *node;
+ unsigned int i = 0;
+
+ if (list_empty(inactive))
+ return;
+
+ last = l->next_inactive_rotation->next;
+ if (last == inactive)
+ last = last->next;
+
+ cur = l->next_inactive_rotation;
+ while (i < lru->nr_scans) {
+ if (cur == inactive) {
+ cur = cur->prev;
+ continue;
+ }
+
+ node = list_entry(cur, struct bpf_lru_node, list);
+ next = cur->prev;
+ if (bpf_lru_node_is_ref(node))
+ __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_ACTIVE);
+ if (cur == last)
+ break;
+ cur = next;
+ i++;
+ }
+
+ l->next_inactive_rotation = next;
+}
+
+/* Shrink the inactive list. It starts from the tail of the
+ * inactive list and only move the nodes without the ref bit
+ * set to the designated free list.
+ */
+static unsigned int
+__bpf_lru_list_shrink_inactive(struct bpf_lru *lru,
+ struct bpf_lru_list *l,
+ unsigned int tgt_nshrink,
+ struct list_head *free_list,
+ enum bpf_lru_list_type tgt_free_type)
+{
+ struct list_head *inactive = &l->lists[BPF_LRU_LIST_T_INACTIVE];
+ struct bpf_lru_node *node, *tmp_node, *first_node;
+ unsigned int nshrinked = 0;
+ unsigned int i = 0;
+
+ first_node = list_first_entry(inactive, struct bpf_lru_node, list);
+ list_for_each_entry_safe_reverse(node, tmp_node, inactive, list) {
+ if (bpf_lru_node_is_ref(node)) {
+ __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_ACTIVE);
+ } else if (lru->del_from_htab(lru->del_arg, node)) {
+ __bpf_lru_node_move_to_free(l, node, free_list,
+ tgt_free_type);
+ if (++nshrinked == tgt_nshrink)
+ break;
+ }
+
+ if (++i == lru->nr_scans)
+ break;
+ }
+
+ return nshrinked;
+}
+
+/* 1. Rotate the active list (if needed)
+ * 2. Always rotate the inactive list
+ */
+static void __bpf_lru_list_rotate(struct bpf_lru *lru, struct bpf_lru_list *l)
+{
+ if (bpf_lru_list_inactive_low(l))
+ __bpf_lru_list_rotate_active(lru, l);
+
+ __bpf_lru_list_rotate_inactive(lru, l);
+}
+
+/* Calls __bpf_lru_list_shrink_inactive() to shrink some
+ * ref-bit-cleared nodes and move them to the designated
+ * free list.
+ *
+ * If it cannot get a free node after calling
+ * __bpf_lru_list_shrink_inactive(). It will just remove
+ * one node from either inactive or active list without
+ * honoring the ref-bit. It prefers inactive list to active
+ * list in this situation.
+ */
+static unsigned int __bpf_lru_list_shrink(struct bpf_lru *lru,
+ struct bpf_lru_list *l,
+ unsigned int tgt_nshrink,
+ struct list_head *free_list,
+ enum bpf_lru_list_type tgt_free_type)
+
+{
+ struct bpf_lru_node *node, *tmp_node;
+ struct list_head *force_shrink_list;
+ unsigned int nshrinked;
+
+ nshrinked = __bpf_lru_list_shrink_inactive(lru, l, tgt_nshrink,
+ free_list, tgt_free_type);
+ if (nshrinked)
+ return nshrinked;
+
+ /* Do a force shrink by ignoring the reference bit */
+ if (!list_empty(&l->lists[BPF_LRU_LIST_T_INACTIVE]))
+ force_shrink_list = &l->lists[BPF_LRU_LIST_T_INACTIVE];
+ else
+ force_shrink_list = &l->lists[BPF_LRU_LIST_T_ACTIVE];
+
+ list_for_each_entry_safe_reverse(node, tmp_node, force_shrink_list,
+ list) {
+ if (lru->del_from_htab(lru->del_arg, node)) {
+ __bpf_lru_node_move_to_free(l, node, free_list,
+ tgt_free_type);
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
+/* Flush the nodes from the local pending list to the LRU list */
+static void __local_list_flush(struct bpf_lru_list *l,
+ struct bpf_lru_locallist *loc_l)
+{
+ struct bpf_lru_node *node, *tmp_node;
+
+ list_for_each_entry_safe_reverse(node, tmp_node,
+ local_pending_list(loc_l), list) {
+ if (bpf_lru_node_is_ref(node))
+ __bpf_lru_node_move_in(l, node, BPF_LRU_LIST_T_ACTIVE);
+ else
+ __bpf_lru_node_move_in(l, node,
+ BPF_LRU_LIST_T_INACTIVE);
+ }
+}
+
+static void bpf_lru_list_push_free(struct bpf_lru_list *l,
+ struct bpf_lru_node *node)
+{
+ unsigned long flags;
+
+ if (WARN_ON_ONCE(IS_LOCAL_LIST_TYPE(node->type)))
+ return;
+
+ raw_spin_lock_irqsave(&l->lock, flags);
+ __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_FREE);
+ raw_spin_unlock_irqrestore(&l->lock, flags);
+}
+
+static void bpf_lru_list_pop_free_to_local(struct bpf_lru *lru,
+ struct bpf_lru_locallist *loc_l)
+{
+ struct bpf_lru_list *l = &lru->common_lru.lru_list;
+ struct bpf_lru_node *node, *tmp_node;
+ unsigned int nfree = 0;
+
+ raw_spin_lock(&l->lock);
+
+ __local_list_flush(l, loc_l);
+
+ __bpf_lru_list_rotate(lru, l);
+
+ list_for_each_entry_safe(node, tmp_node, &l->lists[BPF_LRU_LIST_T_FREE],
+ list) {
+ __bpf_lru_node_move_to_free(l, node, local_free_list(loc_l),
+ BPF_LRU_LOCAL_LIST_T_FREE);
+ if (++nfree == LOCAL_FREE_TARGET)
+ break;
+ }
+
+ if (nfree < LOCAL_FREE_TARGET)
+ __bpf_lru_list_shrink(lru, l, LOCAL_FREE_TARGET - nfree,
+ local_free_list(loc_l),
+ BPF_LRU_LOCAL_LIST_T_FREE);
+
+ raw_spin_unlock(&l->lock);
+}
+
+static void __local_list_add_pending(struct bpf_lru *lru,
+ struct bpf_lru_locallist *loc_l,
+ int cpu,
+ struct bpf_lru_node *node,
+ u32 hash)
+{
+ *(u32 *)((void *)node + lru->hash_offset) = hash;
+ node->cpu = cpu;
+ node->type = BPF_LRU_LOCAL_LIST_T_PENDING;
+ node->ref = 0;
+ list_add(&node->list, local_pending_list(loc_l));
+}
+
+struct bpf_lru_node *__local_list_pop_free(struct bpf_lru_locallist *loc_l)
+{
+ struct bpf_lru_node *node;
+
+ node = list_first_entry_or_null(local_free_list(loc_l),
+ struct bpf_lru_node,
+ list);
+ if (node)
+ list_del(&node->list);
+
+ return node;
+}
+
+struct bpf_lru_node *__local_list_pop_pending(struct bpf_lru *lru,
+ struct bpf_lru_locallist *loc_l)
+{
+ struct bpf_lru_node *node;
+ bool force = false;
+
+ignore_ref:
+ /* Get from the tail (i.e. older element) of the pending list. */
+ list_for_each_entry_reverse(node, local_pending_list(loc_l),
+ list) {
+ if ((!bpf_lru_node_is_ref(node) || force) &&
+ lru->del_from_htab(lru->del_arg, node)) {
+ list_del(&node->list);
+ return node;
+ }
+ }
+
+ if (!force) {
+ force = true;
+ goto ignore_ref;
+ }
+
+ return NULL;
+}
+
+static struct bpf_lru_node *bpf_percpu_lru_pop_free(struct bpf_lru *lru,
+ u32 hash)
+{
+ struct list_head *free_list;
+ struct bpf_lru_node *node = NULL;
+ struct bpf_lru_list *l;
+ unsigned long flags;
+ int cpu = raw_smp_processor_id();
+
+ l = per_cpu_ptr(lru->percpu_lru, cpu);
+
+ raw_spin_lock_irqsave(&l->lock, flags);
+
+ __bpf_lru_list_rotate(lru, l);
+
+ free_list = &l->lists[BPF_LRU_LIST_T_FREE];
+ if (list_empty(free_list))
+ __bpf_lru_list_shrink(lru, l, PERCPU_FREE_TARGET, free_list,
+ BPF_LRU_LIST_T_FREE);
+
+ if (!list_empty(free_list)) {
+ node = list_first_entry(free_list, struct bpf_lru_node, list);
+ *(u32 *)((void *)node + lru->hash_offset) = hash;
+ node->ref = 0;
+ __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE);
+ }
+
+ raw_spin_unlock_irqrestore(&l->lock, flags);
+
+ return node;
+}
+
+static struct bpf_lru_node *bpf_common_lru_pop_free(struct bpf_lru *lru,
+ u32 hash)
+{
+ struct bpf_lru_locallist *loc_l, *steal_loc_l;
+ struct bpf_common_lru *clru = &lru->common_lru;
+ struct bpf_lru_node *node;
+ int steal, first_steal;
+ unsigned long flags;
+ int cpu = raw_smp_processor_id();
+
+ loc_l = per_cpu_ptr(clru->local_list, cpu);
+
+ raw_spin_lock_irqsave(&loc_l->lock, flags);
+
+ node = __local_list_pop_free(loc_l);
+ if (!node) {
+ bpf_lru_list_pop_free_to_local(lru, loc_l);
+ node = __local_list_pop_free(loc_l);
+ }
+
+ if (node)
+ __local_list_add_pending(lru, loc_l, cpu, node, hash);
+
+ raw_spin_unlock_irqrestore(&loc_l->lock, flags);
+
+ if (node)
+ return node;
+
+ /* No free nodes found from the local free list and
+ * the global LRU list.
+ *
+ * Steal from the local free/pending list of the
+ * current CPU and remote CPU in RR. It starts
+ * with the loc_l->next_steal CPU.
+ */
+
+ first_steal = loc_l->next_steal;
+ steal = first_steal;
+ do {
+ steal_loc_l = per_cpu_ptr(clru->local_list, steal);
+
+ raw_spin_lock_irqsave(&steal_loc_l->lock, flags);
+
+ node = __local_list_pop_free(steal_loc_l);
+ if (!node)
+ node = __local_list_pop_pending(lru, steal_loc_l);
+
+ raw_spin_unlock_irqrestore(&steal_loc_l->lock, flags);
+
+ steal = get_next_cpu(steal);
+ } while (!node && steal != first_steal);
+
+ loc_l->next_steal = steal;
+
+ if (node) {
+ raw_spin_lock_irqsave(&loc_l->lock, flags);
+ __local_list_add_pending(lru, loc_l, cpu, node, hash);
+ raw_spin_unlock_irqrestore(&loc_l->lock, flags);
+ }
+
+ return node;
+}
+
+struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash)
+{
+ if (lru->percpu)
+ return bpf_percpu_lru_pop_free(lru, hash);
+ else
+ return bpf_common_lru_pop_free(lru, hash);
+}
+
+static void bpf_common_lru_push_free(struct bpf_lru *lru,
+ struct bpf_lru_node *node)
+{
+ unsigned long flags;
+
+ if (WARN_ON_ONCE(node->type == BPF_LRU_LIST_T_FREE) ||
+ WARN_ON_ONCE(node->type == BPF_LRU_LOCAL_LIST_T_FREE))
+ return;
+
+ if (node->type == BPF_LRU_LOCAL_LIST_T_PENDING) {
+ struct bpf_lru_locallist *loc_l;
+
+ loc_l = per_cpu_ptr(lru->common_lru.local_list, node->cpu);
+
+ raw_spin_lock_irqsave(&loc_l->lock, flags);
+
+ if (unlikely(node->type != BPF_LRU_LOCAL_LIST_T_PENDING)) {
+ raw_spin_unlock_irqrestore(&loc_l->lock, flags);
+ goto check_lru_list;
+ }
+
+ node->type = BPF_LRU_LOCAL_LIST_T_FREE;
+ node->ref = 0;
+ list_move(&node->list, local_free_list(loc_l));
+
+ raw_spin_unlock_irqrestore(&loc_l->lock, flags);
+ return;
+ }
+
+check_lru_list:
+ bpf_lru_list_push_free(&lru->common_lru.lru_list, node);
+}
+
+static void bpf_percpu_lru_push_free(struct bpf_lru *lru,
+ struct bpf_lru_node *node)
+{
+ struct bpf_lru_list *l;
+ unsigned long flags;
+
+ l = per_cpu_ptr(lru->percpu_lru, node->cpu);
+
+ raw_spin_lock_irqsave(&l->lock, flags);
+
+ __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_FREE);
+
+ raw_spin_unlock_irqrestore(&l->lock, flags);
+}
+
+void bpf_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node)
+{
+ if (lru->percpu)
+ bpf_percpu_lru_push_free(lru, node);
+ else
+ bpf_common_lru_push_free(lru, node);
+}
+
+void bpf_common_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset,
+ u32 elem_size, u32 nr_elems)
+{
+ struct bpf_lru_list *l = &lru->common_lru.lru_list;
+ u32 i;
+
+ for (i = 0; i < nr_elems; i++) {
+ struct bpf_lru_node *node;
+
+ node = (struct bpf_lru_node *)(buf + node_offset);
+ node->type = BPF_LRU_LIST_T_FREE;
+ node->ref = 0;
+ list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]);
+ buf += elem_size;
+ }
+}
+
+void bpf_percpu_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset,
+ u32 elem_size, u32 nr_elems)
+{
+ u32 i, pcpu_entries;
+ int cpu;
+ struct bpf_lru_list *l;
+
+ pcpu_entries = nr_elems / num_possible_cpus();
+
+ i = 0;
+
+ for_each_possible_cpu(cpu) {
+ struct bpf_lru_node *node;
+
+ l = per_cpu_ptr(lru->percpu_lru, cpu);
+again:
+ node = (struct bpf_lru_node *)(buf + node_offset);
+ node->cpu = cpu;
+ node->type = BPF_LRU_LIST_T_FREE;
+ node->ref = 0;
+ list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]);
+ i++;
+ buf += elem_size;
+ if (i == nr_elems)
+ break;
+ if (i % pcpu_entries)
+ goto again;
+ }
+}
+
+void bpf_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset,
+ u32 elem_size, u32 nr_elems)
+{
+ if (lru->percpu)
+ bpf_percpu_lru_populate(lru, buf, node_offset, elem_size,
+ nr_elems);
+ else
+ bpf_common_lru_populate(lru, buf, node_offset, elem_size,
+ nr_elems);
+}
+
+static void bpf_lru_locallist_init(struct bpf_lru_locallist *loc_l, int cpu)
+{
+ int i;
+
+ for (i = 0; i < NR_BPF_LRU_LOCAL_LIST_T; i++)
+ INIT_LIST_HEAD(&loc_l->lists[i]);
+
+ loc_l->next_steal = cpu;
+
+ raw_spin_lock_init(&loc_l->lock);
+}
+
+static void bpf_lru_list_init(struct bpf_lru_list *l)
+{
+ int i;
+
+ for (i = 0; i < NR_BPF_LRU_LIST_T; i++)
+ INIT_LIST_HEAD(&l->lists[i]);
+
+ for (i = 0; i < NR_BPF_LRU_LIST_COUNT; i++)
+ l->counts[i] = 0;
+
+ l->next_inactive_rotation = &l->lists[BPF_LRU_LIST_T_INACTIVE];
+
+ raw_spin_lock_init(&l->lock);
+}
+
+int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset,
+ del_from_htab_func del_from_htab, void *del_arg)
+{
+ int cpu;
+
+ if (percpu) {
+ lru->percpu_lru = alloc_percpu(struct bpf_lru_list);
+ if (!lru->percpu_lru)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ struct bpf_lru_list *l;
+
+ l = per_cpu_ptr(lru->percpu_lru, cpu);
+ bpf_lru_list_init(l);
+ }
+ lru->nr_scans = PERCPU_NR_SCANS;
+ } else {
+ struct bpf_common_lru *clru = &lru->common_lru;
+
+ clru->local_list = alloc_percpu(struct bpf_lru_locallist);
+ if (!clru->local_list)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ struct bpf_lru_locallist *loc_l;
+
+ loc_l = per_cpu_ptr(clru->local_list, cpu);
+ bpf_lru_locallist_init(loc_l, cpu);
+ }
+
+ bpf_lru_list_init(&clru->lru_list);
+ lru->nr_scans = LOCAL_NR_SCANS;
+ }
+
+ lru->percpu = percpu;
+ lru->del_from_htab = del_from_htab;
+ lru->del_arg = del_arg;
+ lru->hash_offset = hash_offset;
+
+ return 0;
+}
+
+void bpf_lru_destroy(struct bpf_lru *lru)
+{
+ if (lru->percpu)
+ free_percpu(lru->percpu_lru);
+ else
+ free_percpu(lru->common_lru.local_list);
+}
diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h
new file mode 100644
index 0000000..5c35a98
--- /dev/null
+++ b/kernel/bpf/bpf_lru_list.h
@@ -0,0 +1,84 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef __BPF_LRU_LIST_H_
+#define __BPF_LRU_LIST_H_
+
+#include <linux/list.h>
+#include <linux/spinlock_types.h>
+
+#define NR_BPF_LRU_LIST_T (3)
+#define NR_BPF_LRU_LIST_COUNT (2)
+#define NR_BPF_LRU_LOCAL_LIST_T (2)
+#define BPF_LOCAL_LIST_T_OFFSET NR_BPF_LRU_LIST_T
+
+enum bpf_lru_list_type {
+ BPF_LRU_LIST_T_ACTIVE,
+ BPF_LRU_LIST_T_INACTIVE,
+ BPF_LRU_LIST_T_FREE,
+ BPF_LRU_LOCAL_LIST_T_FREE,
+ BPF_LRU_LOCAL_LIST_T_PENDING,
+};
+
+struct bpf_lru_node {
+ struct list_head list;
+ u16 cpu;
+ u8 type;
+ u8 ref;
+};
+
+struct bpf_lru_list {
+ struct list_head lists[NR_BPF_LRU_LIST_T];
+ unsigned int counts[NR_BPF_LRU_LIST_COUNT];
+ /* The next inacitve list rotation starts from here */
+ struct list_head *next_inactive_rotation;
+
+ raw_spinlock_t lock ____cacheline_aligned_in_smp;
+};
+
+struct bpf_lru_locallist {
+ struct list_head lists[NR_BPF_LRU_LOCAL_LIST_T];
+ u16 next_steal;
+ raw_spinlock_t lock;
+};
+
+struct bpf_common_lru {
+ struct bpf_lru_list lru_list;
+ struct bpf_lru_locallist __percpu *local_list;
+};
+
+typedef bool (*del_from_htab_func)(void *arg, struct bpf_lru_node *node);
+
+struct bpf_lru {
+ union {
+ struct bpf_common_lru common_lru;
+ struct bpf_lru_list __percpu *percpu_lru;
+ };
+ del_from_htab_func del_from_htab;
+ void *del_arg;
+ unsigned int hash_offset;
+ unsigned int nr_scans;
+ bool percpu;
+};
+
+static inline void bpf_lru_node_set_ref(struct bpf_lru_node *node)
+{
+ /* ref is an approximation on access frequency. It does not
+ * have to be very accurate. Hence, no protection is used.
+ */
+ node->ref = 1;
+}
+
+int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset,
+ del_from_htab_func del_from_htab, void *delete_arg);
+void bpf_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset,
+ u32 elem_size, u32 nr_elems);
+void bpf_lru_destroy(struct bpf_lru *lru);
+struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash);
+void bpf_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node);
+void bpf_lru_promote(struct bpf_lru *lru, struct bpf_lru_node *node);
+
+#endif
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 570eeca..34debc1 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -15,6 +15,7 @@
#include <linux/filter.h>
#include <linux/vmalloc.h>
#include "percpu_freelist.h"
+#include "bpf_lru_list.h"
struct bucket {
struct hlist_head head;
@@ -25,7 +26,10 @@ struct bpf_htab {
struct bpf_map map;
struct bucket *buckets;
void *elems;
- struct pcpu_freelist freelist;
+ union {
+ struct pcpu_freelist freelist;
+ struct bpf_lru lru;
+ };
void __percpu *extra_elems;
atomic_t count; /* number of elements in this hashtable */
u32 n_buckets; /* number of hash buckets */
@@ -48,11 +52,26 @@ struct htab_elem {
union {
struct rcu_head rcu;
enum extra_elem_state state;
+ struct bpf_lru_node lru_node;
};
u32 hash;
char key[0] __aligned(8);
};
+static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node);
+
+static bool htab_is_lru(const struct bpf_htab *htab)
+{
+ return htab->map.map_type == BPF_MAP_TYPE_LRU_HASH ||
+ htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
+}
+
+static bool htab_is_percpu(const struct bpf_htab *htab)
+{
+ return htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
+}
+
static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size,
void __percpu *pptr)
{
@@ -73,7 +92,7 @@ static void htab_free_elems(struct bpf_htab *htab)
{
int i;
- if (htab->map.map_type != BPF_MAP_TYPE_PERCPU_HASH)
+ if (!htab_is_percpu(htab))
goto free_elems;
for (i = 0; i < htab->map.max_entries; i++) {
@@ -87,7 +106,22 @@ static void htab_free_elems(struct bpf_htab *htab)
vfree(htab->elems);
}
-static int prealloc_elems_and_freelist(struct bpf_htab *htab)
+static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
+ u32 hash)
+{
+ struct bpf_lru_node *node = bpf_lru_pop_free(&htab->lru, hash);
+ struct htab_elem *l;
+
+ if (node) {
+ l = container_of(node, struct htab_elem, lru_node);
+ memcpy(l->key, key, htab->map.key_size);
+ return l;
+ }
+
+ return NULL;
+}
+
+static int prealloc_init(struct bpf_htab *htab)
{
int err = -ENOMEM, i;
@@ -95,7 +129,7 @@ static int prealloc_elems_and_freelist(struct bpf_htab *htab)
if (!htab->elems)
return -ENOMEM;
- if (htab->map.map_type != BPF_MAP_TYPE_PERCPU_HASH)
+ if (!htab_is_percpu(htab))
goto skip_percpu_elems;
for (i = 0; i < htab->map.max_entries; i++) {
@@ -110,12 +144,27 @@ static int prealloc_elems_and_freelist(struct bpf_htab *htab)
}
skip_percpu_elems:
- err = pcpu_freelist_init(&htab->freelist);
+ if (htab_is_lru(htab))
+ err = bpf_lru_init(&htab->lru,
+ htab->map.map_flags & BPF_F_NO_COMMON_LRU,
+ offsetof(struct htab_elem, hash) -
+ offsetof(struct htab_elem, lru_node),
+ htab_lru_map_delete_node,
+ htab);
+ else
+ err = pcpu_freelist_init(&htab->freelist);
+
if (err)
goto free_elems;
- pcpu_freelist_populate(&htab->freelist, htab->elems, htab->elem_size,
- htab->map.max_entries);
+ if (htab_is_lru(htab))
+ bpf_lru_populate(&htab->lru, htab->elems,
+ offsetof(struct htab_elem, lru_node),
+ htab->elem_size, htab->map.max_entries);
+ else
+ pcpu_freelist_populate(&htab->freelist, htab->elems,
+ htab->elem_size, htab->map.max_entries);
+
return 0;
free_elems:
@@ -123,6 +172,16 @@ static int prealloc_elems_and_freelist(struct bpf_htab *htab)
return err;
}
+static void prealloc_destroy(struct bpf_htab *htab)
+{
+ htab_free_elems(htab);
+
+ if (htab_is_lru(htab))
+ bpf_lru_destroy(&htab->lru);
+ else
+ pcpu_freelist_destroy(&htab->freelist);
+}
+
static int alloc_extra_elems(struct bpf_htab *htab)
{
void __percpu *pptr;
@@ -143,15 +202,37 @@ static int alloc_extra_elems(struct bpf_htab *htab)
/* Called from syscall */
static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
{
- bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_HASH;
+ bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH);
+ bool lru = (attr->map_type == BPF_MAP_TYPE_LRU_HASH ||
+ attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH);
+ /* percpu_lru means each cpu has its own LRU list.
+ * it is different from BPF_MAP_TYPE_PERCPU_HASH where
+ * the map's value itself is percpu. percpu_lru has
+ * nothing to do with the map's value.
+ */
+ bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
+ bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
struct bpf_htab *htab;
int err, i;
u64 cost;
- if (attr->map_flags & ~BPF_F_NO_PREALLOC)
+ if (lru && !capable(CAP_SYS_ADMIN))
+ /* LRU implementation is much complicated than other
+ * maps. Hence, limit to CAP_SYS_ADMIN for now.
+ */
+ return ERR_PTR(-EPERM);
+
+ if (attr->map_flags & ~(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU))
/* reserved bits should not be used */
return ERR_PTR(-EINVAL);
+ if (!lru && percpu_lru)
+ return ERR_PTR(-EINVAL);
+
+ if (lru && !prealloc)
+ return ERR_PTR(-ENOTSUPP);
+
htab = kzalloc(sizeof(*htab), GFP_USER);
if (!htab)
return ERR_PTR(-ENOMEM);
@@ -171,6 +252,18 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
htab->map.value_size == 0)
goto free_htab;
+ if (percpu_lru) {
+ /* ensure each CPU's lru list has >=1 elements.
+ * since we are at it, make each lru list has the same
+ * number of elements.
+ */
+ htab->map.max_entries = roundup(attr->max_entries,
+ num_possible_cpus());
+ if (htab->map.max_entries < attr->max_entries)
+ htab->map.max_entries = rounddown(attr->max_entries,
+ num_possible_cpus());
+ }
+
/* hash table size must be power of 2 */
htab->n_buckets = roundup_pow_of_two(htab->map.max_entries);
@@ -241,14 +334,17 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
raw_spin_lock_init(&htab->buckets[i].lock);
}
- if (!percpu) {
+ if (!percpu && !lru) {
+ /* lru itself can remove the least used element, so
+ * there is no need for an extra elem during map_update.
+ */
err = alloc_extra_elems(htab);
if (err)
goto free_buckets;
}
- if (!(attr->map_flags & BPF_F_NO_PREALLOC)) {
- err = prealloc_elems_and_freelist(htab);
+ if (prealloc) {
+ err = prealloc_init(htab);
if (err)
goto free_extra_elems;
}
@@ -323,6 +419,46 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
return NULL;
}
+static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct htab_elem *l = __htab_map_lookup_elem(map, key);
+
+ if (l) {
+ bpf_lru_node_set_ref(&l->lru_node);
+ return l->key + round_up(map->key_size, 8);
+ }
+
+ return NULL;
+}
+
+/* It is called from the bpf_lru_list when the LRU needs to delete
+ * older elements from the htab.
+ */
+static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
+{
+ struct bpf_htab *htab = (struct bpf_htab *)arg;
+ struct htab_elem *l, *tgt_l;
+ struct hlist_head *head;
+ unsigned long flags;
+ struct bucket *b;
+
+ tgt_l = container_of(node, struct htab_elem, lru_node);
+ b = __select_bucket(htab, tgt_l->hash);
+ head = &b->head;
+
+ raw_spin_lock_irqsave(&b->lock, flags);
+
+ hlist_for_each_entry_rcu(l, head, hash_node)
+ if (l == tgt_l) {
+ hlist_del_rcu(&l->hash_node);
+ break;
+ }
+
+ raw_spin_unlock_irqrestore(&b->lock, flags);
+
+ return l == tgt_l;
+}
+
/* Called from syscall */
static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
@@ -420,6 +556,24 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
}
}
+static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr,
+ void *value, bool onallcpus)
+{
+ if (!onallcpus) {
+ /* copy true value_size bytes */
+ memcpy(this_cpu_ptr(pptr), value, htab->map.value_size);
+ } else {
+ u32 size = round_up(htab->map.value_size, 8);
+ int off = 0, cpu;
+
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(per_cpu_ptr(pptr, cpu),
+ value + off, size);
+ off += size;
+ }
+ }
+}
+
static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
void *value, u32 key_size, u32 hash,
bool percpu, bool onallcpus,
@@ -479,18 +633,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
}
}
- if (!onallcpus) {
- /* copy true value_size bytes */
- memcpy(this_cpu_ptr(pptr), value, htab->map.value_size);
- } else {
- int off = 0, cpu;
+ pcpu_copy_value(htab, pptr, value, onallcpus);
- for_each_possible_cpu(cpu) {
- bpf_long_memcpy(per_cpu_ptr(pptr, cpu),
- value + off, size);
- off += size;
- }
- }
if (!prealloc)
htab_elem_set_ptr(l_new, key_size, pptr);
} else {
@@ -571,6 +715,70 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
return ret;
}
+static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
+ u64 map_flags)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct htab_elem *l_new, *l_old = NULL;
+ struct hlist_head *head;
+ unsigned long flags;
+ struct bucket *b;
+ u32 key_size, hash;
+ int ret;
+
+ if (unlikely(map_flags > BPF_EXIST))
+ /* unknown flags */
+ return -EINVAL;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ key_size = map->key_size;
+
+ hash = htab_map_hash(key, key_size);
+
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ /* For LRU, we need to alloc before taking bucket's
+ * spinlock because getting free nodes from LRU may need
+ * to remove older elements from htab and this removal
+ * operation will need a bucket lock.
+ */
+ l_new = prealloc_lru_pop(htab, key, hash);
+ if (!l_new)
+ return -ENOMEM;
+ memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size);
+
+ /* bpf_map_update_elem() can be called in_irq() */
+ raw_spin_lock_irqsave(&b->lock, flags);
+
+ l_old = lookup_elem_raw(head, hash, key, key_size);
+
+ ret = check_flags(htab, l_old, map_flags);
+ if (ret)
+ goto err;
+
+ /* add new element to the head of the list, so that
+ * concurrent search will find it before old elem
+ */
+ hlist_add_head_rcu(&l_new->hash_node, head);
+ if (l_old) {
+ bpf_lru_node_set_ref(&l_new->lru_node);
+ hlist_del_rcu(&l_old->hash_node);
+ }
+ ret = 0;
+
+err:
+ raw_spin_unlock_irqrestore(&b->lock, flags);
+
+ if (ret)
+ bpf_lru_push_free(&htab->lru, &l_new->lru_node);
+ else if (l_old)
+ bpf_lru_push_free(&htab->lru, &l_old->lru_node);
+
+ return ret;
+}
+
static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
void *value, u64 map_flags,
bool onallcpus)
@@ -606,22 +814,9 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
goto err;
if (l_old) {
- void __percpu *pptr = htab_elem_get_ptr(l_old, key_size);
- u32 size = htab->map.value_size;
-
/* per-cpu hash map can update value in-place */
- if (!onallcpus) {
- memcpy(this_cpu_ptr(pptr), value, size);
- } else {
- int off = 0, cpu;
-
- size = round_up(size, 8);
- for_each_possible_cpu(cpu) {
- bpf_long_memcpy(per_cpu_ptr(pptr, cpu),
- value + off, size);
- off += size;
- }
- }
+ pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
+ value, onallcpus);
} else {
l_new = alloc_htab_elem(htab, key, value, key_size,
hash, true, onallcpus, false);
@@ -637,12 +832,84 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
return ret;
}
+static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags,
+ bool onallcpus)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct htab_elem *l_new = NULL, *l_old;
+ struct hlist_head *head;
+ unsigned long flags;
+ struct bucket *b;
+ u32 key_size, hash;
+ int ret;
+
+ if (unlikely(map_flags > BPF_EXIST))
+ /* unknown flags */
+ return -EINVAL;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ key_size = map->key_size;
+
+ hash = htab_map_hash(key, key_size);
+
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ /* For LRU, we need to alloc before taking bucket's
+ * spinlock because LRU's elem alloc may need
+ * to remove older elem from htab and this removal
+ * operation will need a bucket lock.
+ */
+ if (map_flags != BPF_EXIST) {
+ l_new = prealloc_lru_pop(htab, key, hash);
+ if (!l_new)
+ return -ENOMEM;
+ }
+
+ /* bpf_map_update_elem() can be called in_irq() */
+ raw_spin_lock_irqsave(&b->lock, flags);
+
+ l_old = lookup_elem_raw(head, hash, key, key_size);
+
+ ret = check_flags(htab, l_old, map_flags);
+ if (ret)
+ goto err;
+
+ if (l_old) {
+ bpf_lru_node_set_ref(&l_old->lru_node);
+
+ /* per-cpu hash map can update value in-place */
+ pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
+ value, onallcpus);
+ } else {
+ pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size),
+ value, onallcpus);
+ hlist_add_head_rcu(&l_new->hash_node, head);
+ l_new = NULL;
+ }
+ ret = 0;
+err:
+ raw_spin_unlock_irqrestore(&b->lock, flags);
+ if (l_new)
+ bpf_lru_push_free(&htab->lru, &l_new->lru_node);
+ return ret;
+}
+
static int htab_percpu_map_update_elem(struct bpf_map *map, void *key,
void *value, u64 map_flags)
{
return __htab_percpu_map_update_elem(map, key, value, map_flags, false);
}
+static int htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags)
+{
+ return __htab_lru_percpu_map_update_elem(map, key, value, map_flags,
+ false);
+}
+
/* Called from syscall or from eBPF program */
static int htab_map_delete_elem(struct bpf_map *map, void *key)
{
@@ -676,6 +943,39 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
return ret;
}
+static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct hlist_head *head;
+ struct bucket *b;
+ struct htab_elem *l;
+ unsigned long flags;
+ u32 hash, key_size;
+ int ret = -ENOENT;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ key_size = map->key_size;
+
+ hash = htab_map_hash(key, key_size);
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ raw_spin_lock_irqsave(&b->lock, flags);
+
+ l = lookup_elem_raw(head, hash, key, key_size);
+
+ if (l) {
+ hlist_del_rcu(&l->hash_node);
+ ret = 0;
+ }
+
+ raw_spin_unlock_irqrestore(&b->lock, flags);
+ if (l)
+ bpf_lru_push_free(&htab->lru, &l->lru_node);
+ return ret;
+}
+
static void delete_all_elements(struct bpf_htab *htab)
{
int i;
@@ -687,7 +987,8 @@ static void delete_all_elements(struct bpf_htab *htab)
hlist_for_each_entry_safe(l, n, head, hash_node) {
hlist_del_rcu(&l->hash_node);
- htab_elem_free(htab, l);
+ if (l->state != HTAB_EXTRA_ELEM_USED)
+ htab_elem_free(htab, l);
}
}
}
@@ -707,12 +1008,11 @@ static void htab_map_free(struct bpf_map *map)
* not have executed. Wait for them.
*/
rcu_barrier();
- if (htab->map.map_flags & BPF_F_NO_PREALLOC) {
+ if (htab->map.map_flags & BPF_F_NO_PREALLOC)
delete_all_elements(htab);
- } else {
- htab_free_elems(htab);
- pcpu_freelist_destroy(&htab->freelist);
- }
+ else
+ prealloc_destroy(htab);
+
free_percpu(htab->extra_elems);
kvfree(htab->buckets);
kfree(htab);
@@ -732,6 +1032,20 @@ static struct bpf_map_type_list htab_type __read_mostly = {
.type = BPF_MAP_TYPE_HASH,
};
+static const struct bpf_map_ops htab_lru_ops = {
+ .map_alloc = htab_map_alloc,
+ .map_free = htab_map_free,
+ .map_get_next_key = htab_map_get_next_key,
+ .map_lookup_elem = htab_lru_map_lookup_elem,
+ .map_update_elem = htab_lru_map_update_elem,
+ .map_delete_elem = htab_lru_map_delete_elem,
+};
+
+static struct bpf_map_type_list htab_lru_type __read_mostly = {
+ .ops = &htab_lru_ops,
+ .type = BPF_MAP_TYPE_LRU_HASH,
+};
+
/* Called from eBPF program */
static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key)
{
@@ -743,8 +1057,21 @@ static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key)
return NULL;
}
+static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct htab_elem *l = __htab_map_lookup_elem(map, key);
+
+ if (l) {
+ bpf_lru_node_set_ref(&l->lru_node);
+ return this_cpu_ptr(htab_elem_get_ptr(l, map->key_size));
+ }
+
+ return NULL;
+}
+
int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
struct htab_elem *l;
void __percpu *pptr;
int ret = -ENOENT;
@@ -760,6 +1087,8 @@ int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
l = __htab_map_lookup_elem(map, key);
if (!l)
goto out;
+ if (htab_is_lru(htab))
+ bpf_lru_node_set_ref(&l->lru_node);
pptr = htab_elem_get_ptr(l, map->key_size);
for_each_possible_cpu(cpu) {
bpf_long_memcpy(value + off,
@@ -775,10 +1104,16 @@ int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
int ret;
rcu_read_lock();
- ret = __htab_percpu_map_update_elem(map, key, value, map_flags, true);
+ if (htab_is_lru(htab))
+ ret = __htab_lru_percpu_map_update_elem(map, key, value,
+ map_flags, true);
+ else
+ ret = __htab_percpu_map_update_elem(map, key, value, map_flags,
+ true);
rcu_read_unlock();
return ret;
@@ -798,10 +1133,26 @@ static struct bpf_map_type_list htab_percpu_type __read_mostly = {
.type = BPF_MAP_TYPE_PERCPU_HASH,
};
+static const struct bpf_map_ops htab_lru_percpu_ops = {
+ .map_alloc = htab_map_alloc,
+ .map_free = htab_map_free,
+ .map_get_next_key = htab_map_get_next_key,
+ .map_lookup_elem = htab_lru_percpu_map_lookup_elem,
+ .map_update_elem = htab_lru_percpu_map_update_elem,
+ .map_delete_elem = htab_lru_map_delete_elem,
+};
+
+static struct bpf_map_type_list htab_lru_percpu_type __read_mostly = {
+ .ops = &htab_lru_percpu_ops,
+ .type = BPF_MAP_TYPE_LRU_PERCPU_HASH,
+};
+
static int __init register_htab_map(void)
{
bpf_register_map_type(&htab_type);
bpf_register_map_type(&htab_percpu_type);
+ bpf_register_map_type(&htab_lru_type);
+ bpf_register_map_type(&htab_lru_percpu_type);
return 0;
}
late_initcall(register_htab_map);
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 1ed8473..2565809 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -87,6 +87,7 @@ static struct inode *bpf_get_inode(struct super_block *sb,
switch (mode & S_IFMT) {
case S_IFDIR:
case S_IFREG:
+ case S_IFLNK:
break;
default:
return ERR_PTR(-EINVAL);
@@ -119,6 +120,16 @@ static int bpf_inode_type(const struct inode *inode, enum bpf_type *type)
return 0;
}
+static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode,
+ struct inode *dir)
+{
+ d_instantiate(dentry, inode);
+ dget(dentry);
+
+ dir->i_mtime = current_time(dir);
+ dir->i_ctime = dir->i_mtime;
+}
+
static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
struct inode *inode;
@@ -133,9 +144,7 @@ static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
inc_nlink(inode);
inc_nlink(dir);
- d_instantiate(dentry, inode);
- dget(dentry);
-
+ bpf_dentry_finalize(dentry, inode, dir);
return 0;
}
@@ -151,9 +160,7 @@ static int bpf_mkobj_ops(struct inode *dir, struct dentry *dentry,
inode->i_op = iops;
inode->i_private = dentry->d_fsdata;
- d_instantiate(dentry, inode);
- dget(dentry);
-
+ bpf_dentry_finalize(dentry, inode, dir);
return 0;
}
@@ -181,13 +188,37 @@ bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags)
{
if (strchr(dentry->d_name.name, '.'))
return ERR_PTR(-EPERM);
+
return simple_lookup(dir, dentry, flags);
}
+static int bpf_symlink(struct inode *dir, struct dentry *dentry,
+ const char *target)
+{
+ char *link = kstrdup(target, GFP_USER | __GFP_NOWARN);
+ struct inode *inode;
+
+ if (!link)
+ return -ENOMEM;
+
+ inode = bpf_get_inode(dir->i_sb, dir, S_IRWXUGO | S_IFLNK);
+ if (IS_ERR(inode)) {
+ kfree(link);
+ return PTR_ERR(inode);
+ }
+
+ inode->i_op = &simple_symlink_inode_operations;
+ inode->i_link = link;
+
+ bpf_dentry_finalize(dentry, inode, dir);
+ return 0;
+}
+
static const struct inode_operations bpf_dir_iops = {
.lookup = bpf_lookup,
.mknod = bpf_mkobj,
.mkdir = bpf_mkdir,
+ .symlink = bpf_symlink,
.rmdir = simple_rmdir,
.rename = simple_rename,
.link = simple_link,
@@ -324,6 +355,8 @@ static void bpf_evict_inode(struct inode *inode)
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
+ if (S_ISLNK(inode->i_mode))
+ kfree(inode->i_link);
if (!bpf_inode_type(inode, &type))
bpf_any_put(inode->i_private, type);
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 228f962..ce1b7de 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -17,6 +17,7 @@
#include <linux/license.h>
#include <linux/filter.h>
#include <linux/version.h>
+#include <linux/kernel.h>
DEFINE_PER_CPU(int, bpf_prog_active);
@@ -194,7 +195,7 @@ static int map_create(union bpf_attr *attr)
err = bpf_map_charge_memlock(map);
if (err)
- goto free_map;
+ goto free_map_nouncharge;
err = bpf_map_new_fd(map);
if (err < 0)
@@ -204,6 +205,8 @@ static int map_create(union bpf_attr *attr)
return err;
free_map:
+ bpf_map_uncharge_memlock(map);
+free_map_nouncharge:
map->ops->map_free(map);
return err;
}
@@ -252,12 +255,6 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd)
return map;
}
-/* helper to convert user pointers passed inside __aligned_u64 fields */
-static void __user *u64_to_ptr(__u64 val)
-{
- return (void __user *) (unsigned long) val;
-}
-
int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
{
return -ENOTSUPP;
@@ -268,8 +265,8 @@ int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
static int map_lookup_elem(union bpf_attr *attr)
{
- void __user *ukey = u64_to_ptr(attr->key);
- void __user *uvalue = u64_to_ptr(attr->value);
+ void __user *ukey = u64_to_user_ptr(attr->key);
+ void __user *uvalue = u64_to_user_ptr(attr->value);
int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *value, *ptr;
@@ -295,6 +292,7 @@ static int map_lookup_elem(union bpf_attr *attr)
goto free_key;
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
value_size = round_up(map->value_size, 8) * num_possible_cpus();
else
@@ -305,7 +303,8 @@ static int map_lookup_elem(union bpf_attr *attr)
if (!value)
goto free_key;
- if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) {
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
err = bpf_percpu_hash_copy(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
err = bpf_percpu_array_copy(map, key, value);
@@ -342,8 +341,8 @@ static int map_lookup_elem(union bpf_attr *attr)
static int map_update_elem(union bpf_attr *attr)
{
- void __user *ukey = u64_to_ptr(attr->key);
- void __user *uvalue = u64_to_ptr(attr->value);
+ void __user *ukey = u64_to_user_ptr(attr->key);
+ void __user *uvalue = u64_to_user_ptr(attr->value);
int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *value;
@@ -369,6 +368,7 @@ static int map_update_elem(union bpf_attr *attr)
goto free_key;
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
value_size = round_up(map->value_size, 8) * num_possible_cpus();
else
@@ -388,7 +388,8 @@ static int map_update_elem(union bpf_attr *attr)
*/
preempt_disable();
__this_cpu_inc(bpf_prog_active);
- if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) {
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
err = bpf_percpu_hash_update(map, key, value, attr->flags);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
err = bpf_percpu_array_update(map, key, value, attr->flags);
@@ -420,7 +421,7 @@ static int map_update_elem(union bpf_attr *attr)
static int map_delete_elem(union bpf_attr *attr)
{
- void __user *ukey = u64_to_ptr(attr->key);
+ void __user *ukey = u64_to_user_ptr(attr->key);
int ufd = attr->map_fd;
struct bpf_map *map;
struct fd f;
@@ -464,8 +465,8 @@ static int map_delete_elem(union bpf_attr *attr)
static int map_get_next_key(union bpf_attr *attr)
{
- void __user *ukey = u64_to_ptr(attr->key);
- void __user *unext_key = u64_to_ptr(attr->next_key);
+ void __user *ukey = u64_to_user_ptr(attr->key);
+ void __user *unext_key = u64_to_user_ptr(attr->next_key);
int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *next_key;
@@ -680,6 +681,17 @@ struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i)
}
EXPORT_SYMBOL_GPL(bpf_prog_add);
+void bpf_prog_sub(struct bpf_prog *prog, int i)
+{
+ /* Only to be used for undoing previous bpf_prog_add() in some
+ * error path. We still know that another entity in our call
+ * path holds a reference to the program, thus atomic_sub() can
+ * be safely used in such cases!
+ */
+ WARN_ON(atomic_sub_return(i, &prog->aux->refcnt) == 0);
+}
+EXPORT_SYMBOL_GPL(bpf_prog_sub);
+
struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
{
return bpf_prog_add(prog, 1);
@@ -730,7 +742,7 @@ static int bpf_prog_load(union bpf_attr *attr)
return -EINVAL;
/* copy eBPF program license from user space */
- if (strncpy_from_user(license, u64_to_ptr(attr->license),
+ if (strncpy_from_user(license, u64_to_user_ptr(attr->license),
sizeof(license) - 1) < 0)
return -EFAULT;
license[sizeof(license) - 1] = 0;
@@ -760,7 +772,7 @@ static int bpf_prog_load(union bpf_attr *attr)
prog->len = attr->insn_cnt;
err = -EFAULT;
- if (copy_from_user(prog->insns, u64_to_ptr(attr->insns),
+ if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns),
prog->len * sizeof(struct bpf_insn)) != 0)
goto free_prog;
@@ -811,7 +823,7 @@ static int bpf_obj_pin(const union bpf_attr *attr)
if (CHECK_ATTR(BPF_OBJ))
return -EINVAL;
- return bpf_obj_pin_user(attr->bpf_fd, u64_to_ptr(attr->pathname));
+ return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname));
}
static int bpf_obj_get(const union bpf_attr *attr)
@@ -819,7 +831,7 @@ static int bpf_obj_get(const union bpf_attr *attr)
if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0)
return -EINVAL;
- return bpf_obj_get_user(u64_to_ptr(attr->pathname));
+ return bpf_obj_get_user(u64_to_user_ptr(attr->pathname));
}
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9002575..89f787c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1499,7 +1499,6 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
{
struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg;
u64 min_val = BPF_REGISTER_MIN_RANGE, max_val = BPF_REGISTER_MAX_RANGE;
- bool min_set = false, max_set = false;
u8 opcode = BPF_OP(insn->code);
dst_reg = ®s[insn->dst_reg];
@@ -1522,7 +1521,6 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
} else if (insn->imm < BPF_REGISTER_MAX_RANGE &&
(s64)insn->imm > BPF_REGISTER_MIN_RANGE) {
min_val = max_val = insn->imm;
- min_set = max_set = true;
}
/* We don't know anything about what was done to this register, mark it
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 4406615..85bc9be 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -64,6 +64,9 @@
#include <linux/file.h>
#include <net/sock.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/cgroup.h>
+
/*
* pidlists linger the following amount before being destroyed. The goal
* is avoiding frequent destruction in the middle of consecutive read calls
@@ -1176,6 +1179,8 @@ static void cgroup_destroy_root(struct cgroup_root *root)
struct cgroup *cgrp = &root->cgrp;
struct cgrp_cset_link *link, *tmp_link;
+ trace_cgroup_destroy_root(root);
+
cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
BUG_ON(atomic_read(&root->nr_cgrps));
@@ -1874,6 +1879,9 @@ static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
strcpy(root->release_agent_path, opts.release_agent);
spin_unlock(&release_agent_path_lock);
}
+
+ trace_cgroup_remount(root);
+
out_unlock:
kfree(opts.release_agent);
kfree(opts.name);
@@ -2031,6 +2039,8 @@ static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
if (ret)
goto destroy_root;
+ trace_cgroup_setup_root(root);
+
/*
* There must be no failure case after here, since rebinding takes
* care of subsystems' refcounts, which are explicitly dropped in
@@ -2315,22 +2325,18 @@ static struct file_system_type cgroup2_fs_type = {
.fs_flags = FS_USERNS_MOUNT,
};
-static char *cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen,
- struct cgroup_namespace *ns)
+static int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen,
+ struct cgroup_namespace *ns)
{
struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root);
- int ret;
- ret = kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen);
- if (ret < 0 || ret >= buflen)
- return NULL;
- return buf;
+ return kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen);
}
-char *cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
- struct cgroup_namespace *ns)
+int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
+ struct cgroup_namespace *ns)
{
- char *ret;
+ int ret;
mutex_lock(&cgroup_mutex);
spin_lock_irq(&css_set_lock);
@@ -2357,12 +2363,12 @@ EXPORT_SYMBOL_GPL(cgroup_path_ns);
*
* Return value is the same as kernfs_path().
*/
-char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
+int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
{
struct cgroup_root *root;
struct cgroup *cgrp;
int hierarchy_id = 1;
- char *path = NULL;
+ int ret;
mutex_lock(&cgroup_mutex);
spin_lock_irq(&css_set_lock);
@@ -2371,16 +2377,15 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
if (root) {
cgrp = task_cgroup_from_root(task, root);
- path = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns);
+ ret = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns);
} else {
/* if no hierarchy exists, everyone is in "/" */
- if (strlcpy(buf, "/", buflen) < buflen)
- path = buf;
+ ret = strlcpy(buf, "/", buflen);
}
spin_unlock_irq(&css_set_lock);
mutex_unlock(&cgroup_mutex);
- return path;
+ return ret;
}
EXPORT_SYMBOL_GPL(task_cgroup_path);
@@ -2830,6 +2835,10 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
ret = cgroup_migrate(leader, threadgroup, dst_cgrp->root);
cgroup_migrate_finish(&preloaded_csets);
+
+ if (!ret)
+ trace_cgroup_attach_task(dst_cgrp, leader, threadgroup);
+
return ret;
}
@@ -3611,6 +3620,8 @@ static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
mutex_lock(&cgroup_mutex);
ret = kernfs_rename(kn, new_parent, new_name_str);
+ if (!ret)
+ trace_cgroup_rename(cgrp);
mutex_unlock(&cgroup_mutex);
@@ -4381,6 +4392,8 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
if (task) {
ret = cgroup_migrate(task, false, to->root);
+ if (!ret)
+ trace_cgroup_transfer_tasks(to, task, false);
put_task_struct(task);
}
} while (task && !ret);
@@ -5046,6 +5059,8 @@ static void css_release_work_fn(struct work_struct *work)
ss->css_released(css);
} else {
/* cgroup release path */
+ trace_cgroup_release(cgrp);
+
cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
cgrp->id = -1;
@@ -5332,6 +5347,8 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
if (ret)
goto out_destroy;
+ trace_cgroup_mkdir(cgrp);
+
/* let's create and online css's */
kernfs_activate(kn);
@@ -5507,6 +5524,9 @@ static int cgroup_rmdir(struct kernfs_node *kn)
ret = cgroup_destroy_locked(cgrp);
+ if (!ret)
+ trace_cgroup_rmdir(cgrp);
+
cgroup_kn_unlock(kn);
return ret;
}
@@ -5743,7 +5763,7 @@ core_initcall(cgroup_wq_init);
int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *tsk)
{
- char *buf, *path;
+ char *buf;
int retval;
struct cgroup_root *root;
@@ -5786,17 +5806,17 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
* " (deleted)" is appended to the cgroup path.
*/
if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) {
- path = cgroup_path_ns_locked(cgrp, buf, PATH_MAX,
+ retval = cgroup_path_ns_locked(cgrp, buf, PATH_MAX,
current->nsproxy->cgroup_ns);
- if (!path) {
+ if (retval >= PATH_MAX)
retval = -ENAMETOOLONG;
+ if (retval < 0)
goto out_unlock;
- }
- } else {
- path = "/";
- }
- seq_puts(m, path);
+ seq_puts(m, buf);
+ } else {
+ seq_puts(m, "/");
+ }
if (cgroup_on_dfl(cgrp) && cgroup_is_dead(cgrp))
seq_puts(m, " (deleted)\n");
@@ -6062,8 +6082,9 @@ static void cgroup_release_agent(struct work_struct *work)
{
struct cgroup *cgrp =
container_of(work, struct cgroup, release_agent_work);
- char *pathbuf = NULL, *agentbuf = NULL, *path;
+ char *pathbuf = NULL, *agentbuf = NULL;
char *argv[3], *envp[3];
+ int ret;
mutex_lock(&cgroup_mutex);
@@ -6073,13 +6094,13 @@ static void cgroup_release_agent(struct work_struct *work)
goto out;
spin_lock_irq(&css_set_lock);
- path = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns);
+ ret = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns);
spin_unlock_irq(&css_set_lock);
- if (!path)
+ if (ret < 0 || ret >= PATH_MAX)
goto out;
argv[0] = agentbuf;
- argv[1] = path;
+ argv[1] = pathbuf;
argv[2] = NULL;
/* minimal command environment */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 5df20d6..29de1a9 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -228,7 +228,7 @@ static struct {
.wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq),
.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
#ifdef CONFIG_DEBUG_LOCK_ALLOC
- .dep_map = {.name = "cpu_hotplug.lock" },
+ .dep_map = STATIC_LOCKDEP_MAP_INIT("cpu_hotplug.dep_map", &cpu_hotplug.dep_map),
#endif
};
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 2b4c20a..29f815d 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2715,7 +2715,7 @@ void __cpuset_memory_pressure_bump(void)
int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *tsk)
{
- char *buf, *p;
+ char *buf;
struct cgroup_subsys_state *css;
int retval;
@@ -2724,14 +2724,15 @@ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
if (!buf)
goto out;
- retval = -ENAMETOOLONG;
css = task_get_css(tsk, cpuset_cgrp_id);
- p = cgroup_path_ns(css->cgroup, buf, PATH_MAX,
- current->nsproxy->cgroup_ns);
+ retval = cgroup_path_ns(css->cgroup, buf, PATH_MAX,
+ current->nsproxy->cgroup_ns);
css_put(css);
- if (!p)
+ if (retval >= PATH_MAX)
+ retval = -ENAMETOOLONG;
+ if (retval < 0)
goto out_free;
- seq_puts(m, p);
+ seq_puts(m, buf);
seq_putc(m, '\n');
retval = 0;
out_free:
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c6e47e9..0e29213 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1960,6 +1960,12 @@ void perf_event_disable(struct perf_event *event)
}
EXPORT_SYMBOL_GPL(perf_event_disable);
+void perf_event_disable_inatomic(struct perf_event *event)
+{
+ event->pending_disable = 1;
+ irq_work_queue(&event->pending);
+}
+
static void perf_set_shadow_time(struct perf_event *event,
struct perf_event_context *ctx,
u64 tstamp)
@@ -7075,8 +7081,8 @@ static int __perf_event_overflow(struct perf_event *event,
if (events && atomic_dec_and_test(&event->event_limit)) {
ret = 1;
event->pending_kill = POLL_HUP;
- event->pending_disable = 1;
- irq_work_queue(&event->pending);
+
+ perf_event_disable_inatomic(event);
}
READ_ONCE(event->overflow_handler)(event, data, regs);
@@ -8855,7 +8861,10 @@ EXPORT_SYMBOL_GPL(perf_pmu_register);
void perf_pmu_unregister(struct pmu *pmu)
{
+ int remove_device;
+
mutex_lock(&pmus_lock);
+ remove_device = pmu_bus_running;
list_del_rcu(&pmu->entry);
mutex_unlock(&pmus_lock);
@@ -8869,10 +8878,12 @@ void perf_pmu_unregister(struct pmu *pmu)
free_percpu(pmu->pmu_disable_count);
if (pmu->type >= PERF_TYPE_MAX)
idr_remove(&pmu_idr, pmu->type);
- if (pmu->nr_addr_filters)
- device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
- device_del(pmu->dev);
- put_device(pmu->dev);
+ if (remove_device) {
+ if (pmu->nr_addr_filters)
+ device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
+ device_del(pmu->dev);
+ put_device(pmu->dev);
+ }
free_pmu_context(pmu);
}
EXPORT_SYMBOL_GPL(perf_pmu_unregister);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index d4129bb..f9ec9ad 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -300,7 +300,8 @@ int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr,
retry:
/* Read the page with vaddr into memory */
- ret = get_user_pages_remote(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma);
+ ret = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &old_page,
+ &vma);
if (ret <= 0)
return ret;
@@ -1710,7 +1711,8 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
* but we treat this as a 'remote' access since it is
* essentially a kernel access to the memory.
*/
- result = get_user_pages_remote(NULL, mm, vaddr, 1, 0, 1, &page, NULL);
+ result = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &page,
+ NULL);
if (result < 0)
return result;
diff --git a/kernel/fork.c b/kernel/fork.c
index 6d42242..997ac1d5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -315,6 +315,9 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
static void release_task_stack(struct task_struct *tsk)
{
+ if (WARN_ON(tsk->state != TASK_DEAD))
+ return; /* Better to leak the stack than to free prematurely */
+
account_kernel_stack(tsk, -1);
arch_release_thread_stack(tsk->stack);
free_thread_stack(tsk);
@@ -547,7 +550,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
}
#ifdef CONFIG_MMU
-static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
+static __latent_entropy int dup_mmap(struct mm_struct *mm,
+ struct mm_struct *oldmm)
{
struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
struct rb_node **rb_link, *rb_parent;
@@ -1441,7 +1445,8 @@ init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
* parts of the process environment (as per the clone
* flags). The actual kick-off is left to the caller.
*/
-static struct task_struct *copy_process(unsigned long clone_flags,
+static __latent_entropy struct task_struct *copy_process(
+ unsigned long clone_flags,
unsigned long stack_start,
unsigned long stack_size,
int __user *child_tidptr,
@@ -1860,6 +1865,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
atomic_dec(&p->cred->user->processes);
exit_creds(p);
bad_fork_free:
+ p->state = TASK_DEAD;
put_task_stack(p);
free_task(p);
fork_out:
@@ -1926,6 +1932,7 @@ long _do_fork(unsigned long clone_flags,
p = copy_process(clone_flags, stack_start, stack_size,
child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
+ add_latent_entropy();
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 0c5f1a5..6b66959 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -721,6 +721,7 @@ int irq_set_parent(int irq, int parent_irq)
irq_put_desc_unlock(desc, flags);
return 0;
}
+EXPORT_SYMBOL_GPL(irq_set_parent);
#endif
/*
@@ -1340,12 +1341,12 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
} else if (new->flags & IRQF_TRIGGER_MASK) {
unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK;
- unsigned int omsk = irq_settings_get_trigger_mask(desc);
+ unsigned int omsk = irqd_get_trigger_type(&desc->irq_data);
if (nmsk != omsk)
/* hope the handler works with current trigger mode */
pr_warn("irq %d uses trigger mode %u; requested %u\n",
- irq, nmsk, omsk);
+ irq, omsk, nmsk);
}
*old_ptr = new;
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 8d44b3f..30e6d05 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -53,8 +53,15 @@ void notrace __sanitizer_cov_trace_pc(void)
/*
* We are interested in code coverage as a function of a syscall inputs,
* so we ignore code executed in interrupts.
+ * The checks for whether we are in an interrupt are open-coded, because
+ * 1. We can't use in_interrupt() here, since it also returns true
+ * when we are inside local_bh_disable() section.
+ * 2. We don't want to use (in_irq() | in_serving_softirq() | in_nmi()),
+ * since that leads to slower generated code (three separate tests,
+ * one for each of the flags).
*/
- if (!t || in_interrupt())
+ if (!t || (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET
+ | NMI_MASK)))
return;
mode = READ_ONCE(t->kcov_mode);
if (mode == KCOV_MODE_TRACE) {
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 1e7f5da..6ccb08f 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -498,9 +498,9 @@ static int enter_state(suspend_state_t state)
#ifndef CONFIG_SUSPEND_SKIP_SYNC
trace_suspend_resume(TPS("sync_filesystems"), 0, true);
- printk(KERN_INFO "PM: Syncing filesystems ... ");
+ pr_info("PM: Syncing filesystems ... ");
sys_sync();
- printk("done.\n");
+ pr_cont("done.\n");
trace_suspend_resume(TPS("sync_filesystems"), 0, false);
#endif
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index 084452e..bdff5ed 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -203,8 +203,10 @@ static int __init test_suspend(void)
/* RTCs have initialized by now too ... can we use one? */
dev = class_find_device(rtc_class, NULL, NULL, has_wakealarm);
- if (dev)
+ if (dev) {
rtc = rtc_class_open(dev_name(dev));
+ put_device(dev);
+ }
if (!rtc) {
printk(warn_no_rtc);
return 0;
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index d5e3973..f7a55e9 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -253,17 +253,6 @@ static int preferred_console = -1;
int console_set_on_cmdline;
EXPORT_SYMBOL(console_set_on_cmdline);
-#ifdef CONFIG_OF
-static bool of_specified_console;
-
-void console_set_by_of(void)
-{
- of_specified_console = true;
-}
-#else
-# define of_specified_console false
-#endif
-
/* Flag: console code may call schedule() */
static int console_may_schedule;
@@ -794,8 +783,6 @@ static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from)
return ret;
}
-static void cont_flush(void);
-
static ssize_t devkmsg_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
@@ -811,7 +798,6 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
if (ret)
return ret;
raw_spin_lock_irq(&logbuf_lock);
- cont_flush();
while (user->seq == log_next_seq) {
if (file->f_flags & O_NONBLOCK) {
ret = -EAGAIN;
@@ -874,7 +860,6 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
return -ESPIPE;
raw_spin_lock_irq(&logbuf_lock);
- cont_flush();
switch (whence) {
case SEEK_SET:
/* the first record */
@@ -913,7 +898,6 @@ static unsigned int devkmsg_poll(struct file *file, poll_table *wait)
poll_wait(file, &log_wait, wait);
raw_spin_lock_irq(&logbuf_lock);
- cont_flush();
if (user->seq < log_next_seq) {
/* return error when data has vanished underneath us */
if (user->seq < log_first_seq)
@@ -1300,7 +1284,6 @@ static int syslog_print(char __user *buf, int size)
size_t skip;
raw_spin_lock_irq(&logbuf_lock);
- cont_flush();
if (syslog_seq < log_first_seq) {
/* messages are gone, move to first one */
syslog_seq = log_first_seq;
@@ -1360,7 +1343,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
return -ENOMEM;
raw_spin_lock_irq(&logbuf_lock);
- cont_flush();
if (buf) {
u64 next_seq;
u64 seq;
@@ -1522,7 +1504,6 @@ int do_syslog(int type, char __user *buf, int len, int source)
/* Number of chars in the log buffer */
case SYSLOG_ACTION_SIZE_UNREAD:
raw_spin_lock_irq(&logbuf_lock);
- cont_flush();
if (syslog_seq < log_first_seq) {
/* messages are gone, move to first one */
syslog_seq = log_first_seq;
@@ -1769,6 +1750,10 @@ static size_t log_output(int facility, int level, enum log_flags lflags, const c
cont_flush();
}
+ /* Skip empty continuation lines that couldn't be added - they just flush */
+ if (!text_len && (lflags & LOG_CONT))
+ return 0;
+
/* If it doesn't end in a newline, try to buffer the current line */
if (!(lflags & LOG_NEWLINE)) {
if (cont_add(facility, level, lflags, text, text_len))
@@ -2653,7 +2638,7 @@ void register_console(struct console *newcon)
* didn't select a console we take the first one
* that registers here.
*/
- if (preferred_console < 0 && !of_specified_console) {
+ if (preferred_console < 0) {
if (newcon->index < 0)
newcon->index = 0;
if (newcon->setup == NULL ||
@@ -3035,7 +3020,6 @@ void kmsg_dump(enum kmsg_dump_reason reason)
dumper->active = true;
raw_spin_lock_irqsave(&logbuf_lock, flags);
- cont_flush();
dumper->cur_seq = clear_seq;
dumper->cur_idx = clear_idx;
dumper->next_seq = log_next_seq;
@@ -3126,7 +3110,6 @@ bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog,
bool ret;
raw_spin_lock_irqsave(&logbuf_lock, flags);
- cont_flush();
ret = kmsg_dump_get_line_nolock(dumper, syslog, line, size, len);
raw_spin_unlock_irqrestore(&logbuf_lock, flags);
@@ -3169,7 +3152,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog,
goto out;
raw_spin_lock_irqsave(&logbuf_lock, flags);
- cont_flush();
if (dumper->cur_seq < log_first_seq) {
/* messages are gone, move to first available one */
dumper->cur_seq = log_first_seq;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 2a99027..e6474f7 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -537,7 +537,7 @@ int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst
int this_len, retval;
this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
- retval = access_process_vm(tsk, src, buf, this_len, 0);
+ retval = access_process_vm(tsk, src, buf, this_len, FOLL_FORCE);
if (!retval) {
if (copied)
break;
@@ -564,7 +564,8 @@ int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long ds
this_len = (len > sizeof(buf)) ? sizeof(buf) : len;
if (copy_from_user(buf, src, this_len))
return -EFAULT;
- retval = access_process_vm(tsk, dst, buf, this_len, 1);
+ retval = access_process_vm(tsk, dst, buf, this_len,
+ FOLL_FORCE | FOLL_WRITE);
if (!retval) {
if (copied)
break;
@@ -1127,7 +1128,7 @@ int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr,
unsigned long tmp;
int copied;
- copied = access_process_vm(tsk, addr, &tmp, sizeof(tmp), 0);
+ copied = access_process_vm(tsk, addr, &tmp, sizeof(tmp), FOLL_FORCE);
if (copied != sizeof(tmp))
return -EIO;
return put_user(tmp, (unsigned long __user *)data);
@@ -1138,7 +1139,8 @@ int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr,
{
int copied;
- copied = access_process_vm(tsk, addr, &data, sizeof(data), 1);
+ copied = access_process_vm(tsk, addr, &data, sizeof(data),
+ FOLL_FORCE | FOLL_WRITE);
return (copied == sizeof(data)) ? 0 : -EIO;
}
@@ -1155,7 +1157,8 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request,
switch (request) {
case PTRACE_PEEKTEXT:
case PTRACE_PEEKDATA:
- ret = access_process_vm(child, addr, &word, sizeof(word), 0);
+ ret = access_process_vm(child, addr, &word, sizeof(word),
+ FOLL_FORCE);
if (ret != sizeof(word))
ret = -EIO;
else
@@ -1164,7 +1167,8 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request,
case PTRACE_POKETEXT:
case PTRACE_POKEDATA:
- ret = access_process_vm(child, addr, &data, sizeof(data), 1);
+ ret = access_process_vm(child, addr, &data, sizeof(data),
+ FOLL_FORCE | FOLL_WRITE);
ret = (ret != sizeof(data) ? -EIO : 0);
break;
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 944b1b4..1898559 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -170,7 +170,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
false));
}
-static void rcu_process_callbacks(struct softirq_action *unused)
+static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused)
{
__rcu_process_callbacks(&rcu_sched_ctrlblk);
__rcu_process_callbacks(&rcu_bh_ctrlblk);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 7e2e038..69a5611 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3013,7 +3013,7 @@ __rcu_process_callbacks(struct rcu_state *rsp)
/*
* Do RCU core processing for the current CPU.
*/
-static void rcu_process_callbacks(struct softirq_action *unused)
+static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused)
{
struct rcu_state *rsp;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 94732d1..154fd68 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5192,21 +5192,14 @@ void sched_show_task(struct task_struct *p)
int ppid;
unsigned long state = p->state;
+ if (!try_get_task_stack(p))
+ return;
if (state)
state = __ffs(state) + 1;
printk(KERN_INFO "%-15.15s %c", p->comm,
state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
-#if BITS_PER_LONG == 32
- if (state == TASK_RUNNING)
- printk(KERN_CONT " running ");
- else
- printk(KERN_CONT " %08lx ", thread_saved_pc(p));
-#else
if (state == TASK_RUNNING)
printk(KERN_CONT " running task ");
- else
- printk(KERN_CONT " %016lx ", thread_saved_pc(p));
-#endif
#ifdef CONFIG_DEBUG_STACK_USAGE
free = stack_not_used(p);
#endif
@@ -5221,6 +5214,7 @@ void sched_show_task(struct task_struct *p)
print_worker_info(KERN_INFO, p);
show_stack(p, NULL);
+ put_task_stack(p);
}
void show_state_filter(unsigned long state_filter)
@@ -7515,11 +7509,27 @@ static struct kmem_cache *task_group_cache __read_mostly;
DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
DECLARE_PER_CPU(cpumask_var_t, select_idle_mask);
+#define WAIT_TABLE_BITS 8
+#define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS)
+static wait_queue_head_t bit_wait_table[WAIT_TABLE_SIZE] __cacheline_aligned;
+
+wait_queue_head_t *bit_waitqueue(void *word, int bit)
+{
+ const int shift = BITS_PER_LONG == 32 ? 5 : 6;
+ unsigned long val = (unsigned long)word << shift | bit;
+
+ return bit_wait_table + hash_long(val, WAIT_TABLE_BITS);
+}
+EXPORT_SYMBOL(bit_waitqueue);
+
void __init sched_init(void)
{
int i, j;
unsigned long alloc_size = 0, ptr;
+ for (i = 0; i < WAIT_TABLE_SIZE; i++)
+ init_waitqueue_head(bit_wait_table + i);
+
#ifdef CONFIG_FAIR_GROUP_SCHED
alloc_size += 2 * nr_cpu_ids * sizeof(void **);
#endif
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 1393588..fa178b6 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -415,7 +415,8 @@ static char *task_group_path(struct task_group *tg)
if (autogroup_path(tg, group_path, PATH_MAX))
return group_path;
- return cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
+ cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
+ return group_path;
}
#endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 502e95a..c242944 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -690,7 +690,14 @@ void init_entity_runnable_average(struct sched_entity *se)
* will definitely be update (after enqueue).
*/
sa->period_contrib = 1023;
- sa->load_avg = scale_load_down(se->load.weight);
+ /*
+ * Tasks are intialized with full load to be seen as heavy tasks until
+ * they get a chance to stabilize to their real load level.
+ * Group entities are intialized with zero load to reflect the fact that
+ * nothing has been attached to the task group yet.
+ */
+ if (entity_is_task(se))
+ sa->load_avg = scale_load_down(se->load.weight);
sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
/*
* At this point, util_avg won't be used in select_task_rq_fair anyway
@@ -5471,13 +5478,18 @@ static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd
*/
static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
{
- struct sched_domain *this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
- u64 avg_idle = this_rq()->avg_idle;
- u64 avg_cost = this_sd->avg_scan_cost;
+ struct sched_domain *this_sd;
+ u64 avg_cost, avg_idle = this_rq()->avg_idle;
u64 time, cost;
s64 delta;
int cpu, wrap;
+ this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
+ if (!this_sd)
+ return -1;
+
+ avg_cost = this_sd->avg_scan_cost;
+
/*
* Due to large variance we need a large fuzz factor; hackbench in
* particularly is sensitive here.
@@ -8522,7 +8534,7 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { }
* run_rebalance_domains is triggered when needed from the scheduler tick.
* Also triggered for nohz idle balancing (with nohz_balancing_kick set).
*/
-static void run_rebalance_domains(struct softirq_action *h)
+static __latent_entropy void run_rebalance_domains(struct softirq_action *h)
{
struct rq *this_rq = this_rq();
enum cpu_idle_type idle = this_rq->idle_balance ?
@@ -8827,7 +8839,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
struct sched_entity *se;
struct cfs_rq *cfs_rq;
- struct rq *rq;
int i;
tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
@@ -8842,8 +8853,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
init_cfs_bandwidth(tg_cfs_bandwidth(tg));
for_each_possible_cpu(i) {
- rq = cpu_rq(i);
-
cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
GFP_KERNEL, cpu_to_node(i));
if (!cfs_rq)
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 4f70535..9453efe 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -480,16 +480,6 @@ void wake_up_bit(void *word, int bit)
}
EXPORT_SYMBOL(wake_up_bit);
-wait_queue_head_t *bit_waitqueue(void *word, int bit)
-{
- const int shift = BITS_PER_LONG == 32 ? 5 : 6;
- const struct zone *zone = page_zone(virt_to_page(word));
- unsigned long val = (unsigned long)word << shift | bit;
-
- return &zone->wait_table[hash_long(val, zone->wait_table_bits)];
-}
-EXPORT_SYMBOL(bit_waitqueue);
-
/*
* Manipulate the atomic_t address to produce a better bit waitqueue table hash
* index (we're keying off bit -1, but that would produce a horrible hash
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 6676264..744fa61 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -58,7 +58,7 @@ static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp
DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
const char * const softirq_to_name[NR_SOFTIRQS] = {
- "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL",
+ "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "IRQ_POLL",
"TASKLET", "SCHED", "HRTIMER", "RCU"
};
@@ -496,7 +496,7 @@ void __tasklet_hi_schedule_first(struct tasklet_struct *t)
}
EXPORT_SYMBOL(__tasklet_hi_schedule_first);
-static void tasklet_action(struct softirq_action *a)
+static __latent_entropy void tasklet_action(struct softirq_action *a)
{
struct tasklet_struct *list;
@@ -532,7 +532,7 @@ static void tasklet_action(struct softirq_action *a)
}
}
-static void tasklet_hi_action(struct softirq_action *a)
+static __latent_entropy void tasklet_hi_action(struct softirq_action *a)
{
struct tasklet_struct *list;
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 9b7f838..8a5e442 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -49,7 +49,11 @@ static const struct nla_policy taskstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1
[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK] = { .type = NLA_STRING },
[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK] = { .type = NLA_STRING },};
-static const struct nla_policy cgroupstats_cmd_get_policy[CGROUPSTATS_CMD_ATTR_MAX+1] = {
+/*
+ * We have to use TASKSTATS_CMD_ATTR_MAX here, it is the maxattr in the family.
+ * Make sure they are always aligned.
+ */
+static const struct nla_policy cgroupstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1] = {
[CGROUPSTATS_CMD_ATTR_FD] = { .type = NLA_U32 },
};
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index c3aad68..12dd190 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -542,7 +542,6 @@ static int alarm_clock_get(clockid_t which_clock, struct timespec *tp)
static int alarm_timer_create(struct k_itimer *new_timer)
{
enum alarmtimer_type type;
- struct alarm_base *base;
if (!alarmtimer_get_rtcdev())
return -ENOTSUPP;
@@ -551,7 +550,6 @@ static int alarm_timer_create(struct k_itimer *new_timer)
return -EPERM;
type = clock2alarm(new_timer->it_clock);
- base = &alarm_bases[type];
alarm_init(&new_timer->it.alarm.alarmtimer, type, alarm_handle_timer);
return 0;
}
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 32bf6f7..c611c47 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -878,7 +878,7 @@ static inline struct timer_base *get_timer_base(u32 tflags)
#ifdef CONFIG_NO_HZ_COMMON
static inline struct timer_base *
-__get_target_base(struct timer_base *base, unsigned tflags)
+get_target_base(struct timer_base *base, unsigned tflags)
{
#ifdef CONFIG_SMP
if ((tflags & TIMER_PINNED) || !base->migration_enabled)
@@ -891,25 +891,27 @@ __get_target_base(struct timer_base *base, unsigned tflags)
static inline void forward_timer_base(struct timer_base *base)
{
+ unsigned long jnow = READ_ONCE(jiffies);
+
/*
* We only forward the base when it's idle and we have a delta between
* base clock and jiffies.
*/
- if (!base->is_idle || (long) (jiffies - base->clk) < 2)
+ if (!base->is_idle || (long) (jnow - base->clk) < 2)
return;
/*
* If the next expiry value is > jiffies, then we fast forward to
* jiffies otherwise we forward to the next expiry value.
*/
- if (time_after(base->next_expiry, jiffies))
- base->clk = jiffies;
+ if (time_after(base->next_expiry, jnow))
+ base->clk = jnow;
else
base->clk = base->next_expiry;
}
#else
static inline struct timer_base *
-__get_target_base(struct timer_base *base, unsigned tflags)
+get_target_base(struct timer_base *base, unsigned tflags)
{
return get_timer_this_cpu_base(tflags);
}
@@ -917,14 +919,6 @@ __get_target_base(struct timer_base *base, unsigned tflags)
static inline void forward_timer_base(struct timer_base *base) { }
#endif
-static inline struct timer_base *
-get_target_base(struct timer_base *base, unsigned tflags)
-{
- struct timer_base *target = __get_target_base(base, tflags);
-
- forward_timer_base(target);
- return target;
-}
/*
* We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means
@@ -943,7 +937,14 @@ static struct timer_base *lock_timer_base(struct timer_list *timer,
{
for (;;) {
struct timer_base *base;
- u32 tf = timer->flags;
+ u32 tf;
+
+ /*
+ * We need to use READ_ONCE() here, otherwise the compiler
+ * might re-read @tf between the check for TIMER_MIGRATING
+ * and spin_lock().
+ */
+ tf = READ_ONCE(timer->flags);
if (!(tf & TIMER_MIGRATING)) {
base = get_timer_base(tf);
@@ -964,6 +965,8 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
unsigned long clk = 0, flags;
int ret = 0;
+ BUG_ON(!timer->function);
+
/*
* This is a common optimization triggered by the networking code - if
* the timer is re-modified to have the same timeout or ends up in the
@@ -972,13 +975,16 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
if (timer_pending(timer)) {
if (timer->expires == expires)
return 1;
- /*
- * Take the current timer_jiffies of base, but without holding
- * the lock!
- */
- base = get_timer_base(timer->flags);
- clk = base->clk;
+ /*
+ * We lock timer base and calculate the bucket index right
+ * here. If the timer ends up in the same bucket, then we
+ * just update the expiry time and avoid the whole
+ * dequeue/enqueue dance.
+ */
+ base = lock_timer_base(timer, &flags);
+
+ clk = base->clk;
idx = calc_wheel_index(expires, clk);
/*
@@ -988,14 +994,14 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
*/
if (idx == timer_get_idx(timer)) {
timer->expires = expires;
- return 1;
+ ret = 1;
+ goto out_unlock;
}
+ } else {
+ base = lock_timer_base(timer, &flags);
}
timer_stats_timer_set_start_info(timer);
- BUG_ON(!timer->function);
-
- base = lock_timer_base(timer, &flags);
ret = detach_if_pending(timer, base, false);
if (!ret && pending_only)
@@ -1025,12 +1031,16 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
}
}
+ /* Try to forward a stale timer base clock */
+ forward_timer_base(base);
+
timer->expires = expires;
/*
* If 'idx' was calculated above and the base time did not advance
- * between calculating 'idx' and taking the lock, only enqueue_timer()
- * and trigger_dyntick_cpu() is required. Otherwise we need to
- * (re)calculate the wheel index via internal_add_timer().
+ * between calculating 'idx' and possibly switching the base, only
+ * enqueue_timer() and trigger_dyntick_cpu() is required. Otherwise
+ * we need to (re)calculate the wheel index via
+ * internal_add_timer().
*/
if (idx != UINT_MAX && clk == base->clk) {
enqueue_timer(base, timer, idx);
@@ -1510,12 +1520,16 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA);
base->next_expiry = nextevt;
/*
- * We have a fresh next event. Check whether we can forward the base:
+ * We have a fresh next event. Check whether we can forward the
+ * base. We can only do that when @basej is past base->clk
+ * otherwise we might rewind base->clk.
*/
- if (time_after(nextevt, jiffies))
- base->clk = jiffies;
- else if (time_after(nextevt, base->clk))
- base->clk = nextevt;
+ if (time_after(basej, base->clk)) {
+ if (time_after(nextevt, basej))
+ base->clk = basej;
+ else if (time_after(nextevt, base->clk))
+ base->clk = nextevt;
+ }
if (time_before_eq(nextevt, basej)) {
expires = basem;
@@ -1633,7 +1647,7 @@ static inline void __run_timers(struct timer_base *base)
/*
* This function runs timers and the timer-tq in bottom half context.
*/
-static void run_timer_softirq(struct softirq_action *h)
+static __latent_entropy void run_timer_softirq(struct softirq_action *h)
{
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 39d07e7..b01e547 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -198,6 +198,7 @@
int "Warn for stack frames larger than (needs gcc 4.4)"
range 0 8192
default 0 if KASAN
+ default 2048 if GCC_PLUGIN_LATENT_ENTROPY
default 1024 if !64BIT
default 2048 if 64BIT
help
@@ -1857,15 +1858,6 @@
See Documentation/debugging-via-ohci1394.txt for more information.
-config BUILD_DOCSRC
- bool "Build targets in Documentation/ tree"
- depends on HEADERS_CHECK
- help
- This option attempts to build objects from the source files in the
- kernel Documentation/ tree.
-
- Say N if you are unsure.
-
config DMA_API_DEBUG
bool "Enable debugging of DMA-API usage"
depends on HAVE_DMA_API_DEBUG
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 0a11396..144fe6b 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -292,7 +292,7 @@ unsigned long gen_pool_alloc_algo(struct gen_pool *pool, size_t size,
struct gen_pool_chunk *chunk;
unsigned long addr = 0;
int order = pool->min_alloc_order;
- int nbits, start_bit = 0, end_bit, remain;
+ int nbits, start_bit, end_bit, remain;
#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
BUG_ON(in_nmi());
@@ -307,6 +307,7 @@ unsigned long gen_pool_alloc_algo(struct gen_pool *pool, size_t size,
if (size > atomic_read(&chunk->avail))
continue;
+ start_bit = 0;
end_bit = chunk_size(chunk) >> order;
retry:
start_bit = algo(chunk->bits, end_bit, start_bit,
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 7312e77..f0c7f14 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1139,6 +1139,28 @@ const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags)
}
EXPORT_SYMBOL(dup_iter);
+/**
+ * import_iovec() - Copy an array of &struct iovec from userspace
+ * into the kernel, check that it is valid, and initialize a new
+ * &struct iov_iter iterator to access it.
+ *
+ * @type: One of %READ or %WRITE.
+ * @uvector: Pointer to the userspace array.
+ * @nr_segs: Number of elements in userspace array.
+ * @fast_segs: Number of elements in @iov.
+ * @iov: (input and output parameter) Pointer to pointer to (usually small
+ * on-stack) kernel array.
+ * @i: Pointer to iterator that will be initialized on success.
+ *
+ * If the array pointed to by *@iov is large enough to hold all @nr_segs,
+ * then this function places %NULL in *@iov on return. Otherwise, a new
+ * array will be allocated and the result placed in *@iov. This means that
+ * the caller may call kfree() on *@iov regardless of whether the small
+ * on-stack array was used or not (and regardless of whether this function
+ * returns an error or not).
+ *
+ * Return: 0 on success or negative error code on error.
+ */
int import_iovec(int type, const struct iovec __user * uvector,
unsigned nr_segs, unsigned fast_segs,
struct iovec **iov, struct iov_iter *i)
diff --git a/lib/irq_poll.c b/lib/irq_poll.c
index 2be5569..1d6565e8 100644
--- a/lib/irq_poll.c
+++ b/lib/irq_poll.c
@@ -74,7 +74,7 @@ void irq_poll_complete(struct irq_poll *iop)
}
EXPORT_SYMBOL(irq_poll_complete);
-static void irq_poll_softirq(struct softirq_action *h)
+static void __latent_entropy irq_poll_softirq(struct softirq_action *h)
{
struct list_head *list = this_cpu_ptr(&blk_cpu_iopoll);
int rearm = 0, budget = irq_poll_budget;
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 27fe749..9ac959e 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -33,6 +33,7 @@
#define PERCPU_COUNT_BIAS (1LU << (BITS_PER_LONG - 1))
+static DEFINE_SPINLOCK(percpu_ref_switch_lock);
static DECLARE_WAIT_QUEUE_HEAD(percpu_ref_switch_waitq);
static unsigned long __percpu *percpu_count_ptr(struct percpu_ref *ref)
@@ -82,6 +83,7 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release,
atomic_long_set(&ref->count, start_count);
ref->release = release;
+ ref->confirm_switch = NULL;
return 0;
}
EXPORT_SYMBOL_GPL(percpu_ref_init);
@@ -101,6 +103,8 @@ void percpu_ref_exit(struct percpu_ref *ref)
unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
if (percpu_count) {
+ /* non-NULL confirm_switch indicates switching in progress */
+ WARN_ON_ONCE(ref->confirm_switch);
free_percpu(percpu_count);
ref->percpu_count_ptr = __PERCPU_REF_ATOMIC_DEAD;
}
@@ -161,34 +165,67 @@ static void percpu_ref_noop_confirm_switch(struct percpu_ref *ref)
static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref,
percpu_ref_func_t *confirm_switch)
{
- if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC)) {
- /* switching from percpu to atomic */
- ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC;
-
- /*
- * Non-NULL ->confirm_switch is used to indicate that
- * switching is in progress. Use noop one if unspecified.
- */
- WARN_ON_ONCE(ref->confirm_switch);
- ref->confirm_switch =
- confirm_switch ?: percpu_ref_noop_confirm_switch;
-
- percpu_ref_get(ref); /* put after confirmation */
- call_rcu_sched(&ref->rcu, percpu_ref_switch_to_atomic_rcu);
- } else if (confirm_switch) {
- /*
- * Somebody already set ATOMIC. Switching may still be in
- * progress. @confirm_switch must be invoked after the
- * switching is complete and a full sched RCU grace period
- * has passed. Wait synchronously for the previous
- * switching and schedule @confirm_switch invocation.
- */
- wait_event(percpu_ref_switch_waitq, !ref->confirm_switch);
- ref->confirm_switch = confirm_switch;
-
- percpu_ref_get(ref); /* put after confirmation */
- call_rcu_sched(&ref->rcu, percpu_ref_call_confirm_rcu);
+ if (ref->percpu_count_ptr & __PERCPU_REF_ATOMIC) {
+ if (confirm_switch)
+ confirm_switch(ref);
+ return;
}
+
+ /* switching from percpu to atomic */
+ ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC;
+
+ /*
+ * Non-NULL ->confirm_switch is used to indicate that switching is
+ * in progress. Use noop one if unspecified.
+ */
+ ref->confirm_switch = confirm_switch ?: percpu_ref_noop_confirm_switch;
+
+ percpu_ref_get(ref); /* put after confirmation */
+ call_rcu_sched(&ref->rcu, percpu_ref_switch_to_atomic_rcu);
+}
+
+static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
+{
+ unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
+ int cpu;
+
+ BUG_ON(!percpu_count);
+
+ if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC))
+ return;
+
+ atomic_long_add(PERCPU_COUNT_BIAS, &ref->count);
+
+ /*
+ * Restore per-cpu operation. smp_store_release() is paired with
+ * smp_read_barrier_depends() in __ref_is_percpu() and guarantees
+ * that the zeroing is visible to all percpu accesses which can see
+ * the following __PERCPU_REF_ATOMIC clearing.
+ */
+ for_each_possible_cpu(cpu)
+ *per_cpu_ptr(percpu_count, cpu) = 0;
+
+ smp_store_release(&ref->percpu_count_ptr,
+ ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC);
+}
+
+static void __percpu_ref_switch_mode(struct percpu_ref *ref,
+ percpu_ref_func_t *confirm_switch)
+{
+ lockdep_assert_held(&percpu_ref_switch_lock);
+
+ /*
+ * If the previous ATOMIC switching hasn't finished yet, wait for
+ * its completion. If the caller ensures that ATOMIC switching
+ * isn't in progress, this function can be called from any context.
+ */
+ wait_event_lock_irq(percpu_ref_switch_waitq, !ref->confirm_switch,
+ percpu_ref_switch_lock);
+
+ if (ref->force_atomic || (ref->percpu_count_ptr & __PERCPU_REF_DEAD))
+ __percpu_ref_switch_to_atomic(ref, confirm_switch);
+ else
+ __percpu_ref_switch_to_percpu(ref);
}
/**
@@ -207,47 +244,21 @@ static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref,
* operations. Note that @ref will stay in atomic mode across kill/reinit
* cycles until percpu_ref_switch_to_percpu() is called.
*
- * This function normally doesn't block and can be called from any context
- * but it may block if @confirm_kill is specified and @ref is already in
- * the process of switching to atomic mode. In such cases, @confirm_switch
- * will be invoked after the switching is complete.
- *
- * Due to the way percpu_ref is implemented, @confirm_switch will be called
- * after at least one full sched RCU grace period has passed but this is an
- * implementation detail and must not be depended upon.
+ * This function may block if @ref is in the process of switching to atomic
+ * mode. If the caller ensures that @ref is not in the process of
+ * switching to atomic mode, this function can be called from any context.
*/
void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
percpu_ref_func_t *confirm_switch)
{
+ unsigned long flags;
+
+ spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+
ref->force_atomic = true;
- __percpu_ref_switch_to_atomic(ref, confirm_switch);
-}
+ __percpu_ref_switch_mode(ref, confirm_switch);
-static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
-{
- unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
- int cpu;
-
- BUG_ON(!percpu_count);
-
- if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC))
- return;
-
- wait_event(percpu_ref_switch_waitq, !ref->confirm_switch);
-
- atomic_long_add(PERCPU_COUNT_BIAS, &ref->count);
-
- /*
- * Restore per-cpu operation. smp_store_release() is paired with
- * smp_read_barrier_depends() in __ref_is_percpu() and guarantees
- * that the zeroing is visible to all percpu accesses which can see
- * the following __PERCPU_REF_ATOMIC clearing.
- */
- for_each_possible_cpu(cpu)
- *per_cpu_ptr(percpu_count, cpu) = 0;
-
- smp_store_release(&ref->percpu_count_ptr,
- ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC);
+ spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
}
/**
@@ -264,17 +275,20 @@ static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
* dying or dead, the actual switching takes place on the following
* percpu_ref_reinit().
*
- * This function normally doesn't block and can be called from any context
- * but it may block if @ref is in the process of switching to atomic mode
- * by percpu_ref_switch_atomic().
+ * This function may block if @ref is in the process of switching to atomic
+ * mode. If the caller ensures that @ref is not in the process of
+ * switching to atomic mode, this function can be called from any context.
*/
void percpu_ref_switch_to_percpu(struct percpu_ref *ref)
{
- ref->force_atomic = false;
+ unsigned long flags;
- /* a dying or dead ref can't be switched to percpu mode w/o reinit */
- if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD))
- __percpu_ref_switch_to_percpu(ref);
+ spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+
+ ref->force_atomic = false;
+ __percpu_ref_switch_mode(ref, NULL);
+
+ spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
}
/**
@@ -290,21 +304,23 @@ void percpu_ref_switch_to_percpu(struct percpu_ref *ref)
*
* This function normally doesn't block and can be called from any context
* but it may block if @confirm_kill is specified and @ref is in the
- * process of switching to atomic mode by percpu_ref_switch_atomic().
- *
- * Due to the way percpu_ref is implemented, @confirm_switch will be called
- * after at least one full sched RCU grace period has passed but this is an
- * implementation detail and must not be depended upon.
+ * process of switching to atomic mode by percpu_ref_switch_to_atomic().
*/
void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
percpu_ref_func_t *confirm_kill)
{
+ unsigned long flags;
+
+ spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+
WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_DEAD,
"%s called more than once on %pf!", __func__, ref->release);
ref->percpu_count_ptr |= __PERCPU_REF_DEAD;
- __percpu_ref_switch_to_atomic(ref, confirm_kill);
+ __percpu_ref_switch_mode(ref, confirm_kill);
percpu_ref_put(ref);
+
+ spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
}
EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
@@ -321,11 +337,16 @@ EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
*/
void percpu_ref_reinit(struct percpu_ref *ref)
{
+ unsigned long flags;
+
+ spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+
WARN_ON_ONCE(!percpu_ref_is_zero(ref));
ref->percpu_count_ptr &= ~__PERCPU_REF_DEAD;
percpu_ref_get(ref);
- if (!ref->force_atomic)
- __percpu_ref_switch_to_percpu(ref);
+ __percpu_ref_switch_mode(ref, NULL);
+
+ spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
}
EXPORT_SYMBOL_GPL(percpu_ref_reinit);
diff --git a/lib/random32.c b/lib/random32.c
index 915982b..fa594b1 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -47,7 +47,7 @@ static inline void prandom_state_selftest(void)
}
#endif
-static DEFINE_PER_CPU(struct rnd_state, net_rand_state);
+static DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy;
/**
* prandom_u32_state - seeded pseudo-random number generator.
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 60f77f1..f87d138 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -50,7 +50,7 @@
STACK_ALLOC_ALIGN)
#define STACK_ALLOC_INDEX_BITS (DEPOT_STACK_BITS - \
STACK_ALLOC_NULL_PROTECTION_BITS - STACK_ALLOC_OFFSET_BITS)
-#define STACK_ALLOC_SLABS_CAP 1024
+#define STACK_ALLOC_SLABS_CAP 8192
#define STACK_ALLOC_MAX_SLABS \
(((1LL << (STACK_ALLOC_INDEX_BITS)) < STACK_ALLOC_SLABS_CAP) ? \
(1LL << (STACK_ALLOC_INDEX_BITS)) : STACK_ALLOC_SLABS_CAP)
@@ -192,6 +192,7 @@ void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace)
trace->entries = stack->entries;
trace->skip = 0;
}
+EXPORT_SYMBOL_GPL(depot_fetch_stack);
/**
* depot_save_stack - save stack in a stack depot.
@@ -283,3 +284,4 @@ depot_stack_handle_t depot_save_stack(struct stack_trace *trace,
fast_exit:
return retval;
}
+EXPORT_SYMBOL_GPL(depot_save_stack);
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 94346b4..0362da0 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -4831,7 +4831,7 @@ static struct bpf_test tests[] = {
{ },
INTERNAL,
{ 0x34 },
- { { 1, 0xbef } },
+ { { ETH_HLEN, 0xbef } },
.fill_helper = bpf_fill_ld_abs_vlan_push_pop,
},
/*
diff --git a/mm/Kconfig b/mm/Kconfig
index be0ee11..86e3e0e 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -187,7 +187,7 @@
bool "Allow for memory hot-add"
depends on SPARSEMEM || X86_64_ACPI_NUMA
depends on ARCH_ENABLE_MEMORY_HOTPLUG
- depends on !KASAN
+ depends on COMPILE_TEST || !KASAN
config MEMORY_HOTPLUG_SPARSE
def_bool y
diff --git a/mm/cma.c b/mm/cma.c
index 384c2cb..c960459 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -385,6 +385,9 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align)
bitmap_maxno = cma_bitmap_maxno(cma);
bitmap_count = cma_bitmap_pages_to_bits(cma, count);
+ if (bitmap_count > bitmap_maxno)
+ return NULL;
+
for (;;) {
mutex_lock(&cma->lock);
bitmap_no = bitmap_find_next_zero_area_off(cma->bitmap,
diff --git a/mm/filemap.c b/mm/filemap.c
index 849f459..50b52fe 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -790,9 +790,7 @@ EXPORT_SYMBOL(__page_cache_alloc);
*/
wait_queue_head_t *page_waitqueue(struct page *page)
{
- const struct zone *zone = page_zone(page);
-
- return &zone->wait_table[hash_ptr(page, zone->wait_table_bits)];
+ return bit_waitqueue(page, 0);
}
EXPORT_SYMBOL(page_waitqueue);
@@ -1734,6 +1732,9 @@ static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
if (inode->i_blkbits == PAGE_SHIFT ||
!mapping->a_ops->is_partially_uptodate)
goto page_not_up_to_date;
+ /* pipes can't handle partially uptodate pages */
+ if (unlikely(iter->type & ITER_PIPE))
+ goto page_not_up_to_date;
if (!trylock_page(page))
goto page_not_up_to_date;
/* Did it get truncated before we got the lock? */
diff --git a/mm/frame_vector.c b/mm/frame_vector.c
index 381bb07..db77dcb 100644
--- a/mm/frame_vector.c
+++ b/mm/frame_vector.c
@@ -11,10 +11,7 @@
* get_vaddr_frames() - map virtual addresses to pfns
* @start: starting user address
* @nr_frames: number of pages / pfns from start to map
- * @write: whether pages will be written to by the caller
- * @force: whether to force write access even if user mapping is
- * readonly. See description of the same argument of
- get_user_pages().
+ * @gup_flags: flags modifying lookup behaviour
* @vec: structure which receives pages / pfns of the addresses mapped.
* It should have space for at least nr_frames entries.
*
@@ -34,7 +31,7 @@
* This function takes care of grabbing mmap_sem as necessary.
*/
int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
- bool write, bool force, struct frame_vector *vec)
+ unsigned int gup_flags, struct frame_vector *vec)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
@@ -59,7 +56,7 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
vec->got_ref = true;
vec->is_pfns = false;
ret = get_user_pages_locked(start, nr_frames,
- write, force, (struct page **)(vec->ptrs), &locked);
+ gup_flags, (struct page **)(vec->ptrs), &locked);
goto out;
}
diff --git a/mm/gup.c b/mm/gup.c
index 96b2b2f..ec4f827 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -60,6 +60,16 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
return -EEXIST;
}
+/*
+ * FOLL_FORCE can write to even unwritable pte's, but only
+ * after we've gone through a COW cycle and they are dirty.
+ */
+static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
+{
+ return pte_write(pte) ||
+ ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
+}
+
static struct page *follow_page_pte(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd, unsigned int flags)
{
@@ -95,7 +105,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
}
if ((flags & FOLL_NUMA) && pte_protnone(pte))
goto no_page;
- if ((flags & FOLL_WRITE) && !pte_write(pte)) {
+ if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) {
pte_unmap_unlock(ptep, ptl);
return NULL;
}
@@ -412,7 +422,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
* reCOWed by userspace write).
*/
if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE))
- *flags &= ~FOLL_WRITE;
+ *flags |= FOLL_COW;
return 0;
}
@@ -516,7 +526,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
* instead of __get_user_pages. __get_user_pages should be used only if
* you need some special @gup_flags.
*/
-long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas, int *nonblocking)
@@ -621,7 +631,6 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
} while (nr_pages);
return i;
}
-EXPORT_SYMBOL(__get_user_pages);
bool vma_permits_fault(struct vm_area_struct *vma, unsigned int fault_flags)
{
@@ -729,7 +738,6 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
struct mm_struct *mm,
unsigned long start,
unsigned long nr_pages,
- int write, int force,
struct page **pages,
struct vm_area_struct **vmas,
int *locked, bool notify_drop,
@@ -747,10 +755,6 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
if (pages)
flags |= FOLL_GET;
- if (write)
- flags |= FOLL_WRITE;
- if (force)
- flags |= FOLL_FORCE;
pages_done = 0;
lock_dropped = false;
@@ -843,12 +847,12 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
* up_read(&mm->mmap_sem);
*/
long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages,
+ unsigned int gup_flags, struct page **pages,
int *locked)
{
return __get_user_pages_locked(current, current->mm, start, nr_pages,
- write, force, pages, NULL, locked, true,
- FOLL_TOUCH);
+ pages, NULL, locked, true,
+ gup_flags | FOLL_TOUCH);
}
EXPORT_SYMBOL(get_user_pages_locked);
@@ -864,14 +868,14 @@ EXPORT_SYMBOL(get_user_pages_locked);
*/
__always_inline long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages,
- unsigned int gup_flags)
+ struct page **pages, unsigned int gup_flags)
{
long ret;
int locked = 1;
+
down_read(&mm->mmap_sem);
- ret = __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
- pages, NULL, &locked, false, gup_flags);
+ ret = __get_user_pages_locked(tsk, mm, start, nr_pages, pages, NULL,
+ &locked, false, gup_flags);
if (locked)
up_read(&mm->mmap_sem);
return ret;
@@ -896,10 +900,10 @@ EXPORT_SYMBOL(__get_user_pages_unlocked);
* "force" parameter).
*/
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages)
+ struct page **pages, unsigned int gup_flags)
{
return __get_user_pages_unlocked(current, current->mm, start, nr_pages,
- write, force, pages, FOLL_TOUCH);
+ pages, gup_flags | FOLL_TOUCH);
}
EXPORT_SYMBOL(get_user_pages_unlocked);
@@ -910,9 +914,7 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
* @mm: mm_struct of target mm
* @start: starting user address
* @nr_pages: number of pages from start to pin
- * @write: whether pages will be written to by the caller
- * @force: whether to force access even when user mapping is currently
- * protected (but never forces write access to shared mapping).
+ * @gup_flags: flags modifying lookup behaviour
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long. Or NULL, if caller
* only intends to ensure the pages are faulted in.
@@ -941,9 +943,9 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
* or similar operation cannot guarantee anything stronger anyway because
* locks can't be held over the syscall boundary.
*
- * If write=0, the page must not be written to. If the page is written to,
- * set_page_dirty (or set_page_dirty_lock, as appropriate) must be called
- * after the page is finished with, and before put_page is called.
+ * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page
+ * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must
+ * be called after the page is finished with, and before put_page is called.
*
* get_user_pages is typically used for fewer-copy IO operations, to get a
* handle on the memory by some means other than accesses via the user virtual
@@ -960,12 +962,12 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
*/
long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages,
+ unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas)
{
- return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
- pages, vmas, NULL, false,
- FOLL_TOUCH | FOLL_REMOTE);
+ return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
+ NULL, false,
+ gup_flags | FOLL_TOUCH | FOLL_REMOTE);
}
EXPORT_SYMBOL(get_user_pages_remote);
@@ -976,12 +978,12 @@ EXPORT_SYMBOL(get_user_pages_remote);
* obviously don't pass FOLL_REMOTE in here.
*/
long get_user_pages(unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages,
+ unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas)
{
return __get_user_pages_locked(current, current->mm, start, nr_pages,
- write, force, pages, vmas, NULL, false,
- FOLL_TOUCH);
+ pages, vmas, NULL, false,
+ gup_flags | FOLL_TOUCH);
}
EXPORT_SYMBOL(get_user_pages);
@@ -1505,7 +1507,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
start += nr << PAGE_SHIFT;
pages += nr;
- ret = get_user_pages_unlocked(start, nr_pages - nr, write, 0, pages);
+ ret = get_user_pages_unlocked(start, nr_pages - nr, pages,
+ write ? FOLL_WRITE : 0);
/* Have to be a bit careful with return values */
if (nr > 0) {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ec49d9e..418bf01 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1826,11 +1826,17 @@ static void return_unused_surplus_pages(struct hstate *h,
* is not the case is if a reserve map was changed between calls. It
* is the responsibility of the caller to notice the difference and
* take appropriate action.
+ *
+ * vma_add_reservation is used in error paths where a reservation must
+ * be restored when a newly allocated huge page must be freed. It is
+ * to be called after calling vma_needs_reservation to determine if a
+ * reservation exists.
*/
enum vma_resv_mode {
VMA_NEEDS_RESV,
VMA_COMMIT_RESV,
VMA_END_RESV,
+ VMA_ADD_RESV,
};
static long __vma_reservation_common(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr,
@@ -1856,6 +1862,14 @@ static long __vma_reservation_common(struct hstate *h,
region_abort(resv, idx, idx + 1);
ret = 0;
break;
+ case VMA_ADD_RESV:
+ if (vma->vm_flags & VM_MAYSHARE)
+ ret = region_add(resv, idx, idx + 1);
+ else {
+ region_abort(resv, idx, idx + 1);
+ ret = region_del(resv, idx, idx + 1);
+ }
+ break;
default:
BUG();
}
@@ -1903,6 +1917,56 @@ static void vma_end_reservation(struct hstate *h,
(void)__vma_reservation_common(h, vma, addr, VMA_END_RESV);
}
+static long vma_add_reservation(struct hstate *h,
+ struct vm_area_struct *vma, unsigned long addr)
+{
+ return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV);
+}
+
+/*
+ * This routine is called to restore a reservation on error paths. In the
+ * specific error paths, a huge page was allocated (via alloc_huge_page)
+ * and is about to be freed. If a reservation for the page existed,
+ * alloc_huge_page would have consumed the reservation and set PagePrivate
+ * in the newly allocated page. When the page is freed via free_huge_page,
+ * the global reservation count will be incremented if PagePrivate is set.
+ * However, free_huge_page can not adjust the reserve map. Adjust the
+ * reserve map here to be consistent with global reserve count adjustments
+ * to be made by free_huge_page.
+ */
+static void restore_reserve_on_error(struct hstate *h,
+ struct vm_area_struct *vma, unsigned long address,
+ struct page *page)
+{
+ if (unlikely(PagePrivate(page))) {
+ long rc = vma_needs_reservation(h, vma, address);
+
+ if (unlikely(rc < 0)) {
+ /*
+ * Rare out of memory condition in reserve map
+ * manipulation. Clear PagePrivate so that
+ * global reserve count will not be incremented
+ * by free_huge_page. This will make it appear
+ * as though the reservation for this page was
+ * consumed. This may prevent the task from
+ * faulting in the page at a later time. This
+ * is better than inconsistent global huge page
+ * accounting of reserve counts.
+ */
+ ClearPagePrivate(page);
+ } else if (rc) {
+ rc = vma_add_reservation(h, vma, address);
+ if (unlikely(rc < 0))
+ /*
+ * See above comment about rare out of
+ * memory condition.
+ */
+ ClearPagePrivate(page);
+ } else
+ vma_end_reservation(h, vma, address);
+ }
+}
+
struct page *alloc_huge_page(struct vm_area_struct *vma,
unsigned long addr, int avoid_reserve)
{
@@ -3498,6 +3562,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
spin_unlock(ptl);
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
out_release_all:
+ restore_reserve_on_error(h, vma, address, new_page);
put_page(new_page);
out_release_old:
put_page(old_page);
@@ -3680,6 +3745,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
spin_unlock(ptl);
backout_unlocked:
unlock_page(page);
+ restore_reserve_on_error(h, vma, address, page);
put_page(page);
goto out;
}
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 88af13c..70c0097 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -34,6 +34,7 @@
#include <linux/string.h>
#include <linux/types.h>
#include <linux/vmalloc.h>
+#include <linux/bug.h>
#include "kasan.h"
#include "../slab.h"
@@ -62,7 +63,7 @@ void kasan_unpoison_shadow(const void *address, size_t size)
}
}
-static void __kasan_unpoison_stack(struct task_struct *task, void *sp)
+static void __kasan_unpoison_stack(struct task_struct *task, const void *sp)
{
void *base = task_stack_page(task);
size_t size = sp - base;
@@ -77,9 +78,24 @@ void kasan_unpoison_task_stack(struct task_struct *task)
}
/* Unpoison the stack for the current task beyond a watermark sp value. */
-asmlinkage void kasan_unpoison_remaining_stack(void *sp)
+asmlinkage void kasan_unpoison_task_stack_below(const void *watermark)
{
- __kasan_unpoison_stack(current, sp);
+ __kasan_unpoison_stack(current, watermark);
+}
+
+/*
+ * Clear all poison for the region between the current SP and a provided
+ * watermark value, as is sometimes required prior to hand-crafted asm function
+ * returns in the middle of functions.
+ */
+void kasan_unpoison_stack_above_sp_to(const void *watermark)
+{
+ const void *sp = __builtin_frame_address(0);
+ size_t size = watermark - sp;
+
+ if (WARN_ON(sp > watermark))
+ return;
+ kasan_unpoison_shadow(sp, size);
}
/*
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index a5e453c..d1380ed 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1414,6 +1414,7 @@ static void kmemleak_scan(void)
/* data/bss scanning */
scan_large_block(_sdata, _edata);
scan_large_block(__bss_start, __bss_stop);
+ scan_large_block(__start_data_ro_after_init, __end_data_ro_after_init);
#ifdef CONFIG_SMP
/* per-cpu sections scanning */
@@ -1453,8 +1454,11 @@ static void kmemleak_scan(void)
read_lock(&tasklist_lock);
do_each_thread(g, p) {
- scan_block(task_stack_page(p), task_stack_page(p) +
- THREAD_SIZE, NULL);
+ void *stack = try_get_task_stack(p);
+ if (stack) {
+ scan_block(stack, stack + THREAD_SIZE, NULL);
+ put_task_stack(p);
+ }
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
}
diff --git a/mm/list_lru.c b/mm/list_lru.c
index 1d05cb9..234676e 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -554,6 +554,8 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware,
err = memcg_init_list_lru(lru, memcg_aware);
if (err) {
kfree(lru->node);
+ /* Do this so a list_lru_destroy() doesn't crash: */
+ lru->node = NULL;
goto out;
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ae052b5..0f870ba 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1917,6 +1917,15 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
current->flags & PF_EXITING))
goto force;
+ /*
+ * Prevent unbounded recursion when reclaim operations need to
+ * allocate memory. This might exceed the limits temporarily,
+ * but we prefer facilitating memory reclaim and getting back
+ * under the limit over triggering OOM kills in these cases.
+ */
+ if (unlikely(current->flags & PF_MEMALLOC))
+ goto force;
+
if (unlikely(task_in_memcg_oom(current)))
goto nomem;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index de88f33..19e796d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1112,10 +1112,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
}
if (!PageHuge(p) && PageTransHuge(hpage)) {
- lock_page(hpage);
- if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) {
- unlock_page(hpage);
- if (!PageAnon(hpage))
+ lock_page(p);
+ if (!PageAnon(p) || unlikely(split_huge_page(p))) {
+ unlock_page(p);
+ if (!PageAnon(p))
pr_err("Memory failure: %#lx: non anonymous thp\n",
pfn);
else
@@ -1126,9 +1126,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
put_hwpoison_page(p);
return -EBUSY;
}
- unlock_page(hpage);
- get_hwpoison_page(p);
- put_hwpoison_page(hpage);
+ unlock_page(p);
VM_BUG_ON_PAGE(!page_count(p), p);
hpage = compound_head(p);
}
diff --git a/mm/memory.c b/mm/memory.c
index fc1987d..e18c57b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3869,10 +3869,11 @@ EXPORT_SYMBOL_GPL(generic_access_phys);
* given task for page fault accounting.
*/
static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long addr, void *buf, int len, int write)
+ unsigned long addr, void *buf, int len, unsigned int gup_flags)
{
struct vm_area_struct *vma;
void *old_buf = buf;
+ int write = gup_flags & FOLL_WRITE;
down_read(&mm->mmap_sem);
/* ignore errors, just check how much was successfully transferred */
@@ -3882,7 +3883,7 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
struct page *page = NULL;
ret = get_user_pages_remote(tsk, mm, addr, 1,
- write, 1, &page, &vma);
+ gup_flags, &page, &vma);
if (ret <= 0) {
#ifndef CONFIG_HAVE_IOREMAP_PROT
break;
@@ -3934,14 +3935,14 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
* @addr: start address to access
* @buf: source or destination buffer
* @len: number of bytes to transfer
- * @write: whether the access is a write
+ * @gup_flags: flags modifying lookup behaviour
*
* The caller must hold a reference on @mm.
*/
int access_remote_vm(struct mm_struct *mm, unsigned long addr,
- void *buf, int len, int write)
+ void *buf, int len, unsigned int gup_flags)
{
- return __access_remote_vm(NULL, mm, addr, buf, len, write);
+ return __access_remote_vm(NULL, mm, addr, buf, len, gup_flags);
}
/*
@@ -3950,7 +3951,7 @@ int access_remote_vm(struct mm_struct *mm, unsigned long addr,
* Do not walk the page table directly, use get_user_pages
*/
int access_process_vm(struct task_struct *tsk, unsigned long addr,
- void *buf, int len, int write)
+ void *buf, int len, unsigned int gup_flags)
{
struct mm_struct *mm;
int ret;
@@ -3959,7 +3960,8 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr,
if (!mm)
return 0;
- ret = __access_remote_vm(tsk, mm, addr, buf, len, write);
+ ret = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags);
+
mmput(mm);
return ret;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9629273..cad4b91 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -268,7 +268,6 @@ void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
unsigned long i, pfn, end_pfn, nr_pages;
int node = pgdat->node_id;
struct page *page;
- struct zone *zone;
nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
page = virt_to_page(pgdat);
@@ -276,19 +275,6 @@ void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
for (i = 0; i < nr_pages; i++, page++)
get_page_bootmem(node, page, NODE_INFO);
- zone = &pgdat->node_zones[0];
- for (; zone < pgdat->node_zones + MAX_NR_ZONES - 1; zone++) {
- if (zone_is_initialized(zone)) {
- nr_pages = zone->wait_table_hash_nr_entries
- * sizeof(wait_queue_head_t);
- nr_pages = PAGE_ALIGN(nr_pages) >> PAGE_SHIFT;
- page = virt_to_page(zone->wait_table);
-
- for (i = 0; i < nr_pages; i++, page++)
- get_page_bootmem(node, page, NODE_INFO);
- }
- }
-
pfn = pgdat->node_start_pfn;
end_pfn = pgdat_end_pfn(pgdat);
@@ -2131,7 +2117,6 @@ void try_offline_node(int nid)
unsigned long start_pfn = pgdat->node_start_pfn;
unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
unsigned long pfn;
- int i;
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
unsigned long section_nr = pfn_to_section_nr(pfn);
@@ -2158,20 +2143,6 @@ void try_offline_node(int nid)
*/
node_set_offline(nid);
unregister_one_node(nid);
-
- /* free waittable in each zone */
- for (i = 0; i < MAX_NR_ZONES; i++) {
- struct zone *zone = pgdat->node_zones + i;
-
- /*
- * wait_table may be allocated from boot memory,
- * here only free if it's allocated by vmalloc.
- */
- if (is_vmalloc_addr(zone->wait_table)) {
- vfree(zone->wait_table);
- zone->wait_table = NULL;
- }
- }
}
EXPORT_SYMBOL(try_offline_node);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index ad1c96a..0b859af 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -850,7 +850,7 @@ static int lookup_node(unsigned long addr)
struct page *p;
int err;
- err = get_user_pages(addr & PAGE_MASK, 1, 0, 0, &p, NULL);
+ err = get_user_pages(addr & PAGE_MASK, 1, 0, &p, NULL);
if (err >= 0) {
err = page_to_nid(p);
put_page(p);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index bcdbe62..1193652 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -25,7 +25,6 @@
#include <linux/perf_event.h>
#include <linux/pkeys.h>
#include <linux/ksm.h>
-#include <linux/pkeys.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/cacheflush.h>
diff --git a/mm/nommu.c b/mm/nommu.c
index 95daf81..8b8faaf 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -109,7 +109,7 @@ unsigned int kobjsize(const void *objp)
return PAGE_SIZE << compound_order(page);
}
-long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
unsigned int foll_flags, struct page **pages,
struct vm_area_struct **vmas, int *nonblocking)
@@ -160,33 +160,25 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
* - don't permit access to VMAs that don't support it, such as I/O mappings
*/
long get_user_pages(unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages,
+ unsigned int gup_flags, struct page **pages,
struct vm_area_struct **vmas)
{
- int flags = 0;
-
- if (write)
- flags |= FOLL_WRITE;
- if (force)
- flags |= FOLL_FORCE;
-
- return __get_user_pages(current, current->mm, start, nr_pages, flags,
- pages, vmas, NULL);
+ return __get_user_pages(current, current->mm, start, nr_pages,
+ gup_flags, pages, vmas, NULL);
}
EXPORT_SYMBOL(get_user_pages);
long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages,
+ unsigned int gup_flags, struct page **pages,
int *locked)
{
- return get_user_pages(start, nr_pages, write, force, pages, NULL);
+ return get_user_pages(start, nr_pages, gup_flags, pages, NULL);
}
EXPORT_SYMBOL(get_user_pages_locked);
long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages,
- unsigned int gup_flags)
+ struct page **pages, unsigned int gup_flags)
{
long ret;
down_read(&mm->mmap_sem);
@@ -198,10 +190,10 @@ long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
EXPORT_SYMBOL(__get_user_pages_unlocked);
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
- int write, int force, struct page **pages)
+ struct page **pages, unsigned int gup_flags)
{
return __get_user_pages_unlocked(current, current->mm, start, nr_pages,
- write, force, pages, 0);
+ pages, gup_flags);
}
EXPORT_SYMBOL(get_user_pages_unlocked);
@@ -1817,9 +1809,10 @@ void filemap_map_pages(struct fault_env *fe,
EXPORT_SYMBOL(filemap_map_pages);
static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long addr, void *buf, int len, int write)
+ unsigned long addr, void *buf, int len, unsigned int gup_flags)
{
struct vm_area_struct *vma;
+ int write = gup_flags & FOLL_WRITE;
down_read(&mm->mmap_sem);
@@ -1854,21 +1847,22 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
* @addr: start address to access
* @buf: source or destination buffer
* @len: number of bytes to transfer
- * @write: whether the access is a write
+ * @gup_flags: flags modifying lookup behaviour
*
* The caller must hold a reference on @mm.
*/
int access_remote_vm(struct mm_struct *mm, unsigned long addr,
- void *buf, int len, int write)
+ void *buf, int len, unsigned int gup_flags)
{
- return __access_remote_vm(NULL, mm, addr, buf, len, write);
+ return __access_remote_vm(NULL, mm, addr, buf, len, gup_flags);
}
/*
* Access another process' address space.
* - source/target buffer must be kernel space
*/
-int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write)
+int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len,
+ unsigned int gup_flags)
{
struct mm_struct *mm;
@@ -1879,7 +1873,7 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
if (!mm)
return 0;
- len = __access_remote_vm(tsk, mm, addr, buf, len, write);
+ len = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags);
mmput(mm);
return len;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ca423cc..6de9440 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -91,6 +91,11 @@ EXPORT_PER_CPU_SYMBOL(_numa_mem_);
int _node_numa_mem_[MAX_NUMNODES];
#endif
+#ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
+volatile unsigned long latent_entropy __latent_entropy;
+EXPORT_SYMBOL(latent_entropy);
+#endif
+
/*
* Array of node states.
*/
@@ -3653,7 +3658,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
/* Make sure we know about allocations which stall for too long */
if (time_after(jiffies, alloc_start + stall_timeout)) {
warn_alloc(gfp_mask,
- "page alloction stalls for %ums, order:%u\n",
+ "page allocation stalls for %ums, order:%u",
jiffies_to_msecs(jiffies-alloc_start), order);
stall_timeout += 10 * HZ;
}
@@ -4219,7 +4224,7 @@ static void show_migration_types(unsigned char type)
}
*p = '\0';
- printk("(%s) ", tmp);
+ printk(KERN_CONT "(%s) ", tmp);
}
/*
@@ -4330,7 +4335,8 @@ void show_free_areas(unsigned int filter)
free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count;
show_node(zone);
- printk("%s"
+ printk(KERN_CONT
+ "%s"
" free:%lukB"
" min:%lukB"
" low:%lukB"
@@ -4377,8 +4383,8 @@ void show_free_areas(unsigned int filter)
K(zone_page_state(zone, NR_FREE_CMA_PAGES)));
printk("lowmem_reserve[]:");
for (i = 0; i < MAX_NR_ZONES; i++)
- printk(" %ld", zone->lowmem_reserve[i]);
- printk("\n");
+ printk(KERN_CONT " %ld", zone->lowmem_reserve[i]);
+ printk(KERN_CONT "\n");
}
for_each_populated_zone(zone) {
@@ -4389,7 +4395,7 @@ void show_free_areas(unsigned int filter)
if (skip_free_areas_node(filter, zone_to_nid(zone)))
continue;
show_node(zone);
- printk("%s: ", zone->name);
+ printk(KERN_CONT "%s: ", zone->name);
spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
@@ -4407,11 +4413,12 @@ void show_free_areas(unsigned int filter)
}
spin_unlock_irqrestore(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
- printk("%lu*%lukB ", nr[order], K(1UL) << order);
+ printk(KERN_CONT "%lu*%lukB ",
+ nr[order], K(1UL) << order);
if (nr[order])
show_migration_types(types[order]);
}
- printk("= %lukB\n", K(total));
+ printk(KERN_CONT "= %lukB\n", K(total));
}
hugetlb_show_meminfo();
@@ -4972,72 +4979,6 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
}
/*
- * Helper functions to size the waitqueue hash table.
- * Essentially these want to choose hash table sizes sufficiently
- * large so that collisions trying to wait on pages are rare.
- * But in fact, the number of active page waitqueues on typical
- * systems is ridiculously low, less than 200. So this is even
- * conservative, even though it seems large.
- *
- * The constant PAGES_PER_WAITQUEUE specifies the ratio of pages to
- * waitqueues, i.e. the size of the waitq table given the number of pages.
- */
-#define PAGES_PER_WAITQUEUE 256
-
-#ifndef CONFIG_MEMORY_HOTPLUG
-static inline unsigned long wait_table_hash_nr_entries(unsigned long pages)
-{
- unsigned long size = 1;
-
- pages /= PAGES_PER_WAITQUEUE;
-
- while (size < pages)
- size <<= 1;
-
- /*
- * Once we have dozens or even hundreds of threads sleeping
- * on IO we've got bigger problems than wait queue collision.
- * Limit the size of the wait table to a reasonable size.
- */
- size = min(size, 4096UL);
-
- return max(size, 4UL);
-}
-#else
-/*
- * A zone's size might be changed by hot-add, so it is not possible to determine
- * a suitable size for its wait_table. So we use the maximum size now.
- *
- * The max wait table size = 4096 x sizeof(wait_queue_head_t). ie:
- *
- * i386 (preemption config) : 4096 x 16 = 64Kbyte.
- * ia64, x86-64 (no preemption): 4096 x 20 = 80Kbyte.
- * ia64, x86-64 (preemption) : 4096 x 24 = 96Kbyte.
- *
- * The maximum entries are prepared when a zone's memory is (512K + 256) pages
- * or more by the traditional way. (See above). It equals:
- *
- * i386, x86-64, powerpc(4K page size) : = ( 2G + 1M)byte.
- * ia64(16K page size) : = ( 8G + 4M)byte.
- * powerpc (64K page size) : = (32G +16M)byte.
- */
-static inline unsigned long wait_table_hash_nr_entries(unsigned long pages)
-{
- return 4096UL;
-}
-#endif
-
-/*
- * This is an integer logarithm so that shifts can be used later
- * to extract the more random high bits from the multiplicative
- * hash function before the remainder is taken.
- */
-static inline unsigned long wait_table_bits(unsigned long size)
-{
- return ffz(~size);
-}
-
-/*
* Initially all pages are reserved - free ones are freed
* up by free_all_bootmem() once the early boot process is
* done. Non-atomic initialization, single-pass.
@@ -5299,49 +5240,6 @@ void __init setup_per_cpu_pageset(void)
alloc_percpu(struct per_cpu_nodestat);
}
-static noinline __ref
-int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
-{
- int i;
- size_t alloc_size;
-
- /*
- * The per-page waitqueue mechanism uses hashed waitqueues
- * per zone.
- */
- zone->wait_table_hash_nr_entries =
- wait_table_hash_nr_entries(zone_size_pages);
- zone->wait_table_bits =
- wait_table_bits(zone->wait_table_hash_nr_entries);
- alloc_size = zone->wait_table_hash_nr_entries
- * sizeof(wait_queue_head_t);
-
- if (!slab_is_available()) {
- zone->wait_table = (wait_queue_head_t *)
- memblock_virt_alloc_node_nopanic(
- alloc_size, zone->zone_pgdat->node_id);
- } else {
- /*
- * This case means that a zone whose size was 0 gets new memory
- * via memory hot-add.
- * But it may be the case that a new node was hot-added. In
- * this case vmalloc() will not be able to use this new node's
- * memory - this wait_table must be initialized to use this new
- * node itself as well.
- * To use this new node's memory, further consideration will be
- * necessary.
- */
- zone->wait_table = vmalloc(alloc_size);
- }
- if (!zone->wait_table)
- return -ENOMEM;
-
- for (i = 0; i < zone->wait_table_hash_nr_entries; ++i)
- init_waitqueue_head(zone->wait_table + i);
-
- return 0;
-}
-
static __meminit void zone_pcp_init(struct zone *zone)
{
/*
@@ -5362,10 +5260,7 @@ int __meminit init_currently_empty_zone(struct zone *zone,
unsigned long size)
{
struct pglist_data *pgdat = zone->zone_pgdat;
- int ret;
- ret = zone_wait_table_init(zone, size);
- if (ret)
- return ret;
+
pgdat->nr_zones = zone_idx(zone) + 1;
zone->zone_start_pfn = zone_start_pfn;
@@ -5377,6 +5272,7 @@ int __meminit init_currently_empty_zone(struct zone *zone,
zone_start_pfn, (zone_start_pfn + size));
zone_init_free_lists(zone);
+ zone->initialized = 1;
return 0;
}
diff --git a/mm/percpu.c b/mm/percpu.c
index 9903830..2557143 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1961,8 +1961,9 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
void *base = (void *)ULONG_MAX;
void **areas = NULL;
struct pcpu_alloc_info *ai;
- size_t size_sum, areas_size, max_distance;
- int group, i, rc;
+ size_t size_sum, areas_size;
+ unsigned long max_distance;
+ int group, i, highest_group, rc;
ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size,
cpu_distance_fn);
@@ -1978,7 +1979,8 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
goto out_free;
}
- /* allocate, copy and determine base address */
+ /* allocate, copy and determine base address & max_distance */
+ highest_group = 0;
for (group = 0; group < ai->nr_groups; group++) {
struct pcpu_group_info *gi = &ai->groups[group];
unsigned int cpu = NR_CPUS;
@@ -1999,6 +2001,21 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
areas[group] = ptr;
base = min(ptr, base);
+ if (ptr > areas[highest_group])
+ highest_group = group;
+ }
+ max_distance = areas[highest_group] - base;
+ max_distance += ai->unit_size * ai->groups[highest_group].nr_units;
+
+ /* warn if maximum distance is further than 75% of vmalloc space */
+ if (max_distance > VMALLOC_TOTAL * 3 / 4) {
+ pr_warn("max_distance=0x%lx too large for vmalloc space 0x%lx\n",
+ max_distance, VMALLOC_TOTAL);
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+ /* and fail if we have fallback */
+ rc = -EINVAL;
+ goto out_free_areas;
+#endif
}
/*
@@ -2023,23 +2040,8 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
}
/* base address is now known, determine group base offsets */
- max_distance = 0;
for (group = 0; group < ai->nr_groups; group++) {
ai->groups[group].base_offset = areas[group] - base;
- max_distance = max_t(size_t, max_distance,
- ai->groups[group].base_offset);
- }
- max_distance += ai->unit_size;
-
- /* warn if maximum distance is further than 75% of vmalloc space */
- if (max_distance > VMALLOC_TOTAL * 3 / 4) {
- pr_warn("max_distance=0x%zx too large for vmalloc space 0x%lx\n",
- max_distance, VMALLOC_TOTAL);
-#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
- /* and fail if we have fallback */
- rc = -EINVAL;
- goto out_free;
-#endif
}
pr_info("Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n",
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 07514d4..be8dc8d 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -88,12 +88,16 @@ static int process_vm_rw_single_vec(unsigned long addr,
ssize_t rc = 0;
unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES
/ sizeof(struct pages *);
+ unsigned int flags = FOLL_REMOTE;
/* Work out address and page range required */
if (len == 0)
return 0;
nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1;
+ if (vm_write)
+ flags |= FOLL_WRITE;
+
while (!rc && nr_pages && iov_iter_count(iter)) {
int pages = min(nr_pages, max_pages_per_loop);
size_t bytes;
@@ -104,8 +108,7 @@ static int process_vm_rw_single_vec(unsigned long addr,
* current/current->mm
*/
pages = __get_user_pages_unlocked(task, mm, pa, pages,
- vm_write, 0, process_pages,
- FOLL_REMOTE);
+ process_pages, flags);
if (pages <= 0)
return -EFAULT;
diff --git a/mm/shmem.c b/mm/shmem.c
index ad7813d..166ebf5 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1483,6 +1483,8 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
copy_highpage(newpage, oldpage);
flush_dcache_page(newpage);
+ __SetPageLocked(newpage);
+ __SetPageSwapBacked(newpage);
SetPageUptodate(newpage);
set_page_private(newpage, swap_index);
SetPageSwapCache(newpage);
diff --git a/mm/slab.c b/mm/slab.c
index 090fb26..0b0550c 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -233,6 +233,7 @@ static void kmem_cache_node_init(struct kmem_cache_node *parent)
spin_lock_init(&parent->list_lock);
parent->free_objects = 0;
parent->free_touched = 0;
+ parent->num_slabs = 0;
}
#define MAKE_LIST(cachep, listp, slab, nodeid) \
@@ -966,7 +967,7 @@ static int setup_kmem_cache_node(struct kmem_cache *cachep,
* guaranteed to be valid until irq is re-enabled, because it will be
* freed after synchronize_sched().
*/
- if (force_change)
+ if (old_shared && force_change)
synchronize_sched();
fail:
@@ -1382,24 +1383,27 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
for_each_kmem_cache_node(cachep, node, n) {
unsigned long active_objs = 0, num_objs = 0, free_objects = 0;
unsigned long active_slabs = 0, num_slabs = 0;
+ unsigned long num_slabs_partial = 0, num_slabs_free = 0;
+ unsigned long num_slabs_full;
spin_lock_irqsave(&n->list_lock, flags);
- list_for_each_entry(page, &n->slabs_full, lru) {
- active_objs += cachep->num;
- active_slabs++;
- }
+ num_slabs = n->num_slabs;
list_for_each_entry(page, &n->slabs_partial, lru) {
active_objs += page->active;
- active_slabs++;
+ num_slabs_partial++;
}
list_for_each_entry(page, &n->slabs_free, lru)
- num_slabs++;
+ num_slabs_free++;
free_objects += n->free_objects;
spin_unlock_irqrestore(&n->list_lock, flags);
- num_slabs += active_slabs;
num_objs = num_slabs * cachep->num;
+ active_slabs = num_slabs - num_slabs_free;
+ num_slabs_full = num_slabs -
+ (num_slabs_partial + num_slabs_free);
+ active_objs += (num_slabs_full * cachep->num);
+
pr_warn(" node %d: slabs: %ld/%ld, objs: %ld/%ld, free: %ld\n",
node, active_slabs, num_slabs, active_objs, num_objs,
free_objects);
@@ -2314,6 +2318,7 @@ static int drain_freelist(struct kmem_cache *cache,
page = list_entry(p, struct page, lru);
list_del(&page->lru);
+ n->num_slabs--;
/*
* Safe to drop the lock. The slab is no longer linked
* to the cache.
