Merge branch 'x86/idle' into sched/core
Merge these x86 specific bits - we are going to add generic bits as well.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/Documentation/block/null_blk.txt b/Documentation/block/null_blk.txt
new file mode 100644
index 0000000..b2830b4
--- /dev/null
+++ b/Documentation/block/null_blk.txt
@@ -0,0 +1,72 @@
+Null block device driver
+================================================================================
+
+I. Overview
+
+The null block device (/dev/nullb*) is used for benchmarking the various
+block-layer implementations. It emulates a block device of X gigabytes in size.
+The following instances are possible:
+
+ Single-queue block-layer
+ - Request-based.
+ - Single submission queue per device.
+ - Implements IO scheduling algorithms (CFQ, Deadline, noop).
+ Multi-queue block-layer
+ - Request-based.
+ - Configurable submission queues per device.
+ No block-layer (Known as bio-based)
+ - Bio-based. IO requests are submitted directly to the device driver.
+ - Directly accepts bio data structure and returns them.
+
+All of them have a completion queue for each core in the system.
+
+II. Module parameters applicable for all instances:
+
+queue_mode=[0-2]: Default: 2-Multi-queue
+ Selects which block-layer the module should instantiate with.
+
+ 0: Bio-based.
+ 1: Single-queue.
+ 2: Multi-queue.
+
+home_node=[0--nr_nodes]: Default: NUMA_NO_NODE
+ Selects what CPU node the data structures are allocated from.
+
+gb=[Size in GB]: Default: 250GB
+ The size of the device reported to the system.
+
+bs=[Block size (in bytes)]: Default: 512 bytes
+ The block size reported to the system.
+
+nr_devices=[Number of devices]: Default: 2
+ Number of block devices instantiated. They are instantiated as /dev/nullb0,
+ etc.
+
+irq_mode=[0-2]: Default: 1-Soft-irq
+ The completion mode used for completing IOs to the block-layer.
+
+ 0: None.
+ 1: Soft-irq. Uses IPI to complete IOs across CPU nodes. Simulates the overhead
+ when IOs are issued from another CPU node than the home the device is
+ connected to.
+ 2: Timer: Waits a specific period (completion_nsec) for each IO before
+ completion.
+
+completion_nsec=[ns]: Default: 10.000ns
+ Combined with irq_mode=2 (timer). The time each completion event must wait.
+
+submit_queues=[0..nr_cpus]:
+ The number of submission queues attached to the device driver. If unset, it
+ defaults to 1 on single-queue and bio-based instances. For multi-queue,
+ it is ignored when use_per_node_hctx module parameter is 1.
+
+hw_queue_depth=[0..qdepth]: Default: 64
+ The hardware queue depth of the device.
+
+III: Multi-queue specific parameters
+
+use_per_node_hctx=[0/1]: Default: 0
+ 0: The number of submit queues are set to the value of the submit_queues
+ parameter.
+ 1: The multi-queue block layer is instantiated with a hardware dispatch
+ queue for each CPU node in the system.
diff --git a/Documentation/devicetree/bindings/clock/exynos5250-clock.txt b/Documentation/devicetree/bindings/clock/exynos5250-clock.txt
index 46f5c79..0f2f920 100644
--- a/Documentation/devicetree/bindings/clock/exynos5250-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos5250-clock.txt
@@ -159,6 +159,8 @@
mixer 343
hdmi 344
g2d 345
+ mdma0 346
+ smmu_mdma0 347
[Clock Muxes]
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 50680a5..b9e9bd8 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1529,6 +1529,8 @@
* atapi_dmadir: Enable ATAPI DMADIR bridge support
+ * disable: Disable this device.
+
If there are multiple matching configurations changing
the same attribute, the last one is used.
diff --git a/Documentation/module-signing.txt b/Documentation/module-signing.txt
new file mode 100644
index 0000000..2b40e04
--- /dev/null
+++ b/Documentation/module-signing.txt
@@ -0,0 +1,240 @@
+ ==============================
+ KERNEL MODULE SIGNING FACILITY
+ ==============================
+
+CONTENTS
+
+ - Overview.
+ - Configuring module signing.
+ - Generating signing keys.
+ - Public keys in the kernel.
+ - Manually signing modules.
+ - Signed modules and stripping.
+ - Loading signed modules.
+ - Non-valid signatures and unsigned modules.
+ - Administering/protecting the private key.
+
+
+========
+OVERVIEW
+========
+
+The kernel module signing facility cryptographically signs modules during
+installation and then checks the signature upon loading the module. This
+allows increased kernel security by disallowing the loading of unsigned modules
+or modules signed with an invalid key. Module signing increases security by
+making it harder to load a malicious module into the kernel. The module
+signature checking is done by the kernel so that it is not necessary to have
+trusted userspace bits.
+
+This facility uses X.509 ITU-T standard certificates to encode the public keys
+involved. The signatures are not themselves encoded in any industrial standard
+type. The facility currently only supports the RSA public key encryption
+standard (though it is pluggable and permits others to be used). The possible
+hash algorithms that can be used are SHA-1, SHA-224, SHA-256, SHA-384, and
+SHA-512 (the algorithm is selected by data in the signature).
+
+
+==========================
+CONFIGURING MODULE SIGNING
+==========================
+
+The module signing facility is enabled by going to the "Enable Loadable Module
+Support" section of the kernel configuration and turning on
+
+ CONFIG_MODULE_SIG "Module signature verification"
+
+This has a number of options available:
+
+ (1) "Require modules to be validly signed" (CONFIG_MODULE_SIG_FORCE)
+
+ This specifies how the kernel should deal with a module that has a
+ signature for which the key is not known or a module that is unsigned.
+
+ If this is off (ie. "permissive"), then modules for which the key is not
+ available and modules that are unsigned are permitted, but the kernel will
+ be marked as being tainted.
+
+ If this is on (ie. "restrictive"), only modules that have a valid
+ signature that can be verified by a public key in the kernel's possession
+ will be loaded. All other modules will generate an error.
+
+ Irrespective of the setting here, if the module has a signature block that
+ cannot be parsed, it will be rejected out of hand.
+
+
+ (2) "Automatically sign all modules" (CONFIG_MODULE_SIG_ALL)
+
+ If this is on then modules will be automatically signed during the
+ modules_install phase of a build. If this is off, then the modules must
+ be signed manually using:
+
+ scripts/sign-file
+
+
+ (3) "Which hash algorithm should modules be signed with?"
+
+ This presents a choice of which hash algorithm the installation phase will
+ sign the modules with:
+
+ CONFIG_SIG_SHA1 "Sign modules with SHA-1"
+ CONFIG_SIG_SHA224 "Sign modules with SHA-224"
+ CONFIG_SIG_SHA256 "Sign modules with SHA-256"
+ CONFIG_SIG_SHA384 "Sign modules with SHA-384"
+ CONFIG_SIG_SHA512 "Sign modules with SHA-512"
+
+ The algorithm selected here will also be built into the kernel (rather
+ than being a module) so that modules signed with that algorithm can have
+ their signatures checked without causing a dependency loop.
+
+
+=======================
+GENERATING SIGNING KEYS
+=======================
+
+Cryptographic keypairs are required to generate and check signatures. A
+private key is used to generate a signature and the corresponding public key is
+used to check it. The private key is only needed during the build, after which
+it can be deleted or stored securely. The public key gets built into the
+kernel so that it can be used to check the signatures as the modules are
+loaded.
+
+Under normal conditions, the kernel build will automatically generate a new
+keypair using openssl if one does not exist in the files:
+
+ signing_key.priv
+ signing_key.x509
+
+during the building of vmlinux (the public part of the key needs to be built
+into vmlinux) using parameters in the:
+
+ x509.genkey
+
+file (which is also generated if it does not already exist).
+
+It is strongly recommended that you provide your own x509.genkey file.
+
+Most notably, in the x509.genkey file, the req_distinguished_name section
+should be altered from the default:
+
+ [ req_distinguished_name ]
+ O = Magrathea
+ CN = Glacier signing key
+ emailAddress = slartibartfast@magrathea.h2g2
+
+The generated RSA key size can also be set with:
+
+ [ req ]
+ default_bits = 4096
+
+
+It is also possible to manually generate the key private/public files using the
+x509.genkey key generation configuration file in the root node of the Linux
+kernel sources tree and the openssl command. The following is an example to
+generate the public/private key files:
+
+ openssl req -new -nodes -utf8 -sha256 -days 36500 -batch -x509 \
+ -config x509.genkey -outform DER -out signing_key.x509 \
+ -keyout signing_key.priv
+
+
+=========================
+PUBLIC KEYS IN THE KERNEL
+=========================
+
+The kernel contains a ring of public keys that can be viewed by root. They're
+in a keyring called ".system_keyring" that can be seen by:
+
+ [root@deneb ~]# cat /proc/keys
+ ...
+ 223c7853 I------ 1 perm 1f030000 0 0 keyring .system_keyring: 1
+ 302d2d52 I------ 1 perm 1f010000 0 0 asymmetri Fedora kernel signing key: d69a84e6bce3d216b979e9505b3e3ef9a7118079: X509.RSA a7118079 []
+ ...
+
+Beyond the public key generated specifically for module signing, any file
+placed in the kernel source root directory or the kernel build root directory
+whose name is suffixed with ".x509" will be assumed to be an X.509 public key
+and will be added to the keyring.
+
+Further, the architecture code may take public keys from a hardware store and
+add those in also (e.g. from the UEFI key database).
+
+Finally, it is possible to add additional public keys by doing:
+
+ keyctl padd asymmetric "" [.system_keyring-ID] <[key-file]
+
+e.g.:
+
+ keyctl padd asymmetric "" 0x223c7853 <my_public_key.x509
+
+Note, however, that the kernel will only permit keys to be added to
+.system_keyring _if_ the new key's X.509 wrapper is validly signed by a key
+that is already resident in the .system_keyring at the time the key was added.
+
+
+=========================
+MANUALLY SIGNING MODULES
+=========================
+
+To manually sign a module, use the scripts/sign-file tool available in
+the Linux kernel source tree. The script requires 4 arguments:
+
+ 1. The hash algorithm (e.g., sha256)
+ 2. The private key filename
+ 3. The public key filename
+ 4. The kernel module to be signed
+
+The following is an example to sign a kernel module:
+
+ scripts/sign-file sha512 kernel-signkey.priv \
+ kernel-signkey.x509 module.ko
+
+The hash algorithm used does not have to match the one configured, but if it
+doesn't, you should make sure that hash algorithm is either built into the
+kernel or can be loaded without requiring itself.
+
+
+============================
+SIGNED MODULES AND STRIPPING
+============================
+
+A signed module has a digital signature simply appended at the end. The string
+"~Module signature appended~." at the end of the module's file confirms that a
+signature is present but it does not confirm that the signature is valid!
+
+Signed modules are BRITTLE as the signature is outside of the defined ELF
+container. Thus they MAY NOT be stripped once the signature is computed and
+attached. Note the entire module is the signed payload, including any and all
+debug information present at the time of signing.
+
+
+======================
+LOADING SIGNED MODULES
+======================
+
+Modules are loaded with insmod, modprobe, init_module() or finit_module(),
+exactly as for unsigned modules as no processing is done in userspace. The
+signature checking is all done within the kernel.
+
+
+=========================================
+NON-VALID SIGNATURES AND UNSIGNED MODULES
+=========================================
+
+If CONFIG_MODULE_SIG_FORCE is enabled or enforcemodulesig=1 is supplied on
+the kernel command line, the kernel will only load validly signed modules
+for which it has a public key. Otherwise, it will also load modules that are
+unsigned. Any module for which the kernel has a key, but which proves to have
+a signature mismatch will not be permitted to load.
+
+Any module that has an unparseable signature will be rejected.
+
+
+=========================================
+ADMINISTERING/PROTECTING THE PRIVATE KEY
+=========================================
+
+Since the private key is used to sign modules, viruses and malware could use
+the private key to sign modules and compromise the operating system. The
+private key must be either destroyed or moved to a secure location and not kept
+in the root node of the kernel source tree.
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 3c12d9a..8a984e9 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -16,8 +16,12 @@
Default: 64 (as recommended by RFC1700)
ip_no_pmtu_disc - BOOLEAN
- Disable Path MTU Discovery.
- default FALSE
+ Disable Path MTU Discovery. If enabled and a
+ fragmentation-required ICMP is received, the PMTU to this
+ destination will be set to min_pmtu (see below). You will need
+ to raise min_pmtu to the smallest interface MTU on your system
+ manually if you want to avoid locally generated fragments.
+ Default: FALSE
min_pmtu - INTEGER
default 552 - minimum discovered Path MTU
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 26b7ee4..6d48640 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -428,11 +428,6 @@
numa_balancing_scan_size_mb is how many megabytes worth of pages are
scanned for a given scan.
-numa_balancing_settle_count is how many scan periods must complete before
-the schedule balancer stops pushing the task towards a preferred node. This
-gives the scheduler a chance to place the task on an alternative node if the
-preferred node is overloaded.
-
numa_balancing_migrate_deferred is how many page migrations get skipped
unconditionally, after a page migration is skipped because a page is shared
with other tasks. This reduces page migration overhead, and determines
diff --git a/MAINTAINERS b/MAINTAINERS
index 1344816..31a0462 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -783,7 +783,7 @@
F: arch/arm/boot/dts/sama*.dtsi
ARM/CALXEDA HIGHBANK ARCHITECTURE
-M: Rob Herring <rob.herring@calxeda.com>
+M: Rob Herring <robh@kernel.org>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: arch/arm/mach-highbank/
@@ -1008,6 +1008,8 @@
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: arch/arm/mach-keystone/
+F: drivers/clk/keystone/
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone.git
ARM/LOGICPD PXA270 MACHINE SUPPORT
M: Lennert Buytenhek <kernel@wantstofly.org>
@@ -1366,6 +1368,9 @@
S: Supported
F: arch/arm/mach-zynq/
F: drivers/cpuidle/cpuidle-zynq.c
+N: zynq
+N: xilinx
+F: drivers/clocksource/cadence_ttc_timer.c
ARM SMMU DRIVER
M: Will Deacon <will.deacon@arm.com>
@@ -2823,8 +2828,10 @@
INTEL DRM DRIVERS (excluding Poulsbo, Moorestown and derivative chipsets)
M: Daniel Vetter <daniel.vetter@ffwll.ch>
+M: Jani Nikula <jani.nikula@linux.intel.com>
L: intel-gfx@lists.freedesktop.org
L: dri-devel@lists.freedesktop.org
+Q: http://patchwork.freedesktop.org/project/intel-gfx/
T: git git://people.freedesktop.org/~danvet/drm-intel
S: Supported
F: drivers/gpu/drm/i915/
@@ -3761,9 +3768,11 @@
GPIO SUBSYSTEM
M: Linus Walleij <linus.walleij@linaro.org>
-S: Maintained
+M: Alexandre Courbot <gnurou@gmail.com>
L: linux-gpio@vger.kernel.org
-F: Documentation/gpio.txt
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git
+S: Maintained
+F: Documentation/gpio/
F: drivers/gpio/
F: include/linux/gpio*
F: include/asm-generic/gpio.h
@@ -3831,6 +3840,12 @@
S: Maintained
F: drivers/media/usb/gspca/
+GUID PARTITION TABLE (GPT)
+M: Davidlohr Bueso <davidlohr@hp.com>
+L: linux-efi@vger.kernel.org
+S: Maintained
+F: block/partitions/efi.*
+
STK1160 USB VIDEO CAPTURE DRIVER
M: Ezequiel Garcia <elezegarcia@gmail.com>
L: linux-media@vger.kernel.org
@@ -5911,12 +5926,21 @@
M: Herbert Xu <herbert@gondor.apana.org.au>
M: "David S. Miller" <davem@davemloft.net>
L: netdev@vger.kernel.org
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next.git
S: Maintained
F: net/xfrm/
F: net/key/
F: net/ipv4/xfrm*
+F: net/ipv4/esp4.c
+F: net/ipv4/ah4.c
+F: net/ipv4/ipcomp.c
+F: net/ipv4/ip_vti.c
F: net/ipv6/xfrm*
+F: net/ipv6/esp6.c
+F: net/ipv6/ah6.c
+F: net/ipv6/ipcomp6.c
+F: net/ipv6/ip6_vti.c
F: include/uapi/linux/xfrm.h
F: include/net/xfrm.h
@@ -6237,7 +6261,7 @@
OPEN FIRMWARE AND FLATTENED DEVICE TREE
M: Grant Likely <grant.likely@linaro.org>
-M: Rob Herring <rob.herring@calxeda.com>
+M: Rob Herring <robh+dt@kernel.org>
L: devicetree@vger.kernel.org
W: http://fdt.secretlab.ca
T: git git://git.secretlab.ca/git/linux-2.6.git
@@ -6249,7 +6273,7 @@
K: of_match_table
OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS
-M: Rob Herring <rob.herring@calxeda.com>
+M: Rob Herring <robh+dt@kernel.org>
M: Pawel Moll <pawel.moll@arm.com>
M: Mark Rutland <mark.rutland@arm.com>
M: Ian Campbell <ijc+devicetree@hellion.org.uk>
@@ -9571,7 +9595,7 @@
XFS FILESYSTEM
P: Silicon Graphics Inc
-M: Dave Chinner <dchinner@fromorbit.com>
+M: Dave Chinner <david@fromorbit.com>
M: Ben Myers <bpm@sgi.com>
M: xfs@oss.sgi.com
L: xfs@oss.sgi.com
diff --git a/Makefile b/Makefile
index 858a147..ae1a55ad 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 3
PATCHLEVEL = 13
SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc7
NAME = One Giant Leap for Frogkind
# *DOCUMENTATION*
@@ -732,19 +732,15 @@
# Select initial ramdisk compression format, default is gzip(1).
# This shall be used by the dracut(8) tool while creating an initramfs image.
#
-INITRD_COMPRESS=gzip
-ifeq ($(CONFIG_RD_BZIP2), y)
- INITRD_COMPRESS=bzip2
-else ifeq ($(CONFIG_RD_LZMA), y)
- INITRD_COMPRESS=lzma
-else ifeq ($(CONFIG_RD_XZ), y)
- INITRD_COMPRESS=xz
-else ifeq ($(CONFIG_RD_LZO), y)
- INITRD_COMPRESS=lzo
-else ifeq ($(CONFIG_RD_LZ4), y)
- INITRD_COMPRESS=lz4
-endif
-export INITRD_COMPRESS
+INITRD_COMPRESS-y := gzip
+INITRD_COMPRESS-$(CONFIG_RD_BZIP2) := bzip2
+INITRD_COMPRESS-$(CONFIG_RD_LZMA) := lzma
+INITRD_COMPRESS-$(CONFIG_RD_XZ) := xz
+INITRD_COMPRESS-$(CONFIG_RD_LZO) := lzo
+INITRD_COMPRESS-$(CONFIG_RD_LZ4) := lz4
+# do not export INITRD_COMPRESS, since we didn't actually
+# choose a sane default compression above.
+# export INITRD_COMPRESS := $(INITRD_COMPRESS-y)
ifdef CONFIG_MODULE_SIG_ALL
MODSECKEY = ./signing_key.priv
diff --git a/arch/arc/include/uapi/asm/unistd.h b/arch/arc/include/uapi/asm/unistd.h
index 68125dd..39e58d1 100644
--- a/arch/arc/include/uapi/asm/unistd.h
+++ b/arch/arc/include/uapi/asm/unistd.h
@@ -8,7 +8,11 @@
/******** no-legacy-syscalls-ABI *******/
-#ifndef _UAPI_ASM_ARC_UNISTD_H
+/*
+ * Non-typical guard macro to enable inclusion twice in ARCH sys.c
+ * That is how the Generic syscall wrapper generator works
+ */
+#if !defined(_UAPI_ASM_ARC_UNISTD_H) || defined(__SYSCALL)
#define _UAPI_ASM_ARC_UNISTD_H
#define __ARCH_WANT_SYS_EXECVE
@@ -36,4 +40,6 @@
#define __NR_sysfs (__NR_arch_specific_syscall + 3)
__SYSCALL(__NR_sysfs, sys_sysfs)
+#undef __SYSCALL
+
#endif
diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi
index 9db5047..177becd 100644
--- a/arch/arm/boot/dts/exynos5250.dtsi
+++ b/arch/arm/boot/dts/exynos5250.dtsi
@@ -559,7 +559,7 @@
compatible = "arm,pl330", "arm,primecell";
reg = <0x10800000 0x1000>;
interrupts = <0 33 0>;
- clocks = <&clock 271>;
+ clocks = <&clock 346>;
clock-names = "apb_pclk";
#dma-cells = <1>;
#dma-channels = <8>;
diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index ee845fa..9987dd0e 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -87,9 +87,9 @@
interrupts = <1 9 0xf04>;
};
- gpio0: gpio@ffc40000 {
+ gpio0: gpio@e6050000 {
compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
- reg = <0 0xffc40000 0 0x2c>;
+ reg = <0 0xe6050000 0 0x50>;
interrupt-parent = <&gic>;
interrupts = <0 4 0x4>;
#gpio-cells = <2>;
@@ -99,9 +99,9 @@
interrupt-controller;
};
- gpio1: gpio@ffc41000 {
+ gpio1: gpio@e6051000 {
compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
- reg = <0 0xffc41000 0 0x2c>;
+ reg = <0 0xe6051000 0 0x50>;
interrupt-parent = <&gic>;
interrupts = <0 5 0x4>;
#gpio-cells = <2>;
@@ -111,9 +111,9 @@
interrupt-controller;
};
- gpio2: gpio@ffc42000 {
+ gpio2: gpio@e6052000 {
compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
- reg = <0 0xffc42000 0 0x2c>;
+ reg = <0 0xe6052000 0 0x50>;
interrupt-parent = <&gic>;
interrupts = <0 6 0x4>;
#gpio-cells = <2>;
@@ -123,9 +123,9 @@
interrupt-controller;
};
- gpio3: gpio@ffc43000 {
+ gpio3: gpio@e6053000 {
compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
- reg = <0 0xffc43000 0 0x2c>;
+ reg = <0 0xe6053000 0 0x50>;
interrupt-parent = <&gic>;
interrupts = <0 7 0x4>;
#gpio-cells = <2>;
@@ -135,9 +135,9 @@
interrupt-controller;
};
- gpio4: gpio@ffc44000 {
+ gpio4: gpio@e6054000 {
compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
- reg = <0 0xffc44000 0 0x2c>;
+ reg = <0 0xe6054000 0 0x50>;
interrupt-parent = <&gic>;
interrupts = <0 8 0x4>;
#gpio-cells = <2>;
@@ -147,9 +147,9 @@
interrupt-controller;
};
- gpio5: gpio@ffc45000 {
+ gpio5: gpio@e6055000 {
compatible = "renesas,gpio-r8a7790", "renesas,gpio-rcar";
- reg = <0 0xffc45000 0 0x2c>;
+ reg = <0 0xe6055000 0 0x50>;
interrupt-parent = <&gic>;
interrupts = <0 9 0x4>;
#gpio-cells = <2>;
@@ -241,7 +241,7 @@
sdhi0: sdhi@ee100000 {
compatible = "renesas,sdhi-r8a7790";
- reg = <0 0xee100000 0 0x100>;
+ reg = <0 0xee100000 0 0x200>;
interrupt-parent = <&gic>;
interrupts = <0 165 4>;
cap-sd-highspeed;
@@ -250,7 +250,7 @@
sdhi1: sdhi@ee120000 {
compatible = "renesas,sdhi-r8a7790";
- reg = <0 0xee120000 0 0x100>;
+ reg = <0 0xee120000 0 0x200>;
interrupt-parent = <&gic>;
interrupts = <0 166 4>;
cap-sd-highspeed;
diff --git a/arch/arm/crypto/aesbs-core.S_shipped b/arch/arm/crypto/aesbs-core.S_shipped
index 64205d4..71e5fc7 100644
--- a/arch/arm/crypto/aesbs-core.S_shipped
+++ b/arch/arm/crypto/aesbs-core.S_shipped
@@ -58,7 +58,7 @@
# define VFP_ABI_FRAME 0
# define BSAES_ASM_EXTENDED_KEY
# define XTS_CHAIN_TWEAK
-# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_ARCH__ 7
#endif
#ifdef __thumb__
diff --git a/arch/arm/crypto/bsaes-armv7.pl b/arch/arm/crypto/bsaes-armv7.pl
index f3d96d9..be068db 100644
--- a/arch/arm/crypto/bsaes-armv7.pl
+++ b/arch/arm/crypto/bsaes-armv7.pl
@@ -701,7 +701,7 @@
# define VFP_ABI_FRAME 0
# define BSAES_ASM_EXTENDED_KEY
# define XTS_CHAIN_TWEAK
-# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_ARCH__ 7
#endif
#ifdef __thumb__
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 3c597c2..fbeb39c 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -329,7 +329,7 @@
*/
#define ioremap(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE)
#define ioremap_nocache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_cached(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
+#define ioremap_cache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
#define ioremap_wc(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_WC)
#define iounmap __arm_iounmap
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 6976b03..8756e4b 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -347,7 +347,8 @@
#define ARCH_PFN_OFFSET PHYS_PFN_OFFSET
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-#define virt_addr_valid(kaddr) ((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory)
+#define virt_addr_valid(kaddr) (((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory) \
+ && pfn_valid(__pa(kaddr) >> PAGE_SHIFT) )
#endif
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 141baa3..acabef1 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -15,7 +15,7 @@
#include <uapi/asm/unistd.h>
-#define __NR_syscalls (380)
+#define __NR_syscalls (384)
#define __ARM_NR_cmpxchg (__ARM_NR_BASE+0x00fff0)
#define __ARCH_WANT_STAT64
diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h
index 75579a9..3759cac 100644
--- a/arch/arm/include/asm/xen/page.h
+++ b/arch/arm/include/asm/xen/page.h
@@ -117,6 +117,6 @@
return __set_phys_to_machine(pfn, mfn);
}
-#define xen_remap(cookie, size) ioremap_cached((cookie), (size));
+#define xen_remap(cookie, size) ioremap_cache((cookie), (size));
#endif /* _ASM_ARM_XEN_PAGE_H */
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index af33b44..fb5584d 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -406,6 +406,8 @@
#define __NR_process_vm_writev (__NR_SYSCALL_BASE+377)
#define __NR_kcmp (__NR_SYSCALL_BASE+378)
#define __NR_finit_module (__NR_SYSCALL_BASE+379)
+#define __NR_sched_setattr (__NR_SYSCALL_BASE+380)
+#define __NR_sched_getattr (__NR_SYSCALL_BASE+381)
/*
* This may need to be greater than __NR_last_syscall+1 in order to
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index c6ca7e3..166e945 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -389,6 +389,8 @@
CALL(sys_process_vm_writev)
CALL(sys_kcmp)
CALL(sys_finit_module)
+/* 380 */ CALL(sys_sched_setattr)
+ CALL(sys_sched_getattr)
#ifndef syscalls_counted
.equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
#define syscalls_counted
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 7940241..6eda3bf 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -36,7 +36,13 @@
#include <asm/system_misc.h>
#include <asm/opcodes.h>
-static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" };
+static const char *handler[]= {
+ "prefetch abort",
+ "data abort",
+ "address exception",
+ "interrupt",
+ "undefined instruction",
+};
void *vectors_page;
diff --git a/arch/arm/mach-footbridge/dc21285-timer.c b/arch/arm/mach-footbridge/dc21285-timer.c
index 9ee78f7..782f6c7 100644
--- a/arch/arm/mach-footbridge/dc21285-timer.c
+++ b/arch/arm/mach-footbridge/dc21285-timer.c
@@ -96,11 +96,12 @@
void __init footbridge_timer_init(void)
{
struct clock_event_device *ce = &ckevt_dc21285;
+ unsigned rate = DIV_ROUND_CLOSEST(mem_fclk_21285, 16);
- clocksource_register_hz(&cksrc_dc21285, (mem_fclk_21285 + 8) / 16);
+ clocksource_register_hz(&cksrc_dc21285, rate);
setup_irq(ce->irq, &footbridge_timer_irq);
ce->cpumask = cpumask_of(smp_processor_id());
- clockevents_config_and_register(ce, mem_fclk_21285, 0x4, 0xffffff);
+ clockevents_config_and_register(ce, rate, 0x4, 0xffffff);
}
diff --git a/arch/arm/mach-omap2/board-ldp.c b/arch/arm/mach-omap2/board-ldp.c
index 4ec8d82..44a59c3 100644
--- a/arch/arm/mach-omap2/board-ldp.c
+++ b/arch/arm/mach-omap2/board-ldp.c
@@ -242,12 +242,18 @@
static int ldp_twl_gpio_setup(struct device *dev, unsigned gpio, unsigned ngpio)
{
+ int res;
+
/* LCD enable GPIO */
ldp_lcd_pdata.enable_gpio = gpio + 7;
/* Backlight enable GPIO */
ldp_lcd_pdata.backlight_gpio = gpio + 15;
+ res = platform_device_register(&ldp_lcd_device);
+ if (res)
+ pr_err("Unable to register LCD: %d\n", res);
+
return 0;
}
@@ -346,7 +352,6 @@
static struct platform_device *ldp_devices[] __initdata = {
&ldp_gpio_keys_device,
- &ldp_lcd_device,
};
#ifdef CONFIG_OMAP_MUX
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 58347bb..4cf1655 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -101,13 +101,51 @@
{ "dss_hdmi", "omapdss_hdmi", -1 },
};
+static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes)
+{
+ u32 enable_mask, enable_shift;
+ u32 pipd_mask, pipd_shift;
+ u32 reg;
+
+ if (dsi_id == 0) {
+ enable_mask = OMAP4_DSI1_LANEENABLE_MASK;
+ enable_shift = OMAP4_DSI1_LANEENABLE_SHIFT;
+ pipd_mask = OMAP4_DSI1_PIPD_MASK;
+ pipd_shift = OMAP4_DSI1_PIPD_SHIFT;
+ } else if (dsi_id == 1) {
+ enable_mask = OMAP4_DSI2_LANEENABLE_MASK;
+ enable_shift = OMAP4_DSI2_LANEENABLE_SHIFT;
+ pipd_mask = OMAP4_DSI2_PIPD_MASK;
+ pipd_shift = OMAP4_DSI2_PIPD_SHIFT;
+ } else {
+ return -ENODEV;
+ }
+
+ reg = omap4_ctrl_pad_readl(OMAP4_CTRL_MODULE_PAD_CORE_CONTROL_DSIPHY);
+
+ reg &= ~enable_mask;
+ reg &= ~pipd_mask;
+
+ reg |= (lanes << enable_shift) & enable_mask;
+ reg |= (lanes << pipd_shift) & pipd_mask;
+
+ omap4_ctrl_pad_writel(reg, OMAP4_CTRL_MODULE_PAD_CORE_CONTROL_DSIPHY);
+
+ return 0;
+}
+
static int omap_dsi_enable_pads(int dsi_id, unsigned lane_mask)
{
+ if (cpu_is_omap44xx())
+ return omap4_dsi_mux_pads(dsi_id, lane_mask);
+
return 0;
}
static void omap_dsi_disable_pads(int dsi_id, unsigned lane_mask)
{
+ if (cpu_is_omap44xx())
+ omap4_dsi_mux_pads(dsi_id, 0);
}
static int omap_dss_set_min_bus_tput(struct device *dev, unsigned long tput)
diff --git a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
index 56cebb0..d23c77f 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
@@ -796,7 +796,7 @@
/* gpmc */
static struct omap_hwmod_irq_info omap2xxx_gpmc_irqs[] = {
- { .irq = 20 },
+ { .irq = 20 + OMAP_INTC_START, },
{ .irq = -1 }
};
@@ -841,7 +841,7 @@
};
static struct omap_hwmod_irq_info omap2_rng_mpu_irqs[] = {
- { .irq = 52 },
+ { .irq = 52 + OMAP_INTC_START, },
{ .irq = -1 }
};
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index d337429..4c3b1e6 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -2165,7 +2165,7 @@
};
static struct omap_hwmod_irq_info omap3xxx_gpmc_irqs[] = {
- { .irq = 20 },
+ { .irq = 20 + OMAP_INTC_START, },
{ .irq = -1 }
};
@@ -2999,7 +2999,7 @@
static struct omap_hwmod omap3xxx_mmu_isp_hwmod;
static struct omap_hwmod_irq_info omap3xxx_mmu_isp_irqs[] = {
- { .irq = 24 },
+ { .irq = 24 + OMAP_INTC_START, },
{ .irq = -1 }
};
@@ -3041,7 +3041,7 @@
static struct omap_hwmod omap3xxx_mmu_iva_hwmod;
static struct omap_hwmod_irq_info omap3xxx_mmu_iva_irqs[] = {
- { .irq = 28 },
+ { .irq = 28 + OMAP_INTC_START, },
{ .irq = -1 }
};
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index db32d53..18f333c 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -1637,7 +1637,7 @@
.class = &dra7xx_uart_hwmod_class,
.clkdm_name = "l4per_clkdm",
.main_clk = "uart1_gfclk_mux",
- .flags = HWMOD_SWSUP_SIDLE_ACT,
+ .flags = HWMOD_SWSUP_SIDLE_ACT | DEBUG_OMAP2UART1_FLAGS,
.prcm = {
.omap4 = {
.clkctrl_offs = DRA7XX_CM_L4PER_UART1_CLKCTRL_OFFSET,
diff --git a/arch/arm/mach-pxa/include/mach/lubbock.h b/arch/arm/mach-pxa/include/mach/lubbock.h
index 2a086e8..958cd6af 100644
--- a/arch/arm/mach-pxa/include/mach/lubbock.h
+++ b/arch/arm/mach-pxa/include/mach/lubbock.h
@@ -10,6 +10,8 @@
* published by the Free Software Foundation.
*/
+#include <mach/irqs.h>
+
#define LUBBOCK_ETH_PHYS PXA_CS3_PHYS
#define LUBBOCK_FPGA_PHYS PXA_CS2_PHYS
diff --git a/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c b/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c
index 7eb9a10..2fddf38 100644
--- a/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c
+++ b/arch/arm/mach-s3c64xx/mach-s3c64xx-dt.c
@@ -8,8 +8,6 @@
* published by the Free Software Foundation.
*/
-#include <linux/clk-provider.h>
-#include <linux/irqchip.h>
#include <linux/of_platform.h>
#include <asm/mach/arch.h>
@@ -48,15 +46,9 @@
panic("SoC is not S3C64xx!");
}
-static void __init s3c64xx_dt_init_irq(void)
-{
- of_clk_init(NULL);
- samsung_wdt_reset_of_init();
- irqchip_init();
-};
-
static void __init s3c64xx_dt_init_machine(void)
{
+ samsung_wdt_reset_of_init();
of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
}
@@ -79,7 +71,6 @@
/* Maintainer: Tomasz Figa <tomasz.figa@gmail.com> */
.dt_compat = s3c64xx_dt_compat,
.map_io = s3c64xx_dt_map_io,
- .init_irq = s3c64xx_dt_init_irq,
.init_machine = s3c64xx_dt_init_machine,
.restart = s3c64xx_dt_restart,
MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
index 958e3cb..8ea87bd 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva.c
@@ -483,7 +483,7 @@
.id = 0,
.dev = {
.platform_data = &lcdc0_info,
- .coherent_dma_mask = ~0,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
@@ -580,7 +580,7 @@
.id = 1,
.dev = {
.platform_data = &hdmi_lcdc_info,
- .coherent_dma_mask = ~0,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
@@ -614,6 +614,11 @@
REGULATOR_SUPPLY("vqmmc", "sh_mmcif"),
};
+/* Fixed 3.3V regulator used by LCD backlight */
+static struct regulator_consumer_supply fixed5v0_power_consumers[] = {
+ REGULATOR_SUPPLY("power", "pwm-backlight.0"),
+};
+
/* Fixed 3.3V regulator to be used by SDHI0 */
static struct regulator_consumer_supply vcc_sdhi0_consumers[] = {
REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.0"),
@@ -1196,6 +1201,8 @@
regulator_register_always_on(0, "fixed-3.3V", fixed3v3_power_consumers,
ARRAY_SIZE(fixed3v3_power_consumers), 3300000);
+ regulator_register_always_on(3, "fixed-5.0V", fixed5v0_power_consumers,
+ ARRAY_SIZE(fixed5v0_power_consumers), 5000000);
pinctrl_register_mappings(eva_pinctrl_map, ARRAY_SIZE(eva_pinctrl_map));
pwm_add_table(pwm_lookup, ARRAY_SIZE(pwm_lookup));
diff --git a/arch/arm/mach-shmobile/board-bockw.c b/arch/arm/mach-shmobile/board-bockw.c
index 38611526..3c4995a 100644
--- a/arch/arm/mach-shmobile/board-bockw.c
+++ b/arch/arm/mach-shmobile/board-bockw.c
@@ -679,7 +679,7 @@
.id = i,
.data = &rsnd_card_info[i],
.size_data = sizeof(struct asoc_simple_card_info),
- .dma_mask = ~0,
+ .dma_mask = DMA_BIT_MASK(32),
};
platform_device_register_full(&cardinfo);
diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c
index fe689b7..bc40b85 100644
--- a/arch/arm/mach-shmobile/board-kzm9g.c
+++ b/arch/arm/mach-shmobile/board-kzm9g.c
@@ -334,7 +334,7 @@
.resource = lcdc_resources,
.dev = {
.platform_data = &lcdc_info,
- .coherent_dma_mask = ~0,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
diff --git a/arch/arm/mach-shmobile/board-lager.c b/arch/arm/mach-shmobile/board-lager.c
index a8d3ce6..e0406fd 100644
--- a/arch/arm/mach-shmobile/board-lager.c
+++ b/arch/arm/mach-shmobile/board-lager.c
@@ -245,7 +245,9 @@
{
lager_add_standard_devices();
- phy_register_fixup_for_id("r8a7790-ether-ff:01", lager_ksz8041_fixup);
+ if (IS_ENABLED(CONFIG_PHYLIB))
+ phy_register_fixup_for_id("r8a7790-ether-ff:01",
+ lager_ksz8041_fixup);
}
static const char * const lager_boards_compat_dt[] __initconst = {
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index af06753..e721d2c 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -409,7 +409,7 @@
.resource = lcdc_resources,
.dev = {
.platform_data = &lcdc_info,
- .coherent_dma_mask = ~0,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
@@ -499,7 +499,7 @@
.id = 1,
.dev = {
.platform_data = &hdmi_lcdc_info,
- .coherent_dma_mask = ~0,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 6d5ba9a..3387e60 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -175,16 +175,16 @@
unsigned long i;
if (cache_is_vipt_nonaliasing()) {
for (i = 0; i < (1 << compound_order(page)); i++) {
- void *addr = kmap_atomic(page);
+ void *addr = kmap_atomic(page + i);
__cpuc_flush_dcache_area(addr, PAGE_SIZE);
kunmap_atomic(addr);
}
} else {
for (i = 0; i < (1 << compound_order(page)); i++) {
- void *addr = kmap_high_get(page);
+ void *addr = kmap_high_get(page + i);
if (addr) {
__cpuc_flush_dcache_area(addr, PAGE_SIZE);
- kunmap_high(page);
+ kunmap_high(page + i);
}
}
}
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 83e4f95..8550123 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -96,7 +96,7 @@
struct remap_data *info = data;
struct page *page = info->pages[info->index++];
unsigned long pfn = page_to_pfn(page);
- pte_t pte = pfn_pte(pfn, info->prot);
+ pte_t pte = pte_mkspecial(pfn_pte(pfn, info->prot));
if (map_foreign_page(pfn, info->fgmfn, info->domid))
return -EFAULT;
@@ -224,10 +224,10 @@
}
if (of_address_to_resource(node, GRANT_TABLE_PHYSADDR, &res))
return 0;
- xen_hvm_resume_frames = res.start >> PAGE_SHIFT;
+ xen_hvm_resume_frames = res.start;
xen_events_irq = irq_of_parse_and_map(node, 0);
pr_info("Xen %s support found, events_irq=%d gnttab_frame_pfn=%lx\n",
- version, xen_events_irq, xen_hvm_resume_frames);
+ version, xen_events_irq, (xen_hvm_resume_frames >> PAGE_SHIFT));
xen_domain_type = XEN_HVM_DOMAIN;
xen_setup_features();
diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/page-coherent.h
index 2820f1a..dde3fc9 100644
--- a/arch/arm64/include/asm/xen/page-coherent.h
+++ b/arch/arm64/include/asm/xen/page-coherent.h
@@ -23,25 +23,21 @@
unsigned long offset, size_t size, enum dma_data_direction dir,
struct dma_attrs *attrs)
{
- __generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
}
static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
size_t size, enum dma_data_direction dir,
struct dma_attrs *attrs)
{
- __generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
}
static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
dma_addr_t handle, size_t size, enum dma_data_direction dir)
{
- __generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
}
static inline void xen_dma_sync_single_for_device(struct device *hwdev,
dma_addr_t handle, size_t size, enum dma_data_direction dir)
{
- __generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
}
#endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 6777a21..6a8928b 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -214,31 +214,29 @@
{
int err, len, type, disabled = !ctrl.enabled;
- if (disabled) {
- len = 0;
- type = HW_BREAKPOINT_EMPTY;
- } else {
- err = arch_bp_generic_fields(ctrl, &len, &type);
- if (err)
- return err;
+ attr->disabled = disabled;
+ if (disabled)
+ return 0;
- switch (note_type) {
- case NT_ARM_HW_BREAK:
- if ((type & HW_BREAKPOINT_X) != type)
- return -EINVAL;
- break;
- case NT_ARM_HW_WATCH:
- if ((type & HW_BREAKPOINT_RW) != type)
- return -EINVAL;
- break;
- default:
+ err = arch_bp_generic_fields(ctrl, &len, &type);
+ if (err)
+ return err;
+
+ switch (note_type) {
+ case NT_ARM_HW_BREAK:
+ if ((type & HW_BREAKPOINT_X) != type)
return -EINVAL;
- }
+ break;
+ case NT_ARM_HW_WATCH:
+ if ((type & HW_BREAKPOINT_RW) != type)
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
}
attr->bp_len = len;
attr->bp_type = type;
- attr->disabled = disabled;
return 0;
}
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index f0e2784..2f9b751 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -125,42 +125,38 @@
void mark_rodata_ro(void);
#endif
-#ifdef CONFIG_PA8X00
-/* Only pa8800, pa8900 needs this */
-
#include <asm/kmap_types.h>
#define ARCH_HAS_KMAP
-void kunmap_parisc(void *addr);
-
static inline void *kmap(struct page *page)
{
might_sleep();
+ flush_dcache_page(page);
return page_address(page);
}
static inline void kunmap(struct page *page)
{
- kunmap_parisc(page_address(page));
+ flush_kernel_dcache_page_addr(page_address(page));
}
static inline void *kmap_atomic(struct page *page)
{
pagefault_disable();
+ flush_dcache_page(page);
return page_address(page);
}
static inline void __kunmap_atomic(void *addr)
{
- kunmap_parisc(addr);
+ flush_kernel_dcache_page_addr(addr);
pagefault_enable();
}
#define kmap_atomic_prot(page, prot) kmap_atomic(page)
#define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn))
#define kmap_atomic_to_page(ptr) virt_to_page(ptr)
-#endif
#endif /* _PARISC_CACHEFLUSH_H */
diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h
index b7adb2a..c53fc63 100644
--- a/arch/parisc/include/asm/page.h
+++ b/arch/parisc/include/asm/page.h
@@ -28,9 +28,8 @@
void clear_page_asm(void *page);
void copy_page_asm(void *to, void *from);
-void clear_user_page(void *vto, unsigned long vaddr, struct page *pg);
-void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
- struct page *pg);
+#define clear_user_page(vto, vaddr, page) clear_page_asm(vto)
+#define copy_user_page(vto, vfrom, vaddr, page) copy_page_asm(vto, vfrom)
/* #define CONFIG_PARISC_TMPALIAS */
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index c035673..a725455 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -388,41 +388,6 @@
}
EXPORT_SYMBOL(flush_kernel_dcache_page_addr);
-void clear_user_page(void *vto, unsigned long vaddr, struct page *page)
-{
- clear_page_asm(vto);
- if (!parisc_requires_coherency())
- flush_kernel_dcache_page_asm(vto);
-}
-EXPORT_SYMBOL(clear_user_page);
-
-void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
- struct page *pg)
-{
- /* Copy using kernel mapping. No coherency is needed
- (all in kmap/kunmap) on machines that don't support
- non-equivalent aliasing. However, the `from' page
- needs to be flushed before it can be accessed through
- the kernel mapping. */
- preempt_disable();
- flush_dcache_page_asm(__pa(vfrom), vaddr);
- preempt_enable();
- copy_page_asm(vto, vfrom);
- if (!parisc_requires_coherency())
- flush_kernel_dcache_page_asm(vto);
-}
-EXPORT_SYMBOL(copy_user_page);
-
-#ifdef CONFIG_PA8X00
-
-void kunmap_parisc(void *addr)
-{
- if (parisc_requires_coherency())
- flush_kernel_dcache_page_addr(addr);
-}
-EXPORT_SYMBOL(kunmap_parisc);
-#endif
-
void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
{
unsigned long flags;
diff --git a/arch/powerpc/boot/dts/mpc5125twr.dts b/arch/powerpc/boot/dts/mpc5125twr.dts
index 4177b62..a618dfc 100644
--- a/arch/powerpc/boot/dts/mpc5125twr.dts
+++ b/arch/powerpc/boot/dts/mpc5125twr.dts
@@ -58,7 +58,6 @@
compatible = "fsl,mpc5121-immr";
#address-cells = <1>;
#size-cells = <1>;
- #interrupt-cells = <2>;
ranges = <0x0 0x80000000 0x400000>;
reg = <0x80000000 0x400000>;
bus-frequency = <66000000>; // 66 MHz ips bus
@@ -189,6 +188,10 @@
reg = <0xA000 0x1000>;
};
+ // disable USB1 port
+ // TODO:
+ // correct pinmux config and fix USB3320 ulpi dependency
+ // before re-enabling it
usb@3000 {
compatible = "fsl,mpc5121-usb2-dr";
reg = <0x3000 0x400>;
@@ -197,6 +200,7 @@
interrupts = <43 0x8>;
dr_mode = "host";
phy_type = "ulpi";
+ status = "disabled";
};
// 5125 PSCs are not 52xx or 5121 PSC compatible
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 894662a..243ce69 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -284,7 +284,7 @@
subi r1,r1,INT_FRAME_SIZE; /* alloc frame on kernel stack */ \
beq- 1f; \
ld r1,PACAKSAVE(r13); /* kernel stack to use */ \
-1: cmpdi cr1,r1,0; /* check if r1 is in userspace */ \
+1: cmpdi cr1,r1,-INT_FRAME_SIZE; /* check if r1 is in userspace */ \
blt+ cr1,3f; /* abort if it is */ \
li r1,(n); /* will be reloaded later */ \
sth r1,PACA_TRAP_SAVE(r13); \
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 4a594b7..bc23b1b 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -192,6 +192,10 @@
extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst);
extern ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst);
extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd);
+extern void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu,
+ struct kvm_vcpu *vcpu);
+extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
+ struct kvmppc_book3s_shadow_vcpu *svcpu);
static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
{
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 0bd9348..192917d 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -79,6 +79,7 @@
ulong vmhandler;
ulong scratch0;
ulong scratch1;
+ ulong scratch2;
u8 in_guest;
u8 restore_hid5;
u8 napping;
@@ -106,6 +107,7 @@
};
struct kvmppc_book3s_shadow_vcpu {
+ bool in_use;
ulong gpr[14];
u32 cr;
u32 xer;
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 033c06b..7bdcf34 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -720,13 +720,13 @@
int64_t opal_pci_poll(uint64_t phb_id);
int64_t opal_return_cpu(void);
-int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, uint64_t *val);
+int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, __be64 *val);
int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val);
int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type,
uint32_t addr, uint32_t data, uint32_t sz);
int64_t opal_lpc_read(uint32_t chip_id, enum OpalLPCAddressType addr_type,
- uint32_t addr, uint32_t *data, uint32_t sz);
+ uint32_t addr, __be32 *data, uint32_t sz);
int64_t opal_validate_flash(uint64_t buffer, uint32_t *size, uint32_t *result);
int64_t opal_manage_flash(uint8_t op);
int64_t opal_update_flash(uint64_t blk_list);
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 9ee1261..aace905 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -35,7 +35,7 @@
extern void enable_kernel_spe(void);
extern void giveup_spe(struct task_struct *);
extern void load_up_spe(struct task_struct *);
-extern void switch_booke_debug_regs(struct thread_struct *new_thread);
+extern void switch_booke_debug_regs(struct debug_reg *new_debug);
#ifndef CONFIG_SMP
extern void discard_lazy_cpu_state(void);
diff --git a/arch/powerpc/include/asm/unaligned.h b/arch/powerpc/include/asm/unaligned.h
index 5f1b1e3..8296381 100644
--- a/arch/powerpc/include/asm/unaligned.h
+++ b/arch/powerpc/include/asm/unaligned.h
@@ -4,13 +4,18 @@
#ifdef __KERNEL__
/*
- * The PowerPC can do unaligned accesses itself in big endian mode.
+ * The PowerPC can do unaligned accesses itself based on its endian mode.
*/
#include <linux/unaligned/access_ok.h>
#include <linux/unaligned/generic.h>
+#ifdef __LITTLE_ENDIAN__
+#define get_unaligned __get_unaligned_le
+#define put_unaligned __put_unaligned_le
+#else
#define get_unaligned __get_unaligned_be
#define put_unaligned __put_unaligned_be
+#endif
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_UNALIGNED_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 2ea5cc0..d3de010 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -576,6 +576,7 @@
HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler);
HSTATE_FIELD(HSTATE_SCRATCH0, scratch0);
HSTATE_FIELD(HSTATE_SCRATCH1, scratch1);
+ HSTATE_FIELD(HSTATE_SCRATCH2, scratch2);
HSTATE_FIELD(HSTATE_IN_GUEST, in_guest);
HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5);
HSTATE_FIELD(HSTATE_NAPPING, napping);
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 779a78c..11c1d06 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -124,15 +124,15 @@
void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
{
unsigned long addr;
- const u32 *basep, *sizep;
+ const __be32 *basep, *sizep;
unsigned int rtas_start = 0, rtas_end = 0;
basep = of_get_property(rtas.dev, "linux,rtas-base", NULL);
sizep = of_get_property(rtas.dev, "rtas-size", NULL);
if (basep && sizep) {
- rtas_start = *basep;
- rtas_end = *basep + *sizep;
+ rtas_start = be32_to_cpup(basep);
+ rtas_end = rtas_start + be32_to_cpup(sizep);
}
for (addr = begin; addr < end; addr += PAGE_SIZE) {
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 2ae41ab..4f0946d 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -80,6 +80,7 @@
* of the function that the cpu should jump to to continue
* initialization.
*/
+ .balign 8
.globl __secondary_hold_spinloop
__secondary_hold_spinloop:
.llong 0x0
@@ -470,6 +471,7 @@
mtctr r8
bctr
+.balign 8
p_end: .llong _end - _stext
4: /* Now copy the rest of the kernel up to _end */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 3386d8a..4a96556 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -339,7 +339,7 @@
#endif
}
-static void prime_debug_regs(struct thread_struct *thread)
+static void prime_debug_regs(struct debug_reg *debug)
{
/*
* We could have inherited MSR_DE from userspace, since
@@ -348,22 +348,22 @@
*/
mtmsr(mfmsr() & ~MSR_DE);
- mtspr(SPRN_IAC1, thread->debug.iac1);
- mtspr(SPRN_IAC2, thread->debug.iac2);
+ mtspr(SPRN_IAC1, debug->iac1);
+ mtspr(SPRN_IAC2, debug->iac2);
#if CONFIG_PPC_ADV_DEBUG_IACS > 2
- mtspr(SPRN_IAC3, thread->debug.iac3);
- mtspr(SPRN_IAC4, thread->debug.iac4);
+ mtspr(SPRN_IAC3, debug->iac3);
+ mtspr(SPRN_IAC4, debug->iac4);
#endif
- mtspr(SPRN_DAC1, thread->debug.dac1);
- mtspr(SPRN_DAC2, thread->debug.dac2);
+ mtspr(SPRN_DAC1, debug->dac1);
+ mtspr(SPRN_DAC2, debug->dac2);
#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
- mtspr(SPRN_DVC1, thread->debug.dvc1);
- mtspr(SPRN_DVC2, thread->debug.dvc2);
+ mtspr(SPRN_DVC1, debug->dvc1);
+ mtspr(SPRN_DVC2, debug->dvc2);
#endif
- mtspr(SPRN_DBCR0, thread->debug.dbcr0);
- mtspr(SPRN_DBCR1, thread->debug.dbcr1);
+ mtspr(SPRN_DBCR0, debug->dbcr0);
+ mtspr(SPRN_DBCR1, debug->dbcr1);
#ifdef CONFIG_BOOKE
- mtspr(SPRN_DBCR2, thread->debug.dbcr2);
+ mtspr(SPRN_DBCR2, debug->dbcr2);
#endif
}
/*
@@ -371,11 +371,11 @@
* debug registers, set the debug registers from the values
* stored in the new thread.
*/
-void switch_booke_debug_regs(struct thread_struct *new_thread)
+void switch_booke_debug_regs(struct debug_reg *new_debug)
{
if ((current->thread.debug.dbcr0 & DBCR0_IDM)
- || (new_thread->debug.dbcr0 & DBCR0_IDM))
- prime_debug_regs(new_thread);
+ || (new_debug->dbcr0 & DBCR0_IDM))
+ prime_debug_regs(new_debug);
}
EXPORT_SYMBOL_GPL(switch_booke_debug_regs);
#else /* !CONFIG_PPC_ADV_DEBUG_REGS */
@@ -683,7 +683,7 @@
#endif /* CONFIG_SMP */
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
- switch_booke_debug_regs(&new->thread);
+ switch_booke_debug_regs(&new->thread.debug);
#else
/*
* For PPC_BOOK3S_64, we use the hw-breakpoint interfaces that would
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 75fb404..2e3d2bf 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -1555,7 +1555,7 @@
flush_fp_to_thread(child);
if (fpidx < (PT_FPSCR - PT_FPR0))
- memcpy(&tmp, &child->thread.fp_state.fpr,
+ memcpy(&tmp, &child->thread.TS_FPR(fpidx),
sizeof(long));
else
tmp = child->thread.fp_state.fpscr;
@@ -1588,7 +1588,7 @@
flush_fp_to_thread(child);
if (fpidx < (PT_FPSCR - PT_FPR0))
- memcpy(&child->thread.fp_state.fpr, &data,
+ memcpy(&child->thread.TS_FPR(fpidx), &data,
sizeof(long));
else
child->thread.fp_state.fpscr = data;
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index febc804..bc76cc6 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -479,7 +479,7 @@
if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR) &&
(dn = of_find_node_by_path("/rtas"))) {
int num_addr_cell, num_size_cell, maxcpus;
- const unsigned int *ireg;
+ const __be32 *ireg;
num_addr_cell = of_n_addr_cells(dn);
num_size_cell = of_n_size_cells(dn);
@@ -489,7 +489,7 @@
if (!ireg)
goto out;
- maxcpus = ireg[num_addr_cell + num_size_cell];
+ maxcpus = be32_to_cpup(ireg + num_addr_cell + num_size_cell);
/* Double maxcpus for processors which have SMT capability */
if (cpu_has_feature(CPU_FTR_SMT))
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index a3b64f3..c1cf4a1 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -580,7 +580,7 @@
int cpu_to_core_id(int cpu)
{
struct device_node *np;
- const int *reg;
+ const __be32 *reg;
int id = -1;
np = of_get_cpu_node(cpu, NULL);
@@ -591,7 +591,7 @@
if (!reg)
goto out;
- id = *reg;
+ id = be32_to_cpup(reg);
out:
of_node_put(np);
return id;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index f3ff587..c5d1484 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -469,11 +469,14 @@
slb_v = vcpu->kvm->arch.vrma_slb_v;
}
+ preempt_disable();
/* Find the HPTE in the hash table */
index = kvmppc_hv_find_lock_hpte(kvm, eaddr, slb_v,
HPTE_V_VALID | HPTE_V_ABSENT);
- if (index < 0)
+ if (index < 0) {
+ preempt_enable();
return -ENOENT;
+ }
hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
v = hptep[0] & ~HPTE_V_HVLOCK;
gr = kvm->arch.revmap[index].guest_rpte;
@@ -481,6 +484,7 @@
/* Unlock the HPTE */
asm volatile("lwsync" : : : "memory");
hptep[0] = v;
+ preempt_enable();
gpte->eaddr = eaddr;
gpte->vpage = ((v & HPTE_V_AVPN) << 4) | ((eaddr >> 12) & 0xfff);
@@ -665,6 +669,7 @@
return -EFAULT;
} else {
page = pages[0];
+ pfn = page_to_pfn(page);
if (PageHuge(page)) {
page = compound_head(page);
pte_size <<= compound_order(page);
@@ -689,7 +694,6 @@
}
rcu_read_unlock_sched();
}
- pfn = page_to_pfn(page);
}
ret = -EFAULT;
@@ -707,8 +711,14 @@
r = (r & ~(HPTE_R_W|HPTE_R_I|HPTE_R_G)) | HPTE_R_M;
}
- /* Set the HPTE to point to pfn */
- r = (r & ~(HPTE_R_PP0 - pte_size)) | (pfn << PAGE_SHIFT);
+ /*
+ * Set the HPTE to point to pfn.
+ * Since the pfn is at PAGE_SIZE granularity, make sure we
+ * don't mask out lower-order bits if psize < PAGE_SIZE.
+ */
+ if (psize < PAGE_SIZE)
+ psize = PAGE_SIZE;
+ r = (r & ~(HPTE_R_PP0 - psize)) | ((pfn << PAGE_SHIFT) & ~(psize - 1));
if (hpte_is_writable(r) && !write_ok)
r = hpte_make_readonly(r);
ret = RESUME_GUEST;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 072287f..b51d5db 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -131,8 +131,9 @@
static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
+ unsigned long flags;
- spin_lock(&vcpu->arch.tbacct_lock);
+ spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE &&
vc->preempt_tb != TB_NIL) {
vc->stolen_tb += mftb() - vc->preempt_tb;
@@ -143,19 +144,20 @@
vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt;
vcpu->arch.busy_preempt = TB_NIL;
}
- spin_unlock(&vcpu->arch.tbacct_lock);
+ spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
}
static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
+ unsigned long flags;
- spin_lock(&vcpu->arch.tbacct_lock);
+ spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE)
vc->preempt_tb = mftb();
if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST)
vcpu->arch.busy_preempt = mftb();
- spin_unlock(&vcpu->arch.tbacct_lock);
+ spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
}
static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
@@ -486,11 +488,11 @@
*/
if (vc->vcore_state != VCORE_INACTIVE &&
vc->runner->arch.run_task != current) {
- spin_lock(&vc->runner->arch.tbacct_lock);
+ spin_lock_irq(&vc->runner->arch.tbacct_lock);
p = vc->stolen_tb;
if (vc->preempt_tb != TB_NIL)
p += now - vc->preempt_tb;
- spin_unlock(&vc->runner->arch.tbacct_lock);
+ spin_unlock_irq(&vc->runner->arch.tbacct_lock);
} else {
p = vc->stolen_tb;
}
@@ -512,10 +514,10 @@
core_stolen = vcore_stolen_time(vc, now);
stolen = core_stolen - vcpu->arch.stolen_logged;
vcpu->arch.stolen_logged = core_stolen;
- spin_lock(&vcpu->arch.tbacct_lock);
+ spin_lock_irq(&vcpu->arch.tbacct_lock);
stolen += vcpu->arch.busy_stolen;
vcpu->arch.busy_stolen = 0;
- spin_unlock(&vcpu->arch.tbacct_lock);
+ spin_unlock_irq(&vcpu->arch.tbacct_lock);
if (!dt || !vpa)
return;
memset(dt, 0, sizeof(struct dtl_entry));
@@ -589,7 +591,9 @@
if (list_empty(&vcpu->kvm->arch.rtas_tokens))
return RESUME_HOST;
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
rc = kvmppc_rtas_hcall(vcpu);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
if (rc == -ENOENT)
return RESUME_HOST;
@@ -1115,13 +1119,13 @@
if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
return;
- spin_lock(&vcpu->arch.tbacct_lock);
+ spin_lock_irq(&vcpu->arch.tbacct_lock);
now = mftb();
vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) -
vcpu->arch.stolen_logged;
vcpu->arch.busy_preempt = now;
vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
- spin_unlock(&vcpu->arch.tbacct_lock);
+ spin_unlock_irq(&vcpu->arch.tbacct_lock);
--vc->n_runnable;
list_del(&vcpu->arch.run_list);
}
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 9c51544..8689e2e 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -225,6 +225,7 @@
is_io = pa & (HPTE_R_I | HPTE_R_W);
pte_size = PAGE_SIZE << (pa & KVMPPC_PAGE_ORDER_MASK);
pa &= PAGE_MASK;
+ pa |= gpa & ~PAGE_MASK;
} else {
/* Translate to host virtual address */
hva = __gfn_to_hva_memslot(memslot, gfn);
@@ -238,13 +239,13 @@
ptel = hpte_make_readonly(ptel);
is_io = hpte_cache_bits(pte_val(pte));
pa = pte_pfn(pte) << PAGE_SHIFT;
+ pa |= hva & (pte_size - 1);
+ pa |= gpa & ~PAGE_MASK;
}
}
if (pte_size < psize)
return H_PARAMETER;
- if (pa && pte_size > psize)
- pa |= gpa & (pte_size - 1);
ptel &= ~(HPTE_R_PP0 - psize);
ptel |= pa;
@@ -749,6 +750,10 @@
20, /* 1M, unsupported */
};
+/* When called from virtmode, this func should be protected by
+ * preempt_disable(), otherwise, the holding of HPTE_V_HVLOCK
+ * can trigger deadlock issue.
+ */
long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
unsigned long valid)
{
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bc8de75..be4fa04a 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -153,7 +153,6 @@
13: b machine_check_fwnmi
-
/*
* We come in here when wakened from nap mode on a secondary hw thread.
* Relocation is off and most register values are lost.
@@ -224,6 +223,11 @@
/* Clear our vcpu pointer so we don't come back in early */
li r0, 0
std r0, HSTATE_KVM_VCPU(r13)
+ /*
+ * Make sure we clear HSTATE_KVM_VCPU(r13) before incrementing
+ * the nap_count, because once the increment to nap_count is
+ * visible we could be given another vcpu.
+ */
lwsync
/* Clear any pending IPI - we're an offline thread */
ld r5, HSTATE_XICS_PHYS(r13)
@@ -241,7 +245,6 @@
/* increment the nap count and then go to nap mode */
ld r4, HSTATE_KVM_VCORE(r13)
addi r4, r4, VCORE_NAP_COUNT
- lwsync /* make previous updates visible */
51: lwarx r3, 0, r4
addi r3, r3, 1
stwcx. r3, 0, r4
@@ -751,15 +754,14 @@
* guest CR, R12 saved in shadow VCPU SCRATCH1/0
* guest R13 saved in SPRN_SCRATCH0
*/
- /* abuse host_r2 as third scratch area; we get r2 from PACATOC(r13) */
- std r9, HSTATE_HOST_R2(r13)
+ std r9, HSTATE_SCRATCH2(r13)
lbz r9, HSTATE_IN_GUEST(r13)
cmpwi r9, KVM_GUEST_MODE_HOST_HV
beq kvmppc_bad_host_intr
#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
cmpwi r9, KVM_GUEST_MODE_GUEST
- ld r9, HSTATE_HOST_R2(r13)
+ ld r9, HSTATE_SCRATCH2(r13)
beq kvmppc_interrupt_pr
#endif
/* We're now back in the host but in guest MMU context */
@@ -779,7 +781,7 @@
std r6, VCPU_GPR(R6)(r9)
std r7, VCPU_GPR(R7)(r9)
std r8, VCPU_GPR(R8)(r9)
- ld r0, HSTATE_HOST_R2(r13)
+ ld r0, HSTATE_SCRATCH2(r13)
std r0, VCPU_GPR(R9)(r9)
std r10, VCPU_GPR(R10)(r9)
std r11, VCPU_GPR(R11)(r9)
@@ -990,14 +992,13 @@
*/
/* Increment the threads-exiting-guest count in the 0xff00
bits of vcore->entry_exit_count */
- lwsync
ld r5,HSTATE_KVM_VCORE(r13)
addi r6,r5,VCORE_ENTRY_EXIT
41: lwarx r3,0,r6
addi r0,r3,0x100
stwcx. r0,0,r6
bne 41b
- lwsync
+ isync /* order stwcx. vs. reading napping_threads */
/*
* At this point we have an interrupt that we have to pass
@@ -1030,6 +1031,8 @@
sld r0,r0,r4
andc. r3,r3,r0 /* no sense IPI'ing ourselves */
beq 43f
+ /* Order entry/exit update vs. IPIs */
+ sync
mulli r4,r4,PACA_SIZE /* get paca for thread 0 */
subf r6,r4,r13
42: andi. r0,r3,1
@@ -1638,10 +1641,10 @@
bge kvm_cede_exit
stwcx. r4,0,r6
bne 31b
+ /* order napping_threads update vs testing entry_exit_count */
+ isync
li r0,1
stb r0,HSTATE_NAPPING(r13)
- /* order napping_threads update vs testing entry_exit_count */
- lwsync
mr r4,r3
lwz r7,VCORE_ENTRY_EXIT(r5)
cmpwi r7,0x100
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index f4dd041..f779450 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -129,29 +129,32 @@
* R12 = exit handler id
* R13 = PACA
* SVCPU.* = guest *
+ * MSR.EE = 1
*
*/
+ PPC_LL r3, GPR4(r1) /* vcpu pointer */
+
+ /*
+ * kvmppc_copy_from_svcpu can clobber volatile registers, save
+ * the exit handler id to the vcpu and restore it from there later.
+ */
+ stw r12, VCPU_TRAP(r3)
+
/* Transfer reg values from shadow vcpu back to vcpu struct */
/* On 64-bit, interrupts are still off at this point */
- PPC_LL r3, GPR4(r1) /* vcpu pointer */
+
GET_SHADOW_VCPU(r4)
bl FUNC(kvmppc_copy_from_svcpu)
nop
#ifdef CONFIG_PPC_BOOK3S_64
- /* Re-enable interrupts */
- ld r3, HSTATE_HOST_MSR(r13)
- ori r3, r3, MSR_EE
- MTMSR_EERI(r3)
-
/*
* Reload kernel SPRG3 value.
* No need to save guest value as usermode can't modify SPRG3.
*/
ld r3, PACA_SPRG3(r13)
mtspr SPRN_SPRG3, r3
-
#endif /* CONFIG_PPC_BOOK3S_64 */
/* R7 = vcpu */
@@ -177,7 +180,7 @@
PPC_STL r31, VCPU_GPR(R31)(r7)
/* Pass the exit number as 3rd argument to kvmppc_handle_exit */
- mr r5, r12
+ lwz r5, VCPU_TRAP(r7)
/* Restore r3 (kvm_run) and r4 (vcpu) */
REST_2GPRS(3, r1)
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index fe14ca3..5b9e906 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -66,6 +66,7 @@
struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
memcpy(svcpu->slb, to_book3s(vcpu)->slb_shadow, sizeof(svcpu->slb));
svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max;
+ svcpu->in_use = 0;
svcpu_put(svcpu);
#endif
vcpu->cpu = smp_processor_id();
@@ -78,6 +79,9 @@
{
#ifdef CONFIG_PPC_BOOK3S_64
struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+ if (svcpu->in_use) {
+ kvmppc_copy_from_svcpu(vcpu, svcpu);
+ }
memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb));
to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max;
svcpu_put(svcpu);
@@ -110,12 +114,26 @@
svcpu->ctr = vcpu->arch.ctr;
svcpu->lr = vcpu->arch.lr;
svcpu->pc = vcpu->arch.pc;
+ svcpu->in_use = true;
}
/* Copy data touched by real-mode code from shadow vcpu back to vcpu */
void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
struct kvmppc_book3s_shadow_vcpu *svcpu)
{
+ /*
+ * vcpu_put would just call us again because in_use hasn't
+ * been updated yet.
+ */
+ preempt_disable();
+
+ /*
+ * Maybe we were already preempted and synced the svcpu from
+ * our preempt notifiers. Don't bother touching this svcpu then.
+ */
+ if (!svcpu->in_use)
+ goto out;
+
vcpu->arch.gpr[0] = svcpu->gpr[0];
vcpu->arch.gpr[1] = svcpu->gpr[1];
vcpu->arch.gpr[2] = svcpu->gpr[2];
@@ -139,6 +157,10 @@
vcpu->arch.fault_dar = svcpu->fault_dar;
vcpu->arch.fault_dsisr = svcpu->fault_dsisr;
vcpu->arch.last_inst = svcpu->last_inst;
+ svcpu->in_use = false;
+
+out:
+ preempt_enable();
}
static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index a38c4c9..c3c5231 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -153,15 +153,11 @@
li r6, MSR_IR | MSR_DR
andc r6, r5, r6 /* Clear DR and IR in MSR value */
-#ifdef CONFIG_PPC_BOOK3S_32
/*
* Set EE in HOST_MSR so that it's enabled when we get into our
- * C exit handler function. On 64-bit we delay enabling
- * interrupts until we have finished transferring stuff
- * to or from the PACA.
+ * C exit handler function.
*/
ori r5, r5, MSR_EE
-#endif
mtsrr0 r7
mtsrr1 r6
RFI
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 53e65a2..0591e05 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -681,7 +681,7 @@
int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
{
int ret, s;
- struct thread_struct thread;
+ struct debug_reg debug;
#ifdef CONFIG_PPC_FPU
struct thread_fp_state fp;
int fpexc_mode;
@@ -723,9 +723,9 @@
#endif
/* Switch to guest debug context */
- thread.debug = vcpu->arch.shadow_dbg_reg;
- switch_booke_debug_regs(&thread);
- thread.debug = current->thread.debug;
+ debug = vcpu->arch.shadow_dbg_reg;
+ switch_booke_debug_regs(&debug);
+ debug = current->thread.debug;
current->thread.debug = vcpu->arch.shadow_dbg_reg;
kvmppc_fix_ee_before_entry();
@@ -736,8 +736,8 @@
We also get here with interrupts enabled. */
/* Switch back to user space debug context */
- switch_booke_debug_regs(&thread);
- current->thread.debug = thread.debug;
+ switch_booke_debug_regs(&debug);
+ current->thread.debug = debug;
#ifdef CONFIG_PPC_FPU
kvmppc_save_guest_fp(vcpu);
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index d73a590..596a285 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -9,6 +9,14 @@
#include <asm/processor.h>
#include <asm/ppc_asm.h>
+#ifdef __BIG_ENDIAN__
+#define sLd sld /* Shift towards low-numbered address. */
+#define sHd srd /* Shift towards high-numbered address. */
+#else
+#define sLd srd /* Shift towards low-numbered address. */
+#define sHd sld /* Shift towards high-numbered address. */
+#endif
+
.align 7
_GLOBAL(__copy_tofrom_user)
BEGIN_FTR_SECTION
@@ -118,10 +126,10 @@
24: ld r9,0(r4) /* 3+2n loads, 2+2n stores */
25: ld r0,8(r4)
- sld r6,r9,r10
+ sLd r6,r9,r10
26: ldu r9,16(r4)
- srd r7,r0,r11
- sld r8,r0,r10
+ sHd r7,r0,r11
+ sLd r8,r0,r10
or r7,r7,r6
blt cr6,79f
27: ld r0,8(r4)
@@ -129,35 +137,35 @@
28: ld r0,0(r4) /* 4+2n loads, 3+2n stores */
29: ldu r9,8(r4)
- sld r8,r0,r10
+ sLd r8,r0,r10
addi r3,r3,-8
blt cr6,5f
30: ld r0,8(r4)
- srd r12,r9,r11
- sld r6,r9,r10
+ sHd r12,r9,r11
+ sLd r6,r9,r10
31: ldu r9,16(r4)
or r12,r8,r12
- srd r7,r0,r11
- sld r8,r0,r10
+ sHd r7,r0,r11
+ sLd r8,r0,r10
addi r3,r3,16
beq cr6,78f
1: or r7,r7,r6
32: ld r0,8(r4)
76: std r12,8(r3)
-2: srd r12,r9,r11
- sld r6,r9,r10
+2: sHd r12,r9,r11
+ sLd r6,r9,r10
33: ldu r9,16(r4)
or r12,r8,r12
77: stdu r7,16(r3)
- srd r7,r0,r11
- sld r8,r0,r10
+ sHd r7,r0,r11
+ sLd r8,r0,r10
bdnz 1b
78: std r12,8(r3)
or r7,r7,r6
79: std r7,16(r3)
-5: srd r12,r9,r11
+5: sHd r12,r9,r11
or r12,r8,r12
80: std r12,24(r3)
bne 6f
@@ -165,23 +173,38 @@
blr
6: cmpwi cr1,r5,8
addi r3,r3,32
- sld r9,r9,r10
+ sLd r9,r9,r10
ble cr1,7f
34: ld r0,8(r4)
- srd r7,r0,r11
+ sHd r7,r0,r11
or r9,r7,r9
7:
bf cr7*4+1,1f
+#ifdef __BIG_ENDIAN__
rotldi r9,r9,32
+#endif
94: stw r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+ rotrdi r9,r9,32
+#endif
addi r3,r3,4
1: bf cr7*4+2,2f
+#ifdef __BIG_ENDIAN__
rotldi r9,r9,16
+#endif
95: sth r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+ rotrdi r9,r9,16
+#endif
addi r3,r3,2
2: bf cr7*4+3,3f
+#ifdef __BIG_ENDIAN__
rotldi r9,r9,8
+#endif
96: stb r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+ rotrdi r9,r9,8
+#endif
3: li r3,0
blr
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 02245ce..d7ddcee 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -36,7 +36,6 @@
#include "powernv.h"
#include "pci.h"
-static char *hub_diag = NULL;
static int ioda_eeh_nb_init = 0;
static int ioda_eeh_event(struct notifier_block *nb,
@@ -140,15 +139,6 @@
ioda_eeh_nb_init = 1;
}
- /* We needn't HUB diag-data on PHB3 */
- if (phb->type == PNV_PHB_IODA1 && !hub_diag) {
- hub_diag = (char *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
- if (!hub_diag) {
- pr_err("%s: Out of memory !\n", __func__);
- return -ENOMEM;
- }
- }
-
#ifdef CONFIG_DEBUG_FS
if (phb->dbgfs) {
debugfs_create_file("err_injct_outbound", 0600,
@@ -633,11 +623,10 @@
static void ioda_eeh_hub_diag(struct pci_controller *hose)
{
struct pnv_phb *phb = hose->private_data;
- struct OpalIoP7IOCErrorData *data;
+ struct OpalIoP7IOCErrorData *data = &phb->diag.hub_diag;
long rc;
- data = (struct OpalIoP7IOCErrorData *)ioda_eeh_hub_diag;
- rc = opal_pci_get_hub_diag_data(phb->hub_id, data, PAGE_SIZE);
+ rc = opal_pci_get_hub_diag_data(phb->hub_id, data, sizeof(*data));
if (rc != OPAL_SUCCESS) {
pr_warning("%s: Failed to get HUB#%llx diag-data (%ld)\n",
__func__, phb->hub_id, rc);
@@ -820,14 +809,15 @@
struct OpalIoPhbErrorCommon *common;
long rc;
- common = (struct OpalIoPhbErrorCommon *)phb->diag.blob;
- rc = opal_pci_get_phb_diag_data2(phb->opal_id, common, PAGE_SIZE);
+ rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+ PNV_PCI_DIAG_BUF_SIZE);
if (rc != OPAL_SUCCESS) {
pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
__func__, hose->global_number, rc);
return;
}
+ common = (struct OpalIoPhbErrorCommon *)phb->diag.blob;
switch (common->ioType) {
case OPAL_PHB_ERROR_DATA_TYPE_P7IOC:
ioda_eeh_p7ioc_phb_diag(hose, common);
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
index e7e59e4..79d83ca 100644
--- a/arch/powerpc/platforms/powernv/opal-lpc.c
+++ b/arch/powerpc/platforms/powernv/opal-lpc.c
@@ -24,25 +24,25 @@
static u8 opal_lpc_inb(unsigned long port)
{
int64_t rc;
- uint32_t data;
+ __be32 data;
if (opal_lpc_chip_id < 0 || port > 0xffff)
return 0xff;
rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 1);
- return rc ? 0xff : data;
+ return rc ? 0xff : be32_to_cpu(data);
}
static __le16 __opal_lpc_inw(unsigned long port)
{
int64_t rc;
- uint32_t data;
+ __be32 data;
if (opal_lpc_chip_id < 0 || port > 0xfffe)
return 0xffff;
if (port & 1)
return (__le16)opal_lpc_inb(port) << 8 | opal_lpc_inb(port + 1);
rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 2);
- return rc ? 0xffff : data;
+ return rc ? 0xffff : be32_to_cpu(data);
}
static u16 opal_lpc_inw(unsigned long port)
{
@@ -52,7 +52,7 @@
static __le32 __opal_lpc_inl(unsigned long port)
{
int64_t rc;
- uint32_t data;
+ __be32 data;
if (opal_lpc_chip_id < 0 || port > 0xfffc)
return 0xffffffff;
@@ -62,7 +62,7 @@
(__le32)opal_lpc_inb(port + 2) << 8 |
opal_lpc_inb(port + 3);
rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 4);
- return rc ? 0xffffffff : data;
+ return rc ? 0xffffffff : be32_to_cpu(data);
}
static u32 opal_lpc_inl(unsigned long port)
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 4d99a8f..4fbf276 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -96,9 +96,11 @@
{
struct opal_scom_map *m = map;
int64_t rc;
+ __be64 v;
reg = opal_scom_unmangle(reg);
- rc = opal_xscom_read(m->chip, m->addr + reg, (uint64_t *)__pa(value));
+ rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v));
+ *value = be64_to_cpu(v);
return opal_xscom_err_xlate(rc);
}
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 911c24e..1ed8d5f 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -172,11 +172,13 @@
} ioda;
};
- /* PHB status structure */
+ /* PHB and hub status structure */
union {
unsigned char blob[PNV_PCI_DIAG_BUF_SIZE];
struct OpalIoP7IOCPhbErrorData p7ioc;
+ struct OpalIoP7IOCErrorData hub_diag;
} diag;
+
};
extern struct pci_ops pnv_pci_ops;
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index e738007..c9fecf0 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -157,7 +157,7 @@
{
struct hvcall_ppp_data ppp_data;
struct device_node *root;
- const int *perf_level;
+ const __be32 *perf_level;
int rc;
rc = h_get_ppp(&ppp_data);
@@ -201,7 +201,7 @@
perf_level = of_get_property(root,
"ibm,partition-performance-parameters-level",
NULL);
- if (perf_level && (*perf_level >= 1)) {
+ if (perf_level && (be32_to_cpup(perf_level) >= 1)) {
seq_printf(m,
"physical_procs_allocated_to_virtualization=%d\n",
ppp_data.phys_platform_procs);
@@ -435,7 +435,7 @@
int partition_potential_processors;
int partition_active_processors;
struct device_node *rtas_node;
- const int *lrdrp = NULL;
+ const __be32 *lrdrp = NULL;
rtas_node = of_find_node_by_path("/rtas");
if (rtas_node)
@@ -444,7 +444,7 @@
if (lrdrp == NULL) {
partition_potential_processors = vdso_data->processorCount;
} else {
- partition_potential_processors = *(lrdrp + 4);
+ partition_potential_processors = be32_to_cpup(lrdrp + 4);
}
of_node_put(rtas_node);
@@ -654,7 +654,7 @@
const char *model = "";
const char *system_id = "";
const char *tmp;
- const unsigned int *lp_index_ptr;
+ const __be32 *lp_index_ptr;
unsigned int lp_index = 0;
seq_printf(m, "%s %s\n", MODULE_NAME, MODULE_VERS);
@@ -670,7 +670,7 @@
lp_index_ptr = of_get_property(rootdn, "ibm,partition-no",
NULL);
if (lp_index_ptr)
- lp_index = *lp_index_ptr;
+ lp_index = be32_to_cpup(lp_index_ptr);
of_node_put(rootdn);
}
seq_printf(m, "serial_number=%s\n", system_id);
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 6d2f0ab..0c882e8 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -130,7 +130,8 @@
{
struct device_node *dn;
struct pci_dn *pdn;
- const u32 *req_msi;
+ const __be32 *p;
+ u32 req_msi;
pdn = pci_get_pdn(pdev);
if (!pdn)
@@ -138,19 +139,20 @@
dn = pdn->node;
- req_msi = of_get_property(dn, prop_name, NULL);
- if (!req_msi) {
+ p = of_get_property(dn, prop_name, NULL);
+ if (!p) {
pr_debug("rtas_msi: No %s on %s\n", prop_name, dn->full_name);
return -ENOENT;
}
- if (*req_msi < nvec) {
+ req_msi = be32_to_cpup(p);
+ if (req_msi < nvec) {
pr_debug("rtas_msi: %s requests < %d MSIs\n", prop_name, nvec);
- if (*req_msi == 0) /* Be paranoid */
+ if (req_msi == 0) /* Be paranoid */
return -ENOSPC;
- return *req_msi;
+ return req_msi;
}
return 0;
@@ -171,7 +173,7 @@
static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total)
{
struct device_node *dn;
- const u32 *p;
+ const __be32 *p;
dn = of_node_get(pci_device_to_OF_node(dev));
while (dn) {
@@ -179,7 +181,7 @@
if (p) {
pr_debug("rtas_msi: found prop on dn %s\n",
dn->full_name);
- *total = *p;
+ *total = be32_to_cpup(p);
return dn;
}
@@ -232,13 +234,13 @@
static void *count_non_bridge_devices(struct device_node *dn, void *data)
{
struct msi_counts *counts = data;
- const u32 *p;
+ const __be32 *p;
u32 class;
pr_debug("rtas_msi: counting %s\n", dn->full_name);
p = of_get_property(dn, "class-code", NULL);
- class = p ? *p : 0;
+ class = p ? be32_to_cpup(p) : 0;
if ((class >> 8) != PCI_CLASS_BRIDGE_PCI)
counts->num_devices++;
@@ -249,7 +251,7 @@
static void *count_spare_msis(struct device_node *dn, void *data)
{
struct msi_counts *counts = data;
- const u32 *p;
+ const __be32 *p;
int req;
if (dn == counts->requestor)
@@ -260,11 +262,11 @@
req = 0;
p = of_get_property(dn, "ibm,req#msi", NULL);
if (p)
- req = *p;
+ req = be32_to_cpup(p);
p = of_get_property(dn, "ibm,req#msi-x", NULL);
if (p)
- req = max(req, (int)*p);
+ req = max(req, (int)be32_to_cpup(p));
}
if (req < counts->quota)
diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 7bfaf58..d7096f2 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -43,8 +43,8 @@
static DEFINE_SPINLOCK(nvram_lock);
struct err_log_info {
- int error_type;
- unsigned int seq_num;
+ __be32 error_type;
+ __be32 seq_num;
};
struct nvram_os_partition {
@@ -79,9 +79,9 @@
};
struct oops_log_info {
- u16 version;
- u16 report_length;
- u64 timestamp;
+ __be16 version;
+ __be16 report_length;
+ __be64 timestamp;
} __attribute__((packed));
static void oops_to_nvram(struct kmsg_dumper *dumper,
@@ -291,8 +291,8 @@
length = part->size;
}
- info.error_type = err_type;
- info.seq_num = error_log_cnt;
+ info.error_type = cpu_to_be32(err_type);
+ info.seq_num = cpu_to_be32(error_log_cnt);
tmp_index = part->index;
@@ -364,8 +364,8 @@
}
if (part->os_partition) {
- *error_log_cnt = info.seq_num;
- *err_type = info.error_type;
+ *error_log_cnt = be32_to_cpu(info.seq_num);
+ *err_type = be32_to_cpu(info.error_type);
}
return 0;
@@ -529,9 +529,9 @@
pr_err("nvram: logging uncompressed oops/panic report\n");
return -1;
}
- oops_hdr->version = OOPS_HDR_VERSION;
- oops_hdr->report_length = (u16) zipped_len;
- oops_hdr->timestamp = get_seconds();
+ oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+ oops_hdr->report_length = cpu_to_be16(zipped_len);
+ oops_hdr->timestamp = cpu_to_be64(get_seconds());
return 0;
}
@@ -574,9 +574,9 @@
clobbering_unread_rtas_event())
return -1;
- oops_hdr->version = OOPS_HDR_VERSION;
- oops_hdr->report_length = (u16) size;
- oops_hdr->timestamp = get_seconds();
+ oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+ oops_hdr->report_length = cpu_to_be16(size);
+ oops_hdr->timestamp = cpu_to_be64(get_seconds());
if (compressed)
err_type = ERR_TYPE_KERNEL_PANIC_GZ;
@@ -670,16 +670,16 @@
size_t length, hdr_size;
oops_hdr = (struct oops_log_info *)buff;
- if (oops_hdr->version < OOPS_HDR_VERSION) {
+ if (be16_to_cpu(oops_hdr->version) < OOPS_HDR_VERSION) {
/* Old format oops header had 2-byte record size */
hdr_size = sizeof(u16);
- length = oops_hdr->version;
+ length = be16_to_cpu(oops_hdr->version);
time->tv_sec = 0;
time->tv_nsec = 0;
} else {
hdr_size = sizeof(*oops_hdr);
- length = oops_hdr->report_length;
- time->tv_sec = oops_hdr->timestamp;
+ length = be16_to_cpu(oops_hdr->report_length);
+ time->tv_sec = be64_to_cpu(oops_hdr->timestamp);
time->tv_nsec = 0;
}
*buf = kmalloc(length, GFP_KERNEL);
@@ -889,13 +889,13 @@
kmsg_dump_get_buffer(dumper, false,
oops_data, oops_data_sz, &text_len);
err_type = ERR_TYPE_KERNEL_PANIC;
- oops_hdr->version = OOPS_HDR_VERSION;
- oops_hdr->report_length = (u16) text_len;
- oops_hdr->timestamp = get_seconds();
+ oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+ oops_hdr->report_length = cpu_to_be16(text_len);
+ oops_hdr->timestamp = cpu_to_be64(get_seconds());
}
(void) nvram_write_os_partition(&oops_log_partition, oops_buf,
- (int) (sizeof(*oops_hdr) + oops_hdr->report_length), err_type,
+ (int) (sizeof(*oops_hdr) + text_len), err_type,
++oops_count);
spin_unlock_irqrestore(&lock, flags);
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 5f93856..70670a2 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -113,7 +113,7 @@
{
struct device_node *dn, *pdn;
struct pci_bus *bus;
- const uint32_t *pcie_link_speed_stats;
+ const __be32 *pcie_link_speed_stats;
bus = bridge->bus;
@@ -122,7 +122,7 @@
return 0;
for (pdn = dn; pdn != NULL; pdn = of_get_next_parent(pdn)) {
- pcie_link_speed_stats = (const uint32_t *) of_get_property(pdn,
+ pcie_link_speed_stats = of_get_property(pdn,
"ibm,pcie-link-speed-stats", NULL);
if (pcie_link_speed_stats)
break;
@@ -135,7 +135,7 @@
return 0;
}
- switch (pcie_link_speed_stats[0]) {
+ switch (be32_to_cpup(pcie_link_speed_stats)) {
case 0x01:
bus->max_bus_speed = PCIE_SPEED_2_5GT;
break;
@@ -147,7 +147,7 @@
break;
}
- switch (pcie_link_speed_stats[1]) {
+ switch (be32_to_cpup(pcie_link_speed_stats)) {
case 0x01:
bus->cur_bus_speed = PCIE_SPEED_2_5GT;
break;
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 1e1a03d..e9f3125 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -135,7 +135,6 @@
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_UID16 if 32BIT
select HAVE_VIRT_CPU_ACCOUNTING
- select INIT_ALL_POSSIBLE
select KTIME_SCALAR if 32BIT
select MODULES_USE_ELF_RELA
select OLD_SIGACTION
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index ac9bed8..1607793 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -31,6 +31,7 @@
extern void smp_stop_cpu(void);
extern void smp_cpu_set_polarization(int cpu, int val);
extern int smp_cpu_get_polarization(int cpu);
+extern void smp_fill_possible_mask(void);
#else /* CONFIG_SMP */
@@ -50,6 +51,7 @@
static inline void smp_yield_cpu(int cpu) { }
static inline void smp_yield(void) { }
static inline void smp_stop_cpu(void) { }
+static inline void smp_fill_possible_mask(void) { }
#endif /* CONFIG_SMP */
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 4444875..0f3d44e 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -1023,6 +1023,7 @@
setup_vmcoreinfo();
setup_lowcore();
+ smp_fill_possible_mask();
cpu_init();
s390_init_cpu_topology();
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index dc4a534..9587047 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -721,18 +721,14 @@
return 0;
}
-static int __init setup_possible_cpus(char *s)
-{
- int max, cpu;
+static unsigned int setup_possible_cpus __initdata;
- if (kstrtoint(s, 0, &max) < 0)
- return 0;
- init_cpu_possible(cpumask_of(0));
- for (cpu = 1; cpu < max && cpu < nr_cpu_ids; cpu++)
- set_cpu_possible(cpu, true);
+static int __init _setup_possible_cpus(char *s)
+{
+ get_option(&s, &setup_possible_cpus);
return 0;
}
-early_param("possible_cpus", setup_possible_cpus);
+early_param("possible_cpus", _setup_possible_cpus);
#ifdef CONFIG_HOTPLUG_CPU
@@ -775,6 +771,17 @@
#endif /* CONFIG_HOTPLUG_CPU */
+void __init smp_fill_possible_mask(void)
+{
+ unsigned int possible, cpu;
+
+ possible = setup_possible_cpus;
+ if (!possible)
+ possible = MACHINE_IS_VM ? 64 : nr_cpu_ids;
+ for (cpu = 0; cpu < possible && cpu < nr_cpu_ids; cpu++)
+ set_cpu_possible(cpu, true);
+}
+
void __init smp_prepare_cpus(unsigned int max_cpus)
{
/* request the 0x1201 emergency signal external interrupt */
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 800f064..0696072 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -75,6 +75,7 @@
if (!zdev || zdev->state == ZPCI_FN_STATE_CONFIGURED)
break;
zdev->state = ZPCI_FN_STATE_CONFIGURED;
+ zdev->fh = ccdf->fh;
ret = zpci_enable_device(zdev);
if (ret)
break;
@@ -101,6 +102,7 @@
if (pdev)
pci_stop_and_remove_bus_device(pdev);
+ zdev->fh = ccdf->fh;
zpci_disable_device(zdev);
zdev->state = ZPCI_FN_STATE_STANDBY;
break;
diff --git a/arch/sh/kernel/sh_ksyms_32.c b/arch/sh/kernel/sh_ksyms_32.c
index 2a0a596..d77f2f6 100644
--- a/arch/sh/kernel/sh_ksyms_32.c
+++ b/arch/sh/kernel/sh_ksyms_32.c
@@ -20,6 +20,11 @@
EXPORT_SYMBOL(copy_page);
EXPORT_SYMBOL(__clear_user);
EXPORT_SYMBOL(empty_zero_page);
+#ifdef CONFIG_FLATMEM
+/* need in pfn_valid macro */
+EXPORT_SYMBOL(min_low_pfn);
+EXPORT_SYMBOL(max_low_pfn);
+#endif
#define DECLARE_EXPORT(name) \
extern void name(void);EXPORT_SYMBOL(name)
diff --git a/arch/sh/lib/Makefile b/arch/sh/lib/Makefile
index 7b95f29..3baff31 100644
--- a/arch/sh/lib/Makefile
+++ b/arch/sh/lib/Makefile
@@ -6,7 +6,7 @@
checksum.o strlen.o div64.o div64-generic.o
# Extracted from libgcc
-lib-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
+obj-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o \
udiv_qrnnd.o
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 8358dc1..0f9e945 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -619,7 +619,7 @@
}
#define pte_accessible pte_accessible
-static inline unsigned long pte_accessible(pte_t a)
+static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a)
{
return pte_val(a) & _PAGE_VALID;
}
@@ -847,7 +847,7 @@
* SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
* and SUN4V pte layout, so this inline test is fine.
*/
- if (likely(mm != &init_mm) && pte_accessible(orig))
+ if (likely(mm != &init_mm) && pte_accessible(mm, orig))
tlb_batch_add(mm, addr, ptep, orig, fullmm);
}
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index e562d3c..ad7e178 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -262,8 +262,8 @@
extern __must_check long strlen_user(const char __user *str);
extern __must_check long strnlen_user(const char __user *str, long n);
-#define __copy_to_user_inatomic ___copy_to_user
-#define __copy_from_user_inatomic ___copy_from_user
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
struct pt_regs;
extern unsigned long compute_effective_address(struct pt_regs *,
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 070ed14..76663b0 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -854,7 +854,7 @@
return 1;
#ifdef CONFIG_PCI
- if (dev->bus == &pci_bus_type)
+ if (dev_is_pci(dev))
return pci64_dma_supported(to_pci_dev(dev), device_mask);
#endif
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index 2096468..e7e215d 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -666,10 +666,9 @@
*/
int dma_supported(struct device *dev, u64 mask)
{
-#ifdef CONFIG_PCI
- if (dev->bus == &pci_bus_type)
+ if (dev_is_pci(dev))
return 1;
-#endif
+
return 0;
}
EXPORT_SYMBOL(dma_supported);
diff --git a/arch/sparc/kernel/kgdb_64.c b/arch/sparc/kernel/kgdb_64.c
index 60b19f5..b45fe3f 100644
--- a/arch/sparc/kernel/kgdb_64.c
+++ b/arch/sparc/kernel/kgdb_64.c
@@ -6,6 +6,7 @@
#include <linux/kgdb.h>
#include <linux/kdebug.h>
#include <linux/ftrace.h>
+#include <linux/context_tracking.h>
#include <asm/cacheflush.h>
#include <asm/kdebug.h>
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index b66a533..b085311 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -123,11 +123,12 @@
rmb();
set_cpu_online(cpuid, true);
- local_irq_enable();
/* idle thread is expected to have preempt disabled */
preempt_disable();
+ local_irq_enable();
+
cpu_startup_entry(CPUHP_ONLINE);
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e903c71..0952ecd 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -26,6 +26,7 @@
select HAVE_AOUT if X86_32
select HAVE_UNSTABLE_SCHED_CLOCK
select ARCH_SUPPORTS_NUMA_BALANCING
+ select ARCH_SUPPORTS_INT128 if X86_64
select ARCH_WANTS_PROT_NUMA_PROT_NONE
select HAVE_IDE
select HAVE_OPROFILE
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 3d19994..bbc8b12 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -452,9 +452,16 @@
}
#define pte_accessible pte_accessible
-static inline int pte_accessible(pte_t a)
+static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
{
- return pte_flags(a) & _PAGE_PRESENT;
+ if (pte_flags(a) & _PAGE_PRESENT)
+ return true;
+
+ if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) &&
+ mm_tlb_flush_pending(mm))
+ return true;
+
+ return false;
}
static inline int pte_hidden(pte_t pte)
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 8729723..c8b0519 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -8,6 +8,12 @@
DECLARE_PER_CPU(int, __preempt_count);
/*
+ * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such
+ * that a decrement hitting 0 means we can and should reschedule.
+ */
+#define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED)
+
+/*
* We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
* that think a non-zero value indicates we cannot preempt.
*/
@@ -74,6 +80,11 @@
__this_cpu_add_4(__preempt_count, -val);
}
+/*
+ * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule
+ * a decrement which hits zero means we have no preempt_count and should
+ * reschedule.
+ */
static __always_inline bool __preempt_count_dec_and_test(void)
{
GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index 34baa0e..3de54ef 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -4,6 +4,7 @@
#include <linux/pm.h>
#include <linux/percpu.h>
#include <linux/interrupt.h>
+#include <linux/math64.h>
#define TICK_SIZE (tick_nsec / 1000)
@@ -12,68 +13,26 @@
extern int no_timer_check;
-/* Accelerators for sched_clock()
- * convert from cycles(64bits) => nanoseconds (64bits)
- * basic equation:
- * ns = cycles / (freq / ns_per_sec)
- * ns = cycles * (ns_per_sec / freq)
- * ns = cycles * (10^9 / (cpu_khz * 10^3))
- * ns = cycles * (10^6 / cpu_khz)
+/*
+ * We use the full linear equation: f(x) = a + b*x, in order to allow
+ * a continuous function in the face of dynamic freq changes.
*
- * Then we use scaling math (suggested by george@mvista.com) to get:
- * ns = cycles * (10^6 * SC / cpu_khz) / SC
- * ns = cycles * cyc2ns_scale / SC
+ * Continuity means that when our frequency changes our slope (b); we want to
+ * ensure that: f(t) == f'(t), which gives: a + b*t == a' + b'*t.
*
- * And since SC is a constant power of two, we can convert the div
- * into a shift.
+ * Without an offset (a) the above would not be possible.
*
- * We can use khz divisor instead of mhz to keep a better precision, since
- * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
- * (mathieu.desnoyers@polymtl.ca)
- *
- * -johnstul@us.ibm.com "math is hard, lets go shopping!"
- *
- * In:
- *
- * ns = cycles * cyc2ns_scale / SC
- *
- * Although we may still have enough bits to store the value of ns,
- * in some cases, we may not have enough bits to store cycles * cyc2ns_scale,
- * leading to an incorrect result.
- *
- * To avoid this, we can decompose 'cycles' into quotient and remainder
- * of division by SC. Then,
- *
- * ns = (quot * SC + rem) * cyc2ns_scale / SC
- * = quot * cyc2ns_scale + (rem * cyc2ns_scale) / SC
- *
- * - sqazi@google.com
+ * See the comment near cycles_2_ns() for details on how we compute (b).
*/
+struct cyc2ns_data {
+ u32 cyc2ns_mul;
+ u32 cyc2ns_shift;
+ u64 cyc2ns_offset;
+ u32 __count;
+ /* u32 hole */
+}; /* 24 bytes -- do not grow */
-DECLARE_PER_CPU(unsigned long, cyc2ns);
-DECLARE_PER_CPU(unsigned long long, cyc2ns_offset);
-
-#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
-
-static inline unsigned long long __cycles_2_ns(unsigned long long cyc)
-{
- int cpu = smp_processor_id();
- unsigned long long ns = per_cpu(cyc2ns_offset, cpu);
- ns += mult_frac(cyc, per_cpu(cyc2ns, cpu),
- (1UL << CYC2NS_SCALE_FACTOR));
- return ns;
-}
-
-static inline unsigned long long cycles_2_ns(unsigned long long cyc)
-{
- unsigned long long ns;
- unsigned long flags;
-
- local_irq_save(flags);
- ns = __cycles_2_ns(cyc);
- local_irq_restore(flags);
-
- return ns;
-}
+extern struct cyc2ns_data *cyc2ns_read_begin(void);
+extern void cyc2ns_read_end(struct cyc2ns_data *);
#endif /* _ASM_X86_TIMER_H */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index bca023b..8bc79cd 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -487,7 +487,7 @@
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
if (!check_tsc_unstable())
- sched_clock_stable = 1;
+ set_sched_clock_stable();
}
#ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index ea04b34..1a439c0 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -93,7 +93,7 @@
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
if (!check_tsc_unstable())
- sched_clock_stable = 1;
+ set_sched_clock_stable();
}
/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8e13293..b886451 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1883,21 +1883,27 @@
void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
{
+ struct cyc2ns_data *data;
+
userpg->cap_user_time = 0;
userpg->cap_user_time_zero = 0;
userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
userpg->pmc_width = x86_pmu.cntval_bits;
- if (!sched_clock_stable)
+ if (!sched_clock_stable())
return;
+ data = cyc2ns_read_begin();
+
userpg->cap_user_time = 1;
- userpg->time_mult = this_cpu_read(cyc2ns);
- userpg->time_shift = CYC2NS_SCALE_FACTOR;
- userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
+ userpg->time_mult = data->cyc2ns_mul;
+ userpg->time_shift = data->cyc2ns_shift;
+ userpg->time_offset = data->cyc2ns_offset - now;
userpg->cap_user_time_zero = 1;
- userpg->time_zero = this_cpu_read(cyc2ns_offset);
+ userpg->time_zero = data->cyc2ns_offset;
+
+ cyc2ns_read_end(data);
}
/*
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index fd00bb2..c1a8618 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -262,11 +262,20 @@
__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
-#define EVENT_CONSTRAINT_END \
- EVENT_CONSTRAINT(0, 0, 0)
+/*
+ * We define the end marker as having a weight of -1
+ * to enable blacklisting of events using a counter bitmask
+ * of zero and thus a weight of zero.
+ * The end marker has a weight that cannot possibly be
+ * obtained from counting the bits in the bitmask.
+ */
+#define EVENT_CONSTRAINT_END { .weight = -1 }
+/*
+ * Check for end marker with weight == -1
+ */
#define for_each_event_constraint(e, c) \
- for ((e) = (c); (e)->weight; (e)++)
+ for ((e) = (c); (e)->weight != -1; (e)++)
/*
* Extra registers for specific events.
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 930e5d4..6377fb2 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -11,6 +11,7 @@
#include <linux/clocksource.h>
#include <linux/percpu.h>
#include <linux/timex.h>
+#include <linux/static_key.h>
#include <asm/hpet.h>
#include <asm/timer.h>
@@ -37,13 +38,244 @@
erroneous rdtsc usage on !cpu_has_tsc processors */
static int __read_mostly tsc_disabled = -1;
+static struct static_key __use_tsc = STATIC_KEY_INIT;
+
int tsc_clocksource_reliable;
+
+/*
+ * Use a ring-buffer like data structure, where a writer advances the head by
+ * writing a new data entry and a reader advances the tail when it observes a
+ * new entry.
+ *
+ * Writers are made to wait on readers until there's space to write a new
+ * entry.
+ *
+ * This means that we can always use an {offset, mul} pair to compute a ns
+ * value that is 'roughly' in the right direction, even if we're writing a new
+ * {offset, mul} pair during the clock read.
+ *
+ * The down-side is that we can no longer guarantee strict monotonicity anymore
+ * (assuming the TSC was that to begin with), because while we compute the
+ * intersection point of the two clock slopes and make sure the time is
+ * continuous at the point of switching; we can no longer guarantee a reader is
+ * strictly before or after the switch point.
+ *
+ * It does mean a reader no longer needs to disable IRQs in order to avoid
+ * CPU-Freq updates messing with his times, and similarly an NMI reader will
+ * no longer run the risk of hitting half-written state.
+ */
+
+struct cyc2ns {
+ struct cyc2ns_data data[2]; /* 0 + 2*24 = 48 */
+ struct cyc2ns_data *head; /* 48 + 8 = 56 */
+ struct cyc2ns_data *tail; /* 56 + 8 = 64 */
+}; /* exactly fits one cacheline */
+
+static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns);
+
+struct cyc2ns_data *cyc2ns_read_begin(void)
+{
+ struct cyc2ns_data *head;
+
+ preempt_disable();
+
+ head = this_cpu_read(cyc2ns.head);
+ /*
+ * Ensure we observe the entry when we observe the pointer to it.
+ * matches the wmb from cyc2ns_write_end().
+ */
+ smp_read_barrier_depends();
+ head->__count++;
+ barrier();
+
+ return head;
+}
+
+void cyc2ns_read_end(struct cyc2ns_data *head)
+{
+ barrier();
+ /*
+ * If we're the outer most nested read; update the tail pointer
+ * when we're done. This notifies possible pending writers
+ * that we've observed the head pointer and that the other
+ * entry is now free.
+ */
+ if (!--head->__count) {
+ /*
+ * x86-TSO does not reorder writes with older reads;
+ * therefore once this write becomes visible to another
+ * cpu, we must be finished reading the cyc2ns_data.
+ *
+ * matches with cyc2ns_write_begin().
+ */
+ this_cpu_write(cyc2ns.tail, head);
+ }
+ preempt_enable();
+}
+
+/*
+ * Begin writing a new @data entry for @cpu.
+ *
+ * Assumes some sort of write side lock; currently 'provided' by the assumption
+ * that cpufreq will call its notifiers sequentially.
+ */
+static struct cyc2ns_data *cyc2ns_write_begin(int cpu)
+{
+ struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
+ struct cyc2ns_data *data = c2n->data;
+
+ if (data == c2n->head)
+ data++;
+
+ /* XXX send an IPI to @cpu in order to guarantee a read? */
+
+ /*
+ * When we observe the tail write from cyc2ns_read_end(),
+ * the cpu must be done with that entry and its safe
+ * to start writing to it.
+ */
+ while (c2n->tail == data)
+ cpu_relax();
+
+ return data;
+}
+
+static void cyc2ns_write_end(int cpu, struct cyc2ns_data *data)
+{
+ struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
+
+ /*
+ * Ensure the @data writes are visible before we publish the
+ * entry. Matches the data-depencency in cyc2ns_read_begin().
