Merge branch 'master' of git://1984.lsi.us.es/nf-next
Pablo says:
====================
This is the second batch of Netfilter updates for net-next. It contains the
kernel changes for the new user-space connection tracking helper
infrastructure.
More details on this infrastructure are provides here:
http://lwn.net/Articles/500196/
Still, I plan to provide some official documentation through the
conntrack-tools user manual on how to setup user-space utilities for this.
So far, it provides two helper in user-space, one for NFSv3 and another for
Oracle/SQLnet/TNS. Yet in my TODO list.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt
new file mode 100644
index 0000000..ae8af16
--- /dev/null
+++ b/Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt
@@ -0,0 +1,93 @@
+Pinctrl-based I2C Bus Mux
+
+This binding describes an I2C bus multiplexer that uses pin multiplexing to
+route the I2C signals, and represents the pin multiplexing configuration
+using the pinctrl device tree bindings.
+
+ +-----+ +-----+
+ | dev | | dev |
+ +------------------------+ +-----+ +-----+
+ | SoC | | |
+ | /----|------+--------+
+ | +---+ +------+ | child bus A, on first set of pins
+ | |I2C|---|Pinmux| |
+ | +---+ +------+ | child bus B, on second set of pins
+ | \----|------+--------+--------+
+ | | | | |
+ +------------------------+ +-----+ +-----+ +-----+
+ | dev | | dev | | dev |
+ +-----+ +-----+ +-----+
+
+Required properties:
+- compatible: i2c-mux-pinctrl
+- i2c-parent: The phandle of the I2C bus that this multiplexer's master-side
+ port is connected to.
+
+Also required are:
+
+* Standard pinctrl properties that specify the pin mux state for each child
+ bus. See ../pinctrl/pinctrl-bindings.txt.
+
+* Standard I2C mux properties. See mux.txt in this directory.
+
+* I2C child bus nodes. See mux.txt in this directory.
+
+For each named state defined in the pinctrl-names property, an I2C child bus
+will be created. I2C child bus numbers are assigned based on the index into
+the pinctrl-names property.
+
+The only exception is that no bus will be created for a state named "idle". If
+such a state is defined, it must be the last entry in pinctrl-names. For
+example:
+
+ pinctrl-names = "ddc", "pta", "idle" -> ddc = bus 0, pta = bus 1
+ pinctrl-names = "ddc", "idle", "pta" -> Invalid ("idle" not last)
+ pinctrl-names = "idle", "ddc", "pta" -> Invalid ("idle" not last)
+
+Whenever an access is made to a device on a child bus, the relevant pinctrl
+state will be programmed into hardware.
+
+If an idle state is defined, whenever an access is not being made to a device
+on a child bus, the idle pinctrl state will be programmed into hardware.
+
+If an idle state is not defined, the most recently used pinctrl state will be
+left programmed into hardware whenever no access is being made of a device on
+a child bus.
+
+Example:
+
+ i2cmux {
+ compatible = "i2c-mux-pinctrl";
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ i2c-parent = <&i2c1>;
+
+ pinctrl-names = "ddc", "pta", "idle";
+ pinctrl-0 = <&state_i2cmux_ddc>;
+ pinctrl-1 = <&state_i2cmux_pta>;
+ pinctrl-2 = <&state_i2cmux_idle>;
+
+ i2c@0 {
+ reg = <0>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ eeprom {
+ compatible = "eeprom";
+ reg = <0x50>;
+ };
+ };
+
+ i2c@1 {
+ reg = <1>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ eeprom {
+ compatible = "eeprom";
+ reg = <0x50>;
+ };
+ };
+ };
+
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index c45513d..a92c5eb 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2543,6 +2543,15 @@
sched_debug [KNL] Enables verbose scheduler debug messages.
+ skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate
+ xtime_lock contention on larger systems, and/or RCU lock
+ contention on all systems with CONFIG_MAXSMP set.
+ Format: { "0" | "1" }
+ 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1"
+ 1 -- enable.
+ Note: increases power consumption, thus should only be
+ enabled if running jitter sensitive (HPC/RT) workloads.
+
security= [SECURITY] Choose a security module to enable at boot.
If this boot parameter is not specified, only the first
security module asking for security registration will be
diff --git a/Documentation/vm/frontswap.txt b/Documentation/vm/frontswap.txt
new file mode 100644
index 0000000..37067cf
--- /dev/null
+++ b/Documentation/vm/frontswap.txt
@@ -0,0 +1,278 @@
+Frontswap provides a "transcendent memory" interface for swap pages.
+In some environments, dramatic performance savings may be obtained because
+swapped pages are saved in RAM (or a RAM-like device) instead of a swap disk.
+
+(Note, frontswap -- and cleancache (merged at 3.0) -- are the "frontends"
+and the only necessary changes to the core kernel for transcendent memory;
+all other supporting code -- the "backends" -- is implemented as drivers.
+See the LWN.net article "Transcendent memory in a nutshell" for a detailed
+overview of frontswap and related kernel parts:
+https://lwn.net/Articles/454795/ )
+
+Frontswap is so named because it can be thought of as the opposite of
+a "backing" store for a swap device. The storage is assumed to be
+a synchronous concurrency-safe page-oriented "pseudo-RAM device" conforming
+to the requirements of transcendent memory (such as Xen's "tmem", or
+in-kernel compressed memory, aka "zcache", or future RAM-like devices);
+this pseudo-RAM device is not directly accessible or addressable by the
+kernel and is of unknown and possibly time-varying size. The driver
+links itself to frontswap by calling frontswap_register_ops to set the
+frontswap_ops funcs appropriately and the functions it provides must
+conform to certain policies as follows:
+
+An "init" prepares the device to receive frontswap pages associated
+with the specified swap device number (aka "type"). A "store" will
+copy the page to transcendent memory and associate it with the type and
+offset associated with the page. A "load" will copy the page, if found,
+from transcendent memory into kernel memory, but will NOT remove the page
+from from transcendent memory. An "invalidate_page" will remove the page
+from transcendent memory and an "invalidate_area" will remove ALL pages
+associated with the swap type (e.g., like swapoff) and notify the "device"
+to refuse further stores with that swap type.
+
+Once a page is successfully stored, a matching load on the page will normally
+succeed. So when the kernel finds itself in a situation where it needs
+to swap out a page, it first attempts to use frontswap. If the store returns
+success, the data has been successfully saved to transcendent memory and
+a disk write and, if the data is later read back, a disk read are avoided.
+If a store returns failure, transcendent memory has rejected the data, and the
+page can be written to swap as usual.
+
+If a backend chooses, frontswap can be configured as a "writethrough
+cache" by calling frontswap_writethrough(). In this mode, the reduction
+in swap device writes is lost (and also a non-trivial performance advantage)
+in order to allow the backend to arbitrarily "reclaim" space used to
+store frontswap pages to more completely manage its memory usage.
+
+Note that if a page is stored and the page already exists in transcendent memory
+(a "duplicate" store), either the store succeeds and the data is overwritten,
+or the store fails AND the page is invalidated. This ensures stale data may
+never be obtained from frontswap.
+
+If properly configured, monitoring of frontswap is done via debugfs in
+the /sys/kernel/debug/frontswap directory. The effectiveness of
+frontswap can be measured (across all swap devices) with:
+
+failed_stores - how many store attempts have failed
+loads - how many loads were attempted (all should succeed)
+succ_stores - how many store attempts have succeeded
+invalidates - how many invalidates were attempted
+
+A backend implementation may provide additional metrics.
+
+FAQ
+
+1) Where's the value?
+
+When a workload starts swapping, performance falls through the floor.
+Frontswap significantly increases performance in many such workloads by
+providing a clean, dynamic interface to read and write swap pages to
+"transcendent memory" that is otherwise not directly addressable to the kernel.
+This interface is ideal when data is transformed to a different form
+and size (such as with compression) or secretly moved (as might be
+useful for write-balancing for some RAM-like devices). Swap pages (and
+evicted page-cache pages) are a great use for this kind of slower-than-RAM-
+but-much-faster-than-disk "pseudo-RAM device" and the frontswap (and
+cleancache) interface to transcendent memory provides a nice way to read
+and write -- and indirectly "name" -- the pages.
+
+Frontswap -- and cleancache -- with a fairly small impact on the kernel,
+provides a huge amount of flexibility for more dynamic, flexible RAM
+utilization in various system configurations:
+
+In the single kernel case, aka "zcache", pages are compressed and
+stored in local memory, thus increasing the total anonymous pages
+that can be safely kept in RAM. Zcache essentially trades off CPU
+cycles used in compression/decompression for better memory utilization.
+Benchmarks have shown little or no impact when memory pressure is
+low while providing a significant performance improvement (25%+)
+on some workloads under high memory pressure.
+
+"RAMster" builds on zcache by adding "peer-to-peer" transcendent memory
+support for clustered systems. Frontswap pages are locally compressed
+as in zcache, but then "remotified" to another system's RAM. This
+allows RAM to be dynamically load-balanced back-and-forth as needed,
+i.e. when system A is overcommitted, it can swap to system B, and
+vice versa. RAMster can also be configured as a memory server so
+many servers in a cluster can swap, dynamically as needed, to a single
+server configured with a large amount of RAM... without pre-configuring
+how much of the RAM is available for each of the clients!
+
+In the virtual case, the whole point of virtualization is to statistically
+multiplex physical resources acrosst the varying demands of multiple
+virtual machines. This is really hard to do with RAM and efforts to do
+it well with no kernel changes have essentially failed (except in some
+well-publicized special-case workloads).
+Specifically, the Xen Transcendent Memory backend allows otherwise
+"fallow" hypervisor-owned RAM to not only be "time-shared" between multiple
+virtual machines, but the pages can be compressed and deduplicated to
+optimize RAM utilization. And when guest OS's are induced to surrender
+underutilized RAM (e.g. with "selfballooning"), sudden unexpected
+memory pressure may result in swapping; frontswap allows those pages
+to be swapped to and from hypervisor RAM (if overall host system memory
+conditions allow), thus mitigating the potentially awful performance impact
+of unplanned swapping.
+
+A KVM implementation is underway and has been RFC'ed to lkml. And,
+using frontswap, investigation is also underway on the use of NVM as
+a memory extension technology.
+
+2) Sure there may be performance advantages in some situations, but
+ what's the space/time overhead of frontswap?
+
+If CONFIG_FRONTSWAP is disabled, every frontswap hook compiles into
+nothingness and the only overhead is a few extra bytes per swapon'ed
+swap device. If CONFIG_FRONTSWAP is enabled but no frontswap "backend"
+registers, there is one extra global variable compared to zero for
+every swap page read or written. If CONFIG_FRONTSWAP is enabled
+AND a frontswap backend registers AND the backend fails every "store"
+request (i.e. provides no memory despite claiming it might),
+CPU overhead is still negligible -- and since every frontswap fail
+precedes a swap page write-to-disk, the system is highly likely
+to be I/O bound and using a small fraction of a percent of a CPU
+will be irrelevant anyway.
+
+As for space, if CONFIG_FRONTSWAP is enabled AND a frontswap backend
+registers, one bit is allocated for every swap page for every swap
+device that is swapon'd. This is added to the EIGHT bits (which
+was sixteen until about 2.6.34) that the kernel already allocates
+for every swap page for every swap device that is swapon'd. (Hugh
+Dickins has observed that frontswap could probably steal one of
+the existing eight bits, but let's worry about that minor optimization
+later.) For very large swap disks (which are rare) on a standard
+4K pagesize, this is 1MB per 32GB swap.
+
+When swap pages are stored in transcendent memory instead of written
+out to disk, there is a side effect that this may create more memory
+pressure that can potentially outweigh the other advantages. A
+backend, such as zcache, must implement policies to carefully (but
+dynamically) manage memory limits to ensure this doesn't happen.
+
+3) OK, how about a quick overview of what this frontswap patch does
+ in terms that a kernel hacker can grok?
+
+Let's assume that a frontswap "backend" has registered during
+kernel initialization; this registration indicates that this
+frontswap backend has access to some "memory" that is not directly
+accessible by the kernel. Exactly how much memory it provides is
+entirely dynamic and random.
+
+Whenever a swap-device is swapon'd frontswap_init() is called,
+passing the swap device number (aka "type") as a parameter.
+This notifies frontswap to expect attempts to "store" swap pages
+associated with that number.
+
+Whenever the swap subsystem is readying a page to write to a swap
+device (c.f swap_writepage()), frontswap_store is called. Frontswap
+consults with the frontswap backend and if the backend says it does NOT
+have room, frontswap_store returns -1 and the kernel swaps the page
+to the swap device as normal. Note that the response from the frontswap
+backend is unpredictable to the kernel; it may choose to never accept a
+page, it could accept every ninth page, or it might accept every
+page. But if the backend does accept a page, the data from the page
+has already been copied and associated with the type and offset,
+and the backend guarantees the persistence of the data. In this case,
+frontswap sets a bit in the "frontswap_map" for the swap device
+corresponding to the page offset on the swap device to which it would
+otherwise have written the data.
+
+When the swap subsystem needs to swap-in a page (swap_readpage()),
+it first calls frontswap_load() which checks the frontswap_map to
+see if the page was earlier accepted by the frontswap backend. If
+it was, the page of data is filled from the frontswap backend and
+the swap-in is complete. If not, the normal swap-in code is
+executed to obtain the page of data from the real swap device.
+
+So every time the frontswap backend accepts a page, a swap device read
+and (potentially) a swap device write are replaced by a "frontswap backend
+store" and (possibly) a "frontswap backend loads", which are presumably much
+faster.
+
+4) Can't frontswap be configured as a "special" swap device that is
+ just higher priority than any real swap device (e.g. like zswap,
+ or maybe swap-over-nbd/NFS)?
+
+No. First, the existing swap subsystem doesn't allow for any kind of
+swap hierarchy. Perhaps it could be rewritten to accomodate a hierarchy,
+but this would require fairly drastic changes. Even if it were
+rewritten, the existing swap subsystem uses the block I/O layer which
+assumes a swap device is fixed size and any page in it is linearly
+addressable. Frontswap barely touches the existing swap subsystem,
+and works around the constraints of the block I/O subsystem to provide
+a great deal of flexibility and dynamicity.
+
+For example, the acceptance of any swap page by the frontswap backend is
+entirely unpredictable. This is critical to the definition of frontswap
+backends because it grants completely dynamic discretion to the
+backend. In zcache, one cannot know a priori how compressible a page is.
+"Poorly" compressible pages can be rejected, and "poorly" can itself be
+defined dynamically depending on current memory constraints.
+
+Further, frontswap is entirely synchronous whereas a real swap
+device is, by definition, asynchronous and uses block I/O. The
+block I/O layer is not only unnecessary, but may perform "optimizations"
+that are inappropriate for a RAM-oriented device including delaying
+the write of some pages for a significant amount of time. Synchrony is
+required to ensure the dynamicity of the backend and to avoid thorny race
+conditions that would unnecessarily and greatly complicate frontswap
+and/or the block I/O subsystem. That said, only the initial "store"
+and "load" operations need be synchronous. A separate asynchronous thread
+is free to manipulate the pages stored by frontswap. For example,
+the "remotification" thread in RAMster uses standard asynchronous
+kernel sockets to move compressed frontswap pages to a remote machine.
+Similarly, a KVM guest-side implementation could do in-guest compression
+and use "batched" hypercalls.
+
+In a virtualized environment, the dynamicity allows the hypervisor
+(or host OS) to do "intelligent overcommit". For example, it can
+choose to accept pages only until host-swapping might be imminent,
+then force guests to do their own swapping.
+
+There is a downside to the transcendent memory specifications for
+frontswap: Since any "store" might fail, there must always be a real
+slot on a real swap device to swap the page. Thus frontswap must be
+implemented as a "shadow" to every swapon'd device with the potential
+capability of holding every page that the swap device might have held
+and the possibility that it might hold no pages at all. This means
+that frontswap cannot contain more pages than the total of swapon'd
+swap devices. For example, if NO swap device is configured on some
+installation, frontswap is useless. Swapless portable devices
+can still use frontswap but a backend for such devices must configure
+some kind of "ghost" swap device and ensure that it is never used.
+
+5) Why this weird definition about "duplicate stores"? If a page
+ has been previously successfully stored, can't it always be
+ successfully overwritten?
+
+Nearly always it can, but no, sometimes it cannot. Consider an example
+where data is compressed and the original 4K page has been compressed
+to 1K. Now an attempt is made to overwrite the page with data that
+is non-compressible and so would take the entire 4K. But the backend
+has no more space. In this case, the store must be rejected. Whenever
+frontswap rejects a store that would overwrite, it also must invalidate
+the old data and ensure that it is no longer accessible. Since the
+swap subsystem then writes the new data to the read swap device,
+this is the correct course of action to ensure coherency.
+
+6) What is frontswap_shrink for?
+
+When the (non-frontswap) swap subsystem swaps out a page to a real
+swap device, that page is only taking up low-value pre-allocated disk
+space. But if frontswap has placed a page in transcendent memory, that
+page may be taking up valuable real estate. The frontswap_shrink
+routine allows code outside of the swap subsystem to force pages out
+of the memory managed by frontswap and back into kernel-addressable memory.
+For example, in RAMster, a "suction driver" thread will attempt
+to "repatriate" pages sent to a remote machine back to the local machine;
+this is driven using the frontswap_shrink mechanism when memory pressure
+subsides.
+
+7) Why does the frontswap patch create the new include file swapfile.h?
+
+The frontswap code depends on some swap-subsystem-internal data
+structures that have, over the years, moved back and forth between
+static and global. This seemed a reasonable compromise: Define
+them as global but declare them in a new include file that isn't
+included by the large number of source files that include swap.h.
+
+Dan Magenheimer, last updated April 9, 2012
diff --git a/MAINTAINERS b/MAINTAINERS
index c5fd905..ae5a12a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1077,7 +1077,7 @@
ARM/SAMSUNG S5P SERIES Multi Format Codec (MFC) SUPPORT
M: Kyungmin Park <kyungmin.park@samsung.com>
M: Kamil Debski <k.debski@samsung.com>
-M: Jeongtae Park <jtp.park@samsung.com>
+M: Jeongtae Park <jtp.park@samsung.com>
L: linux-arm-kernel@lists.infradead.org
L: linux-media@vger.kernel.org
S: Maintained
@@ -1743,10 +1743,10 @@
CAPABILITIES
M: Serge Hallyn <serge.hallyn@canonical.com>
L: linux-security-module@vger.kernel.org
-S: Supported
+S: Supported
F: include/linux/capability.h
F: security/capability.c
-F: security/commoncap.c
+F: security/commoncap.c
F: kernel/capability.c
CELL BROADBAND ENGINE ARCHITECTURE
@@ -1800,6 +1800,9 @@
CFG80211 and NL80211
M: Johannes Berg <johannes@sipsolutions.net>
L: linux-wireless@vger.kernel.org
+W: http://wireless.kernel.org/
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git
S: Maintained
F: include/linux/nl80211.h
F: include/net/cfg80211.h
@@ -2146,11 +2149,11 @@
F: drivers/net/wan/pc300*
CYTTSP TOUCHSCREEN DRIVER
-M: Javier Martinez Canillas <javier@dowhile0.org>
-L: linux-input@vger.kernel.org
-S: Maintained
-F: drivers/input/touchscreen/cyttsp*
-F: include/linux/input/cyttsp.h
+M: Javier Martinez Canillas <javier@dowhile0.org>
+L: linux-input@vger.kernel.org
+S: Maintained
+F: drivers/input/touchscreen/cyttsp*
+F: include/linux/input/cyttsp.h
DAMA SLAVE for AX.25
M: Joerg Reuter <jreuter@yaina.de>
@@ -2270,7 +2273,7 @@
F: include/linux/dm-*.h
DIOLAN U2C-12 I2C DRIVER
-M: Guenter Roeck <guenter.roeck@ericsson.com>
+M: Guenter Roeck <linux@roeck-us.net>
L: linux-i2c@vger.kernel.org
S: Maintained
F: drivers/i2c/busses/i2c-diolan-u2c.c
@@ -2930,6 +2933,13 @@
F: include/linux/freezer.h
F: kernel/freezer.c
+FRONTSWAP API
+M: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+L: linux-kernel@vger.kernel.org
+S: Maintained
+F: mm/frontswap.c
+F: include/linux/frontswap.h
+
FS-CACHE: LOCAL CACHING FOR NETWORK FILESYSTEMS
M: David Howells <dhowells@redhat.com>
L: linux-cachefs@redhat.com
@@ -3138,7 +3148,7 @@
HARDWARE MONITORING
M: Jean Delvare <khali@linux-fr.org>
-M: Guenter Roeck <guenter.roeck@ericsson.com>
+M: Guenter Roeck <linux@roeck-us.net>
L: lm-sensors@lm-sensors.org
W: http://www.lm-sensors.org/
T: quilt kernel.org/pub/linux/kernel/people/jdelvare/linux-2.6/jdelvare-hwmon/
@@ -4096,6 +4106,8 @@
LED SUBSYSTEM
M: Bryan Wu <bryan.wu@canonical.com>
M: Richard Purdie <rpurdie@rpsys.net>
+L: linux-leds@vger.kernel.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/cooloney/linux-leds.git
S: Maintained
F: drivers/leds/
F: include/linux/leds.h
@@ -4340,7 +4352,8 @@
M: Johannes Berg <johannes@sipsolutions.net>
L: linux-wireless@vger.kernel.org
W: http://wireless.kernel.org/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git
S: Maintained
F: Documentation/networking/mac80211-injection.txt
F: include/net/mac80211.h
@@ -4351,7 +4364,8 @@
M: Mattias Nissler <mattias.nissler@gmx.de>
L: linux-wireless@vger.kernel.org
W: http://wireless.kernel.org/en/developers/Documentation/mac80211/RateControl/PID
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git
S: Maintained
F: net/mac80211/rc80211_pid*
@@ -4411,6 +4425,13 @@
F: drivers/video/matrox/matroxfb_*
F: include/linux/matroxfb.h
+MAX16065 HARDWARE MONITOR DRIVER
+M: Guenter Roeck <linux@roeck-us.net>
+L: lm-sensors@lm-sensors.org
+S: Maintained
+F: Documentation/hwmon/max16065
+F: drivers/hwmon/max16065.c
+
MAX6650 HARDWARE MONITOR AND FAN CONTROLLER DRIVER
M: "Hans J. Koch" <hjk@hansjkoch.de>
L: lm-sensors@lm-sensors.org
@@ -5149,7 +5170,7 @@
F: include/linux/leds-pca9532.h
PCA9541 I2C BUS MASTER SELECTOR DRIVER
-M: Guenter Roeck <guenter.roeck@ericsson.com>
+M: Guenter Roeck <linux@roeck-us.net>
L: linux-i2c@vger.kernel.org
S: Maintained
F: drivers/i2c/muxes/i2c-mux-pca9541.c
@@ -5169,7 +5190,7 @@
F: drivers/firmware/pcdp.*
PCI ERROR RECOVERY
-M: Linas Vepstas <linasvepstas@gmail.com>
+M: Linas Vepstas <linasvepstas@gmail.com>
L: linux-pci@vger.kernel.org
S: Supported
F: Documentation/PCI/pci-error-recovery.txt
@@ -5299,7 +5320,7 @@
F: drivers/rtc/rtc-puv3.c
PMBUS HARDWARE MONITORING DRIVERS
-M: Guenter Roeck <guenter.roeck@ericsson.com>
+M: Guenter Roeck <linux@roeck-us.net>
L: lm-sensors@lm-sensors.org
W: http://www.lm-sensors.org/
W: http://www.roeck-us.net/linux/drivers/
@@ -5695,6 +5716,9 @@
RFKILL
M: Johannes Berg <johannes@sipsolutions.net>
L: linux-wireless@vger.kernel.org
+W: http://wireless.kernel.org/
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git
S: Maintained
F: Documentation/rfkill.txt
F: net/rfkill/
@@ -7291,11 +7315,11 @@
F: drivers/uio/
F: include/linux/uio*.h
-UTIL-LINUX-NG PACKAGE
+UTIL-LINUX PACKAGE
M: Karel Zak <kzak@redhat.com>
-L: util-linux-ng@vger.kernel.org
-W: http://kernel.org/~kzak/util-linux-ng/
-T: git git://git.kernel.org/pub/scm/utils/util-linux-ng/util-linux-ng.git
+L: util-linux@vger.kernel.org
+W: http://en.wikipedia.org/wiki/Util-linux
+T: git git://git.kernel.org/pub/scm/utils/util-linux/util-linux.git
S: Maintained
UVESAFB DRIVER
diff --git a/Makefile b/Makefile
index 0d718ed..d845c2a 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 3
PATCHLEVEL = 5
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
NAME = Saber-toothed Squirrel
# *DOCUMENTATION*
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index b649c59..84449dd 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -7,7 +7,6 @@
select HAVE_IDE if PCI || ISA || PCMCIA
select HAVE_DMA_ATTRS
select HAVE_DMA_CONTIGUOUS if (CPU_V6 || CPU_V6K || CPU_V7)
- select CMA if (CPU_V6 || CPU_V6K || CPU_V7)
select HAVE_MEMBLOCK
select RTC_LIB
select SYS_SUPPORTS_APM_EMULATION
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 54d49dd..5fb47a1 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -271,9 +271,9 @@
goto err;
}
- r = omap_device_register(pdev);
+ r = platform_device_add(pdev);
if (r) {
- pr_err("Could not register omap_device for %s\n", pdev_name);
+ pr_err("Could not register platform_device for %s\n", pdev_name);
goto err;
}
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index f31383c..df33909 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -186,6 +186,12 @@
help
This enables build of the TMU timer driver.
+config EM_TIMER_STI
+ bool "STI timer driver"
+ default y
+ help
+ This enables build of the STI timer driver.
+
endmenu
config SH_CLK_CPG
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ea6b431..106c4c0 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -268,10 +268,8 @@
unsigned long base = consistent_base;
unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT;
-#ifndef CONFIG_ARM_DMA_USE_IOMMU
- if (cpu_architecture() >= CPU_ARCH_ARMv6)
+ if (IS_ENABLED(CONFIG_CMA) && !IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU))
return 0;
-#endif
consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL);
if (!consistent_pte) {
@@ -342,7 +340,7 @@
struct page *page;
void *ptr;
- if (cpu_architecture() < CPU_ARCH_ARMv6)
+ if (!IS_ENABLED(CONFIG_CMA))
return 0;
ptr = __alloc_from_contiguous(NULL, size, prot, &page);
@@ -704,7 +702,7 @@
if (arch_is_coherent() || nommu())
addr = __alloc_simple_buffer(dev, size, gfp, &page);
- else if (cpu_architecture() < CPU_ARCH_ARMv6)
+ else if (!IS_ENABLED(CONFIG_CMA))
addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
else if (gfp & GFP_ATOMIC)
addr = __alloc_from_pool(dev, size, &page, caller);
@@ -773,7 +771,7 @@
if (arch_is_coherent() || nommu()) {
__dma_free_buffer(page, size);
- } else if (cpu_architecture() < CPU_ARCH_ARMv6) {
+ } else if (!IS_ENABLED(CONFIG_CMA)) {
__dma_free_remap(cpu_addr, size);
__dma_free_buffer(page, size);
} else {
diff --git a/arch/avr32/kernel/signal.c b/arch/avr32/kernel/signal.c
index c140f9b..d552a85 100644
--- a/arch/avr32/kernel/signal.c
+++ b/arch/avr32/kernel/signal.c
@@ -300,7 +300,7 @@
if ((sysreg_read(SR) & MODE_MASK) == MODE_SUPERVISOR)
syscall = 1;
- if (ti->flags & _TIF_SIGPENDING))
+ if (ti->flags & _TIF_SIGPENDING)
do_signal(regs, syscall);
if (ti->flags & _TIF_NOTIFY_RESUME) {
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index 2e3994b..62bcea7 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -173,7 +173,7 @@
unsigned long newsp;
#ifdef __ARCH_SYNC_CORE_DCACHE
- if (current->rt.nr_cpus_allowed == num_possible_cpus())
+ if (current->nr_cpus_allowed == num_possible_cpus())
set_cpus_allowed_ptr(current, cpumask_of(smp_processor_id()));
#endif
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index cac5b6b..1471201 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -7,6 +7,8 @@
select GENERIC_IRQ_SHOW
select ARCH_HAVE_NMI_SAFE_CMPXCHG if RMW_INSNS
select GENERIC_CPU_DEVICES
+ select GENERIC_STRNCPY_FROM_USER if MMU
+ select GENERIC_STRNLEN_USER if MMU
select FPU if MMU
select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 1a922fa..eafa253 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,2 +1,4 @@
include include/asm-generic/Kbuild.asm
header-y += cachectl.h
+
+generic-y += word-at-a-time.h
diff --git a/arch/m68k/include/asm/m528xsim.h b/arch/m68k/include/asm/m528xsim.h
index d63b99f..497c31c 100644
--- a/arch/m68k/include/asm/m528xsim.h
+++ b/arch/m68k/include/asm/m528xsim.h
@@ -86,7 +86,7 @@
/*
* QSPI module.
*/
-#define MCFQSPI_IOBASE (MCF_IPSBAR + 0x340)
+#define MCFQSPI_BASE (MCF_IPSBAR + 0x340)
#define MCFQSPI_SIZE 0x40
#define MCFQSPI_CS0 147
diff --git a/arch/m68k/include/asm/uaccess_mm.h b/arch/m68k/include/asm/uaccess_mm.h
index 9c80cd5..472c891 100644
--- a/arch/m68k/include/asm/uaccess_mm.h
+++ b/arch/m68k/include/asm/uaccess_mm.h
@@ -379,12 +379,15 @@
#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)
-long strncpy_from_user(char *dst, const char __user *src, long count);
-long strnlen_user(const char __user *src, long n);
+#define user_addr_max() \
+ (segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+
+extern long strncpy_from_user(char *dst, const char __user *src, long count);
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
+
unsigned long __clear_user(void __user *to, unsigned long n);
#define clear_user __clear_user
-#define strlen_user(str) strnlen_user(str, 32767)
-
#endif /* _M68K_UACCESS_H */
diff --git a/arch/m68k/kernel/ptrace.c b/arch/m68k/kernel/ptrace.c
index 8b4a222..1bc10e6 100644
--- a/arch/m68k/kernel/ptrace.c
+++ b/arch/m68k/kernel/ptrace.c
@@ -286,7 +286,7 @@
}
}
-#ifdef CONFIG_COLDFIRE
+#if defined(CONFIG_COLDFIRE) || !defined(CONFIG_MMU)
asmlinkage int syscall_trace_enter(void)
{
int ret = 0;
diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c
index d7deb7f..707f057 100644
--- a/arch/m68k/kernel/time.c
+++ b/arch/m68k/kernel/time.c
@@ -85,7 +85,7 @@
mach_sched_init(timer_interrupt);
}
-#ifdef CONFIG_M68KCLASSIC
+#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
u32 arch_gettimeoffset(void)
{
@@ -108,4 +108,4 @@
module_init(rtc_init);
-#endif /* CONFIG_M68KCLASSIC */
+#endif /* CONFIG_ARCH_USES_GETTIMEOFFSET */
diff --git a/arch/m68k/lib/uaccess.c b/arch/m68k/lib/uaccess.c
index 5664386..5e97f2e 100644
--- a/arch/m68k/lib/uaccess.c
+++ b/arch/m68k/lib/uaccess.c
@@ -104,80 +104,6 @@
EXPORT_SYMBOL(__generic_copy_to_user);
/*
- * Copy a null terminated string from userspace.
- */
-long strncpy_from_user(char *dst, const char __user *src, long count)
-{
- long res;
- char c;
-
- if (count <= 0)
- return count;
-
- asm volatile ("\n"
- "1: "MOVES".b (%2)+,%4\n"
- " move.b %4,(%1)+\n"
- " jeq 2f\n"
- " subq.l #1,%3\n"
- " jne 1b\n"
- "2: sub.l %3,%0\n"
- "3:\n"
- " .section .fixup,\"ax\"\n"
- " .even\n"
- "10: move.l %5,%0\n"
- " jra 3b\n"
- " .previous\n"
- "\n"
- " .section __ex_table,\"a\"\n"
- " .align 4\n"
- " .long 1b,10b\n"
- " .previous"
- : "=d" (res), "+a" (dst), "+a" (src), "+r" (count), "=&d" (c)
- : "i" (-EFAULT), "0" (count));
-
- return res;
-}
-EXPORT_SYMBOL(strncpy_from_user);
-
-/*
- * Return the size of a string (including the ending 0)
- *
- * Return 0 on exception, a value greater than N if too long
- */
-long strnlen_user(const char __user *src, long n)
-{
- char c;
- long res;
-
- asm volatile ("\n"
- "1: subq.l #1,%1\n"
- " jmi 3f\n"
- "2: "MOVES".b (%0)+,%2\n"
- " tst.b %2\n"
- " jne 1b\n"
- " jra 4f\n"
- "\n"
- "3: addq.l #1,%0\n"
- "4: sub.l %4,%0\n"
- "5:\n"
- " .section .fixup,\"ax\"\n"
- " .even\n"
- "20: sub.l %0,%0\n"
- " jra 5b\n"
- " .previous\n"
- "\n"
- " .section __ex_table,\"a\"\n"
- " .align 4\n"
- " .long 2b,20b\n"
- " .previous\n"
- : "=&a" (res), "+d" (n), "=&d" (c)
- : "0" (src), "r" (src));
-
- return res;
-}
-EXPORT_SYMBOL(strnlen_user);
-
-/*
* Zero Userspace
*/
diff --git a/arch/m68k/platform/68328/timers.c b/arch/m68k/platform/68328/timers.c
index c801c17..f4dc9b2 100644
--- a/arch/m68k/platform/68328/timers.c
+++ b/arch/m68k/platform/68328/timers.c
@@ -53,6 +53,7 @@
#endif
static u32 m68328_tick_cnt;
+static irq_handler_t timer_interrupt;
/***************************************************************************/
@@ -62,7 +63,7 @@
TSTAT &= 0;
m68328_tick_cnt += TICKS_PER_JIFFY;
- return arch_timer_interrupt(irq, dummy);
+ return timer_interrupt(irq, dummy);
}
/***************************************************************************/
@@ -99,7 +100,7 @@
/***************************************************************************/
-void hw_timer_init(void)
+void hw_timer_init(irq_handler_t handler)
{
/* disable timer 1 */
TCTL = 0;
@@ -115,6 +116,7 @@
/* Enable timer 1 */
TCTL |= TCTL_TEN;
clocksource_register_hz(&m68328_clk, TICKS_PER_JIFFY*HZ);
+ timer_interrupt = handler;
}
/***************************************************************************/
diff --git a/arch/m68k/platform/68360/config.c b/arch/m68k/platform/68360/config.c
index 255fc03..9877cef 100644
--- a/arch/m68k/platform/68360/config.c
+++ b/arch/m68k/platform/68360/config.c
@@ -35,6 +35,7 @@
#define OSCILLATOR (unsigned long int)33000000
#endif
+static irq_handler_t timer_interrupt;
unsigned long int system_clock;
extern QUICC *pquicc;
@@ -52,7 +53,7 @@
pquicc->timer_ter1 = 0x0002; /* clear timer event */
- return arch_timer_interrupt(irq, dummy);
+ return timer_interrupt(irq, dummy);
}
static struct irqaction m68360_timer_irq = {
@@ -61,7 +62,7 @@
.handler = hw_tick,
};
-void hw_timer_init(void)
+void hw_timer_init(irq_handler_t handler)
{
unsigned char prescaler;
unsigned short tgcr_save;
@@ -94,6 +95,8 @@
pquicc->timer_ter1 = 0x0003; /* clear timer events */
+ timer_interrupt = handler;
+
/* enable timer 1 interrupt in CIMR */
setup_irq(CPMVEC_TIMER1, &m68360_timer_irq);
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index dbc3850..5707f1a 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -21,6 +21,7 @@
NM = sh $(srctree)/arch/parisc/nm
CHECKFLAGS += -D__hppa__=1
+LIBGCC = $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
MACHINE := $(shell uname -m)
ifeq ($(MACHINE),parisc*)
@@ -79,7 +80,7 @@
kernel-$(CONFIG_HPUX) += hpux/
core-y += $(addprefix arch/parisc/, $(kernel-y))
-libs-y += arch/parisc/lib/ `$(CC) -print-libgcc-file-name`
+libs-y += arch/parisc/lib/ $(LIBGCC)
drivers-$(CONFIG_OPROFILE) += arch/parisc/oprofile/
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index 19a434f..4383707 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -1,3 +1,4 @@
include include/asm-generic/Kbuild.asm
header-y += pdc.h
+generic-y += word-at-a-time.h
diff --git a/arch/parisc/include/asm/bug.h b/arch/parisc/include/asm/bug.h
index 72cfdb0..62a3333 100644
--- a/arch/parisc/include/asm/bug.h
+++ b/arch/parisc/include/asm/bug.h
@@ -1,6 +1,8 @@
#ifndef _PARISC_BUG_H
#define _PARISC_BUG_H
+#include <linux/kernel.h> /* for BUGFLAG_TAINT */
+
/*
* Tell the user there is some problem.
* The offending file and line are encoded in the __bug_table section.
diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
index 0b6d796..2e3200c 100644
--- a/arch/powerpc/kernel/module_32.c
+++ b/arch/powerpc/kernel/module_32.c
@@ -176,8 +176,8 @@
static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val)
{
- if (entry->jump[0] == 0x3d600000 + ((val + 0x8000) >> 16)
- && entry->jump[1] == 0x396b0000 + (val & 0xffff))
+ if (entry->jump[0] == 0x3d800000 + ((val + 0x8000) >> 16)
+ && entry->jump[1] == 0x398c0000 + (val & 0xffff))
return 1;
return 0;
}
@@ -204,10 +204,9 @@
entry++;
}
- /* Stolen from Paul Mackerras as well... */
- entry->jump[0] = 0x3d600000+((val+0x8000)>>16); /* lis r11,sym@ha */
- entry->jump[1] = 0x396b0000 + (val&0xffff); /* addi r11,r11,sym@l*/
- entry->jump[2] = 0x7d6903a6; /* mtctr r11 */
+ entry->jump[0] = 0x3d800000+((val+0x8000)>>16); /* lis r12,sym@ha */
+ entry->jump[1] = 0x398c0000 + (val&0xffff); /* addi r12,r12,sym@l*/
+ entry->jump[2] = 0x7d8903a6; /* mtctr r12 */
entry->jump[3] = 0x4e800420; /* bctr */
DEBUGP("Initialized plt for 0x%x at %p\n", val, entry);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 99a995c..be171ee 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -475,6 +475,7 @@
struct pt_regs *old_regs;
u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
struct clock_event_device *evt = &__get_cpu_var(decrementers);
+ u64 now;
/* Ensure a positive value is written to the decrementer, or else
* some CPUs will continue to take decrementer exceptions.
@@ -509,9 +510,16 @@
irq_work_run();
}
- *next_tb = ~(u64)0;
- if (evt->event_handler)
- evt->event_handler(evt);
+ now = get_tb_or_rtc();
+ if (now >= *next_tb) {
+ *next_tb = ~(u64)0;
+ if (evt->event_handler)
+ evt->event_handler(evt);
+ } else {
+ now = *next_tb - now;
+ if (now <= DECREMENTER_MAX)
+ set_dec((int)now);
+ }
#ifdef CONFIG_PPC64
/* collect purr register values often, for accurate calculations */
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 99bcd0e..31d9db7 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -32,6 +32,8 @@
select GENERIC_SMP_IDLE_THREAD
select GENERIC_CLOCKEVENTS
select GENERIC_CMOS_UPDATE if SH_SH03 || SH_DREAMCAST
+ select GENERIC_STRNCPY_FROM_USER
+ select GENERIC_STRNLEN_USER
help
The SuperH is a RISC processor targeted for use in embedded systems
and consumer electronics; it was also used in the Sega Dreamcast
diff --git a/arch/sh/Makefile b/arch/sh/Makefile
index 46edf07..aed701c 100644
--- a/arch/sh/Makefile
+++ b/arch/sh/Makefile
@@ -9,6 +9,12 @@
# License. See the file "COPYING" in the main directory of this archive
# for more details.
#
+ifneq ($(SUBARCH),$(ARCH))
+ ifeq ($(CROSS_COMPILE),)
+ CROSS_COMPILE := $(call cc-cross-prefix, $(UTS_MACHINE)-linux- $(UTS_MACHINE)-linux-gnu- $(UTS_MACHINE)-unknown-linux-gnu-)
+ endif
+endif
+
isa-y := any
isa-$(CONFIG_SH_DSP) := sh
isa-$(CONFIG_CPU_SH2) := sh2
@@ -106,19 +112,13 @@
KBUILD_DEFCONFIG := cayman_defconfig
endif
-ifneq ($(SUBARCH),$(ARCH))
- ifeq ($(CROSS_COMPILE),)
- CROSS_COMPILE := $(call cc-cross-prefix, $(UTS_MACHINE)-linux- $(UTS_MACHINE)-linux-gnu- $(UTS_MACHINE)-unknown-linux-gnu-)
- endif
-endif
-
ifdef CONFIG_CPU_LITTLE_ENDIAN
ld-bfd := elf32-$(UTS_MACHINE)-linux
-LDFLAGS_vmlinux += --defsym 'jiffies=jiffies_64' --oformat $(ld-bfd)
+LDFLAGS_vmlinux += --defsym jiffies=jiffies_64 --oformat $(ld-bfd)
LDFLAGS += -EL
else
ld-bfd := elf32-$(UTS_MACHINE)big-linux
-LDFLAGS_vmlinux += --defsym 'jiffies=jiffies_64+4' --oformat $(ld-bfd)
+LDFLAGS_vmlinux += --defsym jiffies=jiffies_64+4 --oformat $(ld-bfd)
LDFLAGS += -EB
endif
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 7beb423..7b673dd 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -1,5 +1,39 @@
include include/asm-generic/Kbuild.asm
+generic-y += bitsperlong.h
+generic-y += cputime.h
+generic-y += current.h
+generic-y += delay.h
+generic-y += div64.h
+generic-y += emergency-restart.h
+generic-y += errno.h
+generic-y += fcntl.h
+generic-y += ioctl.h
+generic-y += ipcbuf.h
+generic-y += irq_regs.h
+generic-y += kvm_para.h
+generic-y += local.h
+generic-y += local64.h
+generic-y += param.h
+generic-y += parport.h
+generic-y += percpu.h
+generic-y += poll.h
+generic-y += mman.h
+generic-y += msgbuf.h
+generic-y += resource.h
+generic-y += scatterlist.h
+generic-y += sembuf.h
+generic-y += serial.h
+generic-y += shmbuf.h
+generic-y += siginfo.h
+generic-y += sizes.h
+generic-y += socket.h
+generic-y += statfs.h
+generic-y += termbits.h
+generic-y += termios.h
+generic-y += ucontext.h
+generic-y += xor.h
+
header-y += cachectl.h
header-y += cpu-features.h
header-y += hw_breakpoint.h
diff --git a/arch/sh/include/asm/bitsperlong.h b/arch/sh/include/asm/bitsperlong.h
deleted file mode 100644
index 6dc0bb0..0000000
--- a/arch/sh/include/asm/bitsperlong.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/bitsperlong.h>
diff --git a/arch/sh/include/asm/cputime.h b/arch/sh/include/asm/cputime.h
deleted file mode 100644
index 6ca395d..0000000
--- a/arch/sh/include/asm/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __SH_CPUTIME_H
-#define __SH_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __SH_CPUTIME_H */
diff --git a/arch/sh/include/asm/current.h b/arch/sh/include/asm/current.h
deleted file mode 100644
index 4c51401..0000000
--- a/arch/sh/include/asm/current.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/current.h>
diff --git a/arch/sh/include/asm/delay.h b/arch/sh/include/asm/delay.h
deleted file mode 100644
index 9670e12..0000000
--- a/arch/sh/include/asm/delay.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/delay.h>
diff --git a/arch/sh/include/asm/div64.h b/arch/sh/include/asm/div64.h
deleted file mode 100644
index 6cd978c..0000000
--- a/arch/sh/include/asm/div64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/div64.h>
diff --git a/arch/sh/include/asm/emergency-restart.h b/arch/sh/include/asm/emergency-restart.h
deleted file mode 100644
index 108d8c4..0000000
--- a/arch/sh/include/asm/emergency-restart.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/arch/sh/include/asm/errno.h b/arch/sh/include/asm/errno.h
deleted file mode 100644
index 51cf6f9..0000000
--- a/arch/sh/include/asm/errno.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_SH_ERRNO_H
-#define __ASM_SH_ERRNO_H
-
-#include <asm-generic/errno.h>
-
-#endif /* __ASM_SH_ERRNO_H */
diff --git a/arch/sh/include/asm/fcntl.h b/arch/sh/include/asm/fcntl.h
deleted file mode 100644
index 46ab12d..0000000
--- a/arch/sh/include/asm/fcntl.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/fcntl.h>
diff --git a/arch/sh/include/asm/ioctl.h b/arch/sh/include/asm/ioctl.h
deleted file mode 100644
index b279fe0..0000000
--- a/arch/sh/include/asm/ioctl.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/ioctl.h>
diff --git a/arch/sh/include/asm/ipcbuf.h b/arch/sh/include/asm/ipcbuf.h
deleted file mode 100644
index 84c7e51..0000000
--- a/arch/sh/include/asm/ipcbuf.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/ipcbuf.h>
diff --git a/arch/sh/include/asm/irq_regs.h b/arch/sh/include/asm/irq_regs.h
deleted file mode 100644
index 3dd9c0b..0000000
--- a/arch/sh/include/asm/irq_regs.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/irq_regs.h>
diff --git a/arch/sh/include/asm/kvm_para.h b/arch/sh/include/asm/kvm_para.h
deleted file mode 100644
index 14fab8f..0000000
--- a/arch/sh/include/asm/kvm_para.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/kvm_para.h>
diff --git a/arch/sh/include/asm/local.h b/arch/sh/include/asm/local.h
deleted file mode 100644
index 9ed9b9c..0000000
--- a/arch/sh/include/asm/local.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __ASM_SH_LOCAL_H
-#define __ASM_SH_LOCAL_H
-
-#include <asm-generic/local.h>
-
-#endif /* __ASM_SH_LOCAL_H */
-
diff --git a/arch/sh/include/asm/local64.h b/arch/sh/include/asm/local64.h
deleted file mode 100644
index 36c93b5..0000000
--- a/arch/sh/include/asm/local64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/local64.h>
diff --git a/arch/sh/include/asm/mman.h b/arch/sh/include/asm/mman.h
deleted file mode 100644
index 8eebf89f5..0000000
--- a/arch/sh/include/asm/mman.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/mman.h>
diff --git a/arch/sh/include/asm/msgbuf.h b/arch/sh/include/asm/msgbuf.h
deleted file mode 100644
index 809134c..0000000
--- a/arch/sh/include/asm/msgbuf.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/msgbuf.h>
diff --git a/arch/sh/include/asm/param.h b/arch/sh/include/asm/param.h
deleted file mode 100644
index 965d454..0000000
--- a/arch/sh/include/asm/param.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/param.h>
diff --git a/arch/sh/include/asm/parport.h b/arch/sh/include/asm/parport.h
deleted file mode 100644
index cf252af..0000000
--- a/arch/sh/include/asm/parport.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/parport.h>
diff --git a/arch/sh/include/asm/percpu.h b/arch/sh/include/asm/percpu.h
deleted file mode 100644
index 4db4b39..0000000
--- a/arch/sh/include/asm/percpu.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ARCH_SH_PERCPU
-#define __ARCH_SH_PERCPU
-
-#include <asm-generic/percpu.h>
-
-#endif /* __ARCH_SH_PERCPU */
diff --git a/arch/sh/include/asm/poll.h b/arch/sh/include/asm/poll.h
deleted file mode 100644
index c98509d..0000000
--- a/arch/sh/include/asm/poll.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/poll.h>
diff --git a/arch/sh/include/asm/resource.h b/arch/sh/include/asm/resource.h
deleted file mode 100644
index 9c2499a..0000000
--- a/arch/sh/include/asm/resource.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_SH_RESOURCE_H
-#define __ASM_SH_RESOURCE_H
-
-#include <asm-generic/resource.h>
-
-#endif /* __ASM_SH_RESOURCE_H */
diff --git a/arch/sh/include/asm/scatterlist.h b/arch/sh/include/asm/scatterlist.h
deleted file mode 100644
index 98dfc35..0000000
--- a/arch/sh/include/asm/scatterlist.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_SH_SCATTERLIST_H
-#define __ASM_SH_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-
-#endif /* __ASM_SH_SCATTERLIST_H */
diff --git a/arch/sh/include/asm/sembuf.h b/arch/sh/include/asm/sembuf.h
deleted file mode 100644
index 7673b83..0000000
--- a/arch/sh/include/asm/sembuf.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/sembuf.h>
diff --git a/arch/sh/include/asm/serial.h b/arch/sh/include/asm/serial.h
deleted file mode 100644
index a0cb0caf..0000000
--- a/arch/sh/include/asm/serial.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/serial.h>
diff --git a/arch/sh/include/asm/shmbuf.h b/arch/sh/include/asm/shmbuf.h
deleted file mode 100644
index 83c05fc..0000000
--- a/arch/sh/include/asm/shmbuf.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/shmbuf.h>
diff --git a/arch/sh/include/asm/siginfo.h b/arch/sh/include/asm/siginfo.h
deleted file mode 100644
index 813040e..0000000
--- a/arch/sh/include/asm/siginfo.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_SH_SIGINFO_H
-#define __ASM_SH_SIGINFO_H
-
-#include <asm-generic/siginfo.h>
-
-#endif /* __ASM_SH_SIGINFO_H */
diff --git a/arch/sh/include/asm/sizes.h b/arch/sh/include/asm/sizes.h
deleted file mode 100644
index dd248c2..0000000
--- a/arch/sh/include/asm/sizes.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/sizes.h>
diff --git a/arch/sh/include/asm/socket.h b/arch/sh/include/asm/socket.h
deleted file mode 100644
index 6b71384..0000000
--- a/arch/sh/include/asm/socket.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/socket.h>
diff --git a/arch/sh/include/asm/statfs.h b/arch/sh/include/asm/statfs.h
deleted file mode 100644
index 9202a02..0000000
--- a/arch/sh/include/asm/statfs.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_SH_STATFS_H
-#define __ASM_SH_STATFS_H
-
-#include <asm-generic/statfs.h>
-
-#endif /* __ASM_SH_STATFS_H */
diff --git a/arch/sh/include/asm/termbits.h b/arch/sh/include/asm/termbits.h
deleted file mode 100644
index 3935b10..0000000
--- a/arch/sh/include/asm/termbits.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/termbits.h>
diff --git a/arch/sh/include/asm/termios.h b/arch/sh/include/asm/termios.h
deleted file mode 100644
index 280d78a..0000000
--- a/arch/sh/include/asm/termios.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/termios.h>
diff --git a/arch/sh/include/asm/uaccess.h b/arch/sh/include/asm/uaccess.h
index 050f221..8698a80 100644
--- a/arch/sh/include/asm/uaccess.h
+++ b/arch/sh/include/asm/uaccess.h
@@ -25,6 +25,8 @@
(__chk_user_ptr(addr), \
__access_ok((unsigned long __force)(addr), (size)))
+#define user_addr_max() (current_thread_info()->addr_limit.seg)
+
/*
* Uh, these should become the main single-value transfer routines ...
* They automatically use the right size if we just have the right
@@ -100,6 +102,11 @@
# include "uaccess_64.h"
#endif
+extern long strncpy_from_user(char *dest, const char __user *src, long count);
+
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
+
/* Generic arbitrary sized copy. */
/* Return the number of bytes NOT copied */
__kernel_size_t __copy_user(void *to, const void *from, __kernel_size_t n);
@@ -137,37 +144,6 @@
__cl_size; \
})
-/**
- * strncpy_from_user: - Copy a NUL terminated string from userspace.
- * @dst: Destination address, in kernel space. This buffer must be at
- * least @count bytes long.
- * @src: Source address, in user space.
- * @count: Maximum number of bytes to copy, including the trailing NUL.
- *
- * Copies a NUL-terminated string from userspace to kernel space.
- *
- * On success, returns the length of the string (not including the trailing
- * NUL).
- *
- * If access to userspace fails, returns -EFAULT (some data may have been
- * copied).
- *
- * If @count is smaller than the length of the string, copies @count bytes
- * and returns @count.
- */
-#define strncpy_from_user(dest,src,count) \
-({ \
- unsigned long __sfu_src = (unsigned long)(src); \
- int __sfu_count = (int)(count); \
- long __sfu_res = -EFAULT; \
- \
- if (__access_ok(__sfu_src, __sfu_count)) \
- __sfu_res = __strncpy_from_user((unsigned long)(dest), \
- __sfu_src, __sfu_count); \
- \
- __sfu_res; \
-})
-
static inline unsigned long
copy_from_user(void *to, const void __user *from, unsigned long n)
{
@@ -192,43 +168,6 @@
return __copy_size;
}
-/**
- * strnlen_user: - Get the size of a string in user space.
- * @s: The string to measure.
- * @n: The maximum valid length
- *
- * Context: User context only. This function may sleep.
- *
- * Get the size of a NUL-terminated string in user space.
- *
- * Returns the size of the string INCLUDING the terminating NUL.
- * On exception, returns 0.
- * If the string is too long, returns a value greater than @n.
- */
-static inline long strnlen_user(const char __user *s, long n)
-{
- if (!__addr_ok(s))
- return 0;
- else
- return __strnlen_user(s, n);
-}
-
-/**
- * strlen_user: - Get the size of a string in user space.
- * @str: The string to measure.
- *
- * Context: User context only. This function may sleep.
- *
- * Get the size of a NUL-terminated string in user space.
- *
- * Returns the size of the string INCLUDING the terminating NUL.
- * On exception, returns 0.
- *
- * If there is a limit on the length of a valid string, you may wish to
- * consider using strnlen_user() instead.
- */
-#define strlen_user(str) strnlen_user(str, ~0UL >> 1)
-
/*
* The exception table consists of pairs of addresses: the first is the
* address of an instruction that is allowed to fault, and the second is
diff --git a/arch/sh/include/asm/uaccess_32.h b/arch/sh/include/asm/uaccess_32.h
index ae0d24f..c0de7ee 100644
--- a/arch/sh/include/asm/uaccess_32.h
+++ b/arch/sh/include/asm/uaccess_32.h
@@ -170,79 +170,4 @@
extern void __put_user_unknown(void);
-static inline int
-__strncpy_from_user(unsigned long __dest, unsigned long __user __src, int __count)
-{
- __kernel_size_t res;
- unsigned long __dummy, _d, _s, _c;
-
- __asm__ __volatile__(
- "9:\n"
- "mov.b @%2+, %1\n\t"
- "cmp/eq #0, %1\n\t"
- "bt/s 2f\n"
- "1:\n"
- "mov.b %1, @%3\n\t"
- "dt %4\n\t"
- "bf/s 9b\n\t"
- " add #1, %3\n\t"
- "2:\n\t"
- "sub %4, %0\n"
- "3:\n"
- ".section .fixup,\"ax\"\n"
- "4:\n\t"
- "mov.l 5f, %1\n\t"
- "jmp @%1\n\t"
- " mov %9, %0\n\t"
- ".balign 4\n"
- "5: .long 3b\n"
- ".previous\n"
- ".section __ex_table,\"a\"\n"
- " .balign 4\n"
- " .long 9b,4b\n"
- ".previous"
- : "=r" (res), "=&z" (__dummy), "=r" (_s), "=r" (_d), "=r"(_c)
- : "0" (__count), "2" (__src), "3" (__dest), "4" (__count),
- "i" (-EFAULT)
- : "memory", "t");
-
- return res;
-}
-
-/*
- * Return the size of a string (including the ending 0 even when we have
- * exceeded the maximum string length).
- */
-static inline long __strnlen_user(const char __user *__s, long __n)
-{
- unsigned long res;
- unsigned long __dummy;
-
- __asm__ __volatile__(
- "1:\t"
- "mov.b @(%0,%3), %1\n\t"
- "cmp/eq %4, %0\n\t"
- "bt/s 2f\n\t"
- " add #1, %0\n\t"
- "tst %1, %1\n\t"
- "bf 1b\n\t"
- "2:\n"
- ".section .fixup,\"ax\"\n"
- "3:\n\t"
- "mov.l 4f, %1\n\t"
- "jmp @%1\n\t"
- " mov #0, %0\n"
- ".balign 4\n"
- "4: .long 2b\n"
- ".previous\n"
- ".section __ex_table,\"a\"\n"
- " .balign 4\n"
- " .long 1b,3b\n"
- ".previous"
- : "=z" (res), "=&r" (__dummy)
- : "0" (0), "r" (__s), "r" (__n)
- : "t");
- return res;
-}
-
#endif /* __ASM_SH_UACCESS_32_H */
diff --git a/arch/sh/include/asm/uaccess_64.h b/arch/sh/include/asm/uaccess_64.h
index 56fd20b..2e07e0f 100644
--- a/arch/sh/include/asm/uaccess_64.h
+++ b/arch/sh/include/asm/uaccess_64.h
@@ -84,8 +84,4 @@
extern long __put_user_asm_q(void *, long);
extern void __put_user_unknown(void);
-extern long __strnlen_user(const char *__s, long __n);
-extern int __strncpy_from_user(unsigned long __dest,
- unsigned long __user __src, int __count);
-
#endif /* __ASM_SH_UACCESS_64_H */
diff --git a/arch/sh/include/asm/ucontext.h b/arch/sh/include/asm/ucontext.h
deleted file mode 100644
index 9bc07b9..0000000
--- a/arch/sh/include/asm/ucontext.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/ucontext.h>
diff --git a/arch/sh/include/asm/word-at-a-time.h b/arch/sh/include/asm/word-at-a-time.h
new file mode 100644
index 0000000..6e38953
--- /dev/null
+++ b/arch/sh/include/asm/word-at-a-time.h
@@ -0,0 +1,53 @@
+#ifndef __ASM_SH_WORD_AT_A_TIME_H
+#define __ASM_SH_WORD_AT_A_TIME_H
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+# include <asm-generic/word-at-a-time.h>
+#else
+/*
+ * Little-endian version cribbed from x86.
+ */
+struct word_at_a_time {
+ const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+ /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+ long a = (0x0ff0001+mask) >> 23;
+ /* Fix the 1 for 00 case */
+ return a & mask;
+}
+
+/* Return nonzero if it has a zero */
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
+{
+ unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+ *bits = mask;
+ return mask;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c)
+{
+ return bits;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+ bits = (bits - 1) & ~bits;
+ return bits >> 7;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+ return count_masked_bytes(mask);
+}
+#endif
+
+#endif
diff --git a/arch/sh/include/asm/xor.h b/arch/sh/include/asm/xor.h
deleted file mode 100644
index c82eb12..0000000
--- a/arch/sh/include/asm/xor.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/xor.h>
diff --git a/arch/sh/include/cpu-sh2a/cpu/ubc.h b/arch/sh/include/cpu-sh2a/cpu/ubc.h
deleted file mode 100644
index 1192e1c..0000000
--- a/arch/sh/include/cpu-sh2a/cpu/ubc.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * SH-2A UBC definitions
- *
- * Copyright (C) 2008 Kieran Bingham
- *
- * 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.
- */
-
-#ifndef __ASM_CPU_SH2A_UBC_H
-#define __ASM_CPU_SH2A_UBC_H
-
-#define UBC_BARA 0xfffc0400
-#define UBC_BAMRA 0xfffc0404
-#define UBC_BBRA 0xfffc04a0 /* 16 bit access */
-#define UBC_BDRA 0xfffc0408
-#define UBC_BDMRA 0xfffc040c
-
-#define UBC_BARB 0xfffc0410
-#define UBC_BAMRB 0xfffc0414
-#define UBC_BBRB 0xfffc04b0 /* 16 bit access */
-#define UBC_BDRB 0xfffc0418
-#define UBC_BDMRB 0xfffc041c
-
-#define UBC_BRCR 0xfffc04c0
-
-#endif /* __ASM_CPU_SH2A_UBC_H */
diff --git a/arch/sh/kernel/cpu/sh5/entry.S b/arch/sh/kernel/cpu/sh5/entry.S
index ff1f0e6..b7cf6a5 100644
--- a/arch/sh/kernel/cpu/sh5/entry.S
+++ b/arch/sh/kernel/cpu/sh5/entry.S
@@ -1569,86 +1569,6 @@
#endif /* CONFIG_MMU */
/*
- * int __strncpy_from_user(unsigned long __dest, unsigned long __src,
- * int __count)
- *
- * Inputs:
- * (r2) target address
- * (r3) source address
- * (r4) maximum size in bytes
- *
- * Ouputs:
- * (*r2) copied data
- * (r2) -EFAULT (in case of faulting)
- * copied data (otherwise)
- */
- .global __strncpy_from_user
-__strncpy_from_user:
- pta ___strncpy_from_user1, tr0
- pta ___strncpy_from_user_done, tr1
- or r4, ZERO, r5 /* r5 = original count */
- beq/u r4, r63, tr1 /* early exit if r4==0 */
- movi -(EFAULT), r6 /* r6 = reply, no real fixup */
- or ZERO, ZERO, r7 /* r7 = data, clear top byte of data */
-
-___strncpy_from_user1:
- ld.b r3, 0, r7 /* Fault address: only in reading */
- st.b r2, 0, r7
- addi r2, 1, r2
- addi r3, 1, r3
- beq/u ZERO, r7, tr1
- addi r4, -1, r4 /* return real number of copied bytes */
- bne/l ZERO, r4, tr0
-
-___strncpy_from_user_done:
- sub r5, r4, r6 /* If done, return copied */
-
-___strncpy_from_user_exit:
- or r6, ZERO, r2
- ptabs LINK, tr0
- blink tr0, ZERO
-
-/*
- * extern long __strnlen_user(const char *__s, long __n)
- *
- * Inputs:
- * (r2) source address
- * (r3) source size in bytes
- *
- * Ouputs:
- * (r2) -EFAULT (in case of faulting)
- * string length (otherwise)
- */
- .global __strnlen_user
-__strnlen_user:
- pta ___strnlen_user_set_reply, tr0
- pta ___strnlen_user1, tr1
- or ZERO, ZERO, r5 /* r5 = counter */
- movi -(EFAULT), r6 /* r6 = reply, no real fixup */
- or ZERO, ZERO, r7 /* r7 = data, clear top byte of data */
- beq r3, ZERO, tr0
-
-___strnlen_user1:
- ldx.b r2, r5, r7 /* Fault address: only in reading */
- addi r3, -1, r3 /* No real fixup */
- addi r5, 1, r5
- beq r3, ZERO, tr0
- bne r7, ZERO, tr1
-! The line below used to be active. This meant led to a junk byte lying between each pair
-! of entries in the argv & envp structures in memory. Whilst the program saw the right data
-! via the argv and envp arguments to main, it meant the 'flat' representation visible through
-! /proc/$pid/cmdline was corrupt, causing trouble with ps, for example.
-! addi r5, 1, r5 /* Include '\0' */
-
-___strnlen_user_set_reply:
- or r5, ZERO, r6 /* If done, return counter */
-
-___strnlen_user_exit:
- or r6, ZERO, r2
- ptabs LINK, tr0
- blink tr0, ZERO
-
-/*
* extern long __get_user_asm_?(void *val, long addr)
*
* Inputs:
@@ -1982,8 +1902,6 @@
.long ___copy_user2, ___copy_user_exit
.long ___clear_user1, ___clear_user_exit
#endif
- .long ___strncpy_from_user1, ___strncpy_from_user_exit
- .long ___strnlen_user1, ___strnlen_user_exit
.long ___get_user_asm_b1, ___get_user_asm_b_exit
.long ___get_user_asm_w1, ___get_user_asm_w_exit
.long ___get_user_asm_l1, ___get_user_asm_l_exit
diff --git a/arch/sh/kernel/process.c b/arch/sh/kernel/process.c
index 9b7a459..055d91b 100644
--- a/arch/sh/kernel/process.c
+++ b/arch/sh/kernel/process.c
@@ -4,6 +4,7 @@
#include <linux/sched.h>
#include <linux/export.h>
#include <linux/stackprotector.h>
+#include <asm/fpu.h>
struct kmem_cache *task_xstate_cachep = NULL;
unsigned int xstate_size;
diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c
index 4264583e..602545b 100644
--- a/arch/sh/kernel/process_64.c
+++ b/arch/sh/kernel/process_64.c
@@ -33,6 +33,7 @@
#include <asm/switch_to.h>
struct task_struct *last_task_used_math = NULL;
+struct pt_regs fake_swapper_regs = { 0, };
void show_regs(struct pt_regs *regs)
{
diff --git a/arch/sh/kernel/sh_ksyms_64.c b/arch/sh/kernel/sh_ksyms_64.c
index 45afa5c..26a0774 100644
--- a/arch/sh/kernel/sh_ksyms_64.c
+++ b/arch/sh/kernel/sh_ksyms_64.c
@@ -32,8 +32,6 @@
EXPORT_SYMBOL(__get_user_asm_w);
EXPORT_SYMBOL(__get_user_asm_l);
EXPORT_SYMBOL(__get_user_asm_q);
-EXPORT_SYMBOL(__strnlen_user);
-EXPORT_SYMBOL(__strncpy_from_user);
EXPORT_SYMBOL(__clear_user);
EXPORT_SYMBOL(copy_page);
EXPORT_SYMBOL(__copy_user);
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index 7e1fef3..e9c670d 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -91,11 +91,6 @@
/* Enable interrupts racelessly and nap forever: helper for cpu_idle(). */
extern void _cpu_idle(void);
-/* Switch boot idle thread to a freshly-allocated stack and free old stack. */
-extern void cpu_idle_on_new_stack(struct thread_info *old_ti,
- unsigned long new_sp,
- unsigned long new_ss10);
-
#else /* __ASSEMBLY__ */
/*
diff --git a/arch/tile/kernel/entry.S b/arch/tile/kernel/entry.S
index 133c4b5..c31637b 100644
--- a/arch/tile/kernel/entry.S
+++ b/arch/tile/kernel/entry.S
@@ -68,20 +68,6 @@
jrp lr /* keep backtracer happy */
STD_ENDPROC(KBacktraceIterator_init_current)
-/*
- * Reset our stack to r1/r2 (sp and ksp0+cpu respectively), then
- * free the old stack (passed in r0) and re-invoke cpu_idle().
- * We update sp and ksp0 simultaneously to avoid backtracer warnings.
- */
-STD_ENTRY(cpu_idle_on_new_stack)
- {
- move sp, r1
- mtspr SPR_SYSTEM_SAVE_K_0, r2
- }
- jal free_thread_info
- j cpu_idle
- STD_ENDPROC(cpu_idle_on_new_stack)
-
/* Loop forever on a nap during SMP boot. */
STD_ENTRY(smp_nap)
nap
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index 6098ccc..dd87f34 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -29,6 +29,7 @@
#include <linux/smp.h>
#include <linux/timex.h>
#include <linux/hugetlb.h>
+#include <linux/start_kernel.h>
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/cacheflush.h>
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 8bbea6a..efe5acf 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -94,10 +94,10 @@
.section ".bsdata", "a"
bugger_off_msg:
- .ascii "Direct booting from floppy is no longer supported.\r\n"
- .ascii "Please use a boot loader program instead.\r\n"
+ .ascii "Direct floppy boot is not supported. "
+ .ascii "Use a boot loader program instead.\r\n"
.ascii "\n"
- .ascii "Remove disk and press any key to reboot . . .\r\n"
+ .ascii "Remove disk and press any key to reboot ...\r\n"
.byte 0
#ifdef CONFIG_EFI_STUB
@@ -111,7 +111,7 @@
#else
.word 0x8664 # x86-64
#endif
- .word 2 # nr_sections
+ .word 3 # nr_sections
.long 0 # TimeDateStamp
.long 0 # PointerToSymbolTable
.long 1 # NumberOfSymbols
@@ -158,8 +158,8 @@
#else
.quad 0 # ImageBase
#endif
- .long 0x1000 # SectionAlignment
- .long 0x200 # FileAlignment
+ .long 0x20 # SectionAlignment
+ .long 0x20 # FileAlignment
.word 0 # MajorOperatingSystemVersion
.word 0 # MinorOperatingSystemVersion
.word 0 # MajorImageVersion
@@ -200,8 +200,10 @@
# Section table
section_table:
- .ascii ".text"
- .byte 0
+ #
+ # The offset & size fields are filled in by build.c.
+ #
+ .ascii ".setup"
.byte 0
.byte 0
.long 0
@@ -217,9 +219,8 @@
#
# The EFI application loader requires a relocation section
- # because EFI applications must be relocatable. But since
- # we don't need the loader to fixup any relocs for us, we
- # just create an empty (zero-length) .reloc section header.
+ # because EFI applications must be relocatable. The .reloc
+ # offset & size fields are filled in by build.c.
#
.ascii ".reloc"
.byte 0
@@ -233,6 +234,25 @@
.word 0 # NumberOfRelocations
.word 0 # NumberOfLineNumbers
.long 0x42100040 # Characteristics (section flags)
+
+ #
+ # The offset & size fields are filled in by build.c.
+ #
+ .ascii ".text"
+ .byte 0
+ .byte 0
+ .byte 0
+ .long 0
+ .long 0x0 # startup_{32,64}
+ .long 0 # Size of initialized data
+ # on disk
+ .long 0x0 # startup_{32,64}
+ .long 0 # PointerToRelocations
+ .long 0 # PointerToLineNumbers
+ .word 0 # NumberOfRelocations
+ .word 0 # NumberOfLineNumbers
+ .long 0x60500020 # Characteristics (section flags)
+
#endif /* CONFIG_EFI_STUB */
# Kernel attributes; used by setup. This is part 1 of the
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index 3f61f6e..4b8e165 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -50,6 +50,8 @@
u8 buf[SETUP_SECT_MAX*512];
int is_big_kernel;
+#define PECOFF_RELOC_RESERVE 0x20
+
/*----------------------------------------------------------------------*/
static const u32 crctab32[] = {
@@ -133,11 +135,103 @@
die("Usage: build setup system [> image]");
}
+#ifdef CONFIG_EFI_STUB
+
+static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+{
+ unsigned int pe_header;
+ unsigned short num_sections;
+ u8 *section;
+
+ pe_header = get_unaligned_le32(&buf[0x3c]);
+ num_sections = get_unaligned_le16(&buf[pe_header + 6]);
+
+#ifdef CONFIG_X86_32
+ section = &buf[pe_header + 0xa8];
+#else
+ section = &buf[pe_header + 0xb8];
+#endif
+
+ while (num_sections > 0) {
+ if (strncmp((char*)section, section_name, 8) == 0) {
+ /* section header size field */
+ put_unaligned_le32(size, section + 0x8);
+
+ /* section header vma field */
+ put_unaligned_le32(offset, section + 0xc);
+
+ /* section header 'size of initialised data' field */
+ put_unaligned_le32(size, section + 0x10);
+
+ /* section header 'file offset' field */
+ put_unaligned_le32(offset, section + 0x14);
+
+ break;
+ }
+ section += 0x28;
+ num_sections--;
+ }
+}
+
+static void update_pecoff_setup_and_reloc(unsigned int size)
+{
+ u32 setup_offset = 0x200;
+ u32 reloc_offset = size - PECOFF_RELOC_RESERVE;
+ u32 setup_size = reloc_offset - setup_offset;
+
+ update_pecoff_section_header(".setup", setup_offset, setup_size);
+ update_pecoff_section_header(".reloc", reloc_offset, PECOFF_RELOC_RESERVE);
+
+ /*
+ * Modify .reloc section contents with a single entry. The
+ * relocation is applied to offset 10 of the relocation section.
+ */
+ put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]);
+ put_unaligned_le32(10, &buf[reloc_offset + 4]);
+}
+
+static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
+{
+ unsigned int pe_header;
+ unsigned int text_sz = file_sz - text_start;
+
+ pe_header = get_unaligned_le32(&buf[0x3c]);
+
+ /* Size of image */
+ put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
+
+ /*
+ * Size of code: Subtract the size of the first sector (512 bytes)
+ * which includes the header.
+ */
+ put_unaligned_le32(file_sz - 512, &buf[pe_header + 0x1c]);
+
+#ifdef CONFIG_X86_32
+ /*
+ * Address of entry point.
+ *
+ * The EFI stub entry point is +16 bytes from the start of
+ * the .text section.
+ */
+ put_unaligned_le32(text_start + 16, &buf[pe_header + 0x28]);
+#else
+ /*
+ * Address of entry point. startup_32 is at the beginning and
+ * the 64-bit entry point (startup_64) is always 512 bytes
+ * after. The EFI stub entry point is 16 bytes after that, as
+ * the first instruction allows legacy loaders to jump over
+ * the EFI stub initialisation
+ */
+ put_unaligned_le32(text_start + 528, &buf[pe_header + 0x28]);
+#endif /* CONFIG_X86_32 */
+
+ update_pecoff_section_header(".text", text_start, text_sz);
+}
+
+#endif /* CONFIG_EFI_STUB */
+
int main(int argc, char ** argv)
{
-#ifdef CONFIG_EFI_STUB
- unsigned int file_sz, pe_header;
-#endif
unsigned int i, sz, setup_sectors;
int c;
u32 sys_size;
@@ -163,6 +257,12 @@
die("Boot block hasn't got boot flag (0xAA55)");
fclose(file);
+#ifdef CONFIG_EFI_STUB
+ /* Reserve 0x20 bytes for .reloc section */
+ memset(buf+c, 0, PECOFF_RELOC_RESERVE);
+ c += PECOFF_RELOC_RESERVE;
+#endif
+
/* Pad unused space with zeros */
setup_sectors = (c + 511) / 512;
if (setup_sectors < SETUP_SECT_MIN)
@@ -170,6 +270,10 @@
i = setup_sectors*512;
memset(buf+c, 0, i-c);
+#ifdef CONFIG_EFI_STUB
+ update_pecoff_setup_and_reloc(i);
+#endif
+
/* Set the default root device */
put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]);
@@ -194,66 +298,8 @@
put_unaligned_le32(sys_size, &buf[0x1f4]);
#ifdef CONFIG_EFI_STUB
- file_sz = sz + i + ((sys_size * 16) - sz);
-
- pe_header = get_unaligned_le32(&buf[0x3c]);
-
- /* Size of image */
- put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
-
- /*
- * Subtract the size of the first section (512 bytes) which
- * includes the header and .reloc section. The remaining size
- * is that of the .text section.
- */
- file_sz -= 512;
-
- /* Size of code */
- put_unaligned_le32(file_sz, &buf[pe_header + 0x1c]);
-
-#ifdef CONFIG_X86_32
- /*
- * Address of entry point.
- *
- * The EFI stub entry point is +16 bytes from the start of
- * the .text section.
- */
- put_unaligned_le32(i + 16, &buf[pe_header + 0x28]);
-
- /* .text size */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xb0]);
-
- /* .text vma */
- put_unaligned_le32(0x200, &buf[pe_header + 0xb4]);
-
- /* .text size of initialised data */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xb8]);
-
- /* .text file offset */
- put_unaligned_le32(0x200, &buf[pe_header + 0xbc]);
-#else
- /*
- * Address of entry point. startup_32 is at the beginning and
- * the 64-bit entry point (startup_64) is always 512 bytes
- * after. The EFI stub entry point is 16 bytes after that, as
- * the first instruction allows legacy loaders to jump over
- * the EFI stub initialisation
- */
- put_unaligned_le32(i + 528, &buf[pe_header + 0x28]);
-
- /* .text size */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xc0]);
-
- /* .text vma */
- put_unaligned_le32(0x200, &buf[pe_header + 0xc4]);
-
- /* .text size of initialised data */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xc8]);
-
- /* .text file offset */
- put_unaligned_le32(0x200, &buf[pe_header + 0xcc]);
-#endif /* CONFIG_X86_32 */
-#endif /* CONFIG_EFI_STUB */
+ update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
+#endif
crc = partial_crc32(buf, i, crc);
if (fwrite(buf, 1, i, stdout) != i)
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index be6d9e3..3470624 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -2460,10 +2460,12 @@
pxor IN3, STATE4
movaps IN4, IV
#else
- pxor (INP), STATE2
- pxor 0x10(INP), STATE3
pxor IN1, STATE4
movaps IN2, IV
+ movups (INP), IN1
+ pxor IN1, STATE2
+ movups 0x10(INP), IN2
+ pxor IN2, STATE3
#endif
movups STATE1, (OUTP)
movups STATE2, 0x10(OUTP)
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 0e3793b..dc580c4 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -54,6 +54,20 @@
__register_nmi_handler((t), &fn##_na); \
})
+/*
+ * For special handlers that register/unregister in the
+ * init section only. This should be considered rare.
+ */
+#define register_nmi_handler_initonly(t, fn, fg, n) \
+({ \
+ static struct nmiaction fn##_na __initdata = { \
+ .handler = (fn), \
+ .name = (n), \
+ .flags = (fg), \
+ }; \
+ __register_nmi_handler((t), &fn##_na); \
+})
+
int __register_nmi_handler(unsigned int, struct nmiaction *);
void unregister_nmi_handler(unsigned int, const char *);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 04cd688..e1f3a17 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -33,9 +33,8 @@
#define segment_eq(a, b) ((a).seg == (b).seg)
#define user_addr_max() (current_thread_info()->addr_limit.seg)
-#define __addr_ok(addr) \
- ((unsigned long __force)(addr) < \
- (current_thread_info()->addr_limit.seg))
+#define __addr_ok(addr) \
+ ((unsigned long __force)(addr) < user_addr_max())
/*
* Test whether a block of memory is a valid user space address.
@@ -47,14 +46,14 @@
* This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
*/
-#define __range_not_ok(addr, size) \
+#define __range_not_ok(addr, size, limit) \
({ \
unsigned long flag, roksum; \
__chk_user_ptr(addr); \
asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0" \
: "=&r" (flag), "=r" (roksum) \
: "1" (addr), "g" ((long)(size)), \
- "rm" (current_thread_info()->addr_limit.seg)); \
+ "rm" (limit)); \
flag; \
})
@@ -77,7 +76,8 @@
* checks that the pointer is in the user space range - after calling
* this function, memory access functions may still return -EFAULT.
*/
-#define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0))
+#define access_ok(type, addr, size) \
+ (likely(__range_not_ok(addr, size, user_addr_max()) == 0))
/*
* The exception table consists of pairs of addresses relative to the
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index becf47b..6149b47 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -149,7 +149,6 @@
/* 4 bits of software ack period */
#define UV2_ACK_MASK 0x7UL
#define UV2_ACK_UNITS_SHFT 3
-#define UV2_LEG_SHFT UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT
#define UV2_EXT_SHFT UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT
/*
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 6e76c19..d5fd66f 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -20,7 +20,6 @@
#include <linux/bitops.h>
#include <linux/ioport.h>
#include <linux/suspend.h>
-#include <linux/kmemleak.h>
#include <asm/e820.h>
#include <asm/io.h>
#include <asm/iommu.h>
@@ -95,11 +94,6 @@
return 0;
}
memblock_reserve(addr, aper_size);
- /*
- * Kmemleak should not scan this block as it may not be mapped via the
- * kernel direct mapping.
- */
- kmemleak_ignore(phys_to_virt(addr));
printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
aper_size >> 10, addr);
insert_aperture_resource((u32)addr, aper_size);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index ac96561..5f0ff59 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1195,7 +1195,7 @@
BUG_ON(!cfg->vector);
vector = cfg->vector;
- for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
+ for_each_cpu(cpu, cfg->domain)
per_cpu(vector_irq, cpu)[vector] = -1;
cfg->vector = 0;
@@ -1203,7 +1203,7 @@
if (likely(!cfg->move_in_progress))
return;
- for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
+ for_each_cpu(cpu, cfg->old_domain) {
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
vector++) {
if (per_cpu(vector_irq, cpu)[vector] != irq)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 0a687fd..da27c5d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1274,7 +1274,7 @@
*/
iv = __this_cpu_read(mce_next_interval);
if (mce_notify_irq())
- iv = max(iv, (unsigned long) HZ/100);
+ iv = max(iv / 2, (unsigned long) HZ/100);
else
iv = min(iv * 2, round_jiffies_relative(check_interval * HZ));
__this_cpu_write(mce_next_interval, iv);
@@ -1557,7 +1557,7 @@
static void __mcheck_cpu_init_timer(void)
{
struct timer_list *t = &__get_cpu_var(mce_timer);
- unsigned long iv = __this_cpu_read(mce_next_interval);
+ unsigned long iv = check_interval * HZ;
setup_timer(t, mce_timer_fn, smp_processor_id());
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index e049d6d..c4706cf 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1496,6 +1496,7 @@
if (!cpuc->shared_regs)
goto error;
}
+ cpuc->is_fake = 1;
return cpuc;
error:
free_fake_cpuc(cpuc);
@@ -1756,6 +1757,12 @@
dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
}
+static inline int
+valid_user_frame(const void __user *fp, unsigned long size)
+{
+ return (__range_not_ok(fp, size, TASK_SIZE) == 0);
+}
+
#ifdef CONFIG_COMPAT
#include <asm/compat.h>
@@ -1780,7 +1787,7 @@
if (bytes != sizeof(frame))
break;
- if (fp < compat_ptr(regs->sp))
+ if (!valid_user_frame(fp, sizeof(frame)))
break;
perf_callchain_store(entry, frame.return_address);
@@ -1826,7 +1833,7 @@
if (bytes != sizeof(frame))
break;
- if ((unsigned long)fp < regs->sp)
+ if (!valid_user_frame(fp, sizeof(frame)))
break;
perf_callchain_store(entry, frame.return_address);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 6638aaf..7241e2f 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -117,6 +117,7 @@
struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
unsigned int group_flag;
+ int is_fake;
/*
* Intel DebugStore bits
@@ -364,6 +365,7 @@
int pebs_record_size;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
+ void (*pebs_aliases)(struct perf_event *event);
/*
* Intel LBR
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 166546e..187c294 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1119,27 +1119,33 @@
return NULL;
}
-static bool intel_try_alt_er(struct perf_event *event, int orig_idx)
+static int intel_alt_er(int idx)
{
if (!(x86_pmu.er_flags & ERF_HAS_RSP_1))
- return false;
+ return idx;
- if (event->hw.extra_reg.idx == EXTRA_REG_RSP_0) {
- event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
- event->hw.config |= 0x01bb;
- event->hw.extra_reg.idx = EXTRA_REG_RSP_1;
- event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
- } else if (event->hw.extra_reg.idx == EXTRA_REG_RSP_1) {
+ if (idx == EXTRA_REG_RSP_0)
+ return EXTRA_REG_RSP_1;
+
+ if (idx == EXTRA_REG_RSP_1)
+ return EXTRA_REG_RSP_0;
+
+ return idx;
+}
+
+static void intel_fixup_er(struct perf_event *event, int idx)
+{
+ event->hw.extra_reg.idx = idx;
+
+ if (idx == EXTRA_REG_RSP_0) {
event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
event->hw.config |= 0x01b7;
- event->hw.extra_reg.idx = EXTRA_REG_RSP_0;
event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0;
+ } else if (idx == EXTRA_REG_RSP_1) {
+ event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
+ event->hw.config |= 0x01bb;
+ event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
}
-
- if (event->hw.extra_reg.idx == orig_idx)
- return false;
-
- return true;
}
/*
@@ -1157,14 +1163,18 @@
struct event_constraint *c = &emptyconstraint;
struct er_account *era;
unsigned long flags;
- int orig_idx = reg->idx;
+ int idx = reg->idx;
- /* already allocated shared msr */
- if (reg->alloc)
+ /*
+ * reg->alloc can be set due to existing state, so for fake cpuc we
+ * need to ignore this, otherwise we might fail to allocate proper fake
+ * state for this extra reg constraint. Also see the comment below.
