From 1e25aa9641e8f3fa39cd5e46b4afcafd7f12a44b Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Mon, 1 Jun 2015 16:36:27 -0700 Subject: hid-sensor: Fix suspend/resume delay By default all the sensors are runtime suspended state (lowest power state). During Linux suspend process, all the run time suspended devices are resumed and then suspended. This caused all sensors to power up and introduced delay in suspend time, when we introduced runtime PM for HID sensors. The opposite process happens during resume process. To fix this, we do powerup process of the sensors only when the request is issued from user (raw or tiggerred). In this way when runtime, resume calls for powerup it will simply return as this will not match user requested state. Note this is a regression fix as the increase in suspend / resume times can be substantial (report of 8 seconds on Len's laptop!) Signed-off-by: Srinivas Pandruvada Tested-by: Len Brown Cc: Signed-off-by: Jonathan Cameron --- include/linux/hid-sensor-hub.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index 0408421d885f..cd224dfd94d8 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -230,6 +230,7 @@ struct hid_sensor_common { struct platform_device *pdev; unsigned usage_id; atomic_t data_ready; + atomic_t user_requested_state; struct iio_trigger *trigger; struct hid_sensor_hub_attribute_info poll; struct hid_sensor_hub_attribute_info report_state; -- cgit v1.2.3 From b1999477ed91c3c33891acfe0e18a4457e5c4915 Mon Sep 17 00:00:00 2001 From: Guo Zeng Date: Tue, 14 Apr 2015 11:55:55 +0000 Subject: ARM: prima2: move to use REGMAP APIs for rtciobrg all devices behind rtciobrg needs a special way to access. currently they are using a platform-specific API. this patch moves to REGMAP, then clients can use regmap APIs to read/write. for the moment, old APIs are still kept, once all clients move to regmap, old APIs will be dropped. this patch also does minor clean for comments, authors statement. Signed-off-by: Guo Zeng Signed-off-by: Barry Song --- include/linux/rtc/sirfsoc_rtciobrg.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/rtc/sirfsoc_rtciobrg.h b/include/linux/rtc/sirfsoc_rtciobrg.h index 2c92e1c8e055..aefd997262e4 100644 --- a/include/linux/rtc/sirfsoc_rtciobrg.h +++ b/include/linux/rtc/sirfsoc_rtciobrg.h @@ -9,10 +9,14 @@ #ifndef _SIRFSOC_RTC_IOBRG_H_ #define _SIRFSOC_RTC_IOBRG_H_ +struct regmap_config; + extern void sirfsoc_rtc_iobrg_besyncing(void); extern u32 sirfsoc_rtc_iobrg_readl(u32 addr); extern void sirfsoc_rtc_iobrg_writel(u32 val, u32 addr); +struct regmap *devm_regmap_init_iobg(struct device *dev, + const struct regmap_config *config); #endif -- cgit v1.2.3 From 31f02455455d405320e2f749696bef4e02903b35 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 30 Jun 2015 12:07:17 -0400 Subject: sparse: fix misplaced __pmem definition Move the definition of __pmem outside of CONFIG_SPARSE_RCU_POINTER to fix: drivers/nvdimm/pmem.c:198:17: sparse: too many arguments for function __builtin_expect drivers/nvdimm/pmem.c:36:33: sparse: expected ; at end of declaration drivers/nvdimm/pmem.c:48:21: sparse: void declaration ...due to __pmem failing to be defined in some configurations when CONFIG_SPARSE_RCU_POINTER=y. Reported-by: kbuild test robot Reported-by: Dan Carpenter Signed-off-by: Dan Williams --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 26fc8bc77f85..d8fbd500330e 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -17,11 +17,11 @@ # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) # define __percpu __attribute__((noderef, address_space(3))) +# define __pmem __attribute__((noderef, address_space(5))) #ifdef CONFIG_SPARSE_RCU_POINTER # define __rcu __attribute__((noderef, address_space(4))) #else # define __rcu -# define __pmem __attribute__((noderef, address_space(5))) #endif extern void __chk_user_ptr(const volatile void __user *); extern void __chk_io_ptr(const volatile void __iomem *); -- cgit v1.2.3 From bd7ade3cd9b0850264306f5c2b79024a417b6396 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Thu, 2 Jul 2015 01:32:44 -0400 Subject: bufferhead: Add _gfp version for sb_getblk() sb_getblk() is used during ext4 (and possibly other FSes) writeback paths. Sometimes such path require allocating memory and guaranteeing that such allocation won't block. Currently, however, there is no way to provide user flags for sb_getblk which could lead to deadlocks. This patch implements a sb_getblk_gfp with the only difference it can accept user-provided GFP flags. Signed-off-by: Nikolay Borisov Signed-off-by: Theodore Ts'o Cc: stable@vger.kernel.org --- include/linux/buffer_head.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 73b45225a7ca..e6797ded700e 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -317,6 +317,13 @@ sb_getblk(struct super_block *sb, sector_t block) return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); } + +static inline struct buffer_head * +sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp) +{ + return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp); +} + static inline struct buffer_head * sb_find_get_block(struct super_block *sb, sector_t block) { -- cgit v1.2.3 From 0fd972a7d91d6e15393c449492a04d94c0b89351 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Fri, 1 May 2015 20:13:42 -0400 Subject: module: relocate module_init from init.h to module.h Modular users will always be users of init functionality, but users of init functionality are not necessarily always modules. Hence any functionality like module_init and module_exit would be more at home in the module.h file. And module.h should explicitly include init.h to make the dependency clear. We've already done all the legwork needed to ensure that this move does not cause any build regressions due to implicit header file include assumptions about where module_init lives. Cc: Rusty Russell Acked-by: Rusty Russell Signed-off-by: Paul Gortmaker --- include/linux/init.h | 78 ---------------------------------------------- include/linux/module.h | 84 ++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 84 insertions(+), 78 deletions(-) (limited to 'include') diff --git a/include/linux/init.h b/include/linux/init.h index 7c68c36d3fd8..b449f378f995 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -282,68 +282,8 @@ void __init parse_early_param(void); void __init parse_early_options(char *cmdline); #endif /* __ASSEMBLY__ */ -/** - * module_init() - driver initialization entry point - * @x: function to be run at kernel boot time or module insertion - * - * module_init() will either be called during do_initcalls() (if - * builtin) or at module insertion time (if a module). There can only - * be one per module. - */ -#define module_init(x) __initcall(x); - -/** - * module_exit() - driver exit entry point - * @x: function to be run when driver is removed - * - * module_exit() will wrap the driver clean-up code - * with cleanup_module() when used with rmmod when - * the driver is a module. If the driver is statically - * compiled into the kernel, module_exit() has no effect. - * There can only be one per module. - */ -#define module_exit(x) __exitcall(x); - #else /* MODULE */ -/* - * In most cases loadable modules do not need custom - * initcall levels. There are still some valid cases where - * a driver may be needed early if built in, and does not - * matter when built as a loadable module. Like bus - * snooping debug drivers. - */ -#define early_initcall(fn) module_init(fn) -#define core_initcall(fn) module_init(fn) -#define core_initcall_sync(fn) module_init(fn) -#define postcore_initcall(fn) module_init(fn) -#define postcore_initcall_sync(fn) module_init(fn) -#define arch_initcall(fn) module_init(fn) -#define subsys_initcall(fn) module_init(fn) -#define subsys_initcall_sync(fn) module_init(fn) -#define fs_initcall(fn) module_init(fn) -#define fs_initcall_sync(fn) module_init(fn) -#define rootfs_initcall(fn) module_init(fn) -#define device_initcall(fn) module_init(fn) -#define device_initcall_sync(fn) module_init(fn) -#define late_initcall(fn) module_init(fn) -#define late_initcall_sync(fn) module_init(fn) - -#define console_initcall(fn) module_init(fn) -#define security_initcall(fn) module_init(fn) - -/* Each module