+ */
+ smp_wmb();
+
+ ACCESS_ONCE(c2n->head) = data;
+}
+
+/*
+ * Accelerators for sched_clock()
+ * convert from cycles(64bits) => nanoseconds (64bits)
+ * basic equation:
+ * ns = cycles / (freq / ns_per_sec)
+ * ns = cycles * (ns_per_sec / freq)
+ * ns = cycles * (10^9 / (cpu_khz * 10^3))
+ * ns = cycles * (10^6 / cpu_khz)
+ *
+ * Then we use scaling math (suggested by george@mvista.com) to get:
+ * ns = cycles * (10^6 * SC / cpu_khz) / SC
+ * ns = cycles * cyc2ns_scale / SC
+ *
+ * And since SC is a constant power of two, we can convert the div
+ * into a shift.
+ *
+ * We can use khz divisor instead of mhz to keep a better precision, since
+ * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
+ * (mathieu.desnoyers@polymtl.ca)
+ *
+ * -johnstul@us.ibm.com "math is hard, lets go shopping!"
+ */
+
+#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
+
+static void cyc2ns_data_init(struct cyc2ns_data *data)
+{
+ data->cyc2ns_mul = 1U << CYC2NS_SCALE_FACTOR;
+ data->cyc2ns_shift = CYC2NS_SCALE_FACTOR;
+ data->cyc2ns_offset = 0;
+ data->__count = 0;
+}
+
+static void cyc2ns_init(int cpu)
+{
+ struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
+
+ cyc2ns_data_init(&c2n->data[0]);
+ cyc2ns_data_init(&c2n->data[1]);
+
+ c2n->head = c2n->data;
+ c2n->tail = c2n->data;
+}
+
+static inline unsigned long long cycles_2_ns(unsigned long long cyc)
+{
+ struct cyc2ns_data *data, *tail;
+ unsigned long long ns;
+
+ /*
+ * See cyc2ns_read_*() for details; replicated in order to avoid
+ * an extra few instructions that came with the abstraction.
+ * Notable, it allows us to only do the __count and tail update
+ * dance when its actually needed.
+ */
+
+ preempt_disable();
+ data = this_cpu_read(cyc2ns.head);
+ tail = this_cpu_read(cyc2ns.tail);
+
+ if (likely(data == tail)) {
+ ns = data->cyc2ns_offset;
+ ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);
+ } else {
+ data->__count++;
+
+ barrier();
+
+ ns = data->cyc2ns_offset;
+ ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);
+
+ barrier();
+
+ if (!--data->__count)
+ this_cpu_write(cyc2ns.tail, data);
+ }
+ preempt_enable();
+
+ return ns;
+}
+
+/* XXX surely we already have this someplace in the kernel?! */
+#define DIV_ROUND(n, d) (((n) + ((d) / 2)) / (d))
+
+static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
+{
+ unsigned long long tsc_now, ns_now;
+ struct cyc2ns_data *data;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ sched_clock_idle_sleep_event();
+
+ if (!cpu_khz)
+ goto done;
+
+ data = cyc2ns_write_begin(cpu);
+
+ rdtscll(tsc_now);
+ ns_now = cycles_2_ns(tsc_now);
+
+ /*
+ * Compute a new multiplier as per the above comment and ensure our
+ * time function is continuous; see the comment near struct
+ * cyc2ns_data.
+ */
+ data->cyc2ns_mul = DIV_ROUND(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR, cpu_khz);
+ data->cyc2ns_shift = CYC2NS_SCALE_FACTOR;
+ data->cyc2ns_offset = ns_now -
+ mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);
+
+ cyc2ns_write_end(cpu, data);
+
+done:
+ sched_clock_idle_wakeup_event(0);
+ local_irq_restore(flags);
+}
/*
* Scheduler clock - returns current time in nanosec units.
*/
u64 native_sched_clock(void)
{
- u64 this_offset;
+ u64 tsc_now;
/*
* Fall back to jiffies if there's no TSC available:
@@ -53,16 +285,16 @@
* very important for it to be as fast as the platform
* can achieve it. )
*/
- if (unlikely(tsc_disabled)) {
+ if (!static_key_false(&__use_tsc)) {
/* No locking but a rare wrong value is not a big deal: */
return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
}
/* read the Time Stamp Counter: */
- rdtscll(this_offset);
+ rdtscll(tsc_now);
/* return the value in ns */
- return __cycles_2_ns(this_offset);
+ return cycles_2_ns(tsc_now);
}
/* We need to define a real function for sched_clock, to override the
@@ -589,61 +821,11 @@
EXPORT_SYMBOL(recalibrate_cpu_khz);
-/* Accelerators for sched_clock()
- * convert from cycles(64bits) => nanoseconds (64bits)
- * basic equation:
- * ns = cycles / (freq / ns_per_sec)
- * ns = cycles * (ns_per_sec / freq)
- * ns = cycles * (10^9 / (cpu_khz * 10^3))
- * ns = cycles * (10^6 / cpu_khz)
- *
- * Then we use scaling math (suggested by george@mvista.com) to get:
- * ns = cycles * (10^6 * SC / cpu_khz) / SC
- * ns = cycles * cyc2ns_scale / SC
- *
- * And since SC is a constant power of two, we can convert the div
- * into a shift.
- *
- * We can use khz divisor instead of mhz to keep a better precision, since
- * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
- * (mathieu.desnoyers@polymtl.ca)
- *
- * -johnstul@us.ibm.com "math is hard, lets go shopping!"
- */
-
-DEFINE_PER_CPU(unsigned long, cyc2ns);
-DEFINE_PER_CPU(unsigned long long, cyc2ns_offset);
-
-static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
-{
- unsigned long long tsc_now, ns_now, *offset;
- unsigned long flags, *scale;
-
- local_irq_save(flags);
- sched_clock_idle_sleep_event();
-
- scale = &per_cpu(cyc2ns, cpu);
- offset = &per_cpu(cyc2ns_offset, cpu);
-
- rdtscll(tsc_now);
- ns_now = __cycles_2_ns(tsc_now);
-
- if (cpu_khz) {
- *scale = ((NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR) +
- cpu_khz / 2) / cpu_khz;
- *offset = ns_now - mult_frac(tsc_now, *scale,
- (1UL << CYC2NS_SCALE_FACTOR));
- }
-
- sched_clock_idle_wakeup_event(0);
- local_irq_restore(flags);
-}
-
static unsigned long long cyc2ns_suspend;
void tsc_save_sched_clock_state(void)
{
- if (!sched_clock_stable)
+ if (!sched_clock_stable())
return;
cyc2ns_suspend = sched_clock();
@@ -663,16 +845,26 @@
unsigned long flags;
int cpu;
- if (!sched_clock_stable)
+ if (!sched_clock_stable())
return;
local_irq_save(flags);
- __this_cpu_write(cyc2ns_offset, 0);
+ /*
+ * We're comming out of suspend, there's no concurrency yet; don't
+ * bother being nice about the RCU stuff, just write to both
+ * data fields.
+ */
+
+ this_cpu_write(cyc2ns.data[0].cyc2ns_offset, 0);
+ this_cpu_write(cyc2ns.data[1].cyc2ns_offset, 0);
+
offset = cyc2ns_suspend - sched_clock();
- for_each_possible_cpu(cpu)
- per_cpu(cyc2ns_offset, cpu) = offset;
+ for_each_possible_cpu(cpu) {
+ per_cpu(cyc2ns.data[0].cyc2ns_offset, cpu) = offset;
+ per_cpu(cyc2ns.data[1].cyc2ns_offset, cpu) = offset;
+ }
local_irq_restore(flags);
}
@@ -795,7 +987,7 @@
{
if (!tsc_unstable) {
tsc_unstable = 1;
- sched_clock_stable = 0;
+ clear_sched_clock_stable();
disable_sched_clock_irqtime();
pr_info("Marking TSC unstable due to %s\n", reason);
/* Change only the rating, when not registered */
@@ -995,14 +1187,18 @@
* speed as the bootup CPU. (cpufreq notifiers will fix this
* up if their speed diverges)
*/
- for_each_possible_cpu(cpu)
+ for_each_possible_cpu(cpu) {
+ cyc2ns_init(cpu);
set_cyc2ns_scale(cpu_khz, cpu);
+ }
if (tsc_disabled > 0)
return;
/* now allow native_sched_clock() to use rdtsc */
+
tsc_disabled = 0;
+ static_key_slow_inc(&__use_tsc);
if (!no_sched_irq_time)
enable_sched_clock_irqtime();
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index dec48bf..1673940c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1350,6 +1350,10 @@
return;
}
+ if (!kvm_vcpu_is_bsp(apic->vcpu))
+ value &= ~MSR_IA32_APICBASE_BSP;
+ vcpu->arch.apic_base = value;
+
/* update jump label if enable bit changes */
if ((vcpu->arch.apic_base ^ value) & MSR_IA32_APICBASE_ENABLE) {
if (value & MSR_IA32_APICBASE_ENABLE)
@@ -1359,10 +1363,6 @@
recalculate_apic_map(vcpu->kvm);
}
- if (!kvm_vcpu_is_bsp(apic->vcpu))
- value &= ~MSR_IA32_APICBASE_BSP;
-
- vcpu->arch.apic_base = value;
if ((old_value ^ value) & X2APIC_ENABLE) {
if (value & X2APIC_ENABLE) {
u32 id = kvm_apic_id(apic);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b2fe1c2..da7837e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8283,8 +8283,7 @@
vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
kvm_set_cr4(vcpu, vmcs12->host_cr4);
- if (nested_cpu_has_ept(vmcs12))
- nested_ept_uninit_mmu_context(vcpu);
+ nested_ept_uninit_mmu_context(vcpu);
kvm_set_cr3(vcpu, vmcs12->host_cr3);
kvm_mmu_reset_context(vcpu);
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index dd74e46..0596e8e 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -83,6 +83,12 @@
pte_t pte = gup_get_pte(ptep);
struct page *page;
+ /* Similar to the PMD case, NUMA hinting must take slow path */
+ if (pte_numa(pte)) {
+ pte_unmap(ptep);
+ return 0;
+ }
+
if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
pte_unmap(ptep);
return 0;
@@ -167,6 +173,13 @@
if (pmd_none(pmd) || pmd_trans_splitting(pmd))
return 0;
if (unlikely(pmd_large(pmd))) {
+ /*
+ * NUMA hinting faults need to be handled in the GUP
+ * slowpath for accounting purposes and so that they
+ * can be serialised against THP migration.
+ */
+ if (pmd_numa(pmd))
+ return 0;
if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))
return 0;
} else {
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index efe4d72..dfe605a 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -433,15 +433,49 @@
return;
}
+/*
+ * Not to be confused with cycles_2_ns() from tsc.c; this gives a relative
+ * number, not an absolute. It converts a duration in cycles to a duration in
+ * ns.
+ */
+static inline unsigned long long cycles_2_ns(unsigned long long cyc)
+{
+ struct cyc2ns_data *data = cyc2ns_read_begin();
+ unsigned long long ns;
+
+ ns = mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift);
+
+ cyc2ns_read_end(data);
+ return ns;
+}
+
+/*
+ * The reverse of the above; converts a duration in ns to a duration in cycles.
+ */
+static inline unsigned long long ns_2_cycles(unsigned long long ns)
+{
+ struct cyc2ns_data *data = cyc2ns_read_begin();
+ unsigned long long cyc;
+
+ cyc = (ns << data->cyc2ns_shift) / data->cyc2ns_mul;
+
+ cyc2ns_read_end(data);
+ return cyc;
+}
+
static inline unsigned long cycles_2_us(unsigned long long cyc)
{
- unsigned long long ns;
- unsigned long us;
- int cpu = smp_processor_id();
+ return cycles_2_ns(cyc) / NSEC_PER_USEC;
+}
- ns = (cyc * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR;
- us = ns / 1000;
- return us;
+static inline cycles_t sec_2_cycles(unsigned long sec)
+{
+ return ns_2_cycles(sec * NSEC_PER_SEC);
+}
+
+static inline unsigned long long usec_2_cycles(unsigned long usec)
+{
+ return ns_2_cycles(usec * NSEC_PER_USEC);
}
/*
@@ -668,16 +702,6 @@
bcp, try);
}
-static inline cycles_t sec_2_cycles(unsigned long sec)
-{
- unsigned long ns;
- cycles_t cyc;
-
- ns = sec * 1000000000;
- cyc = (ns << CYC2NS_SCALE_FACTOR)/(per_cpu(cyc2ns, smp_processor_id()));
- return cyc;
-}
-
/*
* Our retries are blocked by all destination sw ack resources being
* in use, and a timeout is pending. In that case hardware immediately
@@ -1327,16 +1351,6 @@
{
}
-static inline unsigned long long usec_2_cycles(unsigned long microsec)
-{
- unsigned long ns;
- unsigned long long cyc;
-
- ns = microsec * 1000;
- cyc = (ns << CYC2NS_SCALE_FACTOR)/(per_cpu(cyc2ns, smp_processor_id()));
- return cyc;
-}
-
/*
* Display the statistics thru /proc/sgi_uv/ptc_statistics
* 'data' points to the cpu number
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index aabfb83..96bc506 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -357,3 +357,5 @@
348 i386 process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev
349 i386 kcmp sys_kcmp
350 i386 finit_module sys_finit_module
+351 i386 sched_setattr sys_sched_setattr
+352 i386 sched_getattr sys_sched_getattr
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 38ae65d..a12bddc 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -320,6 +320,8 @@
311 64 process_vm_writev sys_process_vm_writev
312 common kcmp sys_kcmp
313 common finit_module sys_finit_module
+314 common sched_setattr sys_sched_setattr
+315 common sched_getattr sys_sched_getattr
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index ba6cf8e..b91ce75 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -335,9 +335,22 @@
void blk_mq_unregister_disk(struct gendisk *disk)
{
struct request_queue *q = disk->queue;
+ struct blk_mq_hw_ctx *hctx;
+ struct blk_mq_ctx *ctx;
+ int i, j;
+
+ queue_for_each_hw_ctx(q, hctx, i) {
+ hctx_for_each_ctx(hctx, ctx, j) {
+ kobject_del(&ctx->kobj);
+ kobject_put(&ctx->kobj);
+ }
+ kobject_del(&hctx->kobj);
+ kobject_put(&hctx->kobj);
+ }
kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
kobject_del(&q->mq_kobj);
+ kobject_put(&q->mq_kobj);
kobject_put(&disk_to_dev(disk)->kobj);
}
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 5d92485..4770de5 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -348,7 +348,6 @@
config ACPI_EXTLOG
tristate "Extended Error Log support"
depends on X86_MCE && X86_LOCAL_APIC
- select EFI
select UEFI_CPER
default n
help
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index 8711e37..3c2e4aa 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -207,7 +207,7 @@
goto end;
result = acpi_install_notify_handler(ACPI_HANDLE(&pdev->dev),
- ACPI_DEVICE_NOTIFY, acpi_ac_notify_handler, ac);
+ ACPI_ALL_NOTIFY, acpi_ac_notify_handler, ac);
if (result) {
power_supply_unregister(&ac->charger);
goto end;
@@ -255,7 +255,7 @@
return -EINVAL;
acpi_remove_notify_handler(ACPI_HANDLE(&pdev->dev),
- ACPI_DEVICE_NOTIFY, acpi_ac_notify_handler);
+ ACPI_ALL_NOTIFY, acpi_ac_notify_handler);
ac = platform_get_drvdata(pdev);
if (ac->charger.dev)
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 6745fe1..e603905 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -162,6 +162,7 @@
{ "80860F14", (unsigned long)&byt_sdio_dev_desc },
{ "80860F41", (unsigned long)&byt_i2c_dev_desc },
{ "INT33B2", },
+ { "INT33FC", },
{ "INT3430", (unsigned long)&lpt_dev_desc },
{ "INT3431", (unsigned long)&lpt_dev_desc },
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index 786294b..3650b21 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -2,7 +2,6 @@
bool "ACPI Platform Error Interface (APEI)"
select MISC_FILESYSTEMS
select PSTORE
- select EFI
select UEFI_CPER
depends on X86
help
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index 26311f2..cb1d557 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -942,6 +942,7 @@
static struct pstore_info erst_info = {
.owner = THIS_MODULE,
.name = "erst",
+ .flags = PSTORE_FLAGS_FRAGILE,
.open = erst_open_pstore,
.close = erst_close_pstore,
.read = erst_reader,
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index fbf1ace..5876a49 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -62,6 +62,7 @@
MODULE_DESCRIPTION("ACPI Battery Driver");
MODULE_LICENSE("GPL");
+static int battery_bix_broken_package;
static unsigned int cache_time = 1000;
module_param(cache_time, uint, 0644);
MODULE_PARM_DESC(cache_time, "cache time in milliseconds");
@@ -416,7 +417,12 @@
ACPI_EXCEPTION((AE_INFO, status, "Evaluating %s", name));
return -ENODEV;
}
- if (test_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags))
+
+ if (battery_bix_broken_package)
+ result = extract_package(battery, buffer.pointer,
+ extended_info_offsets + 1,
+ ARRAY_SIZE(extended_info_offsets) - 1);
+ else if (test_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags))
result = extract_package(battery, buffer.pointer,
extended_info_offsets,
ARRAY_SIZE(extended_info_offsets));
@@ -754,6 +760,17 @@
return 0;
}
+static struct dmi_system_id bat_dmi_table[] = {
+ {
+ .ident = "NEC LZ750/LS",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PC-LZ750LS"),
+ },
+ },
+ {},
+};
+
static int acpi_battery_add(struct acpi_device *device)
{
int result = 0;
@@ -846,6 +863,9 @@
{
if (acpi_disabled)
return;
+
+ if (dmi_check_system(bat_dmi_table))
+ battery_bix_broken_package = 1;
acpi_bus_register_driver(&acpi_battery_driver);
}
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index bba9b72..0710004 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -156,6 +156,16 @@
}
EXPORT_SYMBOL(acpi_bus_get_private_data);
+void acpi_bus_no_hotplug(acpi_handle handle)
+{
+ struct acpi_device *adev = NULL;
+
+ acpi_bus_get_device(handle, &adev);
+ if (adev)
+ adev->flags.no_hotplug = true;
+}
+EXPORT_SYMBOL_GPL(acpi_bus_no_hotplug);
+
static void acpi_print_osc_error(acpi_handle handle,
struct acpi_osc_context *context, char *error)
{
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 14f1e95..e3a92a6 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -427,6 +427,9 @@
.driver_data = board_ahci_yes_fbs }, /* 88se9128 */
{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9125),
.driver_data = board_ahci_yes_fbs }, /* 88se9125 */
+ { PCI_DEVICE_SUB(PCI_VENDOR_ID_MARVELL_EXT, 0x9178,
+ PCI_VENDOR_ID_MARVELL_EXT, 0x9170),
+ .driver_data = board_ahci_yes_fbs }, /* 88se9170 */
{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x917a),
.driver_data = board_ahci_yes_fbs }, /* 88se9172 */
{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9172),
@@ -1238,15 +1241,6 @@
if (rc)
return rc;
- /* AHCI controllers often implement SFF compatible interface.
- * Grab all PCI BARs just in case.
- */
- rc = pcim_iomap_regions_request_all(pdev, 1 << ahci_pci_bar, DRV_NAME);
- if (rc == -EBUSY)
- pcim_pin_device(pdev);
- if (rc)
- return rc;
-
if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
(pdev->device == 0x2652 || pdev->device == 0x2653)) {
u8 map;
@@ -1263,6 +1257,15 @@
}
}
+ /* AHCI controllers often implement SFF compatible interface.
+ * Grab all PCI BARs just in case.
+ */
+ rc = pcim_iomap_regions_request_all(pdev, 1 << ahci_pci_bar, DRV_NAME);
+ if (rc == -EBUSY)
+ pcim_pin_device(pdev);
+ if (rc)
+ return rc;
+
hpriv = devm_kzalloc(dev, sizeof(*hpriv), GFP_KERNEL);
if (!hpriv)
return -ENOMEM;
diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c
index ae2d73f..3e23e99 100644
--- a/drivers/ata/ahci_imx.c
+++ b/drivers/ata/ahci_imx.c
@@ -113,7 +113,7 @@
/*
* set PHY Paremeters, two steps to configure the GPR13,
* one write for rest of parameters, mask of first write
- * is 0x07fffffd, and the other one write for setting
+ * is 0x07ffffff, and the other one write for setting
* the mpll_clk_en.
*/
regmap_update_bits(imxpriv->gpr, 0x34, IMX6Q_GPR13_SATA_RX_EQ_VAL_MASK
@@ -124,6 +124,7 @@
| IMX6Q_GPR13_SATA_TX_ATTEN_MASK
| IMX6Q_GPR13_SATA_TX_BOOST_MASK
| IMX6Q_GPR13_SATA_TX_LVL_MASK
+ | IMX6Q_GPR13_SATA_MPLL_CLK_EN
| IMX6Q_GPR13_SATA_TX_EDGE_RATE
, IMX6Q_GPR13_SATA_RX_EQ_VAL_3_0_DB
| IMX6Q_GPR13_SATA_RX_LOS_LVL_SATA2M
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 75b9367..1393a58 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2149,9 +2149,16 @@
"failed to get NCQ Send/Recv Log Emask 0x%x\n",
err_mask);
} else {
+ u8 *cmds = dev->ncq_send_recv_cmds;
+
dev->flags |= ATA_DFLAG_NCQ_SEND_RECV;
- memcpy(dev->ncq_send_recv_cmds, ap->sector_buf,
- ATA_LOG_NCQ_SEND_RECV_SIZE);
+ memcpy(cmds, ap->sector_buf, ATA_LOG_NCQ_SEND_RECV_SIZE);
+
+ if (dev->horkage & ATA_HORKAGE_NO_NCQ_TRIM) {
+ ata_dev_dbg(dev, "disabling queued TRIM support\n");
+ cmds[ATA_LOG_NCQ_SEND_RECV_DSM_OFFSET] &=
+ ~ATA_LOG_NCQ_SEND_RECV_DSM_TRIM;
+ }
}
}
@@ -4156,6 +4163,9 @@
{ "ST3320[68]13AS", "SD1[5-9]", ATA_HORKAGE_NONCQ |
ATA_HORKAGE_FIRMWARE_WARN },
+ /* Seagate Momentus SpinPoint M8 seem to have FPMDA_AA issues */
+ { "ST1000LM024 HN-M101MBB", "2AR10001", ATA_HORKAGE_BROKEN_FPDMA_AA },
+
/* Blacklist entries taken from Silicon Image 3124/3132
Windows driver .inf file - also several Linux problem reports */
{ "HTS541060G9SA00", "MB3OC60D", ATA_HORKAGE_NONCQ, },
@@ -4202,6 +4212,10 @@
{ "PIONEER DVD-RW DVR-212D", NULL, ATA_HORKAGE_NOSETXFER },
{ "PIONEER DVD-RW DVR-216D", NULL, ATA_HORKAGE_NOSETXFER },
+ /* devices that don't properly handle queued TRIM commands */
+ { "Micron_M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, },
+ { "Crucial_CT???M500SSD1", NULL, ATA_HORKAGE_NO_NCQ_TRIM, },
+
/* End Marker */
{ }
};
@@ -6519,6 +6533,7 @@
{ "norst", .lflags = ATA_LFLAG_NO_HRST | ATA_LFLAG_NO_SRST },
{ "rstonce", .lflags = ATA_LFLAG_RST_ONCE },
{ "atapi_dmadir", .horkage_on = ATA_HORKAGE_ATAPI_DMADIR },
+ { "disable", .horkage_on = ATA_HORKAGE_DISABLE },
};
char *start = *cur, *p = *cur;
char *id, *val, *endp;
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index ab58556..377eb88 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -3872,6 +3872,27 @@
return;
}
+ /*
+ * XXX - UGLY HACK
+ *
+ * The block layer suspend/resume path is fundamentally broken due
+ * to freezable kthreads and workqueue and may deadlock if a block
+ * device gets removed while resume is in progress. I don't know
+ * what the solution is short of removing freezable kthreads and
+ * workqueues altogether.
+ *
+ * The following is an ugly hack to avoid kicking off device
+ * removal while freezer is active. This is a joke but does avoid
+ * this particular deadlock scenario.
+ *
+ * https://bugzilla.kernel.org/show_bug.cgi?id=62801
+ * http://marc.info/?l=linux-kernel&m=138695698516487
+ */
+#ifdef CONFIG_FREEZER
+ while (pm_freezing)
+ msleep(10);
+#endif
+
DPRINTK("ENTER\n");
mutex_lock(&ap->scsi_scan_mutex);
diff --git a/drivers/ata/sata_sis.c b/drivers/ata/sata_sis.c
index fe3ca09..1ad2f62 100644
--- a/drivers/ata/sata_sis.c
+++ b/drivers/ata/sata_sis.c
@@ -83,6 +83,10 @@
.id_table = sis_pci_tbl,
.probe = sis_init_one,
.remove = ata_pci_remove_one,
+#ifdef CONFIG_PM
+ .suspend = ata_pci_device_suspend,
+ .resume = ata_pci_device_resume,
+#endif
};
static struct scsi_host_template sis_sht = {
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index f370fc1..a2e69d2 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -1,4 +1,5 @@
#include <linux/module.h>
+
#include <linux/moduleparam.h>
#include <linux/sched.h>
#include <linux/fs.h>
@@ -65,7 +66,7 @@
NULL_Q_MQ = 2,
};
-static int submit_queues = 1;
+static int submit_queues;
module_param(submit_queues, int, S_IRUGO);
MODULE_PARM_DESC(submit_queues, "Number of submission queues");
@@ -101,9 +102,9 @@
module_param(hw_queue_depth, int, S_IRUGO);
MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 64");
-static bool use_per_node_hctx = true;
+static bool use_per_node_hctx = false;
module_param(use_per_node_hctx, bool, S_IRUGO);
-MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: true");
+MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false");
static void put_tag(struct nullb_queue *nq, unsigned int tag)
{
@@ -346,8 +347,37 @@
static struct blk_mq_hw_ctx *null_alloc_hctx(struct blk_mq_reg *reg, unsigned int hctx_index)
{
- return kzalloc_node(sizeof(struct blk_mq_hw_ctx), GFP_KERNEL,
- hctx_index);
+ int b_size = DIV_ROUND_UP(reg->nr_hw_queues, nr_online_nodes);
+ int tip = (reg->nr_hw_queues % nr_online_nodes);
+ int node = 0, i, n;
+
+ /*
+ * Split submit queues evenly wrt to the number of nodes. If uneven,
+ * fill the first buckets with one extra, until the rest is filled with
+ * no extra.
+ */
+ for (i = 0, n = 1; i < hctx_index; i++, n++) {
+ if (n % b_size == 0) {
+ n = 0;
+ node++;
+
+ tip--;
+ if (!tip)
+ b_size = reg->nr_hw_queues / nr_online_nodes;
+ }
+ }
+
+ /*
+ * A node might not be online, therefore map the relative node id to the
+ * real node id.
+ */
+ for_each_online_node(n) {
+ if (!node)
+ break;
+ node--;
+ }
+
+ return kzalloc_node(sizeof(struct blk_mq_hw_ctx), GFP_KERNEL, n);
}
static void null_free_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_index)
@@ -355,16 +385,24 @@
kfree(hctx);
}
+static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
+{
+ BUG_ON(!nullb);
+ BUG_ON(!nq);
+
+ init_waitqueue_head(&nq->wait);
+ nq->queue_depth = nullb->queue_depth;
+}
+
static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
unsigned int index)
{
struct nullb *nullb = data;
struct nullb_queue *nq = &nullb->queues[index];
- init_waitqueue_head(&nq->wait);
- nq->queue_depth = nullb->queue_depth;
- nullb->nr_queues++;
hctx->driver_data = nq;
+ null_init_queue(nullb, nq);
+ nullb->nr_queues++;
return 0;
}
@@ -417,13 +455,13 @@
nq->cmds = kzalloc(nq->queue_depth * sizeof(*cmd), GFP_KERNEL);
if (!nq->cmds)
- return 1;
+ return -ENOMEM;
tag_size = ALIGN(nq->queue_depth, BITS_PER_LONG) / BITS_PER_LONG;
nq->tag_map = kzalloc(tag_size * sizeof(unsigned long), GFP_KERNEL);
if (!nq->tag_map) {
kfree(nq->cmds);
- return 1;
+ return -ENOMEM;
}
for (i = 0; i < nq->queue_depth; i++) {
@@ -454,33 +492,37 @@
static int setup_queues(struct nullb *nullb)
{
- struct nullb_queue *nq;
- int i;
-
- nullb->queues = kzalloc(submit_queues * sizeof(*nq), GFP_KERNEL);
+ nullb->queues = kzalloc(submit_queues * sizeof(struct nullb_queue),
+ GFP_KERNEL);
if (!nullb->queues)
- return 1;
+ return -ENOMEM;
nullb->nr_queues = 0;
nullb->queue_depth = hw_queue_depth;
- if (queue_mode == NULL_Q_MQ)
- return 0;
+ return 0;
+}
+
+static int init_driver_queues(struct nullb *nullb)
+{
+ struct nullb_queue *nq;
+ int i, ret = 0;
for (i = 0; i < submit_queues; i++) {
nq = &nullb->queues[i];
- init_waitqueue_head(&nq->wait);
- nq->queue_depth = hw_queue_depth;
- if (setup_commands(nq))
- break;
+
+ null_init_queue(nullb, nq);
+
+ ret = setup_commands(nq);
+ if (ret)
+ goto err_queue;
nullb->nr_queues++;
}
- if (i == submit_queues)
- return 0;
-
+ return 0;
+err_queue:
cleanup_queues(nullb);
- return 1;
+ return ret;
}
static int null_add_dev(void)
@@ -518,11 +560,13 @@
} else if (queue_mode == NULL_Q_BIO) {
nullb->q = blk_alloc_queue_node(GFP_KERNEL, home_node);
blk_queue_make_request(nullb->q, null_queue_bio);
+ init_driver_queues(nullb);
} else {
nullb->q = blk_init_queue_node(null_request_fn, &nullb->lock, home_node);
blk_queue_prep_rq(nullb->q, null_rq_prep_fn);
if (nullb->q)
blk_queue_softirq_done(nullb->q, null_softirq_done_fn);
+ init_driver_queues(nullb);
}
if (!nullb->q)
@@ -579,7 +623,13 @@
}
#endif
- if (submit_queues > nr_cpu_ids)
+ if (queue_mode == NULL_Q_MQ && use_per_node_hctx) {
+ if (submit_queues < nr_online_nodes) {
+ pr_warn("null_blk: submit_queues param is set to %u.",
+ nr_online_nodes);
+ submit_queues = nr_online_nodes;
+ }
+ } else if (submit_queues > nr_cpu_ids)
submit_queues = nr_cpu_ids;
else if (!submit_queues)
submit_queues = 1;
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index 9199c93..eb6e1e0 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -5269,7 +5269,7 @@
}
}
-const char *skd_skmsg_state_to_str(enum skd_fit_msg_state state)
+static const char *skd_skmsg_state_to_str(enum skd_fit_msg_state state)
{
switch (state) {
case SKD_MSG_STATE_IDLE:
@@ -5281,7 +5281,7 @@
}
}
-const char *skd_skreq_state_to_str(enum skd_req_state state)
+static const char *skd_skreq_state_to_str(enum skd_req_state state)
{
switch (state) {
case SKD_REQ_STATE_IDLE:
diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c
index 6bfc1bb..dceb85f 100644
--- a/drivers/bluetooth/ath3k.c
+++ b/drivers/bluetooth/ath3k.c
@@ -87,6 +87,7 @@
{ USB_DEVICE(0x0CF3, 0xE004) },
{ USB_DEVICE(0x0CF3, 0xE005) },
{ USB_DEVICE(0x0930, 0x0219) },
+ { USB_DEVICE(0x0930, 0x0220) },
{ USB_DEVICE(0x0489, 0xe057) },
{ USB_DEVICE(0x13d3, 0x3393) },
{ USB_DEVICE(0x0489, 0xe04e) },
@@ -129,6 +130,7 @@
{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 },
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index c0ff34f..3980fd1 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -154,6 +154,7 @@
{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 },
diff --git a/drivers/char/tpm/tpm_ppi.c b/drivers/char/tpm/tpm_ppi.c
index 8e562dc..e1f3337 100644
--- a/drivers/char/tpm/tpm_ppi.c
+++ b/drivers/char/tpm/tpm_ppi.c
@@ -27,15 +27,18 @@
static acpi_status ppi_callback(acpi_handle handle, u32 level, void *context,
void **return_value)
{
- acpi_status status;
+ acpi_status status = AE_OK;
struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
- status = acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
- if (strstr(buffer.pointer, context) != NULL) {
- *return_value = handle;
+
+ if (ACPI_SUCCESS(acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer))) {
+ if (strstr(buffer.pointer, context) != NULL) {
+ *return_value = handle;
+ status = AE_CTRL_TERMINATE;
+ }
kfree(buffer.pointer);
- return AE_CTRL_TERMINATE;
}
- return AE_OK;
+
+ return status;
}
static inline void ppi_assign_params(union acpi_object params[4],
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index 8d3009e..5543b7d 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -87,7 +87,7 @@
return 0;
}
-static unsigned int _get_val(struct clk_divider *divider, u8 div)
+static unsigned int _get_val(struct clk_divider *divider, unsigned int div)
{
if (divider->flags & CLK_DIVIDER_ONE_BASED)
return div;
diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c
index 7be41e6..00a3abe 100644
--- a/drivers/clk/clk-s2mps11.c
+++ b/drivers/clk/clk-s2mps11.c
@@ -60,7 +60,7 @@
struct s2mps11_clk *s2mps11 = to_s2mps11_clk(hw);
int ret;
- ret = regmap_update_bits(s2mps11->iodev->regmap,
+ ret = regmap_update_bits(s2mps11->iodev->regmap_pmic,
S2MPS11_REG_RTC_CTRL,
s2mps11->mask, s2mps11->mask);
if (!ret)
@@ -74,7 +74,7 @@
struct s2mps11_clk *s2mps11 = to_s2mps11_clk(hw);
int ret;
- ret = regmap_update_bits(s2mps11->iodev->regmap, S2MPS11_REG_RTC_CTRL,
+ ret = regmap_update_bits(s2mps11->iodev->regmap_pmic, S2MPS11_REG_RTC_CTRL,
s2mps11->mask, ~s2mps11->mask);
if (!ret)
@@ -174,7 +174,7 @@
s2mps11_clk->hw.init = &s2mps11_clks_init[i];
s2mps11_clk->mask = 1 << i;
- ret = regmap_read(s2mps11_clk->iodev->regmap,
+ ret = regmap_read(s2mps11_clk->iodev->regmap_pmic,
S2MPS11_REG_RTC_CTRL, &val);
if (ret < 0)
goto err_reg;
diff --git a/drivers/clk/samsung/clk-exynos-audss.c b/drivers/clk/samsung/clk-exynos-audss.c
index 39b40aa..68e515d 100644
--- a/drivers/clk/samsung/clk-exynos-audss.c
+++ b/drivers/clk/samsung/clk-exynos-audss.c
@@ -26,17 +26,17 @@
#define ASS_CLK_DIV 0x4
#define ASS_CLK_GATE 0x8
+/* list of all parent clock list */
+static const char *mout_audss_p[] = { "fin_pll", "fout_epll" };
+static const char *mout_i2s_p[] = { "mout_audss", "cdclk0", "sclk_audio0" };
+
+#ifdef CONFIG_PM_SLEEP
static unsigned long reg_save[][2] = {
{ASS_CLK_SRC, 0},
{ASS_CLK_DIV, 0},
{ASS_CLK_GATE, 0},
};
-/* list of all parent clock list */
-static const char *mout_audss_p[] = { "fin_pll", "fout_epll" };
-static const char *mout_i2s_p[] = { "mout_audss", "cdclk0", "sclk_audio0" };
-
-#ifdef CONFIG_PM_SLEEP
static int exynos_audss_clk_suspend(void)
{
int i;
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index ad5ff50..1a7c1b9 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -39,7 +39,7 @@
#define SRC_TOP1 0xc214
#define SRC_CAM 0xc220
#define SRC_TV 0xc224
-#define SRC_MFC 0xcc28
+#define SRC_MFC 0xc228
#define SRC_G3D 0xc22c
#define E4210_SRC_IMAGE 0xc230
#define SRC_LCD0 0xc234
diff --git a/drivers/clk/samsung/clk-exynos5250.c b/drivers/clk/samsung/clk-exynos5250.c
index adf3234..e52359c 100644
--- a/drivers/clk/samsung/clk-exynos5250.c
+++ b/drivers/clk/samsung/clk-exynos5250.c
@@ -25,6 +25,7 @@
#define MPLL_LOCK 0x4000
#define MPLL_CON0 0x4100
#define SRC_CORE1 0x4204
+#define GATE_IP_ACP 0x8800
#define CPLL_LOCK 0x10020
#define EPLL_LOCK 0x10030
#define VPLL_LOCK 0x10040
@@ -75,7 +76,6 @@
#define SRC_CDREX 0x20200
#define PLL_DIV2_SEL 0x20a24
#define GATE_IP_DISP1 0x10928
-#define GATE_IP_ACP 0x10000
/* list of PLLs to be registered */
enum exynos5250_plls {
@@ -120,7 +120,8 @@
spi2, i2s1, i2s2, pcm1, pcm2, pwm, spdif, ac97, hsi2c0, hsi2c1, hsi2c2,
hsi2c3, chipid, sysreg, pmu, cmu_top, cmu_core, cmu_mem, tzpc0, tzpc1,
tzpc2, tzpc3, tzpc4, tzpc5, tzpc6, tzpc7, tzpc8, tzpc9, hdmi_cec, mct,
- wdt, rtc, tmu, fimd1, mie1, dsim0, dp, mixer, hdmi, g2d,
+ wdt, rtc, tmu, fimd1, mie1, dsim0, dp, mixer, hdmi, g2d, mdma0,
+ smmu_mdma0,
/* mux clocks */
mout_hdmi = 1024,
@@ -354,8 +355,8 @@
GATE(smmu_gscl2, "smmu_gscl2", "aclk266", GATE_IP_GSCL, 9, 0, 0),
GATE(smmu_gscl3, "smmu_gscl3", "aclk266", GATE_IP_GSCL, 10, 0, 0),
GATE(mfc, "mfc", "aclk333", GATE_IP_MFC, 0, 0, 0),
- GATE(smmu_mfcl, "smmu_mfcl", "aclk333", GATE_IP_MFC, 1, 0, 0),
- GATE(smmu_mfcr, "smmu_mfcr", "aclk333", GATE_IP_MFC, 2, 0, 0),
+ GATE(smmu_mfcl, "smmu_mfcl", "aclk333", GATE_IP_MFC, 2, 0, 0),
+ GATE(smmu_mfcr, "smmu_mfcr", "aclk333", GATE_IP_MFC, 1, 0, 0),
GATE(rotator, "rotator", "aclk266", GATE_IP_GEN, 1, 0, 0),
GATE(jpeg, "jpeg", "aclk166", GATE_IP_GEN, 2, 0, 0),
GATE(mdma1, "mdma1", "aclk266", GATE_IP_GEN, 4, 0, 0),
@@ -406,7 +407,8 @@
GATE(hsi2c2, "hsi2c2", "aclk66", GATE_IP_PERIC, 30, 0, 0),
GATE(hsi2c3, "hsi2c3", "aclk66", GATE_IP_PERIC, 31, 0, 0),
GATE(chipid, "chipid", "aclk66", GATE_IP_PERIS, 0, 0, 0),
- GATE(sysreg, "sysreg", "aclk66", GATE_IP_PERIS, 1, 0, 0),
+ GATE(sysreg, "sysreg", "aclk66",
+ GATE_IP_PERIS, 1, CLK_IGNORE_UNUSED, 0),
GATE(pmu, "pmu", "aclk66", GATE_IP_PERIS, 2, CLK_IGNORE_UNUSED, 0),
GATE(tzpc0, "tzpc0", "aclk66", GATE_IP_PERIS, 6, 0, 0),
GATE(tzpc1, "tzpc1", "aclk66", GATE_IP_PERIS, 7, 0, 0),
@@ -492,6 +494,8 @@
GATE(mixer, "mixer", "mout_aclk200_disp1", GATE_IP_DISP1, 5, 0, 0),
GATE(hdmi, "hdmi", "mout_aclk200_disp1", GATE_IP_DISP1, 6, 0, 0),
GATE(g2d, "g2d", "aclk200", GATE_IP_ACP, 3, 0, 0),
+ GATE(mdma0, "mdma0", "aclk266", GATE_IP_ACP, 1, 0, 0),
+ GATE(smmu_mdma0, "smmu_mdma0", "aclk266", GATE_IP_ACP, 5, 0, 0),
};
static struct samsung_pll_rate_table vpll_24mhz_tbl[] __initdata = {
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 5c07a56..634c4d6 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -75,6 +75,7 @@
config CLKSRC_EFM32
bool "Clocksource for Energy Micro's EFM32 SoCs" if !ARCH_EFM32
depends on OF && ARM && (ARCH_EFM32 || COMPILE_TEST)
+ select CLKSRC_MMIO
default ARCH_EFM32
help
Support to use the timers of EFM32 SoCs as clock source and clock
diff --git a/drivers/clocksource/clksrc-of.c b/drivers/clocksource/clksrc-of.c
index 35639cf4..b9ddd9e 100644
--- a/drivers/clocksource/clksrc-of.c
+++ b/drivers/clocksource/clksrc-of.c
@@ -35,6 +35,5 @@
init_func = match->data;
init_func(np);
- of_node_put(np);
}
}
diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c
index 45ba8ae..2a2ea27 100644
--- a/drivers/clocksource/dw_apb_timer_of.c
+++ b/drivers/clocksource/dw_apb_timer_of.c
@@ -108,12 +108,11 @@
static u64 read_sched_clock(void)
{
- return __raw_readl(sched_io_base);
+ return ~__raw_readl(sched_io_base);
}
static const struct of_device_id sptimer_ids[] __initconst = {
{ .compatible = "picochip,pc3x2-rtc" },
- { .compatible = "snps,dw-apb-timer-sp" },
{ /* Sentinel */ },
};
@@ -151,4 +150,6 @@
num_called++;
}
CLOCKSOURCE_OF_DECLARE(pc3x2_timer, "picochip,pc3x2-timer", dw_apb_timer_init);
-CLOCKSOURCE_OF_DECLARE(apb_timer, "snps,dw-apb-timer-osc", dw_apb_timer_init);
+CLOCKSOURCE_OF_DECLARE(apb_timer_osc, "snps,dw-apb-timer-osc", dw_apb_timer_init);
+CLOCKSOURCE_OF_DECLARE(apb_timer_sp, "snps,dw-apb-timer-sp", dw_apb_timer_init);
+CLOCKSOURCE_OF_DECLARE(apb_timer, "snps,dw-apb-timer", dw_apb_timer_init);
diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c
index 2fb4695..a4f6119 100644
--- a/drivers/clocksource/sun4i_timer.c
+++ b/drivers/clocksource/sun4i_timer.c
@@ -179,6 +179,9 @@
writel(TIMER_CTL_CLK_SRC(TIMER_CTL_CLK_SRC_OSC24M),
timer_base + TIMER_CTL_REG(0));
+ /* Make sure timer is stopped before playing with interrupts */
+ sun4i_clkevt_time_stop(0);
+
ret = setup_irq(irq, &sun4i_timer_irq);
if (ret)
pr_warn("failed to setup irq %d\n", irq);
diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c
index d8e47e5..4e7f680 100644
--- a/drivers/clocksource/time-armada-370-xp.c
+++ b/drivers/clocksource/time-armada-370-xp.c
@@ -256,11 +256,6 @@
ticks_per_jiffy = (timer_clk + HZ / 2) / HZ;
/*
- * Set scale and timer for sched_clock.
- */
- sched_clock_register(armada_370_xp_read_sched_clock, 32, timer_clk);
-
- /*
* Setup free-running clocksource timer (interrupts
* disabled).
*/
@@ -270,6 +265,11 @@
timer_ctrl_clrset(0, TIMER0_EN | TIMER0_RELOAD_EN |
TIMER0_DIV(TIMER_DIVIDER_SHIFT));
+ /*
+ * Set scale and timer for sched_clock.
+ */
+ sched_clock_register(armada_370_xp_read_sched_clock, 32, timer_clk);
+
clocksource_mmio_init(timer_base + TIMER0_VAL_OFF,
"armada_370_xp_clocksource",
timer_clk, 300, 32, clocksource_mmio_readl_down);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 02d534d..8d19f7c 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -828,14 +828,17 @@
int ret = 0;
memcpy(&new_policy, policy, sizeof(*policy));
+
+ /* Use the default policy if its valid. */
+ if (cpufreq_driver->setpolicy)
+ cpufreq_parse_governor(policy->governor->name,
+ &new_policy.policy, NULL);
+
/* assure that the starting sequence is run in cpufreq_set_policy */
policy->governor = NULL;
/* set default policy */
ret = cpufreq_set_policy(policy, &new_policy);
- policy->user_policy.policy = policy->policy;
- policy->user_policy.governor = policy->governor;
-
if (ret) {
pr_debug("setting policy failed\n");
if (cpufreq_driver->exit)
@@ -845,8 +848,7 @@
#ifdef CONFIG_HOTPLUG_CPU
static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
- unsigned int cpu, struct device *dev,
- bool frozen)
+ unsigned int cpu, struct device *dev)
{
int ret = 0;
unsigned long flags;
@@ -877,11 +879,7 @@
}
}
- /* Don't touch sysfs links during light-weight init */
- if (!frozen)
- ret = sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");
-
- return ret;
+ return sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");
}
#endif
@@ -926,6 +924,27 @@
return NULL;
}
+static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy)
+{
+ struct kobject *kobj;
+ struct completion *cmp;
+
+ down_read(&policy->rwsem);
+ kobj = &policy->kobj;
+ cmp = &policy->kobj_unregister;
+ up_read(&policy->rwsem);
+ kobject_put(kobj);
+
+ /*
+ * We need to make sure that the underlying kobj is
+ * actually not referenced anymore by anybody before we
+ * proceed with unloading.
+ */
+ pr_debug("waiting for dropping of refcount\n");
+ wait_for_completion(cmp);
+ pr_debug("wait complete\n");
+}
+
static void cpufreq_policy_free(struct cpufreq_policy *policy)
{
free_cpumask_var(policy->related_cpus);
@@ -986,7 +1005,7 @@
list_for_each_entry(tpolicy, &cpufreq_policy_list, policy_list) {
if (cpumask_test_cpu(cpu, tpolicy->related_cpus)) {
read_unlock_irqrestore(&cpufreq_driver_lock, flags);
- ret = cpufreq_add_policy_cpu(tpolicy, cpu, dev, frozen);
+ ret = cpufreq_add_policy_cpu(tpolicy, cpu, dev);
up_read(&cpufreq_rwsem);
return ret;
}
@@ -994,15 +1013,17 @@
read_unlock_irqrestore(&cpufreq_driver_lock, flags);
#endif
- if (frozen)
- /* Restore the saved policy when doing light-weight init */
- policy = cpufreq_policy_restore(cpu);
- else
+ /*
+ * Restore the saved policy when doing light-weight init and fall back
+ * to the full init if that fails.
+ */
+ policy = frozen ? cpufreq_policy_restore(cpu) : NULL;
+ if (!policy) {
+ frozen = false;
policy = cpufreq_policy_alloc();
-
- if (!policy)
- goto nomem_out;
-
+ if (!policy)
+ goto nomem_out;
+ }
/*
* In the resume path, since we restore a saved policy, the assignment
@@ -1047,8 +1068,10 @@
*/
cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
- policy->user_policy.min = policy->min;
- policy->user_policy.max = policy->max;
+ if (!frozen) {
+ policy->user_policy.min = policy->min;
+ policy->user_policy.max = policy->max;
+ }
blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
CPUFREQ_START, policy);
@@ -1079,6 +1102,11 @@
cpufreq_init_policy(policy);
+ if (!frozen) {
+ policy->user_policy.policy = policy->policy;
+ policy->user_policy.governor = policy->governor;
+ }
+
kobject_uevent(&policy->kobj, KOBJ_ADD);
up_read(&cpufreq_rwsem);
@@ -1096,7 +1124,13 @@
if (cpufreq_driver->exit)
cpufreq_driver->exit(policy);
err_set_policy_cpu:
+ if (frozen) {
+ /* Do not leave stale fallback data behind. */
+ per_cpu(cpufreq_cpu_data_fallback, cpu) = NULL;
+ cpufreq_policy_put_kobj(policy);
+ }
cpufreq_policy_free(policy);
+
nomem_out:
up_read(&cpufreq_rwsem);
@@ -1118,7 +1152,7 @@
}
static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy,
- unsigned int old_cpu, bool frozen)
+ unsigned int old_cpu)
{
struct device *cpu_dev;
int ret;
@@ -1126,10 +1160,6 @@
/* first sibling now owns the new sysfs dir */
cpu_dev = get_cpu_device(cpumask_any_but(policy->cpus, old_cpu));
- /* Don't touch sysfs files during light-weight tear-down */
- if (frozen)
- return cpu_dev->id;
-
sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
ret = kobject_move(&policy->kobj, &cpu_dev->kobj);
if (ret) {
@@ -1196,7 +1226,7 @@
if (!frozen)
sysfs_remove_link(&dev->kobj, "cpufreq");
} else if (cpus > 1) {
- new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu, frozen);
+ new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu);
if (new_cpu >= 0) {
update_policy_cpu(policy, new_cpu);
@@ -1218,8 +1248,6 @@
int ret;
unsigned long flags;
struct cpufreq_policy *policy;
- struct kobject *kobj;
- struct completion *cmp;
read_lock_irqsave(&cpufreq_driver_lock, flags);
policy = per_cpu(cpufreq_cpu_data, cpu);
@@ -1249,22 +1277,8 @@
}
}
- if (!frozen) {
- down_read(&policy->rwsem);
- kobj = &policy->kobj;
- cmp = &policy->kobj_unregister;
- up_read(&policy->rwsem);
- kobject_put(kobj);
-
- /*
- * We need to make sure that the underlying kobj is
- * actually not referenced anymore by anybody before we
- * proceed with unloading.
- */
- pr_debug("waiting for dropping of refcount\n");
- wait_for_completion(cmp);
- pr_debug("wait complete\n");
- }
+ if (!frozen)
+ cpufreq_policy_put_kobj(policy);
/*
* Perform the ->exit() even during light-weight tear-down,
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 5f1cbae..d51f17ed 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -581,7 +581,8 @@
}
#define ICPU(model, policy) \
- { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&policy }
+ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF,\
+ (unsigned long)&policy }
static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
ICPU(0x2a, core_params),
@@ -614,6 +615,11 @@
cpu = all_cpu_data[cpunum];
intel_pstate_get_cpu_pstates(cpu);
+ if (!cpu->pstate.current_pstate) {
+ all_cpu_data[cpunum] = NULL;
+ kfree(cpu);
+ return -ENODATA;
+ }
cpu->cpu = cpunum;
diff --git a/drivers/cpuidle/cpuidle-calxeda.c b/drivers/cpuidle/cpuidle-calxeda.c
index 3679563..6e51114 100644
--- a/drivers/cpuidle/cpuidle-calxeda.c
+++ b/drivers/cpuidle/cpuidle-calxeda.c
@@ -65,7 +65,7 @@
.state_count = 2,
};
-static int __init calxeda_cpuidle_probe(struct platform_device *pdev)
+static int calxeda_cpuidle_probe(struct platform_device *pdev)
{
return cpuidle_register(&calxeda_idle_driver, NULL);
}
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 9dd6e01..f757a0f 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -1410,14 +1410,12 @@
static int __init ixp_module_init(void)
{
int num = ARRAY_SIZE(ixp4xx_algos);
- int i, err ;
+ int i, err;
pdev = platform_device_register_full(&ixp_dev_info);
if (IS_ERR(pdev))
return PTR_ERR(pdev);
- dev = &pdev->dev;
-
spin_lock_init(&desc_lock);
spin_lock_init(&emerg_lock);
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 446687c..c823daa 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -62,6 +62,7 @@
tristate "Intel I/OAT DMA support"
depends on PCI && X86
select DMA_ENGINE
+ select DMA_ENGINE_RAID
select DCA
help
Enable support for the Intel(R) I/OAT DMA engine present
@@ -112,6 +113,7 @@
bool "Marvell XOR engine support"
depends on PLAT_ORION
select DMA_ENGINE
+ select DMA_ENGINE_RAID
select ASYNC_TX_ENABLE_CHANNEL_SWITCH
---help---
Enable support for the Marvell XOR engine.
@@ -187,6 +189,7 @@
tristate "AMCC PPC440SPe ADMA support"
depends on 440SPe || 440SP
select DMA_ENGINE
+ select DMA_ENGINE_RAID
select ARCH_HAS_ASYNC_TX_FIND_CHANNEL
select ASYNC_TX_ENABLE_CHANNEL_SWITCH
help
@@ -352,6 +355,7 @@
bool "Network: TCP receive copy offload"
depends on DMA_ENGINE && NET
default (INTEL_IOATDMA || FSL_DMA)
+ depends on BROKEN
help
This enables the use of DMA engines in the network stack to
offload receive copy-to-user operations, freeing CPU cycles.
@@ -377,4 +381,7 @@
Simple DMA test client. Say N unless you're debugging a
DMA Device driver.
+config DMA_ENGINE_RAID
+ bool
+
endif
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index f31d647..2787aba 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -347,10 +347,6 @@
{
return &chan->dev->device;
}
-static struct device *chan2parent(struct dma_chan *chan)
-{
- return chan->dev->device.parent;
-}
#if defined(VERBOSE_DEBUG)
static void vdbg_dump_regs(struct at_dma_chan *atchan)
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index ea806bd..ef63b90 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -912,7 +912,7 @@
#define __UNMAP_POOL(x) { .size = x, .name = "dmaengine-unmap-" __stringify(x) }
static struct dmaengine_unmap_pool unmap_pool[] = {
__UNMAP_POOL(2),
- #if IS_ENABLED(CONFIG_ASYNC_TX_DMA)
+ #if IS_ENABLED(CONFIG_DMA_ENGINE_RAID)
__UNMAP_POOL(16),
__UNMAP_POOL(128),
__UNMAP_POOL(256),
@@ -1054,7 +1054,7 @@
dma_cookie_t cookie;
unsigned long flags;
- unmap = dmaengine_get_unmap_data(dev->dev, 2, GFP_NOIO);
+ unmap = dmaengine_get_unmap_data(dev->dev, 2, GFP_NOWAIT);
if (!unmap)
return -ENOMEM;
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 20f9a3a..9dfcaf5c 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -539,9 +539,9 @@
um->len = params->buf_size;
for (i = 0; i < src_cnt; i++) {
- unsigned long buf = (unsigned long) thread->srcs[i];
+ void *buf = thread->srcs[i];
struct page *pg = virt_to_page(buf);
- unsigned pg_off = buf & ~PAGE_MASK;
+ unsigned pg_off = (unsigned long) buf & ~PAGE_MASK;
um->addr[i] = dma_map_page(dev->dev, pg, pg_off,
um->len, DMA_TO_DEVICE);
@@ -559,9 +559,9 @@
/* map with DMA_BIDIRECTIONAL to force writeback/invalidate */
dsts = &um->addr[src_cnt];
for (i = 0; i < dst_cnt; i++) {
- unsigned long buf = (unsigned long) thread->dsts[i];
+ void *buf = thread->dsts[i];
struct page *pg = virt_to_page(buf);
- unsigned pg_off = buf & ~PAGE_MASK;
+ unsigned pg_off = (unsigned long) buf & ~PAGE_MASK;
dsts[i] = dma_map_page(dev->dev, pg, pg_off, um->len,
DMA_BIDIRECTIONAL);
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index 7086a16..f157c6f 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -86,11 +86,6 @@
hw->count = CPU_TO_DMA(chan, count, 32);
}
-static u32 get_desc_cnt(struct fsldma_chan *chan, struct fsl_desc_sw *desc)
-{
- return DMA_TO_CPU(chan, desc->hw.count, 32);
-}
-
static void set_desc_src(struct fsldma_chan *chan,
struct fsl_dma_ld_hw *hw, dma_addr_t src)
{
@@ -101,16 +96,6 @@
hw->src_addr = CPU_TO_DMA(chan, snoop_bits | src, 64);
}
-static dma_addr_t get_desc_src(struct fsldma_chan *chan,
- struct fsl_desc_sw *desc)
-{
- u64 snoop_bits;
-
- snoop_bits = ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX)
- ? ((u64)FSL_DMA_SATR_SREADTYPE_SNOOP_READ << 32) : 0;
- return DMA_TO_CPU(chan, desc->hw.src_addr, 64) & ~snoop_bits;
-}
-
static void set_desc_dst(struct fsldma_chan *chan,
struct fsl_dma_ld_hw *hw, dma_addr_t dst)
{
@@ -121,16 +106,6 @@
hw->dst_addr = CPU_TO_DMA(chan, snoop_bits | dst, 64);
}
-static dma_addr_t get_desc_dst(struct fsldma_chan *chan,
- struct fsl_desc_sw *desc)
-{
- u64 snoop_bits;
-
- snoop_bits = ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX)
- ? ((u64)FSL_DMA_DATR_DWRITETYPE_SNOOP_WRITE << 32) : 0;
- return DMA_TO_CPU(chan, desc->hw.dst_addr, 64) & ~snoop_bits;
-}
-
static void set_desc_next(struct fsldma_chan *chan,
struct fsl_dma_ld_hw *hw, dma_addr_t next)
{
@@ -408,7 +383,7 @@
struct fsl_desc_sw *desc = tx_to_fsl_desc(tx);
struct fsl_desc_sw *child;
unsigned long flags;
- dma_cookie_t cookie;
+ dma_cookie_t cookie = -EINVAL;
spin_lock_irqsave(&chan->desc_lock, flags);
@@ -854,10 +829,6 @@
struct fsl_desc_sw *desc)
{
struct dma_async_tx_descriptor *txd = &desc->async_tx;
- struct device *dev = chan->common.device->dev;
- dma_addr_t src = get_desc_src(chan, desc);
- dma_addr_t dst = get_desc_dst(chan, desc);
- u32 len = get_desc_cnt(chan, desc);
/* Run the link descriptor callback function */
if (txd->callback) {
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 1a49c7776..8752918 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -817,7 +817,15 @@
}
dma_src = dma_map_single(dev, src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
+ if (dma_mapping_error(dev, dma_src)) {
+ dev_err(dev, "mapping src buffer failed\n");
+ goto free_resources;
+ }
dma_dest = dma_map_single(dev, dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
+ if (dma_mapping_error(dev, dma_dest)) {
+ dev_err(dev, "mapping dest buffer failed\n");
+ goto unmap_src;
+ }
flags = DMA_PREP_INTERRUPT;
tx = device->common.device_prep_dma_memcpy(dma_chan, dma_dest, dma_src,
IOAT_TEST_SIZE, flags);
@@ -855,8 +863,9 @@
}
unmap_dma:
- dma_unmap_single(dev, dma_src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
dma_unmap_single(dev, dma_dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
+unmap_src:
+ dma_unmap_single(dev, dma_src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
free_resources:
dma->device_free_chan_resources(dma_chan);
out:
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 7807f0e..53fb0c8 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -54,12 +54,6 @@
hw_desc->desc_command = (1 << 31);
}
-static u32 mv_desc_get_dest_addr(struct mv_xor_desc_slot *desc)
-{
- struct mv_xor_desc *hw_desc = desc->hw_desc;
- return hw_desc->phy_dest_addr;
-}
-
static void mv_desc_set_byte_count(struct mv_xor_desc_slot *desc,
u32 byte_count)
{
@@ -787,7 +781,6 @@
/*
* Perform a transaction to verify the HW works.
*/
-#define MV_XOR_TEST_SIZE 2000
static int mv_xor_memcpy_self_test(struct mv_xor_chan *mv_chan)
{
@@ -797,20 +790,21 @@
struct dma_chan *dma_chan;
dma_cookie_t cookie;
struct dma_async_tx_descriptor *tx;
+ struct dmaengine_unmap_data *unmap;
int err = 0;
- src = kmalloc(sizeof(u8) * MV_XOR_TEST_SIZE, GFP_KERNEL);
+ src = kmalloc(sizeof(u8) * PAGE_SIZE, GFP_KERNEL);
if (!src)
return -ENOMEM;
- dest = kzalloc(sizeof(u8) * MV_XOR_TEST_SIZE, GFP_KERNEL);
+ dest = kzalloc(sizeof(u8) * PAGE_SIZE, GFP_KERNEL);
if (!dest) {
kfree(src);
return -ENOMEM;
}
/* Fill in src buffer */
- for (i = 0; i < MV_XOR_TEST_SIZE; i++)
+ for (i = 0; i < PAGE_SIZE; i++)
((u8 *) src)[i] = (u8)i;
dma_chan = &mv_chan->dmachan;
@@ -819,14 +813,26 @@
goto out;
}
- dest_dma = dma_map_single(dma_chan->device->dev, dest,
- MV_XOR_TEST_SIZE, DMA_FROM_DEVICE);
+ unmap = dmaengine_get_unmap_data(dma_chan->device->dev, 2, GFP_KERNEL);
+ if (!unmap) {
+ err = -ENOMEM;
+ goto free_resources;
+ }
- src_dma = dma_map_single(dma_chan->device->dev, src,
- MV_XOR_TEST_SIZE, DMA_TO_DEVICE);
+ src_dma = dma_map_page(dma_chan->device->dev, virt_to_page(src), 0,
+ PAGE_SIZE, DMA_TO_DEVICE);
+ unmap->to_cnt = 1;
+ unmap->addr[0] = src_dma;
+
+ dest_dma = dma_map_page(dma_chan->device->dev, virt_to_page(dest), 0,
+ PAGE_SIZE, DMA_FROM_DEVICE);
+ unmap->from_cnt = 1;
+ unmap->addr[1] = dest_dma;
+
+ unmap->len = PAGE_SIZE;
tx = mv_xor_prep_dma_memcpy(dma_chan, dest_dma, src_dma,
- MV_XOR_TEST_SIZE, 0);
+ PAGE_SIZE, 0);
cookie = mv_xor_tx_submit(tx);
mv_xor_issue_pending(dma_chan);
async_tx_ack(tx);
@@ -841,8 +847,8 @@
}
dma_sync_single_for_cpu(dma_chan->device->dev, dest_dma,
- MV_XOR_TEST_SIZE, DMA_FROM_DEVICE);
- if (memcmp(src, dest, MV_XOR_TEST_SIZE)) {
+ PAGE_SIZE, DMA_FROM_DEVICE);
+ if (memcmp(src, dest, PAGE_SIZE)) {
dev_err(dma_chan->device->dev,
"Self-test copy failed compare, disabling\n");
err = -ENODEV;
@@ -850,6 +856,7 @@
}
free_resources:
+ dmaengine_unmap_put(unmap);
mv_xor_free_chan_resources(dma_chan);
out:
kfree(src);
@@ -867,13 +874,15 @@
dma_addr_t dma_srcs[MV_XOR_NUM_SRC_TEST];
dma_addr_t dest_dma;
struct dma_async_tx_descriptor *tx;
+ struct dmaengine_unmap_data *unmap;
struct dma_chan *dma_chan;
dma_cookie_t cookie;
u8 cmp_byte = 0;
u32 cmp_word;
int err = 0;
+ int src_count = MV_XOR_NUM_SRC_TEST;
- for (src_idx = 0; src_idx < MV_XOR_NUM_SRC_TEST; src_idx++) {
+ for (src_idx = 0; src_idx < src_count; src_idx++) {
xor_srcs[src_idx] = alloc_page(GFP_KERNEL);
if (!xor_srcs[src_idx]) {
while (src_idx--)
@@ -890,13 +899,13 @@
}
/* Fill in src buffers */
- for (src_idx = 0; src_idx < MV_XOR_NUM_SRC_TEST; src_idx++) {
+ for (src_idx = 0; src_idx < src_count; src_idx++) {
u8 *ptr = page_address(xor_srcs[src_idx]);
for (i = 0; i < PAGE_SIZE; i++)
ptr[i] = (1 << src_idx);
}
- for (src_idx = 0; src_idx < MV_XOR_NUM_SRC_TEST; src_idx++)
+ for (src_idx = 0; src_idx < src_count; src_idx++)
cmp_byte ^= (u8) (1 << src_idx);
cmp_word = (cmp_byte << 24) | (cmp_byte << 16) |
@@ -910,16 +919,29 @@
goto out;
}
- /* test xor */
- dest_dma = dma_map_page(dma_chan->device->dev, dest, 0, PAGE_SIZE,
- DMA_FROM_DEVICE);
+ unmap = dmaengine_get_unmap_data(dma_chan->device->dev, src_count + 1,
+ GFP_KERNEL);
+ if (!unmap) {
+ err = -ENOMEM;
+ goto free_resources;
+ }
- for (i = 0; i < MV_XOR_NUM_SRC_TEST; i++)
- dma_srcs[i] = dma_map_page(dma_chan->device->dev, xor_srcs[i],
- 0, PAGE_SIZE, DMA_TO_DEVICE);
+ /* test xor */
+ for (i = 0; i < src_count; i++) {
+ unmap->addr[i] = dma_map_page(dma_chan->device->dev, xor_srcs[i],
+ 0, PAGE_SIZE, DMA_TO_DEVICE);
+ dma_srcs[i] = unmap->addr[i];
+ unmap->to_cnt++;
+ }
+
+ unmap->addr[src_count] = dma_map_page(dma_chan->device->dev, dest, 0, PAGE_SIZE,
+ DMA_FROM_DEVICE);
+ dest_dma = unmap->addr[src_count];
+ unmap->from_cnt = 1;
+ unmap->len = PAGE_SIZE;
tx = mv_xor_prep_dma_xor(dma_chan, dest_dma, dma_srcs,
- MV_XOR_NUM_SRC_TEST, PAGE_SIZE, 0);
+ src_count, PAGE_SIZE, 0);
cookie = mv_xor_tx_submit(tx);
mv_xor_issue_pending(dma_chan);
@@ -948,9 +970,10 @@
}
free_resources:
+ dmaengine_unmap_put(unmap);
mv_xor_free_chan_resources(dma_chan);
out:
- src_idx = MV_XOR_NUM_SRC_TEST;
+ src_idx = src_count;
while (src_idx--)
__free_page(xor_srcs[src_idx]);
__free_page(dest);
@@ -1176,6 +1199,7 @@
int i = 0;
for_each_child_of_node(pdev->dev.of_node, np) {
+ struct mv_xor_chan *chan;
dma_cap_mask_t cap_mask;
int irq;
@@ -1193,21 +1217,21 @@
goto err_channel_add;
}
- xordev->channels[i] =
- mv_xor_channel_add(xordev, pdev, i,
- cap_mask, irq);
- if (IS_ERR(xordev->channels[i])) {
- ret = PTR_ERR(xordev->channels[i]);
- xordev->channels[i] = NULL;
+ chan = mv_xor_channel_add(xordev, pdev, i,
+ cap_mask, irq);
+ if (IS_ERR(chan)) {
+ ret = PTR_ERR(chan);
irq_dispose_mapping(irq);
goto err_channel_add;
}
+ xordev->channels[i] = chan;
i++;
}
} else if (pdata && pdata->channels) {
for (i = 0; i < MV_XOR_MAX_CHANNELS; i++) {
struct mv_xor_channel_data *cd;
+ struct mv_xor_chan *chan;
int irq;
cd = &pdata->channels[i];
@@ -1222,13 +1246,14 @@
goto err_channel_add;
}
- xordev->channels[i] =
- mv_xor_channel_add(xordev, pdev, i,
- cd->cap_mask, irq);
- if (IS_ERR(xordev->channels[i])) {
- ret = PTR_ERR(xordev->channels[i]);
+ chan = mv_xor_channel_add(xordev, pdev, i,
+ cd->cap_mask, irq);
+ if (IS_ERR(chan)) {
+ ret = PTR_ERR(chan);
goto err_channel_add;
}
+
+ xordev->channels[i] = chan;
}
}
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index cdf0483..536632f 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2492,12 +2492,9 @@
static inline void _init_desc(struct dma_pl330_desc *desc)
{
- desc->pchan = NULL;
desc->req.x = &desc->px;
desc->req.token = desc;
desc->rqcfg.swap = SWAP_NO;
- desc->rqcfg.privileged = 0;
- desc->rqcfg.insnaccess = 0;
desc->rqcfg.scctl = SCCTRL0;
desc->rqcfg.dcctl = DCCTRL0;
desc->req.cfg = &desc->rqcfg;
@@ -2517,7 +2514,7 @@
if (!pdmac)
return 0;
- desc = kmalloc(count * sizeof(*desc), flg);
+ desc = kcalloc(count, sizeof(*desc), flg);
if (!desc)
return 0;
diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c
index 8da48c6..8bba298 100644
--- a/drivers/dma/ppc4xx/adma.c
+++ b/drivers/dma/ppc4xx/adma.c
@@ -533,29 +533,6 @@
}
/**
- * ppc440spe_desc_init_memset - initialize the descriptor for MEMSET operation
- */
-static void ppc440spe_desc_init_memset(struct ppc440spe_adma_desc_slot *desc,
- int value, unsigned long flags)
-{
- struct dma_cdb *hw_desc = desc->hw_desc;
-
- memset(desc->hw_desc, 0, sizeof(struct dma_cdb));
- desc->hw_next = NULL;
- desc->src_cnt = 1;
- desc->dst_cnt = 1;
-
- if (flags & DMA_PREP_INTERRUPT)
- set_bit(PPC440SPE_DESC_INT, &desc->flags);
- else
- clear_bit(PPC440SPE_DESC_INT, &desc->flags);
-
- hw_desc->sg1u = hw_desc->sg1l = cpu_to_le32((u32)value);
- hw_desc->sg3u = hw_desc->sg3l = cpu_to_le32((u32)value);
- hw_desc->opc = DMA_CDB_OPC_DFILL128;
-}
-
-/**
* ppc440spe_desc_set_src_addr - set source address into the descriptor
*/
static void ppc440spe_desc_set_src_addr(struct ppc440spe_adma_desc_slot *desc,
@@ -1504,8 +1481,6 @@
struct ppc440spe_adma_chan *chan,
dma_cookie_t cookie)
{
- int i;
-
BUG_ON(desc->async_tx.cookie < 0);
if (desc->async_tx.cookie > 0) {
cookie = desc->async_tx.cookie;
@@ -3898,7 +3873,7 @@
ppc440spe_adma_prep_dma_interrupt;
}
pr_info("%s: AMCC(R) PPC440SP(E) ADMA Engine: "
- "( %s%s%s%s%s%s%s)\n",
+ "( %s%s%s%s%s%s)\n",
dev_name(adev->dev),
dma_has_cap(DMA_PQ, adev->common.cap_mask) ? "pq " : "",
dma_has_cap(DMA_PQ_VAL, adev->common.cap_mask) ? "pq_val " : "",
diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c
index bae6c29..17686ca 100644
--- a/drivers/dma/txx9dmac.c
+++ b/drivers/dma/txx9dmac.c
@@ -406,7 +406,6 @@
dma_async_tx_callback callback;
void *param;
struct dma_async_tx_descriptor *txd = &desc->txd;
- struct txx9dmac_slave *ds = dc->chan.private;
dev_vdbg(chan2dev(&dc->chan), "descriptor %u %p complete\n",
txd->cookie, desc);
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index b0bb056..281029d 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -1623,7 +1623,6 @@
.cmd_per_lun = 1,
.can_queue = 1,
.sdev_attrs = sbp2_scsi_sysfs_attrs,
- .no_write_same = 1,
};
MODULE_AUTHOR("Kristian Hoegsberg <krh@bitplanet.net>");
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 299fad6..5373dc5 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -14,3 +14,4 @@
obj-$(CONFIG_GOOGLE_FIRMWARE) += google/
obj-$(CONFIG_EFI) += efi/
+obj-$(CONFIG_UEFI_CPER) += efi/
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 3150aa4..6aecbc8 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -36,7 +36,7 @@
backend for pstore by default. This setting can be overridden
using the efivars module's pstore_disable parameter.
-config UEFI_CPER
- def_bool n
-
endmenu
+
+config UEFI_CPER
+ bool
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index 9ba156d..6c2a41e 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -1,7 +1,7 @@
#
# Makefile for linux kernel
#
-obj-y += efi.o vars.o
+obj-$(CONFIG_EFI) += efi.o vars.o
obj-$(CONFIG_EFI_VARS) += efivars.o
obj-$(CONFIG_EFI_VARS_PSTORE) += efi-pstore.o
obj-$(CONFIG_UEFI_CPER) += cper.o
diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index 743fd42..4b9dc83 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -356,6 +356,7 @@
static struct pstore_info efi_pstore_info = {
.owner = THIS_MODULE,
.name = "efi",
+ .flags = PSTORE_FLAGS_FRAGILE,
.open = efi_pstore_open,
.close = efi_pstore_close,
.read = efi_pstore_read,
diff --git a/drivers/gpio/gpio-msm-v2.c b/drivers/gpio/gpio-msm-v2.c
index 7b37300..2baf0dd 100644
--- a/drivers/gpio/gpio-msm-v2.c
+++ b/drivers/gpio/gpio-msm-v2.c
@@ -252,7 +252,7 @@
spin_lock_irqsave(&tlmm_lock, irq_flags);
writel(TARGET_PROC_NONE, GPIO_INTR_CFG_SU(gpio));
- clear_gpio_bits(INTR_RAW_STATUS_EN | INTR_ENABLE, GPIO_INTR_CFG(gpio));
+ clear_gpio_bits(BIT(INTR_RAW_STATUS_EN) | BIT(INTR_ENABLE), GPIO_INTR_CFG(gpio));
__clear_bit(gpio, msm_gpio.enabled_irqs);
spin_unlock_irqrestore(&tlmm_lock, irq_flags);
}
@@ -264,7 +264,7 @@
spin_lock_irqsave(&tlmm_lock, irq_flags);
__set_bit(gpio, msm_gpio.enabled_irqs);
- set_gpio_bits(INTR_RAW_STATUS_EN | INTR_ENABLE, GPIO_INTR_CFG(gpio));
+ set_gpio_bits(BIT(INTR_RAW_STATUS_EN) | BIT(INTR_ENABLE), GPIO_INTR_CFG(gpio));
writel(TARGET_PROC_SCORPION, GPIO_INTR_CFG_SU(gpio));
spin_unlock_irqrestore(&tlmm_lock, irq_flags);
}
diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index fe088a3..8b7e719 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -169,7 +169,8 @@
u32 pending;
unsigned int offset, irqs_handled = 0;
- while ((pending = gpio_rcar_read(p, INTDT))) {
+ while ((pending = gpio_rcar_read(p, INTDT) &
+ gpio_rcar_read(p, INTMSK))) {
offset = __ffs(pending);
gpio_rcar_write(p, INTCLR, BIT(offset));
generic_handle_irq(irq_find_mapping(p->irq_domain, offset));
diff --git a/drivers/gpio/gpio-twl4030.c b/drivers/gpio/gpio-twl4030.c
index b97d6a6..f999689 100644
--- a/drivers/gpio/gpio-twl4030.c
+++ b/drivers/gpio/gpio-twl4030.c
@@ -300,7 +300,7 @@
if (offset < TWL4030_GPIO_MAX)
ret = twl4030_set_gpio_direction(offset, 1);
else
- ret = -EINVAL;
+ ret = -EINVAL; /* LED outputs can't be set as input */
if (!ret)
priv->direction &= ~BIT(offset);
@@ -354,11 +354,20 @@
static int twl_direction_out(struct gpio_chip *chip, unsigned offset, int value)
{
struct gpio_twl4030_priv *priv = to_gpio_twl4030(chip);
- int ret = -EINVAL;
+ int ret = 0;
mutex_lock(&priv->mutex);
- if (offset < TWL4030_GPIO_MAX)
+ if (offset < TWL4030_GPIO_MAX) {
ret = twl4030_set_gpio_direction(offset, 0);
+ if (ret) {
+ mutex_unlock(&priv->mutex);
+ return ret;
+ }
+ }
+
+ /*
+ * LED gpios i.e. offset >= TWL4030_GPIO_MAX are always output
+ */
priv->direction |= BIT(offset);
mutex_unlock(&priv->mutex);
diff --git a/drivers/gpu/drm/armada/armada_drm.h b/drivers/gpu/drm/armada/armada_drm.h
index eef09ec..a72cae0 100644
--- a/drivers/gpu/drm/armada/armada_drm.h
+++ b/drivers/gpu/drm/armada/armada_drm.h
@@ -103,6 +103,7 @@
extern const struct drm_mode_config_funcs armada_drm_mode_config_funcs;
int armada_fbdev_init(struct drm_device *);
+void armada_fbdev_lastclose(struct drm_device *);
void armada_fbdev_fini(struct drm_device *);
int armada_overlay_plane_create(struct drm_device *, unsigned long);
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index 4f2b283..62d0ff3 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -321,6 +321,11 @@
DRM_UNLOCKED),
};
+static void armada_drm_lastclose(struct drm_device *dev)
+{
+ armada_fbdev_lastclose(dev);
+}
+
static const struct file_operations armada_drm_fops = {
.owner = THIS_MODULE,
.llseek = no_llseek,
@@ -337,7 +342,7 @@
.open = NULL,
.preclose = NULL,
.postclose = NULL,
- .lastclose = NULL,
+ .lastclose = armada_drm_lastclose,
.unload = armada_drm_unload,
.get_vblank_counter = drm_vblank_count,
.enable_vblank = armada_drm_enable_vblank,
diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c
index dd5ea77..948cb14 100644
--- a/drivers/gpu/drm/armada/armada_fbdev.c
+++ b/drivers/gpu/drm/armada/armada_fbdev.c
@@ -105,9 +105,9 @@
drm_fb_helper_fill_fix(info, dfb->fb.pitches[0], dfb->fb.depth);
drm_fb_helper_fill_var(info, fbh, sizes->fb_width, sizes->fb_height);
- DRM_DEBUG_KMS("allocated %dx%d %dbpp fb: 0x%08x\n",
- dfb->fb.width, dfb->fb.height,
- dfb->fb.bits_per_pixel, obj->phys_addr);
+ DRM_DEBUG_KMS("allocated %dx%d %dbpp fb: 0x%08llx\n",
+ dfb->fb.width, dfb->fb.height, dfb->fb.bits_per_pixel,
+ (unsigned long long)obj->phys_addr);
return 0;
@@ -177,6 +177,16 @@
return ret;
}
+void armada_fbdev_lastclose(struct drm_device *dev)
+{
+ struct armada_private *priv = dev->dev_private;
+
+ drm_modeset_lock_all(dev);
+ if (priv->fbdev)
+ drm_fb_helper_restore_fbdev_mode(priv->fbdev);
+ drm_modeset_unlock_all(dev);
+}
+
void armada_fbdev_fini(struct drm_device *dev)
{
struct armada_private *priv = dev->dev_private;
@@ -192,11 +202,11 @@
framebuffer_release(info);
}
+ drm_fb_helper_fini(fbh);
+
if (fbh->fb)
fbh->fb->funcs->destroy(fbh->fb);
- drm_fb_helper_fini(fbh);
-
priv->fbdev = NULL;
}
}
diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c
index 9f2356b..887816f 100644
--- a/drivers/gpu/drm/armada/armada_gem.c
+++ b/drivers/gpu/drm/armada/armada_gem.c
@@ -172,8 +172,9 @@
obj->dev_addr = obj->linear->start;
}
- DRM_DEBUG_DRIVER("obj %p phys %#x dev %#x\n",
- obj, obj->phys_addr, obj->dev_addr);
+ DRM_DEBUG_DRIVER("obj %p phys %#llx dev %#llx\n", obj,
+ (unsigned long long)obj->phys_addr,
+ (unsigned long long)obj->dev_addr);
return 0;
}
@@ -557,7 +558,6 @@
* refcount on the gem object itself.
*/
drm_gem_object_reference(obj);
- dma_buf_put(buf);
return obj;
}
}
@@ -573,6 +573,7 @@
}
dobj->obj.import_attach = attach;
+ get_dma_buf(buf);
/*
* Don't call dma_buf_map_attachment() here - it maps the
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 0a1e4a5..8835dcd 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -68,6 +68,8 @@
#define EDID_QUIRK_DETAILED_SYNC_PP (1 << 6)
/* Force reduced-blanking timings for detailed modes */
#define EDID_QUIRK_FORCE_REDUCED_BLANKING (1 << 7)
+/* Force 8bpc */
+#define EDID_QUIRK_FORCE_8BPC (1 << 8)
struct detailed_mode_closure {
struct drm_connector *connector;
@@ -128,6 +130,9 @@
/* Medion MD 30217 PG */
{ "MED", 0x7b8, EDID_QUIRK_PREFER_LARGE_75 },
+
+ /* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */
+ { "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC },
};
/*
@@ -3435,6 +3440,9 @@
drm_add_display_info(edid, &connector->display_info);
+ if (quirks & EDID_QUIRK_FORCE_8BPC)
+ connector->display_info.bpc = 8;
+
return num_modes;
}
EXPORT_SYMBOL(drm_add_edid_modes);
diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c
index f53d524..66dd3a0 100644
--- a/drivers/gpu/drm/drm_stub.c
+++ b/drivers/gpu/drm/drm_stub.c
@@ -566,11 +566,11 @@
if (dev->driver->unload)
dev->driver->unload(dev);
err_primary_node:
- drm_put_minor(dev->primary);
+ drm_unplug_minor(dev->primary);
err_render_node:
- drm_put_minor(dev->render);
+ drm_unplug_minor(dev->render);
err_control_node:
- drm_put_minor(dev->control);
+ drm_unplug_minor(dev->control);
err_agp:
if (dev->driver->bus->agp_destroy)
dev->driver->bus->agp_destroy(dev);
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 0cab2d0..5c64842 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -83,6 +83,14 @@
drm_i915_private_t *dev_priv = dev->dev_private;
struct drm_i915_master_private *master_priv;
+ /*
+ * The dri breadcrumb update races against the drm master disappearing.
+ * Instead of trying to fix this (this is by far not the only ums issue)
+ * just don't do the update in kms mode.
+ */
+ if (drm_core_check_feature(dev, DRIVER_MODESET))
+ return;
+
if (dev->primary->master) {
master_priv = dev->primary->master->driver_priv;
if (master_priv->sarea_priv)
@@ -1490,16 +1498,9 @@
spin_lock_init(&dev_priv->uncore.lock);
spin_lock_init(&dev_priv->mm.object_stat_lock);
mutex_init(&dev_priv->dpio_lock);
- mutex_init(&dev_priv->rps.hw_lock);
mutex_init(&dev_priv->modeset_restore_lock);
- mutex_init(&dev_priv->pc8.lock);
- dev_priv->pc8.requirements_met = false;
- dev_priv->pc8.gpu_idle = false;
- dev_priv->pc8.irqs_disabled = false;
- dev_priv->pc8.enabled = false;
- dev_priv->pc8.disable_count = 2; /* requirements_met + gpu_idle */
- INIT_DELAYED_WORK(&dev_priv->pc8.enable_work, hsw_enable_pc8_work);
+ intel_pm_setup(dev);
intel_display_crc_init(dev);
@@ -1603,7 +1604,6 @@
}
intel_irq_init(dev);
- intel_pm_init(dev);
intel_uncore_sanitize(dev);
/* Try to make sure MCHBAR is enabled before poking at it */
@@ -1848,8 +1848,10 @@
void i915_driver_preclose(struct drm_device * dev, struct drm_file *file_priv)
{
+ mutex_lock(&dev->struct_mutex);
i915_gem_context_close(dev, file_priv);
i915_gem_release(dev, file_priv);
+ mutex_unlock(&dev->struct_mutex);
}
void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 2e367a1..5b7b7e0 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -651,6 +651,7 @@
intel_modeset_init_hw(dev);
drm_modeset_lock_all(dev);
+ drm_mode_config_reset(dev);
intel_modeset_setup_hw_state(dev, true);
drm_modeset_unlock_all(dev);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ccdbecc..90fcccb 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1755,8 +1755,13 @@
#define IS_MOBILE(dev) (INTEL_INFO(dev)->is_mobile)
#define IS_HSW_EARLY_SDV(dev) (IS_HASWELL(dev) && \
((dev)->pdev->device & 0xFF00) == 0x0C00)
-#define IS_ULT(dev) (IS_HASWELL(dev) && \
+#define IS_BDW_ULT(dev) (IS_BROADWELL(dev) && \
+ (((dev)->pdev->device & 0xf) == 0x2 || \
+ ((dev)->pdev->device & 0xf) == 0x6 || \
+ ((dev)->pdev->device & 0xf) == 0xe))
+#define IS_HSW_ULT(dev) (IS_HASWELL(dev) && \
((dev)->pdev->device & 0xFF00) == 0x0A00)
+#define IS_ULT(dev) (IS_HSW_ULT(dev) || IS_BDW_ULT(dev))
#define IS_HSW_GT3(dev) (IS_HASWELL(dev) && \
((dev)->pdev->device & 0x00F0) == 0x0020)
#define IS_PRELIMINARY_HW(intel_info) ((intel_info)->is_preliminary)
@@ -1901,9 +1906,7 @@
void i915_handle_error(struct drm_device *dev, bool wedged);
extern void intel_irq_init(struct drm_device *dev);
-extern void intel_pm_init(struct drm_device *dev);
extern void intel_hpd_init(struct drm_device *dev);
-extern void intel_pm_init(struct drm_device *dev);
extern void intel_uncore_sanitize(struct drm_device *dev);
extern void intel_uncore_early_sanitize(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 621c7c6..76d3d1a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2343,15 +2343,24 @@
kfree(request);
}
-static void i915_gem_reset_ring_lists(struct drm_i915_private *dev_priv,
- struct intel_ring_buffer *ring)
+static void i915_gem_reset_ring_status(struct drm_i915_private *dev_priv,
+ struct intel_ring_buffer *ring)
{
- u32 completed_seqno;
- u32 acthd;
+ u32 completed_seqno = ring->get_seqno(ring, false);
+ u32 acthd = intel_ring_get_active_head(ring);
+ struct drm_i915_gem_request *request;
- acthd = intel_ring_get_active_head(ring);
- completed_seqno = ring->get_seqno(ring, false);
+ list_for_each_entry(request, &ring->request_list, list) {
+ if (i915_seqno_passed(completed_seqno, request->seqno))
+ continue;
+ i915_set_reset_status(ring, request, acthd);
+ }
+}
+
+static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
+ struct intel_ring_buffer *ring)
+{
while (!list_empty(&ring->request_list)) {
struct drm_i915_gem_request *request;
@@ -2359,9 +2368,6 @@
struct drm_i915_gem_request,
list);
- if (request->seqno > completed_seqno)
- i915_set_reset_status(ring, request, acthd);
-
i915_gem_free_request(request);
}
@@ -2403,8 +2409,16 @@
struct intel_ring_buffer *ring;
int i;
+ /*
+ * Before we free the objects from the requests, we need to inspect
+ * them for finding the guilty party. As the requests only borrow
+ * their reference to the objects, the inspection must be done first.
+ */
for_each_ring(ring, dev_priv, i)
- i915_gem_reset_ring_lists(dev_priv, ring);
+ i915_gem_reset_ring_status(dev_priv, ring);
+
+ for_each_ring(ring, dev_priv, i)
+ i915_gem_reset_ring_cleanup(dev_priv, ring);
i915_gem_cleanup_ringbuffer(dev);
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 72a3df3..b0f42b9 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -347,10 +347,8 @@
{
struct drm_i915_file_private *file_priv = file->driver_priv;
- mutex_lock(&dev->struct_mutex);
idr_for_each(&file_priv->context_idr, context_idr_cleanup, NULL);
idr_destroy(&file_priv->context_idr);
- mutex_unlock(&dev->struct_mutex);
}
static struct i915_hw_context *
@@ -423,11 +421,21 @@
if (ret)
return ret;
- /* Clear this page out of any CPU caches for coherent swap-in/out. Note
+ /*
+ * Pin can switch back to the default context if we end up calling into
+ * evict_everything - as a last ditch gtt defrag effort that also
+ * switches to the default context. Hence we need to reload from here.
+ */
+ from = ring->last_context;
+
+ /*
+ * Clear this page out of any CPU caches for coherent swap-in/out. Note
* that thanks to write = false in this call and us not setting any gpu
* write domains when putting a context object onto the active list
* (when switching away from it), this won't block.
- * XXX: We need a real interface to do this instead of trickery. */
+ *
+ * XXX: We need a real interface to do this instead of trickery.
+ */
ret = i915_gem_object_set_to_gtt_domain(to->obj, false);
if (ret) {
i915_gem_object_unpin(to->obj);
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index b737653..8f3adc7 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -88,6 +88,7 @@
} else
drm_mm_init_scan(&vm->mm, min_size, alignment, cache_level);
+search_again:
/* First see if there is a large enough contiguous idle region... */
list_for_each_entry(vma, &vm->inactive_list, mm_list) {
if (mark_free(vma, &unwind_list))
@@ -115,10 +116,17 @@
list_del_init(&vma->exec_list);
}
- /* We expect the caller to unpin, evict all and try again, or give up.
- * So calling i915_gem_evict_vm() is unnecessary.
+ /* Can we unpin some objects such as idle hw contents,
+ * or pending flips?
*/
- return -ENOSPC;
+ ret = nonblocking ? -ENOSPC : i915_gpu_idle(dev);
+ if (ret)
+ return ret;
+
+ /* Only idle the GPU and repeat the search once */
+ i915_gem_retire_requests(dev);
+ nonblocking = true;
+ goto search_again;
found:
/* drm_mm doesn't allow any other other operations while
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index b7e787f..a3ba9a8 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -93,7 +93,7 @@
{
struct drm_i915_gem_object *obj;
struct list_head objects;
- int i, ret = 0;
+ int i, ret;
INIT_LIST_HEAD(&objects);
spin_lock(&file->table_lock);
@@ -106,7 +106,7 @@
DRM_DEBUG("Invalid object handle %d at index %d\n",
exec[i].handle, i);
ret = -ENOENT;
- goto out;
+ goto err;
}
if (!list_empty(&obj->obj_exec_link)) {
@@ -114,7 +114,7 @@
DRM_DEBUG("Object %p [handle %d, index %d] appears more than once in object list\n",
obj, exec[i].handle, i);
ret = -EINVAL;
- goto out;
+ goto err;
}
drm_gem_object_reference(&obj->base);
@@ -123,9 +123,13 @@
spin_unlock(&file->table_lock);
i = 0;
- list_for_each_entry(obj, &objects, obj_exec_link) {
+ while (!list_empty(&objects)) {
struct i915_vma *vma;
+ obj = list_first_entry(&objects,
+ struct drm_i915_gem_object,
+ obj_exec_link);
+
/*
* NOTE: We can leak any vmas created here when something fails
* later on. But that's no issue since vma_unbind can deal with
@@ -138,10 +142,12 @@
if (IS_ERR(vma)) {
DRM_DEBUG("Failed to lookup VMA\n");
ret = PTR_ERR(vma);
- goto out;
+ goto err;
}
+ /* Transfer ownership from the objects list to the vmas list. */
list_add_tail(&vma->exec_list, &eb->vmas);
+ list_del_init(&obj->obj_exec_link);
vma->exec_entry = &exec[i];
if (eb->and < 0) {
@@ -155,16 +161,22 @@
++i;
}
+ return 0;
-out:
+
+err:
while (!list_empty(&objects)) {
obj = list_first_entry(&objects,
struct drm_i915_gem_object,
obj_exec_link);
list_del_init(&obj->obj_exec_link);
- if (ret)
- drm_gem_object_unreference(&obj->base);
+ drm_gem_object_unreference(&obj->base);
}
+ /*
+ * Objects already transfered to the vmas list will be unreferenced by
+ * eb_destroy.
+ */
+
return ret;
}
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 38cb8d4..d3c3b5b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -337,8 +337,8 @@
kfree(ppgtt->gen8_pt_dma_addr[i]);
}
- __free_pages(ppgtt->gen8_pt_pages, ppgtt->num_pt_pages << PAGE_SHIFT);
- __free_pages(ppgtt->pd_pages, ppgtt->num_pd_pages << PAGE_SHIFT);
+ __free_pages(ppgtt->gen8_pt_pages, get_order(ppgtt->num_pt_pages << PAGE_SHIFT));
+ __free_pages(ppgtt->pd_pages, get_order(ppgtt->num_pd_pages << PAGE_SHIFT));
}
/**
@@ -906,14 +906,12 @@
WARN_ON(readq(>t_entries[i-1])
!= gen8_pte_encode(addr, level, true));
-#if 0 /* TODO: Still needed on GEN8? */
/* This next bit makes the above posting read even more important. We
* want to flush the TLBs only after we're certain all the PTE updates
* have finished.
*/
I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
POSTING_READ(GFX_FLSH_CNTL_GEN6);
-#endif
}
/*
@@ -1241,6 +1239,11 @@
bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK;
if (bdw_gmch_ctl)
bdw_gmch_ctl = 1 << bdw_gmch_ctl;
+ if (bdw_gmch_ctl > 4) {
+ WARN_ON(!i915_preliminary_hw_support);
+ return 4<<20;
+ }
+
return bdw_gmch_ctl << 20;
}
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 080f6fd..769b864 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -6303,7 +6303,7 @@
uint32_t val;
list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head)
- WARN(crtc->base.enabled, "CRTC for pipe %c enabled\n",
+ WARN(crtc->active, "CRTC for pipe %c enabled\n",
pipe_name(crtc->pipe));
WARN(I915_READ(HSW_PWR_WELL_DRIVER), "Power well on\n");
@@ -9135,7 +9135,7 @@
if (IS_G4X(dev) || INTEL_INFO(dev)->gen >= 5)
PIPE_CONF_CHECK_I(pipe_bpp);
- if (!IS_HASWELL(dev)) {
+ if (!HAS_DDI(dev)) {
PIPE_CONF_CHECK_CLOCK_FUZZY(adjusted_mode.crtc_clock);
PIPE_CONF_CHECK_CLOCK_FUZZY(port_clock);
}
@@ -10541,11 +10541,20 @@
/* Sony Vaio Y cannot use SSC on LVDS */
{ 0x0046, 0x104d, 0x9076, quirk_ssc_force_disable },
- /*
- * All GM45 Acer (and its brands eMachines and Packard Bell) laptops
- * seem to use inverted backlight PWM.
- */
- { 0x2a42, 0x1025, PCI_ANY_ID, quirk_invert_brightness },
+ /* Acer Aspire 5734Z must invert backlight brightness */
+ { 0x2a42, 0x1025, 0x0459, quirk_invert_brightness },
+
+ /* Acer/eMachines G725 */
+ { 0x2a42, 0x1025, 0x0210, quirk_invert_brightness },
+
+ /* Acer/eMachines e725 */
+ { 0x2a42, 0x1025, 0x0212, quirk_invert_brightness },
+
+ /* Acer/Packard Bell NCL20 */
+ { 0x2a42, 0x1025, 0x034b, quirk_invert_brightness },
+
+ /* Acer Aspire 4736Z */
+ { 0x2a42, 0x1025, 0x0260, quirk_invert_brightness },
/* Dell XPS13 HD Sandy Bridge */
{ 0x0116, 0x1028, 0x052e, quirk_no_pcm_pwm_enable },
@@ -11036,8 +11045,6 @@
}
intel_modeset_check_state(dev);
-
- drm_mode_config_reset(dev);
}
void intel_modeset_gem_init(struct drm_device *dev)
@@ -11046,7 +11053,10 @@
intel_setup_overlay(dev);
+ drm_modeset_lock_all(dev);
+ drm_mode_config_reset(dev);
intel_modeset_setup_hw_state(dev, false);
+ drm_modeset_unlock_all(dev);
}
void intel_modeset_cleanup(struct drm_device *dev)
@@ -11125,14 +11135,15 @@
int intel_modeset_vga_set_state(struct drm_device *dev, bool state)
{
struct drm_i915_private *dev_priv = dev->dev_private;
+ unsigned reg = INTEL_INFO(dev)->gen >= 6 ? SNB_GMCH_CTRL : INTEL_GMCH_CTRL;
u16 gmch_ctrl;
- pci_read_config_word(dev_priv->bridge_dev, INTEL_GMCH_CTRL, &gmch_ctrl);
+ pci_read_config_word(dev_priv->bridge_dev, reg, &gmch_ctrl);
if (state)
gmch_ctrl &= ~INTEL_GMCH_VGA_DISABLE;
else
gmch_ctrl |= INTEL_GMCH_VGA_DISABLE;
- pci_write_config_word(dev_priv->bridge_dev, INTEL_GMCH_CTRL, gmch_ctrl);
+ pci_write_config_word(dev_priv->bridge_dev, reg, gmch_ctrl);
return 0;
}
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index a18e88b..79f91f2 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -821,6 +821,7 @@
uint32_t sprite_width, int pixel_size,
bool enabled, bool scaled);
void intel_init_pm(struct drm_device *dev);
+void intel_pm_setup(struct drm_device *dev);
bool intel_fbc_enabled(struct drm_device *dev);
void intel_update_fbc(struct drm_device *dev);
void intel_gpu_ips_init(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index f161ac0..e6f782d 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -451,7 +451,9 @@
spin_lock_irqsave(&dev_priv->backlight.lock, flags);
- if (HAS_PCH_SPLIT(dev)) {
+ if (IS_BROADWELL(dev)) {
+ val = I915_READ(BLC_PWM_PCH_CTL2) & BACKLIGHT_DUTY_CYCLE_MASK;
+ } else if (HAS_PCH_SPLIT(dev)) {
val = I915_READ(BLC_PWM_CPU_CTL) & BACKLIGHT_DUTY_CYCLE_MASK;
} else {
if (IS_VALLEYVIEW(dev))
@@ -479,6 +481,13 @@
return val;
}
+static void intel_bdw_panel_set_backlight(struct drm_device *dev, u32 level)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ u32 val = I915_READ(BLC_PWM_PCH_CTL2) & ~BACKLIGHT_DUTY_CYCLE_MASK;
+ I915_WRITE(BLC_PWM_PCH_CTL2, val | level);
+}
+
static void intel_pch_panel_set_backlight(struct drm_device *dev, u32 level)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -496,7 +505,9 @@
DRM_DEBUG_DRIVER("set backlight PWM = %d\n", level);
level = intel_panel_compute_brightness(dev, pipe, level);
- if (HAS_PCH_SPLIT(dev))
+ if (IS_BROADWELL(dev))
+ return intel_bdw_panel_set_backlight(dev, level);
+ else if (HAS_PCH_SPLIT(dev))
return intel_pch_panel_set_backlight(dev, level);
if (is_backlight_combination_mode(dev)) {
@@ -666,7 +677,16 @@
POSTING_READ(reg);
I915_WRITE(reg, tmp | BLM_PWM_ENABLE);
- if (HAS_PCH_SPLIT(dev) &&
+ if (IS_BROADWELL(dev)) {
+ /*
+ * Broadwell requires PCH override to drive the PCH
+ * backlight pin. The above will configure the CPU
+ * backlight pin, which we don't plan to use.
+ */
+ tmp = I915_READ(BLC_PWM_PCH_CTL1);
+ tmp |= BLM_PCH_OVERRIDE_ENABLE | BLM_PCH_PWM_ENABLE;
+ I915_WRITE(BLC_PWM_PCH_CTL1, tmp);
+ } else if (HAS_PCH_SPLIT(dev) &&
!(dev_priv->quirks & QUIRK_NO_PCH_PWM_ENABLE)) {
tmp = I915_READ(BLC_PWM_PCH_CTL1);
tmp |= BLM_PCH_PWM_ENABLE;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 6e0d5e0..26c29c1 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5685,8 +5685,11 @@
{
struct drm_i915_private *dev_priv = dev->dev_private;
bool is_enabled, enable_requested;
+ unsigned long irqflags;
uint32_t tmp;
+ WARN_ON(dev_priv->pc8.enabled);
+
tmp = I915_READ(HSW_PWR_WELL_DRIVER);
is_enabled = tmp & HSW_PWR_WELL_STATE_ENABLED;
enable_requested = tmp & HSW_PWR_WELL_ENABLE_REQUEST;
@@ -5702,9 +5705,24 @@
HSW_PWR_WELL_STATE_ENABLED), 20))
DRM_ERROR("Timeout enabling power well\n");
}
+
+ if (IS_BROADWELL(dev)) {
+ spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+ I915_WRITE(GEN8_DE_PIPE_IMR(PIPE_B),
+ dev_priv->de_irq_mask[PIPE_B]);
+ I915_WRITE(GEN8_DE_PIPE_IER(PIPE_B),
+ ~dev_priv->de_irq_mask[PIPE_B] |
+ GEN8_PIPE_VBLANK);
+ I915_WRITE(GEN8_DE_PIPE_IMR(PIPE_C),
+ dev_priv->de_irq_mask[PIPE_C]);
+ I915_WRITE(GEN8_DE_PIPE_IER(PIPE_C),
+ ~dev_priv->de_irq_mask[PIPE_C] |
+ GEN8_PIPE_VBLANK);
+ POSTING_READ(GEN8_DE_PIPE_IER(PIPE_C));
+ spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+ }
} else {
if (enable_requested) {
- unsigned long irqflags;
enum pipe p;
I915_WRITE(HSW_PWR_WELL_DRIVER, 0);
@@ -5731,16 +5749,24 @@
static void __intel_power_well_get(struct drm_device *dev,
struct i915_power_well *power_well)
{
- if (!power_well->count++)
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ if (!power_well->count++) {
+ hsw_disable_package_c8(dev_priv);
__intel_set_power_well(dev, true);
+ }
}
static void __intel_power_well_put(struct drm_device *dev,
struct i915_power_well *power_well)
{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
WARN_ON(!power_well->count);
- if (!--power_well->count && i915_disable_power_well)
+ if (!--power_well->count && i915_disable_power_well) {
__intel_set_power_well(dev, false);
+ hsw_enable_package_c8(dev_priv);
+ }
}
void intel_display_power_get(struct drm_device *dev,
@@ -6130,10 +6156,19 @@
return val;
}
-void intel_pm_init(struct drm_device *dev)
+void intel_pm_setup(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
+ mutex_init(&dev_priv->rps.hw_lock);
+
+ mutex_init(&dev_priv->pc8.lock);
+ dev_priv->pc8.requirements_met = false;
+ dev_priv->pc8.gpu_idle = false;
+ dev_priv->pc8.irqs_disabled = false;
+ dev_priv->pc8.enabled = false;
+ dev_priv->pc8.disable_count = 2; /* requirements_met + gpu_idle */
+ INIT_DELAYED_WORK(&dev_priv->pc8.enable_work, hsw_enable_pc8_work);
INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work,
intel_gen6_powersave_work);
}
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index b620337..c2f09d45 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -965,6 +965,7 @@
} else if (IS_GEN6(ring->dev)) {
mmio = RING_HWS_PGA_GEN6(ring->mmio_base);
} else {
+ /* XXX: gen8 returns to sanity */
mmio = RING_HWS_PGA(ring->mmio_base);
}
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 0b02078..25cbe07 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -784,6 +784,7 @@
int intel_gpu_reset(struct drm_device *dev)
{
switch (INTEL_INFO(dev)->gen) {
+ case 8:
case 7:
case 6: return gen6_do_reset(dev);
case 5: return ironlake_do_reset(dev);
diff --git a/drivers/gpu/drm/nouveau/core/core/subdev.c b/drivers/gpu/drm/nouveau/core/core/subdev.c
index 48f0637..2ea5568 100644
--- a/drivers/gpu/drm/nouveau/core/core/subdev.c
+++ b/drivers/gpu/drm/nouveau/core/core/subdev.c
@@ -104,11 +104,8 @@
if (parent) {
struct nouveau_device *device = nv_device(parent);
- int subidx = nv_hclass(subdev) & 0xff;
-
subdev->debug = nouveau_dbgopt(device->dbgopt, subname);
subdev->mmio = nv_subdev(device)->mmio;
- device->subdev[subidx] = *pobject;
}
return 0;
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/base.c b/drivers/gpu/drm/nouveau/core/engine/device/base.c
index 9135b25a..dd01c6c 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/base.c
@@ -268,6 +268,8 @@
if (ret)
return ret;
+ device->subdev[i] = devobj->subdev[i];
+
/* note: can't init *any* subdevs until devinit has been run
* due to not knowing exactly what the vbios init tables will
* mess with. devinit also can't be run until all of its
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
index 8d06eef..dbc5e33 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
@@ -161,7 +161,7 @@
device->oclass[NVDEV_SUBDEV_THERM ] = &nva3_therm_oclass;
device->oclass[NVDEV_SUBDEV_MXM ] = &nv50_mxm_oclass;
device->oclass[NVDEV_SUBDEV_DEVINIT] = &nvc0_devinit_oclass;
- device->oclass[NVDEV_SUBDEV_MC ] = nvc3_mc_oclass;
+ device->oclass[NVDEV_SUBDEV_MC ] = nvc0_mc_oclass;
device->oclass[NVDEV_SUBDEV_BUS ] = nvc0_bus_oclass;
device->oclass[NVDEV_SUBDEV_TIMER ] = &nv04_timer_oclass;
device->oclass[NVDEV_SUBDEV_FB ] = nvc0_fb_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c
index 434bb4b..5c8a63d 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c
@@ -334,7 +334,7 @@
while ((mthd = &mthds[i++]) && (init = mthd->init)) {
u32 addr = 0x80000000 | mthd->oclass;
for (data = 0; init->count; init++) {
- if (data != init->data) {
+ if (init == mthd->init || data != init->data) {
nv_wr32(priv, 0x40448c, init->data);
data = init->data;
}
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/fb.h b/drivers/gpu/drm/nouveau/core/include/subdev/fb.h
index 8541aa3..d89dbdf 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/fb.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/fb.h
@@ -75,6 +75,11 @@
static inline struct nouveau_fb *
nouveau_fb(void *obj)
{
+ /* fbram uses this before device subdev pointer is valid */
+ if (nv_iclass(obj, NV_SUBDEV_CLASS) &&
+ nv_subidx(obj) == NVDEV_SUBDEV_FB)
+ return obj;
+
return (void *)nv_device(obj)->subdev[NVDEV_SUBDEV_FB];
}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
index 420908c..df1b1b4 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
@@ -365,13 +365,13 @@
init_script(struct nouveau_bios *bios, int index)
{
struct nvbios_init init = { .bios = bios };
- u16 data;
+ u16 bmp_ver = bmp_version(bios), data;
- if (bmp_version(bios) && bmp_version(bios) < 0x0510) {
- if (index > 1)
+ if (bmp_ver && bmp_ver < 0x0510) {
+ if (index > 1 || bmp_ver < 0x0100)
return 0x0000;
- data = bios->bmp_offset + (bios->version.major < 2 ? 14 : 18);
+ data = bios->bmp_offset + (bmp_ver < 0x0200 ? 14 : 18);
return nv_ro16(bios, data + (index * 2));
}
@@ -1294,7 +1294,11 @@
u16 offset = nv_ro16(bios, init->offset + 1);
trace("JUMP\t0x%04x\n", offset);
- init->offset = offset;
+
+ if (init_exec(init))
+ init->offset = offset;
+ else
+ init->offset += 3;
}
/**
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index 6828d81..900fae0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -447,6 +447,8 @@
if (ret)
goto done;
+ info->offset = ntfy->node->offset;
+
done:
if (ret)
nouveau_abi16_ntfy_fini(chan, ntfy);
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index 95c7404..ba0183f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -51,6 +51,7 @@
bool dsm_detected;
bool optimus_detected;
acpi_handle dhandle;
+ acpi_handle other_handle;
acpi_handle rom_handle;
} nouveau_dsm_priv;
@@ -260,9 +261,10 @@
if (!dhandle)
return false;
- if (!acpi_has_method(dhandle, "_DSM"))
+ if (!acpi_has_method(dhandle, "_DSM")) {
+ nouveau_dsm_priv.other_handle = dhandle;
return false;
-
+ }
if (nouveau_test_dsm(dhandle, nouveau_dsm, NOUVEAU_DSM_POWER))
retval |= NOUVEAU_DSM_HAS_MUX;
@@ -338,6 +340,16 @@
printk(KERN_INFO "VGA switcheroo: detected DSM switching method %s handle\n",
acpi_method_name);
nouveau_dsm_priv.dsm_detected = true;
+ /*
+ * On some systems hotplug events are generated for the device
+ * being switched off when _DSM is executed. They cause ACPI
+ * hotplug to trigger and attempt to remove the device from
+ * the system, which causes it to break down. Prevent that from
+ * happening by setting the no_hotplug flag for the involved
+ * ACPI device objects.