+ */
+ if (reg->alloc && !cpuc->is_fake)
return NULL; /* call x86_get_event_constraint() */
again:
- era = &cpuc->shared_regs->regs[reg->idx];
+ era = &cpuc->shared_regs->regs[idx];
/*
* we use spin_lock_irqsave() to avoid lockdep issues when
* passing a fake cpuc
@@ -1173,6 +1183,29 @@
if (!atomic_read(&era->ref) || era->config == reg->config) {
+ /*
+ * If its a fake cpuc -- as per validate_{group,event}() we
+ * shouldn't touch event state and we can avoid doing so
+ * since both will only call get_event_constraints() once
+ * on each event, this avoids the need for reg->alloc.
+ *
+ * Not doing the ER fixup will only result in era->reg being
+ * wrong, but since we won't actually try and program hardware
+ * this isn't a problem either.
+ */
+ if (!cpuc->is_fake) {
+ if (idx != reg->idx)
+ intel_fixup_er(event, idx);
+
+ /*
+ * x86_schedule_events() can call get_event_constraints()
+ * multiple times on events in the case of incremental
+ * scheduling(). reg->alloc ensures we only do the ER
+ * allocation once.
+ */
+ reg->alloc = 1;
+ }
+
/* lock in msr value */
era->config = reg->config;
era->reg = reg->reg;
@@ -1180,17 +1213,17 @@
/* one more user */
atomic_inc(&era->ref);
- /* no need to reallocate during incremental event scheduling */
- reg->alloc = 1;
-
/*
* need to call x86_get_event_constraint()
* to check if associated event has constraints
*/
c = NULL;
- } else if (intel_try_alt_er(event, orig_idx)) {
- raw_spin_unlock_irqrestore(&era->lock, flags);
- goto again;
+ } else {
+ idx = intel_alt_er(idx);
+ if (idx != reg->idx) {
+ raw_spin_unlock_irqrestore(&era->lock, flags);
+ goto again;
+ }
}
raw_spin_unlock_irqrestore(&era->lock, flags);
@@ -1204,11 +1237,14 @@
struct er_account *era;
/*
- * only put constraint if extra reg was actually
- * allocated. Also takes care of event which do
- * not use an extra shared reg
+ * Only put constraint if extra reg was actually allocated. Also takes
+ * care of event which do not use an extra shared reg.
+ *
+ * Also, if this is a fake cpuc we shouldn't touch any event state
+ * (reg->alloc) and we don't care about leaving inconsistent cpuc state
+ * either since it'll be thrown out.
*/
- if (!reg->alloc)
+ if (!reg->alloc || cpuc->is_fake)
return;
era = &cpuc->shared_regs->regs[reg->idx];
@@ -1300,15 +1336,9 @@
intel_put_shared_regs_event_constraints(cpuc, event);
}
-static int intel_pmu_hw_config(struct perf_event *event)
+static void intel_pebs_aliases_core2(struct perf_event *event)
{
- int ret = x86_pmu_hw_config(event);
-
- if (ret)
- return ret;
-
- if (event->attr.precise_ip &&
- (event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+ if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
/*
* Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
* (0x003c) so that we can use it with PEBS.
@@ -1329,10 +1359,48 @@
*/
u64 alt_config = X86_CONFIG(.event=0xc0, .inv=1, .cmask=16);
+ alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
+ event->hw.config = alt_config;
+ }
+}
+
+static void intel_pebs_aliases_snb(struct perf_event *event)
+{
+ if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+ /*
+ * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
+ * (0x003c) so that we can use it with PEBS.
+ *
+ * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't
+ * PEBS capable. However we can use UOPS_RETIRED.ALL
+ * (0x01c2), which is a PEBS capable event, to get the same
+ * count.
+ *
+ * UOPS_RETIRED.ALL counts the number of cycles that retires
+ * CNTMASK micro-ops. By setting CNTMASK to a value (16)
+ * larger than the maximum number of micro-ops that can be
+ * retired per cycle (4) and then inverting the condition, we
+ * count all cycles that retire 16 or less micro-ops, which
+ * is every cycle.
+ *
+ * Thereby we gain a PEBS capable cycle counter.
+ */
+ u64 alt_config = X86_CONFIG(.event=0xc2, .umask=0x01, .inv=1, .cmask=16);
alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
event->hw.config = alt_config;
}
+}
+
+static int intel_pmu_hw_config(struct perf_event *event)
+{
+ int ret = x86_pmu_hw_config(event);
+
+ if (ret)
+ return ret;
+
+ if (event->attr.precise_ip && x86_pmu.pebs_aliases)
+ x86_pmu.pebs_aliases(event);
if (intel_pmu_needs_lbr_smpl(event)) {
ret = intel_pmu_setup_lbr_filter(event);
@@ -1607,6 +1675,7 @@
.max_period = (1ULL << 31) - 1,
.get_event_constraints = intel_get_event_constraints,
.put_event_constraints = intel_put_event_constraints,
+ .pebs_aliases = intel_pebs_aliases_core2,
.format_attrs = intel_arch3_formats_attr,
@@ -1840,8 +1909,9 @@
break;
case 42: /* SandyBridge */
- x86_add_quirk(intel_sandybridge_quirk);
case 45: /* SandyBridge, "Romely-EP" */
+ x86_add_quirk(intel_sandybridge_quirk);
+ case 58: /* IvyBridge */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -1849,6 +1919,7 @@
x86_pmu.event_constraints = intel_snb_event_constraints;
x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
+ x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
x86_pmu.extra_regs = intel_snb_extra_regs;
/* all extra regs are per-cpu when HT is on */
x86_pmu.er_flags |= ERF_HAS_RSP_1;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 5a3edc2..35e2192 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -400,14 +400,7 @@
INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */
- INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_LOADS */
- INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_STORES */
- INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOP_RETIRED.LOCK_LOADS */
- INTEL_UEVENT_CONSTRAINT(0x22d0, 0xf), /* MEM_UOP_RETIRED.LOCK_STORES */
- INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_LOADS */
- INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_STORES */
- INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOP_RETIRED.ANY_LOADS */
- INTEL_UEVENT_CONSTRAINT(0x82d0, 0xf), /* MEM_UOP_RETIRED.ANY_STORES */
+ INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 086eb58..f1b42b3a 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -120,11 +120,6 @@
bool ret = false;
struct pvclock_vcpu_time_info *src;
- /*
- * per_cpu() is safe here because this function is only called from
- * timer functions where preemption is already disabled.
- */
- WARN_ON(!in_atomic());
src = &__get_cpu_var(hv_clock);
if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) {
__this_cpu_and(hv_clock.flags, ~PVCLOCK_GUEST_STOPPED);
diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c
index e31bf8d..149b8d9 100644
--- a/arch/x86/kernel/nmi_selftest.c
+++ b/arch/x86/kernel/nmi_selftest.c
@@ -42,7 +42,7 @@
static void __init init_nmi_testsuite(void)
{
/* trap all the unknown NMIs we may generate */
- register_nmi_handler(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
+ register_nmi_handler_initonly(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
}
static void __init cleanup_nmi_testsuite(void)
@@ -64,7 +64,7 @@
{
unsigned long timeout;
- if (register_nmi_handler(NMI_LOCAL, test_nmi_ipi_callback,
+ if (register_nmi_handler_initonly(NMI_LOCAL, test_nmi_ipi_callback,
NMI_FLAG_FIRST, "nmi_selftest")) {
nmi_fail = FAILURE;
return;
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 79c45af..25b48ed 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -639,9 +639,11 @@
set_cpus_allowed_ptr(current, cpumask_of(reboot_cpu_id));
/*
- * O.K Now that I'm on the appropriate processor,
- * stop all of the others.
+ * O.K Now that I'm on the appropriate processor, stop all of the
+ * others. Also disable the local irq to not receive the per-cpu
+ * timer interrupt which may trigger scheduler's load balance.
*/
+ local_irq_disable();
stop_other_cpus();
#endif
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f56f96d..3fab55b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -382,6 +382,15 @@
if ((i == cpu) || (has_mc && match_llc(c, o)))
link_mask(llc_shared, cpu, i);
+ }
+
+ /*
+ * This needs a separate iteration over the cpus because we rely on all
+ * cpu_sibling_mask links to be set-up.
+ */
+ for_each_cpu(i, cpu_sibling_setup_mask) {
+ o = &cpu_data(i);
+
if ((i == cpu) || (has_mc && match_mc(c, o))) {
link_mask(core, cpu, i);
@@ -410,15 +419,7 @@
/* maps the cpu to the sched domain representing multi-core */
const struct cpumask *cpu_coregroup_mask(int cpu)
{
- struct cpuinfo_x86 *c = &cpu_data(cpu);
- /*
- * For perf, we return last level cache shared map.
- * And for power savings, we return cpu_core_map
- */
- if (!(cpu_has(c, X86_FEATURE_AMD_DCM)))
- return cpu_core_mask(cpu);
- else
- return cpu_llc_shared_mask(cpu);
+ return cpu_llc_shared_mask(cpu);
}
static void impress_friends(void)
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index f61ee67..677b1ed 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -8,6 +8,7 @@
#include <linux/module.h>
#include <asm/word-at-a-time.h>
+#include <linux/sched.h>
/*
* best effort, GUP based copy_from_user() that is NMI-safe
@@ -21,6 +22,9 @@
void *map;
int ret;
+ if (__range_not_ok(from, n, TASK_SIZE) == 0)
+ return len;
+
do {
ret = __get_user_pages_fast(addr, 1, 0, &page);
if (!ret)
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 8191379..5d7e51f 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -28,7 +28,7 @@
# - (66): the last prefix is 0x66
# - (F3): the last prefix is 0xF3
# - (F2): the last prefix is 0xF2
-#
+# - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
Table: one byte opcode
Referrer:
@@ -515,12 +515,12 @@
b5: LGS Gv,Mp
b6: MOVZX Gv,Eb
b7: MOVZX Gv,Ew
-b8: JMPE | POPCNT Gv,Ev (F3)
+b8: JMPE (!F3) | POPCNT Gv,Ev (F3)
b9: Grp10 (1A)
ba: Grp8 Ev,Ib (1A)
bb: BTC Ev,Gv
-bc: BSF Gv,Ev | TZCNT Gv,Ev (F3)
-bd: BSR Gv,Ev | LZCNT Gv,Ev (F3)
+bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3)
+bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3)
be: MOVSX Gv,Eb
bf: MOVSX Gv,Ew
# 0x0f 0xc0-0xcf
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 97141c2..bc4e9d8 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -62,7 +62,8 @@
extra += PMD_SIZE;
#endif
/* The first 2/4M doesn't use large pages. */
- extra += mr->end - mr->start;
+ if (mr->start < PMD_SIZE)
+ extra += mr->end - mr->start;
ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
} else
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 732af3a..4599c3e 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -176,6 +176,8 @@
return;
}
+ node_set(node, numa_nodes_parsed);
+
printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
node, pxm,
(unsigned long long) start, (unsigned long long) end - 1);
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index e31bcd8..fd41a92 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -782,7 +782,7 @@
EXPORT_SYMBOL_GPL(intel_scu_notifier);
/* Called by IPC driver */
-void intel_scu_devices_create(void)
+void __devinit intel_scu_devices_create(void)
{
int i;
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 3ae0e61..59880af 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1295,7 +1295,6 @@
*/
mmr_image |= (1L << SOFTACK_MSHIFT);
if (is_uv2_hub()) {
- mmr_image &= ~(1L << UV2_LEG_SHFT);
mmr_image |= (1L << UV2_EXT_SHFT);
}
write_mmr_misc_control(pnode, mmr_image);
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index 5f6a5b6..ddcf39b 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -66,9 +66,10 @@
rex_expr = "^REX(\\.[XRWB]+)*"
fpu_expr = "^ESC" # TODO
- lprefix1_expr = "\\(66\\)"
+ lprefix1_expr = "\\((66|!F3)\\)"
lprefix2_expr = "\\(F3\\)"
- lprefix3_expr = "\\(F2\\)"
+ lprefix3_expr = "\\((F2|!F3)\\)"
+ lprefix_expr = "\\((66|F2|F3)\\)"
max_lprefix = 4
# All opcodes starting with lower-case 'v' or with (v1) superscript
@@ -333,13 +334,16 @@
if (match(ext, lprefix1_expr)) {
lptable1[idx] = add_flags(lptable1[idx],flags)
variant = "INAT_VARIANT"
- } else if (match(ext, lprefix2_expr)) {
+ }
+ if (match(ext, lprefix2_expr)) {
lptable2[idx] = add_flags(lptable2[idx],flags)
variant = "INAT_VARIANT"
- } else if (match(ext, lprefix3_expr)) {
+ }
+ if (match(ext, lprefix3_expr)) {
lptable3[idx] = add_flags(lptable3[idx],flags)
variant = "INAT_VARIANT"
- } else {
+ }
+ if (!match(ext, lprefix_expr)){
table[idx] = add_flags(table[idx],flags)
}
}
diff --git a/arch/xtensa/include/asm/syscall.h b/arch/xtensa/include/asm/syscall.h
index 0b9f2e1..c1dacca 100644
--- a/arch/xtensa/include/asm/syscall.h
+++ b/arch/xtensa/include/asm/syscall.h
@@ -31,5 +31,5 @@
asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds,
struct timespec __user *tsp, const sigset_t __user *sigmask,
size_t sigsetsize);
-
-
+asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset,
+ size_t sigsetsize);
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index b9f8e58..efe4e85 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -493,7 +493,7 @@
if (ret)
return;
- signal_delivered(signr, info, ka, regs, 0);
+ signal_delivered(signr, &info, &ka, regs, 0);
if (current->ptrace & PT_SINGLESTEP)
task_pt_regs(current)->icountlevel = 1;
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 47768ff..8099895 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -208,7 +208,7 @@
config ACPI_HOTPLUG_CPU
bool
- depends on ACPI_PROCESSOR && HOTPLUG_CPU
+ depends on EXPERIMENTAL && ACPI_PROCESSOR && HOTPLUG_CPU
select ACPI_CONTAINER
default y
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 86933ca..7dd3f9f 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -643,11 +643,19 @@
static void acpi_battery_refresh(struct acpi_battery *battery)
{
+ int power_unit;
+
if (!battery->bat.dev)
return;
+ power_unit = battery->power_unit;
+
acpi_battery_get_info(battery);
- /* The battery may have changed its reporting units. */
+
+ if (power_unit == battery->power_unit)
+ return;
+
+ /* The battery has changed its reporting units. */
sysfs_remove_battery(battery);
sysfs_add_battery(battery);
}
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 3188da3..adceafd 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -182,41 +182,66 @@
Power Management
-------------------------------------------------------------------------- */
+static const char *state_string(int state)
+{
+ switch (state) {
+ case ACPI_STATE_D0:
+ return "D0";
+ case ACPI_STATE_D1:
+ return "D1";
+ case ACPI_STATE_D2:
+ return "D2";
+ case ACPI_STATE_D3_HOT:
+ return "D3hot";
+ case ACPI_STATE_D3_COLD:
+ return "D3";
+ default:
+ return "(unknown)";
+ }
+}
+
static int __acpi_bus_get_power(struct acpi_device *device, int *state)
{
- int result = 0;
- acpi_status status = 0;
- unsigned long long psc = 0;
+ int result = ACPI_STATE_UNKNOWN;
if (!device || !state)
return -EINVAL;
- *state = ACPI_STATE_UNKNOWN;
-
- if (device->flags.power_manageable) {
- /*
- * Get the device's power state either directly (via _PSC) or
- * indirectly (via power resources).
- */
- if (device->power.flags.power_resources) {
- result = acpi_power_get_inferred_state(device, state);
- if (result)
- return result;
- } else if (device->power.flags.explicit_get) {
- status = acpi_evaluate_integer(device->handle, "_PSC",
- NULL, &psc);
- if (ACPI_FAILURE(status))
- return -ENODEV;
- *state = (int)psc;
- }
- } else {
+ if (!device->flags.power_manageable) {
/* TBD: Non-recursive algorithm for walking up hierarchy. */
*state = device->parent ?
device->parent->power.state : ACPI_STATE_D0;
+ goto out;
}
- ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device [%s] power state is D%d\n",
- device->pnp.bus_id, *state));
+ /*
+ * Get the device's power state either directly (via _PSC) or
+ * indirectly (via power resources).
+ */
+ if (device->power.flags.explicit_get) {
+ unsigned long long psc;
+ acpi_status status = acpi_evaluate_integer(device->handle,
+ "_PSC", NULL, &psc);
+ if (ACPI_FAILURE(status))
+ return -ENODEV;
+
+ result = psc;
+ }
+ /* The test below covers ACPI_STATE_UNKNOWN too. */
+ if (result <= ACPI_STATE_D2) {
+ ; /* Do nothing. */
+ } else if (device->power.flags.power_resources) {
+ int error = acpi_power_get_inferred_state(device, &result);
+ if (error)
+ return error;
+ } else if (result == ACPI_STATE_D3_HOT) {
+ result = ACPI_STATE_D3;
+ }
+ *state = result;
+
+ out:
+ ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device [%s] power state is %s\n",
+ device->pnp.bus_id, state_string(*state)));
return 0;
}
@@ -234,13 +259,14 @@
/* Make sure this is a valid target state */
if (state == device->power.state) {
- ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device is already at D%d\n",
- state));
+ ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device is already at %s\n",
+ state_string(state)));
return 0;
}
if (!device->power.states[state].flags.valid) {
- printk(KERN_WARNING PREFIX "Device does not support D%d\n", state);
+ printk(KERN_WARNING PREFIX "Device does not support %s\n",
+ state_string(state));
return -ENODEV;
}
if (device->parent && (state < device->parent->power.state)) {
@@ -294,13 +320,13 @@
end:
if (result)
printk(KERN_WARNING PREFIX
- "Device [%s] failed to transition to D%d\n",
- device->pnp.bus_id, state);
+ "Device [%s] failed to transition to %s\n",
+ device->pnp.bus_id, state_string(state));
else {
device->power.state = state;
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
- "Device [%s] transitioned to D%d\n",
- device->pnp.bus_id, state));
+ "Device [%s] transitioned to %s\n",
+ device->pnp.bus_id, state_string(state)));
}
return result;
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index 0500f71..dd6d6a3 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -631,7 +631,7 @@
* We know a device's inferred power state when all the resources
* required for a given D-state are 'on'.
*/
- for (i = ACPI_STATE_D0; i < ACPI_STATE_D3_HOT; i++) {
+ for (i = ACPI_STATE_D0; i <= ACPI_STATE_D3_HOT; i++) {
list = &device->power.states[i].resources;
if (list->count < 1)
continue;
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 0af48a8..a093dc1 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -333,6 +333,7 @@
struct acpi_buffer state = { 0, NULL };
union acpi_object *pss = NULL;
int i;
+ int last_invalid = -1;
status = acpi_evaluate_object(pr->handle, "_PSS", NULL, &buffer);
@@ -394,14 +395,33 @@
((u32)(px->core_frequency * 1000) !=
(px->core_frequency * 1000))) {
printk(KERN_ERR FW_BUG PREFIX
- "Invalid BIOS _PSS frequency: 0x%llx MHz\n",
- px->core_frequency);
- result = -EFAULT;
- kfree(pr->performance->states);
- goto end;
+ "Invalid BIOS _PSS frequency found for processor %d: 0x%llx MHz\n",
+ pr->id, px->core_frequency);
+ if (last_invalid == -1)
+ last_invalid = i;
+ } else {
+ if (last_invalid != -1) {
+ /*
+ * Copy this valid entry over last_invalid entry
+ */
+ memcpy(&(pr->performance->states[last_invalid]),
+ px, sizeof(struct acpi_processor_px));
+ ++last_invalid;
+ }
}
}
+ if (last_invalid == 0) {
+ printk(KERN_ERR FW_BUG PREFIX
+ "No valid BIOS _PSS frequency found for processor %d\n", pr->id);
+ result = -EFAULT;
+ kfree(pr->performance->states);
+ pr->performance->states = NULL;
+ }
+
+ if (last_invalid > 0)
+ pr->performance->state_count = last_invalid;
+
end:
kfree(buffer.pointer);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 85cbfdc..c8a1f3b 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1567,6 +1567,7 @@
ACPI_BUS_TYPE_POWER_BUTTON,
ACPI_STA_DEFAULT,
&ops);
+ device_init_wakeup(&device->dev, true);
}
if ((acpi_gbl_FADT.flags & ACPI_FADT_SLEEP_BUTTON) == 0) {
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 74ee4ab..88561029 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -57,6 +57,7 @@
MODULE_PARM_DESC(bfs, "Enable evaluation of _BFS on resume".);
static u8 sleep_states[ACPI_S_STATE_COUNT];
+static bool pwr_btn_event_pending;
static void acpi_sleep_tts_switch(u32 acpi_state)
{
@@ -184,6 +185,14 @@
return error;
}
+static int find_powerf_dev(struct device *dev, void *data)
+{
+ struct acpi_device *device = to_acpi_device(dev);
+ const char *hid = acpi_device_hid(device);
+
+ return !strcmp(hid, ACPI_BUTTON_HID_POWERF);
+}
+
/**
* acpi_pm_finish - Instruct the platform to leave a sleep state.
*
@@ -192,6 +201,7 @@
*/
static void acpi_pm_finish(void)
{
+ struct device *pwr_btn_dev;
u32 acpi_state = acpi_target_sleep_state;
acpi_ec_unblock_transactions();
@@ -209,6 +219,23 @@
acpi_set_firmware_waking_vector((acpi_physical_address) 0);
acpi_target_sleep_state = ACPI_STATE_S0;
+
+ /* If we were woken with the fixed power button, provide a small
+ * hint to userspace in the form of a wakeup event on the fixed power
+ * button device (if it can be found).
+ *
+ * We delay the event generation til now, as the PM layer requires
+ * timekeeping to be running before we generate events. */
+ if (!pwr_btn_event_pending)
+ return;
+
+ pwr_btn_event_pending = false;
+ pwr_btn_dev = bus_find_device(&acpi_bus_type, NULL, NULL,
+ find_powerf_dev);
+ if (pwr_btn_dev) {
+ pm_wakeup_event(pwr_btn_dev, 0);
+ put_device(pwr_btn_dev);
+ }
}
/**
@@ -298,9 +325,23 @@
/* ACPI 3.0 specs (P62) says that it's the responsibility
* of the OSPM to clear the status bit [ implying that the
* POWER_BUTTON event should not reach userspace ]
+ *
+ * However, we do generate a small hint for userspace in the form of
+ * a wakeup event. We flag this condition for now and generate the
+ * event later, as we're currently too early in resume to be able to
+ * generate wakeup events.
*/
- if (ACPI_SUCCESS(status) && (acpi_state == ACPI_STATE_S3))
- acpi_clear_event(ACPI_EVENT_POWER_BUTTON);
+ if (ACPI_SUCCESS(status) && (acpi_state == ACPI_STATE_S3)) {
+ acpi_event_status pwr_btn_status;
+
+ acpi_get_event_status(ACPI_EVENT_POWER_BUTTON, &pwr_btn_status);
+
+ if (pwr_btn_status & ACPI_EVENT_FLAG_SET) {
+ acpi_clear_event(ACPI_EVENT_POWER_BUTTON);
+ /* Flag for later */
+ pwr_btn_event_pending = true;
+ }
+ }
/*
* Disable and clear GPE status before interrupt is enabled. Some GPEs
@@ -730,8 +771,8 @@
* can wake the system. _S0W may be valid, too.
*/
if (acpi_target_sleep_state == ACPI_STATE_S0 ||
- (device_may_wakeup(dev) &&
- adev->wakeup.sleep_state <= acpi_target_sleep_state)) {
+ (device_may_wakeup(dev) && adev->wakeup.flags.valid &&
+ adev->wakeup.sleep_state >= acpi_target_sleep_state)) {
acpi_status status;
acpi_method[3] = 'W';
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index 9577b6f..a576575 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -1687,10 +1687,6 @@
set_bit(KEY_BRIGHTNESS_ZERO, input->keybit);
set_bit(KEY_DISPLAY_OFF, input->keybit);
- error = input_register_device(input);
- if (error)
- goto err_stop_video;
-
printk(KERN_INFO PREFIX "%s [%s] (multi-head: %s rom: %s post: %s)\n",
ACPI_VIDEO_DEVICE_NAME, acpi_device_bid(device),
video->flags.multihead ? "yes" : "no",
@@ -1701,12 +1697,16 @@
video->pm_nb.priority = 0;
error = register_pm_notifier(&video->pm_nb);
if (error)
- goto err_unregister_input_dev;
+ goto err_stop_video;
+
+ error = input_register_device(input);
+ if (error)
+ goto err_unregister_pm_notifier;
return 0;
- err_unregister_input_dev:
- input_unregister_device(input);
+ err_unregister_pm_notifier:
+ unregister_pm_notifier(&video->pm_nb);
err_stop_video:
acpi_video_bus_stop_devices(video);
err_free_input_dev:
@@ -1743,9 +1743,18 @@
return 0;
}
+static int __init is_i740(struct pci_dev *dev)
+{
+ if (dev->device == 0x00D1)
+ return 1;
+ if (dev->device == 0x7000)
+ return 1;
+ return 0;
+}
+
static int __init intel_opregion_present(void)
{
-#if defined(CONFIG_DRM_I915) || defined(CONFIG_DRM_I915_MODULE)
+ int opregion = 0;
struct pci_dev *dev = NULL;
u32 address;
@@ -1754,13 +1763,15 @@
continue;
if (dev->vendor != PCI_VENDOR_ID_INTEL)
continue;
+ /* We don't want to poke around undefined i740 registers */
+ if (is_i740(dev))
+ continue;
pci_read_config_dword(dev, 0xfc, &address);
if (!address)
continue;
- return 1;
+ opregion = 1;
}
-#endif
- return 0;
+ return opregion;
}
int acpi_video_register(void)
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 0bcda48..c89aa01 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -246,11 +246,11 @@
map->lock = regmap_lock_mutex;
map->unlock = regmap_unlock_mutex;
}
- map->format.buf_size = (config->reg_bits + config->val_bits) / 8;
map->format.reg_bytes = DIV_ROUND_UP(config->reg_bits, 8);
map->format.pad_bytes = config->pad_bits / 8;
map->format.val_bytes = DIV_ROUND_UP(config->val_bits, 8);
- map->format.buf_size += map->format.pad_bytes;
+ map->format.buf_size = DIV_ROUND_UP(config->reg_bits +
+ config->val_bits + config->pad_bits, 8);
map->reg_shift = config->pad_bits % 8;
if (config->reg_stride)
map->reg_stride = config->reg_stride;
@@ -368,7 +368,7 @@
ret = regcache_init(map, config);
if (ret < 0)
- goto err_free_workbuf;
+ goto err_debugfs;
/* Add a devres resource for dev_get_regmap() */
m = devres_alloc(dev_get_regmap_release, sizeof(*m), GFP_KERNEL);
@@ -383,7 +383,8 @@
err_cache:
regcache_exit(map);
-err_free_workbuf:
+err_debugfs:
+ regmap_debugfs_exit(map);
kfree(map->work_buf);
err_map:
kfree(map);
@@ -471,6 +472,7 @@
return ret;
}
+EXPORT_SYMBOL_GPL(regmap_reinit_cache);
/**
* regmap_exit(): Free a previously allocated register map
diff --git a/drivers/bcma/driver_pci.c b/drivers/bcma/driver_pci.c
index 9a96f14..c32ebd5 100644
--- a/drivers/bcma/driver_pci.c
+++ b/drivers/bcma/driver_pci.c
@@ -232,17 +232,19 @@
int bcma_core_pci_irq_ctl(struct bcma_drv_pci *pc, struct bcma_device *core,
bool enable)
{
- struct pci_dev *pdev = pc->core->bus->host_pci;
+ struct pci_dev *pdev;
u32 coremask, tmp;
int err = 0;
- if (core->bus->hosttype != BCMA_HOSTTYPE_PCI) {
+ if (!pc || core->bus->hosttype != BCMA_HOSTTYPE_PCI) {
/* This bcma device is not on a PCI host-bus. So the IRQs are
* not routed through the PCI core.
* So we must not enable routing through the PCI core. */
goto out;
}
+ pdev = pc->core->bus->host_pci;
+
err = pci_read_config_dword(pdev, BCMA_PCI_IRQMASK, &tmp);
if (err)
goto out;
diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c
index 764f70c..0a41852 100644
--- a/drivers/char/agp/intel-agp.c
+++ b/drivers/char/agp/intel-agp.c
@@ -898,6 +898,7 @@
ID(PCI_DEVICE_ID_INTEL_B43_HB),
ID(PCI_DEVICE_ID_INTEL_B43_1_HB),
ID(PCI_DEVICE_ID_INTEL_IRONLAKE_D_HB),
+ ID(PCI_DEVICE_ID_INTEL_IRONLAKE_D2_HB),
ID(PCI_DEVICE_ID_INTEL_IRONLAKE_M_HB),
ID(PCI_DEVICE_ID_INTEL_IRONLAKE_MA_HB),
ID(PCI_DEVICE_ID_INTEL_IRONLAKE_MC2_HB),
diff --git a/drivers/char/agp/intel-agp.h b/drivers/char/agp/intel-agp.h
index c009175..8e2d914 100644
--- a/drivers/char/agp/intel-agp.h
+++ b/drivers/char/agp/intel-agp.h
@@ -212,6 +212,7 @@
#define PCI_DEVICE_ID_INTEL_G41_HB 0x2E30
#define PCI_DEVICE_ID_INTEL_G41_IG 0x2E32
#define PCI_DEVICE_ID_INTEL_IRONLAKE_D_HB 0x0040
+#define PCI_DEVICE_ID_INTEL_IRONLAKE_D2_HB 0x0069
#define PCI_DEVICE_ID_INTEL_IRONLAKE_D_IG 0x0042
#define PCI_DEVICE_ID_INTEL_IRONLAKE_M_HB 0x0044
#define PCI_DEVICE_ID_INTEL_IRONLAKE_MA_HB 0x0062
diff --git a/drivers/char/hw_random/atmel-rng.c b/drivers/char/hw_random/atmel-rng.c
index f518b99..6289f0e 100644
--- a/drivers/char/hw_random/atmel-rng.c
+++ b/drivers/char/hw_random/atmel-rng.c
@@ -36,6 +36,13 @@
/* data ready? */
if (readl(trng->base + TRNG_ODATA) & 1) {
*data = readl(trng->base + TRNG_ODATA);
+ /*
+ ensure data ready is only set again AFTER the next data
+ word is ready in case it got set between checking ISR
+ and reading ODATA, so we don't risk re-reading the
+ same word
+ */
+ readl(trng->base + TRNG_ISR);
return 4;
} else
return 0;
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 8d81a1d..dd3e661 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -6,6 +6,7 @@
obj-$(CONFIG_SH_TIMER_CMT) += sh_cmt.o
obj-$(CONFIG_SH_TIMER_MTU2) += sh_mtu2.o
obj-$(CONFIG_SH_TIMER_TMU) += sh_tmu.o
+obj-$(CONFIG_EM_TIMER_STI) += em_sti.o
obj-$(CONFIG_CLKBLD_I8253) += i8253.o
obj-$(CONFIG_CLKSRC_MMIO) += mmio.o
obj-$(CONFIG_DW_APB_TIMER) += dw_apb_timer.o
diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c
new file mode 100644
index 0000000..372051d
--- /dev/null
+++ b/drivers/clocksource/em_sti.c
@@ -0,0 +1,406 @@
+/*
+ * Emma Mobile Timer Support - STI
+ *
+ * Copyright (C) 2012 Magnus Damm
+ *
+ * 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
+ *
+ * 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/irq.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+
+enum { USER_CLOCKSOURCE, USER_CLOCKEVENT, USER_NR };
+
+struct em_sti_priv {
+ void __iomem *base;
+ struct clk *clk;
+ struct platform_device *pdev;
+ unsigned int active[USER_NR];
+ unsigned long rate;
+ raw_spinlock_t lock;
+ struct clock_event_device ced;
+ struct clocksource cs;
+};
+
+#define STI_CONTROL 0x00
+#define STI_COMPA_H 0x10
+#define STI_COMPA_L 0x14
+#define STI_COMPB_H 0x18
+#define STI_COMPB_L 0x1c
+#define STI_COUNT_H 0x20
+#define STI_COUNT_L 0x24
+#define STI_COUNT_RAW_H 0x28
+#define STI_COUNT_RAW_L 0x2c
+#define STI_SET_H 0x30
+#define STI_SET_L 0x34
+#define STI_INTSTATUS 0x40
+#define STI_INTRAWSTATUS 0x44
+#define STI_INTENSET 0x48
+#define STI_INTENCLR 0x4c
+#define STI_INTFFCLR 0x50
+
+static inline unsigned long em_sti_read(struct em_sti_priv *p, int offs)
+{
+ return ioread32(p->base + offs);
+}
+
+static inline void em_sti_write(struct em_sti_priv *p, int offs,
+ unsigned long value)
+{
+ iowrite32(value, p->base + offs);
+}
+
+static int em_sti_enable(struct em_sti_priv *p)
+{
+ int ret;
+
+ /* enable clock */
+ ret = clk_enable(p->clk);
+ if (ret) {
+ dev_err(&p->pdev->dev, "cannot enable clock\n");
+ return ret;
+ }
+
+ /* configure channel, periodic mode and maximum timeout */
+ p->rate = clk_get_rate(p->clk);
+
+ /* reset the counter */
+ em_sti_write(p, STI_SET_H, 0x40000000);
+ em_sti_write(p, STI_SET_L, 0x00000000);
+
+ /* mask and clear pending interrupts */
+ em_sti_write(p, STI_INTENCLR, 3);
+ em_sti_write(p, STI_INTFFCLR, 3);
+
+ /* enable updates of counter registers */
+ em_sti_write(p, STI_CONTROL, 1);
+
+ return 0;
+}
+
+static void em_sti_disable(struct em_sti_priv *p)
+{
+ /* mask interrupts */
+ em_sti_write(p, STI_INTENCLR, 3);
+
+ /* stop clock */
+ clk_disable(p->clk);
+}
+
+static cycle_t em_sti_count(struct em_sti_priv *p)
+{
+ cycle_t ticks;
+ unsigned long flags;
+
+ /* the STI hardware buffers the 48-bit count, but to
+ * break it out into two 32-bit access the registers
+ * must be accessed in a certain order.
+ * Always read STI_COUNT_H before STI_COUNT_L.
+ */
+ raw_spin_lock_irqsave(&p->lock, flags);
+ ticks = (cycle_t)(em_sti_read(p, STI_COUNT_H) & 0xffff) << 32;
+ ticks |= em_sti_read(p, STI_COUNT_L);
+ raw_spin_unlock_irqrestore(&p->lock, flags);
+
+ return ticks;
+}
+
+static cycle_t em_sti_set_next(struct em_sti_priv *p, cycle_t next)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&p->lock, flags);
+
+ /* mask compare A interrupt */
+ em_sti_write(p, STI_INTENCLR, 1);
+
+ /* update compare A value */
+ em_sti_write(p, STI_COMPA_H, next >> 32);
+ em_sti_write(p, STI_COMPA_L, next & 0xffffffff);
+
+ /* clear compare A interrupt source */
+ em_sti_write(p, STI_INTFFCLR, 1);
+
+ /* unmask compare A interrupt */
+ em_sti_write(p, STI_INTENSET, 1);
+
+ raw_spin_unlock_irqrestore(&p->lock, flags);
+
+ return next;
+}
+
+static irqreturn_t em_sti_interrupt(int irq, void *dev_id)
+{
+ struct em_sti_priv *p = dev_id;
+
+ p->ced.event_handler(&p->ced);
+ return IRQ_HANDLED;
+}
+
+static int em_sti_start(struct em_sti_priv *p, unsigned int user)
+{
+ unsigned long flags;
+ int used_before;
+ int ret = 0;
+
+ raw_spin_lock_irqsave(&p->lock, flags);
+ used_before = p->active[USER_CLOCKSOURCE] | p->active[USER_CLOCKEVENT];
+ if (!used_before)
+ ret = em_sti_enable(p);
+
+ if (!ret)
+ p->active[user] = 1;
+ raw_spin_unlock_irqrestore(&p->lock, flags);
+
+ return ret;
+}
+
+static void em_sti_stop(struct em_sti_priv *p, unsigned int user)
+{
+ unsigned long flags;
+ int used_before, used_after;
+
+ raw_spin_lock_irqsave(&p->lock, flags);
+ used_before = p->active[USER_CLOCKSOURCE] | p->active[USER_CLOCKEVENT];
+ p->active[user] = 0;
+ used_after = p->active[USER_CLOCKSOURCE] | p->active[USER_CLOCKEVENT];
+
+ if (used_before && !used_after)
+ em_sti_disable(p);
+ raw_spin_unlock_irqrestore(&p->lock, flags);
+}
+
+static struct em_sti_priv *cs_to_em_sti(struct clocksource *cs)
+{
+ return container_of(cs, struct em_sti_priv, cs);
+}
+
+static cycle_t em_sti_clocksource_read(struct clocksource *cs)
+{
+ return em_sti_count(cs_to_em_sti(cs));
+}
+
+static int em_sti_clocksource_enable(struct clocksource *cs)
+{
+ int ret;
+ struct em_sti_priv *p = cs_to_em_sti(cs);
+
+ ret = em_sti_start(p, USER_CLOCKSOURCE);
+ if (!ret)
+ __clocksource_updatefreq_hz(cs, p->rate);
+ return ret;
+}
+
+static void em_sti_clocksource_disable(struct clocksource *cs)
+{
+ em_sti_stop(cs_to_em_sti(cs), USER_CLOCKSOURCE);
+}
+
+static void em_sti_clocksource_resume(struct clocksource *cs)
+{
+ em_sti_clocksource_enable(cs);
+}
+
+static int em_sti_register_clocksource(struct em_sti_priv *p)
+{
+ struct clocksource *cs = &p->cs;
+
+ memset(cs, 0, sizeof(*cs));
+ cs->name = dev_name(&p->pdev->dev);
+ cs->rating = 200;
+ cs->read = em_sti_clocksource_read;
+ cs->enable = em_sti_clocksource_enable;
+ cs->disable = em_sti_clocksource_disable;
+ cs->suspend = em_sti_clocksource_disable;
+ cs->resume = em_sti_clocksource_resume;
+ cs->mask = CLOCKSOURCE_MASK(48);
+ cs->flags = CLOCK_SOURCE_IS_CONTINUOUS;
+
+ dev_info(&p->pdev->dev, "used as clock source\n");
+
+ /* Register with dummy 1 Hz value, gets updated in ->enable() */
+ clocksource_register_hz(cs, 1);
+ return 0;
+}
+
+static struct em_sti_priv *ced_to_em_sti(struct clock_event_device *ced)
+{
+ return container_of(ced, struct em_sti_priv, ced);
+}
+
+static void em_sti_clock_event_mode(enum clock_event_mode mode,
+ struct clock_event_device *ced)
+{
+ struct em_sti_priv *p = ced_to_em_sti(ced);
+
+ /* deal with old setting first */
+ switch (ced->mode) {
+ case CLOCK_EVT_MODE_ONESHOT:
+ em_sti_stop(p, USER_CLOCKEVENT);
+ break;
+ default:
+ break;
+ }
+
+ switch (mode) {
+ case CLOCK_EVT_MODE_ONESHOT:
+ dev_info(&p->pdev->dev, "used for oneshot clock events\n");
+ em_sti_start(p, USER_CLOCKEVENT);
+ clockevents_config(&p->ced, p->rate);
+ break;
+ case CLOCK_EVT_MODE_SHUTDOWN:
+ case CLOCK_EVT_MODE_UNUSED:
+ em_sti_stop(p, USER_CLOCKEVENT);
+ break;
+ default:
+ break;
+ }
+}
+
+static int em_sti_clock_event_next(unsigned long delta,
+ struct clock_event_device *ced)
+{
+ struct em_sti_priv *p = ced_to_em_sti(ced);
+ cycle_t next;
+ int safe;
+
+ next = em_sti_set_next(p, em_sti_count(p) + delta);
+ safe = em_sti_count(p) < (next - 1);
+
+ return !safe;
+}
+
+static void em_sti_register_clockevent(struct em_sti_priv *p)
+{
+ struct clock_event_device *ced = &p->ced;
+
+ memset(ced, 0, sizeof(*ced));
+ ced->name = dev_name(&p->pdev->dev);
+ ced->features = CLOCK_EVT_FEAT_ONESHOT;
+ ced->rating = 200;
+ ced->cpumask = cpumask_of(0);
+ ced->set_next_event = em_sti_clock_event_next;
+ ced->set_mode = em_sti_clock_event_mode;
+
+ dev_info(&p->pdev->dev, "used for clock events\n");
+
+ /* Register with dummy 1 Hz value, gets updated in ->set_mode() */
+ clockevents_config_and_register(ced, 1, 2, 0xffffffff);
+}
+
+static int __devinit em_sti_probe(struct platform_device *pdev)
+{
+ struct em_sti_priv *p;
+ struct resource *res;
+ int irq, ret;
+
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (p == NULL) {
+ dev_err(&pdev->dev, "failed to allocate driver data\n");
+ ret = -ENOMEM;
+ goto err0;
+ }
+
+ p->pdev = pdev;
+ platform_set_drvdata(pdev, p);
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res) {
+ dev_err(&pdev->dev, "failed to get I/O memory\n");
+ ret = -EINVAL;
+ goto err0;
+ }
+
+ irq = platform_get_irq(pdev, 0);
+ if (irq < 0) {
+ dev_err(&pdev->dev, "failed to get irq\n");
+ ret = -EINVAL;
+ goto err0;
+ }
+
+ /* map memory, let base point to the STI instance */
+ p->base = ioremap_nocache(res->start, resource_size(res));
+ if (p->base == NULL) {
+ dev_err(&pdev->dev, "failed to remap I/O memory\n");
+ ret = -ENXIO;
+ goto err0;
+ }
+
+ /* get hold of clock */
+ p->clk = clk_get(&pdev->dev, "sclk");
+ if (IS_ERR(p->clk)) {
+ dev_err(&pdev->dev, "cannot get clock\n");
+ ret = PTR_ERR(p->clk);
+ goto err1;
+ }
+
+ if (request_irq(irq, em_sti_interrupt,
+ IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING,
+ dev_name(&pdev->dev), p)) {
+ dev_err(&pdev->dev, "failed to request low IRQ\n");
+ ret = -ENOENT;
+ goto err2;
+ }
+
+ raw_spin_lock_init(&p->lock);
+ em_sti_register_clockevent(p);
+ em_sti_register_clocksource(p);
+ return 0;
+
+err2:
+ clk_put(p->clk);
+err1:
+ iounmap(p->base);
+err0:
+ kfree(p);
+ return ret;
+}
+
+static int __devexit em_sti_remove(struct platform_device *pdev)
+{
+ return -EBUSY; /* cannot unregister clockevent and clocksource */
+}
+
+static const struct of_device_id em_sti_dt_ids[] __devinitconst = {
+ { .compatible = "renesas,em-sti", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, em_sti_dt_ids);
+
+static struct platform_driver em_sti_device_driver = {
+ .probe = em_sti_probe,
+ .remove = __devexit_p(em_sti_remove),
+ .driver = {
+ .name = "em_sti",
+ .of_match_table = em_sti_dt_ids,
+ }
+};
+
+module_platform_driver(em_sti_device_driver);
+
+MODULE_AUTHOR("Magnus Damm");
+MODULE_DESCRIPTION("Renesas Emma Mobile STI Timer Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index 32fe9ef..98b06ba 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -48,13 +48,13 @@
unsigned long next_match_value;
unsigned long max_match_value;
unsigned long rate;
- spinlock_t lock;
+ raw_spinlock_t lock;
struct clock_event_device ced;
struct clocksource cs;
unsigned long total_cycles;
};
-static DEFINE_SPINLOCK(sh_cmt_lock);
+static DEFINE_RAW_SPINLOCK(sh_cmt_lock);
#define CMSTR -1 /* shared register */
#define CMCSR 0 /* channel register */
@@ -139,7 +139,7 @@
unsigned long flags, value;
/* start stop register shared by multiple timer channels */
- spin_lock_irqsave(&sh_cmt_lock, flags);
+ raw_spin_lock_irqsave(&sh_cmt_lock, flags);
value = sh_cmt_read(p, CMSTR);
if (start)
@@ -148,7 +148,7 @@
value &= ~(1 << cfg->timer_bit);
sh_cmt_write(p, CMSTR, value);
- spin_unlock_irqrestore(&sh_cmt_lock, flags);
+ raw_spin_unlock_irqrestore(&sh_cmt_lock, flags);
}
static int sh_cmt_enable(struct sh_cmt_priv *p, unsigned long *rate)
@@ -328,9 +328,9 @@
{
unsigned long flags;
- spin_lock_irqsave(&p->lock, flags);
+ raw_spin_lock_irqsave(&p->lock, flags);
__sh_cmt_set_next(p, delta);
- spin_unlock_irqrestore(&p->lock, flags);
+ raw_spin_unlock_irqrestore(&p->lock, flags);
}
static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id)
@@ -385,7 +385,7 @@
int ret = 0;
unsigned long flags;
- spin_lock_irqsave(&p->lock, flags);
+ raw_spin_lock_irqsave(&p->lock, flags);
if (!(p->flags & (FLAG_CLOCKEVENT | FLAG_CLOCKSOURCE)))
ret = sh_cmt_enable(p, &p->rate);
@@ -398,7 +398,7 @@
if ((flag == FLAG_CLOCKSOURCE) && (!(p->flags & FLAG_CLOCKEVENT)))
__sh_cmt_set_next(p, p->max_match_value);
out:
- spin_unlock_irqrestore(&p->lock, flags);
+ raw_spin_unlock_irqrestore(&p->lock, flags);
return ret;
}
@@ -408,7 +408,7 @@
unsigned long flags;
unsigned long f;
- spin_lock_irqsave(&p->lock, flags);
+ raw_spin_lock_irqsave(&p->lock, flags);
f = p->flags & (FLAG_CLOCKEVENT | FLAG_CLOCKSOURCE);
p->flags &= ~flag;
@@ -420,7 +420,7 @@
if ((flag == FLAG_CLOCKEVENT) && (p->flags & FLAG_CLOCKSOURCE))
__sh_cmt_set_next(p, p->max_match_value);
- spin_unlock_irqrestore(&p->lock, flags);
+ raw_spin_unlock_irqrestore(&p->lock, flags);
}
static struct sh_cmt_priv *cs_to_sh_cmt(struct clocksource *cs)
@@ -435,13 +435,13 @@
unsigned long value;
int has_wrapped;
- spin_lock_irqsave(&p->lock, flags);
+ raw_spin_lock_irqsave(&p->lock, flags);
value = p->total_cycles;
raw = sh_cmt_get_counter(p, &has_wrapped);
if (unlikely(has_wrapped))
raw += p->match_value + 1;
- spin_unlock_irqrestore(&p->lock, flags);
+ raw_spin_unlock_irqrestore(&p->lock, flags);
return value + raw;
}
@@ -591,7 +591,7 @@
p->max_match_value = (1 << p->width) - 1;
p->match_value = p->max_match_value;
- spin_lock_init(&p->lock);
+ raw_spin_lock_init(&p->lock);
if (clockevent_rating)
sh_cmt_register_clockevent(p, name, clockevent_rating);
diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c
index a2172f6..d9b76ca 100644
--- a/drivers/clocksource/sh_mtu2.c
+++ b/drivers/clocksource/sh_mtu2.c
@@ -43,7 +43,7 @@
struct clock_event_device ced;
};
-static DEFINE_SPINLOCK(sh_mtu2_lock);
+static DEFINE_RAW_SPINLOCK(sh_mtu2_lock);
#define TSTR -1 /* shared register */
#define TCR 0 /* channel register */
@@ -107,7 +107,7 @@
unsigned long flags, value;
/* start stop register shared by multiple timer channels */
- spin_lock_irqsave(&sh_mtu2_lock, flags);
+ raw_spin_lock_irqsave(&sh_mtu2_lock, flags);
value = sh_mtu2_read(p, TSTR);
if (start)
@@ -116,7 +116,7 @@
value &= ~(1 << cfg->timer_bit);
sh_mtu2_write(p, TSTR, value);
- spin_unlock_irqrestore(&sh_mtu2_lock, flags);
+ raw_spin_unlock_irqrestore(&sh_mtu2_lock, flags);
}
static int sh_mtu2_enable(struct sh_mtu2_priv *p)
diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c
index 97f54b6..c1b51d4 100644
--- a/drivers/clocksource/sh_tmu.c
+++ b/drivers/clocksource/sh_tmu.c
@@ -45,7 +45,7 @@
struct clocksource cs;
};
-static DEFINE_SPINLOCK(sh_tmu_lock);
+static DEFINE_RAW_SPINLOCK(sh_tmu_lock);
#define TSTR -1 /* shared register */
#define TCOR 0 /* channel register */
@@ -95,7 +95,7 @@
unsigned long flags, value;
/* start stop register shared by multiple timer channels */
- spin_lock_irqsave(&sh_tmu_lock, flags);
+ raw_spin_lock_irqsave(&sh_tmu_lock, flags);
value = sh_tmu_read(p, TSTR);
if (start)
@@ -104,7 +104,7 @@
value &= ~(1 << cfg->timer_bit);
sh_tmu_write(p, TSTR, value);
- spin_unlock_irqrestore(&sh_tmu_lock, flags);
+ raw_spin_unlock_irqrestore(&sh_tmu_lock, flags);
}
static int sh_tmu_enable(struct sh_tmu_priv *p)
@@ -245,12 +245,7 @@
sh_tmu_enable(p);
- /* TODO: calculate good shift from rate and counter bit width */
-
- ced->shift = 32;
- ced->mult = div_sc(p->rate, NSEC_PER_SEC, ced->shift);
- ced->max_delta_ns = clockevent_delta2ns(0xffffffff, ced);
- ced->min_delta_ns = 5000;
+ clockevents_config(ced, p->rate);
if (periodic) {
p->periodic = (p->rate + HZ/2) / HZ;
@@ -323,7 +318,8 @@
ced->set_mode = sh_tmu_clock_event_mode;
dev_info(&p->pdev->dev, "used for clock events\n");
- clockevents_register_device(ced);
+
+ clockevents_config_and_register(ced, 1, 0x300, 0xffffffff);
ret = setup_irq(p->irqaction.irq, &p->irqaction);
if (ret) {
diff --git a/drivers/gpio/gpio-samsung.c b/drivers/gpio/gpio-samsung.c
index 7bb0044..b6453d0 100644
--- a/drivers/gpio/gpio-samsung.c
+++ b/drivers/gpio/gpio-samsung.c
@@ -2833,7 +2833,7 @@
}
/* need to set base address for gpc4 */
- exonys5_gpios_1[11].base = gpio_base1 + 0x2E0;
+ exynos5_gpios_1[11].base = gpio_base1 + 0x2E0;
/* need to set base address for gpx */
chip = &exynos5_gpios_1[21];
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 4209531..d6de2e07f 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -244,8 +244,8 @@
};
static struct drm_driver exynos_drm_driver = {
- .driver_features = DRIVER_HAVE_IRQ | DRIVER_BUS_PLATFORM |
- DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME,
+ .driver_features = DRIVER_HAVE_IRQ | DRIVER_MODESET |
+ DRIVER_GEM | DRIVER_PRIME,
.load = exynos_drm_load,
.unload = exynos_drm_unload,
.open = exynos_drm_open,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_encoder.c b/drivers/gpu/drm/exynos/exynos_drm_encoder.c
index 6e9ac7b..23d5ad3 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_encoder.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_encoder.c
@@ -172,19 +172,12 @@
manager_ops->commit(manager->dev);
}
-static struct drm_crtc *
-exynos_drm_encoder_get_crtc(struct drm_encoder *encoder)
-{
- return encoder->crtc;
-}
-
static struct drm_encoder_helper_funcs exynos_encoder_helper_funcs = {
.dpms = exynos_drm_encoder_dpms,
.mode_fixup = exynos_drm_encoder_mode_fixup,
.mode_set = exynos_drm_encoder_mode_set,
.prepare = exynos_drm_encoder_prepare,
.commit = exynos_drm_encoder_commit,
- .get_crtc = exynos_drm_encoder_get_crtc,
};
static void exynos_drm_encoder_destroy(struct drm_encoder *encoder)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index f82a299..4ccfe43 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -51,11 +51,22 @@
static void exynos_drm_fb_destroy(struct drm_framebuffer *fb)
{
struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb);
+ unsigned int i;
DRM_DEBUG_KMS("%s\n", __FILE__);
drm_framebuffer_cleanup(fb);
+ for (i = 0; i < ARRAY_SIZE(exynos_fb->exynos_gem_obj); i++) {
+ struct drm_gem_object *obj;
+
+ if (exynos_fb->exynos_gem_obj[i] == NULL)
+ continue;
+
+ obj = &exynos_fb->exynos_gem_obj[i]->base;
+ drm_gem_object_unreference_unlocked(obj);
+ }
+
kfree(exynos_fb);
exynos_fb = NULL;
}
@@ -134,11 +145,11 @@
return ERR_PTR(-ENOENT);
}
- drm_gem_object_unreference_unlocked(obj);
-
fb = exynos_drm_framebuffer_init(dev, mode_cmd, obj);
- if (IS_ERR(fb))
+ if (IS_ERR(fb)) {
+ drm_gem_object_unreference_unlocked(obj);
return fb;
+ }
exynos_fb = to_exynos_fb(fb);
nr = exynos_drm_format_num_buffers(fb->pixel_format);
@@ -152,8 +163,6 @@
return ERR_PTR(-ENOENT);
}
- drm_gem_object_unreference_unlocked(obj);
-
exynos_fb->exynos_gem_obj[i] = to_exynos_gem_obj(obj);
}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.h b/drivers/gpu/drm/exynos/exynos_drm_fb.h
index 3ecb30d..5082375 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.h
@@ -31,10 +31,10 @@
static inline int exynos_drm_format_num_buffers(uint32_t format)
{
switch (format) {
- case DRM_FORMAT_NV12M:
+ case DRM_FORMAT_NV12:
case DRM_FORMAT_NV12MT:
return 2;
- case DRM_FORMAT_YUV420M:
+ case DRM_FORMAT_YUV420:
return 3;
default:
return 1;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index fc91293..5c8b683 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -689,7 +689,6 @@
struct drm_device *dev, uint32_t handle,
uint64_t *offset)
{
- struct exynos_drm_gem_obj *exynos_gem_obj;
struct drm_gem_object *obj;
int ret = 0;
@@ -710,15 +709,13 @@
goto unlock;
}
- exynos_gem_obj = to_exynos_gem_obj(obj);
-
- if (!exynos_gem_obj->base.map_list.map) {
- ret = drm_gem_create_mmap_offset(&exynos_gem_obj->base);
+ if (!obj->map_list.map) {
+ ret = drm_gem_create_mmap_offset(obj);
if (ret)
goto out;
}
- *offset = (u64)exynos_gem_obj->base.map_list.hash.key << PAGE_SHIFT;
+ *offset = (u64)obj->map_list.hash.key << PAGE_SHIFT;
DRM_DEBUG_KMS("offset = 0x%lx\n", (unsigned long)*offset);
out:
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 68ef010..e2147a2 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -365,7 +365,7 @@
switch (win_data->pixel_format) {
case DRM_FORMAT_NV12MT:
tiled_mode = true;
- case DRM_FORMAT_NV12M:
+ case DRM_FORMAT_NV12:
crcb_mode = false;
buf_num = 2;
break;
@@ -601,18 +601,20 @@
mixer_reg_write(res, MXR_BG_COLOR2, 0x008080);
/* setting graphical layers */
-
val = MXR_GRP_CFG_COLOR_KEY_DISABLE; /* no blank key */
val |= MXR_GRP_CFG_WIN_BLEND_EN;
+ val |= MXR_GRP_CFG_BLEND_PRE_MUL;
+ val |= MXR_GRP_CFG_PIXEL_BLEND_EN;
val |= MXR_GRP_CFG_ALPHA_VAL(0xff); /* non-transparent alpha */
/* the same configuration for both layers */
mixer_reg_write(res, MXR_GRAPHIC_CFG(0), val);
-
- val |= MXR_GRP_CFG_BLEND_PRE_MUL;
- val |= MXR_GRP_CFG_PIXEL_BLEND_EN;
mixer_reg_write(res, MXR_GRAPHIC_CFG(1), val);
+ /* setting video layers */
+ val = MXR_GRP_CFG_ALPHA_VAL(0);
+ mixer_reg_write(res, MXR_VIDEO_CFG, val);
+
/* configuration of Video Processor Registers */
vp_win_reset(ctx);
vp_default_filter(res);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 238a521..9fe9ebe 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -233,6 +233,7 @@
.has_blt_ring = 1,
.has_llc = 1,
.has_pch_split = 1,
+ .has_force_wake = 1,
};
static const struct intel_device_info intel_sandybridge_m_info = {
@@ -243,6 +244,7 @@
.has_blt_ring = 1,
.has_llc = 1,
.has_pch_split = 1,
+ .has_force_wake = 1,
};
static const struct intel_device_info intel_ivybridge_d_info = {
@@ -252,6 +254,7 @@
.has_blt_ring = 1,
.has_llc = 1,
.has_pch_split = 1,
+ .has_force_wake = 1,
};
static const struct intel_device_info intel_ivybridge_m_info = {
@@ -262,6 +265,7 @@
.has_blt_ring = 1,
.has_llc = 1,
.has_pch_split = 1,
+ .has_force_wake = 1,
};
static const struct intel_device_info intel_valleyview_m_info = {
@@ -289,6 +293,7 @@
.has_blt_ring = 1,
.has_llc = 1,
.has_pch_split = 1,
+ .has_force_wake = 1,
};
static const struct intel_device_info intel_haswell_m_info = {
@@ -298,6 +303,7 @@
.has_blt_ring = 1,
.has_llc = 1,
.has_pch_split = 1,
+ .has_force_wake = 1,
};
static const struct pci_device_id pciidlist[] = { /* aka */
@@ -1139,10 +1145,9 @@
/* We give fast paths for the really cool registers */
#define NEEDS_FORCE_WAKE(dev_priv, reg) \
- (((dev_priv)->info->gen >= 6) && \
- ((reg) < 0x40000) && \
- ((reg) != FORCEWAKE)) && \
- (!IS_VALLEYVIEW((dev_priv)->dev))
+ ((HAS_FORCE_WAKE((dev_priv)->dev)) && \
+ ((reg) < 0x40000) && \
+ ((reg) != FORCEWAKE))
#define __i915_read(x, y) \
u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c9cfc67..b0b676a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -285,6 +285,7 @@
u8 is_ivybridge:1;
u8 is_valleyview:1;
u8 has_pch_split:1;
+ u8 has_force_wake:1;
u8 is_haswell:1;
u8 has_fbc:1;
u8 has_pipe_cxsr:1;
@@ -1101,6 +1102,8 @@
#define HAS_PCH_CPT(dev) (INTEL_PCH_TYPE(dev) == PCH_CPT)
#define HAS_PCH_IBX(dev) (INTEL_PCH_TYPE(dev) == PCH_IBX)
+#define HAS_FORCE_WAKE(dev) (INTEL_INFO(dev)->has_force_wake)
+
#include "i915_trace.h"
/**
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 1417660..b1fe0ed 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -510,7 +510,7 @@
return ret;
}
-static void pch_irq_handler(struct drm_device *dev, u32 pch_iir)
+static void ibx_irq_handler(struct drm_device *dev, u32 pch_iir)
{
drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
int pipe;
@@ -550,6 +550,35 @@
DRM_DEBUG_DRIVER("PCH transcoder A underrun interrupt\n");
}
+static void cpt_irq_handler(struct drm_device *dev, u32 pch_iir)
+{
+ drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
+ int pipe;
+
+ if (pch_iir & SDE_AUDIO_POWER_MASK_CPT)
+ DRM_DEBUG_DRIVER("PCH audio power change on port %d\n",
+ (pch_iir & SDE_AUDIO_POWER_MASK_CPT) >>
+ SDE_AUDIO_POWER_SHIFT_CPT);
+
+ if (pch_iir & SDE_AUX_MASK_CPT)
+ DRM_DEBUG_DRIVER("AUX channel interrupt\n");
+
+ if (pch_iir & SDE_GMBUS_CPT)
+ DRM_DEBUG_DRIVER("PCH GMBUS interrupt\n");
+
+ if (pch_iir & SDE_AUDIO_CP_REQ_CPT)
+ DRM_DEBUG_DRIVER("Audio CP request interrupt\n");
+
+ if (pch_iir & SDE_AUDIO_CP_CHG_CPT)
+ DRM_DEBUG_DRIVER("Audio CP change interrupt\n");
+
+ if (pch_iir & SDE_FDI_MASK_CPT)
+ for_each_pipe(pipe)
+ DRM_DEBUG_DRIVER(" pipe %c FDI IIR: 0x%08x\n",
+ pipe_name(pipe),
+ I915_READ(FDI_RX_IIR(pipe)));
+}
+
static irqreturn_t ivybridge_irq_handler(DRM_IRQ_ARGS)
{
struct drm_device *dev = (struct drm_device *) arg;
@@ -591,7 +620,7 @@
if (pch_iir & SDE_HOTPLUG_MASK_CPT)
queue_work(dev_priv->wq, &dev_priv->hotplug_work);
- pch_irq_handler(dev, pch_iir);
+ cpt_irq_handler(dev, pch_iir);
/* clear PCH hotplug event before clear CPU irq */
I915_WRITE(SDEIIR, pch_iir);
@@ -684,7 +713,10 @@
if (de_iir & DE_PCH_EVENT) {
if (pch_iir & hotplug_mask)
queue_work(dev_priv->wq, &dev_priv->hotplug_work);
- pch_irq_handler(dev, pch_iir);
+ if (HAS_PCH_CPT(dev))
+ cpt_irq_handler(dev, pch_iir);
+ else
+ ibx_irq_handler(dev, pch_iir);
}
if (de_iir & DE_PCU_EVENT) {
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 2d49b95..48d5e8e 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -210,6 +210,14 @@
#define MI_DISPLAY_FLIP MI_INSTR(0x14, 2)
#define MI_DISPLAY_FLIP_I915 MI_INSTR(0x14, 1)
#define MI_DISPLAY_FLIP_PLANE(n) ((n) << 20)
+/* IVB has funny definitions for which plane to flip. */
+#define MI_DISPLAY_FLIP_IVB_PLANE_A (0 << 19)
+#define MI_DISPLAY_FLIP_IVB_PLANE_B (1 << 19)
+#define MI_DISPLAY_FLIP_IVB_SPRITE_A (2 << 19)
+#define MI_DISPLAY_FLIP_IVB_SPRITE_B (3 << 19)
+#define MI_DISPLAY_FLIP_IVB_PLANE_C (4 << 19)
+#define MI_DISPLAY_FLIP_IVB_SPRITE_C (5 << 19)
+
#define MI_SET_CONTEXT MI_INSTR(0x18, 0)
#define MI_MM_SPACE_GTT (1<<8)
#define MI_MM_SPACE_PHYSICAL (0<<8)
@@ -3313,7 +3321,7 @@
/* PCH */
-/* south display engine interrupt */
+/* south display engine interrupt: IBX */
#define SDE_AUDIO_POWER_D (1 << 27)
#define SDE_AUDIO_POWER_C (1 << 26)
#define SDE_AUDIO_POWER_B (1 << 25)
@@ -3349,15 +3357,44 @@
#define SDE_TRANSA_CRC_ERR (1 << 1)
#define SDE_TRANSA_FIFO_UNDER (1 << 0)
#define SDE_TRANS_MASK (0x3f)
-/* CPT */
-#define SDE_CRT_HOTPLUG_CPT (1 << 19)
+
+/* south display engine interrupt: CPT/PPT */
+#define SDE_AUDIO_POWER_D_CPT (1 << 31)
+#define SDE_AUDIO_POWER_C_CPT (1 << 30)
+#define SDE_AUDIO_POWER_B_CPT (1 << 29)
+#define SDE_AUDIO_POWER_SHIFT_CPT 29
+#define SDE_AUDIO_POWER_MASK_CPT (7 << 29)
+#define SDE_AUXD_CPT (1 << 27)
+#define SDE_AUXC_CPT (1 << 26)
+#define SDE_AUXB_CPT (1 << 25)
+#define SDE_AUX_MASK_CPT (7 << 25)
#define SDE_PORTD_HOTPLUG_CPT (1 << 23)
#define SDE_PORTC_HOTPLUG_CPT (1 << 22)
#define SDE_PORTB_HOTPLUG_CPT (1 << 21)
+#define SDE_CRT_HOTPLUG_CPT (1 << 19)
#define SDE_HOTPLUG_MASK_CPT (SDE_CRT_HOTPLUG_CPT | \
SDE_PORTD_HOTPLUG_CPT | \
SDE_PORTC_HOTPLUG_CPT | \
SDE_PORTB_HOTPLUG_CPT)
+#define SDE_GMBUS_CPT (1 << 17)
+#define SDE_AUDIO_CP_REQ_C_CPT (1 << 10)
+#define SDE_AUDIO_CP_CHG_C_CPT (1 << 9)
+#define SDE_FDI_RXC_CPT (1 << 8)
+#define SDE_AUDIO_CP_REQ_B_CPT (1 << 6)
+#define SDE_AUDIO_CP_CHG_B_CPT (1 << 5)
+#define SDE_FDI_RXB_CPT (1 << 4)
+#define SDE_AUDIO_CP_REQ_A_CPT (1 << 2)
+#define SDE_AUDIO_CP_CHG_A_CPT (1 << 1)
+#define SDE_FDI_RXA_CPT (1 << 0)
+#define SDE_AUDIO_CP_REQ_CPT (SDE_AUDIO_CP_REQ_C_CPT | \
+ SDE_AUDIO_CP_REQ_B_CPT | \
+ SDE_AUDIO_CP_REQ_A_CPT)
+#define SDE_AUDIO_CP_CHG_CPT (SDE_AUDIO_CP_CHG_C_CPT | \
+ SDE_AUDIO_CP_CHG_B_CPT | \
+ SDE_AUDIO_CP_CHG_A_CPT)
+#define SDE_FDI_MASK_CPT (SDE_FDI_RXC_CPT | \
+ SDE_FDI_RXB_CPT | \
+ SDE_FDI_RXA_CPT)
#define SDEISR 0xc4000
#define SDEIMR 0xc4004
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 9147894..e0aa064 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -6158,17 +6158,34 @@
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
struct intel_ring_buffer *ring = &dev_priv->ring[BCS];
+ uint32_t plane_bit = 0;
int ret;
ret = intel_pin_and_fence_fb_obj(dev, obj, ring);
if (ret)
goto err;
+ switch(intel_crtc->plane) {
+ case PLANE_A:
+ plane_bit = MI_DISPLAY_FLIP_IVB_PLANE_A;
+ break;
+ case PLANE_B:
+ plane_bit = MI_DISPLAY_FLIP_IVB_PLANE_B;
+ break;
+ case PLANE_C:
+ plane_bit = MI_DISPLAY_FLIP_IVB_PLANE_C;
+ break;
+ default:
+ WARN_ONCE(1, "unknown plane in flip command\n");
+ ret = -ENODEV;
+ goto err;
+ }
+
ret = intel_ring_begin(ring, 4);
if (ret)
goto err_unpin;
- intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | (intel_crtc->plane << 19));
+ intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | plane_bit);
intel_ring_emit(ring, (fb->pitches[0] | obj->tiling_mode));
intel_ring_emit(ring, (obj->gtt_offset));
intel_ring_emit(ring, (MI_NOOP));
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index b59b6d5..e5b84ff 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -266,10 +266,15 @@
static int init_ring_common(struct intel_ring_buffer *ring)
{
- drm_i915_private_t *dev_priv = ring->dev->dev_private;
+ struct drm_device *dev = ring->dev;
+ drm_i915_private_t *dev_priv = dev->dev_private;
struct drm_i915_gem_object *obj = ring->obj;
+ int ret = 0;
u32 head;
+ if (HAS_FORCE_WAKE(dev))
+ gen6_gt_force_wake_get(dev_priv);
+
/* Stop the ring if it's running. */
I915_WRITE_CTL(ring, 0);
I915_WRITE_HEAD(ring, 0);
@@ -317,7 +322,8 @@
I915_READ_HEAD(ring),
I915_READ_TAIL(ring),
I915_READ_START(ring));
- return -EIO;
+ ret = -EIO;
+ goto out;
}
if (!drm_core_check_feature(ring->dev, DRIVER_MODESET))
@@ -326,9 +332,14 @@
ring->head = I915_READ_HEAD(ring);
ring->tail = I915_READ_TAIL(ring) & TAIL_ADDR;
ring->space = ring_space(ring);
+ ring->last_retired_head = -1;
}
- return 0;
+out:
+ if (HAS_FORCE_WAKE(dev))
+ gen6_gt_force_wake_put(dev_priv);
+
+ return ret;
}
static int
@@ -987,6 +998,10 @@
if (ret)
goto err_unref;
+ ret = i915_gem_object_set_to_gtt_domain(obj, true);
+ if (ret)
+ goto err_unpin;
+
ring->virtual_start = ioremap_wc(dev->agp->base + obj->gtt_offset,
ring->size);
if (ring->virtual_start == NULL) {
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 4e7dd2b..c1655412 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -52,6 +52,7 @@
u32 cb_color_view[12];
u32 cb_color_pitch[12];
u32 cb_color_slice[12];
+ u32 cb_color_slice_idx[12];
u32 cb_color_attrib[12];
u32 cb_color_cmask_slice[8];/* unused */
u32 cb_color_fmask_slice[8];/* unused */
@@ -127,12 +128,14 @@
track->cb_color_info[i] = 0;
track->cb_color_view[i] = 0xFFFFFFFF;
track->cb_color_pitch[i] = 0;
- track->cb_color_slice[i] = 0;
+ track->cb_color_slice[i] = 0xfffffff;
+ track->cb_color_slice_idx[i] = 0;
}
track->cb_target_mask = 0xFFFFFFFF;
track->cb_shader_mask = 0xFFFFFFFF;
track->cb_dirty = true;
+ track->db_depth_slice = 0xffffffff;
track->db_depth_view = 0xFFFFC000;
track->db_depth_size = 0xFFFFFFFF;
track->db_depth_control = 0xFFFFFFFF;
@@ -250,10 +253,9 @@
{
struct evergreen_cs_track *track = p->track;
unsigned palign, halign, tileb, slice_pt;
+ unsigned mtile_pr, mtile_ps, mtileb;
tileb = 64 * surf->bpe * surf->nsamples;
- palign = track->group_size / (8 * surf->bpe * surf->nsamples);
- palign = MAX(8, palign);
slice_pt = 1;
if (tileb > surf->tsplit) {
slice_pt = tileb / surf->tsplit;
@@ -262,7 +264,10 @@
/* macro tile width & height */
palign = (8 * surf->bankw * track->npipes) * surf->mtilea;
halign = (8 * surf->bankh * surf->nbanks) / surf->mtilea;
- surf->layer_size = surf->nbx * surf->nby * surf->bpe * slice_pt;
+ mtileb = (palign / 8) * (halign / 8) * tileb;;
+ mtile_pr = surf->nbx / palign;
+ mtile_ps = (mtile_pr * surf->nby) / halign;
+ surf->layer_size = mtile_ps * mtileb * slice_pt;
surf->base_align = (palign / 8) * (halign / 8) * tileb;
surf->palign = palign;
surf->halign = halign;
@@ -434,6 +439,39 @@
offset += surf.layer_size * mslice;
if (offset > radeon_bo_size(track->cb_color_bo[id])) {
+ /* old ddx are broken they allocate bo with w*h*bpp but
+ * program slice with ALIGN(h, 8), catch this and patch
+ * command stream.