@@ -2752,6 +2757,8 @@ static void cache_grow_end(struct kmem_cache *cachep, struct page *page)
list_add_tail(&page->lru, &(n->slabs_free));
else
fixup_slab_list(cachep, n, page, &list);
+
+ n->num_slabs++;
STATS_INC_GROWN(cachep);
n->free_objects += cachep->num - page->active;
spin_unlock(&n->list_lock);
@@ -3443,6 +3450,7 @@ static void free_block(struct kmem_cache *cachep, void **objpp,
page = list_last_entry(&n->slabs_free, struct page, lru);
list_move(&page->lru, list);
+ n->num_slabs--;
}
}
@@ -4099,6 +4107,8 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
unsigned long num_objs;
unsigned long active_slabs = 0;
unsigned long num_slabs, free_objects = 0, shared_avail = 0;
+ unsigned long num_slabs_partial = 0, num_slabs_free = 0;
+ unsigned long num_slabs_full = 0;
const char *name;
char *error = NULL;
int node;
@@ -4111,33 +4121,34 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
check_irq_on();
spin_lock_irq(&n->list_lock);
- list_for_each_entry(page, &n->slabs_full, lru) {
- if (page->active != cachep->num && !error)
- error = "slabs_full accounting error";
- active_objs += cachep->num;
- active_slabs++;
- }
+ num_slabs += n->num_slabs;
+
list_for_each_entry(page, &n->slabs_partial, lru) {
if (page->active == cachep->num && !error)
error = "slabs_partial accounting error";
if (!page->active && !error)
error = "slabs_partial accounting error";
active_objs += page->active;
- active_slabs++;
+ num_slabs_partial++;
}
+
list_for_each_entry(page, &n->slabs_free, lru) {
if (page->active && !error)
error = "slabs_free accounting error";
- num_slabs++;
+ num_slabs_free++;
}
+
free_objects += n->free_objects;
if (n->shared)
shared_avail += n->shared->avail;
spin_unlock_irq(&n->list_lock);
}
- num_slabs += active_slabs;
num_objs = num_slabs * cachep->num;
+ active_slabs = num_slabs - num_slabs_free;
+ num_slabs_full = num_slabs - (num_slabs_partial + num_slabs_free);
+ active_objs += (num_slabs_full * cachep->num);
+
if (num_objs - active_objs != free_objects && !error)
error = "free_objects accounting error";
diff --git a/mm/slab.h b/mm/slab.h
index 9653f2e..bc05fdc 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -432,6 +432,7 @@ struct kmem_cache_node {
struct list_head slabs_partial; /* partial list first, better asm code */
struct list_head slabs_full;
struct list_head slabs_free;
+ unsigned long num_slabs;
unsigned long free_objects;
unsigned int free_limit;
unsigned int colour_next; /* Per-node cache coloring */
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 71f0b28..329b038 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -533,8 +533,8 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
s = create_cache(cache_name, root_cache->object_size,
root_cache->size, root_cache->align,
- root_cache->flags, root_cache->ctor,
- memcg, root_cache);
+ root_cache->flags & CACHE_CREATE_MASK,
+ root_cache->ctor, memcg, root_cache);
/*
* If we could not create a memcg cache, do not complain, because
* that's not critical at all as we can always proceed with the root
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2210de2..f304389 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2224,6 +2224,8 @@ static unsigned long read_swap_header(struct swap_info_struct *p,
swab32s(&swap_header->info.version);
swab32s(&swap_header->info.last_page);
swab32s(&swap_header->info.nr_badpages);
+ if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
+ return 0;
for (i = 0; i < swap_header->info.nr_badpages; i++)
swab32s(&swap_header->info.badpages[i]);
}
diff --git a/mm/util.c b/mm/util.c
index 662cddf..1a41553 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -230,8 +230,10 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
}
/* Check if the vma is being used as a stack by this task */
-int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t)
+int vma_is_stack_for_current(struct vm_area_struct *vma)
{
+ struct task_struct * __maybe_unused t = current;
+
return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
}
@@ -283,7 +285,8 @@ EXPORT_SYMBOL_GPL(__get_user_pages_fast);
int __weak get_user_pages_fast(unsigned long start,
int nr_pages, int write, struct page **pages)
{
- return get_user_pages_unlocked(start, nr_pages, write, 0, pages);
+ return get_user_pages_unlocked(start, nr_pages, pages,
+ write ? FOLL_WRITE : 0);
}
EXPORT_SYMBOL_GPL(get_user_pages_fast);
@@ -623,7 +626,7 @@ int get_cmdline(struct task_struct *task, char *buffer, int buflen)
if (len > buflen)
len = buflen;
- res = access_process_vm(task, arg_start, buffer, len, 0);
+ res = access_process_vm(task, arg_start, buffer, len, FOLL_FORCE);
/*
* If the nul at the end of args has been overwritten, then
@@ -638,7 +641,8 @@ int get_cmdline(struct task_struct *task, char *buffer, int buflen)
if (len > buflen - res)
len = buflen - res;
res += access_process_vm(task, env_start,
- buffer+res, len, 0);
+ buffer+res, len,
+ FOLL_FORCE);
res = strnlen(buffer, res);
}
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 744f926..76fda22 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3043,7 +3043,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
sc.gfp_mask,
sc.reclaim_idx);
+ current->flags |= PF_MEMALLOC;
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
+ current->flags &= ~PF_MEMALLOC;
trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 9accde3..691f0ad 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -44,7 +44,7 @@
/* Global VLAN variables */
-int vlan_net_id __read_mostly;
+unsigned int vlan_net_id __read_mostly;
const char vlan_fullname[] = "802.1Q VLAN Support";
const char vlan_version[] = DRV_VERSION;
@@ -663,7 +663,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
skb_gro_pull(skb, sizeof(*vhdr));
skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr));
- pp = ptype->callbacks.gro_receive(head, skb);
+ pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
out_unlock:
rcu_read_unlock();
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index cc15579..df8bd65 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -159,7 +159,7 @@ void vlan_netlink_fini(void);
extern struct rtnl_link_ops vlan_link_ops;
-extern int vlan_net_id;
+extern unsigned int vlan_net_id;
struct proc_dir_entry;
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 61a431a..672150b4 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -851,7 +851,6 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface,
batadv_softif_destroy_sysfs(hard_iface->soft_iface);
}
- hard_iface->soft_iface = NULL;
batadv_hardif_put(hard_iface);
out:
diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h
index ab47acf..3284a7b 100644
--- a/net/batman-adv/log.h
+++ b/net/batman-adv/log.h
@@ -63,7 +63,7 @@ enum batadv_dbg_level {
BATADV_DBG_NC = BIT(5),
BATADV_DBG_MCAST = BIT(6),
BATADV_DBG_TP_METER = BIT(7),
- BATADV_DBG_ALL = 127,
+ BATADV_DBG_ALL = 255,
};
#ifdef CONFIG_BATMAN_ADV_DEBUG
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index ad26559..8f3b296 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -547,7 +547,7 @@ batadv_hardif_neigh_create(struct batadv_hard_iface *hard_iface,
if (bat_priv->algo_ops->neigh.hardif_init)
bat_priv->algo_ops->neigh.hardif_init(hardif_neigh);
- hlist_add_head(&hardif_neigh->list, &hard_iface->neigh_list);
+ hlist_add_head_rcu(&hardif_neigh->list, &hard_iface->neigh_list);
out:
spin_unlock_bh(&hard_iface->neigh_list_lock);
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index e228842..1015d9c 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -969,41 +969,38 @@ void __hci_req_enable_advertising(struct hci_request *req)
hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable);
}
-static u8 append_local_name(struct hci_dev *hdev, u8 *ptr, u8 ad_len)
+u8 append_local_name(struct hci_dev *hdev, u8 *ptr, u8 ad_len)
{
- size_t complete_len;
size_t short_len;
- int max_len;
+ size_t complete_len;
- max_len = HCI_MAX_AD_LENGTH - ad_len - 2;
+ /* no space left for name (+ NULL + type + len) */
+ if ((HCI_MAX_AD_LENGTH - ad_len) < HCI_MAX_SHORT_NAME_LENGTH + 3)
+ return ad_len;
+
+ /* use complete name if present and fits */
complete_len = strlen(hdev->dev_name);
- short_len = strlen(hdev->short_name);
-
- /* no space left for name */
- if (max_len < 1)
- return ad_len;
-
- /* no name set */
- if (!complete_len)
- return ad_len;
-
- /* complete name fits and is eq to max short name len or smaller */
- if (complete_len <= max_len &&
- complete_len <= HCI_MAX_SHORT_NAME_LENGTH) {
+ if (complete_len && complete_len <= HCI_MAX_SHORT_NAME_LENGTH)
return eir_append_data(ptr, ad_len, EIR_NAME_COMPLETE,
- hdev->dev_name, complete_len);
- }
+ hdev->dev_name, complete_len + 1);
- /* short name set and fits */
- if (short_len && short_len <= max_len) {
+ /* use short name if present */
+ short_len = strlen(hdev->short_name);
+ if (short_len)
return eir_append_data(ptr, ad_len, EIR_NAME_SHORT,
- hdev->short_name, short_len);
- }
+ hdev->short_name, short_len + 1);
- /* no short name set so shorten complete name */
- if (!short_len) {
- return eir_append_data(ptr, ad_len, EIR_NAME_SHORT,
- hdev->dev_name, max_len);
+ /* use shortened full name if present, we already know that name
+ * is longer then HCI_MAX_SHORT_NAME_LENGTH
+ */
+ if (complete_len) {
+ u8 name[HCI_MAX_SHORT_NAME_LENGTH + 1];
+
+ memcpy(name, hdev->dev_name, HCI_MAX_SHORT_NAME_LENGTH);
+ name[HCI_MAX_SHORT_NAME_LENGTH] = '\0';
+
+ return eir_append_data(ptr, ad_len, EIR_NAME_SHORT, name,
+ sizeof(name));
}
return ad_len;
diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h
index 6b06629..dde77bd 100644
--- a/net/bluetooth/hci_request.h
+++ b/net/bluetooth/hci_request.h
@@ -106,6 +106,8 @@ static inline void hci_update_background_scan(struct hci_dev *hdev)
void hci_request_setup(struct hci_dev *hdev);
void hci_request_cancel_all(struct hci_dev *hdev);
+u8 append_local_name(struct hci_dev *hdev, u8 *ptr, u8 ad_len);
+
static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type,
u8 *data, u8 data_len)
{
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 7360380..1fba2a0 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -6017,7 +6017,15 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev,
return err;
}
-static u8 tlv_data_max_len(u32 adv_flags, bool is_adv_data)
+static u8 calculate_name_len(struct hci_dev *hdev)
+{
+ u8 buf[HCI_MAX_SHORT_NAME_LENGTH + 3];
+
+ return append_local_name(hdev, buf, 0);
+}
+
+static u8 tlv_data_max_len(struct hci_dev *hdev, u32 adv_flags,
+ bool is_adv_data)
{
u8 max_len = HCI_MAX_AD_LENGTH;
@@ -6030,9 +6038,8 @@ static u8 tlv_data_max_len(u32 adv_flags, bool is_adv_data)
if (adv_flags & MGMT_ADV_FLAG_TX_POWER)
max_len -= 3;
} else {
- /* at least 1 byte of name should fit in */
if (adv_flags & MGMT_ADV_FLAG_LOCAL_NAME)
- max_len -= 3;
+ max_len -= calculate_name_len(hdev);
if (adv_flags & (MGMT_ADV_FLAG_APPEARANCE))
max_len -= 4;
@@ -6063,12 +6070,13 @@ static bool appearance_managed(u32 adv_flags)
return adv_flags & MGMT_ADV_FLAG_APPEARANCE;
}
-static bool tlv_data_is_valid(u32 adv_flags, u8 *data, u8 len, bool is_adv_data)
+static bool tlv_data_is_valid(struct hci_dev *hdev, u32 adv_flags, u8 *data,
+ u8 len, bool is_adv_data)
{
int i, cur_len;
u8 max_len;
- max_len = tlv_data_max_len(adv_flags, is_adv_data);
+ max_len = tlv_data_max_len(hdev, adv_flags, is_adv_data);
if (len > max_len)
return false;
@@ -6215,8 +6223,8 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev,
goto unlock;
}
- if (!tlv_data_is_valid(flags, cp->data, cp->adv_data_len, true) ||
- !tlv_data_is_valid(flags, cp->data + cp->adv_data_len,
+ if (!tlv_data_is_valid(hdev, flags, cp->data, cp->adv_data_len, true) ||
+ !tlv_data_is_valid(hdev, flags, cp->data + cp->adv_data_len,
cp->scan_rsp_len, false)) {
err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
MGMT_STATUS_INVALID_PARAMS);
@@ -6429,8 +6437,8 @@ static int get_adv_size_info(struct sock *sk, struct hci_dev *hdev,
rp.instance = cp->instance;
rp.flags = cp->flags;
- rp.max_adv_data_len = tlv_data_max_len(flags, true);
- rp.max_scan_rsp_len = tlv_data_max_len(flags, false);
+ rp.max_adv_data_len = tlv_data_max_len(hdev, flags, true);
+ rp.max_scan_rsp_len = tlv_data_max_len(hdev, flags, false);
err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_ADV_SIZE_INFO,
MGMT_STATUS_SUCCESS, &rp, sizeof(rp));
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index c5fea93..073d54a 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -25,6 +25,7 @@
#include <linux/slab.h>
#include <linux/timer.h>
#include <linux/inetdevice.h>
+#include <linux/mroute.h>
#include <net/ip.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
@@ -972,13 +973,12 @@ static void br_multicast_enable(struct bridge_mcast_own_query *query)
mod_timer(&query->timer, jiffies);
}
-void br_multicast_enable_port(struct net_bridge_port *port)
+static void __br_multicast_enable_port(struct net_bridge_port *port)
{
struct net_bridge *br = port->br;
- spin_lock(&br->multicast_lock);
if (br->multicast_disabled || !netif_running(br->dev))
- goto out;
+ return;
br_multicast_enable(&port->ip4_own_query);
#if IS_ENABLED(CONFIG_IPV6)
@@ -987,8 +987,14 @@ void br_multicast_enable_port(struct net_bridge_port *port)
if (port->multicast_router == MDB_RTR_TYPE_PERM &&
hlist_unhashed(&port->rlist))
br_multicast_add_router(br, port);
+}
-out:
+void br_multicast_enable_port(struct net_bridge_port *port)
+{
+ struct net_bridge *br = port->br;
+
+ spin_lock(&br->multicast_lock);
+ __br_multicast_enable_port(port);
spin_unlock(&br->multicast_lock);
}
@@ -1633,6 +1639,21 @@ static void br_multicast_err_count(const struct net_bridge *br,
u64_stats_update_end(&pstats->syncp);
}
+static void br_multicast_pim(struct net_bridge *br,
+ struct net_bridge_port *port,
+ const struct sk_buff *skb)
+{
+ unsigned int offset = skb_transport_offset(skb);
+ struct pimhdr *pimhdr, _pimhdr;
+
+ pimhdr = skb_header_pointer(skb, offset, sizeof(_pimhdr), &_pimhdr);
+ if (!pimhdr || pim_hdr_version(pimhdr) != PIM_VERSION ||
+ pim_hdr_type(pimhdr) != PIM_TYPE_HELLO)
+ return;
+
+ br_multicast_mark_router(br, port);
+}
+
static int br_multicast_ipv4_rcv(struct net_bridge *br,
struct net_bridge_port *port,
struct sk_buff *skb,
@@ -1645,8 +1666,12 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br,
err = ip_mc_check_igmp(skb, &skb_trimmed);
if (err == -ENOMSG) {
- if (!ipv4_is_local_multicast(ip_hdr(skb)->daddr))
+ if (!ipv4_is_local_multicast(ip_hdr(skb)->daddr)) {
BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
+ } else if (pim_ipv4_all_pim_routers(ip_hdr(skb)->daddr)) {
+ if (ip_hdr(skb)->protocol == IPPROTO_PIM)
+ br_multicast_pim(br, port, skb);
+ }
return 0;
} else if (err < 0) {
br_multicast_err_count(br, port, skb->protocol);
@@ -1994,8 +2019,9 @@ static void br_multicast_start_querier(struct net_bridge *br,
int br_multicast_toggle(struct net_bridge *br, unsigned long val)
{
- int err = 0;
struct net_bridge_mdb_htable *mdb;
+ struct net_bridge_port *port;
+ int err = 0;
spin_lock_bh(&br->multicast_lock);
if (br->multicast_disabled == !val)
@@ -2023,10 +2049,9 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val)
goto rollback;
}
- br_multicast_start_querier(br, &br->ip4_own_query);
-#if IS_ENABLED(CONFIG_IPV6)
- br_multicast_start_querier(br, &br->ip6_own_query);
-#endif
+ br_multicast_open(br);
+ list_for_each_entry(port, &br->port_list, list)
+ __br_multicast_enable_port(port);
unlock:
spin_unlock_bh(&br->multicast_lock);
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 2fe9345..83d937f 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -46,7 +46,7 @@
#include <linux/sysctl.h>
#endif
-static int brnf_net_id __read_mostly;
+static unsigned int brnf_net_id __read_mostly;
struct brnf_net {
bool enabled;
@@ -561,8 +561,8 @@ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff
}
nf_bridge_push_encap_header(skb);
- NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_FORWARD, net, sk, skb,
- in, skb->dev, br_forward_finish, 1);
+ br_nf_hook_thresh(NF_BR_FORWARD, net, sk, skb, in, skb->dev,
+ br_forward_finish);
return 0;
}
@@ -845,8 +845,10 @@ static unsigned int ip_sabotage_in(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- if (skb->nf_bridge && !skb->nf_bridge->in_prerouting)
- return NF_STOP;
+ if (skb->nf_bridge && !skb->nf_bridge->in_prerouting) {
+ state->okfn(state->net, state->sk, skb);
+ return NF_STOLEN;
+ }
return NF_ACCEPT;
}
@@ -1016,10 +1018,10 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net,
/* We may already have this, but read-locks nest anyway */
rcu_read_lock();
- nf_hook_state_init(&state, elem, hook, NF_BR_PRI_BRNF + 1,
- NFPROTO_BRIDGE, indev, outdev, sk, net, okfn);
+ nf_hook_state_init(&state, hook, NFPROTO_BRIDGE, indev, outdev,
+ sk, net, okfn);
- ret = nf_hook_slow(skb, &state);
+ ret = nf_hook_slow(skb, &state, elem);
rcu_read_unlock();
if (ret == 1)
ret = okfn(net, sk, skb);
diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig
index 9cebf47..e7ef1a1 100644
--- a/net/bridge/netfilter/Kconfig
+++ b/net/bridge/netfilter/Kconfig
@@ -22,6 +22,7 @@
config NF_LOG_BRIDGE
tristate "Bridge packet logging"
+ select NF_LOG_COMMON
endif # NF_TABLES_BRIDGE
diff --git a/net/bridge/netfilter/ebt_arpreply.c b/net/bridge/netfilter/ebt_arpreply.c
index 070cf13..5929309 100644
--- a/net/bridge/netfilter/ebt_arpreply.c
+++ b/net/bridge/netfilter/ebt_arpreply.c
@@ -51,7 +51,8 @@ ebt_arpreply_tg(struct sk_buff *skb, const struct xt_action_param *par)
if (diptr == NULL)
return EBT_DROP;
- arp_send(ARPOP_REPLY, ETH_P_ARP, *siptr, (struct net_device *)par->in,
+ arp_send(ARPOP_REPLY, ETH_P_ARP, *siptr,
+ (struct net_device *)xt_in(par),
*diptr, shp, info->mac, shp);
return info->target;
diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c
index 9a11086..e88bd48 100644
--- a/net/bridge/netfilter/ebt_log.c
+++ b/net/bridge/netfilter/ebt_log.c
@@ -179,7 +179,7 @@ ebt_log_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ebt_log_info *info = par->targinfo;
struct nf_loginfo li;
- struct net *net = par->net;
+ struct net *net = xt_net(par);
li.type = NF_LOG_TYPE_LOG;
li.u.log.level = info->loglevel;
@@ -190,11 +190,12 @@ ebt_log_tg(struct sk_buff *skb, const struct xt_action_param *par)
* nf_log_packet() with NFT_LOG_TYPE_LOG here. --Pablo
*/
if (info->bitmask & EBT_LOG_NFLOG)
- nf_log_packet(net, NFPROTO_BRIDGE, par->hooknum, skb,
- par->in, par->out, &li, "%s", info->prefix);
+ nf_log_packet(net, NFPROTO_BRIDGE, xt_hooknum(par), skb,
+ xt_in(par), xt_out(par), &li, "%s",
+ info->prefix);
else
- ebt_log_packet(net, NFPROTO_BRIDGE, par->hooknum, skb, par->in,
- par->out, &li, info->prefix);
+ ebt_log_packet(net, NFPROTO_BRIDGE, xt_hooknum(par), skb,
+ xt_in(par), xt_out(par), &li, info->prefix);
return EBT_CONTINUE;
}
diff --git a/net/bridge/netfilter/ebt_nflog.c b/net/bridge/netfilter/ebt_nflog.c
index 5481615..c1dc486 100644
--- a/net/bridge/netfilter/ebt_nflog.c
+++ b/net/bridge/netfilter/ebt_nflog.c
@@ -23,16 +23,16 @@ static unsigned int
ebt_nflog_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ebt_nflog_info *info = par->targinfo;
+ struct net *net = xt_net(par);
struct nf_loginfo li;
- struct net *net = par->net;
li.type = NF_LOG_TYPE_ULOG;
li.u.ulog.copy_len = info->len;
li.u.ulog.group = info->group;
li.u.ulog.qthreshold = info->threshold;
- nf_log_packet(net, PF_BRIDGE, par->hooknum, skb, par->in,
- par->out, &li, "%s", info->prefix);
+ nf_log_packet(net, PF_BRIDGE, xt_hooknum(par), skb, xt_in(par),
+ xt_out(par), &li, "%s", info->prefix);
return EBT_CONTINUE;
}
diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c
index 2e7c4f9..8d2a85e 100644
--- a/net/bridge/netfilter/ebt_redirect.c
+++ b/net/bridge/netfilter/ebt_redirect.c
@@ -23,12 +23,12 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
if (!skb_make_writable(skb, 0))
return EBT_DROP;
- if (par->hooknum != NF_BR_BROUTING)
+ if (xt_hooknum(par) != NF_BR_BROUTING)
/* rcu_read_lock()ed by nf_hook_thresh */
ether_addr_copy(eth_hdr(skb)->h_dest,
- br_port_get_rcu(par->in)->br->dev->dev_addr);
+ br_port_get_rcu(xt_in(par))->br->dev->dev_addr);
else
- ether_addr_copy(eth_hdr(skb)->h_dest, par->in->dev_addr);
+ ether_addr_copy(eth_hdr(skb)->h_dest, xt_in(par)->dev_addr);
skb->pkt_type = PACKET_HOST;
return info->target;
}
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index ec94c6f..8fe36dc 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -53,7 +53,7 @@ static int ebt_broute(struct sk_buff *skb)
struct nf_hook_state state;
int ret;
- nf_hook_state_init(&state, NULL, NF_BR_BROUTING, INT_MIN,
+ nf_hook_state_init(&state, NF_BR_BROUTING,
NFPROTO_BRIDGE, skb->dev, NULL, NULL,
dev_net(skb->dev), NULL);
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index f5c11bb..1ab6014 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -194,12 +194,8 @@ unsigned int ebt_do_table(struct sk_buff *skb,
const struct ebt_table_info *private;
struct xt_action_param acpar;
- acpar.family = NFPROTO_BRIDGE;
- acpar.net = state->net;
- acpar.in = state->in;
- acpar.out = state->out;
+ acpar.state = state;
acpar.hotdrop = false;
- acpar.hooknum = hook;
read_lock_bh(&table->lock);
private = table->private;
diff --git a/net/bridge/netfilter/nf_log_bridge.c b/net/bridge/netfilter/nf_log_bridge.c
index 1663df5..c197b1f 100644
--- a/net/bridge/netfilter/nf_log_bridge.c
+++ b/net/bridge/netfilter/nf_log_bridge.c
@@ -24,21 +24,7 @@ static void nf_log_bridge_packet(struct net *net, u_int8_t pf,
const struct nf_loginfo *loginfo,
const char *prefix)
{
- switch (eth_hdr(skb)->h_proto) {
- case htons(ETH_P_IP):
- nf_log_packet(net, NFPROTO_IPV4, hooknum, skb, in, out,
- loginfo, "%s", prefix);
- break;
- case htons(ETH_P_IPV6):
- nf_log_packet(net, NFPROTO_IPV6, hooknum, skb, in, out,
- loginfo, "%s", prefix);
- break;
- case htons(ETH_P_ARP):
- case htons(ETH_P_RARP):
- nf_log_packet(net, NFPROTO_ARP, hooknum, skb, in, out,
- loginfo, "%s", prefix);
- break;
- }
+ nf_log_l2packet(net, pf, hooknum, skb, in, out, loginfo, prefix);
}
static struct nf_logger nf_bridge_logger __read_mostly = {
diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c
index ad47a92..5974dbc 100644
--- a/net/bridge/netfilter/nft_meta_bridge.c
+++ b/net/bridge/netfilter/nft_meta_bridge.c
@@ -23,7 +23,7 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr,
const struct nft_pktinfo *pkt)
{
const struct nft_meta *priv = nft_expr_priv(expr);
- const struct net_device *in = pkt->in, *out = pkt->out;
+ const struct net_device *in = nft_in(pkt), *out = nft_out(pkt);
u32 *dest = ®s->data[priv->dreg];
const struct net_bridge_port *p;
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index 4b3df6b..206dc26 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -315,17 +315,20 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr,
case htons(ETH_P_IP):
switch (priv->type) {
case NFT_REJECT_ICMP_UNREACH:
- nft_reject_br_send_v4_unreach(pkt->net, pkt->skb,
- pkt->in, pkt->hook,
+ nft_reject_br_send_v4_unreach(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt),
priv->icmp_code);
break;
case NFT_REJECT_TCP_RST:
- nft_reject_br_send_v4_tcp_reset(pkt->net, pkt->skb,
- pkt->in, pkt->hook);
+ nft_reject_br_send_v4_tcp_reset(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt));
break;
case NFT_REJECT_ICMPX_UNREACH:
- nft_reject_br_send_v4_unreach(pkt->net, pkt->skb,
- pkt->in, pkt->hook,
+ nft_reject_br_send_v4_unreach(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt),
nft_reject_icmp_code(priv->icmp_code));
break;
}
@@ -333,17 +336,20 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr,
case htons(ETH_P_IPV6):
switch (priv->type) {
case NFT_REJECT_ICMP_UNREACH:
- nft_reject_br_send_v6_unreach(pkt->net, pkt->skb,
- pkt->in, pkt->hook,
+ nft_reject_br_send_v6_unreach(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt),
priv->icmp_code);
break;
case NFT_REJECT_TCP_RST:
- nft_reject_br_send_v6_tcp_reset(pkt->net, pkt->skb,
- pkt->in, pkt->hook);
+ nft_reject_br_send_v6_tcp_reset(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt));
break;
case NFT_REJECT_ICMPX_UNREACH:
- nft_reject_br_send_v6_unreach(pkt->net, pkt->skb,
- pkt->in, pkt->hook,
+ nft_reject_br_send_v6_unreach(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt),
nft_reject_icmpv6_code(priv->icmp_code));
break;
}
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index d730a0f..2d38b6e 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -52,7 +52,7 @@ struct caif_net {
struct caif_device_entry_list caifdevs;
};
-static int caif_net_id;
+static unsigned int caif_net_id;
static int q_high = 50; /* Percent */
struct cfcnfg *get_cfcnfg(struct net *net)
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 8e999ff..8af9d25 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1549,24 +1549,31 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len,
struct sockaddr_can *addr = (struct sockaddr_can *)uaddr;
struct sock *sk = sock->sk;
struct bcm_sock *bo = bcm_sk(sk);
+ int ret = 0;
if (len < sizeof(*addr))
return -EINVAL;
- if (bo->bound)
- return -EISCONN;
+ lock_sock(sk);
+
+ if (bo->bound) {
+ ret = -EISCONN;
+ goto fail;
+ }
/* bind a device to this socket */
if (addr->can_ifindex) {
struct net_device *dev;
dev = dev_get_by_index(&init_net, addr->can_ifindex);
- if (!dev)
- return -ENODEV;
-
+ if (!dev) {
+ ret = -ENODEV;
+ goto fail;
+ }
if (dev->type != ARPHRD_CAN) {
dev_put(dev);
- return -ENODEV;
+ ret = -ENODEV;
+ goto fail;
}
bo->ifindex = dev->ifindex;
@@ -1577,17 +1584,24 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len,
bo->ifindex = 0;
}
- bo->bound = 1;
-
if (proc_dir) {
/* unique socket address as filename */
sprintf(bo->procname, "%lu", sock_i_ino(sk));
bo->bcm_proc_read = proc_create_data(bo->procname, 0644,
proc_dir,
&bcm_proc_fops, sk);
+ if (!bo->bcm_proc_read) {
+ ret = -ENOMEM;
+ goto fail;
+ }
}
- return 0;
+ bo->bound = 1;
+
+fail:
+ release_sock(sk);
+
+ return ret;
}
static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
diff --git a/net/ceph/ceph_fs.c b/net/ceph/ceph_fs.c
index 7d54e94..dcbe67f 100644
--- a/net/ceph/ceph_fs.c
+++ b/net/ceph/ceph_fs.c
@@ -34,7 +34,8 @@ void ceph_file_layout_from_legacy(struct ceph_file_layout *fl,
fl->stripe_count = le32_to_cpu(legacy->fl_stripe_count);
fl->object_size = le32_to_cpu(legacy->fl_object_size);
fl->pool_id = le32_to_cpu(legacy->fl_pg_pool);
- if (fl->pool_id == 0)
+ if (fl->pool_id == 0 && fl->stripe_unit == 0 &&
+ fl->stripe_count == 0 && fl->object_size == 0)
fl->pool_id = -1;
}
EXPORT_SYMBOL(ceph_file_layout_from_legacy);
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index d9bf7a1..e6ae15b 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -4094,6 +4094,7 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
osd_init(&osdc->homeless_osd);
osdc->homeless_osd.o_osdc = osdc;
osdc->homeless_osd.o_osd = CEPH_HOMELESS_OSD;
+ osdc->last_linger_id = CEPH_LINGER_ID_START;
osdc->linger_requests = RB_ROOT;
osdc->map_checks = RB_ROOT;
osdc->linger_map_checks = RB_ROOT;
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
index 00d2601..1a7c9a7 100644
--- a/net/ceph/pagevec.c
+++ b/net/ceph/pagevec.c
@@ -26,7 +26,7 @@ struct page **ceph_get_direct_page_vector(const void __user *data,
while (got < num_pages) {
rc = get_user_pages_unlocked(
(unsigned long)data + ((unsigned long)got * PAGE_SIZE),
- num_pages - got, write_page, 0, pages + got);
+ num_pages - got, pages + got, write_page ? FOLL_WRITE : 0);
if (rc < 0)
break;
BUG_ON(rc == 0);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index bfb973a..49816af 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -165,6 +165,7 @@ static struct sk_buff *skb_set_peeked(struct sk_buff *skb)
* __skb_try_recv_datagram - Receive a datagram skbuff
* @sk: socket
* @flags: MSG_ flags
+ * @destructor: invoked under the receive lock on successful dequeue
* @peeked: returns non-zero if this packet has been seen before
* @off: an offset in bytes to peek skb from. Returns an offset
* within an skb where data actually starts
@@ -197,6 +198,8 @@ static struct sk_buff *skb_set_peeked(struct sk_buff *skb)
* the standard around please.
*/
struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
+ void (*destructor)(struct sock *sk,
+ struct sk_buff *skb),
int *peeked, int *off, int *err,
struct sk_buff **last)
{
@@ -241,9 +244,11 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
}
atomic_inc(&skb->users);
- } else
+ } else {
__skb_unlink(skb, queue);
-
+ if (destructor)
+ destructor(sk, skb);
+ }
spin_unlock_irqrestore(&queue->lock, cpu_flags);
*off = _off;
return skb;
@@ -262,6 +267,8 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
EXPORT_SYMBOL(__skb_try_recv_datagram);
struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
+ void (*destructor)(struct sock *sk,
+ struct sk_buff *skb),
int *peeked, int *off, int *err)
{
struct sk_buff *skb, *last;
@@ -270,8 +277,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
do {
- skb = __skb_try_recv_datagram(sk, flags, peeked, off, err,
- &last);
+ skb = __skb_try_recv_datagram(sk, flags, destructor, peeked,
+ off, err, &last);
if (skb)
return skb;
@@ -290,7 +297,7 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags,
int peeked, off = 0;
return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
- &peeked, &off, err);
+ NULL, &peeked, &off, err);
}
EXPORT_SYMBOL(skb_recv_datagram);
diff --git a/net/core/dev.c b/net/core/dev.c
index 6aa43cd..f71b34a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1765,19 +1765,14 @@ EXPORT_SYMBOL_GPL(is_skb_forwardable);
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
{
- if (skb_orphan_frags(skb, GFP_ATOMIC) ||
- unlikely(!is_skb_forwardable(dev, skb))) {
- atomic_long_inc(&dev->rx_dropped);
- kfree_skb(skb);
- return NET_RX_DROP;
+ int ret = ____dev_forward_skb(dev, skb);
+
+ if (likely(!ret)) {
+ skb->protocol = eth_type_trans(skb, dev);
+ skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
}
- skb_scrub_packet(skb, true);
- skb->priority = 0;
- skb->protocol = eth_type_trans(skb, dev);
- skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
-
- return 0;
+ return ret;
}
EXPORT_SYMBOL_GPL(__dev_forward_skb);
@@ -1948,37 +1943,80 @@ static void netif_setup_tc(struct net_device *dev, unsigned int txq)
}
}
+int netdev_txq_to_tc(struct net_device *dev, unsigned int txq)
+{
+ if (dev->num_tc) {
+ struct netdev_tc_txq *tc = &dev->tc_to_txq[0];
+ int i;
+
+ for (i = 0; i < TC_MAX_QUEUE; i++, tc++) {
+ if ((txq - tc->offset) < tc->count)
+ return i;
+ }
+
+ return -1;
+ }
+
+ return 0;
+}
+
#ifdef CONFIG_XPS
static DEFINE_MUTEX(xps_map_mutex);
#define xmap_dereference(P) \
rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex))
-static struct xps_map *remove_xps_queue(struct xps_dev_maps *dev_maps,
- int cpu, u16 index)
+static bool remove_xps_queue(struct xps_dev_maps *dev_maps,
+ int tci, u16 index)
{
struct xps_map *map = NULL;
int pos;
if (dev_maps)
- map = xmap_dereference(dev_maps->cpu_map[cpu]);
+ map = xmap_dereference(dev_maps->cpu_map[tci]);
+ if (!map)
+ return false;
- for (pos = 0; map && pos < map->len; pos++) {
- if (map->queues[pos] == index) {
- if (map->len > 1) {
- map->queues[pos] = map->queues[--map->len];
- } else {
- RCU_INIT_POINTER(dev_maps->cpu_map[cpu], NULL);
- kfree_rcu(map, rcu);
- map = NULL;
- }
+ for (pos = map->len; pos--;) {
+ if (map->queues[pos] != index)
+ continue;
+
+ if (map->len > 1) {
+ map->queues[pos] = map->queues[--map->len];
break;
}
+
+ RCU_INIT_POINTER(dev_maps->cpu_map[tci], NULL);
+ kfree_rcu(map, rcu);
+ return false;
}
- return map;
+ return true;
}
-static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index)
+static bool remove_xps_queue_cpu(struct net_device *dev,
+ struct xps_dev_maps *dev_maps,
+ int cpu, u16 offset, u16 count)
+{
+ int num_tc = dev->num_tc ? : 1;
+ bool active = false;
+ int tci;
+
+ for (tci = cpu * num_tc; num_tc--; tci++) {
+ int i, j;
+
+ for (i = count, j = offset; i--; j++) {
+ if (!remove_xps_queue(dev_maps, cpu, j))
+ break;
+ }
+
+ active |= i < 0;
+ }
+
+ return active;
+}
+
+static void netif_reset_xps_queues(struct net_device *dev, u16 offset,
+ u16 count)
{
struct xps_dev_maps *dev_maps;
int cpu, i;
@@ -1990,21 +2028,16 @@ static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index)
if (!dev_maps)
goto out_no_maps;
- for_each_possible_cpu(cpu) {
- for (i = index; i < dev->num_tx_queues; i++) {
- if (!remove_xps_queue(dev_maps, cpu, i))
- break;
- }
- if (i == dev->num_tx_queues)
- active = true;
- }
+ for_each_possible_cpu(cpu)
+ active |= remove_xps_queue_cpu(dev, dev_maps, cpu,
+ offset, count);
if (!active) {
RCU_INIT_POINTER(dev->xps_maps, NULL);
kfree_rcu(dev_maps, rcu);
}
- for (i = index; i < dev->num_tx_queues; i++)
+ for (i = offset + (count - 1); count--; i--)
netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i),
NUMA_NO_NODE);
@@ -2012,6 +2045,11 @@ static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index)
mutex_unlock(&xps_map_mutex);
}
+static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index)
+{
+ netif_reset_xps_queues(dev, index, dev->num_tx_queues - index);
+}
+
static struct xps_map *expand_xps_map(struct xps_map *map,
int cpu, u16 index)
{
@@ -2051,20 +2089,28 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
u16 index)
{
struct xps_dev_maps *dev_maps, *new_dev_maps = NULL;
+ int i, cpu, tci, numa_node_id = -2;
+ int maps_sz, num_tc = 1, tc = 0;
struct xps_map *map, *new_map;
- int maps_sz = max_t(unsigned int, XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES);
- int cpu, numa_node_id = -2;
bool active = false;
+ if (dev->num_tc) {
+ num_tc = dev->num_tc;
+ tc = netdev_txq_to_tc(dev, index);
+ if (tc < 0)
+ return -EINVAL;
+ }
+
+ maps_sz = XPS_DEV_MAPS_SIZE(num_tc);
+ if (maps_sz < L1_CACHE_BYTES)
+ maps_sz = L1_CACHE_BYTES;
+
mutex_lock(&xps_map_mutex);
dev_maps = xmap_dereference(dev->xps_maps);
/* allocate memory for queue storage */
- for_each_online_cpu(cpu) {
- if (!cpumask_test_cpu(cpu, mask))
- continue;
-
+ for_each_cpu_and(cpu, cpu_online_mask, mask) {
if (!new_dev_maps)
new_dev_maps = kzalloc(maps_sz, GFP_KERNEL);
if (!new_dev_maps) {
@@ -2072,25 +2118,38 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
return -ENOMEM;
}
- map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) :
+ tci = cpu * num_tc + tc;
+ map = dev_maps ? xmap_dereference(dev_maps->cpu_map[tci]) :
NULL;
map = expand_xps_map(map, cpu, index);
if (!map)
goto error;
- RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map);
+ RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
}
if (!new_dev_maps)
goto out_no_new_maps;
for_each_possible_cpu(cpu) {
+ /* copy maps belonging to foreign traffic classes */
+ for (i = tc, tci = cpu * num_tc; dev_maps && i--; tci++) {
+ /* fill in the new device map from the old device map */
+ map = xmap_dereference(dev_maps->cpu_map[tci]);
+ RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
+ }
+
+ /* We need to explicitly update tci as prevous loop
+ * could break out early if dev_maps is NULL.
+ */
+ tci = cpu * num_tc + tc;
+
if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) {
/* add queue to CPU maps */
int pos = 0;
- map = xmap_dereference(new_dev_maps->cpu_map[cpu]);
+ map = xmap_dereference(new_dev_maps->cpu_map[tci]);
while ((pos < map->len) && (map->queues[pos] != index))
pos++;
@@ -2104,26 +2163,36 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
#endif
} else if (dev_maps) {
/* fill in the new device map from the old device map */
- map = xmap_dereference(dev_maps->cpu_map[cpu]);
- RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map);
+ map = xmap_dereference(dev_maps->cpu_map[tci]);
+ RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
}
+ /* copy maps belonging to foreign traffic classes */
+ for (i = num_tc - tc, tci++; dev_maps && --i; tci++) {
+ /* fill in the new device map from the old device map */
+ map = xmap_dereference(dev_maps->cpu_map[tci]);
+ RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
+ }
}
rcu_assign_pointer(dev->xps_maps, new_dev_maps);
/* Cleanup old maps */
- if (dev_maps) {
- for_each_possible_cpu(cpu) {
- new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]);
- map = xmap_dereference(dev_maps->cpu_map[cpu]);
+ if (!dev_maps)
+ goto out_no_old_maps;
+
+ for_each_possible_cpu(cpu) {
+ for (i = num_tc, tci = cpu * num_tc; i--; tci++) {
+ new_map = xmap_dereference(new_dev_maps->cpu_map[tci]);
+ map = xmap_dereference(dev_maps->cpu_map[tci]);
if (map && map != new_map)
kfree_rcu(map, rcu);
}
-
- kfree_rcu(dev_maps, rcu);
}
+ kfree_rcu(dev_maps, rcu);
+
+out_no_old_maps:
dev_maps = new_dev_maps;
active = true;
@@ -2138,11 +2207,12 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
/* removes queue from unused CPUs */
for_each_possible_cpu(cpu) {
- if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu))
- continue;
-
- if (remove_xps_queue(dev_maps, cpu, index))
- active = true;
+ for (i = tc, tci = cpu * num_tc; i--; tci++)
+ active |= remove_xps_queue(dev_maps, tci, index);
+ if (!cpumask_test_cpu(cpu, mask) || !cpu_online(cpu))
+ active |= remove_xps_queue(dev_maps, tci, index);
+ for (i = num_tc - tc, tci++; --i; tci++)
+ active |= remove_xps_queue(dev_maps, tci, index);
}
/* free map if not active */
@@ -2158,11 +2228,14 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
error:
/* remove any maps that we added */
for_each_possible_cpu(cpu) {
- new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]);
- map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) :
- NULL;
- if (new_map && new_map != map)
- kfree(new_map);
+ for (i = num_tc, tci = cpu * num_tc; i--; tci++) {
+ new_map = xmap_dereference(new_dev_maps->cpu_map[tci]);
+ map = dev_maps ?
+ xmap_dereference(dev_maps->cpu_map[tci]) :
+ NULL;
+ if (new_map && new_map != map)
+ kfree(new_map);
+ }
}
mutex_unlock(&xps_map_mutex);
@@ -2173,6 +2246,44 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
EXPORT_SYMBOL(netif_set_xps_queue);
#endif
+void netdev_reset_tc(struct net_device *dev)
+{
+#ifdef CONFIG_XPS
+ netif_reset_xps_queues_gt(dev, 0);
+#endif
+ dev->num_tc = 0;
+ memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq));
+ memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map));
+}
+EXPORT_SYMBOL(netdev_reset_tc);
+
+int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset)
+{
+ if (tc >= dev->num_tc)
+ return -EINVAL;
+
+#ifdef CONFIG_XPS
+ netif_reset_xps_queues(dev, offset, count);
+#endif
+ dev->tc_to_txq[tc].count = count;
+ dev->tc_to_txq[tc].offset = offset;
+ return 0;
+}
+EXPORT_SYMBOL(netdev_set_tc_queue);
+
+int netdev_set_num_tc(struct net_device *dev, u8 num_tc)
+{
+ if (num_tc > TC_MAX_QUEUE)
+ return -EINVAL;
+
+#ifdef CONFIG_XPS
+ netif_reset_xps_queues_gt(dev, 0);
+#endif
+ dev->num_tc = num_tc;
+ return 0;
+}
+EXPORT_SYMBOL(netdev_set_num_tc);
+
/*
* Routine to help set real_num_tx_queues. To avoid skbs mapped to queues
* greater then real_num_tx_queues stale skbs on the qdisc must be flushed.
@@ -2483,7 +2594,7 @@ int skb_checksum_help(struct sk_buff *skb)
goto out;
}
- *(__sum16 *)(skb->data + offset) = csum_fold(csum);
+ *(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0;
out_set_summed:
skb->ip_summed = CHECKSUM_NONE;
out:
@@ -2899,6 +3010,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d
}
return head;
}
+EXPORT_SYMBOL_GPL(validate_xmit_skb_list);
static void qdisc_pkt_len_init(struct sk_buff *skb)
{
@@ -3084,8 +3196,14 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
rcu_read_lock();
dev_maps = rcu_dereference(dev->xps_maps);
if (dev_maps) {
- map = rcu_dereference(
- dev_maps->cpu_map[skb->sender_cpu - 1]);
+ unsigned int tci = skb->sender_cpu - 1;
+
+ if (dev->num_tc) {
+ tci *= dev->num_tc;
+ tci += netdev_get_prio_tc_map(dev, skb->priority);
+ }
+
+ map = rcu_dereference(dev_maps->cpu_map[tci]);
if (map) {
if (map->len == 1)
queue_index = map->queues[0];
@@ -3709,7 +3827,7 @@ int netif_rx_ni(struct sk_buff *skb)
}
EXPORT_SYMBOL(netif_rx_ni);
-static void net_tx_action(struct softirq_action *h)
+static __latent_entropy void net_tx_action(struct softirq_action *h)
{
struct softnet_data *sd = this_cpu_ptr(&softnet_data);
@@ -4359,7 +4477,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
if (!(skb->dev->features & NETIF_F_GRO))
goto normal;
- if (skb_is_gso(skb) || skb_has_frag_list(skb) || skb->csum_bad)
+ if (skb->csum_bad)
goto normal;
gro_list_prepare(napi, skb);
@@ -4372,9 +4490,10 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
skb_set_network_header(skb, skb_gro_offset(skb));
skb_reset_mac_len(skb);
NAPI_GRO_CB(skb)->same_flow = 0;
- NAPI_GRO_CB(skb)->flush = 0;
+ NAPI_GRO_CB(skb)->flush = skb_is_gso(skb) || skb_has_frag_list(skb);
NAPI_GRO_CB(skb)->free = 0;
NAPI_GRO_CB(skb)->encap_mark = 0;
+ NAPI_GRO_CB(skb)->recursion_counter = 0;
NAPI_GRO_CB(skb)->is_fou = 0;
NAPI_GRO_CB(skb)->is_atomic = 1;
NAPI_GRO_CB(skb)->gro_remcsum_start = 0;
@@ -4779,26 +4898,36 @@ void __napi_schedule_irqoff(struct napi_struct *n)
}
EXPORT_SYMBOL(__napi_schedule_irqoff);
-void __napi_complete(struct napi_struct *n)
+bool __napi_complete(struct napi_struct *n)
{
BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
+ /* Some drivers call us directly, instead of calling
+ * napi_complete_done().
+ */
+ if (unlikely(test_bit(NAPI_STATE_IN_BUSY_POLL, &n->state)))
+ return false;
+
list_del_init(&n->poll_list);
smp_mb__before_atomic();
clear_bit(NAPI_STATE_SCHED, &n->state);
+ return true;
}
EXPORT_SYMBOL(__napi_complete);
-void napi_complete_done(struct napi_struct *n, int work_done)
+bool napi_complete_done(struct napi_struct *n, int work_done)
{
unsigned long flags;
/*
- * don't let napi dequeue from the cpu poll list
- * just in case its running on a different cpu
+ * 1) Don't let napi dequeue from the cpu poll list
+ * just in case its running on a different cpu.
+ * 2) If we are busy polling, do nothing here, we have
+ * the guarantee we will be called later.
*/
- if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state)))
- return;
+ if (unlikely(n->state & (NAPIF_STATE_NPSVC |
+ NAPIF_STATE_IN_BUSY_POLL)))
+ return false;
if (n->gro_list) {
unsigned long timeout = 0;
@@ -4820,6 +4949,7 @@ void napi_complete_done(struct napi_struct *n, int work_done)
__napi_complete(n);
local_irq_restore(flags);
}
+ return true;
}
EXPORT_SYMBOL(napi_complete_done);
@@ -4837,13 +4967,41 @@ static struct napi_struct *napi_by_id(unsigned int napi_id)
}
#if defined(CONFIG_NET_RX_BUSY_POLL)
+
#define BUSY_POLL_BUDGET 8
+
+static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
+{
+ int rc;
+
+ clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state);
+
+ local_bh_disable();
+
+ /* All we really want here is to re-enable device interrupts.
+ * Ideally, a new ndo_busy_poll_stop() could avoid another round.
+ */
+ rc = napi->poll(napi, BUSY_POLL_BUDGET);
+ netpoll_poll_unlock(have_poll_lock);
+ if (rc == BUSY_POLL_BUDGET)
+ __napi_schedule(napi);
+ local_bh_enable();
+ if (local_softirq_pending())
+ do_softirq();
+}
+
bool sk_busy_loop(struct sock *sk, int nonblock)
{
unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0;
+ int (*napi_poll)(struct napi_struct *napi, int budget);
int (*busy_poll)(struct napi_struct *dev);
+ void *have_poll_lock = NULL;
struct napi_struct *napi;
- int rc = false;
+ int rc;
+
+restart:
+ rc = false;
+ napi_poll = NULL;
rcu_read_lock();
@@ -4854,24 +5012,33 @@ bool sk_busy_loop(struct sock *sk, int nonblock)
/* Note: ndo_busy_poll method is optional in linux-4.5 */
busy_poll = napi->dev->netdev_ops->ndo_busy_poll;
- do {
+ preempt_disable();
+ for (;;) {
rc = 0;
local_bh_disable();
if (busy_poll) {
rc = busy_poll(napi);
- } else if (napi_schedule_prep(napi)) {
- void *have = netpoll_poll_lock(napi);
-
- if (test_bit(NAPI_STATE_SCHED, &napi->state)) {
- rc = napi->poll(napi, BUSY_POLL_BUDGET);
- trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
- if (rc == BUSY_POLL_BUDGET) {
- napi_complete_done(napi, rc);
- napi_schedule(napi);
- }
- }
- netpoll_poll_unlock(have);
+ goto count;
}
+ if (!napi_poll) {
+ unsigned long val = READ_ONCE(napi->state);
+
+ /* If multiple threads are competing for this napi,
+ * we avoid dirtying napi->state as much as we can.
+ */
+ if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
+ NAPIF_STATE_IN_BUSY_POLL))
+ goto count;
+ if (cmpxchg(&napi->state, val,
+ val | NAPIF_STATE_IN_BUSY_POLL |
+ NAPIF_STATE_SCHED) != val)
+ goto count;
+ have_poll_lock = netpoll_poll_lock(napi);
+ napi_poll = napi->poll;
+ }
+ rc = napi_poll(napi, BUSY_POLL_BUDGET);
+ trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
+count:
if (rc > 0)
__NET_ADD_STATS(sock_net(sk),
LINUX_MIB_BUSYPOLLRXPACKETS, rc);
@@ -4880,10 +5047,26 @@ bool sk_busy_loop(struct sock *sk, int nonblock)
if (rc == LL_FLUSH_FAILED)
break; /* permanent failure */
- cpu_relax();
- } while (!nonblock && skb_queue_empty(&sk->sk_receive_queue) &&
- !need_resched() && !busy_loop_timeout(end_time));
+ if (nonblock || !skb_queue_empty(&sk->sk_receive_queue) ||
+ busy_loop_timeout(end_time))
+ break;
+ if (unlikely(need_resched())) {
+ if (napi_poll)
+ busy_poll_stop(napi, have_poll_lock);
+ preempt_enable();
+ rcu_read_unlock();
+ cond_resched();
+ rc = !skb_queue_empty(&sk->sk_receive_queue);
+ if (rc || busy_loop_timeout(end_time))
+ return rc;
+ goto restart;
+ }
+ cpu_relax_lowlatency();
+ }
+ if (napi_poll)
+ busy_poll_stop(napi, have_poll_lock);
+ preempt_enable();
rc = !skb_queue_empty(&sk->sk_receive_queue);
out:
rcu_read_unlock();
@@ -4893,7 +5076,7 @@ EXPORT_SYMBOL(sk_busy_loop);
#endif /* CONFIG_NET_RX_BUSY_POLL */
-void napi_hash_add(struct napi_struct *napi)
+static void napi_hash_add(struct napi_struct *napi)
{
if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state) ||
test_and_set_bit(NAPI_STATE_HASHED, &napi->state))
@@ -4913,7 +5096,6 @@ void napi_hash_add(struct napi_struct *napi)
spin_unlock(&napi_hash_lock);
}
-EXPORT_SYMBOL_GPL(napi_hash_add);
/* Warning : caller is responsible to make sure rcu grace period
* is respected before freeing memory containing @napi
@@ -4961,7 +5143,6 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
list_add(&napi->dev_list, &dev->napi_list);
napi->dev = dev;
#ifdef CONFIG_NETPOLL
- spin_lock_init(&napi->poll_lock);
napi->poll_owner = -1;
#endif
set_bit(NAPI_STATE_SCHED, &napi->state);
@@ -5062,7 +5243,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
return work;
}
-static void net_rx_action(struct softirq_action *h)
+static __latent_entropy void net_rx_action(struct softirq_action *h)
{
struct softnet_data *sd = this_cpu_ptr(&softnet_data);
unsigned long time_limit = jiffies + 2;
@@ -7527,7 +7708,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
if (!dev->tx_queue_len) {
dev->priv_flags |= IFF_NO_QUEUE;
- dev->tx_queue_len = 1;
+ dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN;
}
dev->num_tx_queues = txqs;
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 9774898..e9b45567 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -119,6 +119,12 @@ tunable_strings[__ETHTOOL_TUNABLE_COUNT][ETH_GSTRING_LEN] = {
[ETHTOOL_TX_COPYBREAK] = "tx-copybreak",
};
+static const char
+phy_tunable_strings[__ETHTOOL_PHY_TUNABLE_COUNT][ETH_GSTRING_LEN] = {
+ [ETHTOOL_ID_UNSPEC] = "Unspec",
+ [ETHTOOL_PHY_DOWNSHIFT] = "phy-downshift",
+};
+
static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
{
struct ethtool_gfeatures cmd = {
@@ -227,6 +233,9 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset)
if (sset == ETH_SS_TUNABLES)
return ARRAY_SIZE(tunable_strings);
+ if (sset == ETH_SS_PHY_TUNABLES)
+ return ARRAY_SIZE(phy_tunable_strings);
+
if (sset == ETH_SS_PHY_STATS) {
if (dev->phydev)
return phy_get_sset_count(dev->phydev);
@@ -253,6 +262,8 @@ static void __ethtool_get_strings(struct net_device *dev,
sizeof(rss_hash_func_strings));
else if (stringset == ETH_SS_TUNABLES)
memcpy(data, tunable_strings, sizeof(tunable_strings));
+ else if (stringset == ETH_SS_PHY_TUNABLES)
+ memcpy(data, phy_tunable_strings, sizeof(phy_tunable_strings));
else if (stringset == ETH_SS_PHY_STATS) {
struct phy_device *phydev = dev->phydev;
@@ -2422,6 +2433,81 @@ static int ethtool_set_per_queue(struct net_device *dev, void __user *useraddr)
};
}
+static int ethtool_phy_tunable_valid(const struct ethtool_tunable *tuna)
+{
+ switch (tuna->id) {
+ case ETHTOOL_PHY_DOWNSHIFT:
+ if (tuna->len != sizeof(u8) ||
+ tuna->type_id != ETHTOOL_TUNABLE_U8)
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int get_phy_tunable(struct net_device *dev, void __user *useraddr)
+{
+ int ret;
+ struct ethtool_tunable tuna;
+ struct phy_device *phydev = dev->phydev;
+ void *data;
+
+ if (!(phydev && phydev->drv && phydev->drv->get_tunable))
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
+ return -EFAULT;
+ ret = ethtool_phy_tunable_valid(&tuna);
+ if (ret)
+ return ret;
+ data = kmalloc(tuna.len, GFP_USER);
+ if (!data)
+ return -ENOMEM;
+ ret = phydev->drv->get_tunable(phydev, &tuna, data);
+ if (ret)
+ goto out;
+ useraddr += sizeof(tuna);
+ ret = -EFAULT;
+ if (copy_to_user(useraddr, data, tuna.len))
+ goto out;
+ ret = 0;
+
+out:
+ kfree(data);
+ return ret;
+}
+
+static int set_phy_tunable(struct net_device *dev, void __user *useraddr)
+{
+ int ret;
+ struct ethtool_tunable tuna;
+ struct phy_device *phydev = dev->phydev;
+ void *data;
+
+ if (!(phydev && phydev->drv && phydev->drv->set_tunable))
+ return -EOPNOTSUPP;
+ if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
+ return -EFAULT;
+ ret = ethtool_phy_tunable_valid(&tuna);
+ if (ret)
+ return ret;
+ data = kmalloc(tuna.len, GFP_USER);
+ if (!data)
+ return -ENOMEM;
+ useraddr += sizeof(tuna);
+ ret = -EFAULT;
+ if (copy_from_user(data, useraddr, tuna.len))
+ goto out;
+ ret = phydev->drv->set_tunable(phydev, &tuna, data);
+
+out:
+ kfree(data);
+ return ret;
+}
+
/* The main entry point in this file. Called from net/core/dev_ioctl.c */
int dev_ethtool(struct net *net, struct ifreq *ifr)
@@ -2479,6 +2565,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_GET_TS_INFO:
case ETHTOOL_GEEE:
case ETHTOOL_GTUNABLE:
+ case ETHTOOL_PHY_GTUNABLE:
break;
default:
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
@@ -2684,6 +2771,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_SLINKSETTINGS:
rc = ethtool_set_link_ksettings(dev, useraddr);
break;
+ case ETHTOOL_PHY_GTUNABLE:
+ rc = get_phy_tunable(dev, useraddr);
+ break;
+ case ETHTOOL_PHY_STUNABLE:
+ rc = set_phy_tunable(dev, useraddr);
+ break;
default:
rc = -EOPNOTSUPP;
}
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index be4629c..b6791d9 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -18,6 +18,11 @@
#include <net/fib_rules.h>
#include <net/ip_tunnels.h>
+static const struct fib_kuid_range fib_kuid_range_unset = {
+ KUIDT_INIT(0),
+ KUIDT_INIT(~0),
+};
+
int fib_default_rule_add(struct fib_rules_ops *ops,
u32 pref, u32 table, u32 flags)
{
@@ -33,6 +38,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
r->table = table;
r->flags = flags;
r->fr_net = ops->fro_net;
+ r->uid_range = fib_kuid_range_unset;
r->suppress_prefixlen = -1;
r->suppress_ifgroup = -1;
@@ -172,6 +178,34 @@ void fib_rules_unregister(struct fib_rules_ops *ops)
}
EXPORT_SYMBOL_GPL(fib_rules_unregister);
+static int uid_range_set(struct fib_kuid_range *range)
+{
+ return uid_valid(range->start) && uid_valid(range->end);
+}
+
+static struct fib_kuid_range nla_get_kuid_range(struct nlattr **tb)
+{
+ struct fib_rule_uid_range *in;
+ struct fib_kuid_range out;
+
+ in = (struct fib_rule_uid_range *)nla_data(tb[FRA_UID_RANGE]);
+
+ out.start = make_kuid(current_user_ns(), in->start);
+ out.end = make_kuid(current_user_ns(), in->end);
+
+ return out;
+}
+
+static int nla_put_uid_range(struct sk_buff *skb, struct fib_kuid_range *range)
+{
+ struct fib_rule_uid_range out = {
+ from_kuid_munged(current_user_ns(), range->start),
+ from_kuid_munged(current_user_ns(), range->end)
+ };
+
+ return nla_put(skb, FRA_UID_RANGE, sizeof(out), &out);
+}
+
static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
struct flowi *fl, int flags,
struct fib_lookup_arg *arg)
@@ -193,6 +227,10 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
if (rule->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg))
goto out;
+ if (uid_lt(fl->flowi_uid, rule->uid_range.start) ||
+ uid_gt(fl->flowi_uid, rule->uid_range.end))
+ goto out;
+
ret = ops->match(rule, fl, flags);
out:
return (rule->flags & FIB_RULE_INVERT) ? !ret : ret;
@@ -305,6 +343,10 @@ static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
if (r->l3mdev != rule->l3mdev)
continue;
+ if (!uid_eq(r->uid_range.start, rule->uid_range.start) ||
+ !uid_eq(r->uid_range.end, rule->uid_range.end))
+ continue;
+
if (!ops->compare(r, frh, tb))
continue;
return 1;
@@ -429,6 +471,21 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh)
if (rule->l3mdev && rule->table)
goto errout_free;
+ if (tb[FRA_UID_RANGE]) {
+ if (current_user_ns() != net->user_ns) {
+ err = -EPERM;
+ goto errout_free;
+ }
+
+ rule->uid_range = nla_get_kuid_range(tb);
+
+ if (!uid_range_set(&rule->uid_range) ||
+ !uid_lte(rule->uid_range.start, rule->uid_range.end))
+ goto errout_free;
+ } else {
+ rule->uid_range = fib_kuid_range_unset;
+ }
+
if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
rule_exists(ops, frh, tb, rule)) {
err = -EEXIST;
@@ -497,6 +554,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
struct fib_rules_ops *ops = NULL;
struct fib_rule *rule, *tmp;
struct nlattr *tb[FRA_MAX+1];
+ struct fib_kuid_range range;
int err = -EINVAL;
if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh)))
@@ -516,6 +574,14 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
if (err < 0)
goto errout;
+ if (tb[FRA_UID_RANGE]) {
+ range = nla_get_kuid_range(tb);
+ if (!uid_range_set(&range))
+ goto errout;
+ } else {
+ range = fib_kuid_range_unset;
+ }
+
list_for_each_entry(rule, &ops->rules_list, list) {
if (frh->action && (frh->action != rule->action))
continue;
@@ -552,6 +618,11 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh)
(rule->l3mdev != nla_get_u8(tb[FRA_L3MDEV])))
continue;
+ if (uid_range_set(&range) &&
+ (!uid_eq(rule->uid_range.start, range.start) ||
+ !uid_eq(rule->uid_range.end, range.end)))
+ continue;
+
if (!ops->compare(rule, frh, tb))
continue;
@@ -619,7 +690,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
+ nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */
+ nla_total_size(4) /* FRA_FWMARK */
+ nla_total_size(4) /* FRA_FWMASK */
- + nla_total_size_64bit(8); /* FRA_TUN_ID */
+ + nla_total_size_64bit(8) /* FRA_TUN_ID */
+ + nla_total_size(sizeof(struct fib_kuid_range));
if (ops->nlmsg_payload)
payload += ops->nlmsg_payload(rule);
@@ -679,7 +751,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
(rule->tun_id &&
nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) ||
(rule->l3mdev &&
- nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)))
+ nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)) ||
+ (uid_range_set(&rule->uid_range) &&
+ nla_put_uid_range(skb, &rule->uid_range)))
goto nla_put_failure;
if (rule->suppress_ifgroup != -1) {
diff --git a/net/core/filter.c b/net/core/filter.c
index cd9e2ba..dece94f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1628,6 +1628,19 @@ static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
return dev_forward_skb(dev, skb);
}
+static inline int __bpf_rx_skb_no_mac(struct net_device *dev,
+ struct sk_buff *skb)
+{
+ int ret = ____dev_forward_skb(dev, skb);
+
+ if (likely(!ret)) {
+ skb->dev = dev;
+ ret = netif_rx(skb);
+ }
+
+ return ret;
+}
+
static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
{
int ret;
@@ -1647,6 +1660,51 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
return ret;
}
+static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev,
+ u32 flags)
+{
+ /* skb->mac_len is not set on normal egress */
+ unsigned int mlen = skb->network_header - skb->mac_header;
+
+ __skb_pull(skb, mlen);
+
+ /* At ingress, the mac header has already been pulled once.
+ * At egress, skb_pospull_rcsum has to be done in case that
+ * the skb is originated from ingress (i.e. a forwarded skb)
+ * to ensure that rcsum starts at net header.
+ */
+ if (!skb_at_tc_ingress(skb))
+ skb_postpull_rcsum(skb, skb_mac_header(skb), mlen);
+ skb_pop_mac_header(skb);
+ skb_reset_mac_len(skb);
+ return flags & BPF_F_INGRESS ?
+ __bpf_rx_skb_no_mac(dev, skb) : __bpf_tx_skb(dev, skb);
+}
+
+static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev,
+ u32 flags)
+{
+ bpf_push_mac_rcsum(skb);
+ return flags & BPF_F_INGRESS ?
+ __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
+}
+
+static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev,
+ u32 flags)
+{
+ switch (dev->type) {
+ case ARPHRD_TUNNEL:
+ case ARPHRD_TUNNEL6:
+ case ARPHRD_SIT:
+ case ARPHRD_IPGRE:
+ case ARPHRD_VOID:
+ case ARPHRD_NONE:
+ return __bpf_redirect_no_mac(skb, dev, flags);
+ default:
+ return __bpf_redirect_common(skb, dev, flags);
+ }
+}
+
BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
{
struct net_device *dev;
@@ -1675,10 +1733,7 @@ BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
return -ENOMEM;
}
- bpf_push_mac_rcsum(clone);
-
- return flags & BPF_F_INGRESS ?
- __bpf_rx_skb(dev, clone) : __bpf_tx_skb(dev, clone);
+ return __bpf_redirect(clone, dev, flags);
}
static const struct bpf_func_proto bpf_clone_redirect_proto = {
@@ -1722,10 +1777,7 @@ int skb_do_redirect(struct sk_buff *skb)
return -EINVAL;
}
- bpf_push_mac_rcsum(skb);
-
- return ri->flags & BPF_F_INGRESS ?
- __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
+ return __bpf_redirect(skb, dev, ri->flags);
}
static const struct bpf_func_proto bpf_redirect_proto = {
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 0cc607d..b481a4a 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -122,7 +122,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
struct flow_dissector_key_keyid *key_keyid;
bool skip_vlan = false;
u8 ip_proto = 0;
- bool ret = false;
+ bool ret;
if (!data) {
data = skb->data;
@@ -246,15 +246,13 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
case htons(ETH_P_8021AD):
case htons(ETH_P_8021Q): {
const struct vlan_hdr *vlan;
+ struct vlan_hdr _vlan;
+ bool vlan_tag_present = skb && skb_vlan_tag_present(skb);
- if (skb_vlan_tag_present(skb))
+ if (vlan_tag_present)
proto = skb->protocol;
- if (!skb_vlan_tag_present(skb) ||
- proto == cpu_to_be16(ETH_P_8021Q) ||
- proto == cpu_to_be16(ETH_P_8021AD)) {
- struct vlan_hdr _vlan;
-
+ if (!vlan_tag_present || eth_type_vlan(skb->protocol)) {
vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan),
data, hlen, &_vlan);
if (!vlan)
@@ -272,7 +270,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
FLOW_DISSECTOR_KEY_VLAN,
target_container);
- if (skb_vlan_tag_present(skb)) {
+ if (vlan_tag_present) {
key_vlan->vlan_id = skb_vlan_tag_get_id(skb);
key_vlan->vlan_priority =
(skb_vlan_tag_get_prio(skb) >> VLAN_PRIO_SHIFT);
@@ -551,12 +549,17 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
out_good:
ret = true;
-out_bad:
+ key_control->thoff = (u16)nhoff;
+out:
key_basic->n_proto = proto;
key_basic->ip_proto = ip_proto;
- key_control->thoff = (u16)nhoff;
return ret;
+
+out_bad:
+ ret = false;
+ key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen);
+ goto out;
}
EXPORT_SYMBOL(__skb_flow_dissect);
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 88fd642..03976e9 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -39,6 +39,8 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type)
return "MPLS";
case LWTUNNEL_ENCAP_ILA:
return "ILA";
+ case LWTUNNEL_ENCAP_SEG6:
+ return "SEG6";
case LWTUNNEL_ENCAP_IP6:
case LWTUNNEL_ENCAP_IP:
case LWTUNNEL_ENCAP_NONE:
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index d4fe286..b0c04cf 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1024,7 +1024,6 @@ static ssize_t show_trans_timeout(struct netdev_queue *queue,
return sprintf(buf, "%lu", trans_timeout);
}
-#ifdef CONFIG_XPS
static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
{
struct net_device *dev = queue->dev;
@@ -1036,6 +1035,21 @@ static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
return i;
}
+static ssize_t show_traffic_class(struct netdev_queue *queue,
+ struct netdev_queue_attribute *attribute,
+ char *buf)
+{
+ struct net_device *dev = queue->dev;
+ int index = get_netdev_queue_index(queue);
+ int tc = netdev_txq_to_tc(dev, index);
+
+ if (tc < 0)
+ return -EINVAL;
+
+ return sprintf(buf, "%u\n", tc);
+}
+
+#ifdef CONFIG_XPS
static ssize_t show_tx_maxrate(struct netdev_queue *queue,
struct netdev_queue_attribute *attribute,
char *buf)
@@ -1078,6 +1092,9 @@ static struct netdev_queue_attribute queue_tx_maxrate =
static struct netdev_queue_attribute queue_trans_timeout =
__ATTR(tx_timeout, S_IRUGO, show_trans_timeout, NULL);
+static struct netdev_queue_attribute queue_traffic_class =
+ __ATTR(traffic_class, S_IRUGO, show_traffic_class, NULL);
+
#ifdef CONFIG_BQL
/*
* Byte queue limits sysfs structures and functions.
@@ -1193,29 +1210,38 @@ static ssize_t show_xps_map(struct netdev_queue *queue,
struct netdev_queue_attribute *attribute, char *buf)
{
struct net_device *dev = queue->dev;
+ int cpu, len, num_tc = 1, tc = 0;
struct xps_dev_maps *dev_maps;
cpumask_var_t mask;
unsigned long index;
- int i, len;
if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
return -ENOMEM;
index = get_netdev_queue_index(queue);
+ if (dev->num_tc) {
+ num_tc = dev->num_tc;
+ tc = netdev_txq_to_tc(dev, index);
+ if (tc < 0)
+ return -EINVAL;
+ }
+
rcu_read_lock();
dev_maps = rcu_dereference(dev->xps_maps);
if (dev_maps) {
- for_each_possible_cpu(i) {
- struct xps_map *map =
- rcu_dereference(dev_maps->cpu_map[i]);
- if (map) {
- int j;
- for (j = 0; j < map->len; j++) {
- if (map->queues[j] == index) {
- cpumask_set_cpu(i, mask);
- break;
- }
+ for_each_possible_cpu(cpu) {
+ int i, tci = cpu * num_tc + tc;
+ struct xps_map *map;
+
+ map = rcu_dereference(dev_maps->cpu_map[tci]);
+ if (!map)
+ continue;
+
+ for (i = map->len; i--;) {
+ if (map->queues[i] == index) {
+ cpumask_set_cpu(cpu, mask);
+ break;
}
}
}
@@ -1263,6 +1289,7 @@ static struct netdev_queue_attribute xps_cpus_attribute =
static struct attribute *netdev_queue_default_attrs[] = {
&queue_trans_timeout.attr,
+ &queue_traffic_class.attr,
#ifdef CONFIG_XPS
&xps_cpus_attribute.attr,
&queue_tx_maxrate.attr,
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index b9243b1..35d37b1 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -55,7 +55,7 @@ static struct net_generic *net_alloc_generic(void)
return ng;
}
-static int net_assign_generic(struct net *net, int id, void *data)
+static int net_assign_generic(struct net *net, unsigned int id, void *data)
{
struct net_generic *ng, *old_ng;
@@ -122,8 +122,7 @@ static int ops_init(const struct pernet_operations *ops, struct net *net)
static void ops_free(const struct pernet_operations *ops, struct net *net)
{
if (ops->id && ops->size) {
- int id = *ops->id;
- kfree(net_generic(net, id));
+ kfree(net_generic(net, *ops->id));
}
}
@@ -215,13 +214,14 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id);
*/
int peernet2id_alloc(struct net *net, struct net *peer)
{
+ unsigned long flags;
bool alloc;
int id;
- spin_lock_bh(&net->nsid_lock);
+ spin_lock_irqsave(&net->nsid_lock, flags);
alloc = atomic_read(&peer->count) == 0 ? false : true;
id = __peernet2id_alloc(net, peer, &alloc);
- spin_unlock_bh(&net->nsid_lock);
+ spin_unlock_irqrestore(&net->nsid_lock, flags);
if (alloc && id >= 0)
rtnl_net_notifyid(net, RTM_NEWNSID, id);
return id;
@@ -230,11 +230,12 @@ int peernet2id_alloc(struct net *net, struct net *peer)
/* This function returns, if assigned, the id of a peer netns. */
int peernet2id(struct net *net, struct net *peer)
{
+ unsigned long flags;
int id;
- spin_lock_bh(&net->nsid_lock);
+ spin_lock_irqsave(&net->nsid_lock, flags);
id = __peernet2id(net, peer);
- spin_unlock_bh(&net->nsid_lock);
+ spin_unlock_irqrestore(&net->nsid_lock, flags);
return id;
}
EXPORT_SYMBOL(peernet2id);
@@ -249,17 +250,18 @@ bool peernet_has_id(struct net *net, struct net *peer)
struct net *get_net_ns_by_id(struct net *net, int id)
{
+ unsigned long flags;
struct net *peer;
if (id < 0)
return NULL;
rcu_read_lock();
- spin_lock_bh(&net->nsid_lock);
+ spin_lock_irqsave(&net->nsid_lock, flags);
peer = idr_find(&net->netns_ids, id);
if (peer)
get_net(peer);
- spin_unlock_bh(&net->nsid_lock);
+ spin_unlock_irqrestore(&net->nsid_lock, flags);
rcu_read_unlock();
return peer;
@@ -429,17 +431,17 @@ static void cleanup_net(struct work_struct *work)
for_each_net(tmp) {
int id;
- spin_lock_bh(&tmp->nsid_lock);
+ spin_lock_irq(&tmp->nsid_lock);
id = __peernet2id(tmp, net);
if (id >= 0)
idr_remove(&tmp->netns_ids, id);
- spin_unlock_bh(&tmp->nsid_lock);
+ spin_unlock_irq(&tmp->nsid_lock);
if (id >= 0)
rtnl_net_notifyid(tmp, RTM_DELNSID, id);
}
- spin_lock_bh(&net->nsid_lock);
+ spin_lock_irq(&net->nsid_lock);
idr_destroy(&net->netns_ids);
- spin_unlock_bh(&net->nsid_lock);
+ spin_unlock_irq(&net->nsid_lock);
}
rtnl_unlock();
@@ -568,6 +570,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct nlattr *tb[NETNSA_MAX + 1];
+ unsigned long flags;
struct net *peer;
int nsid, err;
@@ -588,15 +591,15 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh)
if (IS_ERR(peer))
return PTR_ERR(peer);
- spin_lock_bh(&net->nsid_lock);
+ spin_lock_irqsave(&net->nsid_lock, flags);
if (__peernet2id(net, peer) >= 0) {
- spin_unlock_bh(&net->nsid_lock);
+ spin_unlock_irqrestore(&net->nsid_lock, flags);
err = -EEXIST;
goto out;
}
err = alloc_netid(net, peer, nsid);
- spin_unlock_bh(&net->nsid_lock);
+ spin_unlock_irqrestore(&net->nsid_lock, flags);
if (err >= 0) {
rtnl_net_notifyid(net, RTM_NEWNSID, err);
err = 0;
@@ -718,10 +721,11 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
.idx = 0,
.s_idx = cb->args[0],
};
+ unsigned long flags;
- spin_lock_bh(&net->nsid_lock);
+ spin_lock_irqsave(&net->nsid_lock, flags);
idr_for_each(&net->netns_ids, rtnl_net_dumpid_one, &net_cb);
- spin_unlock_bh(&net->nsid_lock);
+ spin_unlock_irqrestore(&net->nsid_lock, flags);
cb->args[0] = net_cb.idx;
return skb->len;
@@ -876,7 +880,7 @@ static int register_pernet_operations(struct list_head *list,
}
return error;
}
- max_gen_ptrs = max_t(unsigned int, max_gen_ptrs, *ops->id);
+ max_gen_ptrs = max(max_gen_ptrs, *ops->id);
}
error = __register_pernet_operations(list, ops);
if (error) {
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 53599bd..9424673 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -171,12 +171,12 @@ static void poll_one_napi(struct napi_struct *napi)
static void poll_napi(struct net_device *dev)
{
struct napi_struct *napi;
+ int cpu = smp_processor_id();
list_for_each_entry(napi, &dev->napi_list, dev_list) {
- if (napi->poll_owner != smp_processor_id() &&
- spin_trylock(&napi->poll_lock)) {
+ if (cmpxchg(&napi->poll_owner, -1, cpu) == -1) {
poll_one_napi(napi);
- spin_unlock(&napi->poll_lock);
+ smp_store_release(&napi->poll_owner, -1);
}
}
}
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 5219a9e..8e69ce4 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -216,8 +216,8 @@
#define M_QUEUE_XMIT 2 /* Inject packet into qdisc */
/* If lock -- protects updating of if_list */
-#define if_lock(t) spin_lock(&(t->if_lock));
-#define if_unlock(t) spin_unlock(&(t->if_lock));
+#define if_lock(t) mutex_lock(&(t->if_lock));
+#define if_unlock(t) mutex_unlock(&(t->if_lock));
/* Used to help with determining the pkts on receive */
#define PKTGEN_MAGIC 0xbe9be955
@@ -413,7 +413,7 @@ struct pktgen_hdr {
};
-static int pg_net_id __read_mostly;
+static unsigned int pg_net_id __read_mostly;
struct pktgen_net {
struct net *net;
@@ -423,7 +423,7 @@ struct pktgen_net {
};
struct pktgen_thread {
- spinlock_t if_lock; /* for list of devices */
+ struct mutex if_lock; /* for list of devices */
struct list_head if_list; /* All device here */
struct list_head th_list;
struct task_struct *tsk;
@@ -2010,11 +2010,13 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d
{
struct pktgen_thread *t;
+ mutex_lock(&pktgen_thread_lock);
+
list_for_each_entry(t, &pn->pktgen_threads, th_list) {
struct pktgen_dev *pkt_dev;
- rcu_read_lock();
- list_for_each_entry_rcu(pkt_dev, &t->if_list, list) {
+ if_lock(t);
+ list_for_each_entry(pkt_dev, &t->if_list, list) {
if (pkt_dev->odev != dev)
continue;
@@ -2029,8 +2031,9 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d
dev->name);
break;
}
- rcu_read_unlock();
+ if_unlock(t);
}
+ mutex_unlock(&pktgen_thread_lock);
}
static int pktgen_device_event(struct notifier_block *unused,
@@ -3762,7 +3765,7 @@ static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn)
return -ENOMEM;
}
- spin_lock_init(&t->if_lock);
+ mutex_init(&t->if_lock);
t->cpu = cpu;
INIT_LIST_HEAD(&t->if_list);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index fb7348f..db313ec 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -275,6 +275,7 @@ int rtnl_unregister(int protocol, int msgtype)
rtnl_msg_handlers[protocol][msgindex].doit = NULL;
rtnl_msg_handlers[protocol][msgindex].dumpit = NULL;
+ rtnl_msg_handlers[protocol][msgindex].calcit = NULL;
return 0;
}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1e3e008..0b2a6e9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3725,7 +3725,6 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk)
err = SKB_EXT_ERR(skb_next)->ee.ee_errno;
spin_unlock_irqrestore(&q->lock, flags);
- sk->sk_err = err;
if (err)
sk->sk_error_report(sk);
diff --git a/net/core/sock.c b/net/core/sock.c
index d8e4532e..14e6145 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -453,7 +453,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
EXPORT_SYMBOL(sock_queue_rcv_skb);
int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
- const int nested, unsigned int trim_cap)
+ const int nested, unsigned int trim_cap, bool refcounted)
{
int rc = NET_RX_SUCCESS;
@@ -487,7 +487,8 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
bh_unlock_sock(sk);
out:
- sock_put(sk);
+ if (refcounted)
+ sock_put(sk);
return rc;
discard_and_relse:
kfree_skb(skb);
@@ -1543,6 +1544,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL);
newsk->sk_err = 0;
+ newsk->sk_err_soft = 0;
newsk->sk_priority = 0;
newsk->sk_incoming_cpu = raw_smp_processor_id();
atomic64_set(&newsk->sk_cookie, 0);
@@ -2078,14 +2080,14 @@ void __sk_flush_backlog(struct sock *sk)
*/
int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
int rc;
- DEFINE_WAIT(wait);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
- rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb);
+ rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb, &wait);
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
return rc;
}
EXPORT_SYMBOL(sk_wait_data);
@@ -2460,8 +2462,11 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_type = sock->type;
sk->sk_wq = sock->wq;
sock->sk = sk;
- } else
+ sk->sk_uid = SOCK_INODE(sock)->i_uid;
+ } else {
sk->sk_wq = NULL;
+ sk->sk_uid = make_kuid(sock_net(sk)->user_ns, 0);
+ }
rwlock_init(&sk->sk_callback_lock);
lockdep_set_class_and_name(&sk->sk_callback_lock,
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index e92b759..9a1a352 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -129,7 +129,6 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2)
return 0;
}
-EXPORT_SYMBOL(reuseport_add_sock);
static void reuseport_free_rcu(struct rcu_head *head)
{
diff --git a/net/core/stream.c b/net/core/stream.c
index 1086c8b..f575bcf 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -53,8 +53,8 @@ void sk_stream_write_space(struct sock *sk)
*/
int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct task_struct *tsk = current;
- DEFINE_WAIT(wait);
int done;
do {
@@ -68,13 +68,13 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
if (signal_pending(tsk))
return sock_intr_errno(*timeo_p);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending++;
done = sk_wait_event(sk, timeo_p,
!sk->sk_err &&
!((1 << sk->sk_state) &
- ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)));
- finish_wait(sk_sleep(sk), &wait);
+ ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending--;
} while (!done);
return 0;
@@ -94,16 +94,16 @@ static inline int sk_stream_closing(struct sock *sk)
void sk_stream_wait_close(struct sock *sk, long timeout)
{
if (timeout) {
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+ add_wait_queue(sk_sleep(sk), &wait);
do {
- prepare_to_wait(sk_sleep(sk), &wait,
- TASK_INTERRUPTIBLE);
- if (sk_wait_event(sk, &timeout, !sk_stream_closing(sk)))
+ if (sk_wait_event(sk, &timeout, !sk_stream_closing(sk), &wait))
break;
} while (!signal_pending(current) && timeout);
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
}
}
EXPORT_SYMBOL(sk_stream_wait_close);
@@ -119,16 +119,16 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
long vm_wait = 0;
long current_timeo = *timeo_p;
bool noblock = (*timeo_p ? false : true);
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
if (sk_stream_memory_free(sk))
current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2;
+ add_wait_queue(sk_sleep(sk), &wait);
+
while (1) {
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
goto do_error;
if (!*timeo_p) {
@@ -147,7 +147,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
sk_wait_event(sk, ¤t_timeo, sk->sk_err ||
(sk->sk_shutdown & SEND_SHUTDOWN) ||
(sk_stream_memory_free(sk) &&
- !vm_wait));
+ !vm_wait), &wait);
sk->sk_write_pending--;
if (vm_wait) {
@@ -161,7 +161,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
*timeo_p = current_timeo;
}
out:
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
return err;
do_error:
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index a957aca..fda321d 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -235,7 +235,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
{
const struct iphdr *iph = (struct iphdr *)skb->data;
const u8 offset = iph->ihl << 2;
- const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
+ const struct dccp_hdr *dh;
struct dccp_sock *dp;
struct inet_sock *inet;
const int type = icmp_hdr(skb)->type;
@@ -245,11 +245,13 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
int err;
struct net *net = dev_net(skb->dev);
- if (skb->len < offset + sizeof(*dh) ||
- skb->len < offset + __dccp_basic_hdr_len(dh)) {
- __ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
- return;
- }
+ /* Only need dccph_dport & dccph_sport which are the first
+ * 4 bytes in dccp header.
+ * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us.
+ */
+ BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
+ BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
+ dh = (struct dccp_hdr *)(skb->data + offset);
sk = __inet_lookup_established(net, &dccp_hashinfo,
iph->daddr, dh->dccph_dport,
@@ -862,7 +864,7 @@ static int dccp_v4_rcv(struct sk_buff *skb)
goto discard_and_relse;
nf_reset(skb);
- return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4);
+ return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted);
no_dccp_socket:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 32f9f1a..adfc790 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -70,7 +70,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
- const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
+ const struct dccp_hdr *dh;
struct dccp_sock *dp;
struct ipv6_pinfo *np;
struct sock *sk;
@@ -78,12 +78,13 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
__u64 seq;
struct net *net = dev_net(skb->dev);
- if (skb->len < offset + sizeof(*dh) ||
- skb->len < offset + __dccp_basic_hdr_len(dh)) {
- __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
- ICMP6_MIB_INERRORS);
- return;
- }
+ /* Only need dccph_dport & dccph_sport which are the first
+ * 4 bytes in dccp header.
+ * Our caller (icmpv6_notify()) already pulled 8 bytes for us.
+ */
+ BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
+ BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
+ dh = (struct dccp_hdr *)(skb->data + offset);
sk = __inet6_lookup_established(net, &dccp_hashinfo,
&hdr->daddr, dh->dccph_dport,
@@ -738,7 +739,8 @@ static int dccp_v6_rcv(struct sk_buff *skb)
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
- return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4) ? -1 : 0;
+ return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4,
+ refcounted) ? -1 : 0;
no_dccp_socket:
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
@@ -956,6 +958,7 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = {
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
+ .bind_conflict = inet6_csk_bind_conflict,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 41e65804..9fe25bf 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1009,6 +1009,10 @@ void dccp_close(struct sock *sk, long timeout)
__kfree_skb(skb);
}
+ /* If socket has been already reset kill it. */
+ if (sk->sk_state == DCCP_CLOSED)
+ goto adjudge_to_death;
+
if (data_was_unread) {
/* Unread data was tossed, send an appropriate Reset Code */
DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread);
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 13d6b1a..a90ed67 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1718,7 +1718,7 @@ static int dn_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
* See if there is data ready to read, sleep if there isn't
*/
for(;;) {
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
if (sk->sk_err)
goto out;
@@ -1749,11 +1749,11 @@ static int dn_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
goto out;
}
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
- sk_wait_event(sk, &timeo, dn_data_ready(sk, queue, flags, target));
+ sk_wait_event(sk, &timeo, dn_data_ready(sk, queue, flags, target), &wait);
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
}
skb_queue_walk_safe(queue, skb, n) {
@@ -1999,19 +1999,19 @@ static int dn_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
* size.
*/
if (dn_queue_too_long(scp, queue, flags)) {
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
if (flags & MSG_DONTWAIT) {
err = -EWOULDBLOCK;
goto out;
}
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
sk_wait_event(sk, &timeo,
- !dn_queue_too_long(scp, queue, flags));
+ !dn_queue_too_long(scp, queue, flags), &wait);
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
continue;
}
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index f983c10..8c5a479 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -62,6 +62,7 @@
#include <net/dsa.h>
#include <net/flow_dissector.h>
#include <linux/uaccess.h>
+#include <net/pkt_sched.h>
__setup("ether=", netdev_boot_setup);
@@ -359,7 +360,7 @@ void ether_setup(struct net_device *dev)
dev->min_mtu = ETH_MIN_MTU;
dev->max_mtu = ETH_DATA_LEN;
dev->addr_len = ETH_ALEN;
- dev->tx_queue_len = 1000; /* Ethernet wants good queues */
+ dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN;
dev->flags = IFF_BROADCAST|IFF_MULTICAST;
dev->priv_flags |= IFF_TX_SKB_SHARING;
@@ -440,7 +441,7 @@ struct sk_buff **eth_gro_receive(struct sk_buff **head,
skb_gro_pull(skb, sizeof(*eh));
skb_gro_postpull_rcsum(skb, eh, sizeof(*eh));
- pp = ptype->callbacks.gro_receive(head, skb);
+ pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
out_unlock:
rcu_read_unlock();
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index 5ee1d43..4ebe2aa 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -300,10 +300,6 @@ static void hsr_forward_do(struct hsr_frame_info *frame)
static void check_local_dest(struct hsr_priv *hsr, struct sk_buff *skb,
struct hsr_frame_info *frame)
{
- struct net_device *master_dev;
-
- master_dev = hsr_port_get_hsr(hsr, HSR_PT_MASTER)->dev;
-
if (hsr_addr_is_self(hsr, eth_hdr(skb)->h_dest)) {
frame->is_local_exclusive = true;
skb->pkt_type = PACKET_HOST;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 1effc98..5ddf5cd 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -533,9 +533,9 @@ EXPORT_SYMBOL(inet_dgram_connect);
static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
{
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending += writebias;
/* Basic assumption: if someone sets sk->sk_err, he _must_
@@ -545,13 +545,12 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
*/
while ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
release_sock(sk);
- timeo = schedule_timeout(timeo);
+ timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
lock_sock(sk);
if (signal_pending(current) || !timeo)
break;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending -= writebias;
return timeo;
}
@@ -1391,7 +1390,7 @@ struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb)
skb_gro_pull(skb, sizeof(*iph));
skb_set_transport_header(skb, skb_gro_offset(skb));
- pp = ops->callbacks.gro_receive(head, skb);
+ pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
out_unlock:
rcu_read_unlock();
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c3b8047..d93eea8 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -610,6 +610,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
[RTA_FLOW] = { .type = NLA_U32 },
[RTA_ENCAP_TYPE] = { .type = NLA_U16 },
[RTA_ENCAP] = { .type = NLA_NESTED },
+ [RTA_UID] = { .type = NLA_U32 },
};
static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 31cef36..4cff74d 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2413,22 +2413,19 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
struct key_vector *l, **tp = &iter->tnode;
t_key key;
- /* use cache location of next-to-find key */
+ /* use cached location of previously found key */
if (iter->pos > 0 && pos >= iter->pos) {
- pos -= iter->pos;
key = iter->key;
} else {
- iter->pos = 0;
+ iter->pos = 1;
key = 0;
}
- while ((l = leaf_walk_rcu(tp, key)) != NULL) {
+ pos -= iter->pos;
+
+ while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) {
key = l->key + 1;
iter->pos++;
-
- if (--pos <= 0)
- break;
-
l = NULL;
/* handle unlikely case of a key wrap */
@@ -2437,7 +2434,7 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
}
if (l)
- iter->key = key; /* remember it */
+ iter->key = l->key; /* remember it */
else
iter->pos = 0; /* forget it */
@@ -2465,7 +2462,7 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos)
return fib_route_get_idx(iter, *pos);
iter->pos = 0;
- iter->key = 0;
+ iter->key = KEY_MAX;
return SEQ_START_TOKEN;
}
@@ -2474,7 +2471,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct fib_route_iter *iter = seq->private;
struct key_vector *l = NULL;
- t_key key = iter->key;
+ t_key key = iter->key + 1;
++*pos;
@@ -2483,7 +2480,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
l = leaf_walk_rcu(&iter->tnode, key);
if (l) {
- iter->key = l->key + 1;
+ iter->key = l->key;
iter->pos++;
} else {
iter->pos = 0;
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 6cb57bb..805f660 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -249,7 +249,7 @@ static struct sk_buff **fou_gro_receive(struct sock *sk,
if (!ops || !ops->callbacks.gro_receive)
goto out_unlock;
- pp = ops->callbacks.gro_receive(head, skb);
+ pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
out_unlock:
rcu_read_unlock();
@@ -441,7 +441,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk,
if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive))
goto out_unlock;
- pp = ops->callbacks.gro_receive(head, skb);
+ pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
flush = 0;
out_unlock:
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 96e0efe..d5cac99 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -229,7 +229,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
skb_gro_postpull_rcsum(skb, greh, grehlen);
- pp = ptype->callbacks.gro_receive(head, skb);
+ pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
flush = 0;
out_unlock:
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 38abe70..691146a 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -425,6 +425,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
fl4.daddr = daddr;
fl4.saddr = saddr;
fl4.flowi4_mark = mark;
+ fl4.flowi4_uid = sock_net_uid(net, NULL);
fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
fl4.flowi4_proto = IPPROTO_ICMP;
fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev);
@@ -473,11 +474,12 @@ static struct rtable *icmp_route_lookup(struct net *net,
param->replyopts.opt.opt.faddr : iph->saddr);
fl4->saddr = saddr;
fl4->flowi4_mark = mark;
+ fl4->flowi4_uid = sock_net_uid(net, NULL);
fl4->flowi4_tos = RT_TOS(tos);
fl4->flowi4_proto = IPPROTO_ICMP;
fl4->fl4_icmp_type = type;
fl4->fl4_icmp_code = code;
- fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev);
+ fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev);
security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
rt = __ip_route_output_key_hash(net, fl4,
@@ -502,7 +504,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
if (err)
goto relookup_failed;
- if (inet_addr_type_dev_table(net, skb_in->dev,
+ if (inet_addr_type_dev_table(net, skb_dst(skb_in)->dev,
fl4_dec.saddr) == RTN_LOCAL) {
rt2 = __ip_route_output_key(net, &fl4_dec);
if (IS_ERR(rt2))
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 61a9dee..d5d3ead 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -415,7 +415,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
sk->sk_protocol, inet_sk_flowi_flags(sk),
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
- htons(ireq->ir_num));
+ htons(ireq->ir_num), sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
@@ -452,7 +452,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
sk->sk_protocol, inet_sk_flowi_flags(sk),
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
- htons(ireq->ir_num));
+ htons(ireq->ir_num), sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 3b34024..4dea33e 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -861,10 +861,11 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
struct netlink_callback *cb,
const struct inet_diag_req_v2 *r, struct nlattr *bc)
{
- struct net *net = sock_net(skb->sk);
- int i, num, s_i, s_num;
- u32 idiag_states = r->idiag_states;
bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
+ struct net *net = sock_net(skb->sk);
+ u32 idiag_states = r->idiag_states;
+ int i, num, s_i, s_num;
+ struct sock *sk;
if (idiag_states & TCPF_SYN_RECV)
idiag_states |= TCPF_NEW_SYN_RECV;
@@ -877,7 +878,6 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
for (i = s_i; i < INET_LHTABLE_SIZE; i++) {
struct inet_listen_hashbucket *ilb;
- struct sock *sk;
num = 0;
ilb = &hashinfo->listening_hash[i];
@@ -922,13 +922,14 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
if (!(idiag_states & ~TCPF_LISTEN))
goto out;
+#define SKARR_SZ 16
for (i = s_i; i <= hashinfo->ehash_mask; i++) {
struct inet_ehash_bucket *head = &hashinfo->ehash[i];
spinlock_t *lock = inet_ehash_lockp(hashinfo, i);
struct hlist_nulls_node *node;
- struct sock *sk;
-
- num = 0;
+ struct sock *sk_arr[SKARR_SZ];
+ int num_arr[SKARR_SZ];
+ int idx, accum, res;
if (hlist_nulls_empty(&head->chain))
continue;
@@ -936,9 +937,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
if (i > s_i)
s_num = 0;
+next_chunk:
+ num = 0;
+ accum = 0;
spin_lock_bh(lock);
sk_nulls_for_each(sk, node, &head->chain) {
- int state, res;
+ int state;
if (!net_eq(sock_net(sk), net))
continue;
@@ -962,21 +966,35 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
if (!inet_diag_bc_sk(bc, sk))
goto next_normal;
- res = sk_diag_fill(sk, skb, r,
+ sock_hold(sk);
+ num_arr[accum] = num;
+ sk_arr[accum] = sk;
+ if (++accum == SKARR_SZ)
+ break;
+next_normal:
+ ++num;
+ }
+ spin_unlock_bh(lock);
+ res = 0;
+ for (idx = 0; idx < accum; idx++) {
+ if (res >= 0) {
+ res = sk_diag_fill(sk_arr[idx], skb, r,
sk_user_ns(NETLINK_CB(cb->skb).sk),
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
cb->nlh, net_admin);
- if (res < 0) {
- spin_unlock_bh(lock);
- goto done;
+ if (res < 0)
+ num = num_arr[idx];
}
-next_normal:
- ++num;
+ sock_gen_put(sk_arr[idx]);
}
-
- spin_unlock_bh(lock);
+ if (res < 0)
+ break;
cond_resched();
+ if (accum == SKARR_SZ) {
+ s_num = num + 1;
+ goto next_chunk;
+ }
}
done:
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 77c20a4..ca97835 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -25,6 +25,7 @@
#include <net/inet_hashtables.h>
#include <net/secure_seq.h>
#include <net/ip.h>
+#include <net/tcp.h>
#include <net/sock_reuseport.h>
static u32 inet_ehashfn(const struct net *net, const __be32 laddr,
@@ -172,7 +173,7 @@ EXPORT_SYMBOL_GPL(__inet_inherit_port);
static inline int compute_score(struct sock *sk, struct net *net,
const unsigned short hnum, const __be32 daddr,
- const int dif)
+ const int dif, bool exact_dif)
{
int score = -1;
struct inet_sock *inet = inet_sk(sk);
@@ -186,7 +187,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
return -1;
score += 4;
}
- if (sk->sk_bound_dev_if) {
+ if (sk->sk_bound_dev_if || exact_dif) {
if (sk->sk_bound_dev_if != dif)
return -1;
score += 4;
@@ -215,11 +216,12 @@ struct sock *__inet_lookup_listener(struct net *net,
unsigned int hash = inet_lhashfn(net, hnum);
struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
int score, hiscore = 0, matches = 0, reuseport = 0;
+ bool exact_dif = inet_exact_dif_match(net, skb);
struct sock *sk, *result = NULL;
u32 phash = 0;
sk_for_each_rcu(sk, &ilb->head) {
- score = compute_score(sk, net, hnum, daddr, dif);
+ score = compute_score(sk, net, hnum, daddr, dif, exact_dif);
if (score > hiscore) {
reuseport = sk->sk_reuseport;
if (reuseport) {
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 8b4ffd2..9f0a7b9 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -117,7 +117,7 @@ int ip_forward(struct sk_buff *skb)
if (opt->is_strictroute && rt->rt_uses_gateway)
goto sr_failed;
- IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS;
+ IPCB(skb)->flags |= IPSKB_FORWARDED;
mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
if (ip_exceeds_mtu(skb, mtu)) {
IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 576f705..78fd620 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -113,8 +113,8 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
static struct rtnl_link_ops ipgre_link_ops __read_mostly;
static int ipgre_tunnel_init(struct net_device *dev);
-static int ipgre_net_id __read_mostly;
-static int gre_tap_net_id __read_mostly;
+static unsigned int ipgre_net_id __read_mostly;
+static unsigned int gre_tap_net_id __read_mostly;
static void ipgre_err(struct sk_buff *skb, u32 info,
const struct tnl_ptk_info *tpi)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 05d1058..eaf720b 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -239,19 +239,23 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
struct sk_buff *segs;
int ret = 0;
- /* common case: fragmentation of segments is not allowed,
- * or seglen is <= mtu
+ /* common case: seglen is <= mtu
*/
- if (((IPCB(skb)->flags & IPSKB_FRAG_SEGS) == 0) ||
- skb_gso_validate_mtu(skb, mtu))
+ if (skb_gso_validate_mtu(skb, mtu))
return ip_finish_output2(net, sk, skb);
- /* Slowpath - GSO segment length is exceeding the dst MTU.
+ /* Slowpath - GSO segment length exceeds the egress MTU.
*
- * This can happen in two cases:
- * 1) TCP GRO packet, DF bit not set
- * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly
- * from host network stack.
+ * This can happen in several cases:
+ * - Forwarding of a TCP GRO skb, when DF flag is not set.
+ * - Forwarding of an skb that arrived on a virtualization interface
+ * (virtio-net/vhost/tap) with TSO/GSO size set by other network
+ * stack.
+ * - Local GSO skb transmitted on an NETIF_F_TSO tunnel stacked over an
+ * interface with a smaller MTU.
+ * - Arriving GRO skb (or GSO skb in a virtualized environment) that is
+ * bridged to a NETIF_F_TSO tunnel stacked over an interface with an
+ * insufficent MTU.
*/
features = netif_skb_features(skb);
BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
@@ -538,7 +542,6 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
{
struct iphdr *iph;
int ptr;
- struct net_device *dev;
struct sk_buff *skb2;
unsigned int mtu, hlen, left, len, ll_rs;
int offset;
@@ -546,8 +549,6 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
struct rtable *rt = skb_rtable(skb);
int err = 0;
- dev = rt->dst.dev;
-
/* for offloaded checksums cleanup checksum before fragmentation */
if (skb->ip_summed == CHECKSUM_PARTIAL &&
(err = skb_checksum_help(skb)))
@@ -1582,7 +1583,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
}
oif = arg->bound_dev_if;
- oif = oif ? : skb->skb_iif;
+ if (!oif && netif_index_is_l3_master(net, skb->skb_iif))
+ oif = skb->skb_iif;
flowi4_init_output(&fl4, oif,
IP4_REPLY_MARK(net, skb->mark),
@@ -1590,7 +1592,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol,
ip_reply_arg_flowi_flags(arg),
daddr, saddr,
- tcp_hdr(skb)->source, tcp_hdr(skb)->dest);
+ tcp_hdr(skb)->source, tcp_hdr(skb)->dest,
+ arg->uid);
security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index af49197..8b13881 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -97,8 +97,19 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb)
put_cmsg(msg, SOL_IP, IP_RETOPTS, opt->optlen, opt->__data);
}
+static void ip_cmsg_recv_fragsize(struct msghdr *msg, struct sk_buff *skb)
+{
+ int val;
+
+ if (IPCB(skb)->frag_max_size == 0)
+ return;
+
+ val = IPCB(skb)->frag_max_size;
+ put_cmsg(msg, SOL_IP, IP_RECVFRAGSIZE, sizeof(val), &val);
+}
+
static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
- int offset)
+ int tlen, int offset)
{
__wsum csum = skb->csum;
@@ -106,8 +117,9 @@ static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
return;
if (offset != 0)
- csum = csum_sub(csum, csum_partial(skb_transport_header(skb),
- offset, 0));
+ csum = csum_sub(csum,
+ csum_partial(skb_transport_header(skb) + tlen,
+ offset, 0));
put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum);
}
@@ -152,10 +164,10 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
put_cmsg(msg, SOL_IP, IP_ORIGDSTADDR, sizeof(sin), &sin);
}
-void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
- int offset)
+void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
+ struct sk_buff *skb, int tlen, int offset)
{
- struct inet_sock *inet = inet_sk(skb->sk);
+ struct inet_sock *inet = inet_sk(sk);
unsigned int flags = inet->cmsg_flags;
/* Ordered by supposed usage frequency */
@@ -216,7 +228,10 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
}
if (flags & IP_CMSG_CHECKSUM)
- ip_cmsg_recv_checksum(msg, skb, offset);
+ ip_cmsg_recv_checksum(msg, skb, tlen, offset);
+
+ if (flags & IP_CMSG_RECVFRAGSIZE)
+ ip_cmsg_recv_fragsize(msg, skb);
}
EXPORT_SYMBOL(ip_cmsg_recv_offset);
@@ -613,6 +628,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
case IP_MULTICAST_LOOP:
case IP_RECVORIGDSTADDR:
case IP_CHECKSUM:
+ case IP_RECVFRAGSIZE:
if (optlen >= sizeof(int)) {
if (get_user(val, (int __user *) optval))
return -EFAULT;
@@ -725,6 +741,14 @@ static int do_ip_setsockopt(struct sock *sk, int level,
}
}
break;
+ case IP_RECVFRAGSIZE:
+ if (sk->sk_type != SOCK_RAW && sk->sk_type != SOCK_DGRAM)
+ goto e_inval;
+ if (val)
+ inet->cmsg_flags |= IP_CMSG_RECVFRAGSIZE;
+ else
+ inet->cmsg_flags &= ~IP_CMSG_RECVFRAGSIZE;
+ break;
case IP_TOS: /* This sets both TOS and Precedence */
if (sk->sk_type == SOCK_STREAM) {
val &= ~INET_ECN_MASK;
@@ -1356,6 +1380,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
case IP_CHECKSUM:
val = (inet->cmsg_flags & IP_CMSG_CHECKSUM) != 0;
break;
+ case IP_RECVFRAGSIZE:
+ val = (inet->cmsg_flags & IP_CMSG_RECVFRAGSIZE) != 0;
+ break;
case IP_TOS:
val = inet->tos;
break;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 12a92e3..823abae 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -994,7 +994,7 @@ int ip_tunnel_get_iflink(const struct net_device *dev)
}
EXPORT_SYMBOL(ip_tunnel_get_iflink);
-int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
+int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
struct rtnl_link_ops *ops, char *devname)
{
struct ip_tunnel_net *itn = net_generic(net, ip_tnl_net_id);
@@ -1196,7 +1196,7 @@ void ip_tunnel_uninit(struct net_device *dev)
EXPORT_SYMBOL_GPL(ip_tunnel_uninit);
/* Do least required initialization, rest of init is done in tunnel_init call */
-void ip_tunnel_setup(struct net_device *dev, int net_id)
+void ip_tunnel_setup(struct net_device *dev, unsigned int net_id)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
tunnel->ip_tnl_net_id = net_id;
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 777bc18..fed3d29 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -63,7 +63,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
int pkt_len = skb->len - skb_inner_network_offset(skb);
struct net *net = dev_net(rt->dst.dev);
struct net_device *dev = skb->dev;
- int skb_iif = skb->skb_iif;
struct iphdr *iph;
int err;
@@ -73,16 +72,6 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
skb_dst_set(skb, &rt->dst);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
- if (skb_iif && !(df & htons(IP_DF))) {
- /* Arrived from an ingress interface, got encapsulated, with
- * fragmentation of encapulating frames allowed.
- * If skb is gso, the resulting encapsulated network segments
- * may exceed dst mtu.
- * Allow IP Fragmentation of segments.
- */
- IPCB(skb)->flags |= IPSKB_FRAG_SEGS;
- }
-
/* Push down and install the IP header. */
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 5d7944f..8b14f14 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -46,7 +46,7 @@
static struct rtnl_link_ops vti_link_ops __read_mostly;
-static int vti_net_id __read_mostly;
+static unsigned int vti_net_id __read_mostly;
static int vti_tunnel_init(struct net_device *dev);
static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index c939258..79489f0 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -121,7 +121,7 @@ static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
-static int ipip_net_id __read_mostly;
+static unsigned int ipip_net_id __read_mostly;
static int ipip_tunnel_init(struct net_device *dev);
static struct rtnl_link_ops ipip_link_ops __read_mostly;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 5f006e1..665505d 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -137,6 +137,9 @@ static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4,
.flags = FIB_LOOKUP_NOREF,
};
+ /* update flow if oif or iif point to device enslaved to l3mdev */
+ l3mdev_update_flow(net, flowi4_to_flowi(flp4));
+
err = fib_rules_lookup(net->ipv4.mr_rules_ops,
flowi4_to_flowi(flp4), 0, &arg);
if (err < 0)
@@ -163,7 +166,9 @@ static int ipmr_rule_action(struct fib_rule *rule, struct flowi *flp,
return -EINVAL;
}
- mrt = ipmr_get_table(rule->fr_net, rule->table);
+ arg->table = fib_rule_get_table(rule, arg);
+
+ mrt = ipmr_get_table(rule->fr_net, arg->table);
if (!mrt)
return -EAGAIN;
res->mrt = mrt;
@@ -1749,7 +1754,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
vif->dev->stats.tx_bytes += skb->len;
}
- IPCB(skb)->flags |= IPSKB_FORWARDED | IPSKB_FRAG_SEGS;
+ IPCB(skb)->flags |= IPSKB_FORWARDED;
/* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally
* not only before forwarding, but after forwarding on all output
@@ -1809,6 +1814,12 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt,
/* Wrong interface: drop packet and (maybe) send PIM assert. */
if (mrt->vif_table[vif].dev != skb->dev) {
+ struct net_device *mdev;
+
+ mdev = l3mdev_master_dev_rcu(mrt->vif_table[vif].dev);
+ if (mdev == skb->dev)
+ goto forward;
+
if (rt_is_output_route(skb_rtable(skb))) {
/* It is our own packet, looped back.
* Very complicated situation...
@@ -2053,7 +2064,7 @@ static int pim_rcv(struct sk_buff *skb)
goto drop;
pim = (struct pimreghdr *)skb_transport_header(skb);
- if (pim->type != ((PIM_VERSION << 4) | (PIM_REGISTER)) ||
+ if (pim->type != ((PIM_VERSION << 4) | (PIM_TYPE_REGISTER)) ||
(pim->flags & PIM_NULL_REGISTER) ||
(ip_compute_csum((void *)pim, sizeof(*pim)) != 0 &&
csum_fold(skb_checksum(skb, 0, skb->len, 0))))
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index d613309..c11eb17 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -25,6 +25,12 @@
To compile it as a module, choose M here. If unsure, say N.
+config NF_SOCKET_IPV4
+ tristate "IPv4 socket lookup support"
+ help
+ This option enables the IPv4 socket lookup infrastructure. This is
+ is required by the iptables socket match.
+
if NF_TABLES
config NF_TABLES_IPV4
@@ -54,6 +60,14 @@
help
This module enables IPv4 packet duplication support for nf_tables.
+config NFT_FIB_IPV4
+ select NFT_FIB
+ tristate "nf_tables fib / ip route lookup support"
+ help
+ This module enables IPv4 FIB lookups, e.g. for reverse path filtering.
+ It also allows query of the FIB for the route type, e.g. local, unicast,
+ multicast or blackhole.
+
endif # NF_TABLES_IPV4
config NF_TABLES_ARP
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 853328f..f462fee 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -14,6 +14,8 @@
# defrag
obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o
+obj-$(CONFIG_NF_SOCKET_IPV4) += nf_socket_ipv4.o
+
# logging
obj-$(CONFIG_NF_LOG_ARP) += nf_log_arp.o
obj-$(CONFIG_NF_LOG_IPV4) += nf_log_ipv4.o
@@ -34,6 +36,7 @@
obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
+obj-$(CONFIG_NFT_FIB_IPV4) += nft_fib_ipv4.o
obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o
obj-$(CONFIG_NFT_REDIR_IPV4) += nft_redir_ipv4.o
obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index b31df59..39004da 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -217,11 +217,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
*/
e = get_entry(table_base, private->hook_entry[hook]);
- acpar.net = state->net;
- acpar.in = state->in;
- acpar.out = state->out;
- acpar.hooknum = hook;
- acpar.family = NFPROTO_ARP;
+ acpar.state = state;
acpar.hotdrop = false;
arp = arp_hdr(skb);
@@ -809,7 +805,7 @@ static int get_info(struct net *net, void __user *user,
#endif
t = try_then_request_module(xt_find_table_lock(net, NFPROTO_ARP, name),
"arptable_%s", name);
- if (!IS_ERR_OR_NULL(t)) {
+ if (t) {
struct arpt_getinfo info;
const struct xt_table_info *private = t->private;
#ifdef CONFIG_COMPAT
@@ -838,7 +834,7 @@ static int get_info(struct net *net, void __user *user,
xt_table_unlock(t);
module_put(t->me);
} else
- ret = t ? PTR_ERR(t) : -ENOENT;
+ ret = -ENOENT;
#ifdef CONFIG_COMPAT
if (compat)
xt_compat_unlock(NFPROTO_ARP);
@@ -863,7 +859,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr,
get.name[sizeof(get.name) - 1] = '\0';
t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
- if (!IS_ERR_OR_NULL(t)) {
+ if (t) {
const struct xt_table_info *private = t->private;
if (get.size == private->size)
@@ -875,7 +871,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr,
module_put(t->me);
xt_table_unlock(t);
} else
- ret = t ? PTR_ERR(t) : -ENOENT;
+ ret = -ENOENT;
return ret;
}
@@ -902,8 +898,8 @@ static int __do_replace(struct net *net, const char *name,
t = try_then_request_module(xt_find_table_lock(net, NFPROTO_ARP, name),
"arptable_%s", name);
- if (IS_ERR_OR_NULL(t)) {
- ret = t ? PTR_ERR(t) : -ENOENT;
+ if (!t) {
+ ret = -ENOENT;
goto free_newinfo_counters_untrans;
}
@@ -1018,8 +1014,8 @@ static int do_add_counters(struct net *net, const void __user *user,
return PTR_ERR(paddc);
t = xt_find_table_lock(net, NFPROTO_ARP, tmp.name);
- if (IS_ERR_OR_NULL(t)) {
- ret = t ? PTR_ERR(t) : -ENOENT;
+ if (!t) {
+ ret = -ENOENT;
goto free;
}
@@ -1408,7 +1404,7 @@ static int compat_get_entries(struct net *net,
xt_compat_lock(NFPROTO_ARP);
t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
- if (!IS_ERR_OR_NULL(t)) {
+ if (t) {
const struct xt_table_info *private = t->private;
struct xt_table_info info;
@@ -1423,7 +1419,7 @@ static int compat_get_entries(struct net *net,
module_put(t->me);
xt_table_unlock(t);
} else
- ret = t ? PTR_ERR(t) : -ENOENT;
+ ret = -ENOENT;
xt_compat_unlock(NFPROTO_ARP);
return ret;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 7c00ce9..46815c8 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -261,11 +261,7 @@ ipt_do_table(struct sk_buff *skb,
acpar.fragoff = ntohs(ip->frag_off) & IP_OFFSET;
acpar.thoff = ip_hdrlen(skb);
acpar.hotdrop = false;
- acpar.net = state->net;
- acpar.in = state->in;
- acpar.out = state->out;
- acpar.family = NFPROTO_IPV4;
- acpar.hooknum = hook;
+ acpar.state = state;
IP_NF_ASSERT(table->valid_hooks & (1 << hook));
local_bh_disable();
@@ -977,7 +973,7 @@ static int get_info(struct net *net, void __user *user,
#endif
t = try_then_request_module(xt_find_table_lock(net, AF_INET, name),
"iptable_%s", name);
- if (!IS_ERR_OR_NULL(t)) {
+ if (t) {
struct ipt_getinfo info;
const struct xt_table_info *private = t->private;
#ifdef CONFIG_COMPAT
@@ -1007,7 +1003,7 @@ static int get_info(struct net *net, void __user *user,
xt_table_unlock(t);
module_put(t->me);
} else
- ret = t ? PTR_ERR(t) : -ENOENT;
+ ret = -ENOENT;
#ifdef CONFIG_COMPAT
if (compat)
xt_compat_unlock(AF_INET);
@@ -1032,7 +1028,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr,
get.name[sizeof(get.name) - 1] = '\0';
t = xt_find_table_lock(net, AF_INET, get.name);
- if (!IS_ERR_OR_NULL(t)) {
+ if (t) {
const struct xt_table_info *private = t->private;
if (get.size == private->size)
ret = copy_entries_to_user(private->size,
@@ -1043,7 +1039,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr,
module_put(t->me);
xt_table_unlock(t);
} else
- ret = t ? PTR_ERR(t) : -ENOENT;
+ ret = -ENOENT;
return ret;
}
@@ -1068,8 +1064,8 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
t = try_then_request_module(xt_find_table_lock(net, AF_INET, name),
"iptable_%s", name);
- if (IS_ERR_OR_NULL(t)) {
- ret = t ? PTR_ERR(t) : -ENOENT;
+ if (!t) {
+ ret = -ENOENT;
goto free_newinfo_counters_untrans;
}
@@ -1184,8 +1180,8 @@ do_add_counters(struct net *net, const void __user *user,
return PTR_ERR(paddc);
t = xt_find_table_lock(net, AF_INET, tmp.name);
- if (IS_ERR_OR_NULL(t)) {
- ret = t ? PTR_ERR(t) : -ENOENT;
+ if (!t) {
+ ret = -ENOENT;
goto free;
}
@@ -1630,7 +1626,7 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr,
xt_compat_lock(AF_INET);
t = xt_find_table_lock(net, AF_INET, get.name);
- if (!IS_ERR_OR_NULL(t)) {
+ if (t) {
const struct xt_table_info *private = t->private;
struct xt_table_info info;
ret = compat_table_info(private, &info);
@@ -1644,7 +1640,7 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr,
module_put(t->me);
xt_table_unlock(t);
} else
- ret = t ? PTR_ERR(t) : -ENOENT;
+ ret = -ENOENT;
xt_compat_unlock(AF_INET);
return ret;
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 4a9e6db..e6e206f 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -62,7 +62,7 @@ struct clusterip_config {
static const struct file_operations clusterip_proc_fops;
#endif
-static int clusterip_net_id __read_mostly;
+static unsigned int clusterip_net_id __read_mostly;
struct clusterip_net {
struct list_head configs;
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index da7f02a..34cfb9b 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -55,7 +55,8 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
range.min_proto = mr->range[0].min;
range.max_proto = mr->range[0].max;
- return nf_nat_masquerade_ipv4(skb, par->hooknum, &range, par->out);
+ return nf_nat_masquerade_ipv4(skb, xt_hooknum(par), &range,
+ xt_out(par));
}
static struct xt_target masquerade_tg_reg __read_mostly = {
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index 1d16c0f..8bd0d7b 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -34,7 +34,7 @@ static unsigned int
reject_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ipt_reject_info *reject = par->targinfo;
- int hook = par->hooknum;
+ int hook = xt_hooknum(par);
switch (reject->with) {
case IPT_ICMP_NET_UNREACHABLE:
@@ -59,7 +59,7 @@ reject_tg(struct sk_buff *skb, const struct xt_action_param *par)
nf_send_unreach(skb, ICMP_PKT_FILTERED, hook);
break;
case IPT_TCP_RESET:
- nf_send_reset(par->net, skb, hook);
+ nf_send_reset(xt_net(par), skb, hook);
case IPT_ICMP_ECHOREPLY:
/* Doesn't happen. */
break;
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index db5b875..3614116 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -263,12 +263,12 @@ static unsigned int
synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_synproxy_info *info = par->targinfo;
- struct net *net = par->net;
+ struct net *net = xt_net(par);
struct synproxy_net *snet = synproxy_pernet(net);
struct synproxy_options opts = {};
struct tcphdr *th, _th;
- if (nf_ip_checksum(skb, par->hooknum, par->thoff, IPPROTO_TCP))
+ if (nf_ip_checksum(skb, xt_hooknum(par), par->thoff, IPPROTO_TCP))
return NF_DROP;
th = skb_header_pointer(skb, par->thoff, sizeof(_th), &_th);
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index 78cc64e..59b4994 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -95,7 +95,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
flow.flowi4_tos = RT_TOS(iph->tos);
flow.flowi4_scope = RT_SCOPE_UNIVERSE;
- return rpfilter_lookup_reverse(par->net, &flow, par->in, info->flags) ^ invert;
+ return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert;
}
static int rpfilter_check(const struct xt_mtchk_param *par)
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 713c09a..7130ed5 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -336,47 +336,34 @@ MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET));
MODULE_ALIAS("ip_conntrack");
MODULE_LICENSE("GPL");
+static struct nf_conntrack_l4proto *builtin_l4proto4[] = {
+ &nf_conntrack_l4proto_tcp4,
+ &nf_conntrack_l4proto_udp4,
+ &nf_conntrack_l4proto_icmp,
+};
+
static int ipv4_net_init(struct net *net)
{
int ret = 0;
- ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_tcp4);
- if (ret < 0) {
- pr_err("nf_conntrack_tcp4: pernet registration failed\n");
- goto out_tcp;
- }
- ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udp4);
- if (ret < 0) {
- pr_err("nf_conntrack_udp4: pernet registration failed\n");
- goto out_udp;
- }
- ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_icmp);
- if (ret < 0) {
- pr_err("nf_conntrack_icmp4: pernet registration failed\n");
- goto out_icmp;
- }
+ ret = nf_ct_l4proto_pernet_register(net, builtin_l4proto4,
+ ARRAY_SIZE(builtin_l4proto4));
+ if (ret < 0)
+ return ret;
ret = nf_ct_l3proto_pernet_register(net, &nf_conntrack_l3proto_ipv4);
if (ret < 0) {
pr_err("nf_conntrack_ipv4: pernet registration failed\n");
- goto out_ipv4;
+ nf_ct_l4proto_pernet_unregister(net, builtin_l4proto4,
+ ARRAY_SIZE(builtin_l4proto4));
}
- return 0;
-out_ipv4:
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmp);
-out_icmp:
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp4);
-out_udp:
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp4);
-out_tcp:
return ret;
}
static void ipv4_net_exit(struct net *net)
{
nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv4);
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmp);
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp4);
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp4);
+ nf_ct_l4proto_pernet_unregister(net, builtin_l4proto4,
+ ARRAY_SIZE(builtin_l4proto4));
}
static struct pernet_operations ipv4_net_ops = {
@@ -410,37 +397,21 @@ static int __init nf_conntrack_l3proto_ipv4_init(void)
goto cleanup_pernet;
}
- ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_tcp4);
- if (ret < 0) {
- pr_err("nf_conntrack_ipv4: can't register tcp4 proto.\n");
+ ret = nf_ct_l4proto_register(builtin_l4proto4,
+ ARRAY_SIZE(builtin_l4proto4));
+ if (ret < 0)
goto cleanup_hooks;
- }
-
- ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udp4);
- if (ret < 0) {
- pr_err("nf_conntrack_ipv4: can't register udp4 proto.\n");
- goto cleanup_tcp4;
- }
-
- ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_icmp);
- if (ret < 0) {
- pr_err("nf_conntrack_ipv4: can't register icmpv4 proto.\n");
- goto cleanup_udp4;
- }
ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv4);
if (ret < 0) {
pr_err("nf_conntrack_ipv4: can't register ipv4 proto.\n");
- goto cleanup_icmpv4;
+ goto cleanup_l4proto;
}
return ret;
- cleanup_icmpv4:
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmp);
- cleanup_udp4:
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp4);
- cleanup_tcp4:
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp4);
+cleanup_l4proto:
+ nf_ct_l4proto_unregister(builtin_l4proto4,
+ ARRAY_SIZE(builtin_l4proto4));
cleanup_hooks:
nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops));
cleanup_pernet:
@@ -454,9 +425,8 @@ static void __exit nf_conntrack_l3proto_ipv4_fini(void)
{
synchronize_net();
nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv4);
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmp);
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp4);
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp4);
+ nf_ct_l4proto_unregister(builtin_l4proto4,
+ ARRAY_SIZE(builtin_l4proto4));
nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops));
unregister_pernet_subsys(&ipv4_net_ops);
nf_unregister_sockopt(&so_getorigdst);
diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c
new file mode 100644
index 0000000..a83d558
--- /dev/null
+++ b/net/ipv4/netfilter/nf_socket_ipv4.c
@@ -0,0 +1,163 @@
+/*
+ * Copyright (C) 2007-2008 BalaBit IT Ltd.
+ * Author: Krisztian Kovacs
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <net/tcp.h>
+#include <net/udp.h>
+#include <net/icmp.h>
+#include <net/sock.h>
+#include <net/inet_sock.h>
+#include <net/netfilter/nf_socket.h>
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack.h>
+#endif
+
+static int
+extract_icmp4_fields(const struct sk_buff *skb, u8 *protocol,
+ __be32 *raddr, __be32 *laddr,
+ __be16 *rport, __be16 *lport)
+{
+ unsigned int outside_hdrlen = ip_hdrlen(skb);
+ struct iphdr *inside_iph, _inside_iph;
+ struct icmphdr *icmph, _icmph;
+ __be16 *ports, _ports[2];
+
+ icmph = skb_header_pointer(skb, outside_hdrlen,
+ sizeof(_icmph), &_icmph);
+ if (icmph == NULL)
+ return 1;
+
+ switch (icmph->type) {
+ case ICMP_DEST_UNREACH:
+ case ICMP_SOURCE_QUENCH:
+ case ICMP_REDIRECT:
+ case ICMP_TIME_EXCEEDED:
+ case ICMP_PARAMETERPROB:
+ break;
+ default:
+ return 1;
+ }
+
+ inside_iph = skb_header_pointer(skb, outside_hdrlen +
+ sizeof(struct icmphdr),
+ sizeof(_inside_iph), &_inside_iph);
+ if (inside_iph == NULL)
+ return 1;
+
+ if (inside_iph->protocol != IPPROTO_TCP &&
+ inside_iph->protocol != IPPROTO_UDP)
+ return 1;
+
+ ports = skb_header_pointer(skb, outside_hdrlen +
+ sizeof(struct icmphdr) +
+ (inside_iph->ihl << 2),
+ sizeof(_ports), &_ports);
+ if (ports == NULL)
+ return 1;
+
+ /* the inside IP packet is the one quoted from our side, thus
+ * its saddr is the local address */
+ *protocol = inside_iph->protocol;
+ *laddr = inside_iph->saddr;
+ *lport = ports[0];
+ *raddr = inside_iph->daddr;
+ *rport = ports[1];
+
+ return 0;
+}
+
+static struct sock *
+nf_socket_get_sock_v4(struct net *net, struct sk_buff *skb, const int doff,
+ const u8 protocol,
+ const __be32 saddr, const __be32 daddr,
+ const __be16 sport, const __be16 dport,
+ const struct net_device *in)
+{
+ switch (protocol) {
+ case IPPROTO_TCP:
+ return inet_lookup(net, &tcp_hashinfo, skb, doff,
+ saddr, sport, daddr, dport,
+ in->ifindex);
+ case IPPROTO_UDP:
+ return udp4_lib_lookup(net, saddr, sport, daddr, dport,
+ in->ifindex);
+ }
+ return NULL;
+}
+
+struct sock *nf_sk_lookup_slow_v4(struct net *net, const struct sk_buff *skb,
+ const struct net_device *indev)
+{
+ __be32 uninitialized_var(daddr), uninitialized_var(saddr);
+ __be16 uninitialized_var(dport), uninitialized_var(sport);
+ const struct iphdr *iph = ip_hdr(skb);
+ struct sk_buff *data_skb = NULL;
+ u8 uninitialized_var(protocol);
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn const *ct;
+#endif
+ int doff = 0;
+
+ if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) {
+ struct udphdr _hdr, *hp;
+
+ hp = skb_header_pointer(skb, ip_hdrlen(skb),
+ sizeof(_hdr), &_hdr);
+ if (hp == NULL)
+ return NULL;
+
+ protocol = iph->protocol;
+ saddr = iph->saddr;
+ sport = hp->source;
+ daddr = iph->daddr;
+ dport = hp->dest;
+ data_skb = (struct sk_buff *)skb;
+ doff = iph->protocol == IPPROTO_TCP ?
+ ip_hdrlen(skb) + __tcp_hdrlen((struct tcphdr *)hp) :
+ ip_hdrlen(skb) + sizeof(*hp);
+
+ } else if (iph->protocol == IPPROTO_ICMP) {
+ if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr,
+ &sport, &dport))
+ return NULL;
+ } else {
+ return NULL;
+ }
+
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ /* Do the lookup with the original socket address in
+ * case this is a reply packet of an established
+ * SNAT-ted connection.
+ */
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct && !nf_ct_is_untracked(ct) &&
+ ((iph->protocol != IPPROTO_ICMP &&
+ ctinfo == IP_CT_ESTABLISHED_REPLY) ||
+ (iph->protocol == IPPROTO_ICMP &&
+ ctinfo == IP_CT_RELATED_REPLY)) &&
+ (ct->status & IPS_SRC_NAT_DONE)) {
+
+ daddr = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip;
+ dport = (iph->protocol == IPPROTO_TCP) ?
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port :
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port;
+ }
+#endif
+
+ return nf_socket_get_sock_v4(net, data_skb, doff, protocol, saddr,
+ daddr, sport, dport, indev);
+}
+EXPORT_SYMBOL_GPL(nf_sk_lookup_slow_v4);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Krisztian Kovacs, Balazs Scheidler");
+MODULE_DESCRIPTION("Netfilter IPv4 socket lookup infrastructure");
diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c
index bf855e6..0af3d8d 100644
--- a/net/ipv4/netfilter/nft_dup_ipv4.c
+++ b/net/ipv4/netfilter/nft_dup_ipv4.c
@@ -28,9 +28,9 @@ static void nft_dup_ipv4_eval(const struct nft_expr *expr,
struct in_addr gw = {
.s_addr = (__force __be32)regs->data[priv->sreg_addr],
};
- int oif = regs->data[priv->sreg_dev];
+ int oif = priv->sreg_dev ? regs->data[priv->sreg_dev] : -1;
- nf_dup_ipv4(pkt->net, pkt->skb, pkt->hook, &gw, oif);
+ nf_dup_ipv4(nft_net(pkt), pkt->skb, nft_hook(pkt), &gw, oif);
}
static int nft_dup_ipv4_init(const struct nft_ctx *ctx,
@@ -59,7 +59,9 @@ static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
struct nft_dup_ipv4 *priv = nft_expr_priv(expr);
- if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) ||
+ if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr))
+ goto nla_put_failure;
+ if (priv->sreg_dev &&
nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev))
goto nla_put_failure;
diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
new file mode 100644
index 0000000..1b49966
--- /dev/null
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -0,0 +1,238 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_fib.h>
+
+#include <net/ip_fib.h>
+#include <net/route.h>
+
+/* don't try to find route from mcast/bcast/zeronet */
+static __be32 get_saddr(__be32 addr)
+{
+ if (ipv4_is_multicast(addr) || ipv4_is_lbcast(addr) ||
+ ipv4_is_zeronet(addr))
+ return 0;
+ return addr;
+}
+
+static bool fib4_is_local(const struct sk_buff *skb)
+{
+ const struct rtable *rt = skb_rtable(skb);
+
+ return rt && (rt->rt_flags & RTCF_LOCAL);
+}
+
+#define DSCP_BITS 0xfc
+
+void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_fib *priv = nft_expr_priv(expr);
+ u32 *dst = ®s->data[priv->dreg];
+ const struct net_device *dev = NULL;
+ const struct iphdr *iph;
+ __be32 addr;
+
+ if (priv->flags & NFTA_FIB_F_IIF)
+ dev = nft_in(pkt);
+ else if (priv->flags & NFTA_FIB_F_OIF)
+ dev = nft_out(pkt);
+
+ iph = ip_hdr(pkt->skb);
+ if (priv->flags & NFTA_FIB_F_DADDR)
+ addr = iph->daddr;
+ else
+ addr = iph->saddr;
+
+ *dst = inet_dev_addr_type(nft_net(pkt), dev, addr);
+}
+EXPORT_SYMBOL_GPL(nft_fib4_eval_type);
+
+static int get_ifindex(const struct net_device *dev)
+{
+ return dev ? dev->ifindex : 0;
+}
+
+void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_fib *priv = nft_expr_priv(expr);
+ u32 *dest = ®s->data[priv->dreg];
+ const struct iphdr *iph;
+ struct fib_result res;
+ struct flowi4 fl4 = {
+ .flowi4_scope = RT_SCOPE_UNIVERSE,
+ .flowi4_iif = LOOPBACK_IFINDEX,
+ };
+ const struct net_device *oif;
+ struct net_device *found;
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+ int i;
+#endif
+
+ /*
+ * Do not set flowi4_oif, it restricts results (for example, asking
+ * for oif 3 will get RTN_UNICAST result even if the daddr exits
+ * on another interface.
+ *
+ * Search results for the desired outinterface instead.
+ */
+ if (priv->flags & NFTA_FIB_F_OIF)
+ oif = nft_out(pkt);
+ else if (priv->flags & NFTA_FIB_F_IIF)
+ oif = nft_in(pkt);
+ else
+ oif = NULL;
+
+ if (nft_hook(pkt) == NF_INET_PRE_ROUTING && fib4_is_local(pkt->skb)) {
+ nft_fib_store_result(dest, priv->result, pkt, LOOPBACK_IFINDEX);
+ return;
+ }
+
+ iph = ip_hdr(pkt->skb);
+ if (ipv4_is_multicast(iph->daddr) &&
+ ipv4_is_zeronet(iph->saddr) &&
+ ipv4_is_local_multicast(iph->daddr)) {
+ nft_fib_store_result(dest, priv->result, pkt,
+ get_ifindex(pkt->skb->dev));
+ return;
+ }
+
+ if (priv->flags & NFTA_FIB_F_MARK)
+ fl4.flowi4_mark = pkt->skb->mark;
+
+ fl4.flowi4_tos = iph->tos & DSCP_BITS;
+
+ if (priv->flags & NFTA_FIB_F_DADDR) {
+ fl4.daddr = iph->daddr;
+ fl4.saddr = get_saddr(iph->saddr);
+ } else {
+ fl4.daddr = iph->saddr;
+ fl4.saddr = get_saddr(iph->daddr);
+ }
+
+ if (fib_lookup(nft_net(pkt), &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE))
+ return;
+
+ switch (res.type) {
+ case RTN_UNICAST:
+ break;
+ case RTN_LOCAL: /* should not appear here, see fib4_is_local() above */
+ return;
+ default:
+ break;
+ }
+
+ if (!oif) {
+ found = FIB_RES_DEV(res);
+ goto ok;
+ }
+
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+ for (i = 0; i < res.fi->fib_nhs; i++) {
+ struct fib_nh *nh = &res.fi->fib_nh[i];
+
+ if (nh->nh_dev == oif) {
+ found = nh->nh_dev;
+ goto ok;
+ }
+ }
+ return;
+#else
+ found = FIB_RES_DEV(res);
+ if (found != oif)
+ return;
+#endif
+ok:
+ switch (priv->result) {
+ case NFT_FIB_RESULT_OIF:
+ *dest = found->ifindex;
+ break;
+ case NFT_FIB_RESULT_OIFNAME:
+ strncpy((char *)dest, found->name, IFNAMSIZ);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ break;
+ }
+}
+EXPORT_SYMBOL_GPL(nft_fib4_eval);
+
+static struct nft_expr_type nft_fib4_type;
+
+static const struct nft_expr_ops nft_fib4_type_ops = {
+ .type = &nft_fib4_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)),
+ .eval = nft_fib4_eval_type,
+ .init = nft_fib_init,
+ .dump = nft_fib_dump,
+ .validate = nft_fib_validate,
+};
+
+static const struct nft_expr_ops nft_fib4_ops = {
+ .type = &nft_fib4_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)),
+ .eval = nft_fib4_eval,
+ .init = nft_fib_init,
+ .dump = nft_fib_dump,
+ .validate = nft_fib_validate,
+};
+
+static const struct nft_expr_ops *
+nft_fib4_select_ops(const struct nft_ctx *ctx,
+ const struct nlattr * const tb[])
+{
+ enum nft_fib_result result;
+
+ if (!tb[NFTA_FIB_RESULT])
+ return ERR_PTR(-EINVAL);
+
+ result = htonl(nla_get_be32(tb[NFTA_FIB_RESULT]));
+
+ switch (result) {
+ case NFT_FIB_RESULT_OIF:
+ return &nft_fib4_ops;
+ case NFT_FIB_RESULT_OIFNAME:
+ return &nft_fib4_ops;
+ case NFT_FIB_RESULT_ADDRTYPE:
+ return &nft_fib4_type_ops;
+ default:
+ return ERR_PTR(-EOPNOTSUPP);
+ }
+}
+
+static struct nft_expr_type nft_fib4_type __read_mostly = {
+ .name = "fib",
+ .select_ops = &nft_fib4_select_ops,
+ .policy = nft_fib_policy,
+ .maxattr = NFTA_FIB_MAX,
+ .family = NFPROTO_IPV4,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_fib4_module_init(void)
+{
+ return nft_register_expr(&nft_fib4_type);
+}
+
+static void __exit nft_fib4_module_exit(void)
+{
+ nft_unregister_expr(&nft_fib4_type);
+}
+
+module_init(nft_fib4_module_init);
+module_exit(nft_fib4_module_exit);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
+MODULE_ALIAS_NFT_AF_EXPR(2, "fib");
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
index 51ced81..4f697e4 100644
--- a/net/ipv4/netfilter/nft_masq_ipv4.c
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -31,8 +31,8 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr,
range.max_proto.all =
*(__be16 *)®s->data[priv->sreg_proto_max];
}
- regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, pkt->hook,
- &range, pkt->out);
+ regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, nft_hook(pkt),
+ &range, nft_out(pkt));
}
static struct nft_expr_type nft_masq_ipv4_type;
diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c
index c09d438..16df049 100644
--- a/net/ipv4/netfilter/nft_redir_ipv4.c
+++ b/net/ipv4/netfilter/nft_redir_ipv4.c
@@ -35,8 +35,7 @@ static void nft_redir_ipv4_eval(const struct nft_expr *expr,
mr.range[0].flags |= priv->flags;
- regs->verdict.code = nf_nat_redirect_ipv4(pkt->skb, &mr,
- pkt->hook);
+ regs->verdict.code = nf_nat_redirect_ipv4(pkt->skb, &mr, nft_hook(pkt));
}
static struct nft_expr_type nft_redir_ipv4_type;
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
index 2c2553b..517ce93 100644
--- a/net/ipv4/netfilter/nft_reject_ipv4.c
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -27,10 +27,10 @@ static void nft_reject_ipv4_eval(const struct nft_expr *expr,
switch (priv->type) {
case NFT_REJECT_ICMP_UNREACH:
- nf_send_unreach(pkt->skb, priv->icmp_code, pkt->hook);
+ nf_send_unreach(pkt->skb, priv->icmp_code, nft_hook(pkt));
break;
case NFT_REJECT_TCP_RST:
- nf_send_reset(pkt->net, pkt->skb, pkt->hook);
+ nf_send_reset(nft_net(pkt), pkt->skb, nft_hook(pkt));
break;
default:
break;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 7cf7d6e..d11129f 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -789,7 +789,8 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE, sk->sk_protocol,
- inet_sk_flowi_flags(sk), faddr, saddr, 0, 0);
+ inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
+ sk->sk_uid);
security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
rt = ip_route_output_flow(net, &fl4, sk);
@@ -994,7 +995,7 @@ struct proto ping_prot = {
.init = ping_init_sock,
.close = ping_close,
.connect = ip4_datagram_connect,
- .disconnect = udp_disconnect,
+ .disconnect = __udp_disconnect,
.setsockopt = ip_setsockopt,
.getsockopt = ip_getsockopt,
.sendmsg = ping_v4_sendmsg,
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 03618ed..2300fae 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -606,7 +606,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
(inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
- daddr, saddr, 0, 0);
+ daddr, saddr, 0, 0, sk->sk_uid);
if (!inet->hdrincl) {
rfv.msg = msg;
@@ -695,12 +695,20 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
+ u32 tb_id = RT_TABLE_LOCAL;
int ret = -EINVAL;
int chk_addr_ret;
if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_in))
goto out;
- chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);
+
+ if (sk->sk_bound_dev_if)
+ tb_id = l3mdev_fib_table_by_index(sock_net(sk),
+ sk->sk_bound_dev_if) ? : tb_id;
+
+ chk_addr_ret = inet_addr_type_table(sock_net(sk), addr->sin_addr.s_addr,
+ tb_id);
+
ret = -EADDRNOTAVAIL;
if (addr->sin_addr.s_addr && chk_addr_ret != RTN_LOCAL &&
chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST)
@@ -920,7 +928,7 @@ int raw_abort(struct sock *sk, int err)
sk->sk_err = err;
sk->sk_error_report(sk);
- udp_disconnect(sk, 0);
+ __udp_disconnect(sk, 0);
release_sock(sk);
@@ -934,7 +942,7 @@ struct proto raw_prot = {
.close = raw_close,
.destroy = raw_destroy,
.connect = ip4_datagram_connect,
- .disconnect = udp_disconnect,
+ .disconnect = __udp_disconnect,
.ioctl = raw_ioctl,
.init = raw_init,
.setsockopt = raw_setsockopt,
diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c
index be93090..e1a51ca 100644
--- a/net/ipv4/raw_diag.c
+++ b/net/ipv4/raw_diag.c
@@ -79,10 +79,11 @@ static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2
* hashinfo->lock here.
*/
sock_hold(sk);
- break;
+ goto out_unlock;
}
}
}
+out_unlock:
read_unlock(&hashinfo->lock);
return sk ? sk : ERR_PTR(-ENOENT);
@@ -205,11 +206,14 @@ static int raw_diag_destroy(struct sk_buff *in_skb,
{
struct net *net = sock_net(in_skb->sk);
struct sock *sk;
+ int err;
sk = raw_sock_get(net, r);
if (IS_ERR(sk))
return PTR_ERR(sk);
- return sock_diag_destroy(sk, ECONNABORTED);
+ err = sock_diag_destroy(sk, ECONNABORTED);
+ sock_put(sk);
+ return err;
}
#endif
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 62d4d90..d37fc6f 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -507,7 +507,8 @@ void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
}
EXPORT_SYMBOL(__ip_select_ident);
-static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk,
+static void __build_flow_key(const struct net *net, struct flowi4 *fl4,
+ const struct sock *sk,
const struct iphdr *iph,
int oif, u8 tos,
u8 prot, u32 mark, int flow_flags)
@@ -523,7 +524,8 @@ static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk,
flowi4_init_output(fl4, oif, mark, tos,
RT_SCOPE_UNIVERSE, prot,
flow_flags,
- iph->daddr, iph->saddr, 0, 0);
+ iph->daddr, iph->saddr, 0, 0,
+ sock_net_uid(net, sk));
}
static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
@@ -535,7 +537,7 @@ static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
u8 prot = iph->protocol;
u32 mark = skb->mark;
- __build_flow_key(fl4, sk, iph, oif, tos, prot, mark, 0);
+ __build_flow_key(sock_net(sk), fl4, sk, iph, oif, tos, prot, mark, 0);
}
static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
@@ -552,7 +554,7 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk),
- daddr, inet->inet_saddr, 0, 0);
+ daddr, inet->inet_saddr, 0, 0, sk->sk_uid);
rcu_read_unlock();
}
@@ -753,7 +755,9 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
goto reject_redirect;
}
- n = ipv4_neigh_lookup(&rt->dst, NULL, &new_gw);
+ n = __ipv4_neigh_lookup(rt->dst.dev, new_gw);
+ if (!n)
+ n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev);
if (!IS_ERR(n)) {
if (!(n->nud_state & NUD_VALID)) {
neigh_event_send(n, NULL);
@@ -800,7 +804,7 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
rt = (struct rtable *) dst;
- __build_flow_key(&fl4, sk, iph, oif, tos, prot, mark, 0);
+ __build_flow_key(sock_net(sk), &fl4, sk, iph, oif, tos, prot, mark, 0);
__ip_do_redirect(rt, skb, &fl4, true);
}
@@ -1018,7 +1022,7 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
if (!mark)
mark = IP4_REPLY_MARK(net, skb->mark);
- __build_flow_key(&fl4, NULL, iph, oif,
+ __build_flow_key(net, &fl4, NULL, iph, oif,
RT_TOS(iph->tos), protocol, mark, flow_flags);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
@@ -1034,7 +1038,7 @@ static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
struct flowi4 fl4;
struct rtable *rt;
- __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+ __build_flow_key(sock_net(sk), &fl4, sk, iph, 0, 0, 0, 0, 0);
if (!fl4.flowi4_mark)
fl4.flowi4_mark = IP4_REPLY_MARK(sock_net(sk), skb->mark);
@@ -1053,6 +1057,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
struct rtable *rt;
struct dst_entry *odst = NULL;
bool new = false;
+ struct net *net = sock_net(sk);
bh_lock_sock(sk);
@@ -1066,7 +1071,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
goto out;
}
- __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+ __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0);
rt = (struct rtable *)odst;
if (odst->obsolete && !odst->ops->check(odst, 0)) {
@@ -1106,7 +1111,7 @@ void ipv4_redirect(struct sk_buff *skb, struct net *net,
struct flowi4 fl4;
struct rtable *rt;
- __build_flow_key(&fl4, NULL, iph, oif,
+ __build_flow_key(net, &fl4, NULL, iph, oif,
RT_TOS(iph->tos), protocol, mark, flow_flags);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
@@ -1121,9 +1126,10 @@ void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk)
const struct iphdr *iph = (const struct iphdr *) skb->data;
struct flowi4 fl4;
struct rtable *rt;
+ struct net *net = sock_net(sk);
- __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
- rt = __ip_route_output_key(sock_net(sk), &fl4);
+ __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0);
+ rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
__ip_do_redirect(rt, skb, &fl4, false);
ip_rt_put(rt);
@@ -1980,25 +1986,35 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
*/
if (ipv4_is_multicast(daddr)) {
struct in_device *in_dev = __in_dev_get_rcu(dev);
+ int our = 0;
- if (in_dev) {
- int our = ip_check_mc_rcu(in_dev, daddr, saddr,
- ip_hdr(skb)->protocol);
- if (our
+ if (in_dev)
+ our = ip_check_mc_rcu(in_dev, daddr, saddr,
+ ip_hdr(skb)->protocol);
+
+ /* check l3 master if no match yet */
+ if ((!in_dev || !our) && netif_is_l3_slave(dev)) {
+ struct in_device *l3_in_dev;
+
+ l3_in_dev = __in_dev_get_rcu(skb->dev);
+ if (l3_in_dev)
+ our = ip_check_mc_rcu(l3_in_dev, daddr, saddr,
+ ip_hdr(skb)->protocol);
+ }
+
+ res = -EINVAL;
+ if (our
#ifdef CONFIG_IP_MROUTE
- ||
- (!ipv4_is_local_multicast(daddr) &&
- IN_DEV_MFORWARD(in_dev))
+ ||
+ (!ipv4_is_local_multicast(daddr) &&
+ IN_DEV_MFORWARD(in_dev))
#endif
- ) {
- int res = ip_route_input_mc(skb, daddr, saddr,
- tos, dev, our);
- rcu_read_unlock();
- return res;
- }
+ ) {
+ res = ip_route_input_mc(skb, daddr, saddr,
+ tos, dev, our);
}
rcu_read_unlock();
- return -EINVAL;
+ return res;
}
res = ip_route_input_slow(skb, daddr, saddr, tos, dev);
rcu_read_unlock();
@@ -2266,7 +2282,8 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
res.fi = NULL;
res.table = NULL;
if (fl4->flowi4_oif &&
- !netif_index_is_l3_master(net, fl4->flowi4_oif)) {
+ (ipv4_is_multicast(fl4->daddr) ||
+ !netif_index_is_l3_master(net, fl4->flowi4_oif))) {
/* Apparently, routing tables are wrong. Assume,
that the destination is on link.