+ */
+ acpi_bus_no_hotplug(nouveau_dsm_priv.dhandle);
+ acpi_bus_no_hotplug(nouveau_dsm_priv.other_handle);
ret = true;
}
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 29c3efd..25ea82f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -610,7 +610,7 @@
ret = nouveau_fence_sync(fence, chan);
nouveau_fence_unref(&fence);
if (ret)
- return ret;
+ goto fail_free;
if (new_bo != old_bo) {
ret = nouveau_bo_pin(new_bo, TTM_PL_FLAG_VRAM);
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 7a3759f..98a22e6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -858,6 +858,12 @@
if (nouveau_runtime_pm == 0)
return -EINVAL;
+ /* are we optimus enabled? */
+ if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) {
+ DRM_DEBUG_DRIVER("failing to power off - not optimus\n");
+ return -EINVAL;
+ }
+
nv_debug_level(SILENT);
drm_kms_helper_poll_disable(drm_dev);
vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_OFF);
diff --git a/drivers/gpu/drm/qxl/Kconfig b/drivers/gpu/drm/qxl/Kconfig
index 037d324..66ac0ff 100644
--- a/drivers/gpu/drm/qxl/Kconfig
+++ b/drivers/gpu/drm/qxl/Kconfig
@@ -8,5 +8,6 @@
select DRM_KMS_HELPER
select DRM_KMS_FB_HELPER
select DRM_TTM
+ select CRC32
help
QXL virtual GPU for Spice virtualization desktop integration. Do not enable this driver unless your distro ships a corresponding X.org QXL driver that can handle kernel modesetting.
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 5e827c2..d70aafb 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -24,7 +24,7 @@
*/
-#include "linux/crc32.h"
+#include <linux/crc32.h>
#include "qxl_drv.h"
#include "qxl_object.h"
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 80a2012..0b9621c 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1143,31 +1143,53 @@
}
if (tiling_flags & RADEON_TILING_MACRO) {
- if (rdev->family >= CHIP_BONAIRE)
- tmp = rdev->config.cik.tile_config;
- else if (rdev->family >= CHIP_TAHITI)
- tmp = rdev->config.si.tile_config;
- else if (rdev->family >= CHIP_CAYMAN)
- tmp = rdev->config.cayman.tile_config;
- else
- tmp = rdev->config.evergreen.tile_config;
+ evergreen_tiling_fields(tiling_flags, &bankw, &bankh, &mtaspect, &tile_split);
- switch ((tmp & 0xf0) >> 4) {
- case 0: /* 4 banks */
- fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_4_BANK);
- break;
- case 1: /* 8 banks */
- default:
- fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_8_BANK);
- break;
- case 2: /* 16 banks */
- fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_16_BANK);
- break;
+ /* Set NUM_BANKS. */
+ if (rdev->family >= CHIP_BONAIRE) {
+ unsigned tileb, index, num_banks, tile_split_bytes;
+
+ /* Calculate the macrotile mode index. */
+ tile_split_bytes = 64 << tile_split;
+ tileb = 8 * 8 * target_fb->bits_per_pixel / 8;
+ tileb = min(tile_split_bytes, tileb);
+
+ for (index = 0; tileb > 64; index++) {
+ tileb >>= 1;
+ }
+
+ if (index >= 16) {
+ DRM_ERROR("Wrong screen bpp (%u) or tile split (%u)\n",
+ target_fb->bits_per_pixel, tile_split);
+ return -EINVAL;
+ }
+
+ num_banks = (rdev->config.cik.macrotile_mode_array[index] >> 6) & 0x3;
+ fb_format |= EVERGREEN_GRPH_NUM_BANKS(num_banks);
+ } else {
+ /* SI and older. */
+ if (rdev->family >= CHIP_TAHITI)
+ tmp = rdev->config.si.tile_config;
+ else if (rdev->family >= CHIP_CAYMAN)
+ tmp = rdev->config.cayman.tile_config;
+ else
+ tmp = rdev->config.evergreen.tile_config;
+
+ switch ((tmp & 0xf0) >> 4) {
+ case 0: /* 4 banks */
+ fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_4_BANK);
+ break;
+ case 1: /* 8 banks */
+ default:
+ fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_8_BANK);
+ break;
+ case 2: /* 16 banks */
+ fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_16_BANK);
+ break;
+ }
}
fb_format |= EVERGREEN_GRPH_ARRAY_MODE(EVERGREEN_GRPH_ARRAY_2D_TILED_THIN1);
-
- evergreen_tiling_fields(tiling_flags, &bankw, &bankh, &mtaspect, &tile_split);
fb_format |= EVERGREEN_GRPH_TILE_SPLIT(tile_split);
fb_format |= EVERGREEN_GRPH_BANK_WIDTH(bankw);
fb_format |= EVERGREEN_GRPH_BANK_HEIGHT(bankh);
@@ -1180,23 +1202,18 @@
fb_format |= EVERGREEN_GRPH_ARRAY_MODE(EVERGREEN_GRPH_ARRAY_1D_TILED_THIN1);
if (rdev->family >= CHIP_BONAIRE) {
- u32 num_pipe_configs = rdev->config.cik.max_tile_pipes;
- u32 num_rb = rdev->config.cik.max_backends_per_se;
- if (num_pipe_configs > 8)
- num_pipe_configs = 8;
- if (num_pipe_configs == 8)
- fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P8_32x32_16x16);
- else if (num_pipe_configs == 4) {
- if (num_rb == 4)
- fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P4_16x16);
- else if (num_rb < 4)
- fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P4_8x16);
- } else if (num_pipe_configs == 2)
- fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P2);
+ /* Read the pipe config from the 2D TILED SCANOUT mode.
+ * It should be the same for the other modes too, but not all
+ * modes set the pipe config field. */
+ u32 pipe_config = (rdev->config.cik.tile_mode_array[10] >> 6) & 0x1f;
+
+ fb_format |= CIK_GRPH_PIPE_CONFIG(pipe_config);
} else if ((rdev->family == CHIP_TAHITI) ||
(rdev->family == CHIP_PITCAIRN))
fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P8_32x32_8x16);
- else if (rdev->family == CHIP_VERDE)
+ else if ((rdev->family == CHIP_VERDE) ||
+ (rdev->family == CHIP_OLAND) ||
+ (rdev->family == CHIP_HAINAN)) /* for completeness. HAINAN has no display hw */
fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P4_8x16);
switch (radeon_crtc->crtc_id) {
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index b43a3a3..e950fab 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3057,7 +3057,7 @@
* Returns the disabled RB bitmask.
*/
static u32 cik_get_rb_disabled(struct radeon_device *rdev,
- u32 max_rb_num, u32 se_num,
+ u32 max_rb_num_per_se,
u32 sh_per_se)
{
u32 data, mask;
@@ -3071,7 +3071,7 @@
data >>= BACKEND_DISABLE_SHIFT;
- mask = cik_create_bitmask(max_rb_num / se_num / sh_per_se);
+ mask = cik_create_bitmask(max_rb_num_per_se / sh_per_se);
return data & mask;
}
@@ -3088,7 +3088,7 @@
*/
static void cik_setup_rb(struct radeon_device *rdev,
u32 se_num, u32 sh_per_se,
- u32 max_rb_num)
+ u32 max_rb_num_per_se)
{
int i, j;
u32 data, mask;
@@ -3098,7 +3098,7 @@
for (i = 0; i < se_num; i++) {
for (j = 0; j < sh_per_se; j++) {
cik_select_se_sh(rdev, i, j);
- data = cik_get_rb_disabled(rdev, max_rb_num, se_num, sh_per_se);
+ data = cik_get_rb_disabled(rdev, max_rb_num_per_se, sh_per_se);
if (rdev->family == CHIP_HAWAII)
disabled_rbs |= data << ((i * sh_per_se + j) * HAWAII_RB_BITMAP_WIDTH_PER_SH);
else
@@ -3108,12 +3108,14 @@
cik_select_se_sh(rdev, 0xffffffff, 0xffffffff);
mask = 1;
- for (i = 0; i < max_rb_num; i++) {
+ for (i = 0; i < max_rb_num_per_se * se_num; i++) {
if (!(disabled_rbs & mask))
enabled_rbs |= mask;
mask <<= 1;
}
+ rdev->config.cik.backend_enable_mask = enabled_rbs;
+
for (i = 0; i < se_num; i++) {
cik_select_se_sh(rdev, i, 0xffffffff);
data = 0;
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index 0300727..d08b83c 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -458,7 +458,7 @@
radeon_ring_write(ring, 0); /* src/dst endian swap */
radeon_ring_write(ring, src_offset & 0xffffffff);
radeon_ring_write(ring, upper_32_bits(src_offset) & 0xffffffff);
- radeon_ring_write(ring, dst_offset & 0xfffffffc);
+ radeon_ring_write(ring, dst_offset & 0xffffffff);
radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xffffffff);
src_offset += cur_size_in_bytes;
dst_offset += cur_size_in_bytes;
diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c
index de86493..713a5d3 100644
--- a/drivers/gpu/drm/radeon/dce6_afmt.c
+++ b/drivers/gpu/drm/radeon/dce6_afmt.c
@@ -174,7 +174,7 @@
}
sad_count = drm_edid_to_speaker_allocation(radeon_connector->edid, &sadb);
- if (sad_count < 0) {
+ if (sad_count <= 0) {
DRM_ERROR("Couldn't read Speaker Allocation Data Block: %d\n", sad_count);
return;
}
@@ -235,7 +235,7 @@
}
sad_count = drm_edid_to_sad(radeon_connector->edid, &sads);
- if (sad_count < 0) {
+ if (sad_count <= 0) {
DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
return;
}
@@ -308,7 +308,9 @@
rdev->audio.enabled = true;
if (ASIC_IS_DCE8(rdev))
- rdev->audio.num_pins = 7;
+ rdev->audio.num_pins = 6;
+ else if (ASIC_IS_DCE61(rdev))
+ rdev->audio.num_pins = 4;
else
rdev->audio.num_pins = 6;
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index aa695c4..0c6d5ce 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -118,7 +118,7 @@
}
sad_count = drm_edid_to_speaker_allocation(radeon_connector->edid, &sadb);
- if (sad_count < 0) {
+ if (sad_count <= 0) {
DRM_ERROR("Couldn't read Speaker Allocation Data Block: %d\n", sad_count);
return;
}
@@ -173,7 +173,7 @@
}
sad_count = drm_edid_to_sad(radeon_connector->edid, &sads);
- if (sad_count < 0) {
+ if (sad_count <= 0) {
DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
return;
}
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 11aab2a..f59a9e9 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -895,6 +895,10 @@
(rdev->pdev->device == 0x999C)) {
rdev->config.cayman.max_simds_per_se = 6;
rdev->config.cayman.max_backends_per_se = 2;
+ rdev->config.cayman.max_hw_contexts = 8;
+ rdev->config.cayman.sx_max_export_size = 256;
+ rdev->config.cayman.sx_max_export_pos_size = 64;
+ rdev->config.cayman.sx_max_export_smx_size = 192;
} else if ((rdev->pdev->device == 0x9903) ||
(rdev->pdev->device == 0x9904) ||
(rdev->pdev->device == 0x990A) ||
@@ -905,6 +909,10 @@
(rdev->pdev->device == 0x999D)) {
rdev->config.cayman.max_simds_per_se = 4;
rdev->config.cayman.max_backends_per_se = 2;
+ rdev->config.cayman.max_hw_contexts = 8;
+ rdev->config.cayman.sx_max_export_size = 256;
+ rdev->config.cayman.sx_max_export_pos_size = 64;
+ rdev->config.cayman.sx_max_export_smx_size = 192;
} else if ((rdev->pdev->device == 0x9919) ||
(rdev->pdev->device == 0x9990) ||
(rdev->pdev->device == 0x9991) ||
@@ -915,9 +923,17 @@
(rdev->pdev->device == 0x99A0)) {
rdev->config.cayman.max_simds_per_se = 3;
rdev->config.cayman.max_backends_per_se = 1;
+ rdev->config.cayman.max_hw_contexts = 4;
+ rdev->config.cayman.sx_max_export_size = 128;
+ rdev->config.cayman.sx_max_export_pos_size = 32;
+ rdev->config.cayman.sx_max_export_smx_size = 96;
} else {
rdev->config.cayman.max_simds_per_se = 2;
rdev->config.cayman.max_backends_per_se = 1;
+ rdev->config.cayman.max_hw_contexts = 4;
+ rdev->config.cayman.sx_max_export_size = 128;
+ rdev->config.cayman.sx_max_export_pos_size = 32;
+ rdev->config.cayman.sx_max_export_smx_size = 96;
}
rdev->config.cayman.max_texture_channel_caches = 2;
rdev->config.cayman.max_gprs = 256;
@@ -925,10 +941,6 @@
rdev->config.cayman.max_gs_threads = 32;
rdev->config.cayman.max_stack_entries = 512;
rdev->config.cayman.sx_num_of_sets = 8;
- rdev->config.cayman.sx_max_export_size = 256;
- rdev->config.cayman.sx_max_export_pos_size = 64;
- rdev->config.cayman.sx_max_export_smx_size = 192;
- rdev->config.cayman.max_hw_contexts = 8;
rdev->config.cayman.sq_num_cf_insts = 2;
rdev->config.cayman.sc_prim_fifo_size = 0x40;
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index b1f990d..45e1f44 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1940,7 +1940,7 @@
unsigned sc_earlyz_tile_fifo_size;
unsigned num_tile_pipes;
- unsigned num_backends_per_se;
+ unsigned backend_enable_mask;
unsigned backend_disable_mask_per_asic;
unsigned backend_map;
unsigned num_texture_channel_caches;
@@ -1970,7 +1970,7 @@
unsigned sc_earlyz_tile_fifo_size;
unsigned num_tile_pipes;
- unsigned num_backends_per_se;
+ unsigned backend_enable_mask;
unsigned backend_disable_mask_per_asic;
unsigned backend_map;
unsigned num_texture_channel_caches;
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index e354ce9..c0425bb 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -2021,7 +2021,7 @@
.hdmi_setmode = &evergreen_hdmi_setmode,
},
.copy = {
- .blit = NULL,
+ .blit = &cik_copy_cpdma,
.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
.dma = &cik_copy_dma,
.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
@@ -2122,7 +2122,7 @@
.hdmi_setmode = &evergreen_hdmi_setmode,
},
.copy = {
- .blit = NULL,
+ .blit = &cik_copy_cpdma,
.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
.dma = &cik_copy_dma,
.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index 9d302ea..485848f 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -33,6 +33,7 @@
bool atpx_detected;
/* handle for device - and atpx */
acpi_handle dhandle;
+ acpi_handle other_handle;
struct radeon_atpx atpx;
} radeon_atpx_priv;
@@ -451,9 +452,10 @@
return false;
status = acpi_get_handle(dhandle, "ATPX", &atpx_handle);
- if (ACPI_FAILURE(status))
+ if (ACPI_FAILURE(status)) {
+ radeon_atpx_priv.other_handle = dhandle;
return false;
-
+ }
radeon_atpx_priv.dhandle = dhandle;
radeon_atpx_priv.atpx.handle = atpx_handle;
return true;
@@ -530,6 +532,16 @@
printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n",
acpi_method_name);
radeon_atpx_priv.atpx_detected = true;
+ /*
+ * On some systems hotplug events are generated for the device
+ * being switched off when ATPX is executed. They cause ACPI
+ * hotplug to trigger and attempt to remove the device from
+ * the system, which causes it to break down. Prevent that from
+ * happening by setting the no_hotplug flag for the involved
+ * ACPI device objects.
+ */
+ acpi_bus_no_hotplug(radeon_atpx_priv.dhandle);
+ acpi_bus_no_hotplug(radeon_atpx_priv.other_handle);
return true;
}
return false;
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 9f5ff28..db39ea3 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -77,9 +77,10 @@
* 2.33.0 - Add SI tiling mode array query
* 2.34.0 - Add CIK tiling mode array query
* 2.35.0 - Add CIK macrotile mode array query
+ * 2.36.0 - Fix CIK DCE tiling setup
*/
#define KMS_DRIVER_MAJOR 2
-#define KMS_DRIVER_MINOR 35
+#define KMS_DRIVER_MINOR 36
#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);
@@ -508,15 +509,6 @@
#endif
};
-
-static void
-radeon_pci_shutdown(struct pci_dev *pdev)
-{
- struct drm_device *dev = pci_get_drvdata(pdev);
-
- radeon_driver_unload_kms(dev);
-}
-
static struct drm_driver kms_driver = {
.driver_features =
DRIVER_USE_AGP |
@@ -586,7 +578,6 @@
.probe = radeon_pci_probe,
.remove = radeon_pci_remove,
.driver.pm = &radeon_pm_ops,
- .shutdown = radeon_pci_shutdown,
};
static int __init radeon_init(void)
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 55d0b47..21d593c 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -461,6 +461,15 @@
case RADEON_INFO_SI_CP_DMA_COMPUTE:
*value = 1;
break;
+ case RADEON_INFO_SI_BACKEND_ENABLED_MASK:
+ if (rdev->family >= CHIP_BONAIRE) {
+ *value = rdev->config.cik.backend_enable_mask;
+ } else if (rdev->family >= CHIP_TAHITI) {
+ *value = rdev->config.si.backend_enable_mask;
+ } else {
+ DRM_DEBUG_KMS("BACKEND_ENABLED_MASK is si+ only!\n");
+ }
+ break;
default:
DRM_DEBUG_KMS("Invalid request %d\n", info->request);
return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 373d088..b9c0529 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -473,7 +473,7 @@
return -EINVAL;
}
- if ((start >> 28) != (end >> 28)) {
+ if ((start >> 28) != ((end - 1) >> 28)) {
DRM_ERROR("reloc %LX-%LX crossing 256MB boundary!\n",
start, end);
return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 1c56062..e7dab06 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -162,6 +162,16 @@
base = RREG32_MC(R_000100_MCCFG_FB_LOCATION);
base = G_000100_MC_FB_START(base) << 16;
rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev);
+ /* Some boards seem to be configured for 128MB of sideport memory,
+ * but really only have 64MB. Just skip the sideport and use
+ * UMA memory.
+ */
+ if (rdev->mc.igp_sideport_enabled &&
+ (rdev->mc.real_vram_size == (384 * 1024 * 1024))) {
+ base += 128 * 1024 * 1024;
+ rdev->mc.real_vram_size -= 128 * 1024 * 1024;
+ rdev->mc.mc_vram_size = rdev->mc.real_vram_size;
+ }
/* Use K8 direct mapping for fast fb access. */
rdev->fastfb_working = false;
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c
index 913b025..374499d 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.c
+++ b/drivers/gpu/drm/radeon/rv770_dpm.c
@@ -2328,6 +2328,12 @@
pi->mclk_ss = radeon_atombios_get_asic_ss_info(rdev, &ss,
ASIC_INTERNAL_MEMORY_SS, 0);
+ /* disable ss, causes hangs on some cayman boards */
+ if (rdev->family == CHIP_CAYMAN) {
+ pi->sclk_ss = false;
+ pi->mclk_ss = false;
+ }
+
if (pi->sclk_ss || pi->mclk_ss)
pi->dynamic_ss = true;
else
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index a36736d..85e1edf 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2811,7 +2811,7 @@
}
static u32 si_get_rb_disabled(struct radeon_device *rdev,
- u32 max_rb_num, u32 se_num,
+ u32 max_rb_num_per_se,
u32 sh_per_se)
{
u32 data, mask;
@@ -2825,14 +2825,14 @@
data >>= BACKEND_DISABLE_SHIFT;
- mask = si_create_bitmask(max_rb_num / se_num / sh_per_se);
+ mask = si_create_bitmask(max_rb_num_per_se / 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)
+ u32 max_rb_num_per_se)
{
int i, j;
u32 data, mask;
@@ -2842,19 +2842,21 @@
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);
+ data = si_get_rb_disabled(rdev, max_rb_num_per_se, 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++) {
+ for (i = 0; i < max_rb_num_per_se * se_num; i++) {
if (!(disabled_rbs & mask))
enabled_rbs |= mask;
mask <<= 1;
}
+ rdev->config.si.backend_enable_mask = enabled_rbs;
+
for (i = 0; i < se_num; i++) {
si_select_se_sh(rdev, i, 0xffffffff);
data = 0;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 15b86a9..4061521 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -353,7 +353,8 @@
* Don't move nonexistent data. Clear destination instead.
*/
if (old_iomap == NULL &&
- (ttm == NULL || ttm->state == tt_unpopulated)) {
+ (ttm == NULL || (ttm->state == tt_unpopulated &&
+ !(ttm->page_flags & TTM_PAGE_FLAG_SWAPPED)))) {
memset_io(new_iomap, 0, new_mem->num_pages*PAGE_SIZE);
goto out2;
}
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index b249ab9..6440eea 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -169,9 +169,9 @@
}
page_offset = ((address - vma->vm_start) >> PAGE_SHIFT) +
- drm_vma_node_start(&bo->vma_node) - vma->vm_pgoff;
- page_last = vma_pages(vma) +
- drm_vma_node_start(&bo->vma_node) - vma->vm_pgoff;
+ vma->vm_pgoff - drm_vma_node_start(&bo->vma_node);
+ page_last = vma_pages(vma) + vma->vm_pgoff -
+ drm_vma_node_start(&bo->vma_node);
if (unlikely(page_offset >= bo->num_pages)) {
retval = VM_FAULT_SIGBUS;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index a51f48e..45d5b5a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -68,6 +68,9 @@
SVGA_FIFO_3D_HWVERSION));
break;
}
+ case DRM_VMW_PARAM_MAX_SURF_MEMORY:
+ param->value = dev_priv->memory_size;
+ break;
default:
DRM_ERROR("Illegal vmwgfx get param request: %d\n",
param->param);
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index efec405..6c0e045 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -123,7 +123,7 @@
* which is also the index into the MWAIT hint array.
* Thus C0 is a dummy.
*/
-static struct cpuidle_state nehalem_cstates[] __initdata = {
+static struct cpuidle_state nehalem_cstates[] = {
{
.name = "C1-NHM",
.desc = "MWAIT 0x00",
@@ -156,7 +156,7 @@
.enter = NULL }
};
-static struct cpuidle_state snb_cstates[] __initdata = {
+static struct cpuidle_state snb_cstates[] = {
{
.name = "C1-SNB",
.desc = "MWAIT 0x00",
@@ -196,7 +196,7 @@
.enter = NULL }
};
-static struct cpuidle_state ivb_cstates[] __initdata = {
+static struct cpuidle_state ivb_cstates[] = {
{
.name = "C1-IVB",
.desc = "MWAIT 0x00",
@@ -236,7 +236,7 @@
.enter = NULL }
};
-static struct cpuidle_state hsw_cstates[] __initdata = {
+static struct cpuidle_state hsw_cstates[] = {
{
.name = "C1-HSW",
.desc = "MWAIT 0x00",
@@ -297,7 +297,7 @@
.enter = NULL }
};
-static struct cpuidle_state atom_cstates[] __initdata = {
+static struct cpuidle_state atom_cstates[] = {
{
.name = "C1E-ATM",
.desc = "MWAIT 0x00",
@@ -329,7 +329,7 @@
{
.enter = NULL }
};
-static struct cpuidle_state avn_cstates[] __initdata = {
+static struct cpuidle_state avn_cstates[] = {
{
.name = "C1-AVN",
.desc = "MWAIT 0x00",
@@ -344,6 +344,8 @@
.exit_latency = 15,
.target_residency = 45,
.enter = &intel_idle },
+ {
+ .enter = NULL }
};
/**
diff --git a/drivers/iio/adc/ad7887.c b/drivers/iio/adc/ad7887.c
index acb7f90..749a6ca 100644
--- a/drivers/iio/adc/ad7887.c
+++ b/drivers/iio/adc/ad7887.c
@@ -200,7 +200,13 @@
.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
.address = 1,
.scan_index = 1,
- .scan_type = IIO_ST('u', 12, 16, 0),
+ .scan_type = {
+ .sign = 'u',
+ .realbits = 12,
+ .storagebits = 16,
+ .shift = 0,
+ .endianness = IIO_BE,
+ },
},
.channel[1] = {
.type = IIO_VOLTAGE,
@@ -210,7 +216,13 @@
.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
.address = 0,
.scan_index = 0,
- .scan_type = IIO_ST('u', 12, 16, 0),
+ .scan_type = {
+ .sign = 'u',
+ .realbits = 12,
+ .storagebits = 16,
+ .shift = 0,
+ .endianness = IIO_BE,
+ },
},
.channel[2] = IIO_CHAN_SOFT_TIMESTAMP(2),
.int_vref_mv = 2500,
diff --git a/drivers/iio/imu/adis16400_core.c b/drivers/iio/imu/adis16400_core.c
index 3fb7757..368660d 100644
--- a/drivers/iio/imu/adis16400_core.c
+++ b/drivers/iio/imu/adis16400_core.c
@@ -651,7 +651,12 @@
.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
.address = ADIS16448_BARO_OUT,
.scan_index = ADIS16400_SCAN_BARO,
- .scan_type = IIO_ST('s', 16, 16, 0),
+ .scan_type = {
+ .sign = 's',
+ .realbits = 16,
+ .storagebits = 16,
+ .endianness = IIO_BE,
+ },
},
ADIS16400_TEMP_CHAN(ADIS16448_TEMP_OUT, 12),
IIO_CHAN_SOFT_TIMESTAMP(11)
diff --git a/drivers/iio/light/cm36651.c b/drivers/iio/light/cm36651.c
index 21df571..0922e39 100644
--- a/drivers/iio/light/cm36651.c
+++ b/drivers/iio/light/cm36651.c
@@ -387,7 +387,7 @@
return -EINVAL;
}
- return IIO_VAL_INT_PLUS_MICRO;
+ return IIO_VAL_INT;
}
static int cm36651_write_int_time(struct cm36651_data *cm36651,
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index c47c203..0717940 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -181,9 +181,16 @@
static void rem_ref(struct iw_cm_id *cm_id)
{
struct iwcm_id_private *cm_id_priv;
+ int cb_destroy;
+
cm_id_priv = container_of(cm_id, struct iwcm_id_private, id);
- if (iwcm_deref_id(cm_id_priv) &&
- test_bit(IWCM_F_CALLBACK_DESTROY, &cm_id_priv->flags)) {
+
+ /*
+ * Test bit before deref in case the cm_id gets freed on another
+ * thread.
+ */
+ cb_destroy = test_bit(IWCM_F_CALLBACK_DESTROY, &cm_id_priv->flags);
+ if (iwcm_deref_id(cm_id_priv) && cb_destroy) {
BUG_ON(!list_empty(&cm_id_priv->work_list));
free_cm_id(cm_id_priv);
}
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index bdc842e..a283274 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -49,12 +49,20 @@
#define INIT_UDATA(udata, ibuf, obuf, ilen, olen) \
do { \
- (udata)->inbuf = (void __user *) (ibuf); \
+ (udata)->inbuf = (const void __user *) (ibuf); \
(udata)->outbuf = (void __user *) (obuf); \
(udata)->inlen = (ilen); \
(udata)->outlen = (olen); \
} while (0)
+#define INIT_UDATA_BUF_OR_NULL(udata, ibuf, obuf, ilen, olen) \
+ do { \
+ (udata)->inbuf = (ilen) ? (const void __user *) (ibuf) : NULL; \
+ (udata)->outbuf = (olen) ? (void __user *) (obuf) : NULL; \
+ (udata)->inlen = (ilen); \
+ (udata)->outlen = (olen); \
+ } while (0)
+
/*
* Our lifetime rules for these structs are the following:
*
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 65f6e7d..f1cc838 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2593,6 +2593,9 @@
static int kern_spec_to_ib_spec(struct ib_uverbs_flow_spec *kern_spec,
union ib_flow_spec *ib_spec)
{
+ if (kern_spec->reserved)
+ return -EINVAL;
+
ib_spec->type = kern_spec->type;
switch (ib_spec->type) {
@@ -2646,6 +2649,9 @@
void *ib_spec;
int i;
+ if (ucore->inlen < sizeof(cmd))
+ return -EINVAL;
+
if (ucore->outlen < sizeof(resp))
return -ENOSPC;
@@ -2671,6 +2677,10 @@
(cmd.flow_attr.num_of_specs * sizeof(struct ib_uverbs_flow_spec)))
return -EINVAL;
+ if (cmd.flow_attr.reserved[0] ||
+ cmd.flow_attr.reserved[1])
+ return -EINVAL;
+
if (cmd.flow_attr.num_of_specs) {
kern_flow_attr = kmalloc(sizeof(*kern_flow_attr) + cmd.flow_attr.size,
GFP_KERNEL);
@@ -2731,6 +2741,7 @@
if (cmd.flow_attr.size || (i != flow_attr->num_of_specs)) {
pr_warn("create flow failed, flow %d: %d bytes left from uverb cmd\n",
i, cmd.flow_attr.size);
+ err = -EINVAL;
goto err_free;
}
flow_id = ib_create_flow(qp, flow_attr, IB_FLOW_DOMAIN_USER);
@@ -2791,10 +2802,16 @@
struct ib_uobject *uobj;
int ret;
+ if (ucore->inlen < sizeof(cmd))
+ return -EINVAL;
+
ret = ib_copy_from_udata(&cmd, ucore, sizeof(cmd));
if (ret)
return ret;
+ if (cmd.comp_mask)
+ return -EINVAL;
+
uobj = idr_write_uobj(&ib_uverbs_rule_idr, cmd.flow_handle,
file->ucontext);
if (!uobj)
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 3438694..08219fb 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -668,25 +668,30 @@
if ((hdr.in_words + ex_hdr.provider_in_words) * 8 != count)
return -EINVAL;
+ if (ex_hdr.cmd_hdr_reserved)
+ return -EINVAL;
+
if (ex_hdr.response) {
if (!hdr.out_words && !ex_hdr.provider_out_words)
return -EINVAL;
+
+ if (!access_ok(VERIFY_WRITE,
+ (void __user *) (unsigned long) ex_hdr.response,
+ (hdr.out_words + ex_hdr.provider_out_words) * 8))
+ return -EFAULT;
} else {
if (hdr.out_words || ex_hdr.provider_out_words)
return -EINVAL;
}
- INIT_UDATA(&ucore,
- (hdr.in_words) ? buf : 0,
- (unsigned long)ex_hdr.response,
- hdr.in_words * 8,
- hdr.out_words * 8);
+ INIT_UDATA_BUF_OR_NULL(&ucore, buf, (unsigned long) ex_hdr.response,
+ hdr.in_words * 8, hdr.out_words * 8);
- INIT_UDATA(&uhw,
- (ex_hdr.provider_in_words) ? buf + ucore.inlen : 0,
- (ex_hdr.provider_out_words) ? (unsigned long)ex_hdr.response + ucore.outlen : 0,
- ex_hdr.provider_in_words * 8,
- ex_hdr.provider_out_words * 8);
+ INIT_UDATA_BUF_OR_NULL(&uhw,
+ buf + ucore.inlen,
+ (unsigned long) ex_hdr.response + ucore.outlen,
+ ex_hdr.provider_in_words * 8,
+ ex_hdr.provider_out_words * 8);
err = uverbs_ex_cmd_table[command](file,
&ucore,
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 12fef76..4512687 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -524,50 +524,6 @@
return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
}
-#define VLAN_NONE 0xfff
-#define FILTER_SEL_VLAN_NONE 0xffff
-#define FILTER_SEL_WIDTH_P_FC (3+1) /* port uses 3 bits, FCoE one bit */
-#define FILTER_SEL_WIDTH_VIN_P_FC \
- (6 + 7 + FILTER_SEL_WIDTH_P_FC) /* 6 bits are unused, VF uses 7 bits*/
-#define FILTER_SEL_WIDTH_TAG_P_FC \
- (3 + FILTER_SEL_WIDTH_VIN_P_FC) /* PF uses 3 bits */
-#define FILTER_SEL_WIDTH_VLD_TAG_P_FC (1 + FILTER_SEL_WIDTH_TAG_P_FC)
-
-static unsigned int select_ntuple(struct c4iw_dev *dev, struct dst_entry *dst,
- struct l2t_entry *l2t)
-{
- unsigned int ntuple = 0;
- u32 viid;
-
- switch (dev->rdev.lldi.filt_mode) {
-
- /* default filter mode */
- case HW_TPL_FR_MT_PR_IV_P_FC:
- if (l2t->vlan == VLAN_NONE)
- ntuple |= FILTER_SEL_VLAN_NONE << FILTER_SEL_WIDTH_P_FC;
- else {
- ntuple |= l2t->vlan << FILTER_SEL_WIDTH_P_FC;
- ntuple |= 1 << FILTER_SEL_WIDTH_TAG_P_FC;
- }
- ntuple |= l2t->lport << S_PORT | IPPROTO_TCP <<
- FILTER_SEL_WIDTH_VLD_TAG_P_FC;
- break;
- case HW_TPL_FR_MT_PR_OV_P_FC: {
- viid = cxgb4_port_viid(l2t->neigh->dev);
-
- ntuple |= FW_VIID_VIN_GET(viid) << FILTER_SEL_WIDTH_P_FC;
- ntuple |= FW_VIID_PFN_GET(viid) << FILTER_SEL_WIDTH_VIN_P_FC;
- ntuple |= FW_VIID_VIVLD_GET(viid) << FILTER_SEL_WIDTH_TAG_P_FC;
- ntuple |= l2t->lport << S_PORT | IPPROTO_TCP <<
- FILTER_SEL_WIDTH_VLD_TAG_P_FC;
- break;
- }
- default:
- break;
- }
- return ntuple;
-}
-
static int send_connect(struct c4iw_ep *ep)
{
struct cpl_act_open_req *req;
@@ -641,8 +597,9 @@
req->local_ip = la->sin_addr.s_addr;
req->peer_ip = ra->sin_addr.s_addr;
req->opt0 = cpu_to_be64(opt0);
- req->params = cpu_to_be32(select_ntuple(ep->com.dev,
- ep->dst, ep->l2t));
+ req->params = cpu_to_be32(cxgb4_select_ntuple(
+ ep->com.dev->rdev.lldi.ports[0],
+ ep->l2t));
req->opt2 = cpu_to_be32(opt2);
} else {
req6 = (struct cpl_act_open_req6 *)skb_put(skb, wrlen);
@@ -662,9 +619,9 @@
req6->peer_ip_lo = *((__be64 *)
(ra6->sin6_addr.s6_addr + 8));
req6->opt0 = cpu_to_be64(opt0);
- req6->params = cpu_to_be32(
- select_ntuple(ep->com.dev, ep->dst,
- ep->l2t));
+ req6->params = cpu_to_be32(cxgb4_select_ntuple(
+ ep->com.dev->rdev.lldi.ports[0],
+ ep->l2t));
req6->opt2 = cpu_to_be32(opt2);
}
} else {
@@ -681,8 +638,9 @@
t5_req->peer_ip = ra->sin_addr.s_addr;
t5_req->opt0 = cpu_to_be64(opt0);
t5_req->params = cpu_to_be64(V_FILTER_TUPLE(
- select_ntuple(ep->com.dev,
- ep->dst, ep->l2t)));
+ cxgb4_select_ntuple(
+ ep->com.dev->rdev.lldi.ports[0],
+ ep->l2t)));
t5_req->opt2 = cpu_to_be32(opt2);
} else {
t5_req6 = (struct cpl_t5_act_open_req6 *)
@@ -703,7 +661,9 @@
(ra6->sin6_addr.s6_addr + 8));
t5_req6->opt0 = cpu_to_be64(opt0);
t5_req6->params = (__force __be64)cpu_to_be32(
- select_ntuple(ep->com.dev, ep->dst, ep->l2t));
+ cxgb4_select_ntuple(
+ ep->com.dev->rdev.lldi.ports[0],
+ ep->l2t));
t5_req6->opt2 = cpu_to_be32(opt2);
}
}
@@ -1630,7 +1590,8 @@
memset(req, 0, sizeof(*req));
req->op_compl = htonl(V_WR_OP(FW_OFLD_CONNECTION_WR));
req->len16_pkd = htonl(FW_WR_LEN16(DIV_ROUND_UP(sizeof(*req), 16)));
- req->le.filter = cpu_to_be32(select_ntuple(ep->com.dev, ep->dst,
+ req->le.filter = cpu_to_be32(cxgb4_select_ntuple(
+ ep->com.dev->rdev.lldi.ports[0],
ep->l2t));
sin = (struct sockaddr_in *)&ep->com.local_addr;
req->le.lport = sin->sin_port;
@@ -2938,7 +2899,8 @@
/*
* Allocate a server TID.
*/
- if (dev->rdev.lldi.enable_fw_ofld_conn)
+ if (dev->rdev.lldi.enable_fw_ofld_conn &&
+ ep->com.local_addr.ss_family == AF_INET)
ep->stid = cxgb4_alloc_sftid(dev->rdev.lldi.tids,
cm_id->local_addr.ss_family, ep);
else
@@ -3323,9 +3285,7 @@
/*
* Calculate the server tid from filter hit index from cpl_rx_pkt.
*/
- stid = (__force int) cpu_to_be32((__force u32) rss->hash_val)
- - dev->rdev.lldi.tids->sftid_base
- + dev->rdev.lldi.tids->nstids;
+ stid = (__force int) cpu_to_be32((__force u32) rss->hash_val);
lep = (struct c4iw_ep *)lookup_stid(dev->rdev.lldi.tids, stid);
if (!lep) {
@@ -3397,7 +3357,9 @@
window = (__force u16) htons((__force u16)tcph->window);
/* Calcuate filter portion for LE region. */
- filter = (__force unsigned int) cpu_to_be32(select_ntuple(dev, dst, e));
+ filter = (__force unsigned int) cpu_to_be32(cxgb4_select_ntuple(
+ dev->rdev.lldi.ports[0],
+ e));
/*
* Synthesize the cpl_pass_accept_req. We have everything except the
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 4cb8eb2..84e4500 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -173,7 +173,7 @@
return ret;
}
-int _c4iw_write_mem_dma(struct c4iw_rdev *rdev, u32 addr, u32 len, void *data)
+static int _c4iw_write_mem_dma(struct c4iw_rdev *rdev, u32 addr, u32 len, void *data)
{
u32 remain = len;
u32 dmalen;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
index c29b5c8..cdc7df4 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
@@ -31,6 +31,7 @@
*/
#include <linux/netdevice.h>
+#include <linux/if_arp.h> /* For ARPHRD_xxx */
#include <linux/module.h>
#include <net/rtnetlink.h>
#include "ipoib.h"
@@ -103,7 +104,7 @@
return -EINVAL;
pdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
- if (!pdev)
+ if (!pdev || pdev->type != ARPHRD_INFINIBAND)
return -ENODEV;
ppriv = netdev_priv(pdev);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 6be57c3..9804fca 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -207,7 +207,9 @@
isert_conn->conn_rx_descs = NULL;
}
+static void isert_cq_tx_work(struct work_struct *);
static void isert_cq_tx_callback(struct ib_cq *, void *);
+static void isert_cq_rx_work(struct work_struct *);
static void isert_cq_rx_callback(struct ib_cq *, void *);
static int
@@ -259,26 +261,36 @@
cq_desc[i].device = device;
cq_desc[i].cq_index = i;
+ INIT_WORK(&cq_desc[i].cq_rx_work, isert_cq_rx_work);
device->dev_rx_cq[i] = ib_create_cq(device->ib_device,
isert_cq_rx_callback,
isert_cq_event_callback,
(void *)&cq_desc[i],
ISER_MAX_RX_CQ_LEN, i);
- if (IS_ERR(device->dev_rx_cq[i]))
+ if (IS_ERR(device->dev_rx_cq[i])) {
+ ret = PTR_ERR(device->dev_rx_cq[i]);
+ device->dev_rx_cq[i] = NULL;
goto out_cq;
+ }
+ INIT_WORK(&cq_desc[i].cq_tx_work, isert_cq_tx_work);
device->dev_tx_cq[i] = ib_create_cq(device->ib_device,
isert_cq_tx_callback,
isert_cq_event_callback,
(void *)&cq_desc[i],
ISER_MAX_TX_CQ_LEN, i);
- if (IS_ERR(device->dev_tx_cq[i]))
+ if (IS_ERR(device->dev_tx_cq[i])) {
+ ret = PTR_ERR(device->dev_tx_cq[i]);
+ device->dev_tx_cq[i] = NULL;
+ goto out_cq;
+ }
+
+ ret = ib_req_notify_cq(device->dev_rx_cq[i], IB_CQ_NEXT_COMP);
+ if (ret)
goto out_cq;
- if (ib_req_notify_cq(device->dev_rx_cq[i], IB_CQ_NEXT_COMP))
- goto out_cq;
-
- if (ib_req_notify_cq(device->dev_tx_cq[i], IB_CQ_NEXT_COMP))
+ ret = ib_req_notify_cq(device->dev_tx_cq[i], IB_CQ_NEXT_COMP);
+ if (ret)
goto out_cq;
}
@@ -1724,7 +1736,6 @@
{
struct isert_cq_desc *cq_desc = (struct isert_cq_desc *)context;
- INIT_WORK(&cq_desc->cq_tx_work, isert_cq_tx_work);
queue_work(isert_comp_wq, &cq_desc->cq_tx_work);
}
@@ -1768,7 +1779,6 @@
{
struct isert_cq_desc *cq_desc = (struct isert_cq_desc *)context;
- INIT_WORK(&cq_desc->cq_rx_work, isert_cq_rx_work);
queue_work(isert_rx_wq, &cq_desc->cq_rx_work);
}
diff --git a/drivers/input/input.c b/drivers/input/input.c
index 846ccdd..d2965e4 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -1871,6 +1871,10 @@
break;
case EV_ABS:
+ input_alloc_absinfo(dev);
+ if (!dev->absinfo)
+ return;
+
__set_bit(code, dev->absbit);
break;
diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c
index 75762d6..aa127ba 100644
--- a/drivers/input/touchscreen/zforce_ts.c
+++ b/drivers/input/touchscreen/zforce_ts.c
@@ -455,7 +455,18 @@
}
}
-static irqreturn_t zforce_interrupt(int irq, void *dev_id)
+static irqreturn_t zforce_irq(int irq, void *dev_id)
+{
+ struct zforce_ts *ts = dev_id;
+ struct i2c_client *client = ts->client;
+
+ if (ts->suspended && device_may_wakeup(&client->dev))
+ pm_wakeup_event(&client->dev, 500);
+
+ return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t zforce_irq_thread(int irq, void *dev_id)
{
struct zforce_ts *ts = dev_id;
struct i2c_client *client = ts->client;
@@ -465,12 +476,10 @@
u8 *payload;
/*
- * When suspended, emit a wakeup signal if necessary and return.
+ * When still suspended, return.
* Due to the level-interrupt we will get re-triggered later.
*/
if (ts->suspended) {
- if (device_may_wakeup(&client->dev))
- pm_wakeup_event(&client->dev, 500);
msleep(20);
return IRQ_HANDLED;
}
@@ -763,8 +772,8 @@
* Therefore we can trigger the interrupt anytime it is low and do
* not need to limit it to the interrupt edge.
*/
- ret = devm_request_threaded_irq(&client->dev, client->irq, NULL,
- zforce_interrupt,
+ ret = devm_request_threaded_irq(&client->dev, client->irq,
+ zforce_irq, zforce_irq_thread,
IRQF_TRIGGER_LOW | IRQF_ONESHOT,
input_dev->name, ts);
if (ret) {
diff --git a/drivers/irqchip/irq-renesas-intc-irqpin.c b/drivers/irqchip/irq-renesas-intc-irqpin.c
index 82cec63..3ee78f0 100644
--- a/drivers/irqchip/irq-renesas-intc-irqpin.c
+++ b/drivers/irqchip/irq-renesas-intc-irqpin.c
@@ -149,8 +149,9 @@
static void intc_irqpin_mask_unmask_prio(struct intc_irqpin_priv *p,
int irq, int do_mask)
{
- int bitfield_width = 4; /* PRIO assumed to have fixed bitfield width */
- int shift = (7 - irq) * bitfield_width; /* PRIO assumed to be 32-bit */
+ /* The PRIO register is assumed to be 32-bit with fixed 4-bit fields. */
+ int bitfield_width = 4;
+ int shift = 32 - (irq + 1) * bitfield_width;
intc_irqpin_read_modify_write(p, INTC_IRQPIN_REG_PRIO,
shift, bitfield_width,
@@ -159,8 +160,9 @@
static int intc_irqpin_set_sense(struct intc_irqpin_priv *p, int irq, int value)
{
+ /* The SENSE register is assumed to be 32-bit. */
int bitfield_width = p->config.sense_bitfield_width;
- int shift = (7 - irq) * bitfield_width; /* SENSE assumed to be 32-bit */
+ int shift = 32 - (irq + 1) * bitfield_width;
dev_dbg(&p->pdev->dev, "sense irq = %d, mode = %d\n", irq, value);
diff --git a/drivers/isdn/hisax/hfc_pci.c b/drivers/isdn/hisax/hfc_pci.c
index 497bd02..4a48255 100644
--- a/drivers/isdn/hisax/hfc_pci.c
+++ b/drivers/isdn/hisax/hfc_pci.c
@@ -1643,10 +1643,6 @@
int i;
struct pci_dev *tmp_hfcpci = NULL;
-#ifdef __BIG_ENDIAN
-#error "not running on big endian machines now"
-#endif
-
strcpy(tmp, hfcpci_revision);
printk(KERN_INFO "HiSax: HFC-PCI driver Rev. %s\n", HiSax_getrev(tmp));
diff --git a/drivers/isdn/hisax/telespci.c b/drivers/isdn/hisax/telespci.c
index f6ab63a..33eeb46 100644
--- a/drivers/isdn/hisax/telespci.c
+++ b/drivers/isdn/hisax/telespci.c
@@ -290,10 +290,6 @@
struct IsdnCardState *cs = card->cs;
char tmp[64];
-#ifdef __BIG_ENDIAN
-#error "not running on big endian machines now"
-#endif
-
strcpy(tmp, telespci_revision);
printk(KERN_INFO "HiSax: Teles/PCI driver Rev. %s\n", HiSax_getrev(tmp));
if (cs->typ != ISDN_CTYPE_TELESPCI)
diff --git a/drivers/leds/leds-lp5521.c b/drivers/leds/leds-lp5521.c
index 0518835..a97263e 100644
--- a/drivers/leds/leds-lp5521.c
+++ b/drivers/leds/leds-lp5521.c
@@ -244,18 +244,12 @@
if (i % 2)
goto err;
- mutex_lock(&chip->lock);
-
for (i = 0; i < LP5521_PROGRAM_LENGTH; i++) {
ret = lp55xx_write(chip, addr[idx] + i, pattern[i]);
- if (ret) {
- mutex_unlock(&chip->lock);
+ if (ret)
return -EINVAL;
- }
}
- mutex_unlock(&chip->lock);
-
return size;
err:
@@ -427,15 +421,17 @@
{
struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
struct lp55xx_chip *chip = led->chip;
+ int ret;
mutex_lock(&chip->lock);
chip->engine_idx = nr;
lp5521_load_engine(chip);
+ ret = lp5521_update_program_memory(chip, buf, len);
mutex_unlock(&chip->lock);
- return lp5521_update_program_memory(chip, buf, len);
+ return ret;
}
store_load(1)
store_load(2)
diff --git a/drivers/leds/leds-lp5523.c b/drivers/leds/leds-lp5523.c
index 6b553d9..fd9ab5f 100644
--- a/drivers/leds/leds-lp5523.c
+++ b/drivers/leds/leds-lp5523.c
@@ -337,18 +337,12 @@
if (i % 2)
goto err;
- mutex_lock(&chip->lock);
-
for (i = 0; i < LP5523_PROGRAM_LENGTH; i++) {
ret = lp55xx_write(chip, LP5523_REG_PROG_MEM + i, pattern[i]);
- if (ret) {
- mutex_unlock(&chip->lock);
+ if (ret)
return -EINVAL;
- }
}
- mutex_unlock(&chip->lock);
-
return size;
err:
@@ -548,15 +542,17 @@
{
struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
struct lp55xx_chip *chip = led->chip;
+ int ret;
mutex_lock(&chip->lock);
chip->engine_idx = nr;
lp5523_load_engine_and_select_page(chip);
+ ret = lp5523_update_program_memory(chip, buf, len);
mutex_unlock(&chip->lock);
- return lp5523_update_program_memory(chip, buf, len);
+ return ret;
}
store_load(1)
store_load(2)
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 2b46bf1..4c9852d 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -421,9 +421,11 @@
if (watermark <= WATERMARK_METADATA) {
SET_GC_MARK(b, GC_MARK_METADATA);
+ SET_GC_MOVE(b, 0);
b->prio = BTREE_PRIO;
} else {
SET_GC_MARK(b, GC_MARK_RECLAIMABLE);
+ SET_GC_MOVE(b, 0);
b->prio = INITIAL_PRIO;
}
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 4beb55a..754f4317 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -197,7 +197,7 @@
uint8_t disk_gen;
uint8_t last_gc; /* Most out of date gen in the btree */
uint8_t gc_gen;
- uint16_t gc_mark;
+ uint16_t gc_mark; /* Bitfield used by GC. See below for field */
};
/*
@@ -209,7 +209,8 @@
#define GC_MARK_RECLAIMABLE 0
#define GC_MARK_DIRTY 1
#define GC_MARK_METADATA 2
-BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, 14);
+BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, 13);
+BITMASK(GC_MOVE, struct bucket, gc_mark, 15, 1);
#include "journal.h"
#include "stats.h"
@@ -372,14 +373,14 @@
unsigned char writeback_percent;
unsigned writeback_delay;
- int writeback_rate_change;
- int64_t writeback_rate_derivative;
uint64_t writeback_rate_target;
+ int64_t writeback_rate_proportional;
+ int64_t writeback_rate_derivative;
+ int64_t writeback_rate_change;
unsigned writeback_rate_update_seconds;
unsigned writeback_rate_d_term;
unsigned writeback_rate_p_term_inverse;
- unsigned writeback_rate_d_smooth;
};
enum alloc_watermarks {
@@ -445,7 +446,6 @@
* call prio_write() to keep gens from wrapping.
*/
uint8_t need_save_prio;
- unsigned gc_move_threshold;
/*
* If nonzero, we know we aren't going to find any buckets to invalidate
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 5e2765a..31bb53f 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1561,6 +1561,28 @@
SET_GC_MARK(PTR_BUCKET(c, &c->uuid_bucket, i),
GC_MARK_METADATA);
+ /* don't reclaim buckets to which writeback keys point */
+ rcu_read_lock();
+ for (i = 0; i < c->nr_uuids; i++) {
+ struct bcache_device *d = c->devices[i];
+ struct cached_dev *dc;
+ struct keybuf_key *w, *n;
+ unsigned j;
+
+ if (!d || UUID_FLASH_ONLY(&c->uuids[i]))
+ continue;
+ dc = container_of(d, struct cached_dev, disk);
+
+ spin_lock(&dc->writeback_keys.lock);
+ rbtree_postorder_for_each_entry_safe(w, n,
+ &dc->writeback_keys.keys, node)
+ for (j = 0; j < KEY_PTRS(&w->key); j++)
+ SET_GC_MARK(PTR_BUCKET(c, &w->key, j),
+ GC_MARK_DIRTY);
+ spin_unlock(&dc->writeback_keys.lock);
+ }
+ rcu_read_unlock();
+
for_each_cache(ca, c, i) {
uint64_t *i;
@@ -1817,7 +1839,8 @@
if (KEY_START(k) > KEY_START(insert) + sectors_found)
goto check_failed;
- if (KEY_PTRS(replace_key) != KEY_PTRS(k))
+ if (KEY_PTRS(k) != KEY_PTRS(replace_key) ||
+ KEY_DIRTY(k) != KEY_DIRTY(replace_key))
goto check_failed;
/* skip past gen */
@@ -2217,7 +2240,7 @@
struct bkey *replace_key;
};
-int btree_insert_fn(struct btree_op *b_op, struct btree *b)
+static int btree_insert_fn(struct btree_op *b_op, struct btree *b)
{
struct btree_insert_op *op = container_of(b_op,
struct btree_insert_op, op);
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index 7c1275e..f2f0998 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -25,10 +25,9 @@
unsigned i;
for (i = 0; i < KEY_PTRS(k); i++) {
- struct cache *ca = PTR_CACHE(c, k, i);
struct bucket *g = PTR_BUCKET(c, k, i);
- if (GC_SECTORS_USED(g) < ca->gc_move_threshold)
+ if (GC_MOVE(g))
return true;
}
@@ -65,11 +64,16 @@
static void read_moving_endio(struct bio *bio, int error)
{
+ struct bbio *b = container_of(bio, struct bbio, bio);
struct moving_io *io = container_of(bio->bi_private,
struct moving_io, cl);
if (error)
io->op.error = error;
+ else if (!KEY_DIRTY(&b->key) &&
+ ptr_stale(io->op.c, &b->key, 0)) {
+ io->op.error = -EINTR;
+ }
bch_bbio_endio(io->op.c, bio, error, "reading data to move");
}
@@ -141,6 +145,11 @@
if (!w)
break;
+ if (ptr_stale(c, &w->key, 0)) {
+ bch_keybuf_del(&c->moving_gc_keys, w);
+ continue;
+ }
+
io = kzalloc(sizeof(struct moving_io) + sizeof(struct bio_vec)
* DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS),
GFP_KERNEL);
@@ -184,7 +193,8 @@
static unsigned bucket_heap_top(struct cache *ca)
{
- return GC_SECTORS_USED(heap_peek(&ca->heap));
+ struct bucket *b;
+ return (b = heap_peek(&ca->heap)) ? GC_SECTORS_USED(b) : 0;
}
void bch_moving_gc(struct cache_set *c)
@@ -226,9 +236,8 @@
sectors_to_move -= GC_SECTORS_USED(b);
}
- ca->gc_move_threshold = bucket_heap_top(ca);
-
- pr_debug("threshold %u", ca->gc_move_threshold);
+ while (heap_pop(&ca->heap, b, bucket_cmp))
+ SET_GC_MOVE(b, 1);
}
mutex_unlock(&c->bucket_lock);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index dec15cd..c57bfa0 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1676,7 +1676,7 @@
static bool can_attach_cache(struct cache *ca, struct cache_set *c)
{
return ca->sb.block_size == c->sb.block_size &&
- ca->sb.bucket_size == c->sb.block_size &&
+ ca->sb.bucket_size == c->sb.bucket_size &&
ca->sb.nr_in_set == c->sb.nr_in_set;
}
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 80d4c2b..a1f8561 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -83,7 +83,6 @@
rw_attribute(writeback_rate_update_seconds);
rw_attribute(writeback_rate_d_term);
rw_attribute(writeback_rate_p_term_inverse);
-rw_attribute(writeback_rate_d_smooth);
read_attribute(writeback_rate_debug);
read_attribute(stripe_size);
@@ -129,31 +128,41 @@
var_printf(writeback_running, "%i");
var_print(writeback_delay);
var_print(writeback_percent);
- sysfs_print(writeback_rate, dc->writeback_rate.rate);
+ sysfs_hprint(writeback_rate, dc->writeback_rate.rate << 9);
var_print(writeback_rate_update_seconds);
var_print(writeback_rate_d_term);
var_print(writeback_rate_p_term_inverse);
- var_print(writeback_rate_d_smooth);
if (attr == &sysfs_writeback_rate_debug) {
+ char rate[20];
char dirty[20];
- char derivative[20];
char target[20];
- bch_hprint(dirty,
- bcache_dev_sectors_dirty(&dc->disk) << 9);
- bch_hprint(derivative, dc->writeback_rate_derivative << 9);
+ char proportional[20];
+ char derivative[20];
+ char change[20];
+ s64 next_io;
+
+ bch_hprint(rate, dc->writeback_rate.rate << 9);
+ bch_hprint(dirty, bcache_dev_sectors_dirty(&dc->disk) << 9);
bch_hprint(target, dc->writeback_rate_target << 9);
+ bch_hprint(proportional,dc->writeback_rate_proportional << 9);
+ bch_hprint(derivative, dc->writeback_rate_derivative << 9);
+ bch_hprint(change, dc->writeback_rate_change << 9);
+
+ next_io = div64_s64(dc->writeback_rate.next - local_clock(),
+ NSEC_PER_MSEC);
return sprintf(buf,
- "rate:\t\t%u\n"
- "change:\t\t%i\n"
+ "rate:\t\t%s/sec\n"
"dirty:\t\t%s\n"
+ "target:\t\t%s\n"
+ "proportional:\t%s\n"
"derivative:\t%s\n"
- "target:\t\t%s\n",
- dc->writeback_rate.rate,
- dc->writeback_rate_change,
- dirty, derivative, target);
+ "change:\t\t%s/sec\n"
+ "next io:\t%llims\n",
+ rate, dirty, target, proportional,
+ derivative, change, next_io);
}
sysfs_hprint(dirty_data,
@@ -189,6 +198,7 @@
struct kobj_uevent_env *env;
#define d_strtoul(var) sysfs_strtoul(var, dc->var)
+#define d_strtoul_nonzero(var) sysfs_strtoul_clamp(var, dc->var, 1, INT_MAX)
#define d_strtoi_h(var) sysfs_hatoi(var, dc->var)
sysfs_strtoul(data_csum, dc->disk.data_csum);
@@ -197,16 +207,15 @@
d_strtoul(writeback_metadata);
d_strtoul(writeback_running);
d_strtoul(writeback_delay);
- sysfs_strtoul_clamp(writeback_rate,
- dc->writeback_rate.rate, 1, 1000000);
+
sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent, 0, 40);
- d_strtoul(writeback_rate_update_seconds);
+ sysfs_strtoul_clamp(writeback_rate,
+ dc->writeback_rate.rate, 1, INT_MAX);
+
+ d_strtoul_nonzero(writeback_rate_update_seconds);
d_strtoul(writeback_rate_d_term);
- d_strtoul(writeback_rate_p_term_inverse);
- sysfs_strtoul_clamp(writeback_rate_p_term_inverse,
- dc->writeback_rate_p_term_inverse, 1, INT_MAX);
- d_strtoul(writeback_rate_d_smooth);
+ d_strtoul_nonzero(writeback_rate_p_term_inverse);
d_strtoi_h(sequential_cutoff);
d_strtoi_h(readahead);
@@ -313,7 +322,6 @@
&sysfs_writeback_rate_update_seconds,
&sysfs_writeback_rate_d_term,
&sysfs_writeback_rate_p_term_inverse,
- &sysfs_writeback_rate_d_smooth,
&sysfs_writeback_rate_debug,
&sysfs_dirty_data,
&sysfs_stripe_size,
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index 462214e..bb37618 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -209,7 +209,13 @@
{
uint64_t now = local_clock();
- d->next += div_u64(done, d->rate);
+ d->next += div_u64(done * NSEC_PER_SEC, d->rate);
+
+ if (time_before64(now + NSEC_PER_SEC, d->next))
+ d->next = now + NSEC_PER_SEC;
+
+ if (time_after64(now - NSEC_PER_SEC * 2, d->next))
+ d->next = now - NSEC_PER_SEC * 2;
return time_after64(d->next, now)
? div_u64(d->next - now, NSEC_PER_SEC / HZ)
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 362c4b3..1030c60 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -110,7 +110,7 @@
_r; \
})
-#define heap_peek(h) ((h)->size ? (h)->data[0] : NULL)
+#define heap_peek(h) ((h)->used ? (h)->data[0] : NULL)
#define heap_full(h) ((h)->used == (h)->size)
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 99053b1..6c44fe0 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -30,38 +30,40 @@
/* PD controller */
- int change = 0;
- int64_t error;
int64_t dirty = bcache_dev_sectors_dirty(&dc->disk);
int64_t derivative = dirty - dc->disk.sectors_dirty_last;
+ int64_t proportional = dirty - target;
+ int64_t change;
dc->disk.sectors_dirty_last = dirty;
- derivative *= dc->writeback_rate_d_term;
- derivative = clamp(derivative, -dirty, dirty);
+ /* Scale to sectors per second */
+
+ proportional *= dc->writeback_rate_update_seconds;
+ proportional = div_s64(proportional, dc->writeback_rate_p_term_inverse);
+
+ derivative = div_s64(derivative, dc->writeback_rate_update_seconds);
derivative = ewma_add(dc->disk.sectors_dirty_derivative, derivative,
- dc->writeback_rate_d_smooth, 0);
+ (dc->writeback_rate_d_term /
+ dc->writeback_rate_update_seconds) ?: 1, 0);
- /* Avoid divide by zero */
- if (!target)
- goto out;
+ derivative *= dc->writeback_rate_d_term;
+ derivative = div_s64(derivative, dc->writeback_rate_p_term_inverse);
- error = div64_s64((dirty + derivative - target) << 8, target);
-
- change = div_s64((dc->writeback_rate.rate * error) >> 8,
- dc->writeback_rate_p_term_inverse);
+ change = proportional + derivative;
/* Don't increase writeback rate if the device isn't keeping up */
if (change > 0 &&
time_after64(local_clock(),
- dc->writeback_rate.next + 10 * NSEC_PER_MSEC))
+ dc->writeback_rate.next + NSEC_PER_MSEC))
change = 0;
dc->writeback_rate.rate =
- clamp_t(int64_t, dc->writeback_rate.rate + change,
+ clamp_t(int64_t, (int64_t) dc->writeback_rate.rate + change,
1, NSEC_PER_MSEC);
-out:
+
+ dc->writeback_rate_proportional = proportional;
dc->writeback_rate_derivative = derivative;
dc->writeback_rate_change = change;
dc->writeback_rate_target = target;
@@ -87,15 +89,11 @@
static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors)
{
- uint64_t ret;
-
if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) ||
!dc->writeback_percent)
return 0;
- ret = bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL);
-
- return min_t(uint64_t, ret, HZ);
+ return bch_next_delay(&dc->writeback_rate, sectors);
}
struct dirty_io {
@@ -241,7 +239,7 @@
if (KEY_START(&w->key) != dc->last_read ||
jiffies_to_msecs(delay) > 50)
while (!kthread_should_stop() && delay)
- delay = schedule_timeout_interruptible(delay);
+ delay = schedule_timeout_uninterruptible(delay);
dc->last_read = KEY_OFFSET(&w->key);
@@ -438,7 +436,7 @@
while (delay &&
!kthread_should_stop() &&
!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags))
- delay = schedule_timeout_interruptible(delay);
+ delay = schedule_timeout_uninterruptible(delay);
}
}
@@ -476,6 +474,8 @@
bch_btree_map_keys(&op.op, dc->disk.c, &KEY(op.inode, 0, 0),
sectors_dirty_init_fn, 0);
+
+ dc->disk.sectors_dirty_last = bcache_dev_sectors_dirty(&dc->disk);
}
int bch_cached_dev_writeback_init(struct cached_dev *dc)
@@ -490,18 +490,15 @@
dc->writeback_delay = 30;
dc->writeback_rate.rate = 1024;
- dc->writeback_rate_update_seconds = 30;
- dc->writeback_rate_d_term = 16;
- dc->writeback_rate_p_term_inverse = 64;
- dc->writeback_rate_d_smooth = 8;
+ dc->writeback_rate_update_seconds = 5;
+ dc->writeback_rate_d_term = 30;
+ dc->writeback_rate_p_term_inverse = 6000;
dc->writeback_thread = kthread_create(bch_writeback_thread, dc,
"bcache_writeback");
if (IS_ERR(dc->writeback_thread))
return PTR_ERR(dc->writeback_thread);
- set_task_state(dc->writeback_thread, TASK_INTERRUPTIBLE);
-
INIT_DELAYED_WORK(&dc->writeback_rate_update, update_writeback_rate);
schedule_delayed_work(&dc->writeback_rate_update,
dc->writeback_rate_update_seconds * HZ);
diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c
index 11e20af..705698f 100644
--- a/drivers/mfd/rtsx_pcr.c
+++ b/drivers/mfd/rtsx_pcr.c
@@ -1228,8 +1228,14 @@
pcr->remove_pci = true;
- cancel_delayed_work(&pcr->carddet_work);
- cancel_delayed_work(&pcr->idle_work);
+ /* Disable interrupts at the pcr level */
+ spin_lock_irq(&pcr->lock);
+ rtsx_pci_writel(pcr, RTSX_BIER, 0);
+ pcr->bier = 0;
+ spin_unlock_irq(&pcr->lock);
+
+ cancel_delayed_work_sync(&pcr->carddet_work);
+ cancel_delayed_work_sync(&pcr->idle_work);
mfd_remove_devices(&pcidev->dev);
diff --git a/drivers/mtd/maps/pxa2xx-flash.c b/drivers/mtd/maps/pxa2xx-flash.c
index d210d13..0f55589 100644
--- a/drivers/mtd/maps/pxa2xx-flash.c
+++ b/drivers/mtd/maps/pxa2xx-flash.c
@@ -73,7 +73,7 @@
return -ENOMEM;
}
info->map.cached =
- ioremap_cached(info->map.phys, info->map.size);
+ ioremap_cache(info->map.phys, info->map.size);
if (!info->map.cached)
printk(KERN_WARNING "Failed to ioremap cached %s\n",
info->map.name);
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 187b1b7..4ced594 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -2201,20 +2201,25 @@
port = &(SLAVE_AD_INFO(slave).port);
- // if slave is null, the whole port is not initialized
+ /* if slave is null, the whole port is not initialized */
if (!port->slave) {
pr_warning("Warning: %s: speed changed for uninitialized port on %s\n",
slave->bond->dev->name, slave->dev->name);
return;
}
+ __get_state_machine_lock(port);
+
port->actor_admin_port_key &= ~AD_SPEED_KEY_BITS;
port->actor_oper_port_key = port->actor_admin_port_key |=
(__get_link_speed(port) << 1);
pr_debug("Port %d changed speed\n", port->actor_port_number);
- // there is no need to reselect a new aggregator, just signal the
- // state machines to reinitialize
+ /* there is no need to reselect a new aggregator, just signal the
+ * state machines to reinitialize
+ */
port->sm_vars |= AD_PORT_BEGIN;
+
+ __release_state_machine_lock(port);
}
/**
@@ -2229,20 +2234,25 @@
port = &(SLAVE_AD_INFO(slave).port);
- // if slave is null, the whole port is not initialized
+ /* if slave is null, the whole port is not initialized */
if (!port->slave) {
pr_warning("%s: Warning: duplex changed for uninitialized port on %s\n",
slave->bond->dev->name, slave->dev->name);
return;
}
+ __get_state_machine_lock(port);
+
port->actor_admin_port_key &= ~AD_DUPLEX_KEY_BITS;
port->actor_oper_port_key = port->actor_admin_port_key |=
__get_duplex(port);
pr_debug("Port %d changed duplex\n", port->actor_port_number);
- // there is no need to reselect a new aggregator, just signal the
- // state machines to reinitialize
+ /* there is no need to reselect a new aggregator, just signal the
+ * state machines to reinitialize
+ */
port->sm_vars |= AD_PORT_BEGIN;
+
+ __release_state_machine_lock(port);
}
/**
@@ -2258,15 +2268,21 @@
port = &(SLAVE_AD_INFO(slave).port);
- // if slave is null, the whole port is not initialized
+ /* if slave is null, the whole port is not initialized */
if (!port->slave) {
pr_warning("Warning: %s: link status changed for uninitialized port on %s\n",
slave->bond->dev->name, slave->dev->name);
return;
}
- // on link down we are zeroing duplex and speed since some of the adaptors(ce1000.lan) report full duplex/speed instead of N/A(duplex) / 0(speed)
- // on link up we are forcing recheck on the duplex and speed since some of he adaptors(ce1000.lan) report
+ __get_state_machine_lock(port);
+ /* on link down we are zeroing duplex and speed since
+ * some of the adaptors(ce1000.lan) report full duplex/speed
+ * instead of N/A(duplex) / 0(speed).
+ *
+ * on link up we are forcing recheck on the duplex and speed since
+ * some of he adaptors(ce1000.lan) report.
+ */
if (link == BOND_LINK_UP) {
port->is_enabled = true;
port->actor_admin_port_key &= ~AD_DUPLEX_KEY_BITS;
@@ -2282,10 +2298,15 @@
port->actor_oper_port_key = (port->actor_admin_port_key &=
~AD_SPEED_KEY_BITS);
}
- //BOND_PRINT_DBG(("Port %d changed link status to %s", port->actor_port_number, ((link == BOND_LINK_UP)?"UP":"DOWN")));
- // there is no need to reselect a new aggregator, just signal the
- // state machines to reinitialize
+ pr_debug("Port %d changed link status to %s",
+ port->actor_port_number,
+ (link == BOND_LINK_UP) ? "UP" : "DOWN");
+ /* there is no need to reselect a new aggregator, just signal the
+ * state machines to reinitialize
+ */
port->sm_vars |= AD_PORT_BEGIN;
+
+ __release_state_machine_lock(port);
}
/*
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 398e299..4b8c58b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3732,7 +3732,8 @@
}
-static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
/*
* This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index 5f9a7ad..8aeec0b 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -625,6 +625,7 @@
usb_unanchor_urb(urb);
usb_free_coherent(dev->udev, RX_BUFFER_SIZE, buf,
urb->transfer_dma);
+ usb_free_urb(urb);
break;
}
@@ -798,8 +799,8 @@
* allowed (MAX_TX_URBS).
*/
if (!context) {
- usb_unanchor_urb(urb);
usb_free_coherent(dev->udev, size, buf, urb->transfer_dma);
+ usb_free_urb(urb);
netdev_warn(netdev, "couldn't find free context\n");
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
index 8ee9d15..263dd92 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
@@ -927,6 +927,9 @@
/* set LED in default state (end of init phase) */
pcan_usb_pro_set_led(dev, 0, 1);
+ kfree(bi);
+ kfree(fi);
+
return 0;
err_out:
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index b2ffad1..248baf6 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -565,6 +565,8 @@
/* Make sure pointer to data buffer is set */
wmb();
+ skb_tx_timestamp(skb);
+
*info = cpu_to_le32(FOR_EMAC | FIRST_OR_LAST_MASK | len);
/* Increment index to point to the next BD */
@@ -579,8 +581,6 @@
arc_reg_set(priv, R_STATUS, TXPL_MASK);
- skb_tx_timestamp(skb);
-
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index a36a760..2980175 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -145,9 +145,11 @@
* Mask some pcie error bits
*/
pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
- pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, &data);
- data &= ~(PCI_ERR_UNC_DLP | PCI_ERR_UNC_FCP);
- pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, data);
+ if (pos) {
+ pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, &data);
+ data &= ~(PCI_ERR_UNC_DLP | PCI_ERR_UNC_FCP);
+ pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, data);
+ }
/* clear error status */
pcie_capability_write_word(pdev, PCI_EXP_DEVSTA,
PCI_EXP_DEVSTA_NFED |
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index a1f66e2..ec61190 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -520,10 +520,12 @@
#define BNX2X_FP_STATE_IDLE 0
#define BNX2X_FP_STATE_NAPI (1 << 0) /* NAPI owns this FP */
#define BNX2X_FP_STATE_POLL (1 << 1) /* poll owns this FP */
-#define BNX2X_FP_STATE_NAPI_YIELD (1 << 2) /* NAPI yielded this FP */
-#define BNX2X_FP_STATE_POLL_YIELD (1 << 3) /* poll yielded this FP */
+#define BNX2X_FP_STATE_DISABLED (1 << 2)
+#define BNX2X_FP_STATE_NAPI_YIELD (1 << 3) /* NAPI yielded this FP */
+#define BNX2X_FP_STATE_POLL_YIELD (1 << 4) /* poll yielded this FP */
+#define BNX2X_FP_OWNED (BNX2X_FP_STATE_NAPI | BNX2X_FP_STATE_POLL)
#define BNX2X_FP_YIELD (BNX2X_FP_STATE_NAPI_YIELD | BNX2X_FP_STATE_POLL_YIELD)
-#define BNX2X_FP_LOCKED (BNX2X_FP_STATE_NAPI | BNX2X_FP_STATE_POLL)
+#define BNX2X_FP_LOCKED (BNX2X_FP_OWNED | BNX2X_FP_STATE_DISABLED)
#define BNX2X_FP_USER_PEND (BNX2X_FP_STATE_POLL | BNX2X_FP_STATE_POLL_YIELD)
/* protect state */
spinlock_t lock;
@@ -613,7 +615,7 @@
{
bool rc = true;
- spin_lock(&fp->lock);
+ spin_lock_bh(&fp->lock);
if (fp->state & BNX2X_FP_LOCKED) {
WARN_ON(fp->state & BNX2X_FP_STATE_NAPI);
fp->state |= BNX2X_FP_STATE_NAPI_YIELD;
@@ -622,7 +624,7 @@
/* we don't care if someone yielded */
fp->state = BNX2X_FP_STATE_NAPI;
}
- spin_unlock(&fp->lock);
+ spin_unlock_bh(&fp->lock);
return rc;
}
@@ -631,14 +633,16 @@
{
bool rc = false;
- spin_lock(&fp->lock);
+ spin_lock_bh(&fp->lock);
WARN_ON(fp->state &
(BNX2X_FP_STATE_POLL | BNX2X_FP_STATE_NAPI_YIELD));
if (fp->state & BNX2X_FP_STATE_POLL_YIELD)
rc = true;
- fp->state = BNX2X_FP_STATE_IDLE;
- spin_unlock(&fp->lock);
+
+ /* state ==> idle, unless currently disabled */
+ fp->state &= BNX2X_FP_STATE_DISABLED;
+ spin_unlock_bh(&fp->lock);
return rc;
}
@@ -669,7 +673,9 @@
if (fp->state & BNX2X_FP_STATE_POLL_YIELD)
rc = true;
- fp->state = BNX2X_FP_STATE_IDLE;
+
+ /* state ==> idle, unless currently disabled */
+ fp->state &= BNX2X_FP_STATE_DISABLED;
spin_unlock_bh(&fp->lock);
return rc;
}
@@ -677,9 +683,23 @@
/* true if a socket is polling, even if it did not get the lock */
static inline bool bnx2x_fp_ll_polling(struct bnx2x_fastpath *fp)
{
- WARN_ON(!(fp->state & BNX2X_FP_LOCKED));
+ WARN_ON(!(fp->state & BNX2X_FP_OWNED));
return fp->state & BNX2X_FP_USER_PEND;
}
+
+/* false if fp is currently owned */
+static inline bool bnx2x_fp_ll_disable(struct bnx2x_fastpath *fp)
+{
+ int rc = true;
+
+ spin_lock_bh(&fp->lock);
+ if (fp->state & BNX2X_FP_OWNED)
+ rc = false;
+ fp->state |= BNX2X_FP_STATE_DISABLED;
+ spin_unlock_bh(&fp->lock);
+
+ return rc;
+}
#else
static inline void bnx2x_fp_init_lock(struct bnx2x_fastpath *fp)
{
@@ -709,6 +729,10 @@
{
return false;
}
+static inline bool bnx2x_fp_ll_disable(struct bnx2x_fastpath *fp)
+{
+ return true;
+}
#endif /* CONFIG_NET_RX_BUSY_POLL */
/* Use 2500 as a mini-jumbo MTU for FCoE */
@@ -1250,7 +1274,10 @@
* Therefore, if they would have been defined in the same union,
* data can get corrupted.
*/
- struct afex_vif_list_ramrod_data func_afex_rdata;
+ union {
+ struct afex_vif_list_ramrod_data viflist_data;
+ struct function_update_data func_update;
+ } func_afex_rdata;
/* used by dmae command executer */
struct dmae_command dmae[MAX_DMAE_C];
@@ -2499,4 +2526,6 @@
#define MCPR_SCRATCH_BASE(bp) \
(CHIP_IS_E1x(bp) ? MCP_REG_MCPR_SCRATCH : MCP_A_REG_MCPR_SCRATCH)
+#define E1H_MAX_MF_SB_COUNT (HC_SB_MAX_SB_E1X/(E1HVN_MAX * PORT_MAX))
+
#endif /* bnx2x.h */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index ec96130..bf81156 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -160,6 +160,7 @@
struct sk_buff *skb = tx_buf->skb;
u16 bd_idx = TX_BD(tx_buf->first_bd), new_cons;
int nbd;
+ u16 split_bd_len = 0;
/* prefetch skb end pointer to speedup dev_kfree_skb() */
prefetch(&skb->end);
@@ -167,10 +168,7 @@
DP(NETIF_MSG_TX_DONE, "fp[%d]: pkt_idx %d buff @(%p)->skb %p\n",
txdata->txq_index, idx, tx_buf, skb);
- /* unmap first bd */
tx_start_bd = &txdata->tx_desc_ring[bd_idx].start_bd;
- dma_unmap_single(&bp->pdev->dev, BD_UNMAP_ADDR(tx_start_bd),
- BD_UNMAP_LEN(tx_start_bd), DMA_TO_DEVICE);
nbd = le16_to_cpu(tx_start_bd->nbd) - 1;
#ifdef BNX2X_STOP_ON_ERROR
@@ -188,12 +186,19 @@
--nbd;
bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
- /* ...and the TSO split header bd since they have no mapping */
+ /* TSO headers+data bds share a common mapping. See bnx2x_tx_split() */
if (tx_buf->flags & BNX2X_TSO_SPLIT_BD) {
+ tx_data_bd = &txdata->tx_desc_ring[bd_idx].reg_bd;
+ split_bd_len = BD_UNMAP_LEN(tx_data_bd);
--nbd;
bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
}
+ /* unmap first bd */
+ dma_unmap_single(&bp->pdev->dev, BD_UNMAP_ADDR(tx_start_bd),
+ BD_UNMAP_LEN(tx_start_bd) + split_bd_len,
+ DMA_TO_DEVICE);
+
/* now free frags */
while (nbd > 0) {
@@ -1790,26 +1795,22 @@
{
int i;
- local_bh_disable();
for_each_rx_queue_cnic(bp, i) {
napi_disable(&bnx2x_fp(bp, i, napi));
- while (!bnx2x_fp_lock_napi(&bp->fp[i]))
- mdelay(1);
+ while (!bnx2x_fp_ll_disable(&bp->fp[i]))
+ usleep_range(1000, 2000);
}
- local_bh_enable();
}
static void bnx2x_napi_disable(struct bnx2x *bp)
{
int i;
- local_bh_disable();
for_each_eth_queue(bp, i) {
napi_disable(&bnx2x_fp(bp, i, napi));
- while (!bnx2x_fp_lock_napi(&bp->fp[i]))
- mdelay(1);
+ while (!bnx2x_fp_ll_disable(&bp->fp[i]))
+ usleep_range(1000, 2000);
}
- local_bh_enable();
}
void bnx2x_netif_start(struct bnx2x *bp)
@@ -1832,7 +1833,8 @@
bnx2x_napi_disable_cnic(bp);
}
-u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb)
+u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
struct bnx2x *bp = netdev_priv(dev);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index da8fcaa..41f3ca5a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -524,7 +524,8 @@
int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos);
/* select_queue callback */
-u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb);
+u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv);
static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
struct bnx2x_fastpath *fp,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 20dcc02..11fc795 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -3865,6 +3865,19 @@
bnx2x_warpcore_enable_AN_KR2(phy, params, vars);
} else {
+ /* Enable Auto-Detect to support 1G over CL37 as well */
+ bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+ MDIO_WC_REG_SERDESDIGITAL_CONTROL1000X1, 0x10);
+
+ /* Force cl48 sync_status LOW to avoid getting stuck in CL73
+ * parallel-detect loop when CL73 and CL37 are enabled.
+ */
+ CL22_WR_OVER_CL45(bp, phy, MDIO_REG_BANK_AER_BLOCK,
+ MDIO_AER_BLOCK_AER_REG, 0);
+ bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+ MDIO_WC_REG_RXB_ANA_RX_CONTROL_PCI, 0x0800);
+ bnx2x_set_aer_mmd(params, phy);
+
bnx2x_disable_kr2(params, vars, phy);
}
@@ -8120,17 +8133,20 @@
*edc_mode = EDC_MODE_ACTIVE_DAC;
else
check_limiting_mode = 1;
- } else if (copper_module_type &
- SFP_EEPROM_FC_TX_TECH_BITMASK_COPPER_PASSIVE) {
+ } else {
+ *edc_mode = EDC_MODE_PASSIVE_DAC;
+ /* Even in case PASSIVE_DAC indication is not set,
+ * treat it as a passive DAC cable, since some cables
+ * don't have this indication.
+ */
+ if (copper_module_type &
+ SFP_EEPROM_FC_TX_TECH_BITMASK_COPPER_PASSIVE) {
DP(NETIF_MSG_LINK,
"Passive Copper cable detected\n");
- *edc_mode =
- EDC_MODE_PASSIVE_DAC;
- } else {
- DP(NETIF_MSG_LINK,
- "Unknown copper-cable-type 0x%x !!!\n",
- copper_module_type);
- return -EINVAL;
+ } else {
+ DP(NETIF_MSG_LINK,
+ "Unknown copper-cable-type\n");
+ }
}
break;
}
@@ -10825,9 +10841,9 @@
(1<<11));
if (((phy->req_line_speed == SPEED_AUTO_NEG) &&
- (phy->speed_cap_mask &
- PORT_HW_CFG_SPEED_CAPABILITY_D0_1G)) ||
- (phy->req_line_speed == SPEED_1000)) {
+ (phy->speed_cap_mask &
+ PORT_HW_CFG_SPEED_CAPABILITY_D0_1G)) ||
+ (phy->req_line_speed == SPEED_1000)) {
an_1000_val |= (1<<8);
autoneg_val |= (1<<9 | 1<<12);
if (phy->req_duplex == DUPLEX_FULL)
@@ -10843,30 +10859,32 @@
0x09,
&an_1000_val);
- /* Set 100 speed advertisement */
- if (((phy->req_line_speed == SPEED_AUTO_NEG) &&
- (phy->speed_cap_mask &
- (PORT_HW_CFG_SPEED_CAPABILITY_D0_100M_FULL |
- PORT_HW_CFG_SPEED_CAPABILITY_D0_100M_HALF)))) {
- an_10_100_val |= (1<<7);
- /* Enable autoneg and restart autoneg for legacy speeds */
- autoneg_val |= (1<<9 | 1<<12);
-
- if (phy->req_duplex == DUPLEX_FULL)
- an_10_100_val |= (1<<8);
- DP(NETIF_MSG_LINK, "Advertising 100M\n");
- }
-
- /* Set 10 speed advertisement */
- if (((phy->req_line_speed == SPEED_AUTO_NEG) &&
- (phy->speed_cap_mask &
- (PORT_HW_CFG_SPEED_CAPABILITY_D0_10M_FULL |
- PORT_HW_CFG_SPEED_CAPABILITY_D0_10M_HALF)))) {
- an_10_100_val |= (1<<5);
- autoneg_val |= (1<<9 | 1<<12);
- if (phy->req_duplex == DUPLEX_FULL)
+ /* Advertise 10/100 link speed */
+ if (phy->req_line_speed == SPEED_AUTO_NEG) {
+ if (phy->speed_cap_mask &
+ PORT_HW_CFG_SPEED_CAPABILITY_D0_10M_HALF) {
+ an_10_100_val |= (1<<5);
+ autoneg_val |= (1<<9 | 1<<12);
+ DP(NETIF_MSG_LINK, "Advertising 10M-HD\n");
+ }
+ if (phy->speed_cap_mask &
+ PORT_HW_CFG_SPEED_CAPABILITY_D0_10M_FULL) {
an_10_100_val |= (1<<6);
- DP(NETIF_MSG_LINK, "Advertising 10M\n");
+ autoneg_val |= (1<<9 | 1<<12);
+ DP(NETIF_MSG_LINK, "Advertising 10M-FD\n");
+ }
+ if (phy->speed_cap_mask &
+ PORT_HW_CFG_SPEED_CAPABILITY_D0_100M_HALF) {
+ an_10_100_val |= (1<<7);
+ autoneg_val |= (1<<9 | 1<<12);
+ DP(NETIF_MSG_LINK, "Advertising 100M-HD\n");
+ }
+ if (phy->speed_cap_mask &
+ PORT_HW_CFG_SPEED_CAPABILITY_D0_100M_FULL) {
+ an_10_100_val |= (1<<8);
+ autoneg_val |= (1<<9 | 1<<12);
+ DP(NETIF_MSG_LINK, "Advertising 100M-FD\n");
+ }
}
/* Only 10/100 are allowed to work in FORCE mode */
@@ -13342,6 +13360,10 @@
DP(NETIF_MSG_LINK, "Link changed:[%x %x]->%x\n", vars->link_up,
old_status, status);
+ /* Do not touch the link in case physical link down */
+ if ((vars->phy_flags & PHY_PHYSICAL_LINK_FLAG) == 0)
+ return 1;
+
/* a. Update shmem->link_status accordingly
* b. Update link_vars->link_up
*/
@@ -13550,7 +13572,7 @@
*/
not_kr2_device = (((base_page & 0x8000) == 0) ||
(((base_page & 0x8000) &&
- ((next_page & 0xe0) == 0x2))));
+ ((next_page & 0xe0) == 0x20))));
/* In case KR2 is already disabled, check if we need to re-enable it */
if (!(vars->link_attr_sync & LINK_ATTR_SYNC_KR2_ENABLE)) {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 814d0ec..8b3107b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -11447,9 +11447,9 @@
}
}
- /* adjust igu_sb_cnt to MF for E1x */
- if (CHIP_IS_E1x(bp) && IS_MF(bp))
- bp->igu_sb_cnt /= E1HVN_MAX;
+ /* adjust igu_sb_cnt to MF for E1H */
+ if (CHIP_IS_E1H(bp) && IS_MF(bp))
+ bp->igu_sb_cnt = min_t(u8, bp->igu_sb_cnt, E1H_MAX_MF_SB_COUNT);
/* port info */
bnx2x_get_port_hwinfo(bp);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
index 3efbb35..14ffb6e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
@@ -7179,6 +7179,7 @@
#define MDIO_WC_REG_RX1_PCI_CTRL 0x80ca
#define MDIO_WC_REG_RX2_PCI_CTRL 0x80da
#define MDIO_WC_REG_RX3_PCI_CTRL 0x80ea
+#define MDIO_WC_REG_RXB_ANA_RX_CONTROL_PCI 0x80fa
#define MDIO_WC_REG_XGXSBLK2_UNICORE_MODE_10G 0x8104
#define MDIO_WC_REG_XGXS_STATUS3 0x8129
#define MDIO_WC_REG_PAR_DET_10G_STATUS 0x8130
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 32c92ab..18438a5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -2038,6 +2038,7 @@
struct bnx2x_vlan_mac_ramrod_params p;
struct bnx2x_exe_queue_obj *exeq = &o->exe_queue;
struct bnx2x_exeq_elem *exeq_pos, *exeq_pos_n;
+ unsigned long flags;
int read_lock;
int rc = 0;
@@ -2046,8 +2047,9 @@
spin_lock_bh(&exeq->lock);
list_for_each_entry_safe(exeq_pos, exeq_pos_n, &exeq->exe_queue, link) {
- if (exeq_pos->cmd_data.vlan_mac.vlan_mac_flags ==
- *vlan_mac_flags) {
+ flags = exeq_pos->cmd_data.vlan_mac.vlan_mac_flags;
+ if (BNX2X_VLAN_MAC_CMP_FLAGS(flags) ==
+ BNX2X_VLAN_MAC_CMP_FLAGS(*vlan_mac_flags)) {
rc = exeq->remove(bp, exeq->owner, exeq_pos);
if (rc) {
BNX2X_ERR("Failed to remove command\n");
@@ -2080,7 +2082,9 @@
return read_lock;
list_for_each_entry(pos, &o->head, link) {
- if (pos->vlan_mac_flags == *vlan_mac_flags) {
+ flags = pos->vlan_mac_flags;
+ if (BNX2X_VLAN_MAC_CMP_FLAGS(flags) ==
+ BNX2X_VLAN_MAC_CMP_FLAGS(*vlan_mac_flags)) {
p.user_req.vlan_mac_flags = pos->vlan_mac_flags;
memcpy(&p.user_req.u, &pos->u, sizeof(pos->u));
rc = bnx2x_config_vlan_mac(bp, &p);
@@ -4382,8 +4386,11 @@
struct bnx2x_raw_obj *r = &o->raw;
/* Do nothing if only driver cleanup was requested */
- if (test_bit(RAMROD_DRV_CLR_ONLY, &p->ramrod_flags))
+ if (test_bit(RAMROD_DRV_CLR_ONLY, &p->ramrod_flags)) {
+ DP(BNX2X_MSG_SP, "Not configuring RSS ramrod_flags=%lx\n",
+ p->ramrod_flags);
return 0;
+ }
r->set_pending(r);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
index 658f4e3..6a53c15 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
@@ -266,6 +266,13 @@
BNX2X_DONT_CONSUME_CAM_CREDIT,
BNX2X_DONT_CONSUME_CAM_CREDIT_DEST,
};
+/* When looking for matching filters, some flags are not interesting */
+#define BNX2X_VLAN_MAC_CMP_MASK (1 << BNX2X_UC_LIST_MAC | \
+ 1 << BNX2X_ETH_MAC | \
+ 1 << BNX2X_ISCSI_ETH_MAC | \
+ 1 << BNX2X_NETQ_ETH_MAC)
+#define BNX2X_VLAN_MAC_CMP_FLAGS(flags) \
+ ((flags) & BNX2X_VLAN_MAC_CMP_MASK)
struct bnx2x_vlan_mac_ramrod_params {
/* Object to run the command from */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 2e46c28..e7845e5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -1209,6 +1209,11 @@
/* next state */
vfop->state = BNX2X_VFOP_RXMODE_DONE;
+ /* record the accept flags in vfdb so hypervisor can modify them
+ * if necessary
+ */
+ bnx2x_vfq(vf, ramrod->cl_id - vf->igu_base_id, accept_flags) =
+ ramrod->rx_accept_flags;
vfop->rc = bnx2x_config_rx_mode(bp, ramrod);
bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
op_err:
@@ -1224,39 +1229,43 @@
return;
}
+static void bnx2x_vf_prep_rx_mode(struct bnx2x *bp, u8 qid,
+ struct bnx2x_rx_mode_ramrod_params *ramrod,
+ struct bnx2x_virtf *vf,
+ unsigned long accept_flags)
+{
+ struct bnx2x_vf_queue *vfq = vfq_get(vf, qid);
+
+ memset(ramrod, 0, sizeof(*ramrod));
+ ramrod->cid = vfq->cid;
+ ramrod->cl_id = vfq_cl_id(vf, vfq);
+ ramrod->rx_mode_obj = &bp->rx_mode_obj;
+ ramrod->func_id = FW_VF_HANDLE(vf->abs_vfid);
+ ramrod->rx_accept_flags = accept_flags;
+ ramrod->tx_accept_flags = accept_flags;
+ ramrod->pstate = &vf->filter_state;
+ ramrod->state = BNX2X_FILTER_RX_MODE_PENDING;
+
+ set_bit(BNX2X_FILTER_RX_MODE_PENDING, &vf->filter_state);
+ set_bit(RAMROD_RX, &ramrod->ramrod_flags);
+ set_bit(RAMROD_TX, &ramrod->ramrod_flags);
+
+ ramrod->rdata = bnx2x_vf_sp(bp, vf, rx_mode_rdata.e2);
+ ramrod->rdata_mapping = bnx2x_vf_sp_map(bp, vf, rx_mode_rdata.e2);
+}
+
int bnx2x_vfop_rxmode_cmd(struct bnx2x *bp,
struct bnx2x_virtf *vf,
struct bnx2x_vfop_cmd *cmd,
int qid, unsigned long accept_flags)
{
- struct bnx2x_vf_queue *vfq = vfq_get(vf, qid);
struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
if (vfop) {
struct bnx2x_rx_mode_ramrod_params *ramrod =
&vf->op_params.rx_mode;
- memset(ramrod, 0, sizeof(*ramrod));
-
- /* Prepare ramrod parameters */
- ramrod->cid = vfq->cid;
- ramrod->cl_id = vfq_cl_id(vf, vfq);
- ramrod->rx_mode_obj = &bp->rx_mode_obj;
- ramrod->func_id = FW_VF_HANDLE(vf->abs_vfid);
-
- ramrod->rx_accept_flags = accept_flags;
- ramrod->tx_accept_flags = accept_flags;
- ramrod->pstate = &vf->filter_state;
- ramrod->state = BNX2X_FILTER_RX_MODE_PENDING;
-
- set_bit(BNX2X_FILTER_RX_MODE_PENDING, &vf->filter_state);
- set_bit(RAMROD_RX, &ramrod->ramrod_flags);
- set_bit(RAMROD_TX, &ramrod->ramrod_flags);
-
- ramrod->rdata =
- bnx2x_vf_sp(bp, vf, rx_mode_rdata.e2);
- ramrod->rdata_mapping =
- bnx2x_vf_sp_map(bp, vf, rx_mode_rdata.e2);
+ bnx2x_vf_prep_rx_mode(bp, qid, ramrod, vf, accept_flags);
bnx2x_vfop_opset(BNX2X_VFOP_RXMODE_CONFIG,
bnx2x_vfop_rxmode, cmd->done);
@@ -3202,13 +3211,16 @@
bnx2x_iov_static_resc(bp, vf);
}
- /* prepare msix vectors in VF configuration space */
+ /* prepare msix vectors in VF configuration space - the value in the
+ * PCI configuration space should be the index of the last entry,
+ * namely one less than the actual size of the table
+ */
for (vf_idx = first_vf; vf_idx < first_vf + req_vfs; vf_idx++) {
bnx2x_pretend_func(bp, HW_VF_HANDLE(bp, vf_idx));
REG_WR(bp, PCICFG_OFFSET + GRC_CONFIG_REG_VF_MSIX_CONTROL,
- num_vf_queues);
+ num_vf_queues - 1);
DP(BNX2X_MSG_IOV, "set msix vec num in VF %d cfg space to %d\n",
- vf_idx, num_vf_queues);
+ vf_idx, num_vf_queues - 1);
}
bnx2x_pretend_func(bp, BP_ABS_FUNC(bp));
@@ -3436,10 +3448,18 @@
int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos)
{
- struct bnx2x *bp = netdev_priv(dev);
- int rc, q_logical_state;
- struct bnx2x_virtf *vf = NULL;
+ struct bnx2x_queue_state_params q_params = {NULL};
+ struct bnx2x_vlan_mac_ramrod_params ramrod_param;
+ struct bnx2x_queue_update_params *update_params;
struct pf_vf_bulletin_content *bulletin = NULL;
+ struct bnx2x_rx_mode_ramrod_params rx_ramrod;
+ struct bnx2x *bp = netdev_priv(dev);
+ struct bnx2x_vlan_mac_obj *vlan_obj;
+ unsigned long vlan_mac_flags = 0;
+ unsigned long ramrod_flags = 0;
+ struct bnx2x_virtf *vf = NULL;
+ unsigned long accept_flags;
+ int rc;
/* sanity and init */
rc = bnx2x_vf_ndo_prep(bp, vfidx, &vf, &bulletin);
@@ -3457,104 +3477,118 @@
/* update PF's copy of the VF's bulletin. No point in posting the vlan
* to the VF since it doesn't have anything to do with it. But it useful
* to store it here in case the VF is not up yet and we can only
- * configure the vlan later when it does.
+ * configure the vlan later when it does. Treat vlan id 0 as remove the
+ * Host tag.
*/
- bulletin->valid_bitmap |= 1 << VLAN_VALID;
+ if (vlan > 0)
+ bulletin->valid_bitmap |= 1 << VLAN_VALID;
+ else
+ bulletin->valid_bitmap &= ~(1 << VLAN_VALID);
bulletin->vlan = vlan;
/* is vf initialized and queue set up? */
- q_logical_state =
- bnx2x_get_q_logical_state(bp, &bnx2x_leading_vfq(vf, sp_obj));
- if (vf->state == VF_ENABLED &&
- q_logical_state == BNX2X_Q_LOGICAL_STATE_ACTIVE) {
- /* configure the vlan in device on this vf's queue */
- unsigned long ramrod_flags = 0;
- unsigned long vlan_mac_flags = 0;
- struct bnx2x_vlan_mac_obj *vlan_obj =
- &bnx2x_leading_vfq(vf, vlan_obj);
- struct bnx2x_vlan_mac_ramrod_params ramrod_param;
- struct bnx2x_queue_state_params q_params = {NULL};
- struct bnx2x_queue_update_params *update_params;
+ if (vf->state != VF_ENABLED ||
+ bnx2x_get_q_logical_state(bp, &bnx2x_leading_vfq(vf, sp_obj)) !=
+ BNX2X_Q_LOGICAL_STATE_ACTIVE)
+ return rc;
- rc = validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj));
- if (rc)
- return rc;
- memset(&ramrod_param, 0, sizeof(ramrod_param));
+ /* configure the vlan in device on this vf's queue */
+ vlan_obj = &bnx2x_leading_vfq(vf, vlan_obj);
+ rc = validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj));
+ if (rc)
+ return rc;
- /* must lock vfpf channel to protect against vf flows */
- bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_VLAN);
+ /* must lock vfpf channel to protect against vf flows */
+ bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_VLAN);
- /* remove existing vlans */
- __set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
- rc = vlan_obj->delete_all(bp, vlan_obj, &vlan_mac_flags,
- &ramrod_flags);
- if (rc) {
- BNX2X_ERR("failed to delete vlans\n");
- rc = -EINVAL;
- goto out;
- }
-
- /* send queue update ramrod to configure default vlan and silent
- * vlan removal
- */
- __set_bit(RAMROD_COMP_WAIT, &q_params.ramrod_flags);
- q_params.cmd = BNX2X_Q_CMD_UPDATE;
- q_params.q_obj = &bnx2x_leading_vfq(vf, sp_obj);
- update_params = &q_params.params.update;
- __set_bit(BNX2X_Q_UPDATE_DEF_VLAN_EN_CHNG,
- &update_params->update_flags);
- __set_bit(BNX2X_Q_UPDATE_SILENT_VLAN_REM_CHNG,
- &update_params->update_flags);
-
- if (vlan == 0) {
- /* if vlan is 0 then we want to leave the VF traffic
- * untagged, and leave the incoming traffic untouched
- * (i.e. do not remove any vlan tags).
- */
- __clear_bit(BNX2X_Q_UPDATE_DEF_VLAN_EN,
- &update_params->update_flags);
- __clear_bit(BNX2X_Q_UPDATE_SILENT_VLAN_REM,
- &update_params->update_flags);
- } else {
- /* configure the new vlan to device */
- __set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
- ramrod_param.vlan_mac_obj = vlan_obj;
- ramrod_param.ramrod_flags = ramrod_flags;
- ramrod_param.user_req.u.vlan.vlan = vlan;
- ramrod_param.user_req.cmd = BNX2X_VLAN_MAC_ADD;
- rc = bnx2x_config_vlan_mac(bp, &ramrod_param);
- if (rc) {
- BNX2X_ERR("failed to configure vlan\n");
- rc = -EINVAL;
- goto out;
- }
-
- /* configure default vlan to vf queue and set silent
- * vlan removal (the vf remains unaware of this vlan).
- */
- update_params = &q_params.params.update;
- __set_bit(BNX2X_Q_UPDATE_DEF_VLAN_EN,
- &update_params->update_flags);
- __set_bit(BNX2X_Q_UPDATE_SILENT_VLAN_REM,
- &update_params->update_flags);
- update_params->def_vlan = vlan;
- }
-
- /* Update the Queue state */
- rc = bnx2x_queue_state_change(bp, &q_params);
- if (rc) {
- BNX2X_ERR("Failed to configure default VLAN\n");
- goto out;
- }
-
- /* clear the flag indicating that this VF needs its vlan
- * (will only be set if the HV configured the Vlan before vf was
- * up and we were called because the VF came up later
- */
-out:
- vf->cfg_flags &= ~VF_CFG_VLAN;
- bnx2x_unlock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_VLAN);
+ /* remove existing vlans */
+ __set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
+ rc = vlan_obj->delete_all(bp, vlan_obj, &vlan_mac_flags,
+ &ramrod_flags);
+ if (rc) {
+ BNX2X_ERR("failed to delete vlans\n");
+ rc = -EINVAL;
+ goto out;
}
+
+ /* need to remove/add the VF's accept_any_vlan bit */
+ accept_flags = bnx2x_leading_vfq(vf, accept_flags);
+ if (vlan)
+ clear_bit(BNX2X_ACCEPT_ANY_VLAN, &accept_flags);
+ else
+ set_bit(BNX2X_ACCEPT_ANY_VLAN, &accept_flags);
+
+ bnx2x_vf_prep_rx_mode(bp, LEADING_IDX, &rx_ramrod, vf,
+ accept_flags);
+ bnx2x_leading_vfq(vf, accept_flags) = accept_flags;
+ bnx2x_config_rx_mode(bp, &rx_ramrod);
+
+ /* configure the new vlan to device */
+ memset(&ramrod_param, 0, sizeof(ramrod_param));
+ __set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
+ ramrod_param.vlan_mac_obj = vlan_obj;
+ ramrod_param.ramrod_flags = ramrod_flags;
+ set_bit(BNX2X_DONT_CONSUME_CAM_CREDIT,
+ &ramrod_param.user_req.vlan_mac_flags);
+ ramrod_param.user_req.u.vlan.vlan = vlan;
+ ramrod_param.user_req.cmd = BNX2X_VLAN_MAC_ADD;
+ rc = bnx2x_config_vlan_mac(bp, &ramrod_param);
+ if (rc) {
+ BNX2X_ERR("failed to configure vlan\n");
+ rc = -EINVAL;
+ goto out;
+ }
+
+ /* send queue update ramrod to configure default vlan and silent
+ * vlan removal
+ */
+ __set_bit(RAMROD_COMP_WAIT, &q_params.ramrod_flags);
+ q_params.cmd = BNX2X_Q_CMD_UPDATE;
+ q_params.q_obj = &bnx2x_leading_vfq(vf, sp_obj);
+ update_params = &q_params.params.update;
+ __set_bit(BNX2X_Q_UPDATE_DEF_VLAN_EN_CHNG,
+ &update_params->update_flags);
+ __set_bit(BNX2X_Q_UPDATE_SILENT_VLAN_REM_CHNG,
+ &update_params->update_flags);
+ if (vlan == 0) {
+ /* if vlan is 0 then we want to leave the VF traffic
+ * untagged, and leave the incoming traffic untouched
+ * (i.e. do not remove any vlan tags).