+ */
+ if (!surf.mode) {
+ volatile u32 *ib = p->ib.ptr;
+ unsigned long tmp, nby, bsize, size, min = 0;
+
+ /* find the height the ddx wants */
+ if (surf.nby > 8) {
+ min = surf.nby - 8;
+ }
+ bsize = radeon_bo_size(track->cb_color_bo[id]);
+ tmp = track->cb_color_bo_offset[id] << 8;
+ for (nby = surf.nby; nby > min; nby--) {
+ size = nby * surf.nbx * surf.bpe * surf.nsamples;
+ if ((tmp + size * mslice) <= bsize) {
+ break;
+ }
+ }
+ if (nby > min) {
+ surf.nby = nby;
+ slice = ((nby * surf.nbx) / 64) - 1;
+ if (!evergreen_surface_check(p, &surf, "cb")) {
+ /* check if this one works */
+ tmp += surf.layer_size * mslice;
+ if (tmp <= bsize) {
+ ib[track->cb_color_slice_idx[id]] = slice;
+ goto old_ddx_ok;
+ }
+ }
+ }
+ }
dev_warn(p->dev, "%s:%d cb[%d] bo too small (layer size %d, "
"offset %d, max layer %d, bo size %ld, slice %d)\n",
__func__, __LINE__, id, surf.layer_size,
@@ -446,6 +484,7 @@
surf.tsplit, surf.mtilea);
return -EINVAL;
}
+old_ddx_ok:
return 0;
}
@@ -1532,6 +1571,7 @@
case CB_COLOR7_SLICE:
tmp = (reg - CB_COLOR0_SLICE) / 0x3c;
track->cb_color_slice[tmp] = radeon_get_ib_value(p, idx);
+ track->cb_color_slice_idx[tmp] = idx;
track->cb_dirty = true;
break;
case CB_COLOR8_SLICE:
@@ -1540,6 +1580,7 @@
case CB_COLOR11_SLICE:
tmp = ((reg - CB_COLOR8_SLICE) / 0x1c) + 8;
track->cb_color_slice[tmp] = radeon_get_ib_value(p, idx);
+ track->cb_color_slice_idx[tmp] = idx;
track->cb_dirty = true;
break;
case CB_COLOR0_ATTRIB:
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 3df4efa..3186522 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -460,15 +460,28 @@
rdev->config.cayman.max_pipes_per_simd = 4;
rdev->config.cayman.max_tile_pipes = 2;
if ((rdev->pdev->device == 0x9900) ||
- (rdev->pdev->device == 0x9901)) {
+ (rdev->pdev->device == 0x9901) ||
+ (rdev->pdev->device == 0x9905) ||
+ (rdev->pdev->device == 0x9906) ||
+ (rdev->pdev->device == 0x9907) ||
+ (rdev->pdev->device == 0x9908) ||
+ (rdev->pdev->device == 0x9909) ||
+ (rdev->pdev->device == 0x9910) ||
+ (rdev->pdev->device == 0x9917)) {
rdev->config.cayman.max_simds_per_se = 6;
rdev->config.cayman.max_backends_per_se = 2;
} else if ((rdev->pdev->device == 0x9903) ||
- (rdev->pdev->device == 0x9904)) {
+ (rdev->pdev->device == 0x9904) ||
+ (rdev->pdev->device == 0x990A) ||
+ (rdev->pdev->device == 0x9913) ||
+ (rdev->pdev->device == 0x9918)) {
rdev->config.cayman.max_simds_per_se = 4;
rdev->config.cayman.max_backends_per_se = 2;
- } else if ((rdev->pdev->device == 0x9990) ||
- (rdev->pdev->device == 0x9991)) {
+ } else if ((rdev->pdev->device == 0x9919) ||
+ (rdev->pdev->device == 0x9990) ||
+ (rdev->pdev->device == 0x9991) ||
+ (rdev->pdev->device == 0x9994) ||
+ (rdev->pdev->device == 0x99A0)) {
rdev->config.cayman.max_simds_per_se = 3;
rdev->config.cayman.max_backends_per_se = 1;
} else {
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 45cfcea..f30dc95 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2426,6 +2426,12 @@
if (r)
return r;
+ r = r600_audio_init(rdev);
+ if (r) {
+ DRM_ERROR("radeon: audio init failed\n");
+ return r;
+ }
+
return 0;
}
@@ -2462,12 +2468,6 @@
return r;
}
- r = r600_audio_init(rdev);
- if (r) {
- DRM_ERROR("radeon: audio resume failed\n");
- return r;
- }
-
return r;
}
@@ -2577,9 +2577,6 @@
rdev->accel_working = false;
}
- r = r600_audio_init(rdev);
- if (r)
- return r; /* TODO error handling */
return 0;
}
diff --git a/drivers/gpu/drm/radeon/r600_audio.c b/drivers/gpu/drm/radeon/r600_audio.c
index 7c4fa77..7479a5c 100644
--- a/drivers/gpu/drm/radeon/r600_audio.c
+++ b/drivers/gpu/drm/radeon/r600_audio.c
@@ -192,6 +192,7 @@
struct radeon_device *rdev = dev->dev_private;
struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+ struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc);
int base_rate = 48000;
switch (radeon_encoder->encoder_id) {
@@ -217,8 +218,8 @@
WREG32(EVERGREEN_AUDIO_PLL1_DIV, clock * 10);
WREG32(EVERGREEN_AUDIO_PLL1_UNK, 0x00000071);
- /* Some magic trigger or src sel? */
- WREG32_P(0x5ac, 0x01, ~0x77);
+ /* Select DTO source */
+ WREG32(0x5ac, radeon_crtc->crtc_id);
} else {
switch (dig->dig_encoder) {
case 0:
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index 226379e..969c275 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -348,7 +348,6 @@
WREG32(HDMI0_AUDIO_PACKET_CONTROL + offset,
HDMI0_AUDIO_SAMPLE_SEND | /* send audio packets */
HDMI0_AUDIO_DELAY_EN(1) | /* default audio delay */
- HDMI0_AUDIO_SEND_MAX_PACKETS | /* send NULL packets if no audio is available */
HDMI0_AUDIO_PACKETS_PER_LINE(3) | /* should be suffient for all audio modes and small enough for all hblanks */
HDMI0_60958_CS_UPDATE); /* allow 60958 channel status fields to be updated */
}
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 85dac33..fefcca5 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1374,9 +1374,9 @@
struct si_asic {
unsigned max_shader_engines;
- unsigned max_pipes_per_simd;
unsigned max_tile_pipes;
- unsigned max_simds_per_se;
+ unsigned max_cu_per_sh;
+ unsigned max_sh_per_se;
unsigned max_backends_per_se;
unsigned max_texture_channel_caches;
unsigned max_gprs;
@@ -1387,7 +1387,6 @@
unsigned sc_hiz_tile_fifo_size;
unsigned sc_earlyz_tile_fifo_size;
- unsigned num_shader_engines;
unsigned num_tile_pipes;
unsigned num_backends_per_se;
unsigned backend_disable_mask_per_asic;
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index f0bb2b5..03e5f5d 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -57,9 +57,10 @@
* 2.13.0 - virtual memory support, streamout
* 2.14.0 - add evergreen tiling informations
* 2.15.0 - add max_pipes query
+ * 2.16.0 - fix evergreen 2D tiled surface calculation
*/
#define KMS_DRIVER_MAJOR 2
-#define KMS_DRIVER_MINOR 15
+#define KMS_DRIVER_MINOR 16
#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_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 79db56e..59d4493 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -476,12 +476,18 @@
mutex_lock(&vm->mutex);
if (last_pfn > vm->last_pfn) {
- /* grow va space 32M by 32M */
- unsigned align = ((32 << 20) >> 12) - 1;
+ /* release mutex and lock in right order */
+ mutex_unlock(&vm->mutex);
radeon_mutex_lock(&rdev->cs_mutex);
- radeon_vm_unbind_locked(rdev, vm);
+ mutex_lock(&vm->mutex);
+ /* and check again */
+ if (last_pfn > vm->last_pfn) {
+ /* grow va space 32M by 32M */
+ unsigned align = ((32 << 20) >> 12) - 1;
+ radeon_vm_unbind_locked(rdev, vm);
+ vm->last_pfn = (last_pfn + align) & ~align;
+ }
radeon_mutex_unlock(&rdev->cs_mutex);
- vm->last_pfn = (last_pfn + align) & ~align;
}
head = &vm->va;
last_offset = 0;
@@ -595,8 +601,8 @@
if (bo_va == NULL)
return 0;
- mutex_lock(&vm->mutex);
radeon_mutex_lock(&rdev->cs_mutex);
+ mutex_lock(&vm->mutex);
radeon_vm_bo_update_pte(rdev, vm, bo, NULL);
radeon_mutex_unlock(&rdev->cs_mutex);
list_del(&bo_va->vm_list);
@@ -641,9 +647,8 @@
struct radeon_bo_va *bo_va, *tmp;
int r;
- mutex_lock(&vm->mutex);
-
radeon_mutex_lock(&rdev->cs_mutex);
+ mutex_lock(&vm->mutex);
radeon_vm_unbind_locked(rdev, vm);
radeon_mutex_unlock(&rdev->cs_mutex);
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index f1016a5..5c58d7d 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -273,7 +273,7 @@
break;
case RADEON_INFO_MAX_PIPES:
if (rdev->family >= CHIP_TAHITI)
- value = rdev->config.si.max_pipes_per_simd;
+ value = rdev->config.si.max_cu_per_sh;
else if (rdev->family >= CHIP_CAYMAN)
value = rdev->config.cayman.max_pipes_per_simd;
else if (rdev->family >= CHIP_CEDAR)
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 25f9eef..e95c5e6 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -908,12 +908,6 @@
return r;
}
- r = r600_audio_init(rdev);
- if (r) {
- dev_err(rdev->dev, "failed initializing audio\n");
- return r;
- }
-
r = radeon_ib_pool_start(rdev);
if (r)
return r;
@@ -922,6 +916,12 @@
if (r)
return r;
+ r = r600_audio_init(rdev);
+ if (r) {
+ dev_err(rdev->dev, "failed initializing audio\n");
+ return r;
+ }
+
return 0;
}
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 3277dde..159b6a4 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -637,12 +637,6 @@
return r;
}
- r = r600_audio_init(rdev);
- if (r) {
- dev_err(rdev->dev, "failed initializing audio\n");
- return r;
- }
-
r = radeon_ib_pool_start(rdev);
if (r)
return r;
@@ -651,6 +645,12 @@
if (r)
return r;
+ r = r600_audio_init(rdev);
+ if (r) {
+ dev_err(rdev->dev, "failed initializing audio\n");
+ return r;
+ }
+
return 0;
}
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 04ddc36..4ad0281 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -956,6 +956,12 @@
if (r)
return r;
+ r = r600_audio_init(rdev);
+ if (r) {
+ DRM_ERROR("radeon: audio init failed\n");
+ return r;
+ }
+
return 0;
}
@@ -978,12 +984,6 @@
return r;
}
- r = r600_audio_init(rdev);
- if (r) {
- dev_err(rdev->dev, "radeon: audio init failed\n");
- return r;
- }
-
return r;
}
@@ -1092,12 +1092,6 @@
rdev->accel_working = false;
}
- r = r600_audio_init(rdev);
- if (r) {
- dev_err(rdev->dev, "radeon: audio init failed\n");
- return r;
- }
-
return 0;
}
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 549732e..c7b61f1 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -867,200 +867,6 @@
/*
* Core functions
*/
-static u32 si_get_tile_pipe_to_backend_map(struct radeon_device *rdev,
- u32 num_tile_pipes,
- u32 num_backends_per_asic,
- u32 *backend_disable_mask_per_asic,
- u32 num_shader_engines)
-{
- u32 backend_map = 0;
- u32 enabled_backends_mask = 0;
- u32 enabled_backends_count = 0;
- u32 num_backends_per_se;
- u32 cur_pipe;
- u32 swizzle_pipe[SI_MAX_PIPES];
- u32 cur_backend = 0;
- u32 i;
- bool force_no_swizzle;
-
- /* force legal values */
- if (num_tile_pipes < 1)
- num_tile_pipes = 1;
- if (num_tile_pipes > rdev->config.si.max_tile_pipes)
- num_tile_pipes = rdev->config.si.max_tile_pipes;
- if (num_shader_engines < 1)
- num_shader_engines = 1;
- if (num_shader_engines > rdev->config.si.max_shader_engines)
- num_shader_engines = rdev->config.si.max_shader_engines;
- if (num_backends_per_asic < num_shader_engines)
- num_backends_per_asic = num_shader_engines;
- if (num_backends_per_asic > (rdev->config.si.max_backends_per_se * num_shader_engines))
- num_backends_per_asic = rdev->config.si.max_backends_per_se * num_shader_engines;
-
- /* make sure we have the same number of backends per se */
- num_backends_per_asic = ALIGN(num_backends_per_asic, num_shader_engines);
- /* set up the number of backends per se */
- num_backends_per_se = num_backends_per_asic / num_shader_engines;
- if (num_backends_per_se > rdev->config.si.max_backends_per_se) {
- num_backends_per_se = rdev->config.si.max_backends_per_se;
- num_backends_per_asic = num_backends_per_se * num_shader_engines;
- }
-
- /* create enable mask and count for enabled backends */
- for (i = 0; i < SI_MAX_BACKENDS; ++i) {
- if (((*backend_disable_mask_per_asic >> i) & 1) == 0) {
- enabled_backends_mask |= (1 << i);
- ++enabled_backends_count;
- }
- if (enabled_backends_count == num_backends_per_asic)
- break;
- }
-
- /* force the backends mask to match the current number of backends */
- if (enabled_backends_count != num_backends_per_asic) {
- u32 this_backend_enabled;
- u32 shader_engine;
- u32 backend_per_se;
-
- enabled_backends_mask = 0;
- enabled_backends_count = 0;
- *backend_disable_mask_per_asic = SI_MAX_BACKENDS_MASK;
- for (i = 0; i < SI_MAX_BACKENDS; ++i) {
- /* calc the current se */
- shader_engine = i / rdev->config.si.max_backends_per_se;
- /* calc the backend per se */
- backend_per_se = i % rdev->config.si.max_backends_per_se;
- /* default to not enabled */
- this_backend_enabled = 0;
- if ((shader_engine < num_shader_engines) &&
- (backend_per_se < num_backends_per_se))
- this_backend_enabled = 1;
- if (this_backend_enabled) {
- enabled_backends_mask |= (1 << i);
- *backend_disable_mask_per_asic &= ~(1 << i);
- ++enabled_backends_count;
- }
- }
- }
-
-
- memset((uint8_t *)&swizzle_pipe[0], 0, sizeof(u32) * SI_MAX_PIPES);
- switch (rdev->family) {
- case CHIP_TAHITI:
- case CHIP_PITCAIRN:
- case CHIP_VERDE:
- force_no_swizzle = true;
- break;
- default:
- force_no_swizzle = false;
- break;
- }
- if (force_no_swizzle) {
- bool last_backend_enabled = false;
-
- force_no_swizzle = false;
- for (i = 0; i < SI_MAX_BACKENDS; ++i) {
- if (((enabled_backends_mask >> i) & 1) == 1) {
- if (last_backend_enabled)
- force_no_swizzle = true;
- last_backend_enabled = true;
- } else
- last_backend_enabled = false;
- }
- }
-
- switch (num_tile_pipes) {
- case 1:
- case 3:
- case 5:
- case 7:
- DRM_ERROR("odd number of pipes!\n");
- break;
- case 2:
- swizzle_pipe[0] = 0;
- swizzle_pipe[1] = 1;
- break;
- case 4:
- if (force_no_swizzle) {
- swizzle_pipe[0] = 0;
- swizzle_pipe[1] = 1;
- swizzle_pipe[2] = 2;
- swizzle_pipe[3] = 3;
- } else {
- swizzle_pipe[0] = 0;
- swizzle_pipe[1] = 2;
- swizzle_pipe[2] = 1;
- swizzle_pipe[3] = 3;
- }
- break;
- case 6:
- if (force_no_swizzle) {
- swizzle_pipe[0] = 0;
- swizzle_pipe[1] = 1;
- swizzle_pipe[2] = 2;
- swizzle_pipe[3] = 3;
- swizzle_pipe[4] = 4;
- swizzle_pipe[5] = 5;
- } else {
- swizzle_pipe[0] = 0;
- swizzle_pipe[1] = 2;
- swizzle_pipe[2] = 4;
- swizzle_pipe[3] = 1;
- swizzle_pipe[4] = 3;
- swizzle_pipe[5] = 5;
- }
- break;
- case 8:
- if (force_no_swizzle) {
- swizzle_pipe[0] = 0;
- swizzle_pipe[1] = 1;
- swizzle_pipe[2] = 2;
- swizzle_pipe[3] = 3;
- swizzle_pipe[4] = 4;
- swizzle_pipe[5] = 5;
- swizzle_pipe[6] = 6;
- swizzle_pipe[7] = 7;
- } else {
- swizzle_pipe[0] = 0;
- swizzle_pipe[1] = 2;
- swizzle_pipe[2] = 4;
- swizzle_pipe[3] = 6;
- swizzle_pipe[4] = 1;
- swizzle_pipe[5] = 3;
- swizzle_pipe[6] = 5;
- swizzle_pipe[7] = 7;
- }
- break;
- }
-
- for (cur_pipe = 0; cur_pipe < num_tile_pipes; ++cur_pipe) {
- while (((1 << cur_backend) & enabled_backends_mask) == 0)
- cur_backend = (cur_backend + 1) % SI_MAX_BACKENDS;
-
- backend_map |= (((cur_backend & 0xf) << (swizzle_pipe[cur_pipe] * 4)));
-
- cur_backend = (cur_backend + 1) % SI_MAX_BACKENDS;
- }
-
- return backend_map;
-}
-
-static u32 si_get_disable_mask_per_asic(struct radeon_device *rdev,
- u32 disable_mask_per_se,
- u32 max_disable_mask_per_se,
- u32 num_shader_engines)
-{
- u32 disable_field_width_per_se = r600_count_pipe_bits(disable_mask_per_se);
- u32 disable_mask_per_asic = disable_mask_per_se & max_disable_mask_per_se;
-
- if (num_shader_engines == 1)
- return disable_mask_per_asic;
- else if (num_shader_engines == 2)
- return disable_mask_per_asic | (disable_mask_per_asic << disable_field_width_per_se);
- else
- return 0xffffffff;
-}
-
static void si_tiling_mode_table_init(struct radeon_device *rdev)
{
const u32 num_tile_mode_states = 32;
@@ -1562,18 +1368,151 @@
DRM_ERROR("unknown asic: 0x%x\n", rdev->family);
}
+static void si_select_se_sh(struct radeon_device *rdev,
+ u32 se_num, u32 sh_num)
+{
+ u32 data = INSTANCE_BROADCAST_WRITES;
+
+ if ((se_num == 0xffffffff) && (sh_num == 0xffffffff))
+ data = SH_BROADCAST_WRITES | SE_BROADCAST_WRITES;
+ else if (se_num == 0xffffffff)
+ data |= SE_BROADCAST_WRITES | SH_INDEX(sh_num);
+ else if (sh_num == 0xffffffff)
+ data |= SH_BROADCAST_WRITES | SE_INDEX(se_num);
+ else
+ data |= SH_INDEX(sh_num) | SE_INDEX(se_num);
+ WREG32(GRBM_GFX_INDEX, data);
+}
+
+static u32 si_create_bitmask(u32 bit_width)
+{
+ u32 i, mask = 0;
+
+ for (i = 0; i < bit_width; i++) {
+ mask <<= 1;
+ mask |= 1;
+ }
+ return mask;
+}
+
+static u32 si_get_cu_enabled(struct radeon_device *rdev, u32 cu_per_sh)
+{
+ u32 data, mask;
+
+ data = RREG32(CC_GC_SHADER_ARRAY_CONFIG);
+ if (data & 1)
+ data &= INACTIVE_CUS_MASK;
+ else
+ data = 0;
+ data |= RREG32(GC_USER_SHADER_ARRAY_CONFIG);
+
+ data >>= INACTIVE_CUS_SHIFT;
+
+ mask = si_create_bitmask(cu_per_sh);
+
+ return ~data & mask;
+}
+
+static void si_setup_spi(struct radeon_device *rdev,
+ u32 se_num, u32 sh_per_se,
+ u32 cu_per_sh)
+{
+ int i, j, k;
+ u32 data, mask, active_cu;
+
+ for (i = 0; i < se_num; i++) {
+ for (j = 0; j < sh_per_se; j++) {
+ si_select_se_sh(rdev, i, j);
+ data = RREG32(SPI_STATIC_THREAD_MGMT_3);
+ active_cu = si_get_cu_enabled(rdev, cu_per_sh);
+
+ mask = 1;
+ for (k = 0; k < 16; k++) {
+ mask <<= k;
+ if (active_cu & mask) {
+ data &= ~mask;
+ WREG32(SPI_STATIC_THREAD_MGMT_3, data);
+ break;
+ }
+ }
+ }
+ }
+ si_select_se_sh(rdev, 0xffffffff, 0xffffffff);
+}
+
+static u32 si_get_rb_disabled(struct radeon_device *rdev,
+ u32 max_rb_num, u32 se_num,
+ u32 sh_per_se)
+{
+ u32 data, mask;
+
+ data = RREG32(CC_RB_BACKEND_DISABLE);
+ if (data & 1)
+ data &= BACKEND_DISABLE_MASK;
+ else
+ data = 0;
+ data |= RREG32(GC_USER_RB_BACKEND_DISABLE);
+
+ data >>= BACKEND_DISABLE_SHIFT;
+
+ mask = si_create_bitmask(max_rb_num / se_num / sh_per_se);
+
+ return data & mask;
+}
+
+static void si_setup_rb(struct radeon_device *rdev,
+ u32 se_num, u32 sh_per_se,
+ u32 max_rb_num)
+{
+ int i, j;
+ u32 data, mask;
+ u32 disabled_rbs = 0;
+ u32 enabled_rbs = 0;
+
+ for (i = 0; i < se_num; i++) {
+ for (j = 0; j < sh_per_se; j++) {
+ si_select_se_sh(rdev, i, j);
+ data = si_get_rb_disabled(rdev, max_rb_num, se_num, sh_per_se);
+ disabled_rbs |= data << ((i * sh_per_se + j) * TAHITI_RB_BITMAP_WIDTH_PER_SH);
+ }
+ }
+ si_select_se_sh(rdev, 0xffffffff, 0xffffffff);
+
+ mask = 1;
+ for (i = 0; i < max_rb_num; i++) {
+ if (!(disabled_rbs & mask))
+ enabled_rbs |= mask;
+ mask <<= 1;
+ }
+
+ for (i = 0; i < se_num; i++) {
+ si_select_se_sh(rdev, i, 0xffffffff);
+ data = 0;
+ for (j = 0; j < sh_per_se; j++) {
+ switch (enabled_rbs & 3) {
+ case 1:
+ data |= (RASTER_CONFIG_RB_MAP_0 << (i * sh_per_se + j) * 2);
+ break;
+ case 2:
+ data |= (RASTER_CONFIG_RB_MAP_3 << (i * sh_per_se + j) * 2);
+ break;
+ case 3:
+ default:
+ data |= (RASTER_CONFIG_RB_MAP_2 << (i * sh_per_se + j) * 2);
+ break;
+ }
+ enabled_rbs >>= 2;
+ }
+ WREG32(PA_SC_RASTER_CONFIG, data);
+ }
+ si_select_se_sh(rdev, 0xffffffff, 0xffffffff);
+}
+
static void si_gpu_init(struct radeon_device *rdev)
{
- u32 cc_rb_backend_disable = 0;
- u32 cc_gc_shader_array_config;
u32 gb_addr_config = 0;
u32 mc_shared_chmap, mc_arb_ramcfg;
- u32 gb_backend_map;
- u32 cgts_tcc_disable;
u32 sx_debug_1;
- u32 gc_user_shader_array_config;
- u32 gc_user_rb_backend_disable;
- u32 cgts_user_tcc_disable;
u32 hdp_host_path_cntl;
u32 tmp;
int i, j;
@@ -1581,9 +1520,9 @@
switch (rdev->family) {
case CHIP_TAHITI:
rdev->config.si.max_shader_engines = 2;
- rdev->config.si.max_pipes_per_simd = 4;
rdev->config.si.max_tile_pipes = 12;
- rdev->config.si.max_simds_per_se = 8;
+ rdev->config.si.max_cu_per_sh = 8;
+ rdev->config.si.max_sh_per_se = 2;
rdev->config.si.max_backends_per_se = 4;
rdev->config.si.max_texture_channel_caches = 12;
rdev->config.si.max_gprs = 256;
@@ -1594,12 +1533,13 @@
rdev->config.si.sc_prim_fifo_size_backend = 0x100;
rdev->config.si.sc_hiz_tile_fifo_size = 0x30;
rdev->config.si.sc_earlyz_tile_fifo_size = 0x130;
+ gb_addr_config = TAHITI_GB_ADDR_CONFIG_GOLDEN;
break;
case CHIP_PITCAIRN:
rdev->config.si.max_shader_engines = 2;
- rdev->config.si.max_pipes_per_simd = 4;
rdev->config.si.max_tile_pipes = 8;
- rdev->config.si.max_simds_per_se = 5;
+ rdev->config.si.max_cu_per_sh = 5;
+ rdev->config.si.max_sh_per_se = 2;
rdev->config.si.max_backends_per_se = 4;
rdev->config.si.max_texture_channel_caches = 8;
rdev->config.si.max_gprs = 256;
@@ -1610,13 +1550,14 @@
rdev->config.si.sc_prim_fifo_size_backend = 0x100;
rdev->config.si.sc_hiz_tile_fifo_size = 0x30;
rdev->config.si.sc_earlyz_tile_fifo_size = 0x130;
+ gb_addr_config = TAHITI_GB_ADDR_CONFIG_GOLDEN;
break;
case CHIP_VERDE:
default:
rdev->config.si.max_shader_engines = 1;
- rdev->config.si.max_pipes_per_simd = 4;
rdev->config.si.max_tile_pipes = 4;
- rdev->config.si.max_simds_per_se = 2;
+ rdev->config.si.max_cu_per_sh = 2;
+ rdev->config.si.max_sh_per_se = 2;
rdev->config.si.max_backends_per_se = 4;
rdev->config.si.max_texture_channel_caches = 4;
rdev->config.si.max_gprs = 256;
@@ -1627,6 +1568,7 @@
rdev->config.si.sc_prim_fifo_size_backend = 0x40;
rdev->config.si.sc_hiz_tile_fifo_size = 0x30;
rdev->config.si.sc_earlyz_tile_fifo_size = 0x130;
+ gb_addr_config = VERDE_GB_ADDR_CONFIG_GOLDEN;
break;
}
@@ -1648,31 +1590,7 @@
mc_shared_chmap = RREG32(MC_SHARED_CHMAP);
mc_arb_ramcfg = RREG32(MC_ARB_RAMCFG);
- cc_rb_backend_disable = RREG32(CC_RB_BACKEND_DISABLE);
- cc_gc_shader_array_config = RREG32(CC_GC_SHADER_ARRAY_CONFIG);
- cgts_tcc_disable = 0xffff0000;
- for (i = 0; i < rdev->config.si.max_texture_channel_caches; i++)
- cgts_tcc_disable &= ~(1 << (16 + i));
- gc_user_rb_backend_disable = RREG32(GC_USER_RB_BACKEND_DISABLE);
- gc_user_shader_array_config = RREG32(GC_USER_SHADER_ARRAY_CONFIG);
- cgts_user_tcc_disable = RREG32(CGTS_USER_TCC_DISABLE);
-
- rdev->config.si.num_shader_engines = rdev->config.si.max_shader_engines;
rdev->config.si.num_tile_pipes = rdev->config.si.max_tile_pipes;
- tmp = ((~gc_user_rb_backend_disable) & BACKEND_DISABLE_MASK) >> BACKEND_DISABLE_SHIFT;
- rdev->config.si.num_backends_per_se = r600_count_pipe_bits(tmp);
- tmp = (gc_user_rb_backend_disable & BACKEND_DISABLE_MASK) >> BACKEND_DISABLE_SHIFT;
- rdev->config.si.backend_disable_mask_per_asic =
- si_get_disable_mask_per_asic(rdev, tmp, SI_MAX_BACKENDS_PER_SE_MASK,
- rdev->config.si.num_shader_engines);
- rdev->config.si.backend_map =
- si_get_tile_pipe_to_backend_map(rdev, rdev->config.si.num_tile_pipes,
- rdev->config.si.num_backends_per_se *
- rdev->config.si.num_shader_engines,
- &rdev->config.si.backend_disable_mask_per_asic,
- rdev->config.si.num_shader_engines);
- tmp = ((~cgts_user_tcc_disable) & TCC_DISABLE_MASK) >> TCC_DISABLE_SHIFT;
- rdev->config.si.num_texture_channel_caches = r600_count_pipe_bits(tmp);
rdev->config.si.mem_max_burst_length_bytes = 256;
tmp = (mc_arb_ramcfg & NOOFCOLS_MASK) >> NOOFCOLS_SHIFT;
rdev->config.si.mem_row_size_in_kb = (4 * (1 << (8 + tmp))) / 1024;
@@ -1683,55 +1601,8 @@
rdev->config.si.num_gpus = 1;
rdev->config.si.multi_gpu_tile_size = 64;
- gb_addr_config = 0;
- switch (rdev->config.si.num_tile_pipes) {
- case 1:
- gb_addr_config |= NUM_PIPES(0);
- break;
- case 2:
- gb_addr_config |= NUM_PIPES(1);
- break;
- case 4:
- gb_addr_config |= NUM_PIPES(2);
- break;
- case 8:
- default:
- gb_addr_config |= NUM_PIPES(3);
- break;
- }
-
- tmp = (rdev->config.si.mem_max_burst_length_bytes / 256) - 1;
- gb_addr_config |= PIPE_INTERLEAVE_SIZE(tmp);
- gb_addr_config |= NUM_SHADER_ENGINES(rdev->config.si.num_shader_engines - 1);
- tmp = (rdev->config.si.shader_engine_tile_size / 16) - 1;
- gb_addr_config |= SHADER_ENGINE_TILE_SIZE(tmp);
- switch (rdev->config.si.num_gpus) {
- case 1:
- default:
- gb_addr_config |= NUM_GPUS(0);
- break;
- case 2:
- gb_addr_config |= NUM_GPUS(1);
- break;
- case 4:
- gb_addr_config |= NUM_GPUS(2);
- break;
- }
- switch (rdev->config.si.multi_gpu_tile_size) {
- case 16:
- gb_addr_config |= MULTI_GPU_TILE_SIZE(0);
- break;
- case 32:
- default:
- gb_addr_config |= MULTI_GPU_TILE_SIZE(1);
- break;
- case 64:
- gb_addr_config |= MULTI_GPU_TILE_SIZE(2);
- break;
- case 128:
- gb_addr_config |= MULTI_GPU_TILE_SIZE(3);
- break;
- }
+ /* fix up row size */
+ gb_addr_config &= ~ROW_SIZE_MASK;
switch (rdev->config.si.mem_row_size_in_kb) {
case 1:
default:
@@ -1745,26 +1616,6 @@
break;
}
- tmp = (gb_addr_config & NUM_PIPES_MASK) >> NUM_PIPES_SHIFT;
- rdev->config.si.num_tile_pipes = (1 << tmp);
- tmp = (gb_addr_config & PIPE_INTERLEAVE_SIZE_MASK) >> PIPE_INTERLEAVE_SIZE_SHIFT;
- rdev->config.si.mem_max_burst_length_bytes = (tmp + 1) * 256;
- tmp = (gb_addr_config & NUM_SHADER_ENGINES_MASK) >> NUM_SHADER_ENGINES_SHIFT;
- rdev->config.si.num_shader_engines = tmp + 1;
- tmp = (gb_addr_config & NUM_GPUS_MASK) >> NUM_GPUS_SHIFT;
- rdev->config.si.num_gpus = tmp + 1;
- tmp = (gb_addr_config & MULTI_GPU_TILE_SIZE_MASK) >> MULTI_GPU_TILE_SIZE_SHIFT;
- rdev->config.si.multi_gpu_tile_size = 1 << tmp;
- tmp = (gb_addr_config & ROW_SIZE_MASK) >> ROW_SIZE_SHIFT;
- rdev->config.si.mem_row_size_in_kb = 1 << tmp;
-
- gb_backend_map =
- si_get_tile_pipe_to_backend_map(rdev, rdev->config.si.num_tile_pipes,
- rdev->config.si.num_backends_per_se *
- rdev->config.si.num_shader_engines,
- &rdev->config.si.backend_disable_mask_per_asic,
- rdev->config.si.num_shader_engines);
-
/* setup tiling info dword. gb_addr_config is not adequate since it does
* not have bank info, so create a custom tiling dword.
* bits 3:0 num_pipes
@@ -1789,34 +1640,30 @@
rdev->config.si.tile_config |= (3 << 0);
break;
}
- rdev->config.si.tile_config |=
- ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) << 4;
+ if ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT)
+ rdev->config.si.tile_config |= 1 << 4;
+ else
+ rdev->config.si.tile_config |= 0 << 4;
rdev->config.si.tile_config |=
((gb_addr_config & PIPE_INTERLEAVE_SIZE_MASK) >> PIPE_INTERLEAVE_SIZE_SHIFT) << 8;
rdev->config.si.tile_config |=
((gb_addr_config & ROW_SIZE_MASK) >> ROW_SIZE_SHIFT) << 12;
- rdev->config.si.backend_map = gb_backend_map;
WREG32(GB_ADDR_CONFIG, gb_addr_config);
WREG32(DMIF_ADDR_CONFIG, gb_addr_config);
WREG32(HDP_ADDR_CONFIG, gb_addr_config);
- /* primary versions */
- WREG32(CC_RB_BACKEND_DISABLE, cc_rb_backend_disable);
- WREG32(CC_SYS_RB_BACKEND_DISABLE, cc_rb_backend_disable);
- WREG32(CC_GC_SHADER_ARRAY_CONFIG, cc_gc_shader_array_config);
-
- WREG32(CGTS_TCC_DISABLE, cgts_tcc_disable);
-
- /* user versions */
- WREG32(GC_USER_RB_BACKEND_DISABLE, cc_rb_backend_disable);
- WREG32(GC_USER_SYS_RB_BACKEND_DISABLE, cc_rb_backend_disable);
- WREG32(GC_USER_SHADER_ARRAY_CONFIG, cc_gc_shader_array_config);
-
- WREG32(CGTS_USER_TCC_DISABLE, cgts_tcc_disable);
-
si_tiling_mode_table_init(rdev);
+ si_setup_rb(rdev, rdev->config.si.max_shader_engines,
+ rdev->config.si.max_sh_per_se,
+ rdev->config.si.max_backends_per_se);
+
+ si_setup_spi(rdev, rdev->config.si.max_shader_engines,
+ rdev->config.si.max_sh_per_se,
+ rdev->config.si.max_cu_per_sh);
+
+
/* set HW defaults for 3D engine */
WREG32(CP_QUEUE_THRESHOLDS, (ROQ_IB1_START(0x16) |
ROQ_IB2_START(0x2b)));
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 53ea2c4..db40679 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -24,6 +24,11 @@
#ifndef SI_H
#define SI_H
+#define TAHITI_RB_BITMAP_WIDTH_PER_SH 2
+
+#define TAHITI_GB_ADDR_CONFIG_GOLDEN 0x12011003
+#define VERDE_GB_ADDR_CONFIG_GOLDEN 0x12010002
+
#define CG_MULT_THERMAL_STATUS 0x714
#define ASIC_MAX_TEMP(x) ((x) << 0)
#define ASIC_MAX_TEMP_MASK 0x000001ff
@@ -408,6 +413,12 @@
#define SOFT_RESET_IA (1 << 15)
#define GRBM_GFX_INDEX 0x802C
+#define INSTANCE_INDEX(x) ((x) << 0)
+#define SH_INDEX(x) ((x) << 8)
+#define SE_INDEX(x) ((x) << 16)
+#define SH_BROADCAST_WRITES (1 << 29)
+#define INSTANCE_BROADCAST_WRITES (1 << 30)
+#define SE_BROADCAST_WRITES (1 << 31)
#define GRBM_INT_CNTL 0x8060
# define RDERR_INT_ENABLE (1 << 0)
@@ -480,6 +491,8 @@
#define VGT_TF_MEMORY_BASE 0x89B8
#define CC_GC_SHADER_ARRAY_CONFIG 0x89bc
+#define INACTIVE_CUS_MASK 0xFFFF0000
+#define INACTIVE_CUS_SHIFT 16
#define GC_USER_SHADER_ARRAY_CONFIG 0x89c0
#define PA_CL_ENHANCE 0x8A14
@@ -688,6 +701,12 @@
#define RLC_MC_CNTL 0xC344
#define RLC_UCODE_CNTL 0xC348
+#define PA_SC_RASTER_CONFIG 0x28350
+# define RASTER_CONFIG_RB_MAP_0 0
+# define RASTER_CONFIG_RB_MAP_1 1
+# define RASTER_CONFIG_RB_MAP_2 2
+# define RASTER_CONFIG_RB_MAP_3 3
+
#define VGT_EVENT_INITIATOR 0x28a90
# define SAMPLE_STREAMOUTSTATS1 (1 << 0)
# define SAMPLE_STREAMOUTSTATS2 (2 << 0)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index b67cfca..36f4b28 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1204,6 +1204,7 @@
(*destroy)(bo);
else
kfree(bo);
+ ttm_mem_global_free(mem_glob, acc_size);
return -EINVAL;
}
bo->destroy = destroy;
@@ -1307,22 +1308,14 @@
struct ttm_buffer_object **p_bo)
{
struct ttm_buffer_object *bo;
- struct ttm_mem_global *mem_glob = bdev->glob->mem_glob;
size_t acc_size;
int ret;
- acc_size = ttm_bo_acc_size(bdev, size, sizeof(struct ttm_buffer_object));
- ret = ttm_mem_global_alloc(mem_glob, acc_size, false, false);
- if (unlikely(ret != 0))
- return ret;
-
bo = kzalloc(sizeof(*bo), GFP_KERNEL);
-
- if (unlikely(bo == NULL)) {
- ttm_mem_global_free(mem_glob, acc_size);
+ if (unlikely(bo == NULL))
return -ENOMEM;
- }
+ acc_size = ttm_bo_acc_size(bdev, size, sizeof(struct ttm_buffer_object));
ret = ttm_bo_init(bdev, bo, size, type, placement, page_alignment,
buffer_start, interruptible,
persistent_swap_storage, acc_size, NULL, NULL);
diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c
index 38f9534..5b3c7d1 100644
--- a/drivers/gpu/vga/vga_switcheroo.c
+++ b/drivers/gpu/vga/vga_switcheroo.c
@@ -190,6 +190,19 @@
return NULL;
}
+int vga_switcheroo_get_client_state(struct pci_dev *pdev)
+{
+ struct vga_switcheroo_client *client;
+
+ client = find_client_from_pci(&vgasr_priv.clients, pdev);
+ if (!client)
+ return VGA_SWITCHEROO_NOT_FOUND;
+ if (!vgasr_priv.active)
+ return VGA_SWITCHEROO_INIT;
+ return client->pwr_state;
+}
+EXPORT_SYMBOL(vga_switcheroo_get_client_state);
+
void vga_switcheroo_unregister_client(struct pci_dev *pdev)
{
struct vga_switcheroo_client *client;
@@ -291,8 +304,6 @@
vga_switchon(new_client);
vga_set_default_device(new_client->pdev);
- set_audio_state(new_client->id, VGA_SWITCHEROO_ON);
-
return 0;
}
@@ -308,6 +319,8 @@
active->active = false;
+ set_audio_state(active->id, VGA_SWITCHEROO_OFF);
+
if (new_client->fb_info) {
struct fb_event event;
event.info = new_client->fb_info;
@@ -321,11 +334,11 @@
if (new_client->ops->reprobe)
new_client->ops->reprobe(new_client->pdev);
- set_audio_state(active->id, VGA_SWITCHEROO_OFF);
-
if (active->pwr_state == VGA_SWITCHEROO_ON)
vga_switchoff(active);
+ set_audio_state(new_client->id, VGA_SWITCHEROO_ON);
+
new_client->active = true;
return 0;
}
@@ -371,8 +384,9 @@
/* pwr off the device not in use */
if (strncmp(usercmd, "OFF", 3) == 0) {
list_for_each_entry(client, &vgasr_priv.clients, list) {
- if (client->active)
+ if (client->active || client_is_audio(client))
continue;
+ set_audio_state(client->id, VGA_SWITCHEROO_OFF);
if (client->pwr_state == VGA_SWITCHEROO_ON)
vga_switchoff(client);
}
@@ -381,10 +395,11 @@
/* pwr on the device not in use */
if (strncmp(usercmd, "ON", 2) == 0) {
list_for_each_entry(client, &vgasr_priv.clients, list) {
- if (client->active)
+ if (client->active || client_is_audio(client))
continue;
if (client->pwr_state == VGA_SWITCHEROO_OFF)
vga_switchon(client);
+ set_audio_state(client->id, VGA_SWITCHEROO_ON);
}
goto out;
}
diff --git a/drivers/i2c/muxes/Kconfig b/drivers/i2c/muxes/Kconfig
index beb2491..a0edd98 100644
--- a/drivers/i2c/muxes/Kconfig
+++ b/drivers/i2c/muxes/Kconfig
@@ -37,4 +37,16 @@
This driver can also be built as a module. If so, the module
will be called i2c-mux-pca954x.
+config I2C_MUX_PINCTRL
+ tristate "pinctrl-based I2C multiplexer"
+ depends on PINCTRL
+ help
+ If you say yes to this option, support will be included for an I2C
+ multiplexer that uses the pinctrl subsystem, i.e. pin multiplexing.
+ This is useful for SoCs whose I2C module's signals can be routed to
+ different sets of pins at run-time.
+
+ This driver can also be built as a module. If so, the module will be
+ called pinctrl-i2cmux.
+
endmenu
diff --git a/drivers/i2c/muxes/Makefile b/drivers/i2c/muxes/Makefile
index 5826249..76da869 100644
--- a/drivers/i2c/muxes/Makefile
+++ b/drivers/i2c/muxes/Makefile
@@ -4,5 +4,6 @@
obj-$(CONFIG_I2C_MUX_GPIO) += i2c-mux-gpio.o
obj-$(CONFIG_I2C_MUX_PCA9541) += i2c-mux-pca9541.o
obj-$(CONFIG_I2C_MUX_PCA954x) += i2c-mux-pca954x.o
+obj-$(CONFIG_I2C_MUX_PINCTRL) += i2c-mux-pinctrl.o
ccflags-$(CONFIG_I2C_DEBUG_BUS) := -DDEBUG
diff --git a/drivers/i2c/muxes/i2c-mux-pinctrl.c b/drivers/i2c/muxes/i2c-mux-pinctrl.c
new file mode 100644
index 0000000..46a6697
--- /dev/null
+++ b/drivers/i2c/muxes/i2c-mux-pinctrl.c
@@ -0,0 +1,279 @@
+/*
+ * I2C multiplexer using pinctrl API
+ *
+ * Copyright (c) 2012, NVIDIA CORPORATION. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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/>.
+ */
+
+#include <linux/i2c.h>
+#include <linux/i2c-mux.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/of_i2c.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/i2c-mux-pinctrl.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+struct i2c_mux_pinctrl {
+ struct device *dev;
+ struct i2c_mux_pinctrl_platform_data *pdata;
+ struct pinctrl *pinctrl;
+ struct pinctrl_state **states;
+ struct pinctrl_state *state_idle;
+ struct i2c_adapter *parent;
+ struct i2c_adapter **busses;
+};
+
+static int i2c_mux_pinctrl_select(struct i2c_adapter *adap, void *data,
+ u32 chan)
+{
+ struct i2c_mux_pinctrl *mux = data;
+
+ return pinctrl_select_state(mux->pinctrl, mux->states[chan]);
+}
+
+static int i2c_mux_pinctrl_deselect(struct i2c_adapter *adap, void *data,
+ u32 chan)
+{
+ struct i2c_mux_pinctrl *mux = data;
+
+ return pinctrl_select_state(mux->pinctrl, mux->state_idle);
+}
+
+#ifdef CONFIG_OF
+static int i2c_mux_pinctrl_parse_dt(struct i2c_mux_pinctrl *mux,
+ struct platform_device *pdev)
+{
+ struct device_node *np = pdev->dev.of_node;
+ int num_names, i, ret;
+ struct device_node *adapter_np;
+ struct i2c_adapter *adapter;
+
+ if (!np)
+ return 0;
+
+ mux->pdata = devm_kzalloc(&pdev->dev, sizeof(*mux->pdata), GFP_KERNEL);
+ if (!mux->pdata) {
+ dev_err(mux->dev,
+ "Cannot allocate i2c_mux_pinctrl_platform_data\n");
+ return -ENOMEM;
+ }
+
+ num_names = of_property_count_strings(np, "pinctrl-names");
+ if (num_names < 0) {
+ dev_err(mux->dev, "Cannot parse pinctrl-names: %d\n",
+ num_names);
+ return num_names;
+ }
+
+ mux->pdata->pinctrl_states = devm_kzalloc(&pdev->dev,
+ sizeof(*mux->pdata->pinctrl_states) * num_names,
+ GFP_KERNEL);
+ if (!mux->pdata->pinctrl_states) {
+ dev_err(mux->dev, "Cannot allocate pinctrl_states\n");
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < num_names; i++) {
+ ret = of_property_read_string_index(np, "pinctrl-names", i,
+ &mux->pdata->pinctrl_states[mux->pdata->bus_count]);
+ if (ret < 0) {
+ dev_err(mux->dev, "Cannot parse pinctrl-names: %d\n",
+ ret);
+ return ret;
+ }
+ if (!strcmp(mux->pdata->pinctrl_states[mux->pdata->bus_count],
+ "idle")) {
+ if (i != num_names - 1) {
+ dev_err(mux->dev, "idle state must be last\n");
+ return -EINVAL;
+ }
+ mux->pdata->pinctrl_state_idle = "idle";
+ } else {
+ mux->pdata->bus_count++;
+ }
+ }
+
+ adapter_np = of_parse_phandle(np, "i2c-parent", 0);
+ if (!adapter_np) {
+ dev_err(mux->dev, "Cannot parse i2c-parent\n");
+ return -ENODEV;
+ }
+ adapter = of_find_i2c_adapter_by_node(adapter_np);
+ if (!adapter) {
+ dev_err(mux->dev, "Cannot find parent bus\n");
+ return -ENODEV;
+ }
+ mux->pdata->parent_bus_num = i2c_adapter_id(adapter);
+ put_device(&adapter->dev);
+
+ return 0;
+}
+#else
+static inline int i2c_mux_pinctrl_parse_dt(struct i2c_mux_pinctrl *mux,
+ struct platform_device *pdev)
+{
+ return 0;
+}
+#endif
+
+static int __devinit i2c_mux_pinctrl_probe(struct platform_device *pdev)
+{
+ struct i2c_mux_pinctrl *mux;
+ int (*deselect)(struct i2c_adapter *, void *, u32);
+ int i, ret;
+
+ mux = devm_kzalloc(&pdev->dev, sizeof(*mux), GFP_KERNEL);
+ if (!mux) {
+ dev_err(&pdev->dev, "Cannot allocate i2c_mux_pinctrl\n");
+ ret = -ENOMEM;
+ goto err;
+ }
+ platform_set_drvdata(pdev, mux);
+
+ mux->dev = &pdev->dev;
+
+ mux->pdata = pdev->dev.platform_data;
+ if (!mux->pdata) {
+ ret = i2c_mux_pinctrl_parse_dt(mux, pdev);
+ if (ret < 0)
+ goto err;
+ }
+ if (!mux->pdata) {
+ dev_err(&pdev->dev, "Missing platform data\n");
+ ret = -ENODEV;
+ goto err;
+ }
+
+ mux->states = devm_kzalloc(&pdev->dev,
+ sizeof(*mux->states) * mux->pdata->bus_count,
+ GFP_KERNEL);
+ if (!mux->states) {
+ dev_err(&pdev->dev, "Cannot allocate states\n");
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ mux->busses = devm_kzalloc(&pdev->dev,
+ sizeof(mux->busses) * mux->pdata->bus_count,
+ GFP_KERNEL);
+ if (!mux->states) {
+ dev_err(&pdev->dev, "Cannot allocate busses\n");
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ mux->pinctrl = devm_pinctrl_get(&pdev->dev);
+ if (IS_ERR(mux->pinctrl)) {
+ ret = PTR_ERR(mux->pinctrl);
+ dev_err(&pdev->dev, "Cannot get pinctrl: %d\n", ret);
+ goto err;
+ }
+ for (i = 0; i < mux->pdata->bus_count; i++) {
+ mux->states[i] = pinctrl_lookup_state(mux->pinctrl,
+ mux->pdata->pinctrl_states[i]);
+ if (IS_ERR(mux->states[i])) {
+ ret = PTR_ERR(mux->states[i]);
+ dev_err(&pdev->dev,
+ "Cannot look up pinctrl state %s: %d\n",
+ mux->pdata->pinctrl_states[i], ret);
+ goto err;
+ }
+ }
+ if (mux->pdata->pinctrl_state_idle) {
+ mux->state_idle = pinctrl_lookup_state(mux->pinctrl,
+ mux->pdata->pinctrl_state_idle);
+ if (IS_ERR(mux->state_idle)) {
+ ret = PTR_ERR(mux->state_idle);
+ dev_err(&pdev->dev,
+ "Cannot look up pinctrl state %s: %d\n",
+ mux->pdata->pinctrl_state_idle, ret);
+ goto err;
+ }
+
+ deselect = i2c_mux_pinctrl_deselect;
+ } else {
+ deselect = NULL;
+ }
+
+ mux->parent = i2c_get_adapter(mux->pdata->parent_bus_num);
+ if (!mux->parent) {
+ dev_err(&pdev->dev, "Parent adapter (%d) not found\n",
+ mux->pdata->parent_bus_num);
+ ret = -ENODEV;
+ goto err;
+ }
+
+ for (i = 0; i < mux->pdata->bus_count; i++) {
+ u32 bus = mux->pdata->base_bus_num ?
+ (mux->pdata->base_bus_num + i) : 0;
+
+ mux->busses[i] = i2c_add_mux_adapter(mux->parent, &pdev->dev,
+ mux, bus, i,
+ i2c_mux_pinctrl_select,
+ deselect);
+ if (!mux->busses[i]) {
+ ret = -ENODEV;
+ dev_err(&pdev->dev, "Failed to add adapter %d\n", i);
+ goto err_del_adapter;
+ }
+ }
+
+ return 0;
+
+err_del_adapter:
+ for (; i > 0; i--)
+ i2c_del_mux_adapter(mux->busses[i - 1]);
+ i2c_put_adapter(mux->parent);
+err:
+ return ret;
+}
+
+static int __devexit i2c_mux_pinctrl_remove(struct platform_device *pdev)
+{
+ struct i2c_mux_pinctrl *mux = platform_get_drvdata(pdev);
+ int i;
+
+ for (i = 0; i < mux->pdata->bus_count; i++)
+ i2c_del_mux_adapter(mux->busses[i]);
+
+ i2c_put_adapter(mux->parent);
+
+ return 0;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id i2c_mux_pinctrl_of_match[] __devinitconst = {
+ { .compatible = "i2c-mux-pinctrl", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, i2c_mux_pinctrl_of_match);
+#endif
+
+static struct platform_driver i2c_mux_pinctrl_driver = {
+ .driver = {
+ .name = "i2c-mux-pinctrl",
+ .owner = THIS_MODULE,
+ .of_match_table = of_match_ptr(i2c_mux_pinctrl_of_match),
+ },
+ .probe = i2c_mux_pinctrl_probe,
+ .remove = __devexit_p(i2c_mux_pinctrl_remove),
+};
+module_platform_driver(i2c_mux_pinctrl_driver);
+
+MODULE_DESCRIPTION("pinctrl-based I2C multiplexer driver");
+MODULE_AUTHOR("Stephen Warren <swarren@nvidia.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:i2c-mux-pinctrl");
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 55ab284e..b18870c 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -1593,6 +1593,10 @@
struct net_device *pdev;
pdev = ip_dev_find(&init_net, peer_ip);
+ if (!pdev) {
+ err = -ENODEV;
+ goto out;
+ }
ep->l2t = cxgb4_l2t_get(cdev->rdev.lldi.l2t,
n, pdev, 0);
if (!ep->l2t)
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index ee1c577..3530c41 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -140,7 +140,7 @@
props->max_mr_size = ~0ull;
props->page_size_cap = dev->dev->caps.page_size_cap;
props->max_qp = dev->dev->caps.num_qps - dev->dev->caps.reserved_qps;
- props->max_qp_wr = dev->dev->caps.max_wqes;
+ props->max_qp_wr = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE;
props->max_sge = min(dev->dev->caps.max_sq_sg,
dev->dev->caps.max_rq_sg);
props->max_cq = dev->dev->caps.num_cqs - dev->dev->caps.reserved_cqs;
@@ -1084,12 +1084,9 @@
int total_eqs = 0;
int i, j, eq;
- /* Init eq table */
- ibdev->eq_table = NULL;
- ibdev->eq_added = 0;
-
- /* Legacy mode? */
- if (dev->caps.comp_pool == 0)
+ /* Legacy mode or comp_pool is not large enough */
+ if (dev->caps.comp_pool == 0 ||
+ dev->caps.num_ports > dev->caps.comp_pool)
return;
eq_per_port = rounddown_pow_of_two(dev->caps.comp_pool/
@@ -1135,7 +1132,10 @@
static void mlx4_ib_free_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
{
int i;
- int total_eqs;
+
+ /* no additional eqs were added */
+ if (!ibdev->eq_table)
+ return;
/* Reset the advertised EQ number */
ibdev->ib_dev.num_comp_vectors = dev->caps.num_comp_vectors;
@@ -1148,12 +1148,7 @@
mlx4_release_eq(dev, ibdev->eq_table[i]);
}
- total_eqs = dev->caps.num_comp_vectors + ibdev->eq_added;
- memset(ibdev->eq_table, 0, total_eqs * sizeof(int));
kfree(ibdev->eq_table);
-
- ibdev->eq_table = NULL;
- ibdev->eq_added = 0;
}
static void *mlx4_ib_add(struct mlx4_dev *dev)
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index e62297c..ff36655 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -44,6 +44,14 @@
#include <linux/mlx4/device.h>
#include <linux/mlx4/doorbell.h>
+enum {
+ MLX4_IB_SQ_MIN_WQE_SHIFT = 6,
+ MLX4_IB_MAX_HEADROOM = 2048
+};
+
+#define MLX4_IB_SQ_HEADROOM(shift) ((MLX4_IB_MAX_HEADROOM >> (shift)) + 1)
+#define MLX4_IB_SQ_MAX_SPARE (MLX4_IB_SQ_HEADROOM(MLX4_IB_SQ_MIN_WQE_SHIFT))
+
struct mlx4_ib_ucontext {
struct ib_ucontext ibucontext;
struct mlx4_uar uar;
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index ceb3332..8d4ed24 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -310,8 +310,8 @@
int is_user, int has_rq, struct mlx4_ib_qp *qp)
{
/* Sanity check RQ size before proceeding */
- if (cap->max_recv_wr > dev->dev->caps.max_wqes ||
- cap->max_recv_sge > dev->dev->caps.max_rq_sg)
+ if (cap->max_recv_wr > dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE ||
+ cap->max_recv_sge > min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg))
return -EINVAL;
if (!has_rq) {
@@ -329,8 +329,17 @@
qp->rq.wqe_shift = ilog2(qp->rq.max_gs * sizeof (struct mlx4_wqe_data_seg));
}
- cap->max_recv_wr = qp->rq.max_post = qp->rq.wqe_cnt;
- cap->max_recv_sge = qp->rq.max_gs;
+ /* leave userspace return values as they were, so as not to break ABI */
+ if (is_user) {
+ cap->max_recv_wr = qp->rq.max_post = qp->rq.wqe_cnt;
+ cap->max_recv_sge = qp->rq.max_gs;
+ } else {
+ cap->max_recv_wr = qp->rq.max_post =
+ min(dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE, qp->rq.wqe_cnt);
+ cap->max_recv_sge = min(qp->rq.max_gs,
+ min(dev->dev->caps.max_sq_sg,
+ dev->dev->caps.max_rq_sg));
+ }
return 0;
}
@@ -341,8 +350,8 @@
int s;
/* Sanity check SQ size before proceeding */
- if (cap->max_send_wr > dev->dev->caps.max_wqes ||
- cap->max_send_sge > dev->dev->caps.max_sq_sg ||
+ if (cap->max_send_wr > (dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE) ||
+ cap->max_send_sge > min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg) ||
cap->max_inline_data + send_wqe_overhead(type, qp->flags) +
sizeof (struct mlx4_wqe_inline_seg) > dev->dev->caps.max_sq_desc_sz)
return -EINVAL;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h
index 85a69c9..037f5ce 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma.h
@@ -231,7 +231,6 @@
u32 entry_size;
u32 max_cnt;
u32 max_wqe_idx;
- u32 free_delta;
u16 dbid; /* qid, where to ring the doorbell. */
u32 len;
dma_addr_t pa;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_abi.h b/drivers/infiniband/hw/ocrdma/ocrdma_abi.h
index a411a4e..517ab20 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_abi.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_abi.h
@@ -101,8 +101,6 @@
u32 rsvd1;
u32 num_wqe_allocated;
u32 num_rqe_allocated;
- u32 free_wqe_delta;
- u32 free_rqe_delta;
u32 db_sq_offset;
u32 db_rq_offset;
u32 db_shift;
@@ -126,8 +124,7 @@
u32 db_rq_offset;
u32 db_shift;
- u32 free_rqe_delta;
- u32 rsvd2;
+ u64 rsvd2;
u64 rsvd3;
} __packed;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
index 9b204b1..9343a15 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
@@ -732,7 +732,7 @@
break;
case OCRDMA_SRQ_LIMIT_EVENT:
ib_evt.element.srq = &qp->srq->ibsrq;
- ib_evt.event = IB_EVENT_QP_LAST_WQE_REACHED;
+ ib_evt.event = IB_EVENT_SRQ_LIMIT_REACHED;
srq_event = 1;
qp_event = 0;
break;
@@ -1990,19 +1990,12 @@
max_wqe_allocated = 1 << max_wqe_allocated;
max_rqe_allocated = 1 << ((u16)rsp->max_wqe_rqe);
- if (qp->dev->nic_info.dev_family == OCRDMA_GEN2_FAMILY) {
- qp->sq.free_delta = 0;
- qp->rq.free_delta = 1;
- } else
- qp->sq.free_delta = 1;
-
qp->sq.max_cnt = max_wqe_allocated;
qp->sq.max_wqe_idx = max_wqe_allocated - 1;
if (!attrs->srq) {
qp->rq.max_cnt = max_rqe_allocated;
qp->rq.max_wqe_idx = max_rqe_allocated - 1;
- qp->rq.free_delta = 1;
}
}
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index a20d16e..04fef3d 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -26,7 +26,6 @@
*******************************************************************/
#include <linux/module.h>
-#include <linux/version.h>
#include <linux/idr.h>
#include <rdma/ib_verbs.h>
#include <rdma/ib_user_verbs.h>
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index e9f74d1..d16d172 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -940,8 +940,6 @@
uresp.db_rq_offset = OCRDMA_DB_RQ_OFFSET;
uresp.db_shift = 16;
}
- uresp.free_wqe_delta = qp->sq.free_delta;
- uresp.free_rqe_delta = qp->rq.free_delta;
if (qp->dpp_enabled) {
uresp.dpp_credit = dpp_credit_lmt;
@@ -1307,8 +1305,6 @@
free_cnt = (q->max_cnt - q->head) + q->tail;
else
free_cnt = q->tail - q->head;
- if (q->free_delta)
- free_cnt -= q->free_delta;
return free_cnt;
}
@@ -1501,7 +1497,6 @@
(srq->pd->id * srq->dev->nic_info.db_page_size);
uresp.db_page_size = srq->dev->nic_info.db_page_size;
uresp.num_rqe_allocated = srq->rq.max_cnt;
- uresp.free_rqe_delta = 1;
if (srq->dev->nic_info.dev_family == OCRDMA_GEN2_FAMILY) {
uresp.db_rq_offset = OCRDMA_DB_GEN2_RQ1_OFFSET;
uresp.db_shift = 24;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
index e648343..633f03d 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
@@ -28,7 +28,6 @@
#ifndef __OCRDMA_VERBS_H__
#define __OCRDMA_VERBS_H__
-#include <linux/version.h>
int ocrdma_post_send(struct ib_qp *, struct ib_send_wr *,
struct ib_send_wr **bad_wr);
int ocrdma_post_recv(struct ib_qp *, struct ib_recv_wr *,
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index d90a421..a2e418c 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -547,26 +547,12 @@
spin_unlock_irqrestore(&iommu->lock, flags);
}
-static void iommu_handle_ppr_entry(struct amd_iommu *iommu, u32 head)
+static void iommu_handle_ppr_entry(struct amd_iommu *iommu, u64 *raw)
{
struct amd_iommu_fault fault;
- volatile u64 *raw;
- int i;
INC_STATS_COUNTER(pri_requests);
- raw = (u64 *)(iommu->ppr_log + head);
-
- /*
- * Hardware bug: Interrupt may arrive before the entry is written to
- * memory. If this happens we need to wait for the entry to arrive.
- */
- for (i = 0; i < LOOP_TIMEOUT; ++i) {
- if (PPR_REQ_TYPE(raw[0]) != 0)
- break;
- udelay(1);
- }
-
if (PPR_REQ_TYPE(raw[0]) != PPR_REQ_FAULT) {
pr_err_ratelimited("AMD-Vi: Unknown PPR request received\n");
return;
@@ -578,12 +564,6 @@
fault.tag = PPR_TAG(raw[0]);
fault.flags = PPR_FLAGS(raw[0]);
- /*
- * To detect the hardware bug we need to clear the entry
- * to back to zero.
- */
- raw[0] = raw[1] = 0;
-
atomic_notifier_call_chain(&ppr_notifier, 0, &fault);
}
@@ -595,25 +575,62 @@
if (iommu->ppr_log == NULL)
return;
+ /* enable ppr interrupts again */
+ writel(MMIO_STATUS_PPR_INT_MASK, iommu->mmio_base + MMIO_STATUS_OFFSET);
+
spin_lock_irqsave(&iommu->lock, flags);
head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
while (head != tail) {
+ volatile u64 *raw;
+ u64 entry[2];
+ int i;
- /* Handle PPR entry */
- iommu_handle_ppr_entry(iommu, head);
+ raw = (u64 *)(iommu->ppr_log + head);
- /* Update and refresh ring-buffer state*/
+ /*
+ * Hardware bug: Interrupt may arrive before the entry is
+ * written to memory. If this happens we need to wait for the
+ * entry to arrive.
+ */
+ for (i = 0; i < LOOP_TIMEOUT; ++i) {
+ if (PPR_REQ_TYPE(raw[0]) != 0)
+ break;
+ udelay(1);
+ }
+
+ /* Avoid memcpy function-call overhead */
+ entry[0] = raw[0];
+ entry[1] = raw[1];
+
+ /*
+ * To detect the hardware bug we need to clear the entry
+ * back to zero.
+ */
+ raw[0] = raw[1] = 0UL;
+
+ /* Update head pointer of hardware ring-buffer */
head = (head + PPR_ENTRY_SIZE) % PPR_LOG_SIZE;
writel(head, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
+
+ /*
+ * Release iommu->lock because ppr-handling might need to
+ * re-aquire it
+ */
+ spin_unlock_irqrestore(&iommu->lock, flags);
+
+ /* Handle PPR entry */
+ iommu_handle_ppr_entry(iommu, entry);
+
+ spin_lock_irqsave(&iommu->lock, flags);
+
+ /* Refresh ring-buffer information */
+ head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
}
- /* enable ppr interrupts again */
- writel(MMIO_STATUS_PPR_INT_MASK, iommu->mmio_base + MMIO_STATUS_OFFSET);
-
spin_unlock_irqrestore(&iommu->lock, flags);
}
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index c567903..542024b 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1029,6 +1029,9 @@
if (!iommu->dev)
return 1;
+ iommu->root_pdev = pci_get_bus_and_slot(iommu->dev->bus->number,
+ PCI_DEVFN(0, 0));
+
iommu->cap_ptr = h->cap_ptr;
iommu->pci_seg = h->pci_seg;
iommu->mmio_phys = h->mmio_phys;
@@ -1323,20 +1326,16 @@
{
int i, j;
u32 ioc_feature_control;
- struct pci_dev *pdev = NULL;
+ struct pci_dev *pdev = iommu->root_pdev;
/* RD890 BIOSes may not have completely reconfigured the iommu */
- if (!is_rd890_iommu(iommu->dev))
+ if (!is_rd890_iommu(iommu->dev) || !pdev)
return;
/*
* First, we need to ensure that the iommu is enabled. This is
* controlled by a register in the northbridge
*/
- pdev = pci_get_bus_and_slot(iommu->dev->bus->number, PCI_DEVFN(0, 0));
-
- if (!pdev)
- return;
/* Select Northbridge indirect register 0x75 and enable writing */
pci_write_config_dword(pdev, 0x60, 0x75 | (1 << 7));
@@ -1346,8 +1345,6 @@
if (!(ioc_feature_control & 0x1))
pci_write_config_dword(pdev, 0x64, ioc_feature_control | 1);
- pci_dev_put(pdev);
-
/* Restore the iommu BAR */
pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4,
iommu->stored_addr_lo);
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 2452f3b..2435555 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -481,6 +481,9 @@
/* Pointer to PCI device of this IOMMU */
struct pci_dev *dev;
+ /* Cache pdev to root device for resume quirks */
+ struct pci_dev *root_pdev;
+
/* physical address of MMIO space */
u64 mmio_phys;
/* virtual address of MMIO space */
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 04cb8c8..12b2b55 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -379,7 +379,7 @@
config LEDS_ASIC3
bool "LED support for the HTC ASIC3"
- depends on LEDS_CLASS
+ depends on LEDS_CLASS=y
depends on MFD_ASIC3
default y
help
@@ -390,7 +390,7 @@
config LEDS_RENESAS_TPU
bool "LED support for Renesas TPU"
- depends on LEDS_CLASS && HAVE_CLK && GENERIC_GPIO
+ depends on LEDS_CLASS=y && HAVE_CLK && GENERIC_GPIO
help
This option enables build of the LED TPU platform driver,
suitable to drive any TPU channel on newer Renesas SoCs.
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index 8ee92c8..e663e6f 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -29,7 +29,7 @@
led_cdev->brightness = led_cdev->brightness_get(led_cdev);
}
-static ssize_t led_brightness_show(struct device *dev,
+static ssize_t led_brightness_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct led_classdev *led_cdev = dev_get_drvdata(dev);
diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c
index d686004..d65353d 100644
--- a/drivers/leds/led-core.c
+++ b/drivers/leds/led-core.c
@@ -44,13 +44,6 @@
if (!led_cdev->blink_brightness)
led_cdev->blink_brightness = led_cdev->max_brightness;
- if (led_get_trigger_data(led_cdev) &&
- delay_on == led_cdev->blink_delay_on &&
- delay_off == led_cdev->blink_delay_off)
- return;
-
- led_stop_software_blink(led_cdev);
-
led_cdev->blink_delay_on = delay_on;
led_cdev->blink_delay_off = delay_off;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 835de71..a9c7981 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -2550,6 +2550,7 @@
err = -EINVAL;
spin_lock_init(&conf->device_lock);
rdev_for_each(rdev, mddev) {
+ struct request_queue *q;
int disk_idx = rdev->raid_disk;
if (disk_idx >= mddev->raid_disks
|| disk_idx < 0)
@@ -2562,6 +2563,9 @@
if (disk->rdev)
goto abort;
disk->rdev = rdev;
+ q = bdev_get_queue(rdev->bdev);
+ if (q->merge_bvec_fn)
+ mddev->merge_check_needed = 1;
disk->head_position = 0;
}
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 987db37..99ae606 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3475,6 +3475,7 @@
rdev_for_each(rdev, mddev) {
long long diff;
+ struct request_queue *q;
disk_idx = rdev->raid_disk;
if (disk_idx < 0)
@@ -3493,6 +3494,9 @@
goto out_free_conf;
disk->rdev = rdev;
}
+ q = bdev_get_queue(rdev->bdev);
+ if (q->merge_bvec_fn)
+ mddev->merge_check_needed = 1;
diff = (rdev->new_data_offset - rdev->data_offset);
if (!mddev->reshape_backwards)
diff = -diff;
diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c
index 9f957c2..09d4f8d 100644
--- a/drivers/mtd/ubi/debug.c
+++ b/drivers/mtd/ubi/debug.c
@@ -264,6 +264,9 @@
*/
int ubi_debugfs_init(void)
{
+ if (!IS_ENABLED(DEBUG_FS))
+ return 0;
+
dfs_rootdir = debugfs_create_dir("ubi", NULL);
if (IS_ERR_OR_NULL(dfs_rootdir)) {
int err = dfs_rootdir ? -ENODEV : PTR_ERR(dfs_rootdir);
@@ -281,7 +284,8 @@
*/
void ubi_debugfs_exit(void)
{
- debugfs_remove(dfs_rootdir);
+ if (IS_ENABLED(DEBUG_FS))
+ debugfs_remove(dfs_rootdir);
}
/* Read an UBI debugfs file */
@@ -403,6 +407,9 @@
struct dentry *dent;
struct ubi_debug_info *d = ubi->dbg;
+ if (!IS_ENABLED(DEBUG_FS))
+ return 0;
+
n = snprintf(d->dfs_dir_name, UBI_DFS_DIR_LEN + 1, UBI_DFS_DIR_NAME,
ubi->ubi_num);
if (n == UBI_DFS_DIR_LEN) {
@@ -470,5 +477,6 @@
*/
void ubi_debugfs_exit_dev(struct ubi_device *ubi)
{
- debugfs_remove_recursive(ubi->dbg->dfs_dir);
+ if (IS_ENABLED(DEBUG_FS))
+ debugfs_remove_recursive(ubi->dbg->dfs_dir);
}
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 9df100a..b6be644 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -1262,11 +1262,11 @@
dbg_wl("flush pending work for LEB %d:%d (%d pending works)",
vol_id, lnum, ubi->works_count);
- down_write(&ubi->work_sem);
while (found) {
struct ubi_work *wrk;
found = 0;
+ down_read(&ubi->work_sem);
spin_lock(&ubi->wl_lock);
list_for_each_entry(wrk, &ubi->works, list) {
if ((vol_id == UBI_ALL || wrk->vol_id == vol_id) &&
@@ -1277,18 +1277,27 @@
spin_unlock(&ubi->wl_lock);
err = wrk->func(ubi, wrk, 0);
- if (err)
- goto out;
+ if (err) {
+ up_read(&ubi->work_sem);
+ return err;
+ }
+
spin_lock(&ubi->wl_lock);
found = 1;
break;
}
}
spin_unlock(&ubi->wl_lock);
+ up_read(&ubi->work_sem);
}
-out:
+ /*
+ * Make sure all the works which have been done in parallel are
+ * finished.
+ */
+ down_write(&ubi->work_sem);
up_write(&ubi->work_sem);
+
return err;
}
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 3463b46..a030e63 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -2454,24 +2454,27 @@
out:
if (res) {
/* no suitable interface, frame not sent */
- dev_kfree_skb(skb);
+ kfree_skb(skb);
}
return NETDEV_TX_OK;
}
-int bond_3ad_lacpdu_recv(struct sk_buff *skb, struct bonding *bond,
- struct slave *slave)
+int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond,
+ struct slave *slave)
{
int ret = RX_HANDLER_ANOTHER;
+ struct lacpdu *lacpdu, _lacpdu;
+
if (skb->protocol != PKT_TYPE_LACPDU)
return ret;
- if (!pskb_may_pull(skb, sizeof(struct lacpdu)))
+ lacpdu = skb_header_pointer(skb, 0, sizeof(_lacpdu), &_lacpdu);
+ if (!lacpdu)
return ret;
read_lock(&bond->lock);
- ret = bond_3ad_rx_indication((struct lacpdu *) skb->data, slave, skb->len);
+ ret = bond_3ad_rx_indication(lacpdu, slave, skb->len);
read_unlock(&bond->lock);
return ret;
}
diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h
index 5ee7e3c..0cfaa4a 100644
--- a/drivers/net/bonding/bond_3ad.h
+++ b/drivers/net/bonding/bond_3ad.h
@@ -274,8 +274,8 @@
void bond_3ad_handle_link_change(struct slave *slave, char link);
int bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info);
int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev);
-int bond_3ad_lacpdu_recv(struct sk_buff *skb, struct bonding *bond,
- struct slave *slave);
+int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond,
+ struct slave *slave);
int bond_3ad_set_carrier(struct bonding *bond);
void bond_3ad_update_lacp_rate(struct bonding *bond);
#endif //__BOND_3AD_H__
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 0f59c15..e15cc11 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -342,27 +342,17 @@
_unlock_rx_hashtbl_bh(bond);
}
-static int rlb_arp_recv(struct sk_buff *skb, struct bonding *bond,
- struct slave *slave)
+static int rlb_arp_recv(const struct sk_buff *skb, struct bonding *bond,
+ struct slave *slave)
{
- struct arp_pkt *arp;
+ struct arp_pkt *arp, _arp;
if (skb->protocol != cpu_to_be16(ETH_P_ARP))
goto out;
- arp = (struct arp_pkt *) skb->data;
- if (!arp) {
- pr_debug("Packet has no ARP data\n");
+ arp = skb_header_pointer(skb, 0, sizeof(_arp), &_arp);
+ if (!arp)
goto out;
- }
-
- if (!pskb_may_pull(skb, arp_hdr_len(bond->dev)))
- goto out;
-
- if (skb->len < sizeof(struct arp_pkt)) {
- pr_debug("Packet is too small to be an ARP\n");
- goto out;
- }
if (arp->op_code == htons(ARPOP_REPLY)) {
/* update rx hash table for this ARP */
@@ -1356,12 +1346,12 @@
}
}
- if (res) {
- /* no suitable interface, frame not sent */
- dev_kfree_skb(skb);
- }
read_unlock(&bond->curr_slave_lock);
+ if (res) {
+ /* no suitable interface, frame not sent */
+ kfree_skb(skb);
+ }
return NETDEV_TX_OK;
}
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 2ee8cf9..f5a40b9 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -76,6 +76,7 @@
#include <net/route.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
+#include <net/pkt_sched.h>
#include "bonding.h"
#include "bond_3ad.h"
#include "bond_alb.h"
@@ -381,8 +382,6 @@
return next;
}
-#define bond_queue_mapping(skb) (*(u16 *)((skb)->cb))
-
/**
* bond_dev_queue_xmit - Prepare skb for xmit.
*
@@ -395,7 +394,9 @@
{
skb->dev = slave_dev;
- skb->queue_mapping = bond_queue_mapping(skb);
+ BUILD_BUG_ON(sizeof(skb->queue_mapping) !=
+ sizeof(qdisc_skb_cb(skb)->bond_queue_mapping));
+ skb->queue_mapping = qdisc_skb_cb(skb)->bond_queue_mapping;
if (unlikely(netpoll_tx_running(slave_dev)))
bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb);
@@ -1444,8 +1445,8 @@
struct sk_buff *skb = *pskb;
struct slave *slave;
struct bonding *bond;
- int (*recv_probe)(struct sk_buff *, struct bonding *,
- struct slave *);
+ int (*recv_probe)(const struct sk_buff *, struct bonding *,
+ struct slave *);
int ret = RX_HANDLER_ANOTHER;
skb = skb_share_check(skb, GFP_ATOMIC);
@@ -1462,15 +1463,10 @@
recv_probe = ACCESS_ONCE(bond->recv_probe);
if (recv_probe) {
- struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
-
- if (likely(nskb)) {
- ret = recv_probe(nskb, bond, slave);
- dev_kfree_skb(nskb);
- if (ret == RX_HANDLER_CONSUMED) {
- consume_skb(skb);
- return ret;
- }
+ ret = recv_probe(skb, bond, slave);
+ if (ret == RX_HANDLER_CONSUMED) {
+ consume_skb(skb);
+ return ret;
}
}
@@ -2737,25 +2733,31 @@
}
}
-static int bond_arp_rcv(struct sk_buff *skb, struct bonding *bond,
- struct slave *slave)
+static int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
+ struct slave *slave)
{
- struct arphdr *arp;
+ struct arphdr *arp = (struct arphdr *)skb->data;
unsigned char *arp_ptr;
__be32 sip, tip;
+ int alen;
if (skb->protocol != __cpu_to_be16(ETH_P_ARP))
return RX_HANDLER_ANOTHER;
read_lock(&bond->lock);
+ alen = arp_hdr_len(bond->dev);
pr_debug("bond_arp_rcv: bond %s skb->dev %s\n",
bond->dev->name, skb->dev->name);
- if (!pskb_may_pull(skb, arp_hdr_len(bond->dev)))
- goto out_unlock;
+ if (alen > skb_headlen(skb)) {
+ arp = kmalloc(alen, GFP_ATOMIC);
+ if (!arp)
+ goto out_unlock;
+ if (skb_copy_bits(skb, 0, arp, alen) < 0)
+ goto out_unlock;
+ }
- arp = arp_hdr(skb);
if (arp->ar_hln != bond->dev->addr_len ||
skb->pkt_type == PACKET_OTHERHOST ||
skb->pkt_type == PACKET_LOOPBACK ||
@@ -2790,6 +2792,8 @@
out_unlock:
read_unlock(&bond->lock);
+ if (arp != (struct arphdr *)skb->data)
+ kfree(arp);
return RX_HANDLER_ANOTHER;
}
@@ -3986,7 +3990,7 @@
out:
if (res) {
/* no suitable interface, frame not sent */
- dev_kfree_skb(skb);
+ kfree_skb(skb);
}
return NETDEV_TX_OK;
@@ -4008,11 +4012,11 @@
res = bond_dev_queue_xmit(bond, skb,
bond->curr_active_slave->dev);
+ read_unlock(&bond->curr_slave_lock);
+
if (res)
/* no suitable interface, frame not sent */
- dev_kfree_skb(skb);
-
- read_unlock(&bond->curr_slave_lock);
+ kfree_skb(skb);
return NETDEV_TX_OK;
}
@@ -4051,7 +4055,7 @@
if (res) {
/* no suitable interface, frame not sent */
- dev_kfree_skb(skb);
+ kfree_skb(skb);
}
return NETDEV_TX_OK;
@@ -4089,7 +4093,7 @@
res = bond_dev_queue_xmit(bond, skb2, tx_dev);
if (res) {
- dev_kfree_skb(skb2);
+ kfree_skb(skb2);
continue;
}
}
@@ -4103,7 +4107,7 @@
out:
if (res)
/* no suitable interface, frame not sent */
- dev_kfree_skb(skb);
+ kfree_skb(skb);
/* frame sent to all suitable interfaces */
return NETDEV_TX_OK;
@@ -4171,7 +4175,7 @@
/*
* Save the original txq to restore before passing to the driver
*/
- bond_queue_mapping(skb) = skb->queue_mapping;
+ qdisc_skb_cb(skb)->bond_queue_mapping = skb->queue_mapping;
if (unlikely(txq >= dev->real_num_tx_queues)) {
do {
@@ -4209,7 +4213,7 @@
pr_err("%s: Error: Unknown bonding mode %d\n",
dev->name, bond->params.mode);
WARN_ON_ONCE(1);
- dev_kfree_skb(skb);
+ kfree_skb(skb);
return NETDEV_TX_OK;
}
}
@@ -4231,7 +4235,7 @@
if (bond->slave_cnt)
ret = __bond_start_xmit(skb, dev);
else
- dev_kfree_skb(skb);
+ kfree_skb(skb);
read_unlock(&bond->lock);
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index aef42f0..485bedb 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -1082,8 +1082,12 @@
}
}
- pr_info("%s: Unable to set %.*s as primary slave.\n",
- bond->dev->name, (int)strlen(buf) - 1, buf);
+ strncpy(bond->params.primary, ifname, IFNAMSIZ);
+ bond->params.primary[IFNAMSIZ - 1] = 0;
+
+ pr_info("%s: Recording %s as primary, "
+ "but it has not been enslaved to %s yet.\n",
+ bond->dev->name, ifname, bond->dev->name);
out:
write_unlock_bh(&bond->curr_slave_lock);
read_unlock(&bond->lock);
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 4581aa5..f8af2fc 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -218,8 +218,8 @@
struct slave *primary_slave;
bool force_primary;
s32 slave_cnt; /* never change this value outside the attach/detach wrappers */
- int (*recv_probe)(struct sk_buff *, struct bonding *,
- struct slave *);
+ int (*recv_probe)(const struct sk_buff *, struct bonding *,
+ struct slave *);
rwlock_t lock;
rwlock_t curr_slave_lock;
u8 send_peer_notif;
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index e2ce508..eea6608 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -594,8 +594,8 @@
priv->write_reg(priv, C_CAN_CTRL_REG,
CONTROL_ENABLE_AR);
- if (priv->can.ctrlmode & (CAN_CTRLMODE_LISTENONLY &
- CAN_CTRLMODE_LOOPBACK)) {
+ if ((priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) &&
+ (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)) {
/* loopback + silent mode : useful for hot self-test */
priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_EIE |
CONTROL_SIE | CONTROL_IE | CONTROL_TEST);
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index 442d91a..bab0158 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -187,8 +187,10 @@
rtnl_lock();
err = __rtnl_link_register(&dummy_link_ops);
- for (i = 0; i < numdummies && !err; i++)
+ for (i = 0; i < numdummies && !err; i++) {
err = dummy_init_one();
+ cond_resched();
+ }
if (err < 0)
__rtnl_link_unregister(&dummy_link_ops);
rtnl_unlock();
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index e30e2a2..7de8241 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -747,21 +747,6 @@
#define ETH_RX_ERROR_FALGS ETH_FAST_PATH_RX_CQE_PHY_DECODE_ERR_FLG
-#define BNX2X_IP_CSUM_ERR(cqe) \
- (!((cqe)->fast_path_cqe.status_flags & \
- ETH_FAST_PATH_RX_CQE_IP_XSUM_NO_VALIDATION_FLG) && \
- ((cqe)->fast_path_cqe.type_error_flags & \
- ETH_FAST_PATH_RX_CQE_IP_BAD_XSUM_FLG))
-
-#define BNX2X_L4_CSUM_ERR(cqe) \
- (!((cqe)->fast_path_cqe.status_flags & \
- ETH_FAST_PATH_RX_CQE_L4_XSUM_NO_VALIDATION_FLG) && \
- ((cqe)->fast_path_cqe.type_error_flags & \
- ETH_FAST_PATH_RX_CQE_L4_BAD_XSUM_FLG))
-
-#define BNX2X_RX_CSUM_OK(cqe) \
- (!(BNX2X_L4_CSUM_ERR(cqe) || BNX2X_IP_CSUM_ERR(cqe)))
-
#define BNX2X_PRS_FLAG_OVERETH_IPV4(flags) \
(((le16_to_cpu(flags) & \
PARSING_FLAGS_OVER_ETHERNET_PROTOCOL) >> \
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index ad0743b..8098eea 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -190,7 +190,7 @@
if ((netif_tx_queue_stopped(txq)) &&
(bp->state == BNX2X_STATE_OPEN) &&
- (bnx2x_tx_avail(bp, txdata) >= MAX_SKB_FRAGS + 3))
+ (bnx2x_tx_avail(bp, txdata) >= MAX_SKB_FRAGS + 4))
netif_tx_wake_queue(txq);
__netif_tx_unlock(txq);
@@ -617,6 +617,25 @@
return 0;
}
+static void bnx2x_csum_validate(struct sk_buff *skb, union eth_rx_cqe *cqe,
+ struct bnx2x_fastpath *fp)
+{
+ /* Do nothing if no IP/L4 csum validation was done */
+
+ if (cqe->fast_path_cqe.status_flags &
+ (ETH_FAST_PATH_RX_CQE_IP_XSUM_NO_VALIDATION_FLG |
+ ETH_FAST_PATH_RX_CQE_L4_XSUM_NO_VALIDATION_FLG))
+ return;
+
+ /* If both IP/L4 validation were done, check if an error was found. */
+
+ if (cqe->fast_path_cqe.type_error_flags &
+ (ETH_FAST_PATH_RX_CQE_IP_BAD_XSUM_FLG |
+ ETH_FAST_PATH_RX_CQE_L4_BAD_XSUM_FLG))
+ fp->eth_q_stats.hw_csum_err++;
+ else
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+}
int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget)
{
@@ -806,13 +825,9 @@
skb_checksum_none_assert(skb);
- if (bp->dev->features & NETIF_F_RXCSUM) {
+ if (bp->dev->features & NETIF_F_RXCSUM)
+ bnx2x_csum_validate(skb, cqe, fp);
- if (likely(BNX2X_RX_CSUM_OK(cqe)))
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- else
- fp->eth_q_stats.hw_csum_err++;
- }
skb_record_rx_queue(skb, fp->rx_queue);
@@ -2501,8 +2516,6 @@
/* we split the first BD into headers and data BDs
* to ease the pain of our fellow microcode engineers
* we use one mapping for both BDs
- * So far this has only been observed to happen
- * in Other Operating Systems(TM)
*/
static noinline u16 bnx2x_tx_split(struct bnx2x *bp,
struct bnx2x_fp_txdata *txdata,
@@ -3156,7 +3169,7 @@
txdata->tx_bd_prod += nbd;
- if (unlikely(bnx2x_tx_avail(bp, txdata) < MAX_SKB_FRAGS + 3)) {
+ if (unlikely(bnx2x_tx_avail(bp, txdata) < MAX_SKB_FRAGS + 4)) {
netif_tx_stop_queue(txq);
/* paired memory barrier is in bnx2x_tx_int(), we have to keep
@@ -3165,7 +3178,7 @@
smp_mb();
fp->eth_q_stats.driver_xoff++;
- if (bnx2x_tx_avail(bp, txdata) >= MAX_SKB_FRAGS + 3)
+ if (bnx2x_tx_avail(bp, txdata) >= MAX_SKB_FRAGS + 4)
netif_tx_wake_queue(txq);
}
txdata->tx_pkt++;
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index edeeb51..e47ff8b 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -14275,7 +14275,8 @@
}
}
- if (tg3_flag(tp, 5755_PLUS))
+ if (tg3_flag(tp, 5755_PLUS) ||
+ GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906)
tg3_flag_set(tp, SHORT_DMA_BUG);
if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719)
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 896f283..5a34503 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -736,6 +736,8 @@
copied = make_tx_wrbs(adapter, txq, skb, wrb_cnt, dummy_wrb);
if (copied) {
+ int gso_segs = skb_shinfo(skb)->gso_segs;
+
/* record the sent skb in the sent_skb table */
BUG_ON(txo->sent_skb_list[start]);
txo->sent_skb_list[start] = skb;
@@ -753,8 +755,7 @@
be_txq_notify(adapter, txq->id, wrb_cnt);
- be_tx_stats_update(txo, wrb_cnt, copied,
- skb_shinfo(skb)->gso_segs, stopped);
+ be_tx_stats_update(txo, wrb_cnt, copied, gso_segs, stopped);
} else {
txq->head = start;
dev_kfree_skb_any(skb);
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 31d37a2..ba86b3f 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6238,7 +6238,8 @@
}
if (hw->phy.ops.check_reset_block && hw->phy.ops.check_reset_block(hw))
- e_info("PHY reset is blocked due to SOL/IDER session.\n");
+ dev_info(&pdev->dev,
+ "PHY reset is blocked due to SOL/IDER session.\n");
/* Set initial default active device features */
netdev->features = (NETIF_F_SG |
@@ -6288,7 +6289,7 @@
if (e1000_validate_nvm_checksum(&adapter->hw) >= 0)
break;
if (i == 2) {
- e_err("The NVM Checksum Is Not Valid\n");
+ dev_err(&pdev->dev, "The NVM Checksum Is Not Valid\n");
err = -EIO;
goto err_eeprom;
}
@@ -6298,13 +6299,15 @@
/* copy the MAC address */
if (e1000e_read_mac_addr(&adapter->hw))
- e_err("NVM Read Error while reading MAC address\n");
+ dev_err(&pdev->dev,
+ "NVM Read Error while reading MAC address\n");
memcpy(netdev->dev_addr, adapter->hw.mac.addr, netdev->addr_len);
memcpy(netdev->perm_addr, adapter->hw.mac.addr, netdev->addr_len);
if (!is_valid_ether_addr(netdev->perm_addr)) {
- e_err("Invalid MAC Address: %pM\n", netdev->perm_addr);
+ dev_err(&pdev->dev, "Invalid MAC Address: %pM\n",
+ netdev->perm_addr);
err = -EIO;
goto err_eeprom;
}
diff --git a/drivers/net/ethernet/intel/e1000e/param.c b/drivers/net/ethernet/intel/e1000e/param.c
index 55cc1565b..dfbfa7f 100644
--- a/drivers/net/ethernet/intel/e1000e/param.c
+++ b/drivers/net/ethernet/intel/e1000e/param.c
@@ -199,16 +199,19 @@
case enable_option:
switch (*value) {
case OPTION_ENABLED:
- e_info("%s Enabled\n", opt->name);
+ dev_info(&adapter->pdev->dev, "%s Enabled\n",
+ opt->name);
return 0;
case OPTION_DISABLED:
- e_info("%s Disabled\n", opt->name);
+ dev_info(&adapter->pdev->dev, "%s Disabled\n",
+ opt->name);
return 0;
}
break;
case range_option:
if (*value >= opt->arg.r.min && *value <= opt->arg.r.max) {
- e_info("%s set to %i\n", opt->name, *value);
+ dev_info(&adapter->pdev->dev, "%s set to %i\n",
+ opt->name, *value);
return 0;
}
break;
@@ -220,7 +223,8 @@
ent = &opt->arg.l.p[i];
if (*value == ent->i) {
if (ent->str[0] != '\0')
- e_info("%s\n", ent->str);
+ dev_info(&adapter->pdev->dev, "%s\n",
+ ent->str);
return 0;
}
}
@@ -230,8 +234,8 @@
BUG();
}
- e_info("Invalid %s value specified (%i) %s\n", opt->name, *value,
- opt->err);
+ dev_info(&adapter->pdev->dev, "Invalid %s value specified (%i) %s\n",
+ opt->name, *value, opt->err);
*value = opt->def;
return -1;
}
@@ -251,8 +255,10 @@
int bd = adapter->bd_number;
if (bd >= E1000_MAX_NIC) {
- e_notice("Warning: no configuration for board #%i\n", bd);
- e_notice("Using defaults for all values\n");
+ dev_notice(&adapter->pdev->dev,
+ "Warning: no configuration for board #%i\n", bd);
+ dev_notice(&adapter->pdev->dev,
+ "Using defaults for all values\n");
}
{ /* Transmit Interrupt Delay */
@@ -366,27 +372,32 @@
* default values
*/
if (adapter->itr > 4)
- e_info("%s set to default %d\n", opt.name,
- adapter->itr);
+ dev_info(&adapter->pdev->dev,
+ "%s set to default %d\n", opt.name,
+ adapter->itr);
}
adapter->itr_setting = adapter->itr;
switch (adapter->itr) {
case 0:
- e_info("%s turned off\n", opt.name);
+ dev_info(&adapter->pdev->dev, "%s turned off\n",
+ opt.name);
break;
case 1:
- e_info("%s set to dynamic mode\n", opt.name);
+ dev_info(&adapter->pdev->dev,
+ "%s set to dynamic mode\n", opt.name);
adapter->itr = 20000;
break;
case 3:
- e_info("%s set to dynamic conservative mode\n",
- opt.name);
+ dev_info(&adapter->pdev->dev,
+ "%s set to dynamic conservative mode\n",
+ opt.name);
adapter->itr = 20000;
break;
case 4:
- e_info("%s set to simplified (2000-8000 ints) mode\n",
- opt.name);
+ dev_info(&adapter->pdev->dev,
+ "%s set to simplified (2000-8000 ints) mode\n",
+ opt.name);
break;
default:
/*
diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile
index 0bdf06b..5fd5d04 100644
--- a/drivers/net/ethernet/intel/ixgbe/Makefile
+++ b/drivers/net/ethernet/intel/ixgbe/Makefile
@@ -34,11 +34,11 @@
ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \
ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \
- ixgbe_mbx.o ixgbe_x540.o ixgbe_sysfs.o ixgbe_lib.o
+ ixgbe_mbx.o ixgbe_x540.o ixgbe_lib.o
ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \
ixgbe_dcb_82599.o ixgbe_dcb_nl.o
ixgbe-$(CONFIG_IXGBE_PTP) += ixgbe_ptp.o
-
+ixgbe-$(CONFIG_IXGBE_HWMON) += ixgbe_sysfs.o
ixgbe-$(CONFIG_FCOE:m=y) += ixgbe_fcoe.o
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 3ef3c52..41f9f6e 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -561,6 +561,7 @@
spinlock_t tmreg_lock;
struct cyclecounter cc;
struct timecounter tc;
+ int rx_hwtstamp_filter;
u32 base_incval;
u32 cycle_speed;
#endif /* CONFIG_IXGBE_PTP */
@@ -718,6 +719,7 @@
extern void ixgbe_ptp_tx_hwtstamp(struct ixgbe_q_vector *q_vector,
struct sk_buff *skb);
extern void ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector,
+ union ixgbe_adv_rx_desc *rx_desc,
struct sk_buff *skb);
extern int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter,
struct ifreq *ifr, int cmd);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 17ad6a3..b0ddfd4 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -790,12 +790,10 @@
total_packets += tx_buffer->gso_segs;
#ifdef CONFIG_IXGBE_PTP
- if (unlikely(tx_buffer->tx_flags &
- IXGBE_TX_FLAGS_TSTAMP))
- ixgbe_ptp_tx_hwtstamp(q_vector,
- tx_buffer->skb);
-
+ if (unlikely(tx_buffer->tx_flags & IXGBE_TX_FLAGS_TSTAMP))
+ ixgbe_ptp_tx_hwtstamp(q_vector, tx_buffer->skb);
#endif
+
/* free the skb */
dev_kfree_skb_any(tx_buffer->skb);
@@ -1399,8 +1397,7 @@
ixgbe_rx_checksum(rx_ring, rx_desc, skb);
#ifdef CONFIG_IXGBE_PTP
- if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_TS))
- ixgbe_ptp_rx_hwtstamp(rx_ring->q_vector, skb);
+ ixgbe_ptp_rx_hwtstamp(rx_ring->q_vector, rx_desc, skb);
#endif
if ((dev->features & NETIF_F_HW_VLAN_RX) &&
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index ddc6a4d..cb7d1b2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -26,6 +26,7 @@
*******************************************************************************/
#include "ixgbe.h"
#include <linux/export.h>
+#include <linux/ptp_classify.h>
/*
* The 82599 and the X540 do not have true 64bit nanosecond scale
@@ -100,6 +101,10 @@
#define NSECS_PER_SEC 1000000000ULL
#endif
+static struct sock_filter ptp_filter[] = {
+ PTP_FILTER
+};
+
/**
* ixgbe_ptp_read - read raw cycle counter (to be used by time counter)
* @cc - the cyclecounter structure
@@ -307,13 +312,14 @@
!(adapter->flags2 & IXGBE_FLAG2_PTP_PPS_ENABLED))
return;
- switch (hw->mac.type) {
- case ixgbe_mac_X540:
- if (eicr & IXGBE_EICR_TIMESYNC)
+ if (unlikely(eicr & IXGBE_EICR_TIMESYNC)) {
+ switch (hw->mac.type) {
+ case ixgbe_mac_X540:
ptp_clock_event(adapter->ptp_clock, &event);
- break;
- default:
- break;
+ break;
+ default:
+ break;
+ }
}
}
@@ -425,6 +431,68 @@
}
/**
+ * ixgbe_ptp_match - determine if this skb matches a ptp packet
+ * @skb: pointer to the skb
+ * @hwtstamp: pointer to the hwtstamp_config to check
+ *
+ * Determine whether the skb should have been timestamped, assuming the
+ * hwtstamp was set via the hwtstamp ioctl. Returns non-zero when the packet
+ * should have a timestamp waiting in the registers, and 0 otherwise.