@@ -2493,6 +2510,11 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id,
nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark))
goto nla_put_failure;
+ if (!uid_eq(fl4->flowi4_uid, INVALID_UID) &&
+ nla_put_u32(skb, RTA_UID,
+ from_kuid_munged(current_user_ns(), fl4->flowi4_uid)))
+ goto nla_put_failure;
+
error = rt->dst.error;
if (rt_is_input_route(rt)) {
@@ -2545,6 +2567,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
int mark;
struct sk_buff *skb;
u32 table_id = RT_TABLE_MAIN;
+ kuid_t uid;
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
if (err < 0)
@@ -2572,6 +2595,10 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0;
iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0;
+ if (tb[RTA_UID])
+ uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID]));
+ else
+ uid = (iif ? INVALID_UID : current_uid());
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = dst;
@@ -2579,6 +2606,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
fl4.flowi4_tos = rtm->rtm_tos;
fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
fl4.flowi4_mark = mark;
+ fl4.flowi4_uid = uid;
if (iif) {
struct net_device *dev;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index e3c4043..0dc6286 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -372,7 +372,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
inet_sk_flowi_flags(sk),
opt->srr ? opt->faddr : ireq->ir_rmt_addr,
- ireq->ir_loc_addr, th->source, th->dest);
+ ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(&fl4));
rt = ip_route_output_key(sock_net(sk), &fl4);
if (IS_ERR(rt)) {
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 1cb67de..80bc36b 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -96,11 +96,11 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low
container_of(table->data, struct net, ipv4.ping_group_range.range);
unsigned int seq;
do {
- seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
+ seq = read_seqbegin(&net->ipv4.ping_group_range.lock);
*low = data[0];
*high = data[1];
- } while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
+ } while (read_seqretry(&net->ipv4.ping_group_range.lock, seq));
}
/* Update system visible IP port range */
@@ -109,10 +109,10 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig
kgid_t *data = table->data;
struct net *net =
container_of(table->data, struct net, ipv4.ping_group_range.range);
- write_seqlock(&net->ipv4.ip_local_ports.lock);
+ write_seqlock(&net->ipv4.ping_group_range.lock);
data[0] = low;
data[1] = high;
- write_sequnlock(&net->ipv4.ip_local_ports.lock);
+ write_sequnlock(&net->ipv4.ping_group_range.lock);
}
/* Validate changes from /proc interface. */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3251fe7..913f9bb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -279,7 +279,6 @@
#include <asm/uaccess.h>
#include <asm/ioctls.h>
-#include <asm/unaligned.h>
#include <net/busy_poll.h>
int sysctl_tcp_min_tso_segs __read_mostly = 2;
@@ -405,7 +404,6 @@ void tcp_init_sock(struct sock *sk)
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_clamp = ~0;
tp->mss_cache = TCP_MSS_DEFAULT;
- u64_stats_init(&tp->syncp);
tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering;
tcp_enable_early_retrans(tp);
@@ -1164,7 +1162,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
err = -EPIPE;
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
- goto out_err;
+ goto do_error;
sg = !!(sk->sk_route_caps & NETIF_F_SG);
@@ -1241,7 +1239,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
if (!skb_can_coalesce(skb, i, pfrag->page,
pfrag->offset)) {
- if (i == sysctl_max_skb_frags || !sg) {
+ if (i >= sysctl_max_skb_frags || !sg) {
tcp_mark_push(tp, skb);
goto new_segment;
}
@@ -2302,7 +2300,7 @@ EXPORT_SYMBOL(tcp_disconnect);
static inline bool tcp_can_repair_sock(const struct sock *sk)
{
return ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) &&
- ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_ESTABLISHED));
+ (sk->sk_state != TCP_LISTEN);
}
static int tcp_repair_set_window(struct tcp_sock *tp, char __user *optbuf, int len)
@@ -2710,9 +2708,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 now = tcp_time_stamp, intv;
- unsigned int start;
- int notsent_bytes;
u64 rate64;
+ bool slow;
u32 rate;
memset(info, 0, sizeof(*info));
@@ -2721,6 +2718,27 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_state = sk_state_load(sk);
+ /* Report meaningful fields for all TCP states, including listeners */
+ rate = READ_ONCE(sk->sk_pacing_rate);
+ rate64 = rate != ~0U ? rate : ~0ULL;
+ info->tcpi_pacing_rate = rate64;
+
+ rate = READ_ONCE(sk->sk_max_pacing_rate);
+ rate64 = rate != ~0U ? rate : ~0ULL;
+ info->tcpi_max_pacing_rate = rate64;
+
+ info->tcpi_reordering = tp->reordering;
+ info->tcpi_snd_cwnd = tp->snd_cwnd;
+
+ if (info->tcpi_state == TCP_LISTEN) {
+ /* listeners aliased fields :
+ * tcpi_unacked -> Number of children ready for accept()
+ * tcpi_sacked -> max backlog
+ */
+ info->tcpi_unacked = sk->sk_ack_backlog;
+ info->tcpi_sacked = sk->sk_max_ack_backlog;
+ return;
+ }
info->tcpi_ca_state = icsk->icsk_ca_state;
info->tcpi_retransmits = icsk->icsk_retransmits;
info->tcpi_probes = icsk->icsk_probes_out;
@@ -2748,13 +2766,9 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_snd_mss = tp->mss_cache;
info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss;
- if (info->tcpi_state == TCP_LISTEN) {
- info->tcpi_unacked = sk->sk_ack_backlog;
- info->tcpi_sacked = sk->sk_max_ack_backlog;
- } else {
- info->tcpi_unacked = tp->packets_out;
- info->tcpi_sacked = tp->sacked_out;
- }
+ info->tcpi_unacked = tp->packets_out;
+ info->tcpi_sacked = tp->sacked_out;
+
info->tcpi_lost = tp->lost_out;
info->tcpi_retrans = tp->retrans_out;
info->tcpi_fackets = tp->fackets_out;
@@ -2768,34 +2782,24 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_rtt = tp->srtt_us >> 3;
info->tcpi_rttvar = tp->mdev_us >> 2;
info->tcpi_snd_ssthresh = tp->snd_ssthresh;
- info->tcpi_snd_cwnd = tp->snd_cwnd;
info->tcpi_advmss = tp->advmss;
- info->tcpi_reordering = tp->reordering;
info->tcpi_rcv_rtt = jiffies_to_usecs(tp->rcv_rtt_est.rtt)>>3;
info->tcpi_rcv_space = tp->rcvq_space.space;
info->tcpi_total_retrans = tp->total_retrans;
- rate = READ_ONCE(sk->sk_pacing_rate);
- rate64 = rate != ~0U ? rate : ~0ULL;
- put_unaligned(rate64, &info->tcpi_pacing_rate);
+ slow = lock_sock_fast(sk);
- rate = READ_ONCE(sk->sk_max_pacing_rate);
- rate64 = rate != ~0U ? rate : ~0ULL;
- put_unaligned(rate64, &info->tcpi_max_pacing_rate);
+ info->tcpi_bytes_acked = tp->bytes_acked;
+ info->tcpi_bytes_received = tp->bytes_received;
+ info->tcpi_notsent_bytes = max_t(int, 0, tp->write_seq - tp->snd_nxt);
- do {
- start = u64_stats_fetch_begin_irq(&tp->syncp);
- put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked);
- put_unaligned(tp->bytes_received, &info->tcpi_bytes_received);
- } while (u64_stats_fetch_retry_irq(&tp->syncp, start));
+ unlock_sock_fast(sk, slow);
+
info->tcpi_segs_out = tp->segs_out;
info->tcpi_segs_in = tp->segs_in;
- notsent_bytes = READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt);
- info->tcpi_notsent_bytes = max(0, notsent_bytes);
-
info->tcpi_min_rtt = tcp_min_rtt(tp);
info->tcpi_data_segs_in = tp->data_segs_in;
info->tcpi_data_segs_out = tp->data_segs_out;
@@ -2806,7 +2810,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
if (rate && intv) {
rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC;
do_div(rate64, intv);
- put_unaligned(rate64, &info->tcpi_delivery_rate);
+ info->tcpi_delivery_rate = rate64;
}
}
EXPORT_SYMBOL_GPL(tcp_get_info);
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 0ea66c2..b89bce4 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -14,6 +14,36 @@
* observed, or adjust the sending rate if it estimates there is a
* traffic policer, in order to keep the drop rate reasonable.
*
+ * Here is a state transition diagram for BBR:
+ *
+ * |
+ * V
+ * +---> STARTUP ----+
+ * | | |
+ * | V |
+ * | DRAIN ----+
+ * | | |
+ * | V |
+ * +---> PROBE_BW ----+
+ * | ^ | |
+ * | | | |
+ * | +----+ |
+ * | |
+ * +---- PROBE_RTT <--+
+ *
+ * A BBR flow starts in STARTUP, and ramps up its sending rate quickly.
+ * When it estimates the pipe is full, it enters DRAIN to drain the queue.
+ * In steady state a BBR flow only uses PROBE_BW and PROBE_RTT.
+ * A long-lived BBR flow spends the vast majority of its time remaining
+ * (repeatedly) in PROBE_BW, fully probing and utilizing the pipe's bandwidth
+ * in a fair manner, with a small, bounded queue. *If* a flow has been
+ * continuously sending for the entire min_rtt window, and hasn't seen an RTT
+ * sample that matches or decreases its min_rtt estimate for 10 seconds, then
+ * it briefly enters PROBE_RTT to cut inflight to a minimum value to re-probe
+ * the path's two-way propagation delay (min_rtt). When exiting PROBE_RTT, if
+ * we estimated that we reached the full bw of the pipe then we enter PROBE_BW;
+ * otherwise we enter STARTUP to try to fill the pipe.
+ *
* BBR is described in detail in:
* "BBR: Congestion-Based Congestion Control",
* Neal Cardwell, Yuchung Cheng, C. Stephen Gunn, Soheil Hassas Yeganeh,
@@ -51,7 +81,7 @@ enum bbr_mode {
BBR_STARTUP, /* ramp up sending rate rapidly to fill pipe */
BBR_DRAIN, /* drain any queue created during startup */
BBR_PROBE_BW, /* discover, share bw: pace around estimated bw */
- BBR_PROBE_RTT, /* cut cwnd to min to probe min_rtt */
+ BBR_PROBE_RTT, /* cut inflight to min to probe min_rtt */
};
/* BBR congestion control block */
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 10d728b..5113917 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -56,6 +56,7 @@ struct dctcp {
u32 next_seq;
u32 ce_state;
u32 delayed_ack_reserved;
+ u32 loss_cwnd;
};
static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */
@@ -96,6 +97,7 @@ static void dctcp_init(struct sock *sk)
ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
ca->delayed_ack_reserved = 0;
+ ca->loss_cwnd = 0;
ca->ce_state = 0;
dctcp_reset(tp, ca);
@@ -111,9 +113,10 @@ static void dctcp_init(struct sock *sk)
static u32 dctcp_ssthresh(struct sock *sk)
{
- const struct dctcp *ca = inet_csk_ca(sk);
+ struct dctcp *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ ca->loss_cwnd = tp->snd_cwnd;
return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
}
@@ -185,8 +188,8 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
static void dctcp_update_alpha(struct sock *sk, u32 flags)
{
- const struct tcp_sock *tp = tcp_sk(sk);
struct dctcp *ca = inet_csk_ca(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
u32 acked_bytes = tp->snd_una - ca->prior_snd_una;
/* If ack did not advance snd_una, count dupack as MSS size.
@@ -226,6 +229,13 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
WRITE_ONCE(ca->dctcp_alpha, alpha);
dctcp_reset(tp, ca);
}
+
+ if (flags & CA_ACK_ECE) {
+ unsigned int cwnd = dctcp_ssthresh(sk);
+
+ if (cwnd != tp->snd_cwnd)
+ tp->snd_cwnd = cwnd;
+ }
}
static void dctcp_state(struct sock *sk, u8 new_state)
@@ -308,12 +318,20 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
return 0;
}
+static u32 dctcp_cwnd_undo(struct sock *sk)
+{
+ const struct dctcp *ca = inet_csk_ca(sk);
+
+ return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
+}
+
static struct tcp_congestion_ops dctcp __read_mostly = {
.init = dctcp_init,
.in_ack_event = dctcp_update_alpha,
.cwnd_event = dctcp_cwnd_event,
.ssthresh = dctcp_ssthresh,
.cong_avoid = tcp_reno_cong_avoid,
+ .undo_cwnd = dctcp_cwnd_undo,
.set_state = dctcp_state,
.get_info = dctcp_get_info,
.flags = TCP_CONG_NEEDS_ECN,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index f2c59c8..a70046f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3351,9 +3351,7 @@ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack)
u32 delta = ack - tp->snd_una;
sock_owned_by_me((struct sock *)tp);
- u64_stats_update_begin_raw(&tp->syncp);
tp->bytes_acked += delta;
- u64_stats_update_end_raw(&tp->syncp);
tp->snd_una = ack;
}
@@ -3363,9 +3361,7 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
u32 delta = seq - tp->rcv_nxt;
sock_owned_by_me((struct sock *)tp);
- u64_stats_update_begin_raw(&tp->syncp);
tp->bytes_received += delta;
- u64_stats_update_end_raw(&tp->syncp);
tp->rcv_nxt = seq;
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 83b3d0b..5555eb8 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -86,7 +86,6 @@
int sysctl_tcp_tw_reuse __read_mostly;
int sysctl_tcp_low_latency __read_mostly;
-EXPORT_SYMBOL(sysctl_tcp_low_latency);
#ifdef CONFIG_TCP_MD5SIG
static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
@@ -692,6 +691,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
offsetof(struct inet_timewait_sock, tw_bound_dev_if));
arg.tos = ip_hdr(skb)->tos;
+ arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
local_bh_disable();
ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
skb, &TCP_SKB_CB(skb)->header.h4.opt,
@@ -712,7 +712,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
outside socket context is ugly, certainly. What can I do?
*/
-static void tcp_v4_send_ack(struct net *net,
+static void tcp_v4_send_ack(const struct sock *sk,
struct sk_buff *skb, u32 seq, u32 ack,
u32 win, u32 tsval, u32 tsecr, int oif,
struct tcp_md5sig_key *key,
@@ -727,6 +727,7 @@ static void tcp_v4_send_ack(struct net *net,
#endif
];
} rep;
+ struct net *net = sock_net(sk);
struct ip_reply_arg arg;
memset(&rep.th, 0, sizeof(struct tcphdr));
@@ -776,6 +777,7 @@ static void tcp_v4_send_ack(struct net *net,
if (oif)
arg.bound_dev_if = oif;
arg.tos = tos;
+ arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
local_bh_disable();
ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
skb, &TCP_SKB_CB(skb)->header.h4.opt,
@@ -791,7 +793,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
struct inet_timewait_sock *tw = inet_twsk(sk);
struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
- tcp_v4_send_ack(sock_net(sk), skb,
+ tcp_v4_send_ack(sk, skb,
tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcp_time_stamp + tcptw->tw_ts_offset,
@@ -819,7 +821,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
* exception of <SYN> segments, MUST be right-shifted by
* Rcv.Wind.Shift bits:
*/
- tcp_v4_send_ack(sock_net(sk), skb, seq,
+ tcp_v4_send_ack(sk, skb, seq,
tcp_rsk(req)->rcv_nxt,
req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
tcp_time_stamp,
@@ -1565,6 +1567,21 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(tcp_add_backlog);
+int tcp_filter(struct sock *sk, struct sk_buff *skb)
+{
+ struct tcphdr *th = (struct tcphdr *)skb->data;
+ unsigned int eaten = skb->len;
+ int err;
+
+ err = sk_filter_trim_cap(sk, skb, th->doff * 4);
+ if (!err) {
+ eaten -= skb->len;
+ TCP_SKB_CB(skb)->end_seq -= eaten;
+ }
+ return err;
+}
+EXPORT_SYMBOL(tcp_filter);
+
/*
* From tcp_input.c
*/
@@ -1677,8 +1694,10 @@ int tcp_v4_rcv(struct sk_buff *skb)
nf_reset(skb);
- if (sk_filter(sk, skb))
+ if (tcp_filter(sk, skb))
goto discard_and_relse;
+ th = (const struct tcphdr *)skb->data;
+ iph = ip_hdr(skb);
skb->dev = NULL;
@@ -1887,7 +1906,6 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
struct tcp_iter_state *st = seq->private;
struct net *net = seq_file_net(seq);
struct inet_listen_hashbucket *ilb;
- struct inet_connection_sock *icsk;
struct sock *sk = cur;
if (!sk) {
@@ -1909,7 +1927,6 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
continue;
if (sk->sk_family == st->family)
return sk;
- icsk = inet_csk(sk);
}
spin_unlock(&ilb->lock);
st->offset = 0;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 896e9df..f57b5aa 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2529,8 +2529,9 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
tcp_unlink_write_queue(next_skb, sk);
- skb_copy_from_linear_data(next_skb, skb_put(skb, next_skb_size),
- next_skb_size);
+ if (next_skb_size)
+ skb_copy_bits(next_skb, 0, skb_put(skb, next_skb_size),
+ next_skb_size);
if (next_skb->ip_summed == CHECKSUM_PARTIAL)
skb->ip_summed = CHECKSUM_PARTIAL;
@@ -2567,14 +2568,11 @@ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb)
{
if (tcp_skb_pcount(skb) > 1)
return false;
- /* TODO: SACK collapsing could be used to remove this condition */
- if (skb_shinfo(skb)->nr_frags != 0)
- return false;
if (skb_cloned(skb))
return false;
if (skb == tcp_send_head(sk))
return false;
- /* Some heurestics for collapsing over SACK'd could be invented */
+ /* Some heuristics for collapsing over SACK'd could be invented */
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
return false;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c833271..e1fc011 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -580,7 +580,8 @@ EXPORT_SYMBOL_GPL(udp4_lib_lookup_skb);
* Does increment socket refcount.
*/
#if IS_ENABLED(CONFIG_NETFILTER_XT_MATCH_SOCKET) || \
- IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY)
+ IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY) || \
+ IS_ENABLED(CONFIG_NF_SOCKET_IPV4)
struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
__be32 daddr, __be16 dport, int dif)
{
@@ -1019,7 +1020,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE, sk->sk_protocol,
flow_flags,
- faddr, saddr, dport, inet->inet_sport);
+ faddr, saddr, dport, inet->inet_sport,
+ sk->sk_uid);
security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
@@ -1172,26 +1174,26 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
return ret;
}
+/* fully reclaim rmem/fwd memory allocated for skb */
static void udp_rmem_release(struct sock *sk, int size, int partial)
{
int amt;
atomic_sub(size, &sk->sk_rmem_alloc);
-
- spin_lock_bh(&sk->sk_receive_queue.lock);
sk->sk_forward_alloc += size;
amt = (sk->sk_forward_alloc - partial) & ~(SK_MEM_QUANTUM - 1);
sk->sk_forward_alloc -= amt;
- spin_unlock_bh(&sk->sk_receive_queue.lock);
if (amt)
__sk_mem_reduce_allocated(sk, amt >> SK_MEM_QUANTUM_SHIFT);
}
-static void udp_rmem_free(struct sk_buff *skb)
+/* Note: called with sk_receive_queue.lock held */
+void udp_skb_destructor(struct sock *sk, struct sk_buff *skb)
{
- udp_rmem_release(skb->sk, skb->truesize, 1);
+ udp_rmem_release(sk, skb->truesize, 1);
}
+EXPORT_SYMBOL(udp_skb_destructor);
int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
{
@@ -1228,9 +1230,9 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
sk->sk_forward_alloc -= size;
- /* the skb owner in now the udp socket */
- skb->sk = sk;
- skb->destructor = udp_rmem_free;
+ /* no need to setup a destructor, we will explicitly release the
+ * forward allocated memory on dequeue
+ */
skb->dev = NULL;
sock_skb_set_dropcount(sk, skb);
@@ -1251,13 +1253,21 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb);
-static void udp_destruct_sock(struct sock *sk)
+void udp_destruct_sock(struct sock *sk)
{
/* reclaim completely the forward allocated memory */
- __skb_queue_purge(&sk->sk_receive_queue);
- udp_rmem_release(sk, 0, 0);
+ unsigned int total = 0;
+ struct sk_buff *skb;
+
+ while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
+ total += skb->truesize;
+ kfree_skb(skb);
+ }
+ udp_rmem_release(sk, total, 0);
+
inet_sock_destruct(sk);
}
+EXPORT_SYMBOL_GPL(udp_destruct_sock);
int udp_init_sock(struct sock *sk)
{
@@ -1287,12 +1297,11 @@ EXPORT_SYMBOL_GPL(skb_consume_udp);
*/
static int first_packet_length(struct sock *sk)
{
- struct sk_buff_head list_kill, *rcvq = &sk->sk_receive_queue;
+ struct sk_buff_head *rcvq = &sk->sk_receive_queue;
struct sk_buff *skb;
+ int total = 0;
int res;
- __skb_queue_head_init(&list_kill);
-
spin_lock_bh(&rcvq->lock);
while ((skb = skb_peek(rcvq)) != NULL &&
udp_lib_checksum_complete(skb)) {
@@ -1302,12 +1311,13 @@ static int first_packet_length(struct sock *sk)
IS_UDPLITE(sk));
atomic_inc(&sk->sk_drops);
__skb_unlink(skb, rcvq);
- __skb_queue_tail(&list_kill, skb);
+ total += skb->truesize;
+ kfree_skb(skb);
}
res = skb ? skb->len : -1;
+ if (total)
+ udp_rmem_release(sk, total, 1);
spin_unlock_bh(&rcvq->lock);
-
- __skb_queue_purge(&list_kill);
return res;
}
@@ -1362,8 +1372,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
try_again:
peeking = off = sk_peek_offset(sk, flags);
- skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
- &peeked, &off, &err);
+ skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err);
if (!skb)
return err;
@@ -1420,7 +1429,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
*addr_len = sizeof(*sin);
}
if (inet->cmsg_flags)
- ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr) + off);
+ ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off);
err = copied;
if (flags & MSG_TRUNC)
@@ -1442,7 +1451,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
goto try_again;
}
-int udp_disconnect(struct sock *sk, int flags)
+int __udp_disconnect(struct sock *sk, int flags)
{
struct inet_sock *inet = inet_sk(sk);
/*
@@ -1464,6 +1473,15 @@ int udp_disconnect(struct sock *sk, int flags)
sk_dst_reset(sk);
return 0;
}
+EXPORT_SYMBOL(__udp_disconnect);
+
+int udp_disconnect(struct sock *sk, int flags)
+{
+ lock_sock(sk);
+ __udp_disconnect(sk, flags);
+ release_sock(sk);
+ return 0;
+}
EXPORT_SYMBOL(udp_disconnect);
void udp_lib_unhash(struct sock *sk)
@@ -1551,6 +1569,8 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
sock_rps_save_rxhash(sk, skb);
sk_mark_napi_id(sk, skb);
sk_incoming_cpu_update(sk);
+ } else {
+ sk_mark_napi_id_once(sk, skb);
}
rc = __udp_enqueue_schedule_skb(sk, skb);
@@ -2272,7 +2292,7 @@ int udp_abort(struct sock *sk, int err)
sk->sk_err = err;
sk->sk_error_report(sk);
- udp_disconnect(sk, 0);
+ __udp_disconnect(sk, 0);
release_sock(sk);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index f9333c9..b2be1d9 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -295,7 +295,7 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
- pp = udp_sk(sk)->gro_receive(sk, head, skb);
+ pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb);
out_unlock:
rcu_read_unlock();
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index af81715..59f10fe 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -50,10 +50,11 @@ struct proto udplite_prot = {
.sendmsg = udp_sendmsg,
.recvmsg = udp_recvmsg,
.sendpage = udp_sendpage,
- .backlog_rcv = udp_queue_rcv_skb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
.get_port = udp_v4_get_port,
+ .memory_allocated = &udp_memory_allocated,
+ .sysctl_mem = sysctl_udp_mem,
.obj_size = sizeof(struct udp_sock),
.h.udp_table = &udplite_table,
#ifdef CONFIG_COMPAT
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 2343e4f..ec1267e 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -289,4 +289,39 @@
Support for IPv6 PIM multicast routing protocol PIM-SMv2.
If unsure, say N.
+config IPV6_SEG6_LWTUNNEL
+ bool "IPv6: Segment Routing Header encapsulation support"
+ depends on IPV6
+ select LWTUNNEL
+ ---help---
+ Support for encapsulation of packets within an outer IPv6
+ header and a Segment Routing Header using the lightweight
+ tunnels mechanism.
+
+ If unsure, say N.
+
+config IPV6_SEG6_INLINE
+ bool "IPv6: direct Segment Routing Header insertion "
+ depends on IPV6_SEG6_LWTUNNEL
+ ---help---
+ Support for direct insertion of the Segment Routing Header,
+ also known as inline mode. Be aware that direct insertion of
+ extension headers (as opposed to encapsulation) may break
+ multiple mechanisms such as PMTUD or IPSec AH. Use this feature
+ only if you know exactly what you are doing.
+
+ If unsure, say N.
+
+config IPV6_SEG6_HMAC
+ bool "IPv6: Segment Routing HMAC support"
+ depends on IPV6
+ select CRYPTO_HMAC
+ select CRYPTO_SHA1
+ select CRYPTO_SHA256
+ ---help---
+ Support for HMAC signature generation and verification
+ of SR-enabled packets.
+
+ If unsure, say N.
+
endif # IPV6
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index c174ccb..a9e9fec 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -9,7 +9,7 @@
route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \
raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \
exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o \
- udp_offload.o
+ udp_offload.o seg6.o
ipv6-offload := ip6_offload.o tcpv6_offload.o exthdrs_offload.o
@@ -23,6 +23,8 @@
ipv6-$(CONFIG_PROC_FS) += proc.o
ipv6-$(CONFIG_SYN_COOKIES) += syncookies.o
ipv6-$(CONFIG_NETLABEL) += calipso.o
+ipv6-$(CONFIG_IPV6_SEG6_LWTUNNEL) += seg6_iptunnel.o
+ipv6-$(CONFIG_IPV6_SEG6_HMAC) += seg6_hmac.o
ipv6-objs += $(ipv6-y)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index d8983e1..86219c0a 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -147,9 +147,8 @@ static inline void addrconf_sysctl_unregister(struct inet6_dev *idev)
}
#endif
-static void __ipv6_regen_rndid(struct inet6_dev *idev);
-static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr);
-static void ipv6_regen_rndid(unsigned long data);
+static void ipv6_regen_rndid(struct inet6_dev *idev);
+static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr);
static int ipv6_generate_eui64(u8 *eui, struct net_device *dev);
static int ipv6_count_addresses(struct inet6_dev *idev);
@@ -239,6 +238,10 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.use_oif_addrs_only = 0,
.ignore_routes_with_linkdown = 0,
.keep_addr_on_down = 0,
+ .seg6_enabled = 0,
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ .seg6_require_hmac = 0,
+#endif
};
static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -285,6 +288,10 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.use_oif_addrs_only = 0,
.ignore_routes_with_linkdown = 0,
.keep_addr_on_down = 0,
+ .seg6_enabled = 0,
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ .seg6_require_hmac = 0,
+#endif
};
/* Check if a valid qdisc is available */
@@ -409,9 +416,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
goto err_release;
}
- /* One reference from device. We must do this before
- * we invoke __ipv6_regen_rndid().
- */
+ /* One reference from device. */
in6_dev_hold(ndev);
if (dev->flags & (IFF_NOARP | IFF_LOOPBACK))
@@ -425,17 +430,15 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
#endif
INIT_LIST_HEAD(&ndev->tempaddr_list);
- setup_timer(&ndev->regen_timer, ipv6_regen_rndid, (unsigned long)ndev);
+ ndev->desync_factor = U32_MAX;
if ((dev->flags&IFF_LOOPBACK) ||
dev->type == ARPHRD_TUNNEL ||
dev->type == ARPHRD_TUNNEL6 ||
dev->type == ARPHRD_SIT ||
dev->type == ARPHRD_NONE) {
ndev->cnf.use_tempaddr = -1;
- } else {
- in6_dev_hold(ndev);
- ipv6_regen_rndid((unsigned long) ndev);
- }
+ } else
+ ipv6_regen_rndid(ndev);
ndev->token = in6addr_any;
@@ -447,7 +450,6 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
err = addrconf_sysctl_register(ndev);
if (err) {
ipv6_mc_destroy_dev(ndev);
- del_timer(&ndev->regen_timer);
snmp6_unregister_dev(ndev);
goto err_release;
}
@@ -1190,6 +1192,8 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *i
int ret = 0;
u32 addr_flags;
unsigned long now = jiffies;
+ long max_desync_factor;
+ s32 cnf_temp_preferred_lft;
write_lock_bh(&idev->lock);
if (ift) {
@@ -1222,23 +1226,42 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *i
}
in6_ifa_hold(ifp);
memcpy(addr.s6_addr, ifp->addr.s6_addr, 8);
- __ipv6_try_regen_rndid(idev, tmpaddr);
+ ipv6_try_regen_rndid(idev, tmpaddr);
memcpy(&addr.s6_addr[8], idev->rndid, 8);
age = (now - ifp->tstamp) / HZ;
- tmp_valid_lft = min_t(__u32,
- ifp->valid_lft,
- idev->cnf.temp_valid_lft + age);
- tmp_prefered_lft = min_t(__u32,
- ifp->prefered_lft,
- idev->cnf.temp_prefered_lft + age -
- idev->cnf.max_desync_factor);
- tmp_plen = ifp->prefix_len;
- tmp_tstamp = ifp->tstamp;
- spin_unlock_bh(&ifp->lock);
regen_advance = idev->cnf.regen_max_retry *
idev->cnf.dad_transmits *
NEIGH_VAR(idev->nd_parms, RETRANS_TIME) / HZ;
+
+ /* recalculate max_desync_factor each time and update
+ * idev->desync_factor if it's larger
+ */
+ cnf_temp_preferred_lft = READ_ONCE(idev->cnf.temp_prefered_lft);
+ max_desync_factor = min_t(__u32,
+ idev->cnf.max_desync_factor,
+ cnf_temp_preferred_lft - regen_advance);
+
+ if (unlikely(idev->desync_factor > max_desync_factor)) {
+ if (max_desync_factor > 0) {
+ get_random_bytes(&idev->desync_factor,
+ sizeof(idev->desync_factor));
+ idev->desync_factor %= max_desync_factor;
+ } else {
+ idev->desync_factor = 0;
+ }
+ }
+
+ tmp_valid_lft = min_t(__u32,
+ ifp->valid_lft,
+ idev->cnf.temp_valid_lft + age);
+ tmp_prefered_lft = cnf_temp_preferred_lft + age -
+ idev->desync_factor;
+ tmp_prefered_lft = min_t(__u32, ifp->prefered_lft, tmp_prefered_lft);
+ tmp_plen = ifp->prefix_len;
+ tmp_tstamp = ifp->tstamp;
+ spin_unlock_bh(&ifp->lock);
+
write_unlock_bh(&idev->lock);
/* A temporary address is created only if this calculated Preferred
@@ -2150,7 +2173,7 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev)
}
/* (re)generation of randomized interface identifier (RFC 3041 3.2, 3.5) */
-static void __ipv6_regen_rndid(struct inet6_dev *idev)
+static void ipv6_regen_rndid(struct inet6_dev *idev)
{
regen:
get_random_bytes(idev->rndid, sizeof(idev->rndid));
@@ -2179,43 +2202,10 @@ static void __ipv6_regen_rndid(struct inet6_dev *idev)
}
}
-static void ipv6_regen_rndid(unsigned long data)
-{
- struct inet6_dev *idev = (struct inet6_dev *) data;
- unsigned long expires;
-
- rcu_read_lock_bh();
- write_lock_bh(&idev->lock);
-
- if (idev->dead)
- goto out;
-
- __ipv6_regen_rndid(idev);
-
- expires = jiffies +
- idev->cnf.temp_prefered_lft * HZ -
- idev->cnf.regen_max_retry * idev->cnf.dad_transmits *
- NEIGH_VAR(idev->nd_parms, RETRANS_TIME) -
- idev->cnf.max_desync_factor * HZ;
- if (time_before(expires, jiffies)) {
- pr_warn("%s: too short regeneration interval; timer disabled for %s\n",
- __func__, idev->dev->name);
- goto out;
- }
-
- if (!mod_timer(&idev->regen_timer, expires))
- in6_dev_hold(idev);
-
-out:
- write_unlock_bh(&idev->lock);
- rcu_read_unlock_bh();
- in6_dev_put(idev);
-}
-
-static void __ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr)
+static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr)
{
if (tmpaddr && memcmp(idev->rndid, &tmpaddr->s6_addr[8], 8) == 0)
- __ipv6_regen_rndid(idev);
+ ipv6_regen_rndid(idev);
}
/*
@@ -2356,7 +2346,7 @@ static void manage_tempaddrs(struct inet6_dev *idev,
max_valid = 0;
max_prefered = idev->cnf.temp_prefered_lft -
- idev->cnf.max_desync_factor - age;
+ idev->desync_factor - age;
if (max_prefered < 0)
max_prefered = 0;
@@ -3018,7 +3008,7 @@ static void init_loopback(struct net_device *dev)
* lo device down, release this obsolete dst and
* reallocate a new router for ifa.
*/
- if (sp_ifa->rt->dst.obsolete > 0) {
+ if (!atomic_read(&sp_ifa->rt->rt6i_ref)) {
ip6_rt_put(sp_ifa->rt);
sp_ifa->rt = NULL;
} else {
@@ -3594,9 +3584,6 @@ static int addrconf_ifdown(struct net_device *dev, int how)
if (!how)
idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY);
- if (how && del_timer(&idev->regen_timer))
- in6_dev_put(idev);
-
/* Step 3: clear tempaddr list */
while (!list_empty(&idev->tempaddr_list)) {
ifa = list_first_entry(&idev->tempaddr_list,
@@ -4965,6 +4952,10 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast;
array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na;
array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down;
+ array[DEVCONF_SEG6_ENABLED] = cnf->seg6_enabled;
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ array[DEVCONF_SEG6_REQUIRE_HMAC] = cnf->seg6_require_hmac;
+#endif
}
static inline size_t inet6_ifla6_size(void)
@@ -6057,6 +6048,22 @@ static const struct ctl_table addrconf_sysctl[] = {
},
{
+ .procname = "seg6_enabled",
+ .data = &ipv6_devconf.seg6_enabled,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ {
+ .procname = "seg6_require_hmac",
+ .data = &ipv6_devconf.seg6_require_hmac,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+#endif
+ {
/* sentinel */
}
};
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 46ad699..d424f3a 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -61,6 +61,7 @@
#include <net/ip6_tunnel.h>
#endif
#include <net/calipso.h>
+#include <net/seg6.h>
#include <asm/uaccess.h>
#include <linux/mroute6.h>
@@ -678,6 +679,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = inet->inet_dport;
fl6.fl6_sport = inet->inet_sport;
+ fl6.flowi6_uid = sk->sk_uid;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
rcu_read_lock();
@@ -990,6 +992,10 @@ static int __init inet6_init(void)
if (err)
goto calipso_fail;
+ err = seg6_init();
+ if (err)
+ goto seg6_fail;
+
#ifdef CONFIG_SYSCTL
err = ipv6_sysctl_register();
if (err)
@@ -1000,8 +1006,10 @@ static int __init inet6_init(void)
#ifdef CONFIG_SYSCTL
sysctl_fail:
- calipso_exit();
+ seg6_exit();
#endif
+seg6_fail:
+ calipso_exit();
calipso_fail:
pingv6_exit();
pingv6_fail:
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 0630a4d5..189eb10 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -662,9 +662,10 @@ static int ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return 0;
if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 37874e2..c5d76d2 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -54,6 +54,7 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk)
fl6->fl6_dport = inet->inet_dport;
fl6->fl6_sport = inet->inet_sport;
fl6->flowlabel = np->flow_label;
+ fl6->flowi6_uid = sk->sk_uid;
if (!fl6->flowi6_oif)
fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
@@ -715,6 +716,11 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
put_cmsg(msg, SOL_IPV6, IPV6_ORIGDSTADDR, sizeof(sin6), &sin6);
}
}
+ if (np->rxopt.bits.recvfragsize && opt->frag_max_size) {
+ int val = opt->frag_max_size;
+
+ put_cmsg(msg, SOL_IPV6, IPV6_RECVFRAGSIZE, sizeof(val), &val);
+ }
}
void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg,
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 060a60b..218f0cb 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -474,9 +474,10 @@ static int esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return 0;
if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 139ceb6..926818c 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -47,6 +47,11 @@
#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/xfrm.h>
#endif
+#include <linux/seg6.h>
+#include <net/seg6.h>
+#ifdef CONFIG_IPV6_SEG6_HMAC
+#include <net/seg6_hmac.h>
+#endif
#include <linux/uaccess.h>
@@ -286,6 +291,182 @@ static int ipv6_destopt_rcv(struct sk_buff *skb)
return -1;
}
+static void seg6_update_csum(struct sk_buff *skb)
+{
+ struct ipv6_sr_hdr *hdr;
+ struct in6_addr *addr;
+ __be32 from, to;
+
+ /* srh is at transport offset and seg_left is already decremented
+ * but daddr is not yet updated with next segment
+ */
+
+ hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb);
+ addr = hdr->segments + hdr->segments_left;
+
+ hdr->segments_left++;
+ from = *(__be32 *)hdr;
+
+ hdr->segments_left--;
+ to = *(__be32 *)hdr;
+
+ /* update skb csum with diff resulting from seg_left decrement */
+
+ update_csum_diff4(skb, from, to);
+
+ /* compute csum diff between current and next segment and update */
+
+ update_csum_diff16(skb, (__be32 *)(&ipv6_hdr(skb)->daddr),
+ (__be32 *)addr);
+}
+
+static int ipv6_srh_rcv(struct sk_buff *skb)
+{
+ struct inet6_skb_parm *opt = IP6CB(skb);
+ struct net *net = dev_net(skb->dev);
+ struct ipv6_sr_hdr *hdr;
+ struct inet6_dev *idev;
+ struct in6_addr *addr;
+ bool cleanup = false;
+ int accept_seg6;
+
+ hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb);
+
+ idev = __in6_dev_get(skb->dev);
+
+ accept_seg6 = net->ipv6.devconf_all->seg6_enabled;
+ if (accept_seg6 > idev->cnf.seg6_enabled)
+ accept_seg6 = idev->cnf.seg6_enabled;
+
+ if (!accept_seg6) {
+ kfree_skb(skb);
+ return -1;
+ }
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ if (!seg6_hmac_validate_skb(skb)) {
+ kfree_skb(skb);
+ return -1;
+ }
+#endif
+
+looped_back:
+ if (hdr->segments_left > 0) {
+ if (hdr->nexthdr != NEXTHDR_IPV6 && hdr->segments_left == 1 &&
+ sr_has_cleanup(hdr))
+ cleanup = true;
+ } else {
+ if (hdr->nexthdr == NEXTHDR_IPV6) {
+ int offset = (hdr->hdrlen + 1) << 3;
+
+ skb_postpull_rcsum(skb, skb_network_header(skb),
+ skb_network_header_len(skb));
+
+ if (!pskb_pull(skb, offset)) {
+ kfree_skb(skb);
+ return -1;
+ }
+ skb_postpull_rcsum(skb, skb_transport_header(skb),
+ offset);
+
+ skb_reset_network_header(skb);
+ skb_reset_transport_header(skb);
+ skb->encapsulation = 0;
+
+ __skb_tunnel_rx(skb, skb->dev, net);
+
+ netif_rx(skb);
+ return -1;
+ }
+
+ opt->srcrt = skb_network_header_len(skb);
+ opt->lastopt = opt->srcrt;
+ skb->transport_header += (hdr->hdrlen + 1) << 3;
+ opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb);
+
+ return 1;
+ }
+
+ if (hdr->segments_left >= (hdr->hdrlen >> 1)) {
+ __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+ IPSTATS_MIB_INHDRERRORS);
+ icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
+ ((&hdr->segments_left) -
+ skb_network_header(skb)));
+ kfree_skb(skb);
+ return -1;
+ }
+
+ if (skb_cloned(skb)) {
+ if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) {
+ __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+ IPSTATS_MIB_OUTDISCARDS);
+ kfree_skb(skb);
+ return -1;
+ }
+ }
+
+ hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb);
+
+ hdr->segments_left--;
+ addr = hdr->segments + hdr->segments_left;
+
+ skb_push(skb, sizeof(struct ipv6hdr));
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ seg6_update_csum(skb);
+
+ ipv6_hdr(skb)->daddr = *addr;
+
+ if (cleanup) {
+ int srhlen = (hdr->hdrlen + 1) << 3;
+ int nh = hdr->nexthdr;
+
+ skb_pull_rcsum(skb, sizeof(struct ipv6hdr) + srhlen);
+ memmove(skb_network_header(skb) + srhlen,
+ skb_network_header(skb),
+ (unsigned char *)hdr - skb_network_header(skb));
+ skb->network_header += srhlen;
+ ipv6_hdr(skb)->nexthdr = nh;
+ ipv6_hdr(skb)->payload_len = htons(skb->len -
+ sizeof(struct ipv6hdr));
+ skb_push_rcsum(skb, sizeof(struct ipv6hdr));
+ }
+
+ skb_dst_drop(skb);
+
+ ip6_route_input(skb);
+
+ if (skb_dst(skb)->error) {
+ dst_input(skb);
+ return -1;
+ }
+
+ if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) {
+ if (ipv6_hdr(skb)->hop_limit <= 1) {
+ __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+ IPSTATS_MIB_INHDRERRORS);
+ icmpv6_send(skb, ICMPV6_TIME_EXCEED,
+ ICMPV6_EXC_HOPLIMIT, 0);
+ kfree_skb(skb);
+ return -1;
+ }
+ ipv6_hdr(skb)->hop_limit--;
+
+ /* be sure that srh is still present before reinjecting */
+ if (!cleanup) {
+ skb_pull(skb, sizeof(struct ipv6hdr));
+ goto looped_back;
+ }
+ skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+ IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
+ }
+
+ dst_input(skb);
+
+ return -1;
+}
+
/********************************
Routing header.
********************************/
@@ -326,6 +507,10 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb)
return -1;
}
+ /* segment routing */
+ if (hdr->type == IPV6_SRCRT_TYPE_4)
+ return ipv6_srh_rcv(skb);
+
looped_back:
if (hdr->segments_left == 0) {
switch (hdr->type) {
@@ -679,9 +864,9 @@ int ipv6_parse_hopopts(struct sk_buff *skb)
* for headers.
*/
-static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto,
- struct ipv6_rt_hdr *opt,
- struct in6_addr **addr_p)
+static void ipv6_push_rthdr0(struct sk_buff *skb, u8 *proto,
+ struct ipv6_rt_hdr *opt,
+ struct in6_addr **addr_p, struct in6_addr *saddr)
{
struct rt0_hdr *phdr, *ihdr;
int hops;
@@ -704,6 +889,62 @@ static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto,
*proto = NEXTHDR_ROUTING;
}
+static void ipv6_push_rthdr4(struct sk_buff *skb, u8 *proto,
+ struct ipv6_rt_hdr *opt,
+ struct in6_addr **addr_p, struct in6_addr *saddr)
+{
+ struct ipv6_sr_hdr *sr_phdr, *sr_ihdr;
+ int plen, hops;
+
+ sr_ihdr = (struct ipv6_sr_hdr *)opt;
+ plen = (sr_ihdr->hdrlen + 1) << 3;
+
+ sr_phdr = (struct ipv6_sr_hdr *)skb_push(skb, plen);
+ memcpy(sr_phdr, sr_ihdr, sizeof(struct ipv6_sr_hdr));
+
+ hops = sr_ihdr->first_segment + 1;
+ memcpy(sr_phdr->segments + 1, sr_ihdr->segments + 1,
+ (hops - 1) * sizeof(struct in6_addr));
+
+ sr_phdr->segments[0] = **addr_p;
+ *addr_p = &sr_ihdr->segments[hops - 1];
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ if (sr_has_hmac(sr_phdr)) {
+ struct net *net = NULL;
+
+ if (skb->dev)
+ net = dev_net(skb->dev);
+ else if (skb->sk)
+ net = sock_net(skb->sk);
+
+ WARN_ON(!net);
+
+ if (net)
+ seg6_push_hmac(net, saddr, sr_phdr);
+ }
+#endif
+
+ sr_phdr->nexthdr = *proto;
+ *proto = NEXTHDR_ROUTING;
+}
+
+static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto,
+ struct ipv6_rt_hdr *opt,
+ struct in6_addr **addr_p, struct in6_addr *saddr)
+{
+ switch (opt->type) {
+ case IPV6_SRCRT_TYPE_0:
+ ipv6_push_rthdr0(skb, proto, opt, addr_p, saddr);
+ break;
+ case IPV6_SRCRT_TYPE_4:
+ ipv6_push_rthdr4(skb, proto, opt, addr_p, saddr);
+ break;
+ default:
+ break;
+ }
+}
+
static void ipv6_push_exthdr(struct sk_buff *skb, u8 *proto, u8 type, struct ipv6_opt_hdr *opt)
{
struct ipv6_opt_hdr *h = (struct ipv6_opt_hdr *)skb_push(skb, ipv6_optlen(opt));
@@ -715,10 +956,10 @@ static void ipv6_push_exthdr(struct sk_buff *skb, u8 *proto, u8 type, struct ipv
void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt,
u8 *proto,
- struct in6_addr **daddr)
+ struct in6_addr **daddr, struct in6_addr *saddr)
{
if (opt->srcrt) {
- ipv6_push_rthdr(skb, proto, opt->srcrt, daddr);
+ ipv6_push_rthdr(skb, proto, opt->srcrt, daddr, saddr);
/*
* IPV6_RTHDRDSTOPTS is ignored
* unless IPV6_RTHDR is set (RFC3542).
@@ -945,7 +1186,22 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6,
return NULL;
*orig = fl6->daddr;
- fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr;
+
+ switch (opt->srcrt->type) {
+ case IPV6_SRCRT_TYPE_0:
+ fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr;
+ break;
+ case IPV6_SRCRT_TYPE_4:
+ {
+ struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)opt->srcrt;
+
+ fl6->daddr = srh->segments[srh->first_segment];
+ break;
+ }
+ default:
+ return NULL;
+ }
+
return orig;
}
EXPORT_SYMBOL_GPL(fl6_update_dst);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index bd59c34..eb948ff 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -92,9 +92,10 @@ static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
struct net *net = dev_net(skb->dev);
if (type == ICMPV6_PKT_TOOBIG)
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
else if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
if (!(type & ICMPV6_INFOMSG_MASK))
if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
@@ -448,7 +449,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
if (__ipv6_addr_needs_scope_id(addr_type))
iif = skb->dev->ifindex;
else
- iif = l3mdev_master_ifindex(skb->dev);
+ iif = l3mdev_master_ifindex(skb_dst(skb)->dev);
/*
* Must not send error if the source does not uniquely
@@ -484,6 +485,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
fl6.flowi6_oif = iif;
fl6.fl6_icmp_type = type;
fl6.fl6_icmp_code = code;
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
sk = icmpv6_xmit_lock(net);
@@ -658,6 +660,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
fl6.flowi6_oif = skb->dev->ifindex;
fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
fl6.flowi6_mark = mark;
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
sk = icmpv6_xmit_lock(net);
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index 628ae6d..af8f52e 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -474,7 +474,15 @@ static int ila_nl_dump_start(struct netlink_callback *cb)
{
struct net *net = sock_net(cb->skb->sk);
struct ila_net *ilan = net_generic(net, ila_net_id);
- struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args;
+ struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0];
+
+ if (!iter) {
+ iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+ if (!iter)
+ return -ENOMEM;
+
+ cb->args[0] = (long)iter;
+ }
return rhashtable_walk_init(&ilan->rhash_table, &iter->rhiter,
GFP_KERNEL);
@@ -482,16 +490,18 @@ static int ila_nl_dump_start(struct netlink_callback *cb)
static int ila_nl_dump_done(struct netlink_callback *cb)
{
- struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args;
+ struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0];
rhashtable_walk_exit(&iter->rhiter);
+ kfree(iter);
+
return 0;
}
static int ila_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args;
+ struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0];
struct rhashtable_iter *rhiter = &iter->rhiter;
struct ila_map *ila;
int ret;
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 532c3ef..1c86c47 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -88,6 +88,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
fl6->flowi6_mark = ireq->ir_mark;
fl6->fl6_dport = ireq->ir_rmt_port;
fl6->fl6_sport = htons(ireq->ir_num);
+ fl6->flowi6_uid = sk->sk_uid;
security_req_classify_flow(req, flowi6_to_flowi(fl6));
dst = ip6_dst_lookup_flow(sk, fl6, final_p);
@@ -136,6 +137,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
fl6->flowi6_mark = sk->sk_mark;
fl6->fl6_sport = inet->inet_sport;
fl6->fl6_dport = inet->inet_dport;
+ fl6->flowi6_uid = sk->sk_uid;
security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
rcu_read_lock();
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 00cf28a..02761c9 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -96,7 +96,7 @@ EXPORT_SYMBOL(__inet6_lookup_established);
static inline int compute_score(struct sock *sk, struct net *net,
const unsigned short hnum,
const struct in6_addr *daddr,
- const int dif)
+ const int dif, bool exact_dif)
{
int score = -1;
@@ -109,7 +109,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
return -1;
score++;
}
- if (sk->sk_bound_dev_if) {
+ if (sk->sk_bound_dev_if || exact_dif) {
if (sk->sk_bound_dev_if != dif)
return -1;
score++;
@@ -131,11 +131,12 @@ struct sock *inet6_lookup_listener(struct net *net,
unsigned int hash = inet_lhashfn(net, hnum);
struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
int score, hiscore = 0, matches = 0, reuseport = 0;
+ bool exact_dif = inet6_exact_dif_match(net, skb);
struct sock *sk, *result = NULL;
u32 phash = 0;
sk_for_each(sk, &ilb->head) {
- score = compute_score(sk, net, hnum, daddr, dif);
+ score = compute_score(sk, net, hnum, daddr, dif, exact_dif);
if (score > hiscore) {
reuseport = sk->sk_reuseport;
if (reuseport) {
@@ -263,13 +264,15 @@ EXPORT_SYMBOL_GPL(inet6_hash_connect);
int inet6_hash(struct sock *sk)
{
+ int err = 0;
+
if (sk->sk_state != TCP_CLOSE) {
local_bh_disable();
- __inet_hash(sk, NULL, ipv6_rcv_saddr_equal);
+ err = __inet_hash(sk, NULL, ipv6_rcv_saddr_equal);
local_bh_enable();
}
- return 0;
+ return err;
}
EXPORT_SYMBOL_GPL(inet6_hash);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index d7d6d3a..75b6108 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -64,7 +64,7 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
#define IP6_GRE_HASH_SIZE_SHIFT 5
#define IP6_GRE_HASH_SIZE (1 << IP6_GRE_HASH_SIZE_SHIFT)
-static int ip6gre_net_id __read_mostly;
+static unsigned int ip6gre_net_id __read_mostly;
struct ip6gre_net {
struct ip6_tnl __rcu *tunnels[4][IP6_GRE_HASH_SIZE];
@@ -548,6 +548,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev)
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
fl6.flowi6_mark = skb->mark;
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM));
if (err)
return -1;
@@ -602,6 +604,8 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
fl6.flowi6_mark = skb->mark;
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
if (gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM)))
return -1;
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index e7bfd55..1fcf61f 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -246,7 +246,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
skb_gro_postpull_rcsum(skb, iph, nlen);
- pp = ops->callbacks.gro_receive(head, skb);
+ pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
out_unlock:
rcu_read_unlock();
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 6001e78..b37054b 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -203,7 +203,8 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
if (opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt->opt_nflen)
- ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop);
+ ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop,
+ &fl6->saddr);
}
skb_push(skb, sizeof(struct ipv6hdr));
@@ -1366,7 +1367,7 @@ static int __ip6_append_data(struct sock *sk,
if (((length > mtu) ||
(skb && skb_is_gso(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
- (rt->dst.dev->features & NETIF_F_UFO) &&
+ (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
(sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
hh_len, fragheaderlen, exthdrlen,
@@ -1672,7 +1673,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
if (opt && opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt && opt->opt_nflen)
- ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst);
+ ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst, &fl6->saddr);
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 3a70567..d3c619e 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -83,7 +83,7 @@ static int ip6_tnl_dev_init(struct net_device *dev);
static void ip6_tnl_dev_setup(struct net_device *dev);
static struct rtnl_link_ops ip6_link_ops __read_mostly;
-static int ip6_tnl_net_id __read_mostly;
+static unsigned int ip6_tnl_net_id __read_mostly;
struct ip6_tnl_net {
/* the IPv6 tunnel fallback device */
struct net_device *fb_tnl_dev;
@@ -157,6 +157,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
hash = HASH(&any, local);
for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
if (ipv6_addr_equal(local, &t->parms.laddr) &&
+ ipv6_addr_any(&t->parms.raddr) &&
(t->dev->flags & IFF_UP))
return t;
}
@@ -164,6 +165,7 @@ ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_
hash = HASH(remote, &any);
for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
if (ipv6_addr_equal(remote, &t->parms.raddr) &&
+ ipv6_addr_any(&t->parms.laddr) &&
(t->dev->flags & IFF_UP))
return t;
}
@@ -1155,7 +1157,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
if (encap_limit >= 0) {
init_tel_txopt(&opt, encap_limit);
- ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
+ ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL, NULL);
}
/* Calculate max headroom for all the headers and adjust
@@ -1170,6 +1172,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
if (err)
return err;
+ skb->protocol = htons(ETH_P_IPV6);
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
ipv6h = ipv6_hdr(skb);
@@ -1237,6 +1240,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
fl6.flowi6_mark = skb->mark;
}
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
return -1;
@@ -1315,6 +1320,8 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
fl6.flowi6_mark = skb->mark;
}
+ fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
return -1;
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index a752052..b283f29 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -88,9 +88,6 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk,
uh->len = htons(skb->len);
- memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
- IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED
- | IPSKB_REROUTED);
skb_dst_set(skb, dst);
udp6_set_csum(nocheck, skb, saddr, daddr, skb->len);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 35c5b2d..c476bb8 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -64,7 +64,7 @@ static int vti6_dev_init(struct net_device *dev);
static void vti6_dev_setup(struct net_device *dev);
static struct rtnl_link_ops vti6_link_ops __read_mostly;
-static int vti6_net_id __read_mostly;
+static unsigned int vti6_net_id __read_mostly;
struct vti6_net {
/* the vti6 tunnel fallback device */
struct net_device *fb_tnl_dev;
@@ -608,9 +608,10 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return 0;
if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 7f4265b..52101b3 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -636,7 +636,7 @@ static int pim6_rcv(struct sk_buff *skb)
goto drop;
pim = (struct pimreghdr *)skb_transport_header(skb);
- if (pim->type != ((PIM_VERSION << 4) | PIM_REGISTER) ||
+ if (pim->type != ((PIM_VERSION << 4) | PIM_TYPE_REGISTER) ||
(pim->flags & PIM_NULL_REGISTER) ||
(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
sizeof(*pim), IPPROTO_PIM,
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 1b9316e..54d165b 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -74,9 +74,10 @@ static int ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
return 0;
if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, skb->dev->ifindex, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0,
+ sock_net_uid(net, NULL));
else
- ip6_update_pmtu(skb, net, info, 0, 0);
+ ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
xfrm_state_put(x);
return 0;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 5330262..3ba5303 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -52,6 +52,7 @@
#include <net/udplite.h>
#include <net/xfrm.h>
#include <net/compat.h>
+#include <net/seg6.h>
#include <asm/uaccess.h>
@@ -120,6 +121,7 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
static bool setsockopt_needs_rtnl(int optname)
{
switch (optname) {
+ case IPV6_ADDRFORM:
case IPV6_ADD_MEMBERSHIP:
case IPV6_DROP_MEMBERSHIP:
case IPV6_JOIN_ANYCAST:
@@ -198,7 +200,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
}
fl6_free_socklist(sk);
- ipv6_sock_mc_close(sk);
+ __ipv6_sock_mc_close(sk);
/*
* Sock is moving from IPv6 to IPv4 (sk_prot), so
@@ -429,6 +431,15 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
break;
#endif
+ case IPV6_SRCRT_TYPE_4:
+ {
+ struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)
+ opt->srcrt;
+
+ if (!seg6_validate_srh(srh, optlen))
+ goto sticky_done;
+ break;
+ }
default:
goto sticky_done;
}
@@ -867,6 +878,10 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
np->autoflowlabel = valbool;
retv = 0;
break;
+ case IPV6_RECVFRAGSIZE:
+ np->rxopt.bits.recvfragsize = valbool;
+ retv = 0;
+ break;
}
release_sock(sk);
@@ -1309,6 +1324,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
val = np->autoflowlabel;
break;
+ case IPV6_RECVFRAGSIZE:
+ val = np->rxopt.bits.recvfragsize;
+ break;
+
default:
return -ENOPROTOOPT;
}
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 75c1fc5..14a3903 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -276,16 +276,14 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net,
return idev;
}
-void ipv6_sock_mc_close(struct sock *sk)
+void __ipv6_sock_mc_close(struct sock *sk)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6_mc_socklist *mc_lst;
struct net *net = sock_net(sk);
- if (!rcu_access_pointer(np->ipv6_mc_list))
- return;
+ ASSERT_RTNL();
- rtnl_lock();
while ((mc_lst = rtnl_dereference(np->ipv6_mc_list)) != NULL) {
struct net_device *dev;
@@ -303,8 +301,17 @@ void ipv6_sock_mc_close(struct sock *sk)
atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc);
kfree_rcu(mc_lst, rcu);
-
}
+}
+
+void ipv6_sock_mc_close(struct sock *sk)
+{
+ struct ipv6_pinfo *np = inet6_sk(sk);
+
+ if (!rcu_access_pointer(np->ipv6_mc_list))
+ return;
+ rtnl_lock();
+ __ipv6_sock_mc_close(sk);
rtnl_unlock();
}
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index d11c468..39970e2 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -26,6 +26,7 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
struct flowi6 fl6 = {
.flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
.flowi6_mark = skb->mark,
+ .flowi6_uid = sock_net_uid(net, skb->sk),
.daddr = iph->daddr,
.saddr = iph->saddr,
};
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index e10a04c..6acb2ee 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -25,6 +25,12 @@
To compile it as a module, choose M here. If unsure, say N.
+config NF_SOCKET_IPV6
+ tristate "IPv6 socket lookup support"
+ help
+ This option enables the IPv6 socket lookup infrastructure. This
+ is used by the ip6tables socket match.
+
if NF_TABLES
config NF_TABLES_IPV6
@@ -54,6 +60,14 @@
help
This module enables IPv6 packet duplication support for nf_tables.
+config NFT_FIB_IPV6
+ tristate "nf_tables fib / ipv6 route lookup support"
+ select NFT_FIB
+ help
+ This module enables IPv6 FIB lookups, e.g. for reverse path filtering.
+ It also allows query of the FIB for the route type, e.g. local, unicast,
+ multicast or blackhole.
+
endif # NF_TABLES_IPV6
endif # NF_TABLES
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index b4f7d0b..fe180c9 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -24,6 +24,8 @@
nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o
obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
+obj-$(CONFIG_NF_SOCKET_IPV6) += nf_socket_ipv6.o
+
# logging
obj-$(CONFIG_NF_LOG_IPV6) += nf_log_ipv6.o
@@ -40,6 +42,7 @@
obj-$(CONFIG_NFT_MASQ_IPV6) += nft_masq_ipv6.o
obj-$(CONFIG_NFT_REDIR_IPV6) += nft_redir_ipv6.o
obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o
+obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o
# matches
obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 55aacea..6ff42b8 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -291,11 +291,7 @@ ip6t_do_table(struct sk_buff *skb,
* rule is also a fragment-specific rule, non-fragments won't
* match it. */
acpar.hotdrop = false;
- acpar.net = state->net;
- acpar.in = state->in;
- acpar.out = state->out;
- acpar.family = NFPROTO_IPV6;
- acpar.hooknum = hook;
+ acpar.state = state;
IP_NF_ASSERT(table->valid_hooks & (1 << hook));
@@ -1007,7 +1003,7 @@ static int get_info(struct net *net, void __user *user,
#endif
t = try_then_request_module(xt_find_table_lock(net, AF_INET6, name),
"ip6table_%s", name);
- if (!IS_ERR_OR_NULL(t)) {
+ if (t) {
struct ip6t_getinfo info;
const struct xt_table_info *private = t->private;
#ifdef CONFIG_COMPAT
@@ -1037,7 +1033,7 @@ static int get_info(struct net *net, void __user *user,
xt_table_unlock(t);
module_put(t->me);
} else
- ret = t ? PTR_ERR(t) : -ENOENT;
+ ret = -ENOENT;
#ifdef CONFIG_COMPAT
if (compat)
xt_compat_unlock(AF_INET6);
@@ -1063,7 +1059,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr,
get.name[sizeof(get.name) - 1] = '\0';
t = xt_find_table_lock(net, AF_INET6, get.name);
- if (!IS_ERR_OR_NULL(t)) {
+ if (t) {
struct xt_table_info *private = t->private;
if (get.size == private->size)
ret = copy_entries_to_user(private->size,
@@ -1074,7 +1070,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr,
module_put(t->me);
xt_table_unlock(t);
} else
- ret = t ? PTR_ERR(t) : -ENOENT;
+ ret = -ENOENT;
return ret;
}
@@ -1099,8 +1095,8 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
t = try_then_request_module(xt_find_table_lock(net, AF_INET6, name),
"ip6table_%s", name);
- if (IS_ERR_OR_NULL(t)) {
- ret = t ? PTR_ERR(t) : -ENOENT;
+ if (!t) {
+ ret = -ENOENT;
goto free_newinfo_counters_untrans;
}
@@ -1214,8 +1210,8 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len,
if (IS_ERR(paddc))
return PTR_ERR(paddc);
t = xt_find_table_lock(net, AF_INET6, tmp.name);
- if (IS_ERR_OR_NULL(t)) {
- ret = t ? PTR_ERR(t) : -ENOENT;
+ if (!t) {
+ ret = -ENOENT;
goto free;
}
@@ -1651,7 +1647,7 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr,
xt_compat_lock(AF_INET6);
t = xt_find_table_lock(net, AF_INET6, get.name);
- if (!IS_ERR_OR_NULL(t)) {
+ if (t) {
const struct xt_table_info *private = t->private;
struct xt_table_info info;
ret = compat_table_info(private, &info);
@@ -1665,7 +1661,7 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr,
module_put(t->me);
xt_table_unlock(t);
} else
- ret = t ? PTR_ERR(t) : -ENOENT;
+ ret = -ENOENT;
xt_compat_unlock(AF_INET6);
return ret;
diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c
index 7f9f45d..2b1a158 100644
--- a/net/ipv6/netfilter/ip6t_MASQUERADE.c
+++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c
@@ -24,7 +24,7 @@
static unsigned int
masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par)
{
- return nf_nat_masquerade_ipv6(skb, par->targinfo, par->out);
+ return nf_nat_masquerade_ipv6(skb, par->targinfo, xt_out(par));
}
static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par)
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index db29bbf..fa51a20 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -39,35 +39,40 @@ static unsigned int
reject_tg6(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct ip6t_reject_info *reject = par->targinfo;
- struct net *net = par->net;
+ struct net *net = xt_net(par);
switch (reject->with) {
case IP6T_ICMP6_NO_ROUTE:
- nf_send_unreach6(net, skb, ICMPV6_NOROUTE, par->hooknum);
+ nf_send_unreach6(net, skb, ICMPV6_NOROUTE, xt_hooknum(par));
break;
case IP6T_ICMP6_ADM_PROHIBITED:
- nf_send_unreach6(net, skb, ICMPV6_ADM_PROHIBITED, par->hooknum);
+ nf_send_unreach6(net, skb, ICMPV6_ADM_PROHIBITED,
+ xt_hooknum(par));
break;
case IP6T_ICMP6_NOT_NEIGHBOUR:
- nf_send_unreach6(net, skb, ICMPV6_NOT_NEIGHBOUR, par->hooknum);
+ nf_send_unreach6(net, skb, ICMPV6_NOT_NEIGHBOUR,
+ xt_hooknum(par));
break;
case IP6T_ICMP6_ADDR_UNREACH:
- nf_send_unreach6(net, skb, ICMPV6_ADDR_UNREACH, par->hooknum);
+ nf_send_unreach6(net, skb, ICMPV6_ADDR_UNREACH,
+ xt_hooknum(par));
break;
case IP6T_ICMP6_PORT_UNREACH:
- nf_send_unreach6(net, skb, ICMPV6_PORT_UNREACH, par->hooknum);
+ nf_send_unreach6(net, skb, ICMPV6_PORT_UNREACH,
+ xt_hooknum(par));
break;
case IP6T_ICMP6_ECHOREPLY:
/* Do nothing */
break;
case IP6T_TCP_RESET:
- nf_send_reset6(net, skb, par->hooknum);
+ nf_send_reset6(net, skb, xt_hooknum(par));
break;
case IP6T_ICMP6_POLICY_FAIL:
- nf_send_unreach6(net, skb, ICMPV6_POLICY_FAIL, par->hooknum);
+ nf_send_unreach6(net, skb, ICMPV6_POLICY_FAIL, xt_hooknum(par));
break;
case IP6T_ICMP6_REJECT_ROUTE:
- nf_send_unreach6(net, skb, ICMPV6_REJECT_ROUTE, par->hooknum);
+ nf_send_unreach6(net, skb, ICMPV6_REJECT_ROUTE,
+ xt_hooknum(par));
break;
}
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index 06bed74..99a1216 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -277,12 +277,12 @@ static unsigned int
synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_synproxy_info *info = par->targinfo;
- struct net *net = par->net;
+ struct net *net = xt_net(par);
struct synproxy_net *snet = synproxy_pernet(net);
struct synproxy_options opts = {};
struct tcphdr *th, _th;
- if (nf_ip6_checksum(skb, par->hooknum, par->thoff, IPPROTO_TCP))
+ if (nf_ip6_checksum(skb, xt_hooknum(par), par->thoff, IPPROTO_TCP))
return NF_DROP;
th = skb_header_pointer(skb, par->thoff, sizeof(_th), &_th);
diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c
index 1ee1b25..d5263dc 100644
--- a/net/ipv6/netfilter/ip6t_rpfilter.c
+++ b/net/ipv6/netfilter/ip6t_rpfilter.c
@@ -93,7 +93,8 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
if (unlikely(saddrtype == IPV6_ADDR_ANY))
return true ^ invert; /* not routable: forward path will drop it */
- return rpfilter_lookup_reverse6(par->net, skb, par->in, info->flags) ^ invert;
+ return rpfilter_lookup_reverse6(xt_net(par), skb, xt_in(par),
+ info->flags) ^ invert;
}
static int rpfilter_check(const struct xt_mtchk_param *par)
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 963ee38..500be28 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -336,47 +336,35 @@ static struct nf_sockopt_ops so_getorigdst6 = {
.owner = THIS_MODULE,
};
+static struct nf_conntrack_l4proto *builtin_l4proto6[] = {
+ &nf_conntrack_l4proto_tcp6,
+ &nf_conntrack_l4proto_udp6,
+ &nf_conntrack_l4proto_icmpv6,
+};
+
static int ipv6_net_init(struct net *net)
{
int ret = 0;
- ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_tcp6);
- if (ret < 0) {
- pr_err("nf_conntrack_tcp6: pernet registration failed\n");
- goto out;
- }
- ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udp6);
- if (ret < 0) {
- pr_err("nf_conntrack_udp6: pernet registration failed\n");
- goto cleanup_tcp6;
- }
- ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_icmpv6);
- if (ret < 0) {
- pr_err("nf_conntrack_icmp6: pernet registration failed\n");
- goto cleanup_udp6;
- }
+ ret = nf_ct_l4proto_pernet_register(net, builtin_l4proto6,
+ ARRAY_SIZE(builtin_l4proto6));
+ if (ret < 0)
+ return ret;
+
ret = nf_ct_l3proto_pernet_register(net, &nf_conntrack_l3proto_ipv6);
if (ret < 0) {
pr_err("nf_conntrack_ipv6: pernet registration failed.\n");
- goto cleanup_icmpv6;
+ nf_ct_l4proto_pernet_unregister(net, builtin_l4proto6,
+ ARRAY_SIZE(builtin_l4proto6));
}
- return 0;
- cleanup_icmpv6:
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmpv6);
- cleanup_udp6:
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp6);
- cleanup_tcp6:
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp6);
- out:
return ret;
}
static void ipv6_net_exit(struct net *net)
{
nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv6);
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmpv6);
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp6);
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp6);
+ nf_ct_l4proto_pernet_unregister(net, builtin_l4proto6,
+ ARRAY_SIZE(builtin_l4proto6));
}
static struct pernet_operations ipv6_net_ops = {
@@ -409,37 +397,20 @@ static int __init nf_conntrack_l3proto_ipv6_init(void)
goto cleanup_pernet;
}
- ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_tcp6);
- if (ret < 0) {
- pr_err("nf_conntrack_ipv6: can't register tcp6 proto.\n");
+ ret = nf_ct_l4proto_register(builtin_l4proto6,
+ ARRAY_SIZE(builtin_l4proto6));
+ if (ret < 0)
goto cleanup_hooks;
- }
-
- ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udp6);
- if (ret < 0) {
- pr_err("nf_conntrack_ipv6: can't register udp6 proto.\n");
- goto cleanup_tcp6;
- }
-
- ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_icmpv6);
- if (ret < 0) {
- pr_err("nf_conntrack_ipv6: can't register icmpv6 proto.\n");
- goto cleanup_udp6;
- }
ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv6);
if (ret < 0) {
pr_err("nf_conntrack_ipv6: can't register ipv6 proto.\n");
- goto cleanup_icmpv6;
+ goto cleanup_l4proto;
}
return ret;
-
- cleanup_icmpv6:
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmpv6);
- cleanup_udp6:
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp6);
- cleanup_tcp6:
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp6);
+cleanup_l4proto:
+ nf_ct_l4proto_unregister(builtin_l4proto6,
+ ARRAY_SIZE(builtin_l4proto6));
cleanup_hooks:
nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops));
cleanup_pernet:
@@ -453,9 +424,8 @@ static void __exit nf_conntrack_l3proto_ipv6_fini(void)
{
synchronize_net();
nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv6);
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp6);
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp6);
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmpv6);
+ nf_ct_l4proto_unregister(builtin_l4proto6,
+ ARRAY_SIZE(builtin_l4proto6));
nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops));
unregister_pernet_subsys(&ipv6_net_ops);
nf_unregister_sockopt(&so_getorigdst6);
diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c
new file mode 100644
index 0000000..ebb2bf8
--- /dev/null
+++ b/net/ipv6/netfilter/nf_socket_ipv6.c
@@ -0,0 +1,151 @@
+/*
+ * Copyright (C) 2007-2008 BalaBit IT Ltd.
+ * Author: Krisztian Kovacs
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <net/tcp.h>
+#include <net/udp.h>
+#include <net/icmp.h>
+#include <net/sock.h>
+#include <net/inet_sock.h>
+#include <net/inet6_hashtables.h>
+#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+#include <net/netfilter/nf_socket.h>
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack.h>
+#endif
+
+static int
+extract_icmp6_fields(const struct sk_buff *skb,
+ unsigned int outside_hdrlen,
+ int *protocol,
+ const struct in6_addr **raddr,
+ const struct in6_addr **laddr,
+ __be16 *rport,
+ __be16 *lport,
+ struct ipv6hdr *ipv6_var)
+{
+ const struct ipv6hdr *inside_iph;
+ struct icmp6hdr *icmph, _icmph;
+ __be16 *ports, _ports[2];
+ u8 inside_nexthdr;
+ __be16 inside_fragoff;
+ int inside_hdrlen;
+
+ icmph = skb_header_pointer(skb, outside_hdrlen,
+ sizeof(_icmph), &_icmph);
+ if (icmph == NULL)
+ return 1;
+
+ if (icmph->icmp6_type & ICMPV6_INFOMSG_MASK)
+ return 1;
+
+ inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(_icmph),
+ sizeof(*ipv6_var), ipv6_var);
+ if (inside_iph == NULL)
+ return 1;
+ inside_nexthdr = inside_iph->nexthdr;
+
+ inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) +
+ sizeof(*ipv6_var),
+ &inside_nexthdr, &inside_fragoff);
+ if (inside_hdrlen < 0)
+ return 1; /* hjm: Packet has no/incomplete transport layer headers. */
+
+ if (inside_nexthdr != IPPROTO_TCP &&
+ inside_nexthdr != IPPROTO_UDP)
+ return 1;
+
+ ports = skb_header_pointer(skb, inside_hdrlen,
+ sizeof(_ports), &_ports);
+ if (ports == NULL)
+ return 1;
+
+ /* the inside IP packet is the one quoted from our side, thus
+ * its saddr is the local address */
+ *protocol = inside_nexthdr;
+ *laddr = &inside_iph->saddr;
+ *lport = ports[0];
+ *raddr = &inside_iph->daddr;
+ *rport = ports[1];
+
+ return 0;
+}
+
+static struct sock *
+nf_socket_get_sock_v6(struct net *net, struct sk_buff *skb, int doff,
+ const u8 protocol,
+ const struct in6_addr *saddr, const struct in6_addr *daddr,
+ const __be16 sport, const __be16 dport,
+ const struct net_device *in)
+{
+ switch (protocol) {
+ case IPPROTO_TCP:
+ return inet6_lookup(net, &tcp_hashinfo, skb, doff,
+ saddr, sport, daddr, dport,
+ in->ifindex);
+ case IPPROTO_UDP:
+ return udp6_lib_lookup(net, saddr, sport, daddr, dport,
+ in->ifindex);
+ }
+
+ return NULL;
+}
+
+struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
+ const struct net_device *indev)
+{
+ __be16 uninitialized_var(dport), uninitialized_var(sport);
+ const struct in6_addr *daddr = NULL, *saddr = NULL;
+ struct ipv6hdr *iph = ipv6_hdr(skb);
+ struct sk_buff *data_skb = NULL;
+ int doff = 0;
+ int thoff = 0, tproto;
+
+ tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
+ if (tproto < 0) {
+ pr_debug("unable to find transport header in IPv6 packet, dropping\n");
+ return NULL;
+ }
+
+ if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) {
+ struct udphdr _hdr, *hp;
+
+ hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr);
+ if (hp == NULL)
+ return NULL;
+
+ saddr = &iph->saddr;
+ sport = hp->source;
+ daddr = &iph->daddr;
+ dport = hp->dest;
+ data_skb = (struct sk_buff *)skb;
+ doff = tproto == IPPROTO_TCP ?
+ thoff + __tcp_hdrlen((struct tcphdr *)hp) :
+ thoff + sizeof(*hp);
+
+ } else if (tproto == IPPROTO_ICMPV6) {
+ struct ipv6hdr ipv6_var;
+
+ if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr,
+ &sport, &dport, &ipv6_var))
+ return NULL;
+ } else {
+ return NULL;
+ }
+
+ return nf_socket_get_sock_v6(net, data_skb, doff, tproto, saddr, daddr,
+ sport, dport, indev);
+}
+EXPORT_SYMBOL_GPL(nf_sk_lookup_slow_v6);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Krisztian Kovacs, Balazs Scheidler");
+MODULE_DESCRIPTION("Netfilter IPv6 socket lookup infrastructure");
diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c
index 8bfd470..d8b5b60 100644
--- a/net/ipv6/netfilter/nft_dup_ipv6.c
+++ b/net/ipv6/netfilter/nft_dup_ipv6.c
@@ -26,9 +26,9 @@ static void nft_dup_ipv6_eval(const struct nft_expr *expr,
{
struct nft_dup_ipv6 *priv = nft_expr_priv(expr);
struct in6_addr *gw = (struct in6_addr *)®s->data[priv->sreg_addr];
- int oif = regs->data[priv->sreg_dev];
+ int oif = priv->sreg_dev ? regs->data[priv->sreg_dev] : -1;
- nf_dup_ipv6(pkt->net, pkt->skb, pkt->hook, gw, oif);
+ nf_dup_ipv6(nft_net(pkt), pkt->skb, nft_hook(pkt), gw, oif);
}
static int nft_dup_ipv6_init(const struct nft_ctx *ctx,
@@ -57,7 +57,9 @@ static int nft_dup_ipv6_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
struct nft_dup_ipv6 *priv = nft_expr_priv(expr);
- if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) ||
+ if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr))
+ goto nla_put_failure;
+ if (priv->sreg_dev &&
nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev))
goto nla_put_failure;
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
new file mode 100644
index 0000000..d526bb5
--- /dev/null
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -0,0 +1,275 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <linux/netfilter_ipv6.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_fib.h>
+
+#include <net/ip6_fib.h>
+#include <net/ip6_route.h>
+
+static bool fib6_is_local(const struct sk_buff *skb)
+{
+ const struct rt6_info *rt = (const void *)skb_dst(skb);
+
+ return rt && (rt->rt6i_flags & RTF_LOCAL);
+}
+
+static int get_ifindex(const struct net_device *dev)
+{
+ return dev ? dev->ifindex : 0;
+}
+
+static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv,
+ const struct nft_pktinfo *pkt,
+ const struct net_device *dev)
+{
+ const struct ipv6hdr *iph = ipv6_hdr(pkt->skb);
+ int lookup_flags = 0;
+
+ if (priv->flags & NFTA_FIB_F_DADDR) {
+ fl6->daddr = iph->daddr;
+ fl6->saddr = iph->saddr;
+ } else {
+ fl6->daddr = iph->saddr;
+ fl6->saddr = iph->daddr;
+ }
+
+ if (ipv6_addr_type(&fl6->daddr) & IPV6_ADDR_LINKLOCAL) {
+ lookup_flags |= RT6_LOOKUP_F_IFACE;
+ fl6->flowi6_oif = get_ifindex(dev ? dev : pkt->skb->dev);
+ }
+
+ if (ipv6_addr_type(&fl6->saddr) & IPV6_ADDR_UNICAST)
+ lookup_flags |= RT6_LOOKUP_F_HAS_SADDR;
+
+ if (priv->flags & NFTA_FIB_F_MARK)
+ fl6->flowi6_mark = pkt->skb->mark;
+
+ fl6->flowlabel = (*(__be32 *)iph) & IPV6_FLOWINFO_MASK;
+
+ return lookup_flags;
+}
+
+static u32 __nft_fib6_eval_type(const struct nft_fib *priv,
+ const struct nft_pktinfo *pkt)
+{
+ const struct net_device *dev = NULL;
+ const struct nf_ipv6_ops *v6ops;
+ const struct nf_afinfo *afinfo;
+ int route_err, addrtype;
+ struct rt6_info *rt;
+ struct flowi6 fl6 = {
+ .flowi6_iif = LOOPBACK_IFINDEX,
+ .flowi6_proto = pkt->tprot,
+ };
+ u32 ret = 0;
+
+ afinfo = nf_get_afinfo(NFPROTO_IPV6);
+ if (!afinfo)
+ return RTN_UNREACHABLE;
+
+ if (priv->flags & NFTA_FIB_F_IIF)
+ dev = nft_in(pkt);
+ else if (priv->flags & NFTA_FIB_F_OIF)
+ dev = nft_out(pkt);
+
+ nft_fib6_flowi_init(&fl6, priv, pkt, dev);
+
+ v6ops = nf_get_ipv6_ops();
+ if (dev && v6ops && v6ops->chk_addr(nft_net(pkt), &fl6.daddr, dev, true))
+ ret = RTN_LOCAL;
+
+ route_err = afinfo->route(nft_net(pkt), (struct dst_entry **)&rt,
+ flowi6_to_flowi(&fl6), false);
+ if (route_err)
+ goto err;
+
+ if (rt->rt6i_flags & RTF_REJECT) {
+ route_err = rt->dst.error;
+ dst_release(&rt->dst);
+ goto err;
+ }
+
+ if (ipv6_anycast_destination((struct dst_entry *)rt, &fl6.daddr))
+ ret = RTN_ANYCAST;
+ else if (!dev && rt->rt6i_flags & RTF_LOCAL)
+ ret = RTN_LOCAL;
+
+ dst_release(&rt->dst);
+
+ if (ret)
+ return ret;
+
+ addrtype = ipv6_addr_type(&fl6.daddr);
+
+ if (addrtype & IPV6_ADDR_MULTICAST)
+ return RTN_MULTICAST;
+ if (addrtype & IPV6_ADDR_UNICAST)
+ return RTN_UNICAST;
+
+ return RTN_UNSPEC;
+ err:
+ switch (route_err) {
+ case -EINVAL:
+ return RTN_BLACKHOLE;
+ case -EACCES:
+ return RTN_PROHIBIT;
+ case -EAGAIN:
+ return RTN_THROW;
+ default:
+ break;
+ }
+
+ return RTN_UNREACHABLE;
+}
+
+void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_fib *priv = nft_expr_priv(expr);
+ u32 *dest = ®s->data[priv->dreg];
+
+ *dest = __nft_fib6_eval_type(priv, pkt);
+}
+EXPORT_SYMBOL_GPL(nft_fib6_eval_type);
+
+void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_fib *priv = nft_expr_priv(expr);
+ const struct net_device *oif = NULL;
+ u32 *dest = ®s->data[priv->dreg];
+ struct flowi6 fl6 = {
+ .flowi6_iif = LOOPBACK_IFINDEX,
+ .flowi6_proto = pkt->tprot,
+ };
+ struct rt6_info *rt;
+ int lookup_flags;
+
+ if (priv->flags & NFTA_FIB_F_IIF)
+ oif = nft_in(pkt);
+ else if (priv->flags & NFTA_FIB_F_OIF)
+ oif = nft_out(pkt);
+
+ lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif);
+
+ if (nft_hook(pkt) == NF_INET_PRE_ROUTING && fib6_is_local(pkt->skb)) {
+ nft_fib_store_result(dest, priv->result, pkt, LOOPBACK_IFINDEX);
+ return;
+ }
+
+ *dest = 0;
+ again:
+ rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, lookup_flags);
+ if (rt->dst.error)
+ goto put_rt_err;
+
+ /* Should not see RTF_LOCAL here */
+ if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL))
+ goto put_rt_err;
+
+ if (oif && oif != rt->rt6i_idev->dev) {
+ /* multipath route? Try again with F_IFACE */
+ if ((lookup_flags & RT6_LOOKUP_F_IFACE) == 0) {
+ lookup_flags |= RT6_LOOKUP_F_IFACE;
+ fl6.flowi6_oif = oif->ifindex;
+ ip6_rt_put(rt);
+ goto again;
+ }
+ }
+
+ switch (priv->result) {
+ case NFT_FIB_RESULT_OIF:
+ *dest = rt->rt6i_idev->dev->ifindex;
+ break;
+ case NFT_FIB_RESULT_OIFNAME:
+ strncpy((char *)dest, rt->rt6i_idev->dev->name, IFNAMSIZ);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ break;
+ }
+
+ put_rt_err:
+ ip6_rt_put(rt);
+}
+EXPORT_SYMBOL_GPL(nft_fib6_eval);
+
+static struct nft_expr_type nft_fib6_type;
+
+static const struct nft_expr_ops nft_fib6_type_ops = {
+ .type = &nft_fib6_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)),
+ .eval = nft_fib6_eval_type,
+ .init = nft_fib_init,
+ .dump = nft_fib_dump,
+ .validate = nft_fib_validate,
+};
+
+static const struct nft_expr_ops nft_fib6_ops = {
+ .type = &nft_fib6_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)),
+ .eval = nft_fib6_eval,
+ .init = nft_fib_init,
+ .dump = nft_fib_dump,
+ .validate = nft_fib_validate,
+};
+
+static const struct nft_expr_ops *
+nft_fib6_select_ops(const struct nft_ctx *ctx,
+ const struct nlattr * const tb[])
+{
+ enum nft_fib_result result;
+
+ if (!tb[NFTA_FIB_RESULT])
+ return ERR_PTR(-EINVAL);
+
+ result = htonl(nla_get_be32(tb[NFTA_FIB_RESULT]));
+
+ switch (result) {
+ case NFT_FIB_RESULT_OIF:
+ return &nft_fib6_ops;
+ case NFT_FIB_RESULT_OIFNAME:
+ return &nft_fib6_ops;
+ case NFT_FIB_RESULT_ADDRTYPE:
+ return &nft_fib6_type_ops;
+ default:
+ return ERR_PTR(-EOPNOTSUPP);
+ }
+}
+
+static struct nft_expr_type nft_fib6_type __read_mostly = {
+ .name = "fib",
+ .select_ops = &nft_fib6_select_ops,
+ .policy = nft_fib_policy,
+ .maxattr = NFTA_FIB_MAX,
+ .family = NFPROTO_IPV6,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_fib6_module_init(void)
+{
+ return nft_register_expr(&nft_fib6_type);
+}
+
+static void __exit nft_fib6_module_exit(void)
+{
+ nft_unregister_expr(&nft_fib6_type);
+}
+module_init(nft_fib6_module_init);
+module_exit(nft_fib6_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
+MODULE_ALIAS_NFT_AF_EXPR(10, "fib");
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
index 9597ffb..a2aff12 100644
--- a/net/ipv6/netfilter/nft_masq_ipv6.c
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -32,7 +32,8 @@ static void nft_masq_ipv6_eval(const struct nft_expr *expr,
range.max_proto.all =
*(__be16 *)®s->data[priv->sreg_proto_max];
}
- regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range, pkt->out);
+ regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range,
+ nft_out(pkt));
}
static struct nft_expr_type nft_masq_ipv6_type;
diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c
index aca44e8..bfcd5af 100644
--- a/net/ipv6/netfilter/nft_redir_ipv6.c
+++ b/net/ipv6/netfilter/nft_redir_ipv6.c
@@ -35,7 +35,8 @@ static void nft_redir_ipv6_eval(const struct nft_expr *expr,
range.flags |= priv->flags;
- regs->verdict.code = nf_nat_redirect_ipv6(pkt->skb, &range, pkt->hook);
+ regs->verdict.code =
+ nf_nat_redirect_ipv6(pkt->skb, &range, nft_hook(pkt));
}
static struct nft_expr_type nft_redir_ipv6_type;
diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c
index 92bda99..057deea 100644
--- a/net/ipv6/netfilter/nft_reject_ipv6.c
+++ b/net/ipv6/netfilter/nft_reject_ipv6.c
@@ -27,11 +27,11 @@ static void nft_reject_ipv6_eval(const struct nft_expr *expr,
switch (priv->type) {
case NFT_REJECT_ICMP_UNREACH:
- nf_send_unreach6(pkt->net, pkt->skb, priv->icmp_code,
- pkt->hook);
+ nf_send_unreach6(nft_net(pkt), pkt->skb, priv->icmp_code,
+ nft_hook(pkt));
break;
case NFT_REJECT_TCP_RST:
- nf_send_reset6(pkt->net, pkt->skb, pkt->hook);
+ nf_send_reset6(nft_net(pkt), pkt->skb, nft_hook(pkt));
break;
default:
break;
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 0e983b6..e1f8b34 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -113,6 +113,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.daddr = *daddr;
fl6.flowi6_oif = oif;
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sk->sk_uid;
fl6.fl6_icmp_type = user_icmph.icmp6_type;
fl6.fl6_icmp_code = user_icmph.icmp6_code;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
@@ -180,7 +181,7 @@ struct proto pingv6_prot = {
.init = ping_init_sock,
.close = ping_close,
.connect = ip6_datagram_connect_v6_only,
- .disconnect = udp_disconnect,
+ .disconnect = __udp_disconnect,
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
.sendmsg = ping_v6_sendmsg,
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index d7e8b95..291ebc2 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -776,6 +776,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sk->sk_uid;
ipc6.hlimit = -1;
ipc6.tclass = -1;
@@ -1243,7 +1244,7 @@ struct proto rawv6_prot = {
.close = rawv6_close,
.destroy = raw6_destroy,
.connect = ip6_datagram_connect_v6_only,
- .disconnect = udp_disconnect,
+ .disconnect = __udp_disconnect,
.ioctl = rawv6_ioctl,
.init = rawv6_init_sk,
.setsockopt = rawv6_setsockopt,
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 2160d5d..e1da5b8 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -211,7 +211,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
{
struct sk_buff *prev, *next;
struct net_device *dev;
- int offset, end;
+ int offset, end, fragsize;
struct net *net = dev_net(skb_dst(skb)->dev);
u8 ecn;
@@ -336,6 +336,10 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
fq->ecn |= ecn;
add_frag_mem_limit(fq->q.net, skb->truesize);
+ fragsize = -skb_network_offset(skb) + skb->len;
+ if (fragsize > fq->q.max_size)
+ fq->q.max_size = fragsize;
+
/* The first fragment.
* nhoffset is obtained from the first fragment, of course.
*/
@@ -456,7 +460,8 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
skb_network_header(head)[nhoff] = skb_transport_header(head)[0];
memmove(head->head + sizeof(struct frag_hdr), head->head,
(head->data - head->head) - sizeof(struct frag_hdr));
- head->mac_header += sizeof(struct frag_hdr);
+ if (skb_mac_header_was_set(head))
+ head->mac_header += sizeof(struct frag_hdr);
head->network_header += sizeof(struct frag_hdr);
skb_reset_transport_header(head);
@@ -494,6 +499,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn);
IP6CB(head)->nhoff = nhoff;
IP6CB(head)->flags |= IP6SKB_FRAGMENTED;
+ IP6CB(head)->frag_max_size = fq->q.max_size;
/* Yes, and fold redundant checksum back. 8) */
skb_postpush_rcsum(head, skb_network_header(head),
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index bdbc38e..b317bb1 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -102,11 +102,13 @@ static int rt6_score_route(struct rt6_info *rt, int oif, int strict);
#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_add_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex,
+ const struct in6_addr *gwaddr,
+ struct net_device *dev,
unsigned int pref);
static struct rt6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex);
+ const struct in6_addr *gwaddr,
+ struct net_device *dev);
#endif
struct uncached_list {
@@ -656,7 +658,8 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
struct net_device *dev = rt->dst.dev;
if (dev && !netif_carrier_ok(dev) &&
- idev->cnf.ignore_routes_with_linkdown)
+ idev->cnf.ignore_routes_with_linkdown &&
+ !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE))
goto out;
if (rt6_check_expired(rt))
@@ -803,7 +806,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
rt = rt6_get_dflt_router(gwaddr, dev);
else
rt = rt6_get_route_info(net, prefix, rinfo->prefix_len,
- gwaddr, dev->ifindex);
+ gwaddr, dev);
if (rt && !lifetime) {
ip6_del_rt(rt);
@@ -811,8 +814,8 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
}
if (!rt && lifetime)
- rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev->ifindex,
- pref);
+ rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr,
+ dev, pref);
else if (rt)
rt->rt6i_flags = RTF_ROUTEINFO |
(rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
@@ -1050,6 +1053,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
int strict = 0;
strict |= flags & RT6_LOOKUP_F_IFACE;
+ strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
if (net->ipv6.devconf_all->forwarding == 0)
strict |= RT6_LOOKUP_F_REACHABLE;
@@ -1360,6 +1364,9 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
if (rt6->rt6i_flags & RTF_LOCAL)
return;
+ if (dst_metric_locked(dst, RTAX_MTU))
+ return;
+
dst_confirm(dst);
mtu = max_t(u32, mtu, IPV6_MIN_MTU);
if (mtu >= dst_mtu(dst))
@@ -1401,7 +1408,7 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
}
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
- int oif, u32 mark)
+ int oif, u32 mark, kuid_t uid)
{
const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
struct dst_entry *dst;
@@ -1413,6 +1420,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = ip6_flowinfo(iph);
+ fl6.flowi6_uid = uid;
dst = ip6_route_output(net, NULL, &fl6);
if (!dst->error)
@@ -1426,7 +1434,7 @@ void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
struct dst_entry *dst;
ip6_update_pmtu(skb, sock_net(sk), mtu,
- sk->sk_bound_dev_if, sk->sk_mark);
+ sk->sk_bound_dev_if, sk->sk_mark, sk->sk_uid);
dst = __sk_dst_get(sk);
if (!dst || !dst->obsolete ||
@@ -1518,7 +1526,8 @@ static struct dst_entry *ip6_route_redirect(struct net *net,
flags, __ip6_route_redirect);
}
-void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
+void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark,
+ kuid_t uid)
{
const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
struct dst_entry *dst;
@@ -1531,6 +1540,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
fl6.daddr = iph->daddr;
fl6.saddr = iph->saddr;
fl6.flowlabel = ip6_flowinfo(iph);
+ fl6.flowi6_uid = uid;
dst = ip6_route_redirect(net, &fl6, &ipv6_hdr(skb)->saddr);
rt6_do_redirect(dst, NULL, skb);
@@ -1552,6 +1562,7 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
fl6.flowi6_mark = mark;
fl6.daddr = msg->dest;
fl6.saddr = iph->daddr;
+ fl6.flowi6_uid = sock_net_uid(net, NULL);
dst = ip6_route_redirect(net, &fl6, &iph->saddr);
rt6_do_redirect(dst, NULL, skb);
@@ -1560,7 +1571,8 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk)
{
- ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark);
+ ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, sk->sk_mark,
+ sk->sk_uid);
}
EXPORT_SYMBOL_GPL(ip6_sk_redirect);
@@ -1789,7 +1801,7 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net,
};
struct fib6_table *table;
struct rt6_info *rt;
- int flags = RT6_LOOKUP_F_IFACE;
+ int flags = RT6_LOOKUP_F_IFACE | RT6_LOOKUP_F_IGNORE_LINKSTATE;
table = fib6_get_table(net, cfg->fc_table);
if (!table)
@@ -2325,13 +2337,16 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex)
+ const struct in6_addr *gwaddr,
+ struct net_device *dev)
{
+ u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO;
+ int ifindex = dev->ifindex;
struct fib6_node *fn;
struct rt6_info *rt = NULL;
struct fib6_table *table;
- table = fib6_get_table(net, RT6_TABLE_INFO);
+ table = fib6_get_table(net, tb_id);
if (!table)
return NULL;
@@ -2357,12 +2372,13 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
static struct rt6_info *rt6_add_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
- const struct in6_addr *gwaddr, int ifindex,
+ const struct in6_addr *gwaddr,
+ struct net_device *dev,
unsigned int pref)
{
struct fib6_config cfg = {
.fc_metric = IP6_RT_PRIO_USER,
- .fc_ifindex = ifindex,
+ .fc_ifindex = dev->ifindex,
.fc_dst_len = prefixlen,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
RTF_UP | RTF_PREF(pref),
@@ -2371,7 +2387,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
.fc_nlinfo.nl_net = net,
};
- cfg.fc_table = l3mdev_fib_table_by_index(net, ifindex) ? : RT6_TABLE_INFO;
+ cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO,
cfg.fc_dst = *prefix;
cfg.fc_gateway = *gwaddr;
@@ -2381,16 +2397,17 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
ip6_route_add(&cfg);
- return rt6_get_route_info(net, prefix, prefixlen, gwaddr, ifindex);
+ return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev);
}
#endif
struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_device *dev)
{
+ u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT;
struct rt6_info *rt;
struct fib6_table *table;
- table = fib6_get_table(dev_net(dev), RT6_TABLE_DFLT);
+ table = fib6_get_table(dev_net(dev), tb_id);
if (!table)
return NULL;
@@ -2424,20 +2441,20 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
cfg.fc_gateway = *gwaddr;
- ip6_route_add(&cfg);
+ if (!ip6_route_add(&cfg)) {
+ struct fib6_table *table;
+
+ table = fib6_get_table(dev_net(dev), cfg.fc_table);
+ if (table)
+ table->flags |= RT6_TABLE_HAS_DFLT_ROUTER;
+ }
return rt6_get_dflt_router(gwaddr, dev);
}
-void rt6_purge_dflt_routers(struct net *net)
+static void __rt6_purge_dflt_routers(struct fib6_table *table)
{
struct rt6_info *rt;
- struct fib6_table *table;
-
- /* NOTE: Keep consistent with rt6_get_dflt_router */
- table = fib6_get_table(net, RT6_TABLE_DFLT);
- if (!table)
- return;
restart:
read_lock_bh(&table->tb6_lock);
@@ -2451,6 +2468,27 @@ void rt6_purge_dflt_routers(struct net *net)
}
}
read_unlock_bh(&table->tb6_lock);
+
+ table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER;
+}
+
+void rt6_purge_dflt_routers(struct net *net)
+{
+ struct fib6_table *table;
+ struct hlist_head *head;
+ unsigned int h;
+
+ rcu_read_lock();
+
+ for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
+ head = &net->ipv6.fib_table_hash[h];
+ hlist_for_each_entry_rcu(table, head, tb6_hlist) {
+ if (table->flags & RT6_TABLE_HAS_DFLT_ROUTER)
+ __rt6_purge_dflt_routers(table);
+ }
+ }
+
+ rcu_read_unlock();
}
static void rtmsg_to_fib6_config(struct net *net,
@@ -2728,6 +2766,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
PMTU discouvery.
*/
if (rt->dst.dev == arg->dev &&
+ dst_metric_raw(&rt->dst, RTAX_MTU) &&
!dst_metric_locked(&rt->dst, RTAX_MTU)) {
if (rt->rt6i_flags & RTF_CACHE) {
/* For RTF_CACHE with rt6i_pmtu == 0
@@ -2767,6 +2806,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_ENCAP_TYPE] = { .type = NLA_U16 },
[RTA_ENCAP] = { .type = NLA_NESTED },
[RTA_EXPIRES] = { .type = NLA_U32 },
+ [RTA_UID] = { .type = NLA_U32 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -3341,6 +3381,12 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
if (tb[RTA_MARK])
fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]);
+ if (tb[RTA_UID])
+ fl6.flowi6_uid = make_kuid(current_user_ns(),
+ nla_get_u32(tb[RTA_UID]));
+ else
+ fl6.flowi6_uid = iif ? INVALID_UID : current_uid();
+
if (iif) {
struct net_device *dev;
int flags = 0;
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
new file mode 100644
index 0000000..b172d85
--- /dev/null
+++ b/net/ipv6/seg6.c
@@ -0,0 +1,495 @@
+/*
+ * SR-IPv6 implementation
+ *
+ * Author:
+ * David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/net.h>
+#include <linux/in6.h>
+#include <linux/slab.h>
+
+#include <net/ipv6.h>
+#include <net/protocol.h>
+
+#include <net/seg6.h>
+#include <net/genetlink.h>
+#include <linux/seg6.h>
+#include <linux/seg6_genl.h>
+#ifdef CONFIG_IPV6_SEG6_HMAC
+#include <net/seg6_hmac.h>
+#endif
+
+bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len)
+{
+ int trailing;
+ unsigned int tlv_offset;
+
+ if (srh->type != IPV6_SRCRT_TYPE_4)
+ return false;
+
+ if (((srh->hdrlen + 1) << 3) != len)
+ return false;
+
+ if (srh->segments_left != srh->first_segment)
+ return false;
+
+ tlv_offset = sizeof(*srh) + ((srh->first_segment + 1) << 4);
+
+ trailing = len - tlv_offset;
+ if (trailing < 0)
+ return false;
+
+ while (trailing) {
+ struct sr6_tlv *tlv;
+ unsigned int tlv_len;
+
+ tlv = (struct sr6_tlv *)((unsigned char *)srh + tlv_offset);
+ tlv_len = sizeof(*tlv) + tlv->len;
+
+ trailing -= tlv_len;
+ if (trailing < 0)
+ return false;
+
+ tlv_offset += tlv_len;
+ }
+
+ return true;
+}
+
+static struct genl_family seg6_genl_family;
+
+static const struct nla_policy seg6_genl_policy[SEG6_ATTR_MAX + 1] = {
+ [SEG6_ATTR_DST] = { .type = NLA_BINARY,
+ .len = sizeof(struct in6_addr) },
+ [SEG6_ATTR_DSTLEN] = { .type = NLA_S32, },
+ [SEG6_ATTR_HMACKEYID] = { .type = NLA_U32, },
+ [SEG6_ATTR_SECRET] = { .type = NLA_BINARY, },
+ [SEG6_ATTR_SECRETLEN] = { .type = NLA_U8, },
+ [SEG6_ATTR_ALGID] = { .type = NLA_U8, },
+ [SEG6_ATTR_HMACINFO] = { .type = NLA_NESTED, },
+};
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+
+static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ struct seg6_pernet_data *sdata;
+ struct seg6_hmac_info *hinfo;
+ u32 hmackeyid;
+ char *secret;
+ int err = 0;
+ u8 algid;
+ u8 slen;
+
+ sdata = seg6_pernet(net);
+
+ if (!info->attrs[SEG6_ATTR_HMACKEYID] ||
+ !info->attrs[SEG6_ATTR_SECRETLEN] ||
+ !info->attrs[SEG6_ATTR_ALGID])
+ return -EINVAL;
+
+ hmackeyid = nla_get_u32(info->attrs[SEG6_ATTR_HMACKEYID]);
+ slen = nla_get_u8(info->attrs[SEG6_ATTR_SECRETLEN]);
+ algid = nla_get_u8(info->attrs[SEG6_ATTR_ALGID]);
+
+ if (hmackeyid == 0)
+ return -EINVAL;
+
+ if (slen > SEG6_HMAC_SECRET_LEN)
+ return -EINVAL;
+
+ mutex_lock(&sdata->lock);
+ hinfo = seg6_hmac_info_lookup(net, hmackeyid);
+
+ if (!slen) {
+ if (!hinfo)
+ err = -ENOENT;
+
+ err = seg6_hmac_info_del(net, hmackeyid);
+
+ goto out_unlock;
+ }
+
+ if (!info->attrs[SEG6_ATTR_SECRET]) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
+
+ if (hinfo) {
+ err = seg6_hmac_info_del(net, hmackeyid);
+ if (err)
+ goto out_unlock;
+ }
+
+ secret = (char *)nla_data(info->attrs[SEG6_ATTR_SECRET]);
+
+ hinfo = kzalloc(sizeof(*hinfo), GFP_KERNEL);
+ if (!hinfo) {
+ err = -ENOMEM;
+ goto out_unlock;
+ }
+
+ memcpy(hinfo->secret, secret, slen);
+ hinfo->slen = slen;
+ hinfo->alg_id = algid;
+ hinfo->hmackeyid = hmackeyid;
+
+ err = seg6_hmac_info_add(net, hmackeyid, hinfo);
+ if (err)
+ kfree(hinfo);
+
+out_unlock:
+ mutex_unlock(&sdata->lock);
+ return err;
+}
+
+#else
+
+static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info)
+{
+ return -ENOTSUPP;
+}
+
+#endif
+
+static int seg6_genl_set_tunsrc(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ struct in6_addr *val, *t_old, *t_new;
+ struct seg6_pernet_data *sdata;
+
+ sdata = seg6_pernet(net);
+
+ if (!info->attrs[SEG6_ATTR_DST])
+ return -EINVAL;
+
+ val = nla_data(info->attrs[SEG6_ATTR_DST]);
+ t_new = kmemdup(val, sizeof(*val), GFP_KERNEL);
+
+ mutex_lock(&sdata->lock);
+
+ t_old = sdata->tun_src;
+ rcu_assign_pointer(sdata->tun_src, t_new);
+
+ mutex_unlock(&sdata->lock);
+
+ synchronize_net();
+ kfree(t_old);
+
+ return 0;
+}
+
+static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net *net = genl_info_net(info);
+ struct in6_addr *tun_src;
+ struct sk_buff *msg;
+ void *hdr;
+
+ msg = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq,
+ &seg6_genl_family, 0, SEG6_CMD_GET_TUNSRC);
+ if (!hdr)
+ goto free_msg;
+
+ rcu_read_lock();
+ tun_src = rcu_dereference(seg6_pernet(net)->tun_src);
+
+ if (nla_put(msg, SEG6_ATTR_DST, sizeof(struct in6_addr), tun_src))
+ goto nla_put_failure;
+
+ rcu_read_unlock();
+
+ genlmsg_end(msg, hdr);
+ genlmsg_reply(msg, info);
+
+ return 0;
+
+nla_put_failure:
+ rcu_read_unlock();
+ genlmsg_cancel(msg, hdr);
+free_msg:
+ nlmsg_free(msg);
+ return -ENOMEM;
+}
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+
+static int __seg6_hmac_fill_info(struct seg6_hmac_info *hinfo,
+ struct sk_buff *msg)
+{
+ if (nla_put_u32(msg, SEG6_ATTR_HMACKEYID, hinfo->hmackeyid) ||
+ nla_put_u8(msg, SEG6_ATTR_SECRETLEN, hinfo->slen) ||
+ nla_put(msg, SEG6_ATTR_SECRET, hinfo->slen, hinfo->secret) ||
+ nla_put_u8(msg, SEG6_ATTR_ALGID, hinfo->alg_id))
+ return -1;
+
+ return 0;
+}
+
+static int __seg6_genl_dumphmac_element(struct seg6_hmac_info *hinfo,
+ u32 portid, u32 seq, u32 flags,
+ struct sk_buff *skb, u8 cmd)
+{
+ void *hdr;
+
+ hdr = genlmsg_put(skb, portid, seq, &seg6_genl_family, flags, cmd);
+ if (!hdr)
+ return -ENOMEM;
+
+ if (__seg6_hmac_fill_info(hinfo, skb) < 0)
+ goto nla_put_failure;
+
+ genlmsg_end(skb, hdr);
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(skb, hdr);
+ return -EMSGSIZE;
+}
+
+static int seg6_genl_dumphmac_start(struct netlink_callback *cb)
+{
+ struct net *net = sock_net(cb->skb->sk);
+ struct seg6_pernet_data *sdata;
+ struct rhashtable_iter *iter;
+
+ sdata = seg6_pernet(net);
+ iter = (struct rhashtable_iter *)cb->args[0];
+
+ if (!iter) {
+ iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+ if (!iter)
+ return -ENOMEM;
+
+ cb->args[0] = (long)iter;
+ }
+
+ rhashtable_walk_enter(&sdata->hmac_infos, iter);
+
+ return 0;
+}
+
+static int seg6_genl_dumphmac_done(struct netlink_callback *cb)
+{
+ struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0];
+
+ rhashtable_walk_exit(iter);
+
+ kfree(iter);
+
+ return 0;
+}
+
+static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0];
+ struct net *net = sock_net(skb->sk);
+ struct seg6_pernet_data *sdata;
+ struct seg6_hmac_info *hinfo;
+ int ret;
+
+ sdata = seg6_pernet(net);
+
+ ret = rhashtable_walk_start(iter);
+ if (ret && ret != -EAGAIN)
+ goto done;
+
+ for (;;) {
+ hinfo = rhashtable_walk_next(iter);
+
+ if (IS_ERR(hinfo)) {
+ if (PTR_ERR(hinfo) == -EAGAIN)
+ continue;
+ ret = PTR_ERR(hinfo);
+ goto done;
+ } else if (!hinfo) {
+ break;
+ }
+
+ ret = __seg6_genl_dumphmac_element(hinfo,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NLM_F_MULTI,
+ skb, SEG6_CMD_DUMPHMAC);
+ if (ret)
+ goto done;
+ }
+
+ ret = skb->len;
+
+done:
+ rhashtable_walk_stop(iter);
+ return ret;
+}
+
+#else
+
+static int seg6_genl_dumphmac_start(struct netlink_callback *cb)
+{
+ return 0;
+}
+
+static int seg6_genl_dumphmac_done(struct netlink_callback *cb)
+{
+ return 0;
+}
+
+static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ return -ENOTSUPP;
+}
+
+#endif
+
+static int __net_init seg6_net_init(struct net *net)
+{
+ struct seg6_pernet_data *sdata;
+
+ sdata = kzalloc(sizeof(*sdata), GFP_KERNEL);
+ if (!sdata)
+ return -ENOMEM;
+
+ mutex_init(&sdata->lock);
+
+ sdata->tun_src = kzalloc(sizeof(*sdata->tun_src), GFP_KERNEL);
+ if (!sdata->tun_src) {
+ kfree(sdata);
+ return -ENOMEM;
+ }
+
+ net->ipv6.seg6_data = sdata;
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ seg6_hmac_net_init(net);
+#endif
+
+ return 0;
+}
+
+static void __net_exit seg6_net_exit(struct net *net)
+{
+ struct seg6_pernet_data *sdata = seg6_pernet(net);
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ seg6_hmac_net_exit(net);
+#endif
+
+ kfree(sdata->tun_src);
+ kfree(sdata);
+}
+
+static struct pernet_operations ip6_segments_ops = {
+ .init = seg6_net_init,
+ .exit = seg6_net_exit,
+};
+
+static const struct genl_ops seg6_genl_ops[] = {
+ {
+ .cmd = SEG6_CMD_SETHMAC,
+ .doit = seg6_genl_sethmac,
+ .policy = seg6_genl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = SEG6_CMD_DUMPHMAC,
+ .start = seg6_genl_dumphmac_start,
+ .dumpit = seg6_genl_dumphmac,
+ .done = seg6_genl_dumphmac_done,
+ .policy = seg6_genl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = SEG6_CMD_SET_TUNSRC,
+ .doit = seg6_genl_set_tunsrc,
+ .policy = seg6_genl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = SEG6_CMD_GET_TUNSRC,
+ .doit = seg6_genl_get_tunsrc,
+ .policy = seg6_genl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+};
+
+static struct genl_family seg6_genl_family __ro_after_init = {
+ .hdrsize = 0,
+ .name = SEG6_GENL_NAME,
+ .version = SEG6_GENL_VERSION,
+ .maxattr = SEG6_ATTR_MAX,
+ .netnsok = true,
+ .parallel_ops = true,
+ .ops = seg6_genl_ops,
+ .n_ops = ARRAY_SIZE(seg6_genl_ops),
+ .module = THIS_MODULE,
+};
+
+int __init seg6_init(void)
+{
+ int err = -ENOMEM;
+
+ err = genl_register_family(&seg6_genl_family);
+ if (err)
+ goto out;
+
+ err = register_pernet_subsys(&ip6_segments_ops);
+ if (err)
+ goto out_unregister_genl;
+
+#ifdef CONFIG_IPV6_SEG6_LWTUNNEL
+ err = seg6_iptunnel_init();
+ if (err)
+ goto out_unregister_pernet;
+#endif
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ err = seg6_hmac_init();
+ if (err)
+ goto out_unregister_iptun;
+#endif
+
+ pr_info("Segment Routing with IPv6\n");
+
+out:
+ return err;
+#ifdef CONFIG_IPV6_SEG6_HMAC
+out_unregister_iptun:
+#ifdef CONFIG_IPV6_SEG6_LWTUNNEL
+ seg6_iptunnel_exit();
+#endif
+#endif
+#ifdef CONFIG_IPV6_SEG6_LWTUNNEL
+out_unregister_pernet:
+ unregister_pernet_subsys(&ip6_segments_ops);
+#endif
+out_unregister_genl:
+ genl_unregister_family(&seg6_genl_family);
+ goto out;
+}
+
+void seg6_exit(void)
+{
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ seg6_hmac_exit();
+#endif
+#ifdef CONFIG_IPV6_SEG6_LWTUNNEL
+ seg6_iptunnel_exit();
+#endif
+ unregister_pernet_subsys(&ip6_segments_ops);
+ genl_unregister_family(&seg6_genl_family);
+}
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
new file mode 100644
index 0000000..ef1c8a4
--- /dev/null
+++ b/net/ipv6/seg6_hmac.c
@@ -0,0 +1,484 @@
+/*
+ * SR-IPv6 implementation -- HMAC functions
+ *
+ * Author:
+ * David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/in6.h>
+#include <linux/icmpv6.h>
+#include <linux/mroute6.h>
+#include <linux/slab.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+
+#include <net/sock.h>
+#include <net/snmp.h>
+
+#include <net/ipv6.h>
+#include <net/protocol.h>
+#include <net/transp_v6.h>
+#include <net/rawv6.h>
+#include <net/ndisc.h>
+#include <net/ip6_route.h>
+#include <net/addrconf.h>
+#include <net/xfrm.h>
+
+#include <linux/cryptohash.h>
+#include <crypto/hash.h>
+#include <crypto/sha.h>
+#include <net/seg6.h>
+#include <net/genetlink.h>
+#include <net/seg6_hmac.h>
+#include <linux/random.h>
+
+static char * __percpu *hmac_ring;
+
+static int seg6_hmac_cmpfn(struct rhashtable_compare_arg *arg, const void *obj)
+{
+ const struct seg6_hmac_info *hinfo = obj;
+
+ return (hinfo->hmackeyid != *(__u32 *)arg->key);
+}
+
+static inline void seg6_hinfo_release(struct seg6_hmac_info *hinfo)
+{
+ kfree_rcu(hinfo, rcu);
+}
+
+static void seg6_free_hi(void *ptr, void *arg)
+{
+ struct seg6_hmac_info *hinfo = (struct seg6_hmac_info *)ptr;
+
+ if (hinfo)
+ seg6_hinfo_release(hinfo);
+}
+
+static const struct rhashtable_params rht_params = {
+ .head_offset = offsetof(struct seg6_hmac_info, node),
+ .key_offset = offsetof(struct seg6_hmac_info, hmackeyid),
+ .key_len = sizeof(u32),
+ .automatic_shrinking = true,
+ .obj_cmpfn = seg6_hmac_cmpfn,
+};
+
+static struct seg6_hmac_algo hmac_algos[] = {
+ {
+ .alg_id = SEG6_HMAC_ALGO_SHA1,
+ .name = "hmac(sha1)",
+ },
+ {
+ .alg_id = SEG6_HMAC_ALGO_SHA256,
+ .name = "hmac(sha256)",
+ },
+};
+
+static struct sr6_tlv_hmac *seg6_get_tlv_hmac(struct ipv6_sr_hdr *srh)
+{
+ struct sr6_tlv_hmac *tlv;
+
+ if (srh->hdrlen < (srh->first_segment + 1) * 2 + 5)
+ return NULL;
+
+ if (!sr_has_hmac(srh))
+ return NULL;
+
+ tlv = (struct sr6_tlv_hmac *)
+ ((char *)srh + ((srh->hdrlen + 1) << 3) - 40);
+
+ if (tlv->tlvhdr.type != SR6_TLV_HMAC || tlv->tlvhdr.len != 38)
+ return NULL;
+
+ return tlv;
+}
+
+static struct seg6_hmac_algo *__hmac_get_algo(u8 alg_id)
+{
+ struct seg6_hmac_algo *algo;
+ int i, alg_count;
+
+ alg_count = sizeof(hmac_algos) / sizeof(struct seg6_hmac_algo);
+ for (i = 0; i < alg_count; i++) {
+ algo = &hmac_algos[i];
+ if (algo->alg_id == alg_id)
+ return algo;
+ }
+
+ return NULL;
+}
+
+static int __do_hmac(struct seg6_hmac_info *hinfo, const char *text, u8 psize,
+ u8 *output, int outlen)
+{
+ struct seg6_hmac_algo *algo;
+ struct crypto_shash *tfm;
+ struct shash_desc *shash;
+ int ret, dgsize;
+
+ algo = __hmac_get_algo(hinfo->alg_id);
+ if (!algo)
+ return -ENOENT;
+
+ tfm = *this_cpu_ptr(algo->tfms);
+
+ dgsize = crypto_shash_digestsize(tfm);
+ if (dgsize > outlen) {
+ pr_debug("sr-ipv6: __do_hmac: digest size too big (%d / %d)\n",
+ dgsize, outlen);
+ return -ENOMEM;
+ }
+
+ ret = crypto_shash_setkey(tfm, hinfo->secret, hinfo->slen);
+ if (ret < 0) {
+ pr_debug("sr-ipv6: crypto_shash_setkey failed: err %d\n", ret);
+ goto failed;
+ }
+
+ shash = *this_cpu_ptr(algo->shashs);
+ shash->tfm = tfm;
+
+ ret = crypto_shash_digest(shash, text, psize, output);
+ if (ret < 0) {
+ pr_debug("sr-ipv6: crypto_shash_digest failed: err %d\n", ret);
+ goto failed;
+ }
+
+ return dgsize;
+
+failed:
+ return ret;
+}
+
+int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr,
+ struct in6_addr *saddr, u8 *output)
+{
+ __be32 hmackeyid = cpu_to_be32(hinfo->hmackeyid);
+ u8 tmp_out[SEG6_HMAC_MAX_DIGESTSIZE];
+ int plen, i, dgsize, wrsize;
+ char *ring, *off;
+
+ /* a 160-byte buffer for digest output allows to store highest known
+ * hash function (RadioGatun) with up to 1216 bits
+ */
+
+ /* saddr(16) + first_seg(1) + cleanup(1) + keyid(4) + seglist(16n) */
+ plen = 16 + 1 + 1 + 4 + (hdr->first_segment + 1) * 16;
+
+ /* this limit allows for 14 segments */
+ if (plen >= SEG6_HMAC_RING_SIZE)
+ return -EMSGSIZE;
+
+ /* Let's build the HMAC text on the ring buffer. The text is composed
+ * as follows, in order:
+ *
+ * 1. Source IPv6 address (128 bits)
+ * 2. first_segment value (8 bits)
+ * 3. cleanup flag (8 bits: highest bit is cleanup value, others are 0)
+ * 4. HMAC Key ID (32 bits)
+ * 5. All segments in the segments list (n * 128 bits)
+ */
+
+ local_bh_disable();
+ ring = *this_cpu_ptr(hmac_ring);
+ off = ring;
+
+ /* source address */
+ memcpy(off, saddr, 16);
+ off += 16;
+
+ /* first_segment value */
+ *off++ = hdr->first_segment;
+
+ /* cleanup flag */
+ *off++ = !!(sr_has_cleanup(hdr)) << 7;
+
+ /* HMAC Key ID */
+ memcpy(off, &hmackeyid, 4);
+ off += 4;
+
+ /* all segments in the list */
+ for (i = 0; i < hdr->first_segment + 1; i++) {
+ memcpy(off, hdr->segments + i, 16);
+ off += 16;
+ }
+
+ dgsize = __do_hmac(hinfo, ring, plen, tmp_out,
+ SEG6_HMAC_MAX_DIGESTSIZE);
+ local_bh_enable();
+
+ if (dgsize < 0)
+ return dgsize;
+
+ wrsize = SEG6_HMAC_FIELD_LEN;
+ if (wrsize > dgsize)
+ wrsize = dgsize;
+
+ memset(output, 0, SEG6_HMAC_FIELD_LEN);
+ memcpy(output, tmp_out, wrsize);
+
+ return 0;
+}
+EXPORT_SYMBOL(seg6_hmac_compute);
+
+/* checks if an incoming SR-enabled packet's HMAC status matches
+ * the incoming policy.
+ *
+ * called with rcu_read_lock()
+ */
+bool seg6_hmac_validate_skb(struct sk_buff *skb)
+{
+ u8 hmac_output[SEG6_HMAC_FIELD_LEN];
+ struct net *net = dev_net(skb->dev);
+ struct seg6_hmac_info *hinfo;
+ struct sr6_tlv_hmac *tlv;
+ struct ipv6_sr_hdr *srh;
+ struct inet6_dev *idev;
+
+ idev = __in6_dev_get(skb->dev);
+
+ srh = (struct ipv6_sr_hdr *)skb_transport_header(skb);
+
+ tlv = seg6_get_tlv_hmac(srh);
+
+ /* mandatory check but no tlv */
+ if (idev->cnf.seg6_require_hmac > 0 && !tlv)
+ return false;
+
+ /* no check */
+ if (idev->cnf.seg6_require_hmac < 0)
+ return true;
+
+ /* check only if present */
+ if (idev->cnf.seg6_require_hmac == 0 && !tlv)
+ return true;
+
+ /* now, seg6_require_hmac >= 0 && tlv */
+
+ hinfo = seg6_hmac_info_lookup(net, be32_to_cpu(tlv->hmackeyid));
+ if (!hinfo)
+ return false;
+
+ if (seg6_hmac_compute(hinfo, srh, &ipv6_hdr(skb)->saddr, hmac_output))
+ return false;
+
+ if (memcmp(hmac_output, tlv->hmac, SEG6_HMAC_FIELD_LEN) != 0)
+ return false;
+
+ return true;
+}
+EXPORT_SYMBOL(seg6_hmac_validate_skb);
+
+/* called with rcu_read_lock() */
+struct seg6_hmac_info *seg6_hmac_info_lookup(struct net *net, u32 key)
+{
+ struct seg6_pernet_data *sdata = seg6_pernet(net);
+ struct seg6_hmac_info *hinfo;
+
+ hinfo = rhashtable_lookup_fast(&sdata->hmac_infos, &key, rht_params);
+
+ return hinfo;
+}
+EXPORT_SYMBOL(seg6_hmac_info_lookup);
+
+int seg6_hmac_info_add(struct net *net, u32 key, struct seg6_hmac_info *hinfo)
+{
+ struct seg6_pernet_data *sdata = seg6_pernet(net);
+ int err;
+
+ err = rhashtable_lookup_insert_fast(&sdata->hmac_infos, &hinfo->node,
+ rht_params);
+
+ return err;
+}
+EXPORT_SYMBOL(seg6_hmac_info_add);
+
+int seg6_hmac_info_del(struct net *net, u32 key)
+{
+ struct seg6_pernet_data *sdata = seg6_pernet(net);
+ struct seg6_hmac_info *hinfo;
+ int err = -ENOENT;
+
+ hinfo = rhashtable_lookup_fast(&sdata->hmac_infos, &key, rht_params);
+ if (!hinfo)
+ goto out;
+
+ err = rhashtable_remove_fast(&sdata->hmac_infos, &hinfo->node,
+ rht_params);
+ if (err)
+ goto out;
+
+ seg6_hinfo_release(hinfo);
+
+out:
+ return err;
+}
+EXPORT_SYMBOL(seg6_hmac_info_del);
+
+int seg6_push_hmac(struct net *net, struct in6_addr *saddr,
+ struct ipv6_sr_hdr *srh)
+{
+ struct seg6_hmac_info *hinfo;
+ struct sr6_tlv_hmac *tlv;
+ int err = -ENOENT;
+
+ tlv = seg6_get_tlv_hmac(srh);
+ if (!tlv)
+ return -EINVAL;
+
+ rcu_read_lock();
+
+ hinfo = seg6_hmac_info_lookup(net, be32_to_cpu(tlv->hmackeyid));
+ if (!hinfo)
+ goto out;
+
+ memset(tlv->hmac, 0, SEG6_HMAC_FIELD_LEN);
+ err = seg6_hmac_compute(hinfo, srh, saddr, tlv->hmac);
+
+out:
+ rcu_read_unlock();
+ return err;
+}
+EXPORT_SYMBOL(seg6_push_hmac);
+
+static int seg6_hmac_init_ring(void)
+{
+ int i;
+
+ hmac_ring = alloc_percpu(char *);
+
+ if (!hmac_ring)
+ return -ENOMEM;
+
+ for_each_possible_cpu(i) {
+ char *ring = kzalloc(SEG6_HMAC_RING_SIZE, GFP_KERNEL);
+
+ if (!ring)
+ return -ENOMEM;
+
+ *per_cpu_ptr(hmac_ring, i) = ring;
+ }
+
+ return 0;
+}
+
+static int seg6_hmac_init_algo(void)
+{
+ struct seg6_hmac_algo *algo;
+ struct crypto_shash *tfm;
+ struct shash_desc *shash;
+ int i, alg_count, cpu;
+
+ alg_count = sizeof(hmac_algos) / sizeof(struct seg6_hmac_algo);
+
+ for (i = 0; i < alg_count; i++) {
+ struct crypto_shash **p_tfm;
+ int shsize;
+
+ algo = &hmac_algos[i];
+ algo->tfms = alloc_percpu(struct crypto_shash *);
+ if (!algo->tfms)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL);
+ if (IS_ERR(tfm))
+ return PTR_ERR(tfm);
+ p_tfm = per_cpu_ptr(algo->tfms, cpu);
+ *p_tfm = tfm;
+ }
+
+ p_tfm = this_cpu_ptr(algo->tfms);
+ tfm = *p_tfm;
+
+ shsize = sizeof(*shash) + crypto_shash_descsize(tfm);
+
+ algo->shashs = alloc_percpu(struct shash_desc *);
+ if (!algo->shashs)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ shash = kzalloc(shsize, GFP_KERNEL);
+ if (!shash)
+ return -ENOMEM;
+ *per_cpu_ptr(algo->shashs, cpu) = shash;
+ }
+ }
+
+ return 0;
+}
+
+int __init seg6_hmac_init(void)
+{
+ int ret;
+
+ ret = seg6_hmac_init_ring();
+ if (ret < 0)
+ goto out;
+
+ ret = seg6_hmac_init_algo();
+
+out:
+ return ret;
+}
+EXPORT_SYMBOL(seg6_hmac_init);
+
+int __net_init seg6_hmac_net_init(struct net *net)
+{
+ struct seg6_pernet_data *sdata = seg6_pernet(net);
+
+ rhashtable_init(&sdata->hmac_infos, &rht_params);
+
+ return 0;
+}
+EXPORT_SYMBOL(seg6_hmac_net_init);
+
+void seg6_hmac_exit(void)
+{
+ struct seg6_hmac_algo *algo = NULL;
+ int i, alg_count, cpu;
+
+ for_each_possible_cpu(i) {
+ char *ring = *per_cpu_ptr(hmac_ring, i);
+
+ kfree(ring);
+ }
+ free_percpu(hmac_ring);
+
+ alg_count = sizeof(hmac_algos) / sizeof(struct seg6_hmac_algo);
+ for (i = 0; i < alg_count; i++) {
+ algo = &hmac_algos[i];
+ for_each_possible_cpu(cpu) {
+ struct crypto_shash *tfm;
+ struct shash_desc *shash;
+
+ shash = *per_cpu_ptr(algo->shashs, cpu);
+ kfree(shash);
+ tfm = *per_cpu_ptr(algo->tfms, cpu);
+ crypto_free_shash(tfm);
+ }
+ free_percpu(algo->tfms);
+ free_percpu(algo->shashs);
+ }
+}
+EXPORT_SYMBOL(seg6_hmac_exit);
+
+void __net_exit seg6_hmac_net_exit(struct net *net)
+{
+ struct seg6_pernet_data *sdata = seg6_pernet(net);
+
+ rhashtable_free_and_destroy(&sdata->hmac_infos, seg6_free_hi, NULL);
+}
+EXPORT_SYMBOL(seg6_hmac_net_exit);
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
new file mode 100644
index 0000000..bbfca22
--- /dev/null
+++ b/net/ipv6/seg6_iptunnel.c
@@ -0,0 +1,431 @@
+/*
+ * SR-IPv6 implementation
+ *
+ * Author:
+ * David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/types.h>
+#include <linux/skbuff.h>
+#include <linux/net.h>
+#include <linux/module.h>
+#include <net/ip.h>
+#include <net/lwtunnel.h>
+#include <net/netevent.h>
+#include <net/netns/generic.h>
+#include <net/ip6_fib.h>
+#include <net/route.h>
+#include <net/seg6.h>
+#include <linux/seg6.h>
+#include <linux/seg6_iptunnel.h>
+#include <net/addrconf.h>
+#include <net/ip6_route.h>
+#ifdef CONFIG_DST_CACHE
+#include <net/dst_cache.h>
+#endif
+#ifdef CONFIG_IPV6_SEG6_HMAC
+#include <net/seg6_hmac.h>
+#endif
+
+struct seg6_lwt {
+#ifdef CONFIG_DST_CACHE
+ struct dst_cache cache;
+#endif
+ struct seg6_iptunnel_encap tuninfo[0];
+};
+
+static inline struct seg6_lwt *seg6_lwt_lwtunnel(struct lwtunnel_state *lwt)
+{
+ return (struct seg6_lwt *)lwt->data;
+}
+
+static inline struct seg6_iptunnel_encap *
+seg6_encap_lwtunnel(struct lwtunnel_state *lwt)
+{
+ return seg6_lwt_lwtunnel(lwt)->tuninfo;
+}
+
+static const struct nla_policy seg6_iptunnel_policy[SEG6_IPTUNNEL_MAX + 1] = {
+ [SEG6_IPTUNNEL_SRH] = { .type = NLA_BINARY },
+};
+
+int nla_put_srh(struct sk_buff *skb, int attrtype,
+ struct seg6_iptunnel_encap *tuninfo)
+{
+ struct seg6_iptunnel_encap *data;
+ struct nlattr *nla;
+ int len;
+
+ len = SEG6_IPTUN_ENCAP_SIZE(tuninfo);
+
+ nla = nla_reserve(skb, attrtype, len);
+ if (!nla)
+ return -EMSGSIZE;
+
+ data = nla_data(nla);
+ memcpy(data, tuninfo, len);
+
+ return 0;
+}
+
+static void set_tun_src(struct net *net, struct net_device *dev,
+ struct in6_addr *daddr, struct in6_addr *saddr)
+{
+ struct seg6_pernet_data *sdata = seg6_pernet(net);
+ struct in6_addr *tun_src;
+
+ rcu_read_lock();
+
+ tun_src = rcu_dereference(sdata->tun_src);
+
+ if (!ipv6_addr_any(tun_src)) {
+ memcpy(saddr, tun_src, sizeof(struct in6_addr));
+ } else {
+ ipv6_dev_get_saddr(net, dev, daddr, IPV6_PREFER_SRC_PUBLIC,
+ saddr);
+ }
+
+ rcu_read_unlock();
+}
+
+/* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */
+static int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
+{
+ struct net *net = dev_net(skb_dst(skb)->dev);
+ struct ipv6hdr *hdr, *inner_hdr;
+ struct ipv6_sr_hdr *isrh;
+ int hdrlen, tot_len, err;
+
+ hdrlen = (osrh->hdrlen + 1) << 3;
+ tot_len = hdrlen + sizeof(*hdr);
+
+ err = pskb_expand_head(skb, tot_len, 0, GFP_ATOMIC);
+ if (unlikely(err))
+ return err;
+
+ inner_hdr = ipv6_hdr(skb);
+
+ skb_push(skb, tot_len);
+ skb_reset_network_header(skb);
+ skb_mac_header_rebuild(skb);
+ hdr = ipv6_hdr(skb);
+
+ /* inherit tc, flowlabel and hlim
+ * hlim will be decremented in ip6_forward() afterwards and
+ * decapsulation will overwrite inner hlim with outer hlim
+ */
+ ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)),
+ ip6_flowlabel(inner_hdr));
+ hdr->hop_limit = inner_hdr->hop_limit;
+ hdr->nexthdr = NEXTHDR_ROUTING;
+
+ isrh = (void *)hdr + sizeof(*hdr);
+ memcpy(isrh, osrh, hdrlen);
+
+ isrh->nexthdr = NEXTHDR_IPV6;
+
+ hdr->daddr = isrh->segments[isrh->first_segment];
+ set_tun_src(net, skb->dev, &hdr->daddr, &hdr->saddr);
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ if (sr_has_hmac(isrh)) {
+ err = seg6_push_hmac(net, &hdr->saddr, isrh);
+ if (unlikely(err))
+ return err;
+ }
+#endif
+
+ skb_postpush_rcsum(skb, hdr, tot_len);
+
+ return 0;
+}
+
+/* insert an SRH within an IPv6 packet, just after the IPv6 header */
+#ifdef CONFIG_IPV6_SEG6_INLINE
+static int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
+{
+ struct ipv6hdr *hdr, *oldhdr;
+ struct ipv6_sr_hdr *isrh;
+ int hdrlen, err;
+
+ hdrlen = (osrh->hdrlen + 1) << 3;
+
+ err = pskb_expand_head(skb, hdrlen, 0, GFP_ATOMIC);
+ if (unlikely(err))
+ return err;
+
+ oldhdr = ipv6_hdr(skb);
+
+ skb_pull(skb, sizeof(struct ipv6hdr));
+ skb_postpull_rcsum(skb, skb_network_header(skb),
+ sizeof(struct ipv6hdr));
+
+ skb_push(skb, sizeof(struct ipv6hdr) + hdrlen);
+ skb_reset_network_header(skb);
+ skb_mac_header_rebuild(skb);
+
+ hdr = ipv6_hdr(skb);
+
+ memmove(hdr, oldhdr, sizeof(*hdr));
+
+ isrh = (void *)hdr + sizeof(*hdr);
+ memcpy(isrh, osrh, hdrlen);
+
+ isrh->nexthdr = hdr->nexthdr;
+ hdr->nexthdr = NEXTHDR_ROUTING;
+
+ isrh->segments[0] = hdr->daddr;
+ hdr->daddr = isrh->segments[isrh->first_segment];
+
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ if (sr_has_hmac(isrh)) {
+ struct net *net = dev_net(skb_dst(skb)->dev);
+
+ err = seg6_push_hmac(net, &hdr->saddr, isrh);
+ if (unlikely(err))
+ return err;
+ }
+#endif
+
+ skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen);
+
+ return 0;
+}
+#endif
+
+static int seg6_do_srh(struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ struct seg6_iptunnel_encap *tinfo;
+ int err = 0;
+
+ tinfo = seg6_encap_lwtunnel(dst->lwtstate);
+
+ if (likely(!skb->encapsulation)) {
+ skb_reset_inner_headers(skb);
+ skb->encapsulation = 1;
+ }
+
+ switch (tinfo->mode) {
+#ifdef CONFIG_IPV6_SEG6_INLINE
+ case SEG6_IPTUN_MODE_INLINE:
+ err = seg6_do_srh_inline(skb, tinfo->srh);
+ skb_reset_inner_headers(skb);
+ break;
+#endif
+ case SEG6_IPTUN_MODE_ENCAP:
+ err = seg6_do_srh_encap(skb, tinfo->srh);
+ break;
+ }
+
+ if (err)
+ return err;
+
+ ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+ skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+
+ skb_set_inner_protocol(skb, skb->protocol);
+
+ return 0;
+}
+
+int seg6_input(struct sk_buff *skb)
+{
+ int err;
+
+ err = seg6_do_srh(skb);
+ if (unlikely(err)) {
+ kfree_skb(skb);
+ return err;
+ }
+
+ skb_dst_drop(skb);
+ ip6_route_input(skb);
+
+ return dst_input(skb);
+}
+
+int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ struct dst_entry *orig_dst = skb_dst(skb);
+ struct dst_entry *dst = NULL;
+ struct seg6_lwt *slwt;
+ int err = -EINVAL;
+
+ err = seg6_do_srh(skb);
+ if (unlikely(err))
+ goto drop;
+
+ slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
+
+#ifdef CONFIG_DST_CACHE
+ dst = dst_cache_get(&slwt->cache);
+#endif
+
+ if (unlikely(!dst)) {
+ struct ipv6hdr *hdr = ipv6_hdr(skb);
+ struct flowi6 fl6;
+
+ fl6.daddr = hdr->daddr;
+ fl6.saddr = hdr->saddr;
+ fl6.flowlabel = ip6_flowinfo(hdr);
+ fl6.flowi6_mark = skb->mark;
+ fl6.flowi6_proto = hdr->nexthdr;
+
+ dst = ip6_route_output(net, NULL, &fl6);
+ if (dst->error) {
+ err = dst->error;
+ dst_release(dst);
+ goto drop;
+ }
+
+#ifdef CONFIG_DST_CACHE
+ dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
+#endif
+ }
+
+ skb_dst_drop(skb);
+ skb_dst_set(skb, dst);
+
+ return dst_output(net, sk, skb);
+drop:
+ kfree_skb(skb);
+ return err;
+}
+
+static int seg6_build_state(struct net_device *dev, struct nlattr *nla,
+ unsigned int family, const void *cfg,
+ struct lwtunnel_state **ts)
+{
+ struct nlattr *tb[SEG6_IPTUNNEL_MAX + 1];
+ struct seg6_iptunnel_encap *tuninfo;
+ struct lwtunnel_state *newts;
+ int tuninfo_len, min_size;
+ struct seg6_lwt *slwt;
+ int err;
+
+ err = nla_parse_nested(tb, SEG6_IPTUNNEL_MAX, nla,
+ seg6_iptunnel_policy);
+
+ if (err < 0)
+ return err;
+
+ if (!tb[SEG6_IPTUNNEL_SRH])
+ return -EINVAL;
+
+ tuninfo = nla_data(tb[SEG6_IPTUNNEL_SRH]);
+ tuninfo_len = nla_len(tb[SEG6_IPTUNNEL_SRH]);
+
+ /* tuninfo must contain at least the iptunnel encap structure,
+ * the SRH and one segment
+ */
+ min_size = sizeof(*tuninfo) + sizeof(struct ipv6_sr_hdr) +
+ sizeof(struct in6_addr);
+ if (tuninfo_len < min_size)
+ return -EINVAL;
+
+ switch (tuninfo->mode) {
+#ifdef CONFIG_IPV6_SEG6_INLINE
+ case SEG6_IPTUN_MODE_INLINE:
+ break;
+#endif
+ case SEG6_IPTUN_MODE_ENCAP:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ /* verify that SRH is consistent */
+ if (!seg6_validate_srh(tuninfo->srh, tuninfo_len - sizeof(*tuninfo)))
+ return -EINVAL;
+
+ newts = lwtunnel_state_alloc(tuninfo_len + sizeof(*slwt));
+ if (!newts)
+ return -ENOMEM;
+
+ slwt = seg6_lwt_lwtunnel(newts);
+
+#ifdef CONFIG_DST_CACHE
+ err = dst_cache_init(&slwt->cache, GFP_KERNEL);
+ if (err) {
+ kfree(newts);
+ return err;
+ }
+#endif
+
+ memcpy(&slwt->tuninfo, tuninfo, tuninfo_len);
+
+ newts->type = LWTUNNEL_ENCAP_SEG6;
+ newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT |
+ LWTUNNEL_STATE_INPUT_REDIRECT;
+ newts->headroom = seg6_lwt_headroom(tuninfo);
+
+ *ts = newts;
+
+ return 0;
+}
+
+#ifdef CONFIG_DST_CACHE
+static void seg6_destroy_state(struct lwtunnel_state *lwt)
+{
+ dst_cache_destroy(&seg6_lwt_lwtunnel(lwt)->cache);
+}
+#endif
+
+static int seg6_fill_encap_info(struct sk_buff *skb,
+ struct lwtunnel_state *lwtstate)
+{
+ struct seg6_iptunnel_encap *tuninfo = seg6_encap_lwtunnel(lwtstate);
+
+ if (nla_put_srh(skb, SEG6_IPTUNNEL_SRH, tuninfo))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int seg6_encap_nlsize(struct lwtunnel_state *lwtstate)
+{
+ struct seg6_iptunnel_encap *tuninfo = seg6_encap_lwtunnel(lwtstate);
+
+ return nla_total_size(SEG6_IPTUN_ENCAP_SIZE(tuninfo));
+}
+
+static int seg6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
+{
+ struct seg6_iptunnel_encap *a_hdr = seg6_encap_lwtunnel(a);
+ struct seg6_iptunnel_encap *b_hdr = seg6_encap_lwtunnel(b);
+ int len = SEG6_IPTUN_ENCAP_SIZE(a_hdr);
+
+ if (len != SEG6_IPTUN_ENCAP_SIZE(b_hdr))
+ return 1;
+
+ return memcmp(a_hdr, b_hdr, len);
+}
+
+static const struct lwtunnel_encap_ops seg6_iptun_ops = {
+ .build_state = seg6_build_state,
+#ifdef CONFIG_DST_CACHE
+ .destroy_state = seg6_destroy_state,
+#endif
+ .output = seg6_output,
+ .input = seg6_input,
+ .fill_encap = seg6_fill_encap_info,
+ .get_encap_size = seg6_encap_nlsize,
+ .cmp_encap = seg6_encap_cmp,
+};
+
+int __init seg6_iptunnel_init(void)
+{
+ return lwtunnel_encap_add_ops(&seg6_iptun_ops, LWTUNNEL_ENCAP_SEG6);
+}
+
+void seg6_iptunnel_exit(void)
+{
+ lwtunnel_encap_del_ops(&seg6_iptun_ops, LWTUNNEL_ENCAP_SEG6);
+}
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index dc7a344..0355231 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -76,7 +76,7 @@ static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst,
__be32 *v4dst);
static struct rtnl_link_ops sit_link_ops __read_mostly;
-static int sit_net_id __read_mostly;
+static unsigned int sit_net_id __read_mostly;
struct sit_net {
struct ip_tunnel __rcu *tunnels_r_l[IP6_SIT_HASH_SIZE];
struct ip_tunnel __rcu *tunnels_r[IP6_SIT_HASH_SIZE];
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 59c4839..97830a6 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -227,6 +227,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
fl6.flowi6_mark = ireq->ir_mark;
fl6.fl6_dport = ireq->ir_rmt_port;
fl6.fl6_sport = inet_sk(sk)->inet_sport;
+ fl6.flowi6_uid = sk->sk_uid;
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5a27ab4..28ec0a2 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -233,6 +233,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
+ fl6.flowi6_uid = sk->sk_uid;
opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
final_p = fl6_update_dst(&fl6, opt, &final);
@@ -818,12 +819,17 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
fl6.flowi6_proto = IPPROTO_TCP;
if (rt6_need_strict(&fl6.daddr) && !oif)
fl6.flowi6_oif = tcp_v6_iif(skb);
- else
- fl6.flowi6_oif = oif ? : skb->skb_iif;
+ else {
+ if (!oif && netif_index_is_l3_master(net, skb->skb_iif))
+ oif = skb->skb_iif;
+
+ fl6.flowi6_oif = oif;
+ }
fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
fl6.fl6_dport = t1->dest;
fl6.fl6_sport = t1->source;
+ fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
/* Pass a socket to ip6_dst_lookup either it is for RST
@@ -1225,7 +1231,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
if (skb->protocol == htons(ETH_P_IP))
return tcp_v4_do_rcv(sk, skb);
- if (sk_filter(sk, skb))
+ if (tcp_filter(sk, skb))
goto discard;
/*
@@ -1453,8 +1459,10 @@ static int tcp_v6_rcv(struct sk_buff *skb)
if (tcp_v6_inbound_md5_hash(sk, skb))
goto discard_and_relse;
- if (sk_filter(sk, skb))
+ if (tcp_filter(sk, skb))
goto discard_and_relse;
+ th = (const struct tcphdr *)skb->data;
+ hdr = ipv6_hdr(skb);
skb->dev = NULL;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 71963b2..4f99417 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -302,7 +302,8 @@ EXPORT_SYMBOL_GPL(udp6_lib_lookup_skb);
* Does increment socket refcount.