must use one module_init(). */ -#define module_init(initfn) \ - static inline initcall_t __inittest(void) \ - { return initfn; } \ - int init_module(void) __attribute__((alias(#initfn))); - -/* This is only required if you want to be unloadable. */ -#define module_exit(exitfn) \ - static inline exitcall_t __exittest(void) \ - { return exitfn; } \ - void cleanup_module(void) __attribute__((alias(#exitfn))); - #define __setup_param(str, unique_id, fn) /* nothing */ #define __setup(str, func) /* nothing */ #endif @@ -351,24 +291,6 @@ void __init parse_early_options(char *cmdline); /* Data marked not to be saved by software suspend */ #define __nosavedata __section(.data..nosave) -/* This means "can be init if no module support, otherwise module load - may call it." */ -#ifdef CONFIG_MODULES -#define __init_or_module -#define __initdata_or_module -#define __initconst_or_module -#define __INIT_OR_MODULE .text -#define __INITDATA_OR_MODULE .data -#define __INITRODATA_OR_MODULE .section ".rodata","a",%progbits -#else -#define __init_or_module __init -#define __initdata_or_module __initdata -#define __initconst_or_module __initconst -#define __INIT_OR_MODULE __INIT -#define __INITDATA_OR_MODULE __INITDATA -#define __INITRODATA_OR_MODULE __INITRODATA -#endif /*CONFIG_MODULES*/ - #ifdef MODULE #define __exit_p(x) x #else diff --git a/include/linux/module.h b/include/linux/module.h index d67b1932cc59..3a19c79918e0 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -71,6 +72,89 @@ extern struct module_attribute module_uevent; extern int init_module(void); extern void cleanup_module(void); +#ifndef MODULE +/** + * module_init() - driver initialization entry point + * @x: function to be run at kernel boot time or module insertion + * + * module_init() will either be called during do_initcalls() (if + * builtin) or at module insertion time (if a module). There can only + * be one per module. + */ +#define module_init(x) __initcall(x); + +/** + * module_exit() - driver exit entry point + * @x: function to be run when driver is removed + * + * module_exit() will wrap the driver clean-up code + * with cleanup_module() when used with rmmod when + * the driver is a module. If the driver is statically + * compiled into the kernel, module_exit() has no effect. + * There can only be one per module. + */ +#define module_exit(x) __exitcall(x); + +#else /* MODULE */ + +/* + * In most cases loadable modules do not need custom + * initcall levels. There are still some valid cases where + * a driver may be needed early if built in, and does not + * matter when built as a loadable module. Like bus + * snooping debug drivers. + */ +#define early_initcall(fn) module_init(fn) +#define core_initcall(fn) module_init(fn) +#define core_initcall_sync(fn) module_init(fn) +#define postcore_initcall(fn) module_init(fn) +#define postcore_initcall_sync(fn) module_init(fn) +#define arch_initcall(fn) module_init(fn) +#define subsys_initcall(fn) module_init(fn) +#define subsys_initcall_sync(fn) module_init(fn) +#define fs_initcall(fn) module_init(fn) +#define fs_initcall_sync(fn) module_init(fn) +#define rootfs_initcall(fn) module_init(fn) +#define device_initcall(fn) module_init(fn) +#define device_initcall_sync(fn) module_init(fn) +#define late_initcall(fn) module_init(fn) +#define late_initcall_sync(fn) module_init(fn) + +#define console_initcall(fn) module_init(fn) +#define security_initcall(fn) module_init(fn) + +/* Each module must use one module_init(). */ +#define module_init(initfn) \ + static inline initcall_t __inittest(void) \ + { return initfn; } \ + int init_module(void) __attribute__((alias(#initfn))); + +/* This is only required if you want to be unloadable. */ +#define module_exit(exitfn) \ + static inline exitcall_t __exittest(void) \ + { return exitfn; } \ + void cleanup_module(void) __attribute__((alias(#exitfn))); + +#endif + +/* This means "can be init if no module support, otherwise module load + may call it." */ +#ifdef CONFIG_MODULES +#define __init_or_module +#define __initdata_or_module +#define __initconst_or_module +#define __INIT_OR_MODULE .text +#define __INITDATA_OR_MODULE .data +#define __INITRODATA_OR_MODULE .section ".rodata","a",%progbits +#else +#define __init_or_module __init +#define __initdata_or_module __initdata +#define __initconst_or_module __initconst +#define __INIT_OR_MODULE __INIT +#define __INITDATA_OR_MODULE __INITDATA +#define __INITRODATA_OR_MODULE __INITRODATA +#endif /*CONFIG_MODULES*/ + /* Archs provide a method of finding the correct exception table. */ struct exception_table_entry; -- cgit v1.2.3 From 0294112ee3135fbd15eaa70015af8283642dd970 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 4 Jul 2015 03:09:03 +0200 Subject: ACPI / PNP: Reserve ACPI resources at the fs_initcall_sync stage This effectively reverts the following three commits: 7bc10388ccdd ACPI / resources: free memory on error in add_region_before() 0f1b414d1907 ACPI / PNP: Avoid conflicting resource reservations b9a5e5e18fbf ACPI / init: Fix the ordering of acpi_reserve_resources() (commit b9a5e5e18fbf introduced regressions some of which, but not all, were addressed by commit 0f1b414d1907 and commit 7bc10388ccdd was a fixup on top of the latter) and causes ACPI fixed hardware resources to be reserved at the fs_initcall_sync stage of system initialization. The story is as follows. First, a boot regression was reported due to an apparent resource reservation ordering change after a commit that shouldn't lead to such changes. Investigation led to the conclusion that the problem happened because acpi_reserve_resources() was executed at the device_initcall() stage of system initialization which wasn't strictly ordered with respect to driver initialization (and with respect to the initialization of the pcieport driver in particular), so a random change causing the device initcalls to be run in a different order might break things. The response to that was to attempt to run acpi_reserve_resources() as soon as we knew that ACPI would be in use (commit b9a5e5e18fbf). However, that turned out to be too early, because it caused resource reservations made by the PNP system driver to fail on at least one system and that failure was addressed by commit 0f1b414d1907. That fix still turned out to be insufficient, though, because calling acpi_reserve_resources() before the fs_initcall stage of system initialization caused a boot regression to happen on the eCAFE EC-800-H20G/S netbook. That meant that we only could call acpi_reserve_resources() at the fs_initcall initialization stage or later, but then we might just as well call it after the PNP initalization in which case commit 0f1b414d1907 wouldn't be necessary any more. For this reason, the changes made by commit 0f1b414d1907 are reverted (along with a memory leak fixup on top of that commit), the changes made by commit b9a5e5e18fbf that went too far are reverted too and acpi_reserve_resources() is changed into fs_initcall_sync, which will cause it to be executed after the PNP subsystem initialization (which is an fs_initcall) and before device initcalls (including the pcieport driver initialization) which should avoid the initial issue. Link: https://bugzilla.kernel.org/show_bug.cgi?id=100581 Link: http://marc.info/?t=143092384600002&r=1&w=2 Link: https://bugzilla.kernel.org/show_bug.cgi?id=99831 Link: http://marc.info/?t=143389402600001&r=1&w=2 Fixes: b9a5e5e18fbf "ACPI / init: Fix the ordering of acpi_reserve_resources()" Reported-by: Roland Dreier Cc: All applicable Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c471dfc93b71..fedfd1bea3bf 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -309,9 +309,6 @@ int acpi_check_region(resource_size_t start, resource_size_t n, int acpi_resources_are_enforced(void); -int acpi_reserve_region(u64 start, unsigned int length, u8 space_id, - unsigned long flags, char *desc); - #ifdef CONFIG_HIBERNATION void __init acpi_no_s4_hw_signature(void); #endif @@ -507,13 +504,6 @@ static inline int acpi_check_region(resource_size_t start, resource_size_t n, return 0; } -static inline int acpi_reserve_region(u64 start, unsigned int length, - u8 space_id, unsigned long flags, - char *desc) -{ - return -ENXIO; -} - struct