+ *
+ * V1 packets have to check the version type to determine whether they are
+ * correct. However, we can't directly access the data because it might be
+ * fragmented in the SKB, in paged memory. In order to work around this, we
+ * use skb_copy_bits which will properly copy the data whether it is in the
+ * paged memory fragments or not. We have to copy the IP header as well as the
+ * message type.
+ */
+static int ixgbe_ptp_match(struct sk_buff *skb, int rx_filter)
+{
+ struct iphdr iph;
+ u8 msgtype;
+ unsigned int type, offset;
+
+ if (rx_filter == HWTSTAMP_FILTER_NONE)
+ return 0;
+
+ type = sk_run_filter(skb, ptp_filter);
+
+ if (likely(rx_filter == HWTSTAMP_FILTER_PTP_V2_EVENT))
+ return type & PTP_CLASS_V2;
+
+ /* For the remaining cases actually check message type */
+ switch (type) {
+ case PTP_CLASS_V1_IPV4:
+ skb_copy_bits(skb, OFF_IHL, &iph, sizeof(iph));
+ offset = ETH_HLEN + (iph.ihl << 2) + UDP_HLEN + OFF_PTP_CONTROL;
+ break;
+ case PTP_CLASS_V1_IPV6:
+ offset = OFF_PTP6 + OFF_PTP_CONTROL;
+ break;
+ default:
+ /* other cases invalid or handled above */
+ return 0;
+ }
+
+ /* Make sure our buffer is long enough */
+ if (skb->len < offset)
+ return 0;
+
+ skb_copy_bits(skb, offset, &msgtype, sizeof(msgtype));
+
+ switch (rx_filter) {
+ case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+ return (msgtype == IXGBE_RXMTRL_V1_SYNC_MSG);
+ break;
+ case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+ return (msgtype == IXGBE_RXMTRL_V1_DELAY_REQ_MSG);
+ break;
+ default:
+ return 0;
+ }
+}
+
+/**
* ixgbe_ptp_tx_hwtstamp - utility function which checks for TX time stamp
* @q_vector: structure containing interrupt and ring information
* @skb: particular skb to send timestamp with
@@ -473,6 +541,7 @@
/**
* ixgbe_ptp_rx_hwtstamp - utility function which checks for RX time stamp
* @q_vector: structure containing interrupt and ring information
+ * @rx_desc: the rx descriptor
* @skb: particular skb to send timestamp with
*
* if the timestamp is valid, we convert it into the timecounter ns
@@ -480,6 +549,7 @@
* is passed up the network stack
*/
void ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector,
+ union ixgbe_adv_rx_desc *rx_desc,
struct sk_buff *skb)
{
struct ixgbe_adapter *adapter;
@@ -497,21 +567,33 @@
hw = &adapter->hw;
tsyncrxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCRXCTL);
+
+ /* Check if we have a valid timestamp and make sure the skb should
+ * have been timestamped */
+ if (likely(!(tsyncrxctl & IXGBE_TSYNCRXCTL_VALID) ||
+ !ixgbe_ptp_match(skb, adapter->rx_hwtstamp_filter)))
+ return;
+
+ /*
+ * Always read the registers, in order to clear a possible fault
+ * because of stagnant RX timestamp values for a packet that never
+ * reached the queue.
+ */
regval |= (u64)IXGBE_READ_REG(hw, IXGBE_RXSTMPL);
regval |= (u64)IXGBE_READ_REG(hw, IXGBE_RXSTMPH) << 32;
/*
- * If this bit is set, then the RX registers contain the time stamp. No
- * other packet will be time stamped until we read these registers, so
- * read the registers to make them available again. Because only one
- * packet can be time stamped at a time, we know that the register
- * values must belong to this one here and therefore we don't need to
- * compare any of the additional attributes stored for it.
+ * If the timestamp bit is set in the packet's descriptor, we know the
+ * timestamp belongs to this packet. No other packet can be
+ * timestamped until the registers for timestamping have been read.
+ * Therefor only one packet with this bit can be in the queue at a
+ * time, and the rx timestamp values that were in the registers belong
+ * to this packet.
*
* If nothing went wrong, then it should have a skb_shared_tx that we
* can turn into a skb_shared_hwtstamps.
*/
- if (!(tsyncrxctl & IXGBE_TSYNCRXCTL_VALID))
+ if (unlikely(!ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_TS)))
return;
spin_lock_irqsave(&adapter->tmreg_lock, flags);
@@ -539,6 +621,11 @@
* type has to be specified. Matching the kind of event packet is
* not supported, with the exception of "all V2 events regardless of
* level 2 or 4".
+ *
+ * Since hardware always timestamps Path delay packets when timestamping V2
+ * packets, regardless of the type specified in the register, only use V2
+ * Event mode. This more accurately tells the user what the hardware is going
+ * to do anyways.
*/
int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter,
struct ifreq *ifr, int cmd)
@@ -582,41 +669,30 @@
tsync_rx_mtrl = IXGBE_RXMTRL_V1_DELAY_REQ_MSG;
is_l4 = true;
break;
+ case HWTSTAMP_FILTER_PTP_V2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
case HWTSTAMP_FILTER_PTP_V2_SYNC:
case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
- tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L2_L4_V2;
- tsync_rx_mtrl = IXGBE_RXMTRL_V2_SYNC_MSG;
- is_l2 = true;
- is_l4 = true;
- config.rx_filter = HWTSTAMP_FILTER_SOME;
- break;
case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
- tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L2_L4_V2;
- tsync_rx_mtrl = IXGBE_RXMTRL_V2_DELAY_REQ_MSG;
- is_l2 = true;
- is_l4 = true;
- config.rx_filter = HWTSTAMP_FILTER_SOME;
- break;
- case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
- case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
- case HWTSTAMP_FILTER_PTP_V2_EVENT:
tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_EVENT_V2;
- config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
is_l2 = true;
is_l4 = true;
+ config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
break;
case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
case HWTSTAMP_FILTER_ALL:
default:
/*
- * register RXMTRL must be set, therefore it is not
- * possible to time stamp both V1 Sync and Delay_Req messages
- * and hardware does not support timestamping all packets
- * => return error
+ * register RXMTRL must be set in order to do V1 packets,
+ * therefore it is not possible to time stamp both V1 Sync and
+ * Delay_Req messages and hardware does not support
+ * timestamping all packets => return error
*/
+ config.rx_filter = HWTSTAMP_FILTER_NONE;
return -ERANGE;
}
@@ -626,6 +702,9 @@
return 0;
}
+ /* Store filter value for later use */
+ adapter->rx_hwtstamp_filter = config.rx_filter;
+
/* define ethertype filter for timestamped packets */
if (is_l2)
IXGBE_WRITE_REG(hw, IXGBE_ETQF(3),
@@ -861,6 +940,10 @@
return;
}
+ /* initialize the ptp filter */
+ if (ptp_filter_init(ptp_filter, ARRAY_SIZE(ptp_filter)))
+ e_dev_warn("ptp_filter_init failed\n");
+
spin_lock_init(&adapter->tmreg_lock);
ixgbe_ptp_start_cyclecounter(adapter);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c
index 1d80b1c..2334fce 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c
@@ -37,7 +37,6 @@
#include <linux/netdevice.h>
#include <linux/hwmon.h>
-#ifdef CONFIG_IXGBE_HWMON
/* hwmon callback functions */
static ssize_t ixgbe_hwmon_show_location(struct device *dev,
struct device_attribute *attr,
@@ -241,5 +240,4 @@
exit:
return rc;
}
-#endif /* CONFIG_IXGBE_HWMON */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index 204848d..1085c07 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -2419,7 +2419,7 @@
*/
/* BitTimes (BT) conversion */
-#define IXGBE_BT2KB(BT) ((BT + 1023) / (8 * 1024))
+#define IXGBE_BT2KB(BT) ((BT + (8 * 1024 - 1)) / (8 * 1024))
#define IXGBE_B2BT(BT) (BT * 8)
/* Calculate Delay to respond to PFC */
@@ -2450,24 +2450,31 @@
#define IXGBE_PCI_DELAY 10000
/* Calculate X540 delay value in bit times */
-#define IXGBE_FILL_RATE (36 / 25)
-
-#define IXGBE_DV_X540(LINK, TC) (IXGBE_FILL_RATE * \
- (IXGBE_B2BT(LINK) + IXGBE_PFC_D + \
- (2 * IXGBE_CABLE_DC) + \
- (2 * IXGBE_ID_X540) + \
- IXGBE_HD + IXGBE_B2BT(TC)))
+#define IXGBE_DV_X540(_max_frame_link, _max_frame_tc) \
+ ((36 * \
+ (IXGBE_B2BT(_max_frame_link) + \
+ IXGBE_PFC_D + \
+ (2 * IXGBE_CABLE_DC) + \
+ (2 * IXGBE_ID_X540) + \
+ IXGBE_HD) / 25 + 1) + \
+ 2 * IXGBE_B2BT(_max_frame_tc))
/* Calculate 82599, 82598 delay value in bit times */
-#define IXGBE_DV(LINK, TC) (IXGBE_FILL_RATE * \
- (IXGBE_B2BT(LINK) + IXGBE_PFC_D + \
- (2 * IXGBE_CABLE_DC) + (2 * IXGBE_ID) + \
- IXGBE_HD + IXGBE_B2BT(TC)))
+#define IXGBE_DV(_max_frame_link, _max_frame_tc) \
+ ((36 * \
+ (IXGBE_B2BT(_max_frame_link) + \
+ IXGBE_PFC_D + \
+ (2 * IXGBE_CABLE_DC) + \
+ (2 * IXGBE_ID) + \
+ IXGBE_HD) / 25 + 1) + \
+ 2 * IXGBE_B2BT(_max_frame_tc))
/* Calculate low threshold delay values */
-#define IXGBE_LOW_DV_X540(TC) (2 * IXGBE_B2BT(TC) + \
- (IXGBE_FILL_RATE * IXGBE_PCI_DELAY))
-#define IXGBE_LOW_DV(TC) (2 * IXGBE_LOW_DV_X540(TC))
+#define IXGBE_LOW_DV_X540(_max_frame_tc) \
+ (2 * IXGBE_B2BT(_max_frame_tc) + \
+ (36 * IXGBE_PCI_DELAY / 25) + 1)
+#define IXGBE_LOW_DV(_max_frame_tc) \
+ (2 * IXGBE_LOW_DV_X540(_max_frame_tc))
/* Software ATR hash keys */
#define IXGBE_ATR_BUCKET_HASH_KEY 0x3DAD14E2
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index cace36f..28a5445 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -4381,10 +4381,12 @@
struct sky2_port *sky2 = netdev_priv(dev);
netdev_features_t changed = dev->features ^ features;
- if (changed & NETIF_F_RXCSUM) {
- bool on = features & NETIF_F_RXCSUM;
- sky2_write32(sky2->hw, Q_ADDR(rxqaddr[sky2->port], Q_CSR),
- on ? BMU_ENA_RX_CHKSUM : BMU_DIS_RX_CHKSUM);
+ if ((changed & NETIF_F_RXCSUM) &&
+ !(sky2->hw->flags & SKY2_HW_NEW_LE)) {
+ sky2_write32(sky2->hw,
+ Q_ADDR(rxqaddr[sky2->port], Q_CSR),
+ (features & NETIF_F_RXCSUM)
+ ? BMU_ENA_RX_CHKSUM : BMU_DIS_RX_CHKSUM);
}
if (changed & NETIF_F_RXHASH)
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 1fe2c7a..a8fb529 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -697,10 +697,10 @@
if (slave != dev->caps.function)
memset(inbox->buf, 0, 256);
if (dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
- *(u8 *) inbox->buf = !!reset_qkey_viols << 6;
+ *(u8 *) inbox->buf |= !!reset_qkey_viols << 6;
((__be32 *) inbox->buf)[2] = agg_cap_mask;
} else {
- ((u8 *) inbox->buf)[3] = !!reset_qkey_viols;
+ ((u8 *) inbox->buf)[3] |= !!reset_qkey_viols;
((__be32 *) inbox->buf)[1] = agg_cap_mask;
}
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index 8d2666f..083d671 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -946,16 +946,16 @@
/* Update stats */
ndev->stats.tx_packets++;
ndev->stats.tx_bytes += skb->len;
-
- /* Free buffer */
- dev_kfree_skb_irq(skb);
}
+ dev_kfree_skb_irq(skb);
txcidx = readl(LPC_ENET_TXCONSUMEINDEX(pldat->net_base));
}
- if (netif_queue_stopped(ndev))
- netif_wake_queue(ndev);
+ if (pldat->num_used_tx_buffs <= ENET_TX_DESC/2) {
+ if (netif_queue_stopped(ndev))
+ netif_wake_queue(ndev);
+ }
}
static int __lpc_handle_recv(struct net_device *ndev, int budget)
@@ -1320,6 +1320,7 @@
.ndo_set_rx_mode = lpc_eth_set_multicast_list,
.ndo_do_ioctl = lpc_eth_ioctl,
.ndo_set_mac_address = lpc_set_mac_address,
+ .ndo_change_mtu = eth_change_mtu,
};
static int lpc_eth_drv_probe(struct platform_device *pdev)
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 33c3e46..212c121 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -479,7 +479,7 @@
for (i = 0; i < QLCNIC_MAX_PCI_FUNC; i++) {
pfn = pci_info[i].id;
- if (pfn > QLCNIC_MAX_PCI_FUNC) {
+ if (pfn >= QLCNIC_MAX_PCI_FUNC) {
ret = QL_STATUS_INVALID_PARAM;
goto err_eswitch;
}
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 9757ce3..7260aa7 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5889,11 +5889,7 @@
if (status & LinkChg)
__rtl8169_check_link_status(dev, tp, tp->mmio_addr, true);
- napi_disable(&tp->napi);
- rtl_irq_disable(tp);
-
- napi_enable(&tp->napi);
- napi_schedule(&tp->napi);
+ rtl_irq_enable_all(tp);
}
static void rtl_task(struct work_struct *work)
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 0076f77..9f44827 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -15,6 +15,7 @@
config STMMAC_PLATFORM
bool "STMMAC Platform bus support"
depends on STMMAC_ETH
+ default y
---help---
This selects the platform specific bus support for
the stmmac device driver. This is the driver used
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 6d07ba2..dc20c56 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -26,6 +26,7 @@
#include <linux/clk.h>
#include <linux/stmmac.h>
#include <linux/phy.h>
+#include <linux/pci.h>
#include "common.h"
#ifdef CONFIG_STMMAC_TIMER
#include "stmmac_timer.h"
@@ -95,8 +96,6 @@
extern void stmmac_set_ethtool_ops(struct net_device *netdev);
extern const struct stmmac_desc_ops enh_desc_ops;
extern const struct stmmac_desc_ops ndesc_ops;
-extern struct pci_driver stmmac_pci_driver;
-extern struct platform_driver stmmac_pltfr_driver;
int stmmac_freeze(struct net_device *ndev);
int stmmac_restore(struct net_device *ndev);
int stmmac_resume(struct net_device *ndev);
@@ -110,7 +109,7 @@
static inline int stmmac_clk_enable(struct stmmac_priv *priv)
{
if (!IS_ERR(priv->stmmac_clk))
- return clk_enable(priv->stmmac_clk);
+ return clk_prepare_enable(priv->stmmac_clk);
return 0;
}
@@ -120,7 +119,7 @@
if (IS_ERR(priv->stmmac_clk))
return;
- clk_disable(priv->stmmac_clk);
+ clk_disable_unprepare(priv->stmmac_clk);
}
static inline int stmmac_clk_get(struct stmmac_priv *priv)
{
@@ -144,3 +143,60 @@
return 0;
}
#endif /* CONFIG_HAVE_CLK */
+
+
+#ifdef CONFIG_STMMAC_PLATFORM
+extern struct platform_driver stmmac_pltfr_driver;
+static inline int stmmac_register_platform(void)
+{
+ int err;
+
+ err = platform_driver_register(&stmmac_pltfr_driver);
+ if (err)
+ pr_err("stmmac: failed to register the platform driver\n");
+
+ return err;
+}
+static inline void stmmac_unregister_platform(void)
+{
+ platform_driver_register(&stmmac_pltfr_driver);
+}
+#else
+static inline int stmmac_register_platform(void)
+{
+ pr_debug("stmmac: do not register the platf driver\n");
+
+ return -EINVAL;
+}
+static inline void stmmac_unregister_platform(void)
+{
+}
+#endif /* CONFIG_STMMAC_PLATFORM */
+
+#ifdef CONFIG_STMMAC_PCI
+extern struct pci_driver stmmac_pci_driver;
+static inline int stmmac_register_pci(void)
+{
+ int err;
+
+ err = pci_register_driver(&stmmac_pci_driver);
+ if (err)
+ pr_err("stmmac: failed to register the PCI driver\n");
+
+ return err;
+}
+static inline void stmmac_unregister_pci(void)
+{
+ pci_unregister_driver(&stmmac_pci_driver);
+}
+#else
+static inline int stmmac_register_pci(void)
+{
+ pr_debug("stmmac: do not register the PCI driver\n");
+
+ return -EINVAL;
+}
+static inline void stmmac_unregister_pci(void)
+{
+}
+#endif /* CONFIG_STMMAC_PCI */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 8899e10..590e95b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -42,7 +42,6 @@
#include <linux/dma-mapping.h>
#include <linux/slab.h>
#include <linux/prefetch.h>
-#include <linux/pci.h>
#ifdef CONFIG_STMMAC_DEBUG_FS
#include <linux/debugfs.h>
#include <linux/seq_file.h>
@@ -2093,25 +2092,29 @@
}
#endif /* CONFIG_PM */
+/* Driver can be configured w/ and w/ both PCI and Platf drivers
+ * depending on the configuration selected.
+ */
static int __init stmmac_init(void)
{
- int err = 0;
+ int err_plt = 0;
+ int err_pci = 0;
- err = platform_driver_register(&stmmac_pltfr_driver);
+ err_plt = stmmac_register_platform();
+ err_pci = stmmac_register_pci();
- if (!err) {
- err = pci_register_driver(&stmmac_pci_driver);
- if (err)
- platform_driver_unregister(&stmmac_pltfr_driver);
+ if ((err_pci) && (err_plt)) {
+ pr_err("stmmac: driver registration failed\n");
+ return -EINVAL;
}
- return err;
+ return 0;
}
static void __exit stmmac_exit(void)
{
- pci_unregister_driver(&stmmac_pci_driver);
- platform_driver_unregister(&stmmac_pltfr_driver);
+ stmmac_unregister_platform();
+ stmmac_unregister_pci();
}
module_init(stmmac_init);
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 703c8cc..8c726b7 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -3598,7 +3598,6 @@
static void niu_tx_work(struct niu *np, struct tx_ring_info *rp)
{
struct netdev_queue *txq;
- unsigned int tx_bytes;
u16 pkt_cnt, tmp;
int cons, index;
u64 cs;
@@ -3621,18 +3620,12 @@
netif_printk(np, tx_done, KERN_DEBUG, np->dev,
"%s() pkt_cnt[%u] cons[%d]\n", __func__, pkt_cnt, cons);
- tx_bytes = 0;
- tmp = pkt_cnt;
- while (tmp--) {
- tx_bytes += rp->tx_buffs[cons].skb->len;
+ while (pkt_cnt--)
cons = release_tx_packet(np, rp, cons);
- }
rp->cons = cons;
smp_mb();
- netdev_tx_completed_queue(txq, pkt_cnt, tx_bytes);
-
out:
if (unlikely(netif_tx_queue_stopped(txq) &&
(niu_tx_avail(rp) > NIU_TX_WAKEUP_THRESH(rp)))) {
@@ -4333,7 +4326,6 @@
struct tx_ring_info *rp = &np->tx_rings[i];
niu_free_tx_ring_info(np, rp);
- netdev_tx_reset_queue(netdev_get_tx_queue(np->dev, i));
}
kfree(np->tx_rings);
np->tx_rings = NULL;
@@ -6739,8 +6731,6 @@
prod = NEXT_TX(rp, prod);
}
- netdev_tx_sent_queue(txq, skb->len);
-
if (prod < rp->prod)
rp->wrap_bit ^= TX_RING_KICK_WRAP;
rp->prod = prod;
diff --git a/drivers/net/ethernet/tile/Kconfig b/drivers/net/ethernet/tile/Kconfig
index 2d9218f..098b1c4 100644
--- a/drivers/net/ethernet/tile/Kconfig
+++ b/drivers/net/ethernet/tile/Kconfig
@@ -7,6 +7,8 @@
depends on TILE
default y
select CRC32
+ select TILE_GXIO_MPIPE if TILEGX
+ select HIGH_RES_TIMERS if TILEGX
---help---
This is a standard Linux network device driver for the
on-chip Tilera Gigabit Ethernet and XAUI interfaces.
diff --git a/drivers/net/ethernet/tile/Makefile b/drivers/net/ethernet/tile/Makefile
index f634f14..0ef9eef 100644
--- a/drivers/net/ethernet/tile/Makefile
+++ b/drivers/net/ethernet/tile/Makefile
@@ -4,7 +4,7 @@
obj-$(CONFIG_TILE_NET) += tile_net.o
ifdef CONFIG_TILEGX
-tile_net-objs := tilegx.o mpipe.o iorpc_mpipe.o dma_queue.o
+tile_net-y := tilegx.o
else
-tile_net-objs := tilepro.o
+tile_net-y := tilepro.o
endif
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
new file mode 100644
index 0000000..83b4b38
--- /dev/null
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -0,0 +1,1898 @@
+/*
+ * Copyright 2012 Tilera Corporation. All Rights Reserved.
+ *
+ * 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.
+ *
+ * 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, GOOD TITLE or
+ * NON INFRINGEMENT. See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/moduleparam.h>
+#include <linux/sched.h>
+#include <linux/kernel.h> /* printk() */
+#include <linux/slab.h> /* kmalloc() */
+#include <linux/errno.h> /* error codes */
+#include <linux/types.h> /* size_t */
+#include <linux/interrupt.h>
+#include <linux/in.h>
+#include <linux/irq.h>
+#include <linux/netdevice.h> /* struct device, and other headers */
+#include <linux/etherdevice.h> /* eth_type_trans */
+#include <linux/skbuff.h>
+#include <linux/ioctl.h>
+#include <linux/cdev.h>
+#include <linux/hugetlb.h>
+#include <linux/in6.h>
+#include <linux/timer.h>
+#include <linux/hrtimer.h>
+#include <linux/ktime.h>
+#include <linux/io.h>
+#include <linux/ctype.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
+
+#include <asm/checksum.h>
+#include <asm/homecache.h>
+#include <gxio/mpipe.h>
+#include <arch/sim.h>
+
+/* Default transmit lockup timeout period, in jiffies. */
+#define TILE_NET_TIMEOUT (5 * HZ)
+
+/* The maximum number of distinct channels (idesc.channel is 5 bits). */
+#define TILE_NET_CHANNELS 32
+
+/* Maximum number of idescs to handle per "poll". */
+#define TILE_NET_BATCH 128
+
+/* Maximum number of packets to handle per "poll". */
+#define TILE_NET_WEIGHT 64
+
+/* Number of entries in each iqueue. */
+#define IQUEUE_ENTRIES 512
+
+/* Number of entries in each equeue. */
+#define EQUEUE_ENTRIES 2048
+
+/* Total header bytes per equeue slot. Must be big enough for 2 bytes
+ * of NET_IP_ALIGN alignment, plus 14 bytes (?) of L2 header, plus up to
+ * 60 bytes of actual TCP header. We round up to align to cache lines.
+ */
+#define HEADER_BYTES 128
+
+/* Maximum completions per cpu per device (must be a power of two).
+ * ISSUE: What is the right number here? If this is too small, then
+ * egress might block waiting for free space in a completions array.
+ * ISSUE: At the least, allocate these only for initialized echannels.
+ */
+#define TILE_NET_MAX_COMPS 64
+
+#define MAX_FRAGS (MAX_SKB_FRAGS + 1)
+
+/* Size of completions data to allocate.
+ * ISSUE: Probably more than needed since we don't use all the channels.
+ */
+#define COMPS_SIZE (TILE_NET_CHANNELS * sizeof(struct tile_net_comps))
+
+/* Size of NotifRing data to allocate. */
+#define NOTIF_RING_SIZE (IQUEUE_ENTRIES * sizeof(gxio_mpipe_idesc_t))
+
+/* Timeout to wake the per-device TX timer after we stop the queue.
+ * We don't want the timeout too short (adds overhead, and might end
+ * up causing stop/wake/stop/wake cycles) or too long (affects performance).
+ * For the 10 Gb NIC, 30 usec means roughly 30+ 1500-byte packets.
+ */
+#define TX_TIMER_DELAY_USEC 30
+
+/* Timeout to wake the per-cpu egress timer to free completions. */
+#define EGRESS_TIMER_DELAY_USEC 1000
+
+MODULE_AUTHOR("Tilera Corporation");
+MODULE_LICENSE("GPL");
+
+/* A "packet fragment" (a chunk of memory). */
+struct frag {
+ void *buf;
+ size_t length;
+};
+
+/* A single completion. */
+struct tile_net_comp {
+ /* The "complete_count" when the completion will be complete. */
+ s64 when;
+ /* The buffer to be freed when the completion is complete. */
+ struct sk_buff *skb;
+};
+
+/* The completions for a given cpu and echannel. */
+struct tile_net_comps {
+ /* The completions. */
+ struct tile_net_comp comp_queue[TILE_NET_MAX_COMPS];
+ /* The number of completions used. */
+ unsigned long comp_next;
+ /* The number of completions freed. */
+ unsigned long comp_last;
+};
+
+/* The transmit wake timer for a given cpu and echannel. */
+struct tile_net_tx_wake {
+ struct hrtimer timer;
+ struct net_device *dev;
+};
+
+/* Info for a specific cpu. */
+struct tile_net_info {
+ /* The NAPI struct. */
+ struct napi_struct napi;
+ /* Packet queue. */
+ gxio_mpipe_iqueue_t iqueue;
+ /* Our cpu. */
+ int my_cpu;
+ /* True if iqueue is valid. */
+ bool has_iqueue;
+ /* NAPI flags. */
+ bool napi_added;
+ bool napi_enabled;
+ /* Number of small sk_buffs which must still be provided. */
+ unsigned int num_needed_small_buffers;
+ /* Number of large sk_buffs which must still be provided. */
+ unsigned int num_needed_large_buffers;
+ /* A timer for handling egress completions. */
+ struct hrtimer egress_timer;
+ /* True if "egress_timer" is scheduled. */
+ bool egress_timer_scheduled;
+ /* Comps for each egress channel. */
+ struct tile_net_comps *comps_for_echannel[TILE_NET_CHANNELS];
+ /* Transmit wake timer for each egress channel. */
+ struct tile_net_tx_wake tx_wake[TILE_NET_CHANNELS];
+};
+
+/* Info for egress on a particular egress channel. */
+struct tile_net_egress {
+ /* The "equeue". */
+ gxio_mpipe_equeue_t *equeue;
+ /* The headers for TSO. */
+ unsigned char *headers;
+};
+
+/* Info for a specific device. */
+struct tile_net_priv {
+ /* Our network device. */
+ struct net_device *dev;
+ /* The primary link. */
+ gxio_mpipe_link_t link;
+ /* The primary channel, if open, else -1. */
+ int channel;
+ /* The "loopify" egress link, if needed. */
+ gxio_mpipe_link_t loopify_link;
+ /* The "loopify" egress channel, if open, else -1. */
+ int loopify_channel;
+ /* The egress channel (channel or loopify_channel). */
+ int echannel;
+ /* Total stats. */
+ struct net_device_stats stats;
+};
+
+/* Egress info, indexed by "priv->echannel" (lazily created as needed). */
+static struct tile_net_egress egress_for_echannel[TILE_NET_CHANNELS];
+
+/* Devices currently associated with each channel.
+ * NOTE: The array entry can become NULL after ifconfig down, but
+ * we do not free the underlying net_device structures, so it is
+ * safe to use a pointer after reading it from this array.
+ */
+static struct net_device *tile_net_devs_for_channel[TILE_NET_CHANNELS];
+
+/* A mutex for "tile_net_devs_for_channel". */
+static DEFINE_MUTEX(tile_net_devs_for_channel_mutex);
+
+/* The per-cpu info. */
+static DEFINE_PER_CPU(struct tile_net_info, per_cpu_info);
+
+/* The "context" for all devices. */
+static gxio_mpipe_context_t context;
+
+/* Buffer sizes and mpipe enum codes for buffer stacks.
+ * See arch/tile/include/gxio/mpipe.h for the set of possible values.
+ */
+#define BUFFER_SIZE_SMALL_ENUM GXIO_MPIPE_BUFFER_SIZE_128
+#define BUFFER_SIZE_SMALL 128
+#define BUFFER_SIZE_LARGE_ENUM GXIO_MPIPE_BUFFER_SIZE_1664
+#define BUFFER_SIZE_LARGE 1664
+
+/* The small/large "buffer stacks". */
+static int small_buffer_stack = -1;
+static int large_buffer_stack = -1;
+
+/* Amount of memory allocated for each buffer stack. */
+static size_t buffer_stack_size;
+
+/* The actual memory allocated for the buffer stacks. */
+static void *small_buffer_stack_va;
+static void *large_buffer_stack_va;
+
+/* The buckets. */
+static int first_bucket = -1;
+static int num_buckets = 1;
+
+/* The ingress irq. */
+static int ingress_irq = -1;
+
+/* Text value of tile_net.cpus if passed as a module parameter. */
+static char *network_cpus_string;
+
+/* The actual cpus in "network_cpus". */
+static struct cpumask network_cpus_map;
+
+/* If "loopify=LINK" was specified, this is "LINK". */
+static char *loopify_link_name;
+
+/* If "tile_net.custom" was specified, this is non-NULL. */
+static char *custom_str;
+
+/* The "tile_net.cpus" argument specifies the cpus that are dedicated
+ * to handle ingress packets.
+ *
+ * The parameter should be in the form "tile_net.cpus=m-n[,x-y]", where
+ * m, n, x, y are integer numbers that represent the cpus that can be
+ * neither a dedicated cpu nor a dataplane cpu.
+ */
+static bool network_cpus_init(void)
+{
+ char buf[1024];
+ int rc;
+
+ if (network_cpus_string == NULL)
+ return false;
+
+ rc = cpulist_parse_crop(network_cpus_string, &network_cpus_map);
+ if (rc != 0) {
+ pr_warn("tile_net.cpus=%s: malformed cpu list\n",
+ network_cpus_string);
+ return false;
+ }
+
+ /* Remove dedicated cpus. */
+ cpumask_and(&network_cpus_map, &network_cpus_map, cpu_possible_mask);
+
+ if (cpumask_empty(&network_cpus_map)) {
+ pr_warn("Ignoring empty tile_net.cpus='%s'.\n",
+ network_cpus_string);
+ return false;
+ }
+
+ cpulist_scnprintf(buf, sizeof(buf), &network_cpus_map);
+ pr_info("Linux network CPUs: %s\n", buf);
+ return true;
+}
+
+module_param_named(cpus, network_cpus_string, charp, 0444);
+MODULE_PARM_DESC(cpus, "cpulist of cores that handle network interrupts");
+
+/* The "tile_net.loopify=LINK" argument causes the named device to
+ * actually use "loop0" for ingress, and "loop1" for egress. This
+ * allows an app to sit between the actual link and linux, passing
+ * (some) packets along to linux, and forwarding (some) packets sent
+ * out by linux.
+ */
+module_param_named(loopify, loopify_link_name, charp, 0444);
+MODULE_PARM_DESC(loopify, "name the device to use loop0/1 for ingress/egress");
+
+/* The "tile_net.custom" argument causes us to ignore the "conventional"
+ * classifier metadata, in particular, the "l2_offset".
+ */
+module_param_named(custom, custom_str, charp, 0444);
+MODULE_PARM_DESC(custom, "indicates a (heavily) customized classifier");
+
+/* Atomically update a statistics field.
+ * Note that on TILE-Gx, this operation is fire-and-forget on the
+ * issuing core (single-cycle dispatch) and takes only a few cycles
+ * longer than a regular store when the request reaches the home cache.
+ * No expensive bus management overhead is required.
+ */
+static void tile_net_stats_add(unsigned long value, unsigned long *field)
+{
+ BUILD_BUG_ON(sizeof(atomic_long_t) != sizeof(unsigned long));
+ atomic_long_add(value, (atomic_long_t *)field);
+}
+
+/* Allocate and push a buffer. */
+static bool tile_net_provide_buffer(bool small)
+{
+ int stack = small ? small_buffer_stack : large_buffer_stack;
+ const unsigned long buffer_alignment = 128;
+ struct sk_buff *skb;
+ int len;
+
+ len = sizeof(struct sk_buff **) + buffer_alignment;
+ len += (small ? BUFFER_SIZE_SMALL : BUFFER_SIZE_LARGE);
+ skb = dev_alloc_skb(len);
+ if (skb == NULL)
+ return false;
+
+ /* Make room for a back-pointer to 'skb' and guarantee alignment. */
+ skb_reserve(skb, sizeof(struct sk_buff **));
+ skb_reserve(skb, -(long)skb->data & (buffer_alignment - 1));
+
+ /* Save a back-pointer to 'skb'. */
+ *(struct sk_buff **)(skb->data - sizeof(struct sk_buff **)) = skb;
+
+ /* Make sure "skb" and the back-pointer have been flushed. */
+ wmb();
+
+ gxio_mpipe_push_buffer(&context, stack,
+ (void *)va_to_tile_io_addr(skb->data));
+
+ return true;
+}
+
+/* Convert a raw mpipe buffer to its matching skb pointer. */
+static struct sk_buff *mpipe_buf_to_skb(void *va)
+{
+ /* Acquire the associated "skb". */
+ struct sk_buff **skb_ptr = va - sizeof(*skb_ptr);
+ struct sk_buff *skb = *skb_ptr;
+
+ /* Paranoia. */
+ if (skb->data != va) {
+ /* Panic here since there's a reasonable chance
+ * that corrupt buffers means generic memory
+ * corruption, with unpredictable system effects.
+ */
+ panic("Corrupt linux buffer! va=%p, skb=%p, skb->data=%p",
+ va, skb, skb->data);
+ }
+
+ return skb;
+}
+
+static void tile_net_pop_all_buffers(int stack)
+{
+ for (;;) {
+ tile_io_addr_t addr =
+ (tile_io_addr_t)gxio_mpipe_pop_buffer(&context, stack);
+ if (addr == 0)
+ break;
+ dev_kfree_skb_irq(mpipe_buf_to_skb(tile_io_addr_to_va(addr)));
+ }
+}
+
+/* Provide linux buffers to mPIPE. */
+static void tile_net_provide_needed_buffers(void)
+{
+ struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+
+ while (info->num_needed_small_buffers != 0) {
+ if (!tile_net_provide_buffer(true))
+ goto oops;
+ info->num_needed_small_buffers--;
+ }
+
+ while (info->num_needed_large_buffers != 0) {
+ if (!tile_net_provide_buffer(false))
+ goto oops;
+ info->num_needed_large_buffers--;
+ }
+
+ return;
+
+oops:
+ /* Add a description to the page allocation failure dump. */
+ pr_notice("Tile %d still needs some buffers\n", info->my_cpu);
+}
+
+static inline bool filter_packet(struct net_device *dev, void *buf)
+{
+ /* Filter packets received before we're up. */
+ if (dev == NULL || !(dev->flags & IFF_UP))
+ return true;
+
+ /* Filter out packets that aren't for us. */
+ if (!(dev->flags & IFF_PROMISC) &&
+ !is_multicast_ether_addr(buf) &&
+ compare_ether_addr(dev->dev_addr, buf) != 0)
+ return true;
+
+ return false;
+}
+
+static void tile_net_receive_skb(struct net_device *dev, struct sk_buff *skb,
+ gxio_mpipe_idesc_t *idesc, unsigned long len)
+{
+ struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+ struct tile_net_priv *priv = netdev_priv(dev);
+
+ /* Encode the actual packet length. */
+ skb_put(skb, len);
+
+ skb->protocol = eth_type_trans(skb, dev);
+
+ /* Acknowledge "good" hardware checksums. */
+ if (idesc->cs && idesc->csum_seed_val == 0xFFFF)
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+ netif_receive_skb(skb);
+
+ /* Update stats. */
+ tile_net_stats_add(1, &priv->stats.rx_packets);
+ tile_net_stats_add(len, &priv->stats.rx_bytes);
+
+ /* Need a new buffer. */
+ if (idesc->size == BUFFER_SIZE_SMALL_ENUM)
+ info->num_needed_small_buffers++;
+ else
+ info->num_needed_large_buffers++;
+}
+
+/* Handle a packet. Return true if "processed", false if "filtered". */
+static bool tile_net_handle_packet(gxio_mpipe_idesc_t *idesc)
+{
+ struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+ struct net_device *dev = tile_net_devs_for_channel[idesc->channel];
+ uint8_t l2_offset;
+ void *va;
+ void *buf;
+ unsigned long len;
+ bool filter;
+
+ /* Drop packets for which no buffer was available.
+ * NOTE: This happens under heavy load.
+ */
+ if (idesc->be) {
+ struct tile_net_priv *priv = netdev_priv(dev);
+ tile_net_stats_add(1, &priv->stats.rx_dropped);
+ gxio_mpipe_iqueue_consume(&info->iqueue, idesc);
+ if (net_ratelimit())
+ pr_info("Dropping packet (insufficient buffers).\n");
+ return false;
+ }
+
+ /* Get the "l2_offset", if allowed. */
+ l2_offset = custom_str ? 0 : gxio_mpipe_idesc_get_l2_offset(idesc);
+
+ /* Get the raw buffer VA (includes "headroom"). */
+ va = tile_io_addr_to_va((unsigned long)(long)idesc->va);
+
+ /* Get the actual packet start/length. */
+ buf = va + l2_offset;
+ len = idesc->l2_size - l2_offset;
+
+ /* Point "va" at the raw buffer. */
+ va -= NET_IP_ALIGN;
+
+ filter = filter_packet(dev, buf);
+ if (filter) {
+ gxio_mpipe_iqueue_drop(&info->iqueue, idesc);
+ } else {
+ struct sk_buff *skb = mpipe_buf_to_skb(va);
+
+ /* Skip headroom, and any custom header. */
+ skb_reserve(skb, NET_IP_ALIGN + l2_offset);
+
+ tile_net_receive_skb(dev, skb, idesc, len);
+ }
+
+ gxio_mpipe_iqueue_consume(&info->iqueue, idesc);
+ return !filter;
+}
+
+/* Handle some packets for the current CPU.
+ *
+ * This function handles up to TILE_NET_BATCH idescs per call.
+ *
+ * ISSUE: Since we do not provide new buffers until this function is
+ * complete, we must initially provide enough buffers for each network
+ * cpu to fill its iqueue and also its batched idescs.
+ *
+ * ISSUE: The "rotting packet" race condition occurs if a packet
+ * arrives after the queue appears to be empty, and before the
+ * hypervisor interrupt is re-enabled.
+ */
+static int tile_net_poll(struct napi_struct *napi, int budget)
+{
+ struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+ unsigned int work = 0;
+ gxio_mpipe_idesc_t *idesc;
+ int i, n;
+
+ /* Process packets. */
+ while ((n = gxio_mpipe_iqueue_try_peek(&info->iqueue, &idesc)) > 0) {
+ for (i = 0; i < n; i++) {
+ if (i == TILE_NET_BATCH)
+ goto done;
+ if (tile_net_handle_packet(idesc + i)) {
+ if (++work >= budget)
+ goto done;
+ }
+ }
+ }
+
+ /* There are no packets left. */
+ napi_complete(&info->napi);
+
+ /* Re-enable hypervisor interrupts. */
+ gxio_mpipe_enable_notif_ring_interrupt(&context, info->iqueue.ring);
+
+ /* HACK: Avoid the "rotting packet" problem. */
+ if (gxio_mpipe_iqueue_try_peek(&info->iqueue, &idesc) > 0)
+ napi_schedule(&info->napi);
+
+ /* ISSUE: Handle completions? */
+
+done:
+ tile_net_provide_needed_buffers();
+
+ return work;
+}
+
+/* Handle an ingress interrupt on the current cpu. */
+static irqreturn_t tile_net_handle_ingress_irq(int irq, void *unused)
+{
+ struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+ napi_schedule(&info->napi);
+ return IRQ_HANDLED;
+}
+
+/* Free some completions. This must be called with interrupts blocked. */
+static int tile_net_free_comps(gxio_mpipe_equeue_t *equeue,
+ struct tile_net_comps *comps,
+ int limit, bool force_update)
+{
+ int n = 0;
+ while (comps->comp_last < comps->comp_next) {
+ unsigned int cid = comps->comp_last % TILE_NET_MAX_COMPS;
+ struct tile_net_comp *comp = &comps->comp_queue[cid];
+ if (!gxio_mpipe_equeue_is_complete(equeue, comp->when,
+ force_update || n == 0))
+ break;
+ dev_kfree_skb_irq(comp->skb);
+ comps->comp_last++;
+ if (++n == limit)
+ break;
+ }
+ return n;
+}
+
+/* Add a completion. This must be called with interrupts blocked.
+ * tile_net_equeue_try_reserve() will have ensured a free completion entry.
+ */
+static void add_comp(gxio_mpipe_equeue_t *equeue,
+ struct tile_net_comps *comps,
+ uint64_t when, struct sk_buff *skb)
+{
+ int cid = comps->comp_next % TILE_NET_MAX_COMPS;
+ comps->comp_queue[cid].when = when;
+ comps->comp_queue[cid].skb = skb;
+ comps->comp_next++;
+}
+
+static void tile_net_schedule_tx_wake_timer(struct net_device *dev)
+{
+ struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+ struct tile_net_priv *priv = netdev_priv(dev);
+
+ hrtimer_start(&info->tx_wake[priv->echannel].timer,
+ ktime_set(0, TX_TIMER_DELAY_USEC * 1000UL),
+ HRTIMER_MODE_REL_PINNED);
+}
+
+static enum hrtimer_restart tile_net_handle_tx_wake_timer(struct hrtimer *t)
+{
+ struct tile_net_tx_wake *tx_wake =
+ container_of(t, struct tile_net_tx_wake, timer);
+ netif_wake_subqueue(tx_wake->dev, smp_processor_id());
+ return HRTIMER_NORESTART;
+}
+
+/* Make sure the egress timer is scheduled. */
+static void tile_net_schedule_egress_timer(void)
+{
+ struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+
+ if (!info->egress_timer_scheduled) {
+ hrtimer_start(&info->egress_timer,
+ ktime_set(0, EGRESS_TIMER_DELAY_USEC * 1000UL),
+ HRTIMER_MODE_REL_PINNED);
+ info->egress_timer_scheduled = true;
+ }
+}
+
+/* The "function" for "info->egress_timer".
+ *
+ * This timer will reschedule itself as long as there are any pending
+ * completions expected for this tile.
+ */
+static enum hrtimer_restart tile_net_handle_egress_timer(struct hrtimer *t)
+{
+ struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+ unsigned long irqflags;
+ bool pending = false;
+ int i;
+
+ local_irq_save(irqflags);
+
+ /* The timer is no longer scheduled. */
+ info->egress_timer_scheduled = false;
+
+ /* Free all possible comps for this tile. */
+ for (i = 0; i < TILE_NET_CHANNELS; i++) {
+ struct tile_net_egress *egress = &egress_for_echannel[i];
+ struct tile_net_comps *comps = info->comps_for_echannel[i];
+ if (comps->comp_last >= comps->comp_next)
+ continue;
+ tile_net_free_comps(egress->equeue, comps, -1, true);
+ pending = pending || (comps->comp_last < comps->comp_next);
+ }
+
+ /* Reschedule timer if needed. */
+ if (pending)
+ tile_net_schedule_egress_timer();
+
+ local_irq_restore(irqflags);
+
+ return HRTIMER_NORESTART;
+}
+
+/* Helper function for "tile_net_update()".
+ * "dev" (i.e. arg) is the device being brought up or down,
+ * or NULL if all devices are now down.
+ */
+static void tile_net_update_cpu(void *arg)
+{
+ struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+ struct net_device *dev = arg;
+
+ if (!info->has_iqueue)
+ return;
+
+ if (dev != NULL) {
+ if (!info->napi_added) {
+ netif_napi_add(dev, &info->napi,
+ tile_net_poll, TILE_NET_WEIGHT);
+ info->napi_added = true;
+ }
+ if (!info->napi_enabled) {
+ napi_enable(&info->napi);
+ info->napi_enabled = true;
+ }
+ enable_percpu_irq(ingress_irq, 0);
+ } else {
+ disable_percpu_irq(ingress_irq);
+ if (info->napi_enabled) {
+ napi_disable(&info->napi);
+ info->napi_enabled = false;
+ }
+ /* FIXME: Drain the iqueue. */
+ }
+}
+
+/* Helper function for tile_net_open() and tile_net_stop().
+ * Always called under tile_net_devs_for_channel_mutex.
+ */
+static int tile_net_update(struct net_device *dev)
+{
+ static gxio_mpipe_rules_t rules; /* too big to fit on the stack */
+ bool saw_channel = false;
+ int channel;
+ int rc;
+ int cpu;
+
+ gxio_mpipe_rules_init(&rules, &context);
+
+ for (channel = 0; channel < TILE_NET_CHANNELS; channel++) {
+ if (tile_net_devs_for_channel[channel] == NULL)
+ continue;
+ if (!saw_channel) {
+ saw_channel = true;
+ gxio_mpipe_rules_begin(&rules, first_bucket,
+ num_buckets, NULL);
+ gxio_mpipe_rules_set_headroom(&rules, NET_IP_ALIGN);
+ }
+ gxio_mpipe_rules_add_channel(&rules, channel);
+ }
+
+ /* NOTE: This can fail if there is no classifier.
+ * ISSUE: Can anything else cause it to fail?
+ */
+ rc = gxio_mpipe_rules_commit(&rules);
+ if (rc != 0) {
+ netdev_warn(dev, "gxio_mpipe_rules_commit failed: %d\n", rc);
+ return -EIO;
+ }
+
+ /* Update all cpus, sequentially (to protect "netif_napi_add()"). */
+ for_each_online_cpu(cpu)
+ smp_call_function_single(cpu, tile_net_update_cpu,
+ (saw_channel ? dev : NULL), 1);
+
+ /* HACK: Allow packets to flow in the simulator. */
+ if (saw_channel)
+ sim_enable_mpipe_links(0, -1);
+
+ return 0;
+}
+
+/* Allocate and initialize mpipe buffer stacks, and register them in
+ * the mPIPE TLBs, for both small and large packet sizes.
+ * This routine supports tile_net_init_mpipe(), below.
+ */
+static int init_buffer_stacks(struct net_device *dev, int num_buffers)
+{
+ pte_t hash_pte = pte_set_home((pte_t) { 0 }, PAGE_HOME_HASH);
+ int rc;
+
+ /* Compute stack bytes; we round up to 64KB and then use
+ * alloc_pages() so we get the required 64KB alignment as well.
+ */
+ buffer_stack_size =
+ ALIGN(gxio_mpipe_calc_buffer_stack_bytes(num_buffers),
+ 64 * 1024);
+
+ /* Allocate two buffer stack indices. */
+ rc = gxio_mpipe_alloc_buffer_stacks(&context, 2, 0, 0);
+ if (rc < 0) {
+ netdev_err(dev, "gxio_mpipe_alloc_buffer_stacks failed: %d\n",
+ rc);
+ return rc;
+ }
+ small_buffer_stack = rc;
+ large_buffer_stack = rc + 1;
+
+ /* Allocate the small memory stack. */
+ small_buffer_stack_va =
+ alloc_pages_exact(buffer_stack_size, GFP_KERNEL);
+ if (small_buffer_stack_va == NULL) {
+ netdev_err(dev,
+ "Could not alloc %zd bytes for buffer stacks\n",
+ buffer_stack_size);
+ return -ENOMEM;
+ }
+ rc = gxio_mpipe_init_buffer_stack(&context, small_buffer_stack,
+ BUFFER_SIZE_SMALL_ENUM,
+ small_buffer_stack_va,
+ buffer_stack_size, 0);
+ if (rc != 0) {
+ netdev_err(dev, "gxio_mpipe_init_buffer_stack: %d\n", rc);
+ return rc;
+ }
+ rc = gxio_mpipe_register_client_memory(&context, small_buffer_stack,
+ hash_pte, 0);
+ if (rc != 0) {
+ netdev_err(dev,
+ "gxio_mpipe_register_buffer_memory failed: %d\n",
+ rc);
+ return rc;
+ }
+
+ /* Allocate the large buffer stack. */
+ large_buffer_stack_va =
+ alloc_pages_exact(buffer_stack_size, GFP_KERNEL);
+ if (large_buffer_stack_va == NULL) {
+ netdev_err(dev,
+ "Could not alloc %zd bytes for buffer stacks\n",
+ buffer_stack_size);
+ return -ENOMEM;
+ }
+ rc = gxio_mpipe_init_buffer_stack(&context, large_buffer_stack,
+ BUFFER_SIZE_LARGE_ENUM,
+ large_buffer_stack_va,
+ buffer_stack_size, 0);
+ if (rc != 0) {
+ netdev_err(dev, "gxio_mpipe_init_buffer_stack failed: %d\n",
+ rc);
+ return rc;
+ }
+ rc = gxio_mpipe_register_client_memory(&context, large_buffer_stack,
+ hash_pte, 0);
+ if (rc != 0) {
+ netdev_err(dev,
+ "gxio_mpipe_register_buffer_memory failed: %d\n",
+ rc);
+ return rc;
+ }
+
+ return 0;
+}
+
+/* Allocate per-cpu resources (memory for completions and idescs).
+ * This routine supports tile_net_init_mpipe(), below.
+ */
+static int alloc_percpu_mpipe_resources(struct net_device *dev,
+ int cpu, int ring)
+{
+ struct tile_net_info *info = &per_cpu(per_cpu_info, cpu);
+ int order, i, rc;
+ struct page *page;
+ void *addr;
+
+ /* Allocate the "comps". */
+ order = get_order(COMPS_SIZE);
+ page = homecache_alloc_pages(GFP_KERNEL, order, cpu);
+ if (page == NULL) {
+ netdev_err(dev, "Failed to alloc %zd bytes comps memory\n",
+ COMPS_SIZE);
+ return -ENOMEM;
+ }
+ addr = pfn_to_kaddr(page_to_pfn(page));
+ memset(addr, 0, COMPS_SIZE);
+ for (i = 0; i < TILE_NET_CHANNELS; i++)
+ info->comps_for_echannel[i] =
+ addr + i * sizeof(struct tile_net_comps);
+
+ /* If this is a network cpu, create an iqueue. */
+ if (cpu_isset(cpu, network_cpus_map)) {
+ order = get_order(NOTIF_RING_SIZE);
+ page = homecache_alloc_pages(GFP_KERNEL, order, cpu);
+ if (page == NULL) {
+ netdev_err(dev,
+ "Failed to alloc %zd bytes iqueue memory\n",
+ NOTIF_RING_SIZE);
+ return -ENOMEM;
+ }
+ addr = pfn_to_kaddr(page_to_pfn(page));
+ rc = gxio_mpipe_iqueue_init(&info->iqueue, &context, ring++,
+ addr, NOTIF_RING_SIZE, 0);
+ if (rc < 0) {
+ netdev_err(dev,
+ "gxio_mpipe_iqueue_init failed: %d\n", rc);
+ return rc;
+ }
+ info->has_iqueue = true;
+ }
+
+ return ring;
+}
+
+/* Initialize NotifGroup and buckets.
+ * This routine supports tile_net_init_mpipe(), below.
+ */
+static int init_notif_group_and_buckets(struct net_device *dev,
+ int ring, int network_cpus_count)
+{
+ int group, rc;
+
+ /* Allocate one NotifGroup. */
+ rc = gxio_mpipe_alloc_notif_groups(&context, 1, 0, 0);
+ if (rc < 0) {
+ netdev_err(dev, "gxio_mpipe_alloc_notif_groups failed: %d\n",
+ rc);
+ return rc;
+ }
+ group = rc;
+
+ /* Initialize global num_buckets value. */
+ if (network_cpus_count > 4)
+ num_buckets = 256;
+ else if (network_cpus_count > 1)
+ num_buckets = 16;
+
+ /* Allocate some buckets, and set global first_bucket value. */
+ rc = gxio_mpipe_alloc_buckets(&context, num_buckets, 0, 0);
+ if (rc < 0) {
+ netdev_err(dev, "gxio_mpipe_alloc_buckets failed: %d\n", rc);
+ return rc;
+ }
+ first_bucket = rc;
+
+ /* Init group and buckets. */
+ rc = gxio_mpipe_init_notif_group_and_buckets(
+ &context, group, ring, network_cpus_count,
+ first_bucket, num_buckets,
+ GXIO_MPIPE_BUCKET_STICKY_FLOW_LOCALITY);
+ if (rc != 0) {
+ netdev_err(
+ dev,
+ "gxio_mpipe_init_notif_group_and_buckets failed: %d\n",
+ rc);
+ return rc;
+ }
+
+ return 0;
+}
+
+/* Create an irq and register it, then activate the irq and request
+ * interrupts on all cores. Note that "ingress_irq" being initialized
+ * is how we know not to call tile_net_init_mpipe() again.
+ * This routine supports tile_net_init_mpipe(), below.
+ */
+static int tile_net_setup_interrupts(struct net_device *dev)
+{
+ int cpu, rc;
+
+ rc = create_irq();
+ if (rc < 0) {
+ netdev_err(dev, "create_irq failed: %d\n", rc);
+ return rc;
+ }
+ ingress_irq = rc;
+ tile_irq_activate(ingress_irq, TILE_IRQ_PERCPU);
+ rc = request_irq(ingress_irq, tile_net_handle_ingress_irq,
+ 0, NULL, NULL);
+ if (rc != 0) {
+ netdev_err(dev, "request_irq failed: %d\n", rc);
+ destroy_irq(ingress_irq);
+ ingress_irq = -1;
+ return rc;
+ }
+
+ for_each_online_cpu(cpu) {
+ struct tile_net_info *info = &per_cpu(per_cpu_info, cpu);
+ if (info->has_iqueue) {
+ gxio_mpipe_request_notif_ring_interrupt(
+ &context, cpu_x(cpu), cpu_y(cpu),
+ 1, ingress_irq, info->iqueue.ring);
+ }
+ }
+
+ return 0;
+}
+
+/* Undo any state set up partially by a failed call to tile_net_init_mpipe. */
+static void tile_net_init_mpipe_fail(void)
+{
+ int cpu;
+
+ /* Do cleanups that require the mpipe context first. */
+ if (small_buffer_stack >= 0)
+ tile_net_pop_all_buffers(small_buffer_stack);
+ if (large_buffer_stack >= 0)
+ tile_net_pop_all_buffers(large_buffer_stack);
+
+ /* Destroy mpipe context so the hardware no longer owns any memory. */
+ gxio_mpipe_destroy(&context);
+
+ for_each_online_cpu(cpu) {
+ struct tile_net_info *info = &per_cpu(per_cpu_info, cpu);
+ free_pages((unsigned long)(info->comps_for_echannel[0]),
+ get_order(COMPS_SIZE));
+ info->comps_for_echannel[0] = NULL;
+ free_pages((unsigned long)(info->iqueue.idescs),
+ get_order(NOTIF_RING_SIZE));
+ info->iqueue.idescs = NULL;
+ }
+
+ if (small_buffer_stack_va)
+ free_pages_exact(small_buffer_stack_va, buffer_stack_size);
+ if (large_buffer_stack_va)
+ free_pages_exact(large_buffer_stack_va, buffer_stack_size);
+
+ small_buffer_stack_va = NULL;
+ large_buffer_stack_va = NULL;
+ large_buffer_stack = -1;
+ small_buffer_stack = -1;
+ first_bucket = -1;
+}
+
+/* The first time any tilegx network device is opened, we initialize
+ * the global mpipe state. If this step fails, we fail to open the
+ * device, but if it succeeds, we never need to do it again, and since
+ * tile_net can't be unloaded, we never undo it.
+ *
+ * Note that some resources in this path (buffer stack indices,
+ * bindings from init_buffer_stack, etc.) are hypervisor resources
+ * that are freed implicitly by gxio_mpipe_destroy().
+ */
+static int tile_net_init_mpipe(struct net_device *dev)
+{
+ int i, num_buffers, rc;
+ int cpu;
+ int first_ring, ring;
+ int network_cpus_count = cpus_weight(network_cpus_map);
+
+ if (!hash_default) {
+ netdev_err(dev, "Networking requires hash_default!\n");
+ return -EIO;
+ }
+
+ rc = gxio_mpipe_init(&context, 0);
+ if (rc != 0) {
+ netdev_err(dev, "gxio_mpipe_init failed: %d\n", rc);
+ return -EIO;
+ }
+
+ /* Set up the buffer stacks. */
+ num_buffers =
+ network_cpus_count * (IQUEUE_ENTRIES + TILE_NET_BATCH);
+ rc = init_buffer_stacks(dev, num_buffers);
+ if (rc != 0)
+ goto fail;
+
+ /* Provide initial buffers. */
+ rc = -ENOMEM;
+ for (i = 0; i < num_buffers; i++) {
+ if (!tile_net_provide_buffer(true)) {
+ netdev_err(dev, "Cannot allocate initial sk_bufs!\n");
+ goto fail;
+ }
+ }
+ for (i = 0; i < num_buffers; i++) {
+ if (!tile_net_provide_buffer(false)) {
+ netdev_err(dev, "Cannot allocate initial sk_bufs!\n");
+ goto fail;
+ }
+ }
+
+ /* Allocate one NotifRing for each network cpu. */
+ rc = gxio_mpipe_alloc_notif_rings(&context, network_cpus_count, 0, 0);
+ if (rc < 0) {
+ netdev_err(dev, "gxio_mpipe_alloc_notif_rings failed %d\n",
+ rc);
+ goto fail;
+ }
+
+ /* Init NotifRings per-cpu. */
+ first_ring = rc;
+ ring = first_ring;
+ for_each_online_cpu(cpu) {
+ rc = alloc_percpu_mpipe_resources(dev, cpu, ring);
+ if (rc < 0)
+ goto fail;
+ ring = rc;
+ }
+
+ /* Initialize NotifGroup and buckets. */
+ rc = init_notif_group_and_buckets(dev, first_ring, network_cpus_count);
+ if (rc != 0)
+ goto fail;
+
+ /* Create and enable interrupts. */
+ rc = tile_net_setup_interrupts(dev);
+ if (rc != 0)
+ goto fail;
+
+ return 0;
+
+fail:
+ tile_net_init_mpipe_fail();
+ return rc;
+}
+
+/* Create persistent egress info for a given egress channel.
+ * Note that this may be shared between, say, "gbe0" and "xgbe0".
+ * ISSUE: Defer header allocation until TSO is actually needed?
+ */
+static int tile_net_init_egress(struct net_device *dev, int echannel)
+{
+ struct page *headers_page, *edescs_page, *equeue_page;
+ gxio_mpipe_edesc_t *edescs;
+ gxio_mpipe_equeue_t *equeue;
+ unsigned char *headers;
+ int headers_order, edescs_order, equeue_order;
+ size_t edescs_size;
+ int edma;
+ int rc = -ENOMEM;
+
+ /* Only initialize once. */
+ if (egress_for_echannel[echannel].equeue != NULL)
+ return 0;
+
+ /* Allocate memory for the "headers". */
+ headers_order = get_order(EQUEUE_ENTRIES * HEADER_BYTES);
+ headers_page = alloc_pages(GFP_KERNEL, headers_order);
+ if (headers_page == NULL) {
+ netdev_warn(dev,
+ "Could not alloc %zd bytes for TSO headers.\n",
+ PAGE_SIZE << headers_order);
+ goto fail;
+ }
+ headers = pfn_to_kaddr(page_to_pfn(headers_page));
+
+ /* Allocate memory for the "edescs". */
+ edescs_size = EQUEUE_ENTRIES * sizeof(*edescs);
+ edescs_order = get_order(edescs_size);
+ edescs_page = alloc_pages(GFP_KERNEL, edescs_order);
+ if (edescs_page == NULL) {
+ netdev_warn(dev,
+ "Could not alloc %zd bytes for eDMA ring.\n",
+ edescs_size);
+ goto fail_headers;
+ }
+ edescs = pfn_to_kaddr(page_to_pfn(edescs_page));
+
+ /* Allocate memory for the "equeue". */
+ equeue_order = get_order(sizeof(*equeue));
+ equeue_page = alloc_pages(GFP_KERNEL, equeue_order);
+ if (equeue_page == NULL) {
+ netdev_warn(dev,
+ "Could not alloc %zd bytes for equeue info.\n",
+ PAGE_SIZE << equeue_order);
+ goto fail_edescs;
+ }
+ equeue = pfn_to_kaddr(page_to_pfn(equeue_page));
+
+ /* Allocate an edma ring. Note that in practice this can't
+ * fail, which is good, because we will leak an edma ring if so.
+ */
+ rc = gxio_mpipe_alloc_edma_rings(&context, 1, 0, 0);
+ if (rc < 0) {
+ netdev_warn(dev, "gxio_mpipe_alloc_edma_rings failed: %d\n",
+ rc);
+ goto fail_equeue;
+ }
+ edma = rc;
+
+ /* Initialize the equeue. */
+ rc = gxio_mpipe_equeue_init(equeue, &context, edma, echannel,
+ edescs, edescs_size, 0);
+ if (rc != 0) {
+ netdev_err(dev, "gxio_mpipe_equeue_init failed: %d\n", rc);
+ goto fail_equeue;
+ }
+
+ /* Done. */
+ egress_for_echannel[echannel].equeue = equeue;
+ egress_for_echannel[echannel].headers = headers;
+ return 0;
+
+fail_equeue:
+ __free_pages(equeue_page, equeue_order);
+
+fail_edescs:
+ __free_pages(edescs_page, edescs_order);
+
+fail_headers:
+ __free_pages(headers_page, headers_order);
+
+fail:
+ return rc;
+}
+
+/* Return channel number for a newly-opened link. */
+static int tile_net_link_open(struct net_device *dev, gxio_mpipe_link_t *link,
+ const char *link_name)
+{
+ int rc = gxio_mpipe_link_open(link, &context, link_name, 0);
+ if (rc < 0) {
+ netdev_err(dev, "Failed to open '%s'\n", link_name);
+ return rc;
+ }
+ rc = gxio_mpipe_link_channel(link);
+ if (rc < 0 || rc >= TILE_NET_CHANNELS) {
+ netdev_err(dev, "gxio_mpipe_link_channel bad value: %d\n", rc);
+ gxio_mpipe_link_close(link);
+ return -EINVAL;
+ }
+ return rc;
+}
+
+/* Help the kernel activate the given network interface. */
+static int tile_net_open(struct net_device *dev)
+{
+ struct tile_net_priv *priv = netdev_priv(dev);
+ int cpu, rc;
+
+ mutex_lock(&tile_net_devs_for_channel_mutex);
+
+ /* Do one-time initialization the first time any device is opened. */
+ if (ingress_irq < 0) {
+ rc = tile_net_init_mpipe(dev);
+ if (rc != 0)
+ goto fail;
+ }
+
+ /* Determine if this is the "loopify" device. */
+ if (unlikely((loopify_link_name != NULL) &&
+ !strcmp(dev->name, loopify_link_name))) {
+ rc = tile_net_link_open(dev, &priv->link, "loop0");
+ if (rc < 0)
+ goto fail;
+ priv->channel = rc;
+ rc = tile_net_link_open(dev, &priv->loopify_link, "loop1");
+ if (rc < 0)
+ goto fail;
+ priv->loopify_channel = rc;
+ priv->echannel = rc;
+ } else {
+ rc = tile_net_link_open(dev, &priv->link, dev->name);
+ if (rc < 0)
+ goto fail;
+ priv->channel = rc;
+ priv->echannel = rc;
+ }
+
+ /* Initialize egress info (if needed). Once ever, per echannel. */
+ rc = tile_net_init_egress(dev, priv->echannel);
+ if (rc != 0)
+ goto fail;
+
+ tile_net_devs_for_channel[priv->channel] = dev;
+
+ rc = tile_net_update(dev);
+ if (rc != 0)
+ goto fail;
+
+ mutex_unlock(&tile_net_devs_for_channel_mutex);
+
+ /* Initialize the transmit wake timer for this device for each cpu. */
+ for_each_online_cpu(cpu) {
+ struct tile_net_info *info = &per_cpu(per_cpu_info, cpu);
+ struct tile_net_tx_wake *tx_wake =
+ &info->tx_wake[priv->echannel];
+
+ hrtimer_init(&tx_wake->timer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_REL);
+ tx_wake->timer.function = tile_net_handle_tx_wake_timer;
+ tx_wake->dev = dev;
+ }
+
+ for_each_online_cpu(cpu)
+ netif_start_subqueue(dev, cpu);
+ netif_carrier_on(dev);
+ return 0;
+
+fail:
+ if (priv->loopify_channel >= 0) {
+ if (gxio_mpipe_link_close(&priv->loopify_link) != 0)
+ netdev_warn(dev, "Failed to close loopify link!\n");
+ priv->loopify_channel = -1;
+ }
+ if (priv->channel >= 0) {
+ if (gxio_mpipe_link_close(&priv->link) != 0)
+ netdev_warn(dev, "Failed to close link!\n");
+ priv->channel = -1;
+ }
+ priv->echannel = -1;
+ tile_net_devs_for_channel[priv->channel] = NULL;
+ mutex_unlock(&tile_net_devs_for_channel_mutex);
+
+ /* Don't return raw gxio error codes to generic Linux. */
+ return (rc > -512) ? rc : -EIO;
+}
+
+/* Help the kernel deactivate the given network interface. */
+static int tile_net_stop(struct net_device *dev)
+{
+ struct tile_net_priv *priv = netdev_priv(dev);
+ int cpu;
+
+ for_each_online_cpu(cpu) {
+ struct tile_net_info *info = &per_cpu(per_cpu_info, cpu);
+ struct tile_net_tx_wake *tx_wake =
+ &info->tx_wake[priv->echannel];
+
+ hrtimer_cancel(&tx_wake->timer);
+ netif_stop_subqueue(dev, cpu);
+ }
+
+ mutex_lock(&tile_net_devs_for_channel_mutex);
+ tile_net_devs_for_channel[priv->channel] = NULL;
+ (void)tile_net_update(dev);
+ if (priv->loopify_channel >= 0) {
+ if (gxio_mpipe_link_close(&priv->loopify_link) != 0)
+ netdev_warn(dev, "Failed to close loopify link!\n");
+ priv->loopify_channel = -1;
+ }
+ if (priv->channel >= 0) {
+ if (gxio_mpipe_link_close(&priv->link) != 0)
+ netdev_warn(dev, "Failed to close link!\n");
+ priv->channel = -1;
+ }
+ priv->echannel = -1;
+ mutex_unlock(&tile_net_devs_for_channel_mutex);
+
+ return 0;
+}
+
+/* Determine the VA for a fragment. */
+static inline void *tile_net_frag_buf(skb_frag_t *f)
+{
+ unsigned long pfn = page_to_pfn(skb_frag_page(f));
+ return pfn_to_kaddr(pfn) + f->page_offset;
+}
+
+/* Acquire a completion entry and an egress slot, or if we can't,
+ * stop the queue and schedule the tx_wake timer.
+ */
+static s64 tile_net_equeue_try_reserve(struct net_device *dev,
+ struct tile_net_comps *comps,
+ gxio_mpipe_equeue_t *equeue,
+ int num_edescs)
+{
+ /* Try to acquire a completion entry. */
+ if (comps->comp_next - comps->comp_last < TILE_NET_MAX_COMPS - 1 ||
+ tile_net_free_comps(equeue, comps, 32, false) != 0) {
+
+ /* Try to acquire an egress slot. */
+ s64 slot = gxio_mpipe_equeue_try_reserve(equeue, num_edescs);
+ if (slot >= 0)
+ return slot;
+
+ /* Freeing some completions gives the equeue time to drain. */
+ tile_net_free_comps(equeue, comps, TILE_NET_MAX_COMPS, false);
+
+ slot = gxio_mpipe_equeue_try_reserve(equeue, num_edescs);
+ if (slot >= 0)
+ return slot;
+ }
+
+ /* Still nothing; give up and stop the queue for a short while. */
+ netif_stop_subqueue(dev, smp_processor_id());
+ tile_net_schedule_tx_wake_timer(dev);
+ return -1;
+}
+
+/* Determine how many edesc's are needed for TSO.
+ *
+ * Sometimes, if "sendfile()" requires copying, we will be called with
+ * "data" containing the header and payload, with "frags" being empty.
+ * Sometimes, for example when using NFS over TCP, a single segment can
+ * span 3 fragments. This requires special care.
+ */
+static int tso_count_edescs(struct sk_buff *skb)
+{
+ struct skb_shared_info *sh = skb_shinfo(skb);
+ unsigned int data_len = skb->data_len;
+ unsigned int p_len = sh->gso_size;
+ long f_id = -1; /* id of the current fragment */
+ long f_size = -1; /* size of the current fragment */
+ long f_used = -1; /* bytes used from the current fragment */
+ long n; /* size of the current piece of payload */
+ int num_edescs = 0;
+ int segment;
+
+ for (segment = 0; segment < sh->gso_segs; segment++) {
+
+ unsigned int p_used = 0;
+
+ /* One edesc for header and for each piece of the payload. */
+ for (num_edescs++; p_used < p_len; num_edescs++) {
+
+ /* Advance as needed. */
+ while (f_used >= f_size) {
+ f_id++;
+ f_size = sh->frags[f_id].size;
+ f_used = 0;
+ }
+
+ /* Use bytes from the current fragment. */
+ n = p_len - p_used;
+ if (n > f_size - f_used)
+ n = f_size - f_used;
+ f_used += n;
+ p_used += n;
+ }
+
+ /* The last segment may be less than gso_size. */
+ data_len -= p_len;
+ if (data_len < p_len)
+ p_len = data_len;
+ }
+
+ return num_edescs;
+}
+
+/* Prepare modified copies of the skbuff headers.
+ * FIXME: add support for IPv6.
+ */
+static void tso_headers_prepare(struct sk_buff *skb, unsigned char *headers,
+ s64 slot)
+{
+ struct skb_shared_info *sh = skb_shinfo(skb);
+ struct iphdr *ih;
+ struct tcphdr *th;
+ unsigned int data_len = skb->data_len;
+ unsigned char *data = skb->data;
+ unsigned int ih_off, th_off, sh_len, p_len;
+ unsigned int isum_seed, tsum_seed, id, seq;
+ long f_id = -1; /* id of the current fragment */
+ long f_size = -1; /* size of the current fragment */
+ long f_used = -1; /* bytes used from the current fragment */
+ long n; /* size of the current piece of payload */
+ int segment;
+
+ /* Locate original headers and compute various lengths. */
+ ih = ip_hdr(skb);
+ th = tcp_hdr(skb);
+ ih_off = skb_network_offset(skb);
+ th_off = skb_transport_offset(skb);
+ sh_len = th_off + tcp_hdrlen(skb);
+ p_len = sh->gso_size;
+
+ /* Set up seed values for IP and TCP csum and initialize id and seq. */
+ isum_seed = ((0xFFFF - ih->check) +
+ (0xFFFF - ih->tot_len) +
+ (0xFFFF - ih->id));
+ tsum_seed = th->check + (0xFFFF ^ htons(skb->len));
+ id = ntohs(ih->id);
+ seq = ntohl(th->seq);
+
+ /* Prepare all the headers. */
+ for (segment = 0; segment < sh->gso_segs; segment++) {
+ unsigned char *buf;
+ unsigned int p_used = 0;
+
+ /* Copy to the header memory for this segment. */
+ buf = headers + (slot % EQUEUE_ENTRIES) * HEADER_BYTES +
+ NET_IP_ALIGN;
+ memcpy(buf, data, sh_len);
+
+ /* Update copied ip header. */
+ ih = (struct iphdr *)(buf + ih_off);
+ ih->tot_len = htons(sh_len + p_len - ih_off);
+ ih->id = htons(id);
+ ih->check = csum_long(isum_seed + ih->tot_len +
+ ih->id) ^ 0xffff;
+
+ /* Update copied tcp header. */
+ th = (struct tcphdr *)(buf + th_off);
+ th->seq = htonl(seq);
+ th->check = csum_long(tsum_seed + htons(sh_len + p_len));
+ if (segment != sh->gso_segs - 1) {
+ th->fin = 0;
+ th->psh = 0;
+ }
+
+ /* Skip past the header. */
+ slot++;
+
+ /* Skip past the payload. */
+ while (p_used < p_len) {
+
+ /* Advance as needed. */
+ while (f_used >= f_size) {
+ f_id++;
+ f_size = sh->frags[f_id].size;
+ f_used = 0;
+ }
+
+ /* Use bytes from the current fragment. */
+ n = p_len - p_used;
+ if (n > f_size - f_used)
+ n = f_size - f_used;
+ f_used += n;
+ p_used += n;
+
+ slot++;
+ }
+
+ id++;
+ seq += p_len;
+
+ /* The last segment may be less than gso_size. */
+ data_len -= p_len;
+ if (data_len < p_len)
+ p_len = data_len;
+ }
+
+ /* Flush the headers so they are ready for hardware DMA. */
+ wmb();
+}
+
+/* Pass all the data to mpipe for egress. */
+static void tso_egress(struct net_device *dev, gxio_mpipe_equeue_t *equeue,
+ struct sk_buff *skb, unsigned char *headers, s64 slot)
+{
+ struct tile_net_priv *priv = netdev_priv(dev);
+ struct skb_shared_info *sh = skb_shinfo(skb);
+ unsigned int data_len = skb->data_len;
+ unsigned int p_len = sh->gso_size;
+ gxio_mpipe_edesc_t edesc_head = { { 0 } };
+ gxio_mpipe_edesc_t edesc_body = { { 0 } };
+ long f_id = -1; /* id of the current fragment */
+ long f_size = -1; /* size of the current fragment */
+ long f_used = -1; /* bytes used from the current fragment */
+ long n; /* size of the current piece of payload */
+ unsigned long tx_packets = 0, tx_bytes = 0;
+ unsigned int csum_start, sh_len;
+ int segment;
+
+ /* Prepare to egress the headers: set up header edesc. */
+ csum_start = skb_checksum_start_offset(skb);
+ sh_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+ edesc_head.csum = 1;
+ edesc_head.csum_start = csum_start;
+ edesc_head.csum_dest = csum_start + skb->csum_offset;
+ edesc_head.xfer_size = sh_len;
+
+ /* This is only used to specify the TLB. */
+ edesc_head.stack_idx = large_buffer_stack;
+ edesc_body.stack_idx = large_buffer_stack;
+
+ /* Egress all the edescs. */
+ for (segment = 0; segment < sh->gso_segs; segment++) {
+ void *va;
+ unsigned char *buf;
+ unsigned int p_used = 0;
+
+ /* Egress the header. */
+ buf = headers + (slot % EQUEUE_ENTRIES) * HEADER_BYTES +
+ NET_IP_ALIGN;
+ edesc_head.va = va_to_tile_io_addr(buf);
+ gxio_mpipe_equeue_put_at(equeue, edesc_head, slot);
+ slot++;
+
+ /* Egress the payload. */
+ while (p_used < p_len) {
+
+ /* Advance as needed. */
+ while (f_used >= f_size) {
+ f_id++;
+ f_size = sh->frags[f_id].size;
+ f_used = 0;
+ }
+
+ va = tile_net_frag_buf(&sh->frags[f_id]) + f_used;
+
+ /* Use bytes from the current fragment. */
+ n = p_len - p_used;
+ if (n > f_size - f_used)
+ n = f_size - f_used;
+ f_used += n;
+ p_used += n;
+
+ /* Egress a piece of the payload. */
+ edesc_body.va = va_to_tile_io_addr(va);
+ edesc_body.xfer_size = n;
+ edesc_body.bound = !(p_used < p_len);
+ gxio_mpipe_equeue_put_at(equeue, edesc_body, slot);
+ slot++;
+ }
+
+ tx_packets++;
+ tx_bytes += sh_len + p_len;
+
+ /* The last segment may be less than gso_size. */
+ data_len -= p_len;
+ if (data_len < p_len)
+ p_len = data_len;
+ }
+
+ /* Update stats. */
+ tile_net_stats_add(tx_packets, &priv->stats.tx_packets);
+ tile_net_stats_add(tx_bytes, &priv->stats.tx_bytes);
+}
+
+/* Do "TSO" handling for egress.