*/
#if IS_ENABLED(CONFIG_NETFILTER_XT_MATCH_SOCKET) || \
- IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY)
+ IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY) || \
+ IS_ENABLED(CONFIG_NF_SOCKET_IPV6)
struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, __be16 dport, int dif)
{
@@ -343,8 +344,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
try_again:
peeking = off = sk_peek_offset(sk, flags);
- skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
- &peeked, &off, &err);
+ skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err);
if (!skb)
return err;
@@ -425,7 +425,8 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
if (is_udp4) {
if (inet->cmsg_flags)
- ip_cmsg_recv(msg, skb);
+ ip_cmsg_recv_offset(msg, sk, skb,
+ sizeof(struct udphdr), off);
} else {
if (np->rxopt.all)
ip6_datagram_recv_specific_ctl(sk, msg, skb);
@@ -518,6 +519,8 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
sock_rps_save_rxhash(sk, skb);
sk_mark_napi_id(sk, skb);
sk_incoming_cpu_update(sk);
+ } else {
+ sk_mark_napi_id_once(sk, skb);
}
rc = __udp_enqueue_schedule_skb(sk, skb);
@@ -1137,6 +1140,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sk->sk_uid;
sockc.tsflags = sk->sk_tsflags;
if (msg->msg_controllen) {
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 47d0d2b..2784cc3 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -45,10 +45,11 @@ struct proto udplitev6_prot = {
.getsockopt = udpv6_getsockopt,
.sendmsg = udpv6_sendmsg,
.recvmsg = udpv6_recvmsg,
- .backlog_rcv = udpv6_queue_rcv_skb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
.get_port = udp_v6_get_port,
+ .memory_allocated = &udp_memory_allocated,
+ .sysctl_mem = sysctl_udp_mem,
.obj_size = sizeof(struct udp6_sock),
.h.udp_table = &udplite_table,
#ifdef CONFIG_COMPAT
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index e1c0bbe..d7b731a 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -44,7 +44,7 @@ struct xfrm6_tunnel_net {
u32 spi;
};
-static int xfrm6_tunnel_net_id __read_mostly;
+static unsigned int xfrm6_tunnel_net_id __read_mostly;
static inline struct xfrm6_tunnel_net *xfrm6_tunnel_pernet(struct net *net)
{
return net_generic(net, xfrm6_tunnel_net_id);
diff --git a/net/key/af_key.c b/net/key/af_key.c
index f9c9ecb..c6252ed 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -36,7 +36,7 @@
#define _X2KEY(x) ((x) == XFRM_INF ? 0 : (x))
#define _KEY2X(x) ((x) == 0 ? XFRM_INF : (x))
-static int pfkey_net_id __read_mostly;
+static unsigned int pfkey_net_id __read_mostly;
struct netns_pfkey {
/* List of all pfkey sockets. */
struct hlist_head table;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index a2ed3bd..85948c6 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -715,7 +715,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
l2tp_info(session, L2TP_MSG_SEQ,
"%s: requested to enable seq numbers by LNS\n",
session->name);
- session->send_seq = -1;
+ session->send_seq = 1;
l2tp_session_set_header_len(session, tunnel->version);
}
} else {
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 42de4cc..fce25af 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -338,7 +338,7 @@ static int l2tp_ip_disconnect(struct sock *sk, int flags)
if (sock_flag(sk, SOCK_ZAPPED))
return 0;
- return udp_disconnect(sk, flags);
+ return __udp_disconnect(sk, flags);
}
static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index ea2ae66..1cea54f 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -410,7 +410,7 @@ static int l2tp_ip6_disconnect(struct sock *sk, int flags)
if (sock_flag(sk, SOCK_ZAPPED))
return 0;
- return udp_disconnect(sk, flags);
+ return __udp_disconnect(sk, flags);
}
static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr,
@@ -519,6 +519,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_uid = sk->sk_uid;
ipc6.hlimit = -1;
ipc6.tclass = -1;
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 59aa2d2..3620fba 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -220,14 +220,14 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info
cfg.local_udp_port = nla_get_u16(info->attrs[L2TP_ATTR_UDP_SPORT]);
if (info->attrs[L2TP_ATTR_UDP_DPORT])
cfg.peer_udp_port = nla_get_u16(info->attrs[L2TP_ATTR_UDP_DPORT]);
- if (info->attrs[L2TP_ATTR_UDP_CSUM])
- cfg.use_udp_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_CSUM]);
+ cfg.use_udp_checksums = nla_get_flag(
+ info->attrs[L2TP_ATTR_UDP_CSUM]);
#if IS_ENABLED(CONFIG_IPV6)
- if (info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_TX])
- cfg.udp6_zero_tx_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_TX]);
- if (info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_RX])
- cfg.udp6_zero_rx_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_RX]);
+ cfg.udp6_zero_tx_checksums = nla_get_flag(
+ info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_TX]);
+ cfg.udp6_zero_rx_checksums = nla_get_flag(
+ info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_RX]);
#endif
}
@@ -379,9 +379,24 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
switch (tunnel->encap) {
case L2TP_ENCAPTYPE_UDP:
+ switch (sk->sk_family) {
+ case AF_INET:
+ if (nla_put_u8(skb, L2TP_ATTR_UDP_CSUM, !sk->sk_no_check_tx))
+ goto nla_put_failure;
+ break;
+#if IS_ENABLED(CONFIG_IPV6)
+ case AF_INET6:
+ if (udp_get_no_check6_tx(sk) &&
+ nla_put_flag(skb, L2TP_ATTR_UDP_ZERO_CSUM6_TX))
+ goto nla_put_failure;
+ if (udp_get_no_check6_rx(sk) &&
+ nla_put_flag(skb, L2TP_ATTR_UDP_ZERO_CSUM6_RX))
+ goto nla_put_failure;
+ break;
+#endif
+ }
if (nla_put_u16(skb, L2TP_ATTR_UDP_SPORT, ntohs(inet->inet_sport)) ||
- nla_put_u16(skb, L2TP_ATTR_UDP_DPORT, ntohs(inet->inet_dport)) ||
- nla_put_u8(skb, L2TP_ATTR_UDP_CSUM, !sk->sk_no_check_tx))
+ nla_put_u16(skb, L2TP_ATTR_UDP_DPORT, ntohs(inet->inet_dport)))
goto nla_put_failure;
/* NOBREAK */
case L2TP_ENCAPTYPE_IP:
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 41d47bf..2ddfec1 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1272,7 +1272,7 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
err = -EINVAL;
break;
}
- session->recv_seq = val ? -1 : 0;
+ session->recv_seq = !!val;
l2tp_info(session, PPPOL2TP_MSG_CONTROL,
"%s: set recv_seq=%d\n",
session->name, session->recv_seq);
@@ -1283,7 +1283,7 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
err = -EINVAL;
break;
}
- session->send_seq = val ? -1 : 0;
+ session->send_seq = !!val;
{
struct sock *ssk = ps->sock;
struct pppox_sock *po = pppox_sk(ssk);
@@ -1301,7 +1301,7 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
err = -EINVAL;
break;
}
- session->lns_mode = val ? -1 : 0;
+ session->lns_mode = !!val;
l2tp_info(session, PPPOL2TP_MSG_CONTROL,
"%s: set lns_mode=%d\n",
session->name, session->lns_mode);
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index db916cf..5e92963 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -532,12 +532,12 @@ static int llc_ui_listen(struct socket *sock, int backlog)
static int llc_ui_wait_for_disc(struct sock *sk, long timeout)
{
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
int rc = 0;
+ add_wait_queue(sk_sleep(sk), &wait);
while (1) {
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- if (sk_wait_event(sk, &timeout, sk->sk_state == TCP_CLOSE))
+ if (sk_wait_event(sk, &timeout, sk->sk_state == TCP_CLOSE, &wait))
break;
rc = -ERESTARTSYS;
if (signal_pending(current))
@@ -547,39 +547,39 @@ static int llc_ui_wait_for_disc(struct sock *sk, long timeout)
break;
rc = 0;
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
return rc;
}
static bool llc_ui_wait_for_conn(struct sock *sk, long timeout)
{
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+ add_wait_queue(sk_sleep(sk), &wait);
while (1) {
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- if (sk_wait_event(sk, &timeout, sk->sk_state != TCP_SYN_SENT))
+ if (sk_wait_event(sk, &timeout, sk->sk_state != TCP_SYN_SENT, &wait))
break;
if (signal_pending(current) || !timeout)
break;
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
return timeout;
}
static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout)
{
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct llc_sock *llc = llc_sk(sk);
int rc;
+ add_wait_queue(sk_sleep(sk), &wait);
while (1) {
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
rc = 0;
if (sk_wait_event(sk, &timeout,
(sk->sk_shutdown & RCV_SHUTDOWN) ||
(!llc_data_accept_state(llc->state) &&
!llc->remote_busy_flag &&
- !llc->p_flag)))
+ !llc->p_flag), &wait))
break;
rc = -ERESTARTSYS;
if (signal_pending(current))
@@ -588,7 +588,7 @@ static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout)
if (!timeout)
break;
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
return rc;
}
diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile
index f9137a8..0b202b3 100644
--- a/net/mac80211/Makefile
+++ b/net/mac80211/Makefile
@@ -19,6 +19,7 @@
aes_gcm.o \
aes_cmac.o \
aes_gmac.o \
+ fils_aead.o \
cfg.o \
ethtool.o \
rx.o \
diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aes_ccm.c
index 7663c28..a4e0d59 100644
--- a/net/mac80211/aes_ccm.c
+++ b/net/mac80211/aes_ccm.c
@@ -18,21 +18,24 @@
#include "key.h"
#include "aes_ccm.h"
-void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
- u8 *data, size_t data_len, u8 *mic,
- size_t mic_len)
+int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
+ u8 *data, size_t data_len, u8 *mic,
+ size_t mic_len)
{
struct scatterlist sg[3];
+ struct aead_request *aead_req;
+ int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
+ u8 *__aad;
- char aead_req_data[sizeof(struct aead_request) +
- crypto_aead_reqsize(tfm)]
- __aligned(__alignof__(struct aead_request));
- struct aead_request *aead_req = (void *) aead_req_data;
+ aead_req = kzalloc(reqsize + CCM_AAD_LEN, GFP_ATOMIC);
+ if (!aead_req)
+ return -ENOMEM;
- memset(aead_req, 0, sizeof(aead_req_data));
+ __aad = (u8 *)aead_req + reqsize;
+ memcpy(__aad, aad, CCM_AAD_LEN);
sg_init_table(sg, 3);
- sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+ sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad));
sg_set_buf(&sg[1], data, data_len);
sg_set_buf(&sg[2], mic, mic_len);
@@ -41,6 +44,9 @@ void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
aead_request_set_ad(aead_req, sg[0].length);
crypto_aead_encrypt(aead_req);
+ kzfree(aead_req);
+
+ return 0;
}
int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
@@ -48,18 +54,23 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
size_t mic_len)
{
struct scatterlist sg[3];
- char aead_req_data[sizeof(struct aead_request) +
- crypto_aead_reqsize(tfm)]
- __aligned(__alignof__(struct aead_request));
- struct aead_request *aead_req = (void *) aead_req_data;
+ struct aead_request *aead_req;
+ int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
+ u8 *__aad;
+ int err;
if (data_len == 0)
return -EINVAL;
- memset(aead_req, 0, sizeof(aead_req_data));
+ aead_req = kzalloc(reqsize + CCM_AAD_LEN, GFP_ATOMIC);
+ if (!aead_req)
+ return -ENOMEM;
+
+ __aad = (u8 *)aead_req + reqsize;
+ memcpy(__aad, aad, CCM_AAD_LEN);
sg_init_table(sg, 3);
- sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+ sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad));
sg_set_buf(&sg[1], data, data_len);
sg_set_buf(&sg[2], mic, mic_len);
@@ -67,7 +78,10 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
aead_request_set_crypt(aead_req, sg, sg, data_len + mic_len, b_0);
aead_request_set_ad(aead_req, sg[0].length);
- return crypto_aead_decrypt(aead_req);
+ err = crypto_aead_decrypt(aead_req);
+ kzfree(aead_req);
+
+ return err;
}
struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[],
diff --git a/net/mac80211/aes_ccm.h b/net/mac80211/aes_ccm.h
index 6a73d1e..fcd3254 100644
--- a/net/mac80211/aes_ccm.h
+++ b/net/mac80211/aes_ccm.h
@@ -12,12 +12,14 @@
#include <linux/crypto.h>
+#define CCM_AAD_LEN 32
+
struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[],
size_t key_len,
size_t mic_len);
-void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
- u8 *data, size_t data_len, u8 *mic,
- size_t mic_len);
+int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
+ u8 *data, size_t data_len, u8 *mic,
+ size_t mic_len);
int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
u8 *data, size_t data_len, u8 *mic,
size_t mic_len);
diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c
index bdf0790..d0bd5ff 100644
--- a/net/mac80211/aes_cmac.c
+++ b/net/mac80211/aes_cmac.c
@@ -23,7 +23,7 @@
#define AAD_LEN 20
-static void gf_mulx(u8 *pad)
+void gf_mulx(u8 *pad)
{
int i, carry;
@@ -35,9 +35,9 @@ static void gf_mulx(u8 *pad)
pad[AES_BLOCK_SIZE - 1] ^= 0x87;
}
-static void aes_cmac_vector(struct crypto_cipher *tfm, size_t num_elem,
- const u8 *addr[], const size_t *len, u8 *mac,
- size_t mac_len)
+void aes_cmac_vector(struct crypto_cipher *tfm, size_t num_elem,
+ const u8 *addr[], const size_t *len, u8 *mac,
+ size_t mac_len)
{
u8 cbc[AES_BLOCK_SIZE], pad[AES_BLOCK_SIZE];
const u8 *pos, *end;
diff --git a/net/mac80211/aes_cmac.h b/net/mac80211/aes_cmac.h
index 3702041..c827e1d 100644
--- a/net/mac80211/aes_cmac.h
+++ b/net/mac80211/aes_cmac.h
@@ -11,6 +11,10 @@
#include <linux/crypto.h>
+void gf_mulx(u8 *pad);
+void aes_cmac_vector(struct crypto_cipher *tfm, size_t num_elem,
+ const u8 *addr[], const size_t *len, u8 *mac,
+ size_t mac_len);
struct crypto_cipher *ieee80211_aes_cmac_key_setup(const u8 key[],
size_t key_len);
void ieee80211_aes_cmac(struct crypto_cipher *tfm, const u8 *aad,
diff --git a/net/mac80211/aes_gcm.c b/net/mac80211/aes_gcm.c
index 3afe361f..8a4397c 100644
--- a/net/mac80211/aes_gcm.c
+++ b/net/mac80211/aes_gcm.c
@@ -15,20 +15,23 @@
#include "key.h"
#include "aes_gcm.h"
-void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
- u8 *data, size_t data_len, u8 *mic)
+int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
+ u8 *data, size_t data_len, u8 *mic)
{
struct scatterlist sg[3];
+ struct aead_request *aead_req;
+ int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
+ u8 *__aad;
- char aead_req_data[sizeof(struct aead_request) +
- crypto_aead_reqsize(tfm)]
- __aligned(__alignof__(struct aead_request));
- struct aead_request *aead_req = (void *)aead_req_data;
+ aead_req = kzalloc(reqsize + GCM_AAD_LEN, GFP_ATOMIC);
+ if (!aead_req)
+ return -ENOMEM;
- memset(aead_req, 0, sizeof(aead_req_data));
+ __aad = (u8 *)aead_req + reqsize;
+ memcpy(__aad, aad, GCM_AAD_LEN);
sg_init_table(sg, 3);
- sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+ sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad));
sg_set_buf(&sg[1], data, data_len);
sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN);
@@ -37,24 +40,31 @@ void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
aead_request_set_ad(aead_req, sg[0].length);
crypto_aead_encrypt(aead_req);
+ kzfree(aead_req);
+ return 0;
}
int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
u8 *data, size_t data_len, u8 *mic)
{
struct scatterlist sg[3];
- char aead_req_data[sizeof(struct aead_request) +
- crypto_aead_reqsize(tfm)]
- __aligned(__alignof__(struct aead_request));
- struct aead_request *aead_req = (void *)aead_req_data;
+ struct aead_request *aead_req;
+ int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
+ u8 *__aad;
+ int err;
if (data_len == 0)
return -EINVAL;
- memset(aead_req, 0, sizeof(aead_req_data));
+ aead_req = kzalloc(reqsize + GCM_AAD_LEN, GFP_ATOMIC);
+ if (!aead_req)
+ return -ENOMEM;
+
+ __aad = (u8 *)aead_req + reqsize;
+ memcpy(__aad, aad, GCM_AAD_LEN);
sg_init_table(sg, 3);
- sg_set_buf(&sg[0], &aad[2], be16_to_cpup((__be16 *)aad));
+ sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad));
sg_set_buf(&sg[1], data, data_len);
sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN);
@@ -63,7 +73,10 @@ int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
data_len + IEEE80211_GCMP_MIC_LEN, j_0);
aead_request_set_ad(aead_req, sg[0].length);
- return crypto_aead_decrypt(aead_req);
+ err = crypto_aead_decrypt(aead_req);
+ kzfree(aead_req);
+
+ return err;
}
struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[],
diff --git a/net/mac80211/aes_gcm.h b/net/mac80211/aes_gcm.h
index 1347fda..55aed53 100644
--- a/net/mac80211/aes_gcm.h
+++ b/net/mac80211/aes_gcm.h
@@ -11,8 +11,10 @@
#include <linux/crypto.h>
-void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
- u8 *data, size_t data_len, u8 *mic);
+#define GCM_AAD_LEN 32
+
+int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
+ u8 *data, size_t data_len, u8 *mic);
int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
u8 *data, size_t data_len, u8 *mic);
struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[],
diff --git a/net/mac80211/aes_gmac.c b/net/mac80211/aes_gmac.c
index 3ddd927..bd72a86 100644
--- a/net/mac80211/aes_gmac.c
+++ b/net/mac80211/aes_gmac.c
@@ -17,28 +17,27 @@
#include "key.h"
#include "aes_gmac.h"
-#define GMAC_MIC_LEN 16
-#define GMAC_NONCE_LEN 12
-#define AAD_LEN 20
-
int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce,
const u8 *data, size_t data_len, u8 *mic)
{
struct scatterlist sg[4];
- char aead_req_data[sizeof(struct aead_request) +
- crypto_aead_reqsize(tfm)]
- __aligned(__alignof__(struct aead_request));
- struct aead_request *aead_req = (void *)aead_req_data;
- u8 zero[GMAC_MIC_LEN], iv[AES_BLOCK_SIZE];
+ u8 *zero, *__aad, iv[AES_BLOCK_SIZE];
+ struct aead_request *aead_req;
+ int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
if (data_len < GMAC_MIC_LEN)
return -EINVAL;
- memset(aead_req, 0, sizeof(aead_req_data));
+ aead_req = kzalloc(reqsize + GMAC_MIC_LEN + GMAC_AAD_LEN, GFP_ATOMIC);
+ if (!aead_req)
+ return -ENOMEM;
- memset(zero, 0, GMAC_MIC_LEN);
+ zero = (u8 *)aead_req + reqsize;
+ __aad = zero + GMAC_MIC_LEN;
+ memcpy(__aad, aad, GMAC_AAD_LEN);
+
sg_init_table(sg, 4);
- sg_set_buf(&sg[0], aad, AAD_LEN);
+ sg_set_buf(&sg[0], __aad, GMAC_AAD_LEN);
sg_set_buf(&sg[1], data, data_len - GMAC_MIC_LEN);
sg_set_buf(&sg[2], zero, GMAC_MIC_LEN);
sg_set_buf(&sg[3], mic, GMAC_MIC_LEN);
@@ -49,9 +48,10 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce,
aead_request_set_tfm(aead_req, tfm);
aead_request_set_crypt(aead_req, sg, sg, 0, iv);
- aead_request_set_ad(aead_req, AAD_LEN + data_len);
+ aead_request_set_ad(aead_req, GMAC_AAD_LEN + data_len);
crypto_aead_encrypt(aead_req);
+ kzfree(aead_req);
return 0;
}
diff --git a/net/mac80211/aes_gmac.h b/net/mac80211/aes_gmac.h
index d328204..32e6442 100644
--- a/net/mac80211/aes_gmac.h
+++ b/net/mac80211/aes_gmac.h
@@ -11,6 +11,10 @@
#include <linux/crypto.h>
+#define GMAC_AAD_LEN 20
+#define GMAC_MIC_LEN 16
+#define GMAC_NONCE_LEN 12
+
struct crypto_aead *ieee80211_aes_gmac_key_setup(const u8 key[],
size_t key_len);
int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce,
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index f6749dc..3b5fd41 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -315,11 +315,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta,
mutex_lock(&sta->ampdu_mlme.mtx);
if (test_bit(tid, sta->ampdu_mlme.agg_session_valid)) {
- tid_agg_rx = rcu_dereference_protected(
- sta->ampdu_mlme.tid_rx[tid],
- lockdep_is_held(&sta->ampdu_mlme.mtx));
-
- if (tid_agg_rx->dialog_token == dialog_token) {
+ if (sta->ampdu_mlme.tid_rx_token[tid] == dialog_token) {
ht_dbg_ratelimited(sta->sdata,
"updated AddBA Req from %pM on tid %u\n",
sta->sta.addr, tid);
@@ -396,7 +392,6 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta,
}
/* update data */
- tid_agg_rx->dialog_token = dialog_token;
tid_agg_rx->ssn = start_seq_num;
tid_agg_rx->head_seq_num = start_seq_num;
tid_agg_rx->buf_size = buf_size;
@@ -418,6 +413,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta,
if (status == WLAN_STATUS_SUCCESS) {
__set_bit(tid, sta->ampdu_mlme.agg_session_valid);
__clear_bit(tid, sta->ampdu_mlme.unexpected_agg);
+ sta->ampdu_mlme.tid_rx_token[tid] = dialog_token;
}
mutex_unlock(&sta->ampdu_mlme.mtx);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index fd6541f..e91e503 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -357,10 +357,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev,
mutex_lock(&local->sta_mtx);
if (mac_addr) {
- if (ieee80211_vif_is_mesh(&sdata->vif))
- sta = sta_info_get(sdata, mac_addr);
- else
- sta = sta_info_get_bss(sdata, mac_addr);
+ sta = sta_info_get_bss(sdata, mac_addr);
/*
* The ASSOC test makes sure the driver is ready to
* receive the key. When wpa_supplicant has roamed
@@ -867,6 +864,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
}
sdata->needed_rx_chains = sdata->local->rx_chains;
+ sdata->vif.bss_conf.beacon_int = params->beacon_interval;
+
mutex_lock(&local->mtx);
err = ieee80211_vif_use_channel(sdata, ¶ms->chandef,
IEEE80211_CHANCTX_SHARED);
@@ -897,7 +896,6 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
vlan->vif.type);
}
- sdata->vif.bss_conf.beacon_int = params->beacon_interval;
sdata->vif.bss_conf.dtim_period = params->dtim_period;
sdata->vif.bss_conf.enable_beacon = true;
sdata->vif.bss_conf.allow_p2p_go_ps = sdata->vif.p2p;
@@ -1523,9 +1521,6 @@ static int ieee80211_change_station(struct wiphy *wiphy,
goto out_err;
if (params->vlan && params->vlan != sta->sdata->dev) {
- bool prev_4addr = false;
- bool new_4addr = false;
-
vlansdata = IEEE80211_DEV_TO_SUB_IF(params->vlan);
if (params->vlan->ieee80211_ptr->use_4addr) {
@@ -1535,26 +1530,21 @@ static int ieee80211_change_station(struct wiphy *wiphy,
}
rcu_assign_pointer(vlansdata->u.vlan.sta, sta);
- new_4addr = true;
__ieee80211_check_fast_rx_iface(vlansdata);
}
if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
- sta->sdata->u.vlan.sta) {
+ sta->sdata->u.vlan.sta)
RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL);
- prev_4addr = true;
- }
+
+ if (test_sta_flag(sta, WLAN_STA_AUTHORIZED))
+ ieee80211_vif_dec_num_mcast(sta->sdata);
sta->sdata = vlansdata;
ieee80211_check_fast_xmit(sta);
- if (sta->sta_state == IEEE80211_STA_AUTHORIZED &&
- prev_4addr != new_4addr) {
- if (new_4addr)
- atomic_dec(&sta->sdata->bss->num_mcast_sta);
- else
- atomic_inc(&sta->sdata->bss->num_mcast_sta);
- }
+ if (test_sta_flag(sta, WLAN_STA_AUTHORIZED))
+ ieee80211_vif_inc_num_mcast(sta->sdata);
ieee80211_send_layer2_update(sta);
}
@@ -2480,13 +2470,6 @@ int __ieee80211_request_smps_ap(struct ieee80211_sub_if_data *sdata,
smps_mode == IEEE80211_SMPS_AUTOMATIC)
return 0;
- /* If no associated stations, there's no need to do anything */
- if (!atomic_read(&sdata->u.ap.num_mcast_sta)) {
- sdata->smps_mode = smps_mode;
- ieee80211_queue_work(&sdata->local->hw, &sdata->recalc_smps);
- return 0;
- }
-
ht_dbg(sdata,
"SMPS %d requested in AP mode, sending Action frame to %d stations\n",
smps_mode, atomic_read(&sdata->u.ap.num_mcast_sta));
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index f56e2f4..e02ba42 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -210,6 +210,7 @@ static const char *hw_flag_names[] = {
FLAG(TX_AMSDU),
FLAG(TX_FRAG_LIST),
FLAG(REPORTS_LOW_ACK),
+ FLAG(SUPPORTS_TX_FRAG),
#undef FLAG
};
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index bcec124..1a05f85 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -477,6 +477,7 @@ IEEE80211_IF_FILE_RW(tdls_wider_bw);
IEEE80211_IF_FILE(num_mcast_sta, u.ap.num_mcast_sta, ATOMIC);
IEEE80211_IF_FILE(num_sta_ps, u.ap.ps.num_sta_ps, ATOMIC);
IEEE80211_IF_FILE(dtim_count, u.ap.ps.dtim_count, DEC);
+IEEE80211_IF_FILE(num_mcast_sta_vlan, u.vlan.num_mcast_sta, ATOMIC);
static ssize_t ieee80211_if_fmt_num_buffered_multicast(
const struct ieee80211_sub_if_data *sdata, char *buf, int buflen)
@@ -684,6 +685,13 @@ static void add_ap_files(struct ieee80211_sub_if_data *sdata)
DEBUGFS_ADD_MODE(tkip_mic_test, 0200);
}
+static void add_vlan_files(struct ieee80211_sub_if_data *sdata)
+{
+ /* add num_mcast_sta_vlan using name num_mcast_sta */
+ debugfs_create_file("num_mcast_sta", 0400, sdata->vif.debugfs_dir,
+ sdata, &num_mcast_sta_vlan_ops);
+}
+
static void add_ibss_files(struct ieee80211_sub_if_data *sdata)
{
DEBUGFS_ADD_MODE(tsf, 0600);
@@ -787,6 +795,9 @@ static void add_files(struct ieee80211_sub_if_data *sdata)
case NL80211_IFTYPE_AP:
add_ap_files(sdata);
break;
+ case NL80211_IFTYPE_AP_VLAN:
+ add_vlan_files(sdata);
+ break;
case NL80211_IFTYPE_WDS:
add_wds_files(sdata);
break;
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index a2fcdb4..f6003b8 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -199,13 +199,18 @@ static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf,
"TID\t\tRX\tDTKN\tSSN\t\tTX\tDTKN\tpending\n");
for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
+ bool tid_rx_valid;
+
tid_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[i]);
tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[i]);
+ tid_rx_valid = test_bit(i, sta->ampdu_mlme.agg_session_valid);
p += scnprintf(p, sizeof(buf) + buf - p, "%02d", i);
- p += scnprintf(p, sizeof(buf) + buf - p, "\t\t%x", !!tid_rx);
+ p += scnprintf(p, sizeof(buf) + buf - p, "\t\t%x",
+ tid_rx_valid);
p += scnprintf(p, sizeof(buf) + buf - p, "\t%#.2x",
- tid_rx ? tid_rx->dialog_token : 0);
+ tid_rx_valid ?
+ sta->ampdu_mlme.tid_rx_token[i] : 0);
p += scnprintf(p, sizeof(buf) + buf - p, "\t%#.3x",
tid_rx ? tid_rx->ssn : 0);
diff --git a/net/mac80211/fils_aead.c b/net/mac80211/fils_aead.c
new file mode 100644
index 0000000..ecfdd97
--- /dev/null
+++ b/net/mac80211/fils_aead.c
@@ -0,0 +1,342 @@
+/*
+ * FILS AEAD for (Re)Association Request/Response frames
+ * Copyright 2016, Qualcomm Atheros, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/skcipher.h>
+
+#include "ieee80211_i.h"
+#include "aes_cmac.h"
+#include "fils_aead.h"
+
+static int aes_s2v(struct crypto_cipher *tfm,
+ size_t num_elem, const u8 *addr[], size_t len[], u8 *v)
+{
+ u8 d[AES_BLOCK_SIZE], tmp[AES_BLOCK_SIZE];
+ size_t i;
+ const u8 *data[2];
+ size_t data_len[2], data_elems;
+
+ /* D = AES-CMAC(K, <zero>) */
+ memset(tmp, 0, AES_BLOCK_SIZE);
+ data[0] = tmp;
+ data_len[0] = AES_BLOCK_SIZE;
+ aes_cmac_vector(tfm, 1, data, data_len, d, AES_BLOCK_SIZE);
+
+ for (i = 0; i < num_elem - 1; i++) {
+ /* D = dbl(D) xor AES_CMAC(K, Si) */
+ gf_mulx(d); /* dbl */
+ aes_cmac_vector(tfm, 1, &addr[i], &len[i], tmp,
+ AES_BLOCK_SIZE);
+ crypto_xor(d, tmp, AES_BLOCK_SIZE);
+ }
+
+ if (len[i] >= AES_BLOCK_SIZE) {
+ /* len(Sn) >= 128 */
+ size_t j;
+ const u8 *pos;
+
+ /* T = Sn xorend D */
+
+ /* Use a temporary buffer to perform xorend on Sn (addr[i]) to
+ * avoid modifying the const input argument.
+ */
+ data[0] = addr[i];
+ data_len[0] = len[i] - AES_BLOCK_SIZE;
+ pos = addr[i] + data_len[0];
+ for (j = 0; j < AES_BLOCK_SIZE; j++)
+ tmp[j] = pos[j] ^ d[j];
+ data[1] = tmp;
+ data_len[1] = AES_BLOCK_SIZE;
+ data_elems = 2;
+ } else {
+ /* len(Sn) < 128 */
+ /* T = dbl(D) xor pad(Sn) */
+ gf_mulx(d); /* dbl */
+ memset(tmp, 0, AES_BLOCK_SIZE);
+ memcpy(tmp, addr[i], len[i]);
+ tmp[len[i]] = 0x80;
+ crypto_xor(d, tmp, AES_BLOCK_SIZE);
+ data[0] = d;
+ data_len[0] = sizeof(d);
+ data_elems = 1;
+ }
+ /* V = AES-CMAC(K, T) */
+ aes_cmac_vector(tfm, data_elems, data, data_len, v, AES_BLOCK_SIZE);
+
+ return 0;
+}
+
+/* Note: addr[] and len[] needs to have one extra slot at the end. */
+static int aes_siv_encrypt(const u8 *key, size_t key_len,
+ const u8 *plain, size_t plain_len,
+ size_t num_elem, const u8 *addr[],
+ size_t len[], u8 *out)
+{
+ u8 v[AES_BLOCK_SIZE];
+ struct crypto_cipher *tfm;
+ struct crypto_skcipher *tfm2;
+ struct skcipher_request *req;
+ int res;
+ struct scatterlist src[1], dst[1];
+ u8 *tmp;
+
+ key_len /= 2; /* S2V key || CTR key */
+
+ addr[num_elem] = plain;
+ len[num_elem] = plain_len;
+ num_elem++;
+
+ /* S2V */
+
+ tfm = crypto_alloc_cipher("aes", 0, 0);
+ if (IS_ERR(tfm))
+ return PTR_ERR(tfm);
+ /* K1 for S2V */
+ res = crypto_cipher_setkey(tfm, key, key_len);
+ if (!res)
+ res = aes_s2v(tfm, num_elem, addr, len, v);
+ crypto_free_cipher(tfm);
+ if (res)
+ return res;
+
+ /* Use a temporary buffer of the plaintext to handle need for
+ * overwriting this during AES-CTR.
+ */
+ tmp = kmemdup(plain, plain_len, GFP_KERNEL);
+ if (!tmp)
+ return -ENOMEM;
+
+ /* IV for CTR before encrypted data */
+ memcpy(out, v, AES_BLOCK_SIZE);
+
+ /* Synthetic IV to be used as the initial counter in CTR:
+ * Q = V bitand (1^64 || 0^1 || 1^31 || 0^1 || 1^31)
+ */
+ v[8] &= 0x7f;
+ v[12] &= 0x7f;
+
+ /* CTR */
+
+ tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, 0);
+ if (IS_ERR(tfm2)) {
+ kfree(tmp);
+ return PTR_ERR(tfm2);
+ }
+ /* K2 for CTR */
+ res = crypto_skcipher_setkey(tfm2, key + key_len, key_len);
+ if (res)
+ goto fail;
+
+ req = skcipher_request_alloc(tfm2, GFP_KERNEL);
+ if (!req) {
+ res = -ENOMEM;
+ goto fail;
+ }
+
+ sg_init_one(src, tmp, plain_len);
+ sg_init_one(dst, out + AES_BLOCK_SIZE, plain_len);
+ skcipher_request_set_crypt(req, src, dst, plain_len, v);
+ res = crypto_skcipher_encrypt(req);
+ skcipher_request_free(req);
+fail:
+ kfree(tmp);
+ crypto_free_skcipher(tfm2);
+ return res;
+}
+
+/* Note: addr[] and len[] needs to have one extra slot at the end. */
+static int aes_siv_decrypt(const u8 *key, size_t key_len,
+ const u8 *iv_crypt, size_t iv_c_len,
+ size_t num_elem, const u8 *addr[], size_t len[],
+ u8 *out)
+{
+ struct crypto_cipher *tfm;
+ struct crypto_skcipher *tfm2;
+ struct skcipher_request *req;
+ struct scatterlist src[1], dst[1];
+ size_t crypt_len;
+ int res;
+ u8 frame_iv[AES_BLOCK_SIZE], iv[AES_BLOCK_SIZE];
+ u8 check[AES_BLOCK_SIZE];
+
+ crypt_len = iv_c_len - AES_BLOCK_SIZE;
+ key_len /= 2; /* S2V key || CTR key */
+ addr[num_elem] = out;
+ len[num_elem] = crypt_len;
+ num_elem++;
+
+ memcpy(iv, iv_crypt, AES_BLOCK_SIZE);
+ memcpy(frame_iv, iv_crypt, AES_BLOCK_SIZE);
+
+ /* Synthetic IV to be used as the initial counter in CTR:
+ * Q = V bitand (1^64 || 0^1 || 1^31 || 0^1 || 1^31)
+ */
+ iv[8] &= 0x7f;
+ iv[12] &= 0x7f;
+
+ /* CTR */
+
+ tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, 0);
+ if (IS_ERR(tfm2))
+ return PTR_ERR(tfm2);
+ /* K2 for CTR */
+ res = crypto_skcipher_setkey(tfm2, key + key_len, key_len);
+ if (res) {
+ crypto_free_skcipher(tfm2);
+ return res;
+ }
+
+ req = skcipher_request_alloc(tfm2, GFP_KERNEL);
+ if (!req) {
+ crypto_free_skcipher(tfm2);
+ return -ENOMEM;
+ }
+
+ sg_init_one(src, iv_crypt + AES_BLOCK_SIZE, crypt_len);
+ sg_init_one(dst, out, crypt_len);
+ skcipher_request_set_crypt(req, src, dst, crypt_len, iv);
+ res = crypto_skcipher_decrypt(req);
+ skcipher_request_free(req);
+ crypto_free_skcipher(tfm2);
+ if (res)
+ return res;
+
+ /* S2V */
+
+ tfm = crypto_alloc_cipher("aes", 0, 0);
+ if (IS_ERR(tfm))
+ return PTR_ERR(tfm);
+ /* K1 for S2V */
+ res = crypto_cipher_setkey(tfm, key, key_len);
+ if (!res)
+ res = aes_s2v(tfm, num_elem, addr, len, check);
+ crypto_free_cipher(tfm);
+ if (res)
+ return res;
+ if (memcmp(check, frame_iv, AES_BLOCK_SIZE) != 0)
+ return -EINVAL;
+ return 0;
+}
+
+int fils_encrypt_assoc_req(struct sk_buff *skb,
+ struct ieee80211_mgd_assoc_data *assoc_data)
+{
+ struct ieee80211_mgmt *mgmt = (void *)skb->data;
+ u8 *capab, *ies, *encr;
+ const u8 *addr[5 + 1], *session;
+ size_t len[5 + 1];
+ size_t crypt_len;
+
+ if (ieee80211_is_reassoc_req(mgmt->frame_control)) {
+ capab = (u8 *)&mgmt->u.reassoc_req.capab_info;
+ ies = mgmt->u.reassoc_req.variable;
+ } else {
+ capab = (u8 *)&mgmt->u.assoc_req.capab_info;
+ ies = mgmt->u.assoc_req.variable;
+ }
+
+ session = cfg80211_find_ext_ie(WLAN_EID_EXT_FILS_SESSION,
+ ies, skb->data + skb->len - ies);
+ if (!session || session[1] != 1 + 8)
+ return -EINVAL;
+ /* encrypt after FILS Session element */
+ encr = (u8 *)session + 2 + 1 + 8;
+
+ /* AES-SIV AAD vectors */
+
+ /* The STA's MAC address */
+ addr[0] = mgmt->sa;
+ len[0] = ETH_ALEN;
+ /* The AP's BSSID */
+ addr[1] = mgmt->da;
+ len[1] = ETH_ALEN;
+ /* The STA's nonce */
+ addr[2] = assoc_data->fils_nonces;
+ len[2] = FILS_NONCE_LEN;
+ /* The AP's nonce */
+ addr[3] = &assoc_data->fils_nonces[FILS_NONCE_LEN];
+ len[3] = FILS_NONCE_LEN;
+ /* The (Re)Association Request frame from the Capability Information
+ * field to the FILS Session element (both inclusive).
+ */
+ addr[4] = capab;
+ len[4] = encr - capab;
+
+ crypt_len = skb->data + skb->len - encr;
+ skb_put(skb, AES_BLOCK_SIZE);
+ return aes_siv_encrypt(assoc_data->fils_kek, assoc_data->fils_kek_len,
+ encr, crypt_len, 1, addr, len, encr);
+}
+
+int fils_decrypt_assoc_resp(struct ieee80211_sub_if_data *sdata,
+ u8 *frame, size_t *frame_len,
+ struct ieee80211_mgd_assoc_data *assoc_data)
+{
+ struct ieee80211_mgmt *mgmt = (void *)frame;
+ u8 *capab, *ies, *encr;
+ const u8 *addr[5 + 1], *session;
+ size_t len[5 + 1];
+ int res;
+ size_t crypt_len;
+
+ if (*frame_len < 24 + 6)
+ return -EINVAL;
+
+ capab = (u8 *)&mgmt->u.assoc_resp.capab_info;
+ ies = mgmt->u.assoc_resp.variable;
+ session = cfg80211_find_ext_ie(WLAN_EID_EXT_FILS_SESSION,
+ ies, frame + *frame_len - ies);
+ if (!session || session[1] != 1 + 8) {
+ mlme_dbg(sdata,
+ "No (valid) FILS Session element in (Re)Association Response frame from %pM",
+ mgmt->sa);
+ return -EINVAL;
+ }
+ /* decrypt after FILS Session element */
+ encr = (u8 *)session + 2 + 1 + 8;
+
+ /* AES-SIV AAD vectors */
+
+ /* The AP's BSSID */
+ addr[0] = mgmt->sa;
+ len[0] = ETH_ALEN;
+ /* The STA's MAC address */
+ addr[1] = mgmt->da;
+ len[1] = ETH_ALEN;
+ /* The AP's nonce */
+ addr[2] = &assoc_data->fils_nonces[FILS_NONCE_LEN];
+ len[2] = FILS_NONCE_LEN;
+ /* The STA's nonce */
+ addr[3] = assoc_data->fils_nonces;
+ len[3] = FILS_NONCE_LEN;
+ /* The (Re)Association Response frame from the Capability Information
+ * field to the FILS Session element (both inclusive).
+ */
+ addr[4] = capab;
+ len[4] = encr - capab;
+
+ crypt_len = frame + *frame_len - encr;
+ if (crypt_len < AES_BLOCK_SIZE) {
+ mlme_dbg(sdata,
+ "Not enough room for AES-SIV data after FILS Session element in (Re)Association Response frame from %pM",
+ mgmt->sa);
+ return -EINVAL;
+ }
+ res = aes_siv_decrypt(assoc_data->fils_kek, assoc_data->fils_kek_len,
+ encr, crypt_len, 5, addr, len, encr);
+ if (res != 0) {
+ mlme_dbg(sdata,
+ "AES-SIV decryption of (Re)Association Response frame from %pM failed",
+ mgmt->sa);
+ return res;
+ }
+ *frame_len -= AES_BLOCK_SIZE;
+ return 0;
+}
diff --git a/net/mac80211/fils_aead.h b/net/mac80211/fils_aead.h
new file mode 100644
index 0000000..fbc6523
--- /dev/null
+++ b/net/mac80211/fils_aead.h
@@ -0,0 +1,19 @@
+/*
+ * FILS AEAD for (Re)Association Request/Response frames
+ * Copyright 2016, Qualcomm Atheros, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef FILS_AEAD_H
+#define FILS_AEAD_H
+
+int fils_encrypt_assoc_req(struct sk_buff *skb,
+ struct ieee80211_mgd_assoc_data *assoc_data);
+int fils_decrypt_assoc_resp(struct ieee80211_sub_if_data *sdata,
+ u8 *frame, size_t *frame_len,
+ struct ieee80211_mgd_assoc_data *assoc_data);
+
+#endif /* FILS_AEAD_H */
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 34c2add..d37a577 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -84,6 +84,8 @@ struct ieee80211_local;
#define IEEE80211_DEFAULT_MAX_SP_LEN \
IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL
+extern const u8 ieee80211_ac_to_qos_mask[IEEE80211_NUM_ACS];
+
#define IEEE80211_DEAUTH_FRAME_LEN (24 /* hdr */ + 2 /* reason */)
#define IEEE80211_MAX_NAN_INSTANCE_ID 255
@@ -307,6 +309,7 @@ struct ieee80211_if_vlan {
/* used for all tx if the VLAN is configured to 4-addr mode */
struct sta_info __rcu *sta;
+ atomic_t num_mcast_sta; /* number of stations receiving multicast */
};
struct mesh_stats {
@@ -398,6 +401,10 @@ struct ieee80211_mgd_assoc_data {
struct ieee80211_vht_cap ap_vht_cap;
+ u8 fils_nonces[2 * FILS_NONCE_LEN];
+ u8 fils_kek[FILS_MAX_KEK_LEN];
+ size_t fils_kek_len;
+
size_t ie_len;
u8 ie[];
};
@@ -442,7 +449,7 @@ struct ieee80211_if_managed {
struct ieee80211_mgd_auth_data *auth_data;
struct ieee80211_mgd_assoc_data *assoc_data;
- u8 bssid[ETH_ALEN];
+ u8 bssid[ETH_ALEN] __aligned(2);
u16 aid;
@@ -1527,6 +1534,23 @@ ieee80211_have_rx_timestamp(struct ieee80211_rx_status *status)
return false;
}
+void ieee80211_vif_inc_num_mcast(struct ieee80211_sub_if_data *sdata);
+void ieee80211_vif_dec_num_mcast(struct ieee80211_sub_if_data *sdata);
+
+/* This function returns the number of multicast stations connected to this
+ * interface. It returns -1 if that number is not tracked, that is for netdevs
+ * not in AP or AP_VLAN mode or when using 4addr.
+ */
+static inline int
+ieee80211_vif_get_num_mcast_if(struct ieee80211_sub_if_data *sdata)
+{
+ if (sdata->vif.type == NL80211_IFTYPE_AP)
+ return atomic_read(&sdata->u.ap.num_mcast_sta);
+ if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN && !sdata->u.vlan.sta)
+ return atomic_read(&sdata->u.vlan.num_mcast_sta);
+ return -1;
+}
+
u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
struct ieee80211_rx_status *status,
unsigned int mpdu_len,
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 73e6a8f..41497b6 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1998,3 +1998,19 @@ void ieee80211_iface_exit(void)
{
unregister_netdevice_notifier(&mac80211_netdev_notifier);
}
+
+void ieee80211_vif_inc_num_mcast(struct ieee80211_sub_if_data *sdata)
+{
+ if (sdata->vif.type == NL80211_IFTYPE_AP)
+ atomic_inc(&sdata->u.ap.num_mcast_sta);
+ else if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+ atomic_inc(&sdata->u.vlan.num_mcast_sta);
+}
+
+void ieee80211_vif_dec_num_mcast(struct ieee80211_sub_if_data *sdata)
+{
+ if (sdata->vif.type == NL80211_IFTYPE_AP)
+ atomic_dec(&sdata->u.ap.num_mcast_sta);
+ else if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+ atomic_dec(&sdata->u.vlan.num_mcast_sta);
+}
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 1075ac2..1822c77 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -549,6 +549,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
NL80211_FEATURE_MAC_ON_CREATE |
NL80211_FEATURE_USERSPACE_MPM |
NL80211_FEATURE_FULL_AP_CLIENT_STATE;
+ wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_FILS_STA);
if (!ops->hw_scan)
wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN |
@@ -821,6 +822,10 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
!local->ops->tdls_recv_channel_switch))
return -EOPNOTSUPP;
+ if (WARN_ON(ieee80211_hw_check(hw, SUPPORTS_TX_FRAG) &&
+ !local->ops->set_frag_threshold))
+ return -EINVAL;
+
if (WARN_ON(local->hw.wiphy->interface_modes &
BIT(NL80211_IFTYPE_NAN) &&
(!local->ops->start_nan || !local->ops->stop_nan)))
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 7486f2d..d157b25 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -30,6 +30,7 @@
#include "driver-ops.h"
#include "rate.h"
#include "led.h"
+#include "fils_aead.h"
#define IEEE80211_AUTH_TIMEOUT (HZ / 5)
#define IEEE80211_AUTH_TIMEOUT_LONG (HZ / 2)
@@ -652,6 +653,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
2 + sizeof(struct ieee80211_ht_cap) + /* HT */
2 + sizeof(struct ieee80211_vht_cap) + /* VHT */
assoc_data->ie_len + /* extra IEs */
+ (assoc_data->fils_kek_len ? 16 /* AES-SIV */ : 0) +
9, /* WMM */
GFP_KERNEL);
if (!skb)
@@ -875,6 +877,12 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
memcpy(pos, assoc_data->ie + offset, noffset - offset);
}
+ if (assoc_data->fils_kek_len &&
+ fils_encrypt_assoc_req(skb, assoc_data) < 0) {
+ dev_kfree_skb(skb);
+ return;
+ }
+
drv_mgd_prepare_tx(local, sdata);
IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT;
@@ -2618,6 +2626,9 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
case WLAN_AUTH_LEAP:
case WLAN_AUTH_FT:
case WLAN_AUTH_SAE:
+ case WLAN_AUTH_FILS_SK:
+ case WLAN_AUTH_FILS_SK_PFS:
+ case WLAN_AUTH_FILS_PK:
break;
case WLAN_AUTH_SHARED_KEY:
if (ifmgd->auth_data->expected_transaction != 4) {
@@ -3143,6 +3154,10 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
reassoc ? "Rea" : "A", mgmt->sa,
capab_info, status_code, (u16)(aid & ~(BIT(15) | BIT(14))));
+ if (assoc_data->fils_kek_len &&
+ fils_decrypt_assoc_resp(sdata, (u8 *)mgmt, &len, assoc_data) < 0)
+ return;
+
pos = mgmt->u.assoc_resp.variable;
ieee802_11_parse_elems(pos, len - (pos - (u8 *) mgmt), false, &elems);
@@ -3193,7 +3208,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
uapsd_queues = 0;
for (ac = 0; ac < IEEE80211_NUM_ACS; ac++)
if (sdata->tx_conf[ac].uapsd)
- uapsd_queues |= BIT(ac);
+ uapsd_queues |= ieee80211_ac_to_qos_mask[ac];
}
cfg80211_rx_assoc_resp(sdata->dev, bss, (u8 *)mgmt, len, uapsd_queues);
@@ -4479,24 +4494,36 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
case NL80211_AUTHTYPE_SAE:
auth_alg = WLAN_AUTH_SAE;
break;
+ case NL80211_AUTHTYPE_FILS_SK:
+ auth_alg = WLAN_AUTH_FILS_SK;
+ break;
+ case NL80211_AUTHTYPE_FILS_SK_PFS:
+ auth_alg = WLAN_AUTH_FILS_SK_PFS;
+ break;
+ case NL80211_AUTHTYPE_FILS_PK:
+ auth_alg = WLAN_AUTH_FILS_PK;
+ break;
default:
return -EOPNOTSUPP;
}
- auth_data = kzalloc(sizeof(*auth_data) + req->sae_data_len +
+ auth_data = kzalloc(sizeof(*auth_data) + req->auth_data_len +
req->ie_len, GFP_KERNEL);
if (!auth_data)
return -ENOMEM;
auth_data->bss = req->bss;
- if (req->sae_data_len >= 4) {
- __le16 *pos = (__le16 *) req->sae_data;
- auth_data->sae_trans = le16_to_cpu(pos[0]);
- auth_data->sae_status = le16_to_cpu(pos[1]);
- memcpy(auth_data->data, req->sae_data + 4,
- req->sae_data_len - 4);
- auth_data->data_len += req->sae_data_len - 4;
+ if (req->auth_data_len >= 4) {
+ if (req->auth_type == NL80211_AUTHTYPE_SAE) {
+ __le16 *pos = (__le16 *) req->auth_data;
+
+ auth_data->sae_trans = le16_to_cpu(pos[0]);
+ auth_data->sae_status = le16_to_cpu(pos[1]);
+ }
+ memcpy(auth_data->data, req->auth_data + 4,
+ req->auth_data_len - 4);
+ auth_data->data_len += req->auth_data_len - 4;
}
if (req->ie && req->ie_len) {
@@ -4692,6 +4719,21 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
assoc_data->ie_len = req->ie_len;
}
+ if (req->fils_kek) {
+ /* should already be checked in cfg80211 - so warn */
+ if (WARN_ON(req->fils_kek_len > FILS_MAX_KEK_LEN)) {
+ err = -EINVAL;
+ goto err_free;
+ }
+ memcpy(assoc_data->fils_kek, req->fils_kek,
+ req->fils_kek_len);
+ assoc_data->fils_kek_len = req->fils_kek_len;
+ }
+
+ if (req->fils_nonces)
+ memcpy(assoc_data->fils_nonces, req->fils_nonces,
+ 2 * FILS_NONCE_LEN);
+
assoc_data->bss = req->bss;
if (ifmgd->req_smps == IEEE80211_SMPS_AUTOMATIC) {
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index c3f610b..eede5c6 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -820,7 +820,7 @@ int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
mgmt->u.action.category == WLAN_CATEGORY_SPECTRUM_MGMT)
break;
rcu_read_lock();
- sta = sta_info_get(sdata, mgmt->da);
+ sta = sta_info_get_bss(sdata, mgmt->da);
rcu_read_unlock();
if (!sta)
return -ENOLINK;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 6175db3..eeab725 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1394,13 +1394,15 @@ void ieee80211_sta_uapsd_trigger(struct ieee80211_sta *pubsta, u8 tid)
u8 ac = ieee802_1d_to_ac[tid & 7];
/*
- * If this AC is not trigger-enabled do nothing.
+ * If this AC is not trigger-enabled do nothing unless the
+ * driver is calling us after it already checked.
*
* NB: This could/should check a separate bitmap of trigger-
* enabled queues, but for now we only implement uAPSD w/o
* TSPEC changes to the ACs, so they're always the same.
*/
- if (!(sta->sta.uapsd_queues & BIT(ac)))
+ if (!(sta->sta.uapsd_queues & ieee80211_ac_to_qos_mask[ac]) &&
+ tid != IEEE80211_NUM_TIDS)
return;
/* if we are in a service period, do nothing */
@@ -2215,7 +2217,8 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx)
sdata->vif.type == NL80211_IFTYPE_AP_VLAN) &&
!(sdata->flags & IEEE80211_SDATA_DONT_BRIDGE_PACKETS) &&
(sdata->vif.type != NL80211_IFTYPE_AP_VLAN || !sdata->u.vlan.sta)) {
- if (is_multicast_ether_addr(ehdr->h_dest)) {
+ if (is_multicast_ether_addr(ehdr->h_dest) &&
+ ieee80211_vif_get_num_mcast_if(sdata) != 0) {
/*
* send multicast frames both to higher layers in
* local net stack and back to the wireless medium
@@ -2224,7 +2227,7 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx)
if (!xmit_skb)
net_info_ratelimited("%s: failed to clone multicast frame\n",
dev->name);
- } else {
+ } else if (!is_multicast_ether_addr(ehdr->h_dest)) {
dsta = sta_info_get(sdata, skb->data);
if (dsta) {
/*
@@ -2298,6 +2301,8 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx)
__le16 fc = hdr->frame_control;
struct sk_buff_head frame_list;
struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb);
+ struct ethhdr ethhdr;
+ const u8 *check_da = ethhdr.h_dest, *check_sa = ethhdr.h_source;
if (unlikely(!ieee80211_is_data(fc)))
return RX_CONTINUE;
@@ -2308,24 +2313,53 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx)
if (!(status->rx_flags & IEEE80211_RX_AMSDU))
return RX_CONTINUE;
- if (ieee80211_has_a4(hdr->frame_control) &&
- rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
- !rx->sdata->u.vlan.sta)
- return RX_DROP_UNUSABLE;
+ if (unlikely(ieee80211_has_a4(hdr->frame_control))) {
+ switch (rx->sdata->vif.type) {
+ case NL80211_IFTYPE_AP_VLAN:
+ if (!rx->sdata->u.vlan.sta)
+ return RX_DROP_UNUSABLE;
+ break;
+ case NL80211_IFTYPE_STATION:
+ if (!rx->sdata->u.mgd.use_4addr)
+ return RX_DROP_UNUSABLE;
+ break;
+ default:
+ return RX_DROP_UNUSABLE;
+ }
+ check_da = NULL;
+ check_sa = NULL;
+ } else switch (rx->sdata->vif.type) {
+ case NL80211_IFTYPE_AP:
+ case NL80211_IFTYPE_AP_VLAN:
+ check_da = NULL;
+ break;
+ case NL80211_IFTYPE_STATION:
+ if (!rx->sta ||
+ !test_sta_flag(rx->sta, WLAN_STA_TDLS_PEER))
+ check_sa = NULL;
+ break;
+ case NL80211_IFTYPE_MESH_POINT:
+ check_sa = NULL;
+ break;
+ default:
+ break;
+ }
- if (is_multicast_ether_addr(hdr->addr1) &&
- ((rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
- rx->sdata->u.vlan.sta) ||
- (rx->sdata->vif.type == NL80211_IFTYPE_STATION &&
- rx->sdata->u.mgd.use_4addr)))
+ if (is_multicast_ether_addr(hdr->addr1))
return RX_DROP_UNUSABLE;
skb->dev = dev;
__skb_queue_head_init(&frame_list);
+ if (ieee80211_data_to_8023_exthdr(skb, ðhdr,
+ rx->sdata->vif.addr,
+ rx->sdata->vif.type))
+ return RX_DROP_UNUSABLE;
+
ieee80211_amsdu_to_8023s(skb, &frame_list, dev->dev_addr,
rx->sdata->vif.type,
- rx->local->hw.extra_tx_headroom, true);
+ rx->local->hw.extra_tx_headroom,
+ check_da, check_sa);
while (!skb_queue_empty(&frame_list)) {
rx->skb = __skb_dequeue(&frame_list);
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 78e9ecb..236d47e 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -709,7 +709,7 @@ static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending)
for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
unsigned long tids;
- if (ignore_for_tim & BIT(ac))
+ if (ignore_for_tim & ieee80211_ac_to_qos_mask[ac])
continue;
indicate_tim |= !skb_queue_empty(&sta->tx_filtered[ac]) ||
@@ -1389,7 +1389,7 @@ ieee80211_sta_ps_more_data(struct sta_info *sta, u8 ignored_acs,
return true;
for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
- if (ignored_acs & BIT(ac))
+ if (ignored_acs & ieee80211_ac_to_qos_mask[ac])
continue;
if (!skb_queue_empty(&sta->tx_filtered[ac]) ||
@@ -1414,7 +1414,7 @@ ieee80211_sta_ps_get_frames(struct sta_info *sta, int n_frames, u8 ignored_acs,
for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
unsigned long tids;
- if (ignored_acs & BIT(ac))
+ if (ignored_acs & ieee80211_ac_to_qos_mask[ac])
continue;
tids = ieee80211_tids_for_ac(ac);
@@ -1482,7 +1482,7 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
BIT(find_highest_prio_tid(driver_release_tids));
if (skb_queue_empty(&frames) && !driver_release_tids) {
- int tid;
+ int tid, ac;
/*
* For PS-Poll, this can only happen due to a race condition
@@ -1500,7 +1500,10 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
*/
/* This will evaluate to 1, 3, 5 or 7. */
- tid = 7 - ((ffs(~ignored_acs) - 1) << 1);
+ for (ac = IEEE80211_AC_VO; ac < IEEE80211_NUM_ACS; ac++)
+ if (ignored_acs & BIT(ac))
+ continue;
+ tid = 7 - 2 * ac;
ieee80211_send_null_response(sta, tid, reason, true, false);
} else if (!driver_release_tids) {
@@ -1871,10 +1874,7 @@ int sta_info_move_state(struct sta_info *sta,
if (!sta->sta.support_p2p_ps)
ieee80211_recalc_p2p_go_ps_allowed(sta->sdata);
} else if (sta->sta_state == IEEE80211_STA_AUTHORIZED) {
- if (sta->sdata->vif.type == NL80211_IFTYPE_AP ||
- (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
- !sta->sdata->u.vlan.sta))
- atomic_dec(&sta->sdata->bss->num_mcast_sta);
+ ieee80211_vif_dec_num_mcast(sta->sdata);
clear_bit(WLAN_STA_AUTHORIZED, &sta->_flags);
ieee80211_clear_fast_xmit(sta);
ieee80211_clear_fast_rx(sta);
@@ -1882,10 +1882,7 @@ int sta_info_move_state(struct sta_info *sta,
break;
case IEEE80211_STA_AUTHORIZED:
if (sta->sta_state == IEEE80211_STA_ASSOC) {
- if (sta->sdata->vif.type == NL80211_IFTYPE_AP ||
- (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
- !sta->sdata->u.vlan.sta))
- atomic_inc(&sta->sdata->bss->num_mcast_sta);
+ ieee80211_vif_inc_num_mcast(sta->sdata);
set_bit(WLAN_STA_AUTHORIZED, &sta->_flags);
ieee80211_check_fast_xmit(sta);
ieee80211_check_fast_rx(sta);
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index ed5fcb9..dd06ef0 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -184,7 +184,6 @@ struct tid_ampdu_tx {
* @ssn: Starting Sequence Number expected to be aggregated.
* @buf_size: buffer size for incoming A-MPDUs
* @timeout: reset timer value (in TUs).
- * @dialog_token: dialog token for aggregation session
* @rcu_head: RCU head used for freeing this struct
* @reorder_lock: serializes access to reorder buffer, see below.
* @auto_seq: used for offloaded BA sessions to automatically pick head_seq_and
@@ -213,7 +212,6 @@ struct tid_ampdu_rx {
u16 ssn;
u16 buf_size;
u16 timeout;
- u8 dialog_token;
bool auto_seq;
bool removed;
};
@@ -225,6 +223,7 @@ struct tid_ampdu_rx {
* to tid_tx[idx], which are protected by the sta spinlock)
* tid_start_tx is also protected by sta->lock.
* @tid_rx: aggregation info for Rx per TID -- RCU protected
+ * @tid_rx_token: dialog tokens for valid aggregation sessions
* @tid_rx_timer_expired: bitmap indicating on which TIDs the
* RX timer expired until the work for it runs
* @tid_rx_stop_requested: bitmap indicating which BA sessions per TID the
@@ -243,6 +242,7 @@ struct sta_ampdu_mlme {
struct mutex mtx;
/* rx */
struct tid_ampdu_rx __rcu *tid_rx[IEEE80211_NUM_TIDS];
+ u8 tid_rx_token[IEEE80211_NUM_TIDS];
unsigned long tid_rx_timer_expired[BITS_TO_LONGS(IEEE80211_NUM_TIDS)];
unsigned long tid_rx_stop_requested[BITS_TO_LONGS(IEEE80211_NUM_TIDS)];
unsigned long agg_session_valid[BITS_TO_LONGS(IEEE80211_NUM_TIDS)];
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 1c56abc..62ccaf6 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -331,9 +331,8 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx)
I802_DEBUG_INC(tx->local->tx_handlers_drop_not_assoc);
return TX_DROP;
}
- } else if (unlikely(tx->sdata->vif.type == NL80211_IFTYPE_AP &&
- ieee80211_is_data(hdr->frame_control) &&
- !atomic_read(&tx->sdata->u.ap.num_mcast_sta))) {
+ } else if (unlikely(ieee80211_is_data(hdr->frame_control) &&
+ ieee80211_vif_get_num_mcast_if(tx->sdata) == 0)) {
/*
* No associated STAs - no need to send multicast
* frames.
@@ -935,7 +934,7 @@ ieee80211_tx_h_fragment(struct ieee80211_tx_data *tx)
if (info->flags & IEEE80211_TX_CTL_DONTFRAG)
return TX_CONTINUE;
- if (tx->local->ops->set_frag_threshold)
+ if (ieee80211_hw_check(&tx->local->hw, SUPPORTS_TX_FRAG))
return TX_CONTINUE;
/*
@@ -2801,7 +2800,7 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
/* fast-xmit doesn't handle fragmentation at all */
if (local->hw.wiphy->frag_threshold != (u32)-1 &&
- !local->ops->set_frag_threshold)
+ !ieee80211_hw_check(&local->hw, SUPPORTS_TX_FRAG))
goto out;
rcu_read_lock();
@@ -3060,11 +3059,12 @@ static bool ieee80211_amsdu_prepare_head(struct ieee80211_sub_if_data *sdata,
struct ieee80211_local *local = sdata->local;
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
struct ieee80211_hdr *hdr;
- struct ethhdr amsdu_hdr;
+ struct ethhdr *amsdu_hdr;
int hdr_len = fast_tx->hdr_len - sizeof(rfc1042_header);
int subframe_len = skb->len - hdr_len;
void *data;
- u8 *qc;
+ u8 *qc, *h_80211_src, *h_80211_dst;
+ const u8 *bssid;
if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE)
return false;
@@ -3072,19 +3072,44 @@ static bool ieee80211_amsdu_prepare_head(struct ieee80211_sub_if_data *sdata,
if (info->control.flags & IEEE80211_TX_CTRL_AMSDU)
return true;
- if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(amsdu_hdr),
+ if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(*amsdu_hdr),
&subframe_len))
return false;
- amsdu_hdr.h_proto = cpu_to_be16(subframe_len);
- memcpy(amsdu_hdr.h_source, skb->data + fast_tx->sa_offs, ETH_ALEN);
- memcpy(amsdu_hdr.h_dest, skb->data + fast_tx->da_offs, ETH_ALEN);
-
- data = skb_push(skb, sizeof(amsdu_hdr));
- memmove(data, data + sizeof(amsdu_hdr), hdr_len);
- memcpy(data + hdr_len, &amsdu_hdr, sizeof(amsdu_hdr));
-
+ data = skb_push(skb, sizeof(*amsdu_hdr));
+ memmove(data, data + sizeof(*amsdu_hdr), hdr_len);
hdr = data;
+ amsdu_hdr = data + hdr_len;
+ /* h_80211_src/dst is addr* field within hdr */
+ h_80211_src = data + fast_tx->sa_offs;
+ h_80211_dst = data + fast_tx->da_offs;
+
+ amsdu_hdr->h_proto = cpu_to_be16(subframe_len);
+ ether_addr_copy(amsdu_hdr->h_source, h_80211_src);
+ ether_addr_copy(amsdu_hdr->h_dest, h_80211_dst);
+
+ /* according to IEEE 802.11-2012 8.3.2 table 8-19, the outer SA/DA
+ * fields needs to be changed to BSSID for A-MSDU frames depending
+ * on FromDS/ToDS values.
+ */
+ switch (sdata->vif.type) {
+ case NL80211_IFTYPE_STATION:
+ bssid = sdata->u.mgd.bssid;
+ break;
+ case NL80211_IFTYPE_AP:
+ case NL80211_IFTYPE_AP_VLAN:
+ bssid = sdata->vif.addr;
+ break;
+ default:
+ bssid = NULL;
+ }
+
+ if (bssid && ieee80211_has_fromds(hdr->frame_control))
+ ether_addr_copy(h_80211_src, bssid);
+
+ if (bssid && ieee80211_has_tods(hdr->frame_control))
+ ether_addr_copy(h_80211_dst, bssid);
+
qc = ieee80211_get_qos_ctl(hdr);
*qc |= IEEE80211_QOS_CTL_A_MSDU_PRESENT;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 545c79a..ac59fbd 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -3308,10 +3308,11 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata,
struct ieee80211_local *local = sdata->local;
struct ieee80211_sub_if_data *sdata_iter;
enum nl80211_iftype iftype = sdata->wdev.iftype;
- int num[NUM_NL80211_IFTYPES];
struct ieee80211_chanctx *ctx;
- int num_different_channels = 0;
int total = 1;
+ struct iface_combination_params params = {
+ .radar_detect = radar_detect,
+ };
lockdep_assert_held(&local->chanctx_mtx);
@@ -3322,12 +3323,19 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata,
!chandef->chan))
return -EINVAL;
- if (chandef)
- num_different_channels = 1;
-
if (WARN_ON(iftype >= NUM_NL80211_IFTYPES))
return -EINVAL;
+ if (sdata->vif.type == NL80211_IFTYPE_AP ||
+ sdata->vif.type == NL80211_IFTYPE_MESH_POINT) {
+ /*
+ * always passing this is harmless, since it'll be the
+ * same value that cfg80211 finds if it finds the same
+ * interface ... and that's always allowed
+ */
+ params.new_beacon_int = sdata->vif.bss_conf.beacon_int;
+ }
+
/* Always allow software iftypes */
if (local->hw.wiphy->software_iftypes & BIT(iftype)) {
if (radar_detect)
@@ -3335,24 +3343,26 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata,
return 0;
}
- memset(num, 0, sizeof(num));
+ if (chandef)
+ params.num_different_channels = 1;
if (iftype != NL80211_IFTYPE_UNSPECIFIED)
- num[iftype] = 1;
+ params.iftype_num[iftype] = 1;
list_for_each_entry(ctx, &local->chanctx_list, list) {
if (ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED)
continue;
- radar_detect |= ieee80211_chanctx_radar_detect(local, ctx);
+ params.radar_detect |=
+ ieee80211_chanctx_radar_detect(local, ctx);
if (ctx->mode == IEEE80211_CHANCTX_EXCLUSIVE) {
- num_different_channels++;
+ params.num_different_channels++;
continue;
}
if (chandef && chanmode == IEEE80211_CHANCTX_SHARED &&
cfg80211_chandef_compatible(chandef,
&ctx->conf.def))
continue;
- num_different_channels++;
+ params.num_different_channels++;
}
list_for_each_entry_rcu(sdata_iter, &local->interfaces, list) {
@@ -3365,16 +3375,14 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata,
local->hw.wiphy->software_iftypes & BIT(wdev_iter->iftype))
continue;
- num[wdev_iter->iftype]++;
+ params.iftype_num[wdev_iter->iftype]++;
total++;
}
- if (total == 1 && !radar_detect)
+ if (total == 1 && !params.radar_detect)
return 0;
- return cfg80211_check_combinations(local->hw.wiphy,
- num_different_channels,
- radar_detect, num);
+ return cfg80211_check_combinations(local->hw.wiphy, ¶ms);
}
static void
@@ -3390,12 +3398,10 @@ ieee80211_iter_max_chans(const struct ieee80211_iface_combination *c,
int ieee80211_max_num_channels(struct ieee80211_local *local)
{
struct ieee80211_sub_if_data *sdata;
- int num[NUM_NL80211_IFTYPES] = {};
struct ieee80211_chanctx *ctx;
- int num_different_channels = 0;
- u8 radar_detect = 0;
u32 max_num_different_channels = 1;
int err;
+ struct iface_combination_params params = {0};
lockdep_assert_held(&local->chanctx_mtx);
@@ -3403,17 +3409,17 @@ int ieee80211_max_num_channels(struct ieee80211_local *local)
if (ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED)
continue;
- num_different_channels++;
+ params.num_different_channels++;
- radar_detect |= ieee80211_chanctx_radar_detect(local, ctx);
+ params.radar_detect |=
+ ieee80211_chanctx_radar_detect(local, ctx);
}
list_for_each_entry_rcu(sdata, &local->interfaces, list)
- num[sdata->wdev.iftype]++;
+ params.iftype_num[sdata->wdev.iftype]++;
- err = cfg80211_iter_combinations(local->hw.wiphy,
- num_different_channels, radar_detect,
- num, ieee80211_iter_max_chans,
+ err = cfg80211_iter_combinations(local->hw.wiphy, ¶ms,
+ ieee80211_iter_max_chans,
&max_num_different_channels);
if (err < 0)
return err;
@@ -3456,3 +3462,10 @@ void ieee80211_txq_get_depth(struct ieee80211_txq *txq,
*byte_cnt = txqi->tin.backlog_bytes + frag_bytes;
}
EXPORT_SYMBOL(ieee80211_txq_get_depth);
+
+const u8 ieee80211_ac_to_qos_mask[IEEE80211_NUM_ACS] = {
+ IEEE80211_WMM_IE_STA_QOSINFO_AC_VO,
+ IEEE80211_WMM_IE_STA_QOSINFO_AC_VI,
+ IEEE80211_WMM_IE_STA_QOSINFO_AC_BE,
+ IEEE80211_WMM_IE_STA_QOSINFO_AC_BK
+};
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index 9eb0aee..3e3d301 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -236,26 +236,35 @@ void ieee80211_set_qos_hdr(struct ieee80211_sub_if_data *sdata,
{
struct ieee80211_hdr *hdr = (void *)skb->data;
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+ u8 tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK;
+ u8 flags;
u8 *p;
- u8 ack_policy, tid;
if (!ieee80211_is_data_qos(hdr->frame_control))
return;
p = ieee80211_get_qos_ctl(hdr);
- tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK;
- /* preserve EOSP bit */
- ack_policy = *p & IEEE80211_QOS_CTL_EOSP;
+ /* set up the first byte */
+
+ /*
+ * preserve everything but the TID and ACK policy
+ * (which we both write here)
+ */
+ flags = *p & ~(IEEE80211_QOS_CTL_TID_MASK |
+ IEEE80211_QOS_CTL_ACK_POLICY_MASK);
if (is_multicast_ether_addr(hdr->addr1) ||
sdata->noack_map & BIT(tid)) {
- ack_policy |= IEEE80211_QOS_CTL_ACK_POLICY_NOACK;
+ flags |= IEEE80211_QOS_CTL_ACK_POLICY_NOACK;
info->flags |= IEEE80211_TX_CTL_NO_ACK;
}
- /* qos header is 2 bytes */
- *p++ = ack_policy | tid;
+ *p = flags | tid;
+
+ /* set up the second byte */
+ p++;
+
if (ieee80211_vif_is_mesh(&sdata->vif)) {
/* preserve RSPI and Mesh PS Level bit */
*p &= ((IEEE80211_QOS_CTL_RSPI |
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index b48c1e1..8af6dd3 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -57,7 +57,7 @@ ieee80211_tx_h_michael_mic_add(struct ieee80211_tx_data *tx)
if (info->control.hw_key &&
(info->flags & IEEE80211_TX_CTL_DONTFRAG ||
- tx->local->ops->set_frag_threshold) &&
+ ieee80211_hw_check(&tx->local->hw, SUPPORTS_TX_FRAG)) &&
!(tx->key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC)) {
/* hwaccel - with no need for SW-generated MMIC */
return TX_CONTINUE;
@@ -405,7 +405,7 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb,
u8 *pos;
u8 pn[6];
u64 pn64;
- u8 aad[2 * AES_BLOCK_SIZE];
+ u8 aad[CCM_AAD_LEN];
u8 b_0[AES_BLOCK_SIZE];
if (info->control.hw_key &&
@@ -461,10 +461,8 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb,
pos += IEEE80211_CCMP_HDR_LEN;
ccmp_special_blocks(skb, pn, b_0, aad);
- ieee80211_aes_ccm_encrypt(key->u.ccmp.tfm, b_0, aad, pos, len,
- skb_put(skb, mic_len), mic_len);
-
- return 0;
+ return ieee80211_aes_ccm_encrypt(key->u.ccmp.tfm, b_0, aad, pos, len,
+ skb_put(skb, mic_len), mic_len);
}
@@ -639,7 +637,7 @@ static int gcmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb)
u8 *pos;
u8 pn[6];
u64 pn64;
- u8 aad[2 * AES_BLOCK_SIZE];
+ u8 aad[GCM_AAD_LEN];
u8 j_0[AES_BLOCK_SIZE];
if (info->control.hw_key &&
@@ -696,10 +694,8 @@ static int gcmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb)
pos += IEEE80211_GCMP_HDR_LEN;
gcmp_special_blocks(skb, pn, j_0, aad);
- ieee80211_aes_gcm_encrypt(key->u.gcmp.tfm, j_0, aad, pos, len,
- skb_put(skb, IEEE80211_GCMP_MIC_LEN));
-
- return 0;
+ return ieee80211_aes_gcm_encrypt(key->u.gcmp.tfm, j_0, aad, pos, len,
+ skb_put(skb, IEEE80211_GCMP_MIC_LEN));
}
ieee80211_tx_result
@@ -1123,9 +1119,9 @@ ieee80211_crypto_aes_gmac_encrypt(struct ieee80211_tx_data *tx)
struct ieee80211_key *key = tx->key;
struct ieee80211_mmie_16 *mmie;
struct ieee80211_hdr *hdr;
- u8 aad[20];
+ u8 aad[GMAC_AAD_LEN];
u64 pn64;
- u8 nonce[12];
+ u8 nonce[GMAC_NONCE_LEN];
if (WARN_ON(skb_queue_len(&tx->skbs) != 1))
return TX_DROP;
@@ -1171,7 +1167,7 @@ ieee80211_crypto_aes_gmac_decrypt(struct ieee80211_rx_data *rx)
struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
struct ieee80211_key *key = rx->key;
struct ieee80211_mmie_16 *mmie;
- u8 aad[20], mic[16], ipn[6], nonce[12];
+ u8 aad[GMAC_AAD_LEN], mic[GMAC_MIC_LEN], ipn[6], nonce[GMAC_NONCE_LEN];
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
if (!ieee80211_is_mgmt(hdr->frame_control))
diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index 13290a7..1308a56 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -246,6 +246,7 @@ enum {
ncsi_dev_state_config_gls,
ncsi_dev_state_config_done,
ncsi_dev_state_suspend_select = 0x0401,
+ ncsi_dev_state_suspend_gls,
ncsi_dev_state_suspend_dcnt,
ncsi_dev_state_suspend_dc,
ncsi_dev_state_suspend_deselect,
@@ -264,6 +265,7 @@ struct ncsi_dev_priv {
#endif
unsigned int package_num; /* Number of packages */
struct list_head packages; /* List of packages */
+ struct ncsi_channel *hot_channel; /* Channel was ever active */
struct ncsi_request requests[256]; /* Request table */
unsigned int request_id; /* Last used request ID */
#define NCSI_REQ_START_IDX 1
diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c
index b41a661..6898e72 100644
--- a/net/ncsi/ncsi-aen.c
+++ b/net/ncsi/ncsi-aen.c
@@ -141,23 +141,35 @@ static int ncsi_aen_handler_hncdsc(struct ncsi_dev_priv *ndp,
return -ENODEV;
/* If the channel is active one, we need reconfigure it */
+ spin_lock_irqsave(&nc->lock, flags);
ncm = &nc->modes[NCSI_MODE_LINK];
hncdsc = (struct ncsi_aen_hncdsc_pkt *)h;
ncm->data[3] = ntohl(hncdsc->status);
if (!list_empty(&nc->link) ||
- nc->state != NCSI_CHANNEL_ACTIVE ||
- (ncm->data[3] & 0x1))
+ nc->state != NCSI_CHANNEL_ACTIVE) {
+ spin_unlock_irqrestore(&nc->lock, flags);
return 0;
+ }
- if (ndp->flags & NCSI_DEV_HWA)
+ spin_unlock_irqrestore(&nc->lock, flags);
+ if (!(ndp->flags & NCSI_DEV_HWA) && !(ncm->data[3] & 0x1))
ndp->flags |= NCSI_DEV_RESHUFFLE;
/* If this channel is the active one and the link doesn't
* work, we have to choose another channel to be active one.
* The logic here is exactly similar to what we do when link
* is down on the active channel.
+ *
+ * On the other hand, we need configure it when host driver
+ * state on the active channel becomes ready.
*/
ncsi_stop_channel_monitor(nc);
+
+ spin_lock_irqsave(&nc->lock, flags);
+ nc->state = (ncm->data[3] & 0x1) ? NCSI_CHANNEL_INACTIVE :
+ NCSI_CHANNEL_ACTIVE;
+ spin_unlock_irqrestore(&nc->lock, flags);
+
spin_lock_irqsave(&ndp->lock, flags);
list_add_tail_rcu(&nc->link, &ndp->channel_queue);
spin_unlock_irqrestore(&ndp->lock, flags);
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index 5e509e5..a3bd5fa 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -540,42 +540,86 @@ static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp)
nd->state = ncsi_dev_state_suspend_select;
/* Fall through */
case ncsi_dev_state_suspend_select:
+ ndp->pending_req_num = 1;
+
+ nca.type = NCSI_PKT_CMD_SP;
+ nca.package = np->id;
+ nca.channel = NCSI_RESERVED_CHANNEL;
+ if (ndp->flags & NCSI_DEV_HWA)
+ nca.bytes[0] = 0;
+ else
+ nca.bytes[0] = 1;
+
+ /* To retrieve the last link states of channels in current
+ * package when current active channel needs fail over to
+ * another one. It means we will possibly select another
+ * channel as next active one. The link states of channels
+ * are most important factor of the selection. So we need
+ * accurate link states. Unfortunately, the link states on
+ * inactive channels can't be updated with LSC AEN in time.
+ */
+ if (ndp->flags & NCSI_DEV_RESHUFFLE)
+ nd->state = ncsi_dev_state_suspend_gls;
+ else
+ nd->state = ncsi_dev_state_suspend_dcnt;
+ ret = ncsi_xmit_cmd(&nca);
+ if (ret)
+ goto error;
+
+ break;
+ case ncsi_dev_state_suspend_gls:
+ ndp->pending_req_num = np->channel_num;
+
+ nca.type = NCSI_PKT_CMD_GLS;
+ nca.package = np->id;
+
+ nd->state = ncsi_dev_state_suspend_dcnt;
+ NCSI_FOR_EACH_CHANNEL(np, nc) {
+ nca.channel = nc->id;
+ ret = ncsi_xmit_cmd(&nca);
+ if (ret)
+ goto error;
+ }
+
+ break;
case ncsi_dev_state_suspend_dcnt:
+ ndp->pending_req_num = 1;
+
+ nca.type = NCSI_PKT_CMD_DCNT;
+ nca.package = np->id;
+ nca.channel = nc->id;
+
+ nd->state = ncsi_dev_state_suspend_dc;
+ ret = ncsi_xmit_cmd(&nca);
+ if (ret)
+ goto error;
+
+ break;
case ncsi_dev_state_suspend_dc:
+ ndp->pending_req_num = 1;
+
+ nca.type = NCSI_PKT_CMD_DC;
+ nca.package = np->id;
+ nca.channel = nc->id;
+ nca.bytes[0] = 1;
+
+ nd->state = ncsi_dev_state_suspend_deselect;
+ ret = ncsi_xmit_cmd(&nca);
+ if (ret)
+ goto error;
+
+ break;
case ncsi_dev_state_suspend_deselect:
ndp->pending_req_num = 1;
- np = ndp->active_package;
- nc = ndp->active_channel;
+ nca.type = NCSI_PKT_CMD_DP;
nca.package = np->id;
- if (nd->state == ncsi_dev_state_suspend_select) {
- nca.type = NCSI_PKT_CMD_SP;
- nca.channel = NCSI_RESERVED_CHANNEL;
- if (ndp->flags & NCSI_DEV_HWA)
- nca.bytes[0] = 0;
- else
- nca.bytes[0] = 1;
- nd->state = ncsi_dev_state_suspend_dcnt;
- } else if (nd->state == ncsi_dev_state_suspend_dcnt) {
- nca.type = NCSI_PKT_CMD_DCNT;
- nca.channel = nc->id;
- nd->state = ncsi_dev_state_suspend_dc;
- } else if (nd->state == ncsi_dev_state_suspend_dc) {
- nca.type = NCSI_PKT_CMD_DC;
- nca.channel = nc->id;
- nca.bytes[0] = 1;
- nd->state = ncsi_dev_state_suspend_deselect;
- } else if (nd->state == ncsi_dev_state_suspend_deselect) {
- nca.type = NCSI_PKT_CMD_DP;
- nca.channel = NCSI_RESERVED_CHANNEL;
- nd->state = ncsi_dev_state_suspend_done;
- }
+ nca.channel = NCSI_RESERVED_CHANNEL;
+ nd->state = ncsi_dev_state_suspend_done;
ret = ncsi_xmit_cmd(&nca);
- if (ret) {
- nd->state = ncsi_dev_state_functional;
- return;
- }
+ if (ret)
+ goto error;
break;
case ncsi_dev_state_suspend_done:
@@ -589,6 +633,10 @@ static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp)
netdev_warn(nd->dev, "Wrong NCSI state 0x%x in suspend\n",
nd->state);
}
+
+ return;
+error:
+ nd->state = ncsi_dev_state_functional;
}
static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
@@ -597,6 +645,7 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
struct net_device *dev = nd->dev;
struct ncsi_package *np = ndp->active_package;
struct ncsi_channel *nc = ndp->active_channel;
+ struct ncsi_channel *hot_nc = NULL;
struct ncsi_cmd_arg nca;
unsigned char index;
unsigned long flags;
@@ -702,12 +751,20 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
break;
case ncsi_dev_state_config_done:
spin_lock_irqsave(&nc->lock, flags);
- if (nc->modes[NCSI_MODE_LINK].data[2] & 0x1)
+ if (nc->modes[NCSI_MODE_LINK].data[2] & 0x1) {
+ hot_nc = nc;
nc->state = NCSI_CHANNEL_ACTIVE;
- else
+ } else {
+ hot_nc = NULL;
nc->state = NCSI_CHANNEL_INACTIVE;
+ }
spin_unlock_irqrestore(&nc->lock, flags);
+ /* Update the hot channel */
+ spin_lock_irqsave(&ndp->lock, flags);
+ ndp->hot_channel = hot_nc;
+ spin_unlock_irqrestore(&ndp->lock, flags);
+
ncsi_start_channel_monitor(nc);
ncsi_process_next_channel(ndp);
break;
@@ -725,10 +782,14 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
static int ncsi_choose_active_channel(struct ncsi_dev_priv *ndp)
{
struct ncsi_package *np;
- struct ncsi_channel *nc, *found;
+ struct ncsi_channel *nc, *found, *hot_nc;
struct ncsi_channel_mode *ncm;
unsigned long flags;
+ spin_lock_irqsave(&ndp->lock, flags);
+ hot_nc = ndp->hot_channel;
+ spin_unlock_irqrestore(&ndp->lock, flags);
+
/* The search is done once an inactive channel with up
* link is found.
*/
@@ -746,6 +807,9 @@ static int ncsi_choose_active_channel(struct ncsi_dev_priv *ndp)
if (!found)
found = nc;
+ if (nc == hot_nc)
+ found = nc;
+
ncm = &nc->modes[NCSI_MODE_LINK];
if (ncm->data[2] & 0x1) {
spin_unlock_irqrestore(&nc->lock, flags);
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index e8d56d9..44410d3 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -57,6 +57,10 @@
config NF_LOG_COMMON
tristate
+config NF_LOG_NETDEV
+ tristate "Netdev packet logging"
+ select NF_LOG_COMMON
+
if NF_CONNTRACK
config NF_CONNTRACK_MARK
@@ -474,6 +478,12 @@
This option adds the "meta" expression that you can use to match and
to set packet metainformation such as the packet mark.
+config NFT_RT
+ tristate "Netfilter nf_tables routing module"
+ help
+ This option adds the "rt" expression that you can use to match
+ packet routing information such as the packet nexthop.
+
config NFT_NUMGEN
tristate "Netfilter nf_tables number generator module"
help
@@ -581,6 +591,19 @@
This option adds the "hash" expression that you can use to perform
a hash operation on registers.
+config NFT_FIB
+ tristate
+
+config NFT_FIB_INET
+ depends on NF_TABLES_INET
+ depends on NFT_FIB_IPV4
+ depends on NFT_FIB_IPV6
+ tristate "Netfilter nf_tables fib inet support"
+ help
+ This option allows using the FIB expression from the inet table.
+ The lookup will be delegated to the IPv4 or IPv6 FIB depending
+ on the protocol of the packet.
+
if NF_TABLES_NETDEV
config NF_DUP_NETDEV
@@ -1409,9 +1432,10 @@
tristate '"socket" match support'
depends on NETFILTER_XTABLES
depends on NETFILTER_ADVANCED
- depends on !NF_CONNTRACK || NF_CONNTRACK
depends on IPV6 || IPV6=n
depends on IP6_NF_IPTABLES || IP6_NF_IPTABLES=n
+ depends on NF_SOCKET_IPV4
+ depends on NF_SOCKET_IPV6
select NF_DEFRAG_IPV4
select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES != n
help
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index c23c3c8..5bbf767 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -48,6 +48,9 @@
# generic transport layer logging
obj-$(CONFIG_NF_LOG_COMMON) += nf_log_common.o
+# packet logging for netdev family
+obj-$(CONFIG_NF_LOG_NETDEV) += nf_log_netdev.o
+
obj-$(CONFIG_NF_NAT) += nf_nat.o
obj-$(CONFIG_NF_NAT_REDIRECT) += nf_nat_redirect.o
@@ -81,6 +84,7 @@
obj-$(CONFIG_NFT_COMPAT) += nft_compat.o
obj-$(CONFIG_NFT_EXTHDR) += nft_exthdr.o
obj-$(CONFIG_NFT_META) += nft_meta.o
+obj-$(CONFIG_NFT_RT) += nft_rt.o
obj-$(CONFIG_NFT_NUMGEN) += nft_numgen.o
obj-$(CONFIG_NFT_CT) += nft_ct.o
obj-$(CONFIG_NFT_LIMIT) += nft_limit.o
@@ -96,6 +100,8 @@
obj-$(CONFIG_NFT_MASQ) += nft_masq.o
obj-$(CONFIG_NFT_REDIR) += nft_redir.o
obj-$(CONFIG_NFT_HASH) += nft_hash.o
+obj-$(CONFIG_NFT_FIB) += nft_fib.o
+obj-$(CONFIG_NFT_FIB_INET) += nft_fib_inet.o
# nf_tables netdev
obj-$(CONFIG_NFT_DUP_NETDEV) += nft_dup_netdev.o
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index fcb5d1d..de30e08 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -302,77 +302,40 @@ void _nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n)
}
EXPORT_SYMBOL(_nf_unregister_hooks);
-unsigned int nf_iterate(struct sk_buff *skb,
- struct nf_hook_state *state,
- struct nf_hook_entry **entryp)
-{
- unsigned int verdict;
-
- /*
- * The caller must not block between calls to this
- * function because of risk of continuing from deleted element.
- */
- while (*entryp) {
- if (state->thresh > (*entryp)->ops.priority) {
- *entryp = rcu_dereference((*entryp)->next);
- continue;
- }
-
- /* Optimization: we don't need to hold module
- reference here, since function can't sleep. --RR */
-repeat:
- verdict = (*entryp)->ops.hook((*entryp)->ops.priv, skb, state);
- if (verdict != NF_ACCEPT) {
-#ifdef CONFIG_NETFILTER_DEBUG
- if (unlikely((verdict & NF_VERDICT_MASK)
- > NF_MAX_VERDICT)) {
- NFDEBUG("Evil return from %p(%u).\n",
- (*entryp)->ops.hook, state->hook);
- *entryp = rcu_dereference((*entryp)->next);
- continue;
- }
-#endif
- if (verdict != NF_REPEAT)
- return verdict;
- goto repeat;
- }
- *entryp = rcu_dereference((*entryp)->next);
- }
- return NF_ACCEPT;
-}
-
-
/* Returns 1 if okfn() needs to be executed by the caller,
* -EPERM for NF_DROP, 0 otherwise. Caller must hold rcu_read_lock. */
-int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state)
+int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state,
+ struct nf_hook_entry *entry)
{
- struct nf_hook_entry *entry;
unsigned int verdict;
- int ret = 0;
+ int ret;
- entry = rcu_dereference(state->hook_entries);
-next_hook:
- verdict = nf_iterate(skb, state, &entry);
- if (verdict == NF_ACCEPT || verdict == NF_STOP) {
- ret = 1;
- } else if ((verdict & NF_VERDICT_MASK) == NF_DROP) {
- kfree_skb(skb);
- ret = NF_DROP_GETERR(verdict);
- if (ret == 0)
- ret = -EPERM;
- } else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) {
- int err;
-
- RCU_INIT_POINTER(state->hook_entries, entry);
- err = nf_queue(skb, state, verdict >> NF_VERDICT_QBITS);
- if (err < 0) {
- if (err == -ESRCH &&
- (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
- goto next_hook;
+ do {
+ verdict = entry->ops.hook(entry->ops.priv, skb, state);
+ switch (verdict & NF_VERDICT_MASK) {
+ case NF_ACCEPT:
+ entry = rcu_dereference(entry->next);
+ break;
+ case NF_DROP:
kfree_skb(skb);
+ ret = NF_DROP_GETERR(verdict);
+ if (ret == 0)
+ ret = -EPERM;
+ return ret;
+ case NF_QUEUE:
+ ret = nf_queue(skb, state, &entry, verdict);
+ if (ret == 1 && entry)
+ continue;
+ return ret;
+ default:
+ /* Implicit handling for NF_STOLEN, as well as any other
+ * non conventional verdicts.
+ */
+ return 0;
}
- }
- return ret;
+ } while (entry);
+
+ return 1;
}
EXPORT_SYMBOL(nf_hook_slow);
diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig
index 234a8ec..4083a80 100644
--- a/net/netfilter/ipset/Kconfig
+++ b/net/netfilter/ipset/Kconfig
@@ -99,6 +99,15 @@
To compile it as a module, choose M here. If unsure, say N.
+config IP_SET_HASH_IPMAC
+ tristate "hash:ip,mac set support"
+ depends on IP_SET
+ help
+ This option adds the hash:ip,mac set type support, by which
+ one can store IPv4/IPv6 address and MAC (ethernet address) pairs in a set.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config IP_SET_HASH_MAC
tristate "hash:mac set support"
depends on IP_SET
diff --git a/net/netfilter/ipset/Makefile b/net/netfilter/ipset/Makefile
index 3dbd5e9..28ec148 100644
--- a/net/netfilter/ipset/Makefile
+++ b/net/netfilter/ipset/Makefile
@@ -14,6 +14,7 @@
# hash types
obj-$(CONFIG_IP_SET_HASH_IP) += ip_set_hash_ip.o
+obj-$(CONFIG_IP_SET_HASH_IPMAC) += ip_set_hash_ipmac.o
obj-$(CONFIG_IP_SET_HASH_IPMARK) += ip_set_hash_ipmark.o
obj-$(CONFIG_IP_SET_HASH_IPPORT) += ip_set_hash_ipport.o
obj-$(CONFIG_IP_SET_HASH_IPPORTIP) += ip_set_hash_ipportip.o
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 2e8e7e5..6f09a99 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -22,6 +22,7 @@
#define mtype_kadt IPSET_TOKEN(MTYPE, _kadt)
#define mtype_uadt IPSET_TOKEN(MTYPE, _uadt)
#define mtype_destroy IPSET_TOKEN(MTYPE, _destroy)
+#define mtype_memsize IPSET_TOKEN(MTYPE, _memsize)
#define mtype_flush IPSET_TOKEN(MTYPE, _flush)
#define mtype_head IPSET_TOKEN(MTYPE, _head)
#define mtype_same_set IPSET_TOKEN(MTYPE, _same_set)
@@ -40,11 +41,8 @@ mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
{
struct mtype *map = set->data;
- init_timer(&map->gc);
- map->gc.data = (unsigned long)set;
- map->gc.function = gc;
- map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
- add_timer(&map->gc);
+ setup_timer(&map->gc, gc, (unsigned long)set);
+ mod_timer(&map->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ);
}
static void
@@ -82,6 +80,16 @@ mtype_flush(struct ip_set *set)
if (set->extensions & IPSET_EXT_DESTROY)
mtype_ext_cleanup(set);
memset(map->members, 0, map->memsize);
+ set->elements = 0;
+ set->ext_size = 0;
+}
+
+/* Calculate the actual memory size of the set data */
+static size_t
+mtype_memsize(const struct mtype *map, size_t dsize)
+{
+ return sizeof(*map) + map->memsize +
+ map->elements * dsize;
}
static int
@@ -89,14 +97,15 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
{
const struct mtype *map = set->data;
struct nlattr *nested;
- size_t memsize = sizeof(*map) + map->memsize;
+ size_t memsize = mtype_memsize(map, set->dsize) + set->ext_size;
nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
if (!nested)
goto nla_put_failure;
if (mtype_do_head(skb, map) ||
nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) ||
- nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)))
+ nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) ||
+ nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(set->elements)))
goto nla_put_failure;
if (unlikely(ip_set_put_flags(skb, set)))
goto nla_put_failure;
@@ -140,6 +149,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
if (ret == IPSET_ADD_FAILED) {
if (SET_WITH_TIMEOUT(set) &&
ip_set_timeout_expired(ext_timeout(x, set))) {
+ set->elements--;
ret = 0;
} else if (!(flags & IPSET_FLAG_EXIST)) {
set_bit(e->id, map->members);
@@ -148,6 +158,8 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
/* Element is re-added, cleanup extensions */
ip_set_ext_destroy(set, x);
}
+ if (ret > 0)
+ set->elements--;
if (SET_WITH_TIMEOUT(set))
#ifdef IP_SET_BITMAP_STORED_TIMEOUT
@@ -159,12 +171,13 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
if (SET_WITH_COUNTER(set))
ip_set_init_counter(ext_counter(x, set), ext);
if (SET_WITH_COMMENT(set))
- ip_set_init_comment(ext_comment(x, set), ext);
+ ip_set_init_comment(set, ext_comment(x, set), ext);
if (SET_WITH_SKBINFO(set))
ip_set_init_skbinfo(ext_skbinfo(x, set), ext);
/* Activate element */
set_bit(e->id, map->members);
+ set->elements++;
return 0;
}
@@ -181,6 +194,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
return -IPSET_ERR_EXIST;
ip_set_ext_destroy(set, x);
+ set->elements--;
if (SET_WITH_TIMEOUT(set) &&
ip_set_timeout_expired(ext_timeout(x, set)))
return -IPSET_ERR_EXIST;
@@ -276,6 +290,7 @@ mtype_gc(unsigned long ul_set)
if (ip_set_timeout_expired(ext_timeout(x, set))) {
clear_bit(id, map->members);
ip_set_ext_destroy(set, x);
+ set->elements--;
}
}
spin_unlock_bh(&set->lock);
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index a748b0c..c296f9b 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -36,7 +36,7 @@ struct ip_set_net {
bool is_destroyed; /* all sets are destroyed */
};
-static int ip_set_net_id __read_mostly;
+static unsigned int ip_set_net_id __read_mostly;
static inline struct ip_set_net *ip_set_pernet(struct net *net)
{
@@ -324,7 +324,7 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr)
}
EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6);
-typedef void (*destroyer)(void *);
+typedef void (*destroyer)(struct ip_set *, void *);
/* ipset data extension types, in size order */
const struct ip_set_ext_type ip_set_extensions[] = {
@@ -426,20 +426,20 @@ ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[],
if (!SET_WITH_SKBINFO(set))
return -IPSET_ERR_SKBINFO;
fullmark = be64_to_cpu(nla_get_be64(tb[IPSET_ATTR_SKBMARK]));
- ext->skbmark = fullmark >> 32;
- ext->skbmarkmask = fullmark & 0xffffffff;
+ ext->skbinfo.skbmark = fullmark >> 32;
+ ext->skbinfo.skbmarkmask = fullmark & 0xffffffff;
}
if (tb[IPSET_ATTR_SKBPRIO]) {
if (!SET_WITH_SKBINFO(set))
return -IPSET_ERR_SKBINFO;
- ext->skbprio = be32_to_cpu(nla_get_be32(
- tb[IPSET_ATTR_SKBPRIO]));
+ ext->skbinfo.skbprio =
+ be32_to_cpu(nla_get_be32(tb[IPSET_ATTR_SKBPRIO]));
}
if (tb[IPSET_ATTR_SKBQUEUE]) {
if (!SET_WITH_SKBINFO(set))
return -IPSET_ERR_SKBINFO;
- ext->skbqueue = be16_to_cpu(nla_get_be16(
- tb[IPSET_ATTR_SKBQUEUE]));
+ ext->skbinfo.skbqueue =
+ be16_to_cpu(nla_get_be16(tb[IPSET_ATTR_SKBQUEUE]));
}
return 0;
}
@@ -541,7 +541,7 @@ int
ip_set_test(ip_set_id_t index, const struct sk_buff *skb,
const struct xt_action_param *par, struct ip_set_adt_opt *opt)
{
- struct ip_set *set = ip_set_rcu_get(par->net, index);
+ struct ip_set *set = ip_set_rcu_get(xt_net(par), index);
int ret = 0;
BUG_ON(!set);
@@ -579,7 +579,7 @@ int
ip_set_add(ip_set_id_t index, const struct sk_buff *skb,
const struct xt_action_param *par, struct ip_set_adt_opt *opt)
{
- struct ip_set *set = ip_set_rcu_get(par->net, index);
+ struct ip_set *set = ip_set_rcu_get(xt_net(par), index);
int ret;
BUG_ON(!set);
@@ -601,7 +601,7 @@ int
ip_set_del(ip_set_id_t index, const struct sk_buff *skb,
const struct xt_action_param *par, struct ip_set_adt_opt *opt)
{
- struct ip_set *set = ip_set_rcu_get(par->net, index);
+ struct ip_set *set = ip_set_rcu_get(xt_net(par), index);
int ret = 0;
BUG_ON(!set);
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index d32fd6b..1b05d4a 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -85,6 +85,8 @@ struct htable {
};
#define hbucket(h, i) ((h)->bucket[i])
+#define ext_size(n, dsize) \
+ (sizeof(struct hbucket) + (n) * (dsize))
#ifndef IPSET_NET_COUNT
#define IPSET_NET_COUNT 1
@@ -150,24 +152,34 @@ htable_bits(u32 hashsize)
#define INIT_CIDR(cidr, host_mask) \
DCIDR_PUT(((cidr) ? NCIDR_GET(cidr) : host_mask))
-#define SET_HOST_MASK(family) (family == AF_INET ? 32 : 128)
-
#ifdef IP_SET_HASH_WITH_NET0
-/* cidr from 0 to SET_HOST_MASK() value and c = cidr + 1 */
-#define NLEN(family) (SET_HOST_MASK(family) + 1)
+/* cidr from 0 to HOST_MASK value and c = cidr + 1 */
+#define NLEN (HOST_MASK + 1)
#define CIDR_POS(c) ((c) - 1)
#else
-/* cidr from 1 to SET_HOST_MASK() value and c = cidr + 1 */
-#define NLEN(family) SET_HOST_MASK(family)
+/* cidr from 1 to HOST_MASK value and c = cidr + 1 */
+#define NLEN HOST_MASK
#define CIDR_POS(c) ((c) - 2)
#endif
#else
-#define NLEN(family) 0
+#define NLEN 0
#endif /* IP_SET_HASH_WITH_NETS */
#endif /* _IP_SET_HASH_GEN_H */
+#ifndef MTYPE
+#error "MTYPE is not defined!"
+#endif
+
+#ifndef HTYPE
+#error "HTYPE is not defined!"
+#endif
+
+#ifndef HOST_MASK
+#error "HOST_MASK is not defined!"
+#endif
+
/* Family dependent templates */
#undef ahash_data
@@ -191,7 +203,6 @@ htable_bits(u32 hashsize)
#undef mtype_same_set
#undef mtype_kadt
#undef mtype_uadt
-#undef mtype
#undef mtype_add
#undef mtype_del
@@ -207,6 +218,7 @@ htable_bits(u32 hashsize)
#undef mtype_variant
#undef mtype_data_match
+#undef htype
#undef HKEY
#define mtype_data_equal IPSET_TOKEN(MTYPE, _data_equal)
@@ -233,7 +245,6 @@ htable_bits(u32 hashsize)
#define mtype_same_set IPSET_TOKEN(MTYPE, _same_set)
#define mtype_kadt IPSET_TOKEN(MTYPE, _kadt)
#define mtype_uadt IPSET_TOKEN(MTYPE, _uadt)
-#define mtype MTYPE
#define mtype_add IPSET_TOKEN(MTYPE, _add)
#define mtype_del IPSET_TOKEN(MTYPE, _del)
@@ -249,62 +260,54 @@ htable_bits(u32 hashsize)
#define mtype_variant IPSET_TOKEN(MTYPE, _variant)
#define mtype_data_match IPSET_TOKEN(MTYPE, _data_match)
-#ifndef MTYPE
-#error "MTYPE is not defined!"
-#endif
-
-#ifndef HOST_MASK
-#error "HOST_MASK is not defined!"
-#endif
-
#ifndef HKEY_DATALEN
#define HKEY_DATALEN sizeof(struct mtype_elem)
#endif
-#define HKEY(data, initval, htable_bits) \
-(jhash2((u32 *)(data), HKEY_DATALEN / sizeof(u32), initval) \
- & jhash_mask(htable_bits))
+#define htype MTYPE
-#ifndef htype
-#ifndef HTYPE
-#error "HTYPE is not defined!"
-#endif /* HTYPE */
-#define htype HTYPE
+#define HKEY(data, initval, htable_bits) \
+({ \
+ const u32 *__k = (const u32 *)data; \
+ u32 __l = HKEY_DATALEN / sizeof(u32); \
+ \
+ BUILD_BUG_ON(HKEY_DATALEN % sizeof(u32) != 0); \
+ \
+ jhash2(__k, __l, initval) & jhash_mask(htable_bits); \
+})
/* The generic hash structure */
struct htype {
struct htable __rcu *table; /* the hash table */
+ struct timer_list gc; /* garbage collection when timeout enabled */
u32 maxelem; /* max elements in the hash */
- u32 elements; /* current element (vs timeout) */
u32 initval; /* random jhash init value */
#ifdef IP_SET_HASH_WITH_MARKMASK
u32 markmask; /* markmask value for mark mask to store */
#endif
- struct timer_list gc; /* garbage collection when timeout enabled */
- struct mtype_elem next; /* temporary storage for uadd */
#ifdef IP_SET_HASH_WITH_MULTI
u8 ahash_max; /* max elements in an array block */
#endif
#ifdef IP_SET_HASH_WITH_NETMASK
u8 netmask; /* netmask value for subnets to store */
#endif
+ struct mtype_elem next; /* temporary storage for uadd */
#ifdef IP_SET_HASH_WITH_NETS
- struct net_prefixes nets[0]; /* book-keeping of prefixes */
+ struct net_prefixes nets[NLEN]; /* book-keeping of prefixes */
#endif
};
-#endif /* htype */
#ifdef IP_SET_HASH_WITH_NETS
/* Network cidr size book keeping when the hash stores different
* sized networks. cidr == real cidr + 1 to support /0.
*/
static void
-mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
+mtype_add_cidr(struct htype *h, u8 cidr, u8 n)
{
int i, j;
/* Add in increasing prefix order, so larger cidr first */
- for (i = 0, j = -1; i < nets_length && h->nets[i].cidr[n]; i++) {
+ for (i = 0, j = -1; i < NLEN && h->nets[i].cidr[n]; i++) {
if (j != -1) {
continue;
} else if (h->nets[i].cidr[n] < cidr) {
@@ -323,11 +326,11 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
}
static void
-mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
+mtype_del_cidr(struct htype *h, u8 cidr, u8 n)
{
- u8 i, j, net_end = nets_length - 1;
+ u8 i, j, net_end = NLEN - 1;
- for (i = 0; i < nets_length; i++) {
+ for (i = 0; i < NLEN; i++) {
if (h->nets[i].cidr[n] != cidr)
continue;
h->nets[CIDR_POS(cidr)].nets[n]--;
@@ -343,24 +346,9 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
/* Calculate the actual memory size of the set data */
static size_t
-mtype_ahash_memsize(const struct htype *h, const struct htable *t,
- u8 nets_length, size_t dsize)
+mtype_ahash_memsize(const struct htype *h, const struct htable *t)
{
- u32 i;
- struct hbucket *n;
- size_t memsize = sizeof(*h) + sizeof(*t);
-
-#ifdef IP_SET_HASH_WITH_NETS
- memsize += sizeof(struct net_prefixes) * nets_length;
-#endif
- for (i = 0; i < jhash_size(t->htable_bits); i++) {
- n = rcu_dereference_bh(hbucket(t, i));
- if (!n)
- continue;
- memsize += sizeof(struct hbucket) + n->size * dsize;
- }
-
- return memsize;
+ return sizeof(*h) + sizeof(*t);
}
/* Get the ith element from the array block n */
@@ -398,9 +386,10 @@ mtype_flush(struct ip_set *set)
kfree_rcu(n, rcu);
}
#ifdef IP_SET_HASH_WITH_NETS
- memset(h->nets, 0, sizeof(struct net_prefixes) * NLEN(set->family));
+ memset(h->nets, 0, sizeof(h->nets));
#endif
- h->elements = 0;
+ set->elements = 0;
+ set->ext_size = 0;
}
/* Destroy the hashtable part of the set */
@@ -444,11 +433,8 @@ mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
{
struct htype *h = set->data;
- init_timer(&h->gc);
- h->gc.data = (unsigned long)set;
- h->gc.function = gc;
- h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
- add_timer(&h->gc);
+ setup_timer(&h->gc, gc, (unsigned long)set);
+ mod_timer(&h->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ);
pr_debug("gc initialized, run in every %u\n",
IPSET_GC_PERIOD(set->timeout));
}
@@ -473,12 +459,13 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b)
/* Delete expired elements from the hashtable */
static void
-mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize)
+mtype_expire(struct ip_set *set, struct htype *h)
{
struct htable *t;
struct hbucket *n, *tmp;
struct mtype_elem *data;
u32 i, j, d;
+ size_t dsize = set->dsize;
#ifdef IP_SET_HASH_WITH_NETS
u8 k;
#endif
@@ -494,21 +481,20 @@ mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize)
continue;
}
data = ahash_data(n, j, dsize);
- if (ip_set_timeout_expired(ext_timeout(data, set))) {
- pr_debug("expired %u/%u\n", i, j);
- clear_bit(j, n->used);
- smp_mb__after_atomic();
+ if (!ip_set_timeout_expired(ext_timeout(data, set)))
+ continue;
+ pr_debug("expired %u/%u\n", i, j);
+ clear_bit(j, n->used);
+ smp_mb__after_atomic();
#ifdef IP_SET_HASH_WITH_NETS
- for (k = 0; k < IPSET_NET_COUNT; k++)
- mtype_del_cidr(h,
- NCIDR_PUT(DCIDR_GET(data->cidr,
- k)),
- nets_length, k);
+ for (k = 0; k < IPSET_NET_COUNT; k++)
+ mtype_del_cidr(h,
+ NCIDR_PUT(DCIDR_GET(data->cidr, k)),
+ k);
#endif
- ip_set_ext_destroy(set, data);
- h->elements--;
- d++;
- }
+ ip_set_ext_destroy(set, data);
+ set->elements--;
+ d++;
}
if (d >= AHASH_INIT_SIZE) {
if (d >= n->size) {
@@ -532,6 +518,7 @@ mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize)
d++;
}
tmp->pos = d;
+ set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize);
rcu_assign_pointer(hbucket(t, i), tmp);
kfree_rcu(n, rcu);
}
@@ -546,7 +533,7 @@ mtype_gc(unsigned long ul_set)
pr_debug("called\n");
spin_lock_bh(&set->lock);
- mtype_expire(set, h, NLEN(set->family), set->dsize);
+ mtype_expire(set, h);
spin_unlock_bh(&set->lock);
h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
@@ -563,7 +550,7 @@ mtype_resize(struct ip_set *set, bool retried)
struct htype *h = set->data;
struct htable *t, *orig;
u8 htable_bits;
- size_t dsize = set->dsize;
+ size_t extsize, dsize = set->dsize;
#ifdef IP_SET_HASH_WITH_NETS
u8 flags;
struct mtype_elem *tmp;
@@ -606,6 +593,7 @@ mtype_resize(struct ip_set *set, bool retried)
/* There can't be another parallel resizing, but dumping is possible */
atomic_set(&orig->ref, 1);
atomic_inc(&orig->uref);
+ extsize = 0;
pr_debug("attempt to resize set %s from %u to %u, t %p\n",
set->name, orig->htable_bits, htable_bits, orig);
for (i = 0; i < jhash_size(orig->htable_bits); i++) {
@@ -636,6 +624,7 @@ mtype_resize(struct ip_set *set, bool retried)
goto cleanup;
}
m->size = AHASH_INIT_SIZE;
+ extsize = ext_size(AHASH_INIT_SIZE, dsize);
RCU_INIT_POINTER(hbucket(t, key), m);
} else if (m->pos >= m->size) {
struct hbucket *ht;
@@ -655,6 +644,7 @@ mtype_resize(struct ip_set *set, bool retried)
memcpy(ht, m, sizeof(struct hbucket) +
m->size * dsize);
ht->size = m->size + AHASH_INIT_SIZE;
+ extsize += ext_size(AHASH_INIT_SIZE, dsize);
kfree(m);
m = ht;
RCU_INIT_POINTER(hbucket(t, key), ht);
@@ -668,6 +658,7 @@ mtype_resize(struct ip_set *set, bool retried)
}
}
rcu_assign_pointer(h->table, t);
+ set->ext_size = extsize;
spin_unlock_bh(&set->lock);
@@ -715,11 +706,11 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
bool deleted = false, forceadd = false, reuse = false;
u32 key, multi = 0;
- if (h->elements >= h->maxelem) {
+ if (set->elements >= h->maxelem) {
if (SET_WITH_TIMEOUT(set))
/* FIXME: when set is full, we slow down here */
- mtype_expire(set, h, NLEN(set->family), set->dsize);
- if (h->elements >= h->maxelem && SET_WITH_FORCEADD(set))
+ mtype_expire(set, h);
+ if (set->elements >= h->maxelem && SET_WITH_FORCEADD(set))
forceadd = true;
}
@@ -727,20 +718,15 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
key = HKEY(value, h->initval, t->htable_bits);
n = __ipset_dereference_protected(hbucket(t, key), 1);
if (!n) {
- if (forceadd) {
- if (net_ratelimit())
- pr_warn("Set %s is full, maxelem %u reached\n",
- set->name, h->maxelem);
- return -IPSET_ERR_HASH_FULL;
- } else if (h->elements >= h->maxelem) {
+ if (forceadd || set->elements >= h->maxelem)
goto set_full;
- }
old = NULL;
n = kzalloc(sizeof(*n) + AHASH_INIT_SIZE * set->dsize,
GFP_ATOMIC);
if (!n)
return -ENOMEM;
n->size = AHASH_INIT_SIZE;
+ set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize);
goto copy_elem;
}
for (i = 0; i < n->pos; i++) {
@@ -778,14 +764,14 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
for (i = 0; i < IPSET_NET_COUNT; i++)
mtype_del_cidr(h,
NCIDR_PUT(DCIDR_GET(data->cidr, i)),
- NLEN(set->family), i);
+ i);
#endif
ip_set_ext_destroy(set, data);
- h->elements--;
+ set->elements--;
}
goto copy_data;
}
- if (h->elements >= h->maxelem)
+ if (set->elements >= h->maxelem)
goto set_full;
/* Create a new slot */
if (n->pos >= n->size) {
@@ -804,17 +790,17 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
memcpy(n, old, sizeof(struct hbucket) +
old->size * set->dsize);
n->size = old->size + AHASH_INIT_SIZE;
+ set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize);
}
copy_elem:
j = n->pos++;
data = ahash_data(n, j, set->dsize);
copy_data:
- h->elements++;
+ set->elements++;
#ifdef IP_SET_HASH_WITH_NETS
for (i = 0; i < IPSET_NET_COUNT; i++)
- mtype_add_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, i)),
- NLEN(set->family), i);
+ mtype_add_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i);
#endif
memcpy(data, d, sizeof(struct mtype_elem));
overwrite_extensions:
@@ -824,7 +810,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
if (SET_WITH_COUNTER(set))
ip_set_init_counter(ext_counter(data, set), ext);
if (SET_WITH_COMMENT(set))
- ip_set_init_comment(ext_comment(data, set), ext);
+ ip_set_init_comment(set, ext_comment(data, set), ext);
if (SET_WITH_SKBINFO(set))
ip_set_init_skbinfo(ext_skbinfo(data, set), ext);
/* Must come last for the case when timed out entry is reused */
@@ -883,11 +869,11 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
smp_mb__after_atomic();
if (i + 1 == n->pos)
n->pos--;
- h->elements--;
+ set->elements--;
#ifdef IP_SET_HASH_WITH_NETS
for (j = 0; j < IPSET_NET_COUNT; j++)
mtype_del_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, j)),
- NLEN(set->family), j);
+ j);
#endif
ip_set_ext_destroy(set, data);
@@ -896,6 +882,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
k++;
}
if (n->pos == 0 && k == 0) {
+ set->ext_size -= ext_size(n->size, dsize);
rcu_assign_pointer(hbucket(t, key), NULL);
kfree_rcu(n, rcu);
} else if (k >= AHASH_INIT_SIZE) {
@@ -914,6 +901,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
k++;
}
tmp->pos = k;
+ set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize);
rcu_assign_pointer(hbucket(t, key), tmp);
kfree_rcu(n, rcu);
}
@@ -957,14 +945,13 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,
int i, j = 0;
#endif
u32 key, multi = 0;
- u8 nets_length = NLEN(set->family);
pr_debug("test by nets\n");
- for (; j < nets_length && h->nets[j].cidr[0] && !multi; j++) {
+ for (; j < NLEN && h->nets[j].cidr[0] && !multi; j++) {
#if IPSET_NET_COUNT == 2
mtype_data_reset_elem(d, &orig);
mtype_data_netmask(d, NCIDR_GET(h->nets[j].cidr[0]), false);
- for (k = 0; k < nets_length && h->nets[k].cidr[1] && !multi;
+ for (k = 0; k < NLEN && h->nets[k].cidr[1] && !multi;
k++) {
mtype_data_netmask(d, NCIDR_GET(h->nets[k].cidr[1]),
true);
@@ -1021,7 +1008,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,
* try all possible network sizes
*/
for (i = 0; i < IPSET_NET_COUNT; i++)
- if (DCIDR_GET(d->cidr, i) != SET_HOST_MASK(set->family))
+ if (DCIDR_GET(d->cidr, i) != HOST_MASK)
break;
if (i == IPSET_NET_COUNT) {
ret = mtype_test_cidrs(set, d, ext, mext, flags);
@@ -1062,7 +1049,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
rcu_read_lock_bh();
t = rcu_dereference_bh_nfnl(h->table);
- memsize = mtype_ahash_memsize(h, t, NLEN(set->family), set->dsize);
+ memsize = mtype_ahash_memsize(h, t) + set->ext_size;
htable_bits = t->htable_bits;
rcu_read_unlock_bh();
@@ -1083,7 +1070,8 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
goto nla_put_failure;
#endif
if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) ||
- nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)))
+ nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) ||
+ nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(set->elements)))
goto nla_put_failure;
if (unlikely(ip_set_put_flags(skb, set)))
goto nla_put_failure;
@@ -1238,29 +1226,43 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
struct htype *h;
struct htable *t;
+ pr_debug("Create set %s with family %s\n",
+ set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6");
+
#ifndef IP_SET_PROTO_UNDEF
if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6))
return -IPSET_ERR_INVALID_FAMILY;
#endif
-#ifdef IP_SET_HASH_WITH_MARKMASK
- markmask = 0xffffffff;
-#endif
-#ifdef IP_SET_HASH_WITH_NETMASK
- netmask = set->family == NFPROTO_IPV4 ? 32 : 128;
- pr_debug("Create set %s with family %s\n",
- set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6");
-#endif
-
if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
return -IPSET_ERR_PROTOCOL;
+
#ifdef IP_SET_HASH_WITH_MARKMASK
/* Separated condition in order to avoid directive in argument list */
if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_MARKMASK)))
return -IPSET_ERR_PROTOCOL;
+
+ markmask = 0xffffffff;
+ if (tb[IPSET_ATTR_MARKMASK]) {
+ markmask = ntohl(nla_get_be32(tb[IPSET_ATTR_MARKMASK]));
+ if (markmask == 0)
+ return -IPSET_ERR_INVALID_MARKMASK;
+ }
+#endif
+
+#ifdef IP_SET_HASH_WITH_NETMASK
+ netmask = set->family == NFPROTO_IPV4 ? 32 : 128;
+ if (tb[IPSET_ATTR_NETMASK]) {
+ netmask = nla_get_u8(tb[IPSET_ATTR_NETMASK]);
+
+ if ((set->family == NFPROTO_IPV4 && netmask > 32) ||
+ (set->family == NFPROTO_IPV6 && netmask > 128) ||
+ netmask == 0)
+ return -IPSET_ERR_INVALID_NETMASK;
+ }
#endif
if (tb[IPSET_ATTR_HASHSIZE]) {
@@ -1272,43 +1274,11 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
if (tb[IPSET_ATTR_MAXELEM])
maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]);
-#ifdef IP_SET_HASH_WITH_NETMASK
- if (tb[IPSET_ATTR_NETMASK]) {
- netmask = nla_get_u8(tb[IPSET_ATTR_NETMASK]);
-
- if ((set->family == NFPROTO_IPV4 && netmask > 32) ||
- (set->family == NFPROTO_IPV6 && netmask > 128) ||
- netmask == 0)
- return -IPSET_ERR_INVALID_NETMASK;
- }
-#endif
-#ifdef IP_SET_HASH_WITH_MARKMASK
- if (tb[IPSET_ATTR_MARKMASK]) {
- markmask = ntohl(nla_get_be32(tb[IPSET_ATTR_MARKMASK]));
-
- if (markmask == 0)
- return -IPSET_ERR_INVALID_MARKMASK;
- }
-#endif
-
hsize = sizeof(*h);
-#ifdef IP_SET_HASH_WITH_NETS
- hsize += sizeof(struct net_prefixes) * NLEN(set->family);
-#endif
h = kzalloc(hsize, GFP_KERNEL);
if (!h)
return -ENOMEM;
- h->maxelem = maxelem;
-#ifdef IP_SET_HASH_WITH_NETMASK
- h->netmask = netmask;
-#endif
-#ifdef IP_SET_HASH_WITH_MARKMASK
- h->markmask = markmask;
-#endif
- get_random_bytes(&h->initval, sizeof(h->initval));
- set->timeout = IPSET_NO_TIMEOUT;
-
hbits = htable_bits(hashsize);
hsize = htable_size(hbits);
if (hsize == 0) {
@@ -1320,8 +1290,17 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
kfree(h);
return -ENOMEM;
}
+ h->maxelem = maxelem;
+#ifdef IP_SET_HASH_WITH_NETMASK
+ h->netmask = netmask;
+#endif
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ h->markmask = markmask;
+#endif
+ get_random_bytes(&h->initval, sizeof(h->initval));
+
t->htable_bits = hbits;
- rcu_assign_pointer(h->table, t);
+ RCU_INIT_POINTER(h->table, t);
set->data = h;
#ifndef IP_SET_PROTO_UNDEF
@@ -1339,6 +1318,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
__alignof__(struct IPSET_TOKEN(HTYPE, 6_elem)));
}
#endif
+ set->timeout = IPSET_NO_TIMEOUT;
if (tb[IPSET_ATTR_TIMEOUT]) {
set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
#ifndef IP_SET_PROTO_UNDEF
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index 9d6bf19..20bfbd3 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -82,7 +82,7 @@ hash_ip4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_ip *h = set->data;
+ const struct hash_ip4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ip4_elem e = { 0 };
struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
@@ -101,7 +101,7 @@ static int
hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ip *h = set->data;
+ const struct hash_ip4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ip4_elem e = { 0 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
@@ -199,7 +199,7 @@ hash_ip6_data_list(struct sk_buff *skb, const struct hash_ip6_elem *e)
}
static inline void
-hash_ip6_data_next(struct hash_ip4_elem *next, const struct hash_ip6_elem *e)
+hash_ip6_data_next(struct hash_ip6_elem *next, const struct hash_ip6_elem *e)
{
}
@@ -217,7 +217,7 @@ hash_ip6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_ip *h = set->data;
+ const struct hash_ip6 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ip6_elem e = { { .all = { 0 } } };
struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
@@ -234,7 +234,7 @@ static int
hash_ip6_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ip *h = set->data;
+ const struct hash_ip6 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ip6_elem e = { { .all = { 0 } } };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c
new file mode 100644
index 0000000..1ab5ed2
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_hash_ipmac.c
@@ -0,0 +1,315 @@
+/* Copyright (C) 2016 Tomasz Chilinski <tomasz.chilinski@chilan.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Kernel module implementing an IP set type: the hash:ip,mac type */
+
+#include <linux/jhash.h>
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+#include <linux/random.h>
+#include <linux/if_ether.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/netlink.h>
+#include <net/tcp.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter/ipset/pfxlen.h>
+#include <linux/netfilter/ipset/ip_set.h>
+#include <linux/netfilter/ipset/ip_set_hash.h>
+
+#define IPSET_TYPE_REV_MIN 0
+#define IPSET_TYPE_REV_MAX 0
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Tomasz Chilinski <tomasz.chilinski@chilan.com>");
+IP_SET_MODULE_DESC("hash:ip,mac", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
+MODULE_ALIAS("ip_set_hash:ip,mac");
+
+/* Type specific function prefix */
+#define HTYPE hash_ipmac
+
+/* Zero valued element is not supported */
+static const unsigned char invalid_ether[ETH_ALEN] = { 0 };
+
+/* IPv4 variant */
+
+/* Member elements */
+struct hash_ipmac4_elem {
+ /* Zero valued IP addresses cannot be stored */
+ __be32 ip;
+ union {
+ unsigned char ether[ETH_ALEN];
+ __be32 foo[2];
+ };
+};
+
+/* Common functions */
+
+static inline bool
+hash_ipmac4_data_equal(const struct hash_ipmac4_elem *e1,
+ const struct hash_ipmac4_elem *e2,
+ u32 *multi)
+{
+ return e1->ip == e2->ip && ether_addr_equal(e1->ether, e2->ether);
+}
+
+static bool
+hash_ipmac4_data_list(struct sk_buff *skb, const struct hash_ipmac4_elem *e)
+{
+ if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, e->ip) ||
+ nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN, e->ether))
+ goto nla_put_failure;
+ return false;
+
+nla_put_failure:
+ return true;
+}
+
+static inline void
+hash_ipmac4_data_next(struct hash_ipmac4_elem *next,
+ const struct hash_ipmac4_elem *e)
+{
+ next->ip = e->ip;
+}
+
+#define MTYPE hash_ipmac4
+#define PF 4
+#define HOST_MASK 32
+#define HKEY_DATALEN sizeof(struct hash_ipmac4_elem)
+#include "ip_set_hash_gen.h"
+
+static int
+hash_ipmac4_kadt(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_ipmac4_elem e = { .ip = 0, { .foo[0] = 0, .foo[1] = 0 } };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+ /* MAC can be src only */
+ if (!(opt->flags & IPSET_DIM_TWO_SRC))
+ return 0;
+
+ if (skb_mac_header(skb) < skb->head ||
+ (skb_mac_header(skb) + ETH_HLEN) > skb->data)
+ return -EINVAL;
+
+ memcpy(e.ether, eth_hdr(skb)->h_source, ETH_ALEN);
+ if (ether_addr_equal(e.ether, invalid_ether))
+ return -EINVAL;
+
+ ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip);
+
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_ipmac4_uadt(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_ipmac4_elem e = { .ip = 0, { .foo[0] = 0, .foo[1] = 0 } };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ int ret;
+
+ if (unlikely(!tb[IPSET_ATTR_IP] ||
+ !tb[IPSET_ATTR_ETHER] ||
+ nla_len(tb[IPSET_ATTR_ETHER]) != ETH_ALEN ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE)))
+ return -IPSET_ERR_PROTOCOL;
+
+ if (tb[IPSET_ATTR_LINENO])
+ *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+ ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip) ||
+ ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
+ memcpy(e.ether, nla_data(tb[IPSET_ATTR_ETHER]), ETH_ALEN);
+ if (ether_addr_equal(e.ether, invalid_ether))
+ return -IPSET_ERR_HASH_ELEM;
+
+ return adtfn(set, &e, &ext, &ext, flags);
+}
+
+/* IPv6 variant */
+
+/* Member elements */
+struct hash_ipmac6_elem {
+ /* Zero valued IP addresses cannot be stored */
+ union nf_inet_addr ip;
+ union {
+ unsigned char ether[ETH_ALEN];
+ __be32 foo[2];
+ };
+};
+
+/* Common functions */
+
+static inline bool
+hash_ipmac6_data_equal(const struct hash_ipmac6_elem *e1,
+ const struct hash_ipmac6_elem *e2,
+ u32 *multi)
+{
+ return ipv6_addr_equal(&e1->ip.in6, &e2->ip.in6) &&
+ ether_addr_equal(e1->ether, e2->ether);
+}
+
+static bool
+hash_ipmac6_data_list(struct sk_buff *skb, const struct hash_ipmac6_elem *e)
+{
+ if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6) ||
+ nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN, e->ether))
+ goto nla_put_failure;
+ return false;
+
+nla_put_failure:
+ return true;
+}
+
+static inline void
+hash_ipmac6_data_next(struct hash_ipmac6_elem *next,
+ const struct hash_ipmac6_elem *e)
+{
+}
+
+#undef MTYPE
+#undef PF
+#undef HOST_MASK
+#undef HKEY_DATALEN
+
+#define MTYPE hash_ipmac6
+#define PF 6
+#define HOST_MASK 128
+#define HKEY_DATALEN sizeof(struct hash_ipmac6_elem)
+#define IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
+
+static int
+hash_ipmac6_kadt(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_ipmac6_elem e = {
+ { .all = { 0 } },
+ { .foo[0] = 0, .foo[1] = 0 }
+ };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+ /* MAC can be src only */
+ if (!(opt->flags & IPSET_DIM_TWO_SRC))
+ return 0;
+
+ if (skb_mac_header(skb) < skb->head ||
+ (skb_mac_header(skb) + ETH_HLEN) > skb->data)
+ return -EINVAL;
+
+ memcpy(e.ether, eth_hdr(skb)->h_source, ETH_ALEN);
+ if (ether_addr_equal(e.ether, invalid_ether))
+ return -EINVAL;
+
+ ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6);
+
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_ipmac6_uadt(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_ipmac6_elem e = {
+ { .all = { 0 } },
+ { .foo[0] = 0, .foo[1] = 0 }
+ };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ int ret;
+
+ if (unlikely(!tb[IPSET_ATTR_IP] ||
+ !tb[IPSET_ATTR_ETHER] ||
+ nla_len(tb[IPSET_ATTR_ETHER]) != ETH_ALEN ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBMARK) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBPRIO) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_SKBQUEUE)))
+ return -IPSET_ERR_PROTOCOL;
+
+ if (tb[IPSET_ATTR_LINENO])
+ *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) ||
+ ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
+
+ memcpy(e.ether, nla_data(tb[IPSET_ATTR_ETHER]), ETH_ALEN);
+ if (ether_addr_equal(e.ether, invalid_ether))
+ return -IPSET_ERR_HASH_ELEM;
+
+ return adtfn(set, &e, &ext, &ext, flags);
+}
+
+static struct ip_set_type hash_ipmac_type __read_mostly = {
+ .name = "hash:ip,mac",
+ .protocol = IPSET_PROTOCOL,
+ .features = IPSET_TYPE_IP | IPSET_TYPE_MAC,
+ .dimension = IPSET_DIM_TWO,
+ .family = NFPROTO_UNSPEC,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
+ .create = hash_ipmac_create,
+ .create_policy = {
+ [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
+ [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
+ [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
+ [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
+ },
+ .adt_policy = {
+ [IPSET_ATTR_IP] = { .type = NLA_NESTED },
+ [IPSET_ATTR_ETHER] = { .type = NLA_BINARY,
+ .len = ETH_ALEN },
+ [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_LINENO] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
+ [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 },
+ [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 },
+ [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 },
+ },
+ .me = THIS_MODULE,
+};
+
+static int __init
+hash_ipmac_init(void)
+{
+ return ip_set_type_register(&hash_ipmac_type);
+}
+
+static void __exit
+hash_ipmac_fini(void)
+{
+ ip_set_type_unregister(&hash_ipmac_type);
+}
+
+module_init(hash_ipmac_init);
+module_exit(hash_ipmac_fini);
diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c
index a0695a2..b64cf14 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmark.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmark.c
@@ -85,7 +85,7 @@ hash_ipmark4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_ipmark *h = set->data;
+ const struct hash_ipmark4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipmark4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
@@ -101,7 +101,7 @@ static int
hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipmark *h = set->data;
+ const struct hash_ipmark4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipmark4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
@@ -193,7 +193,7 @@ hash_ipmark6_data_list(struct sk_buff *skb,
}
static inline void
-hash_ipmark6_data_next(struct hash_ipmark4_elem *next,
+hash_ipmark6_data_next(struct hash_ipmark6_elem *next,
const struct hash_ipmark6_elem *d)
{
}
@@ -211,7 +211,7 @@ hash_ipmark6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_ipmark *h = set->data;
+ const struct hash_ipmark6 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipmark6_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
@@ -227,7 +227,7 @@ static int
hash_ipmark6_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipmark *h = set->data;
+ const struct hash_ipmark6 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipmark6_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index 9d84b3d..f438740 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -108,7 +108,7 @@ static int
hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipport *h = set->data;
+ const struct hash_ipport4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipport4_elem e = { .ip = 0 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
@@ -231,7 +231,7 @@ hash_ipport6_data_list(struct sk_buff *skb,
}
static inline void
-hash_ipport6_data_next(struct hash_ipport4_elem *next,
+hash_ipport6_data_next(struct hash_ipport6_elem *next,
const struct hash_ipport6_elem *d)
{
next->port = d->port;
@@ -266,7 +266,7 @@ static int
hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipport *h = set->data;
+ const struct hash_ipport6 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipport6_elem e = { .ip = { .all = { 0 } } };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index 215b7b9..6215fb8 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -111,7 +111,7 @@ static int
hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipportip *h = set->data;
+ const struct hash_ipportip4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportip4_elem e = { .ip = 0 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
@@ -241,7 +241,7 @@ hash_ipportip6_data_list(struct sk_buff *skb,
}
static inline void
-hash_ipportip6_data_next(struct hash_ipportip4_elem *next,
+hash_ipportip6_data_next(struct hash_ipportip6_elem *next,
const struct hash_ipportip6_elem *d)
{
next->port = d->port;
@@ -277,7 +277,7 @@ static int
hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipportip *h = set->data;
+ const struct hash_ipportip6 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportip6_elem e = { .ip = { .all = { 0 } } };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index 9ca7196..5ab1b99 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -138,7 +138,7 @@ hash_ipportnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_ipportnet *h = set->data;
+ const struct hash_ipportnet4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportnet4_elem e = {
.cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
@@ -163,7 +163,7 @@ static int
hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipportnet *h = set->data;
+ const struct hash_ipportnet4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportnet4_elem e = { .cidr = HOST_MASK - 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
@@ -370,7 +370,7 @@ hash_ipportnet6_data_list(struct sk_buff *skb,
}
static inline void
-hash_ipportnet6_data_next(struct hash_ipportnet4_elem *next,
+hash_ipportnet6_data_next(struct hash_ipportnet6_elem *next,
const struct hash_ipportnet6_elem *d)
{
next->port = d->port;
@@ -389,7 +389,7 @@ hash_ipportnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_ipportnet *h = set->data;
+ const struct hash_ipportnet6 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportnet6_elem e = {
.cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
@@ -414,7 +414,7 @@ static int
hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipportnet *h = set->data;
+ const struct hash_ipportnet6 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportnet6_elem e = { .cidr = HOST_MASK - 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 3e4bffd..5d9e8954 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -117,7 +117,7 @@ hash_net4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_net *h = set->data;
+ const struct hash_net4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_net4_elem e = {
.cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
@@ -139,7 +139,7 @@ static int
hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_net *h = set->data;
+ const struct hash_net4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_net4_elem e = { .cidr = HOST_MASK };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
@@ -268,7 +268,7 @@ hash_net6_data_list(struct sk_buff *skb, const struct hash_net6_elem *data)
}
static inline void
-hash_net6_data_next(struct hash_net4_elem *next,
+hash_net6_data_next(struct hash_net6_elem *next,
const struct hash_net6_elem *d)
{
}
@@ -286,7 +286,7 @@ hash_net6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_net *h = set->data;
+ const struct hash_net6 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_net6_elem e = {
.cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index f0f688d..44cf119 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -156,7 +156,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- struct hash_netiface *h = set->data;
+ struct hash_netiface4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netiface4_elem e = {
.cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
@@ -170,7 +170,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip);
e.ip &= ip_set_netmask(e.cidr);
-#define IFACE(dir) (par->dir ? par->dir->name : "")
+#define IFACE(dir) (par->state->dir ? par->state->dir->name : "")
#define SRCDIR (opt->flags & IPSET_DIM_TWO_SRC)
if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
@@ -196,7 +196,7 @@ static int
hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- struct hash_netiface *h = set->data;
+ struct hash_netiface4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
@@ -348,7 +348,7 @@ hash_netiface6_data_list(struct sk_buff *skb,
}
static inline void
-hash_netiface6_data_next(struct hash_netiface4_elem *next,
+hash_netiface6_data_next(struct hash_netiface6_elem *next,
const struct hash_netiface6_elem *d)
{
}
@@ -367,7 +367,7 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- struct hash_netiface *h = set->data;
+ struct hash_netiface6 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netiface6_elem e = {
.cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
index a93dfeb..db614e1 100644
--- a/net/netfilter/ipset/ip_set_hash_netnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -143,7 +143,7 @@ hash_netnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_netnet *h = set->data;
+ const struct hash_netnet4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netnet4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
@@ -165,7 +165,7 @@ static int
hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_netnet *h = set->data;
+ const struct hash_netnet4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netnet4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
@@ -352,7 +352,7 @@ hash_netnet6_data_list(struct sk_buff *skb,
}
static inline void
-hash_netnet6_data_next(struct hash_netnet4_elem *next,
+hash_netnet6_data_next(struct hash_netnet6_elem *next,
const struct hash_netnet6_elem *d)
{
}
@@ -377,7 +377,7 @@ hash_netnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_netnet *h = set->data;
+ const struct hash_netnet6 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netnet6_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index 731813e..54b64b6 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -133,7 +133,7 @@ hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_netport *h = set->data;
+ const struct hash_netport4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netport4_elem e = {
.cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
@@ -157,7 +157,7 @@ static int
hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_netport *h = set->data;
+ const struct hash_netport4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
@@ -329,7 +329,7 @@ hash_netport6_data_list(struct sk_buff *skb,
}
static inline void
-hash_netport6_data_next(struct hash_netport4_elem *next,
+hash_netport6_data_next(struct hash_netport6_elem *next,
const struct hash_netport6_elem *d)
{
next->port = d->port;
@@ -348,7 +348,7 @@ hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_netport *h = set->data;
+ const struct hash_netport6 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netport6_elem e = {
.cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
@@ -372,7 +372,7 @@ static int
hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_netport *h = set->data;
+ const struct hash_netport6 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netport6_elem e = { .cidr = HOST_MASK - 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index 9a14c23..aff8469 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -154,7 +154,7 @@ hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_netportnet *h = set->data;
+ const struct hash_netportnet4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netportnet4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
@@ -180,7 +180,7 @@ static int
hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_netportnet *h = set->data;
+ const struct hash_netportnet4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netportnet4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
@@ -406,7 +406,7 @@ hash_netportnet6_data_list(struct sk_buff *skb,
}
static inline void
-hash_netportnet6_data_next(struct hash_netportnet4_elem *next,
+hash_netportnet6_data_next(struct hash_netportnet6_elem *next,
const struct hash_netportnet6_elem *d)
{
next->port = d->port;
@@ -432,7 +432,7 @@ hash_netportnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct hash_netportnet *h = set->data;
+ const struct hash_netportnet6 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netportnet6_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
@@ -458,7 +458,7 @@ static int
hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_netportnet *h = set->data;
+ const struct hash_netportnet6 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netportnet6_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index a2a89e4..51077c5 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -166,6 +166,7 @@ __list_set_del_rcu(struct rcu_head * rcu)
static inline void
list_set_del(struct ip_set *set, struct set_elem *e)
{
+ set->elements--;
list_del_rcu(&e->list);
call_rcu(&e->rcu, __list_set_del_rcu);
}
@@ -227,7 +228,7 @@ list_set_init_extensions(struct ip_set *set, const struct ip_set_ext *ext,
if (SET_WITH_COUNTER(set))
ip_set_init_counter(ext_counter(e, set), ext);
if (SET_WITH_COMMENT(set))
- ip_set_init_comment(ext_comment(e, set), ext);
+ ip_set_init_comment(set, ext_comment(e, set), ext);
if (SET_WITH_SKBINFO(set))
ip_set_init_skbinfo(ext_skbinfo(e, set), ext);
/* Update timeout last */
@@ -309,6 +310,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext,
list_add_rcu(&e->list, &prev->list);
else
list_add_tail_rcu(&e->list, &map->members);
+ set->elements++;
return 0;
}
@@ -419,6 +421,8 @@ list_set_flush(struct ip_set *set)
list_for_each_entry_safe(e, n, &map->members, list)
list_set_del(set, e);
+ set->elements = 0;
+ set->ext_size = 0;
}
static void
@@ -441,12 +445,12 @@ list_set_destroy(struct ip_set *set)
set->data = NULL;
}
-static int
-list_set_head(struct ip_set *set, struct sk_buff *skb)
+/* Calculate the actual memory size of the set data */
+static size_t
+list_set_memsize(const struct list_set *map, size_t dsize)
{
- const struct list_set *map = set->data;
- struct nlattr *nested;
struct set_elem *e;
+ size_t memsize;
u32 n = 0;
rcu_read_lock();
@@ -454,13 +458,25 @@ list_set_head(struct ip_set *set, struct sk_buff *skb)
n++;
rcu_read_unlock();
+ memsize = sizeof(*map) + n * dsize;
+
+ return memsize;
+}
+
+static int
+list_set_head(struct ip_set *set, struct sk_buff *skb)
+{
+ const struct list_set *map = set->data;
+ struct nlattr *nested;
+ size_t memsize = list_set_memsize(map, set->dsize) + set->ext_size;
+
nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
if (!nested)
goto nla_put_failure;
if (nla_put_net32(skb, IPSET_ATTR_SIZE, htonl(map->size)) ||
nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) ||
- nla_put_net32(skb, IPSET_ATTR_MEMSIZE,
- htonl(sizeof(*map) + n * set->dsize)))
+ nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) ||
+ nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(set->elements)))
goto nla_put_failure;
if (unlikely(ip_set_put_flags(skb, set)))
goto nla_put_failure;
@@ -570,11 +586,8 @@ list_set_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
{
struct list_set *map = set->data;
- init_timer(&map->gc);
- map->gc.data = (unsigned long)set;
- map->gc.function = gc;
- map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
- add_timer(&map->gc);
+ setup_timer(&map->gc, gc, (unsigned long)set);
+ mod_timer(&map->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ);
}
/* Create list:set type of sets */
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 2c1b498..db40050 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -70,7 +70,7 @@ EXPORT_SYMBOL(ip_vs_get_debug_level);
#endif
EXPORT_SYMBOL(ip_vs_new_conn_out);
-static int ip_vs_net_id __read_mostly;
+static unsigned int ip_vs_net_id __read_mostly;
/* netns cnt used for uniqueness */
static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 6b85ded..038c2ba 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3869,7 +3869,7 @@ static struct genl_family ip_vs_genl_family __ro_after_init = {
.hdrsize = 0,
.name = IPVS_GENL_NAME,
.version = IPVS_GENL_VERSION,
- .maxattr = IPVS_CMD_MAX,
+ .maxattr = IPVS_CMD_ATTR_MAX,
.netnsok = true, /* Make ipvsadm to work on netns */
.module = THIS_MODULE,
.ops = ip_vs_genl_ops,
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 1b07578..9350530 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -283,6 +283,7 @@ struct ip_vs_sync_buff {
*/
static void ntoh_seq(struct ip_vs_seq *no, struct ip_vs_seq *ho)
{
+ memset(ho, 0, sizeof(*ho));
ho->init_seq = get_unaligned_be32(&no->init_seq);
ho->delta = get_unaligned_be32(&no->delta);
ho->previous_delta = get_unaligned_be32(&no->previous_delta);
@@ -917,8 +918,10 @@ static void ip_vs_proc_conn(struct netns_ipvs *ipvs, struct ip_vs_conn_param *pa
kfree(param->pe_data);
}
- if (opt)
- memcpy(&cp->in_seq, opt, sizeof(*opt));
+ if (opt) {
+ cp->in_seq = opt->in_seq;
+ cp->out_seq = opt->out_seq;
+ }
atomic_set(&cp->in_pkts, sysctl_sync_threshold(ipvs));
cp->state = state;
cp->old_state = cp->state;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index ba6a1d4..6a0bbfa 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -76,6 +76,7 @@ struct conntrack_gc_work {
struct delayed_work dwork;
u32 last_bucket;
bool exiting;
+ long next_gc_run;
};
static __read_mostly struct kmem_cache *nf_conntrack_cachep;
@@ -83,9 +84,11 @@ static __read_mostly spinlock_t nf_conntrack_locks_all_lock;
static __read_mostly DEFINE_SPINLOCK(nf_conntrack_locks_all_lock);
static __read_mostly bool nf_conntrack_locks_all;
+/* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */
#define GC_MAX_BUCKETS_DIV 64u
-#define GC_MAX_BUCKETS 8192u
-#define GC_INTERVAL (5 * HZ)
+/* upper bound of scan intervals */
+#define GC_INTERVAL_MAX (2 * HZ)
+/* maximum conntracks to evict per gc run */
#define GC_MAX_EVICTS 256u
static struct conntrack_gc_work conntrack_gc_work;
@@ -936,13 +939,13 @@ static noinline int early_drop(struct net *net, unsigned int _hash)
static void gc_worker(struct work_struct *work)
{
unsigned int i, goal, buckets = 0, expired_count = 0;
- unsigned long next_run = GC_INTERVAL;
- unsigned int ratio, scanned = 0;
struct conntrack_gc_work *gc_work;
+ unsigned int ratio, scanned = 0;
+ unsigned long next_run;
gc_work = container_of(work, struct conntrack_gc_work, dwork.work);
- goal = min(nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV, GC_MAX_BUCKETS);
+ goal = nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV;
i = gc_work->last_bucket;
do {
@@ -982,17 +985,47 @@ static void gc_worker(struct work_struct *work)
if (gc_work->exiting)
return;
+ /*
+ * Eviction will normally happen from the packet path, and not
+ * from this gc worker.