+ */
+ __clear_bit(BNX2X_Q_UPDATE_DEF_VLAN_EN,
+ &update_params->update_flags);
+ __clear_bit(BNX2X_Q_UPDATE_SILENT_VLAN_REM,
+ &update_params->update_flags);
+ } else {
+ /* configure default vlan to vf queue and set silent
+ * vlan removal (the vf remains unaware of this vlan).
+ */
+ __set_bit(BNX2X_Q_UPDATE_DEF_VLAN_EN,
+ &update_params->update_flags);
+ __set_bit(BNX2X_Q_UPDATE_SILENT_VLAN_REM,
+ &update_params->update_flags);
+ update_params->def_vlan = vlan;
+ update_params->silent_removal_value =
+ vlan & VLAN_VID_MASK;
+ update_params->silent_removal_mask = VLAN_VID_MASK;
+ }
+
+ /* Update the Queue state */
+ rc = bnx2x_queue_state_change(bp, &q_params);
+ if (rc) {
+ BNX2X_ERR("Failed to configure default VLAN\n");
+ goto out;
+ }
+
+
+ /* clear the flag indicating that this VF needs its vlan
+ * (will only be set if the HV configured the Vlan before vf was
+ * up and we were called because the VF came up later
+ */
+out:
+ vf->cfg_flags &= ~VF_CFG_VLAN;
+ bnx2x_unlock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_VLAN);
+
return rc;
}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index 1ff6a93..8c213fa52 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -74,6 +74,7 @@
/* VLANs object */
struct bnx2x_vlan_mac_obj vlan_obj;
atomic_t vlan_count; /* 0 means vlan-0 is set ~ untagged */
+ unsigned long accept_flags; /* last accept flags configured */
/* Queue Slow-path State object */
struct bnx2x_queue_sp_obj sp_obj;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index efa8a15..0756d7d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -208,7 +208,7 @@
return -EINVAL;
}
- BNX2X_ERR("valid ME register value: 0x%08x\n", me_reg);
+ DP(BNX2X_MSG_IOV, "valid ME register value: 0x%08x\n", me_reg);
*vf_id = (me_reg & ME_REG_VF_NUM_MASK) >> ME_REG_VF_NUM_SHIFT;
@@ -1598,6 +1598,8 @@
if (msg->flags & VFPF_SET_Q_FILTERS_RX_MASK_CHANGED) {
unsigned long accept = 0;
+ struct pf_vf_bulletin_content *bulletin =
+ BP_VF_BULLETIN(bp, vf->index);
/* covert VF-PF if mask to bnx2x accept flags */
if (msg->rx_mask & VFPF_RX_MASK_ACCEPT_MATCHED_UNICAST)
@@ -1617,9 +1619,11 @@
__set_bit(BNX2X_ACCEPT_BROADCAST, &accept);
/* A packet arriving the vf's mac should be accepted
- * with any vlan
+ * with any vlan, unless a vlan has already been
+ * configured.
*/
- __set_bit(BNX2X_ACCEPT_ANY_VLAN, &accept);
+ if (!(bulletin->valid_bitmap & (1 << VLAN_VALID)))
+ __set_bit(BNX2X_ACCEPT_ANY_VLAN, &accept);
/* set rx-mode */
rc = bnx2x_vfop_rxmode_cmd(bp, vf, &cmd,
@@ -1710,6 +1714,21 @@
goto response;
}
}
+ /* if vlan was set by hypervisor we don't allow guest to config vlan */
+ if (bulletin->valid_bitmap & 1 << VLAN_VALID) {
+ int i;
+
+ /* search for vlan filters */
+ for (i = 0; i < filters->n_mac_vlan_filters; i++) {
+ if (filters->filters[i].flags &
+ VFPF_Q_FILTER_VLAN_TAG_VALID) {
+ BNX2X_ERR("VF[%d] attempted to configure vlan but one was already set by Hypervisor. Aborting request\n",
+ vf->abs_vfid);
+ vf->op_rc = -EPERM;
+ goto response;
+ }
+ }
+ }
/* verify vf_qid */
if (filters->vf_qid > vf_rxq_count(vf))
@@ -1805,6 +1824,9 @@
vf_op_params->rss_result_mask = rss_tlv->rss_result_mask;
/* flags handled individually for backward/forward compatability */
+ vf_op_params->rss_flags = 0;
+ vf_op_params->ramrod_flags = 0;
+
if (rss_tlv->rss_flags & VFPF_RSS_MODE_DISABLED)
__set_bit(BNX2X_RSS_MODE_DISABLED, &vf_op_params->rss_flags);
if (rss_tlv->rss_flags & VFPF_RSS_MODE_REGULAR)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index f3dd93b..15a66e4 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -7622,7 +7622,7 @@
{
u32 base = (u32) mapping & 0xffffffff;
- return (base > 0xffffdcc0) && (base + len + 8 < base);
+ return base + len + 8 < base;
}
/* Test for TSO DMA buffers that cross into regions which are within MSS bytes
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 6c93088..56e0415 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -228,6 +228,25 @@
uint32_t dack_re; /* DACK timer resolution */
unsigned short tx_modq[NCHAN]; /* channel to modulation queue map */
+
+ u32 vlan_pri_map; /* cached TP_VLAN_PRI_MAP */
+ u32 ingress_config; /* cached TP_INGRESS_CONFIG */
+
+ /* TP_VLAN_PRI_MAP Compressed Filter Tuple field offsets. This is a
+ * subset of the set of fields which may be present in the Compressed
+ * Filter Tuple portion of filters and TCP TCB connections. The
+ * fields which are present are controlled by the TP_VLAN_PRI_MAP.
+ * Since a variable number of fields may or may not be present, their
+ * shifted field positions within the Compressed Filter Tuple may
+ * vary, or not even be present if the field isn't selected in
+ * TP_VLAN_PRI_MAP. Since some of these fields are needed in various
+ * places we store their offsets here, or a -1 if the field isn't
+ * present.
+ */
+ int vlan_shift;
+ int vnic_shift;
+ int port_shift;
+ int protocol_shift;
};
struct vpd_params {
@@ -926,6 +945,8 @@
const u8 *fw_data, unsigned int fw_size,
struct fw_hdr *card_fw, enum dev_state state, int *reset);
int t4_prep_adapter(struct adapter *adapter);
+int t4_init_tp_params(struct adapter *adap);
+int t4_filter_field_shift(const struct adapter *adap, int filter_sel);
int t4_port_init(struct adapter *adap, int mbox, int pf, int vf);
void t4_fatal_err(struct adapter *adapter);
int t4_config_rss_range(struct adapter *adapter, int mbox, unsigned int viid,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index d6b12e0..fff02ed 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2986,7 +2986,14 @@
if (stid >= 0) {
t->stid_tab[stid].data = data;
stid += t->stid_base;
- t->stids_in_use++;
+ /* IPv6 requires max of 520 bits or 16 cells in TCAM
+ * This is equivalent to 4 TIDs. With CLIP enabled it
+ * needs 2 TIDs.
+ */
+ if (family == PF_INET)
+ t->stids_in_use++;
+ else
+ t->stids_in_use += 4;
}
spin_unlock_bh(&t->stid_lock);
return stid;
@@ -3012,7 +3019,8 @@
}
if (stid >= 0) {
t->stid_tab[stid].data = data;
- stid += t->stid_base;
+ stid -= t->nstids;
+ stid += t->sftid_base;
t->stids_in_use++;
}
spin_unlock_bh(&t->stid_lock);
@@ -3024,14 +3032,24 @@
*/
void cxgb4_free_stid(struct tid_info *t, unsigned int stid, int family)
{
- stid -= t->stid_base;
+ /* Is it a server filter TID? */
+ if (t->nsftids && (stid >= t->sftid_base)) {
+ stid -= t->sftid_base;
+ stid += t->nstids;
+ } else {
+ stid -= t->stid_base;
+ }
+
spin_lock_bh(&t->stid_lock);
if (family == PF_INET)
__clear_bit(stid, t->stid_bmap);
else
bitmap_release_region(t->stid_bmap, stid, 2);
t->stid_tab[stid].data = NULL;
- t->stids_in_use--;
+ if (family == PF_INET)
+ t->stids_in_use--;
+ else
+ t->stids_in_use -= 4;
spin_unlock_bh(&t->stid_lock);
}
EXPORT_SYMBOL(cxgb4_free_stid);
@@ -3134,6 +3152,7 @@
size_t size;
unsigned int stid_bmap_size;
unsigned int natids = t->natids;
+ struct adapter *adap = container_of(t, struct adapter, tids);
stid_bmap_size = BITS_TO_LONGS(t->nstids + t->nsftids);
size = t->ntids * sizeof(*t->tid_tab) +
@@ -3167,6 +3186,11 @@
t->afree = t->atid_tab;
}
bitmap_zero(t->stid_bmap, t->nstids + t->nsftids);
+ /* Reserve stid 0 for T4/T5 adapters */
+ if (!t->stid_base &&
+ (is_t4(adap->params.chip) || is_t5(adap->params.chip)))
+ __set_bit(0, t->stid_bmap);
+
return 0;
}
@@ -3731,7 +3755,7 @@
lli.ucq_density = 1 << QUEUESPERPAGEPF0_GET(
t4_read_reg(adap, SGE_INGRESS_QUEUES_PER_PAGE_PF) >>
(adap->fn * 4));
- lli.filt_mode = adap->filter_mode;
+ lli.filt_mode = adap->params.tp.vlan_pri_map;
/* MODQ_REQ_MAP sets queues 0-3 to chan 0-3 */
for (i = 0; i < NCHAN; i++)
lli.tx_modq[i] = i;
@@ -4179,7 +4203,7 @@
adap = netdev2adap(dev);
/* Adjust stid to correct filter index */
- stid -= adap->tids.nstids;
+ stid -= adap->tids.sftid_base;
stid += adap->tids.nftids;
/* Check to make sure the filter requested is writable ...
@@ -4205,12 +4229,17 @@
f->fs.val.lip[i] = val[i];
f->fs.mask.lip[i] = ~0;
}
- if (adap->filter_mode & F_PORT) {
+ if (adap->params.tp.vlan_pri_map & F_PORT) {
f->fs.val.iport = port;
f->fs.mask.iport = mask;
}
}
+ if (adap->params.tp.vlan_pri_map & F_PROTOCOL) {
+ f->fs.val.proto = IPPROTO_TCP;
+ f->fs.mask.proto = ~0;
+ }
+
f->fs.dirsteer = 1;
f->fs.iq = queue;
/* Mark filter as locked */
@@ -4237,7 +4266,7 @@
adap = netdev2adap(dev);
/* Adjust stid to correct filter index */
- stid -= adap->tids.nstids;
+ stid -= adap->tids.sftid_base;
stid += adap->tids.nftids;
f = &adap->tids.ftid_tab[stid];
@@ -5092,7 +5121,7 @@
enum dev_state state;
u32 params[7], val[7];
struct fw_caps_config_cmd caps_cmd;
- int reset = 1, j;
+ int reset = 1;
/*
* Contact FW, advertising Master capability (and potentially forcing
@@ -5434,21 +5463,11 @@
/*
* These are finalized by FW initialization, load their values now.
*/
- v = t4_read_reg(adap, TP_TIMER_RESOLUTION);
- adap->params.tp.tre = TIMERRESOLUTION_GET(v);
- adap->params.tp.dack_re = DELAYEDACKRESOLUTION_GET(v);
t4_read_mtu_tbl(adap, adap->params.mtus, NULL);
t4_load_mtus(adap, adap->params.mtus, adap->params.a_wnd,
adap->params.b_wnd);
- /* MODQ_REQ_MAP defaults to setting queues 0-3 to chan 0-3 */
- for (j = 0; j < NCHAN; j++)
- adap->params.tp.tx_modq[j] = j;
-
- t4_read_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
- &adap->filter_mode, 1,
- TP_VLAN_PRI_MAP);
-
+ t4_init_tp_params(adap);
adap->flags |= FW_OK;
return 0;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 6f21f24..4dd0a82 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -131,7 +131,14 @@
static inline void *lookup_stid(const struct tid_info *t, unsigned int stid)
{
- stid -= t->stid_base;
+ /* Is it a server filter TID? */
+ if (t->nsftids && (stid >= t->sftid_base)) {
+ stid -= t->sftid_base;
+ stid += t->nstids;
+ } else {
+ stid -= t->stid_base;
+ }
+
return stid < (t->nstids + t->nsftids) ? t->stid_tab[stid].data : NULL;
}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index 2987809..cb05be9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -45,6 +45,7 @@
#include "l2t.h"
#include "t4_msg.h"
#include "t4fw_api.h"
+#include "t4_regs.h"
#define VLAN_NONE 0xfff
@@ -411,6 +412,40 @@
}
EXPORT_SYMBOL(cxgb4_l2t_get);
+u64 cxgb4_select_ntuple(struct net_device *dev,
+ const struct l2t_entry *l2t)
+{
+ struct adapter *adap = netdev2adap(dev);
+ struct tp_params *tp = &adap->params.tp;
+ u64 ntuple = 0;
+
+ /* Initialize each of the fields which we care about which are present
+ * in the Compressed Filter Tuple.
+ */
+ if (tp->vlan_shift >= 0 && l2t->vlan != VLAN_NONE)
+ ntuple |= (F_FT_VLAN_VLD | l2t->vlan) << tp->vlan_shift;
+
+ if (tp->port_shift >= 0)
+ ntuple |= (u64)l2t->lport << tp->port_shift;
+
+ if (tp->protocol_shift >= 0)
+ ntuple |= (u64)IPPROTO_TCP << tp->protocol_shift;
+
+ if (tp->vnic_shift >= 0) {
+ u32 viid = cxgb4_port_viid(dev);
+ u32 vf = FW_VIID_VIN_GET(viid);
+ u32 pf = FW_VIID_PFN_GET(viid);
+ u32 vld = FW_VIID_VIVLD_GET(viid);
+
+ ntuple |= (u64)(V_FT_VNID_ID_VF(vf) |
+ V_FT_VNID_ID_PF(pf) |
+ V_FT_VNID_ID_VLD(vld)) << tp->vnic_shift;
+ }
+
+ return ntuple;
+}
+EXPORT_SYMBOL(cxgb4_select_ntuple);
+
/*
* Called when address resolution fails for an L2T entry to handle packets
* on the arpq head. If a packet specifies a failure handler it is invoked,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.h b/drivers/net/ethernet/chelsio/cxgb4/l2t.h
index 108c0f1..85eb5c7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.h
@@ -98,7 +98,8 @@
struct l2t_entry *cxgb4_l2t_get(struct l2t_data *d, struct neighbour *neigh,
const struct net_device *physdev,
unsigned int priority);
-
+u64 cxgb4_select_ntuple(struct net_device *dev,
+ const struct l2t_entry *l2t);
void t4_l2t_update(struct adapter *adap, struct neighbour *neigh);
struct l2t_entry *t4_l2t_alloc_switching(struct l2t_data *d);
int t4_l2t_set_switching(struct adapter *adap, struct l2t_entry *e, u16 vlan,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index cc380c3..cc3511a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -2581,7 +2581,7 @@
#undef READ_FL_BUF
if (fl_small_pg != PAGE_SIZE ||
- (fl_large_pg != 0 && (fl_large_pg <= fl_small_pg ||
+ (fl_large_pg != 0 && (fl_large_pg < fl_small_pg ||
(fl_large_pg & (fl_large_pg-1)) != 0))) {
dev_err(adap->pdev_dev, "bad SGE FL page buffer sizes [%d, %d]\n",
fl_small_pg, fl_large_pg);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 74a6fce..e1413ea 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -3808,6 +3808,109 @@
return 0;
}
+/**
+ * t4_init_tp_params - initialize adap->params.tp
+ * @adap: the adapter
+ *
+ * Initialize various fields of the adapter's TP Parameters structure.
+ */
+int t4_init_tp_params(struct adapter *adap)
+{
+ int chan;
+ u32 v;
+
+ v = t4_read_reg(adap, TP_TIMER_RESOLUTION);
+ adap->params.tp.tre = TIMERRESOLUTION_GET(v);
+ adap->params.tp.dack_re = DELAYEDACKRESOLUTION_GET(v);
+
+ /* MODQ_REQ_MAP defaults to setting queues 0-3 to chan 0-3 */
+ for (chan = 0; chan < NCHAN; chan++)
+ adap->params.tp.tx_modq[chan] = chan;
+
+ /* Cache the adapter's Compressed Filter Mode and global Incress
+ * Configuration.
+ */
+ t4_read_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+ &adap->params.tp.vlan_pri_map, 1,
+ TP_VLAN_PRI_MAP);
+ t4_read_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+ &adap->params.tp.ingress_config, 1,
+ TP_INGRESS_CONFIG);
+
+ /* Now that we have TP_VLAN_PRI_MAP cached, we can calculate the field
+ * shift positions of several elements of the Compressed Filter Tuple
+ * for this adapter which we need frequently ...
+ */
+ adap->params.tp.vlan_shift = t4_filter_field_shift(adap, F_VLAN);
+ adap->params.tp.vnic_shift = t4_filter_field_shift(adap, F_VNIC_ID);
+ adap->params.tp.port_shift = t4_filter_field_shift(adap, F_PORT);
+ adap->params.tp.protocol_shift = t4_filter_field_shift(adap,
+ F_PROTOCOL);
+
+ /* If TP_INGRESS_CONFIG.VNID == 0, then TP_VLAN_PRI_MAP.VNIC_ID
+ * represents the presense of an Outer VLAN instead of a VNIC ID.
+ */
+ if ((adap->params.tp.ingress_config & F_VNIC) == 0)
+ adap->params.tp.vnic_shift = -1;
+
+ return 0;
+}
+
+/**
+ * t4_filter_field_shift - calculate filter field shift
+ * @adap: the adapter
+ * @filter_sel: the desired field (from TP_VLAN_PRI_MAP bits)
+ *
+ * Return the shift position of a filter field within the Compressed
+ * Filter Tuple. The filter field is specified via its selection bit
+ * within TP_VLAN_PRI_MAL (filter mode). E.g. F_VLAN.
+ */
+int t4_filter_field_shift(const struct adapter *adap, int filter_sel)
+{
+ unsigned int filter_mode = adap->params.tp.vlan_pri_map;
+ unsigned int sel;
+ int field_shift;
+
+ if ((filter_mode & filter_sel) == 0)
+ return -1;
+
+ for (sel = 1, field_shift = 0; sel < filter_sel; sel <<= 1) {
+ switch (filter_mode & sel) {
+ case F_FCOE:
+ field_shift += W_FT_FCOE;
+ break;
+ case F_PORT:
+ field_shift += W_FT_PORT;
+ break;
+ case F_VNIC_ID:
+ field_shift += W_FT_VNIC_ID;
+ break;
+ case F_VLAN:
+ field_shift += W_FT_VLAN;
+ break;
+ case F_TOS:
+ field_shift += W_FT_TOS;
+ break;
+ case F_PROTOCOL:
+ field_shift += W_FT_PROTOCOL;
+ break;
+ case F_ETHERTYPE:
+ field_shift += W_FT_ETHERTYPE;
+ break;
+ case F_MACMATCH:
+ field_shift += W_FT_MACMATCH;
+ break;
+ case F_MPSHITTYPE:
+ field_shift += W_FT_MPSHITTYPE;
+ break;
+ case F_FRAGMENTATION:
+ field_shift += W_FT_FRAGMENTATION;
+ break;
+ }
+ }
+ return field_shift;
+}
+
int t4_port_init(struct adapter *adap, int mbox, int pf, int vf)
{
u8 addr[6];
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index 0a8205d..4082522 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1171,10 +1171,50 @@
#define A_TP_TX_SCHED_PCMD 0x25
+#define S_VNIC 11
+#define V_VNIC(x) ((x) << S_VNIC)
+#define F_VNIC V_VNIC(1U)
+
+#define S_FRAGMENTATION 9
+#define V_FRAGMENTATION(x) ((x) << S_FRAGMENTATION)
+#define F_FRAGMENTATION V_FRAGMENTATION(1U)
+
+#define S_MPSHITTYPE 8
+#define V_MPSHITTYPE(x) ((x) << S_MPSHITTYPE)
+#define F_MPSHITTYPE V_MPSHITTYPE(1U)
+
+#define S_MACMATCH 7
+#define V_MACMATCH(x) ((x) << S_MACMATCH)
+#define F_MACMATCH V_MACMATCH(1U)
+
+#define S_ETHERTYPE 6
+#define V_ETHERTYPE(x) ((x) << S_ETHERTYPE)
+#define F_ETHERTYPE V_ETHERTYPE(1U)
+
+#define S_PROTOCOL 5
+#define V_PROTOCOL(x) ((x) << S_PROTOCOL)
+#define F_PROTOCOL V_PROTOCOL(1U)
+
+#define S_TOS 4
+#define V_TOS(x) ((x) << S_TOS)
+#define F_TOS V_TOS(1U)
+
+#define S_VLAN 3
+#define V_VLAN(x) ((x) << S_VLAN)
+#define F_VLAN V_VLAN(1U)
+
+#define S_VNIC_ID 2
+#define V_VNIC_ID(x) ((x) << S_VNIC_ID)
+#define F_VNIC_ID V_VNIC_ID(1U)
+
#define S_PORT 1
#define V_PORT(x) ((x) << S_PORT)
#define F_PORT V_PORT(1U)
+#define S_FCOE 0
+#define V_FCOE(x) ((x) << S_FCOE)
+#define F_FCOE V_FCOE(1U)
+
#define NUM_MPS_CLS_SRAM_L_INSTANCES 336
#define NUM_MPS_T5_CLS_SRAM_L_INSTANCES 512
@@ -1213,4 +1253,37 @@
#define V_CHIPID(x) ((x) << S_CHIPID)
#define G_CHIPID(x) (((x) >> S_CHIPID) & M_CHIPID)
+/* TP_VLAN_PRI_MAP controls which subset of fields will be present in the
+ * Compressed Filter Tuple for LE filters. Each bit set in TP_VLAN_PRI_MAP
+ * selects for a particular field being present. These fields, when present
+ * in the Compressed Filter Tuple, have the following widths in bits.
+ */
+#define W_FT_FCOE 1
+#define W_FT_PORT 3
+#define W_FT_VNIC_ID 17
+#define W_FT_VLAN 17
+#define W_FT_TOS 8
+#define W_FT_PROTOCOL 8
+#define W_FT_ETHERTYPE 16
+#define W_FT_MACMATCH 9
+#define W_FT_MPSHITTYPE 3
+#define W_FT_FRAGMENTATION 1
+
+/* Some of the Compressed Filter Tuple fields have internal structure. These
+ * bit shifts/masks describe those structures. All shifts are relative to the
+ * base position of the fields within the Compressed Filter Tuple
+ */
+#define S_FT_VLAN_VLD 16
+#define V_FT_VLAN_VLD(x) ((x) << S_FT_VLAN_VLD)
+#define F_FT_VLAN_VLD V_FT_VLAN_VLD(1U)
+
+#define S_FT_VNID_ID_VF 0
+#define V_FT_VNID_ID_VF(x) ((x) << S_FT_VNID_ID_VF)
+
+#define S_FT_VNID_ID_PF 7
+#define V_FT_VNID_ID_PF(x) ((x) << S_FT_VNID_ID_PF)
+
+#define S_FT_VNID_ID_VLD 16
+#define V_FT_VNID_ID_VLD(x) ((x) << S_FT_VNID_ID_VLD)
+
#endif /* __T4_REGS_H */
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 5878df6..4ccaf9a 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -104,6 +104,7 @@
#define BE3_MAX_RSS_QS 16
#define BE3_MAX_TX_QS 16
#define BE3_MAX_EVT_QS 16
+#define BE3_SRIOV_MAX_EVT_QS 8
#define MAX_RX_QS 32
#define MAX_EVT_QS 32
@@ -480,7 +481,7 @@
struct list_head entry;
u32 flash_status;
- struct completion flash_compl;
+ struct completion et_cmd_compl;
struct be_resources res; /* resources available for the func */
u16 num_vfs; /* Number of VFs provisioned by PF */
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index e0e8bc1..94c35c8 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -141,11 +141,17 @@
subsystem = resp_hdr->subsystem;
}
+ if (opcode == OPCODE_LOWLEVEL_LOOPBACK_TEST &&
+ subsystem == CMD_SUBSYSTEM_LOWLEVEL) {
+ complete(&adapter->et_cmd_compl);
+ return 0;
+ }
+
if (((opcode == OPCODE_COMMON_WRITE_FLASHROM) ||
(opcode == OPCODE_COMMON_WRITE_OBJECT)) &&
(subsystem == CMD_SUBSYSTEM_COMMON)) {
adapter->flash_status = compl_status;
- complete(&adapter->flash_compl);
+ complete(&adapter->et_cmd_compl);
}
if (compl_status == MCC_STATUS_SUCCESS) {
@@ -2017,6 +2023,9 @@
0x3ea83c02, 0x4a110304};
int status;
+ if (!(be_if_cap_flags(adapter) & BE_IF_FLAGS_RSS))
+ return 0;
+
if (mutex_lock_interruptible(&adapter->mbox_lock))
return -1;
@@ -2160,7 +2169,7 @@
be_mcc_notify(adapter);
spin_unlock_bh(&adapter->mcc_lock);
- if (!wait_for_completion_timeout(&adapter->flash_compl,
+ if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
msecs_to_jiffies(60000)))
status = -1;
else
@@ -2255,8 +2264,8 @@
be_mcc_notify(adapter);
spin_unlock_bh(&adapter->mcc_lock);
- if (!wait_for_completion_timeout(&adapter->flash_compl,
- msecs_to_jiffies(40000)))
+ if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
+ msecs_to_jiffies(40000)))
status = -1;
else
status = adapter->flash_status;
@@ -2367,6 +2376,7 @@
{
struct be_mcc_wrb *wrb;
struct be_cmd_req_loopback_test *req;
+ struct be_cmd_resp_loopback_test *resp;
int status;
spin_lock_bh(&adapter->mcc_lock);
@@ -2381,8 +2391,8 @@
be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_LOWLEVEL,
OPCODE_LOWLEVEL_LOOPBACK_TEST, sizeof(*req), wrb, NULL);
- req->hdr.timeout = cpu_to_le32(4);
+ req->hdr.timeout = cpu_to_le32(15);
req->pattern = cpu_to_le64(pattern);
req->src_port = cpu_to_le32(port_num);
req->dest_port = cpu_to_le32(port_num);
@@ -2390,12 +2400,15 @@
req->num_pkts = cpu_to_le32(num_pkts);
req->loopback_type = cpu_to_le32(loopback_type);
- status = be_mcc_notify_wait(adapter);
- if (!status) {
- struct be_cmd_resp_loopback_test *resp = embedded_payload(wrb);
- status = le32_to_cpu(resp->status);
- }
+ be_mcc_notify(adapter);
+ spin_unlock_bh(&adapter->mcc_lock);
+
+ wait_for_completion(&adapter->et_cmd_compl);
+ resp = embedded_payload(wrb);
+ status = le32_to_cpu(resp->status);
+
+ return status;
err:
spin_unlock_bh(&adapter->mcc_lock);
return status;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 0fde69d..bf40fda 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -2744,13 +2744,16 @@
if (!BEx_chip(adapter))
adapter->rss_flags |= RSS_ENABLE_UDP_IPV4 |
RSS_ENABLE_UDP_IPV6;
+ } else {
+ /* Disable RSS, if only default RX Q is created */
+ adapter->rss_flags = RSS_ENABLE_NONE;
+ }
- rc = be_cmd_rss_config(adapter, rsstable, adapter->rss_flags,
- 128);
- if (rc) {
- adapter->rss_flags = 0;
- return rc;
- }
+ rc = be_cmd_rss_config(adapter, rsstable, adapter->rss_flags,
+ 128);
+ if (rc) {
+ adapter->rss_flags = RSS_ENABLE_NONE;
+ return rc;
}
/* First time posting */
@@ -3124,11 +3127,11 @@
{
struct pci_dev *pdev = adapter->pdev;
bool use_sriov = false;
+ int max_vfs;
+
+ max_vfs = pci_sriov_get_totalvfs(pdev);
if (BE3_chip(adapter) && sriov_want(adapter)) {
- int max_vfs;
-
- max_vfs = pci_sriov_get_totalvfs(pdev);
res->max_vfs = max_vfs > 0 ? min(MAX_VFS, max_vfs) : 0;
use_sriov = res->max_vfs;
}
@@ -3159,7 +3162,11 @@
BE3_MAX_RSS_QS : BE2_MAX_RSS_QS;
res->max_rx_qs = res->max_rss_qs + 1;
- res->max_evt_qs = be_physfn(adapter) ? BE3_MAX_EVT_QS : 1;
+ if (be_physfn(adapter))
+ res->max_evt_qs = (max_vfs > 0) ?
+ BE3_SRIOV_MAX_EVT_QS : BE3_MAX_EVT_QS;
+ else
+ res->max_evt_qs = 1;
res->if_cap_flags = BE_IF_CAP_FLAGS_WANT;
if (!(adapter->function_caps & BE_FUNCTION_CAPS_RSS))
@@ -4205,7 +4212,7 @@
spin_lock_init(&adapter->mcc_lock);
spin_lock_init(&adapter->mcc_cq_lock);
- init_completion(&adapter->flash_compl);
+ init_completion(&adapter->et_cmd_compl);
pci_save_state(adapter->pdev);
return 0;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index e7c8b74..50bb71c 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -428,6 +428,8 @@
/* If this was the last BD in the ring, start at the beginning again. */
bdp = fec_enet_get_nextdesc(bdp, fep);
+ skb_tx_timestamp(skb);
+
fep->cur_tx = bdp;
if (fep->cur_tx == fep->dirty_tx)
@@ -436,8 +438,6 @@
/* Trigger transmission start */
writel(0, fep->hwp + FEC_X_DES_ACTIVE);
- skb_tx_timestamp(skb);
-
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
index 895450e..ff2d806 100644
--- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c
+++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
@@ -718,8 +718,11 @@
e1000_release_phy_80003es2lan(hw);
/* Disable IBIST slave mode (far-end loopback) */
- e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
- &kum_reg_data);
+ ret_val =
+ e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
+ &kum_reg_data);
+ if (ret_val)
+ return ret_val;
kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE;
e1000_write_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
kum_reg_data);
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 8d3945a..c30d41d 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6174,7 +6174,7 @@
return 0;
}
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
static int e1000_suspend(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
@@ -6193,7 +6193,7 @@
return __e1000_resume(pdev);
}
-#endif /* CONFIG_PM_SLEEP */
+#endif /* CONFIG_PM */
#ifdef CONFIG_PM_RUNTIME
static int e1000_runtime_suspend(struct device *dev)
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index da2be59..20e71f4 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -1757,19 +1757,23 @@
* it across the board.
*/
ret_val = e1e_rphy(hw, MII_BMSR, &phy_status);
- if (ret_val)
+ if (ret_val) {
/* If the first read fails, another entity may have
* ownership of the resources, wait and try again to
* see if they have relinquished the resources yet.
*/
- udelay(usec_interval);
+ if (usec_interval >= 1000)
+ msleep(usec_interval / 1000);
+ else
+ udelay(usec_interval);
+ }
ret_val = e1e_rphy(hw, MII_BMSR, &phy_status);
if (ret_val)
break;
if (phy_status & BMSR_LSTATUS)
break;
if (usec_interval >= 1000)
- mdelay(usec_interval / 1000);
+ msleep(usec_interval / 1000);
else
udelay(usec_interval);
}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index cc06854..5bcc870 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6827,12 +6827,20 @@
return __ixgbe_maybe_stop_tx(tx_ring, size);
}
-#ifdef IXGBE_FCOE
-static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
+ struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
+#ifdef IXGBE_FCOE
struct ixgbe_adapter *adapter;
struct ixgbe_ring_feature *f;
int txq;
+#endif
+
+ if (fwd_adapter)
+ return skb->queue_mapping + fwd_adapter->tx_base_queue;
+
+#ifdef IXGBE_FCOE
/*
* only execute the code below if protocol is FCoE
@@ -6858,9 +6866,11 @@
txq -= f->indices;
return txq + f->offset;
+#else
+ return __netdev_pick_tx(dev, skb);
+#endif
}
-#endif
netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
struct ixgbe_adapter *adapter,
struct ixgbe_ring *tx_ring)
@@ -7629,27 +7639,11 @@
kfree(fwd_adapter);
}
-static netdev_tx_t ixgbe_fwd_xmit(struct sk_buff *skb,
- struct net_device *dev,
- void *priv)
-{
- struct ixgbe_fwd_adapter *fwd_adapter = priv;
- unsigned int queue;
- struct ixgbe_ring *tx_ring;
-
- queue = skb->queue_mapping + fwd_adapter->tx_base_queue;
- tx_ring = fwd_adapter->real_adapter->tx_ring[queue];
-
- return __ixgbe_xmit_frame(skb, dev, tx_ring);
-}
-
static const struct net_device_ops ixgbe_netdev_ops = {
.ndo_open = ixgbe_open,
.ndo_stop = ixgbe_close,
.ndo_start_xmit = ixgbe_xmit_frame,
-#ifdef IXGBE_FCOE
.ndo_select_queue = ixgbe_select_queue,
-#endif
.ndo_set_rx_mode = ixgbe_set_rx_mode,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = ixgbe_set_mac,
@@ -7689,7 +7683,6 @@
.ndo_bridge_getlink = ixgbe_ndo_bridge_getlink,
.ndo_dfwd_add_station = ixgbe_fwd_add,
.ndo_dfwd_del_station = ixgbe_fwd_del,
- .ndo_dfwd_start_xmit = ixgbe_fwd_xmit,
};
/**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index d6f0c0d..72084f7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -291,7 +291,9 @@
{
struct ixgbe_adapter *adapter = pci_get_drvdata(dev);
int err;
+#ifdef CONFIG_PCI_IOV
u32 current_flags = adapter->flags;
+#endif
err = ixgbe_disable_sriov(adapter);
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 6a6c1f7..ec94a20 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -619,7 +619,8 @@
}
static u16
-ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb)
+ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
/* we are currently only using the first queue */
return 0;
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index 7354960..c4eeb69 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -92,6 +92,12 @@
if (time_is_before_jiffies(end))
++timedout;
} else {
+ /* wait_event_timeout does not guarantee a delay of at
+ * least one whole jiffie, so timeout must be no less
+ * than two.
+ */
+ if (timeout < 2)
+ timeout = 2;
wait_event_timeout(dev->smi_busy_wait,
orion_mdio_smi_is_done(dev),
timeout);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index f54ebd5..a7fcd59 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -592,7 +592,8 @@
}
}
-u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb)
+u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
u16 rings_p_up = priv->num_tx_rings_p_up;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index f3758de..d5758ad 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -714,7 +714,8 @@
int mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
void mlx4_en_tx_irq(struct mlx4_cq *mcq);
-u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb);
+u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv);
netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
index 7692dfd..cc68657 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
@@ -1604,13 +1604,13 @@
u32 seq_number;
u8 vhdr_len = 0;
- if (unlikely(ring > adapter->max_rds_rings))
+ if (unlikely(ring >= adapter->max_rds_rings))
return NULL;
rds_ring = &recv_ctx->rds_rings[ring];
index = netxen_get_lro_sts_refhandle(sts_data0);
- if (unlikely(index > rds_ring->num_desc))
+ if (unlikely(index >= rds_ring->num_desc))
return NULL;
buffer = &rds_ring->rx_buf_arr[index];
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 631ea0a..f2a7c71 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -487,6 +487,7 @@
struct qlcnic_mailbox *mailbox;
u8 extend_lb_time;
u8 phys_port_id[ETH_ALEN];
+ u8 lb_mode;
};
struct qlcnic_adapter_stats {
@@ -578,6 +579,8 @@
dma_addr_t phys_addr;
dma_addr_t hw_cons_phys_addr;
struct netdev_queue *txq;
+ /* Lock to protect Tx descriptors cleanup */
+ spinlock_t tx_clean_lock;
} ____cacheline_internodealigned_in_smp;
/*
@@ -808,6 +811,7 @@
#define QLCNIC_ILB_MODE 0x1
#define QLCNIC_ELB_MODE 0x2
+#define QLCNIC_LB_MODE_MASK 0x3
#define QLCNIC_LINKEVENT 0x1
#define QLCNIC_LB_RESPONSE 0x2
@@ -1093,7 +1097,6 @@
struct qlcnic_filter_hash rx_fhash;
struct list_head vf_mc_list;
- spinlock_t tx_clean_lock;
spinlock_t mac_learn_lock;
/* spinlock for catching rcv filters for eswitch traffic */
spinlock_t rx_mac_learn_lock;
@@ -1708,6 +1711,7 @@
void qlcnic_83xx_detach_mailbox_work(struct qlcnic_adapter *);
void qlcnic_83xx_reinit_mbx_work(struct qlcnic_mailbox *mbx);
void qlcnic_83xx_free_mailbox(struct qlcnic_mailbox *mbx);
+void qlcnic_update_stats(struct qlcnic_adapter *);
/* Adapter hardware abstraction */
struct qlcnic_hardware_ops {
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index b1cb0ff..f776f99 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -447,8 +447,9 @@
qlcnic_83xx_poll_process_aen(adapter);
- if (ahw->diag_test == QLCNIC_INTERRUPT_TEST) {
- ahw->diag_cnt++;
+ if (ahw->diag_test) {
+ if (ahw->diag_test == QLCNIC_INTERRUPT_TEST)
+ ahw->diag_cnt++;
qlcnic_83xx_enable_legacy_msix_mbx_intr(adapter);
return IRQ_HANDLED;
}
@@ -1345,11 +1346,6 @@
}
if (adapter->ahw->diag_test == QLCNIC_LOOPBACK_TEST) {
- /* disable and free mailbox interrupt */
- if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) {
- qlcnic_83xx_enable_mbx_poll(adapter);
- qlcnic_83xx_free_mbx_intr(adapter);
- }
adapter->ahw->loopback_state = 0;
adapter->ahw->hw_ops->setup_link_event(adapter, 1);
}
@@ -1363,33 +1359,20 @@
{
struct qlcnic_adapter *adapter = netdev_priv(netdev);
struct qlcnic_host_sds_ring *sds_ring;
- int ring, err;
+ int ring;
clear_bit(__QLCNIC_DEV_UP, &adapter->state);
if (adapter->ahw->diag_test == QLCNIC_INTERRUPT_TEST) {
for (ring = 0; ring < adapter->drv_sds_rings; ring++) {
sds_ring = &adapter->recv_ctx->sds_rings[ring];
- qlcnic_83xx_disable_intr(adapter, sds_ring);
- if (!(adapter->flags & QLCNIC_MSIX_ENABLED))
- qlcnic_83xx_enable_mbx_poll(adapter);
+ if (adapter->flags & QLCNIC_MSIX_ENABLED)
+ qlcnic_83xx_disable_intr(adapter, sds_ring);
}
}
qlcnic_fw_destroy_ctx(adapter);
qlcnic_detach(adapter);
- if (adapter->ahw->diag_test == QLCNIC_LOOPBACK_TEST) {
- if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) {
- err = qlcnic_83xx_setup_mbx_intr(adapter);
- qlcnic_83xx_disable_mbx_poll(adapter);
- if (err) {
- dev_err(&adapter->pdev->dev,
- "%s: failed to setup mbx interrupt\n",
- __func__);
- goto out;
- }
- }
- }
adapter->ahw->diag_test = 0;
adapter->drv_sds_rings = drv_sds_rings;
@@ -1399,9 +1382,6 @@
if (netif_running(netdev))
__qlcnic_up(adapter, netdev);
- if (adapter->ahw->diag_test == QLCNIC_INTERRUPT_TEST &&
- !(adapter->flags & QLCNIC_MSIX_ENABLED))
- qlcnic_83xx_disable_mbx_poll(adapter);
out:
netif_device_attach(netdev);
}
@@ -1704,12 +1684,6 @@
}
} while ((adapter->ahw->linkup && ahw->has_link_events) != 1);
- /* Make sure carrier is off and queue is stopped during loopback */
- if (netif_running(netdev)) {
- netif_carrier_off(netdev);
- netif_tx_stop_all_queues(netdev);
- }
-
ret = qlcnic_do_lb_test(adapter, mode);
qlcnic_83xx_clear_lb_mode(adapter, mode);
@@ -2141,6 +2115,7 @@
ahw->link_autoneg = MSB(MSW(data[3]));
ahw->module_type = MSB(LSW(data[3]));
ahw->has_link_events = 1;
+ ahw->lb_mode = data[4] & QLCNIC_LB_MODE_MASK;
qlcnic_advert_link_change(adapter, link_status);
}
@@ -3754,6 +3729,19 @@
return;
}
+static inline void qlcnic_dump_mailbox_registers(struct qlcnic_adapter *adapter)
+{
+ struct qlcnic_hardware_context *ahw = adapter->ahw;
+ u32 offset;
+
+ offset = QLCRDX(ahw, QLCNIC_DEF_INT_MASK);
+ dev_info(&adapter->pdev->dev, "Mbx interrupt mask=0x%x, Mbx interrupt enable=0x%x, Host mbx control=0x%x, Fw mbx control=0x%x",
+ readl(ahw->pci_base0 + offset),
+ QLCRDX(ahw, QLCNIC_MBX_INTR_ENBL),
+ QLCRDX(ahw, QLCNIC_HOST_MBX_CTRL),
+ QLCRDX(ahw, QLCNIC_FW_MBX_CTRL));
+}
+
static void qlcnic_83xx_mailbox_worker(struct work_struct *work)
{
struct qlcnic_mailbox *mbx = container_of(work, struct qlcnic_mailbox,
@@ -3798,6 +3786,8 @@
__func__, cmd->cmd_op, cmd->type, ahw->pci_func,
ahw->op_mode);
clear_bit(QLC_83XX_MBX_READY, &mbx->status);
+ qlcnic_dump_mailbox_registers(adapter);
+ qlcnic_83xx_get_mbx_data(adapter, cmd);
qlcnic_dump_mbx(adapter, cmd);
qlcnic_83xx_idc_request_reset(adapter,
QLCNIC_FORCE_FW_DUMP_KEY);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
index 4cae6ca..a6a3350 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
@@ -662,4 +662,5 @@
pci_channel_state_t);
pci_ers_result_t qlcnic_83xx_io_slot_reset(struct pci_dev *);
void qlcnic_83xx_io_resume(struct pci_dev *);
+void qlcnic_83xx_stop_hw(struct qlcnic_adapter *);
#endif
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index 89208e5..918e18d 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -740,6 +740,7 @@
adapter->ahw->idc.err_code = -EIO;
dev_err(&adapter->pdev->dev,
"%s: Device in unknown state\n", __func__);
+ clear_bit(__QLCNIC_RESETTING, &adapter->state);
return 0;
}
@@ -818,7 +819,6 @@
struct qlcnic_hardware_context *ahw = adapter->ahw;
struct qlcnic_mailbox *mbx = ahw->mailbox;
int ret = 0;
- u32 owner;
u32 val;
/* Perform NIC configuration based ready state entry actions */
@@ -848,9 +848,9 @@
set_bit(__QLCNIC_RESETTING, &adapter->state);
qlcnic_83xx_idc_enter_need_reset_state(adapter, 1);
} else {
- owner = qlcnic_83xx_idc_find_reset_owner_id(adapter);
- if (ahw->pci_func == owner)
- qlcnic_dump_fw(adapter);
+ netdev_info(adapter->netdev, "%s: Auto firmware recovery is disabled\n",
+ __func__);
+ qlcnic_83xx_idc_enter_failed_state(adapter, 1);
}
return -EIO;
}
@@ -948,13 +948,26 @@
return 0;
}
-static int qlcnic_83xx_idc_failed_state(struct qlcnic_adapter *adapter)
+static void qlcnic_83xx_idc_failed_state(struct qlcnic_adapter *adapter)
{
- dev_err(&adapter->pdev->dev, "%s: please restart!!\n", __func__);
- clear_bit(__QLCNIC_RESETTING, &adapter->state);
- adapter->ahw->idc.err_code = -EIO;
+ struct qlcnic_hardware_context *ahw = adapter->ahw;
+ u32 val, owner;
- return 0;
+ val = QLCRDX(adapter->ahw, QLC_83XX_IDC_CTRL);
+ if (val & QLC_83XX_IDC_DISABLE_FW_RESET_RECOVERY) {
+ owner = qlcnic_83xx_idc_find_reset_owner_id(adapter);
+ if (ahw->pci_func == owner) {
+ qlcnic_83xx_stop_hw(adapter);
+ qlcnic_dump_fw(adapter);
+ }
+ }
+
+ netdev_warn(adapter->netdev, "%s: Reboot will be required to recover the adapter!!\n",
+ __func__);
+ clear_bit(__QLCNIC_RESETTING, &adapter->state);
+ ahw->idc.err_code = -EIO;
+
+ return;
}
static int qlcnic_83xx_idc_quiesce_state(struct qlcnic_adapter *adapter)
@@ -1063,12 +1076,6 @@
adapter->ahw->idc.prev_state = adapter->ahw->idc.curr_state;
qlcnic_83xx_periodic_tasks(adapter);
- /* Do not reschedule if firmaware is in hanged state and auto
- * recovery is disabled
- */
- if ((adapter->flags & QLCNIC_FW_HANG) && !qlcnic_auto_fw_reset)
- return;
-
/* Re-schedule the function */
if (test_bit(QLC_83XX_MODULE_LOADED, &adapter->ahw->idc.status))
qlcnic_schedule_work(adapter, qlcnic_83xx_idc_poll_dev_state,
@@ -1219,10 +1226,10 @@
}
val = QLCRDX(adapter->ahw, QLC_83XX_IDC_CTRL);
- if ((val & QLC_83XX_IDC_DISABLE_FW_RESET_RECOVERY) ||
- !qlcnic_auto_fw_reset) {
- dev_err(&adapter->pdev->dev,
- "%s:failed, device in non reset mode\n", __func__);
+ if (val & QLC_83XX_IDC_DISABLE_FW_RESET_RECOVERY) {
+ netdev_info(adapter->netdev, "%s: Auto firmware recovery is disabled\n",
+ __func__);
+ qlcnic_83xx_idc_enter_failed_state(adapter, 0);
qlcnic_83xx_unlock_driver(adapter);
return;
}
@@ -1254,24 +1261,24 @@
if (size & 0xF)
size = (size + 16) & ~0xF;
- p_cache = kzalloc(size, GFP_KERNEL);
+ p_cache = vzalloc(size);
if (p_cache == NULL)
return -ENOMEM;
ret = qlcnic_83xx_lockless_flash_read32(adapter, src, p_cache,
size / sizeof(u32));
if (ret) {
- kfree(p_cache);
+ vfree(p_cache);
return ret;
}
/* 16 byte write to MS memory */
ret = qlcnic_83xx_ms_mem_write128(adapter, dest, (u32 *)p_cache,
size / 16);
if (ret) {
- kfree(p_cache);
+ vfree(p_cache);
return ret;
}
- kfree(p_cache);
+ vfree(p_cache);
return ret;
}
@@ -1939,7 +1946,7 @@
p_dev->ahw->reset.seq_index = index;
}
-static void qlcnic_83xx_stop_hw(struct qlcnic_adapter *p_dev)
+void qlcnic_83xx_stop_hw(struct qlcnic_adapter *p_dev)
{
p_dev->ahw->reset.seq_index = 0;
@@ -1994,6 +2001,14 @@
val = QLCRDX(adapter->ahw, QLC_83XX_IDC_CTRL);
if (!(val & QLC_83XX_IDC_GRACEFULL_RESET))
qlcnic_dump_fw(adapter);
+
+ if (val & QLC_83XX_IDC_DISABLE_FW_RESET_RECOVERY) {
+ netdev_info(adapter->netdev, "%s: Auto firmware recovery is disabled\n",
+ __func__);
+ qlcnic_83xx_idc_enter_failed_state(adapter, 1);
+ return err;
+ }
+
qlcnic_83xx_init_hw(adapter);
if (qlcnic_83xx_copy_bootloader(adapter))
@@ -2073,8 +2088,8 @@
ahw->nic_mode = QLCNIC_DEFAULT_MODE;
adapter->nic_ops->init_driver = qlcnic_83xx_init_default_driver;
ahw->idc.state_entry = qlcnic_83xx_idc_ready_state_entry;
- adapter->max_sds_rings = ahw->max_rx_ques;
- adapter->max_tx_rings = ahw->max_tx_ques;
+ adapter->max_sds_rings = QLCNIC_MAX_SDS_RINGS;
+ adapter->max_tx_rings = QLCNIC_MAX_TX_RINGS;
} else {
return -EIO;
}
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index b36c02f..6b08194 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -167,27 +167,35 @@
#define QLCNIC_TEST_LEN ARRAY_SIZE(qlcnic_gstrings_test)
-static inline int qlcnic_82xx_statistics(void)
+static inline int qlcnic_82xx_statistics(struct qlcnic_adapter *adapter)
{
- return ARRAY_SIZE(qlcnic_device_gstrings_stats) +
- ARRAY_SIZE(qlcnic_83xx_mac_stats_strings);
+ return ARRAY_SIZE(qlcnic_gstrings_stats) +
+ ARRAY_SIZE(qlcnic_83xx_mac_stats_strings) +
+ QLCNIC_TX_STATS_LEN * adapter->drv_tx_rings;
}
-static inline int qlcnic_83xx_statistics(void)
+static inline int qlcnic_83xx_statistics(struct qlcnic_adapter *adapter)
{
- return ARRAY_SIZE(qlcnic_83xx_tx_stats_strings) +
+ return ARRAY_SIZE(qlcnic_gstrings_stats) +
+ ARRAY_SIZE(qlcnic_83xx_tx_stats_strings) +
ARRAY_SIZE(qlcnic_83xx_mac_stats_strings) +
- ARRAY_SIZE(qlcnic_83xx_rx_stats_strings);
+ ARRAY_SIZE(qlcnic_83xx_rx_stats_strings) +
+ QLCNIC_TX_STATS_LEN * adapter->drv_tx_rings;
}
static int qlcnic_dev_statistics_len(struct qlcnic_adapter *adapter)
{
- if (qlcnic_82xx_check(adapter))
- return qlcnic_82xx_statistics();
- else if (qlcnic_83xx_check(adapter))
- return qlcnic_83xx_statistics();
- else
- return -1;
+ int len = -1;
+
+ if (qlcnic_82xx_check(adapter)) {
+ len = qlcnic_82xx_statistics(adapter);
+ if (adapter->flags & QLCNIC_ESWITCH_ENABLED)
+ len += ARRAY_SIZE(qlcnic_device_gstrings_stats);
+ } else if (qlcnic_83xx_check(adapter)) {
+ len = qlcnic_83xx_statistics(adapter);
+ }
+
+ return len;
}
#define QLCNIC_TX_INTR_NOT_CONFIGURED 0X78563412
@@ -667,30 +675,25 @@
static int qlcnic_validate_ring_count(struct qlcnic_adapter *adapter,
u8 rx_ring, u8 tx_ring)
{
+ if (rx_ring == 0 || tx_ring == 0)
+ return -EINVAL;
+
if (rx_ring != 0) {
if (rx_ring > adapter->max_sds_rings) {
- netdev_err(adapter->netdev, "Invalid ring count, SDS ring count %d should not be greater than max %d driver sds rings.\n",
+ netdev_err(adapter->netdev,
+ "Invalid ring count, SDS ring count %d should not be greater than max %d driver sds rings.\n",
rx_ring, adapter->max_sds_rings);
return -EINVAL;
}
}
if (tx_ring != 0) {
- if (qlcnic_82xx_check(adapter) &&
- (tx_ring > adapter->max_tx_rings)) {
+ if (tx_ring > adapter->max_tx_rings) {
netdev_err(adapter->netdev,
"Invalid ring count, Tx ring count %d should not be greater than max %d driver Tx rings.\n",
tx_ring, adapter->max_tx_rings);
return -EINVAL;
}
-
- if (qlcnic_83xx_check(adapter) &&
- (tx_ring > QLCNIC_SINGLE_RING)) {
- netdev_err(adapter->netdev,
- "Invalid ring count, Tx ring count %d should not be greater than %d driver Tx rings.\n",
- tx_ring, QLCNIC_SINGLE_RING);
- return -EINVAL;
- }
}
return 0;
@@ -925,18 +928,13 @@
static int qlcnic_get_sset_count(struct net_device *dev, int sset)
{
- int len;
struct qlcnic_adapter *adapter = netdev_priv(dev);
switch (sset) {
case ETH_SS_TEST:
return QLCNIC_TEST_LEN;
case ETH_SS_STATS:
- len = qlcnic_dev_statistics_len(adapter) + QLCNIC_STATS_LEN;
- if ((adapter->flags & QLCNIC_ESWITCH_ENABLED) ||
- qlcnic_83xx_check(adapter))
- return len;
- return qlcnic_82xx_statistics();
+ return qlcnic_dev_statistics_len(adapter);
default:
return -EOPNOTSUPP;
}
@@ -948,6 +946,7 @@
struct qlcnic_hardware_context *ahw = adapter->ahw;
struct qlcnic_cmd_args cmd;
int ret, drv_sds_rings = adapter->drv_sds_rings;
+ int drv_tx_rings = adapter->drv_tx_rings;
if (qlcnic_83xx_check(adapter))
return qlcnic_83xx_interrupt_test(netdev);
@@ -980,6 +979,7 @@
clear_diag_irq:
adapter->drv_sds_rings = drv_sds_rings;
+ adapter->drv_tx_rings = drv_tx_rings;
clear_bit(__QLCNIC_RESETTING, &adapter->state);
return ret;
@@ -1270,7 +1270,7 @@
return data;
}
-static void qlcnic_update_stats(struct qlcnic_adapter *adapter)
+void qlcnic_update_stats(struct qlcnic_adapter *adapter)
{
struct qlcnic_host_tx_ring *tx_ring;
int ring;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c
index e9c21e5..c4262c2 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c
@@ -134,6 +134,8 @@
struct qlcnic_skb_frag *buffrag;
int i, j;
+ spin_lock(&tx_ring->tx_clean_lock);
+
cmd_buf = tx_ring->cmd_buf_arr;
for (i = 0; i < tx_ring->num_desc; i++) {
buffrag = cmd_buf->frag_array;
@@ -157,6 +159,8 @@
}
cmd_buf++;
}
+
+ spin_unlock(&tx_ring->tx_clean_lock);
}
void qlcnic_free_sw_resources(struct qlcnic_adapter *adapter)
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index 0149c94..ad1531a 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -687,17 +687,15 @@
if (adapter->ahw->linkup && !linkup) {
netdev_info(netdev, "NIC Link is down\n");
adapter->ahw->linkup = 0;
- if (netif_running(netdev)) {
- netif_carrier_off(netdev);
- netif_tx_stop_all_queues(netdev);
- }
+ netif_carrier_off(netdev);
} else if (!adapter->ahw->linkup && linkup) {
+ /* Do not advertise Link up if the port is in loopback mode */
+ if (qlcnic_83xx_check(adapter) && adapter->ahw->lb_mode)
+ return;
+
netdev_info(netdev, "NIC Link is up\n");
adapter->ahw->linkup = 1;
- if (netif_running(netdev)) {
- netif_carrier_on(netdev);
- netif_wake_queue(netdev);
- }
+ netif_carrier_on(netdev);
}
}
@@ -784,7 +782,7 @@
struct net_device *netdev = adapter->netdev;
struct qlcnic_skb_frag *frag;
- if (!spin_trylock(&adapter->tx_clean_lock))
+ if (!spin_trylock(&tx_ring->tx_clean_lock))
return 1;
sw_consumer = tx_ring->sw_consumer;
@@ -813,8 +811,9 @@
break;
}
+ tx_ring->sw_consumer = sw_consumer;
+
if (count && netif_running(netdev)) {
- tx_ring->sw_consumer = sw_consumer;
smp_mb();
if (netif_tx_queue_stopped(tx_ring->txq) &&
netif_carrier_ok(netdev)) {
@@ -840,7 +839,8 @@
*/
hw_consumer = le32_to_cpu(*(tx_ring->hw_consumer));
done = (sw_consumer == hw_consumer);
- spin_unlock(&adapter->tx_clean_lock);
+
+ spin_unlock(&tx_ring->tx_clean_lock);
return done;
}
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 05c1eef..550791b 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -1178,6 +1178,7 @@
} else {
adapter->ahw->nic_mode = QLCNIC_DEFAULT_MODE;
adapter->max_tx_rings = QLCNIC_MAX_HW_TX_RINGS;
+ adapter->max_sds_rings = QLCNIC_MAX_SDS_RINGS;
adapter->flags &= ~QLCNIC_ESWITCH_ENABLED;
}
@@ -1755,7 +1756,6 @@
if (qlcnic_sriov_vf_check(adapter))
qlcnic_sriov_cleanup_async_list(&adapter->ahw->sriov->bc);
smp_mb();
- spin_lock(&adapter->tx_clean_lock);
netif_carrier_off(netdev);
adapter->ahw->linkup = 0;
netif_tx_disable(netdev);
@@ -1776,7 +1776,6 @@
for (ring = 0; ring < adapter->drv_tx_rings; ring++)
qlcnic_release_tx_buffers(adapter, &adapter->tx_ring[ring]);
- spin_unlock(&adapter->tx_clean_lock);
}
/* Usage: During suspend and firmware recovery module */
@@ -1940,7 +1939,6 @@
qlcnic_detach(adapter);
adapter->drv_sds_rings = QLCNIC_SINGLE_RING;
- adapter->drv_tx_rings = QLCNIC_SINGLE_RING;
adapter->ahw->diag_test = test;
adapter->ahw->linkup = 0;
@@ -2172,6 +2170,7 @@
}
memset(cmd_buf_arr, 0, TX_BUFF_RINGSIZE(tx_ring));
tx_ring->cmd_buf_arr = cmd_buf_arr;
+ spin_lock_init(&tx_ring->tx_clean_lock);
}
if (qlcnic_83xx_check(adapter) ||
@@ -2299,7 +2298,6 @@
rwlock_init(&adapter->ahw->crb_lock);
mutex_init(&adapter->ahw->mem_lock);
- spin_lock_init(&adapter->tx_clean_lock);
INIT_LIST_HEAD(&adapter->mac_list);
qlcnic_register_dcb(adapter);
@@ -2782,6 +2780,9 @@
struct qlcnic_adapter *adapter = netdev_priv(netdev);
struct net_device_stats *stats = &netdev->stats;
+ if (test_bit(__QLCNIC_DEV_UP, &adapter->state))
+ qlcnic_update_stats(adapter);
+
stats->rx_packets = adapter->stats.rx_pkts + adapter->stats.lro_pkts;
stats->tx_packets = adapter->stats.xmitfinished;
stats->rx_bytes = adapter->stats.rxbytes + adapter->stats.lrobytes;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
index 686f460..024f816 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
@@ -75,7 +75,6 @@
num_vfs = sriov->num_vfs;
max = num_vfs + 1;
info->bit_offsets = 0xffff;
- info->max_tx_ques = res->num_tx_queues / max;
info->max_rx_mcast_mac_filters = res->num_rx_mcast_mac_filters;
num_vf_macs = QLCNIC_SRIOV_VF_MAX_MAC;
@@ -86,6 +85,7 @@
info->max_tx_mac_filters = temp;
info->min_tx_bw = 0;
info->max_tx_bw = MAX_BW;
+ info->max_tx_ques = res->num_tx_queues - sriov->num_vfs;
} else {
id = qlcnic_sriov_func_to_index(adapter, func);
if (id < 0)
@@ -95,6 +95,7 @@
info->max_tx_bw = vp->max_tx_bw;
info->max_rx_ucast_mac_filters = num_vf_macs;
info->max_tx_mac_filters = num_vf_macs;
+ info->max_tx_ques = QLCNIC_SINGLE_RING;
}
info->max_rx_ip_addr = res->num_destip / max;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 8a7a23a..797b56a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -622,17 +622,15 @@
if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
return -EOPNOTSUPP;
- if (netif_msg_hw(priv)) {
- if (priv->dma_cap.time_stamp) {
- pr_debug("IEEE 1588-2002 Time Stamp supported\n");
- priv->adv_ts = 0;
- }
- if (priv->dma_cap.atime_stamp && priv->extend_desc) {
- pr_debug
- ("IEEE 1588-2008 Advanced Time Stamp supported\n");
- priv->adv_ts = 1;
- }
- }
+ priv->adv_ts = 0;
+ if (priv->dma_cap.atime_stamp && priv->extend_desc)
+ priv->adv_ts = 1;
+
+ if (netif_msg_hw(priv) && priv->dma_cap.time_stamp)
+ pr_debug("IEEE 1588-2002 Time Stamp supported\n");
+
+ if (netif_msg_hw(priv) && priv->adv_ts)
+ pr_debug("IEEE 1588-2008 Advanced Time Stamp supported\n");
priv->hw->ptp = &stmmac_ptp;
priv->hwts_tx_en = 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index b8b0eee..7680581 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -56,7 +56,7 @@
priv->hw->ptp->config_addend(priv->ioaddr, addend);
- spin_unlock_irqrestore(&priv->lock, flags);
+ spin_unlock_irqrestore(&priv->ptp_lock, flags);
return 0;
}
@@ -91,7 +91,7 @@
priv->hw->ptp->adjust_systime(priv->ioaddr, sec, nsec, neg_adj);
- spin_unlock_irqrestore(&priv->lock, flags);
+ spin_unlock_irqrestore(&priv->ptp_lock, flags);
return 0;
}
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 5120d9c..5330fd2 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -740,6 +740,8 @@
/* set speed_in input in case RMII mode is used in 100Mbps */
if (phy->speed == 100)
mac_control |= BIT(15);
+ else if (phy->speed == 10)
+ mac_control |= BIT(18); /* In Band mode */
*link = true;
} else {
@@ -2106,7 +2108,7 @@
while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, k))) {
for (i = res->start; i <= res->end; i++) {
if (devm_request_irq(&pdev->dev, i, cpsw_interrupt, 0,
- dev_name(priv->dev), priv)) {
+ dev_name(&pdev->dev), priv)) {
dev_err(priv->dev, "error attaching irq\n");
goto clean_ale_ret;
}
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 628b736..0e9fb33 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -2080,7 +2080,8 @@
}
/* Return subqueue id on this core (one per core). */
-static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
return smp_processor_id();
}
diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c
index 3169252..5d78c1d 100644
--- a/drivers/net/hamradio/hdlcdrv.c
+++ b/drivers/net/hamradio/hdlcdrv.c
@@ -571,6 +571,8 @@
case HDLCDRVCTL_CALIBRATE:
if(!capable(CAP_SYS_RAWIO))
return -EPERM;
+ if (bi.data.calibrate > INT_MAX / s->par.bitrate)
+ return -EINVAL;
s->hdlctx.calibrate = bi.data.calibrate * s->par.bitrate / 16;
return 0;
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index 1971411..61dd244 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -1057,6 +1057,7 @@
break;
case SIOCYAMGCFG:
+ memset(&yi, 0, sizeof(yi));
yi.cfg.mask = 0xffffffff;
yi.cfg.iobase = yp->iobase;
yi.cfg.irq = yp->irq;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 524f713..71baeb3 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -261,9 +261,7 @@
struct sk_buff *skb;
net = ((struct netvsc_device *)hv_get_drvdata(device_obj))->ndev;
- if (!net) {
- netdev_err(net, "got receive callback but net device"
- " not initialized yet\n");
+ if (!net || net->reg_state != NETREG_REGISTERED) {
packet->status = NVSP_STAT_FAIL;
return 0;
}
@@ -327,7 +325,6 @@
return -EINVAL;
nvdev->start_remove = true;
- cancel_delayed_work_sync(&ndevctx->dwork);
cancel_work_sync(&ndevctx->work);
netif_tx_disable(ndev);
rndis_filter_device_remove(hdev);
@@ -436,19 +433,11 @@
SET_ETHTOOL_OPS(net, ðtool_ops);
SET_NETDEV_DEV(net, &dev->device);
- ret = register_netdev(net);
- if (ret != 0) {
- pr_err("Unable to register netdev.\n");
- free_netdev(net);
- goto out;
- }
-
/* Notify the netvsc driver of the new device */
device_info.ring_size = ring_size;
ret = rndis_filter_device_add(dev, &device_info);
if (ret != 0) {
netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
- unregister_netdev(net);
free_netdev(net);
hv_set_drvdata(dev, NULL);
return ret;
@@ -457,7 +446,13 @@
netif_carrier_on(net);
-out:
+ ret = register_netdev(net);
+ if (ret != 0) {
+ pr_err("Unable to register netdev.\n");
+ rndis_filter_device_remove(dev);
+ free_netdev(net);
+ }
+
return ret;
}
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index acf9379..bc8faae 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -299,7 +299,7 @@
if (vlan->fwd_priv) {
skb->dev = vlan->lowerdev;
- ret = dev_hard_start_xmit(skb, skb->dev, NULL, vlan->fwd_priv);
+ ret = dev_queue_xmit_accel(skb, vlan->fwd_priv);
} else {
ret = macvlan_queue_xmit(skb, dev);
}
@@ -338,6 +338,8 @@
.cache_update = eth_header_cache_update,
};
+static struct rtnl_link_ops macvlan_link_ops;
+
static int macvlan_open(struct net_device *dev)
{
struct macvlan_dev *vlan = netdev_priv(dev);
@@ -353,7 +355,8 @@
goto hash_add;
}
- if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) {
+ if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD &&
+ dev->rtnl_link_ops == &macvlan_link_ops) {
vlan->fwd_priv =
lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev);
@@ -362,10 +365,8 @@
*/
if (IS_ERR_OR_NULL(vlan->fwd_priv)) {
vlan->fwd_priv = NULL;
- } else {
- dev->features &= ~NETIF_F_LLTX;
+ } else
return 0;
- }
}
err = -EBUSY;
@@ -690,8 +691,18 @@
netdev_features_t features)
{
struct macvlan_dev *vlan = netdev_priv(dev);
+ netdev_features_t mask;
- return features & (vlan->set_features | ~MACVLAN_FEATURES);
+ features |= NETIF_F_ALL_FOR_ALL;
+ features &= (vlan->set_features | ~MACVLAN_FEATURES);
+ mask = features;
+
+ features = netdev_increment_features(vlan->lowerdev->features,
+ features,
+ mask);
+ features |= NETIF_F_LLTX;
+
+ return features;
}
static const struct ethtool_ops macvlan_ethtool_ops = {
@@ -1019,9 +1030,8 @@
break;
case NETDEV_FEAT_CHANGE:
list_for_each_entry(vlan, &port->vlans, list) {
- vlan->dev->features = dev->features & MACVLAN_FEATURES;
vlan->dev->gso_max_size = dev->gso_max_size;
- netdev_features_change(vlan->dev);
+ netdev_update_features(vlan->dev);
}
break;
case NETDEV_UNREGISTER:
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 36c6994..98434b8 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -565,10 +565,8 @@
int err = 0;
atomic_set(&phydev->irq_disable, 0);
- if (request_irq(phydev->irq, phy_interrupt,
- IRQF_SHARED,
- "phy_interrupt",
- phydev) < 0) {
+ if (request_irq(phydev->irq, phy_interrupt, 0, "phy_interrupt",
+ phydev) < 0) {
pr_warn("%s: Can't get IRQ %d (PHY)\n",
phydev->bus->name, phydev->irq);
phydev->irq = PHY_POLL;
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 736050d..b75ae5b 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1647,7 +1647,8 @@
return NETDEV_TX_OK;
}
-static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
/*
* This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 7c8343a..ecec802 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -348,7 +348,8 @@
* different rxq no. here. If we could not get rxhash, then we would
* hope the rxq no. may help here.
*/
-static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
struct tun_struct *tun = netdev_priv(dev);
struct tun_flow_entry *e;
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 85e4a016..47b0f73 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -276,12 +276,12 @@
module will be called cdc_mbim.
config USB_NET_DM9601
- tristate "Davicom DM9601 based USB 1.1 10/100 ethernet devices"
+ tristate "Davicom DM96xx based USB 10/100 ethernet devices"
depends on USB_USBNET
select CRC32
help
- This option adds support for Davicom DM9601 based USB 1.1
- 10/100 Ethernet adapters.
+ This option adds support for Davicom DM9601/DM9620/DM9621A
+ based USB 10/100 Ethernet adapters.
config USB_NET_SR9700
tristate "CoreChip-sz SR9700 based USB 1.1 10/100 ethernet devices"
diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index c6867f9..14aa48f 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -1,5 +1,5 @@
/*
- * Davicom DM9601 USB 1.1 10/100Mbps ethernet devices
+ * Davicom DM96xx USB 10/100Mbps ethernet devices
*
* Peter Korsgaard <jacmet@sunsite.dk>
*
@@ -364,7 +364,12 @@
dev->net->ethtool_ops = &dm9601_ethtool_ops;
dev->net->hard_header_len += DM_TX_OVERHEAD;
dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len;
- dev->rx_urb_size = dev->net->mtu + ETH_HLEN + DM_RX_OVERHEAD;
+
+ /* dm9620/21a require room for 4 byte padding, even in dm9601
+ * mode, so we need +1 to be able to receive full size
+ * ethernet frames.
+ */
+ dev->rx_urb_size = dev->net->mtu + ETH_HLEN + DM_RX_OVERHEAD + 1;
dev->mii.dev = dev->net;
dev->mii.mdio_read = dm9601_mdio_read;
@@ -468,7 +473,7 @@
static struct sk_buff *dm9601_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
gfp_t flags)
{
- int len;
+ int len, pad;
/* format:
b1: packet length low
@@ -476,12 +481,23 @@
b3..n: packet data
*/
- len = skb->len;
+ len = skb->len + DM_TX_OVERHEAD;
- if (skb_headroom(skb) < DM_TX_OVERHEAD) {
+ /* workaround for dm962x errata with tx fifo getting out of
+ * sync if a USB bulk transfer retry happens right after a
+ * packet with odd / maxpacket length by adding up to 3 bytes
+ * padding.
+ */
+ while ((len & 1) || !(len % dev->maxpacket))
+ len++;
+
+ len -= DM_TX_OVERHEAD; /* hw header doesn't count as part of length */
+ pad = len - skb->len;
+
+ if (skb_headroom(skb) < DM_TX_OVERHEAD || skb_tailroom(skb) < pad) {
struct sk_buff *skb2;
- skb2 = skb_copy_expand(skb, DM_TX_OVERHEAD, 0, flags);
+ skb2 = skb_copy_expand(skb, DM_TX_OVERHEAD, pad, flags);
dev_kfree_skb_any(skb);
skb = skb2;
if (!skb)
@@ -490,10 +506,10 @@
__skb_push(skb, DM_TX_OVERHEAD);
- /* usbnet adds padding if length is a multiple of packet size
- if so, adjust length value in header */
- if ((skb->len % dev->maxpacket) == 0)
- len++;
+ if (pad) {
+ memset(skb->data + skb->len, 0, pad);
+ __skb_put(skb, pad);
+ }
skb->data[0] = len;
skb->data[1] = len >> 8;
@@ -543,7 +559,7 @@
}
static const struct driver_info dm9601_info = {
- .description = "Davicom DM9601 USB Ethernet",
+ .description = "Davicom DM96xx USB 10/100 Ethernet",
.flags = FLAG_ETHER | FLAG_LINK_INTR,
.bind = dm9601_bind,
.rx_fixup = dm9601_rx_fixup,
@@ -594,6 +610,10 @@
USB_DEVICE(0x0a46, 0x9620), /* DM9620 USB to Fast Ethernet Adapter */
.driver_info = (unsigned long)&dm9601_info,
},
+ {
+ USB_DEVICE(0x0a46, 0x9621), /* DM9621A USB to Fast Ethernet Adapter */
+ .driver_info = (unsigned long)&dm9601_info,
+ },
{}, // END
};
@@ -612,5 +632,5 @@
module_usb_driver(dm9601_driver);
MODULE_AUTHOR("Peter Korsgaard <jacmet@sunsite.dk>");
-MODULE_DESCRIPTION("Davicom DM9601 USB 1.1 ethernet devices");
+MODULE_DESCRIPTION("Davicom DM96xx USB 10/100 ethernet devices");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 86292e6..1a48234 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -185,7 +185,6 @@
#define BM_REQUEST_TYPE (0xa1)
#define B_NOTIFICATION (0x20)
#define W_VALUE (0x0)
-#define W_INDEX (0x2)
#define W_LENGTH (0x2)
#define B_OVERRUN (0x1<<6)
@@ -1487,6 +1486,7 @@
struct uart_icount *icount;
struct hso_serial_state_notification *serial_state_notification;
struct usb_device *usb;
+ int if_num;
/* Sanity checks */
if (!serial)
@@ -1495,15 +1495,24 @@
handle_usb_error(status, __func__, serial->parent);
return;
}
+
+ /* tiocmget is only supported on HSO_PORT_MODEM */
tiocmget = serial->tiocmget;
if (!tiocmget)
return;
+ BUG_ON((serial->parent->port_spec & HSO_PORT_MASK) != HSO_PORT_MODEM);
+
usb = serial->parent->usb;
+ if_num = serial->parent->interface->altsetting->desc.bInterfaceNumber;
+
+ /* wIndex should be the USB interface number of the port to which the
+ * notification applies, which should always be the Modem port.
+ */
serial_state_notification = &tiocmget->serial_state_notification;
if (serial_state_notification->bmRequestType != BM_REQUEST_TYPE ||
serial_state_notification->bNotification != B_NOTIFICATION ||
le16_to_cpu(serial_state_notification->wValue) != W_VALUE ||
- le16_to_cpu(serial_state_notification->wIndex) != W_INDEX ||
+ le16_to_cpu(serial_state_notification->wIndex) != if_num ||
le16_to_cpu(serial_state_notification->wLength) != W_LENGTH) {
dev_warn(&usb->dev,
"hso received invalid serial state notification\n");
diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c
index 03832d3..f546378 100644
--- a/drivers/net/usb/mcs7830.c
+++ b/drivers/net/usb/mcs7830.c
@@ -117,7 +117,6 @@
struct mcs7830_data {
u8 multi_filter[8];
u8 config;
- u8 link_counter;
};
static const char driver_name[] = "MOSCHIP usb-ethernet driver";
@@ -561,26 +560,16 @@
{
u8 *buf = urb->transfer_buffer;
bool link, link_changed;
- struct mcs7830_data *data = mcs7830_get_data(dev);
if (urb->actual_length < 16)
return;
- link = !(buf[1] & 0x20);
+ link = !(buf[1] == 0x20);
link_changed = netif_carrier_ok(dev->net) != link;
if (link_changed) {
- data->link_counter++;
- /*
- track link state 20 times to guard against erroneous
- link state changes reported sometimes by the chip
- */
- if (data->link_counter > 20) {
- data->link_counter = 0;
- usbnet_link_change(dev, link, 0);
- netdev_dbg(dev->net, "Link Status is: %d\n", link);
- }
- } else
- data->link_counter = 0;
+ usbnet_link_change(dev, link, 0);
+ netdev_dbg(dev->net, "Link Status is: %d\n", link);
+ }
}
static const struct driver_info moschip_info = {
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d208f86..5d77644 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1797,16 +1797,17 @@
if (err)
return err;
- if (netif_running(vi->dev))
+ if (netif_running(vi->dev)) {
+ for (i = 0; i < vi->curr_queue_pairs; i++)
+ if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
+ schedule_delayed_work(&vi->refill, 0);
+
for (i = 0; i < vi->max_queue_pairs; i++)
virtnet_napi_enable(&vi->rq[i]);
+ }
netif_device_attach(vi->dev);
- for (i = 0; i < vi->curr_queue_pairs; i++)
- if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
- schedule_delayed_work(&vi->refill, 0);
-
mutex_lock(&vi->config_lock);
vi->config_enable = true;
mutex_unlock(&vi->config_lock);
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 249e01c..ed384fe 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2440,7 +2440,8 @@
/* update header length based on lower device */
dev->hard_header_len = lowerdev->hard_header_len +
(use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
- }
+ } else if (use_ipv6)
+ vxlan->flags |= VXLAN_F_IPV6;
if (data[IFLA_VXLAN_TOS])
vxlan->tos = nla_get_u8(data[IFLA_VXLAN_TOS]);
diff --git a/drivers/net/wireless/ath/ath9k/ar9002_mac.c b/drivers/net/wireless/ath/ath9k/ar9002_mac.c
index 8d78253..a366d6b 100644
--- a/drivers/net/wireless/ath/ath9k/ar9002_mac.c
+++ b/drivers/net/wireless/ath/ath9k/ar9002_mac.c
@@ -76,9 +76,16 @@
mask2 |= ATH9K_INT_CST;
if (isr2 & AR_ISR_S2_TSFOOR)
mask2 |= ATH9K_INT_TSFOOR;
+
+ if (!(pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)) {
+ REG_WRITE(ah, AR_ISR_S2, isr2);
+ isr &= ~AR_ISR_BCNMISC;
+ }
}
- isr = REG_READ(ah, AR_ISR_RAC);
+ if (pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)
+ isr = REG_READ(ah, AR_ISR_RAC);
+
if (isr == 0xffffffff) {
*masked = 0;
return false;
@@ -97,11 +104,23 @@
*masked |= ATH9K_INT_TX;
- s0_s = REG_READ(ah, AR_ISR_S0_S);
+ if (pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED) {
+ s0_s = REG_READ(ah, AR_ISR_S0_S);
+ s1_s = REG_READ(ah, AR_ISR_S1_S);
+ } else {
+ s0_s = REG_READ(ah, AR_ISR_S0);
+ REG_WRITE(ah, AR_ISR_S0, s0_s);
+ s1_s = REG_READ(ah, AR_ISR_S1);
+ REG_WRITE(ah, AR_ISR_S1, s1_s);
+
+ isr &= ~(AR_ISR_TXOK |
+ AR_ISR_TXDESC |
+ AR_ISR_TXERR |
+ AR_ISR_TXEOL);
+ }
+
ah->intr_txqs |= MS(s0_s, AR_ISR_S0_QCU_TXOK);
ah->intr_txqs |= MS(s0_s, AR_ISR_S0_QCU_TXDESC);
-
- s1_s = REG_READ(ah, AR_ISR_S1_S);
ah->intr_txqs |= MS(s1_s, AR_ISR_S1_QCU_TXERR);
ah->intr_txqs |= MS(s1_s, AR_ISR_S1_QCU_TXEOL);
}
@@ -114,13 +133,15 @@
*masked |= mask2;
}
- if (AR_SREV_9100(ah))
- return true;
-
- if (isr & AR_ISR_GENTMR) {
+ if (!AR_SREV_9100(ah) && (isr & AR_ISR_GENTMR)) {
u32 s5_s;
- s5_s = REG_READ(ah, AR_ISR_S5_S);
+ if (pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED) {
+ s5_s = REG_READ(ah, AR_ISR_S5_S);
+ } else {
+ s5_s = REG_READ(ah, AR_ISR_S5);
+ }
+
ah->intr_gen_timer_trigger =
MS(s5_s, AR_ISR_S5_GENTIMER_TRIG);
@@ -133,8 +154,21 @@
if ((s5_s & AR_ISR_S5_TIM_TIMER) &&
!(pCap->hw_caps & ATH9K_HW_CAP_AUTOSLEEP))
*masked |= ATH9K_INT_TIM_TIMER;
+
+ if (!(pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)) {
+ REG_WRITE(ah, AR_ISR_S5, s5_s);
+ isr &= ~AR_ISR_GENTMR;
+ }
}
+ if (!(pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)) {
+ REG_WRITE(ah, AR_ISR, isr);
+ REG_READ(ah, AR_ISR);
+ }
+
+ if (AR_SREV_9100(ah))
+ return true;
+
if (sync_cause) {
ath9k_debug_sync_cause(common, sync_cause);
fatal_int =
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
index 9a2657f..608d739 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
@@ -127,21 +127,26 @@
struct ath9k_vif_iter_data *iter_data = data;
int i;
- for (i = 0; i < ETH_ALEN; i++)
- iter_data->mask[i] &= ~(iter_data->hw_macaddr[i] ^ mac[i]);
+ if (iter_data->hw_macaddr != NULL) {
+ for (i = 0; i < ETH_ALEN; i++)
+ iter_data->mask[i] &= ~(iter_data->hw_macaddr[i] ^ mac[i]);
+ } else {
+ iter_data->hw_macaddr = mac;
+ }
}
-static void ath9k_htc_set_bssid_mask(struct ath9k_htc_priv *priv,
+static void ath9k_htc_set_mac_bssid_mask(struct ath9k_htc_priv *priv,
struct ieee80211_vif *vif)
{
struct ath_common *common = ath9k_hw_common(priv->ah);
struct ath9k_vif_iter_data iter_data;
/*
- * Use the hardware MAC address as reference, the hardware uses it
- * together with the BSSID mask when matching addresses.
+ * Pick the MAC address of the first interface as the new hardware
+ * MAC address. The hardware will use it together with the BSSID mask
+ * when matching addresses.
*/
- iter_data.hw_macaddr = common->macaddr;
+ iter_data.hw_macaddr = NULL;
memset(&iter_data.mask, 0xff, ETH_ALEN);
if (vif)
@@ -153,6 +158,10 @@
ath9k_htc_bssid_iter, &iter_data);
memcpy(common->bssidmask, iter_data.mask, ETH_ALEN);
+
+ if (iter_data.hw_macaddr)
+ memcpy(common->macaddr, iter_data.hw_macaddr, ETH_ALEN);
+
ath_hw_setbssidmask(common);
}
@@ -1063,7 +1072,7 @@
goto out;
}
- ath9k_htc_set_bssid_mask(priv, vif);
+ ath9k_htc_set_mac_bssid_mask(priv, vif);
priv->vif_slot |= (1 << avp->index);
priv->nvifs++;
@@ -1128,7 +1137,7 @@
ath9k_htc_set_opmode(priv);
- ath9k_htc_set_bssid_mask(priv, vif);
+ ath9k_htc_set_mac_bssid_mask(priv, vif);
/*
* Stop ANI only if there are no associated station interfaces.
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 74f452c..21aa09e 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -965,8 +965,9 @@
struct ath_common *common = ath9k_hw_common(ah);
/*
- * Use the hardware MAC address as reference, the hardware uses it
- * together with the BSSID mask when matching addresses.
+ * Pick the MAC address of the first interface as the new hardware
+ * MAC address. The hardware will use it together with the BSSID mask
+ * when matching addresses.
*/
memset(iter_data, 0, sizeof(*iter_data));
memset(&iter_data->mask, 0xff, ETH_ALEN);
diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index 8660502..e627254 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -357,21 +357,27 @@
{IWL_PCI_DEVICE(0x095B, 0x5310, iwl7265_2ac_cfg)},
{IWL_PCI_DEVICE(0x095B, 0x5302, iwl7265_2ac_cfg)},
{IWL_PCI_DEVICE(0x095B, 0x5210, iwl7265_2ac_cfg)},
- {IWL_PCI_DEVICE(0x095B, 0x5012, iwl7265_2ac_cfg)},
- {IWL_PCI_DEVICE(0x095B, 0x500A, iwl7265_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x095A, 0x5012, iwl7265_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x095A, 0x500A, iwl7265_2ac_cfg)},
{IWL_PCI_DEVICE(0x095A, 0x5410, iwl7265_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x095A, 0x5400, iwl7265_2ac_cfg)},
{IWL_PCI_DEVICE(0x095A, 0x1010, iwl7265_2ac_cfg)},
{IWL_PCI_DEVICE(0x095A, 0x5000, iwl7265_2n_cfg)},
{IWL_PCI_DEVICE(0x095B, 0x5200, iwl7265_2n_cfg)},
{IWL_PCI_DEVICE(0x095A, 0x5002, iwl7265_n_cfg)},
{IWL_PCI_DEVICE(0x095B, 0x5202, iwl7265_n_cfg)},
{IWL_PCI_DEVICE(0x095A, 0x9010, iwl7265_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x095A, 0x9110, iwl7265_2ac_cfg)},
{IWL_PCI_DEVICE(0x095A, 0x9210, iwl7265_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x095A, 0x9510, iwl7265_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x095A, 0x9310, iwl7265_2ac_cfg)},
{IWL_PCI_DEVICE(0x095A, 0x9410, iwl7265_2ac_cfg)},
{IWL_PCI_DEVICE(0x095A, 0x5020, iwl7265_2n_cfg)},
{IWL_PCI_DEVICE(0x095A, 0x502A, iwl7265_2n_cfg)},
{IWL_PCI_DEVICE(0x095A, 0x5420, iwl7265_2n_cfg)},
{IWL_PCI_DEVICE(0x095A, 0x5090, iwl7265_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x095A, 0x5190, iwl7265_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x095A, 0x5590, iwl7265_2ac_cfg)},
{IWL_PCI_DEVICE(0x095B, 0x5290, iwl7265_2ac_cfg)},
{IWL_PCI_DEVICE(0x095A, 0x5490, iwl7265_2ac_cfg)},
#endif /* CONFIG_IWLMVM */
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index c72438b..a1b32ee 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -2011,7 +2011,7 @@
(hwsim_flags & HWSIM_TX_STAT_ACK)) {
if (skb->len >= 16) {
hdr = (struct ieee80211_hdr *) skb->data;
- mac80211_hwsim_monitor_ack(txi->rate_driver_data[0],
+ mac80211_hwsim_monitor_ack(data2->channel,
hdr->addr2);
}
txi->flags |= IEEE80211_TX_STAT_ACK;
diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c
index 78e8a66..8bb8988 100644
--- a/drivers/net/wireless/mwifiex/main.c
+++ b/drivers/net/wireless/mwifiex/main.c
@@ -746,7 +746,8 @@
}
static u16
-mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb)
+mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
skb->priority = cfg80211_classify8021d(skb);
return mwifiex_1d_to_wmm_queue[skb->priority];
diff --git a/drivers/net/wireless/rtlwifi/pci.c b/drivers/net/wireless/rtlwifi/pci.c
index 0f49444..5a53195 100644
--- a/drivers/net/wireless/rtlwifi/pci.c
+++ b/drivers/net/wireless/rtlwifi/pci.c
@@ -740,6 +740,8 @@
};
int index = rtlpci->rx_ring[rx_queue_idx].idx;
+ if (rtlpci->driver_is_goingto_unload)
+ return;
/*RX NORMAL PKT */
while (count--) {
/*rx descriptor */
@@ -1636,6 +1638,7 @@
*/
set_hal_stop(rtlhal);
+ rtlpci->driver_is_goingto_unload = true;
rtlpriv->cfg->ops->disable_interrupt(hw);
cancel_work_sync(&rtlpriv->works.lps_change_work);
@@ -1653,7 +1656,6 @@
ppsc->rfchange_inprogress = true;
spin_unlock_irqrestore(&rtlpriv->locks.rf_ps_lock, flags);
- rtlpci->driver_is_goingto_unload = true;
rtlpriv->cfg->ops->hw_disable(hw);
/* some things are not needed if firmware not available */
if (!rtlpriv->max_fw_size)
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 08ae01b..c47794b 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -101,6 +101,13 @@
#define MAX_PENDING_REQS 256
+/* It's possible for an skb to have a maximal number of frags
+ * but still be less than MAX_BUFFER_OFFSET in size. Thus the
+ * worst-case number of copy operations is MAX_SKB_FRAGS per
+ * ring slot.
+ */
+#define MAX_GRANT_COPY_OPS (MAX_SKB_FRAGS * XEN_NETIF_RX_RING_SIZE)
+
struct xenvif {
/* Unique identifier for this interface. */
domid_t domid;
@@ -143,13 +150,13 @@
*/
RING_IDX rx_req_cons_peek;
- /* Given MAX_BUFFER_OFFSET of 4096 the worst case is that each
- * head/fragment page uses 2 copy operations because it
- * straddles two buffers in the frontend.
- */
- struct gnttab_copy grant_copy_op[2*XEN_NETIF_RX_RING_SIZE];
- struct xenvif_rx_meta meta[2*XEN_NETIF_RX_RING_SIZE];
+ /* This array is allocated seperately as it is large */
+ struct gnttab_copy *grant_copy_op;
+ /* We create one meta structure per ring request we consume, so
+ * the maximum number is the same as the ring size.
+ */
+ struct xenvif_rx_meta meta[XEN_NETIF_RX_RING_SIZE];
u8 fe_dev_addr[6];
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 870f1fa..fff8cdd 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -34,6 +34,7 @@
#include <linux/ethtool.h>
#include <linux/rtnetlink.h>
#include <linux/if_vlan.h>
+#include <linux/vmalloc.h>
#include <xen/events.h>
#include <asm/xen/hypercall.h>
@@ -307,6 +308,15 @@
SET_NETDEV_DEV(dev, parent);
vif = netdev_priv(dev);
+
+ vif->grant_copy_op = vmalloc(sizeof(struct gnttab_copy) *
+ MAX_GRANT_COPY_OPS);
+ if (vif->grant_copy_op == NULL) {
+ pr_warn("Could not allocate grant copy space for %s\n", name);
+ free_netdev(dev);
+ return ERR_PTR(-ENOMEM);
+ }
+
vif->domid = domid;
vif->handle = handle;
vif->can_sg = 1;
@@ -487,6 +497,7 @@
unregister_netdev(vif->dev);
+ vfree(vif->grant_copy_op);
free_netdev(vif->dev);
module_put(THIS_MODULE);
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index e884ee1..7842555 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -608,7 +608,7 @@
if (!npo.copy_prod)
return;
- BUG_ON(npo.copy_prod > ARRAY_SIZE(vif->grant_copy_op));
+ BUG_ON(npo.copy_prod > MAX_GRANT_COPY_OPS);
gnttab_batch_copy(vif->grant_copy_op, npo.copy_prod);
while ((skb = __skb_dequeue(&rxq)) != NULL) {
@@ -1197,6 +1197,9 @@
err = -EPROTO;
+ if (fragment)
+ goto out;
+
switch (ip_hdr(skb)->protocol) {
case IPPROTO_TCP:
err = maybe_pull_tail(skb,
@@ -1206,8 +1209,10 @@
goto out;
if (!skb_partial_csum_set(skb, off,
- offsetof(struct tcphdr, check)))
+ offsetof(struct tcphdr, check))) {
+ err = -EPROTO;
goto out;
+ }
if (recalculate_partial_csum)
tcp_hdr(skb)->check =
@@ -1224,8 +1229,10 @@
goto out;
if (!skb_partial_csum_set(skb, off,
- offsetof(struct udphdr, check)))
+ offsetof(struct udphdr, check))) {
+ err = -EPROTO;
goto out;
+ }
if (recalculate_partial_csum)
udp_hdr(skb)->check =
@@ -1347,8 +1354,10 @@
goto out;
if (!skb_partial_csum_set(skb, off,
- offsetof(struct tcphdr, check)))
+ offsetof(struct tcphdr, check))) {
+ err = -EPROTO;
goto out;
+ }
if (recalculate_partial_csum)
tcp_hdr(skb)->check =
@@ -1365,8 +1374,10 @@
goto out;
if (!skb_partial_csum_set(skb, off,
- offsetof(struct udphdr, check)))
+ offsetof(struct udphdr, check))) {
+ err = -EPROTO;
goto out;
+ }
if (recalculate_partial_csum)
udp_hdr(skb)->check =
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index de6f899..c6973f1 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -20,7 +20,7 @@
depends on OF_IRQ
help
This option builds in test cases for the device tree infrastructure
- that are executed one at boot time, and the results dumped to the
+ that are executed once at boot time, and the results dumped to the
console.
If unsure, say N here, but this option is safe to enable.
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 4b9317b..d3dd41c 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -69,14 +69,6 @@
(unsigned long long)cp, (unsigned long long)s,
(unsigned long long)da);
- /*
- * If the number of address cells is larger than 2 we assume the
- * mapping doesn't specify a physical address. Rather, the address
- * specifies an identifier that must match exactly.
- */
- if (na > 2 && memcmp(range, addr, na * 4) != 0)
- return OF_BAD_ADDR;
-
if (da < cp || da >= (cp + s))
return OF_BAD_ADDR;
return da - cp;
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 2fa024b..758b4f8 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -922,8 +922,16 @@
*/
void __init unflatten_and_copy_device_tree(void)
{
- int size = __be32_to_cpu(initial_boot_params->totalsize);
- void *dt = early_init_dt_alloc_memory_arch(size,
+ int size;
+ void *dt;
+
+ if (!initial_boot_params) {
+ pr_warn("No valid device tree found, continuing without\n");
+ return;
+ }
+
+ size = __be32_to_cpu(initial_boot_params->totalsize);
+ dt = early_init_dt_alloc_memory_arch(size,
__alignof__(struct boot_param_header));
if (dt) {
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 786b0b4..2721240 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -165,7 +165,6 @@
if (of_get_property(ipar, "interrupt-controller", NULL) !=
NULL) {
pr_debug(" -> got it !\n");
- of_node_put(old);
return 0;
}
@@ -250,8 +249,7 @@
* Successfully parsed an interrrupt-map translation; copy new
* interrupt specifier into the out_irq structure
*/
- of_node_put(out_irq->np);
- out_irq->np = of_node_get(newpar);
+ out_irq->np = newpar;
match_array = imap - newaddrsize - newintsize;
for (i = 0; i < newintsize; i++)
@@ -268,7 +266,6 @@
}
fail:
of_node_put(ipar);
- of_node_put(out_irq->np);
of_node_put(newpar);
return -EINVAL;
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 1cf605f..e864392 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -279,7 +279,9 @@
status = acpi_evaluate_integer(handle, "_ADR", NULL, &adr);
if (ACPI_FAILURE(status)) {
- acpi_handle_warn(handle, "can't evaluate _ADR (%#x)\n", status);
+ if (status != AE_NOT_FOUND)
+ acpi_handle_warn(handle,
+ "can't evaluate _ADR (%#x)\n", status);
return AE_OK;
}
@@ -643,6 +645,24 @@
slot->flags &= (~SLOT_ENABLED);
}
+static bool acpiphp_no_hotplug(acpi_handle handle)
+{
+ struct acpi_device *adev = NULL;
+
+ acpi_bus_get_device(handle, &adev);
+ return adev && adev->flags.no_hotplug;
+}
+
+static bool slot_no_hotplug(struct acpiphp_slot *slot)
+{
+ struct acpiphp_func *func;
+
+ list_for_each_entry(func, &slot->funcs, sibling)
+ if (acpiphp_no_hotplug(func_to_handle(func)))
+ return true;
+
+ return false;
+}
/**
* get_slot_status - get ACPI slot status
@@ -701,7 +721,8 @@
unsigned long long sta;
status = acpi_evaluate_integer(handle, "_STA", NULL, &sta);
- alive = ACPI_SUCCESS(status) && sta == ACPI_STA_ALL;
+ alive = (ACPI_SUCCESS(status) && sta == ACPI_STA_ALL)
+ || acpiphp_no_hotplug(handle);
}
if (!alive) {
u32 v;
@@ -741,8 +762,9 @@
struct pci_dev *dev, *tmp;
mutex_lock(&slot->crit_sect);
- /* wake up all functions */
- if (get_slot_status(slot) == ACPI_STA_ALL) {
+ if (slot_no_hotplug(slot)) {
+ ; /* do nothing */
+ } else if (get_slot_status(slot) == ACPI_STA_ALL) {
/* remove stale devices if any */
list_for_each_entry_safe(dev, tmp, &bus->devices,
bus_list)
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 577074e..f7ebdba 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -330,29 +330,32 @@
static void pci_acpi_setup(struct device *dev)
{
struct pci_dev *pci_dev = to_pci_dev(dev);
- acpi_handle handle = ACPI_HANDLE(dev);
- struct acpi_device *adev;
+ struct acpi_device *adev = ACPI_COMPANION(dev);
- if (acpi_bus_get_device(handle, &adev) || !adev->wakeup.flags.valid)
+ if (!adev)
+ return;
+
+ pci_acpi_add_pm_notifier(adev, pci_dev);
+ if (!adev->wakeup.flags.valid)
return;
device_set_wakeup_capable(dev, true);
acpi_pci_sleep_wake(pci_dev, false);
-
- pci_acpi_add_pm_notifier(adev, pci_dev);
if (adev->wakeup.flags.run_wake)
device_set_run_wake(dev, true);
}
static void pci_acpi_cleanup(struct device *dev)
{
- acpi_handle handle = ACPI_HANDLE(dev);
- struct acpi_device *adev;
+ struct acpi_device *adev = ACPI_COMPANION(dev);
- if (!acpi_bus_get_device(handle, &adev) && adev->wakeup.flags.valid) {
+ if (!adev)
+ return;
+
+ pci_acpi_remove_pm_notifier(adev);
+ if (adev->wakeup.flags.valid) {
device_set_wakeup_capable(dev, false);
device_set_run_wake(dev, false);
- pci_acpi_remove_pm_notifier(adev);
}
}
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index a344f3d..330ef2d 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -24,8 +24,8 @@
config OMAP_USB2
tristate "OMAP USB2 PHY Driver"
depends on ARCH_OMAP2PLUS
+ depends on USB_PHY
select GENERIC_PHY
- select USB_PHY
select OMAP_CONTROL_USB
help
Enable this to support the transceiver that is part of SOC. This
@@ -36,8 +36,8 @@
config TWL4030_USB
tristate "TWL4030 USB Transceiver Driver"
depends on TWL4030_CORE && REGULATOR_TWL4030 && USB_MUSB_OMAP2PLUS
+ depends on USB_PHY
select GENERIC_PHY
- select USB_PHY
help
Enable this to support the USB OTG transceiver on TWL4030
family chips (including the TWL5030 and TPS659x0 devices).
