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/linux') 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 --- arch/arm/mach-prima2/Kconfig | 1 + arch/arm/mach-prima2/rtciobrg.c | 48 +++++++++++++++++++++++++++++++++--- include/linux/rtc/sirfsoc_rtciobrg.h | 4 +++ 3 files changed, 50 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-prima2/Kconfig b/arch/arm/mach-prima2/Kconfig index e03d8b5c9ad0..9ab8932403e5 100644 --- a/arch/arm/mach-prima2/Kconfig +++ b/arch/arm/mach-prima2/Kconfig @@ -4,6 +4,7 @@ menuconfig ARCH_SIRF select ARCH_REQUIRE_GPIOLIB select GENERIC_IRQ_CHIP select NO_IOPORT_MAP + select REGMAP select PINCTRL select PINCTRL_SIRF help diff --git a/arch/arm/mach-prima2/rtciobrg.c b/arch/arm/mach-prima2/rtciobrg.c index 8f66d8f7ca75..d4852d24dc7d 100644 --- a/arch/arm/mach-prima2/rtciobrg.c +++ b/arch/arm/mach-prima2/rtciobrg.c @@ -1,5 +1,5 @@ /* - * RTC I/O Bridge interfaces for CSR SiRFprimaII + * RTC I/O Bridge interfaces for CSR SiRFprimaII/atlas7 * ARM access the registers of SYSRTC, GPSRTC and PWRC through this module * * Copyright (c) 2011 Cambridge Silicon Radio Limited, a CSR plc group company. @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -66,6 +67,7 @@ u32 sirfsoc_rtc_iobrg_readl(u32 addr) { unsigned long flags, val; + /* TODO: add hwspinlock to sync with M3 */ spin_lock_irqsave(&rtciobrg_lock, flags); val = __sirfsoc_rtc_iobrg_readl(addr); @@ -90,6 +92,7 @@ void sirfsoc_rtc_iobrg_writel(u32 val, u32 addr) { unsigned long flags; + /* TODO: add hwspinlock to sync with M3 */ spin_lock_irqsave(&rtciobrg_lock, flags); sirfsoc_rtc_iobrg_pre_writel(val, addr); @@ -102,6 +105,45 @@ void sirfsoc_rtc_iobrg_writel(u32 val, u32 addr) } EXPORT_SYMBOL_GPL(sirfsoc_rtc_iobrg_writel); + +static int regmap_iobg_regwrite(void *context, unsigned int reg, + unsigned int val) +{ + sirfsoc_rtc_iobrg_writel(val, reg); + return 0; +} + +static int regmap_iobg_regread(void *context, unsigned int reg, + unsigned int *val) +{ + *val = (u32)sirfsoc_rtc_iobrg_readl(reg); + return 0; +} + +static struct regmap_bus regmap_iobg = { + .reg_write = regmap_iobg_regwrite, + .reg_read = regmap_iobg_regread, +}; + +/** + * devm_regmap_init_iobg(): Initialise managed register map + * + * @iobg: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +struct regmap *devm_regmap_init_iobg(struct device *dev, + const struct regmap_config *config) +{ + const struct regmap_bus *bus = ®map_iobg; + + return devm_regmap_init(dev, bus, dev, config); +} +EXPORT_SYMBOL_GPL(devm_regmap_init_iobg); + static const struct of_device_id rtciobrg_ids[] = { { .compatible = "sirf,prima2-rtciobg" }, {} @@ -132,7 +174,7 @@ static int __init sirfsoc_rtciobrg_init(void) } postcore_initcall(sirfsoc_rtciobrg_init); -MODULE_AUTHOR("Zhiwu Song , " - "Barry Song "); +MODULE_AUTHOR("Zhiwu Song "); +MODULE_AUTHOR("Barry Song "); MODULE_DESCRIPTION("CSR SiRFprimaII rtc io bridge"); MODULE_LICENSE("GPL v2"); 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/linux') 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/linux') 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/linux') 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 --- drivers/acpi/osl.c | 12 +++- drivers/acpi/resource.c | 162 ------------------------------------------------ drivers/pnp/system.c | 35 +++-------- include/linux/acpi.h | 10 --- 4 files changed, 18 insertions(+), 201 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index c262e4acd68d..3b8963f21b36 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -175,10 +175,14 @@ static void __init acpi_request_region (struct acpi_generic_address *gas, if (!addr || !length) return; - acpi_reserve_region(addr, length, gas->space_id, 0, desc); + /* Resources are never freed */ + if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO) + request_region(addr, length, desc); + else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) + request_mem_region(addr, length, desc); } -static void __init acpi_reserve_resources(void) +static int __init acpi_reserve_resources(void) { acpi_request_region(&acpi_gbl_FADT.xpm1a_event_block, acpi_gbl_FADT.pm1_event_length, "ACPI PM1a_EVT_BLK"); @@ -207,7 +211,10 @@ static void __init acpi_reserve_resources(void) if (!(acpi_gbl_FADT.gpe1_block_length & 0x1)) acpi_request_region(&acpi_gbl_FADT.xgpe1_block, acpi_gbl_FADT.gpe1_block_length, "ACPI GPE1_BLK"); + + return 0; } +fs_initcall_sync(acpi_reserve_resources); void acpi_os_printf(const char *fmt, ...) { @@ -1862,7 +1869,6 @@ acpi_status __init acpi_os_initialize(void) acpi_status __init acpi_os_initialize1(void) { - acpi_reserve_resources(); kacpid_wq = alloc_workqueue("kacpid", 0, 1); kacpi_notify_wq = alloc_workqueue("kacpi_notify", 0, 1); kacpi_hotplug_wq = alloc_ordered_workqueue("kacpi_hotplug", 0); diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 10561ce16ed1..8244f013f210 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #ifdef CONFIG_X86 @@ -622,164 +621,3 @@ int acpi_dev_filter_resource_type(struct acpi_resource *ares, return (type & types) ? 0 : 1; } EXPORT_SYMBOL_GPL(acpi_dev_filter_resource_type); - -struct reserved_region { - struct list_head node; - u64 start; - u64 end; -}; - -static LIST_HEAD(reserved_io_regions); -static LIST_HEAD(reserved_mem_regions); - -static int request_range(u64 start, u64 end, u8 space_id, unsigned long flags, - char *desc) -{ - unsigned int length = end - start + 1; - struct resource *res; - - res = space_id == ACPI_ADR_SPACE_SYSTEM_IO ? - request_region(start, length, desc) : - request_mem_region(start, length, desc); - if (!res) - return -EIO; - - res->flags &= ~flags; - return 0; -} - -static int add_region_before(u64 start, u64 end, u8 space_id, - unsigned long flags, char *desc, - struct list_head *head) -{ - struct reserved_region *reg; - int error; - - reg = kmalloc(sizeof(*reg), GFP_KERNEL); - if (!reg) - return -ENOMEM; - - error = request_range(start, end, space_id, flags, desc); - if (error) { - kfree(reg); - return error; - } - - reg->start = start; - reg->end = end; - list_add_tail(®->node, head); - return 0; -} - -/** - * acpi_reserve_region - Reserve an I/O or memory region as a system resource. - * @start: Starting address of the region. - * @length: Length of the region. - * @space_id: Identifier of address space to reserve the region from. - * @flags: Resource flags to clear for the region after requesting it. - * @desc: Region description (for messages). - * - * Reserve an I/O or memory region as a system resource to prevent others from - * using it. If the new region overlaps with one of the regions (in the given - * address space) already reserved by this routine, only the non-overlapping - * parts of it will be reserved. - * - * Returned is either 0 (success) or a negative error code indicating a resource - * reservation problem. It is the code of the first encountered error, but the - * routine doesn't abort until it has attempted to request all of the parts of - * the new region that don't overlap with other regions reserved previously. - * - * The resources requested by this routine are never released. - */ -int acpi_reserve_region(u64 start, unsigned int length, u8 space_id, - unsigned long flags, char *desc) -{ - struct list_head *regions; - struct reserved_region *reg; - u64 end = start + length - 1; - int ret = 0, error = 0; - - if (space_id == ACPI_ADR_SPACE_SYSTEM_IO) - regions = &reserved_io_regions; - else if (space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) - regions = &reserved_mem_regions; - else - return -EINVAL; - - if (list_empty(regions)) - return add_region_before(start, end, space_id, flags, desc, regions); - - list_for_each_entry(reg, regions, node) - if (reg->start == end + 1) { - /* The new region can be prepended to this one. */ - ret = request_range(start, end, space_id, flags, desc); - if (!ret) - reg->start = start; - - return ret; - } else if (reg->start > end) { - /* No overlap. Add the new region here and get out. */ - return add_region_before(start, end, space_id, flags, - desc, ®->node); - } else if (reg->end == start - 1) { - goto combine; - } else if (reg->end >= start) { - goto overlap; - } - - /* The new region goes after the last existing one. */ - return add_region_before(start, end, space_id, flags, desc, regions); - - overlap: - /* - * The new region overlaps an existing one. - * - * The head part of the new region immediately preceding the existing - * overlapping one can be combined with it right away. - */ - if (reg->start > start) { - error = request_range(start, reg->start - 1, space_id, flags, desc); - if (error) - ret = error; - else - reg->start = start; - } - - combine: - /* - * The new region is adjacent to an existing one. If it extends beyond - * that region all the way to the next one, it is possible to combine - * all three of them. - */ - while (reg->end < end) { - struct reserved_region *next = NULL; - u64 a = reg->end + 1, b = end; - - if (!list_is_last(®->node, regions)) { - next = list_next_entry(reg, node); - if (next->start <= end) - b = next->start - 1; - } - error = request_range(a, b, space_id, flags, desc); - if (!error) { - if (next && next->start == b + 1) { - reg->end = next->end; - list_del(&next->node); - kfree(next); - } else { - reg->end = end; - break; - } - } else if (next) { - if (!ret) - ret = error; - - reg = next; - } else { - break; - } - } - - return ret ? ret : error; -} -EXPORT_SYMBOL_GPL(acpi_reserve_region); diff --git a/drivers/pnp/system.c b/drivers/pnp/system.c index 515f33882ab8..49c1720df59a 100644 --- a/drivers/pnp/system.c +++ b/drivers/pnp/system.c @@ -7,7 +7,6 @@ * Bjorn Helgaas */ -#include #include #include #include @@ -23,41 +22,25 @@ static const struct pnp_device_id pnp_dev_table[] = { {"", 0} }; -#ifdef CONFIG_ACPI -static bool __reserve_range(u64 start, unsigned int length, bool io, char *desc) -{ - u8 space_id = io ? ACPI_ADR_SPACE_SYSTEM_IO : ACPI_ADR_SPACE_SYSTEM_MEMORY; - return !acpi_reserve_region(start, length, space_id, IORESOURCE_BUSY, desc); -} -#else -static bool __reserve_range(u64 start, unsigned int length, bool io, char *desc) -{ - struct resource *res; - - res = io ? request_region(start, length, desc) : - request_mem_region(start, length, desc); - if (res) { - res->flags &= ~IORESOURCE_BUSY; - return true; - } - return false; -} -#endif - static void reserve_range(struct pnp_dev *dev, struct resource *r, int port) { char *regionid; const char *pnpid = dev_name(&dev->dev); resource_size_t start = r->start, end = r->end; - bool reserved; + struct resource *res; regionid = kmalloc(16, GFP_KERNEL); if (!regionid) return; snprintf(regionid, 16, "pnp %s", pnpid); - reserved = __reserve_range(start, end - start + 1, !!port, regionid); - if (!reserved) + if (port) + res = request_region(start, end - start + 1, regionid); + else + res = request_mem_region(start, end - start + 1, regionid); + if (res) + res->flags &= ~IORESOURCE_BUSY; + else kfree(regionid); /* @@ -66,7 +49,7 @@ static void reserve_range(struct pnp_dev *dev, struct resource *r, int port) * have double reservations. */ dev_info(&dev->dev, "%pR %s reserved\n", r, - reserved ? "has been" : "could not be"); + res ? "has been" : "could not be"); } static void reserve_resources_of_dev(struct pnp_dev *dev) 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 --- drivers/acpi/scan.c | 32 ++++++++++++++++++++++++++++++-- include/linux/acpi.h | 14 ++++++++++++++ include/linux/mod_devicetable.h | 2 ++ scripts/mod/devicetable-offsets.c | 2 ++ scripts/mod/file2alias.c | 32 ++++++++++++++++++++++++++++++-- 5 files changed, 78 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 2649a068671d..ec256352f423 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1019,6 +1019,29 @@ static bool acpi_of_match_device(struct acpi_device *adev, return false; } +static bool __acpi_match_device_cls(const struct acpi_device_id *id, + struct acpi_hardware_id *hwid) +{ + int i, msk, byte_shift; + char buf[3]; + + if (!id->cls) + return false; + + /* Apply class-code bitmask, before checking each class-code byte */ + for (i = 1; i <= 3; i++) { + byte_shift = 8 * (3 - i); + msk = (id->cls_msk >> byte_shift) & 0xFF; + if (!msk) + continue; + + sprintf(buf, "%02x", (id->cls >> byte_shift) & msk); + if (strncmp(buf, &hwid->id[(i - 1) * 2], 2)) + return false; + } + return true; +} + static const struct acpi_device_id *__acpi_match_device( struct acpi_device *device, const struct acpi_device_id *ids, @@ -1036,9 +1059,12 @@ static const struct acpi_device_id *__acpi_match_device( list_for_each_entry(hwid, &device->pnp.ids, list) { /* First, check the ACPI/PNP IDs provided by the caller. */ - for (id = ids; id->id[0]; id++) - if (!strcmp((char *) id->id, hwid->id)) + for (id = ids; id->id[0] || id->cls; id++) { + if (id->id[0] && !strcmp((char *) id->id, hwid->id)) return id; + else if (id->cls && __acpi_match_device_cls(id, hwid)) + return id; + } /* * Next, check ACPI_DT_NAMESPACE_HID and try to match the @@ -2101,6 +2127,8 @@ static void acpi_set_pnp_ids(acpi_handle handle, struct acpi_device_pnp *pnp, if (info->valid & ACPI_VALID_UID) pnp->unique_id = kstrdup(info->unique_id.string, GFP_KERNEL); + if (info->valid & ACPI_VALID_CLS) + acpi_add_id(pnp, info->class_code.string); kfree(info); 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 diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c index eff7de1fc82e..e70fcd12eeeb 100644 --- a/scripts/mod/devicetable-offsets.c +++ b/scripts/mod/devicetable-offsets.c @@ -63,6 +63,8 @@ int main(void) DEVID(acpi_device_id); DEVID_FIELD(acpi_device_id, id); + DEVID_FIELD(acpi_device_id, cls); + DEVID_FIELD(acpi_device_id, cls_msk); DEVID(pnp_device_id); DEVID_FIELD(pnp_device_id, id); diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 84c86f3cd6cd..5f2088209132 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -523,12 +523,40 @@ static int do_serio_entry(const char *filename, } ADD_TO_DEVTABLE("serio", serio_device_id, do_serio_entry); -/* looks like: "acpi:ACPI0003 or acpi:PNP0C0B" or "acpi:LNXVIDEO" */ +/* looks like: "acpi:ACPI0003" or "acpi:PNP0C0B" or "acpi:LNXVIDEO" or + * "acpi:bbsspp" (bb=base-class, ss=sub-class, pp=prog-if) + * + * NOTE: Each driver should use one of the following : _HID, _CIDs + * or _CLS. Also, bb, ss, and pp can be substituted with ?? + * as don't care byte. + */ static int do_acpi_entry(const char *filename, void *symval, char *alias) { DEF_FIELD_ADDR(symval, acpi_device_id, id); - sprintf(alias, "acpi*:%s:*", *id); + DEF_FIELD_ADDR(symval, acpi_device_id, cls); + DEF_FIELD_ADDR(symval, acpi_device_id, cls_msk); + + if (id && strlen((const char *)*id)) + sprintf(alias, "acpi*:%s:*", *id); + else if (cls) { + int i, byte_shift, cnt = 0; + unsigned int msk; + + sprintf(&alias[cnt], "acpi*:"); + cnt = 6; + for (i = 1; i <= 3; i++) { + byte_shift = 8 * (3-i); + msk = (*cls_msk >> byte_shift) & 0xFF; + if (msk) + sprintf(&alias[cnt], "%02x", + (*cls >> byte_shift) & 0xFF); + else + sprintf(&alias[cnt], "??"); + cnt += 2; + } + sprintf(&alias[cnt], ":*"); + } return 1; } ADD_TO_DEVTABLE("acpi", acpi_device_id, do_acpi_entry); -- 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 ---- kernel/time/tick-broadcast.c | 26 +++++++++++--------------- kernel/time/tick-common.c | 21 +++++++++++++++++++++ kernel/time/tick-sched.h | 10 ++++++++++ 4 files changed, 42 insertions(+), 19 deletions(-) (limited to 'include/linux') 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) { diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 9877d0b0aefc..ef77b16ad5df 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -685,18 +685,7 @@ static void broadcast_shutdown_local(struct clock_event_device *bc, clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN); } -/** - * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode - * @state: The target state (enter/exit) - * - * The system enters/leaves a state, where affected devices might stop - * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups. - * - * Called with interrupts disabled, so clockevents_lock is not - * required here because the local clock event device cannot go away - * under us. - */ -int tick_broadcast_oneshot_control(enum tick_broadcast_state state) +int __tick_broadcast_oneshot_control(enum tick_broadcast_state state) { struct clock_event_device *bc, *dev; struct tick_device *td; @@ -717,9 +706,6 @@ int tick_broadcast_oneshot_control(enum tick_broadcast_state state) td = this_cpu_ptr(&tick_cpu_device); dev = td->evtdev; - if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) - return 0; - raw_spin_lock(&tick_broadcast_lock); bc = tick_broadcast_device.evtdev; cpu = smp_processor_id(); @@ -961,6 +947,16 @@ bool tick_broadcast_oneshot_available(void) return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false; } +#else +int __tick_broadcast_oneshot_control(enum tick_broadcast_state state) +{ + struct clock_event_device *bc = tick_broadcast_device.evtdev; + + if (!bc || (bc->features & CLOCK_EVT_FEAT_HRTIMER)) + return -EBUSY; + + return 0; +} #endif void __init tick_broadcast_init(void) diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 76446cb5dfe1..55e13efff1ab 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -343,6 +343,27 @@ out_bc: tick_install_broadcast_device(newdev); } +/** + * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode + * @state: The target state (enter/exit) + * + * The system enters/leaves a state, where affected devices might stop + * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups. + * + * Called with interrupts disabled, so clockevents_lock is not + * required here because the local clock event device cannot go away + * under us. + */ +int tick_broadcast_oneshot_control(enum tick_broadcast_state state) +{ + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); + + if (!(td->evtdev->features & CLOCK_EVT_FEAT_C3STOP)) + return 0; + + return __tick_broadcast_oneshot_control(state); +} + #ifdef CONFIG_HOTPLUG_CPU /* * Transfer the do_timer job away from a dying cpu. diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index 42fdf4958bcc..a4a8d4e9baa1 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -71,4 +71,14 @@ extern void tick_cancel_sched_timer(int cpu); static inline void tick_cancel_sched_timer(int cpu) { } #endif +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +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 -EBUSY; +} +#endif + #endif -- 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/linux') 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 5f867db63473f32cce1b868e281ebd42a41f8fad Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Fri, 26 Jun 2015 19:43:58 -0500 Subject: mtd: nand: Fix NAND_USE_BOUNCE_BUFFER flag conflict Commit 66507c7bc8895f0da6b ("mtd: nand: Add support to use nand_base poi databuf as bounce buffer") added a flag NAND_USE_BOUNCE_BUFFER using the same bit value as the existing NAND_BUSWIDTH_AUTO. Cc: Kamal Dasu Fixes: 66507c7bc8895f0da6b ("mtd: nand: Add support to use nand_base poi databuf as bounce buffer") Signed-off-by: Scott Wood Signed-off-by: Brian Norris --- include/linux/mtd/nand.