+ *
+ * This worker is only here to reap expired entries when system went
+ * idle after a busy period.
+ *
+ * The heuristics below are supposed to balance conflicting goals:
+ *
+ * 1. Minimize time until we notice a stale entry
+ * 2. Maximize scan intervals to not waste cycles
+ *
+ * Normally, expired_count will be 0, this increases the next_run time
+ * to priorize 2) above.
+ *
+ * As soon as a timed-out entry is found, move towards 1) and increase
+ * the scan frequency.
+ * In case we have lots of evictions next scan is done immediately.
+ */
ratio = scanned ? expired_count * 100 / scanned : 0;
- if (ratio >= 90)
+ if (ratio >= 90 || expired_count == GC_MAX_EVICTS) {
+ gc_work->next_gc_run = 0;
next_run = 0;
+ } else if (expired_count) {
+ gc_work->next_gc_run /= 2U;
+ next_run = msecs_to_jiffies(1);
+ } else {
+ if (gc_work->next_gc_run < GC_INTERVAL_MAX)
+ gc_work->next_gc_run += msecs_to_jiffies(1);
+
+ next_run = gc_work->next_gc_run;
+ }
gc_work->last_bucket = i;
- schedule_delayed_work(&gc_work->dwork, next_run);
+ queue_delayed_work(system_long_wq, &gc_work->dwork, next_run);
}
static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work)
{
INIT_DELAYED_WORK(&gc_work->dwork, gc_worker);
+ gc_work->next_gc_run = GC_INTERVAL_MAX;
gc_work->exiting = false;
}
@@ -1305,7 +1338,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
if (skb->nfct)
goto out;
}
-
+repeat:
ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum,
l3proto, l4proto, &set_reply, &ctinfo);
if (!ct) {
@@ -1337,6 +1370,12 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
NF_CT_STAT_INC_ATOMIC(net, invalid);
if (ret == -NF_DROP)
NF_CT_STAT_INC_ATOMIC(net, drop);
+ /* Special case: TCP tracker reports an attempt to reopen a
+ * closed/aborted connection. We have to go back and create a
+ * fresh conntrack.
+ */
+ if (ret == -NF_REPEAT)
+ goto repeat;
ret = -ret;
goto out;
}
@@ -1344,15 +1383,8 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status))
nf_conntrack_event_cache(IPCT_REPLY, ct);
out:
- if (tmpl) {
- /* Special case: we have to repeat this hook, assign the
- * template again to this packet. We assume that this packet
- * has no conntrack assigned. This is used by nf_ct_tcp. */
- if (ret == NF_REPEAT)
- skb->nfct = (struct nf_conntrack *)tmpl;
- else
- nf_ct_put(tmpl);
- }
+ if (tmpl)
+ nf_ct_put(tmpl);
return ret;
}
@@ -1885,7 +1917,7 @@ int nf_conntrack_init_start(void)
nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED);
conntrack_gc_work_init(&conntrack_gc_work);
- schedule_delayed_work(&conntrack_gc_work.dwork, GC_INTERVAL);
+ queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, GC_INTERVAL_MAX);
return 0;
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 336e215..7341adf 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -138,9 +138,14 @@ __nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum)
for (i = 0; i < nf_ct_helper_hsize; i++) {
hlist_for_each_entry_rcu(h, &nf_ct_helper_hash[i], hnode) {
- if (!strcmp(h->name, name) &&
- h->tuple.src.l3num == l3num &&
- h->tuple.dst.protonum == protonum)
+ if (strcmp(h->name, name))
+ continue;
+
+ if (h->tuple.src.l3num != NFPROTO_UNSPEC &&
+ h->tuple.src.l3num != l3num)
+ continue;
+
+ if (h->tuple.dst.protonum == protonum)
return h;
}
}
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 8d2c7d8..9bd3464 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -281,15 +281,15 @@ void nf_ct_l4proto_unregister_sysctl(struct net *net,
/* FIXME: Allow NULL functions and sub in pointers to generic for
them. --RR */
-int nf_ct_l4proto_register(struct nf_conntrack_l4proto *l4proto)
+int nf_ct_l4proto_register_one(struct nf_conntrack_l4proto *l4proto)
{
int ret = 0;
if (l4proto->l3proto >= PF_MAX)
return -EBUSY;
- if ((l4proto->to_nlattr && !l4proto->nlattr_size)
- || (l4proto->tuple_to_nlattr && !l4proto->nlattr_tuple_size))
+ if ((l4proto->to_nlattr && !l4proto->nlattr_size) ||
+ (l4proto->tuple_to_nlattr && !l4proto->nlattr_tuple_size))
return -EINVAL;
mutex_lock(&nf_ct_proto_mutex);
@@ -307,7 +307,8 @@ int nf_ct_l4proto_register(struct nf_conntrack_l4proto *l4proto)
}
for (i = 0; i < MAX_NF_CT_PROTO; i++)
- RCU_INIT_POINTER(proto_array[i], &nf_conntrack_l4proto_generic);
+ RCU_INIT_POINTER(proto_array[i],
+ &nf_conntrack_l4proto_generic);
/* Before making proto_array visible to lockless readers,
* we must make sure its content is committed to memory.
@@ -335,10 +336,10 @@ int nf_ct_l4proto_register(struct nf_conntrack_l4proto *l4proto)
mutex_unlock(&nf_ct_proto_mutex);
return ret;
}
-EXPORT_SYMBOL_GPL(nf_ct_l4proto_register);
+EXPORT_SYMBOL_GPL(nf_ct_l4proto_register_one);
-int nf_ct_l4proto_pernet_register(struct net *net,
- struct nf_conntrack_l4proto *l4proto)
+int nf_ct_l4proto_pernet_register_one(struct net *net,
+ struct nf_conntrack_l4proto *l4proto)
{
int ret = 0;
struct nf_proto_net *pn = NULL;
@@ -361,9 +362,9 @@ int nf_ct_l4proto_pernet_register(struct net *net,
out:
return ret;
}
-EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register);
+EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register_one);
-void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *l4proto)
+void nf_ct_l4proto_unregister_one(struct nf_conntrack_l4proto *l4proto)
{
BUG_ON(l4proto->l3proto >= PF_MAX);
@@ -378,10 +379,10 @@ void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *l4proto)
synchronize_rcu();
}
-EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister);
+EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister_one);
-void nf_ct_l4proto_pernet_unregister(struct net *net,
- struct nf_conntrack_l4proto *l4proto)
+void nf_ct_l4proto_pernet_unregister_one(struct net *net,
+ struct nf_conntrack_l4proto *l4proto)
{
struct nf_proto_net *pn = NULL;
@@ -395,6 +396,66 @@ void nf_ct_l4proto_pernet_unregister(struct net *net,
/* Remove all contrack entries for this protocol */
nf_ct_iterate_cleanup(net, kill_l4proto, l4proto, 0, 0);
}
+EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister_one);
+
+int nf_ct_l4proto_register(struct nf_conntrack_l4proto *l4proto[],
+ unsigned int num_proto)
+{
+ int ret = -EINVAL, ver;
+ unsigned int i;
+
+ for (i = 0; i < num_proto; i++) {
+ ret = nf_ct_l4proto_register_one(l4proto[i]);
+ if (ret < 0)
+ break;
+ }
+ if (i != num_proto) {
+ ver = l4proto[i]->l3proto == PF_INET6 ? 6 : 4;
+ pr_err("nf_conntrack_ipv%d: can't register %s%d proto.\n",
+ ver, l4proto[i]->name, ver);
+ nf_ct_l4proto_unregister(l4proto, i);
+ }
+ return ret;
+}
+EXPORT_SYMBOL_GPL(nf_ct_l4proto_register);
+
+int nf_ct_l4proto_pernet_register(struct net *net,
+ struct nf_conntrack_l4proto *l4proto[],
+ unsigned int num_proto)
+{
+ int ret = -EINVAL;
+ unsigned int i;
+
+ for (i = 0; i < num_proto; i++) {
+ ret = nf_ct_l4proto_pernet_register_one(net, l4proto[i]);
+ if (ret < 0)
+ break;
+ }
+ if (i != num_proto) {
+ pr_err("nf_conntrack_%s%d: pernet registration failed\n",
+ l4proto[i]->name,
+ l4proto[i]->l3proto == PF_INET6 ? 6 : 4);
+ nf_ct_l4proto_pernet_unregister(net, l4proto, i);
+ }
+ return ret;
+}
+EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register);
+
+void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *l4proto[],
+ unsigned int num_proto)
+{
+ while (num_proto-- != 0)
+ nf_ct_l4proto_unregister_one(l4proto[num_proto]);
+}
+EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister);
+
+void nf_ct_l4proto_pernet_unregister(struct net *net,
+ struct nf_conntrack_l4proto *l4proto[],
+ unsigned int num_proto)
+{
+ while (num_proto-- != 0)
+ nf_ct_l4proto_pernet_unregister_one(net, l4proto[num_proto]);
+}
EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister);
int nf_conntrack_proto_pernet_init(struct net *net)
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index a45bee5..073b047 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -385,7 +385,7 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] =
};
/* this module per-net specifics */
-static int dccp_net_id __read_mostly;
+static unsigned int dccp_net_id __read_mostly;
struct dccp_net {
struct nf_proto_net pn;
int dccp_loose;
@@ -936,30 +936,21 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = {
.init_net = dccp_init_net,
};
+static struct nf_conntrack_l4proto *dccp_proto[] = {
+ &dccp_proto4,
+ &dccp_proto6,
+};
+
static __net_init int dccp_net_init(struct net *net)
{
- int ret = 0;
- ret = nf_ct_l4proto_pernet_register(net, &dccp_proto4);
- if (ret < 0) {
- pr_err("nf_conntrack_dccp4: pernet registration failed.\n");
- goto out;
- }
- ret = nf_ct_l4proto_pernet_register(net, &dccp_proto6);
- if (ret < 0) {
- pr_err("nf_conntrack_dccp6: pernet registration failed.\n");
- goto cleanup_dccp4;
- }
- return 0;
-cleanup_dccp4:
- nf_ct_l4proto_pernet_unregister(net, &dccp_proto4);
-out:
- return ret;
+ return nf_ct_l4proto_pernet_register(net, dccp_proto,
+ ARRAY_SIZE(dccp_proto));
}
static __net_exit void dccp_net_exit(struct net *net)
{
- nf_ct_l4proto_pernet_unregister(net, &dccp_proto6);
- nf_ct_l4proto_pernet_unregister(net, &dccp_proto4);
+ nf_ct_l4proto_pernet_unregister(net, dccp_proto,
+ ARRAY_SIZE(dccp_proto));
}
static struct pernet_operations dccp_net_ops = {
@@ -975,29 +966,16 @@ static int __init nf_conntrack_proto_dccp_init(void)
ret = register_pernet_subsys(&dccp_net_ops);
if (ret < 0)
- goto out_pernet;
-
- ret = nf_ct_l4proto_register(&dccp_proto4);
+ return ret;
+ ret = nf_ct_l4proto_register(dccp_proto, ARRAY_SIZE(dccp_proto));
if (ret < 0)
- goto out_dccp4;
-
- ret = nf_ct_l4proto_register(&dccp_proto6);
- if (ret < 0)
- goto out_dccp6;
-
- return 0;
-out_dccp6:
- nf_ct_l4proto_unregister(&dccp_proto4);
-out_dccp4:
- unregister_pernet_subsys(&dccp_net_ops);
-out_pernet:
+ unregister_pernet_subsys(&dccp_net_ops);
return ret;
}
static void __exit nf_conntrack_proto_dccp_fini(void)
{
- nf_ct_l4proto_unregister(&dccp_proto6);
- nf_ct_l4proto_unregister(&dccp_proto4);
+ nf_ct_l4proto_unregister(dccp_proto, ARRAY_SIZE(dccp_proto));
unregister_pernet_subsys(&dccp_net_ops);
}
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index 9a715f8..87bb40a 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -53,7 +53,7 @@ static unsigned int gre_timeouts[GRE_CT_MAX] = {
[GRE_CT_REPLIED] = 180*HZ,
};
-static int proto_gre_net_id __read_mostly;
+static unsigned int proto_gre_net_id __read_mostly;
struct netns_proto_gre {
struct nf_proto_net nf;
rwlock_t keymap_lock;
@@ -396,7 +396,9 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = {
static int proto_gre_net_init(struct net *net)
{
int ret = 0;
- ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_gre4);
+
+ ret = nf_ct_l4proto_pernet_register_one(net,
+ &nf_conntrack_l4proto_gre4);
if (ret < 0)
pr_err("nf_conntrack_gre4: pernet registration failed.\n");
return ret;
@@ -404,7 +406,7 @@ static int proto_gre_net_init(struct net *net)
static void proto_gre_net_exit(struct net *net)
{
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_gre4);
+ nf_ct_l4proto_pernet_unregister_one(net, &nf_conntrack_l4proto_gre4);
nf_ct_gre_keymap_flush(net);
}
@@ -422,8 +424,7 @@ static int __init nf_ct_proto_gre_init(void)
ret = register_pernet_subsys(&proto_gre_net_ops);
if (ret < 0)
goto out_pernet;
-
- ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_gre4);
+ ret = nf_ct_l4proto_register_one(&nf_conntrack_l4proto_gre4);
if (ret < 0)
goto out_gre4;
@@ -436,7 +437,7 @@ static int __init nf_ct_proto_gre_init(void)
static void __exit nf_ct_proto_gre_fini(void)
{
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_gre4);
+ nf_ct_l4proto_unregister_one(&nf_conntrack_l4proto_gre4);
unregister_pernet_subsys(&proto_gre_net_ops);
}
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 982ea62..d096c2d 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -144,7 +144,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
}
};
-static int sctp_net_id __read_mostly;
+static unsigned int sctp_net_id __read_mostly;
struct sctp_net {
struct nf_proto_net pn;
unsigned int timeouts[SCTP_CONNTRACK_MAX];
@@ -816,32 +816,21 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = {
.init_net = sctp_init_net,
};
+static struct nf_conntrack_l4proto *sctp_proto[] = {
+ &nf_conntrack_l4proto_sctp4,
+ &nf_conntrack_l4proto_sctp6,
+};
+
static int sctp_net_init(struct net *net)
{
- int ret = 0;
-
- ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_sctp4);
- if (ret < 0) {
- pr_err("nf_conntrack_sctp4: pernet registration failed.\n");
- goto out;
- }
- ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_sctp6);
- if (ret < 0) {
- pr_err("nf_conntrack_sctp6: pernet registration failed.\n");
- goto cleanup_sctp4;
- }
- return 0;
-
-cleanup_sctp4:
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_sctp4);
-out:
- return ret;
+ return nf_ct_l4proto_pernet_register(net, sctp_proto,
+ ARRAY_SIZE(sctp_proto));
}
static void sctp_net_exit(struct net *net)
{
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_sctp6);
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_sctp4);
+ nf_ct_l4proto_pernet_unregister(net, sctp_proto,
+ ARRAY_SIZE(sctp_proto));
}
static struct pernet_operations sctp_net_ops = {
@@ -857,29 +846,16 @@ static int __init nf_conntrack_proto_sctp_init(void)
ret = register_pernet_subsys(&sctp_net_ops);
if (ret < 0)
- goto out_pernet;
-
- ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_sctp4);
+ return ret;
+ ret = nf_ct_l4proto_register(sctp_proto, ARRAY_SIZE(sctp_proto));
if (ret < 0)
- goto out_sctp4;
-
- ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_sctp6);
- if (ret < 0)
- goto out_sctp6;
-
- return 0;
-out_sctp6:
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp4);
-out_sctp4:
- unregister_pernet_subsys(&sctp_net_ops);
-out_pernet:
+ unregister_pernet_subsys(&sctp_net_ops);
return ret;
}
static void __exit nf_conntrack_proto_sctp_fini(void)
{
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp6);
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp4);
+ nf_ct_l4proto_unregister(sctp_proto, ARRAY_SIZE(sctp_proto));
unregister_pernet_subsys(&sctp_net_ops);
}
diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c
index 029206e8..7808604 100644
--- a/net/netfilter/nf_conntrack_proto_udplite.c
+++ b/net/netfilter/nf_conntrack_proto_udplite.c
@@ -35,7 +35,7 @@ static unsigned int udplite_timeouts[UDPLITE_CT_MAX] = {
[UDPLITE_CT_REPLIED] = 180*HZ,
};
-static int udplite_net_id __read_mostly;
+static unsigned int udplite_net_id __read_mostly;
struct udplite_net {
struct nf_proto_net pn;
unsigned int timeouts[UDPLITE_CT_MAX];
@@ -336,32 +336,21 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly =
.init_net = udplite_init_net,
};
+static struct nf_conntrack_l4proto *udplite_proto[] = {
+ &nf_conntrack_l4proto_udplite4,
+ &nf_conntrack_l4proto_udplite6,
+};
+
static int udplite_net_init(struct net *net)
{
- int ret = 0;
-
- ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udplite4);
- if (ret < 0) {
- pr_err("nf_conntrack_udplite4: pernet registration failed.\n");
- goto out;
- }
- ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udplite6);
- if (ret < 0) {
- pr_err("nf_conntrack_udplite6: pernet registration failed.\n");
- goto cleanup_udplite4;
- }
- return 0;
-
-cleanup_udplite4:
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udplite4);
-out:
- return ret;
+ return nf_ct_l4proto_pernet_register(net, udplite_proto,
+ ARRAY_SIZE(udplite_proto));
}
static void udplite_net_exit(struct net *net)
{
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udplite6);
- nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udplite4);
+ nf_ct_l4proto_pernet_unregister(net, udplite_proto,
+ ARRAY_SIZE(udplite_proto));
}
static struct pernet_operations udplite_net_ops = {
@@ -377,29 +366,16 @@ static int __init nf_conntrack_proto_udplite_init(void)
ret = register_pernet_subsys(&udplite_net_ops);
if (ret < 0)
- goto out_pernet;
-
- ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udplite4);
+ return ret;
+ ret = nf_ct_l4proto_register(udplite_proto, ARRAY_SIZE(udplite_proto));
if (ret < 0)
- goto out_udplite4;
-
- ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udplite6);
- if (ret < 0)
- goto out_udplite6;
-
- return 0;
-out_udplite6:
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite4);
-out_udplite4:
- unregister_pernet_subsys(&udplite_net_ops);
-out_pernet:
+ unregister_pernet_subsys(&udplite_net_ops);
return ret;
}
static void __exit nf_conntrack_proto_udplite_exit(void)
{
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite6);
- nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite4);
+ nf_ct_l4proto_unregister(udplite_proto, ARRAY_SIZE(udplite_proto));
unregister_pernet_subsys(&udplite_net_ops);
}
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 621b81c..c3fc14e 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1436,9 +1436,12 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff,
handler = &sip_handlers[i];
if (handler->request == NULL)
continue;
- if (*datalen < handler->len ||
+ if (*datalen < handler->len + 2 ||
strncasecmp(*dptr, handler->method, handler->len))
continue;
+ if ((*dptr)[handler->len] != ' ' ||
+ !isalpha((*dptr)[handler->len+1]))
+ continue;
if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_CSEQ,
&matchoff, &matchlen) <= 0) {
diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c
index 7ec6972..44ae986 100644
--- a/net/netfilter/nf_dup_netdev.c
+++ b/net/netfilter/nf_dup_netdev.c
@@ -19,7 +19,7 @@ void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif)
struct net_device *dev;
struct sk_buff *skb;
- dev = dev_get_by_index_rcu(pkt->net, oif);
+ dev = dev_get_by_index_rcu(nft_net(pkt), oif);
if (dev == NULL)
return;
diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h
index e0adb59..c46d214 100644
--- a/net/netfilter/nf_internals.h
+++ b/net/netfilter/nf_internals.h
@@ -11,14 +11,9 @@
#define NFDEBUG(format, args...)
#endif
-
-/* core.c */
-unsigned int nf_iterate(struct sk_buff *skb, struct nf_hook_state *state,
- struct nf_hook_entry **entryp);
-
/* nf_queue.c */
int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
- unsigned int queuenum);
+ struct nf_hook_entry **entryp, unsigned int verdict);
void nf_queue_nf_hook_drop(struct net *net, const struct nf_hook_entry *entry);
int __init netfilter_queue_init(void);
diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c
index 119fe1c..ed9b808 100644
--- a/net/netfilter/nf_log_common.c
+++ b/net/netfilter/nf_log_common.c
@@ -175,6 +175,33 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf,
}
EXPORT_SYMBOL_GPL(nf_log_dump_packet_common);
+/* bridge and netdev logging families share this code. */
+void nf_log_l2packet(struct net *net, u_int8_t pf,
+ unsigned int hooknum,
+ const struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ const struct nf_loginfo *loginfo,
+ const char *prefix)
+{
+ switch (eth_hdr(skb)->h_proto) {
+ case htons(ETH_P_IP):
+ nf_log_packet(net, NFPROTO_IPV4, hooknum, skb, in, out,
+ loginfo, "%s", prefix);
+ break;
+ case htons(ETH_P_IPV6):
+ nf_log_packet(net, NFPROTO_IPV6, hooknum, skb, in, out,
+ loginfo, "%s", prefix);
+ break;
+ case htons(ETH_P_ARP):
+ case htons(ETH_P_RARP):
+ nf_log_packet(net, NFPROTO_ARP, hooknum, skb, in, out,
+ loginfo, "%s", prefix);
+ break;
+ }
+}
+EXPORT_SYMBOL_GPL(nf_log_l2packet);
+
static int __init nf_log_common_init(void)
{
return 0;
diff --git a/net/netfilter/nf_log_netdev.c b/net/netfilter/nf_log_netdev.c
new file mode 100644
index 0000000..1f64594
--- /dev/null
+++ b/net/netfilter/nf_log_netdev.c
@@ -0,0 +1,80 @@
+/*
+ * (C) 2016 by Pablo Neira Ayuso <pablo@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <net/route.h>
+
+#include <linux/netfilter.h>
+#include <net/netfilter/nf_log.h>
+
+static void nf_log_netdev_packet(struct net *net, u_int8_t pf,
+ unsigned int hooknum,
+ const struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ const struct nf_loginfo *loginfo,
+ const char *prefix)
+{
+ nf_log_l2packet(net, pf, hooknum, skb, in, out, loginfo, prefix);
+}
+
+static struct nf_logger nf_netdev_logger __read_mostly = {
+ .name = "nf_log_netdev",
+ .type = NF_LOG_TYPE_LOG,
+ .logfn = nf_log_netdev_packet,
+ .me = THIS_MODULE,
+};
+
+static int __net_init nf_log_netdev_net_init(struct net *net)
+{
+ return nf_log_set(net, NFPROTO_NETDEV, &nf_netdev_logger);
+}
+
+static void __net_exit nf_log_netdev_net_exit(struct net *net)
+{
+ nf_log_unset(net, &nf_netdev_logger);
+}
+
+static struct pernet_operations nf_log_netdev_net_ops = {
+ .init = nf_log_netdev_net_init,
+ .exit = nf_log_netdev_net_exit,
+};
+
+static int __init nf_log_netdev_init(void)
+{
+ int ret;
+
+ /* Request to load the real packet loggers. */
+ nf_logger_request_module(NFPROTO_IPV4, NF_LOG_TYPE_LOG);
+ nf_logger_request_module(NFPROTO_IPV6, NF_LOG_TYPE_LOG);
+ nf_logger_request_module(NFPROTO_ARP, NF_LOG_TYPE_LOG);
+
+ ret = register_pernet_subsys(&nf_log_netdev_net_ops);
+ if (ret < 0)
+ return ret;
+
+ nf_log_register(NFPROTO_NETDEV, &nf_netdev_logger);
+ return 0;
+}
+
+static void __exit nf_log_netdev_exit(void)
+{
+ unregister_pernet_subsys(&nf_log_netdev_net_ops);
+ nf_log_unregister(&nf_netdev_logger);
+}
+
+module_init(nf_log_netdev_init);
+module_exit(nf_log_netdev_exit);
+
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_DESCRIPTION("Netfilter netdev packet logging");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NF_LOGGER(5, 0); /* NFPROTO_NETDEV */
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 96964a0..77cba9f 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -107,13 +107,8 @@ void nf_queue_nf_hook_drop(struct net *net, const struct nf_hook_entry *entry)
rcu_read_unlock();
}
-/*
- * Any packet that leaves via this function must come back
- * through nf_reinject().
- */
-int nf_queue(struct sk_buff *skb,
- struct nf_hook_state *state,
- unsigned int queuenum)
+static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state,
+ struct nf_hook_entry *hook_entry, unsigned int queuenum)
{
int status = -ENOENT;
struct nf_queue_entry *entry = NULL;
@@ -141,6 +136,7 @@ int nf_queue(struct sk_buff *skb,
*entry = (struct nf_queue_entry) {
.skb = skb,
.state = *state,
+ .hook = hook_entry,
.size = sizeof(*entry) + afinfo->route_key_size,
};
@@ -161,17 +157,54 @@ int nf_queue(struct sk_buff *skb,
return status;
}
+/* Packets leaving via this function must come back through nf_reinject(). */
+int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
+ struct nf_hook_entry **entryp, unsigned int verdict)
+{
+ struct nf_hook_entry *entry = *entryp;
+ int ret;
+
+ ret = __nf_queue(skb, state, entry, verdict >> NF_VERDICT_QBITS);
+ if (ret < 0) {
+ if (ret == -ESRCH &&
+ (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) {
+ *entryp = rcu_dereference(entry->next);
+ return 1;
+ }
+ kfree_skb(skb);
+ }
+
+ return 0;
+}
+
+static unsigned int nf_iterate(struct sk_buff *skb,
+ struct nf_hook_state *state,
+ struct nf_hook_entry **entryp)
+{
+ unsigned int verdict;
+
+ do {
+repeat:
+ verdict = (*entryp)->ops.hook((*entryp)->ops.priv, skb, state);
+ if (verdict != NF_ACCEPT) {
+ if (verdict != NF_REPEAT)
+ return verdict;
+ goto repeat;
+ }
+ *entryp = rcu_dereference((*entryp)->next);
+ } while (*entryp);
+
+ return NF_ACCEPT;
+}
+
void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
{
- struct nf_hook_entry *hook_entry;
+ struct nf_hook_entry *hook_entry = entry->hook;
+ struct nf_hook_ops *elem = &hook_entry->ops;
struct sk_buff *skb = entry->skb;
const struct nf_afinfo *afinfo;
- struct nf_hook_ops *elem;
int err;
- hook_entry = rcu_dereference(entry->state.hook_entries);
- elem = &hook_entry->ops;
-
nf_queue_entry_release_refs(entry);
/* Continue traversal iff userspace said ok... */
@@ -184,29 +217,27 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
verdict = NF_DROP;
}
- entry->state.thresh = INT_MIN;
-
if (verdict == NF_ACCEPT) {
- next_hook:
- verdict = nf_iterate(skb, &entry->state, &hook_entry);
+ hook_entry = rcu_dereference(hook_entry->next);
+ if (hook_entry)
+next_hook:
+ verdict = nf_iterate(skb, &entry->state, &hook_entry);
}
switch (verdict & NF_VERDICT_MASK) {
case NF_ACCEPT:
case NF_STOP:
+okfn:
local_bh_disable();
entry->state.okfn(entry->state.net, entry->state.sk, skb);
local_bh_enable();
break;
case NF_QUEUE:
- RCU_INIT_POINTER(entry->state.hook_entries, hook_entry);
- err = nf_queue(skb, &entry->state,
- verdict >> NF_VERDICT_QBITS);
- if (err < 0) {
- if (err == -ESRCH &&
- (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
+ err = nf_queue(skb, &entry->state, &hook_entry, verdict);
+ if (err == 1) {
+ if (hook_entry)
goto next_hook;
- kfree_skb(skb);
+ goto okfn;
}
break;
case NF_STOLEN:
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index c8a4a48..7c6d1fb 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -24,7 +24,7 @@
#include <net/netfilter/nf_conntrack_synproxy.h>
#include <net/netfilter/nf_conntrack_zones.h>
-int synproxy_net_id;
+unsigned int synproxy_net_id;
EXPORT_SYMBOL_GPL(synproxy_net_id);
bool
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index b70d3ea..026581b 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2956,12 +2956,14 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
if (err < 0)
- goto err2;
+ goto err3;
list_add_tail_rcu(&set->list, &table->sets);
table->use++;
return 0;
+err3:
+ ops->destroy(set);
err2:
kfree(set);
err1:
@@ -3452,14 +3454,15 @@ void *nft_set_elem_init(const struct nft_set *set,
return elem;
}
-void nft_set_elem_destroy(const struct nft_set *set, void *elem)
+void nft_set_elem_destroy(const struct nft_set *set, void *elem,
+ bool destroy_expr)
{
struct nft_set_ext *ext = nft_set_elem_ext(set, elem);
nft_data_uninit(nft_set_ext_key(ext), NFT_DATA_VALUE);
if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
nft_data_uninit(nft_set_ext_data(ext), set->dtype);
- if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR))
+ if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPR))
nf_tables_expr_destroy(NULL, nft_set_ext_expr(ext));
kfree(elem);
@@ -3565,6 +3568,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
dreg = nft_type_to_reg(set->dtype);
list_for_each_entry(binding, &set->bindings, list) {
struct nft_ctx bind_ctx = {
+ .net = ctx->net,
.afi = ctx->afi,
.table = ctx->table,
.chain = (struct nft_chain *)binding->chain,
@@ -3812,7 +3816,7 @@ void nft_set_gc_batch_release(struct rcu_head *rcu)
gcb = container_of(rcu, struct nft_set_gc_batch, head.rcu);
for (i = 0; i < gcb->head.cnt; i++)
- nft_set_elem_destroy(gcb->head.set, gcb->elems[i]);
+ nft_set_elem_destroy(gcb->head.set, gcb->elems[i], true);
kfree(gcb);
}
EXPORT_SYMBOL_GPL(nft_set_gc_batch_release);
@@ -4030,7 +4034,7 @@ static void nf_tables_commit_release(struct nft_trans *trans)
break;
case NFT_MSG_DELSETELEM:
nft_set_elem_destroy(nft_trans_elem_set(trans),
- nft_trans_elem(trans).priv);
+ nft_trans_elem(trans).priv, true);
break;
}
kfree(trans);
@@ -4171,7 +4175,7 @@ static void nf_tables_abort_release(struct nft_trans *trans)
break;
case NFT_MSG_NEWSETELEM:
nft_set_elem_destroy(nft_trans_elem_set(trans),
- nft_trans_elem(trans).priv);
+ nft_trans_elem(trans).priv, true);
break;
}
kfree(trans);
@@ -4421,9 +4425,9 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
* Otherwise a 0 is returned and the attribute value is stored in the
* destination variable.
*/
-unsigned int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest)
+int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest)
{
- int val;
+ u32 val;
val = ntohl(nla_get_be32(attr));
if (val > max)
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 0dd5c69..65dbead 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -53,10 +53,10 @@ static noinline void __nft_trace_packet(struct nft_traceinfo *info,
nft_trace_notify(info);
- nf_log_trace(pkt->net, pkt->pf, pkt->hook, pkt->skb, pkt->in,
- pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ",
- chain->table->name, chain->name, comments[type],
- rulenum);
+ nf_log_trace(nft_net(pkt), nft_pf(pkt), nft_hook(pkt), pkt->skb,
+ nft_in(pkt), nft_out(pkt), &trace_loginfo,
+ "TRACE: %s:%s:%s:%u ",
+ chain->table->name, chain->name, comments[type], rulenum);
}
static inline void nft_trace_packet(struct nft_traceinfo *info,
@@ -124,7 +124,7 @@ unsigned int
nft_do_chain(struct nft_pktinfo *pkt, void *priv)
{
const struct nft_chain *chain = priv, *basechain = chain;
- const struct net *net = pkt->net;
+ const struct net *net = nft_net(pkt);
const struct nft_rule *rule;
const struct nft_expr *expr, *last;
struct nft_regs regs;
@@ -178,6 +178,7 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv)
case NF_ACCEPT:
case NF_DROP:
case NF_QUEUE:
+ case NF_STOLEN:
nft_trace_packet(&info, chain, rule,
rulenum, NFT_TRACETYPE_RULE);
return regs.verdict.code;
@@ -231,68 +232,40 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv)
}
EXPORT_SYMBOL_GPL(nft_do_chain);
+static struct nft_expr_type *nft_basic_types[] = {
+ &nft_imm_type,
+ &nft_cmp_type,
+ &nft_lookup_type,
+ &nft_bitwise_type,
+ &nft_byteorder_type,
+ &nft_payload_type,
+ &nft_dynset_type,
+ &nft_range_type,
+};
+
int __init nf_tables_core_module_init(void)
{
- int err;
+ int err, i;
- err = nft_immediate_module_init();
- if (err < 0)
- goto err1;
-
- err = nft_cmp_module_init();
- if (err < 0)
- goto err2;
-
- err = nft_lookup_module_init();
- if (err < 0)
- goto err3;
-
- err = nft_bitwise_module_init();
- if (err < 0)
- goto err4;
-
- err = nft_byteorder_module_init();
- if (err < 0)
- goto err5;
-
- err = nft_payload_module_init();
- if (err < 0)
- goto err6;
-
- err = nft_dynset_module_init();
- if (err < 0)
- goto err7;
-
- err = nft_range_module_init();
- if (err < 0)
- goto err8;
+ for (i = 0; i < ARRAY_SIZE(nft_basic_types); i++) {
+ err = nft_register_expr(nft_basic_types[i]);
+ if (err)
+ goto err;
+ }
return 0;
-err8:
- nft_dynset_module_exit();
-err7:
- nft_payload_module_exit();
-err6:
- nft_byteorder_module_exit();
-err5:
- nft_bitwise_module_exit();
-err4:
- nft_lookup_module_exit();
-err3:
- nft_cmp_module_exit();
-err2:
- nft_immediate_module_exit();
-err1:
+
+err:
+ while (i-- > 0)
+ nft_unregister_expr(nft_basic_types[i]);
return err;
}
void nf_tables_core_module_exit(void)
{
- nft_dynset_module_exit();
- nft_payload_module_exit();
- nft_byteorder_module_exit();
- nft_bitwise_module_exit();
- nft_lookup_module_exit();
- nft_cmp_module_exit();
- nft_immediate_module_exit();
+ int i;
+
+ i = ARRAY_SIZE(nft_basic_types);
+ while (i-- > 0)
+ nft_unregister_expr(nft_basic_types[i]);
}
diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c
index ab695f8..12eb904 100644
--- a/net/netfilter/nf_tables_trace.c
+++ b/net/netfilter/nf_tables_trace.c
@@ -171,7 +171,7 @@ void nft_trace_notify(struct nft_traceinfo *info)
unsigned int size;
int event = (NFNL_SUBSYS_NFTABLES << 8) | NFT_MSG_TRACE;
- if (!nfnetlink_has_listeners(pkt->net, NFNLGRP_NFTRACE))
+ if (!nfnetlink_has_listeners(nft_net(pkt), NFNLGRP_NFTRACE))
return;
size = nlmsg_total_size(sizeof(struct nfgenmsg)) +
@@ -207,7 +207,7 @@ void nft_trace_notify(struct nft_traceinfo *info)
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = 0;
- if (nla_put_be32(skb, NFTA_TRACE_NFPROTO, htonl(pkt->pf)))
+ if (nla_put_be32(skb, NFTA_TRACE_NFPROTO, htonl(nft_pf(pkt))))
goto nla_put_failure;
if (nla_put_be32(skb, NFTA_TRACE_TYPE, htonl(info->type)))
@@ -249,7 +249,7 @@ void nft_trace_notify(struct nft_traceinfo *info)
goto nla_put_failure;
if (!info->packet_dumped) {
- if (nf_trace_fill_dev_info(skb, pkt->in, pkt->out))
+ if (nf_trace_fill_dev_info(skb, nft_in(pkt), nft_out(pkt)))
goto nla_put_failure;
if (nf_trace_fill_pkt_info(skb, pkt))
@@ -258,7 +258,7 @@ void nft_trace_notify(struct nft_traceinfo *info)
}
nlmsg_end(skb, nlh);
- nfnetlink_send(skb, pkt->net, 0, NFNLGRP_NFTRACE, 0, GFP_ATOMIC);
+ nfnetlink_send(skb, nft_net(pkt), 0, NFNLGRP_NFTRACE, 0, GFP_ATOMIC);
return;
nla_put_failure:
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index eb086a1..763cb4d 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -80,7 +80,7 @@ struct nfulnl_instance {
#define INSTANCE_BUCKETS 16
-static int nfnl_log_net_id __read_mostly;
+static unsigned int nfnl_log_net_id __read_mostly;
struct nfnl_log_net {
spinlock_t instances_lock;
@@ -330,7 +330,7 @@ nfulnl_alloc_skb(struct net *net, u32 peer_portid, unsigned int inst_size,
* message. WARNING: has to be <= 128k due to slab restrictions */
n = max(inst_size, pkt_size);
- skb = alloc_skb(n, GFP_ATOMIC);
+ skb = alloc_skb(n, GFP_ATOMIC | __GFP_NOWARN);
if (!skb) {
if (n > pkt_size) {
/* try to allocate only as much as we need for current
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index af832c5..be7627b 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -69,7 +69,7 @@ struct nfqnl_instance {
* Following fields are dirtied for each queued packet,
* keep them in same cache line if possible.
*/
- spinlock_t lock;
+ spinlock_t lock ____cacheline_aligned_in_smp;
unsigned int queue_total;
unsigned int id_sequence; /* 'sequence' of pkt ids */
struct list_head queue_list; /* packets in queue */
@@ -77,7 +77,7 @@ struct nfqnl_instance {
typedef int (*nfqnl_cmpfn)(struct nf_queue_entry *, unsigned long);
-static int nfnl_queue_net_id __read_mostly;
+static unsigned int nfnl_queue_net_id __read_mostly;
#define INSTANCE_BUCKETS 16
struct nfnl_queue_net {
@@ -919,7 +919,7 @@ static struct notifier_block nfqnl_dev_notifier = {
static int nf_hook_cmp(struct nf_queue_entry *entry, unsigned long entry_ptr)
{
- return rcu_access_pointer(entry->state.hook_entries) ==
+ return rcu_access_pointer(entry->hook) ==
(struct nf_hook_entry *)entry_ptr;
}
diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c
index 31c15ed..877d9ac 100644
--- a/net/netfilter/nft_bitwise.c
+++ b/net/netfilter/nft_bitwise.c
@@ -121,7 +121,6 @@ static int nft_bitwise_dump(struct sk_buff *skb, const struct nft_expr *expr)
return -1;
}
-static struct nft_expr_type nft_bitwise_type;
static const struct nft_expr_ops nft_bitwise_ops = {
.type = &nft_bitwise_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_bitwise)),
@@ -130,20 +129,10 @@ static const struct nft_expr_ops nft_bitwise_ops = {
.dump = nft_bitwise_dump,
};
-static struct nft_expr_type nft_bitwise_type __read_mostly = {
+struct nft_expr_type nft_bitwise_type __read_mostly = {
.name = "bitwise",
.ops = &nft_bitwise_ops,
.policy = nft_bitwise_policy,
.maxattr = NFTA_BITWISE_MAX,
.owner = THIS_MODULE,
};
-
-int __init nft_bitwise_module_init(void)
-{
- return nft_register_expr(&nft_bitwise_type);
-}
-
-void nft_bitwise_module_exit(void)
-{
- nft_unregister_expr(&nft_bitwise_type);
-}
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index ee63d98..13d4e42 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -169,7 +169,6 @@ static int nft_byteorder_dump(struct sk_buff *skb, const struct nft_expr *expr)
return -1;
}
-static struct nft_expr_type nft_byteorder_type;
static const struct nft_expr_ops nft_byteorder_ops = {
.type = &nft_byteorder_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_byteorder)),
@@ -178,20 +177,10 @@ static const struct nft_expr_ops nft_byteorder_ops = {
.dump = nft_byteorder_dump,
};
-static struct nft_expr_type nft_byteorder_type __read_mostly = {
+struct nft_expr_type nft_byteorder_type __read_mostly = {
.name = "byteorder",
.ops = &nft_byteorder_ops,
.policy = nft_byteorder_policy,
.maxattr = NFTA_BYTEORDER_MAX,
.owner = THIS_MODULE,
};
-
-int __init nft_byteorder_module_init(void)
-{
- return nft_register_expr(&nft_byteorder_type);
-}
-
-void nft_byteorder_module_exit(void)
-{
- nft_unregister_expr(&nft_byteorder_type);
-}
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index 2e53739..2b96eff 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -84,9 +84,6 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
if (err < 0)
return err;
- if (desc.len > U8_MAX)
- return -ERANGE;
-
priv->op = ntohl(nla_get_be32(tb[NFTA_CMP_OP]));
priv->len = desc.len;
return 0;
@@ -110,7 +107,6 @@ static int nft_cmp_dump(struct sk_buff *skb, const struct nft_expr *expr)
return -1;
}
-static struct nft_expr_type nft_cmp_type;
static const struct nft_expr_ops nft_cmp_ops = {
.type = &nft_cmp_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_cmp_expr)),
@@ -211,20 +207,10 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
return &nft_cmp_ops;
}
-static struct nft_expr_type nft_cmp_type __read_mostly = {
+struct nft_expr_type nft_cmp_type __read_mostly = {
.name = "cmp",
.select_ops = nft_cmp_select_ops,
.policy = nft_cmp_policy,
.maxattr = NFTA_CMP_MAX,
.owner = THIS_MODULE,
};
-
-int __init nft_cmp_module_init(void)
-{
- return nft_register_expr(&nft_cmp_type);
-}
-
-void nft_cmp_module_exit(void)
-{
- nft_unregister_expr(&nft_cmp_type);
-}
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index d7b0d171..6837348 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -1,5 +1,6 @@
/*
* Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2016 Pablo Neira Ayuso <pablo@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -518,15 +519,61 @@ static struct nft_expr_type nft_ct_type __read_mostly = {
.owner = THIS_MODULE,
};
+static void nft_notrack_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ struct sk_buff *skb = pkt->skb;
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
+
+ ct = nf_ct_get(pkt->skb, &ctinfo);
+ /* Previously seen (loopback or untracked)? Ignore. */
+ if (ct)
+ return;
+
+ ct = nf_ct_untracked_get();
+ atomic_inc(&ct->ct_general.use);
+ skb->nfct = &ct->ct_general;
+ skb->nfctinfo = IP_CT_NEW;
+}
+
+static struct nft_expr_type nft_notrack_type;
+static const struct nft_expr_ops nft_notrack_ops = {
+ .type = &nft_notrack_type,
+ .size = NFT_EXPR_SIZE(0),
+ .eval = nft_notrack_eval,
+};
+
+static struct nft_expr_type nft_notrack_type __read_mostly = {
+ .name = "notrack",
+ .ops = &nft_notrack_ops,
+ .owner = THIS_MODULE,
+};
+
static int __init nft_ct_module_init(void)
{
+ int err;
+
BUILD_BUG_ON(NF_CT_LABELS_MAX_SIZE > NFT_REG_SIZE);
- return nft_register_expr(&nft_ct_type);
+ err = nft_register_expr(&nft_ct_type);
+ if (err < 0)
+ return err;
+
+ err = nft_register_expr(&nft_notrack_type);
+ if (err < 0)
+ goto err1;
+
+ return 0;
+err1:
+ nft_unregister_expr(&nft_ct_type);
+ return err;
}
static void __exit nft_ct_module_exit(void)
{
+ nft_unregister_expr(&nft_notrack_type);
nft_unregister_expr(&nft_ct_type);
}
@@ -536,3 +583,4 @@ module_exit(nft_ct_module_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
MODULE_ALIAS_NFT_EXPR("ct");
+MODULE_ALIAS_NFT_EXPR("notrack");
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index e3b83c3..7de2f46 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -44,18 +44,22 @@ static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr,
®s->data[priv->sreg_key],
®s->data[priv->sreg_data],
timeout, GFP_ATOMIC);
- if (elem == NULL) {
- if (set->size)
- atomic_dec(&set->nelems);
- return NULL;
- }
+ if (elem == NULL)
+ goto err1;
ext = nft_set_elem_ext(set, elem);
if (priv->expr != NULL &&
nft_expr_clone(nft_set_ext_expr(ext), priv->expr) < 0)
- return NULL;
+ goto err2;
return elem;
+
+err2:
+ nft_set_elem_destroy(set, elem, false);
+err1:
+ if (set->size)
+ atomic_dec(&set->nelems);
+ return NULL;
}
static void nft_dynset_eval(const struct nft_expr *expr,
@@ -139,6 +143,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
return PTR_ERR(set);
}
+ if (set->ops->update == NULL)
+ return -EOPNOTSUPP;
+
if (set->flags & NFT_SET_CONSTANT)
return -EBUSY;
@@ -158,7 +165,8 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
if (tb[NFTA_DYNSET_TIMEOUT] != NULL) {
if (!(set->flags & NFT_SET_TIMEOUT))
return -EINVAL;
- timeout = be64_to_cpu(nla_get_be64(tb[NFTA_DYNSET_TIMEOUT]));
+ timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64(
+ tb[NFTA_DYNSET_TIMEOUT])));
}
priv->sreg_key = nft_parse_register(tb[NFTA_DYNSET_SREG_KEY]);
@@ -246,7 +254,8 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr)
goto nla_put_failure;
if (nla_put_string(skb, NFTA_DYNSET_SET_NAME, priv->set->name))
goto nla_put_failure;
- if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT, cpu_to_be64(priv->timeout),
+ if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT,
+ cpu_to_be64(jiffies_to_msecs(priv->timeout)),
NFTA_DYNSET_PAD))
goto nla_put_failure;
if (priv->expr && nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr))
@@ -259,7 +268,6 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr)
return -1;
}
-static struct nft_expr_type nft_dynset_type;
static const struct nft_expr_ops nft_dynset_ops = {
.type = &nft_dynset_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_dynset)),
@@ -269,20 +277,10 @@ static const struct nft_expr_ops nft_dynset_ops = {
.dump = nft_dynset_dump,
};
-static struct nft_expr_type nft_dynset_type __read_mostly = {
+struct nft_expr_type nft_dynset_type __read_mostly = {
.name = "dynset",
.ops = &nft_dynset_ops,
.policy = nft_dynset_policy,
.maxattr = NFTA_DYNSET_MAX,
.owner = THIS_MODULE,
};
-
-int __init nft_dynset_module_init(void)
-{
- return nft_register_expr(&nft_dynset_type);
-}
-
-void nft_dynset_module_exit(void)
-{
- nft_unregister_expr(&nft_dynset_type);
-}
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index a84cf3d..47beb3a 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -59,7 +59,8 @@ static int nft_exthdr_init(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
struct nft_exthdr *priv = nft_expr_priv(expr);
- u32 offset, len, err;
+ u32 offset, len;
+ int err;
if (tb[NFTA_EXTHDR_DREG] == NULL ||
tb[NFTA_EXTHDR_TYPE] == NULL ||
diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c
new file mode 100644
index 0000000..249c9b8
--- /dev/null
+++ b/net/netfilter/nft_fib.c
@@ -0,0 +1,159 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Generic part shared by ipv4 and ipv6 backends.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_fib.h>
+
+const struct nla_policy nft_fib_policy[NFTA_FIB_MAX + 1] = {
+ [NFTA_FIB_DREG] = { .type = NLA_U32 },
+ [NFTA_FIB_RESULT] = { .type = NLA_U32 },
+ [NFTA_FIB_FLAGS] = { .type = NLA_U32 },
+};
+EXPORT_SYMBOL(nft_fib_policy);
+
+#define NFTA_FIB_F_ALL (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR | \
+ NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)
+
+int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ const struct nft_data **data)
+{
+ const struct nft_fib *priv = nft_expr_priv(expr);
+ unsigned int hooks;
+
+ switch (priv->result) {
+ case NFT_FIB_RESULT_OIF: /* fallthrough */
+ case NFT_FIB_RESULT_OIFNAME:
+ hooks = (1 << NF_INET_PRE_ROUTING);
+ break;
+ case NFT_FIB_RESULT_ADDRTYPE:
+ if (priv->flags & NFTA_FIB_F_IIF)
+ hooks = (1 << NF_INET_PRE_ROUTING) |
+ (1 << NF_INET_LOCAL_IN) |
+ (1 << NF_INET_FORWARD);
+ else if (priv->flags & NFTA_FIB_F_OIF)
+ hooks = (1 << NF_INET_LOCAL_OUT) |
+ (1 << NF_INET_POST_ROUTING) |
+ (1 << NF_INET_FORWARD);
+ else
+ hooks = (1 << NF_INET_LOCAL_IN) |
+ (1 << NF_INET_LOCAL_OUT) |
+ (1 << NF_INET_FORWARD) |
+ (1 << NF_INET_PRE_ROUTING) |
+ (1 << NF_INET_POST_ROUTING);
+
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return nft_chain_validate_hooks(ctx->chain, hooks);
+}
+EXPORT_SYMBOL_GPL(nft_fib_validate);
+
+int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_fib *priv = nft_expr_priv(expr);
+ unsigned int len;
+ int err;
+
+ if (!tb[NFTA_FIB_DREG] || !tb[NFTA_FIB_RESULT] || !tb[NFTA_FIB_FLAGS])
+ return -EINVAL;
+
+ priv->flags = ntohl(nla_get_be32(tb[NFTA_FIB_FLAGS]));
+
+ if (priv->flags == 0 || (priv->flags & ~NFTA_FIB_F_ALL))
+ return -EINVAL;
+
+ if ((priv->flags & (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR)) ==
+ (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR))
+ return -EINVAL;
+ if ((priv->flags & (NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)) ==
+ (NFTA_FIB_F_IIF | NFTA_FIB_F_OIF))
+ return -EINVAL;
+ if ((priv->flags & (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR)) == 0)
+ return -EINVAL;
+
+ priv->result = htonl(nla_get_be32(tb[NFTA_FIB_RESULT]));
+ priv->dreg = nft_parse_register(tb[NFTA_FIB_DREG]);
+
+ switch (priv->result) {
+ case NFT_FIB_RESULT_OIF:
+ if (priv->flags & NFTA_FIB_F_OIF)
+ return -EINVAL;
+ len = sizeof(int);
+ break;
+ case NFT_FIB_RESULT_OIFNAME:
+ if (priv->flags & NFTA_FIB_F_OIF)
+ return -EINVAL;
+ len = IFNAMSIZ;
+ break;
+ case NFT_FIB_RESULT_ADDRTYPE:
+ len = sizeof(u32);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ err = nft_validate_register_store(ctx, priv->dreg, NULL,
+ NFT_DATA_VALUE, len);
+ if (err < 0)
+ return err;
+
+ return nft_fib_validate(ctx, expr, NULL);
+}
+EXPORT_SYMBOL_GPL(nft_fib_init);
+
+int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_fib *priv = nft_expr_priv(expr);
+
+ if (nft_dump_register(skb, NFTA_FIB_DREG, priv->dreg))
+ return -1;
+
+ if (nla_put_be32(skb, NFTA_FIB_RESULT, htonl(priv->result)))
+ return -1;
+
+ if (nla_put_be32(skb, NFTA_FIB_FLAGS, htonl(priv->flags)))
+ return -1;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nft_fib_dump);
+
+void nft_fib_store_result(void *reg, enum nft_fib_result r,
+ const struct nft_pktinfo *pkt, int index)
+{
+ struct net_device *dev;
+ u32 *dreg = reg;
+
+ switch (r) {
+ case NFT_FIB_RESULT_OIF:
+ *dreg = index;
+ break;
+ case NFT_FIB_RESULT_OIFNAME:
+ dev = dev_get_by_index_rcu(nft_net(pkt), index);
+ strncpy(reg, dev ? dev->name : "", IFNAMSIZ);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ *dreg = 0;
+ break;
+ }
+}
+EXPORT_SYMBOL_GPL(nft_fib_store_result);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
diff --git a/net/netfilter/nft_fib_inet.c b/net/netfilter/nft_fib_inet.c
new file mode 100644
index 0000000..9120fc7
--- /dev/null
+++ b/net/netfilter/nft_fib_inet.c
@@ -0,0 +1,82 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables.h>
+
+#include <net/netfilter/nft_fib.h>
+
+static void nft_fib_inet_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_fib *priv = nft_expr_priv(expr);
+
+ switch (nft_pf(pkt)) {
+ case NFPROTO_IPV4:
+ switch (priv->result) {
+ case NFT_FIB_RESULT_OIF:
+ case NFT_FIB_RESULT_OIFNAME:
+ return nft_fib4_eval(expr, regs, pkt);
+ case NFT_FIB_RESULT_ADDRTYPE:
+ return nft_fib4_eval_type(expr, regs, pkt);
+ }
+ break;
+ case NFPROTO_IPV6:
+ switch (priv->result) {
+ case NFT_FIB_RESULT_OIF:
+ case NFT_FIB_RESULT_OIFNAME:
+ return nft_fib6_eval(expr, regs, pkt);
+ case NFT_FIB_RESULT_ADDRTYPE:
+ return nft_fib6_eval_type(expr, regs, pkt);
+ }
+ break;
+ }
+
+ regs->verdict.code = NF_DROP;
+}
+
+static struct nft_expr_type nft_fib_inet_type;
+static const struct nft_expr_ops nft_fib_inet_ops = {
+ .type = &nft_fib_inet_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)),
+ .eval = nft_fib_inet_eval,
+ .init = nft_fib_init,
+ .dump = nft_fib_dump,
+ .validate = nft_fib_validate,
+};
+
+static struct nft_expr_type nft_fib_inet_type __read_mostly = {
+ .family = NFPROTO_INET,
+ .name = "fib",
+ .ops = &nft_fib_inet_ops,
+ .policy = nft_fib_policy,
+ .maxattr = NFTA_FIB_MAX,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_fib_inet_module_init(void)
+{
+ return nft_register_expr(&nft_fib_inet_type);
+}
+
+static void __exit nft_fib_inet_module_exit(void)
+{
+ nft_unregister_expr(&nft_fib_inet_type);
+}
+
+module_init(nft_fib_inet_module_init);
+module_exit(nft_fib_inet_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
+MODULE_ALIAS_NFT_AF_EXPR(1, "fib");
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 09473b4..97ad8e3 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -44,6 +44,7 @@ static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = {
[NFTA_HASH_LEN] = { .type = NLA_U32 },
[NFTA_HASH_MODULUS] = { .type = NLA_U32 },
[NFTA_HASH_SEED] = { .type = NLA_U32 },
+ [NFTA_HASH_OFFSET] = { .type = NLA_U32 },
};
static int nft_hash_init(const struct nft_ctx *ctx,
@@ -56,7 +57,6 @@ static int nft_hash_init(const struct nft_ctx *ctx,
if (!tb[NFTA_HASH_SREG] ||
!tb[NFTA_HASH_DREG] ||
!tb[NFTA_HASH_LEN] ||
- !tb[NFTA_HASH_SEED] ||
!tb[NFTA_HASH_MODULUS])
return -EINVAL;
@@ -79,7 +79,10 @@ static int nft_hash_init(const struct nft_ctx *ctx,
if (priv->offset + priv->modulus - 1 < priv->offset)
return -EOVERFLOW;
- priv->seed = ntohl(nla_get_be32(tb[NFTA_HASH_SEED]));
+ if (tb[NFTA_HASH_SEED])
+ priv->seed = ntohl(nla_get_be32(tb[NFTA_HASH_SEED]));
+ else
+ get_random_bytes(&priv->seed, sizeof(priv->seed));
return nft_validate_register_load(priv->sreg, len) &&
nft_validate_register_store(ctx, priv->dreg, NULL,
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index d17018f..728baf8 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -54,9 +54,6 @@ static int nft_immediate_init(const struct nft_ctx *ctx,
if (err < 0)
return err;
- if (desc.len > U8_MAX)
- return -ERANGE;
-
priv->dlen = desc.len;
priv->dreg = nft_parse_register(tb[NFTA_IMMEDIATE_DREG]);
@@ -105,7 +102,6 @@ static int nft_immediate_validate(const struct nft_ctx *ctx,
return 0;
}
-static struct nft_expr_type nft_imm_type;
static const struct nft_expr_ops nft_imm_ops = {
.type = &nft_imm_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)),
@@ -116,20 +112,10 @@ static const struct nft_expr_ops nft_imm_ops = {
.validate = nft_immediate_validate,
};
-static struct nft_expr_type nft_imm_type __read_mostly = {
+struct nft_expr_type nft_imm_type __read_mostly = {
.name = "immediate",
.ops = &nft_imm_ops,
.policy = nft_immediate_policy,
.maxattr = NFTA_IMMEDIATE_MAX,
.owner = THIS_MODULE,
};
-
-int __init nft_immediate_module_init(void)
-{
- return nft_register_expr(&nft_imm_type);
-}
-
-void nft_immediate_module_exit(void)
-{
- nft_unregister_expr(&nft_imm_type);
-}
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index 1b01404..6271e40 100644
--- a/net/netfilter/nft_log.c
+++ b/net/netfilter/nft_log.c
@@ -32,8 +32,9 @@ static void nft_log_eval(const struct nft_expr *expr,
{
const struct nft_log *priv = nft_expr_priv(expr);
- nf_log_packet(pkt->net, pkt->pf, pkt->hook, pkt->skb, pkt->in,
- pkt->out, &priv->loginfo, "%s", priv->prefix);
+ nf_log_packet(nft_net(pkt), nft_pf(pkt), nft_hook(pkt), pkt->skb,
+ nft_in(pkt), nft_out(pkt), &priv->loginfo, "%s",
+ priv->prefix);
}
static const struct nla_policy nft_log_policy[NFTA_LOG_MAX + 1] = {
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 8166b69..d4f97fa 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -35,9 +35,8 @@ static void nft_lookup_eval(const struct nft_expr *expr,
const struct nft_set_ext *ext;
bool found;
- found = set->ops->lookup(pkt->net, set, ®s->data[priv->sreg], &ext) ^
- priv->invert;
-
+ found = set->ops->lookup(nft_net(pkt), set, ®s->data[priv->sreg],
+ &ext) ^ priv->invert;
if (!found) {
regs->verdict.code = NFT_BREAK;
return;
@@ -155,7 +154,6 @@ static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr)
return -1;
}
-static struct nft_expr_type nft_lookup_type;
static const struct nft_expr_ops nft_lookup_ops = {
.type = &nft_lookup_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_lookup)),
@@ -165,20 +163,10 @@ static const struct nft_expr_ops nft_lookup_ops = {
.dump = nft_lookup_dump,
};
-static struct nft_expr_type nft_lookup_type __read_mostly = {
+struct nft_expr_type nft_lookup_type __read_mostly = {
.name = "lookup",
.ops = &nft_lookup_ops,
.policy = nft_lookup_policy,
.maxattr = NFTA_LOOKUP_MAX,
.owner = THIS_MODULE,
};
-
-int __init nft_lookup_module_init(void)
-{
- return nft_register_expr(&nft_lookup_type);
-}
-
-void nft_lookup_module_exit(void)
-{
- nft_unregister_expr(&nft_lookup_type);
-}
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 6c1e024..66c7f4b 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -36,7 +36,7 @@ void nft_meta_get_eval(const struct nft_expr *expr,
{
const struct nft_meta *priv = nft_expr_priv(expr);
const struct sk_buff *skb = pkt->skb;
- const struct net_device *in = pkt->in, *out = pkt->out;
+ const struct net_device *in = nft_in(pkt), *out = nft_out(pkt);
struct sock *sk;
u32 *dest = ®s->data[priv->dreg];
@@ -49,7 +49,7 @@ void nft_meta_get_eval(const struct nft_expr *expr,
*(__be16 *)dest = skb->protocol;
break;
case NFT_META_NFPROTO:
- *dest = pkt->pf;
+ *dest = nft_pf(pkt);
break;
case NFT_META_L4PROTO:
if (!pkt->tprot_set)
@@ -146,7 +146,7 @@ void nft_meta_get_eval(const struct nft_expr *expr,
break;
}
- switch (pkt->pf) {
+ switch (nft_pf(pkt)) {
case NFPROTO_IPV4:
if (ipv4_is_multicast(ip_hdr(skb)->daddr))
*dest = PACKET_MULTICAST;
@@ -310,6 +310,11 @@ int nft_meta_set_validate(const struct nft_ctx *ctx,
case NFPROTO_NETDEV:
hooks = 1 << NF_NETDEV_INGRESS;
break;
+ case NFPROTO_IPV4:
+ case NFPROTO_IPV6:
+ case NFPROTO_INET:
+ hooks = 1 << NF_INET_PRE_ROUTING;
+ break;
default:
return -EOPNOTSUPP;
}
diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c
index 55bc5ab..a66b360 100644
--- a/net/netfilter/nft_numgen.c
+++ b/net/netfilter/nft_numgen.c
@@ -65,7 +65,7 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx,
return -EOVERFLOW;
priv->dreg = nft_parse_register(tb[NFTA_NG_DREG]);
- atomic_set(&priv->counter, 0);
+ atomic_set(&priv->counter, priv->modulus - 1);
return nft_validate_register_store(ctx, priv->dreg, NULL,
NFT_DATA_VALUE, sizeof(u32));
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index b2f8861..98fb5d7 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -148,7 +148,6 @@ static int nft_payload_dump(struct sk_buff *skb, const struct nft_expr *expr)
return -1;
}
-static struct nft_expr_type nft_payload_type;
static const struct nft_expr_ops nft_payload_ops = {
.type = &nft_payload_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_payload)),
@@ -320,20 +319,10 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
return &nft_payload_ops;
}
-static struct nft_expr_type nft_payload_type __read_mostly = {
+struct nft_expr_type nft_payload_type __read_mostly = {
.name = "payload",
.select_ops = nft_payload_select_ops,
.policy = nft_payload_policy,
.maxattr = NFTA_PAYLOAD_MAX,
.owner = THIS_MODULE,
};
-
-int __init nft_payload_module_init(void)
-{
- return nft_register_expr(&nft_payload_type);
-}
-
-void nft_payload_module_exit(void)
-{
- nft_unregister_expr(&nft_payload_type);
-}
diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c
index 393d359..3e19fa1 100644
--- a/net/netfilter/nft_queue.c
+++ b/net/netfilter/nft_queue.c
@@ -43,7 +43,7 @@ static void nft_queue_eval(const struct nft_expr *expr,
queue = priv->queuenum + cpu % priv->queues_total;
} else {
queue = nfqueue_hash(pkt->skb, queue,
- priv->queues_total, pkt->pf,
+ priv->queues_total, nft_pf(pkt),
jhash_initval);
}
}
diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c
index c6d5358..0090626 100644
--- a/net/netfilter/nft_range.c
+++ b/net/netfilter/nft_range.c
@@ -28,22 +28,20 @@ static void nft_range_eval(const struct nft_expr *expr,
const struct nft_pktinfo *pkt)
{
const struct nft_range_expr *priv = nft_expr_priv(expr);
- bool mismatch;
int d1, d2;
d1 = memcmp(®s->data[priv->sreg], &priv->data_from, priv->len);
d2 = memcmp(®s->data[priv->sreg], &priv->data_to, priv->len);
switch (priv->op) {
case NFT_RANGE_EQ:
- mismatch = (d1 < 0 || d2 > 0);
+ if (d1 < 0 || d2 > 0)
+ regs->verdict.code = NFT_BREAK;
break;
case NFT_RANGE_NEQ:
- mismatch = (d1 >= 0 && d2 <= 0);
+ if (d1 >= 0 && d2 <= 0)
+ regs->verdict.code = NFT_BREAK;
break;
}
-
- if (mismatch)
- regs->verdict.code = NFT_BREAK;
}
static const struct nla_policy nft_range_policy[NFTA_RANGE_MAX + 1] = {
@@ -59,6 +57,7 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr
struct nft_range_expr *priv = nft_expr_priv(expr);
struct nft_data_desc desc_from, desc_to;
int err;
+ u32 op;
err = nft_data_init(NULL, &priv->data_from, sizeof(priv->data_from),
&desc_from, tb[NFTA_RANGE_FROM_DATA]);
@@ -80,7 +79,20 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr
if (err < 0)
goto err2;
- priv->op = ntohl(nla_get_be32(tb[NFTA_RANGE_OP]));
+ err = nft_parse_u32_check(tb[NFTA_RANGE_OP], U8_MAX, &op);
+ if (err < 0)
+ goto err2;
+
+ switch (op) {
+ case NFT_RANGE_EQ:
+ case NFT_RANGE_NEQ:
+ break;
+ default:
+ err = -EINVAL;
+ goto err2;
+ }
+
+ priv->op = op;
priv->len = desc_from.len;
return 0;
err2:
@@ -110,7 +122,6 @@ static int nft_range_dump(struct sk_buff *skb, const struct nft_expr *expr)
return -1;
}
-static struct nft_expr_type nft_range_type;
static const struct nft_expr_ops nft_range_ops = {
.type = &nft_range_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_range_expr)),
@@ -119,20 +130,10 @@ static const struct nft_expr_ops nft_range_ops = {
.dump = nft_range_dump,
};
-static struct nft_expr_type nft_range_type __read_mostly = {
+struct nft_expr_type nft_range_type __read_mostly = {
.name = "range",
.ops = &nft_range_ops,
.policy = nft_range_policy,
.maxattr = NFTA_RANGE_MAX,
.owner = THIS_MODULE,
};
-
-int __init nft_range_module_init(void)
-{
- return nft_register_expr(&nft_range_type);
-}
-
-void nft_range_module_exit(void)
-{
- nft_unregister_expr(&nft_range_type);
-}
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
index e79d9ca..9e90a02 100644
--- a/net/netfilter/nft_reject_inet.c
+++ b/net/netfilter/nft_reject_inet.c
@@ -23,36 +23,36 @@ static void nft_reject_inet_eval(const struct nft_expr *expr,
{
struct nft_reject *priv = nft_expr_priv(expr);
- switch (pkt->pf) {
+ switch (nft_pf(pkt)) {
case NFPROTO_IPV4:
switch (priv->type) {
case NFT_REJECT_ICMP_UNREACH:
nf_send_unreach(pkt->skb, priv->icmp_code,
- pkt->hook);
+ nft_hook(pkt));
break;
case NFT_REJECT_TCP_RST:
- nf_send_reset(pkt->net, pkt->skb, pkt->hook);
+ nf_send_reset(nft_net(pkt), pkt->skb, nft_hook(pkt));
break;
case NFT_REJECT_ICMPX_UNREACH:
nf_send_unreach(pkt->skb,
nft_reject_icmp_code(priv->icmp_code),
- pkt->hook);
+ nft_hook(pkt));
break;
}
break;
case NFPROTO_IPV6:
switch (priv->type) {
case NFT_REJECT_ICMP_UNREACH:
- nf_send_unreach6(pkt->net, pkt->skb, priv->icmp_code,
- pkt->hook);
+ nf_send_unreach6(nft_net(pkt), pkt->skb,
+ priv->icmp_code, nft_hook(pkt));
break;
case NFT_REJECT_TCP_RST:
- nf_send_reset6(pkt->net, pkt->skb, pkt->hook);
+ nf_send_reset6(nft_net(pkt), pkt->skb, nft_hook(pkt));
break;
case NFT_REJECT_ICMPX_UNREACH:
- nf_send_unreach6(pkt->net, pkt->skb,
+ nf_send_unreach6(nft_net(pkt), pkt->skb,
nft_reject_icmpv6_code(priv->icmp_code),
- pkt->hook);
+ nft_hook(pkt));
break;
}
break;
diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c
new file mode 100644
index 0000000..d3eb640
--- /dev/null
+++ b/net/netfilter/nft_rt.c
@@ -0,0 +1,153 @@
+/*
+ * Copyright (c) 2016 Anders K. Pedersen <akp@cohaesio.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/dst.h>
+#include <net/ip6_route.h>
+#include <net/route.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+
+struct nft_rt {
+ enum nft_rt_keys key:8;
+ enum nft_registers dreg:8;
+};
+
+void nft_rt_get_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ const struct nft_rt *priv = nft_expr_priv(expr);
+ const struct sk_buff *skb = pkt->skb;
+ u32 *dest = ®s->data[priv->dreg];
+ const struct dst_entry *dst;
+
+ dst = skb_dst(skb);
+ if (!dst)
+ goto err;
+
+ switch (priv->key) {
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ case NFT_RT_CLASSID:
+ *dest = dst->tclassid;
+ break;
+#endif
+ case NFT_RT_NEXTHOP4:
+ if (nft_pf(pkt) != NFPROTO_IPV4)
+ goto err;
+
+ *dest = rt_nexthop((const struct rtable *)dst,
+ ip_hdr(skb)->daddr);
+ break;
+ case NFT_RT_NEXTHOP6:
+ if (nft_pf(pkt) != NFPROTO_IPV6)
+ goto err;
+
+ memcpy(dest, rt6_nexthop((struct rt6_info *)dst,
+ &ipv6_hdr(skb)->daddr),
+ sizeof(struct in6_addr));
+ break;
+ default:
+ WARN_ON(1);
+ goto err;
+ }
+ return;
+
+err:
+ regs->verdict.code = NFT_BREAK;
+}
+
+const struct nla_policy nft_rt_policy[NFTA_RT_MAX + 1] = {
+ [NFTA_RT_DREG] = { .type = NLA_U32 },
+ [NFTA_RT_KEY] = { .type = NLA_U32 },
+};
+
+int nft_rt_get_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_rt *priv = nft_expr_priv(expr);
+ unsigned int len;
+
+ if (tb[NFTA_RT_KEY] == NULL ||
+ tb[NFTA_RT_DREG] == NULL)
+ return -EINVAL;
+
+ priv->key = ntohl(nla_get_be32(tb[NFTA_RT_KEY]));
+ switch (priv->key) {
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ case NFT_RT_CLASSID:
+#endif
+ case NFT_RT_NEXTHOP4:
+ len = sizeof(u32);
+ break;
+ case NFT_RT_NEXTHOP6:
+ len = sizeof(struct in6_addr);
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ priv->dreg = nft_parse_register(tb[NFTA_RT_DREG]);
+ return nft_validate_register_store(ctx, priv->dreg, NULL,
+ NFT_DATA_VALUE, len);
+}
+
+int nft_rt_get_dump(struct sk_buff *skb,
+ const struct nft_expr *expr)
+{
+ const struct nft_rt *priv = nft_expr_priv(expr);
+
+ if (nla_put_be32(skb, NFTA_RT_KEY, htonl(priv->key)))
+ goto nla_put_failure;
+ if (nft_dump_register(skb, NFTA_RT_DREG, priv->dreg))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static struct nft_expr_type nft_rt_type;
+static const struct nft_expr_ops nft_rt_get_ops = {
+ .type = &nft_rt_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_rt)),
+ .eval = nft_rt_get_eval,
+ .init = nft_rt_get_init,
+ .dump = nft_rt_get_dump,
+};
+
+static struct nft_expr_type nft_rt_type __read_mostly = {
+ .name = "rt",
+ .ops = &nft_rt_get_ops,
+ .policy = nft_rt_policy,
+ .maxattr = NFTA_RT_MAX,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_rt_module_init(void)
+{
+ return nft_register_expr(&nft_rt_type);
+}
+
+static void __exit nft_rt_module_exit(void)
+{
+ nft_unregister_expr(&nft_rt_type);
+}
+
+module_init(nft_rt_module_init);
+module_exit(nft_rt_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Anders K. Pedersen <akp@cohaesio.com>");
+MODULE_ALIAS_NFT_EXPR("rt");
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 3794cb2..a3dface 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -98,7 +98,7 @@ static bool nft_hash_update(struct nft_set *set, const u32 *key,
const struct nft_set_ext **ext)
{
struct nft_hash *priv = nft_set_priv(set);
- struct nft_hash_elem *he;
+ struct nft_hash_elem *he, *prev;
struct nft_hash_cmp_arg arg = {
.genmask = NFT_GENMASK_ANY,
.set = set,
@@ -112,15 +112,24 @@ static bool nft_hash_update(struct nft_set *set, const u32 *key,
he = new(set, expr, regs);
if (he == NULL)
goto err1;
- if (rhashtable_lookup_insert_key(&priv->ht, &arg, &he->node,
- nft_hash_params))
+
+ prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node,
+ nft_hash_params);
+ if (IS_ERR(prev))
goto err2;
+
+ /* Another cpu may race to insert the element with the same key */
+ if (prev) {
+ nft_set_elem_destroy(set, he, true);
+ he = prev;
+ }
+
out:
*ext = &he->ext;
return true;
err2:
- nft_set_elem_destroy(set, he);
+ nft_set_elem_destroy(set, he, true);
err1:
return false;
}
@@ -332,7 +341,7 @@ static int nft_hash_init(const struct nft_set *set,
static void nft_hash_elem_destroy(void *ptr, void *arg)
{
- nft_set_elem_destroy((const struct nft_set *)arg, ptr);
+ nft_set_elem_destroy((const struct nft_set *)arg, ptr, true);
}
static void nft_hash_destroy(const struct nft_set *set)
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 38b5bda..36493a7 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -266,7 +266,7 @@ static void nft_rbtree_destroy(const struct nft_set *set)
while ((node = priv->root.rb_node) != NULL) {
rb_erase(node, &priv->root);
rbe = rb_entry(node, struct nft_rbtree_elem, node);
- nft_set_elem_destroy(set, rbe);
+ nft_set_elem_destroy(set, rbe, true);
}
}
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index e0aa7c1..ad818e5 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -982,7 +982,7 @@ void xt_free_table_info(struct xt_table_info *info)
}
EXPORT_SYMBOL(xt_free_table_info);
-/* Find table by name, grabs mutex & ref. Returns ERR_PTR() on error. */
+/* Find table by name, grabs mutex & ref. Returns NULL on error. */
struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
const char *name)
{
@@ -1513,7 +1513,7 @@ xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn)
if (!num_hooks)
return ERR_PTR(-EINVAL);
- ops = kmalloc(sizeof(*ops) * num_hooks, GFP_KERNEL);
+ ops = kcalloc(num_hooks, sizeof(*ops), GFP_KERNEL);
if (ops == NULL)
return ERR_PTR(-ENOMEM);
diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c
index 4973cbd..19247a17 100644
--- a/net/netfilter/xt_AUDIT.c
+++ b/net/netfilter/xt_AUDIT.c
@@ -132,9 +132,9 @@ audit_tg(struct sk_buff *skb, const struct xt_action_param *par)
goto errout;
audit_log_format(ab, "action=%hhu hook=%u len=%u inif=%s outif=%s",
- info->type, par->hooknum, skb->len,
- par->in ? par->in->name : "?",
- par->out ? par->out->name : "?");
+ info->type, xt_hooknum(par), skb->len,
+ xt_in(par) ? xt_inname(par) : "?",
+ xt_out(par) ? xt_outname(par) : "?");
if (skb->mark)
audit_log_format(ab, " mark=%#x", skb->mark);
@@ -144,7 +144,7 @@ audit_tg(struct sk_buff *skb, const struct xt_action_param *par)
eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest,
ntohs(eth_hdr(skb)->h_proto));
- if (par->family == NFPROTO_BRIDGE) {
+ if (xt_family(par) == NFPROTO_BRIDGE) {
switch (eth_hdr(skb)->h_proto) {
case htons(ETH_P_IP):
audit_ip4(ab, skb);
@@ -157,7 +157,7 @@ audit_tg(struct sk_buff *skb, const struct xt_action_param *par)
}
}
- switch (par->family) {
+ switch (xt_family(par)) {
case NFPROTO_IPV4:
audit_ip4(ab, skb);
break;
diff --git a/net/netfilter/xt_LOG.c b/net/netfilter/xt_LOG.c
index 1763ab8..c3b2017e 100644
--- a/net/netfilter/xt_LOG.c
+++ b/net/netfilter/xt_LOG.c
@@ -32,15 +32,15 @@ static unsigned int
log_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_log_info *loginfo = par->targinfo;
+ struct net *net = xt_net(par);
struct nf_loginfo li;
- struct net *net = par->net;
li.type = NF_LOG_TYPE_LOG;
li.u.log.level = loginfo->level;
li.u.log.logflags = loginfo->logflags;
- nf_log_packet(net, par->family, par->hooknum, skb, par->in, par->out,
- &li, "%s", loginfo->prefix);
+ nf_log_packet(net, xt_family(par), xt_hooknum(par), skb, xt_in(par),
+ xt_out(par), &li, "%s", loginfo->prefix);
return XT_CONTINUE;
}
diff --git a/net/netfilter/xt_NETMAP.c b/net/netfilter/xt_NETMAP.c
index b253e07..94d0b54 100644
--- a/net/netfilter/xt_NETMAP.c
+++ b/net/netfilter/xt_NETMAP.c
@@ -33,8 +33,8 @@ netmap_tg6(struct sk_buff *skb, const struct xt_action_param *par)
netmask.ip6[i] = ~(range->min_addr.ip6[i] ^
range->max_addr.ip6[i]);
- if (par->hooknum == NF_INET_PRE_ROUTING ||
- par->hooknum == NF_INET_LOCAL_OUT)
+ if (xt_hooknum(par) == NF_INET_PRE_ROUTING ||
+ xt_hooknum(par) == NF_INET_LOCAL_OUT)
new_addr.in6 = ipv6_hdr(skb)->daddr;
else
new_addr.in6 = ipv6_hdr(skb)->saddr;
@@ -51,7 +51,7 @@ netmap_tg6(struct sk_buff *skb, const struct xt_action_param *par)
newrange.min_proto = range->min_proto;
newrange.max_proto = range->max_proto;
- return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(par->hooknum));
+ return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(xt_hooknum(par)));
}
static int netmap_tg6_checkentry(const struct xt_tgchk_param *par)
@@ -72,16 +72,16 @@ netmap_tg4(struct sk_buff *skb, const struct xt_action_param *par)
const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo;
struct nf_nat_range newrange;
- NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
- par->hooknum == NF_INET_POST_ROUTING ||
- par->hooknum == NF_INET_LOCAL_OUT ||
- par->hooknum == NF_INET_LOCAL_IN);
+ NF_CT_ASSERT(xt_hooknum(par) == NF_INET_PRE_ROUTING ||
+ xt_hooknum(par) == NF_INET_POST_ROUTING ||
+ xt_hooknum(par) == NF_INET_LOCAL_OUT ||
+ xt_hooknum(par) == NF_INET_LOCAL_IN);
ct = nf_ct_get(skb, &ctinfo);
netmask = ~(mr->range[0].min_ip ^ mr->range[0].max_ip);
- if (par->hooknum == NF_INET_PRE_ROUTING ||
- par->hooknum == NF_INET_LOCAL_OUT)
+ if (xt_hooknum(par) == NF_INET_PRE_ROUTING ||
+ xt_hooknum(par) == NF_INET_LOCAL_OUT)
new_ip = ip_hdr(skb)->daddr & ~netmask;
else
new_ip = ip_hdr(skb)->saddr & ~netmask;
@@ -96,7 +96,7 @@ netmap_tg4(struct sk_buff *skb, const struct xt_action_param *par)
newrange.max_proto = mr->range[0].max;
/* Hand modified range to generic setup. */
- return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(par->hooknum));
+ return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(xt_hooknum(par)));
}
static int netmap_tg4_check(const struct xt_tgchk_param *par)
diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c
index 018eed7..c7f8958 100644
--- a/net/netfilter/xt_NFLOG.c
+++ b/net/netfilter/xt_NFLOG.c
@@ -25,19 +25,20 @@ static unsigned int
nflog_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_nflog_info *info = par->targinfo;
+ struct net *net = xt_net(par);
struct nf_loginfo li;
- struct net *net = par->net;
li.type = NF_LOG_TYPE_ULOG;
li.u.ulog.copy_len = info->len;
li.u.ulog.group = info->group;
li.u.ulog.qthreshold = info->threshold;
+ li.u.ulog.flags = 0;
if (info->flags & XT_NFLOG_F_COPY_LEN)
li.u.ulog.flags |= NF_LOG_F_COPY_LEN;
- nfulnl_log_packet(net, par->family, par->hooknum, skb, par->in,
- par->out, &li, info->prefix);
+ nfulnl_log_packet(net, xt_family(par), xt_hooknum(par), skb,
+ xt_in(par), xt_out(par), &li, info->prefix);
return XT_CONTINUE;
}
diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c
index 8f1779f..a360b99 100644
--- a/net/netfilter/xt_NFQUEUE.c
+++ b/net/netfilter/xt_NFQUEUE.c
@@ -43,7 +43,7 @@ nfqueue_tg_v1(struct sk_buff *skb, const struct xt_action_param *par)
if (info->queues_total > 1) {
queue = nfqueue_hash(skb, queue, info->queues_total,
- par->family, jhash_initval);
+ xt_family(par), jhash_initval);
}
return NF_QUEUE_NR(queue);
}
@@ -98,7 +98,7 @@ nfqueue_tg_v3(struct sk_buff *skb, const struct xt_action_param *par)
queue = info->queuenum + cpu % info->queues_total;
} else {
queue = nfqueue_hash(skb, queue, info->queues_total,
- par->family, jhash_initval);
+ xt_family(par), jhash_initval);
}
}
diff --git a/net/netfilter/xt_REDIRECT.c b/net/netfilter/xt_REDIRECT.c
index 03f0b37..651dce6 100644
--- a/net/netfilter/xt_REDIRECT.c
+++ b/net/netfilter/xt_REDIRECT.c
@@ -31,7 +31,7 @@
static unsigned int
redirect_tg6(struct sk_buff *skb, const struct xt_action_param *par)
{
- return nf_nat_redirect_ipv6(skb, par->targinfo, par->hooknum);
+ return nf_nat_redirect_ipv6(skb, par->targinfo, xt_hooknum(par));
}
static int redirect_tg6_checkentry(const struct xt_tgchk_param *par)
@@ -62,7 +62,7 @@ static int redirect_tg4_check(const struct xt_tgchk_param *par)
static unsigned int
redirect_tg4(struct sk_buff *skb, const struct xt_action_param *par)
{
- return nf_nat_redirect_ipv4(skb, par->targinfo, par->hooknum);
+ return nf_nat_redirect_ipv4(skb, par->targinfo, xt_hooknum(par));
}
static struct xt_target redirect_tg_reg[] __read_mostly = {
diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c
index 872db2d..27241a7 100644
--- a/net/netfilter/xt_TCPMSS.c
+++ b/net/netfilter/xt_TCPMSS.c
@@ -108,7 +108,7 @@ tcpmss_mangle_packet(struct sk_buff *skb,
return -1;
if (info->mss == XT_TCPMSS_CLAMP_PMTU) {
- struct net *net = par->net;
+ struct net *net = xt_net(par);
unsigned int in_mtu = tcpmss_reverse_mtu(net, skb, family);
unsigned int min_mtu = min(dst_mtu(skb_dst(skb)), in_mtu);
@@ -172,7 +172,7 @@ tcpmss_mangle_packet(struct sk_buff *skb,
* length IPv6 header of 60, ergo the default MSS value is 1220
* Since no MSS was provided, we must use the default values
*/
- if (par->family == NFPROTO_IPV4)
+ if (xt_family(par) == NFPROTO_IPV4)
newmss = min(newmss, (u16)536);
else
newmss = min(newmss, (u16)1220);
diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c
index 0471db4..1c57ace 100644
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -33,7 +33,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par)
const struct xt_tee_tginfo *info = par->targinfo;
int oif = info->priv ? info->priv->oif : 0;
- nf_dup_ipv4(par->net, skb, par->hooknum, &info->gw.in, oif);
+ nf_dup_ipv4(xt_net(par), skb, xt_hooknum(par), &info->gw.in, oif);
return XT_CONTINUE;
}
@@ -45,7 +45,7 @@ tee_tg6(struct sk_buff *skb, const struct xt_action_param *par)
const struct xt_tee_tginfo *info = par->targinfo;
int oif = info->priv ? info->priv->oif : 0;
- nf_dup_ipv6(par->net, skb, par->hooknum, &info->gw.in6, oif);
+ nf_dup_ipv6(xt_net(par), skb, xt_hooknum(par), &info->gw.in6, oif);
return XT_CONTINUE;
}
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 663c4c3..dbd72cc 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -364,7 +364,8 @@ tproxy_tg4_v0(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_tproxy_target_info *tgi = par->targinfo;
- return tproxy_tg4(par->net, skb, tgi->laddr, tgi->lport, tgi->mark_mask, tgi->mark_value);
+ return tproxy_tg4(xt_net(par), skb, tgi->laddr, tgi->lport,
+ tgi->mark_mask, tgi->mark_value);
}
static unsigned int
@@ -372,7 +373,8 @@ tproxy_tg4_v1(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_tproxy_target_info_v1 *tgi = par->targinfo;
- return tproxy_tg4(par->net, skb, tgi->laddr.ip, tgi->lport, tgi->mark_mask, tgi->mark_value);
+ return tproxy_tg4(xt_net(par), skb, tgi->laddr.ip, tgi->lport,
+ tgi->mark_mask, tgi->mark_value);
}
#ifdef XT_TPROXY_HAVE_IPV6
@@ -442,7 +444,7 @@ tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff,
* to a listener socket if there's one */
struct sock *sk2;
- sk2 = nf_tproxy_get_sock_v6(par->net, skb, thoff, hp, tproto,
+ sk2 = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, tproto,
&iph->saddr,
tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr),
hp->source,
@@ -485,10 +487,10 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
* addresses, this happens if the redirect already happened
* and the current packet belongs to an already established
* connection */
- sk = nf_tproxy_get_sock_v6(par->net, skb, thoff, hp, tproto,
+ sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, tproto,
&iph->saddr, &iph->daddr,
hp->source, hp->dest,
- par->in, NFT_LOOKUP_ESTABLISHED);
+ xt_in(par), NFT_LOOKUP_ESTABLISHED);
laddr = tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr);
lport = tgi->lport ? tgi->lport : hp->dest;
@@ -500,10 +502,10 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
else if (!sk)
/* no there's no established connection, check if
* there's a listener on the redirected addr/port */
- sk = nf_tproxy_get_sock_v6(par->net, skb, thoff, hp,
+ sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp,
tproto, &iph->saddr, laddr,
hp->source, lport,
- par->in, NFT_LOOKUP_LISTENER);
+ xt_in(par), NFT_LOOKUP_LISTENER);
/* NOTE: assign_sock consumes our sk reference */
if (sk && tproxy_sk_is_transparent(sk)) {
diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c
index 11d6091..e329dab 100644
--- a/net/netfilter/xt_addrtype.c
+++ b/net/netfilter/xt_addrtype.c
@@ -125,7 +125,7 @@ static inline bool match_type(struct net *net, const struct net_device *dev,
static bool
addrtype_mt_v0(const struct sk_buff *skb, struct xt_action_param *par)
{
- struct net *net = par->net;
+ struct net *net = xt_net(par);
const struct xt_addrtype_info *info = par->matchinfo;
const struct iphdr *iph = ip_hdr(skb);
bool ret = true;
@@ -143,19 +143,19 @@ addrtype_mt_v0(const struct sk_buff *skb, struct xt_action_param *par)
static bool
addrtype_mt_v1(const struct sk_buff *skb, struct xt_action_param *par)
{
- struct net *net = par->net;
+ struct net *net = xt_net(par);
const struct xt_addrtype_info_v1 *info = par->matchinfo;
const struct iphdr *iph;
const struct net_device *dev = NULL;
bool ret = true;
if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_IN)
- dev = par->in;
+ dev = xt_in(par);
else if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT)
- dev = par->out;
+ dev = xt_out(par);
#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
- if (par->family == NFPROTO_IPV6)
+ if (xt_family(par) == NFPROTO_IPV6)
return addrtype_mt6(net, dev, skb, info);
#endif
iph = ip_hdr(skb);
diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c
index 96fa26b..9a9884a 100644
--- a/net/netfilter/xt_cluster.c
+++ b/net/netfilter/xt_cluster.c
@@ -112,7 +112,7 @@ xt_cluster_mt(const struct sk_buff *skb, struct xt_action_param *par)
* know, matches should not alter packets, but we are doing this here
* because we would need to add a PKTTYPE target for this sole purpose.
*/
- if (!xt_cluster_is_multicast_addr(skb, par->family) &&
+ if (!xt_cluster_is_multicast_addr(skb, xt_family(par)) &&
skb->pkt_type == PACKET_MULTICAST) {
pskb->pkt_type = PACKET_HOST;
}
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index b6dc322..bb38453 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -317,7 +317,7 @@ static int count_them(struct net *net,
static bool
connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
- struct net *net = par->net;
+ struct net *net = xt_net(par);
const struct xt_connlimit_info *info = par->matchinfo;
union nf_inet_addr addr;
struct nf_conntrack_tuple tuple;
@@ -332,11 +332,11 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
tuple_ptr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
zone = nf_ct_zone(ct);
} else if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
- par->family, net, &tuple)) {
+ xt_family(par), net, &tuple)) {
goto hotdrop;
}
- if (par->family == NFPROTO_IPV6) {
+ if (xt_family(par) == NFPROTO_IPV6) {
const struct ipv6hdr *iph = ipv6_hdr(skb);
memcpy(&addr.ip6, (info->flags & XT_CONNLIMIT_DADDR) ?
&iph->daddr : &iph->saddr, sizeof(addr.ip6));
@@ -347,7 +347,7 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
}
connections = count_them(net, info->data, tuple_ptr, &addr,
- &info->mask, par->family, zone);
+ &info->mask, xt_family(par), zone);
if (connections == 0)
/* kmalloc failed, drop it entirely */
goto hotdrop;
diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c
index 69f78e9..b83e158 100644
--- a/net/netfilter/xt_connmark.c
+++ b/net/netfilter/xt_connmark.c
@@ -44,7 +44,7 @@ connmark_tg(struct sk_buff *skb, const struct xt_action_param *par)
u_int32_t newmark;
ct = nf_ct_get(skb, &ctinfo);
- if (ct == NULL)
+ if (ct == NULL || nf_ct_is_untracked(ct))
return XT_CONTINUE;
switch (info->mode) {
@@ -97,7 +97,7 @@ connmark_mt(const struct sk_buff *skb, struct xt_action_param *par)
const struct nf_conn *ct;
ct = nf_ct_get(skb, &ctinfo);
- if (ct == NULL)
+ if (ct == NULL || nf_ct_is_untracked(ct))
return false;
return ((ct->mark & info->mask) == info->mark) ^ info->invert;
diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c
index a3b8f69..2dea15e 100644
--- a/net/netfilter/xt_conntrack.c
+++ b/net/netfilter/xt_conntrack.c
@@ -200,22 +200,22 @@ conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par,
return false;
if (info->match_flags & XT_CONNTRACK_ORIGSRC)
- if (conntrack_mt_origsrc(ct, info, par->family) ^
+ if (conntrack_mt_origsrc(ct, info, xt_family(par)) ^
!(info->invert_flags & XT_CONNTRACK_ORIGSRC))
return false;
if (info->match_flags & XT_CONNTRACK_ORIGDST)
- if (conntrack_mt_origdst(ct, info, par->family) ^
+ if (conntrack_mt_origdst(ct, info, xt_family(par)) ^
!(info->invert_flags & XT_CONNTRACK_ORIGDST))
return false;
if (info->match_flags & XT_CONNTRACK_REPLSRC)
- if (conntrack_mt_replsrc(ct, info, par->family) ^
+ if (conntrack_mt_replsrc(ct, info, xt_family(par)) ^
!(info->invert_flags & XT_CONNTRACK_REPLSRC))
return false;
if (info->match_flags & XT_CONNTRACK_REPLDST)
- if (conntrack_mt_repldst(ct, info, par->family) ^
+ if (conntrack_mt_repldst(ct, info, xt_family(par)) ^
!(info->invert_flags & XT_CONNTRACK_REPLDST))
return false;
diff --git a/net/netfilter/xt_devgroup.c b/net/netfilter/xt_devgroup.c
index d9202cd..96ebe1c 100644
--- a/net/netfilter/xt_devgroup.c
+++ b/net/netfilter/xt_devgroup.c
@@ -24,12 +24,12 @@ static bool devgroup_mt(const struct sk_buff *skb, struct xt_action_param *par)
const struct xt_devgroup_info *info = par->matchinfo;
if (info->flags & XT_DEVGROUP_MATCH_SRC &&
- (((info->src_group ^ par->in->group) & info->src_mask ? 1 : 0) ^
+ (((info->src_group ^ xt_in(par)->group) & info->src_mask ? 1 : 0) ^
((info->flags & XT_DEVGROUP_INVERT_SRC) ? 1 : 0)))
return false;
if (info->flags & XT_DEVGROUP_MATCH_DST &&
- (((info->dst_group ^ par->out->group) & info->dst_mask ? 1 : 0) ^
+ (((info->dst_group ^ xt_out(par)->group) & info->dst_mask ? 1 : 0) ^
((info->flags & XT_DEVGROUP_INVERT_DST) ? 1 : 0)))
return false;
diff --git a/net/netfilter/xt_dscp.c b/net/netfilter/xt_dscp.c
index 64670fc..236ac80 100644
--- a/net/netfilter/xt_dscp.c
+++ b/net/netfilter/xt_dscp.c
@@ -58,7 +58,7 @@ static bool tos_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_tos_match_info *info = par->matchinfo;
- if (par->family == NFPROTO_IPV4)
+ if (xt_family(par) == NFPROTO_IPV4)
return ((ip_hdr(skb)->tos & info->tos_mask) ==
info->tos_value) ^ !!info->invert;
else
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 2fab0c6..1006340 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -49,7 +49,7 @@ struct hashlimit_net {
struct proc_dir_entry *ip6t_hashlimit;
};
-static int hashlimit_net_id;
+static unsigned int hashlimit_net_id;
static inline struct hashlimit_net *hashlimit_pernet(struct net *net)
{
return net_generic(net, hashlimit_net_id);
@@ -431,7 +431,7 @@ static void htable_put(struct xt_hashlimit_htable *hinfo)
CREDITS_PER_JIFFY*HZ*60*60*24 < 2^32 ie.
*/
#define MAX_CPJ_v1 (0xFFFFFFFF / (HZ*60*60*24))
-#define MAX_CPJ (0xFFFFFFFFFFFFFFFF / (HZ*60*60*24))
+#define MAX_CPJ (0xFFFFFFFFFFFFFFFFULL / (HZ*60*60*24))
/* Repeated shift and or gives us all 1s, final shift and add 1 gives
* us the power of 2 below the theoretical max, so GCC simply does a
@@ -473,7 +473,7 @@ static u64 user2credits(u64 user, int revision)
return div64_u64(user * HZ * CREDITS_PER_JIFFY_v1,
XT_HASHLIMIT_SCALE);
} else {
- if (user > 0xFFFFFFFFFFFFFFFF / (HZ*CREDITS_PER_JIFFY))
+ if (user > 0xFFFFFFFFFFFFFFFFULL / (HZ*CREDITS_PER_JIFFY))
return div64_u64(user, XT_HASHLIMIT_SCALE_v2)
* HZ * CREDITS_PER_JIFFY;
diff --git a/net/netfilter/xt_ipcomp.c b/net/netfilter/xt_ipcomp.c
index 89d5310..000e703 100644
--- a/net/netfilter/xt_ipcomp.c
+++ b/net/netfilter/xt_ipcomp.c
@@ -26,6 +26,8 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Fan Du <fan.du@windriver.com>");
MODULE_DESCRIPTION("Xtables: IPv4/6 IPsec-IPComp SPI match");
+MODULE_ALIAS("ipt_ipcomp");
+MODULE_ALIAS("ip6t_ipcomp");
/* Returns 1 if the spi is matched by the range, 0 otherwise */
static inline bool
diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c
index 71a9d95..0fdc890 100644
--- a/net/netfilter/xt_ipvs.c
+++ b/net/netfilter/xt_ipvs.c
@@ -48,9 +48,9 @@ static bool
ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_ipvs_mtinfo *data = par->matchinfo;
- struct netns_ipvs *ipvs = net_ipvs(par->net);
+ struct netns_ipvs *ipvs = net_ipvs(xt_net(par));
/* ipvs_mt_check ensures that family is only NFPROTO_IPV[46]. */
- const u_int8_t family = par->family;
+ const u_int8_t family = xt_family(par);
struct ip_vs_iphdr iph;
struct ip_vs_protocol *pp;
struct ip_vs_conn *cp;
diff --git a/net/netfilter/xt_multiport.c b/net/netfilter/xt_multiport.c
index ac1d3c3..ec06fb1 100644
--- a/net/netfilter/xt_multiport.c
+++ b/net/netfilter/xt_multiport.c
@@ -42,29 +42,31 @@ ports_match_v1(const struct xt_multiport_v1 *minfo,
e = minfo->ports[++i];
pr_debug("src or dst matches with %d-%d?\n", s, e);
- if (minfo->flags == XT_MULTIPORT_SOURCE
- && src >= s && src <= e)
- return true ^ minfo->invert;
- if (minfo->flags == XT_MULTIPORT_DESTINATION
- && dst >= s && dst <= e)
- return true ^ minfo->invert;
- if (minfo->flags == XT_MULTIPORT_EITHER
- && ((dst >= s && dst <= e)
- || (src >= s && src <= e)))
- return true ^ minfo->invert;
+ switch (minfo->flags) {
+ case XT_MULTIPORT_SOURCE:
+ return (src >= s && src <= e) ^ minfo->invert;
+ case XT_MULTIPORT_DESTINATION:
+ return (dst >= s && dst <= e) ^ minfo->invert;
+ case XT_MULTIPORT_EITHER:
+ return ((dst >= s && dst <= e) ||
+ (src >= s && src <= e)) ^ minfo->invert;
+ default:
+ break;
+ }
} else {
/* exact port matching */
pr_debug("src or dst matches with %d?\n", s);
- if (minfo->flags == XT_MULTIPORT_SOURCE
- && src == s)
- return true ^ minfo->invert;
- if (minfo->flags == XT_MULTIPORT_DESTINATION
- && dst == s)
- return true ^ minfo->invert;
- if (minfo->flags == XT_MULTIPORT_EITHER
- && (src == s || dst == s))
- return true ^ minfo->invert;
+ switch (minfo->flags) {
+ case XT_MULTIPORT_SOURCE:
+ return (src == s) ^ minfo->invert;
+ case XT_MULTIPORT_DESTINATION:
+ return (dst == s) ^ minfo->invert;
+ case XT_MULTIPORT_EITHER:
+ return (src == s || dst == s) ^ minfo->invert;
+ default:
+ break;
+ }
}
}
diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c
index cf32759..cc0518f 100644
--- a/net/netfilter/xt_nfacct.c
+++ b/net/netfilter/xt_nfacct.c
@@ -26,7 +26,7 @@ static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par)
nfnl_acct_update(skb, info->nfacct);
- overquota = nfnl_acct_overquota(par->net, skb, info->nfacct);
+ overquota = nfnl_acct_overquota(xt_net(par), skb, info->nfacct);
return overquota == NFACCT_UNDERQUOTA ? false : true;
}
diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c
index 2455b69..c05fefc 100644
--- a/net/netfilter/xt_osf.c
+++ b/net/netfilter/xt_osf.c
@@ -201,7 +201,7 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p)
unsigned char opts[MAX_IPOPTLEN];
const struct xt_osf_finger *kf;
const struct xt_osf_user_finger *f;
- struct net *net = p->net;
+ struct net *net = xt_net(p);
if (!info)
return false;
@@ -326,8 +326,8 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p)
fcount++;
if (info->flags & XT_OSF_LOG)
- nf_log_packet(net, p->family, p->hooknum, skb,
- p->in, p->out, NULL,
+ nf_log_packet(net, xt_family(p), xt_hooknum(p), skb,
+ xt_in(p), xt_out(p), NULL,
"%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n",
f->genre, f->version, f->subtype,
&ip->saddr, ntohs(tcp->source),
@@ -341,8 +341,8 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p)
rcu_read_unlock();
if (!fcount && (info->flags & XT_OSF_LOG))
- nf_log_packet(net, p->family, p->hooknum, skb, p->in,
- p->out, NULL,
+ nf_log_packet(net, xt_family(p), xt_hooknum(p), skb, xt_in(p),
+ xt_out(p), NULL,
"Remote OS is not known: %pI4:%u -> %pI4:%u\n",
&ip->saddr, ntohs(tcp->source),
&ip->daddr, ntohs(tcp->dest));
diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c
index a20e731..16477df 100644
--- a/net/netfilter/xt_owner.c
+++ b/net/netfilter/xt_owner.c
@@ -63,7 +63,7 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par)
const struct xt_owner_match_info *info = par->matchinfo;
const struct file *filp;
struct sock *sk = skb_to_full_sk(skb);
- struct net *net = par->net;
+ struct net *net = xt_net(par);
if (sk == NULL || sk->sk_socket == NULL)
return (info->match ^ info->invert) == 0;
diff --git a/net/netfilter/xt_pkttype.c b/net/netfilter/xt_pkttype.c
index 5b645cb..57efb70 100644
--- a/net/netfilter/xt_pkttype.c
+++ b/net/netfilter/xt_pkttype.c
@@ -30,10 +30,10 @@ pkttype_mt(const struct sk_buff *skb, struct xt_action_param *par)
if (skb->pkt_type != PACKET_LOOPBACK)
type = skb->pkt_type;
- else if (par->family == NFPROTO_IPV4 &&
+ else if (xt_family(par) == NFPROTO_IPV4 &&
ipv4_is_multicast(ip_hdr(skb)->daddr))
type = PACKET_MULTICAST;
- else if (par->family == NFPROTO_IPV6 &&
+ else if (xt_family(par) == NFPROTO_IPV6 &&
ipv6_hdr(skb)->daddr.s6_addr[0] == 0xFF)
type = PACKET_MULTICAST;
else
diff --git a/net/netfilter/xt_policy.c b/net/netfilter/xt_policy.c
index f23e97b..2b4ab18 100644
--- a/net/netfilter/xt_policy.c
+++ b/net/netfilter/xt_policy.c
@@ -116,9 +116,9 @@ policy_mt(const struct sk_buff *skb, struct xt_action_param *par)
int ret;
if (info->flags & XT_POLICY_MATCH_IN)
- ret = match_policy_in(skb, info, par->family);
+ ret = match_policy_in(skb, info, xt_family(par));
else
- ret = match_policy_out(skb, info, par->family);
+ ret = match_policy_out(skb, info, xt_family(par));
if (ret < 0)
ret = info->flags & XT_POLICY_MATCH_NONE ? true : false;
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index e3b7a09..1d89a4e 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -95,7 +95,7 @@ struct recent_net {
#endif
};
-static int recent_net_id __read_mostly;
+static unsigned int recent_net_id __read_mostly;
static inline struct recent_net *recent_pernet(struct net *net)
{
@@ -236,7 +236,7 @@ static void recent_table_flush(struct recent_table *t)
static bool
recent_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
- struct net *net = par->net;
+ struct net *net = xt_net(par);
struct recent_net *recent_net = recent_pernet(net);
const struct xt_recent_mtinfo_v1 *info = par->matchinfo;
struct recent_table *t;
@@ -245,7 +245,7 @@ recent_mt(const struct sk_buff *skb, struct xt_action_param *par)
u_int8_t ttl;
bool ret = info->invert;
- if (par->family == NFPROTO_IPV4) {
+ if (xt_family(par) == NFPROTO_IPV4) {
const struct iphdr *iph = ip_hdr(skb);
if (info->side == XT_RECENT_DEST)
@@ -266,7 +266,7 @@ recent_mt(const struct sk_buff *skb, struct xt_action_param *par)
}
/* use TTL as seen before forwarding */
- if (par->out != NULL && skb->sk == NULL)
+ if (xt_out(par) != NULL && skb->sk == NULL)
ttl++;
spin_lock_bh(&recent_lock);
@@ -274,12 +274,12 @@ recent_mt(const struct sk_buff *skb, struct xt_action_param *par)
nf_inet_addr_mask(&addr, &addr_mask, &t->mask);
- e = recent_entry_lookup(t, &addr_mask, par->family,
+ e = recent_entry_lookup(t, &addr_mask, xt_family(par),
(info->check_set & XT_RECENT_TTL) ? ttl : 0);
if (e == NULL) {
if (!(info->check_set & XT_RECENT_SET))
goto out;
- e = recent_entry_init(t, &addr_mask, par->family, ttl);
+ e = recent_entry_init(t, &addr_mask, xt_family(par), ttl);
if (e == NULL)
par->hotdrop = true;
ret = !ret;
diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c
index 5669e5b..6428570 100644
--- a/net/netfilter/xt_set.c
+++ b/net/netfilter/xt_set.c
@@ -55,7 +55,7 @@ set_match_v0(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_set_info_match_v0 *info = par->matchinfo;
- ADT_OPT(opt, par->family, info->match_set.u.compat.dim,
+ ADT_OPT(opt, xt_family(par), info->match_set.u.compat.dim,
info->match_set.u.compat.flags, 0, UINT_MAX);
return match_set(info->match_set.index, skb, par, &opt,
@@ -118,7 +118,7 @@ set_match_v1(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_set_info_match_v1 *info = par->matchinfo;
- ADT_OPT(opt, par->family, info->match_set.dim,
+ ADT_OPT(opt, xt_family(par), info->match_set.dim,
info->match_set.flags, 0, UINT_MAX);
if (opt.flags & IPSET_RETURN_NOMATCH)
@@ -184,7 +184,7 @@ set_match_v3(const struct sk_buff *skb, struct xt_action_param *par)
const struct xt_set_info_match_v3 *info = par->matchinfo;
int ret;
- ADT_OPT(opt, par->family, info->match_set.dim,
+ ADT_OPT(opt, xt_family(par), info->match_set.dim,
info->match_set.flags, info->flags, UINT_MAX);
if (info->packets.op != IPSET_COUNTER_NONE ||
@@ -231,7 +231,7 @@ set_match_v4(const struct sk_buff *skb, struct xt_action_param *par)
const struct xt_set_info_match_v4 *info = par->matchinfo;
int ret;
- ADT_OPT(opt, par->family, info->match_set.dim,
+ ADT_OPT(opt, xt_family(par), info->match_set.dim,
info->match_set.flags, info->flags, UINT_MAX);
if (info->packets.op != IPSET_COUNTER_NONE ||
@@ -259,9 +259,9 @@ set_target_v0(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_set_info_target_v0 *info = par->targinfo;
- ADT_OPT(add_opt, par->family, info->add_set.u.compat.dim,
+ ADT_OPT(add_opt, xt_family(par), info->add_set.u.compat.dim,
info->add_set.u.compat.flags, 0, UINT_MAX);
- ADT_OPT(del_opt, par->family, info->del_set.u.compat.dim,
+ ADT_OPT(del_opt, xt_family(par), info->del_set.u.compat.dim,
info->del_set.u.compat.flags, 0, UINT_MAX);
if (info->add_set.index != IPSET_INVALID_ID)
@@ -332,9 +332,9 @@ set_target_v1(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_set_info_target_v1 *info = par->targinfo;
- ADT_OPT(add_opt, par->family, info->add_set.dim,
+ ADT_OPT(add_opt, xt_family(par), info->add_set.dim,
info->add_set.flags, 0, UINT_MAX);
- ADT_OPT(del_opt, par->family, info->del_set.dim,
+ ADT_OPT(del_opt, xt_family(par), info->del_set.dim,
info->del_set.flags, 0, UINT_MAX);
if (info->add_set.index != IPSET_INVALID_ID)
@@ -401,9 +401,9 @@ set_target_v2(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_set_info_target_v2 *info = par->targinfo;
- ADT_OPT(add_opt, par->family, info->add_set.dim,
+ ADT_OPT(add_opt, xt_family(par), info->add_set.dim,
info->add_set.flags, info->flags, info->timeout);
- ADT_OPT(del_opt, par->family, info->del_set.dim,
+ ADT_OPT(del_opt, xt_family(par), info->del_set.dim,
info->del_set.flags, 0, UINT_MAX);
/* Normalize to fit into jiffies */
@@ -423,17 +423,19 @@ set_target_v2(struct sk_buff *skb, const struct xt_action_param *par)
/* Revision 3 target */
+#define MOPT(opt, member) ((opt).ext.skbinfo.member)
+
static unsigned int
set_target_v3(struct sk_buff *skb, const struct xt_action_param *par)
{
const struct xt_set_info_target_v3 *info = par->targinfo;
int ret;
- ADT_OPT(add_opt, par->family, info->add_set.dim,
+ ADT_OPT(add_opt, xt_family(par), info->add_set.dim,
info->add_set.flags, info->flags, info->timeout);
- ADT_OPT(del_opt, par->family, info->del_set.dim,
+ ADT_OPT(del_opt, xt_family(par), info->del_set.dim,
info->del_set.flags, 0, UINT_MAX);
- ADT_OPT(map_opt, par->family, info->map_set.dim,
+ ADT_OPT(map_opt, xt_family(par), info->map_set.dim,
info->map_set.flags, 0, UINT_MAX);
/* Normalize to fit into jiffies */
@@ -453,14 +455,14 @@ set_target_v3(struct sk_buff *skb, const struct xt_action_param *par)
if (!ret)
return XT_CONTINUE;
if (map_opt.cmdflags & IPSET_FLAG_MAP_SKBMARK)
- skb->mark = (skb->mark & ~(map_opt.ext.skbmarkmask))
- ^ (map_opt.ext.skbmark);
+ skb->mark = (skb->mark & ~MOPT(map_opt,skbmarkmask))
+ ^ MOPT(map_opt, skbmark);
if (map_opt.cmdflags & IPSET_FLAG_MAP_SKBPRIO)
- skb->priority = map_opt.ext.skbprio;
+ skb->priority = MOPT(map_opt, skbprio);
if ((map_opt.cmdflags & IPSET_FLAG_MAP_SKBQUEUE) &&
skb->dev &&
- skb->dev->real_num_tx_queues > map_opt.ext.skbqueue)
- skb_set_queue_mapping(skb, map_opt.ext.skbqueue);
+ skb->dev->real_num_tx_queues > MOPT(map_opt, skbqueue))
+ skb_set_queue_mapping(skb, MOPT(map_opt, skbqueue));
}
return XT_CONTINUE;
}
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index b10ade2..2198914 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -22,76 +22,14 @@
#include <net/netfilter/ipv4/nf_defrag_ipv4.h>
#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
-#define XT_SOCKET_HAVE_IPV6 1
#include <linux/netfilter_ipv6/ip6_tables.h>
#include <net/inet6_hashtables.h>
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#endif
+#include <net/netfilter/nf_socket.h>
#include <linux/netfilter/xt_socket.h>
-#if IS_ENABLED(CONFIG_NF_CONNTRACK)
-#define XT_SOCKET_HAVE_CONNTRACK 1
-#include <net/netfilter/nf_conntrack.h>
-#endif
-
-static int
-extract_icmp4_fields(const struct sk_buff *skb,
- u8 *protocol,
- __be32 *raddr,
- __be32 *laddr,
- __be16 *rport,
- __be16 *lport)
-{
- unsigned int outside_hdrlen = ip_hdrlen(skb);
- struct iphdr *inside_iph, _inside_iph;
- struct icmphdr *icmph, _icmph;
- __be16 *ports, _ports[2];
-
- icmph = skb_header_pointer(skb, outside_hdrlen,
- sizeof(_icmph), &_icmph);
- if (icmph == NULL)
- return 1;
-
- switch (icmph->type) {
- case ICMP_DEST_UNREACH:
- case ICMP_SOURCE_QUENCH:
- case ICMP_REDIRECT:
- case ICMP_TIME_EXCEEDED:
- case ICMP_PARAMETERPROB:
- break;
- default:
- return 1;
- }
-
- inside_iph = skb_header_pointer(skb, outside_hdrlen +
- sizeof(struct icmphdr),
- sizeof(_inside_iph), &_inside_iph);
- if (inside_iph == NULL)
- return 1;
-
- if (inside_iph->protocol != IPPROTO_TCP &&
- inside_iph->protocol != IPPROTO_UDP)
- return 1;
-
- ports = skb_header_pointer(skb, outside_hdrlen +
- sizeof(struct icmphdr) +
- (inside_iph->ihl << 2),
- sizeof(_ports), &_ports);
- if (ports == NULL)
- return 1;
-
- /* the inside IP packet is the one quoted from our side, thus
- * its saddr is the local address */
- *protocol = inside_iph->protocol;
- *laddr = inside_iph->saddr;
- *lport = ports[0];
- *raddr = inside_iph->daddr;
- *rport = ports[1];
-
- return 0;
-}
-
/* "socket" match based redirection (no specific rule)
* ===================================================
*
@@ -111,104 +49,6 @@ extract_icmp4_fields(const struct sk_buff *skb,
* then local services could intercept traffic going through the
* box.
*/
-static struct sock *
-xt_socket_get_sock_v4(struct net *net, struct sk_buff *skb, const int doff,
- const u8 protocol,
- const __be32 saddr, const __be32 daddr,
- const __be16 sport, const __be16 dport,
- const struct net_device *in)
-{
- switch (protocol) {
- case IPPROTO_TCP:
- return inet_lookup(net, &tcp_hashinfo, skb, doff,
- saddr, sport, daddr, dport,
- in->ifindex);
- case IPPROTO_UDP:
- return udp4_lib_lookup(net, saddr, sport, daddr, dport,
- in->ifindex);
- }
- return NULL;
-}
-
-static bool xt_socket_sk_is_transparent(struct sock *sk)
-{
- switch (sk->sk_state) {
- case TCP_TIME_WAIT:
- return inet_twsk(sk)->tw_transparent;
-
- case TCP_NEW_SYN_RECV:
- return inet_rsk(inet_reqsk(sk))->no_srccheck;
-
- default:
- return inet_sk(sk)->transparent;
- }
-}
-
-static struct sock *xt_socket_lookup_slow_v4(struct net *net,
- const struct sk_buff *skb,
- const struct net_device *indev)
-{
- const struct iphdr *iph = ip_hdr(skb);
- struct sk_buff *data_skb = NULL;
- int doff = 0;
- __be32 uninitialized_var(daddr), uninitialized_var(saddr);
- __be16 uninitialized_var(dport), uninitialized_var(sport);
- u8 uninitialized_var(protocol);
-#ifdef XT_SOCKET_HAVE_CONNTRACK
- struct nf_conn const *ct;
- enum ip_conntrack_info ctinfo;
-#endif
-
- if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) {
- struct udphdr _hdr, *hp;
-
- hp = skb_header_pointer(skb, ip_hdrlen(skb),
- sizeof(_hdr), &_hdr);
- if (hp == NULL)
- return NULL;
-
- protocol = iph->protocol;
- saddr = iph->saddr;
- sport = hp->source;
- daddr = iph->daddr;
- dport = hp->dest;
- data_skb = (struct sk_buff *)skb;
- doff = iph->protocol == IPPROTO_TCP ?
- ip_hdrlen(skb) + __tcp_hdrlen((struct tcphdr *)hp) :
- ip_hdrlen(skb) + sizeof(*hp);
-
- } else if (iph->protocol == IPPROTO_ICMP) {
- if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr,
- &sport, &dport))
- return NULL;
- } else {
- return NULL;
- }
-
-#ifdef XT_SOCKET_HAVE_CONNTRACK
- /* Do the lookup with the original socket address in
- * case this is a reply packet of an established
- * SNAT-ted connection.
- */
- ct = nf_ct_get(skb, &ctinfo);
- if (ct && !nf_ct_is_untracked(ct) &&
- ((iph->protocol != IPPROTO_ICMP &&
- ctinfo == IP_CT_ESTABLISHED_REPLY) ||
- (iph->protocol == IPPROTO_ICMP &&
- ctinfo == IP_CT_RELATED_REPLY)) &&
- (ct->status & IPS_SRC_NAT_DONE)) {
-
- daddr = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip;
- dport = (iph->protocol == IPPROTO_TCP) ?
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port :
- ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port;
- }
-#endif
-
- return xt_socket_get_sock_v4(net, data_skb, doff, protocol, saddr,
- daddr, sport, dport, indev);
-}
-
static bool
socket_match(const struct sk_buff *skb, struct xt_action_param *par,
const struct xt_socket_mtinfo1 *info)
@@ -217,7 +57,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
struct sock *sk = skb->sk;
if (!sk)
- sk = xt_socket_lookup_slow_v4(par->net, skb, par->in);
+ sk = nf_sk_lookup_slow_v4(xt_net(par), skb, xt_in(par));
if (sk) {
bool wildcard;
bool transparent = true;
@@ -233,7 +73,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
* if XT_SOCKET_TRANSPARENT is used
*/
if (info->flags & XT_SOCKET_TRANSPARENT)
- transparent = xt_socket_sk_is_transparent(sk);
+ transparent = nf_sk_is_transparent(sk);
if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard &&
transparent)
@@ -265,132 +105,7 @@ socket_mt4_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par)
return socket_match(skb, par, par->matchinfo);
}
-#ifdef XT_SOCKET_HAVE_IPV6
-
-static int
-extract_icmp6_fields(const struct sk_buff *skb,
- unsigned int outside_hdrlen,
- int *protocol,
- const struct in6_addr **raddr,
- const struct in6_addr **laddr,
- __be16 *rport,
- __be16 *lport,
- struct ipv6hdr *ipv6_var)
-{
- const struct ipv6hdr *inside_iph;
- struct icmp6hdr *icmph, _icmph;
- __be16 *ports, _ports[2];
- u8 inside_nexthdr;
- __be16 inside_fragoff;
- int inside_hdrlen;
-
- icmph = skb_header_pointer(skb, outside_hdrlen,
- sizeof(_icmph), &_icmph);
- if (icmph == NULL)
- return 1;
-
- if (icmph->icmp6_type & ICMPV6_INFOMSG_MASK)
- return 1;
-
- inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(_icmph),
- sizeof(*ipv6_var), ipv6_var);
- if (inside_iph == NULL)
- return 1;
- inside_nexthdr = inside_iph->nexthdr;
-
- inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) +
- sizeof(*ipv6_var),
- &inside_nexthdr, &inside_fragoff);
- if (inside_hdrlen < 0)
- return 1; /* hjm: Packet has no/incomplete transport layer headers. */
-
- if (inside_nexthdr != IPPROTO_TCP &&
- inside_nexthdr != IPPROTO_UDP)
- return 1;
-
- ports = skb_header_pointer(skb, inside_hdrlen,
- sizeof(_ports), &_ports);
- if (ports == NULL)
- return 1;
-
- /* the inside IP packet is the one quoted from our side, thus
- * its saddr is the local address */
- *protocol = inside_nexthdr;
- *laddr = &inside_iph->saddr;
- *lport = ports[0];
- *raddr = &inside_iph->daddr;
- *rport = ports[1];
-
- return 0;
-}
-
-static struct sock *
-xt_socket_get_sock_v6(struct net *net, struct sk_buff *skb, int doff,
- const u8 protocol,
- const struct in6_addr *saddr, const struct in6_addr *daddr,
- const __be16 sport, const __be16 dport,
- const struct net_device *in)
-{
- switch (protocol) {
- case IPPROTO_TCP:
- return inet6_lookup(net, &tcp_hashinfo, skb, doff,
- saddr, sport, daddr, dport,
- in->ifindex);
- case IPPROTO_UDP:
- return udp6_lib_lookup(net, saddr, sport, daddr, dport,
- in->ifindex);
- }
-
- return NULL;
-}
-
-static struct sock *xt_socket_lookup_slow_v6(struct net *net,
- const struct sk_buff *skb,
- const struct net_device *indev)
-{
- __be16 uninitialized_var(dport), uninitialized_var(sport);
- const struct in6_addr *daddr = NULL, *saddr = NULL;
- struct ipv6hdr *iph = ipv6_hdr(skb);
- struct sk_buff *data_skb = NULL;
- int doff = 0;
- int thoff = 0, tproto;
-
- tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
- if (tproto < 0) {
- pr_debug("unable to find transport header in IPv6 packet, dropping\n");
- return NULL;
- }
-
- if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) {
- struct udphdr _hdr, *hp;
-
- hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr);
- if (hp == NULL)
- return NULL;
-
- saddr = &iph->saddr;
- sport = hp->source;
- daddr = &iph->daddr;
- dport = hp->dest;
- data_skb = (struct sk_buff *)skb;
- doff = tproto == IPPROTO_TCP ?
- thoff + __tcp_hdrlen((struct tcphdr *)hp) :
- thoff + sizeof(*hp);
-
- } else if (tproto == IPPROTO_ICMPV6) {
- struct ipv6hdr ipv6_var;
-
- if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr,
- &sport, &dport, &ipv6_var))
- return NULL;
- } else {
- return NULL;
- }
-
- return xt_socket_get_sock_v6(net, data_skb, doff, tproto, saddr, daddr,
- sport, dport, indev);
-}
-
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
static bool
socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par)
{
@@ -399,7 +114,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par)
struct sock *sk = skb->sk;
if (!sk)
- sk = xt_socket_lookup_slow_v6(par->net, skb, par->in);
+ sk = nf_sk_lookup_slow_v6(xt_net(par), skb, xt_in(par));
if (sk) {
bool wildcard;
bool transparent = true;
@@ -415,7 +130,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par)
* if XT_SOCKET_TRANSPARENT is used
*/
if (info->flags & XT_SOCKET_TRANSPARENT)
- transparent = xt_socket_sk_is_transparent(sk);
+ transparent = nf_sk_is_transparent(sk);
if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard &&
transparent)
@@ -488,7 +203,7 @@ static struct xt_match socket_mt_reg[] __read_mostly = {
(1 << NF_INET_LOCAL_IN),
.me = THIS_MODULE,
},
-#ifdef XT_SOCKET_HAVE_IPV6
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
{
.name = "socket",
.revision = 1,
@@ -512,7 +227,7 @@ static struct xt_match socket_mt_reg[] __read_mostly = {
(1 << NF_INET_LOCAL_IN),
.me = THIS_MODULE,
},
-#ifdef XT_SOCKET_HAVE_IPV6
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
{
.name = "socket",
.revision = 2,
@@ -536,7 +251,7 @@ static struct xt_match socket_mt_reg[] __read_mostly = {
(1 << NF_INET_LOCAL_IN),
.me = THIS_MODULE,
},
-#ifdef XT_SOCKET_HAVE_IPV6
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
{
.name = "socket",
.revision = 3,
@@ -554,7 +269,7 @@ static struct xt_match socket_mt_reg[] __read_mostly = {
static int __init socket_mt_init(void)
{
nf_defrag_ipv4_enable();
-#ifdef XT_SOCKET_HAVE_IPV6
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
nf_defrag_ipv6_enable();
#endif
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index b2f0e98..a554624 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -178,11 +178,8 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
}
cb->args[1] = i;
} else {
- if (req->sdiag_protocol >= MAX_LINKS) {
- read_unlock(&nl_table_lock);
- rcu_read_unlock();
+ if (req->sdiag_protocol >= MAX_LINKS)
return -ENOENT;
- }
err = __netlink_diag_dump(skb, cb, req->sdiag_protocol, s_num);
}
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index df0cbcd..fb6e10f 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -362,8 +362,10 @@ int genl_register_family(struct genl_family *family)
family->id = idr_alloc(&genl_fam_idr, family,
start, end + 1, GFP_KERNEL);
- if (!family->id)
+ if (family->id < 0) {
+ err = family->id;
goto errout_locked;
+ }
err = genl_validate_assign_mc_groups(family);
if (err)
@@ -381,6 +383,7 @@ int genl_register_family(struct genl_family *family)
errout_remove:
idr_remove(&genl_fam_idr, family->id);
+ kfree(family->attrbuf);
errout_locked:
genl_unlock_all();
return err;
@@ -399,7 +402,7 @@ int genl_unregister_family(const struct genl_family *family)
{
genl_lock_all();
- if (genl_family_find_byid(family->id)) {
+ if (!genl_family_find_byid(family->id)) {
genl_unlock_all();
return -ENOENT;
}
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 1105c4e..514f7bc 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -66,6 +66,7 @@ struct ovs_frag_data {
u16 vlan_tci;
__be16 vlan_proto;
unsigned int l2_len;
+ u8 mac_proto;
u8 l2_data[MAX_L2_LEN];
};
@@ -137,12 +138,12 @@ static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
static void invalidate_flow_key(struct sw_flow_key *key)
{
- key->eth.type = htons(0);
+ key->mac_proto |= SW_FLOW_KEY_INVALID;
}
static bool is_flow_key_valid(const struct sw_flow_key *key)
{
- return !!key->eth.type;
+ return !(key->mac_proto & SW_FLOW_KEY_INVALID);
}
static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr,
@@ -186,7 +187,8 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN);
- update_ethertype(skb, eth_hdr(skb), mpls->mpls_ethertype);
+ if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET)
+ update_ethertype(skb, eth_hdr(skb), mpls->mpls_ethertype);
skb->protocol = mpls->mpls_ethertype;
invalidate_flow_key(key);
@@ -196,7 +198,6 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
const __be16 ethertype)
{
- struct ethhdr *hdr;
int err;
err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
@@ -212,11 +213,15 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb->mac_len);
- /* mpls_hdr() is used to locate the ethertype field correctly in the
- * presence of VLAN tags.
- */
- hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN);
- update_ethertype(skb, hdr, ethertype);
+ if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET) {
+ struct ethhdr *hdr;
+
+ /* mpls_hdr() is used to locate the ethertype field correctly in the
+ * presence of VLAN tags.
+ */
+ hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN);
+ update_ethertype(skb, hdr, ethertype);
+ }
if (eth_p_mpls(skb->protocol))
skb->protocol = ethertype;
@@ -312,6 +317,47 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
return 0;
}
+/* pop_eth does not support VLAN packets as this action is never called
+ * for them.
+ */
+static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
+{
+ skb_pull_rcsum(skb, ETH_HLEN);
+ skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);
+
+ /* safe right before invalidate_flow_key */
+ key->mac_proto = MAC_PROTO_NONE;
+ invalidate_flow_key(key);
+ return 0;
+}
+
+static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,
+ const struct ovs_action_push_eth *ethh)
+{
+ struct ethhdr *hdr;
+
+ /* Add the new Ethernet header */
+ if (skb_cow_head(skb, ETH_HLEN) < 0)
+ return -ENOMEM;
+
+ skb_push(skb, ETH_HLEN);
+ skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);
+
+ hdr = eth_hdr(skb);
+ ether_addr_copy(hdr->h_source, ethh->addresses.eth_src);
+ ether_addr_copy(hdr->h_dest, ethh->addresses.eth_dst);
+ hdr->h_proto = skb->protocol;
+
+ skb_postpush_rcsum(skb, hdr, ETH_HLEN);
+
+ /* safe right before invalidate_flow_key */
+ key->mac_proto = MAC_PROTO_ETHERNET;
+ invalidate_flow_key(key);
+ return 0;
+}
+
static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh,
__be32 addr, __be32 new_addr)
{
@@ -673,7 +719,7 @@ static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *sk
skb_reset_mac_len(skb);
}
- ovs_vport_send(vport, skb);
+ ovs_vport_send(vport, skb, data->mac_proto);
return 0;
}
@@ -692,7 +738,7 @@ static struct dst_ops ovs_dst_ops = {
* ovs_vport_output(), which is called once per fragmented packet.
*/
static void prepare_frag(struct vport *vport, struct sk_buff *skb,
- u16 orig_network_offset)
+ u16 orig_network_offset, u8 mac_proto)
{
unsigned int hlen = skb_network_offset(skb);
struct ovs_frag_data *data;
@@ -705,6 +751,7 @@ static void prepare_frag(struct vport *vport, struct sk_buff *skb,
data->network_offset = orig_network_offset;
data->vlan_tci = skb->vlan_tci;
data->vlan_proto = skb->vlan_proto;
+ data->mac_proto = mac_proto;
data->l2_len = hlen;
memcpy(&data->l2_data, skb->data, hlen);
@@ -713,7 +760,8 @@ static void prepare_frag(struct vport *vport, struct sk_buff *skb,
}
static void ovs_fragment(struct net *net, struct vport *vport,
- struct sk_buff *skb, u16 mru, __be16 ethertype)
+ struct sk_buff *skb, u16 mru,
+ struct sw_flow_key *key)
{
u16 orig_network_offset = 0;
@@ -727,11 +775,12 @@ static void ovs_fragment(struct net *net, struct vport *vport,
goto err;
}
- if (ethertype == htons(ETH_P_IP)) {
+ if (key->eth.type == htons(ETH_P_IP)) {
struct dst_entry ovs_dst;
unsigned long orig_dst;
- prepare_frag(vport, skb, orig_network_offset);
+ prepare_frag(vport, skb, orig_network_offset,
+ ovs_key_mac_proto(key));
dst_init(&ovs_dst, &ovs_dst_ops, NULL, 1,
DST_OBSOLETE_NONE, DST_NOCOUNT);
ovs_dst.dev = vport->dev;
@@ -742,7 +791,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
ip_do_fragment(net, skb->sk, skb, ovs_vport_output);
refdst_drop(orig_dst);
- } else if (ethertype == htons(ETH_P_IPV6)) {
+ } else if (key->eth.type == htons(ETH_P_IPV6)) {
const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
unsigned long orig_dst;
struct rt6_info ovs_rt;
@@ -751,7 +800,8 @@ static void ovs_fragment(struct net *net, struct vport *vport,
goto err;
}
- prepare_frag(vport, skb, orig_network_offset);
+ prepare_frag(vport, skb, orig_network_offset,
+ ovs_key_mac_proto(key));
memset(&ovs_rt, 0, sizeof(ovs_rt));
dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL, 1,
DST_OBSOLETE_NONE, DST_NOCOUNT);
@@ -765,7 +815,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
refdst_drop(orig_dst);
} else {
WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
- ovs_vport_name(vport), ntohs(ethertype), mru,
+ ovs_vport_name(vport), ntohs(key->eth.type), mru,
vport->dev->mtu);
goto err;
}
@@ -785,26 +835,19 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
u32 cutlen = OVS_CB(skb)->cutlen;
if (unlikely(cutlen > 0)) {
- if (skb->len - cutlen > ETH_HLEN)
+ if (skb->len - cutlen > ovs_mac_header_len(key))
pskb_trim(skb, skb->len - cutlen);
else
- pskb_trim(skb, ETH_HLEN);
+ pskb_trim(skb, ovs_mac_header_len(key));
}
- if (likely(!mru || (skb->len <= mru + ETH_HLEN))) {
- ovs_vport_send(vport, skb);
+ if (likely(!mru ||
+ (skb->len <= mru + vport->dev->hard_header_len))) {
+ ovs_vport_send(vport, skb, ovs_key_mac_proto(key));
} else if (mru <= vport->dev->mtu) {
struct net *net = read_pnet(&dp->net);
- __be16 ethertype = key->eth.type;
- if (!is_flow_key_valid(key)) {
- if (eth_p_mpls(skb->protocol))
- ethertype = skb->inner_protocol;
- else
- ethertype = vlan_get_protocol(skb);
- }
-
- ovs_fragment(net, vport, skb, mru, ethertype);
+ ovs_fragment(net, vport, skb, mru, key);
} else {
kfree_skb(skb);
}
@@ -1198,6 +1241,14 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
if (err)
return err == -EINPROGRESS ? 0 : err;
break;
+
+ case OVS_ACTION_ATTR_PUSH_ETH:
+ err = push_eth(skb, key, nla_data(a));
+ break;
+
+ case OVS_ACTION_ATTR_POP_ETH:
+ err = pop_eth(skb, key);
+ break;
}
if (unlikely(err)) {
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 31045ef..9b8a028 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -725,12 +725,8 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
skb->nfctinfo = IP_CT_NEW;
}
- /* Repeat if requested, see nf_iterate(). */
- do {
- err = nf_conntrack_in(net, info->family,
- NF_INET_PRE_ROUTING, skb);
- } while (err == NF_REPEAT);
-
+ err = nf_conntrack_in(net, info->family,
+ NF_INET_PRE_ROUTING, skb);
if (err != NF_ACCEPT)
return -ENOENT;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index fa87601..2d4c4d3 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -58,7 +58,7 @@
#include "vport-internal_dev.h"
#include "vport-netdev.h"
-int ovs_net_id __read_mostly;
+unsigned int ovs_net_id __read_mostly;
static struct genl_family dp_packet_genl_family;
static struct genl_family dp_flow_genl_family;
@@ -560,7 +560,6 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
struct sw_flow *flow;
struct sw_flow_actions *sf_acts;
struct datapath *dp;
- struct ethhdr *eth;
struct vport *input_vport;
u16 mru = 0;
int len;
@@ -581,17 +580,6 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
nla_memcpy(__skb_put(packet, len), a[OVS_PACKET_ATTR_PACKET], len);
- skb_reset_mac_header(packet);
- eth = eth_hdr(packet);
-
- /* Normally, setting the skb 'protocol' field would be handled by a
- * call to eth_type_trans(), but it assumes there's a sending
- * device, which we may not have. */
- if (eth_proto_is_802_3(eth->h_proto))
- packet->protocol = eth->h_proto;
- else
- packet->protocol = htons(ETH_P_802_2);
-
/* Set packet's mru */
if (a[OVS_PACKET_ATTR_MRU]) {
mru = nla_get_u16(a[OVS_PACKET_ATTR_MRU]);
@@ -618,6 +606,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
rcu_assign_pointer(flow->sf_acts, acts);
packet->priority = flow->key.phy.priority;
packet->mark = flow->key.phy.skb_mark;
+ packet->protocol = flow->key.eth.type;
rcu_read_lock();
dp = get_dp_rcu(net, ovs_header->dp_ifindex);
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index ab85c1c..1c6e937 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -144,7 +144,7 @@ struct ovs_net {
bool xt_label;
};
-extern int ovs_net_id;
+extern unsigned int ovs_net_id;
void ovs_lock(void);
void ovs_unlock(void);
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 2208706..08aa926 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -334,14 +334,17 @@ static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh)
return 1;
}
-static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
+static void clear_vlan(struct sw_flow_key *key)
{
- int res;
-
key->eth.vlan.tci = 0;
key->eth.vlan.tpid = 0;
key->eth.cvlan.tci = 0;
key->eth.cvlan.tpid = 0;
+}
+
+static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
+{
+ int res;
if (skb_vlan_tag_present(skb)) {
key->eth.vlan.tci = htons(skb->vlan_tci);
@@ -483,17 +486,20 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
*
* Returns 0 if successful, otherwise a negative errno value.