acpi_table_header; static inline int acpi_table_parse(char *id, int (*handler)(struct acpi_table_header *)) -- cgit v1.2.3 From 26095a01d359827eeccec5459c28ddd976183179 Mon Sep 17 00:00:00 2001 From: "Suthikulpanit, Suravee" Date: Tue, 7 Jul 2015 01:55:20 +0200 Subject: ACPI / scan: Add support for ACPI _CLS device matching Device drivers typically use ACPI _HIDs/_CIDs listed in struct device_driver acpi_match_table to match devices. However, for generic drivers, we do not want to list _HID for all supported devices. Also, certain classes of devices do not have _CID (e.g. SATA, USB). Instead, we can leverage ACPI _CLS, which specifies PCI-defined class code (i.e. base-class, subclass and programming interface). This patch adds support for matching ACPI devices using the _CLS method. To support loadable module, current design uses _HID or _CID to match device's modalias. With the new way of matching with _CLS this would requires modification to the current ACPI modalias key to include _CLS. This patch appends PCI-defined class-code to the existing ACPI modalias as following. acpi::::..::: E.g: # cat /sys/devices/platform/AMDI0600:00/modalias acpi:AMDI0600:010601: where bb is th base-class code, ss is te sub-class code, and pp is the programming interface code Since there would not be _HID/_CID in the ACPI matching table of the driver, this patch adds a field to acpi_device_id to specify the matching _CLS. static const struct acpi_device_id ahci_acpi_match[] = { { ACPI_DEVICE_CLASS(PCI_CLASS_STORAGE_SATA_AHCI, 0xffffff) }, {}, }; In this case, the corresponded entry in modules.alias file would be: alias acpi*:010601:* ahci_platform Acked-by: Mika Westerberg Reviewed-by: Hanjun Guo Signed-off-by: Suravee Suthikulpanit Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 14 ++++++++++++++ include/linux/mod_devicetable.h | 2 ++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c471dfc93b71..bdfdb9f65c23 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -58,6 +58,19 @@ static inline acpi_handle acpi_device_handle(struct acpi_device *adev) acpi_fwnode_handle(adev) : NULL) #define ACPI_HANDLE(dev) acpi_device_handle(ACPI_COMPANION(dev)) +/** + * ACPI_DEVICE_CLASS - macro used to describe an ACPI device with + * the PCI-defined class-code information + * + * @_cls : the class, subclass, prog-if triple for this device + * @_msk : the class mask for this device + * + * This macro is used to create a struct acpi_device_id that matches a + * specific PCI class. The .id and .driver_data fields will be left + * initialized with the default value. + */ +#define ACPI_DEVICE_CLASS(_cls, _msk) .cls = (_cls), .cls_msk = (_msk), + static inline bool has_acpi_companion(struct device *dev) { return is_acpi_node(dev->fwnode); @@ -446,6 +459,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *); #define ACPI_COMPANION(dev) (NULL) #define ACPI_COMPANION_SET(dev, adev) do { } while (0) #define ACPI_HANDLE(dev) (NULL) +#define ACPI_DEVICE_CLASS(_cls, _msk) .cls = (0), .cls_msk = (0), struct fwnode_handle; diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 8183d6640ca7..34f25b7bf642 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -189,6 +189,8 @@ struct css_device_id { struct acpi_device_id { __u8 id[ACPI_ID_LEN]; kernel_ulong_t driver_data; + __u32 cls; + __u32 cls_msk; }; #define PNP_ID_LEN 8 -- cgit v1.2.3 From f32dd117051185da6e923b35491a44d7debeeea5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 7 Jul 2015 16:29:38 +0200 Subject: tick/broadcast: Make idle check independent from mode and config Currently the broadcast busy check, which prevents the idle code from going into deep idle, works only in one shot mode. If NOHZ and HIGHRES are off (config or command line) there is no sanity check at all, so under certain conditions cpus are allowed to go into deep idle, where the local timer stops, and are not woken up again because there is no broadcast timer installed or a hrtimer based broadcast device is not evaluated. Move tick_broadcast_oneshot_control() into the common code and provide proper subfunctions for the various config combinations. The common check in tick_broadcast_oneshot_control() is for the C3STOP misfeature flag of the local clock event device. If its not set, idle can proceed. If set, further checks are necessary. Provide checks for the trivial cases: - If broadcast is disabled in the config, then return busy - If oneshot mode (NOHZ/HIGHES) is disabled in the config, return busy if the broadcast device is hrtimer based. - If oneshot mode is enabled in the config call the original tick_broadcast_oneshot_control() function. That function needs extra checks which will be implemented in seperate patches. [ Split out from a larger combo patch ] Reported-and-tested-by: Sudeep Holla Signed-off-by: Thomas Gleixner Cc: Suzuki Poulose Cc: Lorenzo Pieralisi Cc: Catalin Marinas Cc: Rafael J. Wysocki Cc: Peter Zijlstra Cc: Preeti U Murthy Cc: Ingo Molnar Link: http://lkml.kernel.org/r/alpine.DEB.2.11.1507070929360.3916@nanos --- include/linux/tick.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/tick.h b/include/linux/tick.h index 3741ba1a652c..6916dcb61857 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -67,11 +67,7 @@ extern void tick_broadcast_control(enum tick_broadcast_mode mode); static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { } #endif /* BROADCAST */ -#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state); -#else -static inline int tick_broadcast_oneshot_control(enum tick_broadcast_state state) { return 0; } -#endif static inline void tick_broadcast_enable(void) { -- cgit v1.2.3 From 37b64a42067a04a22468c4e52c12af00d72e462b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 7 Jul 2015 21:56:34 +0200 Subject: tick/broadcast: Unbreak CONFIG_GENERIC_CLOCKEVENTS=n build Making tick_broadcast_oneshot_control() independent from CONFIG_GENERIC_CLOCKEVENTS_BROADCAST broke the build for CONFIG_GENERIC_CLOCKEVENTS=n because the function is not defined there. Provide a proper stub inline. Fixes: f32dd1170511 'tick/broadcast: Make idle check independent from mode and config' Reported-by: kbuild test robot Signed-off-by: Thomas Gleixner --- include/linux/tick.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/tick.h b/include/linux/tick.h index 6916dcb61857..edbfc9a5293e 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -67,7 +67,14 @@ extern void tick_broadcast_control(enum tick_broadcast_mode mode); static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { } #endif /* BROADCAST */ +#ifdef CONFIG_GENERIC_CLOCKEVENTS extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state); +#else +static inline int tick_broadcast_oneshot_control(enum tick_broadcast_state state) +{ + return 0; +} +#endif static inline void tick_broadcast_enable(void) { -- cgit v1.2.3 From a899418167264c7bac574b1a0f1b2c26c5b0995a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 5 Jul 2015 17:12:30 +0000 Subject: hotplug: Prevent alloc/free of irq descriptors during cpu up/down When a cpu goes up some architectures (e.g. x86) have to walk the irq space to set up the vector space for the cpu. While this needs extra protection at the architecture level we can avoid a few race conditions by preventing the concurrent allocation/free of irq descriptors and the associated data. When a cpu goes down it moves the interrupts which are targeted to this cpu away by reassigning the affinities. While this happens interrupts can be allocated and freed, which opens a can of race conditions in the code which reassignes the affinities because interrupt descriptors might be freed underneath. Example: CPU1 CPU2 cpu_up/down irq_desc = irq_to_desc(irq); remove_from_radix_tree(desc); raw_spin_lock(&desc->lock); free(desc); We could protect the irq descriptors with RCU, but that would require a full tree change of all accesses to interrupt descriptors. But fortunately these kind of race conditions are rather limited to a few things like cpu hotplug. The normal setup/teardown is very well serialized. So the simpler and obvious solution is: Prevent allocation and freeing of interrupt descriptors accross cpu hotplug. Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra Cc: xiao jin Cc: Joerg Roedel Cc: Borislav Petkov Cc: Yanmin Zhang Link: http://lkml.kernel.org/r/20150705171102.063519515@linutronix.de --- include/linux/irqdesc.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 624a668e61f1..fcea4e48e21f 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -87,7 +87,12 @@ struct irq_desc { const char *name; } ____cacheline_internodealigned_in_smp; -#ifndef CONFIG_SPARSE_IRQ +#ifdef CONFIG_SPARSE_IRQ +extern void irq_lock_sparse(void); +extern void irq_unlock_sparse(void); +#else +static inline void irq_lock_sparse(void) { } +static inline void irq_unlock_sparse(void) { } extern struct irq_desc irq_desc[NR_IRQS]; #endif -- cgit v1.2.3 From 974d7af5fcc295dcf8315255142b2fe44fd74b0c Mon Sep 17 00:00:00 2001 From: Andy Gospodarek Date: Tue, 7 Jul 2015 13:56:57 -0400 Subject: ipv4: add support for linkdown sysctl to netconf This kernel patch exports the value of the new ignore_routes_with_linkdown via netconf. v2: changes to notify userspace via netlink when sysctl values change and proposed for 'net' since this could be considered a bugfix Signed-off-by: Andy Gospodarek Suggested-by: Nicolas Dichtel Acked-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/uapi/linux/netconf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h index 669a1f0b1d97..23cbd34e4ac7 100644 --- a/include/uapi/linux/netconf.h +++ b/include/uapi/linux/netconf.h @@ -15,6 +15,7 @@ enum { NETCONFA_RP_FILTER, NETCONFA_MC_FORWARDING, NETCONFA_PROXY_NEIGH, + NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, __NETCONFA_MAX }; #define NETCONFA_MAX (__NETCONFA_MAX - 1) -- cgit v1.2.3 From 1f6823faa8c563431a94e614d2b63ce16bb6f658 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 9 Jul 2015 10:51:46 +0200 Subject: time: Get rid of do_posix_clock_monotonic_gettime All users gone. Remove it before we get another one. Signed-off-by: Thomas Gleixner --- include/linux/timekeeping.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 3aa72e648650..6e191e4e6ab6 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -145,7 +145,6 @@ static inline void getboottime(struct timespec *ts) } #endif -#define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts) #define ktime_get_real_ts64(ts) getnstimeofday64(ts) /* -- cgit v1.2.3 From 757856d2b9568a701df9ea6a4be68effbb9d6f44 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 25 Jun 2015 17:47:45 +0300 Subject: libceph: enable ceph in a non-default network namespace Grab a reference on a network namespace of the 'rbd map' (in case of rbd) or 'mount' (in case of ceph) process and use that to open sockets instead of always using init_net and bailing if network namespace is anything but init_net. Be careful to not share struct ceph_client instances between different namespaces and don't add any code in the !CONFIG_NET_NS case. This is based on a patch from Hong Zhiguo . Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/messenger.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index e15499422fdc..37753278987a 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -56,6 +57,7 @@ struct ceph_messenger { struct ceph_entity_addr my_enc_addr; atomic_t stopping; + possible_net_t net; bool nocrc; bool tcp_nodelay; @@ -267,6 +269,7 @@ extern void ceph_messenger_init(struct ceph_messenger *msgr, u64 required_features, bool nocrc, bool tcp_nodelay); +extern void ceph_messenger_fini(struct ceph_messenger *msgr); extern void ceph_con_init(struct ceph_connection *con, void *private, const struct ceph_connection_operations *ops, -- cgit v1.2.3 From 7876f930d0e78addc6bbdbba0d6c196a0788d545 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 9 Jul 2015 16:39:49 -0400 Subject: blkcg: implement all_blkcgs list Add all_blkcgs list goes through blkcg->all_blkcgs_node and is protected by blkcg_pol_mutex. This will be used to fix blkcg_policy_data allocation bug. Signed-off-by: Tejun Heo Cc: Vivek Goyal Cc: Arianna Avanzini Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 58cfab80dd70..cf3e7bc22ef3 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -47,6 +47,7 @@ struct blkcg { struct blkcg_policy_data *pd[BLKCG_MAX_POLS]; + struct list_head all_blkcgs_node; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; #endif -- cgit v1.2.3 From 06b285bd11257bccc5a1b85a835507e33656aff2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 9 Jul 2015 16:39:50 -0400 Subject: blkcg: fix blkcg_policy_data allocation bug e48453c386f3 ("block, cgroup: implement policy-specific per-blkcg data") updated per-blkcg policy data to be dynamically allocated. When a policy is registered, its policy data aren't created. Instead, when the policy is activated on a queue, the policy data are allocated if there are blkg's (blkcg_gq's) which are attached to a given blkcg. This is buggy. Consider the following scenario. 1. A blkcg is created. No blkg's attached yet. 2. The policy is registered. No policy data is allocated. 3. The policy is activated on a queue. As the above blkcg doesn't have any blkg's, it won't allocate the matching blkcg_policy_data. 4. An IO is issued from the blkcg and blkg is created and the blkcg still doesn't have the matching policy data allocated. With cfq-iosched, this leads to an oops. It also doesn't free policy data on policy unregistration assuming that freeing of all policy data on blkcg destruction should take care of it; however, this also is incorrect. 1. A blkcg has policy data. 2. The policy gets unregistered but the policy data remains. 3. Another policy gets registered on the same slot. 4. Later, the new policy tries to allocate policy data on the previous blkcg but the slot is already occupied and gets skipped. The policy ends up operating on the policy data of the previous policy. There's no reason to manage blkcg_policy_data lazily. The reason we do lazy allocation of blkg's is that the number of all possible blkg's is the product of cgroups and block devices which can reach a surprising level. blkcg_policy_data is contrained by the number of cgroups and shouldn't be a problem. This patch makes blkcg_policy_data to be allocated for all existing blkcg's on policy registration and freed on unregistration and removes blkcg_policy_data handling from policy [de]activation paths. This makes that blkcg_policy_data are created and removed with the policy they belong to and fixes the above described problems. Signed-off-by: Tejun Heo Fixes: e48453c386f3 ("block, cgroup: implement policy-specific per-blkcg data") Cc: Vivek Goyal Cc: Arianna Avanzini Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index cf3e7bc22ef3..1b62d768c7df 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -89,18 +89,12 @@ struct blkg_policy_data { * Policies that need to keep per-blkcg data which is independent * from any request_queue associated to it must specify its size * with the cpd_size field of the blkcg_policy structure and - * embed a blkcg_policy_data in it. blkcg core allocates - * policy-specific per-blkcg structures lazily the first time - * they are actually needed, so it handles them together with - * blkgs. cpd_init() is invoked to let each policy handle - * per-blkcg data. + * embed a blkcg_policy_data in it. cpd_init() is invoked to let + * each policy handle per-blkcg data. */ struct blkcg_policy_data { /* the policy id this per-policy data belongs to */ int plid; - - /* used during policy activation */ - struct list_head alloc_node; }; /* association between a blk cgroup and a request queue */ -- cgit v1.2.3 From 4a0e3e989d66bb7204b163d9cfaa7fa96d0f2023 Mon Sep 17 00:00:00 2001 From: Enrico Mioso Date: Wed, 8 Jul 2015 13:05:57 +0200 Subject: cdc_ncm: Add support for moving NDP to end of NCM frame NCM specs are not actually mandating a specific position in the frame for the NDP (Network Datagram Pointer). However, some Huawei devices will ignore our aggregates if it is not placed after the datagrams it points to. Add support for doing just this, in a per-device configurable way. While at it, update NCM subdrivers, disabling this functionality in all of them, except in huawei_cdc_ncm where it is enabled instead. We aren't making any distinction between different Huawei NCM devices, based on what the vendor driver does. Standard NCM devices are left unaffected: if they are compliant, they should be always usable, still stay on the safe side. This change has been tested and working with a Huawei E3131 device (which works regardless of NDP position), a Huawei E3531 (also working both ways) and an E3372 (which mandates NDP to be after indexed datagrams). V1->V2: - corrected wrong NDP acronym definition - fixed possible NULL pointer dereference - patch cleanup V2->V3: - Properly account for the NDP size when writing new packets to SKB Signed-off-by: Enrico Mioso Signed-off-by: David S. Miller --- include/linux/usb/cdc_ncm.