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 03cf8fb..58e0e97 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -437,23 +437,18 @@
int id;
struct phy *phy;
- if (!dev) {
- dev_WARN(dev, "no device provided for PHY\n");
- ret = -EINVAL;
- goto err0;
- }
+ if (WARN_ON(!dev))
+ return ERR_PTR(-EINVAL);
phy = kzalloc(sizeof(*phy), GFP_KERNEL);
- if (!phy) {
- ret = -ENOMEM;
- goto err0;
- }
+ if (!phy)
+ return ERR_PTR(-ENOMEM);
id = ida_simple_get(&phy_ida, 0, 0, GFP_KERNEL);
if (id < 0) {
dev_err(dev, "unable to get id\n");
ret = id;
- goto err0;
+ goto free_phy;
}
device_initialize(&phy->dev);
@@ -468,11 +463,11 @@
ret = dev_set_name(&phy->dev, "phy-%s.%d", dev_name(dev), id);
if (ret)
- goto err1;
+ goto put_dev;
ret = device_add(&phy->dev);
if (ret)
- goto err1;
+ goto put_dev;
if (pm_runtime_enabled(dev)) {
pm_runtime_enable(&phy->dev);
@@ -481,12 +476,11 @@
return phy;
-err1:
- ida_remove(&phy_ida, phy->id);
+put_dev:
put_device(&phy->dev);
+ ida_remove(&phy_ida, phy->id);
+free_phy:
kfree(phy);
-
-err0:
return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(phy_create);
diff --git a/drivers/pinctrl/pinctrl-baytrail.c b/drivers/pinctrl/pinctrl-baytrail.c
index 2832576..114f5ef 100644
--- a/drivers/pinctrl/pinctrl-baytrail.c
+++ b/drivers/pinctrl/pinctrl-baytrail.c
@@ -512,6 +512,7 @@
static const struct acpi_device_id byt_gpio_acpi_match[] = {
{ "INT33B2", 0 },
+ { "INT33FC", 0 },
{ }
};
MODULE_DEVICE_TABLE(acpi, byt_gpio_acpi_match);
diff --git a/drivers/pinctrl/sh-pfc/sh_pfc.h b/drivers/pinctrl/sh-pfc/sh_pfc.h
index 11bd0d9..e214295 100644
--- a/drivers/pinctrl/sh-pfc/sh_pfc.h
+++ b/drivers/pinctrl/sh-pfc/sh_pfc.h
@@ -254,7 +254,7 @@
#define PINMUX_GPIO(_pin) \
[GPIO_##_pin] = { \
.pin = (u16)-1, \
- .name = __stringify(name), \
+ .name = __stringify(GPIO_##_pin), \
.enum_id = _pin##_DATA, \
}
diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig
index 5e2054a..85ad58c 100644
--- a/drivers/power/Kconfig
+++ b/drivers/power/Kconfig
@@ -196,6 +196,7 @@
config BATTERY_MAX17042
tristate "Maxim MAX17042/17047/17050/8997/8966 Fuel Gauge"
depends on I2C
+ select REGMAP_I2C
help
MAX17042 is fuel-gauge systems for lithium-ion (Li+) batteries
in handheld and portable equipment. The MAX17042 is configured
diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c
index 00e6672..557af94 100644
--- a/drivers/power/power_supply_core.c
+++ b/drivers/power/power_supply_core.c
@@ -511,6 +511,10 @@
dev_set_drvdata(dev, psy);
psy->dev = dev;
+ rc = dev_set_name(dev, "%s", psy->name);
+ if (rc)
+ goto dev_set_name_failed;
+
INIT_WORK(&psy->changed_work, power_supply_changed_work);
rc = power_supply_check_supplies(psy);
@@ -524,10 +528,6 @@
if (rc)
goto wakeup_init_failed;
- rc = kobject_set_name(&dev->kobj, "%s", psy->name);
- if (rc)
- goto kobject_set_name_failed;
-
rc = device_add(dev);
if (rc)
goto device_add_failed;
@@ -553,11 +553,11 @@
register_cooler_failed:
psy_unregister_thermal(psy);
register_thermal_failed:
-wakeup_init_failed:
device_del(dev);
-kobject_set_name_failed:
device_add_failed:
+wakeup_init_failed:
check_supplies_failed:
+dev_set_name_failed:
put_device(dev);
success:
return rc;
diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c
index 2a786c5..3c67683 100644
--- a/drivers/powercap/intel_rapl.c
+++ b/drivers/powercap/intel_rapl.c
@@ -833,6 +833,11 @@
return 0;
}
+static const struct x86_cpu_id energy_unit_quirk_ids[] = {
+ { X86_VENDOR_INTEL, 6, 0x37},/* VLV */
+ {}
+};
+
static int rapl_check_unit(struct rapl_package *rp, int cpu)
{
u64 msr_val;
@@ -853,8 +858,11 @@
* time unit: 1/time_unit_divisor Seconds
*/
value = (msr_val & ENERGY_UNIT_MASK) >> ENERGY_UNIT_OFFSET;
- rp->energy_unit_divisor = 1 << value;
-
+ /* some CPUs have different way to calculate energy unit */
+ if (x86_match_cpu(energy_unit_quirk_ids))
+ rp->energy_unit_divisor = 1000000 / (1 << value);
+ else
+ rp->energy_unit_divisor = 1 << value;
value = (msr_val & POWER_UNIT_MASK) >> POWER_UNIT_OFFSET;
rp->power_unit_divisor = 1 << value;
@@ -941,6 +949,7 @@
static const struct x86_cpu_id rapl_ids[] = {
{ X86_VENDOR_INTEL, 6, 0x2a},/* SNB */
{ X86_VENDOR_INTEL, 6, 0x2d},/* SNB EP */
+ { X86_VENDOR_INTEL, 6, 0x37},/* VLV */
{ X86_VENDOR_INTEL, 6, 0x3a},/* IVB */
{ X86_VENDOR_INTEL, 6, 0x45},/* HSW */
/* TODO: Add more CPU IDs after testing */
diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index 333677d..9e61922 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -438,7 +438,7 @@
platform_set_drvdata(pdev, s2mps11);
config.dev = &pdev->dev;
- config.regmap = iodev->regmap;
+ config.regmap = iodev->regmap_pmic;
config.driver_data = s2mps11;
for (i = 0; i < S2MPS11_REGULATOR_MAX; i++) {
if (!reg_np) {
diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c
index 3f4ca4e..34629ea 100644
--- a/drivers/s390/char/tty3270.c
+++ b/drivers/s390/char/tty3270.c
@@ -942,7 +942,7 @@
return rc;
}
- tp->screen = tty3270_alloc_screen(tp->view.cols, tp->view.rows);
+ tp->screen = tty3270_alloc_screen(tp->view.rows, tp->view.cols);
if (IS_ERR(tp->screen)) {
rc = PTR_ERR(tp->screen);
raw3270_put_view(&tp->view);
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 5964800..38a1257 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -471,7 +471,7 @@
schedule_delayed_work(&tgt->sess_del_work, 0);
else
schedule_delayed_work(&tgt->sess_del_work,
- jiffies - sess->expires);
+ sess->expires - jiffies);
}
/* ha->hardware_lock supposed to be held on entry */
@@ -550,13 +550,14 @@
struct scsi_qla_host *vha = tgt->vha;
struct qla_hw_data *ha = vha->hw;
struct qla_tgt_sess *sess;
- unsigned long flags;
+ unsigned long flags, elapsed;
spin_lock_irqsave(&ha->hardware_lock, flags);
while (!list_empty(&tgt->del_sess_list)) {
sess = list_entry(tgt->del_sess_list.next, typeof(*sess),
del_list_entry);
- if (time_after_eq(jiffies, sess->expires)) {
+ elapsed = jiffies;
+ if (time_after_eq(elapsed, sess->expires)) {
qlt_undelete_sess(sess);
ql_dbg(ql_dbg_tgt_mgt, vha, 0xf004,
@@ -566,7 +567,7 @@
ha->tgt.tgt_ops->put_sess(sess);
} else {
schedule_delayed_work(&tgt->sess_del_work,
- jiffies - sess->expires);
+ sess->expires - elapsed);
break;
}
}
@@ -4290,6 +4291,7 @@
if (rc != 0) {
ha->tgt.tgt_ops = NULL;
ha->tgt.target_lport_ptr = NULL;
+ scsi_host_put(host);
}
mutex_unlock(&qla_tgt_mutex);
return rc;
diff --git a/drivers/staging/bcm/Bcmnet.c b/drivers/staging/bcm/Bcmnet.c
index 53fee2f..8dfdd27 100644
--- a/drivers/staging/bcm/Bcmnet.c
+++ b/drivers/staging/bcm/Bcmnet.c
@@ -39,7 +39,8 @@
return 0;
}
-static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
return ClassifyPacket(netdev_priv(dev), skb);
}
diff --git a/drivers/staging/comedi/drivers.c b/drivers/staging/comedi/drivers.c
index 8f02bf6..4964d2a 100644
--- a/drivers/staging/comedi/drivers.c
+++ b/drivers/staging/comedi/drivers.c
@@ -446,7 +446,7 @@
release_firmware(fw);
}
- return ret;
+ return ret < 0 ? ret : 0;
}
EXPORT_SYMBOL_GPL(comedi_load_firmware);
diff --git a/drivers/staging/comedi/drivers/8255_pci.c b/drivers/staging/comedi/drivers/8255_pci.c
index 432e3f9..c55f234 100644
--- a/drivers/staging/comedi/drivers/8255_pci.c
+++ b/drivers/staging/comedi/drivers/8255_pci.c
@@ -63,7 +63,8 @@
BOARD_ADLINK_PCI7296,
BOARD_CB_PCIDIO24,
BOARD_CB_PCIDIO24H,
- BOARD_CB_PCIDIO48H,
+ BOARD_CB_PCIDIO48H_OLD,
+ BOARD_CB_PCIDIO48H_NEW,
BOARD_CB_PCIDIO96H,
BOARD_NI_PCIDIO96,
BOARD_NI_PCIDIO96B,
@@ -106,11 +107,16 @@
.dio_badr = 2,
.n_8255 = 1,
},
- [BOARD_CB_PCIDIO48H] = {
+ [BOARD_CB_PCIDIO48H_OLD] = {
.name = "cb_pci-dio48h",
.dio_badr = 1,
.n_8255 = 2,
},
+ [BOARD_CB_PCIDIO48H_NEW] = {
+ .name = "cb_pci-dio48h",
+ .dio_badr = 2,
+ .n_8255 = 2,
+ },
[BOARD_CB_PCIDIO96H] = {
.name = "cb_pci-dio96h",
.dio_badr = 2,
@@ -263,7 +269,10 @@
{ PCI_VDEVICE(ADLINK, 0x7296), BOARD_ADLINK_PCI7296 },
{ PCI_VDEVICE(CB, 0x0028), BOARD_CB_PCIDIO24 },
{ PCI_VDEVICE(CB, 0x0014), BOARD_CB_PCIDIO24H },
- { PCI_VDEVICE(CB, 0x000b), BOARD_CB_PCIDIO48H },
+ { PCI_DEVICE_SUB(PCI_VENDOR_ID_CB, 0x000b, 0x0000, 0x0000),
+ .driver_data = BOARD_CB_PCIDIO48H_OLD },
+ { PCI_DEVICE_SUB(PCI_VENDOR_ID_CB, 0x000b, PCI_VENDOR_ID_CB, 0x000b),
+ .driver_data = BOARD_CB_PCIDIO48H_NEW },
{ PCI_VDEVICE(CB, 0x0017), BOARD_CB_PCIDIO96H },
{ PCI_VDEVICE(NI, 0x0160), BOARD_NI_PCIDIO96 },
{ PCI_VDEVICE(NI, 0x1630), BOARD_NI_PCIDIO96B },
diff --git a/drivers/staging/iio/magnetometer/hmc5843.c b/drivers/staging/iio/magnetometer/hmc5843.c
index 99421f9..0485d7f 100644
--- a/drivers/staging/iio/magnetometer/hmc5843.c
+++ b/drivers/staging/iio/magnetometer/hmc5843.c
@@ -451,7 +451,12 @@
.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE) | \
BIT(IIO_CHAN_INFO_SAMP_FREQ), \
.scan_index = idx, \
- .scan_type = IIO_ST('s', 16, 16, IIO_BE), \
+ .scan_type = { \
+ .sign = 's', \
+ .realbits = 16, \
+ .storagebits = 16, \
+ .endianness = IIO_BE, \
+ }, \
}
static const struct iio_chan_spec hmc5843_channels[] = {
diff --git a/drivers/staging/imx-drm/imx-drm-core.c b/drivers/staging/imx-drm/imx-drm-core.c
index 6bd015a..96e4eee 100644
--- a/drivers/staging/imx-drm/imx-drm-core.c
+++ b/drivers/staging/imx-drm/imx-drm-core.c
@@ -88,8 +88,9 @@
imx_drm_device_put();
- drm_mode_config_cleanup(imxdrm->drm);
+ drm_vblank_cleanup(imxdrm->drm);
drm_kms_helper_poll_fini(imxdrm->drm);
+ drm_mode_config_cleanup(imxdrm->drm);
return 0;
}
@@ -199,8 +200,8 @@
if (!file->is_master)
return;
- for (i = 0; i < 4; i++)
- imx_drm_disable_vblank(drm , i);
+ for (i = 0; i < MAX_CRTC; i++)
+ imx_drm_disable_vblank(drm, i);
}
static const struct file_operations imx_drm_driver_fops = {
@@ -376,8 +377,6 @@
struct imx_drm_device *imxdrm = __imx_drm_device();
int ret;
- drm_crtc_init(imxdrm->drm, imx_drm_crtc->crtc,
- imx_drm_crtc->imx_drm_helper_funcs.crtc_funcs);
ret = drm_mode_crtc_set_gamma_size(imx_drm_crtc->crtc, 256);
if (ret)
return ret;
@@ -385,6 +384,9 @@
drm_crtc_helper_add(imx_drm_crtc->crtc,
imx_drm_crtc->imx_drm_helper_funcs.crtc_helper_funcs);
+ drm_crtc_init(imxdrm->drm, imx_drm_crtc->crtc,
+ imx_drm_crtc->imx_drm_helper_funcs.crtc_funcs);
+
drm_mode_group_reinit(imxdrm->drm);
return 0;
@@ -428,11 +430,11 @@
ret = drm_mode_group_init_legacy_group(imxdrm->drm,
&imxdrm->drm->primary->mode_group);
if (ret)
- goto err_init;
+ goto err_kms;
ret = drm_vblank_init(imxdrm->drm, MAX_CRTC);
if (ret)
- goto err_init;
+ goto err_kms;
/*
* with vblank_disable_allowed = true, vblank interrupt will be disabled
@@ -441,12 +443,19 @@
*/
imxdrm->drm->vblank_disable_allowed = true;
- if (!imx_drm_device_get())
+ if (!imx_drm_device_get()) {
ret = -EINVAL;
+ goto err_vblank;
+ }
- ret = 0;
+ mutex_unlock(&imxdrm->mutex);
+ return 0;
-err_init:
+err_vblank:
+ drm_vblank_cleanup(drm);
+err_kms:
+ drm_kms_helper_poll_fini(drm);
+ drm_mode_config_cleanup(drm);
mutex_unlock(&imxdrm->mutex);
return ret;
@@ -492,6 +501,15 @@
mutex_lock(&imxdrm->mutex);
+ /*
+ * The vblank arrays are dimensioned by MAX_CRTC - we can't
+ * pass IDs greater than this to those functions.
+ */
+ if (imxdrm->pipes >= MAX_CRTC) {
+ ret = -EINVAL;
+ goto err_busy;
+ }
+
if (imxdrm->drm->open_count) {
ret = -EBUSY;
goto err_busy;
@@ -528,6 +546,7 @@
return 0;
err_register:
+ list_del(&imx_drm_crtc->list);
kfree(imx_drm_crtc);
err_alloc:
err_busy:
diff --git a/drivers/staging/imx-drm/imx-tve.c b/drivers/staging/imx-drm/imx-tve.c
index 680f4c8..2c44fef 100644
--- a/drivers/staging/imx-drm/imx-tve.c
+++ b/drivers/staging/imx-drm/imx-tve.c
@@ -114,7 +114,6 @@
struct drm_encoder encoder;
struct imx_drm_encoder *imx_drm_encoder;
struct device *dev;
- spinlock_t enable_lock; /* serializes tve_enable/disable */
spinlock_t lock; /* register lock */
bool enabled;
int mode;
@@ -146,10 +145,8 @@
static void tve_enable(struct imx_tve *tve)
{
- unsigned long flags;
int ret;
- spin_lock_irqsave(&tve->enable_lock, flags);
if (!tve->enabled) {
tve->enabled = true;
clk_prepare_enable(tve->clk);
@@ -169,23 +166,18 @@
TVE_CD_SM_IEN |
TVE_CD_LM_IEN |
TVE_CD_MON_END_IEN);
-
- spin_unlock_irqrestore(&tve->enable_lock, flags);
}
static void tve_disable(struct imx_tve *tve)
{
- unsigned long flags;
int ret;
- spin_lock_irqsave(&tve->enable_lock, flags);
if (tve->enabled) {
tve->enabled = false;
ret = regmap_update_bits(tve->regmap, TVE_COM_CONF_REG,
TVE_IPU_CLK_EN | TVE_EN, 0);
clk_disable_unprepare(tve->clk);
}
- spin_unlock_irqrestore(&tve->enable_lock, flags);
}
static int tve_setup_tvout(struct imx_tve *tve)
@@ -601,7 +593,6 @@
tve->dev = &pdev->dev;
spin_lock_init(&tve->lock);
- spin_lock_init(&tve->enable_lock);
ddc_node = of_parse_phandle(np, "ddc", 0);
if (ddc_node) {
diff --git a/drivers/staging/imx-drm/ipu-v3/ipu-common.c b/drivers/staging/imx-drm/ipu-v3/ipu-common.c
index 7a22ce6..97ca692 100644
--- a/drivers/staging/imx-drm/ipu-v3/ipu-common.c
+++ b/drivers/staging/imx-drm/ipu-v3/ipu-common.c
@@ -996,35 +996,35 @@
},
};
+static DEFINE_MUTEX(ipu_client_id_mutex);
static int ipu_client_id;
-static int ipu_add_subdevice_pdata(struct device *dev,
- const struct ipu_platform_reg *reg)
-{
- struct platform_device *pdev;
-
- pdev = platform_device_register_data(dev, reg->name, ipu_client_id++,
- ®->pdata, sizeof(struct ipu_platform_reg));
-
- return PTR_ERR_OR_ZERO(pdev);
-}
-
static int ipu_add_client_devices(struct ipu_soc *ipu)
{
- int ret;
- int i;
+ struct device *dev = ipu->dev;
+ unsigned i;
+ int id, ret;
+
+ mutex_lock(&ipu_client_id_mutex);
+ id = ipu_client_id;
+ ipu_client_id += ARRAY_SIZE(client_reg);
+ mutex_unlock(&ipu_client_id_mutex);
for (i = 0; i < ARRAY_SIZE(client_reg); i++) {
const struct ipu_platform_reg *reg = &client_reg[i];
- ret = ipu_add_subdevice_pdata(ipu->dev, reg);
- if (ret)
+ struct platform_device *pdev;
+
+ pdev = platform_device_register_data(dev, reg->name,
+ id++, ®->pdata, sizeof(reg->pdata));
+
+ if (IS_ERR(pdev))
goto err_register;
}
return 0;
err_register:
- platform_device_unregister_children(to_platform_device(ipu->dev));
+ platform_device_unregister_children(to_platform_device(dev));
return ret;
}
diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c
index 235d2b1..eedffed 100644
--- a/drivers/staging/netlogic/xlr_net.c
+++ b/drivers/staging/netlogic/xlr_net.c
@@ -306,7 +306,8 @@
return NETDEV_TX_OK;
}
-static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb)
+static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb,
+ void *accel_priv)
{
return (u16)smp_processor_id();
}
diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
index 17659bb..dd69e34 100644
--- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
@@ -652,7 +652,8 @@
return dscp >> 5;
}
-static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
+ void *accel_priv)
{
struct adapter *padapter = rtw_netdev_priv(dev);
struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index d70e911..0086719 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -465,6 +465,7 @@
*/
send_sig(SIGINT, np->np_thread, 1);
kthread_stop(np->np_thread);
+ np->np_thread = NULL;
}
np->np_transport->iscsit_free_np(np);
@@ -823,24 +824,22 @@
if (((hdr->flags & ISCSI_FLAG_CMD_READ) ||
(hdr->flags & ISCSI_FLAG_CMD_WRITE)) && !hdr->data_length) {
/*
- * Vmware ESX v3.0 uses a modified Cisco Initiator (v3.4.2)
- * that adds support for RESERVE/RELEASE. There is a bug
- * add with this new functionality that sets R/W bits when
- * neither CDB carries any READ or WRITE datapayloads.
+ * From RFC-3720 Section 10.3.1:
+ *
+ * "Either or both of R and W MAY be 1 when either the
+ * Expected Data Transfer Length and/or Bidirectional Read
+ * Expected Data Transfer Length are 0"
+ *
+ * For this case, go ahead and clear the unnecssary bits
+ * to avoid any confusion with ->data_direction.
*/
- if ((hdr->cdb[0] == 0x16) || (hdr->cdb[0] == 0x17)) {
- hdr->flags &= ~ISCSI_FLAG_CMD_READ;
- hdr->flags &= ~ISCSI_FLAG_CMD_WRITE;
- goto done;
- }
+ hdr->flags &= ~ISCSI_FLAG_CMD_READ;
+ hdr->flags &= ~ISCSI_FLAG_CMD_WRITE;
- pr_err("ISCSI_FLAG_CMD_READ or ISCSI_FLAG_CMD_WRITE"
+ pr_warn("ISCSI_FLAG_CMD_READ or ISCSI_FLAG_CMD_WRITE"
" set when Expected Data Transfer Length is 0 for"
- " CDB: 0x%02x. Bad iSCSI Initiator.\n", hdr->cdb[0]);
- return iscsit_add_reject_cmd(cmd,
- ISCSI_REASON_BOOKMARK_INVALID, buf);
+ " CDB: 0x%02x, Fixing up flags\n", hdr->cdb[0]);
}
-done:
if (!(hdr->flags & ISCSI_FLAG_CMD_READ) &&
!(hdr->flags & ISCSI_FLAG_CMD_WRITE) && (hdr->data_length != 0)) {
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index e3318ed..1c0088f 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -474,7 +474,8 @@
\
if (!capable(CAP_SYS_ADMIN)) \
return -EPERM; \
- \
+ if (count >= sizeof(auth->name)) \
+ return -EINVAL; \
snprintf(auth->name, sizeof(auth->name), "%s", page); \
if (!strncmp("NULL", auth->name, 4)) \
auth->naf_flags &= ~flags; \
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 4eb93b2..e29279e 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -1403,11 +1403,6 @@
out:
stop = kthread_should_stop();
- if (!stop && signal_pending(current)) {
- spin_lock_bh(&np->np_thread_lock);
- stop = (np->np_thread_state == ISCSI_NP_THREAD_SHUTDOWN);
- spin_unlock_bh(&np->np_thread_lock);
- }
/* Wait for another socket.. */
if (!stop)
return 1;
@@ -1415,7 +1410,6 @@
iscsi_stop_login_thread_timer(np);
spin_lock_bh(&np->np_thread_lock);
np->np_thread_state = ISCSI_NP_THREAD_EXIT;
- np->np_thread = NULL;
spin_unlock_bh(&np->np_thread_lock);
return 0;
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 207b340..d06de84 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -1106,6 +1106,11 @@
dev->dev_attrib.block_size = block_size;
pr_debug("dev[%p]: SE Device block_size changed to %u\n",
dev, block_size);
+
+ if (dev->dev_attrib.max_bytes_per_io)
+ dev->dev_attrib.hw_max_sectors =
+ dev->dev_attrib.max_bytes_per_io / block_size;
+
return 0;
}
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index 0e34cda..78241a5 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -66,9 +66,8 @@
pr_debug("CORE_HBA[%d] - TCM FILEIO HBA Driver %s on Generic"
" Target Core Stack %s\n", hba->hba_id, FD_VERSION,
TARGET_CORE_MOD_VERSION);
- pr_debug("CORE_HBA[%d] - Attached FILEIO HBA: %u to Generic"
- " MaxSectors: %u\n",
- hba->hba_id, fd_host->fd_host_id, FD_MAX_SECTORS);
+ pr_debug("CORE_HBA[%d] - Attached FILEIO HBA: %u to Generic\n",
+ hba->hba_id, fd_host->fd_host_id);
return 0;
}
@@ -220,7 +219,8 @@
}
dev->dev_attrib.hw_block_size = fd_dev->fd_block_size;
- dev->dev_attrib.hw_max_sectors = FD_MAX_SECTORS;
+ dev->dev_attrib.max_bytes_per_io = FD_MAX_BYTES;
+ dev->dev_attrib.hw_max_sectors = FD_MAX_BYTES / fd_dev->fd_block_size;
dev->dev_attrib.hw_queue_depth = FD_MAX_DEVICE_QUEUE_DEPTH;
if (fd_dev->fbd_flags & FDBD_HAS_BUFFERED_IO_WCE) {
diff --git a/drivers/target/target_core_file.h b/drivers/target/target_core_file.h
index 37ffc5b..d7772c1 100644
--- a/drivers/target/target_core_file.h
+++ b/drivers/target/target_core_file.h
@@ -7,7 +7,10 @@
#define FD_DEVICE_QUEUE_DEPTH 32
#define FD_MAX_DEVICE_QUEUE_DEPTH 128
#define FD_BLOCKSIZE 512
-#define FD_MAX_SECTORS 2048
+/*
+ * Limited by the number of iovecs (2048) per vfs_[writev,readv] call
+ */
+#define FD_MAX_BYTES 8388608
#define RRF_EMULATE_CDB 0x01
#define RRF_GOT_LBA 0x02
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index f697f8b..2a573de 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -278,7 +278,6 @@
snprintf(acl->initiatorname, TRANSPORT_IQN_LEN, "%s", initiatorname);
acl->se_tpg = tpg;
acl->acl_index = scsi_get_new_index(SCSI_AUTH_INTR_INDEX);
- spin_lock_init(&acl->stats_lock);
acl->dynamic_node_acl = 1;
tpg->se_tpg_tfo->set_default_node_attributes(acl);
@@ -406,7 +405,6 @@
snprintf(acl->initiatorname, TRANSPORT_IQN_LEN, "%s", initiatorname);
acl->se_tpg = tpg;
acl->acl_index = scsi_get_new_index(SCSI_AUTH_INTR_INDEX);
- spin_lock_init(&acl->stats_lock);
tpg->se_tpg_tfo->set_default_node_attributes(acl);
@@ -658,16 +656,10 @@
spin_lock_init(&lun->lun_sep_lock);
init_completion(&lun->lun_ref_comp);
- ret = percpu_ref_init(&lun->lun_ref, core_tpg_lun_ref_release);
+ ret = core_tpg_post_addlun(se_tpg, lun, lun_access, dev);
if (ret < 0)
return ret;
- ret = core_tpg_post_addlun(se_tpg, lun, lun_access, dev);
- if (ret < 0) {
- percpu_ref_cancel_init(&lun->lun_ref);
- return ret;
- }
-
return 0;
}
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 268b627..34aacaa 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -93,6 +93,7 @@
size_t canon_head;
size_t echo_head;
size_t echo_commit;
+ size_t echo_mark;
DECLARE_BITMAP(char_map, 256);
/* private to n_tty_receive_overrun (single-threaded) */
@@ -336,6 +337,7 @@
{
ldata->read_head = ldata->canon_head = ldata->read_tail = 0;
ldata->echo_head = ldata->echo_tail = ldata->echo_commit = 0;
+ ldata->echo_mark = 0;
ldata->line_start = 0;
ldata->erasing = 0;
@@ -787,6 +789,7 @@
size_t head;
head = ldata->echo_head;
+ ldata->echo_mark = head;
old = ldata->echo_commit - ldata->echo_tail;
/* Process committed echoes if the accumulated # of bytes
@@ -811,10 +814,11 @@
size_t echoed;
if ((!L_ECHO(tty) && !L_ECHONL(tty)) ||
- ldata->echo_commit == ldata->echo_tail)
+ ldata->echo_mark == ldata->echo_tail)
return;
mutex_lock(&ldata->output_lock);
+ ldata->echo_commit = ldata->echo_mark;
echoed = __process_echoes(tty);
mutex_unlock(&ldata->output_lock);
@@ -822,6 +826,7 @@
tty->ops->flush_chars(tty);
}
+/* NB: echo_mark and echo_head should be equivalent here */
static void flush_echoes(struct tty_struct *tty)
{
struct n_tty_data *ldata = tty->disc_data;
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index 4658e3e..06525f1 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -96,7 +96,8 @@
if (offset == UART_LCR) {
int tries = 1000;
while (tries--) {
- if (value == p->serial_in(p, UART_LCR))
+ unsigned int lcr = p->serial_in(p, UART_LCR);
+ if ((value & ~UART_LCR_SPAR) == (lcr & ~UART_LCR_SPAR))
return;
dw8250_force_idle(p);
writeb(value, p->membase + (UART_LCR << p->regshift));
@@ -132,7 +133,8 @@
if (offset == UART_LCR) {
int tries = 1000;
while (tries--) {
- if (value == p->serial_in(p, UART_LCR))
+ unsigned int lcr = p->serial_in(p, UART_LCR);
+ if ((value & ~UART_LCR_SPAR) == (lcr & ~UART_LCR_SPAR))
return;
dw8250_force_idle(p);
writel(value, p->membase + (UART_LCR << p->regshift));
@@ -455,6 +457,8 @@
static const struct acpi_device_id dw8250_acpi_match[] = {
{ "INT33C4", 0 },
{ "INT33C5", 0 },
+ { "INT3434", 0 },
+ { "INT3435", 0 },
{ "80860F0A", 0 },
{ },
};
diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index e46e9f3..f619ad5 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -240,6 +240,7 @@
continue;
}
+#ifdef SUPPORT_SYSRQ
/*
* uart_handle_sysrq_char() doesn't work if
* spinlocked, for some reason
@@ -253,6 +254,7 @@
}
spin_lock(&port->lock);
}
+#endif
port->icount.rx++;
diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c
index 22fad8a..d8a55e8 100644
--- a/drivers/tty/tty_ldsem.c
+++ b/drivers/tty/tty_ldsem.c
@@ -86,11 +86,21 @@
return atomic_long_add_return(delta, (atomic_long_t *)&sem->count);
}
+/*
+ * ldsem_cmpxchg() updates @*old with the last-known sem->count value.
+ * Returns 1 if count was successfully changed; @*old will have @new value.
+ * Returns 0 if count was not changed; @*old will have most recent sem->count
+ */
static inline int ldsem_cmpxchg(long *old, long new, struct ld_semaphore *sem)
{
- long tmp = *old;
- *old = atomic_long_cmpxchg(&sem->count, *old, new);
- return *old == tmp;
+ long tmp = atomic_long_cmpxchg(&sem->count, *old, new);
+ if (tmp == *old) {
+ *old = new;
+ return 1;
+ } else {
+ *old = tmp;
+ return 0;
+ }
}
/*
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 5d8981c..6e73f8c 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -642,6 +642,10 @@
: CI_ROLE_GADGET;
}
+ /* only update vbus status for peripheral */
+ if (ci->role == CI_ROLE_GADGET)
+ ci_handle_vbus_change(ci);
+
ret = ci_role_start(ci, ci->role);
if (ret) {
dev_err(dev, "can't start %s role\n", ci_role(ci)->name);
diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c
index 59e6020..526cd77 100644
--- a/drivers/usb/chipidea/host.c
+++ b/drivers/usb/chipidea/host.c
@@ -88,7 +88,8 @@
return ret;
disable_reg:
- regulator_disable(ci->platdata->reg_vbus);
+ if (ci->platdata->reg_vbus)
+ regulator_disable(ci->platdata->reg_vbus);
put_hcd:
usb_put_hcd(hcd);
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index b34c819..69d20fb 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -1795,9 +1795,6 @@
pm_runtime_no_callbacks(&ci->gadget.dev);
pm_runtime_enable(&ci->gadget.dev);
- /* Update ci->vbus_active */
- ci_handle_vbus_change(ci);
-
return retval;
destroy_eps:
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index 4d38759..0b23a86 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -854,13 +854,11 @@
{
/* need autopm_get/put here to ensure the usbcore sees the new value */
int rv = usb_autopm_get_interface(intf);
- if (rv < 0)
- goto err;
intf->needs_remote_wakeup = on;
- usb_autopm_put_interface(intf);
-err:
- return rv;
+ if (!rv)
+ usb_autopm_put_interface(intf);
+ return 0;
}
static int wdm_probe(struct usb_interface *intf, const struct usb_device_id *id)
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 74f9cf0..a49217a 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -455,9 +455,6 @@
if (IS_ERR(regs))
return PTR_ERR(regs);
- usb_phy_set_suspend(dwc->usb2_phy, 0);
- usb_phy_set_suspend(dwc->usb3_phy, 0);
-
spin_lock_init(&dwc->lock);
platform_set_drvdata(pdev, dwc);
@@ -488,6 +485,9 @@
goto err0;
}
+ usb_phy_set_suspend(dwc->usb2_phy, 0);
+ usb_phy_set_suspend(dwc->usb3_phy, 0);
+
ret = dwc3_event_buffers_setup(dwc);
if (ret) {
dev_err(dwc->dev, "failed to setup event buffers\n");
@@ -569,6 +569,8 @@
dwc3_event_buffers_cleanup(dwc);
err1:
+ usb_phy_set_suspend(dwc->usb2_phy, 1);
+ usb_phy_set_suspend(dwc->usb3_phy, 1);
dwc3_core_exit(dwc);
err0:
diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c
index 418444e..8c356af 100644
--- a/drivers/usb/host/ohci-at91.c
+++ b/drivers/usb/host/ohci-at91.c
@@ -136,23 +136,27 @@
struct ohci_hcd *ohci;
int retval;
struct usb_hcd *hcd = NULL;
+ struct device *dev = &pdev->dev;
+ struct resource *res;
+ int irq;
- if (pdev->num_resources != 2) {
- pr_debug("hcd probe: invalid num_resources");
- return -ENODEV;
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res) {
+ dev_dbg(dev, "hcd probe: missing memory resource\n");
+ return -ENXIO;
}
- if ((pdev->resource[0].flags != IORESOURCE_MEM)
- || (pdev->resource[1].flags != IORESOURCE_IRQ)) {
- pr_debug("hcd probe: invalid resource type\n");
- return -ENODEV;
+ irq = platform_get_irq(pdev, 0);
+ if (irq < 0) {
+ dev_dbg(dev, "hcd probe: missing irq resource\n");
+ return irq;
}
hcd = usb_create_hcd(driver, &pdev->dev, "at91");
if (!hcd)
return -ENOMEM;
- hcd->rsrc_start = pdev->resource[0].start;
- hcd->rsrc_len = resource_size(&pdev->resource[0]);
+ hcd->rsrc_start = res->start;
+ hcd->rsrc_len = resource_size(res);
if (!request_mem_region(hcd->rsrc_start, hcd->rsrc_len, hcd_name)) {
pr_debug("request_mem_region failed\n");
@@ -199,7 +203,7 @@
ohci->num_ports = board->ports;
at91_start_hc(pdev);
- retval = usb_add_hcd(hcd, pdev->resource[1].start, IRQF_SHARED);
+ retval = usb_add_hcd(hcd, irq, IRQF_SHARED);
if (retval == 0)
return retval;
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index b8dffd5..73f5208 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -128,7 +128,12 @@
* any other sleep) on Haswell machines with LPT and LPT-LP
* with the new Intel BIOS
*/
- xhci->quirks |= XHCI_SPURIOUS_WAKEUP;
+ /* Limit the quirk to only known vendors, as this triggers
+ * yet another BIOS bug on some other machines
+ * https://bugzilla.kernel.org/show_bug.cgi?id=66171
+ */
+ if (pdev->subsystem_vendor == PCI_VENDOR_ID_HP)
+ xhci->quirks |= XHCI_SPURIOUS_WAKEUP;
}
if (pdev->vendor == PCI_VENDOR_ID_ETRON &&
pdev->device == PCI_DEVICE_ID_ASROCK_P67) {
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index 08e2f39..2b41c63 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -19,8 +19,9 @@
in host mode, low speed.
config FSL_USB2_OTG
- bool "Freescale USB OTG Transceiver Driver"
+ tristate "Freescale USB OTG Transceiver Driver"
depends on USB_EHCI_FSL && USB_FSL_USB2 && PM_RUNTIME
+ depends on USB
select USB_OTG
select USB_PHY
help
@@ -29,6 +30,7 @@
config ISP1301_OMAP
tristate "Philips ISP1301 with OMAP OTG"
depends on I2C && ARCH_OMAP_OTG
+ depends on USB
select USB_PHY
help
If you say yes here you get support for the Philips ISP1301
diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c
index 82232ac..bbe4f8e 100644
--- a/drivers/usb/phy/phy-tegra-usb.c
+++ b/drivers/usb/phy/phy-tegra-usb.c
@@ -876,7 +876,7 @@
tegra_phy->pad_regs = devm_ioremap(&pdev->dev, res->start,
resource_size(res));
- if (!tegra_phy->regs) {
+ if (!tegra_phy->pad_regs) {
dev_err(&pdev->dev, "Failed to remap UTMI Pad regs\n");
return -ENOMEM;
}
diff --git a/drivers/usb/phy/phy-twl6030-usb.c b/drivers/usb/phy/phy-twl6030-usb.c
index 30e8a61..bad57ce 100644
--- a/drivers/usb/phy/phy-twl6030-usb.c
+++ b/drivers/usb/phy/phy-twl6030-usb.c
@@ -127,7 +127,8 @@
static inline u8 twl6030_readb(struct twl6030_usb *twl, u8 module, u8 address)
{
- u8 data, ret = 0;
+ u8 data;
+ int ret;
ret = twl_i2c_read_u8(module, &data, address);
if (ret >= 0)
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 496b7e39..cc7a241 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -251,6 +251,7 @@
#define ZTE_PRODUCT_MF628 0x0015
#define ZTE_PRODUCT_MF626 0x0031
#define ZTE_PRODUCT_MC2718 0xffe8
+#define ZTE_PRODUCT_AC2726 0xfff1
#define BENQ_VENDOR_ID 0x04a5
#define BENQ_PRODUCT_H10 0x4068
@@ -1453,6 +1454,7 @@
{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x01) },
{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x05) },
{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x86, 0x10) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) },
{ USB_DEVICE(BENQ_VENDOR_ID, BENQ_PRODUCT_H10) },
{ USB_DEVICE(DLINK_VENDOR_ID, DLINK_PRODUCT_DWM_652) },
diff --git a/drivers/usb/serial/zte_ev.c b/drivers/usb/serial/zte_ev.c
index fca4c75..eae2c87 100644
--- a/drivers/usb/serial/zte_ev.c
+++ b/drivers/usb/serial/zte_ev.c
@@ -281,8 +281,7 @@
{ USB_DEVICE(0x19d2, 0xfffd) },
{ USB_DEVICE(0x19d2, 0xfffc) },
{ USB_DEVICE(0x19d2, 0xfffb) },
- /* AC2726, AC8710_V3 */
- { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xfff1, 0xff, 0xff, 0xff) },
+ /* AC8710_V3 */
{ USB_DEVICE(0x19d2, 0xfff6) },
{ USB_DEVICE(0x19d2, 0xfff7) },
{ USB_DEVICE(0x19d2, 0xfff8) },
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index c444654..5c4a95b 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -285,7 +285,7 @@
{
__le32 actual = cpu_to_le32(vb->num_pages);
- virtio_cwrite(vb->vdev, struct virtio_balloon_config, num_pages,
+ virtio_cwrite(vb->vdev, struct virtio_balloon_config, actual,
&actual);
}
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 55ea73f7..4c02e2b 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -350,17 +350,19 @@
pfn = page_to_pfn(page);
- set_phys_to_machine(pfn, frame_list[i]);
-
#ifdef CONFIG_XEN_HAVE_PVMMU
- /* Link back into the page tables if not highmem. */
- if (xen_pv_domain() && !PageHighMem(page)) {
- int ret;
- ret = HYPERVISOR_update_va_mapping(
- (unsigned long)__va(pfn << PAGE_SHIFT),
- mfn_pte(frame_list[i], PAGE_KERNEL),
- 0);
- BUG_ON(ret);
+ if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+ set_phys_to_machine(pfn, frame_list[i]);
+
+ /* Link back into the page tables if not highmem. */
+ if (!PageHighMem(page)) {
+ int ret;
+ ret = HYPERVISOR_update_va_mapping(
+ (unsigned long)__va(pfn << PAGE_SHIFT),
+ mfn_pte(frame_list[i], PAGE_KERNEL),
+ 0);
+ BUG_ON(ret);
+ }
}
#endif
@@ -378,7 +380,6 @@
enum bp_state state = BP_DONE;
unsigned long pfn, i;
struct page *page;
- struct page *scratch_page;
int ret;
struct xen_memory_reservation reservation = {
.address_bits = 0,
@@ -411,27 +412,29 @@
scrub_page(page);
+#ifdef CONFIG_XEN_HAVE_PVMMU
/*
* Ballooned out frames are effectively replaced with
* a scratch frame. Ensure direct mappings and the
* p2m are consistent.
*/
- scratch_page = get_balloon_scratch_page();
-#ifdef CONFIG_XEN_HAVE_PVMMU
- if (xen_pv_domain() && !PageHighMem(page)) {
- ret = HYPERVISOR_update_va_mapping(
- (unsigned long)__va(pfn << PAGE_SHIFT),
- pfn_pte(page_to_pfn(scratch_page),
- PAGE_KERNEL_RO), 0);
- BUG_ON(ret);
- }
-#endif
if (!xen_feature(XENFEAT_auto_translated_physmap)) {
unsigned long p;
+ struct page *scratch_page = get_balloon_scratch_page();
+
+ if (!PageHighMem(page)) {
+ ret = HYPERVISOR_update_va_mapping(
+ (unsigned long)__va(pfn << PAGE_SHIFT),
+ pfn_pte(page_to_pfn(scratch_page),
+ PAGE_KERNEL_RO), 0);
+ BUG_ON(ret);
+ }
p = page_to_pfn(scratch_page);
__set_phys_to_machine(pfn, pfn_to_mfn(p));
+
+ put_balloon_scratch_page();
}
- put_balloon_scratch_page();
+#endif
balloon_append(pfn_to_page(pfn));
}
@@ -627,15 +630,17 @@
if (!xen_domain())
return -ENODEV;
- for_each_online_cpu(cpu)
- {
- per_cpu(balloon_scratch_page, cpu) = alloc_page(GFP_KERNEL);
- if (per_cpu(balloon_scratch_page, cpu) == NULL) {
- pr_warn("Failed to allocate balloon_scratch_page for cpu %d\n", cpu);
- return -ENOMEM;
+ if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+ for_each_online_cpu(cpu)
+ {
+ per_cpu(balloon_scratch_page, cpu) = alloc_page(GFP_KERNEL);
+ if (per_cpu(balloon_scratch_page, cpu) == NULL) {
+ pr_warn("Failed to allocate balloon_scratch_page for cpu %d\n", cpu);
+ return -ENOMEM;
+ }
}
+ register_cpu_notifier(&balloon_cpu_notifier);
}
- register_cpu_notifier(&balloon_cpu_notifier);
pr_info("Initialising balloon driver\n");
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 02838719..aa846a4 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -1176,7 +1176,8 @@
gnttab_shared.addr = xen_remap(xen_hvm_resume_frames,
PAGE_SIZE * max_nr_gframes);
if (gnttab_shared.addr == NULL) {
- pr_warn("Failed to ioremap gnttab share frames!\n");
+ pr_warn("Failed to ioremap gnttab share frames (addr=0x%08lx)!\n",
+ xen_hvm_resume_frames);
return -ENOMEM;
}
}
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 8e74590..569a13b 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -533,12 +533,17 @@
{
struct page **pages = vma->vm_private_data;
int numpgs = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+ int rc;
if (!xen_feature(XENFEAT_auto_translated_physmap) || !numpgs || !pages)
return;
- xen_unmap_domain_mfn_range(vma, numpgs, pages);
- free_xenballooned_pages(numpgs, pages);
+ rc = xen_unmap_domain_mfn_range(vma, numpgs, pages);
+ if (rc == 0)
+ free_xenballooned_pages(numpgs, pages);
+ else
+ pr_crit("unable to unmap MFN range: leaking %d pages. rc=%d\n",
+ numpgs, rc);
kfree(pages);
}
diff --git a/fs/aio.c b/fs/aio.c
index 6efb7f6..062a5f6 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -244,9 +244,14 @@
int i;
for (i = 0; i < ctx->nr_pages; i++) {
+ struct page *page;
pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i,
page_count(ctx->ring_pages[i]));
- put_page(ctx->ring_pages[i]);
+ page = ctx->ring_pages[i];
+ if (!page)
+ continue;
+ ctx->ring_pages[i] = NULL;
+ put_page(page);
}
put_aio_ring_file(ctx);
@@ -280,18 +285,38 @@
unsigned long flags;
int rc;
+ rc = 0;
+
+ /* Make sure the old page hasn't already been changed */
+ spin_lock(&mapping->private_lock);
+ ctx = mapping->private_data;
+ if (ctx) {
+ pgoff_t idx;
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+ idx = old->index;
+ if (idx < (pgoff_t)ctx->nr_pages) {
+ if (ctx->ring_pages[idx] != old)
+ rc = -EAGAIN;
+ } else
+ rc = -EINVAL;
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+ } else
+ rc = -EINVAL;
+ spin_unlock(&mapping->private_lock);
+
+ if (rc != 0)
+ return rc;
+
/* Writeback must be complete */
BUG_ON(PageWriteback(old));
- put_page(old);
+ get_page(new);
- rc = migrate_page_move_mapping(mapping, new, old, NULL, mode);
+ rc = migrate_page_move_mapping(mapping, new, old, NULL, mode, 1);
if (rc != MIGRATEPAGE_SUCCESS) {
- get_page(old);
+ put_page(new);
return rc;
}
- get_page(new);
-
/* We can potentially race against kioctx teardown here. Use the
* address_space's private data lock to protect the mapping's
* private_data.
@@ -303,13 +328,24 @@
spin_lock_irqsave(&ctx->completion_lock, flags);
migrate_page_copy(new, old);
idx = old->index;
- if (idx < (pgoff_t)ctx->nr_pages)
- ctx->ring_pages[idx] = new;
+ if (idx < (pgoff_t)ctx->nr_pages) {
+ /* And only do the move if things haven't changed */
+ if (ctx->ring_pages[idx] == old)
+ ctx->ring_pages[idx] = new;
+ else
+ rc = -EAGAIN;
+ } else
+ rc = -EINVAL;
spin_unlock_irqrestore(&ctx->completion_lock, flags);
} else
rc = -EBUSY;
spin_unlock(&mapping->private_lock);
+ if (rc == MIGRATEPAGE_SUCCESS)
+ put_page(old);
+ else
+ put_page(new);
+
return rc;
}
#endif
@@ -326,7 +362,7 @@
struct aio_ring *ring;
unsigned nr_events = ctx->max_reqs;
struct mm_struct *mm = current->mm;
- unsigned long size, populate;
+ unsigned long size, unused;
int nr_pages;
int i;
struct file *file;
@@ -347,18 +383,6 @@
return -EAGAIN;
}
- for (i = 0; i < nr_pages; i++) {
- struct page *page;
- page = find_or_create_page(file->f_inode->i_mapping,
- i, GFP_HIGHUSER | __GFP_ZERO);
- if (!page)
- break;
- pr_debug("pid(%d) page[%d]->count=%d\n",
- current->pid, i, page_count(page));
- SetPageUptodate(page);
- SetPageDirty(page);
- unlock_page(page);
- }
ctx->aio_ring_file = file;
nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring))
/ sizeof(struct io_event);
@@ -373,15 +397,36 @@
}
}
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page;
+ page = find_or_create_page(file->f_inode->i_mapping,
+ i, GFP_HIGHUSER | __GFP_ZERO);
+ if (!page)
+ break;
+ pr_debug("pid(%d) page[%d]->count=%d\n",
+ current->pid, i, page_count(page));
+ SetPageUptodate(page);
+ SetPageDirty(page);
+ unlock_page(page);
+
+ ctx->ring_pages[i] = page;
+ }
+ ctx->nr_pages = i;
+
+ if (unlikely(i != nr_pages)) {
+ aio_free_ring(ctx);
+ return -EAGAIN;
+ }
+
ctx->mmap_size = nr_pages * PAGE_SIZE;
pr_debug("attempting mmap of %lu bytes\n", ctx->mmap_size);
down_write(&mm->mmap_sem);
ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size,
PROT_READ | PROT_WRITE,
- MAP_SHARED | MAP_POPULATE, 0, &populate);
+ MAP_SHARED, 0, &unused);
+ up_write(&mm->mmap_sem);
if (IS_ERR((void *)ctx->mmap_base)) {
- up_write(&mm->mmap_sem);
ctx->mmap_size = 0;
aio_free_ring(ctx);
return -EAGAIN;
@@ -389,27 +434,6 @@
pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base);
- /* We must do this while still holding mmap_sem for write, as we
- * need to be protected against userspace attempting to mremap()
- * or munmap() the ring buffer.
- */
- ctx->nr_pages = get_user_pages(current, mm, ctx->mmap_base, nr_pages,
- 1, 0, ctx->ring_pages, NULL);
-
- /* Dropping the reference here is safe as the page cache will hold
- * onto the pages for us. It is also required so that page migration
- * can unmap the pages and get the right reference count.
- */
- for (i = 0; i < ctx->nr_pages; i++)
- put_page(ctx->ring_pages[i]);
-
- up_write(&mm->mmap_sem);
-
- if (unlikely(ctx->nr_pages != nr_pages)) {
- aio_free_ring(ctx);
- return -EAGAIN;
- }
-
ctx->user_id = ctx->mmap_base;
ctx->nr_events = nr_events; /* trusted copy */
@@ -652,7 +676,8 @@
aio_nr += ctx->max_reqs;
spin_unlock(&aio_nr_lock);
- percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */
+ percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */
+ percpu_ref_get(&ctx->reqs); /* free_ioctx_users() will drop this */
err = ioctx_add_table(ctx, mm);
if (err)
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 1e561c0..ec3ba43 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -210,9 +210,13 @@
if (err < 0) {
SetPageError(page);
goto out;
- } else if (err < PAGE_CACHE_SIZE) {
+ } else {
+ if (err < PAGE_CACHE_SIZE) {
/* zero fill remainder of page */
- zero_user_segment(page, err, PAGE_CACHE_SIZE);
+ zero_user_segment(page, err, PAGE_CACHE_SIZE);
+ } else {
+ flush_dcache_page(page);
+ }
}
SetPageUptodate(page);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 9a8e396..278fd28 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -978,7 +978,6 @@
struct ceph_mds_reply_inode *ininfo;
struct ceph_vino vino;
struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
- int i = 0;
int err = 0;
dout("fill_trace %p is_dentry %d is_target %d\n", req,
@@ -1039,6 +1038,29 @@
}
}
+ if (rinfo->head->is_target) {
+ vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
+ vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
+
+ in = ceph_get_inode(sb, vino);
+ if (IS_ERR(in)) {
+ err = PTR_ERR(in);
+ goto done;
+ }
+ req->r_target_inode = in;
+
+ err = fill_inode(in, &rinfo->targeti, NULL,
+ session, req->r_request_started,
+ (le32_to_cpu(rinfo->head->result) == 0) ?
+ req->r_fmode : -1,
+ &req->r_caps_reservation);
+ if (err < 0) {
+ pr_err("fill_inode badness %p %llx.%llx\n",
+ in, ceph_vinop(in));
+ goto done;
+ }
+ }
+
/*
* ignore null lease/binding on snapdir ENOENT, or else we
* will have trouble splicing in the virtual snapdir later
@@ -1108,7 +1130,6 @@
ceph_dentry(req->r_old_dentry)->offset);
dn = req->r_old_dentry; /* use old_dentry */
- in = dn->d_inode;
}
/* null dentry? */
@@ -1130,44 +1151,28 @@
}
/* attach proper inode */
- ininfo = rinfo->targeti.in;
- vino.ino = le64_to_cpu(ininfo->ino);
- vino.snap = le64_to_cpu(ininfo->snapid);
- in = dn->d_inode;
- if (!in) {
- in = ceph_get_inode(sb, vino);
- if (IS_ERR(in)) {
- pr_err("fill_trace bad get_inode "
- "%llx.%llx\n", vino.ino, vino.snap);
- err = PTR_ERR(in);
- d_drop(dn);
- goto done;
- }
+ if (!dn->d_inode) {
+ ihold(in);
dn = splice_dentry(dn, in, &have_lease, true);
if (IS_ERR(dn)) {
err = PTR_ERR(dn);
goto done;
}
req->r_dentry = dn; /* may have spliced */
- ihold(in);
- } else if (ceph_ino(in) == vino.ino &&
- ceph_snap(in) == vino.snap) {
- ihold(in);
- } else {
+ } else if (dn->d_inode && dn->d_inode != in) {
dout(" %p links to %p %llx.%llx, not %llx.%llx\n",
- dn, in, ceph_ino(in), ceph_snap(in),
- vino.ino, vino.snap);
+ dn, dn->d_inode, ceph_vinop(dn->d_inode),
+ ceph_vinop(in));
have_lease = false;
- in = NULL;
}
if (have_lease)
update_dentry_lease(dn, rinfo->dlease, session,
req->r_request_started);
dout(" final dn %p\n", dn);
- i++;
- } else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
- req->r_op == CEPH_MDS_OP_MKSNAP) && !req->r_aborted) {
+ } else if (!req->r_aborted &&
+ (req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
+ req->r_op == CEPH_MDS_OP_MKSNAP)) {
struct dentry *dn = req->r_dentry;
/* fill out a snapdir LOOKUPSNAP dentry */
@@ -1177,52 +1182,15 @@
ininfo = rinfo->targeti.in;
vino.ino = le64_to_cpu(ininfo->ino);
vino.snap = le64_to_cpu(ininfo->snapid);
- in = ceph_get_inode(sb, vino);
- if (IS_ERR(in)) {
- pr_err("fill_inode get_inode badness %llx.%llx\n",
- vino.ino, vino.snap);
- err = PTR_ERR(in);
- d_delete(dn);
- goto done;
- }
dout(" linking snapped dir %p to dn %p\n", in, dn);
+ ihold(in);
dn = splice_dentry(dn, in, NULL, true);
if (IS_ERR(dn)) {
err = PTR_ERR(dn);
goto done;
}
req->r_dentry = dn; /* may have spliced */
- ihold(in);
- rinfo->head->is_dentry = 1; /* fool notrace handlers */
}
-
- if (rinfo->head->is_target) {
- vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
- vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
-
- if (in == NULL || ceph_ino(in) != vino.ino ||
- ceph_snap(in) != vino.snap) {
- in = ceph_get_inode(sb, vino);
- if (IS_ERR(in)) {
- err = PTR_ERR(in);
- goto done;
- }
- }
- req->r_target_inode = in;
-
- err = fill_inode(in,
- &rinfo->targeti, NULL,
- session, req->r_request_started,
- (le32_to_cpu(rinfo->head->result) == 0) ?
- req->r_fmode : -1,
- &req->r_caps_reservation);
- if (err < 0) {
- pr_err("fill_inode badness %p %llx.%llx\n",
- in, ceph_vinop(in));
- goto done;
- }
- }
-
done:
dout("fill_trace done err=%d\n", err);
return err;
@@ -1272,7 +1240,7 @@
struct qstr dname;
struct dentry *dn;
struct inode *in;
- int err = 0, i;
+ int err = 0, ret, i;
struct inode *snapdir = NULL;
struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
struct ceph_dentry_info *di;
@@ -1305,6 +1273,7 @@
ceph_fill_dirfrag(parent->d_inode, rinfo->dir_dir);
}
+ /* FIXME: release caps/leases if error occurs */
for (i = 0; i < rinfo->dir_nr; i++) {
struct ceph_vino vino;
@@ -1329,9 +1298,10 @@
err = -ENOMEM;
goto out;
}
- err = ceph_init_dentry(dn);
- if (err < 0) {
+ ret = ceph_init_dentry(dn);
+ if (ret < 0) {
dput(dn);
+ err = ret;
goto out;
}
} else if (dn->d_inode &&
@@ -1351,9 +1321,6 @@
spin_unlock(&parent->d_lock);
}
- di = dn->d_fsdata;
- di->offset = ceph_make_fpos(frag, i + r_readdir_offset);
-
/* inode */
if (dn->d_inode) {
in = dn->d_inode;
@@ -1366,26 +1333,39 @@
err = PTR_ERR(in);
goto out;
}
- dn = splice_dentry(dn, in, NULL, false);
- if (IS_ERR(dn))
- dn = NULL;
}
if (fill_inode(in, &rinfo->dir_in[i], NULL, session,
req->r_request_started, -1,
&req->r_caps_reservation) < 0) {
pr_err("fill_inode badness on %p\n", in);
+ if (!dn->d_inode)
+ iput(in);
+ d_drop(dn);
goto next_item;
}
- if (dn)
- update_dentry_lease(dn, rinfo->dir_dlease[i],
- req->r_session,
- req->r_request_started);
+
+ if (!dn->d_inode) {
+ dn = splice_dentry(dn, in, NULL, false);
+ if (IS_ERR(dn)) {
+ err = PTR_ERR(dn);
+ dn = NULL;
+ goto next_item;
+ }
+ }
+
+ di = dn->d_fsdata;
+ di->offset = ceph_make_fpos(frag, i + r_readdir_offset);
+
+ update_dentry_lease(dn, rinfo->dir_dlease[i],
+ req->r_session,
+ req->r_request_started);
next_item:
if (dn)
dput(dn);
}
- req->r_did_prepopulate = true;
+ if (err == 0)
+ req->r_did_prepopulate = true;
out:
if (snapdir) {
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index aa33976..2c29db6 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -477,9 +477,10 @@
const int netfid, __u64 *pExtAttrBits, __u64 *pMask);
extern void cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb);
extern bool CIFSCouldBeMFSymlink(const struct cifs_fattr *fattr);
-extern int CIFSCheckMFSymlink(struct cifs_fattr *fattr,
- const unsigned char *path,
- struct cifs_sb_info *cifs_sb, unsigned int xid);
+extern int CIFSCheckMFSymlink(unsigned int xid, struct cifs_tcon *tcon,
+ struct cifs_sb_info *cifs_sb,
+ struct cifs_fattr *fattr,
+ const unsigned char *path);
extern int mdfour(unsigned char *, unsigned char *, int);
extern int E_md4hash(const unsigned char *passwd, unsigned char *p16,
const struct nls_table *codepage);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 124aa02..d707edb 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -4010,7 +4010,7 @@
rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
(struct smb_hdr *) pSMBr, &bytes_returned, 0);
if (rc) {
- cifs_dbg(FYI, "Send error in QPathInfo = %d\n", rc);
+ cifs_dbg(FYI, "Send error in QFileInfo = %d", rc);
} else { /* decode response */
rc = validate_t2((struct smb_t2_rsp *)pSMBr);
@@ -4179,7 +4179,7 @@
rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
(struct smb_hdr *) pSMBr, &bytes_returned, 0);
if (rc) {
- cifs_dbg(FYI, "Send error in QPathInfo = %d\n", rc);
+ cifs_dbg(FYI, "Send error in UnixQFileInfo = %d", rc);
} else { /* decode response */
rc = validate_t2((struct smb_t2_rsp *)pSMBr);
@@ -4263,7 +4263,7 @@
rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
(struct smb_hdr *) pSMBr, &bytes_returned, 0);
if (rc) {
- cifs_dbg(FYI, "Send error in QPathInfo = %d\n", rc);
+ cifs_dbg(FYI, "Send error in UnixQPathInfo = %d", rc);
} else { /* decode response */
rc = validate_t2((struct smb_t2_rsp *)pSMBr);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 11ff5f1..a514e0a 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -193,7 +193,7 @@
static int
cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid,
struct tcon_link *tlink, unsigned oflags, umode_t mode,
- __u32 *oplock, struct cifs_fid *fid, int *created)
+ __u32 *oplock, struct cifs_fid *fid)
{
int rc = -ENOENT;
int create_options = CREATE_NOT_DIR;
@@ -349,7 +349,6 @@
.device = 0,
};
- *created |= FILE_CREATED;
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
args.uid = current_fsuid();
if (inode->i_mode & S_ISGID)
@@ -480,13 +479,16 @@
cifs_add_pending_open(&fid, tlink, &open);
rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode,
- &oplock, &fid, opened);
+ &oplock, &fid);
if (rc) {
cifs_del_pending_open(&open);
goto out;
}
+ if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
+ *opened |= FILE_CREATED;
+
rc = finish_open(file, direntry, generic_file_open, opened);
if (rc) {
if (server->ops->close)
@@ -529,7 +531,6 @@
struct TCP_Server_Info *server;
struct cifs_fid fid;
__u32 oplock;
- int created = FILE_CREATED;
cifs_dbg(FYI, "cifs_create parent inode = 0x%p name is: %s and dentry = 0x%p\n",
inode, direntry->d_name.name, direntry);
@@ -546,7 +547,7 @@
server->ops->new_lease_key(&fid);
rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode,
- &oplock, &fid, &created);
+ &oplock, &fid);
if (!rc && server->ops->close)
server->ops->close(xid, tcon, &fid);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 36f9ebb..49719b8 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -383,7 +383,8 @@
/* check for Minshall+French symlinks */
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
- int tmprc = CIFSCheckMFSymlink(&fattr, full_path, cifs_sb, xid);
+ int tmprc = CIFSCheckMFSymlink(xid, tcon, cifs_sb, &fattr,
+ full_path);
if (tmprc)
cifs_dbg(FYI, "CIFSCheckMFSymlink: %d\n", tmprc);
}
@@ -799,7 +800,8 @@
/* check for Minshall+French symlinks */
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
- tmprc = CIFSCheckMFSymlink(&fattr, full_path, cifs_sb, xid);
+ tmprc = CIFSCheckMFSymlink(xid, tcon, cifs_sb, &fattr,
+ full_path);
if (tmprc)
cifs_dbg(FYI, "CIFSCheckMFSymlink: %d\n", tmprc);
}
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index cc023471..92aee08 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -354,34 +354,30 @@
int
-CIFSCheckMFSymlink(struct cifs_fattr *fattr,
- const unsigned char *path,
- struct cifs_sb_info *cifs_sb, unsigned int xid)
+CIFSCheckMFSymlink(unsigned int xid, struct cifs_tcon *tcon,
+ struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr,
+ const unsigned char *path)
{
- int rc = 0;
+ int rc;
u8 *buf = NULL;
unsigned int link_len = 0;
unsigned int bytes_read = 0;
- struct cifs_tcon *ptcon;
if (!CIFSCouldBeMFSymlink(fattr))
/* it's not a symlink */
return 0;
buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL);
- if (!buf) {
- rc = -ENOMEM;
- goto out;
- }
+ if (!buf)
+ return -ENOMEM;
- ptcon = tlink_tcon(cifs_sb_tlink(cifs_sb));
- if ((ptcon->ses) && (ptcon->ses->server->ops->query_mf_symlink))
- rc = ptcon->ses->server->ops->query_mf_symlink(path, buf,
- &bytes_read, cifs_sb, xid);
+ if (tcon->ses->server->ops->query_mf_symlink)
+ rc = tcon->ses->server->ops->query_mf_symlink(path, buf,
+ &bytes_read, cifs_sb, xid);
else
- goto out;
+ rc = -ENOSYS;
- if (rc != 0)
+ if (rc)
goto out;
if (bytes_read == 0) /* not a symlink */
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 8b5e258..af90312 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1907,10 +1907,6 @@
}
}
}
- if (op == EPOLL_CTL_DEL && is_file_epoll(tf.file)) {
- tep = tf.file->private_data;
- mutex_lock_nested(&tep->mtx, 1);
- }
/*
* Try to lookup the file inside our RB tree, Since we grabbed "mtx"
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 2885349..20d6697 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1493,6 +1493,7 @@
sb->s_blocksize - offset : towrite;
tmp_bh.b_state = 0;
+ tmp_bh.b_size = sb->s_blocksize;
err = ext2_get_block(inode, blk, &tmp_bh, 1);
if (err < 0)
goto out;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index e618503..ece5556 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -268,6 +268,16 @@
/* Translate # of blks to # of clusters */
#define EXT4_NUM_B2C(sbi, blks) (((blks) + (sbi)->s_cluster_ratio - 1) >> \
(sbi)->s_cluster_bits)
+/* Mask out the low bits to get the starting block of the cluster */
+#define EXT4_PBLK_CMASK(s, pblk) ((pblk) & \
+ ~((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
+#define EXT4_LBLK_CMASK(s, lblk) ((lblk) & \
+ ~((ext4_lblk_t) (s)->s_cluster_ratio - 1))
+/* Get the cluster offset */
+#define EXT4_PBLK_COFF(s, pblk) ((pblk) & \
+ ((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
+#define EXT4_LBLK_COFF(s, lblk) ((lblk) & \
+ ((ext4_lblk_t) (s)->s_cluster_ratio - 1))
/*
* Structure of a blocks group descriptor
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 17ac112..3fe29de 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -259,6 +259,15 @@
if (WARN_ON_ONCE(err)) {
ext4_journal_abort_handle(where, line, __func__, bh,
handle, err);
+ ext4_error_inode(inode, where, line,
+ bh->b_blocknr,
+ "journal_dirty_metadata failed: "
+ "handle type %u started at line %u, "
+ "credits %u/%u, errcode %d",
+ handle->h_type,
+ handle->h_line_no,
+ handle->h_requested_credits,
+ handle->h_buffer_credits, err);
}
} else {
if (inode)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 35f65cf..3384dc4 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -360,8 +360,10 @@
{
ext4_fsblk_t block = ext4_ext_pblock(ext);
int len = ext4_ext_get_actual_len(ext);
+ ext4_lblk_t lblock = le32_to_cpu(ext->ee_block);
+ ext4_lblk_t last = lblock + len - 1;
- if (len == 0)
+ if (lblock > last)
return 0;
return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
}
@@ -387,11 +389,26 @@
if (depth == 0) {
/* leaf entries */
struct ext4_extent *ext = EXT_FIRST_EXTENT(eh);
+ struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+ ext4_fsblk_t pblock = 0;
+ ext4_lblk_t lblock = 0;
+ ext4_lblk_t prev = 0;
+ int len = 0;
while (entries) {
if (!ext4_valid_extent(inode, ext))
return 0;
+
+ /* Check for overlapping extents */
+ lblock = le32_to_cpu(ext->ee_block);
+ len = ext4_ext_get_actual_len(ext);
+ if ((lblock <= prev) && prev) {
+ pblock = ext4_ext_pblock(ext);
+ es->s_last_error_block = cpu_to_le64(pblock);
+ return 0;
+ }
ext++;
entries--;
+ prev = lblock + len - 1;
}
} else {
struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh);
@@ -1834,8 +1851,7 @@
depth = ext_depth(inode);
if (!path[depth].p_ext)
goto out;
- b2 = le32_to_cpu(path[depth].p_ext->ee_block);
- b2 &= ~(sbi->s_cluster_ratio - 1);
+ b2 = EXT4_LBLK_CMASK(sbi, le32_to_cpu(path[depth].p_ext->ee_block));
/*
* get the next allocated block if the extent in the path
@@ -1845,7 +1861,7 @@
b2 = ext4_ext_next_allocated_block(path);
if (b2 == EXT_MAX_BLOCKS)
goto out;
- b2 &= ~(sbi->s_cluster_ratio - 1);
+ b2 = EXT4_LBLK_CMASK(sbi, b2);
}
/* check for wrap through zero on extent logical start block*/
@@ -2504,7 +2520,7 @@
* extent, we have to mark the cluster as used (store negative
* cluster number in partial_cluster).
*/
- unaligned = pblk & (sbi->s_cluster_ratio - 1);
+ unaligned = EXT4_PBLK_COFF(sbi, pblk);
if (unaligned && (ee_len == num) &&
(*partial_cluster != -((long long)EXT4_B2C(sbi, pblk))))
*partial_cluster = EXT4_B2C(sbi, pblk);
@@ -2598,7 +2614,7 @@
* accidentally freeing it later on
*/
pblk = ext4_ext_pblock(ex);
- if (pblk & (sbi->s_cluster_ratio - 1))
+ if (EXT4_PBLK_COFF(sbi, pblk))
*partial_cluster =
-((long long)EXT4_B2C(sbi, pblk));
ex--;
@@ -3753,7 +3769,7 @@
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
ext4_lblk_t lblk_start, lblk_end;
- lblk_start = lblk & (~(sbi->s_cluster_ratio - 1));
+ lblk_start = EXT4_LBLK_CMASK(sbi, lblk);
lblk_end = lblk_start + sbi->s_cluster_ratio - 1;
return ext4_find_delalloc_range(inode, lblk_start, lblk_end);
@@ -3812,9 +3828,9 @@
trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks);
/* Check towards left side */
- c_offset = lblk_start & (sbi->s_cluster_ratio - 1);
+ c_offset = EXT4_LBLK_COFF(sbi, lblk_start);
if (c_offset) {
- lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1));
+ lblk_from = EXT4_LBLK_CMASK(sbi, lblk_start);
lblk_to = lblk_from + c_offset - 1;
if (ext4_find_delalloc_range(inode, lblk_from, lblk_to))
@@ -3822,7 +3838,7 @@
}
/* Now check towards right. */
- c_offset = (lblk_start + num_blks) & (sbi->s_cluster_ratio - 1);
+ c_offset = EXT4_LBLK_COFF(sbi, lblk_start + num_blks);
if (allocated_clusters && c_offset) {
lblk_from = lblk_start + num_blks;
lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1;
@@ -4030,7 +4046,7 @@
struct ext4_ext_path *path)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- ext4_lblk_t c_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+ ext4_lblk_t c_offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
ext4_lblk_t ex_cluster_start, ex_cluster_end;
ext4_lblk_t rr_cluster_start;
ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
@@ -4048,8 +4064,7 @@
(rr_cluster_start == ex_cluster_start)) {
if (rr_cluster_start == ex_cluster_end)
ee_start += ee_len - 1;
- map->m_pblk = (ee_start & ~(sbi->s_cluster_ratio - 1)) +
- c_offset;
+ map->m_pblk = EXT4_PBLK_CMASK(sbi, ee_start) + c_offset;
map->m_len = min(map->m_len,
(unsigned) sbi->s_cluster_ratio - c_offset);
/*
@@ -4203,7 +4218,7 @@
*/
map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
newex.ee_block = cpu_to_le32(map->m_lblk);
- cluster_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+ cluster_offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
/*
* If we are doing bigalloc, check to see if the extent returned
@@ -4271,7 +4286,7 @@
* needed so that future calls to get_implied_cluster_alloc()
* work correctly.
*/
- offset = map->m_lblk & (sbi->s_cluster_ratio - 1);
+ offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
ar.len = EXT4_NUM_B2C(sbi, offset+allocated);
ar.goal -= offset;
ar.logical -= offset;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0757634..61d49ff 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1206,7 +1206,6 @@
*/
static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock)
{
- int retries = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int md_needed;
@@ -1218,7 +1217,6 @@
* in order to allocate nrblocks
* worse case is one extent per block
*/
-repeat:
spin_lock(&ei->i_block_reservation_lock);
/*
* ext4_calc_metadata_amount() has side effects, which we have
@@ -1238,10 +1236,6 @@
ei->i_da_metadata_calc_len = save_len;
ei->i_da_metadata_calc_last_lblock = save_last_lblock;
spin_unlock(&ei->i_block_reservation_lock);
- if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
- cond_resched();
- goto repeat;
- }
return -ENOSPC;
}
ei->i_reserved_meta_blocks += md_needed;
@@ -1255,7 +1249,6 @@
*/
static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
{
- int retries = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int md_needed;
@@ -1277,7 +1270,6 @@
* in order to allocate nrblocks
* worse case is one extent per block
*/
-repeat:
spin_lock(&ei->i_block_reservation_lock);
/*
* ext4_calc_metadata_amount() has side effects, which we have
@@ -1297,10 +1289,6 @@
ei->i_da_metadata_calc_len = save_len;
ei->i_da_metadata_calc_last_lblock = save_last_lblock;
spin_unlock(&ei->i_block_reservation_lock);
- if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
- cond_resched();
- goto repeat;
- }
dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
return -ENOSPC;
}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 4d113ef..04a5c75 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3442,6 +3442,9 @@
{
struct ext4_prealloc_space *pa;
pa = container_of(head, struct ext4_prealloc_space, u.pa_rcu);
+
+ BUG_ON(atomic_read(&pa->pa_count));
+ BUG_ON(pa->pa_deleted == 0);
kmem_cache_free(ext4_pspace_cachep, pa);
}
@@ -3455,11 +3458,13 @@
ext4_group_t grp;
ext4_fsblk_t grp_blk;
- if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0)
- return;
-
/* in this short window concurrent discard can set pa_deleted */
spin_lock(&pa->pa_lock);
+ if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0) {
+ spin_unlock(&pa->pa_lock);
+ return;
+ }
+
if (pa->pa_deleted == 1) {
spin_unlock(&pa->pa_lock);
return;
@@ -4121,7 +4126,7 @@
ext4_get_group_no_and_offset(sb, goal, &group, &block);
/* set up allocation goals */
- ac->ac_b_ex.fe_logical = ar->logical & ~(sbi->s_cluster_ratio - 1);
+ ac->ac_b_ex.fe_logical = EXT4_LBLK_CMASK(sbi, ar->logical);
ac->ac_status = AC_STATUS_CONTINUE;
ac->ac_sb = sb;
ac->ac_inode = ar->inode;
@@ -4663,7 +4668,7 @@
* blocks at the beginning or the end unless we are explicitly
* requested to avoid doing so.
*/
- overflow = block & (sbi->s_cluster_ratio - 1);
+ overflow = EXT4_PBLK_COFF(sbi, block);
if (overflow) {
if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) {
overflow = sbi->s_cluster_ratio - overflow;
@@ -4677,7 +4682,7 @@
count += overflow;
}
}
- overflow = count & (sbi->s_cluster_ratio - 1);
+ overflow = EXT4_LBLK_COFF(sbi, count);
if (overflow) {
if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) {
if (count > overflow)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c977f4e..1f7784d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -792,7 +792,7 @@
}
ext4_es_unregister_shrinker(sbi);
- del_timer(&sbi->s_err_report);
+ del_timer_sync(&sbi->s_err_report);
ext4_release_system_zone(sb);
ext4_mb_release(sb);
ext4_ext_release(sb);
@@ -3316,11 +3316,19 @@
}
-static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi)
+static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb)
{
ext4_fsblk_t resv_clusters;
/*
+ * There's no need to reserve anything when we aren't using extents.
+ * The space estimates are exact, there are no unwritten extents,
+ * hole punching doesn't need new metadata... This is needed especially
+ * to keep ext2/3 backward compatibility.
+ */
+ if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS))
+ return 0;
+ /*
* By default we reserve 2% or 4096 clusters, whichever is smaller.
* This should cover the situations where we can not afford to run
* out of space like for example punch hole, or converting
@@ -3328,7 +3336,8 @@
* allocation would require 1, or 2 blocks, higher numbers are
* very rare.
*/
- resv_clusters = ext4_blocks_count(sbi->s_es) >> sbi->s_cluster_bits;
+ resv_clusters = ext4_blocks_count(EXT4_SB(sb)->s_es) >>
+ EXT4_SB(sb)->s_cluster_bits;
do_div(resv_clusters, 50);
resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096);
@@ -4071,10 +4080,10 @@
"available");
}
- err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sbi));
+ err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sb));
if (err) {
ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for "
- "reserved pool", ext4_calculate_resv_clusters(sbi));
+ "reserved pool", ext4_calculate_resv_clusters(sb));
goto failed_mount4a;
}
@@ -4184,7 +4193,7 @@
}
failed_mount3:
ext4_es_unregister_shrinker(sbi);
- del_timer(&sbi->s_err_report);
+ del_timer_sync(&sbi->s_err_report);
if (sbi->s_flex_groups)
ext4_kvfree(sbi->s_flex_groups);
percpu_counter_destroy(&sbi->s_freeclusters_counter);
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index b7fc035..73f3e4e 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -986,6 +986,7 @@
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ struct address_space *mapping = inode->i_mapping;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int rv;
@@ -1006,6 +1007,35 @@
if (rv != 1)
goto out; /* dio not valid, fall back to buffered i/o */
+ /*
+ * Now since we are holding a deferred (CW) lock at this point, you
+ * might be wondering why this is ever needed. There is a case however
+ * where we've granted a deferred local lock against a cached exclusive
+ * glock. That is ok provided all granted local locks are deferred, but
+ * it also means that it is possible to encounter pages which are
+ * cached and possibly also mapped. So here we check for that and sort
+ * them out ahead of the dio. The glock state machine will take care of
+ * everything else.
+ *
+ * If in fact the cached glock state (gl->gl_state) is deferred (CW) in
+ * the first place, mapping->nr_pages will always be zero.
+ */
+ if (mapping->nrpages) {
+ loff_t lstart = offset & (PAGE_CACHE_SIZE - 1);
+ loff_t len = iov_length(iov, nr_segs);
+ loff_t end = PAGE_ALIGN(offset + len) - 1;
+
+ rv = 0;
+ if (len == 0)
+ goto out;
+ if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
+ unmap_shared_mapping_range(ip->i_inode.i_mapping, offset, len);
+ rv = filemap_write_and_wait_range(mapping, lstart, end);
+ if (rv)
+ return rv;
+ truncate_inode_pages_range(mapping, lstart, end);
+ }
+
rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
offset, nr_segs, gfs2_get_block_direct,
NULL, NULL, 0);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index c8420f7..6f7a47c 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1655,6 +1655,7 @@
struct task_struct *gh_owner = NULL;
char flags_buf[32];
+ rcu_read_lock();
if (gh->gh_owner_pid)
gh_owner = pid_task(gh->gh_owner_pid, PIDTYPE_PID);
gfs2_print_dbg(seq, " H: s:%s f:%s e:%d p:%ld [%s] %pS\n",
@@ -1664,6 +1665,7 @@
gh->gh_owner_pid ? (long)pid_nr(gh->gh_owner_pid) : -1,
gh_owner ? gh_owner->comm : "(ended)",
(void *)gh->gh_ip);
+ rcu_read_unlock();
return 0;
}
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index db908f6..f88dcd9 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -192,8 +192,11 @@
if (ip && !S_ISREG(ip->i_inode.i_mode))
ip = NULL;
- if (ip && test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
- unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0);
+ if (ip) {
+ if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
+ unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0);
+ inode_dio_wait(&ip->i_inode);
+ }
if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
return;
@@ -410,6 +413,9 @@
return error;
}
+ if (gh->gh_state != LM_ST_DEFERRED)
+ inode_dio_wait(&ip->i_inode);
+
if ((ip->i_diskflags & GFS2_DIF_TRUNC_IN_PROG) &&
(gl->gl_state == LM_ST_EXCLUSIVE) &&
(gh->gh_state == LM_ST_EXCLUSIVE)) {
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 610613f..9dcb977 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -551,10 +551,10 @@
struct buffer_head *bh = bd->bd_bh;
struct gfs2_glock *gl = bd->bd_gl;
- gfs2_remove_from_ail(bd);
- bd->bd_bh = NULL;
bh->b_private = NULL;
bd->bd_blkno = bh->b_blocknr;
+ gfs2_remove_from_ail(bd); /* drops ref on bh */
+ bd->bd_bh = NULL;
bd->bd_ops = &gfs2_revoke_lops;
sdp->sd_log_num_revoke++;
atomic_inc(&gl->gl_revokes);
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 9324150..52f177b 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -258,6 +258,7 @@
struct address_space *mapping = bh->b_page->mapping;
struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping);
struct gfs2_bufdata *bd = bh->b_private;
+ int was_pinned = 0;
if (test_clear_buffer_pinned(bh)) {
trace_gfs2_pin(bd, 0);
@@ -273,12 +274,16 @@
tr->tr_num_databuf_rm++;
}
tr->tr_touched = 1;
+ was_pinned = 1;
brelse(bh);
}
if (bd) {
spin_lock(&sdp->sd_ail_lock);
if (bd->bd_tr) {
gfs2_trans_add_revoke(sdp, bd);
+ } else if (was_pinned) {
+ bh->b_private = NULL;
+ kmem_cache_free(gfs2_bufdata_cachep, bd);
}
spin_unlock(&sdp->sd_ail_lock);
}
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 82303b4..52fa883 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1366,8 +1366,18 @@
if (IS_ERR(s))
goto error_bdev;
- if (s->s_root)
+ if (s->s_root) {
+ /*
+ * s_umount nests inside bd_mutex during
+ * __invalidate_device(). blkdev_put() acquires
+ * bd_mutex and can't be called under s_umount. Drop
+ * s_umount temporarily. This is safe as we're
+ * holding an active reference.
+ */
+ up_write(&s->s_umount);
blkdev_put(bdev, mode);
+ down_write(&s->s_umount);
+ }
memset(&args, 0, sizeof(args));
args.ar_quota = GFS2_QUOTA_DEFAULT;
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 5203264..5fa344a 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -702,7 +702,7 @@
read_lock(&journal->j_state_lock);
#ifdef CONFIG_JBD2_DEBUG
if (!tid_geq(journal->j_commit_request, tid)) {
- printk(KERN_EMERG
+ printk(KERN_ERR
"%s: error: j_commit_request=%d, tid=%d\n",
__func__, journal->j_commit_request, tid);
}
@@ -718,10 +718,8 @@
}
read_unlock(&journal->j_state_lock);
- if (unlikely(is_journal_aborted(journal))) {
- printk(KERN_EMERG "journal commit I/O error\n");
+ if (unlikely(is_journal_aborted(journal)))
err = -EIO;
- }
return err;
}
@@ -1527,13 +1525,13 @@
if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) &&
JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
/* Can't have checksum v1 and v2 on at the same time! */
- printk(KERN_ERR "JBD: Can't enable checksumming v1 and v2 "
+ printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2 "
"at the same time!\n");
goto out;
}
if (!jbd2_verify_csum_type(journal, sb)) {
- printk(KERN_ERR "JBD: Unknown checksum type\n");
+ printk(KERN_ERR "JBD2: Unknown checksum type\n");
goto out;
}
@@ -1541,7 +1539,7 @@
if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
if (IS_ERR(journal->j_chksum_driver)) {
- printk(KERN_ERR "JBD: Cannot load crc32c driver.\n");
+ printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n");
err = PTR_ERR(journal->j_chksum_driver);
journal->j_chksum_driver = NULL;
goto out;
@@ -1550,7 +1548,7 @@
/* Check superblock checksum */
if (!jbd2_superblock_csum_verify(journal, sb)) {
- printk(KERN_ERR "JBD: journal checksum error\n");
+ printk(KERN_ERR "JBD2: journal checksum error\n");
goto out;
}
@@ -1836,7 +1834,7 @@
journal->j_chksum_driver = crypto_alloc_shash("crc32c",
0, 0);
if (IS_ERR(journal->j_chksum_driver)) {
- printk(KERN_ERR "JBD: Cannot load crc32c "
+ printk(KERN_ERR "JBD2: Cannot load crc32c "
"driver.\n");
journal->j_chksum_driver = NULL;
return 0;
@@ -2645,7 +2643,7 @@
#ifdef CONFIG_JBD2_DEBUG
int n = atomic_read(&nr_journal_heads);
if (n)
- printk(KERN_EMERG "JBD2: leaked %d journal_heads!\n", n);
+ printk(KERN_ERR "JBD2: leaked %d journal_heads!\n", n);
#endif
jbd2_remove_jbd_stats_proc_entry();
jbd2_journal_destroy_caches();
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 3929c50..3b6bb19 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -594,7 +594,7 @@
be32_to_cpu(tmp->h_sequence))) {
brelse(obh);
success = -EIO;
- printk(KERN_ERR "JBD: Invalid "
+ printk(KERN_ERR "JBD2: Invalid "
"checksum recovering "
"block %llu in log\n",
blocknr);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 7aa9a32..8360674 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -932,7 +932,7 @@
jbd2_alloc(jh2bh(jh)->b_size,
GFP_NOFS);
if (!frozen_buffer) {
- printk(KERN_EMERG
+ printk(KERN_ERR
"%s: OOM for frozen_buffer\n",
__func__);
JBUFFER_TRACE(jh, "oom!");
@@ -1166,7 +1166,7 @@
if (!jh->b_committed_data) {
committed_data = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS);
if (!committed_data) {
- printk(KERN_EMERG "%s: No memory for committed data\n",
+ printk(KERN_ERR "%s: No memory for committed data\n",
__func__);
err = -ENOMEM;
goto out;
@@ -1290,7 +1290,10 @@
* once a transaction -bzzz
*/
jh->b_modified = 1;
- J_ASSERT_JH(jh, handle->h_buffer_credits > 0);
+ if (handle->h_buffer_credits <= 0) {
+ ret = -ENOSPC;
+ goto out_unlock_bh;
+ }
handle->h_buffer_credits--;
}
@@ -1305,7 +1308,7 @@
JBUFFER_TRACE(jh, "fastpath");
if (unlikely(jh->b_transaction !=
journal->j_running_transaction)) {
- printk(KERN_EMERG "JBD: %s: "
+ printk(KERN_ERR "JBD2: %s: "
"jh->b_transaction (%llu, %p, %u) != "
"journal->j_running_transaction (%p, %u)",
journal->j_devname,
@@ -1332,7 +1335,7 @@
JBUFFER_TRACE(jh, "already on other transaction");
if (unlikely(jh->b_transaction !=
journal->j_committing_transaction)) {
- printk(KERN_EMERG "JBD: %s: "
+ printk(KERN_ERR "JBD2: %s: "
"jh->b_transaction (%llu, %p, %u) != "
"journal->j_committing_transaction (%p, %u)",
journal->j_devname,
@@ -1345,7 +1348,7 @@
ret = -EINVAL;
}
if (unlikely(jh->b_next_transaction != transaction)) {
- printk(KERN_EMERG "JBD: %s: "
+ printk(KERN_ERR "JBD2: %s: "
"jh->b_next_transaction (%llu, %p, %u) != "
"transaction (%p, %u)",
journal->j_devname,
@@ -1373,7 +1376,6 @@
jbd2_journal_put_journal_head(jh);
out:
JBUFFER_TRACE(jh, "exit");
- WARN_ON(ret); /* All errors are bugs, so dump the stack */
return ret;
}
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index b8e93a4..78c3c20 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -443,8 +443,11 @@
pstore_get_records(0);
kmsg_dump_register(&pstore_dumper);
- pstore_register_console();
- pstore_register_ftrace();
+
+ if ((psi->flags & PSTORE_FLAGS_FRAGILE) == 0) {
+ pstore_register_console();
+ pstore_register_ftrace();
+ }
if (pstore_update_ms >= 0) {
pstore_timer.expires = jiffies +
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index b94f936..35e7d08 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -609,7 +609,7 @@
struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
struct sysfs_open_file *of;
- bool has_read, has_write, has_mmap;
+ bool has_read, has_write;
int error = -EACCES;
/* need attr_sd for attr and ops, its parent for kobj */
@@ -621,7 +621,6 @@
has_read = battr->read || battr->mmap;
has_write = battr->write || battr->mmap;
- has_mmap = battr->mmap;
} else {
const struct sysfs_ops *ops = sysfs_file_ops(attr_sd);
@@ -633,7 +632,6 @@
has_read = ops->show;
has_write = ops->store;
- has_mmap = false;
}
/* check perms and supported operations */
@@ -661,9 +659,9 @@
* open file has a separate mutex, it's okay as long as those don't
* happen on the same file. At this point, we can't easily give
* each file a separate locking class. Let's differentiate on
- * whether the file has mmap or not for now.
+ * whether the file is bin or not for now.
*/
- if (has_mmap)
+ if (sysfs_is_bin(attr_sd))
mutex_init(&of->mutex);
else
mutex_init(&of->mutex);
diff --git a/fs/xfs/xfs_attr_remote.c b/fs/xfs/xfs_attr_remote.c
index 739e0a52..5549d69 100644
--- a/fs/xfs/xfs_attr_remote.c
+++ b/fs/xfs/xfs_attr_remote.c
@@ -110,7 +110,7 @@
if (be32_to_cpu(rmt->rm_bytes) > fsbsize - sizeof(*rmt))
return false;
if (be32_to_cpu(rmt->rm_offset) +
- be32_to_cpu(rmt->rm_bytes) >= XATTR_SIZE_MAX)
+ be32_to_cpu(rmt->rm_bytes) > XATTR_SIZE_MAX)
return false;
if (rmt->rm_owner == 0)
return false;
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 3ef11b2..3b2c14b 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -1635,7 +1635,7 @@
* blocks at the end of the file which do not start at the previous data block,
* we will try to align the new blocks at stripe unit boundaries.
*
- * Returns 0 in bma->aeof if the file (fork) is empty as any new write will be
+ * Returns 1 in bma->aeof if the file (fork) is empty as any new write will be
* at, or past the EOF.
*/
STATIC int
@@ -1650,9 +1650,14 @@
bma->aeof = 0;
error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec,
&is_empty);
- if (error || is_empty)
+ if (error)
return error;
+ if (is_empty) {
+ bma->aeof = 1;
+ return 0;
+ }
+
/*
* Check if we are allocation or past the last extent, or at least into
* the last delayed allocated extent.
@@ -3643,10 +3648,19 @@
int isaligned;
int tryagain;
int error;
+ int stripe_align;
ASSERT(ap->length);
mp = ap->ip->i_mount;
+
+ /* stripe alignment for allocation is determined by mount parameters */
+ stripe_align = 0;
+ if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC))
+ stripe_align = mp->m_swidth;
+ else if (mp->m_dalign)
+ stripe_align = mp->m_dalign;
+
align = ap->userdata ? xfs_get_extsz_hint(ap->ip) : 0;
if (unlikely(align)) {
error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
@@ -3655,6 +3669,8 @@
ASSERT(!error);
ASSERT(ap->length);
}
+
+
nullfb = *ap->firstblock == NULLFSBLOCK;
fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock);
if (nullfb) {
@@ -3730,7 +3746,7 @@
*/
if (!ap->flist->xbf_low && ap->aeof) {
if (!ap->offset) {
- args.alignment = mp->m_dalign;
+ args.alignment = stripe_align;
atype = args.type;
isaligned = 1;
/*
@@ -3755,13 +3771,13 @@
* of minlen+alignment+slop doesn't go up
* between the calls.
*/
- if (blen > mp->m_dalign && blen <= args.maxlen)
- nextminlen = blen - mp->m_dalign;
+ if (blen > stripe_align && blen <= args.maxlen)
+ nextminlen = blen - stripe_align;
else
nextminlen = args.minlen;
- if (nextminlen + mp->m_dalign > args.minlen + 1)
+ if (nextminlen + stripe_align > args.minlen + 1)
args.minalignslop =
- nextminlen + mp->m_dalign -
+ nextminlen + stripe_align -
args.minlen - 1;
else
args.minalignslop = 0;
@@ -3783,7 +3799,7 @@
*/
args.type = atype;
args.fsbno = ap->blkno;
- args.alignment = mp->m_dalign;
+ args.alignment = stripe_align;
args.minlen = nextminlen;
args.minalignslop = 0;
isaligned = 1;
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 5887e41..82e0dab 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -287,6 +287,7 @@
INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker);
queue_work(xfs_alloc_wq, &args->work);
wait_for_completion(&done);
+ destroy_work_on_stack(&args->work);
return args->result;
}
@@ -1187,7 +1188,12 @@
XFS_BUF_UNWRITE(bp);
XFS_BUF_READ(bp);
XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock));
- xfsbdstrat(mp, bp);
+
+ if (XFS_FORCED_SHUTDOWN(mp)) {
+ error = XFS_ERROR(EIO);
+ break;
+ }
+ xfs_buf_iorequest(bp);
error = xfs_buf_iowait(bp);
if (error) {
xfs_buf_ioerror_alert(bp,
@@ -1200,7 +1206,12 @@
XFS_BUF_UNDONE(bp);
XFS_BUF_UNREAD(bp);
XFS_BUF_WRITE(bp);
- xfsbdstrat(mp, bp);
+
+ if (XFS_FORCED_SHUTDOWN(mp)) {
+ error = XFS_ERROR(EIO);
+ break;
+ }
+ xfs_buf_iorequest(bp);
error = xfs_buf_iowait(bp);
if (error) {
xfs_buf_ioerror_alert(bp,
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index c7f0b77..afe7645 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -698,7 +698,11 @@
bp->b_flags |= XBF_READ;
bp->b_ops = ops;
- xfsbdstrat(target->bt_mount, bp);
+ if (XFS_FORCED_SHUTDOWN(target->bt_mount)) {
+ xfs_buf_relse(bp);
+ return NULL;
+ }
+ xfs_buf_iorequest(bp);
xfs_buf_iowait(bp);
return bp;
}
@@ -1089,7 +1093,7 @@
* This is meant for userdata errors; metadata bufs come with
* iodone functions attached, so that we can track down errors.
*/
-STATIC int
+int
xfs_bioerror_relse(
struct xfs_buf *bp)
{
@@ -1152,7 +1156,7 @@
ASSERT(xfs_buf_islocked(bp));
bp->b_flags |= XBF_WRITE;
- bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q);
+ bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | XBF_WRITE_FAIL);
xfs_bdstrat_cb(bp);
@@ -1164,25 +1168,6 @@
return error;
}
-/*
- * Wrapper around bdstrat so that we can stop data from going to disk in case
- * we are shutting down the filesystem. Typically user data goes thru this
- * path; one of the exceptions is the superblock.
- */
-void
-xfsbdstrat(
- struct xfs_mount *mp,
- struct xfs_buf *bp)
-{
- if (XFS_FORCED_SHUTDOWN(mp)) {
- trace_xfs_bdstrat_shut(bp, _RET_IP_);
- xfs_bioerror_relse(bp);
- return;
- }
-
- xfs_buf_iorequest(bp);
-}
-
STATIC void
_xfs_buf_ioend(
xfs_buf_t *bp,
@@ -1516,6 +1501,12 @@
struct xfs_buf *bp;
bp = list_first_entry(&dispose, struct xfs_buf, b_lru);
list_del_init(&bp->b_lru);
+ if (bp->b_flags & XBF_WRITE_FAIL) {
+ xfs_alert(btp->bt_mount,
+"Corruption Alert: Buffer at block 0x%llx had permanent write failures!\n"
+"Please run xfs_repair to determine the extent of the problem.",
+ (long long)bp->b_bn);
+ }
xfs_buf_rele(bp);
}
if (loop++ != 0)
@@ -1799,7 +1790,7 @@
blk_start_plug(&plug);
list_for_each_entry_safe(bp, n, io_list, b_list) {
- bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC);
+ bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC | XBF_WRITE_FAIL);
bp->b_flags |= XBF_WRITE;
if (!wait) {
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index e656833..1cf21a4 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -45,6 +45,7 @@
#define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */
#define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */
#define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */
+#define XBF_WRITE_FAIL (1 << 24)/* async writes have failed on this buffer */
/* I/O hints for the BIO layer */
#define XBF_SYNCIO (1 << 10)/* treat this buffer as synchronous I/O */
@@ -70,6 +71,7 @@
{ XBF_ASYNC, "ASYNC" }, \
{ XBF_DONE, "DONE" }, \
{ XBF_STALE, "STALE" }, \
+ { XBF_WRITE_FAIL, "WRITE_FAIL" }, \
{ XBF_SYNCIO, "SYNCIO" }, \
{ XBF_FUA, "FUA" }, \
{ XBF_FLUSH, "FLUSH" }, \
@@ -80,6 +82,7 @@
{ _XBF_DELWRI_Q, "DELWRI_Q" }, \
{ _XBF_COMPOUND, "COMPOUND" }
+
/*
* Internal state flags.
*/
@@ -269,9 +272,6 @@
/* Buffer Read and Write Routines */
extern int xfs_bwrite(struct xfs_buf *bp);
-
-extern void xfsbdstrat(struct xfs_mount *, struct xfs_buf *);
-
extern void xfs_buf_ioend(xfs_buf_t *, int);
extern void xfs_buf_ioerror(xfs_buf_t *, int);
extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func);
@@ -282,6 +282,8 @@
#define xfs_buf_zero(bp, off, len) \
xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO)
+extern int xfs_bioerror_relse(struct xfs_buf *);
+
static inline int xfs_buf_geterror(xfs_buf_t *bp)
{
return bp ? bp->b_error : ENOMEM;
@@ -301,7 +303,8 @@
#define XFS_BUF_ZEROFLAGS(bp) \
((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC| \
- XBF_SYNCIO|XBF_FUA|XBF_FLUSH))
+ XBF_SYNCIO|XBF_FUA|XBF_FLUSH| \
+ XBF_WRITE_FAIL))
void xfs_buf_stale(struct xfs_buf *bp);
#define XFS_BUF_UNSTALE(bp) ((bp)->b_flags &= ~XBF_STALE)
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index a64f67b..2227b9b 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -496,6 +496,14 @@
}
}
+/*
+ * Buffer IO error rate limiting. Limit it to no more than 10 messages per 30
+ * seconds so as to not spam logs too much on repeated detection of the same
+ * buffer being bad..
+ */
+
+DEFINE_RATELIMIT_STATE(xfs_buf_write_fail_rl_state, 30 * HZ, 10);
+
STATIC uint
xfs_buf_item_push(
struct xfs_log_item *lip,
@@ -524,6 +532,14 @@
trace_xfs_buf_item_push(bip);
+ /* has a previous flush failed due to IO errors? */
+ if ((bp->b_flags & XBF_WRITE_FAIL) &&
+ ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS:")) {
+ xfs_warn(bp->b_target->bt_mount,
+"Detected failing async write on buffer block 0x%llx. Retrying async write.\n",
+ (long long)bp->b_bn);
+ }
+
if (!xfs_buf_delwri_queue(bp, buffer_list))
rval = XFS_ITEM_FLUSHING;
xfs_buf_unlock(bp);
@@ -1096,8 +1112,9 @@
xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */
- if (!XFS_BUF_ISSTALE(bp)) {
- bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE;
+ if (!(bp->b_flags & (XBF_STALE|XBF_WRITE_FAIL))) {
+ bp->b_flags |= XBF_WRITE | XBF_ASYNC |
+ XBF_DONE | XBF_WRITE_FAIL;
xfs_buf_iorequest(bp);
} else {
xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c
index 56369d4..48c7d18 100644
--- a/fs/xfs/xfs_dir2_node.c
+++ b/fs/xfs/xfs_dir2_node.c
@@ -2067,12 +2067,12 @@
*/
int /* error */
xfs_dir2_node_removename(
- xfs_da_args_t *args) /* operation arguments */
+ struct xfs_da_args *args) /* operation arguments */
{
- xfs_da_state_blk_t *blk; /* leaf block */
+ struct xfs_da_state_blk *blk; /* leaf block */
int error; /* error return value */
int rval; /* operation return value */
- xfs_da_state_t *state; /* btree cursor */
+ struct xfs_da_state *state; /* btree cursor */
trace_xfs_dir2_node_removename(args);
@@ -2084,19 +2084,18 @@
state->mp = args->dp->i_mount;
state->blocksize = state->mp->m_dirblksize;
state->node_ents = state->mp->m_dir_node_ents;
- /*
- * Look up the entry we're deleting, set up the cursor.
- */
+
+ /* Look up the entry we're deleting, set up the cursor. */
error = xfs_da3_node_lookup_int(state, &rval);
if (error)
- rval = error;
- /*
- * Didn't find it, upper layer screwed up.
- */
+ goto out_free;
+
+ /* Didn't find it, upper layer screwed up. */
if (rval != EEXIST) {
- xfs_da_state_free(state);
- return rval;
+ error = rval;
+ goto out_free;
}
+
blk = &state->path.blk[state->path.active - 1];
ASSERT(blk->magic == XFS_DIR2_LEAFN_MAGIC);
ASSERT(state->extravalid);
@@ -2107,7 +2106,7 @@
error = xfs_dir2_leafn_remove(args, blk->bp, blk->index,
&state->extrablk, &rval);
if (error)
- return error;
+ goto out_free;
/*
* Fix the hash values up the btree.
*/
@@ -2122,6 +2121,7 @@
*/
if (!error)
error = xfs_dir2_node_to_leaf(state);
+out_free:
xfs_da_state_free(state);
return error;
}
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 27e0e54..104455b 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -618,7 +618,8 @@
}
if (!gid_eq(igid, gid)) {
if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) {
- ASSERT(!XFS_IS_PQUOTA_ON(mp));
+ ASSERT(xfs_sb_version_has_pquotino(&mp->m_sb) ||
+ !XFS_IS_PQUOTA_ON(mp));
ASSERT(mask & ATTR_GID);
ASSERT(gdqp);
olddquot2 = xfs_qm_vop_chown(tp, ip,
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index b6b669d..eae1692 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -193,7 +193,10 @@
bp->b_io_length = nbblks;
bp->b_error = 0;
- xfsbdstrat(log->l_mp, bp);
+ if (XFS_FORCED_SHUTDOWN(log->l_mp))
+ return XFS_ERROR(EIO);
+
+ xfs_buf_iorequest(bp);
error = xfs_buf_iowait(bp);
if (error)
xfs_buf_ioerror_alert(bp, __func__);
@@ -4397,7 +4400,13 @@
XFS_BUF_READ(bp);
XFS_BUF_UNASYNC(bp);
bp->b_ops = &xfs_sb_buf_ops;
- xfsbdstrat(log->l_mp, bp);
+
+ if (XFS_FORCED_SHUTDOWN(log->l_mp)) {
+ xfs_buf_relse(bp);
+ return XFS_ERROR(EIO);
+ }
+
+ xfs_buf_iorequest(bp);
error = xfs_buf_iowait(bp);
if (error) {
xfs_buf_ioerror_alert(bp, __func__);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 14a4996..dd88f0e 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -134,8 +134,6 @@
{
struct xfs_mount *mp = dqp->q_mount;
struct xfs_quotainfo *qi = mp->m_quotainfo;
- struct xfs_dquot *gdqp = NULL;
- struct xfs_dquot *pdqp = NULL;
xfs_dqlock(dqp);
if ((dqp->dq_flags & XFS_DQ_FREEING) || dqp->q_nrefs != 0) {
@@ -143,21 +141,6 @@
return EAGAIN;
}
- /*
- * If this quota has a hint attached, prepare for releasing it now.
- */
- gdqp = dqp->q_gdquot;
- if (gdqp) {
- xfs_dqlock(gdqp);
- dqp->q_gdquot = NULL;
- }
-
- pdqp = dqp->q_pdquot;
- if (pdqp) {
- xfs_dqlock(pdqp);
- dqp->q_pdquot = NULL;
- }
-
dqp->dq_flags |= XFS_DQ_FREEING;
xfs_dqflock(dqp);
@@ -206,11 +189,47 @@
XFS_STATS_DEC(xs_qm_dquot_unused);
xfs_qm_dqdestroy(dqp);
+ return 0;
+}
+
+/*
+ * Release the group or project dquot pointers the user dquots maybe carrying
+ * around as a hint, and proceed to purge the user dquot cache if requested.
+*/
+STATIC int
+xfs_qm_dqpurge_hints(
+ struct xfs_dquot *dqp,
+ void *data)
+{
+ struct xfs_dquot *gdqp = NULL;
+ struct xfs_dquot *pdqp = NULL;
+ uint flags = *((uint *)data);
+
+ xfs_dqlock(dqp);
+ if (dqp->dq_flags & XFS_DQ_FREEING) {
+ xfs_dqunlock(dqp);
+ return EAGAIN;
+ }
+
+ /* If this quota has a hint attached, prepare for releasing it now */
+ gdqp = dqp->q_gdquot;
+ if (gdqp)
+ dqp->q_gdquot = NULL;
+
+ pdqp = dqp->q_pdquot;
+ if (pdqp)
+ dqp->q_pdquot = NULL;
+
+ xfs_dqunlock(dqp);
if (gdqp)
- xfs_qm_dqput(gdqp);
+ xfs_qm_dqrele(gdqp);
if (pdqp)
- xfs_qm_dqput(pdqp);
+ xfs_qm_dqrele(pdqp);
+
+ if (flags & XFS_QMOPT_UQUOTA)
+ return xfs_qm_dqpurge(dqp, NULL);
+
return 0;
}
@@ -222,8 +241,18 @@
struct xfs_mount *mp,
uint flags)
{
- if (flags & XFS_QMOPT_UQUOTA)
- xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge, NULL);
+ /*
+ * We have to release group/project dquot hint(s) from the user dquot
+ * at first if they are there, otherwise we would run into an infinite
+ * loop while walking through radix tree to purge other type of dquots
+ * since their refcount is not zero if the user dquot refers to them
+ * as hint.
+ *
+ * Call the special xfs_qm_dqpurge_hints() will end up go through the
+ * general xfs_qm_dqpurge() against user dquot cache if requested.
+ */
+ xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge_hints, &flags);
+
if (flags & XFS_QMOPT_GQUOTA)
xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge, NULL);
if (flags & XFS_QMOPT_PQUOTA)
@@ -2082,24 +2111,21 @@
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
ASSERT(XFS_IS_QUOTA_RUNNING(mp));
- if (udqp) {
+ if (udqp && XFS_IS_UQUOTA_ON(mp)) {
ASSERT(ip->i_udquot == NULL);
- ASSERT(XFS_IS_UQUOTA_ON(mp));
ASSERT(ip->i_d.di_uid == be32_to_cpu(udqp->q_core.d_id));
ip->i_udquot = xfs_qm_dqhold(udqp);
xfs_trans_mod_dquot(tp, udqp, XFS_TRANS_DQ_ICOUNT, 1);
}
- if (gdqp) {
+ if (gdqp && XFS_IS_GQUOTA_ON(mp)) {
ASSERT(ip->i_gdquot == NULL);
- ASSERT(XFS_IS_GQUOTA_ON(mp));
ASSERT(ip->i_d.di_gid == be32_to_cpu(gdqp->q_core.d_id));
ip->i_gdquot = xfs_qm_dqhold(gdqp);
xfs_trans_mod_dquot(tp, gdqp, XFS_TRANS_DQ_ICOUNT, 1);
}
- if (pdqp) {
+ if (pdqp && XFS_IS_PQUOTA_ON(mp)) {
ASSERT(ip->i_pdquot == NULL);
- ASSERT(XFS_IS_PQUOTA_ON(mp));
ASSERT(xfs_get_projid(ip) == be32_to_cpu(pdqp->q_core.d_id));
ip->i_pdquot = xfs_qm_dqhold(pdqp);
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index c035d11..647b6f1 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -314,7 +314,18 @@
ASSERT(bp->b_iodone == NULL);
XFS_BUF_READ(bp);
bp->b_ops = ops;
- xfsbdstrat(tp->t_mountp, bp);
+
+ /*
+ * XXX(hch): clean up the error handling here to be less
+ * of a mess..
+ */
+ if (XFS_FORCED_SHUTDOWN(mp)) {
+ trace_xfs_bdstrat_shut(bp, _RET_IP_);
+ xfs_bioerror_relse(bp);
+ } else {
+ xfs_buf_iorequest(bp);
+ }
+
error = xfs_buf_iowait(bp);
if (error) {
xfs_buf_ioerror_alert(bp, __func__);
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index c602c77..ddabed1 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -169,7 +169,8 @@
u32 ejectable:1;
u32 power_manageable:1;
u32 match_driver:1;
- u32 reserved:27;
+ u32 no_hotplug:1;
+ u32 reserved:26;
};
/* File System */
@@ -344,6 +345,7 @@
extern int acpi_bus_generate_netlink_event(const char*, const char*, u8, int);
void acpi_bus_private_data_handler(acpi_handle, void *);
int acpi_bus_get_private_data(acpi_handle, void **);
+void acpi_bus_no_hotplug(acpi_handle handle);
extern int acpi_notifier_call_chain(struct acpi_device *, u32, u32);
extern int register_acpi_notifier(struct notifier_block *);
extern int unregister_acpi_notifier(struct notifier_block *);
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index f330d28..db09234 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -217,7 +217,7 @@
#endif
#ifndef pte_accessible
-# define pte_accessible(pte) ((void)(pte),1)
+# define pte_accessible(mm, pte) ((void)(pte), 1)
#endif
#ifndef flush_tlb_fix_spurious_fault
@@ -599,11 +599,10 @@
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
barrier();
#endif
- if (pmd_none(pmdval))
+ if (pmd_none(pmdval) || pmd_trans_huge(pmdval))
return 1;
if (unlikely(pmd_bad(pmdval))) {
- if (!pmd_trans_huge(pmdval))
- pmd_clear_bad(pmd);
+ pmd_clear_bad(pmd);
return 1;
}
return 0;
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index ddf2b42..1cd3f5d 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -3,13 +3,11 @@
#include <linux/thread_info.h>
-/*
- * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
- * that think a non-zero value indicates we cannot preempt.
- */
+#define PREEMPT_ENABLED (0)
+
static __always_inline int preempt_count(void)
{
- return current_thread_info()->preempt_count & ~PREEMPT_NEED_RESCHED;
+ return current_thread_info()->preempt_count;
}
static __always_inline int *preempt_count_ptr(void)
@@ -17,11 +15,6 @@
return ¤t_thread_info()->preempt_count;
}
-/*
- * We now loose PREEMPT_NEED_RESCHED and cause an extra reschedule; however the
- * alternative is loosing a reschedule. Better schedule too often -- also this
- * should be a very rare operation.
- */
static __always_inline void preempt_count_set(int pc)
{
*preempt_count_ptr() = pc;
@@ -41,28 +34,17 @@
task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \
} while (0)
-/*
- * We fold the NEED_RESCHED bit into the preempt count such that
- * preempt_enable() can decrement and test for needing to reschedule with a
- * single instruction.
- *
- * We invert the actual bit, so that when the decrement hits 0 we know we both
- * need to resched (the bit is cleared) and can resched (no preempt count).
- */
-
static __always_inline void set_preempt_need_resched(void)
{
- *preempt_count_ptr() &= ~PREEMPT_NEED_RESCHED;
}
static __always_inline void clear_preempt_need_resched(void)
{
- *preempt_count_ptr() |= PREEMPT_NEED_RESCHED;
}
static __always_inline bool test_preempt_need_resched(void)
{
- return !(*preempt_count_ptr() & PREEMPT_NEED_RESCHED);
+ return false;
}
/*
@@ -81,7 +63,12 @@
static __always_inline bool __preempt_count_dec_and_test(void)
{
- return !--*preempt_count_ptr();
+ /*
+ * Because of load-store architectures cannot do per-cpu atomic
+ * operations; we cannot use PREEMPT_NEED_RESCHED because it might get
+ * lost.