*
- * Initializes @skb header pointers as follows:
+ * Initializes @skb header fields as follows:
*
- * - skb->mac_header: the Ethernet header.
+ * - skb->mac_header: the L2 header.
*
- * - skb->network_header: just past the Ethernet header, or just past the
- * VLAN header, to the first byte of the Ethernet payload.
+ * - skb->network_header: just past the L2 header, or just past the
+ * VLAN header, to the first byte of the L2 payload.
*
* - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6
* on output, then just past the IP header, if one is present and
* of a correct length, otherwise the same as skb->network_header.
* For other key->eth.type values it is left untouched.
+ *
+ * - skb->protocol: the type of the data starting at skb->network_header.
+ * Equals to key->eth.type.
*/
static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
{
@@ -505,28 +511,35 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
skb_reset_mac_header(skb);
- /* Link layer. We are guaranteed to have at least the 14 byte Ethernet
- * header in the linear data area.
- */
- eth = eth_hdr(skb);
- ether_addr_copy(key->eth.src, eth->h_source);
- ether_addr_copy(key->eth.dst, eth->h_dest);
+ /* Link layer. */
+ clear_vlan(key);
+ if (key->mac_proto == MAC_PROTO_NONE) {
+ if (unlikely(eth_type_vlan(skb->protocol)))
+ return -EINVAL;
- __skb_pull(skb, 2 * ETH_ALEN);
- /* We are going to push all headers that we pull, so no need to
- * update skb->csum here.
- */
+ skb_reset_network_header(skb);
+ } else {
+ eth = eth_hdr(skb);
+ ether_addr_copy(key->eth.src, eth->h_source);
+ ether_addr_copy(key->eth.dst, eth->h_dest);
- if (unlikely(parse_vlan(skb, key)))
- return -ENOMEM;
+ __skb_pull(skb, 2 * ETH_ALEN);
+ /* We are going to push all headers that we pull, so no need to
+ * update skb->csum here.
+ */
- key->eth.type = parse_ethertype(skb);
- if (unlikely(key->eth.type == htons(0)))
- return -ENOMEM;
+ if (unlikely(parse_vlan(skb, key)))
+ return -ENOMEM;
- skb_reset_network_header(skb);
+ skb->protocol = parse_ethertype(skb);
+ if (unlikely(skb->protocol == htons(0)))
+ return -ENOMEM;
+
+ skb_reset_network_header(skb);
+ __skb_push(skb, skb->data - skb_mac_header(skb));
+ }
skb_reset_mac_len(skb);
- __skb_push(skb, skb->data - skb_mac_header(skb));
+ key->eth.type = skb->protocol;
/* Network layer. */
if (key->eth.type == htons(ETH_P_IP)) {
@@ -721,9 +734,25 @@ int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
return key_extract(skb, key);
}
+static int key_extract_mac_proto(struct sk_buff *skb)
+{
+ switch (skb->dev->type) {
+ case ARPHRD_ETHER:
+ return MAC_PROTO_ETHERNET;
+ case ARPHRD_NONE:
+ if (skb->protocol == htons(ETH_P_TEB))
+ return MAC_PROTO_ETHERNET;
+ return MAC_PROTO_NONE;
+ }
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+}
+
int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
struct sk_buff *skb, struct sw_flow_key *key)
{
+ int res;
+
/* Extract metadata from packet. */
if (tun_info) {
key->tun_proto = ip_tunnel_info_af(tun_info);
@@ -751,6 +780,10 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
key->phy.skb_mark = skb->mark;
ovs_ct_fill_key(skb, key);
key->ovs_flow_hash = 0;
+ res = key_extract_mac_proto(skb);
+ if (res < 0)
+ return res;
+ key->mac_proto = res;
key->recirc_id = 0;
return key_extract(skb, key);
@@ -767,5 +800,29 @@ int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr,
if (err)
return err;
+ if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
+ /* key_extract assumes that skb->protocol is set-up for
+ * layer 3 packets which is the case for other callers,
+ * in particular packets recieved from the network stack.
+ * Here the correct value can be set from the metadata
+ * extracted above.
+ */
+ skb->protocol = key->eth.type;
+ } else {
+ struct ethhdr *eth;
+
+ skb_reset_mac_header(skb);
+ eth = eth_hdr(skb);
+
+ /* Normally, setting the skb 'protocol' field would be
+ * handled by a call to eth_type_trans(), but it assumes
+ * there's a sending device, which we may not have.
+ */
+ if (eth_proto_is_802_3(eth->h_proto))
+ skb->protocol = eth->h_proto;
+ else
+ skb->protocol = htons(ETH_P_802_2);
+ }
+
return key_extract(skb, key);
}
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index ae783f5..f61cae7 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -37,6 +37,12 @@
struct sk_buff;
+enum sw_flow_mac_proto {
+ MAC_PROTO_NONE = 0,
+ MAC_PROTO_ETHERNET,
+};
+#define SW_FLOW_KEY_INVALID 0x80
+
/* Store options at the end of the array if they are less than the
* maximum size. This allows us to get the benefits of variable length
* matching for small options.
@@ -68,6 +74,7 @@ struct sw_flow_key {
u32 skb_mark; /* SKB mark. */
u16 in_port; /* Input switch port (or DP_MAX_PORTS). */
} __packed phy; /* Safe when right after 'tun_key'. */
+ u8 mac_proto; /* MAC layer protocol (e.g. Ethernet). */
u8 tun_proto; /* Protocol of encapsulating tunnel. */
u32 ovs_flow_hash; /* Datapath computed hash value. */
u32 recirc_id; /* Recirculation ID. */
@@ -206,6 +213,21 @@ struct arp_eth_header {
unsigned char ar_tip[4]; /* target IP address */
} __packed;
+static inline u8 ovs_key_mac_proto(const struct sw_flow_key *key)
+{
+ return key->mac_proto & ~SW_FLOW_KEY_INVALID;
+}
+
+static inline u16 __ovs_mac_header_len(u8 mac_proto)
+{
+ return mac_proto == MAC_PROTO_ETHERNET ? ETH_HLEN : 0;
+}
+
+static inline u16 ovs_mac_header_len(const struct sw_flow_key *key)
+{
+ return __ovs_mac_header_len(ovs_key_mac_proto(key));
+}
+
static inline bool ovs_identifier_is_ufid(const struct sw_flow_id *sfid)
{
return sfid->ufid_len;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index ae25ded..d19044f 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -123,7 +123,7 @@ static void update_range(struct sw_flow_match *match,
static bool match_validate(const struct sw_flow_match *match,
u64 key_attrs, u64 mask_attrs, bool log)
{
- u64 key_expected = 1 << OVS_KEY_ATTR_ETHERNET;
+ u64 key_expected = 0;
u64 mask_allowed = key_attrs; /* At most allow all key attributes */
/* The following mask attributes allowed only if they
@@ -969,10 +969,33 @@ static int parse_vlan_from_nlattrs(struct sw_flow_match *match,
return 0;
}
+static int parse_eth_type_from_nlattrs(struct sw_flow_match *match,
+ u64 *attrs, const struct nlattr **a,
+ bool is_mask, bool log)
+{
+ __be16 eth_type;
+
+ eth_type = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);
+ if (is_mask) {
+ /* Always exact match EtherType. */
+ eth_type = htons(0xffff);
+ } else if (!eth_proto_is_802_3(eth_type)) {
+ OVS_NLERR(log, "EtherType %x is less than min %x",
+ ntohs(eth_type), ETH_P_802_3_MIN);
+ return -EINVAL;
+ }
+
+ SW_FLOW_KEY_PUT(match, eth.type, eth_type, is_mask);
+ *attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
+ return 0;
+}
+
static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match,
u64 *attrs, const struct nlattr **a,
bool is_mask, bool log)
{
+ u8 mac_proto = MAC_PROTO_ETHERNET;
+
if (*attrs & (1 << OVS_KEY_ATTR_DP_HASH)) {
u32 hash_val = nla_get_u32(a[OVS_KEY_ATTR_DP_HASH]);
@@ -1059,6 +1082,21 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match,
sizeof(*cl), is_mask);
*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABELS);
}
+
+ /* For layer 3 packets the Ethernet type is provided
+ * and treated as metadata but no MAC addresses are provided.
+ */
+ if (!(*attrs & (1ULL << OVS_KEY_ATTR_ETHERNET)) &&
+ (*attrs & (1ULL << OVS_KEY_ATTR_ETHERTYPE)))
+ mac_proto = MAC_PROTO_NONE;
+
+ /* Always exact match mac_proto */
+ SW_FLOW_KEY_PUT(match, mac_proto, is_mask ? 0xff : mac_proto, is_mask);
+
+ if (mac_proto == MAC_PROTO_NONE)
+ return parse_eth_type_from_nlattrs(match, attrs, a, is_mask,
+ log);
+
return 0;
}
@@ -1081,33 +1119,26 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match,
SW_FLOW_KEY_MEMCPY(match, eth.dst,
eth_key->eth_dst, ETH_ALEN, is_mask);
attrs &= ~(1 << OVS_KEY_ATTR_ETHERNET);
- }
- if (attrs & (1 << OVS_KEY_ATTR_VLAN)) {
- /* VLAN attribute is always parsed before getting here since it
- * may occur multiple times.
- */
- OVS_NLERR(log, "VLAN attribute unexpected.");
- return -EINVAL;
- }
-
- if (attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) {
- __be16 eth_type;
-
- eth_type = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);
- if (is_mask) {
- /* Always exact match EtherType. */
- eth_type = htons(0xffff);
- } else if (!eth_proto_is_802_3(eth_type)) {
- OVS_NLERR(log, "EtherType %x is less than min %x",
- ntohs(eth_type), ETH_P_802_3_MIN);
+ if (attrs & (1 << OVS_KEY_ATTR_VLAN)) {
+ /* VLAN attribute is always parsed before getting here since it
+ * may occur multiple times.
+ */
+ OVS_NLERR(log, "VLAN attribute unexpected.");
return -EINVAL;
}
- SW_FLOW_KEY_PUT(match, eth.type, eth_type, is_mask);
- attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
- } else if (!is_mask) {
- SW_FLOW_KEY_PUT(match, eth.type, htons(ETH_P_802_2), is_mask);
+ if (attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) {
+ err = parse_eth_type_from_nlattrs(match, &attrs, a, is_mask,
+ log);
+ if (err)
+ return err;
+ } else if (!is_mask) {
+ SW_FLOW_KEY_PUT(match, eth.type, htons(ETH_P_802_2), is_mask);
+ }
+ } else if (!match->key->eth.type) {
+ OVS_NLERR(log, "Either Ethernet header or EtherType is required.");
+ return -EINVAL;
}
if (attrs & (1 << OVS_KEY_ATTR_IPV4)) {
@@ -1556,42 +1587,44 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
if (ovs_ct_put_key(output, skb))
goto nla_put_failure;
- nla = nla_reserve(skb, OVS_KEY_ATTR_ETHERNET, sizeof(*eth_key));
- if (!nla)
- goto nla_put_failure;
-
- eth_key = nla_data(nla);
- ether_addr_copy(eth_key->eth_src, output->eth.src);
- ether_addr_copy(eth_key->eth_dst, output->eth.dst);
-
- if (swkey->eth.vlan.tci || eth_type_vlan(swkey->eth.type)) {
- if (ovs_nla_put_vlan(skb, &output->eth.vlan, is_mask))
+ if (ovs_key_mac_proto(swkey) == MAC_PROTO_ETHERNET) {
+ nla = nla_reserve(skb, OVS_KEY_ATTR_ETHERNET, sizeof(*eth_key));
+ if (!nla)
goto nla_put_failure;
- encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
- if (!swkey->eth.vlan.tci)
- goto unencap;
- if (swkey->eth.cvlan.tci || eth_type_vlan(swkey->eth.type)) {
- if (ovs_nla_put_vlan(skb, &output->eth.cvlan, is_mask))
+ eth_key = nla_data(nla);
+ ether_addr_copy(eth_key->eth_src, output->eth.src);
+ ether_addr_copy(eth_key->eth_dst, output->eth.dst);
+
+ if (swkey->eth.vlan.tci || eth_type_vlan(swkey->eth.type)) {
+ if (ovs_nla_put_vlan(skb, &output->eth.vlan, is_mask))
goto nla_put_failure;
- in_encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
- if (!swkey->eth.cvlan.tci)
+ encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
+ if (!swkey->eth.vlan.tci)
goto unencap;
- }
- }
- if (swkey->eth.type == htons(ETH_P_802_2)) {
- /*
- * Ethertype 802.2 is represented in the netlink with omitted
- * OVS_KEY_ATTR_ETHERTYPE in the flow key attribute, and
- * 0xffff in the mask attribute. Ethertype can also
- * be wildcarded.
- */
- if (is_mask && output->eth.type)
- if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE,
- output->eth.type))
- goto nla_put_failure;
- goto unencap;
+ if (swkey->eth.cvlan.tci || eth_type_vlan(swkey->eth.type)) {
+ if (ovs_nla_put_vlan(skb, &output->eth.cvlan, is_mask))
+ goto nla_put_failure;
+ in_encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
+ if (!swkey->eth.cvlan.tci)
+ goto unencap;
+ }
+ }
+
+ if (swkey->eth.type == htons(ETH_P_802_2)) {
+ /*
+ * Ethertype 802.2 is represented in the netlink with omitted
+ * OVS_KEY_ATTR_ETHERTYPE in the flow key attribute, and
+ * 0xffff in the mask attribute. Ethertype can also
+ * be wildcarded.
+ */
+ if (is_mask && output->eth.type)
+ if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE,
+ output->eth.type))
+ goto nla_put_failure;
+ goto unencap;
+ }
}
if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, output->eth.type))
@@ -2126,8 +2159,8 @@ static bool validate_masked(u8 *data, int len)
static int validate_set(const struct nlattr *a,
const struct sw_flow_key *flow_key,
- struct sw_flow_actions **sfa,
- bool *skip_copy, __be16 eth_type, bool masked, bool log)
+ struct sw_flow_actions **sfa, bool *skip_copy,
+ u8 mac_proto, __be16 eth_type, bool masked, bool log)
{
const struct nlattr *ovs_key = nla_data(a);
int key_type = nla_type(ovs_key);
@@ -2157,9 +2190,12 @@ static int validate_set(const struct nlattr *a,
case OVS_KEY_ATTR_SKB_MARK:
case OVS_KEY_ATTR_CT_MARK:
case OVS_KEY_ATTR_CT_LABELS:
- case OVS_KEY_ATTR_ETHERNET:
break;
+ case OVS_KEY_ATTR_ETHERNET:
+ if (mac_proto != MAC_PROTO_ETHERNET)
+ return -EINVAL;
+
case OVS_KEY_ATTR_TUNNEL:
if (masked)
return -EINVAL; /* Masked tunnel set not supported. */
@@ -2324,6 +2360,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
int depth, struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci, bool log)
{
+ u8 mac_proto = ovs_key_mac_proto(key);
const struct nlattr *a;
int rem, err;
@@ -2346,6 +2383,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
[OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash),
[OVS_ACTION_ATTR_CT] = (u32)-1,
[OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc),
+ [OVS_ACTION_ATTR_PUSH_ETH] = sizeof(struct ovs_action_push_eth),
+ [OVS_ACTION_ATTR_POP_ETH] = 0,
};
const struct ovs_action_push_vlan *vlan;
int type = nla_type(a);
@@ -2394,10 +2433,14 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
}
case OVS_ACTION_ATTR_POP_VLAN:
+ if (mac_proto != MAC_PROTO_ETHERNET)
+ return -EINVAL;
vlan_tci = htons(0);
break;
case OVS_ACTION_ATTR_PUSH_VLAN:
+ if (mac_proto != MAC_PROTO_ETHERNET)
+ return -EINVAL;
vlan = nla_data(a);
if (!eth_type_vlan(vlan->vlan_tpid))
return -EINVAL;
@@ -2447,14 +2490,16 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
case OVS_ACTION_ATTR_SET:
err = validate_set(a, key, sfa,
- &skip_copy, eth_type, false, log);
+ &skip_copy, mac_proto, eth_type,
+ false, log);
if (err)
return err;
break;
case OVS_ACTION_ATTR_SET_MASKED:
err = validate_set(a, key, sfa,
- &skip_copy, eth_type, true, log);
+ &skip_copy, mac_proto, eth_type,
+ true, log);
if (err)
return err;
break;
@@ -2474,6 +2519,22 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
skip_copy = true;
break;
+ case OVS_ACTION_ATTR_PUSH_ETH:
+ /* Disallow pushing an Ethernet header if one
+ * is already present */
+ if (mac_proto != MAC_PROTO_NONE)
+ return -EINVAL;
+ mac_proto = MAC_PROTO_NONE;
+ break;
+
+ case OVS_ACTION_ATTR_POP_ETH:
+ if (mac_proto != MAC_PROTO_ETHERNET)
+ return -EINVAL;
+ if (vlan_tci & htons(VLAN_TAG_PRESENT))
+ return -EINVAL;
+ mac_proto = MAC_PROTO_ETHERNET;
+ break;
+
default:
OVS_NLERR(log, "Unknown Action type %d", type);
return -EINVAL;
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index e825753..0389398 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -57,8 +57,10 @@ static void netdev_port_receive(struct sk_buff *skb)
if (unlikely(!skb))
return;
- skb_push(skb, ETH_HLEN);
- skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
+ if (skb->dev->type == ARPHRD_ETHER) {
+ skb_push(skb, ETH_HLEN);
+ skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
+ }
ovs_vport_receive(vport, skb, skb_tunnel_info(skb));
return;
error:
@@ -97,7 +99,8 @@ struct vport *ovs_netdev_link(struct vport *vport, const char *name)
}
if (vport->dev->flags & IFF_LOOPBACK ||
- vport->dev->type != ARPHRD_ETHER ||
+ (vport->dev->type != ARPHRD_ETHER &&
+ vport->dev->type != ARPHRD_NONE) ||
ovs_is_internal_dev(vport->dev)) {
err = -EINVAL;
goto error_put;
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 9bb85b3..b6c8524 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -464,9 +464,10 @@ int ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
return 0;
}
-static unsigned int packet_length(const struct sk_buff *skb)
+static unsigned int packet_length(const struct sk_buff *skb,
+ struct net_device *dev)
{
- unsigned int length = skb->len - ETH_HLEN;
+ unsigned int length = skb->len - dev->hard_header_len;
if (!skb_vlan_tag_present(skb) &&
eth_type_vlan(skb->protocol))
@@ -480,14 +481,34 @@ static unsigned int packet_length(const struct sk_buff *skb)
return length;
}
-void ovs_vport_send(struct vport *vport, struct sk_buff *skb)
+void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto)
{
int mtu = vport->dev->mtu;
- if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) {
+ switch (vport->dev->type) {
+ case ARPHRD_NONE:
+ if (mac_proto == MAC_PROTO_ETHERNET) {
+ skb_reset_network_header(skb);
+ skb_reset_mac_len(skb);
+ skb->protocol = htons(ETH_P_TEB);
+ } else if (mac_proto != MAC_PROTO_NONE) {
+ WARN_ON_ONCE(1);
+ goto drop;
+ }
+ break;
+ case ARPHRD_ETHER:
+ if (mac_proto != MAC_PROTO_ETHERNET)
+ goto drop;
+ break;
+ default:
+ goto drop;
+ }
+
+ if (unlikely(packet_length(skb, vport->dev) > mtu &&
+ !skb_is_gso(skb))) {
net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n",
vport->dev->name,
- packet_length(skb), mtu);
+ packet_length(skb, vport->dev), mtu);
vport->dev->stats.tx_errors++;
goto drop;
}
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index 46e5b69..cda66c2 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -197,6 +197,6 @@ int __ovs_vport_ops_register(struct vport_ops *ops);
})
void ovs_vport_ops_unregister(struct vport_ops *ops);
-void ovs_vport_send(struct vport *vport, struct sk_buff *skb);
+void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto);
#endif /* vport.h */
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 11db0d6..fab9bbf 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -250,7 +250,7 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po);
static int packet_direct_xmit(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
- netdev_features_t features;
+ struct sk_buff *orig_skb = skb;
struct netdev_queue *txq;
int ret = NETDEV_TX_BUSY;
@@ -258,9 +258,8 @@ static int packet_direct_xmit(struct sk_buff *skb)
!netif_carrier_ok(dev)))
goto drop;
- features = netif_skb_features(skb);
- if (skb_needs_linearize(skb, features) &&
- __skb_linearize(skb))
+ skb = validate_xmit_skb_list(skb, dev);
+ if (skb != orig_skb)
goto drop;
txq = skb_get_tx_queue(dev, skb);
@@ -280,7 +279,7 @@ static int packet_direct_xmit(struct sk_buff *skb)
return ret;
drop:
atomic_long_inc(&dev->tx_dropped);
- kfree_skb(skb);
+ kfree_skb_list(skb);
return NET_XMIT_DROP;
}
@@ -1968,17 +1967,6 @@ static unsigned int run_filter(struct sk_buff *skb,
return res;
}
-static int __packet_rcv_vnet(const struct sk_buff *skb,
- struct virtio_net_hdr *vnet_hdr)
-{
- *vnet_hdr = (const struct virtio_net_hdr) { 0 };
-
- if (virtio_net_hdr_from_skb(skb, vnet_hdr, vio_le()))
- BUG();
-
- return 0;
-}
-
static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb,
size_t *len)
{
@@ -1988,7 +1976,7 @@ static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb,
return -EINVAL;
*len -= sizeof(vnet_hdr);
- if (__packet_rcv_vnet(skb, &vnet_hdr))
+ if (virtio_net_hdr_from_skb(skb, &vnet_hdr, vio_le()))
return -EINVAL;
return memcpy_to_msg(msg, (void *)&vnet_hdr, sizeof(vnet_hdr));
@@ -2247,8 +2235,9 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
spin_unlock(&sk->sk_receive_queue.lock);
if (po->has_vnet_hdr) {
- if (__packet_rcv_vnet(skb, h.raw + macoff -
- sizeof(struct virtio_net_hdr))) {
+ if (virtio_net_hdr_from_skb(skb, h.raw + macoff -
+ sizeof(struct virtio_net_hdr),
+ vio_le())) {
spin_lock(&sk->sk_receive_queue.lock);
goto drop_n_account;
}
@@ -2391,8 +2380,6 @@ static void tpacket_set_protocol(const struct net_device *dev,
static int __packet_snd_vnet_parse(struct virtio_net_hdr *vnet_hdr, size_t len)
{
- unsigned short gso_type = 0;
-
if ((vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
(__virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) +
__virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2 >
@@ -2404,29 +2391,6 @@ static int __packet_snd_vnet_parse(struct virtio_net_hdr *vnet_hdr, size_t len)
if (__virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len) > len)
return -EINVAL;
- if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
- switch (vnet_hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
- case VIRTIO_NET_HDR_GSO_TCPV4:
- gso_type = SKB_GSO_TCPV4;
- break;
- case VIRTIO_NET_HDR_GSO_TCPV6:
- gso_type = SKB_GSO_TCPV6;
- break;
- case VIRTIO_NET_HDR_GSO_UDP:
- gso_type = SKB_GSO_UDP;
- break;
- default:
- return -EINVAL;
- }
-
- if (vnet_hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN)
- gso_type |= SKB_GSO_TCP_ECN;
-
- if (vnet_hdr->gso_size == 0)
- return -EINVAL;
- }
-
- vnet_hdr->gso_type = gso_type; /* changes type, temporary storage */
return 0;
}
@@ -2446,27 +2410,6 @@ static int packet_snd_vnet_parse(struct msghdr *msg, size_t *len,
return __packet_snd_vnet_parse(vnet_hdr, *len);
}
-static int packet_snd_vnet_gso(struct sk_buff *skb,
- struct virtio_net_hdr *vnet_hdr)
-{
- if (vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
- u16 s = __virtio16_to_cpu(vio_le(), vnet_hdr->csum_start);
- u16 o = __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset);
-
- if (!skb_partial_csum_set(skb, s, o))
- return -EINVAL;
- }
-
- skb_shinfo(skb)->gso_size =
- __virtio16_to_cpu(vio_le(), vnet_hdr->gso_size);
- skb_shinfo(skb)->gso_type = vnet_hdr->gso_type;
-
- /* Header must be checked, and gso_segs computed. */
- skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
- skb_shinfo(skb)->gso_segs = 0;
- return 0;
-}
-
static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
void *frame, struct net_device *dev, void *data, int tp_len,
__be16 proto, unsigned char *addr, int hlen, int copylen,
@@ -2726,7 +2669,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
}
}
- if (po->has_vnet_hdr && packet_snd_vnet_gso(skb, vnet_hdr)) {
+ if (po->has_vnet_hdr && virtio_net_hdr_to_skb(skb, vnet_hdr,
+ vio_le())) {
tp_len = -EINVAL;
goto tpacket_error;
}
@@ -2917,7 +2861,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
packet_pick_tx_queue(dev, skb);
if (po->has_vnet_hdr) {
- err = packet_snd_vnet_gso(skb, &vnet_hdr);
+ err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le());
if (err)
goto out_free;
len += sizeof(vnet_hdr);
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 850a86c..8bad562 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -1167,7 +1167,7 @@ static int pep_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
/* Wait until flow control allows TX */
done = atomic_read(&pn->tx_credits);
while (!done) {
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
if (!timeo) {
err = -EAGAIN;
@@ -1178,10 +1178,9 @@ static int pep_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
goto out;
}
- prepare_to_wait(sk_sleep(sk), &wait,
- TASK_INTERRUPTIBLE);
- done = sk_wait_event(sk, &timeo, atomic_read(&pn->tx_credits));
- finish_wait(sk_sleep(sk), &wait);
+ add_wait_queue(sk_sleep(sk), &wait);
+ done = sk_wait_event(sk, &timeo, atomic_read(&pn->tx_credits), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
if (sk->sk_state != TCP_ESTABLISHED)
goto disabled;
diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c
index a586800..2cb4c5d 100644
--- a/net/phonet/pn_dev.c
+++ b/net/phonet/pn_dev.c
@@ -44,7 +44,7 @@ struct phonet_net {
struct phonet_routes routes;
};
-static int phonet_net_id __read_mostly;
+static unsigned int phonet_net_id __read_mostly;
static struct phonet_net *phonet_pernet(struct net *net)
{
diff --git a/net/rds/Makefile b/net/rds/Makefile
index 0e72bec..56c7d27 100644
--- a/net/rds/Makefile
+++ b/net/rds/Makefile
@@ -13,5 +13,5 @@
rds_tcp-y := tcp.o tcp_connect.o tcp_listen.o tcp_recv.o \
tcp_send.o tcp_stats.o
-ccflags-$(CONFIG_RDS_DEBUG) := -DDEBUG
+ccflags-$(CONFIG_RDS_DEBUG) := -DRDS_DEBUG
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index 6beaeb1..2ac1e61 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -605,10 +605,14 @@ static void rds_exit(void)
}
module_exit(rds_exit);
+u32 rds_gen_num;
+
static int rds_init(void)
{
int ret;
+ net_get_random_once(&rds_gen_num, sizeof(rds_gen_num));
+
ret = rds_bind_lock_init();
if (ret)
goto out;
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 13f459d..fe9d31c 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -269,6 +269,8 @@ static struct rds_connection *__rds_conn_create(struct net *net,
kmem_cache_free(rds_conn_slab, conn);
conn = found;
} else {
+ conn->c_my_gen_num = rds_gen_num;
+ conn->c_peer_gen_num = 0;
hlist_add_head_rcu(&conn->c_hash_node, head);
rds_cong_add_conn(conn);
rds_conn_count++;
@@ -681,6 +683,7 @@ void rds_conn_path_connect_if_down(struct rds_conn_path *cp)
!test_and_set_bit(RDS_RECONNECT_PENDING, &cp->cp_flags))
queue_delayed_work(rds_wq, &cp->cp_conn_w, 0);
}
+EXPORT_SYMBOL_GPL(rds_conn_path_connect_if_down);
void rds_conn_connect_if_down(struct rds_connection *conn)
{
diff --git a/net/rds/message.c b/net/rds/message.c
index 6cb9106..49bfb51 100644
--- a/net/rds/message.c
+++ b/net/rds/message.c
@@ -42,6 +42,7 @@ static unsigned int rds_exthdr_size[__RDS_EXTHDR_MAX] = {
[RDS_EXTHDR_RDMA] = sizeof(struct rds_ext_header_rdma),
[RDS_EXTHDR_RDMA_DEST] = sizeof(struct rds_ext_header_rdma_dest),
[RDS_EXTHDR_NPATHS] = sizeof(u16),
+[RDS_EXTHDR_GEN_NUM] = sizeof(u32),
};
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 25532a4..ebbf909 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -33,7 +33,7 @@
#define KERNEL_HAS_ATOMIC64
#endif
-#ifdef DEBUG
+#ifdef RDS_DEBUG
#define rdsdebug(fmt, args...) pr_debug("%s(): " fmt, __func__ , ##args)
#else
/* sigh, pr_debug() causes unused variable warnings */
@@ -151,6 +151,9 @@ struct rds_connection {
struct rds_conn_path c_path[RDS_MPATH_WORKERS];
wait_queue_head_t c_hs_waitq; /* handshake waitq */
+
+ u32 c_my_gen_num;
+ u32 c_peer_gen_num;
};
static inline
@@ -243,7 +246,8 @@ struct rds_ext_header_rdma_dest {
/* Extension header announcing number of paths.
* Implicit length = 2 bytes.
*/
-#define RDS_EXTHDR_NPATHS 4
+#define RDS_EXTHDR_NPATHS 5
+#define RDS_EXTHDR_GEN_NUM 6
#define __RDS_EXTHDR_MAX 16 /* for now */
@@ -338,6 +342,7 @@ static inline u32 rds_rdma_cookie_offset(rds_rdma_cookie_t cookie)
#define RDS_MSG_RETRANSMITTED 5
#define RDS_MSG_MAPPED 6
#define RDS_MSG_PAGEVEC 7
+#define RDS_MSG_FLUSH 8
struct rds_message {
atomic_t m_refcount;
@@ -664,6 +669,7 @@ void rds_cong_exit(void);
struct rds_message *rds_cong_update_alloc(struct rds_connection *conn);
/* conn.c */
+extern u32 rds_gen_num;
int rds_conn_init(void);
void rds_conn_exit(void);
struct rds_connection *rds_conn_create(struct net *net,
diff --git a/net/rds/recv.c b/net/rds/recv.c
index cbfabdf..9d0666e 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -120,6 +120,36 @@ static void rds_recv_rcvbuf_delta(struct rds_sock *rs, struct sock *sk,
/* do nothing if no change in cong state */
}
+static void rds_conn_peer_gen_update(struct rds_connection *conn,
+ u32 peer_gen_num)
+{
+ int i;
+ struct rds_message *rm, *tmp;
+ unsigned long flags;
+
+ WARN_ON(conn->c_trans->t_type != RDS_TRANS_TCP);
+ if (peer_gen_num != 0) {
+ if (conn->c_peer_gen_num != 0 &&
+ peer_gen_num != conn->c_peer_gen_num) {
+ for (i = 0; i < RDS_MPATH_WORKERS; i++) {
+ struct rds_conn_path *cp;
+
+ cp = &conn->c_path[i];
+ spin_lock_irqsave(&cp->cp_lock, flags);
+ cp->cp_next_tx_seq = 1;
+ cp->cp_next_rx_seq = 0;
+ list_for_each_entry_safe(rm, tmp,
+ &cp->cp_retrans,
+ m_conn_item) {
+ set_bit(RDS_MSG_FLUSH, &rm->m_flags);
+ }
+ spin_unlock_irqrestore(&cp->cp_lock, flags);
+ }
+ }
+ conn->c_peer_gen_num = peer_gen_num;
+ }
+}
+
/*
* Process all extension headers that come with this message.
*/
@@ -163,7 +193,9 @@ static void rds_recv_hs_exthdrs(struct rds_header *hdr,
union {
struct rds_ext_header_version version;
u16 rds_npaths;
+ u32 rds_gen_num;
} buffer;
+ u32 new_peer_gen_num = 0;
while (1) {
len = sizeof(buffer);
@@ -176,6 +208,9 @@ static void rds_recv_hs_exthdrs(struct rds_header *hdr,
conn->c_npaths = min_t(int, RDS_MPATH_WORKERS,
buffer.rds_npaths);
break;
+ case RDS_EXTHDR_GEN_NUM:
+ new_peer_gen_num = buffer.rds_gen_num;
+ break;
default:
pr_warn_ratelimited("ignoring unknown exthdr type "
"0x%x\n", type);
@@ -183,6 +218,7 @@ static void rds_recv_hs_exthdrs(struct rds_header *hdr,
}
/* if RDS_EXTHDR_NPATHS was not found, default to a single-path */
conn->c_npaths = max_t(int, conn->c_npaths, 1);
+ rds_conn_peer_gen_update(conn, new_peer_gen_num);
}
/* rds_start_mprds() will synchronously start multiple paths when appropriate.
diff --git a/net/rds/send.c b/net/rds/send.c
index 896626b..77c8c6e 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -259,8 +259,9 @@ int rds_send_xmit(struct rds_conn_path *cp)
* connection.
* Therefore, we never retransmit messages with RDMA ops.
*/
- if (rm->rdma.op_active &&
- test_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags)) {
+ if (test_bit(RDS_MSG_FLUSH, &rm->m_flags) ||
+ (rm->rdma.op_active &&
+ test_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags))) {
spin_lock_irqsave(&cp->cp_lock, flags);
if (test_and_clear_bit(RDS_MSG_ON_CONN, &rm->m_flags))
list_move(&rm->m_conn_item, &to_be_dropped);
@@ -1209,6 +1210,10 @@ rds_send_probe(struct rds_conn_path *cp, __be16 sport,
rds_message_add_extension(&rm->m_inc.i_hdr,
RDS_EXTHDR_NPATHS, &npaths,
sizeof(npaths));
+ rds_message_add_extension(&rm->m_inc.i_hdr,
+ RDS_EXTHDR_GEN_NUM,
+ &cp->cp_conn->c_my_gen_num,
+ sizeof(u32));
}
spin_unlock_irqrestore(&cp->cp_lock, flags);
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index fcddacc..1a0399d 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -220,7 +220,7 @@ void rds_tcp_set_callbacks(struct socket *sock, struct rds_conn_path *cp)
write_unlock_bh(&sock->sk->sk_callback_lock);
}
-static void rds_tcp_tc_info(struct socket *sock, unsigned int len,
+static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len,
struct rds_info_iterator *iter,
struct rds_info_lengths *lens)
{
@@ -229,6 +229,7 @@ static void rds_tcp_tc_info(struct socket *sock, unsigned int len,
unsigned long flags;
struct sockaddr_in sin;
int sinlen;
+ struct socket *sock;
spin_lock_irqsave(&rds_tcp_tc_list_lock, flags);
@@ -237,12 +238,17 @@ static void rds_tcp_tc_info(struct socket *sock, unsigned int len,
list_for_each_entry(tc, &rds_tcp_tc_list, t_list_item) {
- sock->ops->getname(sock, (struct sockaddr *)&sin, &sinlen, 0);
- tsinfo.local_addr = sin.sin_addr.s_addr;
- tsinfo.local_port = sin.sin_port;
- sock->ops->getname(sock, (struct sockaddr *)&sin, &sinlen, 1);
- tsinfo.peer_addr = sin.sin_addr.s_addr;
- tsinfo.peer_port = sin.sin_port;
+ sock = tc->t_sock;
+ if (sock) {
+ sock->ops->getname(sock, (struct sockaddr *)&sin,
+ &sinlen, 0);
+ tsinfo.local_addr = sin.sin_addr.s_addr;
+ tsinfo.local_port = sin.sin_port;
+ sock->ops->getname(sock, (struct sockaddr *)&sin,
+ &sinlen, 1);
+ tsinfo.peer_addr = sin.sin_addr.s_addr;
+ tsinfo.peer_port = sin.sin_port;
+ }
tsinfo.hdr_rem = tc->t_tinc_hdr_rem;
tsinfo.data_rem = tc->t_tinc_data_rem;
@@ -360,7 +366,7 @@ struct rds_transport rds_tcp_transport = {
.t_mp_capable = 1,
};
-static int rds_tcp_netid;
+static unsigned int rds_tcp_netid;
/* per-network namespace private data for this module */
struct rds_tcp_net {
diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c
index 05f61c5..d6839d9 100644
--- a/net/rds/tcp_connect.c
+++ b/net/rds/tcp_connect.c
@@ -60,7 +60,19 @@ void rds_tcp_state_change(struct sock *sk)
case TCP_SYN_RECV:
break;
case TCP_ESTABLISHED:
- rds_connect_path_complete(cp, RDS_CONN_CONNECTING);
+ /* Force the peer to reconnect so that we have the
+ * TCP ports going from <smaller-ip>.<transient> to
+ * <larger-ip>.<RDS_TCP_PORT>. We avoid marking the
+ * RDS connection as RDS_CONN_UP until the reconnect,
+ * to avoid RDS datagram loss.
+ */
+ if (cp->cp_conn->c_laddr > cp->cp_conn->c_faddr &&
+ rds_conn_path_transition(cp, RDS_CONN_CONNECTING,
+ RDS_CONN_ERROR)) {
+ rds_conn_path_drop(cp);
+ } else {
+ rds_connect_path_complete(cp, RDS_CONN_CONNECTING);
+ }
break;
case TCP_CLOSE_WAIT:
case TCP_CLOSE:
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index e0b23fb..f74bab3 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -83,27 +83,22 @@ struct rds_tcp_connection *rds_tcp_accept_one_path(struct rds_connection *conn)
{
int i;
bool peer_is_smaller = (conn->c_faddr < conn->c_laddr);
- int npaths = conn->c_npaths;
+ int npaths = max_t(int, 1, conn->c_npaths);
- if (npaths <= 1) {
- struct rds_conn_path *cp = &conn->c_path[0];
- int ret;
-
- ret = rds_conn_path_transition(cp, RDS_CONN_DOWN,
- RDS_CONN_CONNECTING);
- if (!ret)
- rds_conn_path_transition(cp, RDS_CONN_ERROR,
- RDS_CONN_CONNECTING);
- return cp->cp_transport_data;
- }
-
- /* for mprds, paths with cp_index > 0 MUST be initiated by the peer
+ /* for mprds, all paths MUST be initiated by the peer
* with the smaller address.
*/
- if (!peer_is_smaller)
+ if (!peer_is_smaller) {
+ /* Make sure we initiate at least one path if this
+ * has not already been done; rds_start_mprds() will
+ * take care of additional paths, if necessary.
+ */
+ if (npaths == 1)
+ rds_conn_path_connect_if_down(&conn->c_path[0]);
return NULL;
+ }
- for (i = 1; i < npaths; i++) {
+ for (i = 0; i < npaths; i++) {
struct rds_conn_path *cp = &conn->c_path[i];
if (rds_conn_path_transition(cp, RDS_CONN_DOWN,
@@ -171,8 +166,8 @@ int rds_tcp_accept_one(struct socket *sock)
mutex_lock(&rs_tcp->t_conn_path_lock);
cp = rs_tcp->t_cpath;
conn_state = rds_conn_path_state(cp);
- if (conn_state != RDS_CONN_CONNECTING && conn_state != RDS_CONN_UP &&
- conn_state != RDS_CONN_ERROR)
+ WARN_ON(conn_state == RDS_CONN_UP);
+ if (conn_state != RDS_CONN_CONNECTING && conn_state != RDS_CONN_ERROR)
goto rst_nsk;
if (rs_tcp->t_sock) {
/* Need to resolve a duelling SYN between peers.
diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index 89d09b4..dcf4742 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -100,6 +100,9 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
set_bit(RDS_MSG_HAS_ACK_SEQ, &rm->m_flags);
tc->t_last_expected_una = rm->m_ack_seq + 1;
+ if (test_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags))
+ rm->m_inc.i_hdr.h_flags |= RDS_FLAG_RETRANSMITTED;
+
rdsdebug("rm %p tcp nxt %u ack_seq %llu\n",
rm, rds_tcp_snd_nxt(tc),
(unsigned long long)rm->m_ack_seq);
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 4353a29..1ed18d8 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -276,7 +276,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
goto error;
trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage),
- here, ERR_PTR(ret));
+ here, NULL);
spin_lock_bh(&call->conn->params.peer->lock);
hlist_add_head(&call->error_link,
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 44fb8d8..1d87b54 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -1053,7 +1053,7 @@ void rxrpc_data_ready(struct sock *udp_sk)
ASSERT(!irqs_disabled());
- skb = skb_recv_datagram(udp_sk, 0, 1, &ret);
+ skb = skb_recv_udp(udp_sk, 0, 1, &ret);
if (!skb) {
if (ret == -EAGAIN)
return;
@@ -1075,10 +1075,9 @@ void rxrpc_data_ready(struct sock *udp_sk)
__UDP_INC_STATS(&init_net, UDP_MIB_INDATAGRAMS, 0);
- /* The socket buffer we have is owned by UDP, with UDP's data all over
- * it, but we really want our own data there.
+ /* The UDP protocol already released all skb resources;
+ * we are free to add our own data there.
*/
- skb_orphan(skb);
sp = rxrpc_skb(skb);
/* dig out the RxRPC connection details */
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 941b724..862eea6 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -193,8 +193,8 @@ static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
fl6->fl6_dport = htons(7001);
fl6->fl6_sport = htons(7000);
dst = ip6_route_output(&init_net, NULL, fl6);
- if (IS_ERR(dst)) {
- _leave(" [route err %ld]", PTR_ERR(dst));
+ if (dst->error) {
+ _leave(" [route err %d]", dst->error);
return;
}
break;
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index a512b18..f893d18 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1028,8 +1028,7 @@ static struct nlattr *find_dump_kind(const struct nlmsghdr *n)
if (tb[1] == NULL)
return NULL;
- if (nla_parse(tb2, TCA_ACT_MAX, nla_data(tb[1]),
- nla_len(tb[1]), NULL) < 0)
+ if (nla_parse_nested(tb2, TCA_ACT_MAX, tb[1], NULL) < 0)
return NULL;
kind = tb2[TCA_ACT_KIND];
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 9ff06cf..1aa4ecf 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -33,7 +33,7 @@ struct tcf_bpf_cfg {
bool is_ebpf;
};
-static int bpf_net_id;
+static unsigned int bpf_net_id;
static struct tc_action_ops act_bpf_ops;
static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act,
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index eae07a2..ab80629 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -30,7 +30,7 @@
#define CONNMARK_TAB_MASK 3
-static int connmark_net_id;
+static unsigned int connmark_net_id;
static struct tc_action_ops act_connmark_ops;
static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a,
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index e0defce..a0edd80 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -42,7 +42,7 @@ static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = {
[TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), },
};
-static int csum_net_id;
+static unsigned int csum_net_id;
static struct tc_action_ops act_csum_ops;
static int tcf_csum_init(struct net *net, struct nlattr *nla,
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index e0aa30f..e6c874a 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -25,7 +25,7 @@
#define GACT_TAB_MASK 15
-static int gact_net_id;
+static unsigned int gact_net_id;
static struct tc_action_ops act_gact_ops;
#ifdef CONFIG_GACT_PROB
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 95c463c..80b848d 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -35,7 +35,7 @@
#define IFE_TAB_MASK 15
-static int ife_net_id;
+static unsigned int ife_net_id;
static int max_metacnt = IFE_META_MAX + 1;
static struct tc_action_ops act_ife_ops;
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 378c1c9..992ef8d 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -30,10 +30,10 @@
#define IPT_TAB_MASK 15
-static int ipt_net_id;
+static unsigned int ipt_net_id;
static struct tc_action_ops act_ipt_ops;
-static int xt_net_id;
+static unsigned int xt_net_id;
static struct tc_action_ops act_xt_ops;
static int ipt_init_target(struct xt_entry_target *t, char *table,
@@ -213,6 +213,12 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a,
int ret = 0, result = 0;
struct tcf_ipt *ipt = to_ipt(a);
struct xt_action_param par;
+ struct nf_hook_state state = {
+ .net = dev_net(skb->dev),
+ .in = skb->dev,
+ .hook = ipt->tcfi_hook,
+ .pf = NFPROTO_IPV4,
+ };
if (skb_unclone(skb, GFP_ATOMIC))
return TC_ACT_UNSPEC;
@@ -226,13 +232,9 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a,
* worry later - danger - this API seems to have changed
* from earlier kernels
*/
- par.net = dev_net(skb->dev);
- par.in = skb->dev;
- par.out = NULL;
- par.hooknum = ipt->tcfi_hook;
+ par.state = &state;
par.target = ipt->tcfi_t->u.kernel.target;
par.targinfo = ipt->tcfi_t->data;
- par.family = NFPROTO_IPV4;
ret = par.target->target(skb, &par);
switch (ret) {
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 2d93be6..b2d417b 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -70,7 +70,7 @@ static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = {
[TCA_MIRRED_PARMS] = { .len = sizeof(struct tc_mirred) },
};
-static int mirred_net_id;
+static unsigned int mirred_net_id;
static struct tc_action_ops act_mirred_ops;
static bool dev_is_mac_header_xmit(const struct net_device *dev)
@@ -249,8 +249,11 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets,
u64 lastuse)
{
- tcf_lastuse_update(&a->tcfa_tm);
+ struct tcf_mirred *m = to_mirred(a);
+ struct tcf_t *tm = &m->tcf_tm;
+
_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
+ tm->lastuse = lastuse;
}
static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 8e8b0cc..9b6aec6 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -31,7 +31,7 @@
#define NAT_TAB_MASK 15
-static int nat_net_id;
+static unsigned int nat_net_id;
static struct tc_action_ops act_nat_ops;
static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = {
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index b54d56d..eda3220 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -25,7 +25,7 @@
#define PEDIT_TAB_MASK 15
-static int pedit_net_id;
+static unsigned int pedit_net_id;
static struct tc_action_ops act_pedit_ops;
static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = {
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index d1bd248..c990b73 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -55,7 +55,7 @@ struct tc_police_compat {
/* Each policer is serialized by its individual spinlock */
-static int police_net_id;
+static unsigned int police_net_id;
static struct tc_action_ops act_police_ops;
static int tcf_act_police_walker(struct net *net, struct sk_buff *skb,
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 289af6f..823a73a 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -26,7 +26,7 @@
#define SIMP_TAB_MASK 7
-static int simp_net_id;
+static unsigned int simp_net_id;
static struct tc_action_ops act_simp_ops;
#define SIMP_MAX_DATA 32
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 024f3a3..06ccae3 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -29,7 +29,7 @@
#define SKBEDIT_TAB_MASK 15
-static int skbedit_net_id;
+static unsigned int skbedit_net_id;
static struct tc_action_ops act_skbedit_ops;
static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index e7d9638..3b7074e 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -22,7 +22,7 @@
#define SKBMOD_TAB_MASK 15
-static int skbmod_net_id;
+static unsigned int skbmod_net_id;
static struct tc_action_ops act_skbmod_ops;
#define MAX_EDIT_LEN ETH_HLEN
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index af47bdf..7af7125 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -16,14 +16,13 @@
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/dst.h>
-#include <net/dst_metadata.h>
#include <linux/tc_act/tc_tunnel_key.h>
#include <net/tc_act/tc_tunnel_key.h>
#define TUNNEL_KEY_TAB_MASK 15
-static int tunnel_key_net_id;
+static unsigned int tunnel_key_net_id;
static struct tc_action_ops act_tunnel_key_ops;
static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a,
@@ -67,6 +66,7 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
[TCA_TUNNEL_KEY_ENC_IPV6_SRC] = { .len = sizeof(struct in6_addr) },
[TCA_TUNNEL_KEY_ENC_IPV6_DST] = { .len = sizeof(struct in6_addr) },
[TCA_TUNNEL_KEY_ENC_KEY_ID] = { .type = NLA_U32 },
+ [TCA_TUNNEL_KEY_ENC_DST_PORT] = {.type = NLA_U16},
};
static int tunnel_key_init(struct net *net, struct nlattr *nla,
@@ -81,6 +81,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
struct tc_tunnel_key *parm;
struct tcf_tunnel_key *t;
bool exists = false;
+ __be16 dst_port = 0;
__be64 key_id;
int ret = 0;
int err;
@@ -111,6 +112,9 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
key_id = key32_to_tunnel_id(nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID]));
+ if (tb[TCA_TUNNEL_KEY_ENC_DST_PORT])
+ dst_port = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_DST_PORT]);
+
if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] &&
tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) {
__be32 saddr;
@@ -120,7 +124,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
daddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]);
metadata = __ip_tun_set_dst(saddr, daddr, 0, 0,
- TUNNEL_KEY, key_id, 0);
+ dst_port, TUNNEL_KEY,
+ key_id, 0);
} else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] &&
tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]) {
struct in6_addr saddr;
@@ -130,7 +135,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
daddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]);
metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, 0,
- TUNNEL_KEY, key_id, 0);
+ dst_port, TUNNEL_KEY,
+ key_id, 0);
}
if (!metadata) {
@@ -258,7 +264,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
if (nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id) ||
tunnel_key_dump_addresses(skb,
- ¶ms->tcft_enc_metadata->u.tun_info))
+ ¶ms->tcft_enc_metadata->u.tun_info) ||
+ nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst))
goto nla_put_failure;
}
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index b57fcbc..19e0dba 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -21,7 +21,7 @@
#define VLAN_TAB_MASK 15
-static int vlan_net_id;
+static unsigned int vlan_net_id;
static struct tc_action_ops act_vlan_ops;
static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 2ee29a3..2b2a797 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -345,7 +345,8 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
if (err == 0) {
struct tcf_proto *next = rtnl_dereference(tp->next);
- tfilter_notify(net, skb, n, tp, fh,
+ tfilter_notify(net, skb, n, tp,
+ t->tcm_handle,
RTM_DELTFILTER, false);
if (tcf_destroy(tp, false))
RCU_INIT_POINTER(*back, next);
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index f6f40fb..e8dd09a 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -43,6 +43,7 @@ struct fl_flow_key {
struct flow_dissector_key_ipv4_addrs enc_ipv4;
struct flow_dissector_key_ipv6_addrs enc_ipv6;
};
+ struct flow_dissector_key_ports enc_tp;
} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
struct fl_flow_mask_range {
@@ -155,6 +156,8 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
}
skb_key.enc_key_id.keyid = tunnel_id_to_key32(key->tun_id);
+ skb_key.enc_tp.src = key->tp_src;
+ skb_key.enc_tp.dst = key->tp_dst;
}
skb_key.indev_ifindex = skb->skb_iif;
@@ -269,6 +272,14 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc);
}
+static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f)
+{
+ list_del_rcu(&f->list);
+ fl_hw_destroy_filter(tp, (unsigned long)f);
+ tcf_unbind_filter(tp, &f->res);
+ call_rcu(&f->rcu, fl_destroy_filter);
+}
+
static bool fl_destroy(struct tcf_proto *tp, bool force)
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
@@ -277,11 +288,8 @@ static bool fl_destroy(struct tcf_proto *tp, bool force)
if (!force && !list_empty(&head->filters))
return false;
- list_for_each_entry_safe(f, next, &head->filters, list) {
- fl_hw_destroy_filter(tp, (unsigned long)f);
- list_del_rcu(&f->list);
- call_rcu(&f->rcu, fl_destroy_filter);
- }
+ list_for_each_entry_safe(f, next, &head->filters, list)
+ __fl_delete(tp, f);
RCU_INIT_POINTER(tp->root, NULL);
if (head->mask_assigned)
rhashtable_destroy(&head->ht);
@@ -339,6 +347,14 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
[TCA_FLOWER_KEY_TCP_DST_MASK] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_UDP_SRC_MASK] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_UDP_DST_MASK] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_SCTP_SRC_MASK] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_SCTP_DST_MASK] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_SCTP_SRC] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_SCTP_DST] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_ENC_UDP_SRC_PORT] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_ENC_UDP_DST_PORT] = { .type = NLA_U16 },
+ [TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK] = { .type = NLA_U16 },
};
static void fl_set_key_val(struct nlattr **tb,
@@ -448,6 +464,13 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST,
&mask->tp.dst, TCA_FLOWER_KEY_UDP_DST_MASK,
sizeof(key->tp.dst));
+ } else if (key->basic.ip_proto == IPPROTO_SCTP) {
+ fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_SCTP_SRC,
+ &mask->tp.src, TCA_FLOWER_KEY_SCTP_SRC_MASK,
+ sizeof(key->tp.src));
+ fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_SCTP_DST,
+ &mask->tp.dst, TCA_FLOWER_KEY_SCTP_DST_MASK,
+ sizeof(key->tp.dst));
}
if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] ||
@@ -484,6 +507,14 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
&mask->enc_key_id.keyid, TCA_FLOWER_UNSPEC,
sizeof(key->enc_key_id.keyid));
+ fl_set_key_val(tb, &key->enc_tp.src, TCA_FLOWER_KEY_ENC_UDP_SRC_PORT,
+ &mask->enc_tp.src, TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK,
+ sizeof(key->enc_tp.src));
+
+ fl_set_key_val(tb, &key->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT,
+ &mask->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,
+ sizeof(key->enc_tp.dst));
+
return 0;
}
@@ -551,6 +582,18 @@ static void fl_init_dissector(struct cls_fl_head *head,
FLOW_DISSECTOR_KEY_PORTS, tp);
FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
FLOW_DISSECTOR_KEY_VLAN, vlan);
+ FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id);
+ FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, enc_ipv4);
+ FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, enc_ipv6);
+ if (FL_KEY_IS_MASKED(&mask->key, enc_ipv4) ||
+ FL_KEY_IS_MASKED(&mask->key, enc_ipv6))
+ FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_ENC_CONTROL,
+ enc_control);
+ FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+ FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp);
skb_flow_dissector_init(&head->dissector, keys, cnt);
}
@@ -741,10 +784,7 @@ static int fl_delete(struct tcf_proto *tp, unsigned long arg)
rhashtable_remove_fast(&head->ht, &f->ht_node,
head->ht_params);
- list_del_rcu(&f->list);
- fl_hw_destroy_filter(tp, (unsigned long)f);
- tcf_unbind_filter(tp, &f->res);
- call_rcu(&f->rcu, fl_destroy_filter);
+ __fl_delete(tp, f);
return 0;
}
@@ -895,6 +935,14 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
&mask->tp.dst, TCA_FLOWER_KEY_UDP_DST_MASK,
sizeof(key->tp.dst))))
goto nla_put_failure;
+ else if (key->basic.ip_proto == IPPROTO_SCTP &&
+ (fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_SCTP_SRC,
+ &mask->tp.src, TCA_FLOWER_KEY_SCTP_SRC_MASK,
+ sizeof(key->tp.src)) ||
+ fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_SCTP_DST,
+ &mask->tp.dst, TCA_FLOWER_KEY_SCTP_DST_MASK,
+ sizeof(key->tp.dst))))
+ goto nla_put_failure;
if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
(fl_dump_key_val(skb, &key->enc_ipv4.src,
@@ -920,7 +968,17 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
if (fl_dump_key_val(skb, &key->enc_key_id, TCA_FLOWER_KEY_ENC_KEY_ID,
&mask->enc_key_id, TCA_FLOWER_UNSPEC,
- sizeof(key->enc_key_id)))
+ sizeof(key->enc_key_id)) ||
+ fl_dump_key_val(skb, &key->enc_tp.src,
+ TCA_FLOWER_KEY_ENC_UDP_SRC_PORT,
+ &mask->enc_tp.src,
+ TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK,
+ sizeof(key->enc_tp.src)) ||
+ fl_dump_key_val(skb, &key->enc_tp.dst,
+ TCA_FLOWER_KEY_ENC_UDP_DST_PORT,
+ &mask->enc_tp.dst,
+ TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,
+ sizeof(key->enc_tp.dst)))
goto nla_put_failure;
nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags);
diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c
index c66ca94..c1b23e3 100644
--- a/net/sched/em_ipset.c
+++ b/net/sched/em_ipset.c
@@ -57,17 +57,20 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em,
struct xt_action_param acpar;
const struct xt_set_info *set = (const void *) em->data;
struct net_device *dev, *indev = NULL;
+ struct nf_hook_state state = {
+ .net = em->net,
+ };
int ret, network_offset;
switch (tc_skb_protocol(skb)) {
case htons(ETH_P_IP):
- acpar.family = NFPROTO_IPV4;
+ state.pf = NFPROTO_IPV4;
if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
return 0;
acpar.thoff = ip_hdrlen(skb);
break;
case htons(ETH_P_IPV6):
- acpar.family = NFPROTO_IPV6;
+ state.pf = NFPROTO_IPV6;
if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr)))
return 0;
/* doesn't call ipv6_find_hdr() because ipset doesn't use thoff, yet */
@@ -77,9 +80,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em,
return 0;
}
- acpar.hooknum = 0;
-
- opt.family = acpar.family;
+ opt.family = state.pf;
opt.dim = set->dim;
opt.flags = set->flags;
opt.cmdflags = 0;
@@ -95,9 +96,9 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em,
if (skb->skb_iif)
indev = dev_get_by_index_rcu(em->net, skb->skb_iif);
- acpar.net = em->net;
- acpar.in = indev ? indev : dev;
- acpar.out = dev;
+ state.in = indev ? indev : dev;
+ state.out = dev;
+ acpar.state = &state;
ret = ip_set_test(set->index, skb, &acpar, &opt);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 206dc24..f337f1b 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -960,6 +960,17 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
sch->handle = handle;
+ /* This exist to keep backward compatible with a userspace
+ * loophole, what allowed userspace to get IFF_NO_QUEUE
+ * facility on older kernels by setting tx_queue_len=0 (prior
+ * to qdisc init), and then forgot to reinit tx_queue_len
+ * before again attaching a qdisc.
+ */
+ if ((dev->priv_flags & IFF_NO_QUEUE) && (dev->tx_queue_len == 0)) {
+ dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN;
+ netdev_info(dev, "Caught tx_queue_len zero misconfig\n");
+ }
+
if (!ops->init || (err = ops->init(sch, tca[TCA_OPTIONS])) == 0) {
if (qdisc_is_percpu_stats(sch)) {
sch->cpu_bstats =
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 18e7524..86309a3 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -245,7 +245,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
skb_orphan(skb);
}
- root = &q->fq_root[hash_32((u32)(long)sk, q->fq_trees_log)];
+ root = &q->fq_root[hash_ptr(sk, q->fq_trees_log)];
if (q->flows >= (2U << q->fq_trees_log) &&
q->inactive_flows > q->flows/2)
@@ -599,7 +599,7 @@ static void fq_rehash(struct fq_sched_data *q,
kmem_cache_free(fq_flow_cachep, of);
continue;
}
- nroot = &new_array[hash_32((u32)(long)of->sk, new_log)];
+ nroot = &new_array[hash_ptr(of->sk, new_log)];
np = &nroot->rb_node;
parent = NULL;
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index f10d339..68428e1 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -700,11 +700,15 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
/* Set the peer's active state. */
peer->state = peer_state;
+ /* Add this peer into the transport hashtable */
+ if (sctp_hash_transport(peer)) {
+ sctp_transport_free(peer);
+ return NULL;
+ }
+
/* Attach the remote transport to our asoc. */
list_add_tail_rcu(&peer->transports, &asoc->peer.transport_addr_list);
asoc->peer.transport_count++;
- /* Add this peer into the transport hashtable */
- sctp_hash_transport(peer);
/* If we do not yet have a primary path, set one. */
if (!asoc->peer.primary_path) {
diff --git a/net/sctp/input.c b/net/sctp/input.c
index a2ea1d1..458e506 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -181,9 +181,10 @@ int sctp_rcv(struct sk_buff *skb)
* bound to another interface, via SO_BINDTODEVICE, treat it as OOTB
*/
if (sk->sk_bound_dev_if && (sk->sk_bound_dev_if != af->skb_iif(skb))) {
- if (asoc) {
- sctp_association_put(asoc);
+ if (transport) {
+ sctp_transport_put(transport);
asoc = NULL;
+ transport = NULL;
} else {
sctp_endpoint_put(ep);
ep = NULL;
@@ -269,8 +270,8 @@ int sctp_rcv(struct sk_buff *skb)
bh_unlock_sock(sk);
/* Release the asoc/ep ref we took in the lookup calls. */
- if (asoc)
- sctp_association_put(asoc);
+ if (transport)
+ sctp_transport_put(transport);
else
sctp_endpoint_put(ep);
@@ -283,8 +284,8 @@ int sctp_rcv(struct sk_buff *skb)
discard_release:
/* Release the asoc/ep ref we took in the lookup calls. */
- if (asoc)
- sctp_association_put(asoc);
+ if (transport)
+ sctp_transport_put(transport);
else
sctp_endpoint_put(ep);
@@ -300,6 +301,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
struct sctp_inq *inqueue = &chunk->rcvr->inqueue;
+ struct sctp_transport *t = chunk->transport;
struct sctp_ep_common *rcvr = NULL;
int backloged = 0;
@@ -351,7 +353,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
done:
/* Release the refs we took in sctp_add_backlog */
if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type)
- sctp_association_put(sctp_assoc(rcvr));
+ sctp_transport_put(t);
else if (SCTP_EP_TYPE_SOCKET == rcvr->type)
sctp_endpoint_put(sctp_ep(rcvr));
else
@@ -363,6 +365,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb)
{
struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk;
+ struct sctp_transport *t = chunk->transport;
struct sctp_ep_common *rcvr = chunk->rcvr;
int ret;
@@ -373,7 +376,7 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb)
* from us
*/
if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type)
- sctp_association_hold(sctp_assoc(rcvr));
+ sctp_transport_hold(t);
else if (SCTP_EP_TYPE_SOCKET == rcvr->type)
sctp_endpoint_hold(sctp_ep(rcvr));
else
@@ -537,15 +540,15 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb,
return sk;
out:
- sctp_association_put(asoc);
+ sctp_transport_put(transport);
return NULL;
}
/* Common cleanup code for icmp/icmpv6 error handler. */
-void sctp_err_finish(struct sock *sk, struct sctp_association *asoc)
+void sctp_err_finish(struct sock *sk, struct sctp_transport *t)
{
bh_unlock_sock(sk);
- sctp_association_put(asoc);
+ sctp_transport_put(t);
}
/*
@@ -641,7 +644,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info)
}
out_unlock:
- sctp_err_finish(sk, asoc);
+ sctp_err_finish(sk, transport);
}
/*
@@ -787,10 +790,9 @@ static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(struct net *net,
/* rhashtable for transport */
struct sctp_hash_cmp_arg {
- const struct sctp_endpoint *ep;
- const union sctp_addr *laddr;
- const union sctp_addr *paddr;
- const struct net *net;
+ const union sctp_addr *paddr;
+ const struct net *net;
+ u16 lport;
};
static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg,
@@ -798,7 +800,6 @@ static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg,
{
struct sctp_transport *t = (struct sctp_transport *)ptr;
const struct sctp_hash_cmp_arg *x = arg->key;
- struct sctp_association *asoc;
int err = 1;
if (!sctp_cmp_addr_exact(&t->ipaddr, x->paddr))
@@ -806,19 +807,10 @@ static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg,
if (!sctp_transport_hold(t))
return err;
- asoc = t->asoc;
- if (!net_eq(sock_net(asoc->base.sk), x->net))
+ if (!net_eq(sock_net(t->asoc->base.sk), x->net))
goto out;
- if (x->ep) {
- if (x->ep != asoc->ep)
- goto out;
- } else {
- if (x->laddr->v4.sin_port != htons(asoc->base.bind_addr.port))
- goto out;
- if (!sctp_bind_addr_match(&asoc->base.bind_addr,
- x->laddr, sctp_sk(asoc->base.sk)))
- goto out;
- }
+ if (x->lport != htons(t->asoc->base.bind_addr.port))
+ goto out;
err = 0;
out:
@@ -848,11 +840,9 @@ static inline u32 sctp_hash_key(const void *data, u32 len, u32 seed)
const struct sctp_hash_cmp_arg *x = data;
const union sctp_addr *paddr = x->paddr;
const struct net *net = x->net;
- u16 lport;
+ u16 lport = x->lport;
u32 addr;
- lport = x->ep ? htons(x->ep->base.bind_addr.port) :
- x->laddr->v4.sin_port;
if (paddr->sa.sa_family == AF_INET6)
addr = jhash(&paddr->v6.sin6_addr, 16, seed);
else
@@ -872,29 +862,32 @@ static const struct rhashtable_params sctp_hash_params = {
int sctp_transport_hashtable_init(void)
{
- return rhashtable_init(&sctp_transport_hashtable, &sctp_hash_params);
+ return rhltable_init(&sctp_transport_hashtable, &sctp_hash_params);
}
void sctp_transport_hashtable_destroy(void)
{
- rhashtable_destroy(&sctp_transport_hashtable);
+ rhltable_destroy(&sctp_transport_hashtable);
}
-void sctp_hash_transport(struct sctp_transport *t)
+int sctp_hash_transport(struct sctp_transport *t)
{
struct sctp_hash_cmp_arg arg;
+ int err;
if (t->asoc->temp)
- return;
+ return 0;
- arg.ep = t->asoc->ep;
- arg.paddr = &t->ipaddr;
arg.net = sock_net(t->asoc->base.sk);
+ arg.paddr = &t->ipaddr;
+ arg.lport = htons(t->asoc->base.bind_addr.port);
-reinsert:
- if (rhashtable_lookup_insert_key(&sctp_transport_hashtable, &arg,
- &t->node, sctp_hash_params) == -EBUSY)
- goto reinsert;
+ err = rhltable_insert_key(&sctp_transport_hashtable, &arg,
+ &t->node, sctp_hash_params);
+ if (err)
+ pr_err_once("insert transport fail, errno %d\n", err);
+
+ return err;
}
void sctp_unhash_transport(struct sctp_transport *t)
@@ -902,39 +895,62 @@ void sctp_unhash_transport(struct sctp_transport *t)
if (t->asoc->temp)
return;
- rhashtable_remove_fast(&sctp_transport_hashtable, &t->node,
- sctp_hash_params);
+ rhltable_remove(&sctp_transport_hashtable, &t->node,
+ sctp_hash_params);
}
+/* return a transport with holding it */
struct sctp_transport *sctp_addrs_lookup_transport(
struct net *net,
const union sctp_addr *laddr,
const union sctp_addr *paddr)
{
+ struct rhlist_head *tmp, *list;
+ struct sctp_transport *t;
struct sctp_hash_cmp_arg arg = {
- .ep = NULL,
- .laddr = laddr,
.paddr = paddr,
.net = net,
+ .lport = laddr->v4.sin_port,
};
- return rhashtable_lookup_fast(&sctp_transport_hashtable, &arg,
- sctp_hash_params);
+ list = rhltable_lookup(&sctp_transport_hashtable, &arg,
+ sctp_hash_params);
+
+ rhl_for_each_entry_rcu(t, tmp, list, node) {
+ if (!sctp_transport_hold(t))
+ continue;
+
+ if (sctp_bind_addr_match(&t->asoc->base.bind_addr,
+ laddr, sctp_sk(t->asoc->base.sk)))
+ return t;
+ sctp_transport_put(t);
+ }
+
+ return NULL;
}
+/* return a transport without holding it, as it's only used under sock lock */
struct sctp_transport *sctp_epaddr_lookup_transport(
const struct sctp_endpoint *ep,
const union sctp_addr *paddr)
{
struct net *net = sock_net(ep->base.sk);
+ struct rhlist_head *tmp, *list;
+ struct sctp_transport *t;
struct sctp_hash_cmp_arg arg = {
- .ep = ep,
.paddr = paddr,
.net = net,
+ .lport = htons(ep->base.bind_addr.port),
};
- return rhashtable_lookup_fast(&sctp_transport_hashtable, &arg,
- sctp_hash_params);
+ list = rhltable_lookup(&sctp_transport_hashtable, &arg,
+ sctp_hash_params);
+
+ rhl_for_each_entry_rcu(t, tmp, list, node)
+ if (ep == t->asoc->ep)
+ return t;
+
+ return NULL;
}
/* Look up an association. */
@@ -948,15 +964,12 @@ static struct sctp_association *__sctp_lookup_association(
struct sctp_association *asoc = NULL;
t = sctp_addrs_lookup_transport(net, local, peer);
- if (!t || !sctp_transport_hold(t))
+ if (!t)
goto out;
asoc = t->asoc;
- sctp_association_hold(asoc);
*pt = t;
- sctp_transport_put(t);
-
out:
return asoc;
}
@@ -986,7 +999,7 @@ int sctp_has_association(struct net *net,
struct sctp_transport *transport;
if ((asoc = sctp_lookup_association(net, laddr, paddr, &transport))) {
- sctp_association_put(asoc);
+ sctp_transport_put(transport);
return 1;
}
@@ -1021,7 +1034,6 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net,
struct sctphdr *sh = sctp_hdr(skb);
union sctp_params params;
sctp_init_chunk_t *init;
- struct sctp_transport *transport;
struct sctp_af *af;
/*
@@ -1052,7 +1064,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net,
af->from_addr_param(paddr, params.addr, sh->source, 0);
- asoc = __sctp_lookup_association(net, laddr, paddr, &transport);
+ asoc = __sctp_lookup_association(net, laddr, paddr, transportp);
if (asoc)
return asoc;
}
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index f473779..176af30 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -198,7 +198,7 @@ static void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
}
out_unlock:
- sctp_err_finish(sk, asoc);
+ sctp_err_finish(sk, transport);
out:
if (likely(idev != NULL))
in6_dev_put(idev);
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 4282b48..f5320a8 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -399,181 +399,72 @@ static void sctp_packet_set_owner_w(struct sk_buff *skb, struct sock *sk)
atomic_inc(&sk->sk_wmem_alloc);
}
-/* All packets are sent to the network through this function from
- * sctp_outq_tail().
- *
- * The return value is a normal kernel error return value.
- */
-int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
+static int sctp_packet_pack(struct sctp_packet *packet,
+ struct sk_buff *head, int gso, gfp_t gfp)
{
struct sctp_transport *tp = packet->transport;
- struct sctp_association *asoc = tp->asoc;
- struct sctphdr *sh;
- struct sk_buff *nskb = NULL, *head = NULL;
+ struct sctp_auth_chunk *auth = NULL;
struct sctp_chunk *chunk, *tmp;
- struct sock *sk;
- int err = 0;
- int padding; /* How much padding do we need? */
- int pkt_size;
- __u8 has_data = 0;
- int gso = 0;
- int pktcount = 0;
- struct dst_entry *dst;
- unsigned char *auth = NULL; /* pointer to auth in skb data */
+ int pkt_count = 0, pkt_size;
+ struct sock *sk = head->sk;
+ struct sk_buff *nskb;
+ int auth_len = 0;
- pr_debug("%s: packet:%p\n", __func__, packet);
-
- /* Do NOT generate a chunkless packet. */
- if (list_empty(&packet->chunk_list))
- return err;
-
- /* Set up convenience variables... */
- chunk = list_entry(packet->chunk_list.next, struct sctp_chunk, list);
- sk = chunk->skb->sk;
-
- /* Allocate the head skb, or main one if not in GSO */
- if (packet->size > tp->pathmtu && !packet->ipfragok) {
- if (sk_can_gso(sk)) {
- gso = 1;
- pkt_size = packet->overhead;
- } else {
- /* If this happens, we trash this packet and try
- * to build a new one, hopefully correct this
- * time. Application may notice this error.
- */
- pr_err_once("Trying to GSO but underlying device doesn't support it.");
- goto err;
- }
- } else {
- pkt_size = packet->size;
- }
- head = alloc_skb(pkt_size + MAX_HEADER, gfp);
- if (!head)
- goto err;
if (gso) {
- NAPI_GRO_CB(head)->last = head;
skb_shinfo(head)->gso_type = sk->sk_gso_type;
+ NAPI_GRO_CB(head)->last = head;
+ } else {
+ nskb = head;
+ pkt_size = packet->size;
+ goto merge;
}
- /* Make sure the outbound skb has enough header room reserved. */
- skb_reserve(head, packet->overhead + MAX_HEADER);
-
- /* Set the owning socket so that we know where to get the
- * destination IP address.
- */
- sctp_packet_set_owner_w(head, sk);
-
- if (!sctp_transport_dst_check(tp)) {
- sctp_transport_route(tp, NULL, sctp_sk(sk));
- if (asoc && (asoc->param_flags & SPP_PMTUD_ENABLE)) {
- sctp_assoc_sync_pmtu(sk, asoc);
- }
- }
- dst = dst_clone(tp->dst);
- if (!dst) {
- if (asoc)
- IP_INC_STATS(sock_net(asoc->base.sk),
- IPSTATS_MIB_OUTNOROUTES);
- goto nodst;
- }
- skb_dst_set(head, dst);
-
- /* Build the SCTP header. */
- sh = (struct sctphdr *)skb_push(head, sizeof(struct sctphdr));
- skb_reset_transport_header(head);
- sh->source = htons(packet->source_port);
- sh->dest = htons(packet->destination_port);
-
- /* From 6.8 Adler-32 Checksum Calculation:
- * After the packet is constructed (containing the SCTP common
- * header and one or more control or DATA chunks), the
- * transmitter shall:
- *
- * 1) Fill in the proper Verification Tag in the SCTP common
- * header and initialize the checksum field to 0's.
- */
- sh->vtag = htonl(packet->vtag);
- sh->checksum = 0;
-
- pr_debug("***sctp_transmit_packet***\n");
-
do {
- /* Set up convenience variables... */
- chunk = list_entry(packet->chunk_list.next, struct sctp_chunk, list);
- pktcount++;
+ /* calculate the pkt_size and alloc nskb */
+ pkt_size = packet->overhead;
+ list_for_each_entry_safe(chunk, tmp, &packet->chunk_list,
+ list) {
+ int padded = SCTP_PAD4(chunk->skb->len);
- /* Calculate packet size, so it fits in PMTU. Leave
- * other chunks for the next packets.
- */
- if (gso) {
- pkt_size = packet->overhead;
- list_for_each_entry(chunk, &packet->chunk_list, list) {
- int padded = SCTP_PAD4(chunk->skb->len);
-
- if (pkt_size + padded > tp->pathmtu)
- break;
- pkt_size += padded;
- }
-
- /* Allocate a new skb. */
- nskb = alloc_skb(pkt_size + MAX_HEADER, gfp);
- if (!nskb)
- goto nomem;
-
- /* Make sure the outbound skb has enough header
- * room reserved.
- */
- skb_reserve(nskb, packet->overhead + MAX_HEADER);
- } else {
- nskb = head;
+ if (chunk == packet->auth)
+ auth_len = padded;
+ else if (auth_len + padded + packet->overhead >
+ tp->pathmtu)
+ return 0;
+ else if (pkt_size + padded > tp->pathmtu)
+ break;
+ pkt_size += padded;
}
+ nskb = alloc_skb(pkt_size + MAX_HEADER, gfp);
+ if (!nskb)
+ return 0;
+ skb_reserve(nskb, packet->overhead + MAX_HEADER);
- /**
- * 3.2 Chunk Field Descriptions
- *
- * The total length of a chunk (including Type, Length and
- * Value fields) MUST be a multiple of 4 bytes. If the length
- * of the chunk is not a multiple of 4 bytes, the sender MUST
- * pad the chunk with all zero bytes and this padding is not
- * included in the chunk length field. The sender should
- * never pad with more than 3 bytes.
- *
- * [This whole comment explains SCTP_PAD4() below.]
- */
-
+merge:
+ /* merge chunks into nskb and append nskb into head list */
pkt_size -= packet->overhead;
list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) {
+ int padding;
+
list_del_init(&chunk->list);
if (sctp_chunk_is_data(chunk)) {
- /* 6.3.1 C4) When data is in flight and when allowed
- * by rule C5, a new RTT measurement MUST be made each
- * round trip. Furthermore, new RTT measurements
- * SHOULD be made no more than once per round-trip
- * for a given destination transport address.
- */
-
if (!sctp_chunk_retransmitted(chunk) &&
!tp->rto_pending) {
chunk->rtt_in_progress = 1;
tp->rto_pending = 1;
}
-
- has_data = 1;
}
padding = SCTP_PAD4(chunk->skb->len) - chunk->skb->len;
if (padding)
memset(skb_put(chunk->skb, padding), 0, padding);
- /* if this is the auth chunk that we are adding,
- * store pointer where it will be added and put
- * the auth into the packet.
- */
if (chunk == packet->auth)
- auth = skb_tail_pointer(nskb);
+ auth = (struct sctp_auth_chunk *)
+ skb_tail_pointer(nskb);
- memcpy(skb_put(nskb, chunk->skb->len),
- chunk->skb->data, chunk->skb->len);
+ memcpy(skb_put(nskb, chunk->skb->len), chunk->skb->data,
+ chunk->skb->len);
pr_debug("*** Chunk:%p[%s] %s 0x%x, length:%d, chunk->skb->len:%d, rtt_in_progress:%d\n",
chunk,
@@ -583,11 +474,6 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
ntohs(chunk->chunk_hdr->length), chunk->skb->len,
chunk->rtt_in_progress);
- /* If this is a control chunk, this is our last
- * reference. Free data chunks after they've been
- * acknowledged or have failed.
- * Re-queue auth chunks if needed.
- */
pkt_size -= SCTP_PAD4(chunk->skb->len);
if (!sctp_chunk_is_data(chunk) && chunk != packet->auth)
@@ -597,160 +483,161 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
break;
}
- /* SCTP-AUTH, Section 6.2
- * The sender MUST calculate the MAC as described in RFC2104 [2]
- * using the hash function H as described by the MAC Identifier and
- * the shared association key K based on the endpoint pair shared key
- * described by the shared key identifier. The 'data' used for the
- * computation of the AUTH-chunk is given by the AUTH chunk with its
- * HMAC field set to zero (as shown in Figure 6) followed by all
- * chunks that are placed after the AUTH chunk in the SCTP packet.
- */
- if (auth)
- sctp_auth_calculate_hmac(asoc, nskb,
- (struct sctp_auth_chunk *)auth,
- gfp);
-
- if (packet->auth) {
- if (!list_empty(&packet->chunk_list)) {
- /* We will generate more packets, so re-queue
- * auth chunk.
- */
+ if (auth) {
+ sctp_auth_calculate_hmac(tp->asoc, nskb, auth, gfp);
+ /* free auth if no more chunks, or add it back */
+ if (list_empty(&packet->chunk_list))
+ sctp_chunk_free(packet->auth);
+ else
list_add(&packet->auth->list,
&packet->chunk_list);
- } else {
- sctp_chunk_free(packet->auth);
- packet->auth = NULL;
+ }
+
+ if (gso) {
+ if (skb_gro_receive(&head, nskb)) {
+ kfree_skb(nskb);
+ return 0;
}
+ if (WARN_ON_ONCE(skb_shinfo(head)->gso_segs >=
+ sk->sk_gso_max_segs))
+ return 0;
}
- if (!gso)
- break;
-
- if (skb_gro_receive(&head, nskb)) {
- kfree_skb(nskb);
- goto nomem;
- }
- nskb = NULL;
- if (WARN_ON_ONCE(skb_shinfo(head)->gso_segs >=
- sk->sk_gso_max_segs))
- goto nomem;
+ pkt_count++;
} while (!list_empty(&packet->chunk_list));
- /* 2) Calculate the Adler-32 checksum of the whole packet,
- * including the SCTP common header and all the
- * chunks.
- *
- * Note: Adler-32 is no longer applicable, as has been replaced
- * by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>.
- *
- * If it's a GSO packet, it's postponed to sctp_skb_segment.
- */
- if (!sctp_checksum_disable || gso) {
- if (!gso && (!(dst->dev->features & NETIF_F_SCTP_CRC) ||
- dst_xfrm(dst) || packet->ipfragok)) {
- sh->checksum = sctp_compute_cksum(head, 0);
- } else {
- /* no need to seed pseudo checksum for SCTP */
- head->ip_summed = CHECKSUM_PARTIAL;
- head->csum_start = skb_transport_header(head) - head->head;
- head->csum_offset = offsetof(struct sctphdr, checksum);
- }
- }
-
- /* IP layer ECN support
- * From RFC 2481
- * "The ECN-Capable Transport (ECT) bit would be set by the
- * data sender to indicate that the end-points of the
- * transport protocol are ECN-capable."
- *
- * Now setting the ECT bit all the time, as it should not cause
- * any problems protocol-wise even if our peer ignores it.
- *
- * Note: The works for IPv6 layer checks this bit too later
- * in transmission. See IP6_ECN_flow_xmit().
- */
- tp->af_specific->ecn_capable(sk);
-
- /* Set up the IP options. */
- /* BUG: not implemented
- * For v4 this all lives somewhere in sk->sk_opt...
- */
-
- /* Dump that on IP! */
- if (asoc) {
- asoc->stats.opackets += pktcount;
- if (asoc->peer.last_sent_to != tp)
- /* Considering the multiple CPU scenario, this is a
- * "correcter" place for last_sent_to. --xguo
- */
- asoc->peer.last_sent_to = tp;
- }
-
- if (has_data) {
- struct timer_list *timer;
- unsigned long timeout;
-
- /* Restart the AUTOCLOSE timer when sending data. */
- if (sctp_state(asoc, ESTABLISHED) &&
- asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) {
- timer = &asoc->timers[SCTP_EVENT_TIMEOUT_AUTOCLOSE];
- timeout = asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE];
-
- if (!mod_timer(timer, jiffies + timeout))
- sctp_association_hold(asoc);
- }
- }
-
- pr_debug("***sctp_transmit_packet*** skb->len:%d\n", head->len);
-
if (gso) {
- /* Cleanup our debris for IP stacks */
memset(head->cb, 0, max(sizeof(struct inet_skb_parm),
sizeof(struct inet6_skb_parm)));
-
- skb_shinfo(head)->gso_segs = pktcount;
+ skb_shinfo(head)->gso_segs = pkt_count;
skb_shinfo(head)->gso_size = GSO_BY_FRAGS;
-
- /* We have to refresh this in case we are xmiting to
- * more than one transport at a time
- */
rcu_read_lock();
- if (__sk_dst_get(sk) != tp->dst) {
+ if (skb_dst(head) != tp->dst) {
dst_hold(tp->dst);
sk_setup_caps(sk, tp->dst);
}
rcu_read_unlock();
+ goto chksum;
+ }
+
+ if (sctp_checksum_disable)
+ return 1;
+
+ if (!(skb_dst(head)->dev->features & NETIF_F_SCTP_CRC) ||
+ dst_xfrm(skb_dst(head)) || packet->ipfragok) {
+ struct sctphdr *sh =
+ (struct sctphdr *)skb_transport_header(head);
+
+ sh->checksum = sctp_compute_cksum(head, 0);
+ } else {
+chksum:
+ head->ip_summed = CHECKSUM_PARTIAL;
+ head->csum_start = skb_transport_header(head) - head->head;
+ head->csum_offset = offsetof(struct sctphdr, checksum);
+ }
+
+ return pkt_count;
+}
+
+/* All packets are sent to the network through this function from
+ * sctp_outq_tail().
+ *
+ * The return value is always 0 for now.
+ */
+int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
+{
+ struct sctp_transport *tp = packet->transport;
+ struct sctp_association *asoc = tp->asoc;
+ struct sctp_chunk *chunk, *tmp;
+ int pkt_count, gso = 0;
+ struct dst_entry *dst;
+ struct sk_buff *head;
+ struct sctphdr *sh;
+ struct sock *sk;
+
+ pr_debug("%s: packet:%p\n", __func__, packet);
+ if (list_empty(&packet->chunk_list))
+ return 0;
+ chunk = list_entry(packet->chunk_list.next, struct sctp_chunk, list);
+ sk = chunk->skb->sk;
+
+ /* check gso */
+ if (packet->size > tp->pathmtu && !packet->ipfragok) {
+ if (!sk_can_gso(sk)) {
+ pr_err_once("Trying to GSO but underlying device doesn't support it.");
+ goto out;
+ }
+ gso = 1;
+ }
+
+ /* alloc head skb */
+ head = alloc_skb((gso ? packet->overhead : packet->size) +
+ MAX_HEADER, gfp);
+ if (!head)
+ goto out;
+ skb_reserve(head, packet->overhead + MAX_HEADER);
+ sctp_packet_set_owner_w(head, sk);
+
+ /* set sctp header */
+ sh = (struct sctphdr *)skb_push(head, sizeof(struct sctphdr));
+ skb_reset_transport_header(head);
+ sh->source = htons(packet->source_port);
+ sh->dest = htons(packet->destination_port);
+ sh->vtag = htonl(packet->vtag);
+ sh->checksum = 0;
+
+ /* update dst if in need */
+ if (!sctp_transport_dst_check(tp)) {
+ sctp_transport_route(tp, NULL, sctp_sk(sk));
+ if (asoc && asoc->param_flags & SPP_PMTUD_ENABLE)
+ sctp_assoc_sync_pmtu(sk, asoc);
+ }
+ dst = dst_clone(tp->dst);
+ if (!dst) {
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+ kfree_skb(head);
+ goto out;
+ }
+ skb_dst_set(head, dst);
+
+ /* pack up chunks */
+ pkt_count = sctp_packet_pack(packet, head, gso, gfp);
+ if (!pkt_count) {
+ kfree_skb(head);
+ goto out;
+ }
+ pr_debug("***sctp_transmit_packet*** skb->len:%d\n", head->len);
+
+ /* start autoclose timer */
+ if (packet->has_data && sctp_state(asoc, ESTABLISHED) &&
+ asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE]) {
+ struct timer_list *timer =
+ &asoc->timers[SCTP_EVENT_TIMEOUT_AUTOCLOSE];
+ unsigned long timeout =
+ asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE];
+
+ if (!mod_timer(timer, jiffies + timeout))
+ sctp_association_hold(asoc);
+ }
+
+ /* sctp xmit */
+ tp->af_specific->ecn_capable(sk);
+ if (asoc) {
+ asoc->stats.opackets += pkt_count;
+ if (asoc->peer.last_sent_to != tp)
+ asoc->peer.last_sent_to = tp;
}
head->ignore_df = packet->ipfragok;
tp->af_specific->sctp_xmit(head, tp);
- goto out;
-nomem:
- if (packet->auth && list_empty(&packet->auth->list))
- sctp_chunk_free(packet->auth);
-
-nodst:
- /* FIXME: Returning the 'err' will effect all the associations
- * associated with a socket, although only one of the paths of the
- * association is unreachable.
- * The real failure of a transport or association can be passed on
- * to the user via notifications. So setting this error may not be
- * required.
- */
- /* err = -EHOSTUNREACH; */
- kfree_skb(head);
-
-err:
+out:
list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) {
list_del_init(&chunk->list);
if (!sctp_chunk_is_data(chunk))
sctp_chunk_free(chunk);
}
-
-out:
sctp_packet_reset(packet);
- return err;
+ return 0;
}
/********************************************************************
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 026e3bc..8ec20a6 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3422,6 +3422,12 @@ sctp_disposition_t sctp_sf_ootb(struct net *net,
return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
commands);
+ /* Report violation if chunk len overflows */
+ ch_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length));
+ if (ch_end > skb_tail_pointer(skb))
+ return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
+ commands);
+
/* Now that we know we at least have a chunk header,
* do things that are type appropriate.
*/
@@ -3453,12 +3459,6 @@ sctp_disposition_t sctp_sf_ootb(struct net *net,
}
}
- /* Report violation if chunk len overflows */
- ch_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length));
- if (ch_end > skb_tail_pointer(skb))
- return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
- commands);
-
ch = (sctp_chunkhdr_t *) ch_end;
} while (ch_end < skb_tail_pointer(skb));
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index fb02c70..d5f4b4a 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1214,9 +1214,12 @@ static int __sctp_connect(struct sock *sk,
timeo = sock_sndtimeo(sk, f_flags & O_NONBLOCK);
- err = sctp_wait_for_connect(asoc, &timeo);
- if ((err == 0 || err == -EINPROGRESS) && assoc_id)
+ if (assoc_id)
*assoc_id = asoc->assoc_id;
+ err = sctp_wait_for_connect(asoc, &timeo);
+ /* Note: the asoc may be freed after the return of
+ * sctp_wait_for_connect.
+ */
/* Don't free association on exit. */
asoc = NULL;
@@ -4282,19 +4285,18 @@ static void sctp_shutdown(struct sock *sk, int how)
{
struct net *net = sock_net(sk);
struct sctp_endpoint *ep;
- struct sctp_association *asoc;
if (!sctp_style(sk, TCP))
return;
- if (how & SEND_SHUTDOWN) {
+ ep = sctp_sk(sk)->ep;
+ if (how & SEND_SHUTDOWN && !list_empty(&ep->asocs)) {
+ struct sctp_association *asoc;
+
sk->sk_state = SCTP_SS_CLOSING;
- ep = sctp_sk(sk)->ep;
- if (!list_empty(&ep->asocs)) {
- asoc = list_entry(ep->asocs.next,
- struct sctp_association, asocs);
- sctp_primitive_SHUTDOWN(net, asoc, NULL);
- }
+ asoc = list_entry(ep->asocs.next,
+ struct sctp_association, asocs);
+ sctp_primitive_SHUTDOWN(net, asoc, NULL);
}
}
@@ -4390,10 +4392,7 @@ int sctp_transport_walk_start(struct rhashtable_iter *iter)
{
int err;
- err = rhashtable_walk_init(&sctp_transport_hashtable, iter,
- GFP_KERNEL);
- if (err)
- return err;
+ rhltable_walk_enter(&sctp_transport_hashtable, iter);
err = rhashtable_walk_start(iter);
if (err && err != -EAGAIN) {
@@ -4477,15 +4476,12 @@ int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *),
rcu_read_lock();
transport = sctp_addrs_lookup_transport(net, laddr, paddr);
- if (!transport || !sctp_transport_hold(transport))
+ if (!transport)
goto out;
- sctp_association_hold(transport->asoc);
- sctp_transport_put(transport);
-
rcu_read_unlock();
err = cb(transport, p);
- sctp_association_put(transport->asoc);
+ sctp_transport_put(transport);
out:
return err;
@@ -4687,7 +4683,7 @@ static int sctp_getsockopt_disable_fragments(struct sock *sk, int len,
static int sctp_getsockopt_events(struct sock *sk, int len, char __user *optval,
int __user *optlen)
{
- if (len <= 0)
+ if (len == 0)
return -EINVAL;
if (len > sizeof(struct sctp_event_subscribe))
len = sizeof(struct sctp_event_subscribe);
@@ -6430,6 +6426,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
if (get_user(len, optlen))
return -EFAULT;
+ if (len < 0)
+ return -EINVAL;
+
lock_sock(sk);
switch (optname) {
diff --git a/net/socket.c b/net/socket.c
index 5a9bf5e..f9e26c6 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -518,8 +518,22 @@ static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer,
return used;
}
+int sockfs_setattr(struct dentry *dentry, struct iattr *iattr)
+{
+ int err = simple_setattr(dentry, iattr);
+
+ if (!err) {
+ struct socket *sock = SOCKET_I(d_inode(dentry));
+
+ sock->sk->sk_uid = iattr->ia_uid;
+ }
+
+ return err;
+}
+
static const struct inode_operations sockfs_inode_ops = {
.listxattr = sockfs_listxattr,
+ .setattr = sockfs_setattr,
};
/**
@@ -877,6 +891,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock,
* what to do with it - that's up to the protocol still.
*/
+static struct ns_common *get_net_ns(struct ns_common *ns)
+{
+ return &get_net(container_of(ns, struct net, ns))->ns;
+}
+
static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
struct socket *sock;
@@ -945,6 +964,13 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
err = dlci_ioctl_hook(cmd, argp);
mutex_unlock(&dlci_ioctl_mutex);
break;
+ case SIOCGSKNS:
+ err = -EPERM;
+ if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+ break;
+
+ err = open_related_ns(&net->ns, get_net_ns);
+ break;
default:
err = sock_do_ioctl(net, sock, cmd, arg);
break;
@@ -2038,6 +2064,8 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
if (err)
break;
++datagrams;
+ if (msg_data_left(&msg_sys))
+ break;
cond_resched();
}
@@ -3093,6 +3121,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
case SIOCSIFVLAN:
case SIOCADDDLCI:
case SIOCDELDLCI:
+ case SIOCGSKNS:
return sock_ioctl(file, cmd, arg);
case SIOCGIFFLAGS:
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index d8bd97a..3dfd769 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1616,7 +1616,7 @@ gss_validate(struct rpc_task *task, __be32 *p)
{
struct rpc_cred *cred = task->tk_rqstp->rq_cred;
struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
- __be32 seq;
+ __be32 *seq = NULL;
struct kvec iov;
struct xdr_buf verf_buf;
struct xdr_netobj mic;
@@ -1631,9 +1631,12 @@ gss_validate(struct rpc_task *task, __be32 *p)
goto out_bad;
if (flav != RPC_AUTH_GSS)
goto out_bad;
- seq = htonl(task->tk_rqstp->rq_seqno);
- iov.iov_base = &seq;
- iov.iov_len = sizeof(seq);
+ seq = kmalloc(4, GFP_NOFS);
+ if (!seq)
+ goto out_bad;
+ *seq = htonl(task->tk_rqstp->rq_seqno);
+ iov.iov_base = seq;
+ iov.iov_len = 4;
xdr_buf_from_iov(&iov, &verf_buf);
mic.data = (u8 *)p;
mic.len = len;
@@ -1653,11 +1656,13 @@ gss_validate(struct rpc_task *task, __be32 *p)
gss_put_ctx(ctx);
dprintk("RPC: %5u %s: gss_verify_mic succeeded.\n",
task->tk_pid, __func__);
+ kfree(seq);
return p + XDR_QUADLEN(len);
out_bad:
gss_put_ctx(ctx);
dprintk("RPC: %5u %s failed ret %ld.\n", task->tk_pid, __func__,
PTR_ERR(ret));
+ kfree(seq);
return ret;
}
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index 244245b..90115ce 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -166,8 +166,8 @@ make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen,
unsigned int usage, struct xdr_netobj *cksumout)
{
struct scatterlist sg[1];
- int err;
- u8 checksumdata[GSS_KRB5_MAX_CKSUM_LEN];
+ int err = -1;
+ u8 *checksumdata;
u8 rc4salt[4];
struct crypto_ahash *md5;
struct crypto_ahash *hmac_md5;
@@ -187,23 +187,22 @@ make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen,
return GSS_S_FAILURE;
}
+ checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS);
+ if (!checksumdata)
+ return GSS_S_FAILURE;
+
md5 = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(md5))
- return GSS_S_FAILURE;
+ goto out_free_cksum;
hmac_md5 = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0,
CRYPTO_ALG_ASYNC);
- if (IS_ERR(hmac_md5)) {
- crypto_free_ahash(md5);
- return GSS_S_FAILURE;
- }
+ if (IS_ERR(hmac_md5))
+ goto out_free_md5;
req = ahash_request_alloc(md5, GFP_KERNEL);
- if (!req) {
- crypto_free_ahash(hmac_md5);
- crypto_free_ahash(md5);
- return GSS_S_FAILURE;
- }
+ if (!req)
+ goto out_free_hmac_md5;
ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
@@ -232,11 +231,8 @@ make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen,
ahash_request_free(req);
req = ahash_request_alloc(hmac_md5, GFP_KERNEL);
- if (!req) {
- crypto_free_ahash(hmac_md5);
- crypto_free_ahash(md5);
- return GSS_S_FAILURE;
- }
+ if (!req)
+ goto out_free_hmac_md5;
ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
@@ -258,8 +254,12 @@ make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen,
cksumout->len = kctx->gk5e->cksumlength;
out:
ahash_request_free(req);
- crypto_free_ahash(md5);
+out_free_hmac_md5:
crypto_free_ahash(hmac_md5);
+out_free_md5:
+ crypto_free_ahash(md5);
+out_free_cksum:
+ kfree(checksumdata);
return err ? GSS_S_FAILURE : 0;
}
@@ -276,8 +276,8 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen,
struct crypto_ahash *tfm;
struct ahash_request *req;
struct scatterlist sg[1];
- int err;
- u8 checksumdata[GSS_KRB5_MAX_CKSUM_LEN];
+ int err = -1;
+ u8 *checksumdata;
unsigned int checksumlen;
if (kctx->gk5e->ctype == CKSUMTYPE_HMAC_MD5_ARCFOUR)
@@ -291,15 +291,17 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen,
return GSS_S_FAILURE;
}
- tfm = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC);
- if (IS_ERR(tfm))
+ checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS);
+ if (checksumdata == NULL)
return GSS_S_FAILURE;
+ tfm = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(tfm))
+ goto out_free_cksum;
+
req = ahash_request_alloc(tfm, GFP_KERNEL);
- if (!req) {
- crypto_free_ahash(tfm);
- return GSS_S_FAILURE;
- }
+ if (!req)
+ goto out_free_ahash;
ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
@@ -349,7 +351,10 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen,
cksumout->len = kctx->gk5e->cksumlength;
out:
ahash_request_free(req);
+out_free_ahash:
crypto_free_ahash(tfm);
+out_free_cksum:
+ kfree(checksumdata);
return err ? GSS_S_FAILURE : 0;
}
@@ -368,8 +373,8 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen,
struct crypto_ahash *tfm;
struct ahash_request *req;
struct scatterlist sg[1];
- int err;
- u8 checksumdata[GSS_KRB5_MAX_CKSUM_LEN];
+ int err = -1;
+ u8 *checksumdata;
unsigned int checksumlen;
if (kctx->gk5e->keyed_cksum == 0) {
@@ -383,16 +388,18 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen,
return GSS_S_FAILURE;
}
+ checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS);
+ if (!checksumdata)
+ return GSS_S_FAILURE;
+
tfm = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(tfm))
- return GSS_S_FAILURE;
+ goto out_free_cksum;
checksumlen = crypto_ahash_digestsize(tfm);
req = ahash_request_alloc(tfm, GFP_KERNEL);
- if (!req) {
- crypto_free_ahash(tfm);
- return GSS_S_FAILURE;
- }
+ if (!req)
+ goto out_free_ahash;
ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
@@ -433,7 +440,10 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen,
}
out:
ahash_request_free(req);
+out_free_ahash:
crypto_free_ahash(tfm);
+out_free_cksum:
+ kfree(checksumdata);
return err ? GSS_S_FAILURE : 0;
}
@@ -666,14 +676,17 @@ gss_krb5_cts_crypt(struct crypto_skcipher *cipher, struct xdr_buf *buf,
u32 ret;
struct scatterlist sg[1];
SKCIPHER_REQUEST_ON_STACK(req, cipher);
- u8 data[GSS_KRB5_MAX_BLOCKSIZE * 2];
+ u8 *data;
struct page **save_pages;
u32 len = buf->len - offset;
- if (len > ARRAY_SIZE(data)) {
+ if (len > GSS_KRB5_MAX_BLOCKSIZE * 2) {
WARN_ON(0);
return -ENOMEM;
}
+ data = kmalloc(GSS_KRB5_MAX_BLOCKSIZE * 2, GFP_NOFS);
+ if (!data)
+ return -ENOMEM;
/*
* For encryption, we want to read from the cleartext
@@ -708,6 +721,7 @@ gss_krb5_cts_crypt(struct crypto_skcipher *cipher, struct xdr_buf *buf,
ret = write_bytes_to_xdr_buf(buf, offset, data, len);
out:
+ kfree(data);
return ret;
}
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index d67f7e1..45662d7 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -718,30 +718,37 @@ gss_write_null_verf(struct svc_rqst *rqstp)
static int
gss_write_verf(struct svc_rqst *rqstp, struct gss_ctx *ctx_id, u32 seq)
{
- __be32 xdr_seq;
+ __be32 *xdr_seq;
u32 maj_stat;
struct xdr_buf verf_data;
struct xdr_netobj mic;
__be32 *p;
struct kvec iov;
+ int err = -1;
svc_putnl(rqstp->rq_res.head, RPC_AUTH_GSS);
- xdr_seq = htonl(seq);
+ xdr_seq = kmalloc(4, GFP_KERNEL);
+ if (!xdr_seq)
+ return -1;
+ *xdr_seq = htonl(seq);
- iov.iov_base = &xdr_seq;
- iov.iov_len = sizeof(xdr_seq);
+ iov.iov_base = xdr_seq;
+ iov.iov_len = 4;
xdr_buf_from_iov(&iov, &verf_data);
p = rqstp->rq_res.head->iov_base + rqstp->rq_res.head->iov_len;
mic.data = (u8 *)(p + 1);
maj_stat = gss_get_mic(ctx_id, &verf_data, &mic);
if (maj_stat != GSS_S_COMPLETE)
- return -1;
+ goto out;
*p++ = htonl(mic.len);
memset((u8 *)p + mic.len, 0, round_up_to_quad(mic.len) - mic.len);
p += XDR_QUADLEN(mic.len);
if (!xdr_ressize_check(rqstp, p))
- return -1;
- return 0;
+ goto out;
+ err = 0;
+out:
+ kfree(xdr_seq);
+ return err;
}
struct gss_domain {
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 34dd7b2..62a4827 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2753,14 +2753,18 @@ EXPORT_SYMBOL_GPL(rpc_cap_max_reconnect_timeout);
void rpc_clnt_xprt_switch_put(struct rpc_clnt *clnt)
{
+ rcu_read_lock();
xprt_switch_put(rcu_dereference(clnt->cl_xpi.xpi_xpswitch));
+ rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_put);
void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt)
{
+ rcu_read_lock();
rpc_xprt_switch_add_xprt(rcu_dereference(clnt->cl_xpi.xpi_xpswitch),
xprt);
+ rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_add_xprt);
@@ -2770,9 +2774,8 @@ bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt,
struct rpc_xprt_switch *xps;
bool ret;
- xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch);
-
rcu_read_lock();
+ xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch);
ret = rpc_xprt_switch_has_addr(xps, sap);
rcu_read_unlock();
return ret;
diff --git a/net/sunrpc/netns.h b/net/sunrpc/netns.h
index df58268..394ce52 100644
--- a/net/sunrpc/netns.h
+++ b/net/sunrpc/netns.h
@@ -34,7 +34,7 @@ struct sunrpc_net {
struct proc_dir_entry *use_gssp_proc;
};
-extern int sunrpc_net_id;
+extern unsigned int sunrpc_net_id;
int ip_map_cache_create(struct net *);
void ip_map_cache_destroy(struct net *);
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index ee5d3d2..d1c330a 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -24,7 +24,7 @@
#include "netns.h"
-int sunrpc_net_id;
+unsigned int sunrpc_net_id;
EXPORT_SYMBOL_GPL(sunrpc_net_id);
static __net_init int sunrpc_init_net(struct net *net)
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index e2a55dc..78da4ae 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -547,7 +547,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp)
err = kernel_recvmsg(svsk->sk_sock, &msg, NULL,
0, 0, MSG_PEEK | MSG_DONTWAIT);
if (err >= 0)
- skb = skb_recv_datagram(svsk->sk_sk, 0, 1, &err);
+ skb = skb_recv_udp(svsk->sk_sk, 0, 1, &err);
if (skb == NULL) {
if (err != -EAGAIN) {
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 2109495..26b26be 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -44,18 +44,20 @@
* being done.
*
* When the underlying transport disconnects, MRs are left in one of
- * three states:
+ * four states:
*
* INVALID: The MR was not in use before the QP entered ERROR state.
- * (Or, the LOCAL_INV WR has not completed or flushed yet).
- *
- * STALE: The MR was being registered or unregistered when the QP
- * entered ERROR state, and the pending WR was flushed.
*
* VALID: The MR was registered before the QP entered ERROR state.
*
- * When frwr_op_map encounters STALE and VALID MRs, they are recovered
- * with ib_dereg_mr and then are re-initialized. Beause MR recovery
+ * FLUSHED_FR: The MR was being registered when the QP entered ERROR
+ * state, and the pending WR was flushed.
+ *
+ * FLUSHED_LI: The MR was being invalidated when the QP entered ERROR
+ * state, and the pending WR was flushed.
+ *
+ * When frwr_op_map encounters FLUSHED and VALID MRs, they are recovered
+ * with ib_dereg_mr and then are re-initialized. Because MR recovery
* allocates fresh resources, it is deferred to a workqueue, and the
* recovered MRs are placed back on the rb_mws list when recovery is
* complete. frwr_op_map allocates another MR for the current RPC while
@@ -177,12 +179,15 @@ __frwr_reset_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *r)
static void
frwr_op_recover_mr(struct rpcrdma_mw *mw)
{
+ enum rpcrdma_frmr_state state = mw->frmr.fr_state;
struct rpcrdma_xprt *r_xprt = mw->mw_xprt;
struct rpcrdma_ia *ia = &r_xprt->rx_ia;
int rc;
rc = __frwr_reset_mr(ia, mw);
- ib_dma_unmap_sg(ia->ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir);
+ if (state != FRMR_FLUSHED_LI)
+ ib_dma_unmap_sg(ia->ri_device,
+ mw->mw_sg, mw->mw_nents, mw->mw_dir);
if (rc)
goto out_release;
@@ -262,10 +267,8 @@ frwr_op_maxpages(struct rpcrdma_xprt *r_xprt)
}
static void
-__frwr_sendcompletion_flush(struct ib_wc *wc, struct rpcrdma_frmr *frmr,
- const char *wr)
+__frwr_sendcompletion_flush(struct ib_wc *wc, const char *wr)
{
- frmr->fr_state = FRMR_IS_STALE;
if (wc->status != IB_WC_WR_FLUSH_ERR)
pr_err("rpcrdma: %s: %s (%u/0x%x)\n",
wr, ib_wc_status_msg(wc->status),
@@ -288,7 +291,8 @@ frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc)
if (wc->status != IB_WC_SUCCESS) {
cqe = wc->wr_cqe;
frmr = container_of(cqe, struct rpcrdma_frmr, fr_cqe);
- __frwr_sendcompletion_flush(wc, frmr, "fastreg");
+ frmr->fr_state = FRMR_FLUSHED_FR;
+ __frwr_sendcompletion_flush(wc, "fastreg");
}
}
@@ -308,7 +312,8 @@ frwr_wc_localinv(struct ib_cq *cq, struct ib_wc *wc)
if (wc->status != IB_WC_SUCCESS) {
cqe = wc->wr_cqe;
frmr = container_of(cqe, struct rpcrdma_frmr, fr_cqe);
- __frwr_sendcompletion_flush(wc, frmr, "localinv");
+ frmr->fr_state = FRMR_FLUSHED_LI;
+ __frwr_sendcompletion_flush(wc, "localinv");
}
}
@@ -328,8 +333,10 @@ frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc)
/* WARNING: Only wr_cqe and status are reliable at this point */
cqe = wc->wr_cqe;
frmr = container_of(cqe, struct rpcrdma_frmr, fr_cqe);
- if (wc->status != IB_WC_SUCCESS)
- __frwr_sendcompletion_flush(wc, frmr, "localinv");
+ if (wc->status != IB_WC_SUCCESS) {
+ frmr->fr_state = FRMR_FLUSHED_LI;
+ __frwr_sendcompletion_flush(wc, "localinv");
+ }
complete(&frmr->fr_linv_done);
}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index 2d8545c..20027f8 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -177,18 +177,26 @@ xprt_rdma_bc_allocate(struct rpc_task *task)
return -EINVAL;
}
+ /* svc_rdma_sendto releases this page */
page = alloc_page(RPCRDMA_DEF_GFP);
if (!page)
return -ENOMEM;
-
rqst->rq_buffer = page_address(page);
+
+ rqst->rq_rbuffer = kmalloc(rqst->rq_rcvsize, RPCRDMA_DEF_GFP);
+ if (!rqst->rq_rbuffer) {
+ put_page(page);
+ return -ENOMEM;
+ }
return 0;
}
static void
xprt_rdma_bc_free(struct rpc_task *task)
{
- /* No-op: ctxt and page have already been freed. */
+ struct rpc_rqst *rqst = task->tk_rqstp;
+
+ kfree(rqst->rq_rbuffer);
}
static int
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 0d35b76..6e1bba3 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -216,7 +216,8 @@ struct rpcrdma_rep {
enum rpcrdma_frmr_state {
FRMR_IS_INVALID, /* ready to be used */
FRMR_IS_VALID, /* in use */
- FRMR_IS_STALE, /* failed completion */
+ FRMR_FLUSHED_FR, /* flushed FASTREG WR */
+ FRMR_FLUSHED_LI, /* flushed LOCALINV WR */
};
struct rpcrdma_frmr {
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 1758665..af392d9 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1080,7 +1080,7 @@ static void xs_udp_data_receive(struct sock_xprt *transport)
if (sk == NULL)
goto out;
for (;;) {
- skb = skb_recv_datagram(sk, 0, 1, &err);
+ skb = skb_recv_udp(sk, 0, 1, &err);
if (skb != NULL) {
xs_udp_data_read_skb(&transport->xprt, sk, skb);
consume_skb(skb);
@@ -2563,6 +2563,7 @@ static int bc_malloc(struct rpc_task *task)
buf->len = PAGE_SIZE;
rqst->rq_buffer = buf->data;
+ rqst->rq_rbuffer = (char *)rqst->rq_buffer + rqst->rq_callsize;
return 0;
}
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 6f145b5..017801f 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -768,6 +768,9 @@ int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
u32 mask = BR_LEARNING | BR_LEARNING_SYNC | BR_FLOOD;
int err;
+ if (!netif_is_bridge_port(dev))
+ return -EOPNOTSUPP;
+
err = switchdev_port_attr_get(dev, &attr);
if (err && err != -EOPNOTSUPP)
return err;
@@ -923,6 +926,9 @@ int switchdev_port_bridge_setlink(struct net_device *dev,
struct nlattr *afspec;
int err = 0;
+ if (!netif_is_bridge_port(dev))
+ return -EOPNOTSUPP;
+
protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
IFLA_PROTINFO);
if (protinfo) {
@@ -956,6 +962,9 @@ int switchdev_port_bridge_dellink(struct net_device *dev,
{
struct nlattr *afspec;
+ if (!netif_is_bridge_port(dev))
+ return -EOPNOTSUPP;
+
afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
IFLA_AF_SPEC);
if (afspec)
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index 753f774..aa1babb 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -247,11 +247,17 @@ int tipc_bcast_rcv(struct net *net, struct tipc_link *l, struct sk_buff *skb)
*
* RCU is locked, no other locks set
*/
-void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l, u32 acked)
+void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l,
+ struct tipc_msg *hdr)
{
struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq;
+ u16 acked = msg_bcast_ack(hdr);
struct sk_buff_head xmitq;
+ /* Ignore bc acks sent by peer before bcast synch point was received */
+ if (msg_bc_ack_invalid(hdr))
+ return;
+
__skb_queue_head_init(&xmitq);
tipc_bcast_lock(net);
@@ -279,11 +285,11 @@ int tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l,
__skb_queue_head_init(&xmitq);
tipc_bcast_lock(net);
- if (msg_type(hdr) == STATE_MSG) {
+ if (msg_type(hdr) != STATE_MSG) {
+ tipc_link_bc_init_rcv(l, hdr);
+ } else if (!msg_bc_ack_invalid(hdr)) {
tipc_link_bc_ack_rcv(l, msg_bcast_ack(hdr), &xmitq);
rc = tipc_link_bc_sync_rcv(l, hdr, &xmitq);
- } else {
- tipc_link_bc_init_rcv(l, hdr);
}
tipc_bcast_unlock(net);
diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h
index 5ffe344..855d53c 100644
--- a/net/tipc/bcast.h
+++ b/net/tipc/bcast.h
@@ -55,7 +55,8 @@ void tipc_bcast_dec_bearer_dst_cnt(struct net *net, int bearer_id);
int tipc_bcast_get_mtu(struct net *net);
int tipc_bcast_xmit(struct net *net, struct sk_buff_head *list);
int tipc_bcast_rcv(struct net *net, struct tipc_link *l, struct sk_buff *skb);
-void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l, u32 acked);
+void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l,
+ struct tipc_msg *hdr);
int tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l,
struct tipc_msg *hdr);
int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg);
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 236b043..0b982d0 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -47,7 +47,7 @@
#include <linux/module.h>
/* configurable TIPC parameters */
-int tipc_net_id __read_mostly;
+unsigned int tipc_net_id __read_mostly;
int sysctl_tipc_rmem[3] __read_mostly; /* min/default/max */
static int __net_init tipc_init_net(struct net *net)
diff --git a/net/tipc/core.h b/net/tipc/core.h
index a1845fb..5cc5398 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -74,7 +74,7 @@ struct tipc_monitor;
#define MAX_BEARERS 3
#define TIPC_DEF_MON_THRESHOLD 32
-extern int tipc_net_id __read_mostly;
+extern unsigned int tipc_net_id __read_mostly;
extern int sysctl_tipc_rmem[3] __read_mostly;
extern int sysctl_tipc_named_timeout __read_mostly;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index b36e16c..1055164 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1312,6 +1312,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
msg_set_next_sent(hdr, l->snd_nxt);
msg_set_ack(hdr, l->rcv_nxt - 1);
msg_set_bcast_ack(hdr, bcl->rcv_nxt - 1);
+ msg_set_bc_ack_invalid(hdr, !node_up);
msg_set_last_bcast(hdr, l->bc_sndlink->snd_nxt - 1);
msg_set_link_tolerance(hdr, tolerance);
msg_set_linkprio(hdr, priority);
@@ -1574,6 +1575,7 @@ static void tipc_link_build_bc_init_msg(struct tipc_link *l,
__skb_queue_head_init(&list);
if (!tipc_link_build_bc_proto_msg(l->bc_rcvlink, false, 0, &list))
return;
+ msg_set_bc_ack_invalid(buf_msg(skb_peek(&list)), true);
tipc_link_xmit(l, &list, xmitq);
}
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index c3832cd..8d40861 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -95,7 +95,7 @@ struct plist;
#define TIPC_MEDIA_INFO_OFFSET 5
struct tipc_skb_cb {
- void *handle;
+ u32 bytes_read;
struct sk_buff *tail;
bool validated;
bool wakeup_pending;
@@ -714,6 +714,23 @@ static inline void msg_set_peer_stopping(struct tipc_msg *m, u32 s)
msg_set_bits(m, 5, 13, 0x1, s);
}
+static inline bool msg_bc_ack_invalid(struct tipc_msg *m)
+{
+ switch (msg_user(m)) {
+ case BCAST_PROTOCOL:
+ case NAME_DISTRIBUTOR:
+ case LINK_PROTOCOL:
+ return msg_bits(m, 5, 14, 0x1);
+ default:
+ return false;
+ }
+}
+
+static inline void msg_set_bc_ack_invalid(struct tipc_msg *m, bool invalid)
+{
+ msg_set_bits(m, 5, 14, 0x1, invalid);
+}
+
static inline char *msg_media_addr(struct tipc_msg *m)
{
return (char *)&m->hdr[TIPC_MEDIA_INFO_OFFSET];
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index a04fe9b..c1cfd92 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -156,6 +156,7 @@ static void named_distribute(struct net *net, struct sk_buff_head *list,
pr_warn("Bulk publication failure\n");
return;
}
+ msg_set_bc_ack_invalid(buf_msg(skb), true);
item = (struct distr_item *)msg_data(buf_msg(skb));
}
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 7ef14e2..9d2f4c2 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1535,7 +1535,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
if (unlikely(usr == LINK_PROTOCOL))
tipc_node_bc_sync_rcv(n, hdr, bearer_id, &xmitq);
else if (unlikely(tipc_link_acked(n->bc_entry.link) != bc_ack))
- tipc_bcast_ack_rcv(net, n->bc_entry.link, bc_ack);
+ tipc_bcast_ack_rcv(net, n->bc_entry.link, hdr);
/* Receive packet directly if conditions permit */
tipc_node_read_lock(n);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index f9f5f3c..22d92f0 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -44,44 +44,43 @@
#include "bcast.h"
#include "netlink.h"
-#define SS_LISTENING -1 /* socket is listening */
-#define SS_READY -2 /* socket is connectionless */
-
#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */
#define CONN_PROBING_INTERVAL msecs_to_jiffies(3600000) /* [ms] => 1 h */
#define TIPC_FWD_MSG 1
-#define TIPC_CONN_OK 0
-#define TIPC_CONN_PROBING 1
#define TIPC_MAX_PORT 0xffffffff
#define TIPC_MIN_PORT 1
+enum {
+ TIPC_LISTEN = TCP_LISTEN,
+ TIPC_ESTABLISHED = TCP_ESTABLISHED,
+ TIPC_OPEN = TCP_CLOSE,
+ TIPC_DISCONNECTING = TCP_CLOSE_WAIT,
+ TIPC_CONNECTING = TCP_SYN_SENT,
+};
+
/**
* struct tipc_sock - TIPC socket structure
* @sk: socket - interacts with 'port' and with user via the socket API
- * @connected: non-zero if port is currently connected to a peer port
* @conn_type: TIPC type used when connection was established
* @conn_instance: TIPC instance used when connection was established
* @published: non-zero if port has one or more associated names
* @max_pkt: maximum packet size "hint" used when building messages sent by port
* @portid: unique port identity in TIPC socket hash table
* @phdr: preformatted message header used when sending messages
- * @port_list: adjacent ports in TIPC's global list of ports
* @publications: list of publications for port
* @pub_count: total # of publications port has made during its lifetime
* @probing_state:
- * @probing_intv:
* @conn_timeout: the time we can wait for an unresponded setup request
* @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue
* @link_cong: non-zero if owner must sleep because of link congestion
* @sent_unacked: # messages sent by socket, and not yet acked by peer
* @rcv_unacked: # messages read by user, but not yet acked back to peer
- * @remote: 'connected' peer for dgram/rdm
+ * @peer: 'connected' peer for dgram/rdm
* @node: hash table node
* @rcu: rcu struct for tipc_sock
*/
struct tipc_sock {
struct sock sk;
- int connected;
u32 conn_type;
u32 conn_instance;
int published;
@@ -91,17 +90,16 @@ struct tipc_sock {
struct list_head sock_list;
struct list_head publications;
u32 pub_count;
- u32 probing_state;
- unsigned long probing_intv;
uint conn_timeout;
atomic_t dupl_rcvcnt;
+ bool probe_unacked;
bool link_cong;
u16 snt_unacked;
u16 snd_win;
u16 peer_caps;
u16 rcv_unacked;
u16 rcv_win;
- struct sockaddr_tipc remote;
+ struct sockaddr_tipc peer;
struct rhash_head node;
struct rcu_head rcu;
};
@@ -294,6 +292,21 @@ static void tsk_rej_rx_queue(struct sock *sk)
tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT);
}
+static bool tipc_sk_connected(struct sock *sk)
+{
+ return sk->sk_state == TIPC_ESTABLISHED;
+}
+
+/* tipc_sk_type_connectionless - check if the socket is datagram socket
+ * @sk: socket
+ *
+ * Returns true if connection less, false otherwise
+ */
+static bool tipc_sk_type_connectionless(struct sock *sk)
+{
+ return sk->sk_type == SOCK_RDM || sk->sk_type == SOCK_DGRAM;
+}
+
/* tsk_peer_msg - verify if message was sent by connected port's peer
*
* Handles cases where the node's network address has changed from
@@ -301,12 +314,13 @@ static void tsk_rej_rx_queue(struct sock *sk)
*/
static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg)
{
- struct tipc_net *tn = net_generic(sock_net(&tsk->sk), tipc_net_id);
+ struct sock *sk = &tsk->sk;
+ struct tipc_net *tn = net_generic(sock_net(sk), tipc_net_id);
u32 peer_port = tsk_peer_port(tsk);
u32 orig_node;
u32 peer_node;
- if (unlikely(!tsk->connected))
+ if (unlikely(!tipc_sk_connected(sk)))
return false;
if (unlikely(msg_origport(msg) != peer_port))
@@ -327,6 +341,45 @@ static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg)
return false;
}
+/* tipc_set_sk_state - set the sk_state of the socket
+ * @sk: socket
+ *
+ * Caller must hold socket lock
+ *
+ * Returns 0 on success, errno otherwise
+ */
+static int tipc_set_sk_state(struct sock *sk, int state)
+{
+ int oldsk_state = sk->sk_state;
+ int res = -EINVAL;
+
+ switch (state) {
+ case TIPC_OPEN:
+ res = 0;
+ break;
+ case TIPC_LISTEN:
+ case TIPC_CONNECTING:
+ if (oldsk_state == TIPC_OPEN)
+ res = 0;
+ break;
+ case TIPC_ESTABLISHED:
+ if (oldsk_state == TIPC_CONNECTING ||
+ oldsk_state == TIPC_OPEN)
+ res = 0;
+ break;
+ case TIPC_DISCONNECTING:
+ if (oldsk_state == TIPC_CONNECTING ||
+ oldsk_state == TIPC_ESTABLISHED)
+ res = 0;
+ break;
+ }
+
+ if (!res)
+ sk->sk_state = state;
+
+ return res;
+}
+
/**
* tipc_sk_create - create a TIPC socket
* @net: network namespace (must be default network)
@@ -344,7 +397,6 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
{
struct tipc_net *tn;
const struct proto_ops *ops;
- socket_state state;
struct sock *sk;
struct tipc_sock *tsk;
struct tipc_msg *msg;
@@ -356,16 +408,13 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
switch (sock->type) {
case SOCK_STREAM:
ops = &stream_ops;
- state = SS_UNCONNECTED;
break;
case SOCK_SEQPACKET:
ops = &packet_ops;
- state = SS_UNCONNECTED;
break;
case SOCK_DGRAM:
case SOCK_RDM:
ops = &msg_ops;
- state = SS_READY;
break;
default:
return -EPROTOTYPE;
@@ -386,14 +435,15 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
/* Finish initializing socket data structures */
sock->ops = ops;
- sock->state = state;
sock_init_data(sock, sk);
+ tipc_set_sk_state(sk, TIPC_OPEN);
if (tipc_sk_insert(tsk)) {
pr_warn("Socket create failed; port number exhausted\n");
return -EINVAL;
}
msg_set_origport(msg, tsk->portid);
setup_timer(&sk->sk_timer, tipc_sk_timeout, (unsigned long)tsk);
+ sk->sk_shutdown = 0;
sk->sk_backlog_rcv = tipc_backlog_rcv;
sk->sk_rcvbuf = sysctl_tipc_rmem[1];
sk->sk_data_ready = tipc_data_ready;
@@ -406,11 +456,12 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
tsk->snd_win = tsk_adv_blocks(RCVBUF_MIN);
tsk->rcv_win = tsk->snd_win;
- if (sock->state == SS_READY) {
+ if (tipc_sk_type_connectionless(sk)) {
tsk_set_unreturnable(tsk, true);
if (sock->type == SOCK_DGRAM)
tsk_set_unreliable(tsk, true);
}
+
return 0;
}
@@ -421,6 +472,44 @@ static void tipc_sk_callback(struct rcu_head *head)
sock_put(&tsk->sk);
}
+/* Caller should hold socket lock for the socket. */
+static void __tipc_shutdown(struct socket *sock, int error)
+{
+ struct sock *sk = sock->sk;
+ struct tipc_sock *tsk = tipc_sk(sk);
+ struct net *net = sock_net(sk);
+ u32 dnode = tsk_peer_node(tsk);
+ struct sk_buff *skb;
+
+ /* Reject all unreceived messages, except on an active connection
+ * (which disconnects locally & sends a 'FIN+' to peer).
+ */
+ while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
+ if (TIPC_SKB_CB(skb)->bytes_read) {
+ kfree_skb(skb);
+ } else {
+ if (!tipc_sk_type_connectionless(sk) &&
+ sk->sk_state != TIPC_DISCONNECTING) {
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ tipc_node_remove_conn(net, dnode, tsk->portid);
+ }
+ tipc_sk_respond(sk, skb, error);
+ }
+ }
+ if (sk->sk_state != TIPC_DISCONNECTING) {
+ skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
+ TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
+ tsk_own_node(tsk), tsk_peer_port(tsk),
+ tsk->portid, error);
+ if (skb)
+ tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
+ if (!tipc_sk_type_connectionless(sk)) {
+ tipc_node_remove_conn(net, dnode, tsk->portid);
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ }
+ }
+}
+
/**
* tipc_release - destroy a TIPC socket
* @sock: socket to destroy
@@ -440,10 +529,7 @@ static void tipc_sk_callback(struct rcu_head *head)
static int tipc_release(struct socket *sock)
{
struct sock *sk = sock->sk;
- struct net *net;
struct tipc_sock *tsk;
- struct sk_buff *skb;
- u32 dnode;
/*
* Exit if socket isn't fully initialized (occurs when a failed accept()
@@ -452,47 +538,16 @@ static int tipc_release(struct socket *sock)
if (sk == NULL)
return 0;
- net = sock_net(sk);
tsk = tipc_sk(sk);
lock_sock(sk);
- /*
- * Reject all unreceived messages, except on an active connection
- * (which disconnects locally & sends a 'FIN+' to peer)
- */
- dnode = tsk_peer_node(tsk);
- while (sock->state != SS_DISCONNECTING) {
- skb = __skb_dequeue(&sk->sk_receive_queue);
- if (skb == NULL)
- break;
- if (TIPC_SKB_CB(skb)->handle != NULL)
- kfree_skb(skb);
- else {
- if ((sock->state == SS_CONNECTING) ||
- (sock->state == SS_CONNECTED)) {
- sock->state = SS_DISCONNECTING;
- tsk->connected = 0;
- tipc_node_remove_conn(net, dnode, tsk->portid);
- }
- tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT);
- }
- }
-
+ __tipc_shutdown(sock, TIPC_ERR_NO_PORT);
+ sk->sk_shutdown = SHUTDOWN_MASK;
tipc_sk_withdraw(tsk, 0, NULL);
sk_stop_timer(sk, &sk->sk_timer);
tipc_sk_remove(tsk);
- if (tsk->connected) {
- skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
- TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
- tsk_own_node(tsk), tsk_peer_port(tsk),
- tsk->portid, TIPC_ERR_NO_PORT);
- if (skb)
- tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
- tipc_node_remove_conn(net, dnode, tsk->portid);
- }
/* Reject any messages that accumulated in backlog queue */
- sock->state = SS_DISCONNECTING;
release_sock(sk);
call_rcu(&tsk->rcu, tipc_sk_callback);
@@ -578,13 +633,14 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
int *uaddr_len, int peer)
{
struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
- struct tipc_sock *tsk = tipc_sk(sock->sk);
+ struct sock *sk = sock->sk;
+ struct tipc_sock *tsk = tipc_sk(sk);
struct tipc_net *tn = net_generic(sock_net(sock->sk), tipc_net_id);
memset(addr, 0, sizeof(*addr));
if (peer) {
- if ((sock->state != SS_CONNECTED) &&
- ((peer != 2) || (sock->state != SS_DISCONNECTING)))
+ if ((!tipc_sk_connected(sk)) &&
+ ((peer != 2) || (sk->sk_state != TIPC_DISCONNECTING)))
return -ENOTCONN;
addr->addr.id.ref = tsk_peer_port(tsk);
addr->addr.id.node = tsk_peer_node(tsk);
@@ -616,28 +672,6 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
* exits. TCP and other protocols seem to rely on higher level poll routines
* to handle any preventable race conditions, so TIPC will do the same ...
*
- * TIPC sets the returned events as follows:
- *
- * socket state flags set
- * ------------ ---------
- * unconnected no read flags
- * POLLOUT if port is not congested
- *
- * connecting POLLIN/POLLRDNORM if ACK/NACK in rx queue
- * no write flags
- *
- * connected POLLIN/POLLRDNORM if data in rx queue
- * POLLOUT if port is not congested
- *
- * disconnecting POLLIN/POLLRDNORM/POLLHUP
- * no write flags
- *
- * listening POLLIN if SYN in rx queue
- * no write flags
- *
- * ready POLLIN/POLLRDNORM if data in rx queue
- * [connectionless] POLLOUT (since port cannot be congested)
- *
* IMPORTANT: The fact that a read or write operation is indicated does NOT
* imply that the operation will succeed, merely that it should be performed
* and will not block.