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 7c9b484735c5..1f6526c76ee8 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -80,6 +80,9 @@ #define CDC_NCM_TIMER_INTERVAL_MIN 5UL #define CDC_NCM_TIMER_INTERVAL_MAX (U32_MAX / NSEC_PER_USEC) +/* Driver flags */ +#define CDC_NCM_FLAG_NDP_TO_END 0x02 /* NDP is placed at end of frame */ + #define cdc_ncm_comm_intf_is_mbim(x) ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \ (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE) #define cdc_ncm_data_intf_is_mbim(x) ((x)->desc.bInterfaceProtocol == USB_CDC_MBIM_PROTO_NTB) @@ -103,9 +106,11 @@ struct cdc_ncm_ctx { spinlock_t mtx; atomic_t stop; + int drvflags; u32 timer_interval; u32 max_ndp_size; + struct usb_cdc_ncm_ndp16 *delayed_ndp16; u32 tx_timer_pending; u32 tx_curr_frame_num; @@ -133,7 +138,7 @@ struct cdc_ncm_ctx { }; u8 cdc_ncm_select_altsetting(struct usb_interface *intf); -int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting); +int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags); void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf); struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign); int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in); -- cgit v1.2.3 From 5544eb9b81940647b8fad1f251b37cbe2819ce44 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 7 Jul 2015 15:41:58 +0200 Subject: KVM: count number of assigned devices If there are no assigned devices, the guest PAT are not providing any useful information and can be overridden to writeback; VMX always does this because it has the "IPAT" bit in its extended page table entries, but SVM does not have anything similar. Hook into VFIO and legacy device assignment so that they provide this information to KVM. Reviewed-by: Alex Williamson Tested-by: Joerg Roedel Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9564fd78c547..05e99b8ef465 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -734,6 +734,24 @@ static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) return false; } #endif +#ifdef __KVM_HAVE_ARCH_ASSIGNED_DEVICE +void kvm_arch_start_assignment(struct kvm *kvm); +void kvm_arch_end_assignment(struct kvm *kvm); +bool kvm_arch_has_assigned_device(struct kvm *kvm); +#else +static inline void kvm_arch_start_assignment(struct kvm *kvm) +{ +} + +static inline void kvm_arch_end_assignment(struct kvm *kvm) +{ +} + +static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) +{ + return false; +} +#endif static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) { -- cgit v1.2.3 From d3b58c47d330de8c29898fe9746f7530408f8a59 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Fri, 26 Jun 2015 11:58:19 +0200 Subject: can: replace timestamp as unique skb attribute Commit 514ac99c64b "can: fix multiple delivery of a single CAN frame for overlapping CAN filters" requires the skb->tstamp to be set to check for identical CAN skbs. Without timestamping to be required by user space applications this timestamp was not generated which lead to commit 36c01245eb8 "can: fix loss of CAN frames in raw_rcv" - which forces the timestamp to be set in all CAN related skbuffs by introducing several __net_timestamp() calls. This forces e.g. out of tree drivers which are not using alloc_can{,fd}_skb() to add __net_timestamp() after skbuff creation to prevent the frame loss fixed in mainline Linux. This patch removes the timestamp dependency and uses an atomic counter to create an unique identifier together with the skbuff pointer. Btw: the new skbcnt element introduced in struct can_skb_priv has to be initialized with zero in out-of-tree drivers which are not using alloc_can{,fd}_skb() too. Signed-off-by: Oliver Hartkopp Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- include/linux/can/skb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index b6a52a4b457a..51bb6532785c 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -27,10 +27,12 @@ /** * struct can_skb_priv - private additional data inside CAN sk_buffs * @ifindex: ifindex of the first interface the CAN frame appeared on + * @skbcnt: atomic counter to have an unique id together with skb pointer * @cf: align to the following CAN frame at skb->data */ struct can_skb_priv { int ifindex; + int skbcnt; struct can_frame cf[0]; }; -- cgit v1.2.3 From 29d01b22eaa18d8b46091d3c98c6001c49f78e4a Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Sat, 11 Jul 2015 06:43:02 -0400 Subject: locks: new helpers - flock_lock_inode_wait and posix_lock_inode_wait Allow callers to pass in an inode instead of a filp. Signed-off-by: Jeff Layton Reviewed-by: "J. Bruce Fields" Tested-by: "J. Bruce Fields" --- include/linux/fs.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index a0653e560c26..4c990edd1377 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1046,11 +1046,13 @@ extern void locks_remove_file(struct file *); extern void locks_release_private(struct file_lock *); extern void posix_test_lock(struct file *, struct file_lock *); extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); +extern int posix_lock_inode_wait(struct inode *, struct file_lock *); extern int posix_lock_file_wait(struct file *, struct file_lock *); extern int posix_unblock_lock(struct file_lock *); extern int vfs_test_lock(struct file *, struct file_lock *); extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); +extern int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl); extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); extern void lease_get_mtime(struct inode *, struct timespec *time); @@ -1137,6 +1139,12 @@ static inline int posix_lock_file(struct file *filp, struct file_lock *fl, return -ENOLCK; } +static inline int posix_lock_inode_wait(struct inode *inode, + struct file_lock *fl) +{ + return -ENOLCK; +} + static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl) { return -ENOLCK; @@ -1163,6 +1171,12 @@ static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) return 0; } +static inline int flock_lock_inode_wait(struct inode *inode, + struct file_lock *request) +{ + return -ENOLCK; +} + static inline int flock_lock_file_wait(struct file *filp, struct file_lock *request) { -- cgit v1.2.3 From ee296d7c5709440f8abd36b5b65c6b3e388538d9 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Sat, 11 Jul 2015 06:43:03 -0400 Subject: locks: inline posix_lock_file_wait and flock_lock_file_wait They just call file_inode and then the corresponding *_inode_file_wait function. Just make them static inlines instead. Signed-off-by: Jeff Layton --- include/linux/fs.h | 32 ++++++++++++++------------------ 1 file changed, 14 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4c990edd1377..cc008c338f5a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1047,13 +1047,11 @@ extern void locks_release_private(struct file_lock *); extern void posix_test_lock(struct file *, struct file_lock *); extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); extern int posix_lock_inode_wait(struct inode *, struct file_lock *); -extern int posix_lock_file_wait(struct file *, struct file_lock *); extern int posix_unblock_lock(struct file_lock *); extern int vfs_test_lock(struct file *, struct file_lock *); extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); extern int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl); -extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); extern void lease_get_mtime(struct inode *, struct timespec *time); extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); @@ -1145,11 +1143,6 @@ static inline int posix_lock_inode_wait(struct inode *inode, return -ENOLCK; } -static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl) -{ - return -ENOLCK; -} - static inline int