+ */
+ return !--*preempt_count_ptr() && tif_need_resched();
}
/*
@@ -89,7 +76,7 @@
*/
static __always_inline bool should_resched(void)
{
- return unlikely(!*preempt_count_ptr());
+ return unlikely(!preempt_count() && tif_need_resched());
}
#ifdef CONFIG_PREEMPT
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 87578c1..49376ae 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -600,7 +600,7 @@
{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, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|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}, \
diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h
index 669fef5..3e0fbe4 100644
--- a/include/linux/auxvec.h
+++ b/include/linux/auxvec.h
@@ -3,6 +3,6 @@
#include <uapi/linux/auxvec.h>
-#define AT_VECTOR_SIZE_BASE 19 /* NEW_AUX_ENT entries in auxiliary table */
+#define AT_VECTOR_SIZE_BASE 20 /* NEW_AUX_ENT entries in auxiliary table */
/* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */
#endif /* _LINUX_AUXVEC_H */
diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h
index 27b1bcf..86c12c9 100644
--- a/include/linux/bottom_half.h
+++ b/include/linux/bottom_half.h
@@ -1,9 +1,35 @@
#ifndef _LINUX_BH_H
#define _LINUX_BH_H
-extern void local_bh_disable(void);
+#include <linux/preempt.h>
+#include <linux/preempt_mask.h>
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt);
+#else
+static __always_inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
+{
+ preempt_count_add(cnt);
+ barrier();
+}
+#endif
+
+static inline void local_bh_disable(void)
+{
+ __local_bh_disable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET);
+}
+
extern void _local_bh_enable(void);
-extern void local_bh_enable(void);
-extern void local_bh_enable_ip(unsigned long ip);
+extern void __local_bh_enable_ip(unsigned long ip, unsigned int cnt);
+
+static inline void local_bh_enable_ip(unsigned long ip)
+{
+ __local_bh_enable_ip(ip, SOFTIRQ_DISABLE_OFFSET);
+}
+
+static inline void local_bh_enable(void)
+{
+ __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET);
+}
#endif /* _LINUX_BH_H */
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index d9cf963..12d5f97 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -5,6 +5,7 @@
#include <linux/lockdep.h>
#include <linux/ftrace_irq.h>
#include <linux/vtime.h>
+#include <asm/hardirq.h>
extern void synchronize_irq(unsigned int irq);
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index b0ed422..f0e5238 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -11,6 +11,7 @@
#include <linux/user_namespace.h>
#include <linux/securebits.h>
#include <linux/seqlock.h>
+#include <linux/rbtree.h>
#include <net/net_namespace.h>
#include <linux/sched/rt.h>
@@ -154,6 +155,14 @@
#define INIT_TASK_COMM "swapper"
+#ifdef CONFIG_RT_MUTEXES
+# define INIT_RT_MUTEXES(tsk) \
+ .pi_waiters = RB_ROOT, \
+ .pi_waiters_leftmost = NULL,
+#else
+# define INIT_RT_MUTEXES(tsk)
+#endif
+
/*
* INIT_TASK is used to set up the first task table, touch at
* your own risk!. Base=0, limit=0x1fffff (=2MB)
@@ -221,6 +230,7 @@
INIT_TRACE_RECURSION \
INIT_TASK_RCU_PREEMPT(tsk) \
INIT_CPUSET_SEQ(tsk) \
+ INIT_RT_MUTEXES(tsk) \
INIT_VTIME(tsk) \
}
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 0e23c26..9b50337 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -418,6 +418,7 @@
ATA_HORKAGE_DUMP_ID = (1 << 16), /* dump IDENTIFY data */
ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17), /* Set max sects to 65535 */
ATA_HORKAGE_ATAPI_DMADIR = (1 << 18), /* device requires dmadir */
+ ATA_HORKAGE_NO_NCQ_TRIM = (1 << 19), /* don't use queued TRIM */
/* DMA mask for user DMA control: User visible values; DO NOT
renumber */
diff --git a/include/linux/lockref.h b/include/linux/lockref.h
index c8929c3..4bfde0e 100644
--- a/include/linux/lockref.h
+++ b/include/linux/lockref.h
@@ -19,7 +19,7 @@
#define USE_CMPXCHG_LOCKREF \
(IS_ENABLED(CONFIG_ARCH_USE_CMPXCHG_LOCKREF) && \
- IS_ENABLED(CONFIG_SMP) && !BLOATED_SPINLOCKS)
+ IS_ENABLED(CONFIG_SMP) && SPINLOCK_SIZE <= 4)
struct lockref {
union {
diff --git a/include/linux/math64.h b/include/linux/math64.h
index 69ed5f5..c45c089 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -133,4 +133,34 @@
return ret;
}
+#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+
+#ifndef mul_u64_u32_shr
+static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift)
+{
+ return (u64)(((unsigned __int128)a * mul) >> shift);
+}
+#endif /* mul_u64_u32_shr */
+
+#else
+
+#ifndef mul_u64_u32_shr
+static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift)
+{
+ u32 ah, al;
+ u64 ret;
+
+ al = a;
+ ah = a >> 32;
+
+ ret = ((u64)al * mul) >> shift;
+ if (ah)
+ ret += ((u64)ah * mul) << (32 - shift);
+
+ return ret;
+}
+#endif /* mul_u64_u32_shr */
+
+#endif
+
#endif /* _LINUX_MATH64_H */
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index f5096b5..f015c05 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -55,7 +55,8 @@
struct page *newpage, struct page *page);
extern int migrate_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page,
- struct buffer_head *head, enum migrate_mode mode);
+ struct buffer_head *head, enum migrate_mode mode,
+ int extra_count);
#else
static inline void putback_lru_pages(struct list_head *l) {}
@@ -90,10 +91,19 @@
#endif /* CONFIG_MIGRATION */
#ifdef CONFIG_NUMA_BALANCING
+extern bool pmd_trans_migrating(pmd_t pmd);
+extern void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd);
extern int migrate_misplaced_page(struct page *page,
struct vm_area_struct *vma, int node);
extern bool migrate_ratelimited(int node);
#else
+static inline bool pmd_trans_migrating(pmd_t pmd)
+{
+ return false;
+}
+static inline void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
+{
+}
static inline int migrate_misplaced_page(struct page *page,
struct vm_area_struct *vma, int node)
{
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1cedd00..3552717 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1317,7 +1317,7 @@
#endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */
#if USE_SPLIT_PTE_PTLOCKS
-#if BLOATED_SPINLOCKS
+#if ALLOC_SPLIT_PTLOCKS
extern bool ptlock_alloc(struct page *page);
extern void ptlock_free(struct page *page);
@@ -1325,7 +1325,7 @@
{
return page->ptl;
}
-#else /* BLOATED_SPINLOCKS */
+#else /* ALLOC_SPLIT_PTLOCKS */
static inline bool ptlock_alloc(struct page *page)
{
return true;
@@ -1339,7 +1339,7 @@
{
return &page->ptl;
}
-#endif /* BLOATED_SPINLOCKS */
+#endif /* ALLOC_SPLIT_PTLOCKS */
static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
{
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index bd29941..290901a 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -26,6 +26,7 @@
#define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
#define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \
IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
+#define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8)
/*
* Each physical page in the system has a struct page associated with
@@ -155,7 +156,7 @@
* system if PG_buddy is set.
*/
#if USE_SPLIT_PTE_PTLOCKS
-#if BLOATED_SPINLOCKS
+#if ALLOC_SPLIT_PTLOCKS
spinlock_t *ptl;
#else
spinlock_t ptl;
@@ -443,6 +444,14 @@
/* numa_scan_seq prevents two threads setting pte_numa */
int numa_scan_seq;
#endif
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+ /*
+ * An operation with batched TLB flushing is going on. Anything that
+ * can move process memory needs to flush the TLB when moving a
+ * PROT_NONE or PROT_NUMA mapped page.
+ */
+ bool tlb_flush_pending;
+#endif
struct uprobes_state uprobes_state;
};
@@ -459,4 +468,45 @@
return mm->cpu_vm_mask_var;
}
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+/*
+ * Memory barriers to keep this state in sync are graciously provided by
+ * the page table locks, outside of which no page table modifications happen.
+ * The barriers below prevent the compiler from re-ordering the instructions
+ * around the memory barriers that are already present in the code.
+ */
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+ barrier();
+ return mm->tlb_flush_pending;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+ mm->tlb_flush_pending = true;
+
+ /*
+ * Guarantee that the tlb_flush_pending store does not leak into the
+ * critical section updating the page tables
+ */
+ smp_mb__before_spinlock();
+}
+/* Clearing is done after a TLB flush, which also provides a barrier. */
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+ barrier();
+ mm->tlb_flush_pending = false;
+}
+#else
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+ return false;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+#endif
+
#endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d9a550b..ce2a1f5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -769,7 +769,8 @@
* (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)
* Required can not be NULL.
*
- * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb);
+ * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
+ * void *accel_priv);
* Called to decide which queue to when device supports multiple
* transmit queues.
*
@@ -990,7 +991,8 @@
netdev_tx_t (*ndo_start_xmit) (struct sk_buff *skb,
struct net_device *dev);
u16 (*ndo_select_queue)(struct net_device *dev,
- struct sk_buff *skb);
+ struct sk_buff *skb,
+ void *accel_priv);
void (*ndo_change_rx_flags)(struct net_device *dev,
int flags);
void (*ndo_set_rx_mode)(struct net_device *dev);
@@ -1529,7 +1531,8 @@
}
struct netdev_queue *netdev_pick_tx(struct net_device *dev,
- struct sk_buff *skb);
+ struct sk_buff *skb,
+ void *accel_priv);
u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb);
/*
@@ -1819,6 +1822,7 @@
void dev_disable_lro(struct net_device *dev);
int dev_loopback_xmit(struct sk_buff *newskb);
int dev_queue_xmit(struct sk_buff *skb);
+int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv);
int register_netdevice(struct net_device *dev);
void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
void unregister_netdevice_many(struct list_head *head);
@@ -1912,6 +1916,15 @@
return dev->header_ops->parse(skb, haddr);
}
+static inline int dev_rebuild_header(struct sk_buff *skb)
+{
+ const struct net_device *dev = skb->dev;
+
+ if (!dev->header_ops || !dev->header_ops->rebuild)
+ return 0;
+ return dev->header_ops->rebuild(skb);
+}
+
typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
static inline int unregister_gifconf(unsigned int family)
@@ -2417,7 +2430,7 @@
int dev_get_phys_port_id(struct net_device *dev,
struct netdev_phys_port_id *ppid);
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
- struct netdev_queue *txq, void *accel_priv);
+ struct netdev_queue *txq);
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
extern int netdev_budget;
@@ -3008,6 +3021,19 @@
dev->gso_max_size = size;
}
+static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol,
+ int pulled_hlen, u16 mac_offset,
+ int mac_len)
+{
+ skb->protocol = protocol;
+ skb->encapsulation = 1;
+ skb_push(skb, pulled_hlen);
+ skb_reset_transport_header(skb);
+ skb->mac_header = mac_offset;
+ skb->network_header = skb->mac_header + mac_len;
+ skb->mac_len = mac_len;
+}
+
static inline bool netif_is_macvlan(struct net_device *dev)
{
return dev->priv_flags & IFF_MACVLAN;
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 57e890a..a5fc7d0 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -69,6 +69,7 @@
__PCPU_DUMMY_ATTRS char __pcpu_scope_##name; \
extern __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \
__PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \
+ extern __PCPU_ATTRS(sec) __typeof__(type) name; \
__PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak \
__typeof__(type) name
#else
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index a3d9dc8..dd9ddf8 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -64,7 +64,11 @@
} while (0)
#else
-#define preempt_enable() preempt_enable_no_resched()
+#define preempt_enable() \
+do { \
+ barrier(); \
+ preempt_count_dec(); \
+} while (0)
#define preempt_check_resched() do { } while (0)
#endif
@@ -93,7 +97,11 @@
__preempt_schedule_context(); \
} while (0)
#else
-#define preempt_enable_notrace() preempt_enable_no_resched_notrace()
+#define preempt_enable_notrace() \
+do { \
+ barrier(); \
+ __preempt_count_dec(); \
+} while (0)
#endif
#else /* !CONFIG_PREEMPT_COUNT */
@@ -116,6 +124,16 @@
#endif /* CONFIG_PREEMPT_COUNT */
+#ifdef MODULE
+/*
+ * Modules have no business playing preemption tricks.
+ */
+#undef sched_preempt_enable_no_resched
+#undef preempt_enable_no_resched
+#undef preempt_enable_no_resched_notrace
+#undef preempt_check_resched
+#endif
+
#ifdef CONFIG_PREEMPT_NOTIFIERS
struct preempt_notifier;
diff --git a/include/linux/preempt_mask.h b/include/linux/preempt_mask.h
index d169820..dbeec4d 100644
--- a/include/linux/preempt_mask.h
+++ b/include/linux/preempt_mask.h
@@ -2,7 +2,6 @@
#define LINUX_PREEMPT_MASK_H
#include <linux/preempt.h>
-#include <asm/hardirq.h>
/*
* We put the hardirq and softirq counter into the preemption
@@ -79,6 +78,21 @@
#endif
/*
+ * The preempt_count offset needed for things like:
+ *
+ * spin_lock_bh()
+ *
+ * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and
+ * softirqs, such that unlock sequences of:
+ *
+ * spin_unlock();
+ * local_bh_enable();
+ *
+ * Work as expected.
+ */
+#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_CHECK_OFFSET)
+
+/*
* Are we running in atomic context? WARNING: this macro cannot
* always detect atomic context; in particular, it cannot know about
* held spinlocks in non-preemptible kernels. Thus it should not be
diff --git a/include/linux/pstore.h b/include/linux/pstore.h
index abd437d..ece0c6b 100644
--- a/include/linux/pstore.h
+++ b/include/linux/pstore.h
@@ -51,6 +51,7 @@
char *buf;
size_t bufsize;
struct mutex read_mutex; /* serialize open/read/close */
+ int flags;
int (*open)(struct pstore_info *psi);
int (*close)(struct pstore_info *psi);
ssize_t (*read)(u64 *id, enum pstore_type_id *type,
@@ -70,6 +71,8 @@
void *data;
};
+#define PSTORE_FLAGS_FRAGILE 1
+
#ifdef CONFIG_PSTORE
extern int pstore_register(struct pstore_info *);
extern bool pstore_cannot_block_path(enum kmsg_dump_reason reason);
diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index 8e00f9f..9e7db9e 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -43,6 +43,7 @@
* Architecture-specific implementations of sys_reboot commands.
*/
+extern void migrate_to_reboot_cpu(void);
extern void machine_restart(char *cmd);
extern void machine_halt(void);
extern void machine_power_off(void);
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index de17134..3aed8d7 100644
--- a/include/linux/rtmutex.h
+++ b/include/linux/rtmutex.h
@@ -13,7 +13,7 @@
#define __LINUX_RT_MUTEX_H
#include <linux/linkage.h>
-#include <linux/plist.h>
+#include <linux/rbtree.h>
#include <linux/spinlock_types.h>
extern int max_lock_depth; /* for sysctl */
@@ -22,12 +22,14 @@
* The rt_mutex structure
*
* @wait_lock: spinlock to protect the structure
- * @wait_list: pilist head to enqueue waiters in priority order
+ * @waiters: rbtree root to enqueue waiters in priority order
+ * @waiters_leftmost: top waiter
* @owner: the mutex owner
*/
struct rt_mutex {
raw_spinlock_t wait_lock;
- struct plist_head wait_list;
+ struct rb_root waiters;
+ struct rb_node *waiters_leftmost;
struct task_struct *owner;
#ifdef CONFIG_DEBUG_RT_MUTEXES
int save_state;
@@ -66,7 +68,7 @@
#define __RT_MUTEX_INITIALIZER(mutexname) \
{ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
- , .wait_list = PLIST_HEAD_INIT(mutexname.wait_list) \
+ , .waiters = RB_ROOT \
, .owner = NULL \
__DEBUG_RT_MUTEX_INITIALIZER(mutexname)}
@@ -98,12 +100,4 @@
extern void rt_mutex_unlock(struct rt_mutex *lock);
-#ifdef CONFIG_RT_MUTEXES
-# define INIT_RT_MUTEXES(tsk) \
- .pi_waiters = PLIST_HEAD_INIT(tsk.pi_waiters), \
- INIT_RT_MUTEX_DEBUG(tsk)
-#else
-# define INIT_RT_MUTEXES(tsk)
-#endif
-
#endif
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 939428a..8e3e66a 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -24,6 +24,11 @@
extern int rtnl_is_locked(void);
#ifdef CONFIG_PROVE_LOCKING
extern int lockdep_rtnl_is_held(void);
+#else
+static inline int lockdep_rtnl_is_held(void)
+{
+ return 1;
+}
#endif /* #ifdef CONFIG_PROVE_LOCKING */
/**
diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h
index 9c9f049..5b9b84b 100644
--- a/include/linux/rwlock_api_smp.h
+++ b/include/linux/rwlock_api_smp.h
@@ -172,8 +172,7 @@
static inline void __raw_read_lock_bh(rwlock_t *lock)
{
- local_bh_disable();
- preempt_disable();
+ __local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
LOCK_CONTENDED(lock, do_raw_read_trylock, do_raw_read_lock);
}
@@ -200,8 +199,7 @@
static inline void __raw_write_lock_bh(rwlock_t *lock)
{
- local_bh_disable();
- preempt_disable();
+ __local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
LOCK_CONTENDED(lock, do_raw_write_trylock, do_raw_write_lock);
}
@@ -250,8 +248,7 @@
{
rwlock_release(&lock->dep_map, 1, _RET_IP_);
do_raw_read_unlock(lock);
- preempt_enable_no_resched();
- local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+ __local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
}
static inline void __raw_write_unlock_irqrestore(rwlock_t *lock,
@@ -275,8 +272,7 @@
{
rwlock_release(&lock->dep_map, 1, _RET_IP_);
do_raw_write_unlock(lock);
- preempt_enable_no_resched();
- local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+ __local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
}
#endif /* __LINUX_RWLOCK_API_SMP_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 768b037..a038752 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -16,6 +16,7 @@
#include <linux/types.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
+#include <linux/plist.h>
#include <linux/rbtree.h>
#include <linux/thread_info.h>
#include <linux/cpumask.h>
@@ -56,6 +57,70 @@
#include <asm/processor.h>
+#define SCHED_ATTR_SIZE_VER0 48 /* sizeof first published struct */
+
+/*
+ * Extended scheduling parameters data structure.
+ *
+ * This is needed because the original struct sched_param can not be
+ * altered without introducing ABI issues with legacy applications
+ * (e.g., in sched_getparam()).
+ *
+ * However, the possibility of specifying more than just a priority for
+ * the tasks may be useful for a wide variety of application fields, e.g.,
+ * multimedia, streaming, automation and control, and many others.
+ *
+ * This variant (sched_attr) is meant at describing a so-called
+ * sporadic time-constrained task. In such model a task is specified by:
+ * - the activation period or minimum instance inter-arrival time;
+ * - the maximum (or average, depending on the actual scheduling
+ * discipline) computation time of all instances, a.k.a. runtime;
+ * - the deadline (relative to the actual activation time) of each
+ * instance.
+ * Very briefly, a periodic (sporadic) task asks for the execution of
+ * some specific computation --which is typically called an instance--
+ * (at most) every period. Moreover, each instance typically lasts no more
+ * than the runtime and must be completed by time instant t equal to
+ * the instance activation time + the deadline.
+ *
+ * This is reflected by the actual fields of the sched_attr structure:
+ *
+ * @size size of the structure, for fwd/bwd compat.
+ *
+ * @sched_policy task's scheduling policy
+ * @sched_flags for customizing the scheduler behaviour
+ * @sched_nice task's nice value (SCHED_NORMAL/BATCH)
+ * @sched_priority task's static priority (SCHED_FIFO/RR)
+ * @sched_deadline representative of the task's deadline
+ * @sched_runtime representative of the task's runtime
+ * @sched_period representative of the task's period
+ *
+ * Given this task model, there are a multiplicity of scheduling algorithms
+ * and policies, that can be used to ensure all the tasks will make their
+ * timing constraints.
+ *
+ * As of now, the SCHED_DEADLINE policy (sched_dl scheduling class) is the
+ * only user of this new interface. More information about the algorithm
+ * available in the scheduling class file or in Documentation/.
+ */
+struct sched_attr {
+ u32 size;
+
+ u32 sched_policy;
+ u64 sched_flags;
+
+ /* SCHED_NORMAL, SCHED_BATCH */
+ s32 sched_nice;
+
+ /* SCHED_FIFO, SCHED_RR */
+ u32 sched_priority;
+
+ /* SCHED_DEADLINE */
+ u64 sched_runtime;
+ u64 sched_deadline;
+ u64 sched_period;
+};
+
struct exec_domain;
struct futex_pi_state;
struct robust_list_head;
@@ -168,7 +233,6 @@
#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0)
#define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0)
-#define task_is_dead(task) ((task)->exit_state != 0)
#define task_is_stopped_or_traced(task) \
((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
#define task_contributes_to_load(task) \
@@ -440,8 +504,6 @@
.sum_exec_runtime = 0, \
}
-#define PREEMPT_ENABLED (PREEMPT_NEED_RESCHED)
-
#ifdef CONFIG_PREEMPT_COUNT
#define PREEMPT_DISABLED (1 + PREEMPT_ENABLED)
#else
@@ -932,7 +994,8 @@
struct uts_namespace;
struct load_weight {
- unsigned long weight, inv_weight;
+ unsigned long weight;
+ u32 inv_weight;
};
struct sched_avg {
@@ -1030,6 +1093,51 @@
#endif
};
+struct sched_dl_entity {
+ struct rb_node rb_node;
+
+ /*
+ * Original scheduling parameters. Copied here from sched_attr
+ * during sched_setscheduler2(), they will remain the same until
+ * the next sched_setscheduler2().
+ */
+ u64 dl_runtime; /* maximum runtime for each instance */
+ u64 dl_deadline; /* relative deadline of each instance */
+ u64 dl_period; /* separation of two instances (period) */
+ u64 dl_bw; /* dl_runtime / dl_deadline */
+
+ /*
+ * Actual scheduling parameters. Initialized with the values above,
+ * they are continously updated during task execution. Note that
+ * the remaining runtime could be < 0 in case we are in overrun.
+ */
+ s64 runtime; /* remaining runtime for this instance */
+ u64 deadline; /* absolute deadline for this instance */
+ unsigned int flags; /* specifying the scheduler behaviour */
+
+ /*
+ * Some bool flags:
+ *
+ * @dl_throttled tells if we exhausted the runtime. If so, the
+ * task has to wait for a replenishment to be performed at the
+ * next firing of dl_timer.
+ *
+ * @dl_new tells if a new instance arrived. If so we must
+ * start executing it with full runtime and reset its absolute
+ * deadline;
+ *
+ * @dl_boosted tells if we are boosted due to DI. If so we are
+ * outside bandwidth enforcement mechanism (but only until we
+ * exit the critical section).
+ */
+ int dl_throttled, dl_new, dl_boosted;
+
+ /*
+ * Bandwidth enforcement timer. Each -deadline task has its
+ * own bandwidth to be enforced, thus we need one timer per task.
+ */
+ struct hrtimer dl_timer;
+};
struct rcu_node;
@@ -1066,6 +1174,7 @@
#ifdef CONFIG_CGROUP_SCHED
struct task_group *sched_task_group;
#endif
+ struct sched_dl_entity dl;
#ifdef CONFIG_PREEMPT_NOTIFIERS
/* list of struct preempt_notifier: */
@@ -1099,6 +1208,7 @@
struct list_head tasks;
#ifdef CONFIG_SMP
struct plist_node pushable_tasks;
+ struct rb_node pushable_dl_tasks;
#endif
struct mm_struct *mm, *active_mm;
@@ -1250,9 +1360,12 @@
#ifdef CONFIG_RT_MUTEXES
/* PI waiters blocked on a rt_mutex held by this task */
- struct plist_head pi_waiters;
+ struct rb_root pi_waiters;
+ struct rb_node *pi_waiters_leftmost;
/* Deadlock detection and priority inheritance handling */
struct rt_mutex_waiter *pi_blocked_on;
+ /* Top pi_waiters task */
+ struct task_struct *pi_top_task;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
@@ -1881,7 +1994,9 @@
* but then during bootup it turns out that sched_clock()
* is reliable after all:
*/
-extern int sched_clock_stable;
+extern int sched_clock_stable(void);
+extern void set_sched_clock_stable(void);
+extern void clear_sched_clock_stable(void);
extern void sched_clock_tick(void);
extern void sched_clock_idle_sleep_event(void);
@@ -1960,6 +2075,8 @@
const struct sched_param *);
extern int sched_setscheduler_nocheck(struct task_struct *, int,
const struct sched_param *);
+extern int sched_setattr(struct task_struct *,
+ const struct sched_attr *);
extern struct task_struct *idle_task(int cpu);
/**
* is_idle_task - is the specified task an idle task?
@@ -2039,7 +2156,7 @@
#else
static inline void kick_process(struct task_struct *tsk) { }
#endif
-extern void sched_fork(unsigned long clone_flags, struct task_struct *p);
+extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
extern void sched_dead(struct task_struct *p);
extern void proc_caches_init(void);
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
new file mode 100644
index 0000000..9d303b8
--- /dev/null
+++ b/include/linux/sched/deadline.h
@@ -0,0 +1,24 @@
+#ifndef _SCHED_DEADLINE_H
+#define _SCHED_DEADLINE_H
+
+/*
+ * SCHED_DEADLINE tasks has negative priorities, reflecting
+ * the fact that any of them has higher prio than RT and
+ * NORMAL/BATCH tasks.
+ */
+
+#define MAX_DL_PRIO 0
+
+static inline int dl_prio(int prio)
+{
+ if (unlikely(prio < MAX_DL_PRIO))
+ return 1;
+ return 0;
+}
+
+static inline int dl_task(struct task_struct *p)
+{
+ return dl_prio(p->prio);
+}
+
+#endif /* _SCHED_DEADLINE_H */
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index 440434d..34e4ebe 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -35,6 +35,7 @@
#ifdef CONFIG_RT_MUTEXES
extern int rt_mutex_getprio(struct task_struct *p);
extern void rt_mutex_setprio(struct task_struct *p, int prio);
+extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task);
extern void rt_mutex_adjust_pi(struct task_struct *p);
static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
{
@@ -45,6 +46,10 @@
{
return p->normal_prio;
}
+static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
+{
+ return NULL;
+}
# define rt_mutex_adjust_pi(p) do { } while (0)
static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
{
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 41467f8..31e0193 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -48,7 +48,6 @@
extern unsigned int sysctl_numa_balancing_scan_period_min;
extern unsigned int sysctl_numa_balancing_scan_period_max;
extern unsigned int sysctl_numa_balancing_scan_size;
-extern unsigned int sysctl_numa_balancing_settle_count;
#ifdef CONFIG_SCHED_DEBUG
extern unsigned int sysctl_sched_migration_cost;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 215b5ea..6f69b3f 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1638,6 +1638,11 @@
skb->mac_header += offset;
}
+static inline void skb_pop_mac_header(struct sk_buff *skb)
+{
+ skb->mac_header = skb->network_header;
+}
+
static inline void skb_probe_transport_header(struct sk_buff *skb,
const int offset_hint)
{
@@ -2526,6 +2531,10 @@
* Ethernet MAC Drivers should call this function in their hard_xmit()
* function immediately before giving the sk_buff to the MAC hardware.
*
+ * Specifically, one should make absolutely sure that this function is
+ * called before TX completion of this packet can trigger. Otherwise
+ * the packet could potentially already be freed.
+ *
* @skb: A socket buffer.
*/
static inline void skb_tx_timestamp(struct sk_buff *skb)
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index bdb9993..42dfab8 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -131,8 +131,7 @@
static inline void __raw_spin_lock_bh(raw_spinlock_t *lock)
{
- local_bh_disable();
- preempt_disable();
+ __local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
}
@@ -174,20 +173,17 @@
{
spin_release(&lock->dep_map, 1, _RET_IP_);
do_raw_spin_unlock(lock);
- preempt_enable_no_resched();
- local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+ __local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
}
static inline int __raw_spin_trylock_bh(raw_spinlock_t *lock)
{
- local_bh_disable();
- preempt_disable();
+ __local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
if (do_raw_spin_trylock(lock)) {
spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
return 1;
}
- preempt_enable_no_resched();
- local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+ __local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
return 0;
}
diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h
index af1f472..d0d1888 100644
--- a/include/linux/spinlock_api_up.h
+++ b/include/linux/spinlock_api_up.h
@@ -24,11 +24,14 @@
* flags straight, to suppress compiler warnings of unused lock
* variables, and to add the proper checker annotations:
*/
+#define ___LOCK(lock) \
+ do { __acquire(lock); (void)(lock); } while (0)
+
#define __LOCK(lock) \
- do { preempt_disable(); __acquire(lock); (void)(lock); } while (0)
+ do { preempt_disable(); ___LOCK(lock); } while (0)
#define __LOCK_BH(lock) \
- do { local_bh_disable(); __LOCK(lock); } while (0)
+ do { __local_bh_disable_ip(_THIS_IP_, SOFTIRQ_LOCK_OFFSET); ___LOCK(lock); } while (0)
#define __LOCK_IRQ(lock) \
do { local_irq_disable(); __LOCK(lock); } while (0)
@@ -36,12 +39,15 @@
#define __LOCK_IRQSAVE(lock, flags) \
do { local_irq_save(flags); __LOCK(lock); } while (0)
+#define ___UNLOCK(lock) \
+ do { __release(lock); (void)(lock); } while (0)
+
#define __UNLOCK(lock) \
- do { preempt_enable(); __release(lock); (void)(lock); } while (0)
+ do { preempt_enable(); ___UNLOCK(lock); } while (0)
#define __UNLOCK_BH(lock) \
- do { preempt_enable_no_resched(); local_bh_enable(); \
- __release(lock); (void)(lock); } while (0)
+ do { __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_LOCK_OFFSET); \
+ ___UNLOCK(lock); } while (0)
#define __UNLOCK_IRQ(lock) \
do { local_irq_enable(); __UNLOCK(lock); } while (0)
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 94273bb..40ed9e9 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -38,6 +38,7 @@
struct rlimit64;
struct rusage;
struct sched_param;
+struct sched_attr;
struct sel_arg_struct;
struct semaphore;
struct sembuf;
@@ -279,9 +280,14 @@
struct sched_param __user *param);
asmlinkage long sys_sched_setparam(pid_t pid,
struct sched_param __user *param);
+asmlinkage long sys_sched_setattr(pid_t pid,
+ struct sched_attr __user *attr);
asmlinkage long sys_sched_getscheduler(pid_t pid);
asmlinkage long sys_sched_getparam(pid_t pid,
struct sched_param __user *param);
+asmlinkage long sys_sched_getattr(pid_t pid,
+ struct sched_attr __user *attr,
+ unsigned int size);
asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
unsigned long __user *user_mask_ptr);
asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 9d8cf05..ecd3319 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -25,13 +25,16 @@
static inline void pagefault_enable(void)
{
+#ifndef CONFIG_PREEMPT
/*
* make sure to issue those last loads/stores before enabling
* the pagefault handler again.
*/
barrier();
preempt_count_dec();
- preempt_check_resched();
+#else
+ preempt_enable();
+#endif
}
#ifndef ARCH_HAS_NOCACHE_UACCESS
diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h
index 31e2de7..c0f0a13 100644
--- a/include/net/llc_pdu.h
+++ b/include/net/llc_pdu.h
@@ -142,7 +142,7 @@
#define LLC_S_PF_IS_1(pdu) ((pdu->ctrl_2 & LLC_S_PF_BIT_MASK) ? 1 : 0)
#define PDU_SUPV_GET_Nr(pdu) ((pdu->ctrl_2 & 0xFE) >> 1)
-#define PDU_GET_NEXT_Vr(sn) (++sn & ~LLC_2_SEQ_NBR_MODULO)
+#define PDU_GET_NEXT_Vr(sn) (((sn) + 1) & ~LLC_2_SEQ_NBR_MODULO)
/* FRMR information field macros */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 67b5d00..0a248b3 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1046,9 +1046,6 @@
/* Corked? */
char cork;
-
- /* Is this structure empty? */
- char empty;
};
void sctp_outq_init(struct sctp_association *, struct sctp_outq *);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 979874c..61e1935 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -978,7 +978,7 @@
};
struct ib_udata {
- void __user *inbuf;
+ const void __user *inbuf;
void __user *outbuf;
size_t inlen;
size_t outlen;
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 45412a6..321301c 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -517,10 +517,6 @@
u32 acl_index;
#define MAX_ACL_TAG_SIZE 64
char acl_tag[MAX_ACL_TAG_SIZE];
- u64 num_cmds;
- u64 read_bytes;
- u64 write_bytes;
- spinlock_t stats_lock;
/* Used for PR SPEC_I_PT=1 and REGISTER_AND_MOVE */
atomic_t acl_pr_ref_count;
struct se_dev_entry **device_list;
@@ -624,6 +620,7 @@
u32 unmap_granularity;
u32 unmap_granularity_alignment;
u32 max_write_same_len;
+ u32 max_bytes_per_io;
struct se_device *da_dev;
struct config_group da_group;
};
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 2f3f7ea..fe421e8 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -983,6 +983,8 @@
#define RADEON_INFO_SI_CP_DMA_COMPUTE 0x17
/* CIK macrotile mode array */
#define RADEON_INFO_CIK_MACROTILE_MODE_ARRAY 0x18
+/* query the number of render backends */
+#define RADEON_INFO_SI_BACKEND_ENABLED_MASK 0x19
struct drm_radeon_info {
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index bcb0912..f854ca4 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -75,6 +75,7 @@
#define DRM_VMW_PARAM_FIFO_CAPS 4
#define DRM_VMW_PARAM_MAX_FB_SIZE 5
#define DRM_VMW_PARAM_FIFO_HW_VERSION 6
+#define DRM_VMW_PARAM_MAX_SURF_MEMORY 7
/**
* struct drm_vmw_getparam_arg
diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h
index ecc8859..bd24470 100644
--- a/include/uapi/linux/input.h
+++ b/include/uapi/linux/input.h
@@ -464,7 +464,8 @@
#define KEY_BRIGHTNESS_ZERO 244 /* brightness off, use ambient */
#define KEY_DISPLAY_OFF 245 /* display device to off state */
-#define KEY_WIMAX 246
+#define KEY_WWAN 246 /* Wireless WAN (LTE, UMTS, GSM, etc.) */
+#define KEY_WIMAX KEY_WWAN
#define KEY_RFKILL 247 /* Key that controls all radios */
#define KEY_MICMUTE 248 /* Mute / unmute the microphone */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index e1802d6..959d454 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -679,6 +679,7 @@
*
* { u64 weight; } && PERF_SAMPLE_WEIGHT
* { u64 data_src; } && PERF_SAMPLE_DATA_SRC
+ * { u64 transaction; } && PERF_SAMPLE_TRANSACTION
* };
*/
PERF_RECORD_SAMPLE = 9,
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 5a0f945..2d5e49a 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -39,6 +39,7 @@
#define SCHED_BATCH 3
/* SCHED_ISO: reserved but not implemented yet */
#define SCHED_IDLE 5
+#define SCHED_DEADLINE 6
/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
#define SCHED_RESET_ON_FORK 0x40000000
diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h
index 65e1209..ae665ac 100644
--- a/include/xen/interface/io/blkif.h
+++ b/include/xen/interface/io/blkif.h
@@ -146,7 +146,7 @@
struct blkif_request_rw {
uint8_t nr_segments; /* number of segments */
blkif_vdev_t handle; /* only for read/write requests */
-#ifdef CONFIG_X86_64
+#ifndef CONFIG_X86_32
uint32_t _pad1; /* offsetof(blkif_request,u.rw.id) == 8 */
#endif
uint64_t id; /* private guest value, echoed in resp */
@@ -163,7 +163,7 @@
uint8_t flag; /* BLKIF_DISCARD_SECURE or zero. */
#define BLKIF_DISCARD_SECURE (1<<0) /* ignored if discard-secure=0 */
blkif_vdev_t _pad1; /* only for read/write requests */
-#ifdef CONFIG_X86_64
+#ifndef CONFIG_X86_32
uint32_t _pad2; /* offsetof(blkif_req..,u.discard.id)==8*/
#endif
uint64_t id; /* private guest value, echoed in resp */
@@ -175,7 +175,7 @@
struct blkif_request_other {
uint8_t _pad1;
blkif_vdev_t _pad2; /* only for read/write requests */
-#ifdef CONFIG_X86_64
+#ifndef CONFIG_X86_32
uint32_t _pad3; /* offsetof(blkif_req..,u.other.id)==8*/
#endif
uint64_t id; /* private guest value, echoed in resp */
@@ -184,7 +184,7 @@
struct blkif_request_indirect {
uint8_t indirect_op;
uint16_t nr_segments;
-#ifdef CONFIG_X86_64
+#ifndef CONFIG_X86_32
uint32_t _pad1; /* offsetof(blkif_...,u.indirect.id) == 8 */
#endif
uint64_t id;
@@ -192,7 +192,7 @@
blkif_vdev_t handle;
uint16_t _pad2;
grant_ref_t indirect_grefs[BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST];
-#ifdef CONFIG_X86_64
+#ifndef CONFIG_X86_32
uint32_t _pad3; /* make it 64 byte aligned */
#else
uint64_t _pad3; /* make it 64 byte aligned */
diff --git a/init/Kconfig b/init/Kconfig
index 79383d3..4e5d96a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -809,6 +809,12 @@
config ARCH_SUPPORTS_NUMA_BALANCING
bool
+#
+# For architectures that know their GCC __int128 support is sound
+#
+config ARCH_SUPPORTS_INT128
+ bool
+
# For architectures that (ab)use NUMA to represent different memory regions
# all cpu-local but of different latencies, such as SuperH.
#
diff --git a/kernel/Makefile b/kernel/Makefile
index bbaf7d5..bc010ee 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -137,9 +137,10 @@
###############################################################################
ifeq ($(CONFIG_SYSTEM_TRUSTED_KEYRING),y)
X509_CERTIFICATES-y := $(wildcard *.x509) $(wildcard $(srctree)/*.x509)
-X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += signing_key.x509
-X509_CERTIFICATES := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \
+X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += $(objtree)/signing_key.x509
+X509_CERTIFICATES-raw := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \
$(or $(realpath $(CERT)),$(CERT))))
+X509_CERTIFICATES := $(subst $(realpath $(objtree))/,,$(X509_CERTIFICATES-raw))
ifeq ($(X509_CERTIFICATES),)
$(warning *** No X.509 certificates found ***)
@@ -164,9 +165,9 @@
targets += $(obj)/.x509.list
$(obj)/.x509.list:
@echo $(X509_CERTIFICATES) >$@
+endif
clean-files := x509_certificate_list .x509.list
-endif
ifeq ($(CONFIG_MODULE_SIG),y)
###############################################################################
diff --git a/kernel/bounds.c b/kernel/bounds.c
index 5253204..9fd4246 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -22,6 +22,6 @@
#ifdef CONFIG_SMP
DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS));
#endif
- DEFINE(BLOATED_SPINLOCKS, sizeof(spinlock_t) > sizeof(int));
+ DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
/* End of constants */
}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8b729c2..bc1dcab 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -890,6 +890,16 @@
struct cgroup *cgrp = dentry->d_fsdata;
BUG_ON(!(cgroup_is_dead(cgrp)));
+
+ /*
+ * XXX: cgrp->id is only used to look up css's. As cgroup
+ * and css's lifetimes will be decoupled, it should be made
+ * per-subsystem and moved to css->id so that lookups are
+ * successful until the target css is released.
+ */
+ idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+ cgrp->id = -1;
+
call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
} else {
struct cfent *cfe = __d_cfe(dentry);
@@ -4268,6 +4278,7 @@
struct cgroup_subsys_state *css =
container_of(ref, struct cgroup_subsys_state, refcnt);
+ rcu_assign_pointer(css->cgroup->subsys[css->ss->subsys_id], NULL);
call_rcu(&css->rcu_head, css_free_rcu_fn);
}
@@ -4426,14 +4437,6 @@
list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
root->number_of_cgroups++;
- /* each css holds a ref to the cgroup's dentry and the parent css */
- for_each_root_subsys(root, ss) {
- struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
-
- dget(dentry);
- css_get(css->parent);
- }
-
/* hold a ref to the parent's dentry */
dget(parent->dentry);
@@ -4445,6 +4448,13 @@
if (err)
goto err_destroy;
+ /* each css holds a ref to the cgroup's dentry and parent css */
+ dget(dentry);
+ css_get(css->parent);
+
+ /* mark it consumed for error path */
+ css_ar[ss->subsys_id] = NULL;
+
if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
parent->parent) {
pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
@@ -4491,6 +4501,14 @@
return err;
err_destroy:
+ for_each_root_subsys(root, ss) {
+ struct cgroup_subsys_state *css = css_ar[ss->subsys_id];
+
+ if (css) {
+ percpu_ref_cancel_init(&css->refcnt);
+ ss->css_free(css);
+ }
+ }
cgroup_destroy_locked(cgrp);
mutex_unlock(&cgroup_mutex);
mutex_unlock(&dentry->d_inode->i_mutex);
@@ -4652,8 +4670,12 @@
* will be invoked to perform the rest of destruction once the
* percpu refs of all css's are confirmed to be killed.
*/
- for_each_root_subsys(cgrp->root, ss)
- kill_css(cgroup_css(cgrp, ss));
+ for_each_root_subsys(cgrp->root, ss) {
+ struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
+
+ if (css)
+ kill_css(css);
+ }
/*
* Mark @cgrp dead. This prevents further task migration and child
@@ -4722,14 +4744,6 @@
/* delete this cgroup from parent->children */
list_del_rcu(&cgrp->sibling);
- /*
- * We should remove the cgroup object from idr before its grace
- * period starts, so we won't be looking up a cgroup while the
- * cgroup is being freed.
- */
- idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
- cgrp->id = -1;
-
dput(d);
set_bit(CGRP_RELEASABLE, &parent->flags);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 72348dc..f574401 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1396,6 +1396,8 @@
if (event->state != PERF_EVENT_STATE_ACTIVE)
return;
+ perf_pmu_disable(event->pmu);
+
event->state = PERF_EVENT_STATE_INACTIVE;
if (event->pending_disable) {
event->pending_disable = 0;
@@ -1412,6 +1414,8 @@
ctx->nr_freq--;
if (event->attr.exclusive || !cpuctx->active_oncpu)
cpuctx->exclusive = 0;
+
+ perf_pmu_enable(event->pmu);
}
static void
@@ -1652,6 +1656,7 @@
struct perf_event_context *ctx)
{
u64 tstamp = perf_event_time(event);
+ int ret = 0;
if (event->state <= PERF_EVENT_STATE_OFF)
return 0;
@@ -1674,10 +1679,13 @@
*/
smp_wmb();
+ perf_pmu_disable(event->pmu);
+
if (event->pmu->add(event, PERF_EF_START)) {
event->state = PERF_EVENT_STATE_INACTIVE;
event->oncpu = -1;
- return -EAGAIN;
+ ret = -EAGAIN;
+ goto out;
}
event->tstamp_running += tstamp - event->tstamp_stopped;
@@ -1693,7 +1701,10 @@
if (event->attr.exclusive)
cpuctx->exclusive = 1;
- return 0;
+out:
+ perf_pmu_enable(event->pmu);
+
+ return ret;
}
static int
@@ -2743,6 +2754,8 @@
if (!event_filter_match(event))
continue;
+ perf_pmu_disable(event->pmu);
+
hwc = &event->hw;
if (hwc->interrupts == MAX_INTERRUPTS) {
@@ -2752,7 +2765,7 @@
}
if (!event->attr.freq || !event->attr.sample_freq)
- continue;
+ goto next;
/*
* stop the event and update event->count
@@ -2774,6 +2787,8 @@
perf_adjust_period(event, period, delta, false);
event->pmu->start(event, delta > 0 ? PERF_EF_RELOAD : 0);
+ next:
+ perf_pmu_enable(event->pmu);
}
perf_pmu_enable(ctx->pmu);
diff --git a/kernel/fork.c b/kernel/fork.c
index 728d5be..01b450a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -537,6 +537,7 @@
spin_lock_init(&mm->page_table_lock);
mm_init_aio(mm);
mm_init_owner(mm, p);
+ clear_tlb_flush_pending(mm);
if (likely(!mm_alloc_pgd(mm))) {
mm->def_flags = 0;
@@ -1086,8 +1087,10 @@
{
raw_spin_lock_init(&p->pi_lock);
#ifdef CONFIG_RT_MUTEXES
- plist_head_init(&p->pi_waiters);
+ p->pi_waiters = RB_ROOT;
+ p->pi_waiters_leftmost = NULL;
p->pi_blocked_on = NULL;
+ p->pi_top_task = NULL;
#endif
}
@@ -1310,7 +1313,9 @@
#endif
/* Perform scheduler related setup. Assign this task to a CPU. */
- sched_fork(clone_flags, p);
+ retval = sched_fork(clone_flags, p);
+ if (retval)
+ goto bad_fork_cleanup_policy;
retval = perf_event_init_task(p);
if (retval)
@@ -1402,13 +1407,11 @@
p->tgid = p->pid;
}
- p->pdeath_signal = 0;
- p->exit_state = 0;
-
p->nr_dirtied = 0;
p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
p->dirty_paused_when = 0;
+ p->pdeath_signal = 0;
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
diff --git a/kernel/freezer.c b/kernel/freezer.c
index b462fa1..aa6a8aa 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -19,6 +19,12 @@
bool pm_freezing;
bool pm_nosig_freezing;
+/*
+ * Temporary export for the deadlock workaround in ata_scsi_hotplug().
+ * Remove once the hack becomes unnecessary.
+ */
+EXPORT_SYMBOL_GPL(pm_freezing);
+
/* protects freezing and frozen transitions */
static DEFINE_SPINLOCK(freezer_lock);
diff --git a/kernel/futex.c b/kernel/futex.c
index f6ff019..679531c 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2316,6 +2316,8 @@
* code while we sleep on uaddr.
*/
debug_rt_mutex_init_waiter(&rt_waiter);
+ RB_CLEAR_NODE(&rt_waiter.pi_tree_entry);
+ RB_CLEAR_NODE(&rt_waiter.tree_entry);
rt_waiter.task = NULL;
ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 383319b..0909436 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -46,6 +46,7 @@
#include <linux/sched.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
#include <linux/timer.h>
#include <linux/freezer.h>
@@ -1610,7 +1611,7 @@
unsigned long slack;
slack = current->timer_slack_ns;
- if (rt_task(current))
+ if (dl_task(current) || rt_task(current))
slack = 0;
hrtimer_init_on_stack(&t.timer, clockid, mode);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index d0d8fca..9c97016 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1680,6 +1680,7 @@
{
kexec_in_progress = true;
kernel_restart_prepare(NULL);
+ migrate_to_reboot_cpu();
printk(KERN_EMERG "Starting new kernel\n");
machine_shutdown();
}
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index 13b243a..49b2ed3 100644
--- a/kernel/locking/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -24,7 +24,7 @@
#include <linux/kallsyms.h>
#include <linux/syscalls.h>
#include <linux/interrupt.h>
-#include <linux/plist.h>
+#include <linux/rbtree.h>
#include <linux/fs.h>
#include <linux/debug_locks.h>
@@ -57,7 +57,7 @@
void rt_mutex_debug_task_free(struct task_struct *task)
{
- DEBUG_LOCKS_WARN_ON(!plist_head_empty(&task->pi_waiters));
+ DEBUG_LOCKS_WARN_ON(!RB_EMPTY_ROOT(&task->pi_waiters));
DEBUG_LOCKS_WARN_ON(task->pi_blocked_on);
}
@@ -154,16 +154,12 @@
void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
{
memset(waiter, 0x11, sizeof(*waiter));
- plist_node_init(&waiter->list_entry, MAX_PRIO);
- plist_node_init(&waiter->pi_list_entry, MAX_PRIO);
waiter->deadlock_task_pid = NULL;
}
void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
{
put_pid(waiter->deadlock_task_pid);
- DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->list_entry));
- DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
memset(waiter, 0x22, sizeof(*waiter));
}
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 0dd6aec..2e960a2 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -14,6 +14,7 @@
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
#include <linux/timer.h>
#include "rtmutex_common.h"
@@ -91,10 +92,107 @@
}
#endif
+static inline int
+rt_mutex_waiter_less(struct rt_mutex_waiter *left,
+ struct rt_mutex_waiter *right)
+{
+ if (left->prio < right->prio)
+ return 1;
+
+ /*
+ * If both waiters have dl_prio(), we check the deadlines of the
+ * associated tasks.
+ * If left waiter has a dl_prio(), and we didn't return 1 above,
+ * then right waiter has a dl_prio() too.
+ */
+ if (dl_prio(left->prio))
+ return (left->task->dl.deadline < right->task->dl.deadline);
+
+ return 0;
+}
+
+static void
+rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+ struct rb_node **link = &lock->waiters.rb_node;
+ struct rb_node *parent = NULL;
+ struct rt_mutex_waiter *entry;
+ int leftmost = 1;
+
+ while (*link) {
+ parent = *link;
+ entry = rb_entry(parent, struct rt_mutex_waiter, tree_entry);
+ if (rt_mutex_waiter_less(waiter, entry)) {
+ link = &parent->rb_left;
+ } else {
+ link = &parent->rb_right;
+ leftmost = 0;
+ }
+ }
+
+ if (leftmost)
+ lock->waiters_leftmost = &waiter->tree_entry;
+
+ rb_link_node(&waiter->tree_entry, parent, link);
+ rb_insert_color(&waiter->tree_entry, &lock->waiters);
+}
+
+static void
+rt_mutex_dequeue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+ if (RB_EMPTY_NODE(&waiter->tree_entry))
+ return;
+
+ if (lock->waiters_leftmost == &waiter->tree_entry)
+ lock->waiters_leftmost = rb_next(&waiter->tree_entry);
+
+ rb_erase(&waiter->tree_entry, &lock->waiters);
+ RB_CLEAR_NODE(&waiter->tree_entry);
+}
+
+static void
+rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+ struct rb_node **link = &task->pi_waiters.rb_node;
+ struct rb_node *parent = NULL;
+ struct rt_mutex_waiter *entry;
+ int leftmost = 1;
+
+ while (*link) {
+ parent = *link;
+ entry = rb_entry(parent, struct rt_mutex_waiter, pi_tree_entry);
+ if (rt_mutex_waiter_less(waiter, entry)) {
+ link = &parent->rb_left;
+ } else {
+ link = &parent->rb_right;
+ leftmost = 0;
+ }
+ }
+
+ if (leftmost)
+ task->pi_waiters_leftmost = &waiter->pi_tree_entry;
+
+ rb_link_node(&waiter->pi_tree_entry, parent, link);
+ rb_insert_color(&waiter->pi_tree_entry, &task->pi_waiters);
+}
+
+static void
+rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+ if (RB_EMPTY_NODE(&waiter->pi_tree_entry))
+ return;
+
+ if (task->pi_waiters_leftmost == &waiter->pi_tree_entry)
+ task->pi_waiters_leftmost = rb_next(&waiter->pi_tree_entry);
+
+ rb_erase(&waiter->pi_tree_entry, &task->pi_waiters);
+ RB_CLEAR_NODE(&waiter->pi_tree_entry);
+}
+
/*
- * Calculate task priority from the waiter list priority
+ * Calculate task priority from the waiter tree priority
*
- * Return task->normal_prio when the waiter list is empty or when
+ * Return task->normal_prio when the waiter tree is empty or when
* the waiter is not allowed to do priority boosting
*/
int rt_mutex_getprio(struct task_struct *task)
@@ -102,10 +200,18 @@
if (likely(!task_has_pi_waiters(task)))
return task->normal_prio;
- return min(task_top_pi_waiter(task)->pi_list_entry.prio,
+ return min(task_top_pi_waiter(task)->prio,
task->normal_prio);
}
+struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
+{
+ if (likely(!task_has_pi_waiters(task)))
+ return NULL;
+
+ return task_top_pi_waiter(task)->task;
+}
+
/*
* Adjust the priority of a task, after its pi_waiters got modified.
*
@@ -115,7 +221,7 @@
{
int prio = rt_mutex_getprio(task);
- if (task->prio != prio)
+ if (task->prio != prio || dl_prio(prio))
rt_mutex_setprio(task, prio);
}
@@ -233,7 +339,7 @@
* When deadlock detection is off then we check, if further
* priority adjustment is necessary.
*/
- if (!detect_deadlock && waiter->list_entry.prio == task->prio)
+ if (!detect_deadlock && waiter->prio == task->prio)
goto out_unlock_pi;
lock = waiter->lock;
@@ -254,9 +360,9 @@
top_waiter = rt_mutex_top_waiter(lock);
/* Requeue the waiter */
- plist_del(&waiter->list_entry, &lock->wait_list);
- waiter->list_entry.prio = task->prio;
- plist_add(&waiter->list_entry, &lock->wait_list);
+ rt_mutex_dequeue(lock, waiter);
+ waiter->prio = task->prio;
+ rt_mutex_enqueue(lock, waiter);
/* Release the task */
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
@@ -280,17 +386,15 @@
if (waiter == rt_mutex_top_waiter(lock)) {
/* Boost the owner */
- plist_del(&top_waiter->pi_list_entry, &task->pi_waiters);
- waiter->pi_list_entry.prio = waiter->list_entry.prio;
- plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+ rt_mutex_dequeue_pi(task, top_waiter);
+ rt_mutex_enqueue_pi(task, waiter);
__rt_mutex_adjust_prio(task);
} else if (top_waiter == waiter) {
/* Deboost the owner */
- plist_del(&waiter->pi_list_entry, &task->pi_waiters);
+ rt_mutex_dequeue_pi(task, waiter);
waiter = rt_mutex_top_waiter(lock);
- waiter->pi_list_entry.prio = waiter->list_entry.prio;
- plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+ rt_mutex_enqueue_pi(task, waiter);
__rt_mutex_adjust_prio(task);
}
@@ -355,7 +459,7 @@
* 3) it is top waiter
*/
if (rt_mutex_has_waiters(lock)) {
- if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) {
+ if (task->prio >= rt_mutex_top_waiter(lock)->prio) {
if (!waiter || waiter != rt_mutex_top_waiter(lock))
return 0;
}
@@ -369,7 +473,7 @@
/* remove the queued waiter. */
if (waiter) {
- plist_del(&waiter->list_entry, &lock->wait_list);
+ rt_mutex_dequeue(lock, waiter);
task->pi_blocked_on = NULL;
}
@@ -379,8 +483,7 @@
*/
if (rt_mutex_has_waiters(lock)) {
top = rt_mutex_top_waiter(lock);
- top->pi_list_entry.prio = top->list_entry.prio;
- plist_add(&top->pi_list_entry, &task->pi_waiters);
+ rt_mutex_enqueue_pi(task, top);
}
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
}
@@ -416,13 +519,12 @@
__rt_mutex_adjust_prio(task);
waiter->task = task;
waiter->lock = lock;
- plist_node_init(&waiter->list_entry, task->prio);
- plist_node_init(&waiter->pi_list_entry, task->prio);
+ waiter->prio = task->prio;
/* Get the top priority waiter on the lock */
if (rt_mutex_has_waiters(lock))
top_waiter = rt_mutex_top_waiter(lock);
- plist_add(&waiter->list_entry, &lock->wait_list);
+ rt_mutex_enqueue(lock, waiter);
task->pi_blocked_on = waiter;
@@ -433,8 +535,8 @@
if (waiter == rt_mutex_top_waiter(lock)) {
raw_spin_lock_irqsave(&owner->pi_lock, flags);
- plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
- plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
+ rt_mutex_dequeue_pi(owner, top_waiter);
+ rt_mutex_enqueue_pi(owner, waiter);
__rt_mutex_adjust_prio(owner);
if (owner->pi_blocked_on)
@@ -486,7 +588,7 @@
* boosted mode and go back to normal after releasing
* lock->wait_lock.
*/
- plist_del(&waiter->pi_list_entry, ¤t->pi_waiters);
+ rt_mutex_dequeue_pi(current, waiter);
rt_mutex_set_owner(lock, NULL);
@@ -510,7 +612,7 @@
int chain_walk = 0;
raw_spin_lock_irqsave(¤t->pi_lock, flags);
- plist_del(&waiter->list_entry, &lock->wait_list);
+ rt_mutex_dequeue(lock, waiter);
current->pi_blocked_on = NULL;
raw_spin_unlock_irqrestore(¤t->pi_lock, flags);
@@ -521,13 +623,13 @@
raw_spin_lock_irqsave(&owner->pi_lock, flags);
- plist_del(&waiter->pi_list_entry, &owner->pi_waiters);
+ rt_mutex_dequeue_pi(owner, waiter);
if (rt_mutex_has_waiters(lock)) {
struct rt_mutex_waiter *next;
next = rt_mutex_top_waiter(lock);
- plist_add(&next->pi_list_entry, &owner->pi_waiters);
+ rt_mutex_enqueue_pi(owner, next);
}
__rt_mutex_adjust_prio(owner);
@@ -537,8 +639,6 @@
raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
}
- WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
-
if (!chain_walk)
return;
@@ -565,7 +665,8 @@
raw_spin_lock_irqsave(&task->pi_lock, flags);
waiter = task->pi_blocked_on;
- if (!waiter || waiter->list_entry.prio == task->prio) {
+ if (!waiter || (waiter->prio == task->prio &&
+ !dl_prio(task->prio))) {
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
return;
}
@@ -638,6 +739,8 @@
int ret = 0;
debug_rt_mutex_init_waiter(&waiter);
+ RB_CLEAR_NODE(&waiter.pi_tree_entry);
+ RB_CLEAR_NODE(&waiter.tree_entry);
raw_spin_lock(&lock->wait_lock);
@@ -904,7 +1007,8 @@
{
lock->owner = NULL;
raw_spin_lock_init(&lock->wait_lock);
- plist_head_init(&lock->wait_list);
+ lock->waiters = RB_ROOT;
+ lock->waiters_leftmost = NULL;
debug_rt_mutex_init(lock, name);
}
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 53a66c8..7431a9c 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -40,13 +40,13 @@
* This is the control structure for tasks blocked on a rt_mutex,
* which is allocated on the kernel stack on of the blocked task.
*
- * @list_entry: pi node to enqueue into the mutex waiters list
- * @pi_list_entry: pi node to enqueue into the mutex owner waiters list
+ * @tree_entry: pi node to enqueue into the mutex waiters tree
+ * @pi_tree_entry: pi node to enqueue into the mutex owner waiters tree
* @task: task reference to the blocked task
*/
struct rt_mutex_waiter {
- struct plist_node list_entry;
- struct plist_node pi_list_entry;
+ struct rb_node tree_entry;
+ struct rb_node pi_tree_entry;
struct task_struct *task;
struct rt_mutex *lock;
#ifdef CONFIG_DEBUG_RT_MUTEXES
@@ -54,14 +54,15 @@
struct pid *deadlock_task_pid;
struct rt_mutex *deadlock_lock;
#endif
+ int prio;
};
/*
- * Various helpers to access the waiters-plist:
+ * Various helpers to access the waiters-tree:
*/
static inline int rt_mutex_has_waiters(struct rt_mutex *lock)
{
- return !plist_head_empty(&lock->wait_list);
+ return !RB_EMPTY_ROOT(&lock->waiters);
}
static inline struct rt_mutex_waiter *
@@ -69,8 +70,8 @@
{
struct rt_mutex_waiter *w;
- w = plist_first_entry(&lock->wait_list, struct rt_mutex_waiter,
- list_entry);
+ w = rb_entry(lock->waiters_leftmost, struct rt_mutex_waiter,
+ tree_entry);
BUG_ON(w->lock != lock);
return w;
@@ -78,14 +79,14 @@
static inline int task_has_pi_waiters(struct task_struct *p)
{
- return !plist_head_empty(&p->pi_waiters);
+ return !RB_EMPTY_ROOT(&p->pi_waiters);
}
static inline struct rt_mutex_waiter *
task_top_pi_waiter(struct task_struct *p)
{
- return plist_first_entry(&p->pi_waiters, struct rt_mutex_waiter,
- pi_list_entry);
+ return rb_entry(p->pi_waiters_leftmost, struct rt_mutex_waiter,
+ pi_tree_entry);
}
/*
diff --git a/kernel/power/console.c b/kernel/power/console.c
index 463aa673..eacb8bd 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -81,6 +81,7 @@
list_for_each_entry(tmp, &pm_vt_switch_list, head) {
if (tmp->dev == dev) {
list_del(&tmp->head);
+ kfree(tmp);
break;
}
}
diff --git a/kernel/reboot.c b/kernel/reboot.c
index f813b34..662c83f 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -104,7 +104,7 @@
}
EXPORT_SYMBOL(unregister_reboot_notifier);
-static void migrate_to_reboot_cpu(void)
+void migrate_to_reboot_cpu(void)
{
/* The boot cpu is always logical cpu 0 */
int cpu = reboot_cpu;
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 7b62140..9a95c8c 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -11,9 +11,10 @@
CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
endif
-obj-y += core.o proc.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o
+obj-y += core.o proc.o clock.o cputime.o
+obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
obj-y += wait.o completion.o
-obj-$(CONFIG_SMP) += cpupri.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
obj-$(CONFIG_SCHEDSTATS) += stats.o
obj-$(CONFIG_SCHED_DEBUG) += debug.o
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c3ae144..6bd6a67 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -26,9 +26,10 @@
* at 0 on boot (but people really shouldn't rely on that).
*
* cpu_clock(i) -- can be used from any context, including NMI.
- * sched_clock_cpu(i) -- must be used with local IRQs disabled (implied by NMI)
* local_clock() -- is cpu_clock() on the current cpu.
*
+ * sched_clock_cpu(i)
+ *
* How:
*
* The implementation either uses sched_clock() when
@@ -50,15 +51,6 @@
* Furthermore, explicit sleep and wakeup hooks allow us to account for time
* that is otherwise invisible (TSC gets stopped).
*
- *
- * Notes:
- *
- * The !IRQ-safetly of sched_clock() and sched_clock_cpu() comes from things
- * like cpufreq interrupts that can change the base clock (TSC) multiplier
- * and cause funny jumps in time -- although the filtering provided by
- * sched_clock_cpu() should mitigate serious artifacts we cannot rely on it
- * in general since for !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK we fully rely on
- * sched_clock().
*/
#include <linux/spinlock.h>
#include <linux/hardirq.h>
@@ -66,6 +58,8 @@
#include <linux/percpu.h>
#include <linux/ktime.h>
#include <linux/sched.h>
+#include <linux/static_key.h>
+#include <linux/workqueue.h>
/*
* Scheduler clock - returns current time in nanosec units.
@@ -82,7 +76,37 @@
__read_mostly int sched_clock_running;
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-__read_mostly int sched_clock_stable;
+static struct static_key __sched_clock_stable = STATIC_KEY_INIT;
+
+int sched_clock_stable(void)
+{
+ if (static_key_false(&__sched_clock_stable))
+ return false;
+ return true;
+}
+
+void set_sched_clock_stable(void)
+{
+ if (!sched_clock_stable())
+ static_key_slow_dec(&__sched_clock_stable);
+}
+
+static void __clear_sched_clock_stable(struct work_struct *work)
+{
+ /* XXX worry about clock continuity */
+ if (sched_clock_stable())
+ static_key_slow_inc(&__sched_clock_stable);
+}
+
+static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable);
+
+void clear_sched_clock_stable(void)
+{
+ if (keventd_up())
+ schedule_work(&sched_clock_work);
+ else
+ __clear_sched_clock_stable(&sched_clock_work);
+}
struct sched_clock_data {
u64 tick_raw;
@@ -242,20 +266,20 @@
struct sched_clock_data *scd;
u64 clock;
- WARN_ON_ONCE(!irqs_disabled());
-
- if (sched_clock_stable)
+ if (sched_clock_stable())
return sched_clock();
if (unlikely(!sched_clock_running))
return 0ull;
+ preempt_disable();
scd = cpu_sdc(cpu);
if (cpu != smp_processor_id())
clock = sched_clock_remote(scd);
else
clock = sched_clock_local(scd);
+ preempt_enable();
return clock;
}
@@ -265,7 +289,7 @@
struct sched_clock_data *scd;
u64 now, now_gtod;
- if (sched_clock_stable)
+ if (sched_clock_stable())
return;
if (unlikely(!sched_clock_running))
@@ -316,14 +340,10 @@
*/
u64 cpu_clock(int cpu)
{
- u64 clock;
- unsigned long flags;
+ if (static_key_false(&__sched_clock_stable))
+ return sched_clock_cpu(cpu);
- local_irq_save(flags);
- clock = sched_clock_cpu(cpu);
- local_irq_restore(flags);
-
- return clock;
+ return sched_clock();
}
/*
@@ -335,14 +355,10 @@
*/
u64 local_clock(void)
{
- u64 clock;
- unsigned long flags;
+ if (static_key_false(&__sched_clock_stable))
+ return sched_clock_cpu(raw_smp_processor_id());
- local_irq_save(flags);
- clock = sched_clock_cpu(smp_processor_id());
- local_irq_restore(flags);
-
- return clock;
+ return sched_clock();
}
#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
@@ -362,12 +378,12 @@
u64 cpu_clock(int cpu)
{
- return sched_clock_cpu(cpu);
+ return sched_clock();
}
u64 local_clock(void)
{
- return sched_clock_cpu(0);
+ return sched_clock();
}
#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e85cda2..392c6f8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -296,6 +296,15 @@
*/
int sysctl_sched_rt_runtime = 950000;
+/*
+ * Maximum bandwidth available for all -deadline tasks and groups
+ * (if group scheduling is configured) on each CPU.
+ *
+ * default: 5%
+ */
+unsigned int sysctl_sched_dl_period = 1000000;
+int sysctl_sched_dl_runtime = 50000;
+
/*
@@ -899,7 +908,9 @@
{
int prio;
- if (task_has_rt_policy(p))
+ if (task_has_dl_policy(p))
+ prio = MAX_DL_PRIO-1;
+ else if (task_has_rt_policy(p))
prio = MAX_RT_PRIO-1 - p->rt_priority;
else
prio = __normal_prio(p);
@@ -945,7 +956,7 @@
if (prev_class->switched_from)
prev_class->switched_from(rq, p);
p->sched_class->switched_to(rq, p);
- } else if (oldprio != p->prio)
+ } else if (oldprio != p->prio || dl_task(p))
p->sched_class->prio_changed(rq, p, oldprio);
}
@@ -1717,6 +1728,13 @@
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
#endif
+ RB_CLEAR_NODE(&p->dl.rb_node);
+ hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ p->dl.dl_runtime = p->dl.runtime = 0;
+ p->dl.dl_deadline = p->dl.deadline = 0;
+ p->dl.dl_period = 0;
+ p->dl.flags = 0;
+
INIT_LIST_HEAD(&p->rt.run_list);
#ifdef CONFIG_PREEMPT_NOTIFIERS
@@ -1768,7 +1786,7 @@
/*
* fork()/clone()-time setup:
*/
-void sched_fork(unsigned long clone_flags, struct task_struct *p)
+int sched_fork(unsigned long clone_flags, struct task_struct *p)
{
unsigned long flags;
int cpu = get_cpu();
@@ -1790,7 +1808,7 @@
* Revert to default priority/policy on fork if requested.
*/
if (unlikely(p->sched_reset_on_fork)) {
- if (task_has_rt_policy(p)) {
+ if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
p->policy = SCHED_NORMAL;
p->static_prio = NICE_TO_PRIO(0);
p->rt_priority = 0;
@@ -1807,8 +1825,14 @@
p->sched_reset_on_fork = 0;
}
- if (!rt_prio(p->prio))
+ if (dl_prio(p->prio)) {
+ put_cpu();
+ return -EAGAIN;
+ } else if (rt_prio(p->prio)) {
+ p->sched_class = &rt_sched_class;
+ } else {
p->sched_class = &fair_sched_class;
+ }
if (p->sched_class->task_fork)
p->sched_class->task_fork(p);
@@ -1834,11 +1858,124 @@
init_task_preempt_count(p);
#ifdef CONFIG_SMP
plist_node_init(&p->pushable_tasks, MAX_PRIO);
+ RB_CLEAR_NODE(&p->pushable_dl_tasks);
#endif
put_cpu();
+ return 0;
}
+unsigned long to_ratio(u64 period, u64 runtime)
+{
+ if (runtime == RUNTIME_INF)
+ return 1ULL << 20;
+
+ /*
+ * Doing this here saves a lot of checks in all
+ * the calling paths, and returning zero seems
+ * safe for them anyway.
+ */
+ if (period == 0)
+ return 0;
+
+ return div64_u64(runtime << 20, period);
+}
+
+#ifdef CONFIG_SMP
+inline struct dl_bw *dl_bw_of(int i)
+{
+ return &cpu_rq(i)->rd->dl_bw;
+}
+
+static inline int dl_bw_cpus(int i)
+{
+ struct root_domain *rd = cpu_rq(i)->rd;
+ int cpus = 0;
+
+ for_each_cpu_and(i, rd->span, cpu_active_mask)
+ cpus++;
+
+ return cpus;
+}
+#else
+inline struct dl_bw *dl_bw_of(int i)
+{
+ return &cpu_rq(i)->dl.dl_bw;
+}
+
+static inline int dl_bw_cpus(int i)
+{
+ return 1;
+}
+#endif
+
+static inline
+void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
+{
+ dl_b->total_bw -= tsk_bw;
+}
+
+static inline
+void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
+{
+ dl_b->total_bw += tsk_bw;
+}
+
+static inline
+bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
+{
+ return dl_b->bw != -1 &&
+ dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
+}
+
+/*
+ * We must be sure that accepting a new task (or allowing changing the
+ * parameters of an existing one) is consistent with the bandwidth
+ * constraints. If yes, this function also accordingly updates the currently
+ * allocated bandwidth to reflect the new situation.
+ *
+ * This function is called while holding p's rq->lock.
+ */
+static int dl_overflow(struct task_struct *p, int policy,
+ const struct sched_attr *attr)
+{
+
+ struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+ u64 period = attr->sched_period;
+ u64 runtime = attr->sched_runtime;
+ u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
+ int cpus, err = -1;
+
+ if (new_bw == p->dl.dl_bw)
+ return 0;
+
+ /*
+ * Either if a task, enters, leave, or stays -deadline but changes
+ * its parameters, we may need to update accordingly the total
+ * allocated bandwidth of the container.
+ */
+ raw_spin_lock(&dl_b->lock);
+ cpus = dl_bw_cpus(task_cpu(p));
+ if (dl_policy(policy) && !task_has_dl_policy(p) &&
+ !__dl_overflow(dl_b, cpus, 0, new_bw)) {
+ __dl_add(dl_b, new_bw);
+ err = 0;
+ } else if (dl_policy(policy) && task_has_dl_policy(p) &&
+ !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
+ __dl_clear(dl_b, p->dl.dl_bw);
+ __dl_add(dl_b, new_bw);
+ err = 0;
+ } else if (!dl_policy(policy) && task_has_dl_policy(p)) {
+ __dl_clear(dl_b, p->dl.dl_bw);
+ err = 0;
+ }
+ raw_spin_unlock(&dl_b->lock);
+
+ return err;
+}
+
+extern void init_dl_bw(struct dl_bw *dl_b);
+
/*
* wake_up_new_task - wake up a newly created task for the first time.
*
@@ -2003,6 +2140,9 @@
if (unlikely(prev_state == TASK_DEAD)) {
task_numa_free(prev);
+ if (prev->sched_class->task_dead)
+ prev->sched_class->task_dead(prev);
+
/*
* Remove function-return probe instances associated with this
* task and put them back on the free list.
@@ -2296,7 +2436,7 @@
#ifdef CONFIG_SMP
rq->idle_balance = idle_cpu(cpu);
- trigger_load_balance(rq, cpu);
+ trigger_load_balance(rq);
#endif
rq_last_tick_reset(rq);
}
@@ -2414,10 +2554,10 @@
{
/*
* Test if we are atomic. Since do_exit() needs to call into
- * schedule() atomically, we ignore that path for now.
- * Otherwise, whine if we are scheduling when we should not be.
+ * schedule() atomically, we ignore that path. Otherwise whine
+ * if we are scheduling when we should not.
*/
- if (unlikely(in_atomic_preempt_off() && !prev->exit_state))
+ if (unlikely(in_atomic_preempt_off() && prev->state != TASK_DEAD))
__schedule_bug(prev);
rcu_sleep_check();
@@ -2761,11 +2901,11 @@
*/
void rt_mutex_setprio(struct task_struct *p, int prio)
{
- int oldprio, on_rq, running;
+ int oldprio, on_rq, running, enqueue_flag = 0;
struct rq *rq;
const struct sched_class *prev_class;
- BUG_ON(prio < 0 || prio > MAX_PRIO);
+ BUG_ON(prio > MAX_PRIO);
rq = __task_rq_lock(p);
@@ -2788,6 +2928,7 @@
}
trace_sched_pi_setprio(p, prio);
+ p->pi_top_task = rt_mutex_get_top_task(p);
oldprio = p->prio;
prev_class = p->sched_class;
on_rq = p->on_rq;
@@ -2797,23 +2938,49 @@
if (running)
p->sched_class->put_prev_task(rq, p);
- if (rt_prio(prio))
+ /*
+ * Boosting condition are:
+ * 1. -rt task is running and holds mutex A
+ * --> -dl task blocks on mutex A
+ *
+ * 2. -dl task is running and holds mutex A
+ * --> -dl task blocks on mutex A and could preempt the
+ * running task
+ */
+ if (dl_prio(prio)) {
+ if (!dl_prio(p->normal_prio) || (p->pi_top_task &&
+ dl_entity_preempt(&p->pi_top_task->dl, &p->dl))) {
+ p->dl.dl_boosted = 1;
+ p->dl.dl_throttled = 0;
+ enqueue_flag = ENQUEUE_REPLENISH;
+ } else
+ p->dl.dl_boosted = 0;
+ p->sched_class = &dl_sched_class;
+ } else if (rt_prio(prio)) {
+ if (dl_prio(oldprio))
+ p->dl.dl_boosted = 0;
+ if (oldprio < prio)
+ enqueue_flag = ENQUEUE_HEAD;
p->sched_class = &rt_sched_class;
- else
+ } else {
+ if (dl_prio(oldprio))
+ p->dl.dl_boosted = 0;
p->sched_class = &fair_sched_class;
+ }
p->prio = prio;
if (running)
p->sched_class->set_curr_task(rq);
if (on_rq)
- enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
+ enqueue_task(rq, p, enqueue_flag);
check_class_changed(rq, p, prev_class, oldprio);
out_unlock:
__task_rq_unlock(rq);
}
#endif
+
void set_user_nice(struct task_struct *p, long nice)
{
int old_prio, delta, on_rq;
@@ -2831,9 +2998,9 @@
* The RT priorities are set via sched_setscheduler(), but we still
* allow the 'normal' nice value to be set - but as expected
* it wont have any effect on scheduling until the task is
- * SCHED_FIFO/SCHED_RR:
+ * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR:
*/
- if (task_has_rt_policy(p)) {
+ if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
p->static_prio = NICE_TO_PRIO(nice);
goto out_unlock;
}
@@ -2988,22 +3155,87 @@
return pid ? find_task_by_vpid(pid) : current;
}
-/* Actually do priority change: must hold rq lock. */
+/*
+ * This function initializes the sched_dl_entity of a newly becoming
+ * SCHED_DEADLINE task.
+ *
+ * Only the static values are considered here, the actual runtime and the
+ * absolute deadline will be properly calculated when the task is enqueued
+ * for the first time with its new policy.
+ */
static void
-__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
+__setparam_dl(struct task_struct *p, const struct sched_attr *attr)
{
+ struct sched_dl_entity *dl_se = &p->dl;
+
+ init_dl_task_timer(dl_se);
+ dl_se->dl_runtime = attr->sched_runtime;
+ dl_se->dl_deadline = attr->sched_deadline;
+ dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
+ dl_se->flags = attr->sched_flags;
+ dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
+ dl_se->dl_throttled = 0;
+ dl_se->dl_new = 1;
+}
+
+/* Actually do priority change: must hold pi & rq lock. */
+static void __setscheduler(struct rq *rq, struct task_struct *p,
+ const struct sched_attr *attr)
+{
+ int policy = attr->sched_policy;
+
p->policy = policy;
- p->rt_priority = prio;
+
+ if (dl_policy(policy))
+ __setparam_dl(p, attr);
+ else if (rt_policy(policy))
+ p->rt_priority = attr->sched_priority;
+ else
+ p->static_prio = NICE_TO_PRIO(attr->sched_nice);
+
p->normal_prio = normal_prio(p);
- /* we are holding p->pi_lock already */
p->prio = rt_mutex_getprio(p);
- if (rt_prio(p->prio))
+
+ if (dl_prio(p->prio))
+ p->sched_class = &dl_sched_class;
+ else if (rt_prio(p->prio))
p->sched_class = &rt_sched_class;
else
p->sched_class = &fair_sched_class;
+
set_load_weight(p);
}
+static void
+__getparam_dl(struct task_struct *p, struct sched_attr *attr)
+{
+ struct sched_dl_entity *dl_se = &p->dl;
+
+ attr->sched_priority = p->rt_priority;
+ attr->sched_runtime = dl_se->dl_runtime;
+ attr->sched_deadline = dl_se->dl_deadline;
+ attr->sched_period = dl_se->dl_period;
+ attr->sched_flags = dl_se->flags;
+}
+
+/*
+ * This function validates the new parameters of a -deadline task.
+ * We ask for the deadline not being zero, and greater or equal
+ * than the runtime, as well as the period of being zero or
+ * greater than deadline. Furthermore, we have to be sure that
+ * user parameters are above the internal resolution (1us); we
+ * check sched_runtime only since it is always the smaller one.
+ */
+static bool
+__checkparam_dl(const struct sched_attr *attr)
+{
+ return attr && attr->sched_deadline != 0 &&
+ (attr->sched_period == 0 ||
+ (s64)(attr->sched_period - attr->sched_deadline) >= 0) &&
+ (s64)(attr->sched_deadline - attr->sched_runtime ) >= 0 &&
+ attr->sched_runtime >= (2 << (DL_SCALE - 1));
+}
+
/*
* check the target process has a UID that matches the current process's
*/
@@ -3020,10 +3252,12 @@
return match;
}
-static int __sched_setscheduler(struct task_struct *p, int policy,
- const struct sched_param *param, bool user)
+static int __sched_setscheduler(struct task_struct *p,
+ const struct sched_attr *attr,
+ bool user)
{
int retval, oldprio, oldpolicy = -1, on_rq, running;
+ int policy = attr->sched_policy;
unsigned long flags;
const struct sched_class *prev_class;
struct rq *rq;
@@ -3040,7 +3274,8 @@
reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
policy &= ~SCHED_RESET_ON_FORK;
- if (policy != SCHED_FIFO && policy != SCHED_RR &&
+ if (policy != SCHED_DEADLINE &&
+ policy != SCHED_FIFO && policy != SCHED_RR &&
policy != SCHED_NORMAL && policy != SCHED_BATCH &&
policy != SCHED_IDLE)
return -EINVAL;
@@ -3051,17 +3286,23 @@
* 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
* SCHED_BATCH and SCHED_IDLE is 0.
*/
- if (param->sched_priority < 0 ||
- (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
- (!p->mm && param->sched_priority > MAX_RT_PRIO-1))
+ if (attr->sched_priority < 0 ||
+ (p->mm && attr->sched_priority > MAX_USER_RT_PRIO-1) ||
+ (!p->mm && attr->sched_priority > MAX_RT_PRIO-1))
return -EINVAL;
- if (rt_policy(policy) != (param->sched_priority != 0))
+ if ((dl_policy(policy) && !__checkparam_dl(attr)) ||
+ (rt_policy(policy) != (attr->sched_priority != 0)))
return -EINVAL;
/*
* Allow unprivileged RT tasks to decrease priority:
*/
if (user && !capable(CAP_SYS_NICE)) {
+ if (fair_policy(policy)) {
+ if (!can_nice(p, attr->sched_nice))
+ return -EPERM;
+ }
+
if (rt_policy(policy)) {
unsigned long rlim_rtprio =
task_rlimit(p, RLIMIT_RTPRIO);
@@ -3071,8 +3312,8 @@
return -EPERM;
/* can't increase priority */
- if (param->sched_priority > p->rt_priority &&
- param->sched_priority > rlim_rtprio)
+ if (attr->sched_priority > p->rt_priority &&
+ attr->sched_priority > rlim_rtprio)
return -EPERM;
}
@@ -3120,14 +3361,21 @@
/*
* If not changing anything there's no need to proceed further:
*/
- if (unlikely(policy == p->policy && (!rt_policy(policy) ||
- param->sched_priority == p->rt_priority))) {
+ if (unlikely(policy == p->policy)) {
+ if (fair_policy(policy) && attr->sched_nice != TASK_NICE(p))
+ goto change;
+ if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
+ goto change;
+ if (dl_policy(policy))
+ goto change;
+
task_rq_unlock(rq, p, &flags);
return 0;
}
+change:
-#ifdef CONFIG_RT_GROUP_SCHED
if (user) {
+#ifdef CONFIG_RT_GROUP_SCHED
/*
* Do not allow realtime tasks into groups that have no runtime
* assigned.
@@ -3138,8 +3386,24 @@
task_rq_unlock(rq, p, &flags);
return -EPERM;
}
- }
#endif
+#ifdef CONFIG_SMP
+ if (dl_bandwidth_enabled() && dl_policy(policy)) {
+ cpumask_t *span = rq->rd->span;
+
+ /*
+ * Don't allow tasks with an affinity mask smaller than
+ * the entire root_domain to become SCHED_DEADLINE. We
+ * will also fail if there's no bandwidth available.
+ */
+ if (!cpumask_subset(span, &p->cpus_allowed) ||
+ rq->rd->dl_bw.bw == 0) {
+ task_rq_unlock(rq, p, &flags);
+ return -EPERM;
+ }
+ }
+#endif
+ }
/* recheck policy now with rq lock held */
if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
@@ -3147,6 +3411,17 @@
task_rq_unlock(rq, p, &flags);
goto recheck;
}
+
+ /*
+ * If setscheduling to SCHED_DEADLINE (or changing the parameters
+ * of a SCHED_DEADLINE task) we need to check if enough bandwidth
+ * is available.
+ */
+ if ((dl_policy(policy) || dl_task(p)) && dl_overflow(p, policy, attr)) {
+ task_rq_unlock(rq, p, &flags);
+ return -EBUSY;
+ }
+
on_rq = p->on_rq;
running = task_current(rq, p);
if (on_rq)
@@ -3158,7 +3433,7 @@
oldprio = p->prio;
prev_class = p->sched_class;
- __setscheduler(rq, p, policy, param->sched_priority);
+ __setscheduler(rq, p, attr);
if (running)
p->sched_class->set_curr_task(rq);
@@ -3186,10 +3461,20 @@
int sched_setscheduler(struct task_struct *p, int policy,
const struct sched_param *param)
{
- return __sched_setscheduler(p, policy, param, true);
+ struct sched_attr attr = {
+ .sched_policy = policy,
+ .sched_priority = param->sched_priority
+ };
+ return __sched_setscheduler(p, &attr, true);
}
EXPORT_SYMBOL_GPL(sched_setscheduler);
+int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
+{
+ return __sched_setscheduler(p, attr, true);
+}
+EXPORT_SYMBOL_GPL(sched_setattr);
+
/**
* sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
* @p: the task in question.
@@ -3206,7 +3491,11 @@
int sched_setscheduler_nocheck(struct task_struct *p, int policy,
const struct sched_param *param)
{
- return __sched_setscheduler(p, policy, param, false);
+ struct sched_attr attr = {
+ .sched_policy = policy,
+ .sched_priority = param->sched_priority
+ };
+ return __sched_setscheduler(p, &attr, false);
}
static int
@@ -3231,6 +3520,79 @@
return retval;
}
+/*
+ * Mimics kernel/events/core.c perf_copy_attr().
+ */
+static int sched_copy_attr(struct sched_attr __user *uattr,
+ struct sched_attr *attr)
+{
+ u32 size;
+ int ret;
+
+ if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0))
+ return -EFAULT;
+
+ /*
+ * zero the full structure, so that a short copy will be nice.
+ */
+ memset(attr, 0, sizeof(*attr));
+
+ ret = get_user(size, &uattr->size);
+ if (ret)
+ return ret;
+
+ if (size > PAGE_SIZE) /* silly large */
+ goto err_size;
+
+ if (!size) /* abi compat */
+ size = SCHED_ATTR_SIZE_VER0;
+
+ if (size < SCHED_ATTR_SIZE_VER0)
+ goto err_size;
+
+ /*
+ * If we're handed a bigger struct than we know of,
+ * ensure all the unknown bits are 0 - i.e. new
+ * user-space does not rely on any kernel feature
+ * extensions we dont know about yet.
+ */
+ if (size > sizeof(*attr)) {
+ unsigned char __user *addr;
+ unsigned char __user *end;
+ unsigned char val;
+
+ addr = (void __user *)uattr + sizeof(*attr);
+ end = (void __user *)uattr + size;
+
+ for (; addr < end; addr++) {
+ ret = get_user(val, addr);
+ if (ret)
+ return ret;
+ if (val)
+ goto err_size;
+ }
+ size = sizeof(*attr);
+ }
+
+ ret = copy_from_user(attr, uattr, size);
+ if (ret)
+ return -EFAULT;
+
+ /*
+ * XXX: do we want to be lenient like existing syscalls; or do we want
+ * to be strict and return an error on out-of-bounds values?
+ */
+ attr->sched_nice = clamp(attr->sched_nice, -20, 19);
+
+out:
+ return ret;
+
+err_size:
+ put_user(sizeof(*attr), &uattr->size);
+ ret = -E2BIG;
+ goto out;
+}
+
/**
* sys_sched_setscheduler - set/change the scheduler policy and RT priority
* @pid: the pid in question.
@@ -3262,6 +3624,33 @@
}
/**
+ * sys_sched_setattr - same as above, but with extended sched_attr
+ * @pid: the pid in question.
+ * @attr: structure containing the extended parameters.
+ */
+SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr)
+{
+ struct sched_attr attr;
+ struct task_struct *p;
+ int retval;
+
+ if (!uattr || pid < 0)
+ return -EINVAL;
+
+ if (sched_copy_attr(uattr, &attr))
+ return -EFAULT;
+
+ rcu_read_lock();
+ retval = -ESRCH;
+ p = find_process_by_pid(pid);
+ if (p != NULL)
+ retval = sched_setattr(p, &attr);
+ rcu_read_unlock();
+
+ return retval;
+}
+
+/**
* sys_sched_getscheduler - get the policy (scheduling class) of a thread
* @pid: the pid in question.
*
@@ -3316,6 +3705,10 @@
if (retval)
goto out_unlock;
+ if (task_has_dl_policy(p)) {
+ retval = -EINVAL;
+ goto out_unlock;
+ }
lp.sched_priority = p->rt_priority;
rcu_read_unlock();
@@ -3331,6 +3724,94 @@
return retval;
}
+static int sched_read_attr(struct sched_attr __user *uattr,
+ struct sched_attr *attr,
+ unsigned int usize)
+{
+ int ret;
+
+ if (!access_ok(VERIFY_WRITE, uattr, usize))
+ return -EFAULT;
+
+ /*
+ * If we're handed a smaller struct than we know of,
+ * ensure all the unknown bits are 0 - i.e. old
+ * user-space does not get uncomplete information.
+ */
+ if (usize < sizeof(*attr)) {
+ unsigned char *addr;
+ unsigned char *end;
+
+ addr = (void *)attr + usize;
+ end = (void *)attr + sizeof(*attr);
+
+ for (; addr < end; addr++) {
+ if (*addr)
+ goto err_size;
+ }
+
+ attr->size = usize;
+ }
+
+ ret = copy_to_user(uattr, attr, usize);
+ if (ret)
+ return -EFAULT;
+
+out:
+ return ret;
+
+err_size:
+ ret = -E2BIG;
+ goto out;
+}
+
+/**
+ * sys_sched_getattr - similar to sched_getparam, but with sched_attr
+ * @pid: the pid in question.
+ * @attr: structure containing the extended parameters.
+ * @size: sizeof(attr) for fwd/bwd comp.
+ */
+SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
+ unsigned int, size)
+{
+ struct sched_attr attr = {
+ .size = sizeof(struct sched_attr),
+ };
+ struct task_struct *p;
+ int retval;
+
+ if (!uattr || pid < 0 || size > PAGE_SIZE ||
+ size < SCHED_ATTR_SIZE_VER0)
+ return -EINVAL;
+
+ rcu_read_lock();
+ p = find_process_by_pid(pid);
+ retval = -ESRCH;
+ if (!p)
+ goto out_unlock;
+
+ retval = security_task_getscheduler(p);
+ if (retval)
+ goto out_unlock;
+
+ attr.sched_policy = p->policy;
+ if (task_has_dl_policy(p))
+ __getparam_dl(p, &attr);
+ else if (task_has_rt_policy(p))
+ attr.sched_priority = p->rt_priority;
+ else
+ attr.sched_nice = TASK_NICE(p);
+
+ rcu_read_unlock();
+
+ retval = sched_read_attr(uattr, &attr, size);
+ return retval;
+
+out_unlock:
+ rcu_read_unlock();
+ return retval;
+}
+
long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
{
cpumask_var_t cpus_allowed, new_mask;
@@ -3375,8 +3856,26 @@
if (retval)
goto out_unlock;
+
cpuset_cpus_allowed(p, cpus_allowed);
cpumask_and(new_mask, in_mask, cpus_allowed);
+
+ /*
+ * Since bandwidth control happens on root_domain basis,
+ * if admission test is enabled, we only admit -deadline
+ * tasks allowed to run on all the CPUs in the task's
+ * root_domain.
+ */
+#ifdef CONFIG_SMP
+ if (task_has_dl_policy(p)) {
+ const struct cpumask *span = task_rq(p)->rd->span;
+
+ if (dl_bandwidth_enabled() && !cpumask_subset(span, new_mask)) {
+ retval = -EBUSY;
+ goto out_unlock;
+ }
+ }
+#endif
again:
retval = set_cpus_allowed_ptr(p, new_mask);
@@ -3653,7 +4152,7 @@
}
double_rq_lock(rq, p_rq);
- while (task_rq(p) != p_rq) {
+ if (task_rq(p) != p_rq) {
double_rq_unlock(rq, p_rq);
goto again;
}
@@ -3742,6 +4241,7 @@
case SCHED_RR:
ret = MAX_USER_RT_PRIO-1;
break;
+ case SCHED_DEADLINE:
case SCHED_NORMAL:
case SCHED_BATCH:
case SCHED_IDLE:
@@ -3768,6 +4268,7 @@
case SCHED_RR:
ret = 1;
break;
+ case SCHED_DEADLINE:
case SCHED_NORMAL:
case SCHED_BATCH:
case SCHED_IDLE:
@@ -4514,13 +5015,31 @@
static int sched_cpu_inactive(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
+ unsigned long flags;
+ long cpu = (long)hcpu;
+
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_DOWN_PREPARE:
- set_cpu_active((long)hcpu, false);
+ set_cpu_active(cpu, false);
+
+ /* explicitly allow suspend */
+ if (!(action & CPU_TASKS_FROZEN)) {
+ struct dl_bw *dl_b = dl_bw_of(cpu);
+ bool overflow;
+ int cpus;
+
+ raw_spin_lock_irqsave(&dl_b->lock, flags);
+ cpus = dl_bw_cpus(cpu);
+ overflow = __dl_overflow(dl_b, cpus, 0, 0);
+ raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+ if (overflow)
+ return notifier_from_errno(-EBUSY);
+ }
return NOTIFY_OK;
- default:
- return NOTIFY_DONE;
}
+
+ return NOTIFY_DONE;
}
static int __init migration_init(void)
@@ -4739,6 +5258,8 @@
struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
cpupri_cleanup(&rd->cpupri);
+ cpudl_cleanup(&rd->cpudl);
+ free_cpumask_var(rd->dlo_mask);
free_cpumask_var(rd->rto_mask);
free_cpumask_var(rd->online);
free_cpumask_var(rd->span);
@@ -4790,8 +5311,14 @@
goto out;
if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
goto free_span;
- if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+ if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
goto free_online;
+ if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+ goto free_dlo_mask;
+
+ init_dl_bw(&rd->dl_bw);
+ if (cpudl_init(&rd->cpudl) != 0)
+ goto free_dlo_mask;
if (cpupri_init(&rd->cpupri) != 0)
goto free_rto_mask;
@@ -4799,6 +5326,8 @@
free_rto_mask:
free_cpumask_var(rd->rto_mask);
+free_dlo_mask:
+ free_cpumask_var(rd->dlo_mask);
free_online:
free_cpumask_var(rd->online);
free_span:
@@ -4902,6 +5431,7 @@
static void update_top_cache_domain(int cpu)
{
struct sched_domain *sd;
+ struct sched_domain *busy_sd = NULL;
int id = cpu;
int size = 1;
@@ -4909,9 +5439,9 @@
if (sd) {
id = cpumask_first(sched_domain_span(sd));
size = cpumask_weight(sched_domain_span(sd));
- sd = sd->parent; /* sd_busy */
+ busy_sd = sd->parent; /* sd_busy */
}
- rcu_assign_pointer(per_cpu(sd_busy, cpu), sd);
+ rcu_assign_pointer(per_cpu(sd_busy, cpu), busy_sd);
rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
per_cpu(sd_llc_size, cpu) = size;
@@ -5112,6 +5642,7 @@
* die on a /0 trap.
*/
sg->sgp->power = SCHED_POWER_SCALE * cpumask_weight(sg_span);
+ sg->sgp->power_orig = sg->sgp->power;
/*
* Make sure the first group of this domain contains the
@@ -6148,6 +6679,7 @@
free_cpumask_var(non_isolated_cpus);
init_sched_rt_class();
+ init_sched_dl_class();
}
#else
void __init sched_init_smp(void)
@@ -6217,13 +6749,15 @@
#endif /* CONFIG_CPUMASK_OFFSTACK */
}
+ init_rt_bandwidth(&def_rt_bandwidth,
+ global_rt_period(), global_rt_runtime());
+ init_dl_bandwidth(&def_dl_bandwidth,
+ global_rt_period(), global_rt_runtime());
+
#ifdef CONFIG_SMP
init_defrootdomain();
#endif
- init_rt_bandwidth(&def_rt_bandwidth,
- global_rt_period(), global_rt_runtime());
-
#ifdef CONFIG_RT_GROUP_SCHED
init_rt_bandwidth(&root_task_group.rt_bandwidth,
global_rt_period(), global_rt_runtime());
@@ -6247,6 +6781,7 @@
rq->calc_load_update = jiffies + LOAD_FREQ;
init_cfs_rq(&rq->cfs);
init_rt_rq(&rq->rt, rq);
+ init_dl_rq(&rq->dl, rq);
#ifdef CONFIG_FAIR_GROUP_SCHED
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
@@ -6318,10 +6853,6 @@
INIT_HLIST_HEAD(&init_task.preempt_notifiers);
#endif
-#ifdef CONFIG_RT_MUTEXES
- plist_head_init(&init_task.pi_waiters);
-#endif
-
/*
* The boot idle thread does lazy MMU switching as well:
*/
@@ -6395,13 +6926,16 @@
static void normalize_task(struct rq *rq, struct task_struct *p)
{
const struct sched_class *prev_class = p->sched_class;
+ struct sched_attr attr = {
+ .sched_policy = SCHED_NORMAL,
+ };
int old_prio = p->prio;
int on_rq;
on_rq = p->on_rq;
if (on_rq)
dequeue_task(rq, p, 0);
- __setscheduler(rq, p, SCHED_NORMAL, 0);
+ __setscheduler(rq, p, &attr);
if (on_rq) {
enqueue_task(rq, p, 0);
resched_task(rq->curr);
@@ -6431,7 +6965,7 @@
p->se.statistics.block_start = 0;
#endif
- if (!rt_task(p)) {
+ if (!dl_task(p) && !rt_task(p)) {
/*
* Renice negative nice level userspace
* tasks back to 0:
@@ -6626,16 +7160,6 @@
}
#endif /* CONFIG_CGROUP_SCHED */
-#if defined(CONFIG_RT_GROUP_SCHED) || defined(CONFIG_CFS_BANDWIDTH)
-static unsigned long to_ratio(u64 period, u64 runtime)
-{
- if (runtime == RUNTIME_INF)
- return 1ULL << 20;
-
- return div64_u64(runtime << 20, period);
-}
-#endif
-
#ifdef CONFIG_RT_GROUP_SCHED
/*
* Ensure that the real time constraints are schedulable.
@@ -6809,24 +7333,13 @@
do_div(rt_period_us, NSEC_PER_USEC);
return rt_period_us;
}
+#endif /* CONFIG_RT_GROUP_SCHED */
+#ifdef CONFIG_RT_GROUP_SCHED
static int sched_rt_global_constraints(void)
{
- u64 runtime, period;
int ret = 0;
- if (sysctl_sched_rt_period <= 0)
- return -EINVAL;
-
- runtime = global_rt_runtime();
- period = global_rt_period();
-
- /*
- * Sanity check on the sysctl variables.
- */
- if (runtime > period && runtime != RUNTIME_INF)
- return -EINVAL;
-
mutex_lock(&rt_constraints_mutex);
read_lock(&tasklist_lock);
ret = __rt_schedulable(NULL, 0, 0);
@@ -6849,17 +7362,7 @@
static int sched_rt_global_constraints(void)
{
unsigned long flags;
- int i;
-
- if (sysctl_sched_rt_period <= 0)
- return -EINVAL;
-
- /*
- * There's always some RT tasks in the root group
- * -- migration, kstopmachine etc..
- */
- if (sysctl_sched_rt_runtime == 0)
- return -EBUSY;
+ int i, ret = 0;
raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
for_each_possible_cpu(i) {
@@ -6871,10 +7374,121 @@
}
raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
- return 0;
+ return ret;
}
#endif /* CONFIG_RT_GROUP_SCHED */
+static int sched_dl_global_constraints(void)
+{
+ u64 runtime = global_rt_runtime();
+ u64 period = global_rt_period();
+ u64 new_bw = to_ratio(period, runtime);
+ int cpu, ret = 0;
+
+ /*
+ * Here we want to check the bandwidth not being set to some
+ * value smaller than the currently allocated bandwidth in
+ * any of the root_domains.
+ *
+ * FIXME: Cycling on all the CPUs is overdoing, but simpler than
+ * cycling on root_domains... Discussion on different/better
+ * solutions is welcome!
+ */
+ for_each_possible_cpu(cpu) {
+ struct dl_bw *dl_b = dl_bw_of(cpu);
+
+ raw_spin_lock(&dl_b->lock);
+ if (new_bw < dl_b->total_bw)
+ ret = -EBUSY;
+ raw_spin_unlock(&dl_b->lock);
+
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+static void sched_dl_do_global(void)
+{
+ u64 new_bw = -1;
+ int cpu;
+
+ def_dl_bandwidth.dl_period = global_rt_period();
+ def_dl_bandwidth.dl_runtime = global_rt_runtime();
+
+ if (global_rt_runtime() != RUNTIME_INF)
+ new_bw = to_ratio(global_rt_period(), global_rt_runtime());
+
+ /*
+ * FIXME: As above...
+ */
+ for_each_possible_cpu(cpu) {
+ struct dl_bw *dl_b = dl_bw_of(cpu);
+
+ raw_spin_lock(&dl_b->lock);
+ dl_b->bw = new_bw;
+ raw_spin_unlock(&dl_b->lock);
+ }
+}
+
+static int sched_rt_global_validate(void)
+{
+ if (sysctl_sched_rt_period <= 0)
+ return -EINVAL;
+
+ if (sysctl_sched_rt_runtime > sysctl_sched_rt_period)
+ return -EINVAL;
+
+ return 0;
+}
+
+static void sched_rt_do_global(void)
+{
+ def_rt_bandwidth.rt_runtime = global_rt_runtime();
+ def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
+}
+
+int sched_rt_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int old_period, old_runtime;
+ static DEFINE_MUTEX(mutex);
+ int ret;
+
+ mutex_lock(&mutex);
+ old_period = sysctl_sched_rt_period;
+ old_runtime = sysctl_sched_rt_runtime;
+
+ ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+ if (!ret && write) {
+ ret = sched_rt_global_validate();
+ if (ret)
+ goto undo;
+
+ ret = sched_rt_global_constraints();
+ if (ret)
+ goto undo;
+
+ ret = sched_dl_global_constraints();
+ if (ret)
+ goto undo;
+
+ sched_rt_do_global();
+ sched_dl_do_global();
+ }
+ if (0) {
+undo:
+ sysctl_sched_rt_period = old_period;
+ sysctl_sched_rt_runtime = old_runtime;
+ }
+ mutex_unlock(&mutex);
+
+ return ret;
+}
+
int sched_rr_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
@@ -6894,36 +7508,6 @@
return ret;
}
-int sched_rt_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos)
-{
- int ret;
- int old_period, old_runtime;
- static DEFINE_MUTEX(mutex);
-
- mutex_lock(&mutex);
- old_period = sysctl_sched_rt_period;
- old_runtime = sysctl_sched_rt_runtime;
-
- ret = proc_dointvec(table, write, buffer, lenp, ppos);
-
- if (!ret && write) {
- ret = sched_rt_global_constraints();
- if (ret) {
- sysctl_sched_rt_period = old_period;
- sysctl_sched_rt_runtime = old_runtime;
- } else {
- def_rt_bandwidth.rt_runtime = global_rt_runtime();
- def_rt_bandwidth.rt_period =
- ns_to_ktime(global_rt_period());
- }
- }
- mutex_unlock(&mutex);
-
- return ret;
-}
-
#ifdef CONFIG_CGROUP_SCHED
static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
new file mode 100644
index 0000000..3bcade5
--- /dev/null
+++ b/kernel/sched/cpudeadline.c
@@ -0,0 +1,216 @@
+/*
+ * kernel/sched/cpudl.c
+ *
+ * Global CPU deadline management
+ *
+ * Author: Juri Lelli <j.lelli@sssup.it>
+ *
+ * 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
+ * of the License.
+ */
+
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include "cpudeadline.h"
+
+static inline int parent(int i)
+{
+ return (i - 1) >> 1;
+}
+
+static inline int left_child(int i)
+{
+ return (i << 1) + 1;
+}
+
+static inline int right_child(int i)
+{
+ return (i << 1) + 2;
+}
+
+static inline int dl_time_before(u64 a, u64 b)
+{
+ return (s64)(a - b) < 0;
+}
+
+void cpudl_exchange(struct cpudl *cp, int a, int b)
+{
+ int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu;
+
+ swap(cp->elements[a], cp->elements[b]);
+ swap(cp->cpu_to_idx[cpu_a], cp->cpu_to_idx[cpu_b]);
+}
+
+void cpudl_heapify(struct cpudl *cp, int idx)
+{
+ int l, r, largest;
+
+ /* adapted from lib/prio_heap.c */
+ while(1) {
+ l = left_child(idx);
+ r = right_child(idx);
+ largest = idx;
+
+ if ((l < cp->size) && dl_time_before(cp->elements[idx].dl,
+ cp->elements[l].dl))
+ largest = l;
+ if ((r < cp->size) && dl_time_before(cp->elements[largest].dl,
+ cp->elements[r].dl))
+ largest = r;
+ if (largest == idx)
+ break;
+
+ /* Push idx down the heap one level and bump one up */
+ cpudl_exchange(cp, largest, idx);
+ idx = largest;
+ }
+}
+
+void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
+{
+ WARN_ON(idx > num_present_cpus() || idx == IDX_INVALID);
+
+ if (dl_time_before(new_dl, cp->elements[idx].dl)) {
+ cp->elements[idx].dl = new_dl;
+ cpudl_heapify(cp, idx);
+ } else {
+ cp->elements[idx].dl = new_dl;
+ while (idx > 0 && dl_time_before(cp->elements[parent(idx)].dl,
+ cp->elements[idx].dl)) {
+ cpudl_exchange(cp, idx, parent(idx));
+ idx = parent(idx);
+ }
+ }
+}
+
+static inline int cpudl_maximum(struct cpudl *cp)
+{
+ return cp->elements[0].cpu;
+}
+
+/*
+ * cpudl_find - find the best (later-dl) CPU in the system
+ * @cp: the cpudl max-heap context
+ * @p: the task
+ * @later_mask: a mask to fill in with the selected CPUs (or NULL)
+ *
+ * Returns: int - best CPU (heap maximum if suitable)
+ */
+int cpudl_find(struct cpudl *cp, struct task_struct *p,
+ struct cpumask *later_mask)
+{
+ int best_cpu = -1;
+ const struct sched_dl_entity *dl_se = &p->dl;
+
+ if (later_mask && cpumask_and(later_mask, cp->free_cpus,
+ &p->cpus_allowed) && cpumask_and(later_mask,
+ later_mask, cpu_active_mask)) {
+ best_cpu = cpumask_any(later_mask);
+ goto out;
+ } else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
+ dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
+ best_cpu = cpudl_maximum(cp);
+ if (later_mask)
+ cpumask_set_cpu(best_cpu, later_mask);
+ }
+
+out:
+ WARN_ON(best_cpu > num_present_cpus() && best_cpu != -1);
+
+ return best_cpu;
+}
+
+/*
+ * cpudl_set - update the cpudl max-heap
+ * @cp: the cpudl max-heap context
+ * @cpu: the target cpu
+ * @dl: the new earliest deadline for this cpu
+ *
+ * Notes: assumes cpu_rq(cpu)->lock is locked
+ *
+ * Returns: (void)
+ */
+void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
+{
+ int old_idx, new_cpu;
+ unsigned long flags;
+
+ WARN_ON(cpu > num_present_cpus());
+
+ raw_spin_lock_irqsave(&cp->lock, flags);
+ old_idx = cp->cpu_to_idx[cpu];
+ if (!is_valid) {
+ /* remove item */
+ if (old_idx == IDX_INVALID) {
+ /*
+ * Nothing to remove if old_idx was invalid.
+ * This could happen if a rq_offline_dl is
+ * called for a CPU without -dl tasks running.