+ *
+ * Normally drivers set NETIF_F_TSO only to support hardware TSO;
+ * otherwise the stack uses scatter-gather to implement GSO in software.
+ * On our testing, enabling GSO support (via NETIF_F_SG) drops network
+ * performance down to around 7.5 Gbps on the 10G interfaces, although
+ * also dropping cpu utilization way down, to under 8%. But
+ * implementing "TSO" in the driver brings performance back up to line
+ * rate, while dropping cpu usage even further, to less than 4%. In
+ * practice, profiling of GSO shows that skb_segment() is what causes
+ * the performance overheads; we benefit in the driver from using
+ * preallocated memory to duplicate the TCP/IP headers.
+ */
+static int tile_net_tx_tso(struct sk_buff *skb, struct net_device *dev)
+{
+ struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+ struct tile_net_priv *priv = netdev_priv(dev);
+ int channel = priv->echannel;
+ struct tile_net_egress *egress = &egress_for_echannel[channel];
+ struct tile_net_comps *comps = info->comps_for_echannel[channel];
+ gxio_mpipe_equeue_t *equeue = egress->equeue;
+ unsigned long irqflags;
+ int num_edescs;
+ s64 slot;
+
+ /* Determine how many mpipe edesc's are needed. */
+ num_edescs = tso_count_edescs(skb);
+
+ local_irq_save(irqflags);
+
+ /* Try to acquire a completion entry and an egress slot. */
+ slot = tile_net_equeue_try_reserve(dev, comps, equeue, num_edescs);
+ if (slot < 0) {
+ local_irq_restore(irqflags);
+ return NETDEV_TX_BUSY;
+ }
+
+ /* Set up copies of header data properly. */
+ tso_headers_prepare(skb, egress->headers, slot);
+
+ /* Actually pass the data to the network hardware. */
+ tso_egress(dev, equeue, skb, egress->headers, slot);
+
+ /* Add a completion record. */
+ add_comp(equeue, comps, slot + num_edescs - 1, skb);
+
+ local_irq_restore(irqflags);
+
+ /* Make sure the egress timer is scheduled. */
+ tile_net_schedule_egress_timer();
+
+ return NETDEV_TX_OK;
+}
+
+/* Analyze the body and frags for a transmit request. */
+static unsigned int tile_net_tx_frags(struct frag *frags,
+ struct sk_buff *skb,
+ void *b_data, unsigned int b_len)
+{
+ unsigned int i, n = 0;
+
+ struct skb_shared_info *sh = skb_shinfo(skb);
+
+ if (b_len != 0) {
+ frags[n].buf = b_data;
+ frags[n++].length = b_len;
+ }
+
+ for (i = 0; i < sh->nr_frags; i++) {
+ skb_frag_t *f = &sh->frags[i];
+ frags[n].buf = tile_net_frag_buf(f);
+ frags[n++].length = skb_frag_size(f);
+ }
+
+ return n;
+}
+
+/* Help the kernel transmit a packet. */
+static int tile_net_tx(struct sk_buff *skb, struct net_device *dev)
+{
+ struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+ struct tile_net_priv *priv = netdev_priv(dev);
+ struct tile_net_egress *egress = &egress_for_echannel[priv->echannel];
+ gxio_mpipe_equeue_t *equeue = egress->equeue;
+ struct tile_net_comps *comps =
+ info->comps_for_echannel[priv->echannel];
+ unsigned int len = skb->len;
+ unsigned char *data = skb->data;
+ unsigned int num_edescs;
+ struct frag frags[MAX_FRAGS];
+ gxio_mpipe_edesc_t edescs[MAX_FRAGS];
+ unsigned long irqflags;
+ gxio_mpipe_edesc_t edesc = { { 0 } };
+ unsigned int i;
+ s64 slot;
+
+ if (skb_is_gso(skb))
+ return tile_net_tx_tso(skb, dev);
+
+ num_edescs = tile_net_tx_frags(frags, skb, data, skb_headlen(skb));
+
+ /* This is only used to specify the TLB. */
+ edesc.stack_idx = large_buffer_stack;
+
+ /* Prepare the edescs. */
+ for (i = 0; i < num_edescs; i++) {
+ edesc.xfer_size = frags[i].length;
+ edesc.va = va_to_tile_io_addr(frags[i].buf);
+ edescs[i] = edesc;
+ }
+
+ /* Mark the final edesc. */
+ edescs[num_edescs - 1].bound = 1;
+
+ /* Add checksum info to the initial edesc, if needed. */
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ unsigned int csum_start = skb_checksum_start_offset(skb);
+ edescs[0].csum = 1;
+ edescs[0].csum_start = csum_start;
+ edescs[0].csum_dest = csum_start + skb->csum_offset;
+ }
+
+ local_irq_save(irqflags);
+
+ /* Try to acquire a completion entry and an egress slot. */
+ slot = tile_net_equeue_try_reserve(dev, comps, equeue, num_edescs);
+ if (slot < 0) {
+ local_irq_restore(irqflags);
+ return NETDEV_TX_BUSY;
+ }
+
+ for (i = 0; i < num_edescs; i++)
+ gxio_mpipe_equeue_put_at(equeue, edescs[i], slot++);
+
+ /* Add a completion record. */
+ add_comp(equeue, comps, slot - 1, skb);
+
+ /* NOTE: Use ETH_ZLEN for short packets (e.g. 42 < 60). */
+ tile_net_stats_add(1, &priv->stats.tx_packets);
+ tile_net_stats_add(max_t(unsigned int, len, ETH_ZLEN),
+ &priv->stats.tx_bytes);
+
+ local_irq_restore(irqflags);
+
+ /* Make sure the egress timer is scheduled. */
+ tile_net_schedule_egress_timer();
+
+ return NETDEV_TX_OK;
+}
+
+/* Return subqueue id on this core (one per core). */
+static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb)
+{
+ return smp_processor_id();
+}
+
+/* Deal with a transmit timeout. */
+static void tile_net_tx_timeout(struct net_device *dev)
+{
+ int cpu;
+
+ for_each_online_cpu(cpu)
+ netif_wake_subqueue(dev, cpu);
+}
+
+/* Ioctl commands. */
+static int tile_net_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+ return -EOPNOTSUPP;
+}
+
+/* Get system network statistics for device. */
+static struct net_device_stats *tile_net_get_stats(struct net_device *dev)
+{
+ struct tile_net_priv *priv = netdev_priv(dev);
+ return &priv->stats;
+}
+
+/* Change the MTU. */
+static int tile_net_change_mtu(struct net_device *dev, int new_mtu)
+{
+ if ((new_mtu < 68) || (new_mtu > 1500))
+ return -EINVAL;
+ dev->mtu = new_mtu;
+ return 0;
+}
+
+/* Change the Ethernet address of the NIC.
+ *
+ * The hypervisor driver does not support changing MAC address. However,
+ * the hardware does not do anything with the MAC address, so the address
+ * which gets used on outgoing packets, and which is accepted on incoming
+ * packets, is completely up to us.
+ *
+ * Returns 0 on success, negative on failure.
+ */
+static int tile_net_set_mac_address(struct net_device *dev, void *p)
+{
+ struct sockaddr *addr = p;
+
+ if (!is_valid_ether_addr(addr->sa_data))
+ return -EINVAL;
+ memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
+ return 0;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+/* Polling 'interrupt' - used by things like netconsole to send skbs
+ * without having to re-enable interrupts. It's not called while
+ * the interrupt routine is executing.
+ */
+static void tile_net_netpoll(struct net_device *dev)
+{
+ disable_percpu_irq(ingress_irq);
+ tile_net_handle_ingress_irq(ingress_irq, NULL);
+ enable_percpu_irq(ingress_irq, 0);
+}
+#endif
+
+static const struct net_device_ops tile_net_ops = {
+ .ndo_open = tile_net_open,
+ .ndo_stop = tile_net_stop,
+ .ndo_start_xmit = tile_net_tx,
+ .ndo_select_queue = tile_net_select_queue,
+ .ndo_do_ioctl = tile_net_ioctl,
+ .ndo_get_stats = tile_net_get_stats,
+ .ndo_change_mtu = tile_net_change_mtu,
+ .ndo_tx_timeout = tile_net_tx_timeout,
+ .ndo_set_mac_address = tile_net_set_mac_address,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_poll_controller = tile_net_netpoll,
+#endif
+};
+
+/* The setup function.
+ *
+ * This uses ether_setup() to assign various fields in dev, including
+ * setting IFF_BROADCAST and IFF_MULTICAST, then sets some extra fields.
+ */
+static void tile_net_setup(struct net_device *dev)
+{
+ ether_setup(dev);
+ dev->netdev_ops = &tile_net_ops;
+ dev->watchdog_timeo = TILE_NET_TIMEOUT;
+ dev->features |= NETIF_F_LLTX;
+ dev->features |= NETIF_F_HW_CSUM;
+ dev->features |= NETIF_F_SG;
+ dev->features |= NETIF_F_TSO;
+ dev->mtu = 1500;
+}
+
+/* Allocate the device structure, register the device, and obtain the
+ * MAC address from the hypervisor.
+ */
+static void tile_net_dev_init(const char *name, const uint8_t *mac)
+{
+ int ret;
+ int i;
+ int nz_addr = 0;
+ struct net_device *dev;
+ struct tile_net_priv *priv;
+
+ /* HACK: Ignore "loop" links. */
+ if (strncmp(name, "loop", 4) == 0)
+ return;
+
+ /* Allocate the device structure. Normally, "name" is a
+ * template, instantiated by register_netdev(), but not for us.
+ */
+ dev = alloc_netdev_mqs(sizeof(*priv), name, tile_net_setup,
+ NR_CPUS, 1);
+ if (!dev) {
+ pr_err("alloc_netdev_mqs(%s) failed\n", name);
+ return;
+ }
+
+ /* Initialize "priv". */
+ priv = netdev_priv(dev);
+ memset(priv, 0, sizeof(*priv));
+ priv->dev = dev;
+ priv->channel = -1;
+ priv->loopify_channel = -1;
+ priv->echannel = -1;
+
+ /* Get the MAC address and set it in the device struct; this must
+ * be done before the device is opened. If the MAC is all zeroes,
+ * we use a random address, since we're probably on the simulator.
+ */
+ for (i = 0; i < 6; i++)
+ nz_addr |= mac[i];
+
+ if (nz_addr) {
+ memcpy(dev->dev_addr, mac, 6);
+ dev->addr_len = 6;
+ } else {
+ random_ether_addr(dev->dev_addr);
+ }
+
+ /* Register the network device. */
+ ret = register_netdev(dev);
+ if (ret) {
+ netdev_err(dev, "register_netdev failed %d\n", ret);
+ free_netdev(dev);
+ return;
+ }
+}
+
+/* Per-cpu module initialization. */
+static void tile_net_init_module_percpu(void *unused)
+{
+ struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+ int my_cpu = smp_processor_id();
+
+ info->has_iqueue = false;
+
+ info->my_cpu = my_cpu;
+
+ /* Initialize the egress timer. */
+ hrtimer_init(&info->egress_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ info->egress_timer.function = tile_net_handle_egress_timer;
+}
+
+/* Module initialization. */
+static int __init tile_net_init_module(void)
+{
+ int i;
+ char name[GXIO_MPIPE_LINK_NAME_LEN];
+ uint8_t mac[6];
+
+ pr_info("Tilera Network Driver\n");
+
+ mutex_init(&tile_net_devs_for_channel_mutex);
+
+ /* Initialize each CPU. */
+ on_each_cpu(tile_net_init_module_percpu, NULL, 1);
+
+ /* Find out what devices we have, and initialize them. */
+ for (i = 0; gxio_mpipe_link_enumerate_mac(i, name, mac) >= 0; i++)
+ tile_net_dev_init(name, mac);
+
+ if (!network_cpus_init())
+ network_cpus_map = *cpu_online_mask;
+
+ return 0;
+}
+
+module_init(tile_net_init_module);
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index d4a4992..31470b0 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -99,7 +99,7 @@
}
/**
* of_mdio_find_bus - Given an mii_bus node, find the mii_bus.
- * @mdio_np: Pointer to the mii_bus.
+ * @mdio_bus_np: Pointer to the mii_bus.
*
* Returns a pointer to the mii_bus, or NULL if none found.
*
diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c
index d848d4d..187c144 100644
--- a/drivers/net/usb/cdc-phonet.c
+++ b/drivers/net/usb/cdc-phonet.c
@@ -394,7 +394,7 @@
SET_NETDEV_DEV(dev, &intf->dev);
pnd->dev = dev;
- pnd->usb = usb_get_dev(usbdev);
+ pnd->usb = usbdev;
pnd->intf = intf;
pnd->data_intf = data_intf;
spin_lock_init(&pnd->tx_lock);
@@ -440,7 +440,6 @@
static void usbpn_disconnect(struct usb_interface *intf)
{
struct usbpn_dev *pnd = usb_get_intfdata(intf);
- struct usb_device *usb = pnd->usb;
if (pnd->disconnected)
return;
@@ -449,7 +448,6 @@
usb_driver_release_interface(&usbpn_driver,
(pnd->intf == intf) ? pnd->data_intf : pnd->intf);
unregister_netdev(pnd->dev);
- usb_put_dev(usb);
}
static struct usb_driver usbpn_driver = {
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 7023220..a0b5807 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -1329,8 +1329,6 @@
}
pegasus_count++;
- usb_get_dev(dev);
-
net = alloc_etherdev(sizeof(struct pegasus));
if (!net)
goto out;
@@ -1407,7 +1405,6 @@
out1:
free_netdev(net);
out:
- usb_put_dev(dev);
pegasus_dec_workqueue();
return res;
}
@@ -1425,7 +1422,6 @@
pegasus->flags |= PEGASUS_UNPLUG;
cancel_delayed_work(&pegasus->carrier_check);
unregister_netdev(pegasus->net);
- usb_put_dev(interface_to_usbdev(intf));
unlink_all_urbs(pegasus);
free_all_urbs(pegasus);
free_skb_pool(pegasus);
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 9f58330..ac2e493 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -180,7 +180,40 @@
}
EXPORT_SYMBOL_GPL(usbnet_get_ethernet_addr);
-static void intr_complete (struct urb *urb);
+static void intr_complete (struct urb *urb)
+{
+ struct usbnet *dev = urb->context;
+ int status = urb->status;
+
+ switch (status) {
+ /* success */
+ case 0:
+ dev->driver_info->status(dev, urb);
+ break;
+
+ /* software-driven interface shutdown */
+ case -ENOENT: /* urb killed */
+ case -ESHUTDOWN: /* hardware gone */
+ netif_dbg(dev, ifdown, dev->net,
+ "intr shutdown, code %d\n", status);
+ return;
+
+ /* NOTE: not throttling like RX/TX, since this endpoint
+ * already polls infrequently
+ */
+ default:
+ netdev_dbg(dev->net, "intr status %d\n", status);
+ break;
+ }
+
+ if (!netif_running (dev->net))
+ return;
+
+ status = usb_submit_urb (urb, GFP_ATOMIC);
+ if (status != 0)
+ netif_err(dev, timer, dev->net,
+ "intr resubmit --> %d\n", status);
+}
static int init_status (struct usbnet *dev, struct usb_interface *intf)
{
@@ -519,42 +552,6 @@
netif_dbg(dev, rx_err, dev->net, "no read resubmitted\n");
}
-static void intr_complete (struct urb *urb)
-{
- struct usbnet *dev = urb->context;
- int status = urb->status;
-
- switch (status) {
- /* success */
- case 0:
- dev->driver_info->status(dev, urb);
- break;
-
- /* software-driven interface shutdown */
- case -ENOENT: /* urb killed */
- case -ESHUTDOWN: /* hardware gone */
- netif_dbg(dev, ifdown, dev->net,
- "intr shutdown, code %d\n", status);
- return;
-
- /* NOTE: not throttling like RX/TX, since this endpoint
- * already polls infrequently
- */
- default:
- netdev_dbg(dev->net, "intr status %d\n", status);
- break;
- }
-
- if (!netif_running (dev->net))
- return;
-
- memset(urb->transfer_buffer, 0, urb->transfer_buffer_length);
- status = usb_submit_urb (urb, GFP_ATOMIC);
- if (status != 0)
- netif_err(dev, timer, dev->net,
- "intr resubmit --> %d\n", status);
-}
-
/*-------------------------------------------------------------------------*/
void usbnet_pause_rx(struct usbnet *dev)
{
@@ -1307,7 +1304,6 @@
usb_free_urb(dev->interrupt);
free_netdev(net);
- usb_put_dev (xdev);
}
EXPORT_SYMBOL_GPL(usbnet_disconnect);
@@ -1363,8 +1359,6 @@
xdev = interface_to_usbdev (udev);
interface = udev->cur_altsetting;
- usb_get_dev (xdev);
-
status = -ENOMEM;
// set up our own records
@@ -1493,7 +1487,6 @@
out1:
free_netdev(net);
out:
- usb_put_dev(xdev);
return status;
}
EXPORT_SYMBOL_GPL(usbnet_probe);
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 5214b1e..f18149a 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -42,7 +42,8 @@
#define VIRTNET_DRIVER_VERSION "1.0.0"
struct virtnet_stats {
- struct u64_stats_sync syncp;
+ struct u64_stats_sync tx_syncp;
+ struct u64_stats_sync rx_syncp;
u64 tx_bytes;
u64 tx_packets;
@@ -300,10 +301,10 @@
hdr = skb_vnet_hdr(skb);
- u64_stats_update_begin(&stats->syncp);
+ u64_stats_update_begin(&stats->rx_syncp);
stats->rx_bytes += skb->len;
stats->rx_packets++;
- u64_stats_update_end(&stats->syncp);
+ u64_stats_update_end(&stats->rx_syncp);
if (hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
pr_debug("Needs csum!\n");
@@ -565,10 +566,10 @@
while ((skb = virtqueue_get_buf(vi->svq, &len)) != NULL) {
pr_debug("Sent skb %p\n", skb);
- u64_stats_update_begin(&stats->syncp);
+ u64_stats_update_begin(&stats->tx_syncp);
stats->tx_bytes += skb->len;
stats->tx_packets++;
- u64_stats_update_end(&stats->syncp);
+ u64_stats_update_end(&stats->tx_syncp);
tot_sgs += skb_vnet_hdr(skb)->num_sg;
dev_kfree_skb_any(skb);
@@ -703,12 +704,16 @@
u64 tpackets, tbytes, rpackets, rbytes;
do {
- start = u64_stats_fetch_begin(&stats->syncp);
+ start = u64_stats_fetch_begin(&stats->tx_syncp);
tpackets = stats->tx_packets;
tbytes = stats->tx_bytes;
+ } while (u64_stats_fetch_retry(&stats->tx_syncp, start));
+
+ do {
+ start = u64_stats_fetch_begin(&stats->rx_syncp);
rpackets = stats->rx_packets;
rbytes = stats->rx_bytes;
- } while (u64_stats_fetch_retry(&stats->syncp, start));
+ } while (u64_stats_fetch_retry(&stats->rx_syncp, start));
tot->rx_packets += rpackets;
tot->tx_packets += tpackets;
diff --git a/drivers/net/wireless/b43/b43.h b/drivers/net/wireless/b43/b43.h
index 67c13af..c06b6cb 100644
--- a/drivers/net/wireless/b43/b43.h
+++ b/drivers/net/wireless/b43/b43.h
@@ -877,6 +877,10 @@
* from the mac80211 subsystem. */
u16 mac80211_initially_registered_queues;
+ /* Set this if we call ieee80211_register_hw() and check if we call
+ * ieee80211_unregister_hw(). */
+ bool hw_registred;
+
/* We can only have one operating interface (802.11 core)
* at a time. General information about this interface follows.
*/
diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c
index 5a39b22..acd03a4 100644
--- a/drivers/net/wireless/b43/main.c
+++ b/drivers/net/wireless/b43/main.c
@@ -2437,6 +2437,7 @@
err = ieee80211_register_hw(wl->hw);
if (err)
goto err_one_core_detach;
+ wl->hw_registred = true;
b43_leds_register(wl->current_dev);
goto out;
@@ -5299,6 +5300,7 @@
hw->queues = modparam_qos ? B43_QOS_QUEUE_NUM : 1;
wl->mac80211_initially_registered_queues = hw->queues;
+ wl->hw_registred = false;
hw->max_rates = 2;
SET_IEEE80211_DEV(hw, dev->dev);
if (is_valid_ether_addr(sprom->et1mac))
@@ -5370,12 +5372,15 @@
* as the ieee80211 unreg will destroy the workqueue. */
cancel_work_sync(&wldev->restart_work);
- /* Restore the queues count before unregistering, because firmware detect
- * might have modified it. Restoring is important, so the networking
- * stack can properly free resources. */
- wl->hw->queues = wl->mac80211_initially_registered_queues;
- b43_leds_stop(wldev);
- ieee80211_unregister_hw(wl->hw);
+ B43_WARN_ON(!wl);
+ if (wl->current_dev == wldev && wl->hw_registred) {
+ /* Restore the queues count before unregistering, because firmware detect
+ * might have modified it. Restoring is important, so the networking
+ * stack can properly free resources. */
+ wl->hw->queues = wl->mac80211_initially_registered_queues;
+ b43_leds_stop(wldev);
+ ieee80211_unregister_hw(wl->hw);
+ }
b43_one_core_detach(wldev->dev);
@@ -5446,7 +5451,7 @@
cancel_work_sync(&wldev->restart_work);
B43_WARN_ON(!wl);
- if (wl->current_dev == wldev) {
+ if (wl->current_dev == wldev && wl->hw_registred) {
/* Restore the queues count before unregistering, because firmware detect
* might have modified it. Restoring is important, so the networking
* stack can properly free resources. */
diff --git a/drivers/net/wireless/ipw2x00/ipw2100.c b/drivers/net/wireless/ipw2x00/ipw2100.c
index 9cfae0c..95aa8e1 100644
--- a/drivers/net/wireless/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/ipw2x00/ipw2100.c
@@ -1903,14 +1903,6 @@
netif_stop_queue(priv->net_dev);
}
-/* Called by register_netdev() */
-static int ipw2100_net_init(struct net_device *dev)
-{
- struct ipw2100_priv *priv = libipw_priv(dev);
-
- return ipw2100_up(priv, 1);
-}
-
static int ipw2100_wdev_init(struct net_device *dev)
{
struct ipw2100_priv *priv = libipw_priv(dev);
@@ -6087,7 +6079,6 @@
.ndo_stop = ipw2100_close,
.ndo_start_xmit = libipw_xmit,
.ndo_change_mtu = libipw_change_mtu,
- .ndo_init = ipw2100_net_init,
.ndo_tx_timeout = ipw2100_tx_timeout,
.ndo_set_mac_address = ipw2100_set_address,
.ndo_validate_addr = eth_validate_addr,
@@ -6329,6 +6320,10 @@
printk(KERN_INFO DRV_NAME
": Detected Intel PRO/Wireless 2100 Network Connection\n");
+ err = ipw2100_up(priv, 1);
+ if (err)
+ goto fail;
+
err = ipw2100_wdev_init(dev);
if (err)
goto fail;
@@ -6338,12 +6333,7 @@
* network device we would call ipw2100_up. This introduced a race
* condition with newer hotplug configurations (network was coming
* up and making calls before the device was initialized).
- *
- * If we called ipw2100_up before we registered the device, then the
- * device name wasn't registered. So, we instead use the net_dev->init
- * member to call a function that then just turns and calls ipw2100_up.
- * net_dev->init is called after name allocation but before the
- * notifier chain is called */
+ */
err = register_netdev(dev);
if (err) {
printk(KERN_WARNING DRV_NAME
diff --git a/drivers/net/wireless/iwlwifi/dvm/sta.c b/drivers/net/wireless/iwlwifi/dvm/sta.c
index 286ce4e..b29b798 100644
--- a/drivers/net/wireless/iwlwifi/dvm/sta.c
+++ b/drivers/net/wireless/iwlwifi/dvm/sta.c
@@ -1251,7 +1251,7 @@
key_flags |= STA_KEY_MULTICAST_MSK;
sta_cmd.key.key_flags = key_flags;
- sta_cmd.key.key_offset = WEP_INVALID_OFFSET;
+ sta_cmd.key.key_offset = keyconf->hw_key_idx;
sta_cmd.sta.modify_mask = STA_MODIFY_KEY_MASK;
sta_cmd.mode = STA_CONTROL_MODIFY_MSK;
diff --git a/drivers/net/wireless/iwlwifi/iwl-prph.h b/drivers/net/wireless/iwlwifi/iwl-prph.h
index a9f0415..9253ef1 100644
--- a/drivers/net/wireless/iwlwifi/iwl-prph.h
+++ b/drivers/net/wireless/iwlwifi/iwl-prph.h
@@ -224,6 +224,7 @@
#define SCD_TXFACT (SCD_BASE + 0x10)
#define SCD_ACTIVE (SCD_BASE + 0x14)
#define SCD_QUEUECHAIN_SEL (SCD_BASE + 0xe8)
+#define SCD_CHAINEXT_EN (SCD_BASE + 0x244)
#define SCD_AGGR_SEL (SCD_BASE + 0x248)
#define SCD_INTERRUPT_MASK (SCD_BASE + 0x108)
diff --git a/drivers/net/wireless/iwlwifi/pcie/6000.c b/drivers/net/wireless/iwlwifi/pcie/6000.c
index 8dd8a6f..cb08ba0 100644
--- a/drivers/net/wireless/iwlwifi/pcie/6000.c
+++ b/drivers/net/wireless/iwlwifi/pcie/6000.c
@@ -35,17 +35,20 @@
#define IWL6000_UCODE_API_MAX 6
#define IWL6050_UCODE_API_MAX 5
#define IWL6000G2_UCODE_API_MAX 6
+#define IWL6035_UCODE_API_MAX 6
/* Oldest version we won't warn about */
#define IWL6000_UCODE_API_OK 4
#define IWL6000G2_UCODE_API_OK 5
#define IWL6050_UCODE_API_OK 5
#define IWL6000G2B_UCODE_API_OK 6
+#define IWL6035_UCODE_API_OK 6
/* Lowest firmware API version supported */
#define IWL6000_UCODE_API_MIN 4
#define IWL6050_UCODE_API_MIN 4
-#define IWL6000G2_UCODE_API_MIN 4
+#define IWL6000G2_UCODE_API_MIN 5
+#define IWL6035_UCODE_API_MIN 6
/* EEPROM versions */
#define EEPROM_6000_TX_POWER_VERSION (4)
@@ -243,9 +246,25 @@
IWL_DEVICE_6030,
};
+#define IWL_DEVICE_6035 \
+ .fw_name_pre = IWL6030_FW_PRE, \
+ .ucode_api_max = IWL6035_UCODE_API_MAX, \
+ .ucode_api_ok = IWL6035_UCODE_API_OK, \
+ .ucode_api_min = IWL6035_UCODE_API_MIN, \
+ .device_family = IWL_DEVICE_FAMILY_6030, \
+ .max_inst_size = IWL60_RTC_INST_SIZE, \
+ .max_data_size = IWL60_RTC_DATA_SIZE, \
+ .eeprom_ver = EEPROM_6030_EEPROM_VERSION, \
+ .eeprom_calib_ver = EEPROM_6030_TX_POWER_VERSION, \
+ .base_params = &iwl6000_g2_base_params, \
+ .bt_params = &iwl6000_bt_params, \
+ .need_temp_offset_calib = true, \
+ .led_mode = IWL_LED_RF_STATE, \
+ .adv_pm = true
+
const struct iwl_cfg iwl6035_2agn_cfg = {
.name = "Intel(R) Centrino(R) Advanced-N 6235 AGN",
- IWL_DEVICE_6030,
+ IWL_DEVICE_6035,
.ht_params = &iwl6000_ht_params,
};
diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c
index 969f78f..7461a6a 100644
--- a/drivers/net/wireless/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/iwlwifi/pcie/trans.c
@@ -1065,6 +1065,12 @@
/* Activate all Tx DMA/FIFO channels */
iwl_trans_txq_set_sched(trans, IWL_MASK(0, 7));
+ /* The chain extension of the SCD doesn't work well. This feature is
+ * enabled by default by the HW, so we need to disable it manually.
+ */
+ iwl_write_prph(trans, SCD_CHAINEXT_EN, 0);
+
+
/* Enable DMA channel */
for (chan = 0; chan < FH_TCSR_CHNL_NUM ; chan++)
iwl_write_direct32(trans, FH_TCSR_CHNL_TX_CONFIG_REG(chan),
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 4c9336c..a0b7cfd 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -1555,6 +1555,7 @@
hdr = (struct ieee80211_hdr *) skb->data;
mac80211_hwsim_monitor_ack(data2->hw, hdr->addr2);
}
+ txi->flags |= IEEE80211_TX_STAT_ACK;
}
ieee80211_tx_status_irqsafe(data2->hw, skb);
return 0;
diff --git a/drivers/net/wireless/rtl818x/rtl8187/leds.c b/drivers/net/wireless/rtl818x/rtl8187/leds.c
index 2e0de2f..c2d5b49 100644
--- a/drivers/net/wireless/rtl818x/rtl8187/leds.c
+++ b/drivers/net/wireless/rtl818x/rtl8187/leds.c
@@ -117,7 +117,7 @@
radio_on = true;
} else if (radio_on) {
radio_on = false;
- cancel_delayed_work_sync(&priv->led_on);
+ cancel_delayed_work(&priv->led_on);
ieee80211_queue_delayed_work(hw, &priv->led_off, 0);
}
} else if (radio_on) {
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index c3b331b..0cc053a 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -61,7 +61,7 @@
list_for_each_entry(_maps_node_, &pinctrl_maps, node) \
for (_i_ = 0, _map_ = &_maps_node_->maps[_i_]; \
_i_ < _maps_node_->num_maps; \
- i++, _map_ = &_maps_node_->maps[_i_])
+ _i_++, _map_ = &_maps_node_->maps[_i_])
/**
* pinctrl_provide_dummies() - indicate if pinctrl provides dummy state support
diff --git a/drivers/pinctrl/pinctrl-imx.c b/drivers/pinctrl/pinctrl-imx.c
index f6e7c67..dd6d93a 100644
--- a/drivers/pinctrl/pinctrl-imx.c
+++ b/drivers/pinctrl/pinctrl-imx.c
@@ -27,16 +27,16 @@
#include "core.h"
#include "pinctrl-imx.h"
-#define IMX_PMX_DUMP(info, p, m, c, n) \
-{ \
- int i, j; \
- printk("Format: Pin Mux Config\n"); \
- for (i = 0; i < n; i++) { \
- j = p[i]; \
- printk("%s %d 0x%lx\n", \
- info->pins[j].name, \
- m[i], c[i]); \
- } \
+#define IMX_PMX_DUMP(info, p, m, c, n) \
+{ \
+ int i, j; \
+ printk(KERN_DEBUG "Format: Pin Mux Config\n"); \
+ for (i = 0; i < n; i++) { \
+ j = p[i]; \
+ printk(KERN_DEBUG "%s %d 0x%lx\n", \
+ info->pins[j].name, \
+ m[i], c[i]); \
+ } \
}
/* The bits in CONFIG cell defined in binding doc*/
@@ -173,8 +173,10 @@
/* create mux map */
parent = of_get_parent(np);
- if (!parent)
+ if (!parent) {
+ kfree(new_map);
return -EINVAL;
+ }
new_map[0].type = PIN_MAP_TYPE_MUX_GROUP;
new_map[0].data.mux.function = parent->name;
new_map[0].data.mux.group = np->name;
@@ -193,7 +195,7 @@
}
dev_dbg(pctldev->dev, "maps: function %s group %s num %d\n",
- new_map->data.mux.function, new_map->data.mux.group, map_num);
+ (*map)->data.mux.function, (*map)->data.mux.group, map_num);
return 0;
}
@@ -201,10 +203,7 @@
static void imx_dt_free_map(struct pinctrl_dev *pctldev,
struct pinctrl_map *map, unsigned num_maps)
{
- int i;
-
- for (i = 0; i < num_maps; i++)
- kfree(map);
+ kfree(map);
}
static struct pinctrl_ops imx_pctrl_ops = {
@@ -475,9 +474,8 @@
grp->configs[j] = config & ~IMX_PAD_SION;
}
-#ifdef DEBUG
IMX_PMX_DUMP(info, grp->pins, grp->mux_mode, grp->configs, grp->npins);
-#endif
+
return 0;
}
diff --git a/drivers/pinctrl/pinctrl-mxs.c b/drivers/pinctrl/pinctrl-mxs.c
index 556e45a..afb50ee 100644
--- a/drivers/pinctrl/pinctrl-mxs.c
+++ b/drivers/pinctrl/pinctrl-mxs.c
@@ -107,8 +107,10 @@
/* Compose group name */
group = kzalloc(length, GFP_KERNEL);
- if (!group)
- return -ENOMEM;
+ if (!group) {
+ ret = -ENOMEM;
+ goto free;
+ }
snprintf(group, length, "%s.%d", np->name, reg);
new_map[i].data.mux.group = group;
i++;
@@ -118,7 +120,7 @@
pconfig = kmemdup(&config, sizeof(config), GFP_KERNEL);
if (!pconfig) {
ret = -ENOMEM;
- goto free;
+ goto free_group;
}
new_map[i].type = PIN_MAP_TYPE_CONFIGS_GROUP;
@@ -133,6 +135,9 @@
return 0;
+free_group:
+ if (!purecfg)
+ free(group);
free:
kfree(new_map);
return ret;
@@ -511,6 +516,7 @@
return 0;
err:
+ platform_set_drvdata(pdev, NULL);
iounmap(d->base);
return ret;
}
@@ -520,6 +526,7 @@
{
struct mxs_pinctrl_data *d = platform_get_drvdata(pdev);
+ platform_set_drvdata(pdev, NULL);
pinctrl_unregister(d->pctl);
iounmap(d->base);
diff --git a/drivers/pinctrl/pinctrl-nomadik.c b/drivers/pinctrl/pinctrl-nomadik.c
index b26395d..e8937e7 100644
--- a/drivers/pinctrl/pinctrl-nomadik.c
+++ b/drivers/pinctrl/pinctrl-nomadik.c
@@ -673,7 +673,7 @@
* wakeup is anyhow controlled by the RIMSC and FIMSC registers.
*/
if (nmk_chip->sleepmode && on) {
- __nmk_gpio_set_slpm(nmk_chip, gpio % nmk_chip->chip.base,
+ __nmk_gpio_set_slpm(nmk_chip, gpio % NMK_GPIO_PER_CHIP,
NMK_GPIO_SLPM_WAKEUP_ENABLE);
}
@@ -1246,6 +1246,7 @@
ret = PTR_ERR(clk);
goto out_unmap;
}
+ clk_prepare(clk);
nmk_chip = kzalloc(sizeof(*nmk_chip), GFP_KERNEL);
if (!nmk_chip) {
diff --git a/drivers/pinctrl/pinctrl-sirf.c b/drivers/pinctrl/pinctrl-sirf.c
index ba15b1a..e9f8e7d 100644
--- a/drivers/pinctrl/pinctrl-sirf.c
+++ b/drivers/pinctrl/pinctrl-sirf.c
@@ -1184,7 +1184,7 @@
return ret;
}
-static const struct of_device_id pinmux_ids[] = {
+static const struct of_device_id pinmux_ids[] __devinitconst = {
{ .compatible = "sirf,prima2-gpio-pinmux" },
{}
};
diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c
index 639db4d..2fd9d36 100644
--- a/drivers/platform/x86/acerhdf.c
+++ b/drivers/platform/x86/acerhdf.c
@@ -5,7 +5,7 @@
*
* (C) 2009 - Peter Feuerer peter (a) piie.net
* http://piie.net
- * 2009 Borislav Petkov <petkovbb@gmail.com>
+ * 2009 Borislav Petkov bp (a) alien8.de
*
* Inspired by and many thanks to:
* o acerfand - Rachel Greenham
diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c
index 3660bac..e82e7ea 100644
--- a/drivers/regulator/anatop-regulator.c
+++ b/drivers/regulator/anatop-regulator.c
@@ -224,7 +224,7 @@
.of_match_table = of_anatop_regulator_match_tbl,
},
.probe = anatop_regulator_probe,
- .remove = anatop_regulator_remove,
+ .remove = __devexit_p(anatop_regulator_remove),
};
static int __init anatop_regulator_init(void)
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 7584a74..09a737c 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -2050,6 +2050,9 @@
return -EINVAL;
}
+ if (min_uV < rdev->desc->min_uV)
+ min_uV = rdev->desc->min_uV;
+
ret = DIV_ROUND_UP(min_uV - rdev->desc->min_uV, rdev->desc->uV_step);
if (ret < 0)
return ret;
diff --git a/drivers/regulator/gpio-regulator.c b/drivers/regulator/gpio-regulator.c
index 9997d7a..242851a 100644
--- a/drivers/regulator/gpio-regulator.c
+++ b/drivers/regulator/gpio-regulator.c
@@ -101,16 +101,20 @@
}
static int gpio_regulator_set_value(struct regulator_dev *dev,
- int min, int max)
+ int min, int max, unsigned *selector)
{
struct gpio_regulator_data *data = rdev_get_drvdata(dev);
- int ptr, target, state, best_val = INT_MAX;
+ int ptr, target = 0, state, best_val = INT_MAX;
for (ptr = 0; ptr < data->nr_states; ptr++)
if (data->states[ptr].value < best_val &&
data->states[ptr].value >= min &&
- data->states[ptr].value <= max)
+ data->states[ptr].value <= max) {
target = data->states[ptr].gpios;
+ best_val = data->states[ptr].value;
+ if (selector)
+ *selector = ptr;
+ }
if (best_val == INT_MAX)
return -EINVAL;
@@ -128,7 +132,7 @@
int min_uV, int max_uV,
unsigned *selector)
{
- return gpio_regulator_set_value(dev, min_uV, max_uV);
+ return gpio_regulator_set_value(dev, min_uV, max_uV, selector);
}
static int gpio_regulator_list_voltage(struct regulator_dev *dev,
@@ -145,7 +149,7 @@
static int gpio_regulator_set_current_limit(struct regulator_dev *dev,
int min_uA, int max_uA)
{
- return gpio_regulator_set_value(dev, min_uA, max_uA);
+ return gpio_regulator_set_value(dev, min_uA, max_uA, NULL);
}
static struct regulator_ops gpio_regulator_voltage_ops = {
@@ -286,7 +290,7 @@
cfg.dev = &pdev->dev;
cfg.init_data = config->init_data;
- cfg.driver_data = &drvdata;
+ cfg.driver_data = drvdata;
drvdata->dev = regulator_register(&drvdata->desc, &cfg);
if (IS_ERR(drvdata->dev)) {
diff --git a/drivers/regulator/max8649.c b/drivers/regulator/max8649.c
index 1f4bb80..9d540cd 100644
--- a/drivers/regulator/max8649.c
+++ b/drivers/regulator/max8649.c
@@ -259,6 +259,7 @@
config.dev = &client->dev;
config.init_data = pdata->regulator;
config.driver_data = info;
+ config.regmap = info->regmap;
info->regulator = regulator_register(&dcdc_desc, &config);
if (IS_ERR(info->regulator)) {
diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c
index c4435f6..9b7ca90 100644
--- a/drivers/regulator/palmas-regulator.c
+++ b/drivers/regulator/palmas-regulator.c
@@ -775,9 +775,6 @@
err_unregister_regulator:
while (--id >= 0)
regulator_unregister(pmic->rdev[id]);
- kfree(pmic->rdev);
- kfree(pmic->desc);
- kfree(pmic);
return ret;
}
@@ -788,10 +785,6 @@
for (id = 0; id < PALMAS_NUM_REGS; id++)
regulator_unregister(pmic->rdev[id]);
-
- kfree(pmic->rdev);
- kfree(pmic->desc);
- kfree(pmic);
return 0;
}
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 7d5f56e..4267789 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -910,14 +910,17 @@
static u32 rtc_handler(void *context)
{
+ struct device *dev = context;
+
+ pm_wakeup_event(dev, 0);
acpi_clear_event(ACPI_EVENT_RTC);
acpi_disable_event(ACPI_EVENT_RTC, 0);
return ACPI_INTERRUPT_HANDLED;
}
-static inline void rtc_wake_setup(void)
+static inline void rtc_wake_setup(struct device *dev)
{
- acpi_install_fixed_event_handler(ACPI_EVENT_RTC, rtc_handler, NULL);
+ acpi_install_fixed_event_handler(ACPI_EVENT_RTC, rtc_handler, dev);
/*
* After the RTC handler is installed, the Fixed_RTC event should
* be disabled. Only when the RTC alarm is set will it be enabled.
@@ -950,7 +953,7 @@
if (acpi_disabled)
return;
- rtc_wake_setup();
+ rtc_wake_setup(dev);
acpi_rtc_info.wake_on = rtc_wake_on;
acpi_rtc_info.wake_off = rtc_wake_off;
diff --git a/drivers/staging/ramster/zcache-main.c b/drivers/staging/ramster/zcache-main.c
index 4e7ef0e..d46764b 100644
--- a/drivers/staging/ramster/zcache-main.c
+++ b/drivers/staging/ramster/zcache-main.c
@@ -3002,7 +3002,7 @@
return oid;
}
-static int zcache_frontswap_put_page(unsigned type, pgoff_t offset,
+static int zcache_frontswap_store(unsigned type, pgoff_t offset,
struct page *page)
{
u64 ind64 = (u64)offset;
@@ -3025,7 +3025,7 @@
/* returns 0 if the page was successfully gotten from frontswap, -1 if
* was not present (should never happen!) */
-static int zcache_frontswap_get_page(unsigned type, pgoff_t offset,
+static int zcache_frontswap_load(unsigned type, pgoff_t offset,
struct page *page)
{
u64 ind64 = (u64)offset;
@@ -3080,8 +3080,8 @@
}
static struct frontswap_ops zcache_frontswap_ops = {
- .put_page = zcache_frontswap_put_page,
- .get_page = zcache_frontswap_get_page,
+ .store = zcache_frontswap_store,
+ .load = zcache_frontswap_load,
.invalidate_page = zcache_frontswap_flush_page,
.invalidate_area = zcache_frontswap_flush_area,
.init = zcache_frontswap_init
diff --git a/drivers/staging/zcache/zcache-main.c b/drivers/staging/zcache/zcache-main.c
index 2734dac..784c796 100644
--- a/drivers/staging/zcache/zcache-main.c
+++ b/drivers/staging/zcache/zcache-main.c
@@ -1835,7 +1835,7 @@
* Swizzling increases objects per swaptype, increasing tmem concurrency
* for heavy swaploads. Later, larger nr_cpus -> larger SWIZ_BITS
* Setting SWIZ_BITS to 27 basically reconstructs the swap entry from
- * frontswap_get_page(), but has side-effects. Hence using 8.
+ * frontswap_load(), but has side-effects. Hence using 8.
*/
#define SWIZ_BITS 8
#define SWIZ_MASK ((1 << SWIZ_BITS) - 1)
@@ -1849,7 +1849,7 @@
return oid;
}
-static int zcache_frontswap_put_page(unsigned type, pgoff_t offset,
+static int zcache_frontswap_store(unsigned type, pgoff_t offset,
struct page *page)
{
u64 ind64 = (u64)offset;
@@ -1870,7 +1870,7 @@
/* returns 0 if the page was successfully gotten from frontswap, -1 if
* was not present (should never happen!) */
-static int zcache_frontswap_get_page(unsigned type, pgoff_t offset,
+static int zcache_frontswap_load(unsigned type, pgoff_t offset,
struct page *page)
{
u64 ind64 = (u64)offset;
@@ -1919,8 +1919,8 @@
}
static struct frontswap_ops zcache_frontswap_ops = {
- .put_page = zcache_frontswap_put_page,
- .get_page = zcache_frontswap_get_page,
+ .store = zcache_frontswap_store,
+ .load = zcache_frontswap_load,
.invalidate_page = zcache_frontswap_flush_page,
.invalidate_area = zcache_frontswap_flush_area,
.init = zcache_frontswap_init
diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c
index 37c6098..7e6136e 100644
--- a/drivers/target/sbp/sbp_target.c
+++ b/drivers/target/sbp/sbp_target.c
@@ -587,14 +587,14 @@
{
struct sbp_tport *tport = agent->tport;
struct sbp_tpg *tpg = tport->tpg;
- int login_id;
+ int id;
struct sbp_login_descriptor *login;
- login_id = LOGOUT_ORB_LOGIN_ID(be32_to_cpu(req->orb.misc));
+ id = LOGOUT_ORB_LOGIN_ID(be32_to_cpu(req->orb.misc));
- login = sbp_login_find_by_id(tpg, login_id);
+ login = sbp_login_find_by_id(tpg, id);
if (!login) {
- pr_warn("cannot find login: %d\n", login_id);
+ pr_warn("cannot find login: %d\n", id);
req->status.status = cpu_to_be32(
STATUS_BLOCK_RESP(STATUS_RESP_REQUEST_COMPLETE) |
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index 686dba1..9f99d04 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -133,16 +133,11 @@
ret = PTR_ERR(dev_p);
goto fail;
}
-
- /* O_DIRECT too? */
- flags = O_RDWR | O_CREAT | O_LARGEFILE;
-
/*
- * If fd_buffered_io=1 has not been set explicitly (the default),
- * use O_SYNC to force FILEIO writes to disk.
+ * Use O_DSYNC by default instead of O_SYNC to forgo syncing
+ * of pure timestamp updates.
*/
- if (!(fd_dev->fbd_flags & FDBD_USE_BUFFERED_IO))
- flags |= O_SYNC;
+ flags = O_RDWR | O_CREAT | O_LARGEFILE | O_DSYNC;
file = filp_open(dev_p, flags, 0600);
if (IS_ERR(file)) {
@@ -380,23 +375,6 @@
}
}
-static void fd_emulate_write_fua(struct se_cmd *cmd)
-{
- struct se_device *dev = cmd->se_dev;
- struct fd_dev *fd_dev = dev->dev_ptr;
- loff_t start = cmd->t_task_lba *
- dev->se_sub_dev->se_dev_attrib.block_size;
- loff_t end = start + cmd->data_length;
- int ret;
-
- pr_debug("FILEIO: FUA WRITE LBA: %llu, bytes: %u\n",
- cmd->t_task_lba, cmd->data_length);
-
- ret = vfs_fsync_range(fd_dev->fd_file, start, end, 1);
- if (ret != 0)
- pr_err("FILEIO: vfs_fsync_range() failed: %d\n", ret);
-}
-
static int fd_execute_cmd(struct se_cmd *cmd, struct scatterlist *sgl,
u32 sgl_nents, enum dma_data_direction data_direction)
{
@@ -411,19 +389,21 @@
ret = fd_do_readv(cmd, sgl, sgl_nents);
} else {
ret = fd_do_writev(cmd, sgl, sgl_nents);
-
+ /*
+ * Perform implict vfs_fsync_range() for fd_do_writev() ops
+ * for SCSI WRITEs with Forced Unit Access (FUA) set.
+ * Allow this to happen independent of WCE=0 setting.
+ */
if (ret > 0 &&
- dev->se_sub_dev->se_dev_attrib.emulate_write_cache > 0 &&
dev->se_sub_dev->se_dev_attrib.emulate_fua_write > 0 &&
(cmd->se_cmd_flags & SCF_FUA)) {
- /*
- * We might need to be a bit smarter here
- * and return some sense data to let the initiator
- * know the FUA WRITE cache sync failed..?
- */
- fd_emulate_write_fua(cmd);
- }
+ struct fd_dev *fd_dev = dev->dev_ptr;
+ loff_t start = cmd->t_task_lba *
+ dev->se_sub_dev->se_dev_attrib.block_size;
+ loff_t end = start + cmd->data_length;
+ vfs_fsync_range(fd_dev->fd_file, start, end, 1);
+ }
}
if (ret < 0) {
@@ -442,7 +422,6 @@
static match_table_t tokens = {
{Opt_fd_dev_name, "fd_dev_name=%s"},
{Opt_fd_dev_size, "fd_dev_size=%s"},
- {Opt_fd_buffered_io, "fd_buffered_io=%d"},
{Opt_err, NULL}
};
@@ -454,7 +433,7 @@
struct fd_dev *fd_dev = se_dev->se_dev_su_ptr;
char *orig, *ptr, *arg_p, *opts;
substring_t args[MAX_OPT_ARGS];
- int ret = 0, arg, token;
+ int ret = 0, token;
opts = kstrdup(page, GFP_KERNEL);
if (!opts)
@@ -498,19 +477,6 @@
" bytes\n", fd_dev->fd_dev_size);
fd_dev->fbd_flags |= FBDF_HAS_SIZE;
break;
- case Opt_fd_buffered_io:
- match_int(args, &arg);
- if (arg != 1) {
- pr_err("bogus fd_buffered_io=%d value\n", arg);
- ret = -EINVAL;
- goto out;
- }
-
- pr_debug("FILEIO: Using buffered I/O"
- " operations for struct fd_dev\n");
-
- fd_dev->fbd_flags |= FDBD_USE_BUFFERED_IO;
- break;
default:
break;
}
@@ -542,10 +508,8 @@
ssize_t bl = 0;
bl = sprintf(b + bl, "TCM FILEIO ID: %u", fd_dev->fd_dev_id);
- bl += sprintf(b + bl, " File: %s Size: %llu Mode: %s\n",
- fd_dev->fd_dev_name, fd_dev->fd_dev_size,
- (fd_dev->fbd_flags & FDBD_USE_BUFFERED_IO) ?
- "Buffered" : "Synchronous");
+ bl += sprintf(b + bl, " File: %s Size: %llu Mode: O_DSYNC\n",
+ fd_dev->fd_dev_name, fd_dev->fd_dev_size);
return bl;
}
diff --git a/drivers/target/target_core_file.h b/drivers/target/target_core_file.h
index fbd59ef..70ce7fd 100644
--- a/drivers/target/target_core_file.h
+++ b/drivers/target/target_core_file.h
@@ -14,7 +14,6 @@
#define FBDF_HAS_PATH 0x01
#define FBDF_HAS_SIZE 0x02
-#define FDBD_USE_BUFFERED_IO 0x04
struct fd_dev {
u32 fbd_flags;
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index 4604153..1bd9163 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -2179,6 +2179,16 @@
return 0;
}
+static void sci_cleanup_single(struct sci_port *port)
+{
+ sci_free_gpios(port);
+
+ clk_put(port->iclk);
+ clk_put(port->fclk);
+
+ pm_runtime_disable(port->port.dev);
+}
+
#ifdef CONFIG_SERIAL_SH_SCI_CONSOLE
static void serial_console_putchar(struct uart_port *port, int ch)
{
@@ -2360,14 +2370,10 @@
cpufreq_unregister_notifier(&port->freq_transition,
CPUFREQ_TRANSITION_NOTIFIER);
- sci_free_gpios(port);
-
uart_remove_one_port(&sci_uart_driver, &port->port);
- clk_put(port->iclk);
- clk_put(port->fclk);
+ sci_cleanup_single(port);
- pm_runtime_disable(&dev->dev);
return 0;
}
@@ -2385,14 +2391,20 @@
index+1, SCI_NPORTS);
dev_notice(&dev->dev, "Consider bumping "
"CONFIG_SERIAL_SH_SCI_NR_UARTS!\n");
- return 0;
+ return -EINVAL;
}
ret = sci_init_single(dev, sciport, index, p);
if (ret)
return ret;
- return uart_add_one_port(&sci_uart_driver, &sciport->port);
+ ret = uart_add_one_port(&sci_uart_driver, &sciport->port);
+ if (ret) {
+ sci_cleanup_single(sciport);
+ return ret;
+ }
+
+ return 0;
}
static int __devinit sci_probe(struct platform_device *dev)
@@ -2413,24 +2425,22 @@
ret = sci_probe_single(dev, dev->id, p, sp);
if (ret)
- goto err_unreg;
+ return ret;
sp->freq_transition.notifier_call = sci_notifier;
ret = cpufreq_register_notifier(&sp->freq_transition,
CPUFREQ_TRANSITION_NOTIFIER);
- if (unlikely(ret < 0))
- goto err_unreg;
+ if (unlikely(ret < 0)) {
+ sci_cleanup_single(sp);
+ return ret;
+ }
#ifdef CONFIG_SH_STANDARD_BIOS
sh_bios_gdb_detach();
#endif
return 0;
-
-err_unreg:
- sci_remove(dev);
- return ret;
}
static int sci_suspend(struct device *dev)
diff --git a/drivers/video/omap2/displays/panel-taal.c b/drivers/video/omap2/displays/panel-taal.c
index 2ce9992..901576e 100644
--- a/drivers/video/omap2/displays/panel-taal.c
+++ b/drivers/video/omap2/displays/panel-taal.c
@@ -526,7 +526,7 @@
{
struct omap_dss_device *dssdev = to_dss_device(dev);
struct taal_data *td = dev_get_drvdata(&dssdev->dev);
- u8 errors;
+ u8 errors = 0;
int r;
mutex_lock(&td->lock);
diff --git a/drivers/video/omap2/dss/core.c b/drivers/video/omap2/dss/core.c
index 72ded9c..5066eee 100644
--- a/drivers/video/omap2/dss/core.c
+++ b/drivers/video/omap2/dss/core.c
@@ -194,8 +194,7 @@
static inline void dss_uninitialize_debugfs(void)
{
}
-static inline int dss_debugfs_create_file(const char *name,
- void (*write)(struct seq_file *))
+int dss_debugfs_create_file(const char *name, void (*write)(struct seq_file *))
{
return 0;
}
diff --git a/drivers/video/omap2/dss/dsi.c b/drivers/video/omap2/dss/dsi.c
index ec363d8..ca8382d 100644
--- a/drivers/video/omap2/dss/dsi.c
+++ b/drivers/video/omap2/dss/dsi.c
@@ -3724,7 +3724,7 @@
/* CLKIN4DDR = 16 * TXBYTECLKHS */
tlp_avail = thsbyte_clk * (blank - trans_lp);
- ttxclkesc = tdsi_fclk / lp_clk_div;
+ ttxclkesc = tdsi_fclk * lp_clk_div;
lp_inter = ((tlp_avail - 8 * thsbyte_clk - 5 * tdsi_fclk) / ttxclkesc -
26) / 16;
diff --git a/drivers/video/omap2/dss/dss.c b/drivers/video/omap2/dss/dss.c
index 6ea1ff1..7706323 100644
--- a/drivers/video/omap2/dss/dss.c
+++ b/drivers/video/omap2/dss/dss.c
@@ -731,7 +731,7 @@
DSSDBG("dss_runtime_put\n");
r = pm_runtime_put_sync(&dss.pdev->dev);
- WARN_ON(r < 0);
+ WARN_ON(r < 0 && r != -EBUSY);
}
/* DEBUGFS */
diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c
index dcb79521..89f264c 100644
--- a/drivers/xen/tmem.c
+++ b/drivers/xen/tmem.c
@@ -269,7 +269,7 @@
}
/* returns 0 if the page was successfully put into frontswap, -1 if not */
-static int tmem_frontswap_put_page(unsigned type, pgoff_t offset,
+static int tmem_frontswap_store(unsigned type, pgoff_t offset,
struct page *page)
{
u64 ind64 = (u64)offset;
@@ -295,7 +295,7 @@
* returns 0 if the page was successfully gotten from frontswap, -1 if
* was not present (should never happen!)
*/
-static int tmem_frontswap_get_page(unsigned type, pgoff_t offset,
+static int tmem_frontswap_load(unsigned type, pgoff_t offset,
struct page *page)
{
u64 ind64 = (u64)offset;
@@ -362,8 +362,8 @@
__setup("nofrontswap", no_frontswap);
static struct frontswap_ops __initdata tmem_frontswap_ops = {
- .put_page = tmem_frontswap_put_page,
- .get_page = tmem_frontswap_get_page,
+ .store = tmem_frontswap_store,
+ .load = tmem_frontswap_load,
.invalidate_page = tmem_frontswap_flush_page,
.invalidate_area = tmem_frontswap_flush_area,
.init = tmem_frontswap_init
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 20350a9..6df0cbe 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -174,6 +174,7 @@
void (*add_credits)(struct TCP_Server_Info *, const unsigned int);
void (*set_credits)(struct TCP_Server_Info *, const int);
int * (*get_credits_field)(struct TCP_Server_Info *);
+ __u64 (*get_next_mid)(struct TCP_Server_Info *);
/* data offset from read response message */
unsigned int (*read_data_offset)(char *);
/* data length from read response message */
@@ -399,6 +400,12 @@
server->ops->set_credits(server, val);
}
+static inline __u64
+get_next_mid(struct TCP_Server_Info *server)
+{
+ return server->ops->get_next_mid(server);
+}
+
/*
* Macros to allow the TCP_Server_Info->net field and related code to drop out
* when CONFIG_NET_NS isn't set.
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 5ec21ec..0a6cbfe 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -114,7 +114,6 @@
void **request_buf);
extern int CIFS_SessSetup(unsigned int xid, struct cifs_ses *ses,
const struct nls_table *nls_cp);
-extern __u64 GetNextMid(struct TCP_Server_Info *server);
extern struct timespec cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601);
extern u64 cifs_UnixTimeToNT(struct timespec);
extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time,
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index b5ad716..5b40073 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -268,7 +268,7 @@
return rc;
buffer = (struct smb_hdr *)*request_buf;
- buffer->Mid = GetNextMid(ses->server);
+ buffer->Mid = get_next_mid(ses->server);
if (ses->capabilities & CAP_UNICODE)
buffer->Flags2 |= SMBFLG2_UNICODE;
if (ses->capabilities & CAP_STATUS32)
@@ -402,7 +402,7 @@
cFYI(1, "secFlags 0x%x", secFlags);
- pSMB->hdr.Mid = GetNextMid(server);
+ pSMB->hdr.Mid = get_next_mid(server);
pSMB->hdr.Flags2 |= (SMBFLG2_UNICODE | SMBFLG2_ERR_STATUS);
if ((secFlags & CIFSSEC_MUST_KRB5) == CIFSSEC_MUST_KRB5)
@@ -782,7 +782,7 @@
return rc;
}
- pSMB->hdr.Mid = GetNextMid(ses->server);
+ pSMB->hdr.Mid = get_next_mid(ses->server);
if (ses->server->sec_mode &
(SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
@@ -4762,7 +4762,7 @@
/* server pointer checked in called function,
but should never be null here anyway */
- pSMB->hdr.Mid = GetNextMid(ses->server);
+ pSMB->hdr.Mid = get_next_mid(ses->server);
pSMB->hdr.Tid = ses->ipc_tid;
pSMB->hdr.Uid = ses->Suid;
if (ses->capabilities & CAP_STATUS32)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index ccafded..78db68a 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1058,13 +1058,15 @@
if (mid_entry != NULL) {
if (!mid_entry->multiRsp || mid_entry->multiEnd)
mid_entry->callback(mid_entry);
- } else if (!server->ops->is_oplock_break(buf, server)) {
+ } else if (!server->ops->is_oplock_break ||
+ !server->ops->is_oplock_break(buf, server)) {
cERROR(1, "No task to wake, unknown frame received! "
"NumMids %d", atomic_read(&midCount));
cifs_dump_mem("Received Data is: ", buf,
HEADER_SIZE(server));
#ifdef CONFIG_CIFS_DEBUG2
- server->ops->dump_detail(buf);
+ if (server->ops->dump_detail)
+ server->ops->dump_detail(buf);
cifs_dump_mids(server);
#endif /* CIFS_DEBUG2 */
@@ -3938,7 +3940,7 @@
header_assemble(smb_buffer, SMB_COM_TREE_CONNECT_ANDX,
NULL /*no tid */ , 4 /*wct */ );
- smb_buffer->Mid = GetNextMid(ses->server);
+ smb_buffer->Mid = get_next_mid(ses->server);
smb_buffer->Uid = ses->Suid;
pSMB = (TCONX_REQ *) smb_buffer;
pSMBr = (TCONX_RSP *) smb_buffer_response;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 253170d..513adbc 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -876,7 +876,7 @@
struct cifsLockInfo *li, *tmp;
struct cifs_tcon *tcon;
struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
- unsigned int num, max_num;
+ unsigned int num, max_num, max_buf;
LOCKING_ANDX_RANGE *buf, *cur;
int types[] = {LOCKING_ANDX_LARGE_FILES,
LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES};
@@ -892,8 +892,19 @@
return rc;
}
- max_num = (tcon->ses->server->maxBuf - sizeof(struct smb_hdr)) /
- sizeof(LOCKING_ANDX_RANGE);
+ /*
+ * Accessing maxBuf is racy with cifs_reconnect - need to store value
+ * and check it for zero before using.
+ */
+ max_buf = tcon->ses->server->maxBuf;
+ if (!max_buf) {
+ mutex_unlock(&cinode->lock_mutex);
+ FreeXid(xid);
+ return -EINVAL;
+ }
+
+ max_num = (max_buf - sizeof(struct smb_hdr)) /
+ sizeof(LOCKING_ANDX_RANGE);
buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
if (!buf) {
mutex_unlock(&cinode->lock_mutex);
@@ -1218,7 +1229,7 @@
int types[] = {LOCKING_ANDX_LARGE_FILES,
LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES};
unsigned int i;
- unsigned int max_num, num;
+ unsigned int max_num, num, max_buf;
LOCKING_ANDX_RANGE *buf, *cur;
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
@@ -1228,8 +1239,16 @@
INIT_LIST_HEAD(&tmp_llist);
- max_num = (tcon->ses->server->maxBuf - sizeof(struct smb_hdr)) /
- sizeof(LOCKING_ANDX_RANGE);
+ /*
+ * Accessing maxBuf is racy with cifs_reconnect - need to store value
+ * and check it for zero before using.
+ */
+ max_buf = tcon->ses->server->maxBuf;
+ if (!max_buf)
+ return -EINVAL;
+
+ max_num = (max_buf - sizeof(struct smb_hdr)) /
+ sizeof(LOCKING_ANDX_RANGE);
buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
if (!buf)
return -ENOMEM;
@@ -1247,46 +1266,7 @@
continue;
if (types[i] != li->type)
continue;
- if (!cinode->can_cache_brlcks) {
- cur->Pid = cpu_to_le16(li->pid);
- cur->LengthLow = cpu_to_le32((u32)li->length);
- cur->LengthHigh =
- cpu_to_le32((u32)(li->length>>32));
- cur->OffsetLow = cpu_to_le32((u32)li->offset);
- cur->OffsetHigh =
- cpu_to_le32((u32)(li->offset>>32));
- /*
- * We need to save a lock here to let us add
- * it again to the file's list if the unlock
- * range request fails on the server.
- */
- list_move(&li->llist, &tmp_llist);
- if (++num == max_num) {
- stored_rc = cifs_lockv(xid, tcon,
- cfile->netfid,
- li->type, num,
- 0, buf);
- if (stored_rc) {
- /*
- * We failed on the unlock range
- * request - add all locks from
- * the tmp list to the head of
- * the file's list.
- */
- cifs_move_llist(&tmp_llist,
- &cfile->llist);
- rc = stored_rc;
- } else
- /*
- * The unlock range request
- * succeed - free the tmp list.
- */
- cifs_free_llist(&tmp_llist);
- cur = buf;
- num = 0;
- } else
- cur++;
- } else {
+ if (cinode->can_cache_brlcks) {
/*
* We can cache brlock requests - simply remove
* a lock from the file's list.
@@ -1294,7 +1274,41 @@
list_del(&li->llist);
cifs_del_lock_waiters(li);
kfree(li);
+ continue;
}
+ cur->Pid = cpu_to_le16(li->pid);
+ cur->LengthLow = cpu_to_le32((u32)li->length);
+ cur->LengthHigh = cpu_to_le32((u32)(li->length>>32));
+ cur->OffsetLow = cpu_to_le32((u32)li->offset);
+ cur->OffsetHigh = cpu_to_le32((u32)(li->offset>>32));
+ /*
+ * We need to save a lock here to let us add it again to
+ * the file's list if the unlock range request fails on
+ * the server.
+ */
+ list_move(&li->llist, &tmp_llist);
+ if (++num == max_num) {
+ stored_rc = cifs_lockv(xid, tcon, cfile->netfid,
+ li->type, num, 0, buf);
+ if (stored_rc) {
+ /*
+ * We failed on the unlock range
+ * request - add all locks from the tmp
+ * list to the head of the file's list.
+ */
+ cifs_move_llist(&tmp_llist,
+ &cfile->llist);
+ rc = stored_rc;
+ } else
+ /*
+ * The unlock range request succeed -
+ * free the tmp list.
+ */
+ cifs_free_llist(&tmp_llist);
+ cur = buf;
+ num = 0;
+ } else
+ cur++;
}
if (num) {
stored_rc = cifs_lockv(xid, tcon, cfile->netfid,
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index e2552d2..557506a 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -212,93 +212,6 @@
return;
}
-/*
- * Find a free multiplex id (SMB mid). Otherwise there could be
- * mid collisions which might cause problems, demultiplexing the
- * wrong response to this request. Multiplex ids could collide if
- * one of a series requests takes much longer than the others, or
- * if a very large number of long lived requests (byte range
- * locks or FindNotify requests) are pending. No more than
- * 64K-1 requests can be outstanding at one time. If no
- * mids are available, return zero. A future optimization
- * could make the combination of mids and uid the key we use
- * to demultiplex on (rather than mid alone).
- * In addition to the above check, the cifs demultiplex
- * code already used the command code as a secondary
- * check of the frame and if signing is negotiated the
- * response would be discarded if the mid were the same
- * but the signature was wrong. Since the mid is not put in the
- * pending queue until later (when it is about to be dispatched)
- * we do have to limit the number of outstanding requests
- * to somewhat less than 64K-1 although it is hard to imagine
- * so many threads being in the vfs at one time.
- */
-__u64 GetNextMid(struct TCP_Server_Info *server)
-{
- __u64 mid = 0;
- __u16 last_mid, cur_mid;
- bool collision;
-
- spin_lock(&GlobalMid_Lock);
-
- /* mid is 16 bit only for CIFS/SMB */
- cur_mid = (__u16)((server->CurrentMid) & 0xffff);
- /* we do not want to loop forever */
- last_mid = cur_mid;
- cur_mid++;
-
- /*
- * This nested loop looks more expensive than it is.
- * In practice the list of pending requests is short,
- * fewer than 50, and the mids are likely to be unique
- * on the first pass through the loop unless some request
- * takes longer than the 64 thousand requests before it
- * (and it would also have to have been a request that
- * did not time out).
- */
- while (cur_mid != last_mid) {
- struct mid_q_entry *mid_entry;
- unsigned int num_mids;
-
- collision = false;
- if (cur_mid == 0)
- cur_mid++;
-
- num_mids = 0;
- list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) {
- ++num_mids;
- if (mid_entry->mid == cur_mid &&
- mid_entry->mid_state == MID_REQUEST_SUBMITTED) {
- /* This mid is in use, try a different one */
- collision = true;
- break;
- }
- }
-
- /*
- * if we have more than 32k mids in the list, then something
- * is very wrong. Possibly a local user is trying to DoS the
- * box by issuing long-running calls and SIGKILL'ing them. If
- * we get to 2^16 mids then we're in big trouble as this
- * function could loop forever.
- *
- * Go ahead and assign out the mid in this situation, but force
- * an eventual reconnect to clean out the pending_mid_q.
- */
- if (num_mids > 32768)
- server->tcpStatus = CifsNeedReconnect;
-
- if (!collision) {
- mid = (__u64)cur_mid;
- server->CurrentMid = mid;
- break;
- }
- cur_mid++;
- }
- spin_unlock(&GlobalMid_Lock);
- return mid;
-}
-
/* NB: MID can not be set if treeCon not passed in, in that
case it is responsbility of caller to set the mid */
void
@@ -334,7 +247,7 @@
/* Uid is not converted */
buffer->Uid = treeCon->ses->Suid;
- buffer->Mid = GetNextMid(treeCon->ses->server);
+ buffer->Mid = get_next_mid(treeCon->ses->server);
}
if (treeCon->Flags & SMB_SHARE_IS_IN_DFS)
buffer->Flags2 |= SMBFLG2_DFS;
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index d9d615f..6dec38f 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -125,6 +125,94 @@
return &server->credits;
}
+/*
+ * Find a free multiplex id (SMB mid). Otherwise there could be
+ * mid collisions which might cause problems, demultiplexing the
+ * wrong response to this request. Multiplex ids could collide if
+ * one of a series requests takes much longer than the others, or
+ * if a very large number of long lived requests (byte range
+ * locks or FindNotify requests) are pending. No more than
+ * 64K-1 requests can be outstanding at one time. If no
+ * mids are available, return zero. A future optimization
+ * could make the combination of mids and uid the key we use
+ * to demultiplex on (rather than mid alone).
+ * In addition to the above check, the cifs demultiplex
+ * code already used the command code as a secondary
+ * check of the frame and if signing is negotiated the
+ * response would be discarded if the mid were the same
+ * but the signature was wrong. Since the mid is not put in the
+ * pending queue until later (when it is about to be dispatched)
+ * we do have to limit the number of outstanding requests
+ * to somewhat less than 64K-1 although it is hard to imagine
+ * so many threads being in the vfs at one time.
+ */
+static __u64
+cifs_get_next_mid(struct TCP_Server_Info *server)
+{
+ __u64 mid = 0;
+ __u16 last_mid, cur_mid;
+ bool collision;
+
+ spin_lock(&GlobalMid_Lock);
+
+ /* mid is 16 bit only for CIFS/SMB */
+ cur_mid = (__u16)((server->CurrentMid) & 0xffff);
+ /* we do not want to loop forever */
+ last_mid = cur_mid;
+ cur_mid++;
+
+ /*
+ * This nested loop looks more expensive than it is.
+ * In practice the list of pending requests is short,
+ * fewer than 50, and the mids are likely to be unique
+ * on the first pass through the loop unless some request
+ * takes longer than the 64 thousand requests before it
+ * (and it would also have to have been a request that
+ * did not time out).
+ */
+ while (cur_mid != last_mid) {
+ struct mid_q_entry *mid_entry;
+ unsigned int num_mids;
+
+ collision = false;
+ if (cur_mid == 0)
+ cur_mid++;
+
+ num_mids = 0;
+ list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) {
+ ++num_mids;
+ if (mid_entry->mid == cur_mid &&
+ mid_entry->mid_state == MID_REQUEST_SUBMITTED) {
+ /* This mid is in use, try a different one */
+ collision = true;
+ break;
+ }
+ }
+
+ /*
+ * if we have more than 32k mids in the list, then something
+ * is very wrong. Possibly a local user is trying to DoS the
+ * box by issuing long-running calls and SIGKILL'ing them. If
+ * we get to 2^16 mids then we're in big trouble as this
+ * function could loop forever.
+ *
+ * Go ahead and assign out the mid in this situation, but force
+ * an eventual reconnect to clean out the pending_mid_q.
+ */
+ if (num_mids > 32768)
+ server->tcpStatus = CifsNeedReconnect;
+
+ if (!collision) {
+ mid = (__u64)cur_mid;
+ server->CurrentMid = mid;
+ break;
+ }
+ cur_mid++;
+ }
+ spin_unlock(&GlobalMid_Lock);
+ return mid;
+}
+
struct smb_version_operations smb1_operations = {
.send_cancel = send_nt_cancel,
.compare_fids = cifs_compare_fids,
@@ -133,6 +221,7 @@
.add_credits = cifs_add_credits,
.set_credits = cifs_set_credits,
.get_credits_field = cifs_get_credits_field,
+ .get_next_mid = cifs_get_next_mid,
.read_data_offset = cifs_read_data_offset,
.read_data_length = cifs_read_data_length,
.map_error = map_smb_to_linux_error,
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 1b36ffe..3097ee5 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -779,7 +779,7 @@
pSMB->LockType = LOCKING_ANDX_CANCEL_LOCK|LOCKING_ANDX_LARGE_FILES;
pSMB->Timeout = 0;
- pSMB->hdr.Mid = GetNextMid(ses->server);
+ pSMB->hdr.Mid = get_next_mid(ses->server);
return SendReceive(xid, ses, in_buf, out_buf,
&bytes_returned, 0);
diff --git a/fs/dcache.c b/fs/dcache.c
index 85c9e2b..4046904 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -683,6 +683,8 @@
/**
* d_find_alias - grab a hashed alias of inode
* @inode: inode in question
+ * @want_discon: flag, used by d_splice_alias, to request
+ * that only a DISCONNECTED alias be returned.
*
* If inode has a hashed alias, or is a directory and has any alias,
* acquire the reference to alias and return it. Otherwise return NULL.
@@ -691,9 +693,10 @@
* of a filesystem.
*
* If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer
- * any other hashed alias over that.
+ * any other hashed alias over that one unless @want_discon is set,
+ * in which case only return an IS_ROOT, DCACHE_DISCONNECTED alias.
*/
-static struct dentry *__d_find_alias(struct inode *inode)
+static struct dentry *__d_find_alias(struct inode *inode, int want_discon)
{
struct dentry *alias, *discon_alias;
@@ -705,7 +708,7 @@
if (IS_ROOT(alias) &&
(alias->d_flags & DCACHE_DISCONNECTED)) {
discon_alias = alias;
- } else {
+ } else if (!want_discon) {
__dget_dlock(alias);
spin_unlock(&alias->d_lock);
return alias;
@@ -736,7 +739,7 @@
if (!list_empty(&inode->i_dentry)) {
spin_lock(&inode->i_lock);
- de = __d_find_alias(inode);
+ de = __d_find_alias(inode, 0);
spin_unlock(&inode->i_lock);
}
return de;
@@ -1647,8 +1650,9 @@
if (inode && S_ISDIR(inode->i_mode)) {
spin_lock(&inode->i_lock);
- new = __d_find_any_alias(inode);
+ new = __d_find_alias(inode, 1);
if (new) {
+ BUG_ON(!(new->d_flags & DCACHE_DISCONNECTED));
spin_unlock(&inode->i_lock);
security_d_instantiate(new, inode);
d_move(new, dentry);
@@ -2478,7 +2482,7 @@
struct dentry *alias;
/* Does an aliased dentry already exist? */
- alias = __d_find_alias(inode);
+ alias = __d_find_alias(inode, 0);
if (alias) {
actual = alias;
write_seqlock(&rename_lock);
diff --git a/fs/exofs/sys.c b/fs/exofs/sys.c
index e32bc91..5a7b691 100644
--- a/fs/exofs/sys.c
+++ b/fs/exofs/sys.c
@@ -109,7 +109,7 @@
static struct kobj_type uuid_ktype = {
};
-void exofs_sysfs_dbg_print()
+void exofs_sysfs_dbg_print(void)
{
#ifdef CONFIG_EXOFS_DEBUG
struct kobject *k_name, *k_tmp;
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 99b6324..cee7812 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -90,8 +90,8 @@
* unusual file system layouts.
*/
if (ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), block_group)) {
- block_cluster = EXT4_B2C(sbi, (start -
- ext4_block_bitmap(sb, gdp)));
+ block_cluster = EXT4_B2C(sbi,
+ ext4_block_bitmap(sb, gdp) - start);
if (block_cluster < num_clusters)
block_cluster = -1;
else if (block_cluster == num_clusters) {
@@ -102,7 +102,7 @@
if (ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), block_group)) {
inode_cluster = EXT4_B2C(sbi,
- start - ext4_inode_bitmap(sb, gdp));
+ ext4_inode_bitmap(sb, gdp) - start);
if (inode_cluster < num_clusters)
inode_cluster = -1;
else if (inode_cluster == num_clusters) {
@@ -114,7 +114,7 @@
itbl_blk = ext4_inode_table(sb, gdp);
for (i = 0; i < sbi->s_itb_per_group; i++) {
if (ext4_block_in_group(sb, itbl_blk + i, block_group)) {
- c = EXT4_B2C(sbi, start - itbl_blk + i);
+ c = EXT4_B2C(sbi, itbl_blk + i - start);
if ((c < num_clusters) || (c == inode_cluster) ||
(c == block_cluster) || (c == itbl_cluster))
continue;
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 8ad112a..e34deac 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -123,7 +123,6 @@
else
ext4_clear_inode_flag(inode, i);
}
- ei->i_flags = flags;
ext4_set_inode_flags(inode);
inode->i_ctime = ext4_current_time(inode);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 8d2fb8c..41a3ccf 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -664,6 +664,7 @@
/* Wait for I_SYNC. This function drops i_lock... */
inode_sleep_on_writeback(inode);
/* Inode may be gone, start again */
+ spin_lock(&wb->list_lock);
continue;
}
inode->i_state |= I_SYNC;
diff --git a/fs/fuse/control.c b/fs/fuse/control.c
index 42593c5..03ff5b1 100644
--- a/fs/fuse/control.c
+++ b/fs/fuse/control.c
@@ -75,19 +75,13 @@
unsigned global_limit)
{
unsigned long t;
- char tmp[32];
unsigned limit = (1 << 16) - 1;
int err;
- if (*ppos || count >= sizeof(tmp) - 1)
+ if (*ppos)
return -EINVAL;
- if (copy_from_user(tmp, buf, count))
- return -EINVAL;
-
- tmp[count] = '\0';
-
- err = strict_strtoul(tmp, 0, &t);
+ err = kstrtoul_from_user(buf, count, 0, &t);
if (err)
return err;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index df5ac04..334e0b1 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -775,6 +775,8 @@
static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr,
struct kstat *stat)
{
+ unsigned int blkbits;
+
stat->dev = inode->i_sb->s_dev;
stat->ino = attr->ino;
stat->mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
@@ -790,7 +792,13 @@
stat->ctime.tv_nsec = attr->ctimensec;
stat->size = attr->size;
stat->blocks = attr->blocks;
- stat->blksize = (1 << inode->i_blkbits);
+
+ if (attr->blksize != 0)
+ blkbits = ilog2(attr->blksize);
+ else
+ blkbits = inode->i_sb->s_blocksize_bits;
+
+ stat->blksize = 1 << blkbits;
}
static int fuse_do_getattr(struct inode *inode, struct kstat *stat,
@@ -863,6 +871,7 @@
if (stat) {
generic_fillattr(inode, stat);
stat->mode = fi->orig_i_mode;
+ stat->ino = fi->orig_ino;
}
}
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 9562109..b321a68 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2173,6 +2173,44 @@
return ret;
}
+long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
+ loff_t length)
+{
+ struct fuse_file *ff = file->private_data;
+ struct fuse_conn *fc = ff->fc;
+ struct fuse_req *req;
+ struct fuse_fallocate_in inarg = {
+ .fh = ff->fh,
+ .offset = offset,
+ .length = length,
+ .mode = mode
+ };
+ int err;
+
+ if (fc->no_fallocate)
+ return -EOPNOTSUPP;
+
+ req = fuse_get_req(fc);
+ if (IS_ERR(req))
+ return PTR_ERR(req);
+
+ req->in.h.opcode = FUSE_FALLOCATE;
+ req->in.h.nodeid = ff->nodeid;
+ req->in.numargs = 1;
+ req->in.args[0].size = sizeof(inarg);
+ req->in.args[0].value = &inarg;
+ fuse_request_send(fc, req);
+ err = req->out.h.error;
+ if (err == -ENOSYS) {
+ fc->no_fallocate = 1;
+ err = -EOPNOTSUPP;
+ }
+ fuse_put_request(fc, req);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(fuse_file_fallocate);
+
static const struct file_operations fuse_file_operations = {
.llseek = fuse_file_llseek,
.read = do_sync_read,
@@ -2190,6 +2228,7 @@
.unlocked_ioctl = fuse_file_ioctl,
.compat_ioctl = fuse_file_compat_ioctl,
.poll = fuse_file_poll,
+ .fallocate = fuse_file_fallocate,
};
static const struct file_operations fuse_direct_io_file_operations = {
@@ -2206,6 +2245,7 @@
.unlocked_ioctl = fuse_file_ioctl,
.compat_ioctl = fuse_file_compat_ioctl,
.poll = fuse_file_poll,
+ .fallocate = fuse_file_fallocate,
/* no splice_read */
};
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 572cefc..771fb63 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -82,6 +82,9 @@
preserve the original mode */
umode_t orig_i_mode;
+ /** 64 bit inode number */
+ u64 orig_ino;
+
/** Version of last attribute change */
u64 attr_version;
@@ -478,6 +481,9 @@
/** Are BSD file locking primitives not implemented by fs? */
unsigned no_flock:1;
+ /** Is fallocate not implemented by fs? */
+ unsigned no_fallocate:1;
+
/** The number of requests waiting for completion */
atomic_t num_waiting;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 42678a3..1cd6165 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -91,6 +91,7 @@
fi->nlookup = 0;
fi->attr_version = 0;
fi->writectr = 0;
+ fi->orig_ino = 0;
INIT_LIST_HEAD(&fi->write_files);
INIT_LIST_HEAD(&fi->queued_writes);
INIT_LIST_HEAD(&fi->writepages);
@@ -139,6 +140,18 @@
return 0;
}
+/*
+ * ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down
+ * so that it will fit.