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index f25e2bdd188c..272f42952f34 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -177,11 +177,6 @@ typedef enum { #define NAND_OWN_BUFFERS 0x00020000 /* Chip may not exist, so silence any errors in scan */ #define NAND_SCAN_SILENT_NODEV 0x00040000 -/* - * This option could be defined by controller drivers to protect against - * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers - */ -#define NAND_USE_BOUNCE_BUFFER 0x00080000 /* * Autodetect nand buswidth with readid/onfi. * This suppose the driver will configure the hardware in 8 bits mode @@ -189,6 +184,11 @@ typedef enum { * before calling nand_scan_tail. */ #define NAND_BUSWIDTH_AUTO 0x00080000 +/* + * This option could be defined by controller drivers to protect against + * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers + */ +#define NAND_USE_BOUNCE_BUFFER 0x00100000 /* Options set by nand scan */ /* Nand scan has allocated controller struct */ -- 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 ++++++- kernel/cpu.c | 22 +++++++++++++++++++++- kernel/irq/internals.h | 4 ---- 3 files changed, 27 insertions(+), 6 deletions(-) (limited to 'include/linux') 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 diff --git a/kernel/cpu.c b/kernel/cpu.c index 9c9c9fab16cc..6a374544d495 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include "smpboot.h" @@ -392,13 +393,19 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) smpboot_park_threads(cpu); /* - * So now all preempt/rcu users must observe !cpu_active(). + * Prevent irq alloc/free while the dying cpu reorganizes the + * interrupt affinities. */ + irq_lock_sparse(); + /* + * So now all preempt/rcu users must observe !cpu_active(). + */ err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); if (err) { /* CPU didn't die: tell everyone. Can't complain. */ cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu); + irq_unlock_sparse(); goto out_release; } BUG_ON(cpu_online(cpu)); @@ -415,6 +422,9 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */ per_cpu(cpu_dead_idle, cpu) = false; + /* Interrupts are moved away from the dying cpu, reenable alloc/free */ + irq_unlock_sparse(); + hotplug_cpu__broadcast_tick_pull(cpu); /* This actually kills the CPU. */ __cpu_die(cpu); @@ -517,8 +527,18 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen) goto out_notify; } + /* + * Some architectures have to walk the irq descriptors to + * setup the vector space for the cpu which comes online. + * Prevent irq alloc/free across the bringup. + */ + irq_lock_sparse(); + /* Arch-specific enabling code. */ ret = __cpu_up(cpu, idle); + + irq_unlock_sparse(); + if (ret != 0) goto out_notify; BUG_ON(!cpu_online(cpu)); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 4834ee828c41..61008b8433ab 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -76,12 +76,8 @@ extern void unmask_threaded_irq(struct irq_desc *desc); #ifdef CONFIG_SPARSE_IRQ static inline void irq_mark_irq(unsigned int irq) { } -extern void irq_lock_sparse(void); -extern void irq_unlock_sparse(void); #else extern void irq_mark_irq(unsigned int irq); -static inline void irq_lock_sparse(void) { } -static inline void irq_unlock_sparse(void) { } #endif extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr); -- 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/linux') 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 +++ net/ceph/ceph_common.c | 16 ++++++++++------ net/ceph/messenger.c | 10 +++++++++- 3 files changed, 22 insertions(+), 7 deletions(-) (limited to 'include/linux') 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, diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index cb7db320dd27..f30329f72641 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -16,8 +17,6 @@ #include #include #include -#include -#include #include @@ -131,6 +130,13 @@ int ceph_compare_options(struct ceph_options *new_opt, int i; int ret; + /* + * Don't bother comparing options if network namespaces don't + * match. + */ + if (!net_eq(current->nsproxy->net_ns, read_pnet(&client->msgr.net))) + return -1; + ret = memcmp(opt1, opt2, ofs); if (ret) return ret; @@ -335,9 +341,6 @@ ceph_parse_options(char *options, const char *dev_name, int err = -ENOMEM; substring_t argstr[MAX_OPT_ARGS]; - if (current->nsproxy->net_ns != &init_net) - return ERR_PTR(-EINVAL); - opt = kzalloc(sizeof(*opt), GFP_KERNEL); if (!opt) return ERR_PTR(-ENOMEM); @@ -608,6 +611,7 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, fail_monc: ceph_monc_stop(&client->monc); fail: + ceph_messenger_fini(&client->msgr); kfree(client); return ERR_PTR(err); } @@ -621,8 +625,8 @@ void ceph_destroy_client(struct ceph_client *client) /* unmount */ ceph_osdc_stop(&client->osdc); - ceph_monc_stop(&client->monc); + ceph_messenger_fini(&client->msgr); ceph_debugfs_client_cleanup(client); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 1679f47280e2..5c1f98ea6741 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -479,7 +480,7 @@ static int ceph_tcp_connect(struct ceph_connection *con) int ret; BUG_ON(con->sock); - ret = sock_create_kern(&init_net, con->peer_addr.in_addr.ss_family, + ret = sock_create_kern(read_pnet(&con->msgr->net), paddr->ss_family, SOCK_STREAM, IPPROTO_TCP, &sock); if (ret) return ret; @@ -2944,11 +2945,18 @@ void ceph_messenger_init(struct ceph_messenger *msgr, msgr->tcp_nodelay = tcp_nodelay; atomic_set(&msgr->stopping, 0); + write_pnet(&msgr->net, get_net(current->nsproxy->net_ns)); dout("%s %p\n", __func__, msgr); } EXPORT_SYMBOL(ceph_messenger_init); +void ceph_messenger_fini(struct ceph_messenger *msgr) +{ + put_net(read_pnet(&msgr->net)); +} +EXPORT_SYMBOL(ceph_messenger_fini); + static void clear_standby(struct ceph_connection *con) { /* come back from STANDBY? */ -- 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 --- block/blk-cgroup.c | 17 ++++++++++++----- include/linux/blk-cgroup.h | 1 + 2 files changed, 13 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 05b893de516b..42ff436ffaf4 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -46,6 +46,8 @@ struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css; static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; +static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */ + static bool blkcg_policy_enabled(struct request_queue *q, const struct blkcg_policy *pol) { @@ -817,6 +819,10 @@ static void blkcg_css_free(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); + mutex_lock(&blkcg_pol_mutex); + list_del(&blkcg->all_blkcgs_node); + mutex_unlock(&blkcg_pol_mutex); + if (blkcg != &blkcg_root) { int i; @@ -833,6 +839,8 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css) struct cgroup_subsys_state *ret; int i; + mutex_lock(&blkcg_pol_mutex); + if (!parent_css) { blkcg = &blkcg_root; goto done; @@ -844,8 +852,6 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css) goto free_blkcg; } - mutex_lock(&blkcg_pol_mutex); - for (i = 0; i < BLKCG_MAX_POLS ; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkcg_policy_data *cpd; @@ -862,7 +868,6 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css) BUG_ON(blkcg->pd[i]); cpd = kzalloc(pol->cpd_size, GFP_KERNEL); if (!cpd) { - mutex_unlock(&blkcg_pol_mutex); ret = ERR_PTR(-ENOMEM); goto free_pd_blkcg; } @@ -871,7 +876,6 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css) pol->cpd_init_fn(blkcg); } - mutex_unlock(&blkcg_pol_mutex); done: spin_lock_init(&blkcg->lock); INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_ATOMIC); @@ -879,14 +883,17 @@ done: #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&blkcg->cgwb_list); #endif + list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs); + + mutex_unlock(&blkcg_pol_mutex); return &blkcg->css; free_pd_blkcg: for (i--; i >= 0; i--) kfree(blkcg->pd[i]); - free_blkcg: kfree(blkcg); + mutex_unlock(&blkcg_pol_mutex); return ret; } 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 --- block/blk-cgroup.c | 78 +++++++++++++++++++++++++--------------------- include/linux/blk-cgroup.h | 10 ++---- 2 files changed, 44 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 42ff436ffaf4..9da02c021ebe 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1048,10 +1048,8 @@ int blkcg_activate_policy(struct request_queue *q, const struct blkcg_policy *pol) { LIST_HEAD(pds); - LIST_HEAD(cpds); struct blkcg_gq *blkg; struct blkg_policy_data *pd, *nd; - struct blkcg_policy_data *cpd, *cnd; int cnt = 0, ret; if (blkcg_policy_enabled(q, pol)) @@ -1064,10 +1062,7 @@ int blkcg_activate_policy(struct request_queue *q, cnt++; spin_unlock_irq(q->queue_lock); - /* - * Allocate per-blkg and per-blkcg policy data - * for all existing blkgs. - */ + /* allocate per-blkg policy data for all existing blkgs */ while (cnt--) { pd = kzalloc_node(pol->pd_size, GFP_KERNEL, q->node); if (!pd) { @@ -1075,15 +1070,6 @@ int blkcg_activate_policy(struct request_queue *q, goto out_free; } list_add_tail(&pd->alloc_node, &pds); - - if (!pol->cpd_size) - continue; - cpd = kzalloc_node(pol->cpd_size, GFP_KERNEL, q->node); - if (!cpd) { - ret = -ENOMEM; - goto out_free; - } - list_add_tail(&cpd->alloc_node, &cpds); } /* @@ -1093,32 +1079,17 @@ int blkcg_activate_policy(struct request_queue *q, spin_lock_irq(q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { - if (WARN_ON(list_empty(&pds)) || - WARN_ON(pol->cpd_size && list_empty(&cpds))) { + if (WARN_ON(list_empty(&pds))) { /* umm... this shouldn't happen, just abort */ ret = -ENOMEM; goto out_unlock; } - cpd = list_first_entry(&cpds, struct blkcg_policy_data, - alloc_node); - list_del_init(&cpd->alloc_node); pd = list_first_entry(&pds, struct blkg_policy_data, alloc_node); list_del_init(&pd->alloc_node); /* grab blkcg lock too while installing @pd on @blkg */ spin_lock(&blkg->blkcg->lock); - if (!pol->cpd_size) - goto no_cpd; - if (!blkg->blkcg->pd[pol->plid]) { - /* Per-policy per-blkcg data */ - blkg->blkcg->pd[pol->plid] = cpd; - cpd->plid = pol->plid; - pol->cpd_init_fn(blkg->blkcg); - } else { /* must free it as it has already been extracted */ - kfree(cpd); - } -no_cpd: blkg->pd[pol->plid] = pd; pd->blkg = blkg; pd->plid = pol->plid; @@ -1135,8 +1106,6 @@ out_free: blk_queue_bypass_end(q); list_for_each_entry_safe(pd, nd, &pds, alloc_node) kfree(pd); - list_for_each_entry_safe(cpd, cnd, &cpds, alloc_node) - kfree(cpd); return ret; } EXPORT_SYMBOL_GPL(blkcg_activate_policy); @@ -1191,6 +1160,7 @@ EXPORT_SYMBOL_GPL(blkcg_deactivate_policy); */ int blkcg_policy_register(struct blkcg_policy *pol) { + struct blkcg *blkcg; int i, ret; if (WARN_ON(pol->pd_size < sizeof(struct blkg_policy_data))) @@ -1207,9 +1177,27 @@ int blkcg_policy_register(struct blkcg_policy *pol) if (i >= BLKCG_MAX_POLS) goto err_unlock; - /* register and update blkgs */ + /* register @pol */ pol->plid = i; - blkcg_policy[i] = pol; + blkcg_policy[pol->plid] = pol; + + /* allocate and install cpd's */ + if (pol->cpd_size) { + list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { + struct blkcg_policy_data *cpd; + + cpd = kzalloc(pol->cpd_size, GFP_KERNEL); + if (!cpd) { + mutex_unlock(&blkcg_pol_mutex); + goto err_free_cpds; + } + + blkcg->pd[pol->plid] = cpd; + cpd->plid = pol->plid; + pol->cpd_init_fn(blkcg); + } + } + mutex_unlock(&blkcg_pol_mutex); /* everything is in place, add intf files for the new policy */ @@ -1219,6 +1207,14 @@ int blkcg_policy_register(struct blkcg_policy *pol) mutex_unlock(&blkcg_pol_register_mutex); return 0; +err_free_cpds: + if (pol->cpd_size) { + list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { + kfree(blkcg->pd[pol->plid]); + blkcg->pd[pol->plid] = NULL; + } + } + blkcg_policy[pol->plid] = NULL; err_unlock: mutex_unlock(&blkcg_pol_mutex); mutex_unlock(&blkcg_pol_register_mutex); @@ -1234,6 +1230,8 @@ EXPORT_SYMBOL_GPL(blkcg_policy_register); */ void blkcg_policy_unregister(struct blkcg_policy *pol) { + struct blkcg *blkcg; + mutex_lock(&blkcg_pol_register_mutex); if (WARN_ON(blkcg_policy[pol->plid] != pol)) @@ -1243,9 +1241,17 @@ void blkcg_policy_unregister(struct blkcg_policy *pol) if (pol->cftypes) cgroup_rm_cftypes(pol->cftypes); - /* unregister and update blkgs */ + /* remove cpds and unregister */ mutex_lock(&blkcg_pol_mutex); + + if (pol->cpd_size) { + list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { + kfree(blkcg->pd[pol->plid]); + blkcg->pd[pol->plid] = NULL; + } + } blkcg_policy[pol->plid] = NULL; + mutex_unlock(&blkcg_pol_mutex); out_unlock: mutex_unlock(&blkcg_pol_register_mutex); 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 --- drivers/net/usb/cdc_mbim.c | 2 +- drivers/net/usb/cdc_ncm.c | 61 ++++++++++++++++++++++++++++++++++++---- drivers/net/usb/huawei_cdc_ncm.c | 7 +++-- include/linux/usb/cdc_ncm.h | 7 ++++- 4 files changed, 67 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index e4b7a47a825c..efc18e05af0a 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -158,7 +158,7 @@ static int cdc_mbim_bind(struct usbnet *dev, struct usb_interface *intf) if (!cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting)) goto err; - ret = cdc_ncm_bind_common(dev, intf, data_altsetting); + ret = cdc_ncm_bind_common(dev, intf, data_altsetting, 0); if (ret) goto err; diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 8067b8fbb0ee..1991e4a24657 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -684,10 +684,12 @@ static void cdc_ncm_free(struct cdc_ncm_ctx *ctx) ctx->tx_curr_skb = NULL; } + kfree(ctx->delayed_ndp16); + kfree(ctx); } -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) { const struct usb_cdc_union_desc *union_desc = NULL; struct cdc_ncm_ctx *ctx; @@ -855,6 +857,17 @@ advance: /* finish setting up the device specific data */ cdc_ncm_setup(dev); + /* Device-specific flags */ + ctx->drvflags = drvflags; + + /* Allocate the delayed NDP if needed. */ + if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) { + ctx->delayed_ndp16 = kzalloc(ctx->max_ndp_size, GFP_KERNEL); + if (!ctx->delayed_ndp16) + goto error2; + dev_info(&intf->dev, "NDP will be placed at end of frame for this device."); + } + /* override ethtool_ops */ dev->net->ethtool_ops = &cdc_ncm_ethtool_ops; @@ -954,8 +967,11 @@ static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf) if (cdc_ncm_select_altsetting(intf) != CDC_NCM_COMM_ALTSETTING_NCM) return -ENODEV; - /* The NCM data altsetting is fixed */ - ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM); + /* The NCM data altsetting is fixed, so we hard-coded it. + * Additionally, generic NCM devices are assumed to accept arbitrarily + * placed NDP. + */ + ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0); /* * We should get an event when network connection is "connected" or @@ -986,6 +1002,14 @@ static struct usb_cdc_ncm_ndp16 *cdc_ncm_ndp(struct cdc_ncm_ctx *ctx, struct sk_ struct usb_cdc_ncm_nth16 *nth16 = (void *)skb->data; size_t ndpoffset = le16_to_cpu(nth16->wNdpIndex); + /* If NDP should be moved to the end of the NCM package, we can't follow the + * NTH16 header as we would normally do. NDP isn't written to the SKB yet, and + * the wNdpIndex field in the header is actually not consistent with reality. It will be later. + */ + if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) + if (ctx->delayed_ndp16->dwSignature == sign) + return ctx->delayed_ndp16; + /* follow the chain of NDPs, looking for a match */ while (ndpoffset) { ndp16 = (struct usb_cdc_ncm_ndp16 *)(skb->data + ndpoffset); @@ -995,7 +1019,8 @@ static struct usb_cdc_ncm_ndp16 *cdc_ncm_ndp(struct cdc_ncm_ctx *ctx, struct sk_ } /* align new NDP */ - cdc_ncm_align_tail(skb, ctx->tx_ndp_modulus, 0, ctx->tx_max); + if (!(ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END)) + cdc_ncm_align_tail(skb, ctx->tx_ndp_modulus, 0, ctx->tx_max); /* verify that there is room for the NDP and the datagram (reserve) */ if ((ctx->tx_max - skb->len - reserve) < ctx->max_ndp_size) @@ -1008,7 +1033,11 @@ static struct usb_cdc_ncm_ndp16 *cdc_ncm_ndp(struct cdc_ncm_ctx *ctx, struct sk_ nth16->wNdpIndex = cpu_to_le16(skb->len); /* push a new empty NDP */ - ndp16 = (struct usb_cdc_ncm_ndp16 *)memset(skb_put(skb, ctx->max_ndp_size), 0, ctx->max_ndp_size); + if (!(ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END)) + ndp16 = (struct usb_cdc_ncm_ndp16 *)memset(skb_put(skb, ctx->max_ndp_size), 0, ctx->max_ndp_size); + else + ndp16 = ctx->delayed_ndp16; + ndp16->dwSignature = sign; ndp16->wLength = cpu_to_le16(sizeof(struct usb_cdc_ncm_ndp16) + sizeof(struct usb_cdc_ncm_dpe16)); return ndp16; @@ -1023,6 +1052,15 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) struct sk_buff *skb_out; u16 n = 0, index, ndplen; u8 ready2send = 0; + u32 delayed_ndp_size; + + /* When our NDP gets written in cdc_ncm_ndp(), then skb_out->len gets updated + * accordingly. Otherwise, we should check here. + */ + if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) + delayed_ndp_size = ctx->max_ndp_size; + else + delayed_ndp_size = 0; /* if there is a remaining skb, it gets priority */ if (skb != NULL) { @@ -1077,7 +1115,7 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) cdc_ncm_align_tail(skb_out, ctx->tx_modulus, ctx->tx_remainder, ctx->tx_max); /* check if we had enough room left for both NDP and frame */ - if (!ndp16 || skb_out->len + skb->len > ctx->tx_max) { + if (!ndp16 || skb_out->len + skb->len + delayed_ndp_size > ctx->tx_max) { if (n == 0) { /* won't fit, MTU problem? */ dev_kfree_skb_any(skb); @@ -1150,6 +1188,17 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) /* variables will be reset at next call */ } + /* If requested, put NDP at end of frame. */ + if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) { + nth16 = (struct usb_cdc_ncm_nth16 *)skb_out->data; + cdc_ncm_align_tail(skb_out, ctx->tx_ndp_modulus, 0, ctx->tx_max); + nth16->wNdpIndex = cpu_to_le16(skb_out->len); + memcpy(skb_put(skb_out, ctx->max_ndp_size), ctx->delayed_ndp16, ctx->max_ndp_size); + + /* Zero out delayed NDP - signature checking will naturally fail. */ + ndp16 = memset(ctx->delayed_ndp16, 0, ctx->max_ndp_size); + } + /* If collected data size is less or equal ctx->min_tx_pkt * bytes, we send buffers as it is. If we get more data, it * would be more efficient for USB HS mobile device with DMA diff --git a/drivers/net/usb/huawei_cdc_ncm.c b/drivers/net/usb/huawei_cdc_ncm.c index 735f7dadb9a0..2680a65cd5e4 100644 --- a/drivers/net/usb/huawei_cdc_ncm.c +++ b/drivers/net/usb/huawei_cdc_ncm.c @@ -73,11 +73,14 @@ static int huawei_cdc_ncm_bind(struct usbnet *usbnet_dev, struct usb_driver *subdriver = ERR_PTR(-ENODEV); int ret = -ENODEV; struct huawei_cdc_ncm_state *drvstate = (void *)&usbnet_dev->data; + int drvflags = 0; /* altsetting should always be 1 for NCM devices - so we hard-coded - * it here + * it here. Some huawei devices will need the NDP part of the NCM package to + * be at the end of the frame. */ - ret = cdc_ncm_bind_common(usbnet_dev, intf, 1); + drvflags |= CDC_NCM_FLAG_NDP_TO_END; + ret = cdc_ncm_bind_common(usbnet_dev, intf, 1, drvflags); if (ret) goto err; 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 --- arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/iommu.c | 2 ++ arch/x86/kvm/x86.c | 18 ++++++++++++++++++ include/linux/kvm_host.h | 18 ++++++++++++++++++ virt/kvm/vfio.c | 5 +++++ 5 files changed, 45 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 2a7f5d782c33..49ec9038ec14 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -604,6 +604,8 @@ struct kvm_arch { bool iommu_noncoherent; #define __KVM_HAVE_ARCH_NONCOHERENT_DMA atomic_t noncoherent_dma_count; +#define __KVM_HAVE_ARCH_ASSIGNED_DEVICE + atomic_t assigned_device_count; struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c index 7dbced309ddb..5c520ebf6343 100644 --- a/arch/x86/kvm/iommu.c +++ b/arch/x86/kvm/iommu.c @@ -200,6 +200,7 @@ int kvm_assign_device(struct kvm *kvm, struct pci_dev *pdev) goto out_unmap; } + kvm_arch_start_assignment(kvm); pci_set_dev_assigned(pdev); dev_info(&pdev->dev, "kvm assign device\n"); @@ -224,6 +225,7 @@ int kvm_deassign_device(struct kvm *kvm, struct pci_dev *pdev) iommu_detach_device(domain, &pdev->dev); pci_clear_dev_assigned(pdev); + kvm_arch_end_assignment(kvm); dev_info(&pdev->dev, "kvm deassign device\n"); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6bd19c7abc65..0024968b342d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8213,6 +8213,24 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) kvm_x86_ops->interrupt_allowed(vcpu); } +void kvm_arch_start_assignment(struct kvm *kvm) +{ + atomic_inc(&kvm->arch.assigned_device_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_start_assignment); + +void kvm_arch_end_assignment(struct kvm *kvm) +{ + atomic_dec(&kvm->arch.assigned_device_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); + +bool kvm_arch_has_assigned_device(struct kvm *kvm) +{ + return atomic_read(&kvm->arch.assigned_device_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); + void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { atomic_inc(&kvm->arch.noncoherent_dma_count); 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) { diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c index 620e37f741b8..1dd087da6f31 100644 --- a/virt/kvm/vfio.c +++ b/virt/kvm/vfio.c @@ -155,6 +155,8 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg) list_add_tail(&kvg->node, &kv->group_list); kvg->vfio_group = vfio_group; + kvm_arch_start_assignment(dev->kvm); + mutex_unlock(&kv->lock); kvm_vfio_update_coherency(dev); @@ -190,6 +192,8 @@ static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg) break; } + kvm_arch_end_assignment(dev->kvm); + mutex_unlock(&kv->lock); kvm_vfio_group_put_external_user(vfio_group); @@ -239,6 +243,7 @@ static void kvm_vfio_destroy(struct kvm_device *dev) kvm_vfio_group_put_external_user(kvg->vfio_group); list_del(&kvg->node); kfree(kvg); + kvm_arch_end_assignment(dev->kvm); } kvm_vfio_update_coherency(dev); -- 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 --- drivers/net/can/dev.c | 7 ++----- drivers/net/can/slcan.c | 2 +- drivers/net/can/vcan.c | 3 --- include/linux/can/skb.h | 2 ++ net/can/af_can.c | 12 +++++++----- net/can/bcm.c | 2 ++ net/can/raw.c | 7 ++++--- 7 files changed, 18 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index e9b1810d319f..aede704605c6 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -440,9 +440,6 @@ unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx) struct can_frame *cf = (struct can_frame *)skb->data; u8 dlc = cf->can_dlc; - if (!