posix_unblock_lock(struct file_lock *waiter) { return -ENOENT; @@ -1177,12 +1170,6 @@ static inline int flock_lock_inode_wait(struct inode *inode, return -ENOLCK; } -static inline int flock_lock_file_wait(struct file *filp, - struct file_lock *request) -{ - return -ENOLCK; -} - static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { return 0; @@ -1216,6 +1203,20 @@ static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} #endif /* !CONFIG_FILE_LOCKING */ +static inline struct inode *file_inode(const struct file *f) +{ + return f->f_inode; +} + +static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl) +{ + return posix_lock_inode_wait(file_inode(filp), fl); +} + +static inline int flock_lock_file_wait(struct file *filp, struct file_lock *fl) +{ + return flock_lock_inode_wait(file_inode(filp), fl); +} struct fasync_struct { spinlock_t fa_lock; @@ -2025,11 +2026,6 @@ extern void ihold(struct inode * inode); extern void iput(struct inode *); extern int generic_update_time(struct inode *, struct timespec *, int); -static inline struct inode *file_inode(const struct file *f) -{ - return f->f_inode; -} - /* /sys/fs */ extern struct kobject *fs_kobj; -- cgit v1.2.3 From 4139032b4860c06ff3a7687041f06535fed901ed Mon Sep 17 00:00:00 2001 From: Hal Rosenstock Date: Mon, 29 Jun 2015 09:57:00 -0400 Subject: IB: Add rdma_cap_ib_switch helper and use where appropriate Persuant to Liran's comments on node_type on linux-rdma mailing list: In an effort to reform the RDMA core and ULPs to minimize use of node_type in struct ib_device, an additional bit is added to struct ib_device for is_switch (IB switch). This is needed to be initialized by any IB switch device driver. This is a NEW requirement on such device drivers which are all "out of tree". In addition, an ib_switch helper was added to ib_verbs.h based on the is_switch device bit rather than node_type (although those should be consistent). The RDMA core (MAD, SMI, agent, sa_query, multicast, sysfs) as well as (IPoIB and SRP) ULPs are updated where appropriate to use this new helper. In some cases, the helper is now used under the covers of using rdma_[start end]_port rather than the open coding previously used. Reviewed-by: Sean Hefty Reviewed-By: Jason Gunthorpe Reviewed-by: Ira Weiny Tested-by: Ira Weiny Signed-off-by: Hal Rosenstock Signed-off-by: Doug Ledford --- include/rdma/ib_verbs.h | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 986fddb08579..b0f898e3b2e7 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1745,6 +1745,7 @@ struct ib_device { char node_desc[64]; __be64 node_guid; u32 local_dma_lkey; + u16 is_switch:1; u8 node_type; u8 phys_port_cnt; @@ -1823,6 +1824,20 @@ int ib_query_port(struct ib_device *device, enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u8 port_num); +/** + * rdma_cap_ib_switch - Check if the device is IB switch + * @device: Device to check + * + * Device driver is responsible for setting is_switch bit on + * in ib_device structure at init time. + * + * Return: true if the device is IB switch. + */ +static inline bool rdma_cap_ib_switch(const struct ib_device *device) +{ + return device->is_switch; +} + /** * rdma_start_port - Return the first valid port number for the device * specified @@ -1833,7 +1848,7 @@ enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, */ static inline u8 rdma_start_port(const struct ib_device *device) { - return (device->node_type == RDMA_NODE_IB_SWITCH) ? 0 : 1; + return rdma_cap_ib_switch(device) ? 0 : 1; } /** @@ -1846,8 +1861,7 @@ static inline u8 rdma_start_port(const struct ib_device *device) */ static inline u8 rdma_end_port(const struct ib_device *device) { - return (device->node_type == RDMA_NODE_IB_SWITCH) ? - 0 : device->phys_port_cnt; + return rdma_cap_ib_switch(device) ? 0 : device->phys_port_cnt; } static inline bool rdma_protocol_ib(const struct ib_device *device, u8 port_num) -- cgit v1.2.3 From 3fdf70acec13efc7ecf254f5a364df06348bfd2c Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 25 Jun 2015 13:34:15 +0300 Subject: IB/srp: Avoid using uninitialized variable We might return res which is not initialized. Also reduce code duplication by exporting srp_parse_tmo so srp_tmo_set can reuse it. Detected by Coverity. Signed-off-by: Sagi Grimberg Signed-off-by: Jenny Falkovich Reviewed-by: Bart Van Assche Signed-off-by: Doug Ledford --- include/scsi/scsi_transport_srp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/scsi_transport_srp.h b/include/scsi/scsi_transport_srp.h index cdb05dd1d440..d40d3ef25707 100644 --- a/include/scsi/scsi_transport_srp.h +++ b/include/scsi/scsi_transport_srp.h @@ -119,6 +119,7 @@ extern struct srp_rport *srp_rport_add(struct Scsi_Host *, extern void srp_rport_del(struct srp_rport *); extern int srp_tmo_valid(int reconnect_delay, int fast_io_fail_tmo, int dev_loss_tmo); +int srp_parse_tmo(int *tmo, const char *buf); extern int srp_reconnect_rport(struct srp_rport *rport); extern void srp_start_tl_fail_timers(struct srp_rport *rport); extern void srp_remove_host(struct Scsi_Host *); -- cgit v1.2.3 From 30bb6fb39e5c08b9db5bc592d6cbc9a5fc5e67a4 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 15 Jun 2015 13:31:33 +0200 Subject: gpio: Remove double "base" in comment Signed-off-by: Geert Uytterhoeven Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index cc7ec129b329..c8393cd4d44f 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -45,7 +45,7 @@ struct seq_file; * @base: identifies the first GPIO number handled by this chip; * or, if negative during registration, requests dynamic ID allocation. * DEPRECATION: providing anything non-negative and nailing the base - * base offset of GPIO chips is deprecated. Please pass -1 as base to + * offset of GPIO chips is deprecated. Please pass -1 as base to * let gpiolib select the chip base in all possible cases. We want to * get rid of the static GPIO number space in the long run. * @ngpio: the number of GPIOs handled by this controller; the last GPIO -- cgit v1.2.3 From 2531c8cf56a640cd7d17057df8484e570716a450 Mon Sep 17 00:00:00 2001 From: Dominik Dingel Date: Fri, 17 Jul 2015 16:23:37 -0700 Subject: mm: hugetlb: allow hugepages_supported to be architecture specific s390 has a constant hugepage size, by setting HPAGE_SHIFT we also change e.g. the pageblock_order, which should be independent in respect to hugepage support. With this patch every architecture is free to define how to check for hugepage support. Signed-off-by: Dominik Dingel Acked-by: Martin Schwidefsky Cc: Heiko Carstens Cc: Christian Borntraeger Cc: Michael Holzheu Cc: Gerald Schaefer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 205026175c42..d891f949466a 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -460,15 +460,14 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h, return &mm->page_table_lock; } -static inline bool hugepages_supported(void) -{ - /* - * Some platform decide whether they support huge pages at boot - * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when - * there is no such support - */ - return HPAGE_SHIFT != 0; -} +#ifndef hugepages_supported +/* + * Some platform decide whether they support huge pages at boot + * time. Some of them, such as powerpc, set HPAGE_SHIFT to 0 + * when there is no such support + */ +#define hugepages_supported() (HPAGE_SHIFT != 0) +#endif #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; -- cgit v1.2.3 From 8db1486065141e619e4855b84e350ef32064f7e1 Mon Sep 17 00:00:00 2001 From: Nicolas Iooss Date: Fri, 17 Jul 2015 16:23:42 -0700 Subject: include, lib: add __printf attributes to several function prototypes Using __printf attributes helps to detect several format string issues at compile time (even though -Wformat-security is currently disabled in Makefile). For example it can detect when formatting a pointer as a number, like the issue fixed in commit a3fa71c40f18 ("wl18xx: show rx_frames_per_rates as an array as it really is"), or when the arguments do not match the format string, c.f. for example commit 5ce1aca81435 ("reiserfs: fix __RASSERT format string"). To prevent similar bugs in the future, add a __printf attribute to every function prototype which needs one in include/linux/ and lib/. These functions were mostly