@@ -651,22 +685,29 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
sock_poll_wait(file, sk_sleep(sk), wait);
- switch ((int)sock->state) {
- case SS_UNCONNECTED:
- if (!tsk->link_cong)
- mask |= POLLOUT;
- break;
- case SS_READY:
- case SS_CONNECTED:
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
+ mask |= POLLRDHUP | POLLIN | POLLRDNORM;
+ if (sk->sk_shutdown == SHUTDOWN_MASK)
+ mask |= POLLHUP;
+
+ switch (sk->sk_state) {
+ case TIPC_ESTABLISHED:
if (!tsk->link_cong && !tsk_conn_cong(tsk))
mask |= POLLOUT;
/* fall thru' */
- case SS_CONNECTING:
- case SS_LISTENING:
+ case TIPC_LISTEN:
+ case TIPC_CONNECTING:
if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= (POLLIN | POLLRDNORM);
break;
- case SS_DISCONNECTING:
+ case TIPC_OPEN:
+ if (!tsk->link_cong)
+ mask |= POLLOUT;
+ if (tipc_sk_type_connectionless(sk) &&
+ (!skb_queue_empty(&sk->sk_receive_queue)))
+ mask |= (POLLIN | POLLRDNORM);
+ break;
+ case TIPC_DISCONNECTING:
mask = (POLLIN | POLLRDNORM | POLLHUP);
break;
}
@@ -697,6 +738,9 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq,
uint mtu;
int rc;
+ if (!timeo && tsk->link_cong)
+ return -ELINKCONG;
+
msg_set_type(mhdr, TIPC_MCAST_MSG);
msg_set_lookup_scope(mhdr, TIPC_CLUSTER_SCOPE);
msg_set_destport(mhdr, 0);
@@ -809,7 +853,7 @@ static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
if (!tsk_peer_msg(tsk, hdr))
goto exit;
- tsk->probing_state = TIPC_CONN_OK;
+ tsk->probe_unacked = false;
if (mtyp == CONN_PROBE) {
msg_set_type(hdr, CONN_PROBE_REPLY);
@@ -832,25 +876,25 @@ static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p)
{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
- DEFINE_WAIT(wait);
int done;
do {
int err = sock_error(sk);
if (err)
return err;
- if (sock->state == SS_DISCONNECTING)
+ if (sk->sk_shutdown & SEND_SHUTDOWN)
return -EPIPE;
if (!*timeo_p)
return -EAGAIN;
if (signal_pending(current))
return sock_intr_errno(*timeo_p);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- done = sk_wait_event(sk, timeo_p, !tsk->link_cong);
- finish_wait(sk_sleep(sk), &wait);
+ add_wait_queue(sk_sleep(sk), &wait);
+ done = sk_wait_event(sk, timeo_p, !tsk->link_cong, &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
} while (!done);
return 0;
}
@@ -890,6 +934,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
struct tipc_msg *mhdr = &tsk->phdr;
u32 dnode, dport;
struct sk_buff_head pktchain;
+ bool is_connectionless = tipc_sk_type_connectionless(sk);
struct sk_buff *skb;
struct tipc_name_seq *seq;
struct iov_iter save;
@@ -900,18 +945,18 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
if (dsz > TIPC_MAX_USER_MSG_SIZE)
return -EMSGSIZE;
if (unlikely(!dest)) {
- if (tsk->connected && sock->state == SS_READY)
- dest = &tsk->remote;
+ if (is_connectionless && tsk->peer.family == AF_TIPC)
+ dest = &tsk->peer;
else
return -EDESTADDRREQ;
} else if (unlikely(m->msg_namelen < sizeof(*dest)) ||
dest->family != AF_TIPC) {
return -EINVAL;
}
- if (unlikely(sock->state != SS_READY)) {
- if (sock->state == SS_LISTENING)
+ if (!is_connectionless) {
+ if (sk->sk_state == TIPC_LISTEN)
return -EPIPE;
- if (sock->state != SS_UNCONNECTED)
+ if (sk->sk_state != TIPC_OPEN)
return -EISCONN;
if (tsk->published)
return -EOPNOTSUPP;
@@ -963,8 +1008,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong;
rc = tipc_node_xmit(net, &pktchain, dnode, tsk->portid);
if (likely(!rc)) {
- if (sock->state != SS_READY)
- sock->state = SS_CONNECTING;
+ if (!is_connectionless)
+ tipc_set_sk_state(sk, TIPC_CONNECTING);
return dsz;
}
if (rc == -ELINKCONG) {
@@ -986,30 +1031,30 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz)
static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p)
{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
- DEFINE_WAIT(wait);
int done;
do {
int err = sock_error(sk);
if (err)
return err;
- if (sock->state == SS_DISCONNECTING)
+ if (sk->sk_state == TIPC_DISCONNECTING)
return -EPIPE;
- else if (sock->state != SS_CONNECTED)
+ else if (!tipc_sk_connected(sk))
return -ENOTCONN;
if (!*timeo_p)
return -EAGAIN;
if (signal_pending(current))
return sock_intr_errno(*timeo_p);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
done = sk_wait_event(sk, timeo_p,
(!tsk->link_cong &&
!tsk_conn_cong(tsk)) ||
- !tsk->connected);
- finish_wait(sk_sleep(sk), &wait);
+ !tipc_sk_connected(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
} while (!done);
return 0;
}
@@ -1064,14 +1109,17 @@ static int __tipc_send_stream(struct socket *sock, struct msghdr *m, size_t dsz)
if (dsz > (uint)INT_MAX)
return -EMSGSIZE;
- if (unlikely(sock->state != SS_CONNECTED)) {
- if (sock->state == SS_DISCONNECTING)
+ if (unlikely(!tipc_sk_connected(sk))) {
+ if (sk->sk_state == TIPC_DISCONNECTING)
return -EPIPE;
else
return -ENOTCONN;
}
timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
+ if (!timeo && tsk->link_cong)
+ return -ELINKCONG;
+
dnode = tsk_peer_node(tsk);
skb_queue_head_init(&pktchain);
@@ -1145,10 +1193,8 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port,
msg_set_lookup_scope(msg, 0);
msg_set_hdr_sz(msg, SHORT_H_SIZE);
- tsk->probing_intv = CONN_PROBING_INTERVAL;
- tsk->probing_state = TIPC_CONN_OK;
- tsk->connected = 1;
- sk_reset_timer(sk, &sk->sk_timer, jiffies + tsk->probing_intv);
+ sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTERVAL);
+ tipc_set_sk_state(sk, TIPC_ESTABLISHED);
tipc_node_add_conn(net, peer_node, tsk->portid, peer_port);
tsk->max_pkt = tipc_node_get_mtu(net, peer_node, tsk->portid);
tsk->peer_caps = tipc_node_get_capabilities(net, peer_node);
@@ -1256,13 +1302,14 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
static void tipc_sk_send_ack(struct tipc_sock *tsk)
{
- struct net *net = sock_net(&tsk->sk);
+ struct sock *sk = &tsk->sk;
+ struct net *net = sock_net(sk);
struct sk_buff *skb = NULL;
struct tipc_msg *msg;
u32 peer_port = tsk_peer_port(tsk);
u32 dnode = tsk_peer_node(tsk);
- if (!tsk->connected)
+ if (!tipc_sk_connected(sk))
return;
skb = tipc_msg_create(CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0,
dnode, tsk_own_node(tsk), peer_port,
@@ -1291,7 +1338,7 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
for (;;) {
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
- if (sock->state == SS_DISCONNECTING) {
+ if (sk->sk_shutdown & RCV_SHUTDOWN) {
err = -ENOTCONN;
break;
}
@@ -1332,6 +1379,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buf_len,
struct tipc_sock *tsk = tipc_sk(sk);
struct sk_buff *buf;
struct tipc_msg *msg;
+ bool is_connectionless = tipc_sk_type_connectionless(sk);
long timeo;
unsigned int sz;
u32 err;
@@ -1343,7 +1391,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buf_len,
lock_sock(sk);
- if (unlikely(sock->state == SS_UNCONNECTED)) {
+ if (!is_connectionless && unlikely(sk->sk_state == TIPC_OPEN)) {
res = -ENOTCONN;
goto exit;
}
@@ -1388,8 +1436,8 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buf_len,
goto exit;
res = sz;
} else {
- if ((sock->state == SS_READY) ||
- ((err == TIPC_CONN_SHUTDOWN) || m->msg_control))
+ if (is_connectionless || err == TIPC_CONN_SHUTDOWN ||
+ m->msg_control)
res = 0;
else
res = -ECONNRESET;
@@ -1398,7 +1446,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buf_len,
if (unlikely(flags & MSG_PEEK))
goto exit;
- if (likely(sock->state != SS_READY)) {
+ if (likely(!is_connectionless)) {
tsk->rcv_unacked += tsk_inc(tsk, hlen + sz);
if (unlikely(tsk->rcv_unacked >= (tsk->rcv_win / 4)))
tipc_sk_send_ack(tsk);
@@ -1429,7 +1477,7 @@ static int tipc_recv_stream(struct socket *sock, struct msghdr *m,
struct tipc_msg *msg;
long timeo;
unsigned int sz;
- int sz_to_copy, target, needed;
+ int target;
int sz_copied = 0;
u32 err;
int res = 0, hlen;
@@ -1440,7 +1488,7 @@ static int tipc_recv_stream(struct socket *sock, struct msghdr *m,
lock_sock(sk);
- if (unlikely(sock->state == SS_UNCONNECTED)) {
+ if (unlikely(sk->sk_state == TIPC_OPEN)) {
res = -ENOTCONN;
goto exit;
}
@@ -1477,11 +1525,13 @@ static int tipc_recv_stream(struct socket *sock, struct msghdr *m,
/* Capture message data (if valid) & compute return value (always) */
if (!err) {
- u32 offset = (u32)(unsigned long)(TIPC_SKB_CB(buf)->handle);
+ u32 offset = TIPC_SKB_CB(buf)->bytes_read;
+ u32 needed;
+ int sz_to_copy;
sz -= offset;
needed = (buf_len - sz_copied);
- sz_to_copy = (sz <= needed) ? sz : needed;
+ sz_to_copy = min(sz, needed);
res = skb_copy_datagram_msg(buf, hlen + offset, m, sz_to_copy);
if (res)
@@ -1491,8 +1541,8 @@ static int tipc_recv_stream(struct socket *sock, struct msghdr *m,
if (sz_to_copy < sz) {
if (!(flags & MSG_PEEK))
- TIPC_SKB_CB(buf)->handle =
- (void *)(unsigned long)(offset + sz_to_copy);
+ TIPC_SKB_CB(buf)->bytes_read =
+ offset + sz_to_copy;
goto exit;
}
} else {
@@ -1574,49 +1624,31 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
{
struct sock *sk = &tsk->sk;
struct net *net = sock_net(sk);
- struct socket *sock = sk->sk_socket;
struct tipc_msg *hdr = buf_msg(skb);
if (unlikely(msg_mcast(hdr)))
return false;
- switch ((int)sock->state) {
- case SS_CONNECTED:
-
- /* Accept only connection-based messages sent by peer */
- if (unlikely(!tsk_peer_msg(tsk, hdr)))
- return false;
-
- if (unlikely(msg_errcode(hdr))) {
- sock->state = SS_DISCONNECTING;
- tsk->connected = 0;
- /* Let timer expire on it's own */
- tipc_node_remove_conn(net, tsk_peer_node(tsk),
- tsk->portid);
- }
- return true;
-
- case SS_CONNECTING:
-
+ switch (sk->sk_state) {
+ case TIPC_CONNECTING:
/* Accept only ACK or NACK message */
if (unlikely(!msg_connected(hdr)))
return false;
if (unlikely(msg_errcode(hdr))) {
- sock->state = SS_DISCONNECTING;
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
sk->sk_err = ECONNREFUSED;
return true;
}
if (unlikely(!msg_isdata(hdr))) {
- sock->state = SS_DISCONNECTING;
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
sk->sk_err = EINVAL;
return true;
}
tipc_sk_finish_conn(tsk, msg_origport(hdr), msg_orignode(hdr));
msg_set_importance(&tsk->phdr, msg_importance(hdr));
- sock->state = SS_CONNECTED;
/* If 'ACK+' message, add to socket receive queue */
if (msg_data_sz(hdr))
@@ -1630,18 +1662,31 @@ static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb)
msg_set_dest_droppable(hdr, 1);
return false;
- case SS_LISTENING:
- case SS_UNCONNECTED:
-
+ case TIPC_OPEN:
+ case TIPC_DISCONNECTING:
+ break;
+ case TIPC_LISTEN:
/* Accept only SYN message */
if (!msg_connected(hdr) && !(msg_errcode(hdr)))
return true;
break;
- case SS_DISCONNECTING:
- break;
+ case TIPC_ESTABLISHED:
+ /* Accept only connection-based messages sent by peer */
+ if (unlikely(!tsk_peer_msg(tsk, hdr)))
+ return false;
+
+ if (unlikely(msg_errcode(hdr))) {
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ /* Let timer expire on it's own */
+ tipc_node_remove_conn(net, tsk_peer_node(tsk),
+ tsk->portid);
+ sk->sk_state_change(sk);
+ }
+ return true;
default:
- pr_err("Unknown socket state %u\n", sock->state);
+ pr_err("Unknown sk_state %u\n", sk->sk_state);
}
+
return false;
}
@@ -1692,7 +1737,6 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
static bool filter_rcv(struct sock *sk, struct sk_buff *skb,
struct sk_buff_head *xmitq)
{
- struct socket *sock = sk->sk_socket;
struct tipc_sock *tsk = tipc_sk(sk);
struct tipc_msg *hdr = buf_msg(skb);
unsigned int limit = rcvbuf_limit(sk, skb);
@@ -1718,7 +1762,7 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb,
}
/* Reject if wrong message type for current socket state */
- if (unlikely(sock->state == SS_READY)) {
+ if (tipc_sk_type_connectionless(sk)) {
if (msg_connected(hdr)) {
err = TIPC_ERR_NO_PORT;
goto reject;
@@ -1735,7 +1779,7 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb,
}
/* Enqueue message */
- TIPC_SKB_CB(skb)->handle = NULL;
+ TIPC_SKB_CB(skb)->bytes_read = 0;
__skb_queue_tail(&sk->sk_receive_queue, skb);
skb_set_owner_r(skb, sk);
@@ -1885,8 +1929,8 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq)
static int tipc_wait_for_connect(struct socket *sock, long *timeo_p)
{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct sock *sk = sock->sk;
- DEFINE_WAIT(wait);
int done;
do {
@@ -1898,9 +1942,10 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p)
if (signal_pending(current))
return sock_intr_errno(*timeo_p);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
- done = sk_wait_event(sk, timeo_p, sock->state != SS_CONNECTING);
- finish_wait(sk_sleep(sk), &wait);
+ add_wait_queue(sk_sleep(sk), &wait);
+ done = sk_wait_event(sk, timeo_p,
+ sk->sk_state != TIPC_CONNECTING, &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
} while (!done);
return 0;
}
@@ -1922,21 +1967,19 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
struct sockaddr_tipc *dst = (struct sockaddr_tipc *)dest;
struct msghdr m = {NULL,};
long timeout = (flags & O_NONBLOCK) ? 0 : tsk->conn_timeout;
- socket_state previous;
+ int previous;
int res = 0;
lock_sock(sk);
/* DGRAM/RDM connect(), just save the destaddr */
- if (sock->state == SS_READY) {
+ if (tipc_sk_type_connectionless(sk)) {
if (dst->family == AF_UNSPEC) {
- memset(&tsk->remote, 0, sizeof(struct sockaddr_tipc));
- tsk->connected = 0;
+ memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc));
} else if (destlen != sizeof(struct sockaddr_tipc)) {
res = -EINVAL;
} else {
- memcpy(&tsk->remote, dest, destlen);
- tsk->connected = 1;
+ memcpy(&tsk->peer, dest, destlen);
}
goto exit;
}
@@ -1952,9 +1995,10 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
goto exit;
}
- previous = sock->state;
- switch (sock->state) {
- case SS_UNCONNECTED:
+ previous = sk->sk_state;
+
+ switch (sk->sk_state) {
+ case TIPC_OPEN:
/* Send a 'SYN-' to destination */
m.msg_name = dest;
m.msg_namelen = destlen;
@@ -1969,27 +2013,29 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
if ((res < 0) && (res != -EWOULDBLOCK))
goto exit;
- /* Just entered SS_CONNECTING state; the only
+ /* Just entered TIPC_CONNECTING state; the only
* difference is that return value in non-blocking
* case is EINPROGRESS, rather than EALREADY.
*/
res = -EINPROGRESS;
- case SS_CONNECTING:
- if (previous == SS_CONNECTING)
- res = -EALREADY;
- if (!timeout)
+ /* fall thru' */
+ case TIPC_CONNECTING:
+ if (!timeout) {
+ if (previous == TIPC_CONNECTING)
+ res = -EALREADY;
goto exit;
+ }
timeout = msecs_to_jiffies(timeout);
/* Wait until an 'ACK' or 'RST' arrives, or a timeout occurs */
res = tipc_wait_for_connect(sock, &timeout);
break;
- case SS_CONNECTED:
+ case TIPC_ESTABLISHED:
res = -EISCONN;
break;
default:
res = -EINVAL;
- break;
}
+
exit:
release_sock(sk);
return res;
@@ -2008,15 +2054,9 @@ static int tipc_listen(struct socket *sock, int len)
int res;
lock_sock(sk);
-
- if (sock->state != SS_UNCONNECTED)
- res = -EINVAL;
- else {
- sock->state = SS_LISTENING;
- res = 0;
- }
-
+ res = tipc_set_sk_state(sk, TIPC_LISTEN);
release_sock(sk);
+
return res;
}
@@ -2042,9 +2082,6 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo)
err = 0;
if (!skb_queue_empty(&sk->sk_receive_queue))
break;
- err = -EINVAL;
- if (sock->state != SS_LISTENING)
- break;
err = -EAGAIN;
if (!timeo)
break;
@@ -2075,7 +2112,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
lock_sock(sk);
- if (sock->state != SS_LISTENING) {
+ if (sk->sk_state != TIPC_LISTEN) {
res = -EINVAL;
goto exit;
}
@@ -2086,7 +2123,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
buf = skb_peek(&sk->sk_receive_queue);
- res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 1);
+ res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 0);
if (res)
goto exit;
security_sk_clone(sock->sk, new_sock->sk);
@@ -2106,7 +2143,6 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
/* Connect new socket to it's peer */
tipc_sk_finish_conn(new_tsock, msg_origport(msg), msg_orignode(msg));
- new_sock->state = SS_CONNECTED;
tsk_set_importance(new_tsock, msg_importance(msg));
if (msg_named(msg)) {
@@ -2146,13 +2182,6 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
static int tipc_shutdown(struct socket *sock, int how)
{
struct sock *sk = sock->sk;
- struct net *net = sock_net(sk);
- struct tipc_sock *tsk = tipc_sk(sk);
- struct sk_buff *skb;
- u32 dnode = tsk_peer_node(tsk);
- u32 dport = tsk_peer_port(tsk);
- u32 onode = tipc_own_addr(net);
- u32 oport = tsk->portid;
int res;
if (how != SHUT_RDWR)
@@ -2160,45 +2189,17 @@ static int tipc_shutdown(struct socket *sock, int how)
lock_sock(sk);
- switch (sock->state) {
- case SS_CONNECTING:
- case SS_CONNECTED:
+ __tipc_shutdown(sock, TIPC_CONN_SHUTDOWN);
+ sk->sk_shutdown = SEND_SHUTDOWN;
-restart:
- dnode = tsk_peer_node(tsk);
-
- /* Disconnect and send a 'FIN+' or 'FIN-' message to peer */
- skb = __skb_dequeue(&sk->sk_receive_queue);
- if (skb) {
- if (TIPC_SKB_CB(skb)->handle != NULL) {
- kfree_skb(skb);
- goto restart;
- }
- tipc_sk_respond(sk, skb, TIPC_CONN_SHUTDOWN);
- } else {
- skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
- TIPC_CONN_MSG, SHORT_H_SIZE,
- 0, dnode, onode, dport, oport,
- TIPC_CONN_SHUTDOWN);
- if (skb)
- tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
- }
- tsk->connected = 0;
- sock->state = SS_DISCONNECTING;
- tipc_node_remove_conn(net, dnode, tsk->portid);
- /* fall through */
-
- case SS_DISCONNECTING:
-
+ if (sk->sk_state == TIPC_DISCONNECTING) {
/* Discard any unreceived messages */
__skb_queue_purge(&sk->sk_receive_queue);
/* Wake up anyone sleeping in poll */
sk->sk_state_change(sk);
res = 0;
- break;
-
- default:
+ } else {
res = -ENOTCONN;
}
@@ -2215,17 +2216,16 @@ static void tipc_sk_timeout(unsigned long data)
u32 own_node = tsk_own_node(tsk);
bh_lock_sock(sk);
- if (!tsk->connected) {
+ if (!tipc_sk_connected(sk)) {
bh_unlock_sock(sk);
goto exit;
}
peer_port = tsk_peer_port(tsk);
peer_node = tsk_peer_node(tsk);
- if (tsk->probing_state == TIPC_CONN_PROBING) {
+ if (tsk->probe_unacked) {
if (!sock_owned_by_user(sk)) {
- sk->sk_socket->state = SS_DISCONNECTING;
- tsk->connected = 0;
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk),
tsk_peer_port(tsk));
sk->sk_state_change(sk);
@@ -2234,13 +2234,15 @@ static void tipc_sk_timeout(unsigned long data)
sk_reset_timer(sk, &sk->sk_timer, (HZ / 20));
}
- } else {
- skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE,
- INT_H_SIZE, 0, peer_node, own_node,
- peer_port, tsk->portid, TIPC_OK);
- tsk->probing_state = TIPC_CONN_PROBING;
- sk_reset_timer(sk, &sk->sk_timer, jiffies + tsk->probing_intv);
+ bh_unlock_sock(sk);
+ goto exit;
}
+
+ skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE,
+ INT_H_SIZE, 0, peer_node, own_node,
+ peer_port, tsk->portid, TIPC_OK);
+ tsk->probe_unacked = true;
+ sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTERVAL);
bh_unlock_sock(sk);
if (skb)
tipc_node_xmit_skb(sock_net(sk), skb, peer_node, tsk->portid);
@@ -2251,11 +2253,12 @@ static void tipc_sk_timeout(unsigned long data)
static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
struct tipc_name_seq const *seq)
{
- struct net *net = sock_net(&tsk->sk);
+ struct sock *sk = &tsk->sk;
+ struct net *net = sock_net(sk);
struct publication *publ;
u32 key;
- if (tsk->connected)
+ if (tipc_sk_connected(sk))
return -EINVAL;
key = tsk->portid + tsk->pub_count + 1;
if (key == tsk->portid)
@@ -2713,6 +2716,7 @@ static int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb,
struct nlattr *attrs;
struct net *net = sock_net(skb->sk);
struct tipc_net *tn = net_generic(net, tipc_net_id);
+ struct sock *sk = &tsk->sk;
hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
&tipc_genl_family, NLM_F_MULTI, TIPC_NL_SOCK_GET);
@@ -2727,7 +2731,7 @@ static int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb,
if (nla_put_u32(skb, TIPC_NLA_SOCK_ADDR, tn->own_addr))
goto attr_msg_cancel;
- if (tsk->connected) {
+ if (tipc_sk_connected(sk)) {
err = __tipc_nl_add_sk_con(skb, tsk);
if (err)
goto attr_msg_cancel;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 145082e..6a705d0 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2113,8 +2113,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
mutex_lock(&u->iolock);
skip = sk_peek_offset(sk, flags);
- skb = __skb_try_recv_datagram(sk, flags, &peeked, &skip, &err,
- &last);
+ skb = __skb_try_recv_datagram(sk, flags, NULL, &peeked, &skip,
+ &err, &last);
if (skb)
break;
@@ -2812,7 +2812,8 @@ static int unix_seq_show(struct seq_file *seq, void *v)
i++;
}
for ( ; i < len; i++)
- seq_putc(seq, u->addr->name->sun_path[i]);
+ seq_putc(seq, u->addr->name->sun_path[i] ?:
+ '@');
}
unix_state_unlock(s);
seq_putc(seq, '\n');
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index a53b3a1..687e9fd 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -619,17 +619,17 @@ static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt)
static void virtio_transport_wait_close(struct sock *sk, long timeout)
{
if (timeout) {
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+ add_wait_queue(sk_sleep(sk), &wait);
do {
- prepare_to_wait(sk_sleep(sk), &wait,
- TASK_INTERRUPTIBLE);
if (sk_wait_event(sk, &timeout,
- sock_flag(sk, SOCK_DONE)))
+ sock_flag(sk, SOCK_DONE), &wait))
break;
} while (!signal_pending(current) && timeout);
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
}
}
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 8201e6d..158c59e 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -210,11 +210,11 @@ void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev,
if (WARN_ON(wdev->iftype != NL80211_IFTYPE_P2P_DEVICE))
return;
- if (!wdev->p2p_started)
+ if (!wdev_running(wdev))
return;
rdev_stop_p2p_device(rdev, wdev);
- wdev->p2p_started = false;
+ wdev->is_running = false;
rdev->opencount--;
@@ -233,11 +233,11 @@ void cfg80211_stop_nan(struct cfg80211_registered_device *rdev,
if (WARN_ON(wdev->iftype != NL80211_IFTYPE_NAN))
return;
- if (!wdev->nan_started)
+ if (!wdev_running(wdev))
return;
rdev_stop_nan(rdev, wdev);
- wdev->nan_started = false;
+ wdev->is_running = false;
rdev->opencount--;
}
@@ -562,6 +562,21 @@ static int wiphy_verify_combinations(struct wiphy *wiphy)
c->limits[j].max > 1))
return -EINVAL;
+ /*
+ * This isn't well-defined right now. If you have an
+ * IBSS interface, then its beacon interval may change
+ * by joining other networks, and nothing prevents it
+ * from doing that.
+ * So technically we probably shouldn't even allow AP
+ * and IBSS in the same interface, but it seems that
+ * some drivers support that, possibly only with fixed
+ * beacon intervals for IBSS.
+ */
+ if (WARN_ON(types & BIT(NL80211_IFTYPE_ADHOC) &&
+ c->beacon_int_min_gcd)) {
+ return -EINVAL;
+ }
+
cnt += c->limits[j].max;
/*
* Don't advertise an unsupported type
@@ -571,6 +586,11 @@ static int wiphy_verify_combinations(struct wiphy *wiphy)
return -EINVAL;
}
+#ifndef CONFIG_WIRELESS_WDS
+ if (WARN_ON(all_iftypes & BIT(NL80211_IFTYPE_WDS)))
+ return -EINVAL;
+#endif
+
/* You can't even choose that many! */
if (WARN_ON(cnt < c->max_interfaces))
return -EINVAL;
@@ -609,6 +629,11 @@ int wiphy_register(struct wiphy *wiphy)
!rdev->ops->add_nan_func || !rdev->ops->del_nan_func)))
return -EINVAL;
+#ifndef CONFIG_WIRELESS_WDS
+ if (WARN_ON(wiphy->interface_modes & BIT(NL80211_IFTYPE_WDS)))
+ return -EINVAL;
+#endif
+
/*
* if a wiphy has unsupported modes for regulatory channel enforcement,
* opt-out of enforcement checking
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 08d2e94..fb2fcd5 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -345,7 +345,7 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev,
const u8 *ssid, int ssid_len,
const u8 *ie, int ie_len,
const u8 *key, int key_len, int key_idx,
- const u8 *sae_data, int sae_data_len);
+ const u8 *auth_data, int auth_data_len);
int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev,
struct net_device *dev,
struct ieee80211_channel *chan,
@@ -475,7 +475,7 @@ int ieee80211_get_ratemask(struct ieee80211_supported_band *sband,
u32 *mask);
int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev,
- u32 beacon_int);
+ enum nl80211_iftype iftype, u32 beacon_int);
void cfg80211_update_iface_num(struct cfg80211_registered_device *rdev,
enum nl80211_iftype iftype, int num);
diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c
index fa2066b..2d8518a 100644
--- a/net/wireless/mesh.c
+++ b/net/wireless/mesh.c
@@ -183,6 +183,7 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
memcpy(wdev->ssid, setup->mesh_id, setup->mesh_id_len);
wdev->mesh_id_len = setup->mesh_id_len;
wdev->chandef = setup->chandef;
+ wdev->beacon_interval = setup->beacon_interval;
}
return err;
@@ -258,6 +259,7 @@ int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev,
err = rdev_leave_mesh(rdev, dev);
if (!err) {
wdev->mesh_id_len = 0;
+ wdev->beacon_interval = 0;
memset(&wdev->chandef, 0, sizeof(wdev->chandef));
rdev_set_qos_map(rdev, dev, NULL);
}
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index cbb48e2..bd1f7a1 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -204,14 +204,14 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev,
const u8 *ssid, int ssid_len,
const u8 *ie, int ie_len,
const u8 *key, int key_len, int key_idx,
- const u8 *sae_data, int sae_data_len)
+ const u8 *auth_data, int auth_data_len)
{
struct wireless_dev *wdev = dev->ieee80211_ptr;
struct cfg80211_auth_request req = {
.ie = ie,
.ie_len = ie_len,
- .sae_data = sae_data,
- .sae_data_len = sae_data_len,
+ .auth_data = auth_data,
+ .auth_data_len = auth_data_len,
.auth_type = auth_type,
.key = key,
.key_len = key_len,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 0d3ab4b..24ab199 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -343,7 +343,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
[NL80211_ATTR_BG_SCAN_PERIOD] = { .type = NLA_U16 },
[NL80211_ATTR_WDEV] = { .type = NLA_U64 },
[NL80211_ATTR_USER_REG_HINT_TYPE] = { .type = NLA_U32 },
- [NL80211_ATTR_SAE_DATA] = { .type = NLA_BINARY, },
+ [NL80211_ATTR_AUTH_DATA] = { .type = NLA_BINARY, },
[NL80211_ATTR_VHT_CAPABILITY] = { .len = NL80211_VHT_CAPABILITY_LEN },
[NL80211_ATTR_SCAN_FLAGS] = { .type = NLA_U32 },
[NL80211_ATTR_P2P_CTWINDOW] = { .type = NLA_U8 },
@@ -400,6 +400,10 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
[NL80211_ATTR_NAN_MASTER_PREF] = { .type = NLA_U8 },
[NL80211_ATTR_NAN_DUAL] = { .type = NLA_U8 },
[NL80211_ATTR_NAN_FUNC] = { .type = NLA_NESTED },
+ [NL80211_ATTR_FILS_KEK] = { .type = NLA_BINARY,
+ .len = FILS_MAX_KEK_LEN },
+ [NL80211_ATTR_FILS_NONCES] = { .len = 2 * FILS_NONCE_LEN },
+ [NL80211_ATTR_MULTICAST_TO_UNICAST_ENABLED] = { .type = NLA_FLAG, },
};
/* policy for the key attributes */
@@ -421,6 +425,7 @@ nl80211_key_default_policy[NUM_NL80211_KEY_DEFAULT_TYPES] = {
[NL80211_KEY_DEFAULT_TYPE_MULTICAST] = { .type = NLA_FLAG },
};
+#ifdef CONFIG_PM
/* policy for WoWLAN attributes */
static const struct nla_policy
nl80211_wowlan_policy[NUM_NL80211_WOWLAN_TRIG] = {
@@ -454,6 +459,7 @@ nl80211_wowlan_tcp_policy[NUM_NL80211_WOWLAN_TCP] = {
[NL80211_WOWLAN_TCP_WAKE_PAYLOAD] = { .len = 1 },
[NL80211_WOWLAN_TCP_WAKE_MASK] = { .len = 1 },
};
+#endif /* CONFIG_PM */
/* policy for coalesce rule attributes */
static const struct nla_policy
@@ -1062,6 +1068,10 @@ static int nl80211_put_iface_combinations(struct wiphy *wiphy,
nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_REGIONS,
c->radar_detect_regions)))
goto nla_put_failure;
+ if (c->beacon_int_min_gcd &&
+ nla_put_u32(msg, NL80211_IFACE_COMB_BI_MIN_GCD,
+ c->beacon_int_min_gcd))
+ goto nla_put_failure;
nla_nest_end(msg, nl_combi);
}
@@ -1309,6 +1319,95 @@ nl80211_send_mgmt_stypes(struct sk_buff *msg,
return 0;
}
+#define CMD(op, n) \
+ do { \
+ if (rdev->ops->op) { \
+ i++; \
+ if (nla_put_u32(msg, i, NL80211_CMD_ ## n)) \
+ goto nla_put_failure; \
+ } \
+ } while (0)
+
+static int nl80211_add_commands_unsplit(struct cfg80211_registered_device *rdev,
+ struct sk_buff *msg)
+{
+ int i = 0;
+
+ /*
+ * do *NOT* add anything into this function, new things need to be
+ * advertised only to new versions of userspace that can deal with
+ * the split (and they can't possibly care about new features...
+ */
+ CMD(add_virtual_intf, NEW_INTERFACE);
+ CMD(change_virtual_intf, SET_INTERFACE);
+ CMD(add_key, NEW_KEY);
+ CMD(start_ap, START_AP);
+ CMD(add_station, NEW_STATION);
+ CMD(add_mpath, NEW_MPATH);
+ CMD(update_mesh_config, SET_MESH_CONFIG);
+ CMD(change_bss, SET_BSS);
+ CMD(auth, AUTHENTICATE);
+ CMD(assoc, ASSOCIATE);
+ CMD(deauth, DEAUTHENTICATE);
+ CMD(disassoc, DISASSOCIATE);
+ CMD(join_ibss, JOIN_IBSS);
+ CMD(join_mesh, JOIN_MESH);
+ CMD(set_pmksa, SET_PMKSA);
+ CMD(del_pmksa, DEL_PMKSA);
+ CMD(flush_pmksa, FLUSH_PMKSA);
+ if (rdev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL)
+ CMD(remain_on_channel, REMAIN_ON_CHANNEL);
+ CMD(set_bitrate_mask, SET_TX_BITRATE_MASK);
+ CMD(mgmt_tx, FRAME);
+ CMD(mgmt_tx_cancel_wait, FRAME_WAIT_CANCEL);
+ if (rdev->wiphy.flags & WIPHY_FLAG_NETNS_OK) {
+ i++;
+ if (nla_put_u32(msg, i, NL80211_CMD_SET_WIPHY_NETNS))
+ goto nla_put_failure;
+ }
+ if (rdev->ops->set_monitor_channel || rdev->ops->start_ap ||
+ rdev->ops->join_mesh) {
+ i++;
+ if (nla_put_u32(msg, i, NL80211_CMD_SET_CHANNEL))
+ goto nla_put_failure;
+ }
+ CMD(set_wds_peer, SET_WDS_PEER);
+ if (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) {
+ CMD(tdls_mgmt, TDLS_MGMT);
+ CMD(tdls_oper, TDLS_OPER);
+ }
+ if (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN)
+ CMD(sched_scan_start, START_SCHED_SCAN);
+ CMD(probe_client, PROBE_CLIENT);
+ CMD(set_noack_map, SET_NOACK_MAP);
+ if (rdev->wiphy.flags & WIPHY_FLAG_REPORTS_OBSS) {
+ i++;
+ if (nla_put_u32(msg, i, NL80211_CMD_REGISTER_BEACONS))
+ goto nla_put_failure;
+ }
+ CMD(start_p2p_device, START_P2P_DEVICE);
+ CMD(set_mcast_rate, SET_MCAST_RATE);
+#ifdef CONFIG_NL80211_TESTMODE
+ CMD(testmode_cmd, TESTMODE);
+#endif
+
+ if (rdev->ops->connect || rdev->ops->auth) {
+ i++;
+ if (nla_put_u32(msg, i, NL80211_CMD_CONNECT))
+ goto nla_put_failure;
+ }
+
+ if (rdev->ops->disconnect || rdev->ops->deauth) {
+ i++;
+ if (nla_put_u32(msg, i, NL80211_CMD_DISCONNECT))
+ goto nla_put_failure;
+ }
+
+ return i;
+ nla_put_failure:
+ return -ENOBUFS;
+}
+
struct nl80211_dump_wiphy_state {
s64 filter_wiphy;
long start;
@@ -1536,68 +1635,9 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
if (!nl_cmds)
goto nla_put_failure;
- i = 0;
-#define CMD(op, n) \
- do { \
- if (rdev->ops->op) { \
- i++; \
- if (nla_put_u32(msg, i, NL80211_CMD_ ## n)) \
- goto nla_put_failure; \
- } \
- } while (0)
-
- CMD(add_virtual_intf, NEW_INTERFACE);
- CMD(change_virtual_intf, SET_INTERFACE);
- CMD(add_key, NEW_KEY);
- CMD(start_ap, START_AP);
- CMD(add_station, NEW_STATION);
- CMD(add_mpath, NEW_MPATH);
- CMD(update_mesh_config, SET_MESH_CONFIG);
- CMD(change_bss, SET_BSS);
- CMD(auth, AUTHENTICATE);
- CMD(assoc, ASSOCIATE);
- CMD(deauth, DEAUTHENTICATE);
- CMD(disassoc, DISASSOCIATE);
- CMD(join_ibss, JOIN_IBSS);
- CMD(join_mesh, JOIN_MESH);
- CMD(set_pmksa, SET_PMKSA);
- CMD(del_pmksa, DEL_PMKSA);
- CMD(flush_pmksa, FLUSH_PMKSA);
- if (rdev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL)
- CMD(remain_on_channel, REMAIN_ON_CHANNEL);
- CMD(set_bitrate_mask, SET_TX_BITRATE_MASK);
- CMD(mgmt_tx, FRAME);
- CMD(mgmt_tx_cancel_wait, FRAME_WAIT_CANCEL);
- if (rdev->wiphy.flags & WIPHY_FLAG_NETNS_OK) {
- i++;
- if (nla_put_u32(msg, i, NL80211_CMD_SET_WIPHY_NETNS))
- goto nla_put_failure;
- }
- if (rdev->ops->set_monitor_channel || rdev->ops->start_ap ||
- rdev->ops->join_mesh) {
- i++;
- if (nla_put_u32(msg, i, NL80211_CMD_SET_CHANNEL))
- goto nla_put_failure;
- }
- CMD(set_wds_peer, SET_WDS_PEER);
- if (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) {
- CMD(tdls_mgmt, TDLS_MGMT);
- CMD(tdls_oper, TDLS_OPER);
- }
- if (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN)
- CMD(sched_scan_start, START_SCHED_SCAN);
- CMD(probe_client, PROBE_CLIENT);
- CMD(set_noack_map, SET_NOACK_MAP);
- if (rdev->wiphy.flags & WIPHY_FLAG_REPORTS_OBSS) {
- i++;
- if (nla_put_u32(msg, i, NL80211_CMD_REGISTER_BEACONS))
- goto nla_put_failure;
- }
- CMD(start_p2p_device, START_P2P_DEVICE);
- CMD(set_mcast_rate, SET_MCAST_RATE);
-#ifdef CONFIG_NL80211_TESTMODE
- CMD(testmode_cmd, TESTMODE);
-#endif
+ i = nl80211_add_commands_unsplit(rdev, msg);
+ if (i < 0)
+ goto nla_put_failure;
if (state->split) {
CMD(crit_proto_start, CRIT_PROTOCOL_START);
CMD(crit_proto_stop, CRIT_PROTOCOL_STOP);
@@ -1607,22 +1647,11 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
if (rdev->wiphy.features &
NL80211_FEATURE_SUPPORTS_WMM_ADMISSION)
CMD(add_tx_ts, ADD_TX_TS);
+ CMD(set_multicast_to_unicast, SET_MULTICAST_TO_UNICAST);
+ CMD(update_connect_params, UPDATE_CONNECT_PARAMS);
}
- /* add into the if now */
#undef CMD
- if (rdev->ops->connect || rdev->ops->auth) {
- i++;
- if (nla_put_u32(msg, i, NL80211_CMD_CONNECT))
- goto nla_put_failure;
- }
-
- if (rdev->ops->disconnect || rdev->ops->deauth) {
- i++;
- if (nla_put_u32(msg, i, NL80211_CMD_DISCONNECT))
- goto nla_put_failure;
- }
-
nla_nest_end(msg, nl_cmds);
state->split_start++;
if (state->split)
@@ -2283,10 +2312,9 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
nla_for_each_nested(nl_txq_params,
info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS],
rem_txq_params) {
- result = nla_parse(tb, NL80211_TXQ_ATTR_MAX,
- nla_data(nl_txq_params),
- nla_len(nl_txq_params),
- txq_params_policy);
+ result = nla_parse_nested(tb, NL80211_TXQ_ATTR_MAX,
+ nl_txq_params,
+ txq_params_policy);
if (result)
return result;
result = parse_txq_params(tb, &txq_params);
@@ -3536,8 +3564,8 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
sband = rdev->wiphy.bands[band];
if (sband == NULL)
return -EINVAL;
- err = nla_parse(tb, NL80211_TXRATE_MAX, nla_data(tx_rates),
- nla_len(tx_rates), nl80211_txattr_policy);
+ err = nla_parse_nested(tb, NL80211_TXRATE_MAX, tx_rates,
+ nl80211_txattr_policy);
if (err)
return err;
if (tb[NL80211_TXRATE_LEGACY]) {
@@ -3743,12 +3771,23 @@ static bool nl80211_valid_auth_type(struct cfg80211_registered_device *rdev,
if (!(rdev->wiphy.features & NL80211_FEATURE_SAE) &&
auth_type == NL80211_AUTHTYPE_SAE)
return false;
+ if (!wiphy_ext_feature_isset(&rdev->wiphy,
+ NL80211_EXT_FEATURE_FILS_STA) &&
+ (auth_type == NL80211_AUTHTYPE_FILS_SK ||
+ auth_type == NL80211_AUTHTYPE_FILS_SK_PFS ||
+ auth_type == NL80211_AUTHTYPE_FILS_PK))
+ return false;
return true;
case NL80211_CMD_CONNECT:
case NL80211_CMD_START_AP:
/* SAE not supported yet */
if (auth_type == NL80211_AUTHTYPE_SAE)
return false;
+ /* FILS not supported yet */
+ if (auth_type == NL80211_AUTHTYPE_FILS_SK ||
+ auth_type == NL80211_AUTHTYPE_FILS_SK_PFS ||
+ auth_type == NL80211_AUTHTYPE_FILS_PK)
+ return false;
return true;
default:
return false;
@@ -3790,7 +3829,8 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
params.dtim_period =
nla_get_u32(info->attrs[NL80211_ATTR_DTIM_PERIOD]);
- err = cfg80211_validate_beacon_int(rdev, params.beacon_interval);
+ err = cfg80211_validate_beacon_int(rdev, dev->ieee80211_ptr->iftype,
+ params.beacon_interval);
if (err)
return err;
@@ -6292,9 +6332,8 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info)
nla_for_each_nested(nl_reg_rule, info->attrs[NL80211_ATTR_REG_RULES],
rem_reg_rules) {
- r = nla_parse(tb, NL80211_REG_RULE_ATTR_MAX,
- nla_data(nl_reg_rule), nla_len(nl_reg_rule),
- reg_rule_policy);
+ r = nla_parse_nested(tb, NL80211_REG_RULE_ATTR_MAX,
+ nl_reg_rule, reg_rule_policy);
if (r)
goto bad_reg;
r = parse_reg_rule(tb, &rd->reg_rules[rule_idx]);
@@ -6361,8 +6400,8 @@ static int parse_bss_select(struct nlattr *nla, struct wiphy *wiphy,
if (!nla_ok(nest, nla_len(nest)))
return -EINVAL;
- err = nla_parse(attr, NL80211_BSS_SELECT_ATTR_MAX, nla_data(nest),
- nla_len(nest), nl80211_bss_select_policy);
+ err = nla_parse_nested(attr, NL80211_BSS_SELECT_ATTR_MAX, nest,
+ nl80211_bss_select_policy);
if (err)
return err;
@@ -6752,9 +6791,8 @@ nl80211_parse_sched_scan_plans(struct wiphy *wiphy, int n_plans,
if (WARN_ON(i >= n_plans))
return -EINVAL;
- err = nla_parse(plan, NL80211_SCHED_SCAN_PLAN_MAX,
- nla_data(attr), nla_len(attr),
- nl80211_plan_policy);
+ err = nla_parse_nested(plan, NL80211_SCHED_SCAN_PLAN_MAX,
+ attr, nl80211_plan_policy);
if (err)
return err;
@@ -6843,9 +6881,9 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
tmp) {
struct nlattr *rssi;
- err = nla_parse(tb, NL80211_SCHED_SCAN_MATCH_ATTR_MAX,
- nla_data(attr), nla_len(attr),
- nl80211_match_policy);
+ err = nla_parse_nested(tb,
+ NL80211_SCHED_SCAN_MATCH_ATTR_MAX,
+ attr, nl80211_match_policy);
if (err)
return ERR_PTR(err);
/* add other standalone attributes here */
@@ -7016,9 +7054,9 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
tmp) {
struct nlattr *ssid, *rssi;
- err = nla_parse(tb, NL80211_SCHED_SCAN_MATCH_ATTR_MAX,
- nla_data(attr), nla_len(attr),
- nl80211_match_policy);
+ err = nla_parse_nested(tb,
+ NL80211_SCHED_SCAN_MATCH_ATTR_MAX,
+ attr, nl80211_match_policy);
if (err)
goto out_free;
ssid = tb[NL80211_SCHED_SCAN_MATCH_ATTR_SSID];
@@ -7696,8 +7734,8 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info)
struct cfg80211_registered_device *rdev = info->user_ptr[0];
struct net_device *dev = info->user_ptr[1];
struct ieee80211_channel *chan;
- const u8 *bssid, *ssid, *ie = NULL, *sae_data = NULL;
- int err, ssid_len, ie_len = 0, sae_data_len = 0;
+ const u8 *bssid, *ssid, *ie = NULL, *auth_data = NULL;
+ int err, ssid_len, ie_len = 0, auth_data_len = 0;
enum nl80211_auth_type auth_type;
struct key_parse key;
bool local_state_change;
@@ -7777,17 +7815,23 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info)
if (!nl80211_valid_auth_type(rdev, auth_type, NL80211_CMD_AUTHENTICATE))
return -EINVAL;
- if (auth_type == NL80211_AUTHTYPE_SAE &&
- !info->attrs[NL80211_ATTR_SAE_DATA])
+ if ((auth_type == NL80211_AUTHTYPE_SAE ||
+ auth_type == NL80211_AUTHTYPE_FILS_SK ||
+ auth_type == NL80211_AUTHTYPE_FILS_SK_PFS ||
+ auth_type == NL80211_AUTHTYPE_FILS_PK) &&
+ !info->attrs[NL80211_ATTR_AUTH_DATA])
return -EINVAL;
- if (info->attrs[NL80211_ATTR_SAE_DATA]) {
- if (auth_type != NL80211_AUTHTYPE_SAE)
+ if (info->attrs[NL80211_ATTR_AUTH_DATA]) {
+ if (auth_type != NL80211_AUTHTYPE_SAE &&
+ auth_type != NL80211_AUTHTYPE_FILS_SK &&
+ auth_type != NL80211_AUTHTYPE_FILS_SK_PFS &&
+ auth_type != NL80211_AUTHTYPE_FILS_PK)
return -EINVAL;
- sae_data = nla_data(info->attrs[NL80211_ATTR_SAE_DATA]);
- sae_data_len = nla_len(info->attrs[NL80211_ATTR_SAE_DATA]);
+ auth_data = nla_data(info->attrs[NL80211_ATTR_AUTH_DATA]);
+ auth_data_len = nla_len(info->attrs[NL80211_ATTR_AUTH_DATA]);
/* need to include at least Auth Transaction and Status Code */
- if (sae_data_len < 4)
+ if (auth_data_len < 4)
return -EINVAL;
}
@@ -7804,7 +7848,7 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info)
err = cfg80211_mlme_auth(rdev, dev, chan, auth_type, bssid,
ssid, ssid_len, ie, ie_len,
key.p.key, key.p.key_len, key.idx,
- sae_data, sae_data_len);
+ auth_data, auth_data_len);
wdev_unlock(dev->ieee80211_ptr);
return err;
}
@@ -7983,6 +8027,15 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
req.flags |= ASSOC_REQ_USE_RRM;
}
+ if (info->attrs[NL80211_ATTR_FILS_KEK]) {
+ req.fils_kek = nla_data(info->attrs[NL80211_ATTR_FILS_KEK]);
+ req.fils_kek_len = nla_len(info->attrs[NL80211_ATTR_FILS_KEK]);
+ if (!info->attrs[NL80211_ATTR_FILS_NONCES])
+ return -EINVAL;
+ req.fils_nonces =
+ nla_data(info->attrs[NL80211_ATTR_FILS_NONCES]);
+ }
+
err = nl80211_crypto_settings(rdev, info, &req.crypto, 1);
if (!err) {
wdev_lock(dev->ieee80211_ptr);
@@ -8140,7 +8193,8 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
ibss.beacon_interval =
nla_get_u32(info->attrs[NL80211_ATTR_BEACON_INTERVAL]);
- err = cfg80211_validate_beacon_int(rdev, ibss.beacon_interval);
+ err = cfg80211_validate_beacon_int(rdev, NL80211_IFTYPE_ADHOC,
+ ibss.beacon_interval);
if (err)
return err;
@@ -8713,6 +8767,37 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info)
return err;
}
+static int nl80211_update_connect_params(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct cfg80211_connect_params connect = {};
+ struct cfg80211_registered_device *rdev = info->user_ptr[0];
+ struct net_device *dev = info->user_ptr[1];
+ struct wireless_dev *wdev = dev->ieee80211_ptr;
+ u32 changed = 0;
+ int ret;
+
+ if (!rdev->ops->update_connect_params)
+ return -EOPNOTSUPP;
+
+ if (info->attrs[NL80211_ATTR_IE]) {
+ if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE]))
+ return -EINVAL;
+ connect.ie = nla_data(info->attrs[NL80211_ATTR_IE]);
+ connect.ie_len = nla_len(info->attrs[NL80211_ATTR_IE]);
+ changed |= UPDATE_ASSOC_IES;
+ }
+
+ wdev_lock(dev->ieee80211_ptr);
+ if (!wdev->current_bss)
+ ret = -ENOLINK;
+ else
+ ret = rdev_update_connect_params(rdev, dev, &connect, changed);
+ wdev_unlock(dev->ieee80211_ptr);
+
+ return ret;
+}
+
static int nl80211_disconnect(struct sk_buff *skb, struct genl_info *info)
{
struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -9404,7 +9489,9 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info)
setup.beacon_interval =
nla_get_u32(info->attrs[NL80211_ATTR_BEACON_INTERVAL]);
- err = cfg80211_validate_beacon_int(rdev, setup.beacon_interval);
+ err = cfg80211_validate_beacon_int(rdev,
+ NL80211_IFTYPE_MESH_POINT,
+ setup.beacon_interval);
if (err)
return err;
}
@@ -9715,9 +9802,8 @@ static int nl80211_parse_wowlan_tcp(struct cfg80211_registered_device *rdev,
if (!rdev->wiphy.wowlan->tcp)
return -EINVAL;
- err = nla_parse(tb, MAX_NL80211_WOWLAN_TCP,
- nla_data(attr), nla_len(attr),
- nl80211_wowlan_tcp_policy);
+ err = nla_parse_nested(tb, MAX_NL80211_WOWLAN_TCP, attr,
+ nl80211_wowlan_tcp_policy);
if (err)
return err;
@@ -9862,9 +9948,7 @@ static int nl80211_parse_wowlan_nd(struct cfg80211_registered_device *rdev,
goto out;
}
- err = nla_parse(tb, NL80211_ATTR_MAX,
- nla_data(attr), nla_len(attr),
- nl80211_policy);
+ err = nla_parse_nested(tb, NL80211_ATTR_MAX, attr, nl80211_policy);
if (err)
goto out;
@@ -9898,10 +9982,9 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
goto set_wakeup;
}
- err = nla_parse(tb, MAX_NL80211_WOWLAN_TRIG,
- nla_data(info->attrs[NL80211_ATTR_WOWLAN_TRIGGERS]),
- nla_len(info->attrs[NL80211_ATTR_WOWLAN_TRIGGERS]),
- nl80211_wowlan_policy);
+ err = nla_parse_nested(tb, MAX_NL80211_WOWLAN_TRIG,
+ info->attrs[NL80211_ATTR_WOWLAN_TRIGGERS],
+ nl80211_wowlan_policy);
if (err)
return err;
@@ -9983,8 +10066,8 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
rem) {
u8 *mask_pat;
- nla_parse(pat_tb, MAX_NL80211_PKTPAT, nla_data(pat),
- nla_len(pat), NULL);
+ nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
+ NULL);
err = -EINVAL;
if (!pat_tb[NL80211_PKTPAT_MASK] ||
!pat_tb[NL80211_PKTPAT_PATTERN])
@@ -10194,8 +10277,8 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev,
int rem, pat_len, mask_len, pkt_offset, n_patterns = 0;
struct nlattr *pat_tb[NUM_NL80211_PKTPAT];
- err = nla_parse(tb, NL80211_ATTR_COALESCE_RULE_MAX, nla_data(rule),
- nla_len(rule), nl80211_coalesce_policy);
+ err = nla_parse_nested(tb, NL80211_ATTR_COALESCE_RULE_MAX, rule,
+ nl80211_coalesce_policy);
if (err)
return err;
@@ -10233,8 +10316,7 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev,
rem) {
u8 *mask_pat;
- nla_parse(pat_tb, MAX_NL80211_PKTPAT, nla_data(pat),
- nla_len(pat), NULL);
+ nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, NULL);
if (!pat_tb[NL80211_PKTPAT_MASK] ||
!pat_tb[NL80211_PKTPAT_PATTERN])
return -EINVAL;
@@ -10353,10 +10435,9 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info)
if (!info->attrs[NL80211_ATTR_REKEY_DATA])
return -EINVAL;
- err = nla_parse(tb, MAX_NL80211_REKEY_DATA,
- nla_data(info->attrs[NL80211_ATTR_REKEY_DATA]),
- nla_len(info->attrs[NL80211_ATTR_REKEY_DATA]),
- nl80211_rekey_policy);
+ err = nla_parse_nested(tb, MAX_NL80211_REKEY_DATA,
+ info->attrs[NL80211_ATTR_REKEY_DATA],
+ nl80211_rekey_policy);
if (err)
return err;
@@ -10505,7 +10586,7 @@ static int nl80211_start_p2p_device(struct sk_buff *skb, struct genl_info *info)
if (wdev->iftype != NL80211_IFTYPE_P2P_DEVICE)
return -EOPNOTSUPP;
- if (wdev->p2p_started)
+ if (wdev_running(wdev))
return 0;
if (rfkill_blocked(rdev->rfkill))
@@ -10515,7 +10596,7 @@ static int nl80211_start_p2p_device(struct sk_buff *skb, struct genl_info *info)
if (err)
return err;
- wdev->p2p_started = true;
+ wdev->is_running = true;
rdev->opencount++;
return 0;
@@ -10547,7 +10628,7 @@ static int nl80211_start_nan(struct sk_buff *skb, struct genl_info *info)
if (wdev->iftype != NL80211_IFTYPE_NAN)
return -EOPNOTSUPP;
- if (wdev->nan_started)
+ if (!wdev_running(wdev))
return -EEXIST;
if (rfkill_blocked(rdev->rfkill))
@@ -10570,7 +10651,7 @@ static int nl80211_start_nan(struct sk_buff *skb, struct genl_info *info)
if (err)
return err;
- wdev->nan_started = true;
+ wdev->is_running = true;
rdev->opencount++;
return 0;
@@ -10654,7 +10735,7 @@ static int nl80211_nan_add_func(struct sk_buff *skb,
if (wdev->iftype != NL80211_IFTYPE_NAN)
return -EOPNOTSUPP;
- if (!wdev->nan_started)
+ if (!wdev_running(wdev))
return -ENOTCONN;
if (!info->attrs[NL80211_ATTR_NAN_FUNC])
@@ -10664,10 +10745,9 @@ static int nl80211_nan_add_func(struct sk_buff *skb,
wdev->owner_nlportid != info->snd_portid)
return -ENOTCONN;
- err = nla_parse(tb, NL80211_NAN_FUNC_ATTR_MAX,
- nla_data(info->attrs[NL80211_ATTR_NAN_FUNC]),
- nla_len(info->attrs[NL80211_ATTR_NAN_FUNC]),
- nl80211_nan_func_policy);
+ err = nla_parse_nested(tb, NL80211_NAN_FUNC_ATTR_MAX,
+ info->attrs[NL80211_ATTR_NAN_FUNC],
+ nl80211_nan_func_policy);
if (err)
return err;
@@ -10762,9 +10842,9 @@ static int nl80211_nan_add_func(struct sk_buff *skb,
if (tb[NL80211_NAN_FUNC_SRF]) {
struct nlattr *srf_tb[NUM_NL80211_NAN_SRF_ATTR];
- err = nla_parse(srf_tb, NL80211_NAN_SRF_ATTR_MAX,
- nla_data(tb[NL80211_NAN_FUNC_SRF]),
- nla_len(tb[NL80211_NAN_FUNC_SRF]), NULL);
+ err = nla_parse_nested(srf_tb, NL80211_NAN_SRF_ATTR_MAX,
+ tb[NL80211_NAN_FUNC_SRF],
+ nl80211_nan_srf_policy);
if (err)
goto out;
@@ -10890,7 +10970,7 @@ static int nl80211_nan_del_func(struct sk_buff *skb,
if (wdev->iftype != NL80211_IFTYPE_NAN)
return -EOPNOTSUPP;
- if (!wdev->nan_started)
+ if (!wdev_running(wdev))
return -ENOTCONN;
if (!info->attrs[NL80211_ATTR_COOKIE])
@@ -10918,7 +10998,7 @@ static int nl80211_nan_change_config(struct sk_buff *skb,
if (wdev->iftype != NL80211_IFTYPE_NAN)
return -EOPNOTSUPP;
- if (!wdev->nan_started)
+ if (!wdev_running(wdev))
return -ENOTCONN;
if (info->attrs[NL80211_ATTR_NAN_MASTER_PREF]) {
@@ -11230,10 +11310,7 @@ static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info)
return -EINVAL;
if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_RUNNING) {
- if (wdev->netdev &&
- !netif_running(wdev->netdev))
- return -ENETDOWN;
- if (!wdev->netdev && !wdev->p2p_started)
+ if (!wdev_running(wdev))
return -ENETDOWN;
}
@@ -11394,10 +11471,7 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb,
return -EINVAL;
if (vcmd->flags & WIPHY_VENDOR_CMD_NEED_RUNNING) {
- if (wdev->netdev &&
- !netif_running(wdev->netdev))
- return -ENETDOWN;
- if (!wdev->netdev && !wdev->p2p_started)
+ if (!wdev_running(wdev))
return -ENETDOWN;
}
}
@@ -11710,6 +11784,31 @@ static int nl80211_tdls_cancel_channel_switch(struct sk_buff *skb,
return 0;
}
+static int nl80211_set_multicast_to_unicast(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct cfg80211_registered_device *rdev = info->user_ptr[0];
+ struct net_device *dev = info->user_ptr[1];
+ struct wireless_dev *wdev = dev->ieee80211_ptr;
+ const struct nlattr *nla;
+ bool enabled;
+
+ if (netif_running(dev))
+ return -EBUSY;
+
+ if (!rdev->ops->set_multicast_to_unicast)
+ return -EOPNOTSUPP;
+
+ if (wdev->iftype != NL80211_IFTYPE_AP &&
+ wdev->iftype != NL80211_IFTYPE_P2P_GO)
+ return -EOPNOTSUPP;
+
+ nla = info->attrs[NL80211_ATTR_MULTICAST_TO_UNICAST_ENABLED];
+ enabled = nla_get_flag(nla);
+
+ return rdev_set_multicast_to_unicast(rdev, dev, enabled);
+}
+
#define NL80211_FLAG_NEED_WIPHY 0x01
#define NL80211_FLAG_NEED_NETDEV 0x02
#define NL80211_FLAG_NEED_RTNL 0x04
@@ -11768,30 +11867,16 @@ static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
info->user_ptr[1] = wdev;
}
- if (dev) {
- if (ops->internal_flags & NL80211_FLAG_CHECK_NETDEV_UP &&
- !netif_running(dev)) {
- if (rtnl)
- rtnl_unlock();
- return -ENETDOWN;
- }
-
- dev_hold(dev);
- } else if (ops->internal_flags & NL80211_FLAG_CHECK_NETDEV_UP) {
- if (wdev->iftype == NL80211_IFTYPE_P2P_DEVICE &&
- !wdev->p2p_started) {
- if (rtnl)
- rtnl_unlock();
- return -ENETDOWN;
- }
- if (wdev->iftype == NL80211_IFTYPE_NAN &&
- !wdev->nan_started) {
- if (rtnl)
- rtnl_unlock();
- return -ENETDOWN;
- }
+ if (ops->internal_flags & NL80211_FLAG_CHECK_NETDEV_UP &&
+ !wdev_running(wdev)) {
+ if (rtnl)
+ rtnl_unlock();
+ return -ENETDOWN;
}
+ if (dev)
+ dev_hold(dev);
+
info->user_ptr[0] = rdev;
}
@@ -12163,6 +12248,14 @@ static const struct genl_ops nl80211_ops[] = {
NL80211_FLAG_NEED_RTNL,
},
{
+ .cmd = NL80211_CMD_UPDATE_CONNECT_PARAMS,
+ .doit = nl80211_update_connect_params,
+ .policy = nl80211_policy,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+ NL80211_FLAG_NEED_RTNL,
+ },
+ {
.cmd = NL80211_CMD_DISCONNECT,
.doit = nl80211_disconnect,
.policy = nl80211_policy,
@@ -12583,6 +12676,14 @@ static const struct genl_ops nl80211_ops[] = {
.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
NL80211_FLAG_NEED_RTNL,
},
+ {
+ .cmd = NL80211_CMD_SET_MULTICAST_TO_UNICAST,
+ .doit = nl80211_set_multicast_to_unicast,
+ .policy = nl80211_policy,
+ .flags = GENL_UNS_ADMIN_PERM,
+ .internal_flags = NL80211_FLAG_NEED_NETDEV |
+ NL80211_FLAG_NEED_RTNL,
+ },
};
static struct genl_family nl80211_fam __ro_after_init = {
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 11cf83c..2f42507 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -490,6 +490,18 @@ static inline int rdev_connect(struct cfg80211_registered_device *rdev,
return ret;
}
+static inline int
+rdev_update_connect_params(struct cfg80211_registered_device *rdev,
+ struct net_device *dev,
+ struct cfg80211_connect_params *sme, u32 changed)
+{
+ int ret;
+ trace_rdev_update_connect_params(&rdev->wiphy, dev, sme, changed);
+ ret = rdev->ops->update_connect_params(&rdev->wiphy, dev, sme, changed);
+ trace_rdev_return_int(&rdev->wiphy, ret);
+ return ret;
+}
+
static inline int rdev_disconnect(struct cfg80211_registered_device *rdev,
struct net_device *dev, u16 reason_code)
{
@@ -562,6 +574,18 @@ static inline int rdev_set_wds_peer(struct cfg80211_registered_device *rdev,
return ret;
}
+static inline int
+rdev_set_multicast_to_unicast(struct cfg80211_registered_device *rdev,
+ struct net_device *dev,
+ const bool enabled)
+{
+ int ret;
+ trace_rdev_set_multicast_to_unicast(&rdev->wiphy, dev, enabled);
+ ret = rdev->ops->set_multicast_to_unicast(&rdev->wiphy, dev, enabled);
+ trace_rdev_return_int(&rdev->wiphy, ret);
+ return ret;
+}
+
static inline void rdev_rfkill_poll(struct cfg80211_registered_device *rdev)
{
trace_rdev_rfkill_poll(&rdev->wiphy);
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index a77db33..2b5bb38 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -1088,7 +1088,7 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev,
err = cfg80211_sme_disconnect(wdev, reason);
else if (!rdev->ops->disconnect)
cfg80211_mlme_down(rdev, dev);
- else if (wdev->current_bss)
+ else if (wdev->ssid_len)
err = rdev_disconnect(rdev, dev, reason);
return err;
diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c
index 0082f4b..14b3f00 100644
--- a/net/wireless/sysfs.c
+++ b/net/wireless/sysfs.c
@@ -104,13 +104,16 @@ static int wiphy_suspend(struct device *dev)
rtnl_lock();
if (rdev->wiphy.registered) {
- if (!rdev->wiphy.wowlan_config)
+ if (!rdev->wiphy.wowlan_config) {
cfg80211_leave_all(rdev);
+ cfg80211_process_rdev_events(rdev);
+ }
if (rdev->ops->suspend)
ret = rdev_suspend(rdev, rdev->wiphy.wowlan_config);
if (ret == 1) {
/* Driver refuse to configure wowlan */
cfg80211_leave_all(rdev);
+ cfg80211_process_rdev_events(rdev);
ret = rdev_suspend(rdev, NULL);
}
}
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index a3d0a91b..ea1b47e 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -1281,6 +1281,24 @@ TRACE_EVENT(rdev_connect,
__entry->wpa_versions, __entry->flags, MAC_PR_ARG(prev_bssid))
);
+TRACE_EVENT(rdev_update_connect_params,
+ TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+ struct cfg80211_connect_params *sme, u32 changed),
+ TP_ARGS(wiphy, netdev, sme, changed),
+ TP_STRUCT__entry(
+ WIPHY_ENTRY
+ NETDEV_ENTRY
+ __field(u32, changed)
+ ),
+ TP_fast_assign(
+ WIPHY_ASSIGN;
+ NETDEV_ASSIGN;
+ __entry->changed = changed;
+ ),
+ TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", parameters changed: %u",
+ WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->changed)
+);
+
TRACE_EVENT(rdev_set_cqm_rssi_config,
TP_PROTO(struct wiphy *wiphy,
struct net_device *netdev, s32 rssi_thold,
@@ -3030,6 +3048,25 @@ DEFINE_EVENT(wiphy_wdev_evt, rdev_abort_scan,
TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev),
TP_ARGS(wiphy, wdev)
);
+
+TRACE_EVENT(rdev_set_multicast_to_unicast,
+ TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+ const bool enabled),
+ TP_ARGS(wiphy, netdev, enabled),
+ TP_STRUCT__entry(
+ WIPHY_ENTRY
+ NETDEV_ENTRY
+ __field(bool, enabled)
+ ),
+ TP_fast_assign(
+ WIPHY_ASSIGN;
+ NETDEV_ASSIGN;
+ __entry->enabled = enabled;
+ ),
+ TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", unicast: %s",
+ WIPHY_PR_ARG, NETDEV_PR_ARG,
+ BOOL_TO_STR(__entry->enabled))
+);
#endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */
#undef TRACE_INCLUDE_PATH
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 8edce22..88725f8 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -13,6 +13,7 @@
#include <net/dsfield.h>
#include <linux/if_vlan.h>
#include <linux/mpls.h>
+#include <linux/gcd.h>
#include "core.h"
#include "rdev-ops.h"
@@ -420,8 +421,8 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr)
}
EXPORT_SYMBOL(ieee80211_get_mesh_hdrlen);
-static int __ieee80211_data_to_8023(struct sk_buff *skb, struct ethhdr *ehdr,
- const u8 *addr, enum nl80211_iftype iftype)
+int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
+ const u8 *addr, enum nl80211_iftype iftype)
{
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
struct {
@@ -525,13 +526,7 @@ static int __ieee80211_data_to_8023(struct sk_buff *skb, struct ethhdr *ehdr,
return 0;
}
-
-int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
- enum nl80211_iftype iftype)
-{
- return __ieee80211_data_to_8023(skb, NULL, addr, iftype);
-}
-EXPORT_SYMBOL(ieee80211_data_to_8023);
+EXPORT_SYMBOL(ieee80211_data_to_8023_exthdr);
int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr,
enum nl80211_iftype iftype,
@@ -746,24 +741,18 @@ __ieee80211_amsdu_copy(struct sk_buff *skb, unsigned int hlen,
void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
const u8 *addr, enum nl80211_iftype iftype,
const unsigned int extra_headroom,
- bool has_80211_header)
+ const u8 *check_da, const u8 *check_sa)
{
unsigned int hlen = ALIGN(extra_headroom, 4);
struct sk_buff *frame = NULL;
u16 ethertype;
u8 *payload;
- int offset = 0, remaining, err;
+ int offset = 0, remaining;
struct ethhdr eth;
bool reuse_frag = skb->head_frag && !skb_has_frag_list(skb);
bool reuse_skb = false;
bool last = false;
- if (has_80211_header) {
- err = __ieee80211_data_to_8023(skb, ð, addr, iftype);
- if (err)
- goto out;
- }
-
while (!last) {
unsigned int subframe_len;
int len;
@@ -780,8 +769,17 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
goto purge;
offset += sizeof(struct ethhdr);
- /* reuse skb for the last subframe */
last = remaining <= subframe_len + padding;
+
+ /* FIXME: should we really accept multicast DA? */
+ if ((check_da && !is_multicast_ether_addr(eth.h_dest) &&
+ !ether_addr_equal(check_da, eth.h_dest)) ||
+ (check_sa && !ether_addr_equal(check_sa, eth.h_source))) {
+ offset += len + padding;
+ continue;
+ }
+
+ /* reuse skb for the last subframe */
if (!skb_is_nonlinear(skb) && !reuse_frag && last) {
skb_pull(skb, offset);
frame = skb;
@@ -819,7 +817,6 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
purge:
__skb_queue_purge(list);
- out:
dev_kfree_skb(skb);
}
EXPORT_SYMBOL(ieee80211_amsdu_to_8023s);
@@ -1381,6 +1378,25 @@ static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id)
return false;
}
+static size_t skip_ie(const u8 *ies, size_t ielen, size_t pos)
+{
+ /* we assume a validly formed IEs buffer */
+ u8 len = ies[pos + 1];
+
+ pos += 2 + len;
+
+ /* the IE itself must have 255 bytes for fragments to follow */
+ if (len < 255)
+ return pos;
+
+ while (pos < ielen && ies[pos] == WLAN_EID_FRAGMENT) {
+ len = ies[pos + 1];
+ pos += 2 + len;
+ }
+
+ return pos;
+}
+
size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen,
const u8 *ids, int n_ids,
const u8 *after_ric, int n_after_ric,
@@ -1390,14 +1406,14 @@ size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen,
while (pos < ielen && ieee80211_id_in_list(ids, n_ids, ies[pos])) {
if (ies[pos] == WLAN_EID_RIC_DATA && n_after_ric) {
- pos += 2 + ies[pos + 1];
+ pos = skip_ie(ies, ielen, pos);
while (pos < ielen &&
!ieee80211_id_in_list(after_ric, n_after_ric,
ies[pos]))
- pos += 2 + ies[pos + 1];
+ pos = skip_ie(ies, ielen, pos);
} else {
- pos += 2 + ies[pos + 1];
+ pos = skip_ie(ies, ielen, pos);
}
}
@@ -1558,31 +1574,57 @@ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef,
}
EXPORT_SYMBOL(ieee80211_chandef_to_operating_class);
-int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev,
- u32 beacon_int)
+static void cfg80211_calculate_bi_data(struct wiphy *wiphy, u32 new_beacon_int,
+ u32 *beacon_int_gcd,
+ bool *beacon_int_different)
{
struct wireless_dev *wdev;
- int res = 0;
+
+ *beacon_int_gcd = 0;
+ *beacon_int_different = false;
+
+ list_for_each_entry(wdev, &wiphy->wdev_list, list) {
+ if (!wdev->beacon_interval)
+ continue;
+
+ if (!*beacon_int_gcd) {
+ *beacon_int_gcd = wdev->beacon_interval;
+ continue;
+ }
+
+ if (wdev->beacon_interval == *beacon_int_gcd)
+ continue;
+
+ *beacon_int_different = true;
+ *beacon_int_gcd = gcd(*beacon_int_gcd, wdev->beacon_interval);
+ }
+
+ if (new_beacon_int && *beacon_int_gcd != new_beacon_int) {
+ if (*beacon_int_gcd)
+ *beacon_int_different = true;
+ *beacon_int_gcd = gcd(*beacon_int_gcd, new_beacon_int);
+ }
+}
+
+int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev,
+ enum nl80211_iftype iftype, u32 beacon_int)
+{
+ /*
+ * This is just a basic pre-condition check; if interface combinations
+ * are possible the driver must already be checking those with a call
+ * to cfg80211_check_combinations(), in which case we'll validate more
+ * through the cfg80211_calculate_bi_data() call and code in
+ * cfg80211_iter_combinations().
+ */
if (beacon_int < 10 || beacon_int > 10000)
return -EINVAL;
- list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
- if (!wdev->beacon_interval)
- continue;
- if (wdev->beacon_interval != beacon_int) {
- res = -EINVAL;
- break;
- }
- }
-
- return res;
+ return 0;
}
int cfg80211_iter_combinations(struct wiphy *wiphy,
- const int num_different_channels,
- const u8 radar_detect,
- const int iftype_num[NUM_NL80211_IFTYPES],
+ struct iface_combination_params *params,
void (*iter)(const struct ieee80211_iface_combination *c,
void *data),
void *data)
@@ -1592,8 +1634,23 @@ int cfg80211_iter_combinations(struct wiphy *wiphy,
int i, j, iftype;
int num_interfaces = 0;
u32 used_iftypes = 0;
+ u32 beacon_int_gcd;
+ bool beacon_int_different;
- if (radar_detect) {
+ /*
+ * This is a bit strange, since the iteration used to rely only on
+ * the data given by the driver, but here it now relies on context,
+ * in form of the currently operating interfaces.
+ * This is OK for all current users, and saves us from having to
+ * push the GCD calculations into all the drivers.
+ * In the future, this should probably rely more on data that's in
+ * cfg80211 already - the only thing not would appear to be any new
+ * interfaces (while being brought up) and channel/radar data.
+ */
+ cfg80211_calculate_bi_data(wiphy, params->new_beacon_int,
+ &beacon_int_gcd, &beacon_int_different);
+
+ if (params->radar_detect) {
rcu_read_lock();
regdom = rcu_dereference(cfg80211_regdomain);
if (regdom)
@@ -1602,8 +1659,8 @@ int cfg80211_iter_combinations(struct wiphy *wiphy,
}
for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) {
- num_interfaces += iftype_num[iftype];
- if (iftype_num[iftype] > 0 &&
+ num_interfaces += params->iftype_num[iftype];
+ if (params->iftype_num[iftype] > 0 &&
!(wiphy->software_iftypes & BIT(iftype)))
used_iftypes |= BIT(iftype);
}
@@ -1617,7 +1674,7 @@ int cfg80211_iter_combinations(struct wiphy *wiphy,
if (num_interfaces > c->max_interfaces)
continue;
- if (num_different_channels > c->num_different_channels)
+ if (params->num_different_channels > c->num_different_channels)
continue;
limits = kmemdup(c->limits, sizeof(limits[0]) * c->n_limits,
@@ -1632,16 +1689,17 @@ int cfg80211_iter_combinations(struct wiphy *wiphy,
all_iftypes |= limits[j].types;
if (!(limits[j].types & BIT(iftype)))
continue;
- if (limits[j].max < iftype_num[iftype])
+ if (limits[j].max < params->iftype_num[iftype])
goto cont;
- limits[j].max -= iftype_num[iftype];
+ limits[j].max -= params->iftype_num[iftype];
}
}
- if (radar_detect != (c->radar_detect_widths & radar_detect))
+ if (params->radar_detect !=
+ (c->radar_detect_widths & params->radar_detect))
goto cont;
- if (radar_detect && c->radar_detect_regions &&
+ if (params->radar_detect && c->radar_detect_regions &&
!(c->radar_detect_regions & BIT(region)))
goto cont;
@@ -1653,6 +1711,14 @@ int cfg80211_iter_combinations(struct wiphy *wiphy,
if ((all_iftypes & used_iftypes) != used_iftypes)
goto cont;
+ if (beacon_int_gcd) {
+ if (c->beacon_int_min_gcd &&
+ beacon_int_gcd < c->beacon_int_min_gcd)
+ goto cont;
+ if (!c->beacon_int_min_gcd && beacon_int_different)
+ goto cont;
+ }
+
/* This combination covered all interface types and
* supported the requested numbers, so we're good.
*/
@@ -1675,14 +1741,11 @@ cfg80211_iter_sum_ifcombs(const struct ieee80211_iface_combination *c,
}
int cfg80211_check_combinations(struct wiphy *wiphy,
- const int num_different_channels,
- const u8 radar_detect,
- const int iftype_num[NUM_NL80211_IFTYPES])
+ struct iface_combination_params *params)
{
int err, num = 0;
- err = cfg80211_iter_combinations(wiphy, num_different_channels,
- radar_detect, iftype_num,
+ err = cfg80211_iter_combinations(wiphy, params,
cfg80211_iter_sum_ifcombs, &num);
if (err)
return err;
diff --git a/samples/Kconfig b/samples/Kconfig
index 85c405f..a6d2a43 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -99,4 +99,10 @@
Build samples of seccomp filters using various methods of
BPF filter construction.
+config SAMPLE_BLACKFIN_GPTIMERS
+ tristate "Build blackfin gptimers sample code -- loadable modules only"
+ depends on BLACKFIN && BFIN_GPTIMERS && m
+ help
+ Build samples of blackfin gptimers sample module.
+
endif # SAMPLES
diff --git a/samples/Makefile b/samples/Makefile
index 1a20169..e17d66d 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -2,4 +2,4 @@
obj-$(CONFIG_SAMPLES) += kobject/ kprobes/ trace_events/ livepatch/ \
hw_breakpoint/ kfifo/ kdb/ hidraw/ rpmsg/ seccomp/ \
- configfs/ connector/ v4l/ trace_printk/
+ configfs/ connector/ v4l/ trace_printk/ blackfin/
diff --git a/Documentation/auxdisplay/.gitignore b/samples/auxdisplay/.gitignore
similarity index 100%
rename from Documentation/auxdisplay/.gitignore
rename to samples/auxdisplay/.gitignore
diff --git a/samples/auxdisplay/Makefile b/samples/auxdisplay/Makefile
new file mode 100644
index 0000000..05e471f
--- /dev/null
+++ b/samples/auxdisplay/Makefile
@@ -0,0 +1,9 @@
+CC := $(CROSS_COMPILE)gcc
+CFLAGS := -I../../usr/include
+
+PROGS := cfag12864b-example
+
+all: $(PROGS)
+
+clean:
+ rm -fr $(PROGS)
diff --git a/Documentation/auxdisplay/cfag12864b-example.c b/samples/auxdisplay/cfag12864b-example.c
similarity index 100%
rename from Documentation/auxdisplay/cfag12864b-example.c
rename to samples/auxdisplay/cfag12864b-example.c
diff --git a/samples/blackfin/Makefile b/samples/blackfin/Makefile
new file mode 100644
index 0000000..89b86cf
--- /dev/null
+++ b/samples/blackfin/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_SAMPLE_BLACKFIN_GPTIMERS) += gptimers-example.o
diff --git a/Documentation/blackfin/gptimers-example.c b/samples/blackfin/gptimers-example.c
similarity index 100%
rename from Documentation/blackfin/gptimers-example.c
rename to samples/blackfin/gptimers-example.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 5c53fdb..f394ac6 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -2,6 +2,7 @@
obj- := dummy.o
# List of programs to build
+hostprogs-y := test_lru_dist
hostprogs-y += sock_example
hostprogs-y += fds_example
hostprogs-y += sockex1
@@ -26,7 +27,9 @@
hostprogs-y += test_current_task_under_cgroup
hostprogs-y += trace_event
hostprogs-y += sampleip
+hostprogs-y += tc_l2_redirect
+test_lru_dist-objs := test_lru_dist.o libbpf.o
sock_example-objs := sock_example.o libbpf.o
fds_example-objs := bpf_load.o libbpf.o fds_example.o
sockex1-objs := bpf_load.o libbpf.o sockex1_user.o
@@ -53,6 +56,7 @@
test_current_task_under_cgroup_user.o
trace_event-objs := bpf_load.o libbpf.o trace_event_user.o
sampleip-objs := bpf_load.o libbpf.o sampleip_user.o
+tc_l2_redirect-objs := bpf_load.o libbpf.o tc_l2_redirect_user.o
# Tell kbuild to always build the programs
always := $(hostprogs-y)
@@ -69,6 +73,7 @@
always += trace_output_kern.o
always += tcbpf1_kern.o
always += tcbpf2_kern.o
+always += tc_l2_redirect_kern.o
always += lathist_kern.o
always += offwaketime_kern.o
always += spintest_kern.o
@@ -108,6 +113,7 @@
HOSTLOADLIBES_test_current_task_under_cgroup += -lelf
HOSTLOADLIBES_trace_event += -lelf
HOSTLOADLIBES_sampleip += -lelf
+HOSTLOADLIBES_tc_l2_redirect += -l elf
# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index 311538e..7ee1574 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -19,6 +19,21 @@ struct bpf_map_def SEC("maps") hash_map = {
.max_entries = MAX_ENTRIES,
};
+struct bpf_map_def SEC("maps") lru_hash_map = {
+ .type = BPF_MAP_TYPE_LRU_HASH,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(long),
+ .max_entries = 10000,
+};
+
+struct bpf_map_def SEC("maps") percpu_lru_hash_map = {
+ .type = BPF_MAP_TYPE_LRU_HASH,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(long),
+ .max_entries = 10000,
+ .map_flags = BPF_F_NO_COMMON_LRU,
+};
+
struct bpf_map_def SEC("maps") percpu_hash_map = {
.type = BPF_MAP_TYPE_PERCPU_HASH,
.key_size = sizeof(u32),
@@ -53,6 +68,7 @@ int stress_hmap(struct pt_regs *ctx)
value = bpf_map_lookup_elem(&hash_map, &key);
if (value)
bpf_map_delete_elem(&hash_map, &key);
+
return 0;
}
@@ -96,5 +112,28 @@ int stress_percpu_hmap_alloc(struct pt_regs *ctx)
bpf_map_delete_elem(&percpu_hash_map_alloc, &key);
return 0;
}
+
+SEC("kprobe/sys_getpid")
+int stress_lru_hmap_alloc(struct pt_regs *ctx)
+{
+ u32 key = bpf_get_prandom_u32();
+ long val = 1;
+
+ bpf_map_update_elem(&lru_hash_map, &key, &val, BPF_ANY);
+
+ return 0;
+}
+
+SEC("kprobe/sys_getppid")
+int stress_percpu_lru_hmap_alloc(struct pt_regs *ctx)
+{
+ u32 key = bpf_get_prandom_u32();
+ long val = 1;
+
+ bpf_map_update_elem(&percpu_lru_hash_map, &key, &val, BPF_ANY);
+
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index 3147377..9505b4d 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -35,6 +35,8 @@ static __u64 time_get_ns(void)
#define PERCPU_HASH_PREALLOC (1 << 1)
#define HASH_KMALLOC (1 << 2)
#define PERCPU_HASH_KMALLOC (1 << 3)
+#define LRU_HASH_PREALLOC (1 << 4)
+#define PERCPU_LRU_HASH_PREALLOC (1 << 5)
static int test_flags = ~0;
@@ -50,6 +52,30 @@ static void test_hash_prealloc(int cpu)
cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
}
+static void test_lru_hash_prealloc(int cpu)
+{
+ __u64 start_time;
+ int i;
+
+ start_time = time_get_ns();
+ for (i = 0; i < MAX_CNT; i++)
+ syscall(__NR_getpid);
+ printf("%d:lru_hash_map_perf pre-alloc %lld events per sec\n",
+ cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+}
+
+static void test_percpu_lru_hash_prealloc(int cpu)
+{
+ __u64 start_time;
+ int i;
+
+ start_time = time_get_ns();
+ for (i = 0; i < MAX_CNT; i++)
+ syscall(__NR_getppid);
+ printf("%d:lru_hash_map_perf pre-alloc %lld events per sec\n",
+ cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+}
+
static void test_percpu_hash_prealloc(int cpu)
{
__u64 start_time;
@@ -105,6 +131,12 @@ static void loop(int cpu)
if (test_flags & PERCPU_HASH_KMALLOC)
test_percpu_hash_kmalloc(cpu);
+
+ if (test_flags & LRU_HASH_PREALLOC)
+ test_lru_hash_prealloc(cpu);
+
+ if (test_flags & PERCPU_LRU_HASH_PREALLOC)
+ test_percpu_lru_hash_prealloc(cpu);
}
static void run_perf_test(int tasks)
diff --git a/samples/bpf/parse_ldabs.c b/samples/bpf/parse_ldabs.c
index d175501..6db6b21 100644
--- a/samples/bpf/parse_ldabs.c
+++ b/samples/bpf/parse_ldabs.c
@@ -4,6 +4,7 @@
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
+#define KBUILD_MODNAME "foo"
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/in.h>
diff --git a/samples/bpf/parse_simple.c b/samples/bpf/parse_simple.c
index cf2511c..10af53d 100644
--- a/samples/bpf/parse_simple.c
+++ b/samples/bpf/parse_simple.c
@@ -4,6 +4,7 @@
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
+#define KBUILD_MODNAME "foo"
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/in.h>
diff --git a/samples/bpf/parse_varlen.c b/samples/bpf/parse_varlen.c
index edab34d..95c1632 100644
--- a/samples/bpf/parse_varlen.c
+++ b/samples/bpf/parse_varlen.c
@@ -4,6 +4,7 @@
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
+#define KBUILD_MODNAME "foo"
#include <linux/if_ether.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
diff --git a/samples/bpf/tc_l2_redirect.sh b/samples/bpf/tc_l2_redirect.sh
new file mode 100755
index 0000000..80a05591
--- /dev/null
+++ b/samples/bpf/tc_l2_redirect.sh
@@ -0,0 +1,173 @@
+#!/bin/bash
+
+[[ -z $TC ]] && TC='tc'
+[[ -z $IP ]] && IP='ip'
+
+REDIRECT_USER='./tc_l2_redirect'
+REDIRECT_BPF='./tc_l2_redirect_kern.o'
+
+RP_FILTER=$(< /proc/sys/net/ipv4/conf/all/rp_filter)
+IPV6_FORWARDING=$(< /proc/sys/net/ipv6/conf/all/forwarding)
+
+function config_common {
+ local tun_type=$1
+
+ $IP netns add ns1
+ $IP netns add ns2
+ $IP link add ve1 type veth peer name vens1
+ $IP link add ve2 type veth peer name vens2
+ $IP link set dev ve1 up
+ $IP link set dev ve2 up
+ $IP link set dev ve1 mtu 1500
+ $IP link set dev ve2 mtu 1500
+ $IP link set dev vens1 netns ns1
+ $IP link set dev vens2 netns ns2
+
+ $IP -n ns1 link set dev lo up
+ $IP -n ns1 link set dev vens1 up
+ $IP -n ns1 addr add 10.1.1.101/24 dev vens1
+ $IP -n ns1 addr add 2401:db01::65/64 dev vens1 nodad
+ $IP -n ns1 route add default via 10.1.1.1 dev vens1
+ $IP -n ns1 route add default via 2401:db01::1 dev vens1
+
+ $IP -n ns2 link set dev lo up
+ $IP -n ns2 link set dev vens2 up
+ $IP -n ns2 addr add 10.2.1.102/24 dev vens2
+ $IP -n ns2 addr add 2401:db02::66/64 dev vens2 nodad
+ $IP -n ns2 addr add 10.10.1.102 dev lo
+ $IP -n ns2 addr add 2401:face::66/64 dev lo nodad
+ $IP -n ns2 link add ipt2 type ipip local 10.2.1.102 remote 10.2.1.1
+ $IP -n ns2 link add ip6t2 type ip6tnl mode any local 2401:db02::66 remote 2401:db02::1
+ $IP -n ns2 link set dev ipt2 up
+ $IP -n ns2 link set dev ip6t2 up
+ $IP netns exec ns2 $TC qdisc add dev vens2 clsact
+ $IP netns exec ns2 $TC filter add dev vens2 ingress bpf da obj $REDIRECT_BPF sec drop_non_tun_vip
+ if [[ $tun_type == "ipip" ]]; then
+ $IP -n ns2 route add 10.1.1.0/24 dev ipt2
+ $IP netns exec ns2 sysctl -q -w net.ipv4.conf.all.rp_filter=0
+ $IP netns exec ns2 sysctl -q -w net.ipv4.conf.ipt2.rp_filter=0
+ else
+ $IP -n ns2 route add 10.1.1.0/24 dev ip6t2
+ $IP -n ns2 route add 2401:db01::/64 dev ip6t2
+ $IP netns exec ns2 sysctl -q -w net.ipv4.conf.all.rp_filter=0
+ $IP netns exec ns2 sysctl -q -w net.ipv4.conf.ip6t2.rp_filter=0
+ fi
+
+ $IP addr add 10.1.1.1/24 dev ve1
+ $IP addr add 2401:db01::1/64 dev ve1 nodad
+ $IP addr add 10.2.1.1/24 dev ve2
+ $IP addr add 2401:db02::1/64 dev ve2 nodad
+
+ $TC qdisc add dev ve2 clsact
+ $TC filter add dev ve2 ingress bpf da obj $REDIRECT_BPF sec l2_to_iptun_ingress_forward
+
+ sysctl -q -w net.ipv4.conf.all.rp_filter=0
+ sysctl -q -w net.ipv6.conf.all.forwarding=1
+}
+
+function cleanup {
+ set +e
+ [[ -z $DEBUG ]] || set +x
+ $IP netns delete ns1 >& /dev/null
+ $IP netns delete ns2 >& /dev/null
+ $IP link del ve1 >& /dev/null
+ $IP link del ve2 >& /dev/null
+ $IP link del ipt >& /dev/null
+ $IP link del ip6t >& /dev/null
+ sysctl -q -w net.ipv4.conf.all.rp_filter=$RP_FILTER
+ sysctl -q -w net.ipv6.conf.all.forwarding=$IPV6_FORWARDING
+ rm -f /sys/fs/bpf/tc/globals/tun_iface
+ [[ -z $DEBUG ]] || set -x
+ set -e
+}
+
+function l2_to_ipip {
+ echo -n "l2_to_ipip $1: "
+
+ local dir=$1
+
+ config_common ipip
+
+ $IP link add ipt type ipip external
+ $IP link set dev ipt up
+ sysctl -q -w net.ipv4.conf.ipt.rp_filter=0
+ sysctl -q -w net.ipv4.conf.ipt.forwarding=1
+
+ if [[ $dir == "egress" ]]; then
+ $IP route add 10.10.1.0/24 via 10.2.1.102 dev ve2
+ $TC filter add dev ve2 egress bpf da obj $REDIRECT_BPF sec l2_to_iptun_ingress_redirect
+ sysctl -q -w net.ipv4.conf.ve1.forwarding=1
+ else
+ $TC qdisc add dev ve1 clsact
+ $TC filter add dev ve1 ingress bpf da obj $REDIRECT_BPF sec l2_to_iptun_ingress_redirect
+ fi
+
+ $REDIRECT_USER -U /sys/fs/bpf/tc/globals/tun_iface -i $(< /sys/class/net/ipt/ifindex)
+
+ $IP netns exec ns1 ping -c1 10.10.1.102 >& /dev/null
+
+ if [[ $dir == "egress" ]]; then
+ # test direct egress to ve2 (i.e. not forwarding from
+ # ve1 to ve2).
+ ping -c1 10.10.1.102 >& /dev/null
+ fi
+
+ cleanup
+
+ echo "OK"
+}
+
+function l2_to_ip6tnl {
+ echo -n "l2_to_ip6tnl $1: "
+
+ local dir=$1
+
+ config_common ip6tnl
+
+ $IP link add ip6t type ip6tnl mode any external
+ $IP link set dev ip6t up
+ sysctl -q -w net.ipv4.conf.ip6t.rp_filter=0
+ sysctl -q -w net.ipv4.conf.ip6t.forwarding=1
+
+ if [[ $dir == "egress" ]]; then
+ $IP route add 10.10.1.0/24 via 10.2.1.102 dev ve2
+ $IP route add 2401:face::/64 via 2401:db02::66 dev ve2
+ $TC filter add dev ve2 egress bpf da obj $REDIRECT_BPF sec l2_to_ip6tun_ingress_redirect
+ sysctl -q -w net.ipv4.conf.ve1.forwarding=1
+ else
+ $TC qdisc add dev ve1 clsact
+ $TC filter add dev ve1 ingress bpf da obj $REDIRECT_BPF sec l2_to_ip6tun_ingress_redirect
+ fi
+
+ $REDIRECT_USER -U /sys/fs/bpf/tc/globals/tun_iface -i $(< /sys/class/net/ip6t/ifindex)
+
+ $IP netns exec ns1 ping -c1 10.10.1.102 >& /dev/null
+ $IP netns exec ns1 ping -6 -c1 2401:face::66 >& /dev/null
+
+ if [[ $dir == "egress" ]]; then
+ # test direct egress to ve2 (i.e. not forwarding from
+ # ve1 to ve2).
+ ping -c1 10.10.1.102 >& /dev/null
+ ping -6 -c1 2401:face::66 >& /dev/null
+ fi
+
+ cleanup
+
+ echo "OK"
+}
+
+cleanup
+test_names="l2_to_ipip l2_to_ip6tnl"
+test_dirs="ingress egress"
+if [[ $# -ge 2 ]]; then
+ test_names=$1
+ test_dirs=$2
+elif [[ $# -ge 1 ]]; then
+ test_names=$1
+fi
+
+for t in $test_names; do
+ for d in $test_dirs; do
+ $t $d
+ done
+done
diff --git a/samples/bpf/tc_l2_redirect_kern.c b/samples/bpf/tc_l2_redirect_kern.c
new file mode 100644
index 0000000..92a4472
--- /dev/null
+++ b/samples/bpf/tc_l2_redirect_kern.c
@@ -0,0 +1,236 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/ipv6.h>
+#include <uapi/linux/in.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/filter.h>
+#include <uapi/linux/pkt_cls.h>
+#include <net/ipv6.h>
+#include "bpf_helpers.h"
+
+#define _htonl __builtin_bswap32
+
+#define PIN_GLOBAL_NS 2
+struct bpf_elf_map {
+ __u32 type;
+ __u32 size_key;
+ __u32 size_value;
+ __u32 max_elem;
+ __u32 flags;
+ __u32 id;
+ __u32 pinning;
+};
+
+/* copy of 'struct ethhdr' without __packed */
+struct eth_hdr {
+ unsigned char h_dest[ETH_ALEN];
+ unsigned char h_source[ETH_ALEN];
+ unsigned short h_proto;
+};
+
+struct bpf_elf_map SEC("maps") tun_iface = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .size_key = sizeof(int),
+ .size_value = sizeof(int),
+ .pinning = PIN_GLOBAL_NS,
+ .max_elem = 1,
+};
+
+static __always_inline bool is_vip_addr(__be16 eth_proto, __be32 daddr)
+{
+ if (eth_proto == htons(ETH_P_IP))
+ return (_htonl(0xffffff00) & daddr) == _htonl(0x0a0a0100);
+ else if (eth_proto == htons(ETH_P_IPV6))
+ return (daddr == _htonl(0x2401face));
+
+ return false;
+}
+
+SEC("l2_to_iptun_ingress_forward")
+int _l2_to_iptun_ingress_forward(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key tkey = {};
+ void *data = (void *)(long)skb->data;
+ struct eth_hdr *eth = data;
+ void *data_end = (void *)(long)skb->data_end;
+ int key = 0, *ifindex;
+
+ int ret;
+
+ if (data + sizeof(*eth) > data_end)
+ return TC_ACT_OK;
+
+ ifindex = bpf_map_lookup_elem(&tun_iface, &key);
+ if (!ifindex)
+ return TC_ACT_OK;
+
+ if (eth->h_proto == htons(ETH_P_IP)) {
+ char fmt4[] = "ingress forward to ifindex:%d daddr4:%x\n";
+ struct iphdr *iph = data + sizeof(*eth);
+
+ if (data + sizeof(*eth) + sizeof(*iph) > data_end)
+ return TC_ACT_OK;
+
+ if (iph->protocol != IPPROTO_IPIP)
+ return TC_ACT_OK;
+
+ bpf_trace_printk(fmt4, sizeof(fmt4), *ifindex,
+ _htonl(iph->daddr));
+ return bpf_redirect(*ifindex, BPF_F_INGRESS);
+ } else if (eth->h_proto == htons(ETH_P_IPV6)) {
+ char fmt6[] = "ingress forward to ifindex:%d daddr6:%x::%x\n";
+ struct ipv6hdr *ip6h = data + sizeof(*eth);
+
+ if (data + sizeof(*eth) + sizeof(*ip6h) > data_end)
+ return TC_ACT_OK;
+
+ if (ip6h->nexthdr != IPPROTO_IPIP &&
+ ip6h->nexthdr != IPPROTO_IPV6)
+ return TC_ACT_OK;
+
+ bpf_trace_printk(fmt6, sizeof(fmt6), *ifindex,
+ _htonl(ip6h->daddr.s6_addr32[0]),
+ _htonl(ip6h->daddr.s6_addr32[3]));
+ return bpf_redirect(*ifindex, BPF_F_INGRESS);
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("l2_to_iptun_ingress_redirect")
+int _l2_to_iptun_ingress_redirect(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key tkey = {};
+ void *data = (void *)(long)skb->data;
+ struct eth_hdr *eth = data;
+ void *data_end = (void *)(long)skb->data_end;
+ int key = 0, *ifindex;
+
+ int ret;
+
+ if (data + sizeof(*eth) > data_end)
+ return TC_ACT_OK;
+
+ ifindex = bpf_map_lookup_elem(&tun_iface, &key);
+ if (!ifindex)
+ return TC_ACT_OK;
+
+ if (eth->h_proto == htons(ETH_P_IP)) {
+ char fmt4[] = "e/ingress redirect daddr4:%x to ifindex:%d\n";
+ struct iphdr *iph = data + sizeof(*eth);
+ __be32 daddr = iph->daddr;
+
+ if (data + sizeof(*eth) + sizeof(*iph) > data_end)
+ return TC_ACT_OK;
+
+ if (!is_vip_addr(eth->h_proto, daddr))
+ return TC_ACT_OK;
+
+ bpf_trace_printk(fmt4, sizeof(fmt4), _htonl(daddr), *ifindex);
+ } else {
+ return TC_ACT_OK;
+ }
+
+ tkey.tunnel_id = 10000;
+ tkey.tunnel_ttl = 64;
+ tkey.remote_ipv4 = 0x0a020166; /* 10.2.1.102 */
+ bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), 0);
+ return bpf_redirect(*ifindex, 0);
+}
+
+SEC("l2_to_ip6tun_ingress_redirect")
+int _l2_to_ip6tun_ingress_redirect(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key tkey = {};
+ void *data = (void *)(long)skb->data;
+ struct eth_hdr *eth = data;
+ void *data_end = (void *)(long)skb->data_end;
+ int key = 0, *ifindex;
+
+ if (data + sizeof(*eth) > data_end)
+ return TC_ACT_OK;
+
+ ifindex = bpf_map_lookup_elem(&tun_iface, &key);
+ if (!ifindex)
+ return TC_ACT_OK;
+
+ if (eth->h_proto == htons(ETH_P_IP)) {
+ char fmt4[] = "e/ingress redirect daddr4:%x to ifindex:%d\n";
+ struct iphdr *iph = data + sizeof(*eth);
+
+ if (data + sizeof(*eth) + sizeof(*iph) > data_end)
+ return TC_ACT_OK;
+
+ if (!is_vip_addr(eth->h_proto, iph->daddr))
+ return TC_ACT_OK;
+
+ bpf_trace_printk(fmt4, sizeof(fmt4), _htonl(iph->daddr),
+ *ifindex);
+ } else if (eth->h_proto == htons(ETH_P_IPV6)) {
+ char fmt6[] = "e/ingress redirect daddr6:%x to ifindex:%d\n";
+ struct ipv6hdr *ip6h = data + sizeof(*eth);
+
+ if (data + sizeof(*eth) + sizeof(*ip6h) > data_end)
+ return TC_ACT_OK;
+
+ if (!is_vip_addr(eth->h_proto, ip6h->daddr.s6_addr32[0]))
+ return TC_ACT_OK;
+
+ bpf_trace_printk(fmt6, sizeof(fmt6),
+ _htonl(ip6h->daddr.s6_addr32[0]), *ifindex);
+ } else {
+ return TC_ACT_OK;
+ }
+
+ tkey.tunnel_id = 10000;
+ tkey.tunnel_ttl = 64;
+ /* 2401:db02:0:0:0:0:0:66 */
+ tkey.remote_ipv6[0] = _htonl(0x2401db02);
+ tkey.remote_ipv6[1] = 0;
+ tkey.remote_ipv6[2] = 0;
+ tkey.remote_ipv6[3] = _htonl(0x00000066);
+ bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), BPF_F_TUNINFO_IPV6);
+ return bpf_redirect(*ifindex, 0);
+}
+
+SEC("drop_non_tun_vip")
+int _drop_non_tun_vip(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key tkey = {};
+ void *data = (void *)(long)skb->data;
+ struct eth_hdr *eth = data;
+ void *data_end = (void *)(long)skb->data_end;
+
+ if (data + sizeof(*eth) > data_end)
+ return TC_ACT_OK;
+
+ if (eth->h_proto == htons(ETH_P_IP)) {
+ struct iphdr *iph = data + sizeof(*eth);
+
+ if (data + sizeof(*eth) + sizeof(*iph) > data_end)
+ return TC_ACT_OK;
+
+ if (is_vip_addr(eth->h_proto, iph->daddr))
+ return TC_ACT_SHOT;
+ } else if (eth->h_proto == htons(ETH_P_IPV6)) {
+ struct ipv6hdr *ip6h = data + sizeof(*eth);
+
+ if (data + sizeof(*eth) + sizeof(*ip6h) > data_end)
+ return TC_ACT_OK;
+
+ if (is_vip_addr(eth->h_proto, ip6h->daddr.s6_addr32[0]))
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/tc_l2_redirect_user.c b/samples/bpf/tc_l2_redirect_user.c
new file mode 100644
index 0000000..4013c53
--- /dev/null
+++ b/samples/bpf/tc_l2_redirect_user.c
@@ -0,0 +1,73 @@
+/* Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/unistd.h>
+#include <linux/bpf.h>
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+
+#include "libbpf.h"
+
+static void usage(void)
+{
+ printf("Usage: tc_l2_ipip_redirect [...]\n");
+ printf(" -U <file> Update an already pinned BPF array\n");
+ printf(" -i <ifindex> Interface index\n");
+ printf(" -h Display this help\n");
+}
+
+int main(int argc, char **argv)
+{
+ const char *pinned_file = NULL;
+ int ifindex = -1;
+ int array_key = 0;
+ int array_fd = -1;
+ int ret = -1;
+ int opt;
+
+ while ((opt = getopt(argc, argv, "F:U:i:")) != -1) {
+ switch (opt) {
+ /* General args */
+ case 'U':
+ pinned_file = optarg;
+ break;
+ case 'i':
+ ifindex = atoi(optarg);
+ break;
+ default:
+ usage();
+ goto out;
+ }
+ }
+
+ if (ifindex < 0 || !pinned_file) {
+ usage();
+ goto out;
+ }
+
+ array_fd = bpf_obj_get(pinned_file);
+ if (array_fd < 0) {
+ fprintf(stderr, "bpf_obj_get(%s): %s(%d)\n",
+ pinned_file, strerror(errno), errno);
+ goto out;
+ }
+
+ /* bpf_tunnel_key.remote_ipv4 expects host byte orders */
+ ret = bpf_update_elem(array_fd, &array_key, &ifindex, 0);
+ if (ret) {
+ perror("bpf_update_elem");
+ goto out;
+ }
+
+out:
+ if (array_fd != -1)
+ close(array_fd);
+ return ret;
+}
diff --git a/samples/bpf/tcbpf1_kern.c b/samples/bpf/tcbpf1_kern.c
index fa051b3..274c884 100644
--- a/samples/bpf/tcbpf1_kern.c
+++ b/samples/bpf/tcbpf1_kern.c
@@ -1,3 +1,4 @@
+#define KBUILD_MODNAME "foo"
#include <uapi/linux/bpf.h>
#include <uapi/linux/if_ether.h>
#include <uapi/linux/if_packet.h>
diff --git a/samples/bpf/tcbpf2_kern.c b/samples/bpf/tcbpf2_kern.c
index 3303bb8..9c823a6 100644
--- a/samples/bpf/tcbpf2_kern.c
+++ b/samples/bpf/tcbpf2_kern.c
@@ -5,6 +5,7 @@
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
+#define KBUILD_MODNAME "foo"
#include <uapi/linux/bpf.h>
#include <uapi/linux/if_ether.h>
#include <uapi/linux/if_packet.h>
diff --git a/samples/bpf/test_cgrp2_tc_kern.c b/samples/bpf/test_cgrp2_tc_kern.c
index 10ff734..1547b36 100644
--- a/samples/bpf/test_cgrp2_tc_kern.c
+++ b/samples/bpf/test_cgrp2_tc_kern.c
@@ -4,6 +4,7 @@
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
+#define KBUILD_MODNAME "foo"
#include <uapi/linux/if_ether.h>
#include <uapi/linux/in6.h>
#include <uapi/linux/ipv6.h>
diff --git a/samples/bpf/test_lru_dist.c b/samples/bpf/test_lru_dist.c
new file mode 100644
index 0000000..2859977
--- /dev/null
+++ b/samples/bpf/test_lru_dist.c
@@ -0,0 +1,538 @@
+/*
+ * Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#define _GNU_SOURCE
+#include <linux/types.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <linux/bpf.h>
+#include <errno.h>
+#include <string.h>
+#include <assert.h>
+#include <sched.h>
+#include <sys/wait.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <time.h>
+#include "libbpf.h"
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+#define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER)
+#define container_of(ptr, type, member) ({ \
+ const typeof( ((type *)0)->member ) *__mptr = (ptr); \
+ (type *)( (char *)__mptr - offsetof(type,member) );})
+
+static int nr_cpus;
+static unsigned long long *dist_keys;
+static unsigned int dist_key_counts;
+
+struct list_head {
+ struct list_head *next, *prev;
+};
+
+static inline void INIT_LIST_HEAD(struct list_head *list)
+{
+ list->next = list;
+ list->prev = list;
+}
+
+static inline int list_empty(const struct list_head *head)
+{
+ return head->next == head;
+}
+
+static inline void __list_add(struct list_head *new,
+ struct list_head *prev,
+ struct list_head *next)
+{
+ next->prev = new;
+ new->next = next;
+ new->prev = prev;
+ prev->next = new;
+}
+
+static inline void list_add(struct list_head *new, struct list_head *head)
+{
+ __list_add(new, head, head->next);
+}
+
+static inline void __list_del(struct list_head *prev, struct list_head *next)
+{
+ next->prev = prev;
+ prev->next = next;
+}
+
+static inline void __list_del_entry(struct list_head *entry)
+{
+ __list_del(entry->prev, entry->next);
+}
+
+static inline void list_move(struct list_head *list, struct list_head *head)
+{
+ __list_del_entry(list);
+ list_add(list, head);
+}
+
+#define list_entry(ptr, type, member) \
+ container_of(ptr, type, member)
+
+#define list_last_entry(ptr, type, member) \
+ list_entry((ptr)->prev, type, member)
+
+struct pfect_lru_node {
+ struct list_head list;
+ unsigned long long key;
+};
+
+struct pfect_lru {
+ struct list_head list;
+ struct pfect_lru_node *free_nodes;
+ unsigned int cur_size;
+ unsigned int lru_size;
+ unsigned int nr_unique;
+ unsigned int nr_misses;
+ unsigned int total;
+ int map_fd;
+};
+
+static void pfect_lru_init(struct pfect_lru *lru, unsigned int lru_size,
+ unsigned int nr_possible_elems)
+{
+ lru->map_fd = bpf_create_map(BPF_MAP_TYPE_HASH,
+ sizeof(unsigned long long),
+ sizeof(struct pfect_lru_node *),
+ nr_possible_elems, 0);
+ assert(lru->map_fd != -1);
+
+ lru->free_nodes = malloc(lru_size * sizeof(struct pfect_lru_node));
+ assert(lru->free_nodes);
+
+ INIT_LIST_HEAD(&lru->list);
+ lru->cur_size = 0;
+ lru->lru_size = lru_size;
+ lru->nr_unique = lru->nr_misses = lru->total = 0;
+}
+
+static void pfect_lru_destroy(struct pfect_lru *lru)
+{
+ close(lru->map_fd);
+ free(lru->free_nodes);
+}
+
+static int pfect_lru_lookup_or_insert(struct pfect_lru *lru,
+ unsigned long long key)
+{
+ struct pfect_lru_node *node = NULL;
+ int seen = 0;
+
+ lru->total++;
+ if (!bpf_lookup_elem(lru->map_fd, &key, &node)) {
+ if (node) {
+ list_move(&node->list, &lru->list);
+ return 1;
+ }
+ seen = 1;
+ }
+
+ if (lru->cur_size < lru->lru_size) {
+ node = &lru->free_nodes[lru->cur_size++];
+ INIT_LIST_HEAD(&node->list);
+ } else {
+ struct pfect_lru_node *null_node = NULL;
+
+ node = list_last_entry(&lru->list,
+ struct pfect_lru_node,
+ list);
+ bpf_update_elem(lru->map_fd, &node->key, &null_node, BPF_EXIST);
+ }
+
+ node->key = key;
+ list_move(&node->list, &lru->list);
+
+ lru->nr_misses++;
+ if (seen) {
+ assert(!bpf_update_elem(lru->map_fd, &key, &node, BPF_EXIST));
+ } else {
+ lru->nr_unique++;
+ assert(!bpf_update_elem(lru->map_fd, &key, &node, BPF_NOEXIST));
+ }
+
+ return seen;
+}
+
+static unsigned int read_keys(const char *dist_file,
+ unsigned long long **keys)
+{
+ struct stat fst;
+ unsigned long long *retkeys;
+ unsigned int counts = 0;
+ int dist_fd;
+ char *b, *l;
+ int i;
+
+ dist_fd = open(dist_file, 0);
+ assert(dist_fd != -1);
+
+ assert(fstat(dist_fd, &fst) == 0);
+ b = malloc(fst.st_size);
+ assert(b);
+
+ assert(read(dist_fd, b, fst.st_size) == fst.st_size);
+ close(dist_fd);
+ for (i = 0; i < fst.st_size; i++) {
+ if (b[i] == '\n')
+ counts++;
+ }
+ counts++; /* in case the last line has no \n */
+
+ retkeys = malloc(counts * sizeof(unsigned long long));
+ assert(retkeys);
+
+ counts = 0;
+ for (l = strtok(b, "\n"); l; l = strtok(NULL, "\n"))
+ retkeys[counts++] = strtoull(l, NULL, 10);
+ free(b);
+
+ *keys = retkeys;
+
+ return counts;
+}
+
+static int create_map(int map_type, int map_flags, unsigned int size)
+{
+ int map_fd;
+
+ map_fd = bpf_create_map(map_type, sizeof(unsigned long long),
+ sizeof(unsigned long long), size, map_flags);
+
+ if (map_fd == -1)
+ perror("bpf_create_map");
+
+ return map_fd;
+}
+
+static int sched_next_online(int pid, int next_to_try)
+{
+ cpu_set_t cpuset;
+
+ if (next_to_try == nr_cpus)
+ return -1;
+
+ while (next_to_try < nr_cpus) {
+ CPU_ZERO(&cpuset);
+ CPU_SET(next_to_try++, &cpuset);
+ if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset))
+ break;
+ }
+
+ return next_to_try;
+}
+
+static void run_parallel(unsigned int tasks, void (*fn)(int i, void *data),
+ void *data)
+{
+ int next_sched_cpu = 0;
+ pid_t pid[tasks];
+ int i;
+
+ for (i = 0; i < tasks; i++) {
+ pid[i] = fork();
+ if (pid[i] == 0) {
+ next_sched_cpu = sched_next_online(0, next_sched_cpu);
+ fn(i, data);
+ exit(0);
+ } else if (pid[i] == -1) {
+ printf("couldn't spawn #%d process\n", i);
+ exit(1);
+ }
+ /* It is mostly redundant and just allow the parent
+ * process to update next_shced_cpu for the next child
+ * process
+ */
+ next_sched_cpu = sched_next_online(pid[i], next_sched_cpu);
+ }
+ for (i = 0; i < tasks; i++) {
+ int status;
+
+ assert(waitpid(pid[i], &status, 0) == pid[i]);
+ assert(status == 0);
+ }
+}
+
+static void do_test_lru_dist(int task, void *data)
+{
+ unsigned int nr_misses = 0;
+ struct pfect_lru pfect_lru;
+ unsigned long long key, value = 1234;
+ unsigned int i;
+
+ unsigned int lru_map_fd = ((unsigned int *)data)[0];
+ unsigned int lru_size = ((unsigned int *)data)[1];
+ unsigned long long key_offset = task * dist_key_counts;
+
+ pfect_lru_init(&pfect_lru, lru_size, dist_key_counts);
+
+ for (i = 0; i < dist_key_counts; i++) {
+ key = dist_keys[i] + key_offset;
+
+ pfect_lru_lookup_or_insert(&pfect_lru, key);
+
+ if (!bpf_lookup_elem(lru_map_fd, &key, &value))
+ continue;
+
+ if (bpf_update_elem(lru_map_fd, &key, &value, BPF_NOEXIST)) {
+ printf("bpf_update_elem(lru_map_fd, %llu): errno:%d\n",
+ key, errno);
+ assert(0);
+ }
+
+ nr_misses++;
+ }
+
+ printf(" task:%d BPF LRU: nr_unique:%u(/%u) nr_misses:%u(/%u)\n",
+ task, pfect_lru.nr_unique, dist_key_counts, nr_misses,
+ dist_key_counts);
+ printf(" task:%d Perfect LRU: nr_unique:%u(/%u) nr_misses:%u(/%u)\n",
+ task, pfect_lru.nr_unique, pfect_lru.total,
+ pfect_lru.nr_misses, pfect_lru.total);
+
+ pfect_lru_destroy(&pfect_lru);
+ close(lru_map_fd);
+}
+
+static void test_parallel_lru_dist(int map_type, int map_flags,
+ int nr_tasks, unsigned int lru_size)
+{
+ int child_data[2];
+ int lru_map_fd;
+
+ printf("%s (map_type:%d map_flags:0x%X):\n", __func__, map_type,
+ map_flags);
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ lru_map_fd = create_map(map_type, map_flags,
+ nr_cpus * lru_size);
+ else
+ lru_map_fd = create_map(map_type, map_flags,
+ nr_tasks * lru_size);
+ assert(lru_map_fd != -1);
+
+ child_data[0] = lru_map_fd;
+ child_data[1] = lru_size;
+
+ run_parallel(nr_tasks, do_test_lru_dist, child_data);
+
+ close(lru_map_fd);
+}
+
+static void test_lru_loss0(int map_type, int map_flags)
+{
+ unsigned long long key, value[nr_cpus];
+ unsigned int old_unused_losses = 0;
+ unsigned int new_unused_losses = 0;
+ unsigned int used_losses = 0;
+ int map_fd;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ assert(sched_next_online(0, 0) != -1);
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ map_fd = create_map(map_type, map_flags, 900 * nr_cpus);
+ else
+ map_fd = create_map(map_type, map_flags, 900);
+
+ assert(map_fd != -1);
+
+ value[0] = 1234;
+
+ for (key = 1; key <= 1000; key++) {
+ int start_key, end_key;
+
+ assert(bpf_update_elem(map_fd, &key, value, BPF_NOEXIST) == 0);
+
+ start_key = 101;
+ end_key = min(key, 900);
+
+ while (start_key <= end_key) {
+ bpf_lookup_elem(map_fd, &start_key, value);
+ start_key++;
+ }
+ }
+
+ for (key = 1; key <= 1000; key++) {
+ if (bpf_lookup_elem(map_fd, &key, value)) {
+ if (key <= 100)
+ old_unused_losses++;
+ else if (key <= 900)
+ used_losses++;
+ else
+ new_unused_losses++;
+ }
+ }
+
+ close(map_fd);
+
+ printf("older-elem-losses:%d(/100) active-elem-losses:%d(/800) "
+ "newer-elem-losses:%d(/100)\n",
+ old_unused_losses, used_losses, new_unused_losses);
+}
+
+static void test_lru_loss1(int map_type, int map_flags)
+{
+ unsigned long long key, value[nr_cpus];
+ int map_fd;
+ unsigned int nr_losses = 0;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ assert(sched_next_online(0, 0) != -1);
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ map_fd = create_map(map_type, map_flags, 1000 * nr_cpus);
+ else
+ map_fd = create_map(map_type, map_flags, 1000);
+
+ assert(map_fd != -1);
+
+ value[0] = 1234;
+
+ for (key = 1; key <= 1000; key++)
+ assert(!bpf_update_elem(map_fd, &key, value, BPF_NOEXIST));
+
+ for (key = 1; key <= 1000; key++) {
+ if (bpf_lookup_elem(map_fd, &key, value))
+ nr_losses++;
+ }
+
+ close(map_fd);
+
+ printf("nr_losses:%d(/1000)\n", nr_losses);
+}
+
+static void do_test_parallel_lru_loss(int task, void *data)
+{
+ const unsigned int nr_stable_elems = 1000;
+ const unsigned int nr_repeats = 100000;
+
+ int map_fd = *(int *)data;
+ unsigned long long stable_base;
+ unsigned long long key, value[nr_cpus];
+ unsigned long long next_ins_key;
+ unsigned int nr_losses = 0;
+ unsigned int i;
+
+ stable_base = task * nr_repeats * 2 + 1;
+ next_ins_key = stable_base;
+ value[0] = 1234;
+ for (i = 0; i < nr_stable_elems; i++) {
+ assert(bpf_update_elem(map_fd, &next_ins_key, value,
+ BPF_NOEXIST) == 0);
+ next_ins_key++;
+ }
+
+ for (i = 0; i < nr_repeats; i++) {
+ int rn;
+
+ rn = rand();
+
+ if (rn % 10) {
+ key = rn % nr_stable_elems + stable_base;
+ bpf_lookup_elem(map_fd, &key, value);
+ } else {
+ bpf_update_elem(map_fd, &next_ins_key, value,
+ BPF_NOEXIST);
+ next_ins_key++;
+ }
+ }
+
+ key = stable_base;
+ for (i = 0; i < nr_stable_elems; i++) {
+ if (bpf_lookup_elem(map_fd, &key, value))
+ nr_losses++;
+ key++;
+ }
+
+ printf(" task:%d nr_losses:%u\n", task, nr_losses);
+}
+
+static void test_parallel_lru_loss(int map_type, int map_flags, int nr_tasks)
+{
+ int map_fd;
+
+ printf("%s (map_type:%d map_flags:0x%X):\n", __func__, map_type,
+ map_flags);
+
+ /* Give 20% more than the active working set */
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ map_fd = create_map(map_type, map_flags,
+ nr_cpus * (1000 + 200));
+ else
+ map_fd = create_map(map_type, map_flags,
+ nr_tasks * (1000 + 200));
+
+ assert(map_fd != -1);
+
+ run_parallel(nr_tasks, do_test_parallel_lru_loss, &map_fd);
+
+ close(map_fd);
+}
+
+int main(int argc, char **argv)
+{
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+ int map_flags[] = {0, BPF_F_NO_COMMON_LRU};
+ const char *dist_file;
+ int nr_tasks = 1;
+ int lru_size;
+ int f;
+
+ if (argc < 4) {
+ printf("Usage: %s <dist-file> <lru-size> <nr-tasks>\n",
+ argv[0]);
+ return -1;
+ }
+
+ dist_file = argv[1];
+ lru_size = atoi(argv[2]);
+ nr_tasks = atoi(argv[3]);
+
+ setbuf(stdout, NULL);
+
+ assert(!setrlimit(RLIMIT_MEMLOCK, &r));
+
+ srand(time(NULL));
+
+ nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+ assert(nr_cpus != -1);
+ printf("nr_cpus:%d\n\n", nr_cpus);
+
+ nr_tasks = min(nr_tasks, nr_cpus);
+
+ dist_key_counts = read_keys(dist_file, &dist_keys);
+ if (!dist_key_counts) {
+ printf("%s has no key\n", dist_file);
+ return -1;
+ }
+
+ for (f = 0; f < sizeof(map_flags) / sizeof(*map_flags); f++) {
+ test_lru_loss0(BPF_MAP_TYPE_LRU_HASH, map_flags[f]);
+ test_lru_loss1(BPF_MAP_TYPE_LRU_HASH, map_flags[f]);
+ test_parallel_lru_loss(BPF_MAP_TYPE_LRU_HASH, map_flags[f],
+ nr_tasks);
+ test_parallel_lru_dist(BPF_MAP_TYPE_LRU_HASH, map_flags[f],
+ nr_tasks, lru_size);
+ printf("\n");
+ }
+
+ free(dist_keys);
+
+ return 0;
+}
diff --git a/Documentation/misc-devices/mei/.gitignore b/samples/mei/.gitignore
similarity index 100%
rename from Documentation/misc-devices/mei/.gitignore
rename to samples/mei/.gitignore
diff --git a/samples/mei/Makefile b/samples/mei/Makefile
new file mode 100644
index 0000000..7aac216
--- /dev/null
+++ b/samples/mei/Makefile
@@ -0,0 +1,9 @@
+CC := $(CROSS_COMPILE)gcc
+CFLAGS := -I../../usr/include
+
+PROGS := mei-amt-version
+
+all: $(PROGS)
+
+clean:
+ rm -fr $(PROGS)
diff --git a/Documentation/misc-devices/mei/TODO b/samples/mei/TODO
similarity index 100%
rename from Documentation/misc-devices/mei/TODO
rename to samples/mei/TODO
diff --git a/Documentation/misc-devices/mei/mei-amt-version.c b/samples/mei/mei-amt-version.c
similarity index 100%
rename from Documentation/misc-devices/mei/mei-amt-version.c
rename to samples/mei/mei-amt-version.c
diff --git a/Documentation/mic/mpssd/.gitignore b/samples/mic/mpssd/.gitignore
similarity index 100%
rename from Documentation/mic/mpssd/.gitignore
rename to samples/mic/mpssd/.gitignore
diff --git a/samples/mic/mpssd/Makefile b/samples/mic/mpssd/Makefile
new file mode 100644
index 0000000..3e3ef91
--- /dev/null
+++ b/samples/mic/mpssd/Makefile
@@ -0,0 +1,27 @@
+ifndef CROSS_COMPILE
+uname_M := $(shell uname -m 2>/dev/null || echo not)
+ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
+
+ifeq ($(ARCH),x86)
+
+PROGS := mpssd
+CC = $(CROSS_COMPILE)gcc
+CFLAGS := -I../../../usr/include -I../../../tools/include
+
+ifdef DEBUG
+CFLAGS += -DDEBUG=$(DEBUG)
+endif
+
+all: $(PROGS)
+mpssd: mpssd.c sysfs.c
+ $(CC) $(CFLAGS) mpssd.c sysfs.c -o mpssd -lpthread
+
+install:
+ install mpssd /usr/sbin/mpssd
+ install micctrl /usr/sbin/micctrl
+
+clean:
+ rm -fr $(PROGS)
+
+endif
+endif
diff --git a/Documentation/mic/mpssd/micctrl b/samples/mic/mpssd/micctrl
similarity index 100%
rename from Documentation/mic/mpssd/micctrl
rename to samples/mic/mpssd/micctrl
diff --git a/Documentation/mic/mpssd/mpss b/samples/mic/mpssd/mpss
similarity index 100%
rename from Documentation/mic/mpssd/mpss
rename to samples/mic/mpssd/mpss
diff --git a/Documentation/mic/mpssd/mpssd.c b/samples/mic/mpssd/mpssd.c
similarity index 100%
rename from Documentation/mic/mpssd/mpssd.c
rename to samples/mic/mpssd/mpssd.c
diff --git a/Documentation/mic/mpssd/mpssd.h b/samples/mic/mpssd/mpssd.h
similarity index 100%
rename from Documentation/mic/mpssd/mpssd.h
rename to samples/mic/mpssd/mpssd.h
diff --git a/Documentation/mic/mpssd/sysfs.c b/samples/mic/mpssd/sysfs.c
similarity index 100%
rename from Documentation/mic/mpssd/sysfs.c
rename to samples/mic/mpssd/sysfs.c
diff --git a/Documentation/timers/.gitignore b/samples/timers/.gitignore
similarity index 100%
rename from Documentation/timers/.gitignore
rename to samples/timers/.gitignore
diff --git a/samples/timers/Makefile b/samples/timers/Makefile
new file mode 100644
index 0000000..a5c3c4a
--- /dev/null
+++ b/samples/timers/Makefile
@@ -0,0 +1,15 @@
+ifndef CROSS_COMPILE
+uname_M := $(shell uname -m 2>/dev/null || echo not)
+ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
+
+ifeq ($(ARCH),x86)
+CC := $(CROSS_COMPILE)gcc
+PROGS := hpet_example
+
+all: $(PROGS)
+
+clean:
+ rm -fr $(PROGS)
+
+endif
+endif
diff --git a/Documentation/timers/hpet_example.c b/samples/timers/hpet_example.c
similarity index 100%
rename from Documentation/timers/hpet_example.c
rename to samples/timers/hpet_example.c
diff --git a/samples/watchdog/.gitignore b/samples/watchdog/.gitignore
new file mode 100644
index 0000000..ff0ebb5
--- /dev/null
+++ b/samples/watchdog/.gitignore
@@ -0,0 +1 @@
+watchdog-simple
diff --git a/samples/watchdog/Makefile b/samples/watchdog/Makefile
new file mode 100644
index 0000000..9b53d89
--- /dev/null
+++ b/samples/watchdog/Makefile
@@ -0,0 +1,8 @@
+CC := $(CROSS_COMPILE)gcc
+PROGS := watchdog-simple
+
+all: $(PROGS)
+
+clean:
+ rm -fr $(PROGS)
+
diff --git a/Documentation/watchdog/src/watchdog-simple.c b/samples/watchdog/watchdog-simple.c
similarity index 100%
rename from Documentation/watchdog/src/watchdog-simple.c
rename to samples/watchdog/watchdog-simple.c
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 11602e5..de46ab0 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -81,6 +81,7 @@
ifneq ($(strip $(lib-y) $(lib-m) $(lib-)),)
lib-target := $(obj)/lib.a
+obj-y += $(obj)/lib-ksyms.o
endif
ifneq ($(strip $(obj-y) $(obj-m) $(obj-) $(subdir-m) $(lib-target)),)
@@ -358,12 +359,22 @@
# Rule to compile a set of .o files into one .o file
#
ifdef builtin-target
-quiet_cmd_link_o_target = LD $@
+
+ifdef CONFIG_THIN_ARCHIVES
+ cmd_make_builtin = rm -f $@; $(AR) rcST$(KBUILD_ARFLAGS)
+ cmd_make_empty_builtin = rm -f $@; $(AR) rcST$(KBUILD_ARFLAGS)
+ quiet_cmd_link_o_target = AR $@
+else
+ cmd_make_builtin = $(LD) $(ld_flags) -r -o
+ cmd_make_empty_builtin = rm -f $@; $(AR) rcs$(KBUILD_ARFLAGS)
+ quiet_cmd_link_o_target = LD $@
+endif
+
# If the list of objects to link is empty, just create an empty built-in.o
cmd_link_o_target = $(if $(strip $(obj-y)),\
- $(LD) $(ld_flags) -r -o $@ $(filter $(obj-y), $^) \
+ $(cmd_make_builtin) $@ $(filter $(obj-y), $^) \
$(cmd_secanalysis),\
- rm -f $@; $(AR) rcs$(KBUILD_ARFLAGS) $@)
+ $(cmd_make_empty_builtin) $@)
$(builtin-target): $(obj-y) FORCE
$(call if_changed,link_o_target)
@@ -389,12 +400,36 @@
#
ifdef lib-target
quiet_cmd_link_l_target = AR $@
-cmd_link_l_target = rm -f $@; $(AR) rcs$(KBUILD_ARFLAGS) $@ $(lib-y)
+
+ifdef CONFIG_THIN_ARCHIVES
+ cmd_link_l_target = rm -f $@; $(AR) rcsT$(KBUILD_ARFLAGS) $@ $(lib-y)
+else
+ cmd_link_l_target = rm -f $@; $(AR) rcs$(KBUILD_ARFLAGS) $@ $(lib-y)
+endif
$(lib-target): $(lib-y) FORCE
$(call if_changed,link_l_target)
targets += $(lib-target)
+
+dummy-object = $(obj)/.lib_exports.o
+ksyms-lds = $(dot-target).lds
+ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
+ref_prefix = EXTERN(_
+else
+ref_prefix = EXTERN(
+endif
+
+quiet_cmd_export_list = EXPORTS $@
+cmd_export_list = $(OBJDUMP) -h $< | \
+ sed -ne '/___ksymtab/{s/.*+/$(ref_prefix)/;s/ .*/)/;p}' >$(ksyms-lds);\
+ rm -f $(dummy-object);\
+ $(AR) rcs$(KBUILD_ARFLAGS) $(dummy-object);\
+ $(LD) $(ld_flags) -r -o $@ -T $(ksyms-lds) $(dummy-object);\
+ rm $(dummy-object) $(ksyms-lds)
+
+$(obj)/lib-ksyms.o: $(lib-target) FORCE
+ $(call if_changed,export_list)
endif
#
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index 53449a6..7c321a6 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -36,6 +36,7 @@
warning-2 += $(call cc-option, -Wlogical-op)
warning-2 += $(call cc-option, -Wmissing-field-initializers)
warning-2 += $(call cc-option, -Wsign-compare)
+warning-2 += $(call cc-option, -Wmaybe-uninitialized)
warning-3 := -Wbad-function-cast
warning-3 += -Wcast-qual
diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins
index 61f0e6d..060d2cb 100644
--- a/scripts/Makefile.gcc-plugins
+++ b/scripts/Makefile.gcc-plugins
@@ -6,6 +6,12 @@
gcc-plugin-$(CONFIG_GCC_PLUGIN_CYC_COMPLEXITY) += cyc_complexity_plugin.so
+ gcc-plugin-$(CONFIG_GCC_PLUGIN_LATENT_ENTROPY) += latent_entropy_plugin.so
+ gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_LATENT_ENTROPY) += -DLATENT_ENTROPY_PLUGIN
+ ifdef CONFIG_PAX_LATENT_ENTROPY
+ DISABLE_LATENT_ENTROPY_PLUGIN += -fplugin-arg-latent_entropy_plugin-disable
+ endif
+
ifdef CONFIG_GCC_PLUGIN_SANCOV
ifeq ($(CFLAGS_KCOV),)
# It is needed because of the gcc-plugin.sh and gcc version checks.
@@ -21,7 +27,8 @@
GCC_PLUGINS_CFLAGS := $(strip $(addprefix -fplugin=$(objtree)/scripts/gcc-plugins/, $(gcc-plugin-y)) $(gcc-plugin-cflags-y))
- export PLUGINCC GCC_PLUGINS_CFLAGS GCC_PLUGIN GCC_PLUGIN_SUBDIR SANCOV_PLUGIN
+ export PLUGINCC GCC_PLUGINS_CFLAGS GCC_PLUGIN GCC_PLUGIN_SUBDIR
+ export SANCOV_PLUGIN DISABLE_LATENT_ENTROPY_PLUGIN
ifneq ($(PLUGINCC),)
# SANCOV_PLUGIN can be only in CFLAGS_KCOV because avoid duplication.
diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
index 1366a94..16923ba 100644
--- a/scripts/Makefile.modpost
+++ b/scripts/Makefile.modpost
@@ -115,14 +115,18 @@
targets += $(modules:.ko=.mod.o)
-# Step 6), final link of the modules
+ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink)
+
+# Step 6), final link of the modules with optional arch pass after final link
quiet_cmd_ld_ko_o = LD [M] $@
- cmd_ld_ko_o = $(LD) -r $(LDFLAGS) \
- $(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \
- -o $@ $(filter-out FORCE,$^)
+ cmd_ld_ko_o = \
+ $(LD) -r $(LDFLAGS) \
+ $(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \
+ -o $@ $(filter-out FORCE,$^) ; \
+ $(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
$(modules): %.ko :%.o %.mod.o FORCE
- $(call if_changed,ld_ko_o)
+ +$(call if_changed,ld_ko_o)
targets += $(modules)
diff --git a/scripts/Makefile.ubsan b/scripts/Makefile.ubsan
index dd779c4..3b1b138 100644
--- a/scripts/Makefile.ubsan
+++ b/scripts/Makefile.ubsan
@@ -17,4 +17,8 @@
ifdef CONFIG_UBSAN_NULL
CFLAGS_UBSAN += $(call cc-option, -fsanitize=null)
endif
+
+ # -fsanitize=* options makes GCC less smart than usual and
+ # increase number of 'maybe-uninitialized false-positives
+ CFLAGS_UBSAN += $(call cc-option, -Wno-maybe-uninitialized)
endif
diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c
index 746ec1e..fff818b 100644
--- a/scripts/basic/fixdep.c
+++ b/scripts/basic/fixdep.c
@@ -82,8 +82,7 @@
* to date before even starting the recursive build, so it's too late
* at this point anyway.
*
- * The algorithm to grep for "CONFIG_..." is bit unusual, but should
- * be fast ;-) We don't even try to really parse the header files, but
+ * We don't even try to really parse the header files, but
* merely grep, i.e. if CONFIG_FOO is mentioned in a comment, it will
* be picked up as well. It's not a problem with respect to
* correctness, since that can only give too many dependencies, thus
@@ -115,11 +114,6 @@
#include <ctype.h>
#include <arpa/inet.h>
-#define INT_CONF ntohl(0x434f4e46)
-#define INT_ONFI ntohl(0x4f4e4649)
-#define INT_NFIG ntohl(0x4e464947)
-#define INT_FIG_ ntohl(0x4649475f)
-
int insert_extra_deps;
char *target;
char *depfile;
@@ -241,37 +235,22 @@ static void use_config(const char *m, int slen)
print_config(m, slen);
}
-static void parse_config_file(const char *map, size_t len)
+static void parse_config_file(const char *p)
{
- const int *end = (const int *) (map + len);
- /* start at +1, so that p can never be < map */
- const int *m = (const int *) map + 1;
- const char *p, *q;
+ const char *q, *r;
- for (; m < end; m++) {
- if (*m == INT_CONF) { p = (char *) m ; goto conf; }
- if (*m == INT_ONFI) { p = (char *) m-1; goto conf; }
- if (*m == INT_NFIG) { p = (char *) m-2; goto conf; }
- if (*m == INT_FIG_) { p = (char *) m-3; goto conf; }
- continue;
- conf:
- if (p > map + len - 7)
- continue;
- if (memcmp(p, "CONFIG_", 7))
- continue;
+ while ((p = strstr(p, "CONFIG_"))) {
p += 7;
- for (q = p; q < map + len; q++) {
- if (!(isalnum(*q) || *q == '_'))
- goto found;
- }
- continue;
-
- found:
- if (!memcmp(q - 7, "_MODULE", 7))
- q -= 7;
- if (q - p < 0)
- continue;
- use_config(p, q - p);
+ q = p;
+ while (*q && (isalnum(*q) || *q == '_'))
+ q++;
+ if (memcmp(q - 7, "_MODULE", 7) == 0)
+ r = q - 7;
+ else
+ r = q;
+ if (r > p)
+ use_config(p, r - p);
+ p = q;
}
}
@@ -291,7 +270,7 @@ static void do_config_file(const char *filename)
{
struct stat st;
int fd;
- void *map;
+ char *map;
fd = open(filename, O_RDONLY);
if (fd < 0) {
@@ -308,18 +287,23 @@ static void do_config_file(const char *filename)
close(fd);
return;
}
- map = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
- if ((long) map == -1) {
- perror("fixdep: mmap");
+ map = malloc(st.st_size + 1);
+ if (!map) {
+ perror("fixdep: malloc");
close(fd);
return;
}
-
- parse_config_file(map, st.st_size);
-
- munmap(map, st.st_size);
-
+ if (read(fd, map, st.st_size) != st.st_size) {
+ perror("fixdep: read");
+ close(fd);
+ return;
+ }
+ map[st.st_size] = '\0';
close(fd);
+
+ parse_config_file(map);
+
+ free(map);
}
/*
@@ -446,22 +430,8 @@ static void print_deps(void)
close(fd);
}
-static void traps(void)
-{
- static char test[] __attribute__((aligned(sizeof(int)))) = "CONF";
- int *p = (int *)test;
-
- if (*p != INT_CONF) {
- fprintf(stderr, "fixdep: sizeof(int) != 4 or wrong endianness? %#x\n",
- *p);
- exit(2);
- }
-}
-
int main(int argc, char *argv[])
{
- traps();
-
if (argc == 5 && !strcmp(argv[1], "-e")) {
insert_extra_deps = 1;
argv++;
diff --git a/scripts/bloat-o-meter b/scripts/bloat-o-meter
index 19f5adf..d9ff038 100755
--- a/scripts/bloat-o-meter
+++ b/scripts/bloat-o-meter
@@ -8,6 +8,9 @@
# of the GNU General Public License, incorporated herein by reference.
import sys, os, re
+from signal import signal, SIGPIPE, SIG_DFL
+
+signal(SIGPIPE, SIG_DFL)
if len(sys.argv) != 3:
sys.stderr.write("usage: %s file1 file2\n" % sys.argv[0])
diff --git a/scripts/coccicheck b/scripts/coccicheck
index c92c1528..ec487b8 100755
--- a/scripts/coccicheck
+++ b/scripts/coccicheck
@@ -1,7 +1,7 @@
#!/bin/bash
# Linux kernel coccicheck
#
-# Read Documentation/coccinelle.txt
+# Read Documentation/dev-tools/coccinelle.rst
#
# This script requires at least spatch
# version 1.0.0-rc11.
diff --git a/scripts/coccinelle/api/memdup_user.cocci b/scripts/coccinelle/api/memdup_user.cocci
index c606231..2a5aea8 100644
--- a/scripts/coccinelle/api/memdup_user.cocci
+++ b/scripts/coccinelle/api/memdup_user.cocci
@@ -15,11 +15,11 @@
virtual report
@depends on patch@
-expression from,to,size,flag;
+expression from,to,size;
identifier l1,l2;
@@
-- to = \(kmalloc\|kzalloc\)(size,flag);
+- to = \(kmalloc\|kzalloc\)(size,GFP_KERNEL);
+ to = memdup_user(from,size);
if (
- to==NULL
@@ -37,12 +37,12 @@
- }
@r depends on !patch@
-expression from,to,size,flag;
+expression from,to,size;
position p;
statement S1,S2;
@@
-* to = \(kmalloc@p\|kzalloc@p\)(size,flag);
+* to = \(kmalloc@p\|kzalloc@p\)(size,GFP_KERNEL);
if (to==NULL || ...) S1
if (copy_from_user(to, from, size) != 0)
S2
diff --git a/scripts/coccinelle/api/pm_runtime.cocci b/scripts/coccinelle/api/pm_runtime.cocci
index 89b98a2..d67ccf5 100644
--- a/scripts/coccinelle/api/pm_runtime.cocci
+++ b/scripts/coccinelle/api/pm_runtime.cocci
@@ -17,9 +17,10 @@
@runtime_bad_err_handle exists@
expression ret;
+position p;
@@
(
-ret = \(pm_runtime_idle\|
+ret@p = \(pm_runtime_idle\|
pm_runtime_suspend\|
pm_runtime_autosuspend\|
pm_runtime_resume\|
@@ -47,12 +48,13 @@
// For context mode
//----------------------------------------------------------
-@depends on runtime_bad_err_handle && context@
+@depends on context@
identifier pm_runtime_api;
expression ret;
+position runtime_bad_err_handle.p;
@@
(
-ret = pm_runtime_api(...);
+ret@p = pm_runtime_api(...);
...
* IS_ERR_VALUE(ret)
...
@@ -62,12 +64,13 @@
// For patch mode
//----------------------------------------------------------
-@depends on runtime_bad_err_handle && patch@
+@depends on patch@
identifier pm_runtime_api;
expression ret;
+position runtime_bad_err_handle.p;
@@
(
-ret = pm_runtime_api(...);
+ret@p = pm_runtime_api(...);
...
- IS_ERR_VALUE(ret)
+ ret < 0
@@ -78,13 +81,14 @@
// For org and report mode
//----------------------------------------------------------
-@r depends on runtime_bad_err_handle && (org || report) exists@
+@r depends on (org || report) exists@
position p1, p2;
identifier pm_runtime_api;
expression ret;
+position runtime_bad_err_handle.p;
@@
(
-ret = pm_runtime_api@p1(...);
+ret@p = pm_runtime_api@p1(...);
...
IS_ERR_VALUE@p2(ret)
...
diff --git a/scripts/coccinelle/misc/cond_no_effect.cocci b/scripts/coccinelle/misc/cond_no_effect.cocci
new file mode 100644
index 0000000..8467dbd
--- /dev/null
+++ b/scripts/coccinelle/misc/cond_no_effect.cocci
@@ -0,0 +1,64 @@
+///Find conditions where if and else branch are functionally
+// identical.
+//
+// There can be false positives in cases where the positional
+// information is used (as with lockdep) or where the identity
+// is a placeholder for not yet handled cases.
+// Unfortunately there also seems to be a tendency to use
+// the last if else/else as a "default behavior" - which some
+// might consider a legitimate coding pattern. From discussion
+// on kernelnewbies though it seems that this is not really an
+// accepted pattern and if at all it would need to be commented
+//
+// In the Linux kernel it does not seem to actually report
+// false positives except for those that were documented as
+// being intentional.
+// the two known cases are:
+// arch/sh/kernel/traps_64.c:read_opcode()
+// } else if ((pc & 1) == 0) {
+// /* SHcompact */
+// /* TODO : provide handling for this. We don't really support
+// user-mode SHcompact yet, and for a kernel fault, this would
+// have to come from a module built for SHcompact. */
+// return -EFAULT;
+// } else {
+// /* misaligned */
+// return -EFAULT;
+// }
+// fs/kernfs/file.c:kernfs_fop_open()
+// * Both paths of the branch look the same. They're supposed to
+// * look that way and give @of->mutex different static lockdep keys.
+// */
+// if (has_mmap)
+// mutex_init(&of->mutex);
+// else
+// mutex_init(&of->mutex);
+//
+// All other cases look like bugs or at least lack of documentation
+//
+// Confidence: Moderate
+// Copyright: (C) 2016 Nicholas Mc Guire, OSADL. GPLv2.
+// Comments:
+// Options: --no-includes --include-headers
+
+virtual org
+virtual report
+
+@cond@
+statement S1;
+position p;
+@@
+
+* if@p (...) S1 else S1
+
+@script:python depends on org@
+p << cond.p;
+@@
+
+cocci.print_main("WARNING: possible condition with no effect (if == else)",p)
+
+@script:python depends on report@
+p << cond.p;
+@@
+
+coccilib.report.print_report(p[0],"WARNING: possible condition with no effect (if == else)")
diff --git a/scripts/gcc-plugins/cyc_complexity_plugin.c b/scripts/gcc-plugins/cyc_complexity_plugin.c
index 34df974..8af7db0 100644
--- a/scripts/gcc-plugins/cyc_complexity_plugin.c
+++ b/scripts/gcc-plugins/cyc_complexity_plugin.c
@@ -20,7 +20,7 @@
#include "gcc-common.h"
-int plugin_is_GPL_compatible;
+__visible int plugin_is_GPL_compatible;
static struct plugin_info cyc_complexity_plugin_info = {
.version = "20160225",
@@ -49,7 +49,7 @@ static unsigned int cyc_complexity_execute(void)
#include "gcc-generate-gimple-pass.h"
-int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gcc_version *version)
+__visible int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gcc_version *version)
{
const char * const plugin_name = plugin_info->base_name;
struct register_pass_info cyc_complexity_pass_info;
diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h
index 172850b..950fd2e 100644
--- a/scripts/gcc-plugins/gcc-common.h
+++ b/scripts/gcc-plugins/gcc-common.h
@@ -130,6 +130,7 @@ extern void dump_gimple_stmt(pretty_printer *, gimple, int, int);
#endif
#define __unused __attribute__((__unused__))
+#define __visible __attribute__((visibility("default")))
#define DECL_NAME_POINTER(node) IDENTIFIER_POINTER(DECL_NAME(node))
#define DECL_NAME_LENGTH(node) IDENTIFIER_LENGTH(DECL_NAME(node))
diff --git a/scripts/gcc-plugins/latent_entropy_plugin.c b/scripts/gcc-plugins/latent_entropy_plugin.c
new file mode 100644
index 0000000..8160f1c
--- /dev/null
+++ b/scripts/gcc-plugins/latent_entropy_plugin.c
@@ -0,0 +1,639 @@
+/*
+ * Copyright 2012-2016 by the PaX Team <pageexec@freemail.hu>
+ * Copyright 2016 by Emese Revfy <re.emese@gmail.com>
+ * Licensed under the GPL v2
+ *
+ * Note: the choice of the license means that the compilation process is
+ * NOT 'eligible' as defined by gcc's library exception to the GPL v3,
+ * but for the kernel it doesn't matter since it doesn't link against
+ * any of the gcc libraries
+ *
+ * This gcc plugin helps generate a little bit of entropy from program state,
+ * used throughout the uptime of the kernel. Here is an instrumentation example:
+ *
+ * before:
+ * void __latent_entropy test(int argc, char *argv[])
+ * {
+ * if (argc <= 1)
+ * printf("%s: no command arguments :(\n", *argv);
+ * else
+ * printf("%s: %d command arguments!\n", *argv, args - 1);
+ * }
+ *
+ * after:
+ * void __latent_entropy test(int argc, char *argv[])
+ * {
+ * // latent_entropy_execute() 1.
+ * unsigned long local_entropy;
+ * // init_local_entropy() 1.
+ * void *local_entropy_frameaddr;
+ * // init_local_entropy() 3.
+ * unsigned long tmp_latent_entropy;
+ *
+ * // init_local_entropy() 2.
+ * local_entropy_frameaddr = __builtin_frame_address(0);
+ * local_entropy = (unsigned long) local_entropy_frameaddr;
+ *
+ * // init_local_entropy() 4.
+ * tmp_latent_entropy = latent_entropy;
+ * // init_local_entropy() 5.
+ * local_entropy ^= tmp_latent_entropy;
+ *
+ * // latent_entropy_execute() 3.
+ * if (argc <= 1) {
+ * // perturb_local_entropy()
+ * local_entropy += 4623067384293424948;
+ * printf("%s: no command arguments :(\n", *argv);
+ * // perturb_local_entropy()
+ * } else {
+ * local_entropy ^= 3896280633962944730;
+ * printf("%s: %d command arguments!\n", *argv, args - 1);
+ * }
+ *
+ * // latent_entropy_execute() 4.