(skb->tstamp.tv64)) - __net_timestamp(skb); - netif_rx(priv->echo_skb[idx]); priv->echo_skb[idx] = NULL; @@ -578,7 +575,6 @@ struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf) if (unlikely(!skb)) return NULL; - __net_timestamp(skb); skb->protocol = htons(ETH_P_CAN); skb->pkt_type = PACKET_BROADCAST; skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -589,6 +585,7 @@ struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf) can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; + can_skb_prv(skb)->skbcnt = 0; *cf = (struct can_frame *)skb_put(skb, sizeof(struct can_frame)); memset(*cf, 0, sizeof(struct can_frame)); @@ -607,7 +604,6 @@ struct sk_buff *alloc_canfd_skb(struct net_device *dev, if (unlikely(!skb)) return NULL; - __net_timestamp(skb); skb->protocol = htons(ETH_P_CANFD); skb->pkt_type = PACKET_BROADCAST; skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -618,6 +614,7 @@ struct sk_buff *alloc_canfd_skb(struct net_device *dev, can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; + can_skb_prv(skb)->skbcnt = 0; *cfd = (struct canfd_frame *)skb_put(skb, sizeof(struct canfd_frame)); memset(*cfd, 0, sizeof(struct canfd_frame)); diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index f64f5290d6f8..a23a7af8eb9a 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -207,7 +207,6 @@ static void slc_bump(struct slcan *sl) if (!skb) return; - __net_timestamp(skb); skb->dev = sl->dev; skb->protocol = htons(ETH_P_CAN); skb->pkt_type = PACKET_BROADCAST; @@ -215,6 +214,7 @@ static void slc_bump(struct slcan *sl) can_skb_reserve(skb); can_skb_prv(skb)->ifindex = sl->dev->ifindex; + can_skb_prv(skb)->skbcnt = 0; memcpy(skb_put(skb, sizeof(struct can_frame)), &cf, sizeof(struct can_frame)); diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c index 0ce868de855d..674f367087c5 100644 --- a/drivers/net/can/vcan.c +++ b/drivers/net/can/vcan.c @@ -78,9 +78,6 @@ static void vcan_rx(struct sk_buff *skb, struct net_device *dev) skb->dev = dev; skb->ip_summed = CHECKSUM_UNNECESSARY; - if (!(skb->tstamp.tv64)) - __net_timestamp(skb); - netif_rx_ni(skb); } 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]; }; diff --git a/net/can/af_can.c b/net/can/af_can.c index 7933e62a7318..166d436196c1 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -89,6 +89,8 @@ struct timer_list can_stattimer; /* timer for statistics update */ struct s_stats can_stats; /* packet statistics */ struct s_pstats can_pstats; /* receive list statistics */ +static atomic_t skbcounter = ATOMIC_INIT(0); + /* * af_can socket functions */ @@ -310,12 +312,8 @@ int can_send(struct sk_buff *skb, int loop) return err; } - if (newskb) { - if (!(newskb->tstamp.tv64)) - __net_timestamp(newskb); - + if (newskb) netif_rx_ni(newskb); - } /* update statistics */ can_stats.tx_frames++; @@ -683,6 +681,10 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev) can_stats.rx_frames++; can_stats.rx_frames_delta++; + /* create non-zero unique skb identifier together with *skb */ + while (!(can_skb_prv(skb)->skbcnt)) + can_skb_prv(skb)->skbcnt = atomic_inc_return(&skbcounter); + rcu_read_lock(); /* deliver the packet to sockets listening on all devices */ diff --git a/net/can/bcm.c b/net/can/bcm.c index b523453585be..a1ba6875c2a2 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -261,6 +261,7 @@ static void bcm_can_tx(struct bcm_op *op) can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; + can_skb_prv(skb)->skbcnt = 0; memcpy(skb_put(skb, CFSIZ), cf, CFSIZ); @@ -1217,6 +1218,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk) } can_skb_prv(skb)->ifindex = dev->ifindex; + can_skb_prv(skb)->skbcnt = 0; skb->dev = dev; can_skb_set_owner(skb, sk); err = can_send(skb, 1); /* send with loopback */ diff --git a/net/can/raw.c b/net/can/raw.c index 31b9748cbb4e..2e67b1423cd3 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -75,7 +75,7 @@ MODULE_ALIAS("can-proto-1"); */ struct uniqframe { - ktime_t tstamp; + int skbcnt; const struct sk_buff *skb; unsigned int join_rx_count; }; @@ -133,7 +133,7 @@ static void raw_rcv(struct sk_buff *oskb, void *data) /* eliminate multiple filter matches for the same skb */ if (this_cpu_ptr(ro->uniq)->skb == oskb && - ktime_equal(this_cpu_ptr(ro->uniq)->tstamp, oskb->tstamp)) { + this_cpu_ptr(ro->uniq)->skbcnt == can_skb_prv(oskb)->skbcnt) { if (ro->join_filters) { this_cpu_inc(ro->uniq->join_rx_count); /* drop frame until all enabled filters matched */ @@ -144,7 +144,7 @@ static void raw_rcv(struct sk_buff *oskb, void *data) } } else { this_cpu_ptr(ro->uniq)->skb = oskb; - this_cpu_ptr(ro->uniq)->tstamp = oskb->tstamp; + this_cpu_ptr(ro->uniq)->skbcnt = can_skb_prv(oskb)->skbcnt; this_cpu_ptr(ro->uniq)->join_rx_count = 1; /* drop first frame to check all enabled filters? */ if (ro->join_filters && ro->count > 1) @@ -749,6 +749,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; + can_skb_prv(skb)->skbcnt = 0; err = memcpy_from_msg(skb_put(skb, size), msg, size); if (err < 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" --- fs/locks.c | 50 ++++++++++++++++++++++++++++++++++++++------------ include/linux/fs.h | 14 ++++++++++++++ 2 files changed, 52 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/fs/locks.c b/fs/locks.c index 4366b7c54e6d..ba268a503c1b 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1163,20 +1163,19 @@ int posix_lock_file(struct file *filp, struct file_lock *fl, EXPORT_SYMBOL(posix_lock_file); /** - * posix_lock_file_wait - Apply a POSIX-style lock to a file - * @filp: The file to apply the lock to + * posix_lock_inode_wait - Apply a POSIX-style lock to a file + * @inode: inode of file to which lock request should be applied * @fl: The lock to be applied * - * Add a POSIX style lock to a file. - * We merge adjacent & overlapping locks whenever possible. - * POSIX locks are sorted by owner task, then by starting address + * Variant of posix_lock_file_wait that does not take a filp, and so can be + * used after the filp has already been torn down. */ -int posix_lock_file_wait(struct file *filp, struct file_lock *fl) +int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep (); for (;;) { - error = posix_lock_file(filp, fl, NULL); + error = __posix_lock_file(inode, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->fl_wait, !fl->fl_next); @@ -1188,6 +1187,21 @@ int posix_lock_file_wait(struct file *filp, struct file_lock *fl) } return error; } +EXPORT_SYMBOL(posix_lock_inode_wait); + +/** + * posix_lock_file_wait - Apply a POSIX-style lock to a file + * @filp: The file to apply the lock to + * @fl: The lock to be applied + * + * Add a POSIX style lock to a file. + * We merge adjacent & overlapping locks whenever possible. + * POSIX locks are sorted by owner task, then by starting address + */ +int posix_lock_file_wait(struct file *filp, struct file_lock *fl) +{ + return posix_lock_inode_wait(file_inode(filp), fl); +} EXPORT_SYMBOL(posix_lock_file_wait); /** @@ -1850,18 +1864,18 @@ int fcntl_setlease(unsigned int fd, struct file *filp, long arg) } /** - * flock_lock_file_wait - Apply a FLOCK-style lock to a file - * @filp: The file to apply the lock to + * flock_lock_inode_wait - Apply a FLOCK-style lock to a file + * @inode: inode of the file to apply to * @fl: The lock to be applied * - * Add a FLOCK style lock to a file. + * Apply a FLOCK style lock request to an inode. */ -int flock_lock_file_wait(struct file *filp, struct file_lock *fl) +int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep(); for (;;) { - error = flock_lock_inode(file_inode(filp), fl); + error = flock_lock_inode(inode, fl); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->fl_wait, !fl->fl_next); @@ -1873,7 +1887,19 @@ int flock_lock_file_wait(struct file *filp, struct file_lock *fl) } return error; } +EXPORT_SYMBOL(flock_lock_inode_wait); +/** + * flock_lock_file_wait - Apply a FLOCK-style lock to a file + * @filp: The file to apply the lock to + * @fl: The lock to be applied + * + * Add a FLOCK style lock to a file. + */ +int flock_lock_file_wait(struct file *filp, struct file_lock *fl) +{ + return flock_lock_inode_wait(file_inode(filp), fl); +} EXPORT_SYMBOL(flock_lock_file_wait); /** 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 --- fs/locks.c | 28 ---------------------------- include/linux/fs.h | 32 ++++++++++++++------------------ 2 files changed, 14 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/fs/locks.c b/fs/locks.c index ba268a503c1b..d3d558ba4da7 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1189,21 +1189,6 @@ int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) } EXPORT_SYMBOL(posix_lock_inode_wait); -/** - * posix_lock_file_wait - Apply a POSIX-style lock to a file - * @filp: The file to apply the lock to - * @fl: The lock to be applied - * - * Add a POSIX style lock to a file. - * We merge adjacent & overlapping locks whenever possible. - * POSIX locks are sorted by owner task, then by starting address - */ -int posix_lock_file_wait(struct file *filp, struct file_lock *fl) -{ - return posix_lock_inode_wait(file_inode(filp), fl); -} -EXPORT_SYMBOL(posix_lock_file_wait); - /** * locks_mandatory_locked - Check for an active lock * @file: the file to check @@ -1889,19 +1874,6 @@ int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) } EXPORT_SYMBOL(flock_lock_inode_wait); -/** - * flock_lock_file_wait - Apply a FLOCK-style lock to a file - * @filp: The file to apply the lock to - * @fl: The lock to be applied - * - * Add a FLOCK style lock to a file. - */ -int flock_lock_file_wait(struct file *filp, struct file_lock *fl) -{ - return flock_lock_inode_wait(file_inode(filp), fl); -} -EXPORT_SYMBOL(flock_lock_file_wait); - /** * sys_flock: - flock() system call. * @fd: the file descriptor to lock. 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 4c62360d7562a20c996836d163259c87d9378120 Mon Sep 17 00:00:00 2001 From: "Luck, Tony" Date: Tue, 30 Jun 2015 15:57:51 -0700 Subject: efi: Handle memory error structures produced based on old versions of standard The memory error record structure includes as its first field a bitmask of which subsequent fields are valid. The allows new fields to be added to the structure while keeping compatibility with older software that parses these records. This mechanism was used between versions 2.2 and 2.3 to add four new fields, growing the size of the structure from 73 bytes to 80. But Linux just added all the new fields so this test: if (gdata->error_data_length >= sizeof(*mem_err)) cper_print_mem(newpfx, mem_err); else goto err_section_too_small; now make Linux complain about old format records being too short. Add a definition for the old format of the structure and use that for the minimum size check. Pass the actual size to cper_print_mem() so it can sanity check the validation_bits field to ensure that if a BIOS using the old format sets bits as if it were new, we won't access fields beyond the end of the structure. Signed-off-by: Tony Luck Cc: Signed-off-by: Matt Fleming --- drivers/firmware/efi/cper.c | 15 ++++++++++++--- include/linux/cper.h | 22 +++++++++++++++++++++- 2 files changed, 33 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index 4fd9961d552e..d42537425438 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -305,10 +305,17 @@ const char *cper_mem_err_unpack(struct trace_seq *p, return ret; } -static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem) +static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem, + int len) { struct cper_mem_err_compact cmem; + /* Don't trust UEFI 2.1/2.2 structure with bad validation bits */ + if (len == sizeof(struct cper_sec_mem_err_old) && + (mem->validation_bits & ~(CPER_MEM_VALID_RANK_NUMBER - 1))) { + pr_err(FW_WARN "valid bits set for fields beyond structure\n"); + return; + } if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS) printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status); if (mem->validation_bits & CPER_MEM_VALID_PA) @@ -405,8 +412,10 @@ static void cper_estatus_print_section( } else if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) { struct cper_sec_mem_err *mem_err = (void *)(gdata + 1); printk("%s""section_type: memory error\n", newpfx); - if (gdata->error_data_length >= sizeof(*mem_err)) - cper_print_mem(newpfx, mem_err); + if (gdata->error_data_length >= + sizeof(struct cper_sec_mem_err_old)) + cper_print_mem(newpfx, mem_err, + gdata->error_data_length); else goto err_section_too_small; } else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) { diff --git a/include/linux/cper.h b/include/linux/cper.h index 76abba4b238e..dcacb1a72e26 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -340,7 +340,27 @@ struct cper_ia_proc_ctx { __u64 mm_reg_addr; }; -/* Memory Error Section */ +/* Old Memory Error Section UEFI 2.1, 2.2 */ +struct cper_sec_mem_err_old { + __u64 validation_bits; + __u64 error_status; + __u64 physical_addr; + __u64 physical_addr_mask; + __u16 node; + __u16 card; + __u16 module; + __u16 bank; + __u16 device; + __u16 row; + __u16 column; + __u16 bit_pos; + __u64 requestor_id; + __u64 responder_id; + __u64 target_id; + __u8 error_type; +}; + +/* Memory Error Section UEFI >= 2.3 */ struct cper_sec_mem_err { __u64 validation_bits; __u64 error_status; -- cgit v1.2.3 From 71d126fd28de2d4d9b7b2088dbccd7ca62fad6e0 Mon Sep 17 00:00:00 2001 From: Arne Fitzenreiter Date: Wed, 15 Jul 2015 13:54:36 +0200 Subject: libata: add ATA_HORKAGE_NOTRIM Some devices lose data on TRIM whether queued or not. This patch adds a horkage to disable TRIM. tj: Collapsed unnecessary if() nesting. Signed-off-by: Arne Fitzenreiter Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org --- drivers/ata/libata-scsi.c | 3 ++- drivers/ata/libata-transport.c | 2 ++ include/linux/libata.h | 2 ++ 3 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 3131adcc1f87..641a61a59e89 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2568,7 +2568,8 @@ static unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf) rbuf[14] = (lowest_aligned >> 8) & 0x3f; rbuf[15] = lowest_aligned; - if (ata_id_has_trim(args->id)) { + if (ata_id_has_trim(args->id) && + !(dev->horkage & ATA_HORKAGE_NOTRIM)) { rbuf[14] |= 0x80; /* LBPME */ if (ata_id_has_zero_after_trim(args->id) && diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c index d6c37bcd416d..e2d94972962d 100644 --- a/drivers/ata/libata-transport.c +++ b/drivers/ata/libata-transport.c @@ -569,6 +569,8 @@ show_ata_dev_trim(struct device *dev, if (!ata_id_has_trim(ata_dev->id)) mode = "unsupported"; + else if (ata_dev->horkage & ATA_HORKAGE_NOTRIM) + mode = "forced_unsupported"; else if (ata_dev->horkage & ATA_HORKAGE_NO_NCQ_TRIM) mode = "forced_unqueued"; else if (ata_fpdma_dsm_supported(ata_dev)) diff --git a/include/linux/libata.h b/include/linux/libata.h index 36ce37bcc963..5c8bac6225a6 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -431,6 +431,8 @@ enum { ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21), /* some WDs have broken LPM */ ATA_HORKAGE_ZERO_AFTER_TRIM = (1 << 22),/* guarantees zero after trim */ ATA_HORKAGE_NO_NCQ_LOG = (1 << 23), /* don't use NCQ for log read */ + ATA_HORKAGE_NOTRIM = (1 << 24), /* don't use TRIM */ + /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.2.3 From af34d637637eabaf49406eb35c948cd51ba262a6 Mon Sep 17 00:00:00 2001 From: David Milburn Date: Mon, 13 Jul 2015 11:48:23 -0500 Subject: libata: add ATA_HORKAGE_MAX_SEC_1024 to revert back to previous max_sectors limit Since no longer limiting max_sectors to BLK_DEF_MAX_SECTORS (commit 34b48db66e08), data corruption may occur on ST380013AS drive configured on 82801JI (ICH10 Family) SATA controller. This patch will allow the driver to limit max_sectors as before # cat /sys/block/sdb/queue/max_sectors_kb 512 I was able to double the max_sectors_kb value up to 16384 on linux-4.2.0-rc2 before seeing corruption, but seems safer to use previous limit. Without this patch max_sectors_kb will be 32767. tj: Minor comment update. Reported-by: Jeff Moyer Signed-off-by: David Milburn Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org # v3.19 and later Fixes: 34b48db66e08 ("block: remove artifical max_hw_sectors cap") --- drivers/ata/libata-core.c | 10 ++++++++++ include/linux/ata.h | 1 + include/linux/libata.h | 2 +- 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index ed2b218ea64d..68202a8a3a0b 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2478,6 +2478,10 @@ int ata_dev_configure(struct ata_device *dev) dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_128, dev->max_sectors); + if (dev->horkage & ATA_HORKAGE_MAX_SEC_1024) + dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_1024, + dev->max_sectors); + if (dev->horkage & ATA_HORKAGE_MAX_SEC_LBA48) dev->max_sectors = ATA_MAX_SECTORS_LBA48; @@ -4146,6 +4150,12 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "Slimtype DVD A DS8A8SH", NULL, ATA_HORKAGE_MAX_SEC_LBA48 }, { "Slimtype DVD A DS8A9SH", NULL, ATA_HORKAGE_MAX_SEC_LBA48 }, + /* + * Causes silent data corruption with higher max sects. + * http://lkml.kernel.org/g/x49wpy40ysk.fsf@segfault.boston.devel.redhat.com + */ + { "ST380013AS", "3.20", ATA_HORKAGE_MAX_SEC_1024 }, + /* Devices we expect to fail diagnostics */ /* Devices where NCQ should be avoided */ diff --git a/include/linux/ata.h b/include/linux/ata.h index fed36418dd1c..6c78956aa470 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -45,6 +45,7 @@ enum { ATA_SECT_SIZE = 512, ATA_MAX_SECTORS_128 = 128, ATA_MAX_SECTORS = 256, + ATA_MAX_SECTORS_1024 = 1024, ATA_MAX_SECTORS_LBA48 = 65535,/* TODO: 65536? */ ATA_MAX_SECTORS_TAPE = 65535, diff --git a/include/linux/libata.h b/include/linux/libata.h index 5c8bac6225a6..c9cfbcdb8d14 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -432,7 +432,7 @@ enum { ATA_HORKAGE_ZERO_AFTER_TRIM = (1 << 22),/* guarantees zero after trim */ ATA_HORKAGE_NO_NCQ_LOG = (1 << 23), /* don't use NCQ for log read */ ATA_HORKAGE_NOTRIM = (1 << 24), /* don't use TRIM */ - + ATA_HORKAGE_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- 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/linux') 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/linux') 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 +++--- lib/kobject.c | 5 +++-- 12 files changed, 36 insertions(+), 30 deletions(-) (limited to 'include/linux') 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, ...) { } diff --git a/lib/kobject.c b/lib/kobject.c index 2e3bd01964a9..3e3a5c3cb330 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -337,8 +337,9 @@ error: } EXPORT_SYMBOL(kobject_init); -static int kobject_add_varg(struct kobject *kobj, struct kobject *parent, - const char *fmt, va_list vargs) +static __printf(3, 0) int kobject_add_varg(struct kobject *kobj, + struct kobject *parent, + const char *fmt, va_list vargs) { int retval; -- 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 --- .mailmap | 4 +++- Documentation/arm/SPEAr/overview.txt | 2 +- MAINTAINERS | 12 ++++++------ arch/arm/boot/dts/spear1310-evb.dts | 2 +- arch/arm/boot/dts/spear1310.dtsi | 2 +- arch/arm/boot/dts/spear1340-evb.dts | 2 +- arch/arm/boot/dts/spear1340.dtsi | 2 +- arch/arm/boot/dts/spear13xx.dtsi | 2 +- arch/arm/boot/dts/spear300-evb.dts | 2 +- arch/arm/boot/dts/spear300.dtsi | 2 +- arch/arm/boot/dts/spear310-evb.dts | 2 +- arch/arm/boot/dts/spear310.dtsi | 2 +- arch/arm/boot/dts/spear320-evb.dts | 2 +- arch/arm/boot/dts/spear320.dtsi | 2 +- arch/arm/boot/dts/spear3xx.dtsi | 2 +- arch/arm/mach-spear/generic.h | 2 +- arch/arm/mach-spear/include/mach/irqs.h | 2 +- arch/arm/mach-spear/include/mach/misc_regs.h | 2 +- arch/arm/mach-spear/include/mach/spear.h | 2 +- arch/arm/mach-spear/include/mach/uncompress.h | 2 +- arch/arm/mach-spear/pl080.c | 2 +- arch/arm/mach-spear/pl080.h | 2 +- arch/arm/mach-spear/restart.c | 2 +- arch/arm/mach-spear/spear1310.c | 2 +- arch/arm/mach-spear/spear1340.c | 2 +- arch/arm/mach-spear/spear13xx.c | 2 +- arch/arm/mach-spear/spear300.c | 2 +- arch/arm/mach-spear/spear310.c | 2 +- arch/arm/mach-spear/spear320.c | 2 +- arch/arm/mach-spear/spear3xx.c | 2 +- drivers/ata/pata_arasan_cf.c | 4 ++-- drivers/clk/spear/clk-aux-synth.c | 2 +- drivers/clk/spear/clk-frac-synth.c | 2 +- drivers/clk/spear/clk-gpt-synth.c | 2 +- drivers/clk/spear/clk-vco-pll.c | 2 +- drivers/clk/spear/clk.c | 2 +- drivers/clk/spear/clk.h | 2 +- drivers/clk/spear/spear1310_clock.c | 2 +- drivers/clk/spear/spear1340_clock.c | 2 +- drivers/clk/spear/spear3xx_clock.c | 2 +- drivers/clk/spear/spear6xx_clock.c | 2 +- drivers/dma/dw/core.c | 2 +- drivers/irqchip/spear-shirq.c | 2 +- drivers/mfd/stmpe-i2c.c | 2 +- drivers/mfd/stmpe-spi.c | 4 ++-- drivers/mmc/host/sdhci-spear.c | 4 ++-- drivers/pinctrl/spear/pinctrl-spear.c | 2 +- drivers/pinctrl/spear/pinctrl-spear.h | 2 +- drivers/pinctrl/spear/pinctrl-spear1310.c | 4 ++-- drivers/pinctrl/spear/pinctrl-spear1340.c | 4 ++-- drivers/pinctrl/spear/pinctrl-spear300.c | 4 ++-- drivers/pinctrl/spear/pinctrl-spear310.c | 4 ++-- drivers/pinctrl/spear/pinctrl-spear320.c | 4 ++-- drivers/pinctrl/spear/pinctrl-spear3xx.c | 2 +- drivers/pinctrl/spear/pinctrl-spear3xx.h | 2 +- drivers/watchdog/sp805_wdt.c | 4 ++-- include/linux/amba/sp810.h | 2 +- include/linux/pata_arasan_cf_data.h | 2 +- 58 files changed, 74 insertions(+), 72 deletions(-) (limited to 'include/linux') diff --git a/.mailmap b/.mailmap index 977f958eedbe..8d8ad17dcf9c 100644 --- a/.mailmap +++ b/.mailmap @@ -125,7 +125,9 @@ Uwe Kleine-König Uwe Kleine-König Uwe Kleine-König Valdis Kletnieks -Viresh Kumar +Viresh Kumar +Viresh Kumar +Viresh Kumar Takashi YOSHII Yusuke Goda Gustavo Padovan diff --git a/Documentation/arm/SPEAr/overview.txt b/Documentation/arm/SPEAr/overview.txt index 65610bf52ebf..1b049be6c84f 100644 --- a/Documentation/arm/SPEAr/overview.txt +++ b/Documentation/arm/SPEAr/overview.txt @@ -60,4 +60,4 @@ Introduction Document Author --------------- - Viresh Kumar , (c) 2010-2012 ST Microelectronics + Viresh Kumar , (c) 2010-2012 ST Microelectronics diff --git a/MAINTAINERS b/MAINTAINERS index 2de150384670..093da8a3f8b2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6090,7 +6090,7 @@ F: include/linux/ata.h F: include/linux/libata.h LIBATA PATA ARASAN COMPACT FLASH CONTROLLER -M: Viresh Kumar +M: Viresh Kumar L: linux-ide@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git S: Maintained @@ -7996,7 +7996,7 @@ S: Maintained F: drivers/pinctrl/samsung/ PIN CONTROLLER - ST SPEAR -M: Viresh Kumar +M: Viresh Kumar L: spear-devel@list.st.com L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) W: http://www.st.com/spear @@ -8895,7 +8895,7 @@ S: Maintained F: drivers/tty/serial/ SYNOPSYS DESIGNWARE DMAC DRIVER -M: Viresh Kumar +M: Viresh Kumar M: Andy Shevchenko S: Maintained F: include/linux/dma/dw.h @@ -9062,7 +9062,7 @@ S: Maintained F: drivers/mmc/host/sdhci-s3c* SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) ST SPEAR DRIVER -M: Viresh Kumar +M: Viresh Kumar L: spear-devel@list.st.com L: linux-mmc@vger.kernel.org S: Maintained @@ -9600,7 +9600,7 @@ S: Maintained F: include/linux/compiler.h SPEAR PLATFORM SUPPORT -M: Viresh Kumar +M: Viresh Kumar M: Shiraz Hashim L: spear-devel@list.st.com L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -9609,7 +9609,7 @@ S: Maintained F: arch/arm/mach-spear/ SPEAR CLOCK FRAMEWORK SUPPORT -M: Viresh Kumar +M: Viresh Kumar L: spear-devel@list.st.com L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) W: http://www.st.com/spear diff --git a/arch/arm/boot/dts/spear1310-evb.dts b/arch/arm/boot/dts/spear1310-evb.dts index d42c84b1df8d..e48857249ce7 100644 --- a/arch/arm/boot/dts/spear1310-evb.dts +++ b/arch/arm/boot/dts/spear1310-evb.dts @@ -1,7 +1,7 @@ /* * DTS file for SPEAr1310 Evaluation Baord * - * Copyright 2012 Viresh Kumar + * Copyright 2012 Viresh Kumar * * The code contained herein is licensed under the GNU General Public * License. You may obtain a copy of the GNU General Public License diff --git a/arch/arm/boot/dts/spear1310.dtsi b/arch/arm/boot/dts/spear1310.dtsi index 9d342920695a..54bc6d3cf290 100644 --- a/arch/arm/boot/dts/spear1310.dtsi +++ b/arch/arm/boot/dts/spear1310.dtsi @@ -1,7 +1,7 @@ /* * DTS file for all SPEAr1310 SoCs * - * Copyright 2012 Viresh Kumar + * Copyright 2012 Viresh Kumar * * The code contained herein is licensed under the GNU General Public * License. You may obtain a copy of the GNU General Public License diff --git a/arch/arm/boot/dts/spear1340-evb.dts b/arch/arm/boot/dts/spear1340-evb.dts index b23e05ed1d60..c611f5606dfe 100644 --- a/arch/arm/boot/dts/spear1340-evb.dts +++ b/arch/arm/boot/dts/spear1340-evb.dts @@ -1,7 +1,7 @@ /* * DTS file for SPEAr1340 Evaluation Baord * - * Copyright 2012 Viresh Kumar + * Copyright 2012 Viresh Kumar * * The code contained herein is licensed under the GNU General Public * License. You may obtain a copy of the GNU General Public License diff --git a/arch/arm/boot/dts/spear1340.dtsi b/arch/arm/boot/dts/spear1340.dtsi index 13e1aa33daa2..df2232d767ed 100644 --- a/arch/arm/boot/dts/spear1340.dtsi +++ b/arch/arm/boot/dts/spear1340.dtsi @@ -1,7 +1,7 @@ /* * DTS file for all SPEAr1340 SoCs * - * Copyright 2012 Viresh Kumar + * Copyright 2012 Viresh Kumar * * The code contained herein is licensed under the GNU General Public * License. You may obtain a copy of the GNU General Public License diff --git a/arch/arm/boot/dts/spear13xx.dtsi b/arch/arm/boot/dts/spear13xx.dtsi index 40accc87e3a2..14594ce8c18a 100644 --- a/arch/arm/boot/dts/spear13xx.dtsi +++ b/arch/arm/boot/dts/spear13xx.dtsi @@ -1,7 +1,7 @@ /* * DTS file for all SPEAr13xx SoCs * - * Copyright 2012 Viresh Kumar + * Copyright 2012 Viresh Kumar * * The code contained herein is licensed under the GNU General Public * License. You may obtain a copy of the GNU General Public License diff --git a/arch/arm/boot/dts/spear300-evb.dts b/arch/arm/boot/dts/spear300-evb.dts index 5de1431653e4..e859e8288bcd 100644 --- a/arch/arm/boot/dts/spear300-evb.dts +++ b/arch/arm/boot/dts/spear300-evb.dts @@ -1,7 +1,7 @@ /* * DTS file for SPEAr300 Evaluation Baord * - * Copyright 2012 Viresh Kumar + * Copyright 2012 Viresh Kumar * * The code contained herein is licensed under the GNU General Public * License. You may obtain a copy of the GNU General Public License diff --git a/arch/arm/boot/dts/spear300.dtsi b/arch/arm/boot/dts/spear300.dtsi index f79b3dfaabe6..f4e92e599729 100644 --- a/arch/arm/boot/dts/spear300.dtsi +++ b/arch/arm/boot/dts/spear300.dtsi @@ -1,7 +1,7 @@ /* * DTS file for SPEAr300 SoC * - * Copyright 2012 Viresh Kumar + * Copyright 2012 Viresh Kumar * * The code contained herein is licensed under the GNU General Public * License. You may obtain a copy of the GNU General Public License diff --git a/arch/arm/boot/dts/spear310-evb.dts b/arch/arm/boot/dts/spear310-evb.dts index b09632963d15..070f2c1b7851 100644 --- a/arch/arm/boot/dts/spear310-evb.dts +++ b/arch/arm/boot/dts/spear310-evb.dts @@ -1,7 +1,7 @@ /* * DTS file for SPEAr310 Evaluation Baord * - * Copyright 2012 Viresh Kumar + * Copyright 2012 Viresh Kumar * * The code contained herein is licensed under the GNU General Public * License. You may obtain a copy of the GNU General Public License diff --git a/arch/arm/boot/dts/spear310.dtsi b/arch/arm/boot/dts/spear310.dtsi index 95372080eea6..da210b454753 100644 --- a/arch/arm/boot/dts/spear310.dtsi +++ b/arch/arm/boot/dts/spear310.dtsi @@ -1,7 +1,7 @@ /* * DTS file for SPEAr310 SoC * - * Copyright 2012 Viresh Kumar + * Copyright 2012 Viresh Kumar * * The code contained herein is licensed under the GNU General Public * License. You may obtain a copy of the GNU General Public License diff --git a/arch/arm/boot/dts/spear320-evb.dts b/arch/arm/boot/dts/spear320-evb.dts index fdedbb514102..1b1034477923 100644 --- a/arch/arm/boot/dts/spear320-evb.dts +++ b/arch/arm/boot/dts/spear320-evb.dts @@ -1,7 +1,7 @@ /* * DTS file for SPEAr320 Evaluation Baord * - * Copyright 2012 Viresh Kumar + * Copyright 2012 Viresh Kumar * * The code contained herein is licensed under the GNU General Public * License. You may obtain a copy of the GNU General Public License diff --git a/arch/arm/boot/dts/spear320.dtsi b/arch/arm/boot/dts/spear320.dtsi index ffea342aeec9..22be6e5edaac 100644 --- a/arch/arm/boot/dts/spear320.dtsi +++ b/arch/arm/boot/dts/spear320.dtsi @@ -1,7 +1,7 @@ /* * DTS file for SPEAr320 SoC * - * Copyright 2012 Viresh Kumar + * Copyright 2012 Viresh Kumar * * The code contained herein is licensed under the GNU General Public * License. You may obtain a copy of the GNU General Public License diff --git a/arch/arm/boot/dts/spear3xx.dtsi b/arch/arm/boot/dts/spear3xx.dtsi index f0e3fcf8e323..118135d75899 100644 --- a/arch/arm/boot/dts/spear3xx.dtsi +++ b/arch/arm/boot/dts/spear3xx.dtsi @@ -1,7 +1,7 @@ /* * DTS file for all SPEAr3xx SoCs * - * Copyright 2012 Viresh Kumar + * Copyright 2012 Viresh Kumar * * The code contained herein is licensed under the GNU General Public * License. You may obtain a copy of the GNU General Public License diff --git a/arch/arm/mach-spear/generic.h b/arch/arm/mach-spear/generic.h index a99d90a4d09c..06640914d9a0 100644 --- a/arch/arm/mach-spear/generic.h +++ b/arch/arm/mach-spear/generic.h @@ -3,7 +3,7 @@ * * Copyright (C) 2009-2012 ST Microelectronics * Rajeev Kumar - * 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/arch/arm/mach-spear/include/mach/irqs.h b/arch/arm/mach-spear/include/mach/irqs.h index 92da0a8c6bce..7058720c5278 100644 --- a/arch/arm/mach-spear/include/mach/irqs.h +++ b/arch/arm/mach-spear/include/mach/irqs.h @@ -3,7 +3,7 @@ * * Copyright (C) 2009-2012 ST Microelectronics * Rajeev Kumar - * 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/arch/arm/mach-spear/include/mach/misc_regs.h b/arch/arm/mach-spear/include/mach/misc_regs.h index 935639ce59ba..cfaf7c665b58 100644 --- a/arch/arm/mach-spear/include/mach/misc_regs.h +++ b/arch/arm/mach-spear/include/mach/misc_regs.h @@ -4,7 +4,7 @@ * Miscellaneous registers definitions for SPEAr3xx machine family * * 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/arch/arm/mach-spear/include/mach/spear.h b/arch/arm/mach-spear/include/mach/spear.h index f2d6a0176575..5ed841ccf8a3 100644 --- a/arch/arm/mach-spear/include/mach/spear.h +++ b/arch/arm/mach-spear/include/mach/spear.h @@ -3,7 +3,7 @@ * * Copyright (C) 2009,2012 ST Microelectronics * Rajeev Kumar - * 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/arch/arm/mach-spear/include/mach/uncompress.h b/arch/arm/mach-spear/include/mach/uncompress.h index 51b2dc93e4da..8439b9c12edb 100644 --- a/arch/arm/mach-spear/include/mach/uncompress.h +++ b/arch/arm/mach-spear/include/mach/uncompress.h @@ -4,7 +4,7 @@ * Serial port stubs for kernel decompress status messages * * 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/arch/arm/mach-spear/pl080.c b/arch/arm/mach-spear/pl080.c index cfa1199d0f4a..b4529f3e0ee9 100644 --- a/arch/arm/mach-spear/pl080.c +++ b/arch/arm/mach-spear/pl080.c @@ -4,7 +4,7 @@ * DMAC pl080 definitions for SPEAr platform * * Copyright (C) 2012 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/arch/arm/mach-spear/pl080.h b/arch/arm/mach-spear/pl080.h index eb6590ded40d..608dec6725ae 100644 --- a/arch/arm/mach-spear/pl080.h +++ b/arch/arm/mach-spear/pl080.h @@ -4,7 +4,7 @@ * DMAC pl080 definitions for SPEAr platform * * Copyright (C) 2012 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/arch/arm/mach-spear/restart.c b/arch/arm/mach-spear/restart.c index ce5e098c4888..b4342155a783 100644 --- a/arch/arm/mach-spear/restart.c +++ b/arch/arm/mach-spear/restart.c @@ -4,7 +4,7 @@ * SPEAr platform specific restart functions * * 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/arch/arm/mach-spear/spear1310.c b/arch/arm/mach-spear/spear1310.c index d9ce4d8000f0..cd5d375d91f0 100644 --- a/arch/arm/mach-spear/spear1310.c +++ b/arch/arm/mach-spear/spear1310.c @@ -4,7 +4,7 @@ * SPEAr1310 machine source file * * Copyright (C) 2012 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/arch/arm/mach-spear/spear1340.c b/arch/arm/mach-spear/spear1340.c index 3f3c0f124bd3..94594d5a446c 100644 --- a/arch/arm/mach-spear/spear1340.c +++ b/arch/arm/mach-spear/spear1340.c @@ -4,7 +4,7 @@ * SPEAr1340 machine source file * * Copyright (C) 2012 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/arch/arm/mach-spear/spear13xx.c b/arch/arm/mach-spear/spear13xx.c index 2e463a93468d..b7afce6795f4 100644 --- a/arch/arm/mach-spear/spear13xx.c +++ b/arch/arm/mach-spear/spear13xx.c @@ -4,7 +4,7 @@ * SPEAr13XX machines common source file * * Copyright (C) 2012 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/arch/arm/mach-spear/spear300.c b/arch/arm/mach-spear/spear300.c index b52e48f342f4..5b32edda2276 100644 --- a/arch/arm/mach-spear/spear300.c +++ b/arch/arm/mach-spear/spear300.c @@ -4,7 +4,7 @@ * SPEAr300 machine source file * * Copyright (C) 2009-2012 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/arch/arm/mach-spear/spear310.c b/arch/arm/mach-spear/spear310.c index ed2029db391f..86a44ac7ff67 100644 --- a/arch/arm/mach-spear/spear310.c +++ b/arch/arm/mach-spear/spear310.c @@ -4,7 +4,7 @@ * SPEAr310 machine source file * * Copyright (C) 2009-2012 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/arch/arm/mach-spear/spear320.c b/arch/arm/mach-spear/spear320.c index bf634b32a930..d45d751926c5 100644 --- a/arch/arm/mach-spear/spear320.c +++ b/arch/arm/mach-spear/spear320.c @@ -4,7 +4,7 @@ * SPEAr320 machine source file * * Copyright (C) 2009-2012 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/arch/arm/mach-spear/spear3xx.c b/arch/arm/mach-spear/spear3xx.c index bf3b1fd8cb23..23394ac76cf2 100644 --- a/arch/arm/mach-spear/spear3xx.c +++ b/arch/arm/mach-spear/spear3xx.c @@ -4,7 +4,7 @@ * SPEAr3XX machines common source file * * Copyright (C) 2009-2012 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/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c index a9b0c820f2eb..5d9ee99c2148 100644 --- a/drivers/ata/pata_arasan_cf.c +++ b/drivers/ata/pata_arasan_cf.c @@ -4,7 +4,7 @@ * Arasan Compact Flash host controller source 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 @@ -968,7 +968,7 @@ static struct platform_driver arasan_cf_driver = { module_platform_driver(arasan_cf_driver); -MODULE_AUTHOR("Viresh Kumar "); +MODULE_AUTHOR("Viresh Kumar "); MODULE_DESCRIPTION("Arasan ATA Compact Flash driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:" DRIVER_NAME); diff --git a/drivers/clk/spear/clk-aux-synth.c b/drivers/clk/spear/clk-aux-synth.c index bdfb4421c643..f271c350ef94 100644 --- a/drivers/clk/spear/clk-aux-synth.c +++ b/drivers/clk/spear/clk-aux-synth.c @@ -1,6 +1,6 @@ /* * Copyright (C) 2012 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/drivers/clk/spear/clk-frac-synth.c b/drivers/clk/spear/clk-frac-synth.c index dffd4ce6c8b5..58d678b5b40a 100644 --- a/drivers/clk/spear/clk-frac-synth.c +++ b/drivers/clk/spear/clk-frac-synth.c @@ -1,6 +1,6 @@ /* * Copyright (C) 2012 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/drivers/clk/spear/clk-gpt-synth.c b/drivers/clk/spear/clk-gpt-synth.c index 1afc18c4effc..1a722e99e76e 100644 --- a/drivers/clk/spear/clk-gpt-synth.c +++ b/drivers/clk/spear/clk-gpt-synth.c @@ -1,6 +1,6 @@ /* * Copyright (C) 2012 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/drivers/clk/spear/clk-vco-pll.c b/drivers/clk/spear/clk-vco-pll.c index 1b9b65bca51e..5ebddc528145 100644 --- a/drivers/clk/spear/clk-vco-pll.c +++ b/drivers/clk/spear/clk-vco-pll.c @@ -1,6 +1,6 @@ /* * Copyright (C) 2012 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/drivers/clk/spear/clk.c b/drivers/clk/spear/clk.c index 628b6d5ed3d9..157fe099ea6a 100644 --- a/drivers/clk/spear/clk.c +++ b/drivers/clk/spear/clk.c @@ -1,6 +1,6 @@ /* * Copyright (C) 2012 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/drivers/clk/spear/clk.h b/drivers/clk/spear/clk.h index 931737677dfa..9834944f08b1 100644 --- a/drivers/clk/spear/clk.h +++ b/drivers/clk/spear/clk.h @@ -2,7 +2,7 @@ * Clock framework definitions for SPEAr platform * * Copyright (C) 2012 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/drivers/clk/spear/spear1310_clock.c b/drivers/clk/spear/spear1310_clock.c index 4daa5977793a..222ce108b41a 100644 --- a/drivers/clk/spear/spear1310_clock.c +++ b/drivers/clk/spear/spear1310_clock.c @@ -4,7 +4,7 @@ * SPEAr1310 machine clock framework source file * * Copyright (C) 2012 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/drivers/clk/spear/spear1340_clock.c b/drivers/clk/spear/spear1340_clock.c index 5a5c6648308d..973c9d3fbcf8 100644 --- a/drivers/clk/spear/spear1340_clock.c +++ b/drivers/clk/spear/spear1340_clock.c @@ -4,7 +4,7 @@ * SPEAr1340 machine clock framework source file * * Copyright (C) 2012 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/drivers/clk/spear/spear3xx_clock.c b/drivers/clk/spear/spear3xx_clock.c index bb5f387774e2..404a55edd613 100644 --- a/drivers/clk/spear/spear3xx_clock.c +++ b/drivers/clk/spear/spear3xx_clock.c @@ -2,7 +2,7 @@ * SPEAr3xx machines clock framework source file * * Copyright (C) 2012 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/drivers/clk/spear/spear6xx_clock.c b/drivers/clk/spear/spear6xx_clock.c index 4f649c9cb094..231061fa73a4 100644 --- a/drivers/clk/spear/spear6xx_clock.c +++ b/drivers/clk/spear/spear6xx_clock.c @@ -2,7 +2,7 @@ * SPEAr6xx machines clock framework source file * * Copyright (C) 2012 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/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index 1022c2e1a2b0..cf1c87fa1edd 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -1746,4 +1746,4 @@ EXPORT_SYMBOL_GPL(dw_dma_enable); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller core driver"); MODULE_AUTHOR("Haavard Skinnemoen (Atmel)"); -MODULE_AUTHOR("Viresh Kumar "); +MODULE_AUTHOR("Viresh Kumar "); diff --git a/drivers/irqchip/spear-shirq.c b/drivers/irqchip/spear-shirq.c index a45121546caf..acb721b31bcf 100644 --- a/drivers/irqchip/spear-shirq.c +++ b/drivers/irqchip/spear-shirq.c @@ -2,7 +2,7 @@ * SPEAr platform shared irq layer source file * * Copyright (C) 2009-2012 ST Microelectronics - * Viresh Kumar + * Viresh Kumar * * Copyright (C) 2012 ST Microelectronics * Shiraz Hashim diff --git a/drivers/mfd/stmpe-i2c.c b/drivers/mfd/stmpe-i2c.c index 5c054031c3f8..e14c8c9d189b 100644 --- a/drivers/mfd/stmpe-i2c.c +++ b/drivers/mfd/stmpe-i2c.c @@ -6,7 +6,7 @@ * * License Terms: GNU General Public License, version 2 * Author: Rabin Vincent for ST-Ericsson - * Author: Viresh Kumar for ST Microelectronics + * Author: Viresh Kumar for ST Microelectronics */ #include diff --git a/drivers/mfd/stmpe-spi.c b/drivers/mfd/stmpe-spi.c index a81badbaa917..6fdb30e84a2b 100644 --- a/drivers/mfd/stmpe-spi.c +++ b/drivers/mfd/stmpe-spi.c @@ -4,7 +4,7 @@ * Copyright (C) ST Microelectronics SA 2011 * * License Terms: GNU General Public License, version 2 - * Author: Viresh Kumar for ST Microelectronics + * Author: Viresh Kumar for ST Microelectronics */ #include @@ -146,4 +146,4 @@ module_exit(stmpe_exit); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("STMPE MFD SPI Interface Driver"); -MODULE_AUTHOR("Viresh Kumar "); +MODULE_AUTHOR("Viresh Kumar "); diff --git a/drivers/mmc/host/sdhci-spear.c b/drivers/mmc/host/sdhci-spear.c index df088343d60f..255a896769b8 100644 --- a/drivers/mmc/host/sdhci-spear.c +++ b/drivers/mmc/host/sdhci-spear.c @@ -4,7 +4,7 @@ * Support of SDHCI platform devices for spear soc family * * Copyright (C) 2010 ST Microelectronics - * Viresh Kumar + * Viresh Kumar * * Inspired by sdhci-pltfm.c * @@ -211,5 +211,5 @@ static struct platform_driver sdhci_driver = { module_platform_driver(sdhci_driver); MODULE_DESCRIPTION("SPEAr Secure Digital Host Controller Interface driver"); -MODULE_AUTHOR("Viresh Kumar "); +MODULE_AUTHOR("Viresh Kumar "); MODULE_LICENSE("GPL v2"); diff --git a/drivers/pinctrl/spear/pinctrl-spear.c b/drivers/pinctrl/spear/pinctrl-spear.c index f87a5eaf75da..0afaf79a4e51 100644 --- a/drivers/pinctrl/spear/pinctrl-spear.c +++ b/drivers/pinctrl/spear/pinctrl-spear.c @@ -2,7 +2,7 @@ * Driver for the ST Microelectronics SPEAr pinmux * * Copyright (C) 2012 ST Microelectronics - * Viresh Kumar + * Viresh Kumar * * Inspired from: * - U300 Pinctl drivers diff --git a/drivers/pinctrl/spear/pinctrl-spear.h b/drivers/pinctrl/spear/pinctrl-spear.h index dc8bf85ecb2a..27c2cc8d83ad 100644 --- a/drivers/pinctrl/spear/pinctrl-spear.h +++ b/drivers/pinctrl/spear/pinctrl-spear.h @@ -2,7 +2,7 @@ * Driver header file for the ST Microelectronics SPEAr pinmux * * Copyright (C) 2012 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/drivers/pinctrl/spear/pinctrl-spear1310.c b/drivers/pinctrl/spear/pinctrl-spear1310.c index a7bdc537efa7..92611bb757ac 100644 --- a/drivers/pinctrl/spear/pinctrl-spear1310.c +++ b/drivers/pinctrl/spear/pinctrl-spear1310.c @@ -2,7 +2,7 @@ * Driver for the ST Microelectronics SPEAr1310 pinmux * * Copyright (C) 2012 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 @@ -2730,7 +2730,7 @@ static void __exit spear1310_pinctrl_exit(void) } module_exit(spear1310_pinctrl_exit); -MODULE_AUTHOR("Viresh Kumar "); +MODULE_AUTHOR("Viresh Kumar "); MODULE_DESCRIPTION("ST Microelectronics SPEAr1310 pinctrl driver"); MODULE_LICENSE("GPL v2"); MODULE_DEVICE_TABLE(of, spear1310_pinctrl_of_match); diff --git a/drivers/pinctrl/spear/pinctrl-spear1340.c b/drivers/pinctrl/spear/pinctrl-spear1340.c index f43ec85a0328..f842e9dc40d0 100644 --- a/drivers/pinctrl/spear/pinctrl-spear1340.c +++ b/drivers/pinctrl/spear/pinctrl-spear1340.c @@ -2,7 +2,7 @@ * Driver for the ST Microelectronics SPEAr1340 pinmux * * Copyright (C) 2012 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 @@ -2046,7 +2046,7 @@ static void __exit spear1340_pinctrl_exit(void) } module_exit(spear1340_pinctrl_exit); -MODULE_AUTHOR("Viresh Kumar "); +MODULE_AUTHOR("Viresh Kumar "); MODULE_DESCRIPTION("ST Microelectronics SPEAr1340 pinctrl driver"); MODULE_LICENSE("GPL v2"); MODULE_DEVICE_TABLE(of, spear1340_pinctrl_of_match); diff --git