found by using gcc's -Wsuggest-attribute=format flag. Signed-off-by: Nicolas Iooss Cc: Greg Kroah-Hartman Cc: Felipe Balbi Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/clkdev.h | 7 ++++--- include/linux/compat.h | 2 +- include/linux/configfs.h | 3 ++- include/linux/cpu.h | 7 ++++--- include/linux/dcache.h | 3 ++- include/linux/device.h | 15 +++++++-------- include/linux/iommu.h | 2 +- include/linux/kernel.h | 9 +++++---- include/linux/kobject.h | 5 +++-- include/linux/mmiotrace.h | 2 +- include/linux/printk.h | 6 +++--- 11 files changed, 33 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/linux/clkdev.h b/include/linux/clkdev.h index a240b18e86fa..08bffcc466de 100644 --- a/include/linux/clkdev.h +++ b/include/linux/clkdev.h @@ -33,18 +33,19 @@ struct clk_lookup { } struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id, - const char *dev_fmt, ...); + const char *dev_fmt, ...) __printf(3, 4); void clkdev_add(struct clk_lookup *cl); void clkdev_drop(struct clk_lookup *cl); struct clk_lookup *clkdev_create(struct clk *clk, const char *con_id, - const char *dev_fmt, ...); + const char *dev_fmt, ...) __printf(3, 4); void clkdev_add_table(struct clk_lookup *, size_t); int clk_add_alias(const char *, const char *, const char *, struct device *); -int clk_register_clkdev(struct clk *, const char *, const char *, ...); +int clk_register_clkdev(struct clk *, const char *, const char *, ...) + __printf(3, 4); int clk_register_clkdevs(struct clk *, struct clk_lookup *, size_t); #ifdef CONFIG_COMMON_CLK diff --git a/include/linux/compat.h b/include/linux/compat.h index ab25814690bc..a76c9172b2eb 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -424,7 +424,7 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); -extern int compat_printk(const char *fmt, ...); +extern __printf(1, 2) int compat_printk(const char *fmt, ...); extern void sigset_from_compat(sigset_t *set, const compat_sigset_t *compat); extern void sigset_to_compat(compat_sigset_t *compat, const sigset_t *set); diff --git a/include/linux/configfs.h b/include/linux/configfs.h index c9e5c57e4edf..63a36e89d0eb 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -64,7 +64,8 @@ struct config_item { struct dentry *ci_dentry; }; -extern int config_item_set_name(struct config_item *, const char *, ...); +extern __printf(2, 3) +int config_item_set_name(struct config_item *, const char *, ...); static inline char *config_item_name(struct config_item * item) { diff --git a/include/linux/cpu.h b/include/linux/cpu.h index c0fb6b1b4712..23c30bdcca86 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -40,9 +40,10 @@ extern void cpu_remove_dev_attr(struct device_attribute *attr); extern int cpu_add_dev_attr_group(struct attribute_group *attrs); extern void cpu_remove_dev_attr_group(struct attribute_group *attrs); -extern struct device *cpu_device_create(struct device *parent, void *drvdata, - const struct attribute_group **groups, - const char *fmt, ...); +extern __printf(4, 5) +struct device *cpu_device_create(struct device *parent, void *drvdata, + const struct attribute_group **groups, + const char *fmt, ...); #ifdef CONFIG_HOTPLUG_CPU extern void unregister_cpu(struct cpu *cpu); extern ssize_t arch_cpu_probe(const char *, size_t); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d2d50249b7b2..d67ae119cf4e 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -327,7 +327,8 @@ static inline unsigned d_count(const struct dentry *dentry) /* * helper function for dentry_operations.d_dname() members */ -extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...); +extern __printf(4, 5) +char *dynamic_dname(struct dentry *, char *, int, const char *, ...); extern char *simple_dname(struct dentry *, char *, int); extern char *__d_path(const struct path *, const struct path *, char *, int); diff --git a/include/linux/device.h b/include/linux/device.h index 5a31bf3a4024..a2b4ea70a946 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -637,8 +637,9 @@ extern int devres_release_group(struct device *dev, void *id); /* managed devm_k.alloc/kfree for device drivers */ extern void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp); -extern char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, - va_list ap); +extern __printf(3, 0) +char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, + va_list ap); extern __printf(3, 4) char *devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...); static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp) @@ -1011,12 +1012,10 @@ extern int __must_check device_reprobe(struct device *dev); /* * Easy functions for dynamically creating devices on the fly */ -extern struct device *device_create_vargs(struct class *cls, - struct device *parent, - dev_t devt, - void *drvdata, - const char *fmt, - va_list vargs); +extern __printf(5, 0) +struct device *device_create_vargs(struct class *cls, struct device *parent, + dev_t devt, void *drvdata, + const char *fmt, va_list vargs); extern __printf(5, 6) struct device *device_create(struct class *cls, struct device *parent, dev_t devt, void *drvdata, diff --git a/include/linux/iommu.h b/include/linux/iommu.h index dc767f7c3704..f9c1b6d0f2e4 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -258,7 +258,7 @@ extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr, void *data); struct device *iommu_device_create(struct device *parent, void *drvdata, const struct attribute_group **groups, - const char *fmt, ...); + const char *fmt, ...) __printf(4, 5); void iommu_device_destroy(struct device *dev); int iommu_device_link(struct device *dev, struct device *link); void iommu_device_unlink(struct device *dev, struct device *link); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5f0be58640ea..5582410727cb 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -411,7 +411,8 @@ extern __printf(3, 0) int vscnprintf(char *buf, size_t size, const char *fmt, va_list args); extern __printf(2, 3) char *kasprintf(gfp_t gfp, const char *fmt, ...); -extern char *kvasprintf(gfp_t gfp, const char *fmt, va_list args); +extern __printf(2, 0) +char *kvasprintf(gfp_t gfp, const char *fmt, va_list args); extern __scanf(2, 3) int sscanf(const char *, const char *, ...); @@ -679,10 +680,10 @@ do { \ __ftrace_vprintk(_THIS_IP_, fmt, vargs); \ } while (0) -extern int +extern __printf(2, 0) int __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap); -extern int +extern __printf(2, 0) int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap); extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode); @@ -702,7 +703,7 @@ int trace_printk(const char *fmt, ...) { return 0; } -static inline int +static __printf(1, 0) inline int ftrace_vprintk(const char *fmt, va_list ap) { return 0; diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 2d61b909f414..637f67002c5a 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -80,8 +80,9 @@ struct kobject { extern __printf(2, 3) int kobject_set_name(struct kobject *kobj, const char *name, ...); -extern int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, - va_list vargs); +extern __printf(2, 0) +int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, + va_list vargs); static inline const char *kobject_name(const struct kobject *kobj) { diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h index c5d52780d6a0..3ba327af055c 100644 --- a/include/linux/mmiotrace.h +++ b/include/linux/mmiotrace.h @@ -106,6 +106,6 @@ extern void enable_mmiotrace(void); extern void disable_mmiotrace(void); extern void mmio_trace_rw(struct mmiotrace_rw *rw); extern void mmio_trace_mapping(struct mmiotrace_map *map); -extern int mmio_trace_printk(const char *fmt, va_list args); +extern __printf(1, 0) int mmio_trace_printk(const char *fmt, va_list args); #endif /* _LINUX_MMIOTRACE_H */ diff --git a/include/linux/printk.h b/include/linux/printk.h index 58b1fec40d37..a6298b27ac99 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -122,7 +122,7 @@ static inline __printf(1, 2) __cold void early_printk(const char *s, ...) { } #endif -typedef int(*printk_func_t)(const char *fmt, va_list args); +typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args); #ifdef CONFIG_PRINTK asmlinkage __printf(5, 0) @@ -166,7 +166,7 @@ char *log_buf_addr_get(void); u32 log_buf_len_get(void); void log_buf_kexec_setup(void); void __init setup_log_buf(int early); -void dump_stack_set_arch_desc(const char *fmt, ...); +__printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...); void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); #else @@ -217,7 +217,7 @@ static inline void setup_log_buf(int early) { } -static inline void dump_stack_set_arch_desc(const char *fmt, ...) +static inline __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...) { } -- cgit v1.2.3 From da89947b47a3a355f33a75d7672892c147ed880d Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 17 Jul 2015 16:23:50 -0700 Subject: Update Viresh Kumar's email address Switch to my kernel.org alias instead of a badly named gmail address, which I rarely use. Signed-off-by: Viresh Kumar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/amba/sp810.h | 2 +- include/linux/pata_arasan_cf_data.