+ */
+static ino_t fuse_squash_ino(u64 ino64)
+{
+ ino_t ino = (ino_t) ino64;
+ if (sizeof(ino_t) < sizeof(u64))
+ ino ^= ino64 >> (sizeof(u64) - sizeof(ino_t)) * 8;
+ return ino;
+}
+
void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
u64 attr_valid)
{
@@ -148,7 +161,7 @@
fi->attr_version = ++fc->attr_version;
fi->i_time = attr_valid;
- inode->i_ino = attr->ino;
+ inode->i_ino = fuse_squash_ino(attr->ino);
inode->i_mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
set_nlink(inode, attr->nlink);
inode->i_uid = attr->uid;
@@ -174,6 +187,8 @@
fi->orig_i_mode = inode->i_mode;
if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
inode->i_mode &= ~S_ISVTX;
+
+ fi->orig_ino = attr->ino;
}
void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 616f41a..437195f 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1803,7 +1803,7 @@
rcu_read_lock();
file = fcheck_files(files, fd);
if (file) {
- unsigned i_mode, f_mode = file->f_mode;
+ unsigned f_mode = file->f_mode;
rcu_read_unlock();
put_files_struct(files);
@@ -1819,12 +1819,14 @@
inode->i_gid = GLOBAL_ROOT_GID;
}
- i_mode = S_IFLNK;
- if (f_mode & FMODE_READ)
- i_mode |= S_IRUSR | S_IXUSR;
- if (f_mode & FMODE_WRITE)
- i_mode |= S_IWUSR | S_IXUSR;
- inode->i_mode = i_mode;
+ if (S_ISLNK(inode->i_mode)) {
+ unsigned i_mode = S_IFLNK;
+ if (f_mode & FMODE_READ)
+ i_mode |= S_IRUSR | S_IXUSR;
+ if (f_mode & FMODE_WRITE)
+ i_mode |= S_IWUSR | S_IXUSR;
+ inode->i_mode = i_mode;
+ }
security_task_to_inode(task, inode);
put_task_struct(task);
@@ -1859,6 +1861,7 @@
ei = PROC_I(inode);
ei->fd = fd;
+ inode->i_mode = S_IFLNK;
inode->i_op = &proc_pid_link_inode_operations;
inode->i_size = 64;
ei->op.proc_get_link = proc_fd_link;
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 685a837..84a7e6f 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -2918,6 +2918,9 @@
struct dentry *dent;
struct ubifs_debug_info *d = c->dbg;
+ if (!IS_ENABLED(DEBUG_FS))
+ return 0;
+
n = snprintf(d->dfs_dir_name, UBIFS_DFS_DIR_LEN + 1, UBIFS_DFS_DIR_NAME,
c->vi.ubi_num, c->vi.vol_id);
if (n == UBIFS_DFS_DIR_LEN) {
@@ -3010,7 +3013,8 @@
*/
void dbg_debugfs_exit_fs(struct ubifs_info *c)
{
- debugfs_remove_recursive(c->dbg->dfs_dir);
+ if (IS_ENABLED(DEBUG_FS))
+ debugfs_remove_recursive(c->dbg->dfs_dir);
}
struct ubifs_global_debug_info ubifs_dbg;
@@ -3095,6 +3099,9 @@
const char *fname;
struct dentry *dent;
+ if (!IS_ENABLED(DEBUG_FS))
+ return 0;
+
fname = "ubifs";
dent = debugfs_create_dir(fname, NULL);
if (IS_ERR_OR_NULL(dent))
@@ -3159,7 +3166,8 @@
*/
void dbg_debugfs_exit(void)
{
- debugfs_remove_recursive(dfs_rootdir);
+ if (IS_ENABLED(DEBUG_FS))
+ debugfs_remove_recursive(dfs_rootdir);
}
/**
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index b0d6282..9e6e1c6 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -440,8 +440,8 @@
#else /* CONFIG_ACPI */
-static int register_acpi_bus_type(struct acpi_bus_type *bus) { return 0; }
-static int unregister_acpi_bus_type(struct acpi_bus_type *bus) { return 0; }
+static inline int register_acpi_bus_type(void *bus) { return 0; }
+static inline int unregister_acpi_bus_type(void *bus) { return 0; }
#endif /* CONFIG_ACPI */
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 2520a6e..9f02005 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -2,6 +2,7 @@
#define _ASM_GENERIC_BUG_H
#include <linux/compiler.h>
+#include <linux/kernel.h>
#ifdef CONFIG_BUG
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 73e4560..bac55c2 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -54,7 +54,7 @@
struct drm_object_properties *properties;
};
-#define DRM_OBJECT_MAX_PROPERTY 16
+#define DRM_OBJECT_MAX_PROPERTY 24
struct drm_object_properties {
int count;
uint32_t ids[DRM_OBJECT_MAX_PROPERTY];
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 58d0bda..81368ab 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -181,6 +181,7 @@
{0x1002, 0x6747, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6748, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6749, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x674A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6750, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6751, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6758, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
@@ -198,6 +199,7 @@
{0x1002, 0x6767, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6768, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6770, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6771, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6772, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6778, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6779, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
@@ -229,10 +231,11 @@
{0x1002, 0x6827, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6828, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6829, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x682B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x682D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x682F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
- {0x1002, 0x6830, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
- {0x1002, 0x6831, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6830, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6831, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6837, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6838, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6839, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
@@ -531,6 +534,7 @@
{0x1002, 0x9645, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
{0x1002, 0x9648, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
+ {0x1002, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
{0x1002, 0x964a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x964b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x964c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
@@ -550,6 +554,7 @@
{0x1002, 0x9807, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9808, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9809, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x980A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
@@ -561,11 +566,19 @@
{0x1002, 0x9909, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x990A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x990F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x9910, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x9913, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x9917, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x9918, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x9919, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9990, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9991, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9992, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9993, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9994, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x99A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x99A2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x99A4, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0, 0, 0}
#define r128_PCI_IDS \
diff --git a/include/drm/exynos_drm.h b/include/drm/exynos_drm.h
index b6d7ce9..6873358 100644
--- a/include/drm/exynos_drm.h
+++ b/include/drm/exynos_drm.h
@@ -64,6 +64,7 @@
* A structure for mapping buffer.
*
* @handle: a handle to gem object created.
+ * @pad: just padding to be 64-bit aligned.
* @size: memory size to be mapped.
* @mapped: having user virtual address mmaped.
* - this variable would be filled by exynos gem module
@@ -72,7 +73,8 @@
*/
struct drm_exynos_gem_mmap {
unsigned int handle;
- unsigned int size;
+ unsigned int pad;
+ uint64_t size;
uint64_t mapped;
};
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index 81e803e..acba8943 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -132,6 +132,7 @@
struct clock_event_device *evt);
extern void clockevents_register_device(struct clock_event_device *dev);
+extern void clockevents_config(struct clock_event_device *dev, u32 freq);
extern void clockevents_config_and_register(struct clock_event_device *dev,
u32 freq, unsigned long min_delta,
unsigned long max_delta);
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index e988037..51a90b7 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -1,8 +1,6 @@
#ifndef _LINUX_COMPACTION_H
#define _LINUX_COMPACTION_H
-#include <linux/node.h>
-
/* Return values for compact_zone() and try_to_compact_pages() */
/* compaction didn't start as it was not possible or direct reclaim was more suitable */
#define COMPACT_SKIPPED 0
@@ -13,23 +11,6 @@
/* The full zone was compacted */
#define COMPACT_COMPLETE 3
-/*
- * compaction supports three modes
- *
- * COMPACT_ASYNC_MOVABLE uses asynchronous migration and only scans
- * MIGRATE_MOVABLE pageblocks as migration sources and targets.
- * COMPACT_ASYNC_UNMOVABLE uses asynchronous migration and only scans
- * MIGRATE_MOVABLE pageblocks as migration sources.
- * MIGRATE_UNMOVABLE pageblocks are scanned as potential migration
- * targets and convers them to MIGRATE_MOVABLE if possible
- * COMPACT_SYNC uses synchronous migration and scans all pageblocks
- */
-enum compact_mode {
- COMPACT_ASYNC_MOVABLE,
- COMPACT_ASYNC_UNMOVABLE,
- COMPACT_SYNC,
-};
-
#ifdef CONFIG_COMPACTION
extern int sysctl_compact_memory;
extern int sysctl_compaction_handler(struct ctl_table *table, int write,
diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h
new file mode 100644
index 0000000..0e4e2ee
--- /dev/null
+++ b/include/linux/frontswap.h
@@ -0,0 +1,127 @@
+#ifndef _LINUX_FRONTSWAP_H
+#define _LINUX_FRONTSWAP_H
+
+#include <linux/swap.h>
+#include <linux/mm.h>
+#include <linux/bitops.h>
+
+struct frontswap_ops {
+ void (*init)(unsigned);
+ int (*store)(unsigned, pgoff_t, struct page *);
+ int (*load)(unsigned, pgoff_t, struct page *);
+ void (*invalidate_page)(unsigned, pgoff_t);
+ void (*invalidate_area)(unsigned);
+};
+
+extern bool frontswap_enabled;
+extern struct frontswap_ops
+ frontswap_register_ops(struct frontswap_ops *ops);
+extern void frontswap_shrink(unsigned long);
+extern unsigned long frontswap_curr_pages(void);
+extern void frontswap_writethrough(bool);
+
+extern void __frontswap_init(unsigned type);
+extern int __frontswap_store(struct page *page);
+extern int __frontswap_load(struct page *page);
+extern void __frontswap_invalidate_page(unsigned, pgoff_t);
+extern void __frontswap_invalidate_area(unsigned);
+
+#ifdef CONFIG_FRONTSWAP
+
+static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset)
+{
+ bool ret = false;
+
+ if (frontswap_enabled && sis->frontswap_map)
+ ret = test_bit(offset, sis->frontswap_map);
+ return ret;
+}
+
+static inline void frontswap_set(struct swap_info_struct *sis, pgoff_t offset)
+{
+ if (frontswap_enabled && sis->frontswap_map)
+ set_bit(offset, sis->frontswap_map);
+}
+
+static inline void frontswap_clear(struct swap_info_struct *sis, pgoff_t offset)
+{
+ if (frontswap_enabled && sis->frontswap_map)
+ clear_bit(offset, sis->frontswap_map);
+}
+
+static inline void frontswap_map_set(struct swap_info_struct *p,
+ unsigned long *map)
+{
+ p->frontswap_map = map;
+}
+
+static inline unsigned long *frontswap_map_get(struct swap_info_struct *p)
+{
+ return p->frontswap_map;
+}
+#else
+/* all inline routines become no-ops and all externs are ignored */
+
+#define frontswap_enabled (0)
+
+static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset)
+{
+ return false;
+}
+
+static inline void frontswap_set(struct swap_info_struct *sis, pgoff_t offset)
+{
+}
+
+static inline void frontswap_clear(struct swap_info_struct *sis, pgoff_t offset)
+{
+}
+
+static inline void frontswap_map_set(struct swap_info_struct *p,
+ unsigned long *map)
+{
+}
+
+static inline unsigned long *frontswap_map_get(struct swap_info_struct *p)
+{
+ return NULL;
+}
+#endif
+
+static inline int frontswap_store(struct page *page)
+{
+ int ret = -1;
+
+ if (frontswap_enabled)
+ ret = __frontswap_store(page);
+ return ret;
+}
+
+static inline int frontswap_load(struct page *page)
+{
+ int ret = -1;
+
+ if (frontswap_enabled)
+ ret = __frontswap_load(page);
+ return ret;
+}
+
+static inline void frontswap_invalidate_page(unsigned type, pgoff_t offset)
+{
+ if (frontswap_enabled)
+ __frontswap_invalidate_page(type, offset);
+}
+
+static inline void frontswap_invalidate_area(unsigned type)
+{
+ if (frontswap_enabled)
+ __frontswap_invalidate_area(type);
+}
+
+static inline void frontswap_init(unsigned type)
+{
+ if (frontswap_enabled)
+ __frontswap_init(type);
+}
+
+#endif /* _LINUX_FRONTSWAP_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 51978ed..17fd887 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -802,13 +802,14 @@
unsigned int __i_nlink;
};
dev_t i_rdev;
+ loff_t i_size;
struct timespec i_atime;
struct timespec i_mtime;
struct timespec i_ctime;
spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
unsigned short i_bytes;
+ unsigned int i_blkbits;
blkcnt_t i_blocks;
- loff_t i_size;
#ifdef __NEED_I_SIZE_ORDERED
seqcount_t i_size_seqcount;
@@ -828,9 +829,8 @@
struct list_head i_dentry;
struct rcu_head i_rcu;
};
- atomic_t i_count;
- unsigned int i_blkbits;
u64 i_version;
+ atomic_t i_count;
atomic_t i_dio_count;
atomic_t i_writecount;
const struct file_operations *i_fop; /* former ->i_op->default_file_ops */
diff --git a/include/linux/fuse.h b/include/linux/fuse.h
index 8f2ab8f..9303348 100644
--- a/include/linux/fuse.h
+++ b/include/linux/fuse.h
@@ -54,6 +54,9 @@
* 7.18
* - add FUSE_IOCTL_DIR flag
* - add FUSE_NOTIFY_DELETE
+ *
+ * 7.19
+ * - add FUSE_FALLOCATE
*/
#ifndef _LINUX_FUSE_H
@@ -85,7 +88,7 @@
#define FUSE_KERNEL_VERSION 7
/** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 18
+#define FUSE_KERNEL_MINOR_VERSION 19
/** The node ID of the root inode */
#define FUSE_ROOT_ID 1
@@ -278,6 +281,7 @@
FUSE_POLL = 40,
FUSE_NOTIFY_REPLY = 41,
FUSE_BATCH_FORGET = 42,
+ FUSE_FALLOCATE = 43,
/* CUSE specific operations */
CUSE_INIT = 4096,
@@ -571,6 +575,14 @@
__u64 kh;
};
+struct fuse_fallocate_in {
+ __u64 fh;
+ __u64 offset;
+ __u64 length;
+ __u32 mode;
+ __u32 padding;
+};
+
struct fuse_in_header {
__u32 len;
__u32 opcode;
diff --git a/include/linux/i2c-mux-pinctrl.h b/include/linux/i2c-mux-pinctrl.h
new file mode 100644
index 0000000..a65c864
--- /dev/null
+++ b/include/linux/i2c-mux-pinctrl.h
@@ -0,0 +1,41 @@
+/*
+ * i2c-mux-pinctrl platform data
+ *
+ * Copyright (c) 2012, NVIDIA CORPORATION. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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 _LINUX_I2C_MUX_PINCTRL_H
+#define _LINUX_I2C_MUX_PINCTRL_H
+
+/**
+ * struct i2c_mux_pinctrl_platform_data - Platform data for i2c-mux-pinctrl
+ * @parent_bus_num: Parent I2C bus number
+ * @base_bus_num: Base I2C bus number for the child busses. 0 for dynamic.
+ * @bus_count: Number of child busses. Also the number of elements in
+ * @pinctrl_states
+ * @pinctrl_states: The names of the pinctrl state to select for each child bus
+ * @pinctrl_state_idle: The pinctrl state to select when no child bus is being
+ * accessed. If NULL, the most recently used pinctrl state will be left
+ * selected.
+ */
+struct i2c_mux_pinctrl_platform_data {
+ int parent_bus_num;
+ int base_bus_num;
+ int bus_count;
+ const char **pinctrl_states;
+ const char *pinctrl_state_idle;
+};
+
+#endif
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index e4baff5..9e65eff 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -149,6 +149,7 @@
.normal_prio = MAX_PRIO-20, \
.policy = SCHED_NORMAL, \
.cpus_allowed = CPU_MASK_ALL, \
+ .nr_cpus_allowed= NR_CPUS, \
.mm = NULL, \
.active_mm = &init_mm, \
.se = { \
@@ -157,7 +158,6 @@
.rt = { \
.run_list = LIST_HEAD_INIT(tsk.rt.run_list), \
.time_slice = RR_TIMESLICE, \
- .nr_cpus_allowed = NR_CPUS, \
}, \
.tasks = LIST_HEAD_INIT(tsk.tasks), \
INIT_PUSHABLE_TASKS(tsk) \
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 1b14d25..d6a5806 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -128,7 +128,7 @@
* The ops can have NULL set or get functions.
*/
#define module_param_cb(name, ops, arg, perm) \
- __module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, 0)
+ __module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, -1)
/**
* <level>_param_cb - general callback for a module/cmdline parameter
@@ -192,7 +192,7 @@
{ (void *)set, (void *)get }; \
__module_param_call(MODULE_PARAM_PREFIX, \
name, &__param_ops_##name, arg, \
- (perm) + sizeof(__check_old_set_param(set))*0, 0)
+ (perm) + sizeof(__check_old_set_param(set))*0, -1)
/* We don't get oldget: it's often a new-style param_get_uint, etc. */
static inline int
@@ -272,7 +272,7 @@
*/
#define core_param(name, var, type, perm) \
param_check_##type(name, &(var)); \
- __module_param_call("", name, ¶m_ops_##type, &var, perm, 0)
+ __module_param_call("", name, ¶m_ops_##type, &var, perm, -1)
#endif /* !MODULE */
/**
@@ -290,7 +290,7 @@
= { len, string }; \
__module_param_call(MODULE_PARAM_PREFIX, name, \
¶m_ops_string, \
- .str = &__param_string_##name, perm, 0); \
+ .str = &__param_string_##name, perm, -1); \
__MODULE_PARM_TYPE(name, "string")
/**
@@ -432,7 +432,7 @@
__module_param_call(MODULE_PARAM_PREFIX, name, \
¶m_array_ops, \
.arr = &__param_arr_##name, \
- perm, 0); \
+ perm, -1); \
__MODULE_PARM_TYPE(name, "array of " #type)
extern struct kernel_param_ops param_array_ops;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a0b84e3..2c2ecea 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1627,6 +1627,7 @@
extern int dev_open(struct net_device *dev);
extern int dev_close(struct net_device *dev);
extern void dev_disable_lro(struct net_device *dev);
+extern int dev_loopback_xmit(struct sk_buff *newskb);
extern int dev_queue_xmit(struct sk_buff *skb);
extern int register_netdevice(struct net_device *dev);
extern void unregister_netdevice_queue(struct net_device *dev,
diff --git a/include/linux/netfilter/xt_HMARK.h b/include/linux/netfilter/xt_HMARK.h
index abb1650..826fc58 100644
--- a/include/linux/netfilter/xt_HMARK.h
+++ b/include/linux/netfilter/xt_HMARK.h
@@ -27,7 +27,12 @@
__u16 src;
__u16 dst;
} p16;
+ struct {
+ __be16 src;
+ __be16 dst;
+ } b16;
__u32 v32;
+ __be32 b32;
};
struct xt_hmark_info {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f325786..45db49f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -555,6 +555,8 @@
PERF_RECORD_MAX, /* non-ABI */
};
+#define PERF_MAX_STACK_DEPTH 127
+
enum perf_callchain_context {
PERF_CONTEXT_HV = (__u64)-32,
PERF_CONTEXT_KERNEL = (__u64)-128,
@@ -609,8 +611,6 @@
#include <linux/sysfs.h>
#include <asm/local.h>
-#define PERF_MAX_STACK_DEPTH 255
-
struct perf_callchain_entry {
__u64 nr;
__u64 ip[PERF_MAX_STACK_DEPTH];
diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index 711e0a3..3988012 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -127,8 +127,8 @@
#define PR_SET_PTRACER 0x59616d61
# define PR_SET_PTRACER_ANY ((unsigned long)-1)
-#define PR_SET_CHILD_SUBREAPER 36
-#define PR_GET_CHILD_SUBREAPER 37
+#define PR_SET_CHILD_SUBREAPER 36
+#define PR_GET_CHILD_SUBREAPER 37
/*
* If no_new_privs is set, then operations that grant new privileges (i.e.
@@ -142,7 +142,9 @@
* asking selinux for a specific new context (e.g. with runcon) will result
* in execve returning -EPERM.
*/
-#define PR_SET_NO_NEW_PRIVS 38
-#define PR_GET_NO_NEW_PRIVS 39
+#define PR_SET_NO_NEW_PRIVS 38
+#define PR_GET_NO_NEW_PRIVS 39
+
+#define PR_GET_TID_ADDRESS 40
#endif /* _LINUX_PRCTL_H */
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 0d04cd6..ffc444c 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -368,8 +368,11 @@
iter->index++;
if (likely(*slot))
return slot;
- if (flags & RADIX_TREE_ITER_CONTIG)
+ if (flags & RADIX_TREE_ITER_CONTIG) {
+ /* forbid switching to the next chunk */
+ iter->next_index = 0;
break;
+ }
}
}
return NULL;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f34437e..4059c0f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -145,6 +145,7 @@
extern void calc_global_load(unsigned long ticks);
+extern void update_cpu_load_nohz(void);
extern unsigned long get_parent_ip(unsigned long addr);
@@ -438,6 +439,7 @@
/* leave room for more dump flags */
#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */
#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */
+#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */
#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
@@ -875,6 +877,8 @@
* Number of busy cpus in this group.
*/
atomic_t nr_busy_cpus;
+
+ unsigned long cpumask[0]; /* iteration mask */
};
struct sched_group {
@@ -899,6 +903,15 @@
return to_cpumask(sg->cpumask);
}
+/*
+ * cpumask masking which cpus in the group are allowed to iterate up the domain
+ * tree.
+ */
+static inline struct cpumask *sched_group_mask(struct sched_group *sg)
+{
+ return to_cpumask(sg->sgp->cpumask);
+}
+
/**
* group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
* @group: The group whose first cpu is to be returned.
@@ -1187,7 +1200,6 @@
struct list_head run_list;
unsigned long timeout;
unsigned int time_slice;
- int nr_cpus_allowed;
struct sched_rt_entity *back;
#ifdef CONFIG_RT_GROUP_SCHED
@@ -1252,6 +1264,7 @@
#endif
unsigned int policy;
+ int nr_cpus_allowed;
cpumask_t cpus_allowed;
#ifdef CONFIG_PREEMPT_RCU
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b534a1b..642cb73 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -225,14 +225,11 @@
/* device driver is going to provide hardware time stamp */
SKBTX_IN_PROGRESS = 1 << 2,
- /* ensure the originating sk reference is available on driver level */
- SKBTX_DRV_NEEDS_SK_REF = 1 << 3,
-
/* device driver supports TX zero-copy buffers */
- SKBTX_DEV_ZEROCOPY = 1 << 4,
+ SKBTX_DEV_ZEROCOPY = 1 << 3,
/* generate wifi status information (where possible) */
- SKBTX_WIFI_STATUS = 1 << 5,
+ SKBTX_WIFI_STATUS = 1 << 4,
};
/*
diff --git a/include/linux/swap.h b/include/linux/swap.h
index b666193..c84ec68 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -197,6 +197,10 @@
struct block_device *bdev; /* swap device or bdev of swap file */
struct file *swap_file; /* seldom referenced */
unsigned int old_block_size; /* seldom referenced */
+#ifdef CONFIG_FRONTSWAP
+ unsigned long *frontswap_map; /* frontswap in-use, one bit per page */
+ atomic_t frontswap_pages; /* frontswap pages in-use counter */
+#endif
};
struct swap_list_t {
diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h
new file mode 100644
index 0000000..e282624
--- /dev/null
+++ b/include/linux/swapfile.h
@@ -0,0 +1,13 @@
+#ifndef _LINUX_SWAPFILE_H
+#define _LINUX_SWAPFILE_H
+
+/*
+ * these were static in swapfile.c but frontswap.c needs them and we don't
+ * want to expose them to the dozens of source files that include swap.h
+ */
+extern spinlock_t swap_lock;
+extern struct swap_list_t swap_list;
+extern struct swap_info_struct *swap_info[];
+extern int try_to_unuse(unsigned int, bool, unsigned long);
+
+#endif /* _LINUX_SWAPFILE_H */
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 23e8234..7d3bced 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -69,16 +69,16 @@
#define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3])
enum {
- TCP_FLAG_CWR = __cpu_to_be32(0x00800000),
- TCP_FLAG_ECE = __cpu_to_be32(0x00400000),
- TCP_FLAG_URG = __cpu_to_be32(0x00200000),
- TCP_FLAG_ACK = __cpu_to_be32(0x00100000),
- TCP_FLAG_PSH = __cpu_to_be32(0x00080000),
- TCP_FLAG_RST = __cpu_to_be32(0x00040000),
- TCP_FLAG_SYN = __cpu_to_be32(0x00020000),
- TCP_FLAG_FIN = __cpu_to_be32(0x00010000),
- TCP_RESERVED_BITS = __cpu_to_be32(0x0F000000),
- TCP_DATA_OFFSET = __cpu_to_be32(0xF0000000)
+ TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000),
+ TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000),
+ TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000),
+ TCP_FLAG_ACK = __constant_cpu_to_be32(0x00100000),
+ TCP_FLAG_PSH = __constant_cpu_to_be32(0x00080000),
+ TCP_FLAG_RST = __constant_cpu_to_be32(0x00040000),
+ TCP_FLAG_SYN = __constant_cpu_to_be32(0x00020000),
+ TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000),
+ TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000),
+ TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000)
};
/*
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 76f4396..f87cf62 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -66,9 +66,8 @@
# define EVENT_STS_SPLIT 3
# define EVENT_LINK_RESET 4
# define EVENT_RX_PAUSED 5
-# define EVENT_DEV_WAKING 6
-# define EVENT_DEV_ASLEEP 7
-# define EVENT_DEV_OPEN 8
+# define EVENT_DEV_ASLEEP 6
+# define EVENT_DEV_OPEN 7
};
static inline struct usb_driver *driver_of(struct usb_interface *intf)
diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h
index b455c7c..60da41f 100644
--- a/include/linux/vga_switcheroo.h
+++ b/include/linux/vga_switcheroo.h
@@ -12,6 +12,9 @@
enum vga_switcheroo_state {
VGA_SWITCHEROO_OFF,
VGA_SWITCHEROO_ON,
+ /* below are referred only from vga_switcheroo_get_client_state() */
+ VGA_SWITCHEROO_INIT,
+ VGA_SWITCHEROO_NOT_FOUND,
};
enum vga_switcheroo_client_id {
@@ -50,6 +53,8 @@
int vga_switcheroo_process_delayed_switch(void);
+int vga_switcheroo_get_client_state(struct pci_dev *dev);
+
#else
static inline void vga_switcheroo_unregister_client(struct pci_dev *dev) {}
@@ -62,5 +67,7 @@
int id, bool active) { return 0; }
static inline void vga_switcheroo_unregister_handler(void) {}
static inline int vga_switcheroo_process_delayed_switch(void) { return 0; }
+static inline int vga_switcheroo_get_client_state(struct pci_dev *dev) { return VGA_SWITCHEROO_ON; }
+
#endif
diff --git a/include/net/dst.h b/include/net/dst.h
index 8197ead..f0bf3b8 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -48,8 +48,8 @@
#else
void *__pad1;
#endif
- int (*input)(struct sk_buff*);
- int (*output)(struct sk_buff*);
+ int (*input)(struct sk_buff *);
+ int (*output)(struct sk_buff *);
int flags;
#define DST_HOST 0x0001
@@ -241,7 +241,7 @@
return dst_metric(dst, RTAX_LOCK) & (1<<metric);
}
-static inline void dst_hold(struct dst_entry * dst)
+static inline void dst_hold(struct dst_entry *dst)
{
/*
* If your kernel compilation stops here, please check
@@ -264,8 +264,7 @@
dst->lastuse = time;
}
-static inline
-struct dst_entry * dst_clone(struct dst_entry * dst)
+static inline struct dst_entry *dst_clone(struct dst_entry *dst)
{
if (dst)
atomic_inc(&dst->__refcnt);
@@ -371,12 +370,12 @@
}
extern int dst_discard(struct sk_buff *skb);
-extern void *dst_alloc(struct dst_ops * ops, struct net_device *dev,
+extern void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
int initial_ref, int initial_obsolete, int flags);
-extern void __dst_free(struct dst_entry * dst);
-extern struct dst_entry *dst_destroy(struct dst_entry * dst);
+extern void __dst_free(struct dst_entry *dst);
+extern struct dst_entry *dst_destroy(struct dst_entry *dst);
-static inline void dst_free(struct dst_entry * dst)
+static inline void dst_free(struct dst_entry *dst)
{
if (dst->obsolete > 1)
return;
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index a2cda24..58cb3fc 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -140,10 +140,10 @@
u8 *lladdr,
int on_link);
-extern void rt6_pmtu_discovery(const struct in6_addr *daddr,
- const struct in6_addr *saddr,
- struct net_device *dev,
- u32 pmtu);
+extern void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
+ int oif, u32 mark);
+extern void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk,
+ __be32 mtu);
struct netlink_callback;
diff --git a/include/net/route.h b/include/net/route.h
index 2bfbc93..47eb25a 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -164,9 +164,9 @@
{
struct flowi4 fl4 = {
.flowi4_oif = oif,
+ .flowi4_tos = tos,
.daddr = daddr,
.saddr = saddr,
- .flowi4_tos = tos,
};
return ip_route_output_key(net, &fl4);
}
@@ -215,7 +215,10 @@
return ip_route_input_common(skb, dst, src, tos, devin, true);
}
-extern void ip_rt_send_redirect(struct sk_buff *skb);
+extern void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
+ int oif, u32 mark, u8 protocol, int flow_flags);
+extern void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu);
+extern void ip_rt_send_redirect(struct sk_buff *skb);
extern unsigned int inet_addr_type(struct net *net, __be32 addr);
extern unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 55ce96b..9d7d54a 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -220,13 +220,16 @@
struct qdisc_skb_cb {
unsigned int pkt_len;
- unsigned char data[24];
+ u16 bond_queue_mapping;
+ u16 _pad;
+ unsigned char data[20];
};
static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
{
struct qdisc_skb_cb *qcb;
- BUILD_BUG_ON(sizeof(skb->cb) < sizeof(unsigned int) + sz);
+
+ BUILD_BUG_ON(sizeof(skb->cb) < offsetof(struct qdisc_skb_cb, data) + sz);
BUILD_BUG_ON(sizeof(qcb->data) < sz);
}
diff --git a/init/main.c b/init/main.c
index 1ca6b32..b5cc0a7 100644
--- a/init/main.c
+++ b/init/main.c
@@ -508,7 +508,7 @@
parse_early_param();
parse_args("Booting kernel", static_command_line, __start___param,
__stop___param - __start___param,
- 0, 0, &unknown_bootoption);
+ -1, -1, &unknown_bootoption);
jump_label_init();
@@ -755,13 +755,8 @@
{
int level;
- for (level = 0; level < ARRAY_SIZE(initcall_levels) - 1; level++) {
- pr_info("initlevel:%d=%s, %d registered initcalls\n",
- level, initcall_level_names[level],
- (int) (initcall_levels[level+1]
- - initcall_levels[level]));
+ for (level = 0; level < ARRAY_SIZE(initcall_levels) - 1; level++)
do_initcall_level(level);
- }
}
/*
diff --git a/ipc/shm.c b/ipc/shm.c
index 5e2cbfd..41c1285 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -393,6 +393,16 @@
return sfd->file->f_op->fsync(sfd->file, start, end, datasync);
}
+static long shm_fallocate(struct file *file, int mode, loff_t offset,
+ loff_t len)
+{
+ struct shm_file_data *sfd = shm_file_data(file);
+
+ if (!sfd->file->f_op->fallocate)
+ return -EOPNOTSUPP;
+ return sfd->file->f_op->fallocate(file, mode, offset, len);
+}
+
static unsigned long shm_get_unmapped_area(struct file *file,
unsigned long addr, unsigned long len, unsigned long pgoff,
unsigned long flags)
@@ -410,6 +420,7 @@
.get_unmapped_area = shm_get_unmapped_area,
#endif
.llseek = noop_llseek,
+ .fallocate = shm_fallocate,
};
static const struct file_operations shm_file_operations_huge = {
@@ -418,6 +429,7 @@
.release = shm_release,
.get_unmapped_area = shm_get_unmapped_area,
.llseek = noop_llseek,
+ .fallocate = shm_fallocate,
};
int is_file_shm_hugepages(struct file *file)
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 0f3527d..72fcd30 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -896,10 +896,13 @@
mutex_unlock(&cgroup_mutex);
/*
- * Drop the active superblock reference that we took when we
- * created the cgroup
+ * We want to drop the active superblock reference from the
+ * cgroup creation after all the dentry refs are gone -
+ * kill_sb gets mighty unhappy otherwise. Mark
+ * dentry->d_fsdata with cgroup_diput() to tell
+ * cgroup_d_release() to call deactivate_super().
*/
- deactivate_super(cgrp->root->sb);
+ dentry->d_fsdata = cgroup_diput;
/*
* if we're getting rid of the cgroup, refcount should ensure
@@ -925,6 +928,13 @@
return 1;
}
+static void cgroup_d_release(struct dentry *dentry)
+{
+ /* did cgroup_diput() tell me to deactivate super? */
+ if (dentry->d_fsdata == cgroup_diput)
+ deactivate_super(dentry->d_sb);
+}
+
static void remove_dir(struct dentry *d)
{
struct dentry *parent = dget(d->d_parent);
@@ -1532,6 +1542,7 @@
static const struct dentry_operations cgroup_dops = {
.d_iput = cgroup_diput,
.d_delete = cgroup_delete,
+ .d_release = cgroup_d_release,
};
struct inode *inode =
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5b06cbb..f85c015 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3181,7 +3181,6 @@
event = event->group_leader;
perf_event_for_each_child(event, func);
- func(event);
list_for_each_entry(sibling, &event->sibling_list, group_entry)
perf_event_for_each_child(sibling, func);
mutex_unlock(&ctx->mutex);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index fc275e4..eebd6d5 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -275,8 +275,10 @@
kstat_incr_irqs_this_cpu(irq, desc);
action = desc->action;
- if (unlikely(!action || irqd_irq_disabled(&desc->irq_data)))
+ if (unlikely(!action || irqd_irq_disabled(&desc->irq_data))) {
+ desc->istate |= IRQS_PENDING;
goto out_unlock;
+ }
irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
raw_spin_unlock_irq(&desc->lock);
@@ -324,8 +326,10 @@
desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
kstat_incr_irqs_this_cpu(irq, desc);
- if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data)))
+ if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
+ desc->istate |= IRQS_PENDING;
goto out_unlock;
+ }
handle_irq_event(desc);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 8e5c56b..001fa5b 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -101,6 +101,9 @@
extern void irq_set_thread_affinity(struct irq_desc *desc);
+extern int irq_do_set_affinity(struct irq_data *data,
+ const struct cpumask *dest, bool force);
+
/* Inline functions for support of irq chips on slow busses */
static inline void chip_bus_lock(struct irq_desc *desc)
{
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index ea0c6c2..8c54823 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -142,6 +142,25 @@
irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { }
#endif
+int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
+ bool force)
+{
+ struct irq_desc *desc = irq_data_to_desc(data);
+ struct irq_chip *chip = irq_data_get_irq_chip(data);
+ int ret;
+
+ ret = chip->irq_set_affinity(data, mask, false);
+ switch (ret) {
+ case IRQ_SET_MASK_OK:
+ cpumask_copy(data->affinity, mask);
+ case IRQ_SET_MASK_OK_NOCOPY:
+ irq_set_thread_affinity(desc);
+ ret = 0;
+ }
+
+ return ret;
+}
+
int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
{
struct irq_chip *chip = irq_data_get_irq_chip(data);
@@ -152,14 +171,7 @@
return -EINVAL;
if (irq_can_move_pcntxt(data)) {
- ret = chip->irq_set_affinity(data, mask, false);
- switch (ret) {
- case IRQ_SET_MASK_OK:
- cpumask_copy(data->affinity, mask);
- case IRQ_SET_MASK_OK_NOCOPY:
- irq_set_thread_affinity(desc);
- ret = 0;
- }
+ ret = irq_do_set_affinity(data, mask, false);
} else {
irqd_set_move_pending(data);
irq_copy_pending(desc, mask);
@@ -283,9 +295,8 @@
static int
setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
{
- struct irq_chip *chip = irq_desc_get_chip(desc);
struct cpumask *set = irq_default_affinity;
- int ret, node = desc->irq_data.node;
+ int node = desc->irq_data.node;
/* Excludes PER_CPU and NO_BALANCE interrupts */
if (!irq_can_set_affinity(irq))
@@ -311,13 +322,7 @@
if (cpumask_intersects(mask, nodemask))
cpumask_and(mask, mask, nodemask);
}
- ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
- switch (ret) {
- case IRQ_SET_MASK_OK:
- cpumask_copy(desc->irq_data.affinity, mask);
- case IRQ_SET_MASK_OK_NOCOPY:
- irq_set_thread_affinity(desc);
- }
+ irq_do_set_affinity(&desc->irq_data, mask, false);
return 0;
}
#else
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index c3c8975..ca3f4aa 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -42,17 +42,8 @@
* For correct operation this depends on the caller
* masking the irqs.
*/
- if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
- < nr_cpu_ids)) {
- int ret = chip->irq_set_affinity(&desc->irq_data,
- desc->pending_mask, false);
- switch (ret) {
- case IRQ_SET_MASK_OK:
- cpumask_copy(desc->irq_data.affinity, desc->pending_mask);
- case IRQ_SET_MASK_OK_NOCOPY:
- irq_set_thread_affinity(desc);
- }
- }
+ if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)
+ irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false);
cpumask_clear(desc->pending_mask);
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 39eb601..d5594a4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -142,9 +142,8 @@
#define SCHED_FEAT(name, enabled) \
#name ,
-static __read_mostly char *sched_feat_names[] = {
+static const char * const sched_feat_names[] = {
#include "features.h"
- NULL
};
#undef SCHED_FEAT
@@ -2517,25 +2516,32 @@
sched_avg_update(this_rq);
}
+#ifdef CONFIG_NO_HZ
+/*
+ * There is no sane way to deal with nohz on smp when using jiffies because the
+ * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
+ * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
+ *
+ * Therefore we cannot use the delta approach from the regular tick since that
+ * would seriously skew the load calculation. However we'll make do for those
+ * updates happening while idle (nohz_idle_balance) or coming out of idle
+ * (tick_nohz_idle_exit).
+ *
+ * This means we might still be one tick off for nohz periods.
+ */
+
/*
* Called from nohz_idle_balance() to update the load ratings before doing the
* idle balance.
*/
void update_idle_cpu_load(struct rq *this_rq)
{
- unsigned long curr_jiffies = jiffies;
+ unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
unsigned long load = this_rq->load.weight;
unsigned long pending_updates;
/*
- * Bloody broken means of dealing with nohz, but better than nothing..
- * jiffies is updated by one cpu, another cpu can drift wrt the jiffy
- * update and see 0 difference the one time and 2 the next, even though
- * we ticked at roughtly the same rate.
- *
- * Hence we only use this from nohz_idle_balance() and skip this
- * nonsense when called from the scheduler_tick() since that's
- * guaranteed a stable rate.
+ * bail if there's load or we're actually up-to-date.
*/
if (load || curr_jiffies == this_rq->last_load_update_tick)
return;
@@ -2547,12 +2553,38 @@
}
/*
+ * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
+ */
+void update_cpu_load_nohz(void)
+{
+ struct rq *this_rq = this_rq();
+ unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
+ unsigned long pending_updates;
+
+ if (curr_jiffies == this_rq->last_load_update_tick)
+ return;
+
+ raw_spin_lock(&this_rq->lock);
+ pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+ if (pending_updates) {
+ this_rq->last_load_update_tick = curr_jiffies;
+ /*
+ * We were idle, this means load 0, the current load might be
+ * !0 due to remote wakeups and the sort.
+ */
+ __update_cpu_load(this_rq, 0, pending_updates);
+ }
+ raw_spin_unlock(&this_rq->lock);
+}
+#endif /* CONFIG_NO_HZ */
+
+/*
* Called from scheduler_tick()
*/
static void update_cpu_load_active(struct rq *this_rq)
{
/*
- * See the mess in update_idle_cpu_load().
+ * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
*/
this_rq->last_load_update_tick = jiffies;
__update_cpu_load(this_rq, this_rq->load.weight, 1);
@@ -4982,7 +5014,7 @@
p->sched_class->set_cpus_allowed(p, new_mask);
cpumask_copy(&p->cpus_allowed, new_mask);
- p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
+ p->nr_cpus_allowed = cpumask_weight(new_mask);
}
/*
@@ -5524,15 +5556,20 @@
#ifdef CONFIG_SCHED_DEBUG
-static __read_mostly int sched_domain_debug_enabled;
+static __read_mostly int sched_debug_enabled;
-static int __init sched_domain_debug_setup(char *str)
+static int __init sched_debug_setup(char *str)
{
- sched_domain_debug_enabled = 1;
+ sched_debug_enabled = 1;
return 0;
}
-early_param("sched_debug", sched_domain_debug_setup);
+early_param("sched_debug", sched_debug_setup);
+
+static inline bool sched_debug(void)
+{
+ return sched_debug_enabled;
+}
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
struct cpumask *groupmask)
@@ -5572,7 +5609,12 @@
break;
}
- if (!group->sgp->power) {
+ /*
+ * Even though we initialize ->power to something semi-sane,
+ * we leave power_orig unset. This allows us to detect if
+ * domain iteration is still funny without causing /0 traps.
+ */
+ if (!group->sgp->power_orig) {
printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: domain->cpu_power not "
"set\n");
@@ -5620,7 +5662,7 @@
{
int level = 0;
- if (!sched_domain_debug_enabled)
+ if (!sched_debug_enabled)
return;
if (!sd) {
@@ -5641,6 +5683,10 @@
}
#else /* !CONFIG_SCHED_DEBUG */
# define sched_domain_debug(sd, cpu) do { } while (0)
+static inline bool sched_debug(void)
+{
+ return false;
+}
#endif /* CONFIG_SCHED_DEBUG */
static int sd_degenerate(struct sched_domain *sd)
@@ -5962,6 +6008,44 @@
struct sd_data data;
};
+/*
+ * Build an iteration mask that can exclude certain CPUs from the upwards
+ * domain traversal.
+ *
+ * Asymmetric node setups can result in situations where the domain tree is of
+ * unequal depth, make sure to skip domains that already cover the entire
+ * range.
+ *
+ * In that case build_sched_domains() will have terminated the iteration early
+ * and our sibling sd spans will be empty. Domains should always include the
+ * cpu they're built on, so check that.
+ *
+ */
+static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
+{
+ const struct cpumask *span = sched_domain_span(sd);
+ struct sd_data *sdd = sd->private;
+ struct sched_domain *sibling;
+ int i;
+
+ for_each_cpu(i, span) {
+ sibling = *per_cpu_ptr(sdd->sd, i);
+ if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+ continue;
+
+ cpumask_set_cpu(i, sched_group_mask(sg));
+ }
+}
+
+/*
+ * Return the canonical balance cpu for this group, this is the first cpu
+ * of this group that's also in the iteration mask.
+ */
+int group_balance_cpu(struct sched_group *sg)
+{
+ return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg));
+}
+
static int
build_overlap_sched_groups(struct sched_domain *sd, int cpu)
{
@@ -5980,6 +6064,12 @@
if (cpumask_test_cpu(i, covered))
continue;
+ child = *per_cpu_ptr(sdd->sd, i);
+
+ /* See the comment near build_group_mask(). */
+ if (!cpumask_test_cpu(i, sched_domain_span(child)))
+ continue;
+
sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
GFP_KERNEL, cpu_to_node(cpu));
@@ -5987,8 +6077,6 @@
goto fail;
sg_span = sched_group_cpus(sg);
-
- child = *per_cpu_ptr(sdd->sd, i);
if (child->child) {
child = child->child;
cpumask_copy(sg_span, sched_domain_span(child));
@@ -5997,10 +6085,24 @@
cpumask_or(covered, covered, sg_span);
- sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span));
- atomic_inc(&sg->sgp->ref);
+ sg->sgp = *per_cpu_ptr(sdd->sgp, i);
+ if (atomic_inc_return(&sg->sgp->ref) == 1)
+ build_group_mask(sd, sg);
- if (cpumask_test_cpu(cpu, sg_span))
+ /*
+ * Initialize sgp->power such that even if we mess up the
+ * domains and no possible iteration will get us here, we won't
+ * die on a /0 trap.
+ */
+ sg->sgp->power = SCHED_POWER_SCALE * cpumask_weight(sg_span);
+
+ /*
+ * Make sure the first group of this domain contains the
+ * canonical balance cpu. Otherwise the sched_domain iteration
+ * breaks. See update_sg_lb_stats().
+ */
+ if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
+ group_balance_cpu(sg) == cpu)
groups = sg;
if (!first)
@@ -6074,6 +6176,7 @@
cpumask_clear(sched_group_cpus(sg));
sg->sgp->power = 0;
+ cpumask_setall(sched_group_mask(sg));
for_each_cpu(j, span) {
if (get_group(j, sdd, NULL) != group)
@@ -6115,7 +6218,7 @@
sg = sg->next;
} while (sg != sd->groups);
- if (cpu != group_first_cpu(sg))
+ if (cpu != group_balance_cpu(sg))
return;
update_group_power(sd, cpu);
@@ -6165,11 +6268,8 @@
static int __init setup_relax_domain_level(char *str)
{
- unsigned long val;
-
- val = simple_strtoul(str, NULL, 0);
- if (val < sched_domain_level_max)
- default_relax_domain_level = val;
+ if (kstrtoint(str, 0, &default_relax_domain_level))
+ pr_warn("Unable to set relax_domain_level\n");
return 1;
}
@@ -6279,14 +6379,13 @@
#ifdef CONFIG_NUMA
static int sched_domains_numa_levels;
-static int sched_domains_numa_scale;
static int *sched_domains_numa_distance;
static struct cpumask ***sched_domains_numa_masks;
static int sched_domains_curr_level;
static inline int sd_local_flags(int level)
{
- if (sched_domains_numa_distance[level] > REMOTE_DISTANCE)
+ if (sched_domains_numa_distance[level] > RECLAIM_DISTANCE)
return 0;
return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE;
@@ -6344,6 +6443,42 @@
return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
}
+static void sched_numa_warn(const char *str)
+{
+ static int done = false;
+ int i,j;
+
+ if (done)
+ return;
+
+ done = true;
+
+ printk(KERN_WARNING "ERROR: %s\n\n", str);
+
+ for (i = 0; i < nr_node_ids; i++) {
+ printk(KERN_WARNING " ");
+ for (j = 0; j < nr_node_ids; j++)
+ printk(KERN_CONT "%02d ", node_distance(i,j));
+ printk(KERN_CONT "\n");
+ }
+ printk(KERN_WARNING "\n");
+}
+
+static bool find_numa_distance(int distance)
+{
+ int i;
+
+ if (distance == node_distance(0, 0))
+ return true;
+
+ for (i = 0; i < sched_domains_numa_levels; i++) {
+ if (sched_domains_numa_distance[i] == distance)
+ return true;
+ }
+
+ return false;
+}
+
static void sched_init_numa(void)
{
int next_distance, curr_distance = node_distance(0, 0);
@@ -6351,7 +6486,6 @@
int level = 0;
int i, j, k;
- sched_domains_numa_scale = curr_distance;
sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
if (!sched_domains_numa_distance)
return;
@@ -6362,23 +6496,41 @@
*
* Assumes node_distance(0,j) includes all distances in
* node_distance(i,j) in order to avoid cubic time.
- *
- * XXX: could be optimized to O(n log n) by using sort()
*/
next_distance = curr_distance;
for (i = 0; i < nr_node_ids; i++) {
for (j = 0; j < nr_node_ids; j++) {
- int distance = node_distance(0, j);
- if (distance > curr_distance &&
- (distance < next_distance ||
- next_distance == curr_distance))
- next_distance = distance;
+ for (k = 0; k < nr_node_ids; k++) {
+ int distance = node_distance(i, k);
+
+ if (distance > curr_distance &&
+ (distance < next_distance ||
+ next_distance == curr_distance))
+ next_distance = distance;
+
+ /*
+ * While not a strong assumption it would be nice to know
+ * about cases where if node A is connected to B, B is not
+ * equally connected to A.
+ */
+ if (sched_debug() && node_distance(k, i) != distance)
+ sched_numa_warn("Node-distance not symmetric");
+
+ if (sched_debug() && i && !find_numa_distance(distance))
+ sched_numa_warn("Node-0 not representative");
+ }
+ if (next_distance != curr_distance) {
+ sched_domains_numa_distance[level++] = next_distance;
+ sched_domains_numa_levels = level;
+ curr_distance = next_distance;
+ } else break;
}
- if (next_distance != curr_distance) {
- sched_domains_numa_distance[level++] = next_distance;
- sched_domains_numa_levels = level;
- curr_distance = next_distance;
- } else break;
+
+ /*
+ * In case of sched_debug() we verify the above assumption.
+ */
+ if (!sched_debug())
+ break;
}
/*
* 'level' contains the number of unique distances, excluding the
@@ -6403,7 +6555,7 @@
return;
for (j = 0; j < nr_node_ids; j++) {
- struct cpumask *mask = kzalloc_node(cpumask_size(), GFP_KERNEL, j);
+ struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
if (!mask)
return;
@@ -6490,7 +6642,7 @@
*per_cpu_ptr(sdd->sg, j) = sg;
- sgp = kzalloc_node(sizeof(struct sched_group_power),
+ sgp = kzalloc_node(sizeof(struct sched_group_power) + cpumask_size(),
GFP_KERNEL, cpu_to_node(j));
if (!sgp)
return -ENOMEM;
@@ -6543,7 +6695,6 @@
if (!sd)
return child;
- set_domain_attribute(sd, attr);
cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
if (child) {
sd->level = child->level + 1;
@@ -6551,6 +6702,7 @@
child->parent = sd;
}
sd->child = child;
+ set_domain_attribute(sd, attr);
return sd;
}
@@ -6691,7 +6843,6 @@
if (!doms_cur)
doms_cur = &fallback_doms;
cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
- dattr_cur = NULL;
err = build_sched_domains(doms_cur[0], NULL);
register_sched_domain_sysctl();
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 940e6d1..c099cc6e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2703,7 +2703,7 @@
int want_sd = 1;
int sync = wake_flags & WF_SYNC;
- if (p->rt.nr_cpus_allowed == 1)
+ if (p->nr_cpus_allowed == 1)
return prev_cpu;
if (sd_flag & SD_BALANCE_WAKE) {
@@ -3503,15 +3503,22 @@
unsigned long scale_rt_power(int cpu)
{
struct rq *rq = cpu_rq(cpu);
- u64 total, available;
+ u64 total, available, age_stamp, avg;
- total = sched_avg_period() + (rq->clock - rq->age_stamp);
+ /*
+ * Since we're reading these variables without serialization make sure
+ * we read them once before doing sanity checks on them.
+ */
+ age_stamp = ACCESS_ONCE(rq->age_stamp);
+ avg = ACCESS_ONCE(rq->rt_avg);
- if (unlikely(total < rq->rt_avg)) {
+ total = sched_avg_period() + (rq->clock - age_stamp);
+
+ if (unlikely(total < avg)) {
/* Ensures that power won't end up being negative */
available = 0;
} else {
- available = total - rq->rt_avg;
+ available = total - avg;
}
if (unlikely((s64)total < SCHED_POWER_SCALE))
@@ -3574,13 +3581,28 @@
power = 0;
- group = child->groups;
- do {
- power += group->sgp->power;
- group = group->next;
- } while (group != child->groups);
+ if (child->flags & SD_OVERLAP) {
+ /*
+ * SD_OVERLAP domains cannot assume that child groups
+ * span the current group.
+ */
- sdg->sgp->power = power;
+ for_each_cpu(cpu, sched_group_cpus(sdg))
+ power += power_of(cpu);
+ } else {
+ /*
+ * !SD_OVERLAP domains can assume that child groups
+ * span the current group.
+ */
+
+ group = child->groups;
+ do {
+ power += group->sgp->power;
+ group = group->next;
+ } while (group != child->groups);
+ }
+
+ sdg->sgp->power_orig = sdg->sgp->power = power;
}
/*
@@ -3610,7 +3632,7 @@
/**
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
- * @sd: The sched_domain whose statistics are to be updated.
+ * @env: The load balancing environment.
* @group: sched_group whose statistics are to be updated.
* @load_idx: Load index of sched_domain of this_cpu for load calc.
* @local_group: Does group contain this_cpu.
@@ -3630,7 +3652,7 @@
int i;
if (local_group)
- balance_cpu = group_first_cpu(group);
+ balance_cpu = group_balance_cpu(group);
/* Tally up the load of all CPUs in the group */
max_cpu_load = 0;
@@ -3645,7 +3667,8 @@
/* Bias balancing toward cpus of our domain */
if (local_group) {
- if (idle_cpu(i) && !first_idle_cpu) {
+ if (idle_cpu(i) && !first_idle_cpu &&
+ cpumask_test_cpu(i, sched_group_mask(group))) {
first_idle_cpu = 1;
balance_cpu = i;
}
@@ -3719,11 +3742,10 @@
/**
* update_sd_pick_busiest - return 1 on busiest group
- * @sd: sched_domain whose statistics are to be checked
+ * @env: The load balancing environment.
* @sds: sched_domain statistics
* @sg: sched_group candidate to be checked for being the busiest
* @sgs: sched_group statistics
- * @this_cpu: the current cpu
*
* Determine if @sg is a busier group than the previously selected
* busiest group.
@@ -3761,9 +3783,7 @@
/**
* update_sd_lb_stats - Update sched_domain's statistics for load balancing.
- * @sd: sched_domain whose statistics are to be updated.
- * @this_cpu: Cpu for which load balance is currently performed.
- * @idle: Idle status of this_cpu
+ * @env: The load balancing environment.
* @cpus: Set of cpus considered for load balancing.
* @balance: Should we balance.
* @sds: variable to hold the statistics for this sched_domain.
@@ -3852,10 +3872,8 @@
* Returns 1 when packing is required and a task should be moved to
* this CPU. The amount of the imbalance is returned in *imbalance.
*
- * @sd: The sched_domain whose packing is to be checked.
+ * @env: The load balancing environment.
* @sds: Statistics of the sched_domain which is to be packed
- * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
- * @imbalance: returns amount of imbalanced due to packing.
*/
static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
{
@@ -3881,9 +3899,8 @@
* fix_small_imbalance - Calculate the minor imbalance that exists
* amongst the groups of a sched_domain, during
* load balancing.
+ * @env: The load balancing environment.
* @sds: Statistics of the sched_domain whose imbalance is to be calculated.
- * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
- * @imbalance: Variable to store the imbalance.
*/
static inline
void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
@@ -4026,11 +4043,7 @@
* Also calculates the amount of weighted load which should be moved
* to restore balance.
*
- * @sd: The sched_domain whose busiest group is to be returned.
- * @this_cpu: The cpu for which load balancing is currently being performed.
- * @imbalance: Variable which stores amount of weighted load which should
- * be moved to restore balance/put a group to idle.
- * @idle: The idle status of this_cpu.
+ * @env: The load balancing environment.
* @cpus: The set of CPUs under consideration for load-balancing.
* @balance: Pointer to a variable indicating if this_cpu
* is the appropriate cpu to perform load balancing at this_level.
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index c5565c3..573e1ca 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -274,13 +274,16 @@
static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
+ struct task_struct *p;
+
if (!rt_entity_is_task(rt_se))
return;
+ p = rt_task_of(rt_se);
rt_rq = &rq_of_rt_rq(rt_rq)->rt;
rt_rq->rt_nr_total++;
- if (rt_se->nr_cpus_allowed > 1)
+ if (p->nr_cpus_allowed > 1)
rt_rq->rt_nr_migratory++;
update_rt_migration(rt_rq);
@@ -288,13 +291,16 @@
static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
+ struct task_struct *p;
+
if (!rt_entity_is_task(rt_se))
return;
+ p = rt_task_of(rt_se);
rt_rq = &rq_of_rt_rq(rt_rq)->rt;
rt_rq->rt_nr_total--;
- if (rt_se->nr_cpus_allowed > 1)
+ if (p->nr_cpus_allowed > 1)
rt_rq->rt_nr_migratory--;
update_rt_migration(rt_rq);
@@ -1161,7 +1167,7 @@
enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
- if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
+ if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
enqueue_pushable_task(rq, p);
inc_nr_running(rq);
@@ -1225,7 +1231,7 @@
cpu = task_cpu(p);
- if (p->rt.nr_cpus_allowed == 1)
+ if (p->nr_cpus_allowed == 1)
goto out;
/* For anything but wake ups, just return the task_cpu */
@@ -1260,9 +1266,9 @@
* will have to sort it out.
*/
if (curr && unlikely(rt_task(curr)) &&
- (curr->rt.nr_cpus_allowed < 2 ||
+ (curr->nr_cpus_allowed < 2 ||
curr->prio <= p->prio) &&
- (p->rt.nr_cpus_allowed > 1)) {
+ (p->nr_cpus_allowed > 1)) {
int target = find_lowest_rq(p);
if (target != -1)
@@ -1276,10 +1282,10 @@
static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
{
- if (rq->curr->rt.nr_cpus_allowed == 1)
+ if (rq->curr->nr_cpus_allowed == 1)
return;
- if (p->rt.nr_cpus_allowed != 1
+ if (p->nr_cpus_allowed != 1
&& cpupri_find(&rq->rd->cpupri, p, NULL))
return;
@@ -1395,7 +1401,7 @@
* The previous task needs to be made eligible for pushing
* if it is still active
*/
- if (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1)
+ if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
enqueue_pushable_task(rq, p);
}
@@ -1408,7 +1414,7 @@
{
if (!task_running(rq, p) &&
(cpu < 0 || cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) &&
- (p->rt.nr_cpus_allowed > 1))
+ (p->nr_cpus_allowed > 1))
return 1;
return 0;
}
@@ -1464,7 +1470,7 @@
if (unlikely(!lowest_mask))
return -1;
- if (task->rt.nr_cpus_allowed == 1)
+ if (task->nr_cpus_allowed == 1)
return -1; /* No other targets possible */
if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
@@ -1556,7 +1562,7 @@
task_running(rq, task) ||
!task->on_rq)) {
- raw_spin_unlock(&lowest_rq->lock);
+ double_unlock_balance(rq, lowest_rq);
lowest_rq = NULL;
break;
}
@@ -1586,7 +1592,7 @@
BUG_ON(rq->cpu != task_cpu(p));
BUG_ON(task_current(rq, p));
- BUG_ON(p->rt.nr_cpus_allowed <= 1);
+ BUG_ON(p->nr_cpus_allowed <= 1);
BUG_ON(!p->on_rq);
BUG_ON(!rt_task(p));
@@ -1793,9 +1799,9 @@
if (!task_running(rq, p) &&
!test_tsk_need_resched(rq->curr) &&
has_pushable_tasks(rq) &&
- p->rt.nr_cpus_allowed > 1 &&
+ p->nr_cpus_allowed > 1 &&
rt_task(rq->curr) &&
- (rq->curr->rt.nr_cpus_allowed < 2 ||
+ (rq->curr->nr_cpus_allowed < 2 ||
rq->curr->prio <= p->prio))
push_rt_tasks(rq);
}
@@ -1817,7 +1823,7 @@
* Only update if the process changes its state from whether it
* can migrate or not.
*/
- if ((p->rt.nr_cpus_allowed > 1) == (weight > 1))
+ if ((p->nr_cpus_allowed > 1) == (weight > 1))
return;
rq = task_rq(p);
@@ -1979,6 +1985,8 @@
static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
{
+ struct sched_rt_entity *rt_se = &p->rt;
+
update_curr_rt(rq);
watchdog(rq, p);
@@ -1996,12 +2004,15 @@
p->rt.time_slice = RR_TIMESLICE;
/*
- * Requeue to the end of queue if we are not the only element
- * on the queue:
+ * Requeue to the end of queue if we (and all of our ancestors) are the
+ * only element on the queue
*/
- if (p->rt.run_list.prev != p->rt.run_list.next) {
- requeue_task_rt(rq, p, 0);
- set_tsk_need_resched(p);
+ for_each_sched_rt_entity(rt_se) {
+ if (rt_se->run_list.prev != rt_se->run_list.next) {
+ requeue_task_rt(rq, p, 0);
+ set_tsk_need_resched(p);
+ return;
+ }
}
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ba9dccf..6d52cea 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -526,6 +526,8 @@
DECLARE_PER_CPU(struct sched_domain *, sd_llc);
DECLARE_PER_CPU(int, sd_llc_id);
+extern int group_balance_cpu(struct sched_group *sg);
+
#endif /* CONFIG_SMP */
#include "stats.h"
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index e1a797e..98f60c5 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -31,6 +31,12 @@
per_cpu(idle_threads, smp_processor_id()) = current;
}
+/**
+ * idle_init - Initialize the idle thread for a cpu
+ * @cpu: The cpu for which the idle thread should be initialized
+ *
+ * Creates the thread if it does not exist.
+ */
static inline void idle_init(unsigned int cpu)
{
struct task_struct *tsk = per_cpu(idle_threads, cpu);
@@ -45,17 +51,16 @@
}
/**
- * idle_thread_init - Initialize the idle thread for a cpu
- * @cpu: The cpu for which the idle thread should be initialized
- *
- * Creates the thread if it does not exist.
+ * idle_threads_init - Initialize idle threads for all cpus
*/
void __init idle_threads_init(void)
{
- unsigned int cpu;
+ unsigned int cpu, boot_cpu;
+
+ boot_cpu = smp_processor_id();
for_each_possible_cpu(cpu) {
- if (cpu != smp_processor_id())
+ if (cpu != boot_cpu)
idle_init(cpu);
}
}
diff --git a/kernel/sys.c b/kernel/sys.c
index 9ff89cb..f0ec44d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1786,27 +1786,13 @@
}
#ifdef CONFIG_CHECKPOINT_RESTORE
-static bool vma_flags_mismatch(struct vm_area_struct *vma,
- unsigned long required,
- unsigned long banned)
-{
- return (vma->vm_flags & required) != required ||
- (vma->vm_flags & banned);
-}
-
static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
{
+ struct vm_area_struct *vma;
struct file *exe_file;
struct dentry *dentry;
int err;
- /*
- * Setting new mm::exe_file is only allowed when no VM_EXECUTABLE vma's
- * remain. So perform a quick test first.
- */
- if (mm->num_exe_file_vmas)
- return -EBUSY;
-
exe_file = fget(fd);
if (!exe_file)
return -EBADF;
@@ -1827,17 +1813,30 @@
if (err)
goto exit;
+ down_write(&mm->mmap_sem);
+
+ /*
+ * Forbid mm->exe_file change if there are mapped other files.
+ */
+ err = -EBUSY;
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (vma->vm_file && !path_equal(&vma->vm_file->f_path,
+ &exe_file->f_path))
+ goto exit_unlock;
+ }
+
/*
* The symlink can be changed only once, just to disallow arbitrary
* transitions malicious software might bring in. This means one
* could make a snapshot over all processes running and monitor
* /proc/pid/exe changes to notice unusual activity if needed.
*/
- down_write(&mm->mmap_sem);
- if (likely(!mm->exe_file))
- set_mm_exe_file(mm, exe_file);
- else
- err = -EBUSY;
+ err = -EPERM;
+ if (test_and_set_bit(MMF_EXE_FILE_CHANGED, &mm->flags))
+ goto exit_unlock;
+
+ set_mm_exe_file(mm, exe_file);
+exit_unlock:
up_write(&mm->mmap_sem);
exit:
@@ -1862,7 +1861,7 @@
if (opt == PR_SET_MM_EXE_FILE)
return prctl_set_mm_exe_file(mm, (unsigned int)addr);
- if (addr >= TASK_SIZE)
+ if (addr >= TASK_SIZE || addr < mmap_min_addr)
return -EINVAL;
error = -EINVAL;
@@ -1924,12 +1923,6 @@
error = -EFAULT;
goto out;
}
-#ifdef CONFIG_STACK_GROWSUP
- if (vma_flags_mismatch(vma, VM_READ | VM_WRITE | VM_GROWSUP, 0))
-#else
- if (vma_flags_mismatch(vma, VM_READ | VM_WRITE | VM_GROWSDOWN, 0))
-#endif
- goto out;
if (opt == PR_SET_MM_START_STACK)
mm->start_stack = addr;
else if (opt == PR_SET_MM_ARG_START)
@@ -1981,12 +1974,22 @@
up_read(&mm->mmap_sem);
return error;
}
+
+static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+{
+ return put_user(me->clear_child_tid, tid_addr);
+}
+
#else /* CONFIG_CHECKPOINT_RESTORE */
static int prctl_set_mm(int opt, unsigned long addr,
unsigned long arg4, unsigned long arg5)
{
return -EINVAL;
}
+static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+{
+ return -EINVAL;
+}
#endif
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
@@ -2124,6 +2127,9 @@
else
return -EINVAL;
break;
+ case PR_GET_TID_ADDRESS:
+ error = prctl_get_tid_address(me, (int __user **)arg2);
+ break;
default:
return -EINVAL;
}
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 9cd928f..7e1ce01 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -297,8 +297,7 @@
}
EXPORT_SYMBOL_GPL(clockevents_register_device);
-static void clockevents_config(struct clock_event_device *dev,
- u32 freq)
+void clockevents_config(struct clock_event_device *dev, u32 freq)
{
u64 sec;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 6a3a5b9..da70c6d 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -576,6 +576,7 @@
/* Update jiffies first */
select_nohz_load_balancer(0);
tick_do_update_jiffies64(now);
+ update_cpu_load_nohz();
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
/*
@@ -814,6 +815,16 @@
return HRTIMER_RESTART;
}
+static int sched_skew_tick;
+
+static int __init skew_tick(char *str)
+{
+ get_option(&str, &sched_skew_tick);
+
+ return 0;
+}
+early_param("skew_tick", skew_tick);
+
/**
* tick_setup_sched_timer - setup the tick emulation timer
*/
@@ -831,6 +842,14 @@
/* Get the next period (per cpu) */
hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
+ /* Offset the tick to avert xtime_lock contention. */
+ if (sched_skew_tick) {
+ u64 offset = ktime_to_ns(tick_period) >> 1;
+ do_div(offset, num_possible_cpus());
+ offset *= smp_processor_id();
+ hrtimer_add_expires_ns(&ts->sched_timer, offset);
+ }
+
for (;;) {
hrtimer_forward(&ts->sched_timer, now, tick_period);
hrtimer_start_expires(&ts->sched_timer,
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 6e46cac..6f46a00 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -962,6 +962,7 @@
timekeeper.xtime.tv_sec++;
leap = second_overflow(timekeeper.xtime.tv_sec);
timekeeper.xtime.tv_sec += leap;
+ timekeeper.wall_to_monotonic.tv_sec -= leap;
}
/* Accumulate raw time */
@@ -1077,6 +1078,7 @@
timekeeper.xtime.tv_sec++;
leap = second_overflow(timekeeper.xtime.tv_sec);
timekeeper.xtime.tv_sec += leap;
+ timekeeper.wall_to_monotonic.tv_sec -= leap;
}
timekeeping_update(false);
diff --git a/lib/btree.c b/lib/btree.c
index e5ec1e9..f9a4846 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -319,8 +319,8 @@
if (head->height == 0)
return NULL;
-retry:
longcpy(key, __key, geo->keylen);
+retry:
dec_key(geo, key);
node = head->node;
@@ -351,7 +351,7 @@
}
miss:
if (retry_key) {
- __key = retry_key;
+ longcpy(key, retry_key, geo->keylen);
retry_key = NULL;
goto retry;
}
@@ -509,6 +509,7 @@
int btree_insert(struct btree_head *head, struct btree_geo *geo,
unsigned long *key, void *val, gfp_t gfp)
{
+ BUG_ON(!val);
return btree_insert_level(head, geo, key, val, 1, gfp);
}
EXPORT_SYMBOL_GPL(btree_insert);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index d7c878c..e796429 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -686,6 +686,9 @@
* during iterating; it can be zero only at the beginning.
* And we cannot overflow iter->next_index in a single step,
* because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG.
+ *
+ * This condition also used by radix_tree_next_slot() to stop
+ * contiguous iterating, and forbid swithing to the next chunk.
*/
index = iter->next_index;
if (!index && iter->index)
diff --git a/lib/raid6/recov.c b/lib/raid6/recov.c
index 1805a5c..a95bccb 100644
--- a/lib/raid6/recov.c
+++ b/lib/raid6/recov.c
@@ -22,8 +22,8 @@
#include <linux/raid/pq.h>
/* Recover two failed data blocks. */
-void raid6_2data_recov_intx1(int disks, size_t bytes, int faila, int failb,
- void **ptrs)
+static void raid6_2data_recov_intx1(int disks, size_t bytes, int faila,
+ int failb, void **ptrs)
{
u8 *p, *q, *dp, *dq;
u8 px, qx, db;
@@ -66,7 +66,8 @@
}
/* Recover failure of one data block plus the P block */
-void raid6_datap_recov_intx1(int disks, size_t bytes, int faila, void **ptrs)
+static void raid6_datap_recov_intx1(int disks, size_t bytes, int faila,
+ void **ptrs)
{
u8 *p, *q, *dq;
const u8 *qmul; /* Q multiplier table */
diff --git a/lib/raid6/recov_ssse3.c b/lib/raid6/recov_ssse3.c
index 37ae619..ecb710c 100644
--- a/lib/raid6/recov_ssse3.c
+++ b/lib/raid6/recov_ssse3.c
@@ -19,8 +19,8 @@
boot_cpu_has(X86_FEATURE_SSSE3);
}
-void raid6_2data_recov_ssse3(int disks, size_t bytes, int faila, int failb,
- void **ptrs)
+static void raid6_2data_recov_ssse3(int disks, size_t bytes, int faila,
+ int failb, void **ptrs)
{
u8 *p, *q, *dp, *dq;
const u8 *pbmul; /* P multiplier table for B data */
@@ -194,7 +194,8 @@
}
-void raid6_datap_recov_ssse3(int disks, size_t bytes, int faila, void **ptrs)
+static void raid6_datap_recov_ssse3(int disks, size_t bytes, int faila,
+ void **ptrs)
{
u8 *p, *q, *dq;
const u8 *qmul; /* Q multiplier table */
diff --git a/mm/Kconfig b/mm/Kconfig
index b217637..82fed4e 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -389,3 +389,20 @@
in a negligible performance hit.
If unsure, say Y to enable cleancache
+
+config FRONTSWAP
+ bool "Enable frontswap to cache swap pages if tmem is present"
+ depends on SWAP
+ default n
+ help
+ Frontswap is so named because it can be thought of as the opposite
+ of a "backing" store for a swap device. The data is stored into
+ "transcendent memory", memory that is not directly accessible or
+ addressable by the kernel and is of unknown and possibly
+ time-varying size. When space in transcendent memory is available,
+ a significant swap I/O reduction may be achieved. When none is
+ available, all frontswap calls are reduced to a single pointer-
+ compare-against-NULL resulting in a negligible performance hit
+ and swap data is stored as normal on the matching swap device.
+
+ If unsure, say Y to enable frontswap.
diff --git a/mm/Makefile b/mm/Makefile
index a156285..2e2fbbe 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -29,6 +29,7 @@
obj-$(CONFIG_BOUNCE) += bounce.o
obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o
+obj-$(CONFIG_FRONTSWAP) += frontswap.o
obj-$(CONFIG_HAS_DMA) += dmapool.o
obj-$(CONFIG_HUGETLBFS) += hugetlb.o
obj-$(CONFIG_NUMA) += mempolicy.o
diff --git a/mm/compaction.c b/mm/compaction.c
index 4ac338a..7ea259d 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -236,7 +236,7 @@
*/
while (unlikely(too_many_isolated(zone))) {
/* async migration should just abort */
- if (cc->mode != COMPACT_SYNC)
+ if (!cc->sync)
return 0;
congestion_wait(BLK_RW_ASYNC, HZ/10);
@@ -304,8 +304,7 @@
* satisfies the allocation
*/
pageblock_nr = low_pfn >> pageblock_order;
- if (cc->mode != COMPACT_SYNC &&
- last_pageblock_nr != pageblock_nr &&
+ if (!cc->sync && last_pageblock_nr != pageblock_nr &&
!migrate_async_suitable(get_pageblock_migratetype(page))) {
low_pfn += pageblock_nr_pages;
low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1;
@@ -326,7 +325,7 @@
continue;
}
- if (cc->mode != COMPACT_SYNC)
+ if (!cc->sync)
mode |= ISOLATE_ASYNC_MIGRATE;
lruvec = mem_cgroup_page_lruvec(page, zone);
@@ -361,90 +360,27 @@
#endif /* CONFIG_COMPACTION || CONFIG_CMA */
#ifdef CONFIG_COMPACTION
-/*
- * Returns true if MIGRATE_UNMOVABLE pageblock was successfully
- * converted to MIGRATE_MOVABLE type, false otherwise.
- */
-static bool rescue_unmovable_pageblock(struct page *page)
-{
- unsigned long pfn, start_pfn, end_pfn;
- struct page *start_page, *end_page;
- pfn = page_to_pfn(page);
- start_pfn = pfn & ~(pageblock_nr_pages - 1);
- end_pfn = start_pfn + pageblock_nr_pages;
-
- start_page = pfn_to_page(start_pfn);
- end_page = pfn_to_page(end_pfn);
-
- /* Do not deal with pageblocks that overlap zones */
- if (page_zone(start_page) != page_zone(end_page))
- return false;
-
- for (page = start_page, pfn = start_pfn; page < end_page; pfn++,
- page++) {
- if (!pfn_valid_within(pfn))
- continue;
-
- if (PageBuddy(page)) {
- int order = page_order(page);
-
- pfn += (1 << order) - 1;
- page += (1 << order) - 1;
-
- continue;
- } else if (page_count(page) == 0 || PageLRU(page))
- continue;
-
- return false;
- }
-
- set_pageblock_migratetype(page, MIGRATE_MOVABLE);
- move_freepages_block(page_zone(page), page, MIGRATE_MOVABLE);
- return true;
-}
-
-enum smt_result {
- GOOD_AS_MIGRATION_TARGET,
- FAIL_UNMOVABLE_TARGET,
- FAIL_BAD_TARGET,
-};
-
-/*
- * Returns GOOD_AS_MIGRATION_TARGET if the page is within a block
- * suitable for migration to, FAIL_UNMOVABLE_TARGET if the page
- * is within a MIGRATE_UNMOVABLE block, FAIL_BAD_TARGET otherwise.
- */
-static enum smt_result suitable_migration_target(struct page *page,
- struct compact_control *cc)
+/* Returns true if the page is within a block suitable for migration to */
+static bool suitable_migration_target(struct page *page)
{
int migratetype = get_pageblock_migratetype(page);
/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE)
- return FAIL_BAD_TARGET;
+ return false;
/* If the page is a large free page, then allow migration */
if (PageBuddy(page) && page_order(page) >= pageblock_order)
- return GOOD_AS_MIGRATION_TARGET;
+ return true;
/* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */
- if (cc->mode != COMPACT_ASYNC_UNMOVABLE &&
- migrate_async_suitable(migratetype))
- return GOOD_AS_MIGRATION_TARGET;
-
- if (cc->mode == COMPACT_ASYNC_MOVABLE &&
- migratetype == MIGRATE_UNMOVABLE)
- return FAIL_UNMOVABLE_TARGET;
-
- if (cc->mode != COMPACT_ASYNC_MOVABLE &&
- migratetype == MIGRATE_UNMOVABLE &&
- rescue_unmovable_pageblock(page))
- return GOOD_AS_MIGRATION_TARGET;
+ if (migrate_async_suitable(migratetype))
+ return true;
/* Otherwise skip the block */
- return FAIL_BAD_TARGET;
+ return false;
}
/*
@@ -478,13 +414,6 @@
zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
/*
- * isolate_freepages() may be called more than once during
- * compact_zone_order() run and we want only the most recent
- * count.
- */
- cc->nr_pageblocks_skipped = 0;
-
- /*
* Isolate free pages until enough are available to migrate the
* pages on cc->migratepages. We stop searching if the migrate
* and free page scanners meet or enough free pages are isolated.
@@ -492,7 +421,6 @@
for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages;
pfn -= pageblock_nr_pages) {
unsigned long isolated;
- enum smt_result ret;
if (!pfn_valid(pfn))
continue;
@@ -509,12 +437,9 @@
continue;
/* Check the block is suitable for migration */
- ret = suitable_migration_target(page, cc);
- if (ret != GOOD_AS_MIGRATION_TARGET) {
- if (ret == FAIL_UNMOVABLE_TARGET)
- cc->nr_pageblocks_skipped++;
+ if (!suitable_migration_target(page))
continue;
- }
+
/*
* Found a block suitable for isolating free pages from. Now
* we disabled interrupts, double check things are ok and
@@ -523,14 +448,12 @@
*/
isolated = 0;
spin_lock_irqsave(&zone->lock, flags);
- ret = suitable_migration_target(page, cc);
- if (ret == GOOD_AS_MIGRATION_TARGET) {
+ if (suitable_migration_target(page)) {
end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn);
isolated = isolate_freepages_block(pfn, end_pfn,
freelist, false);
nr_freepages += isolated;
- } else if (ret == FAIL_UNMOVABLE_TARGET)
- cc->nr_pageblocks_skipped++;
+ }
spin_unlock_irqrestore(&zone->lock, flags);
/*
@@ -762,9 +685,8 @@
nr_migrate = cc->nr_migratepages;
err = migrate_pages(&cc->migratepages, compaction_alloc,
- (unsigned long)&cc->freepages, false,
- (cc->mode == COMPACT_SYNC) ? MIGRATE_SYNC_LIGHT
- : MIGRATE_ASYNC);
+ (unsigned long)cc, false,
+ cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC);
update_nr_listpages(cc);
nr_remaining = cc->nr_migratepages;
@@ -793,8 +715,7 @@
static unsigned long compact_zone_order(struct zone *zone,
int order, gfp_t gfp_mask,
- enum compact_mode mode,
- unsigned long *nr_pageblocks_skipped)
+ bool sync)
{
struct compact_control cc = {
.nr_freepages = 0,
@@ -802,17 +723,12 @@
.order = order,
.migratetype = allocflags_to_migratetype(gfp_mask),
.zone = zone,
- .mode = mode,
+ .sync = sync,
};
- unsigned long rc;
-
INIT_LIST_HEAD(&cc.freepages);
INIT_LIST_HEAD(&cc.migratepages);
- rc = compact_zone(zone, &cc);
- *nr_pageblocks_skipped = cc.nr_pageblocks_skipped;
-
- return rc;
+ return compact_zone(zone, &cc);
}
int sysctl_extfrag_threshold = 500;
@@ -837,8 +753,6 @@
struct zoneref *z;
struct zone *zone;
int rc = COMPACT_SKIPPED;
- unsigned long nr_pageblocks_skipped;
- enum compact_mode mode;
/*
* Check whether it is worth even starting compaction. The order check is
@@ -855,22 +769,12 @@
nodemask) {
int status;
- mode = sync ? COMPACT_SYNC : COMPACT_ASYNC_MOVABLE;
-retry:
- status = compact_zone_order(zone, order, gfp_mask, mode,
- &nr_pageblocks_skipped);
+ status = compact_zone_order(zone, order, gfp_mask, sync);
rc = max(status, rc);
/* If a normal allocation would succeed, stop compacting */
if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
break;
-
- if (rc == COMPACT_COMPLETE && mode == COMPACT_ASYNC_MOVABLE) {
- if (nr_pageblocks_skipped) {
- mode = COMPACT_ASYNC_UNMOVABLE;
- goto retry;
- }
- }
}
return rc;
@@ -904,7 +808,7 @@
if (ok && cc->order > zone->compact_order_failed)
zone->compact_order_failed = cc->order + 1;
/* Currently async compaction is never deferred. */
- else if (!ok && cc->mode == COMPACT_SYNC)
+ else if (!ok && cc->sync)
defer_compaction(zone, cc->order);
}
@@ -919,7 +823,7 @@
{
struct compact_control cc = {
.order = order,
- .mode = COMPACT_ASYNC_MOVABLE,
+ .sync = false,
};
return __compact_pgdat(pgdat, &cc);
@@ -929,7 +833,7 @@
{
struct compact_control cc = {
.order = -1,
- .mode = COMPACT_SYNC,
+ .sync = true,
};
return __compact_pgdat(NODE_DATA(nid), &cc);
diff --git a/mm/frontswap.c b/mm/frontswap.c
new file mode 100644
index 0000000..e250255
--- /dev/null
+++ b/mm/frontswap.c
@@ -0,0 +1,314 @@
+/*
+ * Frontswap frontend
+ *
+ * This code provides the generic "frontend" layer to call a matching
+ * "backend" driver implementation of frontswap. See
+ * Documentation/vm/frontswap.txt for more information.
+ *
+ * Copyright (C) 2009-2012 Oracle Corp. All rights reserved.
+ * Author: Dan Magenheimer
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/proc_fs.h>
+#include <linux/security.h>
+#include <linux/capability.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/frontswap.h>
+#include <linux/swapfile.h>
+
+/*
+ * frontswap_ops is set by frontswap_register_ops to contain the pointers
+ * to the frontswap "backend" implementation functions.
+ */
+static struct frontswap_ops frontswap_ops __read_mostly;
+
+/*
+ * This global enablement flag reduces overhead on systems where frontswap_ops
+ * has not been registered, so is preferred to the slower alternative: a
+ * function call that checks a non-global.