+ * tmp_latent_entropy = rol(tmp_latent_entropy, local_entropy);
+ * latent_entropy = tmp_latent_entropy;
+ * }
+ *
+ * TODO:
+ * - add ipa pass to identify not explicitly marked candidate functions
+ * - mix in more program state (function arguments/return values,
+ * loop variables, etc)
+ * - more instrumentation control via attribute parameters
+ *
+ * BUGS:
+ * - none known
+ *
+ * Options:
+ * -fplugin-arg-latent_entropy_plugin-disable
+ *
+ * Attribute: __attribute__((latent_entropy))
+ * The latent_entropy gcc attribute can be only on functions and variables.
+ * If it is on a function then the plugin will instrument it. If the attribute
+ * is on a variable then the plugin will initialize it with a random value.
+ * The variable must be an integer, an integer array type or a structure
+ * with integer fields.
+ */
+
+#include "gcc-common.h"
+
+__visible int plugin_is_GPL_compatible;
+
+static GTY(()) tree latent_entropy_decl;
+
+static struct plugin_info latent_entropy_plugin_info = {
+ .version = "201606141920vanilla",
+ .help = "disable\tturn off latent entropy instrumentation\n",
+};
+
+static unsigned HOST_WIDE_INT seed;
+/*
+ * get_random_seed() (this is a GCC function) generates the seed.
+ * This is a simple random generator without any cryptographic security because
+ * the entropy doesn't come from here.
+ */
+static unsigned HOST_WIDE_INT get_random_const(void)
+{
+ unsigned int i;
+ unsigned HOST_WIDE_INT ret = 0;
+
+ for (i = 0; i < 8 * sizeof(ret); i++) {
+ ret = (ret << 1) | (seed & 1);
+ seed >>= 1;
+ if (ret & 1)
+ seed ^= 0xD800000000000000ULL;
+ }
+
+ return ret;
+}
+
+static tree tree_get_random_const(tree type)
+{
+ unsigned long long mask;
+
+ mask = 1ULL << (TREE_INT_CST_LOW(TYPE_SIZE(type)) - 1);
+ mask = 2 * (mask - 1) + 1;
+
+ if (TYPE_UNSIGNED(type))
+ return build_int_cstu(type, mask & get_random_const());
+ return build_int_cst(type, mask & get_random_const());
+}
+
+static tree handle_latent_entropy_attribute(tree *node, tree name,
+ tree args __unused,
+ int flags __unused,
+ bool *no_add_attrs)
+{
+ tree type;
+#if BUILDING_GCC_VERSION <= 4007
+ VEC(constructor_elt, gc) *vals;
+#else
+ vec<constructor_elt, va_gc> *vals;
+#endif
+
+ switch (TREE_CODE(*node)) {
+ default:
+ *no_add_attrs = true;
+ error("%qE attribute only applies to functions and variables",
+ name);
+ break;
+
+ case VAR_DECL:
+ if (DECL_INITIAL(*node)) {
+ *no_add_attrs = true;
+ error("variable %qD with %qE attribute must not be initialized",
+ *node, name);
+ break;
+ }
+
+ if (!TREE_STATIC(*node)) {
+ *no_add_attrs = true;
+ error("variable %qD with %qE attribute must not be local",
+ *node, name);
+ break;
+ }
+
+ type = TREE_TYPE(*node);
+ switch (TREE_CODE(type)) {
+ default:
+ *no_add_attrs = true;
+ error("variable %qD with %qE attribute must be an integer or a fixed length integer array type or a fixed sized structure with integer fields",
+ *node, name);
+ break;
+
+ case RECORD_TYPE: {
+ tree fld, lst = TYPE_FIELDS(type);
+ unsigned int nelt = 0;
+
+ for (fld = lst; fld; nelt++, fld = TREE_CHAIN(fld)) {
+ tree fieldtype;
+
+ fieldtype = TREE_TYPE(fld);
+ if (TREE_CODE(fieldtype) == INTEGER_TYPE)
+ continue;
+
+ *no_add_attrs = true;
+ error("structure variable %qD with %qE attribute has a non-integer field %qE",
+ *node, name, fld);
+ break;
+ }
+
+ if (fld)
+ break;
+
+#if BUILDING_GCC_VERSION <= 4007
+ vals = VEC_alloc(constructor_elt, gc, nelt);
+#else
+ vec_alloc(vals, nelt);
+#endif
+
+ for (fld = lst; fld; fld = TREE_CHAIN(fld)) {
+ tree random_const, fld_t = TREE_TYPE(fld);
+
+ random_const = tree_get_random_const(fld_t);
+ CONSTRUCTOR_APPEND_ELT(vals, fld, random_const);
+ }
+
+ /* Initialize the fields with random constants */
+ DECL_INITIAL(*node) = build_constructor(type, vals);
+ break;
+ }
+
+ /* Initialize the variable with a random constant */
+ case INTEGER_TYPE:
+ DECL_INITIAL(*node) = tree_get_random_const(type);
+ break;
+
+ case ARRAY_TYPE: {
+ tree elt_type, array_size, elt_size;
+ unsigned int i, nelt;
+ HOST_WIDE_INT array_size_int, elt_size_int;
+
+ elt_type = TREE_TYPE(type);
+ elt_size = TYPE_SIZE_UNIT(TREE_TYPE(type));
+ array_size = TYPE_SIZE_UNIT(type);
+
+ if (TREE_CODE(elt_type) != INTEGER_TYPE || !array_size
+ || TREE_CODE(array_size) != INTEGER_CST) {
+ *no_add_attrs = true;
+ error("array variable %qD with %qE attribute must be a fixed length integer array type",
+ *node, name);
+ break;
+ }
+
+ array_size_int = TREE_INT_CST_LOW(array_size);
+ elt_size_int = TREE_INT_CST_LOW(elt_size);
+ nelt = array_size_int / elt_size_int;
+
+#if BUILDING_GCC_VERSION <= 4007
+ vals = VEC_alloc(constructor_elt, gc, nelt);
+#else
+ vec_alloc(vals, nelt);
+#endif
+
+ for (i = 0; i < nelt; i++) {
+ tree cst = size_int(i);
+ tree rand_cst = tree_get_random_const(elt_type);
+
+ CONSTRUCTOR_APPEND_ELT(vals, cst, rand_cst);
+ }
+
+ /*
+ * Initialize the elements of the array with random
+ * constants
+ */
+ DECL_INITIAL(*node) = build_constructor(type, vals);
+ break;
+ }
+ }
+ break;
+
+ case FUNCTION_DECL:
+ break;
+ }
+
+ return NULL_TREE;
+}
+
+static struct attribute_spec latent_entropy_attr = {
+ .name = "latent_entropy",
+ .min_length = 0,
+ .max_length = 0,
+ .decl_required = true,
+ .type_required = false,
+ .function_type_required = false,
+ .handler = handle_latent_entropy_attribute,
+#if BUILDING_GCC_VERSION >= 4007
+ .affects_type_identity = false
+#endif
+};
+
+static void register_attributes(void *event_data __unused, void *data __unused)
+{
+ register_attribute(&latent_entropy_attr);
+}
+
+static bool latent_entropy_gate(void)
+{
+ tree list;
+
+ /* don't bother with noreturn functions for now */
+ if (TREE_THIS_VOLATILE(current_function_decl))
+ return false;
+
+ /* gcc-4.5 doesn't discover some trivial noreturn functions */
+ if (EDGE_COUNT(EXIT_BLOCK_PTR_FOR_FN(cfun)->preds) == 0)
+ return false;
+
+ list = DECL_ATTRIBUTES(current_function_decl);
+ return lookup_attribute("latent_entropy", list) != NULL_TREE;
+}
+
+static tree create_var(tree type, const char *name)
+{
+ tree var;
+
+ var = create_tmp_var(type, name);
+ add_referenced_var(var);
+ mark_sym_for_renaming(var);
+ return var;
+}
+
+/*
+ * Set up the next operation and its constant operand to use in the latent
+ * entropy PRNG. When RHS is specified, the request is for perturbing the
+ * local latent entropy variable, otherwise it is for perturbing the global
+ * latent entropy variable where the two operands are already given by the
+ * local and global latent entropy variables themselves.
+ *
+ * The operation is one of add/xor/rol when instrumenting the local entropy
+ * variable and one of add/xor when perturbing the global entropy variable.
+ * Rotation is not used for the latter case because it would transmit less
+ * entropy to the global variable than the other two operations.
+ */
+static enum tree_code get_op(tree *rhs)
+{
+ static enum tree_code op;
+ unsigned HOST_WIDE_INT random_const;
+
+ random_const = get_random_const();
+
+ switch (op) {
+ case BIT_XOR_EXPR:
+ op = PLUS_EXPR;
+ break;
+
+ case PLUS_EXPR:
+ if (rhs) {
+ op = LROTATE_EXPR;
+ /*
+ * This code limits the value of random_const to
+ * the size of a wide int for the rotation
+ */
+ random_const &= HOST_BITS_PER_WIDE_INT - 1;
+ break;
+ }
+
+ case LROTATE_EXPR:
+ default:
+ op = BIT_XOR_EXPR;
+ break;
+ }
+ if (rhs)
+ *rhs = build_int_cstu(long_unsigned_type_node, random_const);
+ return op;
+}
+
+static gimple create_assign(enum tree_code code, tree lhs, tree op1,
+ tree op2)
+{
+ return gimple_build_assign_with_ops(code, lhs, op1, op2);
+}
+
+static void perturb_local_entropy(basic_block bb, tree local_entropy)
+{
+ gimple_stmt_iterator gsi;
+ gimple assign;
+ tree rhs;
+ enum tree_code op;
+
+ op = get_op(&rhs);
+ assign = create_assign(op, local_entropy, local_entropy, rhs);
+ gsi = gsi_after_labels(bb);
+ gsi_insert_before(&gsi, assign, GSI_NEW_STMT);
+ update_stmt(assign);
+}
+
+static void __perturb_latent_entropy(gimple_stmt_iterator *gsi,
+ tree local_entropy)
+{
+ gimple assign;
+ tree temp;
+ enum tree_code op;
+
+ /* 1. create temporary copy of latent_entropy */
+ temp = create_var(long_unsigned_type_node, "temp_latent_entropy");
+
+ /* 2. read... */
+ add_referenced_var(latent_entropy_decl);
+ mark_sym_for_renaming(latent_entropy_decl);
+ assign = gimple_build_assign(temp, latent_entropy_decl);
+ gsi_insert_before(gsi, assign, GSI_NEW_STMT);
+ update_stmt(assign);
+
+ /* 3. ...modify... */
+ op = get_op(NULL);
+ assign = create_assign(op, temp, temp, local_entropy);
+ gsi_insert_after(gsi, assign, GSI_NEW_STMT);
+ update_stmt(assign);
+
+ /* 4. ...write latent_entropy */
+ assign = gimple_build_assign(latent_entropy_decl, temp);
+ gsi_insert_after(gsi, assign, GSI_NEW_STMT);
+ update_stmt(assign);
+}
+
+static bool handle_tail_calls(basic_block bb, tree local_entropy)
+{
+ gimple_stmt_iterator gsi;
+
+ for (gsi = gsi_start_bb(bb); !gsi_end_p(gsi); gsi_next(&gsi)) {
+ gcall *call;
+ gimple stmt = gsi_stmt(gsi);
+
+ if (!is_gimple_call(stmt))
+ continue;
+
+ call = as_a_gcall(stmt);
+ if (!gimple_call_tail_p(call))
+ continue;
+
+ __perturb_latent_entropy(&gsi, local_entropy);
+ return true;
+ }
+
+ return false;
+}
+
+static void perturb_latent_entropy(tree local_entropy)
+{
+ edge_iterator ei;
+ edge e, last_bb_e;
+ basic_block last_bb;
+
+ gcc_assert(single_pred_p(EXIT_BLOCK_PTR_FOR_FN(cfun)));
+ last_bb_e = single_pred_edge(EXIT_BLOCK_PTR_FOR_FN(cfun));
+
+ FOR_EACH_EDGE(e, ei, last_bb_e->src->preds) {
+ if (ENTRY_BLOCK_PTR_FOR_FN(cfun) == e->src)
+ continue;
+ if (EXIT_BLOCK_PTR_FOR_FN(cfun) == e->src)
+ continue;
+
+ handle_tail_calls(e->src, local_entropy);
+ }
+
+ last_bb = single_pred(EXIT_BLOCK_PTR_FOR_FN(cfun));
+ if (!handle_tail_calls(last_bb, local_entropy)) {
+ gimple_stmt_iterator gsi = gsi_last_bb(last_bb);
+
+ __perturb_latent_entropy(&gsi, local_entropy);
+ }
+}
+
+static void init_local_entropy(basic_block bb, tree local_entropy)
+{
+ gimple assign, call;
+ tree frame_addr, rand_const, tmp, fndecl, udi_frame_addr;
+ enum tree_code op;
+ unsigned HOST_WIDE_INT rand_cst;
+ gimple_stmt_iterator gsi = gsi_after_labels(bb);
+
+ /* 1. create local_entropy_frameaddr */
+ frame_addr = create_var(ptr_type_node, "local_entropy_frameaddr");
+
+ /* 2. local_entropy_frameaddr = __builtin_frame_address() */
+ fndecl = builtin_decl_implicit(BUILT_IN_FRAME_ADDRESS);
+ call = gimple_build_call(fndecl, 1, integer_zero_node);
+ gimple_call_set_lhs(call, frame_addr);
+ gsi_insert_before(&gsi, call, GSI_NEW_STMT);
+ update_stmt(call);
+
+ udi_frame_addr = fold_convert(long_unsigned_type_node, frame_addr);
+ assign = gimple_build_assign(local_entropy, udi_frame_addr);
+ gsi_insert_after(&gsi, assign, GSI_NEW_STMT);
+ update_stmt(assign);
+
+ /* 3. create temporary copy of latent_entropy */
+ tmp = create_var(long_unsigned_type_node, "temp_latent_entropy");
+
+ /* 4. read the global entropy variable into local entropy */
+ add_referenced_var(latent_entropy_decl);
+ mark_sym_for_renaming(latent_entropy_decl);
+ assign = gimple_build_assign(tmp, latent_entropy_decl);
+ gsi_insert_after(&gsi, assign, GSI_NEW_STMT);
+ update_stmt(assign);
+
+ /* 5. mix local_entropy_frameaddr into local entropy */
+ assign = create_assign(BIT_XOR_EXPR, local_entropy, local_entropy, tmp);
+ gsi_insert_after(&gsi, assign, GSI_NEW_STMT);
+ update_stmt(assign);
+
+ rand_cst = get_random_const();
+ rand_const = build_int_cstu(long_unsigned_type_node, rand_cst);
+ op = get_op(NULL);
+ assign = create_assign(op, local_entropy, local_entropy, rand_const);
+ gsi_insert_after(&gsi, assign, GSI_NEW_STMT);
+ update_stmt(assign);
+}
+
+static bool create_latent_entropy_decl(void)
+{
+ varpool_node_ptr node;
+
+ if (latent_entropy_decl != NULL_TREE)
+ return true;
+
+ FOR_EACH_VARIABLE(node) {
+ tree name, var = NODE_DECL(node);
+
+ if (DECL_NAME_LENGTH(var) < sizeof("latent_entropy") - 1)
+ continue;
+
+ name = DECL_NAME(var);
+ if (strcmp(IDENTIFIER_POINTER(name), "latent_entropy"))
+ continue;
+
+ latent_entropy_decl = var;
+ break;
+ }
+
+ return latent_entropy_decl != NULL_TREE;
+}
+
+static unsigned int latent_entropy_execute(void)
+{
+ basic_block bb;
+ tree local_entropy;
+
+ if (!create_latent_entropy_decl())
+ return 0;
+
+ /* prepare for step 2 below */
+ gcc_assert(single_succ_p(ENTRY_BLOCK_PTR_FOR_FN(cfun)));
+ bb = single_succ(ENTRY_BLOCK_PTR_FOR_FN(cfun));
+ if (!single_pred_p(bb)) {
+ split_edge(single_succ_edge(ENTRY_BLOCK_PTR_FOR_FN(cfun)));
+ gcc_assert(single_succ_p(ENTRY_BLOCK_PTR_FOR_FN(cfun)));
+ bb = single_succ(ENTRY_BLOCK_PTR_FOR_FN(cfun));
+ }
+
+ /* 1. create the local entropy variable */
+ local_entropy = create_var(long_unsigned_type_node, "local_entropy");
+
+ /* 2. initialize the local entropy variable */
+ init_local_entropy(bb, local_entropy);
+
+ bb = bb->next_bb;
+
+ /*
+ * 3. instrument each BB with an operation on the
+ * local entropy variable
+ */
+ while (bb != EXIT_BLOCK_PTR_FOR_FN(cfun)) {
+ perturb_local_entropy(bb, local_entropy);
+ bb = bb->next_bb;
+ };
+
+ /* 4. mix local entropy into the global entropy variable */
+ perturb_latent_entropy(local_entropy);
+ return 0;
+}
+
+static void latent_entropy_start_unit(void *gcc_data __unused,
+ void *user_data __unused)
+{
+ tree type, id;
+ int quals;
+
+ seed = get_random_seed(false);
+
+ if (in_lto_p)
+ return;
+
+ /* extern volatile unsigned long latent_entropy */
+ quals = TYPE_QUALS(long_unsigned_type_node) | TYPE_QUAL_VOLATILE;
+ type = build_qualified_type(long_unsigned_type_node, quals);
+ id = get_identifier("latent_entropy");
+ latent_entropy_decl = build_decl(UNKNOWN_LOCATION, VAR_DECL, id, type);
+
+ TREE_STATIC(latent_entropy_decl) = 1;
+ TREE_PUBLIC(latent_entropy_decl) = 1;
+ TREE_USED(latent_entropy_decl) = 1;
+ DECL_PRESERVE_P(latent_entropy_decl) = 1;
+ TREE_THIS_VOLATILE(latent_entropy_decl) = 1;
+ DECL_EXTERNAL(latent_entropy_decl) = 1;
+ DECL_ARTIFICIAL(latent_entropy_decl) = 1;
+ lang_hooks.decls.pushdecl(latent_entropy_decl);
+}
+
+#define PASS_NAME latent_entropy
+#define PROPERTIES_REQUIRED PROP_gimple_leh | PROP_cfg
+#define TODO_FLAGS_FINISH TODO_verify_ssa | TODO_verify_stmts | TODO_dump_func \
+ | TODO_update_ssa
+#include "gcc-generate-gimple-pass.h"
+
+__visible int plugin_init(struct plugin_name_args *plugin_info,
+ struct plugin_gcc_version *version)
+{
+ bool enabled = true;
+ const char * const plugin_name = plugin_info->base_name;
+ const int argc = plugin_info->argc;
+ const struct plugin_argument * const argv = plugin_info->argv;
+ int i;
+
+ struct register_pass_info latent_entropy_pass_info;
+
+ latent_entropy_pass_info.pass = make_latent_entropy_pass();
+ latent_entropy_pass_info.reference_pass_name = "optimized";
+ latent_entropy_pass_info.ref_pass_instance_number = 1;
+ latent_entropy_pass_info.pos_op = PASS_POS_INSERT_BEFORE;
+ static const struct ggc_root_tab gt_ggc_r_gt_latent_entropy[] = {
+ {
+ .base = &latent_entropy_decl,
+ .nelt = 1,
+ .stride = sizeof(latent_entropy_decl),
+ .cb = >_ggc_mx_tree_node,
+ .pchw = >_pch_nx_tree_node
+ },
+ LAST_GGC_ROOT_TAB
+ };
+
+ if (!plugin_default_version_check(version, &gcc_version)) {
+ error(G_("incompatible gcc/plugin versions"));
+ return 1;
+ }
+
+ for (i = 0; i < argc; ++i) {
+ if (!(strcmp(argv[i].key, "disable"))) {
+ enabled = false;
+ continue;
+ }
+ error(G_("unkown option '-fplugin-arg-%s-%s'"), plugin_name, argv[i].key);
+ }
+
+ register_callback(plugin_name, PLUGIN_INFO, NULL,
+ &latent_entropy_plugin_info);
+ if (enabled) {
+ register_callback(plugin_name, PLUGIN_START_UNIT,
+ &latent_entropy_start_unit, NULL);
+ register_callback(plugin_name, PLUGIN_REGISTER_GGC_ROOTS,
+ NULL, (void *)>_ggc_r_gt_latent_entropy);
+ register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL,
+ &latent_entropy_pass_info);
+ }
+ register_callback(plugin_name, PLUGIN_ATTRIBUTES, register_attributes,
+ NULL);
+
+ return 0;
+}
diff --git a/scripts/gcc-plugins/sancov_plugin.c b/scripts/gcc-plugins/sancov_plugin.c
index aedd611..7ea0b3f 100644
--- a/scripts/gcc-plugins/sancov_plugin.c
+++ b/scripts/gcc-plugins/sancov_plugin.c
@@ -21,7 +21,7 @@
#include "gcc-common.h"
-int plugin_is_GPL_compatible;
+__visible int plugin_is_GPL_compatible;
tree sancov_fndecl;
@@ -86,7 +86,7 @@ static void sancov_start_unit(void __unused *gcc_data, void __unused *user_data)
#endif
}
-int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gcc_version *version)
+__visible int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gcc_version *version)
{
int i;
struct register_pass_info sancov_plugin_pass_info;
diff --git a/scripts/gen_initramfs_list.sh b/scripts/gen_initramfs_list.sh
index 17fa901..0055b07 100755
--- a/scripts/gen_initramfs_list.sh
+++ b/scripts/gen_initramfs_list.sh
@@ -97,7 +97,10 @@
}
list_parse() {
- [ ! -L "$1" ] && echo "$1 \\" || :
+ if [ -L "$1" ]; then
+ return
+ fi
+ echo "$1" | sed 's/:/\\:/g; s/$/ \\/'
}
# for each file print a line in following format
diff --git a/scripts/genksyms/lex.l b/scripts/genksyms/lex.l
index e583565..5235aa5 100644
--- a/scripts/genksyms/lex.l
+++ b/scripts/genksyms/lex.l
@@ -289,6 +289,23 @@
}
break;
+ case ST_TYPEOF_1:
+ if (token == IDENT)
+ {
+ if (is_reserved_word(yytext, yyleng)
+ || find_symbol(yytext, SYM_TYPEDEF, 1))
+ {
+ yyless(0);
+ unput('(');
+ lexstate = ST_NORMAL;
+ token = TYPEOF_KEYW;
+ break;
+ }
+ _APP("(", 1);
+ }
+ lexstate = ST_TYPEOF;
+ /* FALLTHRU */
+
case ST_TYPEOF:
switch (token)
{
@@ -313,24 +330,6 @@
}
break;
- case ST_TYPEOF_1:
- if (token == IDENT)
- {
- if (is_reserved_word(yytext, yyleng)
- || find_symbol(yytext, SYM_TYPEDEF, 1))
- {
- yyless(0);
- unput('(');
- lexstate = ST_NORMAL;
- token = TYPEOF_KEYW;
- break;
- }
- _APP("(", 1);
- }
- APP;
- lexstate = ST_TYPEOF;
- goto repeat;
-
case ST_BRACKET:
APP;
switch (token)
diff --git a/scripts/genksyms/lex.lex.c_shipped b/scripts/genksyms/lex.lex.c_shipped
index f82740a..985c554 100644
--- a/scripts/genksyms/lex.lex.c_shipped
+++ b/scripts/genksyms/lex.lex.c_shipped
@@ -2098,6 +2098,23 @@
}
break;
+ case ST_TYPEOF_1:
+ if (token == IDENT)
+ {
+ if (is_reserved_word(yytext, yyleng)
+ || find_symbol(yytext, SYM_TYPEDEF, 1))
+ {
+ yyless(0);
+ unput('(');
+ lexstate = ST_NORMAL;
+ token = TYPEOF_KEYW;
+ break;
+ }
+ _APP("(", 1);
+ }
+ lexstate = ST_TYPEOF;
+ /* FALLTHRU */
+
case ST_TYPEOF:
switch (token)
{
@@ -2122,24 +2139,6 @@
}
break;
- case ST_TYPEOF_1:
- if (token == IDENT)
- {
- if (is_reserved_word(yytext, yyleng)
- || find_symbol(yytext, SYM_TYPEDEF, 1))
- {
- yyless(0);
- unput('(');
- lexstate = ST_NORMAL;
- token = TYPEOF_KEYW;
- break;
- }
- _APP("(", 1);
- }
- APP;
- lexstate = ST_TYPEOF;
- goto repeat;
-
case ST_BRACKET:
APP;
switch (token)
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 4f727eb..f742c65 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -37,12 +37,40 @@
fi
}
+# Thin archive build here makes a final archive with
+# symbol table and indexes from vmlinux objects, which can be
+# used as input to linker.
+#
+# Traditional incremental style of link does not require this step
+#
+# built-in.o output file
+#
+archive_builtin()
+{
+ if [ -n "${CONFIG_THIN_ARCHIVES}" ]; then
+ info AR built-in.o
+ rm -f built-in.o;
+ ${AR} rcsT${KBUILD_ARFLAGS} built-in.o \
+ ${KBUILD_VMLINUX_INIT} \
+ ${KBUILD_VMLINUX_MAIN}
+ fi
+}
+
# Link of vmlinux.o used for section mismatch analysis
# ${1} output file
modpost_link()
{
- ${LD} ${LDFLAGS} -r -o ${1} ${KBUILD_VMLINUX_INIT} \
- --start-group ${KBUILD_VMLINUX_MAIN} --end-group
+ local objects
+
+ if [ -n "${CONFIG_THIN_ARCHIVES}" ]; then
+ objects="--whole-archive built-in.o"
+ else
+ objects="${KBUILD_VMLINUX_INIT} \
+ --start-group \
+ ${KBUILD_VMLINUX_MAIN} \
+ --end-group"
+ fi
+ ${LD} ${LDFLAGS} -r -o ${1} ${objects}
}
# Link of vmlinux
@@ -51,18 +79,36 @@
vmlinux_link()
{
local lds="${objtree}/${KBUILD_LDS}"
+ local objects
if [ "${SRCARCH}" != "um" ]; then
- ${LD} ${LDFLAGS} ${LDFLAGS_vmlinux} -o ${2} \
- -T ${lds} ${KBUILD_VMLINUX_INIT} \
- --start-group ${KBUILD_VMLINUX_MAIN} --end-group ${1}
+ if [ -n "${CONFIG_THIN_ARCHIVES}" ]; then
+ objects="--whole-archive built-in.o ${1}"
+ else
+ objects="${KBUILD_VMLINUX_INIT} \
+ --start-group \
+ ${KBUILD_VMLINUX_MAIN} \
+ --end-group \
+ ${1}"
+ fi
+
+ ${LD} ${LDFLAGS} ${LDFLAGS_vmlinux} -o ${2} \
+ -T ${lds} ${objects}
else
- ${CC} ${CFLAGS_vmlinux} -o ${2} \
- -Wl,-T,${lds} ${KBUILD_VMLINUX_INIT} \
- -Wl,--start-group \
- ${KBUILD_VMLINUX_MAIN} \
- -Wl,--end-group \
- -lutil -lrt -lpthread ${1}
+ if [ -n "${CONFIG_THIN_ARCHIVES}" ]; then
+ objects="-Wl,--whole-archive built-in.o ${1}"
+ else
+ objects="${KBUILD_VMLINUX_INIT} \
+ -Wl,--start-group \
+ ${KBUILD_VMLINUX_MAIN} \
+ -Wl,--end-group \
+ ${1}"
+ fi
+
+ ${CC} ${CFLAGS_vmlinux} -o ${2} \
+ -Wl,-T,${lds} \
+ ${objects} \
+ -lutil -lrt -lpthread
rm -f linux
fi
}
@@ -119,6 +165,7 @@
rm -f .tmp_kallsyms*
rm -f .tmp_version
rm -f .tmp_vmlinux*
+ rm -f built-in.o
rm -f System.map
rm -f vmlinux
rm -f vmlinux.o
@@ -162,6 +209,8 @@
. "./${KCONFIG_CONFIG}"
esac
+archive_builtin
+
#link vmlinux.o
info LD vmlinux.o
modpost_link vmlinux.o
diff --git a/security/keys/Kconfig b/security/keys/Kconfig
index f826e87..d942c7c 100644
--- a/security/keys/Kconfig
+++ b/security/keys/Kconfig
@@ -41,7 +41,7 @@
bool "Large payload keys"
depends on KEYS
depends on TMPFS
- select CRYPTO
+ depends on (CRYPTO_ANSI_CPRNG = y || CRYPTO_DRBG = y)
select CRYPTO_AES
select CRYPTO_ECB
select CRYPTO_RNG
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index c0b3030..835c1ab 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -9,6 +9,7 @@
* 2 of the Licence, or (at your option) any later version.
*/
+#define pr_fmt(fmt) "big_key: "fmt
#include <linux/init.h>
#include <linux/seq_file.h>
#include <linux/file.h>
@@ -341,44 +342,48 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen)
*/
static int __init big_key_init(void)
{
- return register_key_type(&key_type_big_key);
-}
+ struct crypto_skcipher *cipher;
+ struct crypto_rng *rng;
+ int ret;
-/*
- * Initialize big_key crypto and RNG algorithms
- */
-static int __init big_key_crypto_init(void)
-{
- int ret = -EINVAL;
-
- /* init RNG */
- big_key_rng = crypto_alloc_rng(big_key_rng_name, 0, 0);
- if (IS_ERR(big_key_rng)) {
- big_key_rng = NULL;
- return -EFAULT;
+ rng = crypto_alloc_rng(big_key_rng_name, 0, 0);
+ if (IS_ERR(rng)) {
+ pr_err("Can't alloc rng: %ld\n", PTR_ERR(rng));
+ return PTR_ERR(rng);
}
+ big_key_rng = rng;
+
/* seed RNG */
- ret = crypto_rng_reset(big_key_rng, NULL, crypto_rng_seedsize(big_key_rng));
- if (ret)
- goto error;
+ ret = crypto_rng_reset(rng, NULL, crypto_rng_seedsize(rng));
+ if (ret) {
+ pr_err("Can't reset rng: %d\n", ret);
+ goto error_rng;
+ }
/* init block cipher */
- big_key_skcipher = crypto_alloc_skcipher(big_key_alg_name,
- 0, CRYPTO_ALG_ASYNC);
- if (IS_ERR(big_key_skcipher)) {
- big_key_skcipher = NULL;
- ret = -EFAULT;
- goto error;
+ cipher = crypto_alloc_skcipher(big_key_alg_name, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(cipher)) {
+ ret = PTR_ERR(cipher);
+ pr_err("Can't alloc crypto: %d\n", ret);
+ goto error_rng;
+ }
+
+ big_key_skcipher = cipher;
+
+ ret = register_key_type(&key_type_big_key);
+ if (ret < 0) {
+ pr_err("Can't register type: %d\n", ret);
+ goto error_cipher;
}
return 0;
-error:
+error_cipher:
+ crypto_free_skcipher(big_key_skcipher);
+error_rng:
crypto_free_rng(big_key_rng);
- big_key_rng = NULL;
return ret;
}
-device_initcall(big_key_init);
-late_initcall(big_key_crypto_init);
+late_initcall(big_key_init);
diff --git a/security/keys/proc.c b/security/keys/proc.c
index f0611a6..b9f531c 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -181,7 +181,7 @@ static int proc_keys_show(struct seq_file *m, void *v)
struct timespec now;
unsigned long timo;
key_ref_t key_ref, skey_ref;
- char xbuf[12];
+ char xbuf[16];
int rc;
struct keyring_search_context ctx = {
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 0850579..09fd610 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3557,7 +3557,7 @@ static int selinux_file_mprotect(struct vm_area_struct *vma,
} else if (!vma->vm_file &&
((vma->vm_start <= vma->vm_mm->start_stack &&
vma->vm_end >= vma->vm_mm->start_stack) ||
- vma_is_stack_for_task(vma, current))) {
+ vma_is_stack_for_current(vma))) {
rc = current_has_perm(current, PROCESS__EXECSTACK);
} else if (vma->vm_file && vma->anon_vma) {
/*
diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c
index ade7c6c..682b73a 100644
--- a/security/tomoyo/domain.c
+++ b/security/tomoyo/domain.c
@@ -881,7 +881,7 @@ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos,
* the execve().
*/
if (get_user_pages_remote(current, bprm->mm, pos, 1,
- 0, 1, &page, NULL) <= 0)
+ FOLL_FORCE, &page, NULL) <= 0)
return false;
#else
page = bprm->page[pos / PAGE_SIZE];
diff --git a/sound/core/info.c b/sound/core/info.c
index 895362a..8ab72e0 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -325,10 +325,15 @@ static ssize_t snd_info_text_entry_write(struct file *file,
size_t next;
int err = 0;
+ if (!entry->c.text.write)
+ return -EIO;
pos = *offset;
if (!valid_pos(pos, count))
return -EIO;
next = pos + count;
+ /* don't handle too large text inputs */
+ if (next > 16 * 1024)
+ return -EIO;
mutex_lock(&entry->access);
buf = data->wbuffer;
if (!buf) {
@@ -366,7 +371,9 @@ static int snd_info_seq_show(struct seq_file *seq, void *p)
struct snd_info_private_data *data = seq->private;
struct snd_info_entry *entry = data->entry;
- if (entry->c.text.read) {
+ if (!entry->c.text.read) {
+ return -EIO;
+ } else {
data->rbuffer->buffer = (char *)seq; /* XXX hack! */
entry->c.text.read(entry, data->rbuffer);
}
diff --git a/sound/core/seq/seq_compat.c b/sound/core/seq/seq_compat.c
index fce5697..8c35072 100644
--- a/sound/core/seq/seq_compat.c
+++ b/sound/core/seq/seq_compat.c
@@ -58,7 +58,7 @@ static int snd_seq_call_port_info_ioctl(struct snd_seq_client *client, unsigned
goto error;
data->kernel = NULL;
- err = snd_seq_kernel_client_ctl(client->number, cmd, &data);
+ err = snd_seq_kernel_client_ctl(client->number, cmd, data);
if (err < 0)
goto error;
diff --git a/sound/core/seq/seq_timer.c b/sound/core/seq/seq_timer.c
index dcc10281..37d9cfb 100644
--- a/sound/core/seq/seq_timer.c
+++ b/sound/core/seq/seq_timer.c
@@ -448,8 +448,8 @@ snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr)
ktime_get_ts64(&tm);
tm = timespec64_sub(tm, tmr->last_update);
- cur_time.tv_nsec = tm.tv_nsec;
- cur_time.tv_sec = tm.tv_sec;
+ cur_time.tv_nsec += tm.tv_nsec;
+ cur_time.tv_sec += tm.tv_sec;
snd_seq_sanity_real_time(&cur_time);
}
spin_unlock_irqrestore(&tmr->lock, flags);
diff --git a/sound/pci/asihpi/hpioctl.c b/sound/pci/asihpi/hpioctl.c
index d17937b..7e3aa50 100644
--- a/sound/pci/asihpi/hpioctl.c
+++ b/sound/pci/asihpi/hpioctl.c
@@ -111,7 +111,7 @@ long asihpi_hpi_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
return -EINVAL;
hm = kmalloc(sizeof(*hm), GFP_KERNEL);
- hr = kmalloc(sizeof(*hr), GFP_KERNEL);
+ hr = kzalloc(sizeof(*hr), GFP_KERNEL);
if (!hm || !hr) {
err = -ENOMEM;
goto out;
diff --git a/sound/pci/hda/dell_wmi_helper.c b/sound/pci/hda/dell_wmi_helper.c
index 9c22f95..19d41da 100644
--- a/sound/pci/hda/dell_wmi_helper.c
+++ b/sound/pci/hda/dell_wmi_helper.c
@@ -49,7 +49,7 @@ static void alc_fixup_dell_wmi(struct hda_codec *codec,
removefunc = true;
if (dell_led_set_func(DELL_LED_MICMUTE, false) >= 0) {
dell_led_value = 0;
- if (spec->gen.num_adc_nids > 1)
+ if (spec->gen.num_adc_nids > 1 && !spec->gen.dyn_adc_switch)
codec_dbg(codec, "Skipping micmute LED control due to several ADCs");
else {
dell_old_cap_hook = spec->gen.cap_sync_hook;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index c3469f7..c64d986 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -341,8 +341,7 @@ enum {
/* quirks for Nvidia */
#define AZX_DCAPS_PRESET_NVIDIA \
- (AZX_DCAPS_NO_MSI | /*AZX_DCAPS_ALIGN_BUFSIZE |*/ \
- AZX_DCAPS_NO_64BIT | AZX_DCAPS_CORBRP_SELF_CLEAR |\
+ (AZX_DCAPS_NO_MSI | AZX_DCAPS_CORBRP_SELF_CLEAR |\
AZX_DCAPS_SNOOP_TYPE(NVIDIA))
#define AZX_DCAPS_PRESET_CTHDA \
@@ -1716,6 +1715,10 @@ static int azx_first_init(struct azx *chip)
}
}
+ /* NVidia hardware normally only supports up to 40 bits of DMA */
+ if (chip->pci->vendor == PCI_VENDOR_ID_NVIDIA)
+ dma_bits = 40;
+
/* disable 64bit DMA address on some devices */
if (chip->driver_caps & AZX_DCAPS_NO_64BIT) {
dev_dbg(card->dev, "Disabling 64bit DMA\n");
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index b58e8c7..2f909dd 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5811,8 +5811,6 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
#define ALC295_STANDARD_PINS \
{0x12, 0xb7a60130}, \
{0x14, 0x90170110}, \
- {0x17, 0x21014020}, \
- {0x18, 0x21a19030}, \
{0x21, 0x04211020}
#define ALC298_STANDARD_PINS \
@@ -5859,11 +5857,19 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
{0x1b, 0x02011020},
{0x21, 0x0221101f}),
SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ {0x14, 0x90170110},
+ {0x1b, 0x01011020},
+ {0x21, 0x0221101f}),
+ SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
{0x14, 0x90170130},
{0x1b, 0x01014020},
{0x21, 0x0221103f}),
SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
{0x14, 0x90170130},
+ {0x1b, 0x01011020},
+ {0x21, 0x0221103f}),
+ SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ {0x14, 0x90170130},
{0x1b, 0x02011020},
{0x21, 0x0221103f}),
SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
@@ -6039,7 +6045,13 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
ALC292_STANDARD_PINS,
{0x13, 0x90a60140}),
SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
- ALC295_STANDARD_PINS),
+ ALC295_STANDARD_PINS,
+ {0x17, 0x21014020},
+ {0x18, 0x21a19030}),
+ SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+ ALC295_STANDARD_PINS,
+ {0x17, 0x21014040},
+ {0x18, 0x21a19050}),
SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
ALC298_STANDARD_PINS,
{0x17, 0x90170110}),
@@ -6613,6 +6625,7 @@ enum {
ALC891_FIXUP_HEADSET_MODE,
ALC891_FIXUP_DELL_MIC_NO_PRESENCE,
ALC662_FIXUP_ACER_VERITON,
+ ALC892_FIXUP_ASROCK_MOBO,
};
static const struct hda_fixup alc662_fixups[] = {
@@ -6889,6 +6902,16 @@ static const struct hda_fixup alc662_fixups[] = {
{ }
}
},
+ [ALC892_FIXUP_ASROCK_MOBO] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x15, 0x40f000f0 }, /* disabled */
+ { 0x16, 0x40f000f0 }, /* disabled */
+ { 0x18, 0x01014011 }, /* LO */
+ { 0x1a, 0x01014012 }, /* LO */
+ { }
+ }
+ },
};
static const struct snd_pci_quirk alc662_fixup_tbl[] = {
@@ -6926,6 +6949,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = {
SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD),
SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo Ideapad Y550P", ALC662_FIXUP_IDEAPAD),
SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Ideapad Y550", ALC662_FIXUP_IDEAPAD),
+ SND_PCI_QUIRK(0x1849, 0x5892, "ASRock B150M", ALC892_FIXUP_ASROCK_MOBO),
SND_PCI_QUIRK(0x19da, 0xa130, "Zotac Z68", ALC662_FIXUP_ZOTAC_Z68),
SND_PCI_QUIRK(0x1b0a, 0x01b8, "ACER Veriton", ALC662_FIXUP_ACER_VERITON),
SND_PCI_QUIRK(0x1b35, 0x2206, "CZC P10T", ALC662_FIXUP_CZC_P10T),
diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c
index f0955fd..6a23302 100644
--- a/sound/pci/hda/thinkpad_helper.c
+++ b/sound/pci/hda/thinkpad_helper.c
@@ -62,7 +62,7 @@ static void hda_fixup_thinkpad_acpi(struct hda_codec *codec,
removefunc = false;
}
if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0) {
- if (spec->num_adc_nids > 1)
+ if (spec->num_adc_nids > 1 && !spec->dyn_adc_switch)
codec_dbg(codec,
"Skipping micmute LED control due to several ADCs");
else {
diff --git a/sound/soc/codecs/cs4270.c b/sound/soc/codecs/cs4270.c
index 18baea2..84f8674 100644
--- a/sound/soc/codecs/cs4270.c
+++ b/sound/soc/codecs/cs4270.c
@@ -148,11 +148,11 @@ SND_SOC_DAPM_OUTPUT("AOUTR"),
};
static const struct snd_soc_dapm_route cs4270_dapm_routes[] = {
- { "Capture", NULL, "AINA" },
- { "Capture", NULL, "AINB" },
+ { "Capture", NULL, "AINL" },
+ { "Capture", NULL, "AINR" },
- { "AOUTA", NULL, "Playback" },
- { "AOUTB", NULL, "Playback" },
+ { "AOUTL", NULL, "Playback" },
+ { "AOUTR", NULL, "Playback" },
};
/**
diff --git a/sound/soc/codecs/da7219.c b/sound/soc/codecs/da7219.c
index 1152aa5..cf37936 100644
--- a/sound/soc/codecs/da7219.c
+++ b/sound/soc/codecs/da7219.c
@@ -880,7 +880,8 @@ static const struct snd_soc_dapm_widget da7219_dapm_widgets[] = {
SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
/* DAI */
- SND_SOC_DAPM_AIF_OUT("DAIOUT", "Capture", 0, SND_SOC_NOPM, 0, 0),
+ SND_SOC_DAPM_AIF_OUT("DAIOUT", "Capture", 0, DA7219_DAI_TDM_CTRL,
+ DA7219_DAI_OE_SHIFT, DA7219_NO_INVERT),
SND_SOC_DAPM_AIF_IN("DAIIN", "Playback", 0, SND_SOC_NOPM, 0, 0),
/* Output Muxes */
diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c
index b904492..90b5948 100644
--- a/sound/soc/codecs/hdmi-codec.c
+++ b/sound/soc/codecs/hdmi-codec.c
@@ -364,7 +364,12 @@ static int hdmi_of_xlate_dai_name(struct snd_soc_component *component,
struct of_phandle_args *args,
const char **dai_name)
{
- int id = args->args[0];
+ int id;
+
+ if (args->args_count)
+ id = args->args[0];
+ else
+ id = 0;
if (id < ARRAY_SIZE(hdmi_dai_name)) {
*dai_name = hdmi_dai_name[id];
diff --git a/sound/soc/codecs/rt298.c b/sound/soc/codecs/rt298.c
index 5555864..2db8179 100644
--- a/sound/soc/codecs/rt298.c
+++ b/sound/soc/codecs/rt298.c
@@ -249,6 +249,11 @@ static int rt298_jack_detect(struct rt298_priv *rt298, bool *hp, bool *mic)
snd_soc_dapm_force_enable_pin(dapm, "LDO1");
snd_soc_dapm_sync(dapm);
+ regmap_update_bits(rt298->regmap,
+ RT298_POWER_CTRL1, 0x1001, 0);
+ regmap_update_bits(rt298->regmap,
+ RT298_POWER_CTRL2, 0x4, 0x4);
+
regmap_write(rt298->regmap, RT298_SET_MIC1, 0x24);
msleep(50);
diff --git a/sound/soc/codecs/rt5663.c b/sound/soc/codecs/rt5663.c
index 01a18d8..00ff278 100644
--- a/sound/soc/codecs/rt5663.c
+++ b/sound/soc/codecs/rt5663.c
@@ -1547,11 +1547,11 @@ static int rt5663_jack_detect(struct snd_soc_codec *codec, int jack_insert)
msleep(sleep_time[i]);
val = snd_soc_read(codec, RT5663_EM_JACK_TYPE_2) &
0x0003;
+ dev_dbg(codec->dev, "%s: MX-00e7 val=%x sleep %d\n",
+ __func__, val, sleep_time[i]);
i++;
if (val == 0x1 || val == 0x2 || val == 0x3)
break;
- dev_dbg(codec->dev, "%s: MX-00e7 val=%x sleep %d\n",
- __func__, val, sleep_time[i]);
}
dev_dbg(codec->dev, "%s val = %d\n", __func__, val);
switch (val) {
diff --git a/sound/soc/codecs/sti-sas.c b/sound/soc/codecs/sti-sas.c
index 7b31ee9..d6e00c7 100644
--- a/sound/soc/codecs/sti-sas.c
+++ b/sound/soc/codecs/sti-sas.c
@@ -424,7 +424,7 @@ static const struct snd_soc_dai_ops stih407_dac_ops = {
static const struct regmap_config stih407_sas_regmap = {
.reg_bits = 32,
.val_bits = 32,
-
+ .fast_io = true,
.max_register = STIH407_AUDIO_DAC_CTRL,
.reg_defaults = stih407_sas_reg_defaults,
.num_reg_defaults = ARRAY_SIZE(stih407_sas_reg_defaults),
diff --git a/sound/soc/codecs/tas571x.c b/sound/soc/codecs/tas571x.c
index df5e5cb..810369f 100644
--- a/sound/soc/codecs/tas571x.c
+++ b/sound/soc/codecs/tas571x.c
@@ -341,20 +341,9 @@ static int tas571x_set_bias_level(struct snd_soc_codec *codec,
return ret;
}
}
-
- gpiod_set_value(priv->pdn_gpio, 0);
- usleep_range(5000, 6000);
-
- regcache_cache_only(priv->regmap, false);
- ret = regcache_sync(priv->regmap);
- if (ret)
- return ret;
}
break;
case SND_SOC_BIAS_OFF:
- regcache_cache_only(priv->regmap, true);
- gpiod_set_value(priv->pdn_gpio, 1);
-
if (!IS_ERR(priv->mclk))
clk_disable_unprepare(priv->mclk);
break;
@@ -401,16 +390,6 @@ static const struct snd_kcontrol_new tas5711_controls[] = {
TAS571X_SOFT_MUTE_REG,
TAS571X_SOFT_MUTE_CH1_SHIFT, TAS571X_SOFT_MUTE_CH2_SHIFT,
1, 1),
-
- SOC_DOUBLE_R_RANGE("CH1 Mixer Volume",
- TAS5717_CH1_LEFT_CH_MIX_REG,
- TAS5717_CH1_RIGHT_CH_MIX_REG,
- 16, 0, 0x80, 0),
-
- SOC_DOUBLE_R_RANGE("CH2 Mixer Volume",
- TAS5717_CH2_LEFT_CH_MIX_REG,
- TAS5717_CH2_RIGHT_CH_MIX_REG,
- 16, 0, 0x80, 0),
};
static const struct regmap_range tas571x_readonly_regs_range[] = {
@@ -488,6 +467,16 @@ static const struct snd_kcontrol_new tas5717_controls[] = {
TAS571X_SOFT_MUTE_CH1_SHIFT, TAS571X_SOFT_MUTE_CH2_SHIFT,
1, 1),
+ SOC_DOUBLE_R_RANGE("CH1 Mixer Volume",
+ TAS5717_CH1_LEFT_CH_MIX_REG,
+ TAS5717_CH1_RIGHT_CH_MIX_REG,
+ 16, 0, 0x80, 0),
+
+ SOC_DOUBLE_R_RANGE("CH2 Mixer Volume",
+ TAS5717_CH2_LEFT_CH_MIX_REG,
+ TAS5717_CH2_RIGHT_CH_MIX_REG,
+ 16, 0, 0x80, 0),
+
/*
* The biquads are named according to the register names.
* Please note that TI's TAS57xx Graphical Development Environment
@@ -747,13 +736,14 @@ static int tas571x_i2c_probe(struct i2c_client *client,
/* pulse the active low reset line for ~100us */
usleep_range(100, 200);
gpiod_set_value(priv->reset_gpio, 0);
- usleep_range(12000, 20000);
+ usleep_range(13500, 20000);
}
ret = regmap_write(priv->regmap, TAS571X_OSC_TRIM_REG, 0);
if (ret)
return ret;
+ usleep_range(50000, 60000);
memcpy(&priv->codec_driver, &tas571x_codec, sizeof(priv->codec_driver));
priv->codec_driver.component_driver.controls = priv->chip->controls;
@@ -770,9 +760,6 @@ static int tas571x_i2c_probe(struct i2c_client *client,
return ret;
}
- regcache_cache_only(priv->regmap, true);
- gpiod_set_value(priv->pdn_gpio, 1);
-
return snd_soc_register_codec(&client->dev, &priv->codec_driver,
&tas571x_dai, 1);
}
diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig
index 26eb5a0..fd5d1e0 100644
--- a/sound/soc/intel/Kconfig
+++ b/sound/soc/intel/Kconfig
@@ -47,6 +47,7 @@
config SND_SOC_INTEL_HASWELL
tristate
+ select SND_SOC_INTEL_SST_FIRMWARE
config SND_SOC_INTEL_BAYTRAIL
tristate
@@ -56,7 +57,6 @@
depends on X86_INTEL_LPSS && I2C && I2C_DESIGNWARE_PLATFORM
depends on DW_DMAC_CORE
select SND_SOC_INTEL_SST
- select SND_SOC_INTEL_SST_FIRMWARE
select SND_SOC_INTEL_HASWELL
select SND_SOC_RT5640
help
@@ -138,7 +138,6 @@
I2C_DESIGNWARE_PLATFORM
depends on DW_DMAC_CORE
select SND_SOC_INTEL_SST
- select SND_SOC_INTEL_SST_FIRMWARE
select SND_SOC_INTEL_HASWELL
select SND_SOC_RT286
help
diff --git a/sound/soc/intel/atom/sst/sst_acpi.c b/sound/soc/intel/atom/sst/sst_acpi.c
index ba5c0d7..0a88537 100644
--- a/sound/soc/intel/atom/sst/sst_acpi.c
+++ b/sound/soc/intel/atom/sst/sst_acpi.c
@@ -416,6 +416,7 @@ static const struct dmi_system_id cht_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "Surface 3"),
},
},
+ { }
};
diff --git a/sound/soc/intel/boards/bxt_da7219_max98357a.c b/sound/soc/intel/boards/bxt_da7219_max98357a.c
index 6532b8f..865a21e 100644
--- a/sound/soc/intel/boards/bxt_da7219_max98357a.c
+++ b/sound/soc/intel/boards/bxt_da7219_max98357a.c
@@ -130,8 +130,8 @@ static int broxton_da7219_codec_init(struct snd_soc_pcm_runtime *rtd)
*/
ret = snd_soc_card_jack_new(rtd->card, "Headset Jack",
SND_JACK_HEADSET | SND_JACK_BTN_0 | SND_JACK_BTN_1 |
- SND_JACK_BTN_2 | SND_JACK_BTN_3, &broxton_headset,
- NULL, 0);
+ SND_JACK_BTN_2 | SND_JACK_BTN_3 | SND_JACK_LINEOUT,
+ &broxton_headset, NULL, 0);
if (ret) {
dev_err(rtd->dev, "Headset Jack creation failed: %d\n", ret);
return ret;
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index 2989c16..06fa5e8 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -674,7 +674,7 @@ static int skl_probe(struct pci_dev *pci,
if (skl->nhlt == NULL) {
err = -ENODEV;
- goto out_free;
+ goto out_display_power_off;
}
skl_nhlt_update_topology_bin(skl);
@@ -746,6 +746,9 @@ static int skl_probe(struct pci_dev *pci,
skl_machine_device_unregister(skl);
out_nhlt_free:
skl_nhlt_free(skl->nhlt);
+out_display_power_off:
+ if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI))
+ snd_hdac_display_power(bus, false);
out_free:
skl->init_failed = 1;
skl_free(ebus);
@@ -785,8 +788,7 @@ static void skl_remove(struct pci_dev *pci)
release_firmware(skl->tplg);
- if (pci_dev_run_wake(pci))
- pm_runtime_get_noresume(&pci->dev);
+ pm_runtime_get_noresume(&pci->dev);
/* codec removal, invoke bus_device_remove */
snd_hdac_ext_bus_device_remove(ebus);
diff --git a/sound/soc/pxa/Kconfig b/sound/soc/pxa/Kconfig
index f2bf866..823b5a2 100644
--- a/sound/soc/pxa/Kconfig
+++ b/sound/soc/pxa/Kconfig
@@ -208,7 +208,7 @@
config SND_MMP_SOC_BROWNSTONE
tristate "SoC Audio support for Marvell Brownstone"
- depends on SND_MMP_SOC && MACH_BROWNSTONE
+ depends on SND_MMP_SOC && MACH_BROWNSTONE && I2C
select SND_MMP_SOC_SSPA
select MFD_WM8994
select SND_SOC_WM8994
diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c
index 3cde9fb..eff3f9a 100644
--- a/sound/soc/qcom/lpass-cpu.c
+++ b/sound/soc/qcom/lpass-cpu.c
@@ -586,3 +586,6 @@ int asoc_qcom_lpass_cpu_platform_remove(struct platform_device *pdev)
return 0;
}
EXPORT_SYMBOL_GPL(asoc_qcom_lpass_cpu_platform_remove);
+
+MODULE_DESCRIPTION("QTi LPASS CPU Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c
index e2ff538..b392e51 100644
--- a/sound/soc/qcom/lpass-platform.c
+++ b/sound/soc/qcom/lpass-platform.c
@@ -61,7 +61,41 @@ static int lpass_platform_pcmops_open(struct snd_pcm_substream *substream)
{
struct snd_pcm_runtime *runtime = substream->runtime;
struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
- int ret;
+ struct snd_soc_dai *cpu_dai = soc_runtime->cpu_dai;
+ struct lpass_data *drvdata =
+ snd_soc_platform_get_drvdata(soc_runtime->platform);
+ struct lpass_variant *v = drvdata->variant;
+ int ret, dma_ch, dir = substream->stream;
+ struct lpass_pcm_data *data;
+
+ data = devm_kzalloc(soc_runtime->dev, sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ data->i2s_port = cpu_dai->driver->id;
+ runtime->private_data = data;
+
+ dma_ch = 0;
+ if (v->alloc_dma_channel)
+ dma_ch = v->alloc_dma_channel(drvdata, dir);
+ if (dma_ch < 0)
+ return dma_ch;
+
+ drvdata->substream[dma_ch] = substream;
+
+ ret = regmap_write(drvdata->lpaif_map,
+ LPAIF_DMACTL_REG(v, dma_ch, dir), 0);
+ if (ret) {
+ dev_err(soc_runtime->dev,
+ "%s() error writing to rdmactl reg: %d\n",
+ __func__, ret);
+ return ret;
+ }
+
+ if (dir == SNDRV_PCM_STREAM_PLAYBACK)
+ data->rdma_ch = dma_ch;
+ else
+ data->wrdma_ch = dma_ch;
snd_soc_set_runtime_hwparams(substream, &lpass_platform_pcm_hardware);
@@ -80,13 +114,40 @@ static int lpass_platform_pcmops_open(struct snd_pcm_substream *substream)
return 0;
}
+static int lpass_platform_pcmops_close(struct snd_pcm_substream *substream)
+{
+ struct snd_pcm_runtime *runtime = substream->runtime;
+ struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
+ struct lpass_data *drvdata =
+ snd_soc_platform_get_drvdata(soc_runtime->platform);
+ struct lpass_variant *v = drvdata->variant;
+ struct lpass_pcm_data *data;
+ int dma_ch, dir = substream->stream;
+
+ data = runtime->private_data;
+ v = drvdata->variant;
+
+ if (dir == SNDRV_PCM_STREAM_PLAYBACK)
+ dma_ch = data->rdma_ch;
+ else
+ dma_ch = data->wrdma_ch;
+
+ drvdata->substream[dma_ch] = NULL;
+
+ if (v->free_dma_channel)
+ v->free_dma_channel(drvdata, dma_ch);
+
+ return 0;
+}
+
static int lpass_platform_pcmops_hw_params(struct snd_pcm_substream *substream,
struct snd_pcm_hw_params *params)
{
struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
struct lpass_data *drvdata =
snd_soc_platform_get_drvdata(soc_runtime->platform);
- struct lpass_pcm_data *pcm_data = drvdata->private_data;
+ struct snd_pcm_runtime *rt = substream->runtime;
+ struct lpass_pcm_data *pcm_data = rt->private_data;
struct lpass_variant *v = drvdata->variant;
snd_pcm_format_t format = params_format(params);
unsigned int channels = params_channels(params);
@@ -179,7 +240,8 @@ static int lpass_platform_pcmops_hw_free(struct snd_pcm_substream *substream)
struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
struct lpass_data *drvdata =
snd_soc_platform_get_drvdata(soc_runtime->platform);
- struct lpass_pcm_data *pcm_data = drvdata->private_data;
+ struct snd_pcm_runtime *rt = substream->runtime;
+ struct lpass_pcm_data *pcm_data = rt->private_data;
struct lpass_variant *v = drvdata->variant;
unsigned int reg;
int ret;
@@ -203,7 +265,8 @@ static int lpass_platform_pcmops_prepare(struct snd_pcm_substream *substream)
struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
struct lpass_data *drvdata =
snd_soc_platform_get_drvdata(soc_runtime->platform);
- struct lpass_pcm_data *pcm_data = drvdata->private_data;
+ struct snd_pcm_runtime *rt = substream->runtime;
+ struct lpass_pcm_data *pcm_data = rt->private_data;
struct lpass_variant *v = drvdata->variant;
int ret, ch, dir = substream->stream;
@@ -257,7 +320,8 @@ static int lpass_platform_pcmops_trigger(struct snd_pcm_substream *substream,
struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
struct lpass_data *drvdata =
snd_soc_platform_get_drvdata(soc_runtime->platform);
- struct lpass_pcm_data *pcm_data = drvdata->private_data;
+ struct snd_pcm_runtime *rt = substream->runtime;
+ struct lpass_pcm_data *pcm_data = rt->private_data;
struct lpass_variant *v = drvdata->variant;
int ret, ch, dir = substream->stream;
@@ -333,7 +397,8 @@ static snd_pcm_uframes_t lpass_platform_pcmops_pointer(
struct snd_soc_pcm_runtime *soc_runtime = substream->private_data;
struct lpass_data *drvdata =
snd_soc_platform_get_drvdata(soc_runtime->platform);
- struct lpass_pcm_data *pcm_data = drvdata->private_data;
+ struct snd_pcm_runtime *rt = substream->runtime;
+ struct lpass_pcm_data *pcm_data = rt->private_data;
struct lpass_variant *v = drvdata->variant;
unsigned int base_addr, curr_addr;
int ret, ch, dir = substream->stream;
@@ -374,6 +439,7 @@ static int lpass_platform_pcmops_mmap(struct snd_pcm_substream *substream,
static const struct snd_pcm_ops lpass_platform_pcm_ops = {
.open = lpass_platform_pcmops_open,
+ .close = lpass_platform_pcmops_close,
.ioctl = snd_pcm_lib_ioctl,
.hw_params = lpass_platform_pcmops_hw_params,
.hw_free = lpass_platform_pcmops_hw_free,
@@ -470,117 +536,45 @@ static int lpass_platform_pcm_new(struct snd_soc_pcm_runtime *soc_runtime)
{
struct snd_pcm *pcm = soc_runtime->pcm;
struct snd_pcm_substream *psubstream, *csubstream;
- struct snd_soc_dai *cpu_dai = soc_runtime->cpu_dai;
- struct lpass_data *drvdata =
- snd_soc_platform_get_drvdata(soc_runtime->platform);
- struct lpass_variant *v = drvdata->variant;
int ret = -EINVAL;
- struct lpass_pcm_data *data;
size_t size = lpass_platform_pcm_hardware.buffer_bytes_max;
- data = devm_kzalloc(soc_runtime->dev, sizeof(*data), GFP_KERNEL);
- if (!data)
- return -ENOMEM;
-
- data->i2s_port = cpu_dai->driver->id;
- drvdata->private_data = data;
-
psubstream = pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream;
if (psubstream) {
- if (v->alloc_dma_channel)
- data->rdma_ch = v->alloc_dma_channel(drvdata,
- SNDRV_PCM_STREAM_PLAYBACK);
-
- if (data->rdma_ch < 0)
- return data->rdma_ch;
-
- drvdata->substream[data->rdma_ch] = psubstream;
-
ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV,
soc_runtime->platform->dev,
size, &psubstream->dma_buffer);
- if (ret)
- goto playback_alloc_err;
-
- ret = regmap_write(drvdata->lpaif_map,
- LPAIF_RDMACTL_REG(v, data->rdma_ch), 0);
if (ret) {
- dev_err(soc_runtime->dev,
- "%s() error writing to rdmactl reg: %d\n",
- __func__, ret);
- goto capture_alloc_err;
+ dev_err(soc_runtime->dev, "Cannot allocate buffer(s)\n");
+ return ret;
}
}
csubstream = pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream;
if (csubstream) {
- if (v->alloc_dma_channel)
- data->wrdma_ch = v->alloc_dma_channel(drvdata,
- SNDRV_PCM_STREAM_CAPTURE);
-
- if (data->wrdma_ch < 0) {
- ret = data->wrdma_ch;
- goto capture_alloc_err;
- }
-
- drvdata->substream[data->wrdma_ch] = csubstream;
-
ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV,
soc_runtime->platform->dev,
size, &csubstream->dma_buffer);
- if (ret)
- goto capture_alloc_err;
-
- ret = regmap_write(drvdata->lpaif_map,
- LPAIF_WRDMACTL_REG(v, data->wrdma_ch), 0);
if (ret) {
- dev_err(soc_runtime->dev,
- "%s() error writing to wrdmactl reg: %d\n",
- __func__, ret);
- goto capture_reg_err;
+ dev_err(soc_runtime->dev, "Cannot allocate buffer(s)\n");
+ if (psubstream)
+ snd_dma_free_pages(&psubstream->dma_buffer);
+ return ret;
}
+
}
return 0;
-
-capture_reg_err:
- if (csubstream)
- snd_dma_free_pages(&csubstream->dma_buffer);
-
-capture_alloc_err:
- if (psubstream)
- snd_dma_free_pages(&psubstream->dma_buffer);
-
- playback_alloc_err:
- dev_err(soc_runtime->dev, "Cannot allocate buffer(s)\n");
-
- return ret;
}
static void lpass_platform_pcm_free(struct snd_pcm *pcm)
{
- struct snd_soc_pcm_runtime *rt;
- struct lpass_data *drvdata;
- struct lpass_pcm_data *data;
- struct lpass_variant *v;
struct snd_pcm_substream *substream;
- int ch, i;
+ int i;
for (i = 0; i < ARRAY_SIZE(pcm->streams); i++) {
substream = pcm->streams[i].substream;
if (substream) {
- rt = substream->private_data;
- drvdata = snd_soc_platform_get_drvdata(rt->platform);
- data = drvdata->private_data;
-
- ch = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
- ? data->rdma_ch
- : data->wrdma_ch;
- v = drvdata->variant;
- drvdata->substream[ch] = NULL;
- if (v->free_dma_channel)
- v->free_dma_channel(drvdata, ch);
-
snd_dma_free_pages(&substream->dma_buffer);
substream->dma_buffer.area = NULL;
substream->dma_buffer.addr = 0;
diff --git a/sound/soc/qcom/lpass.h b/sound/soc/qcom/lpass.h
index 35b3cea..924971b 100644
--- a/sound/soc/qcom/lpass.h
+++ b/sound/soc/qcom/lpass.h
@@ -59,7 +59,6 @@ struct lpass_data {
struct clk *pcnoc_mport_clk;
struct clk *pcnoc_sway_clk;
- void *private_data;
};
/* Vairant data per each SOC */
diff --git a/sound/soc/samsung/ac97.c b/sound/soc/samsung/ac97.c
index 97d6700..cbc0023 100644
--- a/sound/soc/samsung/ac97.c
+++ b/sound/soc/samsung/ac97.c
@@ -383,11 +383,6 @@ static int s3c_ac97_probe(struct platform_device *pdev)
goto err4;
}
- ret = devm_snd_soc_register_component(&pdev->dev, &s3c_ac97_component,
- s3c_ac97_dai, ARRAY_SIZE(s3c_ac97_dai));
- if (ret)
- goto err5;
-
ret = samsung_asoc_dma_platform_register(&pdev->dev,
ac97_pdata->dma_filter,
NULL, NULL);
@@ -396,6 +391,11 @@ static int s3c_ac97_probe(struct platform_device *pdev)
goto err5;
}
+ ret = devm_snd_soc_register_component(&pdev->dev, &s3c_ac97_component,
+ s3c_ac97_dai, ARRAY_SIZE(s3c_ac97_dai));
+ if (ret)
+ goto err5;
+
return 0;
err5:
free_irq(irq_res->start, NULL);
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index 7e32cf4..7825bff 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -1237,14 +1237,14 @@ static int samsung_i2s_probe(struct platform_device *pdev)
dev_err(&pdev->dev, "Unable to get drvdata\n");
return -EFAULT;
}
- ret = devm_snd_soc_register_component(&sec_dai->pdev->dev,
- &samsung_i2s_component,
- &sec_dai->i2s_dai_drv, 1);
+ ret = samsung_asoc_dma_platform_register(&pdev->dev,
+ sec_dai->filter, "tx-sec", NULL);
if (ret != 0)
return ret;
- return samsung_asoc_dma_platform_register(&pdev->dev,
- sec_dai->filter, "tx-sec", NULL);
+ return devm_snd_soc_register_component(&sec_dai->pdev->dev,
+ &samsung_i2s_component,
+ &sec_dai->i2s_dai_drv, 1);
}
pri_dai = i2s_alloc_dai(pdev, false);
@@ -1314,6 +1314,11 @@ static int samsung_i2s_probe(struct platform_device *pdev)
if (quirks & QUIRK_PRI_6CHAN)
pri_dai->i2s_dai_drv.playback.channels_max = 6;
+ ret = samsung_asoc_dma_platform_register(&pdev->dev, pri_dai->filter,
+ NULL, NULL);
+ if (ret < 0)
+ goto err_disable_clk;
+
if (quirks & QUIRK_SEC_DAI) {
sec_dai = i2s_alloc_dai(pdev, true);
if (!sec_dai) {
@@ -1353,10 +1358,6 @@ static int samsung_i2s_probe(struct platform_device *pdev)
if (ret < 0)
goto err_free_dai;
- ret = samsung_asoc_dma_platform_register(&pdev->dev, pri_dai->filter,
- NULL, NULL);
- if (ret < 0)
- goto err_free_dai;
pm_runtime_enable(&pdev->dev);
diff --git a/sound/soc/samsung/pcm.c b/sound/soc/samsung/pcm.c
index 43e367a..c484985 100644
--- a/sound/soc/samsung/pcm.c
+++ b/sound/soc/samsung/pcm.c
@@ -565,15 +565,6 @@ static int s3c_pcm_dev_probe(struct platform_device *pdev)
pcm->dma_capture = &s3c_pcm_stereo_in[pdev->id];
pcm->dma_playback = &s3c_pcm_stereo_out[pdev->id];
- pm_runtime_enable(&pdev->dev);
-
- ret = devm_snd_soc_register_component(&pdev->dev, &s3c_pcm_component,
- &s3c_pcm_dai[pdev->id], 1);
- if (ret != 0) {
- dev_err(&pdev->dev, "failed to get register DAI: %d\n", ret);
- goto err5;
- }
-
ret = samsung_asoc_dma_platform_register(&pdev->dev, filter,
NULL, NULL);
if (ret) {
@@ -581,8 +572,18 @@ static int s3c_pcm_dev_probe(struct platform_device *pdev)
goto err5;
}
- return 0;
+ pm_runtime_enable(&pdev->dev);
+ ret = devm_snd_soc_register_component(&pdev->dev, &s3c_pcm_component,
+ &s3c_pcm_dai[pdev->id], 1);
+ if (ret != 0) {
+ dev_err(&pdev->dev, "failed to get register DAI: %d\n", ret);
+ goto err6;
+ }
+
+ return 0;
+err6:
+ pm_runtime_disable(&pdev->dev);
err5:
clk_disable_unprepare(pcm->pclk);
err4:
diff --git a/sound/soc/samsung/s3c2412-i2s.c b/sound/soc/samsung/s3c2412-i2s.c
index 3e89fbc..0a47182 100644
--- a/sound/soc/samsung/s3c2412-i2s.c
+++ b/sound/soc/samsung/s3c2412-i2s.c
@@ -168,19 +168,19 @@ static int s3c2412_iis_dev_probe(struct platform_device *pdev)
s3c2412_i2s_pcm_stereo_in.addr = res->start + S3C2412_IISRXD;
s3c2412_i2s_pcm_stereo_in.filter_data = pdata->dma_capture;
- ret = s3c_i2sv2_register_component(&pdev->dev, -1,
- &s3c2412_i2s_component,
- &s3c2412_i2s_dai);
- if (ret) {
- pr_err("failed to register the dai\n");
- return ret;
- }
-
ret = samsung_asoc_dma_platform_register(&pdev->dev,
pdata->dma_filter,
NULL, NULL);
- if (ret)
+ if (ret) {
pr_err("failed to register the DMA: %d\n", ret);
+ return ret;
+ }
+
+ ret = s3c_i2sv2_register_component(&pdev->dev, -1,
+ &s3c2412_i2s_component,
+ &s3c2412_i2s_dai);
+ if (ret)
+ pr_err("failed to register the dai\n");
return ret;
}
diff --git a/sound/soc/samsung/s3c24xx-i2s.c b/sound/soc/samsung/s3c24xx-i2s.c
index c78a936..9052f6a 100644
--- a/sound/soc/samsung/s3c24xx-i2s.c
+++ b/sound/soc/samsung/s3c24xx-i2s.c
@@ -474,18 +474,18 @@ static int s3c24xx_iis_dev_probe(struct platform_device *pdev)
s3c24xx_i2s_pcm_stereo_in.addr = res->start + S3C2410_IISFIFO;
s3c24xx_i2s_pcm_stereo_in.filter_data = pdata->dma_capture;
- ret = devm_snd_soc_register_component(&pdev->dev,
- &s3c24xx_i2s_component, &s3c24xx_i2s_dai, 1);
- if (ret) {
- pr_err("failed to register the dai\n");
- return ret;
- }
-
ret = samsung_asoc_dma_platform_register(&pdev->dev,
pdata->dma_filter,
NULL, NULL);
- if (ret)
+ if (ret) {
pr_err("failed to register the dma: %d\n", ret);
+ return ret;
+ }
+
+ ret = devm_snd_soc_register_component(&pdev->dev,
+ &s3c24xx_i2s_component, &s3c24xx_i2s_dai, 1);
+ if (ret)
+ pr_err("failed to register the dai\n");
return ret;
}
diff --git a/sound/soc/samsung/spdif.c b/sound/soc/samsung/spdif.c
index 26c1fbe..779504f 100644
--- a/sound/soc/samsung/spdif.c
+++ b/sound/soc/samsung/spdif.c
@@ -416,15 +416,6 @@ static int spdif_probe(struct platform_device *pdev)
goto err3;
}
- dev_set_drvdata(&pdev->dev, spdif);
-
- ret = devm_snd_soc_register_component(&pdev->dev,
- &samsung_spdif_component, &samsung_spdif_dai, 1);
- if (ret != 0) {
- dev_err(&pdev->dev, "fail to register dai\n");
- goto err4;
- }
-
spdif_stereo_out.addr_width = 2;
spdif_stereo_out.addr = mem_res->start + DATA_OUTBUF;
filter = NULL;
@@ -432,7 +423,6 @@ static int spdif_probe(struct platform_device *pdev)
spdif_stereo_out.filter_data = spdif_pdata->dma_playback;
filter = spdif_pdata->dma_filter;
}
-
spdif->dma_playback = &spdif_stereo_out;
ret = samsung_asoc_dma_platform_register(&pdev->dev, filter,
@@ -442,6 +432,15 @@ static int spdif_probe(struct platform_device *pdev)
goto err4;
}
+ dev_set_drvdata(&pdev->dev, spdif);
+
+ ret = devm_snd_soc_register_component(&pdev->dev,
+ &samsung_spdif_component, &samsung_spdif_dai, 1);
+ if (ret != 0) {
+ dev_err(&pdev->dev, "fail to register dai\n");
+ goto err4;
+ }
+
return 0;
err4:
iounmap(spdif->regs);
diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c
index 1bc8ebc..ad54d4c 100644
--- a/sound/soc/sti/uniperif_player.c
+++ b/sound/soc/sti/uniperif_player.c
@@ -614,7 +614,11 @@ static int uni_player_ctl_iec958_put(struct snd_kcontrol *kcontrol,
iec958->status[3] = ucontrol->value.iec958.status[3];
mutex_unlock(&player->ctrl_lock);
- uni_player_set_channel_status(player, NULL);
+ if (player->substream && player->substream->runtime)
+ uni_player_set_channel_status(player,
+ player->substream->runtime);
+ else
+ uni_player_set_channel_status(player, NULL);
return 0;
}
diff --git a/sound/soc/sunxi/sun4i-codec.c b/sound/soc/sunxi/sun4i-codec.c
index e047ec0..56ed947 100644
--- a/sound/soc/sunxi/sun4i-codec.c
+++ b/sound/soc/sunxi/sun4i-codec.c
@@ -765,11 +765,11 @@ static struct snd_soc_card *sun4i_codec_create_card(struct device *dev)
card = devm_kzalloc(dev, sizeof(*card), GFP_KERNEL);
if (!card)
- return NULL;
+ return ERR_PTR(-ENOMEM);
card->dai_link = sun4i_codec_create_link(dev, &card->num_links);
if (!card->dai_link)
- return NULL;
+ return ERR_PTR(-ENOMEM);
card->dev = dev;
card->name = "sun4i-codec";
@@ -829,12 +829,6 @@ static int sun4i_codec_probe(struct platform_device *pdev)
return PTR_ERR(scodec->clk_module);
}
- /* Enable the bus clock */
- if (clk_prepare_enable(scodec->clk_apb)) {
- dev_err(&pdev->dev, "Failed to enable the APB clock\n");
- return -EINVAL;
- }
-
scodec->gpio_pa = devm_gpiod_get_optional(&pdev->dev, "allwinner,pa",
GPIOD_OUT_LOW);
if (IS_ERR(scodec->gpio_pa)) {
@@ -844,6 +838,12 @@ static int sun4i_codec_probe(struct platform_device *pdev)
return ret;
}
+ /* Enable the bus clock */
+ if (clk_prepare_enable(scodec->clk_apb)) {
+ dev_err(&pdev->dev, "Failed to enable the APB clock\n");
+ return -EINVAL;
+ }
+
/* DMA configuration for TX FIFO */
scodec->playback_dma_data.addr = res->start + SUN4I_CODEC_DAC_TXDATA;
scodec->playback_dma_data.maxburst = 4;
@@ -876,7 +876,8 @@ static int sun4i_codec_probe(struct platform_device *pdev)
}
card = sun4i_codec_create_card(&pdev->dev);
- if (!card) {
+ if (IS_ERR(card)) {
+ ret = PTR_ERR(card);
dev_err(&pdev->dev, "Failed to create our card\n");
goto err_unregister_codec;
}
diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c
index 14e587e..90009c0 100644
--- a/sound/usb/line6/driver.c
+++ b/sound/usb/line6/driver.c
@@ -604,8 +604,8 @@ line6_hwdep_write(struct snd_hwdep *hwdep, const char __user *data, long count,
}
data_copy = memdup_user(data, count);
- if (IS_ERR(ERR_PTR))
- return -ENOMEM;
+ if (IS_ERR(data_copy))
+ return PTR_ERR(data_copy);
rv = line6_send_raw_message(line6, data_copy, count);
diff --git a/sound/usb/line6/podhd.c b/sound/usb/line6/podhd.c
index 9352a44..49cd4a6 100644
--- a/sound/usb/line6/podhd.c
+++ b/sound/usb/line6/podhd.c
@@ -317,7 +317,8 @@ static int podhd_init(struct usb_line6 *line6,
if (pod->line6.properties->capabilities & LINE6_CAP_PCM) {
/* initialize PCM subsystem: */
err = line6_init_pcm(line6,
- (id->driver_info == LINE6_PODX3) ? &podx3_pcm_properties :
+ (id->driver_info == LINE6_PODX3 ||
+ id->driver_info == LINE6_PODX3LIVE) ? &podx3_pcm_properties :
&podhd_pcm_properties);
if (err < 0)
return err;
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index c60a776..8a59d47 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -2907,6 +2907,23 @@ AU0828_DEVICE(0x2040, 0x7260, "Hauppauge", "HVR-950Q"),
AU0828_DEVICE(0x2040, 0x7213, "Hauppauge", "HVR-950Q"),
AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
+/* Syntek STK1160 */
+{
+ .match_flags = USB_DEVICE_ID_MATCH_DEVICE |
+ USB_DEVICE_ID_MATCH_INT_CLASS |
+ USB_DEVICE_ID_MATCH_INT_SUBCLASS,
+ .idVendor = 0x05e1,
+ .idProduct = 0x0408,
+ .bInterfaceClass = USB_CLASS_AUDIO,
+ .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL,
+ .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+ .vendor_name = "Syntek",
+ .product_name = "STK1160",
+ .ifnum = QUIRK_ANY_INTERFACE,
+ .type = QUIRK_AUDIO_ALIGN_TRANSFER
+ }
+},
+
/* Digidesign Mbox */
{
/* Thanks to Clemens Ladisch <clemens@ladisch.de> */
diff --git a/Documentation/accounting/.gitignore b/tools/accounting/.gitignore
similarity index 100%
rename from Documentation/accounting/.gitignore
rename to tools/accounting/.gitignore
diff --git a/tools/accounting/Makefile b/tools/accounting/Makefile
new file mode 100644
index 0000000..647c94a
--- /dev/null
+++ b/tools/accounting/Makefile
@@ -0,0 +1,9 @@
+CC := $(CROSS_COMPILE)gcc
+CFLAGS := -I../../usr/include
+
+PROGS := getdelays
+
+all: $(PROGS)
+
+clean:
+ rm -fr $(PROGS)
diff --git a/Documentation/accounting/getdelays.c b/tools/accounting/getdelays.c
similarity index 100%
rename from Documentation/accounting/getdelays.c
rename to tools/accounting/getdelays.c
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 1188bc8..a396292 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -194,6 +194,8 @@
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
+#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/Documentation/laptops/.gitignore b/tools/laptop/dslm/.gitignore
similarity index 100%
rename from Documentation/laptops/.gitignore
rename to tools/laptop/dslm/.gitignore
diff --git a/tools/laptop/dslm/Makefile b/tools/laptop/dslm/Makefile
new file mode 100644
index 0000000..ff613b3
--- /dev/null
+++ b/tools/laptop/dslm/Makefile
@@ -0,0 +1,9 @@
+CC := $(CROSS_COMPILE)gcc
+CFLAGS := -I../../usr/include
+
+PROGS := dslm
+
+all: $(PROGS)
+
+clean:
+ rm -fr $(PROGS)
diff --git a/Documentation/laptops/dslm.c b/tools/laptop/dslm/dslm.c
similarity index 100%
rename from Documentation/laptops/dslm.c
rename to tools/laptop/dslm/dslm.c
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index c0c0b26..b63a31b 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -98,6 +98,15 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
*type = INSN_FP_SETUP;
break;
+ case 0x8d:
+ if (insn.rex_prefix.bytes &&
+ insn.rex_prefix.bytes[0] == 0x48 &&
+ insn.modrm.nbytes && insn.modrm.bytes[0] == 0x2c &&
+ insn.sib.nbytes && insn.sib.bytes[0] == 0x24)
+ /* lea %(rsp), %rbp */
+ *type = INSN_FP_SETUP;
+ break;
+
case 0x90:
*type = INSN_NOP;
break;
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 143b6cd..e8a1f69 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -97,6 +97,19 @@ static struct instruction *next_insn_same_sec(struct objtool_file *file,
return next;
}
+static bool gcov_enabled(struct objtool_file *file)
+{
+ struct section *sec;
+ struct symbol *sym;
+
+ list_for_each_entry(sec, &file->elf->sections, list)
+ list_for_each_entry(sym, &sec->symbol_list, list)
+ if (!strncmp(sym->name, "__gcov_.", 8))
+ return true;
+
+ return false;
+}
+
#define for_each_insn(file, insn) \
list_for_each_entry(insn, &file->insn_list, list)
@@ -713,6 +726,7 @@ static struct rela *find_switch_table(struct objtool_file *file,
struct instruction *insn)
{
struct rela *text_rela, *rodata_rela;
+ struct instruction *orig_insn = insn;
text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len);
if (text_rela && text_rela->sym == file->rodata->sym) {
@@ -733,10 +747,16 @@ static struct rela *find_switch_table(struct objtool_file *file,
/* case 3 */
func_for_each_insn_continue_reverse(file, func, insn) {
- if (insn->type == INSN_JUMP_UNCONDITIONAL ||
- insn->type == INSN_JUMP_DYNAMIC)
+ if (insn->type == INSN_JUMP_DYNAMIC)
break;
+ /* allow small jumps within the range */
+ if (insn->type == INSN_JUMP_UNCONDITIONAL &&
+ insn->jump_dest &&
+ (insn->jump_dest->offset <= insn->offset ||
+ insn->jump_dest->offset > orig_insn->offset))
+ break;
+
text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
insn->len);
if (text_rela && text_rela->sym == file->rodata->sym)
@@ -1034,34 +1054,6 @@ static int validate_branch(struct objtool_file *file,
return 0;
}
-static bool is_gcov_insn(struct instruction *insn)
-{
- struct rela *rela;
- struct section *sec;
- struct symbol *sym;
- unsigned long offset;
-
- rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len);
- if (!rela)
- return false;
-
- if (rela->sym->type != STT_SECTION)
- return false;
-
- sec = rela->sym->sec;
- offset = rela->addend + insn->offset + insn->len - rela->offset;
-
- list_for_each_entry(sym, &sec->symbol_list, list) {
- if (sym->type != STT_OBJECT)
- continue;
-
- if (offset >= sym->offset && offset < sym->offset + sym->len)
- return (!memcmp(sym->name, "__gcov0.", 8));
- }
-
- return false;
-}
-
static bool is_kasan_insn(struct instruction *insn)
{
return (insn->type == INSN_CALL &&
@@ -1083,9 +1075,6 @@ static bool ignore_unreachable_insn(struct symbol *func,
if (insn->type == INSN_NOP)
return true;
- if (is_gcov_insn(insn))
- return true;
-
/*
* Check if this (or a subsequent) instruction is related to
* CONFIG_UBSAN or CONFIG_KASAN.
@@ -1146,6 +1135,19 @@ static int validate_functions(struct objtool_file *file)
ignore_unreachable_insn(func, insn))
continue;
+ /*
+ * gcov produces a lot of unreachable
+ * instructions. If we get an unreachable
+ * warning and the file has gcov enabled, just
+ * ignore it, and all other such warnings for
+ * the file.
+ */
+ if (!file->ignore_unreachables &&
+ gcov_enabled(file)) {
+ file->ignore_unreachables = true;
+ continue;
+ }
+
WARN_FUNC("function has unreachable instruction", insn->sec, insn->offset);
warnings++;
}
diff --git a/Documentation/pcmcia/.gitignore b/tools/pcmcia/.gitignore
similarity index 100%
rename from Documentation/pcmcia/.gitignore
rename to tools/pcmcia/.gitignore
diff --git a/tools/pcmcia/Makefile b/tools/pcmcia/Makefile
new file mode 100644
index 0000000..81a7498
--- /dev/null
+++ b/tools/pcmcia/Makefile
@@ -0,0 +1,9 @@
+CC := $(CROSS_COMPILE)gcc
+CFLAGS := -I../../usr/include
+
+PROGS := crc32hash
+
+all: $(PROGS)
+
+clean:
+ rm -fr $(PROGS)
diff --git a/Documentation/pcmcia/crc32hash.c b/tools/pcmcia/crc32hash.c
similarity index 100%
rename from Documentation/pcmcia/crc32hash.c
rename to tools/pcmcia/crc32hash.c
diff --git a/tools/perf/jvmti/Makefile b/tools/perf/jvmti/Makefile
index 5ce61a1..df14e6b 100644
--- a/tools/perf/jvmti/Makefile
+++ b/tools/perf/jvmti/Makefile
@@ -36,7 +36,7 @@
# The following works at least on fedora 23, you may need the next
# line for other distros.
ifneq (,$(wildcard /usr/sbin/update-java-alternatives))
-JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | cut -d ' ' -f 3)
+JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}')
else
ifneq (,$(wildcard /usr/sbin/alternatives))
JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index fb8e42c..a53fef0 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -601,7 +601,8 @@ int hist_browser__run(struct hist_browser *browser, const char *help)
u64 nr_entries;
hbt->timer(hbt->arg);
- if (hist_browser__has_filter(browser))
+ if (hist_browser__has_filter(browser) ||
+ symbol_conf.report_hierarchy)
hist_browser__update_nr_entries(browser);
nr_entries = hist_browser__nr_entries(browser);
@@ -1336,8 +1337,8 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
}
if (first) {
- ui_browser__printf(&browser->b, "%c", folded_sign);
- width--;
+ ui_browser__printf(&browser->b, "%c ", folded_sign);
+ width -= 2;
first = false;
} else {
ui_browser__printf(&browser->b, " ");
@@ -1360,8 +1361,10 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
width -= hpp.buf - s;
}
- ui_browser__write_nstring(&browser->b, "", hierarchy_indent);
- width -= hierarchy_indent;
+ if (!first) {
+ ui_browser__write_nstring(&browser->b, "", hierarchy_indent);
+ width -= hierarchy_indent;
+ }
if (column >= browser->b.horiz_scroll) {
char s[2048];
@@ -1380,7 +1383,13 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
}
perf_hpp_list__for_each_format(entry->hpp_list, fmt) {
- ui_browser__write_nstring(&browser->b, "", 2);
+ if (first) {
+ ui_browser__printf(&browser->b, "%c ", folded_sign);
+ first = false;
+ } else {
+ ui_browser__write_nstring(&browser->b, "", 2);
+ }
+
width -= 2;
/*
@@ -1554,10 +1563,11 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
int indent = hists->nr_hpp_node - 2;
bool first_node, first_col;
- ret = scnprintf(buf, size, " ");
+ ret = scnprintf(buf, size, " ");
if (advance_hpp_check(&dummy_hpp, ret))
return ret;
+ first_node = true;
/* the first hpp_list_node is for overhead columns */
fmt_node = list_first_entry(&hists->hpp_formats,
struct perf_hpp_list_node, list);
@@ -1572,12 +1582,16 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, " ");
if (advance_hpp_check(&dummy_hpp, ret))
break;
+
+ first_node = false;
}
- ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "%*s",
- indent * HIERARCHY_INDENT, "");
- if (advance_hpp_check(&dummy_hpp, ret))
- return ret;
+ if (!first_node) {
+ ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "%*s",
+ indent * HIERARCHY_INDENT, "");
+ if (advance_hpp_check(&dummy_hpp, ret))
+ return ret;
+ }
first_node = true;
list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
@@ -2075,8 +2089,21 @@ void hist_browser__init(struct hist_browser *browser,
browser->b.use_navkeypressed = true;
browser->show_headers = symbol_conf.show_hist_headers;
- hists__for_each_format(hists, fmt)
+ if (symbol_conf.report_hierarchy) {
+ struct perf_hpp_list_node *fmt_node;
+
+ /* count overhead columns (in the first node) */
+ fmt_node = list_first_entry(&hists->hpp_formats,
+ struct perf_hpp_list_node, list);
+ perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
+ ++browser->b.columns;
+
+ /* add a single column for whole hierarchy sort keys*/
++browser->b.columns;
+ } else {
+ hists__for_each_format(hists, fmt)
+ ++browser->b.columns;
+ }
hists__reset_column_width(hists);
}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 85dd0db..2f3eded 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1895,7 +1895,6 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
if (ph->needs_swap)
nr = bswap_32(nr);
- ph->env.nr_numa_nodes = nr;
nodes = zalloc(sizeof(*nodes) * nr);
if (!nodes)
return -ENOMEM;
@@ -1932,6 +1931,7 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
free(str);
}
+ ph->env.nr_numa_nodes = nr;
ph->env.numa_nodes = nodes;
return 0;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index b02992e..a69f027 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1600,18 +1600,18 @@ static void hists__hierarchy_output_resort(struct hists *hists,
if (prog)
ui_progress__update(prog, 1);
+ hists->nr_entries++;
+ if (!he->filtered) {
+ hists->nr_non_filtered_entries++;
+ hists__calc_col_len(hists, he);
+ }
+
if (!he->leaf) {
hists__hierarchy_output_resort(hists, prog,
&he->hroot_in,
&he->hroot_out,
min_callchain_hits,
use_callchain);
- hists->nr_entries++;
- if (!he->filtered) {
- hists->nr_non_filtered_entries++;
- hists__calc_col_len(hists, he);
- }
-
continue;
}
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 9f43fda..660fca0 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -136,8 +136,8 @@
group [^,{}/]*[{][^}]*[}][^,{}/]*
event_pmu [^,{}/]+[/][^/]*[/][^,{}/]*
event [^,{}/]+
-bpf_object .*\.(o|bpf)
-bpf_source .*\.c
+bpf_object [^,{}]+\.(o|bpf)
+bpf_source [^,{}]+\.c
num_dec [0-9]+
num_hex 0x[a-fA-F0-9]+
diff --git a/tools/power/cpupower/utils/cpufreq-set.c b/tools/power/cpupower/utils/cpufreq-set.c
index b4bf769..1eef0ae 100644
--- a/tools/power/cpupower/utils/cpufreq-set.c
+++ b/tools/power/cpupower/utils/cpufreq-set.c
@@ -296,7 +296,7 @@ int cmd_freq_set(int argc, char **argv)
struct cpufreq_affected_cpus *cpus;
if (!bitmask_isbitset(cpus_chosen, cpu) ||
- cpupower_is_cpu_online(cpu))
+ cpupower_is_cpu_online(cpu) != 1)
continue;
cpus = cpufreq_get_related_cpus(cpu);
@@ -316,10 +316,7 @@ int cmd_freq_set(int argc, char **argv)
cpu <= bitmask_last(cpus_chosen); cpu++) {
if (!bitmask_isbitset(cpus_chosen, cpu) ||
- cpupower_is_cpu_online(cpu))
- continue;
-
- if (cpupower_is_cpu_online(cpu) != 1)
+ cpupower_is_cpu_online(cpu) != 1)
continue;
printf(_("Setting cpu: %d\n"), cpu);
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 4761e2d6..7a5f245 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -1,8 +1,8 @@
-CFLAGS += -Wall -O2
+CFLAGS += -Wall -O2 -I../../../../usr/include
-test_objs = test_verifier test_maps
+test_objs = test_verifier test_maps test_lru_map
-TEST_PROGS := test_verifier test_maps test_kmod.sh
+TEST_PROGS := test_verifier test_maps test_lru_map test_kmod.sh
TEST_FILES := $(test_objs)
all: $(test_objs)
diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
new file mode 100644
index 0000000..627757e
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -0,0 +1,583 @@
+/*
+ * Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <unistd.h>
+#include <errno.h>
+#include <string.h>
+#include <assert.h>
+#include <sched.h>
+#include <sys/wait.h>
+#include <stdlib.h>
+#include <time.h>
+#include "bpf_sys.h"
+
+#define LOCAL_FREE_TARGET (128)
+#define PERCPU_FREE_TARGET (16)
+
+static int nr_cpus;
+
+static int create_map(int map_type, int map_flags, unsigned int size)
+{
+ int map_fd;
+
+ map_fd = bpf_map_create(map_type, sizeof(unsigned long long),
+ sizeof(unsigned long long), size, map_flags);
+
+ if (map_fd == -1)
+ perror("bpf_map_create");
+
+ return map_fd;
+}
+
+static int map_subset(int map0, int map1)
+{
+ unsigned long long next_key = 0;
+ unsigned long long value0[nr_cpus], value1[nr_cpus];
+ int ret;
+
+ while (!bpf_map_next_key(map1, &next_key, &next_key)) {
+ assert(!bpf_map_lookup(map1, &next_key, value1));
+ ret = bpf_map_lookup(map0, &next_key, value0);
+ if (ret) {
+ printf("key:%llu not found from map. %s(%d)\n",
+ next_key, strerror(errno), errno);
+ return 0;
+ }
+ if (value0[0] != value1[0]) {
+ printf("key:%llu value0:%llu != value1:%llu\n",
+ next_key, value0[0], value1[0]);
+ return 0;
+ }
+ }
+ return 1;
+}
+
+static int map_equal(int lru_map, int expected)
+{
+ return map_subset(lru_map, expected) && map_subset(expected, lru_map);
+}
+
+static int sched_next_online(int pid, int next_to_try)
+{
+ cpu_set_t cpuset;
+
+ if (next_to_try == nr_cpus)
+ return -1;
+
+ while (next_to_try < nr_cpus) {
+ CPU_ZERO(&cpuset);
+ CPU_SET(next_to_try++, &cpuset);
+ if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset))
+ break;
+ }
+
+ return next_to_try;
+}
+
+/* Size of the LRU amp is 2
+ * Add key=1 (+1 key)
+ * Add key=2 (+1 key)
+ * Lookup Key=1
+ * Add Key=3
+ * => Key=2 will be removed by LRU
+ * Iterate map. Only found key=1 and key=3
+ */
+static void test_lru_sanity0(int map_type, int map_flags)
+{
+ unsigned long long key, value[nr_cpus];
+ int lru_map_fd, expected_map_fd;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ assert(sched_next_online(0, 0) != -1);
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ lru_map_fd = create_map(map_type, map_flags, 2 * nr_cpus);
+ else
+ lru_map_fd = create_map(map_type, map_flags, 2);
+ assert(lru_map_fd != -1);
+
+ expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, 2);
+ assert(expected_map_fd != -1);
+
+ value[0] = 1234;
+
+ /* insert key=1 element */
+
+ key = 1;
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_update(expected_map_fd, &key, value, BPF_NOEXIST));
+
+ /* BPF_NOEXIST means: add new element if it doesn't exist */
+ assert(bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST) == -1 &&
+ /* key=1 already exists */
+ errno == EEXIST);
+
+ assert(bpf_map_update(lru_map_fd, &key, value, -1) == -1 &&
+ errno == EINVAL);
+
+ /* insert key=2 element */
+
+ /* check that key=2 is not found */
+ key = 2;
+ assert(bpf_map_lookup(lru_map_fd, &key, value) == -1 &&
+ errno == ENOENT);
+
+ /* BPF_EXIST means: update existing element */
+ assert(bpf_map_update(lru_map_fd, &key, value, BPF_EXIST) == -1 &&
+ /* key=2 is not there */
+ errno == ENOENT);
+
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+
+ /* insert key=3 element */
+
+ /* check that key=3 is not found */
+ key = 3;
+ assert(bpf_map_lookup(lru_map_fd, &key, value) == -1 &&
+ errno == ENOENT);
+
+ /* check that key=1 can be found and mark the ref bit to
+ * stop LRU from removing key=1
+ */
+ key = 1;
+ assert(!bpf_map_lookup(lru_map_fd, &key, value));
+ assert(value[0] == 1234);
+
+ key = 3;
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_update(expected_map_fd, &key, value, BPF_NOEXIST));
+
+ /* key=2 has been removed from the LRU */
+ key = 2;
+ assert(bpf_map_lookup(lru_map_fd, &key, value) == -1);
+
+ assert(map_equal(lru_map_fd, expected_map_fd));
+
+ close(expected_map_fd);
+ close(lru_map_fd);
+
+ printf("Pass\n");
+}
+
+/* Size of the LRU map is 1.5*tgt_free
+ * Insert 1 to tgt_free (+tgt_free keys)
+ * Lookup 1 to tgt_free/2
+ * Insert 1+tgt_free to 2*tgt_free (+tgt_free keys)
+ * => 1+tgt_free/2 to LOCALFREE_TARGET will be removed by LRU
+ */
+static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
+{
+ unsigned long long key, end_key, value[nr_cpus];
+ int lru_map_fd, expected_map_fd;
+ unsigned int batch_size;
+ unsigned int map_size;
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ /* Ther percpu lru list (i.e each cpu has its own LRU
+ * list) does not have a local free list. Hence,
+ * it will only free old nodes till there is no free
+ * from the LRU list. Hence, this test does not apply
+ * to BPF_F_NO_COMMON_LRU
+ */
+ return;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ assert(sched_next_online(0, 0) != -1);
+
+ batch_size = tgt_free / 2;
+ assert(batch_size * 2 == tgt_free);
+
+ map_size = tgt_free + batch_size;
+ lru_map_fd = create_map(map_type, map_flags, map_size);
+ assert(lru_map_fd != -1);
+
+ expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
+ assert(expected_map_fd != -1);
+
+ value[0] = 1234;
+
+ /* Insert 1 to tgt_free (+tgt_free keys) */
+ end_key = 1 + tgt_free;
+ for (key = 1; key < end_key; key++)
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+
+ /* Lookup 1 to tgt_free/2 */
+ end_key = 1 + batch_size;
+ for (key = 1; key < end_key; key++) {
+ assert(!bpf_map_lookup(lru_map_fd, &key, value));
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ /* Insert 1+tgt_free to 2*tgt_free
+ * => 1+tgt_free/2 to LOCALFREE_TARGET will be
+ * removed by LRU
+ */
+ key = 1 + tgt_free;
+ end_key = key + tgt_free;
+ for (; key < end_key; key++) {
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ assert(map_equal(lru_map_fd, expected_map_fd));
+
+ close(expected_map_fd);
+ close(lru_map_fd);
+
+ printf("Pass\n");
+}
+
+/* Size of the LRU map 1.5 * tgt_free
+ * Insert 1 to tgt_free (+tgt_free keys)
+ * Update 1 to tgt_free/2
+ * => The original 1 to tgt_free/2 will be removed due to
+ * the LRU shrink process
+ * Re-insert 1 to tgt_free/2 again and do a lookup immeidately
+ * Insert 1+tgt_free to tgt_free*3/2
+ * Insert 1+tgt_free*3/2 to tgt_free*5/2
+ * => Key 1+tgt_free to tgt_free*3/2
+ * will be removed from LRU because it has never
+ * been lookup and ref bit is not set
+ */
+static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
+{
+ unsigned long long key, value[nr_cpus];
+ unsigned long long end_key;
+ int lru_map_fd, expected_map_fd;
+ unsigned int batch_size;
+ unsigned int map_size;
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ /* Ther percpu lru list (i.e each cpu has its own LRU
+ * list) does not have a local free list. Hence,
+ * it will only free old nodes till there is no free
+ * from the LRU list. Hence, this test does not apply
+ * to BPF_F_NO_COMMON_LRU
+ */
+ return;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ assert(sched_next_online(0, 0) != -1);
+
+ batch_size = tgt_free / 2;
+ assert(batch_size * 2 == tgt_free);
+
+ map_size = tgt_free + batch_size;
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ lru_map_fd = create_map(map_type, map_flags,
+ map_size * nr_cpus);
+ else
+ lru_map_fd = create_map(map_type, map_flags, map_size);
+ assert(lru_map_fd != -1);
+
+ expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
+ assert(expected_map_fd != -1);
+
+ value[0] = 1234;
+
+ /* Insert 1 to tgt_free (+tgt_free keys) */
+ end_key = 1 + tgt_free;
+ for (key = 1; key < end_key; key++)
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+
+ /* Any bpf_map_update will require to acquire a new node
+ * from LRU first.
+ *
+ * The local list is running out of free nodes.
+ * It gets from the global LRU list which tries to
+ * shrink the inactive list to get tgt_free
+ * number of free nodes.
+ *
+ * Hence, the oldest key 1 to tgt_free/2
+ * are removed from the LRU list.
+ */
+ key = 1;
+ if (map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_delete(lru_map_fd, &key));
+ } else {
+ assert(bpf_map_update(lru_map_fd, &key, value, BPF_EXIST));
+ }
+
+ /* Re-insert 1 to tgt_free/2 again and do a lookup
+ * immeidately.
+ */
+ end_key = 1 + batch_size;
+ value[0] = 4321;
+ for (key = 1; key < end_key; key++) {
+ assert(bpf_map_lookup(lru_map_fd, &key, value));
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_lookup(lru_map_fd, &key, value));
+ assert(value[0] == 4321);
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ value[0] = 1234;
+
+ /* Insert 1+tgt_free to tgt_free*3/2 */
+ end_key = 1 + tgt_free + batch_size;
+ for (key = 1 + tgt_free; key < end_key; key++)
+ /* These newly added but not referenced keys will be
+ * gone during the next LRU shrink.
+ */
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+
+ /* Insert 1+tgt_free*3/2 to tgt_free*5/2 */
+ end_key = key + tgt_free;
+ for (; key < end_key; key++) {
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ assert(map_equal(lru_map_fd, expected_map_fd));
+
+ close(expected_map_fd);
+ close(lru_map_fd);
+
+ printf("Pass\n");
+}
+
+/* Size of the LRU map is 2*tgt_free
+ * It is to test the active/inactive list rotation
+ * Insert 1 to 2*tgt_free (+2*tgt_free keys)
+ * Lookup key 1 to tgt_free*3/2
+ * Add 1+2*tgt_free to tgt_free*5/2 (+tgt_free/2 keys)
+ * => key 1+tgt_free*3/2 to 2*tgt_free are removed from LRU
+ */
+static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
+{
+ unsigned long long key, end_key, value[nr_cpus];
+ int lru_map_fd, expected_map_fd;
+ unsigned int batch_size;
+ unsigned int map_size;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ assert(sched_next_online(0, 0) != -1);
+
+ batch_size = tgt_free / 2;
+ assert(batch_size * 2 == tgt_free);
+
+ map_size = tgt_free * 2;
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ lru_map_fd = create_map(map_type, map_flags,
+ map_size * nr_cpus);
+ else
+ lru_map_fd = create_map(map_type, map_flags, map_size);
+ assert(lru_map_fd != -1);
+
+ expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
+ assert(expected_map_fd != -1);
+
+ value[0] = 1234;
+
+ /* Insert 1 to 2*tgt_free (+2*tgt_free keys) */
+ end_key = 1 + (2 * tgt_free);
+ for (key = 1; key < end_key; key++)
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+
+ /* Lookup key 1 to tgt_free*3/2 */
+ end_key = tgt_free + batch_size;
+ for (key = 1; key < end_key; key++) {
+ assert(!bpf_map_lookup(lru_map_fd, &key, value));
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ /* Add 1+2*tgt_free to tgt_free*5/2
+ * (+tgt_free/2 keys)
+ */
+ key = 2 * tgt_free + 1;
+ end_key = key + batch_size;
+ for (; key < end_key; key++) {
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ assert(map_equal(lru_map_fd, expected_map_fd));
+
+ close(expected_map_fd);
+ close(lru_map_fd);
+
+ printf("Pass\n");
+}
+
+/* Test deletion */
+static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free)
+{
+ int lru_map_fd, expected_map_fd;
+ unsigned long long key, value[nr_cpus];
+ unsigned long long end_key;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ assert(sched_next_online(0, 0) != -1);
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ lru_map_fd = create_map(map_type, map_flags,
+ 3 * tgt_free * nr_cpus);
+ else
+ lru_map_fd = create_map(map_type, map_flags, 3 * tgt_free);
+ assert(lru_map_fd != -1);
+
+ expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0,
+ 3 * tgt_free);
+ assert(expected_map_fd != -1);
+
+ value[0] = 1234;
+
+ for (key = 1; key <= 2 * tgt_free; key++)
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+
+ key = 1;
+ assert(bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+
+ for (key = 1; key <= tgt_free; key++) {
+ assert(!bpf_map_lookup(lru_map_fd, &key, value));
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ for (; key <= 2 * tgt_free; key++) {
+ assert(!bpf_map_delete(lru_map_fd, &key));
+ assert(bpf_map_delete(lru_map_fd, &key));
+ }
+
+ end_key = key + 2 * tgt_free;
+ for (; key < end_key; key++) {
+ assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_update(expected_map_fd, &key, value,
+ BPF_NOEXIST));
+ }
+
+ assert(map_equal(lru_map_fd, expected_map_fd));
+
+ close(expected_map_fd);
+ close(lru_map_fd);
+
+ printf("Pass\n");
+}
+
+static void do_test_lru_sanity5(unsigned long long last_key, int map_fd)
+{
+ unsigned long long key, value[nr_cpus];
+
+ /* Ensure the last key inserted by previous CPU can be found */
+ assert(!bpf_map_lookup(map_fd, &last_key, value));
+
+ value[0] = 1234;
+
+ key = last_key + 1;
+ assert(!bpf_map_update(map_fd, &key, value, BPF_NOEXIST));
+ assert(!bpf_map_lookup(map_fd, &key, value));
+
+ /* Cannot find the last key because it was removed by LRU */
+ assert(bpf_map_lookup(map_fd, &last_key, value));
+}
+
+/* Test map with only one element */
+static void test_lru_sanity5(int map_type, int map_flags)
+{
+ unsigned long long key, value[nr_cpus];
+ int next_sched_cpu = 0;
+ int map_fd;
+ int i;
+
+ if (map_flags & BPF_F_NO_COMMON_LRU)
+ return;
+
+ printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+ map_flags);
+
+ map_fd = create_map(map_type, map_flags, 1);
+ assert(map_fd != -1);
+
+ value[0] = 1234;
+ key = 0;
+ assert(!bpf_map_update(map_fd, &key, value, BPF_NOEXIST));
+
+ for (i = 0; i < nr_cpus; i++) {
+ pid_t pid;
+
+ pid = fork();
+ if (pid == 0) {
+ next_sched_cpu = sched_next_online(0, next_sched_cpu);
+ if (next_sched_cpu != -1)
+ do_test_lru_sanity5(key, map_fd);
+ exit(0);
+ } else if (pid == -1) {
+ printf("couldn't spawn #%d process\n", i);
+ exit(1);
+ } else {
+ int status;
+
+ /* It is mostly redundant and just allow the parent
+ * process to update next_shced_cpu for the next child
+ * process
+ */
+ next_sched_cpu = sched_next_online(pid, next_sched_cpu);
+
+ assert(waitpid(pid, &status, 0) == pid);
+ assert(status == 0);
+ key++;
+ }
+ }
+
+ close(map_fd);
+
+ printf("Pass\n");
+}
+
+int main(int argc, char **argv)
+{
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+ int map_types[] = {BPF_MAP_TYPE_LRU_HASH,
+ BPF_MAP_TYPE_LRU_PERCPU_HASH};
+ int map_flags[] = {0, BPF_F_NO_COMMON_LRU};
+ int t, f;
+
+ setbuf(stdout, NULL);
+
+ assert(!setrlimit(RLIMIT_MEMLOCK, &r));
+
+ nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+ assert(nr_cpus != -1);
+ printf("nr_cpus:%d\n\n", nr_cpus);
+
+ for (f = 0; f < sizeof(map_flags) / sizeof(*map_flags); f++) {
+ unsigned int tgt_free = (map_flags[f] & BPF_F_NO_COMMON_LRU) ?
+ PERCPU_FREE_TARGET : LOCAL_FREE_TARGET;
+
+ for (t = 0; t < sizeof(map_types) / sizeof(*map_types); t++) {
+ test_lru_sanity0(map_types[t], map_flags[f]);
+ test_lru_sanity1(map_types[t], map_flags[f], tgt_free);
+ test_lru_sanity2(map_types[t], map_flags[f], tgt_free);
+ test_lru_sanity3(map_types[t], map_flags[f], tgt_free);
+ test_lru_sanity4(map_types[t], map_flags[f], tgt_free);
+ test_lru_sanity5(map_types[t], map_flags[f]);
+
+ printf("\n");
+ }
+ }
+
+ return 0;
+}
diff --git a/Documentation/filesystems/.gitignore b/tools/testing/selftests/filesystems/.gitignore
similarity index 100%
rename from Documentation/filesystems/.gitignore
rename to tools/testing/selftests/filesystems/.gitignore
diff --git a/tools/testing/selftests/filesystems/Makefile b/tools/testing/selftests/filesystems/Makefile
new file mode 100644
index 0000000..0ab1130
--- /dev/null
+++ b/tools/testing/selftests/filesystems/Makefile
@@ -0,0 +1,7 @@
+TEST_PROGS := dnotify_test
+all: $(TEST_PROGS)
+
+include ../lib.mk
+
+clean:
+ rm -fr $(TEST_PROGS)
diff --git a/Documentation/filesystems/dnotify_test.c b/tools/testing/selftests/filesystems/dnotify_test.c
similarity index 100%
rename from Documentation/filesystems/dnotify_test.c
rename to tools/testing/selftests/filesystems/dnotify_test.c
diff --git a/tools/testing/selftests/futex/functional/run.sh b/tools/testing/selftests/futex/functional/run.sh
index e87dbe2..7ff002e 100755
--- a/tools/testing/selftests/futex/functional/run.sh
+++ b/tools/testing/selftests/futex/functional/run.sh
@@ -24,7 +24,7 @@
# Test for a color capable console
if [ -z "$USE_COLOR" ]; then
- tput setf 7
+ tput setf 7 || tput setaf 7
if [ $? -eq 0 ]; then
USE_COLOR=1
tput sgr0
diff --git a/tools/testing/selftests/futex/run.sh b/tools/testing/selftests/futex/run.sh
index 4126312..88bcb17 100755
--- a/tools/testing/selftests/futex/run.sh
+++ b/tools/testing/selftests/futex/run.sh
@@ -23,7 +23,7 @@
# Test for a color capable shell and pass the result to the subdir scripts
USE_COLOR=0
-tput setf 7
+tput setf 7 || tput setaf 7
if [ $? -eq 0 ]; then
USE_COLOR=1
tput sgr0
diff --git a/Documentation/ia64/.gitignore b/tools/testing/selftests/ia64/.gitignore
similarity index 100%
rename from Documentation/ia64/.gitignore
rename to tools/testing/selftests/ia64/.gitignore
diff --git a/tools/testing/selftests/ia64/Makefile b/tools/testing/selftests/ia64/Makefile
new file mode 100644
index 0000000..2b3de2d
--- /dev/null
+++ b/tools/testing/selftests/ia64/Makefile
@@ -0,0 +1,8 @@
+TEST_PROGS := aliasing-test
+
+all: $(TEST_PROGS)
+
+include ../lib.mk
+
+clean:
+ rm -fr $(TEST_PROGS)
diff --git a/Documentation/ia64/aliasing-test.c b/tools/testing/selftests/ia64/aliasing-test.c
similarity index 100%
rename from Documentation/ia64/aliasing-test.c
rename to tools/testing/selftests/ia64/aliasing-test.c
diff --git a/Documentation/networking/timestamping/.gitignore b/tools/testing/selftests/networking/timestamping/.gitignore
similarity index 100%
rename from Documentation/networking/timestamping/.gitignore
rename to tools/testing/selftests/networking/timestamping/.gitignore
diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile
new file mode 100644
index 0000000..ccbb9ed
--- /dev/null
+++ b/tools/testing/selftests/networking/timestamping/Makefile
@@ -0,0 +1,8 @@
+TEST_PROGS := hwtstamp_config timestamping txtimestamp
+
+all: $(TEST_PROGS)
+
+include ../../lib.mk
+
+clean:
+ rm -fr $(TEST_PROGS)
diff --git a/Documentation/networking/timestamping/hwtstamp_config.c b/tools/testing/selftests/networking/timestamping/hwtstamp_config.c
similarity index 100%
rename from Documentation/networking/timestamping/hwtstamp_config.c
rename to tools/testing/selftests/networking/timestamping/hwtstamp_config.c
diff --git a/Documentation/networking/timestamping/timestamping.c b/tools/testing/selftests/networking/timestamping/timestamping.c
similarity index 100%
rename from Documentation/networking/timestamping/timestamping.c
rename to tools/testing/selftests/networking/timestamping/timestamping.c
diff --git a/Documentation/networking/timestamping/txtimestamp.c b/tools/testing/selftests/networking/timestamping/txtimestamp.c
similarity index 100%
rename from Documentation/networking/timestamping/txtimestamp.c
rename to tools/testing/selftests/networking/timestamping/txtimestamp.c
diff --git a/tools/testing/selftests/powerpc/copyloops/asm/export.h b/tools/testing/selftests/powerpc/copyloops/asm/export.h
new file mode 100644
index 0000000..2d14a9b
--- /dev/null
+++ b/tools/testing/selftests/powerpc/copyloops/asm/export.h
@@ -0,0 +1 @@
+#define EXPORT_SYMBOL(x)
diff --git a/tools/testing/selftests/powerpc/math/.gitignore b/tools/testing/selftests/powerpc/math/.gitignore
index 4fe13a4..50ded63 100644
--- a/tools/testing/selftests/powerpc/math/.gitignore
+++ b/tools/testing/selftests/powerpc/math/.gitignore
@@ -4,3 +4,4 @@
vmx_preempt
fpu_signal
vmx_signal
+vsx_preempt
diff --git a/tools/testing/selftests/powerpc/signal/.gitignore b/tools/testing/selftests/powerpc/signal/.gitignore
new file mode 100644
index 0000000..1b89224
--- /dev/null
+++ b/tools/testing/selftests/powerpc/signal/.gitignore
@@ -0,0 +1,2 @@
+signal
+signal_tm
diff --git a/tools/testing/selftests/powerpc/stringloops/asm/export.h b/tools/testing/selftests/powerpc/stringloops/asm/export.h
new file mode 100644
index 0000000..2d14a9b
--- /dev/null
+++ b/tools/testing/selftests/powerpc/stringloops/asm/export.h
@@ -0,0 +1 @@
+#define EXPORT_SYMBOL(x)
diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore
index 82c0a9c..4276217 100644
--- a/tools/testing/selftests/powerpc/tm/.gitignore
+++ b/tools/testing/selftests/powerpc/tm/.gitignore
@@ -7,3 +7,7 @@
tm-tar
tm-tmspr
tm-exec
+tm-signal-context-chk-fpu
+tm-signal-context-chk-gpr
+tm-signal-context-chk-vmx
+tm-signal-context-chk-vsx
diff --git a/Documentation/prctl/.gitignore b/tools/testing/selftests/prctl/.gitignore
similarity index 100%
rename from Documentation/prctl/.gitignore
rename to tools/testing/selftests/prctl/.gitignore
diff --git a/tools/testing/selftests/prctl/Makefile b/tools/testing/selftests/prctl/Makefile
new file mode 100644
index 0000000..35aa1c8
--- /dev/null
+++ b/tools/testing/selftests/prctl/Makefile
@@ -0,0 +1,15 @@
+ifndef CROSS_COMPILE
+uname_M := $(shell uname -m 2>/dev/null || echo not)
+ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
+
+ifeq ($(ARCH),x86)
+TEST_PROGS := disable-tsc-ctxt-sw-stress-test disable-tsc-on-off-stress-test \
+ disable-tsc-test
+all: $(TEST_PROGS)
+
+include ../lib.mk
+
+clean:
+ rm -fr $(TEST_PROGS)
+endif
+endif
diff --git a/Documentation/prctl/disable-tsc-ctxt-sw-stress-test.c b/tools/testing/selftests/prctl/disable-tsc-ctxt-sw-stress-test.c
similarity index 100%
rename from Documentation/prctl/disable-tsc-ctxt-sw-stress-test.c
rename to tools/testing/selftests/prctl/disable-tsc-ctxt-sw-stress-test.c
diff --git a/Documentation/prctl/disable-tsc-on-off-stress-test.c b/tools/testing/selftests/prctl/disable-tsc-on-off-stress-test.c
similarity index 100%
rename from Documentation/prctl/disable-tsc-on-off-stress-test.c
rename to tools/testing/selftests/prctl/disable-tsc-on-off-stress-test.c
diff --git a/Documentation/prctl/disable-tsc-test.c b/tools/testing/selftests/prctl/disable-tsc-test.c
similarity index 100%
rename from Documentation/prctl/disable-tsc-test.c
rename to tools/testing/selftests/prctl/disable-tsc-test.c
diff --git a/Documentation/ptp/.gitignore b/tools/testing/selftests/ptp/.gitignore
similarity index 100%
rename from Documentation/ptp/.gitignore
rename to tools/testing/selftests/ptp/.gitignore
diff --git a/tools/testing/selftests/ptp/Makefile b/tools/testing/selftests/ptp/Makefile
new file mode 100644
index 0000000..83dd42b
--- /dev/null
+++ b/tools/testing/selftests/ptp/Makefile
@@ -0,0 +1,8 @@
+TEST_PROGS := testptp
+LDLIBS += -lrt
+all: $(TEST_PROGS)
+
+include ../lib.mk
+
+clean:
+ rm -fr $(TEST_PROGS)
diff --git a/Documentation/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c
similarity index 100%
rename from Documentation/ptp/testptp.c
rename to tools/testing/selftests/ptp/testptp.c
diff --git a/Documentation/ptp/testptp.mk b/tools/testing/selftests/ptp/testptp.mk
similarity index 100%
rename from Documentation/ptp/testptp.mk
rename to tools/testing/selftests/ptp/testptp.mk
diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c
index 5a246a02..15cf56d 100644
--- a/tools/testing/selftests/timers/posix_timers.c
+++ b/tools/testing/selftests/timers/posix_timers.c
@@ -122,7 +122,7 @@ static int check_itimer(int which)
else if (which == ITIMER_REAL)
idle_loop();
- gettimeofday(&end, NULL);
+ err = gettimeofday(&end, NULL);
if (err < 0) {
perror("Can't call gettimeofday()\n");
return -1;
@@ -175,7 +175,7 @@ static int check_timer_create(int which)
user_loop();
- gettimeofday(&end, NULL);
+ err = gettimeofday(&end, NULL);
if (err < 0) {
perror("Can't call gettimeofday()\n");
return -1;
diff --git a/Documentation/vDSO/.gitignore b/tools/testing/selftests/vDSO/.gitignore
similarity index 100%
rename from Documentation/vDSO/.gitignore
rename to tools/testing/selftests/vDSO/.gitignore
diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile
new file mode 100644
index 0000000..706b68b
--- /dev/null
+++ b/tools/testing/selftests/vDSO/Makefile
@@ -0,0 +1,20 @@
+ifndef CROSS_COMPILE
+CFLAGS := -std=gnu99
+CFLAGS_vdso_standalone_test_x86 := -nostdlib -fno-asynchronous-unwind-tables -fno-stack-protector
+ifeq ($(CONFIG_X86_32),y)
+LDLIBS += -lgcc_s
+endif
+
+TEST_PROGS := vdso_test vdso_standalone_test_x86
+
+all: $(TEST_PROGS)
+vdso_test: parse_vdso.c vdso_test.c
+vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c
+ $(CC) $(CFLAGS) $(CFLAGS_vdso_standalone_test_x86) \
+ vdso_standalone_test_x86.c parse_vdso.c \
+ -o vdso_standalone_test_x86
+
+include ../lib.mk
+clean:
+ rm -fr $(TEST_PROGS)
+endif
diff --git a/Documentation/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c
similarity index 100%
rename from Documentation/vDSO/parse_vdso.c
rename to tools/testing/selftests/vDSO/parse_vdso.c
diff --git a/Documentation/vDSO/vdso_standalone_test_x86.c b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c
similarity index 100%
rename from Documentation/vDSO/vdso_standalone_test_x86.c
rename to tools/testing/selftests/vDSO/vdso_standalone_test_x86.c
diff --git a/Documentation/vDSO/vdso_test.c b/tools/testing/selftests/vDSO/vdso_test.c
similarity index 100%
rename from Documentation/vDSO/vdso_test.c
rename to tools/testing/selftests/vDSO/vdso_test.c
diff --git a/tools/testing/selftests/watchdog/.gitignore b/tools/testing/selftests/watchdog/.gitignore
new file mode 100644
index 0000000..5aac515
--- /dev/null
+++ b/tools/testing/selftests/watchdog/.gitignore
@@ -0,0 +1 @@
+watchdog-test
diff --git a/tools/testing/selftests/watchdog/Makefile b/tools/testing/selftests/watchdog/Makefile
new file mode 100644
index 0000000..f863c66
--- /dev/null
+++ b/tools/testing/selftests/watchdog/Makefile
@@ -0,0 +1,8 @@
+TEST_PROGS := watchdog-test
+
+all: $(TEST_PROGS)
+
+include ../lib.mk
+
+clean:
+ rm -fr $(TEST_PROGS)
diff --git a/Documentation/watchdog/src/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c
similarity index 100%
rename from Documentation/watchdog/src/watchdog-test.c
rename to tools/testing/selftests/watchdog/watchdog-test.c
diff --git a/tools/testing/selftests/zram/README b/tools/testing/selftests/zram/README
index eb17917..7972cc5 100644
--- a/tools/testing/selftests/zram/README
+++ b/tools/testing/selftests/zram/README
@@ -13,7 +13,7 @@
Kconfig required:
CONFIG_ZRAM=y
-CONFIG_ZRAM_LZ4_COMPRESS=y
+CONFIG_CRYPTO_LZ4=y
CONFIG_ZPOOL=y
CONFIG_ZSMALLOC=y
diff --git a/tools/virtio/ringtest/Makefile b/tools/virtio/ringtest/Makefile
index 877a8a4..c012edb 100644
--- a/tools/virtio/ringtest/Makefile
+++ b/tools/virtio/ringtest/Makefile
@@ -3,8 +3,8 @@
all: ring virtio_ring_0_9 virtio_ring_poll virtio_ring_inorder ptr_ring noring
CFLAGS += -Wall
-CFLAGS += -pthread -O2 -ggdb
-LDFLAGS += -pthread -O2 -ggdb
+CFLAGS += -pthread -O2 -ggdb -flto -fwhole-program
+LDFLAGS += -pthread -O2 -ggdb -flto -fwhole-program
main.o: main.c main.h
ring.o: ring.c main.h
diff --git a/tools/virtio/ringtest/main.c b/tools/virtio/ringtest/main.c
index 147abb4..f31353f 100644
--- a/tools/virtio/ringtest/main.c
+++ b/tools/virtio/ringtest/main.c
@@ -96,7 +96,13 @@ void set_affinity(const char *arg)
assert(!ret);
}
-static void run_guest(void)
+void poll_used(void)
+{
+ while (used_empty())
+ busy_wait();
+}
+
+static void __attribute__((__flatten__)) run_guest(void)
{
int completed_before;
int completed = 0;
@@ -141,7 +147,7 @@ static void run_guest(void)
assert(completed <= bufs);
assert(started <= bufs);
if (do_sleep) {
- if (enable_call())
+ if (used_empty() && enable_call())
wait_for_call();
} else {
poll_used();
@@ -149,7 +155,13 @@ static void run_guest(void)
}
}
-static void run_host(void)
+void poll_avail(void)
+{
+ while (avail_empty())
+ busy_wait();
+}
+
+static void __attribute__((__flatten__)) run_host(void)
{
int completed_before;
int completed = 0;
@@ -160,7 +172,7 @@ static void run_host(void)
for (;;) {
if (do_sleep) {
- if (enable_kick())
+ if (avail_empty() && enable_kick())
wait_for_kick();
} else {
poll_avail();
diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h
index 16917ac..34e63cc 100644
--- a/tools/virtio/ringtest/main.h
+++ b/tools/virtio/ringtest/main.h
@@ -56,15 +56,15 @@ void alloc_ring(void);
int add_inbuf(unsigned, void *, void *);
void *get_buf(unsigned *, void **);
void disable_call();
+bool used_empty();
bool enable_call();
void kick_available();
-void poll_used();
/* host side */
void disable_kick();
+bool avail_empty();
bool enable_kick();
bool use_buf(unsigned *, void **);
void call_used();
-void poll_avail();
/* implemented by main */
extern bool do_sleep;
diff --git a/tools/virtio/ringtest/noring.c b/tools/virtio/ringtest/noring.c
index eda2f48..b8d1c1d 100644
--- a/tools/virtio/ringtest/noring.c
+++ b/tools/virtio/ringtest/noring.c
@@ -24,8 +24,9 @@ void *get_buf(unsigned *lenp, void **bufp)
return "Buffer";
}
-void poll_used(void)
+bool used_empty()
{
+ return false;
}
void disable_call()
@@ -54,8 +55,9 @@ bool enable_kick()
assert(0);
}
-void poll_avail(void)
+bool avail_empty()
{
+ return false;
}
bool use_buf(unsigned *lenp, void **bufp)
diff --git a/tools/virtio/ringtest/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c
index bd2ad1d..635b07b 100644
--- a/tools/virtio/ringtest/ptr_ring.c
+++ b/tools/virtio/ringtest/ptr_ring.c
@@ -133,18 +133,9 @@ void *get_buf(unsigned *lenp, void **bufp)
return datap;
}
-void poll_used(void)
+bool used_empty()
{
- void *b;
-
- do {
- if (tailcnt == headcnt || __ptr_ring_full(&array)) {
- b = NULL;
- barrier();
- } else {
- b = "Buffer\n";
- }
- } while (!b);
+ return (tailcnt == headcnt || __ptr_ring_full(&array));
}
void disable_call()
@@ -173,14 +164,9 @@ bool enable_kick()
assert(0);
}
-void poll_avail(void)
+bool avail_empty()
{
- void *b;
-
- do {
- barrier();
- b = __ptr_ring_peek(&array);
- } while (!b);
+ return !__ptr_ring_peek(&array);
}
bool use_buf(unsigned *lenp, void **bufp)
diff --git a/tools/virtio/ringtest/ring.c b/tools/virtio/ringtest/ring.c
index c25c8d2..747c5dd 100644
--- a/tools/virtio/ringtest/ring.c
+++ b/tools/virtio/ringtest/ring.c
@@ -163,12 +163,11 @@ void *get_buf(unsigned *lenp, void **bufp)
return datap;
}
-void poll_used(void)
+bool used_empty()
{
unsigned head = (ring_size - 1) & guest.last_used_idx;
- while (ring[head].flags & DESC_HW)
- busy_wait();
+ return (ring[head].flags & DESC_HW);
}
void disable_call()
@@ -180,13 +179,11 @@ void disable_call()
bool enable_call()
{
- unsigned head = (ring_size - 1) & guest.last_used_idx;
-
event->call_index = guest.last_used_idx;
/* Flush call index write */
/* Barrier D (for pairing) */
smp_mb();
- return ring[head].flags & DESC_HW;
+ return used_empty();
}
void kick_available(void)
@@ -213,20 +210,17 @@ void disable_kick()
bool enable_kick()
{
- unsigned head = (ring_size - 1) & host.used_idx;
-
event->kick_index = host.used_idx;
/* Barrier C (for pairing) */
smp_mb();
- return !(ring[head].flags & DESC_HW);
+ return avail_empty();
}
-void poll_avail(void)
+bool avail_empty()
{
unsigned head = (ring_size - 1) & host.used_idx;
- while (!(ring[head].flags & DESC_HW))
- busy_wait();
+ return !(ring[head].flags & DESC_HW);
}
bool use_buf(unsigned *lenp, void **bufp)
diff --git a/tools/virtio/ringtest/virtio_ring_0_9.c b/tools/virtio/ringtest/virtio_ring_0_9.c
index 7618662..bbc3043 100644
--- a/tools/virtio/ringtest/virtio_ring_0_9.c
+++ b/tools/virtio/ringtest/virtio_ring_0_9.c
@@ -194,24 +194,16 @@ void *get_buf(unsigned *lenp, void **bufp)
return datap;
}
-void poll_used(void)
+bool used_empty()
{
+ unsigned short last_used_idx = guest.last_used_idx;
#ifdef RING_POLL
- unsigned head = (ring_size - 1) & guest.last_used_idx;
+ unsigned short head = last_used_idx & (ring_size - 1);
+ unsigned index = ring.used->ring[head].id;
- for (;;) {
- unsigned index = ring.used->ring[head].id;
-
- if ((index ^ guest.last_used_idx ^ 0x8000) & ~(ring_size - 1))
- busy_wait();
- else
- break;
- }
+ return (index ^ last_used_idx ^ 0x8000) & ~(ring_size - 1);
#else
- unsigned head = guest.last_used_idx;
-
- while (ring.used->idx == head)
- busy_wait();
+ return ring.used->idx == last_used_idx;
#endif
}
@@ -224,22 +216,11 @@ void disable_call()
bool enable_call()
{
- unsigned short last_used_idx;
-
- vring_used_event(&ring) = (last_used_idx = guest.last_used_idx);
+ vring_used_event(&ring) = guest.last_used_idx;
/* Flush call index write */
/* Barrier D (for pairing) */
smp_mb();
-#ifdef RING_POLL
- {
- unsigned short head = last_used_idx & (ring_size - 1);
- unsigned index = ring.used->ring[head].id;
-
- return (index ^ last_used_idx ^ 0x8000) & ~(ring_size - 1);
- }
-#else
- return ring.used->idx == last_used_idx;
-#endif
+ return used_empty();
}
void kick_available(void)
@@ -266,36 +247,21 @@ void disable_kick()
bool enable_kick()
{
- unsigned head = host.used_idx;
-
- vring_avail_event(&ring) = head;
+ vring_avail_event(&ring) = host.used_idx;
/* Barrier C (for pairing) */
smp_mb();
-#ifdef RING_POLL
- {
- unsigned index = ring.avail->ring[head & (ring_size - 1)];
-
- return (index ^ head ^ 0x8000) & ~(ring_size - 1);
- }
-#else
- return head == ring.avail->idx;
-#endif
+ return avail_empty();
}
-void poll_avail(void)
+bool avail_empty()
{
unsigned head = host.used_idx;
#ifdef RING_POLL
- for (;;) {
- unsigned index = ring.avail->ring[head & (ring_size - 1)];
- if ((index ^ head ^ 0x8000) & ~(ring_size - 1))
- busy_wait();
- else
- break;
- }
+ unsigned index = ring.avail->ring[head & (ring_size - 1)];
+
+ return ((index ^ head ^ 0x8000) & ~(ring_size - 1));
#else
- while (ring.avail->idx == head)
- busy_wait();
+ return head == ring.avail->idx;
#endif
}
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index e18b30d..ebe1b9f 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -453,17 +453,33 @@ struct vgic_io_device *kvm_to_vgic_iodev(const struct kvm_io_device *dev)
return container_of(dev, struct vgic_io_device, dev);
}
-static bool check_region(const struct vgic_register_region *region,
+static bool check_region(const struct kvm *kvm,
+ const struct vgic_register_region *region,
gpa_t addr, int len)
{
- if ((region->access_flags & VGIC_ACCESS_8bit) && len == 1)
- return true;
- if ((region->access_flags & VGIC_ACCESS_32bit) &&
- len == sizeof(u32) && !(addr & 3))
- return true;
- if ((region->access_flags & VGIC_ACCESS_64bit) &&
- len == sizeof(u64) && !(addr & 7))
- return true;
+ int flags, nr_irqs = kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS;
+
+ switch (len) {
+ case sizeof(u8):
+ flags = VGIC_ACCESS_8bit;
+ break;
+ case sizeof(u32):
+ flags = VGIC_ACCESS_32bit;
+ break;
+ case sizeof(u64):
+ flags = VGIC_ACCESS_64bit;
+ break;
+ default:
+ return false;
+ }
+
+ if ((region->access_flags & flags) && IS_ALIGNED(addr, len)) {
+ if (!region->bits_per_irq)
+ return true;
+
+ /* Do we access a non-allocated IRQ? */
+ return VGIC_ADDR_TO_INTID(addr, region->bits_per_irq) < nr_irqs;
+ }
return false;
}
@@ -477,7 +493,7 @@ static int dispatch_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions,
addr - iodev->base_addr);
- if (!region || !check_region(region, addr, len)) {
+ if (!region || !check_region(vcpu->kvm, region, addr, len)) {
memset(val, 0, len);
return 0;
}
@@ -510,10 +526,7 @@ static int dispatch_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions,
addr - iodev->base_addr);
- if (!region)
- return 0;
-
- if (!check_region(region, addr, len))
+ if (!region || !check_region(vcpu->kvm, region, addr, len))
return 0;
switch (iodev->iodev_type) {
diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h
index 4c34d39..84961b4 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.h
+++ b/virt/kvm/arm/vgic/vgic-mmio.h
@@ -50,15 +50,15 @@ extern struct kvm_io_device_ops kvm_io_gic_ops;
#define VGIC_ADDR_IRQ_MASK(bits) (((bits) * 1024 / 8) - 1)
/*
- * (addr & mask) gives us the byte offset for the INT ID, so we want to
- * divide this with 'bytes per irq' to get the INT ID, which is given
- * by '(bits) / 8'. But we do this with fixed-point-arithmetic and
- * take advantage of the fact that division by a fraction equals
- * multiplication with the inverted fraction, and scale up both the
- * numerator and denominator with 8 to support at most 64 bits per IRQ:
+ * (addr & mask) gives us the _byte_ offset for the INT ID.
+ * We multiply this by 8 the get the _bit_ offset, then divide this by
+ * the number of bits to learn the actual INT ID.
+ * But instead of a division (which requires a "long long div" implementation),
+ * we shift by the binary logarithm of <bits>.
+ * This assumes that <bits> is a power of two.
*/
#define VGIC_ADDR_TO_INTID(addr, bits) (((addr) & VGIC_ADDR_IRQ_MASK(bits)) * \
- 64 / (bits) / 8)
+ 8 >> ilog2(bits))
/*
* Some VGIC registers store per-IRQ information, with a different number
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index 2893d5b..6440b56 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -273,6 +273,18 @@ bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq)
* no more work for us to do.
*/
spin_unlock(&irq->irq_lock);
+
+ /*
+ * We have to kick the VCPU here, because we could be
+ * queueing an edge-triggered interrupt for which we
+ * get no EOI maintenance interrupt. In that case,
+ * while the IRQ is already on the VCPU's AP list, the
+ * VCPU could have EOI'ed the original interrupt and
+ * won't see this one until it exits for some other
+ * reason.
+ */
+ if (vcpu)
+ kvm_vcpu_kick(vcpu);
return false;
}
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index db96688..8035cc1 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -84,7 +84,8 @@ static void async_pf_execute(struct work_struct *work)
* mm and might be done in another context, so we must
* use FOLL_REMOTE.
*/
- __get_user_pages_unlocked(NULL, mm, addr, 1, 1, 0, NULL, FOLL_REMOTE);
+ __get_user_pages_unlocked(NULL, mm, addr, 1, NULL,
+ FOLL_WRITE | FOLL_REMOTE);
kvm_async_page_present_sync(vcpu, apf);
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index f397e9b..a29786d 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -42,6 +42,7 @@
#ifdef CONFIG_HAVE_KVM_IRQFD
+static struct workqueue_struct *irqfd_cleanup_wq;
static void
irqfd_inject(struct work_struct *work)
@@ -167,7 +168,7 @@ irqfd_deactivate(struct kvm_kernel_irqfd *irqfd)
list_del_init(&irqfd->list);
- schedule_work(&irqfd->shutdown);
+ queue_work(irqfd_cleanup_wq, &irqfd->shutdown);
}
int __attribute__((weak)) kvm_arch_set_irq_inatomic(
@@ -554,7 +555,7 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args)
* so that we guarantee there will not be any more interrupts on this
* gsi once this deassign function returns.
*/
- flush_work(&irqfd->shutdown);
+ flush_workqueue(irqfd_cleanup_wq);
return 0;
}
@@ -591,7 +592,7 @@ kvm_irqfd_release(struct kvm *kvm)
* Block until we know all outstanding shutdown jobs have completed
* since we do not take a kvm* reference.
*/
- flush_work(&irqfd->shutdown);
+ flush_workqueue(irqfd_cleanup_wq);
}
@@ -621,8 +622,23 @@ void kvm_irq_routing_update(struct kvm *kvm)
spin_unlock_irq(&kvm->irqfds.lock);
}
+/*
+ * create a host-wide workqueue for issuing deferred shutdown requests
+ * aggregated from all vm* instances. We need our own isolated
+ * queue to ease flushing work items when a VM exits.
+ */
+int kvm_irqfd_init(void)
+{
+ irqfd_cleanup_wq = alloc_workqueue("kvm-irqfd-cleanup", 0, 0);
+ if (!irqfd_cleanup_wq)
+ return -ENOMEM;
+
+ return 0;
+}
+
void kvm_irqfd_exit(void)
{
+ destroy_workqueue(irqfd_cleanup_wq);
}
#endif
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 81dfc73..5c36034 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1346,21 +1346,19 @@ unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *w
static int get_user_page_nowait(unsigned long start, int write,
struct page **page)
{
- int flags = FOLL_TOUCH | FOLL_NOWAIT | FOLL_HWPOISON | FOLL_GET;
+ int flags = FOLL_NOWAIT | FOLL_HWPOISON;
if (write)
flags |= FOLL_WRITE;
- return __get_user_pages(current, current->mm, start, 1, flags, page,
- NULL, NULL);
+ return get_user_pages(start, 1, flags, page, NULL);
}
static inline int check_user_page_hwpoison(unsigned long addr)
{
- int rc, flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_WRITE;
+ int rc, flags = FOLL_HWPOISON | FOLL_WRITE;
- rc = __get_user_pages(current, current->mm, addr, 1,
- flags, NULL, NULL, NULL);
+ rc = get_user_pages(addr, 1, flags, NULL, NULL);
return rc == -EHWPOISON;
}
@@ -1416,10 +1414,15 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
down_read(¤t->mm->mmap_sem);
npages = get_user_page_nowait(addr, write_fault, page);
up_read(¤t->mm->mmap_sem);
- } else
+ } else {
+ unsigned int flags = FOLL_TOUCH | FOLL_HWPOISON;
+
+ if (write_fault)
+ flags |= FOLL_WRITE;
+
npages = __get_user_pages_unlocked(current, current->mm, addr, 1,
- write_fault, 0, page,
- FOLL_TOUCH|FOLL_HWPOISON);
+ page, flags);
+ }
if (npages != 1)
return npages;
@@ -3841,7 +3844,12 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
* kvm_arch_init makes sure there's at most one caller
* for architectures that support multiple implementations,
* like intel and amd on x86.
+ * kvm_arch_init must be called before kvm_irqfd_init to avoid creating
+ * conflicts in case kvm is already setup for another implementation.
*/
+ r = kvm_irqfd_init();
+ if (r)
+ goto out_irqfd;
if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) {
r = -ENOMEM;
@@ -3923,6 +3931,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
free_cpumask_var(cpus_hardware_enabled);
out_free_0:
kvm_irqfd_exit();
+out_irqfd:
kvm_arch_exit();
out_fail:
return r;