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/amba/sp810.h b/include/linux/amba/sp810.h index c7df89f99115..58fe9e8b6fd7 100644 --- a/include/linux/amba/sp810.h +++ b/include/linux/amba/sp810.h @@ -2,7 +2,7 @@ * ARM PrimeXsys System Controller SP810 header file * * Copyright (C) 2009 ST Microelectronics - * Viresh Kumar + * Viresh Kumar * * This file is licensed under the terms of the GNU General Public * License version 2. This program is licensed "as is" without any diff --git a/include/linux/pata_arasan_cf_data.h b/include/linux/pata_arasan_cf_data.h index 3cc21c9cc1e8..9fade5dd2e86 100644 --- a/include/linux/pata_arasan_cf_data.h +++ b/include/linux/pata_arasan_cf_data.h @@ -4,7 +4,7 @@ * Arasan Compact Flash host controller platform data header file * * Copyright (C) 2011 ST Microelectronics - * Viresh Kumar + * Viresh Kumar * * This file is licensed under the terms of the GNU General Public * License version 2. This program is licensed "as is" without any -- cgit v1.2.3 From f2abeef9fd6f03ebf417539ed099828a56733098 Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Fri, 17 Jul 2015 16:23:58 -0700 Subject: mm: clean up per architecture MM hook header files Commit 2ae416b142b6 ("mm: new mm hook framework") introduced an empty header file (mm-arch-hooks.h) for every architecture, even those which doesn't need to define mm hooks. As suggested by Geert Uytterhoeven, this could be cleaned through the use of a generic header file included via each per architecture asm/include/Kbuild file. The PowerPC architecture is not impacted here since this architecture has to defined the arch_remap MM hook. Signed-off-by: Laurent Dufour Suggested-by: Geert Uytterhoeven Acked-by: Geert Uytterhoeven Acked-by: Vineet Gupta Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/mm-arch-hooks.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 include/asm-generic/mm-arch-hooks.h (limited to 'include') diff --git a/include/asm-generic/mm-arch-hooks.h b/include/asm-generic/mm-arch-hooks.h new file mode 100644 index 000000000000..5ff0e5193f85 --- /dev/null +++ b/include/asm-generic/mm-arch-hooks.h @@ -0,0 +1,16 @@ +/* + * Architecture specific mm hooks + */ + +#ifndef _ASM_GENERIC_MM_ARCH_HOOKS_H +#define _ASM_GENERIC_MM_ARCH_HOOKS_H + +/* + * This file should be included through arch/../include/asm/Kbuild for + * the architecture which doesn't need specific mm hooks. + * + * In that case, the generic hooks defined in include/linux/mm-arch-hooks.h + * are used. + */ + +#endif /* _ASM_GENERIC_MM_ARCH_HOOKS_H */ -- cgit v1.2.3 From e2cfc91120fa01e3458167054af993fb83d7d0ec Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Fri, 17 Jul 2015 16:24:18 -0700 Subject: mm/page_owner: set correct gfp_mask on page_owner Currently, we set wrong gfp_mask to page_owner info in case of isolated freepage by compaction and split page. It causes incorrect mixed pageblock report that we can get from '/proc/pagetypeinfo'. This metric is really useful to measure fragmentation effect so should be accurate. This patch fixes it by setting correct information. Without this patch, after kernel build workload is finished, number of mixed pageblock is 112 among roughly 210 movable pageblocks. But, with this fix, output shows that mixed pageblock is just 57. Signed-off-by: Joonsoo Kim Cc: Mel Gorman Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_owner.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index b48c3471c254..cacaabea8a09 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -8,6 +8,7 @@ extern struct page_ext_operations page_owner_ops; extern void __reset_page_owner(struct page *page, unsigned int order); extern void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask); +extern gfp_t __get_page_owner_gfp(struct page *page); static inline void reset_page_owner(struct page *page, unsigned int order) { @@ -25,6 +26,14 @@ static inline void set_page_owner(struct page *page, __set_page_owner(page, order, gfp_mask); } + +static inline gfp_t get_page_owner_gfp(struct page *page) +{ + if (likely(!page_owner_inited)) + return 0; + + return __get_page_owner_gfp(page); +} #else static inline void reset_page_owner(struct page *page, unsigned int order) { @@ -33,6 +42,10 @@ static inline void set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) { } +static inline gfp_t get_page_owner_gfp(struct page *page) +{ + return 0; +} #endif /* CONFIG_PAGE_OWNER */ #endif /* __LINUX_PAGE_OWNER_H */ -- cgit v1.2.3 From 0c8c0f03e3a292e031596484275c14cf39c0ab7a Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 17 Jul 2015 12:28:11 +0200 Subject: x86/fpu, sched: Dynamically allocate 'struct fpu' The FPU rewrite removed the dynamic allocations of 'struct fpu'. But, this potentially wastes massive amounts of memory (2k per task on systems that do not have AVX-512 for instance). Instead of having a separate slab, this patch just appends the space that we need to the 'task_struct' which we dynamically allocate already. This saves from doing an extra slab allocation at fork(). The only real downside here is that we have to stick everything and the end of the task_struct. But, I think the BUILD_BUG_ON()s I stuck in there should keep that from being too fragile. Signed-off-by: Dave Hansen Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1437128892-9831-2-git-send-email-mingo@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index ae21f1591615..e43a41d892b6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1522,8 +1522,6 @@ struct task_struct { /* hung task detection */ unsigned long last_switch_count; #endif -/* CPU-specific state of this task */ - struct thread_struct thread; /* filesystem information */ struct fs_struct *fs; /* open file information */ @@ -1778,8 +1776,18 @@ struct task_struct { unsigned long task_state_change; #endif int pagefault_disabled; +/* CPU-specific state of this task */ + struct thread_struct thread; +/* + * WARNING: on x86, 'thread_struct' contains a variable-sized + * structure. It *MUST* be at the end of 'task_struct'. + * + * Do not put anything below here! + */ }; +extern int arch_task_struct_size(void); + /* Future-safe accessor for struct task_struct's cpus_allowed. */ #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) -- cgit v1.2.3 From 5aaeb5c01c5b6c0be7b7aadbf3ace9f3a4458c3d Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 17 Jul 2015 12:28:12 +0200 Subject: x86/fpu, sched: Introduce CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT and use it on x86 Don't burden architectures without dynamic task_struct sizing with the overhead of dynamic sizing. Also optimize the x86 code a bit by caching task_struct_size. Acked-and-Tested-by: Dave Hansen Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1437128892-9831-3-git-send-email-mingo@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index e43a41d892b6..04b5ada460b4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1786,7 +1786,11 @@ struct task_struct { */ }; -extern int arch_task_struct_size(void); +#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT +extern int arch_task_struct_size __read_mostly; +#else +# define arch_task_struct_size (sizeof(struct task_struct)) +#endif /* Future-safe accessor for struct task_struct's cpus_allowed. */ #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) -- cgit v1.2.3