+ */
+bool frontswap_enabled __read_mostly;
+EXPORT_SYMBOL(frontswap_enabled);
+
+/*
+ * If enabled, frontswap_store will return failure even on success. As
+ * a result, the swap subsystem will always write the page to swap, in
+ * effect converting frontswap into a writethrough cache. In this mode,
+ * there is no direct reduction in swap writes, but a frontswap backend
+ * can unilaterally "reclaim" any pages in use with no data loss, thus
+ * providing increases control over maximum memory usage due to frontswap.
+ */
+static bool frontswap_writethrough_enabled __read_mostly;
+
+#ifdef CONFIG_DEBUG_FS
+/*
+ * Counters available via /sys/kernel/debug/frontswap (if debugfs is
+ * properly configured). These are for information only so are not protected
+ * against increment races.
+ */
+static u64 frontswap_loads;
+static u64 frontswap_succ_stores;
+static u64 frontswap_failed_stores;
+static u64 frontswap_invalidates;
+
+static inline void inc_frontswap_loads(void) {
+ frontswap_loads++;
+}
+static inline void inc_frontswap_succ_stores(void) {
+ frontswap_succ_stores++;
+}
+static inline void inc_frontswap_failed_stores(void) {
+ frontswap_failed_stores++;
+}
+static inline void inc_frontswap_invalidates(void) {
+ frontswap_invalidates++;
+}
+#else
+static inline void inc_frontswap_loads(void) { }
+static inline void inc_frontswap_succ_stores(void) { }
+static inline void inc_frontswap_failed_stores(void) { }
+static inline void inc_frontswap_invalidates(void) { }
+#endif
+/*
+ * Register operations for frontswap, returning previous thus allowing
+ * detection of multiple backends and possible nesting.
+ */
+struct frontswap_ops frontswap_register_ops(struct frontswap_ops *ops)
+{
+ struct frontswap_ops old = frontswap_ops;
+
+ frontswap_ops = *ops;
+ frontswap_enabled = true;
+ return old;
+}
+EXPORT_SYMBOL(frontswap_register_ops);
+
+/*
+ * Enable/disable frontswap writethrough (see above).
+ */
+void frontswap_writethrough(bool enable)
+{
+ frontswap_writethrough_enabled = enable;
+}
+EXPORT_SYMBOL(frontswap_writethrough);
+
+/*
+ * Called when a swap device is swapon'd.
+ */
+void __frontswap_init(unsigned type)
+{
+ struct swap_info_struct *sis = swap_info[type];
+
+ BUG_ON(sis == NULL);
+ if (sis->frontswap_map == NULL)
+ return;
+ if (frontswap_enabled)
+ (*frontswap_ops.init)(type);
+}
+EXPORT_SYMBOL(__frontswap_init);
+
+/*
+ * "Store" data from a page to frontswap and associate it with the page's
+ * swaptype and offset. Page must be locked and in the swap cache.
+ * If frontswap already contains a page with matching swaptype and
+ * offset, the frontswap implmentation may either overwrite the data and
+ * return success or invalidate the page from frontswap and return failure.
+ */
+int __frontswap_store(struct page *page)
+{
+ int ret = -1, dup = 0;
+ swp_entry_t entry = { .val = page_private(page), };
+ int type = swp_type(entry);
+ struct swap_info_struct *sis = swap_info[type];
+ pgoff_t offset = swp_offset(entry);
+
+ BUG_ON(!PageLocked(page));
+ BUG_ON(sis == NULL);
+ if (frontswap_test(sis, offset))
+ dup = 1;
+ ret = (*frontswap_ops.store)(type, offset, page);
+ if (ret == 0) {
+ frontswap_set(sis, offset);
+ inc_frontswap_succ_stores();
+ if (!dup)
+ atomic_inc(&sis->frontswap_pages);
+ } else if (dup) {
+ /*
+ failed dup always results in automatic invalidate of
+ the (older) page from frontswap
+ */
+ frontswap_clear(sis, offset);
+ atomic_dec(&sis->frontswap_pages);
+ inc_frontswap_failed_stores();
+ } else
+ inc_frontswap_failed_stores();
+ if (frontswap_writethrough_enabled)
+ /* report failure so swap also writes to swap device */
+ ret = -1;
+ return ret;
+}
+EXPORT_SYMBOL(__frontswap_store);
+
+/*
+ * "Get" data from frontswap associated with swaptype and offset that were
+ * specified when the data was put to frontswap and use it to fill the
+ * specified page with data. Page must be locked and in the swap cache.
+ */
+int __frontswap_load(struct page *page)
+{
+ int ret = -1;
+ swp_entry_t entry = { .val = page_private(page), };
+ int type = swp_type(entry);
+ struct swap_info_struct *sis = swap_info[type];
+ pgoff_t offset = swp_offset(entry);
+
+ BUG_ON(!PageLocked(page));
+ BUG_ON(sis == NULL);
+ if (frontswap_test(sis, offset))
+ ret = (*frontswap_ops.load)(type, offset, page);
+ if (ret == 0)
+ inc_frontswap_loads();
+ return ret;
+}
+EXPORT_SYMBOL(__frontswap_load);
+
+/*
+ * Invalidate any data from frontswap associated with the specified swaptype
+ * and offset so that a subsequent "get" will fail.
+ */
+void __frontswap_invalidate_page(unsigned type, pgoff_t offset)
+{
+ struct swap_info_struct *sis = swap_info[type];
+
+ BUG_ON(sis == NULL);
+ if (frontswap_test(sis, offset)) {
+ (*frontswap_ops.invalidate_page)(type, offset);
+ atomic_dec(&sis->frontswap_pages);
+ frontswap_clear(sis, offset);
+ inc_frontswap_invalidates();
+ }
+}
+EXPORT_SYMBOL(__frontswap_invalidate_page);
+
+/*
+ * Invalidate all data from frontswap associated with all offsets for the
+ * specified swaptype.
+ */
+void __frontswap_invalidate_area(unsigned type)
+{
+ struct swap_info_struct *sis = swap_info[type];
+
+ BUG_ON(sis == NULL);
+ if (sis->frontswap_map == NULL)
+ return;
+ (*frontswap_ops.invalidate_area)(type);
+ atomic_set(&sis->frontswap_pages, 0);
+ memset(sis->frontswap_map, 0, sis->max / sizeof(long));
+}
+EXPORT_SYMBOL(__frontswap_invalidate_area);
+
+/*
+ * Frontswap, like a true swap device, may unnecessarily retain pages
+ * under certain circumstances; "shrink" frontswap is essentially a
+ * "partial swapoff" and works by calling try_to_unuse to attempt to
+ * unuse enough frontswap pages to attempt to -- subject to memory
+ * constraints -- reduce the number of pages in frontswap to the
+ * number given in the parameter target_pages.
+ */
+void frontswap_shrink(unsigned long target_pages)
+{
+ struct swap_info_struct *si = NULL;
+ int si_frontswap_pages;
+ unsigned long total_pages = 0, total_pages_to_unuse;
+ unsigned long pages = 0, pages_to_unuse = 0;
+ int type;
+ bool locked = false;
+
+ /*
+ * we don't want to hold swap_lock while doing a very
+ * lengthy try_to_unuse, but swap_list may change
+ * so restart scan from swap_list.head each time
+ */
+ spin_lock(&swap_lock);
+ locked = true;
+ total_pages = 0;
+ for (type = swap_list.head; type >= 0; type = si->next) {
+ si = swap_info[type];
+ total_pages += atomic_read(&si->frontswap_pages);
+ }
+ if (total_pages <= target_pages)
+ goto out;
+ total_pages_to_unuse = total_pages - target_pages;
+ for (type = swap_list.head; type >= 0; type = si->next) {
+ si = swap_info[type];
+ si_frontswap_pages = atomic_read(&si->frontswap_pages);
+ if (total_pages_to_unuse < si_frontswap_pages)
+ pages = pages_to_unuse = total_pages_to_unuse;
+ else {
+ pages = si_frontswap_pages;
+ pages_to_unuse = 0; /* unuse all */
+ }
+ /* ensure there is enough RAM to fetch pages from frontswap */
+ if (security_vm_enough_memory_mm(current->mm, pages))
+ continue;
+ vm_unacct_memory(pages);
+ break;
+ }
+ if (type < 0)
+ goto out;
+ locked = false;
+ spin_unlock(&swap_lock);
+ try_to_unuse(type, true, pages_to_unuse);
+out:
+ if (locked)
+ spin_unlock(&swap_lock);
+ return;
+}
+EXPORT_SYMBOL(frontswap_shrink);
+
+/*
+ * Count and return the number of frontswap pages across all
+ * swap devices. This is exported so that backend drivers can
+ * determine current usage without reading debugfs.
+ */
+unsigned long frontswap_curr_pages(void)
+{
+ int type;
+ unsigned long totalpages = 0;
+ struct swap_info_struct *si = NULL;
+
+ spin_lock(&swap_lock);
+ for (type = swap_list.head; type >= 0; type = si->next) {
+ si = swap_info[type];
+ totalpages += atomic_read(&si->frontswap_pages);
+ }
+ spin_unlock(&swap_lock);
+ return totalpages;
+}
+EXPORT_SYMBOL(frontswap_curr_pages);
+
+static int __init init_frontswap(void)
+{
+#ifdef CONFIG_DEBUG_FS
+ struct dentry *root = debugfs_create_dir("frontswap", NULL);
+ if (root == NULL)
+ return -ENXIO;
+ debugfs_create_u64("loads", S_IRUGO, root, &frontswap_loads);
+ debugfs_create_u64("succ_stores", S_IRUGO, root, &frontswap_succ_stores);
+ debugfs_create_u64("failed_stores", S_IRUGO, root,
+ &frontswap_failed_stores);
+ debugfs_create_u64("invalidates", S_IRUGO,
+ root, &frontswap_invalidates);
+#endif
+ return 0;
+}
+
+module_init(init_frontswap);
diff --git a/mm/internal.h b/mm/internal.h
index 5cbb781..2ba87fb 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -94,9 +94,6 @@
/*
* in mm/page_alloc.c
*/
-extern void set_pageblock_migratetype(struct page *page, int migratetype);
-extern int move_freepages_block(struct zone *zone, struct page *page,
- int migratetype);
extern void __free_pages_bootmem(struct page *page, unsigned int order);
extern void prep_compound_page(struct page *page, unsigned long order);
#ifdef CONFIG_MEMORY_FAILURE
@@ -104,7 +101,6 @@
#endif
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
-#include <linux/compaction.h>
/*
* in mm/compaction.c
@@ -123,14 +119,11 @@
unsigned long nr_migratepages; /* Number of pages to migrate */
unsigned long free_pfn; /* isolate_freepages search base */
unsigned long migrate_pfn; /* isolate_migratepages search base */
- enum compact_mode mode; /* Compaction mode */
+ bool sync; /* Synchronous migration */
int order; /* order a direct compactor needs */
int migratetype; /* MOVABLE, RECLAIMABLE etc */
struct zone *zone;
-
- /* Number of UNMOVABLE destination pageblocks skipped during scan */
- unsigned long nr_pageblocks_skipped;
};
unsigned long
diff --git a/mm/migrate.c b/mm/migrate.c
index ab81d48..be26d5c 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -436,7 +436,10 @@
* is actually a signal that all of the page has become dirty.
* Whereas only part of our page may be dirty.
*/
- __set_page_dirty_nobuffers(newpage);
+ if (PageSwapBacked(page))
+ SetPageDirty(newpage);
+ else
+ __set_page_dirty_nobuffers(newpage);
}
mlock_migrate_page(newpage, page);
diff --git a/mm/nommu.c b/mm/nommu.c
index c4acfbc..d4b0c10 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1486,7 +1486,7 @@
flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
- ret = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+ retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
if (file)
fput(file);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index ed0e196..416637f 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -183,7 +183,7 @@
unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
const nodemask_t *nodemask, unsigned long totalpages)
{
- unsigned long points;
+ long points;
if (oom_unkillable_task(p, memcg, nodemask))
return 0;
@@ -223,7 +223,7 @@
* Never return 0 for an eligible task regardless of the root bonus and
* oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here).
*/
- return points ? points : 1;
+ return points > 0 ? points : 1;
}
/*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6092f33..4403009 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -219,7 +219,7 @@
int page_group_by_mobility_disabled __read_mostly;
-void set_pageblock_migratetype(struct page *page, int migratetype)
+static void set_pageblock_migratetype(struct page *page, int migratetype)
{
if (unlikely(page_group_by_mobility_disabled))
@@ -954,8 +954,8 @@
return pages_moved;
}
-int move_freepages_block(struct zone *zone, struct page *page,
- int migratetype)
+static int move_freepages_block(struct zone *zone, struct page *page,
+ int migratetype)
{
unsigned long start_pfn, end_pfn;
struct page *start_page, *end_page;
@@ -5651,7 +5651,7 @@
.nr_migratepages = 0,
.order = -1,
.zone = page_zone(pfn_to_page(start)),
- .mode = COMPACT_SYNC,
+ .sync = true,
};
INIT_LIST_HEAD(&cc.migratepages);
diff --git a/mm/page_io.c b/mm/page_io.c
index dc76b4d..34f0292 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -18,6 +18,7 @@
#include <linux/bio.h>
#include <linux/swapops.h>
#include <linux/writeback.h>
+#include <linux/frontswap.h>
#include <asm/pgtable.h>
static struct bio *get_swap_bio(gfp_t gfp_flags,
@@ -98,6 +99,12 @@
unlock_page(page);
goto out;
}
+ if (frontswap_store(page) == 0) {
+ set_page_writeback(page);
+ unlock_page(page);
+ end_page_writeback(page);
+ goto out;
+ }
bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write);
if (bio == NULL) {
set_page_dirty(page);
@@ -122,6 +129,11 @@
VM_BUG_ON(!PageLocked(page));
VM_BUG_ON(PageUptodate(page));
+ if (frontswap_load(page) == 0) {
+ SetPageUptodate(page);
+ unlock_page(page);
+ goto out;
+ }
bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
if (bio == NULL) {
unlock_page(page);
diff --git a/mm/shmem.c b/mm/shmem.c
index 585bd220..a15a466 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -683,10 +683,21 @@
mutex_lock(&shmem_swaplist_mutex);
/*
* We needed to drop mutex to make that restrictive page
- * allocation; but the inode might already be freed by now,
- * and we cannot refer to inode or mapping or info to check.
- * However, we do hold page lock on the PageSwapCache page,
- * so can check if that still has our reference remaining.
+ * allocation, but the inode might have been freed while we
+ * dropped it: although a racing shmem_evict_inode() cannot
+ * complete without emptying the radix_tree, our page lock
+ * on this swapcache page is not enough to prevent that -
+ * free_swap_and_cache() of our swap entry will only
+ * trylock_page(), removing swap from radix_tree whatever.
+ *
+ * We must not proceed to shmem_add_to_page_cache() if the
+ * inode has been freed, but of course we cannot rely on
+ * inode or mapping or info to check that. However, we can
+ * safely check if our swap entry is still in use (and here
+ * it can't have got reused for another page): if it's still
+ * in use, then the inode cannot have been freed yet, and we
+ * can safely proceed (if it's no longer in use, that tells
+ * nothing about the inode, but we don't need to unuse swap).
*/
if (!page_swapcount(*pagep))
error = -ENOENT;
@@ -730,9 +741,9 @@
/*
* There's a faint possibility that swap page was replaced before
- * caller locked it: it will come back later with the right page.
+ * caller locked it: caller will come back later with the right page.
*/
- if (unlikely(!PageSwapCache(page)))
+ if (unlikely(!PageSwapCache(page) || page_private(page) != swap.val))
goto out;
/*
@@ -995,21 +1006,15 @@
newpage = shmem_alloc_page(gfp, info, index);
if (!newpage)
return -ENOMEM;
- VM_BUG_ON(shmem_should_replace_page(newpage, gfp));
- *pagep = newpage;
page_cache_get(newpage);
copy_highpage(newpage, oldpage);
+ flush_dcache_page(newpage);
- VM_BUG_ON(!PageLocked(oldpage));
__set_page_locked(newpage);
- VM_BUG_ON(!PageUptodate(oldpage));
SetPageUptodate(newpage);
- VM_BUG_ON(!PageSwapBacked(oldpage));
SetPageSwapBacked(newpage);
- VM_BUG_ON(!swap_index);
set_page_private(newpage, swap_index);
- VM_BUG_ON(!PageSwapCache(oldpage));
SetPageSwapCache(newpage);
/*
@@ -1019,13 +1024,24 @@
spin_lock_irq(&swap_mapping->tree_lock);
error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage,
newpage);
- __inc_zone_page_state(newpage, NR_FILE_PAGES);
- __dec_zone_page_state(oldpage, NR_FILE_PAGES);
+ if (!error) {
+ __inc_zone_page_state(newpage, NR_FILE_PAGES);
+ __dec_zone_page_state(oldpage, NR_FILE_PAGES);
+ }
spin_unlock_irq(&swap_mapping->tree_lock);
- BUG_ON(error);
- mem_cgroup_replace_page_cache(oldpage, newpage);
- lru_cache_add_anon(newpage);
+ if (unlikely(error)) {
+ /*
+ * Is this possible? I think not, now that our callers check
+ * both PageSwapCache and page_private after getting page lock;
+ * but be defensive. Reverse old to newpage for clear and free.
+ */
+ oldpage = newpage;
+ } else {
+ mem_cgroup_replace_page_cache(oldpage, newpage);
+ lru_cache_add_anon(newpage);
+ *pagep = newpage;
+ }
ClearPageSwapCache(oldpage);
set_page_private(oldpage, 0);
@@ -1033,7 +1049,7 @@
unlock_page(oldpage);
page_cache_release(oldpage);
page_cache_release(oldpage);
- return 0;
+ return error;
}
/*
@@ -1107,7 +1123,8 @@
/* We have to do this with page locked to prevent races */
lock_page(page);
- if (!PageSwapCache(page) || page->mapping) {
+ if (!PageSwapCache(page) || page_private(page) != swap.val ||
+ page->mapping) {
error = -EEXIST; /* try again */
goto failed;
}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 457b10b..de5bc51 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -31,6 +31,8 @@
#include <linux/memcontrol.h>
#include <linux/poll.h>
#include <linux/oom.h>
+#include <linux/frontswap.h>
+#include <linux/swapfile.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
@@ -42,7 +44,7 @@
static void free_swap_count_continuations(struct swap_info_struct *);
static sector_t map_swap_entry(swp_entry_t, struct block_device**);
-static DEFINE_SPINLOCK(swap_lock);
+DEFINE_SPINLOCK(swap_lock);
static unsigned int nr_swapfiles;
long nr_swap_pages;
long total_swap_pages;
@@ -53,9 +55,9 @@
static const char Bad_offset[] = "Bad swap offset entry ";
static const char Unused_offset[] = "Unused swap offset entry ";
-static struct swap_list_t swap_list = {-1, -1};
+struct swap_list_t swap_list = {-1, -1};
-static struct swap_info_struct *swap_info[MAX_SWAPFILES];
+struct swap_info_struct *swap_info[MAX_SWAPFILES];
static DEFINE_MUTEX(swapon_mutex);
@@ -556,6 +558,7 @@
swap_list.next = p->type;
nr_swap_pages++;
p->inuse_pages--;
+ frontswap_invalidate_page(p->type, offset);
if ((p->flags & SWP_BLKDEV) &&
disk->fops->swap_slot_free_notify)
disk->fops->swap_slot_free_notify(p->bdev, offset);
@@ -985,11 +988,12 @@
}
/*
- * Scan swap_map from current position to next entry still in use.
+ * Scan swap_map (or frontswap_map if frontswap parameter is true)
+ * from current position to next entry still in use.
* Recycle to start on reaching the end, returning 0 when empty.
*/
static unsigned int find_next_to_unuse(struct swap_info_struct *si,
- unsigned int prev)
+ unsigned int prev, bool frontswap)
{
unsigned int max = si->max;
unsigned int i = prev;
@@ -1015,6 +1019,12 @@
prev = 0;
i = 1;
}
+ if (frontswap) {
+ if (frontswap_test(si, i))
+ break;
+ else
+ continue;
+ }
count = si->swap_map[i];
if (count && swap_count(count) != SWAP_MAP_BAD)
break;
@@ -1026,8 +1036,12 @@
* We completely avoid races by reading each swap page in advance,
* and then search for the process using it. All the necessary
* page table adjustments can then be made atomically.
+ *
+ * if the boolean frontswap is true, only unuse pages_to_unuse pages;
+ * pages_to_unuse==0 means all pages; ignored if frontswap is false
*/
-static int try_to_unuse(unsigned int type)
+int try_to_unuse(unsigned int type, bool frontswap,
+ unsigned long pages_to_unuse)
{
struct swap_info_struct *si = swap_info[type];
struct mm_struct *start_mm;
@@ -1060,7 +1074,7 @@
* one pass through swap_map is enough, but not necessarily:
* there are races when an instance of an entry might be missed.
*/
- while ((i = find_next_to_unuse(si, i)) != 0) {
+ while ((i = find_next_to_unuse(si, i, frontswap)) != 0) {
if (signal_pending(current)) {
retval = -EINTR;
break;
@@ -1227,6 +1241,10 @@
* interactive performance.
*/
cond_resched();
+ if (frontswap && pages_to_unuse > 0) {
+ if (!--pages_to_unuse)
+ break;
+ }
}
mmput(start_mm);
@@ -1486,7 +1504,8 @@
}
static void enable_swap_info(struct swap_info_struct *p, int prio,
- unsigned char *swap_map)
+ unsigned char *swap_map,
+ unsigned long *frontswap_map)
{
int i, prev;
@@ -1496,6 +1515,7 @@
else
p->prio = --least_priority;
p->swap_map = swap_map;
+ frontswap_map_set(p, frontswap_map);
p->flags |= SWP_WRITEOK;
nr_swap_pages += p->pages;
total_swap_pages += p->pages;
@@ -1512,6 +1532,7 @@
swap_list.head = swap_list.next = p->type;
else
swap_info[prev]->next = p->type;
+ frontswap_init(p->type);
spin_unlock(&swap_lock);
}
@@ -1585,7 +1606,7 @@
spin_unlock(&swap_lock);
oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
- err = try_to_unuse(type);
+ err = try_to_unuse(type, false, 0); /* force all pages to be unused */
compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, oom_score_adj);
if (err) {
@@ -1596,7 +1617,7 @@
* sys_swapoff for this swap_info_struct at this point.
*/
/* re-insert swap space back into swap_list */
- enable_swap_info(p, p->prio, p->swap_map);
+ enable_swap_info(p, p->prio, p->swap_map, frontswap_map_get(p));
goto out_dput;
}
@@ -1622,9 +1643,11 @@
swap_map = p->swap_map;
p->swap_map = NULL;
p->flags = 0;
+ frontswap_invalidate_area(type);
spin_unlock(&swap_lock);
mutex_unlock(&swapon_mutex);
vfree(swap_map);
+ vfree(frontswap_map_get(p));
/* Destroy swap account informatin */
swap_cgroup_swapoff(type);
@@ -1988,6 +2011,7 @@
sector_t span;
unsigned long maxpages;
unsigned char *swap_map = NULL;
+ unsigned long *frontswap_map = NULL;
struct page *page = NULL;
struct inode *inode = NULL;
@@ -2071,6 +2095,9 @@
error = nr_extents;
goto bad_swap;
}
+ /* frontswap enabled? set up bit-per-page map for frontswap */
+ if (frontswap_enabled)
+ frontswap_map = vzalloc(maxpages / sizeof(long));
if (p->bdev) {
if (blk_queue_nonrot(bdev_get_queue(p->bdev))) {
@@ -2086,14 +2113,15 @@
if (swap_flags & SWAP_FLAG_PREFER)
prio =
(swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT;
- enable_swap_info(p, prio, swap_map);
+ enable_swap_info(p, prio, swap_map, frontswap_map);
printk(KERN_INFO "Adding %uk swap on %s. "
- "Priority:%d extents:%d across:%lluk %s%s\n",
+ "Priority:%d extents:%d across:%lluk %s%s%s\n",
p->pages<<(PAGE_SHIFT-10), name, p->prio,
nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10),
(p->flags & SWP_SOLIDSTATE) ? "SS" : "",
- (p->flags & SWP_DISCARDABLE) ? "D" : "");
+ (p->flags & SWP_DISCARDABLE) ? "D" : "",
+ (frontswap_map) ? "FS" : "");
mutex_unlock(&swapon_mutex);
atomic_inc(&proc_poll_event);
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 0301b32..8685296 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1208,9 +1208,7 @@
if (addr->sat_addr.s_node == ATADDR_BCAST &&
!sock_flag(sk, SOCK_BROADCAST)) {
#if 1
- printk(KERN_WARNING "%s is broken and did not set "
- "SO_BROADCAST. It will break when 2.2 is "
- "released.\n",
+ pr_warn("atalk_connect: %s is broken and did not set SO_BROADCAST.\n",
current->comm);
#else
return -EACCES;
diff --git a/net/can/raw.c b/net/can/raw.c
index cde1b4a..46cca3a 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -681,9 +681,6 @@
if (err < 0)
goto free_skb;
- /* to be able to check the received tx sock reference in raw_rcv() */
- skb_shinfo(skb)->tx_flags |= SKBTX_DRV_NEEDS_SK_REF;
-
skb->dev = dev;
skb->sk = sk;
diff --git a/net/core/dev.c b/net/core/dev.c
index cd09819..57c4f9b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2089,25 +2089,6 @@
return 0;
}
-/*
- * Try to orphan skb early, right before transmission by the device.
- * We cannot orphan skb if tx timestamp is requested or the sk-reference
- * is needed on driver level for other reasons, e.g. see net/can/raw.c
- */
-static inline void skb_orphan_try(struct sk_buff *skb)
-{
- struct sock *sk = skb->sk;
-
- if (sk && !skb_shinfo(skb)->tx_flags) {
- /* skb_tx_hash() wont be able to get sk.
- * We copy sk_hash into skb->rxhash
- */
- if (!skb->rxhash)
- skb->rxhash = sk->sk_hash;
- skb_orphan(skb);
- }
-}
-
static bool can_checksum_protocol(netdev_features_t features, __be16 protocol)
{
return ((features & NETIF_F_GEN_CSUM) ||
@@ -2193,8 +2174,6 @@
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(skb, dev);
- skb_orphan_try(skb);
-
features = netif_skb_features(skb);
if (vlan_tx_tag_present(skb) &&
@@ -2304,7 +2283,7 @@
if (skb->sk && skb->sk->sk_hash)
hash = skb->sk->sk_hash;
else
- hash = (__force u16) skb->protocol ^ skb->rxhash;
+ hash = (__force u16) skb->protocol;
hash = jhash_1word(hash, hashrnd);
return (u16) (((u64) hash * qcount) >> 32) + qoffset;
@@ -2476,6 +2455,23 @@
#define RECURSION_LIMIT 10
/**
+ * dev_loopback_xmit - loop back @skb
+ * @skb: buffer to transmit
+ */
+int dev_loopback_xmit(struct sk_buff *skb)
+{
+ skb_reset_mac_header(skb);
+ __skb_pull(skb, skb_network_offset(skb));
+ skb->pkt_type = PACKET_LOOPBACK;
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ WARN_ON(!skb_dst(skb));
+ skb_dst_force(skb);
+ netif_rx_ni(skb);
+ return 0;
+}
+EXPORT_SYMBOL(dev_loopback_xmit);
+
+/**
* dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
*
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index c73d0a5..cbf033d 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1443,6 +1443,7 @@
case ETHTOOL_GSET:
case ETHTOOL_GDRVINFO:
case ETHTOOL_GMSGLVL:
+ case ETHTOOL_GLINK:
case ETHTOOL_GCOALESCE:
case ETHTOOL_GRINGPARAM:
case ETHTOOL_GPAUSEPARAM:
@@ -1451,6 +1452,7 @@
case ETHTOOL_GSG:
case ETHTOOL_GSSET_INFO:
case ETHTOOL_GSTRINGS:
+ case ETHTOOL_GSTATS:
case ETHTOOL_GTSO:
case ETHTOOL_GPERMADDR:
case ETHTOOL_GUFO:
@@ -1463,8 +1465,11 @@
case ETHTOOL_GRXCLSRLCNT:
case ETHTOOL_GRXCLSRULE:
case ETHTOOL_GRXCLSRLALL:
+ case ETHTOOL_GRXFHINDIR:
case ETHTOOL_GFEATURES:
+ case ETHTOOL_GCHANNELS:
case ETHTOOL_GET_TS_INFO:
+ case ETHTOOL_GEEE:
break;
default:
if (!capable(CAP_NET_ADMIN))
diff --git a/net/core/filter.c b/net/core/filter.c
index a3eddb5..d4ce2dc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -616,9 +616,9 @@
/**
* sk_unattached_filter_create - create an unattached filter
* @fprog: the filter program
- * @sk: the socket to use
+ * @pfp: the unattached filter that is created
*
- * Create a filter independent ofr any socket. We first run some
+ * Create a filter independent of any socket. We first run some
* sanity checks on it to make sure it does not explode on us later.
* If an error occurs or there is insufficient memory for the filter
* a negative errno code is returned. On success the return is zero.
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index eb09f8b..d81d026 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2219,9 +2219,7 @@
rcu_read_lock_bh();
nht = rcu_dereference_bh(tbl->nht);
- for (h = 0; h < (1 << nht->hash_shift); h++) {
- if (h < s_h)
- continue;
+ for (h = s_h; h < (1 << nht->hash_shift); h++) {
if (h > s_h)
s_idx = 0;
for (n = rcu_dereference_bh(nht->hash_buckets[h]), idx = 0;
@@ -2260,9 +2258,7 @@
read_lock_bh(&tbl->lock);
- for (h = 0; h <= PNEIGH_HASHMASK; h++) {
- if (h < s_h)
- continue;
+ for (h = s_h; h <= PNEIGH_HASHMASK; h++) {
if (h > s_h)
s_idx = 0;
for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) {
@@ -2297,7 +2293,7 @@
struct neigh_table *tbl;
int t, family, s_t;
int proxy = 0;
- int err = 0;
+ int err;
read_lock(&neigh_tbl_lock);
family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;
@@ -2311,7 +2307,7 @@
s_t = cb->args[0];
- for (tbl = neigh_tables, t = 0; tbl && (err >= 0);
+ for (tbl = neigh_tables, t = 0; tbl;
tbl = tbl->next, t++) {
if (t < s_t || (family && tbl->family != family))
continue;
@@ -2322,6 +2318,8 @@
err = pneigh_dump_table(tbl, skb, cb);
else
err = neigh_dump_table(tbl, skb, cb);
+ if (err < 0)
+ break;
}
read_unlock(&neigh_tbl_lock);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 3d84fb9..f9f40b9 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -362,22 +362,23 @@
void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
{
- int total_len, eth_len, ip_len, udp_len;
+ int total_len, ip_len, udp_len;
struct sk_buff *skb;
struct udphdr *udph;
struct iphdr *iph;
struct ethhdr *eth;
udp_len = len + sizeof(*udph);
- ip_len = eth_len = udp_len + sizeof(*iph);
- total_len = eth_len + ETH_HLEN + NET_IP_ALIGN;
+ ip_len = udp_len + sizeof(*iph);
+ total_len = ip_len + LL_RESERVED_SPACE(np->dev);
- skb = find_skb(np, total_len, total_len - len);
+ skb = find_skb(np, total_len + np->dev->needed_tailroom,
+ total_len - len);
if (!skb)
return;
skb_copy_to_linear_data(skb, msg, len);
- skb->len += len;
+ skb_put(skb, len);
skb_push(skb, sizeof(*udph));
skb_reset_transport_header(skb);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1d74cea..5b21522 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3361,7 +3361,7 @@
* @to: prior buffer
* @from: buffer to add
* @fragstolen: pointer to boolean
- *
+ * @delta_truesize: how much more was allocated than was requested
*/
bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
bool *fragstolen, int *delta_truesize)
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 656c7c7..0a36007 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -196,92 +196,66 @@
static LIST_HEAD(dcb_app_list);
static DEFINE_SPINLOCK(dcb_lock);
-/* standard netlink reply call */
-static int dcbnl_reply(u8 value, u8 event, u8 cmd, u8 attr, u32 pid,
- u32 seq, u16 flags)
+static struct sk_buff *dcbnl_newmsg(int type, u8 cmd, u32 port, u32 seq,
+ u32 flags, struct nlmsghdr **nlhp)
{
- struct sk_buff *dcbnl_skb;
+ struct sk_buff *skb;
struct dcbmsg *dcb;
struct nlmsghdr *nlh;
- int ret = -EINVAL;
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb)
- return ret;
+ skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!skb)
+ return NULL;
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, event, sizeof(*dcb), flags);
+ nlh = nlmsg_put(skb, port, seq, type, sizeof(*dcb), flags);
+ BUG_ON(!nlh);
- dcb = NLMSG_DATA(nlh);
+ dcb = nlmsg_data(nlh);
dcb->dcb_family = AF_UNSPEC;
dcb->cmd = cmd;
dcb->dcb_pad = 0;
- ret = nla_put_u8(dcbnl_skb, attr, value);
- if (ret)
- goto err;
+ if (nlhp)
+ *nlhp = nlh;
- /* end the message, assign the nlmsg_len. */
- nlmsg_end(dcbnl_skb, nlh);
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret)
- return -EINVAL;
-
- return 0;
-nlmsg_failure:
-err:
- kfree_skb(dcbnl_skb);
- return ret;
+ return skb;
}
-static int dcbnl_getstate(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getstate(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int ret = -EINVAL;
-
/* if (!tb[DCB_ATTR_STATE] || !netdev->dcbnl_ops->getstate) */
if (!netdev->dcbnl_ops->getstate)
- return ret;
+ return -EOPNOTSUPP;
- ret = dcbnl_reply(netdev->dcbnl_ops->getstate(netdev), RTM_GETDCB,
- DCB_CMD_GSTATE, DCB_ATTR_STATE, pid, seq, flags);
-
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_STATE,
+ netdev->dcbnl_ops->getstate(netdev));
}
-static int dcbnl_getpfccfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getpfccfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
struct nlattr *data[DCB_PFC_UP_ATTR_MAX + 1], *nest;
u8 value;
- int ret = -EINVAL;
+ int ret;
int i;
int getall = 0;
- if (!tb[DCB_ATTR_PFC_CFG] || !netdev->dcbnl_ops->getpfccfg)
- return ret;
+ if (!tb[DCB_ATTR_PFC_CFG])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->getpfccfg)
+ return -EOPNOTSUPP;
ret = nla_parse_nested(data, DCB_PFC_UP_ATTR_MAX,
tb[DCB_ATTR_PFC_CFG],
dcbnl_pfc_up_nest);
if (ret)
- goto err_out;
+ return ret;
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb)
- goto err_out;
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_PFC_GCFG;
-
- nest = nla_nest_start(dcbnl_skb, DCB_ATTR_PFC_CFG);
+ nest = nla_nest_start(skb, DCB_ATTR_PFC_CFG);
if (!nest)
- goto err;
+ return -EMSGSIZE;
if (data[DCB_PFC_UP_ATTR_ALL])
getall = 1;
@@ -292,103 +266,53 @@
netdev->dcbnl_ops->getpfccfg(netdev, i - DCB_PFC_UP_ATTR_0,
&value);
- ret = nla_put_u8(dcbnl_skb, i, value);
-
+ ret = nla_put_u8(skb, i, value);
if (ret) {
- nla_nest_cancel(dcbnl_skb, nest);
- goto err;
+ nla_nest_cancel(skb, nest);
+ return ret;
}
}
- nla_nest_end(dcbnl_skb, nest);
-
- nlmsg_end(dcbnl_skb, nlh);
-
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret)
- goto err_out;
+ nla_nest_end(skb, nest);
return 0;
-nlmsg_failure:
-err:
- kfree_skb(dcbnl_skb);
-err_out:
- return -EINVAL;
}
-static int dcbnl_getperm_hwaddr(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getperm_hwaddr(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
u8 perm_addr[MAX_ADDR_LEN];
- int ret = -EINVAL;
if (!netdev->dcbnl_ops->getpermhwaddr)
- return ret;
-
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb)
- goto err_out;
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_GPERM_HWADDR;
+ return -EOPNOTSUPP;
netdev->dcbnl_ops->getpermhwaddr(netdev, perm_addr);
- ret = nla_put(dcbnl_skb, DCB_ATTR_PERM_HWADDR, sizeof(perm_addr),
- perm_addr);
-
- nlmsg_end(dcbnl_skb, nlh);
-
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret)
- goto err_out;
-
- return 0;
-
-nlmsg_failure:
- kfree_skb(dcbnl_skb);
-err_out:
- return -EINVAL;
+ return nla_put(skb, DCB_ATTR_PERM_HWADDR, sizeof(perm_addr), perm_addr);
}
-static int dcbnl_getcap(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getcap(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
struct nlattr *data[DCB_CAP_ATTR_MAX + 1], *nest;
u8 value;
- int ret = -EINVAL;
+ int ret;
int i;
int getall = 0;
- if (!tb[DCB_ATTR_CAP] || !netdev->dcbnl_ops->getcap)
- return ret;
+ if (!tb[DCB_ATTR_CAP])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->getcap)
+ return -EOPNOTSUPP;
ret = nla_parse_nested(data, DCB_CAP_ATTR_MAX, tb[DCB_ATTR_CAP],
dcbnl_cap_nest);
if (ret)
- goto err_out;
+ return ret;
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb)
- goto err_out;
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_GCAP;
-
- nest = nla_nest_start(dcbnl_skb, DCB_ATTR_CAP);
+ nest = nla_nest_start(skb, DCB_ATTR_CAP);
if (!nest)
- goto err;
+ return -EMSGSIZE;
if (data[DCB_CAP_ATTR_ALL])
getall = 1;
@@ -398,69 +322,41 @@
continue;
if (!netdev->dcbnl_ops->getcap(netdev, i, &value)) {
- ret = nla_put_u8(dcbnl_skb, i, value);
-
+ ret = nla_put_u8(skb, i, value);
if (ret) {
- nla_nest_cancel(dcbnl_skb, nest);
- goto err;
+ nla_nest_cancel(skb, nest);
+ return ret;
}
}
}
- nla_nest_end(dcbnl_skb, nest);
-
- nlmsg_end(dcbnl_skb, nlh);
-
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret)
- goto err_out;
+ nla_nest_end(skb, nest);
return 0;
-nlmsg_failure:
-err:
- kfree_skb(dcbnl_skb);
-err_out:
- return -EINVAL;
}
-static int dcbnl_getnumtcs(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getnumtcs(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
struct nlattr *data[DCB_NUMTCS_ATTR_MAX + 1], *nest;
u8 value;
- int ret = -EINVAL;
+ int ret;
int i;
int getall = 0;
- if (!tb[DCB_ATTR_NUMTCS] || !netdev->dcbnl_ops->getnumtcs)
- return ret;
+ if (!tb[DCB_ATTR_NUMTCS])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->getnumtcs)
+ return -EOPNOTSUPP;
ret = nla_parse_nested(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS],
dcbnl_numtcs_nest);
- if (ret) {
- ret = -EINVAL;
- goto err_out;
- }
+ if (ret)
+ return ret;
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb) {
- ret = -EINVAL;
- goto err_out;
- }
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_GNUMTCS;
-
- nest = nla_nest_start(dcbnl_skb, DCB_ATTR_NUMTCS);
- if (!nest) {
- ret = -EINVAL;
- goto err;
- }
+ nest = nla_nest_start(skb, DCB_ATTR_NUMTCS);
+ if (!nest)
+ return -EMSGSIZE;
if (data[DCB_NUMTCS_ATTR_ALL])
getall = 1;
@@ -471,53 +367,37 @@
ret = netdev->dcbnl_ops->getnumtcs(netdev, i, &value);
if (!ret) {
- ret = nla_put_u8(dcbnl_skb, i, value);
-
+ ret = nla_put_u8(skb, i, value);
if (ret) {
- nla_nest_cancel(dcbnl_skb, nest);
- ret = -EINVAL;
- goto err;
+ nla_nest_cancel(skb, nest);
+ return ret;
}
- } else {
- goto err;
- }
+ } else
+ return -EINVAL;
}
- nla_nest_end(dcbnl_skb, nest);
-
- nlmsg_end(dcbnl_skb, nlh);
-
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret) {
- ret = -EINVAL;
- goto err_out;
- }
+ nla_nest_end(skb, nest);
return 0;
-nlmsg_failure:
-err:
- kfree_skb(dcbnl_skb);
-err_out:
- return ret;
}
-static int dcbnl_setnumtcs(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setnumtcs(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
struct nlattr *data[DCB_NUMTCS_ATTR_MAX + 1];
- int ret = -EINVAL;
+ int ret;
u8 value;
int i;
- if (!tb[DCB_ATTR_NUMTCS] || !netdev->dcbnl_ops->setnumtcs)
- return ret;
+ if (!tb[DCB_ATTR_NUMTCS])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->setnumtcs)
+ return -EOPNOTSUPP;
ret = nla_parse_nested(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS],
dcbnl_numtcs_nest);
-
- if (ret) {
- ret = -EINVAL;
- goto err;
- }
+ if (ret)
+ return ret;
for (i = DCB_NUMTCS_ATTR_ALL+1; i <= DCB_NUMTCS_ATTR_MAX; i++) {
if (data[i] == NULL)
@@ -526,84 +406,68 @@
value = nla_get_u8(data[i]);
ret = netdev->dcbnl_ops->setnumtcs(netdev, i, value);
-
if (ret)
- goto operr;
+ break;
}
-operr:
- ret = dcbnl_reply(!!ret, RTM_SETDCB, DCB_CMD_SNUMTCS,
- DCB_ATTR_NUMTCS, pid, seq, flags);
-
-err:
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_NUMTCS, !!ret);
}
-static int dcbnl_getpfcstate(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getpfcstate(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int ret = -EINVAL;
-
if (!netdev->dcbnl_ops->getpfcstate)
- return ret;
+ return -EOPNOTSUPP;
- ret = dcbnl_reply(netdev->dcbnl_ops->getpfcstate(netdev), RTM_GETDCB,
- DCB_CMD_PFC_GSTATE, DCB_ATTR_PFC_STATE,
- pid, seq, flags);
-
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_PFC_STATE,
+ netdev->dcbnl_ops->getpfcstate(netdev));
}
-static int dcbnl_setpfcstate(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setpfcstate(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int ret = -EINVAL;
u8 value;
- if (!tb[DCB_ATTR_PFC_STATE] || !netdev->dcbnl_ops->setpfcstate)
- return ret;
+ if (!tb[DCB_ATTR_PFC_STATE])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->setpfcstate)
+ return -EOPNOTSUPP;
value = nla_get_u8(tb[DCB_ATTR_PFC_STATE]);
netdev->dcbnl_ops->setpfcstate(netdev, value);
- ret = dcbnl_reply(0, RTM_SETDCB, DCB_CMD_PFC_SSTATE, DCB_ATTR_PFC_STATE,
- pid, seq, flags);
-
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_PFC_STATE, 0);
}
-static int dcbnl_getapp(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getapp(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
struct nlattr *app_nest;
struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1];
u16 id;
u8 up, idtype;
- int ret = -EINVAL;
+ int ret;
if (!tb[DCB_ATTR_APP])
- goto out;
+ return -EINVAL;
ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP],
dcbnl_app_nest);
if (ret)
- goto out;
+ return ret;
- ret = -EINVAL;
/* all must be non-null */
if ((!app_tb[DCB_APP_ATTR_IDTYPE]) ||
(!app_tb[DCB_APP_ATTR_ID]))
- goto out;
+ return -EINVAL;
/* either by eth type or by socket number */
idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]);
if ((idtype != DCB_APP_IDTYPE_ETHTYPE) &&
(idtype != DCB_APP_IDTYPE_PORTNUM))
- goto out;
+ return -EINVAL;
id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]);
@@ -617,138 +481,106 @@
up = dcb_getapp(netdev, &app);
}
- /* send this back */
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb)
- goto out;
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_GAPP;
-
- app_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_APP);
+ app_nest = nla_nest_start(skb, DCB_ATTR_APP);
if (!app_nest)
- goto out_cancel;
+ return -EMSGSIZE;
- ret = nla_put_u8(dcbnl_skb, DCB_APP_ATTR_IDTYPE, idtype);
+ ret = nla_put_u8(skb, DCB_APP_ATTR_IDTYPE, idtype);
if (ret)
goto out_cancel;
- ret = nla_put_u16(dcbnl_skb, DCB_APP_ATTR_ID, id);
+ ret = nla_put_u16(skb, DCB_APP_ATTR_ID, id);
if (ret)
goto out_cancel;
- ret = nla_put_u8(dcbnl_skb, DCB_APP_ATTR_PRIORITY, up);
+ ret = nla_put_u8(skb, DCB_APP_ATTR_PRIORITY, up);
if (ret)
goto out_cancel;
- nla_nest_end(dcbnl_skb, app_nest);
- nlmsg_end(dcbnl_skb, nlh);
+ nla_nest_end(skb, app_nest);
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret)
- goto nlmsg_failure;
-
- goto out;
+ return 0;
out_cancel:
- nla_nest_cancel(dcbnl_skb, app_nest);
-nlmsg_failure:
- kfree_skb(dcbnl_skb);
-out:
+ nla_nest_cancel(skb, app_nest);
return ret;
}
-static int dcbnl_setapp(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setapp(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int err, ret = -EINVAL;
+ int ret;
u16 id;
u8 up, idtype;
struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1];
if (!tb[DCB_ATTR_APP])
- goto out;
+ return -EINVAL;
ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP],
dcbnl_app_nest);
if (ret)
- goto out;
+ return ret;
- ret = -EINVAL;
/* all must be non-null */
if ((!app_tb[DCB_APP_ATTR_IDTYPE]) ||
(!app_tb[DCB_APP_ATTR_ID]) ||
(!app_tb[DCB_APP_ATTR_PRIORITY]))
- goto out;
+ return -EINVAL;
/* either by eth type or by socket number */
idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]);
if ((idtype != DCB_APP_IDTYPE_ETHTYPE) &&
(idtype != DCB_APP_IDTYPE_PORTNUM))
- goto out;
+ return -EINVAL;
id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]);
up = nla_get_u8(app_tb[DCB_APP_ATTR_PRIORITY]);
if (netdev->dcbnl_ops->setapp) {
- err = netdev->dcbnl_ops->setapp(netdev, idtype, id, up);
+ ret = netdev->dcbnl_ops->setapp(netdev, idtype, id, up);
} else {
struct dcb_app app;
app.selector = idtype;
app.protocol = id;
app.priority = up;
- err = dcb_setapp(netdev, &app);
+ ret = dcb_setapp(netdev, &app);
}
- ret = dcbnl_reply(err, RTM_SETDCB, DCB_CMD_SAPP, DCB_ATTR_APP,
- pid, seq, flags);
+ ret = nla_put_u8(skb, DCB_ATTR_APP, ret);
dcbnl_cee_notify(netdev, RTM_SETDCB, DCB_CMD_SAPP, seq, 0);
-out:
+
return ret;
}
-static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags, int dir)
+static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ struct nlattr **tb, struct sk_buff *skb, int dir)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
struct nlattr *pg_nest, *param_nest, *data;
struct nlattr *pg_tb[DCB_PG_ATTR_MAX + 1];
struct nlattr *param_tb[DCB_TC_ATTR_PARAM_MAX + 1];
u8 prio, pgid, tc_pct, up_map;
- int ret = -EINVAL;
+ int ret;
int getall = 0;
int i;
- if (!tb[DCB_ATTR_PG_CFG] ||
- !netdev->dcbnl_ops->getpgtccfgtx ||
+ if (!tb[DCB_ATTR_PG_CFG])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->getpgtccfgtx ||
!netdev->dcbnl_ops->getpgtccfgrx ||
!netdev->dcbnl_ops->getpgbwgcfgtx ||
!netdev->dcbnl_ops->getpgbwgcfgrx)
- return ret;
+ return -EOPNOTSUPP;
ret = nla_parse_nested(pg_tb, DCB_PG_ATTR_MAX,
tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest);
-
if (ret)
- goto err_out;
+ return ret;
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb)
- goto err_out;
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = (dir) ? DCB_CMD_PGRX_GCFG : DCB_CMD_PGTX_GCFG;
-
- pg_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_PG_CFG);
+ pg_nest = nla_nest_start(skb, DCB_ATTR_PG_CFG);
if (!pg_nest)
- goto err;
+ return -EMSGSIZE;
if (pg_tb[DCB_PG_ATTR_TC_ALL])
getall = 1;
@@ -766,7 +598,7 @@
if (ret)
goto err_pg;
- param_nest = nla_nest_start(dcbnl_skb, i);
+ param_nest = nla_nest_start(skb, i);
if (!param_nest)
goto err_pg;
@@ -789,33 +621,33 @@
if (param_tb[DCB_TC_ATTR_PARAM_PGID] ||
param_tb[DCB_TC_ATTR_PARAM_ALL]) {
- ret = nla_put_u8(dcbnl_skb,
+ ret = nla_put_u8(skb,
DCB_TC_ATTR_PARAM_PGID, pgid);
if (ret)
goto err_param;
}
if (param_tb[DCB_TC_ATTR_PARAM_UP_MAPPING] ||
param_tb[DCB_TC_ATTR_PARAM_ALL]) {
- ret = nla_put_u8(dcbnl_skb,
+ ret = nla_put_u8(skb,
DCB_TC_ATTR_PARAM_UP_MAPPING, up_map);
if (ret)
goto err_param;
}
if (param_tb[DCB_TC_ATTR_PARAM_STRICT_PRIO] ||
param_tb[DCB_TC_ATTR_PARAM_ALL]) {
- ret = nla_put_u8(dcbnl_skb,
+ ret = nla_put_u8(skb,
DCB_TC_ATTR_PARAM_STRICT_PRIO, prio);
if (ret)
goto err_param;
}
if (param_tb[DCB_TC_ATTR_PARAM_BW_PCT] ||
param_tb[DCB_TC_ATTR_PARAM_ALL]) {
- ret = nla_put_u8(dcbnl_skb, DCB_TC_ATTR_PARAM_BW_PCT,
+ ret = nla_put_u8(skb, DCB_TC_ATTR_PARAM_BW_PCT,
tc_pct);
if (ret)
goto err_param;
}
- nla_nest_end(dcbnl_skb, param_nest);
+ nla_nest_end(skb, param_nest);
}
if (pg_tb[DCB_PG_ATTR_BW_ID_ALL])
@@ -838,80 +670,71 @@
netdev->dcbnl_ops->getpgbwgcfgtx(netdev,
i - DCB_PG_ATTR_BW_ID_0, &tc_pct);
}
- ret = nla_put_u8(dcbnl_skb, i, tc_pct);
-
+ ret = nla_put_u8(skb, i, tc_pct);
if (ret)
goto err_pg;
}
- nla_nest_end(dcbnl_skb, pg_nest);
-
- nlmsg_end(dcbnl_skb, nlh);
-
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret)
- goto err_out;
+ nla_nest_end(skb, pg_nest);
return 0;
err_param:
- nla_nest_cancel(dcbnl_skb, param_nest);
+ nla_nest_cancel(skb, param_nest);
err_pg:
- nla_nest_cancel(dcbnl_skb, pg_nest);
-nlmsg_failure:
-err:
- kfree_skb(dcbnl_skb);
-err_out:
- ret = -EINVAL;
- return ret;
+ nla_nest_cancel(skb, pg_nest);
+
+ return -EMSGSIZE;
}
-static int dcbnl_pgtx_getcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_pgtx_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- return __dcbnl_pg_getcfg(netdev, tb, pid, seq, flags, 0);
+ return __dcbnl_pg_getcfg(netdev, nlh, tb, skb, 0);
}
-static int dcbnl_pgrx_getcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_pgrx_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- return __dcbnl_pg_getcfg(netdev, tb, pid, seq, flags, 1);
+ return __dcbnl_pg_getcfg(netdev, nlh, tb, skb, 1);
}
-static int dcbnl_setstate(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setstate(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int ret = -EINVAL;
u8 value;
- if (!tb[DCB_ATTR_STATE] || !netdev->dcbnl_ops->setstate)
- return ret;
+ if (!tb[DCB_ATTR_STATE])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->setstate)
+ return -EOPNOTSUPP;
value = nla_get_u8(tb[DCB_ATTR_STATE]);
- ret = dcbnl_reply(netdev->dcbnl_ops->setstate(netdev, value),
- RTM_SETDCB, DCB_CMD_SSTATE, DCB_ATTR_STATE,
- pid, seq, flags);
-
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_STATE,
+ netdev->dcbnl_ops->setstate(netdev, value));
}
-static int dcbnl_setpfccfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setpfccfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
struct nlattr *data[DCB_PFC_UP_ATTR_MAX + 1];
int i;
- int ret = -EINVAL;
+ int ret;
u8 value;
- if (!tb[DCB_ATTR_PFC_CFG] || !netdev->dcbnl_ops->setpfccfg)
- return ret;
+ if (!tb[DCB_ATTR_PFC_CFG])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->setpfccfg)
+ return -EOPNOTSUPP;
ret = nla_parse_nested(data, DCB_PFC_UP_ATTR_MAX,
tb[DCB_ATTR_PFC_CFG],
dcbnl_pfc_up_nest);
if (ret)
- goto err;
+ return ret;
for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) {
if (data[i] == NULL)
@@ -921,50 +744,53 @@
data[i]->nla_type - DCB_PFC_UP_ATTR_0, value);
}
- ret = dcbnl_reply(0, RTM_SETDCB, DCB_CMD_PFC_SCFG, DCB_ATTR_PFC_CFG,
- pid, seq, flags);
-err:
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_PFC_CFG, 0);
}
-static int dcbnl_setall(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setall(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int ret = -EINVAL;
+ int ret;
- if (!tb[DCB_ATTR_SET_ALL] || !netdev->dcbnl_ops->setall)
- return ret;
+ if (!tb[DCB_ATTR_SET_ALL])
+ return -EINVAL;
- ret = dcbnl_reply(netdev->dcbnl_ops->setall(netdev), RTM_SETDCB,
- DCB_CMD_SET_ALL, DCB_ATTR_SET_ALL, pid, seq, flags);
+ if (!netdev->dcbnl_ops->setall)
+ return -EOPNOTSUPP;
+
+ ret = nla_put_u8(skb, DCB_ATTR_SET_ALL,
+ netdev->dcbnl_ops->setall(netdev));
dcbnl_cee_notify(netdev, RTM_SETDCB, DCB_CMD_SET_ALL, seq, 0);
return ret;
}
-static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags, int dir)
+static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb,
+ int dir)
{
struct nlattr *pg_tb[DCB_PG_ATTR_MAX + 1];
struct nlattr *param_tb[DCB_TC_ATTR_PARAM_MAX + 1];
- int ret = -EINVAL;
+ int ret;
int i;
u8 pgid;
u8 up_map;
u8 prio;
u8 tc_pct;
- if (!tb[DCB_ATTR_PG_CFG] ||
- !netdev->dcbnl_ops->setpgtccfgtx ||
+ if (!tb[DCB_ATTR_PG_CFG])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->setpgtccfgtx ||
!netdev->dcbnl_ops->setpgtccfgrx ||
!netdev->dcbnl_ops->setpgbwgcfgtx ||
!netdev->dcbnl_ops->setpgbwgcfgrx)
- return ret;
+ return -EOPNOTSUPP;
ret = nla_parse_nested(pg_tb, DCB_PG_ATTR_MAX,
tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest);
if (ret)
- goto err;
+ return ret;
for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) {
if (!pg_tb[i])
@@ -973,7 +799,7 @@
ret = nla_parse_nested(param_tb, DCB_TC_ATTR_PARAM_MAX,
pg_tb[i], dcbnl_tc_param_nest);
if (ret)
- goto err;
+ return ret;
pgid = DCB_ATTR_VALUE_UNDEFINED;
prio = DCB_ATTR_VALUE_UNDEFINED;
@@ -1026,63 +852,48 @@
}
}
- ret = dcbnl_reply(0, RTM_SETDCB,
- (dir ? DCB_CMD_PGRX_SCFG : DCB_CMD_PGTX_SCFG),
- DCB_ATTR_PG_CFG, pid, seq, flags);
-
-err:
- return ret;
+ return nla_put_u8(skb,
+ (dir ? DCB_CMD_PGRX_SCFG : DCB_CMD_PGTX_SCFG), 0);
}
-static int dcbnl_pgtx_setcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_pgtx_setcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- return __dcbnl_pg_setcfg(netdev, tb, pid, seq, flags, 0);
+ return __dcbnl_pg_setcfg(netdev, nlh, seq, tb, skb, 0);
}
-static int dcbnl_pgrx_setcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_pgrx_setcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- return __dcbnl_pg_setcfg(netdev, tb, pid, seq, flags, 1);
+ return __dcbnl_pg_setcfg(netdev, nlh, seq, tb, skb, 1);
}
-static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
struct nlattr *bcn_nest;
struct nlattr *bcn_tb[DCB_BCN_ATTR_MAX + 1];
u8 value_byte;
u32 value_integer;
- int ret = -EINVAL;
+ int ret;
bool getall = false;
int i;
- if (!tb[DCB_ATTR_BCN] || !netdev->dcbnl_ops->getbcnrp ||
+ if (!tb[DCB_ATTR_BCN])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->getbcnrp ||
!netdev->dcbnl_ops->getbcncfg)
- return ret;
+ return -EOPNOTSUPP;
ret = nla_parse_nested(bcn_tb, DCB_BCN_ATTR_MAX,
tb[DCB_ATTR_BCN], dcbnl_bcn_nest);
-
if (ret)
- goto err_out;
+ return ret;
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb)
- goto err_out;
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_BCN_GCFG;
-
- bcn_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_BCN);
+ bcn_nest = nla_nest_start(skb, DCB_ATTR_BCN);
if (!bcn_nest)
- goto err;
+ return -EMSGSIZE;
if (bcn_tb[DCB_BCN_ATTR_ALL])
getall = true;
@@ -1093,7 +904,7 @@
netdev->dcbnl_ops->getbcnrp(netdev, i - DCB_BCN_ATTR_RP_0,
&value_byte);
- ret = nla_put_u8(dcbnl_skb, i, value_byte);
+ ret = nla_put_u8(skb, i, value_byte);
if (ret)
goto err_bcn;
}
@@ -1104,49 +915,41 @@
netdev->dcbnl_ops->getbcncfg(netdev, i,
&value_integer);
- ret = nla_put_u32(dcbnl_skb, i, value_integer);
+ ret = nla_put_u32(skb, i, value_integer);
if (ret)
goto err_bcn;
}
- nla_nest_end(dcbnl_skb, bcn_nest);
-
- nlmsg_end(dcbnl_skb, nlh);
-
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret)
- goto err_out;
+ nla_nest_end(skb, bcn_nest);
return 0;
err_bcn:
- nla_nest_cancel(dcbnl_skb, bcn_nest);
-nlmsg_failure:
-err:
- kfree_skb(dcbnl_skb);
-err_out:
- ret = -EINVAL;
+ nla_nest_cancel(skb, bcn_nest);
return ret;
}
-static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
struct nlattr *data[DCB_BCN_ATTR_MAX + 1];
int i;
- int ret = -EINVAL;
+ int ret;
u8 value_byte;
u32 value_int;
- if (!tb[DCB_ATTR_BCN] || !netdev->dcbnl_ops->setbcncfg ||
+ if (!tb[DCB_ATTR_BCN])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->setbcncfg ||
!netdev->dcbnl_ops->setbcnrp)
- return ret;
+ return -EOPNOTSUPP;
ret = nla_parse_nested(data, DCB_BCN_ATTR_MAX,
tb[DCB_ATTR_BCN],
dcbnl_pfc_up_nest);
if (ret)
- goto err;
+ return ret;
for (i = DCB_BCN_ATTR_RP_0; i <= DCB_BCN_ATTR_RP_7; i++) {
if (data[i] == NULL)
@@ -1164,10 +967,7 @@
i, value_int);
}
- ret = dcbnl_reply(0, RTM_SETDCB, DCB_CMD_BCN_SCFG, DCB_ATTR_BCN,
- pid, seq, flags);
-err:
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_BCN, 0);
}
static int dcbnl_build_peer_app(struct net_device *netdev, struct sk_buff* skb,
@@ -1233,20 +1033,21 @@
struct dcb_app_type *itr;
const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
int dcbx;
- int err = -EMSGSIZE;
+ int err;
if (nla_put_string(skb, DCB_ATTR_IFNAME, netdev->name))
- goto nla_put_failure;
+ return -EMSGSIZE;
+
ieee = nla_nest_start(skb, DCB_ATTR_IEEE);
if (!ieee)
- goto nla_put_failure;
+ return -EMSGSIZE;
if (ops->ieee_getets) {
struct ieee_ets ets;
err = ops->ieee_getets(netdev, &ets);
if (!err &&
nla_put(skb, DCB_ATTR_IEEE_ETS, sizeof(ets), &ets))
- goto nla_put_failure;
+ return -EMSGSIZE;
}
if (ops->ieee_getmaxrate) {
@@ -1256,7 +1057,7 @@
err = nla_put(skb, DCB_ATTR_IEEE_MAXRATE,
sizeof(maxrate), &maxrate);
if (err)
- goto nla_put_failure;
+ return -EMSGSIZE;
}
}
@@ -1265,12 +1066,12 @@
err = ops->ieee_getpfc(netdev, &pfc);
if (!err &&
nla_put(skb, DCB_ATTR_IEEE_PFC, sizeof(pfc), &pfc))
- goto nla_put_failure;
+ return -EMSGSIZE;
}
app = nla_nest_start(skb, DCB_ATTR_IEEE_APP_TABLE);
if (!app)
- goto nla_put_failure;
+ return -EMSGSIZE;
spin_lock(&dcb_lock);
list_for_each_entry(itr, &dcb_app_list, list) {
@@ -1279,7 +1080,7 @@
&itr->app);
if (err) {
spin_unlock(&dcb_lock);
- goto nla_put_failure;
+ return -EMSGSIZE;
}
}
}
@@ -1298,7 +1099,7 @@
err = ops->ieee_peer_getets(netdev, &ets);
if (!err &&
nla_put(skb, DCB_ATTR_IEEE_PEER_ETS, sizeof(ets), &ets))
- goto nla_put_failure;
+ return -EMSGSIZE;
}
if (ops->ieee_peer_getpfc) {
@@ -1306,7 +1107,7 @@
err = ops->ieee_peer_getpfc(netdev, &pfc);
if (!err &&
nla_put(skb, DCB_ATTR_IEEE_PEER_PFC, sizeof(pfc), &pfc))
- goto nla_put_failure;
+ return -EMSGSIZE;
}
if (ops->peer_getappinfo && ops->peer_getapptable) {
@@ -1315,20 +1116,17 @@
DCB_ATTR_IEEE_APP_UNSPEC,
DCB_ATTR_IEEE_APP);
if (err)
- goto nla_put_failure;
+ return -EMSGSIZE;
}
nla_nest_end(skb, ieee);
if (dcbx >= 0) {
err = nla_put_u8(skb, DCB_ATTR_DCBX, dcbx);
if (err)
- goto nla_put_failure;
+ return -EMSGSIZE;
}
return 0;
-
-nla_put_failure:
- return err;
}
static int dcbnl_cee_pg_fill(struct sk_buff *skb, struct net_device *dev,
@@ -1340,13 +1138,13 @@
struct nlattr *pg = nla_nest_start(skb, i);
if (!pg)
- goto nla_put_failure;
+ return -EMSGSIZE;
for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) {
struct nlattr *tc_nest = nla_nest_start(skb, i);
if (!tc_nest)
- goto nla_put_failure;
+ return -EMSGSIZE;
pgid = DCB_ATTR_VALUE_UNDEFINED;
prio = DCB_ATTR_VALUE_UNDEFINED;
@@ -1364,7 +1162,7 @@
nla_put_u8(skb, DCB_TC_ATTR_PARAM_UP_MAPPING, up_map) ||
nla_put_u8(skb, DCB_TC_ATTR_PARAM_STRICT_PRIO, prio) ||
nla_put_u8(skb, DCB_TC_ATTR_PARAM_BW_PCT, tc_pct))
- goto nla_put_failure;
+ return -EMSGSIZE;
nla_nest_end(skb, tc_nest);
}
@@ -1378,13 +1176,10 @@
ops->getpgbwgcfgtx(dev, i - DCB_PG_ATTR_BW_ID_0,
&tc_pct);
if (nla_put_u8(skb, i, tc_pct))
- goto nla_put_failure;
+ return -EMSGSIZE;
}
nla_nest_end(skb, pg);
return 0;
-
-nla_put_failure:
- return -EMSGSIZE;
}
static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev)
@@ -1531,27 +1326,16 @@
struct net *net = dev_net(dev);
struct sk_buff *skb;
struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
const struct dcbnl_rtnl_ops *ops = dev->dcbnl_ops;
int err;
if (!ops)
return -EOPNOTSUPP;
- skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ skb = dcbnl_newmsg(event, cmd, pid, seq, 0, &nlh);
if (!skb)
return -ENOBUFS;
- nlh = nlmsg_put(skb, pid, 0, event, sizeof(*dcb), 0);
- if (nlh == NULL) {
- nlmsg_free(skb);
- return -EMSGSIZE;
- }
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = cmd;
-
if (dcbx_ver == DCB_CAP_DCBX_VER_IEEE)
err = dcbnl_ieee_fill(skb, dev);
else
@@ -1559,8 +1343,7 @@
if (err < 0) {
/* Report error to broadcast listeners */
- nlmsg_cancel(skb, nlh);
- kfree_skb(skb);
+ nlmsg_free(skb);
rtnl_set_sk_err(net, RTNLGRP_DCB, err);
} else {
/* End nlmsg and notify broadcast listeners */
@@ -1590,15 +1373,15 @@
* No attempt is made to reconcile the case where only part of the
* cmd can be completed.
*/
-static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1];
- int err = -EOPNOTSUPP;
+ int err;
if (!ops)
- return err;
+ return -EOPNOTSUPP;
if (!tb[DCB_ATTR_IEEE])
return -EINVAL;
@@ -1649,58 +1432,28 @@
}
err:
- dcbnl_reply(err, RTM_SETDCB, DCB_CMD_IEEE_SET, DCB_ATTR_IEEE,
- pid, seq, flags);
+ err = nla_put_u8(skb, DCB_ATTR_IEEE, err);
dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_SET, seq, 0);
return err;
}
-static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_ieee_get(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct net *net = dev_net(netdev);
- struct sk_buff *skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
- int err;
if (!ops)
return -EOPNOTSUPP;
- skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!skb)
- return -ENOBUFS;
-
- nlh = nlmsg_put(skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
- if (nlh == NULL) {
- nlmsg_free(skb);
- return -EMSGSIZE;
- }
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_IEEE_GET;
-
- err = dcbnl_ieee_fill(skb, netdev);
-
- if (err < 0) {
- nlmsg_cancel(skb, nlh);
- kfree_skb(skb);
- } else {
- nlmsg_end(skb, nlh);
- err = rtnl_unicast(skb, net, pid);
- }
-
- return err;
+ return dcbnl_ieee_fill(skb, netdev);
}
-static int dcbnl_ieee_del(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_ieee_del(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1];
- int err = -EOPNOTSUPP;
+ int err;
if (!ops)
return -EOPNOTSUPP;
@@ -1733,32 +1486,26 @@
}
err:
- dcbnl_reply(err, RTM_SETDCB, DCB_CMD_IEEE_DEL, DCB_ATTR_IEEE,
- pid, seq, flags);
+ err = nla_put_u8(skb, DCB_ATTR_IEEE, err);
dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_DEL, seq, 0);
return err;
}
/* DCBX configuration */
-static int dcbnl_getdcbx(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getdcbx(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int ret;
-
if (!netdev->dcbnl_ops->getdcbx)
return -EOPNOTSUPP;
- ret = dcbnl_reply(netdev->dcbnl_ops->getdcbx(netdev), RTM_GETDCB,
- DCB_CMD_GDCBX, DCB_ATTR_DCBX, pid, seq, flags);
-
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_DCBX,
+ netdev->dcbnl_ops->getdcbx(netdev));
}
-static int dcbnl_setdcbx(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setdcbx(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int ret;
u8 value;
if (!netdev->dcbnl_ops->setdcbx)
@@ -1769,19 +1516,13 @@
value = nla_get_u8(tb[DCB_ATTR_DCBX]);
- ret = dcbnl_reply(netdev->dcbnl_ops->setdcbx(netdev, value),
- RTM_SETDCB, DCB_CMD_SDCBX, DCB_ATTR_DCBX,
- pid, seq, flags);
-
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_DCBX,
+ netdev->dcbnl_ops->setdcbx(netdev, value));
}
-static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1], *nest;
u8 value;
int ret, i;
@@ -1796,25 +1537,11 @@
ret = nla_parse_nested(data, DCB_FEATCFG_ATTR_MAX, tb[DCB_ATTR_FEATCFG],
dcbnl_featcfg_nest);
if (ret)
- goto err_out;
+ return ret;
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb) {
- ret = -ENOBUFS;
- goto err_out;
- }
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_GFEATCFG;
-
- nest = nla_nest_start(dcbnl_skb, DCB_ATTR_FEATCFG);
- if (!nest) {
- ret = -EMSGSIZE;
- goto nla_put_failure;
- }
+ nest = nla_nest_start(skb, DCB_ATTR_FEATCFG);
+ if (!nest)
+ return -EMSGSIZE;
if (data[DCB_FEATCFG_ATTR_ALL])
getall = 1;
@@ -1825,28 +1552,21 @@
ret = netdev->dcbnl_ops->getfeatcfg(netdev, i, &value);
if (!ret)
- ret = nla_put_u8(dcbnl_skb, i, value);
+ ret = nla_put_u8(skb, i, value);
if (ret) {
- nla_nest_cancel(dcbnl_skb, nest);
+ nla_nest_cancel(skb, nest);
goto nla_put_failure;
}
}
- nla_nest_end(dcbnl_skb, nest);
+ nla_nest_end(skb, nest);
- nlmsg_end(dcbnl_skb, nlh);
-
- return rtnl_unicast(dcbnl_skb, &init_net, pid);
nla_put_failure:
- nlmsg_cancel(dcbnl_skb, nlh);
-nlmsg_failure:
- kfree_skb(dcbnl_skb);
-err_out:
return ret;
}
-static int dcbnl_setfeatcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1];
int ret, i;
@@ -1876,60 +1596,73 @@
goto err;
}
err:
- dcbnl_reply(ret, RTM_SETDCB, DCB_CMD_SFEATCFG, DCB_ATTR_FEATCFG,
- pid, seq, flags);
+ ret = nla_put_u8(skb, DCB_ATTR_FEATCFG, ret);
return ret;
}
/* Handle CEE DCBX GET commands. */
-static int dcbnl_cee_get(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_cee_get(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct net *net = dev_net(netdev);
- struct sk_buff *skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
- int err;
if (!ops)
return -EOPNOTSUPP;
- skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!skb)
- return -ENOBUFS;
-
- nlh = nlmsg_put(skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
- if (nlh == NULL) {
- nlmsg_free(skb);
- return -EMSGSIZE;
- }
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_CEE_GET;
-
- err = dcbnl_cee_fill(skb, netdev);
-
- if (err < 0) {
- nlmsg_cancel(skb, nlh);
- nlmsg_free(skb);
- } else {
- nlmsg_end(skb, nlh);
- err = rtnl_unicast(skb, net, pid);
- }
- return err;
+ return dcbnl_cee_fill(skb, netdev);
}
+struct reply_func {
+ /* reply netlink message type */
+ int type;
+
+ /* function to fill message contents */
+ int (*cb)(struct net_device *, struct nlmsghdr *, u32,
+ struct nlattr **, struct sk_buff *);
+};
+
+static const struct reply_func reply_funcs[DCB_CMD_MAX+1] = {
+ [DCB_CMD_GSTATE] = { RTM_GETDCB, dcbnl_getstate },
+ [DCB_CMD_SSTATE] = { RTM_SETDCB, dcbnl_setstate },
+ [DCB_CMD_PFC_GCFG] = { RTM_GETDCB, dcbnl_getpfccfg },
+ [DCB_CMD_PFC_SCFG] = { RTM_SETDCB, dcbnl_setpfccfg },
+ [DCB_CMD_GPERM_HWADDR] = { RTM_GETDCB, dcbnl_getperm_hwaddr },
+ [DCB_CMD_GCAP] = { RTM_GETDCB, dcbnl_getcap },
+ [DCB_CMD_GNUMTCS] = { RTM_GETDCB, dcbnl_getnumtcs },
+ [DCB_CMD_SNUMTCS] = { RTM_SETDCB, dcbnl_setnumtcs },
+ [DCB_CMD_PFC_GSTATE] = { RTM_GETDCB, dcbnl_getpfcstate },
+ [DCB_CMD_PFC_SSTATE] = { RTM_SETDCB, dcbnl_setpfcstate },
+ [DCB_CMD_GAPP] = { RTM_GETDCB, dcbnl_getapp },
+ [DCB_CMD_SAPP] = { RTM_SETDCB, dcbnl_setapp },
+ [DCB_CMD_PGTX_GCFG] = { RTM_GETDCB, dcbnl_pgtx_getcfg },
+ [DCB_CMD_PGTX_SCFG] = { RTM_SETDCB, dcbnl_pgtx_setcfg },
+ [DCB_CMD_PGRX_GCFG] = { RTM_GETDCB, dcbnl_pgrx_getcfg },
+ [DCB_CMD_PGRX_SCFG] = { RTM_SETDCB, dcbnl_pgrx_setcfg },
+ [DCB_CMD_SET_ALL] = { RTM_SETDCB, dcbnl_setall },
+ [DCB_CMD_BCN_GCFG] = { RTM_GETDCB, dcbnl_bcn_getcfg },
+ [DCB_CMD_BCN_SCFG] = { RTM_SETDCB, dcbnl_bcn_setcfg },
+ [DCB_CMD_IEEE_GET] = { RTM_GETDCB, dcbnl_ieee_get },
+ [DCB_CMD_IEEE_SET] = { RTM_SETDCB, dcbnl_ieee_set },
+ [DCB_CMD_IEEE_DEL] = { RTM_SETDCB, dcbnl_ieee_del },
+ [DCB_CMD_GDCBX] = { RTM_GETDCB, dcbnl_getdcbx },
+ [DCB_CMD_SDCBX] = { RTM_SETDCB, dcbnl_setdcbx },
+ [DCB_CMD_GFEATCFG] = { RTM_GETDCB, dcbnl_getfeatcfg },
+ [DCB_CMD_SFEATCFG] = { RTM_SETDCB, dcbnl_setfeatcfg },
+ [DCB_CMD_CEE_GET] = { RTM_GETDCB, dcbnl_cee_get },
+};
+
static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
struct net *net = sock_net(skb->sk);
struct net_device *netdev;
- struct dcbmsg *dcb = (struct dcbmsg *)NLMSG_DATA(nlh);
+ struct dcbmsg *dcb = nlmsg_data(nlh);
struct nlattr *tb[DCB_ATTR_MAX + 1];
u32 pid = skb ? NETLINK_CB(skb).pid : 0;
int ret = -EINVAL;
+ struct sk_buff *reply_skb;
+ struct nlmsghdr *reply_nlh = NULL;
+ const struct reply_func *fn;
if (!net_eq(net, &init_net))
return -EINVAL;
@@ -1939,136 +1672,78 @@
if (ret < 0)
return ret;
+ if (dcb->cmd > DCB_CMD_MAX)
+ return -EINVAL;
+
+ /* check if a reply function has been defined for the command */
+ fn = &reply_funcs[dcb->cmd];
+ if (!fn->cb)
+ return -EOPNOTSUPP;
+
if (!tb[DCB_ATTR_IFNAME])
return -EINVAL;
netdev = dev_get_by_name(&init_net, nla_data(tb[DCB_ATTR_IFNAME]));
if (!netdev)
- return -EINVAL;
+ return -ENODEV;
- if (!netdev->dcbnl_ops)
- goto errout;
-
- switch (dcb->cmd) {
- case DCB_CMD_GSTATE:
- ret = dcbnl_getstate(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
+ if (!netdev->dcbnl_ops) {
+ ret = -EOPNOTSUPP;
goto out;
- case DCB_CMD_PFC_GCFG:
- ret = dcbnl_getpfccfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_GPERM_HWADDR:
- ret = dcbnl_getperm_hwaddr(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_PGTX_GCFG:
- ret = dcbnl_pgtx_getcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_PGRX_GCFG:
- ret = dcbnl_pgrx_getcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_BCN_GCFG:
- ret = dcbnl_bcn_getcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_SSTATE:
- ret = dcbnl_setstate(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_PFC_SCFG:
- ret = dcbnl_setpfccfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
-
- case DCB_CMD_SET_ALL:
- ret = dcbnl_setall(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_PGTX_SCFG:
- ret = dcbnl_pgtx_setcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_PGRX_SCFG:
- ret = dcbnl_pgrx_setcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_GCAP:
- ret = dcbnl_getcap(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_GNUMTCS:
- ret = dcbnl_getnumtcs(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_SNUMTCS:
- ret = dcbnl_setnumtcs(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_PFC_GSTATE:
- ret = dcbnl_getpfcstate(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_PFC_SSTATE:
- ret = dcbnl_setpfcstate(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_BCN_SCFG:
- ret = dcbnl_bcn_setcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_GAPP:
- ret = dcbnl_getapp(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_SAPP:
- ret = dcbnl_setapp(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_IEEE_SET:
- ret = dcbnl_ieee_set(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_IEEE_GET:
- ret = dcbnl_ieee_get(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_IEEE_DEL:
- ret = dcbnl_ieee_del(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_GDCBX:
- ret = dcbnl_getdcbx(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_SDCBX:
- ret = dcbnl_setdcbx(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_GFEATCFG:
- ret = dcbnl_getfeatcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_SFEATCFG:
- ret = dcbnl_setfeatcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_CEE_GET:
- ret = dcbnl_cee_get(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- default:
- goto errout;
}
-errout:
- ret = -EINVAL;
+
+ reply_skb = dcbnl_newmsg(fn->type, dcb->cmd, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags, &reply_nlh);
+ if (!reply_skb) {
+ ret = -ENOBUFS;
+ goto out;
+ }
+
+ ret = fn->cb(netdev, nlh, nlh->nlmsg_seq, tb, reply_skb);
+ if (ret < 0) {
+ nlmsg_free(reply_skb);
+ goto out;
+ }
+
+ nlmsg_end(reply_skb, reply_nlh);
+
+ ret = rtnl_unicast(reply_skb, &init_net, pid);
out:
dev_put(netdev);
return ret;
}
+static struct dcb_app_type *dcb_app_lookup(const struct dcb_app *app,
+ int ifindex, int prio)
+{
+ struct dcb_app_type *itr;
+
+ list_for_each_entry(itr, &dcb_app_list, list) {
+ if (itr->app.selector == app->selector &&
+ itr->app.protocol == app->protocol &&
+ itr->ifindex == ifindex &&
+ (!prio || itr->app.priority == prio))
+ return itr;
+ }
+
+ return NULL;
+}
+
+static int dcb_app_add(const struct dcb_app *app, int ifindex)
+{
+ struct dcb_app_type *entry;
+
+ entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+ if (!entry)
+ return -ENOMEM;
+
+ memcpy(&entry->app, app, sizeof(*app));
+ entry->ifindex = ifindex;
+ list_add(&entry->list, &dcb_app_list);
+
+ return 0;
+}
+
/**
* dcb_getapp - retrieve the DCBX application user priority
*
@@ -2082,14 +1757,8 @@
u8 prio = 0;
spin_lock(&dcb_lock);
- list_for_each_entry(itr, &dcb_app_list, list) {
- if (itr->app.selector == app->selector &&
- itr->app.protocol == app->protocol &&
- itr->ifindex == dev->ifindex) {
- prio = itr->app.priority;
- break;
- }
- }
+ if ((itr = dcb_app_lookup(app, dev->ifindex, 0)))
+ prio = itr->app.priority;
spin_unlock(&dcb_lock);
return prio;
@@ -2107,6 +1776,7 @@
{
struct dcb_app_type *itr;
struct dcb_app_type event;
+ int err = 0;
event.ifindex = dev->ifindex;
memcpy(&event.app, new, sizeof(event.app));
@@ -2115,36 +1785,23 @@
spin_lock(&dcb_lock);
/* Search for existing match and replace */
- list_for_each_entry(itr, &dcb_app_list, list) {
- if (itr->app.selector == new->selector &&
- itr->app.protocol == new->protocol &&
- itr->ifindex == dev->ifindex) {
- if (new->priority)
- itr->app.priority = new->priority;
- else {
- list_del(&itr->list);
- kfree(itr);
- }
- goto out;
+ if ((itr = dcb_app_lookup(new, dev->ifindex, 0))) {
+ if (new->priority)
+ itr->app.priority = new->priority;
+ else {
+ list_del(&itr->list);
+ kfree(itr);
}
+ goto out;
}
/* App type does not exist add new application type */
- if (new->priority) {
- struct dcb_app_type *entry;
- entry = kmalloc(sizeof(struct dcb_app_type), GFP_ATOMIC);
- if (!entry) {
- spin_unlock(&dcb_lock);
- return -ENOMEM;
- }
-
- memcpy(&entry->app, new, sizeof(*new));
- entry->ifindex = dev->ifindex;
- list_add(&entry->list, &dcb_app_list);
- }
+ if (new->priority)
+ err = dcb_app_add(new, dev->ifindex);
out:
spin_unlock(&dcb_lock);
- call_dcbevent_notifiers(DCB_APP_EVENT, &event);
- return 0;
+ if (!err)
+ call_dcbevent_notifiers(DCB_APP_EVENT, &event);
+ return err;
}
EXPORT_SYMBOL(dcb_setapp);
@@ -2161,13 +1818,8 @@
u8 prio = 0;
spin_lock(&dcb_lock);
- list_for_each_entry(itr, &dcb_app_list, list) {
- if (itr->app.selector == app->selector &&
- itr->app.protocol == app->protocol &&
- itr->ifindex == dev->ifindex) {
- prio |= 1 << itr->app.priority;
- }
- }
+ if ((itr = dcb_app_lookup(app, dev->ifindex, 0)))
+ prio |= 1 << itr->app.priority;
spin_unlock(&dcb_lock);
return prio;
@@ -2183,7 +1835,6 @@
*/
int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new)
{
- struct dcb_app_type *itr, *entry;
struct dcb_app_type event;
int err = 0;
@@ -2194,26 +1845,12 @@
spin_lock(&dcb_lock);
/* Search for existing match and abort if found */
- list_for_each_entry(itr, &dcb_app_list, list) {
- if (itr->app.selector == new->selector &&
- itr->app.protocol == new->protocol &&
- itr->app.priority == new->priority &&
- itr->ifindex == dev->ifindex) {
- err = -EEXIST;
- goto out;
- }
- }
-
- /* App entry does not exist add new entry */
- entry = kmalloc(sizeof(struct dcb_app_type), GFP_ATOMIC);
- if (!entry) {
- err = -ENOMEM;
+ if (dcb_app_lookup(new, dev->ifindex, new->priority)) {
+ err = -EEXIST;
goto out;
}
- memcpy(&entry->app, new, sizeof(*new));
- entry->ifindex = dev->ifindex;
- list_add(&entry->list, &dcb_app_list);
+ err = dcb_app_add(new, dev->ifindex);
out:
spin_unlock(&dcb_lock);
if (!err)
@@ -2240,19 +1877,12 @@
spin_lock(&dcb_lock);
/* Search for existing match and remove it. */
- list_for_each_entry(itr, &dcb_app_list, list) {
- if (itr->app.selector == del->selector &&
- itr->app.protocol == del->protocol &&
- itr->app.priority == del->priority &&
- itr->ifindex == dev->ifindex) {
- list_del(&itr->list);
- kfree(itr);
- err = 0;
- goto out;
- }
+ if ((itr = dcb_app_lookup(del, dev->ifindex, del->priority))) {
+ list_del(&itr->list);
+ kfree(itr);
+ err = 0;
}
-out:
spin_unlock(&dcb_lock);
if (!err)
call_dcbevent_notifiers(DCB_APP_EVENT, &event);
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index fa9512d..9991be0 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -165,6 +165,8 @@
} else
dst_hold(dst);
+ dst->ops->update_pmtu(dst, ntohl(info));
+
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
dccp_sync_mss(sk, dst_mtu(dst));
} /* else let the usual retransmit timer handle it */
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index e8f2617..916d5ec 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -408,6 +408,7 @@
return;
pr_debug("pmtu discovery on SA AH/%08x/%08x\n",
ntohl(ah->spi), ntohl(iph->daddr));
+ ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0);
xfrm_state_put(x);
}
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index cb982a6..7b95b49 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -494,6 +494,7 @@
return;
NETDEBUG(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%08x\n",
ntohl(esph->spi), ntohl(iph->daddr));
+ ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0);
xfrm_state_put(x);
}
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index e5c44fc..ab09b12 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -44,6 +44,7 @@
struct ip_options *opt = &(IPCB(skb)->opt);
IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
+ IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
if (unlikely(opt->optlen))
ip_forward_options(skb);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index f49047b..594cec3 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -516,9 +516,6 @@
case ICMP_PORT_UNREACH:
/* Impossible event. */
return;
- case ICMP_FRAG_NEEDED:
- /* Soft state for pmtu is maintained by IP core. */
- return;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
@@ -538,7 +535,16 @@
flags & GRE_KEY ?