a/drivers/pinctrl/spear/pinctrl-spear300.c b/drivers/pinctrl/spear/pinctrl-spear300.c index da8990a8eeef..d998a2ccff48 100644 --- a/drivers/pinctrl/spear/pinctrl-spear300.c +++ b/drivers/pinctrl/spear/pinctrl-spear300.c @@ -2,7 +2,7 @@ * Driver for the ST Microelectronics SPEAr300 pinmux * * Copyright (C) 2012 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 @@ -703,7 +703,7 @@ static void __exit spear300_pinctrl_exit(void) } module_exit(spear300_pinctrl_exit); -MODULE_AUTHOR("Viresh Kumar "); +MODULE_AUTHOR("Viresh Kumar "); MODULE_DESCRIPTION("ST Microelectronics SPEAr300 pinctrl driver"); MODULE_LICENSE("GPL v2"); MODULE_DEVICE_TABLE(of, spear300_pinctrl_of_match); diff --git a/drivers/pinctrl/spear/pinctrl-spear310.c b/drivers/pinctrl/spear/pinctrl-spear310.c index 31ede51e819b..609b18aceb16 100644 --- a/drivers/pinctrl/spear/pinctrl-spear310.c +++ b/drivers/pinctrl/spear/pinctrl-spear310.c @@ -2,7 +2,7 @@ * Driver for the ST Microelectronics SPEAr310 pinmux * * Copyright (C) 2012 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 @@ -426,7 +426,7 @@ static void __exit spear310_pinctrl_exit(void) } module_exit(spear310_pinctrl_exit); -MODULE_AUTHOR("Viresh Kumar "); +MODULE_AUTHOR("Viresh Kumar "); MODULE_DESCRIPTION("ST Microelectronics SPEAr310 pinctrl driver"); MODULE_LICENSE("GPL v2"); MODULE_DEVICE_TABLE(of, spear310_pinctrl_of_match); diff --git a/drivers/pinctrl/spear/pinctrl-spear320.c b/drivers/pinctrl/spear/pinctrl-spear320.c index 506e40b641e0..c07114431bd4 100644 --- a/drivers/pinctrl/spear/pinctrl-spear320.c +++ b/drivers/pinctrl/spear/pinctrl-spear320.c @@ -2,7 +2,7 @@ * Driver for the ST Microelectronics SPEAr320 pinmux * * Copyright (C) 2012 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 @@ -3467,7 +3467,7 @@ static void __exit spear320_pinctrl_exit(void) } module_exit(spear320_pinctrl_exit); -MODULE_AUTHOR("Viresh Kumar "); +MODULE_AUTHOR("Viresh Kumar "); MODULE_DESCRIPTION("ST Microelectronics SPEAr320 pinctrl driver"); MODULE_LICENSE("GPL v2"); MODULE_DEVICE_TABLE(of, spear320_pinctrl_of_match); diff --git a/drivers/pinctrl/spear/pinctrl-spear3xx.c b/drivers/pinctrl/spear/pinctrl-spear3xx.c index 12ee21af766b..d3119aafe709 100644 --- a/drivers/pinctrl/spear/pinctrl-spear3xx.c +++ b/drivers/pinctrl/spear/pinctrl-spear3xx.c @@ -2,7 +2,7 @@ * Driver for the ST Microelectronics SPEAr3xx pinmux * * Copyright (C) 2012 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/drivers/pinctrl/spear/pinctrl-spear3xx.h b/drivers/pinctrl/spear/pinctrl-spear3xx.h index 7860b36053c4..ce19dcf8f08b 100644 --- a/drivers/pinctrl/spear/pinctrl-spear3xx.h +++ b/drivers/pinctrl/spear/pinctrl-spear3xx.h @@ -2,7 +2,7 @@ * Header file for the ST Microelectronics SPEAr3xx pinmux * * Copyright (C) 2012 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/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c index c1b03f4235b9..4e7fec36f5c3 100644 --- a/drivers/watchdog/sp805_wdt.c +++ b/drivers/watchdog/sp805_wdt.c @@ -4,7 +4,7 @@ * Watchdog driver for ARM SP805 watchdog module * * Copyright (C) 2010 ST Microelectronics - * Viresh Kumar + * Viresh Kumar * * This file is licensed under the terms of the GNU General Public * License version 2 or later. This program is licensed "as is" without any @@ -303,6 +303,6 @@ static struct amba_driver sp805_wdt_driver = { module_amba_driver(sp805_wdt_driver); -MODULE_AUTHOR("Viresh Kumar "); +MODULE_AUTHOR("Viresh Kumar "); MODULE_DESCRIPTION("ARM SP805 Watchdog Driver"); MODULE_LICENSE("GPL"); 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 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 +++++++++++++ mm/page_alloc.c | 8 +++++--- mm/page_owner.c | 7 +++++++ 3 files changed, 25 insertions(+), 3 deletions(-) (limited to 'include/linux') 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 */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fbba675a0bd9..ef19f22b2b7d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1948,6 +1948,7 @@ void free_hot_cold_page_list(struct list_head *list, bool cold) void split_page(struct page *page, unsigned int order) { int i; + gfp_t gfp_mask; VM_BUG_ON_PAGE(PageCompound(page), page); VM_BUG_ON_PAGE(!page_count(page), page); @@ -1961,10 +1962,11 @@ void split_page(struct page *page, unsigned int order) split_page(virt_to_page(page[0].shadow), order); #endif - set_page_owner(page, 0, 0); + gfp_mask = get_page_owner_gfp(page); + set_page_owner(page, 0, gfp_mask); for (i = 1; i < (1 << order); i++) { set_page_refcounted(page + i); - set_page_owner(page + i, 0, 0); + set_page_owner(page + i, 0, gfp_mask); } } EXPORT_SYMBOL_GPL(split_page); @@ -1994,7 +1996,7 @@ int __isolate_free_page(struct page *page, unsigned int order) zone->free_area[order].nr_free--; rmv_page_order(page); - set_page_owner(page, order, 0); + set_page_owner(page, order, __GFP_MOVABLE); /* Set the pageblock if the isolated page is at least a pageblock */ if (order >= pageblock_order - 1) { diff --git a/mm/page_owner.c b/mm/page_owner.c index bd5f842b56d2..983c3a10fa07 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -76,6 +76,13 @@ void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) __set_bit(PAGE_EXT_OWNER, &page_ext->flags); } +gfp_t __get_page_owner_gfp(struct page *page) +{ + struct page_ext *page_ext = lookup_page_ext(page); + + return page_ext->gfp_mask; +} + static ssize_t print_page_owner(char __user *buf, size_t count, unsigned long pfn, struct page *page, struct page_ext *page_ext) -- 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 --- arch/x86/include/asm/fpu/types.h | 72 +++++++++++++++++++++------------------- arch/x86/include/asm/processor.h | 10 ++++-- arch/x86/kernel/fpu/init.c | 39 ++++++++++++++++++++++ arch/x86/kernel/process.c | 2 +- fs/proc/kcore.c | 4 +-- include/linux/sched.h | 12 +++++-- kernel/fork.c | 8 ++++- 7 files changed, 104 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index 0637826292de..c49c5173158e 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -189,6 +189,7 @@ union fpregs_state { struct fxregs_state fxsave; struct swregs_state soft; struct xregs_state xsave; + u8 __padding[PAGE_SIZE]; }; /* @@ -197,40 +198,6 @@ union fpregs_state { * state fields: */ struct fpu { - /* - * @state: - * - * In-memory copy of all FPU registers that we save/restore - * over context switches. If the task is using the FPU then - * the registers in the FPU are more recent than this state - * copy. If the task context-switches away then they get - * saved here and represent the FPU state. - * - * After context switches there may be a (short) time period - * during which the in-FPU hardware registers are unchanged - * and still perfectly match this state, if the tasks - * scheduled afterwards are not using the FPU. - * - * This is the 'lazy restore' window of optimization, which - * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'. - * - * We detect whether a subsequent task uses the FPU via setting - * CR0::TS to 1, which causes any FPU use to raise a #NM fault. - * - * During this window, if the task gets scheduled again, we - * might be able to skip having to do a restore from this - * memory buffer to the hardware registers - at the cost of - * incurring the overhead of #NM fault traps. - * - * Note that on modern CPUs that support the XSAVEOPT (or other - * optimized XSAVE instructions), we don't use #NM traps anymore, - * as the hardware can track whether FPU registers need saving - * or not. On such CPUs we activate the non-lazy ('eagerfpu') - * logic, which unconditionally saves/restores all FPU state - * across context switches. (if FPU state exists.) - */ - union fpregs_state state; - /* * @last_cpu: * @@ -288,6 +255,43 @@ struct fpu { * deal with bursty apps that only use the FPU for a short time: */ unsigned char counter; + /* + * @state: + * + * In-memory copy of all FPU registers that we save/restore + * over context switches. If the task is using the FPU then + * the registers in the FPU are more recent than this state + * copy. If the task context-switches away then they get + * saved here and represent the FPU state. + * + * After context switches there may be a (short) time period + * during which the in-FPU hardware registers are unchanged + * and still perfectly match this state, if the tasks + * scheduled afterwards are not using the FPU. + * + * This is the 'lazy restore' window of optimization, which + * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'. + * + * We detect whether a subsequent task uses the FPU via setting + * CR0::TS to 1, which causes any FPU use to raise a #NM fault. + * + * During this window, if the task gets scheduled again, we + * might be able to skip having to do a restore from this + * memory buffer to the hardware registers - at the cost of + * incurring the overhead of #NM fault traps. + * + * Note that on modern CPUs that support the XSAVEOPT (or other + * optimized XSAVE instructions), we don't use #NM traps anymore, + * as the hardware can track whether FPU registers need saving + * or not. On such CPUs we activate the non-lazy ('eagerfpu') + * logic, which unconditionally saves/restores all FPU state + * across context switches. (if FPU state exists.) + */ + union fpregs_state state; + /* + * WARNING: 'state' is dynamically-sized. Do not put + * anything after it here. + */ }; #endif /* _ASM_X86_FPU_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 43e6519df0d5..944f1785ed0d 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -390,9 +390,6 @@ struct thread_struct { #endif unsigned long gs; - /* Floating point and extended processor state */ - struct fpu fpu; - /* Save middle states of ptrace breakpoints */ struct perf_event *ptrace_bps[HBP_NUM]; /* Debug status used for traps, single steps, etc... */ @@ -418,6 +415,13 @@ struct thread_struct { unsigned long iopl; /* Max allowed port in the bitmap, in bytes: */ unsigned io_bitmap_max; + + /* Floating point and extended processor state */ + struct fpu fpu; + /* + * WARNING: 'fpu' is dynamically-sized. It *MUST* be at + * the end. + */ }; /* diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 32826791e675..deacbfa6b33e 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -136,6 +136,45 @@ static void __init fpu__init_system_generic(void) unsigned int xstate_size; EXPORT_SYMBOL_GPL(xstate_size); +#define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \ + BUILD_BUG_ON((sizeof(TYPE) - \ + offsetof(TYPE, MEMBER) - \ + sizeof(((TYPE *)0)->MEMBER)) > \ + 0) \ + +/* + * We append the 'struct fpu' to the task_struct. + */ +int __weak arch_task_struct_size(void) +{ + int task_size = sizeof(struct task_struct); + + /* + * Subtract off the static size of the register state. + * It potentially has a bunch of padding. + */ + task_size -= sizeof(((struct task_struct *)0)->thread.fpu.state); + + /* + * Add back the dynamically-calculated register state + * size. + */ + task_size += xstate_size; + + /* + * We dynamically size 'struct fpu', so we require that + * it be at the end of 'thread_struct' and that + * 'thread_struct' be at the end of 'task_struct'. If + * you hit a compile error here, check the structure to + * see if something got added to the end. + */ + CHECK_MEMBER_AT_END_OF(struct fpu, state); + CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu); + CHECK_MEMBER_AT_END_OF(struct task_struct, thread); + + return task_size; +} + /* * Set up the xstate_size based on the legacy FPU context size. * diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 9cad694ed7c4..975420eac105 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -81,7 +81,7 @@ EXPORT_SYMBOL_GPL(idle_notifier_unregister); */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - *dst = *src; + memcpy(dst, src, arch_task_struct_size()); return fpu__copy(&dst->thread.fpu, &src->thread.fpu); } diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 91a4e6426321..a0fe99485687 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -92,7 +92,7 @@ static size_t get_kcore_size(int *nphdr, size_t *elf_buflen) roundup(sizeof(CORE_STR), 4)) + roundup(sizeof(struct elf_prstatus), 4) + roundup(sizeof(struct elf_prpsinfo), 4) + - roundup(sizeof(struct task_struct), 4); + roundup(arch_task_struct_size(), 4); *elf_buflen = PAGE_ALIGN(*elf_buflen); return size + *elf_buflen; } @@ -415,7 +415,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff) /* set up the task structure */ notes[2].name = CORE_STR; notes[2].type = NT_TASKSTRUCT; - notes[2].datasz = sizeof(struct task_struct); + notes[2].datasz = arch_task_struct_size(); notes[2].data = current; nhdr->p_filesz += notesize(¬es[2]); 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) diff --git a/kernel/fork.c b/kernel/fork.c index 1bfefc6f96a4..431b67a6098c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -287,15 +287,21 @@ static void set_max_threads(unsigned int max_threads_suggested) max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS); } +int __weak arch_task_struct_size(void) +{ + return sizeof(struct task_struct); +} + void __init fork_init(void) { + int task_struct_size = arch_task_struct_size(); #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR #ifndef ARCH_MIN_TASKALIGN #define ARCH_MIN_TASKALIGN L1_CACHE_BYTES #endif /* create a slab on which task_structs can be allocated */ task_struct_cachep = - kmem_cache_create("task_struct", sizeof(struct task_struct), + kmem_cache_create("task_struct", task_struct_size, ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL); #endif -- 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 --- arch/Kconfig | 4 ++++ arch/x86/Kconfig | 1 + arch/x86/kernel/fpu/init.c | 17 +++++++++-------- arch/x86/kernel/process.c | 2 +- fs/proc/kcore.c | 4 ++-- include/linux/sched.h | 6 +++++- kernel/fork.c | 11 +++++------ 7 files changed, 27 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/arch/Kconfig b/arch/Kconfig index bec6666a3cc4..8a8ea7110de8 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -221,6 +221,10 @@ config ARCH_TASK_STRUCT_ALLOCATOR config ARCH_THREAD_INFO_ALLOCATOR bool +# Select if arch wants to size task_struct dynamically via arch_task_struct_size: +config ARCH_WANTS_DYNAMIC_TASK_STRUCT + bool + config HAVE_REGS_AND_STACK_ACCESS_API bool help diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3dbb7e7909ca..b3a1a5d77d92 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -41,6 +41,7 @@ config X86 select ARCH_USE_CMPXCHG_LOCKREF if X86_64 select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS + select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_IPC_PARSE_VERSION if X86_32 select ARCH_WANT_OPTIONAL_GPIOLIB diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index deacbfa6b33e..0b39173dd971 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -4,6 +4,8 @@ #include #include +#include + /* * Initialize the TS bit in CR0 according to the style of context-switches * we are using: @@ -136,16 +138,14 @@ static void __init fpu__init_system_generic(void) unsigned int xstate_size; EXPORT_SYMBOL_GPL(xstate_size); -#define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \ - BUILD_BUG_ON((sizeof(TYPE) - \ - offsetof(TYPE, MEMBER) - \ - sizeof(((TYPE *)0)->MEMBER)) > \ - 0) \ +/* Enforce that 'MEMBER' is the last field of 'TYPE': */ +#define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \ + BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER)) /* - * We append the 'struct fpu' to the task_struct. + * We append the 'struct fpu' to the task_struct: */ -int __weak arch_task_struct_size(void) +static void __init fpu__init_task_struct_size(void) { int task_size = sizeof(struct task_struct); @@ -172,7 +172,7 @@ int __weak arch_task_struct_size(void) CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu); CHECK_MEMBER_AT_END_OF(struct task_struct, thread); - return task_size; + arch_task_struct_size = task_size; } /* @@ -326,6 +326,7 @@ void __init fpu__init_system(struct cpuinfo_x86 *c) fpu__init_system_generic(); fpu__init_system_xstate_size_legacy(); fpu__init_system_xstate(); + fpu__init_task_struct_size(); fpu__init_system_ctx_switch(); } diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 975420eac105..397688beed4b 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -81,7 +81,7 @@ EXPORT_SYMBOL_GPL(idle_notifier_unregister); */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - memcpy(dst, src, arch_task_struct_size()); + memcpy(dst, src, arch_task_struct_size); return fpu__copy(&dst->thread.fpu, &src->thread.fpu); } diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index a0fe99485687..92e6726f6e37 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -92,7 +92,7 @@ static size_t get_kcore_size(int *nphdr, size_t *elf_buflen) roundup(sizeof(CORE_STR), 4)) + roundup(sizeof(struct elf_prstatus), 4) + roundup(sizeof(struct elf_prpsinfo), 4) + - roundup(arch_task_struct_size(), 4); + roundup(arch_task_struct_size, 4); *elf_buflen = PAGE_ALIGN(*elf_buflen); return size + *elf_buflen; } @@ -415,7 +415,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff) /* set up the task structure */ notes[2].name = CORE_STR; notes[2].type = NT_TASKSTRUCT; - notes[2].datasz = arch_task_struct_size(); + notes[2].datasz = arch_task_struct_size; notes[2].data = current; nhdr->p_filesz += notesize(¬es[2]); 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) diff --git a/kernel/fork.c b/kernel/fork.c index 431b67a6098c..dbd9b8d7b7cc 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -287,21 +287,20 @@ static void set_max_threads(unsigned int max_threads_suggested) max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS); } -int __weak arch_task_struct_size(void) -{ - return sizeof(struct task_struct); -} +#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT +/* Initialized by the architecture: */ +int arch_task_struct_size __read_mostly; +#endif void __init fork_init(void) { - int task_struct_size = arch_task_struct_size(); #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR #ifndef ARCH_MIN_TASKALIGN #define ARCH_MIN_TASKALIGN L1_CACHE_BYTES #endif /* create a slab on which task_structs can be allocated */ task_struct_cachep = - kmem_cache_create("task_struct", task_struct_size, + kmem_cache_create("task_struct", arch_task_struct_size, ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL); #endif -- cgit v1.2.3 From cd812599796f500b042f5464b6665755eca21137 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 5 Jul 2015 11:12:07 -0400 Subject: NFS: Remove the "NFS_CAP_CHANGE_ATTR" capability Setting the change attribute has been mandatory for all NFS versions, since commit 3a1556e8662c ("NFSv2/v3: Simulate the change attribute"). We should therefore not have anything be conditional on it being set/unset. Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 2 +- fs/nfs/inode.c | 4 ++-- fs/nfs/nfs4proc.c | 3 --- include/linux/nfs_fs_sb.h | 2 +- 4 files changed, 4 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index ecebb406cc1a..4a90c9bb3135 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -775,7 +775,7 @@ static int nfs_init_server(struct nfs_server *server, server->options = data->options; server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID| NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP| - NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME|NFS_CAP_CHANGE_ATTR; + NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME; if (data->rsize) server->rsize = nfs_block_size(data->rsize, NULL); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 426e4f8207ef..0adc7d245b3d 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -442,7 +442,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); if (fattr->valid & NFS_ATTR_FATTR_CHANGE) inode->i_version = fattr->change_attr; - else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR)) + else nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | NFS_INO_REVAL_PAGECACHE); if (fattr->valid & NFS_ATTR_FATTR_SIZE) @@ -1692,7 +1692,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_force_lookup_revalidate(inode); inode->i_version = fattr->change_attr; } - } else if (server->caps & NFS_CAP_CHANGE_ATTR) + } else nfsi->cache_validity |= save_cache_validity; if (fattr->valid & NFS_ATTR_FATTR_MTIME) { diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 9264994ec9d3..c85ffe67b5f3 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -8591,7 +8591,6 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = { .minor_version = 0, .init_caps = NFS_CAP_READDIRPLUS | NFS_CAP_ATOMIC_OPEN - | NFS_CAP_CHANGE_ATTR | NFS_CAP_POSIX_LOCK, .init_client = nfs40_init_client, .shutdown_client = nfs40_shutdown_client, @@ -8617,7 +8616,6 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = { .minor_version = 1, .init_caps = NFS_CAP_READDIRPLUS | NFS_CAP_ATOMIC_OPEN - | NFS_CAP_CHANGE_ATTR | NFS_CAP_POSIX_LOCK | NFS_CAP_STATEID_NFSV41 | NFS_CAP_ATOMIC_OPEN_V1, @@ -8640,7 +8638,6 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { .minor_version = 2, .init_caps = NFS_CAP_READDIRPLUS | NFS_CAP_ATOMIC_OPEN - | NFS_CAP_CHANGE_ATTR | NFS_CAP_POSIX_LOCK | NFS_CAP_STATEID_NFSV41 | NFS_CAP_ATOMIC_OPEN_V1 diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index a2ea1491d3df..20bc8e51b161 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -220,7 +220,7 @@ struct nfs_server { #define NFS_CAP_SYMLINKS (1U << 2) #define NFS_CAP_ACLS (1U << 3) #define NFS_CAP_ATOMIC_OPEN (1U << 4) -#define NFS_CAP_CHANGE_ATTR (1U << 5) +/* #define NFS_CAP_CHANGE_ATTR (1U << 5) */ #define NFS_CAP_FILEID (1U << 6) #define NFS_CAP_MODE (1U << 7) #define NFS_CAP_NLINK (1U << 8) -- cgit v1.2.3 From 115c48d7a5351abeadd0c8a3dc87eca3d66a6475 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 5 Jul 2015 12:36:34 -0400 Subject: NFS: nfs_mark_for_revalidate should always set NFS_INO_REVAL_PAGECACHE I'm not aware of any existing bugs around this, but the expectation is that nfs_mark_for_revalidate() should always force a revalidation of the cached metadata. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index f91b5ade30c9..874b77228fb9 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -292,9 +292,12 @@ static inline void nfs_mark_for_revalidate(struct inode *inode) struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); - nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS; + nfsi->cache_validity |= NFS_INO_INVALID_ATTR | + NFS_INO_REVAL_PAGECACHE | + NFS_INO_INVALID_ACCESS | + NFS_INO_INVALID_ACL; if (S_ISDIR(inode->i_mode)) - nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_DATA; + nfsi->cache_validity |= NFS_INO_INVALID_DATA; spin_unlock(&inode->i_lock); } -- cgit v1.2.3 From a3bd4f989f532694337dd30538b635d5213ab86a Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Wed, 22 Jul 2015 20:53:09 +0800 Subject: mmc: sdhci-esdhc-imx: clear f_max in boarddata After commit 8d86e4fcccf6 ("mmc: sdhci-esdhc-imx: Call mmc_of_parse()"), it's not used anymore. Signed-off-by: Dong Aisheng Reviewed-by: Johan Derycke Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-esdhc-imx.c | 7 +------ include/linux/platform_data/mmc-esdhc-imx.h | 1 - 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index 1b0e61847e73..c6b9f6492e1a 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -581,13 +581,8 @@ static void esdhc_writeb_le(struct sdhci_host *host, u8 val, int reg) static unsigned int esdhc_pltfm_get_max_clock(struct sdhci_host *host) { struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); - struct pltfm_imx_data *imx_data = pltfm_host->priv; - struct esdhc_platform_data *boarddata = &imx_data->boarddata; - if (boarddata->f_max && (boarddata->f_max < pltfm_host->clock)) - return boarddata->f_max; - else - return pltfm_host->clock; + return pltfm_host->clock; } static unsigned int esdhc_pltfm_get_min_clock(struct sdhci_host *host) diff --git a/include/linux/platform_data/mmc-esdhc-imx.h b/include/linux/platform_data/mmc-esdhc-imx.h index 75f70f6ac137..e1571efa3f2b 100644 --- a/include/linux/platform_data/mmc-esdhc-imx.h +++ b/include/linux/platform_data/mmc-esdhc-imx.h @@ -43,7 +43,6 @@ struct esdhc_platform_data { enum wp_types wp_type; enum cd_types cd_type; int max_bus_width; - unsigned int f_max; bool support_vsel; unsigned int delay_line; }; -- cgit v1.2.3 From e3eea1404f5ff7a2ceb7b5e7ba412a6fd94f2935 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 24 Jul 2015 10:38:12 -0400 Subject: ftrace: Fix breakage of set_ftrace_pid Commit 4104d326b670 ("ftrace: Remove global function list and call function directly") simplified the ftrace code by removing the global_ops list with a new design. But this cleanup also broke the filtering of PIDs that are added to the set_ftrace_pid file. Add back the proper hooks to have pid filtering working once again. Cc: stable@vger.kernel.org # 3.16+ Reported-by: Matt Fleming Reported-by: Richard Weinberger Tested-by: Matt Fleming Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 3 +++ kernel/trace/ftrace.c | 52 +++++++++++++++++++++++++++++++++----------------- 2 files changed, 37 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 1da602982cf9..6cd8c0ee4b6f 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -116,6 +116,7 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); * SAVE_REGS. If another ops with this flag set is already registered * for any of the functions that this ops will be registered for, then * this ops will fail to register or set_filter_ip. + * PID - Is affected by set_ftrace_pid (allows filtering on those pids) */ enum { FTRACE_OPS_FL_ENABLED = 1 << 0, @@ -132,6 +133,7 @@ enum { FTRACE_OPS_FL_MODIFYING = 1 << 11, FTRACE_OPS_FL_ALLOC_TRAMP = 1 << 12, FTRACE_OPS_FL_IPMODIFY = 1 << 13, + FTRACE_OPS_FL_PID = 1 << 14, }; #ifdef CONFIG_DYNAMIC_FTRACE @@ -159,6 +161,7 @@ struct ftrace_ops { struct ftrace_ops *next; unsigned long flags; void *private; + ftrace_func_t saved_func; int __percpu *disabled; #ifdef CONFIG_DYNAMIC_FTRACE int nr_trampolines; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 02bece4a99ea..eb11011b5292 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -98,6 +98,13 @@ struct ftrace_pid { struct pid *pid; }; +static bool ftrace_pids_enabled(void) +{ + return !list_empty(&ftrace_pids); +} + +static void ftrace_update_trampoline(struct ftrace_ops *ops); + /* * ftrace_disabled is set when an anomaly is discovered. * ftrace_disabled is much stronger than ftrace_enabled. @@ -109,7 +116,6 @@ static DEFINE_MUTEX(ftrace_lock); static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end; static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; -ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; static struct ftrace_ops global_ops; static struct ftrace_ops control_ops; @@ -183,14 +189,7 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, if (!test_tsk_trace_trace(current)) return; - ftrace_pid_function(ip, parent_ip, op, regs); -} - -static void set_ftrace_pid_function(ftrace_func_t func) -{ - /* do not set ftrace_pid_function to itself! */ - if (func != ftrace_pid_func) - ftrace_pid_function = func; + op->saved_func(ip, parent_ip, op, regs); } /** @@ -202,7 +201,6 @@ static void set_ftrace_pid_function(ftrace_func_t func) void clear_ftrace_function(void) { ftrace_trace_function = ftrace_stub; - ftrace_pid_function = ftrace_stub; } static void control_ops_disable_all(struct ftrace_ops *ops) @@ -436,6 +434,12 @@ static int __register_ftrace_function(struct ftrace_ops *ops) } else add_ftrace_ops(&ftrace_ops_list, ops); + /* Always save the function, and reset at unregistering */ + ops->saved_func = ops->func; + + if (ops->flags & FTRACE_OPS_FL_PID && ftrace_pids_enabled()) + ops->func = ftrace_pid_func; + ftrace_update_trampoline(ops); if (ftrace_enabled) @@ -463,15 +467,28 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) if (ftrace_enabled) update_ftrace_function(); + ops->func = ops->saved_func; + return 0; } static void ftrace_update_pid_func(void) { + bool enabled = ftrace_pids_enabled(); + struct ftrace_ops *op; + /* Only do something if we are tracing something */ if (ftrace_trace_function == ftrace_stub) return; + do_for_each_ftrace_op(op, ftrace_ops_list) { + if (op->flags & FTRACE_OPS_FL_PID) { + op->func = enabled ? ftrace_pid_func : + op->saved_func; + ftrace_update_trampoline(op); + } + } while_for_each_ftrace_op(op); + update_ftrace_function(); } @@ -1133,7 +1150,8 @@ static struct ftrace_ops global_ops = { .local_hash.filter_hash = EMPTY_HASH, INIT_OPS_HASH(global_ops) .flags = FTRACE_OPS_FL_RECURSION_SAFE | - FTRACE_OPS_FL_INITIALIZED, + FTRACE_OPS_FL_INITIALIZED | + FTRACE_OPS_FL_PID, }; /* @@ -5023,7 +5041,9 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops) static struct ftrace_ops global_ops = { .func = ftrace_stub, - .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED, + .flags = FTRACE_OPS_FL_RECURSION_SAFE | + FTRACE_OPS_FL_INITIALIZED | + FTRACE_OPS_FL_PID, }; static int __init ftrace_nodyn_init(void) @@ -5080,11 +5100,6 @@ void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func) if (WARN_ON(tr->ops->func != ftrace_stub)) printk("ftrace ops had %pS for function\n", tr->ops->func); - /* Only the top level instance does pid tracing */ - if (!list_empty(&ftrace_pids)) { - set_ftrace_pid_function(func); - func = ftrace_pid_func; - } } tr->ops->func = func; tr->ops->private = tr; @@ -5371,7 +5386,7 @@ static void *fpid_start(struct seq_file *m, loff_t *pos) { mutex_lock(&ftrace_lock); - if (list_empty(&ftrace_pids) && (!*pos)) + if (!ftrace_pids_enabled() && (!*pos)) return (void *) 1; return seq_list_start(&ftrace_pids, *pos); @@ -5610,6 +5625,7 @@ static struct ftrace_ops graph_ops = { .func = ftrace_stub, .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED | + FTRACE_OPS_FL_PID | FTRACE_OPS_FL_STUB, #ifdef FTRACE_GRAPH_TRAMP_ADDR .trampoline = FTRACE_GRAPH_TRAMP_ADDR, -- cgit v1.2.3 From e018a0cce3d849bc73e72686c571420adc40bad2 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 24 Jul 2015 21:24:04 +0300 Subject: net/macb: convert to kernel doc This patch coverts struct description to the kernel doc format. There is no functional change. Signed-off-by: Andy Shevchenko Signed-off-by: David S. Miller --- include/linux/platform_data/macb.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/macb.h b/include/linux/platform_data/macb.h index 044a124bfbbc..21b15f6fee25 100644 --- a/include/linux/platform_data/macb.h +++ b/include/linux/platform_data/macb.h @@ -8,11 +8,19 @@ #ifndef __MACB_PDATA_H__ #define __MACB_PDATA_H__ +/** + * struct macb_platform_data - platform data for MACB Ethernet + * @phy_mask: phy mask passed when register the MDIO bus + * within the driver + * @phy_irq_pin: PHY IRQ + * @is_rmii: using RMII interface? + * @rev_eth_addr: reverse Ethernet address byte order + */ struct macb_platform_data { u32 phy_mask; - int phy_irq_pin; /* PHY IRQ */ - u8 is_rmii; /* using RMII interface? */ - u8 rev_eth_addr; /* reverse Ethernet address byte order */ + int phy_irq_pin; + u8 is_rmii; + u8 rev_eth_addr; }; #endif /* __MACB_PDATA_H__ */ -- cgit v1.2.3 From 35068ce8cbf1749ef1a4b9b1493af83b8488c37b Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Wed, 1 Jul 2015 09:10:43 +0200 Subject: of: constify drv arg of of_driver_match_device stub With this change the stub has the same signature as the actual function, preventing this compiler warning when building without CONFIG_OF: drivers/base/property.c: In function 'fwnode_driver_match_device': >> drivers/base/property.c:608:38: warning: passing argument 2 of 'of_driver_match_device' discards 'const' qualifier from pointer target type return of_driver_match_device(dev, drv); ^ In file included from drivers/base/property.c:18:0: include/linux/of_device.h:61:19: note: expected 'struct device_driver *' but argument is of type 'const struct device_driver *' static inline int of_driver_match_device(struct device *dev, ^ Signed-off-by: Tomeu Vizoso Signed-off-by: Rob Herring --- include/linux/of_device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 4c508549833a..cc7dd687a89d 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -59,7 +59,7 @@ void of_dma_configure(struct device *dev, struct device_node *np); #else /* CONFIG_OF */ static inline int of_driver_match_device(struct device *dev, - struct device_driver *drv) + const struct device_driver *drv) { return 0; } -- cgit v1.2.3 From 559ed40752dc63e68f9b9ad301b20e6a3fe5cf21 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 26 Jul 2015 02:07:47 +0200 Subject: cpufreq: Avoid attempts to create duplicate symbolic links After commit 87549141d516 (cpufreq: Stop migrating sysfs files on hotplug) there is a problem with CPUs that share cpufreq policy objects with other CPUs and are initially offline. Say CPU1 shares a policy with CPU0 which is online and is registered first. As part of the registration process, cpufreq_add_dev() is called for it. It creates the policy object and a symbolic link to it from the CPU1's sysfs directory. If CPU1 is registered subsequently and it is offline at that time, cpufreq_add_dev() will attempt to create a symbolic link to the policy object for it, but that link is present already, so a warning about that will be triggered. To avoid that warning, make cpufreq use an additional CPU mask containing related CPUs that are actually present for each policy object. That mask is initialized when the policy object is populated after its creation (for the first online CPU using it) and it includes CPUs from the "policy CPUs" mask returned by the cpufreq driver's ->init() callback that are physically present at that time. Symbolic links to the policy are created only for the CPUs in that mask. If cpufreq_add_dev() is invoked for an offline CPU, it checks the new mask and only creates the symlink if the CPU was not in it (the CPU is added to the mask at the same time). In turn, cpufreq_remove_dev() drops the given CPU from the new mask, removes its symlink to the policy object and returns, unless it is the CPU owning the policy object. In that case, the policy object is moved to a new CPU's sysfs directory or deleted if the CPU being removed was the last user of the policy. While at it, notice that cpufreq_remove_dev() can't fail, because its return value is ignored, so make it ignore return values from __cpufreq_remove_dev_prepare() and __cpufreq_remove_dev_finish() and prevent these functions from aborting on errors returned by __cpufreq_governor(). Also drop the now unused sif argument from them. Fixes: 87549141d516 (cpufreq: Stop migrating sysfs files on hotplug) Signed-off-by: Rafael J. Wysocki Reported-and-tested-by: Russell King Acked-by: Viresh Kumar --- drivers/cpufreq/cpufreq.c | 108 +++++++++++++++++++++++----------------------- include/linux/cpufreq.h | 1 + 2 files changed, 56 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 26063afb3eba..7a3c30c4336f 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1002,7 +1002,7 @@ static int cpufreq_add_dev_symlink(struct cpufreq_policy *policy) int ret = 0; /* Some related CPUs might not be present (physically hotplugged) */ - for_each_cpu_and(j, policy->related_cpus, cpu_present_mask) { + for_each_cpu(j, policy->real_cpus) { if (j == policy->kobj_cpu) continue; @@ -1019,7 +1019,7 @@ static void cpufreq_remove_dev_symlink(struct cpufreq_policy *policy) unsigned int j; /* Some related CPUs might not be present (physically hotplugged) */ - for_each_cpu_and(j, policy->related_cpus, cpu_present_mask) { + for_each_cpu(j, policy->real_cpus) { if (j == policy->kobj_cpu) continue; @@ -1163,11 +1163,14 @@ static struct cpufreq_policy *cpufreq_policy_alloc(struct device *dev) if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL)) goto err_free_cpumask; + if (!zalloc_cpumask_var(&policy->real_cpus, GFP_KERNEL)) + goto err_free_rcpumask; + ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, &dev->kobj, "cpufreq"); if (ret) { pr_err("%s: failed to init policy->kobj: %d\n", __func__, ret); - goto err_free_rcpumask; + goto err_free_real_cpus; } INIT_LIST_HEAD(&policy->policy_list); @@ -1184,6 +1187,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(struct device *dev) return policy; +err_free_real_cpus: + free_cpumask_var(policy->real_cpus); err_free_rcpumask: free_cpumask_var(policy->related_cpus); err_free_cpumask: @@ -1234,6 +1239,7 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy, bool notify) write_unlock_irqrestore(&cpufreq_driver_lock, flags); cpufreq_policy_put_kobj(policy, notify); + free_cpumask_var(policy->real_cpus); free_cpumask_var(policy->related_cpus); free_cpumask_var(policy->cpus); kfree(policy); @@ -1258,14 +1264,17 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) pr_debug("adding CPU %u\n", cpu); - /* - * Only possible if 'cpu' wasn't physically present earlier and we are - * here from subsys_interface add callback. A hotplug notifier will - * follow and we will handle it like logical CPU hotplug then. For now, - * just create the sysfs link. - */ - if (cpu_is_offline(cpu)) - return add_cpu_dev_symlink(per_cpu(cpufreq_cpu_data, cpu), cpu); + if (cpu_is_offline(cpu)) { + /* + * Only possible if we are here from the subsys_interface add + * callback. A hotplug notifier will follow and we will handle + * it as CPU online then. For now, just create the sysfs link, + * unless there is no policy or the link is already present. + */ + policy = per_cpu(cpufreq_cpu_data, cpu); + return policy && !cpumask_test_and_set_cpu(cpu, policy->real_cpus) + ? add_cpu_dev_symlink(policy, cpu) : 0; + } if (!down_read_trylock(&cpufreq_rwsem)) return 0; @@ -1307,6 +1316,10 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) /* related cpus should atleast have policy->cpus */ cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus); + /* Remember which CPUs have been present at the policy creation time. */ + if (!recover_policy) + cpumask_and(policy->real_cpus, policy->cpus, cpu_present_mask); + /* * affected cpus must always be the one, which are online. We aren't * managing offline cpus here. @@ -1420,8 +1433,7 @@ nomem_out: return ret; } -static int __cpufreq_remove_dev_prepare(struct device *dev, - struct subsys_interface *sif) +static int __cpufreq_remove_dev_prepare(struct device *dev) { unsigned int cpu = dev->id; int ret = 0; @@ -1437,10 +1449,8 @@ static int __cpufreq_remove_dev_prepare(struct device *dev, if (has_target()) { ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP); - if (ret) { + if (ret) pr_err("%s: Failed to stop governor\n", __func__); - return ret; - } } down_write(&policy->rwsem); @@ -1473,8 +1483,7 @@ static int __cpufreq_remove_dev_prepare(struct device *dev, return ret; } -static int __cpufreq_remove_dev_finish(struct device *dev, - struct subsys_interface *sif) +static int __cpufreq_remove_dev_finish(struct device *dev) { unsigned int cpu = dev->id; int ret; @@ -1492,10 +1501,8 @@ static int __cpufreq_remove_dev_finish(struct device *dev, /* If cpu is last user of policy, free policy */ if (has_target()) { ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT); - if (ret) { + if (ret) pr_err("%s: Failed to exit governor\n", __func__); - return ret; - } } /* @@ -1506,10 +1513,6 @@ static int __cpufreq_remove_dev_finish(struct device *dev, if (cpufreq_driver->exit) cpufreq_driver->exit(policy); - /* Free the policy only if the driver is getting removed. */ - if (sif) - cpufreq_policy_free(policy, true); - return 0; } @@ -1521,42 +1524,41 @@ static int __cpufreq_remove_dev_finish(struct device *dev, static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif) { unsigned int cpu = dev->id; - int ret; - - /* - * Only possible if 'cpu' is getting physically removed now. A hotplug - * notifier should have already been called and we just need to remove - * link or free policy here. - */ - if (cpu_is_offline(cpu)) { - struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu); - struct cpumask mask; + struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu); - if (!policy) - return 0; + if (!policy) + return 0; - cpumask_copy(&mask, policy->related_cpus); - cpumask_clear_cpu(cpu, &mask); + if (cpu_online(cpu)) { + __cpufreq_remove_dev_prepare(dev); + __cpufreq_remove_dev_finish(dev); + } - /* - * Free policy only if all policy->related_cpus are removed - * physically. - */ - if (cpumask_intersects(&mask, cpu_present_mask)) { - remove_cpu_dev_symlink(policy, cpu); - return 0; - } + cpumask_clear_cpu(cpu, policy->real_cpus); + if (cpumask_empty(policy->real_cpus)) { cpufreq_policy_free(policy, true); return 0; } - ret = __cpufreq_remove_dev_prepare(dev, sif); + if (cpu != policy->kobj_cpu) { + remove_cpu_dev_symlink(policy, cpu); + } else { + /* + * The CPU owning the policy object is going away. Move it to + * another suitable CPU. + */ + unsigned int new_cpu = cpumask_first(policy->real_cpus); + struct device *new_dev = get_cpu_device(new_cpu); + + dev_dbg(dev, "%s: Moving policy object to CPU%u\n", __func__, new_cpu); - if (!ret) - ret = __cpufreq_remove_dev_finish(dev, sif); + sysfs_remove_link(&new_dev->kobj, "cpufreq"); + policy->kobj_cpu = new_cpu; + WARN_ON(kobject_move(&policy->kobj, &new_dev->kobj)); + } - return ret; + return 0; } static void handle_update(struct work_struct *work) @@ -2395,11 +2397,11 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb, break; case CPU_DOWN_PREPARE: - __cpufreq_remove_dev_prepare(dev, NULL); + __cpufreq_remove_dev_prepare(dev); break; case CPU_POST_DEAD: - __cpufreq_remove_dev_finish(dev, NULL); + __cpufreq_remove_dev_finish(dev); break; case CPU_DOWN_FAILED: diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 29ad97c34fd5..bde1e567b3a9 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -62,6 +62,7 @@ struct cpufreq_policy { /* CPUs sharing clock, require sw coordination */ cpumask_var_t cpus; /* Online CPUs only */ cpumask_var_t related_cpus; /* Online + Offline CPUs */ + cpumask_var_t real_cpus; /* Related and present */ unsigned int shared_type; /* ACPI: ANY or ALL affected CPUs should set cpufreq */ -- cgit v1.2.3 From 84ded2f8e7dda336fc2fb3570726ceb3b3b3590f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 3 Aug 2015 11:45:34 -0400 Subject: Revert "libata: Implement support for sense data reporting" This reverts commit fe7173c206de63fc28475ee6ae42ff95c05692de. As implemented, ACS-4 sense reporting for ATA devices bypasses error diagnosis and handling in libata degrading EH behavior significantly. Revert the related changes for now. ATA_ID_COMMAND_SET_3/4 constants are not reverted as they're used by later changes. Signed-off-by: Tejun Heo Cc: Hannes Reinecke Cc: stable@vger.kernel.org #v4.1+ --- drivers/ata/libata-core.c | 20 +---------- drivers/ata/libata-eh.c | 86 ++--------------------------------------------- include/linux/ata.h | 16 --------- 3 files changed, 4 insertions(+), 118 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 426bc12459de..19bcb80b2031 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2147,24 +2147,6 @@ static int ata_dev_config_ncq(struct ata_device *dev, return 0; } -static void ata_dev_config_sense_reporting(struct ata_device *dev) -{ - unsigned int err_mask; - - if (!ata_id_has_sense_reporting(dev->id)) - return; - - if (ata_id_sense_reporting_enabled(dev->id)) - return; - - err_mask = ata_dev_set_feature(dev, SETFEATURE_SENSE_DATA, 0x1); - if (err_mask) { - ata_dev_dbg(dev, - "failed to enable Sense Data Reporting, Emask 0x%x\n", - err_mask); - } -} - /** * ata_dev_configure - Configure the specified ATA/ATAPI device * @dev: Target device to configure @@ -2387,7 +2369,7 @@ int ata_dev_configure(struct ata_device *dev) dev->devslp_timing[i] = sata_setting[j]; } } - ata_dev_config_sense_reporting(dev); + dev->cdb_len = 16; } diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index af08d32af4e0..16125be34893 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -1629,70 +1629,6 @@ unsigned int atapi_eh_tur(struct ata_device *dev, u8 *r_sense_key) return err_mask; } -/** - * ata_eh_request_sense - perform REQUEST_SENSE_DATA_EXT - * @dev: device to perform REQUEST_SENSE_SENSE_DATA_EXT to - * @sense_buf: result sense data buffer (SCSI_SENSE_BUFFERSIZE bytes long) - * @dfl_sense_key: default sense key to use - * - * Perform REQUEST_SENSE_DATA_EXT after the device reported CHECK - * SENSE. This function is EH helper. - * - * LOCKING: - * Kernel thread context (may sleep). - * - * RETURNS: - * encoded sense data on success, 0 on failure or if sense data - * is not available. - */ -static u32 ata_eh_request_sense(struct ata_queued_cmd *qc, - struct scsi_cmnd *cmd) -{ - struct ata_device *dev = qc->dev; - struct ata_taskfile tf; - unsigned int err_mask; - - if (!cmd) - return 0; - - DPRINTK("ATA request sense\n"); - ata_dev_warn(dev, "request sense\n"); - if (!ata_id_sense_reporting_enabled(dev->id)) { - ata_dev_warn(qc->dev, "sense data reporting disabled\n"); - return 0; - } - ata_tf_init(dev, &tf); - - tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; - tf.flags |= ATA_TFLAG_LBA | ATA_TFLAG_LBA48; - tf.command = ATA_CMD_REQ_SENSE_DATA; - tf.protocol = ATA_PROT_NODATA; - - err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0); - /* - * ACS-4 states: - * The device may set the SENSE DATA AVAILABLE bit to one in the - * STATUS field and clear the ERROR bit to zero in the STATUS field - * to indicate that the command returned completion without an error - * and the sense data described in table 306 is available. - * - * IOW the 'ATA_SENSE' bit might not be set even though valid - * sense data is available. - * So check for both. - */ - if ((tf.command & ATA_SENSE) || - tf.lbah != 0 || tf.lbam != 0 || tf.lbal != 0) { - ata_scsi_set_sense(cmd, tf.lbah, tf.lbam, tf.lbal); - qc->flags |= ATA_QCFLAG_SENSE_VALID; - ata_dev_warn(dev, "sense data %02x/%02x/%02x\n", - tf.lbah, tf.lbam, tf.lbal); - } else { - ata_dev_warn(dev, "request sense failed stat %02x emask %x\n", - tf.command, err_mask); - } - return err_mask; -} - /** * atapi_eh_request_sense - perform ATAPI REQUEST_SENSE * @dev: device to perform REQUEST_SENSE to @@ -1896,22 +1832,7 @@ static unsigned int ata_eh_analyze_tf(struct ata_queued_cmd *qc, return ATA_EH_RESET; } - /* - * Sense data reporting does not work if the - * device fault bit is set. - */ - if ((stat & ATA_SENSE) && !(stat & ATA_DF) && - !(qc->flags & ATA_QCFLAG_SENSE_VALID)) { - if (!(qc->ap->pflags & ATA_PFLAG_FROZEN)) { - tmp = ata_eh_request_sense(qc, qc->scsicmd); - if (tmp) - qc->err_mask |= tmp; - } else { - ata_dev_warn(qc->dev, "sense data available but port frozen\n"); - } - } - - /* Set by NCQ autosense or request sense above */ + /* Set by NCQ autosense */ if (qc->flags & ATA_QCFLAG_SENSE_VALID) return 0; @@ -2658,15 +2579,14 @@ static void ata_eh_link_report(struct ata_link *link) #ifdef CONFIG_ATA_VERBOSE_ERROR if (res->command & (ATA_BUSY | ATA_DRDY | ATA_DF | ATA_DRQ | - ATA_SENSE | ATA_ERR)) { + ATA_ERR)) { if (res->command & ATA_BUSY) ata_dev_err(qc->dev, "status: { Busy }\n"); else - ata_dev_err(qc->dev, "status: { %s%s%s%s%s}\n", + ata_dev_err(qc->dev, "status: { %s%s%s%s}\n", res->command & ATA_DRDY ? "DRDY " : "", res->command & ATA_DF ? "DF " : "", res->command & ATA_DRQ ? "DRQ " : "", - res->command & ATA_SENSE ? "SENSE " : "", res->command & ATA_ERR ? "ERR " : ""); } diff --git a/include/linux/ata.h b/include/linux/ata.h index 6c78956aa470..0e6a782575b5 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -385,8 +385,6 @@ enum { SATA_SSP = 0x06, /* Software Settings Preservation */ SATA_DEVSLP = 0x09, /* Device Sleep */ - SETFEATURE_SENSE_DATA = 0xC3, /* Sense Data Reporting feature */ - /* feature values for SET_MAX */ ATA_SET_MAX_ADDR = 0x00, ATA_SET_MAX_PASSWD = 0x01, @@ -720,20 +718,6 @@ static inline bool ata_id_has_read_log_dma_ext(const u16 *id) return false; } -static inline bool ata_id_has_sense_reporting(const u16 *id) -{ - if (!(id[ATA_ID_CFS_ENABLE_2] & (1 << 15))) - return false; - return id[ATA_ID_COMMAND_SET_3] & (1 << 6); -} - -static inline bool ata_id_sense_reporting_enabled(const u16 *id) -{ - if (!(id[ATA_ID_CFS_ENABLE_2] & (1 << 15))) - return false; - return id[ATA_ID_COMMAND_SET_4] & (1 << 6); -} - /** * ata_id_major_version - get ATA level of drive * @id: Identify data -- cgit v1.2.3 From 74a80d67b8316eb3fbeb73dafc060a5a0a708587 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 3 Aug 2015 11:46:39 -0400 Subject: Revert "libata: Implement NCQ autosense" This reverts commit 42b966fbf35da9c87f08d98f9b8978edf9e717cf. As implemented, ACS-4 sense reporting for ATA devices bypasses error diagnosis and handling in libata degrading EH behavior significantly. Revert the related changes for now. Signed-off-by: Tejun Heo Cc: Hannes Reinecke Cc: stable@vger.kernel.org #v4.1+ --- drivers/ata/libata-eh.c | 18 ------------------ drivers/ata/libata-scsi.c | 9 ++------- drivers/ata/libata.h | 1 - include/linux/ata.h | 2 -- 4 files changed, 2 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 16125be34893..cb0508af1459 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -1592,8 +1592,6 @@ static int ata_eh_read_log_10h(struct ata_device *dev, tf->hob_lbah = buf[10]; tf->nsect = buf[12]; tf->hob_nsect = buf[13]; - if (ata_id_has_ncq_autosense(dev->id)) - tf->auxiliary = buf[14] << 16 | buf[15] << 8 | buf[16]; return 0; } @@ -1791,18 +1789,6 @@ void ata_eh_analyze_ncq_error(struct ata_link *link) memcpy(&qc->result_tf, &tf, sizeof(tf)); qc->result_tf.flags = ATA_TFLAG_ISADDR | ATA_TFLAG_LBA | ATA_TFLAG_LBA48; qc->err_mask |= AC_ERR_DEV | AC_ERR_NCQ; - if (qc->result_tf.auxiliary) { - char sense_key, asc, ascq; - - sense_key = (qc->result_tf.auxiliary >> 16) & 0xff; - asc = (qc->result_tf.auxiliary >> 8) & 0xff; - ascq = qc->result_tf.auxiliary & 0xff; - ata_dev_dbg(dev, "NCQ Autosense %02x/%02x/%02x\n", - sense_key, asc, ascq); - ata_scsi_set_sense(qc->scsicmd, sense_key, asc, ascq); - qc->flags |= ATA_QCFLAG_SENSE_VALID; - } - ehc->i.err_mask &= ~AC_ERR_DEV; } @@ -1832,10 +1818,6 @@ static unsigned int ata_eh_analyze_tf(struct ata_queued_cmd *qc, return ATA_EH_RESET; } - /* Set by NCQ autosense */ - if (qc->flags & ATA_QCFLAG_SENSE_VALID) - return 0; - if (stat & (ATA_ERR | ATA_DF)) qc->err_mask |= AC_ERR_DEV; else diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index e1ecd2ab3724..0d7f0da3a269 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -270,11 +270,8 @@ DEVICE_ATTR(unload_heads, S_IRUGO | S_IWUSR, ata_scsi_park_show, ata_scsi_park_store); EXPORT_SYMBOL_GPL(dev_attr_unload_heads); -void ata_scsi_set_sense(struct scsi_cmnd *cmd, u8 sk, u8 asc, u8 ascq) +static void ata_scsi_set_sense(struct scsi_cmnd *cmd, u8 sk, u8 asc, u8 ascq) { - if (!cmd) - return; - cmd->result = (DRIVER_SENSE << 24) | SAM_STAT_CHECK_CONDITION; scsi_build_sense_buffer(0, cmd->sense_buffer, sk, asc, ascq); @@ -1780,9 +1777,7 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc) ((cdb[2] & 0x20) || need_sense)) { ata_gen_passthru_sense(qc); } else { - if (qc->flags & ATA_QCFLAG_SENSE_VALID) { - cmd->result = SAM_STAT_CHECK_CONDITION; - } else if (!need_sense) { + if (!need_sense) { cmd->result = SAM_STAT_GOOD; } else { /* TODO: decide which descriptor format to use diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index 8cfdd9616d16..f840ca18a7c0 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -137,7 +137,6 @@ extern int ata_scsi_add_hosts(struct ata_host *host, struct scsi_host_template *sht); extern void ata_scsi_scan_host(struct ata_port *ap, int sync); extern int ata_scsi_offline_dev(struct ata_device *dev); -extern void ata_scsi_set_sense(struct scsi_cmnd *cmd, u8 sk, u8 asc, u8 ascq); extern void ata_scsi_media_change_notify(struct ata_device *dev); extern void ata_scsi_hotplug(struct work_struct *work); extern void ata_schedule_scsi_eh(struct Scsi_Host *shost); diff --git a/include/linux/ata.h b/include/linux/ata.h index 0e6a782575b5..d2992bfa1706 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -528,8 +528,6 @@ struct ata_bmdma_prd { #define ata_id_cdb_intr(id) (((id)[ATA_ID_CONFIG] & 0x60) == 0x20) #define ata_id_has_da(id) ((id)[ATA_ID_SATA_CAPABILITY_2] & (1 << 4)) #define ata_id_has_devslp(id) ((id)[ATA_ID_FEATURE_SUPP] & (1 << 8)) -#define ata_id_has_ncq_autosense(id) \ - ((id)[ATA_ID_FEATURE_SUPP] & (1 << 7)) static inline bool ata_id_has_hipm(const u16 *id) { -- cgit v1.2.3 From 4248b0da460839e30eaaad78992b9a1dd3e63e21 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 6 Aug 2015 15:46:20 -0700 Subject: fs, file table: reinit files_stat.max_files after deferred memory initialisation Dave Hansen reported the following; My laptop has been behaving strangely with 4.2-rc2. Once I log in to my X session, I start getting all kinds of strange errors from applications and see this in my dmesg: VFS: file-max limit 8192 reached The problem is that the file-max is calculated before memory is fully initialised and miscalculates how much memory the kernel is using. This patch recalculates file-max after deferred memory initialisation. Note that using memory hotplug infrastructure would not have avoided this problem as the value is not recalculated after memory hot-add. 4.1: files_stat.max_files = 6582781 4.2-rc2: files_stat.max_files = 8192 4.2-rc2 patched: files_stat.max_files = 6562467 Small differences with the patch applied and 4.1 but not enough to matter. Signed-off-by: Mel Gorman Reported-by: Dave Hansen Cc: Nicolai Stange Cc: Dave Hansen Cc: Alex Ng Cc: Fengguang Wu Cc: Peter Zijlstra (Intel) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/dcache.c | 13 +++---------- fs/file_table.c | 24 +++++++++++++++--------- include/linux/fs.h | 5 +++-- init/main.c | 2 +- mm/page_alloc.c | 3 +++ 5 files changed, 25 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/fs/dcache.c b/fs/dcache.c index 5c8ea15e73a5..9b5fe503f6cb 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -3442,22 +3442,15 @@ void __init vfs_caches_init_early(void) inode_init_early(); } -void __init vfs_caches_init(unsigned long mempages) +void __init vfs_caches_init(void) { - unsigned long reserve; - - /* Base hash sizes on available memory, with a reserve equal to - 150% of current kernel size */ - - reserve = min((mempages - nr_free_pages()) * 3/2, mempages - 1); - mempages -= reserve; - names_cachep = kmem_cache_create("names_cache", PATH_MAX, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); dcache_init(); inode_init(); - files_init(mempages); + files_init(); + files_maxfiles_init(); mnt_init(); bdev_cache_init(); chrdev_init(); diff --git a/fs/file_table.c b/fs/file_table.c index 7f9d407c7595..ad17e05ebf95 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -25,6 +25,7 @@ #include #include #include +#include #include @@ -308,19 +309,24 @@ void put_filp(struct file *file) } } -void __init files_init(unsigned long mempages) +void __init files_init(void) { - unsigned long n; - filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); + percpu_counter_init(&nr_files, 0, GFP_KERNEL); +} - /* - * One file with associated inode and dcache is very roughly 1K. - * Per default don't use more than 10% of our memory for files. - */ +/* + * One file with associated inode and dcache is very roughly 1K. Per default + * do not use more than 10% of our memory for files. + */ +void __init files_maxfiles_init(void) +{ + unsigned long n; + unsigned long memreserve = (totalram_pages - nr_free_pages()) * 3/2; + + memreserve = min(memreserve, totalram_pages - 1); + n = ((totalram_pages - memreserve) * (PAGE_SIZE / 1024)) / 10; - n = (mempages * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = max_t(unsigned long, n, NR_FILE); - percpu_counter_init(&nr_files, 0, GFP_KERNEL); } diff --git a/include/linux/fs.h b/include/linux/fs.h index cc008c338f5a..84b783f277f7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -55,7 +55,8 @@ struct vm_fault; extern void __init inode_init(void); extern void __init inode_init_early(void); -extern void __init files_init(unsigned long); +extern void __init files_init(void); +extern void __init files_maxfiles_init(void); extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); @@ -2245,7 +2246,7 @@ extern int ioctl_preallocate(struct file *filp, void __user *argp); /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); -extern void __init vfs_caches_init(unsigned long); +extern void __init vfs_caches_init(void); extern struct kmem_cache *names_cachep; diff --git a/init/main.c b/init/main.c index c5d5626289ce..56506553d4d8 100644 --- a/init/main.c +++ b/init/main.c @@ -656,7 +656,7 @@ asmlinkage __visible void __init start_kernel(void) key_init(); security_init(); dbg_late_init(); - vfs_caches_init(totalram_pages); + vfs_caches_init(); signals_init(); /* rootfs populating might need page-writeback */ page_writeback_init(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 322628278ae4..cb61f44eb3fc 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1201,6 +1201,9 @@ void __init page_alloc_init_late(void) /* Block until all are initialised */ wait_for_completion(&pgdat_init_all_done_comp); + + /* Reinit limits that are based on free pages after the kernel is up */ + files_maxfiles_init(); } #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ -- cgit v1.2.3 From f4c18e6f7b5bbb5b528b3334115806b0d76f50f9 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 6 Aug 2015 15:47:08 -0700 Subject: mm: check __PG_HWPOISON separately from PAGE_FLAGS_CHECK_AT_* The race condition addressed in commit add05cecef80 ("mm: soft-offline: don't free target page in successful page migration") was not closed completely, because that can happen not only for soft-offline, but also for hard-offline. Consider that a slab page is about to be freed into buddy pool, and then an uncorrected memory error hits the page just after entering __free_one_page(), then VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP) is triggered, despite the fact that it's not necessary because the data on the affected page is not consumed. To solve it, this patch drops __PG_HWPOISON from page flag checks at allocation/free time. I think it's justified because __PG_HWPOISON flags is defined to prevent the page from being reused, and setting it outside the page's alloc-free cycle is a designed behavior (not a bug.) For recent months, I was annoyed about BUG_ON when soft-offlined page remains on lru cache list for a while, which is avoided by calling put_page() instead of putback_lru_page() in page migration's success path. This means that this patch reverts a major change from commit add05cecef80 about the new refcounting rule of soft-offlined pages, so "reuse window" revives. This will be closed by a subsequent patch. Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Dean Nelson Cc: Tony Luck Cc: "Kirill A. Shutemov" Cc: Hugh Dickins Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 10 +++++++--- mm/huge_memory.c | 7 +------ mm/migrate.c | 5 ++++- mm/page_alloc.c | 4 ++++ 4 files changed, 16 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index f34e040b34e9..41c93844fb1d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -631,15 +631,19 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) 1 << PG_private | 1 << PG_private_2 | \ 1 << PG_writeback | 1 << PG_reserved | \ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ - 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \ + 1 << PG_unevictable | __PG_MLOCKED | \ __PG_COMPOUND_LOCK) /* * Flags checked when a page is prepped for return by the page allocator. - * Pages being prepped should not have any flags set. It they are set, + * Pages being prepped should not have these flags set. It they are set, * there has been a kernel bug or struct page corruption. + * + * __PG_HWPOISON is exceptional because it needs to be kept beyond page's + * alloc-free cycle to prevent from reusing the page. */ -#define PAGE_FLAGS_CHECK_AT_PREP ((1 << NR_PAGEFLAGS) - 1) +#define PAGE_FLAGS_CHECK_AT_PREP \ + (((1 << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON) #define PAGE_FLAGS_PRIVATE \ (1 << PG_private | 1 << PG_private_2) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c107094f79ba..097c7a4bfbd9 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1676,12 +1676,7 @@ static void __split_huge_page_refcount(struct page *page, /* after clearing PageTail the gup refcount can be released */ smp_mb__after_atomic(); - /* - * retain hwpoison flag of the poisoned tail page: - * fix for the unsuitable process killed on Guest Machine(KVM) - * by the memory-failure. - */ - page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON; + page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; page_tail->flags |= (page->flags & ((1L << PG_referenced) | (1L << PG_swapbacked) | diff --git a/mm/migrate.c b/mm/migrate.c index ee401e4e5ef1..f2415be7d93b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -950,7 +950,10 @@ out: list_del(&page->lru); dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); - if (reason != MR_MEMORY_FAILURE) + /* Soft-offlined page shouldn't go through lru cache list */ + if (reason == MR_MEMORY_FAILURE) + put_page(page); + else putback_lru_page(page); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cb61f44eb3fc..beda41710802 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1296,6 +1296,10 @@ static inline int check_new_page(struct page *page) bad_reason = "non-NULL mapping"; if (unlikely(atomic_read(&page->_count) != 0)) bad_reason = "nonzero _count"; + if (unlikely(page->flags & __PG_HWPOISON)) { + bad_reason = "HWPoisoned (hardware-corrupted)"; + bad_flags = __PG_HWPOISON; + } if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) { bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set"; bad_flags = PAGE_FLAGS_CHECK_AT_PREP; -- cgit v1.2.3 From 7a76a021cd5a292be875fbc616daf03eab1e6996 Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Fri, 7 Aug 2015 09:32:21 -0700 Subject: net-timestamp: Update skb_complete_tx_timestamp comment After "62bccb8 net-timestamp: Make the clone operation stand-alone from phy timestamping" the hwtstamps parameter of skb_complete_tx_timestamp() may no longer be NULL. Signed-off-by: Benjamin Poirier Cc: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d6cdd6e87d53..22b6d9ca1654 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2884,11 +2884,11 @@ static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) * * PHY drivers may accept clones of transmitted packets for * timestamping via their phy_driver.txtstamp method. These drivers - * must call this function to return the skb back to the stack, with - * or without a timestamp. + * must call this function to return the skb back to the stack with a + * timestamp. * * @skb: clone of the the original outgoing packet - * @hwtstamps: hardware time stamps, may be NULL if not available + * @hwtstamps: hardware time stamps * */ void skb_complete_tx_timestamp(struct sk_buff *skb, -- cgit v1.2.3 From b7560de198222994374c1340a389f12d5efb244a Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Fri, 14 Aug 2015 15:20:26 +0300 Subject: genirq: Introduce irq_chip_set_type_parent() helper This helper is required for irq chips which do not implement a irq_set_type callback and need to call down the irq domain hierarchy for the actual trigger type change. This helper is required to fix further wreckage caused by the conversion of TI OMAP to hierarchical irq domains and therefor tagged for stable. [ tglx: Massaged changelog ] Signed-off-by: Grygorii Strashko Cc: Sudeep Holla Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: stable@vger.kernel.org # 4.1 Link: http://lkml.kernel.org/r/1439554830-19502-3-git-send-email-grygorii.strashko@ti.com Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 1 + kernel/irq/chip.c | 17 +++++++++++++++++ 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index 92188b0225bb..51744bcf74ee 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -484,6 +484,7 @@ extern int irq_chip_set_affinity_parent(struct irq_data *data, extern int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on); extern int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info); +extern int irq_chip_set_type_parent(struct irq_data *data, unsigned int type); #endif /* Handling of unhandled and spurious interrupts: */ diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 6de638bccba7..ae216824e8ca 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -984,6 +984,23 @@ int irq_chip_set_affinity_parent(struct irq_data *data, return -ENOSYS; } +/** + * irq_chip_set_type_parent - Set IRQ type on the parent interrupt + * @data: Pointer to interrupt specific data + * @type: IRQ_TYPE_{LEVEL,EDGE}_* value - see include/linux/irq.h + * + * Conditional, as the underlying parent chip might not implement it. + */ +int irq_chip_set_type_parent(struct irq_data *data, unsigned int type) +{ + data = data->parent_data; + + if (data->chip->irq_set_type) + return data->chip->irq_set_type(data, type); + + return -ENOSYS; +} + /** * irq_chip_retrigger_hierarchy - Retrigger an interrupt in hardware * @data: Pointer to interrupt specific data -- cgit v1.2.3 From c5f58f2d700ef484fc2fbaa9c624c6076109f989 Mon Sep 17 00:00:00 2001 From: Markus Pargmann Date: Fri, 21 Aug 2015 10:26:40 +0200 Subject: regmap: Add missing comments about struct regmap_bus There are some fields of this struct undocumented or old. This patch updates the missing comments. Signed-off-by: Markus Pargmann Signed-off-by: Mark Brown --- include/linux/regmap.