+ */
+ goto out;
+ }
+ new_cpu = cp->elements[cp->size - 1].cpu;
+ cp->elements[old_idx].dl = cp->elements[cp->size - 1].dl;
+ cp->elements[old_idx].cpu = new_cpu;
+ cp->size--;
+ cp->cpu_to_idx[new_cpu] = old_idx;
+ cp->cpu_to_idx[cpu] = IDX_INVALID;
+ while (old_idx > 0 && dl_time_before(
+ cp->elements[parent(old_idx)].dl,
+ cp->elements[old_idx].dl)) {
+ cpudl_exchange(cp, old_idx, parent(old_idx));
+ old_idx = parent(old_idx);
+ }
+ cpumask_set_cpu(cpu, cp->free_cpus);
+ cpudl_heapify(cp, old_idx);
+
+ goto out;
+ }
+
+ if (old_idx == IDX_INVALID) {
+ cp->size++;
+ cp->elements[cp->size - 1].dl = 0;
+ cp->elements[cp->size - 1].cpu = cpu;
+ cp->cpu_to_idx[cpu] = cp->size - 1;
+ cpudl_change_key(cp, cp->size - 1, dl);
+ cpumask_clear_cpu(cpu, cp->free_cpus);
+ } else {
+ cpudl_change_key(cp, old_idx, dl);
+ }
+
+out:
+ raw_spin_unlock_irqrestore(&cp->lock, flags);
+}
+
+/*
+ * cpudl_init - initialize the cpudl structure
+ * @cp: the cpudl max-heap context
+ */
+int cpudl_init(struct cpudl *cp)
+{
+ int i;
+
+ memset(cp, 0, sizeof(*cp));
+ raw_spin_lock_init(&cp->lock);
+ cp->size = 0;
+ for (i = 0; i < NR_CPUS; i++)
+ cp->cpu_to_idx[i] = IDX_INVALID;
+ if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL))
+ return -ENOMEM;
+ cpumask_setall(cp->free_cpus);
+
+ return 0;
+}
+
+/*
+ * cpudl_cleanup - clean up the cpudl structure
+ * @cp: the cpudl max-heap context
+ */
+void cpudl_cleanup(struct cpudl *cp)
+{
+ /*
+ * nothing to do for the moment
+ */
+}
diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h
new file mode 100644
index 0000000..a202789
--- /dev/null
+++ b/kernel/sched/cpudeadline.h
@@ -0,0 +1,33 @@
+#ifndef _LINUX_CPUDL_H
+#define _LINUX_CPUDL_H
+
+#include <linux/sched.h>
+
+#define IDX_INVALID -1
+
+struct array_item {
+ u64 dl;
+ int cpu;
+};
+
+struct cpudl {
+ raw_spinlock_t lock;
+ int size;
+ int cpu_to_idx[NR_CPUS];
+ struct array_item elements[NR_CPUS];
+ cpumask_var_t free_cpus;
+};
+
+
+#ifdef CONFIG_SMP
+int cpudl_find(struct cpudl *cp, struct task_struct *p,
+ struct cpumask *later_mask);
+void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid);
+int cpudl_init(struct cpudl *cp);
+void cpudl_cleanup(struct cpudl *cp);
+#else
+#define cpudl_set(cp, cpu, dl) do { } while (0)
+#define cpudl_init() do { } while (0)
+#endif /* CONFIG_SMP */
+
+#endif /* _LINUX_CPUDL_H */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
new file mode 100644
index 0000000..ee25361
--- /dev/null
+++ b/kernel/sched/deadline.c
@@ -0,0 +1,1641 @@
+/*
+ * Deadline Scheduling Class (SCHED_DEADLINE)
+ *
+ * Earliest Deadline First (EDF) + Constant Bandwidth Server (CBS).
+ *
+ * Tasks that periodically executes their instances for less than their
+ * runtime won't miss any of their deadlines.
+ * Tasks that are not periodic or sporadic or that tries to execute more
+ * than their reserved bandwidth will be slowed down (and may potentially
+ * miss some of their deadlines), and won't affect any other task.
+ *
+ * Copyright (C) 2012 Dario Faggioli <raistlin@linux.it>,
+ * Juri Lelli <juri.lelli@gmail.com>,
+ * Michael Trimarchi <michael@amarulasolutions.com>,
+ * Fabio Checconi <fchecconi@gmail.com>
+ */
+#include "sched.h"
+
+#include <linux/slab.h>
+
+struct dl_bandwidth def_dl_bandwidth;
+
+static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
+{
+ return container_of(dl_se, struct task_struct, dl);
+}
+
+static inline struct rq *rq_of_dl_rq(struct dl_rq *dl_rq)
+{
+ return container_of(dl_rq, struct rq, dl);
+}
+
+static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se)
+{
+ struct task_struct *p = dl_task_of(dl_se);
+ struct rq *rq = task_rq(p);
+
+ return &rq->dl;
+}
+
+static inline int on_dl_rq(struct sched_dl_entity *dl_se)
+{
+ return !RB_EMPTY_NODE(&dl_se->rb_node);
+}
+
+static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
+{
+ struct sched_dl_entity *dl_se = &p->dl;
+
+ return dl_rq->rb_leftmost == &dl_se->rb_node;
+}
+
+void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime)
+{
+ raw_spin_lock_init(&dl_b->dl_runtime_lock);
+ dl_b->dl_period = period;
+ dl_b->dl_runtime = runtime;
+}
+
+extern unsigned long to_ratio(u64 period, u64 runtime);
+
+void init_dl_bw(struct dl_bw *dl_b)
+{
+ raw_spin_lock_init(&dl_b->lock);
+ raw_spin_lock(&def_dl_bandwidth.dl_runtime_lock);
+ if (global_rt_runtime() == RUNTIME_INF)
+ dl_b->bw = -1;
+ else
+ dl_b->bw = to_ratio(global_rt_period(), global_rt_runtime());
+ raw_spin_unlock(&def_dl_bandwidth.dl_runtime_lock);
+ dl_b->total_bw = 0;
+}
+
+void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq)
+{
+ dl_rq->rb_root = RB_ROOT;
+
+#ifdef CONFIG_SMP
+ /* zero means no -deadline tasks */
+ dl_rq->earliest_dl.curr = dl_rq->earliest_dl.next = 0;
+
+ dl_rq->dl_nr_migratory = 0;
+ dl_rq->overloaded = 0;
+ dl_rq->pushable_dl_tasks_root = RB_ROOT;
+#else
+ init_dl_bw(&dl_rq->dl_bw);
+#endif
+}
+
+#ifdef CONFIG_SMP
+
+static inline int dl_overloaded(struct rq *rq)
+{
+ return atomic_read(&rq->rd->dlo_count);
+}
+
+static inline void dl_set_overload(struct rq *rq)
+{
+ if (!rq->online)
+ return;
+
+ cpumask_set_cpu(rq->cpu, rq->rd->dlo_mask);
+ /*
+ * Must be visible before the overload count is
+ * set (as in sched_rt.c).
+ *
+ * Matched by the barrier in pull_dl_task().
+ */
+ smp_wmb();
+ atomic_inc(&rq->rd->dlo_count);
+}
+
+static inline void dl_clear_overload(struct rq *rq)
+{
+ if (!rq->online)
+ return;
+
+ atomic_dec(&rq->rd->dlo_count);
+ cpumask_clear_cpu(rq->cpu, rq->rd->dlo_mask);
+}
+
+static void update_dl_migration(struct dl_rq *dl_rq)
+{
+ if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_total > 1) {
+ if (!dl_rq->overloaded) {
+ dl_set_overload(rq_of_dl_rq(dl_rq));
+ dl_rq->overloaded = 1;
+ }
+ } else if (dl_rq->overloaded) {
+ dl_clear_overload(rq_of_dl_rq(dl_rq));
+ dl_rq->overloaded = 0;
+ }
+}
+
+static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+ struct task_struct *p = dl_task_of(dl_se);
+ dl_rq = &rq_of_dl_rq(dl_rq)->dl;
+
+ dl_rq->dl_nr_total++;
+ if (p->nr_cpus_allowed > 1)
+ dl_rq->dl_nr_migratory++;
+
+ update_dl_migration(dl_rq);
+}
+
+static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+ struct task_struct *p = dl_task_of(dl_se);
+ dl_rq = &rq_of_dl_rq(dl_rq)->dl;
+
+ dl_rq->dl_nr_total--;
+ if (p->nr_cpus_allowed > 1)
+ dl_rq->dl_nr_migratory--;
+
+ update_dl_migration(dl_rq);
+}
+
+/*
+ * The list of pushable -deadline task is not a plist, like in
+ * sched_rt.c, it is an rb-tree with tasks ordered by deadline.
+ */
+static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+ struct dl_rq *dl_rq = &rq->dl;
+ struct rb_node **link = &dl_rq->pushable_dl_tasks_root.rb_node;
+ struct rb_node *parent = NULL;
+ struct task_struct *entry;
+ int leftmost = 1;
+
+ BUG_ON(!RB_EMPTY_NODE(&p->pushable_dl_tasks));
+
+ while (*link) {
+ parent = *link;
+ entry = rb_entry(parent, struct task_struct,
+ pushable_dl_tasks);
+ if (dl_entity_preempt(&p->dl, &entry->dl))
+ link = &parent->rb_left;
+ else {
+ link = &parent->rb_right;
+ leftmost = 0;
+ }
+ }
+
+ if (leftmost)
+ dl_rq->pushable_dl_tasks_leftmost = &p->pushable_dl_tasks;
+
+ rb_link_node(&p->pushable_dl_tasks, parent, link);
+ rb_insert_color(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
+}
+
+static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+ struct dl_rq *dl_rq = &rq->dl;
+
+ if (RB_EMPTY_NODE(&p->pushable_dl_tasks))
+ return;
+
+ if (dl_rq->pushable_dl_tasks_leftmost == &p->pushable_dl_tasks) {
+ struct rb_node *next_node;
+
+ next_node = rb_next(&p->pushable_dl_tasks);
+ dl_rq->pushable_dl_tasks_leftmost = next_node;
+ }
+
+ rb_erase(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
+ RB_CLEAR_NODE(&p->pushable_dl_tasks);
+}
+
+static inline int has_pushable_dl_tasks(struct rq *rq)
+{
+ return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root);
+}
+
+static int push_dl_task(struct rq *rq);
+
+#else
+
+static inline
+void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline
+void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline
+void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+}
+
+static inline
+void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+}
+
+#endif /* CONFIG_SMP */
+
+static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
+static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags);
+static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
+ int flags);
+
+/*
+ * We are being explicitly informed that a new instance is starting,
+ * and this means that:
+ * - the absolute deadline of the entity has to be placed at
+ * current time + relative deadline;
+ * - the runtime of the entity has to be set to the maximum value.
+ *
+ * The capability of specifying such event is useful whenever a -deadline
+ * entity wants to (try to!) synchronize its behaviour with the scheduler's
+ * one, and to (try to!) reconcile itself with its own scheduling
+ * parameters.
+ */
+static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+
+ WARN_ON(!dl_se->dl_new || dl_se->dl_throttled);
+
+ /*
+ * We use the regular wall clock time to set deadlines in the
+ * future; in fact, we must consider execution overheads (time
+ * spent on hardirq context, etc.).
+ */
+ dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
+ dl_se->dl_new = 0;
+}
+
+/*
+ * Pure Earliest Deadline First (EDF) scheduling does not deal with the
+ * possibility of a entity lasting more than what it declared, and thus
+ * exhausting its runtime.
+ *
+ * Here we are interested in making runtime overrun possible, but we do
+ * not want a entity which is misbehaving to affect the scheduling of all
+ * other entities.
+ * Therefore, a budgeting strategy called Constant Bandwidth Server (CBS)
+ * is used, in order to confine each entity within its own bandwidth.
+ *
+ * This function deals exactly with that, and ensures that when the runtime
+ * of a entity is replenished, its deadline is also postponed. That ensures
+ * the overrunning entity can't interfere with other entity in the system and
+ * can't make them miss their deadlines. Reasons why this kind of overruns
+ * could happen are, typically, a entity voluntarily trying to overcome its
+ * runtime, or it just underestimated it during sched_setscheduler_ex().
+ */
+static void replenish_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+
+ BUG_ON(pi_se->dl_runtime <= 0);
+
+ /*
+ * This could be the case for a !-dl task that is boosted.
+ * Just go with full inherited parameters.
+ */
+ if (dl_se->dl_deadline == 0) {
+ dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
+ }
+
+ /*
+ * We keep moving the deadline away until we get some
+ * available runtime for the entity. This ensures correct
+ * handling of situations where the runtime overrun is
+ * arbitrary large.
+ */
+ while (dl_se->runtime <= 0) {
+ dl_se->deadline += pi_se->dl_period;
+ dl_se->runtime += pi_se->dl_runtime;
+ }
+
+ /*
+ * At this point, the deadline really should be "in
+ * the future" with respect to rq->clock. If it's
+ * not, we are, for some reason, lagging too much!
+ * Anyway, after having warn userspace abut that,
+ * we still try to keep the things running by
+ * resetting the deadline and the budget of the
+ * entity.
+ */
+ if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
+ static bool lag_once = false;
+
+ if (!lag_once) {
+ lag_once = true;
+ printk_sched("sched: DL replenish lagged to much\n");
+ }
+ dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
+ }
+}
+
+/*
+ * Here we check if --at time t-- an entity (which is probably being
+ * [re]activated or, in general, enqueued) can use its remaining runtime
+ * and its current deadline _without_ exceeding the bandwidth it is
+ * assigned (function returns true if it can't). We are in fact applying
+ * one of the CBS rules: when a task wakes up, if the residual runtime
+ * over residual deadline fits within the allocated bandwidth, then we
+ * can keep the current (absolute) deadline and residual budget without
+ * disrupting the schedulability of the system. Otherwise, we should
+ * refill the runtime and set the deadline a period in the future,
+ * because keeping the current (absolute) deadline of the task would
+ * result in breaking guarantees promised to other tasks.
+ *
+ * This function returns true if:
+ *
+ * runtime / (deadline - t) > dl_runtime / dl_period ,
+ *
+ * IOW we can't recycle current parameters.
+ *
+ * Notice that the bandwidth check is done against the period. For
+ * task with deadline equal to period this is the same of using
+ * dl_deadline instead of dl_period in the equation above.
+ */
+static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se, u64 t)
+{
+ u64 left, right;
+
+ /*
+ * left and right are the two sides of the equation above,
+ * after a bit of shuffling to use multiplications instead
+ * of divisions.
+ *
+ * Note that none of the time values involved in the two
+ * multiplications are absolute: dl_deadline and dl_runtime
+ * are the relative deadline and the maximum runtime of each
+ * instance, runtime is the runtime left for the last instance
+ * and (deadline - t), since t is rq->clock, is the time left
+ * to the (absolute) deadline. Even if overflowing the u64 type
+ * is very unlikely to occur in both cases, here we scale down
+ * as we want to avoid that risk at all. Scaling down by 10
+ * means that we reduce granularity to 1us. We are fine with it,
+ * since this is only a true/false check and, anyway, thinking
+ * of anything below microseconds resolution is actually fiction
+ * (but still we want to give the user that illusion >;).
+ */
+ left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+ right = ((dl_se->deadline - t) >> DL_SCALE) *
+ (pi_se->dl_runtime >> DL_SCALE);
+
+ return dl_time_before(right, left);
+}
+
+/*
+ * When a -deadline entity is queued back on the runqueue, its runtime and
+ * deadline might need updating.
+ *
+ * The policy here is that we update the deadline of the entity only if:
+ * - the current deadline is in the past,
+ * - using the remaining runtime with the current deadline would make
+ * the entity exceed its bandwidth.
+ */
+static void update_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+
+ /*
+ * The arrival of a new instance needs special treatment, i.e.,
+ * the actual scheduling parameters have to be "renewed".
+ */
+ if (dl_se->dl_new) {
+ setup_new_dl_entity(dl_se, pi_se);
+ return;
+ }
+
+ if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
+ dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
+ dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+ dl_se->runtime = pi_se->dl_runtime;
+ }
+}
+
+/*
+ * If the entity depleted all its runtime, and if we want it to sleep
+ * while waiting for some new execution time to become available, we
+ * set the bandwidth enforcement timer to the replenishment instant
+ * and try to activate it.
+ *
+ * Notice that it is important for the caller to know if the timer
+ * actually started or not (i.e., the replenishment instant is in
+ * the future or in the past).
+ */
+static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+ ktime_t now, act;
+ ktime_t soft, hard;
+ unsigned long range;
+ s64 delta;
+
+ if (boosted)
+ return 0;
+ /*
+ * We want the timer to fire at the deadline, but considering
+ * that it is actually coming from rq->clock and not from
+ * hrtimer's time base reading.
+ */
+ act = ns_to_ktime(dl_se->deadline);
+ now = hrtimer_cb_get_time(&dl_se->dl_timer);
+ delta = ktime_to_ns(now) - rq_clock(rq);
+ act = ktime_add_ns(act, delta);
+
+ /*
+ * If the expiry time already passed, e.g., because the value
+ * chosen as the deadline is too small, don't even try to
+ * start the timer in the past!
+ */
+ if (ktime_us_delta(act, now) < 0)
+ return 0;
+
+ hrtimer_set_expires(&dl_se->dl_timer, act);
+
+ soft = hrtimer_get_softexpires(&dl_se->dl_timer);
+ hard = hrtimer_get_expires(&dl_se->dl_timer);
+ range = ktime_to_ns(ktime_sub(hard, soft));
+ __hrtimer_start_range_ns(&dl_se->dl_timer, soft,
+ range, HRTIMER_MODE_ABS, 0);
+
+ return hrtimer_active(&dl_se->dl_timer);
+}
+
+/*
+ * This is the bandwidth enforcement timer callback. If here, we know
+ * a task is not on its dl_rq, since the fact that the timer was running
+ * means the task is throttled and needs a runtime replenishment.
+ *
+ * However, what we actually do depends on the fact the task is active,
+ * (it is on its rq) or has been removed from there by a call to
+ * dequeue_task_dl(). In the former case we must issue the runtime
+ * replenishment and add the task back to the dl_rq; in the latter, we just
+ * do nothing but clearing dl_throttled, so that runtime and deadline
+ * updating (and the queueing back to dl_rq) will be done by the
+ * next call to enqueue_task_dl().
+ */
+static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
+{
+ struct sched_dl_entity *dl_se = container_of(timer,
+ struct sched_dl_entity,
+ dl_timer);
+ struct task_struct *p = dl_task_of(dl_se);
+ struct rq *rq = task_rq(p);
+ raw_spin_lock(&rq->lock);
+
+ /*
+ * We need to take care of a possible races here. In fact, the
+ * task might have changed its scheduling policy to something
+ * different from SCHED_DEADLINE or changed its reservation
+ * parameters (through sched_setscheduler()).
+ */
+ if (!dl_task(p) || dl_se->dl_new)
+ goto unlock;
+
+ sched_clock_tick();
+ update_rq_clock(rq);
+ dl_se->dl_throttled = 0;
+ if (p->on_rq) {
+ enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
+ if (task_has_dl_policy(rq->curr))
+ check_preempt_curr_dl(rq, p, 0);
+ else
+ resched_task(rq->curr);
+#ifdef CONFIG_SMP
+ /*
+ * Queueing this task back might have overloaded rq,
+ * check if we need to kick someone away.
+ */
+ if (has_pushable_dl_tasks(rq))
+ push_dl_task(rq);
+#endif
+ }
+unlock:
+ raw_spin_unlock(&rq->lock);
+
+ return HRTIMER_NORESTART;
+}
+
+void init_dl_task_timer(struct sched_dl_entity *dl_se)
+{
+ struct hrtimer *timer = &dl_se->dl_timer;
+
+ if (hrtimer_active(timer)) {
+ hrtimer_try_to_cancel(timer);
+ return;
+ }
+
+ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ timer->function = dl_task_timer;
+}
+
+static
+int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
+{
+ int dmiss = dl_time_before(dl_se->deadline, rq_clock(rq));
+ int rorun = dl_se->runtime <= 0;
+
+ if (!rorun && !dmiss)
+ return 0;
+
+ /*
+ * If we are beyond our current deadline and we are still
+ * executing, then we have already used some of the runtime of
+ * the next instance. Thus, if we do not account that, we are
+ * stealing bandwidth from the system at each deadline miss!
+ */
+ if (dmiss) {
+ dl_se->runtime = rorun ? dl_se->runtime : 0;
+ dl_se->runtime -= rq_clock(rq) - dl_se->deadline;
+ }
+
+ return 1;
+}
+
+/*
+ * Update the current task's runtime statistics (provided it is still
+ * a -deadline task and has not been removed from the dl_rq).
+ */
+static void update_curr_dl(struct rq *rq)
+{
+ struct task_struct *curr = rq->curr;
+ struct sched_dl_entity *dl_se = &curr->dl;
+ u64 delta_exec;
+
+ if (!dl_task(curr) || !on_dl_rq(dl_se))
+ return;
+
+ /*
+ * Consumed budget is computed considering the time as
+ * observed by schedulable tasks (excluding time spent
+ * in hardirq context, etc.). Deadlines are instead
+ * computed using hard walltime. This seems to be the more
+ * natural solution, but the full ramifications of this
+ * approach need further study.
+ */
+ delta_exec = rq_clock_task(rq) - curr->se.exec_start;
+ if (unlikely((s64)delta_exec < 0))
+ delta_exec = 0;
+
+ schedstat_set(curr->se.statistics.exec_max,
+ max(curr->se.statistics.exec_max, delta_exec));
+
+ curr->se.sum_exec_runtime += delta_exec;
+ account_group_exec_runtime(curr, delta_exec);
+
+ curr->se.exec_start = rq_clock_task(rq);
+ cpuacct_charge(curr, delta_exec);
+
+ sched_rt_avg_update(rq, delta_exec);
+
+ dl_se->runtime -= delta_exec;
+ if (dl_runtime_exceeded(rq, dl_se)) {
+ __dequeue_task_dl(rq, curr, 0);
+ if (likely(start_dl_timer(dl_se, curr->dl.dl_boosted)))
+ dl_se->dl_throttled = 1;
+ else
+ enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
+
+ if (!is_leftmost(curr, &rq->dl))
+ resched_task(curr);
+ }
+
+ /*
+ * Because -- for now -- we share the rt bandwidth, we need to
+ * account our runtime there too, otherwise actual rt tasks
+ * would be able to exceed the shared quota.
+ *
+ * Account to the root rt group for now.
+ *
+ * The solution we're working towards is having the RT groups scheduled
+ * using deadline servers -- however there's a few nasties to figure
+ * out before that can happen.
+ */
+ if (rt_bandwidth_enabled()) {
+ struct rt_rq *rt_rq = &rq->rt;
+
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
+ rt_rq->rt_time += delta_exec;
+ /*
+ * We'll let actual RT tasks worry about the overflow here, we
+ * have our own CBS to keep us inline -- see above.
+ */
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
+ }
+}
+
+#ifdef CONFIG_SMP
+
+static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu);
+
+static inline u64 next_deadline(struct rq *rq)
+{
+ struct task_struct *next = pick_next_earliest_dl_task(rq, rq->cpu);
+
+ if (next && dl_prio(next->prio))
+ return next->dl.deadline;
+ else
+ return 0;
+}
+
+static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
+{
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+
+ if (dl_rq->earliest_dl.curr == 0 ||
+ dl_time_before(deadline, dl_rq->earliest_dl.curr)) {
+ /*
+ * If the dl_rq had no -deadline tasks, or if the new task
+ * has shorter deadline than the current one on dl_rq, we
+ * know that the previous earliest becomes our next earliest,
+ * as the new task becomes the earliest itself.
+ */
+ dl_rq->earliest_dl.next = dl_rq->earliest_dl.curr;
+ dl_rq->earliest_dl.curr = deadline;
+ cpudl_set(&rq->rd->cpudl, rq->cpu, deadline, 1);
+ } else if (dl_rq->earliest_dl.next == 0 ||
+ dl_time_before(deadline, dl_rq->earliest_dl.next)) {
+ /*
+ * On the other hand, if the new -deadline task has a
+ * a later deadline than the earliest one on dl_rq, but
+ * it is earlier than the next (if any), we must
+ * recompute the next-earliest.
+ */
+ dl_rq->earliest_dl.next = next_deadline(rq);
+ }
+}
+
+static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
+{
+ struct rq *rq = rq_of_dl_rq(dl_rq);
+
+ /*
+ * Since we may have removed our earliest (and/or next earliest)
+ * task we must recompute them.
+ */
+ if (!dl_rq->dl_nr_running) {
+ dl_rq->earliest_dl.curr = 0;
+ dl_rq->earliest_dl.next = 0;
+ cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0);
+ } else {
+ struct rb_node *leftmost = dl_rq->rb_leftmost;
+ struct sched_dl_entity *entry;
+
+ entry = rb_entry(leftmost, struct sched_dl_entity, rb_node);
+ dl_rq->earliest_dl.curr = entry->deadline;
+ dl_rq->earliest_dl.next = next_deadline(rq);
+ cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline, 1);
+ }
+}
+
+#else
+
+static inline void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
+static inline void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
+
+#endif /* CONFIG_SMP */
+
+static inline
+void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+ int prio = dl_task_of(dl_se)->prio;
+ u64 deadline = dl_se->deadline;
+
+ WARN_ON(!dl_prio(prio));
+ dl_rq->dl_nr_running++;
+
+ inc_dl_deadline(dl_rq, deadline);
+ inc_dl_migration(dl_se, dl_rq);
+}
+
+static inline
+void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+ int prio = dl_task_of(dl_se)->prio;
+
+ WARN_ON(!dl_prio(prio));
+ WARN_ON(!dl_rq->dl_nr_running);
+ dl_rq->dl_nr_running--;
+
+ dec_dl_deadline(dl_rq, dl_se->deadline);
+ dec_dl_migration(dl_se, dl_rq);
+}
+
+static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+ struct rb_node **link = &dl_rq->rb_root.rb_node;
+ struct rb_node *parent = NULL;
+ struct sched_dl_entity *entry;
+ int leftmost = 1;
+
+ BUG_ON(!RB_EMPTY_NODE(&dl_se->rb_node));
+
+ while (*link) {
+ parent = *link;
+ entry = rb_entry(parent, struct sched_dl_entity, rb_node);
+ if (dl_time_before(dl_se->deadline, entry->deadline))
+ link = &parent->rb_left;
+ else {
+ link = &parent->rb_right;
+ leftmost = 0;
+ }
+ }
+
+ if (leftmost)
+ dl_rq->rb_leftmost = &dl_se->rb_node;
+
+ rb_link_node(&dl_se->rb_node, parent, link);
+ rb_insert_color(&dl_se->rb_node, &dl_rq->rb_root);
+
+ inc_dl_tasks(dl_se, dl_rq);
+}
+
+static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
+{
+ struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+
+ if (RB_EMPTY_NODE(&dl_se->rb_node))
+ return;
+
+ if (dl_rq->rb_leftmost == &dl_se->rb_node) {
+ struct rb_node *next_node;
+
+ next_node = rb_next(&dl_se->rb_node);
+ dl_rq->rb_leftmost = next_node;
+ }
+
+ rb_erase(&dl_se->rb_node, &dl_rq->rb_root);
+ RB_CLEAR_NODE(&dl_se->rb_node);
+
+ dec_dl_tasks(dl_se, dl_rq);
+}
+
+static void
+enqueue_dl_entity(struct sched_dl_entity *dl_se,
+ struct sched_dl_entity *pi_se, int flags)
+{
+ BUG_ON(on_dl_rq(dl_se));
+
+ /*
+ * If this is a wakeup or a new instance, the scheduling
+ * parameters of the task might need updating. Otherwise,
+ * we want a replenishment of its runtime.
+ */
+ if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH)
+ replenish_dl_entity(dl_se, pi_se);
+ else
+ update_dl_entity(dl_se, pi_se);
+
+ __enqueue_dl_entity(dl_se);
+}
+
+static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
+{
+ __dequeue_dl_entity(dl_se);
+}
+
+static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+{
+ struct task_struct *pi_task = rt_mutex_get_top_task(p);
+ struct sched_dl_entity *pi_se = &p->dl;
+
+ /*
+ * Use the scheduling parameters of the top pi-waiter
+ * task if we have one and its (relative) deadline is
+ * smaller than our one... OTW we keep our runtime and
+ * deadline.
+ */
+ if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio))
+ pi_se = &pi_task->dl;
+
+ /*
+ * If p is throttled, we do nothing. In fact, if it exhausted
+ * its budget it needs a replenishment and, since it now is on
+ * its rq, the bandwidth timer callback (which clearly has not
+ * run yet) will take care of this.
+ */
+ if (p->dl.dl_throttled)
+ return;
+
+ enqueue_dl_entity(&p->dl, pi_se, flags);
+
+ if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
+ enqueue_pushable_dl_task(rq, p);
+
+ inc_nr_running(rq);
+}
+
+static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+{
+ dequeue_dl_entity(&p->dl);
+ dequeue_pushable_dl_task(rq, p);
+}
+
+static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+{
+ update_curr_dl(rq);
+ __dequeue_task_dl(rq, p, flags);
+
+ dec_nr_running(rq);
+}
+
+/*
+ * Yield task semantic for -deadline tasks is:
+ *
+ * get off from the CPU until our next instance, with
+ * a new runtime. This is of little use now, since we
+ * don't have a bandwidth reclaiming mechanism. Anyway,
+ * bandwidth reclaiming is planned for the future, and
+ * yield_task_dl will indicate that some spare budget
+ * is available for other task instances to use it.
+ */
+static void yield_task_dl(struct rq *rq)
+{
+ struct task_struct *p = rq->curr;
+
+ /*
+ * We make the task go to sleep until its current deadline by
+ * forcing its runtime to zero. This way, update_curr_dl() stops
+ * it and the bandwidth timer will wake it up and will give it
+ * new scheduling parameters (thanks to dl_new=1).
+ */
+ if (p->dl.runtime > 0) {
+ rq->curr->dl.dl_new = 1;
+ p->dl.runtime = 0;
+ }
+ update_curr_dl(rq);
+}
+
+#ifdef CONFIG_SMP
+
+static int find_later_rq(struct task_struct *task);
+
+static int
+select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
+{
+ struct task_struct *curr;
+ struct rq *rq;
+
+ if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
+ goto out;
+
+ rq = cpu_rq(cpu);
+
+ rcu_read_lock();
+ curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+
+ /*
+ * If we are dealing with a -deadline task, we must
+ * decide where to wake it up.
+ * If it has a later deadline and the current task
+ * on this rq can't move (provided the waking task
+ * can!) we prefer to send it somewhere else. On the
+ * other hand, if it has a shorter deadline, we
+ * try to make it stay here, it might be important.
+ */
+ if (unlikely(dl_task(curr)) &&
+ (curr->nr_cpus_allowed < 2 ||
+ !dl_entity_preempt(&p->dl, &curr->dl)) &&
+ (p->nr_cpus_allowed > 1)) {
+ int target = find_later_rq(p);
+
+ if (target != -1)
+ cpu = target;
+ }
+ rcu_read_unlock();
+
+out:
+ return cpu;
+}
+
+static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
+{
+ /*
+ * Current can't be migrated, useless to reschedule,
+ * let's hope p can move out.
+ */
+ if (rq->curr->nr_cpus_allowed == 1 ||
+ cpudl_find(&rq->rd->cpudl, rq->curr, NULL) == -1)
+ return;
+
+ /*
+ * p is migratable, so let's not schedule it and
+ * see if it is pushed or pulled somewhere else.
+ */
+ if (p->nr_cpus_allowed != 1 &&
+ cpudl_find(&rq->rd->cpudl, p, NULL) != -1)
+ return;
+
+ resched_task(rq->curr);
+}
+
+#endif /* CONFIG_SMP */
+
+/*
+ * Only called when both the current and waking task are -deadline
+ * tasks.
+ */
+static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
+ int flags)
+{
+ if (dl_entity_preempt(&p->dl, &rq->curr->dl)) {
+ resched_task(rq->curr);
+ return;
+ }
+
+#ifdef CONFIG_SMP
+ /*
+ * In the unlikely case current and p have the same deadline
+ * let us try to decide what's the best thing to do...
+ */
+ if ((p->dl.deadline == rq->curr->dl.deadline) &&
+ !test_tsk_need_resched(rq->curr))
+ check_preempt_equal_dl(rq, p);
+#endif /* CONFIG_SMP */
+}
+
+#ifdef CONFIG_SCHED_HRTICK
+static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
+{
+ s64 delta = p->dl.dl_runtime - p->dl.runtime;
+
+ if (delta > 10000)
+ hrtick_start(rq, p->dl.runtime);
+}
+#endif
+
+static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
+ struct dl_rq *dl_rq)
+{
+ struct rb_node *left = dl_rq->rb_leftmost;
+
+ if (!left)
+ return NULL;
+
+ return rb_entry(left, struct sched_dl_entity, rb_node);
+}
+
+struct task_struct *pick_next_task_dl(struct rq *rq)
+{
+ struct sched_dl_entity *dl_se;
+ struct task_struct *p;
+ struct dl_rq *dl_rq;
+
+ dl_rq = &rq->dl;
+
+ if (unlikely(!dl_rq->dl_nr_running))
+ return NULL;
+
+ dl_se = pick_next_dl_entity(rq, dl_rq);
+ BUG_ON(!dl_se);
+
+ p = dl_task_of(dl_se);
+ p->se.exec_start = rq_clock_task(rq);
+
+ /* Running task will never be pushed. */
+ if (p)
+ dequeue_pushable_dl_task(rq, p);
+
+#ifdef CONFIG_SCHED_HRTICK
+ if (hrtick_enabled(rq))
+ start_hrtick_dl(rq, p);
+#endif
+
+#ifdef CONFIG_SMP
+ rq->post_schedule = has_pushable_dl_tasks(rq);
+#endif /* CONFIG_SMP */
+
+ return p;
+}
+
+static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
+{
+ update_curr_dl(rq);
+
+ if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
+ enqueue_pushable_dl_task(rq, p);
+}
+
+static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
+{
+ update_curr_dl(rq);
+
+#ifdef CONFIG_SCHED_HRTICK
+ if (hrtick_enabled(rq) && queued && p->dl.runtime > 0)
+ start_hrtick_dl(rq, p);
+#endif
+}
+
+static void task_fork_dl(struct task_struct *p)
+{
+ /*
+ * SCHED_DEADLINE tasks cannot fork and this is achieved through
+ * sched_fork()
+ */
+}
+
+static void task_dead_dl(struct task_struct *p)
+{
+ struct hrtimer *timer = &p->dl.dl_timer;
+ struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
+ /*
+ * Since we are TASK_DEAD we won't slip out of the domain!
+ */
+ raw_spin_lock_irq(&dl_b->lock);
+ dl_b->total_bw -= p->dl.dl_bw;
+ raw_spin_unlock_irq(&dl_b->lock);
+
+ hrtimer_cancel(timer);
+}
+
+static void set_curr_task_dl(struct rq *rq)
+{
+ struct task_struct *p = rq->curr;
+
+ p->se.exec_start = rq_clock_task(rq);
+
+ /* You can't push away the running task */
+ dequeue_pushable_dl_task(rq, p);
+}
+
+#ifdef CONFIG_SMP
+
+/* Only try algorithms three times */
+#define DL_MAX_TRIES 3
+
+static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
+{
+ if (!task_running(rq, p) &&
+ (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) &&
+ (p->nr_cpus_allowed > 1))
+ return 1;
+
+ return 0;
+}
+
+/* Returns the second earliest -deadline task, NULL otherwise */
+static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu)
+{
+ struct rb_node *next_node = rq->dl.rb_leftmost;
+ struct sched_dl_entity *dl_se;
+ struct task_struct *p = NULL;
+
+next_node:
+ next_node = rb_next(next_node);
+ if (next_node) {
+ dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node);
+ p = dl_task_of(dl_se);
+
+ if (pick_dl_task(rq, p, cpu))
+ return p;
+
+ goto next_node;
+ }
+
+ return NULL;
+}
+
+static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
+
+static int find_later_rq(struct task_struct *task)
+{
+ struct sched_domain *sd;
+ struct cpumask *later_mask = __get_cpu_var(local_cpu_mask_dl);
+ int this_cpu = smp_processor_id();
+ int best_cpu, cpu = task_cpu(task);
+
+ /* Make sure the mask is initialized first */
+ if (unlikely(!later_mask))
+ return -1;
+
+ if (task->nr_cpus_allowed == 1)
+ return -1;
+
+ best_cpu = cpudl_find(&task_rq(task)->rd->cpudl,
+ task, later_mask);
+ if (best_cpu == -1)
+ return -1;
+
+ /*
+ * If we are here, some target has been found,
+ * the most suitable of which is cached in best_cpu.
+ * This is, among the runqueues where the current tasks
+ * have later deadlines than the task's one, the rq
+ * with the latest possible one.
+ *
+ * Now we check how well this matches with task's
+ * affinity and system topology.
+ *
+ * The last cpu where the task run is our first
+ * guess, since it is most likely cache-hot there.
+ */
+ if (cpumask_test_cpu(cpu, later_mask))
+ return cpu;
+ /*
+ * Check if this_cpu is to be skipped (i.e., it is
+ * not in the mask) or not.
+ */
+ if (!cpumask_test_cpu(this_cpu, later_mask))
+ this_cpu = -1;
+
+ rcu_read_lock();
+ for_each_domain(cpu, sd) {
+ if (sd->flags & SD_WAKE_AFFINE) {
+
+ /*
+ * If possible, preempting this_cpu is
+ * cheaper than migrating.
+ */
+ if (this_cpu != -1 &&
+ cpumask_test_cpu(this_cpu, sched_domain_span(sd))) {
+ rcu_read_unlock();
+ return this_cpu;
+ }
+
+ /*
+ * Last chance: if best_cpu is valid and is
+ * in the mask, that becomes our choice.
+ */
+ if (best_cpu < nr_cpu_ids &&
+ cpumask_test_cpu(best_cpu, sched_domain_span(sd))) {
+ rcu_read_unlock();
+ return best_cpu;
+ }
+ }
+ }
+ rcu_read_unlock();
+
+ /*
+ * At this point, all our guesses failed, we just return
+ * 'something', and let the caller sort the things out.
+ */
+ if (this_cpu != -1)
+ return this_cpu;
+
+ cpu = cpumask_any(later_mask);
+ if (cpu < nr_cpu_ids)
+ return cpu;
+
+ return -1;
+}
+
+/* Locks the rq it finds */
+static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
+{
+ struct rq *later_rq = NULL;
+ int tries;
+ int cpu;
+
+ for (tries = 0; tries < DL_MAX_TRIES; tries++) {
+ cpu = find_later_rq(task);
+
+ if ((cpu == -1) || (cpu == rq->cpu))
+ break;
+
+ later_rq = cpu_rq(cpu);
+
+ /* Retry if something changed. */
+ if (double_lock_balance(rq, later_rq)) {
+ if (unlikely(task_rq(task) != rq ||
+ !cpumask_test_cpu(later_rq->cpu,
+ &task->cpus_allowed) ||
+ task_running(rq, task) || !task->on_rq)) {
+ double_unlock_balance(rq, later_rq);
+ later_rq = NULL;
+ break;
+ }
+ }
+
+ /*
+ * If the rq we found has no -deadline task, or
+ * its earliest one has a later deadline than our
+ * task, the rq is a good one.
+ */
+ if (!later_rq->dl.dl_nr_running ||
+ dl_time_before(task->dl.deadline,
+ later_rq->dl.earliest_dl.curr))
+ break;
+
+ /* Otherwise we try again. */
+ double_unlock_balance(rq, later_rq);
+ later_rq = NULL;
+ }
+
+ return later_rq;
+}
+
+static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
+{
+ struct task_struct *p;
+
+ if (!has_pushable_dl_tasks(rq))
+ return NULL;
+
+ p = rb_entry(rq->dl.pushable_dl_tasks_leftmost,
+ struct task_struct, pushable_dl_tasks);
+
+ BUG_ON(rq->cpu != task_cpu(p));
+ BUG_ON(task_current(rq, p));
+ BUG_ON(p->nr_cpus_allowed <= 1);
+
+ BUG_ON(!p->on_rq);
+ BUG_ON(!dl_task(p));
+
+ return p;
+}
+
+/*
+ * See if the non running -deadline tasks on this rq
+ * can be sent to some other CPU where they can preempt
+ * and start executing.
+ */
+static int push_dl_task(struct rq *rq)
+{
+ struct task_struct *next_task;
+ struct rq *later_rq;
+
+ if (!rq->dl.overloaded)
+ return 0;
+
+ next_task = pick_next_pushable_dl_task(rq);
+ if (!next_task)
+ return 0;
+
+retry:
+ if (unlikely(next_task == rq->curr)) {
+ WARN_ON(1);
+ return 0;
+ }
+
+ /*
+ * If next_task preempts rq->curr, and rq->curr
+ * can move away, it makes sense to just reschedule
+ * without going further in pushing next_task.
+ */
+ if (dl_task(rq->curr) &&
+ dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) &&
+ rq->curr->nr_cpus_allowed > 1) {
+ resched_task(rq->curr);
+ return 0;
+ }
+
+ /* We might release rq lock */
+ get_task_struct(next_task);
+
+ /* Will lock the rq it'll find */
+ later_rq = find_lock_later_rq(next_task, rq);
+ if (!later_rq) {
+ struct task_struct *task;
+
+ /*
+ * We must check all this again, since
+ * find_lock_later_rq releases rq->lock and it is
+ * then possible that next_task has migrated.
+ */
+ task = pick_next_pushable_dl_task(rq);
+ if (task_cpu(next_task) == rq->cpu && task == next_task) {
+ /*
+ * The task is still there. We don't try
+ * again, some other cpu will pull it when ready.
+ */
+ dequeue_pushable_dl_task(rq, next_task);
+ goto out;
+ }
+
+ if (!task)
+ /* No more tasks */
+ goto out;
+
+ put_task_struct(next_task);
+ next_task = task;
+ goto retry;
+ }
+
+ deactivate_task(rq, next_task, 0);
+ set_task_cpu(next_task, later_rq->cpu);
+ activate_task(later_rq, next_task, 0);
+
+ resched_task(later_rq->curr);
+
+ double_unlock_balance(rq, later_rq);
+
+out:
+ put_task_struct(next_task);
+
+ return 1;
+}
+
+static void push_dl_tasks(struct rq *rq)
+{
+ /* Terminates as it moves a -deadline task */
+ while (push_dl_task(rq))
+ ;
+}
+
+static int pull_dl_task(struct rq *this_rq)
+{
+ int this_cpu = this_rq->cpu, ret = 0, cpu;
+ struct task_struct *p;
+ struct rq *src_rq;
+ u64 dmin = LONG_MAX;
+
+ if (likely(!dl_overloaded(this_rq)))
+ return 0;
+
+ /*
+ * Match the barrier from dl_set_overloaded; this guarantees that if we
+ * see overloaded we must also see the dlo_mask bit.
+ */
+ smp_rmb();
+
+ for_each_cpu(cpu, this_rq->rd->dlo_mask) {
+ if (this_cpu == cpu)
+ continue;
+
+ src_rq = cpu_rq(cpu);
+
+ /*
+ * It looks racy, abd it is! However, as in sched_rt.c,
+ * we are fine with this.
+ */
+ if (this_rq->dl.dl_nr_running &&
+ dl_time_before(this_rq->dl.earliest_dl.curr,
+ src_rq->dl.earliest_dl.next))
+ continue;
+
+ /* Might drop this_rq->lock */
+ double_lock_balance(this_rq, src_rq);
+
+ /*
+ * If there are no more pullable tasks on the
+ * rq, we're done with it.
+ */
+ if (src_rq->dl.dl_nr_running <= 1)
+ goto skip;
+
+ p = pick_next_earliest_dl_task(src_rq, this_cpu);
+
+ /*
+ * We found a task to be pulled if:
+ * - it preempts our current (if there's one),
+ * - it will preempt the last one we pulled (if any).
+ */
+ if (p && dl_time_before(p->dl.deadline, dmin) &&
+ (!this_rq->dl.dl_nr_running ||
+ dl_time_before(p->dl.deadline,
+ this_rq->dl.earliest_dl.curr))) {
+ WARN_ON(p == src_rq->curr);
+ WARN_ON(!p->on_rq);
+
+ /*
+ * Then we pull iff p has actually an earlier
+ * deadline than the current task of its runqueue.
+ */
+ if (dl_time_before(p->dl.deadline,
+ src_rq->curr->dl.deadline))
+ goto skip;
+
+ ret = 1;
+
+ deactivate_task(src_rq, p, 0);
+ set_task_cpu(p, this_cpu);
+ activate_task(this_rq, p, 0);
+ dmin = p->dl.deadline;
+
+ /* Is there any other task even earlier? */
+ }
+skip:
+ double_unlock_balance(this_rq, src_rq);
+ }
+
+ return ret;
+}
+
+static void pre_schedule_dl(struct rq *rq, struct task_struct *prev)
+{
+ /* Try to pull other tasks here */
+ if (dl_task(prev))
+ pull_dl_task(rq);
+}
+
+static void post_schedule_dl(struct rq *rq)
+{
+ push_dl_tasks(rq);
+}
+
+/*
+ * Since the task is not running and a reschedule is not going to happen
+ * anytime soon on its runqueue, we try pushing it away now.
+ */
+static void task_woken_dl(struct rq *rq, struct task_struct *p)
+{
+ if (!task_running(rq, p) &&
+ !test_tsk_need_resched(rq->curr) &&
+ has_pushable_dl_tasks(rq) &&
+ p->nr_cpus_allowed > 1 &&
+ dl_task(rq->curr) &&
+ (rq->curr->nr_cpus_allowed < 2 ||
+ dl_entity_preempt(&rq->curr->dl, &p->dl))) {
+ push_dl_tasks(rq);
+ }
+}
+
+static void set_cpus_allowed_dl(struct task_struct *p,
+ const struct cpumask *new_mask)
+{
+ struct rq *rq;
+ int weight;
+
+ BUG_ON(!dl_task(p));
+
+ /*
+ * Update only if the task is actually running (i.e.,
+ * it is on the rq AND it is not throttled).
+ */
+ if (!on_dl_rq(&p->dl))
+ return;
+
+ weight = cpumask_weight(new_mask);
+
+ /*
+ * Only update if the process changes its state from whether it
+ * can migrate or not.
+ */
+ if ((p->nr_cpus_allowed > 1) == (weight > 1))
+ return;
+
+ rq = task_rq(p);
+
+ /*
+ * The process used to be able to migrate OR it can now migrate
+ */
+ if (weight <= 1) {
+ if (!task_current(rq, p))
+ dequeue_pushable_dl_task(rq, p);
+ BUG_ON(!rq->dl.dl_nr_migratory);
+ rq->dl.dl_nr_migratory--;
+ } else {
+ if (!task_current(rq, p))
+ enqueue_pushable_dl_task(rq, p);
+ rq->dl.dl_nr_migratory++;
+ }
+
+ update_dl_migration(&rq->dl);
+}
+
+/* Assumes rq->lock is held */
+static void rq_online_dl(struct rq *rq)
+{
+ if (rq->dl.overloaded)
+ dl_set_overload(rq);
+
+ if (rq->dl.dl_nr_running > 0)
+ cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr, 1);
+}
+
+/* Assumes rq->lock is held */
+static void rq_offline_dl(struct rq *rq)
+{
+ if (rq->dl.overloaded)
+ dl_clear_overload(rq);
+
+ cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0);
+}
+
+void init_sched_dl_class(void)
+{
+ unsigned int i;
+
+ for_each_possible_cpu(i)
+ zalloc_cpumask_var_node(&per_cpu(local_cpu_mask_dl, i),
+ GFP_KERNEL, cpu_to_node(i));
+}
+
+#endif /* CONFIG_SMP */
+
+static void switched_from_dl(struct rq *rq, struct task_struct *p)
+{
+ if (hrtimer_active(&p->dl.dl_timer) && !dl_policy(p->policy))
+ hrtimer_try_to_cancel(&p->dl.dl_timer);
+
+#ifdef CONFIG_SMP
+ /*
+ * Since this might be the only -deadline task on the rq,
+ * this is the right place to try to pull some other one
+ * from an overloaded cpu, if any.
+ */
+ if (!rq->dl.dl_nr_running)
+ pull_dl_task(rq);
+#endif
+}
+
+/*
+ * When switching to -deadline, we may overload the rq, then
+ * we try to push someone off, if possible.
+ */
+static void switched_to_dl(struct rq *rq, struct task_struct *p)
+{
+ int check_resched = 1;
+
+ /*
+ * If p is throttled, don't consider the possibility
+ * of preempting rq->curr, the check will be done right
+ * after its runtime will get replenished.
+ */
+ if (unlikely(p->dl.dl_throttled))
+ return;
+
+ if (p->on_rq || rq->curr != p) {
+#ifdef CONFIG_SMP
+ if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p))
+ /* Only reschedule if pushing failed */
+ check_resched = 0;
+#endif /* CONFIG_SMP */
+ if (check_resched && task_has_dl_policy(rq->curr))
+ check_preempt_curr_dl(rq, p, 0);
+ }
+}
+
+/*
+ * If the scheduling parameters of a -deadline task changed,
+ * a push or pull operation might be needed.
+ */
+static void prio_changed_dl(struct rq *rq, struct task_struct *p,
+ int oldprio)
+{
+ if (p->on_rq || rq->curr == p) {
+#ifdef CONFIG_SMP
+ /*
+ * This might be too much, but unfortunately
+ * we don't have the old deadline value, and
+ * we can't argue if the task is increasing
+ * or lowering its prio, so...
+ */
+ if (!rq->dl.overloaded)
+ pull_dl_task(rq);
+
+ /*
+ * If we now have a earlier deadline task than p,
+ * then reschedule, provided p is still on this
+ * runqueue.
+ */
+ if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline) &&
+ rq->curr == p)
+ resched_task(p);
+#else
+ /*
+ * Again, we don't know if p has a earlier
+ * or later deadline, so let's blindly set a
+ * (maybe not needed) rescheduling point.
+ */
+ resched_task(p);
+#endif /* CONFIG_SMP */
+ } else
+ switched_to_dl(rq, p);
+}
+
+const struct sched_class dl_sched_class = {
+ .next = &rt_sched_class,
+ .enqueue_task = enqueue_task_dl,
+ .dequeue_task = dequeue_task_dl,
+ .yield_task = yield_task_dl,
+
+ .check_preempt_curr = check_preempt_curr_dl,
+
+ .pick_next_task = pick_next_task_dl,
+ .put_prev_task = put_prev_task_dl,
+
+#ifdef CONFIG_SMP
+ .select_task_rq = select_task_rq_dl,
+ .set_cpus_allowed = set_cpus_allowed_dl,
+ .rq_online = rq_online_dl,
+ .rq_offline = rq_offline_dl,
+ .pre_schedule = pre_schedule_dl,
+ .post_schedule = post_schedule_dl,
+ .task_woken = task_woken_dl,
+#endif
+
+ .set_curr_task = set_curr_task_dl,
+ .task_tick = task_tick_dl,
+ .task_fork = task_fork_dl,
+ .task_dead = task_dead_dl,
+
+ .prio_changed = prio_changed_dl,
+ .switched_from = switched_from_dl,
+ .switched_to = switched_to_dl,
+};
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 5c34d18..dd52e7f 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -139,7 +139,7 @@
0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
#endif
#ifdef CONFIG_NUMA_BALANCING
- SEQ_printf(m, " %d", cpu_to_node(task_cpu(p)));
+ SEQ_printf(m, " %d", task_node(p));
#endif
#ifdef CONFIG_CGROUP_SCHED
SEQ_printf(m, " %s", task_group_path(task_group(p)));
@@ -371,7 +371,7 @@
PN(cpu_clk);
P(jiffies);
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
- P(sched_clock_stable);
+ P(sched_clock_stable());
#endif
#undef PN
#undef P
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fd773ad..b24b6cf 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -178,59 +178,61 @@
update_sysctl();
}
-#if BITS_PER_LONG == 32
-# define WMULT_CONST (~0UL)
-#else
-# define WMULT_CONST (1UL << 32)
-#endif
-
+#define WMULT_CONST (~0U)
#define WMULT_SHIFT 32
-/*
- * Shift right and round:
- */
-#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
-
-/*
- * delta *= weight / lw
- */
-static unsigned long
-calc_delta_mine(unsigned long delta_exec, unsigned long weight,
- struct load_weight *lw)
+static void __update_inv_weight(struct load_weight *lw)
{
- u64 tmp;
+ unsigned long w;
- /*
- * weight can be less than 2^SCHED_LOAD_RESOLUTION for task group sched
- * entities since MIN_SHARES = 2. Treat weight as 1 if less than
- * 2^SCHED_LOAD_RESOLUTION.
- */
- if (likely(weight > (1UL << SCHED_LOAD_RESOLUTION)))
- tmp = (u64)delta_exec * scale_load_down(weight);
+ if (likely(lw->inv_weight))
+ return;
+
+ w = scale_load_down(lw->weight);
+
+ if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST))
+ lw->inv_weight = 1;
+ else if (unlikely(!w))
+ lw->inv_weight = WMULT_CONST;
else
- tmp = (u64)delta_exec;
+ lw->inv_weight = WMULT_CONST / w;
+}
- if (!lw->inv_weight) {
- unsigned long w = scale_load_down(lw->weight);
+/*
+ * delta_exec * weight / lw.weight
+ * OR
+ * (delta_exec * (weight * lw->inv_weight)) >> WMULT_SHIFT
+ *
+ * Either weight := NICE_0_LOAD and lw \e prio_to_wmult[], in which case
+ * we're guaranteed shift stays positive because inv_weight is guaranteed to
+ * fit 32 bits, and NICE_0_LOAD gives another 10 bits; therefore shift >= 22.
+ *
+ * Or, weight =< lw.weight (because lw.weight is the runqueue weight), thus
+ * weight/lw.weight <= 1, and therefore our shift will also be positive.
+ */
+static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw)
+{
+ u64 fact = scale_load_down(weight);
+ int shift = WMULT_SHIFT;
- if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST))
- lw->inv_weight = 1;
- else if (unlikely(!w))
- lw->inv_weight = WMULT_CONST;
- else
- lw->inv_weight = WMULT_CONST / w;
+ __update_inv_weight(lw);
+
+ if (unlikely(fact >> 32)) {
+ while (fact >> 32) {
+ fact >>= 1;
+ shift--;
+ }
}
- /*
- * Check whether we'd overflow the 64-bit multiplication:
- */
- if (unlikely(tmp > WMULT_CONST))
- tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
- WMULT_SHIFT/2);
- else
- tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT);
+ /* hint to use a 32x32->64 mul */
+ fact = (u64)(u32)fact * lw->inv_weight;
- return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
+ while (fact >> 32) {
+ fact >>= 1;
+ shift--;
+ }
+
+ return mul_u64_u32_shr(delta_exec, fact, shift);
}
@@ -443,7 +445,7 @@
#endif /* CONFIG_FAIR_GROUP_SCHED */
static __always_inline
-void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec);
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec);
/**************************************************************
* Scheduling class tree data structure manipulation methods:
@@ -612,11 +614,10 @@
/*
* delta /= w
*/
-static inline unsigned long
-calc_delta_fair(unsigned long delta, struct sched_entity *se)
+static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se)
{
if (unlikely(se->load.weight != NICE_0_LOAD))
- delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load);
+ delta = __calc_delta(delta, NICE_0_LOAD, &se->load);
return delta;
}
@@ -665,7 +666,7 @@
update_load_add(&lw, se->load.weight);
load = &lw;
}
- slice = calc_delta_mine(slice, se->load.weight, load);
+ slice = __calc_delta(slice, se->load.weight, load);
}
return slice;
}
@@ -703,47 +704,32 @@
#endif
/*
- * Update the current task's runtime statistics. Skip current tasks that
- * are not in our scheduling class.
+ * Update the current task's runtime statistics.
*/
-static inline void
-__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
- unsigned long delta_exec)
-{
- unsigned long delta_exec_weighted;
-
- schedstat_set(curr->statistics.exec_max,
- max((u64)delta_exec, curr->statistics.exec_max));
-
- curr->sum_exec_runtime += delta_exec;
- schedstat_add(cfs_rq, exec_clock, delta_exec);
- delta_exec_weighted = calc_delta_fair(delta_exec, curr);
-
- curr->vruntime += delta_exec_weighted;
- update_min_vruntime(cfs_rq);
-}
-
static void update_curr(struct cfs_rq *cfs_rq)
{
struct sched_entity *curr = cfs_rq->curr;
u64 now = rq_clock_task(rq_of(cfs_rq));
- unsigned long delta_exec;
+ u64 delta_exec;
if (unlikely(!curr))
return;
- /*
- * Get the amount of time the current task was running
- * since the last time we changed load (this cannot
- * overflow on 32 bits):
- */
- delta_exec = (unsigned long)(now - curr->exec_start);
- if (!delta_exec)
+ delta_exec = now - curr->exec_start;
+ if (unlikely((s64)delta_exec <= 0))
return;
- __update_curr(cfs_rq, curr, delta_exec);
curr->exec_start = now;
+ schedstat_set(curr->statistics.exec_max,
+ max(delta_exec, curr->statistics.exec_max));
+
+ curr->sum_exec_runtime += delta_exec;
+ schedstat_add(cfs_rq, exec_clock, delta_exec);
+
+ curr->vruntime += calc_delta_fair(delta_exec, curr);
+ update_min_vruntime(cfs_rq);
+
if (entity_is_task(curr)) {
struct task_struct *curtask = task_of(curr);
@@ -886,15 +872,6 @@
return max(smin, smax);
}
-/*
- * Once a preferred node is selected the scheduler balancer will prefer moving
- * a task to that node for sysctl_numa_balancing_settle_count number of PTE
- * scans. This will give the process the chance to accumulate more faults on
- * the preferred node but still allow the scheduler to move the task again if
- * the nodes CPUs are overloaded.
- */
-unsigned int sysctl_numa_balancing_settle_count __read_mostly = 4;
-
static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
{
rq->nr_numa_running += (p->numa_preferred_nid != -1);
@@ -944,7 +921,8 @@
if (!p->numa_group)
return 0;
- return p->numa_group->faults[2*nid] + p->numa_group->faults[2*nid+1];
+ return p->numa_group->faults[task_faults_idx(nid, 0)] +
+ p->numa_group->faults[task_faults_idx(nid, 1)];
}
/*
@@ -1037,7 +1015,7 @@
struct numa_stats src_stats, dst_stats;
- int imbalance_pct, idx;
+ int imbalance_pct;
struct task_struct *best_task;
long best_imp;
@@ -1225,7 +1203,7 @@
* elsewhere, so there is no point in (re)trying.
*/
if (unlikely(!sd)) {
- p->numa_preferred_nid = cpu_to_node(task_cpu(p));
+ p->numa_preferred_nid = task_node(p);
return -EINVAL;
}
@@ -1292,7 +1270,7 @@
p->numa_migrate_retry = jiffies + HZ;
/* Success if task is already running on preferred CPU */
- if (cpu_to_node(task_cpu(p)) == p->numa_preferred_nid)
+ if (task_node(p) == p->numa_preferred_nid)
return;
/* Otherwise, try migrate to a CPU on the preferred node */
@@ -1364,7 +1342,6 @@
* scanning faster if shared accesses dominate as it may
* simply bounce migrations uselessly
*/
- period_slot = DIV_ROUND_UP(diff, NUMA_PERIOD_SLOTS);
ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
}
@@ -1752,6 +1729,13 @@
(vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ)))
continue;
+ /*
+ * Skip inaccessible VMAs to avoid any confusion between
+ * PROT_NONE and NUMA hinting ptes
+ */
+ if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
+ continue;
+
do {
start = max(start, vma->vm_start);
end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
@@ -3015,8 +2999,7 @@
}
}
-static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
- unsigned long delta_exec)
+static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
{
/* dock delta_exec before expiring quota (as it could span periods) */
cfs_rq->runtime_remaining -= delta_exec;
@@ -3034,7 +3017,7 @@
}
static __always_inline
-void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec)
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
{
if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled)
return;
@@ -3574,8 +3557,7 @@
return rq_clock_task(rq_of(cfs_rq));
}
-static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
- unsigned long delta_exec) {}
+static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {}
static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
@@ -3932,7 +3914,7 @@
{
struct sched_entity *se = tg->se[cpu];
- if (!tg->parent || !wl) /* the trivial, non-cgroup case */
+ if (!tg->parent) /* the trivial, non-cgroup case */
return wl;
for_each_sched_entity(se) {
@@ -4110,12 +4092,16 @@
*/
static struct sched_group *
find_idlest_group(struct sched_domain *sd, struct task_struct *p,
- int this_cpu, int load_idx)
+ int this_cpu, int sd_flag)
{
struct sched_group *idlest = NULL, *group = sd->groups;
unsigned long min_load = ULONG_MAX, this_load = 0;
+ int load_idx = sd->forkexec_idx;
int imbalance = 100 + (sd->imbalance_pct-100)/2;
+ if (sd_flag & SD_BALANCE_WAKE)
+ load_idx = sd->wake_idx;
+
do {
unsigned long load, avg_load;
int local_group;
@@ -4283,7 +4269,6 @@
}
while (sd) {
- int load_idx = sd->forkexec_idx;
struct sched_group *group;
int weight;
@@ -4292,10 +4277,7 @@
continue;
}
- if (sd_flag & SD_BALANCE_WAKE)
- load_idx = sd->wake_idx;
-
- group = find_idlest_group(sd, p, cpu, load_idx);
+ group = find_idlest_group(sd, p, cpu, sd_flag);
if (!group) {
sd = sd->child;
continue;
@@ -5521,7 +5503,6 @@
struct sched_group *group, int load_idx,
int local_group, struct sg_lb_stats *sgs)
{
- unsigned long nr_running;
unsigned long load;
int i;
@@ -5530,8 +5511,6 @@
for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
struct rq *rq = cpu_rq(i);
- nr_running = rq->nr_running;
-
/* Bias balancing toward cpus of our domain */
if (local_group)
load = target_load(i, load_idx);
@@ -5539,7 +5518,7 @@
load = source_load(i, load_idx);
sgs->group_load += load;
- sgs->sum_nr_running += nr_running;
+ sgs->sum_nr_running += rq->nr_running;
#ifdef CONFIG_NUMA_BALANCING
sgs->nr_numa_running += rq->nr_numa_running;
sgs->nr_preferred_running += rq->nr_preferred_running;
@@ -6530,7 +6509,7 @@
unsigned long next_balance; /* in jiffy units */
} nohz ____cacheline_aligned;
-static inline int find_new_ilb(int call_cpu)
+static inline int find_new_ilb(void)
{
int ilb = cpumask_first(nohz.idle_cpus_mask);
@@ -6545,13 +6524,13 @@
* nohz_load_balancer CPU (if there is one) otherwise fallback to any idle
* CPU (if there is one).
*/
-static void nohz_balancer_kick(int cpu)
+static void nohz_balancer_kick(void)
{
int ilb_cpu;
nohz.next_balance++;
- ilb_cpu = find_new_ilb(cpu);
+ ilb_cpu = find_new_ilb();
if (ilb_cpu >= nr_cpu_ids)
return;
@@ -6661,10 +6640,10 @@
*
* Balancing parameters are set up in init_sched_domains.
*/
-static void rebalance_domains(int cpu, enum cpu_idle_type idle)
+static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
{
int continue_balancing = 1;
- struct rq *rq = cpu_rq(cpu);
+ int cpu = rq->cpu;
unsigned long interval;
struct sched_domain *sd;
/* Earliest time when we have to do rebalance again */
@@ -6761,9 +6740,9 @@
* In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the
* rebalancing for all the cpus for whom scheduler ticks are stopped.
*/
-static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle)
+static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
{
- struct rq *this_rq = cpu_rq(this_cpu);
+ int this_cpu = this_rq->cpu;
struct rq *rq;
int balance_cpu;
@@ -6790,7 +6769,7 @@
update_idle_cpu_load(rq);
raw_spin_unlock_irq(&rq->lock);
- rebalance_domains(balance_cpu, CPU_IDLE);
+ rebalance_domains(rq, CPU_IDLE);
if (time_after(this_rq->next_balance, rq->next_balance))
this_rq->next_balance = rq->next_balance;
@@ -6809,14 +6788,14 @@
* - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler
* domain span are idle.
*/
-static inline int nohz_kick_needed(struct rq *rq, int cpu)
+static inline int nohz_kick_needed(struct rq *rq)
{
unsigned long now = jiffies;
struct sched_domain *sd;
struct sched_group_power *sgp;
- int nr_busy;
+ int nr_busy, cpu = rq->cpu;
- if (unlikely(idle_cpu(cpu)))
+ if (unlikely(rq->idle_balance))
return 0;
/*
@@ -6865,7 +6844,7 @@
return 1;
}
#else
-static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { }
+static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { }
#endif
/*
@@ -6874,38 +6853,39 @@
*/
static void run_rebalance_domains(struct softirq_action *h)
{
- int this_cpu = smp_processor_id();
- struct rq *this_rq = cpu_rq(this_cpu);
+ struct rq *this_rq = this_rq();
enum cpu_idle_type idle = this_rq->idle_balance ?
CPU_IDLE : CPU_NOT_IDLE;
- rebalance_domains(this_cpu, idle);
+ rebalance_domains(this_rq, idle);
/*
* If this cpu has a pending nohz_balance_kick, then do the
* balancing on behalf of the other idle cpus whose ticks are
* stopped.
*/
- nohz_idle_balance(this_cpu, idle);
+ nohz_idle_balance(this_rq, idle);
}
-static inline int on_null_domain(int cpu)
+static inline int on_null_domain(struct rq *rq)
{
- return !rcu_dereference_sched(cpu_rq(cpu)->sd);
+ return !rcu_dereference_sched(rq->sd);
}
/*
* Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
*/
-void trigger_load_balance(struct rq *rq, int cpu)
+void trigger_load_balance(struct rq *rq)
{
/* Don't need to rebalance while attached to NULL domain */
- if (time_after_eq(jiffies, rq->next_balance) &&
- likely(!on_null_domain(cpu)))
+ if (unlikely(on_null_domain(rq)))
+ return;
+
+ if (time_after_eq(jiffies, rq->next_balance))
raise_softirq(SCHED_SOFTIRQ);
#ifdef CONFIG_NO_HZ_COMMON
- if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu)))
- nohz_balancer_kick(cpu);
+ if (nohz_kick_needed(rq))
+ nohz_balancer_kick();
#endif
}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 7d57275..a2740b7 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -901,6 +901,13 @@
{
struct rq *rq = rq_of_rt_rq(rt_rq);
+#ifdef CONFIG_RT_GROUP_SCHED
+ /*
+ * Change rq's cpupri only if rt_rq is the top queue.
+ */
+ if (&rq->rt != rt_rq)
+ return;
+#endif
if (rq->online && prio < prev_prio)
cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
}
@@ -910,6 +917,13 @@
{
struct rq *rq = rq_of_rt_rq(rt_rq);
+#ifdef CONFIG_RT_GROUP_SCHED
+ /*
+ * Change rq's cpupri only if rt_rq is the top queue.
+ */
+ if (&rq->rt != rt_rq)
+ return;
+#endif
if (rq->online && rt_rq->highest_prio.curr != prev_prio)
cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);
}
@@ -1724,7 +1738,7 @@
!test_tsk_need_resched(rq->curr) &&
has_pushable_tasks(rq) &&
p->nr_cpus_allowed > 1 &&
- rt_task(rq->curr) &&
+ (dl_task(rq->curr) || rt_task(rq->curr)) &&
(rq->curr->nr_cpus_allowed < 2 ||
rq->curr->prio <= p->prio))
push_rt_tasks(rq);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 88c85b2..c2119fd 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2,6 +2,7 @@
#include <linux/sched.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/stop_machine.h>
@@ -9,6 +10,7 @@
#include <linux/slab.h>
#include "cpupri.h"
+#include "cpudeadline.h"
#include "cpuacct.h"
struct rq;
@@ -73,6 +75,13 @@
#define NICE_0_SHIFT SCHED_LOAD_SHIFT
/*
+ * Single value that decides SCHED_DEADLINE internal math precision.
+ * 10 -> just above 1us
+ * 9 -> just above 0.5us
+ */
+#define DL_SCALE (10)
+
+/*
* These are the 'tuning knobs' of the scheduler:
*/
@@ -81,11 +90,19 @@
*/
#define RUNTIME_INF ((u64)~0ULL)
+static inline int fair_policy(int policy)
+{
+ return policy == SCHED_NORMAL || policy == SCHED_BATCH;
+}
+
static inline int rt_policy(int policy)
{
- if (policy == SCHED_FIFO || policy == SCHED_RR)
- return 1;
- return 0;
+ return policy == SCHED_FIFO || policy == SCHED_RR;
+}
+
+static inline int dl_policy(int policy)
+{
+ return policy == SCHED_DEADLINE;
}
static inline int task_has_rt_policy(struct task_struct *p)
@@ -93,6 +110,25 @@
return rt_policy(p->policy);
}
+static inline int task_has_dl_policy(struct task_struct *p)
+{
+ return dl_policy(p->policy);
+}
+
+static inline bool dl_time_before(u64 a, u64 b)
+{
+ return (s64)(a - b) < 0;
+}
+
+/*
+ * Tells if entity @a should preempt entity @b.
+ */
+static inline bool
+dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
+{
+ return dl_time_before(a->deadline, b->deadline);
+}
+
/*
* This is the priority-queue data structure of the RT scheduling class:
*/
@@ -108,6 +144,47 @@
u64 rt_runtime;
struct hrtimer rt_period_timer;
};
+/*
+ * To keep the bandwidth of -deadline tasks and groups under control
+ * we need some place where:
+ * - store the maximum -deadline bandwidth of the system (the group);
+ * - cache the fraction of that bandwidth that is currently allocated.
+ *
+ * This is all done in the data structure below. It is similar to the
+ * one used for RT-throttling (rt_bandwidth), with the main difference
+ * that, since here we are only interested in admission control, we
+ * do not decrease any runtime while the group "executes", neither we
+ * need a timer to replenish it.
+ *
+ * With respect to SMP, the bandwidth is given on a per-CPU basis,
+ * meaning that:
+ * - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
+ * - dl_total_bw array contains, in the i-eth element, the currently
+ * allocated bandwidth on the i-eth CPU.
+ * Moreover, groups consume bandwidth on each CPU, while tasks only
+ * consume bandwidth on the CPU they're running on.
+ * Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw
+ * that will be shown the next time the proc or cgroup controls will
+ * be red. It on its turn can be changed by writing on its own
+ * control.
+ */
+struct dl_bandwidth {
+ raw_spinlock_t dl_runtime_lock;
+ u64 dl_runtime;
+ u64 dl_period;
+};
+
+static inline int dl_bandwidth_enabled(void)
+{
+ return sysctl_sched_rt_runtime >= 0;
+}
+
+extern struct dl_bw *dl_bw_of(int i);
+
+struct dl_bw {
+ raw_spinlock_t lock;
+ u64 bw, total_bw;
+};
extern struct mutex sched_domains_mutex;
@@ -364,6 +441,42 @@
#endif
};
+/* Deadline class' related fields in a runqueue */
+struct dl_rq {
+ /* runqueue is an rbtree, ordered by deadline */
+ struct rb_root rb_root;
+ struct rb_node *rb_leftmost;
+
+ unsigned long dl_nr_running;
+
+#ifdef CONFIG_SMP
+ /*
+ * Deadline values of the currently executing and the
+ * earliest ready task on this rq. Caching these facilitates
+ * the decision wether or not a ready but not running task
+ * should migrate somewhere else.
+ */
+ struct {
+ u64 curr;
+ u64 next;
+ } earliest_dl;
+
+ unsigned long dl_nr_migratory;
+ unsigned long dl_nr_total;
+ int overloaded;
+
+ /*
+ * Tasks on this rq that can be pushed away. They are kept in
+ * an rb-tree, ordered by tasks' deadlines, with caching
+ * of the leftmost (earliest deadline) element.
+ */
+ struct rb_root pushable_dl_tasks_root;
+ struct rb_node *pushable_dl_tasks_leftmost;
+#else
+ struct dl_bw dl_bw;
+#endif
+};
+
#ifdef CONFIG_SMP
/*
@@ -382,6 +495,15 @@
cpumask_var_t online;
/*
+ * The bit corresponding to a CPU gets set here if such CPU has more
+ * than one runnable -deadline task (as it is below for RT tasks).
+ */
+ cpumask_var_t dlo_mask;
+ atomic_t dlo_count;
+ struct dl_bw dl_bw;
+ struct cpudl cpudl;
+
+ /*
* The "RT overload" flag: it gets set if a CPU has more than
* one runnable RT task.
*/
@@ -432,6 +554,7 @@
struct cfs_rq cfs;
struct rt_rq rt;
+ struct dl_rq dl;
#ifdef CONFIG_FAIR_GROUP_SCHED
/* list of leaf cfs_rq on this cpu: */
@@ -827,8 +950,6 @@
return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
}
-
-
static inline int task_current(struct rq *rq, struct task_struct *p)
{
return rq->curr == p;
@@ -988,6 +1109,7 @@
#else
#define ENQUEUE_WAKING 0
#endif
+#define ENQUEUE_REPLENISH 8
#define DEQUEUE_SLEEP 1
@@ -1023,6 +1145,7 @@
void (*set_curr_task) (struct rq *rq);
void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
void (*task_fork) (struct task_struct *p);
+ void (*task_dead) (struct task_struct *p);
void (*switched_from) (struct rq *this_rq, struct task_struct *task);
void (*switched_to) (struct rq *this_rq, struct task_struct *task);
@@ -1042,6 +1165,7 @@
for (class = sched_class_highest; class; class = class->next)
extern const struct sched_class stop_sched_class;
+extern const struct sched_class dl_sched_class;
extern const struct sched_class rt_sched_class;
extern const struct sched_class fair_sched_class;
extern const struct sched_class idle_sched_class;
@@ -1051,7 +1175,7 @@
extern void update_group_power(struct sched_domain *sd, int cpu);
-extern void trigger_load_balance(struct rq *rq, int cpu);
+extern void trigger_load_balance(struct rq *rq);
extern void idle_balance(int this_cpu, struct rq *this_rq);
extern void idle_enter_fair(struct rq *this_rq);
@@ -1068,8 +1192,11 @@
extern void sysrq_sched_debug_show(void);
extern void sched_init_granularity(void);
extern void update_max_interval(void);
+
+extern void init_sched_dl_class(void);
extern void init_sched_rt_class(void);
extern void init_sched_fair_class(void);
+extern void init_sched_dl_class(void);
extern void resched_task(struct task_struct *p);
extern void resched_cpu(int cpu);
@@ -1077,6 +1204,12 @@
extern struct rt_bandwidth def_rt_bandwidth;
extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
+extern struct dl_bandwidth def_dl_bandwidth;
+extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
+extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
+
+unsigned long to_ratio(u64 period, u64 runtime);
+
extern void update_idle_cpu_load(struct rq *this_rq);
extern void init_task_runnable_average(struct task_struct *p);
@@ -1353,6 +1486,7 @@
extern void init_cfs_rq(struct cfs_rq *cfs_rq);
extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
+extern void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq);
extern void cfs_bandwidth_usage_inc(void);
extern void cfs_bandwidth_usage_dec(void);
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 47197de..fdb6bb0 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -103,7 +103,7 @@
* Simple, special scheduling class for the per-CPU stop tasks:
*/
const struct sched_class stop_sched_class = {
- .next = &rt_sched_class,
+ .next = &dl_sched_class,
.enqueue_task = enqueue_task_stop,
.dequeue_task = dequeue_task_stop,
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 11025cc..9e368ef 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -89,7 +89,7 @@
* where hardirqs are disabled legitimately:
*/
#ifdef CONFIG_TRACE_IRQFLAGS
-static void __local_bh_disable(unsigned long ip, unsigned int cnt)
+void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
{
unsigned long flags;
@@ -107,33 +107,21 @@
/*
* Were softirqs turned off above:
*/
- if (softirq_count() == cnt)
+ if (softirq_count() == (cnt & SOFTIRQ_MASK))
trace_softirqs_off(ip);
raw_local_irq_restore(flags);
if (preempt_count() == cnt)
trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
}
-#else /* !CONFIG_TRACE_IRQFLAGS */
-static inline void __local_bh_disable(unsigned long ip, unsigned int cnt)
-{
- preempt_count_add(cnt);
- barrier();
-}
+EXPORT_SYMBOL(__local_bh_disable_ip);
#endif /* CONFIG_TRACE_IRQFLAGS */
-void local_bh_disable(void)
-{
- __local_bh_disable(_RET_IP_, SOFTIRQ_DISABLE_OFFSET);
-}
-
-EXPORT_SYMBOL(local_bh_disable);
-
static void __local_bh_enable(unsigned int cnt)
{
WARN_ON_ONCE(!irqs_disabled());
- if (softirq_count() == cnt)
+ if (softirq_count() == (cnt & SOFTIRQ_MASK))
trace_softirqs_on(_RET_IP_);
preempt_count_sub(cnt);
}
@@ -151,7 +139,7 @@
EXPORT_SYMBOL(_local_bh_enable);
-static inline void _local_bh_enable_ip(unsigned long ip)
+void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
{
WARN_ON_ONCE(in_irq() || irqs_disabled());
#ifdef CONFIG_TRACE_IRQFLAGS
@@ -166,7 +154,7 @@
* Keep preemption disabled until we are done with
* softirq processing:
*/
- preempt_count_sub(SOFTIRQ_DISABLE_OFFSET - 1);
+ preempt_count_sub(cnt - 1);
if (unlikely(!in_interrupt() && local_softirq_pending())) {
/*
@@ -182,18 +170,7 @@
#endif
preempt_check_resched();
}
-
-void local_bh_enable(void)
-{
- _local_bh_enable_ip(_RET_IP_);
-}
-EXPORT_SYMBOL(local_bh_enable);
-
-void local_bh_enable_ip(unsigned long ip)
-{
- _local_bh_enable_ip(ip);
-}
-EXPORT_SYMBOL(local_bh_enable_ip);
+EXPORT_SYMBOL(__local_bh_enable_ip);
/*
* We restart softirq processing for at most MAX_SOFTIRQ_RESTART times,
@@ -230,7 +207,7 @@
pending = local_softirq_pending();
account_irq_enter_time(current);
- __local_bh_disable(_RET_IP_, SOFTIRQ_OFFSET);
+ __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
lockdep_softirq_enter();
cpu = smp_processor_id();
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 34a6047..c8da99f 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -385,13 +385,6 @@
.proc_handler = proc_dointvec,
},
{
- .procname = "numa_balancing_settle_count",
- .data = &sysctl_numa_balancing_settle_count,
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
.procname = "numa_balancing_migrate_deferred",
.data = &sysctl_numa_balancing_migrate_deferred,
.maxlen = sizeof(unsigned int),
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index ea20f7d..c833249 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -177,7 +177,7 @@
* TODO: kick full dynticks CPUs when
* sched_clock_stable is set.
*/
- if (!sched_clock_stable) {
+ if (!sched_clock_stable()) {
trace_tick_stop(0, "unstable sched clock\n");
/*
* Don't allow the user to think they can get
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0e9f9ea..72a0f81 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -775,7 +775,7 @@
int cpu;
int ret = 0;
- for_each_online_cpu(cpu) {
+ for_each_possible_cpu(cpu) {
ret = ftrace_profile_init_cpu(cpu);
if (ret)
break;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index cc2f66f..294b8a2 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2558,7 +2558,7 @@
if (unlikely(test_time_stamp(delta))) {
int local_clock_stable = 1;
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
- local_clock_stable = sched_clock_stable;
+ local_clock_stable = sched_clock_stable();
#endif
WARN_ONCE(delta > (1ULL << 59),
KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s",
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index fee77e1..6e32635 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -16,6 +16,7 @@
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
#include <trace/events/sched.h>
#include "trace.h"
@@ -27,6 +28,8 @@
static int wakeup_current_cpu;
static unsigned wakeup_prio = -1;
static int wakeup_rt;
+static int wakeup_dl;
+static int tracing_dl = 0;
static arch_spinlock_t wakeup_lock =
(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
@@ -437,6 +440,7 @@
{
wakeup_cpu = -1;
wakeup_prio = -1;
+ tracing_dl = 0;
if (wakeup_task)
put_task_struct(wakeup_task);
@@ -472,9 +476,17 @@
tracing_record_cmdline(p);
tracing_record_cmdline(current);
- if ((wakeup_rt && !rt_task(p)) ||
- p->prio >= wakeup_prio ||
- p->prio >= current->prio)
+ /*
+ * Semantic is like this:
+ * - wakeup tracer handles all tasks in the system, independently
+ * from their scheduling class;
+ * - wakeup_rt tracer handles tasks belonging to sched_dl and
+ * sched_rt class;
+ * - wakeup_dl handles tasks belonging to sched_dl class only.
+ */
+ if (tracing_dl || (wakeup_dl && !dl_task(p)) ||
+ (wakeup_rt && !dl_task(p) && !rt_task(p)) ||
+ (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio)))
return;
pc = preempt_count();
@@ -486,7 +498,8 @@
arch_spin_lock(&wakeup_lock);
/* check for races. */
- if (!tracer_enabled || p->prio >= wakeup_prio)
+ if (!tracer_enabled || tracing_dl ||
+ (!dl_task(p) && p->prio >= wakeup_prio))
goto out_locked;
/* reset the trace */
@@ -496,6 +509,15 @@
wakeup_current_cpu = wakeup_cpu;
wakeup_prio = p->prio;
+ /*
+ * Once you start tracing a -deadline task, don't bother tracing
+ * another task until the first one wakes up.
+ */
+ if (dl_task(p))
+ tracing_dl = 1;
+ else
+ tracing_dl = 0;
+
wakeup_task = p;
get_task_struct(wakeup_task);
@@ -597,16 +619,25 @@
static int wakeup_tracer_init(struct trace_array *tr)
{
+ wakeup_dl = 0;
wakeup_rt = 0;
return __wakeup_tracer_init(tr);
}
static int wakeup_rt_tracer_init(struct trace_array *tr)
{
+ wakeup_dl = 0;
wakeup_rt = 1;
return __wakeup_tracer_init(tr);
}
+static int wakeup_dl_tracer_init(struct trace_array *tr)
+{
+ wakeup_dl = 1;
+ wakeup_rt = 0;
+ return __wakeup_tracer_init(tr);
+}
+
static void wakeup_tracer_reset(struct trace_array *tr)
{
int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
@@ -674,6 +705,28 @@
.use_max_tr = true,
};
+static struct tracer wakeup_dl_tracer __read_mostly =
+{
+ .name = "wakeup_dl",
+ .init = wakeup_dl_tracer_init,
+ .reset = wakeup_tracer_reset,
+ .start = wakeup_tracer_start,
+ .stop = wakeup_tracer_stop,
+ .wait_pipe = poll_wait_pipe,
+ .print_max = true,
+ .print_header = wakeup_print_header,
+ .print_line = wakeup_print_line,
+ .flags = &tracer_flags,
+ .set_flag = wakeup_set_flag,
+ .flag_changed = wakeup_flag_changed,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_wakeup,
+#endif
+ .open = wakeup_trace_open,
+ .close = wakeup_trace_close,
+ .use_max_tr = true,
+};
+
__init static int init_wakeup_tracer(void)
{
int ret;
@@ -686,6 +739,10 @@
if (ret)
return ret;
+ ret = register_tracer(&wakeup_dl_tracer);
+ if (ret)
+ return ret;
+
return 0;
}
core_initcall(init_wakeup_tracer);
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index a7329b7..e98fca6 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -1022,11 +1022,16 @@
#ifdef CONFIG_SCHED_TRACER
static int trace_wakeup_test_thread(void *data)
{
- /* Make this a RT thread, doesn't need to be too high */
- static const struct sched_param param = { .sched_priority = 5 };
+ /* Make this a -deadline thread */
+ static const struct sched_attr attr = {
+ .sched_policy = SCHED_DEADLINE,
+ .sched_runtime = 100000ULL,
+ .sched_deadline = 10000000ULL,
+ .sched_period = 10000000ULL
+ };
struct completion *x = data;
- sched_setscheduler(current, SCHED_FIFO, ¶m);
+ sched_setattr(current, &attr);
/* Make it know we have a new prio */
complete(x);
@@ -1040,8 +1045,8 @@
/* we are awake, now wait to disappear */
while (!kthread_should_stop()) {
/*
- * This is an RT task, do short sleeps to let
- * others run.
+ * This will likely be the system top priority
+ * task, do short sleeps to let others run.
*/
msleep(100);
}
@@ -1054,21 +1059,21 @@
{
unsigned long save_max = tracing_max_latency;
struct task_struct *p;
- struct completion isrt;
+ struct completion is_ready;
unsigned long count;
int ret;
- init_completion(&isrt);
+ init_completion(&is_ready);
- /* create a high prio thread */
- p = kthread_run(trace_wakeup_test_thread, &isrt, "ftrace-test");
+ /* create a -deadline thread */
+ p = kthread_run(trace_wakeup_test_thread, &is_ready, "ftrace-test");
if (IS_ERR(p)) {
printk(KERN_CONT "Failed to create ftrace wakeup test thread ");
return -1;
}
- /* make sure the thread is running at an RT prio */
- wait_for_completion(&isrt);
+ /* make sure the thread is running at -deadline policy */
+ wait_for_completion(&is_ready);
/* start the tracing */
ret = tracer_init(trace, tr);
@@ -1082,19 +1087,19 @@
while (p->on_rq) {
/*
- * Sleep to make sure the RT thread is asleep too.
+ * Sleep to make sure the -deadline thread is asleep too.
* On virtual machines we can't rely on timings,
* but we want to make sure this test still works.
*/
msleep(100);
}
- init_completion(&isrt);
+ init_completion(&is_ready);
wake_up_process(p);
/* Wait for the task to wake up */
- wait_for_completion(&isrt);
+ wait_for_completion(&is_ready);
/* stop the tracing. */
tracing_stop();
diff --git a/kernel/user.c b/kernel/user.c
index a3a0dbf..c006131 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,9 +51,9 @@
.owner = GLOBAL_ROOT_UID,
.group = GLOBAL_ROOT_GID,
.proc_inum = PROC_USER_INIT_INO,
-#ifdef CONFIG_KEYS_KERBEROS_CACHE
- .krb_cache_register_sem =
- __RWSEM_INITIALIZER(init_user_ns.krb_cache_register_sem),
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+ .persistent_keyring_register_sem =
+ __RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem),
#endif
};
EXPORT_SYMBOL_GPL(init_user_ns);
diff --git a/mm/Kconfig b/mm/Kconfig
index eb69f35..723bbe0 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -543,7 +543,7 @@
config MEM_SOFT_DIRTY
bool "Track memory changes"
- depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY
+ depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
select PROC_PAGE_MONITOR
help
This option enables memory changes tracking by introducing a
diff --git a/mm/compaction.c b/mm/compaction.c
index 805165b..f58bcd0 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -134,6 +134,10 @@
bool migrate_scanner)
{
struct zone *zone = cc->zone;
+
+ if (cc->ignore_skip_hint)
+ return;
+
if (!page)
return;
diff --git a/mm/fremap.c b/mm/fremap.c
index 5bff081..bbc4d66 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -208,9 +208,10 @@
if (mapping_cap_account_dirty(mapping)) {
unsigned long addr;
struct file *file = get_file(vma->vm_file);
+ /* mmap_region may free vma; grab the info now */
+ vm_flags = vma->vm_flags;
- addr = mmap_region(file, start, size,
- vma->vm_flags, pgoff);
+ addr = mmap_region(file, start, size, vm_flags, pgoff);
fput(file);
if (IS_ERR_VALUE(addr)) {
err = addr;
@@ -218,7 +219,7 @@
BUG_ON(addr != start);
err = 0;
}
- goto out;
+ goto out_freed;
}
mutex_lock(&mapping->i_mmap_mutex);
flush_dcache_mmap_lock(mapping);
@@ -253,6 +254,7 @@
out:
if (vma)
vm_flags = vma->vm_flags;
+out_freed:
if (likely(!has_write_lock))
up_read(&mm->mmap_sem);
else
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 33a5dc4..9c0b172 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -882,6 +882,7 @@
ret = 0;
goto out_unlock;
}
+
if (unlikely(pmd_trans_splitting(pmd))) {
/* split huge page running from under us */
spin_unlock(src_ptl);
@@ -1243,6 +1244,10 @@
if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))
return ERR_PTR(-EFAULT);
+ /* Full NUMA hinting faults to serialise migration in fault paths */
+ if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+ goto out;
+
page = pmd_page(*pmd);
VM_BUG_ON(!PageHead(page));
if (flags & FOLL_TOUCH) {
@@ -1295,6 +1300,17 @@
if (unlikely(!pmd_same(pmd, *pmdp)))
goto out_unlock;
+ /*
+ * If there are potential migrations, wait for completion and retry
+ * without disrupting NUMA hinting information. Do not relock and
+ * check_same as the page may no longer be mapped.
+ */
+ if (unlikely(pmd_trans_migrating(*pmdp))) {
+ spin_unlock(ptl);
+ wait_migrate_huge_page(vma->anon_vma, pmdp);
+ goto out;
+ }
+
page = pmd_page(pmd);
BUG_ON(is_huge_zero_page(page));
page_nid = page_to_nid(page);
@@ -1323,23 +1339,22 @@
/* If the page was locked, there are no parallel migrations */
if (page_locked)
goto clear_pmdnuma;
+ }
- /*
- * Otherwise wait for potential migrations and retry. We do
- * relock and check_same as the page may no longer be mapped.
- * As the fault is being retried, do not account for it.
- */
+ /* Migration could have started since the pmd_trans_migrating check */
+ if (!page_locked) {
spin_unlock(ptl);
wait_on_page_locked(page);
page_nid = -1;
goto out;
}
- /* Page is misplaced, serialise migrations and parallel THP splits */
+ /*
+ * Page is misplaced. Page lock serialises migrations. Acquire anon_vma
+ * to serialises splits
+ */
get_page(page);
spin_unlock(ptl);
- if (!page_locked)
- lock_page(page);
anon_vma = page_lock_anon_vma_read(page);
/* Confirm the PMD did not change while page_table_lock was released */
@@ -1351,6 +1366,13 @@
goto out_unlock;
}
+ /* Bail if we fail to protect against THP splits for any reason */
+ if (unlikely(!anon_vma)) {
+ put_page(page);
+ page_nid = -1;
+ goto clear_pmdnuma;
+ }
+
/*
* Migrate the THP to the requested node, returns with page unlocked
* and pmd_numa cleared.
@@ -1517,6 +1539,8 @@
ret = 1;
if (!prot_numa) {
entry = pmdp_get_and_clear(mm, addr, pmd);
+ if (pmd_numa(entry))
+ entry = pmd_mknonnuma(entry);
entry = pmd_modify(entry, newprot);
ret = HPAGE_PMD_NR;
BUG_ON(pmd_write(entry));
@@ -1531,7 +1555,7 @@
*/
if (!is_huge_zero_page(page) &&
!pmd_numa(*pmd)) {
- entry = pmdp_get_and_clear(mm, addr, pmd);
+ entry = *pmd;
entry = pmd_mknuma(entry);
ret = HPAGE_PMD_NR;
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index bf5e894..7f1a356 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -338,7 +338,7 @@
static size_t memcg_size(void)
{
return sizeof(struct mem_cgroup) +
- nr_node_ids * sizeof(struct mem_cgroup_per_node);
+ nr_node_ids * sizeof(struct mem_cgroup_per_node *);
}
/* internal only representation about the status of kmem accounting. */
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index b7c1716..fabe550 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -938,6 +938,16 @@
BUG_ON(!PageHWPoison(p));
return SWAP_FAIL;
}
+ /*
+ * We pinned the head page for hwpoison handling,
+ * now we split the thp and we are interested in
+ * the hwpoisoned raw page, so move the refcount
+ * to it.
+ */
+ if (hpage != p) {
+ put_page(hpage);
+ get_page(p);
+ }
/* THP is split, so ppage should be the real poisoned page. */
ppage = p;
}
@@ -1505,10 +1515,16 @@
if (ret > 0)
ret = -EIO;
} else {
- set_page_hwpoison_huge_page(hpage);
- dequeue_hwpoisoned_huge_page(hpage);
- atomic_long_add(1 << compound_order(hpage),
- &num_poisoned_pages);
+ /* overcommit hugetlb page will be freed to buddy */
+ if (PageHuge(page)) {
+ set_page_hwpoison_huge_page(hpage);
+ dequeue_hwpoisoned_huge_page(hpage);
+ atomic_long_add(1 << compound_order(hpage),
+ &num_poisoned_pages);
+ } else {
+ SetPageHWPoison(page);
+ atomic_long_inc(&num_poisoned_pages);
+ }
}
return ret;
}
diff --git a/mm/memory.c b/mm/memory.c
index 5d9025f..6768ce9 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4271,7 +4271,7 @@
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
-#if USE_SPLIT_PTE_PTLOCKS && BLOATED_SPINLOCKS
+#if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS
bool ptlock_alloc(struct page *page)
{
spinlock_t *ptl;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index eca4a31..0cd2c4d 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1197,14 +1197,16 @@
break;
vma = vma->vm_next;
}
- /*
- * queue_pages_range() confirms that @page belongs to some vma,
- * so vma shouldn't be NULL.
- */
- BUG_ON(!vma);
- if (PageHuge(page))
- return alloc_huge_page_noerr(vma, address, 1);
+ if (PageHuge(page)) {
+ if (vma)
+ return alloc_huge_page_noerr(vma, address, 1);
+ else
+ return NULL;
+ }
+ /*
+ * if !vma, alloc_page_vma() will use task or system default policy
+ */
return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
}
#else
@@ -1318,7 +1320,7 @@
if (nr_failed && (flags & MPOL_MF_STRICT))
err = -EIO;
} else
- putback_lru_pages(&pagelist);
+ putback_movable_pages(&pagelist);
up_write(&mm->mmap_sem);
mpol_out:
diff --git a/mm/migrate.c b/mm/migrate.c
index bb94004..9194375 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -36,6 +36,7 @@
#include <linux/hugetlb_cgroup.h>
#include <linux/gfp.h>
#include <linux/balloon_compaction.h>
+#include <linux/mmu_notifier.h>
#include <asm/tlbflush.h>
@@ -316,14 +317,15 @@
*/
int migrate_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page,
- struct buffer_head *head, enum migrate_mode mode)
+ struct buffer_head *head, enum migrate_mode mode,
+ int extra_count)
{
- int expected_count = 0;
+ int expected_count = 1 + extra_count;
void **pslot;
if (!mapping) {
/* Anonymous page without mapping */
- if (page_count(page) != 1)
+ if (page_count(page) != expected_count)
return -EAGAIN;
return MIGRATEPAGE_SUCCESS;
}
@@ -333,7 +335,7 @@
pslot = radix_tree_lookup_slot(&mapping->page_tree,
page_index(page));
- expected_count = 2 + page_has_private(page);
+ expected_count += 1 + page_has_private(page);
if (page_count(page) != expected_count ||
radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) {
spin_unlock_irq(&mapping->tree_lock);
@@ -583,7 +585,7 @@
BUG_ON(PageWriteback(page)); /* Writeback must be complete */
- rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode);
+ rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0);
if (rc != MIGRATEPAGE_SUCCESS)
return rc;
@@ -610,7 +612,7 @@
head = page_buffers(page);
- rc = migrate_page_move_mapping(mapping, newpage, page, head, mode);
+ rc = migrate_page_move_mapping(mapping, newpage, page, head, mode, 0);
if (rc != MIGRATEPAGE_SUCCESS)
return rc;
@@ -1654,6 +1656,18 @@
return 1;
}
+bool pmd_trans_migrating(pmd_t pmd)
+{
+ struct page *page = pmd_page(pmd);
+ return PageLocked(page);
+}
+
+void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
+{
+ struct page *page = pmd_page(*pmd);
+ wait_on_page_locked(page);
+}
+
/*
* Attempt to migrate a misplaced page to the specified destination
* node. Caller is expected to have an elevated reference count on
@@ -1716,12 +1730,14 @@
struct page *page, int node)
{
spinlock_t *ptl;
- unsigned long haddr = address & HPAGE_PMD_MASK;
pg_data_t *pgdat = NODE_DATA(node);
int isolated = 0;
struct page *new_page = NULL;
struct mem_cgroup *memcg = NULL;
int page_lru = page_is_file_cache(page);
+ unsigned long mmun_start = address & HPAGE_PMD_MASK;
+ unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE;
+ pmd_t orig_entry;
/*
* Rate-limit the amount of data that is being migrated to a node.
@@ -1744,6 +1760,9 @@
goto out_fail;
}
+ if (mm_tlb_flush_pending(mm))
+ flush_tlb_range(vma, mmun_start, mmun_end);
+
/* Prepare a page as a migration target */
__set_page_locked(new_page);
SetPageSwapBacked(new_page);
@@ -1755,9 +1774,12 @@
WARN_ON(PageLRU(new_page));
/* Recheck the target PMD */
+ mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
ptl = pmd_lock(mm, pmd);
- if (unlikely(!pmd_same(*pmd, entry))) {
+ if (unlikely(!pmd_same(*pmd, entry) || page_count(page) != 2)) {
+fail_putback:
spin_unlock(ptl);
+ mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
/* Reverse changes made by migrate_page_copy() */
if (TestClearPageActive(new_page))
@@ -1774,7 +1796,8 @@
putback_lru_page(page);
mod_zone_page_state(page_zone(page),
NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
- goto out_fail;
+
+ goto out_unlock;
}
/*
@@ -1786,16 +1809,35 @@
*/
mem_cgroup_prepare_migration(page, new_page, &memcg);
+ orig_entry = *pmd;
entry = mk_pmd(new_page, vma->vm_page_prot);
- entry = pmd_mknonnuma(entry);
- entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
entry = pmd_mkhuge(entry);
+ entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
- pmdp_clear_flush(vma, haddr, pmd);
- set_pmd_at(mm, haddr, pmd, entry);
- page_add_new_anon_rmap(new_page, vma, haddr);
+ /*
+ * Clear the old entry under pagetable lock and establish the new PTE.
+ * Any parallel GUP will either observe the old page blocking on the
+ * page lock, block on the page table lock or observe the new page.
+ * The SetPageUptodate on the new page and page_add_new_anon_rmap
+ * guarantee the copy is visible before the pagetable update.
+ */
+ flush_cache_range(vma, mmun_start, mmun_end);
+ page_add_new_anon_rmap(new_page, vma, mmun_start);
+ pmdp_clear_flush(vma, mmun_start, pmd);
+ set_pmd_at(mm, mmun_start, pmd, entry);
+ flush_tlb_range(vma, mmun_start, mmun_end);
update_mmu_cache_pmd(vma, address, &entry);
+
+ if (page_count(page) != 2) {
+ set_pmd_at(mm, mmun_start, pmd, orig_entry);
+ flush_tlb_range(vma, mmun_start, mmun_end);
+ update_mmu_cache_pmd(vma, address, &entry);
+ page_remove_rmap(new_page);
+ goto fail_putback;
+ }
+
page_remove_rmap(page);
+
/*
* Finish the charge transaction under the page table lock to
* prevent split_huge_page() from dividing up the charge
@@ -1803,6 +1845,7 @@
*/
mem_cgroup_end_migration(memcg, page, new_page, true);
spin_unlock(ptl);
+ mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
unlock_page(new_page);
unlock_page(page);
@@ -1820,10 +1863,15 @@
out_fail:
count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
out_dropref:
- entry = pmd_mknonnuma(entry);
- set_pmd_at(mm, haddr, pmd, entry);
- update_mmu_cache_pmd(vma, address, &entry);
+ ptl = pmd_lock(mm, pmd);
+ if (pmd_same(*pmd, entry)) {
+ entry = pmd_mknonnuma(entry);
+ set_pmd_at(mm, mmun_start, pmd, entry);
+ update_mmu_cache_pmd(vma, address, &entry);
+ }
+ spin_unlock(ptl);
+out_unlock:
unlock_page(page);
put_page(page);
return 0;
diff --git a/mm/mlock.c b/mm/mlock.c
index d480cd6..192e6ee 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -133,7 +133,10 @@
/**
* munlock_vma_page - munlock a vma page
- * @page - page to be unlocked
+ * @page - page to be unlocked, either a normal page or THP page head
+ *
+ * returns the size of the page as a page mask (0 for normal page,
+ * HPAGE_PMD_NR - 1 for THP head page)
*
* called from munlock()/munmap() path with page supposedly on the LRU.
* When we munlock a page, because the vma where we found the page is being
@@ -148,21 +151,30 @@
*/
unsigned int munlock_vma_page(struct page *page)
{
- unsigned int page_mask = 0;
+ unsigned int nr_pages;
BUG_ON(!PageLocked(page));
if (TestClearPageMlocked(page)) {
- unsigned int nr_pages = hpage_nr_pages(page);
+ nr_pages = hpage_nr_pages(page);
mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
- page_mask = nr_pages - 1;
if (!isolate_lru_page(page))
__munlock_isolated_page(page);
else
__munlock_isolation_failed(page);
+ } else {
+ nr_pages = hpage_nr_pages(page);
}
- return page_mask;
+ /*
+ * Regardless of the original PageMlocked flag, we determine nr_pages
+ * after touching the flag. This leaves a possible race with a THP page
+ * split, such that a whole THP page was munlocked, but nr_pages == 1.
+ * Returning a smaller mask due to that is OK, the worst that can
+ * happen is subsequent useless scanning of the former tail pages.
+ * The NR_MLOCK accounting can however become broken.
+ */
+ return nr_pages - 1;
}
/**
@@ -286,10 +298,12 @@
{
int i;
int nr = pagevec_count(pvec);
- int delta_munlocked = -nr;
+ int delta_munlocked;
struct pagevec pvec_putback;
int pgrescued = 0;
+ pagevec_init(&pvec_putback, 0);
+
/* Phase 1: page isolation */
spin_lock_irq(&zone->lru_lock);
for (i = 0; i < nr; i++) {
@@ -318,18 +332,21 @@
/*
* We won't be munlocking this page in the next phase
* but we still need to release the follow_page_mask()
- * pin.
+ * pin. We cannot do it under lru_lock however. If it's
+ * the last pin, __page_cache_release would deadlock.
*/
+ pagevec_add(&pvec_putback, pvec->pages[i]);
pvec->pages[i] = NULL;
- put_page(page);
- delta_munlocked++;
}
}
+ delta_munlocked = -nr + pagevec_count(&pvec_putback);
__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
spin_unlock_irq(&zone->lru_lock);
+ /* Now we can release pins of pages that we are not munlocking */
+ pagevec_release(&pvec_putback);
+
/* Phase 2: page munlock */
- pagevec_init(&pvec_putback, 0);
for (i = 0; i < nr; i++) {
struct page *page = pvec->pages[i];
@@ -440,7 +457,8 @@
while (start < end) {
struct page *page = NULL;
- unsigned int page_mask, page_increm;
+ unsigned int page_mask;
+ unsigned long page_increm;
struct pagevec pvec;
struct zone *zone;
int zoneid;
@@ -490,7 +508,9 @@
goto next;
}
}
- page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
+ /* It's a bug to munlock in the middle of a THP page */
+ VM_BUG_ON((start >> PAGE_SHIFT) & page_mask);
+ page_increm = 1 + page_mask;
start += page_increm * PAGE_SIZE;
next:
cond_resched();
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 26667971..bb53a65 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -52,17 +52,21 @@
pte_t ptent;
bool updated = false;
- ptent = ptep_modify_prot_start(mm, addr, pte);
if (!prot_numa) {
+ ptent = ptep_modify_prot_start(mm, addr, pte);
+ if (pte_numa(ptent))
+ ptent = pte_mknonnuma(ptent);
ptent = pte_modify(ptent, newprot);
updated = true;
} else {
struct page *page;
+ ptent = *pte;
page = vm_normal_page(vma, addr, oldpte);
if (page) {
if (!pte_numa(oldpte)) {
ptent = pte_mknuma(ptent);
+ set_pte_at(mm, addr, pte, ptent);
updated = true;
}
}
@@ -79,7 +83,10 @@
if (updated)
pages++;
- ptep_modify_prot_commit(mm, addr, pte, ptent);
+
+ /* Only !prot_numa always clears the pte */
+ if (!prot_numa)
+ ptep_modify_prot_commit(mm, addr, pte, ptent);
} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
swp_entry_t entry = pte_to_swp_entry(oldpte);
@@ -181,6 +188,7 @@
BUG_ON(addr >= end);
pgd = pgd_offset(mm, addr);
flush_cache_range(vma, addr, end);
+ set_tlb_flush_pending(mm);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
@@ -192,6 +200,7 @@
/* Only flush the TLB if we actually modified any entries: */
if (pages)
flush_tlb_range(vma, start, end);
+ clear_tlb_flush_pending(mm);
return pages;
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 580a5f0..5248fe0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1816,7 +1816,7 @@
static bool zone_local(struct zone *local_zone, struct zone *zone)
{
- return node_distance(local_zone->node, zone->node) == LOCAL_DISTANCE;
+ return local_zone->node == zone->node;
}
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
@@ -1913,18 +1913,17 @@
* page was allocated in should have no effect on the
* time the page has in memory before being reclaimed.
*
- * When zone_reclaim_mode is enabled, try to stay in
- * local zones in the fastpath. If that fails, the
- * slowpath is entered, which will do another pass
- * starting with the local zones, but ultimately fall
- * back to remote zones that do not partake in the
- * fairness round-robin cycle of this zonelist.
+ * Try to stay in local zones in the fastpath. If
+ * that fails, the slowpath is entered, which will do
+ * another pass starting with the local zones, but
+ * ultimately fall back to remote zones that do not
+ * partake in the fairness round-robin cycle of this
+ * zonelist.
*/
if (alloc_flags & ALLOC_WMARK_LOW) {
if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
continue;
- if (zone_reclaim_mode &&
- !zone_local(preferred_zone, zone))
+ if (!zone_local(preferred_zone, zone))
continue;
}
/*
@@ -2390,7 +2389,7 @@
* thrash fairness information for zones that are not
* actually part of this zonelist's round-robin cycle.