*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
p[1]);
- if (t == NULL || t->parms.iph.daddr == 0 ||
+ if (t == NULL)
+ goto out;
+
+ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
+ ipv4_update_pmtu(skb, dev_net(skb->dev), info,
+ t->parms.link, 0, IPPROTO_GRE, 0);
+ goto out;
+ }
+
+ if (t->parms.iph.daddr == 0 ||
ipv4_is_multicast(t->parms.iph.daddr))
goto out;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b99ca4e..0f3185a 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -113,19 +113,6 @@
}
EXPORT_SYMBOL_GPL(ip_local_out);
-/* dev_loopback_xmit for use with netfilter. */
-static int ip_dev_loopback_xmit(struct sk_buff *newskb)
-{
- skb_reset_mac_header(newskb);
- __skb_pull(newskb, skb_network_offset(newskb));
- newskb->pkt_type = PACKET_LOOPBACK;
- newskb->ip_summed = CHECKSUM_UNNECESSARY;
- WARN_ON(!skb_dst(newskb));
- skb_dst_force(newskb);
- netif_rx_ni(newskb);
- return 0;
-}
-
static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst)
{
int ttl = inet->uc_ttl;
@@ -281,7 +268,7 @@
if (newskb)
NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING,
newskb, NULL, newskb->dev,
- ip_dev_loopback_xmit);
+ dev_loopback_xmit);
}
/* Multicasts with ttl 0 must not go beyond the host */
@@ -296,7 +283,7 @@
struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
if (newskb)
NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, newskb,
- NULL, newskb->dev, ip_dev_loopback_xmit);
+ NULL, newskb->dev, dev_loopback_xmit);
}
return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, NULL,
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index 63b64c4..b913754 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -42,6 +42,7 @@
return;
NETDEBUG(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/%pI4\n",
spi, &iph->daddr);
+ ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0);
xfrm_state_put(x);
}
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 2d0f99b..715338a 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -348,9 +348,6 @@
case ICMP_PORT_UNREACH:
/* Impossible event. */
return 0;
- case ICMP_FRAG_NEEDED:
- /* Soft state for pmtu is maintained by IP core. */
- return 0;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
@@ -369,7 +366,17 @@
rcu_read_lock();
t = ipip_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr);
- if (t == NULL || t->parms.iph.daddr == 0)
+ if (t == NULL)
+ goto out;
+
+ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
+ ipv4_update_pmtu(skb, dev_net(skb->dev), info,
+ t->dev->ifindex, 0, IPPROTO_IPIP, 0);
+ err = 0;
+ goto out;
+ }
+
+ if (t->parms.iph.daddr == 0)
goto out;
err = 0;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index a9e519a..c94bbc6 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1574,6 +1574,7 @@
struct ip_options *opt = &(IPCB(skb)->opt);
IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
+ IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
if (unlikely(opt->optlen))
ip_forward_options(skb);
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 2c00e8b..340fcf2 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -371,6 +371,7 @@
break;
case ICMP_DEST_UNREACH:
if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
+ ipv4_sk_update_pmtu(skb, sk, info);
if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) {
err = EMSGSIZE;
harderr = 1;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 4032b81..659ddfb 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -216,6 +216,9 @@
int err = 0;
int harderr = 0;
+ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
+ ipv4_sk_update_pmtu(skb, sk, info);
+
/* Report error on raw socket, if:
1. User requested ip_recverr.
2. Socket is connected (otherwise the error indication
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 655506a..41df529 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1711,6 +1711,34 @@
}
}
+void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
+ int oif, u32 mark, u8 protocol, int flow_flags)
+{
+ const struct iphdr *iph = (const struct iphdr *)skb->data;
+ struct flowi4 fl4;
+ struct rtable *rt;
+
+ flowi4_init_output(&fl4, oif, mark, RT_TOS(iph->tos), RT_SCOPE_UNIVERSE,
+ protocol, flow_flags | FLOWI_FLAG_PRECOW_METRICS,
+ iph->daddr, iph->saddr, 0, 0);
+ rt = __ip_route_output_key(net, &fl4);
+ if (!IS_ERR(rt)) {
+ ip_rt_update_pmtu(&rt->dst, mtu);
+ ip_rt_put(rt);
+ }
+}
+EXPORT_SYMBOL_GPL(ipv4_update_pmtu);
+
+void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
+{
+ const struct inet_sock *inet = inet_sk(sk);
+
+ return ipv4_update_pmtu(skb, sock_net(sk), mtu,
+ sk->sk_bound_dev_if, sk->sk_mark,
+ inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ inet_sk_flowi_flags(sk));
+}
+EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
static void ipv4_validate_peer(struct rtable *rt)
{
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index eaca736..db017ef 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -615,6 +615,7 @@
break;
case ICMP_DEST_UNREACH:
if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
+ ipv4_sk_update_pmtu(skb, sk, info);
if (inet->pmtudisc != IP_PMTUDISC_DONT) {
err = EMSGSIZE;
harderr = 1;
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index f1a4a2c..49d4d26 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -35,6 +35,7 @@
#include <linux/pfkeyv2.h>
#include <linux/string.h>
#include <linux/scatterlist.h>
+#include <net/ip6_route.h>
#include <net/icmp.h>
#include <net/ipv6.h>
#include <net/protocol.h>
@@ -621,7 +622,7 @@
NETDEBUG(KERN_DEBUG "pmtu discovery on SA AH/%08x/%pI6\n",
ntohl(ah->spi), &iph->daddr);
-
+ ip6_update_pmtu(skb, net, info, 0, 0);
xfrm_state_put(x);
}
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index db1521f..89a615b 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -39,6 +39,7 @@
#include <linux/random.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
+#include <net/ip6_route.h>
#include <net/icmp.h>
#include <net/ipv6.h>
#include <net/protocol.h>
@@ -442,6 +443,7 @@
return;
pr_debug("pmtu discovery on SA ESP/%08x/%pI6\n",
ntohl(esph->spi), &iph->daddr);
+ ip6_update_pmtu(skb, net, info, 0, 0);
xfrm_state_put(x);
}
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index ed89bba..5247d5c 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -649,7 +649,6 @@
struct net_device *dev = skb->dev;
struct inet6_dev *idev = __in6_dev_get(dev);
const struct in6_addr *saddr, *daddr;
- const struct ipv6hdr *orig_hdr;
struct icmp6hdr *hdr;
u8 type;
@@ -661,7 +660,7 @@
XFRM_STATE_ICMP))
goto drop_no_count;
- if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(*orig_hdr)))
+ if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr)))
goto drop_no_count;
nh = skb_network_offset(skb);
@@ -722,9 +721,6 @@
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto discard_it;
hdr = icmp6_hdr(skb);
- orig_hdr = (struct ipv6hdr *) (hdr + 1);
- rt6_pmtu_discovery(&orig_hdr->daddr, &orig_hdr->saddr, dev,
- ntohl(hdr->icmp6_mtu));
/*
* Drop through to notify
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 7ef0743..215afc7 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1562,7 +1562,7 @@
neigh_flags = neigh->flags;
neigh_release(neigh);
}
- if (neigh_flags & NTF_ROUTER) {
+ if (!(neigh_flags & NTF_ROUTER)) {
RT6_TRACE("purging route %p via non-router but gateway\n",
rt);
return -1;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 62fcf3e..a233a7c 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -83,19 +83,6 @@
}
EXPORT_SYMBOL_GPL(ip6_local_out);
-/* dev_loopback_xmit for use with netfilter. */
-static int ip6_dev_loopback_xmit(struct sk_buff *newskb)
-{
- skb_reset_mac_header(newskb);
- __skb_pull(newskb, skb_network_offset(newskb));
- newskb->pkt_type = PACKET_LOOPBACK;
- newskb->ip_summed = CHECKSUM_UNNECESSARY;
- WARN_ON(!skb_dst(newskb));
-
- netif_rx_ni(newskb);
- return 0;
-}
-
static int ip6_finish_output2(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
@@ -121,7 +108,7 @@
if (newskb)
NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
newskb, NULL, newskb->dev,
- ip6_dev_loopback_xmit);
+ dev_loopback_xmit);
if (ipv6_hdr(skb)->hop_limit == 0) {
IP6_INC_STATS(dev_net(dev), idev,
@@ -526,6 +513,7 @@
hdr->hop_limit--;
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
+ IP6_ADD_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dst->dev,
ip6_forward_finish);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index b15dc08..461e47c 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1886,6 +1886,8 @@
{
IP6_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_OUTFORWDATAGRAMS);
+ IP6_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)),
+ IPSTATS_MIB_OUTOCTETS, skb->len);
return dst_output(skb);
}
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index 5cb75bf..9283238 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -46,6 +46,7 @@
#include <linux/list.h>
#include <linux/vmalloc.h>
#include <linux/rtnetlink.h>
+#include <net/ip6_route.h>
#include <net/icmp.h>
#include <net/ipv6.h>
#include <net/protocol.h>
@@ -74,6 +75,7 @@
pr_debug("pmtu discovery on SA IPCOMP/%08x/%pI6\n",
spi, &iph->daddr);
+ ip6_update_pmtu(skb, net, info, 0, 0);
xfrm_state_put(x);
}
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 93d69836..43b0042 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -328,9 +328,10 @@
return;
harderr = icmpv6_err_convert(type, code, &err);
- if (type == ICMPV6_PKT_TOOBIG)
+ if (type == ICMPV6_PKT_TOOBIG) {
+ ip6_sk_update_pmtu(skb, sk, info);
harderr = (np->pmtudisc == IPV6_PMTUDISC_DO);
-
+ }
if (np->recverr) {
u8 *payload = skb->data;
if (!inet->hdrincl)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 58a3ec2..e649cd7 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1049,7 +1049,10 @@
{
struct rt6_info *rt6 = (struct rt6_info*)dst;
+ dst_confirm(dst);
if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
+ struct net *net = dev_net(dst->dev);
+
rt6->rt6i_flags |= RTF_MODIFIED;
if (mtu < IPV6_MIN_MTU) {
u32 features = dst_metric(dst, RTAX_FEATURES);
@@ -1058,9 +1061,39 @@
dst_metric_set(dst, RTAX_FEATURES, features);
}
dst_metric_set(dst, RTAX_MTU, mtu);
+ rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires);
}
}
+void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
+ int oif, u32 mark)
+{
+ const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
+ struct dst_entry *dst;
+ struct flowi6 fl6;
+
+ memset(&fl6, 0, sizeof(fl6));
+ fl6.flowi6_oif = oif;
+ fl6.flowi6_mark = mark;
+ fl6.flowi6_flags = FLOWI_FLAG_PRECOW_METRICS;
+ fl6.daddr = iph->daddr;
+ fl6.saddr = iph->saddr;
+ fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK;
+
+ dst = ip6_route_output(net, NULL, &fl6);
+ if (!dst->error)
+ ip6_rt_update_pmtu(dst, ntohl(mtu));
+ dst_release(dst);
+}
+EXPORT_SYMBOL_GPL(ip6_update_pmtu);
+
+void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
+{
+ ip6_update_pmtu(skb, sock_net(sk), mtu,
+ sk->sk_bound_dev_if, sk->sk_mark);
+}
+EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
+
static unsigned int ip6_default_advmss(const struct dst_entry *dst)
{
struct net_device *dev = dst->dev;
@@ -1704,116 +1737,6 @@
}
/*
- * Handle ICMP "packet too big" messages
- * i.e. Path MTU discovery
- */
-
-static void rt6_do_pmtu_disc(const struct in6_addr *daddr, const struct in6_addr *saddr,
- struct net *net, u32 pmtu, int ifindex)
-{
- struct rt6_info *rt, *nrt;
- int allfrag = 0;
-again:
- rt = rt6_lookup(net, daddr, saddr, ifindex, 0);
- if (!rt)
- return;
-
- if (rt6_check_expired(rt)) {
- ip6_del_rt(rt);
- goto again;
- }
-
- if (pmtu >= dst_mtu(&rt->dst))
- goto out;
-
- if (pmtu < IPV6_MIN_MTU) {
- /*
- * According to RFC2460, PMTU is set to the IPv6 Minimum Link
- * MTU (1280) and a fragment header should always be included
- * after a node receiving Too Big message reporting PMTU is
- * less than the IPv6 Minimum Link MTU.
- */
- pmtu = IPV6_MIN_MTU;
- allfrag = 1;
- }
-
- /* New mtu received -> path was valid.
- They are sent only in response to data packets,
- so that this nexthop apparently is reachable. --ANK
- */
- dst_confirm(&rt->dst);
-
- /* Host route. If it is static, it would be better
- not to override it, but add new one, so that
- when cache entry will expire old pmtu
- would return automatically.
- */
- if (rt->rt6i_flags & RTF_CACHE) {
- dst_metric_set(&rt->dst, RTAX_MTU, pmtu);
- if (allfrag) {
- u32 features = dst_metric(&rt->dst, RTAX_FEATURES);
- features |= RTAX_FEATURE_ALLFRAG;
- dst_metric_set(&rt->dst, RTAX_FEATURES, features);
- }
- rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
- rt->rt6i_flags |= RTF_MODIFIED;
- goto out;
- }
-
- /* Network route.
- Two cases are possible:
- 1. It is connected route. Action: COW
- 2. It is gatewayed route or NONEXTHOP route. Action: clone it.
- */
- if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
- nrt = rt6_alloc_cow(rt, daddr, saddr);
- else
- nrt = rt6_alloc_clone(rt, daddr);
-
- if (nrt) {
- dst_metric_set(&nrt->dst, RTAX_MTU, pmtu);
- if (allfrag) {
- u32 features = dst_metric(&nrt->dst, RTAX_FEATURES);
- features |= RTAX_FEATURE_ALLFRAG;
- dst_metric_set(&nrt->dst, RTAX_FEATURES, features);
- }
-
- /* According to RFC 1981, detecting PMTU increase shouldn't be
- * happened within 5 mins, the recommended timer is 10 mins.
- * Here this route expiration time is set to ip6_rt_mtu_expires
- * which is 10 mins. After 10 mins the decreased pmtu is expired
- * and detecting PMTU increase will be automatically happened.
- */
- rt6_update_expires(nrt, net->ipv6.sysctl.ip6_rt_mtu_expires);
- nrt->rt6i_flags |= RTF_DYNAMIC;
- ip6_ins_rt(nrt);
- }
-out:
- dst_release(&rt->dst);
-}
-
-void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *saddr,
- struct net_device *dev, u32 pmtu)
-{
- struct net *net = dev_net(dev);
-
- /*
- * RFC 1981 states that a node "MUST reduce the size of the packets it
- * is sending along the path" that caused the Packet Too Big message.
- * Since it's not possible in the general case to determine which
- * interface was used to send the original packet, we update the MTU
- * on the interface that will be used to send future packets. We also
- * update the MTU on the interface that received the Packet Too Big in
- * case the original packet was forced out that interface with
- * SO_BINDTODEVICE or similar. This is the next best thing to the
- * correct behaviour, which would be to update the MTU on all
- * interfaces.
- */
- rt6_do_pmtu_disc(daddr, saddr, net, pmtu, 0);
- rt6_do_pmtu_disc(daddr, saddr, net, pmtu, dev->ifindex);
-}
-
-/*
* Misc support functions
*/
@@ -3051,13 +2974,13 @@
if (ret)
goto out_kmem_cache;
- ret = register_pernet_subsys(&ip6_route_net_ops);
+ ret = register_pernet_subsys(&ipv6_inetpeer_ops);
if (ret)
goto out_dst_entries;
- ret = register_pernet_subsys(&ipv6_inetpeer_ops);
+ ret = register_pernet_subsys(&ip6_route_net_ops);
if (ret)
- goto out_register_subsys;
+ goto out_register_inetpeer;
ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep;
@@ -3074,7 +2997,7 @@
#endif
ret = fib6_init();
if (ret)
- goto out_register_inetpeer;
+ goto out_register_subsys;
ret = xfrm6_init();
if (ret)
@@ -3103,10 +3026,10 @@
xfrm6_fini();
out_fib6_init:
fib6_gc_cleanup();
-out_register_inetpeer:
- unregister_pernet_subsys(&ipv6_inetpeer_ops);
out_register_subsys:
unregister_pernet_subsys(&ip6_route_net_ops);
+out_register_inetpeer:
+ unregister_pernet_subsys(&ipv6_inetpeer_ops);
out_dst_entries:
dst_entries_destroy(&ip6_dst_blackhole_ops);
out_kmem_cache:
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 6041571..49aea94 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -527,9 +527,6 @@
case ICMP_PORT_UNREACH:
/* Impossible event. */
return 0;
- case ICMP_FRAG_NEEDED:
- /* Soft state for pmtu is maintained by IP core. */
- return 0;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
@@ -551,7 +548,17 @@
skb->dev,
iph->daddr,
iph->saddr);
- if (t == NULL || t->parms.iph.daddr == 0)
+ if (t == NULL)
+ goto out;
+
+ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
+ ipv4_update_pmtu(skb, dev_net(skb->dev), info,
+ t->dev->ifindex, 0, IPPROTO_IPV6, 0);
+ err = 0;
+ goto out;
+ }
+
+ if (t->parms.iph.daddr == 0)
goto out;
err = 0;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index f91b0bf..26a8862 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -415,6 +415,8 @@
} else
dst_hold(dst);
+ dst->ops->update_pmtu(dst, ntohl(info));
+
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
tcp_sync_mss(sk, dst_mtu(dst));
tcp_simple_retransmit(sk);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index f05099f..051ad48 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -479,6 +479,9 @@
if (sk == NULL)
return;
+ if (type == ICMPV6_PKT_TOOBIG)
+ ip6_sk_update_pmtu(skb, sk, info);
+
np = inet6_sk(sk);
if (!icmpv6_err_convert(type, code, &err) && !np->recverr)
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 07d7d55..cd6f7a9 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -372,7 +372,6 @@
skb_trim(skb, skb->dev->mtu);
}
skb->protocol = ETH_P_AF_IUCV;
- skb_shinfo(skb)->tx_flags |= SKBTX_DRV_NEEDS_SK_REF;
nskb = skb_clone(skb, GFP_ATOMIC);
if (!nskb)
return -ENOMEM;
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 443591d..185f12f 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -162,6 +162,7 @@
if (dev) {
unregister_netdev(dev);
spriv->dev = NULL;
+ module_put(THIS_MODULE);
}
}
}
@@ -249,6 +250,7 @@
if (rc < 0)
goto out_del_dev;
+ __module_get(THIS_MODULE);
/* Must be done after register_netdev() */
strlcpy(session->ifname, dev->name, IFNAMSIZ);
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 70614e7..61d8b75 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -464,10 +464,12 @@
sk->sk_bound_dev_if);
if (IS_ERR(rt))
goto no_route;
- if (connected)
+ if (connected) {
sk_setup_caps(sk, &rt->dst);
- else
- dst_release(&rt->dst); /* safe since we hold rcu_read_lock */
+ } else {
+ skb_dst_set(skb, &rt->dst);
+ goto xmit;
+ }
}
/* We dont need to clone dst here, it is guaranteed to not disappear.
@@ -475,6 +477,7 @@
*/
skb_dst_set_noref(skb, &rt->dst);
+xmit:
/* Queue the packet to IP for output */
rc = ip_queue_xmit(skb, &inet->cork.fl);
rcu_read_unlock();
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 0f45d02..d7134c1 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3100,7 +3100,7 @@
}
local->oper_channel = cbss->channel;
- ieee80211_hw_config(local, 0);
+ ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL);
if (!have_sta) {
u32 rates = 0, basic_rates = 0;
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index ed21992..4283b20 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -270,9 +270,8 @@
return 0;
/* RTP port is even */
- port &= htons(~1);
- rtp_port = port;
- rtcp_port = htons(ntohs(port) + 1);
+ rtp_port = port & ~htons(1);
+ rtcp_port = port | htons(1);
/* Create expect for RTP */
if ((rtp_exp = nf_ct_expect_alloc(ct)) == NULL)
diff --git a/net/netfilter/xt_HMARK.c b/net/netfilter/xt_HMARK.c
index 0a96a43..1686ca1 100644
--- a/net/netfilter/xt_HMARK.c
+++ b/net/netfilter/xt_HMARK.c
@@ -32,13 +32,13 @@
MODULE_ALIAS("ip6t_HMARK");
struct hmark_tuple {
- u32 src;
- u32 dst;
+ __be32 src;
+ __be32 dst;
union hmark_ports uports;
- uint8_t proto;
+ u8 proto;
};
-static inline u32 hmark_addr6_mask(const __u32 *addr32, const __u32 *mask)
+static inline __be32 hmark_addr6_mask(const __be32 *addr32, const __be32 *mask)
{
return (addr32[0] & mask[0]) ^
(addr32[1] & mask[1]) ^
@@ -46,8 +46,8 @@
(addr32[3] & mask[3]);
}
-static inline u32
-hmark_addr_mask(int l3num, const __u32 *addr32, const __u32 *mask)
+static inline __be32
+hmark_addr_mask(int l3num, const __be32 *addr32, const __be32 *mask)
{
switch (l3num) {
case AF_INET:
@@ -58,6 +58,22 @@
return 0;
}
+static inline void hmark_swap_ports(union hmark_ports *uports,
+ const struct xt_hmark_info *info)
+{
+ union hmark_ports hp;
+ u16 src, dst;
+
+ hp.b32 = (uports->b32 & info->port_mask.b32) | info->port_set.b32;
+ src = ntohs(hp.b16.src);
+ dst = ntohs(hp.b16.dst);
+
+ if (dst > src)
+ uports->v32 = (dst << 16) | src;
+ else
+ uports->v32 = (src << 16) | dst;
+}
+
static int
hmark_ct_set_htuple(const struct sk_buff *skb, struct hmark_tuple *t,
const struct xt_hmark_info *info)
@@ -74,22 +90,19 @@
otuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
rtuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple;
- t->src = hmark_addr_mask(otuple->src.l3num, otuple->src.u3.all,
- info->src_mask.all);
- t->dst = hmark_addr_mask(otuple->src.l3num, rtuple->src.u3.all,
- info->dst_mask.all);
+ t->src = hmark_addr_mask(otuple->src.l3num, otuple->src.u3.ip6,
+ info->src_mask.ip6);
+ t->dst = hmark_addr_mask(otuple->src.l3num, rtuple->src.u3.ip6,
+ info->dst_mask.ip6);
if (info->flags & XT_HMARK_FLAG(XT_HMARK_METHOD_L3))
return 0;
t->proto = nf_ct_protonum(ct);
if (t->proto != IPPROTO_ICMP) {
- t->uports.p16.src = otuple->src.u.all;
- t->uports.p16.dst = rtuple->src.u.all;
- t->uports.v32 = (t->uports.v32 & info->port_mask.v32) |
- info->port_set.v32;
- if (t->uports.p16.dst < t->uports.p16.src)
- swap(t->uports.p16.dst, t->uports.p16.src);
+ t->uports.b16.src = otuple->src.u.all;
+ t->uports.b16.dst = rtuple->src.u.all;
+ hmark_swap_ports(&t->uports, info);
}
return 0;
@@ -98,15 +111,19 @@
#endif
}
+/* This hash function is endian independent, to ensure consistent hashing if
+ * the cluster is composed of big and little endian systems. */
static inline u32
hmark_hash(struct hmark_tuple *t, const struct xt_hmark_info *info)
{
u32 hash;
+ u32 src = ntohl(t->src);
+ u32 dst = ntohl(t->dst);
- if (t->dst < t->src)
- swap(t->src, t->dst);
+ if (dst < src)
+ swap(src, dst);
- hash = jhash_3words(t->src, t->dst, t->uports.v32, info->hashrnd);
+ hash = jhash_3words(src, dst, t->uports.v32, info->hashrnd);
hash = hash ^ (t->proto & info->proto_mask);
return (((u64)hash * info->hmodulus) >> 32) + info->hoffset;
@@ -126,11 +143,7 @@
if (skb_copy_bits(skb, nhoff, &t->uports, sizeof(t->uports)) < 0)
return;
- t->uports.v32 = (t->uports.v32 & info->port_mask.v32) |
- info->port_set.v32;
-
- if (t->uports.p16.dst < t->uports.p16.src)
- swap(t->uports.p16.dst, t->uports.p16.src);
+ hmark_swap_ports(&t->uports, info);
}
#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
@@ -178,8 +191,8 @@
return -1;
}
noicmp:
- t->src = hmark_addr6_mask(ip6->saddr.s6_addr32, info->src_mask.all);
- t->dst = hmark_addr6_mask(ip6->daddr.s6_addr32, info->dst_mask.all);
+ t->src = hmark_addr6_mask(ip6->saddr.s6_addr32, info->src_mask.ip6);
+ t->dst = hmark_addr6_mask(ip6->daddr.s6_addr32, info->dst_mask.ip6);
if (info->flags & XT_HMARK_FLAG(XT_HMARK_METHOD_L3))
return 0;
@@ -255,11 +268,8 @@
}
}
- t->src = (__force u32) ip->saddr;
- t->dst = (__force u32) ip->daddr;
-
- t->src &= info->src_mask.ip;
- t->dst &= info->dst_mask.ip;
+ t->src = ip->saddr & info->src_mask.ip;
+ t->dst = ip->daddr & info->dst_mask.ip;
if (info->flags & XT_HMARK_FLAG(XT_HMARK_METHOD_L3))
return 0;
diff --git a/net/nfc/llcp/sock.c b/net/nfc/llcp/sock.c
index 30e3cc7..2c0b317 100644
--- a/net/nfc/llcp/sock.c
+++ b/net/nfc/llcp/sock.c
@@ -292,6 +292,9 @@
pr_debug("%p\n", sk);
+ if (llcp_sock == NULL)
+ return -EBADFD;
+
addr->sa_family = AF_NFC;
*len = sizeof(struct sockaddr_nfc_llcp);
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index a68aed7..ec2118d 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -502,10 +502,8 @@
if (stream->runtime->state != SNDRV_PCM_STATE_RUNNING)
return -EPERM;
retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_PAUSE_PUSH);
- if (!retval) {
+ if (!retval)
stream->runtime->state = SNDRV_PCM_STATE_PAUSED;
- wake_up(&stream->runtime->sleep);
- }
return retval;
}
@@ -544,6 +542,10 @@
if (!retval) {
stream->runtime->state = SNDRV_PCM_STATE_SETUP;
wake_up(&stream->runtime->sleep);
+ stream->runtime->hw_pointer = 0;
+ stream->runtime->app_pointer = 0;
+ stream->runtime->total_bytes_available = 0;
+ stream->runtime->total_bytes_transferred = 0;
}
return retval;
}
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 2b6392b..0276382 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2484,9 +2484,9 @@
static int DELAYED_INIT_MARK azx_first_init(struct azx *chip);
static int DELAYED_INIT_MARK azx_probe_continue(struct azx *chip);
+#ifdef SUPPORT_VGA_SWITCHEROO
static struct pci_dev __devinit *get_bound_vga(struct pci_dev *pci);
-#ifdef SUPPORT_VGA_SWITCHEROO
static void azx_vs_set_state(struct pci_dev *pci,
enum vga_switcheroo_state state)
{
@@ -2578,6 +2578,7 @@
#else
#define init_vga_switcheroo(chip) /* NOP */
#define register_vga_switcheroo(chip) 0
+#define check_hdmi_disabled(pci) false
#endif /* SUPPORT_VGA_SWITCHER */
/*
@@ -2638,6 +2639,7 @@
return azx_free(device->device_data);
}
+#ifdef SUPPORT_VGA_SWITCHEROO
/*
* Check of disabled HDMI controller by vga-switcheroo
*/
@@ -2670,12 +2672,13 @@
struct pci_dev *p = get_bound_vga(pci);
if (p) {
- if (vga_default_device() && p != vga_default_device())
+ if (vga_switcheroo_get_client_state(p) == VGA_SWITCHEROO_OFF)
vga_inactive = true;
pci_dev_put(p);
}
return vga_inactive;
}
+#endif /* SUPPORT_VGA_SWITCHEROO */
/*
* white/black-listing for position_fix
@@ -3351,6 +3354,11 @@
{ PCI_DEVICE(0x6549, 0x1200),
.driver_data = AZX_DRIVER_TERA | AZX_DCAPS_NO_64BIT },
/* Creative X-Fi (CA0110-IBG) */
+ /* CTHDA chips */
+ { PCI_DEVICE(0x1102, 0x0010),
+ .driver_data = AZX_DRIVER_CTHDA | AZX_DCAPS_PRESET_CTHDA },
+ { PCI_DEVICE(0x1102, 0x0012),
+ .driver_data = AZX_DRIVER_CTHDA | AZX_DCAPS_PRESET_CTHDA },
#if !defined(CONFIG_SND_CTXFI) && !defined(CONFIG_SND_CTXFI_MODULE)
/* the following entry conflicts with snd-ctxfi driver,
* as ctxfi driver mutates from HD-audio to native mode with
@@ -3367,11 +3375,6 @@
.driver_data = AZX_DRIVER_CTX | AZX_DCAPS_CTX_WORKAROUND |
AZX_DCAPS_RIRB_PRE_DELAY | AZX_DCAPS_POSFIX_LPIB },
#endif
- /* CTHDA chips */
- { PCI_DEVICE(0x1102, 0x0010),
- .driver_data = AZX_DRIVER_CTHDA | AZX_DCAPS_PRESET_CTHDA },
- { PCI_DEVICE(0x1102, 0x0012),
- .driver_data = AZX_DRIVER_CTHDA | AZX_DCAPS_PRESET_CTHDA },
/* Vortex86MX */
{ PCI_DEVICE(0x17f3, 0x3010), .driver_data = AZX_DRIVER_GENERIC },
/* VMware HDAudio */
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index 3acb582..172370b 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -4061,7 +4061,7 @@
static int cx_auto_init(struct hda_codec *codec)
{
struct conexant_spec *spec = codec->spec;
- /*snd_hda_sequence_write(codec, cx_auto_init_verbs);*/
+ snd_hda_gen_apply_verbs(codec);
cx_auto_init_output(codec);
cx_auto_init_input(codec);
cx_auto_init_digital(codec);
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 224410e..f8f4906 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -1896,6 +1896,7 @@
alc_fix_pll(codec);
alc_auto_init_amp(codec, spec->init_amp);
+ snd_hda_gen_apply_verbs(codec);
alc_init_special_input_src(codec);
alc_auto_init_std(codec);
@@ -6439,6 +6440,7 @@
ALC662_FIXUP_ASUS_MODE7,
ALC662_FIXUP_ASUS_MODE8,
ALC662_FIXUP_NO_JACK_DETECT,
+ ALC662_FIXUP_ZOTAC_Z68,
};
static const struct alc_fixup alc662_fixups[] = {
@@ -6588,6 +6590,13 @@
.type = ALC_FIXUP_FUNC,
.v.func = alc_fixup_no_jack_detect,
},
+ [ALC662_FIXUP_ZOTAC_Z68] = {
+ .type = ALC_FIXUP_PINS,
+ .v.pins = (const struct alc_pincfg[]) {
+ { 0x1b, 0x02214020 }, /* Front HP */
+ { }
+ }
+ },
};
static const struct snd_pci_quirk alc662_fixup_tbl[] = {
@@ -6601,6 +6610,7 @@
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(0x19da, 0xa130, "Zotac Z68", ALC662_FIXUP_ZOTAC_Z68),
SND_PCI_QUIRK(0x1b35, 0x2206, "CZC P10T", ALC662_FIXUP_CZC_P10T),
#if 0
diff --git a/sound/soc/codecs/wm2000.c b/sound/soc/codecs/wm2000.c
index a75c376..0418fa1 100644
--- a/sound/soc/codecs/wm2000.c
+++ b/sound/soc/codecs/wm2000.c
@@ -99,8 +99,9 @@
}
static int wm2000_poll_bit(struct i2c_client *i2c,
- unsigned int reg, u8 mask, int timeout)
+ unsigned int reg, u8 mask)
{
+ int timeout = 4000;
int val;
val = wm2000_read(i2c, reg);
@@ -119,7 +120,7 @@
static int wm2000_power_up(struct i2c_client *i2c, int analogue)
{
struct wm2000_priv *wm2000 = dev_get_drvdata(&i2c->dev);
- int ret, timeout;
+ int ret;
BUG_ON(wm2000->anc_mode != ANC_OFF);
@@ -140,13 +141,13 @@
/* Wait for ANC engine to become ready */
if (!wm2000_poll_bit(i2c, WM2000_REG_ANC_STAT,
- WM2000_ANC_ENG_IDLE, 1)) {
+ WM2000_ANC_ENG_IDLE)) {
dev_err(&i2c->dev, "ANC engine failed to reset\n");
return -ETIMEDOUT;
}
if (!wm2000_poll_bit(i2c, WM2000_REG_SYS_STATUS,
- WM2000_STATUS_BOOT_COMPLETE, 1)) {
+ WM2000_STATUS_BOOT_COMPLETE)) {
dev_err(&i2c->dev, "ANC engine failed to initialise\n");
return -ETIMEDOUT;
}
@@ -173,16 +174,13 @@
dev_dbg(&i2c->dev, "Download complete\n");
if (analogue) {
- timeout = 248;
- wm2000_write(i2c, WM2000_REG_ANA_VMID_PU_TIME, timeout / 4);
+ wm2000_write(i2c, WM2000_REG_ANA_VMID_PU_TIME, 248 / 4);
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_ANA_SEQ_INCLUDE |
WM2000_MODE_MOUSE_ENABLE |
WM2000_MODE_THERMAL_ENABLE);
} else {
- timeout = 10;
-
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_MOUSE_ENABLE |
WM2000_MODE_THERMAL_ENABLE);
@@ -201,9 +199,8 @@
wm2000_write(i2c, WM2000_REG_SYS_CTL2, WM2000_ANC_INT_N_CLR);
if (!wm2000_poll_bit(i2c, WM2000_REG_SYS_STATUS,
- WM2000_STATUS_MOUSE_ACTIVE, timeout)) {
- dev_err(&i2c->dev, "Timed out waiting for device after %dms\n",
- timeout * 10);
+ WM2000_STATUS_MOUSE_ACTIVE)) {
+ dev_err(&i2c->dev, "Timed out waiting for device\n");
return -ETIMEDOUT;
}
@@ -218,28 +215,25 @@
static int wm2000_power_down(struct i2c_client *i2c, int analogue)
{
struct wm2000_priv *wm2000 = dev_get_drvdata(&i2c->dev);
- int timeout;
if (analogue) {
- timeout = 248;
- wm2000_write(i2c, WM2000_REG_ANA_VMID_PD_TIME, timeout / 4);
+ wm2000_write(i2c, WM2000_REG_ANA_VMID_PD_TIME, 248 / 4);
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_ANA_SEQ_INCLUDE |
WM2000_MODE_POWER_DOWN);
} else {
- timeout = 10;
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_POWER_DOWN);
}
if (!wm2000_poll_bit(i2c, WM2000_REG_SYS_STATUS,
- WM2000_STATUS_POWER_DOWN_COMPLETE, timeout)) {
+ WM2000_STATUS_POWER_DOWN_COMPLETE)) {
dev_err(&i2c->dev, "Timeout waiting for ANC power down\n");
return -ETIMEDOUT;
}
if (!wm2000_poll_bit(i2c, WM2000_REG_ANC_STAT,
- WM2000_ANC_ENG_IDLE, 1)) {
+ WM2000_ANC_ENG_IDLE)) {
dev_err(&i2c->dev, "Timeout waiting for ANC engine idle\n");
return -ETIMEDOUT;
}
@@ -268,13 +262,13 @@
}
if (!wm2000_poll_bit(i2c, WM2000_REG_SYS_STATUS,
- WM2000_STATUS_ANC_DISABLED, 10)) {
+ WM2000_STATUS_ANC_DISABLED)) {
dev_err(&i2c->dev, "Timeout waiting for ANC disable\n");
return -ETIMEDOUT;
}
if (!wm2000_poll_bit(i2c, WM2000_REG_ANC_STAT,
- WM2000_ANC_ENG_IDLE, 1)) {
+ WM2000_ANC_ENG_IDLE)) {
dev_err(&i2c->dev, "Timeout waiting for ANC engine idle\n");
return -ETIMEDOUT;
}
@@ -311,7 +305,7 @@
wm2000_write(i2c, WM2000_REG_SYS_CTL2, WM2000_ANC_INT_N_CLR);
if (!wm2000_poll_bit(i2c, WM2000_REG_SYS_STATUS,
- WM2000_STATUS_MOUSE_ACTIVE, 10)) {
+ WM2000_STATUS_MOUSE_ACTIVE)) {
dev_err(&i2c->dev, "Timed out waiting for MOUSE\n");
return -ETIMEDOUT;
}
@@ -325,38 +319,32 @@
static int wm2000_enter_standby(struct i2c_client *i2c, int analogue)
{
struct wm2000_priv *wm2000 = dev_get_drvdata(&i2c->dev);
- int timeout;
BUG_ON(wm2000->anc_mode != ANC_ACTIVE);
if (analogue) {
- timeout = 248;
- wm2000_write(i2c, WM2000_REG_ANA_VMID_PD_TIME, timeout / 4);
+ wm2000_write(i2c, WM2000_REG_ANA_VMID_PD_TIME, 248 / 4);
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_ANA_SEQ_INCLUDE |
WM2000_MODE_THERMAL_ENABLE |
WM2000_MODE_STANDBY_ENTRY);
} else {
- timeout = 10;
-
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_THERMAL_ENABLE |
WM2000_MODE_STANDBY_ENTRY);
}
if (!wm2000_poll_bit(i2c, WM2000_REG_SYS_STATUS,
- WM2000_STATUS_ANC_DISABLED, timeout)) {
+ WM2000_STATUS_ANC_DISABLED)) {
dev_err(&i2c->dev,
"Timed out waiting for ANC disable after 1ms\n");
return -ETIMEDOUT;
}
- if (!wm2000_poll_bit(i2c, WM2000_REG_ANC_STAT, WM2000_ANC_ENG_IDLE,
- 1)) {
+ if (!wm2000_poll_bit(i2c, WM2000_REG_ANC_STAT, WM2000_ANC_ENG_IDLE)) {
dev_err(&i2c->dev,
- "Timed out waiting for standby after %dms\n",
- timeout * 10);
+ "Timed out waiting for standby\n");
return -ETIMEDOUT;
}
@@ -374,23 +362,19 @@
static int wm2000_exit_standby(struct i2c_client *i2c, int analogue)
{
struct wm2000_priv *wm2000 = dev_get_drvdata(&i2c->dev);
- int timeout;
BUG_ON(wm2000->anc_mode != ANC_STANDBY);
wm2000_write(i2c, WM2000_REG_SYS_CTL1, 0);
if (analogue) {
- timeout = 248;
- wm2000_write(i2c, WM2000_REG_ANA_VMID_PU_TIME, timeout / 4);
+ wm2000_write(i2c, WM2000_REG_ANA_VMID_PU_TIME, 248 / 4);
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_ANA_SEQ_INCLUDE |
WM2000_MODE_THERMAL_ENABLE |
WM2000_MODE_MOUSE_ENABLE);
} else {
- timeout = 10;
-
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_THERMAL_ENABLE |
WM2000_MODE_MOUSE_ENABLE);
@@ -400,9 +384,8 @@
wm2000_write(i2c, WM2000_REG_SYS_CTL2, WM2000_ANC_INT_N_CLR);
if (!wm2000_poll_bit(i2c, WM2000_REG_SYS_STATUS,
- WM2000_STATUS_MOUSE_ACTIVE, timeout)) {
- dev_err(&i2c->dev, "Timed out waiting for MOUSE after %dms\n",
- timeout * 10);
+ WM2000_STATUS_MOUSE_ACTIVE)) {
+ dev_err(&i2c->dev, "Timed out waiting for MOUSE\n");
return -ETIMEDOUT;
}
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index 993639d..aa8c98b 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -46,6 +46,39 @@
#define WM8994_NUM_DRC 3
#define WM8994_NUM_EQ 3
+static struct {
+ unsigned int reg;
+ unsigned int mask;
+} wm8994_vu_bits[] = {
+ { WM8994_LEFT_LINE_INPUT_1_2_VOLUME, WM8994_IN1_VU },
+ { WM8994_RIGHT_LINE_INPUT_1_2_VOLUME, WM8994_IN1_VU },
+ { WM8994_LEFT_LINE_INPUT_3_4_VOLUME, WM8994_IN2_VU },
+ { WM8994_RIGHT_LINE_INPUT_3_4_VOLUME, WM8994_IN2_VU },
+ { WM8994_SPEAKER_VOLUME_LEFT, WM8994_SPKOUT_VU },
+ { WM8994_SPEAKER_VOLUME_RIGHT, WM8994_SPKOUT_VU },
+ { WM8994_LEFT_OUTPUT_VOLUME, WM8994_HPOUT1_VU },
+ { WM8994_RIGHT_OUTPUT_VOLUME, WM8994_HPOUT1_VU },
+ { WM8994_LEFT_OPGA_VOLUME, WM8994_MIXOUT_VU },
+ { WM8994_RIGHT_OPGA_VOLUME, WM8994_MIXOUT_VU },
+
+ { WM8994_AIF1_DAC1_LEFT_VOLUME, WM8994_AIF1DAC1_VU },
+ { WM8994_AIF1_DAC1_RIGHT_VOLUME, WM8994_AIF1DAC1_VU },
+ { WM8994_AIF1_DAC2_LEFT_VOLUME, WM8994_AIF1DAC2_VU },
+ { WM8994_AIF1_DAC2_RIGHT_VOLUME, WM8994_AIF1DAC2_VU },
+ { WM8994_AIF2_DAC_LEFT_VOLUME, WM8994_AIF2DAC_VU },
+ { WM8994_AIF2_DAC_RIGHT_VOLUME, WM8994_AIF2DAC_VU },
+ { WM8994_AIF1_ADC1_LEFT_VOLUME, WM8994_AIF1ADC1_VU },
+ { WM8994_AIF1_ADC1_RIGHT_VOLUME, WM8994_AIF1ADC1_VU },
+ { WM8994_AIF1_ADC2_LEFT_VOLUME, WM8994_AIF1ADC2_VU },
+ { WM8994_AIF1_ADC2_RIGHT_VOLUME, WM8994_AIF1ADC2_VU },
+ { WM8994_AIF2_ADC_LEFT_VOLUME, WM8994_AIF2ADC_VU },
+ { WM8994_AIF2_ADC_RIGHT_VOLUME, WM8994_AIF1ADC2_VU },
+ { WM8994_DAC1_LEFT_VOLUME, WM8994_DAC1_VU },
+ { WM8994_DAC1_RIGHT_VOLUME, WM8994_DAC1_VU },
+ { WM8994_DAC2_LEFT_VOLUME, WM8994_DAC2_VU },
+ { WM8994_DAC2_RIGHT_VOLUME, WM8994_DAC2_VU },
+};
+
static int wm8994_drc_base[] = {
WM8994_AIF1_DRC1_1,
WM8994_AIF1_DRC2_1,
@@ -989,6 +1022,7 @@
struct snd_soc_codec *codec = w->codec;
struct wm8994 *control = codec->control_data;
int mask = WM8994_AIF1DAC1L_ENA | WM8994_AIF1DAC1R_ENA;
+ int i;
int dac;
int adc;
int val;
@@ -1047,6 +1081,13 @@
WM8994_AIF1DAC2L_ENA);
break;
+ case SND_SOC_DAPM_POST_PMU:
+ for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++)
+ snd_soc_write(codec, wm8994_vu_bits[i].reg,
+ snd_soc_read(codec,
+ wm8994_vu_bits[i].reg));
+ break;
+
case SND_SOC_DAPM_PRE_PMD:
case SND_SOC_DAPM_POST_PMD:
snd_soc_update_bits(codec, WM8994_POWER_MANAGEMENT_5,
@@ -1072,6 +1113,7 @@
struct snd_kcontrol *kcontrol, int event)
{
struct snd_soc_codec *codec = w->codec;
+ int i;
int dac;
int adc;
int val;
@@ -1122,6 +1164,13 @@
WM8994_AIF2DACR_ENA);
break;
+ case SND_SOC_DAPM_POST_PMU:
+ for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++)
+ snd_soc_write(codec, wm8994_vu_bits[i].reg,
+ snd_soc_read(codec,
+ wm8994_vu_bits[i].reg));
+ break;
+
case SND_SOC_DAPM_PRE_PMD:
case SND_SOC_DAPM_POST_PMD:
snd_soc_update_bits(codec, WM8994_POWER_MANAGEMENT_5,
@@ -1190,17 +1239,19 @@
switch (event) {
case SND_SOC_DAPM_PRE_PMU:
if (wm8994->aif1clk_enable) {
- aif1clk_ev(w, kcontrol, event);
+ aif1clk_ev(w, kcontrol, SND_SOC_DAPM_PRE_PMU);
snd_soc_update_bits(codec, WM8994_AIF1_CLOCKING_1,
WM8994_AIF1CLK_ENA_MASK,
WM8994_AIF1CLK_ENA);
+ aif1clk_ev(w, kcontrol, SND_SOC_DAPM_POST_PMU);
wm8994->aif1clk_enable = 0;
}
if (wm8994->aif2clk_enable) {
- aif2clk_ev(w, kcontrol, event);
+ aif2clk_ev(w, kcontrol, SND_SOC_DAPM_PRE_PMU);
snd_soc_update_bits(codec, WM8994_AIF2_CLOCKING_1,
WM8994_AIF2CLK_ENA_MASK,
WM8994_AIF2CLK_ENA);
+ aif2clk_ev(w, kcontrol, SND_SOC_DAPM_POST_PMU);
wm8994->aif2clk_enable = 0;
}
break;
@@ -1221,15 +1272,17 @@
switch (event) {
case SND_SOC_DAPM_POST_PMD:
if (wm8994->aif1clk_disable) {
+ aif1clk_ev(w, kcontrol, SND_SOC_DAPM_PRE_PMD);
snd_soc_update_bits(codec, WM8994_AIF1_CLOCKING_1,
WM8994_AIF1CLK_ENA_MASK, 0);
- aif1clk_ev(w, kcontrol, event);
+ aif1clk_ev(w, kcontrol, SND_SOC_DAPM_POST_PMD);
wm8994->aif1clk_disable = 0;
}
if (wm8994->aif2clk_disable) {
+ aif2clk_ev(w, kcontrol, SND_SOC_DAPM_PRE_PMD);
snd_soc_update_bits(codec, WM8994_AIF2_CLOCKING_1,
WM8994_AIF2CLK_ENA_MASK, 0);
- aif2clk_ev(w, kcontrol, event);
+ aif2clk_ev(w, kcontrol, SND_SOC_DAPM_POST_PMD);
wm8994->aif2clk_disable = 0;
}
break;
@@ -1527,9 +1580,11 @@
static const struct snd_soc_dapm_widget wm8994_lateclk_widgets[] = {
SND_SOC_DAPM_SUPPLY("AIF1CLK", WM8994_AIF1_CLOCKING_1, 0, 0, aif1clk_ev,
- SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_PRE_PMD),
+ SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU |
+ SND_SOC_DAPM_PRE_PMD),
SND_SOC_DAPM_SUPPLY("AIF2CLK", WM8994_AIF2_CLOCKING_1, 0, 0, aif2clk_ev,
- SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_PRE_PMD),
+ SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU |
+ SND_SOC_DAPM_PRE_PMD),
SND_SOC_DAPM_PGA("Direct Voice", SND_SOC_NOPM, 0, 0, NULL, 0),
SND_SOC_DAPM_MIXER("SPKL", WM8994_POWER_MANAGEMENT_3, 8, 0,
left_speaker_mixer, ARRAY_SIZE(left_speaker_mixer)),
@@ -3879,39 +3934,11 @@
pm_runtime_put(codec->dev);
- /* Latch volume updates (right only; we always do left then right). */
- snd_soc_update_bits(codec, WM8994_AIF1_DAC1_LEFT_VOLUME,
- WM8994_AIF1DAC1_VU, WM8994_AIF1DAC1_VU);
- snd_soc_update_bits(codec, WM8994_AIF1_DAC1_RIGHT_VOLUME,
- WM8994_AIF1DAC1_VU, WM8994_AIF1DAC1_VU);
- snd_soc_update_bits(codec, WM8994_AIF1_DAC2_LEFT_VOLUME,
- WM8994_AIF1DAC2_VU, WM8994_AIF1DAC2_VU);
- snd_soc_update_bits(codec, WM8994_AIF1_DAC2_RIGHT_VOLUME,
- WM8994_AIF1DAC2_VU, WM8994_AIF1DAC2_VU);
- snd_soc_update_bits(codec, WM8994_AIF2_DAC_LEFT_VOLUME,
- WM8994_AIF2DAC_VU, WM8994_AIF2DAC_VU);
- snd_soc_update_bits(codec, WM8994_AIF2_DAC_RIGHT_VOLUME,
- WM8994_AIF2DAC_VU, WM8994_AIF2DAC_VU);
- snd_soc_update_bits(codec, WM8994_AIF1_ADC1_LEFT_VOLUME,
- WM8994_AIF1ADC1_VU, WM8994_AIF1ADC1_VU);
- snd_soc_update_bits(codec, WM8994_AIF1_ADC1_RIGHT_VOLUME,
- WM8994_AIF1ADC1_VU, WM8994_AIF1ADC1_VU);
- snd_soc_update_bits(codec, WM8994_AIF1_ADC2_LEFT_VOLUME,
- WM8994_AIF1ADC2_VU, WM8994_AIF1ADC2_VU);
- snd_soc_update_bits(codec, WM8994_AIF1_ADC2_RIGHT_VOLUME,
- WM8994_AIF1ADC2_VU, WM8994_AIF1ADC2_VU);
- snd_soc_update_bits(codec, WM8994_AIF2_ADC_LEFT_VOLUME,
- WM8994_AIF2ADC_VU, WM8994_AIF1ADC2_VU);
- snd_soc_update_bits(codec, WM8994_AIF2_ADC_RIGHT_VOLUME,
- WM8994_AIF2ADC_VU, WM8994_AIF1ADC2_VU);
- snd_soc_update_bits(codec, WM8994_DAC1_LEFT_VOLUME,
- WM8994_DAC1_VU, WM8994_DAC1_VU);
- snd_soc_update_bits(codec, WM8994_DAC1_RIGHT_VOLUME,
- WM8994_DAC1_VU, WM8994_DAC1_VU);
- snd_soc_update_bits(codec, WM8994_DAC2_LEFT_VOLUME,
- WM8994_DAC2_VU, WM8994_DAC2_VU);
- snd_soc_update_bits(codec, WM8994_DAC2_RIGHT_VOLUME,
- WM8994_DAC2_VU, WM8994_DAC2_VU);
+ /* Latch volume update bits */
+ for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++)
+ snd_soc_update_bits(codec, wm8994_vu_bits[i].reg,
+ wm8994_vu_bits[i].mask,
+ wm8994_vu_bits[i].mask);
/* Set the low bit of the 3D stereo depth so TLV matches */
snd_soc_update_bits(codec, WM8994_AIF1_DAC1_FILTERS_2,
diff --git a/sound/soc/fsl/imx-audmux.c b/sound/soc/fsl/imx-audmux.c
index f237003..0803274 100644
--- a/sound/soc/fsl/imx-audmux.c
+++ b/sound/soc/fsl/imx-audmux.c
@@ -26,6 +26,7 @@
#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
+#include <linux/pinctrl/consumer.h>
#include "imx-audmux.h"
@@ -249,6 +250,7 @@
static int __devinit imx_audmux_probe(struct platform_device *pdev)
{
struct resource *res;
+ struct pinctrl *pinctrl;
const struct of_device_id *of_id =
of_match_device(imx_audmux_dt_ids, &pdev->dev);
@@ -257,6 +259,12 @@
if (!audmux_base)
return -EADDRNOTAVAIL;
+ pinctrl = devm_pinctrl_get_select_default(&pdev->dev);
+ if (IS_ERR(pinctrl)) {
+ dev_err(&pdev->dev, "setup pinctrl failed!");
+ return PTR_ERR(pinctrl);
+ }
+
audmux_clk = clk_get(&pdev->dev, "audmux");
if (IS_ERR(audmux_clk)) {
dev_dbg(&pdev->dev, "cannot get clock: %ld\n",
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 90ee77d..89eae93 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -913,7 +913,7 @@
/* do we need to add this widget to the list ? */
if (list) {
int err;
- err = dapm_list_add_widget(list, path->sink);
+ err = dapm_list_add_widget(list, path->source);
if (err < 0) {
dev_err(widget->dapm->dev, "could not add widget %s\n",
widget->name);
@@ -954,7 +954,7 @@
if (stream == SNDRV_PCM_STREAM_PLAYBACK)
paths = is_connected_output_ep(dai->playback_widget, list);
else
- paths = is_connected_input_ep(dai->playback_widget, list);
+ paths = is_connected_input_ep(dai->capture_widget, list);
trace_snd_soc_dapm_connected(paths, stream);
dapm_clear_walk(&card->dapm);
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index bedd171..48fd15b 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -794,6 +794,9 @@
for (i = 0; i < card->num_links; i++) {
be = &card->rtd[i];
+ if (!be->dai_link->no_pcm)
+ continue;
+
if (be->cpu_dai->playback_widget == widget ||
be->codec_dai->playback_widget == widget)
return be;
@@ -803,6 +806,9 @@
for (i = 0; i < card->num_links; i++) {
be = &card->rtd[i];
+ if (!be->dai_link->no_pcm)
+ continue;
+
if (be->cpu_dai->capture_widget == widget ||
be->codec_dai->capture_widget == widget)
return be;
diff --git a/sound/soc/tegra/tegra30_ahub.c b/sound/soc/tegra/tegra30_ahub.c
index 57cd419..f43edb3 100644
--- a/sound/soc/tegra/tegra30_ahub.c
+++ b/sound/soc/tegra/tegra30_ahub.c
@@ -629,3 +629,4 @@
MODULE_DESCRIPTION("Tegra30 AHUB driver");
MODULE_LICENSE("GPL v2");
MODULE_ALIAS("platform:" DRV_NAME);
+MODULE_DEVICE_TABLE(of, tegra30_ahub_of_match);
diff --git a/sound/usb/card.h b/sound/usb/card.h
index 0d37238..2b9ffff 100644
--- a/sound/usb/card.h
+++ b/sound/usb/card.h
@@ -119,6 +119,7 @@
unsigned long unlink_mask; /* bitmask of unlinked urbs */
/* data and sync endpoints for this stream */
+ unsigned int ep_num; /* the endpoint number */
struct snd_usb_endpoint *data_endpoint;
struct snd_usb_endpoint *sync_endpoint;
unsigned long flags;
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index 6b7d7a2..083ed81 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -97,6 +97,7 @@
subs->formats |= fp->formats;
subs->num_formats++;
subs->fmt_type = fp->fmt_type;
+ subs->ep_num = fp->endpoint;
}
/*
@@ -119,9 +120,7 @@
if (as->fmt_type != fp->fmt_type)
continue;
subs = &as->substream[stream];
- if (!subs->data_endpoint)
- continue;
- if (subs->data_endpoint->ep_num == fp->endpoint) {
+ if (subs->ep_num == fp->endpoint) {
list_add_tail(&fp->list, &subs->fmt_list);
subs->num_formats++;
subs->formats |= fp->formats;
@@ -134,7 +133,7 @@
if (as->fmt_type != fp->fmt_type)
continue;
subs = &as->substream[stream];
- if (subs->data_endpoint)
+ if (subs->ep_num)
continue;
err = snd_pcm_new_stream(as->pcm, stream, 1);
if (err < 0)
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 5476bc0..b4b572e 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,4 +1,6 @@
tools/perf
+tools/scripts
+tools/lib/traceevent
include/linux/const.h
include/linux/perf_event.h
include/linux/rbtree.h
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8c767c6..25249f7 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -152,7 +152,7 @@
if (symbol_conf.use_callchain) {
err = callchain_append(he->callchain,
- &evsel->hists.callchain_cursor,
+ &callchain_cursor,
sample->period);
if (err)
return err;
@@ -162,7 +162,7 @@
* so we don't allocated the extra space needed because the stdio
* code will not use it.
*/
- if (al->sym != NULL && use_browser > 0) {
+ if (he->ms.sym != NULL && use_browser > 0) {
struct annotation *notes = symbol__annotation(he->ms.sym);
assert(evsel != NULL);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 62ae30d..2625899 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1129,7 +1129,7 @@
return 0;
if (!evsel_list->nr_entries) {
- if (perf_evlist__add_attrs_array(evsel_list, default_attrs) < 0)
+ if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0)
return -1;
}
@@ -1139,21 +1139,21 @@
return 0;
/* Append detailed run extra attributes: */
- if (perf_evlist__add_attrs_array(evsel_list, detailed_attrs) < 0)
+ if (perf_evlist__add_default_attrs(evsel_list, detailed_attrs) < 0)
return -1;
if (detailed_run < 2)
return 0;
/* Append very detailed run extra attributes: */
- if (perf_evlist__add_attrs_array(evsel_list, very_detailed_attrs) < 0)
+ if (perf_evlist__add_default_attrs(evsel_list, very_detailed_attrs) < 0)
return -1;
if (detailed_run < 3)
return 0;
/* Append very, very detailed run extra attributes: */
- return perf_evlist__add_attrs_array(evsel_list, very_very_detailed_attrs);
+ return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
}
int cmd_stat(int argc, const char **argv, const char *prefix __used)
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 871b540..6bb0277 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -787,7 +787,7 @@
}
if (symbol_conf.use_callchain) {
- err = callchain_append(he->callchain, &evsel->hists.callchain_cursor,
+ err = callchain_append(he->callchain, &callchain_cursor,
sample->period);
if (err)
return;
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index bd0bb1b..67e5d0c 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -409,14 +409,15 @@
prctl. When a counter is disabled, it doesn't count or generate
events but does continue to exist and maintain its count value.
-An individual counter or counter group can be enabled with
+An individual counter can be enabled with
- ioctl(fd, PERF_EVENT_IOC_ENABLE);
+ ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
or disabled with
- ioctl(fd, PERF_EVENT_IOC_DISABLE);
+ ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
+For a counter group, pass PERF_IOC_FLAG_GROUP as the third argument.
Enabling or disabling the leader of a group enables or disables the
whole group; that is, while the group leader is disabled, none of the
counters in the group will count. Enabling or disabling a member of a
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 4deea6a..34b1c46 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -668,7 +668,7 @@
"q/ESC/CTRL+C Exit\n\n"
"-> Go to target\n"
"<- Exit\n"
- "h Cycle thru hottest instructions\n"
+ "H Cycle thru hottest instructions\n"
"j Toggle showing jump to target arrows\n"
"J Toggle showing number of jump sources on targets\n"
"n Search next string\n"
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index ad73300..95264f3 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -12,7 +12,7 @@
# First check if there is a .git to get the version from git describe
# otherwise try to get the version from the kernel makefile
if test -d ../../.git -o -f ../../.git &&
- VN=$(git describe --abbrev=4 HEAD 2>/dev/null) &&
+ VN=$(git describe --match 'v[0-9].[0-9]*' --abbrev=4 HEAD 2>/dev/null) &&
case "$VN" in
*$LF*) (exit 1) ;;
v[0-9]*)
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 9f7106a..3a6bff4 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -18,6 +18,8 @@
#include "util.h"
#include "callchain.h"
+__thread struct callchain_cursor callchain_cursor;
+
bool ip_callchain__valid(struct ip_callchain *chain,
const union perf_event *event)
{
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 7f9c0f1..3bdb407 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -76,6 +76,8 @@
struct callchain_cursor_node *curr;
};
+extern __thread struct callchain_cursor callchain_cursor;
+
static inline void callchain_init(struct callchain_root *root)
{
INIT_LIST_HEAD(&root->node.siblings);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 4ac5f5a..7400fb3 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -159,6 +159,17 @@
return -1;
}
+int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
+ struct perf_event_attr *attrs, size_t nr_attrs)
+{
+ size_t i;
+
+ for (i = 0; i < nr_attrs; i++)
+ event_attr_init(attrs + i);
+
+ return perf_evlist__add_attrs(evlist, attrs, nr_attrs);
+}
+
static int trace_event__id(const char *evname)
{
char *filename, *colon;
@@ -263,7 +274,8 @@
for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
list_for_each_entry(pos, &evlist->entries, node) {
for (thread = 0; thread < evlist->threads->nr; thread++)
- ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_DISABLE);
+ ioctl(FD(pos, cpu, thread),
+ PERF_EVENT_IOC_DISABLE, 0);
}
}
}
@@ -276,7 +288,8 @@
for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
list_for_each_entry(pos, &evlist->entries, node) {
for (thread = 0; thread < evlist->threads->nr; thread++)
- ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_ENABLE);
+ ioctl(FD(pos, cpu, thread),
+ PERF_EVENT_IOC_ENABLE, 0);
}
}
}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 58abb63..989bee9 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -54,6 +54,8 @@
int perf_evlist__add_default(struct perf_evlist *evlist);
int perf_evlist__add_attrs(struct perf_evlist *evlist,
struct perf_event_attr *attrs, size_t nr_attrs);
+int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
+ struct perf_event_attr *attrs, size_t nr_attrs);
int perf_evlist__add_tracepoints(struct perf_evlist *evlist,
const char *tracepoints[], size_t nr_tracepoints);
int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
@@ -62,6 +64,8 @@
#define perf_evlist__add_attrs_array(evlist, array) \
perf_evlist__add_attrs(evlist, array, ARRAY_SIZE(array))
+#define perf_evlist__add_default_attrs(evlist, array) \
+ __perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
#define perf_evlist__add_tracepoints_array(evlist, array) \
perf_evlist__add_tracepoints(evlist, array, ARRAY_SIZE(array))
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 91d1913..9f6cebd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -494,16 +494,24 @@
}
static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
- struct perf_sample *sample)
+ struct perf_sample *sample,
+ bool swapped)
{
const u64 *array = event->sample.array;
+ union u64_swap u;
array += ((event->header.size -
sizeof(event->header)) / sizeof(u64)) - 1;
if (type & PERF_SAMPLE_CPU) {
- u32 *p = (u32 *)array;
- sample->cpu = *p;
+ u.val64 = *array;
+ if (swapped) {
+ /* undo swap of u64, then swap on individual u32s */
+ u.val64 = bswap_64(u.val64);
+ u.val32[0] = bswap_32(u.val32[0]);
+ }
+
+ sample->cpu = u.val32[0];
array--;
}
@@ -523,9 +531,16 @@
}
if (type & PERF_SAMPLE_TID) {
- u32 *p = (u32 *)array;
- sample->pid = p[0];
- sample->tid = p[1];
+ u.val64 = *array;
+ if (swapped) {
+ /* undo swap of u64, then swap on individual u32s */
+ u.val64 = bswap_64(u.val64);
+ u.val32[0] = bswap_32(u.val32[0]);
+ u.val32[1] = bswap_32(u.val32[1]);
+ }
+
+ sample->pid = u.val32[0];
+ sample->tid = u.val32[1];
}
return 0;
@@ -562,7 +577,7 @@
if (event->header.type != PERF_RECORD_SAMPLE) {
if (!sample_id_all)
return 0;
- return perf_event__parse_id_sample(event, type, data);
+ return perf_event__parse_id_sample(event, type, data, swapped);
}
array = event->sample.array;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 1293b5e..514e2a4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -378,7 +378,7 @@
* collapse the histogram
*/
-static bool hists__collapse_insert_entry(struct hists *hists,
+static bool hists__collapse_insert_entry(struct hists *hists __used,
struct rb_root *root,
struct hist_entry *he)
{
@@ -397,8 +397,9 @@
iter->period += he->period;
iter->nr_events += he->nr_events;
if (symbol_conf.use_callchain) {
- callchain_cursor_reset(&hists->callchain_cursor);
- callchain_merge(&hists->callchain_cursor, iter->callchain,
+ callchain_cursor_reset(&callchain_cursor);
+ callchain_merge(&callchain_cursor,
+ iter->callchain,
he->callchain);
}
hist_entry__free(he);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index cfc64e2..34bb556 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -67,8 +67,6 @@
struct events_stats stats;
u64 event_stream;
u16 col_len[HISTC_NR_COLS];
- /* Best would be to reuse the session callchain cursor */
- struct callchain_cursor callchain_cursor;
};
struct hist_entry *__hists__add_entry(struct hists *self,
diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c
index 1915de2..3322b84 100644
--- a/tools/perf/util/pager.c
+++ b/tools/perf/util/pager.c
@@ -57,6 +57,10 @@
}
if (!pager)
pager = getenv("PAGER");
+ if (!pager) {
+ if (!access("/usr/bin/pager", X_OK))
+ pager = "/usr/bin/pager";
+ }
if (!pager)
pager = "less";
else if (!*pager || !strcmp(pager, "cat"))
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 59dccc9..0dda25d 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2164,16 +2164,12 @@
error:
if (kfd >= 0) {
- if (namelist)
- strlist__delete(namelist);
-
+ strlist__delete(namelist);
close(kfd);
}
if (ufd >= 0) {
- if (unamelist)
- strlist__delete(unamelist);
-
+ strlist__delete(unamelist);
close(ufd);
}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 93d355d..2600916 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -288,7 +288,8 @@
return bi;
}
-int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
+int machine__resolve_callchain(struct machine *self,
+ struct perf_evsel *evsel __used,
struct thread *thread,
struct ip_callchain *chain,
struct symbol **parent)
@@ -297,7 +298,12 @@
unsigned int i;
int err;
- callchain_cursor_reset(&evsel->hists.callchain_cursor);
+ callchain_cursor_reset(&callchain_cursor);
+
+ if (chain->nr > PERF_MAX_STACK_DEPTH) {
+ pr_warning("corrupted callchain. skipping...\n");
+ return 0;
+ }
for (i = 0; i < chain->nr; i++) {
u64 ip;
@@ -317,7 +323,14 @@
case PERF_CONTEXT_USER:
cpumode = PERF_RECORD_MISC_USER; break;
default:
- break;
+ pr_debug("invalid callchain context: "
+ "%"PRId64"\n", (s64) ip);
+ /*
+ * It seems the callchain is corrupted.
+ * Discard all.
+ */
+ callchain_cursor_reset(&callchain_cursor);
+ return 0;
}
continue;
}
@@ -333,7 +346,7 @@
break;
}
- err = callchain_cursor_append(&evsel->hists.callchain_cursor,
+ err = callchain_cursor_append(&callchain_cursor,
ip, al.map, al.sym);
if (err)
return err;
@@ -441,37 +454,65 @@
}
}
-static void perf_event__all64_swap(union perf_event *event)
+static void swap_sample_id_all(union perf_event *event, void *data)
+{
+ void *end = (void *) event + event->header.size;
+ int size = end - data;
+
+ BUG_ON(size % sizeof(u64));
+ mem_bswap_64(data, size);
+}
+
+static void perf_event__all64_swap(union perf_event *event,
+ bool sample_id_all __used)
{
struct perf_event_header *hdr = &event->header;
mem_bswap_64(hdr + 1, event->header.size - sizeof(*hdr));
}
-static void perf_event__comm_swap(union perf_event *event)
+static void perf_event__comm_swap(union perf_event *event, bool sample_id_all)
{
event->comm.pid = bswap_32(event->comm.pid);
event->comm.tid = bswap_32(event->comm.tid);
+
+ if (sample_id_all) {
+ void *data = &event->comm.comm;
+
+ data += ALIGN(strlen(data) + 1, sizeof(u64));
+ swap_sample_id_all(event, data);
+ }
}
-static void perf_event__mmap_swap(union perf_event *event)
+static void perf_event__mmap_swap(union perf_event *event,
+ bool sample_id_all)
{
event->mmap.pid = bswap_32(event->mmap.pid);
event->mmap.tid = bswap_32(event->mmap.tid);
event->mmap.start = bswap_64(event->mmap.start);
event->mmap.len = bswap_64(event->mmap.len);
event->mmap.pgoff = bswap_64(event->mmap.pgoff);
+
+ if (sample_id_all) {
+ void *data = &event->mmap.filename;
+
+ data += ALIGN(strlen(data) + 1, sizeof(u64));
+ swap_sample_id_all(event, data);
+ }
}
-static void perf_event__task_swap(union perf_event *event)
+static void perf_event__task_swap(union perf_event *event, bool sample_id_all)
{
event->fork.pid = bswap_32(event->fork.pid);
event->fork.tid = bswap_32(event->fork.tid);
event->fork.ppid = bswap_32(event->fork.ppid);
event->fork.ptid = bswap_32(event->fork.ptid);
event->fork.time = bswap_64(event->fork.time);
+
+ if (sample_id_all)
+ swap_sample_id_all(event, &event->fork + 1);
}
-static void perf_event__read_swap(union perf_event *event)
+static void perf_event__read_swap(union perf_event *event, bool sample_id_all)
{
event->read.pid = bswap_32(event->read.pid);
event->read.tid = bswap_32(event->read.tid);
@@ -479,6 +520,9 @@
event->read.time_enabled = bswap_64(event->read.time_enabled);
event->read.time_running = bswap_64(event->read.time_running);
event->read.id = bswap_64(event->read.id);
+
+ if (sample_id_all)
+ swap_sample_id_all(event, &event->read + 1);
}
static u8 revbyte(u8 b)
@@ -530,7 +574,8 @@
swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
}
-static void perf_event__hdr_attr_swap(union perf_event *event)
+static void perf_event__hdr_attr_swap(union perf_event *event,
+ bool sample_id_all __used)
{
size_t size;
@@ -541,18 +586,21 @@
mem_bswap_64(event->attr.id, size);
}
-static void perf_event__event_type_swap(union perf_event *event)
+static void perf_event__event_type_swap(union perf_event *event,
+ bool sample_id_all __used)
{
event->event_type.event_type.event_id =
bswap_64(event->event_type.event_type.event_id);
}
-static void perf_event__tracing_data_swap(union perf_event *event)
+static void perf_event__tracing_data_swap(union perf_event *event,
+ bool sample_id_all __used)
{
event->tracing_data.size = bswap_32(event->tracing_data.size);
}
-typedef void (*perf_event__swap_op)(union perf_event *event);
+typedef void (*perf_event__swap_op)(union perf_event *event,
+ bool sample_id_all);
static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_MMAP] = perf_event__mmap_swap,
@@ -986,6 +1034,15 @@
}
}
+static void event_swap(union perf_event *event, bool sample_id_all)
+{
+ perf_event__swap_op swap;
+
+ swap = perf_event__swap_ops[event->header.type];
+ if (swap)
+ swap(event, sample_id_all);
+}
+
static int perf_session__process_event(struct perf_session *session,
union perf_event *event,
struct perf_tool *tool,
@@ -994,9 +1051,8 @@
struct perf_sample sample;
int ret;
- if (session->header.needs_swap &&
- perf_event__swap_ops[event->header.type])
- perf_event__swap_ops[event->header.type](event);
+ if (session->header.needs_swap)
+ event_swap(event, session->sample_id_all);
if (event->header.type >= PERF_RECORD_HEADER_MAX)
return -EINVAL;
@@ -1428,7 +1484,6 @@
int print_sym, int print_dso, int print_symoffset)
{
struct addr_location al;
- struct callchain_cursor *cursor = &evsel->hists.callchain_cursor;
struct callchain_cursor_node *node;
if (perf_event__preprocess_sample(event, machine, &al, sample,
@@ -1446,10 +1501,10 @@
error("Failed to resolve callchain. Skipping\n");
return;
}
- callchain_cursor_commit(cursor);
+ callchain_cursor_commit(&callchain_cursor);
while (1) {
- node = callchain_cursor_current(cursor);
+ node = callchain_cursor_current(&callchain_cursor);
if (!node)
break;
@@ -1460,12 +1515,12 @@
}
if (print_dso) {
printf(" (");
- map__fprintf_dsoname(al.map, stdout);
+ map__fprintf_dsoname(node->map, stdout);
printf(")");
}
printf("\n");
- callchain_cursor_advance(cursor);
+ callchain_cursor_advance(&callchain_cursor);
}
} else {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index e2ba885..3e2e5ea 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -323,6 +323,7 @@
dso->sorted_by_name = 0;
dso->has_build_id = 0;
dso->kernel = DSO_TYPE_USER;
+ dso->needs_swap = DSO_SWAP__UNSET;
INIT_LIST_HEAD(&dso->node);
}
@@ -1156,6 +1157,33 @@
return -1;
}
+static int dso__swap_init(struct dso *dso, unsigned char eidata)
+{
+ static unsigned int const endian = 1;
+
+ dso->needs_swap = DSO_SWAP__NO;
+
+ switch (eidata) {
+ case ELFDATA2LSB:
+ /* We are big endian, DSO is little endian. */
+ if (*(unsigned char const *)&endian != 1)
+ dso->needs_swap = DSO_SWAP__YES;
+ break;
+
+ case ELFDATA2MSB:
+ /* We are little endian, DSO is big endian. */
+ if (*(unsigned char const *)&endian != 0)
+ dso->needs_swap = DSO_SWAP__YES;
+ break;
+
+ default:
+ pr_err("unrecognized DSO data encoding %d\n", eidata);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
int fd, symbol_filter_t filter, int kmodule,
int want_symtab)
@@ -1187,6 +1215,9 @@
goto out_elf_end;
}
+ if (dso__swap_init(dso, ehdr.e_ident[EI_DATA]))
+ goto out_elf_end;
+
/* Always reject images with a mismatched build-id: */
if (dso->has_build_id) {
u8 build_id[BUILD_ID_SIZE];
@@ -1272,7 +1303,7 @@
if (opdsec && sym.st_shndx == opdidx) {
u32 offset = sym.st_value - opdshdr.sh_addr;
u64 *opd = opddata->d_buf + offset;
- sym.st_value = *opd;
+ sym.st_value = DSO__SWAP(dso, u64, *opd);
sym.st_shndx = elf_addr_to_index(elf, sym.st_value);
}
@@ -2786,8 +2817,11 @@
struct map *dso__new_map(const char *name)
{
+ struct map *map = NULL;
struct dso *dso = dso__new(name);
- struct map *map = map__new2(0, dso, MAP__FUNCTION);
+
+ if (dso)
+ map = map__new2(0, dso, MAP__FUNCTION);
return map;
}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 5649d63..af0752b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -9,6 +9,7 @@
#include <linux/list.h>
#include <linux/rbtree.h>
#include <stdio.h>
+#include <byteswap.h>
#ifdef HAVE_CPLUS_DEMANGLE
extern char *cplus_demangle(const char *, int);
@@ -160,11 +161,18 @@
DSO_TYPE_GUEST_KERNEL
};
+enum dso_swap_type {
+ DSO_SWAP__UNSET,
+ DSO_SWAP__NO,
+ DSO_SWAP__YES,
+};
+
struct dso {
struct list_head node;
struct rb_root symbols[MAP__NR_TYPES];
struct rb_root symbol_names[MAP__NR_TYPES];
enum dso_kernel_type kernel;
+ enum dso_swap_type needs_swap;
u8 adjust_symbols:1;
u8 has_build_id:1;
u8 hit:1;
@@ -182,6 +190,28 @@
char name[0];
};
+#define DSO__SWAP(dso, type, val) \
+({ \
+ type ____r = val; \
+ BUG_ON(dso->needs_swap == DSO_SWAP__UNSET); \
+ if (dso->needs_swap == DSO_SWAP__YES) { \
+ switch (sizeof(____r)) { \
+ case 2: \
+ ____r = bswap_16(val); \
+ break; \
+ case 4: \
+ ____r = bswap_32(val); \
+ break; \
+ case 8: \
+ ____r = bswap_64(val); \
+ break; \
+ default: \
+ BUG_ON(1); \
+ } \
+ } \
+ ____r; \
+})
+
struct dso *dso__new(const char *name);
void dso__delete(struct dso *dso);
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index ab2f682..16de7ad 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -73,8 +73,8 @@
char *progname;
int num_cpus;
-cpu_set_t *cpu_mask;
-size_t cpu_mask_size;
+cpu_set_t *cpu_present_set, *cpu_mask;
+size_t cpu_present_setsize, cpu_mask_size;
struct counters {
unsigned long long tsc; /* per thread */
@@ -103,6 +103,12 @@
struct timeval tv_odd;
struct timeval tv_delta;
+int mark_cpu_present(int pkg, int core, int cpu)
+{
+ CPU_SET_S(cpu, cpu_present_setsize, cpu_present_set);
+ return 0;
+}
+
/*
* cpu_mask_init(ncpus)
*
@@ -118,6 +124,18 @@
}
cpu_mask_size = CPU_ALLOC_SIZE(ncpus);
CPU_ZERO_S(cpu_mask_size, cpu_mask);
+
+ /*
+ * Allocate and initialize cpu_present_set
+ */
+ cpu_present_set = CPU_ALLOC(ncpus);
+ if (cpu_present_set == NULL) {
+ perror("CPU_ALLOC");
+ exit(3);
+ }
+ cpu_present_setsize = CPU_ALLOC_SIZE(ncpus);
+ CPU_ZERO_S(cpu_present_setsize, cpu_present_set);
+ for_all_cpus(mark_cpu_present);
}
void cpu_mask_uninit()
@@ -125,6 +143,9 @@
CPU_FREE(cpu_mask);
cpu_mask = NULL;
cpu_mask_size = 0;
+ CPU_FREE(cpu_present_set);
+ cpu_present_set = NULL;
+ cpu_present_setsize = 0;
}
int cpu_migrate(int cpu)
@@ -912,6 +933,8 @@
switch (model) {
case 0x2A:
case 0x2D:
+ case 0x3A: /* IVB */
+ case 0x3D: /* IVB Xeon */
return 1;
}
return 0;
@@ -1047,6 +1070,9 @@
int retval;
pid_t child_pid;
get_counters(cnt_even);
+
+ /* clear affinity side-effect of get_counters() */
+ sched_setaffinity(0, cpu_present_setsize, cpu_present_set);
gettimeofday(&tv_even, (struct timezone *)NULL);
child_pid = fork();
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index a6a0365..5afb431 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -332,6 +332,7 @@
*/
hlist_for_each_entry(ei, n, &rt->map[ue->gsi], link)
if (ei->type == KVM_IRQ_ROUTING_MSI ||
+ ue->type == KVM_IRQ_ROUTING_MSI ||
ue->u.irqchip.irqchip == ei->irqchip.irqchip)
return r;