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 59c55ea0f0b5..73fc34d0c4c2 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -296,8 +296,12 @@ typedef void (*regmap_hw_free_context)(void *context); * if not implemented on a given device. * @async_write: Write operation which completes asynchronously, optional and * must serialise with respect to non-async I/O. + * @reg_write: Write a single register value to the given register address. This + * write operation has to complete when returning from the function. * @read: Read operation. Data is returned in the buffer used to transmit * data. + * @reg_read: Read a single register value from a given register address. + * @free_context: Free context. * @async_alloc: Allocate a regmap_async() structure. * @read_flag_mask: Mask to be set in the top byte of the register when doing * a read. @@ -307,7 +311,6 @@ typedef void (*regmap_hw_free_context)(void *context); * @val_format_endian_default: Default endianness for formatted register * values. Used when the regmap_config specifies DEFAULT. If this is * DEFAULT, BIG is assumed. - * @async_size: Size of struct used for async work. */ struct regmap_bus { bool fast_io; -- cgit v1.2.3 From 2f064f3485cd29633ad1b3cfb00cc519509a3d72 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 21 Aug 2015 14:11:51 -0700 Subject: mm: make page pfmemalloc check more robust Commit c48a11c7ad26 ("netvm: propagate page->pfmemalloc to skb") added checks for page->pfmemalloc to __skb_fill_page_desc(): if (page->pfmemalloc && !page->mapping) skb->pfmemalloc = true; It assumes page->mapping == NULL implies that page->pfmemalloc can be trusted. However, __delete_from_page_cache() can set set page->mapping to NULL and leave page->index value alone. Due to being in union, a non-zero page->index will be interpreted as true page->pfmemalloc. So the assumption is invalid if the networking code can see such a page. And it seems it can. We have encountered this with a NFS over loopback setup when such a page is attached to a new skbuf. There is no copying going on in this case so the page confuses __skb_fill_page_desc which interprets the index as pfmemalloc flag and the network stack drops packets that have been allocated using the reserves unless they are to be queued on sockets handling the swapping which is the case here and that leads to hangs when the nfs client waits for a response from the server which has been dropped and thus never arrive. The struct page is already heavily packed so rather than finding another hole to put it in, let's do a trick instead. We can reuse the index again but define it to an impossible value (-1UL). This is the page index so it should never see the value that large. Replace all direct users of page->pfmemalloc by page_is_pfmemalloc which will hide this nastiness from unspoiled eyes. The information will get lost if somebody wants to use page->index obviously but that was the case before and the original code expected that the information should be persisted somewhere else if that is really needed (e.g. what SLAB and SLUB do). [akpm@linux-foundation.org: fix blooper in slub] Fixes: c48a11c7ad26 ("netvm: propagate page->pfmemalloc to skb") Signed-off-by: Michal Hocko Debugged-by: Vlastimil Babka Debugged-by: Jiri Bohac Cc: Eric Dumazet Cc: David Miller Acked-by: Mel Gorman Cc: [3.6+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/net/ethernet/intel/fm10k/fm10k_main.c | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 2 +- include/linux/mm.h | 28 +++++++++++++++++++++++ include/linux/mm_types.h | 9 -------- include/linux/skbuff.h | 14 ++++-------- mm/page_alloc.c | 9 +++++--- mm/slab.c | 4 ++-- mm/slub.c | 2 +- net/core/skbuff.c | 2 +- 11 files changed, 47 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 982fdcdc795b..b5b2925103ec 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -216,7 +216,7 @@ static void fm10k_reuse_rx_page(struct fm10k_ring *rx_ring, static inline bool fm10k_page_is_reserved(struct page *page) { - return (page_to_nid(page) != numa_mem_id()) || page->pfmemalloc; + return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); } static bool fm10k_can_reuse_rx_page(struct fm10k_rx_buffer *rx_buffer, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 2f70a9b152bd..830466c49987 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6566,7 +6566,7 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring, static inline bool igb_page_is_reserved(struct page *page) { - return (page_to_nid(page) != numa_mem_id()) || page->pfmemalloc; + return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); } static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 9aa6104e34ea..ae21e0b06c3a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1832,7 +1832,7 @@ static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring, static inline bool ixgbe_page_is_reserved(struct page *page) { - return (page_to_nid(page) != numa_mem_id()) || page->pfmemalloc; + return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); } /** diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index e71cdde9cb01..1d7b00b038a2 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -765,7 +765,7 @@ static void ixgbevf_reuse_rx_page(struct ixgbevf_ring *rx_ring, static inline bool ixgbevf_page_is_reserved(struct page *page) { - return (page_to_nid(page) != numa_mem_id()) || page->pfmemalloc; + return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); } /** diff --git a/include/linux/mm.h b/include/linux/mm.h index 2e872f92dbac..bf6f117fcf4d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1002,6 +1002,34 @@ static inline int page_mapped(struct page *page) return atomic_read(&(page)->_mapcount) >= 0; } +/* + * Return true only if the page has been allocated with + * ALLOC_NO_WATERMARKS and the low watermark was not + * met implying that the system is under some pressure. + */ +static inline bool page_is_pfmemalloc(struct page *page) +{ + /* + * Page index cannot be this large so this must be + * a pfmemalloc page. + */ + return page->index == -1UL; +} + +/* + * Only to be called by the page allocator on a freshly allocated + * page. + */ +static inline void set_page_pfmemalloc(struct page *page) +{ + page->index = -1UL; +} + +static inline void clear_page_pfmemalloc(struct page *page) +{ + page->index = 0; +} + /* * Different kinds of faults, as returned by handle_mm_fault(). * Used to decide whether a process gets delivered SIGBUS or diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0038ac7466fd..15549578d559 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -63,15 +63,6 @@ struct page { union { pgoff_t index; /* Our offset within mapping. */ void *freelist; /* sl[aou]b first free object */ - bool pfmemalloc; /* If set by the page allocator, - * ALLOC_NO_WATERMARKS was set - * and the low watermark was not - * met implying that the system - * is under some pressure. The - * caller should try ensure - * this page is only used to - * free other pages. - */ }; union { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 22b6d9ca1654..9b88536487e6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1602,20 +1602,16 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; /* - * Propagate page->pfmemalloc to the skb if we can. The problem is - * that not all callers have unique ownership of the page. If - * pfmemalloc is set, we check the mapping as a mapping implies - * page->index is set (index and pfmemalloc share space). - * If it's a valid mapping, we cannot use page->pfmemalloc but we - * do not lose pfmemalloc information as the pages would not be - * allocated using __GFP_MEMALLOC. + * Propagate page pfmemalloc to the skb if we can. The problem is + * that not all callers have unique ownership of the page but rely + * on page_is_pfmemalloc doing the right thing(tm). */ frag->page.p = page; frag->page_offset = off; skb_frag_size_set(frag, size); page = compound_head(page); - if (page->pfmemalloc && !page->mapping) + if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } @@ -2263,7 +2259,7 @@ static inline struct page *dev_alloc_page(void) static inline void skb_propagate_pfmemalloc(struct page *page, struct sk_buff *skb) { - if (page && page->pfmemalloc) + if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index df959b7d6085..5b5240b7f642 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1343,12 +1343,15 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, set_page_owner(page, order, gfp_flags); /* - * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was necessary to + * page is set pfmemalloc when ALLOC_NO_WATERMARKS was necessary to * allocate the page. The expectation is that the caller is taking * steps that will free more memory. The caller should avoid the page * being used for !PFMEMALLOC purposes. */ - page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS); + if (alloc_flags & ALLOC_NO_WATERMARKS) + set_page_pfmemalloc(page); + else + clear_page_pfmemalloc(page); return 0; } @@ -3345,7 +3348,7 @@ refill: atomic_add(size - 1, &page->_count); /* reset page count bias and offset to start of new frag */ - nc->pfmemalloc = page->pfmemalloc; + nc->pfmemalloc = page_is_pfmemalloc(page); nc->pagecnt_bias = size; nc->offset = size; } diff --git a/mm/slab.c b/mm/slab.c index 200e22412a16..bbd0b47dc6a9 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1603,7 +1603,7 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, } /* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */ - if (unlikely(page->pfmemalloc)) + if (page_is_pfmemalloc(page)) pfmemalloc_active = true; nr_pages = (1 << cachep->gfporder); @@ -1614,7 +1614,7 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, add_zone_page_state(page_zone(page), NR_SLAB_UNRECLAIMABLE, nr_pages); __SetPageSlab(page); - if (page->pfmemalloc) + if (page_is_pfmemalloc(page)) SetPageSlabPfmemalloc(page); if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) { diff --git a/mm/slub.c b/mm/slub.c index 816df0016555..f68c0e50f3c0 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1427,7 +1427,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) inc_slabs_node(s, page_to_nid(page), page->objects); page->slab_cache = s; __SetPageSlab(page); - if (page->pfmemalloc) + if (page_is_pfmemalloc(page)) SetPageSlabPfmemalloc(page); start = page_address(page); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index bf9a5d93c2d1..7b84330e5d30 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -340,7 +340,7 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) if (skb && frag_size) { skb->head_frag = 1; - if (virt_to_head_page(data)->pfmemalloc) + if (page_is_pfmemalloc(virt_to_head_page(data))) skb->pfmemalloc = 1; } return skb; -- cgit v1.2.3 From adaac459759db4a1fd35baddbe47bac700095496 Mon Sep 17 00:00:00 2001 From: Markus Pargmann Date: Sun, 30 Aug 2015 09:33:53 +0200 Subject: regmap: Introduce max_raw_read/write for regmap_bulk_read/write There are some buses which have a limit on the maximum number of bytes that can be send/received. An example for this is I2C_FUNC_SMBUS_I2C_BLOCK which does not support any reads/writes of more than 32 bytes. The regmap_bulk operations should still be able to utilize the full 32 bytes in this case. Signed-off-by: Markus Pargmann Signed-off-by: Mark Brown --- drivers/base/regmap/internal.h | 4 ++ drivers/base/regmap/regmap.c | 85 ++++++++++++++++++++++++++++++++++-------- include/linux/regmap.h | 4 ++ 3 files changed, 78 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index d744ae3926dd..fc554e357c5d 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -146,6 +146,10 @@ struct regmap { /* if set, the device supports multi write mode */ bool can_multi_write; + /* if set, raw reads/writes are limited to this size */ + size_t max_raw_read; + size_t max_raw_write; + struct rb_root range_tree; void *selector_work_buf; /* Scratch buffer used for selector */ }; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index a6b6f7ee87ee..7cbe42680877 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -579,6 +579,8 @@ struct regmap *regmap_init(struct device *dev, map->use_single_read = config->use_single_rw || !bus || !bus->read; map->use_single_write = config->use_single_rw || !bus || !bus->write; map->can_multi_write = config->can_multi_write && bus && bus->write; + map->max_raw_read = bus->max_raw_read; + map->max_raw_write = bus->max_raw_write; map->dev = dev; map->bus = bus; map->bus_context = bus_context; @@ -1674,6 +1676,7 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, { int ret = 0, i; size_t val_bytes = map->format.val_bytes; + size_t total_size = val_bytes * val_count; if (map->bus && !map->format.parse_inplace) return -EINVAL; @@ -1722,16 +1725,37 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, } out: map->unlock(map->lock_arg); - } else if (map->use_single_write) { + } else if (map->use_single_write || + (map->max_raw_write && map->max_raw_write < total_size)) { + int chunk_stride = map->reg_stride; + size_t chunk_size = val_bytes; + size_t chunk_count = val_count; + + if (!map->use_single_write) { + chunk_size = map->max_raw_write; + if (chunk_size % val_bytes) + chunk_size -= chunk_size % val_bytes; + chunk_count = total_size / chunk_size; + chunk_stride *= chunk_size / val_bytes; + } + map->lock(map->lock_arg); - for (i = 0; i < val_count; i++) { + /* Write as many bytes as possible with chunk_size */ + for (i = 0; i < chunk_count; i++) { ret = _regmap_raw_write(map, - reg + (i * map->reg_stride), - val + (i * val_bytes), - val_bytes); + reg + (i * chunk_stride), + val + (i * chunk_size), + chunk_size); if (ret) break; } + + /* Write remaining bytes */ + if (!ret && chunk_size * i < total_size) { + ret = _regmap_raw_write(map, reg + (i * chunk_stride), + val + (i * chunk_size), + total_size - i * chunk_size); + } map->unlock(map->lock_arg); } else { void *wval; @@ -2319,20 +2343,51 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, * Some devices does not support bulk read, for * them we have a series of single read operations. */ - if (map->use_single_read) { - for (i = 0; i < val_count; i++) { - ret = regmap_raw_read(map, - reg + (i * map->reg_stride), - val + (i * val_bytes), - val_bytes); - if (ret != 0) - return ret; - } - } else { + size_t total_size = val_bytes * val_count; + + if (!map->use_single_read && + (!map->max_raw_read || map->max_raw_read > total_size)) { ret = regmap_raw_read(map, reg, val, val_bytes * val_count); if (ret != 0) return ret; + } else { + /* + * Some devices do not support bulk read or do not + * support large bulk reads, for them we have a series + * of read operations. + */ + int chunk_stride = map->reg_stride; + size_t chunk_size = val_bytes; + size_t chunk_count = val_count; + + if (!map->use_single_read) { + chunk_size = map->max_raw_read; + if (chunk_size % val_bytes) + chunk_size -= chunk_size % val_bytes; + chunk_count = total_size / chunk_size; + chunk_stride *= chunk_size / val_bytes; + } + + /* Read bytes that fit into a multiple of chunk_size */ + for (i = 0; i < chunk_count; i++) { + ret = regmap_raw_read(map, + reg + (i * chunk_stride), + val + (i * chunk_size), + chunk_size); + if (ret != 0) + return ret; + } + + /* Read remaining bytes */ + if (chunk_size * i < total_size) { + ret = regmap_raw_read(map, + reg + (i * chunk_stride), + val + (i * chunk_size), + total_size - i * chunk_size); + if (ret != 0) + return ret; + } } for (i = 0; i < val_count * val_bytes; i += val_bytes) diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 73fc34d0c4c2..327b8f291d3f 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -311,6 +311,8 @@ typedef void (*regmap_hw_free_context)(void *context); * @val_format_endian_default: Default endianness for formatted register * values. Used when the regmap_config specifies DEFAULT. If this is * DEFAULT, BIG is assumed. + * @max_raw_read: Max raw read size that can be used on the bus. + * @max_raw_write: Max raw write size that can be used on the bus. */ struct regmap_bus { bool fast_io; @@ -325,6 +327,8 @@ struct regmap_bus { u8 read_flag_mask; enum regmap_endian reg_format_endian_default; enum regmap_endian val_format_endian_default; + size_t max_raw_read; + size_t max_raw_write; }; struct regmap *regmap_init(struct device *dev, -- cgit v1.2.3 From f50c9eb4e9304cf555206c93152f580c0e7213b2 Mon Sep 17 00:00:00 2001 From: Markus Pargmann Date: Sun, 30 Aug 2015 09:33:54 +0200 Subject: regmap: regmap max_raw_read/write getter functions Add functions to access the maximum size we can read/write using regmap_raw_read/write(). This helps drivers that need to know how much they can write with the raw functions without problems. There are some devices (e.g. bmc150) that have fifos as registers which need to be read in specific chunks otherwise samples are dropped. Signed-off-by: Markus Pargmann Signed-off-by: Mark Brown --- drivers/base/regmap/regmap.c | 22 ++++++++++++++++++++++ include/linux/regmap.h | 2 ++ 2 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 7cbe42680877..47210101e308 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1393,6 +1393,28 @@ bool regmap_can_raw_write(struct regmap *map) } EXPORT_SYMBOL_GPL(regmap_can_raw_write); +/** + * regmap_get_raw_read_max - Get the maximum size we can read + * + * @map: Map to check. + */ +size_t regmap_get_raw_read_max(struct regmap *map) +{ + return map->max_raw_read; +} +EXPORT_SYMBOL_GPL(regmap_get_raw_read_max); + +/** + * regmap_get_raw_write_max - Get the maximum size we can read + * + * @map: Map to check. + */ +size_t regmap_get_raw_write_max(struct regmap *map) +{ + return map->max_raw_write; +} +EXPORT_SYMBOL_GPL(regmap_get_raw_write_max); + static int _regmap_bus_formatted_write(void *context, unsigned int reg, unsigned int val) { diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 327b8f291d3f..6724d0e3819e 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -444,6 +444,8 @@ int regmap_get_max_register(struct regmap *map); int regmap_get_reg_stride(struct regmap *map); int regmap_async_complete(struct regmap *map); bool regmap_can_raw_write(struct regmap *map); +size_t regmap_get_raw_read_max(struct regmap *map); +size_t regmap_get_raw_write_max(struct regmap *map); int regcache_sync(struct regmap *map); int regcache_sync_region(struct regmap *map, unsigned int min, -- cgit v1.2.3