*/
- if (zone_reclaim_mode && !zone_local(preferred_zone, zone))
+ if (!zone_local(preferred_zone, zone))
continue;
mod_zone_page_state(zone, NR_ALLOC_BATCH,
high_wmark_pages(zone) -
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index cbb3854..a8b9199 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -110,9 +110,10 @@
pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
pte_t *ptep)
{
+ struct mm_struct *mm = (vma)->vm_mm;
pte_t pte;
- pte = ptep_get_and_clear((vma)->vm_mm, address, ptep);
- if (pte_accessible(pte))
+ pte = ptep_get_and_clear(mm, address, ptep);
+ if (pte_accessible(mm, pte))
flush_tlb_page(vma, address);
return pte;
}
@@ -191,6 +192,9 @@
void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
+ pmd_t entry = *pmdp;
+ if (pmd_numa(entry))
+ entry = pmd_mknonnuma(entry);
set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(*pmdp));
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
}
diff --git a/mm/rmap.c b/mm/rmap.c
index 55c8b8d..068522d 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -600,7 +600,11 @@
spinlock_t *ptl;
if (unlikely(PageHuge(page))) {
+ /* when pud is not present, pte will be NULL */
pte = huge_pte_offset(mm, address);
+ if (!pte)
+ return NULL;
+
ptl = huge_pte_lockptr(page_hstate(page), mm, pte);
goto check;
}
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 762896e..47c908f 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -530,6 +530,23 @@
.parse = eth_header_parse,
};
+static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev,
+ unsigned short type,
+ const void *daddr, const void *saddr,
+ unsigned int len)
+{
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+ struct net_device *real_dev = vlan->real_dev;
+
+ return dev_hard_header(skb, real_dev, type, daddr, saddr, len);
+}
+
+static const struct header_ops vlan_passthru_header_ops = {
+ .create = vlan_passthru_hard_header,
+ .rebuild = dev_rebuild_header,
+ .parse = eth_header_parse,
+};
+
static struct device_type vlan_type = {
.name = "vlan",
};
@@ -573,7 +590,7 @@
dev->needed_headroom = real_dev->needed_headroom;
if (real_dev->features & NETIF_F_HW_VLAN_CTAG_TX) {
- dev->header_ops = real_dev->header_ops;
+ dev->header_ops = &vlan_passthru_header_ops;
dev->hard_header_len = real_dev->hard_header_len;
} else {
dev->header_ops = &vlan_header_ops;
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index a2b480a..b9c8a6e 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -307,9 +307,9 @@
hard_iface->bat_iv.ogm_buff = ogm_buff;
batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff;
- batadv_ogm_packet->header.packet_type = BATADV_IV_OGM;
- batadv_ogm_packet->header.version = BATADV_COMPAT_VERSION;
- batadv_ogm_packet->header.ttl = 2;
+ batadv_ogm_packet->packet_type = BATADV_IV_OGM;
+ batadv_ogm_packet->version = BATADV_COMPAT_VERSION;
+ batadv_ogm_packet->ttl = 2;
batadv_ogm_packet->flags = BATADV_NO_FLAGS;
batadv_ogm_packet->reserved = 0;
batadv_ogm_packet->tq = BATADV_TQ_MAX_VALUE;
@@ -346,7 +346,7 @@
batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff;
batadv_ogm_packet->flags = BATADV_PRIMARIES_FIRST_HOP;
- batadv_ogm_packet->header.ttl = BATADV_TTL;
+ batadv_ogm_packet->ttl = BATADV_TTL;
}
/* when do we schedule our own ogm to be sent */
@@ -435,7 +435,7 @@
fwd_str, (packet_num > 0 ? "aggregated " : ""),
batadv_ogm_packet->orig,
ntohl(batadv_ogm_packet->seqno),
- batadv_ogm_packet->tq, batadv_ogm_packet->header.ttl,
+ batadv_ogm_packet->tq, batadv_ogm_packet->ttl,
(batadv_ogm_packet->flags & BATADV_DIRECTLINK ?
"on" : "off"),
hard_iface->net_dev->name,
@@ -491,7 +491,7 @@
/* multihomed peer assumed
* non-primary OGMs are only broadcasted on their interface
*/
- if ((directlink && (batadv_ogm_packet->header.ttl == 1)) ||
+ if ((directlink && (batadv_ogm_packet->ttl == 1)) ||
(forw_packet->own && (forw_packet->if_incoming != primary_if))) {
/* FIXME: what about aggregated packets ? */
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
@@ -499,7 +499,7 @@
(forw_packet->own ? "Sending own" : "Forwarding"),
batadv_ogm_packet->orig,
ntohl(batadv_ogm_packet->seqno),
- batadv_ogm_packet->header.ttl,
+ batadv_ogm_packet->ttl,
forw_packet->if_incoming->net_dev->name,
forw_packet->if_incoming->net_dev->dev_addr);
@@ -572,7 +572,7 @@
*/
if ((!directlink) &&
(!(batadv_ogm_packet->flags & BATADV_DIRECTLINK)) &&
- (batadv_ogm_packet->header.ttl != 1) &&
+ (batadv_ogm_packet->ttl != 1) &&
/* own packets originating non-primary
* interfaces leave only that interface
@@ -587,7 +587,7 @@
* interface only - we still can aggregate
*/
if ((directlink) &&
- (new_bat_ogm_packet->header.ttl == 1) &&
+ (new_bat_ogm_packet->ttl == 1) &&
(forw_packet->if_incoming == if_incoming) &&
/* packets from direct neighbors or
@@ -778,7 +778,7 @@
struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
uint16_t tvlv_len;
- if (batadv_ogm_packet->header.ttl <= 1) {
+ if (batadv_ogm_packet->ttl <= 1) {
batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "ttl exceeded\n");
return;
}
@@ -798,7 +798,7 @@
tvlv_len = ntohs(batadv_ogm_packet->tvlv_len);
- batadv_ogm_packet->header.ttl--;
+ batadv_ogm_packet->ttl--;
memcpy(batadv_ogm_packet->prev_sender, ethhdr->h_source, ETH_ALEN);
/* apply hop penalty */
@@ -807,7 +807,7 @@
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
"Forwarding packet: tq: %i, ttl: %i\n",
- batadv_ogm_packet->tq, batadv_ogm_packet->header.ttl);
+ batadv_ogm_packet->tq, batadv_ogm_packet->ttl);
/* switch of primaries first hop flag when forwarding */
batadv_ogm_packet->flags &= ~BATADV_PRIMARIES_FIRST_HOP;
@@ -972,8 +972,8 @@
spin_unlock_bh(&neigh_node->bat_iv.lq_update_lock);
if (dup_status == BATADV_NO_DUP) {
- orig_node->last_ttl = batadv_ogm_packet->header.ttl;
- neigh_node->last_ttl = batadv_ogm_packet->header.ttl;
+ orig_node->last_ttl = batadv_ogm_packet->ttl;
+ neigh_node->last_ttl = batadv_ogm_packet->ttl;
}
batadv_bonding_candidate_add(bat_priv, orig_node, neigh_node);
@@ -1247,7 +1247,7 @@
* packet in an aggregation. Here we expect that the padding
* is always zero (or not 0x01)
*/
- if (batadv_ogm_packet->header.packet_type != BATADV_IV_OGM)
+ if (batadv_ogm_packet->packet_type != BATADV_IV_OGM)
return;
/* could be changed by schedule_own_packet() */
@@ -1267,8 +1267,8 @@
if_incoming->net_dev->dev_addr, batadv_ogm_packet->orig,
batadv_ogm_packet->prev_sender,
ntohl(batadv_ogm_packet->seqno), batadv_ogm_packet->tq,
- batadv_ogm_packet->header.ttl,
- batadv_ogm_packet->header.version, has_directlink_flag);
+ batadv_ogm_packet->ttl,
+ batadv_ogm_packet->version, has_directlink_flag);
rcu_read_lock();
list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
@@ -1433,7 +1433,7 @@
* seqno and similar ttl as the non-duplicate
*/
sameseq = orig_node->last_real_seqno == ntohl(batadv_ogm_packet->seqno);
- similar_ttl = orig_node->last_ttl - 3 <= batadv_ogm_packet->header.ttl;
+ similar_ttl = orig_node->last_ttl - 3 <= batadv_ogm_packet->ttl;
if (is_bidirect && ((dup_status == BATADV_NO_DUP) ||
(sameseq && similar_ttl)))
batadv_iv_ogm_orig_update(bat_priv, orig_node, ethhdr,
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 6c8c393..b316a4c 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -349,7 +349,7 @@
unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data;
- switch (unicast_4addr_packet->u.header.packet_type) {
+ switch (unicast_4addr_packet->u.packet_type) {
case BATADV_UNICAST:
batadv_dbg(BATADV_DBG_DAT, bat_priv,
"* encapsulated within a UNICAST packet\n");
@@ -374,7 +374,7 @@
break;
default:
batadv_dbg(BATADV_DBG_DAT, bat_priv, "* type: Unknown (%u)!\n",
- unicast_4addr_packet->u.header.packet_type);
+ unicast_4addr_packet->u.packet_type);
}
break;
case BATADV_BCAST:
@@ -387,7 +387,7 @@
default:
batadv_dbg(BATADV_DBG_DAT, bat_priv,
"* encapsulated within an unknown packet type (0x%x)\n",
- unicast_4addr_packet->u.header.packet_type);
+ unicast_4addr_packet->u.packet_type);
}
}
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 271d321..6ddb614 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -355,7 +355,7 @@
batadv_add_counter(bat_priv, BATADV_CNT_FRAG_FWD_BYTES,
skb->len + ETH_HLEN);
- packet->header.ttl--;
+ packet->ttl--;
batadv_send_skb_packet(skb, neigh_node->if_incoming,
neigh_node->addr);
ret = true;
@@ -444,9 +444,9 @@
goto out_err;
/* Create one header to be copied to all fragments */
- frag_header.header.packet_type = BATADV_UNICAST_FRAG;
- frag_header.header.version = BATADV_COMPAT_VERSION;
- frag_header.header.ttl = BATADV_TTL;
+ frag_header.packet_type = BATADV_UNICAST_FRAG;
+ frag_header.version = BATADV_COMPAT_VERSION;
+ frag_header.ttl = BATADV_TTL;
frag_header.seqno = htons(atomic_inc_return(&bat_priv->frag_seqno));
frag_header.reserved = 0;
frag_header.no = 0;
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c
index 29ae4ef..130cc32 100644
--- a/net/batman-adv/icmp_socket.c
+++ b/net/batman-adv/icmp_socket.c
@@ -194,7 +194,7 @@
goto free_skb;
}
- if (icmp_header->header.packet_type != BATADV_ICMP) {
+ if (icmp_header->packet_type != BATADV_ICMP) {
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
"Error - can't send packet from char device: got bogus packet type (expected: BAT_ICMP)\n");
len = -EINVAL;
@@ -243,9 +243,9 @@
icmp_header->uid = socket_client->index;
- if (icmp_header->header.version != BATADV_COMPAT_VERSION) {
+ if (icmp_header->version != BATADV_COMPAT_VERSION) {
icmp_header->msg_type = BATADV_PARAMETER_PROBLEM;
- icmp_header->header.version = BATADV_COMPAT_VERSION;
+ icmp_header->version = BATADV_COMPAT_VERSION;
batadv_socket_add_packet(socket_client, icmp_header,
packet_len);
goto free_skb;
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index c51a5e5..1511f64 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -383,17 +383,17 @@
batadv_ogm_packet = (struct batadv_ogm_packet *)skb->data;
- if (batadv_ogm_packet->header.version != BATADV_COMPAT_VERSION) {
+ if (batadv_ogm_packet->version != BATADV_COMPAT_VERSION) {
batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
"Drop packet: incompatible batman version (%i)\n",
- batadv_ogm_packet->header.version);
+ batadv_ogm_packet->version);
goto err_free;
}
/* all receive handlers return whether they received or reused
* the supplied skb. if not, we have to free the skb.
*/
- idx = batadv_ogm_packet->header.packet_type;
+ idx = batadv_ogm_packet->packet_type;
ret = (*batadv_rx_handler[idx])(skb, hard_iface);
if (ret == NET_RX_DROP)
@@ -426,8 +426,8 @@
BUILD_BUG_ON(offsetof(struct batadv_unicast_packet, dest) != 4);
BUILD_BUG_ON(offsetof(struct batadv_unicast_tvlv_packet, dst) != 4);
BUILD_BUG_ON(offsetof(struct batadv_frag_packet, dest) != 4);
- BUILD_BUG_ON(offsetof(struct batadv_icmp_packet, icmph.dst) != 4);
- BUILD_BUG_ON(offsetof(struct batadv_icmp_packet_rr, icmph.dst) != 4);
+ BUILD_BUG_ON(offsetof(struct batadv_icmp_packet, dst) != 4);
+ BUILD_BUG_ON(offsetof(struct batadv_icmp_packet_rr, dst) != 4);
/* broadcast packet */
batadv_rx_handler[BATADV_BCAST] = batadv_recv_bcast_packet;
@@ -1119,9 +1119,9 @@
skb_reserve(skb, ETH_HLEN);
tvlv_buff = skb_put(skb, sizeof(*unicast_tvlv_packet) + tvlv_len);
unicast_tvlv_packet = (struct batadv_unicast_tvlv_packet *)tvlv_buff;
- unicast_tvlv_packet->header.packet_type = BATADV_UNICAST_TVLV;
- unicast_tvlv_packet->header.version = BATADV_COMPAT_VERSION;
- unicast_tvlv_packet->header.ttl = BATADV_TTL;
+ unicast_tvlv_packet->packet_type = BATADV_UNICAST_TVLV;
+ unicast_tvlv_packet->version = BATADV_COMPAT_VERSION;
+ unicast_tvlv_packet->ttl = BATADV_TTL;
unicast_tvlv_packet->reserved = 0;
unicast_tvlv_packet->tvlv_len = htons(tvlv_len);
unicast_tvlv_packet->align = 0;
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 351e199..511d7e1 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -722,7 +722,7 @@
{
if (orig_node->last_real_seqno != ntohl(ogm_packet->seqno))
return false;
- if (orig_node->last_ttl != ogm_packet->header.ttl + 1)
+ if (orig_node->last_ttl != ogm_packet->ttl + 1)
return false;
if (!batadv_compare_eth(ogm_packet->orig, ogm_packet->prev_sender))
return false;
@@ -1082,9 +1082,9 @@
coded_packet = (struct batadv_coded_packet *)skb_dest->data;
skb_reset_mac_header(skb_dest);
- coded_packet->header.packet_type = BATADV_CODED;
- coded_packet->header.version = BATADV_COMPAT_VERSION;
- coded_packet->header.ttl = packet1->header.ttl;
+ coded_packet->packet_type = BATADV_CODED;
+ coded_packet->version = BATADV_COMPAT_VERSION;
+ coded_packet->ttl = packet1->ttl;
/* Info about first unicast packet */
memcpy(coded_packet->first_source, first_source, ETH_ALEN);
@@ -1097,7 +1097,7 @@
memcpy(coded_packet->second_source, second_source, ETH_ALEN);
memcpy(coded_packet->second_orig_dest, packet2->dest, ETH_ALEN);
coded_packet->second_crc = packet_id2;
- coded_packet->second_ttl = packet2->header.ttl;
+ coded_packet->second_ttl = packet2->ttl;
coded_packet->second_ttvn = packet2->ttvn;
coded_packet->coded_len = htons(coding_len);
@@ -1452,7 +1452,7 @@
/* We only handle unicast packets */
payload = skb_network_header(skb);
packet = (struct batadv_unicast_packet *)payload;
- if (packet->header.packet_type != BATADV_UNICAST)
+ if (packet->packet_type != BATADV_UNICAST)
goto out;
/* Try to find a coding opportunity and send the skb if one is found */
@@ -1505,7 +1505,7 @@
/* Check for supported packet type */
payload = skb_network_header(skb);
packet = (struct batadv_unicast_packet *)payload;
- if (packet->header.packet_type != BATADV_UNICAST)
+ if (packet->packet_type != BATADV_UNICAST)
goto out;
/* Find existing nc_path or create a new */
@@ -1623,7 +1623,7 @@
ttvn = coded_packet_tmp.second_ttvn;
} else {
orig_dest = coded_packet_tmp.first_orig_dest;
- ttl = coded_packet_tmp.header.ttl;
+ ttl = coded_packet_tmp.ttl;
ttvn = coded_packet_tmp.first_ttvn;
}
@@ -1648,9 +1648,9 @@
/* Create decoded unicast packet */
unicast_packet = (struct batadv_unicast_packet *)skb->data;
- unicast_packet->header.packet_type = BATADV_UNICAST;
- unicast_packet->header.version = BATADV_COMPAT_VERSION;
- unicast_packet->header.ttl = ttl;
+ unicast_packet->packet_type = BATADV_UNICAST;
+ unicast_packet->version = BATADV_COMPAT_VERSION;
+ unicast_packet->ttl = ttl;
memcpy(unicast_packet->dest, orig_dest, ETH_ALEN);
unicast_packet->ttvn = ttvn;
diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h
index 207459b..2dd8f24 100644
--- a/net/batman-adv/packet.h
+++ b/net/batman-adv/packet.h
@@ -155,6 +155,7 @@
BATADV_TVLV_ROAM = 0x05,
};
+#pragma pack(2)
/* the destination hardware field in the ARP frame is used to
* transport the claim type and the group id
*/
@@ -163,24 +164,20 @@
uint8_t type; /* bla_claimframe */
__be16 group; /* group id */
};
-
-struct batadv_header {
- uint8_t packet_type;
- uint8_t version; /* batman version field */
- uint8_t ttl;
- /* the parent struct has to add a byte after the header to make
- * everything 4 bytes aligned again
- */
-};
+#pragma pack()
/**
* struct batadv_ogm_packet - ogm (routing protocol) packet
- * @header: common batman packet header
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
* @flags: contains routing relevant flags - see enum batadv_iv_flags
* @tvlv_len: length of tvlv data following the ogm header
*/
struct batadv_ogm_packet {
- struct batadv_header header;
+ uint8_t packet_type;
+ uint8_t version;
+ uint8_t ttl;
uint8_t flags;
__be32 seqno;
uint8_t orig[ETH_ALEN];
@@ -196,29 +193,51 @@
#define BATADV_OGM_HLEN sizeof(struct batadv_ogm_packet)
/**
- * batadv_icmp_header - common ICMP header
- * @header: common batman header
+ * batadv_icmp_header - common members among all the ICMP packets
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
* @msg_type: ICMP packet type
* @dst: address of the destination node
* @orig: address of the source node
* @uid: local ICMP socket identifier
+ * @align: not used - useful for alignment purposes only
+ *
+ * This structure is used for ICMP packets parsing only and it is never sent
+ * over the wire. The alignment field at the end is there to ensure that
+ * members are padded the same way as they are in real packets.
*/
struct batadv_icmp_header {
- struct batadv_header header;
+ uint8_t packet_type;
+ uint8_t version;
+ uint8_t ttl;
uint8_t msg_type; /* see ICMP message types above */
uint8_t dst[ETH_ALEN];
uint8_t orig[ETH_ALEN];
uint8_t uid;
+ uint8_t align[3];
};
/**
* batadv_icmp_packet - ICMP packet
- * @icmph: common ICMP header
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
+ * @msg_type: ICMP packet type
+ * @dst: address of the destination node
+ * @orig: address of the source node
+ * @uid: local ICMP socket identifier
* @reserved: not used - useful for alignment
* @seqno: ICMP sequence number
*/
struct batadv_icmp_packet {
- struct batadv_icmp_header icmph;
+ uint8_t packet_type;
+ uint8_t version;
+ uint8_t ttl;
+ uint8_t msg_type; /* see ICMP message types above */
+ uint8_t dst[ETH_ALEN];
+ uint8_t orig[ETH_ALEN];
+ uint8_t uid;
uint8_t reserved;
__be16 seqno;
};
@@ -227,13 +246,25 @@
/**
* batadv_icmp_packet_rr - ICMP RouteRecord packet
- * @icmph: common ICMP header
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
+ * @msg_type: ICMP packet type
+ * @dst: address of the destination node
+ * @orig: address of the source node
+ * @uid: local ICMP socket identifier
* @rr_cur: number of entries the rr array
* @seqno: ICMP sequence number
* @rr: route record array
*/
struct batadv_icmp_packet_rr {
- struct batadv_icmp_header icmph;
+ uint8_t packet_type;
+ uint8_t version;
+ uint8_t ttl;
+ uint8_t msg_type; /* see ICMP message types above */
+ uint8_t dst[ETH_ALEN];
+ uint8_t orig[ETH_ALEN];
+ uint8_t uid;
uint8_t rr_cur;
__be16 seqno;
uint8_t rr[BATADV_RR_LEN][ETH_ALEN];
@@ -253,8 +284,18 @@
*/
#pragma pack(2)
+/**
+ * struct batadv_unicast_packet - unicast packet for network payload
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
+ * @ttvn: translation table version number
+ * @dest: originator destination of the unicast packet
+ */
struct batadv_unicast_packet {
- struct batadv_header header;
+ uint8_t packet_type;
+ uint8_t version;
+ uint8_t ttl;
uint8_t ttvn; /* destination translation table version number */
uint8_t dest[ETH_ALEN];
/* "4 bytes boundary + 2 bytes" long to make the payload after the
@@ -280,7 +321,9 @@
/**
* struct batadv_frag_packet - fragmented packet
- * @header: common batman packet header with type, compatversion, and ttl
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
* @dest: final destination used when routing fragments
* @orig: originator of the fragment used when merging the packet
* @no: fragment number within this sequence
@@ -289,7 +332,9 @@
* @total_size: size of the merged packet
*/
struct batadv_frag_packet {
- struct batadv_header header;
+ uint8_t packet_type;
+ uint8_t version; /* batman version field */
+ uint8_t ttl;
#if defined(__BIG_ENDIAN_BITFIELD)
uint8_t no:4;
uint8_t reserved:4;
@@ -305,8 +350,19 @@
__be16 total_size;
};
+/**
+ * struct batadv_bcast_packet - broadcast packet for network payload
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
+ * @reserved: reserved byte for alignment
+ * @seqno: sequence identification
+ * @orig: originator of the broadcast packet
+ */
struct batadv_bcast_packet {
- struct batadv_header header;
+ uint8_t packet_type;
+ uint8_t version; /* batman version field */
+ uint8_t ttl;
uint8_t reserved;
__be32 seqno;
uint8_t orig[ETH_ALEN];
@@ -315,11 +371,11 @@
*/
};
-#pragma pack()
-
/**
* struct batadv_coded_packet - network coded packet
- * @header: common batman packet header and ttl of first included packet
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
* @reserved: Align following fields to 2-byte boundaries
* @first_source: original source of first included packet
* @first_orig_dest: original destinal of first included packet
@@ -334,7 +390,9 @@
* @coded_len: length of network coded part of the payload
*/
struct batadv_coded_packet {
- struct batadv_header header;
+ uint8_t packet_type;
+ uint8_t version; /* batman version field */
+ uint8_t ttl;
uint8_t first_ttvn;
/* uint8_t first_dest[ETH_ALEN]; - saved in mac header destination */
uint8_t first_source[ETH_ALEN];
@@ -349,9 +407,13 @@
__be16 coded_len;
};
+#pragma pack()
+
/**
* struct batadv_unicast_tvlv - generic unicast packet with tvlv payload
- * @header: common batman packet header
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
* @reserved: reserved field (for packet alignment)
* @src: address of the source
* @dst: address of the destination
@@ -359,7 +421,9 @@
* @align: 2 bytes to align the header to a 4 byte boundry
*/
struct batadv_unicast_tvlv_packet {
- struct batadv_header header;
+ uint8_t packet_type;
+ uint8_t version; /* batman version field */
+ uint8_t ttl;
uint8_t reserved;
uint8_t dst[ETH_ALEN];
uint8_t src[ETH_ALEN];
@@ -420,13 +484,13 @@
* struct batadv_tvlv_tt_change - translation table diff data
* @flags: status indicators concerning the non-mesh client (see
* batadv_tt_client_flags)
- * @reserved: reserved field
+ * @reserved: reserved field - useful for alignment purposes only
* @addr: mac address of non-mesh client that triggered this tt change
* @vid: VLAN identifier
*/
struct batadv_tvlv_tt_change {
uint8_t flags;
- uint8_t reserved;
+ uint8_t reserved[3];
uint8_t addr[ETH_ALEN];
__be16 vid;
};
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index d4114d7..46278bf 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -308,7 +308,7 @@
memcpy(icmph->dst, icmph->orig, ETH_ALEN);
memcpy(icmph->orig, primary_if->net_dev->dev_addr, ETH_ALEN);
icmph->msg_type = BATADV_ECHO_REPLY;
- icmph->header.ttl = BATADV_TTL;
+ icmph->ttl = BATADV_TTL;
res = batadv_send_skb_to_orig(skb, orig_node, NULL);
if (res != NET_XMIT_DROP)
@@ -338,9 +338,9 @@
icmp_packet = (struct batadv_icmp_packet *)skb->data;
/* send TTL exceeded if packet is an echo request (traceroute) */
- if (icmp_packet->icmph.msg_type != BATADV_ECHO_REQUEST) {
+ if (icmp_packet->msg_type != BATADV_ECHO_REQUEST) {
pr_debug("Warning - can't forward icmp packet from %pM to %pM: ttl exceeded\n",
- icmp_packet->icmph.orig, icmp_packet->icmph.dst);
+ icmp_packet->orig, icmp_packet->dst);
goto out;
}
@@ -349,7 +349,7 @@
goto out;
/* get routing information */
- orig_node = batadv_orig_hash_find(bat_priv, icmp_packet->icmph.orig);
+ orig_node = batadv_orig_hash_find(bat_priv, icmp_packet->orig);
if (!orig_node)
goto out;
@@ -359,11 +359,11 @@
icmp_packet = (struct batadv_icmp_packet *)skb->data;
- memcpy(icmp_packet->icmph.dst, icmp_packet->icmph.orig, ETH_ALEN);
- memcpy(icmp_packet->icmph.orig, primary_if->net_dev->dev_addr,
+ memcpy(icmp_packet->dst, icmp_packet->orig, ETH_ALEN);
+ memcpy(icmp_packet->orig, primary_if->net_dev->dev_addr,
ETH_ALEN);
- icmp_packet->icmph.msg_type = BATADV_TTL_EXCEEDED;
- icmp_packet->icmph.header.ttl = BATADV_TTL;
+ icmp_packet->msg_type = BATADV_TTL_EXCEEDED;
+ icmp_packet->ttl = BATADV_TTL;
if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP)
ret = NET_RX_SUCCESS;
@@ -434,7 +434,7 @@
return batadv_recv_my_icmp_packet(bat_priv, skb);
/* TTL exceeded */
- if (icmph->header.ttl < 2)
+ if (icmph->ttl < 2)
return batadv_recv_icmp_ttl_exceeded(bat_priv, skb);
/* get routing information */
@@ -449,7 +449,7 @@
icmph = (struct batadv_icmp_header *)skb->data;
/* decrement ttl */
- icmph->header.ttl--;
+ icmph->ttl--;
/* route it */
if (batadv_send_skb_to_orig(skb, orig_node, recv_if) != NET_XMIT_DROP)
@@ -709,7 +709,7 @@
unicast_packet = (struct batadv_unicast_packet *)skb->data;
/* TTL exceeded */
- if (unicast_packet->header.ttl < 2) {
+ if (unicast_packet->ttl < 2) {
pr_debug("Warning - can't forward unicast packet from %pM to %pM: ttl exceeded\n",
ethhdr->h_source, unicast_packet->dest);
goto out;
@@ -727,9 +727,9 @@
/* decrement ttl */
unicast_packet = (struct batadv_unicast_packet *)skb->data;
- unicast_packet->header.ttl--;
+ unicast_packet->ttl--;
- switch (unicast_packet->header.packet_type) {
+ switch (unicast_packet->packet_type) {
case BATADV_UNICAST_4ADDR:
hdr_len = sizeof(struct batadv_unicast_4addr_packet);
break;
@@ -970,7 +970,7 @@
unicast_packet = (struct batadv_unicast_packet *)skb->data;
unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data;
- is4addr = unicast_packet->header.packet_type == BATADV_UNICAST_4ADDR;
+ is4addr = unicast_packet->packet_type == BATADV_UNICAST_4ADDR;
/* the caller function should have already pulled 2 bytes */
if (is4addr)
hdr_size = sizeof(*unicast_4addr_packet);
@@ -1160,7 +1160,7 @@
if (batadv_is_my_mac(bat_priv, bcast_packet->orig))
goto out;
- if (bcast_packet->header.ttl < 2)
+ if (bcast_packet->ttl < 2)
goto out;
orig_node = batadv_orig_hash_find(bat_priv, bcast_packet->orig);
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index c83be5e..fba4dcf 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -161,11 +161,11 @@
return false;
unicast_packet = (struct batadv_unicast_packet *)skb->data;
- unicast_packet->header.version = BATADV_COMPAT_VERSION;
+ unicast_packet->version = BATADV_COMPAT_VERSION;
/* batman packet type: unicast */
- unicast_packet->header.packet_type = BATADV_UNICAST;
+ unicast_packet->packet_type = BATADV_UNICAST;
/* set unicast ttl */
- unicast_packet->header.ttl = BATADV_TTL;
+ unicast_packet->ttl = BATADV_TTL;
/* copy the destination for faster routing */
memcpy(unicast_packet->dest, orig_node->orig, ETH_ALEN);
/* set the destination tt version number */
@@ -221,7 +221,7 @@
goto out;
uc_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data;
- uc_4addr_packet->u.header.packet_type = BATADV_UNICAST_4ADDR;
+ uc_4addr_packet->u.packet_type = BATADV_UNICAST_4ADDR;
memcpy(uc_4addr_packet->src, primary_if->net_dev->dev_addr, ETH_ALEN);
uc_4addr_packet->subtype = packet_subtype;
uc_4addr_packet->reserved = 0;
@@ -436,7 +436,7 @@
/* as we have a copy now, it is safe to decrease the TTL */
bcast_packet = (struct batadv_bcast_packet *)newskb->data;
- bcast_packet->header.ttl--;
+ bcast_packet->ttl--;
skb_reset_mac_header(newskb);
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 36f0508..a8f99d1 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -264,11 +264,11 @@
goto dropped;
bcast_packet = (struct batadv_bcast_packet *)skb->data;
- bcast_packet->header.version = BATADV_COMPAT_VERSION;
- bcast_packet->header.ttl = BATADV_TTL;
+ bcast_packet->version = BATADV_COMPAT_VERSION;
+ bcast_packet->ttl = BATADV_TTL;
/* batman packet type: broadcast */
- bcast_packet->header.packet_type = BATADV_BCAST;
+ bcast_packet->packet_type = BATADV_BCAST;
bcast_packet->reserved = 0;
/* hw address of first interface is the orig mac because only
@@ -328,7 +328,7 @@
struct sk_buff *skb, struct batadv_hard_iface *recv_if,
int hdr_size, struct batadv_orig_node *orig_node)
{
- struct batadv_header *batadv_header = (struct batadv_header *)skb->data;
+ struct batadv_bcast_packet *batadv_bcast_packet;
struct batadv_priv *bat_priv = netdev_priv(soft_iface);
__be16 ethertype = htons(ETH_P_BATMAN);
struct vlan_ethhdr *vhdr;
@@ -336,7 +336,8 @@
unsigned short vid;
bool is_bcast;
- is_bcast = (batadv_header->packet_type == BATADV_BCAST);
+ batadv_bcast_packet = (struct batadv_bcast_packet *)skb->data;
+ is_bcast = (batadv_bcast_packet->packet_type == BATADV_BCAST);
/* check if enough space is available for pulling, and pull */
if (!pskb_may_pull(skb, hdr_size))
@@ -345,7 +346,12 @@
skb_pull_rcsum(skb, hdr_size);
skb_reset_mac_header(skb);
- vid = batadv_get_vid(skb, hdr_size);
+ /* clean the netfilter state now that the batman-adv header has been
+ * removed
+ */
+ nf_reset(skb);
+
+ vid = batadv_get_vid(skb, 0);
ethhdr = eth_hdr(skb);
switch (ntohs(ethhdr->h_proto)) {
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 4add57d..ff625fe 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -333,7 +333,8 @@
return;
tt_change_node->change.flags = flags;
- tt_change_node->change.reserved = 0;
+ memset(tt_change_node->change.reserved, 0,
+ sizeof(tt_change_node->change.reserved));
memcpy(tt_change_node->change.addr, common->addr, ETH_ALEN);
tt_change_node->change.vid = htons(common->vid);
@@ -2221,7 +2222,8 @@
ETH_ALEN);
tt_change->flags = tt_common_entry->flags;
tt_change->vid = htons(tt_common_entry->vid);
- tt_change->reserved = 0;
+ memset(tt_change->reserved, 0,
+ sizeof(tt_change->reserved));
tt_num_entries++;
tt_change++;
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 6a6c8bb..7552f9e 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -940,8 +940,22 @@
bt_cb(skb)->pkt_type = *((unsigned char *) skb->data);
skb_pull(skb, 1);
- if (hci_pi(sk)->channel == HCI_CHANNEL_RAW &&
- bt_cb(skb)->pkt_type == HCI_COMMAND_PKT) {
+ if (hci_pi(sk)->channel == HCI_CHANNEL_USER) {
+ /* No permission check is needed for user channel
+ * since that gets enforced when binding the socket.
+ *
+ * However check that the packet type is valid.
+ */
+ if (bt_cb(skb)->pkt_type != HCI_COMMAND_PKT &&
+ bt_cb(skb)->pkt_type != HCI_ACLDATA_PKT &&
+ bt_cb(skb)->pkt_type != HCI_SCODATA_PKT) {
+ err = -EINVAL;
+ goto drop;
+ }
+
+ skb_queue_tail(&hdev->raw_q, skb);
+ queue_work(hdev->workqueue, &hdev->tx_work);
+ } else if (bt_cb(skb)->pkt_type == HCI_COMMAND_PKT) {
u16 opcode = get_unaligned_le16(skb->data);
u16 ogf = hci_opcode_ogf(opcode);
u16 ocf = hci_opcode_ocf(opcode);
@@ -972,14 +986,6 @@
goto drop;
}
- if (hci_pi(sk)->channel == HCI_CHANNEL_USER &&
- bt_cb(skb)->pkt_type != HCI_COMMAND_PKT &&
- bt_cb(skb)->pkt_type != HCI_ACLDATA_PKT &&
- bt_cb(skb)->pkt_type != HCI_SCODATA_PKT) {
- err = -EINVAL;
- goto drop;
- }
-
skb_queue_tail(&hdev->raw_q, skb);
queue_work(hdev->workqueue, &hdev->tx_work);
}
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 4c214b2..ef66365 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1998,7 +1998,7 @@
u32 old;
struct net_bridge_mdb_htable *mdb;
- spin_lock(&br->multicast_lock);
+ spin_lock_bh(&br->multicast_lock);
if (!netif_running(br->dev))
goto unlock;
@@ -2030,7 +2030,7 @@
}
unlock:
- spin_unlock(&br->multicast_lock);
+ spin_unlock_bh(&br->multicast_lock);
return err;
}
diff --git a/net/core/dev.c b/net/core/dev.c
index ba3b7ea..0ce469e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2539,7 +2539,7 @@
}
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
- struct netdev_queue *txq, void *accel_priv)
+ struct netdev_queue *txq)
{
const struct net_device_ops *ops = dev->netdev_ops;
int rc = NETDEV_TX_OK;
@@ -2605,13 +2605,10 @@
dev_queue_xmit_nit(skb, dev);
skb_len = skb->len;
- if (accel_priv)
- rc = ops->ndo_dfwd_start_xmit(skb, dev, accel_priv);
- else
rc = ops->ndo_start_xmit(skb, dev);
trace_net_dev_xmit(skb, rc, dev, skb_len);
- if (rc == NETDEV_TX_OK && txq)
+ if (rc == NETDEV_TX_OK)
txq_trans_update(txq);
return rc;
}
@@ -2627,10 +2624,7 @@
dev_queue_xmit_nit(nskb, dev);
skb_len = nskb->len;
- if (accel_priv)
- rc = ops->ndo_dfwd_start_xmit(nskb, dev, accel_priv);
- else
- rc = ops->ndo_start_xmit(nskb, dev);
+ rc = ops->ndo_start_xmit(nskb, dev);
trace_net_dev_xmit(nskb, rc, dev, skb_len);
if (unlikely(rc != NETDEV_TX_OK)) {
if (rc & ~NETDEV_TX_MASK)
@@ -2811,7 +2805,7 @@
* the BH enable code must have IRQs enabled so that it will not deadlock.
* --BLG
*/
-int dev_queue_xmit(struct sk_buff *skb)
+int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
{
struct net_device *dev = skb->dev;
struct netdev_queue *txq;
@@ -2827,7 +2821,7 @@
skb_update_prio(skb);
- txq = netdev_pick_tx(dev, skb);
+ txq = netdev_pick_tx(dev, skb, accel_priv);
q = rcu_dereference_bh(txq->qdisc);
#ifdef CONFIG_NET_CLS_ACT
@@ -2863,7 +2857,7 @@
if (!netif_xmit_stopped(txq)) {
__this_cpu_inc(xmit_recursion);
- rc = dev_hard_start_xmit(skb, dev, txq, NULL);
+ rc = dev_hard_start_xmit(skb, dev, txq);
__this_cpu_dec(xmit_recursion);
if (dev_xmit_complete(rc)) {
HARD_TX_UNLOCK(dev, txq);
@@ -2892,8 +2886,19 @@
rcu_read_unlock_bh();
return rc;
}
+
+int dev_queue_xmit(struct sk_buff *skb)
+{
+ return __dev_queue_xmit(skb, NULL);
+}
EXPORT_SYMBOL(dev_queue_xmit);
+int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
+{
+ return __dev_queue_xmit(skb, accel_priv);
+}
+EXPORT_SYMBOL(dev_queue_xmit_accel);
+
/*=======================================================================
Receiver routines
@@ -4500,7 +4505,7 @@
{
struct netdev_adjacent *upper;
- WARN_ON_ONCE(!rcu_read_lock_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d6ef173..2fc5bea 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -395,17 +395,21 @@
EXPORT_SYMBOL(__netdev_pick_tx);
struct netdev_queue *netdev_pick_tx(struct net_device *dev,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ void *accel_priv)
{
int queue_index = 0;
if (dev->real_num_tx_queues != 1) {
const struct net_device_ops *ops = dev->netdev_ops;
if (ops->ndo_select_queue)
- queue_index = ops->ndo_select_queue(dev, skb);
+ queue_index = ops->ndo_select_queue(dev, skb,
+ accel_priv);
else
queue_index = __netdev_pick_tx(dev, skb);
- queue_index = dev_cap_txqueue(dev, queue_index);
+
+ if (!accel_priv)
+ queue_index = dev_cap_txqueue(dev, queue_index);
}
skb_set_queue_mapping(skb, queue_index);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index ca15f32..932c6d7 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1161,6 +1161,7 @@
neigh->parms->reachable_time :
0)));
neigh->nud_state = new;
+ notify = 1;
}
if (lladdr != neigh->ha) {
@@ -1274,7 +1275,7 @@
if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL,
skb->len) < 0 &&
- dev->header_ops->rebuild(skb))
+ dev_rebuild_header(skb))
return 0;
return dev_queue_xmit(skb);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 8f97199..19fe9c7 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -375,7 +375,7 @@
if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) {
struct netdev_queue *txq;
- txq = netdev_pick_tx(dev, skb);
+ txq = netdev_pick_tx(dev, skb, NULL);
/* try until next clock tick */
for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
@@ -386,8 +386,14 @@
!vlan_hw_offload_capable(netif_skb_features(skb),
skb->vlan_proto)) {
skb = __vlan_put_tag(skb, skb->vlan_proto, vlan_tx_tag_get(skb));
- if (unlikely(!skb))
- break;
+ if (unlikely(!skb)) {
+ /* This is actually a packet drop, but we
+ * don't want the code at the end of this
+ * function to try and re-queue a NULL skb.
+ */
+ status = NETDEV_TX_OK;
+ goto unlock_txq;
+ }
skb->vlan_tci = 0;
}
@@ -395,6 +401,7 @@
if (status == NETDEV_TX_OK)
txq_trans_update(txq);
}
+ unlock_txq:
__netif_tx_unlock(txq);
if (status == NETDEV_TX_OK)
diff --git a/net/dccp/probe.c b/net/dccp/probe.c
index 4c6bdf9..595ddf0 100644
--- a/net/dccp/probe.c
+++ b/net/dccp/probe.c
@@ -152,17 +152,6 @@
.llseek = noop_llseek,
};
-static __init int setup_jprobe(void)
-{
- int ret = register_jprobe(&dccp_send_probe);
-
- if (ret) {
- request_module("dccp");
- ret = register_jprobe(&dccp_send_probe);
- }
- return ret;
-}
-
static __init int dccpprobe_init(void)
{
int ret = -ENOMEM;
@@ -174,7 +163,13 @@
if (!proc_create(procname, S_IRUSR, init_net.proc_net, &dccpprobe_fops))
goto err0;
- ret = setup_jprobe();
+ ret = register_jprobe(&dccp_send_probe);
+ if (ret) {
+ ret = request_module("dccp");
+ if (!ret)
+ ret = register_jprobe(&dccp_send_probe);
+ }
+
if (ret)
goto err1;
diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c
index 459e200..a2d2456 100644
--- a/net/ieee802154/6lowpan.c
+++ b/net/ieee802154/6lowpan.c
@@ -547,7 +547,7 @@
hc06_ptr += 3;
} else {
/* compress nothing */
- memcpy(hc06_ptr, &hdr, 4);
+ memcpy(hc06_ptr, hdr, 4);
/* replace the top byte with new ECN | DSCP format */
*hc06_ptr = tmp;
hc06_ptr += 4;
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index e5d4361..2cd02f3 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -28,6 +28,7 @@
netdev_features_t enc_features;
int ghl = GRE_HEADER_SECTION;
struct gre_base_hdr *greh;
+ u16 mac_offset = skb->mac_header;
int mac_len = skb->mac_len;
__be16 protocol = skb->protocol;
int tnl_hlen;
@@ -58,13 +59,13 @@
} else
csum = false;
+ if (unlikely(!pskb_may_pull(skb, ghl)))
+ goto out;
+
/* setup inner skb. */
skb->protocol = greh->protocol;
skb->encapsulation = 0;
- if (unlikely(!pskb_may_pull(skb, ghl)))
- goto out;
-
__skb_pull(skb, ghl);
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb_inner_network_offset(skb));
@@ -73,8 +74,10 @@
/* segment inner packet. */
enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
segs = skb_mac_gso_segment(skb, enc_features);
- if (!segs || IS_ERR(segs))
+ if (!segs || IS_ERR(segs)) {
+ skb_gso_error_unwind(skb, protocol, ghl, mac_offset, mac_len);
goto out;
+ }
skb = segs;
tnl_hlen = skb_tnl_header_len(skb);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 56a964a..a0f52da 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -106,6 +106,10 @@
r->id.idiag_sport = inet->inet_sport;
r->id.idiag_dport = inet->inet_dport;
+
+ memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+ memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
r->id.idiag_src[0] = inet->inet_rcv_saddr;
r->id.idiag_dst[0] = inet->inet_daddr;
@@ -240,12 +244,19 @@
r->idiag_family = tw->tw_family;
r->idiag_retrans = 0;
+
r->id.idiag_if = tw->tw_bound_dev_if;
sock_diag_save_cookie(tw, r->id.idiag_cookie);
+
r->id.idiag_sport = tw->tw_sport;
r->id.idiag_dport = tw->tw_dport;
+
+ memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+ memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
r->id.idiag_src[0] = tw->tw_rcv_saddr;
r->id.idiag_dst[0] = tw->tw_daddr;
+
r->idiag_state = tw->tw_substate;
r->idiag_timer = 3;
r->idiag_expires = jiffies_to_msecs(tmo);
@@ -726,8 +737,13 @@
r->id.idiag_sport = inet->inet_sport;
r->id.idiag_dport = ireq->ir_rmt_port;
+
+ memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+ memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
r->id.idiag_src[0] = ireq->ir_loc_addr;
r->id.idiag_dst[0] = ireq->ir_rmt_addr;
+
r->idiag_expires = jiffies_to_msecs(tmo);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index d7aea4c..e560ef3 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -217,6 +217,7 @@
iph->saddr, iph->daddr, tpi->key);
if (tunnel) {
+ skb_pop_mac_header(skb);
ip_tunnel_rcv(tunnel, skb, tpi, log_ecn_error);
return PACKET_RCVD;
}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 9124027..df18461 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -828,7 +828,7 @@
if (cork->length + length > maxnonfragsize - fragheaderlen) {
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
- mtu-exthdrlen);
+ mtu - (opt ? opt->optlen : 0));
return -EMSGSIZE;
}
@@ -1151,7 +1151,8 @@
mtu : 0xFFFF;
if (cork->length + size > maxnonfragsize - fragheaderlen) {
- ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu);
+ ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
+ mtu - (opt ? opt->optlen : 0));
return -EMSGSIZE;
}
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index f13bd91..a313c3f 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -423,6 +423,7 @@
static struct xt_target synproxy_tg4_reg __read_mostly = {
.name = "SYNPROXY",
.family = NFPROTO_IPV4,
+ .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD),
.target = synproxy_tg4,
.targetsize = sizeof(struct xt_synproxy_info),
.checkentry = synproxy_tg4_check,
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
index fff5ba1..4a5e94a 100644
--- a/net/ipv4/netfilter/nft_reject_ipv4.c
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -72,7 +72,7 @@
{
const struct nft_reject *priv = nft_expr_priv(expr);
- if (nla_put_be32(skb, NFTA_REJECT_TYPE, priv->type))
+ if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type)))
goto nla_put_failure;
switch (priv->type) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 62c19fd..a7e4729 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1600,20 +1600,15 @@
}
/* For TCP sockets, sk_rx_dst is protected by socket lock
- * For UDP, we use sk_dst_lock to guard against concurrent changes.
+ * For UDP, we use xchg() to guard against concurrent changes.
*/
static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
{
struct dst_entry *old;
- spin_lock(&sk->sk_dst_lock);
- old = sk->sk_rx_dst;
- if (likely(old != dst)) {
- dst_hold(dst);
- sk->sk_rx_dst = dst;
- dst_release(old);
- }
- spin_unlock(&sk->sk_dst_lock);
+ dst_hold(dst);
+ old = xchg(&sk->sk_rx_dst, dst);
+ dst_release(old);
}
/*
@@ -2483,6 +2478,7 @@
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
+ u16 mac_offset = skb->mac_header;
int mac_len = skb->mac_len;
int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
__be16 protocol = skb->protocol;
@@ -2502,8 +2498,11 @@
/* segment inner packet. */
enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
segs = skb_mac_gso_segment(skb, enc_features);
- if (!segs || IS_ERR(segs))
+ if (!segs || IS_ERR(segs)) {
+ skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
+ mac_len);
goto out;
+ }
outer_hlen = skb_tnl_header_len(skb);
skb = segs;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 83206de..79c62bd 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -41,6 +41,14 @@
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
unsigned int mss;
+ int offset;
+ __wsum csum;
+
+ if (skb->encapsulation &&
+ skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL) {
+ segs = skb_udp_tunnel_segment(skb, features);
+ goto out;
+ }
mss = skb_shinfo(skb)->gso_size;
if (unlikely(skb->len <= mss))
@@ -63,27 +71,20 @@
goto out;
}
+ /* Do software UFO. Complete and fill in the UDP checksum as
+ * HW cannot do checksum of UDP packets sent as multiple
+ * IP fragments.
+ */
+ offset = skb_checksum_start_offset(skb);
+ csum = skb_checksum(skb, offset, skb->len - offset, 0);
+ offset += skb->csum_offset;
+ *(__sum16 *)(skb->data + offset) = csum_fold(csum);
+ skb->ip_summed = CHECKSUM_NONE;
+
/* Fragment the skb. IP headers of the fragments are updated in
* inet_gso_segment()
*/
- if (skb->encapsulation && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL)
- segs = skb_udp_tunnel_segment(skb, features);
- else {
- int offset;
- __wsum csum;
-
- /* Do software UFO. Complete and fill in the UDP checksum as
- * HW cannot do checksum of UDP packets sent as multiple
- * IP fragments.
- */
- offset = skb_checksum_start_offset(skb);
- csum = skb_checksum(skb, offset, skb->len - offset, 0);
- offset += skb->csum_offset;
- *(__sum16 *)(skb->data + offset) = csum_fold(csum);
- skb->ip_summed = CHECKSUM_NONE;
-
- segs = skb_segment(skb, features);
- }
+ segs = skb_segment(skb, features);
out:
return segs;
}
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index d5fa5b8..abe46a4 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1671,7 +1671,7 @@
static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
{
struct in6_addr addr;
- if (ifp->prefix_len == 127) /* RFC 6164 */
+ if (ifp->prefix_len >= 127) /* RFC 6164 */
return;
ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
if (ipv6_addr_any(&addr))
@@ -1682,7 +1682,7 @@
static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
{
struct in6_addr addr;
- if (ifp->prefix_len == 127) /* RFC 6164 */
+ if (ifp->prefix_len >= 127) /* RFC 6164 */
return;
ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
if (ipv6_addr_any(&addr))
@@ -2509,7 +2509,8 @@
struct inet6_ifaddr *ifp;
ifp = ipv6_add_addr(idev, addr, NULL, plen,
- scope, IFA_F_PERMANENT, 0, 0);
+ scope, IFA_F_PERMANENT,
+ INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
if (!IS_ERR(ifp)) {
spin_lock_bh(&ifp->lock);
ifp->flags &= ~IFA_F_TENTATIVE;
@@ -2637,7 +2638,8 @@
#endif
- ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, 0, 0);
+ ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags,
+ INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
if (!IS_ERR(ifp)) {
addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0);
addrconf_dad_start(ifp);
@@ -3456,7 +3458,12 @@
&inet6_addr_lst[i], addr_lst) {
unsigned long age;
- if (ifp->flags & IFA_F_PERMANENT)
+ /* When setting preferred_lft to a value not zero or
+ * infinity, while valid_lft is infinity
+ * IFA_F_PERMANENT has a non-infinity life time.
+ */
+ if ((ifp->flags & IFA_F_PERMANENT) &&
+ (ifp->prefered_lft == INFINITY_LIFE_TIME))
continue;
spin_lock(&ifp->lock);
@@ -3481,7 +3488,8 @@
ifp->flags |= IFA_F_DEPRECATED;
}
- if (time_before(ifp->tstamp + ifp->valid_lft * HZ, next))
+ if ((ifp->valid_lft != INFINITY_LIFE_TIME) &&
+ (time_before(ifp->tstamp + ifp->valid_lft * HZ, next)))
next = ifp->tstamp + ifp->valid_lft * HZ;
spin_unlock(&ifp->lock);
@@ -3761,7 +3769,8 @@
put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope),
ifa->idev->dev->ifindex);
- if (!(ifa->flags&IFA_F_PERMANENT)) {
+ if (!((ifa->flags&IFA_F_PERMANENT) &&
+ (ifa->prefered_lft == INFINITY_LIFE_TIME))) {
preferred = ifa->prefered_lft;
valid = ifa->valid_lft;
if (preferred != INFINITY_LIFE_TIME) {
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 4acdb63..e6f9319 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1193,11 +1193,35 @@
fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
(opt ? opt->opt_nflen : 0);
- maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
+ maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen -
+ sizeof(struct frag_hdr);
if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
- if (cork->length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
- ipv6_local_error(sk, EMSGSIZE, fl6, mtu-exthdrlen);
+ unsigned int maxnonfragsize, headersize;
+
+ headersize = sizeof(struct ipv6hdr) +
+ (opt ? opt->tot_len : 0) +
+ (dst_allfrag(&rt->dst) ?
+ sizeof(struct frag_hdr) : 0) +
+ rt->rt6i_nfheader_len;
+
+ maxnonfragsize = (np->pmtudisc >= IPV6_PMTUDISC_DO) ?
+ mtu : sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
+
+ /* dontfrag active */
+ if ((cork->length + length > mtu - headersize) && dontfrag &&
+ (sk->sk_protocol == IPPROTO_UDP ||
+ sk->sk_protocol == IPPROTO_RAW)) {
+ ipv6_local_rxpmtu(sk, fl6, mtu - headersize +
+ sizeof(struct ipv6hdr));
+ goto emsgsize;
+ }
+
+ if (cork->length + length > maxnonfragsize - headersize) {
+emsgsize:
+ ipv6_local_error(sk, EMSGSIZE, fl6,
+ mtu - headersize +
+ sizeof(struct ipv6hdr));
return -EMSGSIZE;
}
}
@@ -1222,12 +1246,6 @@
* --yoshfuji
*/
- if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP ||
- sk->sk_protocol == IPPROTO_RAW)) {
- ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
- return -EMSGSIZE;
- }
-
skb = skb_peek_tail(&sk->sk_write_queue);
cork->length += length;
if (((length > mtu) ||
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index d606232..7881965 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -103,16 +103,25 @@
static struct net_device_stats *ip6_get_stats(struct net_device *dev)
{
- struct pcpu_tstats sum = { 0 };
+ struct pcpu_tstats tmp, sum = { 0 };
int i;
for_each_possible_cpu(i) {
+ unsigned int start;
const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
- sum.rx_packets += tstats->rx_packets;
- sum.rx_bytes += tstats->rx_bytes;
- sum.tx_packets += tstats->tx_packets;
- sum.tx_bytes += tstats->tx_bytes;
+ do {
+ start = u64_stats_fetch_begin_bh(&tstats->syncp);
+ tmp.rx_packets = tstats->rx_packets;
+ tmp.rx_bytes = tstats->rx_bytes;
+ tmp.tx_packets = tstats->tx_packets;
+ tmp.tx_bytes = tstats->tx_bytes;
+ } while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
+
+ sum.rx_packets += tmp.rx_packets;
+ sum.rx_bytes += tmp.rx_bytes;
+ sum.tx_packets += tmp.tx_packets;
+ sum.tx_bytes += tmp.tx_bytes;
}
dev->stats.rx_packets = sum.rx_packets;
dev->stats.rx_bytes = sum.rx_bytes;
@@ -824,8 +833,10 @@
}
tstats = this_cpu_ptr(t->dev->tstats);
+ u64_stats_update_begin(&tstats->syncp);
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
+ u64_stats_update_end(&tstats->syncp);
netif_rx(skb);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index ed94ba6..7b42d5e 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -75,26 +75,6 @@
struct ip6_tnl __rcu **tnls[2];
};
-static struct net_device_stats *vti6_get_stats(struct net_device *dev)
-{
- struct pcpu_tstats sum = { 0 };
- int i;
-
- for_each_possible_cpu(i) {
- const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
-
- sum.rx_packets += tstats->rx_packets;
- sum.rx_bytes += tstats->rx_bytes;
- sum.tx_packets += tstats->tx_packets;
- sum.tx_bytes += tstats->tx_bytes;
- }
- dev->stats.rx_packets = sum.rx_packets;
- dev->stats.rx_bytes = sum.rx_bytes;
- dev->stats.tx_packets = sum.tx_packets;
- dev->stats.tx_bytes = sum.tx_bytes;
- return &dev->stats;
-}
-
#define for_each_vti6_tunnel_rcu(start) \
for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
@@ -331,8 +311,10 @@
}
tstats = this_cpu_ptr(t->dev->tstats);
+ u64_stats_update_begin(&tstats->syncp);
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
+ u64_stats_update_end(&tstats->syncp);
skb->mark = 0;
secpath_reset(skb);
@@ -716,7 +698,7 @@
.ndo_start_xmit = vti6_tnl_xmit,
.ndo_do_ioctl = vti6_ioctl,
.ndo_change_mtu = vti6_change_mtu,
- .ndo_get_stats = vti6_get_stats,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
};
/**
@@ -750,12 +732,18 @@
static inline int vti6_dev_init_gen(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
+ int i;
t->dev = dev;
t->net = dev_net(dev);
dev->tstats = alloc_percpu(struct pcpu_tstats);
if (!dev->tstats)
return -ENOMEM;
+ for_each_possible_cpu(i) {
+ struct pcpu_tstats *stats;
+ stats = per_cpu_ptr(dev->tstats, i);
+ u64_stats_init(&stats->syncp);
+ }
return 0;
}
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index f78f41a..a0d1727 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -446,6 +446,7 @@
static struct xt_target synproxy_tg6_reg __read_mostly = {
.name = "SYNPROXY",
.family = NFPROTO_IPV6,
+ .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD),
.target = synproxy_tg6,
.targetsize = sizeof(struct xt_synproxy_info),
.checkentry = synproxy_tg6_check,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a0a48ac..4b4944c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1905,9 +1905,7 @@
else
rt->rt6i_gateway = *dest;
rt->rt6i_flags = ort->rt6i_flags;
- if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) ==
- (RTF_DEFAULT | RTF_ADDRCONF))
- rt6_set_from(rt, ort);
+ rt6_set_from(rt, ort);
rt->rt6i_metric = 0;
#ifdef CONFIG_IPV6_SUBTREES
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 366fbba..d3005b3 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -702,8 +702,10 @@
}
tstats = this_cpu_ptr(tunnel->dev->tstats);
+ u64_stats_update_begin(&tstats->syncp);
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
+ u64_stats_update_end(&tstats->syncp);
netif_rx(skb);
@@ -924,7 +926,7 @@
if (tunnel->parms.iph.daddr && skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
- if (skb->len > mtu) {
+ if (skb->len > mtu && !skb_is_gso(skb)) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
ip_rt_put(rt);
goto tx_error;
@@ -966,8 +968,10 @@
tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
skb = iptunnel_handle_offloads(skb, false, SKB_GSO_SIT);
- if (IS_ERR(skb))
+ if (IS_ERR(skb)) {
+ ip_rt_put(rt);
goto out;
+ }
err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, IPPROTO_IPV6, tos,
ttl, df, !net_eq(tunnel->net, dev_net(dev)));
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 7b01b9f..c71b699 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -715,7 +715,7 @@
unsigned long cpu_flags;
size_t copied = 0;
u32 peek_seq = 0;
- u32 *seq;
+ u32 *seq, skb_len;
unsigned long used;
int target; /* Read at least this many bytes */
long timeo;
@@ -812,6 +812,7 @@
}
continue;
found_ok_skb:
+ skb_len = skb->len;
/* Ok so how much can we use? */
used = skb->len - offset;
if (len < used)
@@ -844,7 +845,7 @@
}
/* Partial read */
- if (used + offset < skb->len)
+ if (used + offset < skb_len)
continue;
} while (len > 0);
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 36c3a4c..a075791 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1061,7 +1061,8 @@
}
static u16 ieee80211_netdev_select_queue(struct net_device *dev,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ void *accel_priv)
{
return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb);
}
@@ -1078,7 +1079,8 @@
};
static u16 ieee80211_monitor_select_queue(struct net_device *dev,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ void *accel_priv)
{
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
struct ieee80211_local *local = sdata->local;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index c558b24..ca7fa7f 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -463,7 +463,6 @@
{
struct sta_info *sta = tx->sta;
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
- struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
struct ieee80211_local *local = tx->local;
if (unlikely(!sta))
@@ -474,15 +473,6 @@
!(info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER))) {
int ac = skb_get_queue_mapping(tx->skb);
- /* only deauth, disassoc and action are bufferable MMPDUs */
- if (ieee80211_is_mgmt(hdr->frame_control) &&
- !ieee80211_is_deauth(hdr->frame_control) &&
- !ieee80211_is_disassoc(hdr->frame_control) &&
- !ieee80211_is_action(hdr->frame_control)) {
- info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER;
- return TX_CONTINUE;
- }
-
ps_dbg(sta->sdata, "STA %pM aid %d: PS buffer for AC %d\n",
sta->sta.addr, sta->sta.aid, ac);
if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER)
@@ -525,9 +515,22 @@
static ieee80211_tx_result debug_noinline
ieee80211_tx_h_ps_buf(struct ieee80211_tx_data *tx)
{
+ struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
+ struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
+
if (unlikely(tx->flags & IEEE80211_TX_PS_BUFFERED))
return TX_CONTINUE;
+ /* only deauth, disassoc and action are bufferable MMPDUs */
+ if (ieee80211_is_mgmt(hdr->frame_control) &&
+ !ieee80211_is_deauth(hdr->frame_control) &&
+ !ieee80211_is_disassoc(hdr->frame_control) &&
+ !ieee80211_is_action(hdr->frame_control)) {
+ if (tx->flags & IEEE80211_TX_UNICAST)
+ info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER;
+ return TX_CONTINUE;
+ }
+
if (tx->flags & IEEE80211_TX_UNICAST)
return ieee80211_tx_h_unicast_ps_buf(tx);
else
diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c
index c8beafd..5a355a4 100644
--- a/net/netfilter/ipvs/ip_vs_nfct.c
+++ b/net/netfilter/ipvs/ip_vs_nfct.c
@@ -63,6 +63,7 @@
#include <net/ip_vs.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_expect.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_zones.h>
@@ -97,6 +98,11 @@
if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
return;
+ /* Applications may adjust TCP seqs */
+ if (cp->app && nf_ct_protonum(ct) == IPPROTO_TCP &&
+ !nfct_seqadj(ct) && !nfct_seqadj_ext_add(ct))
+ return;
+
/*
* The connection is not yet in the hashtable, so we update it.
* CIP->VIP will remain the same, so leave the tuple in
diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c
index 17c1bcb..f6e2ae9 100644
--- a/net/netfilter/nf_conntrack_seqadj.c
+++ b/net/netfilter/nf_conntrack_seqadj.c
@@ -36,6 +36,11 @@
if (off == 0)
return 0;
+ if (unlikely(!seqadj)) {
+ WARN_ONCE(1, "Missing nfct_seqadj_ext_add() setup call\n");
+ return 0;
+ }
+
set_bit(IPS_SEQ_ADJUST_BIT, &ct->status);
spin_lock_bh(&ct->lock);
diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c
index 902fb0a..7a394df 100644
--- a/net/netfilter/nf_conntrack_timestamp.c
+++ b/net/netfilter/nf_conntrack_timestamp.c
@@ -97,7 +97,6 @@
void nf_conntrack_tstamp_pernet_fini(struct net *net)
{
nf_conntrack_tstamp_fini_sysctl(net);
- nf_ct_extend_unregister(&tstamp_extend);
}
int nf_conntrack_tstamp_init(void)
diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c
index f02b360..1fb2258 100644
--- a/net/netfilter/nf_nat_irc.c
+++ b/net/netfilter/nf_nat_irc.c
@@ -34,10 +34,14 @@
struct nf_conntrack_expect *exp)
{
char buffer[sizeof("4294967296 65635")];
+ struct nf_conn *ct = exp->master;
+ union nf_inet_addr newaddr;
u_int16_t port;
unsigned int ret;
/* Reply comes from server. */
+ newaddr = ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3;
+
exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port;
exp->dir = IP_CT_DIR_REPLY;
exp->expectfn = nf_nat_follow_master;
@@ -57,17 +61,35 @@
}
if (port == 0) {
- nf_ct_helper_log(skb, exp->master, "all ports in use");
+ nf_ct_helper_log(skb, ct, "all ports in use");
return NF_DROP;
}
- ret = nf_nat_mangle_tcp_packet(skb, exp->master, ctinfo,
- protoff, matchoff, matchlen, buffer,
- strlen(buffer));
+ /* strlen("\1DCC CHAT chat AAAAAAAA P\1\n")=27
+ * strlen("\1DCC SCHAT chat AAAAAAAA P\1\n")=28
+ * strlen("\1DCC SEND F AAAAAAAA P S\1\n")=26
+ * strlen("\1DCC MOVE F AAAAAAAA P S\1\n")=26
+ * strlen("\1DCC TSEND F AAAAAAAA P S\1\n")=27
+ *
+ * AAAAAAAAA: bound addr (1.0.0.0==16777216, min 8 digits,
+ * 255.255.255.255==4294967296, 10 digits)
+ * P: bound port (min 1 d, max 5d (65635))
+ * F: filename (min 1 d )
+ * S: size (min 1 d )
+ * 0x01, \n: terminators
+ */
+ /* AAA = "us", ie. where server normally talks to. */
+ snprintf(buffer, sizeof(buffer), "%u %u", ntohl(newaddr.ip), port);
+ pr_debug("nf_nat_irc: inserting '%s' == %pI4, port %u\n",
+ buffer, &newaddr.ip, port);
+
+ ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, matchoff,
+ matchlen, buffer, strlen(buffer));
if (ret != NF_ACCEPT) {
- nf_ct_helper_log(skb, exp->master, "cannot mangle packet");
+ nf_ct_helper_log(skb, ct, "cannot mangle packet");
nf_ct_unexpect_related(exp);
}
+
return ret;
}
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index f93b7d0..71a9f49 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -312,6 +312,9 @@
int err, i = 0;
list_for_each_entry(chain, &table->chains, list) {
+ if (!(chain->flags & NFT_BASE_CHAIN))
+ continue;
+
err = nf_register_hook(&nft_base_chain(chain)->ops);
if (err < 0)
goto err;
@@ -321,6 +324,9 @@
return 0;
err:
list_for_each_entry(chain, &table->chains, list) {
+ if (!(chain->flags & NFT_BASE_CHAIN))
+ continue;
+
if (i-- <= 0)
break;
@@ -333,8 +339,10 @@
{
struct nft_chain *chain;
- list_for_each_entry(chain, &table->chains, list)
- nf_unregister_hook(&nft_base_chain(chain)->ops);
+ list_for_each_entry(chain, &table->chains, list) {
+ if (chain->flags & NFT_BASE_CHAIN)
+ nf_unregister_hook(&nft_base_chain(chain)->ops);
+ }
return 0;
}
@@ -2098,17 +2106,21 @@
struct netlink_callback *cb)
{
const struct nft_set *set;
- unsigned int idx = 0, s_idx = cb->args[0];
+ unsigned int idx, s_idx = cb->args[0];
struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2];
if (cb->args[1])
return skb->len;
list_for_each_entry(table, &ctx->afi->tables, list) {
- if (cur_table && cur_table != table)
- continue;
+ if (cur_table) {
+ if (cur_table != table)
+ continue;
+ cur_table = NULL;
+ }
ctx->table = table;
+ idx = 0;
list_for_each_entry(set, &ctx->table->sets, list) {
if (idx < s_idx)
goto cont;
@@ -2370,7 +2382,9 @@
enum nft_registers dreg;
dreg = nft_type_to_reg(set->dtype);
- return nft_validate_data_load(ctx, dreg, &elem->data, set->dtype);
+ return nft_validate_data_load(ctx, dreg, &elem->data,
+ set->dtype == NFT_DATA_VERDICT ?
+ NFT_DATA_VERDICT : NFT_DATA_VALUE);
}
int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 3c4b69e..a155d19 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -1053,6 +1053,7 @@
#ifdef CONFIG_PROC_FS
remove_proc_entry("nfnetlink_log", net->nf.proc_netfilter);
#endif
+ nf_log_unset(net, &nfulnl_logger);
}
static struct pernet_operations nfnl_log_net_ops = {
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index 8e0bb75..55c939f 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -31,7 +31,7 @@
{
struct nft_exthdr *priv = nft_expr_priv(expr);
struct nft_data *dest = &data[priv->dreg];
- unsigned int offset;
+ unsigned int offset = 0;
int err;
err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL);
diff --git a/net/nfc/core.c b/net/nfc/core.c
index 8725291..83b9927 100644
--- a/net/nfc/core.c
+++ b/net/nfc/core.c
@@ -384,7 +384,7 @@
{
dev->dep_link_up = true;
- if (!dev->active_target) {
+ if (!dev->active_target && rf_mode == NFC_RF_INITIATOR) {
struct nfc_target *target;
target = nfc_find_target(dev, target_idx);
diff --git a/net/rds/ib.c b/net/rds/ib.c
index b4c8b00..ba2dffe 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -338,7 +338,8 @@
ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
/* due to this, we will claim to support iWARP devices unless we
check node_type. */
- if (ret || cm_id->device->node_type != RDMA_NODE_IB_CA)
+ if (ret || !cm_id->device ||
+ cm_id->device->node_type != RDMA_NODE_IB_CA)
ret = -EADDRNOTAVAIL;
rdsdebug("addr %pI4 ret %d node type %d\n",
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 33af772..62ced65 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1253,6 +1253,7 @@
if (msg->msg_name) {
struct sockaddr_rose *srose;
+ struct full_sockaddr_rose *full_srose = msg->msg_name;
memset(msg->msg_name, 0, sizeof(struct full_sockaddr_rose));
srose = msg->msg_name;
@@ -1260,18 +1261,9 @@
srose->srose_addr = rose->dest_addr;
srose->srose_call = rose->dest_call;
srose->srose_ndigis = rose->dest_ndigis;
- if (msg->msg_namelen >= sizeof(struct full_sockaddr_rose)) {
- struct full_sockaddr_rose *full_srose = (struct full_sockaddr_rose *)msg->msg_name;
- for (n = 0 ; n < rose->dest_ndigis ; n++)
- full_srose->srose_digis[n] = rose->dest_digis[n];
- msg->msg_namelen = sizeof(struct full_sockaddr_rose);
- } else {
- if (rose->dest_ndigis >= 1) {
- srose->srose_ndigis = 1;
- srose->srose_digi = rose->dest_digis[0];
- }
- msg->msg_namelen = sizeof(struct sockaddr_rose);
- }
+ for (n = 0 ; n < rose->dest_ndigis ; n++)
+ full_srose->srose_digis[n] = rose->dest_digis[n];
+ msg->msg_namelen = sizeof(struct full_sockaddr_rose);
}
skb_free_datagram(sk, skb);
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 5c5edf5..11fe1a4 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -77,16 +77,16 @@
&csum_idx_gen, &csum_hash_info);
if (IS_ERR(pc))
return PTR_ERR(pc);
- p = to_tcf_csum(pc);
ret = ACT_P_CREATED;
} else {
- p = to_tcf_csum(pc);
- if (!ovr) {
- tcf_hash_release(pc, bind, &csum_hash_info);
+ if (bind)/* dont override defaults */
+ return 0;
+ tcf_hash_release(pc, bind, &csum_hash_info);
+ if (!ovr)
return -EEXIST;
- }
}
+ p = to_tcf_csum(pc);
spin_lock_bh(&p->tcf_lock);
p->tcf_action = parm->action;
p->update_flags = parm->update_flags;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 5645a4d..eb9ba60 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -102,10 +102,11 @@
return PTR_ERR(pc);
ret = ACT_P_CREATED;
} else {
- if (!ovr) {
- tcf_hash_release(pc, bind, &gact_hash_info);
+ if (bind)/* dont override defaults */
+ return 0;
+ tcf_hash_release(pc, bind, &gact_hash_info);
+ if (!ovr)
return -EEXIST;
- }
}
gact = to_gact(pc);
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 882a897..dcbfe8c 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -141,10 +141,12 @@
return PTR_ERR(pc);
ret = ACT_P_CREATED;
} else {
- if (!ovr) {
- tcf_ipt_release(to_ipt(pc), bind);
+ if (bind)/* dont override defaults */
+ return 0;
+ tcf_ipt_release(to_ipt(pc), bind);
+
+ if (!ovr)
return -EEXIST;
- }
}
ipt = to_ipt(pc);
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 6a15ace..7686953 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -70,15 +70,15 @@
&nat_idx_gen, &nat_hash_info);
if (IS_ERR(pc))
return PTR_ERR(pc);
- p = to_tcf_nat(pc);
ret = ACT_P_CREATED;
} else {
- p = to_tcf_nat(pc);
- if (!ovr) {
- tcf_hash_release(pc, bind, &nat_hash_info);
+ if (bind)
+ return 0;
+ tcf_hash_release(pc, bind, &nat_hash_info);
+ if (!ovr)
return -EEXIST;
- }
}
+ p = to_tcf_nat(pc);
spin_lock_bh(&p->tcf_lock);
p->old_addr = parm->old_addr;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 03b6767..7aa2dcd 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -84,10 +84,12 @@
ret = ACT_P_CREATED;
} else {
p = to_pedit(pc);
- if (!ovr) {
- tcf_hash_release(pc, bind, &pedit_hash_info);
+ tcf_hash_release(pc, bind, &pedit_hash_info);
+ if (bind)
+ return 0;
+ if (!ovr)
return -EEXIST;
- }
+
if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) {
keys = kmalloc(ksize, GFP_KERNEL);
if (keys == NULL)
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 16a62c3..ef246d8 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -177,10 +177,12 @@
if (bind) {
police->tcf_bindcnt += 1;
police->tcf_refcnt += 1;
+ return 0;
}
if (ovr)
goto override;
- return ret;
+ /* not replacing */
+ return -EEXIST;
}
}
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 31157d3..f7b45ab 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -142,10 +142,13 @@
ret = ACT_P_CREATED;
} else {
d = to_defact(pc);
- if (!ovr) {
- tcf_simp_release(d, bind);
+
+ if (bind)
+ return 0;
+ tcf_simp_release(d, bind);
+ if (!ovr)
return -EEXIST;
- }
+
reset_policy(d, defdata, parm);
}
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 35ea643..8fe9d25 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -120,10 +120,11 @@
ret = ACT_P_CREATED;
} else {
d = to_skbedit(pc);
- if (!ovr) {
- tcf_hash_release(pc, bind, &skbedit_hash_info);
+ if (bind)
+ return 0;
+ tcf_hash_release(pc, bind, &skbedit_hash_info);
+ if (!ovr)
return -EEXIST;
- }
}
spin_lock_bh(&d->tcf_lock);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 922a094..7fc899a 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -126,7 +126,7 @@
HARD_TX_LOCK(dev, txq, smp_processor_id());
if (!netif_xmit_frozen_or_stopped(txq))
- ret = dev_hard_start_xmit(skb, dev, txq, NULL);
+ ret = dev_hard_start_xmit(skb, dev, txq);
HARD_TX_UNLOCK(dev, txq);
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index f51ba98..59268f6 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -208,8 +208,6 @@
INIT_LIST_HEAD(&q->retransmit);
INIT_LIST_HEAD(&q->sacked);
INIT_LIST_HEAD(&q->abandoned);
-
- q->empty = 1;
}
/* Free the outqueue structure and any related pending chunks.
@@ -332,7 +330,6 @@
SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS);
else
SCTP_INC_STATS(net, SCTP_MIB_OUTORDERCHUNKS);
- q->empty = 0;
break;
}
} else {
@@ -654,7 +651,6 @@
if (chunk->fast_retransmit == SCTP_NEED_FRTX)
chunk->fast_retransmit = SCTP_DONT_FRTX;
- q->empty = 0;
q->asoc->stats.rtxchunks++;
break;
}
@@ -1065,8 +1061,6 @@
sctp_transport_reset_timers(transport);
- q->empty = 0;
-
/* Only let one DATA chunk get bundled with a
* COOKIE-ECHO chunk.
*/
@@ -1275,29 +1269,17 @@
"advertised peer ack point:0x%x\n", __func__, asoc, ctsn,
asoc->adv_peer_ack_point);
- /* See if all chunks are acked.
- * Make sure the empty queue handler will get run later.
- */
- q->empty = (list_empty(&q->out_chunk_list) &&
- list_empty(&q->retransmit));
- if (!q->empty)
- goto finish;
-
- list_for_each_entry(transport, transport_list, transports) {
- q->empty = q->empty && list_empty(&transport->transmitted);
- if (!q->empty)
- goto finish;
- }
-
- pr_debug("%s: sack queue is empty\n", __func__);
-finish:
- return q->empty;
+ return sctp_outq_is_empty(q);
}
-/* Is the outqueue empty? */
+/* Is the outqueue empty?
+ * The queue is empty when we have not pending data, no in-flight data
+ * and nothing pending retransmissions.
+ */
int sctp_outq_is_empty(const struct sctp_outq *q)
{
- return q->empty;
+ return q->out_qlen == 0 && q->outstanding_bytes == 0 &&
+ list_empty(&q->retransmit);
}
/********************************************************************
diff --git a/net/sctp/probe.c b/net/sctp/probe.c
index 53c452e..5e68b94 100644
--- a/net/sctp/probe.c
+++ b/net/sctp/probe.c
@@ -38,6 +38,7 @@
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
+MODULE_SOFTDEP("pre: sctp");
MODULE_AUTHOR("Wei Yongjun <yjwei@cn.fujitsu.com>");
MODULE_DESCRIPTION("SCTP snooper");
MODULE_LICENSE("GPL");
@@ -182,6 +183,20 @@
.entry = jsctp_sf_eat_sack,
};
+static __init int sctp_setup_jprobe(void)
+{
+ int ret = register_jprobe(&sctp_recv_probe);
+
+ if (ret) {
+ if (request_module("sctp"))
+ goto out;
+ ret = register_jprobe(&sctp_recv_probe);
+ }
+
+out:
+ return ret;
+}
+
static __init int sctpprobe_init(void)
{
int ret = -ENOMEM;
@@ -202,7 +217,7 @@
&sctpprobe_fops))
goto free_kfifo;
- ret = register_jprobe(&sctp_recv_probe);
+ ret = sctp_setup_jprobe();
if (ret)
goto remove_proc;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 69cd9bf..13b9877 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1498,6 +1498,7 @@
int type;
head = head->next;
+ buf->next = NULL;
/* Ensure bearer is still enabled */
if (unlikely(!b_ptr->active))
diff --git a/net/tipc/port.c b/net/tipc/port.c
index c081a76..d43f318 100644
--- a/net/tipc/port.c
+++ b/net/tipc/port.c
@@ -251,18 +251,15 @@
return p_ptr;
}
-int tipc_deleteport(u32 ref)
+int tipc_deleteport(struct tipc_port *p_ptr)
{
- struct tipc_port *p_ptr;
struct sk_buff *buf = NULL;
- tipc_withdraw(ref, 0, NULL);
- p_ptr = tipc_port_lock(ref);
- if (!p_ptr)
- return -EINVAL;
+ tipc_withdraw(p_ptr, 0, NULL);
- tipc_ref_discard(ref);
- tipc_port_unlock(p_ptr);
+ spin_lock_bh(p_ptr->lock);
+ tipc_ref_discard(p_ptr->ref);
+ spin_unlock_bh(p_ptr->lock);
k_cancel_timer(&p_ptr->timer);
if (p_ptr->connected) {
@@ -704,47 +701,36 @@
}
-int tipc_publish(u32 ref, unsigned int scope, struct tipc_name_seq const *seq)
+int tipc_publish(struct tipc_port *p_ptr, unsigned int scope,
+ struct tipc_name_seq const *seq)
{
- struct tipc_port *p_ptr;
struct publication *publ;
u32 key;
- int res = -EINVAL;
-
- p_ptr = tipc_port_lock(ref);
- if (!p_ptr)
- return -EINVAL;
if (p_ptr->connected)
- goto exit;
- key = ref + p_ptr->pub_count + 1;
- if (key == ref) {
- res = -EADDRINUSE;
- goto exit;
- }
+ return -EINVAL;
+ key = p_ptr->ref + p_ptr->pub_count + 1;
+ if (key == p_ptr->ref)
+ return -EADDRINUSE;
+
publ = tipc_nametbl_publish(seq->type, seq->lower, seq->upper,
scope, p_ptr->ref, key);
if (publ) {
list_add(&publ->pport_list, &p_ptr->publications);
p_ptr->pub_count++;
p_ptr->published = 1;
- res = 0;
+ return 0;
}
-exit:
- tipc_port_unlock(p_ptr);
- return res;
+ return -EINVAL;
}
-int tipc_withdraw(u32 ref, unsigned int scope, struct tipc_name_seq const *seq)
+int tipc_withdraw(struct tipc_port *p_ptr, unsigned int scope,
+ struct tipc_name_seq const *seq)
{
- struct tipc_port *p_ptr;
struct publication *publ;
struct publication *tpubl;
int res = -EINVAL;
- p_ptr = tipc_port_lock(ref);
- if (!p_ptr)
- return -EINVAL;
if (!seq) {
list_for_each_entry_safe(publ, tpubl,
&p_ptr->publications, pport_list) {
@@ -771,7 +757,6 @@
}
if (list_empty(&p_ptr->publications))
p_ptr->published = 0;
- tipc_port_unlock(p_ptr);
return res;
}
diff --git a/net/tipc/port.h b/net/tipc/port.h
index 9122535..34f12bd 100644
--- a/net/tipc/port.h
+++ b/net/tipc/port.h
@@ -116,7 +116,7 @@
void tipc_acknowledge(u32 port_ref, u32 ack);
-int tipc_deleteport(u32 portref);
+int tipc_deleteport(struct tipc_port *p_ptr);
int tipc_portimportance(u32 portref, unsigned int *importance);
int tipc_set_portimportance(u32 portref, unsigned int importance);
@@ -127,9 +127,9 @@
int tipc_portunreturnable(u32 portref, unsigned int *isunreturnable);
int tipc_set_portunreturnable(u32 portref, unsigned int isunreturnable);
-int tipc_publish(u32 portref, unsigned int scope,
+int tipc_publish(struct tipc_port *p_ptr, unsigned int scope,
struct tipc_name_seq const *name_seq);
-int tipc_withdraw(u32 portref, unsigned int scope,
+int tipc_withdraw(struct tipc_port *p_ptr, unsigned int scope,
struct tipc_name_seq const *name_seq);
int tipc_connect(u32 portref, struct tipc_portid const *port);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3b61851..e741416 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -354,7 +354,7 @@
* Delete TIPC port; this ensures no more messages are queued
* (also disconnects an active connection & sends a 'FIN-' to peer)
*/
- res = tipc_deleteport(tport->ref);
+ res = tipc_deleteport(tport);
/* Discard any remaining (connection-based) messages in receive queue */
__skb_queue_purge(&sk->sk_receive_queue);
@@ -386,30 +386,46 @@
*/
static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len)
{
+ struct sock *sk = sock->sk;
struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
- u32 portref = tipc_sk_port(sock->sk)->ref;
+ struct tipc_port *tport = tipc_sk_port(sock->sk);
+ int res = -EINVAL;
- if (unlikely(!uaddr_len))
- return tipc_withdraw(portref, 0, NULL);
+ lock_sock(sk);
+ if (unlikely(!uaddr_len)) {
+ res = tipc_withdraw(tport, 0, NULL);
+ goto exit;
+ }
- if (uaddr_len < sizeof(struct sockaddr_tipc))
- return -EINVAL;
- if (addr->family != AF_TIPC)
- return -EAFNOSUPPORT;
+ if (uaddr_len < sizeof(struct sockaddr_tipc)) {
+ res = -EINVAL;
+ goto exit;
+ }
+ if (addr->family != AF_TIPC) {
+ res = -EAFNOSUPPORT;
+ goto exit;
+ }
if (addr->addrtype == TIPC_ADDR_NAME)
addr->addr.nameseq.upper = addr->addr.nameseq.lower;
- else if (addr->addrtype != TIPC_ADDR_NAMESEQ)
- return -EAFNOSUPPORT;
+ else if (addr->addrtype != TIPC_ADDR_NAMESEQ) {
+ res = -EAFNOSUPPORT;
+ goto exit;
+ }
if ((addr->addr.nameseq.type < TIPC_RESERVED_TYPES) &&
(addr->addr.nameseq.type != TIPC_TOP_SRV) &&
- (addr->addr.nameseq.type != TIPC_CFG_SRV))
- return -EACCES;
+ (addr->addr.nameseq.type != TIPC_CFG_SRV)) {
+ res = -EACCES;
+ goto exit;
+ }
- return (addr->scope > 0) ?
- tipc_publish(portref, addr->scope, &addr->addr.nameseq) :
- tipc_withdraw(portref, -addr->scope, &addr->addr.nameseq);
+ res = (addr->scope > 0) ?
+ tipc_publish(tport, addr->scope, &addr->addr.nameseq) :
+ tipc_withdraw(tport, -addr->scope, &addr->addr.nameseq);
+exit:
+ release_sock(sk);
+ return res;
}
/**
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index a0ca162..a427623 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -718,7 +718,9 @@
int err;
unsigned int retries = 0;
- mutex_lock(&u->readlock);
+ err = mutex_lock_interruptible(&u->readlock);
+ if (err)
+ return err;
err = 0;
if (u->addr)
@@ -877,7 +879,9 @@
goto out;
addr_len = err;
- mutex_lock(&u->readlock);
+ err = mutex_lock_interruptible(&u->readlock);
+ if (err)
+ goto out;
err = -EINVAL;
if (u->addr)
diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c
index a271c27..722da61 100644
--- a/net/wireless/radiotap.c
+++ b/net/wireless/radiotap.c
@@ -124,6 +124,10 @@
/* find payload start allowing for extended bitmap(s) */
if (iterator->_bitmap_shifter & (1<<IEEE80211_RADIOTAP_EXT)) {
+ if ((unsigned long)iterator->_arg -
+ (unsigned long)iterator->_rtheader + sizeof(uint32_t) >
+ (unsigned long)iterator->_max_length)
+ return -EINVAL;
while (get_unaligned_le32(iterator->_arg) &
(1 << IEEE80211_RADIOTAP_EXT)) {
iterator->_arg += sizeof(uint32_t);
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 65f8008..d3c5bd7 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -632,6 +632,16 @@
}
#endif
+ if (!bss && (status == WLAN_STATUS_SUCCESS)) {
+ WARN_ON_ONCE(!wiphy_to_dev(wdev->wiphy)->ops->connect);
+ bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid,
+ wdev->ssid, wdev->ssid_len,
+ WLAN_CAPABILITY_ESS,
+ WLAN_CAPABILITY_ESS);
+ if (bss)
+ cfg80211_hold_bss(bss_from_pub(bss));
+ }
+
if (wdev->current_bss) {
cfg80211_unhold_bss(wdev->current_bss);
cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub);
@@ -649,16 +659,8 @@
return;
}
- if (!bss) {
- WARN_ON_ONCE(!wiphy_to_dev(wdev->wiphy)->ops->connect);
- bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid,
- wdev->ssid, wdev->ssid_len,
- WLAN_CAPABILITY_ESS,
- WLAN_CAPABILITY_ESS);
- if (WARN_ON(!bss))
- return;
- cfg80211_hold_bss(bss_from_pub(bss));
- }
+ if (WARN_ON(!bss))
+ return;
wdev->current_bss = bss_from_pub(bss);
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 32b10f5..2dcb377 100644
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -82,7 +82,9 @@
kallsymopt="${kallsymopt} --all-symbols"
fi
- kallsymopt="${kallsymopt} --page-offset=$CONFIG_PAGE_OFFSET"
+ if [ -n "${CONFIG_ARM}" ] && [ -n "${CONFIG_PAGE_OFFSET}" ]; then
+ kallsymopt="${kallsymopt} --page-offset=$CONFIG_PAGE_OFFSET"
+ fi
local aflags="${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL} \
${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS}"
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 419491d..6625699 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4334,8 +4334,10 @@
}
err = avc_has_perm(sk_sid, peer_sid, SECCLASS_PEER,
PEER__RECV, &ad);
- if (err)
+ if (err) {
selinux_netlbl_err(skb, err, 0);
+ return err;
+ }
}
if (secmark_active) {
@@ -5586,11 +5588,11 @@
/* Check for ptracing, and update the task SID if ok.
Otherwise, leave SID unchanged and fail. */
ptsid = 0;
- task_lock(p);
+ rcu_read_lock();
tracer = ptrace_parent(p);
if (tracer)
ptsid = task_sid(tracer);
- task_unlock(p);
+ rcu_read_unlock();
if (tracer) {
error = avc_has_perm(ptsid, sid, SECCLASS_PROCESS,
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index 6e03b46..a210467 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -1937,6 +1937,8 @@
case SNDRV_PCM_STATE_DISCONNECTED:
err = -EBADFD;
goto _endloop;
+ case SNDRV_PCM_STATE_PAUSED:
+ continue;
}
if (!tout) {
snd_printd("%s write error (DMA or IRQ trouble?)\n",
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 27aa140..956871d 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -3433,6 +3433,10 @@
* white/black-list for enable_msi
*/
static struct snd_pci_quirk msi_black_list[] = {
+ SND_PCI_QUIRK(0x103c, 0x2191, "HP", 0), /* AMD Hudson */
+ SND_PCI_QUIRK(0x103c, 0x2192, "HP", 0), /* AMD Hudson */
+ SND_PCI_QUIRK(0x103c, 0x21f7, "HP", 0), /* AMD Hudson */
+ SND_PCI_QUIRK(0x103c, 0x21fa, "HP", 0), /* AMD Hudson */
SND_PCI_QUIRK(0x1043, 0x81f2, "ASUS", 0), /* Athlon64 X2 + nvidia */
SND_PCI_QUIRK(0x1043, 0x81f6, "ASUS", 0), /* nvidia */
SND_PCI_QUIRK(0x1043, 0x822d, "ASUS", 0), /* Athlon64 X2 + nvidia MCP55 */
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 34de5dc..c564694 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4247,12 +4247,16 @@
SND_PCI_QUIRK(0x1028, 0x0606, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0608, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0609, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x0610, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0613, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0614, "Dell Inspiron 3135", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_MONO_SPEAKERS),
SND_PCI_QUIRK(0x1028, 0x061f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x0629, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS),
+ SND_PCI_QUIRK(0x1028, 0x063e, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x063f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x0640, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x15cc, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x15cd, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c
index 8697ced..1ead3c9 100644
--- a/sound/soc/atmel/atmel_ssc_dai.c
+++ b/sound/soc/atmel/atmel_ssc_dai.c
@@ -648,7 +648,7 @@
dma_params = ssc_p->dma_params[dir];
- ssc_writel(ssc_p->ssc->regs, CR, dma_params->mask->ssc_enable);
+ ssc_writel(ssc_p->ssc->regs, CR, dma_params->mask->ssc_disable);
ssc_writel(ssc_p->ssc->regs, IDR, dma_params->mask->ssc_error);
pr_debug("%s enabled SSC_SR=0x%08x\n",
@@ -657,6 +657,33 @@
return 0;
}
+static int atmel_ssc_trigger(struct snd_pcm_substream *substream,
+ int cmd, struct snd_soc_dai *dai)
+{
+ struct atmel_ssc_info *ssc_p = &ssc_info[dai->id];
+ struct atmel_pcm_dma_params *dma_params;
+ int dir;
+
+ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+ dir = 0;
+ else
+ dir = 1;
+
+ dma_params = ssc_p->dma_params[dir];
+
+ switch (cmd) {
+ case SNDRV_PCM_TRIGGER_START:
+ case SNDRV_PCM_TRIGGER_RESUME:
+ case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+ ssc_writel(ssc_p->ssc->regs, CR, dma_params->mask->ssc_enable);
+ break;
+ default:
+ ssc_writel(ssc_p->ssc->regs, CR, dma_params->mask->ssc_disable);
+ break;
+ }
+
+ return 0;
+}
#ifdef CONFIG_PM
static int atmel_ssc_suspend(struct snd_soc_dai *cpu_dai)
@@ -731,6 +758,7 @@
.startup = atmel_ssc_startup,
.shutdown = atmel_ssc_shutdown,
.prepare = atmel_ssc_prepare,
+ .trigger = atmel_ssc_trigger,
.hw_params = atmel_ssc_hw_params,
.set_fmt = atmel_ssc_set_dai_fmt,
.set_clkdiv = atmel_ssc_set_dai_clkdiv,
diff --git a/sound/soc/atmel/sam9x5_wm8731.c b/sound/soc/atmel/sam9x5_wm8731.c
index 1b37228..7d6a905 100644
--- a/sound/soc/atmel/sam9x5_wm8731.c
+++ b/sound/soc/atmel/sam9x5_wm8731.c
@@ -109,7 +109,7 @@
dai->stream_name = "WM8731 PCM";
dai->codec_dai_name = "wm8731-hifi";
dai->init = sam9x5_wm8731_init;
- dai->dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
+ dai->dai_fmt = SND_SOC_DAIFMT_DSP_A | SND_SOC_DAIFMT_NB_NF
| SND_SOC_DAIFMT_CBM_CFM;
ret = snd_soc_of_parse_card_name(card, "atmel,model");
diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c
index 99b359e..0ab2dc2 100644
--- a/sound/soc/codecs/wm5110.c
+++ b/sound/soc/codecs/wm5110.c
@@ -1012,7 +1012,7 @@
{ "AEC Loopback", "HPOUT3L", "OUT3L" },
{ "AEC Loopback", "HPOUT3R", "OUT3R" },
{ "HPOUT3L", NULL, "OUT3L" },
- { "HPOUT3R", NULL, "OUT3L" },
+ { "HPOUT3R", NULL, "OUT3R" },
{ "AEC Loopback", "SPKOUTL", "OUT4L" },
{ "SPKOUTLN", NULL, "OUT4L" },
diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c
index 3938fb1..53bbfac 100644
--- a/sound/soc/codecs/wm8904.c
+++ b/sound/soc/codecs/wm8904.c
@@ -1444,7 +1444,7 @@
switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
case SND_SOC_DAIFMT_DSP_B:
- aif1 |= WM8904_AIF_LRCLK_INV;
+ aif1 |= 0x3 | WM8904_AIF_LRCLK_INV;
case SND_SOC_DAIFMT_DSP_A:
aif1 |= 0x3;
break;
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index 543c5c2..0f17ed3 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -2439,7 +2439,20 @@
snd_soc_update_bits(codec, WM8962_CLOCKING_4,
WM8962_SYSCLK_RATE_MASK, clocking4);
+ /* DSPCLK_DIV can be only generated correctly after enabling SYSCLK.
+ * So we here provisionally enable it and then disable it afterward
+ * if current bias_level hasn't reached SND_SOC_BIAS_ON.
+ */
+ if (codec->dapm.bias_level != SND_SOC_BIAS_ON)
+ snd_soc_update_bits(codec, WM8962_CLOCKING2,
+ WM8962_SYSCLK_ENA_MASK, WM8962_SYSCLK_ENA);
+
dspclk = snd_soc_read(codec, WM8962_CLOCKING1);
+
+ if (codec->dapm.bias_level != SND_SOC_BIAS_ON)
+ snd_soc_update_bits(codec, WM8962_CLOCKING2,
+ WM8962_SYSCLK_ENA_MASK, 0);
+
if (dspclk < 0) {
dev_err(codec->dev, "Failed to read DSPCLK: %d\n", dspclk);
return;
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 46ec0e9..4fbcab6 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1474,13 +1474,17 @@
return ret;
/* Wait for the RAM to start, should be near instantaneous */
- count = 0;
- do {
+ for (count = 0; count < 10; ++count) {
ret = regmap_read(dsp->regmap, dsp->base + ADSP2_STATUS1,
&val);
if (ret != 0)
return ret;
- } while (!(val & ADSP2_RAM_RDY) && ++count < 10);
+
+ if (val & ADSP2_RAM_RDY)
+ break;
+
+ msleep(1);
+ }
if (!(val & ADSP2_RAM_RDY)) {
adsp_err(dsp, "Failed to start DSP RAM\n");
diff --git a/sound/soc/fsl/imx-wm8962.c b/sound/soc/fsl/imx-wm8962.c
index 61e4885..3fd76bc 100644
--- a/sound/soc/fsl/imx-wm8962.c
+++ b/sound/soc/fsl/imx-wm8962.c
@@ -130,8 +130,6 @@
break;
}
- dapm->bias_level = level;
-
return 0;
}
diff --git a/sound/soc/kirkwood/kirkwood-i2s.c b/sound/soc/kirkwood/kirkwood-i2s.c
index 0b18f65..3920a5e 100644
--- a/sound/soc/kirkwood/kirkwood-i2s.c
+++ b/sound/soc/kirkwood/kirkwood-i2s.c
@@ -473,17 +473,17 @@
.playback = {
.channels_min = 1,
.channels_max = 2,
- .rates = SNDRV_PCM_RATE_8000_192000 |
- SNDRV_PCM_RATE_CONTINUOUS |
- SNDRV_PCM_RATE_KNOT,
+ .rates = SNDRV_PCM_RATE_CONTINUOUS,
+ .rate_min = 5512,
+ .rate_max = 192000,
.formats = KIRKWOOD_I2S_FORMATS,
},
.capture = {
.channels_min = 1,
.channels_max = 2,
- .rates = SNDRV_PCM_RATE_8000_192000 |
- SNDRV_PCM_RATE_CONTINUOUS |
- SNDRV_PCM_RATE_KNOT,
+ .rates = SNDRV_PCM_RATE_CONTINUOUS,
+ .rate_min = 5512,
+ .rate_max = 192000,
.formats = KIRKWOOD_I2S_FORMATS,
},
.ops = &kirkwood_i2s_dai_ops,
@@ -494,17 +494,17 @@
.playback = {
.channels_min = 1,
.channels_max = 2,
- .rates = SNDRV_PCM_RATE_8000_192000 |
- SNDRV_PCM_RATE_CONTINUOUS |
- SNDRV_PCM_RATE_KNOT,
+ .rates = SNDRV_PCM_RATE_CONTINUOUS,
+ .rate_min = 5512,
+ .rate_max = 192000,
.formats = KIRKWOOD_SPDIF_FORMATS,
},
.capture = {
.channels_min = 1,
.channels_max = 2,
- .rates = SNDRV_PCM_RATE_8000_192000 |
- SNDRV_PCM_RATE_CONTINUOUS |
- SNDRV_PCM_RATE_KNOT,
+ .rates = SNDRV_PCM_RATE_CONTINUOUS,
+ .rate_min = 5512,
+ .rate_max = 192000,
.formats = KIRKWOOD_SPDIF_FORMATS,
},
.ops = &kirkwood_i2s_dai_ops,
diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c
index cbc9c96..41949af 100644
--- a/sound/soc/soc-generic-dmaengine-pcm.c
+++ b/sound/soc/soc-generic-dmaengine-pcm.c
@@ -305,6 +305,20 @@
}
}
+static void dmaengine_pcm_release_chan(struct dmaengine_pcm *pcm)
+{
+ unsigned int i;
+
+ for (i = SNDRV_PCM_STREAM_PLAYBACK; i <= SNDRV_PCM_STREAM_CAPTURE;
+ i++) {
+ if (!pcm->chan[i])
+ continue;
+ dma_release_channel(pcm->chan[i]);
+ if (pcm->flags & SND_DMAENGINE_PCM_FLAG_HALF_DUPLEX)
+ break;
+ }
+}
+
/**
* snd_dmaengine_pcm_register - Register a dmaengine based PCM device
* @dev: The parent device for the PCM device
@@ -315,6 +329,7 @@
const struct snd_dmaengine_pcm_config *config, unsigned int flags)
{
struct dmaengine_pcm *pcm;
+ int ret;
pcm = kzalloc(sizeof(*pcm), GFP_KERNEL);
if (!pcm)
@@ -326,11 +341,20 @@
dmaengine_pcm_request_chan_of(pcm, dev);
if (flags & SND_DMAENGINE_PCM_FLAG_NO_RESIDUE)
- return snd_soc_add_platform(dev, &pcm->platform,
+ ret = snd_soc_add_platform(dev, &pcm->platform,
&dmaengine_no_residue_pcm_platform);
else
- return snd_soc_add_platform(dev, &pcm->platform,
+ ret = snd_soc_add_platform(dev, &pcm->platform,
&dmaengine_pcm_platform);
+ if (ret)
+ goto err_free_dma;
+
+ return 0;
+
+err_free_dma:
+ dmaengine_pcm_release_chan(pcm);
+ kfree(pcm);
+ return ret;
}
EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_register);
@@ -345,7 +369,6 @@
{
struct snd_soc_platform *platform;
struct dmaengine_pcm *pcm;
- unsigned int i;
platform = snd_soc_lookup_platform(dev);
if (!platform)
@@ -353,15 +376,8 @@
pcm = soc_platform_to_pcm(platform);
- for (i = SNDRV_PCM_STREAM_PLAYBACK; i <= SNDRV_PCM_STREAM_CAPTURE; i++) {
- if (pcm->chan[i]) {
- dma_release_channel(pcm->chan[i]);
- if (pcm->flags & SND_DMAENGINE_PCM_FLAG_HALF_DUPLEX)
- break;
- }
- }
-
snd_soc_remove_platform(platform);
+ dmaengine_pcm_release_chan(pcm);
kfree(pcm);
}
EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_unregister);
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 11a90cd..891b9a9 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -600,12 +600,13 @@
struct snd_soc_platform *platform = rtd->platform;
struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
struct snd_soc_dai *codec_dai = rtd->codec_dai;
- struct snd_soc_codec *codec = rtd->codec;
+ bool playback = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
mutex_lock_nested(&rtd->pcm_mutex, rtd->pcm_subclass);
/* apply codec digital mute */
- if (!codec->active)
+ if ((playback && codec_dai->playback_active == 1) ||
+ (!playback && codec_dai->capture_active == 1))
snd_soc_dai_digital_mute(codec_dai, 1, substream->stream);
/* free any machine hw params */
diff --git a/sound/soc/tegra/tegra20_i2s.c b/sound/soc/tegra/tegra20_i2s.c
index 364bf6a9..8c819f8 100644
--- a/sound/soc/tegra/tegra20_i2s.c
+++ b/sound/soc/tegra/tegra20_i2s.c
@@ -74,7 +74,7 @@
unsigned int fmt)
{
struct tegra20_i2s *i2s = snd_soc_dai_get_drvdata(dai);
- unsigned int mask, val;
+ unsigned int mask = 0, val = 0;
switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
case SND_SOC_DAIFMT_NB_NF:
@@ -83,10 +83,10 @@
return -EINVAL;
}
- mask = TEGRA20_I2S_CTRL_MASTER_ENABLE;
+ mask |= TEGRA20_I2S_CTRL_MASTER_ENABLE;
switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
case SND_SOC_DAIFMT_CBS_CFS:
- val = TEGRA20_I2S_CTRL_MASTER_ENABLE;
+ val |= TEGRA20_I2S_CTRL_MASTER_ENABLE;
break;
case SND_SOC_DAIFMT_CBM_CFM:
break;
diff --git a/sound/soc/tegra/tegra20_spdif.c b/sound/soc/tegra/tegra20_spdif.c
index 08bc693..8c7c102 100644
--- a/sound/soc/tegra/tegra20_spdif.c
+++ b/sound/soc/tegra/tegra20_spdif.c
@@ -67,15 +67,15 @@
{
struct device *dev = dai->dev;
struct tegra20_spdif *spdif = snd_soc_dai_get_drvdata(dai);
- unsigned int mask, val;
+ unsigned int mask = 0, val = 0;
int ret, spdifclock;
- mask = TEGRA20_SPDIF_CTRL_PACK |
- TEGRA20_SPDIF_CTRL_BIT_MODE_MASK;
+ mask |= TEGRA20_SPDIF_CTRL_PACK |
+ TEGRA20_SPDIF_CTRL_BIT_MODE_MASK;
switch (params_format(params)) {
case SNDRV_PCM_FORMAT_S16_LE:
- val = TEGRA20_SPDIF_CTRL_PACK |
- TEGRA20_SPDIF_CTRL_BIT_MODE_16BIT;
+ val |= TEGRA20_SPDIF_CTRL_PACK |
+ TEGRA20_SPDIF_CTRL_BIT_MODE_16BIT;
break;
default:
return -EINVAL;
diff --git a/sound/soc/tegra/tegra30_i2s.c b/sound/soc/tegra/tegra30_i2s.c
index 231a785..02247fe 100644
--- a/sound/soc/tegra/tegra30_i2s.c
+++ b/sound/soc/tegra/tegra30_i2s.c
@@ -118,7 +118,7 @@
unsigned int fmt)
{
struct tegra30_i2s *i2s = snd_soc_dai_get_drvdata(dai);
- unsigned int mask, val;
+ unsigned int mask = 0, val = 0;
switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
case SND_SOC_DAIFMT_NB_NF:
@@ -127,10 +127,10 @@
return -EINVAL;
}
- mask = TEGRA30_I2S_CTRL_MASTER_ENABLE;
+ mask |= TEGRA30_I2S_CTRL_MASTER_ENABLE;
switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
case SND_SOC_DAIFMT_CBS_CFS:
- val = TEGRA30_I2S_CTRL_MASTER_ENABLE;
+ val |= TEGRA30_I2S_CTRL_MASTER_ENABLE;
break;
case SND_SOC_DAIFMT_CBM_CFM:
break;
diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c
index dc4de37..bcf1d2f 100644
--- a/tools/power/cpupower/utils/cpupower-set.c
+++ b/tools/power/cpupower/utils/cpupower-set.c
@@ -18,9 +18,9 @@
#include "helpers/bitmask.h"
static struct option set_opts[] = {
- { .name = "perf-bias", .has_arg = optional_argument, .flag = NULL, .val = 'b'},
- { .name = "sched-mc", .has_arg = optional_argument, .flag = NULL, .val = 'm'},
- { .name = "sched-smt", .has_arg = optional_argument, .flag = NULL, .val = 's'},
+ { .name = "perf-bias", .has_arg = required_argument, .flag = NULL, .val = 'b'},
+ { .name = "sched-mc", .has_arg = required_argument, .flag = NULL, .val = 'm'},
+ { .name = "sched-smt", .has_arg = required_argument, .flag = NULL, .val = 's'},
{ },
};